Merge branch 'for-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next
Johan Hedberg says:
====================
pull request: bluetooth-next 2020-01-26
Here's (probably) the last bluetooth-next pull request for the 5.6 kernel.
- Initial pieces of Bluetooth 5.2 Isochronous Channels support
- mgmt: Various cleanups and a new Set Blocked Keys command
- btusb: Added support for 04ca:3021 QCA_ROME device
- hci_qca: Multiple fixes & cleanups
- hci_bcm: Fixes & improved device tree support
- Fixed attempts to create duplicate debugfs entries
Please let me know if there are any issues pulling. Thanks.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/.mailmap b/.mailmap
index a7bc8ca..d9d5c80 100644
--- a/.mailmap
+++ b/.mailmap
@@ -99,6 +99,7 @@
Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@google.com>
Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@motorola.com>
Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk.kim@samsung.com>
+Jakub Kicinski <kuba@kernel.org> <jakub.kicinski@netronome.com>
James Bottomley <jejb@mulgrave.(none)>
James Bottomley <jejb@titanic.il.steeleye.com>
James E Wilson <wilson@specifix.com>
diff --git a/Documentation/ABI/stable/sysfs-driver-mlxreg-io b/Documentation/ABI/stable/sysfs-driver-mlxreg-io
index 8ca4984..05601a9 100644
--- a/Documentation/ABI/stable/sysfs-driver-mlxreg-io
+++ b/Documentation/ABI/stable/sysfs-driver-mlxreg-io
@@ -29,13 +29,13 @@
The files are read only.
-What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/jtag_enable
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/cpld3_version
Date: November 2018
KernelVersion: 5.0
Contact: Vadim Pasternak <vadimpmellanox.com>
Description: These files show with which CPLD versions have been burned
- on LED board.
+ on LED or Gearbox board.
The files are read only.
@@ -121,6 +121,15 @@
The files are read only.
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/cpld4_version
+Date: November 2018
+KernelVersion: 5.0
+Contact: Vadim Pasternak <vadimpmellanox.com>
+Description: These files show with which CPLD versions have been burned
+ on LED board.
+
+ The files are read only.
+
Date: June 2019
KernelVersion: 5.3
Contact: Vadim Pasternak <vadimpmellanox.com>
diff --git a/Documentation/ABI/testing/sysfs-bus-mdio b/Documentation/ABI/testing/sysfs-bus-mdio
new file mode 100644
index 0000000..da86efc
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-mdio
@@ -0,0 +1,63 @@
+What: /sys/bus/mdio_bus/devices/.../statistics/
+Date: January 2020
+KernelVersion: 5.6
+Contact: netdev@vger.kernel.org
+Description:
+ This folder contains statistics about global and per
+ MDIO bus address statistics.
+
+What: /sys/bus/mdio_bus/devices/.../statistics/transfers
+Date: January 2020
+KernelVersion: 5.6
+Contact: netdev@vger.kernel.org
+Description:
+ Total number of transfers for this MDIO bus.
+
+What: /sys/bus/mdio_bus/devices/.../statistics/errors
+Date: January 2020
+KernelVersion: 5.6
+Contact: netdev@vger.kernel.org
+Description:
+ Total number of transfer errors for this MDIO bus.
+
+What: /sys/bus/mdio_bus/devices/.../statistics/writes
+Date: January 2020
+KernelVersion: 5.6
+Contact: netdev@vger.kernel.org
+Description:
+ Total number of write transactions for this MDIO bus.
+
+What: /sys/bus/mdio_bus/devices/.../statistics/reads
+Date: January 2020
+KernelVersion: 5.6
+Contact: netdev@vger.kernel.org
+Description:
+ Total number of read transactions for this MDIO bus.
+
+What: /sys/bus/mdio_bus/devices/.../statistics/transfers_<addr>
+Date: January 2020
+KernelVersion: 5.6
+Contact: netdev@vger.kernel.org
+Description:
+ Total number of transfers for this MDIO bus address.
+
+What: /sys/bus/mdio_bus/devices/.../statistics/errors_<addr>
+Date: January 2020
+KernelVersion: 5.6
+Contact: netdev@vger.kernel.org
+Description:
+ Total number of transfer errors for this MDIO bus address.
+
+What: /sys/bus/mdio_bus/devices/.../statistics/writes_<addr>
+Date: January 2020
+KernelVersion: 5.6
+Contact: netdev@vger.kernel.org
+Description:
+ Total number of write transactions for this MDIO bus address.
+
+What: /sys/bus/mdio_bus/devices/.../statistics/reads_<addr>
+Date: January 2020
+KernelVersion: 5.6
+Contact: netdev@vger.kernel.org
+Description:
+ Total number of read transactions for this MDIO bus address.
diff --git a/Documentation/admin-guide/devices.txt b/Documentation/admin-guide/devices.txt
index 1c5d228..2a97aae 100644
--- a/Documentation/admin-guide/devices.txt
+++ b/Documentation/admin-guide/devices.txt
@@ -319,7 +319,7 @@
182 = /dev/perfctr Performance-monitoring counters
183 = /dev/hwrng Generic random number generator
184 = /dev/cpu/microcode CPU microcode update interface
- 186 = /dev/atomicps Atomic shapshot of process state data
+ 186 = /dev/atomicps Atomic snapshot of process state data
187 = /dev/irnet IrNET device
188 = /dev/smbusbios SMBus BIOS
189 = /dev/ussp_ctl User space serial port control
diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst
index fcedc53..640934b 100644
--- a/Documentation/core-api/xarray.rst
+++ b/Documentation/core-api/xarray.rst
@@ -25,10 +25,6 @@
``ULONG_MAX`` then the XArray is not the data type for you. The most
important user of the XArray is the page cache.
-Each non-``NULL`` entry in the array has three bits associated with
-it called marks. Each mark may be set or cleared independently of
-the others. You can iterate over entries which are marked.
-
Normal pointers may be stored in the XArray directly. They must be 4-byte
aligned, which is true for any pointer returned from kmalloc() and
alloc_page(). It isn't true for arbitrary user-space pointers,
@@ -41,12 +37,11 @@
a value entry by calling xa_is_value(), and convert it back to
an integer by calling xa_to_value().
-Some users want to store tagged pointers instead of using the marks
-described above. They can call xa_tag_pointer() to create an
-entry with a tag, xa_untag_pointer() to turn a tagged entry
-back into an untagged pointer and xa_pointer_tag() to retrieve
-the tag of an entry. Tagged pointers use the same bits that are used
-to distinguish value entries from normal pointers, so each user must
+Some users want to tag the pointers they store in the XArray. You can
+call xa_tag_pointer() to create an entry with a tag, xa_untag_pointer()
+to turn a tagged entry back into an untagged pointer and xa_pointer_tag()
+to retrieve the tag of an entry. Tagged pointers use the same bits that
+are used to distinguish value entries from normal pointers, so you must
decide whether they want to store value entries or tagged pointers in
any particular XArray.
@@ -56,10 +51,9 @@
An unusual feature of the XArray is the ability to create entries which
occupy a range of indices. Once stored to, looking up any index in
the range will return the same entry as looking up any other index in
-the range. Setting a mark on one index will set it on all of them.
-Storing to any index will store to all of them. Multi-index entries can
-be explicitly split into smaller entries, or storing ``NULL`` into any
-entry will cause the XArray to forget about the range.
+the range. Storing to any index will store to all of them. Multi-index
+entries can be explicitly split into smaller entries, or storing ``NULL``
+into any entry will cause the XArray to forget about the range.
Normal API
==========
@@ -87,17 +81,11 @@
at that index is ``NULL``, you can use xa_insert() which
returns ``-EBUSY`` if the entry is not empty.
-You can enquire whether a mark is set on an entry by using
-xa_get_mark(). If the entry is not ``NULL``, you can set a mark
-on it by using xa_set_mark() and remove the mark from an entry by
-calling xa_clear_mark(). You can ask whether any entry in the
-XArray has a particular mark set by calling xa_marked().
-
You can copy entries out of the XArray into a plain array by calling
-xa_extract(). Or you can iterate over the present entries in
-the XArray by calling xa_for_each(). You may prefer to use
-xa_find() or xa_find_after() to move to the next present
-entry in the XArray.
+xa_extract(). Or you can iterate over the present entries in the XArray
+by calling xa_for_each(), xa_for_each_start() or xa_for_each_range().
+You may prefer to use xa_find() or xa_find_after() to move to the next
+present entry in the XArray.
Calling xa_store_range() stores the same entry in a range
of indices. If you do this, some of the other operations will behave
@@ -124,6 +112,31 @@
to free the entries first. You can do this by iterating over all present
entries in the XArray using the xa_for_each() iterator.
+Search Marks
+------------
+
+Each entry in the array has three bits associated with it called marks.
+Each mark may be set or cleared independently of the others. You can
+iterate over marked entries by using the xa_for_each_marked() iterator.
+
+You can enquire whether a mark is set on an entry by using
+xa_get_mark(). If the entry is not ``NULL``, you can set a mark on it
+by using xa_set_mark() and remove the mark from an entry by calling
+xa_clear_mark(). You can ask whether any entry in the XArray has a
+particular mark set by calling xa_marked(). Erasing an entry from the
+XArray causes all marks associated with that entry to be cleared.
+
+Setting or clearing a mark on any index of a multi-index entry will
+affect all indices covered by that entry. Querying the mark on any
+index will return the same result.
+
+There is no way to iterate over entries which are not marked; the data
+structure does not allow this to be implemented efficiently. There are
+not currently iterators to search for logical combinations of bits (eg
+iterate over all entries which have both ``XA_MARK_1`` and ``XA_MARK_2``
+set, or iterate over all entries which have ``XA_MARK_0`` or ``XA_MARK_2``
+set). It would be possible to add these if a user arises.
+
Allocating XArrays
------------------
@@ -180,6 +193,8 @@
Takes RCU read lock:
* xa_load()
* xa_for_each()
+ * xa_for_each_start()
+ * xa_for_each_range()
* xa_find()
* xa_find_after()
* xa_extract()
@@ -419,10 +434,9 @@
then it is good manners to pause the iteration and reenable interrupts
every ``XA_CHECK_SCHED`` entries.
-The xas_get_mark(), xas_set_mark() and
-xas_clear_mark() functions require the xa_state cursor to have
-been moved to the appropriate location in the xarray; they will do
-nothing if you have called xas_pause() or xas_set()
+The xas_get_mark(), xas_set_mark() and xas_clear_mark() functions require
+the xa_state cursor to have been moved to the appropriate location in the
+XArray; they will do nothing if you have called xas_pause() or xas_set()
immediately before.
You can call xas_set_update() to have a callback function
diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst
index 36890b0..1c4e182 100644
--- a/Documentation/dev-tools/kcov.rst
+++ b/Documentation/dev-tools/kcov.rst
@@ -251,11 +251,11 @@
.. code-block:: c
struct kcov_remote_arg {
- unsigned trace_mode;
- unsigned area_size;
- unsigned num_handles;
- uint64_t common_handle;
- uint64_t handles[0];
+ __u32 trace_mode;
+ __u32 area_size;
+ __u32 num_handles;
+ __aligned_u64 common_handle;
+ __aligned_u64 handles[0];
};
#define KCOV_INIT_TRACE _IOR('c', 1, unsigned long)
diff --git a/Documentation/devicetree/bindings/i2c/i2c-at91.txt b/Documentation/devicetree/bindings/i2c/i2c-at91.txt
index 2210f43..8347b1e 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-at91.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-at91.txt
@@ -18,8 +18,10 @@
- dma-names: should contain "tx" and "rx".
- atmel,fifo-size: maximum number of data the RX and TX FIFOs can store for FIFO
capable I2C controllers.
-- i2c-sda-hold-time-ns: TWD hold time, only available for "atmel,sama5d4-i2c"
- and "atmel,sama5d2-i2c".
+- i2c-sda-hold-time-ns: TWD hold time, only available for:
+ "atmel,sama5d4-i2c",
+ "atmel,sama5d2-i2c",
+ "microchip,sam9x60-i2c".
- Child nodes conforming to i2c bus binding
Examples :
diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt
index 299c0dc..250f8d8 100644
--- a/Documentation/devicetree/bindings/net/fsl-fman.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fman.txt
@@ -403,6 +403,19 @@
The settings and programming routines for internal/external
MDIO are different. Must be included for internal MDIO.
+- fsl,erratum-a011043
+ Usage: optional
+ Value type: <boolean>
+ Definition: Indicates the presence of the A011043 erratum
+ describing that the MDIO_CFG[MDIO_RD_ER] bit may be falsely
+ set when reading internal PCS registers. MDIO reads to
+ internal PCS registers may result in having the
+ MDIO_CFG[MDIO_RD_ER] bit set, even when there is no error and
+ read data (MDIO_DATA[MDIO_DATA]) is correct.
+ Software may get false read error when reading internal
+ PCS registers through MDIO. As a workaround, all internal
+ MDIO accesses should ignore the MDIO_CFG[MDIO_RD_ER] bit.
+
For internal PHY device on internal mdio bus, a PHY node should be created.
See the definition of the PHY node in booting-without-of.txt for an
example of how to define a PHY (Internal PHY has no interrupt line).
diff --git a/Documentation/devicetree/bindings/spi/spi-controller.yaml b/Documentation/devicetree/bindings/spi/spi-controller.yaml
index 7323392..1e0ca6c 100644
--- a/Documentation/devicetree/bindings/spi/spi-controller.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-controller.yaml
@@ -111,7 +111,7 @@
spi-rx-bus-width:
allOf:
- $ref: /schemas/types.yaml#/definitions/uint32
- - enum: [ 1, 2, 4 ]
+ - enum: [ 1, 2, 4, 8 ]
- default: 1
description:
Bus width to the SPI bus used for MISO.
@@ -123,7 +123,7 @@
spi-tx-bus-width:
allOf:
- $ref: /schemas/types.yaml#/definitions/uint32
- - enum: [ 1, 2, 4 ]
+ - enum: [ 1, 2, 4, 8 ]
- default: 1
description:
Bus width to the SPI bus used for MOSI.
diff --git a/Documentation/features/debug/gcov-profile-all/arch-support.txt b/Documentation/features/debug/gcov-profile-all/arch-support.txt
index 059d58a..6fb2b06 100644
--- a/Documentation/features/debug/gcov-profile-all/arch-support.txt
+++ b/Documentation/features/debug/gcov-profile-all/arch-support.txt
@@ -23,7 +23,7 @@
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
- | riscv: | TODO |
+ | riscv: | ok |
| s390: | ok |
| sh: | ok |
| sparc: | TODO |
diff --git a/Documentation/media/v4l-drivers/meye.rst b/Documentation/media/v4l-drivers/meye.rst
index a572996..dc57a6a 100644
--- a/Documentation/media/v4l-drivers/meye.rst
+++ b/Documentation/media/v4l-drivers/meye.rst
@@ -95,7 +95,7 @@
Besides the video4linux interface, the driver has a private interface
for accessing the Motion Eye extended parameters (camera sharpness,
-agc, video framerate), the shapshot and the MJPEG capture facilities.
+agc, video framerate), the snapshot and the MJPEG capture facilities.
This interface consists of several ioctls (prototypes and structures
can be found in include/linux/meye.h):
diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index c1f7f75..4bc6ff2 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -25,6 +25,7 @@
mellanox/mlx5
netronome/nfp
pensando/ionic
+ stmicro/stmmac
.. only:: subproject and html
diff --git a/Documentation/networking/device_drivers/microsoft/netvsc.txt b/Documentation/networking/device_drivers/microsoft/netvsc.txt
index 3bfa635..cd63556 100644
--- a/Documentation/networking/device_drivers/microsoft/netvsc.txt
+++ b/Documentation/networking/device_drivers/microsoft/netvsc.txt
@@ -82,3 +82,24 @@
contain one or more packets. The send buffer is an optimization, the driver
will use slower method to handle very large packets or if the send buffer
area is exhausted.
+
+ XDP support
+ -----------
+ XDP (eXpress Data Path) is a feature that runs eBPF bytecode at the early
+ stage when packets arrive at a NIC card. The goal is to increase performance
+ for packet processing, reducing the overhead of SKB allocation and other
+ upper network layers.
+
+ hv_netvsc supports XDP in native mode, and transparently sets the XDP
+ program on the associated VF NIC as well.
+
+ Setting / unsetting XDP program on synthetic NIC (netvsc) propagates to
+ VF NIC automatically. Setting / unsetting XDP program on VF NIC directly
+ is not recommended, also not propagated to synthetic NIC, and may be
+ overwritten by setting of synthetic NIC.
+
+ XDP program cannot run with LRO (RSC) enabled, so you need to disable LRO
+ before running XDP:
+ ethtool -K eth0 lro off
+
+ XDP_REDIRECT action is not yet supported.
diff --git a/Documentation/networking/device_drivers/stmicro/stmmac.rst b/Documentation/networking/device_drivers/stmicro/stmmac.rst
new file mode 100644
index 0000000..c34bab3
--- /dev/null
+++ b/Documentation/networking/device_drivers/stmicro/stmmac.rst
@@ -0,0 +1,697 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+==============================================================
+Linux Driver for the Synopsys(R) Ethernet Controllers "stmmac"
+==============================================================
+
+Authors: Giuseppe Cavallaro <peppe.cavallaro@st.com>,
+Alexandre Torgue <alexandre.torgue@st.com>, Jose Abreu <joabreu@synopsys.com>
+
+Contents
+========
+
+- In This Release
+- Feature List
+- Kernel Configuration
+- Command Line Parameters
+- Driver Information and Notes
+- Debug Information
+- Support
+
+In This Release
+===============
+
+This file describes the stmmac Linux Driver for all the Synopsys(R) Ethernet
+Controllers.
+
+Currently, this network device driver is for all STi embedded MAC/GMAC
+(i.e. 7xxx/5xxx SoCs), SPEAr (arm), Loongson1B (mips) and XILINX XC2V3000
+FF1152AMT0221 D1215994A VIRTEX FPGA board. The Synopsys Ethernet QoS 5.0 IPK
+is also supported.
+
+DesignWare(R) Cores Ethernet MAC 10/100/1000 Universal version 3.70a
+(and older) and DesignWare(R) Cores Ethernet Quality-of-Service version 4.0
+(and upper) have been used for developing this driver as well as
+DesignWare(R) Cores XGMAC - 10G Ethernet MAC.
+
+This driver supports both the platform bus and PCI.
+
+This driver includes support for the following Synopsys(R) DesignWare(R)
+Cores Ethernet Controllers and corresponding minimum and maximum versions:
+
++-------------------------------+--------------+--------------+--------------+
+| Controller Name | Min. Version | Max. Version | Abbrev. Name |
++===============================+==============+==============+==============+
+| Ethernet MAC Universal | N/A | 3.73a | GMAC |
++-------------------------------+--------------+--------------+--------------+
+| Ethernet Quality-of-Service | 4.00a | N/A | GMAC4+ |
++-------------------------------+--------------+--------------+--------------+
+| XGMAC - 10G Ethernet MAC | 2.10a | N/A | XGMAC2+ |
++-------------------------------+--------------+--------------+--------------+
+
+For questions related to hardware requirements, refer to the documentation
+supplied with your Ethernet adapter. All hardware requirements listed apply
+to use with Linux.
+
+Feature List
+============
+
+The following features are available in this driver:
+ - GMII/MII/RGMII/SGMII/RMII/XGMII Interface
+ - Half-Duplex / Full-Duplex Operation
+ - Energy Efficient Ethernet (EEE)
+ - IEEE 802.3x PAUSE Packets (Flow Control)
+ - RMON/MIB Counters
+ - IEEE 1588 Timestamping (PTP)
+ - Pulse-Per-Second Output (PPS)
+ - MDIO Clause 22 / Clause 45 Interface
+ - MAC Loopback
+ - ARP Offloading
+ - Automatic CRC / PAD Insertion and Checking
+ - Checksum Offload for Received and Transmitted Packets
+ - Standard or Jumbo Ethernet Packets
+ - Source Address Insertion / Replacement
+ - VLAN TAG Insertion / Replacement / Deletion / Filtering (HASH and PERFECT)
+ - Programmable TX and RX Watchdog and Coalesce Settings
+ - Destination Address Filtering (PERFECT)
+ - HASH Filtering (Multicast)
+ - Layer 3 / Layer 4 Filtering
+ - Remote Wake-Up Detection
+ - Receive Side Scaling (RSS)
+ - Frame Preemption for TX and RX
+ - Programmable Burst Length, Threshold, Queue Size
+ - Multiple Queues (up to 8)
+ - Multiple Scheduling Algorithms (TX: WRR, DWRR, WFQ, SP, CBS, EST, TBS;
+ RX: WRR, SP)
+ - Flexible RX Parser
+ - TCP / UDP Segmentation Offload (TSO, USO)
+ - Split Header (SPH)
+ - Safety Features (ECC Protection, Data Parity Protection)
+ - Selftests using Ethtool
+
+Kernel Configuration
+====================
+
+The kernel configuration option is ``CONFIG_STMMAC_ETH``:
+ - ``CONFIG_STMMAC_PLATFORM``: is to enable the platform driver.
+ - ``CONFIG_STMMAC_PCI``: is to enable the pci driver.
+
+Command Line Parameters
+=======================
+
+If the driver is built as a module the following optional parameters are used
+by entering them on the command line with the modprobe command using this
+syntax (e.g. for PCI module)::
+
+ modprobe stmmac_pci [<option>=<VAL1>,<VAL2>,...]
+
+Driver parameters can be also passed in command line by using::
+
+ stmmaceth=watchdog:100,chain_mode=1
+
+The default value for each parameter is generally the recommended setting,
+unless otherwise noted.
+
+watchdog
+--------
+:Valid Range: 5000-None
+:Default Value: 5000
+
+This parameter overrides the transmit timeout in milliseconds.
+
+debug
+-----
+:Valid Range: 0-16 (0=none,...,16=all)
+:Default Value: 0
+
+This parameter adjusts the level of debug messages displayed in the system
+logs.
+
+phyaddr
+-------
+:Valid Range: 0-31
+:Default Value: -1
+
+This parameter overrides the physical address of the PHY device.
+
+flow_ctrl
+---------
+:Valid Range: 0-3 (0=off,1=rx,2=tx,3=rx/tx)
+:Default Value: 3
+
+This parameter changes the default Flow Control ability.
+
+pause
+-----
+:Valid Range: 0-65535
+:Default Value: 65535
+
+This parameter changes the default Flow Control Pause time.
+
+tc
+--
+:Valid Range: 64-256
+:Default Value: 64
+
+This parameter changes the default HW FIFO Threshold control value.
+
+buf_sz
+------
+:Valid Range: 1536-16384
+:Default Value: 1536
+
+This parameter changes the default RX DMA packet buffer size.
+
+eee_timer
+---------
+:Valid Range: 0-None
+:Default Value: 1000
+
+This parameter changes the default LPI TX Expiration time in milliseconds.
+
+chain_mode
+----------
+:Valid Range: 0-1 (0=off,1=on)
+:Default Value: 0
+
+This parameter changes the default mode of operation from Ring Mode to
+Chain Mode.
+
+Driver Information and Notes
+============================
+
+Transmit Process
+----------------
+
+The xmit method is invoked when the kernel needs to transmit a packet; it sets
+the descriptors in the ring and informs the DMA engine that there is a packet
+ready to be transmitted.
+
+By default, the driver sets the ``NETIF_F_SG`` bit in the features field of
+the ``net_device`` structure, enabling the scatter-gather feature. This is
+true on chips and configurations where the checksum can be done in hardware.
+
+Once the controller has finished transmitting the packet, timer will be
+scheduled to release the transmit resources.
+
+Receive Process
+---------------
+
+When one or more packets are received, an interrupt happens. The interrupts
+are not queued, so the driver has to scan all the descriptors in the ring
+during the receive process.
+
+This is based on NAPI, so the interrupt handler signals only if there is work
+to be done, and it exits. Then the poll method will be scheduled at some
+future point.
+
+The incoming packets are stored, by the DMA, in a list of pre-allocated socket
+buffers in order to avoid the memcpy (zero-copy).
+
+Interrupt Mitigation
+--------------------
+
+The driver is able to mitigate the number of its DMA interrupts using NAPI for
+the reception on chips older than the 3.50. New chips have an HW RX Watchdog
+used for this mitigation.
+
+Mitigation parameters can be tuned by ethtool.
+
+WoL
+---
+
+Wake up on Lan feature through Magic and Unicast frames are supported for the
+GMAC, GMAC4/5 and XGMAC core.
+
+DMA Descriptors
+---------------
+
+Driver handles both normal and alternate descriptors. The latter has been only
+tested on DesignWare(R) Cores Ethernet MAC Universal version 3.41a and later.
+
+stmmac supports DMA descriptor to operate both in dual buffer (RING) and
+linked-list(CHAINED) mode. In RING each descriptor points to two data buffer
+pointers whereas in CHAINED mode they point to only one data buffer pointer.
+RING mode is the default.
+
+In CHAINED mode each descriptor will have pointer to next descriptor in the
+list, hence creating the explicit chaining in the descriptor itself, whereas
+such explicit chaining is not possible in RING mode.
+
+Extended Descriptors
+--------------------
+
+The extended descriptors give us information about the Ethernet payload when
+it is carrying PTP packets or TCP/UDP/ICMP over IP. These are not available on
+GMAC Synopsys(R) chips older than the 3.50. At probe time the driver will
+decide if these can be actually used. This support also is mandatory for PTPv2
+because the extra descriptors are used for saving the hardware timestamps and
+Extended Status.
+
+Ethtool Support
+---------------
+
+Ethtool is supported. For example, driver statistics (including RMON),
+internal errors can be taken using::
+
+ ethtool -S ethX
+
+Ethtool selftests are also supported. This allows to do some early sanity
+checks to the HW using MAC and PHY loopback mechanisms::
+
+ ethtool -t ethX
+
+Jumbo and Segmentation Offloading
+---------------------------------
+
+Jumbo frames are supported and tested for the GMAC. The GSO has been also
+added but it's performed in software. LRO is not supported.
+
+TSO Support
+-----------
+
+TSO (TCP Segmentation Offload) feature is supported by GMAC > 4.x and XGMAC
+chip family. When a packet is sent through TCP protocol, the TCP stack ensures
+that the SKB provided to the low level driver (stmmac in our case) matches
+with the maximum frame len (IP header + TCP header + payload <= 1500 bytes
+(for MTU set to 1500)). It means that if an application using TCP want to send
+a packet which will have a length (after adding headers) > 1514 the packet
+will be split in several TCP packets: The data payload is split and headers
+(TCP/IP ..) are added. It is done by software.
+
+When TSO is enabled, the TCP stack doesn't care about the maximum frame length
+and provide SKB packet to stmmac as it is. The GMAC IP will have to perform
+the segmentation by it self to match with maximum frame length.
+
+This feature can be enabled in device tree through ``snps,tso`` entry.
+
+Energy Efficient Ethernet
+-------------------------
+
+Energy Efficient Ethernet (EEE) enables IEEE 802.3 MAC sublayer along with a
+family of Physical layer to operate in the Low Power Idle (LPI) mode. The EEE
+mode supports the IEEE 802.3 MAC operation at 100Mbps, 1000Mbps and 1Gbps.
+
+The LPI mode allows power saving by switching off parts of the communication
+device functionality when there is no data to be transmitted & received.
+The system on both the side of the link can disable some functionalities and
+save power during the period of low-link utilization. The MAC controls whether
+the system should enter or exit the LPI mode and communicate this to PHY.
+
+As soon as the interface is opened, the driver verifies if the EEE can be
+supported. This is done by looking at both the DMA HW capability register and
+the PHY devices MCD registers.
+
+To enter in TX LPI mode the driver needs to have a software timer that enable
+and disable the LPI mode when there is nothing to be transmitted.
+
+Precision Time Protocol (PTP)
+-----------------------------
+
+The driver supports the IEEE 1588-2002, Precision Time Protocol (PTP), which
+enables precise synchronization of clocks in measurement and control systems
+implemented with technologies such as network communication.
+
+In addition to the basic timestamp features mentioned in IEEE 1588-2002
+Timestamps, new GMAC cores support the advanced timestamp features.
+IEEE 1588-2008 can be enabled when configuring the Kernel.
+
+SGMII/RGMII Support
+-------------------
+
+New GMAC devices provide own way to manage RGMII/SGMII. This information is
+available at run-time by looking at the HW capability register. This means
+that the stmmac can manage auto-negotiation and link status w/o using the
+PHYLIB stuff. In fact, the HW provides a subset of extended registers to
+restart the ANE, verify Full/Half duplex mode and Speed. Thanks to these
+registers, it is possible to look at the Auto-negotiated Link Parter Ability.
+
+Physical
+--------
+
+The driver is compatible with Physical Abstraction Layer to be connected with
+PHY and GPHY devices.
+
+Platform Information
+--------------------
+
+Several information can be passed through the platform and device-tree.
+
+::
+
+ struct plat_stmmacenet_data {
+
+1) Bus identifier::
+
+ int bus_id;
+
+2) PHY Physical Address. If set to -1 the driver will pick the first PHY it
+finds::
+
+ int phy_addr;
+
+3) PHY Device Interface::
+
+ int interface;
+
+4) Specific platform fields for the MDIO bus::
+
+ struct stmmac_mdio_bus_data *mdio_bus_data;
+
+5) Internal DMA parameters::
+
+ struct stmmac_dma_cfg *dma_cfg;
+
+6) Fixed CSR Clock Range selection::
+
+ int clk_csr;
+
+7) HW uses the GMAC core::
+
+ int has_gmac;
+
+8) If set the MAC will use Enhanced Descriptors::
+
+ int enh_desc;
+
+9) Core is able to perform TX Checksum and/or RX Checksum in HW::
+
+ int tx_coe;
+ int rx_coe;
+
+11) Some HWs are not able to perform the csum in HW for over-sized frames due
+to limited buffer sizes. Setting this flag the csum will be done in SW on
+JUMBO frames::
+
+ int bugged_jumbo;
+
+12) Core has the embedded power module::
+
+ int pmt;
+
+13) Force DMA to use the Store and Forward mode or Threshold mode::
+
+ int force_sf_dma_mode;
+ int force_thresh_dma_mode;
+
+15) Force to disable the RX Watchdog feature and switch to NAPI mode::
+
+ int riwt_off;
+
+16) Limit the maximum operating speed and MTU::
+
+ int max_speed;
+ int maxmtu;
+
+18) Number of Multicast/Unicast filters::
+
+ int multicast_filter_bins;
+ int unicast_filter_entries;
+
+20) Limit the maximum TX and RX FIFO size::
+
+ int tx_fifo_size;
+ int rx_fifo_size;
+
+21) Use the specified number of TX and RX Queues::
+
+ u32 rx_queues_to_use;
+ u32 tx_queues_to_use;
+
+22) Use the specified TX and RX scheduling algorithm::
+
+ u8 rx_sched_algorithm;
+ u8 tx_sched_algorithm;
+
+23) Internal TX and RX Queue parameters::
+
+ struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
+ struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES];
+
+24) This callback is used for modifying some syscfg registers (on ST SoCs)
+according to the link speed negotiated by the physical layer::
+
+ void (*fix_mac_speed)(void *priv, unsigned int speed);
+
+25) Callbacks used for calling a custom initialization; This is sometimes
+necessary on some platforms (e.g. ST boxes) where the HW needs to have set
+some PIO lines or system cfg registers. init/exit callbacks should not use
+or modify platform data::
+
+ int (*init)(struct platform_device *pdev, void *priv);
+ void (*exit)(struct platform_device *pdev, void *priv);
+
+26) Perform HW setup of the bus. For example, on some ST platforms this field
+is used to configure the AMBA bridge to generate more efficient STBus traffic::
+
+ struct mac_device_info *(*setup)(void *priv);
+ void *bsp_priv;
+
+27) Internal clocks and rates::
+
+ struct clk *stmmac_clk;
+ struct clk *pclk;
+ struct clk *clk_ptp_ref;
+ unsigned int clk_ptp_rate;
+ unsigned int clk_ref_rate;
+ s32 ptp_max_adj;
+
+28) Main reset::
+
+ struct reset_control *stmmac_rst;
+
+29) AXI Internal Parameters::
+
+ struct stmmac_axi *axi;
+
+30) HW uses GMAC>4 cores::
+
+ int has_gmac4;
+
+31) HW is sun8i based::
+
+ bool has_sun8i;
+
+32) Enables TSO feature::
+
+ bool tso_en;
+
+33) Enables Receive Side Scaling (RSS) feature::
+
+ int rss_en;
+
+34) MAC Port selection::
+
+ int mac_port_sel_speed;
+
+35) Enables TX LPI Clock Gating::
+
+ bool en_tx_lpi_clockgating;
+
+36) HW uses XGMAC>2.10 cores::
+
+ int has_xgmac;
+
+::
+
+ }
+
+For MDIO bus data, we have:
+
+::
+
+ struct stmmac_mdio_bus_data {
+
+1) PHY mask passed when MDIO bus is registered::
+
+ unsigned int phy_mask;
+
+2) List of IRQs, one per PHY::
+
+ int *irqs;
+
+3) If IRQs is NULL, use this for probed PHY::
+
+ int probed_phy_irq;
+
+4) Set to true if PHY needs reset::
+
+ bool needs_reset;
+
+::
+
+ }
+
+For DMA engine configuration, we have:
+
+::
+
+ struct stmmac_dma_cfg {
+
+1) Programmable Burst Length (TX and RX)::
+
+ int pbl;
+
+2) If set, DMA TX / RX will use this value rather than pbl::
+
+ int txpbl;
+ int rxpbl;
+
+3) Enable 8xPBL::
+
+ bool pblx8;
+
+4) Enable Fixed or Mixed burst::
+
+ int fixed_burst;
+ int mixed_burst;
+
+5) Enable Address Aligned Beats::
+
+ bool aal;
+
+6) Enable Enhanced Addressing (> 32 bits)::
+
+ bool eame;
+
+::
+
+ }
+
+For DMA AXI parameters, we have:
+
+::
+
+ struct stmmac_axi {
+
+1) Enable AXI LPI::
+
+ bool axi_lpi_en;
+ bool axi_xit_frm;
+
+2) Set AXI Write / Read maximum outstanding requests::
+
+ u32 axi_wr_osr_lmt;
+ u32 axi_rd_osr_lmt;
+
+3) Set AXI 4KB bursts::
+
+ bool axi_kbbe;
+
+4) Set AXI maximum burst length map::
+
+ u32 axi_blen[AXI_BLEN];
+
+5) Set AXI Fixed burst / mixed burst::
+
+ bool axi_fb;
+ bool axi_mb;
+
+6) Set AXI rebuild incrx mode::
+
+ bool axi_rb;
+
+::
+
+ }
+
+For the RX Queues configuration, we have:
+
+::
+
+ struct stmmac_rxq_cfg {
+
+1) Mode to use (DCB or AVB)::
+
+ u8 mode_to_use;
+
+2) DMA channel to use::
+
+ u32 chan;
+
+3) Packet routing, if applicable::
+
+ u8 pkt_route;
+
+4) Use priority routing, and priority to route::
+
+ bool use_prio;
+ u32 prio;
+
+::
+
+ }
+
+For the TX Queues configuration, we have:
+
+::
+
+ struct stmmac_txq_cfg {
+
+1) Queue weight in scheduler::
+
+ u32 weight;
+
+2) Mode to use (DCB or AVB)::
+
+ u8 mode_to_use;
+
+3) Credit Base Shaper Parameters::
+
+ u32 send_slope;
+ u32 idle_slope;
+ u32 high_credit;
+ u32 low_credit;
+
+4) Use priority scheduling, and priority::
+
+ bool use_prio;
+ u32 prio;
+
+::
+
+ }
+
+Device Tree Information
+-----------------------
+
+Please refer to the following document:
+Documentation/devicetree/bindings/net/snps,dwmac.yaml
+
+HW Capabilities
+---------------
+
+Note that, starting from new chips, where it is available the HW capability
+register, many configurations are discovered at run-time for example to
+understand if EEE, HW csum, PTP, enhanced descriptor etc are actually
+available. As strategy adopted in this driver, the information from the HW
+capability register can replace what has been passed from the platform.
+
+Debug Information
+=================
+
+The driver exports many information i.e. internal statistics, debug
+information, MAC and DMA registers etc.
+
+These can be read in several ways depending on the type of the information
+actually needed.
+
+For example a user can be use the ethtool support to get statistics: e.g.
+using: ``ethtool -S ethX`` (that shows the Management counters (MMC) if
+supported) or sees the MAC/DMA registers: e.g. using: ``ethtool -d ethX``
+
+Compiling the Kernel with ``CONFIG_DEBUG_FS`` the driver will export the
+following debugfs entries:
+
+ - ``descriptors_status``: To show the DMA TX/RX descriptor rings
+ - ``dma_cap``: To show the HW Capabilities
+
+Developer can also use the ``debug`` module parameter to get further debug
+information (please see: NETIF Msg Level).
+
+Support
+=======
+
+If an issue is identified with the released source code on a supported kernel
+with a supported adapter, email the specific information related to the
+issue to netdev@vger.kernel.org
diff --git a/Documentation/networking/device_drivers/stmicro/stmmac.txt b/Documentation/networking/device_drivers/stmicro/stmmac.txt
deleted file mode 100644
index 1ae979f..0000000
--- a/Documentation/networking/device_drivers/stmicro/stmmac.txt
+++ /dev/null
@@ -1,401 +0,0 @@
- STMicroelectronics 10/100/1000 Synopsys Ethernet driver
-
-Copyright (C) 2007-2015 STMicroelectronics Ltd
-Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
-
-This is the driver for the MAC 10/100/1000 on-chip Ethernet controllers
-(Synopsys IP blocks).
-
-Currently this network device driver is for all STi embedded MAC/GMAC
-(i.e. 7xxx/5xxx SoCs), SPEAr (arm), Loongson1B (mips) and XLINX XC2V3000
-FF1152AMT0221 D1215994A VIRTEX FPGA board.
-
-DWC Ether MAC 10/100/1000 Universal version 3.70a (and older) and DWC Ether
-MAC 10/100 Universal version 4.0 have been used for developing this driver.
-
-This driver supports both the platform bus and PCI.
-
-Please, for more information also visit: www.stlinux.com
-
-1) Kernel Configuration
-The kernel configuration option is STMMAC_ETH:
- Device Drivers ---> Network device support ---> Ethernet (1000 Mbit) --->
- STMicroelectronics 10/100/1000 Ethernet driver (STMMAC_ETH)
-
-CONFIG_STMMAC_PLATFORM: is to enable the platform driver.
-CONFIG_STMMAC_PCI: is to enable the pci driver.
-
-2) Driver parameters list:
- debug: message level (0: no output, 16: all);
- phyaddr: to manually provide the physical address to the PHY device;
- buf_sz: DMA buffer size;
- tc: control the HW FIFO threshold;
- watchdog: transmit timeout (in milliseconds);
- flow_ctrl: Flow control ability [on/off];
- pause: Flow Control Pause Time;
- eee_timer: tx EEE timer;
- chain_mode: select chain mode instead of ring.
-
-3) Command line options
-Driver parameters can be also passed in command line by using:
- stmmaceth=watchdog:100,chain_mode=1
-
-4) Driver information and notes
-
-4.1) Transmit process
-The xmit method is invoked when the kernel needs to transmit a packet; it sets
-the descriptors in the ring and informs the DMA engine, that there is a packet
-ready to be transmitted.
-By default, the driver sets the NETIF_F_SG bit in the features field of the
-net_device structure, enabling the scatter-gather feature. This is true on
-chips and configurations where the checksum can be done in hardware.
-Once the controller has finished transmitting the packet, timer will be
-scheduled to release the transmit resources.
-
-4.2) Receive process
-When one or more packets are received, an interrupt happens. The interrupts
-are not queued, so the driver has to scan all the descriptors in the ring during
-the receive process.
-This is based on NAPI, so the interrupt handler signals only if there is work
-to be done, and it exits.
-Then the poll method will be scheduled at some future point.
-The incoming packets are stored, by the DMA, in a list of pre-allocated socket
-buffers in order to avoid the memcpy (zero-copy).
-
-4.3) Interrupt mitigation
-The driver is able to mitigate the number of its DMA interrupts
-using NAPI for the reception on chips older than the 3.50.
-New chips have an HW RX-Watchdog used for this mitigation.
-Mitigation parameters can be tuned by ethtool.
-
-4.4) WOL
-Wake up on Lan feature through Magic and Unicast frames are supported for the
-GMAC core.
-
-4.5) DMA descriptors
-Driver handles both normal and alternate descriptors. The latter has been only
-tested on DWC Ether MAC 10/100/1000 Universal version 3.41a and later.
-
-STMMAC supports DMA descriptor to operate both in dual buffer (RING)
-and linked-list(CHAINED) mode. In RING each descriptor points to two
-data buffer pointers whereas in CHAINED mode they point to only one data
-buffer pointer. RING mode is the default.
-
-In CHAINED mode each descriptor will have pointer to next descriptor in
-the list, hence creating the explicit chaining in the descriptor itself,
-whereas such explicit chaining is not possible in RING mode.
-
-4.5.1) Extended descriptors
-The extended descriptors give us information about the Ethernet payload
-when it is carrying PTP packets or TCP/UDP/ICMP over IP.
-These are not available on GMAC Synopsys chips older than the 3.50.
-At probe time the driver will decide if these can be actually used.
-This support also is mandatory for PTPv2 because the extra descriptors
-are used for saving the hardware timestamps and Extended Status.
-
-4.6) Ethtool support
-Ethtool is supported.
-
-For example, driver statistics (including RMON), internal errors can be taken
-using:
- # ethtool -S ethX
-command
-
-4.7) Jumbo and Segmentation Offloading
-Jumbo frames are supported and tested for the GMAC.
-The GSO has been also added but it's performed in software.
-LRO is not supported.
-
-4.8) Physical
-The driver is compatible with Physical Abstraction Layer to be connected with
-PHY and GPHY devices.
-
-4.9) Platform information
-Several information can be passed through the platform and device-tree.
-
-struct plat_stmmacenet_data {
- char *phy_bus_name;
- int bus_id;
- int phy_addr;
- int interface;
- struct stmmac_mdio_bus_data *mdio_bus_data;
- struct stmmac_dma_cfg *dma_cfg;
- int clk_csr;
- int has_gmac;
- int enh_desc;
- int tx_coe;
- int rx_coe;
- int bugged_jumbo;
- int pmt;
- int force_sf_dma_mode;
- int force_thresh_dma_mode;
- int riwt_off;
- int max_speed;
- int maxmtu;
- void (*fix_mac_speed)(void *priv, unsigned int speed);
- void (*bus_setup)(void __iomem *ioaddr);
- int (*init)(struct platform_device *pdev, void *priv);
- void (*exit)(struct platform_device *pdev, void *priv);
- void *bsp_priv;
- int has_gmac4;
- bool tso_en;
-};
-
-Where:
- o phy_bus_name: phy bus name to attach to the stmmac.
- o bus_id: bus identifier.
- o phy_addr: the physical address can be passed from the platform.
- If it is set to -1 the driver will automatically
- detect it at run-time by probing all the 32 addresses.
- o interface: PHY device's interface.
- o mdio_bus_data: specific platform fields for the MDIO bus.
- o dma_cfg: internal DMA parameters
- o pbl: the Programmable Burst Length is maximum number of beats to
- be transferred in one DMA transaction.
- GMAC also enables the 4xPBL by default. (8xPBL for GMAC 3.50 and newer)
- o txpbl/rxpbl: GMAC and newer supports independent DMA pbl for tx/rx.
- o pblx8: Enable 8xPBL (4xPBL for core rev < 3.50). Enabled by default.
- o fixed_burst/mixed_burst/aal
- o clk_csr: fixed CSR Clock range selection.
- o has_gmac: uses the GMAC core.
- o enh_desc: if sets the MAC will use the enhanced descriptor structure.
- o tx_coe: core is able to perform the tx csum in HW.
- o rx_coe: the supports three check sum offloading engine types:
- type_1, type_2 (full csum) and no RX coe.
- o bugged_jumbo: some HWs are not able to perform the csum in HW for
- over-sized frames due to limited buffer sizes.
- Setting this flag the csum will be done in SW on
- JUMBO frames.
- o pmt: core has the embedded power module (optional).
- o force_sf_dma_mode: force DMA to use the Store and Forward mode
- instead of the Threshold.
- o force_thresh_dma_mode: force DMA to use the Threshold mode other than
- the Store and Forward mode.
- o riwt_off: force to disable the RX watchdog feature and switch to NAPI mode.
- o fix_mac_speed: this callback is used for modifying some syscfg registers
- (on ST SoCs) according to the link speed negotiated by the
- physical layer .
- o bus_setup: perform HW setup of the bus. For example, on some ST platforms
- this field is used to configure the AMBA bridge to generate more
- efficient STBus traffic.
- o init/exit: callbacks used for calling a custom initialization;
- this is sometime necessary on some platforms (e.g. ST boxes)
- where the HW needs to have set some PIO lines or system cfg
- registers. init/exit callbacks should not use or modify
- platform data.
- o bsp_priv: another private pointer.
- o has_gmac4: uses GMAC4 core.
- o tso_en: Enables TSO (TCP Segmentation Offload) feature.
-
-For MDIO bus The we have:
-
- struct stmmac_mdio_bus_data {
- int (*phy_reset)(void *priv);
- unsigned int phy_mask;
- int *irqs;
- int probed_phy_irq;
- };
-
-Where:
- o phy_reset: hook to reset the phy device attached to the bus.
- o phy_mask: phy mask passed when register the MDIO bus within the driver.
- o irqs: list of IRQs, one per PHY.
- o probed_phy_irq: if irqs is NULL, use this for probed PHY.
-
-For DMA engine we have the following internal fields that should be
-tuned according to the HW capabilities.
-
-struct stmmac_dma_cfg {
- int pbl;
- int txpbl;
- int rxpbl;
- bool pblx8;
- int fixed_burst;
- int mixed_burst;
- bool aal;
-};
-
-Where:
- o pbl: Programmable Burst Length (tx and rx)
- o txpbl: Transmit Programmable Burst Length. Only for GMAC and newer.
- If set, DMA tx will use this value rather than pbl.
- o rxpbl: Receive Programmable Burst Length. Only for GMAC and newer.
- If set, DMA rx will use this value rather than pbl.
- o pblx8: Enable 8xPBL (4xPBL for core rev < 3.50). Enabled by default.
- o fixed_burst: program the DMA to use the fixed burst mode
- o mixed_burst: program the DMA to use the mixed burst mode
- o aal: Address-Aligned Beats
-
----
-
-Below an example how the structures above are using on ST platforms.
-
- static struct plat_stmmacenet_data stxYYY_ethernet_platform_data = {
- .has_gmac = 0,
- .enh_desc = 0,
- .fix_mac_speed = stxYYY_ethernet_fix_mac_speed,
- |
- |-> to write an internal syscfg
- | on this platform when the
- | link speed changes from 10 to
- | 100 and viceversa
- .init = &stmmac_claim_resource,
- |
- |-> On ST SoC this calls own "PAD"
- | manager framework to claim
- | all the resources necessary
- | (GPIO ...). The .custom_cfg field
- | is used to pass a custom config.
-};
-
-Below the usage of the stmmac_mdio_bus_data: on this SoC, in fact,
-there are two MAC cores: one MAC is for MDIO Bus/PHY emulation
-with fixed_link support.
-
-static struct stmmac_mdio_bus_data stmmac1_mdio_bus = {
- .phy_reset = phy_reset;
- |
- |-> function to provide the phy_reset on this board
- .phy_mask = 0,
-};
-
-static struct fixed_phy_status stmmac0_fixed_phy_status = {
- .link = 1,
- .speed = 100,
- .duplex = 1,
-};
-
-During the board's device_init we can configure the first
-MAC for fixed_link by calling:
- fixed_phy_add(PHY_POLL, 1, &stmmac0_fixed_phy_status);
-and the second one, with a real PHY device attached to the bus,
-by using the stmmac_mdio_bus_data structure (to provide the id, the
-reset procedure etc).
-
-Note that, starting from new chips, where it is available the HW capability
-register, many configurations are discovered at run-time for example to
-understand if EEE, HW csum, PTP, enhanced descriptor etc are actually
-available. As strategy adopted in this driver, the information from the HW
-capability register can replace what has been passed from the platform.
-
-4.10) Device-tree support.
-
-Please see the following document:
- Documentation/devicetree/bindings/net/stmmac.txt
-
-4.11) This is a summary of the content of some relevant files:
- o stmmac_main.c: implements the main network device driver;
- o stmmac_mdio.c: provides MDIO functions;
- o stmmac_pci: this is the PCI driver;
- o stmmac_platform.c: this the platform driver (OF supported);
- o stmmac_ethtool.c: implements the ethtool support;
- o stmmac.h: private driver structure;
- o common.h: common definitions and VFTs;
- o mmc_core.c/mmc.h: Management MAC Counters;
- o stmmac_hwtstamp.c: HW timestamp support for PTP;
- o stmmac_ptp.c: PTP 1588 clock;
- o stmmac_pcs.h: Physical Coding Sublayer common implementation;
- o dwmac-<XXX>.c: these are for the platform glue-logic file; e.g. dwmac-sti.c
- for STMicroelectronics SoCs.
-
-- GMAC 3.x
- o descs.h: descriptor structure definitions;
- o dwmac1000_core.c: dwmac GiGa core functions;
- o dwmac1000_dma.c: dma functions for the GMAC chip;
- o dwmac1000.h: specific header file for the dwmac GiGa;
- o dwmac100_core: dwmac 100 core code;
- o dwmac100_dma.c: dma functions for the dwmac 100 chip;
- o dwmac1000.h: specific header file for the MAC;
- o dwmac_lib.c: generic DMA functions;
- o enh_desc.c: functions for handling enhanced descriptors;
- o norm_desc.c: functions for handling normal descriptors;
- o chain_mode.c/ring_mode.c:: functions to manage RING/CHAINED modes;
-
-- GMAC4.x generation
- o dwmac4_core.c: dwmac GMAC4.x core functions;
- o dwmac4_desc.c: functions for handling GMAC4.x descriptors;
- o dwmac4_descs.h: descriptor definitions;
- o dwmac4_dma.c: dma functions for the GMAC4.x chip;
- o dwmac4_dma.h: dma definitions for the GMAC4.x chip;
- o dwmac4.h: core definitions for the GMAC4.x chip;
- o dwmac4_lib.c: generic GMAC4.x functions;
-
-4.12) TSO support (GMAC4.x)
-
-TSO (Tcp Segmentation Offload) feature is supported by GMAC 4.x chip family.
-When a packet is sent through TCP protocol, the TCP stack ensures that
-the SKB provided to the low level driver (stmmac in our case) matches with
-the maximum frame len (IP header + TCP header + payload <= 1500 bytes (for
-MTU set to 1500)). It means that if an application using TCP want to send a
-packet which will have a length (after adding headers) > 1514 the packet
-will be split in several TCP packets: The data payload is split and headers
-(TCP/IP ..) are added. It is done by software.
-
-When TSO is enabled, the TCP stack doesn't care about the maximum frame
-length and provide SKB packet to stmmac as it is. The GMAC IP will have to
-perform the segmentation by it self to match with maximum frame length.
-
-This feature can be enabled in device tree through "snps,tso" entry.
-
-5) Debug Information
-
-The driver exports many information i.e. internal statistics,
-debug information, MAC and DMA registers etc.
-
-These can be read in several ways depending on the
-type of the information actually needed.
-
-For example a user can be use the ethtool support
-to get statistics: e.g. using: ethtool -S ethX
-(that shows the Management counters (MMC) if supported)
-or sees the MAC/DMA registers: e.g. using: ethtool -d ethX
-
-Compiling the Kernel with CONFIG_DEBUG_FS the driver will export the following
-debugfs entries:
-
-/sys/kernel/debug/stmmaceth/descriptors_status
- To show the DMA TX/RX descriptor rings
-
-Developer can also use the "debug" module parameter to get further debug
-information (please see: NETIF Msg Level).
-
-6) Energy Efficient Ethernet
-
-Energy Efficient Ethernet(EEE) enables IEEE 802.3 MAC sublayer along
-with a family of Physical layer to operate in the Low power Idle(LPI)
-mode. The EEE mode supports the IEEE 802.3 MAC operation at 100Mbps,
-1000Mbps & 10Gbps.
-
-The LPI mode allows power saving by switching off parts of the
-communication device functionality when there is no data to be
-transmitted & received. The system on both the side of the link can
-disable some functionalities & save power during the period of low-link
-utilization. The MAC controls whether the system should enter or exit
-the LPI mode & communicate this to PHY.
-
-As soon as the interface is opened, the driver verifies if the EEE can
-be supported. This is done by looking at both the DMA HW capability
-register and the PHY devices MCD registers.
-To enter in Tx LPI mode the driver needs to have a software timer
-that enable and disable the LPI mode when there is nothing to be
-transmitted.
-
-7) Precision Time Protocol (PTP)
-The driver supports the IEEE 1588-2002, Precision Time Protocol (PTP),
-which enables precise synchronization of clocks in measurement and
-control systems implemented with technologies such as network
-communication.
-
-In addition to the basic timestamp features mentioned in IEEE 1588-2002
-Timestamps, new GMAC cores support the advanced timestamp features.
-IEEE 1588-2008 that can be enabled when configure the Kernel.
-
-8) SGMII/RGMII support
-New GMAC devices provide own way to manage RGMII/SGMII.
-This information is available at run-time by looking at the
-HW capability register. This means that the stmmac can manage
-auto-negotiation and link status w/o using the PHYLIB stuff.
-In fact, the HW provides a subset of extended registers to
-restart the ANE, verify Full/Half duplex mode and Speed.
-Thanks to these registers, it is possible to look at the
-Auto-negotiated Link Parter Ability.
diff --git a/Documentation/networking/device_drivers/ti/cpsw_switchdev.txt b/Documentation/networking/device_drivers/ti/cpsw_switchdev.txt
index 5c8cee1..12855ab 100644
--- a/Documentation/networking/device_drivers/ti/cpsw_switchdev.txt
+++ b/Documentation/networking/device_drivers/ti/cpsw_switchdev.txt
@@ -39,7 +39,7 @@
Devlink configuration parameters
====================
-See Documentation/networking/devlink-params-ti-cpsw-switch.txt
+See Documentation/networking/devlink/ti-cpsw-switch.rst
====================
# Bridging in dual mac mode
diff --git a/Documentation/networking/devlink-health.txt b/Documentation/networking/devlink-health.txt
deleted file mode 100644
index 1db3fbe..0000000
--- a/Documentation/networking/devlink-health.txt
+++ /dev/null
@@ -1,86 +0,0 @@
-The health mechanism is targeted for Real Time Alerting, in order to know when
-something bad had happened to a PCI device
-- Provide alert debug information
-- Self healing
-- If problem needs vendor support, provide a way to gather all needed debugging
- information.
-
-The main idea is to unify and centralize driver health reports in the
-generic devlink instance and allow the user to set different
-attributes of the health reporting and recovery procedures.
-
-The devlink health reporter:
-Device driver creates a "health reporter" per each error/health type.
-Error/Health type can be a known/generic (eg pci error, fw error, rx/tx error)
-or unknown (driver specific).
-For each registered health reporter a driver can issue error/health reports
-asynchronously. All health reports handling is done by devlink.
-Device driver can provide specific callbacks for each "health reporter", e.g.
- - Recovery procedures
- - Diagnostics and object dump procedures
- - OOB initial parameters
-Different parts of the driver can register different types of health reporters
-with different handlers.
-
-Once an error is reported, devlink health will do the following actions:
- * A log is being send to the kernel trace events buffer
- * Health status and statistics are being updated for the reporter instance
- * Object dump is being taken and saved at the reporter instance (as long as
- there is no other dump which is already stored)
- * Auto recovery attempt is being done. Depends on:
- - Auto-recovery configuration
- - Grace period vs. time passed since last recover
-
-The user interface:
-User can access/change each reporter's parameters and driver specific callbacks
-via devlink, e.g per error type (per health reporter)
- - Configure reporter's generic parameters (like: disable/enable auto recovery)
- - Invoke recovery procedure
- - Run diagnostics
- - Object dump
-
-The devlink health interface (via netlink):
-DEVLINK_CMD_HEALTH_REPORTER_GET
- Retrieves status and configuration info per DEV and reporter.
-DEVLINK_CMD_HEALTH_REPORTER_SET
- Allows reporter-related configuration setting.
-DEVLINK_CMD_HEALTH_REPORTER_RECOVER
- Triggers a reporter's recovery procedure.
-DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE
- Retrieves diagnostics data from a reporter on a device.
-DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET
- Retrieves the last stored dump. Devlink health
- saves a single dump. If an dump is not already stored by the devlink
- for this reporter, devlink generates a new dump.
- dump output is defined by the reporter.
-DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR
- Clears the last saved dump file for the specified reporter.
-
-
- netlink
- +--------------------------+
- | |
- | + |
- | | |
- +--------------------------+
- |request for ops
- |(diagnose,
- mlx5_core devlink |recover,
- |dump)
-+--------+ +--------------------------+
-| | | reporter| |
-| | | +---------v----------+ |
-| | ops execution | | | |
-| <----------------------------------+ | |
-| | | | | |
-| | | + ^------------------+ |
-| | | | request for ops |
-| | | | (recover, dump) |
-| | | | |
-| | | +-+------------------+ |
-| | health report | | health handler | |
-| +-------------------------------> | |
-| | | +--------------------+ |
-| | health reporter create | |
-| +----------------------------> |
-+--------+ +--------------------------+
diff --git a/Documentation/networking/devlink-info-versions.rst b/Documentation/networking/devlink-info-versions.rst
deleted file mode 100644
index 4914f58..0000000
--- a/Documentation/networking/devlink-info-versions.rst
+++ /dev/null
@@ -1,64 +0,0 @@
-.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-
-=====================
-Devlink info versions
-=====================
-
-board.id
-========
-
-Unique identifier of the board design.
-
-board.rev
-=========
-
-Board design revision.
-
-asic.id
-=======
-
-ASIC design identifier.
-
-asic.rev
-========
-
-ASIC design revision.
-
-board.manufacture
-=================
-
-An identifier of the company or the facility which produced the part.
-
-fw
-==
-
-Overall firmware version, often representing the collection of
-fw.mgmt, fw.app, etc.
-
-fw.mgmt
-=======
-
-Control unit firmware version. This firmware is responsible for house
-keeping tasks, PHY control etc. but not the packet-by-packet data path
-operation.
-
-fw.app
-======
-
-Data path microcode controlling high-speed packet processing.
-
-fw.undi
-=======
-
-UNDI software, may include the UEFI driver, firmware or both.
-
-fw.ncsi
-=======
-
-Version of the software responsible for supporting/handling the
-Network Controller Sideband Interface.
-
-fw.psid
-=======
-
-Unique identifier of the firmware parameter set.
diff --git a/Documentation/networking/devlink-params-bnxt.txt b/Documentation/networking/devlink-params-bnxt.txt
deleted file mode 100644
index 481aa30..0000000
--- a/Documentation/networking/devlink-params-bnxt.txt
+++ /dev/null
@@ -1,18 +0,0 @@
-enable_sriov [DEVICE, GENERIC]
- Configuration mode: Permanent
-
-ignore_ari [DEVICE, GENERIC]
- Configuration mode: Permanent
-
-msix_vec_per_pf_max [DEVICE, GENERIC]
- Configuration mode: Permanent
-
-msix_vec_per_pf_min [DEVICE, GENERIC]
- Configuration mode: Permanent
-
-gre_ver_check [DEVICE, DRIVER-SPECIFIC]
- Generic Routing Encapsulation (GRE) version check will
- be enabled in the device. If disabled, device skips
- version checking for incoming packets.
- Type: Boolean
- Configuration mode: Permanent
diff --git a/Documentation/networking/devlink-params-mlx5.txt b/Documentation/networking/devlink-params-mlx5.txt
deleted file mode 100644
index 5071467..0000000
--- a/Documentation/networking/devlink-params-mlx5.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-flow_steering_mode [DEVICE, DRIVER-SPECIFIC]
- Controls the flow steering mode of the driver.
- Two modes are supported:
- 1. 'dmfs' - Device managed flow steering.
- 2. 'smfs - Software/Driver managed flow steering.
- In DMFS mode, the HW steering entities are created and
- managed through the Firmware.
- In SMFS mode, the HW steering entities are created and
- managed though by the driver directly into Hardware
- without firmware intervention.
- Type: String
- Configuration mode: runtime
-
-enable_roce [DEVICE, GENERIC]
- Enable handling of RoCE traffic in the device.
- Defaultly enabled.
- Configuration mode: driverinit
diff --git a/Documentation/networking/devlink-params-mlxsw.txt b/Documentation/networking/devlink-params-mlxsw.txt
deleted file mode 100644
index c63ea9f..0000000
--- a/Documentation/networking/devlink-params-mlxsw.txt
+++ /dev/null
@@ -1,10 +0,0 @@
-fw_load_policy [DEVICE, GENERIC]
- Configuration mode: driverinit
-
-acl_region_rehash_interval [DEVICE, DRIVER-SPECIFIC]
- Sets an interval for periodic ACL region rehashes.
- The value is in milliseconds, minimal value is "3000".
- Value "0" disables the periodic work.
- The first rehash will be run right after value is set.
- Type: u32
- Configuration mode: runtime
diff --git a/Documentation/networking/devlink-params-mv88e6xxx.txt b/Documentation/networking/devlink-params-mv88e6xxx.txt
deleted file mode 100644
index 21c4b35..0000000
--- a/Documentation/networking/devlink-params-mv88e6xxx.txt
+++ /dev/null
@@ -1,7 +0,0 @@
-ATU_hash [DEVICE, DRIVER-SPECIFIC]
- Select one of four possible hashing algorithms for
- MAC addresses in the Address Translation Unit.
- A value of 3 seems to work better than the default of
- 1 when many MAC addresses have the same OUI.
- Configuration mode: runtime
- Type: u8. 0-3 valid.
diff --git a/Documentation/networking/devlink-params-nfp.txt b/Documentation/networking/devlink-params-nfp.txt
deleted file mode 100644
index 43e4d40..0000000
--- a/Documentation/networking/devlink-params-nfp.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-fw_load_policy [DEVICE, GENERIC]
- Configuration mode: permanent
-
-reset_dev_on_drv_probe [DEVICE, GENERIC]
- Configuration mode: permanent
diff --git a/Documentation/networking/devlink-params-ti-cpsw-switch.txt b/Documentation/networking/devlink-params-ti-cpsw-switch.txt
deleted file mode 100644
index 4037458..0000000
--- a/Documentation/networking/devlink-params-ti-cpsw-switch.txt
+++ /dev/null
@@ -1,10 +0,0 @@
-ale_bypass [DEVICE, DRIVER-SPECIFIC]
- Allows to enable ALE_CONTROL(4).BYPASS mode for debug purposes.
- All packets will be sent to the Host port only if enabled.
- Type: bool
- Configuration mode: runtime
-
-switch_mode [DEVICE, DRIVER-SPECIFIC]
- Enable switch mode
- Type: bool
- Configuration mode: runtime
diff --git a/Documentation/networking/devlink-params.txt b/Documentation/networking/devlink-params.txt
deleted file mode 100644
index 04e234e..0000000
--- a/Documentation/networking/devlink-params.txt
+++ /dev/null
@@ -1,71 +0,0 @@
-Devlink configuration parameters
-================================
-Following is the list of configuration parameters via devlink interface.
-Each parameter can be generic or driver specific and are device level
-parameters.
-
-Note that the driver-specific files should contain the generic params
-they support to, with supported config modes.
-
-Each parameter can be set in different configuration modes:
- runtime - set while driver is running, no reset required.
- driverinit - applied while driver initializes, requires restart
- driver by devlink reload command.
- permanent - written to device's non-volatile memory, hard reset
- required.
-
-Following is the list of parameters:
-====================================
-enable_sriov [DEVICE, GENERIC]
- Enable Single Root I/O Virtualisation (SRIOV) in
- the device.
- Type: Boolean
-
-ignore_ari [DEVICE, GENERIC]
- Ignore Alternative Routing-ID Interpretation (ARI)
- capability. If enabled, adapter will ignore ARI
- capability even when platforms has the support
- enabled and creates same number of partitions when
- platform does not support ARI.
- Type: Boolean
-
-msix_vec_per_pf_max [DEVICE, GENERIC]
- Provides the maximum number of MSIX interrupts that
- a device can create. Value is same across all
- physical functions (PFs) in the device.
- Type: u32
-
-msix_vec_per_pf_min [DEVICE, GENERIC]
- Provides the minimum number of MSIX interrupts required
- for the device initialization. Value is same across all
- physical functions (PFs) in the device.
- Type: u32
-
-fw_load_policy [DEVICE, GENERIC]
- Controls the device's firmware loading policy.
- Valid values:
- * DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER (0)
- Load firmware version preferred by the driver.
- * DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH (1)
- Load firmware currently stored in flash.
- * DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DISK (2)
- Load firmware currently available on host's disk.
- Type: u8
-
-reset_dev_on_drv_probe [DEVICE, GENERIC]
- Controls the device's reset policy on driver probe.
- Valid values:
- * DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_UNKNOWN (0)
- Unknown or invalid value.
- * DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_ALWAYS (1)
- Always reset device on driver probe.
- * DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_NEVER (2)
- Never reset device on driver probe.
- * DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_DISK (3)
- Reset only if device firmware can be found in the
- filesystem.
- Type: u8
-
-enable_roce [DEVICE, GENERIC]
- Enable handling of RoCE traffic in the device.
- Type: Boolean
diff --git a/Documentation/networking/devlink-trap-netdevsim.rst b/Documentation/networking/devlink-trap-netdevsim.rst
deleted file mode 100644
index b721c94..0000000
--- a/Documentation/networking/devlink-trap-netdevsim.rst
+++ /dev/null
@@ -1,20 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-======================
-Devlink Trap netdevsim
-======================
-
-Driver-specific Traps
-=====================
-
-.. list-table:: List of Driver-specific Traps Registered by ``netdevsim``
- :widths: 5 5 90
-
- * - Name
- - Type
- - Description
- * - ``fid_miss``
- - ``exception``
- - When a packet enters the device it is classified to a filtering
- indentifier (FID) based on the ingress port and VLAN. This trap is used
- to trap packets for which a FID could not be found
diff --git a/Documentation/networking/devlink/bnxt.rst b/Documentation/networking/devlink/bnxt.rst
new file mode 100644
index 0000000..79e746d
--- /dev/null
+++ b/Documentation/networking/devlink/bnxt.rst
@@ -0,0 +1,41 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
+bnxt devlink support
+====================
+
+This document describes the devlink features implemented by the ``bnxt``
+device driver.
+
+Parameters
+==========
+
+.. list-table:: Generic parameters implemented
+
+ * - Name
+ - Mode
+ * - ``enable_sriov``
+ - Permanent
+ * - ``ignore_ari``
+ - Permanent
+ * - ``msix_vec_per_pf_max``
+ - Permanent
+ * - ``msix_vec_per_pf_min``
+ - Permanent
+
+The ``bnxt`` driver also implements the following driver-specific
+parameters.
+
+.. list-table:: Driver-specific parameters implemented
+ :widths: 5 5 5 85
+
+ * - Name
+ - Type
+ - Mode
+ - Description
+ * - ``gre_ver_check``
+ - Boolean
+ - Permanent
+ - Generic Routing Encapsulation (GRE) version check will be enabled in
+ the device. If disabled, the device will skip the version check for
+ incoming packets.
diff --git a/Documentation/networking/devlink/devlink-dpipe.rst b/Documentation/networking/devlink/devlink-dpipe.rst
new file mode 100644
index 0000000..468fe10
--- /dev/null
+++ b/Documentation/networking/devlink/devlink-dpipe.rst
@@ -0,0 +1,252 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=============
+Devlink DPIPE
+=============
+
+Background
+==========
+
+While performing the hardware offloading process, much of the hardware
+specifics cannot be presented. These details are useful for debugging, and
+``devlink-dpipe`` provides a standardized way to provide visibility into the
+offloading process.
+
+For example, the routing longest prefix match (LPM) algorithm used by the
+Linux kernel may differ from the hardware implementation. The pipeline debug
+API (DPIPE) is aimed at providing the user visibility into the ASIC's
+pipeline in a generic way.
+
+The hardware offload process is expected to be done in a way that the user
+should not be able to distinguish between the hardware vs. software
+implementation. In this process, hardware specifics are neglected. In
+reality those details can have lots of meaning and should be exposed in some
+standard way.
+
+This problem is made even more complex when one wishes to offload the
+control path of the whole networking stack to a switch ASIC. Due to
+differences in the hardware and software models some processes cannot be
+represented correctly.
+
+One example is the kernel's LPM algorithm which in many cases differs
+greatly to the hardware implementation. The configuration API is the same,
+but one cannot rely on the Forward Information Base (FIB) to look like the
+Level Path Compression trie (LPC-trie) in hardware.
+
+In many situations trying to analyze systems failure solely based on the
+kernel's dump may not be enough. By combining this data with complementary
+information about the underlying hardware, this debugging can be made
+easier; additionally, the information can be useful when debugging
+performance issues.
+
+Overview
+========
+
+The ``devlink-dpipe`` interface closes this gap. The hardware's pipeline is
+modeled as a graph of match/action tables. Each table represents a specific
+hardware block. This model is not new, first being used by the P4 language.
+
+Traditionally it has been used as an alternative model for hardware
+configuration, but the ``devlink-dpipe`` interface uses it for visibility
+purposes as a standard complementary tool. The system's view from
+``devlink-dpipe`` should change according to the changes done by the
+standard configuration tools.
+
+For example, it’s quiet common to implement Access Control Lists (ACL)
+using Ternary Content Addressable Memory (TCAM). The TCAM memory can be
+divided into TCAM regions. Complex TC filters can have multiple rules with
+different priorities and different lookup keys. On the other hand hardware
+TCAM regions have a predefined lookup key. Offloading the TC filter rules
+using TCAM engine can result in multiple TCAM regions being interconnected
+in a chain (which may affect the data path latency). In response to a new TC
+filter new tables should be created describing those regions.
+
+Model
+=====
+
+The ``DPIPE`` model introduces several objects:
+
+ * headers
+ * tables
+ * entries
+
+A ``header`` describes packet formats and provides names for fields within
+the packet. A ``table`` describes hardware blocks. An ``entry`` describes
+the actual content of a specific table.
+
+The hardware pipeline is not port specific, but rather describes the whole
+ASIC. Thus it is tied to the top of the ``devlink`` infrastructure.
+
+Drivers can register and unregister tables at run time, in order to support
+dynamic behavior. This dynamic behavior is mandatory for describing hardware
+blocks like TCAM regions which can be allocated and freed dynamically.
+
+``devlink-dpipe`` generally is not intended for configuration. The exception
+is hardware counting for a specific table.
+
+The following commands are used to obtain the ``dpipe`` objects from
+userspace:
+
+ * ``table_get``: Receive a table's description.
+ * ``headers_get``: Receive a device's supported headers.
+ * ``entries_get``: Receive a table's current entries.
+ * ``counters_set``: Enable or disable counters on a table.
+
+Table
+-----
+
+The driver should implement the following operations for each table:
+
+ * ``matches_dump``: Dump the supported matches.
+ * ``actions_dump``: Dump the supported actions.
+ * ``entries_dump``: Dump the actual content of the table.
+ * ``counters_set_update``: Synchronize hardware with counters enabled or
+ disabled.
+
+Header/Field
+------------
+
+In a similar way to P4 headers and fields are used to describe a table's
+behavior. There is a slight difference between the standard protocol headers
+and specific ASIC metadata. The protocol headers should be declared in the
+``devlink`` core API. On the other hand ASIC meta data is driver specific
+and should be defined in the driver. Additionally, each driver-specific
+devlink documentation file should document the driver-specific ``dpipe``
+headers it implements. The headers and fields are identified by enumeration.
+
+In order to provide further visibility some ASIC metadata fields could be
+mapped to kernel objects. For example, internal router interface indexes can
+be directly mapped to the net device ifindex. FIB table indexes used by
+different Virtual Routing and Forwarding (VRF) tables can be mapped to
+internal routing table indexes.
+
+Match
+-----
+
+Matches are kept primitive and close to hardware operation. Match types like
+LPM are not supported due to the fact that this is exactly a process we wish
+to describe in full detail. Example of matches:
+
+ * ``field_exact``: Exact match on a specific field.
+ * ``field_exact_mask``: Exact match on a specific field after masking.
+ * ``field_range``: Match on a specific range.
+
+The id's of the header and the field should be specified in order to
+identify the specific field. Furthermore, the header index should be
+specified in order to distinguish multiple headers of the same type in a
+packet (tunneling).
+
+Action
+------
+
+Similar to match, the actions are kept primitive and close to hardware
+operation. For example:
+
+ * ``field_modify``: Modify the field value.
+ * ``field_inc``: Increment the field value.
+ * ``push_header``: Add a header.
+ * ``pop_header``: Remove a header.
+
+Entry
+-----
+
+Entries of a specific table can be dumped on demand. Each eentry is
+identified with an index and its properties are described by a list of
+match/action values and specific counter. By dumping the tables content the
+interactions between tables can be resolved.
+
+Abstraction Example
+===================
+
+The following is an example of the abstraction model of the L3 part of
+Mellanox Spectrum ASIC. The blocks are described in the order they appear in
+the pipeline. The table sizes in the following examples are not real
+hardware sizes and are provided for demonstration purposes.
+
+LPM
+---
+
+The LPM algorithm can be implemented as a list of hash tables. Each hash
+table contains routes with the same prefix length. The root of the list is
+/32, and in case of a miss the hardware will continue to the next hash
+table. The depth of the search will affect the data path latency.
+
+In case of a hit the entry contains information about the next stage of the
+pipeline which resolves the MAC address. The next stage can be either local
+host table for directly connected routes, or adjacency table for next-hops.
+The ``meta.lpm_prefix`` field is used to connect two LPM tables.
+
+.. code::
+
+ table lpm_prefix_16 {
+ size: 4096,
+ counters_enabled: true,
+ match: { meta.vr_id: exact,
+ ipv4.dst_addr: exact_mask,
+ ipv6.dst_addr: exact_mask,
+ meta.lpm_prefix: exact },
+ action: { meta.adj_index: set,
+ meta.adj_group_size: set,
+ meta.rif_port: set,
+ meta.lpm_prefix: set },
+ }
+
+Local Host
+----------
+
+In the case of local routes the LPM lookup already resolves the egress
+router interface (RIF), yet the exact MAC address is not known. The local
+host table is a hash table combining the output interface id with
+destination IP address as a key. The result is the MAC address.
+
+.. code::
+
+ table local_host {
+ size: 4096,
+ counters_enabled: true,
+ match: { meta.rif_port: exact,
+ ipv4.dst_addr: exact},
+ action: { ethernet.daddr: set }
+ }
+
+Adjacency
+---------
+
+In case of remote routes this table does the ECMP. The LPM lookup results in
+ECMP group size and index that serves as a global offset into this table.
+Concurrently a hash of the packet is generated. Based on the ECMP group size
+and the packet's hash a local offset is generated. Multiple LPM entries can
+point to the same adjacency group.
+
+.. code::
+
+ table adjacency {
+ size: 4096,
+ counters_enabled: true,
+ match: { meta.adj_index: exact,
+ meta.adj_group_size: exact,
+ meta.packet_hash_index: exact },
+ action: { ethernet.daddr: set,
+ meta.erif: set }
+ }
+
+ERIF
+----
+
+In case the egress RIF and destination MAC have been resolved by previous
+tables this table does multiple operations like TTL decrease and MTU check.
+Then the decision of forward/drop is taken and the port L3 statistics are
+updated based on the packet's type (broadcast, unicast, multicast).
+
+.. code::
+
+ table erif {
+ size: 800,
+ counters_enabled: true,
+ match: { meta.rif_port: exact,
+ meta.is_l3_unicast: exact,
+ meta.is_l3_broadcast: exact,
+ meta.is_l3_multicast, exact },
+ action: { meta.l3_drop: set,
+ meta.l3_forward: set }
+ }
diff --git a/Documentation/networking/devlink/devlink-health.rst b/Documentation/networking/devlink/devlink-health.rst
new file mode 100644
index 0000000..0c99b11
--- /dev/null
+++ b/Documentation/networking/devlink/devlink-health.rst
@@ -0,0 +1,114 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+Devlink Health
+==============
+
+Background
+==========
+
+The ``devlink`` health mechanism is targeted for Real Time Alerting, in
+order to know when something bad happened to a PCI device.
+
+ * Provide alert debug information.
+ * Self healing.
+ * If problem needs vendor support, provide a way to gather all needed
+ debugging information.
+
+Overview
+========
+
+The main idea is to unify and centralize driver health reports in the
+generic ``devlink`` instance and allow the user to set different
+attributes of the health reporting and recovery procedures.
+
+The ``devlink`` health reporter:
+Device driver creates a "health reporter" per each error/health type.
+Error/Health type can be a known/generic (eg pci error, fw error, rx/tx error)
+or unknown (driver specific).
+For each registered health reporter a driver can issue error/health reports
+asynchronously. All health reports handling is done by ``devlink``.
+Device driver can provide specific callbacks for each "health reporter", e.g.:
+
+ * Recovery procedures
+ * Diagnostics procedures
+ * Object dump procedures
+ * OOB initial parameters
+
+Different parts of the driver can register different types of health reporters
+with different handlers.
+
+Actions
+=======
+
+Once an error is reported, devlink health will perform the following actions:
+
+ * A log is being send to the kernel trace events buffer
+ * Health status and statistics are being updated for the reporter instance
+ * Object dump is being taken and saved at the reporter instance (as long as
+ there is no other dump which is already stored)
+ * Auto recovery attempt is being done. Depends on:
+ - Auto-recovery configuration
+ - Grace period vs. time passed since last recover
+
+User Interface
+==============
+
+User can access/change each reporter's parameters and driver specific callbacks
+via ``devlink``, e.g per error type (per health reporter):
+
+ * Configure reporter's generic parameters (like: disable/enable auto recovery)
+ * Invoke recovery procedure
+ * Run diagnostics
+ * Object dump
+
+.. list-table:: List of devlink health interfaces
+ :widths: 10 90
+
+ * - Name
+ - Description
+ * - ``DEVLINK_CMD_HEALTH_REPORTER_GET``
+ - Retrieves status and configuration info per DEV and reporter.
+ * - ``DEVLINK_CMD_HEALTH_REPORTER_SET``
+ - Allows reporter-related configuration setting.
+ * - ``DEVLINK_CMD_HEALTH_REPORTER_RECOVER``
+ - Triggers a reporter's recovery procedure.
+ * - ``DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE``
+ - Retrieves diagnostics data from a reporter on a device.
+ * - ``DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET``
+ - Retrieves the last stored dump. Devlink health
+ saves a single dump. If an dump is not already stored by the devlink
+ for this reporter, devlink generates a new dump.
+ dump output is defined by the reporter.
+ * - ``DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR``
+ - Clears the last saved dump file for the specified reporter.
+
+The following diagram provides a general overview of ``devlink-health``::
+
+ netlink
+ +--------------------------+
+ | |
+ | + |
+ | | |
+ +--------------------------+
+ |request for ops
+ |(diagnose,
+ mlx5_core devlink |recover,
+ |dump)
+ +--------+ +--------------------------+
+ | | | reporter| |
+ | | | +---------v----------+ |
+ | | ops execution | | | |
+ | <----------------------------------+ | |
+ | | | | | |
+ | | | + ^------------------+ |
+ | | | | request for ops |
+ | | | | (recover, dump) |
+ | | | | |
+ | | | +-+------------------+ |
+ | | health report | | health handler | |
+ | +-------------------------------> | |
+ | | | +--------------------+ |
+ | | health reporter create | |
+ | +----------------------------> |
+ +--------+ +--------------------------+
diff --git a/Documentation/networking/devlink/devlink-info.rst b/Documentation/networking/devlink/devlink-info.rst
new file mode 100644
index 0000000..0385f15
--- /dev/null
+++ b/Documentation/networking/devlink/devlink-info.rst
@@ -0,0 +1,94 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
+============
+Devlink Info
+============
+
+The ``devlink-info`` mechanism enables device drivers to report device
+information in a generic fashion. It is extensible, and enables exporting
+even device or driver specific information.
+
+devlink supports representing the following types of versions
+
+.. list-table:: List of version types
+ :widths: 5 95
+
+ * - Type
+ - Description
+ * - ``fixed``
+ - Represents fixed versions, which cannot change. For example,
+ component identifiers or the board version reported in the PCI VPD.
+ * - ``running``
+ - Represents the version of the currently running component. For
+ example the running version of firmware. These versions generally
+ only update after a reboot.
+ * - ``stored``
+ - Represents the version of a component as stored, such as after a
+ flash update. Stored values should update to reflect changes in the
+ flash even if a reboot has not yet occurred.
+
+Generic Versions
+================
+
+It is expected that drivers use the following generic names for exporting
+version information. Other information may be exposed using driver-specific
+names, but these should be documented in the driver-specific file.
+
+board.id
+--------
+
+Unique identifier of the board design.
+
+board.rev
+---------
+
+Board design revision.
+
+asic.id
+-------
+
+ASIC design identifier.
+
+asic.rev
+--------
+
+ASIC design revision.
+
+board.manufacture
+-----------------
+
+An identifier of the company or the facility which produced the part.
+
+fw
+--
+
+Overall firmware version, often representing the collection of
+fw.mgmt, fw.app, etc.
+
+fw.mgmt
+-------
+
+Control unit firmware version. This firmware is responsible for house
+keeping tasks, PHY control etc. but not the packet-by-packet data path
+operation.
+
+fw.app
+------
+
+Data path microcode controlling high-speed packet processing.
+
+fw.undi
+-------
+
+UNDI software, may include the UEFI driver, firmware or both.
+
+fw.ncsi
+-------
+
+Version of the software responsible for supporting/handling the
+Network Controller Sideband Interface.
+
+fw.psid
+-------
+
+Unique identifier of the firmware parameter set.
diff --git a/Documentation/networking/devlink/devlink-params.rst b/Documentation/networking/devlink/devlink-params.rst
new file mode 100644
index 0000000..da2f85c
--- /dev/null
+++ b/Documentation/networking/devlink/devlink-params.rst
@@ -0,0 +1,108 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+Devlink Params
+==============
+
+``devlink`` provides capability for a driver to expose device parameters for low
+level device functionality. Since devlink can operate at the device-wide
+level, it can be used to provide configuration that may affect multiple
+ports on a single device.
+
+This document describes a number of generic parameters that are supported
+across multiple drivers. Each driver is also free to add their own
+parameters. Each driver must document the specific parameters they support,
+whether generic or not.
+
+Configuration modes
+===================
+
+Parameters may be set in different configuration modes.
+
+.. list-table:: Possible configuration modes
+ :widths: 5 90
+
+ * - Name
+ - Description
+ * - ``runtime``
+ - set while the driver is running, and takes effect immediately. No
+ reset is required.
+ * - ``driverinit``
+ - applied while the driver initializes. Requires the user to restart
+ the driver using the ``devlink`` reload command.
+ * - ``permanent``
+ - written to the device's non-volatile memory. A hard reset is required
+ for it to take effect.
+
+Reloading
+---------
+
+In order for ``driverinit`` parameters to take effect, the driver must
+support reloading via the ``devlink-reload`` command. This command will
+request a reload of the device driver.
+
+Generic configuration parameters
+================================
+The following is a list of generic configuration parameters that drivers may
+add. Use of generic parameters is preferred over each driver creating their
+own name.
+
+.. list-table:: List of generic parameters
+ :widths: 5 5 90
+
+ * - Name
+ - Type
+ - Description
+ * - ``enable_sriov``
+ - Boolean
+ - Enable Single Root I/O Virtualization (SRIOV) in the device.
+ * - ``ignore_ari``
+ - Boolean
+ - Ignore Alternative Routing-ID Interpretation (ARI) capability. If
+ enabled, the adapter will ignore ARI capability even when the
+ platform has support enabled. The device will create the same number
+ of partitions as when the platform does not support ARI.
+ * - ``msix_vec_per_pf_max``
+ - u32
+ - Provides the maximum number of MSI-X interrupts that a device can
+ create. Value is the same across all physical functions (PFs) in the
+ device.
+ * - ``msix_vec_per_pf_min``
+ - u32
+ - Provides the minimum number of MSI-X interrupts required for the
+ device to initialize. Value is the same across all physical functions
+ (PFs) in the device.
+ * - ``fw_load_policy``
+ - u8
+ - Control the device's firmware loading policy.
+ - ``DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER`` (0)
+ Load firmware version preferred by the driver.
+ - ``DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH`` (1)
+ Load firmware currently stored in flash.
+ - ``DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DISK`` (2)
+ Load firmware currently available on host's disk.
+ * - ``reset_dev_on_drv_probe``
+ - u8
+ - Controls the device's reset policy on driver probe.
+ - ``DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_UNKNOWN`` (0)
+ Unknown or invalid value.
+ - ``DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_ALWAYS`` (1)
+ Always reset device on driver probe.
+ - ``DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_NEVER`` (2)
+ Never reset device on driver probe.
+ - ``DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_DISK`` (3)
+ Reset the device only if firmware can be found in the filesystem.
+ * - ``enable_roce``
+ - Boolean
+ - Enable handling of RoCE traffic in the device.
+ * - ``internal_err_reset``
+ - Boolean
+ - When enabled, the device driver will reset the device on internal
+ errors.
+ * - ``max_macs``
+ - u32
+ - Specifies the maximum number of MAC addresses per ethernet port of
+ this device.
+ * - ``region_snapshot_enable``
+ - Boolean
+ - Enable capture of ``devlink-region`` snapshots.
diff --git a/Documentation/networking/devlink/devlink-region.rst b/Documentation/networking/devlink/devlink-region.rst
new file mode 100644
index 0000000..1a7683e
--- /dev/null
+++ b/Documentation/networking/devlink/devlink-region.rst
@@ -0,0 +1,60 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+Devlink Region
+==============
+
+``devlink`` regions enable access to driver defined address regions using
+devlink.
+
+Each device can create and register its own supported address regions. The
+region can then be accessed via the devlink region interface.
+
+Region snapshots are collected by the driver, and can be accessed via read
+or dump commands. This allows future analysis on the created snapshots.
+Regions may optionally support triggering snapshots on demand.
+
+The major benefit to creating a region is to provide access to internal
+address regions that are otherwise inaccessible to the user.
+
+Regions may also be used to provide an additional way to debug complex error
+states, but see also :doc:`devlink-health`
+
+example usage
+-------------
+
+.. code:: shell
+
+ $ devlink region help
+ $ devlink region show [ DEV/REGION ]
+ $ devlink region del DEV/REGION snapshot SNAPSHOT_ID
+ $ devlink region dump DEV/REGION [ snapshot SNAPSHOT_ID ]
+ $ devlink region read DEV/REGION [ snapshot SNAPSHOT_ID ]
+ address ADDRESS length length
+
+ # Show all of the exposed regions with region sizes:
+ $ devlink region show
+ pci/0000:00:05.0/cr-space: size 1048576 snapshot [1 2]
+ pci/0000:00:05.0/fw-health: size 64 snapshot [1 2]
+
+ # Delete a snapshot using:
+ $ devlink region del pci/0000:00:05.0/cr-space snapshot 1
+
+ # Trigger (request) a snapshot be taken:
+ $ devlink region trigger pci/0000:00:05.0/cr-space
+
+ # Dump a snapshot:
+ $ devlink region dump pci/0000:00:05.0/fw-health snapshot 1
+ 0000000000000000 0014 95dc 0014 9514 0035 1670 0034 db30
+ 0000000000000010 0000 0000 ffff ff04 0029 8c00 0028 8cc8
+ 0000000000000020 0016 0bb8 0016 1720 0000 0000 c00f 3ffc
+ 0000000000000030 bada cce5 bada cce5 bada cce5 bada cce5
+
+ # Read a specific part of a snapshot:
+ $ devlink region read pci/0000:00:05.0/fw-health snapshot 1 address 0
+ length 16
+ 0000000000000000 0014 95dc 0014 9514 0035 1670 0034 db30
+
+As regions are likely very device or driver specific, no generic regions are
+defined. See the driver-specific documentation files for information on the
+specific regions a driver supports.
diff --git a/Documentation/networking/devlink/devlink-resource.rst b/Documentation/networking/devlink/devlink-resource.rst
new file mode 100644
index 0000000..93e92d2
--- /dev/null
+++ b/Documentation/networking/devlink/devlink-resource.rst
@@ -0,0 +1,62 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+================
+Devlink Resource
+================
+
+``devlink`` provides the ability for drivers to register resources, which
+can allow administrators to see the device restrictions for a given
+resource, as well as how much of the given resource is currently
+in use. Additionally, these resources can optionally have configurable size.
+This could enable the administrator to limit the number of resources that
+are used.
+
+For example, the ``netdevsim`` driver enables ``/IPv4/fib`` and
+``/IPv4/fib-rules`` as resources to limit the number of IPv4 FIB entries and
+rules for a given device.
+
+Resource Ids
+============
+
+Each resource is represented by an id, and contains information about its
+current size and related sub resources. To access a sub resource, you
+specify the path of the resource. For example ``/IPv4/fib`` is the id for
+the ``fib`` sub-resource under the ``IPv4`` resource.
+
+example usage
+-------------
+
+The resources exposed by the driver can be observed, for example:
+
+.. code:: shell
+
+ $devlink resource show pci/0000:03:00.0
+ pci/0000:03:00.0:
+ name kvd size 245760 unit entry
+ resources:
+ name linear size 98304 occ 0 unit entry size_min 0 size_max 147456 size_gran 128
+ name hash_double size 60416 unit entry size_min 32768 size_max 180224 size_gran 128
+ name hash_single size 87040 unit entry size_min 65536 size_max 212992 size_gran 128
+
+Some resource's size can be changed. Examples:
+
+.. code:: shell
+
+ $devlink resource set pci/0000:03:00.0 path /kvd/hash_single size 73088
+ $devlink resource set pci/0000:03:00.0 path /kvd/hash_double size 74368
+
+The changes do not apply immediately, this can be validated by the 'size_new'
+attribute, which represents the pending change in size. For example:
+
+.. code:: shell
+
+ $devlink resource show pci/0000:03:00.0
+ pci/0000:03:00.0:
+ name kvd size 245760 unit entry size_valid false
+ resources:
+ name linear size 98304 size_new 147456 occ 0 unit entry size_min 0 size_max 147456 size_gran 128
+ name hash_double size 60416 unit entry size_min 32768 size_max 180224 size_gran 128
+ name hash_single size 87040 unit entry size_min 65536 size_max 212992 size_gran 128
+
+Note that changes in resource size may require a device reload to properly
+take effect.
diff --git a/Documentation/networking/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst
similarity index 92%
rename from Documentation/networking/devlink-trap.rst
rename to Documentation/networking/devlink/devlink-trap.rst
index 0331184..47a429b 100644
--- a/Documentation/networking/devlink-trap.rst
+++ b/Documentation/networking/devlink/devlink-trap.rst
@@ -223,6 +223,21 @@
* - ``ipv6_lpm_miss``
- ``exception``
- Traps unicast IPv6 packets that did not match any route
+ * - ``non_routable_packet``
+ - ``drop``
+ - Traps packets that the device decided to drop because they are not
+ supposed to be routed. For example, IGMP queries can be flooded by the
+ device in layer 2 and reach the router. Such packets should not be
+ routed and instead dropped
+ * - ``decap_error``
+ - ``exception``
+ - Traps NVE and IPinIP packets that the device decided to drop because of
+ failure during decapsulation (e.g., packet being too short, reserved
+ bits set in VXLAN header)
+ * - ``overlay_smac_is_mc``
+ - ``drop``
+ - Traps NVE packets that the device decided to drop because their overlay
+ source MAC is multicast
Driver-specific Packet Traps
============================
@@ -233,7 +248,8 @@
links to the description of driver-specific traps registered by various device
drivers:
- * :doc:`devlink-trap-netdevsim`
+ * :doc:`netdevsim`
+ * :doc:`mlxsw`
Generic Packet Trap Groups
==========================
@@ -258,6 +274,9 @@
* - ``buffer_drops``
- Contains packet traps for packets that were dropped by the device due to
an enqueue decision
+ * - ``tunnel_drops``
+ - Contains packet traps for packets that were dropped by the device during
+ tunnel encapsulation / decapsulation
Testing
=======
diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst
new file mode 100644
index 0000000..087ff54
--- /dev/null
+++ b/Documentation/networking/devlink/index.rst
@@ -0,0 +1,42 @@
+Linux Devlink Documentation
+===========================
+
+devlink is an API to expose device information and resources not directly
+related to any device class, such as chip-wide/switch-ASIC-wide configuration.
+
+Interface documentation
+-----------------------
+
+The following pages describe various interfaces available through devlink in
+general.
+
+.. toctree::
+ :maxdepth: 1
+
+ devlink-dpipe
+ devlink-health
+ devlink-info
+ devlink-params
+ devlink-region
+ devlink-resource
+ devlink-trap
+
+Driver-specific documentation
+-----------------------------
+
+Each driver that implements ``devlink`` is expected to document what
+parameters, info versions, and other features it supports.
+
+.. toctree::
+ :maxdepth: 1
+
+ bnxt
+ ionic
+ mlx4
+ mlx5
+ mlxsw
+ mv88e6xxx
+ netdevsim
+ nfp
+ qed
+ ti-cpsw-switch
diff --git a/Documentation/networking/devlink/ionic.rst b/Documentation/networking/devlink/ionic.rst
new file mode 100644
index 0000000..48da9c9
--- /dev/null
+++ b/Documentation/networking/devlink/ionic.rst
@@ -0,0 +1,29 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+ionic devlink support
+=====================
+
+This document describes the devlink features implemented by the ``ionic``
+device driver.
+
+Info versions
+=============
+
+The ``ionic`` driver reports the following versions
+
+.. list-table:: devlink info versions implemented
+ :widths: 5 5 90
+
+ * - Name
+ - Type
+ - Description
+ * - ``fw``
+ - running
+ - Version of firmware running on the device
+ * - ``asic.id``
+ - fixed
+ - The ASIC type for this device
+ * - ``asic.rev``
+ - fixed
+ - The revision of the ASIC for this device
diff --git a/Documentation/networking/devlink/mlx4.rst b/Documentation/networking/devlink/mlx4.rst
new file mode 100644
index 0000000..7b2d17e
--- /dev/null
+++ b/Documentation/networking/devlink/mlx4.rst
@@ -0,0 +1,56 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
+mlx4 devlink support
+====================
+
+This document describes the devlink features implemented by the ``mlx4``
+device driver.
+
+Parameters
+==========
+
+.. list-table:: Generic parameters implemented
+
+ * - Name
+ - Mode
+ * - ``internal_err_reset``
+ - driverinit, runtime
+ * - ``max_macs``
+ - driverinit
+ * - ``region_snapshot_enable``
+ - driverinit, runtime
+
+The ``mlx4`` driver also implements the following driver-specific
+parameters.
+
+.. list-table:: Driver-specific parameters implemented
+ :widths: 5 5 5 85
+
+ * - Name
+ - Type
+ - Mode
+ - Description
+ * - ``enable_64b_cqe_eqe``
+ - Boolean
+ - driverinit
+ - Enable 64 byte CQEs/EQEs, if the FW supports it.
+ * - ``enable_4k_uar``
+ - Boolean
+ - driverinit
+ - Enable using the 4k UAR.
+
+The ``mlx4`` driver supports reloading via ``DEVLINK_CMD_RELOAD``
+
+Regions
+=======
+
+The ``mlx4`` driver supports dumping the firmware PCI crspace and health
+buffer during a critical firmware issue.
+
+In case a firmware command times out, firmware getting stuck, or a non zero
+value on the catastrophic buffer, a snapshot will be taken by the driver.
+
+The ``cr-space`` region will contain the firmware PCI crspace contents. The
+``fw-health`` region will contain the device firmware's health buffer.
+Snapshots for both of these regions are taken on the same event triggers.
diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
new file mode 100644
index 0000000..629a6e6
--- /dev/null
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -0,0 +1,59 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
+mlx5 devlink support
+====================
+
+This document describes the devlink features implemented by the ``mlx5``
+device driver.
+
+Parameters
+==========
+
+.. list-table:: Generic parameters implemented
+
+ * - Name
+ - Mode
+ * - ``enable_roce``
+ - driverinit
+
+The ``mlx5`` driver also implements the following driver-specific
+parameters.
+
+.. list-table:: Driver-specific parameters implemented
+ :widths: 5 5 5 85
+
+ * - Name
+ - Type
+ - Mode
+ - Description
+ * - ``flow_steering_mode``
+ - string
+ - runtime
+ - Controls the flow steering mode of the driver
+
+ * ``dmfs`` Device managed flow steering. In DMFS mode, the HW
+ steering entities are created and managed through firmware.
+ * ``smfs`` Software managed flow steering. In SMFS mode, the HW
+ steering entities are created and manage through the driver without
+ firmware intervention.
+
+The ``mlx5`` driver supports reloading via ``DEVLINK_CMD_RELOAD``
+
+Info versions
+=============
+
+The ``mlx5`` driver reports the following versions
+
+.. list-table:: devlink info versions implemented
+ :widths: 5 5 90
+
+ * - Name
+ - Type
+ - Description
+ * - ``fw.psid``
+ - fixed
+ - Used to represent the board id of the device.
+ * - ``fw.version``
+ - stored, running
+ - Three digit major.minor.subminor firmware version number.
diff --git a/Documentation/networking/devlink/mlxsw.rst b/Documentation/networking/devlink/mlxsw.rst
new file mode 100644
index 0000000..cf857cb
--- /dev/null
+++ b/Documentation/networking/devlink/mlxsw.rst
@@ -0,0 +1,81 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+mlxsw devlink support
+=====================
+
+This document describes the devlink features implemented by the ``mlxsw``
+device driver.
+
+Parameters
+==========
+
+.. list-table:: Generic parameters implemented
+
+ * - Name
+ - Mode
+ * - ``fw_load_policy``
+ - driverinit
+
+The ``mlxsw`` driver also implements the following driver-specific
+parameters.
+
+.. list-table:: Driver-specific parameters implemented
+ :widths: 5 5 5 85
+
+ * - Name
+ - Type
+ - Mode
+ - Description
+ * - ``acl_region_rehash_interval``
+ - u32
+ - runtime
+ - Sets an interval for periodic ACL region rehashes. The value is
+ specified in milliseconds, with a minimum of ``3000``. The value of
+ ``0`` disables periodic work entirely. The first rehash will be run
+ immediately after the value is set.
+
+The ``mlxsw`` driver supports reloading via ``DEVLINK_CMD_RELOAD``
+
+Info versions
+=============
+
+The ``mlxsw`` driver reports the following versions
+
+.. list-table:: devlink info versions implemented
+ :widths: 5 5 90
+
+ * - Name
+ - Type
+ - Description
+ * - ``hw.revision``
+ - fixed
+ - The hardware revision for this board
+ * - ``fw.psid``
+ - fixed
+ - Firmware PSID
+ * - ``fw.version``
+ - running
+ - Three digit firmware version
+
+Driver-specific Traps
+=====================
+
+.. list-table:: List of Driver-specific Traps Registered by ``mlxsw``
+ :widths: 5 5 90
+
+ * - Name
+ - Type
+ - Description
+ * - ``irif_disabled``
+ - ``drop``
+ - Traps packets that the device decided to drop because they need to be
+ routed from a disabled router interface (RIF). This can happen during
+ RIF dismantle, when the RIF is first disabled before being removed
+ completely
+ * - ``erif_disabled``
+ - ``drop``
+ - Traps packets that the device decided to drop because they need to be
+ routed through a disabled router interface (RIF). This can happen during
+ RIF dismantle, when the RIF is first disabled before being removed
+ completely
diff --git a/Documentation/networking/devlink/mv88e6xxx.rst b/Documentation/networking/devlink/mv88e6xxx.rst
new file mode 100644
index 0000000..c621212
--- /dev/null
+++ b/Documentation/networking/devlink/mv88e6xxx.rst
@@ -0,0 +1,28 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================
+mv88e6xxx devlink support
+=========================
+
+This document describes the devlink features implemented by the ``mv88e6xxx``
+device driver.
+
+Parameters
+==========
+
+The ``mv88e6xxx`` driver implements the following driver-specific parameters.
+
+.. list-table:: Driver-specific parameters implemented
+ :widths: 5 5 5 85
+
+ * - Name
+ - Type
+ - Mode
+ - Description
+ * - ``ATU_hash``
+ - u8
+ - runtime
+ - Select one of four possible hashing algorithms for MAC addresses in
+ the Address Translation Unit. A value of 3 may work better than the
+ default of 1 when many MAC addresses have the same OUI. Only the
+ values 0 to 3 are valid for this parameter.
diff --git a/Documentation/networking/devlink/netdevsim.rst b/Documentation/networking/devlink/netdevsim.rst
new file mode 100644
index 0000000..2a266b7
--- /dev/null
+++ b/Documentation/networking/devlink/netdevsim.rst
@@ -0,0 +1,72 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================
+netdevsim devlink support
+=========================
+
+This document describes the ``devlink`` features supported by the
+``netdevsim`` device driver.
+
+Parameters
+==========
+
+.. list-table:: Generic parameters implemented
+
+ * - Name
+ - Mode
+ * - ``max_macs``
+ - driverinit
+
+The ``netdevsim`` driver also implements the following driver-specific
+parameters.
+
+.. list-table:: Driver-specific parameters implemented
+ :widths: 5 5 5 85
+
+ * - Name
+ - Type
+ - Mode
+ - Description
+ * - ``test1``
+ - Boolean
+ - driverinit
+ - Test parameter used to show how a driver-specific devlink parameter
+ can be implemented.
+
+The ``netdevsim`` driver supports reloading via ``DEVLINK_CMD_RELOAD``
+
+Regions
+=======
+
+The ``netdevsim`` driver exposes a ``dummy`` region as an example of how the
+devlink-region interfaces work. A snapshot is taken whenever the
+``take_snapshot`` debugfs file is written to.
+
+Resources
+=========
+
+The ``netdevsim`` driver exposes resources to control the number of FIB
+entries and FIB rule entries that the driver will allow.
+
+.. code:: shell
+
+ $ devlink resource set netdevsim/netdevsim0 path /IPv4/fib size 96
+ $ devlink resource set netdevsim/netdevsim0 path /IPv4/fib-rules size 16
+ $ devlink resource set netdevsim/netdevsim0 path /IPv6/fib size 64
+ $ devlink resource set netdevsim/netdevsim0 path /IPv6/fib-rules size 16
+ $ devlink dev reload netdevsim/netdevsim0
+
+Driver-specific Traps
+=====================
+
+.. list-table:: List of Driver-specific Traps Registered by ``netdevsim``
+ :widths: 5 5 90
+
+ * - Name
+ - Type
+ - Description
+ * - ``fid_miss``
+ - ``exception``
+ - When a packet enters the device it is classified to a filtering
+ indentifier (FID) based on the ingress port and VLAN. This trap is used
+ to trap packets for which a FID could not be found
diff --git a/Documentation/networking/devlink/nfp.rst b/Documentation/networking/devlink/nfp.rst
new file mode 100644
index 0000000..a1717db0
--- /dev/null
+++ b/Documentation/networking/devlink/nfp.rst
@@ -0,0 +1,65 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================
+nfp devlink support
+===================
+
+This document describes the devlink features implemented by the ``nfp``
+device driver.
+
+Parameters
+==========
+
+.. list-table:: Generic parameters implemented
+
+ * - Name
+ - Mode
+ * - ``fw_load_policy``
+ - permanent
+ * - ``reset_dev_on_drv_probe``
+ - permanent
+
+Info versions
+=============
+
+The ``nfp`` driver reports the following versions
+
+.. list-table:: devlink info versions implemented
+ :widths: 5 5 90
+
+ * - Name
+ - Type
+ - Description
+ * - ``board.id``
+ - fixed
+ - Part number identifying the board design
+ * - ``board.rev``
+ - fixed
+ - Revision of the board design
+ * - ``board.manufacture``
+ - fixed
+ - Vendor of the board design
+ * - ``board.model``
+ - fixed
+ - Model name of the board design
+ * - ``fw.bundle_id``
+ - stored, running
+ - Firmware bundle id
+ * - ``fw.mgmt``
+ - stored, running
+ - Version of the management firmware
+ * - ``fw.cpld``
+ - stored, running
+ - The CPLD firmware component version
+ * - ``fw.app``
+ - stored, running
+ - The APP firmware component version
+ * - ``fw.undi``
+ - stored, running
+ - The UNDI firmware component version
+ * - ``fw.ncsi``
+ - stored, running
+ - The NSCI firmware component version
+ * - ``chip.init``
+ - stored, running
+ - The CFGR firmware component version
diff --git a/Documentation/networking/devlink/qed.rst b/Documentation/networking/devlink/qed.rst
new file mode 100644
index 0000000..805c6f6
--- /dev/null
+++ b/Documentation/networking/devlink/qed.rst
@@ -0,0 +1,26 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================
+qed devlink support
+===================
+
+This document describes the devlink features implemented by the ``qed`` core
+device driver.
+
+Parameters
+==========
+
+The ``qed`` driver implements the following driver-specific parameters.
+
+.. list-table:: Driver-specific parameters implemented
+ :widths: 5 5 5 85
+
+ * - Name
+ - Type
+ - Mode
+ - Description
+ * - ``iwarp_cmt``
+ - Boolean
+ - runtime
+ - Enable iWARP functionality for 100g devices. Note that this impacts
+ L2 performance, and is therefore not enabled by default.
diff --git a/Documentation/networking/devlink/ti-cpsw-switch.rst b/Documentation/networking/devlink/ti-cpsw-switch.rst
new file mode 100644
index 0000000..dc399e3
--- /dev/null
+++ b/Documentation/networking/devlink/ti-cpsw-switch.rst
@@ -0,0 +1,31 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================
+ti-cpsw-switch devlink support
+==============================
+
+This document describes the devlink features implemented by the ``ti-cpsw-switch``
+device driver.
+
+Parameters
+==========
+
+The ``ti-cpsw-switch`` driver implements the following driver-specific
+parameters.
+
+.. list-table:: Driver-specific parameters implemented
+ :widths: 5 5 5 85
+
+ * - Name
+ - Type
+ - Mode
+ - Description
+ * - ``ale_bypass``
+ - Boolean
+ - runtime
+ - Enables ALE_CONTROL(4).BYPASS mode for debugging purposes. In this
+ mode, all packets will be sent to the host port only.
+ * - ``switch_mode``
+ - Boolean
+ - runtime
+ - Enable switch mode
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index bee73be..d07d985 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -13,9 +13,7 @@
can_ucan_protocol
device_drivers/index
dsa/index
- devlink-info-versions
- devlink-trap
- devlink-trap-netdevsim
+ devlink/index
ethtool-netlink
ieee802154
j1939
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 90b8f14..5f53faf 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -607,7 +607,7 @@
with the current initial RTO of 1second. With this the final timeout
for a passive TCP connection will happen after 63seconds.
-tcp_syncookies - BOOLEAN
+tcp_syncookies - INTEGER
Only valid when the kernel was compiled with CONFIG_SYN_COOKIES
Send out syncookies when the syn backlog queue of a socket
overflows. This is to prevent against the common 'SYN flood attack'
diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst
index 642fa96..d5c9320 100644
--- a/Documentation/networking/netdev-FAQ.rst
+++ b/Documentation/networking/netdev-FAQ.rst
@@ -34,8 +34,8 @@
mainline tree from Linus, and ``net-next`` is where the new code goes
for the future release. You can find the trees here:
-- https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
-- https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
+- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
+- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
Q: How often do changes from these trees make it to the mainline Linus tree?
----------------------------------------------------------------------------
diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst
index e0a7c7a..1e4735c 100644
--- a/Documentation/networking/phy.rst
+++ b/Documentation/networking/phy.rst
@@ -267,6 +267,24 @@
duplex, pause or other settings. This is dependent on the MAC and/or
PHY behaviour.
+``PHY_INTERFACE_MODE_10GBASER``
+ This is the IEEE 802.3 Clause 49 defined 10GBASE-R protocol used with
+ various different mediums. Please refer to the IEEE standard for a
+ definition of this.
+
+ Note: 10GBASE-R is just one protocol that can be used with XFI and SFI.
+ XFI and SFI permit multiple protocols over a single SERDES lane, and
+ also defines the electrical characteristics of the signals with a host
+ compliance board plugged into the host XFP/SFP connector. Therefore,
+ XFI and SFI are not PHY interface types in their own right.
+
+``PHY_INTERFACE_MODE_10GKR``
+ This is the IEEE 802.3 Clause 49 defined 10GBASE-R with Clause 73
+ autonegotiation. Please refer to the IEEE standard for further
+ information.
+
+ Note: due to legacy usage, some 10GBASE-R usage incorrectly makes
+ use of this definition.
Pause frames / flow control
===========================
diff --git a/Documentation/networking/sfp-phylink.rst b/Documentation/networking/sfp-phylink.rst
index a5e00a1..d753a30 100644
--- a/Documentation/networking/sfp-phylink.rst
+++ b/Documentation/networking/sfp-phylink.rst
@@ -251,7 +251,8 @@
phylink_mac_change(priv->phylink, link_is_up);
where ``link_is_up`` is true if the link is currently up or false
- otherwise.
+ otherwise. If a MAC is unable to provide these interrupts, then
+ it should set ``priv->phylink_config.pcs_poll = true;`` in step 9.
11. Verify that the driver does not call::
diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst
index 799580a..5d54946 100644
--- a/Documentation/process/embargoed-hardware-issues.rst
+++ b/Documentation/process/embargoed-hardware-issues.rst
@@ -255,7 +255,7 @@
Red Hat Josh Poimboeuf <jpoimboe@redhat.com>
SUSE Jiri Kosina <jkosina@suse.cz>
- Amazon
+ Amazon Peter Bowen <pzb@amzn.com>
Google Kees Cook <keescook@chromium.org>
============= ========================================================
diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst
index 21aa7d5..6399d92 100644
--- a/Documentation/process/index.rst
+++ b/Documentation/process/index.rst
@@ -60,6 +60,7 @@
volatile-considered-harmful
botching-up-ioctls
clang-format
+ ../riscv/patch-acceptance
.. only:: subproject and html
diff --git a/Documentation/riscv/index.rst b/Documentation/riscv/index.rst
index 215fd3c..fa33bffd 100644
--- a/Documentation/riscv/index.rst
+++ b/Documentation/riscv/index.rst
@@ -7,6 +7,7 @@
boot-image-header
pmu
+ patch-acceptance
.. only:: subproject and html
diff --git a/Documentation/riscv/patch-acceptance.rst b/Documentation/riscv/patch-acceptance.rst
new file mode 100644
index 0000000..dfe0ac5
--- /dev/null
+++ b/Documentation/riscv/patch-acceptance.rst
@@ -0,0 +1,35 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+arch/riscv maintenance guidelines for developers
+================================================
+
+Overview
+--------
+The RISC-V instruction set architecture is developed in the open:
+in-progress drafts are available for all to review and to experiment
+with implementations. New module or extension drafts can change
+during the development process - sometimes in ways that are
+incompatible with previous drafts. This flexibility can present a
+challenge for RISC-V Linux maintenance. Linux maintainers disapprove
+of churn, and the Linux development process prefers well-reviewed and
+tested code over experimental code. We wish to extend these same
+principles to the RISC-V-related code that will be accepted for
+inclusion in the kernel.
+
+Submit Checklist Addendum
+-------------------------
+We'll only accept patches for new modules or extensions if the
+specifications for those modules or extensions are listed as being
+"Frozen" or "Ratified" by the RISC-V Foundation. (Developers may, of
+course, maintain their own Linux kernel trees that contain code for
+any draft extensions that they wish.)
+
+Additionally, the RISC-V specification allows implementors to create
+their own custom extensions. These custom extensions aren't required
+to go through any review or ratification process by the RISC-V
+Foundation. To avoid the maintenance complexity and potential
+performance impact of adding kernel code for implementor-specific
+RISC-V extensions, we'll only to accept patches for extensions that
+have been officially frozen or ratified by the RISC-V Foundation.
+(Implementors, may, of course, maintain their own Linux kernel trees
+containing code for any custom extensions that they wish.)
diff --git a/MAINTAINERS b/MAINTAINERS
index 34de478..1726b4e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -720,7 +720,7 @@
F: drivers/i2c/busses/i2c-altera.c
ALTERA MAILBOX DRIVER
-M: Ley Foon Tan <lftan@altera.com>
+M: Ley Foon Tan <ley.foon.tan@intel.com>
L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
S: Maintained
F: drivers/mailbox/mailbox-altera.c
@@ -1407,7 +1407,7 @@
ARM/ACTIONS SEMI ARCHITECTURE
M: Andreas Färber <afaerber@suse.de>
-R: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
N: owl
@@ -3150,7 +3150,7 @@
F: arch/mips/net/
BPF JIT for NFP NICs
-M: Jakub Kicinski <jakub.kicinski@netronome.com>
+M: Jakub Kicinski <kuba@kernel.org>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
S: Supported
@@ -4848,6 +4848,7 @@
F: net/core/devlink.c
F: include/net/devlink.h
F: include/uapi/linux/devlink.h
+F: Documentation/networking/devlink
DIALOG SEMICONDUCTOR DRIVERS
M: Support Opensource <support.opensource@diasemi.com>
@@ -6197,6 +6198,7 @@
M: Andrew Lunn <andrew@lunn.ch>
M: Florian Fainelli <f.fainelli@gmail.com>
M: Heiner Kallweit <hkallweit1@gmail.com>
+R: Russell King <linux@armlinux.org.uk>
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/ABI/testing/sysfs-class-net-phydev
@@ -8569,7 +8571,7 @@
F: drivers/platform/x86/intel-vbtn.c
INTEL WIRELESS 3945ABG/BG, 4965AGN (iwlegacy)
-M: Stanislaw Gruszka <sgruszka@redhat.com>
+M: Stanislaw Gruszka <stf_xl@wp.pl>
L: linux-wireless@vger.kernel.org
S: Supported
F: drivers/net/wireless/intel/iwlegacy/
@@ -9889,7 +9891,7 @@
F: drivers/net/dsa/mv88e6xxx/
F: include/linux/platform_data/mv88e6xxx.h
F: Documentation/devicetree/bindings/net/dsa/marvell.txt
-F: Documentation/networking/devlink-params-mv88e6xxx.txt
+F: Documentation/networking/devlink/mv88e6xxx.rst
MARVELL ARMADA DRM SUPPORT
M: Russell King <linux@armlinux.org.uk>
@@ -11431,7 +11433,7 @@
F: net/netrom/
NETRONOME ETHERNET DRIVERS
-M: Jakub Kicinski <jakub.kicinski@netronome.com>
+M: Jakub Kicinski <kuba@kernel.org>
L: oss-drivers@netronome.com
S: Maintained
F: drivers/net/ethernet/netronome/
@@ -11460,8 +11462,8 @@
L: netdev@vger.kernel.org
W: http://www.linuxfoundation.org/en/Net
Q: http://patchwork.ozlabs.org/project/netdev/list/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
S: Odd Fixes
F: Documentation/devicetree/bindings/net/
F: drivers/net/
@@ -11499,11 +11501,12 @@
NETWORKING [GENERAL]
M: "David S. Miller" <davem@davemloft.net>
+M: Jakub Kicinski <kuba@kernel.org>
L: netdev@vger.kernel.org
W: http://www.linuxfoundation.org/en/Net
Q: http://patchwork.ozlabs.org/project/netdev/list/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
B: mailto:netdev@vger.kernel.org
S: Maintained
F: net/
@@ -11548,7 +11551,7 @@
M: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
M: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
L: netdev@vger.kernel.org
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
S: Maintained
F: net/ipv4/
F: net/ipv6/
@@ -11573,6 +11576,18 @@
F: net/netfilter/xt_CONNSECMARK.c
F: net/netfilter/xt_SECMARK.c
+NETWORKING [MPTCP]
+M: Mat Martineau <mathew.j.martineau@linux.intel.com>
+M: Matthieu Baerts <matthieu.baerts@tessares.net>
+L: netdev@vger.kernel.org
+L: mptcp@lists.01.org
+W: https://github.com/multipath-tcp/mptcp_net-next/wiki
+B: https://github.com/multipath-tcp/mptcp_net-next/issues
+S: Maintained
+F: include/net/mptcp.h
+F: net/mptcp/
+F: tools/testing/selftests/net/mptcp/
+
NETWORKING [TCP]
M: Eric Dumazet <edumazet@google.com>
L: netdev@vger.kernel.org
@@ -11591,7 +11606,7 @@
M: Aviad Yehezkel <aviadye@mellanox.com>
M: John Fastabend <john.fastabend@gmail.com>
M: Daniel Borkmann <daniel@iogearbox.net>
-M: Jakub Kicinski <jakub.kicinski@netronome.com>
+M: Jakub Kicinski <kuba@kernel.org>
L: netdev@vger.kernel.org
S: Maintained
F: net/tls/*
@@ -11603,7 +11618,7 @@
Q: http://patchwork.kernel.org/project/linux-wireless/list/
NETDEVSIM
-M: Jakub Kicinski <jakub.kicinski@netronome.com>
+M: Jakub Kicinski <kuba@kernel.org>
S: Maintained
F: drivers/net/netdevsim/*
@@ -11680,7 +11695,7 @@
F: drivers/scsi/nsp32*
NIOS2 ARCHITECTURE
-M: Ley Foon Tan <lftan@altera.com>
+M: Ley Foon Tan <ley.foon.tan@intel.com>
L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
T: git git://git.kernel.org/pub/scm/linux/kernel/git/lftan/nios2.git
S: Maintained
@@ -12564,7 +12579,7 @@
F: drivers/pci/controller/pci-aardvark.c
PCI DRIVER FOR ALTERA PCIE IP
-M: Ley Foon Tan <lftan@altera.com>
+M: Ley Foon Tan <ley.foon.tan@intel.com>
L: rfi@lists.rocketboards.org (moderated for non-subscribers)
L: linux-pci@vger.kernel.org
S: Supported
@@ -12743,7 +12758,7 @@
F: Documentation/PCI/pci-error-recovery.rst
PCI MSI DRIVER FOR ALTERA MSI IP
-M: Ley Foon Tan <lftan@altera.com>
+M: Ley Foon Tan <ley.foon.tan@intel.com>
L: rfi@lists.rocketboards.org (moderated for non-subscribers)
L: linux-pci@vger.kernel.org
S: Supported
@@ -13686,7 +13701,6 @@
QUALCOMM ETHQOS ETHERNET DRIVER
M: Vinod Koul <vkoul@kernel.org>
-M: Niklas Cassel <niklas.cassel@linaro.org>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -13828,7 +13842,7 @@
F: arch/mips/ralink
RALINK RT2X00 WIRELESS LAN DRIVER
-M: Stanislaw Gruszka <sgruszka@redhat.com>
+M: Stanislaw Gruszka <stf_xl@wp.pl>
M: Helmut Schaa <helmut.schaa@googlemail.com>
L: linux-wireless@vger.kernel.org
S: Maintained
@@ -14128,6 +14142,7 @@
M: Palmer Dabbelt <palmer@dabbelt.com>
M: Albert Ou <aou@eecs.berkeley.edu>
L: linux-riscv@lists.infradead.org
+P: Documentation/riscv/patch-acceptance.rst
T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git
S: Supported
F: arch/riscv/
@@ -14555,8 +14570,6 @@
SAMSUNG SXGBE DRIVERS
M: Byungho An <bh74.an@samsung.com>
-M: Girish K S <ks.giri@samsung.com>
-M: Vipul Pandya <vipul.pandya@samsung.com>
S: Supported
L: netdev@vger.kernel.org
F: drivers/net/ethernet/samsung/sxgbe/
@@ -15777,6 +15790,7 @@
L: netdev@vger.kernel.org
W: http://www.stlinux.com
S: Supported
+F: Documentation/networking/device_drivers/stmicro/
F: drivers/net/ethernet/stmicro/stmmac/
SUN3/3X
@@ -16610,7 +16624,7 @@
F: tools/testing/selftests/timers/
TIPC NETWORK LAYER
-M: Jon Maloy <jon.maloy@ericsson.com>
+M: Jon Maloy <jmaloy@redhat.com>
M: Ying Xue <ying.xue@windriver.com>
L: netdev@vger.kernel.org (core kernel code)
L: tipc-discussion@lists.sourceforge.net (user apps, general discussion)
@@ -18060,7 +18074,7 @@
M: Alexei Starovoitov <ast@kernel.org>
M: Daniel Borkmann <daniel@iogearbox.net>
M: David S. Miller <davem@davemloft.net>
-M: Jakub Kicinski <jakub.kicinski@netronome.com>
+M: Jakub Kicinski <kuba@kernel.org>
M: Jesper Dangaard Brouer <hawk@kernel.org>
M: John Fastabend <john.fastabend@gmail.com>
L: netdev@vger.kernel.org
diff --git a/Makefile b/Makefile
index b99d95d..c50ef91 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 5
PATCHLEVEL = 5
SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc7
NAME = Kleptomaniac Octopus
# *DOCUMENTATION*
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index 41b16f2..0b8b63d 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -162,7 +162,7 @@
#endif
#ifdef CONFIG_ARC_HAS_ACCL_REGS
- ST2 r58, r59, PT_sp + 12
+ ST2 r58, r59, PT_r58
#endif
.endm
@@ -172,8 +172,8 @@
LD2 gp, fp, PT_r26 ; gp (r26), fp (r27)
- ld r12, [sp, PT_sp + 4]
- ld r30, [sp, PT_sp + 8]
+ ld r12, [sp, PT_r12]
+ ld r30, [sp, PT_r30]
; Restore SP (into AUX_USER_SP) only if returning to U mode
; - for K mode, it will be implicitly restored as stack is unwound
@@ -190,7 +190,7 @@
#endif
#ifdef CONFIG_ARC_HAS_ACCL_REGS
- LD2 r58, r59, PT_sp + 12
+ LD2 r58, r59, PT_r58
#endif
.endm
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
index 9a74ce7..30ac40f 100644
--- a/arch/arc/include/asm/hugepage.h
+++ b/arch/arc/include/asm/hugepage.h
@@ -8,7 +8,6 @@
#define _ASM_ARC_HUGEPAGE_H
#include <linux/types.h>
-#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
static inline pte_t pmd_pte(pmd_t pmd)
diff --git a/arch/arc/kernel/asm-offsets.c b/arch/arc/kernel/asm-offsets.c
index 1f621e4..c783bcd 100644
--- a/arch/arc/kernel/asm-offsets.c
+++ b/arch/arc/kernel/asm-offsets.c
@@ -66,7 +66,15 @@ int main(void)
DEFINE(SZ_CALLEE_REGS, sizeof(struct callee_regs));
DEFINE(SZ_PT_REGS, sizeof(struct pt_regs));
- DEFINE(PT_user_r25, offsetof(struct pt_regs, user_r25));
+
+#ifdef CONFIG_ISA_ARCV2
+ OFFSET(PT_r12, pt_regs, r12);
+ OFFSET(PT_r30, pt_regs, r30);
+#endif
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+ OFFSET(PT_r58, pt_regs, r58);
+ OFFSET(PT_r59, pt_regs, r59);
+#endif
return 0;
}
diff --git a/arch/arc/plat-eznps/Kconfig b/arch/arc/plat-eznps/Kconfig
index a376a50..a931d0a 100644
--- a/arch/arc/plat-eznps/Kconfig
+++ b/arch/arc/plat-eznps/Kconfig
@@ -7,7 +7,7 @@
menuconfig ARC_PLAT_EZNPS
bool "\"EZchip\" ARC dev platform"
select CPU_BIG_ENDIAN
- select CLKSRC_NPS
+ select CLKSRC_NPS if !PHYS_ADDR_T_64BIT
select EZNPS_GIC
select EZCHIP_NPS_MANAGEMENT_ENET if ETHERNET
help
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ba75e36..96dab76 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -72,6 +72,7 @@
select HAVE_ARM_SMCCC if CPU_V7
select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32
select HAVE_CONTEXT_TRACKING
+ select HAVE_COPY_THREAD_TLS
select HAVE_C_RECORDMCOUNT
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS if MMU
diff --git a/arch/arm/boot/dts/am335x-boneblack-common.dtsi b/arch/arm/boot/dts/am335x-boneblack-common.dtsi
index 7ad0798..91f93bc 100644
--- a/arch/arm/boot/dts/am335x-boneblack-common.dtsi
+++ b/arch/arm/boot/dts/am335x-boneblack-common.dtsi
@@ -131,6 +131,11 @@ &mcasp0 {
};
/ {
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0x80000000 0x20000000>; /* 512 MB */
+ };
+
clk_mcasp0_fixed: clk_mcasp0_fixed {
#clock-cells = <0>;
compatible = "fixed-clock";
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index 078cb47..a6fbc08 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -848,6 +848,7 @@ &spi0 {
pinctrl-names = "default", "sleep";
pinctrl-0 = <&spi0_pins_default>;
pinctrl-1 = <&spi0_pins_sleep>;
+ ti,pindir-d0-out-d1-in = <1>;
};
&spi1 {
@@ -855,6 +856,7 @@ &spi1 {
pinctrl-names = "default", "sleep";
pinctrl-0 = <&spi1_pins_default>;
pinctrl-1 = <&spi1_pins_sleep>;
+ ti,pindir-d0-out-d1-in = <1>;
};
&usb2_phy1 {
diff --git a/arch/arm/boot/dts/am571x-idk.dts b/arch/arm/boot/dts/am571x-idk.dts
index 820ce3b..669559c 100644
--- a/arch/arm/boot/dts/am571x-idk.dts
+++ b/arch/arm/boot/dts/am571x-idk.dts
@@ -167,11 +167,7 @@ mbox_ipu2_ipc3x: mbox_ipu2_ipc3x {
&pcie1_rc {
status = "okay";
- gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
-};
-
-&pcie1_ep {
- gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
+ gpios = <&gpio5 18 GPIO_ACTIVE_HIGH>;
};
&mmc1 {
diff --git a/arch/arm/boot/dts/am572x-idk-common.dtsi b/arch/arm/boot/dts/am572x-idk-common.dtsi
index a064f13..ddf1236 100644
--- a/arch/arm/boot/dts/am572x-idk-common.dtsi
+++ b/arch/arm/boot/dts/am572x-idk-common.dtsi
@@ -147,10 +147,6 @@ &pcie1_rc {
gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
};
-&pcie1_ep {
- gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
-};
-
&mailbox5 {
status = "okay";
mbox_ipu1_ipc3x: mbox_ipu1_ipc3x {
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
index bc76f17..a813a0c 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
@@ -29,6 +29,27 @@ memory@0 {
reg = <0x0 0x80000000 0x0 0x80000000>;
};
+ main_12v0: fixedregulator-main_12v0 {
+ /* main supply */
+ compatible = "regulator-fixed";
+ regulator-name = "main_12v0";
+ regulator-min-microvolt = <12000000>;
+ regulator-max-microvolt = <12000000>;
+ regulator-always-on;
+ regulator-boot-on;
+ };
+
+ evm_5v0: fixedregulator-evm_5v0 {
+ /* Output of TPS54531D */
+ compatible = "regulator-fixed";
+ regulator-name = "evm_5v0";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ vin-supply = <&main_12v0>;
+ regulator-always-on;
+ regulator-boot-on;
+ };
+
vdd_3v3: fixedregulator-vdd_3v3 {
compatible = "regulator-fixed";
regulator-name = "vdd_3v3";
@@ -547,10 +568,6 @@ &pcie1_rc {
gpios = <&gpio2 8 GPIO_ACTIVE_LOW>;
};
-&pcie1_ep {
- gpios = <&gpio2 8 GPIO_ACTIVE_LOW>;
-};
-
&mcasp3 {
#sound-dai-cells = <0>;
assigned-clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>;
diff --git a/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts b/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts
index c1c9cd3..13f7aef 100644
--- a/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts
+++ b/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts
@@ -258,9 +258,9 @@ fan@3 {
};
};
- pca0: pca9552@60 {
+ pca0: pca9552@61 {
compatible = "nxp,pca9552";
- reg = <0x60>;
+ reg = <0x61>;
#address-cells = <1>;
#size-cells = <0>;
@@ -521,371 +521,6 @@ &i2c12 {
&i2c13 {
status = "okay";
-};
-
-&i2c14 {
- status = "okay";
-};
-
-&i2c15 {
- status = "okay";
-};
-
-&i2c0 {
- status = "okay";
-};
-
-&i2c1 {
- status = "okay";
-};
-
-&i2c2 {
- status = "okay";
-};
-
-&i2c3 {
- status = "okay";
-
- power-supply@68 {
- compatible = "ibm,cffps2";
- reg = <0x68>;
- };
-
- power-supply@69 {
- compatible = "ibm,cffps2";
- reg = <0x69>;
- };
-
- power-supply@6a {
- compatible = "ibm,cffps2";
- reg = <0x6a>;
- };
-
- power-supply@6b {
- compatible = "ibm,cffps2";
- reg = <0x6b>;
- };
-};
-
-&i2c4 {
- status = "okay";
-
- tmp275@48 {
- compatible = "ti,tmp275";
- reg = <0x48>;
- };
-
- tmp275@49 {
- compatible = "ti,tmp275";
- reg = <0x49>;
- };
-
- tmp275@4a {
- compatible = "ti,tmp275";
- reg = <0x4a>;
- };
-};
-
-&i2c5 {
- status = "okay";
-
- tmp275@48 {
- compatible = "ti,tmp275";
- reg = <0x48>;
- };
-
- tmp275@49 {
- compatible = "ti,tmp275";
- reg = <0x49>;
- };
-};
-
-&i2c6 {
- status = "okay";
-
- tmp275@48 {
- compatible = "ti,tmp275";
- reg = <0x48>;
- };
-
- tmp275@4a {
- compatible = "ti,tmp275";
- reg = <0x4a>;
- };
-
- tmp275@4b {
- compatible = "ti,tmp275";
- reg = <0x4b>;
- };
-};
-
-&i2c7 {
- status = "okay";
-
- si7021-a20@20 {
- compatible = "silabs,si7020";
- reg = <0x20>;
- };
-
- tmp275@48 {
- compatible = "ti,tmp275";
- reg = <0x48>;
- };
-
- max31785@52 {
- compatible = "maxim,max31785a";
- reg = <0x52>;
- #address-cells = <1>;
- #size-cells = <0>;
-
- fan@0 {
- compatible = "pmbus-fan";
- reg = <0>;
- tach-pulses = <2>;
- };
-
- fan@1 {
- compatible = "pmbus-fan";
- reg = <1>;
- tach-pulses = <2>;
- };
-
- fan@2 {
- compatible = "pmbus-fan";
- reg = <2>;
- tach-pulses = <2>;
- };
-
- fan@3 {
- compatible = "pmbus-fan";
- reg = <3>;
- tach-pulses = <2>;
- };
- };
-
- pca0: pca9552@60 {
- compatible = "nxp,pca9552";
- reg = <0x60>;
- #address-cells = <1>;
- #size-cells = <0>;
-
- gpio-controller;
- #gpio-cells = <2>;
-
- gpio@0 {
- reg = <0>;
- };
-
- gpio@1 {
- reg = <1>;
- };
-
- gpio@2 {
- reg = <2>;
- };
-
- gpio@3 {
- reg = <3>;
- };
-
- gpio@4 {
- reg = <4>;
- };
-
- gpio@5 {
- reg = <5>;
- };
-
- gpio@6 {
- reg = <6>;
- };
-
- gpio@7 {
- reg = <7>;
- };
-
- gpio@8 {
- reg = <8>;
- };
-
- gpio@9 {
- reg = <9>;
- };
-
- gpio@10 {
- reg = <10>;
- };
-
- gpio@11 {
- reg = <11>;
- };
-
- gpio@12 {
- reg = <12>;
- };
-
- gpio@13 {
- reg = <13>;
- };
-
- gpio@14 {
- reg = <14>;
- };
-
- gpio@15 {
- reg = <15>;
- };
- };
-
- dps: dps310@76 {
- compatible = "infineon,dps310";
- reg = <0x76>;
- #io-channel-cells = <0>;
- };
-};
-
-&i2c8 {
- status = "okay";
-
- ucd90320@b {
- compatible = "ti,ucd90160";
- reg = <0x0b>;
- };
-
- ucd90320@c {
- compatible = "ti,ucd90160";
- reg = <0x0c>;
- };
-
- ucd90320@11 {
- compatible = "ti,ucd90160";
- reg = <0x11>;
- };
-
- rtc@32 {
- compatible = "epson,rx8900";
- reg = <0x32>;
- };
-
- tmp275@48 {
- compatible = "ti,tmp275";
- reg = <0x48>;
- };
-
- tmp275@4a {
- compatible = "ti,tmp275";
- reg = <0x4a>;
- };
-};
-
-&i2c9 {
- status = "okay";
-
- ir35221@42 {
- compatible = "infineon,ir35221";
- reg = <0x42>;
- };
-
- ir35221@43 {
- compatible = "infineon,ir35221";
- reg = <0x43>;
- };
-
- ir35221@44 {
- compatible = "infineon,ir35221";
- reg = <0x44>;
- };
-
- tmp423a@4c {
- compatible = "ti,tmp423";
- reg = <0x4c>;
- };
-
- tmp423b@4d {
- compatible = "ti,tmp423";
- reg = <0x4d>;
- };
-
- ir35221@72 {
- compatible = "infineon,ir35221";
- reg = <0x72>;
- };
-
- ir35221@73 {
- compatible = "infineon,ir35221";
- reg = <0x73>;
- };
-
- ir35221@74 {
- compatible = "infineon,ir35221";
- reg = <0x74>;
- };
-};
-
-&i2c10 {
- status = "okay";
-
- ir35221@42 {
- compatible = "infineon,ir35221";
- reg = <0x42>;
- };
-
- ir35221@43 {
- compatible = "infineon,ir35221";
- reg = <0x43>;
- };
-
- ir35221@44 {
- compatible = "infineon,ir35221";
- reg = <0x44>;
- };
-
- tmp423a@4c {
- compatible = "ti,tmp423";
- reg = <0x4c>;
- };
-
- tmp423b@4d {
- compatible = "ti,tmp423";
- reg = <0x4d>;
- };
-
- ir35221@72 {
- compatible = "infineon,ir35221";
- reg = <0x72>;
- };
-
- ir35221@73 {
- compatible = "infineon,ir35221";
- reg = <0x73>;
- };
-
- ir35221@74 {
- compatible = "infineon,ir35221";
- reg = <0x74>;
- };
-};
-
-&i2c11 {
- status = "okay";
-
- tmp275@48 {
- compatible = "ti,tmp275";
- reg = <0x48>;
- };
-
- tmp275@49 {
- compatible = "ti,tmp275";
- reg = <0x49>;
- };
-};
-
-&i2c12 {
- status = "okay";
-};
-
-&i2c13 {
- status = "okay";
eeprom@50 {
compatible = "atmel,24c64";
diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts b/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts
index f02de4a..ff49ec7 100644
--- a/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts
+++ b/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts
@@ -122,37 +122,6 @@ flash@0 {
};
};
-&fmc {
- status = "okay";
- flash@0 {
- status = "okay";
- m25p,fast-read;
- label = "bmc";
- spi-max-frequency = <50000000>;
-#include "openbmc-flash-layout-128.dtsi"
- };
-
- flash@1 {
- status = "okay";
- m25p,fast-read;
- label = "alt-bmc";
- spi-max-frequency = <50000000>;
- };
-};
-
-&spi1 {
- status = "okay";
- pinctrl-names = "default";
- pinctrl-0 = <&pinctrl_spi1_default>;
-
- flash@0 {
- status = "okay";
- m25p,fast-read;
- label = "pnor";
- spi-max-frequency = <100000000>;
- };
-};
-
&mac2 {
status = "okay";
pinctrl-names = "default";
@@ -165,6 +134,11 @@ &mac2 {
&emmc {
status = "okay";
+};
+
+&fsim0 {
+ status = "okay";
+
#address-cells = <2>;
#size-cells = <0>;
@@ -820,373 +794,6 @@ &wdt2 {
status = "okay";
};
-&i2c0 {
- status = "okay";
-};
-
-&i2c1 {
- status = "okay";
-};
-
-&i2c2 {
- status = "okay";
-};
-
-&i2c3 {
- status = "okay";
-
- bmp: bmp280@77 {
- compatible = "bosch,bmp280";
- reg = <0x77>;
- #io-channel-cells = <1>;
- };
-
- max31785@52 {
- compatible = "maxim,max31785a";
- reg = <0x52>;
- #address-cells = <1>;
- #size-cells = <0>;
-
- fan@0 {
- compatible = "pmbus-fan";
- reg = <0>;
- tach-pulses = <2>;
- maxim,fan-rotor-input = "tach";
- maxim,fan-pwm-freq = <25000>;
- maxim,fan-dual-tach;
- maxim,fan-no-watchdog;
- maxim,fan-no-fault-ramp;
- maxim,fan-ramp = <2>;
- maxim,fan-fault-pin-mon;
- };
-
- fan@1 {
- compatible = "pmbus-fan";
- reg = <1>;
- tach-pulses = <2>;
- maxim,fan-rotor-input = "tach";
- maxim,fan-pwm-freq = <25000>;
- maxim,fan-dual-tach;
- maxim,fan-no-watchdog;
- maxim,fan-no-fault-ramp;
- maxim,fan-ramp = <2>;
- maxim,fan-fault-pin-mon;
- };
-
- fan@2 {
- compatible = "pmbus-fan";
- reg = <2>;
- tach-pulses = <2>;
- maxim,fan-rotor-input = "tach";
- maxim,fan-pwm-freq = <25000>;
- maxim,fan-dual-tach;
- maxim,fan-no-watchdog;
- maxim,fan-no-fault-ramp;
- maxim,fan-ramp = <2>;
- maxim,fan-fault-pin-mon;
- };
-
- fan@3 {
- compatible = "pmbus-fan";
- reg = <3>;
- tach-pulses = <2>;
- maxim,fan-rotor-input = "tach";
- maxim,fan-pwm-freq = <25000>;
- maxim,fan-dual-tach;
- maxim,fan-no-watchdog;
- maxim,fan-no-fault-ramp;
- maxim,fan-ramp = <2>;
- maxim,fan-fault-pin-mon;
- };
- };
-
- dps: dps310@76 {
- compatible = "infineon,dps310";
- reg = <0x76>;
- #io-channel-cells = <0>;
- };
-
- pca0: pca9552@60 {
- compatible = "nxp,pca9552";
- reg = <0x60>;
- #address-cells = <1>;
- #size-cells = <0>;
-
- gpio-controller;
- #gpio-cells = <2>;
-
- gpio@0 {
- reg = <0>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@1 {
- reg = <1>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@2 {
- reg = <2>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@3 {
- reg = <3>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@4 {
- reg = <4>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@5 {
- reg = <5>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@6 {
- reg = <6>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@7 {
- reg = <7>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@8 {
- reg = <8>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@9 {
- reg = <9>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@10 {
- reg = <10>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@11 {
- reg = <11>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@12 {
- reg = <12>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@13 {
- reg = <13>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@14 {
- reg = <14>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@15 {
- reg = <15>;
- type = <PCA955X_TYPE_GPIO>;
- };
- };
-
- power-supply@68 {
- compatible = "ibm,cffps1";
- reg = <0x68>;
- };
-
- power-supply@69 {
- compatible = "ibm,cffps1";
- reg = <0x69>;
- };
-};
-
-&i2c4 {
- status = "okay";
-
- tmp423a@4c {
- compatible = "ti,tmp423";
- reg = <0x4c>;
- };
-
- ir35221@70 {
- compatible = "infineon,ir35221";
- reg = <0x70>;
- };
-
- ir35221@71 {
- compatible = "infineon,ir35221";
- reg = <0x71>;
- };
-};
-
-&i2c5 {
- status = "okay";
-
- tmp423a@4c {
- compatible = "ti,tmp423";
- reg = <0x4c>;
- };
-
- ir35221@70 {
- compatible = "infineon,ir35221";
- reg = <0x70>;
- };
-
- ir35221@71 {
- compatible = "infineon,ir35221";
- reg = <0x71>;
- };
-};
-
-&i2c7 {
- status = "okay";
-};
-
-&i2c9 {
- status = "okay";
-
- tmp275@4a {
- compatible = "ti,tmp275";
- reg = <0x4a>;
- };
-};
-
-&i2c10 {
- status = "okay";
-};
-
-&i2c11 {
- status = "okay";
-
- pca9552: pca9552@60 {
- compatible = "nxp,pca9552";
- reg = <0x60>;
- #address-cells = <1>;
- #size-cells = <0>;
- gpio-controller;
- #gpio-cells = <2>;
-
- gpio-line-names = "PS_SMBUS_RESET_N", "APSS_RESET_N",
- "GPU0_TH_OVERT_N_BUFF", "GPU1_TH_OVERT_N_BUFF",
- "GPU2_TH_OVERT_N_BUFF", "GPU3_TH_OVERT_N_BUFF",
- "GPU4_TH_OVERT_N_BUFF", "GPU5_TH_OVERT_N_BUFF",
- "GPU0_PWR_GOOD_BUFF", "GPU1_PWR_GOOD_BUFF",
- "GPU2_PWR_GOOD_BUFF", "GPU3_PWR_GOOD_BUFF",
- "GPU4_PWR_GOOD_BUFF", "GPU5_PWR_GOOD_BUFF",
- "12V_BREAKER_FLT_N", "THROTTLE_UNLATCHED_N";
-
- gpio@0 {
- reg = <0>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@1 {
- reg = <1>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@2 {
- reg = <2>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@3 {
- reg = <3>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@4 {
- reg = <4>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@5 {
- reg = <5>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@6 {
- reg = <6>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@7 {
- reg = <7>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@8 {
- reg = <8>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@9 {
- reg = <9>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@10 {
- reg = <10>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@11 {
- reg = <11>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@12 {
- reg = <12>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@13 {
- reg = <13>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@14 {
- reg = <14>;
- type = <PCA955X_TYPE_GPIO>;
- };
-
- gpio@15 {
- reg = <15>;
- type = <PCA955X_TYPE_GPIO>;
- };
- };
-
- rtc@32 {
- compatible = "epson,rx8900";
- reg = <0x32>;
- };
-
- eeprom@51 {
- compatible = "atmel,24c64";
- reg = <0x51>;
- };
-
- ucd90160@64 {
- compatible = "ti,ucd90160";
- reg = <0x64>;
- };
-};
-
-&i2c12 {
- status = "okay";
-};
-
-&i2c13 {
- status = "okay";
-};
-
&pinctrl {
/* Hog these as no driver is probed for the entire LPC block */
pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/aspeed-g6.dtsi b/arch/arm/boot/dts/aspeed-g6.dtsi
index 5f6142d..b72afba 100644
--- a/arch/arm/boot/dts/aspeed-g6.dtsi
+++ b/arch/arm/boot/dts/aspeed-g6.dtsi
@@ -163,26 +163,6 @@ flash@2 {
spi-max-frequency = <50000000>;
status = "disabled";
};
-
- fsim0: fsi@1e79b000 {
- compatible = "aspeed,ast2600-fsi-master", "fsi-master";
- reg = <0x1e79b000 0x94>;
- interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
- pinctrl-names = "default";
- pinctrl-0 = <&pinctrl_fsi1_default>;
- clocks = <&syscon ASPEED_CLK_GATE_FSICLK>;
- status = "disabled";
- };
-
- fsim1: fsi@1e79b100 {
- compatible = "aspeed,ast2600-fsi-master", "fsi-master";
- reg = <0x1e79b100 0x94>;
- interrupts = <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>;
- pinctrl-names = "default";
- pinctrl-0 = <&pinctrl_fsi2_default>;
- clocks = <&syscon ASPEED_CLK_GATE_FSICLK>;
- status = "disabled";
- };
};
mdio0: mdio@1e650000 {
@@ -595,6 +575,25 @@ i2c: bus@1e78a000 {
ranges = <0 0x1e78a000 0x1000>;
};
+ fsim0: fsi@1e79b000 {
+ compatible = "aspeed,ast2600-fsi-master", "fsi-master";
+ reg = <0x1e79b000 0x94>;
+ interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_fsi1_default>;
+ clocks = <&syscon ASPEED_CLK_GATE_FSICLK>;
+ status = "disabled";
+ };
+
+ fsim1: fsi@1e79b100 {
+ compatible = "aspeed,ast2600-fsi-master", "fsi-master";
+ reg = <0x1e79b100 0x94>;
+ interrupts = <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_fsi2_default>;
+ clocks = <&syscon ASPEED_CLK_GATE_FSICLK>;
+ status = "disabled";
+ };
};
};
};
diff --git a/arch/arm/boot/dts/imx6dl-icore-mipi.dts b/arch/arm/boot/dts/imx6dl-icore-mipi.dts
index e43bccb..d8f3821 100644
--- a/arch/arm/boot/dts/imx6dl-icore-mipi.dts
+++ b/arch/arm/boot/dts/imx6dl-icore-mipi.dts
@@ -8,7 +8,7 @@
/dts-v1/;
#include "imx6dl.dtsi"
-#include "imx6qdl-icore.dtsi"
+#include "imx6qdl-icore-1.5.dtsi"
/ {
model = "Engicam i.CoreM6 DualLite/Solo MIPI Starter Kit";
diff --git a/arch/arm/boot/dts/imx6q-dhcom-pdk2.dts b/arch/arm/boot/dts/imx6q-dhcom-pdk2.dts
index 5219553..bb74fc6 100644
--- a/arch/arm/boot/dts/imx6q-dhcom-pdk2.dts
+++ b/arch/arm/boot/dts/imx6q-dhcom-pdk2.dts
@@ -63,7 +63,7 @@ sgtl5000: codec@a {
#sound-dai-cells = <0>;
clocks = <&clk_ext_audio_codec>;
VDDA-supply = <®_3p3v>;
- VDDIO-supply = <®_3p3v>;
+ VDDIO-supply = <&sw2_reg>;
};
};
diff --git a/arch/arm/boot/dts/imx6q-dhcom-som.dtsi b/arch/arm/boot/dts/imx6q-dhcom-som.dtsi
index 845cfad..87f0aa8 100644
--- a/arch/arm/boot/dts/imx6q-dhcom-som.dtsi
+++ b/arch/arm/boot/dts/imx6q-dhcom-som.dtsi
@@ -204,7 +204,7 @@ eeprom@50 {
};
rtc@56 {
- compatible = "rv3029c2";
+ compatible = "microcrystal,rv3029";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_rtc_hw300>;
reg = <0x56>;
diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
index 71ca76a..fe59dde 100644
--- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
@@ -749,10 +749,6 @@ ®_vdd1p1 {
vin-supply = <&vgen5_reg>;
};
-®_vdd3p0 {
- vin-supply = <&sw2_reg>;
-};
-
®_vdd2p5 {
vin-supply = <&vgen5_reg>;
};
diff --git a/arch/arm/boot/dts/imx6sl-evk.dts b/arch/arm/boot/dts/imx6sl-evk.dts
index 4829aa6..bc86cfa 100644
--- a/arch/arm/boot/dts/imx6sl-evk.dts
+++ b/arch/arm/boot/dts/imx6sl-evk.dts
@@ -584,10 +584,6 @@ ®_vdd1p1 {
vin-supply = <&sw2_reg>;
};
-®_vdd3p0 {
- vin-supply = <&sw2_reg>;
-};
-
®_vdd2p5 {
vin-supply = <&sw2_reg>;
};
diff --git a/arch/arm/boot/dts/imx6sll-evk.dts b/arch/arm/boot/dts/imx6sll-evk.dts
index 3e1d32fd..5ace9e6 100644
--- a/arch/arm/boot/dts/imx6sll-evk.dts
+++ b/arch/arm/boot/dts/imx6sll-evk.dts
@@ -265,10 +265,6 @@ &pwm1 {
status = "okay";
};
-®_3p0 {
- vin-supply = <&sw2_reg>;
-};
-
&snvs_poweroff {
status = "okay";
};
diff --git a/arch/arm/boot/dts/imx6sx-sdb-reva.dts b/arch/arm/boot/dts/imx6sx-sdb-reva.dts
index f1830ed..91a7548 100644
--- a/arch/arm/boot/dts/imx6sx-sdb-reva.dts
+++ b/arch/arm/boot/dts/imx6sx-sdb-reva.dts
@@ -159,10 +159,6 @@ ®_vdd1p1 {
vin-supply = <&vgen6_reg>;
};
-®_vdd3p0 {
- vin-supply = <&sw2_reg>;
-};
-
®_vdd2p5 {
vin-supply = <&vgen6_reg>;
};
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts
index a8ee708..5a63ca6 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dts
+++ b/arch/arm/boot/dts/imx6sx-sdb.dts
@@ -141,10 +141,6 @@ ®_vdd1p1 {
vin-supply = <&vgen6_reg>;
};
-®_vdd3p0 {
- vin-supply = <&sw2_reg>;
-};
-
®_vdd2p5 {
vin-supply = <&vgen6_reg>;
};
diff --git a/arch/arm/boot/dts/imx7s-colibri.dtsi b/arch/arm/boot/dts/imx7s-colibri.dtsi
index 1fb1ec5..6d16e32 100644
--- a/arch/arm/boot/dts/imx7s-colibri.dtsi
+++ b/arch/arm/boot/dts/imx7s-colibri.dtsi
@@ -49,3 +49,7 @@ memory@80000000 {
reg = <0x80000000 0x10000000>;
};
};
+
+&gpmi {
+ status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx7ulp.dtsi b/arch/arm/boot/dts/imx7ulp.dtsi
index d37a192..ab91c98 100644
--- a/arch/arm/boot/dts/imx7ulp.dtsi
+++ b/arch/arm/boot/dts/imx7ulp.dtsi
@@ -37,10 +37,10 @@ cpus {
#address-cells = <1>;
#size-cells = <0>;
- cpu0: cpu@0 {
+ cpu0: cpu@f00 {
compatible = "arm,cortex-a7";
device_type = "cpu";
- reg = <0>;
+ reg = <0xf00>;
};
};
diff --git a/arch/arm/boot/dts/meson8.dtsi b/arch/arm/boot/dts/meson8.dtsi
index 5a7e3e5..3c534cd 100644
--- a/arch/arm/boot/dts/meson8.dtsi
+++ b/arch/arm/boot/dts/meson8.dtsi
@@ -253,7 +253,7 @@ mali: gpu@c0000 {
&aobus {
pmu: pmu@e0 {
compatible = "amlogic,meson8-pmu", "syscon";
- reg = <0xe0 0x8>;
+ reg = <0xe0 0x18>;
};
pinctrl_aobus: pinctrl@84 {
diff --git a/arch/arm/boot/dts/mmp3.dtsi b/arch/arm/boot/dts/mmp3.dtsi
index d9762de..6f48082 100644
--- a/arch/arm/boot/dts/mmp3.dtsi
+++ b/arch/arm/boot/dts/mmp3.dtsi
@@ -356,7 +356,7 @@ gcb5: gpio@d4019108 {
twsi1: i2c@d4011000 {
compatible = "mrvl,mmp-twsi";
- reg = <0xd4011000 0x1000>;
+ reg = <0xd4011000 0x70>;
interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&soc_clocks MMP2_CLK_TWSI0>;
resets = <&soc_clocks MMP2_CLK_TWSI0>;
@@ -368,7 +368,7 @@ twsi1: i2c@d4011000 {
twsi2: i2c@d4031000 {
compatible = "mrvl,mmp-twsi";
- reg = <0xd4031000 0x1000>;
+ reg = <0xd4031000 0x70>;
interrupt-parent = <&twsi_mux>;
interrupts = <0>;
clocks = <&soc_clocks MMP2_CLK_TWSI1>;
@@ -380,7 +380,7 @@ twsi2: i2c@d4031000 {
twsi3: i2c@d4032000 {
compatible = "mrvl,mmp-twsi";
- reg = <0xd4032000 0x1000>;
+ reg = <0xd4032000 0x70>;
interrupt-parent = <&twsi_mux>;
interrupts = <1>;
clocks = <&soc_clocks MMP2_CLK_TWSI2>;
@@ -392,7 +392,7 @@ twsi3: i2c@d4032000 {
twsi4: i2c@d4033000 {
compatible = "mrvl,mmp-twsi";
- reg = <0xd4033000 0x1000>;
+ reg = <0xd4033000 0x70>;
interrupt-parent = <&twsi_mux>;
interrupts = <2>;
clocks = <&soc_clocks MMP2_CLK_TWSI3>;
@@ -405,7 +405,7 @@ twsi4: i2c@d4033000 {
twsi5: i2c@d4033800 {
compatible = "mrvl,mmp-twsi";
- reg = <0xd4033800 0x1000>;
+ reg = <0xd4033800 0x70>;
interrupt-parent = <&twsi_mux>;
interrupts = <3>;
clocks = <&soc_clocks MMP2_CLK_TWSI4>;
@@ -417,7 +417,7 @@ twsi5: i2c@d4033800 {
twsi6: i2c@d4034000 {
compatible = "mrvl,mmp-twsi";
- reg = <0xd4034000 0x1000>;
+ reg = <0xd4034000 0x70>;
interrupt-parent = <&twsi_mux>;
interrupts = <4>;
clocks = <&soc_clocks MMP2_CLK_TWSI5>;
diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
index fb92850..d9be511 100644
--- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
@@ -101,7 +101,7 @@ usb-hub {
initial-mode = <1>; /* initialize in HUB mode */
disabled-ports = <1>;
intn-gpios = <&pio 7 5 GPIO_ACTIVE_HIGH>; /* PH5 */
- reset-gpios = <&pio 4 16 GPIO_ACTIVE_HIGH>; /* PE16 */
+ reset-gpios = <&pio 4 16 GPIO_ACTIVE_LOW>; /* PE16 */
connect-gpios = <&pio 4 17 GPIO_ACTIVE_HIGH>; /* PE17 */
refclk-frequency = <19200000>;
};
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index ae50203..6607fa8 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -146,10 +146,9 @@
#if !defined(ZIMAGE) && defined(CONFIG_ARM_ARCH_TIMER)
@ make CNTP_* and CNTPCT accessible from PL1
mrc p15, 0, r7, c0, c1, 1 @ ID_PFR1
- lsr r7, #16
- and r7, #0xf
- cmp r7, #1
- bne 1f
+ ubfx r7, r7, #16, #4
+ teq r7, #0
+ beq 1f
mrc p15, 4, r7, c14, c1, 0 @ CNTHCTL
orr r7, r7, #3 @ PL1PCEN | PL1PCTEN
mcr p15, 4, r7, c14, c1, 0 @ CNTHCTL
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index cea1c27..46e478f 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -226,8 +226,8 @@ void release_thread(struct task_struct *dead_task)
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
int
-copy_thread(unsigned long clone_flags, unsigned long stack_start,
- unsigned long stk_sz, struct task_struct *p)
+copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
+ unsigned long stk_sz, struct task_struct *p, unsigned long tls)
{
struct thread_info *thread = task_thread_info(p);
struct pt_regs *childregs = task_pt_regs(p);
@@ -261,7 +261,7 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
clear_ptrace_hw_breakpoint(p);
if (clone_flags & CLONE_SETTLS)
- thread->tp_value[0] = childregs->ARM_r3;
+ thread->tp_value[0] = tls;
thread->tp_value[1] = get_tpuser();
thread_notify(THREAD_NOTIFY_COPY, thread);
diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index dd427bd..02b180a 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -9,6 +9,7 @@
select PM_GENERIC_DOMAINS if PM
select PM_GENERIC_DOMAINS_OF if PM && OF
select REGMAP_MMIO
+ select RESET_CONTROLLER
select HAVE_IDE
select PINCTRL_SINGLE
diff --git a/arch/arm/mach-ixp4xx/fsg-setup.c b/arch/arm/mach-ixp4xx/fsg-setup.c
index 648932d..507ee38 100644
--- a/arch/arm/mach-ixp4xx/fsg-setup.c
+++ b/arch/arm/mach-ixp4xx/fsg-setup.c
@@ -132,6 +132,22 @@ static struct platform_device fsg_leds = {
};
/* Built-in 10/100 Ethernet MAC interfaces */
+static struct resource fsg_eth_npeb_resources[] = {
+ {
+ .start = IXP4XX_EthB_BASE_PHYS,
+ .end = IXP4XX_EthB_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct resource fsg_eth_npec_resources[] = {
+ {
+ .start = IXP4XX_EthC_BASE_PHYS,
+ .end = IXP4XX_EthC_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
static struct eth_plat_info fsg_plat_eth[] = {
{
.phy = 5,
@@ -151,12 +167,16 @@ static struct platform_device fsg_eth[] = {
.dev = {
.platform_data = fsg_plat_eth,
},
+ .num_resources = ARRAY_SIZE(fsg_eth_npeb_resources),
+ .resource = fsg_eth_npeb_resources,
}, {
.name = "ixp4xx_eth",
.id = IXP4XX_ETH_NPEC,
.dev = {
.platform_data = fsg_plat_eth + 1,
},
+ .num_resources = ARRAY_SIZE(fsg_eth_npec_resources),
+ .resource = fsg_eth_npec_resources,
}
};
diff --git a/arch/arm/mach-ixp4xx/goramo_mlr.c b/arch/arm/mach-ixp4xx/goramo_mlr.c
index a0e0b6b..07b50df 100644
--- a/arch/arm/mach-ixp4xx/goramo_mlr.c
+++ b/arch/arm/mach-ixp4xx/goramo_mlr.c
@@ -11,6 +11,7 @@
#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/pci.h>
+#include <linux/platform_data/wan_ixp4xx_hss.h>
#include <linux/serial_8250.h>
#include <asm/mach-types.h>
#include <asm/mach/arch.h>
@@ -272,6 +273,22 @@ static struct platform_device device_uarts = {
/* Built-in 10/100 Ethernet MAC interfaces */
+static struct resource eth_npeb_resources[] = {
+ {
+ .start = IXP4XX_EthB_BASE_PHYS,
+ .end = IXP4XX_EthB_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct resource eth_npec_resources[] = {
+ {
+ .start = IXP4XX_EthC_BASE_PHYS,
+ .end = IXP4XX_EthC_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
static struct eth_plat_info eth_plat[] = {
{
.phy = 0,
@@ -289,10 +306,14 @@ static struct platform_device device_eth_tab[] = {
.name = "ixp4xx_eth",
.id = IXP4XX_ETH_NPEB,
.dev.platform_data = eth_plat,
+ .num_resources = ARRAY_SIZE(eth_npeb_resources),
+ .resource = eth_npeb_resources,
}, {
.name = "ixp4xx_eth",
.id = IXP4XX_ETH_NPEC,
.dev.platform_data = eth_plat + 1,
+ .num_resources = ARRAY_SIZE(eth_npec_resources),
+ .resource = eth_npec_resources,
}
};
@@ -405,6 +426,9 @@ static void __init gmlr_init(void)
if (hw_bits & CFG_HW_HAS_HSS1)
device_tab[devices++] = &device_hss_tab[1]; /* max index 5 */
+ hss_plat[0].timer_freq = ixp4xx_timer_freq;
+ hss_plat[1].timer_freq = ixp4xx_timer_freq;
+
gpio_request(GPIO_SCL, "SCL/clock");
gpio_request(GPIO_SDA, "SDA/data");
gpio_request(GPIO_STR, "strobe");
diff --git a/arch/arm/mach-ixp4xx/include/mach/platform.h b/arch/arm/mach-ixp4xx/include/mach/platform.h
index 342acbe..6d403fe 100644
--- a/arch/arm/mach-ixp4xx/include/mach/platform.h
+++ b/arch/arm/mach-ixp4xx/include/mach/platform.h
@@ -15,6 +15,7 @@
#ifndef __ASSEMBLY__
#include <linux/reboot.h>
+#include <linux/platform_data/eth_ixp4xx.h>
#include <asm/types.h>
@@ -92,27 +93,6 @@ struct ixp4xx_pata_data {
void __iomem *cs1;
};
-#define IXP4XX_ETH_NPEA 0x00
-#define IXP4XX_ETH_NPEB 0x10
-#define IXP4XX_ETH_NPEC 0x20
-
-/* Information about built-in Ethernet MAC interfaces */
-struct eth_plat_info {
- u8 phy; /* MII PHY ID, 0 - 31 */
- u8 rxq; /* configurable, currently 0 - 31 only */
- u8 txreadyq;
- u8 hwaddr[6];
-};
-
-/* Information about built-in HSS (synchronous serial) interfaces */
-struct hss_plat_info {
- int (*set_clock)(int port, unsigned int clock_type);
- int (*open)(int port, void *pdev,
- void (*set_carrier_cb)(void *pdev, int carrier));
- void (*close)(int port, void *pdev);
- u8 txreadyq;
-};
-
/*
* Frequency of clock used for primary clocksource
*/
diff --git a/arch/arm/mach-ixp4xx/ixdp425-setup.c b/arch/arm/mach-ixp4xx/ixdp425-setup.c
index 6f0f7ed..45d5b72 100644
--- a/arch/arm/mach-ixp4xx/ixdp425-setup.c
+++ b/arch/arm/mach-ixp4xx/ixdp425-setup.c
@@ -187,6 +187,22 @@ static struct platform_device ixdp425_uart = {
};
/* Built-in 10/100 Ethernet MAC interfaces */
+static struct resource ixp425_npeb_resources[] = {
+ {
+ .start = IXP4XX_EthB_BASE_PHYS,
+ .end = IXP4XX_EthB_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct resource ixp425_npec_resources[] = {
+ {
+ .start = IXP4XX_EthC_BASE_PHYS,
+ .end = IXP4XX_EthC_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
static struct eth_plat_info ixdp425_plat_eth[] = {
{
.phy = 0,
@@ -204,10 +220,14 @@ static struct platform_device ixdp425_eth[] = {
.name = "ixp4xx_eth",
.id = IXP4XX_ETH_NPEB,
.dev.platform_data = ixdp425_plat_eth,
+ .num_resources = ARRAY_SIZE(ixp425_npeb_resources),
+ .resource = ixp425_npeb_resources,
}, {
.name = "ixp4xx_eth",
.id = IXP4XX_ETH_NPEC,
.dev.platform_data = ixdp425_plat_eth + 1,
+ .num_resources = ARRAY_SIZE(ixp425_npec_resources),
+ .resource = ixp425_npec_resources,
}
};
diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c
index c142cfa..6959ad2 100644
--- a/arch/arm/mach-ixp4xx/nas100d-setup.c
+++ b/arch/arm/mach-ixp4xx/nas100d-setup.c
@@ -165,6 +165,14 @@ static struct platform_device nas100d_uart = {
};
/* Built-in 10/100 Ethernet MAC interfaces */
+static struct resource nas100d_eth_resources[] = {
+ {
+ .start = IXP4XX_EthB_BASE_PHYS,
+ .end = IXP4XX_EthB_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
static struct eth_plat_info nas100d_plat_eth[] = {
{
.phy = 0,
@@ -178,6 +186,8 @@ static struct platform_device nas100d_eth[] = {
.name = "ixp4xx_eth",
.id = IXP4XX_ETH_NPEB,
.dev.platform_data = nas100d_plat_eth,
+ .num_resources = ARRAY_SIZE(nas100d_eth_resources),
+ .resource = nas100d_eth_resources,
}
};
diff --git a/arch/arm/mach-ixp4xx/nslu2-setup.c b/arch/arm/mach-ixp4xx/nslu2-setup.c
index ee1877f..a428bb9 100644
--- a/arch/arm/mach-ixp4xx/nslu2-setup.c
+++ b/arch/arm/mach-ixp4xx/nslu2-setup.c
@@ -185,6 +185,14 @@ static struct platform_device nslu2_uart = {
};
/* Built-in 10/100 Ethernet MAC interfaces */
+static struct resource nslu2_eth_resources[] = {
+ {
+ .start = IXP4XX_EthB_BASE_PHYS,
+ .end = IXP4XX_EthB_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
static struct eth_plat_info nslu2_plat_eth[] = {
{
.phy = 1,
@@ -198,6 +206,8 @@ static struct platform_device nslu2_eth[] = {
.name = "ixp4xx_eth",
.id = IXP4XX_ETH_NPEB,
.dev.platform_data = nslu2_plat_eth,
+ .num_resources = ARRAY_SIZE(nslu2_eth_resources),
+ .resource = nslu2_eth_resources,
}
};
diff --git a/arch/arm/mach-ixp4xx/omixp-setup.c b/arch/arm/mach-ixp4xx/omixp-setup.c
index 6ed5a9a..8f2b8c4 100644
--- a/arch/arm/mach-ixp4xx/omixp-setup.c
+++ b/arch/arm/mach-ixp4xx/omixp-setup.c
@@ -170,6 +170,22 @@ static struct platform_device mic256_leds = {
};
/* Built-in 10/100 Ethernet MAC interfaces */
+static struct resource ixp425_npeb_resources[] = {
+ {
+ .start = IXP4XX_EthB_BASE_PHYS,
+ .end = IXP4XX_EthB_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct resource ixp425_npec_resources[] = {
+ {
+ .start = IXP4XX_EthC_BASE_PHYS,
+ .end = IXP4XX_EthC_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
static struct eth_plat_info ixdp425_plat_eth[] = {
{
.phy = 0,
@@ -187,10 +203,14 @@ static struct platform_device ixdp425_eth[] = {
.name = "ixp4xx_eth",
.id = IXP4XX_ETH_NPEB,
.dev.platform_data = ixdp425_plat_eth,
+ .num_resources = ARRAY_SIZE(ixp425_npeb_resources),
+ .resource = ixp425_npeb_resources,
}, {
.name = "ixp4xx_eth",
.id = IXP4XX_ETH_NPEC,
.dev.platform_data = ixdp425_plat_eth + 1,
+ .num_resources = ARRAY_SIZE(ixp425_npec_resources),
+ .resource = ixp425_npec_resources,
},
};
diff --git a/arch/arm/mach-ixp4xx/vulcan-setup.c b/arch/arm/mach-ixp4xx/vulcan-setup.c
index d2ebb7c..e506d2a 100644
--- a/arch/arm/mach-ixp4xx/vulcan-setup.c
+++ b/arch/arm/mach-ixp4xx/vulcan-setup.c
@@ -124,6 +124,22 @@ static struct platform_device vulcan_uart = {
.num_resources = ARRAY_SIZE(vulcan_uart_resources),
};
+static struct resource vulcan_npeb_resources[] = {
+ {
+ .start = IXP4XX_EthB_BASE_PHYS,
+ .end = IXP4XX_EthB_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct resource vulcan_npec_resources[] = {
+ {
+ .start = IXP4XX_EthC_BASE_PHYS,
+ .end = IXP4XX_EthC_BASE_PHYS + 0x0fff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
static struct eth_plat_info vulcan_plat_eth[] = {
[0] = {
.phy = 0,
@@ -144,6 +160,8 @@ static struct platform_device vulcan_eth[] = {
.dev = {
.platform_data = &vulcan_plat_eth[0],
},
+ .num_resources = ARRAY_SIZE(vulcan_npeb_resources),
+ .resource = vulcan_npeb_resources,
},
[1] = {
.name = "ixp4xx_eth",
@@ -151,6 +169,8 @@ static struct platform_device vulcan_eth[] = {
.dev = {
.platform_data = &vulcan_plat_eth[1],
},
+ .num_resources = ARRAY_SIZE(vulcan_npec_resources),
+ .resource = vulcan_npec_resources,
},
};
diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c
index 110dcb3..c65cfc1 100644
--- a/arch/arm/mach-mmp/time.c
+++ b/arch/arm/mach-mmp/time.c
@@ -207,7 +207,7 @@ static int __init mmp_dt_init_timer(struct device_node *np)
ret = clk_prepare_enable(clk);
if (ret)
return ret;
- rate = clk_get_rate(clk) / 2;
+ rate = clk_get_rate(clk);
} else if (cpu_is_pj4()) {
rate = 6500000;
} else {
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index ad08d47..dca7d06 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -95,6 +95,7 @@
bool
select ARCH_HAS_BANDGAP
select ARCH_HAS_HOLES_MEMORYMODEL
+ select ARCH_HAS_RESET_CONTROLLER
select ARCH_OMAP
select CLKSRC_MMIO
select GENERIC_IRQ_CHIP
@@ -105,11 +106,11 @@
select OMAP_DM_TIMER
select OMAP_GPMC
select PINCTRL
+ select RESET_CONTROLLER
select SOC_BUS
select TI_SYSC
select OMAP_IRQCHIP
select CLKSRC_TI_32K
- select ARCH_HAS_RESET_CONTROLLER
help
Systems based on OMAP2, OMAP3, OMAP4 or OMAP5
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index ca52271..e95c224 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -306,10 +306,14 @@ static void __init dra7x_evm_mmc_quirk(void)
static struct clockdomain *ti_sysc_find_one_clockdomain(struct clk *clk)
{
+ struct clk_hw *hw = __clk_get_hw(clk);
struct clockdomain *clkdm = NULL;
struct clk_hw_omap *hwclk;
- hwclk = to_clk_hw_omap(__clk_get_hw(clk));
+ hwclk = to_clk_hw_omap(hw);
+ if (!omap2_clk_is_hw_omap(hw))
+ return NULL;
+
if (hwclk && hwclk->clkdm_name)
clkdm = clkdm_lookup(hwclk->clkdm_name);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 29d0345..e2c758d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -139,6 +139,7 @@
select HAVE_CMPXCHG_DOUBLE
select HAVE_CMPXCHG_LOCAL
select HAVE_CONTEXT_TRACKING
+ select HAVE_COPY_THREAD_TLS
select HAVE_DEBUG_BUGVERBOSE
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino-emmc.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino-emmc.dts
index 96ab022..121e6cc 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino-emmc.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino-emmc.dts
@@ -15,7 +15,7 @@ &mmc2 {
pinctrl-names = "default";
pinctrl-0 = <&mmc2_pins>;
vmmc-supply = <®_dcdc1>;
- vqmmc-supply = <®_dcdc1>;
+ vqmmc-supply = <®_eldo1>;
bus-width = <8>;
non-removable;
cap-mmc-hw-reset;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts
index 01a9a52..393c194 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts
@@ -140,7 +140,7 @@ &mmc0 {
&mmc1 {
pinctrl-names = "default";
pinctrl-0 = <&mmc1_pins>;
- vmmc-supply = <®_aldo2>;
+ vmmc-supply = <®_dcdc1>;
vqmmc-supply = <®_dldo4>;
mmc-pwrseq = <&wifi_pwrseq>;
bus-width = <4>;
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 144a2c1..d1fc9c2 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -61,10 +61,10 @@ cpu3: cpu@3 {
pmu {
compatible = "arm,armv8-pmuv3";
- interrupts = <0 120 8>,
- <0 121 8>,
- <0 122 8>,
- <0 123 8>;
+ interrupts = <0 170 4>,
+ <0 171 4>,
+ <0 172 4>,
+ <0 173 4>;
interrupt-affinity = <&cpu0>,
<&cpu1>,
<&cpu2>,
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
index 5bd0746..a8bb3fa 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
@@ -46,25 +46,47 @@ emmc_pwrseq: emmc-pwrseq {
};
gpio-keys {
- compatible = "gpio-keys-polled";
- poll-interval = <100>;
+ compatible = "gpio-keys";
key1 {
label = "A";
linux,code = <BTN_0>;
gpios = <&gpio GPIOH_6 GPIO_ACTIVE_LOW>;
+ interrupt-parent = <&gpio_intc>;
+ interrupts = <34 IRQ_TYPE_EDGE_BOTH>;
};
key2 {
label = "B";
linux,code = <BTN_1>;
gpios = <&gpio GPIOH_7 GPIO_ACTIVE_LOW>;
+ interrupt-parent = <&gpio_intc>;
+ interrupts = <35 IRQ_TYPE_EDGE_BOTH>;
};
key3 {
label = "C";
linux,code = <BTN_2>;
gpios = <&gpio_ao GPIOAO_2 GPIO_ACTIVE_LOW>;
+ interrupt-parent = <&gpio_intc>;
+ interrupts = <2 IRQ_TYPE_EDGE_BOTH>;
+ };
+
+ mic_mute {
+ label = "MicMute";
+ linux,code = <SW_MUTE_DEVICE>;
+ linux,input-type = <EV_SW>;
+ gpios = <&gpio_ao GPIOE_2 GPIO_ACTIVE_LOW>;
+ interrupt-parent = <&gpio_intc>;
+ interrupts = <99 IRQ_TYPE_EDGE_BOTH>;
+ };
+
+ power_key {
+ label = "PowerKey";
+ linux,code = <KEY_POWER>;
+ gpios = <&gpio_ao GPIOAO_3 GPIO_ACTIVE_LOW>;
+ interrupt-parent = <&gpio_intc>;
+ interrupts = <3 IRQ_TYPE_EDGE_BOTH>;
};
};
@@ -569,6 +591,8 @@ &uart_A {
bluetooth {
compatible = "brcm,bcm43438-bt";
+ interrupt-parent = <&gpio_intc>;
+ interrupts = <95 IRQ_TYPE_LEVEL_HIGH>;
shutdown-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>;
max-speed = <2000000>;
clocks = <&wifi32k>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index 13a3cbe..a6f9b77 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -175,7 +175,7 @@ ddr: memory-controller@1080000 {
dcfg: syscon@1e00000 {
compatible = "fsl,ls1028a-dcfg", "syscon";
reg = <0x0 0x1e00000 0x0 0x10000>;
- big-endian;
+ little-endian;
};
rst: syscon@1e60000 {
diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
index 6edbdfe..3d95b66 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
@@ -740,7 +740,7 @@ sdma1: dma-controller@30bd0000 {
reg = <0x30bd0000 0x10000>;
interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clk IMX8MM_CLK_SDMA1_ROOT>,
- <&clk IMX8MM_CLK_SDMA1_ROOT>;
+ <&clk IMX8MM_CLK_AHB>;
clock-names = "ipg", "ahb";
#dma-cells = <3>;
fsl,sdma-ram-script-name = "imx/sdma/sdma-imx7d.bin";
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts b/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts
index 2a759df..596bc65 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts
@@ -421,7 +421,7 @@ magnetometer@1e {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_imu>;
interrupt-parent = <&gpio3>;
- interrupts = <19 IRQ_TYPE_LEVEL_LOW>;
+ interrupts = <19 IRQ_TYPE_LEVEL_HIGH>;
vdd-supply = <®_3v3_p>;
vddio-supply = <®_3v3_p>;
};
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi
index 94090c6..d43e129 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi
@@ -60,10 +60,10 @@ cpu3: cpu@3 {
pmu {
compatible = "arm,armv8-pmuv3";
- interrupts = <0 120 8>,
- <0 121 8>,
- <0 122 8>,
- <0 123 8>;
+ interrupts = <0 170 4>,
+ <0 171 4>,
+ <0 172 4>,
+ <0 173 4>;
interrupt-affinity = <&cpu0>,
<&cpu1>,
<&cpu2>,
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-a1.dts b/arch/arm64/boot/dts/rockchip/rk3328-a1.dts
index 76b49f5..16f1656 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-a1.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-a1.dts
@@ -49,7 +49,8 @@ vcc_sys: vcc-sys {
ir-receiver {
compatible = "gpio-ir-receiver";
- gpios = <&gpio2 RK_PA2 GPIO_ACTIVE_HIGH>;
+ gpios = <&gpio2 RK_PA2 GPIO_ACTIVE_LOW>;
+ linux,rc-map-name = "rc-beelink-gs1";
};
};
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 8dc6c5c..baf52ba 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -85,13 +85,12 @@
#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)
#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
#define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
-#define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
#define __P000 PAGE_NONE
#define __P001 PAGE_READONLY
#define __P010 PAGE_READONLY
#define __P011 PAGE_READONLY
-#define __P100 PAGE_EXECONLY
+#define __P100 PAGE_READONLY_EXEC
#define __P101 PAGE_READONLY_EXEC
#define __P110 PAGE_READONLY_EXEC
#define __P111 PAGE_READONLY_EXEC
@@ -100,7 +99,7 @@
#define __S001 PAGE_READONLY
#define __S010 PAGE_SHARED
#define __S011 PAGE_SHARED
-#define __S100 PAGE_EXECONLY
+#define __S100 PAGE_READONLY_EXEC
#define __S101 PAGE_READONLY_EXEC
#define __S110 PAGE_SHARED_EXEC
#define __S111 PAGE_SHARED_EXEC
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 5d15b47..cd5de0e 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -96,12 +96,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
#define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte))
#define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID))
-/*
- * Execute-only user mappings do not have the PTE_USER bit set. All valid
- * kernel mappings have the PTE_UXN bit set.
- */
#define pte_valid_not_user(pte) \
- ((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
+ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
#define pte_valid_young(pte) \
((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
#define pte_valid_user(pte) \
@@ -117,8 +113,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
/*
* p??_access_permitted() is true for valid user mappings (subject to the
- * write permission check) other than user execute-only which do not have the
- * PTE_USER bit set. PROT_NONE mappings do not have the PTE_VALID bit set.
+ * write permission check). PROT_NONE mappings do not have the PTE_VALID bit
+ * set.
*/
#define pte_access_permitted(pte, write) \
(pte_valid_user(pte) && (!(write) || pte_write(pte)))
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 2629a68..5af8258 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -42,7 +42,6 @@
#endif
#define __ARCH_WANT_SYS_CLONE
-#define __ARCH_WANT_SYS_CLONE3
#ifndef __COMPAT_SYSCALL_NR
#include <uapi/asm/unistd.h>
diff --git a/arch/arm64/include/uapi/asm/unistd.h b/arch/arm64/include/uapi/asm/unistd.h
index 4703d21..f83a70e 100644
--- a/arch/arm64/include/uapi/asm/unistd.h
+++ b/arch/arm64/include/uapi/asm/unistd.h
@@ -19,5 +19,6 @@
#define __ARCH_WANT_NEW_STAT
#define __ARCH_WANT_SET_GET_RLIMIT
#define __ARCH_WANT_TIME32_SYSCALLS
+#define __ARCH_WANT_SYS_CLONE3
#include <asm-generic/unistd.h>
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 71f788c..d54586d 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -360,8 +360,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
asmlinkage void ret_from_fork(void) asm("ret_from_fork");
-int copy_thread(unsigned long clone_flags, unsigned long stack_start,
- unsigned long stk_sz, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
+ unsigned long stk_sz, struct task_struct *p, unsigned long tls)
{
struct pt_regs *childregs = task_pt_regs(p);
@@ -394,11 +394,11 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
}
/*
- * If a TLS pointer was passed to clone (4th argument), use it
- * for the new thread.
+ * If a TLS pointer was passed to clone, use it for the new
+ * thread.
*/
if (clone_flags & CLONE_SETTLS)
- p->thread.uw.tp_value = childregs->regs[3];
+ p->thread.uw.tp_value = tls;
} else {
memset(childregs, 0, sizeof(struct pt_regs));
childregs->pstate = PSR_MODE_EL1h;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 077b02a..85566d3 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -445,7 +445,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
const struct fault_info *inf;
struct mm_struct *mm = current->mm;
vm_fault_t fault, major = 0;
- unsigned long vm_flags = VM_READ | VM_WRITE;
+ unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (kprobe_page_fault(regs, esr))
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 5a3b15a..40797cb 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1070,7 +1070,6 @@ void arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
/*
* FIXME: Cleanup page tables (also in arch_add_memory() in case
@@ -1079,7 +1078,6 @@ void arch_remove_memory(int nid, u64 start, u64 size,
* unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be
* unlocked yet.
*/
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
}
#endif
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 12cd923..0231d69 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -91,7 +91,7 @@ static inline void atomic_##op(int i, atomic_t *v) \
"1: %0 = memw_locked(%1);\n" \
" %0 = "#op "(%0,%2);\n" \
" memw_locked(%1,P3)=%0;\n" \
- " if !P3 jump 1b;\n" \
+ " if (!P3) jump 1b;\n" \
: "=&r" (output) \
: "r" (&v->counter), "r" (i) \
: "memory", "p3" \
@@ -107,7 +107,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \
"1: %0 = memw_locked(%1);\n" \
" %0 = "#op "(%0,%2);\n" \
" memw_locked(%1,P3)=%0;\n" \
- " if !P3 jump 1b;\n" \
+ " if (!P3) jump 1b;\n" \
: "=&r" (output) \
: "r" (&v->counter), "r" (i) \
: "memory", "p3" \
@@ -124,7 +124,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \
"1: %0 = memw_locked(%2);\n" \
" %1 = "#op "(%0,%3);\n" \
" memw_locked(%2,P3)=%1;\n" \
- " if !P3 jump 1b;\n" \
+ " if (!P3) jump 1b;\n" \
: "=&r" (output), "=&r" (val) \
: "r" (&v->counter), "r" (i) \
: "memory", "p3" \
@@ -173,7 +173,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
" }"
" memw_locked(%2, p3) = %1;"
" {"
- " if !p3 jump 1b;"
+ " if (!p3) jump 1b;"
" }"
"2:"
: "=&r" (__oldval), "=&r" (tmp)
diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h
index 47384b0..71429f7 100644
--- a/arch/hexagon/include/asm/bitops.h
+++ b/arch/hexagon/include/asm/bitops.h
@@ -38,7 +38,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr)
"1: R12 = memw_locked(R10);\n"
" { P0 = tstbit(R12,R11); R12 = clrbit(R12,R11); }\n"
" memw_locked(R10,P1) = R12;\n"
- " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n"
+ " {if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
: "=&r" (oldval)
: "r" (addr), "r" (nr)
: "r10", "r11", "r12", "p0", "p1", "memory"
@@ -62,7 +62,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr)
"1: R12 = memw_locked(R10);\n"
" { P0 = tstbit(R12,R11); R12 = setbit(R12,R11); }\n"
" memw_locked(R10,P1) = R12;\n"
- " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n"
+ " {if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
: "=&r" (oldval)
: "r" (addr), "r" (nr)
: "r10", "r11", "r12", "p0", "p1", "memory"
@@ -88,7 +88,7 @@ static inline int test_and_change_bit(int nr, volatile void *addr)
"1: R12 = memw_locked(R10);\n"
" { P0 = tstbit(R12,R11); R12 = togglebit(R12,R11); }\n"
" memw_locked(R10,P1) = R12;\n"
- " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n"
+ " {if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
: "=&r" (oldval)
: "r" (addr), "r" (nr)
: "r10", "r11", "r12", "p0", "p1", "memory"
@@ -223,7 +223,7 @@ static inline int ffs(int x)
int r;
asm("{ P0 = cmp.eq(%1,#0); %0 = ct0(%1);}\n"
- "{ if P0 %0 = #0; if !P0 %0 = add(%0,#1);}\n"
+ "{ if (P0) %0 = #0; if (!P0) %0 = add(%0,#1);}\n"
: "=&r" (r)
: "r" (x)
: "p0");
diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h
index 6091322..92b8a02 100644
--- a/arch/hexagon/include/asm/cmpxchg.h
+++ b/arch/hexagon/include/asm/cmpxchg.h
@@ -30,7 +30,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
__asm__ __volatile__ (
"1: %0 = memw_locked(%1);\n" /* load into retval */
" memw_locked(%1,P0) = %2;\n" /* store into memory */
- " if !P0 jump 1b;\n"
+ " if (!P0) jump 1b;\n"
: "=&r" (retval)
: "r" (ptr), "r" (x)
: "memory", "p0"
diff --git a/arch/hexagon/include/asm/futex.h b/arch/hexagon/include/asm/futex.h
index cb63521..0191f7c 100644
--- a/arch/hexagon/include/asm/futex.h
+++ b/arch/hexagon/include/asm/futex.h
@@ -16,7 +16,7 @@
/* For example: %1 = %4 */ \
insn \
"2: memw_locked(%3,p2) = %1;\n" \
- " if !p2 jump 1b;\n" \
+ " if (!p2) jump 1b;\n" \
" %1 = #0;\n" \
"3:\n" \
".section .fixup,\"ax\"\n" \
@@ -84,10 +84,10 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
"1: %1 = memw_locked(%3)\n"
" {\n"
" p2 = cmp.eq(%1,%4)\n"
- " if !p2.new jump:NT 3f\n"
+ " if (!p2.new) jump:NT 3f\n"
" }\n"
"2: memw_locked(%3,p2) = %5\n"
- " if !p2 jump 1b\n"
+ " if (!p2) jump 1b\n"
"3:\n"
".section .fixup,\"ax\"\n"
"4: %0 = #%6\n"
diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h
index 539e3ef..b0dbc34 100644
--- a/arch/hexagon/include/asm/io.h
+++ b/arch/hexagon/include/asm/io.h
@@ -173,6 +173,7 @@ static inline void writel(u32 data, volatile void __iomem *addr)
void __iomem *ioremap(unsigned long phys_addr, unsigned long size);
#define ioremap_nocache ioremap
+#define ioremap_uc(X, Y) ioremap((X), (Y))
#define __raw_writel writel
diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h
index bfe07d8..ef103b7 100644
--- a/arch/hexagon/include/asm/spinlock.h
+++ b/arch/hexagon/include/asm/spinlock.h
@@ -30,9 +30,9 @@ static inline void arch_read_lock(arch_rwlock_t *lock)
__asm__ __volatile__(
"1: R6 = memw_locked(%0);\n"
" { P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n"
- " { if !P3 jump 1b; }\n"
+ " { if (!P3) jump 1b; }\n"
" memw_locked(%0,P3) = R6;\n"
- " { if !P3 jump 1b; }\n"
+ " { if (!P3) jump 1b; }\n"
:
: "r" (&lock->lock)
: "memory", "r6", "p3"
@@ -46,7 +46,7 @@ static inline void arch_read_unlock(arch_rwlock_t *lock)
"1: R6 = memw_locked(%0);\n"
" R6 = add(R6,#-1);\n"
" memw_locked(%0,P3) = R6\n"
- " if !P3 jump 1b;\n"
+ " if (!P3) jump 1b;\n"
:
: "r" (&lock->lock)
: "memory", "r6", "p3"
@@ -61,7 +61,7 @@ static inline int arch_read_trylock(arch_rwlock_t *lock)
__asm__ __volatile__(
" R6 = memw_locked(%1);\n"
" { %0 = #0; P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n"
- " { if !P3 jump 1f; }\n"
+ " { if (!P3) jump 1f; }\n"
" memw_locked(%1,P3) = R6;\n"
" { %0 = P3 }\n"
"1:\n"
@@ -78,9 +78,9 @@ static inline void arch_write_lock(arch_rwlock_t *lock)
__asm__ __volatile__(
"1: R6 = memw_locked(%0)\n"
" { P3 = cmp.eq(R6,#0); R6 = #-1;}\n"
- " { if !P3 jump 1b; }\n"
+ " { if (!P3) jump 1b; }\n"
" memw_locked(%0,P3) = R6;\n"
- " { if !P3 jump 1b; }\n"
+ " { if (!P3) jump 1b; }\n"
:
: "r" (&lock->lock)
: "memory", "r6", "p3"
@@ -94,7 +94,7 @@ static inline int arch_write_trylock(arch_rwlock_t *lock)
__asm__ __volatile__(
" R6 = memw_locked(%1)\n"
" { %0 = #0; P3 = cmp.eq(R6,#0); R6 = #-1;}\n"
- " { if !P3 jump 1f; }\n"
+ " { if (!P3) jump 1f; }\n"
" memw_locked(%1,P3) = R6;\n"
" %0 = P3;\n"
"1:\n"
@@ -117,9 +117,9 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
__asm__ __volatile__(
"1: R6 = memw_locked(%0);\n"
" P3 = cmp.eq(R6,#0);\n"
- " { if !P3 jump 1b; R6 = #1; }\n"
+ " { if (!P3) jump 1b; R6 = #1; }\n"
" memw_locked(%0,P3) = R6;\n"
- " { if !P3 jump 1b; }\n"
+ " { if (!P3) jump 1b; }\n"
:
: "r" (&lock->lock)
: "memory", "r6", "p3"
@@ -139,7 +139,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
__asm__ __volatile__(
" R6 = memw_locked(%1);\n"
" P3 = cmp.eq(R6,#0);\n"
- " { if !P3 jump 1f; R6 = #1; %0 = #0; }\n"
+ " { if (!P3) jump 1f; R6 = #1; %0 = #0; }\n"
" memw_locked(%1,P3) = R6;\n"
" %0 = P3;\n"
"1:\n"
diff --git a/arch/hexagon/kernel/stacktrace.c b/arch/hexagon/kernel/stacktrace.c
index 35f2942..5ed02f6 100644
--- a/arch/hexagon/kernel/stacktrace.c
+++ b/arch/hexagon/kernel/stacktrace.c
@@ -11,8 +11,6 @@
#include <linux/thread_info.h>
#include <linux/module.h>
-register unsigned long current_frame_pointer asm("r30");
-
struct stackframe {
unsigned long fp;
unsigned long rets;
@@ -30,7 +28,7 @@ void save_stack_trace(struct stack_trace *trace)
low = (unsigned long)task_stack_page(current);
high = low + THREAD_SIZE;
- fp = current_frame_pointer;
+ fp = (unsigned long)__builtin_frame_address(0);
while (fp >= low && fp <= (high - sizeof(*frame))) {
frame = (struct stackframe *)fp;
diff --git a/arch/hexagon/kernel/vm_entry.S b/arch/hexagon/kernel/vm_entry.S
index 12242c2..4023fdb 100644
--- a/arch/hexagon/kernel/vm_entry.S
+++ b/arch/hexagon/kernel/vm_entry.S
@@ -369,7 +369,7 @@
R26.L = #LO(do_work_pending);
R0 = #VM_INT_DISABLE;
}
- if P0 jump check_work_pending
+ if (P0) jump check_work_pending
{
R0 = R25;
callr R24
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 58fd670..b01d68a 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -689,9 +689,7 @@ void arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
}
#endif
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index add3882..ed8e28b 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -47,7 +47,7 @@
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES
select HAVE_ASM_MODVERSIONS
- select HAVE_EBPF_JIT if (!CPU_MICROMIPS)
+ select HAVE_EBPF_JIT if 64BIT && !CPU_MICROMIPS && TARGET_ISA_REV >= 2
select HAVE_CONTEXT_TRACKING
select HAVE_COPY_THREAD_TLS
select HAVE_C_RECORDMCOUNT
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index 172801e..d859f07 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -29,6 +29,9 @@
-DBOOT_HEAP_SIZE=$(BOOT_HEAP_SIZE) \
-DKERNEL_ENTRY=$(VMLINUX_ENTRY_ADDRESS)
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT := n
+
# decompressor objects (linked with vmlinuz)
vmlinuzobjs-y := $(obj)/head.o $(obj)/decompress.o $(obj)/string.o
diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
index c46c59b..49f0061 100644
--- a/arch/mips/include/asm/cpu-type.h
+++ b/arch/mips/include/asm/cpu-type.h
@@ -15,7 +15,8 @@
static inline int __pure __get_cpu_type(const int cpu_type)
{
switch (cpu_type) {
-#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2EF)
+#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2E) || \
+ defined(CONFIG_SYS_HAS_CPU_LOONGSON2F)
case CPU_LOONGSON2EF:
#endif
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 4993db4..ee26f9a 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -49,8 +49,26 @@ struct thread_info {
.addr_limit = KERNEL_DS, \
}
-/* How to get the thread information struct from C. */
+/*
+ * A pointer to the struct thread_info for the currently executing thread is
+ * held in register $28/$gp.
+ *
+ * We declare __current_thread_info as a global register variable rather than a
+ * local register variable within current_thread_info() because clang doesn't
+ * support explicit local register variables.
+ *
+ * When building the VDSO we take care not to declare the global register
+ * variable because this causes GCC to not preserve the value of $28/$gp in
+ * functions that change its value (which is common in the PIC VDSO when
+ * accessing the GOT). Since the VDSO shouldn't be accessing
+ * __current_thread_info anyway we declare it extern in order to cause a link
+ * failure if it's referenced.
+ */
+#ifdef __VDSO__
+extern struct thread_info *__current_thread_info;
+#else
register struct thread_info *__current_thread_info __asm__("$28");
+#endif
static inline struct thread_info *current_thread_info(void)
{
diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h
index b088255..0ae9b4c 100644
--- a/arch/mips/include/asm/vdso/gettimeofday.h
+++ b/arch/mips/include/asm/vdso/gettimeofday.h
@@ -26,8 +26,6 @@
#define __VDSO_USE_SYSCALL ULLONG_MAX
-#ifdef CONFIG_MIPS_CLOCK_VSYSCALL
-
static __always_inline long gettimeofday_fallback(
struct __kernel_old_timeval *_tv,
struct timezone *_tz)
@@ -48,17 +46,6 @@ static __always_inline long gettimeofday_fallback(
return error ? -ret : ret;
}
-#else
-
-static __always_inline long gettimeofday_fallback(
- struct __kernel_old_timeval *_tv,
- struct timezone *_tz)
-{
- return -1;
-}
-
-#endif
-
static __always_inline long clock_gettime_fallback(
clockid_t _clkid,
struct __kernel_timespec *_ts)
diff --git a/arch/mips/kernel/cacheinfo.c b/arch/mips/kernel/cacheinfo.c
index f777e44..47312c5 100644
--- a/arch/mips/kernel/cacheinfo.c
+++ b/arch/mips/kernel/cacheinfo.c
@@ -50,6 +50,25 @@ static int __init_cache_level(unsigned int cpu)
return 0;
}
+static void fill_cpumask_siblings(int cpu, cpumask_t *cpu_map)
+{
+ int cpu1;
+
+ for_each_possible_cpu(cpu1)
+ if (cpus_are_siblings(cpu, cpu1))
+ cpumask_set_cpu(cpu1, cpu_map);
+}
+
+static void fill_cpumask_cluster(int cpu, cpumask_t *cpu_map)
+{
+ int cpu1;
+ int cluster = cpu_cluster(&cpu_data[cpu]);
+
+ for_each_possible_cpu(cpu1)
+ if (cpu_cluster(&cpu_data[cpu1]) == cluster)
+ cpumask_set_cpu(cpu1, cpu_map);
+}
+
static int __populate_cache_leaves(unsigned int cpu)
{
struct cpuinfo_mips *c = ¤t_cpu_data;
@@ -57,14 +76,20 @@ static int __populate_cache_leaves(unsigned int cpu)
struct cacheinfo *this_leaf = this_cpu_ci->info_list;
if (c->icache.waysize) {
+ /* L1 caches are per core */
+ fill_cpumask_siblings(cpu, &this_leaf->shared_cpu_map);
populate_cache(dcache, this_leaf, 1, CACHE_TYPE_DATA);
+ fill_cpumask_siblings(cpu, &this_leaf->shared_cpu_map);
populate_cache(icache, this_leaf, 1, CACHE_TYPE_INST);
} else {
populate_cache(dcache, this_leaf, 1, CACHE_TYPE_UNIFIED);
}
- if (c->scache.waysize)
+ if (c->scache.waysize) {
+ /* L2 cache is per cluster */
+ fill_cpumask_cluster(cpu, &this_leaf->shared_cpu_map);
populate_cache(scache, this_leaf, 2, CACHE_TYPE_UNIFIED);
+ }
if (c->tcache.waysize)
populate_cache(tcache, this_leaf, 3, CACHE_TYPE_UNIFIED);
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 3ec69d9..561154c 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -1804,7 +1804,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
unsigned int image_size;
u8 *image_ptr;
- if (!prog->jit_requested || MIPS_ISA_REV < 2)
+ if (!prog->jit_requested)
return prog;
tmp = bpf_jit_blind_constants(prog);
diff --git a/arch/mips/vdso/vgettimeofday.c b/arch/mips/vdso/vgettimeofday.c
index 6ebdc37..6b83b63 100644
--- a/arch/mips/vdso/vgettimeofday.c
+++ b/arch/mips/vdso/vgettimeofday.c
@@ -17,12 +17,22 @@ int __vdso_clock_gettime(clockid_t clock,
return __cvdso_clock_gettime32(clock, ts);
}
+#ifdef CONFIG_MIPS_CLOCK_VSYSCALL
+
+/*
+ * This is behind the ifdef so that we don't provide the symbol when there's no
+ * possibility of there being a usable clocksource, because there's nothing we
+ * can do without it. When libc fails the symbol lookup it should fall back on
+ * the standard syscall path.
+ */
int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
struct timezone *tz)
{
return __cvdso_gettimeofday(tv, tz);
}
+#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */
+
int __vdso_clock_getres(clockid_t clock_id,
struct old_timespec32 *res)
{
@@ -43,12 +53,22 @@ int __vdso_clock_gettime(clockid_t clock,
return __cvdso_clock_gettime(clock, ts);
}
+#ifdef CONFIG_MIPS_CLOCK_VSYSCALL
+
+/*
+ * This is behind the ifdef so that we don't provide the symbol when there's no
+ * possibility of there being a usable clocksource, because there's nothing we
+ * can do without it. When libc fails the symbol lookup it should fall back on
+ * the standard syscall path.
+ */
int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
struct timezone *tz)
{
return __cvdso_gettimeofday(tv, tz);
}
+#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */
+
int __vdso_clock_getres(clockid_t clock_id,
struct __kernel_timespec *res)
{
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index d9ac7e6..caddded 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -9,7 +9,11 @@
#define PG_dcache_dirty PG_arch_1
void flush_icache_range(unsigned long start, unsigned long end);
+#define flush_icache_range flush_icache_range
+
void flush_icache_page(struct vm_area_struct *vma, struct page *page);
+#define flush_icache_page flush_icache_page
+
#ifdef CONFIG_CPU_CACHE_ALIASING
void flush_cache_mm(struct mm_struct *mm);
void flush_cache_dup_mm(struct mm_struct *mm);
@@ -40,12 +44,11 @@ void invalidate_kernel_vmap_range(void *addr, int size);
#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages)
#else
-#include <asm-generic/cacheflush.h>
-#undef flush_icache_range
-#undef flush_icache_page
-#undef flush_icache_user_range
void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
unsigned long addr, int len);
+#define flush_icache_user_range flush_icache_user_range
+
+#include <asm-generic/cacheflush.h>
#endif
#endif /* __NDS32_CACHEFLUSH_H__ */
diff --git a/arch/nds32/include/asm/pgtable.h b/arch/nds32/include/asm/pgtable.h
index 0214e41..6abc58a 100644
--- a/arch/nds32/include/asm/pgtable.h
+++ b/arch/nds32/include/asm/pgtable.h
@@ -195,7 +195,7 @@ extern void paging_init(void);
#define pte_unmap(pte) do { } while (0)
#define pte_unmap_nested(pte) do { } while (0)
-#define pmd_off_k(address) pmd_offset(pgd_offset_k(address), address)
+#define pmd_off_k(address) pmd_offset(pud_offset(p4d_offset(pgd_offset_k(address), (address)), (address)), (address))
#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
/*
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index b16237c..0c29d6c 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -62,6 +62,7 @@
select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE
select HAVE_KPROBES_ON_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
+ select HAVE_COPY_THREAD_TLS
help
The PA-RISC microprocessor is designed by Hewlett-Packard and used
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index a6c9f49..a5f3e50 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -889,8 +889,8 @@ static void print_parisc_device(struct parisc_device *dev)
static int count;
print_pa_hwpath(dev, hw_path);
- pr_info("%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
- ++count, dev->name, (void*) dev->hpa.start, hw_path, dev->id.hw_type,
+ pr_info("%d. %s at %pap [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
+ ++count, dev->name, &(dev->hpa.start), hw_path, dev->id.hw_type,
dev->id.hversion_rev, dev->id.hversion, dev->id.sversion);
if (dev->num_addrs) {
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index ecc5c27..230a642 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -208,8 +208,8 @@ arch_initcall(parisc_idle_init);
* Copy architecture-specific thread state
*/
int
-copy_thread(unsigned long clone_flags, unsigned long usp,
- unsigned long kthread_arg, struct task_struct *p)
+copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+ unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
{
struct pt_regs *cregs = &(p->thread.regs);
void *stack = task_stack_page(p);
@@ -254,9 +254,9 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
cregs->ksp = (unsigned long)stack + THREAD_SZ_ALGN + FRAME_SIZE;
cregs->kpc = (unsigned long) &child_return;
- /* Setup thread TLS area from the 4th parameter in clone */
+ /* Setup thread TLS area */
if (clone_flags & CLONE_SETTLS)
- cregs->cr27 = cregs->gr[23];
+ cregs->cr27 = tls;
}
return 0;
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index ddca828..354cf06 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -401,7 +401,7 @@ static void __init map_pages(unsigned long start_vaddr,
pmd = (pmd_t *) __pa(pmd);
}
- pgd_populate(NULL, pg_dir, __va(pmd));
+ pud_populate(NULL, (pud_t *)pg_dir, __va(pmd));
#endif
pg_dir++;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1ec34e1..e2a4121 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -455,11 +455,7 @@
config PPC_UV
bool "Ultravisor support"
depends on KVM_BOOK3S_HV_POSSIBLE
- select ZONE_DEVICE
- select DEV_PAGEMAP_OPS
- select DEVICE_PRIVATE
- select MEMORY_HOTPLUG
- select MEMORY_HOTREMOVE
+ depends on DEVICE_PRIVATE
default n
help
This option paravirtualizes the kernel to run in POWER platforms that
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi
index e1a961f..baa0c50 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi
@@ -63,6 +63,7 @@ mdio@e1000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe1000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy0: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi
index c288f3c..9309560 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi
@@ -60,6 +60,7 @@ mdio@f1000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xf1000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy6: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
index 94f3e71..ff4bd38 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
@@ -63,6 +63,7 @@ mdio@e3000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe3000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy1: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi
index 94a7698..1fa38ed 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi
@@ -60,6 +60,7 @@ mdio@f3000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xf3000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy7: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi
index b5ff5f7..a8cc978 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi
@@ -59,6 +59,7 @@ mdio@e1000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe1000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy0: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi
index ee44182..8b8bd70 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi
@@ -59,6 +59,7 @@ mdio@e3000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe3000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy1: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi
index f05f0d7..619c880 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi
@@ -59,6 +59,7 @@ mdio@e5000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe5000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy2: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi
index a9114ec..d7ebb73 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi
@@ -59,6 +59,7 @@ mdio@e7000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe7000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy3: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi
index 44dd00a..b151d69 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi
@@ -59,6 +59,7 @@ mdio@e9000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe9000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy4: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi
index 5b1b84b..adc0ae0 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi
@@ -59,6 +59,7 @@ mdio@eb000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xeb000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy5: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi
index 0e1daae..435047e 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi
@@ -60,6 +60,7 @@ mdio@f1000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xf1000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy14: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi
index 68c5ef7..c098657 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi
@@ -60,6 +60,7 @@ mdio@f3000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xf3000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy15: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi
index 605363c..9d06824 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi
@@ -59,6 +59,7 @@ mdio@e1000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe1000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy8: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi
index 1955dfa..70e9477 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi
@@ -59,6 +59,7 @@ mdio@e3000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe3000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy9: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi
index 2c14764..ad96e65 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi
@@ -59,6 +59,7 @@ mdio@e5000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe5000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy10: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi
index b8b541f..034bc4b 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi
@@ -59,6 +59,7 @@ mdio@e7000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe7000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy11: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi
index 4b2cfdd..93ca23d 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi
@@ -59,6 +59,7 @@ mdio@e9000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xe9000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy12: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi
index 0a52ddf..23b3117 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi
@@ -59,6 +59,7 @@ mdio@eb000 {
#size-cells = <0>;
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xeb000 0x1000>;
+ fsl,erratum-a011043; /* must ignore read errors */
pcsphy13: ethernet-phy@0 {
reg = <0x0>;
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 15b7500..3fa1b96 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -600,8 +600,11 @@ extern void slb_set_size(u16 size);
*
*/
#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2)
+
+// The + 2 accounts for INVALID_REGION and 1 more to avoid overlap with kernel
#define MIN_USER_CONTEXT (MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \
- MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT)
+ MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2)
+
/*
* For platforms that support on 65bit VA we limit the context bits
*/
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 1b55fc0..860228e 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -15,6 +15,7 @@
*
* (the type definitions are in asm/spinlock_types.h)
*/
+#include <linux/jump_label.h>
#include <linux/irqflags.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h
index f2dfcd5..33aee74 100644
--- a/arch/powerpc/include/asm/xive-regs.h
+++ b/arch/powerpc/include/asm/xive-regs.h
@@ -39,6 +39,7 @@
#define XIVE_ESB_VAL_P 0x2
#define XIVE_ESB_VAL_Q 0x1
+#define XIVE_ESB_INVALID 0xFF
/*
* Thread Management (aka "TM") registers
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 617c277..f5535ea 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -151,10 +151,9 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
int ret;
- __remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
/* Remove htab bolted mappings for this section of memory */
start = (unsigned long)__va(start);
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 42bbcd4..dffe1a4 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -50,7 +50,7 @@ static void slice_print_mask(const char *label, const struct slice_mask *mask) {
#endif
-static inline bool slice_addr_is_low(unsigned long addr)
+static inline notrace bool slice_addr_is_low(unsigned long addr)
{
u64 tmp = (u64)addr;
@@ -659,7 +659,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
mm_ctx_user_psize(¤t->mm->context), 1);
}
-unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
+unsigned int notrace get_slice_psize(struct mm_struct *mm, unsigned long addr)
{
unsigned char *psizes;
int index, mask_index;
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index f5fadbd..9651ca0 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -972,12 +972,21 @@ static int xive_get_irqchip_state(struct irq_data *data,
enum irqchip_irq_state which, bool *state)
{
struct xive_irq_data *xd = irq_data_get_irq_handler_data(data);
+ u8 pq;
switch (which) {
case IRQCHIP_STATE_ACTIVE:
- *state = !xd->stale_p &&
- (xd->saved_p ||
- !!(xive_esb_read(xd, XIVE_ESB_GET) & XIVE_ESB_VAL_P));
+ pq = xive_esb_read(xd, XIVE_ESB_GET);
+
+ /*
+ * The esb value being all 1's means we couldn't get
+ * the PQ state of the interrupt through mmio. It may
+ * happen, for example when querying a PHB interrupt
+ * while the PHB is in an error state. We consider the
+ * interrupt to be inactive in that case.
+ */
+ *state = (pq != XIVE_ESB_INVALID) && !xd->stale_p &&
+ (xd->saved_p || !!(pq & XIVE_ESB_VAL_P));
return 0;
default:
return -EINVAL;
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index d8efbaa..fa7dc03 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -64,6 +64,8 @@
select SPARSEMEM_STATIC if 32BIT
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
select HAVE_ARCH_MMAP_RND_BITS if MMU
+ select ARCH_HAS_GCOV_PROFILE_ALL
+ select HAVE_COPY_THREAD_TLS
config ARCH_MMAP_RND_BITS_MIN
default 18 if 64BIT
diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
index 70a1891..a2e3d54 100644
--- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
+++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
@@ -54,6 +54,7 @@ cpu1: cpu@1 {
reg = <1>;
riscv,isa = "rv64imafdc";
tlb-split;
+ next-level-cache = <&l2cache>;
cpu1_intc: interrupt-controller {
#interrupt-cells = <1>;
compatible = "riscv,cpu-intc";
@@ -77,6 +78,7 @@ cpu2: cpu@2 {
reg = <2>;
riscv,isa = "rv64imafdc";
tlb-split;
+ next-level-cache = <&l2cache>;
cpu2_intc: interrupt-controller {
#interrupt-cells = <1>;
compatible = "riscv,cpu-intc";
@@ -100,6 +102,7 @@ cpu3: cpu@3 {
reg = <3>;
riscv,isa = "rv64imafdc";
tlb-split;
+ next-level-cache = <&l2cache>;
cpu3_intc: interrupt-controller {
#interrupt-cells = <1>;
compatible = "riscv,cpu-intc";
@@ -123,6 +126,7 @@ cpu4: cpu@4 {
reg = <4>;
riscv,isa = "rv64imafdc";
tlb-split;
+ next-level-cache = <&l2cache>;
cpu4_intc: interrupt-controller {
#interrupt-cells = <1>;
compatible = "riscv,cpu-intc";
@@ -253,6 +257,17 @@ pwm1: pwm@10021000 {
#pwm-cells = <3>;
status = "disabled";
};
+ l2cache: cache-controller@2010000 {
+ compatible = "sifive,fu540-c000-ccache", "cache";
+ cache-block-size = <64>;
+ cache-level = <2>;
+ cache-sets = <1024>;
+ cache-size = <2097152>;
+ cache-unified;
+ interrupt-parent = <&plic0>;
+ interrupts = <1 2 3>;
+ reg = <0x0 0x2010000 0x0 0x1000>;
+ };
};
};
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index dd62b69..27e005f 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -5,4 +5,8 @@
#include <linux/ftrace.h>
#include <asm-generic/asm-prototypes.h>
+long long __lshrti3(long long a, int b);
+long long __ashrti3(long long a, int b);
+long long __ashlti3(long long a, int b);
+
#endif /* _ASM_RISCV_PROTOTYPES_H */
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 0a62d2d..435b655 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -116,9 +116,9 @@
# define SR_PIE SR_MPIE
# define SR_PP SR_MPP
-# define IRQ_SOFT IRQ_M_SOFT
-# define IRQ_TIMER IRQ_M_TIMER
-# define IRQ_EXT IRQ_M_EXT
+# define RV_IRQ_SOFT IRQ_M_SOFT
+# define RV_IRQ_TIMER IRQ_M_TIMER
+# define RV_IRQ_EXT IRQ_M_EXT
#else /* CONFIG_RISCV_M_MODE */
# define CSR_STATUS CSR_SSTATUS
# define CSR_IE CSR_SIE
@@ -133,15 +133,15 @@
# define SR_PIE SR_SPIE
# define SR_PP SR_SPP
-# define IRQ_SOFT IRQ_S_SOFT
-# define IRQ_TIMER IRQ_S_TIMER
-# define IRQ_EXT IRQ_S_EXT
+# define RV_IRQ_SOFT IRQ_S_SOFT
+# define RV_IRQ_TIMER IRQ_S_TIMER
+# define RV_IRQ_EXT IRQ_S_EXT
#endif /* CONFIG_RISCV_M_MODE */
/* IE/IP (Supervisor/Machine Interrupt Enable/Pending) flags */
-#define IE_SIE (_AC(0x1, UL) << IRQ_SOFT)
-#define IE_TIE (_AC(0x1, UL) << IRQ_TIMER)
-#define IE_EIE (_AC(0x1, UL) << IRQ_EXT)
+#define IE_SIE (_AC(0x1, UL) << RV_IRQ_SOFT)
+#define IE_TIE (_AC(0x1, UL) << RV_IRQ_TIMER)
+#define IE_EIE (_AC(0x1, UL) << RV_IRQ_EXT)
#ifndef __ASSEMBLY__
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index b94d8db..c40fdcd 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -142,7 +142,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
*/
old = *parent;
- if (function_graph_enter(old, self_addr, frame_pointer, parent))
+ if (!function_graph_enter(old, self_addr, frame_pointer, parent))
*parent = return_hooker;
}
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 797802c..a4242be 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -80,7 +80,9 @@
#ifdef CONFIG_SMP
li t0, CONFIG_NR_CPUS
- bgeu a0, t0, .Lsecondary_park
+ blt a0, t0, .Lgood_cores
+ tail .Lsecondary_park
+.Lgood_cores:
#endif
/* Pick one hart to run the main boot sequence */
@@ -209,11 +211,6 @@
tail smp_callin
#endif
-.align 2
-.Lsecondary_park:
- /* We lack SMP support or have too many harts, so park this hart */
- wfi
- j .Lsecondary_park
END(_start)
#ifdef CONFIG_RISCV_M_MODE
@@ -251,7 +248,7 @@
#ifdef CONFIG_FPU
csrr t0, CSR_MISA
andi t0, t0, (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D)
- bnez t0, .Lreset_regs_done
+ beqz t0, .Lreset_regs_done
li t1, SR_FS
csrs CSR_STATUS, t1
@@ -295,6 +292,13 @@
END(reset_regs)
#endif /* CONFIG_RISCV_M_MODE */
+.section ".text", "ax",@progbits
+.align 2
+.Lsecondary_park:
+ /* We lack SMP support or have too many harts, so park this hart */
+ wfi
+ j .Lsecondary_park
+
__PAGE_ALIGNED_BSS
/* Empty zero page */
.balign PAGE_SIZE
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
index 3f07a91..345c4f2 100644
--- a/arch/riscv/kernel/irq.c
+++ b/arch/riscv/kernel/irq.c
@@ -23,11 +23,11 @@ asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs)
irq_enter();
switch (regs->cause & ~CAUSE_IRQ_FLAG) {
- case IRQ_TIMER:
+ case RV_IRQ_TIMER:
riscv_timer_interrupt();
break;
#ifdef CONFIG_SMP
- case IRQ_SOFT:
+ case RV_IRQ_SOFT:
/*
* We only use software interrupts to pass IPIs, so if a non-SMP
* system gets one, then we don't know what to do.
@@ -35,7 +35,7 @@ asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs)
riscv_software_interrupt();
break;
#endif
- case IRQ_EXT:
+ case RV_IRQ_EXT:
handle_arch_irq(regs);
break;
default:
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 95a3031..817cf7b 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -99,8 +99,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
return 0;
}
-int copy_thread(unsigned long clone_flags, unsigned long usp,
- unsigned long arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+ unsigned long arg, struct task_struct *p, unsigned long tls)
{
struct pt_regs *childregs = task_pt_regs(p);
@@ -121,7 +121,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
if (usp) /* User fork */
childregs->sp = usp;
if (clone_flags & CLONE_SETTLS)
- childregs->tp = childregs->a5;
+ childregs->tp = tls;
childregs->a0 = 0; /* Return value of fork() */
p->thread.ra = (unsigned long)ret_from_fork;
}
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 49a5852..33b16f4 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -58,7 +58,8 @@
cmd_vdsold = $(CC) $(KBUILD_CFLAGS) $(call cc-option, -no-pie) -nostdlib -nostartfiles $(SYSCFLAGS_$(@F)) \
-Wl,-T,$(filter-out FORCE,$^) -o $@.tmp && \
$(CROSS_COMPILE)objcopy \
- $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@
+ $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
+ rm $@.tmp
# install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/riscv/lib/tishift.S b/arch/riscv/lib/tishift.S
index 15f9d54..ef90075 100644
--- a/arch/riscv/lib/tishift.S
+++ b/arch/riscv/lib/tishift.S
@@ -4,34 +4,73 @@
*/
#include <linux/linkage.h>
+#include <asm-generic/export.h>
-ENTRY(__lshrti3)
+SYM_FUNC_START(__lshrti3)
beqz a2, .L1
li a5,64
sub a5,a5,a2
- addi sp,sp,-16
sext.w a4,a5
blez a5, .L2
sext.w a2,a2
- sll a4,a1,a4
srl a0,a0,a2
- srl a1,a1,a2
+ sll a4,a1,a4
+ srl a2,a1,a2
or a0,a0,a4
- sd a1,8(sp)
- sd a0,0(sp)
- ld a0,0(sp)
- ld a1,8(sp)
- addi sp,sp,16
- ret
+ mv a1,a2
.L1:
ret
.L2:
- negw a4,a4
- srl a1,a1,a4
- sd a1,0(sp)
- sd zero,8(sp)
- ld a0,0(sp)
- ld a1,8(sp)
- addi sp,sp,16
+ negw a0,a4
+ li a2,0
+ srl a0,a1,a0
+ mv a1,a2
ret
-ENDPROC(__lshrti3)
+SYM_FUNC_END(__lshrti3)
+EXPORT_SYMBOL(__lshrti3)
+
+SYM_FUNC_START(__ashrti3)
+ beqz a2, .L3
+ li a5,64
+ sub a5,a5,a2
+ sext.w a4,a5
+ blez a5, .L4
+ sext.w a2,a2
+ srl a0,a0,a2
+ sll a4,a1,a4
+ sra a2,a1,a2
+ or a0,a0,a4
+ mv a1,a2
+.L3:
+ ret
+.L4:
+ negw a0,a4
+ srai a2,a1,0x3f
+ sra a0,a1,a0
+ mv a1,a2
+ ret
+SYM_FUNC_END(__ashrti3)
+EXPORT_SYMBOL(__ashrti3)
+
+SYM_FUNC_START(__ashlti3)
+ beqz a2, .L5
+ li a5,64
+ sub a5,a5,a2
+ sext.w a4,a5
+ blez a5, .L6
+ sext.w a2,a2
+ sll a1,a1,a2
+ srl a4,a0,a4
+ sll a2,a0,a2
+ or a1,a1,a4
+ mv a0,a2
+.L5:
+ ret
+.L6:
+ negw a1,a4
+ li a2,0
+ sll a1,a0,a1
+ mv a0,a2
+ ret
+SYM_FUNC_END(__ashlti3)
+EXPORT_SYMBOL(__ashlti3)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 69f6678..965a8cf4 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -99,13 +99,13 @@ static void __init setup_initrd(void)
pr_info("initrd not found or empty");
goto disable;
}
- if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) {
+ if (__pa_symbol(initrd_end) > PFN_PHYS(max_low_pfn)) {
pr_err("initrd extends beyond end of memory");
goto disable;
}
size = initrd_end - initrd_start;
- memblock_reserve(__pa(initrd_start), size);
+ memblock_reserve(__pa_symbol(initrd_start), size);
initrd_below_start_ok = 1;
pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n",
@@ -124,8 +124,8 @@ void __init setup_bootmem(void)
{
struct memblock_region *reg;
phys_addr_t mem_size = 0;
- phys_addr_t vmlinux_end = __pa(&_end);
- phys_addr_t vmlinux_start = __pa(&_start);
+ phys_addr_t vmlinux_end = __pa_symbol(&_end);
+ phys_addr_t vmlinux_start = __pa_symbol(&_start);
/* Find the memory region containing the kernel */
for_each_memblock(memory, reg) {
@@ -445,7 +445,7 @@ static void __init setup_vm_final(void)
/* Setup swapper PGD for fixmap */
create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
- __pa(fixmap_pgd_next),
+ __pa_symbol(fixmap_pgd_next),
PGDIR_SIZE, PAGE_TABLE);
/* Map all memory banks */
@@ -474,7 +474,7 @@ static void __init setup_vm_final(void)
clear_fixmap(FIX_PMD);
/* Move to swapper page table */
- csr_write(CSR_SATP, PFN_DOWN(__pa(swapper_pg_dir)) | SATP_MODE);
+ csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | SATP_MODE);
local_flush_tlb_all();
}
#else
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 9cbf490..d5fbd75 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1052,7 +1052,7 @@ static void __init log_component_list(void)
if (!early_ipl_comp_list_addr)
return;
- if (ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR)
+ if (ipl_block.hdr.flags & IPL_PL_FLAG_SIPL)
pr_info("Linux is running with Secure-IPL enabled\n");
else
pr_info("Linux is running with Secure-IPL disabled\n");
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f0ce222..ac44bd7 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -292,10 +292,8 @@ void arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
vmem_remove_mapping(start, size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index dfdbaa5..d1b1ff2 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -434,9 +434,7 @@ void arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = PFN_DOWN(start);
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 2a6d04fc..6f0edd0 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -14,6 +14,7 @@
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_DEBUG_KMEMLEAK
select HAVE_DEBUG_BUGVERBOSE
+ select HAVE_COPY_THREAD_TLS
select GENERIC_IRQ_SHOW
select GENERIC_CPU_DEVICES
select GENERIC_CLOCKEVENTS
diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h
index 81c647e..adf91ef 100644
--- a/arch/um/include/asm/ptrace-generic.h
+++ b/arch/um/include/asm/ptrace-generic.h
@@ -36,7 +36,7 @@ extern long subarch_ptrace(struct task_struct *child, long request,
extern unsigned long getreg(struct task_struct *child, int regno);
extern int putreg(struct task_struct *child, int regno, unsigned long value);
-extern int arch_copy_tls(struct task_struct *new);
+extern int arch_set_tls(struct task_struct *new, unsigned long tls);
extern void clear_flushed_tls(struct task_struct *task);
extern int syscall_trace_enter(struct pt_regs *regs);
extern void syscall_trace_leave(struct pt_regs *regs);
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 263a8f0..17045e7 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -153,8 +153,8 @@ void fork_handler(void)
userspace(¤t->thread.regs.regs, current_thread_info()->aux_fp_regs);
}
-int copy_thread(unsigned long clone_flags, unsigned long sp,
- unsigned long arg, struct task_struct * p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
+ unsigned long arg, struct task_struct * p, unsigned long tls)
{
void (*handler)(void);
int kthread = current->flags & PF_KTHREAD;
@@ -188,7 +188,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
* Set a new TLS for the child thread?
*/
if (clone_flags & CLONE_SETTLS)
- ret = arch_copy_tls(p);
+ ret = arch_set_tls(p, tls);
}
return ret;
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 58a512e..ee60b81 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -244,6 +244,11 @@
leal efi32_config(%ebp), %eax
movl %eax, efi_config(%ebp)
+ /* Disable paging */
+ movl %cr0, %eax
+ btrl $X86_CR0_PG_BIT, %eax
+ movl %eax, %cr0
+
jmp startup_32
SYM_FUNC_END(efi32_stub_entry)
#endif
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index dbaa1b0..c37cb12 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -15,6 +15,7 @@
#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
+#define PCI_DEVICE_ID_INTEL_SKL_E3_IMC 0x1918
#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c
#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904
#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914
@@ -658,6 +659,10 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_E3_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
@@ -826,6 +831,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Quad Core */
IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Dual Core */
IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Quad Core */
+ IMC_DEV(SKL_E3_IMC, &skl_uncore_pci_driver), /* Xeon E3 V5 Gen Core processor */
IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver), /* 7th Gen Core Y */
IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U */
IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index b10a5ec..ad20220 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -369,11 +369,6 @@
#define SNR_M2M_PCI_PMON_BOX_CTL 0x438
#define SNR_M2M_PCI_PMON_UMASK_EXT 0xff
-/* SNR PCIE3 */
-#define SNR_PCIE3_PCI_PMON_CTL0 0x508
-#define SNR_PCIE3_PCI_PMON_CTR0 0x4e8
-#define SNR_PCIE3_PCI_PMON_BOX_CTL 0x4e4
-
/* SNR IMC */
#define SNR_IMC_MMIO_PMON_FIXED_CTL 0x54
#define SNR_IMC_MMIO_PMON_FIXED_CTR 0x38
@@ -4328,27 +4323,12 @@ static struct intel_uncore_type snr_uncore_m2m = {
.format_group = &snr_m2m_uncore_format_group,
};
-static struct intel_uncore_type snr_uncore_pcie3 = {
- .name = "pcie3",
- .num_counters = 4,
- .num_boxes = 1,
- .perf_ctr_bits = 48,
- .perf_ctr = SNR_PCIE3_PCI_PMON_CTR0,
- .event_ctl = SNR_PCIE3_PCI_PMON_CTL0,
- .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
- .box_ctl = SNR_PCIE3_PCI_PMON_BOX_CTL,
- .ops = &ivbep_uncore_pci_ops,
- .format_group = &ivbep_uncore_format_group,
-};
-
enum {
SNR_PCI_UNCORE_M2M,
- SNR_PCI_UNCORE_PCIE3,
};
static struct intel_uncore_type *snr_pci_uncores[] = {
[SNR_PCI_UNCORE_M2M] = &snr_uncore_m2m,
- [SNR_PCI_UNCORE_PCIE3] = &snr_uncore_pcie3,
NULL,
};
@@ -4357,10 +4337,6 @@ static const struct pci_device_id snr_uncore_pci_ids[] = {
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a),
.driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, SNR_PCI_UNCORE_M2M, 0),
},
- { /* PCIe3 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x334a),
- .driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 0, SNR_PCI_UNCORE_PCIE3, 0),
- },
{ /* end: all zeroes */ }
};
@@ -4536,6 +4512,7 @@ static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = {
INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"),
INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"),
INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"),
+ { /* end: all zeroes */ },
};
static struct intel_uncore_ops snr_uncore_imc_freerunning_ops = {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 90f75e5..62c3027 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -615,9 +615,9 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
return;
clear_all:
- clear_cpu_cap(c, X86_FEATURE_SME);
+ setup_clear_cpu_cap(X86_FEATURE_SME);
clear_sev:
- clear_cpu_cap(c, X86_FEATURE_SEV);
+ setup_clear_cpu_cap(X86_FEATURE_SEV);
}
}
diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c
index b38010b..6c3e1c9 100644
--- a/arch/x86/kernel/cpu/mce/therm_throt.c
+++ b/arch/x86/kernel/cpu/mce/therm_throt.c
@@ -467,6 +467,7 @@ static int thermal_throttle_online(unsigned int cpu)
{
struct thermal_state *state = &per_cpu(thermal_state, cpu);
struct device *dev = get_cpu_device(cpu);
+ u32 l;
state->package_throttle.level = PACKAGE_LEVEL;
state->core_throttle.level = CORE_LEVEL;
@@ -474,6 +475,10 @@ static int thermal_throttle_online(unsigned int cpu)
INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work);
INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work);
+ /* Unmask the thermal vector after the above workqueues are initialized. */
+ l = apic_read(APIC_LVTTHMR);
+ apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
+
return thermal_throttle_add_dev(dev, cpu);
}
@@ -722,10 +727,6 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h);
- /* Unmask the thermal vector: */
- l = apic_read(APIC_LVTTHMR);
- apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
-
pr_info_once("CPU0: Thermal monitoring enabled (%s)\n",
tm2 ? "TM2" : "TM1");
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 03eb90d..89049b3 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -618,7 +618,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
if (static_branch_unlikely(&rdt_mon_enable_key))
rmdir_mondata_subdir_allrdtgrp(r, d->id);
list_del(&d->list);
- if (is_mbm_enabled())
+ if (r->mon_capable && is_mbm_enabled())
cancel_delayed_work(&d->mbm_over);
if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) {
/*
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 2e3b06d..dac7209 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1741,9 +1741,6 @@ static int set_cache_qos_cfg(int level, bool enable)
struct rdt_domain *d;
int cpu;
- if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
- return -ENOMEM;
-
if (level == RDT_RESOURCE_L3)
update = l3_qos_cfg_update;
else if (level == RDT_RESOURCE_L2)
@@ -1751,6 +1748,9 @@ static int set_cache_qos_cfg(int level, bool enable)
else
return -EINVAL;
+ if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+ return -ENOMEM;
+
r_l = &rdt_resources_all[level];
list_for_each_entry(d, &r_l->domains, list) {
/* Pick one CPU from each domain instance to update MSR */
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 930edeb..0a74407 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -865,10 +865,8 @@ void arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
}
#endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index dcb9bc9..bcfede4 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1212,10 +1212,8 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
- struct zone *zone = page_zone(page);
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
kernel_physical_mapping_remove(start, start + size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 4c8a2d1..9ba08e9 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1328,7 +1328,7 @@ xadd: if (is_imm8(insn->off))
return proglen;
}
-static void save_regs(struct btf_func_model *m, u8 **prog, int nr_args,
+static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
int stack_size)
{
int i;
@@ -1344,7 +1344,7 @@ static void save_regs(struct btf_func_model *m, u8 **prog, int nr_args,
-(stack_size - i * 8));
}
-static void restore_regs(struct btf_func_model *m, u8 **prog, int nr_args,
+static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
int stack_size)
{
int i;
@@ -1361,7 +1361,7 @@ static void restore_regs(struct btf_func_model *m, u8 **prog, int nr_args,
-(stack_size - i * 8));
}
-static int invoke_bpf(struct btf_func_model *m, u8 **pprog,
+static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
struct bpf_prog **progs, int prog_cnt, int stack_size)
{
u8 *prog = *pprog;
@@ -1456,7 +1456,8 @@ static int invoke_bpf(struct btf_func_model *m, u8 **pprog,
* add rsp, 8 // skip eth_type_trans's frame
* ret // return to its caller
*/
-int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
+int arch_prepare_bpf_trampoline(void *image, void *image_end,
+ const struct btf_func_model *m, u32 flags,
struct bpf_prog **fentry_progs, int fentry_cnt,
struct bpf_prog **fexit_progs, int fexit_cnt,
void *orig_call)
@@ -1523,13 +1524,10 @@ int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags
/* skip our return address and return to parent */
EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
EMIT1(0xC3); /* ret */
- /* One half of the page has active running trampoline.
- * Another half is an area for next trampoline.
- * Make sure the trampoline generation logic doesn't overflow.
- */
- if (WARN_ON_ONCE(prog - (u8 *)image > PAGE_SIZE / 2 - BPF_INSN_SAFETY))
+ /* Make sure the trampoline generation logic doesn't overflow */
+ if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY))
return -EFAULT;
- return 0;
+ return prog - (u8 *)image;
}
static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index 5bd949d..ac8eee0 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -215,14 +215,12 @@ static int set_tls_entry(struct task_struct* task, struct user_desc *info,
return 0;
}
-int arch_copy_tls(struct task_struct *new)
+int arch_set_tls(struct task_struct *new, unsigned long tls)
{
struct user_desc info;
int idx, ret = -EFAULT;
- if (copy_from_user(&info,
- (void __user *) UPT_SI(&new->thread.regs.regs),
- sizeof(info)))
+ if (copy_from_user(&info, (void __user *) tls, sizeof(info)))
goto out;
ret = -EINVAL;
diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c
index 3a621e0..ebd3855 100644
--- a/arch/x86/um/tls_64.c
+++ b/arch/x86/um/tls_64.c
@@ -6,14 +6,13 @@ void clear_flushed_tls(struct task_struct *task)
{
}
-int arch_copy_tls(struct task_struct *t)
+int arch_set_tls(struct task_struct *t, unsigned long tls)
{
/*
* If CLONE_SETTLS is set, we need to save the thread id
- * (which is argument 5, child_tid, of clone) so it can be set
- * during context switches.
+ * so it can be set during context switches.
*/
- t->thread.arch.fs = t->thread.regs.regs.gp[R8 / sizeof(long)];
+ t->thread.arch.fs = tls;
return 0;
}
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 4a3fa29..296c532 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -24,6 +24,7 @@
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL
select HAVE_ARCH_TRACEHOOK
+ select HAVE_COPY_THREAD_TLS
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_EXIT_THREAD
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 9e1c491..3edecc4 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -202,8 +202,9 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
* involved. Much simpler to just not copy those live frames across.
*/
-int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn,
- unsigned long thread_fn_arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long usp_thread_fn,
+ unsigned long thread_fn_arg, struct task_struct *p,
+ unsigned long tls)
{
struct pt_regs *childregs = task_pt_regs(p);
@@ -266,9 +267,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn,
childregs->syscall = regs->syscall;
- /* The thread pointer is passed in the '4th argument' (= a5) */
if (clone_flags & CLONE_SETTLS)
- childregs->threadptr = childregs->areg[5];
+ childregs->threadptr = tls;
} else {
p->thread.ra = MAKE_RA_FOR_CALL(
(unsigned long)ret_from_kernel_thread, 1);
diff --git a/block/bio.c b/block/bio.c
index a5d75f6..94d6972 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -539,6 +539,55 @@ void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start)
EXPORT_SYMBOL(zero_fill_bio_iter);
/**
+ * bio_truncate - truncate the bio to small size of @new_size
+ * @bio: the bio to be truncated
+ * @new_size: new size for truncating the bio
+ *
+ * Description:
+ * Truncate the bio to new size of @new_size. If bio_op(bio) is
+ * REQ_OP_READ, zero the truncated part. This function should only
+ * be used for handling corner cases, such as bio eod.
+ */
+void bio_truncate(struct bio *bio, unsigned new_size)
+{
+ struct bio_vec bv;
+ struct bvec_iter iter;
+ unsigned int done = 0;
+ bool truncated = false;
+
+ if (new_size >= bio->bi_iter.bi_size)
+ return;
+
+ if (bio_op(bio) != REQ_OP_READ)
+ goto exit;
+
+ bio_for_each_segment(bv, bio, iter) {
+ if (done + bv.bv_len > new_size) {
+ unsigned offset;
+
+ if (!truncated)
+ offset = new_size - done;
+ else
+ offset = 0;
+ zero_user(bv.bv_page, offset, bv.bv_len - offset);
+ truncated = true;
+ }
+ done += bv.bv_len;
+ }
+
+ exit:
+ /*
+ * Don't touch bvec table here and make it really immutable, since
+ * fs bio user has to retrieve all pages via bio_for_each_segment_all
+ * in its .end_bio() callback.
+ *
+ * It is enough to truncate bio by updating .bi_size since we can make
+ * correct bvec with the updated .bi_size for drivers.
+ */
+ bio->bi_iter.bi_size = new_size;
+}
+
+/**
* bio_put - release a reference to a bio
* @bio: bio to release reference to
*
diff --git a/block/blk-merge.c b/block/blk-merge.c
index d783bdc..1534ed7 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -157,17 +157,20 @@ static inline unsigned get_max_io_size(struct request_queue *q,
return sectors & (lbs - 1);
}
-static unsigned get_max_segment_size(const struct request_queue *q,
- unsigned offset)
+static inline unsigned get_max_segment_size(const struct request_queue *q,
+ struct page *start_page,
+ unsigned long offset)
{
unsigned long mask = queue_segment_boundary(q);
- /* default segment boundary mask means no boundary limit */
- if (mask == BLK_SEG_BOUNDARY_MASK)
- return queue_max_segment_size(q);
+ offset = mask & (page_to_phys(start_page) + offset);
- return min_t(unsigned long, mask - (mask & offset) + 1,
- queue_max_segment_size(q));
+ /*
+ * overflow may be triggered in case of zero page physical address
+ * on 32bit arch, use queue's max segment size when that happens.
+ */
+ return min_not_zero(mask - offset + 1,
+ (unsigned long)queue_max_segment_size(q));
}
/**
@@ -201,7 +204,8 @@ static bool bvec_split_segs(const struct request_queue *q,
unsigned seg_size = 0;
while (len && *nsegs < max_segs) {
- seg_size = get_max_segment_size(q, bv->bv_offset + total_len);
+ seg_size = get_max_segment_size(q, bv->bv_page,
+ bv->bv_offset + total_len);
seg_size = min(seg_size, len);
(*nsegs)++;
@@ -419,7 +423,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q,
while (nbytes > 0) {
unsigned offset = bvec->bv_offset + total;
- unsigned len = min(get_max_segment_size(q, offset), nbytes);
+ unsigned len = min(get_max_segment_size(q, bvec->bv_page,
+ offset), nbytes);
struct page *page = bvec->bv_page;
/*
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5f6dcc7..c8eda2e 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -328,7 +328,7 @@ EXPORT_SYMBOL(blk_queue_max_segment_size);
* storage device can address. The default of 512 covers most
* hardware.
**/
-void blk_queue_logical_block_size(struct request_queue *q, unsigned short size)
+void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
{
q->limits.logical_block_size = size;
diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index b23d1e4..9d0d65e 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -374,7 +374,7 @@ static int do_rx_dma(struct atm_vcc *vcc,struct sk_buff *skb,
here = (eni_vcc->descr+skip) & (eni_vcc->words-1);
dma[j++] = (here << MID_DMA_COUNT_SHIFT) | (vcc->vci
<< MID_DMA_VCI_SHIFT) | MID_DT_JK;
- j++;
+ dma[j++] = 0;
}
here = (eni_vcc->descr+size+skip) & (eni_vcc->words-1);
if (!eff) size += skip;
@@ -447,7 +447,7 @@ static int do_rx_dma(struct atm_vcc *vcc,struct sk_buff *skb,
if (size != eff) {
dma[j++] = (here << MID_DMA_COUNT_SHIFT) |
(vcc->vci << MID_DMA_VCI_SHIFT) | MID_DT_JK;
- j++;
+ dma[j++] = 0;
}
if (!j || j > 2*RX_DMA_BUF) {
printk(KERN_CRIT DEV_LABEL "!j or j too big!!!\n");
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index aad00d2..cc87004 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -912,6 +912,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
}
if (!to) {
printk ("No more free channels for FS50..\n");
+ kfree(vcc);
return -EBUSY;
}
vcc->channo = dev->channo;
@@ -922,6 +923,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
if (((DO_DIRECTION(rxtp) && dev->atm_vccs[vcc->channo])) ||
( DO_DIRECTION(txtp) && test_bit (vcc->channo, dev->tx_inuse))) {
printk ("Channel is in use for FS155.\n");
+ kfree(vcc);
return -EBUSY;
}
}
@@ -935,6 +937,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
tc, sizeof (struct fs_transmit_config));
if (!tc) {
fs_dprintk (FS_DEBUG_OPEN, "fs: can't alloc transmit_config.\n");
+ kfree(vcc);
return -ENOMEM;
}
diff --git a/drivers/base/firmware_loader/builtin/Makefile b/drivers/base/firmware_loader/builtin/Makefile
index 4a66888..5fa7ce3 100644
--- a/drivers/base/firmware_loader/builtin/Makefile
+++ b/drivers/base/firmware_loader/builtin/Makefile
@@ -17,7 +17,7 @@
filechk_fwbin = \
echo "/* Generated by $(src)/Makefile */" ;\
echo " .section .rodata" ;\
- echo " .p2align $(ASM_ALIGN)" ;\
+ echo " .p2align 4" ;\
echo "_fw_$(FWSTR)_bin:" ;\
echo " .incbin \"$(fwdir)/$(FWNAME)\"" ;\
echo "_fw_end:" ;\
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index d4d88b5..ed34785 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -129,11 +129,13 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
return BLK_STS_IOERR;
case BLK_ZONE_COND_EMPTY:
case BLK_ZONE_COND_IMP_OPEN:
+ case BLK_ZONE_COND_EXP_OPEN:
+ case BLK_ZONE_COND_CLOSED:
/* Writes must be at the write pointer position */
if (sector != zone->wp)
return BLK_STS_IOERR;
- if (zone->cond == BLK_ZONE_COND_EMPTY)
+ if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
zone->cond = BLK_ZONE_COND_IMP_OPEN;
zone->wp += nr_sectors;
@@ -186,7 +188,10 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
if (zone->cond == BLK_ZONE_COND_FULL)
return BLK_STS_IOERR;
- zone->cond = BLK_ZONE_COND_CLOSED;
+ if (zone->wp == zone->start)
+ zone->cond = BLK_ZONE_COND_EMPTY;
+ else
+ zone->cond = BLK_ZONE_COND_CLOSED;
break;
case REQ_OP_ZONE_FINISH:
if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index f4d1597..ccb44fe 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -343,6 +343,12 @@ static int sysc_get_clocks(struct sysc *ddata)
return -EINVAL;
}
+ /* Always add a slot for main clocks fck and ick even if unused */
+ if (!nr_fck)
+ ddata->nr_clocks++;
+ if (!nr_ick)
+ ddata->nr_clocks++;
+
ddata->clocks = devm_kcalloc(ddata->dev,
ddata->nr_clocks, sizeof(*ddata->clocks),
GFP_KERNEL);
@@ -421,7 +427,7 @@ static int sysc_enable_opt_clocks(struct sysc *ddata)
struct clk *clock;
int i, error;
- if (!ddata->clocks)
+ if (!ddata->clocks || ddata->nr_clocks < SYSC_OPTFCK0 + 1)
return 0;
for (i = SYSC_OPTFCK0; i < SYSC_MAX_CLOCKS; i++) {
@@ -455,7 +461,7 @@ static void sysc_disable_opt_clocks(struct sysc *ddata)
struct clk *clock;
int i;
- if (!ddata->clocks)
+ if (!ddata->clocks || ddata->nr_clocks < SYSC_OPTFCK0 + 1)
return;
for (i = SYSC_OPTFCK0; i < SYSC_MAX_CLOCKS; i++) {
diff --git a/drivers/char/agp/isoch.c b/drivers/char/agp/isoch.c
index 31c374b..7ecf20a 100644
--- a/drivers/char/agp/isoch.c
+++ b/drivers/char/agp/isoch.c
@@ -84,7 +84,6 @@ static int agp_3_5_isochronous_node_enable(struct agp_bridge_data *bridge,
unsigned int cdev = 0;
u32 mnistat, tnistat, tstatus, mcmd;
u16 tnicmd, mnicmd;
- u8 mcapndx;
u32 tot_bw = 0, tot_n = 0, tot_rq = 0, y_max, rq_isoch, rq_async;
u32 step, rem, rem_isoch, rem_async;
int ret = 0;
@@ -138,8 +137,6 @@ static int agp_3_5_isochronous_node_enable(struct agp_bridge_data *bridge,
cur = list_entry(pos, struct agp_3_5_dev, list);
dev = cur->dev;
- mcapndx = cur->capndx;
-
pci_read_config_dword(dev, cur->capndx+AGPNISTAT, &mnistat);
master[cdev].maxbw = (mnistat >> 16) & 0xff;
@@ -251,8 +248,6 @@ static int agp_3_5_isochronous_node_enable(struct agp_bridge_data *bridge,
cur = master[cdev].dev;
dev = cur->dev;
- mcapndx = cur->capndx;
-
master[cdev].rq += (cdev == ndevs - 1)
? (rem_async + rem_isoch) : step;
@@ -319,7 +314,7 @@ int agp_3_5_enable(struct agp_bridge_data *bridge)
{
struct pci_dev *td = bridge->dev, *dev = NULL;
u8 mcapndx;
- u32 isoch, arqsz;
+ u32 isoch;
u32 tstatus, mstatus, ncapid;
u32 mmajor;
u16 mpstat;
@@ -334,8 +329,6 @@ int agp_3_5_enable(struct agp_bridge_data *bridge)
if (isoch == 0) /* isoch xfers not available, bail out. */
return -ENODEV;
- arqsz = (tstatus >> 13) & 0x7;
-
/*
* Allocate a head for our AGP 3.5 device list
* (multiple AGP v3 devices are allowed behind a single bridge).
diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c
index b23b0b9..87f4493 100644
--- a/drivers/char/tpm/tpm-dev-common.c
+++ b/drivers/char/tpm/tpm-dev-common.c
@@ -130,7 +130,7 @@ ssize_t tpm_common_read(struct file *file, char __user *buf,
priv->response_read = true;
ret_size = min_t(ssize_t, size, priv->response_length);
- if (!ret_size) {
+ if (ret_size <= 0) {
priv->response_length = 0;
goto out;
}
diff --git a/drivers/char/tpm/tpm-dev.h b/drivers/char/tpm/tpm-dev.h
index 1089fc0..f3742bcc 100644
--- a/drivers/char/tpm/tpm-dev.h
+++ b/drivers/char/tpm/tpm-dev.h
@@ -14,7 +14,7 @@ struct file_priv {
struct work_struct timeout_work;
struct work_struct async_work;
wait_queue_head_t async_wait;
- size_t response_length;
+ ssize_t response_length;
bool response_read;
bool command_enqueued;
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index bb0343f..27c6ca0 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -978,13 +978,13 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
if (wait_startup(chip, 0) != 0) {
rc = -ENODEV;
- goto err_start;
+ goto out_err;
}
/* Take control of the TPM's interrupt hardware and shut it off */
rc = tpm_tis_read32(priv, TPM_INT_ENABLE(priv->locality), &intmask);
if (rc < 0)
- goto err_start;
+ goto out_err;
intmask |= TPM_INTF_CMD_READY_INT | TPM_INTF_LOCALITY_CHANGE_INT |
TPM_INTF_DATA_AVAIL_INT | TPM_INTF_STS_VALID_INT;
@@ -993,21 +993,21 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
rc = tpm_chip_start(chip);
if (rc)
- goto err_start;
-
+ goto out_err;
rc = tpm2_probe(chip);
+ tpm_chip_stop(chip);
if (rc)
- goto err_probe;
+ goto out_err;
rc = tpm_tis_read32(priv, TPM_DID_VID(0), &vendor);
if (rc < 0)
- goto err_probe;
+ goto out_err;
priv->manufacturer_id = vendor;
rc = tpm_tis_read8(priv, TPM_RID(0), &rid);
if (rc < 0)
- goto err_probe;
+ goto out_err;
dev_info(dev, "%s TPM (device-id 0x%X, rev-id %d)\n",
(chip->flags & TPM_CHIP_FLAG_TPM2) ? "2.0" : "1.2",
@@ -1016,13 +1016,13 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
probe = probe_itpm(chip);
if (probe < 0) {
rc = -ENODEV;
- goto err_probe;
+ goto out_err;
}
/* Figure out the capabilities */
rc = tpm_tis_read32(priv, TPM_INTF_CAPS(priv->locality), &intfcaps);
if (rc < 0)
- goto err_probe;
+ goto out_err;
dev_dbg(dev, "TPM interface capabilities (0x%x):\n",
intfcaps);
@@ -1056,10 +1056,9 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
if (tpm_get_timeouts(chip)) {
dev_err(dev, "Could not get TPM timeouts and durations\n");
rc = -ENODEV;
- goto err_probe;
+ goto out_err;
}
- chip->flags |= TPM_CHIP_FLAG_IRQ;
if (irq) {
tpm_tis_probe_irq_single(chip, intmask, IRQF_SHARED,
irq);
@@ -1071,18 +1070,15 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
}
}
- tpm_chip_stop(chip);
-
rc = tpm_chip_register(chip);
if (rc)
- goto err_start;
+ goto out_err;
+
+ if (chip->ops->clk_enable != NULL)
+ chip->ops->clk_enable(chip, false);
return 0;
-
-err_probe:
- tpm_chip_stop(chip);
-
-err_start:
+out_err:
if ((chip->ops != NULL) && (chip->ops->clk_enable != NULL))
chip->ops->clk_enable(chip, false);
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 6a11239..772258d 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -3426,11 +3426,17 @@ static int __clk_core_init(struct clk_core *core)
if (core->flags & CLK_IS_CRITICAL) {
unsigned long flags;
- clk_core_prepare(core);
+ ret = clk_core_prepare(core);
+ if (ret)
+ goto out;
flags = clk_enable_lock();
- clk_core_enable(core);
+ ret = clk_core_enable(core);
clk_enable_unlock(flags);
+ if (ret) {
+ clk_core_unprepare(core);
+ goto out;
+ }
}
clk_core_reparent_orphans_nolock();
diff --git a/drivers/clk/mmp/clk-of-mmp2.c b/drivers/clk/mmp/clk-of-mmp2.c
index a60a1be..b4a95cb 100644
--- a/drivers/clk/mmp/clk-of-mmp2.c
+++ b/drivers/clk/mmp/clk-of-mmp2.c
@@ -134,7 +134,7 @@ static DEFINE_SPINLOCK(ssp3_lock);
static const char *ssp_parent_names[] = {"vctcxo_4", "vctcxo_2", "vctcxo", "pll1_16"};
static DEFINE_SPINLOCK(timer_lock);
-static const char *timer_parent_names[] = {"clk32", "vctcxo_2", "vctcxo_4", "vctcxo"};
+static const char *timer_parent_names[] = {"clk32", "vctcxo_4", "vctcxo_2", "vctcxo"};
static DEFINE_SPINLOCK(reset_lock);
diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c
index f7b370f..f6ce888 100644
--- a/drivers/clk/qcom/gcc-sdm845.c
+++ b/drivers/clk/qcom/gcc-sdm845.c
@@ -3255,6 +3255,7 @@ static struct gdsc hlos1_vote_aggre_noc_mmu_audio_tbu_gdsc = {
.name = "hlos1_vote_aggre_noc_mmu_audio_tbu_gdsc",
},
.pwrsts = PWRSTS_OFF_ON,
+ .flags = VOTABLE,
};
static struct gdsc hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc = {
@@ -3263,6 +3264,7 @@ static struct gdsc hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc = {
.name = "hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc",
},
.pwrsts = PWRSTS_OFF_ON,
+ .flags = VOTABLE,
};
static struct gdsc hlos1_vote_aggre_noc_mmu_tbu1_gdsc = {
@@ -3271,6 +3273,7 @@ static struct gdsc hlos1_vote_aggre_noc_mmu_tbu1_gdsc = {
.name = "hlos1_vote_aggre_noc_mmu_tbu1_gdsc",
},
.pwrsts = PWRSTS_OFF_ON,
+ .flags = VOTABLE,
};
static struct gdsc hlos1_vote_aggre_noc_mmu_tbu2_gdsc = {
@@ -3279,6 +3282,7 @@ static struct gdsc hlos1_vote_aggre_noc_mmu_tbu2_gdsc = {
.name = "hlos1_vote_aggre_noc_mmu_tbu2_gdsc",
},
.pwrsts = PWRSTS_OFF_ON,
+ .flags = VOTABLE,
};
static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = {
@@ -3287,6 +3291,7 @@ static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = {
.name = "hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc",
},
.pwrsts = PWRSTS_OFF_ON,
+ .flags = VOTABLE,
};
static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc = {
@@ -3295,6 +3300,7 @@ static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc = {
.name = "hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc",
},
.pwrsts = PWRSTS_OFF_ON,
+ .flags = VOTABLE,
};
static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf_gdsc = {
@@ -3303,6 +3309,7 @@ static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf_gdsc = {
.name = "hlos1_vote_mmnoc_mmu_tbu_sf_gdsc",
},
.pwrsts = PWRSTS_OFF_ON,
+ .flags = VOTABLE,
};
static struct clk_regmap *gcc_sdm845_clocks[] = {
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index 3a991ca..c9e5a1f 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -12,6 +12,7 @@
#include <linux/clk-provider.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/clk.h>
#include "clk.h"
#include "clk-cpu.h"
@@ -1646,6 +1647,13 @@ static void __init exynos5x_clk_init(struct device_node *np,
exynos5x_subcmus);
}
+ /*
+ * Keep top part of G3D clock path enabled permanently to ensure
+ * that the internal busses get their clock regardless of the
+ * main G3D clock enablement status.
+ */
+ clk_prepare_enable(__clk_lookup("mout_sw_aclk_g3d"));
+
samsung_clk_of_add_provider(np, ctx);
}
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c
index 45a1ed3..50f8d1bc 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c
@@ -23,9 +23,9 @@
*/
static const char * const ar100_r_apb2_parents[] = { "osc24M", "osc32k",
- "pll-periph0", "iosc" };
+ "iosc", "pll-periph0" };
static const struct ccu_mux_var_prediv ar100_r_apb2_predivs[] = {
- { .index = 2, .shift = 0, .width = 5 },
+ { .index = 3, .shift = 0, .width = 5 },
};
static struct ccu_div ar100_clk = {
@@ -51,17 +51,7 @@ static struct ccu_div ar100_clk = {
static CLK_FIXED_FACTOR_HW(r_ahb_clk, "r-ahb", &ar100_clk.common.hw, 1, 1, 0);
-static struct ccu_div r_apb1_clk = {
- .div = _SUNXI_CCU_DIV(0, 2),
-
- .common = {
- .reg = 0x00c,
- .hw.init = CLK_HW_INIT("r-apb1",
- "r-ahb",
- &ccu_div_ops,
- 0),
- },
-};
+static SUNXI_CCU_M(r_apb1_clk, "r-apb1", "r-ahb", 0x00c, 0, 2, 0);
static struct ccu_div r_apb2_clk = {
.div = _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO),
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r.c b/drivers/clk/sunxi-ng/ccu-sun8i-r.c
index 4646fdc..4c8c491 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-r.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-r.c
@@ -51,19 +51,7 @@ static struct ccu_div ar100_clk = {
static CLK_FIXED_FACTOR_HW(ahb0_clk, "ahb0", &ar100_clk.common.hw, 1, 1, 0);
-static struct ccu_div apb0_clk = {
- .div = _SUNXI_CCU_DIV_FLAGS(0, 2, CLK_DIVIDER_POWER_OF_TWO),
-
- .common = {
- .reg = 0x0c,
- .hw.init = CLK_HW_INIT_HW("apb0",
- &ahb0_clk.hw,
- &ccu_div_ops,
- 0),
- },
-};
-
-static SUNXI_CCU_M(a83t_apb0_clk, "apb0", "ahb0", 0x0c, 0, 2, 0);
+static SUNXI_CCU_M(apb0_clk, "apb0", "ahb0", 0x0c, 0, 2, 0);
/*
* Define the parent as an array that can be reused to save space
@@ -127,7 +115,7 @@ static struct ccu_mp a83t_ir_clk = {
static struct ccu_common *sun8i_a83t_r_ccu_clks[] = {
&ar100_clk.common,
- &a83t_apb0_clk.common,
+ &apb0_clk.common,
&apb0_pio_clk.common,
&apb0_ir_clk.common,
&apb0_timer_clk.common,
@@ -167,7 +155,7 @@ static struct clk_hw_onecell_data sun8i_a83t_r_hw_clks = {
.hws = {
[CLK_AR100] = &ar100_clk.common.hw,
[CLK_AHB0] = &ahb0_clk.hw,
- [CLK_APB0] = &a83t_apb0_clk.common.hw,
+ [CLK_APB0] = &apb0_clk.common.hw,
[CLK_APB0_PIO] = &apb0_pio_clk.common.hw,
[CLK_APB0_IR] = &apb0_ir_clk.common.hw,
[CLK_APB0_TIMER] = &apb0_timer_clk.common.hw,
@@ -282,9 +270,6 @@ static void __init sunxi_r_ccu_init(struct device_node *node,
static void __init sun8i_a83t_r_ccu_setup(struct device_node *node)
{
- /* Fix apb0 bus gate parents here */
- apb0_gate_parent[0] = &a83t_apb0_clk.common.hw;
-
sunxi_r_ccu_init(node, &sun8i_a83t_r_ccu_desc);
}
CLK_OF_DECLARE(sun8i_a83t_r_ccu, "allwinner,sun8i-a83t-r-ccu",
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r40.c b/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
index 8974908..23bfe1d 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
@@ -761,7 +761,8 @@ static struct ccu_mp outa_clk = {
.reg = 0x1f0,
.features = CCU_FEATURE_FIXED_PREDIV,
.hw.init = CLK_HW_INIT_PARENTS("outa", out_parents,
- &ccu_mp_ops, 0),
+ &ccu_mp_ops,
+ CLK_SET_RATE_PARENT),
}
};
@@ -779,7 +780,8 @@ static struct ccu_mp outb_clk = {
.reg = 0x1f4,
.features = CCU_FEATURE_FIXED_PREDIV,
.hw.init = CLK_HW_INIT_PARENTS("outb", out_parents,
- &ccu_mp_ops, 0),
+ &ccu_mp_ops,
+ CLK_SET_RATE_PARENT),
}
};
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c
index 5c779ee..0e36ca3 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c
@@ -618,7 +618,7 @@ static struct clk_hw_onecell_data sun8i_v3s_hw_clks = {
[CLK_MBUS] = &mbus_clk.common.hw,
[CLK_MIPI_CSI] = &mipi_csi_clk.common.hw,
},
- .num = CLK_NUMBER,
+ .num = CLK_PLL_DDR1 + 1,
};
static struct clk_hw_onecell_data sun8i_v3_hw_clks = {
@@ -700,7 +700,7 @@ static struct clk_hw_onecell_data sun8i_v3_hw_clks = {
[CLK_MBUS] = &mbus_clk.common.hw,
[CLK_MIPI_CSI] = &mipi_csi_clk.common.hw,
},
- .num = CLK_NUMBER,
+ .num = CLK_I2S0 + 1,
};
static struct ccu_reset_map sun8i_v3s_ccu_resets[] = {
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.h b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.h
index b0160d3..108eeee 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.h
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.h
@@ -51,6 +51,4 @@
#define CLK_PLL_DDR1 74
-#define CLK_NUMBER (CLK_I2S0 + 1)
-
#endif /* _CCU_SUN8I_H3_H_ */
diff --git a/drivers/clk/tegra/clk.c b/drivers/clk/tegra/clk.c
index e6bd6d1..f6cdce4 100644
--- a/drivers/clk/tegra/clk.c
+++ b/drivers/clk/tegra/clk.c
@@ -231,8 +231,10 @@ struct clk ** __init tegra_clk_init(void __iomem *regs, int num, int banks)
periph_banks = banks;
clks = kcalloc(num, sizeof(struct clk *), GFP_KERNEL);
- if (!clks)
+ if (!clks) {
kfree(periph_clk_enb_refcnt);
+ return NULL;
+ }
clk_num = num;
diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c
index f65e16c..8d4c08b 100644
--- a/drivers/clk/ti/clk-dra7-atl.c
+++ b/drivers/clk/ti/clk-dra7-atl.c
@@ -233,7 +233,6 @@ static int of_dra7_atl_clk_probe(struct platform_device *pdev)
cinfo->iobase = of_iomap(node, 0);
cinfo->dev = &pdev->dev;
pm_runtime_enable(cinfo->dev);
- pm_runtime_irq_safe(cinfo->dev);
pm_runtime_get_sync(cinfo->dev);
atl_write(cinfo, DRA7_ATL_PCLKMUX_REG(0), DRA7_ATL_PCLKMUX);
diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index 4e54856..c4f15c4 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -56,7 +56,7 @@ static unsigned long long riscv_clocksource_rdtime(struct clocksource *cs)
return get_cycles64();
}
-static u64 riscv_sched_clock(void)
+static u64 notrace riscv_sched_clock(void)
{
return get_cycles64();
}
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index f1d170d..aba591d5 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -121,6 +121,8 @@ static const struct of_device_id blacklist[] __initconst = {
{ .compatible = "mediatek,mt8176", },
{ .compatible = "mediatek,mt8183", },
+ { .compatible = "nvidia,tegra20", },
+ { .compatible = "nvidia,tegra30", },
{ .compatible = "nvidia,tegra124", },
{ .compatible = "nvidia,tegra210", },
diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c
index de7e706..6deaaf5 100644
--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -198,7 +198,7 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
* pattern detection.
*/
cpu_data->intervals[cpu_data->interval_idx++] = measured_ns;
- if (cpu_data->interval_idx > INTERVALS)
+ if (cpu_data->interval_idx >= INTERVALS)
cpu_data->interval_idx = 0;
}
diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h
index 26754d0..b846d73 100644
--- a/drivers/crypto/hisilicon/sec2/sec.h
+++ b/drivers/crypto/hisilicon/sec2/sec.h
@@ -40,7 +40,7 @@ struct sec_req {
int req_id;
/* Status of the SEC request */
- int fake_busy;
+ atomic_t fake_busy;
};
/**
@@ -132,8 +132,8 @@ struct sec_debug_file {
};
struct sec_dfx {
- u64 send_cnt;
- u64 recv_cnt;
+ atomic64_t send_cnt;
+ atomic64_t recv_cnt;
};
struct sec_debug {
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c
index 62b04e1..0a5391f 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.c
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c
@@ -120,7 +120,7 @@ static void sec_req_cb(struct hisi_qp *qp, void *resp)
return;
}
- __sync_add_and_fetch(&req->ctx->sec->debug.dfx.recv_cnt, 1);
+ atomic64_inc(&req->ctx->sec->debug.dfx.recv_cnt);
req->ctx->req_op->buf_unmap(req->ctx, req);
@@ -135,13 +135,13 @@ static int sec_bd_send(struct sec_ctx *ctx, struct sec_req *req)
mutex_lock(&qp_ctx->req_lock);
ret = hisi_qp_send(qp_ctx->qp, &req->sec_sqe);
mutex_unlock(&qp_ctx->req_lock);
- __sync_add_and_fetch(&ctx->sec->debug.dfx.send_cnt, 1);
+ atomic64_inc(&ctx->sec->debug.dfx.send_cnt);
if (ret == -EBUSY)
return -ENOBUFS;
if (!ret) {
- if (req->fake_busy)
+ if (atomic_read(&req->fake_busy))
ret = -EBUSY;
else
ret = -EINPROGRESS;
@@ -641,7 +641,7 @@ static void sec_skcipher_callback(struct sec_ctx *ctx, struct sec_req *req)
if (ctx->c_ctx.c_mode == SEC_CMODE_CBC && req->c_req.encrypt)
sec_update_iv(req);
- if (__sync_bool_compare_and_swap(&req->fake_busy, 1, 0))
+ if (atomic_cmpxchg(&req->fake_busy, 1, 0) != 1)
sk_req->base.complete(&sk_req->base, -EINPROGRESS);
sk_req->base.complete(&sk_req->base, req->err_type);
@@ -672,9 +672,9 @@ static int sec_request_init(struct sec_ctx *ctx, struct sec_req *req)
}
if (ctx->fake_req_limit <= atomic_inc_return(&qp_ctx->pending_reqs))
- req->fake_busy = 1;
+ atomic_set(&req->fake_busy, 1);
else
- req->fake_busy = 0;
+ atomic_set(&req->fake_busy, 0);
ret = ctx->req_op->get_res(ctx, req);
if (ret) {
diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c
index 74f0654..ab742df 100644
--- a/drivers/crypto/hisilicon/sec2/sec_main.c
+++ b/drivers/crypto/hisilicon/sec2/sec_main.c
@@ -608,6 +608,14 @@ static const struct file_operations sec_dbg_fops = {
.write = sec_debug_write,
};
+static int debugfs_atomic64_t_get(void *data, u64 *val)
+{
+ *val = atomic64_read((atomic64_t *)data);
+ return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic64_t_ro, debugfs_atomic64_t_get, NULL,
+ "%lld\n");
+
static int sec_core_debug_init(struct sec_dev *sec)
{
struct hisi_qm *qm = &sec->qm;
@@ -628,9 +636,11 @@ static int sec_core_debug_init(struct sec_dev *sec)
debugfs_create_regset32("regs", 0444, tmp_d, regset);
- debugfs_create_u64("send_cnt", 0444, tmp_d, &dfx->send_cnt);
+ debugfs_create_file("send_cnt", 0444, tmp_d, &dfx->send_cnt,
+ &fops_atomic64_t_ro);
- debugfs_create_u64("recv_cnt", 0444, tmp_d, &dfx->recv_cnt);
+ debugfs_create_file("recv_cnt", 0444, tmp_d, &dfx->recv_cnt,
+ &fops_atomic64_t_ro);
return 0;
}
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index fa626acd..44af435 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -999,7 +999,8 @@ static const struct jz4780_dma_soc_data jz4740_dma_soc_data = {
static const struct jz4780_dma_soc_data jz4725b_dma_soc_data = {
.nb_channels = 6,
.transfer_ord_max = 5,
- .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC,
+ .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC |
+ JZ_SOC_DATA_BREAK_LINKS,
};
static const struct jz4780_dma_soc_data jz4770_dma_soc_data = {
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 1a422a8..18c011e 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -377,10 +377,11 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
descs->virt = dma_alloc_coherent(to_dev(ioat_chan),
SZ_2M, &descs->hw, flags);
- if (!descs->virt && (i > 0)) {
+ if (!descs->virt) {
int idx;
for (idx = 0; idx < i; idx++) {
+ descs = &ioat_chan->descs[idx];
dma_free_coherent(to_dev(ioat_chan), SZ_2M,
descs->virt, descs->hw);
descs->virt = NULL;
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index adecea5..c5c1aa0 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -229,9 +229,11 @@ static irqreturn_t k3_dma_int_handler(int irq, void *dev_id)
c = p->vchan;
if (c && (tc1 & BIT(i))) {
spin_lock_irqsave(&c->vc.lock, flags);
- vchan_cookie_complete(&p->ds_run->vd);
- p->ds_done = p->ds_run;
- p->ds_run = NULL;
+ if (p->ds_run != NULL) {
+ vchan_cookie_complete(&p->ds_run->vd);
+ p->ds_done = p->ds_run;
+ p->ds_run = NULL;
+ }
spin_unlock_irqrestore(&c->vc.lock, flags);
}
if (c && (tc2 & BIT(i))) {
@@ -271,6 +273,10 @@ static int k3_dma_start_txd(struct k3_dma_chan *c)
if (BIT(c->phy->idx) & k3_dma_get_chan_stat(d))
return -EAGAIN;
+ /* Avoid losing track of ds_run if a transaction is in flight */
+ if (c->phy->ds_run)
+ return -EAGAIN;
+
if (vd) {
struct k3_dma_desc_sw *ds =
container_of(vd, struct k3_dma_desc_sw, vd);
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index ec4adf4..256fc66 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -104,9 +104,8 @@ static void vchan_complete(unsigned long arg)
dmaengine_desc_get_callback(&vd->tx, &cb);
list_del(&vd->node);
- vchan_vdesc_fini(vd);
-
dmaengine_desc_callback_invoke(&cb, &vd->tx_result);
+ vchan_vdesc_fini(vd);
}
}
diff --git a/drivers/edac/sifive_edac.c b/drivers/edac/sifive_edac.c
index 413cdb4..c0cc72a 100644
--- a/drivers/edac/sifive_edac.c
+++ b/drivers/edac/sifive_edac.c
@@ -10,7 +10,7 @@
#include <linux/edac.h>
#include <linux/platform_device.h>
#include "edac_module.h"
-#include <asm/sifive_l2_cache.h>
+#include <soc/sifive/sifive_l2_cache.h>
#define DRVNAME "sifive_edac"
diff --git a/drivers/firmware/broadcom/tee_bnxt_fw.c b/drivers/firmware/broadcom/tee_bnxt_fw.c
index 5b7ef89..ed10da5 100644
--- a/drivers/firmware/broadcom/tee_bnxt_fw.c
+++ b/drivers/firmware/broadcom/tee_bnxt_fw.c
@@ -215,7 +215,6 @@ static int tee_bnxt_fw_probe(struct device *dev)
fw_shm_pool = tee_shm_alloc(pvt_data.ctx, MAX_SHM_MEM_SZ,
TEE_SHM_MAPPED | TEE_SHM_DMA_BUF);
if (IS_ERR(fw_shm_pool)) {
- tee_client_close_context(pvt_data.ctx);
dev_err(pvt_data.dev, "tee_shm_alloc failed\n");
err = PTR_ERR(fw_shm_pool);
goto out_sess;
diff --git a/drivers/firmware/efi/earlycon.c b/drivers/firmware/efi/earlycon.c
index d4077db..5d4f847 100644
--- a/drivers/firmware/efi/earlycon.c
+++ b/drivers/firmware/efi/earlycon.c
@@ -17,7 +17,7 @@ static const struct console *earlycon_console __initdata;
static const struct font_desc *font;
static u32 efi_x, efi_y;
static u64 fb_base;
-static pgprot_t fb_prot;
+static bool fb_wb;
static void *efi_fb;
/*
@@ -33,10 +33,8 @@ static int __init efi_earlycon_remap_fb(void)
if (!earlycon_console || !(earlycon_console->flags & CON_ENABLED))
return 0;
- if (pgprot_val(fb_prot) == pgprot_val(PAGE_KERNEL))
- efi_fb = memremap(fb_base, screen_info.lfb_size, MEMREMAP_WB);
- else
- efi_fb = memremap(fb_base, screen_info.lfb_size, MEMREMAP_WC);
+ efi_fb = memremap(fb_base, screen_info.lfb_size,
+ fb_wb ? MEMREMAP_WB : MEMREMAP_WC);
return efi_fb ? 0 : -ENOMEM;
}
@@ -53,9 +51,12 @@ late_initcall(efi_earlycon_unmap_fb);
static __ref void *efi_earlycon_map(unsigned long start, unsigned long len)
{
+ pgprot_t fb_prot;
+
if (efi_fb)
return efi_fb + start;
+ fb_prot = fb_wb ? PAGE_KERNEL : pgprot_writecombine(PAGE_KERNEL);
return early_memremap_prot(fb_base + start, len, pgprot_val(fb_prot));
}
@@ -215,10 +216,7 @@ static int __init efi_earlycon_setup(struct earlycon_device *device,
if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
fb_base |= (u64)screen_info.ext_lfb_base << 32;
- if (opt && !strcmp(opt, "ram"))
- fb_prot = PAGE_KERNEL;
- else
- fb_prot = pgprot_writecombine(PAGE_KERNEL);
+ fb_wb = opt && !strcmp(opt, "ram");
si = &screen_info;
xres = si->lfb_width;
diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c
index 35edd7c..97378cf 100644
--- a/drivers/firmware/efi/libstub/random.c
+++ b/drivers/firmware/efi/libstub/random.c
@@ -33,7 +33,7 @@ efi_status_t efi_get_random_bytes(efi_system_table_t *sys_table_arg,
{
efi_guid_t rng_proto = EFI_RNG_PROTOCOL_GUID;
efi_status_t status;
- struct efi_rng_protocol *rng;
+ struct efi_rng_protocol *rng = NULL;
status = efi_call_early(locate_protocol, &rng_proto, NULL,
(void **)&rng);
@@ -162,8 +162,8 @@ efi_status_t efi_random_get_seed(efi_system_table_t *sys_table_arg)
efi_guid_t rng_proto = EFI_RNG_PROTOCOL_GUID;
efi_guid_t rng_algo_raw = EFI_RNG_ALGORITHM_RAW;
efi_guid_t rng_table_guid = LINUX_EFI_RANDOM_SEED_TABLE_GUID;
- struct efi_rng_protocol *rng;
- struct linux_efi_random_seed *seed;
+ struct efi_rng_protocol *rng = NULL;
+ struct linux_efi_random_seed *seed = NULL;
efi_status_t status;
status = efi_call_early(locate_protocol, &rng_proto, NULL,
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 6ab25fe..4b6d2ef 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -573,7 +573,6 @@
tristate "Cavium ThunderX/OCTEON-TX GPIO"
depends on ARCH_THUNDER || (64BIT && COMPILE_TEST)
depends on PCI_MSI
- select GPIOLIB_IRQCHIP
select IRQ_DOMAIN_HIERARCHY
select IRQ_FASTEOI_HIERARCHY_HANDLERS
help
@@ -1148,6 +1147,7 @@
config GPIO_MAX77620
tristate "GPIO support for PMIC MAX77620 and MAX20024"
depends on MFD_MAX77620
+ select GPIOLIB_IRQCHIP
help
GPIO driver for MAX77620 and MAX20024 PMIC from Maxim Semiconductor.
MAX77620 PMIC has 8 pins that can be configured as GPIOs. The
diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c
index c4fdc19..94b8d3ae 100644
--- a/drivers/gpio/gpio-mockup.c
+++ b/drivers/gpio/gpio-mockup.c
@@ -156,7 +156,7 @@ static int gpio_mockup_apply_pull(struct gpio_mockup_chip *chip,
mutex_lock(&chip->lock);
if (test_bit(FLAG_REQUESTED, &desc->flags) &&
- !test_bit(FLAG_IS_OUT, &desc->flags)) {
+ !test_bit(FLAG_IS_OUT, &desc->flags)) {
curr = __gpio_mockup_get(chip, offset);
if (curr == value)
goto out;
@@ -165,7 +165,7 @@ static int gpio_mockup_apply_pull(struct gpio_mockup_chip *chip,
irq_type = irq_get_trigger_type(irq);
if ((value == 1 && (irq_type & IRQ_TYPE_EDGE_RISING)) ||
- (value == 0 && (irq_type & IRQ_TYPE_EDGE_FALLING)))
+ (value == 0 && (irq_type & IRQ_TYPE_EDGE_FALLING)))
irq_sim_fire(sim, offset);
}
diff --git a/drivers/gpio/gpio-thunderx.c b/drivers/gpio/gpio-thunderx.c
index d08d86a..4627704 100644
--- a/drivers/gpio/gpio-thunderx.c
+++ b/drivers/gpio/gpio-thunderx.c
@@ -53,6 +53,7 @@ struct thunderx_line {
struct thunderx_gpio {
struct gpio_chip chip;
u8 __iomem *register_base;
+ struct irq_domain *irqd;
struct msix_entry *msix_entries; /* per line MSI-X */
struct thunderx_line *line_entries; /* per line irq info */
raw_spinlock_t lock;
@@ -285,60 +286,54 @@ static void thunderx_gpio_set_multiple(struct gpio_chip *chip,
}
}
-static void thunderx_gpio_irq_ack(struct irq_data *d)
+static void thunderx_gpio_irq_ack(struct irq_data *data)
{
- struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
- struct thunderx_gpio *txgpio = gpiochip_get_data(gc);
+ struct thunderx_line *txline = irq_data_get_irq_chip_data(data);
writeq(GPIO_INTR_INTR,
- txgpio->register_base + intr_reg(irqd_to_hwirq(d)));
+ txline->txgpio->register_base + intr_reg(txline->line));
}
-static void thunderx_gpio_irq_mask(struct irq_data *d)
+static void thunderx_gpio_irq_mask(struct irq_data *data)
{
- struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
- struct thunderx_gpio *txgpio = gpiochip_get_data(gc);
+ struct thunderx_line *txline = irq_data_get_irq_chip_data(data);
writeq(GPIO_INTR_ENA_W1C,
- txgpio->register_base + intr_reg(irqd_to_hwirq(d)));
+ txline->txgpio->register_base + intr_reg(txline->line));
}
-static void thunderx_gpio_irq_mask_ack(struct irq_data *d)
+static void thunderx_gpio_irq_mask_ack(struct irq_data *data)
{
- struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
- struct thunderx_gpio *txgpio = gpiochip_get_data(gc);
+ struct thunderx_line *txline = irq_data_get_irq_chip_data(data);
writeq(GPIO_INTR_ENA_W1C | GPIO_INTR_INTR,
- txgpio->register_base + intr_reg(irqd_to_hwirq(d)));
+ txline->txgpio->register_base + intr_reg(txline->line));
}
-static void thunderx_gpio_irq_unmask(struct irq_data *d)
+static void thunderx_gpio_irq_unmask(struct irq_data *data)
{
- struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
- struct thunderx_gpio *txgpio = gpiochip_get_data(gc);
+ struct thunderx_line *txline = irq_data_get_irq_chip_data(data);
writeq(GPIO_INTR_ENA_W1S,
- txgpio->register_base + intr_reg(irqd_to_hwirq(d)));
+ txline->txgpio->register_base + intr_reg(txline->line));
}
-static int thunderx_gpio_irq_set_type(struct irq_data *d,
+static int thunderx_gpio_irq_set_type(struct irq_data *data,
unsigned int flow_type)
{
- struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
- struct thunderx_gpio *txgpio = gpiochip_get_data(gc);
- struct thunderx_line *txline =
- &txgpio->line_entries[irqd_to_hwirq(d)];
+ struct thunderx_line *txline = irq_data_get_irq_chip_data(data);
+ struct thunderx_gpio *txgpio = txline->txgpio;
u64 bit_cfg;
- irqd_set_trigger_type(d, flow_type);
+ irqd_set_trigger_type(data, flow_type);
bit_cfg = txline->fil_bits | GPIO_BIT_CFG_INT_EN;
if (flow_type & IRQ_TYPE_EDGE_BOTH) {
- irq_set_handler_locked(d, handle_fasteoi_ack_irq);
+ irq_set_handler_locked(data, handle_fasteoi_ack_irq);
bit_cfg |= GPIO_BIT_CFG_INT_TYPE;
} else {
- irq_set_handler_locked(d, handle_fasteoi_mask_irq);
+ irq_set_handler_locked(data, handle_fasteoi_mask_irq);
}
raw_spin_lock(&txgpio->lock);
@@ -367,6 +362,33 @@ static void thunderx_gpio_irq_disable(struct irq_data *data)
irq_chip_disable_parent(data);
}
+static int thunderx_gpio_irq_request_resources(struct irq_data *data)
+{
+ struct thunderx_line *txline = irq_data_get_irq_chip_data(data);
+ struct thunderx_gpio *txgpio = txline->txgpio;
+ int r;
+
+ r = gpiochip_lock_as_irq(&txgpio->chip, txline->line);
+ if (r)
+ return r;
+
+ r = irq_chip_request_resources_parent(data);
+ if (r)
+ gpiochip_unlock_as_irq(&txgpio->chip, txline->line);
+
+ return r;
+}
+
+static void thunderx_gpio_irq_release_resources(struct irq_data *data)
+{
+ struct thunderx_line *txline = irq_data_get_irq_chip_data(data);
+ struct thunderx_gpio *txgpio = txline->txgpio;
+
+ irq_chip_release_resources_parent(data);
+
+ gpiochip_unlock_as_irq(&txgpio->chip, txline->line);
+}
+
/*
* Interrupts are chained from underlying MSI-X vectors. We have
* these irq_chip functions to be able to handle level triggering
@@ -383,24 +405,50 @@ static struct irq_chip thunderx_gpio_irq_chip = {
.irq_unmask = thunderx_gpio_irq_unmask,
.irq_eoi = irq_chip_eoi_parent,
.irq_set_affinity = irq_chip_set_affinity_parent,
+ .irq_request_resources = thunderx_gpio_irq_request_resources,
+ .irq_release_resources = thunderx_gpio_irq_release_resources,
.irq_set_type = thunderx_gpio_irq_set_type,
.flags = IRQCHIP_SET_TYPE_MASKED
};
-static int thunderx_gpio_child_to_parent_hwirq(struct gpio_chip *gc,
- unsigned int child,
- unsigned int child_type,
- unsigned int *parent,
- unsigned int *parent_type)
+static int thunderx_gpio_irq_translate(struct irq_domain *d,
+ struct irq_fwspec *fwspec,
+ irq_hw_number_t *hwirq,
+ unsigned int *type)
{
- struct thunderx_gpio *txgpio = gpiochip_get_data(gc);
+ struct thunderx_gpio *txgpio = d->host_data;
- *parent = txgpio->base_msi + (2 * child);
- *parent_type = IRQ_TYPE_LEVEL_HIGH;
+ if (WARN_ON(fwspec->param_count < 2))
+ return -EINVAL;
+ if (fwspec->param[0] >= txgpio->chip.ngpio)
+ return -EINVAL;
+ *hwirq = fwspec->param[0];
+ *type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK;
return 0;
}
+static int thunderx_gpio_irq_alloc(struct irq_domain *d, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
+{
+ struct thunderx_line *txline = arg;
+
+ return irq_domain_set_hwirq_and_chip(d, virq, txline->line,
+ &thunderx_gpio_irq_chip, txline);
+}
+
+static const struct irq_domain_ops thunderx_gpio_irqd_ops = {
+ .alloc = thunderx_gpio_irq_alloc,
+ .translate = thunderx_gpio_irq_translate
+};
+
+static int thunderx_gpio_to_irq(struct gpio_chip *chip, unsigned int offset)
+{
+ struct thunderx_gpio *txgpio = gpiochip_get_data(chip);
+
+ return irq_find_mapping(txgpio->irqd, offset);
+}
+
static int thunderx_gpio_probe(struct pci_dev *pdev,
const struct pci_device_id *id)
{
@@ -408,7 +456,6 @@ static int thunderx_gpio_probe(struct pci_dev *pdev,
struct device *dev = &pdev->dev;
struct thunderx_gpio *txgpio;
struct gpio_chip *chip;
- struct gpio_irq_chip *girq;
int ngpio, i;
int err = 0;
@@ -453,8 +500,8 @@ static int thunderx_gpio_probe(struct pci_dev *pdev,
}
txgpio->msix_entries = devm_kcalloc(dev,
- ngpio, sizeof(struct msix_entry),
- GFP_KERNEL);
+ ngpio, sizeof(struct msix_entry),
+ GFP_KERNEL);
if (!txgpio->msix_entries) {
err = -ENOMEM;
goto out;
@@ -495,6 +542,27 @@ static int thunderx_gpio_probe(struct pci_dev *pdev,
if (err < 0)
goto out;
+ /*
+ * Push GPIO specific irqdomain on hierarchy created as a side
+ * effect of the pci_enable_msix()
+ */
+ txgpio->irqd = irq_domain_create_hierarchy(irq_get_irq_data(txgpio->msix_entries[0].vector)->domain,
+ 0, 0, of_node_to_fwnode(dev->of_node),
+ &thunderx_gpio_irqd_ops, txgpio);
+ if (!txgpio->irqd) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ /* Push on irq_data and the domain for each line. */
+ for (i = 0; i < ngpio; i++) {
+ err = irq_domain_push_irq(txgpio->irqd,
+ txgpio->msix_entries[i].vector,
+ &txgpio->line_entries[i]);
+ if (err < 0)
+ dev_err(dev, "irq_domain_push_irq: %d\n", err);
+ }
+
chip->label = KBUILD_MODNAME;
chip->parent = dev;
chip->owner = THIS_MODULE;
@@ -509,28 +577,11 @@ static int thunderx_gpio_probe(struct pci_dev *pdev,
chip->set = thunderx_gpio_set;
chip->set_multiple = thunderx_gpio_set_multiple;
chip->set_config = thunderx_gpio_set_config;
- girq = &chip->irq;
- girq->chip = &thunderx_gpio_irq_chip;
- girq->fwnode = of_node_to_fwnode(dev->of_node);
- girq->parent_domain =
- irq_get_irq_data(txgpio->msix_entries[0].vector)->domain;
- girq->child_to_parent_hwirq = thunderx_gpio_child_to_parent_hwirq;
- girq->handler = handle_bad_irq;
- girq->default_type = IRQ_TYPE_NONE;
-
+ chip->to_irq = thunderx_gpio_to_irq;
err = devm_gpiochip_add_data(dev, chip, txgpio);
if (err)
goto out;
- /* Push on irq_data and the domain for each line. */
- for (i = 0; i < ngpio; i++) {
- err = irq_domain_push_irq(chip->irq.domain,
- txgpio->msix_entries[i].vector,
- chip);
- if (err < 0)
- dev_err(dev, "irq_domain_push_irq: %d\n", err);
- }
-
dev_info(dev, "ThunderX GPIO: %d lines with base %d.\n",
ngpio, chip->base);
return 0;
@@ -545,10 +596,10 @@ static void thunderx_gpio_remove(struct pci_dev *pdev)
struct thunderx_gpio *txgpio = pci_get_drvdata(pdev);
for (i = 0; i < txgpio->chip.ngpio; i++)
- irq_domain_pop_irq(txgpio->chip.irq.domain,
+ irq_domain_pop_irq(txgpio->irqd,
txgpio->msix_entries[i].vector);
- irq_domain_remove(txgpio->chip.irq.domain);
+ irq_domain_remove(txgpio->irqd);
pci_set_drvdata(pdev, NULL);
}
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 4c3f637..05ba16f 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -684,6 +684,8 @@ static void zynq_gpio_restore_context(struct zynq_gpio *gpio)
unsigned int bank_num;
for (bank_num = 0; bank_num < gpio->p_data->max_bank; bank_num++) {
+ writel_relaxed(ZYNQ_GPIO_IXR_DISABLE_ALL, gpio->base_addr +
+ ZYNQ_GPIO_INTDIS_OFFSET(bank_num));
writel_relaxed(gpio->context.datalsw[bank_num],
gpio->base_addr +
ZYNQ_GPIO_DATA_LSW_OFFSET(bank_num));
@@ -693,9 +695,6 @@ static void zynq_gpio_restore_context(struct zynq_gpio *gpio)
writel_relaxed(gpio->context.dirm[bank_num],
gpio->base_addr +
ZYNQ_GPIO_DIRM_OFFSET(bank_num));
- writel_relaxed(gpio->context.int_en[bank_num],
- gpio->base_addr +
- ZYNQ_GPIO_INTEN_OFFSET(bank_num));
writel_relaxed(gpio->context.int_type[bank_num],
gpio->base_addr +
ZYNQ_GPIO_INTTYPE_OFFSET(bank_num));
@@ -705,6 +704,9 @@ static void zynq_gpio_restore_context(struct zynq_gpio *gpio)
writel_relaxed(gpio->context.int_any[bank_num],
gpio->base_addr +
ZYNQ_GPIO_INTANY_OFFSET(bank_num));
+ writel_relaxed(~(gpio->context.int_en[bank_num]),
+ gpio->base_addr +
+ ZYNQ_GPIO_INTEN_OFFSET(bank_num));
}
}
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index d30e57d..31fee5e 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -21,11 +21,19 @@
#include "gpiolib.h"
#include "gpiolib-acpi.h"
+#define QUIRK_NO_EDGE_EVENTS_ON_BOOT 0x01l
+#define QUIRK_NO_WAKEUP 0x02l
+
static int run_edge_events_on_boot = -1;
module_param(run_edge_events_on_boot, int, 0444);
MODULE_PARM_DESC(run_edge_events_on_boot,
"Run edge _AEI event-handlers at boot: 0=no, 1=yes, -1=auto");
+static int honor_wakeup = -1;
+module_param(honor_wakeup, int, 0444);
+MODULE_PARM_DESC(honor_wakeup,
+ "Honor the ACPI wake-capable flag: 0=no, 1=yes, -1=auto");
+
/**
* struct acpi_gpio_event - ACPI GPIO event handler data
*
@@ -281,7 +289,7 @@ static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares,
event->handle = evt_handle;
event->handler = handler;
event->irq = irq;
- event->irq_is_wake = agpio->wake_capable == ACPI_WAKE_CAPABLE;
+ event->irq_is_wake = honor_wakeup && agpio->wake_capable == ACPI_WAKE_CAPABLE;
event->pin = pin;
event->desc = desc;
@@ -1309,7 +1317,7 @@ static int acpi_gpio_handle_deferred_request_irqs(void)
/* We must use _sync so that this runs after the first deferred_probe run */
late_initcall_sync(acpi_gpio_handle_deferred_request_irqs);
-static const struct dmi_system_id run_edge_events_on_boot_blacklist[] = {
+static const struct dmi_system_id gpiolib_acpi_quirks[] = {
{
/*
* The Minix Neo Z83-4 has a micro-USB-B id-pin handler for
@@ -1319,7 +1327,8 @@ static const struct dmi_system_id run_edge_events_on_boot_blacklist[] = {
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "MINIX"),
DMI_MATCH(DMI_PRODUCT_NAME, "Z83-4"),
- }
+ },
+ .driver_data = (void *)QUIRK_NO_EDGE_EVENTS_ON_BOOT,
},
{
/*
@@ -1331,20 +1340,52 @@ static const struct dmi_system_id run_edge_events_on_boot_blacklist[] = {
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Wortmann_AG"),
DMI_MATCH(DMI_PRODUCT_NAME, "TERRA_PAD_1061"),
- }
+ },
+ .driver_data = (void *)QUIRK_NO_EDGE_EVENTS_ON_BOOT,
+ },
+ {
+ /*
+ * Various HP X2 10 Cherry Trail models use an external
+ * embedded-controller connected via I2C + an ACPI GPIO
+ * event handler. The embedded controller generates various
+ * spurious wakeup events when suspended. So disable wakeup
+ * for its handler (it uses the only ACPI GPIO event handler).
+ * This breaks wakeup when opening the lid, the user needs
+ * to press the power-button to wakeup the system. The
+ * alternative is suspend simply not working, which is worse.
+ */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP x2 Detachable 10-p0XX"),
+ },
+ .driver_data = (void *)QUIRK_NO_WAKEUP,
},
{} /* Terminating entry */
};
static int acpi_gpio_setup_params(void)
{
+ const struct dmi_system_id *id;
+ long quirks = 0;
+
+ id = dmi_first_match(gpiolib_acpi_quirks);
+ if (id)
+ quirks = (long)id->driver_data;
+
if (run_edge_events_on_boot < 0) {
- if (dmi_check_system(run_edge_events_on_boot_blacklist))
+ if (quirks & QUIRK_NO_EDGE_EVENTS_ON_BOOT)
run_edge_events_on_boot = 0;
else
run_edge_events_on_boot = 1;
}
+ if (honor_wakeup < 0) {
+ if (quirks & QUIRK_NO_WAKEUP)
+ honor_wakeup = 0;
+ else
+ honor_wakeup = 1;
+ }
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index a97fb75..3e35a8f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -613,7 +613,17 @@ static bool amdgpu_atpx_detect(void)
bool d3_supported = false;
struct pci_dev *parent_pdev;
- while ((pdev = pci_get_class(PCI_BASE_CLASS_DISPLAY << 16, pdev)) != NULL) {
+ while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
+ vga_count++;
+
+ has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true);
+
+ parent_pdev = pci_upstream_bridge(pdev);
+ d3_supported |= parent_pdev && parent_pdev->bridge_d3;
+ amdgpu_atpx_get_quirks(pdev);
+ }
+
+ while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
vga_count++;
has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0ffc944..30a1e3a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -142,7 +142,7 @@ int amdgpu_async_gfx_ring = 1;
int amdgpu_mcbp = 0;
int amdgpu_discovery = -1;
int amdgpu_mes = 0;
-int amdgpu_noretry = 1;
+int amdgpu_noretry;
int amdgpu_force_asic_type = -1;
struct amdgpu_mgpu_info mgpu_info = {
@@ -588,7 +588,7 @@ MODULE_PARM_DESC(mes,
module_param_named(mes, amdgpu_mes, int, 0444);
MODULE_PARM_DESC(noretry,
- "Disable retry faults (0 = retry enabled, 1 = retry disabled (default))");
+ "Disable retry faults (0 = retry enabled (default), 1 = retry disabled)");
module_param_named(noretry, amdgpu_noretry, int, 0644);
/**
@@ -1004,7 +1004,7 @@ static const struct pci_device_id pciidlist[] = {
{0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
/* Renoir */
- {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT},
+ {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
/* Navi12 */
{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
@@ -1359,7 +1359,8 @@ static struct drm_driver kms_driver = {
.driver_features =
DRIVER_USE_AGP | DRIVER_ATOMIC |
DRIVER_GEM |
- DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ,
+ DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ |
+ DRIVER_SYNCOBJ_TIMELINE,
.load = amdgpu_driver_load_kms,
.open = amdgpu_driver_open_kms,
.postclose = amdgpu_driver_postclose_kms,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 44be3a4..e1b8d8d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1488,7 +1488,7 @@ static int psp_np_fw_load(struct psp_context *psp)
/* Start rlc autoload after psp recieved all the gfx firmware */
if (psp->autoload_supported && ucode->ucode_id == (amdgpu_sriov_vf(adev) ?
- AMDGPU_UCODE_ID_CP_MEC2 : AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM)) {
+ AMDGPU_UCODE_ID_CP_MEC2 : AMDGPU_UCODE_ID_RLC_G)) {
ret = psp_rlc_autoload(psp);
if (ret) {
DRM_ERROR("Failed to start rlc autoload\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 410587b..914acec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -292,10 +292,10 @@ enum AMDGPU_UCODE_ID {
AMDGPU_UCODE_ID_CP_MEC2_JT,
AMDGPU_UCODE_ID_CP_MES,
AMDGPU_UCODE_ID_CP_MES_DATA,
- AMDGPU_UCODE_ID_RLC_G,
AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL,
AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM,
AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM,
+ AMDGPU_UCODE_ID_RLC_G,
AMDGPU_UCODE_ID_STORAGE,
AMDGPU_UCODE_ID_SMC,
AMDGPU_UCODE_ID_UVD,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 66328ff..97105a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1052,17 +1052,10 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
case CHIP_VEGA20:
break;
case CHIP_RAVEN:
- /* Disable GFXOFF on original raven. There are combinations
- * of sbios and platforms that are not stable.
- */
- if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8))
- adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
- else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
- &&((adev->gfx.rlc_fw_version != 106 &&
- adev->gfx.rlc_fw_version < 531) ||
- (adev->gfx.rlc_fw_version == 53815) ||
- (adev->gfx.rlc_feature_version < 1) ||
- !adev->gfx.rlc.is_rlc_v2_1))
+ if (!(adev->rev_id >= 0x8 ||
+ adev->pdev->device == 0x15d8) &&
+ (adev->pm.fw_version < 0x41e2b || /* not raven1 fresh */
+ !adev->gfx.rlc.is_rlc_v2_1)) /* without rlc save restore ucodes */
adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
if (adev->pm.pp_feature & PP_GFXOFF_MASK)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 4ef4d31..2f52b7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -254,7 +254,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = {
SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
- SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000)
+ SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x03fbe1fe)
};
static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 7aac956..803e59d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3356,27 +3356,21 @@ get_output_color_space(const struct dc_crtc_timing *dc_crtc_timing)
return color_space;
}
-static void reduce_mode_colour_depth(struct dc_crtc_timing *timing_out)
+static bool adjust_colour_depth_from_display_info(
+ struct dc_crtc_timing *timing_out,
+ const struct drm_display_info *info)
{
- if (timing_out->display_color_depth <= COLOR_DEPTH_888)
- return;
-
- timing_out->display_color_depth--;
-}
-
-static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_out,
- const struct drm_display_info *info)
-{
+ enum dc_color_depth depth = timing_out->display_color_depth;
int normalized_clk;
- if (timing_out->display_color_depth <= COLOR_DEPTH_888)
- return;
do {
normalized_clk = timing_out->pix_clk_100hz / 10;
/* YCbCr 4:2:0 requires additional adjustment of 1/2 */
if (timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420)
normalized_clk /= 2;
/* Adjusting pix clock following on HDMI spec based on colour depth */
- switch (timing_out->display_color_depth) {
+ switch (depth) {
+ case COLOR_DEPTH_888:
+ break;
case COLOR_DEPTH_101010:
normalized_clk = (normalized_clk * 30) / 24;
break;
@@ -3387,14 +3381,15 @@ static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_
normalized_clk = (normalized_clk * 48) / 24;
break;
default:
- return;
+ /* The above depths are the only ones valid for HDMI. */
+ return false;
}
- if (normalized_clk <= info->max_tmds_clock)
- return;
- reduce_mode_colour_depth(timing_out);
-
- } while (timing_out->display_color_depth > COLOR_DEPTH_888);
-
+ if (normalized_clk <= info->max_tmds_clock) {
+ timing_out->display_color_depth = depth;
+ return true;
+ }
+ } while (--depth > COLOR_DEPTH_666);
+ return false;
}
static void fill_stream_properties_from_drm_display_mode(
@@ -3474,8 +3469,14 @@ static void fill_stream_properties_from_drm_display_mode(
stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
- if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
- adjust_colour_depth_from_display_info(timing_out, info);
+ if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) {
+ if (!adjust_colour_depth_from_display_info(timing_out, info) &&
+ drm_mode_is_420_also(info, mode_in) &&
+ timing_out->pixel_encoding != PIXEL_ENCODING_YCBCR420) {
+ timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420;
+ adjust_colour_depth_from_display_info(timing_out, info);
+ }
+ }
}
static void fill_audio_info(struct audio_info *audio_info,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 62d8289..4619f94 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -817,8 +817,8 @@ static bool dc_link_detect_helper(struct dc_link *link,
}
case SIGNAL_TYPE_EDP: {
- read_current_link_settings_on_detect(link);
detect_edp_sink_caps(link);
+ read_current_link_settings_on_detect(link);
sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C_OVER_AUX;
sink_caps.signal = SIGNAL_TYPE_EDP;
break;
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 5ff7cce..a23729d 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -866,6 +866,7 @@ static int smu_sw_init(void *handle)
smu->smu_baco.platform_support = false;
mutex_init(&smu->sensor_lock);
+ mutex_init(&smu->metrics_lock);
smu->watermarks_bitmap = 0;
smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index cc71a10..472e9fe 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -862,18 +862,21 @@ static int arcturus_get_metrics_table(struct smu_context *smu,
struct smu_table_context *smu_table= &smu->smu_table;
int ret = 0;
+ mutex_lock(&smu->metrics_lock);
if (!smu_table->metrics_time ||
time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
(void *)smu_table->metrics_table, false);
if (ret) {
pr_info("Failed to export SMU metrics table!\n");
+ mutex_unlock(&smu->metrics_lock);
return ret;
}
smu_table->metrics_time = jiffies;
}
memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+ mutex_unlock(&smu->metrics_lock);
return ret;
}
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index ac97583..41fce75 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -349,6 +349,7 @@ struct smu_context
const struct pptable_funcs *ppt_funcs;
struct mutex mutex;
struct mutex sensor_lock;
+ struct mutex metrics_lock;
uint64_t pool_size;
struct smu_table_context smu_table;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 4a14fd1..ca62e92 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -562,17 +562,20 @@ static int navi10_get_metrics_table(struct smu_context *smu,
struct smu_table_context *smu_table= &smu->smu_table;
int ret = 0;
+ mutex_lock(&smu->metrics_lock);
if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) {
ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
(void *)smu_table->metrics_table, false);
if (ret) {
pr_info("Failed to export SMU metrics table!\n");
+ mutex_unlock(&smu->metrics_lock);
return ret;
}
smu_table->metrics_time = jiffies;
}
memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+ mutex_unlock(&smu->metrics_lock);
return ret;
}
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 60b9ff0..0d3a3b0a 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -1678,17 +1678,20 @@ static int vega20_get_metrics_table(struct smu_context *smu,
struct smu_table_context *smu_table= &smu->smu_table;
int ret = 0;
+ mutex_lock(&smu->metrics_lock);
if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
(void *)smu_table->metrics_table, false);
if (ret) {
pr_info("Failed to export SMU metrics table!\n");
+ mutex_unlock(&smu->metrics_lock);
return ret;
}
smu_table->metrics_time = jiffies;
}
memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+ mutex_unlock(&smu->metrics_lock);
return ret;
}
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index 875a3a9..7d0e7b0 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -56,7 +56,7 @@ malidp_mw_connector_mode_valid(struct drm_connector *connector,
return MODE_OK;
}
-const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = {
+static const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = {
.get_modes = malidp_mw_connector_get_modes,
.mode_valid = malidp_mw_connector_mode_valid,
};
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 273dd80..e6afe4f 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -393,7 +393,7 @@ drm_dp_encode_sideband_req(const struct drm_dp_sideband_msg_req_body *req,
memcpy(&buf[idx], req->u.i2c_read.transactions[i].bytes, req->u.i2c_read.transactions[i].num_bytes);
idx += req->u.i2c_read.transactions[i].num_bytes;
- buf[idx] = (req->u.i2c_read.transactions[i].no_stop_bit & 0x1) << 5;
+ buf[idx] = (req->u.i2c_read.transactions[i].no_stop_bit & 0x1) << 4;
buf[idx] |= (req->u.i2c_read.transactions[i].i2c_transaction_delay & 0xf);
idx++;
}
@@ -1190,6 +1190,8 @@ static int drm_dp_mst_wait_tx_reply(struct drm_dp_mst_branch *mstb,
txmsg->state == DRM_DP_SIDEBAND_TX_SENT) {
mstb->tx_slots[txmsg->seqno] = NULL;
}
+ mgr->is_waiting_for_dwn_reply = false;
+
}
out:
if (unlikely(ret == -EIO) && drm_debug_enabled(DRM_UT_DP)) {
@@ -1199,6 +1201,7 @@ static int drm_dp_mst_wait_tx_reply(struct drm_dp_mst_branch *mstb,
}
mutex_unlock(&mgr->qlock);
+ drm_dp_mst_kick_tx(mgr);
return ret;
}
@@ -1913,73 +1916,90 @@ static u8 drm_dp_calculate_rad(struct drm_dp_mst_port *port,
return parent_lct + 1;
}
-static int drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt)
+static bool drm_dp_mst_is_dp_mst_end_device(u8 pdt, bool mcs)
+{
+ switch (pdt) {
+ case DP_PEER_DEVICE_DP_LEGACY_CONV:
+ case DP_PEER_DEVICE_SST_SINK:
+ return true;
+ case DP_PEER_DEVICE_MST_BRANCHING:
+ /* For sst branch device */
+ if (!mcs)
+ return true;
+
+ return false;
+ }
+ return true;
+}
+
+static int
+drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt,
+ bool new_mcs)
{
struct drm_dp_mst_topology_mgr *mgr = port->mgr;
struct drm_dp_mst_branch *mstb;
u8 rad[8], lct;
int ret = 0;
- if (port->pdt == new_pdt)
+ if (port->pdt == new_pdt && port->mcs == new_mcs)
return 0;
/* Teardown the old pdt, if there is one */
- switch (port->pdt) {
- case DP_PEER_DEVICE_DP_LEGACY_CONV:
- case DP_PEER_DEVICE_SST_SINK:
- /*
- * If the new PDT would also have an i2c bus, don't bother
- * with reregistering it
- */
- if (new_pdt == DP_PEER_DEVICE_DP_LEGACY_CONV ||
- new_pdt == DP_PEER_DEVICE_SST_SINK) {
- port->pdt = new_pdt;
- return 0;
- }
+ if (port->pdt != DP_PEER_DEVICE_NONE) {
+ if (drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) {
+ /*
+ * If the new PDT would also have an i2c bus,
+ * don't bother with reregistering it
+ */
+ if (new_pdt != DP_PEER_DEVICE_NONE &&
+ drm_dp_mst_is_dp_mst_end_device(new_pdt, new_mcs)) {
+ port->pdt = new_pdt;
+ port->mcs = new_mcs;
+ return 0;
+ }
- /* remove i2c over sideband */
- drm_dp_mst_unregister_i2c_bus(&port->aux);
- break;
- case DP_PEER_DEVICE_MST_BRANCHING:
- mutex_lock(&mgr->lock);
- drm_dp_mst_topology_put_mstb(port->mstb);
- port->mstb = NULL;
- mutex_unlock(&mgr->lock);
- break;
+ /* remove i2c over sideband */
+ drm_dp_mst_unregister_i2c_bus(&port->aux);
+ } else {
+ mutex_lock(&mgr->lock);
+ drm_dp_mst_topology_put_mstb(port->mstb);
+ port->mstb = NULL;
+ mutex_unlock(&mgr->lock);
+ }
}
port->pdt = new_pdt;
- switch (port->pdt) {
- case DP_PEER_DEVICE_DP_LEGACY_CONV:
- case DP_PEER_DEVICE_SST_SINK:
- /* add i2c over sideband */
- ret = drm_dp_mst_register_i2c_bus(&port->aux);
- break;
+ port->mcs = new_mcs;
- case DP_PEER_DEVICE_MST_BRANCHING:
- lct = drm_dp_calculate_rad(port, rad);
- mstb = drm_dp_add_mst_branch_device(lct, rad);
- if (!mstb) {
- ret = -ENOMEM;
- DRM_ERROR("Failed to create MSTB for port %p", port);
- goto out;
+ if (port->pdt != DP_PEER_DEVICE_NONE) {
+ if (drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) {
+ /* add i2c over sideband */
+ ret = drm_dp_mst_register_i2c_bus(&port->aux);
+ } else {
+ lct = drm_dp_calculate_rad(port, rad);
+ mstb = drm_dp_add_mst_branch_device(lct, rad);
+ if (!mstb) {
+ ret = -ENOMEM;
+ DRM_ERROR("Failed to create MSTB for port %p",
+ port);
+ goto out;
+ }
+
+ mutex_lock(&mgr->lock);
+ port->mstb = mstb;
+ mstb->mgr = port->mgr;
+ mstb->port_parent = port;
+
+ /*
+ * Make sure this port's memory allocation stays
+ * around until its child MSTB releases it
+ */
+ drm_dp_mst_get_port_malloc(port);
+ mutex_unlock(&mgr->lock);
+
+ /* And make sure we send a link address for this */
+ ret = 1;
}
-
- mutex_lock(&mgr->lock);
- port->mstb = mstb;
- mstb->mgr = port->mgr;
- mstb->port_parent = port;
-
- /*
- * Make sure this port's memory allocation stays
- * around until its child MSTB releases it
- */
- drm_dp_mst_get_port_malloc(port);
- mutex_unlock(&mgr->lock);
-
- /* And make sure we send a link address for this */
- ret = 1;
- break;
}
out:
@@ -2132,9 +2152,8 @@ drm_dp_mst_port_add_connector(struct drm_dp_mst_branch *mstb,
goto error;
}
- if ((port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV ||
- port->pdt == DP_PEER_DEVICE_SST_SINK) &&
- port->port_num >= DP_MST_LOGICAL_PORT_0) {
+ if (port->pdt != DP_PEER_DEVICE_NONE &&
+ drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) {
port->cached_edid = drm_get_edid(port->connector,
&port->aux.ddc);
drm_connector_set_tile_property(port->connector);
@@ -2198,6 +2217,7 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb,
struct drm_dp_mst_port *port;
int old_ddps = 0, ret;
u8 new_pdt = DP_PEER_DEVICE_NONE;
+ bool new_mcs = 0;
bool created = false, send_link_addr = false, changed = false;
port = drm_dp_get_port(mstb, port_msg->port_number);
@@ -2242,7 +2262,7 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb,
port->input = port_msg->input_port;
if (!port->input)
new_pdt = port_msg->peer_device_type;
- port->mcs = port_msg->mcs;
+ new_mcs = port_msg->mcs;
port->ddps = port_msg->ddps;
port->ldps = port_msg->legacy_device_plug_status;
port->dpcd_rev = port_msg->dpcd_revision;
@@ -2269,7 +2289,7 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb,
}
}
- ret = drm_dp_port_set_pdt(port, new_pdt);
+ ret = drm_dp_port_set_pdt(port, new_pdt, new_mcs);
if (ret == 1) {
send_link_addr = true;
} else if (ret < 0) {
@@ -2283,7 +2303,8 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb,
* we're coming out of suspend. In this case, always resend the link
* address if there's an MSTB on this port
*/
- if (!created && port->pdt == DP_PEER_DEVICE_MST_BRANCHING)
+ if (!created && port->pdt == DP_PEER_DEVICE_MST_BRANCHING &&
+ port->mcs)
send_link_addr = true;
if (port->connector)
@@ -2318,8 +2339,9 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb,
{
struct drm_dp_mst_topology_mgr *mgr = mstb->mgr;
struct drm_dp_mst_port *port;
- int old_ddps, ret;
+ int old_ddps, old_input, ret, i;
u8 new_pdt;
+ bool new_mcs;
bool dowork = false, create_connector = false;
port = drm_dp_get_port(mstb, conn_stat->port_number);
@@ -2349,8 +2371,8 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb,
}
old_ddps = port->ddps;
+ old_input = port->input;
port->input = conn_stat->input_port;
- port->mcs = conn_stat->message_capability_status;
port->ldps = conn_stat->legacy_device_plug_status;
port->ddps = conn_stat->displayport_device_plug_status;
@@ -2363,8 +2385,8 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb,
}
new_pdt = port->input ? DP_PEER_DEVICE_NONE : conn_stat->peer_device_type;
-
- ret = drm_dp_port_set_pdt(port, new_pdt);
+ new_mcs = conn_stat->message_capability_status;
+ ret = drm_dp_port_set_pdt(port, new_pdt, new_mcs);
if (ret == 1) {
dowork = true;
} else if (ret < 0) {
@@ -2373,6 +2395,28 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb,
dowork = false;
}
+ if (!old_input && old_ddps != port->ddps && !port->ddps) {
+ for (i = 0; i < mgr->max_payloads; i++) {
+ struct drm_dp_vcpi *vcpi = mgr->proposed_vcpis[i];
+ struct drm_dp_mst_port *port_validated;
+
+ if (!vcpi)
+ continue;
+
+ port_validated =
+ container_of(vcpi, struct drm_dp_mst_port, vcpi);
+ port_validated =
+ drm_dp_mst_topology_get_port_validated(mgr, port_validated);
+ if (!port_validated) {
+ mutex_lock(&mgr->payload_lock);
+ vcpi->num_slots = 0;
+ mutex_unlock(&mgr->payload_lock);
+ } else {
+ drm_dp_mst_topology_put_port(port_validated);
+ }
+ }
+ }
+
if (port->connector)
drm_modeset_unlock(&mgr->base.lock);
else if (create_connector)
@@ -2718,9 +2762,11 @@ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr)
ret = process_single_tx_qlock(mgr, txmsg, false);
if (ret == 1) {
/* txmsg is sent it should be in the slots now */
+ mgr->is_waiting_for_dwn_reply = true;
list_del(&txmsg->next);
} else if (ret) {
DRM_DEBUG_KMS("failed to send msg in q %d\n", ret);
+ mgr->is_waiting_for_dwn_reply = false;
list_del(&txmsg->next);
if (txmsg->seqno != -1)
txmsg->dst->tx_slots[txmsg->seqno] = NULL;
@@ -2760,7 +2806,8 @@ static void drm_dp_queue_down_tx(struct drm_dp_mst_topology_mgr *mgr,
drm_dp_mst_dump_sideband_msg_tx(&p, txmsg);
}
- if (list_is_singular(&mgr->tx_msg_downq))
+ if (list_is_singular(&mgr->tx_msg_downq) &&
+ !mgr->is_waiting_for_dwn_reply)
process_single_down_tx_qlock(mgr);
mutex_unlock(&mgr->qlock);
}
@@ -3678,6 +3725,7 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr)
mutex_lock(&mgr->qlock);
txmsg->state = DRM_DP_SIDEBAND_TX_RX;
mstb->tx_slots[slot] = NULL;
+ mgr->is_waiting_for_dwn_reply = false;
mutex_unlock(&mgr->qlock);
wake_up_all(&mgr->tx_waitq);
@@ -3687,6 +3735,9 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr)
no_msg:
drm_dp_mst_topology_put_mstb(mstb);
clear_down_rep_recv:
+ mutex_lock(&mgr->qlock);
+ mgr->is_waiting_for_dwn_reply = false;
+ mutex_unlock(&mgr->qlock);
memset(&mgr->down_rep_recv, 0, sizeof(struct drm_dp_sideband_msg_rx));
return 0;
@@ -3896,6 +3947,8 @@ drm_dp_mst_detect_port(struct drm_connector *connector,
switch (port->pdt) {
case DP_PEER_DEVICE_NONE:
case DP_PEER_DEVICE_MST_BRANCHING:
+ if (!port->mcs)
+ ret = connector_status_connected;
break;
case DP_PEER_DEVICE_SST_SINK:
@@ -4497,7 +4550,7 @@ static void drm_dp_tx_work(struct work_struct *work)
struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, tx_work);
mutex_lock(&mgr->qlock);
- if (!list_empty(&mgr->tx_msg_downq))
+ if (!list_empty(&mgr->tx_msg_downq) && !mgr->is_waiting_for_dwn_reply)
process_single_down_tx_qlock(mgr);
mutex_unlock(&mgr->qlock);
}
@@ -4508,7 +4561,7 @@ drm_dp_delayed_destroy_port(struct drm_dp_mst_port *port)
if (port->connector)
port->mgr->cbs->destroy_connector(port->mgr, port->connector);
- drm_dp_port_set_pdt(port, DP_PEER_DEVICE_NONE);
+ drm_dp_port_set_pdt(port, DP_PEER_DEVICE_NONE, port->mcs);
drm_dp_mst_put_port_malloc(port);
}
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 8ebeccd..d8e8f39 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1283,7 +1283,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
* Changes struct fb_var_screeninfo are currently not pushed back
* to KMS, hence fail if different settings are requested.
*/
- if (var->bits_per_pixel != fb->format->cpp[0] * 8 ||
+ if (var->bits_per_pixel > fb->format->cpp[0] * 8 ||
var->xres > fb->width || var->yres > fb->height ||
var->xres_virtual > fb->width || var->yres_virtual > fb->height) {
DRM_DEBUG("fb requested width/height/bpp can't fit in current fb "
@@ -1309,6 +1309,11 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
}
/*
+ * Likewise, bits_per_pixel should be rounded up to a supported value.
+ */
+ var->bits_per_pixel = fb->format->cpp[0] * 8;
+
+ /*
* drm fbdev emulation doesn't support changing the pixel format at all,
* so reject all pixel format changing requests.
*/
diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index 85e6b2b..3a5ac13 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -856,7 +856,7 @@ static unsigned long i915_audio_component_get_power(struct device *kdev)
}
/* Force CDCLK to 2*BCLK as long as we need audio powered. */
- if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+ if (IS_GEMINILAKE(dev_priv))
glk_force_audio_cdclk(dev_priv, true);
if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
@@ -875,7 +875,7 @@ static void i915_audio_component_put_power(struct device *kdev,
/* Stop forcing CDCLK to 2*BCLK if no need for audio to be powered. */
if (--dev_priv->audio_power_refcount == 0)
- if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+ if (IS_GEMINILAKE(dev_priv))
glk_force_audio_cdclk(dev_priv, false);
intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO, cookie);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index effc425..3018977 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -4515,8 +4515,6 @@ static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_
{
struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
- i915_reg_t reg;
- u32 trans_ddi_func_ctl2_val;
if (old_crtc_state->master_transcoder == INVALID_TRANSCODER)
return;
@@ -4524,10 +4522,7 @@ static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_
DRM_DEBUG_KMS("Disabling Transcoder Port Sync on Slave Transcoder %s\n",
transcoder_name(old_crtc_state->cpu_transcoder));
- reg = TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder);
- trans_ddi_func_ctl2_val = ~(PORT_SYNC_MODE_ENABLE |
- PORT_SYNC_MODE_MASTER_SELECT_MASK);
- I915_WRITE(reg, trans_ddi_func_ctl2_val);
+ I915_WRITE(TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder), 0);
}
static void intel_fdi_normal_train(struct intel_crtc *crtc)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c
index 3d4f577..25235ef 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c
@@ -9,16 +9,16 @@
#include "i915_gem_ioctls.h"
#include "i915_gem_object.h"
-static __always_inline u32 __busy_read_flag(u8 id)
+static __always_inline u32 __busy_read_flag(u16 id)
{
- if (id == (u8)I915_ENGINE_CLASS_INVALID)
+ if (id == (u16)I915_ENGINE_CLASS_INVALID)
return 0xffff0000u;
GEM_BUG_ON(id >= 16);
return 0x10000u << id;
}
-static __always_inline u32 __busy_write_id(u8 id)
+static __always_inline u32 __busy_write_id(u16 id)
{
/*
* The uABI guarantees an active writer is also amongst the read
@@ -29,14 +29,14 @@ static __always_inline u32 __busy_write_id(u8 id)
* last_read - hence we always set both read and write busy for
* last_write.
*/
- if (id == (u8)I915_ENGINE_CLASS_INVALID)
+ if (id == (u16)I915_ENGINE_CLASS_INVALID)
return 0xffffffffu;
return (id + 1) | __busy_read_flag(id);
}
static __always_inline unsigned int
-__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u8 id))
+__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id))
{
const struct i915_request *rq;
@@ -57,7 +57,7 @@ __busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u8 id))
return 0;
/* Beware type-expansion follies! */
- BUILD_BUG_ON(!typecheck(u8, rq->engine->uabi_class));
+ BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class));
return flag(rq->engine->uabi_class);
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 4c72d74..0dbb44d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -402,7 +402,7 @@ struct get_pages_work {
static struct sg_table *
__i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
- struct page **pvec, int num_pages)
+ struct page **pvec, unsigned long num_pages)
{
unsigned int max_segment = i915_sg_segment_size();
struct sg_table *st;
@@ -448,9 +448,10 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
{
struct get_pages_work *work = container_of(_work, typeof(*work), work);
struct drm_i915_gem_object *obj = work->obj;
- const int npages = obj->base.size >> PAGE_SHIFT;
+ const unsigned long npages = obj->base.size >> PAGE_SHIFT;
+ unsigned long pinned;
struct page **pvec;
- int pinned, ret;
+ int ret;
ret = -ENOMEM;
pinned = 0;
@@ -553,7 +554,7 @@ __i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj)
static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
{
- const int num_pages = obj->base.size >> PAGE_SHIFT;
+ const unsigned long num_pages = obj->base.size >> PAGE_SHIFT;
struct mm_struct *mm = obj->userptr.mm->mm;
struct page **pvec;
struct sg_table *pages;
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index ef7bc41..5b7ff3c 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -123,6 +123,10 @@ static int __context_pin_state(struct i915_vma *vma)
if (err)
return err;
+ err = i915_active_acquire(&vma->active);
+ if (err)
+ goto err_unpin;
+
/*
* And mark it as a globally pinned object to let the shrinker know
* it cannot reclaim the object until we release it.
@@ -131,14 +135,44 @@ static int __context_pin_state(struct i915_vma *vma)
vma->obj->mm.dirty = true;
return 0;
+
+err_unpin:
+ i915_vma_unpin(vma);
+ return err;
}
static void __context_unpin_state(struct i915_vma *vma)
{
i915_vma_make_shrinkable(vma);
+ i915_active_release(&vma->active);
__i915_vma_unpin(vma);
}
+static int __ring_active(struct intel_ring *ring)
+{
+ int err;
+
+ err = i915_active_acquire(&ring->vma->active);
+ if (err)
+ return err;
+
+ err = intel_ring_pin(ring);
+ if (err)
+ goto err_active;
+
+ return 0;
+
+err_active:
+ i915_active_release(&ring->vma->active);
+ return err;
+}
+
+static void __ring_retire(struct intel_ring *ring)
+{
+ intel_ring_unpin(ring);
+ i915_active_release(&ring->vma->active);
+}
+
__i915_active_call
static void __intel_context_retire(struct i915_active *active)
{
@@ -151,7 +185,7 @@ static void __intel_context_retire(struct i915_active *active)
__context_unpin_state(ce->state);
intel_timeline_unpin(ce->timeline);
- intel_ring_unpin(ce->ring);
+ __ring_retire(ce->ring);
intel_context_put(ce);
}
@@ -163,7 +197,7 @@ static int __intel_context_active(struct i915_active *active)
intel_context_get(ce);
- err = intel_ring_pin(ce->ring);
+ err = __ring_active(ce->ring);
if (err)
goto err_put;
@@ -183,7 +217,7 @@ static int __intel_context_active(struct i915_active *active)
err_timeline:
intel_timeline_unpin(ce->timeline);
err_ring:
- intel_ring_unpin(ce->ring);
+ __ring_retire(ce->ring);
err_put:
intel_context_put(ce);
return err;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 17f1f14..2b44647 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -274,8 +274,8 @@ struct intel_engine_cs {
u8 class;
u8 instance;
- u8 uabi_class;
- u8 uabi_instance;
+ u16 uabi_class;
+ u16 uabi_instance;
u32 uabi_capabilities;
u32 context_size;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 75dd0e0..d925a10 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2664,6 +2664,14 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
batch = gen8_emit_flush_coherentl3_wa(engine, batch);
+ /* WaClearSlmSpaceAtContextSwitch:skl,bxt,kbl,glk,cfl */
+ batch = gen8_emit_pipe_control(batch,
+ PIPE_CONTROL_FLUSH_L3 |
+ PIPE_CONTROL_STORE_DATA_INDEX |
+ PIPE_CONTROL_CS_STALL |
+ PIPE_CONTROL_QW_WRITE,
+ LRC_PPHWSP_SCRATCH_ADDR);
+
batch = emit_lri(batch, lri, ARRAY_SIZE(lri));
/* WaMediaPoolStateCmdInWABB:bxt,glk */
@@ -4416,9 +4424,11 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
ve->base.gt = siblings[0]->gt;
ve->base.uncore = siblings[0]->uncore;
ve->base.id = -1;
+
ve->base.class = OTHER_CLASS;
ve->base.uabi_class = I915_ENGINE_CLASS_INVALID;
ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
+ ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
/*
* The decision on whether to submit a request using semaphores
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index a47d5a7..9302621 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -1413,14 +1413,6 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
int len;
u32 *cs;
- flags |= MI_MM_SPACE_GTT;
- if (IS_HASWELL(i915))
- /* These flags are for resource streamer on HSW+ */
- flags |= HSW_MI_RS_SAVE_STATE_EN | HSW_MI_RS_RESTORE_STATE_EN;
- else
- /* We need to save the extended state for powersaving modes */
- flags |= MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN;
-
len = 4;
if (IS_GEN(i915, 7))
len += 2 + (num_engines ? 4 * num_engines + 6 : 0);
@@ -1589,22 +1581,21 @@ static int switch_context(struct i915_request *rq)
}
if (ce->state) {
- u32 hw_flags;
+ u32 flags;
GEM_BUG_ON(rq->engine->id != RCS0);
- /*
- * The kernel context(s) is treated as pure scratch and is not
- * expected to retain any state (as we sacrifice it during
- * suspend and on resume it may be corrupted). This is ok,
- * as nothing actually executes using the kernel context; it
- * is purely used for flushing user contexts.
- */
- hw_flags = 0;
- if (i915_gem_context_is_kernel(rq->gem_context))
- hw_flags = MI_RESTORE_INHIBIT;
+ /* For resource streamer on HSW+ and power context elsewhere */
+ BUILD_BUG_ON(HSW_MI_RS_SAVE_STATE_EN != MI_SAVE_EXT_STATE_EN);
+ BUILD_BUG_ON(HSW_MI_RS_RESTORE_STATE_EN != MI_RESTORE_EXT_STATE_EN);
- ret = mi_set_context(rq, hw_flags);
+ flags = MI_SAVE_EXT_STATE_EN | MI_MM_SPACE_GTT;
+ if (!i915_gem_context_is_kernel(rq->gem_context))
+ flags |= MI_RESTORE_EXT_STATE_EN;
+ else
+ flags |= MI_RESTORE_INHIBIT;
+
+ ret = mi_set_context(rq, flags);
if (ret)
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e29bc13..21aa08f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1660,8 +1660,10 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
(IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9))
/* WaRsDisableCoarsePowerGating:skl,cnl */
-#define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
- (IS_CANNONLAKE(dev_priv) || IS_GEN(dev_priv, 9))
+#define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
+ (IS_CANNONLAKE(dev_priv) || \
+ IS_SKL_GT3(dev_priv) || \
+ IS_SKL_GT4(dev_priv))
#define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
#define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 6239a9a..4472780 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1177,6 +1177,7 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
do {
+ GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
iter->dma += I915_GTT_PAGE_SIZE;
@@ -1660,6 +1661,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
do {
+ GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE);
vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
iter.dma += I915_GTT_PAGE_SIZE;
@@ -3304,7 +3306,7 @@ void i915_ggtt_disable_guc(struct i915_ggtt *ggtt)
static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
{
- struct i915_vma *vma, *vn;
+ struct i915_vma *vma;
bool flush = false;
int open;
@@ -3319,15 +3321,12 @@ static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
open = atomic_xchg(&ggtt->vm.open, 0);
/* clflush objects bound into the GGTT and rebind them. */
- list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link) {
+ list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link) {
struct drm_i915_gem_object *obj = vma->obj;
if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
continue;
- if (!__i915_vma_unbind(vma))
- continue;
-
clear_bit(I915_VMA_GLOBAL_BIND_BIT, __i915_vma_flags(vma));
WARN_ON(i915_vma_bind(vma,
obj ? obj->cache_level : 0,
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 6f09aa0..d6d2e6f 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -1074,12 +1074,17 @@ void i915_pmu_register(struct drm_i915_private *i915)
hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
pmu->timer.function = i915_sample;
- if (!is_igp(i915))
+ if (!is_igp(i915)) {
pmu->name = kasprintf(GFP_KERNEL,
- "i915-%s",
+ "i915_%s",
dev_name(i915->drm.dev));
- else
+ if (pmu->name) {
+ /* tools/perf reserves colons as special. */
+ strreplace((char *)pmu->name, ':', '_');
+ }
+ } else {
pmu->name = "i915";
+ }
if (!pmu->name)
goto err;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4fd3d76..094011b 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4177,7 +4177,13 @@ enum {
#define CPSSUNIT_CLKGATE_DIS REG_BIT(9)
#define UNSLICE_UNIT_LEVEL_CLKGATE _MMIO(0x9434)
-#define VFUNIT_CLKGATE_DIS (1 << 20)
+#define VFUNIT_CLKGATE_DIS REG_BIT(20)
+#define HSUNIT_CLKGATE_DIS REG_BIT(8)
+#define VSUNIT_CLKGATE_DIS REG_BIT(3)
+
+#define UNSLICE_UNIT_LEVEL_CLKGATE2 _MMIO(0x94e4)
+#define VSUNIT_CLKGATE_DIS_TGL REG_BIT(19)
+#define PSDUNIT_CLKGATE_DIS REG_BIT(5)
#define INF_UNIT_LEVEL_CLKGATE _MMIO(0x9560)
#define CGPSF_CLKGATE_DIS (1 << 3)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 75ae6f4..86379ed 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6565,6 +6565,17 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv)
/* WaEnable32PlaneMode:icl */
I915_WRITE(GEN9_CSFE_CHICKEN1_RCS,
_MASKED_BIT_ENABLE(GEN11_ENABLE_32_PLANE_MODE));
+
+ /*
+ * Wa_1408615072:icl,ehl (vsunit)
+ * Wa_1407596294:icl,ehl (hsunit)
+ */
+ intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE,
+ 0, VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
+
+ /* Wa_1407352427:icl,ehl */
+ intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE2,
+ 0, PSDUNIT_CLKGATE_DIS);
}
static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.h b/drivers/gpu/drm/i915/selftests/i915_random.h
index 35cc69a..05364ec 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.h
+++ b/drivers/gpu/drm/i915/selftests/i915_random.h
@@ -25,6 +25,7 @@
#ifndef __I915_SELFTESTS_RANDOM_H__
#define __I915_SELFTESTS_RANDOM_H__
+#include <linux/math64.h>
#include <linux/random.h>
#include "../i915_selftest.h"
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index f80a8ba..3305a94 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -215,11 +215,12 @@ struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc,
struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
struct mtk_ddp_comp *comp;
int i, count = 0;
+ unsigned int local_index = plane - mtk_crtc->planes;
for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
comp = mtk_crtc->ddp_comp[i];
- if (plane->index < (count + mtk_ddp_comp_layer_nr(comp))) {
- *local_layer = plane->index - count;
+ if (local_index < (count + mtk_ddp_comp_layer_nr(comp))) {
+ *local_layer = local_index - count;
return comp;
}
count += mtk_ddp_comp_layer_nr(comp);
@@ -310,7 +311,9 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
plane_state = to_mtk_plane_state(plane->state);
comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer);
- mtk_ddp_comp_layer_config(comp, local_layer, plane_state);
+ if (comp)
+ mtk_ddp_comp_layer_config(comp, local_layer,
+ plane_state);
}
return 0;
@@ -386,8 +389,9 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
comp = mtk_drm_ddp_comp_for_plane(crtc, plane,
&local_layer);
- mtk_ddp_comp_layer_config(comp, local_layer,
- plane_state);
+ if (comp)
+ mtk_ddp_comp_layer_config(comp, local_layer,
+ plane_state);
plane_state->pending.config = false;
}
mtk_crtc->pending_planes = false;
@@ -401,7 +405,9 @@ int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
struct mtk_ddp_comp *comp;
comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer);
- return mtk_ddp_comp_layer_check(comp, local_layer, state);
+ if (comp)
+ return mtk_ddp_comp_layer_check(comp, local_layer, state);
+ return 0;
}
static void mtk_drm_crtc_atomic_enable(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index e9931bb..d77c9f4 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -230,28 +230,25 @@ static void mtk_dsi_mask(struct mtk_dsi *dsi, u32 offset, u32 mask, u32 data)
static void mtk_dsi_phy_timconfig(struct mtk_dsi *dsi)
{
u32 timcon0, timcon1, timcon2, timcon3;
- u32 ui, cycle_time;
+ u32 data_rate_mhz = DIV_ROUND_UP(dsi->data_rate, 1000000);
struct mtk_phy_timing *timing = &dsi->phy_timing;
- ui = DIV_ROUND_UP(1000000000, dsi->data_rate);
- cycle_time = div_u64(8000000000ULL, dsi->data_rate);
+ timing->lpx = (60 * data_rate_mhz / (8 * 1000)) + 1;
+ timing->da_hs_prepare = (80 * data_rate_mhz + 4 * 1000) / 8000;
+ timing->da_hs_zero = (170 * data_rate_mhz + 10 * 1000) / 8000 + 1 -
+ timing->da_hs_prepare;
+ timing->da_hs_trail = timing->da_hs_prepare + 1;
- timing->lpx = NS_TO_CYCLE(60, cycle_time);
- timing->da_hs_prepare = NS_TO_CYCLE(50 + 5 * ui, cycle_time);
- timing->da_hs_zero = NS_TO_CYCLE(110 + 6 * ui, cycle_time);
- timing->da_hs_trail = NS_TO_CYCLE(77 + 4 * ui, cycle_time);
+ timing->ta_go = 4 * timing->lpx - 2;
+ timing->ta_sure = timing->lpx + 2;
+ timing->ta_get = 4 * timing->lpx;
+ timing->da_hs_exit = 2 * timing->lpx + 1;
- timing->ta_go = 4 * timing->lpx;
- timing->ta_sure = 3 * timing->lpx / 2;
- timing->ta_get = 5 * timing->lpx;
- timing->da_hs_exit = 2 * timing->lpx;
-
- timing->clk_hs_zero = NS_TO_CYCLE(336, cycle_time);
- timing->clk_hs_trail = NS_TO_CYCLE(100, cycle_time) + 10;
-
- timing->clk_hs_prepare = NS_TO_CYCLE(64, cycle_time);
- timing->clk_hs_post = NS_TO_CYCLE(80 + 52 * ui, cycle_time);
- timing->clk_hs_exit = 2 * timing->lpx;
+ timing->clk_hs_prepare = 70 * data_rate_mhz / (8 * 1000);
+ timing->clk_hs_post = timing->clk_hs_prepare + 8;
+ timing->clk_hs_trail = timing->clk_hs_prepare;
+ timing->clk_hs_zero = timing->clk_hs_trail * 4;
+ timing->clk_hs_exit = 2 * timing->clk_hs_trail;
timcon0 = timing->lpx | timing->da_hs_prepare << 8 |
timing->da_hs_zero << 16 | timing->da_hs_trail << 24;
@@ -482,27 +479,39 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi)
dsi_tmp_buf_bpp - 10);
data_phy_cycles = timing->lpx + timing->da_hs_prepare +
- timing->da_hs_zero + timing->da_hs_exit + 2;
+ timing->da_hs_zero + timing->da_hs_exit + 3;
if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
- if (vm->hfront_porch * dsi_tmp_buf_bpp >
+ if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp >
data_phy_cycles * dsi->lanes + 18) {
- horizontal_frontporch_byte = vm->hfront_porch *
- dsi_tmp_buf_bpp -
- data_phy_cycles *
- dsi->lanes - 18;
+ horizontal_frontporch_byte =
+ vm->hfront_porch * dsi_tmp_buf_bpp -
+ (data_phy_cycles * dsi->lanes + 18) *
+ vm->hfront_porch /
+ (vm->hfront_porch + vm->hback_porch);
+
+ horizontal_backporch_byte =
+ horizontal_backporch_byte -
+ (data_phy_cycles * dsi->lanes + 18) *
+ vm->hback_porch /
+ (vm->hfront_porch + vm->hback_porch);
} else {
DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n");
horizontal_frontporch_byte = vm->hfront_porch *
dsi_tmp_buf_bpp;
}
} else {
- if (vm->hfront_porch * dsi_tmp_buf_bpp >
+ if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp >
data_phy_cycles * dsi->lanes + 12) {
- horizontal_frontporch_byte = vm->hfront_porch *
- dsi_tmp_buf_bpp -
- data_phy_cycles *
- dsi->lanes - 12;
+ horizontal_frontporch_byte =
+ vm->hfront_porch * dsi_tmp_buf_bpp -
+ (data_phy_cycles * dsi->lanes + 12) *
+ vm->hfront_porch /
+ (vm->hfront_porch + vm->hback_porch);
+ horizontal_backporch_byte = horizontal_backporch_byte -
+ (data_phy_cycles * dsi->lanes + 12) *
+ vm->hback_porch /
+ (vm->hfront_porch + vm->hback_porch);
} else {
DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n");
horizontal_frontporch_byte = vm->hfront_porch *
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index f61364f..88b431a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -78,8 +78,10 @@ static int panfrost_ioctl_get_param(struct drm_device *ddev, void *data, struct
static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data,
struct drm_file *file)
{
+ struct panfrost_file_priv *priv = file->driver_priv;
struct panfrost_gem_object *bo;
struct drm_panfrost_create_bo *args = data;
+ struct panfrost_gem_mapping *mapping;
if (!args->size || args->pad ||
(args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP)))
@@ -95,7 +97,14 @@ static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data,
if (IS_ERR(bo))
return PTR_ERR(bo);
- args->offset = bo->node.start << PAGE_SHIFT;
+ mapping = panfrost_gem_mapping_get(bo, priv);
+ if (!mapping) {
+ drm_gem_object_put_unlocked(&bo->base.base);
+ return -EINVAL;
+ }
+
+ args->offset = mapping->mmnode.start << PAGE_SHIFT;
+ panfrost_gem_mapping_put(mapping);
return 0;
}
@@ -119,6 +128,11 @@ panfrost_lookup_bos(struct drm_device *dev,
struct drm_panfrost_submit *args,
struct panfrost_job *job)
{
+ struct panfrost_file_priv *priv = file_priv->driver_priv;
+ struct panfrost_gem_object *bo;
+ unsigned int i;
+ int ret;
+
job->bo_count = args->bo_handle_count;
if (!job->bo_count)
@@ -130,9 +144,32 @@ panfrost_lookup_bos(struct drm_device *dev,
if (!job->implicit_fences)
return -ENOMEM;
- return drm_gem_objects_lookup(file_priv,
- (void __user *)(uintptr_t)args->bo_handles,
- job->bo_count, &job->bos);
+ ret = drm_gem_objects_lookup(file_priv,
+ (void __user *)(uintptr_t)args->bo_handles,
+ job->bo_count, &job->bos);
+ if (ret)
+ return ret;
+
+ job->mappings = kvmalloc_array(job->bo_count,
+ sizeof(struct panfrost_gem_mapping *),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!job->mappings)
+ return -ENOMEM;
+
+ for (i = 0; i < job->bo_count; i++) {
+ struct panfrost_gem_mapping *mapping;
+
+ bo = to_panfrost_bo(job->bos[i]);
+ mapping = panfrost_gem_mapping_get(bo, priv);
+ if (!mapping) {
+ ret = -EINVAL;
+ break;
+ }
+
+ job->mappings[i] = mapping;
+ }
+
+ return ret;
}
/**
@@ -320,7 +357,9 @@ static int panfrost_ioctl_mmap_bo(struct drm_device *dev, void *data,
static int panfrost_ioctl_get_bo_offset(struct drm_device *dev, void *data,
struct drm_file *file_priv)
{
+ struct panfrost_file_priv *priv = file_priv->driver_priv;
struct drm_panfrost_get_bo_offset *args = data;
+ struct panfrost_gem_mapping *mapping;
struct drm_gem_object *gem_obj;
struct panfrost_gem_object *bo;
@@ -331,18 +370,26 @@ static int panfrost_ioctl_get_bo_offset(struct drm_device *dev, void *data,
}
bo = to_panfrost_bo(gem_obj);
- args->offset = bo->node.start << PAGE_SHIFT;
-
+ mapping = panfrost_gem_mapping_get(bo, priv);
drm_gem_object_put_unlocked(gem_obj);
+
+ if (!mapping)
+ return -EINVAL;
+
+ args->offset = mapping->mmnode.start << PAGE_SHIFT;
+ panfrost_gem_mapping_put(mapping);
return 0;
}
static int panfrost_ioctl_madvise(struct drm_device *dev, void *data,
struct drm_file *file_priv)
{
+ struct panfrost_file_priv *priv = file_priv->driver_priv;
struct drm_panfrost_madvise *args = data;
struct panfrost_device *pfdev = dev->dev_private;
struct drm_gem_object *gem_obj;
+ struct panfrost_gem_object *bo;
+ int ret = 0;
gem_obj = drm_gem_object_lookup(file_priv, args->handle);
if (!gem_obj) {
@@ -350,22 +397,48 @@ static int panfrost_ioctl_madvise(struct drm_device *dev, void *data,
return -ENOENT;
}
+ bo = to_panfrost_bo(gem_obj);
+
mutex_lock(&pfdev->shrinker_lock);
+ mutex_lock(&bo->mappings.lock);
+ if (args->madv == PANFROST_MADV_DONTNEED) {
+ struct panfrost_gem_mapping *first;
+
+ first = list_first_entry(&bo->mappings.list,
+ struct panfrost_gem_mapping,
+ node);
+
+ /*
+ * If we want to mark the BO purgeable, there must be only one
+ * user: the caller FD.
+ * We could do something smarter and mark the BO purgeable only
+ * when all its users have marked it purgeable, but globally
+ * visible/shared BOs are likely to never be marked purgeable
+ * anyway, so let's not bother.
+ */
+ if (!list_is_singular(&bo->mappings.list) ||
+ WARN_ON_ONCE(first->mmu != &priv->mmu)) {
+ ret = -EINVAL;
+ goto out_unlock_mappings;
+ }
+ }
+
args->retained = drm_gem_shmem_madvise(gem_obj, args->madv);
if (args->retained) {
- struct panfrost_gem_object *bo = to_panfrost_bo(gem_obj);
-
if (args->madv == PANFROST_MADV_DONTNEED)
list_add_tail(&bo->base.madv_list,
&pfdev->shrinker_list);
else if (args->madv == PANFROST_MADV_WILLNEED)
list_del_init(&bo->base.madv_list);
}
+
+out_unlock_mappings:
+ mutex_unlock(&bo->mappings.lock);
mutex_unlock(&pfdev->shrinker_lock);
drm_gem_object_put_unlocked(gem_obj);
- return 0;
+ return ret;
}
int panfrost_unstable_ioctl_check(void)
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index fd766b1..17b654e 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -29,6 +29,12 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj)
list_del_init(&bo->base.madv_list);
mutex_unlock(&pfdev->shrinker_lock);
+ /*
+ * If we still have mappings attached to the BO, there's a problem in
+ * our refcounting.
+ */
+ WARN_ON_ONCE(!list_empty(&bo->mappings.list));
+
if (bo->sgts) {
int i;
int n_sgt = bo->base.base.size / SZ_2M;
@@ -46,6 +52,69 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj)
drm_gem_shmem_free_object(obj);
}
+struct panfrost_gem_mapping *
+panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
+ struct panfrost_file_priv *priv)
+{
+ struct panfrost_gem_mapping *iter, *mapping = NULL;
+
+ mutex_lock(&bo->mappings.lock);
+ list_for_each_entry(iter, &bo->mappings.list, node) {
+ if (iter->mmu == &priv->mmu) {
+ kref_get(&iter->refcount);
+ mapping = iter;
+ break;
+ }
+ }
+ mutex_unlock(&bo->mappings.lock);
+
+ return mapping;
+}
+
+static void
+panfrost_gem_teardown_mapping(struct panfrost_gem_mapping *mapping)
+{
+ struct panfrost_file_priv *priv;
+
+ if (mapping->active)
+ panfrost_mmu_unmap(mapping);
+
+ priv = container_of(mapping->mmu, struct panfrost_file_priv, mmu);
+ spin_lock(&priv->mm_lock);
+ if (drm_mm_node_allocated(&mapping->mmnode))
+ drm_mm_remove_node(&mapping->mmnode);
+ spin_unlock(&priv->mm_lock);
+}
+
+static void panfrost_gem_mapping_release(struct kref *kref)
+{
+ struct panfrost_gem_mapping *mapping;
+
+ mapping = container_of(kref, struct panfrost_gem_mapping, refcount);
+
+ panfrost_gem_teardown_mapping(mapping);
+ drm_gem_object_put_unlocked(&mapping->obj->base.base);
+ kfree(mapping);
+}
+
+void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping)
+{
+ if (!mapping)
+ return;
+
+ kref_put(&mapping->refcount, panfrost_gem_mapping_release);
+}
+
+void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo)
+{
+ struct panfrost_gem_mapping *mapping;
+
+ mutex_lock(&bo->mappings.lock);
+ list_for_each_entry(mapping, &bo->mappings.list, node)
+ panfrost_gem_teardown_mapping(mapping);
+ mutex_unlock(&bo->mappings.lock);
+}
+
int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
{
int ret;
@@ -54,6 +123,16 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
struct panfrost_gem_object *bo = to_panfrost_bo(obj);
unsigned long color = bo->noexec ? PANFROST_BO_NOEXEC : 0;
struct panfrost_file_priv *priv = file_priv->driver_priv;
+ struct panfrost_gem_mapping *mapping;
+
+ mapping = kzalloc(sizeof(*mapping), GFP_KERNEL);
+ if (!mapping)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&mapping->node);
+ kref_init(&mapping->refcount);
+ drm_gem_object_get(obj);
+ mapping->obj = bo;
/*
* Executable buffers cannot cross a 16MB boundary as the program
@@ -66,37 +145,48 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
else
align = size >= SZ_2M ? SZ_2M >> PAGE_SHIFT : 0;
- bo->mmu = &priv->mmu;
+ mapping->mmu = &priv->mmu;
spin_lock(&priv->mm_lock);
- ret = drm_mm_insert_node_generic(&priv->mm, &bo->node,
+ ret = drm_mm_insert_node_generic(&priv->mm, &mapping->mmnode,
size >> PAGE_SHIFT, align, color, 0);
spin_unlock(&priv->mm_lock);
if (ret)
- return ret;
+ goto err;
if (!bo->is_heap) {
- ret = panfrost_mmu_map(bo);
- if (ret) {
- spin_lock(&priv->mm_lock);
- drm_mm_remove_node(&bo->node);
- spin_unlock(&priv->mm_lock);
- }
+ ret = panfrost_mmu_map(mapping);
+ if (ret)
+ goto err;
}
+
+ mutex_lock(&bo->mappings.lock);
+ WARN_ON(bo->base.madv != PANFROST_MADV_WILLNEED);
+ list_add_tail(&mapping->node, &bo->mappings.list);
+ mutex_unlock(&bo->mappings.lock);
+
+err:
+ if (ret)
+ panfrost_gem_mapping_put(mapping);
return ret;
}
void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv)
{
- struct panfrost_gem_object *bo = to_panfrost_bo(obj);
struct panfrost_file_priv *priv = file_priv->driver_priv;
+ struct panfrost_gem_object *bo = to_panfrost_bo(obj);
+ struct panfrost_gem_mapping *mapping = NULL, *iter;
- if (bo->is_mapped)
- panfrost_mmu_unmap(bo);
+ mutex_lock(&bo->mappings.lock);
+ list_for_each_entry(iter, &bo->mappings.list, node) {
+ if (iter->mmu == &priv->mmu) {
+ mapping = iter;
+ list_del(&iter->node);
+ break;
+ }
+ }
+ mutex_unlock(&bo->mappings.lock);
- spin_lock(&priv->mm_lock);
- if (drm_mm_node_allocated(&bo->node))
- drm_mm_remove_node(&bo->node);
- spin_unlock(&priv->mm_lock);
+ panfrost_gem_mapping_put(mapping);
}
static int panfrost_gem_pin(struct drm_gem_object *obj)
@@ -136,6 +226,8 @@ struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t
if (!obj)
return NULL;
+ INIT_LIST_HEAD(&obj->mappings.list);
+ mutex_init(&obj->mappings.lock);
obj->base.base.funcs = &panfrost_gem_funcs;
return &obj->base.base;
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h
index 4b17e73..ca1bc90 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.h
@@ -13,23 +13,46 @@ struct panfrost_gem_object {
struct drm_gem_shmem_object base;
struct sg_table *sgts;
- struct panfrost_mmu *mmu;
- struct drm_mm_node node;
- bool is_mapped :1;
+ /*
+ * Use a list for now. If searching a mapping ever becomes the
+ * bottleneck, we should consider using an RB-tree, or even better,
+ * let the core store drm_gem_object_mapping entries (where we
+ * could place driver specific data) instead of drm_gem_object ones
+ * in its drm_file->object_idr table.
+ *
+ * struct drm_gem_object_mapping {
+ * struct drm_gem_object *obj;
+ * void *driver_priv;
+ * };
+ */
+ struct {
+ struct list_head list;
+ struct mutex lock;
+ } mappings;
+
bool noexec :1;
bool is_heap :1;
};
+struct panfrost_gem_mapping {
+ struct list_head node;
+ struct kref refcount;
+ struct panfrost_gem_object *obj;
+ struct drm_mm_node mmnode;
+ struct panfrost_mmu *mmu;
+ bool active :1;
+};
+
static inline
struct panfrost_gem_object *to_panfrost_bo(struct drm_gem_object *obj)
{
return container_of(to_drm_gem_shmem_obj(obj), struct panfrost_gem_object, base);
}
-static inline
-struct panfrost_gem_object *drm_mm_node_to_panfrost_bo(struct drm_mm_node *node)
+static inline struct panfrost_gem_mapping *
+drm_mm_node_to_panfrost_mapping(struct drm_mm_node *node)
{
- return container_of(node, struct panfrost_gem_object, node);
+ return container_of(node, struct panfrost_gem_mapping, mmnode);
}
struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t size);
@@ -49,6 +72,12 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv);
void panfrost_gem_close(struct drm_gem_object *obj,
struct drm_file *file_priv);
+struct panfrost_gem_mapping *
+panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
+ struct panfrost_file_priv *priv);
+void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping);
+void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo);
+
void panfrost_gem_shrinker_init(struct drm_device *dev);
void panfrost_gem_shrinker_cleanup(struct drm_device *dev);
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
index 458f0fa..f5dd7b2 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
@@ -39,11 +39,12 @@ panfrost_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc
static bool panfrost_gem_purge(struct drm_gem_object *obj)
{
struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+ struct panfrost_gem_object *bo = to_panfrost_bo(obj);
if (!mutex_trylock(&shmem->pages_lock))
return false;
- panfrost_mmu_unmap(to_panfrost_bo(obj));
+ panfrost_gem_teardown_mappings(bo);
drm_gem_shmem_purge_locked(obj);
mutex_unlock(&shmem->pages_lock);
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index d411eb6..e364ee0 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -268,9 +268,20 @@ static void panfrost_job_cleanup(struct kref *ref)
dma_fence_put(job->done_fence);
dma_fence_put(job->render_done_fence);
- if (job->bos) {
+ if (job->mappings) {
for (i = 0; i < job->bo_count; i++)
+ panfrost_gem_mapping_put(job->mappings[i]);
+ kvfree(job->mappings);
+ }
+
+ if (job->bos) {
+ struct panfrost_gem_object *bo;
+
+ for (i = 0; i < job->bo_count; i++) {
+ bo = to_panfrost_bo(job->bos[i]);
drm_gem_object_put_unlocked(job->bos[i]);
+ }
+
kvfree(job->bos);
}
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.h b/drivers/gpu/drm/panfrost/panfrost_job.h
index 6245412..bbd3ba9 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.h
+++ b/drivers/gpu/drm/panfrost/panfrost_job.h
@@ -32,6 +32,7 @@ struct panfrost_job {
/* Exclusive fences we have taken from the BOs to wait for */
struct dma_fence **implicit_fences;
+ struct panfrost_gem_mapping **mappings;
struct drm_gem_object **bos;
u32 bo_count;
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index a3ed64a..763cfca 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -269,14 +269,15 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
return 0;
}
-int panfrost_mmu_map(struct panfrost_gem_object *bo)
+int panfrost_mmu_map(struct panfrost_gem_mapping *mapping)
{
+ struct panfrost_gem_object *bo = mapping->obj;
struct drm_gem_object *obj = &bo->base.base;
struct panfrost_device *pfdev = to_panfrost_device(obj->dev);
struct sg_table *sgt;
int prot = IOMMU_READ | IOMMU_WRITE;
- if (WARN_ON(bo->is_mapped))
+ if (WARN_ON(mapping->active))
return 0;
if (bo->noexec)
@@ -286,25 +287,28 @@ int panfrost_mmu_map(struct panfrost_gem_object *bo)
if (WARN_ON(IS_ERR(sgt)))
return PTR_ERR(sgt);
- mmu_map_sg(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, prot, sgt);
- bo->is_mapped = true;
+ mmu_map_sg(pfdev, mapping->mmu, mapping->mmnode.start << PAGE_SHIFT,
+ prot, sgt);
+ mapping->active = true;
return 0;
}
-void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
+void panfrost_mmu_unmap(struct panfrost_gem_mapping *mapping)
{
+ struct panfrost_gem_object *bo = mapping->obj;
struct drm_gem_object *obj = &bo->base.base;
struct panfrost_device *pfdev = to_panfrost_device(obj->dev);
- struct io_pgtable_ops *ops = bo->mmu->pgtbl_ops;
- u64 iova = bo->node.start << PAGE_SHIFT;
- size_t len = bo->node.size << PAGE_SHIFT;
+ struct io_pgtable_ops *ops = mapping->mmu->pgtbl_ops;
+ u64 iova = mapping->mmnode.start << PAGE_SHIFT;
+ size_t len = mapping->mmnode.size << PAGE_SHIFT;
size_t unmapped_len = 0;
- if (WARN_ON(!bo->is_mapped))
+ if (WARN_ON(!mapping->active))
return;
- dev_dbg(pfdev->dev, "unmap: as=%d, iova=%llx, len=%zx", bo->mmu->as, iova, len);
+ dev_dbg(pfdev->dev, "unmap: as=%d, iova=%llx, len=%zx",
+ mapping->mmu->as, iova, len);
while (unmapped_len < len) {
size_t unmapped_page;
@@ -318,8 +322,9 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
unmapped_len += pgsize;
}
- panfrost_mmu_flush_range(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, len);
- bo->is_mapped = false;
+ panfrost_mmu_flush_range(pfdev, mapping->mmu,
+ mapping->mmnode.start << PAGE_SHIFT, len);
+ mapping->active = false;
}
static void mmu_tlb_inv_context_s1(void *cookie)
@@ -394,10 +399,10 @@ void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv)
free_io_pgtable_ops(mmu->pgtbl_ops);
}
-static struct panfrost_gem_object *
-addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr)
+static struct panfrost_gem_mapping *
+addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr)
{
- struct panfrost_gem_object *bo = NULL;
+ struct panfrost_gem_mapping *mapping = NULL;
struct panfrost_file_priv *priv;
struct drm_mm_node *node;
u64 offset = addr >> PAGE_SHIFT;
@@ -418,8 +423,9 @@ addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr)
drm_mm_for_each_node(node, &priv->mm) {
if (offset >= node->start &&
offset < (node->start + node->size)) {
- bo = drm_mm_node_to_panfrost_bo(node);
- drm_gem_object_get(&bo->base.base);
+ mapping = drm_mm_node_to_panfrost_mapping(node);
+
+ kref_get(&mapping->refcount);
break;
}
}
@@ -427,7 +433,7 @@ addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr)
spin_unlock(&priv->mm_lock);
out:
spin_unlock(&pfdev->as_lock);
- return bo;
+ return mapping;
}
#define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE)
@@ -436,28 +442,30 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
u64 addr)
{
int ret, i;
+ struct panfrost_gem_mapping *bomapping;
struct panfrost_gem_object *bo;
struct address_space *mapping;
pgoff_t page_offset;
struct sg_table *sgt;
struct page **pages;
- bo = addr_to_drm_mm_node(pfdev, as, addr);
- if (!bo)
+ bomapping = addr_to_mapping(pfdev, as, addr);
+ if (!bomapping)
return -ENOENT;
+ bo = bomapping->obj;
if (!bo->is_heap) {
dev_WARN(pfdev->dev, "matching BO is not heap type (GPU VA = %llx)",
- bo->node.start << PAGE_SHIFT);
+ bomapping->mmnode.start << PAGE_SHIFT);
ret = -EINVAL;
goto err_bo;
}
- WARN_ON(bo->mmu->as != as);
+ WARN_ON(bomapping->mmu->as != as);
/* Assume 2MB alignment and size multiple */
addr &= ~((u64)SZ_2M - 1);
page_offset = addr >> PAGE_SHIFT;
- page_offset -= bo->node.start;
+ page_offset -= bomapping->mmnode.start;
mutex_lock(&bo->base.pages_lock);
@@ -509,13 +517,14 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
goto err_map;
}
- mmu_map_sg(pfdev, bo->mmu, addr, IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt);
+ mmu_map_sg(pfdev, bomapping->mmu, addr,
+ IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt);
- bo->is_mapped = true;
+ bomapping->active = true;
dev_dbg(pfdev->dev, "mapped page fault @ AS%d %llx", as, addr);
- drm_gem_object_put_unlocked(&bo->base.base);
+ panfrost_gem_mapping_put(bomapping);
return 0;
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.h b/drivers/gpu/drm/panfrost/panfrost_mmu.h
index 7c5b677..44fc2ed 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.h
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.h
@@ -4,12 +4,12 @@
#ifndef __PANFROST_MMU_H__
#define __PANFROST_MMU_H__
-struct panfrost_gem_object;
+struct panfrost_gem_mapping;
struct panfrost_file_priv;
struct panfrost_mmu;
-int panfrost_mmu_map(struct panfrost_gem_object *bo);
-void panfrost_mmu_unmap(struct panfrost_gem_object *bo);
+int panfrost_mmu_map(struct panfrost_gem_mapping *mapping);
+void panfrost_mmu_unmap(struct panfrost_gem_mapping *mapping);
int panfrost_mmu_init(struct panfrost_device *pfdev);
void panfrost_mmu_fini(struct panfrost_device *pfdev);
diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
index 2c04e85..6848204 100644
--- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
+++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
@@ -25,7 +25,7 @@
#define V4_SHADERS_PER_COREGROUP 4
struct panfrost_perfcnt {
- struct panfrost_gem_object *bo;
+ struct panfrost_gem_mapping *mapping;
size_t bosize;
void *buf;
struct panfrost_file_priv *user;
@@ -49,7 +49,7 @@ static int panfrost_perfcnt_dump_locked(struct panfrost_device *pfdev)
int ret;
reinit_completion(&pfdev->perfcnt->dump_comp);
- gpuva = pfdev->perfcnt->bo->node.start << PAGE_SHIFT;
+ gpuva = pfdev->perfcnt->mapping->mmnode.start << PAGE_SHIFT;
gpu_write(pfdev, GPU_PERFCNT_BASE_LO, gpuva);
gpu_write(pfdev, GPU_PERFCNT_BASE_HI, gpuva >> 32);
gpu_write(pfdev, GPU_INT_CLEAR,
@@ -89,17 +89,22 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev,
if (IS_ERR(bo))
return PTR_ERR(bo);
- perfcnt->bo = to_panfrost_bo(&bo->base);
-
/* Map the perfcnt buf in the address space attached to file_priv. */
- ret = panfrost_gem_open(&perfcnt->bo->base.base, file_priv);
+ ret = panfrost_gem_open(&bo->base, file_priv);
if (ret)
goto err_put_bo;
+ perfcnt->mapping = panfrost_gem_mapping_get(to_panfrost_bo(&bo->base),
+ user);
+ if (!perfcnt->mapping) {
+ ret = -EINVAL;
+ goto err_close_bo;
+ }
+
perfcnt->buf = drm_gem_shmem_vmap(&bo->base);
if (IS_ERR(perfcnt->buf)) {
ret = PTR_ERR(perfcnt->buf);
- goto err_close_bo;
+ goto err_put_mapping;
}
/*
@@ -154,12 +159,17 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev,
if (panfrost_has_hw_issue(pfdev, HW_ISSUE_8186))
gpu_write(pfdev, GPU_PRFCNT_TILER_EN, 0xffffffff);
+ /* The BO ref is retained by the mapping. */
+ drm_gem_object_put_unlocked(&bo->base);
+
return 0;
err_vunmap:
- drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf);
+ drm_gem_shmem_vunmap(&bo->base, perfcnt->buf);
+err_put_mapping:
+ panfrost_gem_mapping_put(perfcnt->mapping);
err_close_bo:
- panfrost_gem_close(&perfcnt->bo->base.base, file_priv);
+ panfrost_gem_close(&bo->base, file_priv);
err_put_bo:
drm_gem_object_put_unlocked(&bo->base);
return ret;
@@ -182,11 +192,11 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev,
GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_OFF));
perfcnt->user = NULL;
- drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf);
+ drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, perfcnt->buf);
perfcnt->buf = NULL;
- panfrost_gem_close(&perfcnt->bo->base.base, file_priv);
- drm_gem_object_put_unlocked(&perfcnt->bo->base.base);
- perfcnt->bo = NULL;
+ panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv);
+ panfrost_gem_mapping_put(perfcnt->mapping);
+ perfcnt->mapping = NULL;
pm_runtime_mark_last_busy(pfdev->dev);
pm_runtime_put_autosuspend(pfdev->dev);
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.h b/drivers/gpu/drm/rockchip/cdn-dp-core.h
index 83c4586..81ac9b6 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.h
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.h
@@ -95,7 +95,7 @@ struct cdn_dp_device {
struct cdn_dp_port *port[MAX_PHY];
u8 ports;
u8 max_lanes;
- u8 max_rate;
+ unsigned int max_rate;
u8 lanes;
int active_port;
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index a7c4654..68d4644 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -685,8 +685,6 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master,
struct sun4i_hdmi *hdmi = dev_get_drvdata(dev);
cec_unregister_adapter(hdmi->cec_adap);
- drm_connector_cleanup(&hdmi->connector);
- drm_encoder_cleanup(&hdmi->encoder);
i2c_del_adapter(hdmi->i2c);
i2c_put_adapter(hdmi->ddc_i2c);
clk_disable_unprepare(hdmi->mod_clk);
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 42651d7..c81cdce 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -489,7 +489,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
WARN_ON(!tcon->quirks->has_channel_0);
- tcon->dclk_min_div = 1;
+ tcon->dclk_min_div = tcon->quirks->dclk_min_div;
tcon->dclk_max_div = 127;
sun4i_tcon0_mode_set_common(tcon, mode);
@@ -1426,12 +1426,14 @@ static int sun8i_r40_tcon_tv_set_mux(struct sun4i_tcon *tcon,
static const struct sun4i_tcon_quirks sun4i_a10_quirks = {
.has_channel_0 = true,
.has_channel_1 = true,
+ .dclk_min_div = 4,
.set_mux = sun4i_a10_tcon_set_mux,
};
static const struct sun4i_tcon_quirks sun5i_a13_quirks = {
.has_channel_0 = true,
.has_channel_1 = true,
+ .dclk_min_div = 4,
.set_mux = sun5i_a13_tcon_set_mux,
};
@@ -1440,6 +1442,7 @@ static const struct sun4i_tcon_quirks sun6i_a31_quirks = {
.has_channel_1 = true,
.has_lvds_alt = true,
.needs_de_be_mux = true,
+ .dclk_min_div = 1,
.set_mux = sun6i_tcon_set_mux,
};
@@ -1447,11 +1450,13 @@ static const struct sun4i_tcon_quirks sun6i_a31s_quirks = {
.has_channel_0 = true,
.has_channel_1 = true,
.needs_de_be_mux = true,
+ .dclk_min_div = 1,
};
static const struct sun4i_tcon_quirks sun7i_a20_quirks = {
.has_channel_0 = true,
.has_channel_1 = true,
+ .dclk_min_div = 4,
/* Same display pipeline structure as A10 */
.set_mux = sun4i_a10_tcon_set_mux,
};
@@ -1459,11 +1464,13 @@ static const struct sun4i_tcon_quirks sun7i_a20_quirks = {
static const struct sun4i_tcon_quirks sun8i_a33_quirks = {
.has_channel_0 = true,
.has_lvds_alt = true,
+ .dclk_min_div = 1,
};
static const struct sun4i_tcon_quirks sun8i_a83t_lcd_quirks = {
.supports_lvds = true,
.has_channel_0 = true,
+ .dclk_min_div = 1,
};
static const struct sun4i_tcon_quirks sun8i_a83t_tv_quirks = {
@@ -1477,11 +1484,13 @@ static const struct sun4i_tcon_quirks sun8i_r40_tv_quirks = {
static const struct sun4i_tcon_quirks sun8i_v3s_quirks = {
.has_channel_0 = true,
+ .dclk_min_div = 1,
};
static const struct sun4i_tcon_quirks sun9i_a80_tcon_lcd_quirks = {
- .has_channel_0 = true,
- .needs_edp_reset = true,
+ .has_channel_0 = true,
+ .needs_edp_reset = true,
+ .dclk_min_div = 1,
};
static const struct sun4i_tcon_quirks sun9i_a80_tcon_tv_quirks = {
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.h b/drivers/gpu/drm/sun4i/sun4i_tcon.h
index f9f1fe80..a62ec82 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.h
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.h
@@ -224,6 +224,7 @@ struct sun4i_tcon_quirks {
bool needs_de_be_mux; /* sun6i needs mux to select backend */
bool needs_edp_reset; /* a80 edp reset needed for tcon0 access */
bool supports_lvds; /* Does the TCON support an LVDS output? */
+ u8 dclk_min_div; /* minimum divider for TCON0 DCLK */
/* callback to handle tcon muxing options */
int (*set_mux)(struct sun4i_tcon *, const struct drm_encoder *);
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index 3905241..1635a9f 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -232,6 +232,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
if (!objs)
return;
virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]);
+ virtio_gpu_array_lock_resv(objs);
virtio_gpu_cmd_transfer_to_host_2d
(vgdev, 0,
plane->state->crtc_w,
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 8063b1d..e6e4c84 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -261,7 +261,8 @@ static int asus_event(struct hid_device *hdev, struct hid_field *field,
struct hid_usage *usage, __s32 value)
{
if ((usage->hid & HID_USAGE_PAGE) == 0xff310000 &&
- (usage->hid & HID_USAGE) != 0x00 && !usage->type) {
+ (usage->hid & HID_USAGE) != 0x00 &&
+ (usage->hid & HID_USAGE) != 0xff && !usage->type) {
hid_warn(hdev, "Unmapped Asus vendor usagepage code 0x%02x\n",
usage->hid & HID_USAGE);
}
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index e0b241bd..851fe54 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -288,6 +288,12 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign
offset = report->size;
report->size += parser->global.report_size * parser->global.report_count;
+ /* Total size check: Allow for possible report index byte */
+ if (report->size > (HID_MAX_BUFFER_SIZE - 1) << 3) {
+ hid_err(parser->device, "report is too long\n");
+ return -1;
+ }
+
if (!parser->local.usage_index) /* Ignore padding fields */
return 0;
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 7e1689e..3a400ce 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -631,6 +631,7 @@
#define USB_VENDOR_ID_ITE 0x048d
#define USB_DEVICE_ID_ITE_LENOVO_YOGA 0x8386
#define USB_DEVICE_ID_ITE_LENOVO_YOGA2 0x8350
+#define I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720 0x837a
#define USB_DEVICE_ID_ITE_LENOVO_YOGA900 0x8396
#define USB_DEVICE_ID_ITE8595 0x8595
@@ -730,6 +731,7 @@
#define USB_DEVICE_ID_LG_MULTITOUCH 0x0064
#define USB_DEVICE_ID_LG_MELFAS_MT 0x6007
#define I2C_DEVICE_ID_LG_8001 0x8001
+#define I2C_DEVICE_ID_LG_7010 0x7010
#define USB_VENDOR_ID_LOGITECH 0x046d
#define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e
@@ -1102,6 +1104,7 @@
#define USB_DEVICE_ID_SYNAPTICS_LTS2 0x1d10
#define USB_DEVICE_ID_SYNAPTICS_HD 0x0ac3
#define USB_DEVICE_ID_SYNAPTICS_QUAD_HD 0x1ac3
+#define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012 0x2968
#define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710
#define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 63855f2..dea9cc6 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1132,9 +1132,15 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
}
mapped:
- if (device->driver->input_mapped && device->driver->input_mapped(device,
- hidinput, field, usage, &bit, &max) < 0)
- goto ignore;
+ if (device->driver->input_mapped &&
+ device->driver->input_mapped(device, hidinput, field, usage,
+ &bit, &max) < 0) {
+ /*
+ * The driver indicated that no further generic handling
+ * of the usage is desired.
+ */
+ return;
+ }
set_bit(usage->type, input->evbit);
@@ -1215,9 +1221,11 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
set_bit(MSC_SCAN, input->mscbit);
}
-ignore:
return;
+ignore:
+ usage->type = 0;
+ usage->code = 0;
}
static void hidinput_handle_scroll(struct hid_usage *usage,
diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c
index a45f235..c436e12 100644
--- a/drivers/hid/hid-ite.c
+++ b/drivers/hid/hid-ite.c
@@ -40,6 +40,9 @@ static int ite_event(struct hid_device *hdev, struct hid_field *field,
static const struct hid_device_id ite_devices[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) },
{ HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) },
+ /* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */
+ { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS,
+ USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) },
{ }
};
MODULE_DEVICE_TABLE(hid, ite_devices);
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 3cfeb16..362805d 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1019,7 +1019,7 @@ static int mt_process_slot(struct mt_device *td, struct input_dev *input,
tool = MT_TOOL_DIAL;
else if (unlikely(!confidence_state)) {
tool = MT_TOOL_PALM;
- if (!active &&
+ if (!active && mt &&
input_mt_is_active(&mt->slots[slotnum])) {
/*
* The non-confidence was reported for
@@ -1985,6 +1985,9 @@ static const struct hid_device_id mt_devices[] = {
{ .driver_data = MT_CLS_LG,
HID_USB_DEVICE(USB_VENDOR_ID_LG,
USB_DEVICE_ID_LG_MELFAS_MT) },
+ { .driver_data = MT_CLS_LG,
+ HID_DEVICE(BUS_I2C, HID_GROUP_GENERIC,
+ USB_VENDOR_ID_LG, I2C_DEVICE_ID_LG_7010) },
/* MosArt panels */
{ .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE,
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index d1b39c2..0e7b2d9 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -174,6 +174,7 @@ static const struct hid_device_id hid_quirks[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SIRIUS_BATTERY_FREE_TABLET), HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD2, USB_DEVICE_ID_SMARTJOY_DUAL_PLUS), HID_QUIRK_NOGET | HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_QUAD_USB_JOYPAD), HID_QUIRK_NOGET | HID_QUIRK_MULTI_INPUT },
+ { HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_XIN_MO_DUAL_ARCADE), HID_QUIRK_MULTI_INPUT },
{ 0 }
};
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index 8dae0f9..6286204 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -768,8 +768,12 @@ static int steam_probe(struct hid_device *hdev,
if (steam->quirks & STEAM_QUIRK_WIRELESS) {
hid_info(hdev, "Steam wireless receiver connected");
+ /* If using a wireless adaptor ask for connection status */
+ steam->connected = false;
steam_request_conn_status(steam);
} else {
+ /* A wired connection is always present */
+ steam->connected = true;
ret = steam_register(steam);
if (ret) {
hid_err(hdev,
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index c3fc0ce..7a75aff 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -249,13 +249,14 @@ static ssize_t hidraw_get_report(struct file *file, char __user *buffer, size_t
static __poll_t hidraw_poll(struct file *file, poll_table *wait)
{
struct hidraw_list *list = file->private_data;
+ __poll_t mask = EPOLLOUT | EPOLLWRNORM; /* hidraw is always writable */
poll_wait(file, &list->hidraw->wait, wait);
if (list->head != list->tail)
- return EPOLLIN | EPOLLRDNORM | EPOLLOUT;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (!list->hidraw->exist)
- return EPOLLERR | EPOLLHUP;
- return 0;
+ mask |= EPOLLERR | EPOLLHUP;
+ return mask;
}
static int hidraw_open(struct inode *inode, struct file *file)
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index a358e61..009000c 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -49,6 +49,8 @@
#define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET BIT(1)
#define I2C_HID_QUIRK_BOGUS_IRQ BIT(4)
#define I2C_HID_QUIRK_RESET_ON_RESUME BIT(5)
+#define I2C_HID_QUIRK_BAD_INPUT_SIZE BIT(6)
+
/* flags */
#define I2C_HID_STARTED 0
@@ -175,6 +177,8 @@ static const struct i2c_hid_quirks {
I2C_HID_QUIRK_BOGUS_IRQ },
{ USB_VENDOR_ID_ALPS_JP, HID_ANY_ID,
I2C_HID_QUIRK_RESET_ON_RESUME },
+ { USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720,
+ I2C_HID_QUIRK_BAD_INPUT_SIZE },
{ 0, 0 }
};
@@ -496,9 +500,15 @@ static void i2c_hid_get_input(struct i2c_hid *ihid)
}
if ((ret_size > size) || (ret_size < 2)) {
- dev_err(&ihid->client->dev, "%s: incomplete report (%d/%d)\n",
- __func__, size, ret_size);
- return;
+ if (ihid->quirks & I2C_HID_QUIRK_BAD_INPUT_SIZE) {
+ ihid->inbuf[0] = size & 0xff;
+ ihid->inbuf[1] = size >> 8;
+ ret_size = size;
+ } else {
+ dev_err(&ihid->client->dev, "%s: incomplete report (%d/%d)\n",
+ __func__, size, ret_size);
+ return;
+ }
}
i2c_hid_dbg(ihid, "input: %*ph\n", ret_size, ihid->inbuf);
diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
index 6c1e611..1fb294c 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
@@ -24,7 +24,9 @@
#define ICL_MOBILE_DEVICE_ID 0x34FC
#define SPT_H_DEVICE_ID 0xA135
#define CML_LP_DEVICE_ID 0x02FC
+#define CMP_H_DEVICE_ID 0x06FC
#define EHL_Ax_DEVICE_ID 0x4BB3
+#define TGL_LP_DEVICE_ID 0xA0FC
#define REVISION_ID_CHT_A0 0x6
#define REVISION_ID_CHT_Ax_SI 0x0
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 784dcc8..f491d8b 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -34,7 +34,9 @@ static const struct pci_device_id ish_pci_tbl[] = {
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, ICL_MOBILE_DEVICE_ID)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, SPT_H_DEVICE_ID)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, CML_LP_DEVICE_ID)},
+ {PCI_DEVICE(PCI_VENDOR_ID_INTEL, CMP_H_DEVICE_ID)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, EHL_Ax_DEVICE_ID)},
+ {PCI_DEVICE(PCI_VENDOR_ID_INTEL, TGL_LP_DEVICE_ID)},
{0, }
};
MODULE_DEVICE_TABLE(pci, ish_pci_tbl);
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index fa0cc089..8fe3efc 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -766,13 +766,14 @@ static ssize_t uhid_char_write(struct file *file, const char __user *buffer,
static __poll_t uhid_char_poll(struct file *file, poll_table *wait)
{
struct uhid_device *uhid = file->private_data;
+ __poll_t mask = EPOLLOUT | EPOLLWRNORM; /* uhid is always writable */
poll_wait(file, &uhid->waitq, wait);
if (uhid->head != uhid->tail)
- return EPOLLIN | EPOLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
- return 0;
+ return mask;
}
static const struct file_operations uhid_fops = {
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index e421cdf..a970b80 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -241,12 +241,51 @@ static int hiddev_release(struct inode * inode, struct file * file)
return 0;
}
+static int __hiddev_open(struct hiddev *hiddev, struct file *file)
+{
+ struct hiddev_list *list;
+ int error;
+
+ lockdep_assert_held(&hiddev->existancelock);
+
+ list = vzalloc(sizeof(*list));
+ if (!list)
+ return -ENOMEM;
+
+ mutex_init(&list->thread_lock);
+ list->hiddev = hiddev;
+
+ if (!hiddev->open++) {
+ error = hid_hw_power(hiddev->hid, PM_HINT_FULLON);
+ if (error < 0)
+ goto err_drop_count;
+
+ error = hid_hw_open(hiddev->hid);
+ if (error < 0)
+ goto err_normal_power;
+ }
+
+ spin_lock_irq(&hiddev->list_lock);
+ list_add_tail(&list->node, &hiddev->list);
+ spin_unlock_irq(&hiddev->list_lock);
+
+ file->private_data = list;
+
+ return 0;
+
+err_normal_power:
+ hid_hw_power(hiddev->hid, PM_HINT_NORMAL);
+err_drop_count:
+ hiddev->open--;
+ vfree(list);
+ return error;
+}
+
/*
* open file op
*/
static int hiddev_open(struct inode *inode, struct file *file)
{
- struct hiddev_list *list;
struct usb_interface *intf;
struct hid_device *hid;
struct hiddev *hiddev;
@@ -255,66 +294,14 @@ static int hiddev_open(struct inode *inode, struct file *file)
intf = usbhid_find_interface(iminor(inode));
if (!intf)
return -ENODEV;
+
hid = usb_get_intfdata(intf);
hiddev = hid->hiddev;
- if (!(list = vzalloc(sizeof(struct hiddev_list))))
- return -ENOMEM;
- mutex_init(&list->thread_lock);
- list->hiddev = hiddev;
- file->private_data = list;
-
- /*
- * no need for locking because the USB major number
- * is shared which usbcore guards against disconnect
- */
- if (list->hiddev->exist) {
- if (!list->hiddev->open++) {
- res = hid_hw_open(hiddev->hid);
- if (res < 0)
- goto bail;
- }
- } else {
- res = -ENODEV;
- goto bail;
- }
-
- spin_lock_irq(&list->hiddev->list_lock);
- list_add_tail(&list->node, &hiddev->list);
- spin_unlock_irq(&list->hiddev->list_lock);
-
mutex_lock(&hiddev->existancelock);
- /*
- * recheck exist with existance lock held to
- * avoid opening a disconnected device
- */
- if (!list->hiddev->exist) {
- res = -ENODEV;
- goto bail_unlock;
- }
- if (!list->hiddev->open++)
- if (list->hiddev->exist) {
- struct hid_device *hid = hiddev->hid;
- res = hid_hw_power(hid, PM_HINT_FULLON);
- if (res < 0)
- goto bail_unlock;
- res = hid_hw_open(hid);
- if (res < 0)
- goto bail_normal_power;
- }
- mutex_unlock(&hiddev->existancelock);
- return 0;
-bail_normal_power:
- hid_hw_power(hid, PM_HINT_NORMAL);
-bail_unlock:
+ res = hiddev->exist ? __hiddev_open(hiddev, file) : -ENODEV;
mutex_unlock(&hiddev->existancelock);
- spin_lock_irq(&list->hiddev->list_lock);
- list_del(&list->node);
- spin_unlock_irq(&list->hiddev->list_lock);
-bail:
- file->private_data = NULL;
- vfree(list);
return res;
}
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index ccb7452..d99a9d4 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2096,14 +2096,16 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
(hdev->product == 0x34d || hdev->product == 0x34e || /* MobileStudio Pro */
hdev->product == 0x357 || hdev->product == 0x358 || /* Intuos Pro 2 */
hdev->product == 0x392 || /* Intuos Pro 2 */
- hdev->product == 0x398 || hdev->product == 0x399)) { /* MobileStudio Pro */
+ hdev->product == 0x398 || hdev->product == 0x399 || /* MobileStudio Pro */
+ hdev->product == 0x3AA)) { /* MobileStudio Pro */
value = (field->logical_maximum - value);
if (hdev->product == 0x357 || hdev->product == 0x358 ||
hdev->product == 0x392)
value = wacom_offset_rotation(input, usage, value, 3, 16);
else if (hdev->product == 0x34d || hdev->product == 0x34e ||
- hdev->product == 0x398 || hdev->product == 0x399)
+ hdev->product == 0x398 || hdev->product == 0x399 ||
+ hdev->product == 0x3AA)
value = wacom_offset_rotation(input, usage, value, 1, 2);
}
else {
diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index 6c64d50..01c2eeb 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -294,9 +294,10 @@ static inline u16 volt2reg(int channel, long volt, u8 bypass_attn)
long reg;
if (bypass_attn & (1 << channel))
- reg = (volt * 1024) / 2250;
+ reg = DIV_ROUND_CLOSEST(volt * 1024, 2250);
else
- reg = (volt * r[1] * 1024) / ((r[0] + r[1]) * 2250);
+ reg = DIV_ROUND_CLOSEST(volt * r[1] * 1024,
+ (r[0] + r[1]) * 2250);
return clamp_val(reg, 0, 1023) & (0xff << 2);
}
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 1f3b30b..d018b20 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -51,6 +51,7 @@ struct hwmon_device_attribute {
#define to_hwmon_attr(d) \
container_of(d, struct hwmon_device_attribute, dev_attr)
+#define to_dev_attr(a) container_of(a, struct device_attribute, attr)
/*
* Thermal zone information
@@ -58,7 +59,7 @@ struct hwmon_device_attribute {
* also provides the sensor index.
*/
struct hwmon_thermal_data {
- struct hwmon_device *hwdev; /* Reference to hwmon device */
+ struct device *dev; /* Reference to hwmon device */
int index; /* sensor index */
};
@@ -95,9 +96,27 @@ static const struct attribute_group *hwmon_dev_attr_groups[] = {
NULL
};
+static void hwmon_free_attrs(struct attribute **attrs)
+{
+ int i;
+
+ for (i = 0; attrs[i]; i++) {
+ struct device_attribute *dattr = to_dev_attr(attrs[i]);
+ struct hwmon_device_attribute *hattr = to_hwmon_attr(dattr);
+
+ kfree(hattr);
+ }
+ kfree(attrs);
+}
+
static void hwmon_dev_release(struct device *dev)
{
- kfree(to_hwmon_device(dev));
+ struct hwmon_device *hwdev = to_hwmon_device(dev);
+
+ if (hwdev->group.attrs)
+ hwmon_free_attrs(hwdev->group.attrs);
+ kfree(hwdev->groups);
+ kfree(hwdev);
}
static struct class hwmon_class = {
@@ -119,11 +138,11 @@ static DEFINE_IDA(hwmon_ida);
static int hwmon_thermal_get_temp(void *data, int *temp)
{
struct hwmon_thermal_data *tdata = data;
- struct hwmon_device *hwdev = tdata->hwdev;
+ struct hwmon_device *hwdev = to_hwmon_device(tdata->dev);
int ret;
long t;
- ret = hwdev->chip->ops->read(&hwdev->dev, hwmon_temp, hwmon_temp_input,
+ ret = hwdev->chip->ops->read(tdata->dev, hwmon_temp, hwmon_temp_input,
tdata->index, &t);
if (ret < 0)
return ret;
@@ -137,8 +156,7 @@ static const struct thermal_zone_of_device_ops hwmon_thermal_ops = {
.get_temp = hwmon_thermal_get_temp,
};
-static int hwmon_thermal_add_sensor(struct device *dev,
- struct hwmon_device *hwdev, int index)
+static int hwmon_thermal_add_sensor(struct device *dev, int index)
{
struct hwmon_thermal_data *tdata;
struct thermal_zone_device *tzd;
@@ -147,10 +165,10 @@ static int hwmon_thermal_add_sensor(struct device *dev,
if (!tdata)
return -ENOMEM;
- tdata->hwdev = hwdev;
+ tdata->dev = dev;
tdata->index = index;
- tzd = devm_thermal_zone_of_sensor_register(&hwdev->dev, index, tdata,
+ tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata,
&hwmon_thermal_ops);
/*
* If CONFIG_THERMAL_OF is disabled, this returns -ENODEV,
@@ -162,8 +180,7 @@ static int hwmon_thermal_add_sensor(struct device *dev,
return 0;
}
#else
-static int hwmon_thermal_add_sensor(struct device *dev,
- struct hwmon_device *hwdev, int index)
+static int hwmon_thermal_add_sensor(struct device *dev, int index)
{
return 0;
}
@@ -250,8 +267,7 @@ static bool is_string_attr(enum hwmon_sensor_types type, u32 attr)
(type == hwmon_fan && attr == hwmon_fan_label);
}
-static struct attribute *hwmon_genattr(struct device *dev,
- const void *drvdata,
+static struct attribute *hwmon_genattr(const void *drvdata,
enum hwmon_sensor_types type,
u32 attr,
int index,
@@ -279,7 +295,7 @@ static struct attribute *hwmon_genattr(struct device *dev,
if ((mode & 0222) && !ops->write)
return ERR_PTR(-EINVAL);
- hattr = devm_kzalloc(dev, sizeof(*hattr), GFP_KERNEL);
+ hattr = kzalloc(sizeof(*hattr), GFP_KERNEL);
if (!hattr)
return ERR_PTR(-ENOMEM);
@@ -492,8 +508,7 @@ static int hwmon_num_channel_attrs(const struct hwmon_channel_info *info)
return n;
}
-static int hwmon_genattrs(struct device *dev,
- const void *drvdata,
+static int hwmon_genattrs(const void *drvdata,
struct attribute **attrs,
const struct hwmon_ops *ops,
const struct hwmon_channel_info *info)
@@ -519,7 +534,7 @@ static int hwmon_genattrs(struct device *dev,
attr_mask &= ~BIT(attr);
if (attr >= template_size)
return -EINVAL;
- a = hwmon_genattr(dev, drvdata, info->type, attr, i,
+ a = hwmon_genattr(drvdata, info->type, attr, i,
templates[attr], ops);
if (IS_ERR(a)) {
if (PTR_ERR(a) != -ENOENT)
@@ -533,8 +548,7 @@ static int hwmon_genattrs(struct device *dev,
}
static struct attribute **
-__hwmon_create_attrs(struct device *dev, const void *drvdata,
- const struct hwmon_chip_info *chip)
+__hwmon_create_attrs(const void *drvdata, const struct hwmon_chip_info *chip)
{
int ret, i, aindex = 0, nattrs = 0;
struct attribute **attrs;
@@ -545,15 +559,17 @@ __hwmon_create_attrs(struct device *dev, const void *drvdata,
if (nattrs == 0)
return ERR_PTR(-EINVAL);
- attrs = devm_kcalloc(dev, nattrs + 1, sizeof(*attrs), GFP_KERNEL);
+ attrs = kcalloc(nattrs + 1, sizeof(*attrs), GFP_KERNEL);
if (!attrs)
return ERR_PTR(-ENOMEM);
for (i = 0; chip->info[i]; i++) {
- ret = hwmon_genattrs(dev, drvdata, &attrs[aindex], chip->ops,
+ ret = hwmon_genattrs(drvdata, &attrs[aindex], chip->ops,
chip->info[i]);
- if (ret < 0)
+ if (ret < 0) {
+ hwmon_free_attrs(attrs);
return ERR_PTR(ret);
+ }
aindex += ret;
}
@@ -595,14 +611,13 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
for (i = 0; groups[i]; i++)
ngroups++;
- hwdev->groups = devm_kcalloc(dev, ngroups, sizeof(*groups),
- GFP_KERNEL);
+ hwdev->groups = kcalloc(ngroups, sizeof(*groups), GFP_KERNEL);
if (!hwdev->groups) {
err = -ENOMEM;
goto free_hwmon;
}
- attrs = __hwmon_create_attrs(dev, drvdata, chip);
+ attrs = __hwmon_create_attrs(drvdata, chip);
if (IS_ERR(attrs)) {
err = PTR_ERR(attrs);
goto free_hwmon;
@@ -647,8 +662,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
hwmon_temp_input, j))
continue;
if (info[i]->config[j] & HWMON_T_INPUT) {
- err = hwmon_thermal_add_sensor(dev,
- hwdev, j);
+ err = hwmon_thermal_add_sensor(hdev, j);
if (err) {
device_unregister(hdev);
/*
@@ -667,7 +681,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
return hdev;
free_hwmon:
- kfree(hwdev);
+ hwmon_dev_release(hdev);
ida_remove:
ida_simple_remove(&hwmon_ida, id);
return ERR_PTR(err);
diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c
index f3dd2a1..2e97e56 100644
--- a/drivers/hwmon/nct7802.c
+++ b/drivers/hwmon/nct7802.c
@@ -23,8 +23,8 @@
static const u8 REG_VOLTAGE[5] = { 0x09, 0x0a, 0x0c, 0x0d, 0x0e };
static const u8 REG_VOLTAGE_LIMIT_LSB[2][5] = {
- { 0x40, 0x00, 0x42, 0x44, 0x46 },
- { 0x3f, 0x00, 0x41, 0x43, 0x45 },
+ { 0x46, 0x00, 0x40, 0x42, 0x44 },
+ { 0x45, 0x00, 0x3f, 0x41, 0x43 },
};
static const u8 REG_VOLTAGE_LIMIT_MSB[5] = { 0x48, 0x00, 0x47, 0x47, 0x48 };
@@ -58,6 +58,8 @@ static const u8 REG_VOLTAGE_LIMIT_MSB_SHIFT[2][5] = {
struct nct7802_data {
struct regmap *regmap;
struct mutex access_lock; /* for multi-byte read and write operations */
+ u8 in_status;
+ struct mutex in_alarm_lock;
};
static ssize_t temp_type_show(struct device *dev,
@@ -368,6 +370,66 @@ static ssize_t in_store(struct device *dev, struct device_attribute *attr,
return err ? : count;
}
+static ssize_t in_alarm_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
+ struct nct7802_data *data = dev_get_drvdata(dev);
+ int volt, min, max, ret;
+ unsigned int val;
+
+ mutex_lock(&data->in_alarm_lock);
+
+ /*
+ * The SMI Voltage status register is the only register giving a status
+ * for voltages. A bit is set for each input crossing a threshold, in
+ * both direction, but the "inside" or "outside" limits info is not
+ * available. Also this register is cleared on read.
+ * Note: this is not explicitly spelled out in the datasheet, but
+ * from experiment.
+ * To deal with this we use a status cache with one validity bit and
+ * one status bit for each input. Validity is cleared at startup and
+ * each time the register reports a change, and the status is processed
+ * by software based on current input value and limits.
+ */
+ ret = regmap_read(data->regmap, 0x1e, &val); /* SMI Voltage status */
+ if (ret < 0)
+ goto abort;
+
+ /* invalidate cached status for all inputs crossing a threshold */
+ data->in_status &= ~((val & 0x0f) << 4);
+
+ /* if cached status for requested input is invalid, update it */
+ if (!(data->in_status & (0x10 << sattr->index))) {
+ ret = nct7802_read_voltage(data, sattr->nr, 0);
+ if (ret < 0)
+ goto abort;
+ volt = ret;
+
+ ret = nct7802_read_voltage(data, sattr->nr, 1);
+ if (ret < 0)
+ goto abort;
+ min = ret;
+
+ ret = nct7802_read_voltage(data, sattr->nr, 2);
+ if (ret < 0)
+ goto abort;
+ max = ret;
+
+ if (volt < min || volt > max)
+ data->in_status |= (1 << sattr->index);
+ else
+ data->in_status &= ~(1 << sattr->index);
+
+ data->in_status |= 0x10 << sattr->index;
+ }
+
+ ret = sprintf(buf, "%u\n", !!(data->in_status & (1 << sattr->index)));
+abort:
+ mutex_unlock(&data->in_alarm_lock);
+ return ret;
+}
+
static ssize_t temp_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
@@ -660,7 +722,7 @@ static const struct attribute_group nct7802_temp_group = {
static SENSOR_DEVICE_ATTR_2_RO(in0_input, in, 0, 0);
static SENSOR_DEVICE_ATTR_2_RW(in0_min, in, 0, 1);
static SENSOR_DEVICE_ATTR_2_RW(in0_max, in, 0, 2);
-static SENSOR_DEVICE_ATTR_2_RO(in0_alarm, alarm, 0x1e, 3);
+static SENSOR_DEVICE_ATTR_2_RO(in0_alarm, in_alarm, 0, 3);
static SENSOR_DEVICE_ATTR_2_RW(in0_beep, beep, 0x5a, 3);
static SENSOR_DEVICE_ATTR_2_RO(in1_input, in, 1, 0);
@@ -668,19 +730,19 @@ static SENSOR_DEVICE_ATTR_2_RO(in1_input, in, 1, 0);
static SENSOR_DEVICE_ATTR_2_RO(in2_input, in, 2, 0);
static SENSOR_DEVICE_ATTR_2_RW(in2_min, in, 2, 1);
static SENSOR_DEVICE_ATTR_2_RW(in2_max, in, 2, 2);
-static SENSOR_DEVICE_ATTR_2_RO(in2_alarm, alarm, 0x1e, 0);
+static SENSOR_DEVICE_ATTR_2_RO(in2_alarm, in_alarm, 2, 0);
static SENSOR_DEVICE_ATTR_2_RW(in2_beep, beep, 0x5a, 0);
static SENSOR_DEVICE_ATTR_2_RO(in3_input, in, 3, 0);
static SENSOR_DEVICE_ATTR_2_RW(in3_min, in, 3, 1);
static SENSOR_DEVICE_ATTR_2_RW(in3_max, in, 3, 2);
-static SENSOR_DEVICE_ATTR_2_RO(in3_alarm, alarm, 0x1e, 1);
+static SENSOR_DEVICE_ATTR_2_RO(in3_alarm, in_alarm, 3, 1);
static SENSOR_DEVICE_ATTR_2_RW(in3_beep, beep, 0x5a, 1);
static SENSOR_DEVICE_ATTR_2_RO(in4_input, in, 4, 0);
static SENSOR_DEVICE_ATTR_2_RW(in4_min, in, 4, 1);
static SENSOR_DEVICE_ATTR_2_RW(in4_max, in, 4, 2);
-static SENSOR_DEVICE_ATTR_2_RO(in4_alarm, alarm, 0x1e, 2);
+static SENSOR_DEVICE_ATTR_2_RO(in4_alarm, in_alarm, 4, 2);
static SENSOR_DEVICE_ATTR_2_RW(in4_beep, beep, 0x5a, 2);
static struct attribute *nct7802_in_attrs[] = {
@@ -1011,6 +1073,7 @@ static int nct7802_probe(struct i2c_client *client,
return PTR_ERR(data->regmap);
mutex_init(&data->access_lock);
+ mutex_init(&data->in_alarm_lock);
ret = nct7802_init_chip(data);
if (ret < 0)
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index dc3f507..a90d757 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -1132,7 +1132,6 @@ static void etm4_init_trace_id(struct etmv4_drvdata *drvdata)
drvdata->trcid = coresight_get_trace_id(drvdata->cpu);
}
-#ifdef CONFIG_CPU_PM
static int etm4_cpu_save(struct etmv4_drvdata *drvdata)
{
int i, ret = 0;
@@ -1402,17 +1401,17 @@ static struct notifier_block etm4_cpu_pm_nb = {
static int etm4_cpu_pm_register(void)
{
- return cpu_pm_register_notifier(&etm4_cpu_pm_nb);
+ if (IS_ENABLED(CONFIG_CPU_PM))
+ return cpu_pm_register_notifier(&etm4_cpu_pm_nb);
+
+ return 0;
}
static void etm4_cpu_pm_unregister(void)
{
- cpu_pm_unregister_notifier(&etm4_cpu_pm_nb);
+ if (IS_ENABLED(CONFIG_CPU_PM))
+ cpu_pm_unregister_notifier(&etm4_cpu_pm_nb);
}
-#else
-static int etm4_cpu_pm_register(void) { return 0; }
-static void etm4_cpu_pm_unregister(void) { }
-#endif
static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
{
diff --git a/drivers/i2c/busses/i2c-at91-core.c b/drivers/i2c/busses/i2c-at91-core.c
index e13af48..5137e62 100644
--- a/drivers/i2c/busses/i2c-at91-core.c
+++ b/drivers/i2c/busses/i2c-at91-core.c
@@ -174,7 +174,7 @@ static struct at91_twi_pdata sama5d2_config = {
static struct at91_twi_pdata sam9x60_config = {
.clk_max_div = 7,
- .clk_offset = 4,
+ .clk_offset = 3,
.has_unre_flag = true,
.has_alt_cmd = true,
.has_hold_field = true,
diff --git a/drivers/i2c/busses/i2c-bcm2835.c b/drivers/i2c/busses/i2c-bcm2835.c
index e01b2b5..5ab901a 100644
--- a/drivers/i2c/busses/i2c-bcm2835.c
+++ b/drivers/i2c/busses/i2c-bcm2835.c
@@ -58,6 +58,7 @@ struct bcm2835_i2c_dev {
struct i2c_adapter adapter;
struct completion completion;
struct i2c_msg *curr_msg;
+ struct clk *bus_clk;
int num_msgs;
u32 msg_err;
u8 *msg_buf;
@@ -404,7 +405,6 @@ static int bcm2835_i2c_probe(struct platform_device *pdev)
struct resource *mem, *irq;
int ret;
struct i2c_adapter *adap;
- struct clk *bus_clk;
struct clk *mclk;
u32 bus_clk_rate;
@@ -427,11 +427,11 @@ static int bcm2835_i2c_probe(struct platform_device *pdev)
return PTR_ERR(mclk);
}
- bus_clk = bcm2835_i2c_register_div(&pdev->dev, mclk, i2c_dev);
+ i2c_dev->bus_clk = bcm2835_i2c_register_div(&pdev->dev, mclk, i2c_dev);
- if (IS_ERR(bus_clk)) {
+ if (IS_ERR(i2c_dev->bus_clk)) {
dev_err(&pdev->dev, "Could not register clock\n");
- return PTR_ERR(bus_clk);
+ return PTR_ERR(i2c_dev->bus_clk);
}
ret = of_property_read_u32(pdev->dev.of_node, "clock-frequency",
@@ -442,13 +442,13 @@ static int bcm2835_i2c_probe(struct platform_device *pdev)
bus_clk_rate = 100000;
}
- ret = clk_set_rate_exclusive(bus_clk, bus_clk_rate);
+ ret = clk_set_rate_exclusive(i2c_dev->bus_clk, bus_clk_rate);
if (ret < 0) {
dev_err(&pdev->dev, "Could not set clock frequency\n");
return ret;
}
- ret = clk_prepare_enable(bus_clk);
+ ret = clk_prepare_enable(i2c_dev->bus_clk);
if (ret) {
dev_err(&pdev->dev, "Couldn't prepare clock");
return ret;
@@ -491,10 +491,9 @@ static int bcm2835_i2c_probe(struct platform_device *pdev)
static int bcm2835_i2c_remove(struct platform_device *pdev)
{
struct bcm2835_i2c_dev *i2c_dev = platform_get_drvdata(pdev);
- struct clk *bus_clk = devm_clk_get(i2c_dev->dev, "div");
- clk_rate_exclusive_put(bus_clk);
- clk_disable_unprepare(bus_clk);
+ clk_rate_exclusive_put(i2c_dev->bus_clk);
+ clk_disable_unprepare(i2c_dev->bus_clk);
free_irq(i2c_dev->irq, i2c_dev);
i2c_del_adapter(&i2c_dev->adapter);
diff --git a/drivers/i2c/busses/i2c-iop3xx.c b/drivers/i2c/busses/i2c-iop3xx.c
index 3855638..2f8b805 100644
--- a/drivers/i2c/busses/i2c-iop3xx.c
+++ b/drivers/i2c/busses/i2c-iop3xx.c
@@ -433,13 +433,17 @@ iop3xx_i2c_probe(struct platform_device *pdev)
adapter_data->gpio_scl = devm_gpiod_get_optional(&pdev->dev,
"scl",
GPIOD_ASIS);
- if (IS_ERR(adapter_data->gpio_scl))
- return PTR_ERR(adapter_data->gpio_scl);
+ if (IS_ERR(adapter_data->gpio_scl)) {
+ ret = PTR_ERR(adapter_data->gpio_scl);
+ goto free_both;
+ }
adapter_data->gpio_sda = devm_gpiod_get_optional(&pdev->dev,
"sda",
GPIOD_ASIS);
- if (IS_ERR(adapter_data->gpio_sda))
- return PTR_ERR(adapter_data->gpio_sda);
+ if (IS_ERR(adapter_data->gpio_sda)) {
+ ret = PTR_ERR(adapter_data->gpio_sda);
+ goto free_both;
+ }
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!res) {
diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
index a98bf31..61339c6 100644
--- a/drivers/i2c/busses/i2c-tegra.c
+++ b/drivers/i2c/busses/i2c-tegra.c
@@ -1608,14 +1608,18 @@ static int tegra_i2c_probe(struct platform_device *pdev)
}
pm_runtime_enable(&pdev->dev);
- if (!pm_runtime_enabled(&pdev->dev))
+ if (!pm_runtime_enabled(&pdev->dev)) {
ret = tegra_i2c_runtime_resume(&pdev->dev);
- else
+ if (ret < 0) {
+ dev_err(&pdev->dev, "runtime resume failed\n");
+ goto unprepare_div_clk;
+ }
+ } else {
ret = pm_runtime_get_sync(i2c_dev->dev);
-
- if (ret < 0) {
- dev_err(&pdev->dev, "runtime resume failed\n");
- goto unprepare_div_clk;
+ if (ret < 0) {
+ dev_err(&pdev->dev, "runtime resume failed\n");
+ goto disable_rpm;
+ }
}
if (i2c_dev->is_multimaster_mode) {
@@ -1623,7 +1627,7 @@ static int tegra_i2c_probe(struct platform_device *pdev)
if (ret < 0) {
dev_err(i2c_dev->dev, "div_clk enable failed %d\n",
ret);
- goto disable_rpm;
+ goto put_rpm;
}
}
@@ -1671,11 +1675,16 @@ static int tegra_i2c_probe(struct platform_device *pdev)
if (i2c_dev->is_multimaster_mode)
clk_disable(i2c_dev->div_clk);
-disable_rpm:
- pm_runtime_disable(&pdev->dev);
- if (!pm_runtime_status_suspended(&pdev->dev))
+put_rpm:
+ if (pm_runtime_enabled(&pdev->dev))
+ pm_runtime_put_sync(&pdev->dev);
+ else
tegra_i2c_runtime_suspend(&pdev->dev);
+disable_rpm:
+ if (pm_runtime_enabled(&pdev->dev))
+ pm_runtime_disable(&pdev->dev);
+
unprepare_div_clk:
clk_unprepare(i2c_dev->div_clk);
@@ -1710,9 +1719,14 @@ static int tegra_i2c_remove(struct platform_device *pdev)
static int __maybe_unused tegra_i2c_suspend(struct device *dev)
{
struct tegra_i2c_dev *i2c_dev = dev_get_drvdata(dev);
+ int err;
i2c_mark_adapter_suspended(&i2c_dev->adapter);
+ err = pm_runtime_force_suspend(dev);
+ if (err < 0)
+ return err;
+
return 0;
}
@@ -1733,6 +1747,10 @@ static int __maybe_unused tegra_i2c_resume(struct device *dev)
if (err)
return err;
+ err = pm_runtime_force_resume(dev);
+ if (err < 0)
+ return err;
+
i2c_mark_adapter_resumed(&i2c_dev->adapter);
return 0;
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 9f8dcd3..35b2097 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -186,10 +186,11 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap)
* If we can set SDA, we will always create a STOP to ensure additional
* pulses will do no harm. This is achieved by letting SDA follow SCL
* half a cycle later. Check the 'incomplete_write_byte' fault injector
- * for details.
+ * for details. Note that we must honour tsu:sto, 4us, but lets use 5us
+ * here for simplicity.
*/
bri->set_scl(adap, scl);
- ndelay(RECOVERY_NDELAY / 2);
+ ndelay(RECOVERY_NDELAY);
if (bri->set_sda)
bri->set_sda(adap, scl);
ndelay(RECOVERY_NDELAY / 2);
@@ -211,7 +212,13 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap)
scl = !scl;
bri->set_scl(adap, scl);
/* Creating STOP again, see above */
- ndelay(RECOVERY_NDELAY / 2);
+ if (scl) {
+ /* Honour minimum tsu:sto */
+ ndelay(RECOVERY_NDELAY);
+ } else {
+ /* Honour minimum tf and thd:dat */
+ ndelay(RECOVERY_NDELAY / 2);
+ }
if (bri->set_sda)
bri->set_sda(adap, scl);
ndelay(RECOVERY_NDELAY / 2);
diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c
index 3f03abf..306bf15 100644
--- a/drivers/iio/adc/ad7124.c
+++ b/drivers/iio/adc/ad7124.c
@@ -494,13 +494,11 @@ static int ad7124_of_parse_channel_config(struct iio_dev *indio_dev,
st->channel_config[channel].buf_negative =
of_property_read_bool(child, "adi,buffered-negative");
- *chan = ad7124_channel_template;
- chan->address = channel;
- chan->scan_index = channel;
- chan->channel = ain[0];
- chan->channel2 = ain[1];
-
- chan++;
+ chan[channel] = ad7124_channel_template;
+ chan[channel].address = channel;
+ chan[channel].scan_index = channel;
+ chan[channel].channel = ain[0];
+ chan[channel].channel2 = ain[1];
}
return 0;
diff --git a/drivers/iio/chemical/Kconfig b/drivers/iio/chemical/Kconfig
index fa45860..0b91de4 100644
--- a/drivers/iio/chemical/Kconfig
+++ b/drivers/iio/chemical/Kconfig
@@ -65,6 +65,7 @@
config PMS7003
tristate "Plantower PMS7003 particulate matter sensor"
depends on SERIAL_DEV_BUS
+ select IIO_BUFFER
select IIO_TRIGGERED_BUFFER
help
Say Y here to build support for the Plantower PMS7003 particulate
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
index a7d40c0..b921dd9 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
@@ -1301,7 +1301,8 @@ static int st_lsm6dsx_check_whoami(struct st_lsm6dsx_hw *hw, int id,
for (i = 0; i < ARRAY_SIZE(st_lsm6dsx_sensor_settings); i++) {
for (j = 0; j < ST_LSM6DSX_MAX_ID; j++) {
- if (id == st_lsm6dsx_sensor_settings[i].id[j].hw_id)
+ if (st_lsm6dsx_sensor_settings[i].id[j].name &&
+ id == st_lsm6dsx_sensor_settings[i].id[j].hw_id)
break;
}
if (j < ST_LSM6DSX_MAX_ID)
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index c193d64..112225c 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -566,7 +566,7 @@ static int iio_compute_scan_bytes(struct iio_dev *indio_dev,
const unsigned long *mask, bool timestamp)
{
unsigned bytes = 0;
- int length, i;
+ int length, i, largest = 0;
/* How much space will the demuxed element take? */
for_each_set_bit(i, mask,
@@ -574,13 +574,17 @@ static int iio_compute_scan_bytes(struct iio_dev *indio_dev,
length = iio_storage_bytes_for_si(indio_dev, i);
bytes = ALIGN(bytes, length);
bytes += length;
+ largest = max(largest, length);
}
if (timestamp) {
length = iio_storage_bytes_for_timestamp(indio_dev);
bytes = ALIGN(bytes, length);
bytes += length;
+ largest = max(largest, length);
}
+
+ bytes = ALIGN(bytes, largest);
return bytes;
}
diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c
index 16dacea..b0e241a 100644
--- a/drivers/iio/light/vcnl4000.c
+++ b/drivers/iio/light/vcnl4000.c
@@ -163,7 +163,6 @@ static int vcnl4200_init(struct vcnl4000_data *data)
if (ret < 0)
return ret;
- data->al_scale = 24000;
data->vcnl4200_al.reg = VCNL4200_AL_DATA;
data->vcnl4200_ps.reg = VCNL4200_PS_DATA;
switch (id) {
@@ -172,11 +171,13 @@ static int vcnl4200_init(struct vcnl4000_data *data)
/* show 54ms in total. */
data->vcnl4200_al.sampling_rate = ktime_set(0, 54000 * 1000);
data->vcnl4200_ps.sampling_rate = ktime_set(0, 4200 * 1000);
+ data->al_scale = 24000;
break;
case VCNL4040_PROD_ID:
/* Integration time is 80ms, add 10ms. */
data->vcnl4200_al.sampling_rate = ktime_set(0, 100000 * 1000);
data->vcnl4200_ps.sampling_rate = ktime_set(0, 100000 * 1000);
+ data->al_scale = 120000;
break;
}
data->vcnl4200_al.last_measurement = ktime_set(0, 0);
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 7a3b995..146f98f 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -181,15 +181,14 @@ EXPORT_SYMBOL(ib_umem_find_best_pgsz);
/**
* ib_umem_get - Pin and DMA map userspace memory.
*
- * @udata: userspace context to pin memory for
+ * @device: IB device to connect UMEM
* @addr: userspace virtual address to start at
* @size: length of region to pin
* @access: IB_ACCESS_xxx flags for memory being pinned
*/
-struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
+struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
size_t size, int access)
{
- struct ib_ucontext *context;
struct ib_umem *umem;
struct page **page_list;
unsigned long lock_limit;
@@ -201,14 +200,6 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
struct scatterlist *sg;
unsigned int gup_flags = FOLL_WRITE;
- if (!udata)
- return ERR_PTR(-EIO);
-
- context = container_of(udata, struct uverbs_attr_bundle, driver_udata)
- ->context;
- if (!context)
- return ERR_PTR(-EIO);
-
/*
* If the combination of the addr and size requested for this memory
* region causes an integer overflow, return error.
@@ -226,7 +217,7 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
umem = kzalloc(sizeof(*umem), GFP_KERNEL);
if (!umem)
return ERR_PTR(-ENOMEM);
- umem->ibdev = context->device;
+ umem->ibdev = device;
umem->length = size;
umem->address = addr;
umem->writable = ib_access_writable(access);
@@ -281,7 +272,7 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
npages -= ret;
sg = ib_umem_add_sg_table(sg, page_list, ret,
- dma_get_max_seg_size(context->device->dma_device),
+ dma_get_max_seg_size(device->dma_device),
&umem->sg_nents);
up_read(&mm->mmap_sem);
@@ -289,10 +280,10 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
sg_mark_end(sg);
- umem->nmap = ib_dma_map_sg(context->device,
- umem->sg_head.sgl,
- umem->sg_nents,
- DMA_BIDIRECTIONAL);
+ umem->nmap = ib_dma_map_sg(device,
+ umem->sg_head.sgl,
+ umem->sg_nents,
+ DMA_BIDIRECTIONAL);
if (!umem->nmap) {
ret = -ENOMEM;
@@ -303,7 +294,7 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
goto out;
umem_release:
- __ib_umem_release(context->device, umem, 0);
+ __ib_umem_release(device, umem, 0);
vma:
atomic64_sub(ib_umem_num_pages(umem), &mm->pinned_vm);
out:
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index e42d44e..dac3fd2 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -110,15 +110,12 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
* They exist only to hold the per_mm reference to help the driver create
* children umems.
*
- * @udata: udata from the syscall being used to create the umem
+ * @device: IB device to create UMEM
* @access: ib_reg_mr access flags
*/
-struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_udata *udata,
+struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_device *device,
int access)
{
- struct ib_ucontext *context =
- container_of(udata, struct uverbs_attr_bundle, driver_udata)
- ->context;
struct ib_umem *umem;
struct ib_umem_odp *umem_odp;
int ret;
@@ -126,14 +123,11 @@ struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_udata *udata,
if (access & IB_ACCESS_HUGETLB)
return ERR_PTR(-EINVAL);
- if (!context)
- return ERR_PTR(-EIO);
-
umem_odp = kzalloc(sizeof(*umem_odp), GFP_KERNEL);
if (!umem_odp)
return ERR_PTR(-ENOMEM);
umem = &umem_odp->umem;
- umem->ibdev = context->device;
+ umem->ibdev = device;
umem->writable = ib_access_writable(access);
umem->owning_mm = current->mm;
umem_odp->is_implicit_odp = 1;
@@ -201,7 +195,7 @@ EXPORT_SYMBOL(ib_umem_odp_alloc_child);
/**
* ib_umem_odp_get - Create a umem_odp for a userspace va
*
- * @udata: userspace context to pin memory for
+ * @device: IB device struct to get UMEM
* @addr: userspace virtual address to start at
* @size: length of region to pin
* @access: IB_ACCESS_xxx flags for memory being pinned
@@ -210,23 +204,14 @@ EXPORT_SYMBOL(ib_umem_odp_alloc_child);
* pinning, instead, stores the mm for future page fault handling in
* conjunction with MMU notifiers.
*/
-struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata, unsigned long addr,
- size_t size, int access,
+struct ib_umem_odp *ib_umem_odp_get(struct ib_device *device,
+ unsigned long addr, size_t size, int access,
const struct mmu_interval_notifier_ops *ops)
{
struct ib_umem_odp *umem_odp;
- struct ib_ucontext *context;
struct mm_struct *mm;
int ret;
- if (!udata)
- return ERR_PTR(-EIO);
-
- context = container_of(udata, struct uverbs_attr_bundle, driver_udata)
- ->context;
- if (!context)
- return ERR_PTR(-EIO);
-
if (WARN_ON_ONCE(!(access & IB_ACCESS_ON_DEMAND)))
return ERR_PTR(-EINVAL);
@@ -234,7 +219,7 @@ struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata, unsigned long addr,
if (!umem_odp)
return ERR_PTR(-ENOMEM);
- umem_odp->umem.ibdev = context->device;
+ umem_odp->umem.ibdev = device;
umem_odp->umem.length = size;
umem_odp->umem.address = addr;
umem_odp->umem.writable = ib_access_writable(access);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index dd765e1..d33bdc9 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1990,6 +1990,47 @@ EXPORT_SYMBOL(ib_resize_cq);
/* Memory regions */
+struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
+ u64 virt_addr, int access_flags)
+{
+ struct ib_mr *mr;
+
+ if (access_flags & IB_ACCESS_ON_DEMAND) {
+ if (!(pd->device->attrs.device_cap_flags &
+ IB_DEVICE_ON_DEMAND_PAGING)) {
+ pr_debug("ODP support not available\n");
+ return ERR_PTR(-EINVAL);
+ }
+ }
+
+ mr = pd->device->ops.reg_user_mr(pd, start, length, virt_addr,
+ access_flags, NULL);
+
+ if (IS_ERR(mr))
+ return mr;
+
+ mr->device = pd->device;
+ mr->pd = pd;
+ mr->dm = NULL;
+ atomic_inc(&pd->usecnt);
+ mr->res.type = RDMA_RESTRACK_MR;
+ rdma_restrack_kadd(&mr->res);
+
+ return mr;
+}
+EXPORT_SYMBOL(ib_reg_user_mr);
+
+int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
+ u32 flags, struct ib_sge *sg_list, u32 num_sge)
+{
+ if (!pd->device->ops.advise_mr)
+ return -EOPNOTSUPP;
+
+ return pd->device->ops.advise_mr(pd, advice, flags, sg_list, num_sge,
+ NULL);
+}
+EXPORT_SYMBOL(ib_advise_mr);
+
int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata)
{
struct ib_pd *pd = mr->pd;
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 9b6ca15..52b6a4d8 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -837,7 +837,8 @@ static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd,
bytes += (qplib_qp->sq.max_wqe * psn_sz);
}
bytes = PAGE_ALIGN(bytes);
- umem = ib_umem_get(udata, ureq.qpsva, bytes, IB_ACCESS_LOCAL_WRITE);
+ umem = ib_umem_get(&rdev->ibdev, ureq.qpsva, bytes,
+ IB_ACCESS_LOCAL_WRITE);
if (IS_ERR(umem))
return PTR_ERR(umem);
@@ -850,7 +851,7 @@ static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd,
if (!qp->qplib_qp.srq) {
bytes = (qplib_qp->rq.max_wqe * BNXT_QPLIB_MAX_RQE_ENTRY_SIZE);
bytes = PAGE_ALIGN(bytes);
- umem = ib_umem_get(udata, ureq.qprva, bytes,
+ umem = ib_umem_get(&rdev->ibdev, ureq.qprva, bytes,
IB_ACCESS_LOCAL_WRITE);
if (IS_ERR(umem))
goto rqfail;
@@ -1304,7 +1305,8 @@ static int bnxt_re_init_user_srq(struct bnxt_re_dev *rdev,
bytes = (qplib_srq->max_wqe * BNXT_QPLIB_MAX_RQE_ENTRY_SIZE);
bytes = PAGE_ALIGN(bytes);
- umem = ib_umem_get(udata, ureq.srqva, bytes, IB_ACCESS_LOCAL_WRITE);
+ umem = ib_umem_get(&rdev->ibdev, ureq.srqva, bytes,
+ IB_ACCESS_LOCAL_WRITE);
if (IS_ERR(umem))
return PTR_ERR(umem);
@@ -2545,7 +2547,7 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
goto fail;
}
- cq->umem = ib_umem_get(udata, req.cq_va,
+ cq->umem = ib_umem_get(&rdev->ibdev, req.cq_va,
entries * sizeof(struct cq_base),
IB_ACCESS_LOCAL_WRITE);
if (IS_ERR(cq->umem)) {
@@ -3305,8 +3307,10 @@ int bnxt_re_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata)
int rc;
rc = bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
- if (rc)
+ if (rc) {
dev_err(rdev_to_dev(rdev), "Dereg MR failed: %#x\n", rc);
+ return rc;
+ }
if (mr->pages) {
rc = bnxt_qplib_free_fast_reg_page_list(&rdev->qplib_res,
@@ -3512,7 +3516,7 @@ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length,
/* The fixed portion of the rkey is the same as the lkey */
mr->ib_mr.rkey = mr->qplib_mr.rkey;
- umem = ib_umem_get(udata, start, length, mr_access_flags);
+ umem = ib_umem_get(&rdev->ibdev, start, length, mr_access_flags);
if (IS_ERR(umem)) {
dev_err(rdev_to_dev(rdev), "Failed to get umem");
rc = -EFAULT;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 958c1ff..4d07d22 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -2283,13 +2283,13 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
/* Add qp to flush list of the CQ */
bnxt_qplib_add_flush_qp(qp);
} else {
+ /* Before we complete, do WA 9060 */
+ if (do_wa9060(qp, cq, cq_cons, sw_sq_cons,
+ cqe_sq_cons)) {
+ *lib_qp = qp;
+ goto out;
+ }
if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) {
- /* Before we complete, do WA 9060 */
- if (do_wa9060(qp, cq, cq_cons, sw_sq_cons,
- cqe_sq_cons)) {
- *lib_qp = qp;
- goto out;
- }
cqe->status = CQ_REQ_STATUS_OK;
cqe++;
(*budget)--;
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index fe3a7e8..962dc97 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -543,7 +543,7 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
mhp->rhp = rhp;
- mhp->umem = ib_umem_get(udata, start, length, acc);
+ mhp->umem = ib_umem_get(pd->device, start, length, acc);
if (IS_ERR(mhp->umem))
goto err_free_skb;
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 50c2257..4822f5f 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -1358,7 +1358,7 @@ struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length,
int inline_size;
int err;
- if (udata->inlen &&
+ if (udata && udata->inlen &&
!ib_is_udata_cleared(udata, 0, sizeof(udata->inlen))) {
ibdev_dbg(&dev->ibdev,
"Incompatible ABI params, udata not cleared\n");
@@ -1384,7 +1384,7 @@ struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length,
goto err_out;
}
- mr->umem = ib_umem_get(udata, start, length, access_flags);
+ mr->umem = ib_umem_get(ibpd->device, start, length, access_flags);
if (IS_ERR(mr->umem)) {
err = PTR_ERR(mr->umem);
ibdev_dbg(&dev->ibdev,
diff --git a/drivers/infiniband/hw/hfi1/iowait.c b/drivers/infiniband/hw/hfi1/iowait.c
index adb4a1b..5836fe7 100644
--- a/drivers/infiniband/hw/hfi1/iowait.c
+++ b/drivers/infiniband/hw/hfi1/iowait.c
@@ -81,7 +81,9 @@ void iowait_init(struct iowait *wait, u32 tx_limit,
void iowait_cancel_work(struct iowait *w)
{
cancel_work_sync(&iowait_get_ib_work(w)->iowork);
- cancel_work_sync(&iowait_get_tid_work(w)->iowork);
+ /* Make sure that the iowork for TID RDMA is used */
+ if (iowait_get_tid_work(w)->iowork.func)
+ cancel_work_sync(&iowait_get_tid_work(w)->iowork);
}
/**
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index e53f542..8a2e0d9 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -4633,6 +4633,15 @@ void hfi1_rc_rcv_tid_rdma_ack(struct hfi1_packet *packet)
*/
fpsn = full_flow_psn(flow, flow->flow_state.spsn);
req->r_ack_psn = psn;
+ /*
+ * If resync_psn points to the last flow PSN for a
+ * segment and the new segment (likely from a new
+ * request) starts with a new generation number, we
+ * need to adjust resync_psn accordingly.
+ */
+ if (flow->flow_state.generation !=
+ (resync_psn >> HFI1_KDETH_BTH_SEQ_SHIFT))
+ resync_psn = mask_psn(fpsn - 1);
flow->resync_npkts +=
delta_psn(mask_psn(resync_psn + 1), fpsn);
/*
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index af1d882..a2d1e53 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -163,7 +163,7 @@ static int get_cq_umem(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
u32 npages;
int ret;
- *umem = ib_umem_get(udata, ucmd.buf_addr, buf->size,
+ *umem = ib_umem_get(&hr_dev->ib_dev, ucmd.buf_addr, buf->size,
IB_ACCESS_LOCAL_WRITE);
if (IS_ERR(*umem))
return PTR_ERR(*umem);
diff --git a/drivers/infiniband/hw/hns/hns_roce_db.c b/drivers/infiniband/hw/hns/hns_roce_db.c
index 10af695..bff6abd 100644
--- a/drivers/infiniband/hw/hns/hns_roce_db.c
+++ b/drivers/infiniband/hw/hns/hns_roce_db.c
@@ -31,7 +31,8 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context,
refcount_set(&page->refcount, 1);
page->user_virt = page_addr;
- page->umem = ib_umem_get(udata, page_addr, PAGE_SIZE, 0);
+ page->umem = ib_umem_get(context->ibucontext.device, page_addr,
+ PAGE_SIZE, 0);
if (IS_ERR(page->umem)) {
ret = PTR_ERR(page->umem);
kfree(page);
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index 9ad1917..3ff6105 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -1145,7 +1145,7 @@ struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
if (!mr)
return ERR_PTR(-ENOMEM);
- mr->umem = ib_umem_get(udata, start, length, access_flags);
+ mr->umem = ib_umem_get(pd->device, start, length, access_flags);
if (IS_ERR(mr->umem)) {
ret = PTR_ERR(mr->umem);
goto err_free;
@@ -1230,7 +1230,7 @@ static int rereg_mr_trans(struct ib_mr *ibmr, int flags,
}
ib_umem_release(mr->umem);
- mr->umem = ib_umem_get(udata, start, length, mr_access_flags);
+ mr->umem = ib_umem_get(ibmr->device, start, length, mr_access_flags);
if (IS_ERR(mr->umem)) {
ret = PTR_ERR(mr->umem);
mr->umem = NULL;
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index a6565b6..eb2ee6a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -744,7 +744,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
goto err_alloc_rq_inline_buf;
}
- hr_qp->umem = ib_umem_get(udata, ucmd.buf_addr,
+ hr_qp->umem = ib_umem_get(ib_pd->device, ucmd.buf_addr,
hr_qp->buff_size, 0);
if (IS_ERR(hr_qp->umem)) {
dev_err(dev, "ib_umem_get error for create qp\n");
diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c
index 7113ebf..c6d5f06 100644
--- a/drivers/infiniband/hw/hns/hns_roce_srq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_srq.c
@@ -186,7 +186,8 @@ static int create_user_srq(struct hns_roce_srq *srq, struct ib_udata *udata,
if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)))
return -EFAULT;
- srq->umem = ib_umem_get(udata, ucmd.buf_addr, srq_buf_size, 0);
+ srq->umem =
+ ib_umem_get(srq->ibsrq.device, ucmd.buf_addr, srq_buf_size, 0);
if (IS_ERR(srq->umem))
return PTR_ERR(srq->umem);
@@ -205,7 +206,7 @@ static int create_user_srq(struct hns_roce_srq *srq, struct ib_udata *udata,
goto err_user_srq_mtt;
/* config index queue BA */
- srq->idx_que.umem = ib_umem_get(udata, ucmd.que_addr,
+ srq->idx_que.umem = ib_umem_get(srq->ibsrq.device, ucmd.que_addr,
srq->idx_que.buf_size, 0);
if (IS_ERR(srq->idx_que.umem)) {
dev_err(hr_dev->dev, "ib_umem_get error for index queue\n");
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 8637594..c335de9 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -169,8 +169,7 @@ static void i40iw_dealloc_ucontext(struct ib_ucontext *context)
static int i40iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
{
struct i40iw_ucontext *ucontext;
- u64 db_addr_offset;
- u64 push_offset;
+ u64 db_addr_offset, push_offset, pfn;
ucontext = to_ucontext(context);
if (ucontext->iwdev->sc_dev.is_pf) {
@@ -189,7 +188,6 @@ static int i40iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
if (vma->vm_pgoff == (db_addr_offset >> PAGE_SHIFT)) {
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- vma->vm_private_data = ucontext;
} else {
if ((vma->vm_pgoff - (push_offset >> PAGE_SHIFT)) % 2)
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
@@ -197,12 +195,12 @@ static int i40iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
}
- if (io_remap_pfn_range(vma, vma->vm_start,
- vma->vm_pgoff + (pci_resource_start(ucontext->iwdev->ldev->pcidev, 0) >> PAGE_SHIFT),
- PAGE_SIZE, vma->vm_page_prot))
- return -EAGAIN;
+ pfn = vma->vm_pgoff +
+ (pci_resource_start(ucontext->iwdev->ldev->pcidev, 0) >>
+ PAGE_SHIFT);
- return 0;
+ return rdma_user_mmap_io(context, vma, pfn, PAGE_SIZE,
+ vma->vm_page_prot, NULL);
}
/**
@@ -1758,12 +1756,15 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd,
int ret;
int pg_shift;
+ if (!udata)
+ return ERR_PTR(-EOPNOTSUPP);
+
if (iwdev->closing)
return ERR_PTR(-ENODEV);
if (length > I40IW_MAX_MR_SIZE)
return ERR_PTR(-EINVAL);
- region = ib_umem_get(udata, start, length, acc);
+ region = ib_umem_get(pd->device, start, length, acc);
if (IS_ERR(region))
return (struct ib_mr *)region;
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 306b212..a57033d 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -144,7 +144,7 @@ static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_udata *udata,
int shift;
int n;
- *umem = ib_umem_get(udata, buf_addr, cqe * cqe_size,
+ *umem = ib_umem_get(&dev->ib_dev, buf_addr, cqe * cqe_size,
IB_ACCESS_LOCAL_WRITE);
if (IS_ERR(*umem))
return PTR_ERR(*umem);
diff --git a/drivers/infiniband/hw/mlx4/doorbell.c b/drivers/infiniband/hw/mlx4/doorbell.c
index 714f9df..d41f03cc 100644
--- a/drivers/infiniband/hw/mlx4/doorbell.c
+++ b/drivers/infiniband/hw/mlx4/doorbell.c
@@ -64,7 +64,8 @@ int mlx4_ib_db_map_user(struct ib_udata *udata, unsigned long virt,
page->user_virt = (virt & PAGE_MASK);
page->refcnt = 0;
- page->umem = ib_umem_get(udata, virt & PAGE_MASK, PAGE_SIZE, 0);
+ page->umem = ib_umem_get(context->ibucontext.device, virt & PAGE_MASK,
+ PAGE_SIZE, 0);
if (IS_ERR(page->umem)) {
err = PTR_ERR(page->umem);
kfree(page);
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index dfa17bc..b0121c9 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -367,7 +367,7 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
return block_shift;
}
-static struct ib_umem *mlx4_get_umem_mr(struct ib_udata *udata, u64 start,
+static struct ib_umem *mlx4_get_umem_mr(struct ib_device *device, u64 start,
u64 length, int access_flags)
{
/*
@@ -398,7 +398,7 @@ static struct ib_umem *mlx4_get_umem_mr(struct ib_udata *udata, u64 start,
up_read(¤t->mm->mmap_sem);
}
- return ib_umem_get(udata, start, length, access_flags);
+ return ib_umem_get(device, start, length, access_flags);
}
struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
@@ -415,7 +415,7 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
if (!mr)
return ERR_PTR(-ENOMEM);
- mr->umem = mlx4_get_umem_mr(udata, start, length, access_flags);
+ mr->umem = mlx4_get_umem_mr(pd->device, start, length, access_flags);
if (IS_ERR(mr->umem)) {
err = PTR_ERR(mr->umem);
goto err_free;
@@ -504,7 +504,7 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
mlx4_mr_rereg_mem_cleanup(dev->dev, &mmr->mmr);
ib_umem_release(mmr->umem);
- mmr->umem = mlx4_get_umem_mr(udata, start, length,
+ mmr->umem = mlx4_get_umem_mr(mr->device, start, length,
mr_access_flags);
if (IS_ERR(mmr->umem)) {
err = PTR_ERR(mmr->umem);
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 85f57b7..cb23cdb 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -916,7 +916,7 @@ static int create_rq(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
qp->buf_size = (qp->rq.wqe_cnt << qp->rq.wqe_shift) +
(qp->sq.wqe_cnt << qp->sq.wqe_shift);
- qp->umem = ib_umem_get(udata, wq.buf_addr, qp->buf_size, 0);
+ qp->umem = ib_umem_get(pd->device, wq.buf_addr, qp->buf_size, 0);
if (IS_ERR(qp->umem)) {
err = PTR_ERR(qp->umem);
goto err;
@@ -1110,7 +1110,8 @@ static int create_qp_common(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
if (err)
goto err;
- qp->umem = ib_umem_get(udata, ucmd.buf_addr, qp->buf_size, 0);
+ qp->umem =
+ ib_umem_get(pd->device, ucmd.buf_addr, qp->buf_size, 0);
if (IS_ERR(qp->umem)) {
err = PTR_ERR(qp->umem);
goto err;
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index 8dcf6e3..8f9d503 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -110,7 +110,8 @@ int mlx4_ib_create_srq(struct ib_srq *ib_srq,
if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)))
return -EFAULT;
- srq->umem = ib_umem_get(udata, ucmd.buf_addr, buf_size, 0);
+ srq->umem =
+ ib_umem_get(ib_srq->device, ucmd.buf_addr, buf_size, 0);
if (IS_ERR(srq->umem))
return PTR_ERR(srq->umem);
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index dd8d24e..367a71b 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -708,8 +708,8 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
*cqe_size = ucmd.cqe_size;
cq->buf.umem =
- ib_umem_get(udata, ucmd.buf_addr, entries * ucmd.cqe_size,
- IB_ACCESS_LOCAL_WRITE);
+ ib_umem_get(&dev->ib_dev, ucmd.buf_addr,
+ entries * ucmd.cqe_size, IB_ACCESS_LOCAL_WRITE);
if (IS_ERR(cq->buf.umem)) {
err = PTR_ERR(cq->buf.umem);
return err;
@@ -1108,7 +1108,7 @@ static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
if (ucmd.cqe_size && SIZE_MAX / ucmd.cqe_size <= entries - 1)
return -EINVAL;
- umem = ib_umem_get(udata, ucmd.buf_addr,
+ umem = ib_umem_get(&dev->ib_dev, ucmd.buf_addr,
(size_t)ucmd.cqe_size * entries,
IB_ACCESS_LOCAL_WRITE);
if (IS_ERR(umem)) {
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 9d0a18c..685b8ed 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -2134,7 +2134,7 @@ static int devx_umem_get(struct mlx5_ib_dev *dev, struct ib_ucontext *ucontext,
if (err)
return err;
- obj->umem = ib_umem_get(&attrs->driver_udata, addr, size, access);
+ obj->umem = ib_umem_get(&dev->ib_dev, addr, size, access);
if (IS_ERR(obj->umem))
return PTR_ERR(obj->umem);
diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c
index 12737c5..61475b5 100644
--- a/drivers/infiniband/hw/mlx5/doorbell.c
+++ b/drivers/infiniband/hw/mlx5/doorbell.c
@@ -64,7 +64,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context,
page->user_virt = (virt & PAGE_MASK);
page->refcnt = 0;
- page->umem = ib_umem_get(udata, virt & PAGE_MASK, PAGE_SIZE, 0);
+ page->umem = ib_umem_get(context->ibucontext.device, virt & PAGE_MASK,
+ PAGE_SIZE, 0);
if (IS_ERR(page->umem)) {
err = PTR_ERR(page->umem);
kfree(page);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 997cbfe..904d508 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -815,6 +815,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
struct ib_device_attr *props,
struct ib_udata *uhw)
{
+ size_t uhw_outlen = (uhw) ? uhw->outlen : 0;
struct mlx5_ib_dev *dev = to_mdev(ibdev);
struct mlx5_core_dev *mdev = dev->mdev;
int err = -ENOMEM;
@@ -828,12 +829,12 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
u64 max_tso;
resp_len = sizeof(resp.comp_mask) + sizeof(resp.response_length);
- if (uhw->outlen && uhw->outlen < resp_len)
+ if (uhw_outlen && uhw_outlen < resp_len)
return -EINVAL;
resp.response_length = resp_len;
- if (uhw->inlen && !ib_is_udata_cleared(uhw, 0, uhw->inlen))
+ if (uhw && uhw->inlen && !ib_is_udata_cleared(uhw, 0, uhw->inlen))
return -EINVAL;
memset(props, 0, sizeof(*props));
@@ -897,7 +898,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
props->raw_packet_caps |=
IB_RAW_PACKET_CAP_CVLAN_STRIPPING;
- if (field_avail(typeof(resp), tso_caps, uhw->outlen)) {
+ if (field_avail(typeof(resp), tso_caps, uhw_outlen)) {
max_tso = MLX5_CAP_ETH(mdev, max_lso_cap);
if (max_tso) {
resp.tso_caps.max_tso = 1 << max_tso;
@@ -907,7 +908,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
}
}
- if (field_avail(typeof(resp), rss_caps, uhw->outlen)) {
+ if (field_avail(typeof(resp), rss_caps, uhw_outlen)) {
resp.rss_caps.rx_hash_function =
MLX5_RX_HASH_FUNC_TOEPLITZ;
resp.rss_caps.rx_hash_fields_mask =
@@ -927,9 +928,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
resp.response_length += sizeof(resp.rss_caps);
}
} else {
- if (field_avail(typeof(resp), tso_caps, uhw->outlen))
+ if (field_avail(typeof(resp), tso_caps, uhw_outlen))
resp.response_length += sizeof(resp.tso_caps);
- if (field_avail(typeof(resp), rss_caps, uhw->outlen))
+ if (field_avail(typeof(resp), rss_caps, uhw_outlen))
resp.response_length += sizeof(resp.rss_caps);
}
@@ -1014,6 +1015,23 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
if (dev->odp_caps.general_caps & IB_ODP_SUPPORT)
props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING;
props->odp_caps = dev->odp_caps;
+ if (!uhw) {
+ /* ODP for kernel QPs is not implemented for receive
+ * WQEs and SRQ WQEs
+ */
+ props->odp_caps.per_transport_caps.rc_odp_caps &=
+ ~(IB_ODP_SUPPORT_READ |
+ IB_ODP_SUPPORT_SRQ_RECV);
+ props->odp_caps.per_transport_caps.uc_odp_caps &=
+ ~(IB_ODP_SUPPORT_READ |
+ IB_ODP_SUPPORT_SRQ_RECV);
+ props->odp_caps.per_transport_caps.ud_odp_caps &=
+ ~(IB_ODP_SUPPORT_READ |
+ IB_ODP_SUPPORT_SRQ_RECV);
+ props->odp_caps.per_transport_caps.xrc_odp_caps &=
+ ~(IB_ODP_SUPPORT_READ |
+ IB_ODP_SUPPORT_SRQ_RECV);
+ }
}
if (MLX5_CAP_GEN(mdev, cd))
@@ -1054,7 +1072,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
MLX5_MAX_CQ_PERIOD;
}
- if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
+ if (field_avail(typeof(resp), cqe_comp_caps, uhw_outlen)) {
resp.response_length += sizeof(resp.cqe_comp_caps);
if (MLX5_CAP_GEN(dev->mdev, cqe_compression)) {
@@ -1072,7 +1090,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
}
}
- if (field_avail(typeof(resp), packet_pacing_caps, uhw->outlen) &&
+ if (field_avail(typeof(resp), packet_pacing_caps, uhw_outlen) &&
raw_support) {
if (MLX5_CAP_QOS(mdev, packet_pacing) &&
MLX5_CAP_GEN(mdev, qos)) {
@@ -1091,7 +1109,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
}
if (field_avail(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes,
- uhw->outlen)) {
+ uhw_outlen)) {
if (MLX5_CAP_ETH(mdev, multi_pkt_send_wqe))
resp.mlx5_ib_support_multi_pkt_send_wqes =
MLX5_IB_ALLOW_MPW;
@@ -1104,7 +1122,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
}
- if (field_avail(typeof(resp), flags, uhw->outlen)) {
+ if (field_avail(typeof(resp), flags, uhw_outlen)) {
resp.response_length += sizeof(resp.flags);
if (MLX5_CAP_GEN(mdev, cqe_compression_128))
@@ -1120,8 +1138,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT;
}
- if (field_avail(typeof(resp), sw_parsing_caps,
- uhw->outlen)) {
+ if (field_avail(typeof(resp), sw_parsing_caps, uhw_outlen)) {
resp.response_length += sizeof(resp.sw_parsing_caps);
if (MLX5_CAP_ETH(mdev, swp)) {
resp.sw_parsing_caps.sw_parsing_offloads |=
@@ -1141,7 +1158,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
}
}
- if (field_avail(typeof(resp), striding_rq_caps, uhw->outlen) &&
+ if (field_avail(typeof(resp), striding_rq_caps, uhw_outlen) &&
raw_support) {
resp.response_length += sizeof(resp.striding_rq_caps);
if (MLX5_CAP_GEN(mdev, striding_rq)) {
@@ -1164,8 +1181,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
}
}
- if (field_avail(typeof(resp), tunnel_offloads_caps,
- uhw->outlen)) {
+ if (field_avail(typeof(resp), tunnel_offloads_caps, uhw_outlen)) {
resp.response_length += sizeof(resp.tunnel_offloads_caps);
if (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan))
resp.tunnel_offloads_caps |=
@@ -1186,7 +1202,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
MLX5_IB_TUNNELED_OFFLOADS_MPLS_UDP;
}
- if (uhw->outlen) {
+ if (uhw_outlen) {
err = ib_copy_to_udata(uhw, &resp, resp.response_length);
if (err)
@@ -3276,12 +3292,14 @@ static struct mlx5_ib_flow_prio *_get_prio(struct mlx5_flow_namespace *ns,
int num_entries, int num_groups,
u32 flags)
{
+ struct mlx5_flow_table_attr ft_attr = {};
struct mlx5_flow_table *ft;
- ft = mlx5_create_auto_grouped_flow_table(ns, priority,
- num_entries,
- num_groups,
- 0, flags);
+ ft_attr.prio = priority;
+ ft_attr.max_fte = num_entries;
+ ft_attr.flags = flags;
+ ft_attr.autogroup.max_num_groups = num_groups;
+ ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
if (IS_ERR(ft))
return ERR_CAST(ft);
@@ -4771,7 +4789,6 @@ static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port)
struct ib_device_attr *dprops = NULL;
struct ib_port_attr *pprops = NULL;
int err = -ENOMEM;
- struct ib_udata uhw = {.inlen = 0, .outlen = 0};
pprops = kzalloc(sizeof(*pprops), GFP_KERNEL);
if (!pprops)
@@ -4781,7 +4798,7 @@ static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port)
if (!dprops)
goto out;
- err = mlx5_ib_query_device(&dev->ib_dev, dprops, &uhw);
+ err = mlx5_ib_query_device(&dev->ib_dev, dprops, NULL);
if (err) {
mlx5_ib_warn(dev, "query_device failed %d\n", err);
goto out;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index b06f32f..77d495b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1153,12 +1153,12 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
const struct ib_send_wr **bad_wr);
int mlx5_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
const struct ib_recv_wr **bad_wr);
-int mlx5_ib_read_user_wqe_sq(struct mlx5_ib_qp *qp, int wqe_index, void *buffer,
- int buflen, size_t *bc);
-int mlx5_ib_read_user_wqe_rq(struct mlx5_ib_qp *qp, int wqe_index, void *buffer,
- int buflen, size_t *bc);
-int mlx5_ib_read_user_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index,
- void *buffer, int buflen, size_t *bc);
+int mlx5_ib_read_wqe_sq(struct mlx5_ib_qp *qp, int wqe_index, void *buffer,
+ size_t buflen, size_t *bc);
+int mlx5_ib_read_wqe_rq(struct mlx5_ib_qp *qp, int wqe_index, void *buffer,
+ size_t buflen, size_t *bc);
+int mlx5_ib_read_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index, void *buffer,
+ size_t buflen, size_t *bc);
int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
struct ib_udata *udata);
void mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index ea8bfc3..44a0ee6 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -737,10 +737,9 @@ static int mr_cache_max_order(struct mlx5_ib_dev *dev)
return MLX5_MAX_UMR_SHIFT;
}
-static int mr_umem_get(struct mlx5_ib_dev *dev, struct ib_udata *udata,
- u64 start, u64 length, int access_flags,
- struct ib_umem **umem, int *npages, int *page_shift,
- int *ncont, int *order)
+static int mr_umem_get(struct mlx5_ib_dev *dev, u64 start, u64 length,
+ int access_flags, struct ib_umem **umem, int *npages,
+ int *page_shift, int *ncont, int *order)
{
struct ib_umem *u;
@@ -749,7 +748,7 @@ static int mr_umem_get(struct mlx5_ib_dev *dev, struct ib_udata *udata,
if (access_flags & IB_ACCESS_ON_DEMAND) {
struct ib_umem_odp *odp;
- odp = ib_umem_odp_get(udata, start, length, access_flags,
+ odp = ib_umem_odp_get(&dev->ib_dev, start, length, access_flags,
&mlx5_mn_ops);
if (IS_ERR(odp)) {
mlx5_ib_dbg(dev, "umem get failed (%ld)\n",
@@ -765,7 +764,7 @@ static int mr_umem_get(struct mlx5_ib_dev *dev, struct ib_udata *udata,
if (order)
*order = ilog2(roundup_pow_of_two(*ncont));
} else {
- u = ib_umem_get(udata, start, length, access_flags);
+ u = ib_umem_get(&dev->ib_dev, start, length, access_flags);
if (IS_ERR(u)) {
mlx5_ib_dbg(dev, "umem get failed (%ld)\n", PTR_ERR(u));
return PTR_ERR(u);
@@ -1247,6 +1246,8 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && !start &&
length == U64_MAX) {
+ if (virt_addr != start)
+ return ERR_PTR(-EINVAL);
if (!(access_flags & IB_ACCESS_ON_DEMAND) ||
!(dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT))
return ERR_PTR(-EINVAL);
@@ -1257,7 +1258,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
return &mr->ibmr;
}
- err = mr_umem_get(dev, udata, start, length, access_flags, &umem,
+ err = mr_umem_get(dev, start, length, access_flags, &umem,
&npages, &page_shift, &ncont, &order);
if (err < 0)
@@ -1424,9 +1425,8 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
flags |= IB_MR_REREG_TRANS;
ib_umem_release(mr->umem);
mr->umem = NULL;
- err = mr_umem_get(dev, udata, addr, len, access_flags,
- &mr->umem, &npages, &page_shift, &ncont,
- &order);
+ err = mr_umem_get(dev, addr, len, access_flags, &mr->umem,
+ &npages, &page_shift, &ncont, &order);
if (err)
goto err;
}
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index f924250..0afb004 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -497,7 +497,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd,
struct mlx5_ib_mr *imr;
int err;
- umem_odp = ib_umem_odp_alloc_implicit(udata, access_flags);
+ umem_odp = ib_umem_odp_alloc_implicit(&dev->ib_dev, access_flags);
if (IS_ERR(umem_odp))
return ERR_CAST(umem_odp);
@@ -624,11 +624,10 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE;
unsigned long current_seq;
u64 access_mask;
- u64 start_idx, page_mask;
+ u64 start_idx;
page_shift = odp->page_shift;
- page_mask = ~(BIT(page_shift) - 1);
- start_idx = (user_va - (mr->mmkey.iova & page_mask)) >> page_shift;
+ start_idx = (user_va - ib_umem_start(odp)) >> page_shift;
access_mask = ODP_READ_ALLOWED_BIT;
if (odp->umem.writable && !downgrade)
@@ -767,11 +766,19 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt,
{
struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem);
+ if (unlikely(io_virt < mr->mmkey.iova))
+ return -EFAULT;
+
if (!odp->is_implicit_odp) {
- if (unlikely(io_virt < ib_umem_start(odp) ||
- ib_umem_end(odp) - io_virt < bcnt))
+ u64 user_va;
+
+ if (check_add_overflow(io_virt - mr->mmkey.iova,
+ (u64)odp->umem.address, &user_va))
return -EFAULT;
- return pagefault_real_mr(mr, odp, io_virt, bcnt, bytes_mapped,
+ if (unlikely(user_va >= ib_umem_end(odp) ||
+ ib_umem_end(odp) - user_va < bcnt))
+ return -EFAULT;
+ return pagefault_real_mr(mr, odp, user_va, bcnt, bytes_mapped,
flags);
}
return pagefault_implicit_mr(mr, odp, io_virt, bcnt, bytes_mapped,
@@ -1237,15 +1244,15 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_dev *dev,
wqe = wqe_start;
qp = (res->res == MLX5_RES_QP) ? res_to_qp(res) : NULL;
if (qp && sq) {
- ret = mlx5_ib_read_user_wqe_sq(qp, wqe_index, wqe, PAGE_SIZE,
- &bytes_copied);
+ ret = mlx5_ib_read_wqe_sq(qp, wqe_index, wqe, PAGE_SIZE,
+ &bytes_copied);
if (ret)
goto read_user;
ret = mlx5_ib_mr_initiator_pfault_handler(
dev, pfault, qp, &wqe, &wqe_end, bytes_copied);
} else if (qp && !sq) {
- ret = mlx5_ib_read_user_wqe_rq(qp, wqe_index, wqe, PAGE_SIZE,
- &bytes_copied);
+ ret = mlx5_ib_read_wqe_rq(qp, wqe_index, wqe, PAGE_SIZE,
+ &bytes_copied);
if (ret)
goto read_user;
ret = mlx5_ib_mr_responder_pfault_handler_rq(
@@ -1253,8 +1260,8 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_dev *dev,
} else if (!qp) {
struct mlx5_ib_srq *srq = res_to_srq(res);
- ret = mlx5_ib_read_user_wqe_srq(srq, wqe_index, wqe, PAGE_SIZE,
- &bytes_copied);
+ ret = mlx5_ib_read_wqe_srq(srq, wqe_index, wqe, PAGE_SIZE,
+ &bytes_copied);
if (ret)
goto read_user;
ret = mlx5_ib_mr_responder_pfault_handler_srq(
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7e51870..ae7cbd9 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -129,14 +129,10 @@ static int is_sqp(enum ib_qp_type qp_type)
*
* Return: zero on success, or an error code.
*/
-static int mlx5_ib_read_user_wqe_common(struct ib_umem *umem,
- void *buffer,
- u32 buflen,
- int wqe_index,
- int wq_offset,
- int wq_wqe_cnt,
- int wq_wqe_shift,
- int bcnt,
+static int mlx5_ib_read_user_wqe_common(struct ib_umem *umem, void *buffer,
+ size_t buflen, int wqe_index,
+ int wq_offset, int wq_wqe_cnt,
+ int wq_wqe_shift, int bcnt,
size_t *bytes_copied)
{
size_t offset = wq_offset + ((wqe_index % wq_wqe_cnt) << wq_wqe_shift);
@@ -160,11 +156,43 @@ static int mlx5_ib_read_user_wqe_common(struct ib_umem *umem,
return 0;
}
-int mlx5_ib_read_user_wqe_sq(struct mlx5_ib_qp *qp,
- int wqe_index,
- void *buffer,
- int buflen,
- size_t *bc)
+static int mlx5_ib_read_kernel_wqe_sq(struct mlx5_ib_qp *qp, int wqe_index,
+ void *buffer, size_t buflen, size_t *bc)
+{
+ struct mlx5_wqe_ctrl_seg *ctrl;
+ size_t bytes_copied = 0;
+ size_t wqe_length;
+ void *p;
+ int ds;
+
+ wqe_index = wqe_index & qp->sq.fbc.sz_m1;
+
+ /* read the control segment first */
+ p = mlx5_frag_buf_get_wqe(&qp->sq.fbc, wqe_index);
+ ctrl = p;
+ ds = be32_to_cpu(ctrl->qpn_ds) & MLX5_WQE_CTRL_DS_MASK;
+ wqe_length = ds * MLX5_WQE_DS_UNITS;
+
+ /* read rest of WQE if it spreads over more than one stride */
+ while (bytes_copied < wqe_length) {
+ size_t copy_length =
+ min_t(size_t, buflen - bytes_copied, MLX5_SEND_WQE_BB);
+
+ if (!copy_length)
+ break;
+
+ memcpy(buffer + bytes_copied, p, copy_length);
+ bytes_copied += copy_length;
+
+ wqe_index = (wqe_index + 1) & qp->sq.fbc.sz_m1;
+ p = mlx5_frag_buf_get_wqe(&qp->sq.fbc, wqe_index);
+ }
+ *bc = bytes_copied;
+ return 0;
+}
+
+static int mlx5_ib_read_user_wqe_sq(struct mlx5_ib_qp *qp, int wqe_index,
+ void *buffer, size_t buflen, size_t *bc)
{
struct mlx5_ib_qp_base *base = &qp->trans_qp.base;
struct ib_umem *umem = base->ubuffer.umem;
@@ -176,18 +204,10 @@ int mlx5_ib_read_user_wqe_sq(struct mlx5_ib_qp *qp,
int ret;
int ds;
- if (buflen < sizeof(*ctrl))
- return -EINVAL;
-
/* at first read as much as possible */
- ret = mlx5_ib_read_user_wqe_common(umem,
- buffer,
- buflen,
- wqe_index,
- wq->offset,
- wq->wqe_cnt,
- wq->wqe_shift,
- buflen,
+ ret = mlx5_ib_read_user_wqe_common(umem, buffer, buflen, wqe_index,
+ wq->offset, wq->wqe_cnt,
+ wq->wqe_shift, buflen,
&bytes_copied);
if (ret)
return ret;
@@ -210,13 +230,9 @@ int mlx5_ib_read_user_wqe_sq(struct mlx5_ib_qp *qp,
* so read the remaining bytes starting
* from wqe_index 0
*/
- ret = mlx5_ib_read_user_wqe_common(umem,
- buffer + bytes_copied,
- buflen - bytes_copied,
- 0,
- wq->offset,
- wq->wqe_cnt,
- wq->wqe_shift,
+ ret = mlx5_ib_read_user_wqe_common(umem, buffer + bytes_copied,
+ buflen - bytes_copied, 0, wq->offset,
+ wq->wqe_cnt, wq->wqe_shift,
wqe_length - bytes_copied,
&bytes_copied2);
@@ -226,11 +242,24 @@ int mlx5_ib_read_user_wqe_sq(struct mlx5_ib_qp *qp,
return 0;
}
-int mlx5_ib_read_user_wqe_rq(struct mlx5_ib_qp *qp,
- int wqe_index,
- void *buffer,
- int buflen,
- size_t *bc)
+int mlx5_ib_read_wqe_sq(struct mlx5_ib_qp *qp, int wqe_index, void *buffer,
+ size_t buflen, size_t *bc)
+{
+ struct mlx5_ib_qp_base *base = &qp->trans_qp.base;
+ struct ib_umem *umem = base->ubuffer.umem;
+
+ if (buflen < sizeof(struct mlx5_wqe_ctrl_seg))
+ return -EINVAL;
+
+ if (!umem)
+ return mlx5_ib_read_kernel_wqe_sq(qp, wqe_index, buffer,
+ buflen, bc);
+
+ return mlx5_ib_read_user_wqe_sq(qp, wqe_index, buffer, buflen, bc);
+}
+
+static int mlx5_ib_read_user_wqe_rq(struct mlx5_ib_qp *qp, int wqe_index,
+ void *buffer, size_t buflen, size_t *bc)
{
struct mlx5_ib_qp_base *base = &qp->trans_qp.base;
struct ib_umem *umem = base->ubuffer.umem;
@@ -238,14 +267,9 @@ int mlx5_ib_read_user_wqe_rq(struct mlx5_ib_qp *qp,
size_t bytes_copied;
int ret;
- ret = mlx5_ib_read_user_wqe_common(umem,
- buffer,
- buflen,
- wqe_index,
- wq->offset,
- wq->wqe_cnt,
- wq->wqe_shift,
- buflen,
+ ret = mlx5_ib_read_user_wqe_common(umem, buffer, buflen, wqe_index,
+ wq->offset, wq->wqe_cnt,
+ wq->wqe_shift, buflen,
&bytes_copied);
if (ret)
@@ -254,25 +278,33 @@ int mlx5_ib_read_user_wqe_rq(struct mlx5_ib_qp *qp,
return 0;
}
-int mlx5_ib_read_user_wqe_srq(struct mlx5_ib_srq *srq,
- int wqe_index,
- void *buffer,
- int buflen,
- size_t *bc)
+int mlx5_ib_read_wqe_rq(struct mlx5_ib_qp *qp, int wqe_index, void *buffer,
+ size_t buflen, size_t *bc)
+{
+ struct mlx5_ib_qp_base *base = &qp->trans_qp.base;
+ struct ib_umem *umem = base->ubuffer.umem;
+ struct mlx5_ib_wq *wq = &qp->rq;
+ size_t wqe_size = 1 << wq->wqe_shift;
+
+ if (buflen < wqe_size)
+ return -EINVAL;
+
+ if (!umem)
+ return -EOPNOTSUPP;
+
+ return mlx5_ib_read_user_wqe_rq(qp, wqe_index, buffer, buflen, bc);
+}
+
+static int mlx5_ib_read_user_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index,
+ void *buffer, size_t buflen, size_t *bc)
{
struct ib_umem *umem = srq->umem;
size_t bytes_copied;
int ret;
- ret = mlx5_ib_read_user_wqe_common(umem,
- buffer,
- buflen,
- wqe_index,
- 0,
- srq->msrq.max,
- srq->msrq.wqe_shift,
- buflen,
- &bytes_copied);
+ ret = mlx5_ib_read_user_wqe_common(umem, buffer, buflen, wqe_index, 0,
+ srq->msrq.max, srq->msrq.wqe_shift,
+ buflen, &bytes_copied);
if (ret)
return ret;
@@ -280,6 +312,21 @@ int mlx5_ib_read_user_wqe_srq(struct mlx5_ib_srq *srq,
return 0;
}
+int mlx5_ib_read_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index, void *buffer,
+ size_t buflen, size_t *bc)
+{
+ struct ib_umem *umem = srq->umem;
+ size_t wqe_size = 1 << srq->msrq.wqe_shift;
+
+ if (buflen < wqe_size)
+ return -EINVAL;
+
+ if (!umem)
+ return -EOPNOTSUPP;
+
+ return mlx5_ib_read_user_wqe_srq(srq, wqe_index, buffer, buflen, bc);
+}
+
static void mlx5_ib_qp_event(struct mlx5_core_qp *qp, int type)
{
struct ib_qp *ibqp = &to_mibqp(qp)->ibqp;
@@ -749,7 +796,7 @@ static int mlx5_ib_umem_get(struct mlx5_ib_dev *dev, struct ib_udata *udata,
{
int err;
- *umem = ib_umem_get(udata, addr, size, 0);
+ *umem = ib_umem_get(&dev->ib_dev, addr, size, 0);
if (IS_ERR(*umem)) {
mlx5_ib_dbg(dev, "umem_get failed\n");
return PTR_ERR(*umem);
@@ -806,7 +853,7 @@ static int create_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd,
if (!ucmd->buf_addr)
return -EINVAL;
- rwq->umem = ib_umem_get(udata, ucmd->buf_addr, rwq->buf_size, 0);
+ rwq->umem = ib_umem_get(&dev->ib_dev, ucmd->buf_addr, rwq->buf_size, 0);
if (IS_ERR(rwq->umem)) {
mlx5_ib_dbg(dev, "umem_get failed\n");
err = PTR_ERR(rwq->umem);
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 62939df..b1a8a91 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -80,7 +80,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE);
- srq->umem = ib_umem_get(udata, ucmd.buf_addr, buf_size, 0);
+ srq->umem = ib_umem_get(pd->device, ucmd.buf_addr, buf_size, 0);
if (IS_ERR(srq->umem)) {
mlx5_ib_dbg(dev, "failed umem get, size %d\n", buf_size);
err = PTR_ERR(srq->umem);
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 3300253..ac19d57 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -880,7 +880,7 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
if (!mr)
return ERR_PTR(-ENOMEM);
- mr->umem = ib_umem_get(udata, start, length, acc);
+ mr->umem = ib_umem_get(pd->device, start, length, acc);
if (IS_ERR(mr->umem)) {
err = PTR_ERR(mr->umem);
goto err;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 9bc1ca6..d47ea67 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -869,7 +869,7 @@ struct ib_mr *ocrdma_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
mr = kzalloc(sizeof(*mr), GFP_KERNEL);
if (!mr)
return ERR_PTR(status);
- mr->umem = ib_umem_get(udata, start, len, acc);
+ mr->umem = ib_umem_get(ibpd->device, start, len, acc);
if (IS_ERR(mr->umem)) {
status = -EFAULT;
goto umem_err;
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 4cd2929..920f35e 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -772,7 +772,7 @@ static inline int qedr_init_user_queue(struct ib_udata *udata,
q->buf_addr = buf_addr;
q->buf_len = buf_len;
- q->umem = ib_umem_get(udata, q->buf_addr, q->buf_len, access);
+ q->umem = ib_umem_get(&dev->ibdev, q->buf_addr, q->buf_len, access);
if (IS_ERR(q->umem)) {
DP_ERR(dev, "create user queue: failed ib_umem_get, got %ld\n",
PTR_ERR(q->umem));
@@ -1415,9 +1415,8 @@ static int qedr_init_srq_user_params(struct ib_udata *udata,
if (rc)
return rc;
- srq->prod_umem =
- ib_umem_get(udata, ureq->prod_pair_addr,
- sizeof(struct rdma_srq_producers), access);
+ srq->prod_umem = ib_umem_get(srq->ibsrq.device, ureq->prod_pair_addr,
+ sizeof(struct rdma_srq_producers), access);
if (IS_ERR(srq->prod_umem)) {
qedr_free_pbl(srq->dev, &srq->usrq.pbl_info, srq->usrq.pbl_tbl);
ib_umem_release(srq->usrq.umem);
@@ -2839,7 +2838,7 @@ struct ib_mr *qedr_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
mr->type = QEDR_MR_USER;
- mr->umem = ib_umem_get(udata, start, len, acc);
+ mr->umem = ib_umem_get(ibpd->device, start, len, acc);
if (IS_ERR(mr->umem)) {
rc = -EFAULT;
goto err0;
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
index a26a4fd..4f6cc0d 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
@@ -135,7 +135,7 @@ int pvrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
goto err_cq;
}
- cq->umem = ib_umem_get(udata, ucmd.buf_addr, ucmd.buf_size,
+ cq->umem = ib_umem_get(ibdev, ucmd.buf_addr, ucmd.buf_size,
IB_ACCESS_LOCAL_WRITE);
if (IS_ERR(cq->umem)) {
ret = PTR_ERR(cq->umem);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c
index c61e665..b039f1f 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c
@@ -126,7 +126,7 @@ struct ib_mr *pvrdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
return ERR_PTR(-EINVAL);
}
- umem = ib_umem_get(udata, start, length, access_flags);
+ umem = ib_umem_get(pd->device, start, length, access_flags);
if (IS_ERR(umem)) {
dev_warn(&dev->pdev->dev,
"could not get umem for mem region\n");
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
index f15809c..9de1281 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
@@ -276,8 +276,9 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
if (!is_srq) {
/* set qp->sq.wqe_cnt, shift, buf_size.. */
- qp->rumem = ib_umem_get(udata, ucmd.rbuf_addr,
- ucmd.rbuf_size, 0);
+ qp->rumem =
+ ib_umem_get(pd->device, ucmd.rbuf_addr,
+ ucmd.rbuf_size, 0);
if (IS_ERR(qp->rumem)) {
ret = PTR_ERR(qp->rumem);
goto err_qp;
@@ -288,7 +289,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
qp->srq = to_vsrq(init_attr->srq);
}
- qp->sumem = ib_umem_get(udata, ucmd.sbuf_addr,
+ qp->sumem = ib_umem_get(pd->device, ucmd.sbuf_addr,
ucmd.sbuf_size, 0);
if (IS_ERR(qp->sumem)) {
if (!is_srq)
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
index 98c8be7..d330dec 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
@@ -146,7 +146,7 @@ int pvrdma_create_srq(struct ib_srq *ibsrq, struct ib_srq_init_attr *init_attr,
goto err_srq;
}
- srq->umem = ib_umem_get(udata, ucmd.buf_addr, ucmd.buf_size, 0);
+ srq->umem = ib_umem_get(ibsrq->device, ucmd.buf_addr, ucmd.buf_size, 0);
if (IS_ERR(srq->umem)) {
ret = PTR_ERR(srq->umem);
goto err_srq;
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index b9a76bf..72f6534 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -390,7 +390,7 @@ struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
if (length == 0)
return ERR_PTR(-EINVAL);
- umem = ib_umem_get(udata, start, length, mr_access_flags);
+ umem = ib_umem_get(pd->device, start, length, mr_access_flags);
if (IS_ERR(umem))
return (void *)umem;
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 35a2baf..e83c7b5 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -169,7 +169,7 @@ int rxe_mem_init_user(struct rxe_pd *pd, u64 start,
void *vaddr;
int err;
- umem = ib_umem_get(udata, start, length, access);
+ umem = ib_umem_get(pd->ibpd.device, start, length, access);
if (IS_ERR(umem)) {
pr_warn("err %d from rxe_umem_get\n",
(int)PTR_ERR(umem));
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index d7dd6fc..cb6e3a5 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -224,13 +224,13 @@ static void __pass_event(struct evdev_client *client,
*/
client->tail = (client->head - 2) & (client->bufsize - 1);
- client->buffer[client->tail].input_event_sec =
- event->input_event_sec;
- client->buffer[client->tail].input_event_usec =
- event->input_event_usec;
- client->buffer[client->tail].type = EV_SYN;
- client->buffer[client->tail].code = SYN_DROPPED;
- client->buffer[client->tail].value = 0;
+ client->buffer[client->tail] = (struct input_event) {
+ .input_event_sec = event->input_event_sec,
+ .input_event_usec = event->input_event_usec,
+ .type = EV_SYN,
+ .code = SYN_DROPPED,
+ .value = 0,
+ };
client->packet_head = client->tail;
}
@@ -484,10 +484,7 @@ static int evdev_open(struct inode *inode, struct file *file)
struct evdev_client *client;
int error;
- client = kzalloc(struct_size(client, buffer, bufsize),
- GFP_KERNEL | __GFP_NOWARN);
- if (!client)
- client = vzalloc(struct_size(client, buffer, bufsize));
+ client = kvzalloc(struct_size(client, buffer, bufsize), GFP_KERNEL);
if (!client)
return -ENOMEM;
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 5508627..ee6c323 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -878,16 +878,18 @@ static int input_default_setkeycode(struct input_dev *dev,
}
}
- __clear_bit(*old_keycode, dev->keybit);
- __set_bit(ke->keycode, dev->keybit);
-
- for (i = 0; i < dev->keycodemax; i++) {
- if (input_fetch_keycode(dev, i) == *old_keycode) {
- __set_bit(*old_keycode, dev->keybit);
- break; /* Setting the bit twice is useless, so break */
+ if (*old_keycode <= KEY_MAX) {
+ __clear_bit(*old_keycode, dev->keybit);
+ for (i = 0; i < dev->keycodemax; i++) {
+ if (input_fetch_keycode(dev, i) == *old_keycode) {
+ __set_bit(*old_keycode, dev->keybit);
+ /* Setting the bit twice is useless, so break */
+ break;
+ }
}
}
+ __set_bit(ke->keycode, dev->keybit);
return 0;
}
@@ -943,9 +945,13 @@ int input_set_keycode(struct input_dev *dev,
* Simulate keyup event if keycode is not present
* in the keymap anymore
*/
- if (test_bit(EV_KEY, dev->evbit) &&
- !is_event_supported(old_keycode, dev->keybit, KEY_MAX) &&
- __test_and_clear_bit(old_keycode, dev->key)) {
+ if (old_keycode > KEY_MAX) {
+ dev_warn(dev->dev.parent ?: &dev->dev,
+ "%s: got too big old keycode %#x\n",
+ __func__, old_keycode);
+ } else if (test_bit(EV_KEY, dev->evbit) &&
+ !is_event_supported(old_keycode, dev->keybit, KEY_MAX) &&
+ __test_and_clear_bit(old_keycode, dev->key)) {
struct input_value vals[] = {
{ EV_KEY, old_keycode, 0 },
input_value_sync
diff --git a/drivers/input/keyboard/imx_sc_key.c b/drivers/input/keyboard/imx_sc_key.c
index 5379952..9f809aeb7 100644
--- a/drivers/input/keyboard/imx_sc_key.c
+++ b/drivers/input/keyboard/imx_sc_key.c
@@ -78,7 +78,13 @@ static void imx_sc_check_for_events(struct work_struct *work)
return;
}
- state = (bool)msg.state;
+ /*
+ * The response data from SCU firmware is 4 bytes,
+ * but ONLY the first byte is the key state, other
+ * 3 bytes could be some dirty data, so we should
+ * ONLY take the first byte as key state.
+ */
+ state = (bool)(msg.state & 0xff);
if (state ^ priv->keystate) {
priv->keystate = state;
diff --git a/drivers/input/misc/keyspan_remote.c b/drivers/input/misc/keyspan_remote.c
index 83368f1..4650f4a 100644
--- a/drivers/input/misc/keyspan_remote.c
+++ b/drivers/input/misc/keyspan_remote.c
@@ -336,7 +336,8 @@ static int keyspan_setup(struct usb_device* dev)
int retval = 0;
retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
- 0x11, 0x40, 0x5601, 0x0, NULL, 0, 0);
+ 0x11, 0x40, 0x5601, 0x0, NULL, 0,
+ USB_CTRL_SET_TIMEOUT);
if (retval) {
dev_dbg(&dev->dev, "%s - failed to set bit rate due to error: %d\n",
__func__, retval);
@@ -344,7 +345,8 @@ static int keyspan_setup(struct usb_device* dev)
}
retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
- 0x44, 0x40, 0x0, 0x0, NULL, 0, 0);
+ 0x44, 0x40, 0x0, 0x0, NULL, 0,
+ USB_CTRL_SET_TIMEOUT);
if (retval) {
dev_dbg(&dev->dev, "%s - failed to set resume sensitivity due to error: %d\n",
__func__, retval);
@@ -352,7 +354,8 @@ static int keyspan_setup(struct usb_device* dev)
}
retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
- 0x22, 0x40, 0x0, 0x0, NULL, 0, 0);
+ 0x22, 0x40, 0x0, 0x0, NULL, 0,
+ USB_CTRL_SET_TIMEOUT);
if (retval) {
dev_dbg(&dev->dev, "%s - failed to turn receive on due to error: %d\n",
__func__, retval);
diff --git a/drivers/input/misc/max77650-onkey.c b/drivers/input/misc/max77650-onkey.c
index 4d875f2..ee55f22 100644
--- a/drivers/input/misc/max77650-onkey.c
+++ b/drivers/input/misc/max77650-onkey.c
@@ -108,9 +108,16 @@ static int max77650_onkey_probe(struct platform_device *pdev)
return input_register_device(onkey->input);
}
+static const struct of_device_id max77650_onkey_of_match[] = {
+ { .compatible = "maxim,max77650-onkey" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, max77650_onkey_of_match);
+
static struct platform_driver max77650_onkey_driver = {
.driver = {
.name = "max77650-onkey",
+ .of_match_table = max77650_onkey_of_match,
},
.probe = max77650_onkey_probe,
};
diff --git a/drivers/input/misc/pm8xxx-vibrator.c b/drivers/input/misc/pm8xxx-vibrator.c
index ecd762f..53ad25e 100644
--- a/drivers/input/misc/pm8xxx-vibrator.c
+++ b/drivers/input/misc/pm8xxx-vibrator.c
@@ -90,7 +90,7 @@ static int pm8xxx_vib_set(struct pm8xxx_vib *vib, bool on)
if (regs->enable_mask)
rc = regmap_update_bits(vib->regmap, regs->enable_addr,
- on ? regs->enable_mask : 0, val);
+ regs->enable_mask, on ? ~0 : 0);
return rc;
}
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index fd25378..f259313 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -74,12 +74,16 @@ static int uinput_dev_event(struct input_dev *dev,
struct uinput_device *udev = input_get_drvdata(dev);
struct timespec64 ts;
- udev->buff[udev->head].type = type;
- udev->buff[udev->head].code = code;
- udev->buff[udev->head].value = value;
ktime_get_ts64(&ts);
- udev->buff[udev->head].input_event_sec = ts.tv_sec;
- udev->buff[udev->head].input_event_usec = ts.tv_nsec / NSEC_PER_USEC;
+
+ udev->buff[udev->head] = (struct input_event) {
+ .input_event_sec = ts.tv_sec,
+ .input_event_usec = ts.tv_nsec / NSEC_PER_USEC,
+ .type = type,
+ .code = code,
+ .value = value,
+ };
+
udev->head = (udev->head + 1) % UINPUT_BUFFER_SIZE;
wake_up_interruptible(&udev->waitq);
@@ -689,13 +693,14 @@ static ssize_t uinput_read(struct file *file, char __user *buffer,
static __poll_t uinput_poll(struct file *file, poll_table *wait)
{
struct uinput_device *udev = file->private_data;
+ __poll_t mask = EPOLLOUT | EPOLLWRNORM; /* uinput is always writable */
poll_wait(file, &udev->waitq, wait);
if (udev->head != udev->tail)
- return EPOLLIN | EPOLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
- return EPOLLOUT | EPOLLWRNORM;
+ return mask;
}
static int uinput_release(struct inode *inode, struct file *file)
diff --git a/drivers/input/rmi4/rmi_f54.c b/drivers/input/rmi4/rmi_f54.c
index 0bc01cf..6b23e67 100644
--- a/drivers/input/rmi4/rmi_f54.c
+++ b/drivers/input/rmi4/rmi_f54.c
@@ -24,6 +24,12 @@
#define F54_NUM_TX_OFFSET 1
#define F54_NUM_RX_OFFSET 0
+/*
+ * The smbus protocol can read only 32 bytes max at a time.
+ * But this should be fine for i2c/spi as well.
+ */
+#define F54_REPORT_DATA_SIZE 32
+
/* F54 commands */
#define F54_GET_REPORT 1
#define F54_FORCE_CAL 2
@@ -526,6 +532,7 @@ static void rmi_f54_work(struct work_struct *work)
int report_size;
u8 command;
int error;
+ int i;
report_size = rmi_f54_get_report_size(f54);
if (report_size == 0) {
@@ -558,23 +565,27 @@ static void rmi_f54_work(struct work_struct *work)
rmi_dbg(RMI_DEBUG_FN, &fn->dev, "Get report command completed, reading data\n");
- fifo[0] = 0;
- fifo[1] = 0;
- error = rmi_write_block(fn->rmi_dev,
- fn->fd.data_base_addr + F54_FIFO_OFFSET,
- fifo, sizeof(fifo));
- if (error) {
- dev_err(&fn->dev, "Failed to set fifo start offset\n");
- goto abort;
- }
+ for (i = 0; i < report_size; i += F54_REPORT_DATA_SIZE) {
+ int size = min(F54_REPORT_DATA_SIZE, report_size - i);
- error = rmi_read_block(fn->rmi_dev, fn->fd.data_base_addr +
- F54_REPORT_DATA_OFFSET, f54->report_data,
- report_size);
- if (error) {
- dev_err(&fn->dev, "%s: read [%d bytes] returned %d\n",
- __func__, report_size, error);
- goto abort;
+ fifo[0] = i & 0xff;
+ fifo[1] = i >> 8;
+ error = rmi_write_block(fn->rmi_dev,
+ fn->fd.data_base_addr + F54_FIFO_OFFSET,
+ fifo, sizeof(fifo));
+ if (error) {
+ dev_err(&fn->dev, "Failed to set fifo start offset\n");
+ goto abort;
+ }
+
+ error = rmi_read_block(fn->rmi_dev, fn->fd.data_base_addr +
+ F54_REPORT_DATA_OFFSET,
+ f54->report_data + i, size);
+ if (error) {
+ dev_err(&fn->dev, "%s: read [%d bytes] returned %d\n",
+ __func__, size, error);
+ goto abort;
+ }
}
abort:
diff --git a/drivers/input/rmi4/rmi_smbus.c b/drivers/input/rmi4/rmi_smbus.c
index b313c57..2407ea4 100644
--- a/drivers/input/rmi4/rmi_smbus.c
+++ b/drivers/input/rmi4/rmi_smbus.c
@@ -163,6 +163,7 @@ static int rmi_smb_write_block(struct rmi_transport_dev *xport, u16 rmiaddr,
/* prepare to write next block of bytes */
cur_len -= SMB_MAX_COUNT;
databuff += SMB_MAX_COUNT;
+ rmiaddr += SMB_MAX_COUNT;
}
exit:
mutex_unlock(&rmi_smb->page_mutex);
@@ -214,6 +215,7 @@ static int rmi_smb_read_block(struct rmi_transport_dev *xport, u16 rmiaddr,
/* prepare to read next block of bytes */
cur_len -= SMB_MAX_COUNT;
databuff += SMB_MAX_COUNT;
+ rmiaddr += SMB_MAX_COUNT;
}
retval = 0;
diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c
index 2ca586f..e08b0ef 100644
--- a/drivers/input/tablet/aiptek.c
+++ b/drivers/input/tablet/aiptek.c
@@ -1713,7 +1713,7 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id)
aiptek->inputdev = inputdev;
aiptek->intf = intf;
- aiptek->ifnum = intf->altsetting[0].desc.bInterfaceNumber;
+ aiptek->ifnum = intf->cur_altsetting->desc.bInterfaceNumber;
aiptek->inDelay = 0;
aiptek->endDelay = 0;
aiptek->previousJitterable = 0;
@@ -1802,14 +1802,14 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id)
input_set_abs_params(inputdev, ABS_WHEEL, AIPTEK_WHEEL_MIN, AIPTEK_WHEEL_MAX - 1, 0, 0);
/* Verify that a device really has an endpoint */
- if (intf->altsetting[0].desc.bNumEndpoints < 1) {
+ if (intf->cur_altsetting->desc.bNumEndpoints < 1) {
dev_err(&intf->dev,
"interface has %d endpoints, but must have minimum 1\n",
- intf->altsetting[0].desc.bNumEndpoints);
+ intf->cur_altsetting->desc.bNumEndpoints);
err = -EINVAL;
goto fail3;
}
- endpoint = &intf->altsetting[0].endpoint[0].desc;
+ endpoint = &intf->cur_altsetting->endpoint[0].desc;
/* Go set up our URB, which is called when the tablet receives
* input.
diff --git a/drivers/input/tablet/gtco.c b/drivers/input/tablet/gtco.c
index 3503122..96d6557 100644
--- a/drivers/input/tablet/gtco.c
+++ b/drivers/input/tablet/gtco.c
@@ -875,18 +875,14 @@ static int gtco_probe(struct usb_interface *usbinterface,
}
/* Sanity check that a device has an endpoint */
- if (usbinterface->altsetting[0].desc.bNumEndpoints < 1) {
+ if (usbinterface->cur_altsetting->desc.bNumEndpoints < 1) {
dev_err(&usbinterface->dev,
"Invalid number of endpoints\n");
error = -EINVAL;
goto err_free_urb;
}
- /*
- * The endpoint is always altsetting 0, we know this since we know
- * this device only has one interrupt endpoint
- */
- endpoint = &usbinterface->altsetting[0].endpoint[0].desc;
+ endpoint = &usbinterface->cur_altsetting->endpoint[0].desc;
/* Some debug */
dev_dbg(&usbinterface->dev, "gtco # interfaces: %d\n", usbinterface->num_altsetting);
@@ -896,7 +892,8 @@ static int gtco_probe(struct usb_interface *usbinterface,
if (usb_endpoint_xfer_int(endpoint))
dev_dbg(&usbinterface->dev, "endpoint: we have interrupt endpoint\n");
- dev_dbg(&usbinterface->dev, "endpoint extra len:%d\n", usbinterface->altsetting[0].extralen);
+ dev_dbg(&usbinterface->dev, "interface extra len:%d\n",
+ usbinterface->cur_altsetting->extralen);
/*
* Find the HID descriptor so we can find out the size of the
@@ -973,8 +970,6 @@ static int gtco_probe(struct usb_interface *usbinterface,
input_dev->dev.parent = &usbinterface->dev;
/* Setup the URB, it will be posted later on open of input device */
- endpoint = &usbinterface->altsetting[0].endpoint[0].desc;
-
usb_fill_int_urb(gtco->urbinfo,
udev,
usb_rcvintpipe(udev,
diff --git a/drivers/input/tablet/pegasus_notetaker.c b/drivers/input/tablet/pegasus_notetaker.c
index a1f3a0c..38f0874 100644
--- a/drivers/input/tablet/pegasus_notetaker.c
+++ b/drivers/input/tablet/pegasus_notetaker.c
@@ -275,7 +275,7 @@ static int pegasus_probe(struct usb_interface *intf,
return -ENODEV;
/* Sanity check that the device has an endpoint */
- if (intf->altsetting[0].desc.bNumEndpoints < 1) {
+ if (intf->cur_altsetting->desc.bNumEndpoints < 1) {
dev_err(&intf->dev, "Invalid number of endpoints\n");
return -EINVAL;
}
diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c
index 0af0fe8..742a7e9 100644
--- a/drivers/input/touchscreen/sun4i-ts.c
+++ b/drivers/input/touchscreen/sun4i-ts.c
@@ -237,6 +237,7 @@ static int sun4i_ts_probe(struct platform_device *pdev)
struct device *dev = &pdev->dev;
struct device_node *np = dev->of_node;
struct device *hwmon;
+ struct thermal_zone_device *thermal;
int error;
u32 reg;
bool ts_attached;
@@ -355,7 +356,10 @@ static int sun4i_ts_probe(struct platform_device *pdev)
if (IS_ERR(hwmon))
return PTR_ERR(hwmon);
- devm_thermal_zone_of_sensor_register(ts->dev, 0, ts, &sun4i_ts_tz_ops);
+ thermal = devm_thermal_zone_of_sensor_register(ts->dev, 0, ts,
+ &sun4i_ts_tz_ops);
+ if (IS_ERR(thermal))
+ return PTR_ERR(thermal);
writel(TEMP_IRQ_EN(1), ts->base + TP_INT_FIFOC);
diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c
index 1dd47dd..34d31c7e 100644
--- a/drivers/input/touchscreen/sur40.c
+++ b/drivers/input/touchscreen/sur40.c
@@ -661,7 +661,7 @@ static int sur40_probe(struct usb_interface *interface,
int error;
/* Check if we really have the right interface. */
- iface_desc = &interface->altsetting[0];
+ iface_desc = interface->cur_altsetting;
if (iface_desc->desc.bInterfaceClass != 0xFF)
return -ENODEV;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 568c523..483f7bc 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1655,27 +1655,39 @@ static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
static void init_iommu_perf_ctr(struct amd_iommu *iommu)
{
struct pci_dev *pdev = iommu->dev;
- u64 val = 0xabcd, val2 = 0;
+ u64 val = 0xabcd, val2 = 0, save_reg = 0;
if (!iommu_feature(iommu, FEATURE_PC))
return;
amd_iommu_pc_present = true;
+ /* save the value to restore, if writable */
+ if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, false))
+ goto pc_false;
+
/* Check if the performance counters can be written to */
if ((iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true)) ||
(iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false)) ||
- (val != val2)) {
- pci_err(pdev, "Unable to write to IOMMU perf counter.\n");
- amd_iommu_pc_present = false;
- return;
- }
+ (val != val2))
+ goto pc_false;
+
+ /* restore */
+ if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, true))
+ goto pc_false;
pci_info(pdev, "IOMMU performance counters supported\n");
val = readl(iommu->mmio_base + MMIO_CNTR_CONF_OFFSET);
iommu->max_banks = (u8) ((val >> 12) & 0x3f);
iommu->max_counters = (u8) ((val >> 7) & 0xf);
+
+ return;
+
+pc_false:
+ pci_err(pdev, "Unable to read/write to IOMMU perf counter.\n");
+ amd_iommu_pc_present = false;
+ return;
}
static ssize_t amd_iommu_show_cap(struct device *dev,
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index c363294..a2e96a5 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1203,7 +1203,6 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
{
struct device *dev = msi_desc_to_dev(desc);
struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
- struct iommu_dma_cookie *cookie;
struct iommu_dma_msi_page *msi_page;
static DEFINE_MUTEX(msi_prepare_lock); /* see below */
@@ -1212,8 +1211,6 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
return 0;
}
- cookie = domain->iova_cookie;
-
/*
* In fact the whole prepare operation should already be serialised by
* irq_domain_mutex further up the callchain, but that's pretty subtle
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 4296661..932267f 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -5163,7 +5163,8 @@ static void dmar_remove_one_dev_info(struct device *dev)
spin_lock_irqsave(&device_domain_lock, flags);
info = dev->archdata.iommu;
- if (info)
+ if (info && info != DEFER_DEVICE_DOMAIN_INFO
+ && info != DUMMY_DEVICE_DOMAIN_INFO)
__dmar_remove_one_dev_info(info);
spin_unlock_irqrestore(&device_domain_lock, flags);
}
@@ -5624,8 +5625,10 @@ static int intel_iommu_add_device(struct device *dev)
group = iommu_group_get_for_dev(dev);
- if (IS_ERR(group))
- return PTR_ERR(group);
+ if (IS_ERR(group)) {
+ ret = PTR_ERR(group);
+ goto unlink;
+ }
iommu_group_put(group);
@@ -5651,7 +5654,8 @@ static int intel_iommu_add_device(struct device *dev)
if (!get_private_domain_for_dev(dev)) {
dev_warn(dev,
"Failed to get a private domain.\n");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto unlink;
}
dev_info(dev,
@@ -5666,6 +5670,10 @@ static int intel_iommu_add_device(struct device *dev)
}
return 0;
+
+unlink:
+ iommu_device_unlink(&iommu->iommu, dev);
+ return ret;
}
static void intel_iommu_remove_device(struct device *dev)
@@ -5817,6 +5825,13 @@ static void intel_iommu_apply_resv_region(struct device *dev,
WARN_ON_ONCE(!reserve_iova(&dmar_domain->iovad, start, end));
}
+static struct iommu_group *intel_iommu_device_group(struct device *dev)
+{
+ if (dev_is_pci(dev))
+ return pci_device_group(dev);
+ return generic_device_group(dev);
+}
+
#ifdef CONFIG_INTEL_IOMMU_SVM
struct intel_iommu *intel_svm_device_to_iommu(struct device *dev)
{
@@ -5989,7 +6004,7 @@ const struct iommu_ops intel_iommu_ops = {
.get_resv_regions = intel_iommu_get_resv_regions,
.put_resv_regions = intel_iommu_put_resv_regions,
.apply_resv_region = intel_iommu_apply_resv_region,
- .device_group = pci_device_group,
+ .device_group = intel_iommu_device_group,
.dev_has_feat = intel_iommu_dev_has_feat,
.dev_feat_enabled = intel_iommu_dev_feat_enabled,
.dev_enable_feat = intel_iommu_dev_enable_feat,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index fdd4075..3ead597 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -751,6 +751,7 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
mutex_unlock(&group->mutex);
dev->iommu_group = NULL;
kobject_put(group->devices_kobj);
+ sysfs_remove_link(group->devices_kobj, device->name);
err_free_name:
kfree(device->name);
err_remove_link:
diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c
index 01d18b3..c5589ee 100644
--- a/drivers/irqchip/irq-ingenic.c
+++ b/drivers/irqchip/irq-ingenic.c
@@ -17,7 +17,6 @@
#include <linux/delay.h>
#include <asm/io.h>
-#include <asm/mach-jz4740/irq.h>
struct ingenic_intc_data {
void __iomem *base;
@@ -50,7 +49,7 @@ static irqreturn_t intc_cascade(int irq, void *data)
while (pending) {
int bit = __fls(pending);
- irq = irq_find_mapping(domain, bit + (i * 32));
+ irq = irq_linear_revmap(domain, bit + (i * 32));
generic_handle_irq(irq);
pending &= ~BIT(bit);
}
@@ -97,8 +96,7 @@ static int __init ingenic_intc_of_init(struct device_node *node,
goto out_unmap_irq;
}
- domain = irq_domain_add_legacy(node, num_chips * 32,
- JZ4740_IRQ_BASE, 0,
+ domain = irq_domain_add_linear(node, num_chips * 32,
&irq_generic_chip_ops, NULL);
if (!domain) {
err = -ENOMEM;
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index 8df547d2..0aca580 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -256,7 +256,7 @@ static int __init plic_init(struct device_node *node,
* Skip contexts other than external interrupts for our
* privilege level.
*/
- if (parent.args[0] != IRQ_EXT)
+ if (parent.args[0] != RV_IRQ_EXT)
continue;
hartid = plic_find_hart_id(parent.np);
diff --git a/drivers/leds/leds-as3645a.c b/drivers/leds/leds-as3645a.c
index b7e0ae1..e8922fa 100644
--- a/drivers/leds/leds-as3645a.c
+++ b/drivers/leds/leds-as3645a.c
@@ -493,16 +493,17 @@ static int as3645a_parse_node(struct as3645a *flash,
switch (id) {
case AS_LED_FLASH:
flash->flash_node = child;
+ fwnode_handle_get(child);
break;
case AS_LED_INDICATOR:
flash->indicator_node = child;
+ fwnode_handle_get(child);
break;
default:
dev_warn(&flash->client->dev,
"unknown LED %u encountered, ignoring\n", id);
break;
}
- fwnode_handle_get(child);
}
if (!flash->flash_node) {
diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index a5c73f3..2bf74595 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -151,9 +151,14 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev)
struct gpio_led led = {};
const char *state = NULL;
+ /*
+ * Acquire gpiod from DT with uninitialized label, which
+ * will be updated after LED class device is registered,
+ * Only then the final LED name is known.
+ */
led.gpiod = devm_fwnode_get_gpiod_from_child(dev, NULL, child,
GPIOD_ASIS,
- led.name);
+ NULL);
if (IS_ERR(led.gpiod)) {
fwnode_handle_put(child);
return ERR_CAST(led.gpiod);
@@ -186,6 +191,9 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev)
fwnode_handle_put(child);
return ERR_PTR(ret);
}
+ /* Set gpiod label to match the corresponding LED name. */
+ gpiod_set_consumer_name(led_dat->gpiod,
+ led_dat->cdev.dev->kobj.name);
priv->num_leds++;
}
diff --git a/drivers/leds/leds-lm3532.c b/drivers/leds/leds-lm3532.c
index 0507c65..491268b 100644
--- a/drivers/leds/leds-lm3532.c
+++ b/drivers/leds/leds-lm3532.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// TI LM3532 LED driver
// Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/
+// http://www.ti.com/lit/ds/symlink/lm3532.pdf
#include <linux/i2c.h>
#include <linux/leds.h>
@@ -623,7 +624,7 @@ static int lm3532_parse_node(struct lm3532_data *priv)
led->num_leds = fwnode_property_count_u32(child, "led-sources");
if (led->num_leds > LM3532_MAX_LED_STRINGS) {
- dev_err(&priv->client->dev, "To many LED string defined\n");
+ dev_err(&priv->client->dev, "Too many LED string defined\n");
continue;
}
diff --git a/drivers/leds/leds-max77650.c b/drivers/leds/leds-max77650.c
index 4c2d0b3..a0d4b72 100644
--- a/drivers/leds/leds-max77650.c
+++ b/drivers/leds/leds-max77650.c
@@ -135,9 +135,16 @@ static int max77650_led_probe(struct platform_device *pdev)
return rv;
}
+static const struct of_device_id max77650_led_of_match[] = {
+ { .compatible = "maxim,max77650-led" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, max77650_led_of_match);
+
static struct platform_driver max77650_led_driver = {
.driver = {
.name = "max77650-led",
+ .of_match_table = max77650_led_of_match,
},
.probe = max77650_led_probe,
};
diff --git a/drivers/leds/leds-rb532.c b/drivers/leds/leds-rb532.c
index db5af83f..b6447c1 100644
--- a/drivers/leds/leds-rb532.c
+++ b/drivers/leds/leds-rb532.c
@@ -21,7 +21,6 @@ static void rb532_led_set(struct led_classdev *cdev,
{
if (brightness)
set_latch_u5(LO_ULED, 0);
-
else
set_latch_u5(0, LO_ULED);
}
diff --git a/drivers/leds/trigger/ledtrig-pattern.c b/drivers/leds/trigger/ledtrig-pattern.c
index 718729c..3abcafe 100644
--- a/drivers/leds/trigger/ledtrig-pattern.c
+++ b/drivers/leds/trigger/ledtrig-pattern.c
@@ -455,7 +455,7 @@ static void __exit pattern_trig_exit(void)
module_init(pattern_trig_init);
module_exit(pattern_trig_exit);
-MODULE_AUTHOR("Raphael Teysseyre <rteysseyre@gmail.com");
-MODULE_AUTHOR("Baolin Wang <baolin.wang@linaro.org");
+MODULE_AUTHOR("Raphael Teysseyre <rteysseyre@gmail.com>");
+MODULE_AUTHOR("Baolin Wang <baolin.wang@linaro.org>");
MODULE_DESCRIPTION("LED Pattern trigger");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 3c50c4e..963d377 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -17,7 +17,7 @@
#include <linux/dm-bufio.h>
#define DM_MSG_PREFIX "persistent snapshot"
-#define DM_CHUNK_SIZE_DEFAULT_SECTORS 32 /* 16KB */
+#define DM_CHUNK_SIZE_DEFAULT_SECTORS 32U /* 16KB */
#define DM_PREFETCH_CHUNKS 12
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index b7c2097..322386f 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -87,7 +87,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
char b[BDEVNAME_SIZE];
char b2[BDEVNAME_SIZE];
struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
- unsigned short blksize = 512;
+ unsigned blksize = 512;
*private_conf = ERR_PTR(-ENOMEM);
if (!conf)
diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index 9340435..6c95dc4 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -380,7 +380,8 @@ static void cec_data_cancel(struct cec_data *data, u8 tx_status)
} else {
list_del_init(&data->list);
if (!(data->msg.tx_status & CEC_TX_STATUS_OK))
- data->adap->transmit_queue_sz--;
+ if (!WARN_ON(!data->adap->transmit_queue_sz))
+ data->adap->transmit_queue_sz--;
}
if (data->msg.tx_status & CEC_TX_STATUS_OK) {
@@ -432,6 +433,14 @@ static void cec_flush(struct cec_adapter *adap)
* need to do anything special in that case.
*/
}
+ /*
+ * If something went wrong and this counter isn't what it should
+ * be, then this will reset it back to 0. Warn if it is not 0,
+ * since it indicates a bug, either in this framework or in a
+ * CEC driver.
+ */
+ if (WARN_ON(adap->transmit_queue_sz))
+ adap->transmit_queue_sz = 0;
}
/*
@@ -456,7 +465,7 @@ int cec_thread_func(void *_adap)
bool timeout = false;
u8 attempts;
- if (adap->transmitting) {
+ if (adap->transmit_in_progress) {
int err;
/*
@@ -491,7 +500,7 @@ int cec_thread_func(void *_adap)
goto unlock;
}
- if (adap->transmitting && timeout) {
+ if (adap->transmit_in_progress && timeout) {
/*
* If we timeout, then log that. Normally this does
* not happen and it is an indication of a faulty CEC
@@ -500,14 +509,18 @@ int cec_thread_func(void *_adap)
* so much traffic on the bus that the adapter was
* unable to transmit for CEC_XFER_TIMEOUT_MS (2.1s).
*/
- pr_warn("cec-%s: message %*ph timed out\n", adap->name,
- adap->transmitting->msg.len,
- adap->transmitting->msg.msg);
+ if (adap->transmitting) {
+ pr_warn("cec-%s: message %*ph timed out\n", adap->name,
+ adap->transmitting->msg.len,
+ adap->transmitting->msg.msg);
+ /* Just give up on this. */
+ cec_data_cancel(adap->transmitting,
+ CEC_TX_STATUS_TIMEOUT);
+ } else {
+ pr_warn("cec-%s: transmit timed out\n", adap->name);
+ }
adap->transmit_in_progress = false;
adap->tx_timeouts++;
- /* Just give up on this. */
- cec_data_cancel(adap->transmitting,
- CEC_TX_STATUS_TIMEOUT);
goto unlock;
}
@@ -522,7 +535,8 @@ int cec_thread_func(void *_adap)
data = list_first_entry(&adap->transmit_queue,
struct cec_data, list);
list_del_init(&data->list);
- adap->transmit_queue_sz--;
+ if (!WARN_ON(!data->adap->transmit_queue_sz))
+ adap->transmit_queue_sz--;
/* Make this the current transmitting message */
adap->transmitting = data;
@@ -1085,11 +1099,11 @@ void cec_received_msg_ts(struct cec_adapter *adap,
valid_la = false;
else if (!cec_msg_is_broadcast(msg) && !(dir_fl & DIRECTED))
valid_la = false;
- else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST1_4))
+ else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST))
valid_la = false;
else if (cec_msg_is_broadcast(msg) &&
- adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0 &&
- !(dir_fl & BCAST2_0))
+ adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0 &&
+ !(dir_fl & BCAST1_4))
valid_la = false;
}
if (valid_la && min_len) {
diff --git a/drivers/media/usb/pulse8-cec/pulse8-cec.c b/drivers/media/usb/pulse8-cec/pulse8-cec.c
index ac88ade..5960955 100644
--- a/drivers/media/usb/pulse8-cec/pulse8-cec.c
+++ b/drivers/media/usb/pulse8-cec/pulse8-cec.c
@@ -116,6 +116,7 @@ struct pulse8 {
unsigned int vers;
struct completion cmd_done;
struct work_struct work;
+ u8 work_result;
struct delayed_work ping_eeprom_work;
struct cec_msg rx_msg;
u8 data[DATA_SIZE];
@@ -137,8 +138,10 @@ static void pulse8_irq_work_handler(struct work_struct *work)
{
struct pulse8 *pulse8 =
container_of(work, struct pulse8, work);
+ u8 result = pulse8->work_result;
- switch (pulse8->data[0] & 0x3f) {
+ pulse8->work_result = 0;
+ switch (result & 0x3f) {
case MSGCODE_FRAME_DATA:
cec_received_msg(pulse8->adap, &pulse8->rx_msg);
break;
@@ -172,12 +175,12 @@ static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data,
pulse8->escape = false;
} else if (data == MSGEND) {
struct cec_msg *msg = &pulse8->rx_msg;
+ u8 msgcode = pulse8->buf[0];
if (debug)
dev_info(pulse8->dev, "received: %*ph\n",
pulse8->idx, pulse8->buf);
- pulse8->data[0] = pulse8->buf[0];
- switch (pulse8->buf[0] & 0x3f) {
+ switch (msgcode & 0x3f) {
case MSGCODE_FRAME_START:
msg->len = 1;
msg->msg[0] = pulse8->buf[1];
@@ -186,14 +189,20 @@ static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data,
if (msg->len == CEC_MAX_MSG_SIZE)
break;
msg->msg[msg->len++] = pulse8->buf[1];
- if (pulse8->buf[0] & MSGCODE_FRAME_EOM)
+ if (msgcode & MSGCODE_FRAME_EOM) {
+ WARN_ON(pulse8->work_result);
+ pulse8->work_result = msgcode;
schedule_work(&pulse8->work);
+ break;
+ }
break;
case MSGCODE_TRANSMIT_SUCCEEDED:
case MSGCODE_TRANSMIT_FAILED_LINE:
case MSGCODE_TRANSMIT_FAILED_ACK:
case MSGCODE_TRANSMIT_FAILED_TIMEOUT_DATA:
case MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE:
+ WARN_ON(pulse8->work_result);
+ pulse8->work_result = msgcode;
schedule_work(&pulse8->work);
break;
case MSGCODE_HIGH_ERROR:
diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c
index f9ac224..1074b88 100644
--- a/drivers/message/fusion/mptctl.c
+++ b/drivers/message/fusion/mptctl.c
@@ -100,19 +100,19 @@ struct buflist {
* Function prototypes. Called from OS entry point mptctl_ioctl.
* arg contents specific to function.
*/
-static int mptctl_fw_download(unsigned long arg);
-static int mptctl_getiocinfo(unsigned long arg, unsigned int cmd);
-static int mptctl_gettargetinfo(unsigned long arg);
-static int mptctl_readtest(unsigned long arg);
-static int mptctl_mpt_command(unsigned long arg);
-static int mptctl_eventquery(unsigned long arg);
-static int mptctl_eventenable(unsigned long arg);
-static int mptctl_eventreport(unsigned long arg);
-static int mptctl_replace_fw(unsigned long arg);
+static int mptctl_fw_download(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_getiocinfo(MPT_ADAPTER *iocp, unsigned long arg, unsigned int cmd);
+static int mptctl_gettargetinfo(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_readtest(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_mpt_command(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_eventquery(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_eventenable(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_eventreport(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_replace_fw(MPT_ADAPTER *iocp, unsigned long arg);
-static int mptctl_do_reset(unsigned long arg);
-static int mptctl_hp_hostinfo(unsigned long arg, unsigned int cmd);
-static int mptctl_hp_targetinfo(unsigned long arg);
+static int mptctl_do_reset(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_hp_hostinfo(MPT_ADAPTER *iocp, unsigned long arg, unsigned int cmd);
+static int mptctl_hp_targetinfo(MPT_ADAPTER *iocp, unsigned long arg);
static int mptctl_probe(struct pci_dev *, const struct pci_device_id *);
static void mptctl_remove(struct pci_dev *);
@@ -123,8 +123,8 @@ static long compat_mpctl_ioctl(struct file *f, unsigned cmd, unsigned long arg);
/*
* Private function calls.
*/
-static int mptctl_do_mpt_command(struct mpt_ioctl_command karg, void __user *mfPtr);
-static int mptctl_do_fw_download(int ioc, char __user *ufwbuf, size_t fwlen);
+static int mptctl_do_mpt_command(MPT_ADAPTER *iocp, struct mpt_ioctl_command karg, void __user *mfPtr);
+static int mptctl_do_fw_download(MPT_ADAPTER *iocp, char __user *ufwbuf, size_t fwlen);
static MptSge_t *kbuf_alloc_2_sgl(int bytes, u32 dir, int sge_offset, int *frags,
struct buflist **blp, dma_addr_t *sglbuf_dma, MPT_ADAPTER *ioc);
static void kfree_sgl(MptSge_t *sgl, dma_addr_t sgl_dma,
@@ -656,19 +656,19 @@ __mptctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
* by TM and FW reloads.
*/
if ((cmd & ~IOCSIZE_MASK) == (MPTIOCINFO & ~IOCSIZE_MASK)) {
- return mptctl_getiocinfo(arg, _IOC_SIZE(cmd));
+ return mptctl_getiocinfo(iocp, arg, _IOC_SIZE(cmd));
} else if (cmd == MPTTARGETINFO) {
- return mptctl_gettargetinfo(arg);
+ return mptctl_gettargetinfo(iocp, arg);
} else if (cmd == MPTTEST) {
- return mptctl_readtest(arg);
+ return mptctl_readtest(iocp, arg);
} else if (cmd == MPTEVENTQUERY) {
- return mptctl_eventquery(arg);
+ return mptctl_eventquery(iocp, arg);
} else if (cmd == MPTEVENTENABLE) {
- return mptctl_eventenable(arg);
+ return mptctl_eventenable(iocp, arg);
} else if (cmd == MPTEVENTREPORT) {
- return mptctl_eventreport(arg);
+ return mptctl_eventreport(iocp, arg);
} else if (cmd == MPTFWREPLACE) {
- return mptctl_replace_fw(arg);
+ return mptctl_replace_fw(iocp, arg);
}
/* All of these commands require an interrupt or
@@ -678,15 +678,15 @@ __mptctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return ret;
if (cmd == MPTFWDOWNLOAD)
- ret = mptctl_fw_download(arg);
+ ret = mptctl_fw_download(iocp, arg);
else if (cmd == MPTCOMMAND)
- ret = mptctl_mpt_command(arg);
+ ret = mptctl_mpt_command(iocp, arg);
else if (cmd == MPTHARDRESET)
- ret = mptctl_do_reset(arg);
+ ret = mptctl_do_reset(iocp, arg);
else if ((cmd & ~IOCSIZE_MASK) == (HP_GETHOSTINFO & ~IOCSIZE_MASK))
- ret = mptctl_hp_hostinfo(arg, _IOC_SIZE(cmd));
+ ret = mptctl_hp_hostinfo(iocp, arg, _IOC_SIZE(cmd));
else if (cmd == HP_GETTARGETINFO)
- ret = mptctl_hp_targetinfo(arg);
+ ret = mptctl_hp_targetinfo(iocp, arg);
else
ret = -EINVAL;
@@ -705,11 +705,10 @@ mptctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return ret;
}
-static int mptctl_do_reset(unsigned long arg)
+static int mptctl_do_reset(MPT_ADAPTER *iocp, unsigned long arg)
{
struct mpt_ioctl_diag_reset __user *urinfo = (void __user *) arg;
struct mpt_ioctl_diag_reset krinfo;
- MPT_ADAPTER *iocp;
if (copy_from_user(&krinfo, urinfo, sizeof(struct mpt_ioctl_diag_reset))) {
printk(KERN_ERR MYNAM "%s@%d::mptctl_do_reset - "
@@ -718,12 +717,6 @@ static int mptctl_do_reset(unsigned long arg)
return -EFAULT;
}
- if (mpt_verify_adapter(krinfo.hdr.iocnum, &iocp) < 0) {
- printk(KERN_DEBUG MYNAM "%s@%d::mptctl_do_reset - ioc%d not found!\n",
- __FILE__, __LINE__, krinfo.hdr.iocnum);
- return -ENODEV; /* (-6) No such device or address */
- }
-
dctlprintk(iocp, printk(MYIOC_s_DEBUG_FMT "mptctl_do_reset called.\n",
iocp->name));
@@ -754,7 +747,7 @@ static int mptctl_do_reset(unsigned long arg)
* -ENOMSG if FW upload returned bad status
*/
static int
-mptctl_fw_download(unsigned long arg)
+mptctl_fw_download(MPT_ADAPTER *iocp, unsigned long arg)
{
struct mpt_fw_xfer __user *ufwdl = (void __user *) arg;
struct mpt_fw_xfer kfwdl;
@@ -766,7 +759,7 @@ mptctl_fw_download(unsigned long arg)
return -EFAULT;
}
- return mptctl_do_fw_download(kfwdl.iocnum, kfwdl.bufp, kfwdl.fwlen);
+ return mptctl_do_fw_download(iocp, kfwdl.bufp, kfwdl.fwlen);
}
/*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
@@ -784,11 +777,10 @@ mptctl_fw_download(unsigned long arg)
* -ENOMSG if FW upload returned bad status
*/
static int
-mptctl_do_fw_download(int ioc, char __user *ufwbuf, size_t fwlen)
+mptctl_do_fw_download(MPT_ADAPTER *iocp, char __user *ufwbuf, size_t fwlen)
{
FWDownload_t *dlmsg;
MPT_FRAME_HDR *mf;
- MPT_ADAPTER *iocp;
FWDownloadTCSGE_t *ptsge;
MptSge_t *sgl, *sgIn;
char *sgOut;
@@ -808,17 +800,10 @@ mptctl_do_fw_download(int ioc, char __user *ufwbuf, size_t fwlen)
pFWDownloadReply_t ReplyMsg = NULL;
unsigned long timeleft;
- if (mpt_verify_adapter(ioc, &iocp) < 0) {
- printk(KERN_DEBUG MYNAM "ioctl_fwdl - ioc%d not found!\n",
- ioc);
- return -ENODEV; /* (-6) No such device or address */
- } else {
-
- /* Valid device. Get a message frame and construct the FW download message.
- */
- if ((mf = mpt_get_msg_frame(mptctl_id, iocp)) == NULL)
- return -EAGAIN;
- }
+ /* Valid device. Get a message frame and construct the FW download message.
+ */
+ if ((mf = mpt_get_msg_frame(mptctl_id, iocp)) == NULL)
+ return -EAGAIN;
dctlprintk(iocp, printk(MYIOC_s_DEBUG_FMT
"mptctl_do_fwdl called. mptctl_id = %xh.\n", iocp->name, mptctl_id));
@@ -826,8 +811,6 @@ mptctl_do_fw_download(int ioc, char __user *ufwbuf, size_t fwlen)
iocp->name, ufwbuf));
dctlprintk(iocp, printk(MYIOC_s_DEBUG_FMT "DbG: kfwdl.fwlen = %d\n",
iocp->name, (int)fwlen));
- dctlprintk(iocp, printk(MYIOC_s_DEBUG_FMT "DbG: kfwdl.ioc = %04xh\n",
- iocp->name, ioc));
dlmsg = (FWDownload_t*) mf;
ptsge = (FWDownloadTCSGE_t *) &dlmsg->SGL;
@@ -1238,13 +1221,11 @@ kfree_sgl(MptSge_t *sgl, dma_addr_t sgl_dma, struct buflist *buflist, MPT_ADAPTE
* -ENODEV if no such device/adapter
*/
static int
-mptctl_getiocinfo (unsigned long arg, unsigned int data_size)
+mptctl_getiocinfo (MPT_ADAPTER *ioc, unsigned long arg, unsigned int data_size)
{
struct mpt_ioctl_iocinfo __user *uarg = (void __user *) arg;
struct mpt_ioctl_iocinfo *karg;
- MPT_ADAPTER *ioc;
struct pci_dev *pdev;
- int iocnum;
unsigned int port;
int cim_rev;
struct scsi_device *sdev;
@@ -1272,14 +1253,6 @@ mptctl_getiocinfo (unsigned long arg, unsigned int data_size)
return PTR_ERR(karg);
}
- if (((iocnum = mpt_verify_adapter(karg->hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_getiocinfo() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- kfree(karg);
- return -ENODEV;
- }
-
/* Verify the data transfer size is correct. */
if (karg->hdr.maxDataSize != data_size) {
printk(MYIOC_s_ERR_FMT "%s@%d::mptctl_getiocinfo - "
@@ -1385,15 +1358,13 @@ mptctl_getiocinfo (unsigned long arg, unsigned int data_size)
* -ENODEV if no such device/adapter
*/
static int
-mptctl_gettargetinfo (unsigned long arg)
+mptctl_gettargetinfo (MPT_ADAPTER *ioc, unsigned long arg)
{
struct mpt_ioctl_targetinfo __user *uarg = (void __user *) arg;
struct mpt_ioctl_targetinfo karg;
- MPT_ADAPTER *ioc;
VirtDevice *vdevice;
char *pmem;
int *pdata;
- int iocnum;
int numDevices = 0;
int lun;
int maxWordsLeft;
@@ -1408,13 +1379,6 @@ mptctl_gettargetinfo (unsigned long arg)
return -EFAULT;
}
- if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_gettargetinfo() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- return -ENODEV;
- }
-
dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_gettargetinfo called.\n",
ioc->name));
/* Get the port number and set the maximum number of bytes
@@ -1510,12 +1474,10 @@ mptctl_gettargetinfo (unsigned long arg)
* -ENODEV if no such device/adapter
*/
static int
-mptctl_readtest (unsigned long arg)
+mptctl_readtest (MPT_ADAPTER *ioc, unsigned long arg)
{
struct mpt_ioctl_test __user *uarg = (void __user *) arg;
struct mpt_ioctl_test karg;
- MPT_ADAPTER *ioc;
- int iocnum;
if (copy_from_user(&karg, uarg, sizeof(struct mpt_ioctl_test))) {
printk(KERN_ERR MYNAM "%s@%d::mptctl_readtest - "
@@ -1524,13 +1486,6 @@ mptctl_readtest (unsigned long arg)
return -EFAULT;
}
- if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_readtest() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- return -ENODEV;
- }
-
dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_readtest called.\n",
ioc->name));
/* Fill in the data and return the structure to the calling
@@ -1571,12 +1526,10 @@ mptctl_readtest (unsigned long arg)
* -ENODEV if no such device/adapter
*/
static int
-mptctl_eventquery (unsigned long arg)
+mptctl_eventquery (MPT_ADAPTER *ioc, unsigned long arg)
{
struct mpt_ioctl_eventquery __user *uarg = (void __user *) arg;
struct mpt_ioctl_eventquery karg;
- MPT_ADAPTER *ioc;
- int iocnum;
if (copy_from_user(&karg, uarg, sizeof(struct mpt_ioctl_eventquery))) {
printk(KERN_ERR MYNAM "%s@%d::mptctl_eventquery - "
@@ -1585,13 +1538,6 @@ mptctl_eventquery (unsigned long arg)
return -EFAULT;
}
- if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_eventquery() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- return -ENODEV;
- }
-
dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_eventquery called.\n",
ioc->name));
karg.eventEntries = MPTCTL_EVENT_LOG_SIZE;
@@ -1610,12 +1556,10 @@ mptctl_eventquery (unsigned long arg)
/*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
static int
-mptctl_eventenable (unsigned long arg)
+mptctl_eventenable (MPT_ADAPTER *ioc, unsigned long arg)
{
struct mpt_ioctl_eventenable __user *uarg = (void __user *) arg;
struct mpt_ioctl_eventenable karg;
- MPT_ADAPTER *ioc;
- int iocnum;
if (copy_from_user(&karg, uarg, sizeof(struct mpt_ioctl_eventenable))) {
printk(KERN_ERR MYNAM "%s@%d::mptctl_eventenable - "
@@ -1624,13 +1568,6 @@ mptctl_eventenable (unsigned long arg)
return -EFAULT;
}
- if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_eventenable() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- return -ENODEV;
- }
-
dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_eventenable called.\n",
ioc->name));
if (ioc->events == NULL) {
@@ -1658,12 +1595,10 @@ mptctl_eventenable (unsigned long arg)
/*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
static int
-mptctl_eventreport (unsigned long arg)
+mptctl_eventreport (MPT_ADAPTER *ioc, unsigned long arg)
{
struct mpt_ioctl_eventreport __user *uarg = (void __user *) arg;
struct mpt_ioctl_eventreport karg;
- MPT_ADAPTER *ioc;
- int iocnum;
int numBytes, maxEvents, max;
if (copy_from_user(&karg, uarg, sizeof(struct mpt_ioctl_eventreport))) {
@@ -1673,12 +1608,6 @@ mptctl_eventreport (unsigned long arg)
return -EFAULT;
}
- if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_eventreport() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- return -ENODEV;
- }
dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_eventreport called.\n",
ioc->name));
@@ -1712,12 +1641,10 @@ mptctl_eventreport (unsigned long arg)
/*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
static int
-mptctl_replace_fw (unsigned long arg)
+mptctl_replace_fw (MPT_ADAPTER *ioc, unsigned long arg)
{
struct mpt_ioctl_replace_fw __user *uarg = (void __user *) arg;
struct mpt_ioctl_replace_fw karg;
- MPT_ADAPTER *ioc;
- int iocnum;
int newFwSize;
if (copy_from_user(&karg, uarg, sizeof(struct mpt_ioctl_replace_fw))) {
@@ -1727,13 +1654,6 @@ mptctl_replace_fw (unsigned long arg)
return -EFAULT;
}
- if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_replace_fw() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- return -ENODEV;
- }
-
dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_replace_fw called.\n",
ioc->name));
/* If caching FW, Free the old FW image
@@ -1780,12 +1700,10 @@ mptctl_replace_fw (unsigned long arg)
* -ENOMEM if memory allocation error
*/
static int
-mptctl_mpt_command (unsigned long arg)
+mptctl_mpt_command (MPT_ADAPTER *ioc, unsigned long arg)
{
struct mpt_ioctl_command __user *uarg = (void __user *) arg;
struct mpt_ioctl_command karg;
- MPT_ADAPTER *ioc;
- int iocnum;
int rc;
@@ -1796,14 +1714,7 @@ mptctl_mpt_command (unsigned long arg)
return -EFAULT;
}
- if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_mpt_command() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- return -ENODEV;
- }
-
- rc = mptctl_do_mpt_command (karg, &uarg->MF);
+ rc = mptctl_do_mpt_command (ioc, karg, &uarg->MF);
return rc;
}
@@ -1821,9 +1732,8 @@ mptctl_mpt_command (unsigned long arg)
* -EPERM if SCSI I/O and target is untagged
*/
static int
-mptctl_do_mpt_command (struct mpt_ioctl_command karg, void __user *mfPtr)
+mptctl_do_mpt_command (MPT_ADAPTER *ioc, struct mpt_ioctl_command karg, void __user *mfPtr)
{
- MPT_ADAPTER *ioc;
MPT_FRAME_HDR *mf = NULL;
MPIHeader_t *hdr;
char *psge;
@@ -1832,7 +1742,7 @@ mptctl_do_mpt_command (struct mpt_ioctl_command karg, void __user *mfPtr)
dma_addr_t dma_addr_in;
dma_addr_t dma_addr_out;
int sgSize = 0; /* Num SG elements */
- int iocnum, flagsLength;
+ int flagsLength;
int sz, rc = 0;
int msgContext;
u16 req_idx;
@@ -1847,13 +1757,6 @@ mptctl_do_mpt_command (struct mpt_ioctl_command karg, void __user *mfPtr)
bufIn.kptr = bufOut.kptr = NULL;
bufIn.len = bufOut.len = 0;
- if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_do_mpt_command() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- return -ENODEV;
- }
-
spin_lock_irqsave(&ioc->taskmgmt_lock, flags);
if (ioc->ioc_reset_in_progress) {
spin_unlock_irqrestore(&ioc->taskmgmt_lock, flags);
@@ -2418,17 +2321,15 @@ mptctl_do_mpt_command (struct mpt_ioctl_command karg, void __user *mfPtr)
* -ENOMEM if memory allocation error
*/
static int
-mptctl_hp_hostinfo(unsigned long arg, unsigned int data_size)
+mptctl_hp_hostinfo(MPT_ADAPTER *ioc, unsigned long arg, unsigned int data_size)
{
hp_host_info_t __user *uarg = (void __user *) arg;
- MPT_ADAPTER *ioc;
struct pci_dev *pdev;
char *pbuf=NULL;
dma_addr_t buf_dma;
hp_host_info_t karg;
CONFIGPARMS cfg;
ConfigPageHeader_t hdr;
- int iocnum;
int rc, cim_rev;
ToolboxIstwiReadWriteRequest_t *IstwiRWRequest;
MPT_FRAME_HDR *mf = NULL;
@@ -2452,12 +2353,6 @@ mptctl_hp_hostinfo(unsigned long arg, unsigned int data_size)
return -EFAULT;
}
- if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_hp_hostinfo() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- return -ENODEV;
- }
dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT ": mptctl_hp_hostinfo called.\n",
ioc->name));
@@ -2659,15 +2554,13 @@ mptctl_hp_hostinfo(unsigned long arg, unsigned int data_size)
* -ENOMEM if memory allocation error
*/
static int
-mptctl_hp_targetinfo(unsigned long arg)
+mptctl_hp_targetinfo(MPT_ADAPTER *ioc, unsigned long arg)
{
hp_target_info_t __user *uarg = (void __user *) arg;
SCSIDevicePage0_t *pg0_alloc;
SCSIDevicePage3_t *pg3_alloc;
- MPT_ADAPTER *ioc;
MPT_SCSI_HOST *hd = NULL;
hp_target_info_t karg;
- int iocnum;
int data_sz;
dma_addr_t page_dma;
CONFIGPARMS cfg;
@@ -2681,12 +2574,6 @@ mptctl_hp_targetinfo(unsigned long arg)
return -EFAULT;
}
- if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
- (ioc == NULL)) {
- printk(KERN_DEBUG MYNAM "%s::mptctl_hp_targetinfo() @%d - ioc%d not found!\n",
- __FILE__, __LINE__, iocnum);
- return -ENODEV;
- }
if (karg.hdr.id >= MPT_MAX_FC_DEVICES)
return -EINVAL;
dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_hp_targetinfo called.\n",
@@ -2854,7 +2741,7 @@ compat_mptfwxfer_ioctl(struct file *filp, unsigned int cmd,
kfw.fwlen = kfw32.fwlen;
kfw.bufp = compat_ptr(kfw32.bufp);
- ret = mptctl_do_fw_download(kfw.iocnum, kfw.bufp, kfw.fwlen);
+ ret = mptctl_do_fw_download(iocp, kfw.bufp, kfw.fwlen);
mutex_unlock(&iocp->ioctl_cmds.mutex);
@@ -2908,7 +2795,7 @@ compat_mpt_command(struct file *filp, unsigned int cmd,
/* Pass new structure to do_mpt_command
*/
- ret = mptctl_do_mpt_command (karg, &uarg->MF);
+ ret = mptctl_do_mpt_command (iocp, karg, &uarg->MF);
mutex_unlock(&iocp->ioctl_cmds.mutex);
diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index 6d27ccf..3c2d405 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -406,10 +406,9 @@ int enclosure_remove_device(struct enclosure_device *edev, struct device *dev)
cdev = &edev->component[i];
if (cdev->dev == dev) {
enclosure_remove_links(cdev);
- device_del(&cdev->cdev);
put_device(dev);
cdev->dev = NULL;
- return device_add(&cdev->cdev);
+ return 0;
}
}
return -ENODEV;
diff --git a/drivers/misc/lkdtm/bugs.c b/drivers/misc/lkdtm/bugs.c
index a4fdad04..de87693 100644
--- a/drivers/misc/lkdtm/bugs.c
+++ b/drivers/misc/lkdtm/bugs.c
@@ -278,7 +278,7 @@ void lkdtm_STACK_GUARD_PAGE_TRAILING(void)
void lkdtm_UNSET_SMEP(void)
{
-#ifdef CONFIG_X86_64
+#if IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_UML)
#define MOV_CR4_DEPTH 64
void (*direct_write_cr4)(unsigned long val);
unsigned char *insn;
@@ -338,13 +338,13 @@ void lkdtm_UNSET_SMEP(void)
native_write_cr4(cr4);
}
#else
- pr_err("FAIL: this test is x86_64-only\n");
+ pr_err("XFAIL: this test is x86_64-only\n");
#endif
}
-#ifdef CONFIG_X86_32
void lkdtm_DOUBLE_FAULT(void)
{
+#ifdef CONFIG_X86_32
/*
* Trigger #DF by setting the stack limit to zero. This clobbers
* a GDT TLS slot, which is okay because the current task will die
@@ -373,6 +373,8 @@ void lkdtm_DOUBLE_FAULT(void)
asm volatile ("movw %0, %%ss; addl $0, (%%esp)" ::
"r" ((unsigned short)(GDT_ENTRY_TLS_MIN << 3)));
- panic("tried to double fault but didn't die\n");
-}
+ pr_err("FAIL: tried to double fault but didn't die\n");
+#else
+ pr_err("XFAIL: this test is ia32-only\n");
#endif
+}
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index 7bc9505..403ac44 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -386,7 +386,7 @@ static void tegra_sdhci_reset(struct sdhci_host *host, u8 mask)
misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_DDR50;
if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR104)
misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR104;
- if (soc_data->nvquirks & SDHCI_MISC_CTRL_ENABLE_SDR50)
+ if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR50)
clk_ctrl |= SDHCI_CLOCK_CTRL_SDR50_TUNING_OVERRIDE;
}
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 1b1c26d..659a945 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -3913,11 +3913,13 @@ int sdhci_setup_host(struct sdhci_host *host)
if (host->ops->get_min_clock)
mmc->f_min = host->ops->get_min_clock(host);
else if (host->version >= SDHCI_SPEC_300) {
- if (host->clk_mul) {
- mmc->f_min = (host->max_clk * host->clk_mul) / 1024;
+ if (host->clk_mul)
max_clk = host->max_clk * host->clk_mul;
- } else
- mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300;
+ /*
+ * Divided Clock Mode minimum clock rate is always less than
+ * Programmable Clock Mode minimum clock rate.
+ */
+ mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300;
} else
mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_200;
diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c
index b8e897e..b8fe94f 100644
--- a/drivers/mmc/host/sdhci_am654.c
+++ b/drivers/mmc/host/sdhci_am654.c
@@ -240,28 +240,21 @@ static void sdhci_am654_write_b(struct sdhci_host *host, u8 val, int reg)
writeb(val, host->ioaddr + reg);
}
-static struct sdhci_ops sdhci_am654_ops = {
- .get_max_clock = sdhci_pltfm_clk_get_max_clock,
- .get_timeout_clock = sdhci_pltfm_clk_get_max_clock,
- .set_uhs_signaling = sdhci_set_uhs_signaling,
- .set_bus_width = sdhci_set_bus_width,
- .set_power = sdhci_am654_set_power,
- .set_clock = sdhci_am654_set_clock,
- .write_b = sdhci_am654_write_b,
- .reset = sdhci_reset,
-};
+static int sdhci_am654_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+ struct sdhci_host *host = mmc_priv(mmc);
+ int err = sdhci_execute_tuning(mmc, opcode);
-static const struct sdhci_pltfm_data sdhci_am654_pdata = {
- .ops = &sdhci_am654_ops,
- .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT |
- SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
- .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
-};
+ if (err)
+ return err;
+ /*
+ * Tuning data remains in the buffer after tuning.
+ * Do a command and data reset to get rid of it
+ */
+ sdhci_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA);
-static const struct sdhci_am654_driver_data sdhci_am654_drvdata = {
- .pdata = &sdhci_am654_pdata,
- .flags = IOMUX_PRESENT | FREQSEL_2_BIT | STRBSEL_4_BIT | DLL_PRESENT,
-};
+ return 0;
+}
static u32 sdhci_am654_cqhci_irq(struct sdhci_host *host, u32 intmask)
{
@@ -276,6 +269,29 @@ static u32 sdhci_am654_cqhci_irq(struct sdhci_host *host, u32 intmask)
return 0;
}
+static struct sdhci_ops sdhci_am654_ops = {
+ .get_max_clock = sdhci_pltfm_clk_get_max_clock,
+ .get_timeout_clock = sdhci_pltfm_clk_get_max_clock,
+ .set_uhs_signaling = sdhci_set_uhs_signaling,
+ .set_bus_width = sdhci_set_bus_width,
+ .set_power = sdhci_am654_set_power,
+ .set_clock = sdhci_am654_set_clock,
+ .write_b = sdhci_am654_write_b,
+ .irq = sdhci_am654_cqhci_irq,
+ .reset = sdhci_reset,
+};
+
+static const struct sdhci_pltfm_data sdhci_am654_pdata = {
+ .ops = &sdhci_am654_ops,
+ .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
+ .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+};
+
+static const struct sdhci_am654_driver_data sdhci_am654_drvdata = {
+ .pdata = &sdhci_am654_pdata,
+ .flags = IOMUX_PRESENT | FREQSEL_2_BIT | STRBSEL_4_BIT | DLL_PRESENT,
+};
+
static struct sdhci_ops sdhci_j721e_8bit_ops = {
.get_max_clock = sdhci_pltfm_clk_get_max_clock,
.get_timeout_clock = sdhci_pltfm_clk_get_max_clock,
@@ -290,8 +306,7 @@ static struct sdhci_ops sdhci_j721e_8bit_ops = {
static const struct sdhci_pltfm_data sdhci_j721e_8bit_pdata = {
.ops = &sdhci_j721e_8bit_ops,
- .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT |
- SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
+ .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
};
@@ -314,8 +329,7 @@ static struct sdhci_ops sdhci_j721e_4bit_ops = {
static const struct sdhci_pltfm_data sdhci_j721e_4bit_pdata = {
.ops = &sdhci_j721e_4bit_ops,
- .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT |
- SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
+ .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
};
@@ -549,6 +563,8 @@ static int sdhci_am654_probe(struct platform_device *pdev)
goto pm_runtime_put;
}
+ host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning;
+
ret = sdhci_am654_init(host);
if (ret)
goto pm_runtime_put;
diff --git a/drivers/mtd/nand/onenand/omap2.c b/drivers/mtd/nand/onenand/omap2.c
index edf94ee..aa9368b 100644
--- a/drivers/mtd/nand/onenand/omap2.c
+++ b/drivers/mtd/nand/onenand/omap2.c
@@ -148,13 +148,13 @@ static int omap2_onenand_wait(struct mtd_info *mtd, int state)
unsigned long timeout;
u32 syscfg;
- if (state == FL_RESETING || state == FL_PREPARING_ERASE ||
+ if (state == FL_RESETTING || state == FL_PREPARING_ERASE ||
state == FL_VERIFYING_ERASE) {
int i = 21;
unsigned int intr_flags = ONENAND_INT_MASTER;
switch (state) {
- case FL_RESETING:
+ case FL_RESETTING:
intr_flags |= ONENAND_INT_RESET;
break;
case FL_PREPARING_ERASE:
@@ -328,7 +328,8 @@ static inline int omap2_onenand_dma_transfer(struct omap2_onenand *c,
struct dma_async_tx_descriptor *tx;
dma_cookie_t cookie;
- tx = dmaengine_prep_dma_memcpy(c->dma_chan, dst, src, count, 0);
+ tx = dmaengine_prep_dma_memcpy(c->dma_chan, dst, src, count,
+ DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
if (!tx) {
dev_err(&c->pdev->dev, "Failed to prepare DMA memcpy\n");
return -EIO;
@@ -375,7 +376,7 @@ static int omap2_onenand_read_bufferram(struct mtd_info *mtd, int area,
* context fallback to PIO mode.
*/
if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 ||
- count < 384 || in_interrupt() || oops_in_progress )
+ count < 384 || in_interrupt() || oops_in_progress)
goto out_copy;
xtra = count & 3;
@@ -422,7 +423,7 @@ static int omap2_onenand_write_bufferram(struct mtd_info *mtd, int area,
* context fallback to PIO mode.
*/
if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 ||
- count < 384 || in_interrupt() || oops_in_progress )
+ count < 384 || in_interrupt() || oops_in_progress)
goto out_copy;
dma_src = dma_map_single(dev, buf, count, DMA_TO_DEVICE);
@@ -528,7 +529,8 @@ static int omap2_onenand_probe(struct platform_device *pdev)
c->gpmc_cs, c->phys_base, c->onenand.base,
c->dma_chan ? "DMA" : "PIO");
- if ((r = onenand_scan(&c->mtd, 1)) < 0)
+ r = onenand_scan(&c->mtd, 1);
+ if (r < 0)
goto err_release_dma;
freq = omap2_onenand_get_freq(c->onenand.version_id);
diff --git a/drivers/mtd/nand/onenand/onenand_base.c b/drivers/mtd/nand/onenand/onenand_base.c
index 77bd32a..85640ee 100644
--- a/drivers/mtd/nand/onenand/onenand_base.c
+++ b/drivers/mtd/nand/onenand/onenand_base.c
@@ -2853,7 +2853,7 @@ static int onenand_otp_write_oob_nolock(struct mtd_info *mtd, loff_t to,
/* Exit OTP access mode */
this->command(mtd, ONENAND_CMD_RESET, 0, 0);
- this->wait(mtd, FL_RESETING);
+ this->wait(mtd, FL_RESETTING);
status = this->read_word(this->base + ONENAND_REG_CTRL_STATUS);
status &= 0x60;
@@ -2924,7 +2924,7 @@ static int do_otp_read(struct mtd_info *mtd, loff_t from, size_t len,
/* Exit OTP access mode */
this->command(mtd, ONENAND_CMD_RESET, 0, 0);
- this->wait(mtd, FL_RESETING);
+ this->wait(mtd, FL_RESETTING);
return ret;
}
@@ -2968,7 +2968,7 @@ static int do_otp_write(struct mtd_info *mtd, loff_t to, size_t len,
/* Exit OTP access mode */
this->command(mtd, ONENAND_CMD_RESET, 0, 0);
- this->wait(mtd, FL_RESETING);
+ this->wait(mtd, FL_RESETTING);
return ret;
}
@@ -3008,7 +3008,7 @@ static int do_otp_lock(struct mtd_info *mtd, loff_t from, size_t len,
/* Exit OTP access mode */
this->command(mtd, ONENAND_CMD_RESET, 0, 0);
- this->wait(mtd, FL_RESETING);
+ this->wait(mtd, FL_RESETTING);
} else {
ops.mode = MTD_OPS_PLACE_OOB;
ops.ooblen = len;
@@ -3413,7 +3413,7 @@ static int flexonenand_get_boundary(struct mtd_info *mtd)
this->boundary[die] = bdry & FLEXONENAND_PI_MASK;
this->command(mtd, ONENAND_CMD_RESET, 0, 0);
- this->wait(mtd, FL_RESETING);
+ this->wait(mtd, FL_RESETTING);
printk(KERN_INFO "Die %d boundary: %d%s\n", die,
this->boundary[die], locked ? "(Locked)" : "(Unlocked)");
@@ -3635,7 +3635,7 @@ static int flexonenand_set_boundary(struct mtd_info *mtd, int die,
ret = this->wait(mtd, FL_WRITING);
out:
this->write_word(ONENAND_CMD_RESET, this->base + ONENAND_REG_COMMAND);
- this->wait(mtd, FL_RESETING);
+ this->wait(mtd, FL_RESETTING);
if (!ret)
/* Recalculate device size on boundary change*/
flexonenand_get_size(mtd);
@@ -3671,7 +3671,7 @@ static int onenand_chip_probe(struct mtd_info *mtd)
/* Reset OneNAND to read default register values */
this->write_word(ONENAND_CMD_RESET, this->base + ONENAND_BOOTRAM);
/* Wait reset */
- this->wait(mtd, FL_RESETING);
+ this->wait(mtd, FL_RESETTING);
/* Restore system configuration 1 */
this->write_word(syscfg, this->base + ONENAND_REG_SYS_CFG1);
diff --git a/drivers/mtd/nand/onenand/samsung_mtd.c b/drivers/mtd/nand/onenand/samsung_mtd.c
index 55e5536..beb7987 100644
--- a/drivers/mtd/nand/onenand/samsung_mtd.c
+++ b/drivers/mtd/nand/onenand/samsung_mtd.c
@@ -675,12 +675,12 @@ static int s5pc110_read_bufferram(struct mtd_info *mtd, int area,
normal:
if (count != mtd->writesize) {
/* Copy the bufferram to memory to prevent unaligned access */
- memcpy(this->page_buf, p, mtd->writesize);
- p = this->page_buf + offset;
+ memcpy_fromio(this->page_buf, p, mtd->writesize);
+ memcpy(buffer, this->page_buf + offset, count);
+ } else {
+ memcpy_fromio(buffer, p, count);
}
- memcpy(buffer, p, count);
-
return 0;
}
diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 3a36285..f6c7102 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -914,8 +914,8 @@ static void cadence_nand_get_caps(struct cdns_nand_ctrl *cdns_ctrl)
/* Prepare CDMA descriptor. */
static void
cadence_nand_cdma_desc_prepare(struct cdns_nand_ctrl *cdns_ctrl,
- char nf_mem, u32 flash_ptr, char *mem_ptr,
- char *ctrl_data_ptr, u16 ctype)
+ char nf_mem, u32 flash_ptr, dma_addr_t mem_ptr,
+ dma_addr_t ctrl_data_ptr, u16 ctype)
{
struct cadence_nand_cdma_desc *cdma_desc = cdns_ctrl->cdma_desc;
@@ -931,13 +931,13 @@ cadence_nand_cdma_desc_prepare(struct cdns_nand_ctrl *cdns_ctrl,
cdma_desc->command_flags |= CDMA_CF_DMA_MASTER;
cdma_desc->command_flags |= CDMA_CF_INT;
- cdma_desc->memory_pointer = (uintptr_t)mem_ptr;
+ cdma_desc->memory_pointer = mem_ptr;
cdma_desc->status = 0;
cdma_desc->sync_flag_pointer = 0;
cdma_desc->sync_arguments = 0;
cdma_desc->command_type = ctype;
- cdma_desc->ctrl_data_ptr = (uintptr_t)ctrl_data_ptr;
+ cdma_desc->ctrl_data_ptr = ctrl_data_ptr;
}
static u8 cadence_nand_check_desc_error(struct cdns_nand_ctrl *cdns_ctrl,
@@ -1280,8 +1280,7 @@ cadence_nand_cdma_transfer(struct cdns_nand_ctrl *cdns_ctrl, u8 chip_nr,
}
cadence_nand_cdma_desc_prepare(cdns_ctrl, chip_nr, page,
- (void *)dma_buf, (void *)dma_ctrl_dat,
- ctype);
+ dma_buf, dma_ctrl_dat, ctype);
status = cadence_nand_cdma_send_and_wait(cdns_ctrl, thread_nr);
@@ -1360,7 +1359,7 @@ static int cadence_nand_erase(struct nand_chip *chip, u32 page)
cadence_nand_cdma_desc_prepare(cdns_ctrl,
cdns_chip->cs[chip->cur_cs],
- page, NULL, NULL,
+ page, 0, 0,
CDMA_CT_ERASE);
status = cadence_nand_cdma_send_and_wait(cdns_ctrl, thread_nr);
if (status) {
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index 334fe31..b9d5d55 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -148,6 +148,10 @@ static int gpmi_init(struct gpmi_nand_data *this)
struct resources *r = &this->resources;
int ret;
+ ret = pm_runtime_get_sync(this->dev);
+ if (ret < 0)
+ return ret;
+
ret = gpmi_reset_block(r->gpmi_regs, false);
if (ret)
goto err_out;
@@ -179,8 +183,9 @@ static int gpmi_init(struct gpmi_nand_data *this)
*/
writel(BM_GPMI_CTRL1_DECOUPLE_CS, r->gpmi_regs + HW_GPMI_CTRL1_SET);
- return 0;
err_out:
+ pm_runtime_mark_last_busy(this->dev);
+ pm_runtime_put_autosuspend(this->dev);
return ret;
}
@@ -2722,6 +2727,10 @@ static int gpmi_pm_resume(struct device *dev)
return ret;
}
+ /* Set flag to get timing setup restored for next exec_op */
+ if (this->hw.clk_rate)
+ this->hw.must_apply_timings = true;
+
/* re-init the BCH registers */
ret = bch_set_geometry(this);
if (ret) {
diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index 9e63800..3ba73f1 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -37,6 +37,7 @@
/* Max ECC buffer length */
#define FMC2_MAX_ECC_BUF_LEN (FMC2_BCHDSRS_LEN * FMC2_MAX_SG)
+#define FMC2_TIMEOUT_US 1000
#define FMC2_TIMEOUT_MS 1000
/* Timings */
@@ -53,6 +54,8 @@
#define FMC2_PMEM 0x88
#define FMC2_PATT 0x8c
#define FMC2_HECCR 0x94
+#define FMC2_ISR 0x184
+#define FMC2_ICR 0x188
#define FMC2_CSQCR 0x200
#define FMC2_CSQCFGR1 0x204
#define FMC2_CSQCFGR2 0x208
@@ -118,6 +121,12 @@
#define FMC2_PATT_ATTHIZ(x) (((x) & 0xff) << 24)
#define FMC2_PATT_DEFAULT 0x0a0a0a0a
+/* Register: FMC2_ISR */
+#define FMC2_ISR_IHLF BIT(1)
+
+/* Register: FMC2_ICR */
+#define FMC2_ICR_CIHLF BIT(1)
+
/* Register: FMC2_CSQCR */
#define FMC2_CSQCR_CSQSTART BIT(0)
@@ -1322,6 +1331,31 @@ static void stm32_fmc2_write_data(struct nand_chip *chip, const void *buf,
stm32_fmc2_set_buswidth_16(fmc2, true);
}
+static int stm32_fmc2_waitrdy(struct nand_chip *chip, unsigned long timeout_ms)
+{
+ struct stm32_fmc2_nfc *fmc2 = to_stm32_nfc(chip->controller);
+ const struct nand_sdr_timings *timings;
+ u32 isr, sr;
+
+ /* Check if there is no pending requests to the NAND flash */
+ if (readl_relaxed_poll_timeout_atomic(fmc2->io_base + FMC2_SR, sr,
+ sr & FMC2_SR_NWRF, 1,
+ FMC2_TIMEOUT_US))
+ dev_warn(fmc2->dev, "Waitrdy timeout\n");
+
+ /* Wait tWB before R/B# signal is low */
+ timings = nand_get_sdr_timings(&chip->data_interface);
+ ndelay(PSEC_TO_NSEC(timings->tWB_max));
+
+ /* R/B# signal is low, clear high level flag */
+ writel_relaxed(FMC2_ICR_CIHLF, fmc2->io_base + FMC2_ICR);
+
+ /* Wait R/B# signal is high */
+ return readl_relaxed_poll_timeout_atomic(fmc2->io_base + FMC2_ISR,
+ isr, isr & FMC2_ISR_IHLF,
+ 5, 1000 * timeout_ms);
+}
+
static int stm32_fmc2_exec_op(struct nand_chip *chip,
const struct nand_operation *op,
bool check_only)
@@ -1366,8 +1400,8 @@ static int stm32_fmc2_exec_op(struct nand_chip *chip,
break;
case NAND_OP_WAITRDY_INSTR:
- ret = nand_soft_waitrdy(chip,
- instr->ctx.waitrdy.timeout_ms);
+ ret = stm32_fmc2_waitrdy(chip,
+ instr->ctx.waitrdy.timeout_ms);
break;
}
}
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index 4744bf9..b9f2724 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -247,7 +247,8 @@ static int sm_read_sector(struct sm_ftl *ftl,
/* FTL can contain -1 entries that are by default filled with bits */
if (block == -1) {
- memset(buffer, 0xFF, SM_SECTOR_SIZE);
+ if (buffer)
+ memset(buffer, 0xFF, SM_SECTOR_SIZE);
return 0;
}
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index f4afe12..b0cd443 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -2124,6 +2124,8 @@ static int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor)
if (nor->bouncebuf[0] & SR2_QUAD_EN_BIT1)
return 0;
+ nor->bouncebuf[0] |= SR2_QUAD_EN_BIT1;
+
return spi_nor_write_16bit_cr_and_check(nor, nor->bouncebuf[0]);
}
@@ -4596,6 +4598,7 @@ static void sst_set_default_init(struct spi_nor *nor)
static void st_micron_set_default_init(struct spi_nor *nor)
{
nor->flags |= SNOR_F_HAS_LOCK;
+ nor->flags &= ~SNOR_F_HAS_16BIT_SR;
nor->params.quad_enable = NULL;
nor->params.set_4byte = st_micron_set_4byte;
}
@@ -4768,9 +4771,7 @@ static void spi_nor_info_init_params(struct spi_nor *nor)
static void spansion_post_sfdp_fixups(struct spi_nor *nor)
{
- struct mtd_info *mtd = &nor->mtd;
-
- if (mtd->size <= SZ_16M)
+ if (nor->params.size <= SZ_16M)
return;
nor->flags |= SNOR_F_4B_OPCODES;
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 01e2657..dee7958 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -549,6 +549,8 @@
config NETDEVSIM
tristate "Simulated networking device"
depends on DEBUG_FS
+ depends on INET
+ depends on IPV6 || IPV6=n
select NET_DEVLINK
help
This driver is a developer testing tool and software model that can
diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c
index 4e1789e..eacd428 100644
--- a/drivers/net/can/m_can/tcan4x5x.c
+++ b/drivers/net/can/m_can/tcan4x5x.c
@@ -102,6 +102,7 @@
#define TCAN4X5X_MODE_NORMAL BIT(7)
#define TCAN4X5X_DISABLE_WAKE_MSK (BIT(31) | BIT(30))
+#define TCAN4X5X_DISABLE_INH_MSK BIT(9)
#define TCAN4X5X_SW_RESET BIT(2)
@@ -166,6 +167,28 @@ static void tcan4x5x_check_wake(struct tcan4x5x_priv *priv)
}
}
+static int tcan4x5x_reset(struct tcan4x5x_priv *priv)
+{
+ int ret = 0;
+
+ if (priv->reset_gpio) {
+ gpiod_set_value(priv->reset_gpio, 1);
+
+ /* tpulse_width minimum 30us */
+ usleep_range(30, 100);
+ gpiod_set_value(priv->reset_gpio, 0);
+ } else {
+ ret = regmap_write(priv->regmap, TCAN4X5X_CONFIG,
+ TCAN4X5X_SW_RESET);
+ if (ret)
+ return ret;
+ }
+
+ usleep_range(700, 1000);
+
+ return ret;
+}
+
static int regmap_spi_gather_write(void *context, const void *reg,
size_t reg_len, const void *val,
size_t val_len)
@@ -348,14 +371,23 @@ static int tcan4x5x_disable_wake(struct m_can_classdev *cdev)
TCAN4X5X_DISABLE_WAKE_MSK, 0x00);
}
+static int tcan4x5x_disable_state(struct m_can_classdev *cdev)
+{
+ struct tcan4x5x_priv *tcan4x5x = cdev->device_data;
+
+ return regmap_update_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG,
+ TCAN4X5X_DISABLE_INH_MSK, 0x01);
+}
+
static int tcan4x5x_parse_config(struct m_can_classdev *cdev)
{
struct tcan4x5x_priv *tcan4x5x = cdev->device_data;
+ int ret;
tcan4x5x->device_wake_gpio = devm_gpiod_get(cdev->dev, "device-wake",
GPIOD_OUT_HIGH);
if (IS_ERR(tcan4x5x->device_wake_gpio)) {
- if (PTR_ERR(tcan4x5x->power) == -EPROBE_DEFER)
+ if (PTR_ERR(tcan4x5x->device_wake_gpio) == -EPROBE_DEFER)
return -EPROBE_DEFER;
tcan4x5x_disable_wake(cdev);
@@ -366,18 +398,17 @@ static int tcan4x5x_parse_config(struct m_can_classdev *cdev)
if (IS_ERR(tcan4x5x->reset_gpio))
tcan4x5x->reset_gpio = NULL;
- usleep_range(700, 1000);
+ ret = tcan4x5x_reset(tcan4x5x);
+ if (ret)
+ return ret;
tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev,
"device-state",
GPIOD_IN);
- if (IS_ERR(tcan4x5x->device_state_gpio))
+ if (IS_ERR(tcan4x5x->device_state_gpio)) {
tcan4x5x->device_state_gpio = NULL;
-
- tcan4x5x->power = devm_regulator_get_optional(cdev->dev,
- "vsup");
- if (PTR_ERR(tcan4x5x->power) == -EPROBE_DEFER)
- return -EPROBE_DEFER;
+ tcan4x5x_disable_state(cdev);
+ }
return 0;
}
@@ -412,6 +443,12 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
if (!priv)
return -ENOMEM;
+ priv->power = devm_regulator_get_optional(&spi->dev, "vsup");
+ if (PTR_ERR(priv->power) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+ else
+ priv->power = NULL;
+
mcan_class->device_data = priv;
m_can_class_get_clocks(mcan_class);
@@ -451,11 +488,17 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
priv->regmap = devm_regmap_init(&spi->dev, &tcan4x5x_bus,
&spi->dev, &tcan4x5x_regmap);
- ret = tcan4x5x_parse_config(mcan_class);
+ ret = tcan4x5x_power_enable(priv->power, 1);
if (ret)
goto out_clk;
- tcan4x5x_power_enable(priv->power, 1);
+ ret = tcan4x5x_parse_config(mcan_class);
+ if (ret)
+ goto out_power;
+
+ ret = tcan4x5x_init(mcan_class);
+ if (ret)
+ goto out_power;
ret = m_can_class_register(mcan_class);
if (ret)
diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c
index 8caf7af..99101d7 100644
--- a/drivers/net/can/mscan/mscan.c
+++ b/drivers/net/can/mscan/mscan.c
@@ -381,13 +381,12 @@ static int mscan_rx_poll(struct napi_struct *napi, int quota)
struct net_device *dev = napi->dev;
struct mscan_regs __iomem *regs = priv->reg_base;
struct net_device_stats *stats = &dev->stats;
- int npackets = 0;
- int ret = 1;
+ int work_done = 0;
struct sk_buff *skb;
struct can_frame *frame;
u8 canrflg;
- while (npackets < quota) {
+ while (work_done < quota) {
canrflg = in_8(®s->canrflg);
if (!(canrflg & (MSCAN_RXF | MSCAN_ERR_IF)))
break;
@@ -408,18 +407,18 @@ static int mscan_rx_poll(struct napi_struct *napi, int quota)
stats->rx_packets++;
stats->rx_bytes += frame->can_dlc;
- npackets++;
+ work_done++;
netif_receive_skb(skb);
}
- if (!(in_8(®s->canrflg) & (MSCAN_RXF | MSCAN_ERR_IF))) {
- napi_complete(&priv->napi);
- clear_bit(F_RX_PROGRESS, &priv->flags);
- if (priv->can.state < CAN_STATE_BUS_OFF)
- out_8(®s->canrier, priv->shadow_canrier);
- ret = 0;
+ if (work_done < quota) {
+ if (likely(napi_complete_done(&priv->napi, work_done))) {
+ clear_bit(F_RX_PROGRESS, &priv->flags);
+ if (priv->can.state < CAN_STATE_BUS_OFF)
+ out_8(®s->canrier, priv->shadow_canrier);
+ }
}
- return ret;
+ return work_done;
}
static irqreturn_t mscan_isr(int irq, void *dev_id)
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 2e57122..2f5c287 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -344,9 +344,16 @@ static void slcan_transmit(struct work_struct *work)
*/
static void slcan_write_wakeup(struct tty_struct *tty)
{
- struct slcan *sl = tty->disc_data;
+ struct slcan *sl;
+
+ rcu_read_lock();
+ sl = rcu_dereference(tty->disc_data);
+ if (!sl)
+ goto out;
schedule_work(&sl->tx_work);
+out:
+ rcu_read_unlock();
}
/* Send a can_frame to a TTY queue. */
@@ -644,10 +651,11 @@ static void slcan_close(struct tty_struct *tty)
return;
spin_lock_bh(&sl->lock);
- tty->disc_data = NULL;
+ rcu_assign_pointer(tty->disc_data, NULL);
sl->tty = NULL;
spin_unlock_bh(&sl->lock);
+ synchronize_rcu();
flush_work(&sl->tx_work);
/* Flush network side */
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 2f74f670..a4b4b742 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -918,7 +918,7 @@ static int gs_usb_probe(struct usb_interface *intf,
GS_USB_BREQ_HOST_FORMAT,
USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
1,
- intf->altsetting[0].desc.bInterfaceNumber,
+ intf->cur_altsetting->desc.bInterfaceNumber,
hconf,
sizeof(*hconf),
1000);
@@ -941,7 +941,7 @@ static int gs_usb_probe(struct usb_interface *intf,
GS_USB_BREQ_DEVICE_CONFIG,
USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
1,
- intf->altsetting[0].desc.bInterfaceNumber,
+ intf->cur_altsetting->desc.bInterfaceNumber,
dconf,
sizeof(*dconf),
1000);
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index 5fc0be5..7ab87a7 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -1590,7 +1590,7 @@ static int kvaser_usb_hydra_setup_endpoints(struct kvaser_usb *dev)
struct usb_endpoint_descriptor *ep;
int i;
- iface_desc = &dev->intf->altsetting[0];
+ iface_desc = dev->intf->cur_altsetting;
for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
ep = &iface_desc->endpoint[i].desc;
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index ae4c37e..1b9957f1 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -1310,7 +1310,7 @@ static int kvaser_usb_leaf_setup_endpoints(struct kvaser_usb *dev)
struct usb_endpoint_descriptor *endpoint;
int i;
- iface_desc = &dev->intf->altsetting[0];
+ iface_desc = dev->intf->cur_altsetting;
for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
endpoint = &iface_desc->endpoint[i].desc;
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index cbd74a7..2d38dbc 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -105,7 +105,6 @@
config NET_DSA_VITESSE_VSC73XX
tristate
- depends on OF
depends on NET_DSA
select FIXED_PHY
select VITESSE_PHY
@@ -116,7 +115,6 @@
config NET_DSA_VITESSE_VSC73XX_SPI
tristate "Vitesse VSC7385/7388/7395/7398 SPI mode support"
- depends on OF
depends on NET_DSA
depends on SPI
select NET_DSA_VITESSE_VSC73XX
@@ -126,7 +124,6 @@
config NET_DSA_VITESSE_VSC73XX_PLATFORM
tristate "Vitesse VSC7385/7388/7395/7398 Platform mode support"
- depends on OF
depends on NET_DSA
depends on HAS_IOMEM
select NET_DSA_VITESSE_VSC73XX
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index edacacf..0604975 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -371,8 +371,6 @@ static void b53_enable_vlan(struct b53_device *dev, bool enable,
b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, &vc5);
}
- mgmt &= ~SM_SW_FWD_MODE;
-
if (enable) {
vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID;
vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN;
@@ -573,9 +571,8 @@ EXPORT_SYMBOL(b53_disable_port);
void b53_brcm_hdr_setup(struct dsa_switch *ds, int port)
{
- bool tag_en = !(ds->ops->get_tag_protocol(ds, port) ==
- DSA_TAG_PROTO_NONE);
struct b53_device *dev = ds->priv;
+ bool tag_en = !(dev->tag_protocol == DSA_TAG_PROTO_NONE);
u8 hdr_ctl, val;
u16 reg;
@@ -595,6 +592,22 @@ void b53_brcm_hdr_setup(struct dsa_switch *ds, int port)
break;
}
+ /* Enable management mode if tagging is requested */
+ b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &hdr_ctl);
+ if (tag_en)
+ hdr_ctl |= SM_SW_FWD_MODE;
+ else
+ hdr_ctl &= ~SM_SW_FWD_MODE;
+ b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, hdr_ctl);
+
+ /* Configure the appropriate IMP port */
+ b53_read8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, &hdr_ctl);
+ if (port == 8)
+ hdr_ctl |= GC_FRM_MGMT_PORT_MII;
+ else if (port == 5)
+ hdr_ctl |= GC_FRM_MGMT_PORT_M;
+ b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, hdr_ctl);
+
/* Enable Broadcom tags for IMP port */
b53_read8(dev, B53_MGMT_PAGE, B53_BRCM_HDR, &hdr_ctl);
if (tag_en)
@@ -1866,36 +1879,57 @@ static bool b53_possible_cpu_port(struct dsa_switch *ds, int port)
return false;
}
-static bool b53_can_enable_brcm_tags(struct dsa_switch *ds, int port)
+static bool b53_can_enable_brcm_tags(struct dsa_switch *ds, int port,
+ enum dsa_tag_protocol tag_protocol)
{
bool ret = b53_possible_cpu_port(ds, port);
- if (!ret)
+ if (!ret) {
dev_warn(ds->dev, "Port %d is not Broadcom tag capable\n",
port);
+ return ret;
+ }
+
+ switch (tag_protocol) {
+ case DSA_TAG_PROTO_BRCM:
+ case DSA_TAG_PROTO_BRCM_PREPEND:
+ dev_warn(ds->dev,
+ "Port %d is stacked to Broadcom tag switch\n", port);
+ ret = false;
+ break;
+ default:
+ ret = true;
+ break;
+ }
+
return ret;
}
-enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port)
+enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port,
+ enum dsa_tag_protocol mprot)
{
struct b53_device *dev = ds->priv;
/* Older models (5325, 5365) support a different tag format that we do
- * not support in net/dsa/tag_brcm.c yet. 539x and 531x5 require managed
- * mode to be turned on which means we need to specifically manage ARL
- * misses on multicast addresses (TBD).
+ * not support in net/dsa/tag_brcm.c yet.
*/
- if (is5325(dev) || is5365(dev) || is539x(dev) || is531x5(dev) ||
- !b53_can_enable_brcm_tags(ds, port))
- return DSA_TAG_PROTO_NONE;
+ if (is5325(dev) || is5365(dev) ||
+ !b53_can_enable_brcm_tags(ds, port, mprot)) {
+ dev->tag_protocol = DSA_TAG_PROTO_NONE;
+ goto out;
+ }
/* Broadcom BCM58xx chips have a flow accelerator on Port 8
* which requires us to use the prepended Broadcom tag type
*/
- if (dev->chip_id == BCM58XX_DEVICE_ID && port == B53_CPU_PORT)
- return DSA_TAG_PROTO_BRCM_PREPEND;
+ if (dev->chip_id == BCM58XX_DEVICE_ID && port == B53_CPU_PORT) {
+ dev->tag_protocol = DSA_TAG_PROTO_BRCM_PREPEND;
+ goto out;
+ }
- return DSA_TAG_PROTO_BRCM;
+ dev->tag_protocol = DSA_TAG_PROTO_BRCM;
+out:
+ return dev->tag_protocol;
}
EXPORT_SYMBOL(b53_get_tag_protocol);
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 1877acf..3c30f3a 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -118,6 +118,7 @@ struct b53_device {
u8 jumbo_size_reg;
int reset_gpio;
u8 num_arl_entries;
+ enum dsa_tag_protocol tag_protocol;
/* used ports mask */
u16 enabled_ports;
@@ -359,7 +360,8 @@ int b53_mdb_del(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_mdb *mdb);
int b53_mirror_add(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror, bool ingress);
-enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port);
+enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port,
+ enum dsa_tag_protocol mprot);
void b53_mirror_del(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror);
int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index e43040c..3e86353 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -68,7 +68,7 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
/* Force link status for IMP port */
reg = core_readl(priv, offset);
- reg |= (MII_SW_OR | LINK_STS);
+ reg |= (MII_SW_OR | LINK_STS | GMII_SPEED_UP_2G);
core_writel(priv, reg, offset);
/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index c8d7ef2..fdcb70b 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -61,7 +61,8 @@ struct dsa_loop_priv {
static struct phy_device *phydevs[PHY_MAX_ADDR];
static enum dsa_tag_protocol dsa_loop_get_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol mp)
{
dev_dbg(ds->dev, "%s: port: %d\n", __func__, port);
diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c
index e3c333a..cc17a44 100644
--- a/drivers/net/dsa/lan9303-core.c
+++ b/drivers/net/dsa/lan9303-core.c
@@ -883,7 +883,8 @@ static int lan9303_check_device(struct lan9303 *chip)
/* ---------------------------- DSA -----------------------------------*/
static enum dsa_tag_protocol lan9303_get_tag_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol mp)
{
return DSA_TAG_PROTO_LAN9303;
}
diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 9553249..0369c22 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -841,7 +841,8 @@ static int gswip_setup(struct dsa_switch *ds)
}
static enum dsa_tag_protocol gswip_get_tag_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol mp)
{
return DSA_TAG_PROTO_GSWIP;
}
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 24a5e99..47d65b7 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -645,7 +645,8 @@ static void ksz8795_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
}
static enum dsa_tag_protocol ksz8795_get_tag_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol mp)
{
return DSA_TAG_PROTO_KSZ8795;
}
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 50ffc63..9a51b8a 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -295,7 +295,8 @@ static void ksz9477_port_init_cnt(struct ksz_device *dev, int port)
}
static enum dsa_tag_protocol ksz9477_get_tag_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol mp)
{
enum dsa_tag_protocol proto = DSA_TAG_PROTO_KSZ9477;
struct ksz_device *dev = ds->priv;
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index ed1ec10..022466c 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -1223,7 +1223,8 @@ mt7530_port_vlan_del(struct dsa_switch *ds, int port,
}
static enum dsa_tag_protocol
-mtk_get_tag_protocol(struct dsa_switch *ds, int port)
+mtk_get_tag_protocol(struct dsa_switch *ds, int port,
+ enum dsa_tag_protocol mp)
{
struct mt7530_priv *priv = ds->priv;
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index a5a37f4..24b8219 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -43,7 +43,8 @@ static const char *mv88e6060_get_name(struct mii_bus *bus, int sw_addr)
}
static enum dsa_tag_protocol mv88e6060_get_tag_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol m)
{
return DSA_TAG_PROTO_TRAILER;
}
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 5eeeb65..8c92895 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -340,11 +340,14 @@ static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip)
*/
irq_set_lockdep_class(chip->irq, &lock_key, &request_key);
+ snprintf(chip->irq_name, sizeof(chip->irq_name),
+ "mv88e6xxx-%s", dev_name(chip->dev));
+
mv88e6xxx_reg_unlock(chip);
err = request_threaded_irq(chip->irq, NULL,
mv88e6xxx_g1_irq_thread_fn,
IRQF_ONESHOT | IRQF_SHARED,
- dev_name(chip->dev), chip);
+ chip->irq_name, chip);
mv88e6xxx_reg_lock(chip);
if (err)
mv88e6xxx_g1_irq_free_common(chip);
@@ -2303,10 +2306,14 @@ static int mv88e6xxx_serdes_irq_request(struct mv88e6xxx_chip *chip, int port,
if (!irq)
return 0;
+ snprintf(dev_id->serdes_irq_name, sizeof(dev_id->serdes_irq_name),
+ "mv88e6xxx-%s-serdes-%d", dev_name(chip->dev), port);
+
/* Requesting the IRQ will trigger IRQ callbacks, so release the lock */
mv88e6xxx_reg_unlock(chip);
err = request_threaded_irq(irq, NULL, mv88e6xxx_serdes_irq_thread_fn,
- IRQF_ONESHOT, "mv88e6xxx-serdes", dev_id);
+ IRQF_ONESHOT, dev_id->serdes_irq_name,
+ dev_id);
mv88e6xxx_reg_lock(chip);
if (err)
return err;
@@ -3838,6 +3845,9 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
.serdes_irq_enable = mv88e6390_serdes_irq_enable,
.serdes_irq_status = mv88e6390_serdes_irq_status,
+ .serdes_get_strings = mv88e6390_serdes_get_strings,
+ .serdes_get_stats = mv88e6390_serdes_get_stats,
+ .phylink_validate = mv88e6390_phylink_validate,
.gpio_ops = &mv88e6352_gpio_ops,
.phylink_validate = mv88e6390_phylink_validate,
};
@@ -3889,6 +3899,9 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
.serdes_irq_enable = mv88e6390_serdes_irq_enable,
.serdes_irq_status = mv88e6390_serdes_irq_status,
+ .serdes_get_strings = mv88e6390_serdes_get_strings,
+ .serdes_get_stats = mv88e6390_serdes_get_stats,
+ .phylink_validate = mv88e6390_phylink_validate,
.gpio_ops = &mv88e6352_gpio_ops,
.phylink_validate = mv88e6390x_phylink_validate,
};
@@ -3939,6 +3952,9 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
.serdes_irq_enable = mv88e6390_serdes_irq_enable,
.serdes_irq_status = mv88e6390_serdes_irq_status,
+ .serdes_get_strings = mv88e6390_serdes_get_strings,
+ .serdes_get_stats = mv88e6390_serdes_get_stats,
+ .phylink_validate = mv88e6390_phylink_validate,
.avb_ops = &mv88e6390_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
.phylink_validate = mv88e6390_phylink_validate,
@@ -4085,6 +4101,9 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
.serdes_irq_enable = mv88e6390_serdes_irq_enable,
.serdes_irq_status = mv88e6390_serdes_irq_status,
+ .serdes_get_strings = mv88e6390_serdes_get_strings,
+ .serdes_get_stats = mv88e6390_serdes_get_stats,
+ .phylink_validate = mv88e6390_phylink_validate,
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6390_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
@@ -4479,6 +4498,9 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
.serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
.serdes_irq_enable = mv88e6390_serdes_irq_enable,
.serdes_irq_status = mv88e6390_serdes_irq_status,
+ .serdes_get_sset_count = mv88e6390_serdes_get_sset_count,
+ .serdes_get_strings = mv88e6390_serdes_get_strings,
+ .serdes_get_stats = mv88e6390_serdes_get_stats,
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6390_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
@@ -5210,7 +5232,8 @@ static struct mv88e6xxx_chip *mv88e6xxx_alloc_chip(struct device *dev)
}
static enum dsa_tag_protocol mv88e6xxx_get_tag_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol m)
{
struct mv88e6xxx_chip *chip = ds->priv;
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 8a8e38b..f332cb4 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -236,6 +236,7 @@ struct mv88e6xxx_port {
bool mirror_ingress;
bool mirror_egress;
unsigned int serdes_irq;
+ char serdes_irq_name[32];
};
struct mv88e6xxx_chip {
@@ -292,11 +293,16 @@ struct mv88e6xxx_chip {
struct mv88e6xxx_irq g1_irq;
struct mv88e6xxx_irq g2_irq;
int irq;
+ char irq_name[32];
int device_irq;
+ char device_irq_name[32];
int watchdog_irq;
+ char watchdog_irq_name[32];
int atu_prob_irq;
+ char atu_prob_irq_name[32];
int vtu_prob_irq;
+ char vtu_prob_irq_name[32];
struct kthread_worker *kworker;
struct kthread_delayed_work irq_poll_work;
diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index 120a65d..b016cc2 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -360,6 +360,11 @@ int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port)
{
u16 ptr = MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST;
+ /* Use the default high priority for management frames sent to
+ * the CPU.
+ */
+ port |= MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI;
+
return mv88e6390_g1_monitor_write(chip, ptr, port);
}
diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h
index bc5a6b2..5324c6f4 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.h
+++ b/drivers/net/dsa/mv88e6xxx/global1.h
@@ -211,6 +211,7 @@
#define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_INGRESS_DEST 0x2000
#define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_EGRESS_DEST 0x2100
#define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST 0x3000
+#define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI 0x00e0
#define MV88E6390_G1_MONITOR_MGMT_CTL_DATA_MASK 0x00ff
/* Offset 0x1C: Global Control 2 */
diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c
index bdcd255..bac9a8a 100644
--- a/drivers/net/dsa/mv88e6xxx/global1_atu.c
+++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c
@@ -425,9 +425,12 @@ int mv88e6xxx_g1_atu_prob_irq_setup(struct mv88e6xxx_chip *chip)
if (chip->atu_prob_irq < 0)
return chip->atu_prob_irq;
+ snprintf(chip->atu_prob_irq_name, sizeof(chip->atu_prob_irq_name),
+ "mv88e6xxx-%s-g1-atu-prob", dev_name(chip->dev));
+
err = request_threaded_irq(chip->atu_prob_irq, NULL,
mv88e6xxx_g1_atu_prob_irq_thread_fn,
- IRQF_ONESHOT, "mv88e6xxx-g1-atu-prob",
+ IRQF_ONESHOT, chip->atu_prob_irq_name,
chip);
if (err)
irq_dispose_mapping(chip->atu_prob_irq);
diff --git a/drivers/net/dsa/mv88e6xxx/global1_vtu.c b/drivers/net/dsa/mv88e6xxx/global1_vtu.c
index 33056a6..48390b7 100644
--- a/drivers/net/dsa/mv88e6xxx/global1_vtu.c
+++ b/drivers/net/dsa/mv88e6xxx/global1_vtu.c
@@ -631,9 +631,12 @@ int mv88e6xxx_g1_vtu_prob_irq_setup(struct mv88e6xxx_chip *chip)
if (chip->vtu_prob_irq < 0)
return chip->vtu_prob_irq;
+ snprintf(chip->vtu_prob_irq_name, sizeof(chip->vtu_prob_irq_name),
+ "mv88e6xxx-%s-g1-vtu-prob", dev_name(chip->dev));
+
err = request_threaded_irq(chip->vtu_prob_irq, NULL,
mv88e6xxx_g1_vtu_prob_irq_thread_fn,
- IRQF_ONESHOT, "mv88e6xxx-g1-vtu-prob",
+ IRQF_ONESHOT, chip->vtu_prob_irq_name,
chip);
if (err)
irq_dispose_mapping(chip->vtu_prob_irq);
diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index 87bfe7c..0150301 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -948,10 +948,13 @@ static int mv88e6xxx_g2_watchdog_setup(struct mv88e6xxx_chip *chip)
if (chip->watchdog_irq < 0)
return chip->watchdog_irq;
+ snprintf(chip->watchdog_irq_name, sizeof(chip->watchdog_irq_name),
+ "mv88e6xxx-%s-watchdog", dev_name(chip->dev));
+
err = request_threaded_irq(chip->watchdog_irq, NULL,
mv88e6xxx_g2_watchdog_thread_fn,
IRQF_ONESHOT | IRQF_TRIGGER_FALLING,
- "mv88e6xxx-watchdog", chip);
+ chip->watchdog_irq_name, chip);
if (err)
return err;
@@ -1114,9 +1117,12 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
goto out;
}
+ snprintf(chip->device_irq_name, sizeof(chip->device_irq_name),
+ "mv88e6xxx-%s-g2", dev_name(chip->dev));
+
err = request_threaded_irq(chip->device_irq, NULL,
mv88e6xxx_g2_irq_thread_fn,
- IRQF_ONESHOT, "mv88e6xxx-g2", chip);
+ IRQF_ONESHOT, chip->device_irq_name, chip);
if (err)
goto out;
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 7fe256c..0b43c65 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -393,7 +393,7 @@ phy_interface_t mv88e6390x_port_max_speed_mode(int port)
}
static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
- phy_interface_t mode)
+ phy_interface_t mode, bool force)
{
u8 lane;
u16 cmode;
@@ -427,8 +427,8 @@ static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
cmode = 0;
}
- /* cmode doesn't change, nothing to do for us */
- if (cmode == chip->ports[port].cmode)
+ /* cmode doesn't change, nothing to do for us unless forced */
+ if (cmode == chip->ports[port].cmode && !force)
return 0;
lane = mv88e6xxx_serdes_get_lane(chip, port);
@@ -484,7 +484,7 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
if (port != 9 && port != 10)
return -EOPNOTSUPP;
- return mv88e6xxx_port_set_cmode(chip, port, mode);
+ return mv88e6xxx_port_set_cmode(chip, port, mode, false);
}
int mv88e6390_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
@@ -504,7 +504,7 @@ int mv88e6390_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
break;
}
- return mv88e6xxx_port_set_cmode(chip, port, mode);
+ return mv88e6xxx_port_set_cmode(chip, port, mode, false);
}
static int mv88e6341_port_set_cmode_writable(struct mv88e6xxx_chip *chip,
@@ -555,7 +555,7 @@ int mv88e6341_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
if (err)
return err;
- return mv88e6xxx_port_set_cmode(chip, port, mode);
+ return mv88e6xxx_port_set_cmode(chip, port, mode, true);
}
int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig
index 6f98040..a5b7cca 100644
--- a/drivers/net/dsa/ocelot/Kconfig
+++ b/drivers/net/dsa/ocelot/Kconfig
@@ -3,8 +3,10 @@
tristate "Ocelot / Felix Ethernet switch support"
depends on NET_DSA && PCI
depends on NET_VENDOR_MICROSEMI
+ depends on NET_VENDOR_FREESCALE
select MSCC_OCELOT_SWITCH
select NET_DSA_TAG_OCELOT
+ select FSL_ENETC_MDIO
help
This driver supports the VSC9959 network switch, which is a member of
the Vitesse / Microsemi / Microchip Ocelot family of switching cores.
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index b7f9246..3257962 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -2,16 +2,22 @@
/* Copyright 2019 NXP Semiconductors
*/
#include <uapi/linux/if_bridge.h>
+#include <soc/mscc/ocelot_qsys.h>
+#include <soc/mscc/ocelot_sys.h>
+#include <soc/mscc/ocelot_dev.h>
+#include <soc/mscc/ocelot_ana.h>
#include <soc/mscc/ocelot.h>
#include <linux/packing.h>
#include <linux/module.h>
+#include <linux/of_net.h>
#include <linux/pci.h>
#include <linux/of.h>
#include <net/dsa.h>
#include "felix.h"
static enum dsa_tag_protocol felix_get_tag_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol mp)
{
return DSA_TAG_PROTO_OCELOT;
}
@@ -26,14 +32,6 @@ static int felix_set_ageing_time(struct dsa_switch *ds,
return 0;
}
-static void felix_adjust_link(struct dsa_switch *ds, int port,
- struct phy_device *phydev)
-{
- struct ocelot *ocelot = ds->priv;
-
- ocelot_adjust_link(ocelot, port, phydev);
-}
-
static int felix_fdb_dump(struct dsa_switch *ds, int port,
dsa_fdb_dump_cb_t *cb, void *data)
{
@@ -155,6 +153,141 @@ static void felix_port_disable(struct dsa_switch *ds, int port)
return ocelot_port_disable(ocelot, port);
}
+static void felix_phylink_validate(struct dsa_switch *ds, int port,
+ unsigned long *supported,
+ struct phylink_link_state *state)
+{
+ struct ocelot *ocelot = ds->priv;
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+
+ if (state->interface != PHY_INTERFACE_MODE_NA &&
+ state->interface != ocelot_port->phy_mode) {
+ bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+ return;
+ }
+
+ /* No half-duplex. */
+ phylink_set_port_modes(mask);
+ phylink_set(mask, Autoneg);
+ phylink_set(mask, Pause);
+ phylink_set(mask, Asym_Pause);
+ phylink_set(mask, 10baseT_Full);
+ phylink_set(mask, 100baseT_Full);
+ phylink_set(mask, 1000baseT_Full);
+
+ /* The internal ports that run at 2.5G are overclocked GMII */
+ if (state->interface == PHY_INTERFACE_MODE_GMII ||
+ state->interface == PHY_INTERFACE_MODE_2500BASEX ||
+ state->interface == PHY_INTERFACE_MODE_USXGMII) {
+ phylink_set(mask, 2500baseT_Full);
+ phylink_set(mask, 2500baseX_Full);
+ }
+
+ bitmap_and(supported, supported, mask,
+ __ETHTOOL_LINK_MODE_MASK_NBITS);
+ bitmap_and(state->advertising, state->advertising, mask,
+ __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
+static int felix_phylink_mac_pcs_get_state(struct dsa_switch *ds, int port,
+ struct phylink_link_state *state)
+{
+ struct ocelot *ocelot = ds->priv;
+ struct felix *felix = ocelot_to_felix(ocelot);
+
+ if (felix->info->pcs_link_state)
+ felix->info->pcs_link_state(ocelot, port, state);
+
+ return 0;
+}
+
+static void felix_phylink_mac_config(struct dsa_switch *ds, int port,
+ unsigned int link_an_mode,
+ const struct phylink_link_state *state)
+{
+ struct ocelot *ocelot = ds->priv;
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
+ struct felix *felix = ocelot_to_felix(ocelot);
+ u32 mac_fc_cfg;
+
+ /* Take port out of reset by clearing the MAC_TX_RST, MAC_RX_RST and
+ * PORT_RST bits in CLOCK_CFG
+ */
+ ocelot_port_writel(ocelot_port, DEV_CLOCK_CFG_LINK_SPEED(state->speed),
+ DEV_CLOCK_CFG);
+
+ /* Flow control. Link speed is only used here to evaluate the time
+ * specification in incoming pause frames.
+ */
+ mac_fc_cfg = SYS_MAC_FC_CFG_FC_LINK_SPEED(state->speed);
+
+ /* handle Rx pause in all cases, with 2500base-X this is used for rate
+ * adaptation.
+ */
+ mac_fc_cfg |= SYS_MAC_FC_CFG_RX_FC_ENA;
+
+ if (state->pause & MLO_PAUSE_TX)
+ mac_fc_cfg |= SYS_MAC_FC_CFG_TX_FC_ENA |
+ SYS_MAC_FC_CFG_PAUSE_VAL_CFG(0xffff) |
+ SYS_MAC_FC_CFG_FC_LATENCY_CFG(0x7) |
+ SYS_MAC_FC_CFG_ZERO_PAUSE_ENA;
+ ocelot_write_rix(ocelot, mac_fc_cfg, SYS_MAC_FC_CFG, port);
+
+ ocelot_write_rix(ocelot, 0, ANA_POL_FLOWC, port);
+
+ if (felix->info->pcs_init)
+ felix->info->pcs_init(ocelot, port, link_an_mode, state);
+}
+
+static void felix_phylink_mac_an_restart(struct dsa_switch *ds, int port)
+{
+ struct ocelot *ocelot = ds->priv;
+ struct felix *felix = ocelot_to_felix(ocelot);
+
+ if (felix->info->pcs_an_restart)
+ felix->info->pcs_an_restart(ocelot, port);
+}
+
+static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port,
+ unsigned int link_an_mode,
+ phy_interface_t interface)
+{
+ struct ocelot *ocelot = ds->priv;
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
+
+ ocelot_port_writel(ocelot_port, 0, DEV_MAC_ENA_CFG);
+ ocelot_rmw_rix(ocelot, 0, QSYS_SWITCH_PORT_MODE_PORT_ENA,
+ QSYS_SWITCH_PORT_MODE, port);
+}
+
+static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port,
+ unsigned int link_an_mode,
+ phy_interface_t interface,
+ struct phy_device *phydev)
+{
+ struct ocelot *ocelot = ds->priv;
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
+
+ /* Enable MAC module */
+ ocelot_port_writel(ocelot_port, DEV_MAC_ENA_CFG_RX_ENA |
+ DEV_MAC_ENA_CFG_TX_ENA, DEV_MAC_ENA_CFG);
+
+ /* Enable receiving frames on the port, and activate auto-learning of
+ * MAC addresses.
+ */
+ ocelot_write_gix(ocelot, ANA_PORT_PORT_CFG_LEARNAUTO |
+ ANA_PORT_PORT_CFG_RECV_ENA |
+ ANA_PORT_PORT_CFG_PORTID_VAL(port),
+ ANA_PORT_PORT_CFG, port);
+
+ /* Core: Enable port for frame transfer */
+ ocelot_write_rix(ocelot, QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE |
+ QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(1) |
+ QSYS_SWITCH_PORT_MODE_PORT_ENA,
+ QSYS_SWITCH_PORT_MODE, port);
+}
+
static void felix_get_strings(struct dsa_switch *ds, int port,
u32 stringset, u8 *data)
{
@@ -185,10 +318,76 @@ static int felix_get_ts_info(struct dsa_switch *ds, int port,
return ocelot_get_ts_info(ocelot, port, info);
}
+static int felix_parse_ports_node(struct felix *felix,
+ struct device_node *ports_node,
+ phy_interface_t *port_phy_modes)
+{
+ struct ocelot *ocelot = &felix->ocelot;
+ struct device *dev = felix->ocelot.dev;
+ struct device_node *child;
+
+ for_each_available_child_of_node(ports_node, child) {
+ phy_interface_t phy_mode;
+ u32 port;
+ int err;
+
+ /* Get switch port number from DT */
+ if (of_property_read_u32(child, "reg", &port) < 0) {
+ dev_err(dev, "Port number not defined in device tree "
+ "(property \"reg\")\n");
+ of_node_put(child);
+ return -ENODEV;
+ }
+
+ /* Get PHY mode from DT */
+ err = of_get_phy_mode(child, &phy_mode);
+ if (err) {
+ dev_err(dev, "Failed to read phy-mode or "
+ "phy-interface-type property for port %d\n",
+ port);
+ of_node_put(child);
+ return -ENODEV;
+ }
+
+ err = felix->info->prevalidate_phy_mode(ocelot, port, phy_mode);
+ if (err < 0) {
+ dev_err(dev, "Unsupported PHY mode %s on port %d\n",
+ phy_modes(phy_mode), port);
+ return err;
+ }
+
+ port_phy_modes[port] = phy_mode;
+ }
+
+ return 0;
+}
+
+static int felix_parse_dt(struct felix *felix, phy_interface_t *port_phy_modes)
+{
+ struct device *dev = felix->ocelot.dev;
+ struct device_node *switch_node;
+ struct device_node *ports_node;
+ int err;
+
+ switch_node = dev->of_node;
+
+ ports_node = of_get_child_by_name(switch_node, "ports");
+ if (!ports_node) {
+ dev_err(dev, "Incorrect bindings: absent \"ports\" node\n");
+ return -ENODEV;
+ }
+
+ err = felix_parse_ports_node(felix, ports_node, port_phy_modes);
+ of_node_put(ports_node);
+
+ return err;
+}
+
static int felix_init_structs(struct felix *felix, int num_phys_ports)
{
struct ocelot *ocelot = &felix->ocelot;
- resource_size_t base;
+ phy_interface_t *port_phy_modes;
+ resource_size_t switch_base;
int port, i, err;
ocelot->num_phys_ports = num_phys_ports;
@@ -203,7 +402,19 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
ocelot->shared_queue_sz = felix->info->shared_queue_sz;
ocelot->ops = felix->info->ops;
- base = pci_resource_start(felix->pdev, felix->info->pci_bar);
+ port_phy_modes = kcalloc(num_phys_ports, sizeof(phy_interface_t),
+ GFP_KERNEL);
+ if (!port_phy_modes)
+ return -ENOMEM;
+
+ err = felix_parse_dt(felix, port_phy_modes);
+ if (err) {
+ kfree(port_phy_modes);
+ return err;
+ }
+
+ switch_base = pci_resource_start(felix->pdev,
+ felix->info->switch_pci_bar);
for (i = 0; i < TARGET_MAX; i++) {
struct regmap *target;
@@ -214,13 +425,14 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
res = &felix->info->target_io_res[i];
res->flags = IORESOURCE_MEM;
- res->start += base;
- res->end += base;
+ res->start += switch_base;
+ res->end += switch_base;
target = ocelot_regmap_init(ocelot, res);
if (IS_ERR(target)) {
dev_err(ocelot->dev,
"Failed to map device memory space\n");
+ kfree(port_phy_modes);
return PTR_ERR(target);
}
@@ -230,6 +442,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
err = ocelot_regfields_init(ocelot, felix->info->regfields);
if (err) {
dev_err(ocelot->dev, "failed to init reg fields map\n");
+ kfree(port_phy_modes);
return err;
}
@@ -244,26 +457,37 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
if (!ocelot_port) {
dev_err(ocelot->dev,
"failed to allocate port memory\n");
+ kfree(port_phy_modes);
return -ENOMEM;
}
res = &felix->info->port_io_res[port];
res->flags = IORESOURCE_MEM;
- res->start += base;
- res->end += base;
+ res->start += switch_base;
+ res->end += switch_base;
port_regs = devm_ioremap_resource(ocelot->dev, res);
if (IS_ERR(port_regs)) {
dev_err(ocelot->dev,
"failed to map registers for port %d\n", port);
+ kfree(port_phy_modes);
return PTR_ERR(port_regs);
}
+ ocelot_port->phy_mode = port_phy_modes[port];
ocelot_port->ocelot = ocelot;
ocelot_port->regs = port_regs;
ocelot->ports[port] = ocelot_port;
}
+ kfree(port_phy_modes);
+
+ if (felix->info->mdio_bus_alloc) {
+ err = felix->info->mdio_bus_alloc(ocelot);
+ if (err < 0)
+ return err;
+ }
+
return 0;
}
@@ -293,12 +517,22 @@ static int felix_setup(struct dsa_switch *ds)
OCELOT_TAG_PREFIX_LONG);
}
+ /* It looks like the MAC/PCS interrupt register - PM0_IEVENT (0x8040)
+ * isn't instantiated for the Felix PF.
+ * In-band AN may take a few ms to complete, so we need to poll.
+ */
+ ds->pcs_poll = true;
+
return 0;
}
static void felix_teardown(struct dsa_switch *ds)
{
struct ocelot *ocelot = ds->priv;
+ struct felix *felix = ocelot_to_felix(ocelot);
+
+ if (felix->info->mdio_bus_free)
+ felix->info->mdio_bus_free(ocelot);
/* stop workqueue thread */
ocelot_deinit(ocelot);
@@ -369,7 +603,12 @@ static const struct dsa_switch_ops felix_switch_ops = {
.get_ethtool_stats = felix_get_ethtool_stats,
.get_sset_count = felix_get_sset_count,
.get_ts_info = felix_get_ts_info,
- .adjust_link = felix_adjust_link,
+ .phylink_validate = felix_phylink_validate,
+ .phylink_mac_link_state = felix_phylink_mac_pcs_get_state,
+ .phylink_mac_config = felix_phylink_mac_config,
+ .phylink_mac_an_restart = felix_phylink_mac_an_restart,
+ .phylink_mac_link_down = felix_phylink_mac_link_down,
+ .phylink_mac_link_up = felix_phylink_mac_link_up,
.port_enable = felix_port_enable,
.port_disable = felix_port_disable,
.port_fdb_dump = felix_fdb_dump,
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 204296e..3a75800 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -10,6 +10,7 @@
struct felix_info {
struct resource *target_io_res;
struct resource *port_io_res;
+ struct resource *imdio_res;
const struct reg_field *regfields;
const u32 *const *map;
const struct ocelot_ops *ops;
@@ -17,7 +18,18 @@ struct felix_info {
const struct ocelot_stat_layout *stats_layout;
unsigned int num_stats;
int num_ports;
- int pci_bar;
+ int switch_pci_bar;
+ int imdio_pci_bar;
+ int (*mdio_bus_alloc)(struct ocelot *ocelot);
+ void (*mdio_bus_free)(struct ocelot *ocelot);
+ void (*pcs_init)(struct ocelot *ocelot, int port,
+ unsigned int link_an_mode,
+ const struct phylink_link_state *state);
+ void (*pcs_an_restart)(struct ocelot *ocelot, int port);
+ void (*pcs_link_state)(struct ocelot *ocelot, int port,
+ struct phylink_link_state *state);
+ int (*prevalidate_phy_mode)(struct ocelot *ocelot, int port,
+ phy_interface_t phy_mode);
};
extern struct felix_info felix_info_vsc9959;
@@ -32,6 +44,8 @@ struct felix {
struct pci_dev *pdev;
struct felix_info *info;
struct ocelot ocelot;
+ struct mii_bus *imdio;
+ struct phy_device **pcs;
};
#endif
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index b9758b0..2c812b4 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -2,12 +2,33 @@
/* Copyright 2017 Microsemi Corporation
* Copyright 2018-2019 NXP Semiconductors
*/
+#include <linux/fsl/enetc_mdio.h>
#include <soc/mscc/ocelot_sys.h>
#include <soc/mscc/ocelot.h>
#include <linux/iopoll.h>
#include <linux/pci.h>
#include "felix.h"
+/* TODO: should find a better place for these */
+#define USXGMII_BMCR_RESET BIT(15)
+#define USXGMII_BMCR_AN_EN BIT(12)
+#define USXGMII_BMCR_RST_AN BIT(9)
+#define USXGMII_BMSR_LNKS(status) (((status) & GENMASK(2, 2)) >> 2)
+#define USXGMII_BMSR_AN_CMPL(status) (((status) & GENMASK(5, 5)) >> 5)
+#define USXGMII_ADVERTISE_LNKS(x) (((x) << 15) & BIT(15))
+#define USXGMII_ADVERTISE_FDX BIT(12)
+#define USXGMII_ADVERTISE_SPEED(x) (((x) << 9) & GENMASK(11, 9))
+#define USXGMII_LPA_LNKS(lpa) ((lpa) >> 15)
+#define USXGMII_LPA_DUPLEX(lpa) (((lpa) & GENMASK(12, 12)) >> 12)
+#define USXGMII_LPA_SPEED(lpa) (((lpa) & GENMASK(11, 9)) >> 9)
+
+enum usxgmii_speed {
+ USXGMII_SPEED_10 = 0,
+ USXGMII_SPEED_100 = 1,
+ USXGMII_SPEED_1000 = 2,
+ USXGMII_SPEED_2500 = 4,
+};
+
static const u32 vsc9959_ana_regmap[] = {
REG(ANA_ADVLEARN, 0x0089a0),
REG(ANA_VLANMASK, 0x0089a4),
@@ -386,6 +407,15 @@ static struct resource vsc9959_port_io_res[] = {
},
};
+/* Port MAC 0 Internal MDIO bus through which the SerDes acting as an
+ * SGMII/QSGMII MAC PCS can be found.
+ */
+static struct resource vsc9959_imdio_res = {
+ .start = 0x8030,
+ .end = 0x8040,
+ .name = "imdio",
+};
+
static const struct reg_field vsc9959_regfields[] = {
[ANA_ADVLEARN_VLAN_CHK] = REG_FIELD(ANA_ADVLEARN, 6, 6),
[ANA_ADVLEARN_LEARN_MIRROR] = REG_FIELD(ANA_ADVLEARN, 0, 5),
@@ -565,13 +595,495 @@ static int vsc9959_reset(struct ocelot *ocelot)
return 0;
}
+static void vsc9959_pcs_an_restart_sgmii(struct phy_device *pcs)
+{
+ phy_set_bits(pcs, MII_BMCR, BMCR_ANRESTART);
+}
+
+static void vsc9959_pcs_an_restart_usxgmii(struct phy_device *pcs)
+{
+ phy_write_mmd(pcs, MDIO_MMD_VEND2, MII_BMCR,
+ USXGMII_BMCR_RESET |
+ USXGMII_BMCR_AN_EN |
+ USXGMII_BMCR_RST_AN);
+}
+
+static void vsc9959_pcs_an_restart(struct ocelot *ocelot, int port)
+{
+ struct felix *felix = ocelot_to_felix(ocelot);
+ struct phy_device *pcs = felix->pcs[port];
+
+ if (!pcs)
+ return;
+
+ switch (pcs->interface) {
+ case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_QSGMII:
+ vsc9959_pcs_an_restart_sgmii(pcs);
+ break;
+ case PHY_INTERFACE_MODE_USXGMII:
+ vsc9959_pcs_an_restart_usxgmii(pcs);
+ break;
+ default:
+ dev_err(ocelot->dev, "Invalid PCS interface type %s\n",
+ phy_modes(pcs->interface));
+ break;
+ }
+}
+
+/* We enable SGMII AN only when the PHY has managed = "in-band-status" in the
+ * device tree. If we are in MLO_AN_PHY mode, we program directly state->speed
+ * into the PCS, which is retrieved out-of-band over MDIO. This also has the
+ * benefit of working with SGMII fixed-links, like downstream switches, where
+ * both link partners attempt to operate as AN slaves and therefore AN never
+ * completes. But it also has the disadvantage that some PHY chips don't pass
+ * traffic if SGMII AN is enabled but not completed (acknowledged by us), so
+ * setting MLO_AN_INBAND is actually required for those.
+ */
+static void vsc9959_pcs_init_sgmii(struct phy_device *pcs,
+ unsigned int link_an_mode,
+ const struct phylink_link_state *state)
+{
+ if (link_an_mode == MLO_AN_INBAND) {
+ int bmsr, bmcr;
+
+ /* Some PHYs like VSC8234 don't like it when AN restarts on
+ * their system side and they restart line side AN too, going
+ * into an endless link up/down loop. Don't restart PCS AN if
+ * link is up already.
+ * We do check that AN is enabled just in case this is the 1st
+ * call, PCS detects a carrier but AN is disabled from power on
+ * or by boot loader.
+ */
+ bmcr = phy_read(pcs, MII_BMCR);
+ if (bmcr < 0)
+ return;
+
+ bmsr = phy_read(pcs, MII_BMSR);
+ if (bmsr < 0)
+ return;
+
+ if ((bmcr & BMCR_ANENABLE) && (bmsr & BMSR_LSTATUS))
+ return;
+
+ /* SGMII spec requires tx_config_Reg[15:0] to be exactly 0x4001
+ * for the MAC PCS in order to acknowledge the AN.
+ */
+ phy_write(pcs, MII_ADVERTISE, ADVERTISE_SGMII |
+ ADVERTISE_LPACK);
+
+ phy_write(pcs, ENETC_PCS_IF_MODE,
+ ENETC_PCS_IF_MODE_SGMII_EN |
+ ENETC_PCS_IF_MODE_USE_SGMII_AN);
+
+ /* Adjust link timer for SGMII */
+ phy_write(pcs, ENETC_PCS_LINK_TIMER1,
+ ENETC_PCS_LINK_TIMER1_VAL);
+ phy_write(pcs, ENETC_PCS_LINK_TIMER2,
+ ENETC_PCS_LINK_TIMER2_VAL);
+
+ phy_write(pcs, MII_BMCR, BMCR_ANRESTART | BMCR_ANENABLE);
+ } else {
+ int speed;
+
+ if (state->duplex == DUPLEX_HALF) {
+ phydev_err(pcs, "Half duplex not supported\n");
+ return;
+ }
+ switch (state->speed) {
+ case SPEED_1000:
+ speed = ENETC_PCS_SPEED_1000;
+ break;
+ case SPEED_100:
+ speed = ENETC_PCS_SPEED_100;
+ break;
+ case SPEED_10:
+ speed = ENETC_PCS_SPEED_10;
+ break;
+ case SPEED_UNKNOWN:
+ /* Silently don't do anything */
+ return;
+ default:
+ phydev_err(pcs, "Invalid PCS speed %d\n", state->speed);
+ return;
+ }
+
+ phy_write(pcs, ENETC_PCS_IF_MODE,
+ ENETC_PCS_IF_MODE_SGMII_EN |
+ ENETC_PCS_IF_MODE_SGMII_SPEED(speed));
+
+ /* Yes, not a mistake: speed is given by IF_MODE. */
+ phy_write(pcs, MII_BMCR, BMCR_RESET |
+ BMCR_SPEED1000 |
+ BMCR_FULLDPLX);
+ }
+}
+
+/* 2500Base-X is SerDes protocol 7 on Felix and 6 on ENETC. It is a SerDes lane
+ * clocked at 3.125 GHz which encodes symbols with 8b/10b and does not have
+ * auto-negotiation of any link parameters. Electrically it is compatible with
+ * a single lane of XAUI.
+ * The hardware reference manual wants to call this mode SGMII, but it isn't
+ * really, since the fundamental features of SGMII:
+ * - Downgrading the link speed by duplicating symbols
+ * - Auto-negotiation
+ * are not there.
+ * The speed is configured at 1000 in the IF_MODE and BMCR MDIO registers
+ * because the clock frequency is actually given by a PLL configured in the
+ * Reset Configuration Word (RCW).
+ * Since there is no difference between fixed speed SGMII w/o AN and 802.3z w/o
+ * AN, we call this PHY interface type 2500Base-X. In case a PHY negotiates a
+ * lower link speed on line side, the system-side interface remains fixed at
+ * 2500 Mbps and we do rate adaptation through pause frames.
+ */
+static void vsc9959_pcs_init_2500basex(struct phy_device *pcs,
+ unsigned int link_an_mode,
+ const struct phylink_link_state *state)
+{
+ if (link_an_mode == MLO_AN_INBAND) {
+ phydev_err(pcs, "AN not supported on 3.125GHz SerDes lane\n");
+ return;
+ }
+
+ phy_write(pcs, ENETC_PCS_IF_MODE,
+ ENETC_PCS_IF_MODE_SGMII_EN |
+ ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_2500));
+
+ phy_write(pcs, MII_BMCR, BMCR_SPEED1000 |
+ BMCR_FULLDPLX |
+ BMCR_RESET);
+}
+
+static void vsc9959_pcs_init_usxgmii(struct phy_device *pcs,
+ unsigned int link_an_mode,
+ const struct phylink_link_state *state)
+{
+ if (link_an_mode != MLO_AN_INBAND) {
+ phydev_err(pcs, "USXGMII only supports in-band AN for now\n");
+ return;
+ }
+
+ /* Configure device ability for the USXGMII Replicator */
+ phy_write_mmd(pcs, MDIO_MMD_VEND2, MII_ADVERTISE,
+ USXGMII_ADVERTISE_SPEED(USXGMII_SPEED_2500) |
+ USXGMII_ADVERTISE_LNKS(1) |
+ ADVERTISE_SGMII |
+ ADVERTISE_LPACK |
+ USXGMII_ADVERTISE_FDX);
+}
+
+static void vsc9959_pcs_init(struct ocelot *ocelot, int port,
+ unsigned int link_an_mode,
+ const struct phylink_link_state *state)
+{
+ struct felix *felix = ocelot_to_felix(ocelot);
+ struct phy_device *pcs = felix->pcs[port];
+
+ if (!pcs)
+ return;
+
+ /* The PCS does not implement the BMSR register fully, so capability
+ * detection via genphy_read_abilities does not work. Since we can get
+ * the PHY config word from the LPA register though, there is still
+ * value in using the generic phy_resolve_aneg_linkmode function. So
+ * populate the supported and advertising link modes manually here.
+ */
+ linkmode_set_bit_array(phy_basic_ports_array,
+ ARRAY_SIZE(phy_basic_ports_array),
+ pcs->supported);
+ linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, pcs->supported);
+ linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, pcs->supported);
+ linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, pcs->supported);
+ if (pcs->interface == PHY_INTERFACE_MODE_2500BASEX ||
+ pcs->interface == PHY_INTERFACE_MODE_USXGMII)
+ linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
+ pcs->supported);
+ if (pcs->interface != PHY_INTERFACE_MODE_2500BASEX)
+ linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+ pcs->supported);
+ phy_advertise_supported(pcs);
+
+ switch (pcs->interface) {
+ case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_QSGMII:
+ vsc9959_pcs_init_sgmii(pcs, link_an_mode, state);
+ break;
+ case PHY_INTERFACE_MODE_2500BASEX:
+ vsc9959_pcs_init_2500basex(pcs, link_an_mode, state);
+ break;
+ case PHY_INTERFACE_MODE_USXGMII:
+ vsc9959_pcs_init_usxgmii(pcs, link_an_mode, state);
+ break;
+ default:
+ dev_err(ocelot->dev, "Unsupported link mode %s\n",
+ phy_modes(pcs->interface));
+ }
+}
+
+static void vsc9959_pcs_link_state_resolve(struct phy_device *pcs,
+ struct phylink_link_state *state)
+{
+ state->an_complete = pcs->autoneg_complete;
+ state->an_enabled = pcs->autoneg;
+ state->link = pcs->link;
+ state->duplex = pcs->duplex;
+ state->speed = pcs->speed;
+ /* SGMII AN does not negotiate flow control, but that's ok,
+ * since phylink already knows that, and does:
+ * link_state.pause |= pl->phy_state.pause;
+ */
+ state->pause = MLO_PAUSE_NONE;
+
+ phydev_dbg(pcs,
+ "mode=%s/%s/%s adv=%*pb lpa=%*pb link=%u an_enabled=%u an_complete=%u\n",
+ phy_modes(pcs->interface),
+ phy_speed_to_str(pcs->speed),
+ phy_duplex_to_str(pcs->duplex),
+ __ETHTOOL_LINK_MODE_MASK_NBITS, pcs->advertising,
+ __ETHTOOL_LINK_MODE_MASK_NBITS, pcs->lp_advertising,
+ pcs->link, pcs->autoneg, pcs->autoneg_complete);
+}
+
+static void vsc9959_pcs_link_state_sgmii(struct phy_device *pcs,
+ struct phylink_link_state *state)
+{
+ int err;
+
+ err = genphy_update_link(pcs);
+ if (err < 0)
+ return;
+
+ if (pcs->autoneg_complete) {
+ u16 lpa = phy_read(pcs, MII_LPA);
+
+ mii_lpa_to_linkmode_lpa_sgmii(pcs->lp_advertising, lpa);
+
+ phy_resolve_aneg_linkmode(pcs);
+ }
+}
+
+static void vsc9959_pcs_link_state_2500basex(struct phy_device *pcs,
+ struct phylink_link_state *state)
+{
+ int err;
+
+ err = genphy_update_link(pcs);
+ if (err < 0)
+ return;
+
+ pcs->speed = SPEED_2500;
+ pcs->asym_pause = true;
+ pcs->pause = true;
+}
+
+static void vsc9959_pcs_link_state_usxgmii(struct phy_device *pcs,
+ struct phylink_link_state *state)
+{
+ int status, lpa;
+
+ status = phy_read_mmd(pcs, MDIO_MMD_VEND2, MII_BMSR);
+ if (status < 0)
+ return;
+
+ pcs->autoneg = true;
+ pcs->autoneg_complete = USXGMII_BMSR_AN_CMPL(status);
+ pcs->link = USXGMII_BMSR_LNKS(status);
+
+ if (!pcs->link || !pcs->autoneg_complete)
+ return;
+
+ lpa = phy_read_mmd(pcs, MDIO_MMD_VEND2, MII_LPA);
+ if (lpa < 0)
+ return;
+
+ switch (USXGMII_LPA_SPEED(lpa)) {
+ case USXGMII_SPEED_10:
+ pcs->speed = SPEED_10;
+ break;
+ case USXGMII_SPEED_100:
+ pcs->speed = SPEED_100;
+ break;
+ case USXGMII_SPEED_1000:
+ pcs->speed = SPEED_1000;
+ break;
+ case USXGMII_SPEED_2500:
+ pcs->speed = SPEED_2500;
+ break;
+ default:
+ break;
+ }
+
+ if (USXGMII_LPA_DUPLEX(lpa))
+ pcs->duplex = DUPLEX_FULL;
+ else
+ pcs->duplex = DUPLEX_HALF;
+}
+
+static void vsc9959_pcs_link_state(struct ocelot *ocelot, int port,
+ struct phylink_link_state *state)
+{
+ struct felix *felix = ocelot_to_felix(ocelot);
+ struct phy_device *pcs = felix->pcs[port];
+
+ if (!pcs)
+ return;
+
+ pcs->speed = SPEED_UNKNOWN;
+ pcs->duplex = DUPLEX_UNKNOWN;
+ pcs->pause = 0;
+ pcs->asym_pause = 0;
+
+ switch (pcs->interface) {
+ case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_QSGMII:
+ vsc9959_pcs_link_state_sgmii(pcs, state);
+ break;
+ case PHY_INTERFACE_MODE_2500BASEX:
+ vsc9959_pcs_link_state_2500basex(pcs, state);
+ break;
+ case PHY_INTERFACE_MODE_USXGMII:
+ vsc9959_pcs_link_state_usxgmii(pcs, state);
+ break;
+ default:
+ return;
+ }
+
+ vsc9959_pcs_link_state_resolve(pcs, state);
+}
+
+static int vsc9959_prevalidate_phy_mode(struct ocelot *ocelot, int port,
+ phy_interface_t phy_mode)
+{
+ switch (phy_mode) {
+ case PHY_INTERFACE_MODE_GMII:
+ /* Only supported on internal to-CPU ports */
+ if (port != 4 && port != 5)
+ return -ENOTSUPP;
+ return 0;
+ case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_QSGMII:
+ case PHY_INTERFACE_MODE_USXGMII:
+ case PHY_INTERFACE_MODE_2500BASEX:
+ /* Not supported on internal to-CPU ports */
+ if (port == 4 || port == 5)
+ return -ENOTSUPP;
+ return 0;
+ default:
+ return -ENOTSUPP;
+ }
+}
+
static const struct ocelot_ops vsc9959_ops = {
.reset = vsc9959_reset,
};
+static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot)
+{
+ struct felix *felix = ocelot_to_felix(ocelot);
+ struct enetc_mdio_priv *mdio_priv;
+ struct device *dev = ocelot->dev;
+ resource_size_t imdio_base;
+ void __iomem *imdio_regs;
+ struct resource *res;
+ struct enetc_hw *hw;
+ struct mii_bus *bus;
+ int port;
+ int rc;
+
+ felix->pcs = devm_kcalloc(dev, felix->info->num_ports,
+ sizeof(struct phy_device *),
+ GFP_KERNEL);
+ if (!felix->pcs) {
+ dev_err(dev, "failed to allocate array for PCS PHYs\n");
+ return -ENOMEM;
+ }
+
+ imdio_base = pci_resource_start(felix->pdev,
+ felix->info->imdio_pci_bar);
+
+ res = felix->info->imdio_res;
+ res->flags = IORESOURCE_MEM;
+ res->start += imdio_base;
+ res->end += imdio_base;
+
+ imdio_regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(imdio_regs)) {
+ dev_err(dev, "failed to map internal MDIO registers\n");
+ return PTR_ERR(imdio_regs);
+ }
+
+ hw = enetc_hw_alloc(dev, imdio_regs);
+ if (IS_ERR(hw)) {
+ dev_err(dev, "failed to allocate ENETC HW structure\n");
+ return PTR_ERR(hw);
+ }
+
+ bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv));
+ if (!bus)
+ return -ENOMEM;
+
+ bus->name = "VSC9959 internal MDIO bus";
+ bus->read = enetc_mdio_read;
+ bus->write = enetc_mdio_write;
+ bus->parent = dev;
+ mdio_priv = bus->priv;
+ mdio_priv->hw = hw;
+ /* This gets added to imdio_regs, which already maps addresses
+ * starting with the proper offset.
+ */
+ mdio_priv->mdio_base = 0;
+ snprintf(bus->id, MII_BUS_ID_SIZE, "%s-imdio", dev_name(dev));
+
+ /* Needed in order to initialize the bus mutex lock */
+ rc = mdiobus_register(bus);
+ if (rc < 0) {
+ dev_err(dev, "failed to register MDIO bus\n");
+ return rc;
+ }
+
+ felix->imdio = bus;
+
+ for (port = 0; port < felix->info->num_ports; port++) {
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
+ struct phy_device *pcs;
+ bool is_c45 = false;
+
+ if (ocelot_port->phy_mode == PHY_INTERFACE_MODE_USXGMII)
+ is_c45 = true;
+
+ pcs = get_phy_device(felix->imdio, port, is_c45);
+ if (IS_ERR(pcs))
+ continue;
+
+ pcs->interface = ocelot_port->phy_mode;
+ felix->pcs[port] = pcs;
+
+ dev_info(dev, "Found PCS at internal MDIO address %d\n", port);
+ }
+
+ return 0;
+}
+
+static void vsc9959_mdio_bus_free(struct ocelot *ocelot)
+{
+ struct felix *felix = ocelot_to_felix(ocelot);
+ int port;
+
+ for (port = 0; port < ocelot->num_phys_ports; port++) {
+ struct phy_device *pcs = felix->pcs[port];
+
+ if (!pcs)
+ continue;
+
+ put_device(&pcs->mdio.dev);
+ }
+ mdiobus_unregister(felix->imdio);
+}
+
struct felix_info felix_info_vsc9959 = {
.target_io_res = vsc9959_target_io_res,
.port_io_res = vsc9959_port_io_res,
+ .imdio_res = &vsc9959_imdio_res,
.regfields = vsc9959_regfields,
.map = vsc9959_regmap,
.ops = &vsc9959_ops,
@@ -579,5 +1091,12 @@ struct felix_info felix_info_vsc9959 = {
.num_stats = ARRAY_SIZE(vsc9959_stats_layout),
.shared_queue_sz = 128 * 1024,
.num_ports = 6,
- .pci_bar = 4,
+ .switch_pci_bar = 4,
+ .imdio_pci_bar = 0,
+ .mdio_bus_alloc = vsc9959_mdio_bus_alloc,
+ .mdio_bus_free = vsc9959_mdio_bus_free,
+ .pcs_init = vsc9959_pcs_init,
+ .pcs_an_restart = vsc9959_pcs_an_restart,
+ .pcs_link_state = vsc9959_pcs_link_state,
+ .prevalidate_phy_mode = vsc9959_prevalidate_phy_mode,
};
diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c
index da3bece..de25f99 100644
--- a/drivers/net/dsa/qca/ar9331.c
+++ b/drivers/net/dsa/qca/ar9331.c
@@ -347,7 +347,8 @@ static void ar9331_sw_port_disable(struct dsa_switch *ds, int port)
}
static enum dsa_tag_protocol ar9331_sw_get_tag_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol m)
{
return DSA_TAG_PROTO_AR9331;
}
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index e548289..9f4205b 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -1017,7 +1017,8 @@ qca8k_port_fdb_dump(struct dsa_switch *ds, int port,
}
static enum dsa_tag_protocol
-qca8k_get_tag_protocol(struct dsa_switch *ds, int port)
+qca8k_get_tag_protocol(struct dsa_switch *ds, int port,
+ enum dsa_tag_protocol mp)
{
return DSA_TAG_PROTO_QCA;
}
diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c
index f5cc8b0..fd197759 100644
--- a/drivers/net/dsa/rtl8366rb.c
+++ b/drivers/net/dsa/rtl8366rb.c
@@ -964,7 +964,8 @@ static int rtl8366rb_setup(struct dsa_switch *ds)
}
static enum dsa_tag_protocol rtl8366_get_tag_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol mp)
{
/* For now, the RTL switches are handled without any custom tags.
*
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 1da5ac1..03ba6d2 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -426,14 +426,6 @@ static int sja1105_init_general_params(struct sja1105_private *priv)
.tpid2 = ETH_P_SJA1105,
};
struct sja1105_table *table;
- int i, k = 0;
-
- for (i = 0; i < SJA1105_NUM_PORTS; i++) {
- if (dsa_is_dsa_port(priv->ds, i))
- default_general_params.casc_port = i;
- else if (dsa_is_user_port(priv->ds, i))
- priv->ports[i].mgmt_slot = k++;
- }
table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
@@ -582,7 +574,7 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv,
struct device *dev = &priv->spidev->dev;
struct device_node *child;
- for_each_child_of_node(ports_node, child) {
+ for_each_available_child_of_node(ports_node, child) {
struct device_node *phy_node;
phy_interface_t phy_mode;
u32 index;
@@ -1542,7 +1534,8 @@ static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled)
}
static enum dsa_tag_protocol
-sja1105_get_tag_protocol(struct dsa_switch *ds, int port)
+sja1105_get_tag_protocol(struct dsa_switch *ds, int port,
+ enum dsa_tag_protocol mp)
{
return DSA_TAG_PROTO_SJA1105;
}
@@ -1740,6 +1733,16 @@ static int sja1105_setup(struct dsa_switch *ds)
static void sja1105_teardown(struct dsa_switch *ds)
{
struct sja1105_private *priv = ds->priv;
+ int port;
+
+ for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+ struct sja1105_port *sp = &priv->ports[port];
+
+ if (!dsa_is_user_port(ds, port))
+ continue;
+
+ kthread_destroy_worker(sp->xmit_worker);
+ }
sja1105_tas_teardown(ds);
sja1105_ptp_clock_unregister(ds);
@@ -1761,6 +1764,18 @@ static int sja1105_port_enable(struct dsa_switch *ds, int port,
return 0;
}
+static void sja1105_port_disable(struct dsa_switch *ds, int port)
+{
+ struct sja1105_private *priv = ds->priv;
+ struct sja1105_port *sp = &priv->ports[port];
+
+ if (!dsa_is_user_port(ds, port))
+ return;
+
+ kthread_cancel_work_sync(&sp->xmit_work);
+ skb_queue_purge(&sp->xmit_queue);
+}
+
static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot,
struct sk_buff *skb, bool takets)
{
@@ -1819,47 +1834,36 @@ static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot,
return NETDEV_TX_OK;
}
+#define work_to_port(work) \
+ container_of((work), struct sja1105_port, xmit_work)
+#define tagger_to_sja1105(t) \
+ container_of((t), struct sja1105_private, tagger_data)
+
/* Deferred work is unfortunately necessary because setting up the management
* route cannot be done from atomit context (SPI transfer takes a sleepable
* lock on the bus)
*/
-static netdev_tx_t sja1105_port_deferred_xmit(struct dsa_switch *ds, int port,
- struct sk_buff *skb)
+static void sja1105_port_deferred_xmit(struct kthread_work *work)
{
- struct sja1105_private *priv = ds->priv;
- struct sja1105_port *sp = &priv->ports[port];
- int slot = sp->mgmt_slot;
- struct sk_buff *clone;
+ struct sja1105_port *sp = work_to_port(work);
+ struct sja1105_tagger_data *tagger_data = sp->data;
+ struct sja1105_private *priv = tagger_to_sja1105(tagger_data);
+ int port = sp - priv->ports;
+ struct sk_buff *skb;
- /* The tragic fact about the switch having 4x2 slots for installing
- * management routes is that all of them except one are actually
- * useless.
- * If 2 slots are simultaneously configured for two BPDUs sent to the
- * same (multicast) DMAC but on different egress ports, the switch
- * would confuse them and redirect first frame it receives on the CPU
- * port towards the port configured on the numerically first slot
- * (therefore wrong port), then second received frame on second slot
- * (also wrong port).
- * So for all practical purposes, there needs to be a lock that
- * prevents that from happening. The slot used here is utterly useless
- * (could have simply been 0 just as fine), but we are doing it
- * nonetheless, in case a smarter idea ever comes up in the future.
- */
- mutex_lock(&priv->mgmt_lock);
+ while ((skb = skb_dequeue(&sp->xmit_queue)) != NULL) {
+ struct sk_buff *clone = DSA_SKB_CB(skb)->clone;
- /* The clone, if there, was made by dsa_skb_tx_timestamp */
- clone = DSA_SKB_CB(skb)->clone;
+ mutex_lock(&priv->mgmt_lock);
- sja1105_mgmt_xmit(ds, port, slot, skb, !!clone);
+ sja1105_mgmt_xmit(priv->ds, port, 0, skb, !!clone);
- if (!clone)
- goto out;
+ /* The clone, if there, was made by dsa_skb_tx_timestamp */
+ if (clone)
+ sja1105_ptp_txtstamp_skb(priv->ds, port, clone);
- sja1105_ptp_txtstamp_skb(ds, port, clone);
-
-out:
- mutex_unlock(&priv->mgmt_lock);
- return NETDEV_TX_OK;
+ mutex_unlock(&priv->mgmt_lock);
+ }
}
/* The MAXAGE setting belongs to the L2 Forwarding Parameters table,
@@ -1990,6 +1994,7 @@ static const struct dsa_switch_ops sja1105_switch_ops = {
.get_sset_count = sja1105_get_sset_count,
.get_ts_info = sja1105_get_ts_info,
.port_enable = sja1105_port_enable,
+ .port_disable = sja1105_port_disable,
.port_fdb_dump = sja1105_fdb_dump,
.port_fdb_add = sja1105_fdb_add,
.port_fdb_del = sja1105_fdb_del,
@@ -2003,7 +2008,6 @@ static const struct dsa_switch_ops sja1105_switch_ops = {
.port_mdb_prepare = sja1105_mdb_prepare,
.port_mdb_add = sja1105_mdb_add,
.port_mdb_del = sja1105_mdb_del,
- .port_deferred_xmit = sja1105_port_deferred_xmit,
.port_hwtstamp_get = sja1105_hwtstamp_get,
.port_hwtstamp_set = sja1105_hwtstamp_set,
.port_rxtstamp = sja1105_port_rxtstamp,
@@ -2055,7 +2059,7 @@ static int sja1105_probe(struct spi_device *spi)
struct device *dev = &spi->dev;
struct sja1105_private *priv;
struct dsa_switch *ds;
- int rc, i;
+ int rc, port;
if (!dev->of_node) {
dev_err(dev, "No DTS bindings for SJA1105 driver\n");
@@ -2120,15 +2124,42 @@ static int sja1105_probe(struct spi_device *spi)
return rc;
/* Connections between dsa_port and sja1105_port */
- for (i = 0; i < SJA1105_NUM_PORTS; i++) {
- struct sja1105_port *sp = &priv->ports[i];
+ for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+ struct sja1105_port *sp = &priv->ports[port];
+ struct dsa_port *dp = dsa_to_port(ds, port);
+ struct net_device *slave;
- dsa_to_port(ds, i)->priv = sp;
- sp->dp = dsa_to_port(ds, i);
+ if (!dsa_is_user_port(ds, port))
+ continue;
+
+ dp->priv = sp;
+ sp->dp = dp;
sp->data = tagger_data;
+ slave = dp->slave;
+ kthread_init_work(&sp->xmit_work, sja1105_port_deferred_xmit);
+ sp->xmit_worker = kthread_create_worker(0, "%s_xmit",
+ slave->name);
+ if (IS_ERR(sp->xmit_worker)) {
+ rc = PTR_ERR(sp->xmit_worker);
+ dev_err(ds->dev,
+ "failed to create deferred xmit thread: %d\n",
+ rc);
+ goto out;
+ }
+ skb_queue_head_init(&sp->xmit_queue);
}
return 0;
+out:
+ while (port-- > 0) {
+ struct sja1105_port *sp = &priv->ports[port];
+
+ if (!dsa_is_user_port(ds, port))
+ continue;
+
+ kthread_destroy_worker(sp->xmit_worker);
+ }
+ return rc;
}
static int sja1105_remove(struct spi_device *spi)
diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index 42c1574..6e21a2a 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -542,7 +542,8 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum,
}
static enum dsa_tag_protocol vsc73xx_get_tag_protocol(struct dsa_switch *ds,
- int port)
+ int port,
+ enum dsa_tag_protocol mp)
{
/* The switch internally uses a 8 byte header with length,
* source port, tag, LPA and priority. This is supposedly
@@ -1111,7 +1112,9 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc)
vsc->gc.ngpio = 4;
vsc->gc.owner = THIS_MODULE;
vsc->gc.parent = vsc->dev;
+#if IS_ENABLED(CONFIG_OF_GPIO)
vsc->gc.of_node = vsc->dev->of_node;
+#endif
vsc->gc.base = -1;
vsc->gc.get = vsc73xx_gpio_get;
vsc->gc.set = vsc73xx_gpio_set;
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index fc04679..a2b7f7a 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1548,7 +1548,7 @@ vortex_up(struct net_device *dev)
struct vortex_private *vp = netdev_priv(dev);
void __iomem *ioaddr = vp->ioaddr;
unsigned int config;
- int i, mii_reg1, mii_reg5, err = 0;
+ int i, mii_reg5, err = 0;
if (VORTEX_PCI(vp)) {
pci_set_power_state(VORTEX_PCI(vp), PCI_D0); /* Go active */
@@ -1605,7 +1605,7 @@ vortex_up(struct net_device *dev)
window_write32(vp, config, 3, Wn3_Config);
if (dev->if_port == XCVR_MII || dev->if_port == XCVR_NWAY) {
- mii_reg1 = mdio_read(dev, vp->phys[0], MII_BMSR);
+ mdio_read(dev, vp->phys[0], MII_BMSR);
mii_reg5 = mdio_read(dev, vp->phys[0], MII_LPA);
vp->partner_flow_ctrl = ((mii_reg5 & 0x0400) != 0);
vp->mii.full_duplex = vp->full_duplex;
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 3c51d8c..cb6a761 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -3651,15 +3651,6 @@ static int et131x_close(struct net_device *netdev)
return del_timer_sync(&adapter->error_timer);
}
-static int et131x_ioctl(struct net_device *netdev, struct ifreq *reqbuf,
- int cmd)
-{
- if (!netdev->phydev)
- return -EINVAL;
-
- return phy_mii_ioctl(netdev->phydev, reqbuf, cmd);
-}
-
/* et131x_set_packet_filter - Configures the Rx Packet filtering */
static int et131x_set_packet_filter(struct et131x_adapter *adapter)
{
@@ -3899,7 +3890,7 @@ static const struct net_device_ops et131x_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_get_stats = et131x_stats,
- .ndo_do_ioctl = et131x_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl,
};
static int et131x_pci_setup(struct pci_dev *pdev,
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 5ea8064..22cadfb 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -207,19 +207,6 @@ static void emac_inblk_32bit(void __iomem *reg, void *data, int count)
readsl(reg, data, round_up(count, 4) / 4);
}
-static int emac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- struct phy_device *phydev = dev->phydev;
-
- if (!netif_running(dev))
- return -EINVAL;
-
- if (!phydev)
- return -ENODEV;
-
- return phy_mii_ioctl(phydev, rq, cmd);
-}
-
/* ethtool ops */
static void emac_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *info)
@@ -791,7 +778,7 @@ static const struct net_device_ops emac_netdev_ops = {
.ndo_start_xmit = emac_start_xmit,
.ndo_tx_timeout = emac_timeout,
.ndo_set_rx_mode = emac_set_rx_mode,
- .ndo_do_ioctl = emac_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = emac_set_mac_address,
#ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/amd/a2065.c b/drivers/net/ethernet/amd/a2065.c
index a3faf4f..2f808dbc8 100644
--- a/drivers/net/ethernet/amd/a2065.c
+++ b/drivers/net/ethernet/amd/a2065.c
@@ -118,10 +118,6 @@ struct lance_private {
int auto_select; /* cable-selection by carrier */
unsigned short busmaster_regval;
-#ifdef CONFIG_SUNLANCE
- struct Linux_SBus_DMA *ledma; /* if set this points to ledma and arch=4m */
- int burst_sizes; /* ledma SBus burst sizes */
-#endif
struct timer_list multicast_timer;
struct net_device *dev;
};
@@ -551,11 +547,10 @@ static netdev_tx_t lance_start_xmit(struct sk_buff *skb,
if (!lance_tx_buffs_avail(lp))
goto out_free;
-#ifdef DEBUG
/* dump the packet */
- print_hex_dump(KERN_DEBUG, "skb->data: ", DUMP_PREFIX_NONE,
- 16, 1, skb->data, 64, true);
-#endif
+ print_hex_dump_debug("skb->data: ", DUMP_PREFIX_NONE, 16, 1, skb->data,
+ 64, true);
+
entry = lp->tx_new & lp->tx_ring_mod_mask;
ib->btx_ring[entry].length = (-skblen) | 0xf000;
ib->btx_ring[entry].misc = 0;
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index d832c9f..255847e 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -1053,23 +1053,12 @@ static void au1000_multicast_list(struct net_device *dev)
writel(reg, &aup->mac->control);
}
-static int au1000_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- if (!netif_running(dev))
- return -EINVAL;
-
- if (!dev->phydev)
- return -EINVAL; /* PHY not controllable */
-
- return phy_mii_ioctl(dev->phydev, rq, cmd);
-}
-
static const struct net_device_ops au1000_netdev_ops = {
.ndo_open = au1000_open,
.ndo_stop = au1000_close,
.ndo_start_xmit = au1000_tx,
.ndo_set_rx_mode = au1000_multicast_list,
- .ndo_do_ioctl = au1000_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_tx_timeout = au1000_tx_timeout,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c
index 6592a2d..7282ce5 100644
--- a/drivers/net/ethernet/amd/declance.c
+++ b/drivers/net/ethernet/amd/declance.c
@@ -608,7 +608,7 @@ static int lance_rx(struct net_device *dev)
len = (*rds_ptr(rd, mblength, lp->type) & 0xfff) - 4;
skb = netdev_alloc_skb(dev, len + 2);
- if (skb == 0) {
+ if (!skb) {
dev->stats.rx_dropped++;
*rds_ptr(rd, mblength, lp->type) = 0;
*rds_ptr(rd, rmd1, lp->type) =
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 128cd64..46c3c1c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -1227,7 +1227,7 @@ static bool xgbe_phy_sfp_verify_eeprom(u8 cc_in, u8 *buf, unsigned int len)
for (cc = 0; len; buf++, len--)
cc += *buf;
- return (cc == cc_in) ? true : false;
+ return cc == cc_in;
}
static int xgbe_phy_sfp_read_eeprom(struct xgbe_prv_data *pdata)
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index e284b67..6aee2f0f 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -2020,7 +2020,7 @@ static int xgene_enet_probe(struct platform_device *pdev)
int ret;
ndev = alloc_etherdev_mqs(sizeof(struct xgene_enet_pdata),
- XGENE_NUM_RX_RING, XGENE_NUM_TX_RING);
+ XGENE_NUM_TX_RING, XGENE_NUM_RX_RING);
if (!ndev)
return -ENOMEM;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index a17a4da..c85e3e2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -403,6 +403,8 @@ int aq_nic_start(struct aq_nic_s *self)
if (err < 0)
goto err_exit;
+ aq_nic_set_loopback(self);
+
err = self->aq_hw_ops->hw_start(self->aq_hw);
if (err < 0)
goto err_exit;
@@ -413,8 +415,6 @@ int aq_nic_start(struct aq_nic_s *self)
INIT_WORK(&self->service_task, aq_nic_service_task);
- aq_nic_set_loopback(self);
-
timer_setup(&self->service_timer, aq_nic_service_timer_cb, 0);
aq_nic_service_timer_cb(&self->service_timer);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 58e891a..ec041f7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -1525,9 +1525,6 @@ const struct aq_hw_ops hw_atl_ops_b0 = {
.rx_extract_ts = hw_atl_b0_rx_extract_ts,
.extract_hwts = hw_atl_b0_extract_hwts,
.hw_set_offload = hw_atl_b0_hw_offload_set,
- .hw_get_hw_stats = hw_atl_utils_get_hw_stats,
- .hw_get_fw_version = hw_atl_utils_get_fw_version,
- .hw_set_offload = hw_atl_b0_hw_offload_set,
.hw_set_loopback = hw_atl_b0_set_loopback,
.hw_set_fc = hw_atl_b0_set_fc,
};
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 8910b62..f547baa 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -667,9 +667,7 @@ int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self)
u32 speed;
mpi_state = hw_atl_utils_mpi_get_state(self);
- speed = mpi_state & (FW2X_RATE_100M | FW2X_RATE_1G |
- FW2X_RATE_2G5 | FW2X_RATE_5G |
- FW2X_RATE_10G);
+ speed = mpi_state >> HW_ATL_MPI_SPEED_SHIFT;
if (!speed) {
link_status->mbps = 0U;
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index 6f2c867..17bda4e 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -781,18 +781,6 @@ static int arc_emac_set_address(struct net_device *ndev, void *p)
return 0;
}
-static int arc_emac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- if (!netif_running(dev))
- return -EINVAL;
-
- if (!dev->phydev)
- return -ENODEV;
-
- return phy_mii_ioctl(dev->phydev, rq, cmd);
-}
-
-
/**
* arc_emac_restart - Restart EMAC
* @ndev: Pointer to net_device structure.
@@ -857,7 +845,7 @@ static const struct net_device_ops arc_emac_netdev_ops = {
.ndo_set_mac_address = arc_emac_set_address,
.ndo_get_stats = arc_emac_stats,
.ndo_set_rx_mode = arc_emac_set_rx_mode,
- .ndo_do_ioctl = arc_emac_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = arc_emac_poll_controller,
#endif
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 88e4e15..5ce2df4 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1394,14 +1394,6 @@ static netdev_tx_t ag71xx_hard_start_xmit(struct sk_buff *skb,
return NETDEV_TX_OK;
}
-static int ag71xx_do_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
-{
- if (!ndev->phydev)
- return -EINVAL;
-
- return phy_mii_ioctl(ndev->phydev, ifr, cmd);
-}
-
static void ag71xx_oom_timer_handler(struct timer_list *t)
{
struct ag71xx *ag = from_timer(ag, t, oom_timer);
@@ -1618,7 +1610,7 @@ static const struct net_device_ops ag71xx_netdev_ops = {
.ndo_open = ag71xx_open,
.ndo_stop = ag71xx_stop,
.ndo_start_xmit = ag71xx_hard_start_xmit,
- .ndo_do_ioctl = ag71xx_do_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl,
.ndo_tx_timeout = ag71xx_tx_timeout,
.ndo_change_mtu = ag71xx_change_mtu,
.ndo_set_mac_address = eth_mac_addr,
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index 30b4550..bc273e0 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -1005,18 +1005,13 @@ static int nb8800_stop(struct net_device *dev)
return 0;
}
-static int nb8800_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- return phy_mii_ioctl(dev->phydev, rq, cmd);
-}
-
static const struct net_device_ops nb8800_netdev_ops = {
.ndo_open = nb8800_open,
.ndo_stop = nb8800_stop,
.ndo_start_xmit = nb8800_xmit,
.ndo_set_mac_address = nb8800_set_mac_address,
.ndo_set_rx_mode = nb8800_set_rx_mode,
- .ndo_do_ioctl = nb8800_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl,
.ndo_validate_addr = eth_validate_addr,
};
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 5b3464c..a780b72 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -1516,8 +1516,10 @@ static int b44_magic_pattern(u8 *macaddr, u8 *ppattern, u8 *pmask, int offset)
int ethaddr_bytes = ETH_ALEN;
memset(ppattern + offset, 0xff, magicsync);
- for (j = 0; j < magicsync; j++)
- set_bit(len++, (unsigned long *) pmask);
+ for (j = 0; j < magicsync; j++) {
+ pmask[len >> 3] |= BIT(len & 7);
+ len++;
+ }
for (j = 0; j < B44_MAX_PATTERNS; j++) {
if ((B44_PATTERN_SIZE - len) >= ETH_ALEN)
@@ -1529,7 +1531,8 @@ static int b44_magic_pattern(u8 *macaddr, u8 *ppattern, u8 *pmask, int offset)
for (k = 0; k< ethaddr_bytes; k++) {
ppattern[offset + magicsync +
(j * ETH_ALEN) + k] = macaddr[k];
- set_bit(len++, (unsigned long *) pmask);
+ pmask[len >> 3] |= BIT(len & 7);
+ len++;
}
}
return len - 1;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 1907e47..f07ac0e 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2323,7 +2323,7 @@ static int bcm_sysport_map_queues(struct notifier_block *nb,
ring->switch_queue = qp;
ring->switch_port = port;
ring->inspect = true;
- priv->ring_map[q + port * num_tx_queues] = ring;
+ priv->ring_map[qp + port * num_tx_queues] = ring;
qp++;
}
@@ -2338,7 +2338,7 @@ static int bcm_sysport_unmap_queues(struct notifier_block *nb,
struct net_device *slave_dev;
unsigned int num_tx_queues;
struct net_device *dev;
- unsigned int q, port;
+ unsigned int q, qp, port;
priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
if (priv->netdev != info->master)
@@ -2364,7 +2364,8 @@ static int bcm_sysport_unmap_queues(struct notifier_block *nb,
continue;
ring->inspect = false;
- priv->ring_map[q + port * num_tx_queues] = NULL;
+ qp = ring->switch_queue;
+ priv->ring_map[qp + port * num_tx_queues] = NULL;
}
return 0;
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 148734b..1bb07a5 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1248,14 +1248,6 @@ static int bgmac_set_mac_address(struct net_device *net_dev, void *addr)
return 0;
}
-static int bgmac_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
-{
- if (!netif_running(net_dev))
- return -EINVAL;
-
- return phy_mii_ioctl(net_dev->phydev, ifr, cmd);
-}
-
static const struct net_device_ops bgmac_netdev_ops = {
.ndo_open = bgmac_open,
.ndo_stop = bgmac_stop,
@@ -1263,7 +1255,7 @@ static const struct net_device_ops bgmac_netdev_ops = {
.ndo_set_rx_mode = bgmac_set_rx_mode,
.ndo_set_mac_address = bgmac_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
- .ndo_do_ioctl = bgmac_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
};
/**************************************************
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7b0fe19..198c69dc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -944,6 +944,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
dma_addr -= bp->rx_dma_offset;
dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir,
DMA_ATTR_WEAK_ORDERING);
+ page_pool_release_page(rxr->page_pool, page);
if (unlikely(!payload))
payload = eth_get_headlen(bp->dev, data_ptr, len);
@@ -10822,6 +10823,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
smp_mb__before_atomic();
clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
bnxt_ulp_start(bp, rc);
+ bnxt_dl_health_recovery_done(bp);
bnxt_dl_health_status_update(bp, true);
rtnl_unlock();
break;
@@ -11065,11 +11067,23 @@ static bool bnxt_fltr_match(struct bnxt_ntuple_filter *f1,
struct flow_keys *keys1 = &f1->fkeys;
struct flow_keys *keys2 = &f2->fkeys;
- if (keys1->addrs.v4addrs.src == keys2->addrs.v4addrs.src &&
- keys1->addrs.v4addrs.dst == keys2->addrs.v4addrs.dst &&
- keys1->ports.ports == keys2->ports.ports &&
- keys1->basic.ip_proto == keys2->basic.ip_proto &&
- keys1->basic.n_proto == keys2->basic.n_proto &&
+ if (keys1->basic.n_proto != keys2->basic.n_proto ||
+ keys1->basic.ip_proto != keys2->basic.ip_proto)
+ return false;
+
+ if (keys1->basic.n_proto == htons(ETH_P_IP)) {
+ if (keys1->addrs.v4addrs.src != keys2->addrs.v4addrs.src ||
+ keys1->addrs.v4addrs.dst != keys2->addrs.v4addrs.dst)
+ return false;
+ } else {
+ if (memcmp(&keys1->addrs.v6addrs.src, &keys2->addrs.v6addrs.src,
+ sizeof(keys1->addrs.v6addrs.src)) ||
+ memcmp(&keys1->addrs.v6addrs.dst, &keys2->addrs.v6addrs.dst,
+ sizeof(keys1->addrs.v6addrs.dst)))
+ return false;
+ }
+
+ if (keys1->ports.ports == keys2->ports.ports &&
keys1->control.flags == keys2->control.flags &&
ether_addr_equal(f1->src_mac_addr, f2->src_mac_addr) &&
ether_addr_equal(f1->dst_mac_addr, f2->dst_mac_addr))
@@ -11361,7 +11375,7 @@ int bnxt_get_port_parent_id(struct net_device *dev,
return -EOPNOTSUPP;
/* The PF and it's VF-reps only support the switchdev framework */
- if (!BNXT_PF(bp))
+ if (!BNXT_PF(bp) || !(bp->flags & BNXT_FLAG_DSN_VALID))
return -EOPNOTSUPP;
ppid->id_len = sizeof(bp->switch_id);
@@ -11734,6 +11748,7 @@ static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[])
put_unaligned_le32(dw, &dsn[0]);
pci_read_config_dword(pdev, pos + 4, &dw);
put_unaligned_le32(dw, &dsn[4]);
+ bp->flags |= BNXT_FLAG_DSN_VALID;
return 0;
}
@@ -11845,9 +11860,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if (BNXT_PF(bp)) {
/* Read the adapter's DSN to use as the eswitch switch_id */
- rc = bnxt_pcie_dsn_get(bp, bp->switch_id);
- if (rc)
- goto init_err_pci_clean;
+ bnxt_pcie_dsn_get(bp, bp->switch_id);
}
/* MTU range: 60 - FW defined max */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 505af5c..f143354 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1532,6 +1532,7 @@ struct bnxt {
#define BNXT_FLAG_NO_AGG_RINGS 0x20000
#define BNXT_FLAG_RX_PAGE_MODE 0x40000
#define BNXT_FLAG_MULTI_HOST 0x100000
+ #define BNXT_FLAG_DSN_VALID 0x200000
#define BNXT_FLAG_DOUBLE_DB 0x400000
#define BNXT_FLAG_CHIP_NITRO_A0 0x1000000
#define BNXT_FLAG_DIM 0x2000000
@@ -1936,9 +1937,6 @@ static inline bool bnxt_cfa_hwrm_message(u16 req_type)
case HWRM_CFA_ENCAP_RECORD_FREE:
case HWRM_CFA_DECAP_FILTER_ALLOC:
case HWRM_CFA_DECAP_FILTER_FREE:
- case HWRM_CFA_NTUPLE_FILTER_ALLOC:
- case HWRM_CFA_NTUPLE_FILTER_FREE:
- case HWRM_CFA_NTUPLE_FILTER_CFG:
case HWRM_CFA_EM_FLOW_ALLOC:
case HWRM_CFA_EM_FLOW_FREE:
case HWRM_CFA_EM_FLOW_CFG:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 3eedd44..0c3d224 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -89,7 +89,7 @@ static int bnxt_fw_reset_recover(struct devlink_health_reporter *reporter,
return -EOPNOTSUPP;
bnxt_fw_reset(bp);
- return 0;
+ return -EINPROGRESS;
}
static const
@@ -116,7 +116,7 @@ static int bnxt_fw_fatal_recover(struct devlink_health_reporter *reporter,
else if (event == BNXT_FW_EXCEPTION_SP_EVENT)
bnxt_fw_exception(bp);
- return 0;
+ return -EINPROGRESS;
}
static const
@@ -262,6 +262,16 @@ void bnxt_dl_health_status_update(struct bnxt *bp, bool healthy)
health->fatal = false;
}
+void bnxt_dl_health_recovery_done(struct bnxt *bp)
+{
+ struct bnxt_fw_health *hlth = bp->fw_health;
+
+ if (hlth->fatal)
+ devlink_health_reporter_recovery_done(hlth->fw_fatal_reporter);
+ else
+ devlink_health_reporter_recovery_done(hlth->fw_reset_reporter);
+}
+
static const struct devlink_ops bnxt_dl_ops = {
#ifdef CONFIG_BNXT_SRIOV
.eswitch_mode_set = bnxt_dl_eswitch_mode_set,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index 6db6c3d..08aaa44 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -58,6 +58,7 @@ struct bnxt_dl_nvm_param {
void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event);
void bnxt_dl_health_status_update(struct bnxt *bp, bool healthy);
+void bnxt_dl_health_recovery_done(struct bnxt *bp);
void bnxt_dl_fw_reporters_create(struct bnxt *bp);
void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all);
int bnxt_dl_register(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index f9bf7d7..b010b34 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -398,6 +398,9 @@ static int bnxt_vf_reps_create(struct bnxt *bp)
struct net_device *dev;
int rc, i;
+ if (!(bp->flags & BNXT_FLAG_DSN_VALID))
+ return -ENODEV;
+
bp->vf_reps = kcalloc(num_vfs, sizeof(vf_rep), GFP_KERNEL);
if (!bp->vf_reps)
return -ENOMEM;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 3ee7917..e50a153 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1225,18 +1225,6 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
}
}
-/* ioctl handle special commands that are not present in ethtool. */
-static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- if (!netif_running(dev))
- return -EINVAL;
-
- if (!dev->phydev)
- return -ENODEV;
-
- return phy_mii_ioctl(dev->phydev, rq, cmd);
-}
-
static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
struct bcmgenet_tx_ring *ring)
{
@@ -2169,8 +2157,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
DMA_END_ADDR);
/* Initialize Tx NAPI */
- netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
- NAPI_POLL_WEIGHT);
+ netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
+ NAPI_POLL_WEIGHT);
}
/* Initialize a RDMA ring */
@@ -3222,7 +3210,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
.ndo_tx_timeout = bcmgenet_timeout,
.ndo_set_rx_mode = bcmgenet_set_rx_mode,
.ndo_set_mac_address = bcmgenet_set_mac_addr,
- .ndo_do_ioctl = bcmgenet_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_set_features = bcmgenet_set_features,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = bcmgenet_poll_controller,
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 460b499..8846625 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7874,8 +7874,8 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *);
static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi,
struct netdev_queue *txq, struct sk_buff *skb)
{
- struct sk_buff *segs, *nskb;
u32 frag_cnt_est = skb_shinfo(skb)->gso_segs * 3;
+ struct sk_buff *segs, *seg, *next;
/* Estimate the number of fragments in the worst case */
if (unlikely(tg3_tx_avail(tnapi) <= frag_cnt_est)) {
@@ -7898,12 +7898,10 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi,
if (IS_ERR(segs) || !segs)
goto tg3_tso_bug_end;
- do {
- nskb = segs;
- segs = segs->next;
- nskb->next = NULL;
- tg3_start_xmit(nskb, tp->dev);
- } while (segs);
+ skb_list_walk_safe(segs, seg, next) {
+ skb_mark_not_on_list(seg);
+ tg3_start_xmit(seg, tp->dev);
+ }
tg3_tso_bug_end:
dev_consume_skb_any(skb);
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 19fe4f4..dbf7070 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -630,10 +630,17 @@
#define GEM_CLK_DIV96 5
/* Constants for MAN register */
-#define MACB_MAN_SOF 1
-#define MACB_MAN_WRITE 1
-#define MACB_MAN_READ 2
-#define MACB_MAN_CODE 2
+#define MACB_MAN_C22_SOF 1
+#define MACB_MAN_C22_WRITE 1
+#define MACB_MAN_C22_READ 2
+#define MACB_MAN_C22_CODE 2
+
+#define MACB_MAN_C45_SOF 0
+#define MACB_MAN_C45_ADDR 0
+#define MACB_MAN_C45_WRITE 1
+#define MACB_MAN_C45_POST_READ_INCR 2
+#define MACB_MAN_C45_READ 3
+#define MACB_MAN_C45_CODE 2
/* Capability mask bits */
#define MACB_CAPS_ISR_CLEAR_ON_WRITE 0x00000001
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index c5ee363..7a2fe63 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -337,11 +337,30 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
if (status < 0)
goto mdio_read_exit;
- macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_SOF)
- | MACB_BF(RW, MACB_MAN_READ)
- | MACB_BF(PHYA, mii_id)
- | MACB_BF(REGA, regnum)
- | MACB_BF(CODE, MACB_MAN_CODE)));
+ if (regnum & MII_ADDR_C45) {
+ macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF)
+ | MACB_BF(RW, MACB_MAN_C45_ADDR)
+ | MACB_BF(PHYA, mii_id)
+ | MACB_BF(REGA, (regnum >> 16) & 0x1F)
+ | MACB_BF(DATA, regnum & 0xFFFF)
+ | MACB_BF(CODE, MACB_MAN_C45_CODE)));
+
+ status = macb_mdio_wait_for_idle(bp);
+ if (status < 0)
+ goto mdio_read_exit;
+
+ macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF)
+ | MACB_BF(RW, MACB_MAN_C45_READ)
+ | MACB_BF(PHYA, mii_id)
+ | MACB_BF(REGA, (regnum >> 16) & 0x1F)
+ | MACB_BF(CODE, MACB_MAN_C45_CODE)));
+ } else {
+ macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C22_SOF)
+ | MACB_BF(RW, MACB_MAN_C22_READ)
+ | MACB_BF(PHYA, mii_id)
+ | MACB_BF(REGA, regnum)
+ | MACB_BF(CODE, MACB_MAN_C22_CODE)));
+ }
status = macb_mdio_wait_for_idle(bp);
if (status < 0)
@@ -370,12 +389,32 @@ static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
if (status < 0)
goto mdio_write_exit;
- macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_SOF)
- | MACB_BF(RW, MACB_MAN_WRITE)
- | MACB_BF(PHYA, mii_id)
- | MACB_BF(REGA, regnum)
- | MACB_BF(CODE, MACB_MAN_CODE)
- | MACB_BF(DATA, value)));
+ if (regnum & MII_ADDR_C45) {
+ macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF)
+ | MACB_BF(RW, MACB_MAN_C45_ADDR)
+ | MACB_BF(PHYA, mii_id)
+ | MACB_BF(REGA, (regnum >> 16) & 0x1F)
+ | MACB_BF(DATA, regnum & 0xFFFF)
+ | MACB_BF(CODE, MACB_MAN_C45_CODE)));
+
+ status = macb_mdio_wait_for_idle(bp);
+ if (status < 0)
+ goto mdio_write_exit;
+
+ macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF)
+ | MACB_BF(RW, MACB_MAN_C45_WRITE)
+ | MACB_BF(PHYA, mii_id)
+ | MACB_BF(REGA, (regnum >> 16) & 0x1F)
+ | MACB_BF(CODE, MACB_MAN_C45_CODE)
+ | MACB_BF(DATA, value)));
+ } else {
+ macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C22_SOF)
+ | MACB_BF(RW, MACB_MAN_C22_WRITE)
+ | MACB_BF(PHYA, mii_id)
+ | MACB_BF(REGA, regnum)
+ | MACB_BF(CODE, MACB_MAN_C22_CODE)
+ | MACB_BF(DATA, value)));
+ }
status = macb_mdio_wait_for_idle(bp);
if (status < 0)
@@ -611,21 +650,24 @@ static const struct phylink_mac_ops macb_phylink_ops = {
.mac_link_up = macb_mac_link_up,
};
+static bool macb_phy_handle_exists(struct device_node *dn)
+{
+ dn = of_parse_phandle(dn, "phy-handle", 0);
+ of_node_put(dn);
+ return dn != NULL;
+}
+
static int macb_phylink_connect(struct macb *bp)
{
+ struct device_node *dn = bp->pdev->dev.of_node;
struct net_device *dev = bp->dev;
struct phy_device *phydev;
int ret;
- if (bp->pdev->dev.of_node &&
- of_parse_phandle(bp->pdev->dev.of_node, "phy-handle", 0)) {
- ret = phylink_of_phy_connect(bp->phylink, bp->pdev->dev.of_node,
- 0);
- if (ret) {
- netdev_err(dev, "Could not attach PHY (%d)\n", ret);
- return ret;
- }
- } else {
+ if (dn)
+ ret = phylink_of_phy_connect(bp->phylink, dn, 0);
+
+ if (!dn || (ret && !macb_phy_handle_exists(dn))) {
phydev = phy_find_first(bp->mii_bus);
if (!phydev) {
netdev_err(dev, "no PHY found\n");
@@ -634,10 +676,11 @@ static int macb_phylink_connect(struct macb *bp)
/* attach the mac to the phy */
ret = phylink_connect_phy(bp->phylink, phydev);
- if (ret) {
- netdev_err(dev, "Could not attach to PHY (%d)\n", ret);
- return ret;
- }
+ }
+
+ if (ret) {
+ netdev_err(dev, "Could not attach PHY (%d)\n", ret);
+ return ret;
}
phylink_start(bp->phylink);
@@ -4088,7 +4131,7 @@ static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk,
mgmt->rate = 0;
mgmt->hw.init = &init;
- *tx_clk = clk_register(NULL, &mgmt->hw);
+ *tx_clk = devm_clk_register(&pdev->dev, &mgmt->hw);
if (IS_ERR(*tx_clk))
return PTR_ERR(*tx_clk);
@@ -4416,7 +4459,6 @@ static int macb_probe(struct platform_device *pdev)
err_disable_clocks:
clk_disable_unprepare(tx_clk);
- clk_unregister(tx_clk);
clk_disable_unprepare(hclk);
clk_disable_unprepare(pclk);
clk_disable_unprepare(rx_clk);
@@ -4446,7 +4488,6 @@ static int macb_remove(struct platform_device *pdev)
pm_runtime_dont_use_autosuspend(&pdev->dev);
if (!pm_runtime_suspended(&pdev->dev)) {
clk_disable_unprepare(bp->tx_clk);
- clk_unregister(bp->tx_clk);
clk_disable_unprepare(bp->hclk);
clk_disable_unprepare(bp->pclk);
clk_disable_unprepare(bp->rx_clk);
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index cdd7e5d..e957588 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -790,9 +790,7 @@ static int octeon_mgmt_ioctl(struct net_device *netdev,
case SIOCSHWTSTAMP:
return octeon_mgmt_ioctl_hwtstamp(netdev, rq, cmd);
default:
- if (netdev->phydev)
- return phy_mii_ioctl(netdev->phydev, rq, cmd);
- return -EINVAL;
+ return phy_do_ioctl(netdev, rq, cmd);
}
}
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 58f89f6..97ff860 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -2448,6 +2448,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
if (!is_offload(adapter))
return -EOPNOTSUPP;
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
if (!(adapter->flags & FULL_INIT_DONE))
return -EIO; /* need the memory controllers */
if (copy_from_user(&t, useraddr, sizeof(t)))
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index ee3aab56..9d1f2f8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -70,8 +70,7 @@ static void *seq_tab_start(struct seq_file *seq, loff_t *pos)
static void *seq_tab_next(struct seq_file *seq, void *v, loff_t *pos)
{
v = seq_tab_get_idx(seq->private, *pos + 1);
- if (v)
- ++*pos;
+ ++(*pos);
return v;
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 1930e39..649842a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3163,9 +3163,9 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
{
struct port_info *pi = netdev_priv(dev);
struct adapter *adap = pi->adapter;
+ struct ch_sched_queue qe = { 0 };
+ struct ch_sched_params p = { 0 };
struct sched_class *e;
- struct ch_sched_params p;
- struct ch_sched_queue qe;
u32 req_rate;
int err = 0;
@@ -3182,6 +3182,15 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
return -EINVAL;
}
+ qe.queue = index;
+ e = cxgb4_sched_queue_lookup(dev, &qe);
+ if (e && e->info.u.params.level != SCHED_CLASS_LEVEL_CL_RL) {
+ dev_err(adap->pdev_dev,
+ "Queue %u already bound to class %u of type: %u\n",
+ index, e->idx, e->info.u.params.level);
+ return -EBUSY;
+ }
+
/* Convert from Mbps to Kbps */
req_rate = rate * 1000;
@@ -3211,7 +3220,6 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
return 0;
/* Fetch any available unused or matching scheduling class */
- memset(&p, 0, sizeof(p));
p.type = SCHED_CLASS_TYPE_PACKET;
p.u.params.level = SCHED_CLASS_LEVEL_CL_RL;
p.u.params.mode = SCHED_CLASS_MODE_CLASS;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c
index 24c3c2dc..1b7681a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c
@@ -15,6 +15,8 @@ static int cxgb4_matchall_egress_validate(struct net_device *dev,
struct flow_action *actions = &cls->rule->action;
struct port_info *pi = netdev2pinfo(dev);
struct flow_action_entry *entry;
+ struct ch_sched_queue qe;
+ struct sched_class *e;
u64 max_link_rate;
u32 i, speed;
int ret;
@@ -60,9 +62,61 @@ static int cxgb4_matchall_egress_validate(struct net_device *dev,
}
}
+ for (i = 0; i < pi->nqsets; i++) {
+ memset(&qe, 0, sizeof(qe));
+ qe.queue = i;
+
+ e = cxgb4_sched_queue_lookup(dev, &qe);
+ if (e && e->info.u.params.level != SCHED_CLASS_LEVEL_CH_RL) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Some queues are already bound to different class");
+ return -EBUSY;
+ }
+ }
+
return 0;
}
+static int cxgb4_matchall_tc_bind_queues(struct net_device *dev, u32 tc)
+{
+ struct port_info *pi = netdev2pinfo(dev);
+ struct ch_sched_queue qe;
+ int ret;
+ u32 i;
+
+ for (i = 0; i < pi->nqsets; i++) {
+ qe.queue = i;
+ qe.class = tc;
+ ret = cxgb4_sched_class_bind(dev, &qe, SCHED_QUEUE);
+ if (ret)
+ goto out_free;
+ }
+
+ return 0;
+
+out_free:
+ while (i--) {
+ qe.queue = i;
+ qe.class = SCHED_CLS_NONE;
+ cxgb4_sched_class_unbind(dev, &qe, SCHED_QUEUE);
+ }
+
+ return ret;
+}
+
+static void cxgb4_matchall_tc_unbind_queues(struct net_device *dev)
+{
+ struct port_info *pi = netdev2pinfo(dev);
+ struct ch_sched_queue qe;
+ u32 i;
+
+ for (i = 0; i < pi->nqsets; i++) {
+ qe.queue = i;
+ qe.class = SCHED_CLS_NONE;
+ cxgb4_sched_class_unbind(dev, &qe, SCHED_QUEUE);
+ }
+}
+
static int cxgb4_matchall_alloc_tc(struct net_device *dev,
struct tc_cls_matchall_offload *cls)
{
@@ -83,6 +137,7 @@ static int cxgb4_matchall_alloc_tc(struct net_device *dev,
struct adapter *adap = netdev2adap(dev);
struct flow_action_entry *entry;
struct sched_class *e;
+ int ret;
u32 i;
tc_port_matchall = &adap->tc_matchall->port_matchall[pi->port_id];
@@ -101,10 +156,21 @@ static int cxgb4_matchall_alloc_tc(struct net_device *dev,
return -ENOMEM;
}
+ ret = cxgb4_matchall_tc_bind_queues(dev, e->idx);
+ if (ret) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Could not bind queues to traffic class");
+ goto out_free;
+ }
+
tc_port_matchall->egress.hwtc = e->idx;
tc_port_matchall->egress.cookie = cls->cookie;
tc_port_matchall->egress.state = CXGB4_MATCHALL_STATE_ENABLED;
return 0;
+
+out_free:
+ cxgb4_sched_class_free(dev, e->idx);
+ return ret;
}
static void cxgb4_matchall_free_tc(struct net_device *dev)
@@ -114,6 +180,7 @@ static void cxgb4_matchall_free_tc(struct net_device *dev)
struct adapter *adap = netdev2adap(dev);
tc_port_matchall = &adap->tc_matchall->port_matchall[pi->port_id];
+ cxgb4_matchall_tc_unbind_queues(dev);
cxgb4_sched_class_free(dev, tc_port_matchall->egress.hwtc);
tc_port_matchall->egress.hwtc = SCHED_CLS_NONE;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
index 8971ddd..ec3eb45 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
@@ -12,8 +12,9 @@ static int cxgb4_mqprio_validate(struct net_device *dev,
struct port_info *pi = netdev2pinfo(dev);
struct adapter *adap = netdev2adap(dev);
u32 speed, qcount = 0, qoffset = 0;
+ u32 start_a, start_b, end_a, end_b;
int ret;
- u8 i;
+ u8 i, j;
if (!mqprio->qopt.num_tc)
return 0;
@@ -47,6 +48,31 @@ static int cxgb4_mqprio_validate(struct net_device *dev,
qoffset = max_t(u16, mqprio->qopt.offset[i], qoffset);
qcount += mqprio->qopt.count[i];
+ start_a = mqprio->qopt.offset[i];
+ end_a = start_a + mqprio->qopt.count[i] - 1;
+ for (j = i + 1; j < mqprio->qopt.num_tc; j++) {
+ start_b = mqprio->qopt.offset[j];
+ end_b = start_b + mqprio->qopt.count[j] - 1;
+
+ /* If queue count is 0, then the traffic
+ * belonging to this class will not use
+ * ETHOFLD queues. So, no need to validate
+ * further.
+ */
+ if (!mqprio->qopt.count[i])
+ break;
+
+ if (!mqprio->qopt.count[j])
+ continue;
+
+ if (max_t(u32, start_a, start_b) <=
+ min_t(u32, end_a, end_b)) {
+ netdev_err(dev,
+ "Queues can't overlap across tc\n");
+ return -EINVAL;
+ }
+ }
+
/* Convert byte per second to bits per second */
min_rate += (mqprio->min_rate[i] * 8);
max_rate += (mqprio->max_rate[i] * 8);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index e9e4500..1a16449 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -678,8 +678,7 @@ static void *l2t_seq_start(struct seq_file *seq, loff_t *pos)
static void *l2t_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
v = l2t_get_idx(seq, *pos);
- if (v)
- ++*pos;
+ ++(*pos);
return v;
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c
index 3e61bd5..cebe141 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c
@@ -165,6 +165,22 @@ static void *t4_sched_entry_lookup(struct port_info *pi,
return found;
}
+struct sched_class *cxgb4_sched_queue_lookup(struct net_device *dev,
+ struct ch_sched_queue *p)
+{
+ struct port_info *pi = netdev2pinfo(dev);
+ struct sched_queue_entry *qe = NULL;
+ struct adapter *adap = pi->adapter;
+ struct sge_eth_txq *txq;
+
+ if (p->queue < 0 || p->queue >= pi->nqsets)
+ return NULL;
+
+ txq = &adap->sge.ethtxq[pi->first_qset + p->queue];
+ qe = t4_sched_entry_lookup(pi, SCHED_QUEUE, txq->q.cntxt_id);
+ return qe ? &pi->sched_tbl->tab[qe->param.class] : NULL;
+}
+
static int t4_sched_queue_unbind(struct port_info *pi, struct ch_sched_queue *p)
{
struct sched_queue_entry *qe = NULL;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.h b/drivers/net/ethernet/chelsio/cxgb4/sched.h
index e92ff68..5cc74a5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.h
@@ -103,6 +103,8 @@ static inline bool valid_class_id(struct net_device *dev, u8 class_id)
return true;
}
+struct sched_class *cxgb4_sched_queue_lookup(struct net_device *dev,
+ struct ch_sched_queue *p);
int cxgb4_sched_class_bind(struct net_device *dev, void *arg,
enum sched_bind_type type);
int cxgb4_sched_class_unbind(struct net_device *dev, void *arg,
diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index e249790..5f8fa11 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -725,19 +725,6 @@ static struct net_device_stats *dnet_get_stats(struct net_device *dev)
return nstat;
}
-static int dnet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- struct phy_device *phydev = dev->phydev;
-
- if (!netif_running(dev))
- return -EINVAL;
-
- if (!phydev)
- return -ENODEV;
-
- return phy_mii_ioctl(phydev, rq, cmd);
-}
-
static void dnet_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *info)
{
@@ -759,7 +746,7 @@ static const struct net_device_ops dnet_netdev_ops = {
.ndo_stop = dnet_close,
.ndo_get_stats = dnet_get_stats,
.ndo_start_xmit = dnet_start_xmit,
- .ndo_do_ioctl = dnet_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 48b3b72..4572797 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1536,15 +1536,6 @@ static int ftgmac100_stop(struct net_device *netdev)
return 0;
}
-/* optional */
-static int ftgmac100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
- if (!netdev->phydev)
- return -ENXIO;
-
- return phy_mii_ioctl(netdev->phydev, ifr, cmd);
-}
-
static void ftgmac100_tx_timeout(struct net_device *netdev, unsigned int txqueue)
{
struct ftgmac100 *priv = netdev_priv(netdev);
@@ -1597,7 +1588,7 @@ static const struct net_device_ops ftgmac100_netdev_ops = {
.ndo_start_xmit = ftgmac100_hard_start_xmit,
.ndo_set_mac_address = ftgmac100_set_mac_addr,
.ndo_validate_addr = eth_validate_addr,
- .ndo_do_ioctl = ftgmac100_do_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl,
.ndo_tx_timeout = ftgmac100_tx_timeout,
.ndo_set_rx_mode = ftgmac100_set_rx_mode,
.ndo_set_features = ftgmac100_set_features,
diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile
index 6a93293..67c4364 100644
--- a/drivers/net/ethernet/freescale/Makefile
+++ b/drivers/net/ethernet/freescale/Makefile
@@ -25,4 +25,5 @@
obj-$(CONFIG_FSL_DPAA2_ETH) += dpaa2/
obj-$(CONFIG_FSL_ENETC) += enetc/
+obj-$(CONFIG_FSL_ENETC_MDIO) += enetc/
obj-$(CONFIG_FSL_ENETC_VF) += enetc/
diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig
index edad4ca..fe942de 100644
--- a/drivers/net/ethernet/freescale/enetc/Kconfig
+++ b/drivers/net/ethernet/freescale/enetc/Kconfig
@@ -2,6 +2,7 @@
config FSL_ENETC
tristate "ENETC PF driver"
depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST)
+ select FSL_ENETC_MDIO
select PHYLIB
help
This driver supports NXP ENETC gigabit ethernet controller PCIe
diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile
index d0db33e..74f7ac2 100644
--- a/drivers/net/ethernet/freescale/enetc/Makefile
+++ b/drivers/net/ethernet/freescale/enetc/Makefile
@@ -3,7 +3,7 @@
common-objs := enetc.o enetc_cbdr.o enetc_ethtool.o
obj-$(CONFIG_FSL_ENETC) += fsl-enetc.o
-fsl-enetc-y := enetc_pf.o enetc_mdio.o $(common-objs)
+fsl-enetc-y := enetc_pf.o $(common-objs)
fsl-enetc-$(CONFIG_PCI_IOV) += enetc_msg.o
fsl-enetc-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 8375cd8..62554f2 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -200,6 +200,7 @@ enum enetc_bdr_type {TX, RX};
#define ENETC_PFPMR 0x1900
#define ENETC_PFPMR_PMACE BIT(1)
#define ENETC_PFPMR_MWLM BIT(0)
+#define ENETC_EMDIO_BASE 0x1c00
#define ENETC_PSIUMHFR0(n, err) (((err) ? 0x1d08 : 0x1d00) + (n) * 0x10)
#define ENETC_PSIUMHFR1(n) (0x1d04 + (n) * 0x10)
#define ENETC_PSIMMHFR0(n, err) (((err) ? 0x1d00 : 0x1d08) + (n) * 0x10)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c
index 149883c..48c32a1 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c
@@ -1,41 +1,56 @@
// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
/* Copyright 2019 NXP */
+#include <linux/fsl/enetc_mdio.h>
#include <linux/mdio.h>
#include <linux/of_mdio.h>
#include <linux/iopoll.h>
#include <linux/of.h>
-#include "enetc_mdio.h"
+#include "enetc_pf.h"
-#define ENETC_MDIO_REG_OFFSET 0x1c00
#define ENETC_MDIO_CFG 0x0 /* MDIO configuration and status */
#define ENETC_MDIO_CTL 0x4 /* MDIO control */
#define ENETC_MDIO_DATA 0x8 /* MDIO data */
#define ENETC_MDIO_ADDR 0xc /* MDIO address */
-#define enetc_mdio_rd(hw, off) \
- enetc_port_rd(hw, ENETC_##off + ENETC_MDIO_REG_OFFSET)
-#define enetc_mdio_wr(hw, off, val) \
- enetc_port_wr(hw, ENETC_##off + ENETC_MDIO_REG_OFFSET, val)
-#define enetc_mdio_rd_reg(off) enetc_mdio_rd(hw, off)
+static inline u32 _enetc_mdio_rd(struct enetc_mdio_priv *mdio_priv, int off)
+{
+ return enetc_port_rd(mdio_priv->hw, mdio_priv->mdio_base + off);
+}
-#define ENETC_MDC_DIV 258
+static inline void _enetc_mdio_wr(struct enetc_mdio_priv *mdio_priv, int off,
+ u32 val)
+{
+ enetc_port_wr(mdio_priv->hw, mdio_priv->mdio_base + off, val);
+}
+
+#define enetc_mdio_rd(mdio_priv, off) \
+ _enetc_mdio_rd(mdio_priv, ENETC_##off)
+#define enetc_mdio_wr(mdio_priv, off, val) \
+ _enetc_mdio_wr(mdio_priv, ENETC_##off, val)
+#define enetc_mdio_rd_reg(off) enetc_mdio_rd(mdio_priv, off)
#define MDIO_CFG_CLKDIV(x) ((((x) >> 1) & 0xff) << 8)
#define MDIO_CFG_BSY BIT(0)
#define MDIO_CFG_RD_ER BIT(1)
+#define MDIO_CFG_HOLD(x) (((x) << 2) & GENMASK(4, 2))
#define MDIO_CFG_ENC45 BIT(6)
/* external MDIO only - driven on neg MDC edge */
#define MDIO_CFG_NEG BIT(23)
+#define ENETC_EMDIO_CFG \
+ (MDIO_CFG_HOLD(2) | \
+ MDIO_CFG_CLKDIV(258) | \
+ MDIO_CFG_NEG)
+
#define MDIO_CTL_DEV_ADDR(x) ((x) & 0x1f)
#define MDIO_CTL_PORT_ADDR(x) (((x) & 0x1f) << 5)
#define MDIO_CTL_READ BIT(15)
#define MDIO_DATA(x) ((x) & 0xffff)
#define TIMEOUT 1000
-static int enetc_mdio_wait_complete(struct enetc_hw *hw)
+static int enetc_mdio_wait_complete(struct enetc_mdio_priv *mdio_priv)
{
u32 val;
@@ -46,12 +61,11 @@ static int enetc_mdio_wait_complete(struct enetc_hw *hw)
int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value)
{
struct enetc_mdio_priv *mdio_priv = bus->priv;
- struct enetc_hw *hw = mdio_priv->hw;
u32 mdio_ctl, mdio_cfg;
u16 dev_addr;
int ret;
- mdio_cfg = MDIO_CFG_CLKDIV(ENETC_MDC_DIV) | MDIO_CFG_NEG;
+ mdio_cfg = ENETC_EMDIO_CFG;
if (regnum & MII_ADDR_C45) {
dev_addr = (regnum >> 16) & 0x1f;
mdio_cfg |= MDIO_CFG_ENC45;
@@ -61,44 +75,44 @@ int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value)
mdio_cfg &= ~MDIO_CFG_ENC45;
}
- enetc_mdio_wr(hw, MDIO_CFG, mdio_cfg);
+ enetc_mdio_wr(mdio_priv, MDIO_CFG, mdio_cfg);
- ret = enetc_mdio_wait_complete(hw);
+ ret = enetc_mdio_wait_complete(mdio_priv);
if (ret)
return ret;
/* set port and dev addr */
mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr);
- enetc_mdio_wr(hw, MDIO_CTL, mdio_ctl);
+ enetc_mdio_wr(mdio_priv, MDIO_CTL, mdio_ctl);
/* set the register address */
if (regnum & MII_ADDR_C45) {
- enetc_mdio_wr(hw, MDIO_ADDR, regnum & 0xffff);
+ enetc_mdio_wr(mdio_priv, MDIO_ADDR, regnum & 0xffff);
- ret = enetc_mdio_wait_complete(hw);
+ ret = enetc_mdio_wait_complete(mdio_priv);
if (ret)
return ret;
}
/* write the value */
- enetc_mdio_wr(hw, MDIO_DATA, MDIO_DATA(value));
+ enetc_mdio_wr(mdio_priv, MDIO_DATA, MDIO_DATA(value));
- ret = enetc_mdio_wait_complete(hw);
+ ret = enetc_mdio_wait_complete(mdio_priv);
if (ret)
return ret;
return 0;
}
+EXPORT_SYMBOL_GPL(enetc_mdio_write);
int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
{
struct enetc_mdio_priv *mdio_priv = bus->priv;
- struct enetc_hw *hw = mdio_priv->hw;
u32 mdio_ctl, mdio_cfg;
u16 dev_addr, value;
int ret;
- mdio_cfg = MDIO_CFG_CLKDIV(ENETC_MDC_DIV) | MDIO_CFG_NEG;
+ mdio_cfg = ENETC_EMDIO_CFG;
if (regnum & MII_ADDR_C45) {
dev_addr = (regnum >> 16) & 0x1f;
mdio_cfg |= MDIO_CFG_ENC45;
@@ -107,86 +121,56 @@ int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
mdio_cfg &= ~MDIO_CFG_ENC45;
}
- enetc_mdio_wr(hw, MDIO_CFG, mdio_cfg);
+ enetc_mdio_wr(mdio_priv, MDIO_CFG, mdio_cfg);
- ret = enetc_mdio_wait_complete(hw);
+ ret = enetc_mdio_wait_complete(mdio_priv);
if (ret)
return ret;
/* set port and device addr */
mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr);
- enetc_mdio_wr(hw, MDIO_CTL, mdio_ctl);
+ enetc_mdio_wr(mdio_priv, MDIO_CTL, mdio_ctl);
/* set the register address */
if (regnum & MII_ADDR_C45) {
- enetc_mdio_wr(hw, MDIO_ADDR, regnum & 0xffff);
+ enetc_mdio_wr(mdio_priv, MDIO_ADDR, regnum & 0xffff);
- ret = enetc_mdio_wait_complete(hw);
+ ret = enetc_mdio_wait_complete(mdio_priv);
if (ret)
return ret;
}
/* initiate the read */
- enetc_mdio_wr(hw, MDIO_CTL, mdio_ctl | MDIO_CTL_READ);
+ enetc_mdio_wr(mdio_priv, MDIO_CTL, mdio_ctl | MDIO_CTL_READ);
- ret = enetc_mdio_wait_complete(hw);
+ ret = enetc_mdio_wait_complete(mdio_priv);
if (ret)
return ret;
/* return all Fs if nothing was there */
- if (enetc_mdio_rd(hw, MDIO_CFG) & MDIO_CFG_RD_ER) {
+ if (enetc_mdio_rd(mdio_priv, MDIO_CFG) & MDIO_CFG_RD_ER) {
dev_dbg(&bus->dev,
"Error while reading PHY%d reg at %d.%hhu\n",
phy_id, dev_addr, regnum);
return 0xffff;
}
- value = enetc_mdio_rd(hw, MDIO_DATA) & 0xffff;
+ value = enetc_mdio_rd(mdio_priv, MDIO_DATA) & 0xffff;
return value;
}
+EXPORT_SYMBOL_GPL(enetc_mdio_read);
-int enetc_mdio_probe(struct enetc_pf *pf)
+struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs)
{
- struct device *dev = &pf->si->pdev->dev;
- struct enetc_mdio_priv *mdio_priv;
- struct device_node *np;
- struct mii_bus *bus;
- int err;
+ struct enetc_hw *hw;
- bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv));
- if (!bus)
- return -ENOMEM;
+ hw = devm_kzalloc(dev, sizeof(*hw), GFP_KERNEL);
+ if (!hw)
+ return ERR_PTR(-ENOMEM);
- bus->name = "Freescale ENETC MDIO Bus";
- bus->read = enetc_mdio_read;
- bus->write = enetc_mdio_write;
- bus->parent = dev;
- mdio_priv = bus->priv;
- mdio_priv->hw = &pf->si->hw;
- snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev));
+ hw->port = port_regs;
- np = of_get_child_by_name(dev->of_node, "mdio");
- if (!np) {
- dev_err(dev, "MDIO node missing\n");
- return -EINVAL;
- }
-
- err = of_mdiobus_register(bus, np);
- if (err) {
- of_node_put(np);
- dev_err(dev, "cannot register MDIO bus\n");
- return err;
- }
-
- of_node_put(np);
- pf->mdio = bus;
-
- return 0;
+ return hw;
}
-
-void enetc_mdio_remove(struct enetc_pf *pf)
-{
- if (pf->mdio)
- mdiobus_unregister(pf->mdio);
-}
+EXPORT_SYMBOL_GPL(enetc_hw_alloc);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.h b/drivers/net/ethernet/freescale/enetc/enetc_mdio.h
deleted file mode 100644
index 60c9a38..0000000
--- a/drivers/net/ethernet/freescale/enetc/enetc_mdio.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
-/* Copyright 2019 NXP */
-
-#include <linux/phy.h>
-#include "enetc_pf.h"
-
-struct enetc_mdio_priv {
- struct enetc_hw *hw;
-};
-
-int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value);
-int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c
index fbd41ce..ebc635f 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c
@@ -1,7 +1,8 @@
// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
/* Copyright 2019 NXP */
+#include <linux/fsl/enetc_mdio.h>
#include <linux/of_mdio.h>
-#include "enetc_mdio.h"
+#include "enetc_pf.h"
#define ENETC_MDIO_DEV_ID 0xee01
#define ENETC_MDIO_DEV_NAME "FSL PCIe IE Central MDIO"
@@ -13,17 +14,29 @@ static int enetc_pci_mdio_probe(struct pci_dev *pdev,
{
struct enetc_mdio_priv *mdio_priv;
struct device *dev = &pdev->dev;
+ void __iomem *port_regs;
struct enetc_hw *hw;
struct mii_bus *bus;
int err;
- hw = devm_kzalloc(dev, sizeof(*hw), GFP_KERNEL);
- if (!hw)
- return -ENOMEM;
+ port_regs = pci_iomap(pdev, 0, 0);
+ if (!port_regs) {
+ dev_err(dev, "iomap failed\n");
+ err = -ENXIO;
+ goto err_ioremap;
+ }
+
+ hw = enetc_hw_alloc(dev, port_regs);
+ if (IS_ERR(hw)) {
+ err = PTR_ERR(hw);
+ goto err_hw_alloc;
+ }
bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv));
- if (!bus)
- return -ENOMEM;
+ if (!bus) {
+ err = -ENOMEM;
+ goto err_mdiobus_alloc;
+ }
bus->name = ENETC_MDIO_BUS_NAME;
bus->read = enetc_mdio_read;
@@ -31,13 +44,14 @@ static int enetc_pci_mdio_probe(struct pci_dev *pdev,
bus->parent = dev;
mdio_priv = bus->priv;
mdio_priv->hw = hw;
+ mdio_priv->mdio_base = ENETC_EMDIO_BASE;
snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev));
pcie_flr(pdev);
err = pci_enable_device_mem(pdev);
if (err) {
dev_err(dev, "device enable failed\n");
- return err;
+ goto err_pci_enable;
}
err = pci_request_region(pdev, 0, KBUILD_MODNAME);
@@ -46,13 +60,6 @@ static int enetc_pci_mdio_probe(struct pci_dev *pdev,
goto err_pci_mem_reg;
}
- hw->port = pci_iomap(pdev, 0, 0);
- if (!hw->port) {
- err = -ENXIO;
- dev_err(dev, "iomap failed\n");
- goto err_ioremap;
- }
-
err = of_mdiobus_register(bus, dev->of_node);
if (err)
goto err_mdiobus_reg;
@@ -62,12 +69,14 @@ static int enetc_pci_mdio_probe(struct pci_dev *pdev,
return 0;
err_mdiobus_reg:
- iounmap(mdio_priv->hw->port);
-err_ioremap:
pci_release_mem_regions(pdev);
err_pci_mem_reg:
pci_disable_device(pdev);
-
+err_pci_enable:
+err_mdiobus_alloc:
+ iounmap(port_regs);
+err_hw_alloc:
+err_ioremap:
return err;
}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index e7482d4..fc0d7d9 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -2,6 +2,7 @@
/* Copyright 2017-2019 NXP */
#include <linux/module.h>
+#include <linux/fsl/enetc_mdio.h>
#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include "enetc_pf.h"
@@ -749,6 +750,52 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr);
}
+static int enetc_mdio_probe(struct enetc_pf *pf)
+{
+ struct device *dev = &pf->si->pdev->dev;
+ struct enetc_mdio_priv *mdio_priv;
+ struct device_node *np;
+ struct mii_bus *bus;
+ int err;
+
+ bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv));
+ if (!bus)
+ return -ENOMEM;
+
+ bus->name = "Freescale ENETC MDIO Bus";
+ bus->read = enetc_mdio_read;
+ bus->write = enetc_mdio_write;
+ bus->parent = dev;
+ mdio_priv = bus->priv;
+ mdio_priv->hw = &pf->si->hw;
+ mdio_priv->mdio_base = ENETC_EMDIO_BASE;
+ snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev));
+
+ np = of_get_child_by_name(dev->of_node, "mdio");
+ if (!np) {
+ dev_err(dev, "MDIO node missing\n");
+ return -EINVAL;
+ }
+
+ err = of_mdiobus_register(bus, np);
+ if (err) {
+ of_node_put(np);
+ dev_err(dev, "cannot register MDIO bus\n");
+ return err;
+ }
+
+ of_node_put(np);
+ pf->mdio = bus;
+
+ return 0;
+}
+
+static void enetc_mdio_remove(struct enetc_pf *pf)
+{
+ if (pf->mdio)
+ mdiobus_unregister(pf->mdio);
+}
+
static int enetc_of_get_phy(struct enetc_ndev_priv *priv)
{
struct enetc_pf *pf = enetc_si_priv(priv->si);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
index 10dd1b5..59e65a6 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -49,7 +49,3 @@ struct enetc_pf {
int enetc_msg_psi_init(struct enetc_pf *pf);
void enetc_msg_psi_free(struct enetc_pf *pf);
void enetc_msg_handle_rxmsg(struct enetc_pf *pf, int mbox_id, u16 *status);
-
-/* MDIO */
-int enetc_mdio_probe(struct enetc_pf *pf);
-void enetc_mdio_remove(struct enetc_pf *pf);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
index e910aaf..0c6bf3a 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
@@ -36,7 +36,6 @@ void enetc_sched_speed_set(struct net_device *ndev)
case SPEED_10:
default:
pspeed = ENETC_PMR_PSPEED_10M;
- netdev_err(ndev, "Qbv PSPEED set speed link down.\n");
}
priv->speed = speed;
@@ -315,7 +314,7 @@ int enetc_setup_tc_txtime(struct net_device *ndev, void *type_data)
tc = qopt->queue;
- if (tc < 0 || tc > priv->num_tx_rings)
+ if (tc < 0 || tc >= priv->num_tx_rings)
return -EINVAL;
/* Do not support TXSTART and TX CSUM offload simutaniously */
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 798fed3..4432a59 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2199,8 +2199,14 @@ static void fec_enet_get_regs(struct net_device *ndev,
{
struct fec_enet_private *fep = netdev_priv(ndev);
u32 __iomem *theregs = (u32 __iomem *)fep->hwp;
+ struct device *dev = &fep->pdev->dev;
u32 *buf = (u32 *)regbuf;
u32 i, off;
+ int ret;
+
+ ret = pm_runtime_get_sync(dev);
+ if (ret < 0)
+ return;
regs->version = fec_enet_register_version;
@@ -2216,6 +2222,9 @@ static void fec_enet_get_regs(struct net_device *ndev,
off >>= 2;
buf[off] = readl(&theregs[off]);
}
+
+ pm_runtime_mark_last_busy(dev);
+ pm_runtime_put_autosuspend(dev);
}
static int fec_enet_get_ts_info(struct net_device *ndev,
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c
index de52784..7a3f066 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c
@@ -785,16 +785,6 @@ static const struct ethtool_ops mpc52xx_fec_ethtool_ops = {
};
-static int mpc52xx_fec_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- struct phy_device *phydev = dev->phydev;
-
- if (!phydev)
- return -ENOTSUPP;
-
- return phy_mii_ioctl(phydev, rq, cmd);
-}
-
static const struct net_device_ops mpc52xx_fec_netdev_ops = {
.ndo_open = mpc52xx_fec_open,
.ndo_stop = mpc52xx_fec_close,
@@ -802,7 +792,7 @@ static const struct net_device_ops mpc52xx_fec_netdev_ops = {
.ndo_set_rx_mode = mpc52xx_fec_set_multicast_list,
.ndo_set_mac_address = mpc52xx_fec_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
- .ndo_do_ioctl = mpc52xx_fec_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl,
.ndo_tx_timeout = mpc52xx_fec_tx_timeout,
.ndo_get_stats = mpc52xx_fec_get_stats,
#ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 41c6fa20..e190187 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -110,7 +110,7 @@ do { \
/* Interface Mode Register (IF_MODE) */
#define IF_MODE_MASK 0x00000003 /* 30-31 Mask on i/f mode bits */
-#define IF_MODE_XGMII 0x00000000 /* 30-31 XGMII (10G) interface */
+#define IF_MODE_10G 0x00000000 /* 30-31 10G interface */
#define IF_MODE_GMII 0x00000002 /* 30-31 GMII (1G) interface */
#define IF_MODE_RGMII 0x00000004
#define IF_MODE_RGMII_AUTO 0x00008000
@@ -440,7 +440,7 @@ static int init(struct memac_regs __iomem *regs, struct memac_cfg *cfg,
tmp = 0;
switch (phy_if) {
case PHY_INTERFACE_MODE_XGMII:
- tmp |= IF_MODE_XGMII;
+ tmp |= IF_MODE_10G;
break;
default:
tmp |= IF_MODE_GMII;
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 80903cd..add61fe 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -882,14 +882,6 @@ static const struct ethtool_ops fs_ethtool_ops = {
.set_tunable = fs_set_tunable,
};
-static int fs_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- if (!netif_running(dev))
- return -EINVAL;
-
- return phy_mii_ioctl(dev->phydev, rq, cmd);
-}
-
extern int fs_mii_connect(struct net_device *dev);
extern void fs_mii_disconnect(struct net_device *dev);
@@ -907,7 +899,7 @@ static const struct net_device_ops fs_enet_netdev_ops = {
.ndo_start_xmit = fs_enet_start_xmit,
.ndo_tx_timeout = fs_timeout,
.ndo_set_rx_mode = fs_set_multicast_list,
- .ndo_do_ioctl = fs_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
#ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c
index e03b30c..c82c85e 100644
--- a/drivers/net/ethernet/freescale/xgmac_mdio.c
+++ b/drivers/net/ethernet/freescale/xgmac_mdio.c
@@ -49,6 +49,7 @@ struct tgec_mdio_controller {
struct mdio_fsl_priv {
struct tgec_mdio_controller __iomem *mdio_base;
bool is_little_endian;
+ bool has_a011043;
};
static u32 xgmac_read32(void __iomem *regs,
@@ -226,7 +227,8 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
return ret;
/* Return all Fs if nothing was there */
- if (xgmac_read32(®s->mdio_stat, endian) & MDIO_STAT_RD_ER) {
+ if ((xgmac_read32(®s->mdio_stat, endian) & MDIO_STAT_RD_ER) &&
+ !priv->has_a011043) {
dev_err(&bus->dev,
"Error while reading PHY%d reg at %d.%hhu\n",
phy_id, dev_addr, regnum);
@@ -274,6 +276,9 @@ static int xgmac_mdio_probe(struct platform_device *pdev)
priv->is_little_endian = of_property_read_bool(pdev->dev.of_node,
"little-endian");
+ priv->has_a011043 = of_property_read_bool(pdev->dev.of_node,
+ "fsl,erratum-a011043");
+
ret = of_mdiobus_register(bus, np);
if (ret) {
dev_err(&pdev->dev, "cannot register MDIO bus\n");
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index edec61d..9f52e72 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -418,8 +418,6 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget,
rx->cnt = cnt;
rx->fill_cnt += work_done;
- /* restock desc ring slots */
- dma_wmb(); /* Ensure descs are visible before ringing doorbell */
gve_rx_write_doorbell(priv, rx);
return gve_rx_work_pending(rx);
}
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index f488943..d0244fe 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -487,10 +487,6 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev)
* may have added descriptors without ringing the doorbell.
*/
- /* Ensure tx descs from a prior gve_tx are visible before
- * ringing doorbell.
- */
- dma_wmb();
gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
return NETDEV_TX_BUSY;
}
@@ -505,8 +501,6 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev)
if (!netif_xmit_stopped(tx->netdev_txq) && netdev_xmit_more())
return NETDEV_TX_OK;
- /* Ensure tx descs are visible before ringing doorbell */
- dma_wmb();
gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c
index 90ab7ad..57c3bc4 100644
--- a/drivers/net/ethernet/hisilicon/hisi_femac.c
+++ b/drivers/net/ethernet/hisilicon/hisi_femac.c
@@ -675,18 +675,6 @@ static void hisi_femac_net_set_rx_mode(struct net_device *dev)
}
}
-static int hisi_femac_net_ioctl(struct net_device *dev,
- struct ifreq *ifreq, int cmd)
-{
- if (!netif_running(dev))
- return -EINVAL;
-
- if (!dev->phydev)
- return -EINVAL;
-
- return phy_mii_ioctl(dev->phydev, ifreq, cmd);
-}
-
static const struct ethtool_ops hisi_femac_ethtools_ops = {
.get_link = ethtool_op_get_link,
.get_link_ksettings = phy_ethtool_get_link_ksettings,
@@ -697,7 +685,7 @@ static const struct net_device_ops hisi_femac_netdev_ops = {
.ndo_open = hisi_femac_net_open,
.ndo_stop = hisi_femac_net_close,
.ndo_start_xmit = hisi_femac_net_xmit,
- .ndo_do_ioctl = hisi_femac_net_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_set_mac_address = hisi_femac_set_mac_address,
.ndo_set_rx_mode = hisi_femac_net_set_rx_mode,
};
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index e45553e..c117074 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -565,7 +565,6 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
skb = *out_skb = napi_alloc_skb(&ring_data->napi,
HNS_RX_HEAD_SIZE);
if (unlikely(!skb)) {
- netdev_err(ndev, "alloc rx skb fail\n");
ring->stats.sw_err_cnt++;
return -ENOMEM;
}
@@ -1056,7 +1055,6 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget)
container_of(napi, struct hns_nic_ring_data, napi);
struct hnae_ring *ring = ring_data->ring;
-try_again:
clean_complete += ring_data->poll_one(
ring_data, budget - clean_complete,
ring_data->ex_process);
@@ -1066,7 +1064,7 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget)
napi_complete(napi);
ring->q->handle->dev->ops->toggle_ring_irq(ring, 0);
} else {
- goto try_again;
+ return budget;
}
}
@@ -1499,20 +1497,6 @@ static void hns_nic_net_timeout(struct net_device *ndev, unsigned int txqueue)
}
}
-static int hns_nic_do_ioctl(struct net_device *netdev, struct ifreq *ifr,
- int cmd)
-{
- struct phy_device *phy_dev = netdev->phydev;
-
- if (!netif_running(netdev))
- return -EINVAL;
-
- if (!phy_dev)
- return -ENOTSUPP;
-
- return phy_mii_ioctl(phy_dev, ifr, cmd);
-}
-
static netdev_tx_t hns_nic_net_xmit(struct sk_buff *skb,
struct net_device *ndev)
{
@@ -1960,7 +1944,7 @@ static const struct net_device_ops hns_nic_netdev_ops = {
.ndo_tx_timeout = hns_nic_net_timeout,
.ndo_set_mac_address = hns_nic_net_set_mac_address,
.ndo_change_mtu = hns_nic_change_mtu,
- .ndo_do_ioctl = hns_nic_do_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_set_features = hns_nic_set_features,
.ndo_fix_features = hns_nic_fix_features,
.ndo_get_stats64 = hns_nic_get_stats64,
diff --git a/drivers/net/ethernet/hisilicon/hns3/Makefile b/drivers/net/ethernet/hisilicon/hns3/Makefile
index d01bf53..7aa2fac 100644
--- a/drivers/net/ethernet/hisilicon/hns3/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/Makefile
@@ -3,6 +3,8 @@
# Makefile for the HISILICON network device drivers.
#
+ccflags-y += -I$(srctree)/$(src)
+
obj-$(CONFIG_HNS3) += hns3pf/
obj-$(CONFIG_HNS3) += hns3vf/
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 3b5e2d7..a3e4081b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -164,11 +164,7 @@ enum hnae3_reset_type {
HNAE3_IMP_RESET,
HNAE3_UNKNOWN_RESET,
HNAE3_NONE_RESET,
-};
-
-enum hnae3_flr_state {
- HNAE3_FLR_DOWN,
- HNAE3_FLR_DONE,
+ HNAE3_MAX_RESET,
};
enum hnae3_port_base_vlan_state {
@@ -575,8 +571,7 @@ struct hnae3_ae_algo {
const struct pci_device_id *pdev_id_table;
};
-#define HNAE3_INT_NAME_EXT_LEN 32 /* Max extra information length */
-#define HNAE3_INT_NAME_LEN (IFNAMSIZ + HNAE3_INT_NAME_EXT_LEN)
+#define HNAE3_INT_NAME_LEN 32
#define HNAE3_ITR_COUNTDOWN_START 100
struct hnae3_tc_info {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 6b328a2..1d4ffc5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -176,7 +176,7 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf)
return -EINVAL;
}
- ring = &priv->ring[q_num];
+ ring = &priv->ring[q_num];
value = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);
tx_index = (cnt == 1) ? value : tx_index;
@@ -209,10 +209,10 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf)
le16_to_cpu(tx_desc->tx.bdtp_fe_sc_vld_ra_ri));
dev_info(dev, "(TX)mss: %u\n", le16_to_cpu(tx_desc->tx.mss));
- ring = &priv->ring[q_num + h->kinfo.num_tqps];
+ ring = &priv->ring[q_num + h->kinfo.num_tqps];
value = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG);
rx_index = (cnt == 1) ? value : tx_index;
- rx_desc = &ring->desc[rx_index];
+ rx_desc = &ring->desc[rx_index];
addr = le64_to_cpu(rx_desc->addr);
dev_info(dev, "RX Queue Num: %u, BD Index: %u\n", q_num, rx_index);
@@ -297,8 +297,8 @@ static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
if (!buf)
return -ENOMEM;
- len = snprintf(buf, HNS3_DBG_READ_LEN, "%s\n",
- "Please echo help to cmd to get help information");
+ len = scnprintf(buf, HNS3_DBG_READ_LEN, "%s\n",
+ "Please echo help to cmd to get help information");
uncopy_bytes = copy_to_user(buffer, buf, len);
kfree(buf);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index aee5fac..acb796c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -24,6 +24,12 @@
#include "hnae3.h"
#include "hns3_enet.h"
+/* All hns3 tracepoints are defined by the include below, which
+ * must be included exactly once across the whole kernel with
+ * CREATE_TRACE_POINTS defined
+ */
+#define CREATE_TRACE_POINTS
+#include "hns3_trace.h"
#define hns3_set_field(origin, shift, val) ((origin) |= ((val) << (shift)))
#define hns3_tx_bd_count(S) DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE)
@@ -54,6 +60,8 @@ MODULE_PARM_DESC(debug, " Network interface message level setting");
#define HNS3_INNER_VLAN_TAG 1
#define HNS3_OUTER_VLAN_TAG 2
+#define HNS3_MIN_TX_LEN 33U
+
/* hns3_pci_tbl - PCI Device ID Table
*
* Last entry must be all 0s
@@ -127,18 +135,21 @@ static int hns3_nic_init_irq(struct hns3_nic_priv *priv)
continue;
if (tqp_vectors->tx_group.ring && tqp_vectors->rx_group.ring) {
- snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN - 1,
- "%s-%s-%d", priv->netdev->name, "TxRx",
- txrx_int_idx++);
+ snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN,
+ "%s-%s-%s-%d", hns3_driver_name,
+ pci_name(priv->ae_handle->pdev),
+ "TxRx", txrx_int_idx++);
txrx_int_idx++;
} else if (tqp_vectors->rx_group.ring) {
- snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN - 1,
- "%s-%s-%d", priv->netdev->name, "Rx",
- rx_int_idx++);
+ snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN,
+ "%s-%s-%s-%d", hns3_driver_name,
+ pci_name(priv->ae_handle->pdev),
+ "Rx", rx_int_idx++);
} else if (tqp_vectors->tx_group.ring) {
- snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN - 1,
- "%s-%s-%d", priv->netdev->name, "Tx",
- tx_int_idx++);
+ snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN,
+ "%s-%s-%s-%d", hns3_driver_name,
+ pci_name(priv->ae_handle->pdev),
+ "Tx", tx_int_idx++);
} else {
/* Skip this unused q_vector */
continue;
@@ -155,6 +166,8 @@ static int hns3_nic_init_irq(struct hns3_nic_priv *priv)
return ret;
}
+ disable_irq(tqp_vectors->vector_irq);
+
irq_set_affinity_hint(tqp_vectors->vector_irq,
&tqp_vectors->affinity_mask);
@@ -173,6 +186,7 @@ static void hns3_mask_vector_irq(struct hns3_enet_tqp_vector *tqp_vector,
static void hns3_vector_enable(struct hns3_enet_tqp_vector *tqp_vector)
{
napi_enable(&tqp_vector->napi);
+ enable_irq(tqp_vector->vector_irq);
/* enable vector */
hns3_mask_vector_irq(tqp_vector, 1);
@@ -372,18 +386,6 @@ static int hns3_nic_net_up(struct net_device *netdev)
if (ret)
return ret;
- /* the device can work without cpu rmap, only aRFS needs it */
- ret = hns3_set_rx_cpu_rmap(netdev);
- if (ret)
- netdev_warn(netdev, "set rx cpu rmap fail, ret=%d!\n", ret);
-
- /* get irq resource for all vectors */
- ret = hns3_nic_init_irq(priv);
- if (ret) {
- netdev_err(netdev, "init irq failed! ret=%d\n", ret);
- goto free_rmap;
- }
-
clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
/* enable the vectors */
@@ -396,22 +398,15 @@ static int hns3_nic_net_up(struct net_device *netdev)
/* start the ae_dev */
ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
- if (ret)
- goto out_start_err;
+ if (ret) {
+ set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
+ while (j--)
+ hns3_tqp_disable(h->kinfo.tqp[j]);
- return 0;
+ for (j = i - 1; j >= 0; j--)
+ hns3_vector_disable(&priv->tqp_vector[j]);
+ }
-out_start_err:
- set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
- while (j--)
- hns3_tqp_disable(h->kinfo.tqp[j]);
-
- for (j = i - 1; j >= 0; j--)
- hns3_vector_disable(&priv->tqp_vector[j]);
-
- hns3_nic_uninit_irq(priv);
-free_rmap:
- hns3_free_rx_cpu_rmap(netdev);
return ret;
}
@@ -508,11 +503,6 @@ static void hns3_nic_net_down(struct net_device *netdev)
if (ops->stop)
ops->stop(priv->ae_handle);
- hns3_free_rx_cpu_rmap(netdev);
-
- /* free irq resources */
- hns3_nic_uninit_irq(priv);
-
/* delay ring buffer clearing to hns3_reset_notify_uninit_enet
* during reset process, because driver may not be able
* to disable the ring through firmware when downing the netdev.
@@ -734,6 +724,8 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
/* get MSS for TSO */
*mss = skb_shinfo(skb)->gso_size;
+ trace_hns3_tso(skb);
+
return 0;
}
@@ -1138,6 +1130,7 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
desc->tx.bdtp_fe_sc_vld_ra_ri =
cpu_to_le16(BIT(HNS3_TXD_VLD_B));
+ trace_hns3_tx_desc(ring, ring->next_to_use);
ring_ptr_move_fw(ring, next_to_use);
return HNS3_LIKELY_BD_NUM;
}
@@ -1161,6 +1154,7 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
desc->tx.bdtp_fe_sc_vld_ra_ri =
cpu_to_le16(BIT(HNS3_TXD_VLD_B));
+ trace_hns3_tx_desc(ring, ring->next_to_use);
/* move ring pointer to next */
ring_ptr_move_fw(ring, next_to_use);
@@ -1286,6 +1280,14 @@ static bool hns3_skb_need_linearized(struct sk_buff *skb, unsigned int *bd_size,
return false;
}
+void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size)
+{
+ int i = 0;
+
+ for (i = 0; i < MAX_SKB_FRAGS; i++)
+ size[i] = skb_frag_size(&shinfo->frags[i]);
+}
+
static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
struct net_device *netdev,
struct sk_buff *skb)
@@ -1297,8 +1299,10 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
bd_num = hns3_tx_bd_num(skb, bd_size);
if (unlikely(bd_num > HNS3_MAX_NON_TSO_BD_NUM)) {
if (bd_num <= HNS3_MAX_TSO_BD_NUM && skb_is_gso(skb) &&
- !hns3_skb_need_linearized(skb, bd_size, bd_num))
+ !hns3_skb_need_linearized(skb, bd_size, bd_num)) {
+ trace_hns3_over_8bd(skb);
goto out;
+ }
if (__skb_linearize(skb))
return -ENOMEM;
@@ -1306,8 +1310,10 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
bd_num = hns3_tx_bd_count(skb->len);
if ((skb_is_gso(skb) && bd_num > HNS3_MAX_TSO_BD_NUM) ||
(!skb_is_gso(skb) &&
- bd_num > HNS3_MAX_NON_TSO_BD_NUM))
+ bd_num > HNS3_MAX_NON_TSO_BD_NUM)) {
+ trace_hns3_over_8bd(skb);
return -ENOMEM;
+ }
u64_stats_update_begin(&ring->syncp);
ring->stats.tx_copy++;
@@ -1405,6 +1411,10 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
int bd_num = 0;
int ret;
+ /* Hardware can only handle short frames above 32 bytes */
+ if (skb_put_padto(skb, HNS3_MIN_TX_LEN))
+ return NETDEV_TX_OK;
+
/* Prefetch the data used later */
prefetch(skb->data);
@@ -1448,6 +1458,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
(ring->desc_num - 1);
ring->desc[pre_ntu].tx.bdtp_fe_sc_vld_ra_ri |=
cpu_to_le16(BIT(HNS3_TXD_FE_B));
+ trace_hns3_tx_desc(ring, pre_ntu);
/* Complete translate all packets */
dev_queue = netdev_get_tx_queue(netdev, ring->queue_index);
@@ -2083,10 +2094,8 @@ static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
int ret;
ae_dev = devm_kzalloc(&pdev->dev, sizeof(*ae_dev), GFP_KERNEL);
- if (!ae_dev) {
- ret = -ENOMEM;
- return ret;
- }
+ if (!ae_dev)
+ return -ENOMEM;
ae_dev->pdev = pdev;
ae_dev->flag = ent->driver_data;
@@ -2529,8 +2538,8 @@ void hns3_clean_tx_ring(struct hns3_enet_ring *ring)
rmb(); /* Make sure head is ready before touch any data */
if (unlikely(!is_valid_clean_head(ring, head))) {
- netdev_err(netdev, "wrong head (%d, %d-%d)\n", head,
- ring->next_to_use, ring->next_to_clean);
+ hns3_rl_err(netdev, "wrong head (%d, %d-%d)\n", head,
+ ring->next_to_use, ring->next_to_clean);
u64_stats_update_begin(&ring->syncp);
ring->stats.io_err_cnt++;
@@ -2616,6 +2625,12 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
writel_relaxed(i, ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG);
}
+static bool hns3_page_is_reusable(struct page *page)
+{
+ return page_to_nid(page) == numa_mem_id() &&
+ !page_is_pfmemalloc(page);
+}
+
static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
struct hns3_enet_ring *ring, int pull_len,
struct hns3_desc_cb *desc_cb)
@@ -2630,7 +2645,7 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
/* Avoid re-using remote pages, or the stack is still using the page
* when page_offset rollback to zero, flag default unreuse
*/
- if (unlikely(page_to_nid(desc_cb->priv) != numa_mem_id()) ||
+ if (unlikely(!hns3_page_is_reusable(desc_cb->priv)) ||
(!desc_cb->page_offset && page_count(desc_cb->priv) > 1))
return;
@@ -2700,6 +2715,9 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
skb->csum_start = (unsigned char *)th - skb->head;
skb->csum_offset = offsetof(struct tcphdr, check);
skb->ip_summed = CHECKSUM_PARTIAL;
+
+ trace_hns3_gro(skb);
+
return 0;
}
@@ -2836,6 +2854,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
return -ENOMEM;
}
+ trace_hns3_rx_desc(ring);
prefetchw(skb->data);
ring->pending_buf = 1;
@@ -2845,7 +2864,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long)));
/* We can reuse buffer as-is, just make sure it is local */
- if (likely(page_to_nid(desc_cb->priv) == numa_mem_id()))
+ if (likely(hns3_page_is_reusable(desc_cb->priv)))
desc_cb->reuse_flag = 1;
else /* This page cannot be reused so discard it */
put_page(desc_cb->priv);
@@ -2910,6 +2929,7 @@ static int hns3_add_frag(struct hns3_enet_ring *ring)
}
hns3_nic_reuse_page(skb, ring->frag_num++, ring, 0, desc_cb);
+ trace_hns3_rx_desc(ring);
ring_ptr_move_fw(ring, next_to_clean);
ring->pending_buf++;
} while (!(bd_base_info & BIT(HNS3_RXD_FE_B)));
@@ -3614,19 +3634,13 @@ static void hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv)
hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain);
- if (tqp_vector->irq_init_flag == HNS3_VECTOR_INITED) {
- irq_set_affinity_hint(tqp_vector->vector_irq, NULL);
- free_irq(tqp_vector->vector_irq, tqp_vector);
- tqp_vector->irq_init_flag = HNS3_VECTOR_NOT_INITED;
- }
-
hns3_clear_ring_group(&tqp_vector->rx_group);
hns3_clear_ring_group(&tqp_vector->tx_group);
netif_napi_del(&priv->tqp_vector[i].napi);
}
}
-static int hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
+static void hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
{
struct hnae3_handle *h = priv->ae_handle;
struct pci_dev *pdev = h->pdev;
@@ -3638,11 +3652,10 @@ static int hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
tqp_vector = &priv->tqp_vector[i];
ret = h->ae_algo->ops->put_vector(h, tqp_vector->vector_irq);
if (ret)
- return ret;
+ return;
}
devm_kfree(&pdev->dev, priv->tqp_vector);
- return 0;
}
static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
@@ -4041,6 +4054,18 @@ static int hns3_client_init(struct hnae3_handle *handle)
goto out_reg_netdev_fail;
}
+ /* the device can work without cpu rmap, only aRFS needs it */
+ ret = hns3_set_rx_cpu_rmap(netdev);
+ if (ret)
+ dev_warn(priv->dev, "set rx cpu rmap fail, ret=%d\n", ret);
+
+ ret = hns3_nic_init_irq(priv);
+ if (ret) {
+ dev_err(priv->dev, "init irq failed! ret=%d\n", ret);
+ hns3_free_rx_cpu_rmap(netdev);
+ goto out_init_irq_fail;
+ }
+
ret = hns3_client_start(handle);
if (ret) {
dev_err(priv->dev, "hns3_client_start fail! ret=%d\n", ret);
@@ -4062,6 +4087,9 @@ static int hns3_client_init(struct hnae3_handle *handle)
return ret;
out_client_start:
+ hns3_free_rx_cpu_rmap(netdev);
+ hns3_nic_uninit_irq(priv);
+out_init_irq_fail:
unregister_netdev(netdev);
out_reg_netdev_fail:
hns3_uninit_phy(netdev);
@@ -4099,15 +4127,17 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
goto out_netdev_free;
}
+ hns3_free_rx_cpu_rmap(netdev);
+
+ hns3_nic_uninit_irq(priv);
+
hns3_del_all_fd_rules(netdev, true);
hns3_clear_all_ring(handle, true);
hns3_nic_uninit_vector_data(priv);
- ret = hns3_nic_dealloc_vector_data(priv);
- if (ret)
- netdev_err(netdev, "dealloc vector error\n");
+ hns3_nic_dealloc_vector_data(priv);
ret = hns3_uninit_all_ring(priv);
if (ret)
@@ -4434,17 +4464,32 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
if (ret)
goto err_uninit_vector;
+ /* the device can work without cpu rmap, only aRFS needs it */
+ ret = hns3_set_rx_cpu_rmap(netdev);
+ if (ret)
+ dev_warn(priv->dev, "set rx cpu rmap fail, ret=%d\n", ret);
+
+ ret = hns3_nic_init_irq(priv);
+ if (ret) {
+ dev_err(priv->dev, "init irq failed! ret=%d\n", ret);
+ hns3_free_rx_cpu_rmap(netdev);
+ goto err_init_irq_fail;
+ }
+
ret = hns3_client_start(handle);
if (ret) {
dev_err(priv->dev, "hns3_client_start fail! ret=%d\n", ret);
- goto err_uninit_ring;
+ goto err_client_start_fail;
}
set_bit(HNS3_NIC_STATE_INITED, &priv->state);
return ret;
-err_uninit_ring:
+err_client_start_fail:
+ hns3_free_rx_cpu_rmap(netdev);
+ hns3_nic_uninit_irq(priv);
+err_init_irq_fail:
hns3_uninit_all_ring(priv);
err_uninit_vector:
hns3_nic_uninit_vector_data(priv);
@@ -4494,6 +4539,8 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
return 0;
}
+ hns3_free_rx_cpu_rmap(netdev);
+ hns3_nic_uninit_irq(priv);
hns3_clear_all_ring(handle, true);
hns3_reset_tx_queue(priv->ae_handle);
@@ -4501,9 +4548,7 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
hns3_store_coal(priv);
- ret = hns3_nic_dealloc_vector_data(priv);
- if (ret)
- netdev_err(netdev, "dealloc vector error\n");
+ hns3_nic_dealloc_vector_data(priv);
ret = hns3_uninit_all_ring(priv);
if (ret)
@@ -4669,7 +4714,7 @@ static int __init hns3_init_module(void)
pr_info("%s: %s\n", hns3_driver_name, hns3_copyright);
client.type = HNAE3_CLIENT_KNIC;
- snprintf(client.name, HNAE3_CLIENT_NAME_LENGTH - 1, "%s",
+ snprintf(client.name, HNAE3_CLIENT_NAME_LENGTH, "%s",
hns3_driver_name);
client.ops = &client_ops;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 9d47abd..abefd7a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -673,4 +673,5 @@ void hns3_dbg_init(struct hnae3_handle *handle);
void hns3_dbg_uninit(struct hnae3_handle *handle);
void hns3_dbg_register_debugfs(const char *debugfs_dir_name);
void hns3_dbg_unregister_debugfs(void);
+void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size);
#endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 6e0212b..c03856e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -423,9 +423,8 @@ static void *hns3_update_strings(u8 *data, const struct hns3_stats *stats,
data[ETH_GSTRING_LEN - 1] = '\0';
/* first, prepend the prefix string */
- n1 = snprintf(data, MAX_PREFIX_SIZE, "%s%d_",
- prefix, i);
- n1 = min_t(uint, n1, MAX_PREFIX_SIZE - 1);
+ n1 = scnprintf(data, MAX_PREFIX_SIZE, "%s%d_",
+ prefix, i);
size_left = (ETH_GSTRING_LEN - 1) - n1;
/* now, concatenate the stats string to it */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3_trace.h
new file mode 100644
index 0000000..7bddcca
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_trace.h
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2018-2019 Hisilicon Limited. */
+
+/* This must be outside ifdef _HNS3_TRACE_H */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM hns3
+
+#if !defined(_HNS3_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _HNS3_TRACE_H_
+
+#include <linux/tracepoint.h>
+
+#define DESC_NR (sizeof(struct hns3_desc) / sizeof(u32))
+
+DECLARE_EVENT_CLASS(hns3_skb_template,
+ TP_PROTO(struct sk_buff *skb),
+ TP_ARGS(skb),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, headlen)
+ __field(unsigned int, len)
+ __field(__u8, nr_frags)
+ __field(__u8, ip_summed)
+ __field(unsigned int, hdr_len)
+ __field(unsigned short, gso_size)
+ __field(unsigned short, gso_segs)
+ __field(unsigned int, gso_type)
+ __field(bool, fraglist)
+ __array(__u32, size, MAX_SKB_FRAGS)
+ ),
+
+ TP_fast_assign(
+ __entry->headlen = skb_headlen(skb);
+ __entry->len = skb->len;
+ __entry->nr_frags = skb_shinfo(skb)->nr_frags;
+ __entry->gso_size = skb_shinfo(skb)->gso_size;
+ __entry->gso_segs = skb_shinfo(skb)->gso_segs;
+ __entry->gso_type = skb_shinfo(skb)->gso_type;
+ __entry->hdr_len = skb->encapsulation ?
+ skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb) :
+ skb_transport_offset(skb) + tcp_hdrlen(skb);
+ __entry->ip_summed = skb->ip_summed;
+ __entry->fraglist = skb_has_frag_list(skb);
+ hns3_shinfo_pack(skb_shinfo(skb), __entry->size);
+ ),
+
+ TP_printk(
+ "len: %u, %u, %u, cs: %u, gso: %u, %u, %x, frag(%d %u): %s",
+ __entry->headlen, __entry->len, __entry->hdr_len,
+ __entry->ip_summed, __entry->gso_size, __entry->gso_segs,
+ __entry->gso_type, __entry->fraglist, __entry->nr_frags,
+ __print_array(__entry->size, MAX_SKB_FRAGS, sizeof(__u32))
+ )
+);
+
+DEFINE_EVENT(hns3_skb_template, hns3_over_8bd,
+ TP_PROTO(struct sk_buff *skb),
+ TP_ARGS(skb));
+
+DEFINE_EVENT(hns3_skb_template, hns3_gro,
+ TP_PROTO(struct sk_buff *skb),
+ TP_ARGS(skb));
+
+DEFINE_EVENT(hns3_skb_template, hns3_tso,
+ TP_PROTO(struct sk_buff *skb),
+ TP_ARGS(skb));
+
+TRACE_EVENT(hns3_tx_desc,
+ TP_PROTO(struct hns3_enet_ring *ring, int cur_ntu),
+ TP_ARGS(ring, cur_ntu),
+
+ TP_STRUCT__entry(
+ __field(int, index)
+ __field(int, ntu)
+ __field(int, ntc)
+ __field(dma_addr_t, desc_dma)
+ __array(u32, desc, DESC_NR)
+ __string(devname, ring->tqp->handle->kinfo.netdev->name)
+ ),
+
+ TP_fast_assign(
+ __entry->index = ring->tqp->tqp_index;
+ __entry->ntu = ring->next_to_use;
+ __entry->ntc = ring->next_to_clean;
+ __entry->desc_dma = ring->desc_dma_addr,
+ memcpy(__entry->desc, &ring->desc[cur_ntu],
+ sizeof(struct hns3_desc));
+ __assign_str(devname, ring->tqp->handle->kinfo.netdev->name);
+ ),
+
+ TP_printk(
+ "%s-%d-%d/%d desc(%pad): %s",
+ __get_str(devname), __entry->index, __entry->ntu,
+ __entry->ntc, &__entry->desc_dma,
+ __print_array(__entry->desc, DESC_NR, sizeof(u32))
+ )
+);
+
+TRACE_EVENT(hns3_rx_desc,
+ TP_PROTO(struct hns3_enet_ring *ring),
+ TP_ARGS(ring),
+
+ TP_STRUCT__entry(
+ __field(int, index)
+ __field(int, ntu)
+ __field(int, ntc)
+ __field(dma_addr_t, desc_dma)
+ __field(dma_addr_t, buf_dma)
+ __array(u32, desc, DESC_NR)
+ __string(devname, ring->tqp->handle->kinfo.netdev->name)
+ ),
+
+ TP_fast_assign(
+ __entry->index = ring->tqp->tqp_index;
+ __entry->ntu = ring->next_to_use;
+ __entry->ntc = ring->next_to_clean;
+ __entry->desc_dma = ring->desc_dma_addr;
+ __entry->buf_dma = ring->desc_cb[ring->next_to_clean].dma;
+ memcpy(__entry->desc, &ring->desc[ring->next_to_clean],
+ sizeof(struct hns3_desc));
+ __assign_str(devname, ring->tqp->handle->kinfo.netdev->name);
+ ),
+
+ TP_printk(
+ "%s-%d-%d/%d desc(%pad) buf(%pad): %s",
+ __get_str(devname), __entry->index, __entry->ntu,
+ __entry->ntc, &__entry->desc_dma, &__entry->buf_dma,
+ __print_array(__entry->desc, DESC_NR, sizeof(u32))
+ )
+);
+
+#endif /* _HNS3_TRACE_H_ */
+
+/* This must be outside ifdef _HNS3_TRACE_H */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE hns3_trace
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index d97da67..96498d9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -6,6 +6,7 @@
#include <linux/types.h>
#include <linux/io.h>
#include <linux/etherdevice.h>
+#include "hnae3.h"
#define HCLGE_CMDQ_TX_TIMEOUT 30000
#define HCLGE_DESC_DATA_LEN 6
@@ -63,6 +64,7 @@ enum hclge_cmd_status {
struct hclge_misc_vector {
u8 __iomem *addr;
int vector_irq;
+ char name[HNAE3_INT_NAME_LEN];
};
struct hclge_cmq {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index f3d4cbd..67fad80 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -73,8 +73,6 @@ static struct hclge_dbg_reg_type_info hclge_dbg_reg_info[] = {
static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset)
{
-#define HCLGE_GET_DFX_REG_TYPE_CNT 4
-
struct hclge_desc desc[HCLGE_GET_DFX_REG_TYPE_CNT];
int entries_per_desc;
int index;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index dc66b4e..c85b72d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -505,7 +505,7 @@ static const struct hclge_hw_error hclge_ssu_mem_ecc_err_int[] = {
static const struct hclge_hw_error hclge_ssu_port_based_err_int[] = {
{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port",
- .reset_level = HNAE3_GLOBAL_RESET },
+ .reset_level = HNAE3_FUNC_RESET },
{ .int_msk = BIT(1), .msg = "tpu_pkt_without_key_port",
.reset_level = HNAE3_GLOBAL_RESET },
{ .int_msk = BIT(2), .msg = "igu_pkt_without_key_port",
@@ -599,7 +599,7 @@ static const struct hclge_hw_error hclge_ssu_ets_tcg_int[] = {
static const struct hclge_hw_error hclge_ssu_port_based_pf_int[] = {
{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port",
- .reset_level = HNAE3_GLOBAL_RESET },
+ .reset_level = HNAE3_FUNC_RESET },
{ .int_msk = BIT(9), .msg = "low_water_line_err_port",
.reset_level = HNAE3_NONE_RESET },
{ .int_msk = BIT(10), .msg = "hi_water_line_err_port",
@@ -1898,10 +1898,8 @@ static int hclge_handle_all_hw_msix_error(struct hclge_dev *hdev,
bd_num = max_t(u32, mpf_bd_num, pf_bd_num);
desc = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
- if (!desc) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!desc)
+ return -ENOMEM;
ret = hclge_handle_mpf_msix_error(hdev, desc, mpf_bd_num,
reset_requests);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 5e37439..ec5f6ee 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -862,9 +862,7 @@ static int hclge_query_function_status(struct hclge_dev *hdev)
usleep_range(1000, 2000);
} while (timeout++ < HCLGE_QUERY_MAX_CNT);
- ret = hclge_parse_func_status(hdev, req);
-
- return ret;
+ return hclge_parse_func_status(hdev, req);
}
static int hclge_query_pf_resource(struct hclge_dev *hdev)
@@ -882,12 +880,12 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
}
req = (struct hclge_pf_res_cmd *)desc.data;
- hdev->num_tqps = __le16_to_cpu(req->tqp_num);
- hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
+ hdev->num_tqps = le16_to_cpu(req->tqp_num);
+ hdev->pkt_buf_size = le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
if (req->tx_buf_size)
hdev->tx_buf_size =
- __le16_to_cpu(req->tx_buf_size) << HCLGE_BUF_UNIT_S;
+ le16_to_cpu(req->tx_buf_size) << HCLGE_BUF_UNIT_S;
else
hdev->tx_buf_size = HCLGE_DEFAULT_TX_BUF;
@@ -895,7 +893,7 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
if (req->dv_buf_size)
hdev->dv_buf_size =
- __le16_to_cpu(req->dv_buf_size) << HCLGE_BUF_UNIT_S;
+ le16_to_cpu(req->dv_buf_size) << HCLGE_BUF_UNIT_S;
else
hdev->dv_buf_size = HCLGE_DEFAULT_DV;
@@ -903,10 +901,10 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
if (hnae3_dev_roce_supported(hdev)) {
hdev->roce_base_msix_offset =
- hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
+ hnae3_get_field(le16_to_cpu(req->msixcap_localid_ba_rocee),
HCLGE_MSIX_OFT_ROCEE_M, HCLGE_MSIX_OFT_ROCEE_S);
hdev->num_roce_msi =
- hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
+ hnae3_get_field(le16_to_cpu(req->pf_intr_vector_number),
HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
/* nic's msix numbers is always equals to the roce's. */
@@ -919,7 +917,7 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
hdev->roce_base_msix_offset;
} else {
hdev->num_msi =
- hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
+ hnae3_get_field(le16_to_cpu(req->pf_intr_vector_number),
HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
hdev->num_nic_msi = hdev->num_msi;
@@ -1333,11 +1331,7 @@ static int hclge_get_cap(struct hclge_dev *hdev)
}
/* get pf resource */
- ret = hclge_query_pf_resource(hdev);
- if (ret)
- dev_err(&hdev->pdev->dev, "query pf resource error %d.\n", ret);
-
- return ret;
+ return hclge_query_pf_resource(hdev);
}
static void hclge_init_kdump_kernel_config(struct hclge_dev *hdev)
@@ -2621,30 +2615,21 @@ static int hclge_mac_init(struct hclge_dev *hdev)
hdev->hw.mac.duplex = HCLGE_MAC_FULL;
ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed,
hdev->hw.mac.duplex);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "Config mac speed dup fail ret=%d\n", ret);
+ if (ret)
return ret;
- }
if (hdev->hw.mac.support_autoneg) {
ret = hclge_set_autoneg_en(hdev, hdev->hw.mac.autoneg);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "Config mac autoneg fail ret=%d\n", ret);
+ if (ret)
return ret;
- }
}
mac->link = 0;
if (mac->user_fec_mode & BIT(HNAE3_FEC_USER_DEF)) {
ret = hclge_set_fec_hw(hdev, mac->user_fec_mode);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "Fec mode init fail, ret = %d\n", ret);
+ if (ret)
return ret;
- }
}
ret = hclge_set_mac_mtu(hdev, hdev->mps);
@@ -2835,6 +2820,12 @@ static int hclge_get_sfp_info(struct hclge_dev *hdev, struct hclge_mac *mac)
return ret;
}
+ /* In some case, mac speed get from IMP may be 0, it shouldn't be
+ * set to mac->speed.
+ */
+ if (!le32_to_cpu(resp->speed))
+ return 0;
+
mac->speed = le32_to_cpu(resp->speed);
/* if resp->speed_ability is 0, it means it's an old version
* firmware, do not update these params
@@ -2910,7 +2901,7 @@ static int hclge_get_status(struct hnae3_handle *handle)
static struct hclge_vport *hclge_get_vf_vport(struct hclge_dev *hdev, int vf)
{
- if (pci_num_vf(hdev->pdev) == 0) {
+ if (!pci_num_vf(hdev->pdev)) {
dev_err(&hdev->pdev->dev,
"SRIOV is disabled, can not get vport(%d) info.\n", vf);
return NULL;
@@ -3177,8 +3168,10 @@ static int hclge_misc_irq_init(struct hclge_dev *hdev)
hclge_get_misc_vector(hdev);
/* this would be explicitly freed in the end */
+ snprintf(hdev->misc_vector.name, HNAE3_INT_NAME_LEN, "%s-misc-%s",
+ HCLGE_NAME, pci_name(hdev->pdev));
ret = request_irq(hdev->misc_vector.vector_irq, hclge_misc_irq_handle,
- 0, "hclge_misc", hdev);
+ 0, hdev->misc_vector.name, hdev);
if (ret) {
hclge_free_vector(hdev, 0);
dev_err(&hdev->pdev->dev, "request misc irq(%d) fail\n",
@@ -3252,7 +3245,8 @@ static int hclge_notify_roce_client(struct hclge_dev *hdev,
static int hclge_reset_wait(struct hclge_dev *hdev)
{
#define HCLGE_RESET_WATI_MS 100
-#define HCLGE_RESET_WAIT_CNT 200
+#define HCLGE_RESET_WAIT_CNT 350
+
u32 val, reg, reg_bit;
u32 cnt = 0;
@@ -3269,8 +3263,6 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
reg = HCLGE_FUN_RST_ING;
reg_bit = HCLGE_FUN_RST_ING_B;
break;
- case HNAE3_FLR_RESET:
- break;
default:
dev_err(&hdev->pdev->dev,
"Wait for unsupported reset type: %d\n",
@@ -3278,20 +3270,6 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
return -EINVAL;
}
- if (hdev->reset_type == HNAE3_FLR_RESET) {
- while (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state) &&
- cnt++ < HCLGE_RESET_WAIT_CNT)
- msleep(HCLGE_RESET_WATI_MS);
-
- if (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state)) {
- dev_err(&hdev->pdev->dev,
- "flr wait timeout: %u\n", cnt);
- return -EBUSY;
- }
-
- return 0;
- }
-
val = hclge_read_dev(&hdev->hw, reg);
while (hnae3_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) {
msleep(HCLGE_RESET_WATI_MS);
@@ -3369,7 +3347,7 @@ static void hclge_mailbox_service_task(struct hclge_dev *hdev)
clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state);
}
-static int hclge_func_reset_sync_vf(struct hclge_dev *hdev)
+static void hclge_func_reset_sync_vf(struct hclge_dev *hdev)
{
struct hclge_pf_rst_sync_cmd *req;
struct hclge_desc desc;
@@ -3389,20 +3367,19 @@ static int hclge_func_reset_sync_vf(struct hclge_dev *hdev)
*/
if (ret == -EOPNOTSUPP) {
msleep(HCLGE_RESET_SYNC_TIME);
- return 0;
+ return;
} else if (ret) {
- dev_err(&hdev->pdev->dev, "sync with VF fail %d!\n",
- ret);
- return ret;
+ dev_warn(&hdev->pdev->dev, "sync with VF fail %d!\n",
+ ret);
+ return;
} else if (req->all_vf_ready) {
- return 0;
+ return;
}
msleep(HCLGE_PF_RESET_SYNC_TIME);
hclge_cmd_reuse_desc(&desc, true);
} while (cnt++ < HCLGE_PF_RESET_SYNC_CNT);
- dev_err(&hdev->pdev->dev, "sync with VF timeout!\n");
- return -ETIME;
+ dev_warn(&hdev->pdev->dev, "sync with VF timeout!\n");
}
void hclge_report_hw_error(struct hclge_dev *hdev,
@@ -3482,12 +3459,6 @@ static void hclge_do_reset(struct hclge_dev *hdev)
set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending);
hclge_reset_task_schedule(hdev);
break;
- case HNAE3_FLR_RESET:
- dev_info(&pdev->dev, "FLR requested\n");
- /* schedule again to check later */
- set_bit(HNAE3_FLR_RESET, &hdev->reset_pending);
- hclge_reset_task_schedule(hdev);
- break;
default:
dev_warn(&pdev->dev,
"Unsupported reset type: %d\n", hdev->reset_type);
@@ -3576,23 +3547,6 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
hclge_enable_vector(&hdev->misc_vector, true);
}
-static int hclge_reset_prepare_down(struct hclge_dev *hdev)
-{
- int ret = 0;
-
- switch (hdev->reset_type) {
- case HNAE3_FUNC_RESET:
- /* fall through */
- case HNAE3_FLR_RESET:
- ret = hclge_set_all_vf_rst(hdev, true);
- break;
- default:
- break;
- }
-
- return ret;
-}
-
static void hclge_reset_handshake(struct hclge_dev *hdev, bool enable)
{
u32 reg_val;
@@ -3606,6 +3560,19 @@ static void hclge_reset_handshake(struct hclge_dev *hdev, bool enable)
hclge_write_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG, reg_val);
}
+static int hclge_func_reset_notify_vf(struct hclge_dev *hdev)
+{
+ int ret;
+
+ ret = hclge_set_all_vf_rst(hdev, true);
+ if (ret)
+ return ret;
+
+ hclge_func_reset_sync_vf(hdev);
+
+ return 0;
+}
+
static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
{
u32 reg_val;
@@ -3613,10 +3580,7 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
switch (hdev->reset_type) {
case HNAE3_FUNC_RESET:
- /* to confirm whether all running VF is ready
- * before request PF reset
- */
- ret = hclge_func_reset_sync_vf(hdev);
+ ret = hclge_func_reset_notify_vf(hdev);
if (ret)
return ret;
@@ -3636,16 +3600,9 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
hdev->rst_stats.pf_rst_cnt++;
break;
case HNAE3_FLR_RESET:
- /* to confirm whether all running VF is ready
- * before request PF reset
- */
- ret = hclge_func_reset_sync_vf(hdev);
+ ret = hclge_func_reset_notify_vf(hdev);
if (ret)
return ret;
-
- set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
- set_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
- hdev->rst_stats.flr_rst_cnt++;
break;
case HNAE3_IMP_RESET:
hclge_handle_imp_error(hdev);
@@ -3774,10 +3731,9 @@ static int hclge_reset_stack(struct hclge_dev *hdev)
return hclge_notify_client(hdev, HNAE3_RESTORE_CLIENT);
}
-static void hclge_reset(struct hclge_dev *hdev)
+static int hclge_reset_prepare(struct hclge_dev *hdev)
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
- enum hnae3_reset_type reset_level;
int ret;
/* Initialize ae_dev reset status as well, in case enet layer wants to
@@ -3788,45 +3744,41 @@ static void hclge_reset(struct hclge_dev *hdev)
/* perform reset of the stack & ae device for a client */
ret = hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
if (ret)
- goto err_reset;
-
- ret = hclge_reset_prepare_down(hdev);
- if (ret)
- goto err_reset;
+ return ret;
rtnl_lock();
ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
- if (ret)
- goto err_reset_lock;
-
rtnl_unlock();
-
- ret = hclge_reset_prepare_wait(hdev);
if (ret)
- goto err_reset;
+ return ret;
- if (hclge_reset_wait(hdev))
- goto err_reset;
+ return hclge_reset_prepare_wait(hdev);
+}
+
+static int hclge_reset_rebuild(struct hclge_dev *hdev)
+{
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+ enum hnae3_reset_type reset_level;
+ int ret;
hdev->rst_stats.hw_reset_done_cnt++;
ret = hclge_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
if (ret)
- goto err_reset;
+ return ret;
rtnl_lock();
-
ret = hclge_reset_stack(hdev);
+ rtnl_unlock();
if (ret)
- goto err_reset_lock;
+ return ret;
hclge_clear_reset_cause(hdev);
ret = hclge_reset_prepare_up(hdev);
if (ret)
- goto err_reset_lock;
+ return ret;
- rtnl_unlock();
ret = hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
/* ignore RoCE notify error if it fails HCLGE_RESET_MAX_FAIL_CNT - 1
@@ -3834,19 +3786,17 @@ static void hclge_reset(struct hclge_dev *hdev)
*/
if (ret &&
hdev->rst_stats.reset_fail_cnt < HCLGE_RESET_MAX_FAIL_CNT - 1)
- goto err_reset;
+ return ret;
rtnl_lock();
-
ret = hclge_notify_client(hdev, HNAE3_UP_CLIENT);
- if (ret)
- goto err_reset_lock;
-
rtnl_unlock();
+ if (ret)
+ return ret;
ret = hclge_notify_roce_client(hdev, HNAE3_UP_CLIENT);
if (ret)
- goto err_reset;
+ return ret;
hdev->last_reset_time = jiffies;
hdev->rst_stats.reset_fail_cnt = 0;
@@ -3863,10 +3813,22 @@ static void hclge_reset(struct hclge_dev *hdev)
if (reset_level != HNAE3_NONE_RESET)
set_bit(reset_level, &hdev->reset_request);
+ return 0;
+}
+
+static void hclge_reset(struct hclge_dev *hdev)
+{
+ if (hclge_reset_prepare(hdev))
+ goto err_reset;
+
+ if (hclge_reset_wait(hdev))
+ goto err_reset;
+
+ if (hclge_reset_rebuild(hdev))
+ goto err_reset;
+
return;
-err_reset_lock:
- rtnl_unlock();
err_reset:
if (hclge_reset_err_handle(hdev))
hclge_reset_task_schedule(hdev);
@@ -3972,12 +3934,13 @@ static void hclge_reset_service_task(struct hclge_dev *hdev)
if (!test_and_clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state))
return;
- if (test_and_set_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
- return;
+ down(&hdev->reset_sem);
+ set_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
hclge_reset_subtask(hdev);
clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+ up(&hdev->reset_sem);
}
static void hclge_update_vport_alive(struct hclge_dev *hdev)
@@ -4123,7 +4086,7 @@ static int hclge_put_vector(struct hnae3_handle *handle, int vector)
vector_id = hclge_get_vector_index(hdev, vector);
if (vector_id < 0) {
dev_err(&hdev->pdev->dev,
- "Get vector index fail. vector_id =%d\n", vector_id);
+ "Get vector index fail. vector = %d\n", vector);
return vector_id;
}
@@ -4698,7 +4661,7 @@ static int hclge_map_ring_to_vector(struct hnae3_handle *handle, int vector,
vector_id = hclge_get_vector_index(hdev, vector);
if (vector_id < 0) {
dev_err(&hdev->pdev->dev,
- "Get vector index fail. vector_id =%d\n", vector_id);
+ "failed to get vector index. vector=%d\n", vector);
return vector_id;
}
@@ -6606,7 +6569,7 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en,
hclge_cfg_mac_mode(hdev, en);
- ret = hclge_mac_phy_link_status_wait(hdev, en, FALSE);
+ ret = hclge_mac_phy_link_status_wait(hdev, en, false);
if (ret)
dev_err(&hdev->pdev->dev,
"serdes loopback config mac mode timeout\n");
@@ -6664,7 +6627,7 @@ static int hclge_set_phy_loopback(struct hclge_dev *hdev, bool en)
hclge_cfg_mac_mode(hdev, en);
- ret = hclge_mac_phy_link_status_wait(hdev, en, TRUE);
+ ret = hclge_mac_phy_link_status_wait(hdev, en, true);
if (ret)
dev_err(&hdev->pdev->dev,
"phy loopback config mac mode timeout\n");
@@ -9324,30 +9287,53 @@ static void hclge_state_uninit(struct hclge_dev *hdev)
static void hclge_flr_prepare(struct hnae3_ae_dev *ae_dev)
{
-#define HCLGE_FLR_WAIT_MS 100
-#define HCLGE_FLR_WAIT_CNT 50
+#define HCLGE_FLR_RETRY_WAIT_MS 500
+#define HCLGE_FLR_RETRY_CNT 5
+
struct hclge_dev *hdev = ae_dev->priv;
- int cnt = 0;
+ int retry_cnt = 0;
+ int ret;
- clear_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
- clear_bit(HNAE3_FLR_DONE, &hdev->flr_state);
- set_bit(HNAE3_FLR_RESET, &hdev->default_reset_request);
- hclge_reset_event(hdev->pdev, NULL);
+retry:
+ down(&hdev->reset_sem);
+ set_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+ hdev->reset_type = HNAE3_FLR_RESET;
+ ret = hclge_reset_prepare(hdev);
+ if (ret) {
+ dev_err(&hdev->pdev->dev, "fail to prepare FLR, ret=%d\n",
+ ret);
+ if (hdev->reset_pending ||
+ retry_cnt++ < HCLGE_FLR_RETRY_CNT) {
+ dev_err(&hdev->pdev->dev,
+ "reset_pending:0x%lx, retry_cnt:%d\n",
+ hdev->reset_pending, retry_cnt);
+ clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+ up(&hdev->reset_sem);
+ msleep(HCLGE_FLR_RETRY_WAIT_MS);
+ goto retry;
+ }
+ }
- while (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state) &&
- cnt++ < HCLGE_FLR_WAIT_CNT)
- msleep(HCLGE_FLR_WAIT_MS);
-
- if (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state))
- dev_err(&hdev->pdev->dev,
- "flr wait down timeout: %d\n", cnt);
+ /* disable misc vector before FLR done */
+ hclge_enable_vector(&hdev->misc_vector, false);
+ set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+ hdev->rst_stats.flr_rst_cnt++;
}
static void hclge_flr_done(struct hnae3_ae_dev *ae_dev)
{
struct hclge_dev *hdev = ae_dev->priv;
+ int ret;
- set_bit(HNAE3_FLR_DONE, &hdev->flr_state);
+ hclge_enable_vector(&hdev->misc_vector, true);
+
+ ret = hclge_reset_rebuild(hdev);
+ if (ret)
+ dev_err(&hdev->pdev->dev, "fail to rebuild, ret=%d\n", ret);
+
+ hdev->reset_type = HNAE3_NONE_RESET;
+ clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+ up(&hdev->reset_sem);
}
static void hclge_clear_resetting_state(struct hclge_dev *hdev)
@@ -9390,19 +9376,16 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
mutex_init(&hdev->vport_lock);
spin_lock_init(&hdev->fd_rule_lock);
+ sema_init(&hdev->reset_sem, 1);
ret = hclge_pci_init(hdev);
- if (ret) {
- dev_err(&pdev->dev, "PCI init failed\n");
+ if (ret)
goto out;
- }
/* Firmware command queue initialize */
ret = hclge_cmd_queue_init(hdev);
- if (ret) {
- dev_err(&pdev->dev, "Cmd queue init failed, ret = %d.\n", ret);
+ if (ret)
goto err_pci_uninit;
- }
/* Firmware command initialize */
ret = hclge_cmd_init(hdev);
@@ -9410,11 +9393,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
goto err_cmd_uninit;
ret = hclge_get_cap(hdev);
- if (ret) {
- dev_err(&pdev->dev, "get hw capability error, ret = %d.\n",
- ret);
+ if (ret)
goto err_cmd_uninit;
- }
ret = hclge_configure(hdev);
if (ret) {
@@ -9429,12 +9409,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
}
ret = hclge_misc_irq_init(hdev);
- if (ret) {
- dev_err(&pdev->dev,
- "Misc IRQ(vector0) init error, ret = %d.\n",
- ret);
+ if (ret)
goto err_msi_uninit;
- }
ret = hclge_alloc_tqps(hdev);
if (ret) {
@@ -9443,31 +9419,22 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
}
ret = hclge_alloc_vport(hdev);
- if (ret) {
- dev_err(&pdev->dev, "Allocate vport error, ret = %d.\n", ret);
+ if (ret)
goto err_msi_irq_uninit;
- }
ret = hclge_map_tqp(hdev);
- if (ret) {
- dev_err(&pdev->dev, "Map tqp error, ret = %d.\n", ret);
+ if (ret)
goto err_msi_irq_uninit;
- }
if (hdev->hw.mac.media_type == HNAE3_MEDIA_TYPE_COPPER) {
ret = hclge_mac_mdio_config(hdev);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "mdio config fail ret=%d\n", ret);
+ if (ret)
goto err_msi_irq_uninit;
- }
}
ret = hclge_init_umv_space(hdev);
- if (ret) {
- dev_err(&pdev->dev, "umv space init error, ret=%d.\n", ret);
+ if (ret)
goto err_mdiobus_unreg;
- }
ret = hclge_mac_init(hdev);
if (ret) {
@@ -10202,10 +10169,8 @@ static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev,
int *bd_num_list,
u32 type_num)
{
-#define HCLGE_DFX_REG_BD_NUM 4
-
u32 entries_per_desc, desc_index, index, offset, i;
- struct hclge_desc desc[HCLGE_DFX_REG_BD_NUM];
+ struct hclge_desc desc[HCLGE_GET_DFX_REG_TYPE_CNT];
int ret;
ret = hclge_query_bd_num_cmd_send(hdev, desc);
@@ -10318,10 +10283,8 @@ static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
buf_len = sizeof(*desc_src) * bd_num_max;
desc_src = kzalloc(buf_len, GFP_KERNEL);
- if (!desc_src) {
- dev_err(&hdev->pdev->dev, "%s kzalloc failed\n", __func__);
+ if (!desc_src)
return -ENOMEM;
- }
for (i = 0; i < dfx_reg_type_num; i++) {
bd_num = bd_num_list[i];
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 4e5cfda..f78cbb4c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -139,6 +139,8 @@
#define HCLGE_PHY_MDIX_STATUS_B 6
#define HCLGE_PHY_SPEED_DUP_RESOLVE_B 11
+#define HCLGE_GET_DFX_REG_TYPE_CNT 4
+
/* Factor used to calculate offset and bitmap of VF num */
#define HCLGE_VF_NUM_PER_CMD 64
@@ -720,6 +722,7 @@ struct hclge_dev {
unsigned long reset_request; /* reset has been requested */
unsigned long reset_pending; /* client rst is pending to be served */
struct hclge_rst_stats rst_stats;
+ struct semaphore reset_sem; /* protect reset process */
u32 fw_version;
u16 num_vmdq_vport; /* Num vmdq vport this PF has set up */
u16 num_tqps; /* Num task queue pairs of this PF */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index f905dd3..a3c0822 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -86,10 +86,12 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len,
int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
{
struct hclge_dev *hdev = vport->back;
- enum hnae3_reset_type reset_type;
+ u16 reset_type;
u8 msg_data[2];
u8 dest_vfid;
+ BUILD_BUG_ON(HNAE3_MAX_RESET > U16_MAX);
+
dest_vfid = (u8)vport->vport_id;
if (hdev->reset_type == HNAE3_FUNC_RESET)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index c33b802..d659720 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1316,14 +1316,13 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle,
msg_data[0] = is_kill;
memcpy(&msg_data[1], &vlan_id, sizeof(vlan_id));
memcpy(&msg_data[3], &proto, sizeof(proto));
- ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
- HCLGE_MBX_VLAN_FILTER, msg_data,
- HCLGEVF_VLAN_MBX_MSG_LEN, true, NULL, 0);
-
/* when remove hw vlan filter failed, record the vlan id,
* and try to remove it from hw later, to be consistence
* with stack.
*/
+ ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
+ HCLGE_MBX_VLAN_FILTER, msg_data,
+ HCLGEVF_VLAN_MBX_MSG_LEN, true, NULL, 0);
if (is_kill && ret)
set_bit(vlan_id, hdev->vlan_del_fail_bmap);
@@ -1411,32 +1410,6 @@ static int hclgevf_notify_client(struct hclgevf_dev *hdev,
return ret;
}
-static void hclgevf_flr_done(struct hnae3_ae_dev *ae_dev)
-{
- struct hclgevf_dev *hdev = ae_dev->priv;
-
- set_bit(HNAE3_FLR_DONE, &hdev->flr_state);
-}
-
-static int hclgevf_flr_poll_timeout(struct hclgevf_dev *hdev,
- unsigned long delay_us,
- unsigned long wait_cnt)
-{
- unsigned long cnt = 0;
-
- while (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state) &&
- cnt++ < wait_cnt)
- usleep_range(delay_us, delay_us * 2);
-
- if (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state)) {
- dev_err(&hdev->pdev->dev,
- "flr wait timeout\n");
- return -ETIMEDOUT;
- }
-
- return 0;
-}
-
static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
{
#define HCLGEVF_RESET_WAIT_US 20000
@@ -1447,11 +1420,7 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
u32 val;
int ret;
- if (hdev->reset_type == HNAE3_FLR_RESET)
- return hclgevf_flr_poll_timeout(hdev,
- HCLGEVF_RESET_WAIT_US,
- HCLGEVF_RESET_WAIT_CNT);
- else if (hdev->reset_type == HNAE3_VF_RESET)
+ if (hdev->reset_type == HNAE3_VF_RESET)
ret = readl_poll_timeout(hdev->hw.io_base +
HCLGEVF_VF_RST_ING, val,
!(val & HCLGEVF_VF_RST_ING_BIT),
@@ -1523,7 +1492,8 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev)
/* clear handshake status with IMP */
hclgevf_reset_handshake(hdev, false);
- return 0;
+ /* bring up the nic to enable TX/RX again */
+ return hclgevf_notify_client(hdev, HNAE3_UP_CLIENT);
}
static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev)
@@ -1532,18 +1502,10 @@ static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev)
int ret = 0;
- switch (hdev->reset_type) {
- case HNAE3_VF_FUNC_RESET:
+ if (hdev->reset_type == HNAE3_VF_FUNC_RESET) {
ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_RESET, 0, NULL,
0, true, NULL, sizeof(u8));
hdev->rst_stats.vf_func_rst_cnt++;
- break;
- case HNAE3_FLR_RESET:
- set_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
- hdev->rst_stats.flr_rst_cnt++;
- break;
- default:
- break;
}
set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
@@ -1603,7 +1565,7 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev)
}
}
-static int hclgevf_reset(struct hclgevf_dev *hdev)
+static int hclgevf_reset_prepare(struct hclgevf_dev *hdev)
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
int ret;
@@ -1613,62 +1575,64 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
*/
ae_dev->reset_type = hdev->reset_type;
hdev->rst_stats.rst_cnt++;
- rtnl_lock();
+ rtnl_lock();
/* bring down the nic to stop any ongoing TX/RX */
ret = hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT);
- if (ret)
- goto err_reset_lock;
-
rtnl_unlock();
-
- ret = hclgevf_reset_prepare_wait(hdev);
if (ret)
- goto err_reset;
+ return ret;
- /* check if VF could successfully fetch the hardware reset completion
- * status from the hardware
- */
- ret = hclgevf_reset_wait(hdev);
- if (ret) {
- /* can't do much in this situation, will disable VF */
- dev_err(&hdev->pdev->dev,
- "VF failed(=%d) to fetch H/W reset completion status\n",
- ret);
- goto err_reset;
- }
+ return hclgevf_reset_prepare_wait(hdev);
+}
+
+static int hclgevf_reset_rebuild(struct hclgevf_dev *hdev)
+{
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+ int ret;
hdev->rst_stats.hw_rst_done_cnt++;
rtnl_lock();
-
/* now, re-initialize the nic client and ae device */
ret = hclgevf_reset_stack(hdev);
+ rtnl_unlock();
if (ret) {
dev_err(&hdev->pdev->dev, "failed to reset VF stack\n");
- goto err_reset_lock;
+ return ret;
}
- /* bring up the nic to enable TX/RX again */
- ret = hclgevf_notify_client(hdev, HNAE3_UP_CLIENT);
- if (ret)
- goto err_reset_lock;
-
- rtnl_unlock();
-
hdev->last_reset_time = jiffies;
ae_dev->reset_type = HNAE3_NONE_RESET;
hdev->rst_stats.rst_done_cnt++;
hdev->rst_stats.rst_fail_cnt = 0;
clear_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state);
- return ret;
-err_reset_lock:
- rtnl_unlock();
+ return 0;
+}
+
+static void hclgevf_reset(struct hclgevf_dev *hdev)
+{
+ if (hclgevf_reset_prepare(hdev))
+ goto err_reset;
+
+ /* check if VF could successfully fetch the hardware reset completion
+ * status from the hardware
+ */
+ if (hclgevf_reset_wait(hdev)) {
+ /* can't do much in this situation, will disable VF */
+ dev_err(&hdev->pdev->dev,
+ "failed to fetch H/W reset completion status\n");
+ goto err_reset;
+ }
+
+ if (hclgevf_reset_rebuild(hdev))
+ goto err_reset;
+
+ return;
+
err_reset:
hclgevf_reset_err_handle(hdev);
-
- return ret;
}
static enum hnae3_reset_type hclgevf_get_reset_level(struct hclgevf_dev *hdev,
@@ -1731,25 +1695,60 @@ static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
set_bit(rst_type, &hdev->default_reset_request);
}
+static void hclgevf_enable_vector(struct hclgevf_misc_vector *vector, bool en)
+{
+ writel(en ? 1 : 0, vector->addr);
+}
+
static void hclgevf_flr_prepare(struct hnae3_ae_dev *ae_dev)
{
-#define HCLGEVF_FLR_WAIT_MS 100
-#define HCLGEVF_FLR_WAIT_CNT 50
+#define HCLGEVF_FLR_RETRY_WAIT_MS 500
+#define HCLGEVF_FLR_RETRY_CNT 5
+
struct hclgevf_dev *hdev = ae_dev->priv;
- int cnt = 0;
+ int retry_cnt = 0;
+ int ret;
- clear_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
- clear_bit(HNAE3_FLR_DONE, &hdev->flr_state);
- set_bit(HNAE3_FLR_RESET, &hdev->default_reset_request);
- hclgevf_reset_event(hdev->pdev, NULL);
+retry:
+ down(&hdev->reset_sem);
+ set_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
+ hdev->reset_type = HNAE3_FLR_RESET;
+ ret = hclgevf_reset_prepare(hdev);
+ if (ret) {
+ dev_err(&hdev->pdev->dev, "fail to prepare FLR, ret=%d\n",
+ ret);
+ if (hdev->reset_pending ||
+ retry_cnt++ < HCLGEVF_FLR_RETRY_CNT) {
+ dev_err(&hdev->pdev->dev,
+ "reset_pending:0x%lx, retry_cnt:%d\n",
+ hdev->reset_pending, retry_cnt);
+ clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
+ up(&hdev->reset_sem);
+ msleep(HCLGEVF_FLR_RETRY_WAIT_MS);
+ goto retry;
+ }
+ }
- while (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state) &&
- cnt++ < HCLGEVF_FLR_WAIT_CNT)
- msleep(HCLGEVF_FLR_WAIT_MS);
+ /* disable misc vector before FLR done */
+ hclgevf_enable_vector(&hdev->misc_vector, false);
+ hdev->rst_stats.flr_rst_cnt++;
+}
- if (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state))
- dev_err(&hdev->pdev->dev,
- "flr wait down timeout: %d\n", cnt);
+static void hclgevf_flr_done(struct hnae3_ae_dev *ae_dev)
+{
+ struct hclgevf_dev *hdev = ae_dev->priv;
+ int ret;
+
+ hclgevf_enable_vector(&hdev->misc_vector, true);
+
+ ret = hclgevf_reset_rebuild(hdev);
+ if (ret)
+ dev_warn(&hdev->pdev->dev, "fail to rebuild, ret=%d\n",
+ ret);
+
+ hdev->reset_type = HNAE3_NONE_RESET;
+ clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
+ up(&hdev->reset_sem);
}
static u32 hclgevf_get_fw_version(struct hnae3_handle *handle)
@@ -1802,13 +1801,11 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev)
{
#define HCLGEVF_MAX_RESET_ATTEMPTS_CNT 3
- int ret;
-
if (!test_and_clear_bit(HCLGEVF_STATE_RST_SERVICE_SCHED, &hdev->state))
return;
- if (test_and_set_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state))
- return;
+ down(&hdev->reset_sem);
+ set_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
if (test_and_clear_bit(HCLGEVF_RESET_PENDING,
&hdev->reset_state)) {
@@ -1822,12 +1819,8 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev)
hdev->last_reset_time = jiffies;
while ((hdev->reset_type =
hclgevf_get_reset_level(hdev, &hdev->reset_pending))
- != HNAE3_NONE_RESET) {
- ret = hclgevf_reset(hdev);
- if (ret)
- dev_err(&hdev->pdev->dev,
- "VF stack reset failed %d.\n", ret);
- }
+ != HNAE3_NONE_RESET)
+ hclgevf_reset(hdev);
} else if (test_and_clear_bit(HCLGEVF_RESET_REQUESTED,
&hdev->reset_state)) {
/* we could be here when either of below happens:
@@ -1868,7 +1861,9 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev)
hclgevf_reset_task_schedule(hdev);
}
+ hdev->reset_type = HNAE3_NONE_RESET;
clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
+ up(&hdev->reset_sem);
}
static void hclgevf_mailbox_service_task(struct hclgevf_dev *hdev)
@@ -2012,11 +2007,6 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
return HCLGEVF_VECTOR0_EVENT_OTHER;
}
-static void hclgevf_enable_vector(struct hclgevf_misc_vector *vector, bool en)
-{
- writel(en ? 1 : 0, vector->addr);
-}
-
static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data)
{
enum hclgevf_evt_cause event_cause;
@@ -2291,6 +2281,7 @@ static void hclgevf_state_init(struct hclgevf_dev *hdev)
INIT_DELAYED_WORK(&hdev->service_task, hclgevf_service_task);
mutex_init(&hdev->mbx_resp.mbx_mutex);
+ sema_init(&hdev->reset_sem, 1);
/* bring the device down */
set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
@@ -2376,8 +2367,10 @@ static int hclgevf_misc_irq_init(struct hclgevf_dev *hdev)
hclgevf_get_misc_vector(hdev);
+ snprintf(hdev->misc_vector.name, HNAE3_INT_NAME_LEN, "%s-misc-%s",
+ HCLGEVF_NAME, pci_name(hdev->pdev));
ret = request_irq(hdev->misc_vector.vector_irq, hclgevf_misc_irq_handle,
- 0, "hclgevf_cmd", hdev);
+ 0, hdev->misc_vector.name, hdev);
if (ret) {
dev_err(&hdev->pdev->dev, "VF failed to request misc irq(%d)\n",
hdev->misc_vector.vector_irq);
@@ -2604,11 +2597,11 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
if (hnae3_dev_roce_supported(hdev)) {
hdev->roce_base_msix_offset =
- hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
+ hnae3_get_field(le16_to_cpu(req->msixcap_localid_ba_rocee),
HCLGEVF_MSIX_OFT_ROCEE_M,
HCLGEVF_MSIX_OFT_ROCEE_S);
hdev->num_roce_msix =
- hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number),
+ hnae3_get_field(le16_to_cpu(req->vf_intr_vector_number),
HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S);
/* nic's msix numbers is always equals to the roce's. */
@@ -2621,7 +2614,7 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
hdev->roce_base_msix_offset;
} else {
hdev->num_msi =
- hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number),
+ hnae3_get_field(le16_to_cpu(req->vf_intr_vector_number),
HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S);
hdev->num_nic_msix = hdev->num_msi;
@@ -2718,16 +2711,12 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
int ret;
ret = hclgevf_pci_init(hdev);
- if (ret) {
- dev_err(&pdev->dev, "PCI initialization failed\n");
+ if (ret)
return ret;
- }
ret = hclgevf_cmd_queue_init(hdev);
- if (ret) {
- dev_err(&pdev->dev, "Cmd queue init failed: %d\n", ret);
+ if (ret)
goto err_cmd_queue_init;
- }
ret = hclgevf_cmd_init(hdev);
if (ret)
@@ -2735,11 +2724,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
/* Get vf resource */
ret = hclgevf_query_vf_resource(hdev);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "Query vf status error, ret = %d.\n", ret);
+ if (ret)
goto err_cmd_init;
- }
ret = hclgevf_init_msi(hdev);
if (ret) {
@@ -2749,13 +2735,11 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
hclgevf_state_init(hdev);
hdev->reset_level = HNAE3_VF_FUNC_RESET;
+ hdev->reset_type = HNAE3_NONE_RESET;
ret = hclgevf_misc_irq_init(hdev);
- if (ret) {
- dev_err(&pdev->dev, "failed(%d) to init Misc IRQ(vector0)\n",
- ret);
+ if (ret)
goto err_misc_irq_init;
- }
set_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
@@ -2772,10 +2756,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
}
ret = hclgevf_set_handle_info(hdev);
- if (ret) {
- dev_err(&pdev->dev, "failed(%d) to set handle info\n", ret);
+ if (ret)
goto err_config;
- }
ret = hclgevf_config_gro(hdev, true);
if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 003114f..fee8d97 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -221,6 +221,7 @@ struct hclgevf_rss_cfg {
struct hclgevf_misc_vector {
u8 __iomem *addr;
int vector_irq;
+ char name[HNAE3_INT_NAME_LEN];
};
struct hclgevf_rst_stats {
@@ -252,6 +253,7 @@ struct hclgevf_dev {
unsigned long reset_state; /* requested, pending */
struct hclgevf_rst_stats rst_stats;
u32 reset_attempts;
+ struct semaphore reset_sem; /* protect reset process */
u32 fw_version;
u16 num_tqps; /* num task queue pairs of this PF */
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 6c51b1b..37a2314 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -185,13 +185,12 @@ struct e1000_phy_regs {
/* board specific private data structure */
struct e1000_adapter {
+ struct timer_list watchdog_timer;
struct timer_list phy_info_timer;
struct timer_list blink_timer;
struct work_struct reset_task;
- struct delayed_work watchdog_task;
-
- struct workqueue_struct *e1000_workqueue;
+ struct work_struct watchdog_task;
const struct e1000_info *ei;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 8797913..db4ea58 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1780,8 +1780,7 @@ static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data)
}
/* guard against interrupt when we're going down */
if (!test_bit(__E1000_DOWN, &adapter->state))
- mod_delayed_work(adapter->e1000_workqueue,
- &adapter->watchdog_task, HZ);
+ mod_timer(&adapter->watchdog_timer, jiffies + 1);
}
/* Reset on uncorrectable ECC error */
@@ -1861,8 +1860,7 @@ static irqreturn_t e1000_intr(int __always_unused irq, void *data)
}
/* guard against interrupt when we're going down */
if (!test_bit(__E1000_DOWN, &adapter->state))
- mod_delayed_work(adapter->e1000_workqueue,
- &adapter->watchdog_task, HZ);
+ mod_timer(&adapter->watchdog_timer, jiffies + 1);
}
/* Reset on uncorrectable ECC error */
@@ -1907,8 +1905,7 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data)
hw->mac.get_link_status = true;
/* guard against interrupt when we're going down */
if (!test_bit(__E1000_DOWN, &adapter->state))
- mod_delayed_work(adapter->e1000_workqueue,
- &adapter->watchdog_task, HZ);
+ mod_timer(&adapter->watchdog_timer, jiffies + 1);
}
if (!test_bit(__E1000_DOWN, &adapter->state))
@@ -4284,6 +4281,7 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset)
napi_synchronize(&adapter->napi);
+ del_timer_sync(&adapter->watchdog_timer);
del_timer_sync(&adapter->phy_info_timer);
spin_lock(&adapter->stats64_lock);
@@ -5156,11 +5154,25 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter)
}
}
+/**
+ * e1000_watchdog - Timer Call-back
+ * @data: pointer to adapter cast into an unsigned long
+ **/
+static void e1000_watchdog(struct timer_list *t)
+{
+ struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+
+ /* Do the rest outside of interrupt context */
+ schedule_work(&adapter->watchdog_task);
+
+ /* TODO: make this use queue_delayed_work() */
+}
+
static void e1000_watchdog_task(struct work_struct *work)
{
struct e1000_adapter *adapter = container_of(work,
struct e1000_adapter,
- watchdog_task.work);
+ watchdog_task);
struct net_device *netdev = adapter->netdev;
struct e1000_mac_info *mac = &adapter->hw.mac;
struct e1000_phy_info *phy = &adapter->hw.phy;
@@ -5408,9 +5420,8 @@ static void e1000_watchdog_task(struct work_struct *work)
/* Reset the timer */
if (!test_bit(__E1000_DOWN, &adapter->state))
- queue_delayed_work(adapter->e1000_workqueue,
- &adapter->watchdog_task,
- round_jiffies(2 * HZ));
+ mod_timer(&adapter->watchdog_timer,
+ round_jiffies(jiffies + 2 * HZ));
}
#define E1000_TX_FLAGS_CSUM 0x00000001
@@ -7450,21 +7461,11 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err_eeprom;
}
- adapter->e1000_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
- e1000e_driver_name);
-
- if (!adapter->e1000_workqueue) {
- err = -ENOMEM;
- goto err_workqueue;
- }
-
- INIT_DELAYED_WORK(&adapter->watchdog_task, e1000_watchdog_task);
- queue_delayed_work(adapter->e1000_workqueue, &adapter->watchdog_task,
- 0);
-
+ timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0);
timer_setup(&adapter->phy_info_timer, e1000_update_phy_info, 0);
INIT_WORK(&adapter->reset_task, e1000_reset_task);
+ INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task);
INIT_WORK(&adapter->downshift_task, e1000e_downshift_workaround);
INIT_WORK(&adapter->update_phy_task, e1000e_update_phy_task);
INIT_WORK(&adapter->print_hang_task, e1000_print_hw_hang);
@@ -7558,9 +7559,6 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
return 0;
err_register:
- flush_workqueue(adapter->e1000_workqueue);
- destroy_workqueue(adapter->e1000_workqueue);
-err_workqueue:
if (!(adapter->flags & FLAG_HAS_AMT))
e1000e_release_hw_control(adapter);
err_eeprom:
@@ -7605,17 +7603,15 @@ static void e1000_remove(struct pci_dev *pdev)
* from being rescheduled.
*/
set_bit(__E1000_DOWN, &adapter->state);
+ del_timer_sync(&adapter->watchdog_timer);
del_timer_sync(&adapter->phy_info_timer);
cancel_work_sync(&adapter->reset_task);
+ cancel_work_sync(&adapter->watchdog_task);
cancel_work_sync(&adapter->downshift_task);
cancel_work_sync(&adapter->update_phy_task);
cancel_work_sync(&adapter->print_hang_task);
- cancel_delayed_work(&adapter->watchdog_task);
- flush_workqueue(adapter->e1000_workqueue);
- destroy_workqueue(adapter->e1000_workqueue);
-
if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) {
cancel_work_sync(&adapter->tx_hwtstamp_work);
if (adapter->tx_hwtstamp_skb) {
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index ba2566e..0637cca 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -696,21 +696,24 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev)
/**
* fm10k_tx_timeout - Respond to a Tx Hang
* @netdev: network interface device structure
+ * @txqueue: the index of the Tx queue that timed out
**/
static void fm10k_tx_timeout(struct net_device *netdev, unsigned int txqueue)
{
struct fm10k_intfc *interface = netdev_priv(netdev);
+ struct fm10k_ring *tx_ring;
bool real_tx_hang = false;
- int i;
-#define TX_TIMEO_LIMIT 16000
- for (i = 0; i < interface->num_tx_queues; i++) {
- struct fm10k_ring *tx_ring = interface->tx_ring[i];
-
- if (check_for_tx_hang(tx_ring) && fm10k_check_tx_hang(tx_ring))
- real_tx_hang = true;
+ if (txqueue >= interface->num_tx_queues) {
+ WARN(1, "invalid Tx queue index %d", txqueue);
+ return;
}
+ tx_ring = interface->tx_ring[txqueue];
+ if (check_for_tx_hang(tx_ring) && fm10k_check_tx_hang(tx_ring))
+ real_tx_hang = true;
+
+#define TX_TIMEO_LIMIT 16000
if (real_tx_hang) {
fm10k_tx_timeout_reset(interface);
} else {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 9f0a4e9..37514a7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -536,6 +536,11 @@ static void i40e_set_hw_flags(struct i40e_hw *hw)
(aq->api_maj_ver == 1 &&
aq->api_min_ver >= I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722))
hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
+
+ if (aq->api_maj_ver > 1 ||
+ (aq->api_maj_ver == 1 &&
+ aq->api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_X722))
+ hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE;
/* fall through */
default:
break;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index d405503..45b90eb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1113,7 +1113,7 @@ i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num,
*/
pba_size--;
if (pba_num_size < (((u32)pba_size * 2) + 1)) {
- hw_dbg(hw, "Buffer to small for PBA data.\n");
+ hw_dbg(hw, "Buffer too small for PBA data.\n");
return I40E_ERR_PARAM;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 33912cf..8c3e753 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -307,37 +307,18 @@ static void i40e_tx_timeout(struct net_device *netdev, unsigned int txqueue)
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
struct i40e_ring *tx_ring = NULL;
- unsigned int i, hung_queue = 0;
+ unsigned int i;
u32 head, val;
pf->tx_timeout_count++;
- /* find the stopped queue the same way the stack does */
- for (i = 0; i < netdev->num_tx_queues; i++) {
- struct netdev_queue *q;
- unsigned long trans_start;
-
- q = netdev_get_tx_queue(netdev, i);
- trans_start = q->trans_start;
- if (netif_xmit_stopped(q) &&
- time_after(jiffies,
- (trans_start + netdev->watchdog_timeo))) {
- hung_queue = i;
- break;
- }
- }
-
- if (i == netdev->num_tx_queues) {
- netdev_info(netdev, "tx_timeout: no netdev hung queue found\n");
- } else {
- /* now that we have an index, find the tx_ring struct */
- for (i = 0; i < vsi->num_queue_pairs; i++) {
- if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) {
- if (hung_queue ==
- vsi->tx_rings[i]->queue_index) {
- tx_ring = vsi->tx_rings[i];
- break;
- }
+ /* with txqueue index, find the tx_ring struct */
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) {
+ if (txqueue ==
+ vsi->tx_rings[i]->queue_index) {
+ tx_ring = vsi->tx_rings[i];
+ break;
}
}
}
@@ -363,14 +344,14 @@ static void i40e_tx_timeout(struct net_device *netdev, unsigned int txqueue)
val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0);
netdev_info(netdev, "tx_timeout: VSI_seid: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n",
- vsi->seid, hung_queue, tx_ring->next_to_clean,
+ vsi->seid, txqueue, tx_ring->next_to_clean,
head, tx_ring->next_to_use,
readl(tx_ring->tail), val);
}
pf->tx_timeout_last_recovery = jiffies;
- netdev_info(netdev, "tx_timeout recovery level %d, hung_queue %d\n",
- pf->tx_timeout_recovery_level, hung_queue);
+ netdev_info(netdev, "tx_timeout recovery level %d, txqueue %d\n",
+ pf->tx_timeout_recovery_level, txqueue);
switch (pf->tx_timeout_recovery_level) {
case 1:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 6a3f0fc..69523ac 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2322,6 +2322,22 @@ static int i40e_ctrl_vf_rx_rings(struct i40e_vsi *vsi, unsigned long q_map,
}
/**
+ * i40e_vc_validate_vqs_bitmaps - validate Rx/Tx queue bitmaps from VIRTHCHNL
+ * @vqs: virtchnl_queue_select structure containing bitmaps to validate
+ *
+ * Returns true if validation was successful, else false.
+ */
+static bool i40e_vc_validate_vqs_bitmaps(struct virtchnl_queue_select *vqs)
+{
+ if ((!vqs->rx_queues && !vqs->tx_queues) ||
+ vqs->rx_queues >= BIT(I40E_MAX_VF_QUEUES) ||
+ vqs->tx_queues >= BIT(I40E_MAX_VF_QUEUES))
+ return false;
+
+ return true;
+}
+
+/**
* i40e_vc_enable_queues_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
@@ -2346,7 +2362,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
goto error_param;
}
- if ((0 == vqs->rx_queues) && (0 == vqs->tx_queues)) {
+ if (i40e_vc_validate_vqs_bitmaps(vqs)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
@@ -2408,9 +2424,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg)
goto error_param;
}
- if ((vqs->rx_queues == 0 && vqs->tx_queues == 0) ||
- vqs->rx_queues > I40E_MAX_VF_QUEUES ||
- vqs->tx_queues > I40E_MAX_VF_QUEUES) {
+ if (i40e_vc_validate_vqs_bitmaps(vqs)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 29de3ae..bd1b1ed 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -415,4 +415,6 @@ void iavf_enable_channels(struct iavf_adapter *adapter);
void iavf_disable_channels(struct iavf_adapter *adapter);
void iavf_add_cloud_filter(struct iavf_adapter *adapter);
void iavf_del_cloud_filter(struct iavf_adapter *adapter);
+struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
+ const u8 *macaddr);
#endif /* _IAVF_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 0a88248..62fe56dd 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -743,9 +743,8 @@ iavf_mac_filter *iavf_find_filter(struct iavf_adapter *adapter,
*
* Returns ptr to the filter object or NULL when no memory available.
**/
-static struct
-iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
- const u8 *macaddr)
+struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
+ const u8 *macaddr)
{
struct iavf_mac_filter *f;
@@ -2065,9 +2064,9 @@ static void iavf_reset_task(struct work_struct *work)
struct virtchnl_vf_resource *vfres = adapter->vf_res;
struct net_device *netdev = adapter->netdev;
struct iavf_hw *hw = &adapter->hw;
+ struct iavf_mac_filter *f, *ftmp;
struct iavf_vlan_filter *vlf;
struct iavf_cloud_filter *cf;
- struct iavf_mac_filter *f;
u32 reg_val;
int i = 0, err;
bool running;
@@ -2181,6 +2180,16 @@ static void iavf_reset_task(struct work_struct *work)
spin_lock_bh(&adapter->mac_vlan_list_lock);
+ /* Delete filter for the current MAC address, it could have
+ * been changed by the PF via administratively set MAC.
+ * Will be re-added via VIRTCHNL_OP_GET_VF_RESOURCES.
+ */
+ list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) {
+ if (ether_addr_equal(f->macaddr, adapter->hw.mac.addr)) {
+ list_del(&f->list);
+ kfree(f);
+ }
+ }
/* re-add all MAC filters */
list_for_each_entry(f, &adapter->mac_filter_list, list) {
f->add = true;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index c46770e..1ab9cb3 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1359,6 +1359,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
ether_addr_copy(netdev->perm_addr,
adapter->hw.mac.addr);
}
+ spin_lock_bh(&adapter->mac_vlan_list_lock);
+ iavf_add_filter(adapter, adapter->hw.mac.addr);
+ spin_unlock_bh(&adapter->mac_vlan_list_lock);
iavf_process_config(adapter);
}
break;
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 7cb8291..59544b0 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -17,7 +17,8 @@
ice_lib.o \
ice_txrx_lib.o \
ice_txrx.o \
- ice_flex_pipe.o \
+ ice_flex_pipe.o \
+ ice_flow.o \
ice_ethtool.o
ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o
ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index f972dce..cb10abb 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -174,6 +174,8 @@ struct ice_sw {
struct ice_pf *pf;
u16 sw_id; /* switch ID for this switch */
u16 bridge_mode; /* VEB/VEPA/Port Virtualizer */
+ struct ice_vsi *dflt_vsi; /* default VSI for this switch */
+ u8 dflt_vsi_ena:1; /* true if above dflt_vsi is enabled */
};
enum ice_state {
@@ -275,6 +277,7 @@ struct ice_vsi {
u8 current_isup:1; /* Sync 'link up' logging */
u8 stat_offsets_loaded:1;
u8 vlan_ena:1;
+ u16 num_vlan;
/* queue information */
u8 tx_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */
@@ -462,12 +465,13 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring)
static inline struct xdp_umem *ice_xsk_umem(struct ice_ring *ring)
{
struct xdp_umem **umems = ring->vsi->xsk_umems;
- int qid = ring->q_index;
+ u16 qid = ring->q_index;
if (ice_ring_is_xdp(ring))
qid -= ring->vsi->num_xdp_txq;
- if (!umems || !umems[qid] || !ice_is_xdp_ena_vsi(ring->vsi))
+ if (qid >= ring->vsi->num_xsk_umems || !umems || !umems[qid] ||
+ !ice_is_xdp_ena_vsi(ring->vsi))
return NULL;
return umems[qid];
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 5421fc4..4459bc5 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -232,6 +232,13 @@ struct ice_aqc_get_sw_cfg_resp {
*/
#define ICE_AQC_RES_TYPE_VSI_LIST_REP 0x03
#define ICE_AQC_RES_TYPE_VSI_LIST_PRUNE 0x04
+#define ICE_AQC_RES_TYPE_HASH_PROF_BLDR_PROFID 0x60
+#define ICE_AQC_RES_TYPE_HASH_PROF_BLDR_TCAM 0x61
+
+#define ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM BIT(12)
+#define ICE_AQC_RES_TYPE_FLAG_IGNORE_INDEX BIT(13)
+
+#define ICE_AQC_RES_TYPE_FLAG_DEDICATED 0x00
/* Allocate Resources command (indirect 0x0208)
* Free Resources command (indirect 0x0209)
@@ -1849,6 +1856,7 @@ enum ice_adminq_opc {
/* package commands */
ice_aqc_opc_download_pkg = 0x0C40,
+ ice_aqc_opc_update_pkg = 0x0C42,
ice_aqc_opc_get_pkg_info_list = 0x0C43,
/* debug commands */
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 77d6a02..d8e975c 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -93,7 +93,8 @@ static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena)
* @vsi: the VSI being configured
* @v_idx: index of the vector in the VSI struct
*
- * We allocate one q_vector. If allocation fails we return -ENOMEM.
+ * We allocate one q_vector and set default value for ITR setting associated
+ * with this q_vector. If allocation fails we return -ENOMEM.
*/
static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx)
{
@@ -108,6 +109,8 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx)
q_vector->vsi = vsi;
q_vector->v_idx = v_idx;
+ q_vector->tx.itr_setting = ICE_DFLT_TX_ITR;
+ q_vector->rx.itr_setting = ICE_DFLT_RX_ITR;
if (vsi->type == ICE_VSI_VF)
goto out;
/* only set affinity_mask if the CPU is online */
@@ -299,6 +302,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
if (ring->vsi->type == ICE_VSI_PF) {
if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
+ /* coverity[check_return] */
xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
ring->q_index);
@@ -323,7 +327,9 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
dev_info(&vsi->back->pdev->dev, "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n",
ring->q_index);
} else {
+ ring->zca.free = NULL;
if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
+ /* coverity[check_return] */
xdp_rxq_info_reg(&ring->xdp_rxq,
ring->netdev,
ring->q_index);
@@ -674,10 +680,6 @@ void ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector)
if (q_vector->num_ring_rx) {
struct ice_ring_container *rc = &q_vector->rx;
- /* if this value is set then don't overwrite with default */
- if (!rc->itr_setting)
- rc->itr_setting = ICE_DFLT_RX_ITR;
-
rc->target_itr = ITR_TO_REG(rc->itr_setting);
rc->next_update = jiffies + 1;
rc->current_itr = rc->target_itr;
@@ -688,10 +690,6 @@ void ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector)
if (q_vector->num_ring_tx) {
struct ice_ring_container *rc = &q_vector->tx;
- /* if this value is set then don't overwrite with default */
- if (!rc->itr_setting)
- rc->itr_setting = ICE_DFLT_TX_ITR;
-
rc->target_itr = ITR_TO_REG(rc->itr_setting);
rc->next_update = jiffies + 1;
rc->current_itr = rc->target_itr;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index fb1d930..0207e28 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -4,28 +4,10 @@
#include "ice_common.h"
#include "ice_sched.h"
#include "ice_adminq_cmd.h"
+#include "ice_flow.h"
#define ICE_PF_RESET_WAIT_COUNT 200
-#define ICE_PROG_FLEX_ENTRY(hw, rxdid, mdid, idx) \
- wr32((hw), GLFLXP_RXDID_FLX_WRD_##idx(rxdid), \
- ((ICE_RX_OPC_MDID << \
- GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_S) & \
- GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_M) | \
- (((mdid) << GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_S) & \
- GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_M))
-
-#define ICE_PROG_FLG_ENTRY(hw, rxdid, flg_0, flg_1, flg_2, flg_3, idx) \
- wr32((hw), GLFLXP_RXDID_FLAGS(rxdid, idx), \
- (((flg_0) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) & \
- GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) | \
- (((flg_1) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S) & \
- GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M) | \
- (((flg_2) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S) & \
- GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M) | \
- (((flg_3) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S) & \
- GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M))
-
/**
* ice_set_mac_type - Sets MAC type
* @hw: pointer to the HW structure
@@ -348,88 +330,6 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
}
/**
- * ice_init_flex_flags
- * @hw: pointer to the hardware structure
- * @prof_id: Rx Descriptor Builder profile ID
- *
- * Function to initialize Rx flex flags
- */
-static void ice_init_flex_flags(struct ice_hw *hw, enum ice_rxdid prof_id)
-{
- u8 idx = 0;
-
- /* Flex-flag fields (0-2) are programmed with FLG64 bits with layout:
- * flexiflags0[5:0] - TCP flags, is_packet_fragmented, is_packet_UDP_GRE
- * flexiflags1[3:0] - Not used for flag programming
- * flexiflags2[7:0] - Tunnel and VLAN types
- * 2 invalid fields in last index
- */
- switch (prof_id) {
- /* Rx flex flags are currently programmed for the NIC profiles only.
- * Different flag bit programming configurations can be added per
- * profile as needed.
- */
- case ICE_RXDID_FLEX_NIC:
- case ICE_RXDID_FLEX_NIC_2:
- ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_PKT_FRG,
- ICE_FLG_UDP_GRE, ICE_FLG_PKT_DSI,
- ICE_FLG_FIN, idx++);
- /* flex flag 1 is not used for flexi-flag programming, skipping
- * these four FLG64 bits.
- */
- ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_SYN, ICE_FLG_RST,
- ICE_FLG_PKT_DSI, ICE_FLG_PKT_DSI, idx++);
- ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_PKT_DSI,
- ICE_FLG_PKT_DSI, ICE_FLG_EVLAN_x8100,
- ICE_FLG_EVLAN_x9100, idx++);
- ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_VLAN_x8100,
- ICE_FLG_TNL_VLAN, ICE_FLG_TNL_MAC,
- ICE_FLG_TNL0, idx++);
- ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_TNL1, ICE_FLG_TNL2,
- ICE_FLG_PKT_DSI, ICE_FLG_PKT_DSI, idx);
- break;
-
- default:
- ice_debug(hw, ICE_DBG_INIT,
- "Flag programming for profile ID %d not supported\n",
- prof_id);
- }
-}
-
-/**
- * ice_init_flex_flds
- * @hw: pointer to the hardware structure
- * @prof_id: Rx Descriptor Builder profile ID
- *
- * Function to initialize flex descriptors
- */
-static void ice_init_flex_flds(struct ice_hw *hw, enum ice_rxdid prof_id)
-{
- enum ice_flex_rx_mdid mdid;
-
- switch (prof_id) {
- case ICE_RXDID_FLEX_NIC:
- case ICE_RXDID_FLEX_NIC_2:
- ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_HASH_LOW, 0);
- ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_HASH_HIGH, 1);
- ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_FLOW_ID_LOWER, 2);
-
- mdid = (prof_id == ICE_RXDID_FLEX_NIC_2) ?
- ICE_RX_MDID_SRC_VSI : ICE_RX_MDID_FLOW_ID_HIGH;
-
- ICE_PROG_FLEX_ENTRY(hw, prof_id, mdid, 3);
-
- ice_init_flex_flags(hw, prof_id);
- break;
-
- default:
- ice_debug(hw, ICE_DBG_INIT,
- "Field init for profile ID %d not supported\n",
- prof_id);
- }
-}
-
-/**
* ice_init_fltr_mgmt_struct - initializes filter management list and locks
* @hw: pointer to the HW struct
*/
@@ -882,9 +782,6 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
if (status)
goto err_unroll_fltr_mgmt_struct;
-
- ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC);
- ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC_2);
status = ice_init_hw_tbls(hw);
if (status)
goto err_unroll_fltr_mgmt_struct;
@@ -1601,6 +1498,114 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res)
}
/**
+ * ice_aq_alloc_free_res - command to allocate/free resources
+ * @hw: pointer to the HW struct
+ * @num_entries: number of resource entries in buffer
+ * @buf: Indirect buffer to hold data parameters and response
+ * @buf_size: size of buffer for indirect commands
+ * @opc: pass in the command opcode
+ * @cd: pointer to command details structure or NULL
+ *
+ * Helper function to allocate/free resources using the admin queue commands
+ */
+enum ice_status
+ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries,
+ struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size,
+ enum ice_adminq_opc opc, struct ice_sq_cd *cd)
+{
+ struct ice_aqc_alloc_free_res_cmd *cmd;
+ struct ice_aq_desc desc;
+
+ cmd = &desc.params.sw_res_ctrl;
+
+ if (!buf)
+ return ICE_ERR_PARAM;
+
+ if (buf_size < (num_entries * sizeof(buf->elem[0])))
+ return ICE_ERR_PARAM;
+
+ ice_fill_dflt_direct_cmd_desc(&desc, opc);
+
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+ cmd->num_entries = cpu_to_le16(num_entries);
+
+ return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+}
+
+/**
+ * ice_alloc_hw_res - allocate resource
+ * @hw: pointer to the HW struct
+ * @type: type of resource
+ * @num: number of resources to allocate
+ * @btm: allocate from bottom
+ * @res: pointer to array that will receive the resources
+ */
+enum ice_status
+ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res)
+{
+ struct ice_aqc_alloc_free_res_elem *buf;
+ enum ice_status status;
+ u16 buf_len;
+
+ buf_len = struct_size(buf, elem, num - 1);
+ buf = kzalloc(buf_len, GFP_KERNEL);
+ if (!buf)
+ return ICE_ERR_NO_MEMORY;
+
+ /* Prepare buffer to allocate resource. */
+ buf->num_elems = cpu_to_le16(num);
+ buf->res_type = cpu_to_le16(type | ICE_AQC_RES_TYPE_FLAG_DEDICATED |
+ ICE_AQC_RES_TYPE_FLAG_IGNORE_INDEX);
+ if (btm)
+ buf->res_type |= cpu_to_le16(ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM);
+
+ status = ice_aq_alloc_free_res(hw, 1, buf, buf_len,
+ ice_aqc_opc_alloc_res, NULL);
+ if (status)
+ goto ice_alloc_res_exit;
+
+ memcpy(res, buf->elem, sizeof(buf->elem) * num);
+
+ice_alloc_res_exit:
+ kfree(buf);
+ return status;
+}
+
+/**
+ * ice_free_hw_res - free allocated HW resource
+ * @hw: pointer to the HW struct
+ * @type: type of resource to free
+ * @num: number of resources
+ * @res: pointer to array that contains the resources to free
+ */
+enum ice_status
+ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res)
+{
+ struct ice_aqc_alloc_free_res_elem *buf;
+ enum ice_status status;
+ u16 buf_len;
+
+ buf_len = struct_size(buf, elem, num - 1);
+ buf = kzalloc(buf_len, GFP_KERNEL);
+ if (!buf)
+ return ICE_ERR_NO_MEMORY;
+
+ /* Prepare buffer to free resource. */
+ buf->num_elems = cpu_to_le16(num);
+ buf->res_type = cpu_to_le16(type);
+ memcpy(buf->elem, res, sizeof(buf->elem) * num);
+
+ status = ice_aq_alloc_free_res(hw, num, buf, buf_len,
+ ice_aqc_opc_free_res, NULL);
+ if (status)
+ ice_debug(hw, ICE_DBG_SW, "CQ CMD Buffer:\n");
+
+ kfree(buf);
+ return status;
+}
+
+/**
* ice_get_num_per_func - determine number of resources per PF
* @hw: pointer to the HW structure
* @max: value to be evenly split between each PF
@@ -3510,7 +3515,10 @@ enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle)
if (status)
return status;
}
-
+ /* Replay per VSI all RSS configurations */
+ status = ice_replay_rss_cfg(hw, vsi_handle);
+ if (status)
+ return status;
/* Replay per VSI all filters */
status = ice_replay_vsi_all_fltr(hw, vsi_handle);
return status;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index b22aa56..b5c013f 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -34,10 +34,18 @@ enum ice_status
ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res,
enum ice_aq_res_access_type access, u32 timeout);
void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res);
+enum ice_status
+ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res);
+enum ice_status
+ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res);
enum ice_status ice_init_nvm(struct ice_hw *hw);
enum ice_status
ice_read_sr_buf(struct ice_hw *hw, u16 offset, u16 *words, u16 *data);
enum ice_status
+ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries,
+ struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size,
+ enum ice_adminq_opc opc, struct ice_sq_cd *cd);
+enum ice_status
ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
struct ice_aq_desc *desc, void *buf, u16 buf_size,
struct ice_sq_cd *cd);
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index d3d3ec2..0664e5b 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -396,6 +396,12 @@ void ice_dcb_rebuild(struct ice_pf *pf)
prev_cfg->etscfg.tcbwtable[0] = ICE_TC_MAX_BW;
prev_cfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;
memcpy(&prev_cfg->etsrec, &prev_cfg->etscfg, sizeof(prev_cfg->etsrec));
+ /* Coverity warns the return code of ice_pf_dcb_cfg() is not checked
+ * here as is done for other calls to that function. That check is
+ * not necessary since this is in this function's error cleanup path.
+ * Suppress the Coverity warning with the following comment...
+ */
+ /* coverity[check_return] */
ice_pf_dcb_cfg(pf, prev_cfg, false);
kfree(prev_cfg);
}
diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h
index f8d5c66..ce63017c 100644
--- a/drivers/net/ethernet/intel/ice/ice_devids.h
+++ b/drivers/net/ethernet/intel/ice/ice_devids.h
@@ -11,5 +11,23 @@
#define ICE_DEV_ID_E810C_QSFP 0x1592
/* Intel(R) Ethernet Controller E810-C for SFP */
#define ICE_DEV_ID_E810C_SFP 0x1593
+/* Intel(R) Ethernet Connection E822-C for backplane */
+#define ICE_DEV_ID_E822C_BACKPLANE 0x1890
+/* Intel(R) Ethernet Connection E822-C for QSFP */
+#define ICE_DEV_ID_E822C_QSFP 0x1891
+/* Intel(R) Ethernet Connection E822-C for SFP */
+#define ICE_DEV_ID_E822C_SFP 0x1892
+/* Intel(R) Ethernet Connection E822-C/X557-AT 10GBASE-T */
+#define ICE_DEV_ID_E822C_10G_BASE_T 0x1893
+/* Intel(R) Ethernet Connection E822-C 1GbE */
+#define ICE_DEV_ID_E822C_SGMII 0x1894
+/* Intel(R) Ethernet Connection E822-X for backplane */
+#define ICE_DEV_ID_E822X_BACKPLANE 0x1897
+/* Intel(R) Ethernet Connection E822-L for SFP */
+#define ICE_DEV_ID_E822L_SFP 0x1898
+/* Intel(R) Ethernet Connection E822-L/X557-AT 10GBASE-T */
+#define ICE_DEV_ID_E822L_10G_BASE_T 0x1899
+/* Intel(R) Ethernet Connection E822-L 1GbE */
+#define ICE_DEV_ID_E822L_SGMII 0x189A
#endif /* _ICE_DEVIDS_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 9ebd93e..90c6a3c 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -4,6 +4,7 @@
/* ethtool support for ice */
#include "ice.h"
+#include "ice_flow.h"
#include "ice_lib.h"
#include "ice_dcb_lib.h"
@@ -283,12 +284,15 @@ ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
*/
static bool ice_active_vfs(struct ice_pf *pf)
{
- struct ice_vf *vf = pf->vf;
int i;
- for (i = 0; i < pf->num_alloc_vfs; i++, vf++)
+ ice_for_each_vf(pf, i) {
+ struct ice_vf *vf = &pf->vf[i];
+
if (test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
return true;
+ }
+
return false;
}
@@ -2531,6 +2535,243 @@ ice_set_link_ksettings(struct net_device *netdev,
}
/**
+ * ice_parse_hdrs - parses headers from RSS hash input
+ * @nfc: ethtool rxnfc command
+ *
+ * This function parses the rxnfc command and returns intended
+ * header types for RSS configuration
+ */
+static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc)
+{
+ u32 hdrs = ICE_FLOW_SEG_HDR_NONE;
+
+ switch (nfc->flow_type) {
+ case TCP_V4_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4;
+ break;
+ case UDP_V4_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4;
+ break;
+ case SCTP_V4_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4;
+ break;
+ case TCP_V6_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6;
+ break;
+ case UDP_V6_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6;
+ break;
+ case SCTP_V6_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6;
+ break;
+ default:
+ break;
+ }
+ return hdrs;
+}
+
+#define ICE_FLOW_HASH_FLD_IPV4_SA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)
+#define ICE_FLOW_HASH_FLD_IPV6_SA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)
+#define ICE_FLOW_HASH_FLD_IPV4_DA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)
+#define ICE_FLOW_HASH_FLD_IPV6_DA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)
+#define ICE_FLOW_HASH_FLD_TCP_SRC_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)
+#define ICE_FLOW_HASH_FLD_TCP_DST_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)
+#define ICE_FLOW_HASH_FLD_UDP_SRC_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)
+#define ICE_FLOW_HASH_FLD_UDP_DST_PORT BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT)
+#define ICE_FLOW_HASH_FLD_SCTP_SRC_PORT \
+ BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)
+#define ICE_FLOW_HASH_FLD_SCTP_DST_PORT \
+ BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)
+
+/**
+ * ice_parse_hash_flds - parses hash fields from RSS hash input
+ * @nfc: ethtool rxnfc command
+ *
+ * This function parses the rxnfc command and returns intended
+ * hash fields for RSS configuration
+ */
+static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc)
+{
+ u64 hfld = ICE_HASH_INVALID;
+
+ if (nfc->data & RXH_IP_SRC || nfc->data & RXH_IP_DST) {
+ switch (nfc->flow_type) {
+ case TCP_V4_FLOW:
+ case UDP_V4_FLOW:
+ case SCTP_V4_FLOW:
+ if (nfc->data & RXH_IP_SRC)
+ hfld |= ICE_FLOW_HASH_FLD_IPV4_SA;
+ if (nfc->data & RXH_IP_DST)
+ hfld |= ICE_FLOW_HASH_FLD_IPV4_DA;
+ break;
+ case TCP_V6_FLOW:
+ case UDP_V6_FLOW:
+ case SCTP_V6_FLOW:
+ if (nfc->data & RXH_IP_SRC)
+ hfld |= ICE_FLOW_HASH_FLD_IPV6_SA;
+ if (nfc->data & RXH_IP_DST)
+ hfld |= ICE_FLOW_HASH_FLD_IPV6_DA;
+ break;
+ default:
+ break;
+ }
+ }
+
+ if (nfc->data & RXH_L4_B_0_1 || nfc->data & RXH_L4_B_2_3) {
+ switch (nfc->flow_type) {
+ case TCP_V4_FLOW:
+ case TCP_V6_FLOW:
+ if (nfc->data & RXH_L4_B_0_1)
+ hfld |= ICE_FLOW_HASH_FLD_TCP_SRC_PORT;
+ if (nfc->data & RXH_L4_B_2_3)
+ hfld |= ICE_FLOW_HASH_FLD_TCP_DST_PORT;
+ break;
+ case UDP_V4_FLOW:
+ case UDP_V6_FLOW:
+ if (nfc->data & RXH_L4_B_0_1)
+ hfld |= ICE_FLOW_HASH_FLD_UDP_SRC_PORT;
+ if (nfc->data & RXH_L4_B_2_3)
+ hfld |= ICE_FLOW_HASH_FLD_UDP_DST_PORT;
+ break;
+ case SCTP_V4_FLOW:
+ case SCTP_V6_FLOW:
+ if (nfc->data & RXH_L4_B_0_1)
+ hfld |= ICE_FLOW_HASH_FLD_SCTP_SRC_PORT;
+ if (nfc->data & RXH_L4_B_2_3)
+ hfld |= ICE_FLOW_HASH_FLD_SCTP_DST_PORT;
+ break;
+ default:
+ break;
+ }
+ }
+
+ return hfld;
+}
+
+/**
+ * ice_set_rss_hash_opt - Enable/Disable flow types for RSS hash
+ * @vsi: the VSI being configured
+ * @nfc: ethtool rxnfc command
+ *
+ * Returns Success if the flow input set is supported.
+ */
+static int
+ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
+{
+ struct ice_pf *pf = vsi->back;
+ enum ice_status status;
+ struct device *dev;
+ u64 hashed_flds;
+ u32 hdrs;
+
+ dev = ice_pf_to_dev(pf);
+ if (ice_is_safe_mode(pf)) {
+ dev_dbg(dev, "Advanced RSS disabled. Package download failed, vsi num = %d\n",
+ vsi->vsi_num);
+ return -EINVAL;
+ }
+
+ hashed_flds = ice_parse_hash_flds(nfc);
+ if (hashed_flds == ICE_HASH_INVALID) {
+ dev_dbg(dev, "Invalid hash fields, vsi num = %d\n",
+ vsi->vsi_num);
+ return -EINVAL;
+ }
+
+ hdrs = ice_parse_hdrs(nfc);
+ if (hdrs == ICE_FLOW_SEG_HDR_NONE) {
+ dev_dbg(dev, "Header type is not valid, vsi num = %d\n",
+ vsi->vsi_num);
+ return -EINVAL;
+ }
+
+ status = ice_add_rss_cfg(&pf->hw, vsi->idx, hashed_flds, hdrs);
+ if (status) {
+ dev_dbg(dev, "ice_add_rss_cfg failed, vsi num = %d, error = %d\n",
+ vsi->vsi_num, status);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_get_rss_hash_opt - Retrieve hash fields for a given flow-type
+ * @vsi: the VSI being configured
+ * @nfc: ethtool rxnfc command
+ */
+static void
+ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
+{
+ struct ice_pf *pf = vsi->back;
+ struct device *dev;
+ u64 hash_flds;
+ u32 hdrs;
+
+ dev = ice_pf_to_dev(pf);
+
+ nfc->data = 0;
+ if (ice_is_safe_mode(pf)) {
+ dev_dbg(dev, "Advanced RSS disabled. Package download failed, vsi num = %d\n",
+ vsi->vsi_num);
+ return;
+ }
+
+ hdrs = ice_parse_hdrs(nfc);
+ if (hdrs == ICE_FLOW_SEG_HDR_NONE) {
+ dev_dbg(dev, "Header type is not valid, vsi num = %d\n",
+ vsi->vsi_num);
+ return;
+ }
+
+ hash_flds = ice_get_rss_cfg(&pf->hw, vsi->idx, hdrs);
+ if (hash_flds == ICE_HASH_INVALID) {
+ dev_dbg(dev, "No hash fields found for the given header type, vsi num = %d\n",
+ vsi->vsi_num);
+ return;
+ }
+
+ if (hash_flds & ICE_FLOW_HASH_FLD_IPV4_SA ||
+ hash_flds & ICE_FLOW_HASH_FLD_IPV6_SA)
+ nfc->data |= (u64)RXH_IP_SRC;
+
+ if (hash_flds & ICE_FLOW_HASH_FLD_IPV4_DA ||
+ hash_flds & ICE_FLOW_HASH_FLD_IPV6_DA)
+ nfc->data |= (u64)RXH_IP_DST;
+
+ if (hash_flds & ICE_FLOW_HASH_FLD_TCP_SRC_PORT ||
+ hash_flds & ICE_FLOW_HASH_FLD_UDP_SRC_PORT ||
+ hash_flds & ICE_FLOW_HASH_FLD_SCTP_SRC_PORT)
+ nfc->data |= (u64)RXH_L4_B_0_1;
+
+ if (hash_flds & ICE_FLOW_HASH_FLD_TCP_DST_PORT ||
+ hash_flds & ICE_FLOW_HASH_FLD_UDP_DST_PORT ||
+ hash_flds & ICE_FLOW_HASH_FLD_SCTP_DST_PORT)
+ nfc->data |= (u64)RXH_L4_B_2_3;
+}
+
+/**
+ * ice_set_rxnfc - command to set Rx flow rules.
+ * @netdev: network interface device structure
+ * @cmd: ethtool rxnfc command
+ *
+ * Returns 0 for success and negative values for errors
+ */
+static int ice_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_vsi *vsi = np->vsi;
+
+ switch (cmd->cmd) {
+ case ETHTOOL_SRXFH:
+ return ice_set_rss_hash_opt(vsi, cmd);
+ default:
+ break;
+ }
+ return -EOPNOTSUPP;
+}
+
+/**
* ice_get_rxnfc - command to get Rx flow classification rules
* @netdev: network interface device structure
* @cmd: ethtool rxnfc command
@@ -2551,6 +2792,10 @@ ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
cmd->data = vsi->rss_size;
ret = 0;
break;
+ case ETHTOOL_GRXFH:
+ ice_get_rss_hash_opt(vsi, cmd);
+ ret = 0;
+ break;
default:
break;
}
@@ -3585,6 +3830,53 @@ ice_set_q_coalesce(struct ice_vsi *vsi, struct ethtool_coalesce *ec, int q_num)
}
/**
+ * ice_is_coalesce_param_invalid - check for unsupported coalesce parameters
+ * @netdev: pointer to the netdev associated with this query
+ * @ec: ethtool structure to fill with driver's coalesce settings
+ *
+ * Print netdev info if driver doesn't support one of the parameters
+ * and return error. When any parameters will be implemented, remove only
+ * this parameter from param array.
+ */
+static int
+ice_is_coalesce_param_invalid(struct net_device *netdev,
+ struct ethtool_coalesce *ec)
+{
+ struct ice_ethtool_not_used {
+ u32 value;
+ const char *name;
+ } param[] = {
+ {ec->stats_block_coalesce_usecs, "stats-block-usecs"},
+ {ec->rate_sample_interval, "sample-interval"},
+ {ec->pkt_rate_low, "pkt-rate-low"},
+ {ec->pkt_rate_high, "pkt-rate-high"},
+ {ec->rx_max_coalesced_frames, "rx-frames"},
+ {ec->rx_coalesce_usecs_irq, "rx-usecs-irq"},
+ {ec->rx_max_coalesced_frames_irq, "rx-frames-irq"},
+ {ec->tx_max_coalesced_frames, "tx-frames"},
+ {ec->tx_coalesce_usecs_irq, "tx-usecs-irq"},
+ {ec->tx_max_coalesced_frames_irq, "tx-frames-irq"},
+ {ec->rx_coalesce_usecs_low, "rx-usecs-low"},
+ {ec->rx_max_coalesced_frames_low, "rx-frames-low"},
+ {ec->tx_coalesce_usecs_low, "tx-usecs-low"},
+ {ec->tx_max_coalesced_frames_low, "tx-frames-low"},
+ {ec->rx_max_coalesced_frames_high, "rx-frames-high"},
+ {ec->tx_max_coalesced_frames_high, "tx-frames-high"}
+ };
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(param); i++) {
+ if (param[i].value) {
+ netdev_info(netdev, "Setting %s not supported\n",
+ param[i].name);
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+/**
* __ice_set_coalesce - set ITR/INTRL values for the device
* @netdev: pointer to the netdev associated with this query
* @ec: ethtool structure to fill with driver's coalesce settings
@@ -3600,6 +3892,9 @@ __ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec,
struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
+ if (ice_is_coalesce_param_invalid(netdev, ec))
+ return -EINVAL;
+
if (q_num < 0) {
int v_idx;
@@ -3804,6 +4099,7 @@ static const struct ethtool_ops ice_ethtool_ops = {
.set_priv_flags = ice_set_priv_flags,
.get_sset_count = ice_get_sset_count,
.get_rxnfc = ice_get_rxnfc,
+ .set_rxnfc = ice_set_rxnfc,
.get_ringparam = ice_get_ringparam,
.set_ringparam = ice_set_ringparam,
.nway_reset = ice_nway_reset,
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index cbd53b5..9920894 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -3,6 +3,87 @@
#include "ice_common.h"
#include "ice_flex_pipe.h"
+#include "ice_flow.h"
+
+static const u32 ice_sect_lkup[ICE_BLK_COUNT][ICE_SECT_COUNT] = {
+ /* SWITCH */
+ {
+ ICE_SID_XLT0_SW,
+ ICE_SID_XLT_KEY_BUILDER_SW,
+ ICE_SID_XLT1_SW,
+ ICE_SID_XLT2_SW,
+ ICE_SID_PROFID_TCAM_SW,
+ ICE_SID_PROFID_REDIR_SW,
+ ICE_SID_FLD_VEC_SW,
+ ICE_SID_CDID_KEY_BUILDER_SW,
+ ICE_SID_CDID_REDIR_SW
+ },
+
+ /* ACL */
+ {
+ ICE_SID_XLT0_ACL,
+ ICE_SID_XLT_KEY_BUILDER_ACL,
+ ICE_SID_XLT1_ACL,
+ ICE_SID_XLT2_ACL,
+ ICE_SID_PROFID_TCAM_ACL,
+ ICE_SID_PROFID_REDIR_ACL,
+ ICE_SID_FLD_VEC_ACL,
+ ICE_SID_CDID_KEY_BUILDER_ACL,
+ ICE_SID_CDID_REDIR_ACL
+ },
+
+ /* FD */
+ {
+ ICE_SID_XLT0_FD,
+ ICE_SID_XLT_KEY_BUILDER_FD,
+ ICE_SID_XLT1_FD,
+ ICE_SID_XLT2_FD,
+ ICE_SID_PROFID_TCAM_FD,
+ ICE_SID_PROFID_REDIR_FD,
+ ICE_SID_FLD_VEC_FD,
+ ICE_SID_CDID_KEY_BUILDER_FD,
+ ICE_SID_CDID_REDIR_FD
+ },
+
+ /* RSS */
+ {
+ ICE_SID_XLT0_RSS,
+ ICE_SID_XLT_KEY_BUILDER_RSS,
+ ICE_SID_XLT1_RSS,
+ ICE_SID_XLT2_RSS,
+ ICE_SID_PROFID_TCAM_RSS,
+ ICE_SID_PROFID_REDIR_RSS,
+ ICE_SID_FLD_VEC_RSS,
+ ICE_SID_CDID_KEY_BUILDER_RSS,
+ ICE_SID_CDID_REDIR_RSS
+ },
+
+ /* PE */
+ {
+ ICE_SID_XLT0_PE,
+ ICE_SID_XLT_KEY_BUILDER_PE,
+ ICE_SID_XLT1_PE,
+ ICE_SID_XLT2_PE,
+ ICE_SID_PROFID_TCAM_PE,
+ ICE_SID_PROFID_REDIR_PE,
+ ICE_SID_FLD_VEC_PE,
+ ICE_SID_CDID_KEY_BUILDER_PE,
+ ICE_SID_CDID_REDIR_PE
+ }
+};
+
+/**
+ * ice_sect_id - returns section ID
+ * @blk: block type
+ * @sect: section type
+ *
+ * This helper function returns the proper section ID given a block type and a
+ * section type.
+ */
+static u32 ice_sect_id(enum ice_block blk, enum ice_sect sect)
+{
+ return ice_sect_lkup[blk][sect];
+}
/**
* ice_pkg_val_buf
@@ -158,6 +239,176 @@ ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
return state->sect;
}
+/* Key creation */
+
+#define ICE_DC_KEY 0x1 /* don't care */
+#define ICE_DC_KEYINV 0x1
+#define ICE_NM_KEY 0x0 /* never match */
+#define ICE_NM_KEYINV 0x0
+#define ICE_0_KEY 0x1 /* match 0 */
+#define ICE_0_KEYINV 0x0
+#define ICE_1_KEY 0x0 /* match 1 */
+#define ICE_1_KEYINV 0x1
+
+/**
+ * ice_gen_key_word - generate 16-bits of a key/mask word
+ * @val: the value
+ * @valid: valid bits mask (change only the valid bits)
+ * @dont_care: don't care mask
+ * @nvr_mtch: never match mask
+ * @key: pointer to an array of where the resulting key portion
+ * @key_inv: pointer to an array of where the resulting key invert portion
+ *
+ * This function generates 16-bits from a 8-bit value, an 8-bit don't care mask
+ * and an 8-bit never match mask. The 16-bits of output are divided into 8 bits
+ * of key and 8 bits of key invert.
+ *
+ * '0' = b01, always match a 0 bit
+ * '1' = b10, always match a 1 bit
+ * '?' = b11, don't care bit (always matches)
+ * '~' = b00, never match bit
+ *
+ * Input:
+ * val: b0 1 0 1 0 1
+ * dont_care: b0 0 1 1 0 0
+ * never_mtch: b0 0 0 0 1 1
+ * ------------------------------
+ * Result: key: b01 10 11 11 00 00
+ */
+static enum ice_status
+ice_gen_key_word(u8 val, u8 valid, u8 dont_care, u8 nvr_mtch, u8 *key,
+ u8 *key_inv)
+{
+ u8 in_key = *key, in_key_inv = *key_inv;
+ u8 i;
+
+ /* 'dont_care' and 'nvr_mtch' masks cannot overlap */
+ if ((dont_care ^ nvr_mtch) != (dont_care | nvr_mtch))
+ return ICE_ERR_CFG;
+
+ *key = 0;
+ *key_inv = 0;
+
+ /* encode the 8 bits into 8-bit key and 8-bit key invert */
+ for (i = 0; i < 8; i++) {
+ *key >>= 1;
+ *key_inv >>= 1;
+
+ if (!(valid & 0x1)) { /* change only valid bits */
+ *key |= (in_key & 0x1) << 7;
+ *key_inv |= (in_key_inv & 0x1) << 7;
+ } else if (dont_care & 0x1) { /* don't care bit */
+ *key |= ICE_DC_KEY << 7;
+ *key_inv |= ICE_DC_KEYINV << 7;
+ } else if (nvr_mtch & 0x1) { /* never match bit */
+ *key |= ICE_NM_KEY << 7;
+ *key_inv |= ICE_NM_KEYINV << 7;
+ } else if (val & 0x01) { /* exact 1 match */
+ *key |= ICE_1_KEY << 7;
+ *key_inv |= ICE_1_KEYINV << 7;
+ } else { /* exact 0 match */
+ *key |= ICE_0_KEY << 7;
+ *key_inv |= ICE_0_KEYINV << 7;
+ }
+
+ dont_care >>= 1;
+ nvr_mtch >>= 1;
+ valid >>= 1;
+ val >>= 1;
+ in_key >>= 1;
+ in_key_inv >>= 1;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_bits_max_set - determine if the number of bits set is within a maximum
+ * @mask: pointer to the byte array which is the mask
+ * @size: the number of bytes in the mask
+ * @max: the max number of set bits
+ *
+ * This function determines if there are at most 'max' number of bits set in an
+ * array. Returns true if the number for bits set is <= max or will return false
+ * otherwise.
+ */
+static bool ice_bits_max_set(const u8 *mask, u16 size, u16 max)
+{
+ u16 count = 0;
+ u16 i;
+
+ /* check each byte */
+ for (i = 0; i < size; i++) {
+ /* if 0, go to next byte */
+ if (!mask[i])
+ continue;
+
+ /* We know there is at least one set bit in this byte because of
+ * the above check; if we already have found 'max' number of
+ * bits set, then we can return failure now.
+ */
+ if (count == max)
+ return false;
+
+ /* count the bits in this byte, checking threshold */
+ count += hweight8(mask[i]);
+ if (count > max)
+ return false;
+ }
+
+ return true;
+}
+
+/**
+ * ice_set_key - generate a variable sized key with multiples of 16-bits
+ * @key: pointer to where the key will be stored
+ * @size: the size of the complete key in bytes (must be even)
+ * @val: array of 8-bit values that makes up the value portion of the key
+ * @upd: array of 8-bit masks that determine what key portion to update
+ * @dc: array of 8-bit masks that make up the don't care mask
+ * @nm: array of 8-bit masks that make up the never match mask
+ * @off: the offset of the first byte in the key to update
+ * @len: the number of bytes in the key update
+ *
+ * This function generates a key from a value, a don't care mask and a never
+ * match mask.
+ * upd, dc, and nm are optional parameters, and can be NULL:
+ * upd == NULL --> udp mask is all 1's (update all bits)
+ * dc == NULL --> dc mask is all 0's (no don't care bits)
+ * nm == NULL --> nm mask is all 0's (no never match bits)
+ */
+static enum ice_status
+ice_set_key(u8 *key, u16 size, u8 *val, u8 *upd, u8 *dc, u8 *nm, u16 off,
+ u16 len)
+{
+ u16 half_size;
+ u16 i;
+
+ /* size must be a multiple of 2 bytes. */
+ if (size % 2)
+ return ICE_ERR_CFG;
+
+ half_size = size / 2;
+ if (off + len > half_size)
+ return ICE_ERR_CFG;
+
+ /* Make sure at most one bit is set in the never match mask. Having more
+ * than one never match mask bit set will cause HW to consume excessive
+ * power otherwise; this is a power management efficiency check.
+ */
+#define ICE_NVR_MTCH_BITS_MAX 1
+ if (nm && !ice_bits_max_set(nm, len, ICE_NVR_MTCH_BITS_MAX))
+ return ICE_ERR_CFG;
+
+ for (i = 0; i < len; i++)
+ if (ice_gen_key_word(val[i], upd ? upd[i] : 0xff,
+ dc ? dc[i] : 0, nm ? nm[i] : 0,
+ key + off + i, key + half_size + off + i))
+ return ICE_ERR_CFG;
+
+ return 0;
+}
+
/**
* ice_acquire_global_cfg_lock
* @hw: pointer to the HW structure
@@ -205,6 +456,31 @@ static void ice_release_global_cfg_lock(struct ice_hw *hw)
}
/**
+ * ice_acquire_change_lock
+ * @hw: pointer to the HW structure
+ * @access: access type (read or write)
+ *
+ * This function will request ownership of the change lock.
+ */
+static enum ice_status
+ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access)
+{
+ return ice_acquire_res(hw, ICE_CHANGE_LOCK_RES_ID, access,
+ ICE_CHANGE_LOCK_TIMEOUT);
+}
+
+/**
+ * ice_release_change_lock
+ * @hw: pointer to the HW structure
+ *
+ * This function will release the change lock using the proper Admin Command.
+ */
+static void ice_release_change_lock(struct ice_hw *hw)
+{
+ ice_release_res(hw, ICE_CHANGE_LOCK_RES_ID);
+}
+
+/**
* ice_aq_download_pkg
* @hw: pointer to the hardware structure
* @pkg_buf: the package buffer to transfer
@@ -253,6 +529,54 @@ ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
}
/**
+ * ice_aq_update_pkg
+ * @hw: pointer to the hardware structure
+ * @pkg_buf: the package cmd buffer
+ * @buf_size: the size of the package cmd buffer
+ * @last_buf: last buffer indicator
+ * @error_offset: returns error offset
+ * @error_info: returns error information
+ * @cd: pointer to command details structure or NULL
+ *
+ * Update Package (0x0C42)
+ */
+static enum ice_status
+ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, u16 buf_size,
+ bool last_buf, u32 *error_offset, u32 *error_info,
+ struct ice_sq_cd *cd)
+{
+ struct ice_aqc_download_pkg *cmd;
+ struct ice_aq_desc desc;
+ enum ice_status status;
+
+ if (error_offset)
+ *error_offset = 0;
+ if (error_info)
+ *error_info = 0;
+
+ cmd = &desc.params.download_pkg;
+ ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+ if (last_buf)
+ cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
+
+ status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
+ if (status == ICE_ERR_AQ_ERROR) {
+ /* Read error from buffer only when the FW returned an error */
+ struct ice_aqc_download_pkg_resp *resp;
+
+ resp = (struct ice_aqc_download_pkg_resp *)pkg_buf;
+ if (error_offset)
+ *error_offset = le32_to_cpu(resp->error_offset);
+ if (error_info)
+ *error_info = le32_to_cpu(resp->error_info);
+ }
+
+ return status;
+}
+
+/**
* ice_find_seg_in_pkg
* @hw: pointer to the hardware structure
* @seg_type: the segment type to search for (i.e., SEGMENT_TYPE_CPK)
@@ -287,6 +611,44 @@ ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type,
}
/**
+ * ice_update_pkg
+ * @hw: pointer to the hardware structure
+ * @bufs: pointer to an array of buffers
+ * @count: the number of buffers in the array
+ *
+ * Obtains change lock and updates package.
+ */
+static enum ice_status
+ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
+{
+ enum ice_status status;
+ u32 offset, info, i;
+
+ status = ice_acquire_change_lock(hw, ICE_RES_WRITE);
+ if (status)
+ return status;
+
+ for (i = 0; i < count; i++) {
+ struct ice_buf_hdr *bh = (struct ice_buf_hdr *)(bufs + i);
+ bool last = ((i + 1) == count);
+
+ status = ice_aq_update_pkg(hw, bh, le16_to_cpu(bh->data_end),
+ last, &offset, &info, NULL);
+
+ if (status) {
+ ice_debug(hw, ICE_DBG_PKG,
+ "Update pkg failed: err %d off %d inf %d\n",
+ status, offset, info);
+ break;
+ }
+ }
+
+ ice_release_change_lock(hw);
+
+ return status;
+}
+
+/**
* ice_dwnld_cfg_bufs
* @hw: pointer to the hardware structure
* @bufs: pointer to an array of buffers
@@ -767,6 +1129,169 @@ enum ice_status ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len)
return status;
}
+/**
+ * ice_pkg_buf_alloc
+ * @hw: pointer to the HW structure
+ *
+ * Allocates a package buffer and returns a pointer to the buffer header.
+ * Note: all package contents must be in Little Endian form.
+ */
+static struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw)
+{
+ struct ice_buf_build *bld;
+ struct ice_buf_hdr *buf;
+
+ bld = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*bld), GFP_KERNEL);
+ if (!bld)
+ return NULL;
+
+ buf = (struct ice_buf_hdr *)bld;
+ buf->data_end = cpu_to_le16(offsetof(struct ice_buf_hdr,
+ section_entry));
+ return bld;
+}
+
+/**
+ * ice_pkg_buf_free
+ * @hw: pointer to the HW structure
+ * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
+ *
+ * Frees a package buffer
+ */
+static void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld)
+{
+ devm_kfree(ice_hw_to_dev(hw), bld);
+}
+
+/**
+ * ice_pkg_buf_reserve_section
+ * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
+ * @count: the number of sections to reserve
+ *
+ * Reserves one or more section table entries in a package buffer. This routine
+ * can be called multiple times as long as they are made before calling
+ * ice_pkg_buf_alloc_section(). Once ice_pkg_buf_alloc_section()
+ * is called once, the number of sections that can be allocated will not be able
+ * to be increased; not using all reserved sections is fine, but this will
+ * result in some wasted space in the buffer.
+ * Note: all package contents must be in Little Endian form.
+ */
+static enum ice_status
+ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count)
+{
+ struct ice_buf_hdr *buf;
+ u16 section_count;
+ u16 data_end;
+
+ if (!bld)
+ return ICE_ERR_PARAM;
+
+ buf = (struct ice_buf_hdr *)&bld->buf;
+
+ /* already an active section, can't increase table size */
+ section_count = le16_to_cpu(buf->section_count);
+ if (section_count > 0)
+ return ICE_ERR_CFG;
+
+ if (bld->reserved_section_table_entries + count > ICE_MAX_S_COUNT)
+ return ICE_ERR_CFG;
+ bld->reserved_section_table_entries += count;
+
+ data_end = le16_to_cpu(buf->data_end) +
+ (count * sizeof(buf->section_entry[0]));
+ buf->data_end = cpu_to_le16(data_end);
+
+ return 0;
+}
+
+/**
+ * ice_pkg_buf_alloc_section
+ * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
+ * @type: the section type value
+ * @size: the size of the section to reserve (in bytes)
+ *
+ * Reserves memory in the buffer for a section's content and updates the
+ * buffers' status accordingly. This routine returns a pointer to the first
+ * byte of the section start within the buffer, which is used to fill in the
+ * section contents.
+ * Note: all package contents must be in Little Endian form.
+ */
+static void *
+ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size)
+{
+ struct ice_buf_hdr *buf;
+ u16 sect_count;
+ u16 data_end;
+
+ if (!bld || !type || !size)
+ return NULL;
+
+ buf = (struct ice_buf_hdr *)&bld->buf;
+
+ /* check for enough space left in buffer */
+ data_end = le16_to_cpu(buf->data_end);
+
+ /* section start must align on 4 byte boundary */
+ data_end = ALIGN(data_end, 4);
+
+ if ((data_end + size) > ICE_MAX_S_DATA_END)
+ return NULL;
+
+ /* check for more available section table entries */
+ sect_count = le16_to_cpu(buf->section_count);
+ if (sect_count < bld->reserved_section_table_entries) {
+ void *section_ptr = ((u8 *)buf) + data_end;
+
+ buf->section_entry[sect_count].offset = cpu_to_le16(data_end);
+ buf->section_entry[sect_count].size = cpu_to_le16(size);
+ buf->section_entry[sect_count].type = cpu_to_le32(type);
+
+ data_end += size;
+ buf->data_end = cpu_to_le16(data_end);
+
+ buf->section_count = cpu_to_le16(sect_count + 1);
+ return section_ptr;
+ }
+
+ /* no free section table entries */
+ return NULL;
+}
+
+/**
+ * ice_pkg_buf_get_active_sections
+ * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
+ *
+ * Returns the number of active sections. Before using the package buffer
+ * in an update package command, the caller should make sure that there is at
+ * least one active section - otherwise, the buffer is not legal and should
+ * not be used.
+ * Note: all package contents must be in Little Endian form.
+ */
+static u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld)
+{
+ struct ice_buf_hdr *buf;
+
+ if (!bld)
+ return 0;
+
+ buf = (struct ice_buf_hdr *)&bld->buf;
+ return le16_to_cpu(buf->section_count);
+}
+
+/**
+ * ice_pkg_buf
+ * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
+ *
+ * Return a pointer to the buffer's header
+ */
+static struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld)
+{
+ if (!bld)
+ return NULL;
+
+ return &bld->buf;
+}
+
/* PTG Management */
/**
@@ -951,6 +1476,48 @@ enum ice_sid_all {
ICE_SID_OFF_COUNT,
};
+/* Characteristic handling */
+
+/**
+ * ice_match_prop_lst - determine if properties of two lists match
+ * @list1: first properties list
+ * @list2: second properties list
+ *
+ * Count, cookies and the order must match in order to be considered equivalent.
+ */
+static bool
+ice_match_prop_lst(struct list_head *list1, struct list_head *list2)
+{
+ struct ice_vsig_prof *tmp1;
+ struct ice_vsig_prof *tmp2;
+ u16 chk_count = 0;
+ u16 count = 0;
+
+ /* compare counts */
+ list_for_each_entry(tmp1, list1, list)
+ count++;
+ list_for_each_entry(tmp2, list2, list)
+ chk_count++;
+ if (!count || count != chk_count)
+ return false;
+
+ tmp1 = list_first_entry(list1, struct ice_vsig_prof, list);
+ tmp2 = list_first_entry(list2, struct ice_vsig_prof, list);
+
+ /* profile cookies must compare, and in the exact same order to take
+ * into account priority
+ */
+ while (count--) {
+ if (tmp2->profile_cookie != tmp1->profile_cookie)
+ return false;
+
+ tmp1 = list_next_entry(tmp1, list);
+ tmp2 = list_next_entry(tmp2, list);
+ }
+
+ return true;
+}
+
/* VSIG Management */
/**
@@ -999,6 +1566,117 @@ static u16 ice_vsig_alloc_val(struct ice_hw *hw, enum ice_block blk, u16 vsig)
}
/**
+ * ice_vsig_alloc - Finds a free entry and allocates a new VSIG
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ *
+ * This function will iterate through the VSIG list and mark the first
+ * unused entry for the new VSIG entry as used and return that value.
+ */
+static u16 ice_vsig_alloc(struct ice_hw *hw, enum ice_block blk)
+{
+ u16 i;
+
+ for (i = 1; i < ICE_MAX_VSIGS; i++)
+ if (!hw->blk[blk].xlt2.vsig_tbl[i].in_use)
+ return ice_vsig_alloc_val(hw, blk, i);
+
+ return ICE_DEFAULT_VSIG;
+}
+
+/**
+ * ice_find_dup_props_vsig - find VSI group with a specified set of properties
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @chs: characteristic list
+ * @vsig: returns the VSIG with the matching profiles, if found
+ *
+ * Each VSIG is associated with a characteristic set; i.e. all VSIs under
+ * a group have the same characteristic set. To check if there exists a VSIG
+ * which has the same characteristics as the input characteristics; this
+ * function will iterate through the XLT2 list and return the VSIG that has a
+ * matching configuration. In order to make sure that priorities are accounted
+ * for, the list must match exactly, including the order in which the
+ * characteristics are listed.
+ */
+static enum ice_status
+ice_find_dup_props_vsig(struct ice_hw *hw, enum ice_block blk,
+ struct list_head *chs, u16 *vsig)
+{
+ struct ice_xlt2 *xlt2 = &hw->blk[blk].xlt2;
+ u16 i;
+
+ for (i = 0; i < xlt2->count; i++)
+ if (xlt2->vsig_tbl[i].in_use &&
+ ice_match_prop_lst(chs, &xlt2->vsig_tbl[i].prop_lst)) {
+ *vsig = ICE_VSIG_VALUE(i, hw->pf_id);
+ return 0;
+ }
+
+ return ICE_ERR_DOES_NOT_EXIST;
+}
+
+/**
+ * ice_vsig_free - free VSI group
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @vsig: VSIG to remove
+ *
+ * The function will remove all VSIs associated with the input VSIG and move
+ * them to the DEFAULT_VSIG and mark the VSIG available.
+ */
+static enum ice_status
+ice_vsig_free(struct ice_hw *hw, enum ice_block blk, u16 vsig)
+{
+ struct ice_vsig_prof *dtmp, *del;
+ struct ice_vsig_vsi *vsi_cur;
+ u16 idx;
+
+ idx = vsig & ICE_VSIG_IDX_M;
+ if (idx >= ICE_MAX_VSIGS)
+ return ICE_ERR_PARAM;
+
+ if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use)
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ hw->blk[blk].xlt2.vsig_tbl[idx].in_use = false;
+
+ vsi_cur = hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi;
+ /* If the VSIG has at least 1 VSI then iterate through the
+ * list and remove the VSIs before deleting the group.
+ */
+ if (vsi_cur) {
+ /* remove all vsis associated with this VSIG XLT2 entry */
+ do {
+ struct ice_vsig_vsi *tmp = vsi_cur->next_vsi;
+
+ vsi_cur->vsig = ICE_DEFAULT_VSIG;
+ vsi_cur->changed = 1;
+ vsi_cur->next_vsi = NULL;
+ vsi_cur = tmp;
+ } while (vsi_cur);
+
+ /* NULL terminate head of VSI list */
+ hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi = NULL;
+ }
+
+ /* free characteristic list */
+ list_for_each_entry_safe(del, dtmp,
+ &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst,
+ list) {
+ list_del(&del->list);
+ devm_kfree(ice_hw_to_dev(hw), del);
+ }
+
+ /* if VSIG characteristic list was cleared for reset
+ * re-initialize the list head
+ */
+ INIT_LIST_HEAD(&hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst);
+
+ return 0;
+}
+
+/**
* ice_vsig_remove_vsi - remove VSI from VSIG
* @hw: pointer to the hardware structure
* @blk: HW block
@@ -1117,6 +1795,215 @@ ice_vsig_add_mv_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig)
return 0;
}
+/**
+ * ice_find_prof_id - find profile ID for a given field vector
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @fv: field vector to search for
+ * @prof_id: receives the profile ID
+ */
+static enum ice_status
+ice_find_prof_id(struct ice_hw *hw, enum ice_block blk,
+ struct ice_fv_word *fv, u8 *prof_id)
+{
+ struct ice_es *es = &hw->blk[blk].es;
+ u16 off, i;
+
+ for (i = 0; i < es->count; i++) {
+ off = i * es->fvw;
+
+ if (memcmp(&es->t[off], fv, es->fvw * sizeof(*fv)))
+ continue;
+
+ *prof_id = i;
+ return 0;
+ }
+
+ return ICE_ERR_DOES_NOT_EXIST;
+}
+
+/**
+ * ice_prof_id_rsrc_type - get profile ID resource type for a block type
+ * @blk: the block type
+ * @rsrc_type: pointer to variable to receive the resource type
+ */
+static bool ice_prof_id_rsrc_type(enum ice_block blk, u16 *rsrc_type)
+{
+ switch (blk) {
+ case ICE_BLK_RSS:
+ *rsrc_type = ICE_AQC_RES_TYPE_HASH_PROF_BLDR_PROFID;
+ break;
+ default:
+ return false;
+ }
+ return true;
+}
+
+/**
+ * ice_tcam_ent_rsrc_type - get TCAM entry resource type for a block type
+ * @blk: the block type
+ * @rsrc_type: pointer to variable to receive the resource type
+ */
+static bool ice_tcam_ent_rsrc_type(enum ice_block blk, u16 *rsrc_type)
+{
+ switch (blk) {
+ case ICE_BLK_RSS:
+ *rsrc_type = ICE_AQC_RES_TYPE_HASH_PROF_BLDR_TCAM;
+ break;
+ default:
+ return false;
+ }
+ return true;
+}
+
+/**
+ * ice_alloc_tcam_ent - allocate hardware TCAM entry
+ * @hw: pointer to the HW struct
+ * @blk: the block to allocate the TCAM for
+ * @tcam_idx: pointer to variable to receive the TCAM entry
+ *
+ * This function allocates a new entry in a Profile ID TCAM for a specific
+ * block.
+ */
+static enum ice_status
+ice_alloc_tcam_ent(struct ice_hw *hw, enum ice_block blk, u16 *tcam_idx)
+{
+ u16 res_type;
+
+ if (!ice_tcam_ent_rsrc_type(blk, &res_type))
+ return ICE_ERR_PARAM;
+
+ return ice_alloc_hw_res(hw, res_type, 1, true, tcam_idx);
+}
+
+/**
+ * ice_free_tcam_ent - free hardware TCAM entry
+ * @hw: pointer to the HW struct
+ * @blk: the block from which to free the TCAM entry
+ * @tcam_idx: the TCAM entry to free
+ *
+ * This function frees an entry in a Profile ID TCAM for a specific block.
+ */
+static enum ice_status
+ice_free_tcam_ent(struct ice_hw *hw, enum ice_block blk, u16 tcam_idx)
+{
+ u16 res_type;
+
+ if (!ice_tcam_ent_rsrc_type(blk, &res_type))
+ return ICE_ERR_PARAM;
+
+ return ice_free_hw_res(hw, res_type, 1, &tcam_idx);
+}
+
+/**
+ * ice_alloc_prof_id - allocate profile ID
+ * @hw: pointer to the HW struct
+ * @blk: the block to allocate the profile ID for
+ * @prof_id: pointer to variable to receive the profile ID
+ *
+ * This function allocates a new profile ID, which also corresponds to a Field
+ * Vector (Extraction Sequence) entry.
+ */
+static enum ice_status
+ice_alloc_prof_id(struct ice_hw *hw, enum ice_block blk, u8 *prof_id)
+{
+ enum ice_status status;
+ u16 res_type;
+ u16 get_prof;
+
+ if (!ice_prof_id_rsrc_type(blk, &res_type))
+ return ICE_ERR_PARAM;
+
+ status = ice_alloc_hw_res(hw, res_type, 1, false, &get_prof);
+ if (!status)
+ *prof_id = (u8)get_prof;
+
+ return status;
+}
+
+/**
+ * ice_free_prof_id - free profile ID
+ * @hw: pointer to the HW struct
+ * @blk: the block from which to free the profile ID
+ * @prof_id: the profile ID to free
+ *
+ * This function frees a profile ID, which also corresponds to a Field Vector.
+ */
+static enum ice_status
+ice_free_prof_id(struct ice_hw *hw, enum ice_block blk, u8 prof_id)
+{
+ u16 tmp_prof_id = (u16)prof_id;
+ u16 res_type;
+
+ if (!ice_prof_id_rsrc_type(blk, &res_type))
+ return ICE_ERR_PARAM;
+
+ return ice_free_hw_res(hw, res_type, 1, &tmp_prof_id);
+}
+
+/**
+ * ice_prof_inc_ref - increment reference count for profile
+ * @hw: pointer to the HW struct
+ * @blk: the block from which to free the profile ID
+ * @prof_id: the profile ID for which to increment the reference count
+ */
+static enum ice_status
+ice_prof_inc_ref(struct ice_hw *hw, enum ice_block blk, u8 prof_id)
+{
+ if (prof_id > hw->blk[blk].es.count)
+ return ICE_ERR_PARAM;
+
+ hw->blk[blk].es.ref_count[prof_id]++;
+
+ return 0;
+}
+
+/**
+ * ice_write_es - write an extraction sequence to hardware
+ * @hw: pointer to the HW struct
+ * @blk: the block in which to write the extraction sequence
+ * @prof_id: the profile ID to write
+ * @fv: pointer to the extraction sequence to write - NULL to clear extraction
+ */
+static void
+ice_write_es(struct ice_hw *hw, enum ice_block blk, u8 prof_id,
+ struct ice_fv_word *fv)
+{
+ u16 off;
+
+ off = prof_id * hw->blk[blk].es.fvw;
+ if (!fv) {
+ memset(&hw->blk[blk].es.t[off], 0,
+ hw->blk[blk].es.fvw * sizeof(*fv));
+ hw->blk[blk].es.written[prof_id] = false;
+ } else {
+ memcpy(&hw->blk[blk].es.t[off], fv,
+ hw->blk[blk].es.fvw * sizeof(*fv));
+ }
+}
+
+/**
+ * ice_prof_dec_ref - decrement reference count for profile
+ * @hw: pointer to the HW struct
+ * @blk: the block from which to free the profile ID
+ * @prof_id: the profile ID for which to decrement the reference count
+ */
+static enum ice_status
+ice_prof_dec_ref(struct ice_hw *hw, enum ice_block blk, u8 prof_id)
+{
+ if (prof_id > hw->blk[blk].es.count)
+ return ICE_ERR_PARAM;
+
+ if (hw->blk[blk].es.ref_count[prof_id] > 0) {
+ if (!--hw->blk[blk].es.ref_count[prof_id]) {
+ ice_write_es(hw, blk, prof_id, NULL);
+ return ice_free_prof_id(hw, blk, prof_id);
+ }
+ }
+
+ return 0;
+}
+
/* Block / table section IDs */
static const u32 ice_blk_sids[ICE_BLK_COUNT][ICE_SID_OFF_COUNT] = {
/* SWITCH */
@@ -1374,16 +2261,85 @@ void ice_fill_blk_tbls(struct ice_hw *hw)
}
/**
+ * ice_free_prof_map - free profile map
+ * @hw: pointer to the hardware structure
+ * @blk_idx: HW block index
+ */
+static void ice_free_prof_map(struct ice_hw *hw, u8 blk_idx)
+{
+ struct ice_es *es = &hw->blk[blk_idx].es;
+ struct ice_prof_map *del, *tmp;
+
+ mutex_lock(&es->prof_map_lock);
+ list_for_each_entry_safe(del, tmp, &es->prof_map, list) {
+ list_del(&del->list);
+ devm_kfree(ice_hw_to_dev(hw), del);
+ }
+ INIT_LIST_HEAD(&es->prof_map);
+ mutex_unlock(&es->prof_map_lock);
+}
+
+/**
+ * ice_free_flow_profs - free flow profile entries
+ * @hw: pointer to the hardware structure
+ * @blk_idx: HW block index
+ */
+static void ice_free_flow_profs(struct ice_hw *hw, u8 blk_idx)
+{
+ struct ice_flow_prof *p, *tmp;
+
+ mutex_lock(&hw->fl_profs_locks[blk_idx]);
+ list_for_each_entry_safe(p, tmp, &hw->fl_profs[blk_idx], l_entry) {
+ list_del(&p->l_entry);
+ devm_kfree(ice_hw_to_dev(hw), p);
+ }
+ mutex_unlock(&hw->fl_profs_locks[blk_idx]);
+
+ /* if driver is in reset and tables are being cleared
+ * re-initialize the flow profile list heads
+ */
+ INIT_LIST_HEAD(&hw->fl_profs[blk_idx]);
+}
+
+/**
+ * ice_free_vsig_tbl - free complete VSIG table entries
+ * @hw: pointer to the hardware structure
+ * @blk: the HW block on which to free the VSIG table entries
+ */
+static void ice_free_vsig_tbl(struct ice_hw *hw, enum ice_block blk)
+{
+ u16 i;
+
+ if (!hw->blk[blk].xlt2.vsig_tbl)
+ return;
+
+ for (i = 1; i < ICE_MAX_VSIGS; i++)
+ if (hw->blk[blk].xlt2.vsig_tbl[i].in_use)
+ ice_vsig_free(hw, blk, i);
+}
+
+/**
* ice_free_hw_tbls - free hardware table memory
* @hw: pointer to the hardware structure
*/
void ice_free_hw_tbls(struct ice_hw *hw)
{
+ struct ice_rss_cfg *r, *rt;
u8 i;
for (i = 0; i < ICE_BLK_COUNT; i++) {
- hw->blk[i].is_list_init = false;
+ if (hw->blk[i].is_list_init) {
+ struct ice_es *es = &hw->blk[i].es;
+ ice_free_prof_map(hw, i);
+ mutex_destroy(&es->prof_map_lock);
+
+ ice_free_flow_profs(hw, i);
+ mutex_destroy(&hw->fl_profs_locks[i]);
+
+ hw->blk[i].is_list_init = false;
+ }
+ ice_free_vsig_tbl(hw, (enum ice_block)i);
devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt1.ptypes);
devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt1.ptg_tbl);
devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt1.t);
@@ -1397,10 +2353,26 @@ void ice_free_hw_tbls(struct ice_hw *hw)
devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.written);
}
+ list_for_each_entry_safe(r, rt, &hw->rss_list_head, l_entry) {
+ list_del(&r->l_entry);
+ devm_kfree(ice_hw_to_dev(hw), r);
+ }
+ mutex_destroy(&hw->rss_locks);
memset(hw->blk, 0, sizeof(hw->blk));
}
/**
+ * ice_init_flow_profs - init flow profile locks and list heads
+ * @hw: pointer to the hardware structure
+ * @blk_idx: HW block index
+ */
+static void ice_init_flow_profs(struct ice_hw *hw, u8 blk_idx)
+{
+ mutex_init(&hw->fl_profs_locks[blk_idx]);
+ INIT_LIST_HEAD(&hw->fl_profs[blk_idx]);
+}
+
+/**
* ice_clear_hw_tbls - clear HW tables and flow profiles
* @hw: pointer to the hardware structure
*/
@@ -1415,6 +2387,13 @@ void ice_clear_hw_tbls(struct ice_hw *hw)
struct ice_xlt2 *xlt2 = &hw->blk[i].xlt2;
struct ice_es *es = &hw->blk[i].es;
+ if (hw->blk[i].is_list_init) {
+ ice_free_prof_map(hw, i);
+ ice_free_flow_profs(hw, i);
+ }
+
+ ice_free_vsig_tbl(hw, (enum ice_block)i);
+
memset(xlt1->ptypes, 0, xlt1->count * sizeof(*xlt1->ptypes));
memset(xlt1->ptg_tbl, 0,
ICE_MAX_PTGS * sizeof(*xlt1->ptg_tbl));
@@ -1443,6 +2422,8 @@ enum ice_status ice_init_hw_tbls(struct ice_hw *hw)
{
u8 i;
+ mutex_init(&hw->rss_locks);
+ INIT_LIST_HEAD(&hw->rss_list_head);
for (i = 0; i < ICE_BLK_COUNT; i++) {
struct ice_prof_redir *prof_redir = &hw->blk[i].prof_redir;
struct ice_prof_tcam *prof = &hw->blk[i].prof;
@@ -1454,6 +2435,9 @@ enum ice_status ice_init_hw_tbls(struct ice_hw *hw)
if (hw->blk[i].is_list_init)
continue;
+ ice_init_flow_profs(hw, i);
+ mutex_init(&es->prof_map_lock);
+ INIT_LIST_HEAD(&es->prof_map);
hw->blk[i].is_list_init = true;
hw->blk[i].overwrite = blk_sizes[i].overwrite;
@@ -1547,3 +2531,1580 @@ enum ice_status ice_init_hw_tbls(struct ice_hw *hw)
ice_free_hw_tbls(hw);
return ICE_ERR_NO_MEMORY;
}
+
+/**
+ * ice_prof_gen_key - generate profile ID key
+ * @hw: pointer to the HW struct
+ * @blk: the block in which to write profile ID to
+ * @ptg: packet type group (PTG) portion of key
+ * @vsig: VSIG portion of key
+ * @cdid: CDID portion of key
+ * @flags: flag portion of key
+ * @vl_msk: valid mask
+ * @dc_msk: don't care mask
+ * @nm_msk: never match mask
+ * @key: output of profile ID key
+ */
+static enum ice_status
+ice_prof_gen_key(struct ice_hw *hw, enum ice_block blk, u8 ptg, u16 vsig,
+ u8 cdid, u16 flags, u8 vl_msk[ICE_TCAM_KEY_VAL_SZ],
+ u8 dc_msk[ICE_TCAM_KEY_VAL_SZ], u8 nm_msk[ICE_TCAM_KEY_VAL_SZ],
+ u8 key[ICE_TCAM_KEY_SZ])
+{
+ struct ice_prof_id_key inkey;
+
+ inkey.xlt1 = ptg;
+ inkey.xlt2_cdid = cpu_to_le16(vsig);
+ inkey.flags = cpu_to_le16(flags);
+
+ switch (hw->blk[blk].prof.cdid_bits) {
+ case 0:
+ break;
+ case 2:
+#define ICE_CD_2_M 0xC000U
+#define ICE_CD_2_S 14
+ inkey.xlt2_cdid &= ~cpu_to_le16(ICE_CD_2_M);
+ inkey.xlt2_cdid |= cpu_to_le16(BIT(cdid) << ICE_CD_2_S);
+ break;
+ case 4:
+#define ICE_CD_4_M 0xF000U
+#define ICE_CD_4_S 12
+ inkey.xlt2_cdid &= ~cpu_to_le16(ICE_CD_4_M);
+ inkey.xlt2_cdid |= cpu_to_le16(BIT(cdid) << ICE_CD_4_S);
+ break;
+ case 8:
+#define ICE_CD_8_M 0xFF00U
+#define ICE_CD_8_S 16
+ inkey.xlt2_cdid &= ~cpu_to_le16(ICE_CD_8_M);
+ inkey.xlt2_cdid |= cpu_to_le16(BIT(cdid) << ICE_CD_8_S);
+ break;
+ default:
+ ice_debug(hw, ICE_DBG_PKG, "Error in profile config\n");
+ break;
+ }
+
+ return ice_set_key(key, ICE_TCAM_KEY_SZ, (u8 *)&inkey, vl_msk, dc_msk,
+ nm_msk, 0, ICE_TCAM_KEY_SZ / 2);
+}
+
+/**
+ * ice_tcam_write_entry - write TCAM entry
+ * @hw: pointer to the HW struct
+ * @blk: the block in which to write profile ID to
+ * @idx: the entry index to write to
+ * @prof_id: profile ID
+ * @ptg: packet type group (PTG) portion of key
+ * @vsig: VSIG portion of key
+ * @cdid: CDID portion of key
+ * @flags: flag portion of key
+ * @vl_msk: valid mask
+ * @dc_msk: don't care mask
+ * @nm_msk: never match mask
+ */
+static enum ice_status
+ice_tcam_write_entry(struct ice_hw *hw, enum ice_block blk, u16 idx,
+ u8 prof_id, u8 ptg, u16 vsig, u8 cdid, u16 flags,
+ u8 vl_msk[ICE_TCAM_KEY_VAL_SZ],
+ u8 dc_msk[ICE_TCAM_KEY_VAL_SZ],
+ u8 nm_msk[ICE_TCAM_KEY_VAL_SZ])
+{
+ struct ice_prof_tcam_entry;
+ enum ice_status status;
+
+ status = ice_prof_gen_key(hw, blk, ptg, vsig, cdid, flags, vl_msk,
+ dc_msk, nm_msk, hw->blk[blk].prof.t[idx].key);
+ if (!status) {
+ hw->blk[blk].prof.t[idx].addr = cpu_to_le16(idx);
+ hw->blk[blk].prof.t[idx].prof_id = prof_id;
+ }
+
+ return status;
+}
+
+/**
+ * ice_vsig_get_ref - returns number of VSIs belong to a VSIG
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @vsig: VSIG to query
+ * @refs: pointer to variable to receive the reference count
+ */
+static enum ice_status
+ice_vsig_get_ref(struct ice_hw *hw, enum ice_block blk, u16 vsig, u16 *refs)
+{
+ u16 idx = vsig & ICE_VSIG_IDX_M;
+ struct ice_vsig_vsi *ptr;
+
+ *refs = 0;
+
+ if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use)
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ ptr = hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi;
+ while (ptr) {
+ (*refs)++;
+ ptr = ptr->next_vsi;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_has_prof_vsig - check to see if VSIG has a specific profile
+ * @hw: pointer to the hardware structure
+ * @blk: HW block
+ * @vsig: VSIG to check against
+ * @hdl: profile handle
+ */
+static bool
+ice_has_prof_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl)
+{
+ u16 idx = vsig & ICE_VSIG_IDX_M;
+ struct ice_vsig_prof *ent;
+
+ list_for_each_entry(ent, &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst,
+ list)
+ if (ent->profile_cookie == hdl)
+ return true;
+
+ ice_debug(hw, ICE_DBG_INIT,
+ "Characteristic list for VSI group %d not found.\n",
+ vsig);
+ return false;
+}
+
+/**
+ * ice_prof_bld_es - build profile ID extraction sequence changes
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @bld: the update package buffer build to add to
+ * @chgs: the list of changes to make in hardware
+ */
+static enum ice_status
+ice_prof_bld_es(struct ice_hw *hw, enum ice_block blk,
+ struct ice_buf_build *bld, struct list_head *chgs)
+{
+ u16 vec_size = hw->blk[blk].es.fvw * sizeof(struct ice_fv_word);
+ struct ice_chs_chg *tmp;
+
+ list_for_each_entry(tmp, chgs, list_entry)
+ if (tmp->type == ICE_PTG_ES_ADD && tmp->add_prof) {
+ u16 off = tmp->prof_id * hw->blk[blk].es.fvw;
+ struct ice_pkg_es *p;
+ u32 id;
+
+ id = ice_sect_id(blk, ICE_VEC_TBL);
+ p = (struct ice_pkg_es *)
+ ice_pkg_buf_alloc_section(bld, id, sizeof(*p) +
+ vec_size -
+ sizeof(p->es[0]));
+
+ if (!p)
+ return ICE_ERR_MAX_LIMIT;
+
+ p->count = cpu_to_le16(1);
+ p->offset = cpu_to_le16(tmp->prof_id);
+
+ memcpy(p->es, &hw->blk[blk].es.t[off], vec_size);
+ }
+
+ return 0;
+}
+
+/**
+ * ice_prof_bld_tcam - build profile ID TCAM changes
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @bld: the update package buffer build to add to
+ * @chgs: the list of changes to make in hardware
+ */
+static enum ice_status
+ice_prof_bld_tcam(struct ice_hw *hw, enum ice_block blk,
+ struct ice_buf_build *bld, struct list_head *chgs)
+{
+ struct ice_chs_chg *tmp;
+
+ list_for_each_entry(tmp, chgs, list_entry)
+ if (tmp->type == ICE_TCAM_ADD && tmp->add_tcam_idx) {
+ struct ice_prof_id_section *p;
+ u32 id;
+
+ id = ice_sect_id(blk, ICE_PROF_TCAM);
+ p = (struct ice_prof_id_section *)
+ ice_pkg_buf_alloc_section(bld, id, sizeof(*p));
+
+ if (!p)
+ return ICE_ERR_MAX_LIMIT;
+
+ p->count = cpu_to_le16(1);
+ p->entry[0].addr = cpu_to_le16(tmp->tcam_idx);
+ p->entry[0].prof_id = tmp->prof_id;
+
+ memcpy(p->entry[0].key,
+ &hw->blk[blk].prof.t[tmp->tcam_idx].key,
+ sizeof(hw->blk[blk].prof.t->key));
+ }
+
+ return 0;
+}
+
+/**
+ * ice_prof_bld_xlt1 - build XLT1 changes
+ * @blk: hardware block
+ * @bld: the update package buffer build to add to
+ * @chgs: the list of changes to make in hardware
+ */
+static enum ice_status
+ice_prof_bld_xlt1(enum ice_block blk, struct ice_buf_build *bld,
+ struct list_head *chgs)
+{
+ struct ice_chs_chg *tmp;
+
+ list_for_each_entry(tmp, chgs, list_entry)
+ if (tmp->type == ICE_PTG_ES_ADD && tmp->add_ptg) {
+ struct ice_xlt1_section *p;
+ u32 id;
+
+ id = ice_sect_id(blk, ICE_XLT1);
+ p = (struct ice_xlt1_section *)
+ ice_pkg_buf_alloc_section(bld, id, sizeof(*p));
+
+ if (!p)
+ return ICE_ERR_MAX_LIMIT;
+
+ p->count = cpu_to_le16(1);
+ p->offset = cpu_to_le16(tmp->ptype);
+ p->value[0] = tmp->ptg;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_prof_bld_xlt2 - build XLT2 changes
+ * @blk: hardware block
+ * @bld: the update package buffer build to add to
+ * @chgs: the list of changes to make in hardware
+ */
+static enum ice_status
+ice_prof_bld_xlt2(enum ice_block blk, struct ice_buf_build *bld,
+ struct list_head *chgs)
+{
+ struct ice_chs_chg *tmp;
+
+ list_for_each_entry(tmp, chgs, list_entry) {
+ struct ice_xlt2_section *p;
+ u32 id;
+
+ switch (tmp->type) {
+ case ICE_VSIG_ADD:
+ case ICE_VSI_MOVE:
+ case ICE_VSIG_REM:
+ id = ice_sect_id(blk, ICE_XLT2);
+ p = (struct ice_xlt2_section *)
+ ice_pkg_buf_alloc_section(bld, id, sizeof(*p));
+
+ if (!p)
+ return ICE_ERR_MAX_LIMIT;
+
+ p->count = cpu_to_le16(1);
+ p->offset = cpu_to_le16(tmp->vsi);
+ p->value[0] = cpu_to_le16(tmp->vsig);
+ break;
+ default:
+ break;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ice_upd_prof_hw - update hardware using the change list
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @chgs: the list of changes to make in hardware
+ */
+static enum ice_status
+ice_upd_prof_hw(struct ice_hw *hw, enum ice_block blk,
+ struct list_head *chgs)
+{
+ struct ice_buf_build *b;
+ struct ice_chs_chg *tmp;
+ enum ice_status status;
+ u16 pkg_sects;
+ u16 xlt1 = 0;
+ u16 xlt2 = 0;
+ u16 tcam = 0;
+ u16 es = 0;
+ u16 sects;
+
+ /* count number of sections we need */
+ list_for_each_entry(tmp, chgs, list_entry) {
+ switch (tmp->type) {
+ case ICE_PTG_ES_ADD:
+ if (tmp->add_ptg)
+ xlt1++;
+ if (tmp->add_prof)
+ es++;
+ break;
+ case ICE_TCAM_ADD:
+ tcam++;
+ break;
+ case ICE_VSIG_ADD:
+ case ICE_VSI_MOVE:
+ case ICE_VSIG_REM:
+ xlt2++;
+ break;
+ default:
+ break;
+ }
+ }
+ sects = xlt1 + xlt2 + tcam + es;
+
+ if (!sects)
+ return 0;
+
+ /* Build update package buffer */
+ b = ice_pkg_buf_alloc(hw);
+ if (!b)
+ return ICE_ERR_NO_MEMORY;
+
+ status = ice_pkg_buf_reserve_section(b, sects);
+ if (status)
+ goto error_tmp;
+
+ /* Preserve order of table update: ES, TCAM, PTG, VSIG */
+ if (es) {
+ status = ice_prof_bld_es(hw, blk, b, chgs);
+ if (status)
+ goto error_tmp;
+ }
+
+ if (tcam) {
+ status = ice_prof_bld_tcam(hw, blk, b, chgs);
+ if (status)
+ goto error_tmp;
+ }
+
+ if (xlt1) {
+ status = ice_prof_bld_xlt1(blk, b, chgs);
+ if (status)
+ goto error_tmp;
+ }
+
+ if (xlt2) {
+ status = ice_prof_bld_xlt2(blk, b, chgs);
+ if (status)
+ goto error_tmp;
+ }
+
+ /* After package buffer build check if the section count in buffer is
+ * non-zero and matches the number of sections detected for package
+ * update.
+ */
+ pkg_sects = ice_pkg_buf_get_active_sections(b);
+ if (!pkg_sects || pkg_sects != sects) {
+ status = ICE_ERR_INVAL_SIZE;
+ goto error_tmp;
+ }
+
+ /* update package */
+ status = ice_update_pkg(hw, ice_pkg_buf(b), 1);
+ if (status == ICE_ERR_AQ_ERROR)
+ ice_debug(hw, ICE_DBG_INIT, "Unable to update HW profile\n");
+
+error_tmp:
+ ice_pkg_buf_free(hw, b);
+ return status;
+}
+
+/**
+ * ice_add_prof - add profile
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @id: profile tracking ID
+ * @ptypes: array of bitmaps indicating ptypes (ICE_FLOW_PTYPE_MAX bits)
+ * @es: extraction sequence (length of array is determined by the block)
+ *
+ * This function registers a profile, which matches a set of PTGs with a
+ * particular extraction sequence. While the hardware profile is allocated
+ * it will not be written until the first call to ice_add_flow that specifies
+ * the ID value used here.
+ */
+enum ice_status
+ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
+ struct ice_fv_word *es)
+{
+ u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE);
+ DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT);
+ struct ice_prof_map *prof;
+ enum ice_status status;
+ u32 byte = 0;
+ u8 prof_id;
+
+ bitmap_zero(ptgs_used, ICE_XLT1_CNT);
+
+ mutex_lock(&hw->blk[blk].es.prof_map_lock);
+
+ /* search for existing profile */
+ status = ice_find_prof_id(hw, blk, es, &prof_id);
+ if (status) {
+ /* allocate profile ID */
+ status = ice_alloc_prof_id(hw, blk, &prof_id);
+ if (status)
+ goto err_ice_add_prof;
+
+ /* and write new es */
+ ice_write_es(hw, blk, prof_id, es);
+ }
+
+ ice_prof_inc_ref(hw, blk, prof_id);
+
+ /* add profile info */
+ prof = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*prof), GFP_KERNEL);
+ if (!prof)
+ goto err_ice_add_prof;
+
+ prof->profile_cookie = id;
+ prof->prof_id = prof_id;
+ prof->ptg_cnt = 0;
+ prof->context = 0;
+
+ /* build list of ptgs */
+ while (bytes && prof->ptg_cnt < ICE_MAX_PTG_PER_PROFILE) {
+ u32 bit;
+
+ if (!ptypes[byte]) {
+ bytes--;
+ byte++;
+ continue;
+ }
+
+ /* Examine 8 bits per byte */
+ for_each_set_bit(bit, (unsigned long *)&ptypes[byte],
+ BITS_PER_BYTE) {
+ u16 ptype;
+ u8 ptg;
+ u8 m;
+
+ ptype = byte * BITS_PER_BYTE + bit;
+
+ /* The package should place all ptypes in a non-zero
+ * PTG, so the following call should never fail.
+ */
+ if (ice_ptg_find_ptype(hw, blk, ptype, &ptg))
+ continue;
+
+ /* If PTG is already added, skip and continue */
+ if (test_bit(ptg, ptgs_used))
+ continue;
+
+ set_bit(ptg, ptgs_used);
+ prof->ptg[prof->ptg_cnt] = ptg;
+
+ if (++prof->ptg_cnt >= ICE_MAX_PTG_PER_PROFILE)
+ break;
+
+ /* nothing left in byte, then exit */
+ m = ~((1 << (bit + 1)) - 1);
+ if (!(ptypes[byte] & m))
+ break;
+ }
+
+ bytes--;
+ byte++;
+ }
+
+ list_add(&prof->list, &hw->blk[blk].es.prof_map);
+ status = 0;
+
+err_ice_add_prof:
+ mutex_unlock(&hw->blk[blk].es.prof_map_lock);
+ return status;
+}
+
+/**
+ * ice_search_prof_id_low - Search for a profile tracking ID low level
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @id: profile tracking ID
+ *
+ * This will search for a profile tracking ID which was previously added. This
+ * version assumes that the caller has already acquired the prof map lock.
+ */
+static struct ice_prof_map *
+ice_search_prof_id_low(struct ice_hw *hw, enum ice_block blk, u64 id)
+{
+ struct ice_prof_map *entry = NULL;
+ struct ice_prof_map *map;
+
+ list_for_each_entry(map, &hw->blk[blk].es.prof_map, list)
+ if (map->profile_cookie == id) {
+ entry = map;
+ break;
+ }
+
+ return entry;
+}
+
+/**
+ * ice_search_prof_id - Search for a profile tracking ID
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @id: profile tracking ID
+ *
+ * This will search for a profile tracking ID which was previously added.
+ */
+static struct ice_prof_map *
+ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id)
+{
+ struct ice_prof_map *entry;
+
+ mutex_lock(&hw->blk[blk].es.prof_map_lock);
+ entry = ice_search_prof_id_low(hw, blk, id);
+ mutex_unlock(&hw->blk[blk].es.prof_map_lock);
+
+ return entry;
+}
+
+/**
+ * ice_vsig_prof_id_count - count profiles in a VSIG
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsig: VSIG to remove the profile from
+ */
+static u16
+ice_vsig_prof_id_count(struct ice_hw *hw, enum ice_block blk, u16 vsig)
+{
+ u16 idx = vsig & ICE_VSIG_IDX_M, count = 0;
+ struct ice_vsig_prof *p;
+
+ list_for_each_entry(p, &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst,
+ list)
+ count++;
+
+ return count;
+}
+
+/**
+ * ice_rel_tcam_idx - release a TCAM index
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @idx: the index to release
+ */
+static enum ice_status
+ice_rel_tcam_idx(struct ice_hw *hw, enum ice_block blk, u16 idx)
+{
+ /* Masks to invoke a never match entry */
+ u8 vl_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
+ u8 dc_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFE, 0xFF, 0xFF, 0xFF, 0xFF };
+ u8 nm_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x01, 0x00, 0x00, 0x00, 0x00 };
+ enum ice_status status;
+
+ /* write the TCAM entry */
+ status = ice_tcam_write_entry(hw, blk, idx, 0, 0, 0, 0, 0, vl_msk,
+ dc_msk, nm_msk);
+ if (status)
+ return status;
+
+ /* release the TCAM entry */
+ status = ice_free_tcam_ent(hw, blk, idx);
+
+ return status;
+}
+
+/**
+ * ice_rem_prof_id - remove one profile from a VSIG
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @prof: pointer to profile structure to remove
+ */
+static enum ice_status
+ice_rem_prof_id(struct ice_hw *hw, enum ice_block blk,
+ struct ice_vsig_prof *prof)
+{
+ enum ice_status status;
+ u16 i;
+
+ for (i = 0; i < prof->tcam_count; i++)
+ if (prof->tcam[i].in_use) {
+ prof->tcam[i].in_use = false;
+ status = ice_rel_tcam_idx(hw, blk,
+ prof->tcam[i].tcam_idx);
+ if (status)
+ return ICE_ERR_HW_TABLE;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_rem_vsig - remove VSIG
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsig: the VSIG to remove
+ * @chg: the change list
+ */
+static enum ice_status
+ice_rem_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig,
+ struct list_head *chg)
+{
+ u16 idx = vsig & ICE_VSIG_IDX_M;
+ struct ice_vsig_vsi *vsi_cur;
+ struct ice_vsig_prof *d, *t;
+ enum ice_status status;
+
+ /* remove TCAM entries */
+ list_for_each_entry_safe(d, t,
+ &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst,
+ list) {
+ status = ice_rem_prof_id(hw, blk, d);
+ if (status)
+ return status;
+
+ list_del(&d->list);
+ devm_kfree(ice_hw_to_dev(hw), d);
+ }
+
+ /* Move all VSIS associated with this VSIG to the default VSIG */
+ vsi_cur = hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi;
+ /* If the VSIG has at least 1 VSI then iterate through the list
+ * and remove the VSIs before deleting the group.
+ */
+ if (vsi_cur)
+ do {
+ struct ice_vsig_vsi *tmp = vsi_cur->next_vsi;
+ struct ice_chs_chg *p;
+
+ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p),
+ GFP_KERNEL);
+ if (!p)
+ return ICE_ERR_NO_MEMORY;
+
+ p->type = ICE_VSIG_REM;
+ p->orig_vsig = vsig;
+ p->vsig = ICE_DEFAULT_VSIG;
+ p->vsi = vsi_cur - hw->blk[blk].xlt2.vsis;
+
+ list_add(&p->list_entry, chg);
+
+ vsi_cur = tmp;
+ } while (vsi_cur);
+
+ return ice_vsig_free(hw, blk, vsig);
+}
+
+/**
+ * ice_rem_prof_id_vsig - remove a specific profile from a VSIG
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsig: VSIG to remove the profile from
+ * @hdl: profile handle indicating which profile to remove
+ * @chg: list to receive a record of changes
+ */
+static enum ice_status
+ice_rem_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl,
+ struct list_head *chg)
+{
+ u16 idx = vsig & ICE_VSIG_IDX_M;
+ struct ice_vsig_prof *p, *t;
+ enum ice_status status;
+
+ list_for_each_entry_safe(p, t,
+ &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst,
+ list)
+ if (p->profile_cookie == hdl) {
+ if (ice_vsig_prof_id_count(hw, blk, vsig) == 1)
+ /* this is the last profile, remove the VSIG */
+ return ice_rem_vsig(hw, blk, vsig, chg);
+
+ status = ice_rem_prof_id(hw, blk, p);
+ if (!status) {
+ list_del(&p->list);
+ devm_kfree(ice_hw_to_dev(hw), p);
+ }
+ return status;
+ }
+
+ return ICE_ERR_DOES_NOT_EXIST;
+}
+
+/**
+ * ice_rem_flow_all - remove all flows with a particular profile
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @id: profile tracking ID
+ */
+static enum ice_status
+ice_rem_flow_all(struct ice_hw *hw, enum ice_block blk, u64 id)
+{
+ struct ice_chs_chg *del, *tmp;
+ enum ice_status status;
+ struct list_head chg;
+ u16 i;
+
+ INIT_LIST_HEAD(&chg);
+
+ for (i = 1; i < ICE_MAX_VSIGS; i++)
+ if (hw->blk[blk].xlt2.vsig_tbl[i].in_use) {
+ if (ice_has_prof_vsig(hw, blk, i, id)) {
+ status = ice_rem_prof_id_vsig(hw, blk, i, id,
+ &chg);
+ if (status)
+ goto err_ice_rem_flow_all;
+ }
+ }
+
+ status = ice_upd_prof_hw(hw, blk, &chg);
+
+err_ice_rem_flow_all:
+ list_for_each_entry_safe(del, tmp, &chg, list_entry) {
+ list_del(&del->list_entry);
+ devm_kfree(ice_hw_to_dev(hw), del);
+ }
+
+ return status;
+}
+
+/**
+ * ice_rem_prof - remove profile
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @id: profile tracking ID
+ *
+ * This will remove the profile specified by the ID parameter, which was
+ * previously created through ice_add_prof. If any existing entries
+ * are associated with this profile, they will be removed as well.
+ */
+enum ice_status ice_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 id)
+{
+ struct ice_prof_map *pmap;
+ enum ice_status status;
+
+ mutex_lock(&hw->blk[blk].es.prof_map_lock);
+
+ pmap = ice_search_prof_id_low(hw, blk, id);
+ if (!pmap) {
+ status = ICE_ERR_DOES_NOT_EXIST;
+ goto err_ice_rem_prof;
+ }
+
+ /* remove all flows with this profile */
+ status = ice_rem_flow_all(hw, blk, pmap->profile_cookie);
+ if (status)
+ goto err_ice_rem_prof;
+
+ /* dereference profile, and possibly remove */
+ ice_prof_dec_ref(hw, blk, pmap->prof_id);
+
+ list_del(&pmap->list);
+ devm_kfree(ice_hw_to_dev(hw), pmap);
+
+err_ice_rem_prof:
+ mutex_unlock(&hw->blk[blk].es.prof_map_lock);
+ return status;
+}
+
+/**
+ * ice_get_prof - get profile
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @hdl: profile handle
+ * @chg: change list
+ */
+static enum ice_status
+ice_get_prof(struct ice_hw *hw, enum ice_block blk, u64 hdl,
+ struct list_head *chg)
+{
+ struct ice_prof_map *map;
+ struct ice_chs_chg *p;
+ u16 i;
+
+ /* Get the details on the profile specified by the handle ID */
+ map = ice_search_prof_id(hw, blk, hdl);
+ if (!map)
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ for (i = 0; i < map->ptg_cnt; i++)
+ if (!hw->blk[blk].es.written[map->prof_id]) {
+ /* add ES to change list */
+ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p),
+ GFP_KERNEL);
+ if (!p)
+ goto err_ice_get_prof;
+
+ p->type = ICE_PTG_ES_ADD;
+ p->ptype = 0;
+ p->ptg = map->ptg[i];
+ p->add_ptg = 0;
+
+ p->add_prof = 1;
+ p->prof_id = map->prof_id;
+
+ hw->blk[blk].es.written[map->prof_id] = true;
+
+ list_add(&p->list_entry, chg);
+ }
+
+ return 0;
+
+err_ice_get_prof:
+ /* let caller clean up the change list */
+ return ICE_ERR_NO_MEMORY;
+}
+
+/**
+ * ice_get_profs_vsig - get a copy of the list of profiles from a VSIG
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsig: VSIG from which to copy the list
+ * @lst: output list
+ *
+ * This routine makes a copy of the list of profiles in the specified VSIG.
+ */
+static enum ice_status
+ice_get_profs_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig,
+ struct list_head *lst)
+{
+ struct ice_vsig_prof *ent1, *ent2;
+ u16 idx = vsig & ICE_VSIG_IDX_M;
+
+ list_for_each_entry(ent1, &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst,
+ list) {
+ struct ice_vsig_prof *p;
+
+ /* copy to the input list */
+ p = devm_kmemdup(ice_hw_to_dev(hw), ent1, sizeof(*p),
+ GFP_KERNEL);
+ if (!p)
+ goto err_ice_get_profs_vsig;
+
+ list_add_tail(&p->list, lst);
+ }
+
+ return 0;
+
+err_ice_get_profs_vsig:
+ list_for_each_entry_safe(ent1, ent2, lst, list) {
+ list_del(&ent1->list);
+ devm_kfree(ice_hw_to_dev(hw), ent1);
+ }
+
+ return ICE_ERR_NO_MEMORY;
+}
+
+/**
+ * ice_add_prof_to_lst - add profile entry to a list
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @lst: the list to be added to
+ * @hdl: profile handle of entry to add
+ */
+static enum ice_status
+ice_add_prof_to_lst(struct ice_hw *hw, enum ice_block blk,
+ struct list_head *lst, u64 hdl)
+{
+ struct ice_prof_map *map;
+ struct ice_vsig_prof *p;
+ u16 i;
+
+ map = ice_search_prof_id(hw, blk, hdl);
+ if (!map)
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return ICE_ERR_NO_MEMORY;
+
+ p->profile_cookie = map->profile_cookie;
+ p->prof_id = map->prof_id;
+ p->tcam_count = map->ptg_cnt;
+
+ for (i = 0; i < map->ptg_cnt; i++) {
+ p->tcam[i].prof_id = map->prof_id;
+ p->tcam[i].tcam_idx = ICE_INVALID_TCAM;
+ p->tcam[i].ptg = map->ptg[i];
+ }
+
+ list_add(&p->list, lst);
+
+ return 0;
+}
+
+/**
+ * ice_move_vsi - move VSI to another VSIG
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsi: the VSI to move
+ * @vsig: the VSIG to move the VSI to
+ * @chg: the change list
+ */
+static enum ice_status
+ice_move_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig,
+ struct list_head *chg)
+{
+ enum ice_status status;
+ struct ice_chs_chg *p;
+ u16 orig_vsig;
+
+ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return ICE_ERR_NO_MEMORY;
+
+ status = ice_vsig_find_vsi(hw, blk, vsi, &orig_vsig);
+ if (!status)
+ status = ice_vsig_add_mv_vsi(hw, blk, vsi, vsig);
+
+ if (status) {
+ devm_kfree(ice_hw_to_dev(hw), p);
+ return status;
+ }
+
+ p->type = ICE_VSI_MOVE;
+ p->vsi = vsi;
+ p->orig_vsig = orig_vsig;
+ p->vsig = vsig;
+
+ list_add(&p->list_entry, chg);
+
+ return 0;
+}
+
+/**
+ * ice_prof_tcam_ena_dis - add enable or disable TCAM change
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @enable: true to enable, false to disable
+ * @vsig: the VSIG of the TCAM entry
+ * @tcam: pointer the TCAM info structure of the TCAM to disable
+ * @chg: the change list
+ *
+ * This function appends an enable or disable TCAM entry in the change log
+ */
+static enum ice_status
+ice_prof_tcam_ena_dis(struct ice_hw *hw, enum ice_block blk, bool enable,
+ u16 vsig, struct ice_tcam_inf *tcam,
+ struct list_head *chg)
+{
+ enum ice_status status;
+ struct ice_chs_chg *p;
+
+ /* Default: enable means change the low flag bit to don't care */
+ u8 dc_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x01, 0x00, 0x00, 0x00, 0x00 };
+ u8 nm_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x00, 0x00, 0x00, 0x00, 0x00 };
+ u8 vl_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x01, 0x00, 0x00, 0x00, 0x00 };
+
+ /* if disabling, free the TCAM */
+ if (!enable) {
+ status = ice_free_tcam_ent(hw, blk, tcam->tcam_idx);
+ tcam->tcam_idx = 0;
+ tcam->in_use = 0;
+ return status;
+ }
+
+ /* for re-enabling, reallocate a TCAM */
+ status = ice_alloc_tcam_ent(hw, blk, &tcam->tcam_idx);
+ if (status)
+ return status;
+
+ /* add TCAM to change list */
+ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return ICE_ERR_NO_MEMORY;
+
+ status = ice_tcam_write_entry(hw, blk, tcam->tcam_idx, tcam->prof_id,
+ tcam->ptg, vsig, 0, 0, vl_msk, dc_msk,
+ nm_msk);
+ if (status)
+ goto err_ice_prof_tcam_ena_dis;
+
+ tcam->in_use = 1;
+
+ p->type = ICE_TCAM_ADD;
+ p->add_tcam_idx = true;
+ p->prof_id = tcam->prof_id;
+ p->ptg = tcam->ptg;
+ p->vsig = 0;
+ p->tcam_idx = tcam->tcam_idx;
+
+ /* log change */
+ list_add(&p->list_entry, chg);
+
+ return 0;
+
+err_ice_prof_tcam_ena_dis:
+ devm_kfree(ice_hw_to_dev(hw), p);
+ return status;
+}
+
+/**
+ * ice_adj_prof_priorities - adjust profile based on priorities
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsig: the VSIG for which to adjust profile priorities
+ * @chg: the change list
+ */
+static enum ice_status
+ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig,
+ struct list_head *chg)
+{
+ DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT);
+ struct ice_vsig_prof *t;
+ enum ice_status status;
+ u16 idx;
+
+ bitmap_zero(ptgs_used, ICE_XLT1_CNT);
+ idx = vsig & ICE_VSIG_IDX_M;
+
+ /* Priority is based on the order in which the profiles are added. The
+ * newest added profile has highest priority and the oldest added
+ * profile has the lowest priority. Since the profile property list for
+ * a VSIG is sorted from newest to oldest, this code traverses the list
+ * in order and enables the first of each PTG that it finds (that is not
+ * already enabled); it also disables any duplicate PTGs that it finds
+ * in the older profiles (that are currently enabled).
+ */
+
+ list_for_each_entry(t, &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst,
+ list) {
+ u16 i;
+
+ for (i = 0; i < t->tcam_count; i++) {
+ /* Scan the priorities from newest to oldest.
+ * Make sure that the newest profiles take priority.
+ */
+ if (test_bit(t->tcam[i].ptg, ptgs_used) &&
+ t->tcam[i].in_use) {
+ /* need to mark this PTG as never match, as it
+ * was already in use and therefore duplicate
+ * (and lower priority)
+ */
+ status = ice_prof_tcam_ena_dis(hw, blk, false,
+ vsig,
+ &t->tcam[i],
+ chg);
+ if (status)
+ return status;
+ } else if (!test_bit(t->tcam[i].ptg, ptgs_used) &&
+ !t->tcam[i].in_use) {
+ /* need to enable this PTG, as it in not in use
+ * and not enabled (highest priority)
+ */
+ status = ice_prof_tcam_ena_dis(hw, blk, true,
+ vsig,
+ &t->tcam[i],
+ chg);
+ if (status)
+ return status;
+ }
+
+ /* keep track of used ptgs */
+ set_bit(t->tcam[i].ptg, ptgs_used);
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ice_add_prof_id_vsig - add profile to VSIG
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsig: the VSIG to which this profile is to be added
+ * @hdl: the profile handle indicating the profile to add
+ * @chg: the change list
+ */
+static enum ice_status
+ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl,
+ struct list_head *chg)
+{
+ /* Masks that ignore flags */
+ u8 vl_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
+ u8 dc_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0x00, 0x00, 0x00 };
+ u8 nm_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x00, 0x00, 0x00, 0x00, 0x00 };
+ struct ice_prof_map *map;
+ struct ice_vsig_prof *t;
+ struct ice_chs_chg *p;
+ u16 i;
+
+ /* Get the details on the profile specified by the handle ID */
+ map = ice_search_prof_id(hw, blk, hdl);
+ if (!map)
+ return ICE_ERR_DOES_NOT_EXIST;
+
+ /* Error, if this VSIG already has this profile */
+ if (ice_has_prof_vsig(hw, blk, vsig, hdl))
+ return ICE_ERR_ALREADY_EXISTS;
+
+ /* new VSIG profile structure */
+ t = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*t), GFP_KERNEL);
+ if (!t)
+ return ICE_ERR_NO_MEMORY;
+
+ t->profile_cookie = map->profile_cookie;
+ t->prof_id = map->prof_id;
+ t->tcam_count = map->ptg_cnt;
+
+ /* create TCAM entries */
+ for (i = 0; i < map->ptg_cnt; i++) {
+ enum ice_status status;
+ u16 tcam_idx;
+
+ /* add TCAM to change list */
+ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL);
+ if (!p)
+ goto err_ice_add_prof_id_vsig;
+
+ /* allocate the TCAM entry index */
+ status = ice_alloc_tcam_ent(hw, blk, &tcam_idx);
+ if (status) {
+ devm_kfree(ice_hw_to_dev(hw), p);
+ goto err_ice_add_prof_id_vsig;
+ }
+
+ t->tcam[i].ptg = map->ptg[i];
+ t->tcam[i].prof_id = map->prof_id;
+ t->tcam[i].tcam_idx = tcam_idx;
+ t->tcam[i].in_use = true;
+
+ p->type = ICE_TCAM_ADD;
+ p->add_tcam_idx = true;
+ p->prof_id = t->tcam[i].prof_id;
+ p->ptg = t->tcam[i].ptg;
+ p->vsig = vsig;
+ p->tcam_idx = t->tcam[i].tcam_idx;
+
+ /* write the TCAM entry */
+ status = ice_tcam_write_entry(hw, blk, t->tcam[i].tcam_idx,
+ t->tcam[i].prof_id,
+ t->tcam[i].ptg, vsig, 0, 0,
+ vl_msk, dc_msk, nm_msk);
+ if (status)
+ goto err_ice_add_prof_id_vsig;
+
+ /* log change */
+ list_add(&p->list_entry, chg);
+ }
+
+ /* add profile to VSIG */
+ list_add(&t->list,
+ &hw->blk[blk].xlt2.vsig_tbl[(vsig & ICE_VSIG_IDX_M)].prop_lst);
+
+ return 0;
+
+err_ice_add_prof_id_vsig:
+ /* let caller clean up the change list */
+ devm_kfree(ice_hw_to_dev(hw), t);
+ return ICE_ERR_NO_MEMORY;
+}
+
+/**
+ * ice_create_prof_id_vsig - add a new VSIG with a single profile
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsi: the initial VSI that will be in VSIG
+ * @hdl: the profile handle of the profile that will be added to the VSIG
+ * @chg: the change list
+ */
+static enum ice_status
+ice_create_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl,
+ struct list_head *chg)
+{
+ enum ice_status status;
+ struct ice_chs_chg *p;
+ u16 new_vsig;
+
+ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return ICE_ERR_NO_MEMORY;
+
+ new_vsig = ice_vsig_alloc(hw, blk);
+ if (!new_vsig) {
+ status = ICE_ERR_HW_TABLE;
+ goto err_ice_create_prof_id_vsig;
+ }
+
+ status = ice_move_vsi(hw, blk, vsi, new_vsig, chg);
+ if (status)
+ goto err_ice_create_prof_id_vsig;
+
+ status = ice_add_prof_id_vsig(hw, blk, new_vsig, hdl, chg);
+ if (status)
+ goto err_ice_create_prof_id_vsig;
+
+ p->type = ICE_VSIG_ADD;
+ p->vsi = vsi;
+ p->orig_vsig = ICE_DEFAULT_VSIG;
+ p->vsig = new_vsig;
+
+ list_add(&p->list_entry, chg);
+
+ return 0;
+
+err_ice_create_prof_id_vsig:
+ /* let caller clean up the change list */
+ devm_kfree(ice_hw_to_dev(hw), p);
+ return status;
+}
+
+/**
+ * ice_create_vsig_from_lst - create a new VSIG with a list of profiles
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsi: the initial VSI that will be in VSIG
+ * @lst: the list of profile that will be added to the VSIG
+ * @chg: the change list
+ */
+static enum ice_status
+ice_create_vsig_from_lst(struct ice_hw *hw, enum ice_block blk, u16 vsi,
+ struct list_head *lst, struct list_head *chg)
+{
+ struct ice_vsig_prof *t;
+ enum ice_status status;
+ u16 vsig;
+
+ vsig = ice_vsig_alloc(hw, blk);
+ if (!vsig)
+ return ICE_ERR_HW_TABLE;
+
+ status = ice_move_vsi(hw, blk, vsi, vsig, chg);
+ if (status)
+ return status;
+
+ list_for_each_entry(t, lst, list) {
+ status = ice_add_prof_id_vsig(hw, blk, vsig, t->profile_cookie,
+ chg);
+ if (status)
+ return status;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_find_prof_vsig - find a VSIG with a specific profile handle
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @hdl: the profile handle of the profile to search for
+ * @vsig: returns the VSIG with the matching profile
+ */
+static bool
+ice_find_prof_vsig(struct ice_hw *hw, enum ice_block blk, u64 hdl, u16 *vsig)
+{
+ struct ice_vsig_prof *t;
+ enum ice_status status;
+ struct list_head lst;
+
+ INIT_LIST_HEAD(&lst);
+
+ t = kzalloc(sizeof(*t), GFP_KERNEL);
+ if (!t)
+ return false;
+
+ t->profile_cookie = hdl;
+ list_add(&t->list, &lst);
+
+ status = ice_find_dup_props_vsig(hw, blk, &lst, vsig);
+
+ list_del(&t->list);
+ kfree(t);
+
+ return !status;
+}
+
+/**
+ * ice_add_prof_id_flow - add profile flow
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsi: the VSI to enable with the profile specified by ID
+ * @hdl: profile handle
+ *
+ * Calling this function will update the hardware tables to enable the
+ * profile indicated by the ID parameter for the VSIs specified in the VSI
+ * array. Once successfully called, the flow will be enabled.
+ */
+enum ice_status
+ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl)
+{
+ struct ice_vsig_prof *tmp1, *del1;
+ struct ice_chs_chg *tmp, *del;
+ struct list_head union_lst;
+ enum ice_status status;
+ struct list_head chg;
+ u16 vsig;
+
+ INIT_LIST_HEAD(&union_lst);
+ INIT_LIST_HEAD(&chg);
+
+ /* Get profile */
+ status = ice_get_prof(hw, blk, hdl, &chg);
+ if (status)
+ return status;
+
+ /* determine if VSI is already part of a VSIG */
+ status = ice_vsig_find_vsi(hw, blk, vsi, &vsig);
+ if (!status && vsig) {
+ bool only_vsi;
+ u16 or_vsig;
+ u16 ref;
+
+ /* found in VSIG */
+ or_vsig = vsig;
+
+ /* make sure that there is no overlap/conflict between the new
+ * characteristics and the existing ones; we don't support that
+ * scenario
+ */
+ if (ice_has_prof_vsig(hw, blk, vsig, hdl)) {
+ status = ICE_ERR_ALREADY_EXISTS;
+ goto err_ice_add_prof_id_flow;
+ }
+
+ /* last VSI in the VSIG? */
+ status = ice_vsig_get_ref(hw, blk, vsig, &ref);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+ only_vsi = (ref == 1);
+
+ /* create a union of the current profiles and the one being
+ * added
+ */
+ status = ice_get_profs_vsig(hw, blk, vsig, &union_lst);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+
+ status = ice_add_prof_to_lst(hw, blk, &union_lst, hdl);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+
+ /* search for an existing VSIG with an exact charc match */
+ status = ice_find_dup_props_vsig(hw, blk, &union_lst, &vsig);
+ if (!status) {
+ /* move VSI to the VSIG that matches */
+ status = ice_move_vsi(hw, blk, vsi, vsig, &chg);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+
+ /* VSI has been moved out of or_vsig. If the or_vsig had
+ * only that VSI it is now empty and can be removed.
+ */
+ if (only_vsi) {
+ status = ice_rem_vsig(hw, blk, or_vsig, &chg);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+ }
+ } else if (only_vsi) {
+ /* If the original VSIG only contains one VSI, then it
+ * will be the requesting VSI. In this case the VSI is
+ * not sharing entries and we can simply add the new
+ * profile to the VSIG.
+ */
+ status = ice_add_prof_id_vsig(hw, blk, vsig, hdl, &chg);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+
+ /* Adjust priorities */
+ status = ice_adj_prof_priorities(hw, blk, vsig, &chg);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+ } else {
+ /* No match, so we need a new VSIG */
+ status = ice_create_vsig_from_lst(hw, blk, vsi,
+ &union_lst, &chg);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+
+ /* Adjust priorities */
+ status = ice_adj_prof_priorities(hw, blk, vsig, &chg);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+ }
+ } else {
+ /* need to find or add a VSIG */
+ /* search for an existing VSIG with an exact charc match */
+ if (ice_find_prof_vsig(hw, blk, hdl, &vsig)) {
+ /* found an exact match */
+ /* add or move VSI to the VSIG that matches */
+ status = ice_move_vsi(hw, blk, vsi, vsig, &chg);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+ } else {
+ /* we did not find an exact match */
+ /* we need to add a VSIG */
+ status = ice_create_prof_id_vsig(hw, blk, vsi, hdl,
+ &chg);
+ if (status)
+ goto err_ice_add_prof_id_flow;
+ }
+ }
+
+ /* update hardware */
+ if (!status)
+ status = ice_upd_prof_hw(hw, blk, &chg);
+
+err_ice_add_prof_id_flow:
+ list_for_each_entry_safe(del, tmp, &chg, list_entry) {
+ list_del(&del->list_entry);
+ devm_kfree(ice_hw_to_dev(hw), del);
+ }
+
+ list_for_each_entry_safe(del1, tmp1, &union_lst, list) {
+ list_del(&del1->list);
+ devm_kfree(ice_hw_to_dev(hw), del1);
+ }
+
+ return status;
+}
+
+/**
+ * ice_rem_prof_from_list - remove a profile from list
+ * @hw: pointer to the HW struct
+ * @lst: list to remove the profile from
+ * @hdl: the profile handle indicating the profile to remove
+ */
+static enum ice_status
+ice_rem_prof_from_list(struct ice_hw *hw, struct list_head *lst, u64 hdl)
+{
+ struct ice_vsig_prof *ent, *tmp;
+
+ list_for_each_entry_safe(ent, tmp, lst, list)
+ if (ent->profile_cookie == hdl) {
+ list_del(&ent->list);
+ devm_kfree(ice_hw_to_dev(hw), ent);
+ return 0;
+ }
+
+ return ICE_ERR_DOES_NOT_EXIST;
+}
+
+/**
+ * ice_rem_prof_id_flow - remove flow
+ * @hw: pointer to the HW struct
+ * @blk: hardware block
+ * @vsi: the VSI from which to remove the profile specified by ID
+ * @hdl: profile tracking handle
+ *
+ * Calling this function will update the hardware tables to remove the
+ * profile indicated by the ID parameter for the VSIs specified in the VSI
+ * array. Once successfully called, the flow will be disabled.
+ */
+enum ice_status
+ice_rem_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl)
+{
+ struct ice_vsig_prof *tmp1, *del1;
+ struct ice_chs_chg *tmp, *del;
+ struct list_head chg, copy;
+ enum ice_status status;
+ u16 vsig;
+
+ INIT_LIST_HEAD(©);
+ INIT_LIST_HEAD(&chg);
+
+ /* determine if VSI is already part of a VSIG */
+ status = ice_vsig_find_vsi(hw, blk, vsi, &vsig);
+ if (!status && vsig) {
+ bool last_profile;
+ bool only_vsi;
+ u16 ref;
+
+ /* found in VSIG */
+ last_profile = ice_vsig_prof_id_count(hw, blk, vsig) == 1;
+ status = ice_vsig_get_ref(hw, blk, vsig, &ref);
+ if (status)
+ goto err_ice_rem_prof_id_flow;
+ only_vsi = (ref == 1);
+
+ if (only_vsi) {
+ /* If the original VSIG only contains one reference,
+ * which will be the requesting VSI, then the VSI is not
+ * sharing entries and we can simply remove the specific
+ * characteristics from the VSIG.
+ */
+
+ if (last_profile) {
+ /* If there are no profiles left for this VSIG,
+ * then simply remove the the VSIG.
+ */
+ status = ice_rem_vsig(hw, blk, vsig, &chg);
+ if (status)
+ goto err_ice_rem_prof_id_flow;
+ } else {
+ status = ice_rem_prof_id_vsig(hw, blk, vsig,
+ hdl, &chg);
+ if (status)
+ goto err_ice_rem_prof_id_flow;
+
+ /* Adjust priorities */
+ status = ice_adj_prof_priorities(hw, blk, vsig,
+ &chg);
+ if (status)
+ goto err_ice_rem_prof_id_flow;
+ }
+
+ } else {
+ /* Make a copy of the VSIG's list of Profiles */
+ status = ice_get_profs_vsig(hw, blk, vsig, ©);
+ if (status)
+ goto err_ice_rem_prof_id_flow;
+
+ /* Remove specified profile entry from the list */
+ status = ice_rem_prof_from_list(hw, ©, hdl);
+ if (status)
+ goto err_ice_rem_prof_id_flow;
+
+ if (list_empty(©)) {
+ status = ice_move_vsi(hw, blk, vsi,
+ ICE_DEFAULT_VSIG, &chg);
+ if (status)
+ goto err_ice_rem_prof_id_flow;
+
+ } else if (!ice_find_dup_props_vsig(hw, blk, ©,
+ &vsig)) {
+ /* found an exact match */
+ /* add or move VSI to the VSIG that matches */
+ /* Search for a VSIG with a matching profile
+ * list
+ */
+
+ /* Found match, move VSI to the matching VSIG */
+ status = ice_move_vsi(hw, blk, vsi, vsig, &chg);
+ if (status)
+ goto err_ice_rem_prof_id_flow;
+ } else {
+ /* since no existing VSIG supports this
+ * characteristic pattern, we need to create a
+ * new VSIG and TCAM entries
+ */
+ status = ice_create_vsig_from_lst(hw, blk, vsi,
+ ©, &chg);
+ if (status)
+ goto err_ice_rem_prof_id_flow;
+
+ /* Adjust priorities */
+ status = ice_adj_prof_priorities(hw, blk, vsig,
+ &chg);
+ if (status)
+ goto err_ice_rem_prof_id_flow;
+ }
+ }
+ } else {
+ status = ICE_ERR_DOES_NOT_EXIST;
+ }
+
+ /* update hardware tables */
+ if (!status)
+ status = ice_upd_prof_hw(hw, blk, &chg);
+
+err_ice_rem_prof_id_flow:
+ list_for_each_entry_safe(del, tmp, &chg, list_entry) {
+ list_del(&del->list_entry);
+ devm_kfree(ice_hw_to_dev(hw), del);
+ }
+
+ list_for_each_entry_safe(del1, tmp1, ©, list) {
+ list_del(&del1->list);
+ devm_kfree(ice_hw_to_dev(hw), del1);
+ }
+
+ return status;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index 37eb282..c7b5e1a 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -18,6 +18,13 @@
#define ICE_PKG_CNT 4
+enum ice_status
+ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
+ struct ice_fv_word *es);
+enum ice_status
+ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl);
+enum ice_status
+ice_rem_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl);
enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buff, u32 len);
enum ice_status
ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len);
@@ -26,4 +33,6 @@ void ice_free_seg(struct ice_hw *hw);
void ice_fill_blk_tbls(struct ice_hw *hw);
void ice_clear_hw_tbls(struct ice_hw *hw);
void ice_free_hw_tbls(struct ice_hw *hw);
+enum ice_status
+ice_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 id);
#endif /* _ICE_FLEX_PIPE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h
index 5d5a7ea..0fb3fe3 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h
@@ -3,6 +3,9 @@
#ifndef _ICE_FLEX_TYPE_H_
#define _ICE_FLEX_TYPE_H_
+
+#define ICE_FV_OFFSET_INVAL 0x1FF
+
/* Extraction Sequence (Field Vector) Table */
struct ice_fv_word {
u8 prot_id;
@@ -105,37 +108,57 @@ struct ice_buf_hdr {
sizeof(struct ice_buf_hdr) - (hd_sz)) / (ent_sz))
/* ice package section IDs */
+#define ICE_SID_XLT0_SW 10
+#define ICE_SID_XLT_KEY_BUILDER_SW 11
#define ICE_SID_XLT1_SW 12
#define ICE_SID_XLT2_SW 13
#define ICE_SID_PROFID_TCAM_SW 14
#define ICE_SID_PROFID_REDIR_SW 15
#define ICE_SID_FLD_VEC_SW 16
+#define ICE_SID_CDID_KEY_BUILDER_SW 17
+#define ICE_SID_CDID_REDIR_SW 18
+#define ICE_SID_XLT0_ACL 20
+#define ICE_SID_XLT_KEY_BUILDER_ACL 21
#define ICE_SID_XLT1_ACL 22
#define ICE_SID_XLT2_ACL 23
#define ICE_SID_PROFID_TCAM_ACL 24
#define ICE_SID_PROFID_REDIR_ACL 25
#define ICE_SID_FLD_VEC_ACL 26
+#define ICE_SID_CDID_KEY_BUILDER_ACL 27
+#define ICE_SID_CDID_REDIR_ACL 28
+#define ICE_SID_XLT0_FD 30
+#define ICE_SID_XLT_KEY_BUILDER_FD 31
#define ICE_SID_XLT1_FD 32
#define ICE_SID_XLT2_FD 33
#define ICE_SID_PROFID_TCAM_FD 34
#define ICE_SID_PROFID_REDIR_FD 35
#define ICE_SID_FLD_VEC_FD 36
+#define ICE_SID_CDID_KEY_BUILDER_FD 37
+#define ICE_SID_CDID_REDIR_FD 38
+#define ICE_SID_XLT0_RSS 40
+#define ICE_SID_XLT_KEY_BUILDER_RSS 41
#define ICE_SID_XLT1_RSS 42
#define ICE_SID_XLT2_RSS 43
#define ICE_SID_PROFID_TCAM_RSS 44
#define ICE_SID_PROFID_REDIR_RSS 45
#define ICE_SID_FLD_VEC_RSS 46
+#define ICE_SID_CDID_KEY_BUILDER_RSS 47
+#define ICE_SID_CDID_REDIR_RSS 48
#define ICE_SID_RXPARSER_BOOST_TCAM 56
+#define ICE_SID_XLT0_PE 80
+#define ICE_SID_XLT_KEY_BUILDER_PE 81
#define ICE_SID_XLT1_PE 82
#define ICE_SID_XLT2_PE 83
#define ICE_SID_PROFID_TCAM_PE 84
#define ICE_SID_PROFID_REDIR_PE 85
#define ICE_SID_FLD_VEC_PE 86
+#define ICE_SID_CDID_KEY_BUILDER_PE 87
+#define ICE_SID_CDID_REDIR_PE 88
/* Label Metadata section IDs */
#define ICE_SID_LBL_FIRST 0x80000010
@@ -152,6 +175,19 @@ enum ice_block {
ICE_BLK_COUNT
};
+enum ice_sect {
+ ICE_XLT0 = 0,
+ ICE_XLT_KB,
+ ICE_XLT1,
+ ICE_XLT2,
+ ICE_PROF_TCAM,
+ ICE_PROF_REDIR,
+ ICE_VEC_TBL,
+ ICE_CDID_KB,
+ ICE_CDID_REDIR,
+ ICE_SECT_COUNT
+};
+
/* package labels */
struct ice_label {
__le16 value;
@@ -234,6 +270,13 @@ struct ice_prof_redir_section {
u8 redir_value[1];
};
+/* package buffer building */
+
+struct ice_buf_build {
+ struct ice_buf buf;
+ u16 reserved_section_table_entries;
+};
+
struct ice_pkg_enum {
struct ice_buf_table *buf_table;
u32 buf_idx;
@@ -248,6 +291,12 @@ struct ice_pkg_enum {
void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset);
};
+struct ice_pkg_es {
+ __le16 count;
+ __le16 offset;
+ struct ice_fv_word es[1];
+};
+
struct ice_es {
u32 sid;
u16 count;
@@ -280,6 +329,35 @@ struct ice_ptg_ptype {
u8 ptg;
};
+#define ICE_MAX_TCAM_PER_PROFILE 32
+#define ICE_MAX_PTG_PER_PROFILE 32
+
+struct ice_prof_map {
+ struct list_head list;
+ u64 profile_cookie;
+ u64 context;
+ u8 prof_id;
+ u8 ptg_cnt;
+ u8 ptg[ICE_MAX_PTG_PER_PROFILE];
+};
+
+#define ICE_INVALID_TCAM 0xFFFF
+
+struct ice_tcam_inf {
+ u16 tcam_idx;
+ u8 ptg;
+ u8 prof_id;
+ u8 in_use;
+};
+
+struct ice_vsig_prof {
+ struct list_head list;
+ u64 profile_cookie;
+ u8 prof_id;
+ u8 tcam_count;
+ struct ice_tcam_inf tcam[ICE_MAX_TCAM_PER_PROFILE];
+};
+
struct ice_vsig_entry {
struct list_head prop_lst;
struct ice_vsig_vsi *first_vsi;
@@ -329,6 +407,13 @@ struct ice_xlt2 {
u16 count;
};
+/* Profile ID Management */
+struct ice_prof_id_key {
+ __le16 flags;
+ u8 xlt1;
+ __le16 xlt2_cdid;
+} __packed;
+
/* Keys are made up of two values, each one-half the size of the key.
* For TCAM, the entire key is 80 bits wide (or 2, 40-bit wide values)
*/
@@ -371,4 +456,31 @@ struct ice_blk_info {
u8 is_list_init;
};
+enum ice_chg_type {
+ ICE_TCAM_NONE = 0,
+ ICE_PTG_ES_ADD,
+ ICE_TCAM_ADD,
+ ICE_VSIG_ADD,
+ ICE_VSIG_REM,
+ ICE_VSI_MOVE,
+};
+
+struct ice_chs_chg {
+ struct list_head list_entry;
+ enum ice_chg_type type;
+
+ u8 add_ptg;
+ u8 add_vsig;
+ u8 add_tcam_idx;
+ u8 add_prof;
+ u16 ptype;
+ u8 ptg;
+ u8 prof_id;
+ u16 vsi;
+ u16 vsig;
+ u16 orig_vsig;
+ u16 tcam_idx;
+};
+
+#define ICE_FLOW_PTYPE_MAX ICE_XLT1_CNT
#endif /* _ICE_FLEX_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
new file mode 100644
index 0000000..a05ceb5
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -0,0 +1,1275 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019, Intel Corporation. */
+
+#include "ice_common.h"
+#include "ice_flow.h"
+
+/* Describe properties of a protocol header field */
+struct ice_flow_field_info {
+ enum ice_flow_seg_hdr hdr;
+ s16 off; /* Offset from start of a protocol header, in bits */
+ u16 size; /* Size of fields in bits */
+};
+
+#define ICE_FLOW_FLD_INFO(_hdr, _offset_bytes, _size_bytes) { \
+ .hdr = _hdr, \
+ .off = (_offset_bytes) * BITS_PER_BYTE, \
+ .size = (_size_bytes) * BITS_PER_BYTE, \
+}
+
+/* Table containing properties of supported protocol header fields */
+static const
+struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = {
+ /* IPv4 / IPv6 */
+ /* ICE_FLOW_FIELD_IDX_IPV4_SA */
+ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV4, 12, sizeof(struct in_addr)),
+ /* ICE_FLOW_FIELD_IDX_IPV4_DA */
+ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV4, 16, sizeof(struct in_addr)),
+ /* ICE_FLOW_FIELD_IDX_IPV6_SA */
+ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 8, sizeof(struct in6_addr)),
+ /* ICE_FLOW_FIELD_IDX_IPV6_DA */
+ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24, sizeof(struct in6_addr)),
+ /* Transport */
+ /* ICE_FLOW_FIELD_IDX_TCP_SRC_PORT */
+ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 0, sizeof(__be16)),
+ /* ICE_FLOW_FIELD_IDX_TCP_DST_PORT */
+ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 2, sizeof(__be16)),
+ /* ICE_FLOW_FIELD_IDX_UDP_SRC_PORT */
+ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_UDP, 0, sizeof(__be16)),
+ /* ICE_FLOW_FIELD_IDX_UDP_DST_PORT */
+ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_UDP, 2, sizeof(__be16)),
+ /* ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT */
+ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_SCTP, 0, sizeof(__be16)),
+ /* ICE_FLOW_FIELD_IDX_SCTP_DST_PORT */
+ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_SCTP, 2, sizeof(__be16)),
+
+};
+
+/* Bitmaps indicating relevant packet types for a particular protocol header
+ *
+ * Packet types for packets with an Outer/First/Single IPv4 header
+ */
+static const u32 ice_ptypes_ipv4_ofos[] = {
+ 0x1DC00000, 0x04000800, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
+/* Packet types for packets with an Innermost/Last IPv4 header */
+static const u32 ice_ptypes_ipv4_il[] = {
+ 0xE0000000, 0xB807700E, 0x80000003, 0xE01DC03B,
+ 0x0000000E, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
+/* Packet types for packets with an Outer/First/Single IPv6 header */
+static const u32 ice_ptypes_ipv6_ofos[] = {
+ 0x00000000, 0x00000000, 0x77000000, 0x10002000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
+/* Packet types for packets with an Innermost/Last IPv6 header */
+static const u32 ice_ptypes_ipv6_il[] = {
+ 0x00000000, 0x03B80770, 0x000001DC, 0x0EE00000,
+ 0x00000770, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
+/* UDP Packet types for non-tunneled packets or tunneled
+ * packets with inner UDP.
+ */
+static const u32 ice_ptypes_udp_il[] = {
+ 0x81000000, 0x20204040, 0x04000010, 0x80810102,
+ 0x00000040, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
+/* Packet types for packets with an Innermost/Last TCP header */
+static const u32 ice_ptypes_tcp_il[] = {
+ 0x04000000, 0x80810102, 0x10000040, 0x02040408,
+ 0x00000102, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
+/* Packet types for packets with an Innermost/Last SCTP header */
+static const u32 ice_ptypes_sctp_il[] = {
+ 0x08000000, 0x01020204, 0x20000081, 0x04080810,
+ 0x00000204, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
+/* Manage parameters and info. used during the creation of a flow profile */
+struct ice_flow_prof_params {
+ enum ice_block blk;
+ u16 entry_length; /* # of bytes formatted entry will require */
+ u8 es_cnt;
+ struct ice_flow_prof *prof;
+
+ /* For ACL, the es[0] will have the data of ICE_RX_MDID_PKT_FLAGS_15_0
+ * This will give us the direction flags.
+ */
+ struct ice_fv_word es[ICE_MAX_FV_WORDS];
+ DECLARE_BITMAP(ptypes, ICE_FLOW_PTYPE_MAX);
+};
+
+#define ICE_FLOW_SEG_HDRS_L3_MASK \
+ (ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV6)
+#define ICE_FLOW_SEG_HDRS_L4_MASK \
+ (ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_SCTP)
+
+/**
+ * ice_flow_val_hdrs - validates packet segments for valid protocol headers
+ * @segs: array of one or more packet segments that describe the flow
+ * @segs_cnt: number of packet segments provided
+ */
+static enum ice_status
+ice_flow_val_hdrs(struct ice_flow_seg_info *segs, u8 segs_cnt)
+{
+ u8 i;
+
+ for (i = 0; i < segs_cnt; i++) {
+ /* Multiple L3 headers */
+ if (segs[i].hdrs & ICE_FLOW_SEG_HDRS_L3_MASK &&
+ !is_power_of_2(segs[i].hdrs & ICE_FLOW_SEG_HDRS_L3_MASK))
+ return ICE_ERR_PARAM;
+
+ /* Multiple L4 headers */
+ if (segs[i].hdrs & ICE_FLOW_SEG_HDRS_L4_MASK &&
+ !is_power_of_2(segs[i].hdrs & ICE_FLOW_SEG_HDRS_L4_MASK))
+ return ICE_ERR_PARAM;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_flow_proc_seg_hdrs - process protocol headers present in pkt segments
+ * @params: information about the flow to be processed
+ *
+ * This function identifies the packet types associated with the protocol
+ * headers being present in packet segments of the specified flow profile.
+ */
+static enum ice_status
+ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params)
+{
+ struct ice_flow_prof *prof;
+ u8 i;
+
+ memset(params->ptypes, 0xff, sizeof(params->ptypes));
+
+ prof = params->prof;
+
+ for (i = 0; i < params->prof->segs_cnt; i++) {
+ const unsigned long *src;
+ u32 hdrs;
+
+ hdrs = prof->segs[i].hdrs;
+
+ if (hdrs & ICE_FLOW_SEG_HDR_IPV4) {
+ src = !i ? (const unsigned long *)ice_ptypes_ipv4_ofos :
+ (const unsigned long *)ice_ptypes_ipv4_il;
+ bitmap_and(params->ptypes, params->ptypes, src,
+ ICE_FLOW_PTYPE_MAX);
+ } else if (hdrs & ICE_FLOW_SEG_HDR_IPV6) {
+ src = !i ? (const unsigned long *)ice_ptypes_ipv6_ofos :
+ (const unsigned long *)ice_ptypes_ipv6_il;
+ bitmap_and(params->ptypes, params->ptypes, src,
+ ICE_FLOW_PTYPE_MAX);
+ }
+
+ if (hdrs & ICE_FLOW_SEG_HDR_UDP) {
+ src = (const unsigned long *)ice_ptypes_udp_il;
+ bitmap_and(params->ptypes, params->ptypes, src,
+ ICE_FLOW_PTYPE_MAX);
+ } else if (hdrs & ICE_FLOW_SEG_HDR_TCP) {
+ bitmap_and(params->ptypes, params->ptypes,
+ (const unsigned long *)ice_ptypes_tcp_il,
+ ICE_FLOW_PTYPE_MAX);
+ } else if (hdrs & ICE_FLOW_SEG_HDR_SCTP) {
+ src = (const unsigned long *)ice_ptypes_sctp_il;
+ bitmap_and(params->ptypes, params->ptypes, src,
+ ICE_FLOW_PTYPE_MAX);
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ice_flow_xtract_fld - Create an extraction sequence entry for the given field
+ * @hw: pointer to the HW struct
+ * @params: information about the flow to be processed
+ * @seg: packet segment index of the field to be extracted
+ * @fld: ID of field to be extracted
+ *
+ * This function determines the protocol ID, offset, and size of the given
+ * field. It then allocates one or more extraction sequence entries for the
+ * given field, and fill the entries with protocol ID and offset information.
+ */
+static enum ice_status
+ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params,
+ u8 seg, enum ice_flow_field fld)
+{
+ enum ice_prot_id prot_id = ICE_PROT_ID_INVAL;
+ u8 fv_words = hw->blk[params->blk].es.fvw;
+ struct ice_flow_fld_info *flds;
+ u16 cnt, ese_bits, i;
+ u16 off;
+
+ flds = params->prof->segs[seg].fields;
+
+ switch (fld) {
+ case ICE_FLOW_FIELD_IDX_IPV4_SA:
+ case ICE_FLOW_FIELD_IDX_IPV4_DA:
+ prot_id = seg == 0 ? ICE_PROT_IPV4_OF_OR_S : ICE_PROT_IPV4_IL;
+ break;
+ case ICE_FLOW_FIELD_IDX_IPV6_SA:
+ case ICE_FLOW_FIELD_IDX_IPV6_DA:
+ prot_id = seg == 0 ? ICE_PROT_IPV6_OF_OR_S : ICE_PROT_IPV6_IL;
+ break;
+ case ICE_FLOW_FIELD_IDX_TCP_SRC_PORT:
+ case ICE_FLOW_FIELD_IDX_TCP_DST_PORT:
+ prot_id = ICE_PROT_TCP_IL;
+ break;
+ case ICE_FLOW_FIELD_IDX_UDP_SRC_PORT:
+ case ICE_FLOW_FIELD_IDX_UDP_DST_PORT:
+ prot_id = ICE_PROT_UDP_IL_OR_S;
+ break;
+ case ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT:
+ case ICE_FLOW_FIELD_IDX_SCTP_DST_PORT:
+ prot_id = ICE_PROT_SCTP_IL;
+ break;
+ default:
+ return ICE_ERR_NOT_IMPL;
+ }
+
+ /* Each extraction sequence entry is a word in size, and extracts a
+ * word-aligned offset from a protocol header.
+ */
+ ese_bits = ICE_FLOW_FV_EXTRACT_SZ * BITS_PER_BYTE;
+
+ flds[fld].xtrct.prot_id = prot_id;
+ flds[fld].xtrct.off = (ice_flds_info[fld].off / ese_bits) *
+ ICE_FLOW_FV_EXTRACT_SZ;
+ flds[fld].xtrct.disp = (u8)(ice_flds_info[fld].off % ese_bits);
+ flds[fld].xtrct.idx = params->es_cnt;
+
+ /* Adjust the next field-entry index after accommodating the number of
+ * entries this field consumes
+ */
+ cnt = DIV_ROUND_UP(flds[fld].xtrct.disp + ice_flds_info[fld].size,
+ ese_bits);
+
+ /* Fill in the extraction sequence entries needed for this field */
+ off = flds[fld].xtrct.off;
+ for (i = 0; i < cnt; i++) {
+ u8 idx;
+
+ /* Make sure the number of extraction sequence required
+ * does not exceed the block's capability
+ */
+ if (params->es_cnt >= fv_words)
+ return ICE_ERR_MAX_LIMIT;
+
+ /* some blocks require a reversed field vector layout */
+ if (hw->blk[params->blk].es.reverse)
+ idx = fv_words - params->es_cnt - 1;
+ else
+ idx = params->es_cnt;
+
+ params->es[idx].prot_id = prot_id;
+ params->es[idx].off = off;
+ params->es_cnt++;
+
+ off += ICE_FLOW_FV_EXTRACT_SZ;
+ }
+
+ return 0;
+}
+
+/**
+ * ice_flow_create_xtrct_seq - Create an extraction sequence for given segments
+ * @hw: pointer to the HW struct
+ * @params: information about the flow to be processed
+ *
+ * This function iterates through all matched fields in the given segments, and
+ * creates an extraction sequence for the fields.
+ */
+static enum ice_status
+ice_flow_create_xtrct_seq(struct ice_hw *hw,
+ struct ice_flow_prof_params *params)
+{
+ struct ice_flow_prof *prof = params->prof;
+ enum ice_status status = 0;
+ u8 i;
+
+ for (i = 0; i < prof->segs_cnt; i++) {
+ u8 j;
+
+ for_each_set_bit(j, (unsigned long *)&prof->segs[i].match,
+ ICE_FLOW_FIELD_IDX_MAX) {
+ status = ice_flow_xtract_fld(hw, params, i,
+ (enum ice_flow_field)j);
+ if (status)
+ return status;
+ }
+ }
+
+ return status;
+}
+
+/**
+ * ice_flow_proc_segs - process all packet segments associated with a profile
+ * @hw: pointer to the HW struct
+ * @params: information about the flow to be processed
+ */
+static enum ice_status
+ice_flow_proc_segs(struct ice_hw *hw, struct ice_flow_prof_params *params)
+{
+ enum ice_status status;
+
+ status = ice_flow_proc_seg_hdrs(params);
+ if (status)
+ return status;
+
+ status = ice_flow_create_xtrct_seq(hw, params);
+ if (status)
+ return status;
+
+ switch (params->blk) {
+ case ICE_BLK_RSS:
+ /* Only header information is provided for RSS configuration.
+ * No further processing is needed.
+ */
+ status = 0;
+ break;
+ default:
+ return ICE_ERR_NOT_IMPL;
+ }
+
+ return status;
+}
+
+#define ICE_FLOW_FIND_PROF_CHK_FLDS 0x00000001
+#define ICE_FLOW_FIND_PROF_CHK_VSI 0x00000002
+#define ICE_FLOW_FIND_PROF_NOT_CHK_DIR 0x00000004
+
+/**
+ * ice_flow_find_prof_conds - Find a profile matching headers and conditions
+ * @hw: pointer to the HW struct
+ * @blk: classification stage
+ * @dir: flow direction
+ * @segs: array of one or more packet segments that describe the flow
+ * @segs_cnt: number of packet segments provided
+ * @vsi_handle: software VSI handle to check VSI (ICE_FLOW_FIND_PROF_CHK_VSI)
+ * @conds: additional conditions to be checked (ICE_FLOW_FIND_PROF_CHK_*)
+ */
+static struct ice_flow_prof *
+ice_flow_find_prof_conds(struct ice_hw *hw, enum ice_block blk,
+ enum ice_flow_dir dir, struct ice_flow_seg_info *segs,
+ u8 segs_cnt, u16 vsi_handle, u32 conds)
+{
+ struct ice_flow_prof *p, *prof = NULL;
+
+ mutex_lock(&hw->fl_profs_locks[blk]);
+ list_for_each_entry(p, &hw->fl_profs[blk], l_entry)
+ if ((p->dir == dir || conds & ICE_FLOW_FIND_PROF_NOT_CHK_DIR) &&
+ segs_cnt && segs_cnt == p->segs_cnt) {
+ u8 i;
+
+ /* Check for profile-VSI association if specified */
+ if ((conds & ICE_FLOW_FIND_PROF_CHK_VSI) &&
+ ice_is_vsi_valid(hw, vsi_handle) &&
+ !test_bit(vsi_handle, p->vsis))
+ continue;
+
+ /* Protocol headers must be checked. Matched fields are
+ * checked if specified.
+ */
+ for (i = 0; i < segs_cnt; i++)
+ if (segs[i].hdrs != p->segs[i].hdrs ||
+ ((conds & ICE_FLOW_FIND_PROF_CHK_FLDS) &&
+ segs[i].match != p->segs[i].match))
+ break;
+
+ /* A match is found if all segments are matched */
+ if (i == segs_cnt) {
+ prof = p;
+ break;
+ }
+ }
+ mutex_unlock(&hw->fl_profs_locks[blk]);
+
+ return prof;
+}
+
+/**
+ * ice_flow_find_prof_id - Look up a profile with given profile ID
+ * @hw: pointer to the HW struct
+ * @blk: classification stage
+ * @prof_id: unique ID to identify this flow profile
+ */
+static struct ice_flow_prof *
+ice_flow_find_prof_id(struct ice_hw *hw, enum ice_block blk, u64 prof_id)
+{
+ struct ice_flow_prof *p;
+
+ list_for_each_entry(p, &hw->fl_profs[blk], l_entry)
+ if (p->id == prof_id)
+ return p;
+
+ return NULL;
+}
+
+/**
+ * ice_flow_add_prof_sync - Add a flow profile for packet segments and fields
+ * @hw: pointer to the HW struct
+ * @blk: classification stage
+ * @dir: flow direction
+ * @prof_id: unique ID to identify this flow profile
+ * @segs: array of one or more packet segments that describe the flow
+ * @segs_cnt: number of packet segments provided
+ * @prof: stores the returned flow profile added
+ *
+ * Assumption: the caller has acquired the lock to the profile list
+ */
+static enum ice_status
+ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk,
+ enum ice_flow_dir dir, u64 prof_id,
+ struct ice_flow_seg_info *segs, u8 segs_cnt,
+ struct ice_flow_prof **prof)
+{
+ struct ice_flow_prof_params params;
+ enum ice_status status;
+ u8 i;
+
+ if (!prof)
+ return ICE_ERR_BAD_PTR;
+
+ memset(¶ms, 0, sizeof(params));
+ params.prof = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*params.prof),
+ GFP_KERNEL);
+ if (!params.prof)
+ return ICE_ERR_NO_MEMORY;
+
+ /* initialize extraction sequence to all invalid (0xff) */
+ for (i = 0; i < ICE_MAX_FV_WORDS; i++) {
+ params.es[i].prot_id = ICE_PROT_INVALID;
+ params.es[i].off = ICE_FV_OFFSET_INVAL;
+ }
+
+ params.blk = blk;
+ params.prof->id = prof_id;
+ params.prof->dir = dir;
+ params.prof->segs_cnt = segs_cnt;
+
+ /* Make a copy of the segments that need to be persistent in the flow
+ * profile instance
+ */
+ for (i = 0; i < segs_cnt; i++)
+ memcpy(¶ms.prof->segs[i], &segs[i], sizeof(*segs));
+
+ status = ice_flow_proc_segs(hw, ¶ms);
+ if (status) {
+ ice_debug(hw, ICE_DBG_FLOW,
+ "Error processing a flow's packet segments\n");
+ goto out;
+ }
+
+ /* Add a HW profile for this flow profile */
+ status = ice_add_prof(hw, blk, prof_id, (u8 *)params.ptypes, params.es);
+ if (status) {
+ ice_debug(hw, ICE_DBG_FLOW, "Error adding a HW flow profile\n");
+ goto out;
+ }
+
+ INIT_LIST_HEAD(¶ms.prof->entries);
+ mutex_init(¶ms.prof->entries_lock);
+ *prof = params.prof;
+
+out:
+ if (status)
+ devm_kfree(ice_hw_to_dev(hw), params.prof);
+
+ return status;
+}
+
+/**
+ * ice_flow_rem_prof_sync - remove a flow profile
+ * @hw: pointer to the hardware structure
+ * @blk: classification stage
+ * @prof: pointer to flow profile to remove
+ *
+ * Assumption: the caller has acquired the lock to the profile list
+ */
+static enum ice_status
+ice_flow_rem_prof_sync(struct ice_hw *hw, enum ice_block blk,
+ struct ice_flow_prof *prof)
+{
+ enum ice_status status;
+
+ /* Remove all hardware profiles associated with this flow profile */
+ status = ice_rem_prof(hw, blk, prof->id);
+ if (!status) {
+ list_del(&prof->l_entry);
+ mutex_destroy(&prof->entries_lock);
+ devm_kfree(ice_hw_to_dev(hw), prof);
+ }
+
+ return status;
+}
+
+/**
+ * ice_flow_assoc_prof - associate a VSI with a flow profile
+ * @hw: pointer to the hardware structure
+ * @blk: classification stage
+ * @prof: pointer to flow profile
+ * @vsi_handle: software VSI handle
+ *
+ * Assumption: the caller has acquired the lock to the profile list
+ * and the software VSI handle has been validated
+ */
+static enum ice_status
+ice_flow_assoc_prof(struct ice_hw *hw, enum ice_block blk,
+ struct ice_flow_prof *prof, u16 vsi_handle)
+{
+ enum ice_status status = 0;
+
+ if (!test_bit(vsi_handle, prof->vsis)) {
+ status = ice_add_prof_id_flow(hw, blk,
+ ice_get_hw_vsi_num(hw,
+ vsi_handle),
+ prof->id);
+ if (!status)
+ set_bit(vsi_handle, prof->vsis);
+ else
+ ice_debug(hw, ICE_DBG_FLOW,
+ "HW profile add failed, %d\n",
+ status);
+ }
+
+ return status;
+}
+
+/**
+ * ice_flow_disassoc_prof - disassociate a VSI from a flow profile
+ * @hw: pointer to the hardware structure
+ * @blk: classification stage
+ * @prof: pointer to flow profile
+ * @vsi_handle: software VSI handle
+ *
+ * Assumption: the caller has acquired the lock to the profile list
+ * and the software VSI handle has been validated
+ */
+static enum ice_status
+ice_flow_disassoc_prof(struct ice_hw *hw, enum ice_block blk,
+ struct ice_flow_prof *prof, u16 vsi_handle)
+{
+ enum ice_status status = 0;
+
+ if (test_bit(vsi_handle, prof->vsis)) {
+ status = ice_rem_prof_id_flow(hw, blk,
+ ice_get_hw_vsi_num(hw,
+ vsi_handle),
+ prof->id);
+ if (!status)
+ clear_bit(vsi_handle, prof->vsis);
+ else
+ ice_debug(hw, ICE_DBG_FLOW,
+ "HW profile remove failed, %d\n",
+ status);
+ }
+
+ return status;
+}
+
+/**
+ * ice_flow_add_prof - Add a flow profile for packet segments and matched fields
+ * @hw: pointer to the HW struct
+ * @blk: classification stage
+ * @dir: flow direction
+ * @prof_id: unique ID to identify this flow profile
+ * @segs: array of one or more packet segments that describe the flow
+ * @segs_cnt: number of packet segments provided
+ * @prof: stores the returned flow profile added
+ */
+static enum ice_status
+ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir,
+ u64 prof_id, struct ice_flow_seg_info *segs, u8 segs_cnt,
+ struct ice_flow_prof **prof)
+{
+ enum ice_status status;
+
+ if (segs_cnt > ICE_FLOW_SEG_MAX)
+ return ICE_ERR_MAX_LIMIT;
+
+ if (!segs_cnt)
+ return ICE_ERR_PARAM;
+
+ if (!segs)
+ return ICE_ERR_BAD_PTR;
+
+ status = ice_flow_val_hdrs(segs, segs_cnt);
+ if (status)
+ return status;
+
+ mutex_lock(&hw->fl_profs_locks[blk]);
+
+ status = ice_flow_add_prof_sync(hw, blk, dir, prof_id, segs, segs_cnt,
+ prof);
+ if (!status)
+ list_add(&(*prof)->l_entry, &hw->fl_profs[blk]);
+
+ mutex_unlock(&hw->fl_profs_locks[blk]);
+
+ return status;
+}
+
+/**
+ * ice_flow_rem_prof - Remove a flow profile and all entries associated with it
+ * @hw: pointer to the HW struct
+ * @blk: the block for which the flow profile is to be removed
+ * @prof_id: unique ID of the flow profile to be removed
+ */
+static enum ice_status
+ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id)
+{
+ struct ice_flow_prof *prof;
+ enum ice_status status;
+
+ mutex_lock(&hw->fl_profs_locks[blk]);
+
+ prof = ice_flow_find_prof_id(hw, blk, prof_id);
+ if (!prof) {
+ status = ICE_ERR_DOES_NOT_EXIST;
+ goto out;
+ }
+
+ /* prof becomes invalid after the call */
+ status = ice_flow_rem_prof_sync(hw, blk, prof);
+
+out:
+ mutex_unlock(&hw->fl_profs_locks[blk]);
+
+ return status;
+}
+
+/**
+ * ice_flow_set_fld_ext - specifies locations of field from entry's input buffer
+ * @seg: packet segment the field being set belongs to
+ * @fld: field to be set
+ * @type: type of the field
+ * @val_loc: if not ICE_FLOW_FLD_OFF_INVAL, location of the value to match from
+ * entry's input buffer
+ * @mask_loc: if not ICE_FLOW_FLD_OFF_INVAL, location of mask value from entry's
+ * input buffer
+ * @last_loc: if not ICE_FLOW_FLD_OFF_INVAL, location of last/upper value from
+ * entry's input buffer
+ *
+ * This helper function stores information of a field being matched, including
+ * the type of the field and the locations of the value to match, the mask, and
+ * and the upper-bound value in the start of the input buffer for a flow entry.
+ * This function should only be used for fixed-size data structures.
+ *
+ * This function also opportunistically determines the protocol headers to be
+ * present based on the fields being set. Some fields cannot be used alone to
+ * determine the protocol headers present. Sometimes, fields for particular
+ * protocol headers are not matched. In those cases, the protocol headers
+ * must be explicitly set.
+ */
+static void
+ice_flow_set_fld_ext(struct ice_flow_seg_info *seg, enum ice_flow_field fld,
+ enum ice_flow_fld_match_type type, u16 val_loc,
+ u16 mask_loc, u16 last_loc)
+{
+ u64 bit = BIT_ULL(fld);
+
+ seg->match |= bit;
+ if (type == ICE_FLOW_FLD_TYPE_RANGE)
+ seg->range |= bit;
+
+ seg->fields[fld].type = type;
+ seg->fields[fld].src.val = val_loc;
+ seg->fields[fld].src.mask = mask_loc;
+ seg->fields[fld].src.last = last_loc;
+
+ ICE_FLOW_SET_HDRS(seg, ice_flds_info[fld].hdr);
+}
+
+/**
+ * ice_flow_set_fld - specifies locations of field from entry's input buffer
+ * @seg: packet segment the field being set belongs to
+ * @fld: field to be set
+ * @val_loc: if not ICE_FLOW_FLD_OFF_INVAL, location of the value to match from
+ * entry's input buffer
+ * @mask_loc: if not ICE_FLOW_FLD_OFF_INVAL, location of mask value from entry's
+ * input buffer
+ * @last_loc: if not ICE_FLOW_FLD_OFF_INVAL, location of last/upper value from
+ * entry's input buffer
+ * @range: indicate if field being matched is to be in a range
+ *
+ * This function specifies the locations, in the form of byte offsets from the
+ * start of the input buffer for a flow entry, from where the value to match,
+ * the mask value, and upper value can be extracted. These locations are then
+ * stored in the flow profile. When adding a flow entry associated with the
+ * flow profile, these locations will be used to quickly extract the values and
+ * create the content of a match entry. This function should only be used for
+ * fixed-size data structures.
+ */
+static void
+ice_flow_set_fld(struct ice_flow_seg_info *seg, enum ice_flow_field fld,
+ u16 val_loc, u16 mask_loc, u16 last_loc, bool range)
+{
+ enum ice_flow_fld_match_type t = range ?
+ ICE_FLOW_FLD_TYPE_RANGE : ICE_FLOW_FLD_TYPE_REG;
+
+ ice_flow_set_fld_ext(seg, fld, t, val_loc, mask_loc, last_loc);
+}
+
+#define ICE_FLOW_RSS_SEG_HDR_L3_MASKS \
+ (ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV6)
+
+#define ICE_FLOW_RSS_SEG_HDR_L4_MASKS \
+ (ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_SCTP)
+
+#define ICE_FLOW_RSS_SEG_HDR_VAL_MASKS \
+ (ICE_FLOW_RSS_SEG_HDR_L3_MASKS | \
+ ICE_FLOW_RSS_SEG_HDR_L4_MASKS)
+
+/**
+ * ice_flow_set_rss_seg_info - setup packet segments for RSS
+ * @segs: pointer to the flow field segment(s)
+ * @hash_fields: fields to be hashed on for the segment(s)
+ * @flow_hdr: protocol header fields within a packet segment
+ *
+ * Helper function to extract fields from hash bitmap and use flow
+ * header value to set flow field segment for further use in flow
+ * profile entry or removal.
+ */
+static enum ice_status
+ice_flow_set_rss_seg_info(struct ice_flow_seg_info *segs, u64 hash_fields,
+ u32 flow_hdr)
+{
+ u64 val;
+ u8 i;
+
+ for_each_set_bit(i, (unsigned long *)&hash_fields,
+ ICE_FLOW_FIELD_IDX_MAX)
+ ice_flow_set_fld(segs, (enum ice_flow_field)i,
+ ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+ ICE_FLOW_FLD_OFF_INVAL, false);
+
+ ICE_FLOW_SET_HDRS(segs, flow_hdr);
+
+ if (segs->hdrs & ~ICE_FLOW_RSS_SEG_HDR_VAL_MASKS)
+ return ICE_ERR_PARAM;
+
+ val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L3_MASKS);
+ if (val && !is_power_of_2(val))
+ return ICE_ERR_CFG;
+
+ val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L4_MASKS);
+ if (val && !is_power_of_2(val))
+ return ICE_ERR_CFG;
+
+ return 0;
+}
+
+/**
+ * ice_rem_vsi_rss_list - remove VSI from RSS list
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: software VSI handle
+ *
+ * Remove the VSI from all RSS configurations in the list.
+ */
+void ice_rem_vsi_rss_list(struct ice_hw *hw, u16 vsi_handle)
+{
+ struct ice_rss_cfg *r, *tmp;
+
+ if (list_empty(&hw->rss_list_head))
+ return;
+
+ mutex_lock(&hw->rss_locks);
+ list_for_each_entry_safe(r, tmp, &hw->rss_list_head, l_entry)
+ if (test_and_clear_bit(vsi_handle, r->vsis))
+ if (bitmap_empty(r->vsis, ICE_MAX_VSI)) {
+ list_del(&r->l_entry);
+ devm_kfree(ice_hw_to_dev(hw), r);
+ }
+ mutex_unlock(&hw->rss_locks);
+}
+
+/**
+ * ice_rem_vsi_rss_cfg - remove RSS configurations associated with VSI
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: software VSI handle
+ *
+ * This function will iterate through all flow profiles and disassociate
+ * the VSI from that profile. If the flow profile has no VSIs it will
+ * be removed.
+ */
+enum ice_status ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle)
+{
+ const enum ice_block blk = ICE_BLK_RSS;
+ struct ice_flow_prof *p, *t;
+ enum ice_status status = 0;
+
+ if (!ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+
+ if (list_empty(&hw->fl_profs[blk]))
+ return 0;
+
+ mutex_lock(&hw->fl_profs_locks[blk]);
+ list_for_each_entry_safe(p, t, &hw->fl_profs[blk], l_entry)
+ if (test_bit(vsi_handle, p->vsis)) {
+ status = ice_flow_disassoc_prof(hw, blk, p, vsi_handle);
+ if (status)
+ break;
+
+ if (bitmap_empty(p->vsis, ICE_MAX_VSI)) {
+ status = ice_flow_rem_prof_sync(hw, blk, p);
+ if (status)
+ break;
+ }
+ }
+ mutex_unlock(&hw->fl_profs_locks[blk]);
+
+ return status;
+}
+
+/**
+ * ice_rem_rss_list - remove RSS configuration from list
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: software VSI handle
+ * @prof: pointer to flow profile
+ *
+ * Assumption: lock has already been acquired for RSS list
+ */
+static void
+ice_rem_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
+{
+ struct ice_rss_cfg *r, *tmp;
+
+ /* Search for RSS hash fields associated to the VSI that match the
+ * hash configurations associated to the flow profile. If found
+ * remove from the RSS entry list of the VSI context and delete entry.
+ */
+ list_for_each_entry_safe(r, tmp, &hw->rss_list_head, l_entry)
+ if (r->hashed_flds == prof->segs[prof->segs_cnt - 1].match &&
+ r->packet_hdr == prof->segs[prof->segs_cnt - 1].hdrs) {
+ clear_bit(vsi_handle, r->vsis);
+ if (bitmap_empty(r->vsis, ICE_MAX_VSI)) {
+ list_del(&r->l_entry);
+ devm_kfree(ice_hw_to_dev(hw), r);
+ }
+ return;
+ }
+}
+
+/**
+ * ice_add_rss_list - add RSS configuration to list
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: software VSI handle
+ * @prof: pointer to flow profile
+ *
+ * Assumption: lock has already been acquired for RSS list
+ */
+static enum ice_status
+ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
+{
+ struct ice_rss_cfg *r, *rss_cfg;
+
+ list_for_each_entry(r, &hw->rss_list_head, l_entry)
+ if (r->hashed_flds == prof->segs[prof->segs_cnt - 1].match &&
+ r->packet_hdr == prof->segs[prof->segs_cnt - 1].hdrs) {
+ set_bit(vsi_handle, r->vsis);
+ return 0;
+ }
+
+ rss_cfg = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*rss_cfg),
+ GFP_KERNEL);
+ if (!rss_cfg)
+ return ICE_ERR_NO_MEMORY;
+
+ rss_cfg->hashed_flds = prof->segs[prof->segs_cnt - 1].match;
+ rss_cfg->packet_hdr = prof->segs[prof->segs_cnt - 1].hdrs;
+ set_bit(vsi_handle, rss_cfg->vsis);
+
+ list_add_tail(&rss_cfg->l_entry, &hw->rss_list_head);
+
+ return 0;
+}
+
+#define ICE_FLOW_PROF_HASH_S 0
+#define ICE_FLOW_PROF_HASH_M (0xFFFFFFFFULL << ICE_FLOW_PROF_HASH_S)
+#define ICE_FLOW_PROF_HDR_S 32
+#define ICE_FLOW_PROF_HDR_M (0x3FFFFFFFULL << ICE_FLOW_PROF_HDR_S)
+#define ICE_FLOW_PROF_ENCAP_S 63
+#define ICE_FLOW_PROF_ENCAP_M (BIT_ULL(ICE_FLOW_PROF_ENCAP_S))
+
+#define ICE_RSS_OUTER_HEADERS 1
+
+/* Flow profile ID format:
+ * [0:31] - Packet match fields
+ * [32:62] - Protocol header
+ * [63] - Encapsulation flag, 0 if non-tunneled, 1 if tunneled
+ */
+#define ICE_FLOW_GEN_PROFID(hash, hdr, segs_cnt) \
+ (u64)(((u64)(hash) & ICE_FLOW_PROF_HASH_M) | \
+ (((u64)(hdr) << ICE_FLOW_PROF_HDR_S) & ICE_FLOW_PROF_HDR_M) | \
+ ((u8)((segs_cnt) - 1) ? ICE_FLOW_PROF_ENCAP_M : 0))
+
+/**
+ * ice_add_rss_cfg_sync - add an RSS configuration
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: software VSI handle
+ * @hashed_flds: hash bit fields (ICE_FLOW_HASH_*) to configure
+ * @addl_hdrs: protocol header fields
+ * @segs_cnt: packet segment count
+ *
+ * Assumption: lock has already been acquired for RSS list
+ */
+static enum ice_status
+ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
+ u32 addl_hdrs, u8 segs_cnt)
+{
+ const enum ice_block blk = ICE_BLK_RSS;
+ struct ice_flow_prof *prof = NULL;
+ struct ice_flow_seg_info *segs;
+ enum ice_status status;
+
+ if (!segs_cnt || segs_cnt > ICE_FLOW_SEG_MAX)
+ return ICE_ERR_PARAM;
+
+ segs = kcalloc(segs_cnt, sizeof(*segs), GFP_KERNEL);
+ if (!segs)
+ return ICE_ERR_NO_MEMORY;
+
+ /* Construct the packet segment info from the hashed fields */
+ status = ice_flow_set_rss_seg_info(&segs[segs_cnt - 1], hashed_flds,
+ addl_hdrs);
+ if (status)
+ goto exit;
+
+ /* Search for a flow profile that has matching headers, hash fields
+ * and has the input VSI associated to it. If found, no further
+ * operations required and exit.
+ */
+ prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt,
+ vsi_handle,
+ ICE_FLOW_FIND_PROF_CHK_FLDS |
+ ICE_FLOW_FIND_PROF_CHK_VSI);
+ if (prof)
+ goto exit;
+
+ /* Check if a flow profile exists with the same protocol headers and
+ * associated with the input VSI. If so disassociate the VSI from
+ * this profile. The VSI will be added to a new profile created with
+ * the protocol header and new hash field configuration.
+ */
+ prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt,
+ vsi_handle, ICE_FLOW_FIND_PROF_CHK_VSI);
+ if (prof) {
+ status = ice_flow_disassoc_prof(hw, blk, prof, vsi_handle);
+ if (!status)
+ ice_rem_rss_list(hw, vsi_handle, prof);
+ else
+ goto exit;
+
+ /* Remove profile if it has no VSIs associated */
+ if (bitmap_empty(prof->vsis, ICE_MAX_VSI)) {
+ status = ice_flow_rem_prof(hw, blk, prof->id);
+ if (status)
+ goto exit;
+ }
+ }
+
+ /* Search for a profile that has same match fields only. If this
+ * exists then associate the VSI to this profile.
+ */
+ prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt,
+ vsi_handle,
+ ICE_FLOW_FIND_PROF_CHK_FLDS);
+ if (prof) {
+ status = ice_flow_assoc_prof(hw, blk, prof, vsi_handle);
+ if (!status)
+ status = ice_add_rss_list(hw, vsi_handle, prof);
+ goto exit;
+ }
+
+ /* Create a new flow profile with generated profile and packet
+ * segment information.
+ */
+ status = ice_flow_add_prof(hw, blk, ICE_FLOW_RX,
+ ICE_FLOW_GEN_PROFID(hashed_flds,
+ segs[segs_cnt - 1].hdrs,
+ segs_cnt),
+ segs, segs_cnt, &prof);
+ if (status)
+ goto exit;
+
+ status = ice_flow_assoc_prof(hw, blk, prof, vsi_handle);
+ /* If association to a new flow profile failed then this profile can
+ * be removed.
+ */
+ if (status) {
+ ice_flow_rem_prof(hw, blk, prof->id);
+ goto exit;
+ }
+
+ status = ice_add_rss_list(hw, vsi_handle, prof);
+
+exit:
+ kfree(segs);
+ return status;
+}
+
+/**
+ * ice_add_rss_cfg - add an RSS configuration with specified hashed fields
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: software VSI handle
+ * @hashed_flds: hash bit fields (ICE_FLOW_HASH_*) to configure
+ * @addl_hdrs: protocol header fields
+ *
+ * This function will generate a flow profile based on fields associated with
+ * the input fields to hash on, the flow type and use the VSI number to add
+ * a flow entry to the profile.
+ */
+enum ice_status
+ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
+ u32 addl_hdrs)
+{
+ enum ice_status status;
+
+ if (hashed_flds == ICE_HASH_INVALID ||
+ !ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+
+ mutex_lock(&hw->rss_locks);
+ status = ice_add_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs,
+ ICE_RSS_OUTER_HEADERS);
+ mutex_unlock(&hw->rss_locks);
+
+ return status;
+}
+
+/* Mapping of AVF hash bit fields to an L3-L4 hash combination.
+ * As the ice_flow_avf_hdr_field represent individual bit shifts in a hash,
+ * convert its values to their appropriate flow L3, L4 values.
+ */
+#define ICE_FLOW_AVF_RSS_IPV4_MASKS \
+ (BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_OTHER) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV4))
+#define ICE_FLOW_AVF_RSS_TCP_IPV4_MASKS \
+ (BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP_SYN_NO_ACK) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP))
+#define ICE_FLOW_AVF_RSS_UDP_IPV4_MASKS \
+ (BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV4_UDP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV4_UDP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_UDP))
+#define ICE_FLOW_AVF_RSS_ALL_IPV4_MASKS \
+ (ICE_FLOW_AVF_RSS_TCP_IPV4_MASKS | ICE_FLOW_AVF_RSS_UDP_IPV4_MASKS | \
+ ICE_FLOW_AVF_RSS_IPV4_MASKS | BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP))
+
+#define ICE_FLOW_AVF_RSS_IPV6_MASKS \
+ (BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_OTHER) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV6))
+#define ICE_FLOW_AVF_RSS_UDP_IPV6_MASKS \
+ (BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_UDP))
+#define ICE_FLOW_AVF_RSS_TCP_IPV6_MASKS \
+ (BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP_SYN_NO_ACK) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP))
+#define ICE_FLOW_AVF_RSS_ALL_IPV6_MASKS \
+ (ICE_FLOW_AVF_RSS_TCP_IPV6_MASKS | ICE_FLOW_AVF_RSS_UDP_IPV6_MASKS | \
+ ICE_FLOW_AVF_RSS_IPV6_MASKS | BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP))
+
+/**
+ * ice_add_avf_rss_cfg - add an RSS configuration for AVF driver
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: software VSI handle
+ * @avf_hash: hash bit fields (ICE_AVF_FLOW_FIELD_*) to configure
+ *
+ * This function will take the hash bitmap provided by the AVF driver via a
+ * message, convert it to ICE-compatible values, and configure RSS flow
+ * profiles.
+ */
+enum ice_status
+ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash)
+{
+ enum ice_status status = 0;
+ u64 hash_flds;
+
+ if (avf_hash == ICE_AVF_FLOW_FIELD_INVALID ||
+ !ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+
+ /* Make sure no unsupported bits are specified */
+ if (avf_hash & ~(ICE_FLOW_AVF_RSS_ALL_IPV4_MASKS |
+ ICE_FLOW_AVF_RSS_ALL_IPV6_MASKS))
+ return ICE_ERR_CFG;
+
+ hash_flds = avf_hash;
+
+ /* Always create an L3 RSS configuration for any L4 RSS configuration */
+ if (hash_flds & ICE_FLOW_AVF_RSS_ALL_IPV4_MASKS)
+ hash_flds |= ICE_FLOW_AVF_RSS_IPV4_MASKS;
+
+ if (hash_flds & ICE_FLOW_AVF_RSS_ALL_IPV6_MASKS)
+ hash_flds |= ICE_FLOW_AVF_RSS_IPV6_MASKS;
+
+ /* Create the corresponding RSS configuration for each valid hash bit */
+ while (hash_flds) {
+ u64 rss_hash = ICE_HASH_INVALID;
+
+ if (hash_flds & ICE_FLOW_AVF_RSS_ALL_IPV4_MASKS) {
+ if (hash_flds & ICE_FLOW_AVF_RSS_IPV4_MASKS) {
+ rss_hash = ICE_FLOW_HASH_IPV4;
+ hash_flds &= ~ICE_FLOW_AVF_RSS_IPV4_MASKS;
+ } else if (hash_flds &
+ ICE_FLOW_AVF_RSS_TCP_IPV4_MASKS) {
+ rss_hash = ICE_FLOW_HASH_IPV4 |
+ ICE_FLOW_HASH_TCP_PORT;
+ hash_flds &= ~ICE_FLOW_AVF_RSS_TCP_IPV4_MASKS;
+ } else if (hash_flds &
+ ICE_FLOW_AVF_RSS_UDP_IPV4_MASKS) {
+ rss_hash = ICE_FLOW_HASH_IPV4 |
+ ICE_FLOW_HASH_UDP_PORT;
+ hash_flds &= ~ICE_FLOW_AVF_RSS_UDP_IPV4_MASKS;
+ } else if (hash_flds &
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP)) {
+ rss_hash = ICE_FLOW_HASH_IPV4 |
+ ICE_FLOW_HASH_SCTP_PORT;
+ hash_flds &=
+ ~BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP);
+ }
+ } else if (hash_flds & ICE_FLOW_AVF_RSS_ALL_IPV6_MASKS) {
+ if (hash_flds & ICE_FLOW_AVF_RSS_IPV6_MASKS) {
+ rss_hash = ICE_FLOW_HASH_IPV6;
+ hash_flds &= ~ICE_FLOW_AVF_RSS_IPV6_MASKS;
+ } else if (hash_flds &
+ ICE_FLOW_AVF_RSS_TCP_IPV6_MASKS) {
+ rss_hash = ICE_FLOW_HASH_IPV6 |
+ ICE_FLOW_HASH_TCP_PORT;
+ hash_flds &= ~ICE_FLOW_AVF_RSS_TCP_IPV6_MASKS;
+ } else if (hash_flds &
+ ICE_FLOW_AVF_RSS_UDP_IPV6_MASKS) {
+ rss_hash = ICE_FLOW_HASH_IPV6 |
+ ICE_FLOW_HASH_UDP_PORT;
+ hash_flds &= ~ICE_FLOW_AVF_RSS_UDP_IPV6_MASKS;
+ } else if (hash_flds &
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP)) {
+ rss_hash = ICE_FLOW_HASH_IPV6 |
+ ICE_FLOW_HASH_SCTP_PORT;
+ hash_flds &=
+ ~BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP);
+ }
+ }
+
+ if (rss_hash == ICE_HASH_INVALID)
+ return ICE_ERR_OUT_OF_RANGE;
+
+ status = ice_add_rss_cfg(hw, vsi_handle, rss_hash,
+ ICE_FLOW_SEG_HDR_NONE);
+ if (status)
+ break;
+ }
+
+ return status;
+}
+
+/**
+ * ice_replay_rss_cfg - replay RSS configurations associated with VSI
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: software VSI handle
+ */
+enum ice_status ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle)
+{
+ enum ice_status status = 0;
+ struct ice_rss_cfg *r;
+
+ if (!ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_ERR_PARAM;
+
+ mutex_lock(&hw->rss_locks);
+ list_for_each_entry(r, &hw->rss_list_head, l_entry) {
+ if (test_bit(vsi_handle, r->vsis)) {
+ status = ice_add_rss_cfg_sync(hw, vsi_handle,
+ r->hashed_flds,
+ r->packet_hdr,
+ ICE_RSS_OUTER_HEADERS);
+ if (status)
+ break;
+ }
+ }
+ mutex_unlock(&hw->rss_locks);
+
+ return status;
+}
+
+/**
+ * ice_get_rss_cfg - returns hashed fields for the given header types
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: software VSI handle
+ * @hdrs: protocol header type
+ *
+ * This function will return the match fields of the first instance of flow
+ * profile having the given header types and containing input VSI
+ */
+u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs)
+{
+ struct ice_rss_cfg *r, *rss_cfg = NULL;
+
+ /* verify if the protocol header is non zero and VSI is valid */
+ if (hdrs == ICE_FLOW_SEG_HDR_NONE || !ice_is_vsi_valid(hw, vsi_handle))
+ return ICE_HASH_INVALID;
+
+ mutex_lock(&hw->rss_locks);
+ list_for_each_entry(r, &hw->rss_list_head, l_entry)
+ if (test_bit(vsi_handle, r->vsis) &&
+ r->packet_hdr == hdrs) {
+ rss_cfg = r;
+ break;
+ }
+ mutex_unlock(&hw->rss_locks);
+
+ return rss_cfg ? rss_cfg->hashed_flds : ICE_HASH_INVALID;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
new file mode 100644
index 0000000..5558627
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -0,0 +1,207 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Intel Corporation. */
+
+#ifndef _ICE_FLOW_H_
+#define _ICE_FLOW_H_
+
+#define ICE_FLOW_ENTRY_HANDLE_INVAL 0
+#define ICE_FLOW_FLD_OFF_INVAL 0xffff
+
+/* Generate flow hash field from flow field type(s) */
+#define ICE_FLOW_HASH_IPV4 \
+ (BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | \
+ BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA))
+#define ICE_FLOW_HASH_IPV6 \
+ (BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) | \
+ BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA))
+#define ICE_FLOW_HASH_TCP_PORT \
+ (BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT) | \
+ BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT))
+#define ICE_FLOW_HASH_UDP_PORT \
+ (BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT) | \
+ BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT))
+#define ICE_FLOW_HASH_SCTP_PORT \
+ (BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT) | \
+ BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT))
+
+#define ICE_HASH_INVALID 0
+#define ICE_HASH_TCP_IPV4 (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_TCP_PORT)
+#define ICE_HASH_TCP_IPV6 (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_TCP_PORT)
+#define ICE_HASH_UDP_IPV4 (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_UDP_PORT)
+#define ICE_HASH_UDP_IPV6 (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_UDP_PORT)
+
+/* Protocol header fields within a packet segment. A segment consists of one or
+ * more protocol headers that make up a logical group of protocol headers. Each
+ * logical group of protocol headers encapsulates or is encapsulated using/by
+ * tunneling or encapsulation protocols for network virtualization such as GRE,
+ * VxLAN, etc.
+ */
+enum ice_flow_seg_hdr {
+ ICE_FLOW_SEG_HDR_NONE = 0x00000000,
+ ICE_FLOW_SEG_HDR_IPV4 = 0x00000004,
+ ICE_FLOW_SEG_HDR_IPV6 = 0x00000008,
+ ICE_FLOW_SEG_HDR_TCP = 0x00000040,
+ ICE_FLOW_SEG_HDR_UDP = 0x00000080,
+ ICE_FLOW_SEG_HDR_SCTP = 0x00000100,
+};
+
+enum ice_flow_field {
+ /* L3 */
+ ICE_FLOW_FIELD_IDX_IPV4_SA,
+ ICE_FLOW_FIELD_IDX_IPV4_DA,
+ ICE_FLOW_FIELD_IDX_IPV6_SA,
+ ICE_FLOW_FIELD_IDX_IPV6_DA,
+ /* L4 */
+ ICE_FLOW_FIELD_IDX_TCP_SRC_PORT,
+ ICE_FLOW_FIELD_IDX_TCP_DST_PORT,
+ ICE_FLOW_FIELD_IDX_UDP_SRC_PORT,
+ ICE_FLOW_FIELD_IDX_UDP_DST_PORT,
+ ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT,
+ ICE_FLOW_FIELD_IDX_SCTP_DST_PORT,
+ /* The total number of enums must not exceed 64 */
+ ICE_FLOW_FIELD_IDX_MAX
+};
+
+/* Flow headers and fields for AVF support */
+enum ice_flow_avf_hdr_field {
+ /* Values 0 - 28 are reserved for future use */
+ ICE_AVF_FLOW_FIELD_INVALID = 0,
+ ICE_AVF_FLOW_FIELD_UNICAST_IPV4_UDP = 29,
+ ICE_AVF_FLOW_FIELD_MULTICAST_IPV4_UDP,
+ ICE_AVF_FLOW_FIELD_IPV4_UDP,
+ ICE_AVF_FLOW_FIELD_IPV4_TCP_SYN_NO_ACK,
+ ICE_AVF_FLOW_FIELD_IPV4_TCP,
+ ICE_AVF_FLOW_FIELD_IPV4_SCTP,
+ ICE_AVF_FLOW_FIELD_IPV4_OTHER,
+ ICE_AVF_FLOW_FIELD_FRAG_IPV4,
+ /* Values 37-38 are reserved */
+ ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP = 39,
+ ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP,
+ ICE_AVF_FLOW_FIELD_IPV6_UDP,
+ ICE_AVF_FLOW_FIELD_IPV6_TCP_SYN_NO_ACK,
+ ICE_AVF_FLOW_FIELD_IPV6_TCP,
+ ICE_AVF_FLOW_FIELD_IPV6_SCTP,
+ ICE_AVF_FLOW_FIELD_IPV6_OTHER,
+ ICE_AVF_FLOW_FIELD_FRAG_IPV6,
+ ICE_AVF_FLOW_FIELD_RSVD47,
+ ICE_AVF_FLOW_FIELD_FCOE_OX,
+ ICE_AVF_FLOW_FIELD_FCOE_RX,
+ ICE_AVF_FLOW_FIELD_FCOE_OTHER,
+ /* Values 51-62 are reserved */
+ ICE_AVF_FLOW_FIELD_L2_PAYLOAD = 63,
+ ICE_AVF_FLOW_FIELD_MAX
+};
+
+/* Supported RSS offloads This macro is defined to support
+ * VIRTCHNL_OP_GET_RSS_HENA_CAPS ops. PF driver sends the RSS hardware
+ * capabilities to the caller of this ops.
+ */
+#define ICE_DEFAULT_RSS_HENA ( \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_UDP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_OTHER) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV4) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_UDP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_OTHER) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV6) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP_SYN_NO_ACK) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV4_UDP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV4_UDP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP_SYN_NO_ACK) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP) | \
+ BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP))
+
+enum ice_flow_dir {
+ ICE_FLOW_RX = 0x02,
+};
+
+enum ice_flow_priority {
+ ICE_FLOW_PRIO_LOW,
+ ICE_FLOW_PRIO_NORMAL,
+ ICE_FLOW_PRIO_HIGH
+};
+
+#define ICE_FLOW_SEG_MAX 2
+#define ICE_FLOW_FV_EXTRACT_SZ 2
+
+#define ICE_FLOW_SET_HDRS(seg, val) ((seg)->hdrs |= (u32)(val))
+
+struct ice_flow_seg_xtrct {
+ u8 prot_id; /* Protocol ID of extracted header field */
+ u16 off; /* Starting offset of the field in header in bytes */
+ u8 idx; /* Index of FV entry used */
+ u8 disp; /* Displacement of field in bits fr. FV entry's start */
+};
+
+enum ice_flow_fld_match_type {
+ ICE_FLOW_FLD_TYPE_REG, /* Value, mask */
+ ICE_FLOW_FLD_TYPE_RANGE, /* Value, mask, last (upper bound) */
+ ICE_FLOW_FLD_TYPE_PREFIX, /* IP address, prefix, size of prefix */
+ ICE_FLOW_FLD_TYPE_SIZE, /* Value, mask, size of match */
+};
+
+struct ice_flow_fld_loc {
+ /* Describe offsets of field information relative to the beginning of
+ * input buffer provided when adding flow entries.
+ */
+ u16 val; /* Offset where the value is located */
+ u16 mask; /* Offset where the mask/prefix value is located */
+ u16 last; /* Length or offset where the upper value is located */
+};
+
+struct ice_flow_fld_info {
+ enum ice_flow_fld_match_type type;
+ /* Location where to retrieve data from an input buffer */
+ struct ice_flow_fld_loc src;
+ /* Location where to put the data into the final entry buffer */
+ struct ice_flow_fld_loc entry;
+ struct ice_flow_seg_xtrct xtrct;
+};
+
+struct ice_flow_seg_info {
+ u32 hdrs; /* Bitmask indicating protocol headers present */
+ u64 match; /* Bitmask indicating header fields to be matched */
+ u64 range; /* Bitmask indicating header fields matched as ranges */
+
+ struct ice_flow_fld_info fields[ICE_FLOW_FIELD_IDX_MAX];
+};
+
+struct ice_flow_prof {
+ struct list_head l_entry;
+
+ u64 id;
+ enum ice_flow_dir dir;
+ u8 segs_cnt;
+
+ /* Keep track of flow entries associated with this flow profile */
+ struct mutex entries_lock;
+ struct list_head entries;
+
+ struct ice_flow_seg_info segs[ICE_FLOW_SEG_MAX];
+
+ /* software VSI handles referenced by this flow profile */
+ DECLARE_BITMAP(vsis, ICE_MAX_VSI);
+};
+
+struct ice_rss_cfg {
+ struct list_head l_entry;
+ /* bitmap of VSIs added to the RSS entry */
+ DECLARE_BITMAP(vsis, ICE_MAX_VSI);
+ u64 hashed_flds;
+ u32 packet_hdr;
+};
+
+enum ice_status ice_flow_rem_entry(struct ice_hw *hw, u64 entry_h);
+void ice_rem_vsi_rss_list(struct ice_hw *hw, u16 vsi_handle);
+enum ice_status ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle);
+enum ice_status
+ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds);
+enum ice_status ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle);
+enum ice_status
+ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
+ u32 addl_hdrs);
+u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs);
+#endif /* _ICE_FLOW_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index e8f3235..f2cabab 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -60,15 +60,6 @@
#define PRTDCB_GENS_DCBX_STATUS_M ICE_M(0x7, 0)
#define GL_PREEXT_L2_PMASK0(_i) (0x0020F0FC + ((_i) * 4))
#define GL_PREEXT_L2_PMASK1(_i) (0x0020F108 + ((_i) * 4))
-#define GLFLXP_RXDID_FLAGS(_i, _j) (0x0045D000 + ((_i) * 4 + (_j) * 256))
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S 0
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, 0)
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S 8
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M ICE_M(0x3F, 8)
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S 16
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M ICE_M(0x3F, 16)
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S 24
-#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M ICE_M(0x3F, 24)
#define GLFLXP_RXDID_FLX_WRD_0(_i) (0x0045c800 + ((_i) * 4))
#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S 0
#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, 0)
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 0997d35..878e125 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -199,6 +199,14 @@ enum ice_rxdid {
/* Receive Flex Descriptor Rx opcode values */
#define ICE_RX_OPC_MDID 0x01
+/* Receive Descriptor MDID values that access packet flags */
+enum ice_flex_mdid_pkt_flags {
+ ICE_RX_MDID_PKT_FLAGS_15_0 = 20,
+ ICE_RX_MDID_PKT_FLAGS_31_16,
+ ICE_RX_MDID_PKT_FLAGS_47_32,
+ ICE_RX_MDID_PKT_FLAGS_63_48,
+};
+
/* Receive Descriptor MDID values */
enum ice_flex_rx_mdid {
ICE_RX_MDID_FLOW_ID_LOWER = 5,
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index e744924..1874c9f 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -3,6 +3,7 @@
#include "ice.h"
#include "ice_base.h"
+#include "ice_flow.h"
#include "ice_lib.h"
#include "ice_dcb_lib.h"
@@ -493,7 +494,28 @@ bool ice_is_safe_mode(struct ice_pf *pf)
}
/**
- * ice_rss_clean - Delete RSS related VSI structures that hold user inputs
+ * ice_vsi_clean_rss_flow_fld - Delete RSS configuration
+ * @vsi: the VSI being cleaned up
+ *
+ * This function deletes RSS input set for all flows that were configured
+ * for this VSI
+ */
+static void ice_vsi_clean_rss_flow_fld(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ enum ice_status status;
+
+ if (ice_is_safe_mode(pf))
+ return;
+
+ status = ice_rem_vsi_rss_cfg(&pf->hw, vsi->idx);
+ if (status)
+ dev_dbg(ice_pf_to_dev(pf), "ice_rem_vsi_rss_cfg failed for vsi = %d, error = %d\n",
+ vsi->vsi_num, status);
+}
+
+/**
+ * ice_rss_clean - Delete RSS related VSI structures and configuration
* @vsi: the VSI being removed
*/
static void ice_rss_clean(struct ice_vsi *vsi)
@@ -507,6 +529,11 @@ static void ice_rss_clean(struct ice_vsi *vsi)
devm_kfree(dev, vsi->rss_hkey_user);
if (vsi->rss_lut_user)
devm_kfree(dev, vsi->rss_lut_user);
+
+ ice_vsi_clean_rss_flow_fld(vsi);
+ /* remove RSS replay list */
+ if (!ice_is_safe_mode(pf))
+ ice_rem_vsi_rss_list(&pf->hw, vsi->idx);
}
/**
@@ -817,12 +844,23 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi)
ctxt->info.valid_sections |=
cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID);
- /* Enable MAC Antispoof with new VSI being initialized or updated */
- if (vsi->type == ICE_VSI_VF && pf->vf[vsi->vf_id].spoofchk) {
+ /* enable/disable MAC and VLAN anti-spoof when spoofchk is on/off
+ * respectively
+ */
+ if (vsi->type == ICE_VSI_VF) {
ctxt->info.valid_sections |=
cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
- ctxt->info.sec_flags |=
- ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF;
+ if (pf->vf[vsi->vf_id].spoofchk) {
+ ctxt->info.sec_flags |=
+ ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF |
+ (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA <<
+ ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S);
+ } else {
+ ctxt->info.sec_flags &=
+ ~(ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF |
+ (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA <<
+ ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S));
+ }
}
/* Allow control frames out of main VSI */
@@ -1076,6 +1114,115 @@ static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi)
}
/**
+ * ice_vsi_set_vf_rss_flow_fld - Sets VF VSI RSS input set for different flows
+ * @vsi: VSI to be configured
+ *
+ * This function will only be called during the VF VSI setup. Upon successful
+ * completion of package download, this function will configure default RSS
+ * input sets for VF VSI.
+ */
+static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ enum ice_status status;
+ struct device *dev;
+
+ dev = ice_pf_to_dev(pf);
+ if (ice_is_safe_mode(pf)) {
+ dev_dbg(dev, "Advanced RSS disabled. Package download failed, vsi num = %d\n",
+ vsi->vsi_num);
+ return;
+ }
+
+ status = ice_add_avf_rss_cfg(&pf->hw, vsi->idx, ICE_DEFAULT_RSS_HENA);
+ if (status)
+ dev_dbg(dev, "ice_add_avf_rss_cfg failed for vsi = %d, error = %d\n",
+ vsi->vsi_num, status);
+}
+
+/**
+ * ice_vsi_set_rss_flow_fld - Sets RSS input set for different flows
+ * @vsi: VSI to be configured
+ *
+ * This function will only be called after successful download package call
+ * during initialization of PF. Since the downloaded package will erase the
+ * RSS section, this function will configure RSS input sets for different
+ * flow types. The last profile added has the highest priority, therefore 2
+ * tuple profiles (i.e. IPv4 src/dst) are added before 4 tuple profiles
+ * (i.e. IPv4 src/dst TCP src/dst port).
+ */
+static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi)
+{
+ u16 vsi_handle = vsi->idx, vsi_num = vsi->vsi_num;
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ enum ice_status status;
+ struct device *dev;
+
+ dev = ice_pf_to_dev(pf);
+ if (ice_is_safe_mode(pf)) {
+ dev_dbg(dev, "Advanced RSS disabled. Package download failed, vsi num = %d\n",
+ vsi_num);
+ return;
+ }
+ /* configure RSS for IPv4 with input set IP src/dst */
+ status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4,
+ ICE_FLOW_SEG_HDR_IPV4);
+ if (status)
+ dev_dbg(dev, "ice_add_rss_cfg failed for ipv4 flow, vsi = %d, error = %d\n",
+ vsi_num, status);
+
+ /* configure RSS for IPv6 with input set IPv6 src/dst */
+ status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6,
+ ICE_FLOW_SEG_HDR_IPV6);
+ if (status)
+ dev_dbg(dev, "ice_add_rss_cfg failed for ipv6 flow, vsi = %d, error = %d\n",
+ vsi_num, status);
+
+ /* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */
+ status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV4,
+ ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4);
+ if (status)
+ dev_dbg(dev, "ice_add_rss_cfg failed for tcp4 flow, vsi = %d, error = %d\n",
+ vsi_num, status);
+
+ /* configure RSS for udp4 with input set IP src/dst, UDP src/dst */
+ status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV4,
+ ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4);
+ if (status)
+ dev_dbg(dev, "ice_add_rss_cfg failed for udp4 flow, vsi = %d, error = %d\n",
+ vsi_num, status);
+
+ /* configure RSS for sctp4 with input set IP src/dst */
+ status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4,
+ ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4);
+ if (status)
+ dev_dbg(dev, "ice_add_rss_cfg failed for sctp4 flow, vsi = %d, error = %d\n",
+ vsi_num, status);
+
+ /* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */
+ status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV6,
+ ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6);
+ if (status)
+ dev_dbg(dev, "ice_add_rss_cfg failed for tcp6 flow, vsi = %d, error = %d\n",
+ vsi_num, status);
+
+ /* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */
+ status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV6,
+ ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6);
+ if (status)
+ dev_dbg(dev, "ice_add_rss_cfg failed for udp6 flow, vsi = %d, error = %d\n",
+ vsi_num, status);
+
+ /* configure RSS for sctp6 with input set IPv6 src/dst */
+ status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6,
+ ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6);
+ if (status)
+ dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %d\n",
+ vsi_num, status);
+}
+
+/**
* ice_add_mac_to_list - Add a MAC address filter entry to the list
* @vsi: the VSI to be forwarded to
* @add_list: pointer to the list which contains MAC filter entries
@@ -1636,22 +1783,14 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc)
ctxt->info = vsi->info;
- if (ena) {
- ctxt->info.sec_flags |=
- ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA <<
- ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S;
+ if (ena)
ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
- } else {
- ctxt->info.sec_flags &=
- ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA <<
- ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S);
+ else
ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
- }
if (!vlan_promisc)
ctxt->info.valid_sections =
- cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID |
- ICE_AQ_VSI_PROP_SW_VALID);
+ cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID);
status = ice_update_vsi(&pf->hw, vsi->idx, ctxt, NULL);
if (status) {
@@ -1661,7 +1800,6 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc)
goto err_out;
}
- vsi->info.sec_flags = ctxt->info.sec_flags;
vsi->info.sw_flags2 = ctxt->info.sw_flags2;
kfree(ctxt);
@@ -1899,8 +2037,10 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
* receive traffic on first queue. Hence no need to capture
* return value
*/
- if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
ice_vsi_cfg_rss_lut_key(vsi);
+ ice_vsi_set_rss_flow_fld(vsi);
+ }
break;
case ICE_VSI_VF:
/* VF driver will take care of creating netdev for this type and
@@ -1924,8 +2064,10 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
* receive traffic on first queue. Hence no need to capture
* return value
*/
- if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
ice_vsi_cfg_rss_lut_key(vsi);
+ ice_vsi_set_vf_rss_flow_fld(vsi);
+ }
break;
case ICE_VSI_LB:
ret = ice_vsi_alloc_rings(vsi);
@@ -2402,6 +2544,97 @@ int ice_vsi_release(struct ice_vsi *vsi)
}
/**
+ * ice_vsi_rebuild_update_coalesce - set coalesce for a q_vector
+ * @q_vector: pointer to q_vector which is being updated
+ * @coalesce: pointer to array of struct with stored coalesce
+ *
+ * Set coalesce param in q_vector and update these parameters in HW.
+ */
+static void
+ice_vsi_rebuild_update_coalesce(struct ice_q_vector *q_vector,
+ struct ice_coalesce_stored *coalesce)
+{
+ struct ice_ring_container *rx_rc = &q_vector->rx;
+ struct ice_ring_container *tx_rc = &q_vector->tx;
+ struct ice_hw *hw = &q_vector->vsi->back->hw;
+
+ tx_rc->itr_setting = coalesce->itr_tx;
+ rx_rc->itr_setting = coalesce->itr_rx;
+
+ /* dynamic ITR values will be updated during Tx/Rx */
+ if (!ITR_IS_DYNAMIC(tx_rc->itr_setting))
+ wr32(hw, GLINT_ITR(tx_rc->itr_idx, q_vector->reg_idx),
+ ITR_REG_ALIGN(tx_rc->itr_setting) >>
+ ICE_ITR_GRAN_S);
+ if (!ITR_IS_DYNAMIC(rx_rc->itr_setting))
+ wr32(hw, GLINT_ITR(rx_rc->itr_idx, q_vector->reg_idx),
+ ITR_REG_ALIGN(rx_rc->itr_setting) >>
+ ICE_ITR_GRAN_S);
+
+ q_vector->intrl = coalesce->intrl;
+ wr32(hw, GLINT_RATE(q_vector->reg_idx),
+ ice_intrl_usec_to_reg(q_vector->intrl, hw->intrl_gran));
+}
+
+/**
+ * ice_vsi_rebuild_get_coalesce - get coalesce from all q_vectors
+ * @vsi: VSI connected with q_vectors
+ * @coalesce: array of struct with stored coalesce
+ *
+ * Returns array size.
+ */
+static int
+ice_vsi_rebuild_get_coalesce(struct ice_vsi *vsi,
+ struct ice_coalesce_stored *coalesce)
+{
+ int i;
+
+ ice_for_each_q_vector(vsi, i) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[i];
+
+ coalesce[i].itr_tx = q_vector->tx.itr_setting;
+ coalesce[i].itr_rx = q_vector->rx.itr_setting;
+ coalesce[i].intrl = q_vector->intrl;
+ }
+
+ return vsi->num_q_vectors;
+}
+
+/**
+ * ice_vsi_rebuild_set_coalesce - set coalesce from earlier saved arrays
+ * @vsi: VSI connected with q_vectors
+ * @coalesce: pointer to array of struct with stored coalesce
+ * @size: size of coalesce array
+ *
+ * Before this function, ice_vsi_rebuild_get_coalesce should be called to save
+ * ITR params in arrays. If size is 0 or coalesce wasn't stored set coalesce
+ * to default value.
+ */
+static void
+ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi,
+ struct ice_coalesce_stored *coalesce, int size)
+{
+ int i;
+
+ if ((size && !coalesce) || !vsi)
+ return;
+
+ for (i = 0; i < size && i < vsi->num_q_vectors; i++)
+ ice_vsi_rebuild_update_coalesce(vsi->q_vectors[i],
+ &coalesce[i]);
+
+ for (; i < vsi->num_q_vectors; i++) {
+ struct ice_coalesce_stored coalesce_dflt = {
+ .itr_tx = ICE_DFLT_TX_ITR,
+ .itr_rx = ICE_DFLT_RX_ITR,
+ .intrl = 0
+ };
+ ice_vsi_rebuild_update_coalesce(vsi->q_vectors[i],
+ &coalesce_dflt);
+ }
+}
+
+/**
* ice_vsi_rebuild - Rebuild VSI after reset
* @vsi: VSI to be rebuild
* @init_vsi: is this an initialization or a reconfigure of the VSI
@@ -2411,6 +2644,8 @@ int ice_vsi_release(struct ice_vsi *vsi)
int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
{
u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+ struct ice_coalesce_stored *coalesce;
+ int prev_num_q_vectors = 0;
struct ice_vf *vf = NULL;
enum ice_status status;
struct ice_pf *pf;
@@ -2423,6 +2658,11 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
if (vsi->type == ICE_VSI_VF)
vf = &pf->vf[vsi->vf_id];
+ coalesce = kcalloc(vsi->num_q_vectors,
+ sizeof(struct ice_coalesce_stored), GFP_KERNEL);
+ if (coalesce)
+ prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi,
+ coalesce);
ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
ice_vsi_free_q_vectors(vsi);
@@ -2535,6 +2775,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
return ice_schedule_reset(pf, ICE_RESET_PFR);
}
}
+ ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors);
+ kfree(coalesce);
+
return 0;
err_vectors:
@@ -2549,6 +2792,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
err_vsi:
ice_vsi_clear(vsi);
set_bit(__ICE_RESET_FAILED, pf->state);
+ kfree(coalesce);
return ret;
}
@@ -2740,3 +2984,121 @@ ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set)
ice_free_fltr_list(&vsi->back->pdev->dev, &tmp_add_list);
return status;
}
+
+/**
+ * ice_is_dflt_vsi_in_use - check if the default forwarding VSI is being used
+ * @sw: switch to check if its default forwarding VSI is free
+ *
+ * Return true if the default forwarding VSI is already being used, else returns
+ * false signalling that it's available to use.
+ */
+bool ice_is_dflt_vsi_in_use(struct ice_sw *sw)
+{
+ return (sw->dflt_vsi && sw->dflt_vsi_ena);
+}
+
+/**
+ * ice_is_vsi_dflt_vsi - check if the VSI passed in is the default VSI
+ * @sw: switch for the default forwarding VSI to compare against
+ * @vsi: VSI to compare against default forwarding VSI
+ *
+ * If this VSI passed in is the default forwarding VSI then return true, else
+ * return false
+ */
+bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi)
+{
+ return (sw->dflt_vsi == vsi && sw->dflt_vsi_ena);
+}
+
+/**
+ * ice_set_dflt_vsi - set the default forwarding VSI
+ * @sw: switch used to assign the default forwarding VSI
+ * @vsi: VSI getting set as the default forwarding VSI on the switch
+ *
+ * If the VSI passed in is already the default VSI and it's enabled just return
+ * success.
+ *
+ * If there is already a default VSI on the switch and it's enabled then return
+ * -EEXIST since there can only be one default VSI per switch.
+ *
+ * Otherwise try to set the VSI passed in as the switch's default VSI and
+ * return the result.
+ */
+int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi)
+{
+ enum ice_status status;
+ struct device *dev;
+
+ if (!sw || !vsi)
+ return -EINVAL;
+
+ dev = ice_pf_to_dev(vsi->back);
+
+ /* the VSI passed in is already the default VSI */
+ if (ice_is_vsi_dflt_vsi(sw, vsi)) {
+ dev_dbg(dev, "VSI %d passed in is already the default forwarding VSI, nothing to do\n",
+ vsi->vsi_num);
+ return 0;
+ }
+
+ /* another VSI is already the default VSI for this switch */
+ if (ice_is_dflt_vsi_in_use(sw)) {
+ dev_err(dev,
+ "Default forwarding VSI %d already in use, disable it and try again\n",
+ sw->dflt_vsi->vsi_num);
+ return -EEXIST;
+ }
+
+ status = ice_cfg_dflt_vsi(&vsi->back->hw, vsi->idx, true, ICE_FLTR_RX);
+ if (status) {
+ dev_err(dev,
+ "Failed to set VSI %d as the default forwarding VSI, error %d\n",
+ vsi->vsi_num, status);
+ return -EIO;
+ }
+
+ sw->dflt_vsi = vsi;
+ sw->dflt_vsi_ena = true;
+
+ return 0;
+}
+
+/**
+ * ice_clear_dflt_vsi - clear the default forwarding VSI
+ * @sw: switch used to clear the default VSI
+ *
+ * If the switch has no default VSI or it's not enabled then return error.
+ *
+ * Otherwise try to clear the default VSI and return the result.
+ */
+int ice_clear_dflt_vsi(struct ice_sw *sw)
+{
+ struct ice_vsi *dflt_vsi;
+ enum ice_status status;
+ struct device *dev;
+
+ if (!sw)
+ return -EINVAL;
+
+ dev = ice_pf_to_dev(sw->pf);
+
+ dflt_vsi = sw->dflt_vsi;
+
+ /* there is no default VSI configured */
+ if (!ice_is_dflt_vsi_in_use(sw))
+ return -ENODEV;
+
+ status = ice_cfg_dflt_vsi(&dflt_vsi->back->hw, dflt_vsi->idx, false,
+ ICE_FLTR_RX);
+ if (status) {
+ dev_err(dev,
+ "Failed to clear the default forwarding VSI %d, error %d\n",
+ dflt_vsi->vsi_num, status);
+ return -EIO;
+ }
+
+ sw->dflt_vsi = NULL;
+ sw->dflt_vsi_ena = false;
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 6e31e30..68fd0d4 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -103,4 +103,12 @@ enum ice_status
ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set);
bool ice_is_safe_mode(struct ice_pf *pf);
+
+bool ice_is_dflt_vsi_in_use(struct ice_sw *sw);
+
+bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi);
+
+int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi);
+
+int ice_clear_dflt_vsi(struct ice_sw *sw);
#endif /* !_ICE_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 4d5220c..5ae67160 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -13,7 +13,7 @@
#define DRV_VERSION_MAJOR 0
#define DRV_VERSION_MINOR 8
-#define DRV_VERSION_BUILD 1
+#define DRV_VERSION_BUILD 2
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
@@ -379,25 +379,29 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
clear_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags);
if (vsi->current_netdev_flags & IFF_PROMISC) {
/* Apply Rx filter rule to get traffic from wire */
- status = ice_cfg_dflt_vsi(hw, vsi->idx, true,
- ICE_FLTR_RX);
- if (status) {
- netdev_err(netdev, "Error setting default VSI %i Rx rule\n",
- vsi->vsi_num);
- vsi->current_netdev_flags &= ~IFF_PROMISC;
- err = -EIO;
- goto out_promisc;
+ if (!ice_is_dflt_vsi_in_use(pf->first_sw)) {
+ err = ice_set_dflt_vsi(pf->first_sw, vsi);
+ if (err && err != -EEXIST) {
+ netdev_err(netdev,
+ "Error %d setting default VSI %i Rx rule\n",
+ err, vsi->vsi_num);
+ vsi->current_netdev_flags &=
+ ~IFF_PROMISC;
+ goto out_promisc;
+ }
}
} else {
/* Clear Rx filter to remove traffic from wire */
- status = ice_cfg_dflt_vsi(hw, vsi->idx, false,
- ICE_FLTR_RX);
- if (status) {
- netdev_err(netdev, "Error clearing default VSI %i Rx rule\n",
- vsi->vsi_num);
- vsi->current_netdev_flags |= IFF_PROMISC;
- err = -EIO;
- goto out_promisc;
+ if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) {
+ err = ice_clear_dflt_vsi(pf->first_sw);
+ if (err) {
+ netdev_err(netdev,
+ "Error %d clearing default VSI %i Rx rule\n",
+ err, vsi->vsi_num);
+ vsi->current_netdev_flags |=
+ IFF_PROMISC;
+ goto out_promisc;
+ }
}
}
}
@@ -472,7 +476,7 @@ ice_prepare_for_reset(struct ice_pf *pf)
ice_vc_notify_reset(pf);
/* Disable VFs until reset is completed */
- for (i = 0; i < pf->num_alloc_vfs; i++)
+ ice_for_each_vf(pf, i)
ice_set_vf_state_qs_dis(&pf->vf[i]);
/* clear SW filtering DB */
@@ -840,8 +844,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
ice_vsi_link_event(vsi, link_up);
ice_print_link_msg(vsi, link_up);
- if (pf->num_alloc_vfs)
- ice_vc_notify_link_state(pf);
+ ice_vc_notify_link_state(pf);
return result;
}
@@ -1291,7 +1294,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
}
/* check to see if one of the VFs caused the MDD */
- for (i = 0; i < pf->num_alloc_vfs; i++) {
+ ice_for_each_vf(pf, i) {
struct ice_vf *vf = &pf->vf[i];
bool vf_mdd_detected = false;
@@ -2330,7 +2333,8 @@ static void ice_set_netdev_features(struct net_device *netdev)
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX;
- tso_features = NETIF_F_TSO;
+ tso_features = NETIF_F_TSO |
+ NETIF_F_GSO_UDP_L4;
/* set features that user can change */
netdev->hw_features = dflt_features | csumo_features |
@@ -3568,6 +3572,15 @@ static const struct pci_device_id ice_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 },
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 },
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_BACKPLANE), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_QSFP), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SFP), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_10G_BASE_T), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SGMII), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822X_BACKPLANE), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SFP), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_10G_BASE_T), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SGMII), 0 },
/* required last entry */
{ 0, }
};
@@ -4670,6 +4683,13 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
goto err_init_ctrlq;
}
+ if (pf->first_sw->dflt_vsi_ena)
+ dev_info(dev,
+ "Clearing default VSI, re-enable after reset completes\n");
+ /* clear the default VSI configuration if it exists */
+ pf->first_sw->dflt_vsi = NULL;
+ pf->first_sw->dflt_vsi_ena = false;
+
ice_clear_pxe_mode(hw);
ret = ice_get_caps(hw);
@@ -4825,7 +4845,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
}
}
- netdev_info(netdev, "changed MTU to %d\n", new_mtu);
+ netdev_dbg(netdev, "changed MTU to %d\n", new_mtu);
return 0;
}
@@ -5066,36 +5086,17 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
struct ice_ring *tx_ring = NULL;
struct ice_vsi *vsi = np->vsi;
struct ice_pf *pf = vsi->back;
- int hung_queue = -1;
u32 i;
pf->tx_timeout_count++;
- /* find the stopped queue the same way dev_watchdog() does */
- for (i = 0; i < netdev->num_tx_queues; i++) {
- unsigned long trans_start;
- struct netdev_queue *q;
-
- q = netdev_get_tx_queue(netdev, i);
- trans_start = q->trans_start;
- if (netif_xmit_stopped(q) &&
- time_after(jiffies,
- trans_start + netdev->watchdog_timeo)) {
- hung_queue = i;
- break;
- }
- }
-
- if (i == netdev->num_tx_queues)
- netdev_info(netdev, "tx_timeout: no netdev hung queue found\n");
- else
- /* now that we have an index, find the tx_ring struct */
- for (i = 0; i < vsi->num_txq; i++)
- if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
- if (hung_queue == vsi->tx_rings[i]->q_index) {
- tx_ring = vsi->tx_rings[i];
- break;
- }
+ /* now that we have an index, find the tx_ring struct */
+ for (i = 0; i < vsi->num_txq; i++)
+ if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
+ if (txqueue == vsi->tx_rings[i]->q_index) {
+ tx_ring = vsi->tx_rings[i];
+ break;
+ }
/* Reset recovery level if enough time has elapsed after last timeout.
* Also ensure no new reset action happens before next timeout period.
@@ -5110,19 +5111,19 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
struct ice_hw *hw = &pf->hw;
u32 head, val = 0;
- head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[hung_queue])) &
+ head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])) &
QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S;
/* Read interrupt register */
val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
- vsi->vsi_num, hung_queue, tx_ring->next_to_clean,
+ vsi->vsi_num, txqueue, tx_ring->next_to_clean,
head, tx_ring->next_to_use, val);
}
pf->tx_timeout_last_recovery = jiffies;
- netdev_info(netdev, "tx_timeout recovery level %d, hung_queue %d\n",
- pf->tx_timeout_recovery_level, hung_queue);
+ netdev_info(netdev, "tx_timeout recovery level %d, txqueue %d\n",
+ pf->tx_timeout_recovery_level, txqueue);
switch (pf->tx_timeout_recovery_level) {
case 1:
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 57c73f6..7525ac5 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -289,6 +289,18 @@ enum ice_status ice_init_nvm(struct ice_hw *hw)
nvm->eetrack = (eetrack_hi << 16) | eetrack_lo;
+ /* the following devices do not have boot_cfg_tlv yet */
+ if (hw->device_id == ICE_DEV_ID_E822C_BACKPLANE ||
+ hw->device_id == ICE_DEV_ID_E822C_QSFP ||
+ hw->device_id == ICE_DEV_ID_E822C_10G_BASE_T ||
+ hw->device_id == ICE_DEV_ID_E822C_SGMII ||
+ hw->device_id == ICE_DEV_ID_E822C_SFP ||
+ hw->device_id == ICE_DEV_ID_E822X_BACKPLANE ||
+ hw->device_id == ICE_DEV_ID_E822L_SFP ||
+ hw->device_id == ICE_DEV_ID_E822L_10G_BASE_T ||
+ hw->device_id == ICE_DEV_ID_E822L_SGMII)
+ return status;
+
status = ice_get_pfa_module_tlv(hw, &boot_cfg_tlv, &boot_cfg_tlv_len,
ICE_SR_BOOT_CFG_PTR);
if (status) {
diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
new file mode 100644
index 0000000..7164756
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Intel Corporation. */
+
+#ifndef _ICE_PROTOCOL_TYPE_H_
+#define _ICE_PROTOCOL_TYPE_H_
+/* Decoders for ice_prot_id:
+ * - F: First
+ * - I: Inner
+ * - L: Last
+ * - O: Outer
+ * - S: Single
+ */
+enum ice_prot_id {
+ ICE_PROT_ID_INVAL = 0,
+ ICE_PROT_IPV4_OF_OR_S = 32,
+ ICE_PROT_IPV4_IL = 33,
+ ICE_PROT_IPV6_OF_OR_S = 40,
+ ICE_PROT_IPV6_IL = 41,
+ ICE_PROT_TCP_IL = 49,
+ ICE_PROT_UDP_IL_OR_S = 53,
+ ICE_PROT_SCTP_IL = 96,
+ ICE_PROT_META_ID = 255, /* when offset == metadata */
+ ICE_PROT_INVALID = 255 /* when offset == ICE_FV_OFFSET_INVAL */
+};
+#endif /* _ICE_PROTOCOL_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h
index c015978..a9a8bc3 100644
--- a/drivers/net/ethernet/intel/ice/ice_status.h
+++ b/drivers/net/ethernet/intel/ice/ice_status.h
@@ -26,6 +26,7 @@ enum ice_status {
ICE_ERR_IN_USE = -16,
ICE_ERR_MAX_LIMIT = -17,
ICE_ERR_RESET_ONGOING = -18,
+ ICE_ERR_HW_TABLE = -19,
ICE_ERR_NVM_CHECKSUM = -51,
ICE_ERR_BUF_TOO_SHORT = -52,
ICE_ERR_NVM_BLANK_MODE = -53,
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index b5a53f8..4312660 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -50,42 +50,6 @@ static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0,
((n) * sizeof(((struct ice_sw_rule_vsi_list *)0)->vsi)))
/**
- * ice_aq_alloc_free_res - command to allocate/free resources
- * @hw: pointer to the HW struct
- * @num_entries: number of resource entries in buffer
- * @buf: Indirect buffer to hold data parameters and response
- * @buf_size: size of buffer for indirect commands
- * @opc: pass in the command opcode
- * @cd: pointer to command details structure or NULL
- *
- * Helper function to allocate/free resources using the admin queue commands
- */
-static enum ice_status
-ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries,
- struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size,
- enum ice_adminq_opc opc, struct ice_sq_cd *cd)
-{
- struct ice_aqc_alloc_free_res_cmd *cmd;
- struct ice_aq_desc desc;
-
- cmd = &desc.params.sw_res_ctrl;
-
- if (!buf)
- return ICE_ERR_PARAM;
-
- if (buf_size < (num_entries * sizeof(buf->elem[0])))
- return ICE_ERR_PARAM;
-
- ice_fill_dflt_direct_cmd_desc(&desc, opc);
-
- desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-
- cmd->num_entries = cpu_to_le16(num_entries);
-
- return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-}
-
-/**
* ice_init_def_sw_recp - initialize the recipe book keeping tables
* @hw: pointer to the HW struct
*
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 2c212f6..fd17ace 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1071,13 +1071,16 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
ice_put_rx_buf(rx_ring, rx_buf);
continue;
construct_skb:
- if (skb)
+ if (skb) {
ice_add_rx_frag(rx_ring, rx_buf, skb, size);
- else if (ice_ring_uses_build_skb(rx_ring))
- skb = ice_build_skb(rx_ring, rx_buf, &xdp);
- else
+ } else if (likely(xdp.data)) {
+ if (ice_ring_uses_build_skb(rx_ring))
+ skb = ice_build_skb(rx_ring, rx_buf, &xdp);
+ else
+ skb = ice_construct_skb(rx_ring, rx_buf, &xdp);
+ } else {
skb = ice_construct_skb(rx_ring, rx_buf, &xdp);
-
+ }
/* exit if we failed to retrieve a buffer */
if (!skb) {
rx_ring->rx_stats.alloc_buf_failed++;
@@ -1925,6 +1928,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
} ip;
union {
struct tcphdr *tcp;
+ struct udphdr *udp;
unsigned char *hdr;
} l4;
u64 cd_mss, cd_tso_len;
@@ -1958,10 +1962,18 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
/* remove payload length from checksum */
paylen = skb->len - l4_start;
- csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen));
- /* compute length of segmentation header */
- off->header_len = (l4.tcp->doff * 4) + l4_start;
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+ csum_replace_by_diff(&l4.udp->check,
+ (__force __wsum)htonl(paylen));
+ /* compute length of UDP segmentation header */
+ off->header_len = sizeof(l4.udp) + l4_start;
+ } else {
+ csum_replace_by_diff(&l4.tcp->check,
+ (__force __wsum)htonl(paylen));
+ /* compute length of TCP segmentation header */
+ off->header_len = (l4.tcp->doff * 4) + l4_start;
+ }
/* update gso_segs and bytecount */
first->gso_segs = skb_shinfo(skb)->gso_segs;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index a84cc0e..a862706 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -341,6 +341,12 @@ struct ice_ring_container {
u16 itr_setting;
};
+struct ice_coalesce_stored {
+ u16 itr_tx;
+ u16 itr_rx;
+ u8 intrl;
+};
+
/* iterator for handling rings in ring container */
#define ice_for_each_ring(pos, head) \
for (pos = (head).ring; pos; pos = pos->next)
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index c4854a9..b361ffa 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -13,6 +13,7 @@
#include "ice_controlq.h"
#include "ice_lan_tx_rx.h"
#include "ice_flex_type.h"
+#include "ice_protocol_type.h"
static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc)
{
@@ -41,6 +42,7 @@ static inline u32 ice_round_to_num(u32 N, u32 R)
#define ICE_DBG_QCTX BIT_ULL(6)
#define ICE_DBG_NVM BIT_ULL(7)
#define ICE_DBG_LAN BIT_ULL(8)
+#define ICE_DBG_FLOW BIT_ULL(9)
#define ICE_DBG_SW BIT_ULL(13)
#define ICE_DBG_SCHED BIT_ULL(14)
#define ICE_DBG_PKG BIT_ULL(16)
@@ -559,6 +561,10 @@ struct ice_hw {
/* HW block tables */
struct ice_blk_info blk[ICE_BLK_COUNT];
+ struct mutex fl_profs_locks[ICE_BLK_COUNT]; /* lock fltr profiles */
+ struct list_head fl_profs[ICE_BLK_COUNT];
+ struct mutex rss_locks; /* protect RSS configuration */
+ struct list_head rss_list_head;
};
/* Statistics collected by each port, VSI, VEB, and S-channel */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index edb3742..82b1e7a 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -35,37 +35,6 @@ static int ice_check_vf_init(struct ice_pf *pf, struct ice_vf *vf)
}
/**
- * ice_err_to_virt err - translate errors for VF return code
- * @ice_err: error return code
- */
-static enum virtchnl_status_code ice_err_to_virt_err(enum ice_status ice_err)
-{
- switch (ice_err) {
- case ICE_SUCCESS:
- return VIRTCHNL_STATUS_SUCCESS;
- case ICE_ERR_BAD_PTR:
- case ICE_ERR_INVAL_SIZE:
- case ICE_ERR_DEVICE_NOT_SUPPORTED:
- case ICE_ERR_PARAM:
- case ICE_ERR_CFG:
- return VIRTCHNL_STATUS_ERR_PARAM;
- case ICE_ERR_NO_MEMORY:
- return VIRTCHNL_STATUS_ERR_NO_MEMORY;
- case ICE_ERR_NOT_READY:
- case ICE_ERR_RESET_FAILED:
- case ICE_ERR_FW_API_VER:
- case ICE_ERR_AQ_ERROR:
- case ICE_ERR_AQ_TIMEOUT:
- case ICE_ERR_AQ_FULL:
- case ICE_ERR_AQ_NO_WORK:
- case ICE_ERR_AQ_EMPTY:
- return VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
- default:
- return VIRTCHNL_STATUS_ERR_NOT_SUPPORTED;
- }
-}
-
-/**
* ice_vc_vf_broadcast - Broadcast a message to all VFs on PF
* @pf: pointer to the PF structure
* @v_opcode: operation code
@@ -78,10 +47,11 @@ ice_vc_vf_broadcast(struct ice_pf *pf, enum virtchnl_ops v_opcode,
enum virtchnl_status_code v_retval, u8 *msg, u16 msglen)
{
struct ice_hw *hw = &pf->hw;
- struct ice_vf *vf = pf->vf;
int i;
- for (i = 0; i < pf->num_alloc_vfs; i++, vf++) {
+ ice_for_each_vf(pf, i) {
+ struct ice_vf *vf = &pf->vf[i];
+
/* Not all vfs are enabled so skip the ones that are not */
if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) &&
!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
@@ -121,26 +91,6 @@ ice_set_pfe_link(struct ice_vf *vf, struct virtchnl_pf_event *pfe,
}
/**
- * ice_set_pfe_link_forced - Force the virtchnl_pf_event link speed/status
- * @vf: pointer to the VF structure
- * @pfe: pointer to the virtchnl_pf_event to set link speed/status for
- * @link_up: whether or not to set the link up/down
- */
-static void
-ice_set_pfe_link_forced(struct ice_vf *vf, struct virtchnl_pf_event *pfe,
- bool link_up)
-{
- u16 link_speed;
-
- if (link_up)
- link_speed = ICE_AQ_LINK_SPEED_100GB;
- else
- link_speed = ICE_AQ_LINK_SPEED_UNKNOWN;
-
- ice_set_pfe_link(vf, pfe, link_speed, link_up);
-}
-
-/**
* ice_vc_notify_vf_link_state - Inform a VF of link status
* @vf: pointer to the VF structure
*
@@ -160,13 +110,17 @@ static void ice_vc_notify_vf_link_state(struct ice_vf *vf)
pfe.severity = PF_EVENT_SEVERITY_INFO;
/* Always report link is down if the VF queues aren't enabled */
- if (!vf->num_qs_ena)
+ if (!vf->num_qs_ena) {
ice_set_pfe_link(vf, &pfe, ICE_AQ_LINK_SPEED_UNKNOWN, false);
- else if (vf->link_forced)
- ice_set_pfe_link_forced(vf, &pfe, vf->link_up);
- else
- ice_set_pfe_link(vf, &pfe, ls->link_speed, ls->link_info &
- ICE_AQ_LINK_UP);
+ } else if (vf->link_forced) {
+ u16 link_speed = vf->link_up ?
+ ls->link_speed : ICE_AQ_LINK_SPEED_UNKNOWN;
+
+ ice_set_pfe_link(vf, &pfe, link_speed, vf->link_up);
+ } else {
+ ice_set_pfe_link(vf, &pfe, ls->link_speed,
+ ls->link_info & ICE_AQ_LINK_UP);
+ }
ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT,
VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe,
@@ -331,7 +285,7 @@ void ice_free_vfs(struct ice_pf *pf)
usleep_range(1000, 2000);
/* Avoid wait time by stopping all VFs at the same time */
- for (i = 0; i < pf->num_alloc_vfs; i++)
+ ice_for_each_vf(pf, i)
if (test_bit(ICE_VF_STATE_QS_ENA, pf->vf[i].vf_states))
ice_dis_vf_qs(&pf->vf[i]);
@@ -991,10 +945,17 @@ static void ice_cleanup_and_realloc_vf(struct ice_vf *vf)
/* reallocate VF resources to finish resetting the VSI state */
if (!ice_alloc_vf_res(vf)) {
+ struct ice_vsi *vsi;
+
ice_ena_vf_mappings(vf);
set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states);
clear_bit(ICE_VF_STATE_DIS, vf->vf_states);
- vf->num_vlan = 0;
+
+ vsi = pf->vsi[vf->lan_vsi_idx];
+ if (ice_vsi_add_vlan(vsi, 0))
+ dev_warn(ice_pf_to_dev(pf),
+ "Failed to add VLAN 0 filter for VF %d, MDD events will trigger. Reset the VF, disable spoofchk, or enable 8021q module on the guest",
+ vf->vf_id);
}
/* Tell the VF driver the reset is done. This needs to be done only
@@ -1023,7 +984,7 @@ ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m,
struct ice_hw *hw;
hw = &pf->hw;
- if (vf->num_vlan) {
+ if (vsi->num_vlan) {
status = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_m,
rm_promisc);
} else if (vf->port_vlan_id) {
@@ -1070,7 +1031,7 @@ static bool ice_config_res_vfs(struct ice_pf *pf)
ice_irq_dynamic_ena(hw, NULL, NULL);
/* Finish resetting each VF and allocate resources */
- for (v = 0; v < pf->num_alloc_vfs; v++) {
+ ice_for_each_vf(pf, v) {
struct ice_vf *vf = &pf->vf[v];
vf->num_vf_qs = pf->num_vf_qps;
@@ -1113,10 +1074,10 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
return false;
/* Begin reset on all VFs at once */
- for (v = 0; v < pf->num_alloc_vfs; v++)
+ ice_for_each_vf(pf, v)
ice_trigger_vf_reset(&pf->vf[v], is_vflr, true);
- for (v = 0; v < pf->num_alloc_vfs; v++) {
+ ice_for_each_vf(pf, v) {
struct ice_vsi *vsi;
vf = &pf->vf[v];
@@ -1161,7 +1122,7 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
dev_warn(dev, "VF reset check timeout\n");
/* free VF resources to begin resetting the VSI state */
- for (v = 0; v < pf->num_alloc_vfs; v++) {
+ ice_for_each_vf(pf, v) {
vf = &pf->vf[v];
ice_free_vf_res(vf);
@@ -1273,7 +1234,7 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
*/
if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) ||
test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) {
- if (vf->port_vlan_id || vf->num_vlan)
+ if (vf->port_vlan_id || vsi->num_vlan)
promisc_m = ICE_UCAST_VLAN_PROMISC_BITS;
else
promisc_m = ICE_UCAST_PROMISC_BITS;
@@ -1301,7 +1262,7 @@ void ice_vc_notify_link_state(struct ice_pf *pf)
{
int i;
- for (i = 0; i < pf->num_alloc_vfs; i++)
+ ice_for_each_vf(pf, i)
ice_vc_notify_vf_link_state(&pf->vf[i]);
}
@@ -1385,9 +1346,10 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
goto err_pci_disable_sriov;
}
pf->vf = vfs;
+ pf->num_alloc_vfs = num_alloc_vfs;
/* apply default profile */
- for (i = 0; i < num_alloc_vfs; i++) {
+ ice_for_each_vf(pf, i) {
vfs[i].pf = pf;
vfs[i].vf_sw_id = pf->first_sw;
vfs[i].vf_id = i;
@@ -1396,7 +1358,6 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps);
vfs[i].spoofchk = true;
}
- pf->num_alloc_vfs = num_alloc_vfs;
/* VF resources get allocated with initialization */
if (!ice_config_res_vfs(pf)) {
@@ -1535,7 +1496,7 @@ void ice_process_vflr_event(struct ice_pf *pf)
!pf->num_alloc_vfs)
return;
- for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) {
+ ice_for_each_vf(pf, vf_id) {
struct ice_vf *vf = &pf->vf[vf_id];
u32 reg_idx, bit_idx;
@@ -1918,6 +1879,89 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg)
}
/**
+ * ice_set_vf_spoofchk
+ * @netdev: network interface device structure
+ * @vf_id: VF identifier
+ * @ena: flag to enable or disable feature
+ *
+ * Enable or disable VF spoof checking
+ */
+int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_pf *pf = np->vsi->back;
+ struct ice_vsi_ctx *ctx;
+ struct ice_vsi *vf_vsi;
+ enum ice_status status;
+ struct device *dev;
+ struct ice_vf *vf;
+ int ret = 0;
+
+ dev = ice_pf_to_dev(pf);
+ if (ice_validate_vf_id(pf, vf_id))
+ return -EINVAL;
+
+ vf = &pf->vf[vf_id];
+
+ if (ice_check_vf_init(pf, vf))
+ return -EBUSY;
+
+ vf_vsi = pf->vsi[vf->lan_vsi_idx];
+ if (!vf_vsi) {
+ netdev_err(netdev, "VSI %d for VF %d is null\n",
+ vf->lan_vsi_idx, vf->vf_id);
+ return -EINVAL;
+ }
+
+ if (vf_vsi->type != ICE_VSI_VF) {
+ netdev_err(netdev,
+ "Type %d of VSI %d for VF %d is no ICE_VSI_VF\n",
+ vf_vsi->type, vf_vsi->vsi_num, vf->vf_id);
+ return -ENODEV;
+ }
+
+ if (ena == vf->spoofchk) {
+ dev_dbg(dev, "VF spoofchk already %s\n", ena ? "ON" : "OFF");
+ return 0;
+ }
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ ctx->info.sec_flags = vf_vsi->info.sec_flags;
+ ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
+ if (ena) {
+ ctx->info.sec_flags |=
+ ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF |
+ (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA <<
+ ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S);
+ } else {
+ ctx->info.sec_flags &=
+ ~(ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF |
+ (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA <<
+ ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S));
+ }
+
+ status = ice_update_vsi(&pf->hw, vf_vsi->idx, ctx, NULL);
+ if (status) {
+ dev_err(dev,
+ "Failed to %sable spoofchk on VF %d VSI %d\n error %d",
+ ena ? "en" : "dis", vf->vf_id, vf_vsi->vsi_num, status);
+ ret = -EIO;
+ goto out;
+ }
+
+ /* only update spoofchk state and VSI context on success */
+ vf_vsi->info.sec_flags = ctx->info.sec_flags;
+ vf->spoofchk = ena;
+
+out:
+ kfree(ctx);
+ return ret;
+}
+
+/**
* ice_vc_get_stats_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
@@ -2409,6 +2453,83 @@ static bool ice_can_vf_change_mac(struct ice_vf *vf)
}
/**
+ * ice_vc_add_mac_addr - attempt to add the MAC address passed in
+ * @vf: pointer to the VF info
+ * @vsi: pointer to the VF's VSI
+ * @mac_addr: MAC address to add
+ */
+static int
+ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
+{
+ struct device *dev = ice_pf_to_dev(vf->pf);
+ enum ice_status status;
+
+ /* default unicast MAC already added */
+ if (ether_addr_equal(mac_addr, vf->dflt_lan_addr.addr))
+ return 0;
+
+ if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) {
+ dev_err(dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
+ return -EPERM;
+ }
+
+ status = ice_vsi_cfg_mac_fltr(vsi, mac_addr, true);
+ if (status == ICE_ERR_ALREADY_EXISTS) {
+ dev_err(dev, "MAC %pM already exists for VF %d\n", mac_addr,
+ vf->vf_id);
+ return -EEXIST;
+ } else if (status) {
+ dev_err(dev, "Failed to add MAC %pM for VF %d\n, error %d\n",
+ mac_addr, vf->vf_id, status);
+ return -EIO;
+ }
+
+ /* only set dflt_lan_addr once */
+ if (is_zero_ether_addr(vf->dflt_lan_addr.addr) &&
+ is_unicast_ether_addr(mac_addr))
+ ether_addr_copy(vf->dflt_lan_addr.addr, mac_addr);
+
+ vf->num_mac++;
+
+ return 0;
+}
+
+/**
+ * ice_vc_del_mac_addr - attempt to delete the MAC address passed in
+ * @vf: pointer to the VF info
+ * @vsi: pointer to the VF's VSI
+ * @mac_addr: MAC address to delete
+ */
+static int
+ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
+{
+ struct device *dev = ice_pf_to_dev(vf->pf);
+ enum ice_status status;
+
+ if (!ice_can_vf_change_mac(vf) &&
+ ether_addr_equal(mac_addr, vf->dflt_lan_addr.addr))
+ return 0;
+
+ status = ice_vsi_cfg_mac_fltr(vsi, mac_addr, false);
+ if (status == ICE_ERR_DOES_NOT_EXIST) {
+ dev_err(dev, "MAC %pM does not exist for VF %d\n", mac_addr,
+ vf->vf_id);
+ return -ENOENT;
+ } else if (status) {
+ dev_err(dev, "Failed to delete MAC %pM for VF %d, error %d\n",
+ mac_addr, vf->vf_id, status);
+ return -EIO;
+ }
+
+ if (ether_addr_equal(mac_addr, vf->dflt_lan_addr.addr))
+ eth_zero_addr(vf->dflt_lan_addr.addr);
+
+ vf->num_mac--;
+
+ return 0;
+}
+
+/**
* ice_vc_handle_mac_addr_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
@@ -2419,23 +2540,23 @@ static bool ice_can_vf_change_mac(struct ice_vf *vf)
static int
ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
{
+ int (*ice_vc_cfg_mac)
+ (struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr);
enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
struct virtchnl_ether_addr_list *al =
(struct virtchnl_ether_addr_list *)msg;
struct ice_pf *pf = vf->pf;
enum virtchnl_ops vc_op;
- enum ice_status status;
struct ice_vsi *vsi;
- struct device *dev;
- int mac_count = 0;
int i;
- dev = ice_pf_to_dev(pf);
-
- if (set)
+ if (set) {
vc_op = VIRTCHNL_OP_ADD_ETH_ADDR;
- else
+ ice_vc_cfg_mac = ice_vc_add_mac_addr;
+ } else {
vc_op = VIRTCHNL_OP_DEL_ETH_ADDR;
+ ice_vc_cfg_mac = ice_vc_del_mac_addr;
+ }
if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
!ice_vc_isvalid_vsi_id(vf, al->vsi_id)) {
@@ -2443,14 +2564,15 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
goto handle_mac_exit;
}
+ /* If this VF is not privileged, then we can't add more than a
+ * limited number of addresses. Check to make sure that the
+ * additions do not push us over the limit.
+ */
if (set && !ice_is_vf_trusted(vf) &&
(vf->num_mac + al->num_elements) > ICE_MAX_MACADDR_PER_VF) {
- dev_err(dev,
+ dev_err(ice_pf_to_dev(pf),
"Can't add more MAC addresses, because VF-%d is not trusted, switch the VF to trusted mode in order to add more functionalities\n",
vf->vf_id);
- /* There is no need to let VF know about not being trusted
- * to add more MAC addr, so we can just return success message.
- */
v_ret = VIRTCHNL_STATUS_ERR_PARAM;
goto handle_mac_exit;
}
@@ -2462,70 +2584,22 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
}
for (i = 0; i < al->num_elements; i++) {
- u8 *maddr = al->list[i].addr;
+ u8 *mac_addr = al->list[i].addr;
+ int result;
- if (ether_addr_equal(maddr, vf->dflt_lan_addr.addr) ||
- is_broadcast_ether_addr(maddr)) {
- if (set) {
- /* VF is trying to add filters that the PF
- * already added. Just continue.
- */
- dev_info(dev,
- "MAC %pM already set for VF %d\n",
- maddr, vf->vf_id);
- continue;
- } else {
- /* VF can't remove dflt_lan_addr/bcast MAC */
- dev_err(dev,
- "VF can't remove default MAC address or MAC %pM programmed by PF for VF %d\n",
- maddr, vf->vf_id);
- continue;
- }
- }
+ if (is_broadcast_ether_addr(mac_addr) ||
+ is_zero_ether_addr(mac_addr))
+ continue;
- /* check for the invalid cases and bail if necessary */
- if (is_zero_ether_addr(maddr)) {
- dev_err(dev,
- "invalid MAC %pM provided for VF %d\n",
- maddr, vf->vf_id);
- v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ result = ice_vc_cfg_mac(vf, vsi, mac_addr);
+ if (result == -EEXIST || result == -ENOENT) {
+ continue;
+ } else if (result) {
+ v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
goto handle_mac_exit;
}
-
- if (is_unicast_ether_addr(maddr) &&
- !ice_can_vf_change_mac(vf)) {
- dev_err(dev,
- "can't change unicast MAC for untrusted VF %d\n",
- vf->vf_id);
- v_ret = VIRTCHNL_STATUS_ERR_PARAM;
- goto handle_mac_exit;
- }
-
- /* program the updated filter list */
- status = ice_vsi_cfg_mac_fltr(vsi, maddr, set);
- if (status == ICE_ERR_DOES_NOT_EXIST ||
- status == ICE_ERR_ALREADY_EXISTS) {
- dev_info(dev,
- "can't %s MAC filters %pM for VF %d, error %d\n",
- set ? "add" : "remove", maddr, vf->vf_id,
- status);
- } else if (status) {
- dev_err(dev,
- "can't %s MAC filters for VF %d, error %d\n",
- set ? "add" : "remove", vf->vf_id, status);
- v_ret = ice_err_to_virt_err(status);
- goto handle_mac_exit;
- }
-
- mac_count++;
}
- /* Track number of MAC filters programmed for the VF VSI */
- if (set)
- vf->num_mac += mac_count;
- else
- vf->num_mac -= mac_count;
-
handle_mac_exit:
/* send the response to the VF */
return ice_vc_send_msg_to_vf(vf, vc_op, v_ret, NULL, 0);
@@ -2744,17 +2818,6 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
goto error_param;
}
- if (add_v && !ice_is_vf_trusted(vf) &&
- vf->num_vlan >= ICE_MAX_VLAN_PER_VF) {
- dev_info(dev,
- "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
- vf->vf_id);
- /* There is no need to let VF know about being not trusted,
- * so we can just return success message here
- */
- goto error_param;
- }
-
for (i = 0; i < vfl->num_elements; i++) {
if (vfl->vlan_id[i] > ICE_MAX_VLANID) {
v_ret = VIRTCHNL_STATUS_ERR_PARAM;
@@ -2771,6 +2834,17 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
goto error_param;
}
+ if (add_v && !ice_is_vf_trusted(vf) &&
+ vsi->num_vlan >= ICE_MAX_VLAN_PER_VF) {
+ dev_info(dev,
+ "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
+ vf->vf_id);
+ /* There is no need to let VF know about being not trusted,
+ * so we can just return success message here
+ */
+ goto error_param;
+ }
+
if (vsi->info.pvid) {
v_ret = VIRTCHNL_STATUS_ERR_PARAM;
goto error_param;
@@ -2785,7 +2859,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
u16 vid = vfl->vlan_id[i];
if (!ice_is_vf_trusted(vf) &&
- vf->num_vlan >= ICE_MAX_VLAN_PER_VF) {
+ vsi->num_vlan >= ICE_MAX_VLAN_PER_VF) {
dev_info(dev,
"VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
vf->vf_id);
@@ -2796,12 +2870,20 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
goto error_param;
}
- if (ice_vsi_add_vlan(vsi, vid)) {
+ /* we add VLAN 0 by default for each VF so we can enable
+ * Tx VLAN anti-spoof without triggering MDD events so
+ * we don't need to add it again here
+ */
+ if (!vid)
+ continue;
+
+ status = ice_vsi_add_vlan(vsi, vid);
+ if (status) {
v_ret = VIRTCHNL_STATUS_ERR_PARAM;
goto error_param;
}
- vf->num_vlan++;
+ vsi->num_vlan++;
/* Enable VLAN pruning when VLAN is added */
if (!vlan_promisc) {
status = ice_cfg_vlan_pruning(vsi, true, false);
@@ -2837,21 +2919,29 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
*/
int num_vf_vlan;
- num_vf_vlan = vf->num_vlan;
+ num_vf_vlan = vsi->num_vlan;
for (i = 0; i < vfl->num_elements && i < num_vf_vlan; i++) {
u16 vid = vfl->vlan_id[i];
+ /* we add VLAN 0 by default for each VF so we can enable
+ * Tx VLAN anti-spoof without triggering MDD events so
+ * we don't want a VIRTCHNL request to remove it
+ */
+ if (!vid)
+ continue;
+
/* Make sure ice_vsi_kill_vlan is successful before
* updating VLAN information
*/
- if (ice_vsi_kill_vlan(vsi, vid)) {
+ status = ice_vsi_kill_vlan(vsi, vid);
+ if (status) {
v_ret = VIRTCHNL_STATUS_ERR_PARAM;
goto error_param;
}
- vf->num_vlan--;
+ vsi->num_vlan--;
/* Disable VLAN pruning when the last VLAN is removed */
- if (!vf->num_vlan)
+ if (!vsi->num_vlan)
ice_cfg_vlan_pruning(vsi, false, false);
/* Disable Unicast/Multicast VLAN promiscuous mode */
@@ -3165,65 +3255,6 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi)
}
/**
- * ice_set_vf_spoofchk
- * @netdev: network interface device structure
- * @vf_id: VF identifier
- * @ena: flag to enable or disable feature
- *
- * Enable or disable VF spoof checking
- */
-int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena)
-{
- struct ice_pf *pf = ice_netdev_to_pf(netdev);
- struct ice_vsi *vsi = pf->vsi[0];
- struct ice_vsi_ctx *ctx;
- enum ice_status status;
- struct device *dev;
- struct ice_vf *vf;
- int ret = 0;
-
- dev = ice_pf_to_dev(pf);
- if (ice_validate_vf_id(pf, vf_id))
- return -EINVAL;
-
- vf = &pf->vf[vf_id];
- if (ice_check_vf_init(pf, vf))
- return -EBUSY;
-
- if (ena == vf->spoofchk) {
- dev_dbg(dev, "VF spoofchk already %s\n",
- ena ? "ON" : "OFF");
- return 0;
- }
-
- ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
- if (!ctx)
- return -ENOMEM;
-
- ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
-
- if (ena) {
- ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF;
- ctx->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M;
- }
-
- status = ice_update_vsi(&pf->hw, vsi->idx, ctx, NULL);
- if (status) {
- dev_dbg(dev,
- "Error %d, failed to update VSI* parameters\n", status);
- ret = -EIO;
- goto out;
- }
-
- vf->spoofchk = ena;
- vsi->info.sec_flags = ctx->info.sec_flags;
- vsi->info.sw_flags2 = ctx->info.sw_flags2;
-out:
- kfree(ctx);
- return ret;
-}
-
-/**
* ice_wait_on_vf_reset
* @vf: The VF being resseting
*
@@ -3344,28 +3375,18 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted)
int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state)
{
struct ice_pf *pf = ice_netdev_to_pf(netdev);
- struct virtchnl_pf_event pfe = { 0 };
- struct ice_link_status *ls;
struct ice_vf *vf;
- struct ice_hw *hw;
if (ice_validate_vf_id(pf, vf_id))
return -EINVAL;
vf = &pf->vf[vf_id];
- hw = &pf->hw;
- ls = &pf->hw.port_info->phy.link_info;
-
if (ice_check_vf_init(pf, vf))
return -EBUSY;
- pfe.event = VIRTCHNL_EVENT_LINK_CHANGE;
- pfe.severity = PF_EVENT_SEVERITY_INFO;
-
switch (link_state) {
case IFLA_VF_LINK_STATE_AUTO:
vf->link_forced = false;
- vf->link_up = ls->link_info & ICE_AQ_LINK_UP;
break;
case IFLA_VF_LINK_STATE_ENABLE:
vf->link_forced = true;
@@ -3379,15 +3400,7 @@ int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state)
return -EINVAL;
}
- if (vf->link_forced)
- ice_set_pfe_link_forced(vf, &pfe, vf->link_up);
- else
- ice_set_pfe_link(vf, &pfe, ls->link_speed, vf->link_up);
-
- /* Notify the VF of its new link state */
- ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT,
- VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe,
- sizeof(pfe), NULL);
+ ice_vc_notify_vf_link_state(vf);
return 0;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
index 88aa65d..4647d63 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -40,6 +40,9 @@
#define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1)
#define ICE_MAX_VF_RESET_WAIT 15
+#define ice_for_each_vf(pf, i) \
+ for ((i) = 0; (i) < (pf)->num_alloc_vfs; (i)++)
+
/* Specific VF states */
enum ice_vf_states {
ICE_VF_STATE_INIT = 0, /* PF is initializing VF */
@@ -91,7 +94,6 @@ struct ice_vf {
unsigned long vf_caps; /* VF's adv. capabilities */
u8 num_req_qs; /* num of queue pairs requested by VF */
u16 num_mac;
- u16 num_vlan;
u16 num_vf_qs; /* num of queue configured per VF */
u16 num_qs_ena; /* total num of Tx/Rx queue enabled */
};
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 0af1f0b..149dca0 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -414,7 +414,8 @@ ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
if (vsi->type != ICE_VSI_PF)
return -EINVAL;
- vsi->num_xsk_umems = min_t(u16, vsi->num_rxq, vsi->num_txq);
+ if (!vsi->num_xsk_umems)
+ vsi->num_xsk_umems = min_t(u16, vsi->num_rxq, vsi->num_txq);
if (qid >= vsi->num_xsk_umems)
return -EINVAL;
@@ -1019,8 +1020,8 @@ bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget)
s16 ntc = xdp_ring->next_to_clean;
struct ice_tx_desc *tx_desc;
struct ice_tx_buf *tx_buf;
- bool xmit_done = true;
u32 xsk_frames = 0;
+ bool xmit_done;
tx_desc = ICE_TX_DESC(xdp_ring, ntc);
tx_buf = &xdp_ring->tx_buf[ntc];
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 8a6ef35..438b42c 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -530,7 +530,7 @@ static s32 igb_set_sfp_media_type_82575(struct e1000_hw *hw)
dev_spec->module_plugged = true;
if (eth_flags->e1000_base_lx || eth_flags->e1000_base_sx) {
hw->phy.media_type = e1000_media_type_internal_serdes;
- } else if (eth_flags->e100_base_fx) {
+ } else if (eth_flags->e100_base_fx || eth_flags->e100_base_lx) {
dev_spec->sgmii_active = true;
hw->phy.media_type = e1000_media_type_internal_serdes;
} else if (eth_flags->e1000_base_t) {
@@ -657,14 +657,10 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw)
break;
}
- /* do not change link mode for 100BaseFX */
- if (dev_spec->eth_flags.e100_base_fx)
- break;
-
/* change current link mode setting */
ctrl_ext &= ~E1000_CTRL_EXT_LINK_MODE_MASK;
- if (hw->phy.media_type == e1000_media_type_copper)
+ if (dev_spec->sgmii_active)
ctrl_ext |= E1000_CTRL_EXT_LINK_MODE_SGMII;
else
ctrl_ext |= E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES;
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 43c4383..f96ffa8 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -181,7 +181,7 @@ static int igb_get_link_ksettings(struct net_device *netdev,
advertising &= ~ADVERTISED_1000baseKX_Full;
}
}
- if (eth_flags->e100_base_fx) {
+ if (eth_flags->e100_base_fx || eth_flags->e100_base_lx) {
supported |= SUPPORTED_100baseT_Full;
advertising |= ADVERTISED_100baseT_Full;
}
diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile
index 88c6f88..49fb1e1 100644
--- a/drivers/net/ethernet/intel/igc/Makefile
+++ b/drivers/net/ethernet/intel/igc/Makefile
@@ -8,4 +8,4 @@
obj-$(CONFIG_IGC) += igc.o
igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \
-igc_ethtool.o
+igc_ethtool.o igc_ptp.o
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 612fe9e..52066bd 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -10,6 +10,9 @@
#include <linux/vmalloc.h>
#include <linux/ethtool.h>
#include <linux/sctp.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/timecounter.h>
+#include <linux/net_tstamp.h>
#include "igc_hw.h"
@@ -45,11 +48,15 @@ extern char igc_driver_version[];
#define IGC_REGS_LEN 740
#define IGC_RETA_SIZE 128
+/* flags controlling PTP/1588 function */
+#define IGC_PTP_ENABLED BIT(0)
+
/* Interrupt defines */
#define IGC_START_ITR 648 /* ~6000 ints/sec */
#define IGC_FLAG_HAS_MSI BIT(0)
#define IGC_FLAG_QUEUE_PAIRS BIT(3)
#define IGC_FLAG_DMAC BIT(4)
+#define IGC_FLAG_PTP BIT(8)
#define IGC_FLAG_NEED_LINK_UPDATE BIT(9)
#define IGC_FLAG_MEDIA_RESET BIT(10)
#define IGC_FLAG_MAS_ENABLE BIT(12)
@@ -100,6 +107,20 @@ extern char igc_driver_version[];
#define AUTO_ALL_MODES 0
#define IGC_RX_HDR_LEN IGC_RXBUFFER_256
+/* Transmit and receive latency (for PTP timestamps) */
+/* FIXME: These values were estimated using the ones that i210 has as
+ * basis, they seem to provide good numbers with ptp4l/phc2sys, but we
+ * need to confirm them.
+ */
+#define IGC_I225_TX_LATENCY_10 9542
+#define IGC_I225_TX_LATENCY_100 1024
+#define IGC_I225_TX_LATENCY_1000 178
+#define IGC_I225_TX_LATENCY_2500 64
+#define IGC_I225_RX_LATENCY_10 20662
+#define IGC_I225_RX_LATENCY_100 2213
+#define IGC_I225_RX_LATENCY_1000 448
+#define IGC_I225_RX_LATENCY_2500 160
+
/* RX and TX descriptor control thresholds.
* PTHRESH - MAC will consider prefetch if it has fewer than this number of
* descriptors available in its onboard memory.
@@ -432,6 +453,20 @@ struct igc_adapter {
unsigned long link_check_timeout;
struct igc_info ei;
+
+ struct ptp_clock *ptp_clock;
+ struct ptp_clock_info ptp_caps;
+ struct work_struct ptp_tx_work;
+ struct sk_buff *ptp_tx_skb;
+ struct hwtstamp_config tstamp_config;
+ unsigned long ptp_tx_start;
+ unsigned long last_rx_ptp_check;
+ unsigned long last_rx_timestamp;
+ unsigned int ptp_flags;
+ /* System time value lock */
+ spinlock_t tmreg_lock;
+ struct cyclecounter cc;
+ struct timecounter tc;
};
/* igc_desc_unused - calculate if we have unused descriptors */
@@ -515,6 +550,16 @@ int igc_add_filter(struct igc_adapter *adapter,
int igc_erase_filter(struct igc_adapter *adapter,
struct igc_nfc_filter *input);
+void igc_ptp_init(struct igc_adapter *adapter);
+void igc_ptp_reset(struct igc_adapter *adapter);
+void igc_ptp_stop(struct igc_adapter *adapter);
+void igc_ptp_rx_rgtstamp(struct igc_q_vector *q_vector, struct sk_buff *skb);
+void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va,
+ struct sk_buff *skb);
+int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
+int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
+void igc_ptp_tx_hang(struct igc_adapter *adapter);
+
#define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring))
#define IGC_TXD_DCMD (IGC_ADVTXD_DCMD_EOP | IGC_ADVTXD_DCMD_RS)
diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index db289bc..5a50644 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -212,6 +212,7 @@ static s32 igc_get_invariants_base(struct igc_hw *hw)
case IGC_DEV_ID_I225_I:
case IGC_DEV_ID_I220_V:
case IGC_DEV_ID_I225_K:
+ case IGC_DEV_ID_I225_BLANK_NVM:
mac->type = igc_i225;
break;
default:
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 50dffd5..58efa7a 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -218,6 +218,7 @@
#define IGC_ICR_RXDMT0 BIT(4) /* Rx desc min. threshold (0) */
#define IGC_ICR_RXO BIT(6) /* Rx overrun */
#define IGC_ICR_RXT0 BIT(7) /* Rx timer intr (ring 0) */
+#define IGC_ICR_TS BIT(19) /* Time Sync Interrupt */
#define IGC_ICR_DRSTA BIT(30) /* Device Reset Asserted */
/* If this bit asserted, the driver should claim the interrupt */
@@ -240,6 +241,7 @@
#define IGC_IMS_DRSTA IGC_ICR_DRSTA /* Device Reset Asserted */
#define IGC_IMS_RXT0 IGC_ICR_RXT0 /* Rx timer intr */
#define IGC_IMS_RXDMT0 IGC_ICR_RXDMT0 /* Rx desc min. threshold */
+#define IGC_IMS_TS IGC_ICR_TS /* Time Sync Interrupt */
#define IGC_QVECTOR_MASK 0x7FFC /* Q-vector mask */
#define IGC_ITR_VAL_MASK 0x04 /* ITR value mask */
@@ -280,6 +282,10 @@
#define IGC_TXD_STAT_TC 0x00000004 /* Tx Underrun */
#define IGC_TXD_EXTCMD_TSTAMP 0x00000010 /* IEEE1588 Timestamp packet */
+/* IPSec Encrypt Enable */
+#define IGC_ADVTXD_L4LEN_SHIFT 8 /* Adv ctxt L4LEN shift */
+#define IGC_ADVTXD_MSS_SHIFT 16 /* Adv ctxt MSS shift */
+
/* Transmit Control */
#define IGC_TCTL_EN 0x00000002 /* enable Tx */
#define IGC_TCTL_PSP 0x00000008 /* pad short packets */
@@ -312,12 +318,21 @@
#define IGC_RCTL_RDMTS_HALF 0x00000000 /* Rx desc min thresh size */
#define IGC_RCTL_BAM 0x00008000 /* broadcast enable */
+/* Split Replication Receive Control */
+#define IGC_SRRCTL_TIMESTAMP 0x40000000
+#define IGC_SRRCTL_TIMER1SEL(timer) (((timer) & 0x3) << 14)
+#define IGC_SRRCTL_TIMER0SEL(timer) (((timer) & 0x3) << 17)
+
/* Receive Descriptor bit definitions */
#define IGC_RXD_STAT_EOP 0x02 /* End of Packet */
#define IGC_RXD_STAT_IXSM 0x04 /* Ignore checksum */
#define IGC_RXD_STAT_UDPCS 0x10 /* UDP xsum calculated */
#define IGC_RXD_STAT_TCPCS 0x20 /* TCP xsum calculated */
+/* Advanced Receive Descriptor bit definitions */
+#define IGC_RXDADV_STAT_TSIP 0x08000 /* timestamp in packet */
+#define IGC_RXDADV_STAT_TS 0x10000 /* Pkt was time stamped */
+
#define IGC_RXDEXT_STATERR_CE 0x01000000
#define IGC_RXDEXT_STATERR_SE 0x02000000
#define IGC_RXDEXT_STATERR_SEQ 0x04000000
@@ -354,6 +369,61 @@
#define I225_RXPBSIZE_DEFAULT 0x000000A2 /* RXPBSIZE default */
#define I225_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */
+#define IGC_RXPBS_CFG_TS_EN 0x80000000 /* Timestamp in Rx buffer */
+
+/* Time Sync Interrupt Causes */
+#define IGC_TSICR_SYS_WRAP BIT(0) /* SYSTIM Wrap around. */
+#define IGC_TSICR_TXTS BIT(1) /* Transmit Timestamp. */
+#define IGC_TSICR_TT0 BIT(3) /* Target Time 0 Trigger. */
+#define IGC_TSICR_TT1 BIT(4) /* Target Time 1 Trigger. */
+#define IGC_TSICR_AUTT0 BIT(5) /* Auxiliary Timestamp 0 Taken. */
+#define IGC_TSICR_AUTT1 BIT(6) /* Auxiliary Timestamp 1 Taken. */
+
+#define IGC_TSICR_INTERRUPTS IGC_TSICR_TXTS
+
+/* PTP Queue Filter */
+#define IGC_ETQF_1588 BIT(30)
+
+#define IGC_FTQF_VF_BP 0x00008000
+#define IGC_FTQF_1588_TIME_STAMP 0x08000000
+#define IGC_FTQF_MASK 0xF0000000
+#define IGC_FTQF_MASK_PROTO_BP 0x10000000
+
+/* Time Sync Receive Control bit definitions */
+#define IGC_TSYNCRXCTL_VALID 0x00000001 /* Rx timestamp valid */
+#define IGC_TSYNCRXCTL_TYPE_MASK 0x0000000E /* Rx type mask */
+#define IGC_TSYNCRXCTL_TYPE_L2_V2 0x00
+#define IGC_TSYNCRXCTL_TYPE_L4_V1 0x02
+#define IGC_TSYNCRXCTL_TYPE_L2_L4_V2 0x04
+#define IGC_TSYNCRXCTL_TYPE_ALL 0x08
+#define IGC_TSYNCRXCTL_TYPE_EVENT_V2 0x0A
+#define IGC_TSYNCRXCTL_ENABLED 0x00000010 /* enable Rx timestamping */
+#define IGC_TSYNCRXCTL_SYSCFI 0x00000020 /* Sys clock frequency */
+#define IGC_TSYNCRXCTL_RXSYNSIG 0x00000400 /* Sample RX tstamp in PHY sop */
+
+/* Time Sync Receive Configuration */
+#define IGC_TSYNCRXCFG_PTP_V1_CTRLT_MASK 0x000000FF
+#define IGC_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE 0x00
+#define IGC_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE 0x01
+
+/* Immediate Interrupt Receive */
+#define IGC_IMIR_CLEAR_MASK 0xF001FFFF /* IMIR Reg Clear Mask */
+#define IGC_IMIR_PORT_BYPASS 0x20000 /* IMIR Port Bypass Bit */
+#define IGC_IMIR_PRIORITY_SHIFT 29 /* IMIR Priority Shift */
+#define IGC_IMIREXT_CLEAR_MASK 0x7FFFF /* IMIREXT Reg Clear Mask */
+
+/* Immediate Interrupt Receive Extended */
+#define IGC_IMIREXT_CTRL_BP 0x00080000 /* Bypass check of ctrl bits */
+#define IGC_IMIREXT_SIZE_BP 0x00001000 /* Packet size bypass */
+
+/* Time Sync Transmit Control bit definitions */
+#define IGC_TSYNCTXCTL_VALID 0x00000001 /* Tx timestamp valid */
+#define IGC_TSYNCTXCTL_ENABLED 0x00000010 /* enable Tx timestamping */
+#define IGC_TSYNCTXCTL_MAX_ALLOWED_DLY_MASK 0x0000F000 /* max delay */
+#define IGC_TSYNCTXCTL_SYNC_COMP_ERR 0x20000000 /* sync err */
+#define IGC_TSYNCTXCTL_SYNC_COMP 0x40000000 /* sync complete */
+#define IGC_TSYNCTXCTL_START_SYNC 0x80000000 /* initiate sync */
+#define IGC_TSYNCTXCTL_TXSYNSIG 0x00000020 /* Sample TX tstamp in PHY sop */
/* Receive Checksum Control */
#define IGC_RXCSUM_CRCOFL 0x00000800 /* CRC32 offload enable */
@@ -394,6 +464,7 @@
/* PHY Status Register */
#define MII_SR_LINK_STATUS 0x0004 /* Link Status 1 = link */
#define MII_SR_AUTONEG_COMPLETE 0x0020 /* Auto Neg Complete */
+#define IGC_PHY_RST_COMP 0x0100 /* Internal PHY reset completion */
/* PHY 1000 MII Register/Bit Definitions */
/* PHY Registers defined by IEEE */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 455c1cd..ee07011 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1600,6 +1600,39 @@ static int igc_set_channels(struct net_device *netdev,
return 0;
}
+static int igc_get_ts_info(struct net_device *dev,
+ struct ethtool_ts_info *info)
+{
+ struct igc_adapter *adapter = netdev_priv(dev);
+
+ if (adapter->ptp_clock)
+ info->phc_index = ptp_clock_index(adapter->ptp_clock);
+ else
+ info->phc_index = -1;
+
+ switch (adapter->hw.mac.type) {
+ case igc_i225:
+ info->so_timestamping =
+ SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE |
+ SOF_TIMESTAMPING_TX_HARDWARE |
+ SOF_TIMESTAMPING_RX_HARDWARE |
+ SOF_TIMESTAMPING_RAW_HARDWARE;
+
+ info->tx_types =
+ BIT(HWTSTAMP_TX_OFF) |
+ BIT(HWTSTAMP_TX_ON);
+
+ info->rx_filters = BIT(HWTSTAMP_FILTER_NONE);
+ info->rx_filters |= BIT(HWTSTAMP_FILTER_ALL);
+
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static u32 igc_get_priv_flags(struct net_device *netdev)
{
struct igc_adapter *adapter = netdev_priv(netdev);
@@ -1847,6 +1880,7 @@ static const struct ethtool_ops igc_ethtool_ops = {
.get_rxfh_indir_size = igc_get_rxfh_indir_size,
.get_rxfh = igc_get_rxfh,
.set_rxfh = igc_set_rxfh,
+ .get_ts_info = igc_get_ts_info,
.get_channels = igc_get_channels,
.set_channels = igc_set_channels,
.get_priv_flags = igc_get_priv_flags,
diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h
index 20f7106..90ac0e0 100644
--- a/drivers/net/ethernet/intel/igc/igc_hw.h
+++ b/drivers/net/ethernet/intel/igc/igc_hw.h
@@ -21,8 +21,7 @@
#define IGC_DEV_ID_I225_I 0x15F8
#define IGC_DEV_ID_I220_V 0x15F7
#define IGC_DEV_ID_I225_K 0x3100
-
-#define IGC_FUNC_0 0
+#define IGC_DEV_ID_I225_BLANK_NVM 0x15FD
/* Function pointers for the MAC. */
struct igc_mac_operations {
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 25989c0..d9d5425 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -45,31 +45,13 @@ static const struct pci_device_id igc_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_I), board_base },
{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I220_V), board_base },
{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_K), board_base },
+ { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_BLANK_NVM), board_base },
/* required last entry */
{0, }
};
MODULE_DEVICE_TABLE(pci, igc_pci_tbl);
-/* forward declaration */
-static void igc_clean_tx_ring(struct igc_ring *tx_ring);
-static int igc_sw_init(struct igc_adapter *);
-static void igc_configure(struct igc_adapter *adapter);
-static void igc_power_down_link(struct igc_adapter *adapter);
-static void igc_set_default_mac_filter(struct igc_adapter *adapter);
-static void igc_set_rx_mode(struct net_device *netdev);
-static void igc_write_itr(struct igc_q_vector *q_vector);
-static void igc_assign_vector(struct igc_q_vector *q_vector, int msix_vector);
-static void igc_free_q_vector(struct igc_adapter *adapter, int v_idx);
-static void igc_set_interrupt_capability(struct igc_adapter *adapter,
- bool msix);
-static void igc_free_q_vectors(struct igc_adapter *adapter);
-static void igc_irq_disable(struct igc_adapter *adapter);
-static void igc_irq_enable(struct igc_adapter *adapter);
-static void igc_configure_msix(struct igc_adapter *adapter);
-static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
- struct igc_rx_buffer *bi);
-
enum latency_range {
lowest_latency = 0,
low_latency = 1,
@@ -77,6 +59,16 @@ enum latency_range {
latency_invalid = 255
};
+/**
+ * igc_power_down_link - Power down the phy/serdes link
+ * @adapter: address of board private structure
+ */
+static void igc_power_down_link(struct igc_adapter *adapter)
+{
+ if (adapter->hw.phy.media_type == igc_media_type_copper)
+ igc_power_down_phy_copper_base(&adapter->hw);
+}
+
void igc_reset(struct igc_adapter *adapter)
{
struct pci_dev *pdev = adapter->pdev;
@@ -111,6 +103,9 @@ void igc_reset(struct igc_adapter *adapter)
if (!netif_running(adapter->netdev))
igc_power_down_link(adapter);
+ /* Re-enable PTP, where applicable. */
+ igc_ptp_reset(adapter);
+
igc_get_phy_info(hw);
}
@@ -129,16 +124,6 @@ static void igc_power_up_link(struct igc_adapter *adapter)
}
/**
- * igc_power_down_link - Power down the phy link
- * @adapter: address of board private structure
- */
-static void igc_power_down_link(struct igc_adapter *adapter)
-{
- if (adapter->hw.phy.media_type == igc_media_type_copper)
- igc_power_down_phy_copper_base(&adapter->hw);
-}
-
-/**
* igc_release_hw_control - release control of the h/w to f/w
* @adapter: address of board private structure
*
@@ -177,43 +162,6 @@ static void igc_get_hw_control(struct igc_adapter *adapter)
}
/**
- * igc_free_tx_resources - Free Tx Resources per Queue
- * @tx_ring: Tx descriptor ring for a specific queue
- *
- * Free all transmit software resources
- */
-void igc_free_tx_resources(struct igc_ring *tx_ring)
-{
- igc_clean_tx_ring(tx_ring);
-
- vfree(tx_ring->tx_buffer_info);
- tx_ring->tx_buffer_info = NULL;
-
- /* if not set, then don't free */
- if (!tx_ring->desc)
- return;
-
- dma_free_coherent(tx_ring->dev, tx_ring->size,
- tx_ring->desc, tx_ring->dma);
-
- tx_ring->desc = NULL;
-}
-
-/**
- * igc_free_all_tx_resources - Free Tx Resources for All Queues
- * @adapter: board private structure
- *
- * Free all transmit software resources
- */
-static void igc_free_all_tx_resources(struct igc_adapter *adapter)
-{
- int i;
-
- for (i = 0; i < adapter->num_tx_queues; i++)
- igc_free_tx_resources(adapter->tx_ring[i]);
-}
-
-/**
* igc_clean_tx_ring - Free Tx Buffers
* @tx_ring: ring to be cleaned
*/
@@ -275,6 +223,43 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring)
}
/**
+ * igc_free_tx_resources - Free Tx Resources per Queue
+ * @tx_ring: Tx descriptor ring for a specific queue
+ *
+ * Free all transmit software resources
+ */
+void igc_free_tx_resources(struct igc_ring *tx_ring)
+{
+ igc_clean_tx_ring(tx_ring);
+
+ vfree(tx_ring->tx_buffer_info);
+ tx_ring->tx_buffer_info = NULL;
+
+ /* if not set, then don't free */
+ if (!tx_ring->desc)
+ return;
+
+ dma_free_coherent(tx_ring->dev, tx_ring->size,
+ tx_ring->desc, tx_ring->dma);
+
+ tx_ring->desc = NULL;
+}
+
+/**
+ * igc_free_all_tx_resources - Free Tx Resources for All Queues
+ * @adapter: board private structure
+ *
+ * Free all transmit software resources
+ */
+static void igc_free_all_tx_resources(struct igc_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ igc_free_tx_resources(adapter->tx_ring[i]);
+}
+
+/**
* igc_clean_all_tx_rings - Free Tx Buffers for all queues
* @adapter: board private structure
*/
@@ -772,6 +757,51 @@ static void igc_setup_tctl(struct igc_adapter *adapter)
}
/**
+ * igc_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table
+ * @adapter: address of board private structure
+ * @index: Index of the RAR entry which need to be synced with MAC table
+ */
+static void igc_rar_set_index(struct igc_adapter *adapter, u32 index)
+{
+ u8 *addr = adapter->mac_table[index].addr;
+ struct igc_hw *hw = &adapter->hw;
+ u32 rar_low, rar_high;
+
+ /* HW expects these to be in network order when they are plugged
+ * into the registers which are little endian. In order to guarantee
+ * that ordering we need to do an leXX_to_cpup here in order to be
+ * ready for the byteswap that occurs with writel
+ */
+ rar_low = le32_to_cpup((__le32 *)(addr));
+ rar_high = le16_to_cpup((__le16 *)(addr + 4));
+
+ /* Indicate to hardware the Address is Valid. */
+ if (adapter->mac_table[index].state & IGC_MAC_STATE_IN_USE) {
+ if (is_valid_ether_addr(addr))
+ rar_high |= IGC_RAH_AV;
+
+ rar_high |= IGC_RAH_POOL_1 <<
+ adapter->mac_table[index].queue;
+ }
+
+ wr32(IGC_RAL(index), rar_low);
+ wrfl();
+ wr32(IGC_RAH(index), rar_high);
+ wrfl();
+}
+
+/* Set default MAC address for the PF in the first RAR entry */
+static void igc_set_default_mac_filter(struct igc_adapter *adapter)
+{
+ struct igc_mac_addr *mac_table = &adapter->mac_table[0];
+
+ ether_addr_copy(mac_table->addr, adapter->hw.mac.addr);
+ mac_table->state = IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
+
+ igc_rar_set_index(adapter, 0);
+}
+
+/**
* igc_set_mac - Change the Ethernet Address of the NIC
* @netdev: network interface device structure
* @p: pointer to an address structure
@@ -851,7 +881,7 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring,
/* set bits to identify this as an advanced context descriptor */
type_tucmd |= IGC_TXD_CMD_DEXT | IGC_ADVTXD_DTYP_CTXT;
- /* For 82575, context index must be unique per ring. */
+ /* For i225, context index must be unique per ring. */
if (test_bit(IGC_RING_FLAG_TX_CTX_IDX, &tx_ring->flags))
mss_l4len_idx |= tx_ring->reg_idx << 4;
@@ -958,6 +988,11 @@ static inline int igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size)
return __igc_maybe_stop_tx(tx_ring, size);
}
+#define IGC_SET_FLAG(_input, _flag, _result) \
+ (((_flag) <= (_result)) ? \
+ ((u32)((_input) & (_flag)) * ((_result) / (_flag))) : \
+ ((u32)((_input) & (_flag)) / ((_flag) / (_result))))
+
static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags)
{
/* set type for advanced descriptor with frame checksum insertion */
@@ -965,6 +1000,14 @@ static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags)
IGC_ADVTXD_DCMD_DEXT |
IGC_ADVTXD_DCMD_IFCS;
+ /* set segmentation bits for TSO */
+ cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSO,
+ (IGC_ADVTXD_DCMD_TSE));
+
+ /* set timestamp bit if present */
+ cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP,
+ (IGC_ADVTXD_MAC_TSTAMP));
+
return cmd_type;
}
@@ -1132,6 +1175,100 @@ static int igc_tx_map(struct igc_ring *tx_ring,
return -1;
}
+static int igc_tso(struct igc_ring *tx_ring,
+ struct igc_tx_buffer *first,
+ u8 *hdr_len)
+{
+ u32 vlan_macip_lens, type_tucmd, mss_l4len_idx;
+ struct sk_buff *skb = first->skb;
+ union {
+ struct iphdr *v4;
+ struct ipv6hdr *v6;
+ unsigned char *hdr;
+ } ip;
+ union {
+ struct tcphdr *tcp;
+ struct udphdr *udp;
+ unsigned char *hdr;
+ } l4;
+ u32 paylen, l4_offset;
+ int err;
+
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return 0;
+
+ if (!skb_is_gso(skb))
+ return 0;
+
+ err = skb_cow_head(skb, 0);
+ if (err < 0)
+ return err;
+
+ ip.hdr = skb_network_header(skb);
+ l4.hdr = skb_checksum_start(skb);
+
+ /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
+ type_tucmd = IGC_ADVTXD_TUCMD_L4T_TCP;
+
+ /* initialize outer IP header fields */
+ if (ip.v4->version == 4) {
+ unsigned char *csum_start = skb_checksum_start(skb);
+ unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4);
+
+ /* IP header will have to cancel out any data that
+ * is not a part of the outer IP header
+ */
+ ip.v4->check = csum_fold(csum_partial(trans_start,
+ csum_start - trans_start,
+ 0));
+ type_tucmd |= IGC_ADVTXD_TUCMD_IPV4;
+
+ ip.v4->tot_len = 0;
+ first->tx_flags |= IGC_TX_FLAGS_TSO |
+ IGC_TX_FLAGS_CSUM |
+ IGC_TX_FLAGS_IPV4;
+ } else {
+ ip.v6->payload_len = 0;
+ first->tx_flags |= IGC_TX_FLAGS_TSO |
+ IGC_TX_FLAGS_CSUM;
+ }
+
+ /* determine offset of inner transport header */
+ l4_offset = l4.hdr - skb->data;
+
+ /* remove payload length from inner checksum */
+ paylen = skb->len - l4_offset;
+ if (type_tucmd & IGC_ADVTXD_TUCMD_L4T_TCP) {
+ /* compute length of segmentation header */
+ *hdr_len = (l4.tcp->doff * 4) + l4_offset;
+ csum_replace_by_diff(&l4.tcp->check,
+ (__force __wsum)htonl(paylen));
+ } else {
+ /* compute length of segmentation header */
+ *hdr_len = sizeof(*l4.udp) + l4_offset;
+ csum_replace_by_diff(&l4.udp->check,
+ (__force __wsum)htonl(paylen));
+ }
+
+ /* update gso size and bytecount with header size */
+ first->gso_segs = skb_shinfo(skb)->gso_segs;
+ first->bytecount += (first->gso_segs - 1) * *hdr_len;
+
+ /* MSS L4LEN IDX */
+ mss_l4len_idx = (*hdr_len - l4_offset) << IGC_ADVTXD_L4LEN_SHIFT;
+ mss_l4len_idx |= skb_shinfo(skb)->gso_size << IGC_ADVTXD_MSS_SHIFT;
+
+ /* VLAN MACLEN IPLEN */
+ vlan_macip_lens = l4.hdr - ip.hdr;
+ vlan_macip_lens |= (ip.hdr - skb->data) << IGC_ADVTXD_MACLEN_SHIFT;
+ vlan_macip_lens |= first->tx_flags & IGC_TX_FLAGS_VLAN_MASK;
+
+ igc_tx_ctxtdesc(tx_ring, first, vlan_macip_lens,
+ type_tucmd, mss_l4len_idx);
+
+ return 1;
+}
+
static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
struct igc_ring *tx_ring)
{
@@ -1141,6 +1278,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
u32 tx_flags = 0;
unsigned short f;
u8 hdr_len = 0;
+ int tso = 0;
/* need: 1 descriptor per page * PAGE_SIZE/IGC_MAX_DATA_PER_TXD,
* + 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD,
@@ -1163,15 +1301,45 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
first->bytecount = skb->len;
first->gso_segs = 1;
+ if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
+ struct igc_adapter *adapter = netdev_priv(tx_ring->netdev);
+
+ /* FIXME: add support for retrieving timestamps from
+ * the other timer registers before skipping the
+ * timestamping request.
+ */
+ if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON &&
+ !test_and_set_bit_lock(__IGC_PTP_TX_IN_PROGRESS,
+ &adapter->state)) {
+ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+ tx_flags |= IGC_TX_FLAGS_TSTAMP;
+
+ adapter->ptp_tx_skb = skb_get(skb);
+ adapter->ptp_tx_start = jiffies;
+ } else {
+ adapter->tx_hwtstamp_skipped++;
+ }
+ }
+
/* record initial flags and protocol */
first->tx_flags = tx_flags;
first->protocol = protocol;
- igc_tx_csum(tx_ring, first);
+ tso = igc_tso(tx_ring, first, &hdr_len);
+ if (tso < 0)
+ goto out_drop;
+ else if (!tso)
+ igc_tx_csum(tx_ring, first);
igc_tx_map(tx_ring, first, hdr_len);
return NETDEV_TX_OK;
+
+out_drop:
+ dev_kfree_skb_any(first->skb);
+ first->skb = NULL;
+
+ return NETDEV_TX_OK;
}
static inline struct igc_ring *igc_tx_queue_mapping(struct igc_adapter *adapter,
@@ -1270,6 +1438,10 @@ static void igc_process_skb_fields(struct igc_ring *rx_ring,
igc_rx_checksum(rx_ring, rx_desc, skb);
+ if (igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TS) &&
+ !igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TSIP))
+ igc_ptp_rx_rgtstamp(rx_ring->q_vector, skb);
+
skb_record_rx_queue(skb, rx_ring->queue_index);
skb->protocol = eth_type_trans(skb, rx_ring->netdev);
@@ -1389,6 +1561,12 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
if (unlikely(!skb))
return NULL;
+ if (unlikely(igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TSIP))) {
+ igc_ptp_rx_pktstamp(rx_ring->q_vector, va, skb);
+ va += IGC_TS_HDR_LEN;
+ size -= IGC_TS_HDR_LEN;
+ }
+
/* Determine available headroom for copy */
headlen = size;
if (headlen > IGC_RX_HDR_LEN)
@@ -1565,6 +1743,52 @@ static void igc_put_rx_buffer(struct igc_ring *rx_ring,
rx_buffer->page = NULL;
}
+static inline unsigned int igc_rx_offset(struct igc_ring *rx_ring)
+{
+ return ring_uses_build_skb(rx_ring) ? IGC_SKB_PAD : 0;
+}
+
+static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
+ struct igc_rx_buffer *bi)
+{
+ struct page *page = bi->page;
+ dma_addr_t dma;
+
+ /* since we are recycling buffers we should seldom need to alloc */
+ if (likely(page))
+ return true;
+
+ /* alloc new page for storage */
+ page = dev_alloc_pages(igc_rx_pg_order(rx_ring));
+ if (unlikely(!page)) {
+ rx_ring->rx_stats.alloc_failed++;
+ return false;
+ }
+
+ /* map page for use */
+ dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+ igc_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE,
+ IGC_RX_DMA_ATTR);
+
+ /* if mapping failed free memory back to system since
+ * there isn't much point in holding memory we can't use
+ */
+ if (dma_mapping_error(rx_ring->dev, dma)) {
+ __free_page(page);
+
+ rx_ring->rx_stats.alloc_failed++;
+ return false;
+ }
+
+ bi->dma = dma;
+ bi->page = page;
+ bi->page_offset = igc_rx_offset(rx_ring);
+ bi->pagecnt_bias = 1;
+
+ return true;
+}
+
/**
* igc_alloc_rx_buffers - Replace used receive buffers; packet split
* @rx_ring: rx descriptor ring
@@ -1726,52 +1950,6 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
return total_packets;
}
-static inline unsigned int igc_rx_offset(struct igc_ring *rx_ring)
-{
- return ring_uses_build_skb(rx_ring) ? IGC_SKB_PAD : 0;
-}
-
-static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
- struct igc_rx_buffer *bi)
-{
- struct page *page = bi->page;
- dma_addr_t dma;
-
- /* since we are recycling buffers we should seldom need to alloc */
- if (likely(page))
- return true;
-
- /* alloc new page for storage */
- page = dev_alloc_pages(igc_rx_pg_order(rx_ring));
- if (unlikely(!page)) {
- rx_ring->rx_stats.alloc_failed++;
- return false;
- }
-
- /* map page for use */
- dma = dma_map_page_attrs(rx_ring->dev, page, 0,
- igc_rx_pg_size(rx_ring),
- DMA_FROM_DEVICE,
- IGC_RX_DMA_ATTR);
-
- /* if mapping failed free memory back to system since
- * there isn't much point in holding memory we can't use
- */
- if (dma_mapping_error(rx_ring->dev, dma)) {
- __free_page(page);
-
- rx_ring->rx_stats.alloc_failed++;
- return false;
- }
-
- bi->dma = dma;
- bi->page = page;
- bi->page_offset = igc_rx_offset(rx_ring);
- bi->pagecnt_bias = 1;
-
- return true;
-}
-
/**
* igc_clean_tx_irq - Reclaim resources after transmit completes
* @q_vector: pointer to q_vector containing needed info
@@ -1943,6 +2121,1128 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
return !!budget;
}
+static void igc_nfc_filter_restore(struct igc_adapter *adapter)
+{
+ struct igc_nfc_filter *rule;
+
+ spin_lock(&adapter->nfc_lock);
+
+ hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
+ igc_add_filter(adapter, rule);
+
+ spin_unlock(&adapter->nfc_lock);
+}
+
+/* If the filter to be added and an already existing filter express
+ * the same address and address type, it should be possible to only
+ * override the other configurations, for example the queue to steer
+ * traffic.
+ */
+static bool igc_mac_entry_can_be_used(const struct igc_mac_addr *entry,
+ const u8 *addr, const u8 flags)
+{
+ if (!(entry->state & IGC_MAC_STATE_IN_USE))
+ return true;
+
+ if ((entry->state & IGC_MAC_STATE_SRC_ADDR) !=
+ (flags & IGC_MAC_STATE_SRC_ADDR))
+ return false;
+
+ if (!ether_addr_equal(addr, entry->addr))
+ return false;
+
+ return true;
+}
+
+/* Add a MAC filter for 'addr' directing matching traffic to 'queue',
+ * 'flags' is used to indicate what kind of match is made, match is by
+ * default for the destination address, if matching by source address
+ * is desired the flag IGC_MAC_STATE_SRC_ADDR can be used.
+ */
+static int igc_add_mac_filter(struct igc_adapter *adapter,
+ const u8 *addr, const u8 queue)
+{
+ struct igc_hw *hw = &adapter->hw;
+ int rar_entries = hw->mac.rar_entry_count;
+ int i;
+
+ if (is_zero_ether_addr(addr))
+ return -EINVAL;
+
+ /* Search for the first empty entry in the MAC table.
+ * Do not touch entries at the end of the table reserved for the VF MAC
+ * addresses.
+ */
+ for (i = 0; i < rar_entries; i++) {
+ if (!igc_mac_entry_can_be_used(&adapter->mac_table[i],
+ addr, 0))
+ continue;
+
+ ether_addr_copy(adapter->mac_table[i].addr, addr);
+ adapter->mac_table[i].queue = queue;
+ adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE;
+
+ igc_rar_set_index(adapter, i);
+ return i;
+ }
+
+ return -ENOSPC;
+}
+
+/* Remove a MAC filter for 'addr' directing matching traffic to
+ * 'queue', 'flags' is used to indicate what kind of match need to be
+ * removed, match is by default for the destination address, if
+ * matching by source address is to be removed the flag
+ * IGC_MAC_STATE_SRC_ADDR can be used.
+ */
+static int igc_del_mac_filter(struct igc_adapter *adapter,
+ const u8 *addr, const u8 queue)
+{
+ struct igc_hw *hw = &adapter->hw;
+ int rar_entries = hw->mac.rar_entry_count;
+ int i;
+
+ if (is_zero_ether_addr(addr))
+ return -EINVAL;
+
+ /* Search for matching entry in the MAC table based on given address
+ * and queue. Do not touch entries at the end of the table reserved
+ * for the VF MAC addresses.
+ */
+ for (i = 0; i < rar_entries; i++) {
+ if (!(adapter->mac_table[i].state & IGC_MAC_STATE_IN_USE))
+ continue;
+ if (adapter->mac_table[i].state != 0)
+ continue;
+ if (adapter->mac_table[i].queue != queue)
+ continue;
+ if (!ether_addr_equal(adapter->mac_table[i].addr, addr))
+ continue;
+
+ /* When a filter for the default address is "deleted",
+ * we return it to its initial configuration
+ */
+ if (adapter->mac_table[i].state & IGC_MAC_STATE_DEFAULT) {
+ adapter->mac_table[i].state =
+ IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
+ adapter->mac_table[i].queue = 0;
+ } else {
+ adapter->mac_table[i].state = 0;
+ adapter->mac_table[i].queue = 0;
+ memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
+ }
+
+ igc_rar_set_index(adapter, i);
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ int ret;
+
+ ret = igc_add_mac_filter(adapter, addr, adapter->num_rx_queues);
+
+ return min_t(int, ret, 0);
+}
+
+static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+
+ igc_del_mac_filter(adapter, addr, adapter->num_rx_queues);
+
+ return 0;
+}
+
+/**
+ * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set
+ * @netdev: network interface device structure
+ *
+ * The set_rx_mode entry point is called whenever the unicast or multicast
+ * address lists or the network interface flags are updated. This routine is
+ * responsible for configuring the hardware for proper unicast, multicast,
+ * promiscuous mode, and all-multi behavior.
+ */
+static void igc_set_rx_mode(struct net_device *netdev)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+ u32 rctl = 0, rlpml = MAX_JUMBO_FRAME_SIZE;
+ int count;
+
+ /* Check for Promiscuous and All Multicast modes */
+ if (netdev->flags & IFF_PROMISC) {
+ rctl |= IGC_RCTL_UPE | IGC_RCTL_MPE;
+ } else {
+ if (netdev->flags & IFF_ALLMULTI) {
+ rctl |= IGC_RCTL_MPE;
+ } else {
+ /* Write addresses to the MTA, if the attempt fails
+ * then we should just turn on promiscuous mode so
+ * that we can at least receive multicast traffic
+ */
+ count = igc_write_mc_addr_list(netdev);
+ if (count < 0)
+ rctl |= IGC_RCTL_MPE;
+ }
+ }
+
+ /* Write addresses to available RAR registers, if there is not
+ * sufficient space to store all the addresses then enable
+ * unicast promiscuous mode
+ */
+ if (__dev_uc_sync(netdev, igc_uc_sync, igc_uc_unsync))
+ rctl |= IGC_RCTL_UPE;
+
+ /* update state of unicast and multicast */
+ rctl |= rd32(IGC_RCTL) & ~(IGC_RCTL_UPE | IGC_RCTL_MPE);
+ wr32(IGC_RCTL, rctl);
+
+#if (PAGE_SIZE < 8192)
+ if (adapter->max_frame_size <= IGC_MAX_FRAME_BUILD_SKB)
+ rlpml = IGC_MAX_FRAME_BUILD_SKB;
+#endif
+ wr32(IGC_RLPML, rlpml);
+}
+
+/**
+ * igc_configure - configure the hardware for RX and TX
+ * @adapter: private board structure
+ */
+static void igc_configure(struct igc_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int i = 0;
+
+ igc_get_hw_control(adapter);
+ igc_set_rx_mode(netdev);
+
+ igc_setup_tctl(adapter);
+ igc_setup_mrqc(adapter);
+ igc_setup_rctl(adapter);
+
+ igc_nfc_filter_restore(adapter);
+ igc_configure_tx(adapter);
+ igc_configure_rx(adapter);
+
+ igc_rx_fifo_flush_base(&adapter->hw);
+
+ /* call igc_desc_unused which always leaves
+ * at least 1 descriptor unused to make sure
+ * next_to_use != next_to_clean
+ */
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct igc_ring *ring = adapter->rx_ring[i];
+
+ igc_alloc_rx_buffers(ring, igc_desc_unused(ring));
+ }
+}
+
+/**
+ * igc_write_ivar - configure ivar for given MSI-X vector
+ * @hw: pointer to the HW structure
+ * @msix_vector: vector number we are allocating to a given ring
+ * @index: row index of IVAR register to write within IVAR table
+ * @offset: column offset of in IVAR, should be multiple of 8
+ *
+ * The IVAR table consists of 2 columns,
+ * each containing an cause allocation for an Rx and Tx ring, and a
+ * variable number of rows depending on the number of queues supported.
+ */
+static void igc_write_ivar(struct igc_hw *hw, int msix_vector,
+ int index, int offset)
+{
+ u32 ivar = array_rd32(IGC_IVAR0, index);
+
+ /* clear any bits that are currently set */
+ ivar &= ~((u32)0xFF << offset);
+
+ /* write vector and valid bit */
+ ivar |= (msix_vector | IGC_IVAR_VALID) << offset;
+
+ array_wr32(IGC_IVAR0, index, ivar);
+}
+
+static void igc_assign_vector(struct igc_q_vector *q_vector, int msix_vector)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ struct igc_hw *hw = &adapter->hw;
+ int rx_queue = IGC_N0_QUEUE;
+ int tx_queue = IGC_N0_QUEUE;
+
+ if (q_vector->rx.ring)
+ rx_queue = q_vector->rx.ring->reg_idx;
+ if (q_vector->tx.ring)
+ tx_queue = q_vector->tx.ring->reg_idx;
+
+ switch (hw->mac.type) {
+ case igc_i225:
+ if (rx_queue > IGC_N0_QUEUE)
+ igc_write_ivar(hw, msix_vector,
+ rx_queue >> 1,
+ (rx_queue & 0x1) << 4);
+ if (tx_queue > IGC_N0_QUEUE)
+ igc_write_ivar(hw, msix_vector,
+ tx_queue >> 1,
+ ((tx_queue & 0x1) << 4) + 8);
+ q_vector->eims_value = BIT(msix_vector);
+ break;
+ default:
+ WARN_ONCE(hw->mac.type != igc_i225, "Wrong MAC type\n");
+ break;
+ }
+
+ /* add q_vector eims value to global eims_enable_mask */
+ adapter->eims_enable_mask |= q_vector->eims_value;
+
+ /* configure q_vector to set itr on first interrupt */
+ q_vector->set_itr = 1;
+}
+
+/**
+ * igc_configure_msix - Configure MSI-X hardware
+ * @adapter: Pointer to adapter structure
+ *
+ * igc_configure_msix sets up the hardware to properly
+ * generate MSI-X interrupts.
+ */
+static void igc_configure_msix(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ int i, vector = 0;
+ u32 tmp;
+
+ adapter->eims_enable_mask = 0;
+
+ /* set vector for other causes, i.e. link changes */
+ switch (hw->mac.type) {
+ case igc_i225:
+ /* Turn on MSI-X capability first, or our settings
+ * won't stick. And it will take days to debug.
+ */
+ wr32(IGC_GPIE, IGC_GPIE_MSIX_MODE |
+ IGC_GPIE_PBA | IGC_GPIE_EIAME |
+ IGC_GPIE_NSICR);
+
+ /* enable msix_other interrupt */
+ adapter->eims_other = BIT(vector);
+ tmp = (vector++ | IGC_IVAR_VALID) << 8;
+
+ wr32(IGC_IVAR_MISC, tmp);
+ break;
+ default:
+ /* do nothing, since nothing else supports MSI-X */
+ break;
+ } /* switch (hw->mac.type) */
+
+ adapter->eims_enable_mask |= adapter->eims_other;
+
+ for (i = 0; i < adapter->num_q_vectors; i++)
+ igc_assign_vector(adapter->q_vector[i], vector++);
+
+ wrfl();
+}
+
+/**
+ * igc_irq_enable - Enable default interrupt generation settings
+ * @adapter: board private structure
+ */
+static void igc_irq_enable(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+
+ if (adapter->msix_entries) {
+ u32 ims = IGC_IMS_LSC | IGC_IMS_DOUTSYNC | IGC_IMS_DRSTA;
+ u32 regval = rd32(IGC_EIAC);
+
+ wr32(IGC_EIAC, regval | adapter->eims_enable_mask);
+ regval = rd32(IGC_EIAM);
+ wr32(IGC_EIAM, regval | adapter->eims_enable_mask);
+ wr32(IGC_EIMS, adapter->eims_enable_mask);
+ wr32(IGC_IMS, ims);
+ } else {
+ wr32(IGC_IMS, IMS_ENABLE_MASK | IGC_IMS_DRSTA);
+ wr32(IGC_IAM, IMS_ENABLE_MASK | IGC_IMS_DRSTA);
+ }
+}
+
+/**
+ * igc_irq_disable - Mask off interrupt generation on the NIC
+ * @adapter: board private structure
+ */
+static void igc_irq_disable(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+
+ if (adapter->msix_entries) {
+ u32 regval = rd32(IGC_EIAM);
+
+ wr32(IGC_EIAM, regval & ~adapter->eims_enable_mask);
+ wr32(IGC_EIMC, adapter->eims_enable_mask);
+ regval = rd32(IGC_EIAC);
+ wr32(IGC_EIAC, regval & ~adapter->eims_enable_mask);
+ }
+
+ wr32(IGC_IAM, 0);
+ wr32(IGC_IMC, ~0);
+ wrfl();
+
+ if (adapter->msix_entries) {
+ int vector = 0, i;
+
+ synchronize_irq(adapter->msix_entries[vector++].vector);
+
+ for (i = 0; i < adapter->num_q_vectors; i++)
+ synchronize_irq(adapter->msix_entries[vector++].vector);
+ } else {
+ synchronize_irq(adapter->pdev->irq);
+ }
+}
+
+void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
+ const u32 max_rss_queues)
+{
+ /* Determine if we need to pair queues. */
+ /* If rss_queues > half of max_rss_queues, pair the queues in
+ * order to conserve interrupts due to limited supply.
+ */
+ if (adapter->rss_queues > (max_rss_queues / 2))
+ adapter->flags |= IGC_FLAG_QUEUE_PAIRS;
+ else
+ adapter->flags &= ~IGC_FLAG_QUEUE_PAIRS;
+}
+
+unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter)
+{
+ unsigned int max_rss_queues;
+
+ /* Determine the maximum number of RSS queues supported. */
+ max_rss_queues = IGC_MAX_RX_QUEUES;
+
+ return max_rss_queues;
+}
+
+static void igc_init_queue_configuration(struct igc_adapter *adapter)
+{
+ u32 max_rss_queues;
+
+ max_rss_queues = igc_get_max_rss_queues(adapter);
+ adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus());
+
+ igc_set_flag_queue_pairs(adapter, max_rss_queues);
+}
+
+/**
+ * igc_reset_q_vector - Reset config for interrupt vector
+ * @adapter: board private structure to initialize
+ * @v_idx: Index of vector to be reset
+ *
+ * If NAPI is enabled it will delete any references to the
+ * NAPI struct. This is preparation for igc_free_q_vector.
+ */
+static void igc_reset_q_vector(struct igc_adapter *adapter, int v_idx)
+{
+ struct igc_q_vector *q_vector = adapter->q_vector[v_idx];
+
+ /* if we're coming from igc_set_interrupt_capability, the vectors are
+ * not yet allocated
+ */
+ if (!q_vector)
+ return;
+
+ if (q_vector->tx.ring)
+ adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL;
+
+ if (q_vector->rx.ring)
+ adapter->rx_ring[q_vector->rx.ring->queue_index] = NULL;
+
+ netif_napi_del(&q_vector->napi);
+}
+
+/**
+ * igc_free_q_vector - Free memory allocated for specific interrupt vector
+ * @adapter: board private structure to initialize
+ * @v_idx: Index of vector to be freed
+ *
+ * This function frees the memory allocated to the q_vector.
+ */
+static void igc_free_q_vector(struct igc_adapter *adapter, int v_idx)
+{
+ struct igc_q_vector *q_vector = adapter->q_vector[v_idx];
+
+ adapter->q_vector[v_idx] = NULL;
+
+ /* igc_get_stats64() might access the rings on this vector,
+ * we must wait a grace period before freeing it.
+ */
+ if (q_vector)
+ kfree_rcu(q_vector, rcu);
+}
+
+/**
+ * igc_free_q_vectors - Free memory allocated for interrupt vectors
+ * @adapter: board private structure to initialize
+ *
+ * This function frees the memory allocated to the q_vectors. In addition if
+ * NAPI is enabled it will delete any references to the NAPI struct prior
+ * to freeing the q_vector.
+ */
+static void igc_free_q_vectors(struct igc_adapter *adapter)
+{
+ int v_idx = adapter->num_q_vectors;
+
+ adapter->num_tx_queues = 0;
+ adapter->num_rx_queues = 0;
+ adapter->num_q_vectors = 0;
+
+ while (v_idx--) {
+ igc_reset_q_vector(adapter, v_idx);
+ igc_free_q_vector(adapter, v_idx);
+ }
+}
+
+/**
+ * igc_update_itr - update the dynamic ITR value based on statistics
+ * @q_vector: pointer to q_vector
+ * @ring_container: ring info to update the itr for
+ *
+ * Stores a new ITR value based on packets and byte
+ * counts during the last interrupt. The advantage of per interrupt
+ * computation is faster updates and more accurate ITR for the current
+ * traffic pattern. Constants in this function were computed
+ * based on theoretical maximum wire speed and thresholds were set based
+ * on testing data as well as attempting to minimize response time
+ * while increasing bulk throughput.
+ * NOTE: These calculations are only valid when operating in a single-
+ * queue environment.
+ */
+static void igc_update_itr(struct igc_q_vector *q_vector,
+ struct igc_ring_container *ring_container)
+{
+ unsigned int packets = ring_container->total_packets;
+ unsigned int bytes = ring_container->total_bytes;
+ u8 itrval = ring_container->itr;
+
+ /* no packets, exit with status unchanged */
+ if (packets == 0)
+ return;
+
+ switch (itrval) {
+ case lowest_latency:
+ /* handle TSO and jumbo frames */
+ if (bytes / packets > 8000)
+ itrval = bulk_latency;
+ else if ((packets < 5) && (bytes > 512))
+ itrval = low_latency;
+ break;
+ case low_latency: /* 50 usec aka 20000 ints/s */
+ if (bytes > 10000) {
+ /* this if handles the TSO accounting */
+ if (bytes / packets > 8000)
+ itrval = bulk_latency;
+ else if ((packets < 10) || ((bytes / packets) > 1200))
+ itrval = bulk_latency;
+ else if ((packets > 35))
+ itrval = lowest_latency;
+ } else if (bytes / packets > 2000) {
+ itrval = bulk_latency;
+ } else if (packets <= 2 && bytes < 512) {
+ itrval = lowest_latency;
+ }
+ break;
+ case bulk_latency: /* 250 usec aka 4000 ints/s */
+ if (bytes > 25000) {
+ if (packets > 35)
+ itrval = low_latency;
+ } else if (bytes < 1500) {
+ itrval = low_latency;
+ }
+ break;
+ }
+
+ /* clear work counters since we have the values we need */
+ ring_container->total_bytes = 0;
+ ring_container->total_packets = 0;
+
+ /* write updated itr to ring container */
+ ring_container->itr = itrval;
+}
+
+static void igc_set_itr(struct igc_q_vector *q_vector)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ u32 new_itr = q_vector->itr_val;
+ u8 current_itr = 0;
+
+ /* for non-gigabit speeds, just fix the interrupt rate at 4000 */
+ switch (adapter->link_speed) {
+ case SPEED_10:
+ case SPEED_100:
+ current_itr = 0;
+ new_itr = IGC_4K_ITR;
+ goto set_itr_now;
+ default:
+ break;
+ }
+
+ igc_update_itr(q_vector, &q_vector->tx);
+ igc_update_itr(q_vector, &q_vector->rx);
+
+ current_itr = max(q_vector->rx.itr, q_vector->tx.itr);
+
+ /* conservative mode (itr 3) eliminates the lowest_latency setting */
+ if (current_itr == lowest_latency &&
+ ((q_vector->rx.ring && adapter->rx_itr_setting == 3) ||
+ (!q_vector->rx.ring && adapter->tx_itr_setting == 3)))
+ current_itr = low_latency;
+
+ switch (current_itr) {
+ /* counts and packets in update_itr are dependent on these numbers */
+ case lowest_latency:
+ new_itr = IGC_70K_ITR; /* 70,000 ints/sec */
+ break;
+ case low_latency:
+ new_itr = IGC_20K_ITR; /* 20,000 ints/sec */
+ break;
+ case bulk_latency:
+ new_itr = IGC_4K_ITR; /* 4,000 ints/sec */
+ break;
+ default:
+ break;
+ }
+
+set_itr_now:
+ if (new_itr != q_vector->itr_val) {
+ /* this attempts to bias the interrupt rate towards Bulk
+ * by adding intermediate steps when interrupt rate is
+ * increasing
+ */
+ new_itr = new_itr > q_vector->itr_val ?
+ max((new_itr * q_vector->itr_val) /
+ (new_itr + (q_vector->itr_val >> 2)),
+ new_itr) : new_itr;
+ /* Don't write the value here; it resets the adapter's
+ * internal timer, and causes us to delay far longer than
+ * we should between interrupts. Instead, we write the ITR
+ * value at the beginning of the next interrupt so the timing
+ * ends up being correct.
+ */
+ q_vector->itr_val = new_itr;
+ q_vector->set_itr = 1;
+ }
+}
+
+static void igc_reset_interrupt_capability(struct igc_adapter *adapter)
+{
+ int v_idx = adapter->num_q_vectors;
+
+ if (adapter->msix_entries) {
+ pci_disable_msix(adapter->pdev);
+ kfree(adapter->msix_entries);
+ adapter->msix_entries = NULL;
+ } else if (adapter->flags & IGC_FLAG_HAS_MSI) {
+ pci_disable_msi(adapter->pdev);
+ }
+
+ while (v_idx--)
+ igc_reset_q_vector(adapter, v_idx);
+}
+
+/**
+ * igc_set_interrupt_capability - set MSI or MSI-X if supported
+ * @adapter: Pointer to adapter structure
+ * @msix: boolean value for MSI-X capability
+ *
+ * Attempt to configure interrupts using the best available
+ * capabilities of the hardware and kernel.
+ */
+static void igc_set_interrupt_capability(struct igc_adapter *adapter,
+ bool msix)
+{
+ int numvecs, i;
+ int err;
+
+ if (!msix)
+ goto msi_only;
+ adapter->flags |= IGC_FLAG_HAS_MSIX;
+
+ /* Number of supported queues. */
+ adapter->num_rx_queues = adapter->rss_queues;
+
+ adapter->num_tx_queues = adapter->rss_queues;
+
+ /* start with one vector for every Rx queue */
+ numvecs = adapter->num_rx_queues;
+
+ /* if Tx handler is separate add 1 for every Tx queue */
+ if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS))
+ numvecs += adapter->num_tx_queues;
+
+ /* store the number of vectors reserved for queues */
+ adapter->num_q_vectors = numvecs;
+
+ /* add 1 vector for link status interrupts */
+ numvecs++;
+
+ adapter->msix_entries = kcalloc(numvecs, sizeof(struct msix_entry),
+ GFP_KERNEL);
+
+ if (!adapter->msix_entries)
+ return;
+
+ /* populate entry values */
+ for (i = 0; i < numvecs; i++)
+ adapter->msix_entries[i].entry = i;
+
+ err = pci_enable_msix_range(adapter->pdev,
+ adapter->msix_entries,
+ numvecs,
+ numvecs);
+ if (err > 0)
+ return;
+
+ kfree(adapter->msix_entries);
+ adapter->msix_entries = NULL;
+
+ igc_reset_interrupt_capability(adapter);
+
+msi_only:
+ adapter->flags &= ~IGC_FLAG_HAS_MSIX;
+
+ adapter->rss_queues = 1;
+ adapter->flags |= IGC_FLAG_QUEUE_PAIRS;
+ adapter->num_rx_queues = 1;
+ adapter->num_tx_queues = 1;
+ adapter->num_q_vectors = 1;
+ if (!pci_enable_msi(adapter->pdev))
+ adapter->flags |= IGC_FLAG_HAS_MSI;
+}
+
+/**
+ * igc_update_ring_itr - update the dynamic ITR value based on packet size
+ * @q_vector: pointer to q_vector
+ *
+ * Stores a new ITR value based on strictly on packet size. This
+ * algorithm is less sophisticated than that used in igc_update_itr,
+ * due to the difficulty of synchronizing statistics across multiple
+ * receive rings. The divisors and thresholds used by this function
+ * were determined based on theoretical maximum wire speed and testing
+ * data, in order to minimize response time while increasing bulk
+ * throughput.
+ * NOTE: This function is called only when operating in a multiqueue
+ * receive environment.
+ */
+static void igc_update_ring_itr(struct igc_q_vector *q_vector)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ int new_val = q_vector->itr_val;
+ int avg_wire_size = 0;
+ unsigned int packets;
+
+ /* For non-gigabit speeds, just fix the interrupt rate at 4000
+ * ints/sec - ITR timer value of 120 ticks.
+ */
+ switch (adapter->link_speed) {
+ case SPEED_10:
+ case SPEED_100:
+ new_val = IGC_4K_ITR;
+ goto set_itr_val;
+ default:
+ break;
+ }
+
+ packets = q_vector->rx.total_packets;
+ if (packets)
+ avg_wire_size = q_vector->rx.total_bytes / packets;
+
+ packets = q_vector->tx.total_packets;
+ if (packets)
+ avg_wire_size = max_t(u32, avg_wire_size,
+ q_vector->tx.total_bytes / packets);
+
+ /* if avg_wire_size isn't set no work was done */
+ if (!avg_wire_size)
+ goto clear_counts;
+
+ /* Add 24 bytes to size to account for CRC, preamble, and gap */
+ avg_wire_size += 24;
+
+ /* Don't starve jumbo frames */
+ avg_wire_size = min(avg_wire_size, 3000);
+
+ /* Give a little boost to mid-size frames */
+ if (avg_wire_size > 300 && avg_wire_size < 1200)
+ new_val = avg_wire_size / 3;
+ else
+ new_val = avg_wire_size / 2;
+
+ /* conservative mode (itr 3) eliminates the lowest_latency setting */
+ if (new_val < IGC_20K_ITR &&
+ ((q_vector->rx.ring && adapter->rx_itr_setting == 3) ||
+ (!q_vector->rx.ring && adapter->tx_itr_setting == 3)))
+ new_val = IGC_20K_ITR;
+
+set_itr_val:
+ if (new_val != q_vector->itr_val) {
+ q_vector->itr_val = new_val;
+ q_vector->set_itr = 1;
+ }
+clear_counts:
+ q_vector->rx.total_bytes = 0;
+ q_vector->rx.total_packets = 0;
+ q_vector->tx.total_bytes = 0;
+ q_vector->tx.total_packets = 0;
+}
+
+static void igc_ring_irq_enable(struct igc_q_vector *q_vector)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ struct igc_hw *hw = &adapter->hw;
+
+ if ((q_vector->rx.ring && (adapter->rx_itr_setting & 3)) ||
+ (!q_vector->rx.ring && (adapter->tx_itr_setting & 3))) {
+ if (adapter->num_q_vectors == 1)
+ igc_set_itr(q_vector);
+ else
+ igc_update_ring_itr(q_vector);
+ }
+
+ if (!test_bit(__IGC_DOWN, &adapter->state)) {
+ if (adapter->msix_entries)
+ wr32(IGC_EIMS, q_vector->eims_value);
+ else
+ igc_irq_enable(adapter);
+ }
+}
+
+static void igc_add_ring(struct igc_ring *ring,
+ struct igc_ring_container *head)
+{
+ head->ring = ring;
+ head->count++;
+}
+
+/**
+ * igc_cache_ring_register - Descriptor ring to register mapping
+ * @adapter: board private structure to initialize
+ *
+ * Once we know the feature-set enabled for the device, we'll cache
+ * the register offset the descriptor ring is assigned to.
+ */
+static void igc_cache_ring_register(struct igc_adapter *adapter)
+{
+ int i = 0, j = 0;
+
+ switch (adapter->hw.mac.type) {
+ case igc_i225:
+ /* Fall through */
+ default:
+ for (; i < adapter->num_rx_queues; i++)
+ adapter->rx_ring[i]->reg_idx = i;
+ for (; j < adapter->num_tx_queues; j++)
+ adapter->tx_ring[j]->reg_idx = j;
+ break;
+ }
+}
+
+/**
+ * igc_poll - NAPI Rx polling callback
+ * @napi: napi polling structure
+ * @budget: count of how many packets we should handle
+ */
+static int igc_poll(struct napi_struct *napi, int budget)
+{
+ struct igc_q_vector *q_vector = container_of(napi,
+ struct igc_q_vector,
+ napi);
+ bool clean_complete = true;
+ int work_done = 0;
+
+ if (q_vector->tx.ring)
+ clean_complete = igc_clean_tx_irq(q_vector, budget);
+
+ if (q_vector->rx.ring) {
+ int cleaned = igc_clean_rx_irq(q_vector, budget);
+
+ work_done += cleaned;
+ if (cleaned >= budget)
+ clean_complete = false;
+ }
+
+ /* If all work not completed, return budget and keep polling */
+ if (!clean_complete)
+ return budget;
+
+ /* Exit the polling mode, but don't re-enable interrupts if stack might
+ * poll us due to busy-polling
+ */
+ if (likely(napi_complete_done(napi, work_done)))
+ igc_ring_irq_enable(q_vector);
+
+ return min(work_done, budget - 1);
+}
+
+/**
+ * igc_alloc_q_vector - Allocate memory for a single interrupt vector
+ * @adapter: board private structure to initialize
+ * @v_count: q_vectors allocated on adapter, used for ring interleaving
+ * @v_idx: index of vector in adapter struct
+ * @txr_count: total number of Tx rings to allocate
+ * @txr_idx: index of first Tx ring to allocate
+ * @rxr_count: total number of Rx rings to allocate
+ * @rxr_idx: index of first Rx ring to allocate
+ *
+ * We allocate one q_vector. If allocation fails we return -ENOMEM.
+ */
+static int igc_alloc_q_vector(struct igc_adapter *adapter,
+ unsigned int v_count, unsigned int v_idx,
+ unsigned int txr_count, unsigned int txr_idx,
+ unsigned int rxr_count, unsigned int rxr_idx)
+{
+ struct igc_q_vector *q_vector;
+ struct igc_ring *ring;
+ int ring_count;
+
+ /* igc only supports 1 Tx and/or 1 Rx queue per vector */
+ if (txr_count > 1 || rxr_count > 1)
+ return -ENOMEM;
+
+ ring_count = txr_count + rxr_count;
+
+ /* allocate q_vector and rings */
+ q_vector = adapter->q_vector[v_idx];
+ if (!q_vector)
+ q_vector = kzalloc(struct_size(q_vector, ring, ring_count),
+ GFP_KERNEL);
+ else
+ memset(q_vector, 0, struct_size(q_vector, ring, ring_count));
+ if (!q_vector)
+ return -ENOMEM;
+
+ /* initialize NAPI */
+ netif_napi_add(adapter->netdev, &q_vector->napi,
+ igc_poll, 64);
+
+ /* tie q_vector and adapter together */
+ adapter->q_vector[v_idx] = q_vector;
+ q_vector->adapter = adapter;
+
+ /* initialize work limits */
+ q_vector->tx.work_limit = adapter->tx_work_limit;
+
+ /* initialize ITR configuration */
+ q_vector->itr_register = adapter->io_addr + IGC_EITR(0);
+ q_vector->itr_val = IGC_START_ITR;
+
+ /* initialize pointer to rings */
+ ring = q_vector->ring;
+
+ /* initialize ITR */
+ if (rxr_count) {
+ /* rx or rx/tx vector */
+ if (!adapter->rx_itr_setting || adapter->rx_itr_setting > 3)
+ q_vector->itr_val = adapter->rx_itr_setting;
+ } else {
+ /* tx only vector */
+ if (!adapter->tx_itr_setting || adapter->tx_itr_setting > 3)
+ q_vector->itr_val = adapter->tx_itr_setting;
+ }
+
+ if (txr_count) {
+ /* assign generic ring traits */
+ ring->dev = &adapter->pdev->dev;
+ ring->netdev = adapter->netdev;
+
+ /* configure backlink on ring */
+ ring->q_vector = q_vector;
+
+ /* update q_vector Tx values */
+ igc_add_ring(ring, &q_vector->tx);
+
+ /* apply Tx specific ring traits */
+ ring->count = adapter->tx_ring_count;
+ ring->queue_index = txr_idx;
+
+ /* assign ring to adapter */
+ adapter->tx_ring[txr_idx] = ring;
+
+ /* push pointer to next ring */
+ ring++;
+ }
+
+ if (rxr_count) {
+ /* assign generic ring traits */
+ ring->dev = &adapter->pdev->dev;
+ ring->netdev = adapter->netdev;
+
+ /* configure backlink on ring */
+ ring->q_vector = q_vector;
+
+ /* update q_vector Rx values */
+ igc_add_ring(ring, &q_vector->rx);
+
+ /* apply Rx specific ring traits */
+ ring->count = adapter->rx_ring_count;
+ ring->queue_index = rxr_idx;
+
+ /* assign ring to adapter */
+ adapter->rx_ring[rxr_idx] = ring;
+ }
+
+ return 0;
+}
+
+/**
+ * igc_alloc_q_vectors - Allocate memory for interrupt vectors
+ * @adapter: board private structure to initialize
+ *
+ * We allocate one q_vector per queue interrupt. If allocation fails we
+ * return -ENOMEM.
+ */
+static int igc_alloc_q_vectors(struct igc_adapter *adapter)
+{
+ int rxr_remaining = adapter->num_rx_queues;
+ int txr_remaining = adapter->num_tx_queues;
+ int rxr_idx = 0, txr_idx = 0, v_idx = 0;
+ int q_vectors = adapter->num_q_vectors;
+ int err;
+
+ if (q_vectors >= (rxr_remaining + txr_remaining)) {
+ for (; rxr_remaining; v_idx++) {
+ err = igc_alloc_q_vector(adapter, q_vectors, v_idx,
+ 0, 0, 1, rxr_idx);
+
+ if (err)
+ goto err_out;
+
+ /* update counts and index */
+ rxr_remaining--;
+ rxr_idx++;
+ }
+ }
+
+ for (; v_idx < q_vectors; v_idx++) {
+ int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx);
+ int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx);
+
+ err = igc_alloc_q_vector(adapter, q_vectors, v_idx,
+ tqpv, txr_idx, rqpv, rxr_idx);
+
+ if (err)
+ goto err_out;
+
+ /* update counts and index */
+ rxr_remaining -= rqpv;
+ txr_remaining -= tqpv;
+ rxr_idx++;
+ txr_idx++;
+ }
+
+ return 0;
+
+err_out:
+ adapter->num_tx_queues = 0;
+ adapter->num_rx_queues = 0;
+ adapter->num_q_vectors = 0;
+
+ while (v_idx--)
+ igc_free_q_vector(adapter, v_idx);
+
+ return -ENOMEM;
+}
+
+/**
+ * igc_init_interrupt_scheme - initialize interrupts, allocate queues/vectors
+ * @adapter: Pointer to adapter structure
+ * @msix: boolean for MSI-X capability
+ *
+ * This function initializes the interrupts and allocates all of the queues.
+ */
+static int igc_init_interrupt_scheme(struct igc_adapter *adapter, bool msix)
+{
+ struct pci_dev *pdev = adapter->pdev;
+ int err = 0;
+
+ igc_set_interrupt_capability(adapter, msix);
+
+ err = igc_alloc_q_vectors(adapter);
+ if (err) {
+ dev_err(&pdev->dev, "Unable to allocate memory for vectors\n");
+ goto err_alloc_q_vectors;
+ }
+
+ igc_cache_ring_register(adapter);
+
+ return 0;
+
+err_alloc_q_vectors:
+ igc_reset_interrupt_capability(adapter);
+ return err;
+}
+
+/**
+ * igc_sw_init - Initialize general software structures (struct igc_adapter)
+ * @adapter: board private structure to initialize
+ *
+ * igc_sw_init initializes the Adapter private data structure.
+ * Fields are initialized based on PCI device information and
+ * OS network device settings (MTU size).
+ */
+static int igc_sw_init(struct igc_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct pci_dev *pdev = adapter->pdev;
+ struct igc_hw *hw = &adapter->hw;
+
+ int size = sizeof(struct igc_mac_addr) * hw->mac.rar_entry_count;
+
+ pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
+
+ /* set default ring sizes */
+ adapter->tx_ring_count = IGC_DEFAULT_TXD;
+ adapter->rx_ring_count = IGC_DEFAULT_RXD;
+
+ /* set default ITR values */
+ adapter->rx_itr_setting = IGC_DEFAULT_ITR;
+ adapter->tx_itr_setting = IGC_DEFAULT_ITR;
+
+ /* set default work limits */
+ adapter->tx_work_limit = IGC_DEFAULT_TX_WORK;
+
+ /* adjust max frame to be at least the size of a standard frame */
+ adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN +
+ VLAN_HLEN;
+ adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
+
+ spin_lock_init(&adapter->nfc_lock);
+ spin_lock_init(&adapter->stats64_lock);
+ /* Assume MSI-X interrupts, will be checked during IRQ allocation */
+ adapter->flags |= IGC_FLAG_HAS_MSIX;
+
+ adapter->mac_table = kzalloc(size, GFP_ATOMIC);
+ if (!adapter->mac_table)
+ return -ENOMEM;
+
+ igc_init_queue_configuration(adapter);
+
+ /* This call may decrease the number of queues */
+ if (igc_init_interrupt_scheme(adapter, true)) {
+ dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+ return -ENOMEM;
+ }
+
+ /* Explicitly disable IRQ since the NIC can be in any state. */
+ igc_irq_disable(adapter);
+
+ set_bit(__IGC_DOWN, &adapter->state);
+
+ return 0;
+}
+
/**
* igc_up - Open the interface and prepare it to handle traffic
* @adapter: board private structure
@@ -2164,18 +3464,6 @@ static void igc_nfc_filter_exit(struct igc_adapter *adapter)
spin_unlock(&adapter->nfc_lock);
}
-static void igc_nfc_filter_restore(struct igc_adapter *adapter)
-{
- struct igc_nfc_filter *rule;
-
- spin_lock(&adapter->nfc_lock);
-
- hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
- igc_add_filter(adapter, rule);
-
- spin_unlock(&adapter->nfc_lock);
-}
-
/**
* igc_down - Close the interface
* @adapter: board private structure
@@ -2399,105 +3687,6 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev,
return features;
}
-/**
- * igc_configure - configure the hardware for RX and TX
- * @adapter: private board structure
- */
-static void igc_configure(struct igc_adapter *adapter)
-{
- struct net_device *netdev = adapter->netdev;
- int i = 0;
-
- igc_get_hw_control(adapter);
- igc_set_rx_mode(netdev);
-
- igc_setup_tctl(adapter);
- igc_setup_mrqc(adapter);
- igc_setup_rctl(adapter);
-
- igc_nfc_filter_restore(adapter);
- igc_configure_tx(adapter);
- igc_configure_rx(adapter);
-
- igc_rx_fifo_flush_base(&adapter->hw);
-
- /* call igc_desc_unused which always leaves
- * at least 1 descriptor unused to make sure
- * next_to_use != next_to_clean
- */
- for (i = 0; i < adapter->num_rx_queues; i++) {
- struct igc_ring *ring = adapter->rx_ring[i];
-
- igc_alloc_rx_buffers(ring, igc_desc_unused(ring));
- }
-}
-
-/**
- * igc_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table
- * @adapter: address of board private structure
- * @index: Index of the RAR entry which need to be synced with MAC table
- */
-static void igc_rar_set_index(struct igc_adapter *adapter, u32 index)
-{
- u8 *addr = adapter->mac_table[index].addr;
- struct igc_hw *hw = &adapter->hw;
- u32 rar_low, rar_high;
-
- /* HW expects these to be in network order when they are plugged
- * into the registers which are little endian. In order to guarantee
- * that ordering we need to do an leXX_to_cpup here in order to be
- * ready for the byteswap that occurs with writel
- */
- rar_low = le32_to_cpup((__le32 *)(addr));
- rar_high = le16_to_cpup((__le16 *)(addr + 4));
-
- /* Indicate to hardware the Address is Valid. */
- if (adapter->mac_table[index].state & IGC_MAC_STATE_IN_USE) {
- if (is_valid_ether_addr(addr))
- rar_high |= IGC_RAH_AV;
-
- rar_high |= IGC_RAH_POOL_1 <<
- adapter->mac_table[index].queue;
- }
-
- wr32(IGC_RAL(index), rar_low);
- wrfl();
- wr32(IGC_RAH(index), rar_high);
- wrfl();
-}
-
-/* Set default MAC address for the PF in the first RAR entry */
-static void igc_set_default_mac_filter(struct igc_adapter *adapter)
-{
- struct igc_mac_addr *mac_table = &adapter->mac_table[0];
-
- ether_addr_copy(mac_table->addr, adapter->hw.mac.addr);
- mac_table->state = IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
-
- igc_rar_set_index(adapter, 0);
-}
-
-/* If the filter to be added and an already existing filter express
- * the same address and address type, it should be possible to only
- * override the other configurations, for example the queue to steer
- * traffic.
- */
-static bool igc_mac_entry_can_be_used(const struct igc_mac_addr *entry,
- const u8 *addr, const u8 flags)
-{
- if (!(entry->state & IGC_MAC_STATE_IN_USE))
- return true;
-
- if ((entry->state & IGC_MAC_STATE_SRC_ADDR) !=
- (flags & IGC_MAC_STATE_SRC_ADDR))
- return false;
-
- if (!ether_addr_equal(addr, entry->addr))
- return false;
-
- return true;
-}
-
/* Add a MAC filter for 'addr' directing matching traffic to 'queue',
* 'flags' is used to indicate what kind of match is made, match is by
* default for the destination address, if matching by source address
@@ -2598,159 +3787,20 @@ int igc_del_mac_steering_filter(struct igc_adapter *adapter,
IGC_MAC_STATE_QUEUE_STEERING | flags);
}
-/* Add a MAC filter for 'addr' directing matching traffic to 'queue',
- * 'flags' is used to indicate what kind of match is made, match is by
- * default for the destination address, if matching by source address
- * is desired the flag IGC_MAC_STATE_SRC_ADDR can be used.
- */
-static int igc_add_mac_filter(struct igc_adapter *adapter,
- const u8 *addr, const u8 queue)
+static void igc_tsync_interrupt(struct igc_adapter *adapter)
{
struct igc_hw *hw = &adapter->hw;
- int rar_entries = hw->mac.rar_entry_count;
- int i;
+ u32 tsicr = rd32(IGC_TSICR);
+ u32 ack = 0;
- if (is_zero_ether_addr(addr))
- return -EINVAL;
-
- /* Search for the first empty entry in the MAC table.
- * Do not touch entries at the end of the table reserved for the VF MAC
- * addresses.
- */
- for (i = 0; i < rar_entries; i++) {
- if (!igc_mac_entry_can_be_used(&adapter->mac_table[i],
- addr, 0))
- continue;
-
- ether_addr_copy(adapter->mac_table[i].addr, addr);
- adapter->mac_table[i].queue = queue;
- adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE;
-
- igc_rar_set_index(adapter, i);
- return i;
+ if (tsicr & IGC_TSICR_TXTS) {
+ /* retrieve hardware timestamp */
+ schedule_work(&adapter->ptp_tx_work);
+ ack |= IGC_TSICR_TXTS;
}
- return -ENOSPC;
-}
-
-/* Remove a MAC filter for 'addr' directing matching traffic to
- * 'queue', 'flags' is used to indicate what kind of match need to be
- * removed, match is by default for the destination address, if
- * matching by source address is to be removed the flag
- * IGC_MAC_STATE_SRC_ADDR can be used.
- */
-static int igc_del_mac_filter(struct igc_adapter *adapter,
- const u8 *addr, const u8 queue)
-{
- struct igc_hw *hw = &adapter->hw;
- int rar_entries = hw->mac.rar_entry_count;
- int i;
-
- if (is_zero_ether_addr(addr))
- return -EINVAL;
-
- /* Search for matching entry in the MAC table based on given address
- * and queue. Do not touch entries at the end of the table reserved
- * for the VF MAC addresses.
- */
- for (i = 0; i < rar_entries; i++) {
- if (!(adapter->mac_table[i].state & IGC_MAC_STATE_IN_USE))
- continue;
- if (adapter->mac_table[i].state != 0)
- continue;
- if (adapter->mac_table[i].queue != queue)
- continue;
- if (!ether_addr_equal(adapter->mac_table[i].addr, addr))
- continue;
-
- /* When a filter for the default address is "deleted",
- * we return it to its initial configuration
- */
- if (adapter->mac_table[i].state & IGC_MAC_STATE_DEFAULT) {
- adapter->mac_table[i].state =
- IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
- adapter->mac_table[i].queue = 0;
- } else {
- adapter->mac_table[i].state = 0;
- adapter->mac_table[i].queue = 0;
- memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
- }
-
- igc_rar_set_index(adapter, i);
- return 0;
- }
-
- return -ENOENT;
-}
-
-static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
-{
- struct igc_adapter *adapter = netdev_priv(netdev);
- int ret;
-
- ret = igc_add_mac_filter(adapter, addr, adapter->num_rx_queues);
-
- return min_t(int, ret, 0);
-}
-
-static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
-{
- struct igc_adapter *adapter = netdev_priv(netdev);
-
- igc_del_mac_filter(adapter, addr, adapter->num_rx_queues);
-
- return 0;
-}
-
-/**
- * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set
- * @netdev: network interface device structure
- *
- * The set_rx_mode entry point is called whenever the unicast or multicast
- * address lists or the network interface flags are updated. This routine is
- * responsible for configuring the hardware for proper unicast, multicast,
- * promiscuous mode, and all-multi behavior.
- */
-static void igc_set_rx_mode(struct net_device *netdev)
-{
- struct igc_adapter *adapter = netdev_priv(netdev);
- struct igc_hw *hw = &adapter->hw;
- u32 rctl = 0, rlpml = MAX_JUMBO_FRAME_SIZE;
- int count;
-
- /* Check for Promiscuous and All Multicast modes */
- if (netdev->flags & IFF_PROMISC) {
- rctl |= IGC_RCTL_UPE | IGC_RCTL_MPE;
- } else {
- if (netdev->flags & IFF_ALLMULTI) {
- rctl |= IGC_RCTL_MPE;
- } else {
- /* Write addresses to the MTA, if the attempt fails
- * then we should just turn on promiscuous mode so
- * that we can at least receive multicast traffic
- */
- count = igc_write_mc_addr_list(netdev);
- if (count < 0)
- rctl |= IGC_RCTL_MPE;
- }
- }
-
- /* Write addresses to available RAR registers, if there is not
- * sufficient space to store all the addresses then enable
- * unicast promiscuous mode
- */
- if (__dev_uc_sync(netdev, igc_uc_sync, igc_uc_unsync))
- rctl |= IGC_RCTL_UPE;
-
- /* update state of unicast and multicast */
- rctl |= rd32(IGC_RCTL) & ~(IGC_RCTL_UPE | IGC_RCTL_MPE);
- wr32(IGC_RCTL, rctl);
-
-#if (PAGE_SIZE < 8192)
- if (adapter->max_frame_size <= IGC_MAX_FRAME_BUILD_SKB)
- rlpml = IGC_MAX_FRAME_BUILD_SKB;
-#endif
- wr32(IGC_RLPML, rlpml);
+ /* acknowledge the interrupts */
+ wr32(IGC_TSICR, ack);
}
/**
@@ -2780,114 +3830,28 @@ static irqreturn_t igc_msix_other(int irq, void *data)
mod_timer(&adapter->watchdog_timer, jiffies + 1);
}
+ if (icr & IGC_ICR_TS)
+ igc_tsync_interrupt(adapter);
+
wr32(IGC_EIMS, adapter->eims_other);
return IRQ_HANDLED;
}
-/**
- * igc_write_ivar - configure ivar for given MSI-X vector
- * @hw: pointer to the HW structure
- * @msix_vector: vector number we are allocating to a given ring
- * @index: row index of IVAR register to write within IVAR table
- * @offset: column offset of in IVAR, should be multiple of 8
- *
- * The IVAR table consists of 2 columns,
- * each containing an cause allocation for an Rx and Tx ring, and a
- * variable number of rows depending on the number of queues supported.
- */
-static void igc_write_ivar(struct igc_hw *hw, int msix_vector,
- int index, int offset)
+static void igc_write_itr(struct igc_q_vector *q_vector)
{
- u32 ivar = array_rd32(IGC_IVAR0, index);
+ u32 itr_val = q_vector->itr_val & IGC_QVECTOR_MASK;
- /* clear any bits that are currently set */
- ivar &= ~((u32)0xFF << offset);
+ if (!q_vector->set_itr)
+ return;
- /* write vector and valid bit */
- ivar |= (msix_vector | IGC_IVAR_VALID) << offset;
+ if (!itr_val)
+ itr_val = IGC_ITR_VAL_MASK;
- array_wr32(IGC_IVAR0, index, ivar);
-}
+ itr_val |= IGC_EITR_CNT_IGNR;
-static void igc_assign_vector(struct igc_q_vector *q_vector, int msix_vector)
-{
- struct igc_adapter *adapter = q_vector->adapter;
- struct igc_hw *hw = &adapter->hw;
- int rx_queue = IGC_N0_QUEUE;
- int tx_queue = IGC_N0_QUEUE;
-
- if (q_vector->rx.ring)
- rx_queue = q_vector->rx.ring->reg_idx;
- if (q_vector->tx.ring)
- tx_queue = q_vector->tx.ring->reg_idx;
-
- switch (hw->mac.type) {
- case igc_i225:
- if (rx_queue > IGC_N0_QUEUE)
- igc_write_ivar(hw, msix_vector,
- rx_queue >> 1,
- (rx_queue & 0x1) << 4);
- if (tx_queue > IGC_N0_QUEUE)
- igc_write_ivar(hw, msix_vector,
- tx_queue >> 1,
- ((tx_queue & 0x1) << 4) + 8);
- q_vector->eims_value = BIT(msix_vector);
- break;
- default:
- WARN_ONCE(hw->mac.type != igc_i225, "Wrong MAC type\n");
- break;
- }
-
- /* add q_vector eims value to global eims_enable_mask */
- adapter->eims_enable_mask |= q_vector->eims_value;
-
- /* configure q_vector to set itr on first interrupt */
- q_vector->set_itr = 1;
-}
-
-/**
- * igc_configure_msix - Configure MSI-X hardware
- * @adapter: Pointer to adapter structure
- *
- * igc_configure_msix sets up the hardware to properly
- * generate MSI-X interrupts.
- */
-static void igc_configure_msix(struct igc_adapter *adapter)
-{
- struct igc_hw *hw = &adapter->hw;
- int i, vector = 0;
- u32 tmp;
-
- adapter->eims_enable_mask = 0;
-
- /* set vector for other causes, i.e. link changes */
- switch (hw->mac.type) {
- case igc_i225:
- /* Turn on MSI-X capability first, or our settings
- * won't stick. And it will take days to debug.
- */
- wr32(IGC_GPIE, IGC_GPIE_MSIX_MODE |
- IGC_GPIE_PBA | IGC_GPIE_EIAME |
- IGC_GPIE_NSICR);
-
- /* enable msix_other interrupt */
- adapter->eims_other = BIT(vector);
- tmp = (vector++ | IGC_IVAR_VALID) << 8;
-
- wr32(IGC_IVAR_MISC, tmp);
- break;
- default:
- /* do nothing, since nothing else supports MSI-X */
- break;
- } /* switch (hw->mac.type) */
-
- adapter->eims_enable_mask |= adapter->eims_other;
-
- for (i = 0; i < adapter->num_q_vectors; i++)
- igc_assign_vector(adapter->q_vector[i], vector++);
-
- wrfl();
+ writel(itr_val, q_vector->itr_register);
+ q_vector->set_itr = 0;
}
static irqreturn_t igc_msix_ring(int irq, void *data)
@@ -2962,49 +3926,6 @@ static int igc_request_msix(struct igc_adapter *adapter)
}
/**
- * igc_reset_q_vector - Reset config for interrupt vector
- * @adapter: board private structure to initialize
- * @v_idx: Index of vector to be reset
- *
- * If NAPI is enabled it will delete any references to the
- * NAPI struct. This is preparation for igc_free_q_vector.
- */
-static void igc_reset_q_vector(struct igc_adapter *adapter, int v_idx)
-{
- struct igc_q_vector *q_vector = adapter->q_vector[v_idx];
-
- /* if we're coming from igc_set_interrupt_capability, the vectors are
- * not yet allocated
- */
- if (!q_vector)
- return;
-
- if (q_vector->tx.ring)
- adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL;
-
- if (q_vector->rx.ring)
- adapter->rx_ring[q_vector->rx.ring->queue_index] = NULL;
-
- netif_napi_del(&q_vector->napi);
-}
-
-static void igc_reset_interrupt_capability(struct igc_adapter *adapter)
-{
- int v_idx = adapter->num_q_vectors;
-
- if (adapter->msix_entries) {
- pci_disable_msix(adapter->pdev);
- kfree(adapter->msix_entries);
- adapter->msix_entries = NULL;
- } else if (adapter->flags & IGC_FLAG_HAS_MSI) {
- pci_disable_msi(adapter->pdev);
- }
-
- while (v_idx--)
- igc_reset_q_vector(adapter, v_idx);
-}
-
-/**
* igc_clear_interrupt_scheme - reset the device to a state of no interrupts
* @adapter: Pointer to adapter structure
*
@@ -3017,48 +3938,6 @@ static void igc_clear_interrupt_scheme(struct igc_adapter *adapter)
igc_reset_interrupt_capability(adapter);
}
-/**
- * igc_free_q_vectors - Free memory allocated for interrupt vectors
- * @adapter: board private structure to initialize
- *
- * This function frees the memory allocated to the q_vectors. In addition if
- * NAPI is enabled it will delete any references to the NAPI struct prior
- * to freeing the q_vector.
- */
-static void igc_free_q_vectors(struct igc_adapter *adapter)
-{
- int v_idx = adapter->num_q_vectors;
-
- adapter->num_tx_queues = 0;
- adapter->num_rx_queues = 0;
- adapter->num_q_vectors = 0;
-
- while (v_idx--) {
- igc_reset_q_vector(adapter, v_idx);
- igc_free_q_vector(adapter, v_idx);
- }
-}
-
-/**
- * igc_free_q_vector - Free memory allocated for specific interrupt vector
- * @adapter: board private structure to initialize
- * @v_idx: Index of vector to be freed
- *
- * This function frees the memory allocated to the q_vector.
- */
-static void igc_free_q_vector(struct igc_adapter *adapter, int v_idx)
-{
- struct igc_q_vector *q_vector = adapter->q_vector[v_idx];
-
- adapter->q_vector[v_idx] = NULL;
-
- /* igc_get_stats64() might access the rings on this vector,
- * we must wait a grace period before freeing it.
- */
- if (q_vector)
- kfree_rcu(q_vector, rcu);
-}
-
/* Need to wait a few seconds after link up to get diagnostic information from
* the phy
*/
@@ -3283,6 +4162,8 @@ static void igc_watchdog_task(struct work_struct *work)
wr32(IGC_ICS, IGC_ICS_RXDMT0);
}
+ igc_ptp_tx_hang(adapter);
+
/* Reset the timer */
if (!test_bit(__IGC_DOWN, &adapter->state)) {
if (adapter->flags & IGC_FLAG_NEED_LINK_UPDATE)
@@ -3295,149 +4176,6 @@ static void igc_watchdog_task(struct work_struct *work)
}
/**
- * igc_update_ring_itr - update the dynamic ITR value based on packet size
- * @q_vector: pointer to q_vector
- *
- * Stores a new ITR value based on strictly on packet size. This
- * algorithm is less sophisticated than that used in igc_update_itr,
- * due to the difficulty of synchronizing statistics across multiple
- * receive rings. The divisors and thresholds used by this function
- * were determined based on theoretical maximum wire speed and testing
- * data, in order to minimize response time while increasing bulk
- * throughput.
- * NOTE: This function is called only when operating in a multiqueue
- * receive environment.
- */
-static void igc_update_ring_itr(struct igc_q_vector *q_vector)
-{
- struct igc_adapter *adapter = q_vector->adapter;
- int new_val = q_vector->itr_val;
- int avg_wire_size = 0;
- unsigned int packets;
-
- /* For non-gigabit speeds, just fix the interrupt rate at 4000
- * ints/sec - ITR timer value of 120 ticks.
- */
- switch (adapter->link_speed) {
- case SPEED_10:
- case SPEED_100:
- new_val = IGC_4K_ITR;
- goto set_itr_val;
- default:
- break;
- }
-
- packets = q_vector->rx.total_packets;
- if (packets)
- avg_wire_size = q_vector->rx.total_bytes / packets;
-
- packets = q_vector->tx.total_packets;
- if (packets)
- avg_wire_size = max_t(u32, avg_wire_size,
- q_vector->tx.total_bytes / packets);
-
- /* if avg_wire_size isn't set no work was done */
- if (!avg_wire_size)
- goto clear_counts;
-
- /* Add 24 bytes to size to account for CRC, preamble, and gap */
- avg_wire_size += 24;
-
- /* Don't starve jumbo frames */
- avg_wire_size = min(avg_wire_size, 3000);
-
- /* Give a little boost to mid-size frames */
- if (avg_wire_size > 300 && avg_wire_size < 1200)
- new_val = avg_wire_size / 3;
- else
- new_val = avg_wire_size / 2;
-
- /* conservative mode (itr 3) eliminates the lowest_latency setting */
- if (new_val < IGC_20K_ITR &&
- ((q_vector->rx.ring && adapter->rx_itr_setting == 3) ||
- (!q_vector->rx.ring && adapter->tx_itr_setting == 3)))
- new_val = IGC_20K_ITR;
-
-set_itr_val:
- if (new_val != q_vector->itr_val) {
- q_vector->itr_val = new_val;
- q_vector->set_itr = 1;
- }
-clear_counts:
- q_vector->rx.total_bytes = 0;
- q_vector->rx.total_packets = 0;
- q_vector->tx.total_bytes = 0;
- q_vector->tx.total_packets = 0;
-}
-
-/**
- * igc_update_itr - update the dynamic ITR value based on statistics
- * @q_vector: pointer to q_vector
- * @ring_container: ring info to update the itr for
- *
- * Stores a new ITR value based on packets and byte
- * counts during the last interrupt. The advantage of per interrupt
- * computation is faster updates and more accurate ITR for the current
- * traffic pattern. Constants in this function were computed
- * based on theoretical maximum wire speed and thresholds were set based
- * on testing data as well as attempting to minimize response time
- * while increasing bulk throughput.
- * NOTE: These calculations are only valid when operating in a single-
- * queue environment.
- */
-static void igc_update_itr(struct igc_q_vector *q_vector,
- struct igc_ring_container *ring_container)
-{
- unsigned int packets = ring_container->total_packets;
- unsigned int bytes = ring_container->total_bytes;
- u8 itrval = ring_container->itr;
-
- /* no packets, exit with status unchanged */
- if (packets == 0)
- return;
-
- switch (itrval) {
- case lowest_latency:
- /* handle TSO and jumbo frames */
- if (bytes / packets > 8000)
- itrval = bulk_latency;
- else if ((packets < 5) && (bytes > 512))
- itrval = low_latency;
- break;
- case low_latency: /* 50 usec aka 20000 ints/s */
- if (bytes > 10000) {
- /* this if handles the TSO accounting */
- if (bytes / packets > 8000)
- itrval = bulk_latency;
- else if ((packets < 10) || ((bytes / packets) > 1200))
- itrval = bulk_latency;
- else if ((packets > 35))
- itrval = lowest_latency;
- } else if (bytes / packets > 2000) {
- itrval = bulk_latency;
- } else if (packets <= 2 && bytes < 512) {
- itrval = lowest_latency;
- }
- break;
- case bulk_latency: /* 250 usec aka 4000 ints/s */
- if (bytes > 25000) {
- if (packets > 35)
- itrval = low_latency;
- } else if (bytes < 1500) {
- itrval = low_latency;
- }
- break;
- }
-
- /* clear work counters since we have the values we need */
- ring_container->total_bytes = 0;
- ring_container->total_packets = 0;
-
- /* write updated itr to ring container */
- ring_container->itr = itrval;
-}
-
-/**
* igc_intr_msi - Interrupt Handler
* @irq: interrupt number
* @data: pointer to a network interface device structure
@@ -3514,426 +4252,6 @@ static irqreturn_t igc_intr(int irq, void *data)
return IRQ_HANDLED;
}
-static void igc_set_itr(struct igc_q_vector *q_vector)
-{
- struct igc_adapter *adapter = q_vector->adapter;
- u32 new_itr = q_vector->itr_val;
- u8 current_itr = 0;
-
- /* for non-gigabit speeds, just fix the interrupt rate at 4000 */
- switch (adapter->link_speed) {
- case SPEED_10:
- case SPEED_100:
- current_itr = 0;
- new_itr = IGC_4K_ITR;
- goto set_itr_now;
- default:
- break;
- }
-
- igc_update_itr(q_vector, &q_vector->tx);
- igc_update_itr(q_vector, &q_vector->rx);
-
- current_itr = max(q_vector->rx.itr, q_vector->tx.itr);
-
- /* conservative mode (itr 3) eliminates the lowest_latency setting */
- if (current_itr == lowest_latency &&
- ((q_vector->rx.ring && adapter->rx_itr_setting == 3) ||
- (!q_vector->rx.ring && adapter->tx_itr_setting == 3)))
- current_itr = low_latency;
-
- switch (current_itr) {
- /* counts and packets in update_itr are dependent on these numbers */
- case lowest_latency:
- new_itr = IGC_70K_ITR; /* 70,000 ints/sec */
- break;
- case low_latency:
- new_itr = IGC_20K_ITR; /* 20,000 ints/sec */
- break;
- case bulk_latency:
- new_itr = IGC_4K_ITR; /* 4,000 ints/sec */
- break;
- default:
- break;
- }
-
-set_itr_now:
- if (new_itr != q_vector->itr_val) {
- /* this attempts to bias the interrupt rate towards Bulk
- * by adding intermediate steps when interrupt rate is
- * increasing
- */
- new_itr = new_itr > q_vector->itr_val ?
- max((new_itr * q_vector->itr_val) /
- (new_itr + (q_vector->itr_val >> 2)),
- new_itr) : new_itr;
- /* Don't write the value here; it resets the adapter's
- * internal timer, and causes us to delay far longer than
- * we should between interrupts. Instead, we write the ITR
- * value at the beginning of the next interrupt so the timing
- * ends up being correct.
- */
- q_vector->itr_val = new_itr;
- q_vector->set_itr = 1;
- }
-}
-
-static void igc_ring_irq_enable(struct igc_q_vector *q_vector)
-{
- struct igc_adapter *adapter = q_vector->adapter;
- struct igc_hw *hw = &adapter->hw;
-
- if ((q_vector->rx.ring && (adapter->rx_itr_setting & 3)) ||
- (!q_vector->rx.ring && (adapter->tx_itr_setting & 3))) {
- if (adapter->num_q_vectors == 1)
- igc_set_itr(q_vector);
- else
- igc_update_ring_itr(q_vector);
- }
-
- if (!test_bit(__IGC_DOWN, &adapter->state)) {
- if (adapter->msix_entries)
- wr32(IGC_EIMS, q_vector->eims_value);
- else
- igc_irq_enable(adapter);
- }
-}
-
-/**
- * igc_poll - NAPI Rx polling callback
- * @napi: napi polling structure
- * @budget: count of how many packets we should handle
- */
-static int igc_poll(struct napi_struct *napi, int budget)
-{
- struct igc_q_vector *q_vector = container_of(napi,
- struct igc_q_vector,
- napi);
- bool clean_complete = true;
- int work_done = 0;
-
- if (q_vector->tx.ring)
- clean_complete = igc_clean_tx_irq(q_vector, budget);
-
- if (q_vector->rx.ring) {
- int cleaned = igc_clean_rx_irq(q_vector, budget);
-
- work_done += cleaned;
- if (cleaned >= budget)
- clean_complete = false;
- }
-
- /* If all work not completed, return budget and keep polling */
- if (!clean_complete)
- return budget;
-
- /* Exit the polling mode, but don't re-enable interrupts if stack might
- * poll us due to busy-polling
- */
- if (likely(napi_complete_done(napi, work_done)))
- igc_ring_irq_enable(q_vector);
-
- return min(work_done, budget - 1);
-}
-
-/**
- * igc_set_interrupt_capability - set MSI or MSI-X if supported
- * @adapter: Pointer to adapter structure
- * @msix: boolean value for MSI-X capability
- *
- * Attempt to configure interrupts using the best available
- * capabilities of the hardware and kernel.
- */
-static void igc_set_interrupt_capability(struct igc_adapter *adapter,
- bool msix)
-{
- int numvecs, i;
- int err;
-
- if (!msix)
- goto msi_only;
- adapter->flags |= IGC_FLAG_HAS_MSIX;
-
- /* Number of supported queues. */
- adapter->num_rx_queues = adapter->rss_queues;
-
- adapter->num_tx_queues = adapter->rss_queues;
-
- /* start with one vector for every Rx queue */
- numvecs = adapter->num_rx_queues;
-
- /* if Tx handler is separate add 1 for every Tx queue */
- if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS))
- numvecs += adapter->num_tx_queues;
-
- /* store the number of vectors reserved for queues */
- adapter->num_q_vectors = numvecs;
-
- /* add 1 vector for link status interrupts */
- numvecs++;
-
- adapter->msix_entries = kcalloc(numvecs, sizeof(struct msix_entry),
- GFP_KERNEL);
-
- if (!adapter->msix_entries)
- return;
-
- /* populate entry values */
- for (i = 0; i < numvecs; i++)
- adapter->msix_entries[i].entry = i;
-
- err = pci_enable_msix_range(adapter->pdev,
- adapter->msix_entries,
- numvecs,
- numvecs);
- if (err > 0)
- return;
-
- kfree(adapter->msix_entries);
- adapter->msix_entries = NULL;
-
- igc_reset_interrupt_capability(adapter);
-
-msi_only:
- adapter->flags &= ~IGC_FLAG_HAS_MSIX;
-
- adapter->rss_queues = 1;
- adapter->flags |= IGC_FLAG_QUEUE_PAIRS;
- adapter->num_rx_queues = 1;
- adapter->num_tx_queues = 1;
- adapter->num_q_vectors = 1;
- if (!pci_enable_msi(adapter->pdev))
- adapter->flags |= IGC_FLAG_HAS_MSI;
-}
-
-static void igc_add_ring(struct igc_ring *ring,
- struct igc_ring_container *head)
-{
- head->ring = ring;
- head->count++;
-}
-
-/**
- * igc_alloc_q_vector - Allocate memory for a single interrupt vector
- * @adapter: board private structure to initialize
- * @v_count: q_vectors allocated on adapter, used for ring interleaving
- * @v_idx: index of vector in adapter struct
- * @txr_count: total number of Tx rings to allocate
- * @txr_idx: index of first Tx ring to allocate
- * @rxr_count: total number of Rx rings to allocate
- * @rxr_idx: index of first Rx ring to allocate
- *
- * We allocate one q_vector. If allocation fails we return -ENOMEM.
- */
-static int igc_alloc_q_vector(struct igc_adapter *adapter,
- unsigned int v_count, unsigned int v_idx,
- unsigned int txr_count, unsigned int txr_idx,
- unsigned int rxr_count, unsigned int rxr_idx)
-{
- struct igc_q_vector *q_vector;
- struct igc_ring *ring;
- int ring_count;
-
- /* igc only supports 1 Tx and/or 1 Rx queue per vector */
- if (txr_count > 1 || rxr_count > 1)
- return -ENOMEM;
-
- ring_count = txr_count + rxr_count;
-
- /* allocate q_vector and rings */
- q_vector = adapter->q_vector[v_idx];
- if (!q_vector)
- q_vector = kzalloc(struct_size(q_vector, ring, ring_count),
- GFP_KERNEL);
- else
- memset(q_vector, 0, struct_size(q_vector, ring, ring_count));
- if (!q_vector)
- return -ENOMEM;
-
- /* initialize NAPI */
- netif_napi_add(adapter->netdev, &q_vector->napi,
- igc_poll, 64);
-
- /* tie q_vector and adapter together */
- adapter->q_vector[v_idx] = q_vector;
- q_vector->adapter = adapter;
-
- /* initialize work limits */
- q_vector->tx.work_limit = adapter->tx_work_limit;
-
- /* initialize ITR configuration */
- q_vector->itr_register = adapter->io_addr + IGC_EITR(0);
- q_vector->itr_val = IGC_START_ITR;
-
- /* initialize pointer to rings */
- ring = q_vector->ring;
-
- /* initialize ITR */
- if (rxr_count) {
- /* rx or rx/tx vector */
- if (!adapter->rx_itr_setting || adapter->rx_itr_setting > 3)
- q_vector->itr_val = adapter->rx_itr_setting;
- } else {
- /* tx only vector */
- if (!adapter->tx_itr_setting || adapter->tx_itr_setting > 3)
- q_vector->itr_val = adapter->tx_itr_setting;
- }
-
- if (txr_count) {
- /* assign generic ring traits */
- ring->dev = &adapter->pdev->dev;
- ring->netdev = adapter->netdev;
-
- /* configure backlink on ring */
- ring->q_vector = q_vector;
-
- /* update q_vector Tx values */
- igc_add_ring(ring, &q_vector->tx);
-
- /* apply Tx specific ring traits */
- ring->count = adapter->tx_ring_count;
- ring->queue_index = txr_idx;
-
- /* assign ring to adapter */
- adapter->tx_ring[txr_idx] = ring;
-
- /* push pointer to next ring */
- ring++;
- }
-
- if (rxr_count) {
- /* assign generic ring traits */
- ring->dev = &adapter->pdev->dev;
- ring->netdev = adapter->netdev;
-
- /* configure backlink on ring */
- ring->q_vector = q_vector;
-
- /* update q_vector Rx values */
- igc_add_ring(ring, &q_vector->rx);
-
- /* apply Rx specific ring traits */
- ring->count = adapter->rx_ring_count;
- ring->queue_index = rxr_idx;
-
- /* assign ring to adapter */
- adapter->rx_ring[rxr_idx] = ring;
- }
-
- return 0;
-}
-
-/**
- * igc_alloc_q_vectors - Allocate memory for interrupt vectors
- * @adapter: board private structure to initialize
- *
- * We allocate one q_vector per queue interrupt. If allocation fails we
- * return -ENOMEM.
- */
-static int igc_alloc_q_vectors(struct igc_adapter *adapter)
-{
- int rxr_remaining = adapter->num_rx_queues;
- int txr_remaining = adapter->num_tx_queues;
- int rxr_idx = 0, txr_idx = 0, v_idx = 0;
- int q_vectors = adapter->num_q_vectors;
- int err;
-
- if (q_vectors >= (rxr_remaining + txr_remaining)) {
- for (; rxr_remaining; v_idx++) {
- err = igc_alloc_q_vector(adapter, q_vectors, v_idx,
- 0, 0, 1, rxr_idx);
-
- if (err)
- goto err_out;
-
- /* update counts and index */
- rxr_remaining--;
- rxr_idx++;
- }
- }
-
- for (; v_idx < q_vectors; v_idx++) {
- int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx);
- int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx);
-
- err = igc_alloc_q_vector(adapter, q_vectors, v_idx,
- tqpv, txr_idx, rqpv, rxr_idx);
-
- if (err)
- goto err_out;
-
- /* update counts and index */
- rxr_remaining -= rqpv;
- txr_remaining -= tqpv;
- rxr_idx++;
- txr_idx++;
- }
-
- return 0;
-
-err_out:
- adapter->num_tx_queues = 0;
- adapter->num_rx_queues = 0;
- adapter->num_q_vectors = 0;
-
- while (v_idx--)
- igc_free_q_vector(adapter, v_idx);
-
- return -ENOMEM;
-}
-
-/**
- * igc_cache_ring_register - Descriptor ring to register mapping
- * @adapter: board private structure to initialize
- *
- * Once we know the feature-set enabled for the device, we'll cache
- * the register offset the descriptor ring is assigned to.
- */
-static void igc_cache_ring_register(struct igc_adapter *adapter)
-{
- int i = 0, j = 0;
-
- switch (adapter->hw.mac.type) {
- case igc_i225:
- /* Fall through */
- default:
- for (; i < adapter->num_rx_queues; i++)
- adapter->rx_ring[i]->reg_idx = i;
- for (; j < adapter->num_tx_queues; j++)
- adapter->tx_ring[j]->reg_idx = j;
- break;
- }
-}
-
-/**
- * igc_init_interrupt_scheme - initialize interrupts, allocate queues/vectors
- * @adapter: Pointer to adapter structure
- * @msix: boolean for MSI-X capability
- *
- * This function initializes the interrupts and allocates all of the queues.
- */
-static int igc_init_interrupt_scheme(struct igc_adapter *adapter, bool msix)
-{
- struct pci_dev *pdev = adapter->pdev;
- int err = 0;
-
- igc_set_interrupt_capability(adapter, msix);
-
- err = igc_alloc_q_vectors(adapter);
- if (err) {
- dev_err(&pdev->dev, "Unable to allocate memory for vectors\n");
- goto err_alloc_q_vectors;
- }
-
- igc_cache_ring_register(adapter);
-
- return 0;
-
-err_alloc_q_vectors:
- igc_reset_interrupt_capability(adapter);
- return err;
-}
-
static void igc_free_irq(struct igc_adapter *adapter)
{
if (adapter->msix_entries) {
@@ -3950,62 +4268,6 @@ static void igc_free_irq(struct igc_adapter *adapter)
}
/**
- * igc_irq_disable - Mask off interrupt generation on the NIC
- * @adapter: board private structure
- */
-static void igc_irq_disable(struct igc_adapter *adapter)
-{
- struct igc_hw *hw = &adapter->hw;
-
- if (adapter->msix_entries) {
- u32 regval = rd32(IGC_EIAM);
-
- wr32(IGC_EIAM, regval & ~adapter->eims_enable_mask);
- wr32(IGC_EIMC, adapter->eims_enable_mask);
- regval = rd32(IGC_EIAC);
- wr32(IGC_EIAC, regval & ~adapter->eims_enable_mask);
- }
-
- wr32(IGC_IAM, 0);
- wr32(IGC_IMC, ~0);
- wrfl();
-
- if (adapter->msix_entries) {
- int vector = 0, i;
-
- synchronize_irq(adapter->msix_entries[vector++].vector);
-
- for (i = 0; i < adapter->num_q_vectors; i++)
- synchronize_irq(adapter->msix_entries[vector++].vector);
- } else {
- synchronize_irq(adapter->pdev->irq);
- }
-}
-
-/**
- * igc_irq_enable - Enable default interrupt generation settings
- * @adapter: board private structure
- */
-static void igc_irq_enable(struct igc_adapter *adapter)
-{
- struct igc_hw *hw = &adapter->hw;
-
- if (adapter->msix_entries) {
- u32 ims = IGC_IMS_LSC | IGC_IMS_DOUTSYNC | IGC_IMS_DRSTA;
- u32 regval = rd32(IGC_EIAC);
-
- wr32(IGC_EIAC, regval | adapter->eims_enable_mask);
- regval = rd32(IGC_EIAM);
- wr32(IGC_EIAM, regval | adapter->eims_enable_mask);
- wr32(IGC_EIMS, adapter->eims_enable_mask);
- wr32(IGC_IMS, ims);
- } else {
- wr32(IGC_IMS, IMS_ENABLE_MASK | IGC_IMS_DRSTA);
- wr32(IGC_IAM, IMS_ENABLE_MASK | IGC_IMS_DRSTA);
- }
-}
-
-/**
* igc_request_irq - initialize interrupts
* @adapter: Pointer to adapter structure
*
@@ -4059,22 +4321,6 @@ static int igc_request_irq(struct igc_adapter *adapter)
return err;
}
-static void igc_write_itr(struct igc_q_vector *q_vector)
-{
- u32 itr_val = q_vector->itr_val & IGC_QVECTOR_MASK;
-
- if (!q_vector->set_itr)
- return;
-
- if (!itr_val)
- itr_val = IGC_ITR_VAL_MASK;
-
- itr_val |= IGC_EITR_CNT_IGNR;
-
- writel(itr_val, q_vector->itr_register);
- q_vector->set_itr = 0;
-}
-
/**
* __igc_open - Called when a network interface is made active
* @netdev: network interface device structure
@@ -4204,6 +4450,24 @@ static int igc_close(struct net_device *netdev)
return 0;
}
+/**
+ * igc_ioctl - Access the hwtstamp interface
+ * @netdev: network interface device structure
+ * @ifreq: interface request data
+ * @cmd: ioctl command
+ **/
+static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+{
+ switch (cmd) {
+ case SIOCGHWTSTAMP:
+ return igc_ptp_get_ts_config(netdev, ifr);
+ case SIOCSHWTSTAMP:
+ return igc_ptp_set_ts_config(netdev, ifr);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static const struct net_device_ops igc_netdev_ops = {
.ndo_open = igc_open,
.ndo_stop = igc_close,
@@ -4215,6 +4479,7 @@ static const struct net_device_ops igc_netdev_ops = {
.ndo_fix_features = igc_fix_features,
.ndo_set_features = igc_set_features,
.ndo_features_check = igc_features_check,
+ .ndo_do_ioctl = igc_ioctl,
};
/* PCIe configuration access */
@@ -4433,6 +4698,8 @@ static int igc_probe(struct pci_dev *pdev,
/* Add supported features to the features list*/
netdev->features |= NETIF_F_SG;
+ netdev->features |= NETIF_F_TSO;
+ netdev->features |= NETIF_F_TSO6;
netdev->features |= NETIF_F_RXCSUM;
netdev->features |= NETIF_F_HW_CSUM;
netdev->features |= NETIF_F_SCTP_CRC;
@@ -4515,6 +4782,9 @@ static int igc_probe(struct pci_dev *pdev,
/* carrier off reporting is important to ethtool even BEFORE open */
netif_carrier_off(netdev);
+ /* do hw tstamp init after resetting */
+ igc_ptp_init(adapter);
+
/* Check if Media Autosense is enabled */
adapter->ei = *ei;
@@ -4556,6 +4826,8 @@ static void igc_remove(struct pci_dev *pdev)
struct net_device *netdev = pci_get_drvdata(pdev);
struct igc_adapter *adapter = netdev_priv(netdev);
+ igc_ptp_stop(adapter);
+
set_bit(__IGC_DOWN, &adapter->state);
del_timer_sync(&adapter->watchdog_timer);
@@ -4792,98 +5064,6 @@ static struct pci_driver igc_driver = {
.shutdown = igc_shutdown,
};
-void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
- const u32 max_rss_queues)
-{
- /* Determine if we need to pair queues. */
- /* If rss_queues > half of max_rss_queues, pair the queues in
- * order to conserve interrupts due to limited supply.
- */
- if (adapter->rss_queues > (max_rss_queues / 2))
- adapter->flags |= IGC_FLAG_QUEUE_PAIRS;
- else
- adapter->flags &= ~IGC_FLAG_QUEUE_PAIRS;
-}
-
-unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter)
-{
- unsigned int max_rss_queues;
-
- /* Determine the maximum number of RSS queues supported. */
- max_rss_queues = IGC_MAX_RX_QUEUES;
-
- return max_rss_queues;
-}
-
-static void igc_init_queue_configuration(struct igc_adapter *adapter)
-{
- u32 max_rss_queues;
-
- max_rss_queues = igc_get_max_rss_queues(adapter);
- adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus());
-
- igc_set_flag_queue_pairs(adapter, max_rss_queues);
-}
-
-/**
- * igc_sw_init - Initialize general software structures (struct igc_adapter)
- * @adapter: board private structure to initialize
- *
- * igc_sw_init initializes the Adapter private data structure.
- * Fields are initialized based on PCI device information and
- * OS network device settings (MTU size).
- */
-static int igc_sw_init(struct igc_adapter *adapter)
-{
- struct net_device *netdev = adapter->netdev;
- struct pci_dev *pdev = adapter->pdev;
- struct igc_hw *hw = &adapter->hw;
-
- int size = sizeof(struct igc_mac_addr) * hw->mac.rar_entry_count;
-
- pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
-
- /* set default ring sizes */
- adapter->tx_ring_count = IGC_DEFAULT_TXD;
- adapter->rx_ring_count = IGC_DEFAULT_RXD;
-
- /* set default ITR values */
- adapter->rx_itr_setting = IGC_DEFAULT_ITR;
- adapter->tx_itr_setting = IGC_DEFAULT_ITR;
-
- /* set default work limits */
- adapter->tx_work_limit = IGC_DEFAULT_TX_WORK;
-
- /* adjust max frame to be at least the size of a standard frame */
- adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN +
- VLAN_HLEN;
- adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
-
- spin_lock_init(&adapter->nfc_lock);
- spin_lock_init(&adapter->stats64_lock);
- /* Assume MSI-X interrupts, will be checked during IRQ allocation */
- adapter->flags |= IGC_FLAG_HAS_MSIX;
-
- adapter->mac_table = kzalloc(size, GFP_ATOMIC);
- if (!adapter->mac_table)
- return -ENOMEM;
-
- igc_init_queue_configuration(adapter);
-
- /* This call may decrease the number of queues */
- if (igc_init_interrupt_scheme(adapter, true)) {
- dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
- return -ENOMEM;
- }
-
- /* Explicitly disable IRQ since the NIC can be in any state. */
- igc_irq_disable(adapter);
-
- set_bit(__IGC_DOWN, &adapter->state);
-
- return 0;
-}
-
/**
* igc_reinit_queues - return error
* @adapter: pointer to adapter structure
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index f4b05af..8e17995 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -173,6 +173,7 @@ s32 igc_check_downshift(struct igc_hw *hw)
s32 igc_phy_hw_reset(struct igc_hw *hw)
{
struct igc_phy_info *phy = &hw->phy;
+ u32 phpm = 0, timeout = 10000;
s32 ret_val;
u32 ctrl;
@@ -186,6 +187,8 @@ s32 igc_phy_hw_reset(struct igc_hw *hw)
if (ret_val)
goto out;
+ phpm = rd32(IGC_I225_PHPM);
+
ctrl = rd32(IGC_CTRL);
wr32(IGC_CTRL, ctrl | IGC_CTRL_PHY_RST);
wrfl();
@@ -195,7 +198,18 @@ s32 igc_phy_hw_reset(struct igc_hw *hw)
wr32(IGC_CTRL, ctrl);
wrfl();
- usleep_range(1500, 2000);
+ /* SW should guarantee 100us for the completion of the PHY reset */
+ usleep_range(100, 150);
+ do {
+ phpm = rd32(IGC_I225_PHPM);
+ timeout--;
+ udelay(1);
+ } while (!(phpm & IGC_PHY_RST_COMP) && timeout);
+
+ if (!timeout)
+ hw_dbg("Timeout is expired after a phy reset\n");
+
+ usleep_range(100, 150);
phy->ops.release(hw);
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
new file mode 100644
index 0000000..6935065
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -0,0 +1,716 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Intel Corporation */
+
+#include "igc.h"
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/pci.h>
+#include <linux/ptp_classify.h>
+#include <linux/clocksource.h>
+
+#define INCVALUE_MASK 0x7fffffff
+#define ISGN 0x80000000
+
+#define IGC_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 9)
+#define IGC_PTP_TX_TIMEOUT (HZ * 15)
+
+/* SYSTIM read access for I225 */
+static void igc_ptp_read_i225(struct igc_adapter *adapter,
+ struct timespec64 *ts)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 sec, nsec;
+
+ /* The timestamp latches on lowest register read. For I210/I211, the
+ * lowest register is SYSTIMR. Since we only need to provide nanosecond
+ * resolution, we can ignore it.
+ */
+ rd32(IGC_SYSTIMR);
+ nsec = rd32(IGC_SYSTIML);
+ sec = rd32(IGC_SYSTIMH);
+
+ ts->tv_sec = sec;
+ ts->tv_nsec = nsec;
+}
+
+static void igc_ptp_write_i225(struct igc_adapter *adapter,
+ const struct timespec64 *ts)
+{
+ struct igc_hw *hw = &adapter->hw;
+
+ /* Writing the SYSTIMR register is not necessary as it only
+ * provides sub-nanosecond resolution.
+ */
+ wr32(IGC_SYSTIML, ts->tv_nsec);
+ wr32(IGC_SYSTIMH, ts->tv_sec);
+}
+
+static int igc_ptp_adjfine_i225(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+ struct igc_adapter *igc = container_of(ptp, struct igc_adapter,
+ ptp_caps);
+ struct igc_hw *hw = &igc->hw;
+ int neg_adj = 0;
+ u64 rate;
+ u32 inca;
+
+ if (scaled_ppm < 0) {
+ neg_adj = 1;
+ scaled_ppm = -scaled_ppm;
+ }
+ rate = scaled_ppm;
+ rate <<= 14;
+ rate = div_u64(rate, 78125);
+
+ inca = rate & INCVALUE_MASK;
+ if (neg_adj)
+ inca |= ISGN;
+
+ wr32(IGC_TIMINCA, inca);
+
+ return 0;
+}
+
+static int igc_ptp_adjtime_i225(struct ptp_clock_info *ptp, s64 delta)
+{
+ struct igc_adapter *igc = container_of(ptp, struct igc_adapter,
+ ptp_caps);
+ struct timespec64 now, then = ns_to_timespec64(delta);
+ unsigned long flags;
+
+ spin_lock_irqsave(&igc->tmreg_lock, flags);
+
+ igc_ptp_read_i225(igc, &now);
+ now = timespec64_add(now, then);
+ igc_ptp_write_i225(igc, (const struct timespec64 *)&now);
+
+ spin_unlock_irqrestore(&igc->tmreg_lock, flags);
+
+ return 0;
+}
+
+static int igc_ptp_gettimex64_i225(struct ptp_clock_info *ptp,
+ struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
+{
+ struct igc_adapter *igc = container_of(ptp, struct igc_adapter,
+ ptp_caps);
+ struct igc_hw *hw = &igc->hw;
+ unsigned long flags;
+
+ spin_lock_irqsave(&igc->tmreg_lock, flags);
+
+ ptp_read_system_prets(sts);
+ rd32(IGC_SYSTIMR);
+ ptp_read_system_postts(sts);
+ ts->tv_nsec = rd32(IGC_SYSTIML);
+ ts->tv_sec = rd32(IGC_SYSTIMH);
+
+ spin_unlock_irqrestore(&igc->tmreg_lock, flags);
+
+ return 0;
+}
+
+static int igc_ptp_settime_i225(struct ptp_clock_info *ptp,
+ const struct timespec64 *ts)
+{
+ struct igc_adapter *igc = container_of(ptp, struct igc_adapter,
+ ptp_caps);
+ unsigned long flags;
+
+ spin_lock_irqsave(&igc->tmreg_lock, flags);
+
+ igc_ptp_write_i225(igc, ts);
+
+ spin_unlock_irqrestore(&igc->tmreg_lock, flags);
+
+ return 0;
+}
+
+static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
+ struct ptp_clock_request *rq, int on)
+{
+ return -EOPNOTSUPP;
+}
+
+/**
+ * igc_ptp_systim_to_hwtstamp - convert system time value to HW timestamp
+ * @adapter: board private structure
+ * @hwtstamps: timestamp structure to update
+ * @systim: unsigned 64bit system time value
+ *
+ * We need to convert the system time value stored in the RX/TXSTMP registers
+ * into a hwtstamp which can be used by the upper level timestamping functions.
+ **/
+static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter,
+ struct skb_shared_hwtstamps *hwtstamps,
+ u64 systim)
+{
+ switch (adapter->hw.mac.type) {
+ case igc_i225:
+ memset(hwtstamps, 0, sizeof(*hwtstamps));
+ /* Upper 32 bits contain s, lower 32 bits contain ns. */
+ hwtstamps->hwtstamp = ktime_set(systim >> 32,
+ systim & 0xFFFFFFFF);
+ break;
+ default:
+ break;
+ }
+}
+
+/**
+ * igc_ptp_rx_pktstamp - retrieve Rx per packet timestamp
+ * @q_vector: Pointer to interrupt specific structure
+ * @va: Pointer to address containing Rx buffer
+ * @skb: Buffer containing timestamp and packet
+ *
+ * This function is meant to retrieve the first timestamp from the
+ * first buffer of an incoming frame. The value is stored in little
+ * endian format starting on byte 0. There's a second timestamp
+ * starting on byte 8.
+ **/
+void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va,
+ struct sk_buff *skb)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ __le64 *regval = (__le64 *)va;
+ int adjust = 0;
+
+ /* The timestamp is recorded in little endian format.
+ * DWORD: | 0 | 1 | 2 | 3
+ * Field: | Timer0 Low | Timer0 High | Timer1 Low | Timer1 High
+ */
+ igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb),
+ le64_to_cpu(regval[0]));
+
+ /* adjust timestamp for the RX latency based on link speed */
+ if (adapter->hw.mac.type == igc_i225) {
+ switch (adapter->link_speed) {
+ case SPEED_10:
+ adjust = IGC_I225_RX_LATENCY_10;
+ break;
+ case SPEED_100:
+ adjust = IGC_I225_RX_LATENCY_100;
+ break;
+ case SPEED_1000:
+ adjust = IGC_I225_RX_LATENCY_1000;
+ break;
+ case SPEED_2500:
+ adjust = IGC_I225_RX_LATENCY_2500;
+ break;
+ }
+ }
+ skb_hwtstamps(skb)->hwtstamp =
+ ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);
+}
+
+/**
+ * igc_ptp_rx_rgtstamp - retrieve Rx timestamp stored in register
+ * @q_vector: Pointer to interrupt specific structure
+ * @skb: Buffer containing timestamp and packet
+ *
+ * This function is meant to retrieve a timestamp from the internal registers
+ * of the adapter and store it in the skb.
+ */
+void igc_ptp_rx_rgtstamp(struct igc_q_vector *q_vector,
+ struct sk_buff *skb)
+{
+ struct igc_adapter *adapter = q_vector->adapter;
+ struct igc_hw *hw = &adapter->hw;
+ u64 regval;
+
+ /* If this bit is set, then the RX registers contain the time
+ * stamp. No other packet will be time stamped until we read
+ * these registers, so read the registers to make them
+ * available again. Because only one packet can be time
+ * stamped at a time, we know that the register values must
+ * belong to this one here and therefore we don't need to
+ * compare any of the additional attributes stored for it.
+ *
+ * If nothing went wrong, then it should have a shared
+ * tx_flags that we can turn into a skb_shared_hwtstamps.
+ */
+ if (!(rd32(IGC_TSYNCRXCTL) & IGC_TSYNCRXCTL_VALID))
+ return;
+
+ regval = rd32(IGC_RXSTMPL);
+ regval |= (u64)rd32(IGC_RXSTMPH) << 32;
+
+ igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval);
+
+ /* Update the last_rx_timestamp timer in order to enable watchdog check
+ * for error case of latched timestamp on a dropped packet.
+ */
+ adapter->last_rx_timestamp = jiffies;
+}
+
+/**
+ * igc_ptp_enable_tstamp_rxqueue - Enable RX timestamp for a queue
+ * @rx_ring: Pointer to RX queue
+ * @timer: Index for timer
+ *
+ * This function enables RX timestamping for a queue, and selects
+ * which 1588 timer will provide the timestamp.
+ */
+static void igc_ptp_enable_tstamp_rxqueue(struct igc_adapter *adapter,
+ struct igc_ring *rx_ring, u8 timer)
+{
+ struct igc_hw *hw = &adapter->hw;
+ int reg_idx = rx_ring->reg_idx;
+ u32 srrctl = rd32(IGC_SRRCTL(reg_idx));
+
+ srrctl |= IGC_SRRCTL_TIMESTAMP;
+ srrctl |= IGC_SRRCTL_TIMER1SEL(timer);
+ srrctl |= IGC_SRRCTL_TIMER0SEL(timer);
+
+ wr32(IGC_SRRCTL(reg_idx), srrctl);
+}
+
+static void igc_ptp_enable_tstamp_all_rxqueues(struct igc_adapter *adapter,
+ u8 timer)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct igc_ring *ring = adapter->rx_ring[i];
+
+ igc_ptp_enable_tstamp_rxqueue(adapter, ring, timer);
+ }
+}
+
+/**
+ * igc_ptp_set_timestamp_mode - setup hardware for timestamping
+ * @adapter: networking device structure
+ * @config: hwtstamp configuration
+ *
+ * Outgoing time stamping can be enabled and disabled. Play nice and
+ * disable it when requested, although it shouldn't case any overhead
+ * when no packet needs it. At most one packet in the queue may be
+ * marked for time stamping, otherwise it would be impossible to tell
+ * for sure to which packet the hardware time stamp belongs.
+ *
+ * Incoming time stamping has to be configured via the hardware
+ * filters. Not all combinations are supported, in particular event
+ * type has to be specified. Matching the kind of event packet is
+ * not supported, with the exception of "all V2 events regardless of
+ * level 2 or 4".
+ *
+ */
+static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter,
+ struct hwtstamp_config *config)
+{
+ u32 tsync_tx_ctl = IGC_TSYNCTXCTL_ENABLED;
+ u32 tsync_rx_ctl = IGC_TSYNCRXCTL_ENABLED;
+ struct igc_hw *hw = &adapter->hw;
+ u32 tsync_rx_cfg = 0;
+ bool is_l4 = false;
+ bool is_l2 = false;
+ u32 regval;
+
+ /* reserved for future extensions */
+ if (config->flags)
+ return -EINVAL;
+
+ switch (config->tx_type) {
+ case HWTSTAMP_TX_OFF:
+ tsync_tx_ctl = 0;
+ case HWTSTAMP_TX_ON:
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ switch (config->rx_filter) {
+ case HWTSTAMP_FILTER_NONE:
+ tsync_rx_ctl = 0;
+ break;
+ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+ tsync_rx_ctl |= IGC_TSYNCRXCTL_TYPE_L4_V1;
+ tsync_rx_cfg = IGC_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE;
+ is_l4 = true;
+ break;
+ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+ tsync_rx_ctl |= IGC_TSYNCRXCTL_TYPE_L4_V1;
+ tsync_rx_cfg = IGC_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE;
+ is_l4 = true;
+ break;
+ case HWTSTAMP_FILTER_PTP_V2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+ tsync_rx_ctl |= IGC_TSYNCRXCTL_TYPE_EVENT_V2;
+ config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+ is_l2 = true;
+ is_l4 = true;
+ break;
+ case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+ case HWTSTAMP_FILTER_NTP_ALL:
+ case HWTSTAMP_FILTER_ALL:
+ tsync_rx_ctl |= IGC_TSYNCRXCTL_TYPE_ALL;
+ config->rx_filter = HWTSTAMP_FILTER_ALL;
+ break;
+ /* fall through */
+ default:
+ config->rx_filter = HWTSTAMP_FILTER_NONE;
+ return -ERANGE;
+ }
+
+ /* Per-packet timestamping only works if all packets are
+ * timestamped, so enable timestamping in all packets as long
+ * as one Rx filter was configured.
+ */
+ if (tsync_rx_ctl) {
+ tsync_rx_ctl = IGC_TSYNCRXCTL_ENABLED;
+ tsync_rx_ctl |= IGC_TSYNCRXCTL_TYPE_ALL;
+ tsync_rx_ctl |= IGC_TSYNCRXCTL_RXSYNSIG;
+ config->rx_filter = HWTSTAMP_FILTER_ALL;
+ is_l2 = true;
+ is_l4 = true;
+
+ if (hw->mac.type == igc_i225) {
+ regval = rd32(IGC_RXPBS);
+ regval |= IGC_RXPBS_CFG_TS_EN;
+ wr32(IGC_RXPBS, regval);
+
+ /* FIXME: For now, only support retrieving RX
+ * timestamps from timer 0
+ */
+ igc_ptp_enable_tstamp_all_rxqueues(adapter, 0);
+ }
+ }
+
+ if (tsync_tx_ctl) {
+ tsync_tx_ctl = IGC_TSYNCTXCTL_ENABLED;
+ tsync_tx_ctl |= IGC_TSYNCTXCTL_TXSYNSIG;
+ }
+
+ /* enable/disable TX */
+ regval = rd32(IGC_TSYNCTXCTL);
+ regval &= ~IGC_TSYNCTXCTL_ENABLED;
+ regval |= tsync_tx_ctl;
+ wr32(IGC_TSYNCTXCTL, regval);
+
+ /* enable/disable RX */
+ regval = rd32(IGC_TSYNCRXCTL);
+ regval &= ~(IGC_TSYNCRXCTL_ENABLED | IGC_TSYNCRXCTL_TYPE_MASK);
+ regval |= tsync_rx_ctl;
+ wr32(IGC_TSYNCRXCTL, regval);
+
+ /* define which PTP packets are time stamped */
+ wr32(IGC_TSYNCRXCFG, tsync_rx_cfg);
+
+ /* define ethertype filter for timestamped packets */
+ if (is_l2)
+ wr32(IGC_ETQF(3),
+ (IGC_ETQF_FILTER_ENABLE | /* enable filter */
+ IGC_ETQF_1588 | /* enable timestamping */
+ ETH_P_1588)); /* 1588 eth protocol type */
+ else
+ wr32(IGC_ETQF(3), 0);
+
+ /* L4 Queue Filter[3]: filter by destination port and protocol */
+ if (is_l4) {
+ u32 ftqf = (IPPROTO_UDP /* UDP */
+ | IGC_FTQF_VF_BP /* VF not compared */
+ | IGC_FTQF_1588_TIME_STAMP /* Enable Timestamp */
+ | IGC_FTQF_MASK); /* mask all inputs */
+ ftqf &= ~IGC_FTQF_MASK_PROTO_BP; /* enable protocol check */
+
+ wr32(IGC_IMIR(3), htons(PTP_EV_PORT));
+ wr32(IGC_IMIREXT(3),
+ (IGC_IMIREXT_SIZE_BP | IGC_IMIREXT_CTRL_BP));
+ wr32(IGC_FTQF(3), ftqf);
+ } else {
+ wr32(IGC_FTQF(3), IGC_FTQF_MASK);
+ }
+ wrfl();
+
+ /* clear TX/RX time stamp registers, just to be sure */
+ regval = rd32(IGC_TXSTMPL);
+ regval = rd32(IGC_TXSTMPH);
+ regval = rd32(IGC_RXSTMPL);
+ regval = rd32(IGC_RXSTMPH);
+
+ return 0;
+}
+
+void igc_ptp_tx_hang(struct igc_adapter *adapter)
+{
+ bool timeout = time_is_before_jiffies(adapter->ptp_tx_start +
+ IGC_PTP_TX_TIMEOUT);
+ struct igc_hw *hw = &adapter->hw;
+
+ if (!adapter->ptp_tx_skb)
+ return;
+
+ if (!test_bit(__IGC_PTP_TX_IN_PROGRESS, &adapter->state))
+ return;
+
+ /* If we haven't received a timestamp within the timeout, it is
+ * reasonable to assume that it will never occur, so we can unlock the
+ * timestamp bit when this occurs.
+ */
+ if (timeout) {
+ cancel_work_sync(&adapter->ptp_tx_work);
+ dev_kfree_skb_any(adapter->ptp_tx_skb);
+ adapter->ptp_tx_skb = NULL;
+ clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state);
+ adapter->tx_hwtstamp_timeouts++;
+ /* Clear the Tx valid bit in TSYNCTXCTL register to enable
+ * interrupt
+ */
+ rd32(IGC_TXSTMPH);
+ dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n");
+ }
+}
+
+/**
+ * igc_ptp_tx_hwtstamp - utility function which checks for TX time stamp
+ * @adapter: Board private structure
+ *
+ * If we were asked to do hardware stamping and such a time stamp is
+ * available, then it must have been for this skb here because we only
+ * allow only one such packet into the queue.
+ */
+static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter)
+{
+ struct sk_buff *skb = adapter->ptp_tx_skb;
+ struct skb_shared_hwtstamps shhwtstamps;
+ struct igc_hw *hw = &adapter->hw;
+ u64 regval;
+
+ regval = rd32(IGC_TXSTMPL);
+ regval |= (u64)rd32(IGC_TXSTMPH) << 32;
+ igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval);
+
+ /* Clear the lock early before calling skb_tstamp_tx so that
+ * applications are not woken up before the lock bit is clear. We use
+ * a copy of the skb pointer to ensure other threads can't change it
+ * while we're notifying the stack.
+ */
+ adapter->ptp_tx_skb = NULL;
+ clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state);
+
+ /* Notify the stack and free the skb after we've unlocked */
+ skb_tstamp_tx(skb, &shhwtstamps);
+ dev_kfree_skb_any(skb);
+}
+
+/**
+ * igc_ptp_tx_work
+ * @work: pointer to work struct
+ *
+ * This work function polls the TSYNCTXCTL valid bit to determine when a
+ * timestamp has been taken for the current stored skb.
+ */
+void igc_ptp_tx_work(struct work_struct *work)
+{
+ struct igc_adapter *adapter = container_of(work, struct igc_adapter,
+ ptp_tx_work);
+ struct igc_hw *hw = &adapter->hw;
+ u32 tsynctxctl;
+
+ if (!adapter->ptp_tx_skb)
+ return;
+
+ if (time_is_before_jiffies(adapter->ptp_tx_start +
+ IGC_PTP_TX_TIMEOUT)) {
+ dev_kfree_skb_any(adapter->ptp_tx_skb);
+ adapter->ptp_tx_skb = NULL;
+ clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state);
+ adapter->tx_hwtstamp_timeouts++;
+ /* Clear the tx valid bit in TSYNCTXCTL register to enable
+ * interrupt
+ */
+ rd32(IGC_TXSTMPH);
+ dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n");
+ return;
+ }
+
+ tsynctxctl = rd32(IGC_TSYNCTXCTL);
+ if (tsynctxctl & IGC_TSYNCTXCTL_VALID)
+ igc_ptp_tx_hwtstamp(adapter);
+ else
+ /* reschedule to check later */
+ schedule_work(&adapter->ptp_tx_work);
+}
+
+/**
+ * igc_ptp_set_ts_config - set hardware time stamping config
+ * @netdev: network interface device structure
+ * @ifreq: interface request data
+ *
+ **/
+int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct hwtstamp_config config;
+ int err;
+
+ if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+ return -EFAULT;
+
+ err = igc_ptp_set_timestamp_mode(adapter, &config);
+ if (err)
+ return err;
+
+ /* save these settings for future reference */
+ memcpy(&adapter->tstamp_config, &config,
+ sizeof(adapter->tstamp_config));
+
+ return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+ -EFAULT : 0;
+}
+
+/**
+ * igc_ptp_get_ts_config - get hardware time stamping config
+ * @netdev: network interface device structure
+ * @ifreq: interface request data
+ *
+ * Get the hwtstamp_config settings to return to the user. Rather than attempt
+ * to deconstruct the settings from the registers, just return a shadow copy
+ * of the last known settings.
+ **/
+int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct hwtstamp_config *config = &adapter->tstamp_config;
+
+ return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
+ -EFAULT : 0;
+}
+
+/**
+ * igc_ptp_init - Initialize PTP functionality
+ * @adapter: Board private structure
+ *
+ * This function is called at device probe to initialize the PTP
+ * functionality.
+ */
+void igc_ptp_init(struct igc_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct igc_hw *hw = &adapter->hw;
+
+ switch (hw->mac.type) {
+ case igc_i225:
+ snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr);
+ adapter->ptp_caps.owner = THIS_MODULE;
+ adapter->ptp_caps.max_adj = 62499999;
+ adapter->ptp_caps.adjfine = igc_ptp_adjfine_i225;
+ adapter->ptp_caps.adjtime = igc_ptp_adjtime_i225;
+ adapter->ptp_caps.gettimex64 = igc_ptp_gettimex64_i225;
+ adapter->ptp_caps.settime64 = igc_ptp_settime_i225;
+ adapter->ptp_caps.enable = igc_ptp_feature_enable_i225;
+ break;
+ default:
+ adapter->ptp_clock = NULL;
+ return;
+ }
+
+ spin_lock_init(&adapter->tmreg_lock);
+ INIT_WORK(&adapter->ptp_tx_work, igc_ptp_tx_work);
+
+ adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+ adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
+
+ igc_ptp_reset(adapter);
+
+ adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
+ &adapter->pdev->dev);
+ if (IS_ERR(adapter->ptp_clock)) {
+ adapter->ptp_clock = NULL;
+ dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n");
+ } else if (adapter->ptp_clock) {
+ dev_info(&adapter->pdev->dev, "added PHC on %s\n",
+ adapter->netdev->name);
+ adapter->ptp_flags |= IGC_PTP_ENABLED;
+ }
+}
+
+/**
+ * igc_ptp_suspend - Disable PTP work items and prepare for suspend
+ * @adapter: Board private structure
+ *
+ * This function stops the overflow check work and PTP Tx timestamp work, and
+ * will prepare the device for OS suspend.
+ */
+void igc_ptp_suspend(struct igc_adapter *adapter)
+{
+ if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+ return;
+
+ cancel_work_sync(&adapter->ptp_tx_work);
+ if (adapter->ptp_tx_skb) {
+ dev_kfree_skb_any(adapter->ptp_tx_skb);
+ adapter->ptp_tx_skb = NULL;
+ clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state);
+ }
+}
+
+/**
+ * igc_ptp_stop - Disable PTP device and stop the overflow check.
+ * @adapter: Board private structure.
+ *
+ * This function stops the PTP support and cancels the delayed work.
+ **/
+void igc_ptp_stop(struct igc_adapter *adapter)
+{
+ igc_ptp_suspend(adapter);
+
+ if (adapter->ptp_clock) {
+ ptp_clock_unregister(adapter->ptp_clock);
+ dev_info(&adapter->pdev->dev, "removed PHC on %s\n",
+ adapter->netdev->name);
+ adapter->ptp_flags &= ~IGC_PTP_ENABLED;
+ }
+}
+
+/**
+ * igc_ptp_reset - Re-enable the adapter for PTP following a reset.
+ * @adapter: Board private structure.
+ *
+ * This function handles the reset work required to re-enable the PTP device.
+ **/
+void igc_ptp_reset(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ unsigned long flags;
+
+ /* reset the tstamp_config */
+ igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
+
+ spin_lock_irqsave(&adapter->tmreg_lock, flags);
+
+ switch (adapter->hw.mac.type) {
+ case igc_i225:
+ wr32(IGC_TSAUXC, 0x0);
+ wr32(IGC_TSSDP, 0x0);
+ wr32(IGC_TSIM, IGC_TSICR_INTERRUPTS);
+ wr32(IGC_IMS, IGC_IMS_TS);
+ break;
+ default:
+ /* No work to do. */
+ goto out;
+ }
+
+ /* Re-initialize the timer. */
+ if (hw->mac.type == igc_i225) {
+ struct timespec64 ts64 = ktime_to_timespec64(ktime_get_real());
+
+ igc_ptp_write_i225(adapter, &ts64);
+ } else {
+ timecounter_init(&adapter->tc, &adapter->cc,
+ ktime_to_ns(ktime_get_real()));
+ }
+out:
+ spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+
+ wrfl();
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 93a9139..c9029b5 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -12,6 +12,7 @@
#define IGC_MDIC 0x00020 /* MDI Control - RW */
#define IGC_MDICNFG 0x00E04 /* MDC/MDIO Configuration - RW */
#define IGC_CONNSW 0x00034 /* Copper/Fiber switch control - RW */
+#define IGC_I225_PHPM 0x00E14 /* I225 PHY Power Management */
/* Internal Packet Buffer Size Registers */
#define IGC_RXPBS 0x02404 /* Rx Packet Buffer Size - RW */
@@ -209,6 +210,33 @@
#define IGC_LENERRS 0x04138 /* Length Errors Count */
#define IGC_HRMPC 0x0A018 /* Header Redirection Missed Packet Count */
+/* Time sync registers */
+#define IGC_TSICR 0x0B66C /* Time Sync Interrupt Cause */
+#define IGC_TSIM 0x0B674 /* Time Sync Interrupt Mask Register */
+#define IGC_TSAUXC 0x0B640 /* Timesync Auxiliary Control register */
+#define IGC_TSYNCRXCTL 0x0B620 /* Rx Time Sync Control register - RW */
+#define IGC_TSYNCTXCTL 0x0B614 /* Tx Time Sync Control register - RW */
+#define IGC_TSYNCRXCFG 0x05F50 /* Time Sync Rx Configuration - RW */
+#define IGC_TSSDP 0x0003C /* Time Sync SDP Configuration Register - RW */
+
+#define IGC_IMIR(_i) (0x05A80 + ((_i) * 4)) /* Immediate Interrupt */
+#define IGC_IMIREXT(_i) (0x05AA0 + ((_i) * 4)) /* Immediate INTR Ext*/
+
+#define IGC_FTQF(_n) (0x059E0 + (4 * (_n))) /* 5-tuple Queue Fltr */
+
+#define IGC_RXPBS 0x02404 /* Rx Packet Buffer Size - RW */
+
+/* System Time Registers */
+#define IGC_SYSTIML 0x0B600 /* System time register Low - RO */
+#define IGC_SYSTIMH 0x0B604 /* System time register High - RO */
+#define IGC_SYSTIMR 0x0B6F8 /* System time register Residue */
+#define IGC_TIMINCA 0x0B608 /* Increment attributes register - RW */
+
+#define IGC_RXSTMPL 0x0B624 /* Rx timestamp Low - RO */
+#define IGC_RXSTMPH 0x0B628 /* Rx timestamp High - RO */
+#define IGC_TXSTMPL 0x0B618 /* Tx timestamp value Low - RO */
+#define IGC_TXSTMPH 0x0B61C /* Tx timestamp value High - RO */
+
/* Management registers */
#define IGC_MANC 0x05820 /* Management Control - RW */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 4c13cca..718931d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5239,7 +5239,7 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter)
struct ixgbe_hw *hw = &adapter->hw;
struct hlist_node *node2;
struct ixgbe_fdir_filter *filter;
- u64 action;
+ u8 queue;
spin_lock(&adapter->fdir_perfect_lock);
@@ -5248,17 +5248,34 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter)
hlist_for_each_entry_safe(filter, node2,
&adapter->fdir_filter_list, fdir_node) {
- action = filter->action;
- if (action != IXGBE_FDIR_DROP_QUEUE && action != 0)
- action =
- (action >> ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF) - 1;
+ if (filter->action == IXGBE_FDIR_DROP_QUEUE) {
+ queue = IXGBE_FDIR_DROP_QUEUE;
+ } else {
+ u32 ring = ethtool_get_flow_spec_ring(filter->action);
+ u8 vf = ethtool_get_flow_spec_ring_vf(filter->action);
+
+ if (!vf && (ring >= adapter->num_rx_queues)) {
+ e_err(drv, "FDIR restore failed without VF, ring: %u\n",
+ ring);
+ continue;
+ } else if (vf &&
+ ((vf > adapter->num_vfs) ||
+ ring >= adapter->num_rx_queues_per_pool)) {
+ e_err(drv, "FDIR restore failed with VF, vf: %hhu, ring: %u\n",
+ vf, ring);
+ continue;
+ }
+
+ /* Map the ring onto the absolute queue index */
+ if (!vf)
+ queue = adapter->rx_ring[ring]->reg_idx;
+ else
+ queue = ((vf - 1) *
+ adapter->num_rx_queues_per_pool) + ring;
+ }
ixgbe_fdir_write_perfect_filter_82599(hw,
- &filter->filter,
- filter->sw_idx,
- (action == IXGBE_FDIR_DROP_QUEUE) ?
- IXGBE_FDIR_DROP_QUEUE :
- adapter->rx_ring[action]->reg_idx);
+ &filter->filter, filter->sw_idx, queue);
}
spin_unlock(&adapter->fdir_perfect_lock);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index fa28669..4622c4e 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -2081,11 +2081,6 @@ static int ixgbevf_write_uc_addr_list(struct net_device *netdev)
struct ixgbe_hw *hw = &adapter->hw;
int count = 0;
- if ((netdev_uc_count(netdev)) > 10) {
- pr_err("Too many unicast filters - No Space\n");
- return -ENOSPC;
- }
-
if (!netdev_uc_empty(netdev)) {
struct netdev_hw_addr *ha;
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 028e3e6..578c316 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -510,13 +510,6 @@ ltq_etop_change_mtu(struct net_device *dev, int new_mtu)
}
static int
-ltq_etop_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- /* TODO: mii-toll reports "No MII transceiver present!." ?!*/
- return phy_mii_ioctl(dev->phydev, rq, cmd);
-}
-
-static int
ltq_etop_set_mac_address(struct net_device *dev, void *p)
{
int ret = eth_mac_addr(dev, p);
@@ -616,7 +609,7 @@ static const struct net_device_ops ltq_eth_netdev_ops = {
.ndo_stop = ltq_etop_stop,
.ndo_start_xmit = ltq_etop_tx,
.ndo_change_mtu = ltq_etop_change_mtu,
- .ndo_do_ioctl = ltq_etop_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl,
.ndo_set_mac_address = ltq_etop_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = ltq_etop_set_multicast_list,
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 71a872d..2dfbfdf 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2081,7 +2081,11 @@ static int
mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
struct bpf_prog *prog, struct xdp_buff *xdp)
{
- u32 ret, act = bpf_prog_run_xdp(prog, xdp);
+ unsigned int len;
+ u32 ret, act;
+
+ len = xdp->data_end - xdp->data_hard_start - pp->rx_offset_correction;
+ act = bpf_prog_run_xdp(prog, xdp);
switch (act) {
case XDP_PASS:
@@ -2094,9 +2098,8 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
if (err) {
ret = MVNETA_XDP_DROPPED;
__page_pool_put_page(rxq->page_pool,
- virt_to_head_page(xdp->data),
- xdp->data_end - xdp->data_hard_start,
- true);
+ virt_to_head_page(xdp->data),
+ len, true);
} else {
ret = MVNETA_XDP_REDIR;
}
@@ -2106,9 +2109,8 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
ret = mvneta_xdp_xmit_back(pp, xdp);
if (ret != MVNETA_XDP_TX)
__page_pool_put_page(rxq->page_pool,
- virt_to_head_page(xdp->data),
- xdp->data_end - xdp->data_hard_start,
- true);
+ virt_to_head_page(xdp->data),
+ len, true);
break;
default:
bpf_warn_invalid_xdp_action(act);
@@ -2119,8 +2121,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
case XDP_DROP:
__page_pool_put_page(rxq->page_pool,
virt_to_head_page(xdp->data),
- xdp->data_end - xdp->data_hard_start,
- true);
+ len, true);
ret = MVNETA_XDP_DROPPED;
break;
}
@@ -3071,7 +3072,7 @@ static int mvneta_create_page_pool(struct mvneta_port *pp,
.order = 0,
.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
.pool_size = size,
- .nid = cpu_to_node(0),
+ .nid = NUMA_NO_NODE,
.dev = pp->dev->dev.parent,
.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
.offset = pp->rx_offset_correction,
@@ -4225,6 +4226,12 @@ static int mvneta_xdp_setup(struct net_device *dev, struct bpf_prog *prog,
return -EOPNOTSUPP;
}
+ if (pp->bm_priv) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Hardware Buffer Management not supported on XDP");
+ return -EOPNOTSUPP;
+ }
+
need_update = !!pp->xdp_prog != !!prog;
if (running && need_update)
mvneta_stop(dev);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index cd32c71..72133cb 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1114,7 +1114,7 @@ mvpp2_shared_interrupt_mask_unmask(struct mvpp2_port *port, bool mask)
/* Port configuration routines */
static bool mvpp2_is_xlg(phy_interface_t interface)
{
- return interface == PHY_INTERFACE_MODE_10GKR ||
+ return interface == PHY_INTERFACE_MODE_10GBASER ||
interface == PHY_INTERFACE_MODE_XAUI;
}
@@ -1200,7 +1200,7 @@ static int mvpp22_gop_init(struct mvpp2_port *port)
case PHY_INTERFACE_MODE_2500BASEX:
mvpp22_gop_init_sgmii(port);
break;
- case PHY_INTERFACE_MODE_10GKR:
+ case PHY_INTERFACE_MODE_10GBASER:
if (port->gop_id != 0)
goto invalid_conf;
mvpp22_gop_init_10gkr(port);
@@ -1649,7 +1649,7 @@ static void mvpp22_pcs_reset_deassert(struct mvpp2_port *port)
xpcs = priv->iface_base + MVPP22_XPCS_BASE(port->gop_id);
switch (port->phy_interface) {
- case PHY_INTERFACE_MODE_10GKR:
+ case PHY_INTERFACE_MODE_10GBASER:
val = readl(mpcs + MVPP22_MPCS_CLK_RESET);
val |= MAC_CLK_RESET_MAC | MAC_CLK_RESET_SD_RX |
MAC_CLK_RESET_SD_TX;
@@ -4758,7 +4758,7 @@ static void mvpp2_phylink_validate(struct phylink_config *config,
/* Invalid combinations */
switch (state->interface) {
- case PHY_INTERFACE_MODE_10GKR:
+ case PHY_INTERFACE_MODE_10GBASER:
case PHY_INTERFACE_MODE_XAUI:
if (port->gop_id != 0)
goto empty_set;
@@ -4780,7 +4780,7 @@ static void mvpp2_phylink_validate(struct phylink_config *config,
phylink_set(mask, Asym_Pause);
switch (state->interface) {
- case PHY_INTERFACE_MODE_10GKR:
+ case PHY_INTERFACE_MODE_10GBASER:
case PHY_INTERFACE_MODE_XAUI:
case PHY_INTERFACE_MODE_NA:
if (port->gop_id == 0) {
@@ -5247,6 +5247,15 @@ static int mvpp2_port_probe(struct platform_device *pdev,
goto err_free_netdev;
}
+ /*
+ * Rewrite 10GBASE-KR to 10GBASE-R for compatibility with existing DT.
+ * Existing usage of 10GBASE-KR is not correct; no backplane
+ * negotiation is done, and this driver does not actually support
+ * 10GBASE-KR.
+ */
+ if (phy_mode == PHY_INTERFACE_MODE_10GKR)
+ phy_mode = PHY_INTERFACE_MODE_10GBASER;
+
if (port_node) {
comphy = devm_of_phy_get(&pdev->dev, port_node, NULL);
if (IS_ERR(comphy)) {
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 1a68779..7a0d785 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1344,15 +1344,6 @@ static int pxa168_smi_write(struct mii_bus *bus, int phy_addr, int regnum,
return 0;
}
-static int pxa168_eth_do_ioctl(struct net_device *dev, struct ifreq *ifr,
- int cmd)
-{
- if (dev->phydev)
- return phy_mii_ioctl(dev->phydev, ifr, cmd);
-
- return -EOPNOTSUPP;
-}
-
#ifdef CONFIG_NET_POLL_CONTROLLER
static void pxa168_eth_netpoll(struct net_device *dev)
{
@@ -1387,7 +1378,7 @@ static const struct net_device_ops pxa168_eth_netdev_ops = {
.ndo_set_rx_mode = pxa168_eth_set_rx_mode,
.ndo_set_mac_address = pxa168_eth_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
- .ndo_do_ioctl = pxa168_eth_do_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl,
.ndo_change_mtu = pxa168_eth_change_mtu,
.ndo_tx_timeout = pxa168_eth_tx_timeout,
#ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c
index eaf08f7..64ed725 100644
--- a/drivers/net/ethernet/mellanox/mlx4/crdump.c
+++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c
@@ -182,7 +182,7 @@ int mlx4_crdump_collect(struct mlx4_dev *dev)
crdump_enable_crspace_access(dev, cr_space);
/* Get the available snapshot ID for the dumps */
- id = devlink_region_shapshot_id_get(devlink);
+ id = devlink_region_snapshot_id_get(devlink);
/* Try to capture dumps */
mlx4_crdump_collect_crspace(dev, cr_space, id);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index a6f390f..d3e06cec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -42,7 +42,7 @@
# Core extra
#
mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \
- ecpf.o rdma.o
+ ecpf.o rdma.o eswitch_offloads_chains.o
mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o
mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 549f962..42198e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -71,8 +71,8 @@ static void *mlx5_dma_zalloc_coherent_node(struct mlx5_core_dev *dev,
return cpu_handle;
}
-int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
- struct mlx5_frag_buf *buf, int node)
+static int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
+ struct mlx5_frag_buf *buf, int node)
{
dma_addr_t t;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 9c84276..220ef9f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -135,7 +135,7 @@ struct page_pool;
#define MLX5E_LOG_INDIR_RQT_SIZE 0x7
#define MLX5E_INDIR_RQT_SIZE BIT(MLX5E_LOG_INDIR_RQT_SIZE)
#define MLX5E_MIN_NUM_CHANNELS 0x1
-#define MLX5E_MAX_NUM_CHANNELS (MLX5E_INDIR_RQT_SIZE >> 1)
+#define MLX5E_MAX_NUM_CHANNELS MLX5E_INDIR_RQT_SIZE
#define MLX5E_MAX_NUM_SQS (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
#define MLX5E_TX_CQ_POLL_BUDGET 128
#define MLX5E_TX_XSK_POLL_BUDGET 64
@@ -892,6 +892,8 @@ struct mlx5e_profile {
int (*update_rx)(struct mlx5e_priv *priv);
void (*update_stats)(struct mlx5e_priv *priv);
void (*update_carrier)(struct mlx5e_priv *priv);
+ unsigned int (*stats_grps_num)(struct mlx5e_priv *priv);
+ mlx5e_stats_grp_t *stats_grps;
struct {
mlx5e_fp_handle_rx_cqe handle_rx_cqe;
mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
@@ -964,7 +966,6 @@ struct sk_buff *
mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt);
-void mlx5e_update_stats(struct mlx5e_priv *priv);
void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s);
@@ -1175,11 +1176,11 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv);
void mlx5e_detach_netdev(struct mlx5e_priv *priv);
void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv);
-void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+void mlx5e_build_nic_params(struct mlx5e_priv *priv,
struct mlx5e_xsk *xsk,
struct mlx5e_rss_params *rss_params,
struct mlx5e_params *params,
- u16 max_channels, u16 mtu);
+ u16 mtu);
void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
struct mlx5e_params *params);
void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 68d5930..0416f77 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -21,6 +21,7 @@ struct mlx5e_tc_table {
DECLARE_HASHTABLE(hairpin_tbl, 8);
struct notifier_block netdevice_nb;
+ struct netdev_net_notifier netdevice_nn;
};
struct mlx5e_flow_table {
@@ -122,6 +123,22 @@ enum {
#endif
};
+#define MLX5E_TTC_NUM_GROUPS 3
+#define MLX5E_TTC_GROUP1_SIZE (BIT(3) + MLX5E_NUM_TUNNEL_TT)
+#define MLX5E_TTC_GROUP2_SIZE BIT(1)
+#define MLX5E_TTC_GROUP3_SIZE BIT(0)
+#define MLX5E_TTC_TABLE_SIZE (MLX5E_TTC_GROUP1_SIZE +\
+ MLX5E_TTC_GROUP2_SIZE +\
+ MLX5E_TTC_GROUP3_SIZE)
+
+#define MLX5E_INNER_TTC_NUM_GROUPS 3
+#define MLX5E_INNER_TTC_GROUP1_SIZE BIT(3)
+#define MLX5E_INNER_TTC_GROUP2_SIZE BIT(1)
+#define MLX5E_INNER_TTC_GROUP3_SIZE BIT(0)
+#define MLX5E_INNER_TTC_TABLE_SIZE (MLX5E_INNER_TTC_GROUP1_SIZE +\
+ MLX5E_INNER_TTC_GROUP2_SIZE +\
+ MLX5E_INNER_TTC_GROUP3_SIZE)
+
#ifdef CONFIG_MLX5_EN_RXNFC
struct mlx5e_ethtool_table {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
index 1d6b588..3a97564 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -197,9 +197,10 @@ int mlx5e_health_report(struct mlx5e_priv *priv,
struct devlink_health_reporter *reporter, char *err_str,
struct mlx5e_err_ctx *err_ctx)
{
- if (!reporter) {
- netdev_err(priv->netdev, err_str);
+ netdev_err(priv->netdev, err_str);
+
+ if (!reporter)
return err_ctx->recover(&err_ctx->ctx);
- }
+
return devlink_health_report(reporter, err_str, err_ctx);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 778dab1..f260dd9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -180,7 +180,7 @@ mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq,
struct tx_sync_info {
u64 rcd_sn;
- s32 sync_len;
+ u32 sync_len;
int nr_frags;
skb_frag_t frags[MAX_SKB_FRAGS];
};
@@ -193,13 +193,14 @@ enum mlx5e_ktls_sync_retval {
static enum mlx5e_ktls_sync_retval
tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
- u32 tcp_seq, struct tx_sync_info *info)
+ u32 tcp_seq, int datalen, struct tx_sync_info *info)
{
struct tls_offload_context_tx *tx_ctx = priv_tx->tx_ctx;
enum mlx5e_ktls_sync_retval ret = MLX5E_KTLS_SYNC_DONE;
struct tls_record_info *record;
int remaining, i = 0;
unsigned long flags;
+ bool ends_before;
spin_lock_irqsave(&tx_ctx->lock, flags);
record = tls_get_record(tx_ctx, tcp_seq, &info->rcd_sn);
@@ -209,9 +210,21 @@ tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
goto out;
}
- if (unlikely(tcp_seq < tls_record_start_seq(record))) {
- ret = tls_record_is_start_marker(record) ?
- MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL;
+ /* There are the following cases:
+ * 1. packet ends before start marker: bypass offload.
+ * 2. packet starts before start marker and ends after it: drop,
+ * not supported, breaks contract with kernel.
+ * 3. packet ends before tls record info starts: drop,
+ * this packet was already acknowledged and its record info
+ * was released.
+ */
+ ends_before = before(tcp_seq + datalen, tls_record_start_seq(record));
+
+ if (unlikely(tls_record_is_start_marker(record))) {
+ ret = ends_before ? MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL;
+ goto out;
+ } else if (ends_before) {
+ ret = MLX5E_KTLS_SYNC_FAIL;
goto out;
}
@@ -337,7 +350,7 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
u8 num_wqebbs;
int i = 0;
- ret = tx_sync_info_get(priv_tx, seq, &info);
+ ret = tx_sync_info_get(priv_tx, seq, datalen, &info);
if (unlikely(ret != MLX5E_KTLS_SYNC_DONE)) {
if (ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA) {
stats->tls_skip_no_sync_data++;
@@ -351,14 +364,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
goto err_out;
}
- if (unlikely(info.sync_len < 0)) {
- if (likely(datalen <= -info.sync_len))
- return MLX5E_KTLS_SYNC_DONE;
-
- stats->tls_drop_bypass_req++;
- goto err_out;
- }
-
stats->tls_ooo++;
tx_post_resync_params(sq, priv_tx, info.rcd_sn);
@@ -378,8 +383,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
if (unlikely(contig_wqebbs_room < num_wqebbs))
mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
- tx_post_resync_params(sq, priv_tx, info.rcd_sn);
-
for (; i < info.nr_frags; i++) {
unsigned int orig_fsz, frag_offset = 0, n = 0;
skb_frag_t *f = &info.frags[i];
@@ -455,12 +458,18 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
enum mlx5e_ktls_sync_retval ret =
mlx5e_ktls_tx_handle_ooo(priv_tx, sq, datalen, seq);
- if (likely(ret == MLX5E_KTLS_SYNC_DONE))
+ switch (ret) {
+ case MLX5E_KTLS_SYNC_DONE:
*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
- else if (ret == MLX5E_KTLS_SYNC_FAIL)
+ break;
+ case MLX5E_KTLS_SYNC_SKIP_NO_DATA:
+ if (likely(!skb->decrypted))
+ goto out;
+ WARN_ON_ONCE(1);
+ /* fall-through */
+ default: /* MLX5E_KTLS_SYNC_FAIL */
goto err_out;
- else /* ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA */
- goto out;
+ }
}
priv_tx->expected_seq = seq + datalen;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index c6776f3..d674cb6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -218,13 +218,9 @@ static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS];
int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset)
{
- int i, num_stats = 0;
-
switch (sset) {
case ETH_SS_STATS:
- for (i = 0; i < mlx5e_num_stats_grps; i++)
- num_stats += mlx5e_stats_grps[i].get_num_stats(priv);
- return num_stats;
+ return mlx5e_stats_total_num(priv);
case ETH_SS_PRIV_FLAGS:
return MLX5E_NUM_PFLAGS;
case ETH_SS_TEST:
@@ -242,14 +238,6 @@ static int mlx5e_get_sset_count(struct net_device *dev, int sset)
return mlx5e_ethtool_get_sset_count(priv, sset);
}
-static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, u8 *data)
-{
- int i, idx = 0;
-
- for (i = 0; i < mlx5e_num_stats_grps; i++)
- idx = mlx5e_stats_grps[i].fill_strings(priv, data, idx);
-}
-
void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, u32 stringset, u8 *data)
{
int i;
@@ -268,7 +256,7 @@ void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, u32 stringset, u8 *data)
break;
case ETH_SS_STATS:
- mlx5e_fill_stats_strings(priv, data);
+ mlx5e_stats_fill_strings(priv, data);
break;
}
}
@@ -283,14 +271,13 @@ static void mlx5e_get_strings(struct net_device *dev, u32 stringset, u8 *data)
void mlx5e_ethtool_get_ethtool_stats(struct mlx5e_priv *priv,
struct ethtool_stats *stats, u64 *data)
{
- int i, idx = 0;
+ int idx = 0;
mutex_lock(&priv->state_lock);
- mlx5e_update_stats(priv);
+ mlx5e_stats_update(priv);
mutex_unlock(&priv->state_lock);
- for (i = 0; i < mlx5e_num_stats_grps; i++)
- idx = mlx5e_stats_grps[i].fill_stats(priv, data, idx);
+ mlx5e_stats_fill(priv, data, idx);
}
static void mlx5e_get_ethtool_stats(struct net_device *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 15b7f0f..73d3dc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -904,22 +904,6 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv,
return err;
}
-#define MLX5E_TTC_NUM_GROUPS 3
-#define MLX5E_TTC_GROUP1_SIZE (BIT(3) + MLX5E_NUM_TUNNEL_TT)
-#define MLX5E_TTC_GROUP2_SIZE BIT(1)
-#define MLX5E_TTC_GROUP3_SIZE BIT(0)
-#define MLX5E_TTC_TABLE_SIZE (MLX5E_TTC_GROUP1_SIZE +\
- MLX5E_TTC_GROUP2_SIZE +\
- MLX5E_TTC_GROUP3_SIZE)
-
-#define MLX5E_INNER_TTC_NUM_GROUPS 3
-#define MLX5E_INNER_TTC_GROUP1_SIZE BIT(3)
-#define MLX5E_INNER_TTC_GROUP2_SIZE BIT(1)
-#define MLX5E_INNER_TTC_GROUP3_SIZE BIT(0)
-#define MLX5E_INNER_TTC_TABLE_SIZE (MLX5E_INNER_TTC_GROUP1_SIZE +\
- MLX5E_INNER_TTC_GROUP2_SIZE +\
- MLX5E_INNER_TTC_GROUP3_SIZE)
-
static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc,
bool use_ipv)
{
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index acd946f..3bc2ac3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -58,6 +58,7 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
struct ethtool_rx_flow_spec *fs,
int num_tuples)
{
+ struct mlx5_flow_table_attr ft_attr = {};
struct mlx5e_ethtool_table *eth_ft;
struct mlx5_flow_namespace *ns;
struct mlx5_flow_table *ft;
@@ -102,9 +103,11 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
table_size = min_t(u32, BIT(MLX5_CAP_FLOWTABLE(priv->mdev,
flow_table_properties_nic_receive.log_max_ft_size)),
MLX5E_ETHTOOL_NUM_ENTRIES);
- ft = mlx5_create_auto_grouped_flow_table(ns, prio,
- table_size,
- MLX5E_ETHTOOL_NUM_GROUPS, 0, 0);
+
+ ft_attr.prio = prio;
+ ft_attr.max_fte = table_size;
+ ft_attr.autogroup.max_num_groups = MLX5E_ETHTOOL_NUM_GROUPS;
+ ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
if (IS_ERR(ft))
return (void *)ft;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 319b39f..454d345 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -159,23 +159,14 @@ static void mlx5e_update_carrier_work(struct work_struct *work)
mutex_unlock(&priv->state_lock);
}
-void mlx5e_update_stats(struct mlx5e_priv *priv)
-{
- int i;
-
- for (i = mlx5e_num_stats_grps - 1; i >= 0; i--)
- if (mlx5e_stats_grps[i].update_stats)
- mlx5e_stats_grps[i].update_stats(priv);
-}
-
void mlx5e_update_ndo_stats(struct mlx5e_priv *priv)
{
int i;
- for (i = mlx5e_num_stats_grps - 1; i >= 0; i--)
- if (mlx5e_stats_grps[i].update_stats_mask &
+ for (i = mlx5e_nic_stats_grps_num(priv) - 1; i >= 0; i--)
+ if (mlx5e_nic_stats_grps[i]->update_stats_mask &
MLX5E_NDO_UPDATE_STATS)
- mlx5e_stats_grps[i].update_stats(priv);
+ mlx5e_nic_stats_grps[i]->update_stats(priv);
}
static void mlx5e_update_stats_work(struct work_struct *work)
@@ -4739,17 +4730,19 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
tirc_default_config[tt].rx_hash_fields;
}
-void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+void mlx5e_build_nic_params(struct mlx5e_priv *priv,
struct mlx5e_xsk *xsk,
struct mlx5e_rss_params *rss_params,
struct mlx5e_params *params,
- u16 max_channels, u16 mtu)
+ u16 mtu)
{
+ struct mlx5_core_dev *mdev = priv->mdev;
u8 rx_cq_period_mode;
params->sw_mtu = mtu;
params->hard_mtu = MLX5E_ETH_HARD_MTU;
- params->num_channels = max_channels;
+ params->num_channels = min_t(unsigned int, MLX5E_MAX_NUM_CHANNELS / 2,
+ priv->max_nch);
params->num_tc = 1;
/* SQ */
@@ -4876,6 +4869,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
NETIF_F_GSO_UDP_TUNNEL_CSUM;
netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL |
+ NETIF_F_GSO_UDP_TUNNEL_CSUM;
}
if (mlx5e_tunnel_proto_supported(mdev, IPPROTO_GRE)) {
@@ -4986,8 +4981,8 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
if (err)
return err;
- mlx5e_build_nic_params(mdev, &priv->xsk, rss, &priv->channels.params,
- priv->max_nch, netdev->mtu);
+ mlx5e_build_nic_params(priv, &priv->xsk, rss, &priv->channels.params,
+ netdev->mtu);
mlx5e_timestamp_init(priv);
@@ -5149,6 +5144,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
static void mlx5e_nic_disable(struct mlx5e_priv *priv)
{
+ struct net_device *netdev = priv->netdev;
struct mlx5_core_dev *mdev = priv->mdev;
#ifdef CONFIG_MLX5_CORE_EN_DCB
@@ -5169,7 +5165,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
mlx5e_monitor_counter_cleanup(priv);
mlx5e_disable_async_events(priv);
- mlx5_lag_remove(mdev);
+ mlx5_lag_remove(mdev, netdev);
}
int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
@@ -5193,6 +5189,8 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
.max_tc = MLX5E_MAX_NUM_TC,
.rq_groups = MLX5E_NUM_RQ_GROUPS(XSK),
+ .stats_grps = mlx5e_nic_stats_grps,
+ .stats_grps_num = mlx5e_nic_stats_grps_num,
};
/* mlx5e generic netdev management API (move to en_common.c) */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index f175cb2..7b48cca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -41,6 +41,7 @@
#include <net/ipv6_stubs.h>
#include "eswitch.h"
+#include "eswitch_offloads_chains.h"
#include "en.h"
#include "en_rep.h"
#include "en_tc.h"
@@ -116,24 +117,71 @@ static const struct counter_desc vport_rep_stats_desc[] = {
#define NUM_VPORT_REP_SW_COUNTERS ARRAY_SIZE(sw_rep_stats_desc)
#define NUM_VPORT_REP_HW_COUNTERS ARRAY_SIZE(vport_rep_stats_desc)
-static void mlx5e_rep_get_strings(struct net_device *dev,
- u32 stringset, uint8_t *data)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(sw_rep)
{
- int i, j;
-
- switch (stringset) {
- case ETH_SS_STATS:
- for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
- strcpy(data + (i * ETH_GSTRING_LEN),
- sw_rep_stats_desc[i].format);
- for (j = 0; j < NUM_VPORT_REP_HW_COUNTERS; j++, i++)
- strcpy(data + (i * ETH_GSTRING_LEN),
- vport_rep_stats_desc[j].format);
- break;
- }
+ return NUM_VPORT_REP_SW_COUNTERS;
}
-static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(sw_rep)
+{
+ int i;
+
+ for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
+ strcpy(data + (idx++) * ETH_GSTRING_LEN,
+ sw_rep_stats_desc[i].format);
+ return idx;
+}
+
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(sw_rep)
+{
+ int i;
+
+ for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
+ data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.sw,
+ sw_rep_stats_desc, i);
+ return idx;
+}
+
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw_rep)
+{
+ struct mlx5e_sw_stats *s = &priv->stats.sw;
+ struct rtnl_link_stats64 stats64 = {};
+
+ memset(s, 0, sizeof(*s));
+ mlx5e_fold_sw_stats64(priv, &stats64);
+
+ s->rx_packets = stats64.rx_packets;
+ s->rx_bytes = stats64.rx_bytes;
+ s->tx_packets = stats64.tx_packets;
+ s->tx_bytes = stats64.tx_bytes;
+ s->tx_queue_dropped = stats64.tx_dropped;
+}
+
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(vport_rep)
+{
+ return NUM_VPORT_REP_HW_COUNTERS;
+}
+
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vport_rep)
+{
+ int i;
+
+ for (i = 0; i < NUM_VPORT_REP_HW_COUNTERS; i++)
+ strcpy(data + (idx++) * ETH_GSTRING_LEN, vport_rep_stats_desc[i].format);
+ return idx;
+}
+
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport_rep)
+{
+ int i;
+
+ for (i = 0; i < NUM_VPORT_REP_HW_COUNTERS; i++)
+ data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.vf_vport,
+ vport_rep_stats_desc, i);
+ return idx;
+}
+
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -156,64 +204,33 @@ static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
vport_stats->tx_bytes = vf_stats.rx_bytes;
}
-static void mlx5e_uplink_rep_update_hw_counters(struct mlx5e_priv *priv)
+static void mlx5e_rep_get_strings(struct net_device *dev,
+ u32 stringset, uint8_t *data)
{
- struct mlx5e_pport_stats *pstats = &priv->stats.pport;
- struct rtnl_link_stats64 *vport_stats;
+ struct mlx5e_priv *priv = netdev_priv(dev);
- mlx5e_grp_802_3_update_stats(priv);
-
- vport_stats = &priv->stats.vf_vport;
-
- vport_stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
- vport_stats->rx_bytes = PPORT_802_3_GET(pstats, a_octets_received_ok);
- vport_stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
- vport_stats->tx_bytes = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
-}
-
-static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
-{
- struct mlx5e_sw_stats *s = &priv->stats.sw;
- struct rtnl_link_stats64 stats64 = {};
-
- memset(s, 0, sizeof(*s));
- mlx5e_fold_sw_stats64(priv, &stats64);
-
- s->rx_packets = stats64.rx_packets;
- s->rx_bytes = stats64.rx_bytes;
- s->tx_packets = stats64.tx_packets;
- s->tx_bytes = stats64.tx_bytes;
- s->tx_queue_dropped = stats64.tx_dropped;
+ switch (stringset) {
+ case ETH_SS_STATS:
+ mlx5e_stats_fill_strings(priv, data);
+ break;
+ }
}
static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct mlx5e_priv *priv = netdev_priv(dev);
- int i, j;
- if (!data)
- return;
-
- mutex_lock(&priv->state_lock);
- mlx5e_rep_update_sw_counters(priv);
- priv->profile->update_stats(priv);
- mutex_unlock(&priv->state_lock);
-
- for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
- data[i] = MLX5E_READ_CTR64_CPU(&priv->stats.sw,
- sw_rep_stats_desc, i);
-
- for (j = 0; j < NUM_VPORT_REP_HW_COUNTERS; j++, i++)
- data[i] = MLX5E_READ_CTR64_CPU(&priv->stats.vf_vport,
- vport_rep_stats_desc, j);
+ mlx5e_ethtool_get_ethtool_stats(priv, stats, data);
}
static int mlx5e_rep_get_sset_count(struct net_device *dev, int sset)
{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+
switch (sset) {
case ETH_SS_STATS:
- return NUM_VPORT_REP_SW_COUNTERS + NUM_VPORT_REP_HW_COUNTERS;
+ return mlx5e_stats_total_num(priv);
default:
return -EOPNOTSUPP;
}
@@ -1247,8 +1264,7 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data,
void *cb_priv)
{
- struct flow_cls_offload *f = type_data;
- struct flow_cls_offload cls_flower;
+ struct flow_cls_offload tmp, *f = type_data;
struct mlx5e_priv *priv = cb_priv;
struct mlx5_eswitch *esw;
unsigned long flags;
@@ -1261,16 +1277,30 @@ static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data,
switch (type) {
case TC_SETUP_CLSFLOWER:
- if (!mlx5_eswitch_prios_supported(esw) || f->common.chain_index)
+ memcpy(&tmp, f, sizeof(*f));
+
+ if (!mlx5_esw_chains_prios_supported(esw) ||
+ tmp.common.chain_index)
return -EOPNOTSUPP;
/* Re-use tc offload path by moving the ft flow to the
* reserved ft chain.
+ *
+ * FT offload can use prio range [0, INT_MAX], so we normalize
+ * it to range [1, mlx5_esw_chains_get_prio_range(esw)]
+ * as with tc, where prio 0 isn't supported.
+ *
+ * We only support chain 0 of FT offload.
*/
- memcpy(&cls_flower, f, sizeof(*f));
- cls_flower.common.chain_index = FDB_FT_CHAIN;
- err = mlx5e_rep_setup_tc_cls_flower(priv, &cls_flower, flags);
- memcpy(&f->stats, &cls_flower.stats, sizeof(f->stats));
+ if (tmp.common.prio >= mlx5_esw_chains_get_prio_range(esw))
+ return -EOPNOTSUPP;
+ if (tmp.common.chain_index != 0)
+ return -EOPNOTSUPP;
+
+ tmp.common.chain_index = mlx5_esw_chains_get_ft_chain(esw);
+ tmp.common.prio++;
+ err = mlx5e_rep_setup_tc_cls_flower(priv, &tmp, flags);
+ memcpy(&f->stats, &tmp.stats, sizeof(f->stats));
return err;
default:
return -EOPNOTSUPP;
@@ -1660,10 +1690,65 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
mlx5e_close_drop_rq(&priv->drop_rq);
}
+static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv)
+{
+ int err = mlx5e_init_rep_rx(priv);
+
+ if (err)
+ return err;
+
+ mlx5e_create_q_counters(priv);
+ return 0;
+}
+
+static void mlx5e_cleanup_ul_rep_rx(struct mlx5e_priv *priv)
+{
+ mlx5e_destroy_q_counters(priv);
+ mlx5e_cleanup_rep_rx(priv);
+}
+
+static int mlx5e_init_uplink_rep_tx(struct mlx5e_rep_priv *rpriv)
+{
+ struct mlx5_rep_uplink_priv *uplink_priv;
+ struct net_device *netdev;
+ struct mlx5e_priv *priv;
+ int err;
+
+ netdev = rpriv->netdev;
+ priv = netdev_priv(netdev);
+ uplink_priv = &rpriv->uplink_priv;
+
+ mutex_init(&uplink_priv->unready_flows_lock);
+ INIT_LIST_HEAD(&uplink_priv->unready_flows);
+
+ /* init shared tc flow table */
+ err = mlx5e_tc_esw_init(&uplink_priv->tc_ht);
+ if (err)
+ return err;
+
+ mlx5_init_port_tun_entropy(&uplink_priv->tun_entropy, priv->mdev);
+
+ /* init indirect block notifications */
+ INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list);
+ uplink_priv->netdevice_nb.notifier_call = mlx5e_nic_rep_netdevice_event;
+ err = register_netdevice_notifier_dev_net(rpriv->netdev,
+ &uplink_priv->netdevice_nb,
+ &uplink_priv->netdevice_nn);
+ if (err) {
+ mlx5_core_err(priv->mdev, "Failed to register netdev notifier\n");
+ goto tc_esw_cleanup;
+ }
+
+ return 0;
+
+tc_esw_cleanup:
+ mlx5e_tc_esw_cleanup(&uplink_priv->tc_ht);
+ return err;
+}
+
static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
{
struct mlx5e_rep_priv *rpriv = priv->ppriv;
- struct mlx5_rep_uplink_priv *uplink_priv;
int err;
err = mlx5e_create_tises(priv);
@@ -1673,52 +1758,41 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
}
if (rpriv->rep->vport == MLX5_VPORT_UPLINK) {
- uplink_priv = &rpriv->uplink_priv;
-
- mutex_init(&uplink_priv->unready_flows_lock);
- INIT_LIST_HEAD(&uplink_priv->unready_flows);
-
- /* init shared tc flow table */
- err = mlx5e_tc_esw_init(&uplink_priv->tc_ht);
+ err = mlx5e_init_uplink_rep_tx(rpriv);
if (err)
goto destroy_tises;
-
- mlx5_init_port_tun_entropy(&uplink_priv->tun_entropy, priv->mdev);
-
- /* init indirect block notifications */
- INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list);
- uplink_priv->netdevice_nb.notifier_call = mlx5e_nic_rep_netdevice_event;
- err = register_netdevice_notifier(&uplink_priv->netdevice_nb);
- if (err) {
- mlx5_core_err(priv->mdev, "Failed to register netdev notifier\n");
- goto tc_esw_cleanup;
- }
}
return 0;
-tc_esw_cleanup:
- mlx5e_tc_esw_cleanup(&uplink_priv->tc_ht);
destroy_tises:
mlx5e_destroy_tises(priv);
return err;
}
+static void mlx5e_cleanup_uplink_rep_tx(struct mlx5e_rep_priv *rpriv)
+{
+ struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+
+ /* clean indirect TC block notifications */
+ unregister_netdevice_notifier_dev_net(rpriv->netdev,
+ &uplink_priv->netdevice_nb,
+ &uplink_priv->netdevice_nn);
+ mlx5e_rep_indr_clean_block_privs(rpriv);
+
+ /* delete shared tc flow table */
+ mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht);
+ mutex_destroy(&rpriv->uplink_priv.unready_flows_lock);
+}
+
static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
{
struct mlx5e_rep_priv *rpriv = priv->ppriv;
mlx5e_destroy_tises(priv);
- if (rpriv->rep->vport == MLX5_VPORT_UPLINK) {
- /* clean indirect TC block notifications */
- unregister_netdevice_notifier(&rpriv->uplink_priv.netdevice_nb);
- mlx5e_rep_indr_clean_block_privs(rpriv);
-
- /* delete shared tc flow table */
- mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht);
- mutex_destroy(&rpriv->uplink_priv.unready_flows_lock);
- }
+ if (rpriv->rep->vport == MLX5_VPORT_UPLINK)
+ mlx5e_cleanup_uplink_rep_tx(rpriv);
}
static void mlx5e_rep_enable(struct mlx5e_priv *priv)
@@ -1787,6 +1861,7 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
{
+ struct net_device *netdev = priv->netdev;
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -1795,7 +1870,44 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
#endif
mlx5_notifier_unregister(mdev, &priv->events_nb);
cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work);
- mlx5_lag_remove(mdev);
+ mlx5_lag_remove(mdev, netdev);
+}
+
+static MLX5E_DEFINE_STATS_GRP(sw_rep, 0);
+static MLX5E_DEFINE_STATS_GRP(vport_rep, MLX5E_NDO_UPDATE_STATS);
+
+/* The stats groups order is opposite to the update_stats() order calls */
+static mlx5e_stats_grp_t mlx5e_rep_stats_grps[] = {
+ &MLX5E_STATS_GRP(sw_rep),
+ &MLX5E_STATS_GRP(vport_rep),
+};
+
+static unsigned int mlx5e_rep_stats_grps_num(struct mlx5e_priv *priv)
+{
+ return ARRAY_SIZE(mlx5e_rep_stats_grps);
+}
+
+/* The stats groups order is opposite to the update_stats() order calls */
+static mlx5e_stats_grp_t mlx5e_ul_rep_stats_grps[] = {
+ &MLX5E_STATS_GRP(sw),
+ &MLX5E_STATS_GRP(qcnt),
+ &MLX5E_STATS_GRP(vnic_env),
+ &MLX5E_STATS_GRP(vport),
+ &MLX5E_STATS_GRP(802_3),
+ &MLX5E_STATS_GRP(2863),
+ &MLX5E_STATS_GRP(2819),
+ &MLX5E_STATS_GRP(phy),
+ &MLX5E_STATS_GRP(eth_ext),
+ &MLX5E_STATS_GRP(pcie),
+ &MLX5E_STATS_GRP(per_prio),
+ &MLX5E_STATS_GRP(pme),
+ &MLX5E_STATS_GRP(channels),
+ &MLX5E_STATS_GRP(per_port_buff_congest),
+};
+
+static unsigned int mlx5e_ul_rep_stats_grps_num(struct mlx5e_priv *priv)
+{
+ return ARRAY_SIZE(mlx5e_ul_rep_stats_grps);
}
static const struct mlx5e_profile mlx5e_rep_profile = {
@@ -1807,29 +1919,33 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
.cleanup_tx = mlx5e_cleanup_rep_tx,
.enable = mlx5e_rep_enable,
.update_rx = mlx5e_update_rep_rx,
- .update_stats = mlx5e_rep_update_hw_counters,
+ .update_stats = mlx5e_update_ndo_stats,
.rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep,
.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
.max_tc = 1,
.rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR),
+ .stats_grps = mlx5e_rep_stats_grps,
+ .stats_grps_num = mlx5e_rep_stats_grps_num,
};
static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
.init = mlx5e_init_rep,
.cleanup = mlx5e_cleanup_rep,
- .init_rx = mlx5e_init_rep_rx,
- .cleanup_rx = mlx5e_cleanup_rep_rx,
+ .init_rx = mlx5e_init_ul_rep_rx,
+ .cleanup_rx = mlx5e_cleanup_ul_rep_rx,
.init_tx = mlx5e_init_rep_tx,
.cleanup_tx = mlx5e_cleanup_rep_tx,
.enable = mlx5e_uplink_rep_enable,
.disable = mlx5e_uplink_rep_disable,
.update_rx = mlx5e_update_rep_rx,
- .update_stats = mlx5e_uplink_rep_update_hw_counters,
+ .update_stats = mlx5e_update_ndo_stats,
.update_carrier = mlx5e_update_carrier,
.rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep,
.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
.max_tc = MLX5E_MAX_NUM_TC,
.rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR),
+ .stats_grps = mlx5e_ul_rep_stats_grps,
+ .stats_grps_num = mlx5e_ul_rep_stats_grps_num,
};
static bool
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 31f83c8..3f756d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -73,6 +73,7 @@ struct mlx5_rep_uplink_priv {
*/
struct list_head tc_indr_block_priv_list;
struct notifier_block netdevice_nb;
+ struct netdev_net_notifier netdevice_nn;
struct mlx5_tun_entropy tun_entropy;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 9f09253..30b216d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -35,6 +35,58 @@
#include "en_accel/ipsec.h"
#include "en_accel/tls.h"
+static unsigned int stats_grps_num(struct mlx5e_priv *priv)
+{
+ return !priv->profile->stats_grps_num ? 0 :
+ priv->profile->stats_grps_num(priv);
+}
+
+unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv)
+{
+ mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps;
+ const unsigned int num_stats_grps = stats_grps_num(priv);
+ unsigned int total = 0;
+ int i;
+
+ for (i = 0; i < num_stats_grps; i++)
+ total += stats_grps[i]->get_num_stats(priv);
+
+ return total;
+}
+
+void mlx5e_stats_update(struct mlx5e_priv *priv)
+{
+ mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps;
+ const unsigned int num_stats_grps = stats_grps_num(priv);
+ int i;
+
+ for (i = num_stats_grps - 1; i >= 0; i--)
+ if (stats_grps[i]->update_stats)
+ stats_grps[i]->update_stats(priv);
+}
+
+void mlx5e_stats_fill(struct mlx5e_priv *priv, u64 *data, int idx)
+{
+ mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps;
+ const unsigned int num_stats_grps = stats_grps_num(priv);
+ int i;
+
+ for (i = 0; i < num_stats_grps; i++)
+ idx = stats_grps[i]->fill_stats(priv, data, idx);
+}
+
+void mlx5e_stats_fill_strings(struct mlx5e_priv *priv, u8 *data)
+{
+ mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps;
+ const unsigned int num_stats_grps = stats_grps_num(priv);
+ int i, idx = 0;
+
+ for (i = 0; i < num_stats_grps; i++)
+ idx = stats_grps[i]->fill_strings(priv, data, idx);
+}
+
+/* Concrete NIC Stats */
+
static const struct counter_desc sw_stats_desc[] = {
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_bytes) },
@@ -146,12 +198,12 @@ static const struct counter_desc sw_stats_desc[] = {
#define NUM_SW_COUNTERS ARRAY_SIZE(sw_stats_desc)
-static int mlx5e_grp_sw_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(sw)
{
return NUM_SW_COUNTERS;
}
-static int mlx5e_grp_sw_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(sw)
{
int i;
@@ -160,7 +212,7 @@ static int mlx5e_grp_sw_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx)
return idx;
}
-static int mlx5e_grp_sw_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(sw)
{
int i;
@@ -169,7 +221,7 @@ static int mlx5e_grp_sw_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
return idx;
}
-static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
{
struct mlx5e_sw_stats *s = &priv->stats.sw;
int i;
@@ -297,6 +349,9 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
s->tx_tls_drop_bypass_req += sq_stats->tls_drop_bypass_req;
#endif
s->tx_cqes += sq_stats->cqes;
+
+ /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92657 */
+ barrier();
}
}
}
@@ -312,7 +367,7 @@ static const struct counter_desc drop_rq_stats_desc[] = {
#define NUM_Q_COUNTERS ARRAY_SIZE(q_stats_desc)
#define NUM_DROP_RQ_COUNTERS ARRAY_SIZE(drop_rq_stats_desc)
-static int mlx5e_grp_q_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(qcnt)
{
int num_stats = 0;
@@ -325,7 +380,7 @@ static int mlx5e_grp_q_get_num_stats(struct mlx5e_priv *priv)
return num_stats;
}
-static int mlx5e_grp_q_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(qcnt)
{
int i;
@@ -340,7 +395,7 @@ static int mlx5e_grp_q_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx)
return idx;
}
-static int mlx5e_grp_q_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qcnt)
{
int i;
@@ -353,7 +408,7 @@ static int mlx5e_grp_q_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
return idx;
}
-static void mlx5e_grp_q_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(qcnt)
{
struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt;
u32 out[MLX5_ST_SZ_DW(query_q_counter_out)];
@@ -388,14 +443,13 @@ static const struct counter_desc vnic_env_stats_dev_oob_desc[] = {
(MLX5_CAP_GEN(dev, vnic_env_int_rq_oob) ? \
ARRAY_SIZE(vnic_env_stats_dev_oob_desc) : 0)
-static int mlx5e_grp_vnic_env_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(vnic_env)
{
return NUM_VNIC_ENV_STEER_COUNTERS(priv->mdev) +
NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev);
}
-static int mlx5e_grp_vnic_env_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vnic_env)
{
int i;
@@ -409,8 +463,7 @@ static int mlx5e_grp_vnic_env_fill_strings(struct mlx5e_priv *priv, u8 *data,
return idx;
}
-static int mlx5e_grp_vnic_env_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vnic_env)
{
int i;
@@ -424,7 +477,7 @@ static int mlx5e_grp_vnic_env_fill_stats(struct mlx5e_priv *priv, u64 *data,
return idx;
}
-static void mlx5e_grp_vnic_env_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vnic_env)
{
u32 *out = (u32 *)priv->stats.vnic.query_vnic_env_out;
int outlen = MLX5_ST_SZ_BYTES(query_vnic_env_out);
@@ -487,13 +540,12 @@ static const struct counter_desc vport_stats_desc[] = {
#define NUM_VPORT_COUNTERS ARRAY_SIZE(vport_stats_desc)
-static int mlx5e_grp_vport_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(vport)
{
return NUM_VPORT_COUNTERS;
}
-static int mlx5e_grp_vport_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vport)
{
int i;
@@ -502,8 +554,7 @@ static int mlx5e_grp_vport_fill_strings(struct mlx5e_priv *priv, u8 *data,
return idx;
}
-static int mlx5e_grp_vport_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport)
{
int i;
@@ -513,7 +564,7 @@ static int mlx5e_grp_vport_fill_stats(struct mlx5e_priv *priv, u64 *data,
return idx;
}
-static void mlx5e_grp_vport_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport)
{
int outlen = MLX5_ST_SZ_BYTES(query_vport_counter_out);
u32 *out = (u32 *)priv->stats.vport.query_vport_out;
@@ -552,13 +603,12 @@ static const struct counter_desc pport_802_3_stats_desc[] = {
#define NUM_PPORT_802_3_COUNTERS ARRAY_SIZE(pport_802_3_stats_desc)
-static int mlx5e_grp_802_3_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(802_3)
{
return NUM_PPORT_802_3_COUNTERS;
}
-static int mlx5e_grp_802_3_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(802_3)
{
int i;
@@ -567,8 +617,7 @@ static int mlx5e_grp_802_3_fill_strings(struct mlx5e_priv *priv, u8 *data,
return idx;
}
-static int mlx5e_grp_802_3_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(802_3)
{
int i;
@@ -581,7 +630,7 @@ static int mlx5e_grp_802_3_fill_stats(struct mlx5e_priv *priv, u64 *data,
#define MLX5_BASIC_PPCNT_SUPPORTED(mdev) \
(MLX5_CAP_GEN(mdev, pcam_reg) ? MLX5_CAP_PCAM_REG(mdev, ppcnt) : 1)
-void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(802_3)
{
struct mlx5e_pport_stats *pstats = &priv->stats.pport;
struct mlx5_core_dev *mdev = priv->mdev;
@@ -609,13 +658,12 @@ static const struct counter_desc pport_2863_stats_desc[] = {
#define NUM_PPORT_2863_COUNTERS ARRAY_SIZE(pport_2863_stats_desc)
-static int mlx5e_grp_2863_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(2863)
{
return NUM_PPORT_2863_COUNTERS;
}
-static int mlx5e_grp_2863_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(2863)
{
int i;
@@ -624,8 +672,7 @@ static int mlx5e_grp_2863_fill_strings(struct mlx5e_priv *priv, u8 *data,
return idx;
}
-static int mlx5e_grp_2863_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(2863)
{
int i;
@@ -635,7 +682,7 @@ static int mlx5e_grp_2863_fill_stats(struct mlx5e_priv *priv, u64 *data,
return idx;
}
-static void mlx5e_grp_2863_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(2863)
{
struct mlx5e_pport_stats *pstats = &priv->stats.pport;
struct mlx5_core_dev *mdev = priv->mdev;
@@ -670,13 +717,12 @@ static const struct counter_desc pport_2819_stats_desc[] = {
#define NUM_PPORT_2819_COUNTERS ARRAY_SIZE(pport_2819_stats_desc)
-static int mlx5e_grp_2819_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(2819)
{
return NUM_PPORT_2819_COUNTERS;
}
-static int mlx5e_grp_2819_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(2819)
{
int i;
@@ -685,8 +731,7 @@ static int mlx5e_grp_2819_fill_strings(struct mlx5e_priv *priv, u8 *data,
return idx;
}
-static int mlx5e_grp_2819_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(2819)
{
int i;
@@ -696,7 +741,7 @@ static int mlx5e_grp_2819_fill_stats(struct mlx5e_priv *priv, u64 *data,
return idx;
}
-static void mlx5e_grp_2819_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(2819)
{
struct mlx5e_pport_stats *pstats = &priv->stats.pport;
struct mlx5_core_dev *mdev = priv->mdev;
@@ -734,7 +779,7 @@ pport_phy_statistical_err_lanes_stats_desc[] = {
#define NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS \
ARRAY_SIZE(pport_phy_statistical_err_lanes_stats_desc)
-static int mlx5e_grp_phy_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(phy)
{
struct mlx5_core_dev *mdev = priv->mdev;
int num_stats;
@@ -751,8 +796,7 @@ static int mlx5e_grp_phy_get_num_stats(struct mlx5e_priv *priv)
return num_stats;
}
-static int mlx5e_grp_phy_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(phy)
{
struct mlx5_core_dev *mdev = priv->mdev;
int i;
@@ -774,7 +818,7 @@ static int mlx5e_grp_phy_fill_strings(struct mlx5e_priv *priv, u8 *data,
return idx;
}
-static int mlx5e_grp_phy_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
{
struct mlx5_core_dev *mdev = priv->mdev;
int i;
@@ -800,7 +844,7 @@ static int mlx5e_grp_phy_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
return idx;
}
-static void mlx5e_grp_phy_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(phy)
{
struct mlx5e_pport_stats *pstats = &priv->stats.pport;
struct mlx5_core_dev *mdev = priv->mdev;
@@ -830,7 +874,7 @@ static const struct counter_desc pport_eth_ext_stats_desc[] = {
#define NUM_PPORT_ETH_EXT_COUNTERS ARRAY_SIZE(pport_eth_ext_stats_desc)
-static int mlx5e_grp_eth_ext_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(eth_ext)
{
if (MLX5_CAP_PCAM_FEATURE((priv)->mdev, rx_buffer_fullness_counters))
return NUM_PPORT_ETH_EXT_COUNTERS;
@@ -838,8 +882,7 @@ static int mlx5e_grp_eth_ext_get_num_stats(struct mlx5e_priv *priv)
return 0;
}
-static int mlx5e_grp_eth_ext_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(eth_ext)
{
int i;
@@ -850,8 +893,7 @@ static int mlx5e_grp_eth_ext_fill_strings(struct mlx5e_priv *priv, u8 *data,
return idx;
}
-static int mlx5e_grp_eth_ext_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(eth_ext)
{
int i;
@@ -863,7 +905,7 @@ static int mlx5e_grp_eth_ext_fill_stats(struct mlx5e_priv *priv, u64 *data,
return idx;
}
-static void mlx5e_grp_eth_ext_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(eth_ext)
{
struct mlx5e_pport_stats *pstats = &priv->stats.pport;
struct mlx5_core_dev *mdev = priv->mdev;
@@ -904,7 +946,7 @@ static const struct counter_desc pcie_perf_stall_stats_desc[] = {
#define NUM_PCIE_PERF_COUNTERS64 ARRAY_SIZE(pcie_perf_stats_desc64)
#define NUM_PCIE_PERF_STALL_COUNTERS ARRAY_SIZE(pcie_perf_stall_stats_desc)
-static int mlx5e_grp_pcie_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(pcie)
{
int num_stats = 0;
@@ -920,8 +962,7 @@ static int mlx5e_grp_pcie_get_num_stats(struct mlx5e_priv *priv)
return num_stats;
}
-static int mlx5e_grp_pcie_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(pcie)
{
int i;
@@ -942,8 +983,7 @@ static int mlx5e_grp_pcie_fill_strings(struct mlx5e_priv *priv, u8 *data,
return idx;
}
-static int mlx5e_grp_pcie_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pcie)
{
int i;
@@ -967,7 +1007,7 @@ static int mlx5e_grp_pcie_fill_stats(struct mlx5e_priv *priv, u64 *data,
return idx;
}
-static void mlx5e_grp_pcie_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(pcie)
{
struct mlx5e_pcie_stats *pcie_stats = &priv->stats.pcie;
struct mlx5_core_dev *mdev = priv->mdev;
@@ -1015,8 +1055,7 @@ static int mlx5e_grp_per_tc_prio_get_num_stats(struct mlx5e_priv *priv)
return NUM_PPORT_PER_TC_PRIO_COUNTERS * NUM_PPORT_PRIO;
}
-static int mlx5e_grp_per_port_buffer_congest_fill_strings(struct mlx5e_priv *priv,
- u8 *data, int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(per_port_buff_congest)
{
struct mlx5_core_dev *mdev = priv->mdev;
int i, prio;
@@ -1036,8 +1075,7 @@ static int mlx5e_grp_per_port_buffer_congest_fill_strings(struct mlx5e_priv *pri
return idx;
}
-static int mlx5e_grp_per_port_buffer_congest_fill_stats(struct mlx5e_priv *priv,
- u64 *data, int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(per_port_buff_congest)
{
struct mlx5e_pport_stats *pport = &priv->stats.pport;
struct mlx5_core_dev *mdev = priv->mdev;
@@ -1112,13 +1150,13 @@ static void mlx5e_grp_per_tc_congest_prio_update_stats(struct mlx5e_priv *priv)
}
}
-static int mlx5e_grp_per_port_buffer_congest_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(per_port_buff_congest)
{
return mlx5e_grp_per_tc_prio_get_num_stats(priv) +
mlx5e_grp_per_tc_congest_prio_get_num_stats(priv);
}
-static void mlx5e_grp_per_port_buffer_congest_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(per_port_buff_congest)
{
mlx5e_grp_per_tc_prio_update_stats(priv);
mlx5e_grp_per_tc_congest_prio_update_stats(priv);
@@ -1130,6 +1168,7 @@ static void mlx5e_grp_per_port_buffer_congest_update_stats(struct mlx5e_priv *pr
static const struct counter_desc pport_per_prio_traffic_stats_desc[] = {
{ "rx_prio%d_bytes", PPORT_PER_PRIO_OFF(rx_octets) },
{ "rx_prio%d_packets", PPORT_PER_PRIO_OFF(rx_frames) },
+ { "rx_prio%d_discards", PPORT_PER_PRIO_OFF(rx_discards) },
{ "tx_prio%d_bytes", PPORT_PER_PRIO_OFF(tx_octets) },
{ "tx_prio%d_packets", PPORT_PER_PRIO_OFF(tx_frames) },
};
@@ -1292,29 +1331,27 @@ static int mlx5e_grp_per_prio_pfc_fill_stats(struct mlx5e_priv *priv,
return idx;
}
-static int mlx5e_grp_per_prio_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(per_prio)
{
return mlx5e_grp_per_prio_traffic_get_num_stats() +
mlx5e_grp_per_prio_pfc_get_num_stats(priv);
}
-static int mlx5e_grp_per_prio_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(per_prio)
{
idx = mlx5e_grp_per_prio_traffic_fill_strings(priv, data, idx);
idx = mlx5e_grp_per_prio_pfc_fill_strings(priv, data, idx);
return idx;
}
-static int mlx5e_grp_per_prio_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(per_prio)
{
idx = mlx5e_grp_per_prio_traffic_fill_stats(priv, data, idx);
idx = mlx5e_grp_per_prio_pfc_fill_stats(priv, data, idx);
return idx;
}
-static void mlx5e_grp_per_prio_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(per_prio)
{
struct mlx5e_pport_stats *pstats = &priv->stats.pport;
struct mlx5_core_dev *mdev = priv->mdev;
@@ -1349,13 +1386,12 @@ static const struct counter_desc mlx5e_pme_error_desc[] = {
#define NUM_PME_STATUS_STATS ARRAY_SIZE(mlx5e_pme_status_desc)
#define NUM_PME_ERR_STATS ARRAY_SIZE(mlx5e_pme_error_desc)
-static int mlx5e_grp_pme_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(pme)
{
return NUM_PME_STATUS_STATS + NUM_PME_ERR_STATS;
}
-static int mlx5e_grp_pme_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(pme)
{
int i;
@@ -1368,8 +1404,7 @@ static int mlx5e_grp_pme_fill_strings(struct mlx5e_priv *priv, u8 *data,
return idx;
}
-static int mlx5e_grp_pme_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pme)
{
struct mlx5_pme_stats pme_stats;
int i;
@@ -1387,45 +1422,46 @@ static int mlx5e_grp_pme_fill_stats(struct mlx5e_priv *priv, u64 *data,
return idx;
}
-static int mlx5e_grp_ipsec_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(pme) { return; }
+
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec)
{
return mlx5e_ipsec_get_count(priv);
}
-static int mlx5e_grp_ipsec_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec)
{
return idx + mlx5e_ipsec_get_strings(priv,
data + idx * ETH_GSTRING_LEN);
}
-static int mlx5e_grp_ipsec_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec)
{
return idx + mlx5e_ipsec_get_stats(priv, data + idx);
}
-static void mlx5e_grp_ipsec_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec)
{
mlx5e_ipsec_update_stats(priv);
}
-static int mlx5e_grp_tls_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(tls)
{
return mlx5e_tls_get_count(priv);
}
-static int mlx5e_grp_tls_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(tls)
{
return idx + mlx5e_tls_get_strings(priv, data + idx * ETH_GSTRING_LEN);
}
-static int mlx5e_grp_tls_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(tls)
{
return idx + mlx5e_tls_get_stats(priv, data + idx);
}
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(tls) { return; }
+
static const struct counter_desc rq_stats_desc[] = {
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
@@ -1559,7 +1595,7 @@ static const struct counter_desc ch_stats_desc[] = {
#define NUM_XSKSQ_STATS ARRAY_SIZE(xsksq_stats_desc)
#define NUM_CH_STATS ARRAY_SIZE(ch_stats_desc)
-static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels)
{
int max_nch = priv->max_nch;
@@ -1572,8 +1608,7 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
(NUM_XSKSQ_STATS * max_nch * priv->xsk.ever_used);
}
-static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels)
{
bool is_xsk = priv->xsk.ever_used;
int max_nch = priv->max_nch;
@@ -1615,8 +1650,7 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
return idx;
}
-static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
- int idx)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels)
{
bool is_xsk = priv->xsk.ever_used;
int max_nch = priv->max_nch;
@@ -1664,104 +1698,46 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
return idx;
}
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(channels) { return; }
+
+MLX5E_DEFINE_STATS_GRP(sw, 0);
+MLX5E_DEFINE_STATS_GRP(qcnt, MLX5E_NDO_UPDATE_STATS);
+MLX5E_DEFINE_STATS_GRP(vnic_env, 0);
+MLX5E_DEFINE_STATS_GRP(vport, MLX5E_NDO_UPDATE_STATS);
+MLX5E_DEFINE_STATS_GRP(802_3, MLX5E_NDO_UPDATE_STATS);
+MLX5E_DEFINE_STATS_GRP(2863, 0);
+MLX5E_DEFINE_STATS_GRP(2819, 0);
+MLX5E_DEFINE_STATS_GRP(phy, 0);
+MLX5E_DEFINE_STATS_GRP(pcie, 0);
+MLX5E_DEFINE_STATS_GRP(per_prio, 0);
+MLX5E_DEFINE_STATS_GRP(pme, 0);
+MLX5E_DEFINE_STATS_GRP(channels, 0);
+MLX5E_DEFINE_STATS_GRP(per_port_buff_congest, 0);
+MLX5E_DEFINE_STATS_GRP(eth_ext, 0);
+static MLX5E_DEFINE_STATS_GRP(ipsec, 0);
+static MLX5E_DEFINE_STATS_GRP(tls, 0);
+
/* The stats groups order is opposite to the update_stats() order calls */
-const struct mlx5e_stats_grp mlx5e_stats_grps[] = {
- {
- .get_num_stats = mlx5e_grp_sw_get_num_stats,
- .fill_strings = mlx5e_grp_sw_fill_strings,
- .fill_stats = mlx5e_grp_sw_fill_stats,
- .update_stats = mlx5e_grp_sw_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_q_get_num_stats,
- .fill_strings = mlx5e_grp_q_fill_strings,
- .fill_stats = mlx5e_grp_q_fill_stats,
- .update_stats_mask = MLX5E_NDO_UPDATE_STATS,
- .update_stats = mlx5e_grp_q_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_vnic_env_get_num_stats,
- .fill_strings = mlx5e_grp_vnic_env_fill_strings,
- .fill_stats = mlx5e_grp_vnic_env_fill_stats,
- .update_stats = mlx5e_grp_vnic_env_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_vport_get_num_stats,
- .fill_strings = mlx5e_grp_vport_fill_strings,
- .fill_stats = mlx5e_grp_vport_fill_stats,
- .update_stats_mask = MLX5E_NDO_UPDATE_STATS,
- .update_stats = mlx5e_grp_vport_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_802_3_get_num_stats,
- .fill_strings = mlx5e_grp_802_3_fill_strings,
- .fill_stats = mlx5e_grp_802_3_fill_stats,
- .update_stats_mask = MLX5E_NDO_UPDATE_STATS,
- .update_stats = mlx5e_grp_802_3_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_2863_get_num_stats,
- .fill_strings = mlx5e_grp_2863_fill_strings,
- .fill_stats = mlx5e_grp_2863_fill_stats,
- .update_stats = mlx5e_grp_2863_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_2819_get_num_stats,
- .fill_strings = mlx5e_grp_2819_fill_strings,
- .fill_stats = mlx5e_grp_2819_fill_stats,
- .update_stats = mlx5e_grp_2819_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_phy_get_num_stats,
- .fill_strings = mlx5e_grp_phy_fill_strings,
- .fill_stats = mlx5e_grp_phy_fill_stats,
- .update_stats = mlx5e_grp_phy_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_eth_ext_get_num_stats,
- .fill_strings = mlx5e_grp_eth_ext_fill_strings,
- .fill_stats = mlx5e_grp_eth_ext_fill_stats,
- .update_stats = mlx5e_grp_eth_ext_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_pcie_get_num_stats,
- .fill_strings = mlx5e_grp_pcie_fill_strings,
- .fill_stats = mlx5e_grp_pcie_fill_stats,
- .update_stats = mlx5e_grp_pcie_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_per_prio_get_num_stats,
- .fill_strings = mlx5e_grp_per_prio_fill_strings,
- .fill_stats = mlx5e_grp_per_prio_fill_stats,
- .update_stats = mlx5e_grp_per_prio_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_pme_get_num_stats,
- .fill_strings = mlx5e_grp_pme_fill_strings,
- .fill_stats = mlx5e_grp_pme_fill_stats,
- },
- {
- .get_num_stats = mlx5e_grp_ipsec_get_num_stats,
- .fill_strings = mlx5e_grp_ipsec_fill_strings,
- .fill_stats = mlx5e_grp_ipsec_fill_stats,
- .update_stats = mlx5e_grp_ipsec_update_stats,
- },
- {
- .get_num_stats = mlx5e_grp_tls_get_num_stats,
- .fill_strings = mlx5e_grp_tls_fill_strings,
- .fill_stats = mlx5e_grp_tls_fill_stats,
- },
- {
- .get_num_stats = mlx5e_grp_channels_get_num_stats,
- .fill_strings = mlx5e_grp_channels_fill_strings,
- .fill_stats = mlx5e_grp_channels_fill_stats,
- },
- {
- .get_num_stats = mlx5e_grp_per_port_buffer_congest_get_num_stats,
- .fill_strings = mlx5e_grp_per_port_buffer_congest_fill_strings,
- .fill_stats = mlx5e_grp_per_port_buffer_congest_fill_stats,
- .update_stats = mlx5e_grp_per_port_buffer_congest_update_stats,
- },
+mlx5e_stats_grp_t mlx5e_nic_stats_grps[] = {
+ &MLX5E_STATS_GRP(sw),
+ &MLX5E_STATS_GRP(qcnt),
+ &MLX5E_STATS_GRP(vnic_env),
+ &MLX5E_STATS_GRP(vport),
+ &MLX5E_STATS_GRP(802_3),
+ &MLX5E_STATS_GRP(2863),
+ &MLX5E_STATS_GRP(2819),
+ &MLX5E_STATS_GRP(phy),
+ &MLX5E_STATS_GRP(eth_ext),
+ &MLX5E_STATS_GRP(pcie),
+ &MLX5E_STATS_GRP(per_prio),
+ &MLX5E_STATS_GRP(pme),
+ &MLX5E_STATS_GRP(ipsec),
+ &MLX5E_STATS_GRP(tls),
+ &MLX5E_STATS_GRP(channels),
+ &MLX5E_STATS_GRP(per_port_buff_congest),
};
-const int mlx5e_num_stats_grps = ARRAY_SIZE(mlx5e_stats_grps);
+unsigned int mlx5e_nic_stats_grps_num(struct mlx5e_priv *priv)
+{
+ return ARRAY_SIZE(mlx5e_nic_stats_grps);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 869f350..092b39f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -29,6 +29,7 @@
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
+
#ifndef __MLX5_EN_STATS_H__
#define __MLX5_EN_STATS_H__
@@ -55,6 +56,56 @@ struct counter_desc {
size_t offset; /* Byte offset */
};
+enum {
+ MLX5E_NDO_UPDATE_STATS = BIT(0x1),
+};
+
+struct mlx5e_priv;
+struct mlx5e_stats_grp {
+ u16 update_stats_mask;
+ int (*get_num_stats)(struct mlx5e_priv *priv);
+ int (*fill_strings)(struct mlx5e_priv *priv, u8 *data, int idx);
+ int (*fill_stats)(struct mlx5e_priv *priv, u64 *data, int idx);
+ void (*update_stats)(struct mlx5e_priv *priv);
+};
+
+typedef const struct mlx5e_stats_grp *const mlx5e_stats_grp_t;
+
+#define MLX5E_STATS_GRP_OP(grp, name) mlx5e_stats_grp_ ## grp ## _ ## name
+
+#define MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(grp) \
+ int MLX5E_STATS_GRP_OP(grp, num_stats)(struct mlx5e_priv *priv)
+
+#define MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(grp) \
+ void MLX5E_STATS_GRP_OP(grp, update_stats)(struct mlx5e_priv *priv)
+
+#define MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(grp) \
+ int MLX5E_STATS_GRP_OP(grp, fill_strings)(struct mlx5e_priv *priv, u8 *data, int idx)
+
+#define MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(grp) \
+ int MLX5E_STATS_GRP_OP(grp, fill_stats)(struct mlx5e_priv *priv, u64 *data, int idx)
+
+#define MLX5E_STATS_GRP(grp) mlx5e_stats_grp_ ## grp
+
+#define MLX5E_DECLARE_STATS_GRP(grp) \
+ const struct mlx5e_stats_grp MLX5E_STATS_GRP(grp)
+
+#define MLX5E_DEFINE_STATS_GRP(grp, mask) \
+MLX5E_DECLARE_STATS_GRP(grp) = { \
+ .get_num_stats = MLX5E_STATS_GRP_OP(grp, num_stats), \
+ .fill_stats = MLX5E_STATS_GRP_OP(grp, fill_stats), \
+ .fill_strings = MLX5E_STATS_GRP_OP(grp, fill_strings), \
+ .update_stats = MLX5E_STATS_GRP_OP(grp, update_stats), \
+ .update_stats_mask = mask, \
+}
+
+unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv);
+void mlx5e_stats_update(struct mlx5e_priv *priv);
+void mlx5e_stats_fill(struct mlx5e_priv *priv, u64 *data, int idx);
+void mlx5e_stats_fill_strings(struct mlx5e_priv *priv, u8 *data);
+
+/* Concrete NIC Stats */
+
struct mlx5e_sw_stats {
u64 rx_packets;
u64 rx_bytes;
@@ -322,22 +373,22 @@ struct mlx5e_stats {
struct mlx5e_pcie_stats pcie;
};
-enum {
- MLX5E_NDO_UPDATE_STATS = BIT(0x1),
-};
+extern mlx5e_stats_grp_t mlx5e_nic_stats_grps[];
+unsigned int mlx5e_nic_stats_grps_num(struct mlx5e_priv *priv);
-struct mlx5e_priv;
-struct mlx5e_stats_grp {
- u16 update_stats_mask;
- int (*get_num_stats)(struct mlx5e_priv *priv);
- int (*fill_strings)(struct mlx5e_priv *priv, u8 *data, int idx);
- int (*fill_stats)(struct mlx5e_priv *priv, u64 *data, int idx);
- void (*update_stats)(struct mlx5e_priv *priv);
-};
-
-extern const struct mlx5e_stats_grp mlx5e_stats_grps[];
-extern const int mlx5e_num_stats_grps;
-
-void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv);
+extern MLX5E_DECLARE_STATS_GRP(sw);
+extern MLX5E_DECLARE_STATS_GRP(qcnt);
+extern MLX5E_DECLARE_STATS_GRP(vnic_env);
+extern MLX5E_DECLARE_STATS_GRP(vport);
+extern MLX5E_DECLARE_STATS_GRP(802_3);
+extern MLX5E_DECLARE_STATS_GRP(2863);
+extern MLX5E_DECLARE_STATS_GRP(2819);
+extern MLX5E_DECLARE_STATS_GRP(phy);
+extern MLX5E_DECLARE_STATS_GRP(eth_ext);
+extern MLX5E_DECLARE_STATS_GRP(pcie);
+extern MLX5E_DECLARE_STATS_GRP(per_prio);
+extern MLX5E_DECLARE_STATS_GRP(pme);
+extern MLX5E_DECLARE_STATS_GRP(channels);
+extern MLX5E_DECLARE_STATS_GRP(per_port_buff_congest);
#endif /* __MLX5_EN_STATS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9b32a9c..74091f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -51,6 +51,7 @@
#include "en_rep.h"
#include "en_tc.h"
#include "eswitch.h"
+#include "eswitch_offloads_chains.h"
#include "fs_core.h"
#include "en/port.h"
#include "en/tc_tun.h"
@@ -592,7 +593,7 @@ static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp,
for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
ttc_params->indir_tirn[tt] = hp->indir_tirn[tt];
- ft_attr->max_fte = MLX5E_NUM_TT;
+ ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE;
ft_attr->level = MLX5E_TC_TTC_FT_LEVEL;
ft_attr->prio = MLX5E_TC_PRIO;
}
@@ -960,7 +961,8 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
mutex_lock(&priv->fs.tc.t_lock);
if (IS_ERR_OR_NULL(priv->fs.tc.t)) {
- int tc_grp_size, tc_tbl_size;
+ struct mlx5_flow_table_attr ft_attr = {};
+ int tc_grp_size, tc_tbl_size, tc_num_grps;
u32 max_flow_counter;
max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
@@ -970,13 +972,15 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
tc_tbl_size = min_t(int, tc_grp_size * MLX5E_TC_TABLE_NUM_GROUPS,
BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev, log_max_ft_size)));
+ tc_num_grps = MLX5E_TC_TABLE_NUM_GROUPS;
+ ft_attr.prio = MLX5E_TC_PRIO;
+ ft_attr.max_fte = tc_tbl_size;
+ ft_attr.level = MLX5E_TC_FT_LEVEL;
+ ft_attr.autogroup.max_num_groups = tc_num_grps;
priv->fs.tc.t =
mlx5_create_auto_grouped_flow_table(priv->fs.ns,
- MLX5E_TC_PRIO,
- tc_tbl_size,
- MLX5E_TC_TABLE_NUM_GROUPS,
- MLX5E_TC_FT_LEVEL, 0);
+ &ft_attr);
if (IS_ERR(priv->fs.tc.t)) {
mutex_unlock(&priv->fs.tc.t_lock);
NL_SET_ERR_MSG_MOD(extack,
@@ -1080,7 +1084,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr));
slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
slow_attr->split_count = 0;
- slow_attr->dest_chain = FDB_TC_SLOW_PATH_CHAIN;
+ slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH;
rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr);
if (!IS_ERR(rule))
@@ -1097,7 +1101,7 @@ mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr));
slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
slow_attr->split_count = 0;
- slow_attr->dest_chain = FDB_TC_SLOW_PATH_CHAIN;
+ slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH;
mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr);
flow_flag_clear(flow, SLOW);
}
@@ -1157,19 +1161,18 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
struct netlink_ext_ack *extack)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
- u32 max_chain = mlx5_eswitch_get_chain_range(esw);
struct mlx5_esw_flow_attr *attr = flow->esw_attr;
struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
- u16 max_prio = mlx5_eswitch_get_prio_range(esw);
struct net_device *out_dev, *encap_dev = NULL;
struct mlx5_fc *counter = NULL;
struct mlx5e_rep_priv *rpriv;
struct mlx5e_priv *out_priv;
bool encap_valid = true;
+ u32 max_prio, max_chain;
int err = 0;
int out_index;
- if (!mlx5_eswitch_prios_supported(esw) && attr->prio != 1) {
+ if (!mlx5_esw_chains_prios_supported(esw) && attr->prio != 1) {
NL_SET_ERR_MSG(extack, "E-switch priorities unsupported, upgrade FW");
return -EOPNOTSUPP;
}
@@ -1179,11 +1182,13 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
* FDB_FT_CHAIN which is outside tc range.
* See mlx5e_rep_setup_ft_cb().
*/
+ max_chain = mlx5_esw_chains_get_chain_range(esw);
if (!mlx5e_is_ft_flow(flow) && attr->chain > max_chain) {
NL_SET_ERR_MSG(extack, "Requested chain is out of supported range");
return -EOPNOTSUPP;
}
+ max_prio = mlx5_esw_chains_get_prio_range(esw);
if (attr->prio > max_prio) {
NL_SET_ERR_MSG(extack, "Requested priority is out of supported range");
return -EOPNOTSUPP;
@@ -1805,6 +1810,40 @@ static void *get_match_headers_value(u32 flags,
outer_headers);
}
+static int mlx5e_flower_parse_meta(struct net_device *filter_dev,
+ struct flow_cls_offload *f)
+{
+ struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+ struct netlink_ext_ack *extack = f->common.extack;
+ struct net_device *ingress_dev;
+ struct flow_match_meta match;
+
+ if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META))
+ return 0;
+
+ flow_rule_match_meta(rule, &match);
+ if (match.mask->ingress_ifindex != 0xFFFFFFFF) {
+ NL_SET_ERR_MSG_MOD(extack, "Unsupported ingress ifindex mask");
+ return -EINVAL;
+ }
+
+ ingress_dev = __dev_get_by_index(dev_net(filter_dev),
+ match.key->ingress_ifindex);
+ if (!ingress_dev) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Can't find the ingress port to match on");
+ return -EINVAL;
+ }
+
+ if (ingress_dev != filter_dev) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Can't match on the ingress filter port");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int __parse_cls_flower(struct mlx5e_priv *priv,
struct mlx5_flow_spec *spec,
struct flow_cls_offload *f,
@@ -1825,6 +1864,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
u16 addr_type = 0;
u8 ip_proto = 0;
u8 *match_level;
+ int err;
match_level = outer_match_level;
@@ -1868,6 +1908,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
spec);
}
+ err = mlx5e_flower_parse_meta(filter_dev, f);
+ if (err)
+ return err;
+
if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
struct flow_match_basic match;
@@ -2842,6 +2886,10 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
flow_action_for_each(i, act, flow_action) {
switch (act->id) {
+ case FLOW_ACTION_ACCEPT:
+ action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ break;
case FLOW_ACTION_DROP:
action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
if (MLX5_CAP_FLOWTABLE(priv->mdev,
@@ -2999,6 +3047,25 @@ static struct ip_tunnel_info *dup_tun_info(const struct ip_tunnel_info *tun_info
return kmemdup(tun_info, tun_size, GFP_KERNEL);
}
+static bool is_duplicated_encap_entry(struct mlx5e_priv *priv,
+ struct mlx5e_tc_flow *flow,
+ int out_index,
+ struct mlx5e_encap_entry *e,
+ struct netlink_ext_ack *extack)
+{
+ int i;
+
+ for (i = 0; i < out_index; i++) {
+ if (flow->encaps[i].e != e)
+ continue;
+ NL_SET_ERR_MSG_MOD(extack, "can't duplicate encap action");
+ netdev_err(priv->netdev, "can't duplicate encap action\n");
+ return true;
+ }
+
+ return false;
+}
+
static int mlx5e_attach_encap(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
struct net_device *mirred_dev,
@@ -3034,6 +3101,12 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
/* must verify if encap is valid or not */
if (e) {
+ /* Check that entry was not already attached to this flow */
+ if (is_duplicated_encap_entry(priv, flow, out_index, e, extack)) {
+ err = -EOPNOTSUPP;
+ goto out_err;
+ }
+
mutex_unlock(&esw->offloads.encap_tbl_lock);
wait_for_completion(&e->res_ready);
@@ -3220,6 +3293,26 @@ bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv,
same_hw_devs(priv, netdev_priv(out_dev));
}
+static bool is_duplicated_output_device(struct net_device *dev,
+ struct net_device *out_dev,
+ int *ifindexes, int if_count,
+ struct netlink_ext_ack *extack)
+{
+ int i;
+
+ for (i = 0; i < if_count; i++) {
+ if (ifindexes[i] == out_dev->ifindex) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "can't duplicate output to same device");
+ netdev_err(dev, "can't duplicate output to same device: %s\n",
+ out_dev->name);
+ return true;
+ }
+ }
+
+ return false;
+}
+
static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
struct flow_action *flow_action,
struct mlx5e_tc_flow *flow,
@@ -3231,11 +3324,12 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
const struct ip_tunnel_info *info = NULL;
+ int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS];
bool ft_flow = mlx5e_is_ft_flow(flow);
const struct flow_action_entry *act;
+ int err, i, if_count = 0;
bool encap = false;
u32 action = 0;
- int err, i;
if (!flow_action_has_entries(flow_action))
return -EINVAL;
@@ -3312,6 +3406,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
struct net_device *uplink_upper;
+ if (is_duplicated_output_device(priv->netdev,
+ out_dev,
+ ifindexes,
+ if_count,
+ extack))
+ return -EOPNOTSUPP;
+
+ ifindexes[if_count] = out_dev->ifindex;
+ if_count++;
+
rcu_read_lock();
uplink_upper =
netdev_master_upper_dev_get_rcu(uplink_dev);
@@ -3406,7 +3510,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
break;
case FLOW_ACTION_GOTO: {
u32 dest_chain = act->chain_index;
- u32 max_chain = mlx5_eswitch_get_chain_range(esw);
+ u32 max_chain = mlx5_esw_chains_get_chain_range(esw);
if (ft_flow) {
NL_SET_ERR_MSG_MOD(extack, "Goto action is not supported");
@@ -3980,6 +4084,13 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate,
u32 rate_mbps;
int err;
+ vport_num = rpriv->rep->vport;
+ if (vport_num >= MLX5_VPORT_ECPF) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Ingress rate limit is supported only for Eswitch ports connected to VFs");
+ return -EOPNOTSUPP;
+ }
+
esw = priv->mdev->priv.eswitch;
/* rate is given in bytes/sec.
* First convert to bits/sec and then round to the nearest mbit/secs.
@@ -3988,8 +4099,6 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate,
* 1 mbit/sec.
*/
rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0;
- vport_num = rpriv->rep->vport;
-
err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps);
if (err)
NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware");
@@ -4142,7 +4251,10 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
return err;
tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event;
- if (register_netdevice_notifier(&tc->netdevice_nb)) {
+ err = register_netdevice_notifier_dev_net(priv->netdev,
+ &tc->netdevice_nb,
+ &tc->netdevice_nn);
+ if (err) {
tc->netdevice_nb.notifier_call = NULL;
mlx5_core_warn(priv->mdev, "Failed to register netdev notifier\n");
}
@@ -4164,7 +4276,9 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
struct mlx5e_tc_table *tc = &priv->fs.tc;
if (tc->netdevice_nb.notifier_call)
- unregister_netdevice_notifier(&tc->netdevice_nb);
+ unregister_netdevice_notifier_dev_net(priv->netdev,
+ &tc->netdevice_nb,
+ &tc->netdevice_nn);
mutex_destroy(&tc->mod_hdr.lock);
mutex_destroy(&tc->hairpin_tbl_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 580c71c..cccea3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -156,7 +156,8 @@ static int mlx5_eq_comp_int(struct notifier_block *nb,
cq->comp(cq, eqe);
mlx5_cq_put(cq);
} else {
- mlx5_core_warn(eq->dev, "Completion event for bogus CQ 0x%x\n", cqn);
+ dev_dbg_ratelimited(eq->dev->device,
+ "Completion event for bogus CQ 0x%x\n", cqn);
}
++eq->cons_index;
@@ -563,6 +564,39 @@ static void gather_async_events_mask(struct mlx5_core_dev *dev, u64 mask[4])
gather_user_async_events(dev, mask);
}
+static int
+setup_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq_async *eq,
+ struct mlx5_eq_param *param, const char *name)
+{
+ int err;
+
+ eq->irq_nb.notifier_call = mlx5_eq_async_int;
+
+ err = create_async_eq(dev, &eq->core, param);
+ if (err) {
+ mlx5_core_warn(dev, "failed to create %s EQ %d\n", name, err);
+ return err;
+ }
+ err = mlx5_eq_enable(dev, &eq->core, &eq->irq_nb);
+ if (err) {
+ mlx5_core_warn(dev, "failed to enable %s EQ %d\n", name, err);
+ destroy_async_eq(dev, &eq->core);
+ }
+ return err;
+}
+
+static void cleanup_async_eq(struct mlx5_core_dev *dev,
+ struct mlx5_eq_async *eq, const char *name)
+{
+ int err;
+
+ mlx5_eq_disable(dev, &eq->core, &eq->irq_nb);
+ err = destroy_async_eq(dev, &eq->core);
+ if (err)
+ mlx5_core_err(dev, "failed to destroy %s eq, err(%d)\n",
+ name, err);
+}
+
static int create_async_eqs(struct mlx5_core_dev *dev)
{
struct mlx5_eq_table *table = dev->priv.eq_table;
@@ -572,77 +606,45 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
MLX5_NB_INIT(&table->cq_err_nb, cq_err_event_notifier, CQ_ERROR);
mlx5_eq_notifier_register(dev, &table->cq_err_nb);
- table->cmd_eq.irq_nb.notifier_call = mlx5_eq_async_int;
param = (struct mlx5_eq_param) {
.irq_index = 0,
.nent = MLX5_NUM_CMD_EQE,
+ .mask[0] = 1ull << MLX5_EVENT_TYPE_CMD,
};
-
- param.mask[0] = 1ull << MLX5_EVENT_TYPE_CMD;
- err = create_async_eq(dev, &table->cmd_eq.core, ¶m);
- if (err) {
- mlx5_core_warn(dev, "failed to create cmd EQ %d\n", err);
- goto err0;
- }
- err = mlx5_eq_enable(dev, &table->cmd_eq.core, &table->cmd_eq.irq_nb);
- if (err) {
- mlx5_core_warn(dev, "failed to enable cmd EQ %d\n", err);
+ err = setup_async_eq(dev, &table->cmd_eq, ¶m, "cmd");
+ if (err)
goto err1;
- }
+
mlx5_cmd_use_events(dev);
- table->async_eq.irq_nb.notifier_call = mlx5_eq_async_int;
param = (struct mlx5_eq_param) {
.irq_index = 0,
.nent = MLX5_NUM_ASYNC_EQE,
};
gather_async_events_mask(dev, param.mask);
- err = create_async_eq(dev, &table->async_eq.core, ¶m);
- if (err) {
- mlx5_core_warn(dev, "failed to create async EQ %d\n", err);
+ err = setup_async_eq(dev, &table->async_eq, ¶m, "async");
+ if (err)
goto err2;
- }
- err = mlx5_eq_enable(dev, &table->async_eq.core,
- &table->async_eq.irq_nb);
- if (err) {
- mlx5_core_warn(dev, "failed to enable async EQ %d\n", err);
- goto err3;
- }
- table->pages_eq.irq_nb.notifier_call = mlx5_eq_async_int;
param = (struct mlx5_eq_param) {
.irq_index = 0,
.nent = /* TODO: sriov max_vf + */ 1,
+ .mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST,
};
- param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST;
- err = create_async_eq(dev, &table->pages_eq.core, ¶m);
- if (err) {
- mlx5_core_warn(dev, "failed to create pages EQ %d\n", err);
- goto err4;
- }
- err = mlx5_eq_enable(dev, &table->pages_eq.core,
- &table->pages_eq.irq_nb);
- if (err) {
- mlx5_core_warn(dev, "failed to enable pages EQ %d\n", err);
- goto err5;
- }
+ err = setup_async_eq(dev, &table->pages_eq, ¶m, "pages");
+ if (err)
+ goto err3;
- return err;
+ return 0;
-err5:
- destroy_async_eq(dev, &table->pages_eq.core);
-err4:
- mlx5_eq_disable(dev, &table->async_eq.core, &table->async_eq.irq_nb);
err3:
- destroy_async_eq(dev, &table->async_eq.core);
+ cleanup_async_eq(dev, &table->async_eq, "async");
err2:
mlx5_cmd_use_polling(dev);
- mlx5_eq_disable(dev, &table->cmd_eq.core, &table->cmd_eq.irq_nb);
+ cleanup_async_eq(dev, &table->cmd_eq, "cmd");
err1:
- destroy_async_eq(dev, &table->cmd_eq.core);
-err0:
mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
return err;
}
@@ -650,28 +652,11 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
static void destroy_async_eqs(struct mlx5_core_dev *dev)
{
struct mlx5_eq_table *table = dev->priv.eq_table;
- int err;
- mlx5_eq_disable(dev, &table->pages_eq.core, &table->pages_eq.irq_nb);
- err = destroy_async_eq(dev, &table->pages_eq.core);
- if (err)
- mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n",
- err);
-
- mlx5_eq_disable(dev, &table->async_eq.core, &table->async_eq.irq_nb);
- err = destroy_async_eq(dev, &table->async_eq.core);
- if (err)
- mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n",
- err);
-
+ cleanup_async_eq(dev, &table->pages_eq, "pages");
+ cleanup_async_eq(dev, &table->async_eq, "async");
mlx5_cmd_use_polling(dev);
-
- mlx5_eq_disable(dev, &table->cmd_eq.core, &table->cmd_eq.irq_nb);
- err = destroy_async_eq(dev, &table->cmd_eq.core);
- if (err)
- mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n",
- err);
-
+ cleanup_async_eq(dev, &table->cmd_eq, "cmd");
mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 2c965ad..5acf60b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -277,6 +277,7 @@ enum {
static int esw_create_legacy_vepa_table(struct mlx5_eswitch *esw)
{
+ struct mlx5_flow_table_attr ft_attr = {};
struct mlx5_core_dev *dev = esw->dev;
struct mlx5_flow_namespace *root_ns;
struct mlx5_flow_table *fdb;
@@ -289,8 +290,10 @@ static int esw_create_legacy_vepa_table(struct mlx5_eswitch *esw)
}
/* num FTE 2, num FG 2 */
- fdb = mlx5_create_auto_grouped_flow_table(root_ns, LEGACY_VEPA_PRIO,
- 2, 2, 0, 0);
+ ft_attr.prio = LEGACY_VEPA_PRIO;
+ ft_attr.max_fte = 2;
+ ft_attr.autogroup.max_num_groups = 2;
+ fdb = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr);
if (IS_ERR(fdb)) {
err = PTR_ERR(fdb);
esw_warn(dev, "Failed to create VEPA FDB err %d\n", err);
@@ -1928,8 +1931,10 @@ static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw)
struct mlx5_vport *vport;
int i;
- mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+ mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
memset(&vport->info, 0, sizeof(vport->info));
+ vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+ }
}
/* Public E-Switch API */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index ffcff3b..4472710 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -157,7 +157,7 @@ enum offloads_fdb_flags {
ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED = BIT(0),
};
-extern const unsigned int ESW_POOLS[4];
+struct mlx5_esw_chains_priv;
struct mlx5_eswitch_fdb {
union {
@@ -182,14 +182,7 @@ struct mlx5_eswitch_fdb {
struct mlx5_flow_handle *miss_rule_multi;
int vlan_push_pop_refcount;
- struct {
- struct mlx5_flow_table *fdb;
- u32 num_rules;
- } fdb_prio[FDB_NUM_CHAINS][FDB_TC_MAX_PRIO + 1][FDB_TC_LEVELS_PER_PRIO];
- /* Protects fdb_prio table */
- struct mutex fdb_prio_lock;
-
- int fdb_left[ARRAY_SIZE(ESW_POOLS)];
+ struct mlx5_esw_chains_priv *esw_chains_priv;
} offloads;
};
u32 flags;
@@ -355,15 +348,6 @@ mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_handle *rule,
struct mlx5_esw_flow_attr *attr);
-bool
-mlx5_eswitch_prios_supported(struct mlx5_eswitch *esw);
-
-u16
-mlx5_eswitch_get_prio_range(struct mlx5_eswitch *esw);
-
-u32
-mlx5_eswitch_get_chain_range(struct mlx5_eswitch *esw);
-
struct mlx5_flow_handle *
mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport,
struct mlx5_flow_destination *dest);
@@ -388,6 +372,11 @@ enum {
MLX5_ESW_DEST_ENCAP_VALID = BIT(1),
};
+enum {
+ MLX5_ESW_ATTR_FLAG_VLAN_HANDLED = BIT(0),
+ MLX5_ESW_ATTR_FLAG_SLOW_PATH = BIT(1),
+};
+
struct mlx5_esw_flow_attr {
struct mlx5_eswitch_rep *in_rep;
struct mlx5_core_dev *in_mdev;
@@ -401,7 +390,6 @@ struct mlx5_esw_flow_attr {
u16 vlan_vid[MLX5_FS_VLAN_DEPTH];
u8 vlan_prio[MLX5_FS_VLAN_DEPTH];
u8 total_vlan;
- bool vlan_handled;
struct {
u32 flags;
struct mlx5_eswitch_rep *rep;
@@ -416,6 +404,7 @@ struct mlx5_esw_flow_attr {
u32 chain;
u16 prio;
u32 dest_chain;
+ u32 flags;
struct mlx5e_tc_flow_parse_attr *parse_attr;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 243a544..979f13b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -37,6 +37,7 @@
#include <linux/mlx5/fs.h>
#include "mlx5_core.h"
#include "eswitch.h"
+#include "eswitch_offloads_chains.h"
#include "rdma.h"
#include "en.h"
#include "fs_core.h"
@@ -47,10 +48,6 @@
* one for multicast.
*/
#define MLX5_ESW_MISS_FLOWS (2)
-
-#define fdb_prio_table(esw, chain, prio, level) \
- (esw)->fdb_table.offloads.fdb_prio[(chain)][(prio)][(level)]
-
#define UPLINK_REP_INDEX 0
static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw,
@@ -62,32 +59,6 @@ static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw,
return &esw->offloads.vport_reps[idx];
}
-static struct mlx5_flow_table *
-esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level);
-static void
-esw_put_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level);
-
-bool mlx5_eswitch_prios_supported(struct mlx5_eswitch *esw)
-{
- return (!!(esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED));
-}
-
-u32 mlx5_eswitch_get_chain_range(struct mlx5_eswitch *esw)
-{
- if (esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)
- return FDB_TC_MAX_CHAIN;
-
- return 0;
-}
-
-u16 mlx5_eswitch_get_prio_range(struct mlx5_eswitch *esw)
-{
- if (esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)
- return FDB_TC_MAX_PRIO;
-
- return 1;
-}
-
static bool
esw_check_ingress_prio_tag_enabled(const struct mlx5_eswitch *esw,
const struct mlx5_vport *vport)
@@ -175,10 +146,17 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
}
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
- if (attr->dest_chain) {
- struct mlx5_flow_table *ft;
+ struct mlx5_flow_table *ft;
- ft = esw_get_prio_table(esw, attr->dest_chain, 1, 0);
+ if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) {
+ flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+ dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+ dest[i].ft = mlx5_esw_chains_get_tc_end_ft(esw);
+ i++;
+ } else if (attr->dest_chain) {
+ flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+ ft = mlx5_esw_chains_get_table(esw, attr->dest_chain,
+ 1, 0);
if (IS_ERR(ft)) {
rule = ERR_CAST(ft);
goto err_create_goto_table;
@@ -223,7 +201,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
flow_act.modify_hdr = attr->modify_hdr;
- fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split);
+ fdb = mlx5_esw_chains_get_table(esw, attr->chain, attr->prio,
+ !!split);
if (IS_ERR(fdb)) {
rule = ERR_CAST(fdb);
goto err_esw_get;
@@ -242,10 +221,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
return rule;
err_add_rule:
- esw_put_prio_table(esw, attr->chain, attr->prio, !!split);
+ mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, !!split);
err_esw_get:
- if (attr->dest_chain)
- esw_put_prio_table(esw, attr->dest_chain, 1, 0);
+ if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) && attr->dest_chain)
+ mlx5_esw_chains_put_table(esw, attr->dest_chain, 1, 0);
err_create_goto_table:
return rule;
}
@@ -262,13 +241,13 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_handle *rule;
int i;
- fast_fdb = esw_get_prio_table(esw, attr->chain, attr->prio, 0);
+ fast_fdb = mlx5_esw_chains_get_table(esw, attr->chain, attr->prio, 0);
if (IS_ERR(fast_fdb)) {
rule = ERR_CAST(fast_fdb);
goto err_get_fast;
}
- fwd_fdb = esw_get_prio_table(esw, attr->chain, attr->prio, 1);
+ fwd_fdb = mlx5_esw_chains_get_table(esw, attr->chain, attr->prio, 1);
if (IS_ERR(fwd_fdb)) {
rule = ERR_CAST(fwd_fdb);
goto err_get_fwd;
@@ -296,6 +275,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
if (attr->outer_match_level != MLX5_MATCH_NONE)
spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
+ flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
rule = mlx5_add_flow_rules(fast_fdb, spec, &flow_act, dest, i);
if (IS_ERR(rule))
@@ -305,9 +285,9 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
return rule;
add_err:
- esw_put_prio_table(esw, attr->chain, attr->prio, 1);
+ mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 1);
err_get_fwd:
- esw_put_prio_table(esw, attr->chain, attr->prio, 0);
+ mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0);
err_get_fast:
return rule;
}
@@ -332,12 +312,13 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
atomic64_dec(&esw->offloads.num_flows);
if (fwd_rule) {
- esw_put_prio_table(esw, attr->chain, attr->prio, 1);
- esw_put_prio_table(esw, attr->chain, attr->prio, 0);
+ mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 1);
+ mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0);
} else {
- esw_put_prio_table(esw, attr->chain, attr->prio, !!split);
+ mlx5_esw_chains_put_table(esw, attr->chain, attr->prio,
+ !!split);
if (attr->dest_chain)
- esw_put_prio_table(esw, attr->dest_chain, 1, 0);
+ mlx5_esw_chains_put_table(esw, attr->dest_chain, 1, 0);
}
}
@@ -451,7 +432,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
if (err)
goto unlock;
- attr->vlan_handled = false;
+ attr->flags &= ~MLX5_ESW_ATTR_FLAG_VLAN_HANDLED;
vport = esw_vlan_action_get_vport(attr, push, pop);
@@ -459,7 +440,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
/* tracks VF --> wire rules without vlan push action */
if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
vport->vlan_refcount++;
- attr->vlan_handled = true;
+ attr->flags |= MLX5_ESW_ATTR_FLAG_VLAN_HANDLED;
}
goto unlock;
@@ -490,7 +471,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
}
out:
if (!err)
- attr->vlan_handled = true;
+ attr->flags |= MLX5_ESW_ATTR_FLAG_VLAN_HANDLED;
unlock:
mutex_unlock(&esw->state_lock);
return err;
@@ -508,7 +489,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
return 0;
- if (!attr->vlan_handled)
+ if (!(attr->flags & MLX5_ESW_ATTR_FLAG_VLAN_HANDLED))
return 0;
push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
@@ -582,8 +563,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, u16 vport,
dest.vport.num = vport;
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
- flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
- &flow_act, &dest, 1);
+ flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+ spec, &flow_act, &dest, 1);
if (IS_ERR(flow_rule))
esw_warn(esw->dev, "FDB: Failed to add send to vport rule err %ld\n", PTR_ERR(flow_rule));
out:
@@ -824,8 +805,8 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
dest.vport.num = esw->manager_vport;
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
- flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
- &flow_act, &dest, 1);
+ flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+ spec, &flow_act, &dest, 1);
if (IS_ERR(flow_rule)) {
err = PTR_ERR(flow_rule);
esw_warn(esw->dev, "FDB: Failed to add unicast miss flow rule err %d\n", err);
@@ -839,8 +820,8 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v,
outer_headers.dmac_47_16);
dmac_v[0] = 0x01;
- flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
- &flow_act, &dest, 1);
+ flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+ spec, &flow_act, &dest, 1);
if (IS_ERR(flow_rule)) {
err = PTR_ERR(flow_rule);
esw_warn(esw->dev, "FDB: Failed to add multicast miss flow rule err %d\n", err);
@@ -855,174 +836,6 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
return err;
}
-#define ESW_OFFLOADS_NUM_GROUPS 4
-
-/* Firmware currently has 4 pool of 4 sizes that it supports (ESW_POOLS),
- * and a virtual memory region of 16M (ESW_SIZE), this region is duplicated
- * for each flow table pool. We can allocate up to 16M of each pool,
- * and we keep track of how much we used via put/get_sz_to_pool.
- * Firmware doesn't report any of this for now.
- * ESW_POOL is expected to be sorted from large to small
- */
-#define ESW_SIZE (16 * 1024 * 1024)
-const unsigned int ESW_POOLS[4] = { 4 * 1024 * 1024, 1 * 1024 * 1024,
- 64 * 1024, 4 * 1024 };
-
-static int
-get_sz_from_pool(struct mlx5_eswitch *esw)
-{
- int sz = 0, i;
-
- for (i = 0; i < ARRAY_SIZE(ESW_POOLS); i++) {
- if (esw->fdb_table.offloads.fdb_left[i]) {
- --esw->fdb_table.offloads.fdb_left[i];
- sz = ESW_POOLS[i];
- break;
- }
- }
-
- return sz;
-}
-
-static void
-put_sz_to_pool(struct mlx5_eswitch *esw, int sz)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(ESW_POOLS); i++) {
- if (sz >= ESW_POOLS[i]) {
- ++esw->fdb_table.offloads.fdb_left[i];
- break;
- }
- }
-}
-
-static struct mlx5_flow_table *
-create_next_size_table(struct mlx5_eswitch *esw,
- struct mlx5_flow_namespace *ns,
- u16 table_prio,
- int level,
- u32 flags)
-{
- struct mlx5_flow_table *fdb;
- int sz;
-
- sz = get_sz_from_pool(esw);
- if (!sz)
- return ERR_PTR(-ENOSPC);
-
- fdb = mlx5_create_auto_grouped_flow_table(ns,
- table_prio,
- sz,
- ESW_OFFLOADS_NUM_GROUPS,
- level,
- flags);
- if (IS_ERR(fdb)) {
- esw_warn(esw->dev, "Failed to create FDB Table err %d (table prio: %d, level: %d, size: %d)\n",
- (int)PTR_ERR(fdb), table_prio, level, sz);
- put_sz_to_pool(esw, sz);
- }
-
- return fdb;
-}
-
-static struct mlx5_flow_table *
-esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level)
-{
- struct mlx5_core_dev *dev = esw->dev;
- struct mlx5_flow_table *fdb = NULL;
- struct mlx5_flow_namespace *ns;
- int table_prio, l = 0;
- u32 flags = 0;
-
- if (chain == FDB_TC_SLOW_PATH_CHAIN)
- return esw->fdb_table.offloads.slow_fdb;
-
- mutex_lock(&esw->fdb_table.offloads.fdb_prio_lock);
-
- fdb = fdb_prio_table(esw, chain, prio, level).fdb;
- if (fdb) {
- /* take ref on earlier levels as well */
- while (level >= 0)
- fdb_prio_table(esw, chain, prio, level--).num_rules++;
- mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
- return fdb;
- }
-
- ns = mlx5_get_fdb_sub_ns(dev, chain);
- if (!ns) {
- esw_warn(dev, "Failed to get FDB sub namespace\n");
- mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
- return ERR_PTR(-EOPNOTSUPP);
- }
-
- if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
- flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
- MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
-
- table_prio = prio - 1;
-
- /* create earlier levels for correct fs_core lookup when
- * connecting tables
- */
- for (l = 0; l <= level; l++) {
- if (fdb_prio_table(esw, chain, prio, l).fdb) {
- fdb_prio_table(esw, chain, prio, l).num_rules++;
- continue;
- }
-
- fdb = create_next_size_table(esw, ns, table_prio, l, flags);
- if (IS_ERR(fdb)) {
- l--;
- goto err_create_fdb;
- }
-
- fdb_prio_table(esw, chain, prio, l).fdb = fdb;
- fdb_prio_table(esw, chain, prio, l).num_rules = 1;
- }
-
- mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
- return fdb;
-
-err_create_fdb:
- mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
- if (l >= 0)
- esw_put_prio_table(esw, chain, prio, l);
-
- return fdb;
-}
-
-static void
-esw_put_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level)
-{
- int l;
-
- if (chain == FDB_TC_SLOW_PATH_CHAIN)
- return;
-
- mutex_lock(&esw->fdb_table.offloads.fdb_prio_lock);
-
- for (l = level; l >= 0; l--) {
- if (--(fdb_prio_table(esw, chain, prio, l).num_rules) > 0)
- continue;
-
- put_sz_to_pool(esw, fdb_prio_table(esw, chain, prio, l).fdb->max_fte);
- mlx5_destroy_flow_table(fdb_prio_table(esw, chain, prio, l).fdb);
- fdb_prio_table(esw, chain, prio, l).fdb = NULL;
- }
-
- mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
-}
-
-static void esw_destroy_offloads_fast_fdb_tables(struct mlx5_eswitch *esw)
-{
- /* If lazy creation isn't supported, deref the fast path tables */
- if (!(esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)) {
- esw_put_prio_table(esw, 0, 1, 1);
- esw_put_prio_table(esw, 0, 1, 0);
- }
-}
-
#define MAX_PF_SQ 256
#define MAX_SQ_NVPORTS 32
@@ -1055,16 +868,16 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
struct mlx5_flow_table_attr ft_attr = {};
struct mlx5_core_dev *dev = esw->dev;
- u32 *flow_group_in, max_flow_counter;
struct mlx5_flow_namespace *root_ns;
struct mlx5_flow_table *fdb = NULL;
- int table_size, ix, err = 0, i;
+ u32 flags = 0, *flow_group_in;
+ int table_size, ix, err = 0;
struct mlx5_flow_group *g;
- u32 flags = 0, fdb_max;
void *match_criteria;
u8 *dmac;
esw_debug(esw->dev, "Create offloads FDB Tables\n");
+
flow_group_in = kvzalloc(inlen, GFP_KERNEL);
if (!flow_group_in)
return -ENOMEM;
@@ -1083,19 +896,6 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
goto ns_err;
}
- max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
- MLX5_CAP_GEN(dev, max_flow_counter_15_0);
- fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size);
-
- esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(%d))\n",
- MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size),
- max_flow_counter, ESW_OFFLOADS_NUM_GROUPS,
- fdb_max);
-
- for (i = 0; i < ARRAY_SIZE(ESW_POOLS); i++)
- esw->fdb_table.offloads.fdb_left[i] =
- ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0;
-
table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ +
MLX5_ESW_MISS_FLOWS + esw->total_vports;
@@ -1118,16 +918,10 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
}
esw->fdb_table.offloads.slow_fdb = fdb;
- /* If lazy creation isn't supported, open the fast path tables now */
- if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, multi_fdb_encap) &&
- esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) {
- esw->fdb_table.flags &= ~ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
- esw_warn(dev, "Lazy creation of flow tables isn't supported, ignoring priorities\n");
- esw_get_prio_table(esw, 0, 1, 0);
- esw_get_prio_table(esw, 0, 1, 1);
- } else {
- esw_debug(dev, "Lazy creation of flow tables supported, deferring table opening\n");
- esw->fdb_table.flags |= ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
+ err = mlx5_esw_chains_create(esw);
+ if (err) {
+ esw_warn(dev, "Failed to create fdb chains err(%d)\n", err);
+ goto fdb_chains_err;
}
/* create send-to-vport group */
@@ -1218,7 +1012,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
peer_miss_err:
mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
send_vport_err:
- esw_destroy_offloads_fast_fdb_tables(esw);
+ mlx5_esw_chains_destroy(esw);
+fdb_chains_err:
mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
slow_fdb_err:
/* Holds true only as long as DMFS is the default */
@@ -1240,8 +1035,8 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
+ mlx5_esw_chains_destroy(esw);
mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
- esw_destroy_offloads_fast_fdb_tables(esw);
/* Holds true only as long as DMFS is the default */
mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns,
MLX5_FLOW_STEERING_MODE_DMFS);
@@ -1377,7 +1172,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
return -EINVAL;
}
- mlx5_eswitch_disable(esw, false);
+ mlx5_eswitch_disable(esw, true);
mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
if (err) {
@@ -2111,7 +1906,6 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev);
memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
- mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
err = esw_create_uplink_offloads_acl_tables(esw);
if (err)
@@ -2220,7 +2014,8 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type
int esw_offloads_enable(struct mlx5_eswitch *esw)
{
- int err;
+ struct mlx5_vport *vport;
+ int err, i;
if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap))
@@ -2237,6 +2032,10 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
if (err)
goto err_vport_metadata;
+ /* Representor will control the vport link state */
+ mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+ vport->info.link_state = MLX5_VPORT_ADMIN_STATE_DOWN;
+
err = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE);
if (err)
goto err_vports;
@@ -2266,7 +2065,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
{
int err, err1;
- mlx5_eswitch_disable(esw, false);
+ mlx5_eswitch_disable(esw, true);
err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
if (err) {
NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c
new file mode 100644
index 0000000..c5a446e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c
@@ -0,0 +1,758 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2020 Mellanox Technologies.
+
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/fs.h>
+
+#include "eswitch_offloads_chains.h"
+#include "mlx5_core.h"
+#include "fs_core.h"
+#include "eswitch.h"
+#include "en.h"
+
+#define esw_chains_priv(esw) ((esw)->fdb_table.offloads.esw_chains_priv)
+#define esw_chains_lock(esw) (esw_chains_priv(esw)->lock)
+#define esw_chains_ht(esw) (esw_chains_priv(esw)->chains_ht)
+#define esw_prios_ht(esw) (esw_chains_priv(esw)->prios_ht)
+#define fdb_pool_left(esw) (esw_chains_priv(esw)->fdb_left)
+#define tc_slow_fdb(esw) ((esw)->fdb_table.offloads.slow_fdb)
+#define tc_end_fdb(esw) (esw_chains_priv(esw)->tc_end_fdb)
+#define fdb_ignore_flow_level_supported(esw) \
+ (MLX5_CAP_ESW_FLOWTABLE_FDB((esw)->dev, ignore_flow_level))
+
+#define ESW_OFFLOADS_NUM_GROUPS 4
+
+/* Firmware currently has 4 pool of 4 sizes that it supports (ESW_POOLS),
+ * and a virtual memory region of 16M (ESW_SIZE), this region is duplicated
+ * for each flow table pool. We can allocate up to 16M of each pool,
+ * and we keep track of how much we used via get_next_avail_sz_from_pool.
+ * Firmware doesn't report any of this for now.
+ * ESW_POOL is expected to be sorted from large to small and match firmware
+ * pools.
+ */
+#define ESW_SIZE (16 * 1024 * 1024)
+static const unsigned int ESW_POOLS[] = { 4 * 1024 * 1024,
+ 1 * 1024 * 1024,
+ 64 * 1024,
+ 4 * 1024, };
+
+struct mlx5_esw_chains_priv {
+ struct rhashtable chains_ht;
+ struct rhashtable prios_ht;
+ /* Protects above chains_ht and prios_ht */
+ struct mutex lock;
+
+ struct mlx5_flow_table *tc_end_fdb;
+
+ int fdb_left[ARRAY_SIZE(ESW_POOLS)];
+};
+
+struct fdb_chain {
+ struct rhash_head node;
+
+ u32 chain;
+
+ int ref;
+
+ struct mlx5_eswitch *esw;
+ struct list_head prios_list;
+};
+
+struct fdb_prio_key {
+ u32 chain;
+ u32 prio;
+ u32 level;
+};
+
+struct fdb_prio {
+ struct rhash_head node;
+ struct list_head list;
+
+ struct fdb_prio_key key;
+
+ int ref;
+
+ struct fdb_chain *fdb_chain;
+ struct mlx5_flow_table *fdb;
+ struct mlx5_flow_table *next_fdb;
+ struct mlx5_flow_group *miss_group;
+ struct mlx5_flow_handle *miss_rule;
+};
+
+static const struct rhashtable_params chain_params = {
+ .head_offset = offsetof(struct fdb_chain, node),
+ .key_offset = offsetof(struct fdb_chain, chain),
+ .key_len = sizeof_field(struct fdb_chain, chain),
+ .automatic_shrinking = true,
+};
+
+static const struct rhashtable_params prio_params = {
+ .head_offset = offsetof(struct fdb_prio, node),
+ .key_offset = offsetof(struct fdb_prio, key),
+ .key_len = sizeof_field(struct fdb_prio, key),
+ .automatic_shrinking = true,
+};
+
+bool mlx5_esw_chains_prios_supported(struct mlx5_eswitch *esw)
+{
+ return esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
+}
+
+u32 mlx5_esw_chains_get_chain_range(struct mlx5_eswitch *esw)
+{
+ if (!mlx5_esw_chains_prios_supported(esw))
+ return 1;
+
+ if (fdb_ignore_flow_level_supported(esw))
+ return UINT_MAX - 1;
+
+ return FDB_TC_MAX_CHAIN;
+}
+
+u32 mlx5_esw_chains_get_ft_chain(struct mlx5_eswitch *esw)
+{
+ return mlx5_esw_chains_get_chain_range(esw) + 1;
+}
+
+u32 mlx5_esw_chains_get_prio_range(struct mlx5_eswitch *esw)
+{
+ if (!mlx5_esw_chains_prios_supported(esw))
+ return 1;
+
+ if (fdb_ignore_flow_level_supported(esw))
+ return UINT_MAX;
+
+ return FDB_TC_MAX_PRIO;
+}
+
+static unsigned int mlx5_esw_chains_get_level_range(struct mlx5_eswitch *esw)
+{
+ if (fdb_ignore_flow_level_supported(esw))
+ return UINT_MAX;
+
+ return FDB_TC_LEVELS_PER_PRIO;
+}
+
+#define POOL_NEXT_SIZE 0
+static int
+mlx5_esw_chains_get_avail_sz_from_pool(struct mlx5_eswitch *esw,
+ int desired_size)
+{
+ int i, found_i = -1;
+
+ for (i = ARRAY_SIZE(ESW_POOLS) - 1; i >= 0; i--) {
+ if (fdb_pool_left(esw)[i] && ESW_POOLS[i] > desired_size) {
+ found_i = i;
+ if (desired_size != POOL_NEXT_SIZE)
+ break;
+ }
+ }
+
+ if (found_i != -1) {
+ --fdb_pool_left(esw)[found_i];
+ return ESW_POOLS[found_i];
+ }
+
+ return 0;
+}
+
+static void
+mlx5_esw_chains_put_sz_to_pool(struct mlx5_eswitch *esw, int sz)
+{
+ int i;
+
+ for (i = ARRAY_SIZE(ESW_POOLS) - 1; i >= 0; i--) {
+ if (sz == ESW_POOLS[i]) {
+ ++fdb_pool_left(esw)[i];
+ return;
+ }
+ }
+
+ WARN_ONCE(1, "Couldn't find size %d in fdb size pool", sz);
+}
+
+static void
+mlx5_esw_chains_init_sz_pool(struct mlx5_eswitch *esw)
+{
+ u32 fdb_max;
+ int i;
+
+ fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, log_max_ft_size);
+
+ for (i = ARRAY_SIZE(ESW_POOLS) - 1; i >= 0; i--)
+ fdb_pool_left(esw)[i] =
+ ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0;
+}
+
+static struct mlx5_flow_table *
+mlx5_esw_chains_create_fdb_table(struct mlx5_eswitch *esw,
+ u32 chain, u32 prio, u32 level)
+{
+ struct mlx5_flow_table_attr ft_attr = {};
+ struct mlx5_flow_namespace *ns;
+ struct mlx5_flow_table *fdb;
+ int sz;
+
+ if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
+ ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
+ MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
+
+ sz = mlx5_esw_chains_get_avail_sz_from_pool(esw, POOL_NEXT_SIZE);
+ if (!sz)
+ return ERR_PTR(-ENOSPC);
+ ft_attr.max_fte = sz;
+
+ /* We use tc_slow_fdb(esw) as the table's next_ft till
+ * ignore_flow_level is allowed on FT creation and not just for FTEs.
+ * Instead caller should add an explicit miss rule if needed.
+ */
+ ft_attr.next_ft = tc_slow_fdb(esw);
+
+ /* The root table(chain 0, prio 1, level 0) is required to be
+ * connected to the previous prio (FDB_BYPASS_PATH if exists).
+ * We always create it, as a managed table, in order to align with
+ * fs_core logic.
+ */
+ if (!fdb_ignore_flow_level_supported(esw) ||
+ (chain == 0 && prio == 1 && level == 0)) {
+ ft_attr.level = level;
+ ft_attr.prio = prio - 1;
+ ns = mlx5_get_fdb_sub_ns(esw->dev, chain);
+ } else {
+ ft_attr.flags |= MLX5_FLOW_TABLE_UNMANAGED;
+ ft_attr.prio = FDB_TC_OFFLOAD;
+ /* Firmware doesn't allow us to create another level 0 table,
+ * so we create all unmanaged tables as level 1.
+ *
+ * To connect them, we use explicit miss rules with
+ * ignore_flow_level. Caller is responsible to create
+ * these rules (if needed).
+ */
+ ft_attr.level = 1;
+ ns = mlx5_get_flow_namespace(esw->dev, MLX5_FLOW_NAMESPACE_FDB);
+ }
+
+ ft_attr.autogroup.num_reserved_entries = 2;
+ ft_attr.autogroup.max_num_groups = ESW_OFFLOADS_NUM_GROUPS;
+ fdb = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
+ if (IS_ERR(fdb)) {
+ esw_warn(esw->dev,
+ "Failed to create FDB table err %d (chain: %d, prio: %d, level: %d, size: %d)\n",
+ (int)PTR_ERR(fdb), chain, prio, level, sz);
+ mlx5_esw_chains_put_sz_to_pool(esw, sz);
+ return fdb;
+ }
+
+ return fdb;
+}
+
+static void
+mlx5_esw_chains_destroy_fdb_table(struct mlx5_eswitch *esw,
+ struct mlx5_flow_table *fdb)
+{
+ mlx5_esw_chains_put_sz_to_pool(esw, fdb->max_fte);
+ mlx5_destroy_flow_table(fdb);
+}
+
+static struct fdb_chain *
+mlx5_esw_chains_create_fdb_chain(struct mlx5_eswitch *esw, u32 chain)
+{
+ struct fdb_chain *fdb_chain = NULL;
+ int err;
+
+ fdb_chain = kvzalloc(sizeof(*fdb_chain), GFP_KERNEL);
+ if (!fdb_chain)
+ return ERR_PTR(-ENOMEM);
+
+ fdb_chain->esw = esw;
+ fdb_chain->chain = chain;
+ INIT_LIST_HEAD(&fdb_chain->prios_list);
+
+ err = rhashtable_insert_fast(&esw_chains_ht(esw), &fdb_chain->node,
+ chain_params);
+ if (err)
+ goto err_insert;
+
+ return fdb_chain;
+
+err_insert:
+ kvfree(fdb_chain);
+ return ERR_PTR(err);
+}
+
+static void
+mlx5_esw_chains_destroy_fdb_chain(struct fdb_chain *fdb_chain)
+{
+ struct mlx5_eswitch *esw = fdb_chain->esw;
+
+ rhashtable_remove_fast(&esw_chains_ht(esw), &fdb_chain->node,
+ chain_params);
+ kvfree(fdb_chain);
+}
+
+static struct fdb_chain *
+mlx5_esw_chains_get_fdb_chain(struct mlx5_eswitch *esw, u32 chain)
+{
+ struct fdb_chain *fdb_chain;
+
+ fdb_chain = rhashtable_lookup_fast(&esw_chains_ht(esw), &chain,
+ chain_params);
+ if (!fdb_chain) {
+ fdb_chain = mlx5_esw_chains_create_fdb_chain(esw, chain);
+ if (IS_ERR(fdb_chain))
+ return fdb_chain;
+ }
+
+ fdb_chain->ref++;
+
+ return fdb_chain;
+}
+
+static struct mlx5_flow_handle *
+mlx5_esw_chains_add_miss_rule(struct mlx5_flow_table *fdb,
+ struct mlx5_flow_table *next_fdb)
+{
+ static const struct mlx5_flow_spec spec = {};
+ struct mlx5_flow_destination dest = {};
+ struct mlx5_flow_act act = {};
+
+ act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL | FLOW_ACT_NO_APPEND;
+ act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+ dest.ft = next_fdb;
+
+ return mlx5_add_flow_rules(fdb, &spec, &act, &dest, 1);
+}
+
+static int
+mlx5_esw_chains_update_prio_prevs(struct fdb_prio *fdb_prio,
+ struct mlx5_flow_table *next_fdb)
+{
+ struct mlx5_flow_handle *miss_rules[FDB_TC_LEVELS_PER_PRIO + 1] = {};
+ struct fdb_chain *fdb_chain = fdb_prio->fdb_chain;
+ struct fdb_prio *pos;
+ int n = 0, err;
+
+ if (fdb_prio->key.level)
+ return 0;
+
+ /* Iterate in reverse order until reaching the level 0 rule of
+ * the previous priority, adding all the miss rules first, so we can
+ * revert them if any of them fails.
+ */
+ pos = fdb_prio;
+ list_for_each_entry_continue_reverse(pos,
+ &fdb_chain->prios_list,
+ list) {
+ miss_rules[n] = mlx5_esw_chains_add_miss_rule(pos->fdb,
+ next_fdb);
+ if (IS_ERR(miss_rules[n])) {
+ err = PTR_ERR(miss_rules[n]);
+ goto err_prev_rule;
+ }
+
+ n++;
+ if (!pos->key.level)
+ break;
+ }
+
+ /* Success, delete old miss rules, and update the pointers. */
+ n = 0;
+ pos = fdb_prio;
+ list_for_each_entry_continue_reverse(pos,
+ &fdb_chain->prios_list,
+ list) {
+ mlx5_del_flow_rules(pos->miss_rule);
+
+ pos->miss_rule = miss_rules[n];
+ pos->next_fdb = next_fdb;
+
+ n++;
+ if (!pos->key.level)
+ break;
+ }
+
+ return 0;
+
+err_prev_rule:
+ while (--n >= 0)
+ mlx5_del_flow_rules(miss_rules[n]);
+
+ return err;
+}
+
+static void
+mlx5_esw_chains_put_fdb_chain(struct fdb_chain *fdb_chain)
+{
+ if (--fdb_chain->ref == 0)
+ mlx5_esw_chains_destroy_fdb_chain(fdb_chain);
+}
+
+static struct fdb_prio *
+mlx5_esw_chains_create_fdb_prio(struct mlx5_eswitch *esw,
+ u32 chain, u32 prio, u32 level)
+{
+ int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+ struct mlx5_flow_handle *miss_rule = NULL;
+ struct mlx5_flow_group *miss_group;
+ struct fdb_prio *fdb_prio = NULL;
+ struct mlx5_flow_table *next_fdb;
+ struct fdb_chain *fdb_chain;
+ struct mlx5_flow_table *fdb;
+ struct list_head *pos;
+ u32 *flow_group_in;
+ int err;
+
+ fdb_chain = mlx5_esw_chains_get_fdb_chain(esw, chain);
+ if (IS_ERR(fdb_chain))
+ return ERR_CAST(fdb_chain);
+
+ fdb_prio = kvzalloc(sizeof(*fdb_prio), GFP_KERNEL);
+ flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+ if (!fdb_prio || !flow_group_in) {
+ err = -ENOMEM;
+ goto err_alloc;
+ }
+
+ /* Chain's prio list is sorted by prio and level.
+ * And all levels of some prio point to the next prio's level 0.
+ * Example list (prio, level):
+ * (3,0)->(3,1)->(5,0)->(5,1)->(6,1)->(7,0)
+ * In hardware, we will we have the following pointers:
+ * (3,0) -> (5,0) -> (7,0) -> Slow path
+ * (3,1) -> (5,0)
+ * (5,1) -> (7,0)
+ * (6,1) -> (7,0)
+ */
+
+ /* Default miss for each chain: */
+ next_fdb = (chain == mlx5_esw_chains_get_ft_chain(esw)) ?
+ tc_slow_fdb(esw) :
+ tc_end_fdb(esw);
+ list_for_each(pos, &fdb_chain->prios_list) {
+ struct fdb_prio *p = list_entry(pos, struct fdb_prio, list);
+
+ /* exit on first pos that is larger */
+ if (prio < p->key.prio || (prio == p->key.prio &&
+ level < p->key.level)) {
+ /* Get next level 0 table */
+ next_fdb = p->key.level == 0 ? p->fdb : p->next_fdb;
+ break;
+ }
+ }
+
+ fdb = mlx5_esw_chains_create_fdb_table(esw, chain, prio, level);
+ if (IS_ERR(fdb)) {
+ err = PTR_ERR(fdb);
+ goto err_create;
+ }
+
+ MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index,
+ fdb->max_fte - 2);
+ MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+ fdb->max_fte - 1);
+ miss_group = mlx5_create_flow_group(fdb, flow_group_in);
+ if (IS_ERR(miss_group)) {
+ err = PTR_ERR(miss_group);
+ goto err_group;
+ }
+
+ /* Add miss rule to next_fdb */
+ miss_rule = mlx5_esw_chains_add_miss_rule(fdb, next_fdb);
+ if (IS_ERR(miss_rule)) {
+ err = PTR_ERR(miss_rule);
+ goto err_miss_rule;
+ }
+
+ fdb_prio->miss_group = miss_group;
+ fdb_prio->miss_rule = miss_rule;
+ fdb_prio->next_fdb = next_fdb;
+ fdb_prio->fdb_chain = fdb_chain;
+ fdb_prio->key.chain = chain;
+ fdb_prio->key.prio = prio;
+ fdb_prio->key.level = level;
+ fdb_prio->fdb = fdb;
+
+ err = rhashtable_insert_fast(&esw_prios_ht(esw), &fdb_prio->node,
+ prio_params);
+ if (err)
+ goto err_insert;
+
+ list_add(&fdb_prio->list, pos->prev);
+
+ /* Table is ready, connect it */
+ err = mlx5_esw_chains_update_prio_prevs(fdb_prio, fdb);
+ if (err)
+ goto err_update;
+
+ kvfree(flow_group_in);
+ return fdb_prio;
+
+err_update:
+ list_del(&fdb_prio->list);
+ rhashtable_remove_fast(&esw_prios_ht(esw), &fdb_prio->node,
+ prio_params);
+err_insert:
+ mlx5_del_flow_rules(miss_rule);
+err_miss_rule:
+ mlx5_destroy_flow_group(miss_group);
+err_group:
+ mlx5_esw_chains_destroy_fdb_table(esw, fdb);
+err_create:
+err_alloc:
+ kvfree(fdb_prio);
+ kvfree(flow_group_in);
+ mlx5_esw_chains_put_fdb_chain(fdb_chain);
+ return ERR_PTR(err);
+}
+
+static void
+mlx5_esw_chains_destroy_fdb_prio(struct mlx5_eswitch *esw,
+ struct fdb_prio *fdb_prio)
+{
+ struct fdb_chain *fdb_chain = fdb_prio->fdb_chain;
+
+ WARN_ON(mlx5_esw_chains_update_prio_prevs(fdb_prio,
+ fdb_prio->next_fdb));
+
+ list_del(&fdb_prio->list);
+ rhashtable_remove_fast(&esw_prios_ht(esw), &fdb_prio->node,
+ prio_params);
+ mlx5_del_flow_rules(fdb_prio->miss_rule);
+ mlx5_destroy_flow_group(fdb_prio->miss_group);
+ mlx5_esw_chains_destroy_fdb_table(esw, fdb_prio->fdb);
+ mlx5_esw_chains_put_fdb_chain(fdb_chain);
+ kvfree(fdb_prio);
+}
+
+struct mlx5_flow_table *
+mlx5_esw_chains_get_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
+ u32 level)
+{
+ struct mlx5_flow_table *prev_fts;
+ struct fdb_prio *fdb_prio;
+ struct fdb_prio_key key;
+ int l = 0;
+
+ if ((chain > mlx5_esw_chains_get_chain_range(esw) &&
+ chain != mlx5_esw_chains_get_ft_chain(esw)) ||
+ prio > mlx5_esw_chains_get_prio_range(esw) ||
+ level > mlx5_esw_chains_get_level_range(esw))
+ return ERR_PTR(-EOPNOTSUPP);
+
+ /* create earlier levels for correct fs_core lookup when
+ * connecting tables.
+ */
+ for (l = 0; l < level; l++) {
+ prev_fts = mlx5_esw_chains_get_table(esw, chain, prio, l);
+ if (IS_ERR(prev_fts)) {
+ fdb_prio = ERR_CAST(prev_fts);
+ goto err_get_prevs;
+ }
+ }
+
+ key.chain = chain;
+ key.prio = prio;
+ key.level = level;
+
+ mutex_lock(&esw_chains_lock(esw));
+ fdb_prio = rhashtable_lookup_fast(&esw_prios_ht(esw), &key,
+ prio_params);
+ if (!fdb_prio) {
+ fdb_prio = mlx5_esw_chains_create_fdb_prio(esw, chain,
+ prio, level);
+ if (IS_ERR(fdb_prio))
+ goto err_create_prio;
+ }
+
+ ++fdb_prio->ref;
+ mutex_unlock(&esw_chains_lock(esw));
+
+ return fdb_prio->fdb;
+
+err_create_prio:
+ mutex_unlock(&esw_chains_lock(esw));
+err_get_prevs:
+ while (--l >= 0)
+ mlx5_esw_chains_put_table(esw, chain, prio, l);
+ return ERR_CAST(fdb_prio);
+}
+
+void
+mlx5_esw_chains_put_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
+ u32 level)
+{
+ struct fdb_prio *fdb_prio;
+ struct fdb_prio_key key;
+
+ key.chain = chain;
+ key.prio = prio;
+ key.level = level;
+
+ mutex_lock(&esw_chains_lock(esw));
+ fdb_prio = rhashtable_lookup_fast(&esw_prios_ht(esw), &key,
+ prio_params);
+ if (!fdb_prio)
+ goto err_get_prio;
+
+ if (--fdb_prio->ref == 0)
+ mlx5_esw_chains_destroy_fdb_prio(esw, fdb_prio);
+ mutex_unlock(&esw_chains_lock(esw));
+
+ while (level-- > 0)
+ mlx5_esw_chains_put_table(esw, chain, prio, level);
+
+ return;
+
+err_get_prio:
+ mutex_unlock(&esw_chains_lock(esw));
+ WARN_ONCE(1,
+ "Couldn't find table: (chain: %d prio: %d level: %d)",
+ chain, prio, level);
+}
+
+struct mlx5_flow_table *
+mlx5_esw_chains_get_tc_end_ft(struct mlx5_eswitch *esw)
+{
+ return tc_end_fdb(esw);
+}
+
+static int
+mlx5_esw_chains_init(struct mlx5_eswitch *esw)
+{
+ struct mlx5_esw_chains_priv *chains_priv;
+ struct mlx5_core_dev *dev = esw->dev;
+ u32 max_flow_counter, fdb_max;
+ int err;
+
+ chains_priv = kzalloc(sizeof(*chains_priv), GFP_KERNEL);
+ if (!chains_priv)
+ return -ENOMEM;
+ esw_chains_priv(esw) = chains_priv;
+
+ max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
+ MLX5_CAP_GEN(dev, max_flow_counter_15_0);
+ fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size);
+
+ esw_debug(dev,
+ "Init esw offloads chains, max counters(%d), groups(%d), max flow table size(%d)\n",
+ max_flow_counter, ESW_OFFLOADS_NUM_GROUPS, fdb_max);
+
+ mlx5_esw_chains_init_sz_pool(esw);
+
+ if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, multi_fdb_encap) &&
+ esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) {
+ esw->fdb_table.flags &= ~ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
+ esw_warn(dev, "Tc chains and priorities offload aren't supported, update firmware if needed\n");
+ } else {
+ esw->fdb_table.flags |= ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
+ esw_info(dev, "Supported tc offload range - chains: %u, prios: %u\n",
+ mlx5_esw_chains_get_chain_range(esw),
+ mlx5_esw_chains_get_prio_range(esw));
+ }
+
+ err = rhashtable_init(&esw_chains_ht(esw), &chain_params);
+ if (err)
+ goto init_chains_ht_err;
+
+ err = rhashtable_init(&esw_prios_ht(esw), &prio_params);
+ if (err)
+ goto init_prios_ht_err;
+
+ mutex_init(&esw_chains_lock(esw));
+
+ return 0;
+
+init_prios_ht_err:
+ rhashtable_destroy(&esw_chains_ht(esw));
+init_chains_ht_err:
+ kfree(chains_priv);
+ return err;
+}
+
+static void
+mlx5_esw_chains_cleanup(struct mlx5_eswitch *esw)
+{
+ mutex_destroy(&esw_chains_lock(esw));
+ rhashtable_destroy(&esw_prios_ht(esw));
+ rhashtable_destroy(&esw_chains_ht(esw));
+
+ kfree(esw_chains_priv(esw));
+}
+
+static int
+mlx5_esw_chains_open(struct mlx5_eswitch *esw)
+{
+ struct mlx5_flow_table *ft;
+ int err;
+
+ /* Create tc_end_fdb(esw) which is the always created ft chain */
+ ft = mlx5_esw_chains_get_table(esw, mlx5_esw_chains_get_ft_chain(esw),
+ 1, 0);
+ if (IS_ERR(ft))
+ return PTR_ERR(ft);
+
+ tc_end_fdb(esw) = ft;
+
+ /* Always open the root for fast path */
+ ft = mlx5_esw_chains_get_table(esw, 0, 1, 0);
+ if (IS_ERR(ft)) {
+ err = PTR_ERR(ft);
+ goto level_0_err;
+ }
+
+ /* Open level 1 for split rules now if prios isn't supported */
+ if (!mlx5_esw_chains_prios_supported(esw)) {
+ ft = mlx5_esw_chains_get_table(esw, 0, 1, 1);
+
+ if (IS_ERR(ft)) {
+ err = PTR_ERR(ft);
+ goto level_1_err;
+ }
+ }
+
+ return 0;
+
+level_1_err:
+ mlx5_esw_chains_put_table(esw, 0, 1, 0);
+level_0_err:
+ mlx5_esw_chains_put_table(esw, mlx5_esw_chains_get_ft_chain(esw), 1, 0);
+ return err;
+}
+
+static void
+mlx5_esw_chains_close(struct mlx5_eswitch *esw)
+{
+ if (!mlx5_esw_chains_prios_supported(esw))
+ mlx5_esw_chains_put_table(esw, 0, 1, 1);
+ mlx5_esw_chains_put_table(esw, 0, 1, 0);
+ mlx5_esw_chains_put_table(esw, mlx5_esw_chains_get_ft_chain(esw), 1, 0);
+}
+
+int
+mlx5_esw_chains_create(struct mlx5_eswitch *esw)
+{
+ int err;
+
+ err = mlx5_esw_chains_init(esw);
+ if (err)
+ return err;
+
+ err = mlx5_esw_chains_open(esw);
+ if (err)
+ goto err_open;
+
+ return 0;
+
+err_open:
+ mlx5_esw_chains_cleanup(esw);
+ return err;
+}
+
+void
+mlx5_esw_chains_destroy(struct mlx5_eswitch *esw)
+{
+ mlx5_esw_chains_close(esw);
+ mlx5_esw_chains_cleanup(esw);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.h
new file mode 100644
index 0000000..2e13097
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies. */
+
+#ifndef __ML5_ESW_CHAINS_H__
+#define __ML5_ESW_CHAINS_H__
+
+bool
+mlx5_esw_chains_prios_supported(struct mlx5_eswitch *esw);
+u32
+mlx5_esw_chains_get_prio_range(struct mlx5_eswitch *esw);
+u32
+mlx5_esw_chains_get_chain_range(struct mlx5_eswitch *esw);
+u32
+mlx5_esw_chains_get_ft_chain(struct mlx5_eswitch *esw);
+
+struct mlx5_flow_table *
+mlx5_esw_chains_get_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
+ u32 level);
+void
+mlx5_esw_chains_put_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
+ u32 level);
+
+struct mlx5_flow_table *
+mlx5_esw_chains_get_tc_end_ft(struct mlx5_eswitch *esw);
+
+int mlx5_esw_chains_create(struct mlx5_eswitch *esw);
+void mlx5_esw_chains_destroy(struct mlx5_eswitch *esw);
+
+#endif /* __ML5_ESW_CHAINS_H__ */
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
index 366bda1b..dc08ed9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
@@ -50,8 +50,8 @@ mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev,
struct mlx5_flow_act *flow_act)
{
static const struct mlx5_flow_spec spec = {};
+ struct mlx5_flow_table_attr ft_attr = {};
struct mlx5_flow_namespace *root_ns;
- int prio, flags;
int err;
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
@@ -63,10 +63,11 @@ mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev,
/* As this is the terminating action then the termination table is the
* same prio as the slow path
*/
- prio = FDB_SLOW_PATH;
- flags = MLX5_FLOW_TABLE_TERMINATION;
- tt->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, prio, 1, 1,
- 0, flags);
+ ft_attr.flags = MLX5_FLOW_TABLE_TERMINATION;
+ ft_attr.prio = FDB_SLOW_PATH;
+ ft_attr.max_fte = 1;
+ ft_attr.autogroup.max_num_groups = 1;
+ tt->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr);
if (IS_ERR(tt->termtbl)) {
esw_warn(dev, "Failed to create termination table\n");
return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 3c816e8..b25465d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -432,6 +432,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
MLX5_SET(set_fte_in, in, table_type, ft->type);
MLX5_SET(set_fte_in, in, table_id, ft->id);
MLX5_SET(set_fte_in, in, flow_index, fte->index);
+ MLX5_SET(set_fte_in, in, ignore_flow_level,
+ !!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL));
+
if (ft->vport) {
MLX5_SET(set_fte_in, in, vport_number, ft->vport);
MLX5_SET(set_fte_in, in, other_vport, 1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 9a48c43..c7a16ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -531,16 +531,9 @@ static void del_hw_fte(struct fs_node *node)
}
}
-static void del_sw_fte_rcu(struct rcu_head *head)
-{
- struct fs_fte *fte = container_of(head, struct fs_fte, rcu);
- struct mlx5_flow_steering *steering = get_steering(&fte->node);
-
- kmem_cache_free(steering->ftes_cache, fte);
-}
-
static void del_sw_fte(struct fs_node *node)
{
+ struct mlx5_flow_steering *steering = get_steering(node);
struct mlx5_flow_group *fg;
struct fs_fte *fte;
int err;
@@ -553,8 +546,7 @@ static void del_sw_fte(struct fs_node *node)
rhash_fte);
WARN_ON(err);
ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index);
-
- call_rcu(&fte->rcu, del_sw_fte_rcu);
+ kmem_cache_free(steering->ftes_cache, fte);
}
static void del_hw_flow_group(struct fs_node *node)
@@ -587,7 +579,9 @@ static void del_sw_flow_group(struct fs_node *node)
rhashtable_destroy(&fg->ftes_hash);
ida_destroy(&fg->fte_allocator);
- if (ft->autogroup.active && fg->max_ftes == ft->autogroup.group_size)
+ if (ft->autogroup.active &&
+ fg->max_ftes == ft->autogroup.group_size &&
+ fg->start_index < ft->autogroup.max_fte)
ft->autogroup.num_groups--;
err = rhltable_remove(&ft->fgs_hash,
&fg->hash,
@@ -1014,7 +1008,8 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
u16 vport)
{
struct mlx5_flow_root_namespace *root = find_root(&ns->node);
- struct mlx5_flow_table *next_ft = NULL;
+ bool unmanaged = ft_attr->flags & MLX5_FLOW_TABLE_UNMANAGED;
+ struct mlx5_flow_table *next_ft;
struct fs_prio *fs_prio = NULL;
struct mlx5_flow_table *ft;
int log_table_sz;
@@ -1031,14 +1026,21 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
err = -EINVAL;
goto unlock_root;
}
- if (ft_attr->level >= fs_prio->num_levels) {
- err = -ENOSPC;
- goto unlock_root;
+ if (!unmanaged) {
+ /* The level is related to the
+ * priority level range.
+ */
+ if (ft_attr->level >= fs_prio->num_levels) {
+ err = -ENOSPC;
+ goto unlock_root;
+ }
+
+ ft_attr->level += fs_prio->start_level;
}
+
/* The level is related to the
* priority level range.
*/
- ft_attr->level += fs_prio->start_level;
ft = alloc_flow_table(ft_attr->level,
vport,
ft_attr->max_fte ? roundup_pow_of_two(ft_attr->max_fte) : 0,
@@ -1051,19 +1053,27 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table);
log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0;
- next_ft = find_next_chained_ft(fs_prio);
+ next_ft = unmanaged ? ft_attr->next_ft :
+ find_next_chained_ft(fs_prio);
ft->def_miss_action = ns->def_miss_action;
err = root->cmds->create_flow_table(root, ft, log_table_sz, next_ft);
if (err)
goto free_ft;
- err = connect_flow_table(root->dev, ft, fs_prio);
- if (err)
- goto destroy_ft;
+ if (!unmanaged) {
+ err = connect_flow_table(root->dev, ft, fs_prio);
+ if (err)
+ goto destroy_ft;
+ }
+
ft->node.active = true;
down_write_ref_node(&fs_prio->node, false);
- tree_add_node(&ft->node, &fs_prio->node);
- list_add_flow_table(ft, fs_prio);
+ if (!unmanaged) {
+ tree_add_node(&ft->node, &fs_prio->node);
+ list_add_flow_table(ft, fs_prio);
+ } else {
+ ft->node.root = fs_prio->node.root;
+ }
fs_prio->num_ft++;
up_write_ref_node(&fs_prio->node, false);
mutex_unlock(&root->chain_lock);
@@ -1111,31 +1121,27 @@ EXPORT_SYMBOL(mlx5_create_lag_demux_flow_table);
struct mlx5_flow_table*
mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
- int prio,
- int num_flow_table_entries,
- int max_num_groups,
- u32 level,
- u32 flags)
+ struct mlx5_flow_table_attr *ft_attr)
{
- struct mlx5_flow_table_attr ft_attr = {};
+ int num_reserved_entries = ft_attr->autogroup.num_reserved_entries;
+ int autogroups_max_fte = ft_attr->max_fte - num_reserved_entries;
+ int max_num_groups = ft_attr->autogroup.max_num_groups;
struct mlx5_flow_table *ft;
- if (max_num_groups > num_flow_table_entries)
+ if (max_num_groups > autogroups_max_fte)
+ return ERR_PTR(-EINVAL);
+ if (num_reserved_entries > ft_attr->max_fte)
return ERR_PTR(-EINVAL);
- ft_attr.max_fte = num_flow_table_entries;
- ft_attr.prio = prio;
- ft_attr.level = level;
- ft_attr.flags = flags;
-
- ft = mlx5_create_flow_table(ns, &ft_attr);
+ ft = mlx5_create_flow_table(ns, ft_attr);
if (IS_ERR(ft))
return ft;
ft->autogroup.active = true;
ft->autogroup.required_groups = max_num_groups;
+ ft->autogroup.max_fte = autogroups_max_fte;
/* We save place for flow groups in addition to max types */
- ft->autogroup.group_size = ft->max_fte / (max_num_groups + 1);
+ ft->autogroup.group_size = autogroups_max_fte / (max_num_groups + 1);
return ft;
}
@@ -1157,7 +1163,7 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft,
struct mlx5_flow_group *fg;
int err;
- if (ft->autogroup.active)
+ if (ft->autogroup.active && start_index < ft->autogroup.max_fte)
return ERR_PTR(-EPERM);
down_write_ref_node(&ft->node, false);
@@ -1330,9 +1336,10 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft
const struct mlx5_flow_spec *spec)
{
struct list_head *prev = &ft->node.children;
- struct mlx5_flow_group *fg;
+ u32 max_fte = ft->autogroup.max_fte;
unsigned int candidate_index = 0;
unsigned int group_size = 0;
+ struct mlx5_flow_group *fg;
if (!ft->autogroup.active)
return ERR_PTR(-ENOENT);
@@ -1340,7 +1347,7 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft
if (ft->autogroup.num_groups < ft->autogroup.required_groups)
group_size = ft->autogroup.group_size;
- /* ft->max_fte == ft->autogroup.max_types */
+ /* max_fte == ft->autogroup.max_types */
if (group_size == 0)
group_size = 1;
@@ -1353,7 +1360,7 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft
prev = &fg->node.list;
}
- if (candidate_index + group_size > ft->max_fte)
+ if (candidate_index + group_size > max_fte)
return ERR_PTR(-ENOSPC);
fg = alloc_insert_flow_group(ft,
@@ -1537,18 +1544,30 @@ static bool counter_is_valid(u32 action)
}
static bool dest_is_valid(struct mlx5_flow_destination *dest,
- u32 action,
+ struct mlx5_flow_act *flow_act,
struct mlx5_flow_table *ft)
{
+ bool ignore_level = flow_act->flags & FLOW_ACT_IGNORE_FLOW_LEVEL;
+ u32 action = flow_act->action;
+
if (dest && (dest->type == MLX5_FLOW_DESTINATION_TYPE_COUNTER))
return counter_is_valid(action);
if (!(action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
return true;
+ if (ignore_level) {
+ if (ft->type != FS_FT_FDB)
+ return false;
+
+ if (dest->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
+ dest->ft->type != FS_FT_FDB)
+ return false;
+ }
+
if (!dest || ((dest->type ==
MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) &&
- (dest->ft->level <= ft->level)))
+ (dest->ft->level <= ft->level && !ignore_level)))
return false;
return true;
}
@@ -1633,67 +1652,35 @@ static u64 matched_fgs_get_version(struct list_head *match_head)
}
static struct fs_fte *
-lookup_fte_for_write_locked(struct mlx5_flow_group *g, const u32 *match_value)
+lookup_fte_locked(struct mlx5_flow_group *g,
+ const u32 *match_value,
+ bool take_write)
{
struct fs_fte *fte_tmp;
- nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
-
- fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value, rhash_fte);
- if (!fte_tmp || !tree_get_node(&fte_tmp->node)) {
- fte_tmp = NULL;
- goto out;
- }
-
- if (!fte_tmp->node.active) {
- tree_put_node(&fte_tmp->node, false);
- fte_tmp = NULL;
- goto out;
- }
- nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
-
-out:
- up_write_ref_node(&g->node, false);
- return fte_tmp;
-}
-
-static struct fs_fte *
-lookup_fte_for_read_locked(struct mlx5_flow_group *g, const u32 *match_value)
-{
- struct fs_fte *fte_tmp;
-
- if (!tree_get_node(&g->node))
- return NULL;
-
- rcu_read_lock();
- fte_tmp = rhashtable_lookup(&g->ftes_hash, match_value, rhash_fte);
- if (!fte_tmp || !tree_get_node(&fte_tmp->node)) {
- rcu_read_unlock();
- fte_tmp = NULL;
- goto out;
- }
- rcu_read_unlock();
-
- if (!fte_tmp->node.active) {
- tree_put_node(&fte_tmp->node, false);
- fte_tmp = NULL;
- goto out;
- }
-
- nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
-
-out:
- tree_put_node(&g->node, false);
- return fte_tmp;
-}
-
-static struct fs_fte *
-lookup_fte_locked(struct mlx5_flow_group *g, const u32 *match_value, bool write)
-{
- if (write)
- return lookup_fte_for_write_locked(g, match_value);
+ if (take_write)
+ nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
else
- return lookup_fte_for_read_locked(g, match_value);
+ nested_down_read_ref_node(&g->node, FS_LOCK_PARENT);
+ fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value,
+ rhash_fte);
+ if (!fte_tmp || !tree_get_node(&fte_tmp->node)) {
+ fte_tmp = NULL;
+ goto out;
+ }
+ if (!fte_tmp->node.active) {
+ tree_put_node(&fte_tmp->node, false);
+ fte_tmp = NULL;
+ goto out;
+ }
+
+ nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
+out:
+ if (take_write)
+ up_write_ref_node(&g->node, false);
+ else
+ up_read_ref_node(&g->node);
+ return fte_tmp;
}
static struct mlx5_flow_handle *
@@ -1810,7 +1797,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
return ERR_PTR(-EINVAL);
for (i = 0; i < dest_num; i++) {
- if (!dest_is_valid(&dest[i], flow_act->action, ft))
+ if (!dest_is_valid(&dest[i], flow_act, ft))
return ERR_PTR(-EINVAL);
}
nested_down_read_ref_node(&ft->node, FS_LOCK_GRANDPARENT);
@@ -2073,7 +2060,8 @@ int mlx5_destroy_flow_table(struct mlx5_flow_table *ft)
int err = 0;
mutex_lock(&root->chain_lock);
- err = disconnect_flow_table(ft);
+ if (!(ft->flags & MLX5_FLOW_TABLE_UNMANAGED))
+ err = disconnect_flow_table(ft);
if (err) {
mutex_unlock(&root->chain_lock);
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index e8cd997..be5f5e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -164,6 +164,7 @@ struct mlx5_flow_table {
unsigned int required_groups;
unsigned int group_size;
unsigned int num_groups;
+ unsigned int max_fte;
} autogroup;
/* Protect fwd_rules */
struct mutex lock;
@@ -203,7 +204,6 @@ struct fs_fte {
enum fs_fte_status status;
struct mlx5_fc *counter;
struct rhash_head hash;
- struct rcu_head rcu;
int modify_mask;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index a19790d..d89ff1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -131,11 +131,11 @@ static int mlx5_get_pcam_reg(struct mlx5_core_dev *dev)
MLX5_PCAM_REGS_5000_TO_507F);
}
-static int mlx5_get_mcam_reg(struct mlx5_core_dev *dev)
+static int mlx5_get_mcam_access_reg_group(struct mlx5_core_dev *dev,
+ enum mlx5_mcam_reg_groups group)
{
- return mlx5_query_mcam_reg(dev, dev->caps.mcam,
- MLX5_MCAM_FEATURE_ENHANCED_FEATURES,
- MLX5_MCAM_REGS_FIRST_128);
+ return mlx5_query_mcam_reg(dev, dev->caps.mcam[group],
+ MLX5_MCAM_FEATURE_ENHANCED_FEATURES, group);
}
static int mlx5_get_qcam_reg(struct mlx5_core_dev *dev)
@@ -221,8 +221,11 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
if (MLX5_CAP_GEN(dev, pcam_reg))
mlx5_get_pcam_reg(dev);
- if (MLX5_CAP_GEN(dev, mcam_reg))
- mlx5_get_mcam_reg(dev);
+ if (MLX5_CAP_GEN(dev, mcam_reg)) {
+ mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_FIRST_128);
+ mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9080_0x90FF);
+ mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9100_0x917F);
+ }
if (MLX5_CAP_GEN(dev, qcam_reg))
mlx5_get_qcam_reg(dev);
@@ -245,6 +248,13 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
return err;
}
+ if (MLX5_CAP_GEN_64(dev, general_obj_types) &
+ MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q) {
+ err = mlx5_core_get_caps(dev, MLX5_CAP_VDPA_EMULATION);
+ if (err)
+ return err;
+ }
+
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 3ed8ab2..56078b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -87,8 +87,8 @@ int mlx5i_init(struct mlx5_core_dev *mdev,
mlx5e_set_netdev_mtu_boundaries(priv);
netdev->mtu = netdev->max_mtu;
- mlx5e_build_nic_params(mdev, NULL, &priv->rss_params, &priv->channels.params,
- priv->max_nch, netdev->mtu);
+ mlx5e_build_nic_params(priv, NULL, &priv->rss_params, &priv->channels.params,
+ netdev->mtu);
mlx5i_build_nic_params(mdev, &priv->channels.params);
mlx5e_timestamp_init(priv);
@@ -419,6 +419,28 @@ static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
mlx5e_destroy_q_counters(priv);
}
+/* The stats groups order is opposite to the update_stats() order calls */
+static mlx5e_stats_grp_t mlx5i_stats_grps[] = {
+ &MLX5E_STATS_GRP(sw),
+ &MLX5E_STATS_GRP(qcnt),
+ &MLX5E_STATS_GRP(vnic_env),
+ &MLX5E_STATS_GRP(vport),
+ &MLX5E_STATS_GRP(802_3),
+ &MLX5E_STATS_GRP(2863),
+ &MLX5E_STATS_GRP(2819),
+ &MLX5E_STATS_GRP(phy),
+ &MLX5E_STATS_GRP(pcie),
+ &MLX5E_STATS_GRP(per_prio),
+ &MLX5E_STATS_GRP(pme),
+ &MLX5E_STATS_GRP(channels),
+ &MLX5E_STATS_GRP(per_port_buff_congest),
+};
+
+static unsigned int mlx5i_stats_grps_num(struct mlx5e_priv *priv)
+{
+ return ARRAY_SIZE(mlx5i_stats_grps);
+}
+
static const struct mlx5e_profile mlx5i_nic_profile = {
.init = mlx5i_init,
.cleanup = mlx5i_cleanup,
@@ -435,6 +457,8 @@ static const struct mlx5e_profile mlx5i_nic_profile = {
.rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */
.max_tc = MLX5I_MAX_NUM_TC,
.rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR),
+ .stats_grps = mlx5i_stats_grps,
+ .stats_grps_num = mlx5i_stats_grps_num,
};
/* mlx5i netdev NDos */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index fc0d958..b91eabc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -586,7 +586,8 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
if (!ldev->nb.notifier_call) {
ldev->nb.notifier_call = mlx5_lag_netdev_event;
- if (register_netdevice_notifier(&ldev->nb)) {
+ if (register_netdevice_notifier_dev_net(netdev, &ldev->nb,
+ &ldev->nn)) {
ldev->nb.notifier_call = NULL;
mlx5_core_err(dev, "Failed to register LAG netdev notifier\n");
}
@@ -599,7 +600,7 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
}
/* Must be called with intf_mutex held */
-void mlx5_lag_remove(struct mlx5_core_dev *dev)
+void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev)
{
struct mlx5_lag *ldev;
int i;
@@ -619,7 +620,8 @@ void mlx5_lag_remove(struct mlx5_core_dev *dev)
if (i == MLX5_MAX_PORTS) {
if (ldev->nb.notifier_call)
- unregister_netdevice_notifier(&ldev->nb);
+ unregister_netdevice_notifier_dev_net(netdev, &ldev->nb,
+ &ldev->nn);
mlx5_lag_mp_cleanup(ldev);
cancel_delayed_work_sync(&ldev->bond_work);
mlx5_lag_dev_free(ldev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
index f1068aa..316ab09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
@@ -44,6 +44,7 @@ struct mlx5_lag {
struct workqueue_struct *wq;
struct delayed_work bond_work;
struct notifier_block nb;
+ struct netdev_net_notifier nn;
struct lag_mp lag_mp;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 173e2c12..f554cfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1193,6 +1193,12 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
if (err)
goto err_load;
+ if (boot) {
+ err = mlx5_devlink_register(priv_to_devlink(dev), dev->device);
+ if (err)
+ goto err_devlink_reg;
+ }
+
if (mlx5_device_registered(dev)) {
mlx5_attach_device(dev);
} else {
@@ -1210,6 +1216,9 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
return err;
err_reg_dev:
+ if (boot)
+ mlx5_devlink_unregister(priv_to_devlink(dev));
+err_devlink_reg:
mlx5_unload(dev);
err_load:
if (boot)
@@ -1347,10 +1356,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
request_module_nowait(MLX5_IB_MOD);
- err = mlx5_devlink_register(devlink, &pdev->dev);
- if (err)
- goto clean_load;
-
err = mlx5_crdump_enable(dev);
if (err)
dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
@@ -1358,9 +1363,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
pci_save_state(pdev);
return 0;
-clean_load:
- mlx5_unload_one(dev, true);
-
err_load_one:
mlx5_pci_close(dev);
pci_init_err:
@@ -1561,6 +1563,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
{ PCI_VDEVICE(MELLANOX, 0x101d) }, /* ConnectX-6 Dx */
{ PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF}, /* ConnectX Family mlx5Gen Virtual Function */
{ PCI_VDEVICE(MELLANOX, 0x101f) }, /* ConnectX-6 LX */
+ { PCI_VDEVICE(MELLANOX, 0x1021) }, /* ConnectX-7 */
{ PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */
{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */
{ PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index da67b28..fcce9e0f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -157,7 +157,7 @@ int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam,
u8 feature_group, u8 access_reg_group);
void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev);
-void mlx5_lag_remove(struct mlx5_core_dev *dev);
+void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev);
int mlx5_irq_table_init(struct mlx5_core_dev *dev);
void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 004c56c..6dec2a55 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -677,9 +677,12 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
goto out_invalid_arg;
}
if (action->dest_tbl.tbl->level <= matcher->tbl->level) {
+ mlx5_core_warn_once(dmn->mdev,
+ "Connecting table to a lower/same level destination table\n");
mlx5dr_dbg(dmn,
- "Destination table level should be higher than source table\n");
- goto out_invalid_arg;
+ "Connecting table at level %d to a destination table at level %d\n",
+ matcher->tbl->level,
+ action->dest_tbl.tbl->level);
}
attr.final_icm_addr = rx_rule ?
action->dest_tbl.tbl->rx.s_anchor->chunk->icm_addr :
@@ -690,9 +693,9 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
/* get the relevant addresses */
if (!action->dest_tbl.fw_tbl.rx_icm_addr) {
- ret = mlx5dr_cmd_query_flow_table(action->dest_tbl.fw_tbl.mdev,
- action->dest_tbl.fw_tbl.ft->type,
- action->dest_tbl.fw_tbl.ft->id,
+ ret = mlx5dr_cmd_query_flow_table(dmn->mdev,
+ action->dest_tbl.fw_tbl.type,
+ action->dest_tbl.fw_tbl.id,
&output);
if (!ret) {
action->dest_tbl.fw_tbl.tx_icm_addr =
@@ -982,8 +985,106 @@ mlx5dr_action_create_dest_table(struct mlx5dr_table *tbl)
}
struct mlx5dr_action *
-mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft,
- struct mlx5_core_dev *mdev)
+mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn,
+ struct mlx5dr_action_dest *dests,
+ u32 num_of_dests)
+{
+ struct mlx5dr_cmd_flow_destination_hw_info *hw_dests;
+ struct mlx5dr_action **ref_actions;
+ struct mlx5dr_action *action;
+ bool reformat_req = false;
+ u32 num_of_ref = 0;
+ int ret;
+ int i;
+
+ if (dmn->type != MLX5DR_DOMAIN_TYPE_FDB) {
+ mlx5dr_err(dmn, "Multiple destination support is for FDB only\n");
+ return NULL;
+ }
+
+ hw_dests = kzalloc(sizeof(*hw_dests) * num_of_dests, GFP_KERNEL);
+ if (!hw_dests)
+ return NULL;
+
+ ref_actions = kzalloc(sizeof(*ref_actions) * num_of_dests * 2, GFP_KERNEL);
+ if (!ref_actions)
+ goto free_hw_dests;
+
+ for (i = 0; i < num_of_dests; i++) {
+ struct mlx5dr_action *reformat_action = dests[i].reformat;
+ struct mlx5dr_action *dest_action = dests[i].dest;
+
+ ref_actions[num_of_ref++] = dest_action;
+
+ switch (dest_action->action_type) {
+ case DR_ACTION_TYP_VPORT:
+ hw_dests[i].vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID;
+ hw_dests[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+ hw_dests[i].vport.num = dest_action->vport.caps->num;
+ hw_dests[i].vport.vhca_id = dest_action->vport.caps->vhca_gvmi;
+ if (reformat_action) {
+ reformat_req = true;
+ hw_dests[i].vport.reformat_id =
+ reformat_action->reformat.reformat_id;
+ ref_actions[num_of_ref++] = reformat_action;
+ hw_dests[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
+ }
+ break;
+
+ case DR_ACTION_TYP_FT:
+ hw_dests[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+ if (dest_action->dest_tbl.is_fw_tbl)
+ hw_dests[i].ft_id = dest_action->dest_tbl.fw_tbl.id;
+ else
+ hw_dests[i].ft_id = dest_action->dest_tbl.tbl->table_id;
+ break;
+
+ default:
+ mlx5dr_dbg(dmn, "Invalid multiple destinations action\n");
+ goto free_ref_actions;
+ }
+ }
+
+ action = dr_action_create_generic(DR_ACTION_TYP_FT);
+ if (!action)
+ goto free_ref_actions;
+
+ ret = mlx5dr_fw_create_md_tbl(dmn,
+ hw_dests,
+ num_of_dests,
+ reformat_req,
+ &action->dest_tbl.fw_tbl.id,
+ &action->dest_tbl.fw_tbl.group_id);
+ if (ret)
+ goto free_action;
+
+ refcount_inc(&dmn->refcount);
+
+ for (i = 0; i < num_of_ref; i++)
+ refcount_inc(&ref_actions[i]->refcount);
+
+ action->dest_tbl.is_fw_tbl = true;
+ action->dest_tbl.fw_tbl.dmn = dmn;
+ action->dest_tbl.fw_tbl.type = FS_FT_FDB;
+ action->dest_tbl.fw_tbl.ref_actions = ref_actions;
+ action->dest_tbl.fw_tbl.num_of_ref_actions = num_of_ref;
+
+ kfree(hw_dests);
+
+ return action;
+
+free_action:
+ kfree(action);
+free_ref_actions:
+ kfree(ref_actions);
+free_hw_dests:
+ kfree(hw_dests);
+ return NULL;
+}
+
+struct mlx5dr_action *
+mlx5dr_action_create_dest_flow_fw_table(struct mlx5dr_domain *dmn,
+ struct mlx5_flow_table *ft)
{
struct mlx5dr_action *action;
@@ -992,8 +1093,11 @@ mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft,
return NULL;
action->dest_tbl.is_fw_tbl = 1;
- action->dest_tbl.fw_tbl.ft = ft;
- action->dest_tbl.fw_tbl.mdev = mdev;
+ action->dest_tbl.fw_tbl.type = ft->type;
+ action->dest_tbl.fw_tbl.id = ft->id;
+ action->dest_tbl.fw_tbl.dmn = dmn;
+
+ refcount_inc(&dmn->refcount);
return action;
}
@@ -1213,19 +1317,61 @@ dr_action_modify_get_hw_info(u16 sw_field)
}
static int
-dr_action_modify_sw_to_hw(struct mlx5dr_domain *dmn,
- __be64 *sw_action,
- __be64 *hw_action,
- const struct dr_action_modify_field_conv **ret_hw_info)
+dr_action_modify_sw_to_hw_add(struct mlx5dr_domain *dmn,
+ __be64 *sw_action,
+ __be64 *hw_action,
+ const struct dr_action_modify_field_conv **ret_hw_info)
{
const struct dr_action_modify_field_conv *hw_action_info;
- u8 offset, length, max_length, action;
+ u8 max_length;
u16 sw_field;
- u8 hw_opcode;
u32 data;
/* Get SW modify action data */
- action = MLX5_GET(set_action_in, sw_action, action_type);
+ sw_field = MLX5_GET(set_action_in, sw_action, field);
+ data = MLX5_GET(set_action_in, sw_action, data);
+
+ /* Convert SW data to HW modify action format */
+ hw_action_info = dr_action_modify_get_hw_info(sw_field);
+ if (!hw_action_info) {
+ mlx5dr_dbg(dmn, "Modify add action invalid field given\n");
+ return -EINVAL;
+ }
+
+ max_length = hw_action_info->end - hw_action_info->start + 1;
+
+ MLX5_SET(dr_action_hw_set, hw_action,
+ opcode, MLX5DR_ACTION_MDFY_HW_OP_ADD);
+
+ MLX5_SET(dr_action_hw_set, hw_action, destination_field_code,
+ hw_action_info->hw_field);
+
+ MLX5_SET(dr_action_hw_set, hw_action, destination_left_shifter,
+ hw_action_info->start);
+
+ /* PRM defines that length zero specific length of 32bits */
+ MLX5_SET(dr_action_hw_set, hw_action, destination_length,
+ max_length == 32 ? 0 : max_length);
+
+ MLX5_SET(dr_action_hw_set, hw_action, inline_data, data);
+
+ *ret_hw_info = hw_action_info;
+
+ return 0;
+}
+
+static int
+dr_action_modify_sw_to_hw_set(struct mlx5dr_domain *dmn,
+ __be64 *sw_action,
+ __be64 *hw_action,
+ const struct dr_action_modify_field_conv **ret_hw_info)
+{
+ const struct dr_action_modify_field_conv *hw_action_info;
+ u8 offset, length, max_length;
+ u16 sw_field;
+ u32 data;
+
+ /* Get SW modify action data */
length = MLX5_GET(set_action_in, sw_action, length);
offset = MLX5_GET(set_action_in, sw_action, offset);
sw_field = MLX5_GET(set_action_in, sw_action, field);
@@ -1234,37 +1380,22 @@ dr_action_modify_sw_to_hw(struct mlx5dr_domain *dmn,
/* Convert SW data to HW modify action format */
hw_action_info = dr_action_modify_get_hw_info(sw_field);
if (!hw_action_info) {
- mlx5dr_dbg(dmn, "Modify action invalid field given\n");
+ mlx5dr_dbg(dmn, "Modify set action invalid field given\n");
return -EINVAL;
}
+ /* PRM defines that length zero specific length of 32bits */
+ length = length ? length : 32;
+
max_length = hw_action_info->end - hw_action_info->start + 1;
- switch (action) {
- case MLX5_ACTION_TYPE_SET:
- hw_opcode = MLX5DR_ACTION_MDFY_HW_OP_SET;
- /* PRM defines that length zero specific length of 32bits */
- if (!length)
- length = 32;
-
- if (length + offset > max_length) {
- mlx5dr_dbg(dmn, "Modify action length + offset exceeds limit\n");
- return -EINVAL;
- }
- break;
-
- case MLX5_ACTION_TYPE_ADD:
- hw_opcode = MLX5DR_ACTION_MDFY_HW_OP_ADD;
- offset = 0;
- length = max_length;
- break;
-
- default:
- mlx5dr_info(dmn, "Unsupported action_type for modify action\n");
- return -EOPNOTSUPP;
+ if (length + offset > max_length) {
+ mlx5dr_dbg(dmn, "Modify action length + offset exceeds limit\n");
+ return -EINVAL;
}
- MLX5_SET(dr_action_hw_set, hw_action, opcode, hw_opcode);
+ MLX5_SET(dr_action_hw_set, hw_action,
+ opcode, MLX5DR_ACTION_MDFY_HW_OP_SET);
MLX5_SET(dr_action_hw_set, hw_action, destination_field_code,
hw_action_info->hw_field);
@@ -1283,48 +1414,236 @@ dr_action_modify_sw_to_hw(struct mlx5dr_domain *dmn,
}
static int
-dr_action_modify_check_field_limitation(struct mlx5dr_domain *dmn,
- const __be64 *sw_action)
+dr_action_modify_sw_to_hw_copy(struct mlx5dr_domain *dmn,
+ __be64 *sw_action,
+ __be64 *hw_action,
+ const struct dr_action_modify_field_conv **ret_dst_hw_info,
+ const struct dr_action_modify_field_conv **ret_src_hw_info)
{
- u16 sw_field;
- u8 action;
+ u8 src_offset, dst_offset, src_max_length, dst_max_length, length;
+ const struct dr_action_modify_field_conv *hw_dst_action_info;
+ const struct dr_action_modify_field_conv *hw_src_action_info;
+ u16 src_field, dst_field;
- sw_field = MLX5_GET(set_action_in, sw_action, field);
+ /* Get SW modify action data */
+ src_field = MLX5_GET(copy_action_in, sw_action, src_field);
+ dst_field = MLX5_GET(copy_action_in, sw_action, dst_field);
+ src_offset = MLX5_GET(copy_action_in, sw_action, src_offset);
+ dst_offset = MLX5_GET(copy_action_in, sw_action, dst_offset);
+ length = MLX5_GET(copy_action_in, sw_action, length);
+
+ /* Convert SW data to HW modify action format */
+ hw_src_action_info = dr_action_modify_get_hw_info(src_field);
+ hw_dst_action_info = dr_action_modify_get_hw_info(dst_field);
+ if (!hw_src_action_info || !hw_dst_action_info) {
+ mlx5dr_dbg(dmn, "Modify copy action invalid field given\n");
+ return -EINVAL;
+ }
+
+ /* PRM defines that length zero specific length of 32bits */
+ length = length ? length : 32;
+
+ src_max_length = hw_src_action_info->end -
+ hw_src_action_info->start + 1;
+ dst_max_length = hw_dst_action_info->end -
+ hw_dst_action_info->start + 1;
+
+ if (length + src_offset > src_max_length ||
+ length + dst_offset > dst_max_length) {
+ mlx5dr_dbg(dmn, "Modify action length + offset exceeds limit\n");
+ return -EINVAL;
+ }
+
+ MLX5_SET(dr_action_hw_copy, hw_action,
+ opcode, MLX5DR_ACTION_MDFY_HW_OP_COPY);
+
+ MLX5_SET(dr_action_hw_copy, hw_action, destination_field_code,
+ hw_dst_action_info->hw_field);
+
+ MLX5_SET(dr_action_hw_copy, hw_action, destination_left_shifter,
+ hw_dst_action_info->start + dst_offset);
+
+ MLX5_SET(dr_action_hw_copy, hw_action, destination_length,
+ length == 32 ? 0 : length);
+
+ MLX5_SET(dr_action_hw_copy, hw_action, source_field_code,
+ hw_src_action_info->hw_field);
+
+ MLX5_SET(dr_action_hw_copy, hw_action, source_left_shifter,
+ hw_src_action_info->start + dst_offset);
+
+ *ret_dst_hw_info = hw_dst_action_info;
+ *ret_src_hw_info = hw_src_action_info;
+
+ return 0;
+}
+
+static int
+dr_action_modify_sw_to_hw(struct mlx5dr_domain *dmn,
+ __be64 *sw_action,
+ __be64 *hw_action,
+ const struct dr_action_modify_field_conv **ret_dst_hw_info,
+ const struct dr_action_modify_field_conv **ret_src_hw_info)
+{
+ u8 action;
+ int ret;
+
+ *hw_action = 0;
+ *ret_src_hw_info = NULL;
+
+ /* Get SW modify action type */
action = MLX5_GET(set_action_in, sw_action, action_type);
- /* Check if SW field is supported in current domain (RX/TX) */
- if (action == MLX5_ACTION_TYPE_SET) {
- if (sw_field == MLX5_ACTION_IN_FIELD_METADATA_REG_A) {
- if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_TX) {
- mlx5dr_dbg(dmn, "Unsupported field %d for RX/FDB set action\n",
- sw_field);
- return -EINVAL;
- }
- }
+ switch (action) {
+ case MLX5_ACTION_TYPE_SET:
+ ret = dr_action_modify_sw_to_hw_set(dmn, sw_action,
+ hw_action,
+ ret_dst_hw_info);
+ break;
- if (sw_field == MLX5_ACTION_IN_FIELD_METADATA_REG_B) {
- if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_RX) {
- mlx5dr_dbg(dmn, "Unsupported field %d for TX/FDB set action\n",
- sw_field);
- return -EINVAL;
- }
- }
- } else if (action == MLX5_ACTION_TYPE_ADD) {
- if (sw_field != MLX5_ACTION_IN_FIELD_OUT_IP_TTL &&
- sw_field != MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT &&
- sw_field != MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM &&
- sw_field != MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM) {
- mlx5dr_dbg(dmn, "Unsupported field %d for add action\n", sw_field);
+ case MLX5_ACTION_TYPE_ADD:
+ ret = dr_action_modify_sw_to_hw_add(dmn, sw_action,
+ hw_action,
+ ret_dst_hw_info);
+ break;
+
+ case MLX5_ACTION_TYPE_COPY:
+ ret = dr_action_modify_sw_to_hw_copy(dmn, sw_action,
+ hw_action,
+ ret_dst_hw_info,
+ ret_src_hw_info);
+ break;
+
+ default:
+ mlx5dr_info(dmn, "Unsupported action_type for modify action\n");
+ ret = -EOPNOTSUPP;
+ }
+
+ return ret;
+}
+
+static int
+dr_action_modify_check_set_field_limitation(struct mlx5dr_action *action,
+ const __be64 *sw_action)
+{
+ u16 sw_field = MLX5_GET(set_action_in, sw_action, field);
+ struct mlx5dr_domain *dmn = action->rewrite.dmn;
+
+ if (sw_field == MLX5_ACTION_IN_FIELD_METADATA_REG_A) {
+ action->rewrite.allow_rx = 0;
+ if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_TX) {
+ mlx5dr_dbg(dmn, "Unsupported field %d for RX/FDB set action\n",
+ sw_field);
return -EINVAL;
}
- } else {
- mlx5dr_info(dmn, "Unsupported action %d modify action\n", action);
- return -EOPNOTSUPP;
+ } else if (sw_field == MLX5_ACTION_IN_FIELD_METADATA_REG_B) {
+ action->rewrite.allow_tx = 0;
+ if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_RX) {
+ mlx5dr_dbg(dmn, "Unsupported field %d for TX/FDB set action\n",
+ sw_field);
+ return -EINVAL;
+ }
+ }
+
+ if (!action->rewrite.allow_rx && !action->rewrite.allow_tx) {
+ mlx5dr_dbg(dmn, "Modify SET actions not supported on both RX and TX\n");
+ return -EINVAL;
}
return 0;
}
+static int
+dr_action_modify_check_add_field_limitation(struct mlx5dr_action *action,
+ const __be64 *sw_action)
+{
+ u16 sw_field = MLX5_GET(set_action_in, sw_action, field);
+ struct mlx5dr_domain *dmn = action->rewrite.dmn;
+
+ if (sw_field != MLX5_ACTION_IN_FIELD_OUT_IP_TTL &&
+ sw_field != MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT &&
+ sw_field != MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM &&
+ sw_field != MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM) {
+ mlx5dr_dbg(dmn, "Unsupported field %d for add action\n",
+ sw_field);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int
+dr_action_modify_check_copy_field_limitation(struct mlx5dr_action *action,
+ const __be64 *sw_action)
+{
+ struct mlx5dr_domain *dmn = action->rewrite.dmn;
+ u16 sw_fields[2];
+ int i;
+
+ sw_fields[0] = MLX5_GET(copy_action_in, sw_action, src_field);
+ sw_fields[1] = MLX5_GET(copy_action_in, sw_action, dst_field);
+
+ for (i = 0; i < 2; i++) {
+ if (sw_fields[i] == MLX5_ACTION_IN_FIELD_METADATA_REG_A) {
+ action->rewrite.allow_rx = 0;
+ if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_TX) {
+ mlx5dr_dbg(dmn, "Unsupported field %d for RX/FDB set action\n",
+ sw_fields[i]);
+ return -EINVAL;
+ }
+ } else if (sw_fields[i] == MLX5_ACTION_IN_FIELD_METADATA_REG_B) {
+ action->rewrite.allow_tx = 0;
+ if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_RX) {
+ mlx5dr_dbg(dmn, "Unsupported field %d for TX/FDB set action\n",
+ sw_fields[i]);
+ return -EINVAL;
+ }
+ }
+ }
+
+ if (!action->rewrite.allow_rx && !action->rewrite.allow_tx) {
+ mlx5dr_dbg(dmn, "Modify copy actions not supported on both RX and TX\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int
+dr_action_modify_check_field_limitation(struct mlx5dr_action *action,
+ const __be64 *sw_action)
+{
+ struct mlx5dr_domain *dmn = action->rewrite.dmn;
+ u8 action_type;
+ int ret;
+
+ action_type = MLX5_GET(set_action_in, sw_action, action_type);
+
+ switch (action_type) {
+ case MLX5_ACTION_TYPE_SET:
+ ret = dr_action_modify_check_set_field_limitation(action,
+ sw_action);
+ break;
+
+ case MLX5_ACTION_TYPE_ADD:
+ ret = dr_action_modify_check_add_field_limitation(action,
+ sw_action);
+ break;
+
+ case MLX5_ACTION_TYPE_COPY:
+ ret = dr_action_modify_check_copy_field_limitation(action,
+ sw_action);
+ break;
+
+ default:
+ mlx5dr_info(dmn, "Unsupported action %d modify action\n",
+ action_type);
+ ret = -EOPNOTSUPP;
+ }
+
+ return ret;
+}
+
static bool
dr_action_modify_check_is_ttl_modify(const u64 *sw_action)
{
@@ -1333,7 +1652,7 @@ dr_action_modify_check_is_ttl_modify(const u64 *sw_action)
return sw_field == MLX5_ACTION_IN_FIELD_OUT_IP_TTL;
}
-static int dr_actions_convert_modify_header(struct mlx5dr_domain *dmn,
+static int dr_actions_convert_modify_header(struct mlx5dr_action *action,
u32 max_hw_actions,
u32 num_sw_actions,
__be64 sw_actions[],
@@ -1341,20 +1660,26 @@ static int dr_actions_convert_modify_header(struct mlx5dr_domain *dmn,
u32 *num_hw_actions,
bool *modify_ttl)
{
- const struct dr_action_modify_field_conv *hw_action_info;
+ const struct dr_action_modify_field_conv *hw_dst_action_info;
+ const struct dr_action_modify_field_conv *hw_src_action_info;
u16 hw_field = MLX5DR_ACTION_MDFY_HW_FLD_RESERVED;
u32 l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_NONE;
u32 l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_NONE;
+ struct mlx5dr_domain *dmn = action->rewrite.dmn;
int ret, i, hw_idx = 0;
__be64 *sw_action;
__be64 hw_action;
*modify_ttl = false;
+ action->rewrite.allow_rx = 1;
+ action->rewrite.allow_tx = 1;
+
for (i = 0; i < num_sw_actions; i++) {
sw_action = &sw_actions[i];
- ret = dr_action_modify_check_field_limitation(dmn, sw_action);
+ ret = dr_action_modify_check_field_limitation(action,
+ sw_action);
if (ret)
return ret;
@@ -1365,32 +1690,35 @@ static int dr_actions_convert_modify_header(struct mlx5dr_domain *dmn,
ret = dr_action_modify_sw_to_hw(dmn,
sw_action,
&hw_action,
- &hw_action_info);
+ &hw_dst_action_info,
+ &hw_src_action_info);
if (ret)
return ret;
/* Due to a HW limitation we cannot modify 2 different L3 types */
- if (l3_type && hw_action_info->l3_type &&
- hw_action_info->l3_type != l3_type) {
+ if (l3_type && hw_dst_action_info->l3_type &&
+ hw_dst_action_info->l3_type != l3_type) {
mlx5dr_dbg(dmn, "Action list can't support two different L3 types\n");
return -EINVAL;
}
- if (hw_action_info->l3_type)
- l3_type = hw_action_info->l3_type;
+ if (hw_dst_action_info->l3_type)
+ l3_type = hw_dst_action_info->l3_type;
/* Due to a HW limitation we cannot modify two different L4 types */
- if (l4_type && hw_action_info->l4_type &&
- hw_action_info->l4_type != l4_type) {
+ if (l4_type && hw_dst_action_info->l4_type &&
+ hw_dst_action_info->l4_type != l4_type) {
mlx5dr_dbg(dmn, "Action list can't support two different L4 types\n");
return -EINVAL;
}
- if (hw_action_info->l4_type)
- l4_type = hw_action_info->l4_type;
+ if (hw_dst_action_info->l4_type)
+ l4_type = hw_dst_action_info->l4_type;
/* HW reads and executes two actions at once this means we
* need to create a gap if two actions access the same field
*/
- if ((hw_idx % 2) && hw_field == hw_action_info->hw_field) {
+ if ((hw_idx % 2) && (hw_field == hw_dst_action_info->hw_field ||
+ (hw_src_action_info &&
+ hw_field == hw_src_action_info->hw_field))) {
/* Check if after gap insertion the total number of HW
* modify actions doesn't exceeds the limit
*/
@@ -1400,7 +1728,7 @@ static int dr_actions_convert_modify_header(struct mlx5dr_domain *dmn,
return -EINVAL;
}
}
- hw_field = hw_action_info->hw_field;
+ hw_field = hw_dst_action_info->hw_field;
hw_actions[hw_idx] = hw_action;
hw_idx++;
@@ -1443,7 +1771,7 @@ static int dr_action_create_modify_action(struct mlx5dr_domain *dmn,
goto free_chunk;
}
- ret = dr_actions_convert_modify_header(dmn,
+ ret = dr_actions_convert_modify_header(action,
max_hw_actions,
num_sw_actions,
actions,
@@ -1559,8 +1887,26 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action)
switch (action->action_type) {
case DR_ACTION_TYP_FT:
- if (!action->dest_tbl.is_fw_tbl)
+ if (action->dest_tbl.is_fw_tbl)
+ refcount_dec(&action->dest_tbl.fw_tbl.dmn->refcount);
+ else
refcount_dec(&action->dest_tbl.tbl->refcount);
+
+ if (action->dest_tbl.is_fw_tbl &&
+ action->dest_tbl.fw_tbl.num_of_ref_actions) {
+ struct mlx5dr_action **ref_actions;
+ int i;
+
+ ref_actions = action->dest_tbl.fw_tbl.ref_actions;
+ for (i = 0; i < action->dest_tbl.fw_tbl.num_of_ref_actions; i++)
+ refcount_dec(&ref_actions[i]->refcount);
+
+ kfree(ref_actions);
+
+ mlx5dr_fw_destroy_md_tbl(action->dest_tbl.fw_tbl.dmn,
+ action->dest_tbl.fw_tbl.id,
+ action->dest_tbl.fw_tbl.group_id);
+ }
break;
case DR_ACTION_TYP_TNL_L2_TO_L2:
refcount_dec(&action->reformat.dmn->refcount);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
index 41662c4e..461b393 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
@@ -320,12 +320,7 @@ int mlx5dr_cmd_destroy_flow_group(struct mlx5_core_dev *mdev,
}
int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev,
- u32 table_type,
- u64 icm_addr_rx,
- u64 icm_addr_tx,
- u8 level,
- bool sw_owner,
- bool term_tbl,
+ struct mlx5dr_cmd_create_flow_table_attr *attr,
u64 *fdb_rx_icm_addr,
u32 *table_id)
{
@@ -335,37 +330,43 @@ int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev,
int err;
MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE);
- MLX5_SET(create_flow_table_in, in, table_type, table_type);
+ MLX5_SET(create_flow_table_in, in, table_type, attr->table_type);
ft_mdev = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context);
- MLX5_SET(flow_table_context, ft_mdev, termination_table, term_tbl);
- MLX5_SET(flow_table_context, ft_mdev, sw_owner, sw_owner);
- MLX5_SET(flow_table_context, ft_mdev, level, level);
+ MLX5_SET(flow_table_context, ft_mdev, termination_table, attr->term_tbl);
+ MLX5_SET(flow_table_context, ft_mdev, sw_owner, attr->sw_owner);
+ MLX5_SET(flow_table_context, ft_mdev, level, attr->level);
- if (sw_owner) {
+ if (attr->sw_owner) {
/* icm_addr_0 used for FDB RX / NIC TX / NIC_RX
* icm_addr_1 used for FDB TX
*/
- if (table_type == MLX5_FLOW_TABLE_TYPE_NIC_RX) {
+ if (attr->table_type == MLX5_FLOW_TABLE_TYPE_NIC_RX) {
MLX5_SET64(flow_table_context, ft_mdev,
- sw_owner_icm_root_0, icm_addr_rx);
- } else if (table_type == MLX5_FLOW_TABLE_TYPE_NIC_TX) {
+ sw_owner_icm_root_0, attr->icm_addr_rx);
+ } else if (attr->table_type == MLX5_FLOW_TABLE_TYPE_NIC_TX) {
MLX5_SET64(flow_table_context, ft_mdev,
- sw_owner_icm_root_0, icm_addr_tx);
- } else if (table_type == MLX5_FLOW_TABLE_TYPE_FDB) {
+ sw_owner_icm_root_0, attr->icm_addr_tx);
+ } else if (attr->table_type == MLX5_FLOW_TABLE_TYPE_FDB) {
MLX5_SET64(flow_table_context, ft_mdev,
- sw_owner_icm_root_0, icm_addr_rx);
+ sw_owner_icm_root_0, attr->icm_addr_rx);
MLX5_SET64(flow_table_context, ft_mdev,
- sw_owner_icm_root_1, icm_addr_tx);
+ sw_owner_icm_root_1, attr->icm_addr_tx);
}
}
+ MLX5_SET(create_flow_table_in, in, flow_table_context.decap_en,
+ attr->decap_en);
+ MLX5_SET(create_flow_table_in, in, flow_table_context.reformat_en,
+ attr->reformat_en);
+
err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
if (err)
return err;
*table_id = MLX5_GET(create_flow_table_out, out, table_id);
- if (!sw_owner && table_type == MLX5_FLOW_TABLE_TYPE_FDB)
+ if (!attr->sw_owner && attr->table_type == MLX5_FLOW_TABLE_TYPE_FDB &&
+ fdb_rx_icm_addr)
*fdb_rx_icm_addr =
(u64)MLX5_GET(create_flow_table_out, out, icm_address_31_0) |
(u64)MLX5_GET(create_flow_table_out, out, icm_address_39_32) << 32 |
@@ -478,3 +479,208 @@ int mlx5dr_cmd_query_gid(struct mlx5_core_dev *mdev, u8 vhca_port_num,
return 0;
}
+
+static int mlx5dr_cmd_set_extended_dest(struct mlx5_core_dev *dev,
+ struct mlx5dr_cmd_fte_info *fte,
+ bool *extended_dest)
+{
+ int fw_log_max_fdb_encap_uplink = MLX5_CAP_ESW(dev, log_max_fdb_encap_uplink);
+ int num_fwd_destinations = 0;
+ int num_encap = 0;
+ int i;
+
+ *extended_dest = false;
+ if (!(fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
+ return 0;
+ for (i = 0; i < fte->dests_size; i++) {
+ if (fte->dest_arr[i].type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+ continue;
+ if (fte->dest_arr[i].type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
+ fte->dest_arr[i].vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID)
+ num_encap++;
+ num_fwd_destinations++;
+ }
+
+ if (num_fwd_destinations > 1 && num_encap > 0)
+ *extended_dest = true;
+
+ if (*extended_dest && !fw_log_max_fdb_encap_uplink) {
+ mlx5_core_warn(dev, "FW does not support extended destination");
+ return -EOPNOTSUPP;
+ }
+ if (num_encap > (1 << fw_log_max_fdb_encap_uplink)) {
+ mlx5_core_warn(dev, "FW does not support more than %d encaps",
+ 1 << fw_log_max_fdb_encap_uplink);
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev,
+ int opmod, int modify_mask,
+ struct mlx5dr_cmd_ft_info *ft,
+ u32 group_id,
+ struct mlx5dr_cmd_fte_info *fte)
+{
+ u32 out[MLX5_ST_SZ_DW(set_fte_out)] = {};
+ void *in_flow_context, *vlan;
+ bool extended_dest = false;
+ void *in_match_value;
+ unsigned int inlen;
+ int dst_cnt_size;
+ void *in_dests;
+ u32 *in;
+ int err;
+ int i;
+
+ if (mlx5dr_cmd_set_extended_dest(dev, fte, &extended_dest))
+ return -EOPNOTSUPP;
+
+ if (!extended_dest)
+ dst_cnt_size = MLX5_ST_SZ_BYTES(dest_format_struct);
+ else
+ dst_cnt_size = MLX5_ST_SZ_BYTES(extended_dest_format);
+
+ inlen = MLX5_ST_SZ_BYTES(set_fte_in) + fte->dests_size * dst_cnt_size;
+ in = kvzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(set_fte_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY);
+ MLX5_SET(set_fte_in, in, op_mod, opmod);
+ MLX5_SET(set_fte_in, in, modify_enable_mask, modify_mask);
+ MLX5_SET(set_fte_in, in, table_type, ft->type);
+ MLX5_SET(set_fte_in, in, table_id, ft->id);
+ MLX5_SET(set_fte_in, in, flow_index, fte->index);
+ if (ft->vport) {
+ MLX5_SET(set_fte_in, in, vport_number, ft->vport);
+ MLX5_SET(set_fte_in, in, other_vport, 1);
+ }
+
+ in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
+ MLX5_SET(flow_context, in_flow_context, group_id, group_id);
+
+ MLX5_SET(flow_context, in_flow_context, flow_tag,
+ fte->flow_context.flow_tag);
+ MLX5_SET(flow_context, in_flow_context, flow_source,
+ fte->flow_context.flow_source);
+
+ MLX5_SET(flow_context, in_flow_context, extended_destination,
+ extended_dest);
+ if (extended_dest) {
+ u32 action;
+
+ action = fte->action.action &
+ ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+ MLX5_SET(flow_context, in_flow_context, action, action);
+ } else {
+ MLX5_SET(flow_context, in_flow_context, action,
+ fte->action.action);
+ if (fte->action.pkt_reformat)
+ MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
+ fte->action.pkt_reformat->id);
+ }
+ if (fte->action.modify_hdr)
+ MLX5_SET(flow_context, in_flow_context, modify_header_id,
+ fte->action.modify_hdr->id);
+
+ vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan);
+
+ MLX5_SET(vlan, vlan, ethtype, fte->action.vlan[0].ethtype);
+ MLX5_SET(vlan, vlan, vid, fte->action.vlan[0].vid);
+ MLX5_SET(vlan, vlan, prio, fte->action.vlan[0].prio);
+
+ vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan_2);
+
+ MLX5_SET(vlan, vlan, ethtype, fte->action.vlan[1].ethtype);
+ MLX5_SET(vlan, vlan, vid, fte->action.vlan[1].vid);
+ MLX5_SET(vlan, vlan, prio, fte->action.vlan[1].prio);
+
+ in_match_value = MLX5_ADDR_OF(flow_context, in_flow_context,
+ match_value);
+ memcpy(in_match_value, fte->val, sizeof(u32) * MLX5_ST_SZ_DW_MATCH_PARAM);
+
+ in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination);
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+ int list_size = 0;
+
+ for (i = 0; i < fte->dests_size; i++) {
+ unsigned int id, type = fte->dest_arr[i].type;
+
+ if (type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+ continue;
+
+ switch (type) {
+ case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
+ id = fte->dest_arr[i].ft_num;
+ type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+ break;
+ case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
+ id = fte->dest_arr[i].ft_id;
+ break;
+ case MLX5_FLOW_DESTINATION_TYPE_VPORT:
+ id = fte->dest_arr[i].vport.num;
+ MLX5_SET(dest_format_struct, in_dests,
+ destination_eswitch_owner_vhca_id_valid,
+ !!(fte->dest_arr[i].vport.flags &
+ MLX5_FLOW_DEST_VPORT_VHCA_ID));
+ MLX5_SET(dest_format_struct, in_dests,
+ destination_eswitch_owner_vhca_id,
+ fte->dest_arr[i].vport.vhca_id);
+ if (extended_dest && (fte->dest_arr[i].vport.flags &
+ MLX5_FLOW_DEST_VPORT_REFORMAT_ID)) {
+ MLX5_SET(dest_format_struct, in_dests,
+ packet_reformat,
+ !!(fte->dest_arr[i].vport.flags &
+ MLX5_FLOW_DEST_VPORT_REFORMAT_ID));
+ MLX5_SET(extended_dest_format, in_dests,
+ packet_reformat_id,
+ fte->dest_arr[i].vport.reformat_id);
+ }
+ break;
+ default:
+ id = fte->dest_arr[i].tir_num;
+ }
+
+ MLX5_SET(dest_format_struct, in_dests, destination_type,
+ type);
+ MLX5_SET(dest_format_struct, in_dests, destination_id, id);
+ in_dests += dst_cnt_size;
+ list_size++;
+ }
+
+ MLX5_SET(flow_context, in_flow_context, destination_list_size,
+ list_size);
+ }
+
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+ int max_list_size = BIT(MLX5_CAP_FLOWTABLE_TYPE(dev,
+ log_max_flow_counter,
+ ft->type));
+ int list_size = 0;
+
+ for (i = 0; i < fte->dests_size; i++) {
+ if (fte->dest_arr[i].type !=
+ MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+ continue;
+
+ MLX5_SET(flow_counter_list, in_dests, flow_counter_id,
+ fte->dest_arr[i].counter_id);
+ in_dests += dst_cnt_size;
+ list_size++;
+ }
+ if (list_size > max_list_size) {
+ err = -EINVAL;
+ goto err_out;
+ }
+
+ MLX5_SET(flow_context, in_flow_context, flow_counter_list_size,
+ list_size);
+ }
+
+ err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+err_out:
+ kvfree(in);
+ return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
index 60ef6e6..1fbcd01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
@@ -7,6 +7,7 @@
struct mlx5dr_fw_recalc_cs_ft *
mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u32 vport_num)
{
+ struct mlx5dr_cmd_create_flow_table_attr ft_attr = {};
struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft;
u32 table_id, group_id, modify_hdr_id;
u64 rx_icm_addr, modify_ttl_action;
@@ -16,9 +17,14 @@ mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u32 vport_num)
if (!recalc_cs_ft)
return NULL;
- ret = mlx5dr_cmd_create_flow_table(dmn->mdev, MLX5_FLOW_TABLE_TYPE_FDB,
- 0, 0, dmn->info.caps.max_ft_level - 1,
- false, true, &rx_icm_addr, &table_id);
+ ft_attr.table_type = MLX5_FLOW_TABLE_TYPE_FDB;
+ ft_attr.level = dmn->info.caps.max_ft_level - 1;
+ ft_attr.term_tbl = true;
+
+ ret = mlx5dr_cmd_create_flow_table(dmn->mdev,
+ &ft_attr,
+ &rx_icm_addr,
+ &table_id);
if (ret) {
mlx5dr_err(dmn, "Failed creating TTL W/A FW flow table %d\n", ret);
goto free_ttl_tbl;
@@ -91,3 +97,70 @@ void mlx5dr_fw_destroy_recalc_cs_ft(struct mlx5dr_domain *dmn,
kfree(recalc_cs_ft);
}
+
+int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn,
+ struct mlx5dr_cmd_flow_destination_hw_info *dest,
+ int num_dest,
+ bool reformat_req,
+ u32 *tbl_id,
+ u32 *group_id)
+{
+ struct mlx5dr_cmd_create_flow_table_attr ft_attr = {};
+ struct mlx5dr_cmd_fte_info fte_info = {};
+ u32 val[MLX5_ST_SZ_DW_MATCH_PARAM] = {};
+ struct mlx5dr_cmd_ft_info ft_info = {};
+ int ret;
+
+ ft_attr.table_type = MLX5_FLOW_TABLE_TYPE_FDB;
+ ft_attr.level = dmn->info.caps.max_ft_level - 2;
+ ft_attr.reformat_en = reformat_req;
+ ft_attr.decap_en = reformat_req;
+
+ ret = mlx5dr_cmd_create_flow_table(dmn->mdev, &ft_attr, NULL, tbl_id);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed creating multi dest FW flow table %d\n", ret);
+ return ret;
+ }
+
+ ret = mlx5dr_cmd_create_empty_flow_group(dmn->mdev,
+ MLX5_FLOW_TABLE_TYPE_FDB,
+ *tbl_id, group_id);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed creating multi dest FW flow group %d\n", ret);
+ goto free_flow_table;
+ }
+
+ ft_info.id = *tbl_id;
+ ft_info.type = FS_FT_FDB;
+ fte_info.action.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ fte_info.dests_size = num_dest;
+ fte_info.val = val;
+ fte_info.dest_arr = dest;
+
+ ret = mlx5dr_cmd_set_fte(dmn->mdev, 0, 0, &ft_info, *group_id, &fte_info);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed setting fte into table %d\n", ret);
+ goto free_flow_group;
+ }
+
+ return 0;
+
+free_flow_group:
+ mlx5dr_cmd_destroy_flow_group(dmn->mdev, MLX5_FLOW_TABLE_TYPE_FDB,
+ *tbl_id, *group_id);
+free_flow_table:
+ mlx5dr_cmd_destroy_flow_table(dmn->mdev, *tbl_id,
+ MLX5_FLOW_TABLE_TYPE_FDB);
+ return ret;
+}
+
+void mlx5dr_fw_destroy_md_tbl(struct mlx5dr_domain *dmn,
+ u32 tbl_id, u32 group_id)
+{
+ mlx5dr_cmd_del_flow_table_entry(dmn->mdev, FS_FT_FDB, tbl_id);
+ mlx5dr_cmd_destroy_flow_group(dmn->mdev,
+ MLX5_FLOW_TABLE_TYPE_FDB,
+ tbl_id, group_id);
+ mlx5dr_cmd_destroy_flow_table(dmn->mdev, tbl_id,
+ MLX5_FLOW_TABLE_TYPE_FDB);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index 32e94d2e..e4cff7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -209,7 +209,7 @@ static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher,
/* We need to copy the refcount since this ste
* may have been traversed several times
*/
- refcount_set(&new_ste->refcount, refcount_read(&cur_ste->refcount));
+ new_ste->refcount = cur_ste->refcount;
/* Link old STEs rule_mem list to the new ste */
mlx5dr_rule_update_rule_member(cur_ste, new_ste);
@@ -638,6 +638,9 @@ static int dr_rule_add_member(struct mlx5dr_rule_rx_tx *nic_rule,
if (!rule_mem)
return -ENOMEM;
+ INIT_LIST_HEAD(&rule_mem->list);
+ INIT_LIST_HEAD(&rule_mem->use_ste_list);
+
rule_mem->ste = ste;
list_add_tail(&rule_mem->list, &nic_rule->rule_members_list);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 51803ee..c7f10d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* Copyright (c) 2019 Mellanox Technologies. */
+#include <linux/smp.h>
#include "dr_types.h"
#define QUEUE_SIZE 128
@@ -729,7 +730,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
if (!in)
goto err_cqwq;
- vector = smp_processor_id() % mlx5_comp_vectors_count(mdev);
+ vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev);
err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn);
if (err) {
kvfree(in);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
index a5a2669..c6c7d1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -348,7 +348,7 @@ static void dr_ste_replace(struct mlx5dr_ste *dst, struct mlx5dr_ste *src)
if (dst->next_htbl)
dst->next_htbl->pointing_ste = dst;
- refcount_set(&dst->refcount, refcount_read(&src->refcount));
+ dst->refcount = src->refcount;
INIT_LIST_HEAD(&dst->rule_list);
list_splice_tail_init(&src->rule_list, &dst->rule_list);
@@ -565,7 +565,7 @@ bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste)
bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste)
{
- return !refcount_read(&ste->refcount);
+ return !ste->refcount;
}
/* Init one ste as a pattern for ste data array */
@@ -689,14 +689,14 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool,
htbl->ste_arr = chunk->ste_arr;
htbl->hw_ste_arr = chunk->hw_ste_arr;
htbl->miss_list = chunk->miss_list;
- refcount_set(&htbl->refcount, 0);
+ htbl->refcount = 0;
for (i = 0; i < chunk->num_of_entries; i++) {
struct mlx5dr_ste *ste = &htbl->ste_arr[i];
ste->hw_ste = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED;
ste->htbl = htbl;
- refcount_set(&ste->refcount, 0);
+ ste->refcount = 0;
INIT_LIST_HEAD(&ste->miss_list_node);
INIT_LIST_HEAD(&htbl->miss_list[i]);
INIT_LIST_HEAD(&ste->rule_list);
@@ -713,7 +713,7 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool,
int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl)
{
- if (refcount_read(&htbl->refcount))
+ if (htbl->refcount)
return -EBUSY;
mlx5dr_icm_free_chunk(htbl->chunk);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
index e178d8d..14ce2d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
@@ -211,6 +211,9 @@ static int dr_table_destroy_sw_owned_tbl(struct mlx5dr_table *tbl)
static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl)
{
+ bool en_encap = !!(tbl->flags & MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT);
+ bool en_decap = !!(tbl->flags & MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
+ struct mlx5dr_cmd_create_flow_table_attr ft_attr = {};
u64 icm_addr_rx = 0;
u64 icm_addr_tx = 0;
int ret;
@@ -221,18 +224,21 @@ static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl)
if (tbl->tx.s_anchor)
icm_addr_tx = tbl->tx.s_anchor->chunk->icm_addr;
- ret = mlx5dr_cmd_create_flow_table(tbl->dmn->mdev,
- tbl->table_type,
- icm_addr_rx,
- icm_addr_tx,
- tbl->dmn->info.caps.max_ft_level - 1,
- true, false, NULL,
- &tbl->table_id);
+ ft_attr.table_type = tbl->table_type;
+ ft_attr.icm_addr_rx = icm_addr_rx;
+ ft_attr.icm_addr_tx = icm_addr_tx;
+ ft_attr.level = tbl->dmn->info.caps.max_ft_level - 1;
+ ft_attr.sw_owner = true;
+ ft_attr.decap_en = en_decap;
+ ft_attr.reformat_en = en_encap;
+
+ ret = mlx5dr_cmd_create_flow_table(tbl->dmn->mdev, &ft_attr,
+ NULL, &tbl->table_id);
return ret;
}
-struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level)
+struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level, u32 flags)
{
struct mlx5dr_table *tbl;
int ret;
@@ -245,6 +251,7 @@ struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level)
tbl->dmn = dmn;
tbl->level = level;
+ tbl->flags = flags;
refcount_set(&tbl->refcount, 1);
ret = dr_table_init(tbl);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 290fe61..dffe351 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -123,7 +123,7 @@ struct mlx5dr_matcher_rx_tx;
struct mlx5dr_ste {
u8 *hw_ste;
/* refcount: indicates the num of rules that using this ste */
- refcount_t refcount;
+ u32 refcount;
/* attached to the miss_list head at each htbl entry */
struct list_head miss_list_node;
@@ -155,7 +155,7 @@ struct mlx5dr_ste_htbl_ctrl {
struct mlx5dr_ste_htbl {
u8 lu_type;
u16 byte_mask;
- refcount_t refcount;
+ u32 refcount;
struct mlx5dr_icm_chunk *chunk;
struct mlx5dr_ste *ste_arr;
u8 *hw_ste_arr;
@@ -206,13 +206,14 @@ int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl);
static inline void mlx5dr_htbl_put(struct mlx5dr_ste_htbl *htbl)
{
- if (refcount_dec_and_test(&htbl->refcount))
+ htbl->refcount--;
+ if (!htbl->refcount)
mlx5dr_ste_htbl_free(htbl);
}
static inline void mlx5dr_htbl_get(struct mlx5dr_ste_htbl *htbl)
{
- refcount_inc(&htbl->refcount);
+ htbl->refcount++;
}
/* STE utils */
@@ -254,14 +255,15 @@ static inline void mlx5dr_ste_put(struct mlx5dr_ste *ste,
struct mlx5dr_matcher *matcher,
struct mlx5dr_matcher_rx_tx *nic_matcher)
{
- if (refcount_dec_and_test(&ste->refcount))
+ ste->refcount--;
+ if (!ste->refcount)
mlx5dr_ste_free(ste, matcher, nic_matcher);
}
/* initial as 0, increased only when ste appears in a new rule */
static inline void mlx5dr_ste_get(struct mlx5dr_ste *ste)
{
- refcount_inc(&ste->refcount);
+ ste->refcount++;
}
void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste,
@@ -679,6 +681,7 @@ struct mlx5dr_table {
u32 level;
u32 table_type;
u32 table_id;
+ u32 flags;
struct list_head matcher_list;
struct mlx5dr_action *miss_action;
refcount_t refcount;
@@ -742,10 +745,14 @@ struct mlx5dr_action {
union {
struct mlx5dr_table *tbl;
struct {
- struct mlx5_flow_table *ft;
+ struct mlx5dr_domain *dmn;
+ u32 id;
+ u32 group_id;
+ enum fs_flow_table_type type;
u64 rx_icm_addr;
u64 tx_icm_addr;
- struct mlx5_core_dev *mdev;
+ struct mlx5dr_action **ref_actions;
+ u32 num_of_ref_actions;
} fw_tbl;
};
} dest_tbl;
@@ -867,6 +874,17 @@ struct mlx5dr_cmd_query_flow_table_details {
u64 sw_owner_icm_root_0;
};
+struct mlx5dr_cmd_create_flow_table_attr {
+ u32 table_type;
+ u64 icm_addr_rx;
+ u64 icm_addr_tx;
+ u8 level;
+ bool sw_owner;
+ bool term_tbl;
+ bool decap_en;
+ bool reformat_en;
+};
+
/* internal API functions */
int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev,
struct mlx5dr_cmd_caps *caps);
@@ -904,12 +922,7 @@ int mlx5dr_cmd_destroy_flow_group(struct mlx5_core_dev *mdev,
u32 table_id,
u32 group_id);
int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev,
- u32 table_type,
- u64 icm_addr_rx,
- u64 icm_addr_tx,
- u8 level,
- bool sw_owner,
- bool term_tbl,
+ struct mlx5dr_cmd_create_flow_table_attr *attr,
u64 *fdb_rx_icm_addr,
u32 *table_id);
int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev,
@@ -1051,6 +1064,43 @@ int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn,
int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn,
struct mlx5dr_action *action);
+struct mlx5dr_cmd_ft_info {
+ u32 id;
+ u16 vport;
+ enum fs_flow_table_type type;
+};
+
+struct mlx5dr_cmd_flow_destination_hw_info {
+ enum mlx5_flow_destination_type type;
+ union {
+ u32 tir_num;
+ u32 ft_num;
+ u32 ft_id;
+ u32 counter_id;
+ struct {
+ u16 num;
+ u16 vhca_id;
+ u32 reformat_id;
+ u8 flags;
+ } vport;
+ };
+};
+
+struct mlx5dr_cmd_fte_info {
+ u32 dests_size;
+ u32 index;
+ struct mlx5_flow_context flow_context;
+ u32 *val;
+ struct mlx5_flow_act action;
+ struct mlx5dr_cmd_flow_destination_hw_info *dest_arr;
+};
+
+int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev,
+ int opmod, int modify_mask,
+ struct mlx5dr_cmd_ft_info *ft,
+ u32 group_id,
+ struct mlx5dr_cmd_fte_info *fte);
+
struct mlx5dr_fw_recalc_cs_ft {
u64 rx_icm_addr;
u32 table_id;
@@ -1065,4 +1115,12 @@ void mlx5dr_fw_destroy_recalc_cs_ft(struct mlx5dr_domain *dmn,
int mlx5dr_domain_cache_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn,
u32 vport_num,
u64 *rx_icm_addr);
+int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn,
+ struct mlx5dr_cmd_flow_destination_hw_info *dest,
+ int num_dest,
+ bool reformat_req,
+ u32 *tbl_id,
+ u32 *group_id);
+void mlx5dr_fw_destroy_md_tbl(struct mlx5dr_domain *dmn, u32 tbl_id,
+ u32 group_id);
#endif /* _DR_TYPES_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 3d587d0..3abfc81 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -74,7 +74,7 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns,
next_ft);
tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain,
- ft->level);
+ ft->level, ft->flags);
if (!tbl) {
mlx5_core_err(ns->dev, "Failed creating dr flow_table\n");
return -EINVAL;
@@ -184,13 +184,13 @@ static struct mlx5dr_action *create_vport_action(struct mlx5dr_domain *domain,
dest_attr->vport.vhca_id);
}
-static struct mlx5dr_action *create_ft_action(struct mlx5_core_dev *dev,
+static struct mlx5dr_action *create_ft_action(struct mlx5dr_domain *domain,
struct mlx5_flow_rule *dst)
{
struct mlx5_flow_table *dest_ft = dst->dest_attr.ft;
if (mlx5_dr_is_fw_table(dest_ft->flags))
- return mlx5dr_create_action_dest_flow_fw_table(dest_ft, dev);
+ return mlx5dr_action_create_dest_flow_fw_table(domain, dest_ft);
return mlx5dr_action_create_dest_table(dest_ft->fs_dr_table.dr_table);
}
@@ -206,6 +206,12 @@ static struct mlx5dr_action *create_action_push_vlan(struct mlx5dr_domain *domai
return mlx5dr_action_create_push_vlan(domain, htonl(vlan_hdr));
}
+static bool contain_vport_reformat_action(struct mlx5_flow_rule *dst)
+{
+ return dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
+ dst->dest_attr.vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
+}
+
#define MLX5_FLOW_CONTEXT_ACTION_MAX 20
static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
struct mlx5_flow_table *ft,
@@ -213,7 +219,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
struct fs_fte *fte)
{
struct mlx5dr_domain *domain = ns->fs_dr_domain.dr_domain;
- struct mlx5dr_action *term_action = NULL;
+ struct mlx5dr_action_dest *term_actions;
struct mlx5dr_match_parameters params;
struct mlx5_core_dev *dev = ns->dev;
struct mlx5dr_action **fs_dr_actions;
@@ -223,6 +229,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
struct mlx5dr_rule *rule;
struct mlx5_flow_rule *dst;
int fs_dr_num_actions = 0;
+ int num_term_actions = 0;
int num_actions = 0;
size_t match_sz;
int err = 0;
@@ -233,18 +240,38 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(*actions),
GFP_KERNEL);
- if (!actions)
- return -ENOMEM;
+ if (!actions) {
+ err = -ENOMEM;
+ goto out_err;
+ }
fs_dr_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX,
sizeof(*fs_dr_actions), GFP_KERNEL);
if (!fs_dr_actions) {
- kfree(actions);
- return -ENOMEM;
+ err = -ENOMEM;
+ goto free_actions_alloc;
+ }
+
+ term_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX,
+ sizeof(*term_actions), GFP_KERNEL);
+ if (!term_actions) {
+ err = -ENOMEM;
+ goto free_fs_dr_actions_alloc;
}
match_sz = sizeof(fte->val);
+ /* Drop reformat action bit if destination vport set with reformat */
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+ list_for_each_entry(dst, &fte->node.children, node.list) {
+ if (!contain_vport_reformat_action(dst))
+ continue;
+
+ fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+ break;
+ }
+ }
+
/* The order of the actions are must to be keep, only the following
* order is supported by SW steering:
* TX: push vlan -> modify header -> encap
@@ -335,7 +362,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
goto free_actions;
}
fs_dr_actions[fs_dr_num_actions++] = tmp_action;
- term_action = tmp_action;
+ term_actions[num_term_actions++].dest = tmp_action;
}
if (fte->flow_context.flow_tag) {
@@ -352,34 +379,25 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
list_for_each_entry(dst, &fte->node.children, node.list) {
enum mlx5_flow_destination_type type = dst->dest_attr.type;
- u32 id;
- if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+ if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX ||
+ num_term_actions >= MLX5_FLOW_CONTEXT_ACTION_MAX) {
err = -ENOSPC;
goto free_actions;
}
- switch (type) {
- case MLX5_FLOW_DESTINATION_TYPE_COUNTER:
- id = dst->dest_attr.counter_id;
+ if (type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+ continue;
- tmp_action =
- mlx5dr_action_create_flow_counter(id);
- if (!tmp_action) {
- err = -ENOMEM;
- goto free_actions;
- }
- fs_dr_actions[fs_dr_num_actions++] = tmp_action;
- actions[num_actions++] = tmp_action;
- break;
+ switch (type) {
case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
- tmp_action = create_ft_action(dev, dst);
+ tmp_action = create_ft_action(domain, dst);
if (!tmp_action) {
err = -ENOMEM;
goto free_actions;
}
fs_dr_actions[fs_dr_num_actions++] = tmp_action;
- term_action = tmp_action;
+ term_actions[num_term_actions++].dest = tmp_action;
break;
case MLX5_FLOW_DESTINATION_TYPE_VPORT:
tmp_action = create_vport_action(domain, dst);
@@ -388,7 +406,14 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
goto free_actions;
}
fs_dr_actions[fs_dr_num_actions++] = tmp_action;
- term_action = tmp_action;
+ term_actions[num_term_actions].dest = tmp_action;
+
+ if (dst->dest_attr.vport.flags &
+ MLX5_FLOW_DEST_VPORT_REFORMAT_ID)
+ term_actions[num_term_actions].reformat =
+ dst->dest_attr.vport.pkt_reformat->action.dr_action;
+
+ num_term_actions++;
break;
default:
err = -EOPNOTSUPP;
@@ -397,11 +422,50 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
}
}
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+ list_for_each_entry(dst, &fte->node.children, node.list) {
+ u32 id;
+
+ if (dst->dest_attr.type !=
+ MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+ continue;
+
+ if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+ err = -ENOSPC;
+ goto free_actions;
+ }
+
+ id = dst->dest_attr.counter_id;
+ tmp_action =
+ mlx5dr_action_create_flow_counter(id);
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ actions[num_actions++] = tmp_action;
+ }
+ }
+
params.match_sz = match_sz;
params.match_buf = (u64 *)fte->val;
+ if (num_term_actions == 1) {
+ if (term_actions->reformat)
+ actions[num_actions++] = term_actions->reformat;
- if (term_action)
- actions[num_actions++] = term_action;
+ actions[num_actions++] = term_actions->dest;
+ } else if (num_term_actions > 1) {
+ tmp_action = mlx5dr_action_create_mult_dest_tbl(domain,
+ term_actions,
+ num_term_actions);
+ if (!tmp_action) {
+ err = -EOPNOTSUPP;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ actions[num_actions++] = tmp_action;
+ }
rule = mlx5dr_rule_create(group->fs_dr_matcher.dr_matcher,
¶ms,
@@ -412,7 +476,9 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
goto free_actions;
}
+ kfree(term_actions);
kfree(actions);
+
fte->fs_dr_rule.dr_rule = rule;
fte->fs_dr_rule.num_actions = fs_dr_num_actions;
fte->fs_dr_rule.dr_actions = fs_dr_actions;
@@ -420,13 +486,18 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
return 0;
free_actions:
- for (i = 0; i < fs_dr_num_actions; i++)
+ /* Free in reverse order to handle action dependencies */
+ for (i = fs_dr_num_actions - 1; i >= 0; i--)
if (!IS_ERR_OR_NULL(fs_dr_actions[i]))
mlx5dr_action_destroy(fs_dr_actions[i]);
- mlx5_core_err(dev, "Failed to create dr rule err(%d)\n", err);
- kfree(actions);
+ kfree(term_actions);
+free_fs_dr_actions_alloc:
kfree(fs_dr_actions);
+free_actions_alloc:
+ kfree(actions);
+out_err:
+ mlx5_core_err(dev, "Failed to create dr rule err(%d)\n", err);
return err;
}
@@ -533,7 +604,8 @@ static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns,
if (err)
return err;
- for (i = 0; i < rule->num_actions; i++)
+ /* Free in reverse order to handle action dependencies */
+ for (i = rule->num_actions - 1; i >= 0; i--)
if (!IS_ERR_OR_NULL(rule->dr_actions[i]))
mlx5dr_action_destroy(rule->dr_actions[i]);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
index 1722f4668..e01c376 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
@@ -32,6 +32,7 @@ enum {
};
enum {
+ MLX5DR_ACTION_MDFY_HW_OP_COPY = 0x1,
MLX5DR_ACTION_MDFY_HW_OP_SET = 0x2,
MLX5DR_ACTION_MDFY_HW_OP_ADD = 0x3,
};
@@ -625,4 +626,19 @@ struct mlx5_ifc_dr_action_hw_set_bits {
u8 inline_data[0x20];
};
+struct mlx5_ifc_dr_action_hw_copy_bits {
+ u8 opcode[0x8];
+ u8 destination_field_code[0x8];
+ u8 reserved_at_10[0x2];
+ u8 destination_left_shifter[0x6];
+ u8 reserved_at_18[0x2];
+ u8 destination_length[0x6];
+
+ u8 reserved_at_20[0x8];
+ u8 source_field_code[0x8];
+ u8 reserved_at_30[0x2];
+ u8 source_left_shifter[0x6];
+ u8 reserved_at_38[0x8];
+};
+
#endif /* MLX5_IFC_DR_H */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
index adda9cb..e1edc9c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
@@ -33,6 +33,11 @@ struct mlx5dr_match_parameters {
u64 *match_buf; /* Device spec format */
};
+struct mlx5dr_action_dest {
+ struct mlx5dr_action *dest;
+ struct mlx5dr_action *reformat;
+};
+
#ifdef CONFIG_MLX5_SW_STEERING
struct mlx5dr_domain *
@@ -46,7 +51,7 @@ void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
struct mlx5dr_domain *peer_dmn);
struct mlx5dr_table *
-mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level);
+mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level, u32 flags);
int mlx5dr_table_destroy(struct mlx5dr_table *table);
@@ -75,14 +80,19 @@ struct mlx5dr_action *
mlx5dr_action_create_dest_table(struct mlx5dr_table *table);
struct mlx5dr_action *
-mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft,
- struct mlx5_core_dev *mdev);
+mlx5dr_action_create_dest_flow_fw_table(struct mlx5dr_domain *domain,
+ struct mlx5_flow_table *ft);
struct mlx5dr_action *
mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain,
u32 vport, u8 vhca_id_valid,
u16 vhca_id);
+struct mlx5dr_action *
+mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn,
+ struct mlx5dr_action_dest *dests,
+ u32 num_of_dests);
+
struct mlx5dr_action *mlx5dr_action_create_drop(void);
struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value);
@@ -131,7 +141,7 @@ mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
struct mlx5dr_domain *peer_dmn) { }
static inline struct mlx5dr_table *
-mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level) { return NULL; }
+mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level, u32 flags) { return NULL; }
static inline int
mlx5dr_table_destroy(struct mlx5dr_table *table) { return 0; }
@@ -165,8 +175,8 @@ static inline struct mlx5dr_action *
mlx5dr_action_create_dest_table(struct mlx5dr_table *table) { return NULL; }
static inline struct mlx5dr_action *
-mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft,
- struct mlx5_core_dev *mdev) { return NULL; }
+mlx5dr_action_create_dest_flow_fw_table(struct mlx5dr_domain *domain,
+ struct mlx5_flow_table *ft) { return NULL; }
static inline struct mlx5dr_action *
mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain,
@@ -174,6 +184,11 @@ mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain,
u16 vhca_id) { return NULL; }
static inline struct mlx5dr_action *
+mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn,
+ struct mlx5dr_action_dest *dests,
+ u32 num_of_dests) { return NULL; }
+
+static inline struct mlx5dr_action *
mlx5dr_action_create_drop(void) { return NULL; }
static inline struct mlx5dr_action *
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index f2a0e72..02f7e4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -89,7 +89,7 @@ void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides)
len = nstrides << wq->fbc.log_stride;
wqe = mlx5_wq_cyc_get_wqe(wq, ix);
- pr_info("WQE DUMP: WQ size %d WQ cur size %d, WQE index 0x%x, len: %ld\n",
+ pr_info("WQE DUMP: WQ size %d WQ cur size %d, WQE index 0x%x, len: %zu\n",
mlx5_wq_cyc_get_size(wq), wq->cur_sz, ix, len);
print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
index 2b54391..c4caeeadc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -213,8 +213,8 @@ mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u8 local_port, u8 module)
err_register_netdev:
mlxsw_m->ports[local_port] = NULL;
- free_netdev(dev);
err_dev_addr_get:
+ free_netdev(dev);
err_alloc_etherdev:
mlxsw_core_port_fini(mlxsw_m->core, local_port);
return err;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index fd59280..dd66851 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3563,8 +3563,8 @@ MLXSW_ITEM32(reg, qeec, min_shaper_rate, 0x0C, 0, 28);
*/
MLXSW_ITEM32(reg, qeec, mase, 0x10, 31, 1);
-/* A large max rate will disable the max shaper. */
-#define MLXSW_REG_QEEC_MAS_DIS 200000000 /* Kbps */
+/* The largest max shaper value possible to disable the shaper. */
+#define MLXSW_REG_QEEC_MAS_DIS ((1u << 31) - 1) /* Kbps */
/* reg_qeec_max_shaper_rate
* Max shaper information rate.
@@ -3602,6 +3602,21 @@ MLXSW_ITEM32(reg, qeec, dwrr, 0x18, 15, 1);
*/
MLXSW_ITEM32(reg, qeec, dwrr_weight, 0x18, 0, 8);
+/* reg_qeec_max_shaper_bs
+ * Max shaper burst size
+ * Burst size is 2^max_shaper_bs * 512 bits
+ * For Spectrum-1: Range is: 5..25
+ * For Spectrum-2: Range is: 11..25
+ * Reserved when ptps = 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qeec, max_shaper_bs, 0x1C, 0, 6);
+
+#define MLXSW_REG_QEEC_HIGHEST_SHAPER_BS 25
+#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP1 5
+#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP2 11
+#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 5
+
static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port,
enum mlxsw_reg_qeec_hr hr, u8 index,
u8 next_index)
@@ -5513,6 +5528,7 @@ enum mlxsw_reg_htgt_discard_trap_group {
MLXSW_REG_HTGT_DISCARD_TRAP_GROUP_BASE = MLXSW_REG_HTGT_TRAP_GROUP_MAX,
MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS,
MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS,
+ MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS,
};
/* reg_htgt_trap_group
@@ -10140,6 +10156,92 @@ static inline void mlxsw_reg_tigcr_pack(char *payload, bool ttlc, u8 ttl_uc)
mlxsw_reg_tigcr_ttl_uc_set(payload, ttl_uc);
}
+/* TIEEM - Tunneling IPinIP Encapsulation ECN Mapping Register
+ * -----------------------------------------------------------
+ * The TIEEM register maps ECN of the IP header at the ingress to the
+ * encapsulation to the ECN of the underlay network.
+ */
+#define MLXSW_REG_TIEEM_ID 0xA812
+#define MLXSW_REG_TIEEM_LEN 0x0C
+
+MLXSW_REG_DEFINE(tieem, MLXSW_REG_TIEEM_ID, MLXSW_REG_TIEEM_LEN);
+
+/* reg_tieem_overlay_ecn
+ * ECN of the IP header in the overlay network.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, tieem, overlay_ecn, 0x04, 24, 2);
+
+/* reg_tineem_underlay_ecn
+ * ECN of the IP header in the underlay network.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, tieem, underlay_ecn, 0x04, 16, 2);
+
+static inline void mlxsw_reg_tieem_pack(char *payload, u8 overlay_ecn,
+ u8 underlay_ecn)
+{
+ MLXSW_REG_ZERO(tieem, payload);
+ mlxsw_reg_tieem_overlay_ecn_set(payload, overlay_ecn);
+ mlxsw_reg_tieem_underlay_ecn_set(payload, underlay_ecn);
+}
+
+/* TIDEM - Tunneling IPinIP Decapsulation ECN Mapping Register
+ * -----------------------------------------------------------
+ * The TIDEM register configures the actions that are done in the
+ * decapsulation.
+ */
+#define MLXSW_REG_TIDEM_ID 0xA813
+#define MLXSW_REG_TIDEM_LEN 0x0C
+
+MLXSW_REG_DEFINE(tidem, MLXSW_REG_TIDEM_ID, MLXSW_REG_TIDEM_LEN);
+
+/* reg_tidem_underlay_ecn
+ * ECN field of the IP header in the underlay network.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, tidem, underlay_ecn, 0x04, 24, 2);
+
+/* reg_tidem_overlay_ecn
+ * ECN field of the IP header in the overlay network.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, tidem, overlay_ecn, 0x04, 16, 2);
+
+/* reg_tidem_eip_ecn
+ * Egress IP ECN. ECN field of the IP header of the packet which goes out
+ * from the decapsulation.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, tidem, eip_ecn, 0x04, 8, 2);
+
+/* reg_tidem_trap_en
+ * Trap enable:
+ * 0 - No trap due to decap ECN
+ * 1 - Trap enable with trap_id
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, tidem, trap_en, 0x08, 28, 4);
+
+/* reg_tidem_trap_id
+ * Trap ID. Either DECAP_ECN0 or DECAP_ECN1.
+ * Reserved when trap_en is '0'.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, tidem, trap_id, 0x08, 0, 9);
+
+static inline void mlxsw_reg_tidem_pack(char *payload, u8 underlay_ecn,
+ u8 overlay_ecn, u8 eip_ecn,
+ bool trap_en, u16 trap_id)
+{
+ MLXSW_REG_ZERO(tidem, payload);
+ mlxsw_reg_tidem_underlay_ecn_set(payload, underlay_ecn);
+ mlxsw_reg_tidem_overlay_ecn_set(payload, overlay_ecn);
+ mlxsw_reg_tidem_eip_ecn_set(payload, eip_ecn);
+ mlxsw_reg_tidem_trap_en_set(payload, trap_en);
+ mlxsw_reg_tidem_trap_id_set(payload, trap_id);
+}
+
/* SBPR - Shared Buffer Pools Register
* -----------------------------------
* The SBPR configures and retrieves the shared buffer pools and configuration.
@@ -10684,6 +10786,8 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
MLXSW_REG(tndem),
MLXSW_REG(tnpc),
MLXSW_REG(tigcr),
+ MLXSW_REG(tieem),
+ MLXSW_REG(tidem),
MLXSW_REG(sbpr),
MLXSW_REG(sbcm),
MLXSW_REG(sbpm),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index fe02ffb..7358b5b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -45,11 +45,9 @@
#include "spectrum_ptp.h"
#include "../mlxfw/mlxfw.h"
-#define MLXSW_SP_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
-
#define MLXSW_SP1_FWREV_MAJOR 13
#define MLXSW_SP1_FWREV_MINOR 2000
-#define MLXSW_SP1_FWREV_SUBMINOR 2308
+#define MLXSW_SP1_FWREV_SUBMINOR 2714
#define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702
static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
@@ -66,7 +64,7 @@ static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
#define MLXSW_SP2_FWREV_MAJOR 29
#define MLXSW_SP2_FWREV_MINOR 2000
-#define MLXSW_SP2_FWREV_SUBMINOR 2308
+#define MLXSW_SP2_FWREV_SUBMINOR 2714
static const struct mlxsw_fw_rev mlxsw_sp2_fw_rev = {
.major = MLXSW_SP2_FWREV_MAJOR,
@@ -197,6 +195,10 @@ struct mlxsw_sp_ptp_ops {
u64 *data, int data_index);
};
+struct mlxsw_sp_span_ops {
+ u32 (*buffsize_get)(int mtu, u32 speed);
+};
+
static int mlxsw_sp_component_query(struct mlxfw_dev *mlxfw_dev,
u16 component_index, u32 *p_max_size,
u8 *p_align_bits, u16 *p_max_write_size)
@@ -423,13 +425,12 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
rev->major, req_rev->major);
return -EINVAL;
}
- if (MLXSW_SP_FWREV_MINOR_TO_BRANCH(rev->minor) ==
- MLXSW_SP_FWREV_MINOR_TO_BRANCH(req_rev->minor) &&
- mlxsw_core_fw_rev_minor_subminor_validate(rev, req_rev))
+ if (mlxsw_core_fw_rev_minor_subminor_validate(rev, req_rev))
return 0;
- dev_info(mlxsw_sp->bus_info->dev, "The firmware version %d.%d.%d is incompatible with the driver\n",
- rev->major, rev->minor, rev->subminor);
+ dev_err(mlxsw_sp->bus_info->dev, "The firmware version %d.%d.%d is incompatible with the driver (required >= %d.%d.%d)\n",
+ rev->major, rev->minor, rev->subminor, req_rev->major,
+ req_rev->minor, req_rev->subminor);
dev_info(mlxsw_sp->bus_info->dev, "Flashing firmware using file %s\n",
fw_filename);
@@ -860,23 +861,17 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
u64 len;
int err;
+ if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
+ this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
+
memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb));
if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &tx_info))
return NETDEV_TX_BUSY;
- if (unlikely(skb_headroom(skb) < MLXSW_TXHDR_LEN)) {
- struct sk_buff *skb_orig = skb;
-
- skb = skb_realloc_headroom(skb, MLXSW_TXHDR_LEN);
- if (!skb) {
- this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
- dev_kfree_skb_any(skb_orig);
- return NETDEV_TX_OK;
- }
- dev_consume_skb_any(skb_orig);
- }
-
if (eth_skb_pad(skb)) {
this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
return NETDEV_TX_OK;
@@ -1215,6 +1210,9 @@ static void update_stats_cache(struct work_struct *work)
periodic_hw_stats.update_dw.work);
if (!netif_carrier_ok(mlxsw_sp_port->dev))
+ /* Note: mlxsw_sp_port_down_wipe_counters() clears the cache as
+ * necessary when port goes down.
+ */
goto out;
mlxsw_sp_port_get_hw_stats(mlxsw_sp_port->dev,
@@ -1798,6 +1796,8 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, enum tc_setup_type type,
return mlxsw_sp_setup_tc_prio(mlxsw_sp_port, type_data);
case TC_SETUP_QDISC_ETS:
return mlxsw_sp_setup_tc_ets(mlxsw_sp_port, type_data);
+ case TC_SETUP_QDISC_TBF:
+ return mlxsw_sp_setup_tc_tbf(mlxsw_sp_port, type_data);
default:
return -EOPNOTSUPP;
}
@@ -3541,6 +3541,27 @@ mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port)
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
}
+int mlxsw_sp_port_speed_get(struct mlxsw_sp_port *mlxsw_sp_port, u32 *speed)
+{
+ const struct mlxsw_sp_port_type_speed_ops *port_type_speed_ops;
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char ptys_pl[MLXSW_REG_PTYS_LEN];
+ u32 eth_proto_oper;
+ int err;
+
+ port_type_speed_ops = mlxsw_sp->port_type_speed_ops;
+ port_type_speed_ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl,
+ mlxsw_sp_port->local_port, 0,
+ false);
+ err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
+ if (err)
+ return err;
+ port_type_speed_ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, NULL, NULL,
+ ð_proto_oper);
+ *speed = port_type_speed_ops->from_ptys_speed(mlxsw_sp, eth_proto_oper);
+ return 0;
+}
+
int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
bool dwrr, u8 dwrr_weight)
@@ -3558,7 +3579,7 @@ int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
int mlxsw_sp_port_ets_maxrate_set(struct mlxsw_sp_port *mlxsw_sp_port,
enum mlxsw_reg_qeec_hr hr, u8 index,
- u8 next_index, u32 maxrate)
+ u8 next_index, u32 maxrate, u8 burst_size)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
char qeec_pl[MLXSW_REG_QEEC_LEN];
@@ -3567,6 +3588,7 @@ int mlxsw_sp_port_ets_maxrate_set(struct mlxsw_sp_port *mlxsw_sp_port,
next_index);
mlxsw_reg_qeec_mase_set(qeec_pl, true);
mlxsw_reg_qeec_max_shaper_rate_set(qeec_pl, maxrate);
+ mlxsw_reg_qeec_max_shaper_bs_set(qeec_pl, burst_size);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qeec), qeec_pl);
}
@@ -3635,14 +3657,14 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
*/
err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
MLXSW_REG_QEEC_HR_PORT, 0, 0,
- MLXSW_REG_QEEC_MAS_DIS);
+ MLXSW_REG_QEEC_MAS_DIS, 0);
if (err)
return err;
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
MLXSW_REG_QEEC_HR_SUBGROUP,
i, 0,
- MLXSW_REG_QEEC_MAS_DIS);
+ MLXSW_REG_QEEC_MAS_DIS, 0);
if (err)
return err;
}
@@ -3650,14 +3672,14 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
MLXSW_REG_QEEC_HR_TC,
i, i,
- MLXSW_REG_QEEC_MAS_DIS);
+ MLXSW_REG_QEEC_MAS_DIS, 0);
if (err)
return err;
err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
MLXSW_REG_QEEC_HR_TC,
i + 8, i,
- MLXSW_REG_QEEC_MAS_DIS);
+ MLXSW_REG_QEEC_MAS_DIS, 0);
if (err)
return err;
}
@@ -3889,6 +3911,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
INIT_DELAYED_WORK(&mlxsw_sp_port->ptp.shaper_dw,
mlxsw_sp->ptp_ops->shaper_work);
+ INIT_DELAYED_WORK(&mlxsw_sp_port->span.speed_update_dw,
+ mlxsw_sp_span_speed_update_work);
mlxsw_sp->ports[local_port] = mlxsw_sp_port;
err = register_netdev(dev);
@@ -3945,6 +3969,7 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
cancel_delayed_work_sync(&mlxsw_sp_port->periodic_hw_stats.update_dw);
+ cancel_delayed_work_sync(&mlxsw_sp_port->span.speed_update_dw);
cancel_delayed_work_sync(&mlxsw_sp_port->ptp.shaper_dw);
mlxsw_sp_port_ptp_clear(mlxsw_sp_port);
mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
@@ -4325,6 +4350,15 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port,
return 0;
}
+static void
+mlxsw_sp_port_down_wipe_counters(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ int i;
+
+ for (i = 0; i < TC_MAX_QUEUE; i++)
+ mlxsw_sp_port->periodic_hw_stats.xstats.backlog[i] = 0;
+}
+
static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
char *pude_pl, void *priv)
{
@@ -4343,9 +4377,11 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
netdev_info(mlxsw_sp_port->dev, "link up\n");
netif_carrier_on(mlxsw_sp_port->dev);
mlxsw_core_schedule_dw(&mlxsw_sp_port->ptp.shaper_dw, 0);
+ mlxsw_core_schedule_dw(&mlxsw_sp_port->span.speed_update_dw, 0);
} else {
netdev_info(mlxsw_sp_port->dev, "link down\n");
netif_carrier_off(mlxsw_sp_port->dev);
+ mlxsw_sp_port_down_wipe_counters(mlxsw_sp_port);
}
}
@@ -4541,10 +4577,16 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
false),
MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, TRAP_TO_CPU, ROUTER_EXP, false),
MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false),
- MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false),
- MLXSW_SP_RXL_MARK(DECAP_ECN0, TRAP_TO_CPU, ROUTER_EXP, false),
MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, VRRP, false),
MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, VRRP, false),
+ MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_CLASS_E, FORWARD,
+ ROUTER_EXP, false),
+ MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_MC_DMAC, FORWARD,
+ ROUTER_EXP, false),
+ MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_DIP, FORWARD,
+ ROUTER_EXP, false),
+ MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_DIP_LINK_LOCAL, FORWARD,
+ ROUTER_EXP, false),
/* PKT Sample trap */
MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU,
false, SP_IP2ME, DISCARD),
@@ -4883,6 +4925,33 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = {
.get_stats = mlxsw_sp2_get_stats,
};
+static u32 mlxsw_sp1_span_buffsize_get(int mtu, u32 speed)
+{
+ return mtu * 5 / 2;
+}
+
+static const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops = {
+ .buffsize_get = mlxsw_sp1_span_buffsize_get,
+};
+
+#define MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR 38
+
+static u32 mlxsw_sp2_span_buffsize_get(int mtu, u32 speed)
+{
+ return 3 * mtu + MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR * speed / 1000;
+}
+
+static const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops = {
+ .buffsize_get = mlxsw_sp2_span_buffsize_get,
+};
+
+u32 mlxsw_sp_span_buffsize_get(struct mlxsw_sp *mlxsw_sp, int mtu, u32 speed)
+{
+ u32 buffsize = mlxsw_sp->span_ops->buffsize_get(speed, mtu);
+
+ return mlxsw_sp_bytes_cells(mlxsw_sp, buffsize) + 1;
+}
+
static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
unsigned long event, void *ptr);
@@ -5104,8 +5173,10 @@ static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core,
mlxsw_sp->sb_vals = &mlxsw_sp1_sb_vals;
mlxsw_sp->port_type_speed_ops = &mlxsw_sp1_port_type_speed_ops;
mlxsw_sp->ptp_ops = &mlxsw_sp1_ptp_ops;
+ mlxsw_sp->span_ops = &mlxsw_sp1_span_ops;
mlxsw_sp->listeners = mlxsw_sp1_listener;
mlxsw_sp->listeners_count = ARRAY_SIZE(mlxsw_sp1_listener);
+ mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP1;
return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info, extack);
}
@@ -5129,6 +5200,31 @@ static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core,
mlxsw_sp->sb_vals = &mlxsw_sp2_sb_vals;
mlxsw_sp->port_type_speed_ops = &mlxsw_sp2_port_type_speed_ops;
mlxsw_sp->ptp_ops = &mlxsw_sp2_ptp_ops;
+ mlxsw_sp->span_ops = &mlxsw_sp2_span_ops;
+ mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP2;
+
+ return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info, extack);
+}
+
+static int mlxsw_sp3_init(struct mlxsw_core *mlxsw_core,
+ const struct mlxsw_bus_info *mlxsw_bus_info,
+ struct netlink_ext_ack *extack)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+
+ mlxsw_sp->kvdl_ops = &mlxsw_sp2_kvdl_ops;
+ mlxsw_sp->afa_ops = &mlxsw_sp2_act_afa_ops;
+ mlxsw_sp->afk_ops = &mlxsw_sp2_afk_ops;
+ mlxsw_sp->mr_tcam_ops = &mlxsw_sp2_mr_tcam_ops;
+ mlxsw_sp->acl_tcam_ops = &mlxsw_sp2_acl_tcam_ops;
+ mlxsw_sp->nve_ops_arr = mlxsw_sp2_nve_ops_arr;
+ mlxsw_sp->mac_mask = mlxsw_sp2_mac_mask;
+ mlxsw_sp->rif_ops_arr = mlxsw_sp2_rif_ops_arr;
+ mlxsw_sp->sb_vals = &mlxsw_sp2_sb_vals;
+ mlxsw_sp->port_type_speed_ops = &mlxsw_sp2_port_type_speed_ops;
+ mlxsw_sp->ptp_ops = &mlxsw_sp2_ptp_ops;
+ mlxsw_sp->span_ops = &mlxsw_sp2_span_ops;
+ mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3;
return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info, extack);
}
@@ -5635,7 +5731,7 @@ static struct mlxsw_driver mlxsw_sp2_driver = {
static struct mlxsw_driver mlxsw_sp3_driver = {
.kind = mlxsw_sp3_driver_name,
.priv_size = sizeof(struct mlxsw_sp),
- .init = mlxsw_sp2_init,
+ .init = mlxsw_sp3_init,
.fini = mlxsw_sp_fini,
.basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set,
.port_split = mlxsw_sp_port_split,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 948ef47..a0f1f9d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -140,6 +140,7 @@ struct mlxsw_sp_sb_vals;
struct mlxsw_sp_port_type_speed_ops;
struct mlxsw_sp_ptp_state;
struct mlxsw_sp_ptp_ops;
+struct mlxsw_sp_span_ops;
struct mlxsw_sp_port_mapping {
u8 module;
@@ -185,8 +186,10 @@ struct mlxsw_sp {
const struct mlxsw_sp_sb_vals *sb_vals;
const struct mlxsw_sp_port_type_speed_ops *port_type_speed_ops;
const struct mlxsw_sp_ptp_ops *ptp_ops;
+ const struct mlxsw_sp_span_ops *span_ops;
const struct mlxsw_listener *listeners;
size_t listeners_count;
+ u32 lowest_shaper_bs;
};
static inline struct mlxsw_sp_upper *
@@ -292,6 +295,9 @@ struct mlxsw_sp_port {
struct mlxsw_sp_ptp_port_stats stats;
} ptp;
u8 split_base_local_port;
+ struct {
+ struct delayed_work speed_update_dw;
+ } span;
};
struct mlxsw_sp_port_type_speed_ops {
@@ -471,6 +477,7 @@ extern struct notifier_block mlxsw_sp_switchdev_notifier;
/* spectrum.c */
void mlxsw_sp_rx_listener_no_mark_func(struct sk_buff *skb,
u8 local_port, void *priv);
+int mlxsw_sp_port_speed_get(struct mlxsw_sp_port *mlxsw_sp_port, u32 *speed);
int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
bool dwrr, u8 dwrr_weight);
@@ -481,7 +488,7 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
struct ieee_pfc *my_pfc);
int mlxsw_sp_port_ets_maxrate_set(struct mlxsw_sp_port *mlxsw_sp_port,
enum mlxsw_reg_qeec_hr hr, u8 index,
- u8 next_index, u32 maxrate);
+ u8 next_index, u32 maxrate, u8 burst_size);
enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 stp_state);
int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
u8 state);
@@ -501,6 +508,7 @@ int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp,
unsigned int *p_counter_index);
void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
unsigned int counter_index);
+u32 mlxsw_sp_span_buffsize_get(struct mlxsw_sp *mlxsw_sp, int mtu, u32 speed);
bool mlxsw_sp_port_dev_check(const struct net_device *dev);
struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev);
struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev);
@@ -854,6 +862,8 @@ int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port,
struct tc_prio_qopt_offload *p);
int mlxsw_sp_setup_tc_ets(struct mlxsw_sp_port *mlxsw_sp_port,
struct tc_ets_qopt_offload *p);
+int mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct tc_tbf_qopt_offload *p);
/* spectrum_fid.c */
bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 150b3a1..3d3cca5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -8,6 +8,7 @@
#include <linux/string.h>
#include <linux/rhashtable.h>
#include <linux/netdevice.h>
+#include <linux/mutex.h>
#include <net/net_namespace.h>
#include <net/tc_act/tc_vlan.h>
@@ -25,6 +26,7 @@ struct mlxsw_sp_acl {
struct mlxsw_sp_fid *dummy_fid;
struct rhashtable ruleset_ht;
struct list_head rules;
+ struct mutex rules_lock; /* Protects rules list */
struct {
struct delayed_work dw;
unsigned long interval; /* ms */
@@ -701,7 +703,9 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
goto err_ruleset_block_bind;
}
+ mutex_lock(&mlxsw_sp->acl->rules_lock);
list_add_tail(&rule->list, &mlxsw_sp->acl->rules);
+ mutex_unlock(&mlxsw_sp->acl->rules_lock);
block->rule_count++;
block->egress_blocker_rule_count += rule->rulei->egress_bind_blocker;
return 0;
@@ -723,7 +727,9 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker;
ruleset->ht_key.block->rule_count--;
+ mutex_lock(&mlxsw_sp->acl->rules_lock);
list_del(&rule->list);
+ mutex_unlock(&mlxsw_sp->acl->rules_lock);
if (!ruleset->ht_key.chain_index &&
mlxsw_sp_acl_ruleset_is_singular(ruleset))
mlxsw_sp_acl_ruleset_block_unbind(mlxsw_sp, ruleset,
@@ -783,19 +789,18 @@ static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl)
struct mlxsw_sp_acl_rule *rule;
int err;
- /* Protect internal structures from changes */
- rtnl_lock();
+ mutex_lock(&acl->rules_lock);
list_for_each_entry(rule, &acl->rules, list) {
err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp,
rule);
if (err)
goto err_rule_update;
}
- rtnl_unlock();
+ mutex_unlock(&acl->rules_lock);
return 0;
err_rule_update:
- rtnl_unlock();
+ mutex_unlock(&acl->rules_lock);
return err;
}
@@ -880,6 +885,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
acl->dummy_fid = fid;
INIT_LIST_HEAD(&acl->rules);
+ mutex_init(&acl->rules_lock);
err = mlxsw_sp_acl_tcam_init(mlxsw_sp, &acl->tcam);
if (err)
goto err_acl_ops_init;
@@ -892,6 +898,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
return 0;
err_acl_ops_init:
+ mutex_destroy(&acl->rules_lock);
mlxsw_sp_fid_put(fid);
err_fid_get:
rhashtable_destroy(&acl->ruleset_ht);
@@ -908,6 +915,7 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw);
mlxsw_sp_acl_tcam_fini(mlxsw_sp, &acl->tcam);
+ mutex_destroy(&acl->rules_lock);
WARN_ON(!list_empty(&acl->rules));
mlxsw_sp_fid_put(acl->dummy_fid);
rhashtable_destroy(&acl->ruleset_ht);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
index db66f2b5..49a72a8f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
@@ -526,7 +526,7 @@ static int mlxsw_sp_dcbnl_ieee_setmaxrate(struct net_device *dev,
err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
MLXSW_REG_QEEC_HR_SUBGROUP,
i, 0,
- maxrate->tc_maxrate[i]);
+ maxrate->tc_maxrate[i], 0);
if (err) {
netdev_err(dev, "Failed to set maxrate for TC %d\n", i);
goto err_port_ets_maxrate_set;
@@ -541,7 +541,8 @@ static int mlxsw_sp_dcbnl_ieee_setmaxrate(struct net_device *dev,
for (i--; i >= 0; i--)
mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
MLXSW_REG_QEEC_HR_SUBGROUP,
- i, 0, my_maxrate->tc_maxrate[i]);
+ i, 0,
+ my_maxrate->tc_maxrate[i], 0);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
index 6400cd6..a852599 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -3,8 +3,10 @@
#include <net/ip_tunnels.h>
#include <net/ip6_tunnel.h>
+#include <net/inet_ecn.h>
#include "spectrum_ipip.h"
+#include "reg.h"
struct ip_tunnel_parm
mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev)
@@ -338,3 +340,61 @@ static const struct mlxsw_sp_ipip_ops mlxsw_sp_ipip_gre4_ops = {
const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[] = {
[MLXSW_SP_IPIP_TYPE_GRE4] = &mlxsw_sp_ipip_gre4_ops,
};
+
+static int mlxsw_sp_ipip_ecn_encap_init_one(struct mlxsw_sp *mlxsw_sp,
+ u8 inner_ecn, u8 outer_ecn)
+{
+ char tieem_pl[MLXSW_REG_TIEEM_LEN];
+
+ mlxsw_reg_tieem_pack(tieem_pl, inner_ecn, outer_ecn);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tieem), tieem_pl);
+}
+
+int mlxsw_sp_ipip_ecn_encap_init(struct mlxsw_sp *mlxsw_sp)
+{
+ int i;
+
+ /* Iterate over inner ECN values */
+ for (i = INET_ECN_NOT_ECT; i <= INET_ECN_CE; i++) {
+ u8 outer_ecn = INET_ECN_encapsulate(0, i);
+ int err;
+
+ err = mlxsw_sp_ipip_ecn_encap_init_one(mlxsw_sp, i, outer_ecn);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int mlxsw_sp_ipip_ecn_decap_init_one(struct mlxsw_sp *mlxsw_sp,
+ u8 inner_ecn, u8 outer_ecn)
+{
+ char tidem_pl[MLXSW_REG_TIDEM_LEN];
+ bool trap_en, set_ce = false;
+ u8 new_inner_ecn;
+
+ trap_en = __INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce);
+ new_inner_ecn = set_ce ? INET_ECN_CE : inner_ecn;
+
+ mlxsw_reg_tidem_pack(tidem_pl, outer_ecn, inner_ecn, new_inner_ecn,
+ trap_en, trap_en ? MLXSW_TRAP_ID_DECAP_ECN0 : 0);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tidem), tidem_pl);
+}
+
+int mlxsw_sp_ipip_ecn_decap_init(struct mlxsw_sp *mlxsw_sp)
+{
+ int i, j, err;
+
+ /* Iterate over inner ECN values */
+ for (i = INET_ECN_NOT_ECT; i <= INET_ECN_CE; i++) {
+ /* Iterate over outer ECN values */
+ for (j = INET_ECN_NOT_ECT; j <= INET_ECN_CE; j++) {
+ err = mlxsw_sp_ipip_ecn_decap_init_one(mlxsw_sp, i, j);
+ if (err)
+ return err;
+ }
+ }
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index 4aaaa49..34f7c35 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -1016,27 +1016,17 @@ mlxsw_sp1_ptp_port_shaper_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable)
static int mlxsw_sp1_ptp_port_shaper_check(struct mlxsw_sp_port *mlxsw_sp_port)
{
- const struct mlxsw_sp_port_type_speed_ops *port_type_speed_ops;
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
- char ptys_pl[MLXSW_REG_PTYS_LEN];
- u32 eth_proto_oper, speed;
bool ptps = false;
int err, i;
+ u32 speed;
if (!mlxsw_sp1_ptp_hwtstamp_enabled(mlxsw_sp_port))
return mlxsw_sp1_ptp_port_shaper_set(mlxsw_sp_port, false);
- port_type_speed_ops = mlxsw_sp->port_type_speed_ops;
- port_type_speed_ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl,
- mlxsw_sp_port->local_port, 0,
- false);
- err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
+ err = mlxsw_sp_port_speed_get(mlxsw_sp_port, &speed);
if (err)
return err;
- port_type_speed_ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, NULL, NULL,
- ð_proto_oper);
- speed = port_type_speed_ops->from_ptys_speed(mlxsw_sp, eth_proto_oper);
for (i = 0; i < MLXSW_SP1_PTP_SHAPER_PARAMS_LEN; i++) {
if (mlxsw_sp1_ptp_shaper_params[i].ethtool_speed == speed) {
ptps = true;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
index 81a2c08..79a2801 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
@@ -19,6 +19,7 @@ enum mlxsw_sp_qdisc_type {
MLXSW_SP_QDISC_RED,
MLXSW_SP_QDISC_PRIO,
MLXSW_SP_QDISC_ETS,
+ MLXSW_SP_QDISC_TBF,
};
struct mlxsw_sp_qdisc_ops {
@@ -196,6 +197,20 @@ mlxsw_sp_qdisc_get_xstats(struct mlxsw_sp_port *mlxsw_sp_port,
return -EOPNOTSUPP;
}
+static u64
+mlxsw_sp_xstats_backlog(struct mlxsw_sp_port_xstats *xstats, int tclass_num)
+{
+ return xstats->backlog[tclass_num] +
+ xstats->backlog[tclass_num + 8];
+}
+
+static u64
+mlxsw_sp_xstats_tail_drop(struct mlxsw_sp_port_xstats *xstats, int tclass_num)
+{
+ return xstats->tail_drop[tclass_num] +
+ xstats->tail_drop[tclass_num + 8];
+}
+
static void
mlxsw_sp_qdisc_bstats_per_priority_get(struct mlxsw_sp_port_xstats *xstats,
u8 prio_bitmap, u64 *tx_packets,
@@ -213,6 +228,70 @@ mlxsw_sp_qdisc_bstats_per_priority_get(struct mlxsw_sp_port_xstats *xstats,
}
}
+static void
+mlxsw_sp_qdisc_collect_tc_stats(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+ u64 *p_tx_bytes, u64 *p_tx_packets,
+ u64 *p_drops, u64 *p_backlog)
+{
+ u8 tclass_num = mlxsw_sp_qdisc->tclass_num;
+ struct mlxsw_sp_port_xstats *xstats;
+ u64 tx_bytes, tx_packets;
+
+ xstats = &mlxsw_sp_port->periodic_hw_stats.xstats;
+ mlxsw_sp_qdisc_bstats_per_priority_get(xstats,
+ mlxsw_sp_qdisc->prio_bitmap,
+ &tx_packets, &tx_bytes);
+
+ *p_tx_packets += tx_packets;
+ *p_tx_bytes += tx_bytes;
+ *p_drops += xstats->wred_drop[tclass_num] +
+ mlxsw_sp_xstats_tail_drop(xstats, tclass_num);
+ *p_backlog += mlxsw_sp_xstats_backlog(xstats, tclass_num);
+}
+
+static void
+mlxsw_sp_qdisc_update_stats(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+ u64 tx_bytes, u64 tx_packets,
+ u64 drops, u64 backlog,
+ struct tc_qopt_offload_stats *stats_ptr)
+{
+ struct mlxsw_sp_qdisc_stats *stats_base = &mlxsw_sp_qdisc->stats_base;
+
+ tx_bytes -= stats_base->tx_bytes;
+ tx_packets -= stats_base->tx_packets;
+ drops -= stats_base->drops;
+ backlog -= stats_base->backlog;
+
+ _bstats_update(stats_ptr->bstats, tx_bytes, tx_packets);
+ stats_ptr->qstats->drops += drops;
+ stats_ptr->qstats->backlog += mlxsw_sp_cells_bytes(mlxsw_sp, backlog);
+
+ stats_base->backlog += backlog;
+ stats_base->drops += drops;
+ stats_base->tx_bytes += tx_bytes;
+ stats_base->tx_packets += tx_packets;
+}
+
+static void
+mlxsw_sp_qdisc_get_tc_stats(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+ struct tc_qopt_offload_stats *stats_ptr)
+{
+ u64 tx_packets = 0;
+ u64 tx_bytes = 0;
+ u64 backlog = 0;
+ u64 drops = 0;
+
+ mlxsw_sp_qdisc_collect_tc_stats(mlxsw_sp_port, mlxsw_sp_qdisc,
+ &tx_bytes, &tx_packets,
+ &drops, &backlog);
+ mlxsw_sp_qdisc_update_stats(mlxsw_sp_port->mlxsw_sp, mlxsw_sp_qdisc,
+ tx_bytes, tx_packets, drops, backlog,
+ stats_ptr);
+}
+
static int
mlxsw_sp_tclass_congestion_enable(struct mlxsw_sp_port *mlxsw_sp_port,
int tclass_num, u32 min, u32 max,
@@ -270,7 +349,7 @@ mlxsw_sp_setup_tc_qdisc_red_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port,
&stats_base->tx_bytes);
red_base->prob_mark = xstats->ecn;
red_base->prob_drop = xstats->wred_drop[tclass_num];
- red_base->pdrop = xstats->tail_drop[tclass_num];
+ red_base->pdrop = mlxsw_sp_xstats_tail_drop(xstats, tclass_num);
stats_base->overlimits = red_base->prob_drop + red_base->prob_mark;
stats_base->drops = red_base->prob_drop + red_base->pdrop;
@@ -343,17 +422,26 @@ mlxsw_sp_qdisc_red_replace(struct mlxsw_sp_port *mlxsw_sp_port,
}
static void
+mlxsw_sp_qdisc_leaf_unoffload(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+ struct gnet_stats_queue *qstats)
+{
+ u64 backlog;
+
+ backlog = mlxsw_sp_cells_bytes(mlxsw_sp_port->mlxsw_sp,
+ mlxsw_sp_qdisc->stats_base.backlog);
+ qstats->backlog -= backlog;
+ mlxsw_sp_qdisc->stats_base.backlog = 0;
+}
+
+static void
mlxsw_sp_qdisc_red_unoffload(struct mlxsw_sp_port *mlxsw_sp_port,
struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
void *params)
{
struct tc_red_qopt_offload_params *p = params;
- u64 backlog;
- backlog = mlxsw_sp_cells_bytes(mlxsw_sp_port->mlxsw_sp,
- mlxsw_sp_qdisc->stats_base.backlog);
- p->qstats->backlog -= backlog;
- mlxsw_sp_qdisc->stats_base.backlog = 0;
+ mlxsw_sp_qdisc_leaf_unoffload(mlxsw_sp_port, mlxsw_sp_qdisc, p->qstats);
}
static int
@@ -371,7 +459,8 @@ mlxsw_sp_qdisc_get_red_xstats(struct mlxsw_sp_port *mlxsw_sp_port,
early_drops = xstats->wred_drop[tclass_num] - xstats_base->prob_drop;
marks = xstats->ecn - xstats_base->prob_mark;
- pdrops = xstats->tail_drop[tclass_num] - xstats_base->pdrop;
+ pdrops = mlxsw_sp_xstats_tail_drop(xstats, tclass_num) -
+ xstats_base->pdrop;
res->pdrop += pdrops;
res->prob_drop += early_drops;
@@ -388,40 +477,21 @@ mlxsw_sp_qdisc_get_red_stats(struct mlxsw_sp_port *mlxsw_sp_port,
struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
struct tc_qopt_offload_stats *stats_ptr)
{
- u64 tx_bytes, tx_packets, overlimits, drops, backlog;
u8 tclass_num = mlxsw_sp_qdisc->tclass_num;
struct mlxsw_sp_qdisc_stats *stats_base;
struct mlxsw_sp_port_xstats *xstats;
+ u64 overlimits;
xstats = &mlxsw_sp_port->periodic_hw_stats.xstats;
stats_base = &mlxsw_sp_qdisc->stats_base;
- mlxsw_sp_qdisc_bstats_per_priority_get(xstats,
- mlxsw_sp_qdisc->prio_bitmap,
- &tx_packets, &tx_bytes);
- tx_bytes = tx_bytes - stats_base->tx_bytes;
- tx_packets = tx_packets - stats_base->tx_packets;
-
+ mlxsw_sp_qdisc_get_tc_stats(mlxsw_sp_port, mlxsw_sp_qdisc, stats_ptr);
overlimits = xstats->wred_drop[tclass_num] + xstats->ecn -
stats_base->overlimits;
- drops = xstats->wred_drop[tclass_num] + xstats->tail_drop[tclass_num] -
- stats_base->drops;
- backlog = xstats->backlog[tclass_num];
- _bstats_update(stats_ptr->bstats, tx_bytes, tx_packets);
stats_ptr->qstats->overlimits += overlimits;
- stats_ptr->qstats->drops += drops;
- stats_ptr->qstats->backlog +=
- mlxsw_sp_cells_bytes(mlxsw_sp_port->mlxsw_sp,
- backlog) -
- mlxsw_sp_cells_bytes(mlxsw_sp_port->mlxsw_sp,
- stats_base->backlog);
-
- stats_base->backlog = backlog;
- stats_base->drops += drops;
stats_base->overlimits += overlimits;
- stats_base->tx_bytes += tx_bytes;
- stats_base->tx_packets += tx_packets;
+
return 0;
}
@@ -471,6 +541,204 @@ int mlxsw_sp_setup_tc_red(struct mlxsw_sp_port *mlxsw_sp_port,
}
}
+static void
+mlxsw_sp_setup_tc_qdisc_leaf_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
+{
+ u64 backlog_cells = 0;
+ u64 tx_packets = 0;
+ u64 tx_bytes = 0;
+ u64 drops = 0;
+
+ mlxsw_sp_qdisc_collect_tc_stats(mlxsw_sp_port, mlxsw_sp_qdisc,
+ &tx_bytes, &tx_packets,
+ &drops, &backlog_cells);
+
+ mlxsw_sp_qdisc->stats_base.tx_packets = tx_packets;
+ mlxsw_sp_qdisc->stats_base.tx_bytes = tx_bytes;
+ mlxsw_sp_qdisc->stats_base.drops = drops;
+ mlxsw_sp_qdisc->stats_base.backlog = 0;
+}
+
+static int
+mlxsw_sp_qdisc_tbf_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
+{
+ struct mlxsw_sp_qdisc *root_qdisc = mlxsw_sp_port->root_qdisc;
+
+ if (root_qdisc != mlxsw_sp_qdisc)
+ root_qdisc->stats_base.backlog -=
+ mlxsw_sp_qdisc->stats_base.backlog;
+
+ return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
+ MLXSW_REG_QEEC_HR_SUBGROUP,
+ mlxsw_sp_qdisc->tclass_num, 0,
+ MLXSW_REG_QEEC_MAS_DIS, 0);
+}
+
+static int
+mlxsw_sp_qdisc_tbf_bs(struct mlxsw_sp_port *mlxsw_sp_port,
+ u32 max_size, u8 *p_burst_size)
+{
+ /* TBF burst size is configured in bytes. The ASIC burst size value is
+ * ((2 ^ bs) * 512 bits. Convert the TBF bytes to 512-bit units.
+ */
+ u32 bs512 = max_size / 64;
+ u8 bs = fls(bs512);
+
+ if (!bs)
+ return -EINVAL;
+ --bs;
+
+ /* Demand a power of two. */
+ if ((1 << bs) != bs512)
+ return -EINVAL;
+
+ if (bs < mlxsw_sp_port->mlxsw_sp->lowest_shaper_bs ||
+ bs > MLXSW_REG_QEEC_HIGHEST_SHAPER_BS)
+ return -EINVAL;
+
+ *p_burst_size = bs;
+ return 0;
+}
+
+static u32
+mlxsw_sp_qdisc_tbf_max_size(u8 bs)
+{
+ return (1U << bs) * 64;
+}
+
+static u64
+mlxsw_sp_qdisc_tbf_rate_kbps(struct tc_tbf_qopt_offload_replace_params *p)
+{
+ /* TBF interface is in bytes/s, whereas Spectrum ASIC is configured in
+ * Kbits/s.
+ */
+ return p->rate.rate_bytes_ps / 1000 * 8;
+}
+
+static int
+mlxsw_sp_qdisc_tbf_check_params(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+ void *params)
+{
+ struct tc_tbf_qopt_offload_replace_params *p = params;
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ u64 rate_kbps = mlxsw_sp_qdisc_tbf_rate_kbps(p);
+ u8 burst_size;
+ int err;
+
+ if (rate_kbps >= MLXSW_REG_QEEC_MAS_DIS) {
+ dev_err(mlxsw_sp_port->mlxsw_sp->bus_info->dev,
+ "spectrum: TBF: rate of %lluKbps must be below %u\n",
+ rate_kbps, MLXSW_REG_QEEC_MAS_DIS);
+ return -EINVAL;
+ }
+
+ err = mlxsw_sp_qdisc_tbf_bs(mlxsw_sp_port, p->max_size, &burst_size);
+ if (err) {
+ u8 highest_shaper_bs = MLXSW_REG_QEEC_HIGHEST_SHAPER_BS;
+
+ dev_err(mlxsw_sp->bus_info->dev,
+ "spectrum: TBF: invalid burst size of %u, must be a power of two between %u and %u",
+ p->max_size,
+ mlxsw_sp_qdisc_tbf_max_size(mlxsw_sp->lowest_shaper_bs),
+ mlxsw_sp_qdisc_tbf_max_size(highest_shaper_bs));
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int
+mlxsw_sp_qdisc_tbf_replace(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+ void *params)
+{
+ struct tc_tbf_qopt_offload_replace_params *p = params;
+ u64 rate_kbps = mlxsw_sp_qdisc_tbf_rate_kbps(p);
+ u8 burst_size;
+ int err;
+
+ err = mlxsw_sp_qdisc_tbf_bs(mlxsw_sp_port, p->max_size, &burst_size);
+ if (WARN_ON_ONCE(err))
+ /* check_params above was supposed to reject this value. */
+ return -EINVAL;
+
+ /* Configure subgroup shaper, so that both UC and MC traffic is subject
+ * to shaping. That is unlike RED, however UC queue lengths are going to
+ * be different than MC ones due to different pool and quota
+ * configurations, so the configuration is not applicable. For shaper on
+ * the other hand, subjecting the overall stream to the configured
+ * shaper makes sense. Also note that that is what we do for
+ * ieee_setmaxrate().
+ */
+ return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
+ MLXSW_REG_QEEC_HR_SUBGROUP,
+ mlxsw_sp_qdisc->tclass_num, 0,
+ rate_kbps, burst_size);
+}
+
+static void
+mlxsw_sp_qdisc_tbf_unoffload(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+ void *params)
+{
+ struct tc_tbf_qopt_offload_replace_params *p = params;
+
+ mlxsw_sp_qdisc_leaf_unoffload(mlxsw_sp_port, mlxsw_sp_qdisc, p->qstats);
+}
+
+static int
+mlxsw_sp_qdisc_get_tbf_stats(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+ struct tc_qopt_offload_stats *stats_ptr)
+{
+ mlxsw_sp_qdisc_get_tc_stats(mlxsw_sp_port, mlxsw_sp_qdisc,
+ stats_ptr);
+ return 0;
+}
+
+static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_tbf = {
+ .type = MLXSW_SP_QDISC_TBF,
+ .check_params = mlxsw_sp_qdisc_tbf_check_params,
+ .replace = mlxsw_sp_qdisc_tbf_replace,
+ .unoffload = mlxsw_sp_qdisc_tbf_unoffload,
+ .destroy = mlxsw_sp_qdisc_tbf_destroy,
+ .get_stats = mlxsw_sp_qdisc_get_tbf_stats,
+ .clean_stats = mlxsw_sp_setup_tc_qdisc_leaf_clean_stats,
+};
+
+int mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct tc_tbf_qopt_offload *p)
+{
+ struct mlxsw_sp_qdisc *mlxsw_sp_qdisc;
+
+ mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, false);
+ if (!mlxsw_sp_qdisc)
+ return -EOPNOTSUPP;
+
+ if (p->command == TC_TBF_REPLACE)
+ return mlxsw_sp_qdisc_replace(mlxsw_sp_port, p->handle,
+ mlxsw_sp_qdisc,
+ &mlxsw_sp_qdisc_ops_tbf,
+ &p->replace_params);
+
+ if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle,
+ MLXSW_SP_QDISC_TBF))
+ return -EOPNOTSUPP;
+
+ switch (p->command) {
+ case TC_TBF_DESTROY:
+ return mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
+ case TC_TBF_STATS:
+ return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc,
+ &p->stats);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static int
__mlxsw_sp_qdisc_ets_destroy(struct mlxsw_sp_port *mlxsw_sp_port)
{
@@ -612,37 +880,23 @@ mlxsw_sp_qdisc_get_prio_stats(struct mlxsw_sp_port *mlxsw_sp_port,
struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
struct tc_qopt_offload_stats *stats_ptr)
{
- u64 tx_bytes, tx_packets, drops = 0, backlog = 0;
- struct mlxsw_sp_qdisc_stats *stats_base;
- struct mlxsw_sp_port_xstats *xstats;
- struct rtnl_link_stats64 *stats;
+ struct mlxsw_sp_qdisc *tc_qdisc;
+ u64 tx_packets = 0;
+ u64 tx_bytes = 0;
+ u64 backlog = 0;
+ u64 drops = 0;
int i;
- xstats = &mlxsw_sp_port->periodic_hw_stats.xstats;
- stats = &mlxsw_sp_port->periodic_hw_stats.stats;
- stats_base = &mlxsw_sp_qdisc->stats_base;
-
- tx_bytes = stats->tx_bytes - stats_base->tx_bytes;
- tx_packets = stats->tx_packets - stats_base->tx_packets;
-
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
- drops += xstats->tail_drop[i];
- drops += xstats->wred_drop[i];
- backlog += xstats->backlog[i];
+ tc_qdisc = &mlxsw_sp_port->tclass_qdiscs[i];
+ mlxsw_sp_qdisc_collect_tc_stats(mlxsw_sp_port, tc_qdisc,
+ &tx_bytes, &tx_packets,
+ &drops, &backlog);
}
- drops = drops - stats_base->drops;
- _bstats_update(stats_ptr->bstats, tx_bytes, tx_packets);
- stats_ptr->qstats->drops += drops;
- stats_ptr->qstats->backlog +=
- mlxsw_sp_cells_bytes(mlxsw_sp_port->mlxsw_sp,
- backlog) -
- mlxsw_sp_cells_bytes(mlxsw_sp_port->mlxsw_sp,
- stats_base->backlog);
- stats_base->backlog = backlog;
- stats_base->drops += drops;
- stats_base->tx_bytes += tx_bytes;
- stats_base->tx_packets += tx_packets;
+ mlxsw_sp_qdisc_update_stats(mlxsw_sp_port->mlxsw_sp, mlxsw_sp_qdisc,
+ tx_bytes, tx_packets, drops, backlog,
+ stats_ptr);
return 0;
}
@@ -664,7 +918,7 @@ mlxsw_sp_setup_tc_qdisc_prio_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port,
stats_base->drops = 0;
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
- stats_base->drops += xstats->tail_drop[i];
+ stats_base->drops += mlxsw_sp_xstats_tail_drop(xstats, i);
stats_base->drops += xstats->wred_drop[i];
}
@@ -767,6 +1021,13 @@ __mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port,
mlxsw_sp_port->tclass_qdiscs[tclass_num].handle == child_handle)
return 0;
+ if (!child_handle) {
+ /* This is an invisible FIFO replacing the original Qdisc.
+ * Ignore it--the original Qdisc's destroy will follow.
+ */
+ return 0;
+ }
+
/* See if the grafted qdisc is already offloaded on any tclass. If so,
* unoffload it.
*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 7f70aa7..ce70772 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3235,20 +3235,6 @@ mlxsw_sp_nexthop_fib_entries_update(struct mlxsw_sp *mlxsw_sp,
return 0;
}
-static void
-mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op, int err);
-
-static void
-mlxsw_sp_nexthop_fib_entries_refresh(struct mlxsw_sp_nexthop_group *nh_grp)
-{
- enum mlxsw_reg_ralue_op op = MLXSW_REG_RALUE_OP_WRITE_WRITE;
- struct mlxsw_sp_fib_entry *fib_entry;
-
- list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node)
- mlxsw_sp_fib_entry_offload_refresh(fib_entry, op, 0);
-}
-
static void mlxsw_sp_adj_grp_size_round_up(u16 *p_adj_grp_size)
{
/* Valid sizes for an adjacency group are:
@@ -3352,6 +3338,73 @@ mlxsw_sp_nexthop_group_rebalance(struct mlxsw_sp_nexthop_group *nh_grp)
}
}
+static struct mlxsw_sp_nexthop *
+mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp,
+ const struct mlxsw_sp_rt6 *mlxsw_sp_rt6);
+
+static void
+mlxsw_sp_nexthop4_group_offload_refresh(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ int i;
+
+ for (i = 0; i < nh_grp->count; i++) {
+ struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+
+ if (nh->offloaded)
+ nh->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
+ else
+ nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
+ }
+}
+
+static void
+__mlxsw_sp_nexthop6_group_offload_refresh(struct mlxsw_sp_nexthop_group *nh_grp,
+ struct mlxsw_sp_fib6_entry *fib6_entry)
+{
+ struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
+
+ list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
+ struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh;
+ struct mlxsw_sp_nexthop *nh;
+
+ nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6);
+ if (nh && nh->offloaded)
+ fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
+ else
+ fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
+ }
+}
+
+static void
+mlxsw_sp_nexthop6_group_offload_refresh(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ struct mlxsw_sp_fib6_entry *fib6_entry;
+
+ /* Unfortunately, in IPv6 the route and the nexthop are described by
+ * the same struct, so we need to iterate over all the routes using the
+ * nexthop group and set / clear the offload indication for them.
+ */
+ list_for_each_entry(fib6_entry, &nh_grp->fib_list,
+ common.nexthop_group_node)
+ __mlxsw_sp_nexthop6_group_offload_refresh(nh_grp, fib6_entry);
+}
+
+static void
+mlxsw_sp_nexthop_group_offload_refresh(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ switch (mlxsw_sp_nexthop_group_type(nh_grp)) {
+ case AF_INET:
+ mlxsw_sp_nexthop4_group_offload_refresh(mlxsw_sp, nh_grp);
+ break;
+ case AF_INET6:
+ mlxsw_sp_nexthop6_group_offload_refresh(mlxsw_sp, nh_grp);
+ break;
+ }
+}
+
static void
mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp)
@@ -3425,6 +3478,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
goto set_trap;
}
+ mlxsw_sp_nexthop_group_offload_refresh(mlxsw_sp, nh_grp);
+
if (!old_adj_index_valid) {
/* The trap was set for fib entries, so we have to call
* fib entry update to unset it and use adjacency index.
@@ -3446,9 +3501,6 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
goto set_trap;
}
- /* Offload state within the group changed, so update the flags. */
- mlxsw_sp_nexthop_fib_entries_refresh(nh_grp);
-
return;
set_trap:
@@ -3461,6 +3513,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
if (err)
dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n");
+ mlxsw_sp_nexthop_group_offload_refresh(mlxsw_sp, nh_grp);
if (old_adj_index_valid)
mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
nh_grp->ecmp_size, nh_grp->adj_index);
@@ -4043,131 +4096,128 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp,
}
static void
-mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
+mlxsw_sp_fib4_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
- struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
- int i;
+ struct fib_info *fi = mlxsw_sp_nexthop4_group_fi(fib_entry->nh_group);
+ u32 *p_dst = (u32 *) fib_entry->fib_node->key.addr;
+ int dst_len = fib_entry->fib_node->key.prefix_len;
+ struct mlxsw_sp_fib4_entry *fib4_entry;
+ struct fib_rt_info fri;
+ bool should_offload;
- if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL ||
- fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE ||
- fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP ||
- fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP) {
- nh_grp->nexthops->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
- return;
- }
-
- for (i = 0; i < nh_grp->count; i++) {
- struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
-
- if (nh->offloaded)
- nh->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
- else
- nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
- }
+ should_offload = mlxsw_sp_fib_entry_should_offload(fib_entry);
+ fib4_entry = container_of(fib_entry, struct mlxsw_sp_fib4_entry,
+ common);
+ fri.fi = fi;
+ fri.tb_id = fib4_entry->tb_id;
+ fri.dst = cpu_to_be32(*p_dst);
+ fri.dst_len = dst_len;
+ fri.tos = fib4_entry->tos;
+ fri.type = fib4_entry->type;
+ fri.offload = should_offload;
+ fri.trap = !should_offload;
+ fib_alias_hw_flags_set(mlxsw_sp_net(mlxsw_sp), &fri);
}
static void
-mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
+mlxsw_sp_fib4_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
- struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
- int i;
+ struct fib_info *fi = mlxsw_sp_nexthop4_group_fi(fib_entry->nh_group);
+ u32 *p_dst = (u32 *) fib_entry->fib_node->key.addr;
+ int dst_len = fib_entry->fib_node->key.prefix_len;
+ struct mlxsw_sp_fib4_entry *fib4_entry;
+ struct fib_rt_info fri;
- if (!list_is_singular(&nh_grp->fib_list))
- return;
-
- for (i = 0; i < nh_grp->count; i++) {
- struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
-
- nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
- }
+ fib4_entry = container_of(fib_entry, struct mlxsw_sp_fib4_entry,
+ common);
+ fri.fi = fi;
+ fri.tb_id = fib4_entry->tb_id;
+ fri.dst = cpu_to_be32(*p_dst);
+ fri.dst_len = dst_len;
+ fri.tos = fib4_entry->tos;
+ fri.type = fib4_entry->type;
+ fri.offload = false;
+ fri.trap = false;
+ fib_alias_hw_flags_set(mlxsw_sp_net(mlxsw_sp), &fri);
}
static void
-mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
+mlxsw_sp_fib6_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
+{
+ struct mlxsw_sp_fib6_entry *fib6_entry;
+ struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
+ bool should_offload;
+
+ should_offload = mlxsw_sp_fib_entry_should_offload(fib_entry);
+
+ /* In IPv6 a multipath route is represented using multiple routes, so
+ * we need to set the flags on all of them.
+ */
+ fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry,
+ common);
+ list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list)
+ fib6_info_hw_flags_set(mlxsw_sp_rt6->rt, should_offload,
+ !should_offload);
+}
+
+static void
+mlxsw_sp_fib6_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry,
common);
-
- if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL ||
- fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE) {
- list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6,
- list)->rt->fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
- return;
- }
-
- list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
- struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
- struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh;
- struct mlxsw_sp_nexthop *nh;
-
- nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6);
- if (nh && nh->offloaded)
- fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
- else
- fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
- }
+ list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list)
+ fib6_info_hw_flags_set(mlxsw_sp_rt6->rt, false, false);
}
static void
-mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
-{
- struct mlxsw_sp_fib6_entry *fib6_entry;
- struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
-
- fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry,
- common);
- list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
- struct fib6_info *rt = mlxsw_sp_rt6->rt;
-
- rt->fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
- }
-}
-
-static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
+mlxsw_sp_fib_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
switch (fib_entry->fib_node->fib->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
- mlxsw_sp_fib4_entry_offload_set(fib_entry);
+ mlxsw_sp_fib4_entry_hw_flags_set(mlxsw_sp, fib_entry);
break;
case MLXSW_SP_L3_PROTO_IPV6:
- mlxsw_sp_fib6_entry_offload_set(fib_entry);
+ mlxsw_sp_fib6_entry_hw_flags_set(mlxsw_sp, fib_entry);
break;
}
}
static void
-mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
+mlxsw_sp_fib_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
switch (fib_entry->fib_node->fib->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
- mlxsw_sp_fib4_entry_offload_unset(fib_entry);
+ mlxsw_sp_fib4_entry_hw_flags_clear(mlxsw_sp, fib_entry);
break;
case MLXSW_SP_L3_PROTO_IPV6:
- mlxsw_sp_fib6_entry_offload_unset(fib_entry);
+ mlxsw_sp_fib6_entry_hw_flags_clear(mlxsw_sp, fib_entry);
break;
}
}
static void
-mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op, int err)
+mlxsw_sp_fib_entry_hw_flags_refresh(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry,
+ enum mlxsw_reg_ralue_op op)
{
switch (op) {
- case MLXSW_REG_RALUE_OP_WRITE_DELETE:
- return mlxsw_sp_fib_entry_offload_unset(fib_entry);
case MLXSW_REG_RALUE_OP_WRITE_WRITE:
- if (err)
- return;
- if (mlxsw_sp_fib_entry_should_offload(fib_entry))
- mlxsw_sp_fib_entry_offload_set(fib_entry);
- else
- mlxsw_sp_fib_entry_offload_unset(fib_entry);
- return;
+ mlxsw_sp_fib_entry_hw_flags_set(mlxsw_sp, fib_entry);
+ break;
+ case MLXSW_REG_RALUE_OP_WRITE_DELETE:
+ mlxsw_sp_fib_entry_hw_flags_clear(mlxsw_sp, fib_entry);
+ break;
default:
- return;
+ break;
}
}
@@ -4394,7 +4444,10 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
{
int err = __mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, op);
- mlxsw_sp_fib_entry_offload_refresh(fib_entry, op, err);
+ if (err)
+ return err;
+
+ mlxsw_sp_fib_entry_hw_flags_refresh(mlxsw_sp, fib_entry, op);
return err;
}
@@ -4830,7 +4883,7 @@ mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp,
if (!replaced)
return 0;
- mlxsw_sp_fib_entry_offload_unset(replaced);
+ mlxsw_sp_fib_entry_hw_flags_clear(mlxsw_sp, replaced);
fib4_replaced = container_of(replaced, struct mlxsw_sp_fib4_entry,
common);
mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib4_replaced);
@@ -5113,6 +5166,11 @@ static int mlxsw_sp_nexthop6_group_get(struct mlxsw_sp *mlxsw_sp,
&nh_grp->fib_list);
fib6_entry->common.nh_group = nh_grp;
+ /* The route and the nexthop are described by the same struct, so we
+ * need to the update the nexthop offload indication for the new route.
+ */
+ __mlxsw_sp_nexthop6_group_offload_refresh(nh_grp, fib6_entry);
+
return 0;
}
@@ -5393,7 +5451,7 @@ static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp,
if (!replaced)
return 0;
- mlxsw_sp_fib_entry_offload_unset(replaced);
+ mlxsw_sp_fib_entry_hw_flags_clear(mlxsw_sp, replaced);
fib6_replaced = container_of(replaced, struct mlxsw_sp_fib6_entry,
common);
mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_replaced);
@@ -7733,8 +7791,18 @@ mlxsw_sp_ipip_config_tigcr(struct mlxsw_sp *mlxsw_sp)
static int mlxsw_sp_ipips_init(struct mlxsw_sp *mlxsw_sp)
{
+ int err;
+
mlxsw_sp->router->ipip_ops_arr = mlxsw_sp_ipip_ops_arr;
INIT_LIST_HEAD(&mlxsw_sp->router->ipip_list);
+
+ err = mlxsw_sp_ipip_ecn_encap_init(mlxsw_sp);
+ if (err)
+ return err;
+ err = mlxsw_sp_ipip_ecn_decap_init(mlxsw_sp);
+ if (err)
+ return err;
+
return mlxsw_sp_ipip_config_tigcr(mlxsw_sp);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index cc1de91..c9b94f4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -104,4 +104,7 @@ static inline bool mlxsw_sp_l3addr_eq(const union mlxsw_sp_l3addr *addr1,
return !memcmp(addr1, addr2, sizeof(*addr1));
}
+int mlxsw_sp_ipip_ecn_encap_init(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_ipip_ecn_decap_init(struct mlxsw_sp *mlxsw_sp);
+
#endif /* _MLXSW_ROUTER_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 200d324..0cdd795 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -748,35 +748,52 @@ static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port)
return false;
}
-static int mlxsw_sp_span_mtu_to_buffsize(const struct mlxsw_sp *mlxsw_sp,
- int mtu)
+static int
+mlxsw_sp_span_port_buffsize_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
{
- return mlxsw_sp_bytes_cells(mlxsw_sp, mtu * 5 / 2) + 1;
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char sbib_pl[MLXSW_REG_SBIB_LEN];
+ u32 buffsize;
+ u32 speed;
+ int err;
+
+ err = mlxsw_sp_port_speed_get(mlxsw_sp_port, &speed);
+ if (err)
+ return err;
+ if (speed == SPEED_UNKNOWN)
+ speed = 0;
+
+ buffsize = mlxsw_sp_span_buffsize_get(mlxsw_sp, speed, mtu);
+ mlxsw_reg_sbib_pack(sbib_pl, mlxsw_sp_port->local_port, buffsize);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
}
int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu)
{
- struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp;
- char sbib_pl[MLXSW_REG_SBIB_LEN];
- int err;
-
/* If port is egress mirrored, the shared buffer size should be
* updated according to the mtu value
*/
- if (mlxsw_sp_span_is_egress_mirror(port)) {
- u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, mtu);
-
- mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize);
- err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
- if (err) {
- netdev_err(port->dev, "Could not update shared buffer for mirroring\n");
- return err;
- }
- }
-
+ if (mlxsw_sp_span_is_egress_mirror(port))
+ return mlxsw_sp_span_port_buffsize_update(port, mtu);
return 0;
}
+void mlxsw_sp_span_speed_update_work(struct work_struct *work)
+{
+ struct delayed_work *dwork = to_delayed_work(work);
+ struct mlxsw_sp_port *mlxsw_sp_port;
+
+ mlxsw_sp_port = container_of(dwork, struct mlxsw_sp_port,
+ span.speed_update_dw);
+
+ /* If port is egress mirrored, the shared buffer size should be
+ * updated according to the speed value.
+ */
+ if (mlxsw_sp_span_is_egress_mirror(mlxsw_sp_port))
+ mlxsw_sp_span_port_buffsize_update(mlxsw_sp_port,
+ mlxsw_sp_port->dev->mtu);
+}
+
static struct mlxsw_sp_span_inspected_port *
mlxsw_sp_span_entry_bound_port_find(struct mlxsw_sp_span_entry *span_entry,
enum mlxsw_sp_span_type type,
@@ -836,15 +853,9 @@ mlxsw_sp_span_inspected_port_add(struct mlxsw_sp_port *port,
/* if it is an egress SPAN, bind a shared buffer to it */
if (type == MLXSW_SP_SPAN_EGRESS) {
- u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp,
- port->dev->mtu);
-
- mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize);
- err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
- if (err) {
- netdev_err(port->dev, "Could not create shared buffer for mirroring\n");
+ err = mlxsw_sp_span_port_buffsize_update(port, port->dev->mtu);
+ if (err)
return err;
- }
}
if (bind) {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
index 5e04252..5972433 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
@@ -74,5 +74,6 @@ void mlxsw_sp_span_entry_invalidate(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_span_entry *span_entry);
int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu);
+void mlxsw_sp_span_speed_update_work(struct work_struct *work);
#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index e0d7c49..60205aa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -9,6 +9,20 @@
#include "reg.h"
#include "spectrum.h"
+/* All driver-specific traps must be documented in
+ * Documentation/networking/devlink/mlxsw.rst
+ */
+enum {
+ DEVLINK_MLXSW_TRAP_ID_BASE = DEVLINK_TRAP_GENERIC_ID_MAX,
+ DEVLINK_MLXSW_TRAP_ID_IRIF_DISABLED,
+ DEVLINK_MLXSW_TRAP_ID_ERIF_DISABLED,
+};
+
+#define DEVLINK_MLXSW_TRAP_NAME_IRIF_DISABLED \
+ "irif_disabled"
+#define DEVLINK_MLXSW_TRAP_NAME_ERIF_DISABLED \
+ "erif_disabled"
+
#define MLXSW_SP_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT
static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port,
@@ -21,6 +35,12 @@ static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port,
DEVLINK_TRAP_GROUP_GENERIC(_group_id), \
MLXSW_SP_TRAP_METADATA)
+#define MLXSW_SP_TRAP_DRIVER_DROP(_id, _group_id) \
+ DEVLINK_TRAP_DRIVER(DROP, DROP, DEVLINK_MLXSW_TRAP_ID_##_id, \
+ DEVLINK_MLXSW_TRAP_NAME_##_id, \
+ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \
+ MLXSW_SP_TRAP_METADATA)
+
#define MLXSW_SP_TRAP_EXCEPTION(_id, _group_id) \
DEVLINK_TRAP_GENERIC(EXCEPTION, TRAP, _id, \
DEVLINK_TRAP_GROUP_GENERIC(_group_id), \
@@ -58,6 +78,11 @@ static struct devlink_trap mlxsw_sp_traps_arr[] = {
MLXSW_SP_TRAP_EXCEPTION(UNRESOLVED_NEIGH, L3_DROPS),
MLXSW_SP_TRAP_EXCEPTION(IPV4_LPM_UNICAST_MISS, L3_DROPS),
MLXSW_SP_TRAP_EXCEPTION(IPV6_LPM_UNICAST_MISS, L3_DROPS),
+ MLXSW_SP_TRAP_DRIVER_DROP(IRIF_DISABLED, L3_DROPS),
+ MLXSW_SP_TRAP_DRIVER_DROP(ERIF_DISABLED, L3_DROPS),
+ MLXSW_SP_TRAP_DROP(NON_ROUTABLE, L3_DROPS),
+ MLXSW_SP_TRAP_EXCEPTION(DECAP_ERROR, TUNNEL_DROPS),
+ MLXSW_SP_TRAP_DROP(OVERLAY_SMAC_MC, TUNNEL_DROPS),
};
static struct mlxsw_listener mlxsw_sp_listeners_arr[] = {
@@ -90,6 +115,15 @@ static struct mlxsw_listener mlxsw_sp_listeners_arr[] = {
TRAP_EXCEPTION_TO_CPU),
MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM6, ROUTER_EXP,
TRAP_EXCEPTION_TO_CPU),
+ MLXSW_SP_RXL_DISCARD(ROUTER_IRIF_EN, L3_DISCARDS),
+ MLXSW_SP_RXL_DISCARD(ROUTER_ERIF_EN, L3_DISCARDS),
+ MLXSW_SP_RXL_DISCARD(NON_ROUTABLE, L3_DISCARDS),
+ MLXSW_SP_RXL_EXCEPTION(DECAP_ECN0, ROUTER_EXP, TRAP_EXCEPTION_TO_CPU),
+ MLXSW_SP_RXL_EXCEPTION(IPIP_DECAP_ERROR, ROUTER_EXP,
+ TRAP_EXCEPTION_TO_CPU),
+ MLXSW_SP_RXL_EXCEPTION(DISCARD_DEC_PKT, TUNNEL_DISCARDS,
+ TRAP_EXCEPTION_TO_CPU),
+ MLXSW_SP_RXL_DISCARD(OVERLAY_SMAC_MC, TUNNEL_DISCARDS),
};
/* Mapping between hardware trap and devlink trap. Multiple hardware traps can
@@ -123,6 +157,13 @@ static u16 mlxsw_sp_listener_devlink_map[] = {
DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH,
DEVLINK_TRAP_GENERIC_ID_IPV4_LPM_UNICAST_MISS,
DEVLINK_TRAP_GENERIC_ID_IPV6_LPM_UNICAST_MISS,
+ DEVLINK_MLXSW_TRAP_ID_IRIF_DISABLED,
+ DEVLINK_MLXSW_TRAP_ID_ERIF_DISABLED,
+ DEVLINK_TRAP_GENERIC_ID_NON_ROUTABLE,
+ DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR,
+ DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR,
+ DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR,
+ DEVLINK_TRAP_GENERIC_ID_OVERLAY_SMAC_MC,
};
static int mlxsw_sp_rx_listener(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
@@ -304,8 +345,9 @@ mlxsw_sp_trap_group_policer_init(struct mlxsw_sp *mlxsw_sp,
u32 rate;
switch (group->id) {
- case DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS:/* fall through */
- case DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS:
+ case DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS: /* fall through */
+ case DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS: /* fall through */
+ case DEVLINK_TRAP_GROUP_GENERIC_ID_TUNNEL_DROPS:
policer_id = MLXSW_SP_DISCARD_POLICER_ID;
ir_units = MLXSW_REG_QPCR_IR_UNITS_M;
is_bytes = false;
@@ -342,6 +384,12 @@ __mlxsw_sp_trap_group_init(struct mlxsw_sp *mlxsw_sp,
priority = 0;
tc = 1;
break;
+ case DEVLINK_TRAP_GROUP_GENERIC_ID_TUNNEL_DROPS:
+ group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS;
+ policer_id = MLXSW_SP_DISCARD_POLICER_ID;
+ priority = 0;
+ tc = 1;
+ break;
default:
return -EINVAL;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index de6cb22..f0e98ec 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -299,22 +299,17 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
u64 len;
int err;
+ if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
+ this_cpu_inc(mlxsw_sx_port->pcpu_stats->tx_dropped);
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
+
memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb));
if (mlxsw_core_skb_transmit_busy(mlxsw_sx->core, &tx_info))
return NETDEV_TX_BUSY;
- if (unlikely(skb_headroom(skb) < MLXSW_TXHDR_LEN)) {
- struct sk_buff *skb_orig = skb;
-
- skb = skb_realloc_headroom(skb, MLXSW_TXHDR_LEN);
- if (!skb) {
- this_cpu_inc(mlxsw_sx_port->pcpu_stats->tx_dropped);
- dev_kfree_skb_any(skb_orig);
- return NETDEV_TX_OK;
- }
- dev_consume_skb_any(skb_orig);
- }
mlxsw_sx_txhdr_construct(skb, &tx_info);
/* TX header is consumed by HW on the way so we shouldn't count its
* bytes as being sent.
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 0c1c142..12e1fa9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -67,6 +67,7 @@ enum {
MLXSW_TRAP_ID_NVE_ENCAP_ARP = 0xBD,
MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6,
MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7,
+ MLXSW_TRAP_ID_DISCARD_NON_ROUTABLE = 0x11A,
MLXSW_TRAP_ID_DISCARD_ROUTER2 = 0x130,
MLXSW_TRAP_ID_DISCARD_ROUTER3 = 0x131,
MLXSW_TRAP_ID_DISCARD_ING_PACKET_SMAC_MC = 0x140,
@@ -80,12 +81,20 @@ enum {
MLXSW_TRAP_ID_DISCARD_ING_ROUTER_UC_DIP_MC_DMAC = 0x161,
MLXSW_TRAP_ID_DISCARD_ING_ROUTER_DIP_LB = 0x162,
MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_MC = 0x163,
+ MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_CLASS_E = 0x164,
MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_LB = 0x165,
MLXSW_TRAP_ID_DISCARD_ING_ROUTER_CORRUPTED_IP_HDR = 0x167,
+ MLXSW_TRAP_ID_DISCARD_ING_ROUTER_MC_DMAC = 0x168,
+ MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_DIP = 0x169,
MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_SIP_BC = 0x16A,
MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_DIP_LOCAL_NET = 0x16B,
+ MLXSW_TRAP_ID_DISCARD_ING_ROUTER_DIP_LINK_LOCAL = 0x16C,
+ MLXSW_TRAP_ID_DISCARD_ROUTER_IRIF_EN = 0x178,
+ MLXSW_TRAP_ID_DISCARD_ROUTER_ERIF_EN = 0x179,
MLXSW_TRAP_ID_DISCARD_ROUTER_LPM4 = 0x17B,
MLXSW_TRAP_ID_DISCARD_ROUTER_LPM6 = 0x17C,
+ MLXSW_TRAP_ID_DISCARD_DEC_PKT = 0x188,
+ MLXSW_TRAP_ID_DISCARD_OVERLAY_SMAC_MC = 0x190,
MLXSW_TRAP_ID_DISCARD_IPV6_MC_DIP_RESERVED_SCOPE = 0x1B0,
MLXSW_TRAP_ID_DISCARD_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE = 0x1B1,
MLXSW_TRAP_ID_ACL0 = 0x1C0,
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 985b46d..86d543a 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -500,13 +500,14 @@ EXPORT_SYMBOL(ocelot_port_enable);
static int ocelot_port_open(struct net_device *dev)
{
struct ocelot_port_private *priv = netdev_priv(dev);
- struct ocelot *ocelot = priv->port.ocelot;
+ struct ocelot_port *ocelot_port = &priv->port;
+ struct ocelot *ocelot = ocelot_port->ocelot;
int port = priv->chip_port;
int err;
if (priv->serdes) {
err = phy_set_mode_ext(priv->serdes, PHY_MODE_ETHERNET,
- priv->phy_mode);
+ ocelot_port->phy_mode);
if (err) {
netdev_err(dev, "Could not set mode of SerDes\n");
return err;
@@ -514,7 +515,7 @@ static int ocelot_port_open(struct net_device *dev)
}
err = phy_connect_direct(dev, priv->phy, &ocelot_port_adjust_link,
- priv->phy_mode);
+ ocelot_port->phy_mode);
if (err) {
netdev_err(dev, "Could not attach to PHY\n");
return err;
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index c259114..04372ba 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -18,11 +18,11 @@
#include <linux/ptp_clock_kernel.h>
#include <linux/regmap.h>
+#include <soc/mscc/ocelot_qsys.h>
#include <soc/mscc/ocelot_sys.h>
+#include <soc/mscc/ocelot_dev.h>
+#include <soc/mscc/ocelot_ana.h>
#include <soc/mscc/ocelot.h>
-#include "ocelot_ana.h"
-#include "ocelot_dev.h"
-#include "ocelot_qsys.h"
#include "ocelot_rew.h"
#include "ocelot_qs.h"
#include "ocelot_tc.h"
@@ -68,7 +68,6 @@ struct ocelot_port_private {
u8 vlan_aware;
- phy_interface_t phy_mode;
struct phy *serdes;
struct ocelot_port_tc tc;
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index 2da8eee..b388208 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -402,9 +402,9 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
of_get_phy_mode(portnp, &phy_mode);
- priv->phy_mode = phy_mode;
+ ocelot_port->phy_mode = phy_mode;
- switch (priv->phy_mode) {
+ switch (ocelot_port->phy_mode) {
case PHY_INTERFACE_MODE_NA:
continue;
case PHY_INTERFACE_MODE_SGMII:
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index c979f38..2ee0d0b 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -2892,7 +2892,7 @@ static netdev_tx_t myri10ge_xmit(struct sk_buff *skb,
static netdev_tx_t myri10ge_sw_tso(struct sk_buff *skb,
struct net_device *dev)
{
- struct sk_buff *segs, *curr;
+ struct sk_buff *segs, *curr, *next;
struct myri10ge_priv *mgp = netdev_priv(dev);
struct myri10ge_slice_state *ss;
netdev_tx_t status;
@@ -2901,10 +2901,8 @@ static netdev_tx_t myri10ge_sw_tso(struct sk_buff *skb,
if (IS_ERR(segs))
goto drop;
- while (segs) {
- curr = segs;
- segs = segs->next;
- curr->next = NULL;
+ skb_list_walk_safe(segs, curr, next) {
+ skb_mark_not_on_list(curr);
status = myri10ge_xmit(curr, dev);
if (status != 0) {
dev_kfree_skb_any(curr);
diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index fdebc85..31be3ba 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -64,6 +64,8 @@ static int sonic_open(struct net_device *dev)
netif_dbg(lp, ifup, dev, "%s: initializing sonic driver\n", __func__);
+ spin_lock_init(&lp->lock);
+
for (i = 0; i < SONIC_NUM_RRS; i++) {
struct sk_buff *skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
if (skb == NULL) {
@@ -114,6 +116,24 @@ static int sonic_open(struct net_device *dev)
return 0;
}
+/* Wait for the SONIC to become idle. */
+static void sonic_quiesce(struct net_device *dev, u16 mask)
+{
+ struct sonic_local * __maybe_unused lp = netdev_priv(dev);
+ int i;
+ u16 bits;
+
+ for (i = 0; i < 1000; ++i) {
+ bits = SONIC_READ(SONIC_CMD) & mask;
+ if (!bits)
+ return;
+ if (irqs_disabled() || in_interrupt())
+ udelay(20);
+ else
+ usleep_range(100, 200);
+ }
+ WARN_ONCE(1, "command deadline expired! 0x%04x\n", bits);
+}
/*
* Close the SONIC device
@@ -130,6 +150,9 @@ static int sonic_close(struct net_device *dev)
/*
* stop the SONIC, disable interrupts
*/
+ SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
+ sonic_quiesce(dev, SONIC_CR_ALL);
+
SONIC_WRITE(SONIC_IMR, 0);
SONIC_WRITE(SONIC_ISR, 0x7fff);
SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
@@ -169,6 +192,9 @@ static void sonic_tx_timeout(struct net_device *dev, unsigned int txqueue)
* put the Sonic into software-reset mode and
* disable all interrupts before releasing DMA buffers
*/
+ SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
+ sonic_quiesce(dev, SONIC_CR_ALL);
+
SONIC_WRITE(SONIC_IMR, 0);
SONIC_WRITE(SONIC_ISR, 0x7fff);
SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
@@ -206,8 +232,6 @@ static void sonic_tx_timeout(struct net_device *dev, unsigned int txqueue)
* wake the tx queue
* Concurrently with all of this, the SONIC is potentially writing to
* the status flags of the TDs.
- * Until some mutual exclusion is added, this code will not work with SMP. However,
- * MIPS Jazz machines and m68k Macs were all uni-processor machines.
*/
static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
@@ -215,7 +239,8 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
struct sonic_local *lp = netdev_priv(dev);
dma_addr_t laddr;
int length;
- int entry = lp->next_tx;
+ int entry;
+ unsigned long flags;
netif_dbg(lp, tx_queued, dev, "%s: skb=%p\n", __func__, skb);
@@ -237,6 +262,10 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
+ spin_lock_irqsave(&lp->lock, flags);
+
+ entry = lp->next_tx;
+
sonic_tda_put(dev, entry, SONIC_TD_STATUS, 0); /* clear status */
sonic_tda_put(dev, entry, SONIC_TD_FRAG_COUNT, 1); /* single fragment */
sonic_tda_put(dev, entry, SONIC_TD_PKTSIZE, length); /* length of packet */
@@ -246,10 +275,6 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
sonic_tda_put(dev, entry, SONIC_TD_LINK,
sonic_tda_get(dev, entry, SONIC_TD_LINK) | SONIC_EOL);
- /*
- * Must set tx_skb[entry] only after clearing status, and
- * before clearing EOL and before stopping queue
- */
wmb();
lp->tx_len[entry] = length;
lp->tx_laddr[entry] = laddr;
@@ -272,6 +297,8 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP);
+ spin_unlock_irqrestore(&lp->lock, flags);
+
return NETDEV_TX_OK;
}
@@ -284,15 +311,28 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
struct net_device *dev = dev_id;
struct sonic_local *lp = netdev_priv(dev);
int status;
+ unsigned long flags;
- if (!(status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT))
+ /* The lock has two purposes. Firstly, it synchronizes sonic_interrupt()
+ * with sonic_send_packet() so that the two functions can share state.
+ * Secondly, it makes sonic_interrupt() re-entrant, as that is required
+ * by macsonic which must use two IRQs with different priority levels.
+ */
+ spin_lock_irqsave(&lp->lock, flags);
+
+ status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT;
+ if (!status) {
+ spin_unlock_irqrestore(&lp->lock, flags);
+
return IRQ_NONE;
+ }
do {
+ SONIC_WRITE(SONIC_ISR, status); /* clear the interrupt(s) */
+
if (status & SONIC_INT_PKTRX) {
netif_dbg(lp, intr, dev, "%s: packet rx\n", __func__);
sonic_rx(dev); /* got packet(s) */
- SONIC_WRITE(SONIC_ISR, SONIC_INT_PKTRX); /* clear the interrupt */
}
if (status & SONIC_INT_TXDN) {
@@ -300,11 +340,12 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
int td_status;
int freed_some = 0;
- /* At this point, cur_tx is the index of a TD that is one of:
- * unallocated/freed (status set & tx_skb[entry] clear)
- * allocated and sent (status set & tx_skb[entry] set )
- * allocated and not yet sent (status clear & tx_skb[entry] set )
- * still being allocated by sonic_send_packet (status clear & tx_skb[entry] clear)
+ /* The state of a Transmit Descriptor may be inferred
+ * from { tx_skb[entry], td_status } as follows.
+ * { clear, clear } => the TD has never been used
+ * { set, clear } => the TD was handed to SONIC
+ * { set, set } => the TD was handed back
+ * { clear, set } => the TD is available for re-use
*/
netif_dbg(lp, intr, dev, "%s: tx done\n", __func__);
@@ -313,18 +354,19 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
if ((td_status = sonic_tda_get(dev, entry, SONIC_TD_STATUS)) == 0)
break;
- if (td_status & 0x0001) {
+ if (td_status & SONIC_TCR_PTX) {
lp->stats.tx_packets++;
lp->stats.tx_bytes += sonic_tda_get(dev, entry, SONIC_TD_PKTSIZE);
} else {
- lp->stats.tx_errors++;
- if (td_status & 0x0642)
+ if (td_status & (SONIC_TCR_EXD |
+ SONIC_TCR_EXC | SONIC_TCR_BCM))
lp->stats.tx_aborted_errors++;
- if (td_status & 0x0180)
+ if (td_status &
+ (SONIC_TCR_NCRS | SONIC_TCR_CRLS))
lp->stats.tx_carrier_errors++;
- if (td_status & 0x0020)
+ if (td_status & SONIC_TCR_OWC)
lp->stats.tx_window_errors++;
- if (td_status & 0x0004)
+ if (td_status & SONIC_TCR_FU)
lp->stats.tx_fifo_errors++;
}
@@ -346,7 +388,6 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
if (freed_some || lp->tx_skb[entry] == NULL)
netif_wake_queue(dev); /* The ring is no longer full */
lp->cur_tx = entry;
- SONIC_WRITE(SONIC_ISR, SONIC_INT_TXDN); /* clear the interrupt */
}
/*
@@ -355,42 +396,37 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
if (status & SONIC_INT_RFO) {
netif_dbg(lp, rx_err, dev, "%s: rx fifo overrun\n",
__func__);
- lp->stats.rx_fifo_errors++;
- SONIC_WRITE(SONIC_ISR, SONIC_INT_RFO); /* clear the interrupt */
}
if (status & SONIC_INT_RDE) {
netif_dbg(lp, rx_err, dev, "%s: rx descriptors exhausted\n",
__func__);
- lp->stats.rx_dropped++;
- SONIC_WRITE(SONIC_ISR, SONIC_INT_RDE); /* clear the interrupt */
}
if (status & SONIC_INT_RBAE) {
netif_dbg(lp, rx_err, dev, "%s: rx buffer area exceeded\n",
__func__);
- lp->stats.rx_dropped++;
- SONIC_WRITE(SONIC_ISR, SONIC_INT_RBAE); /* clear the interrupt */
}
/* counter overruns; all counters are 16bit wide */
- if (status & SONIC_INT_FAE) {
+ if (status & SONIC_INT_FAE)
lp->stats.rx_frame_errors += 65536;
- SONIC_WRITE(SONIC_ISR, SONIC_INT_FAE); /* clear the interrupt */
- }
- if (status & SONIC_INT_CRC) {
+ if (status & SONIC_INT_CRC)
lp->stats.rx_crc_errors += 65536;
- SONIC_WRITE(SONIC_ISR, SONIC_INT_CRC); /* clear the interrupt */
- }
- if (status & SONIC_INT_MP) {
+ if (status & SONIC_INT_MP)
lp->stats.rx_missed_errors += 65536;
- SONIC_WRITE(SONIC_ISR, SONIC_INT_MP); /* clear the interrupt */
- }
/* transmit error */
if (status & SONIC_INT_TXER) {
- if (SONIC_READ(SONIC_TCR) & SONIC_TCR_FU)
- netif_dbg(lp, tx_err, dev, "%s: tx fifo underrun\n",
- __func__);
- SONIC_WRITE(SONIC_ISR, SONIC_INT_TXER); /* clear the interrupt */
+ u16 tcr = SONIC_READ(SONIC_TCR);
+
+ netif_dbg(lp, tx_err, dev, "%s: TXER intr, TCR %04x\n",
+ __func__, tcr);
+
+ if (tcr & (SONIC_TCR_EXD | SONIC_TCR_EXC |
+ SONIC_TCR_FU | SONIC_TCR_BCM)) {
+ /* Aborted transmission. Try again. */
+ netif_stop_queue(dev);
+ SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP);
+ }
}
/* bus retry */
@@ -400,107 +436,164 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
/* ... to help debug DMA problems causing endless interrupts. */
/* Bounce the eth interface to turn on the interrupt again. */
SONIC_WRITE(SONIC_IMR, 0);
- SONIC_WRITE(SONIC_ISR, SONIC_INT_BR); /* clear the interrupt */
}
- /* load CAM done */
- if (status & SONIC_INT_LCD)
- SONIC_WRITE(SONIC_ISR, SONIC_INT_LCD); /* clear the interrupt */
- } while((status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT));
+ status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT;
+ } while (status);
+
+ spin_unlock_irqrestore(&lp->lock, flags);
+
return IRQ_HANDLED;
}
+/* Return the array index corresponding to a given Receive Buffer pointer. */
+static int index_from_addr(struct sonic_local *lp, dma_addr_t addr,
+ unsigned int last)
+{
+ unsigned int i = last;
+
+ do {
+ i = (i + 1) & SONIC_RRS_MASK;
+ if (addr == lp->rx_laddr[i])
+ return i;
+ } while (i != last);
+
+ return -ENOENT;
+}
+
+/* Allocate and map a new skb to be used as a receive buffer. */
+static bool sonic_alloc_rb(struct net_device *dev, struct sonic_local *lp,
+ struct sk_buff **new_skb, dma_addr_t *new_addr)
+{
+ *new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
+ if (!*new_skb)
+ return false;
+
+ if (SONIC_BUS_SCALE(lp->dma_bitmode) == 2)
+ skb_reserve(*new_skb, 2);
+
+ *new_addr = dma_map_single(lp->device, skb_put(*new_skb, SONIC_RBSIZE),
+ SONIC_RBSIZE, DMA_FROM_DEVICE);
+ if (!*new_addr) {
+ dev_kfree_skb(*new_skb);
+ *new_skb = NULL;
+ return false;
+ }
+
+ return true;
+}
+
+/* Place a new receive resource in the Receive Resource Area and update RWP. */
+static void sonic_update_rra(struct net_device *dev, struct sonic_local *lp,
+ dma_addr_t old_addr, dma_addr_t new_addr)
+{
+ unsigned int entry = sonic_rr_entry(dev, SONIC_READ(SONIC_RWP));
+ unsigned int end = sonic_rr_entry(dev, SONIC_READ(SONIC_RRP));
+ u32 buf;
+
+ /* The resources in the range [RRP, RWP) belong to the SONIC. This loop
+ * scans the other resources in the RRA, those in the range [RWP, RRP).
+ */
+ do {
+ buf = (sonic_rra_get(dev, entry, SONIC_RR_BUFADR_H) << 16) |
+ sonic_rra_get(dev, entry, SONIC_RR_BUFADR_L);
+
+ if (buf == old_addr)
+ break;
+
+ entry = (entry + 1) & SONIC_RRS_MASK;
+ } while (entry != end);
+
+ WARN_ONCE(buf != old_addr, "failed to find resource!\n");
+
+ sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, new_addr >> 16);
+ sonic_rra_put(dev, entry, SONIC_RR_BUFADR_L, new_addr & 0xffff);
+
+ entry = (entry + 1) & SONIC_RRS_MASK;
+
+ SONIC_WRITE(SONIC_RWP, sonic_rr_addr(dev, entry));
+}
+
/*
* We have a good packet(s), pass it/them up the network stack.
*/
static void sonic_rx(struct net_device *dev)
{
struct sonic_local *lp = netdev_priv(dev);
- int status;
int entry = lp->cur_rx;
+ int prev_entry = lp->eol_rx;
+ bool rbe = false;
while (sonic_rda_get(dev, entry, SONIC_RD_IN_USE) == 0) {
- struct sk_buff *used_skb;
- struct sk_buff *new_skb;
- dma_addr_t new_laddr;
- u16 bufadr_l;
- u16 bufadr_h;
- int pkt_len;
+ u16 status = sonic_rda_get(dev, entry, SONIC_RD_STATUS);
- status = sonic_rda_get(dev, entry, SONIC_RD_STATUS);
- if (status & SONIC_RCR_PRX) {
- /* Malloc up new buffer. */
- new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
- if (new_skb == NULL) {
- lp->stats.rx_dropped++;
- break;
- }
- /* provide 16 byte IP header alignment unless DMA requires otherwise */
- if(SONIC_BUS_SCALE(lp->dma_bitmode) == 2)
- skb_reserve(new_skb, 2);
+ /* If the RD has LPKT set, the chip has finished with the RB */
+ if ((status & SONIC_RCR_PRX) && (status & SONIC_RCR_LPKT)) {
+ struct sk_buff *new_skb;
+ dma_addr_t new_laddr;
+ u32 addr = (sonic_rda_get(dev, entry,
+ SONIC_RD_PKTPTR_H) << 16) |
+ sonic_rda_get(dev, entry, SONIC_RD_PKTPTR_L);
+ int i = index_from_addr(lp, addr, entry);
- new_laddr = dma_map_single(lp->device, skb_put(new_skb, SONIC_RBSIZE),
- SONIC_RBSIZE, DMA_FROM_DEVICE);
- if (!new_laddr) {
- dev_kfree_skb(new_skb);
- printk(KERN_ERR "%s: Failed to map rx buffer, dropping packet.\n", dev->name);
- lp->stats.rx_dropped++;
+ if (i < 0) {
+ WARN_ONCE(1, "failed to find buffer!\n");
break;
}
- /* now we have a new skb to replace it, pass the used one up the stack */
- dma_unmap_single(lp->device, lp->rx_laddr[entry], SONIC_RBSIZE, DMA_FROM_DEVICE);
- used_skb = lp->rx_skb[entry];
- pkt_len = sonic_rda_get(dev, entry, SONIC_RD_PKTLEN);
- skb_trim(used_skb, pkt_len);
- used_skb->protocol = eth_type_trans(used_skb, dev);
- netif_rx(used_skb);
- lp->stats.rx_packets++;
- lp->stats.rx_bytes += pkt_len;
+ if (sonic_alloc_rb(dev, lp, &new_skb, &new_laddr)) {
+ struct sk_buff *used_skb = lp->rx_skb[i];
+ int pkt_len;
- /* and insert the new skb */
- lp->rx_laddr[entry] = new_laddr;
- lp->rx_skb[entry] = new_skb;
+ /* Pass the used buffer up the stack */
+ dma_unmap_single(lp->device, addr, SONIC_RBSIZE,
+ DMA_FROM_DEVICE);
- bufadr_l = (unsigned long)new_laddr & 0xffff;
- bufadr_h = (unsigned long)new_laddr >> 16;
- sonic_rra_put(dev, entry, SONIC_RR_BUFADR_L, bufadr_l);
- sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, bufadr_h);
- } else {
- /* This should only happen, if we enable accepting broken packets. */
- lp->stats.rx_errors++;
- if (status & SONIC_RCR_FAER)
- lp->stats.rx_frame_errors++;
- if (status & SONIC_RCR_CRCR)
- lp->stats.rx_crc_errors++;
- }
- if (status & SONIC_RCR_LPKT) {
- /*
- * this was the last packet out of the current receive buffer
- * give the buffer back to the SONIC
+ pkt_len = sonic_rda_get(dev, entry,
+ SONIC_RD_PKTLEN);
+ skb_trim(used_skb, pkt_len);
+ used_skb->protocol = eth_type_trans(used_skb,
+ dev);
+ netif_rx(used_skb);
+ lp->stats.rx_packets++;
+ lp->stats.rx_bytes += pkt_len;
+
+ lp->rx_skb[i] = new_skb;
+ lp->rx_laddr[i] = new_laddr;
+ } else {
+ /* Failed to obtain a new buffer so re-use it */
+ new_laddr = addr;
+ lp->stats.rx_dropped++;
+ }
+ /* If RBE is already asserted when RWP advances then
+ * it's safe to clear RBE after processing this packet.
*/
- lp->cur_rwp += SIZEOF_SONIC_RR * SONIC_BUS_SCALE(lp->dma_bitmode);
- if (lp->cur_rwp >= lp->rra_end) lp->cur_rwp = lp->rra_laddr & 0xffff;
- SONIC_WRITE(SONIC_RWP, lp->cur_rwp);
- if (SONIC_READ(SONIC_ISR) & SONIC_INT_RBE) {
- netif_dbg(lp, rx_err, dev, "%s: rx buffer exhausted\n",
- __func__);
- SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* clear the flag */
- }
- } else
- printk(KERN_ERR "%s: rx desc without RCR_LPKT. Shouldn't happen !?\n",
- dev->name);
+ rbe = rbe || SONIC_READ(SONIC_ISR) & SONIC_INT_RBE;
+ sonic_update_rra(dev, lp, addr, new_laddr);
+ }
/*
* give back the descriptor
*/
- sonic_rda_put(dev, entry, SONIC_RD_LINK,
- sonic_rda_get(dev, entry, SONIC_RD_LINK) | SONIC_EOL);
+ sonic_rda_put(dev, entry, SONIC_RD_STATUS, 0);
sonic_rda_put(dev, entry, SONIC_RD_IN_USE, 1);
- sonic_rda_put(dev, lp->eol_rx, SONIC_RD_LINK,
- sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK) & ~SONIC_EOL);
- lp->eol_rx = entry;
- lp->cur_rx = entry = (entry + 1) & SONIC_RDS_MASK;
+
+ prev_entry = entry;
+ entry = (entry + 1) & SONIC_RDS_MASK;
}
+
+ lp->cur_rx = entry;
+
+ if (prev_entry != lp->eol_rx) {
+ /* Advance the EOL flag to put descriptors back into service */
+ sonic_rda_put(dev, prev_entry, SONIC_RD_LINK, SONIC_EOL |
+ sonic_rda_get(dev, prev_entry, SONIC_RD_LINK));
+ sonic_rda_put(dev, lp->eol_rx, SONIC_RD_LINK, ~SONIC_EOL &
+ sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK));
+ lp->eol_rx = prev_entry;
+ }
+
+ if (rbe)
+ SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE);
/*
* If any worth-while packets have been received, netif_rx()
* has done a mark_bh(NET_BH) for us and will work on them
@@ -550,6 +643,8 @@ static void sonic_multicast_list(struct net_device *dev)
(netdev_mc_count(dev) > 15)) {
rcr |= SONIC_RCR_AMC;
} else {
+ unsigned long flags;
+
netif_dbg(lp, ifup, dev, "%s: mc_count %d\n", __func__,
netdev_mc_count(dev));
sonic_set_cam_enable(dev, 1); /* always enable our own address */
@@ -563,9 +658,14 @@ static void sonic_multicast_list(struct net_device *dev)
i++;
}
SONIC_WRITE(SONIC_CDC, 16);
- /* issue Load CAM command */
SONIC_WRITE(SONIC_CDP, lp->cda_laddr & 0xffff);
+
+ /* LCAM and TXP commands can't be used simultaneously */
+ spin_lock_irqsave(&lp->lock, flags);
+ sonic_quiesce(dev, SONIC_CR_TXP);
SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM);
+ sonic_quiesce(dev, SONIC_CR_LCAM);
+ spin_unlock_irqrestore(&lp->lock, flags);
}
}
@@ -580,7 +680,6 @@ static void sonic_multicast_list(struct net_device *dev)
*/
static int sonic_init(struct net_device *dev)
{
- unsigned int cmd;
struct sonic_local *lp = netdev_priv(dev);
int i;
@@ -592,12 +691,16 @@ static int sonic_init(struct net_device *dev)
SONIC_WRITE(SONIC_ISR, 0x7fff);
SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
+ /* While in reset mode, clear CAM Enable register */
+ SONIC_WRITE(SONIC_CE, 0);
+
/*
* clear software reset flag, disable receiver, clear and
* enable interrupts, then completely initialize the SONIC
*/
SONIC_WRITE(SONIC_CMD, 0);
- SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
+ SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS | SONIC_CR_STP);
+ sonic_quiesce(dev, SONIC_CR_ALL);
/*
* initialize the receive resource area
@@ -615,15 +718,10 @@ static int sonic_init(struct net_device *dev)
}
/* initialize all RRA registers */
- lp->rra_end = (lp->rra_laddr + SONIC_NUM_RRS * SIZEOF_SONIC_RR *
- SONIC_BUS_SCALE(lp->dma_bitmode)) & 0xffff;
- lp->cur_rwp = (lp->rra_laddr + (SONIC_NUM_RRS - 1) * SIZEOF_SONIC_RR *
- SONIC_BUS_SCALE(lp->dma_bitmode)) & 0xffff;
-
- SONIC_WRITE(SONIC_RSA, lp->rra_laddr & 0xffff);
- SONIC_WRITE(SONIC_REA, lp->rra_end);
- SONIC_WRITE(SONIC_RRP, lp->rra_laddr & 0xffff);
- SONIC_WRITE(SONIC_RWP, lp->cur_rwp);
+ SONIC_WRITE(SONIC_RSA, sonic_rr_addr(dev, 0));
+ SONIC_WRITE(SONIC_REA, sonic_rr_addr(dev, SONIC_NUM_RRS));
+ SONIC_WRITE(SONIC_RRP, sonic_rr_addr(dev, 0));
+ SONIC_WRITE(SONIC_RWP, sonic_rr_addr(dev, SONIC_NUM_RRS - 1));
SONIC_WRITE(SONIC_URRA, lp->rra_laddr >> 16);
SONIC_WRITE(SONIC_EOBC, (SONIC_RBSIZE >> 1) - (lp->dma_bitmode ? 2 : 1));
@@ -631,14 +729,7 @@ static int sonic_init(struct net_device *dev)
netif_dbg(lp, ifup, dev, "%s: issuing RRRA command\n", __func__);
SONIC_WRITE(SONIC_CMD, SONIC_CR_RRRA);
- i = 0;
- while (i++ < 100) {
- if (SONIC_READ(SONIC_CMD) & SONIC_CR_RRRA)
- break;
- }
-
- netif_dbg(lp, ifup, dev, "%s: status=%x, i=%d\n", __func__,
- SONIC_READ(SONIC_CMD), i);
+ sonic_quiesce(dev, SONIC_CR_RRRA);
/*
* Initialize the receive descriptors so that they
@@ -713,28 +804,17 @@ static int sonic_init(struct net_device *dev)
* load the CAM
*/
SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM);
-
- i = 0;
- while (i++ < 100) {
- if (SONIC_READ(SONIC_ISR) & SONIC_INT_LCD)
- break;
- }
- netif_dbg(lp, ifup, dev, "%s: CMD=%x, ISR=%x, i=%d\n", __func__,
- SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i);
+ sonic_quiesce(dev, SONIC_CR_LCAM);
/*
* enable receiver, disable loopback
* and enable all interrupts
*/
- SONIC_WRITE(SONIC_CMD, SONIC_CR_RXEN | SONIC_CR_STP);
SONIC_WRITE(SONIC_RCR, SONIC_RCR_DEFAULT);
SONIC_WRITE(SONIC_TCR, SONIC_TCR_DEFAULT);
SONIC_WRITE(SONIC_ISR, 0x7fff);
SONIC_WRITE(SONIC_IMR, SONIC_IMR_DEFAULT);
-
- cmd = SONIC_READ(SONIC_CMD);
- if ((cmd & SONIC_CR_RXEN) == 0 || (cmd & SONIC_CR_STP) == 0)
- printk(KERN_ERR "sonic_init: failed, status=%x\n", cmd);
+ SONIC_WRITE(SONIC_CMD, SONIC_CR_RXEN);
netif_dbg(lp, ifup, dev, "%s: new status=%x\n", __func__,
SONIC_READ(SONIC_CMD));
diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h
index f1544481..e0e4cba 100644
--- a/drivers/net/ethernet/natsemi/sonic.h
+++ b/drivers/net/ethernet/natsemi/sonic.h
@@ -110,6 +110,9 @@
#define SONIC_CR_TXP 0x0002
#define SONIC_CR_HTX 0x0001
+#define SONIC_CR_ALL (SONIC_CR_LCAM | SONIC_CR_RRRA | \
+ SONIC_CR_RXEN | SONIC_CR_TXP)
+
/*
* SONIC data configuration bits
*/
@@ -175,6 +178,7 @@
#define SONIC_TCR_NCRS 0x0100
#define SONIC_TCR_CRLS 0x0080
#define SONIC_TCR_EXC 0x0040
+#define SONIC_TCR_OWC 0x0020
#define SONIC_TCR_PMB 0x0008
#define SONIC_TCR_FU 0x0004
#define SONIC_TCR_BCM 0x0002
@@ -274,8 +278,9 @@
#define SONIC_NUM_RDS SONIC_NUM_RRS /* number of receive descriptors */
#define SONIC_NUM_TDS 16 /* number of transmit descriptors */
-#define SONIC_RDS_MASK (SONIC_NUM_RDS-1)
-#define SONIC_TDS_MASK (SONIC_NUM_TDS-1)
+#define SONIC_RRS_MASK (SONIC_NUM_RRS - 1)
+#define SONIC_RDS_MASK (SONIC_NUM_RDS - 1)
+#define SONIC_TDS_MASK (SONIC_NUM_TDS - 1)
#define SONIC_RBSIZE 1520 /* size of one resource buffer */
@@ -312,8 +317,6 @@ struct sonic_local {
u32 rda_laddr; /* logical DMA address of RDA */
dma_addr_t rx_laddr[SONIC_NUM_RRS]; /* logical DMA addresses of rx skbuffs */
dma_addr_t tx_laddr[SONIC_NUM_TDS]; /* logical DMA addresses of tx skbuffs */
- unsigned int rra_end;
- unsigned int cur_rwp;
unsigned int cur_rx;
unsigned int cur_tx; /* first unacked transmit packet */
unsigned int eol_rx;
@@ -322,6 +325,7 @@ struct sonic_local {
int msg_enable;
struct device *device; /* generic device */
struct net_device_stats stats;
+ spinlock_t lock;
};
#define TX_TIMEOUT (3 * HZ)
@@ -344,30 +348,30 @@ static void sonic_msg_init(struct net_device *dev);
as far as we can tell. */
/* OpenBSD calls this "SWO". I'd like to think that sonic_buf_put()
is a much better name. */
-static inline void sonic_buf_put(void* base, int bitmode,
+static inline void sonic_buf_put(u16 *base, int bitmode,
int offset, __u16 val)
{
if (bitmode)
#ifdef __BIG_ENDIAN
- ((__u16 *) base + (offset*2))[1] = val;
+ __raw_writew(val, base + (offset * 2) + 1);
#else
- ((__u16 *) base + (offset*2))[0] = val;
+ __raw_writew(val, base + (offset * 2) + 0);
#endif
else
- ((__u16 *) base)[offset] = val;
+ __raw_writew(val, base + (offset * 1) + 0);
}
-static inline __u16 sonic_buf_get(void* base, int bitmode,
+static inline __u16 sonic_buf_get(u16 *base, int bitmode,
int offset)
{
if (bitmode)
#ifdef __BIG_ENDIAN
- return ((volatile __u16 *) base + (offset*2))[1];
+ return __raw_readw(base + (offset * 2) + 1);
#else
- return ((volatile __u16 *) base + (offset*2))[0];
+ return __raw_readw(base + (offset * 2) + 0);
#endif
else
- return ((volatile __u16 *) base)[offset];
+ return __raw_readw(base + (offset * 1) + 0);
}
/* Inlines that you should actually use for reading/writing DMA buffers */
@@ -447,6 +451,22 @@ static inline __u16 sonic_rra_get(struct net_device* dev, int entry,
(entry * SIZEOF_SONIC_RR) + offset);
}
+static inline u16 sonic_rr_addr(struct net_device *dev, int entry)
+{
+ struct sonic_local *lp = netdev_priv(dev);
+
+ return lp->rra_laddr +
+ entry * SIZEOF_SONIC_RR * SONIC_BUS_SCALE(lp->dma_bitmode);
+}
+
+static inline u16 sonic_rr_entry(struct net_device *dev, u16 addr)
+{
+ struct sonic_local *lp = netdev_priv(dev);
+
+ return (addr - (u16)lp->rra_laddr) / (SIZEOF_SONIC_RR *
+ SONIC_BUS_SCALE(lp->dma_bitmode));
+}
+
static const char version[] =
"sonic.c:v0.92 20.9.98 tsbogend@alpha.franken.de\n";
diff --git a/drivers/net/ethernet/netronome/Kconfig b/drivers/net/ethernet/netronome/Kconfig
index bac5be4..a3f68a7 100644
--- a/drivers/net/ethernet/netronome/Kconfig
+++ b/drivers/net/ethernet/netronome/Kconfig
@@ -31,6 +31,7 @@
bool "NFP4000/NFP6000 TC Flower offload support"
depends on NFP
depends on NET_SWITCHDEV
+ depends on IPV6!=m || NFP=m
default y
---help---
Enable driver support for TC Flower offload on NFP4000 and NFP6000.
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 6561692..d20cf03 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1149,19 +1149,6 @@ static void lpc_eth_set_multicast_list(struct net_device *ndev)
spin_unlock_irqrestore(&pldat->lock, flags);
}
-static int lpc_eth_ioctl(struct net_device *ndev, struct ifreq *req, int cmd)
-{
- struct phy_device *phydev = ndev->phydev;
-
- if (!netif_running(ndev))
- return -EINVAL;
-
- if (!phydev)
- return -ENODEV;
-
- return phy_mii_ioctl(phydev, req, cmd);
-}
-
static int lpc_eth_open(struct net_device *ndev)
{
struct netdata_local *pldat = netdev_priv(ndev);
@@ -1229,7 +1216,7 @@ static const struct net_device_ops lpc_netdev_ops = {
.ndo_stop = lpc_eth_close,
.ndo_start_xmit = lpc_eth_hard_start_xmit,
.ndo_set_rx_mode = lpc_eth_set_multicast_list,
- .ndo_do_ioctl = lpc_eth_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_set_mac_address = lpc_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
};
diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h
index 98e102a..bb106a3 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic.h
@@ -12,19 +12,27 @@ struct ionic_lif;
#define IONIC_DRV_NAME "ionic"
#define IONIC_DRV_DESCRIPTION "Pensando Ethernet NIC Driver"
-#define IONIC_DRV_VERSION "0.18.0-k"
+#define IONIC_DRV_VERSION "0.20.0-k"
#define PCI_VENDOR_ID_PENSANDO 0x1dd8
#define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF 0x1002
#define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF 0x1003
-#define IONIC_SUBDEV_ID_NAPLES_25 0x4000
-#define IONIC_SUBDEV_ID_NAPLES_100_4 0x4001
-#define IONIC_SUBDEV_ID_NAPLES_100_8 0x4002
-
#define DEVCMD_TIMEOUT 10
+struct ionic_vf {
+ u16 index;
+ u8 macaddr[6];
+ __le32 maxrate;
+ __le16 vlanid;
+ u8 spoofchk;
+ u8 trusted;
+ u8 linkstate;
+ dma_addr_t stats_pa;
+ struct ionic_lif_stats stats;
+};
+
struct ionic {
struct pci_dev *pdev;
struct device *dev;
@@ -46,6 +54,9 @@ struct ionic {
DECLARE_BITMAP(intrs, IONIC_INTR_CTRL_REGS_MAX);
struct work_struct nb_work;
struct notifier_block nb;
+ struct rw_semaphore vf_op_lock; /* lock for VF operations */
+ struct ionic_vf *vfs;
+ int num_vfs;
struct timer_list watchdog_timer;
int watchdog_period;
};
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index 9a9ab8c..448d7b2 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -104,10 +104,112 @@ void ionic_bus_unmap_dbpage(struct ionic *ionic, void __iomem *page)
iounmap(page);
}
+static void ionic_vf_dealloc_locked(struct ionic *ionic)
+{
+ struct ionic_vf *v;
+ dma_addr_t dma = 0;
+ int i;
+
+ if (!ionic->vfs)
+ return;
+
+ for (i = ionic->num_vfs - 1; i >= 0; i--) {
+ v = &ionic->vfs[i];
+
+ if (v->stats_pa) {
+ (void)ionic_set_vf_config(ionic, i,
+ IONIC_VF_ATTR_STATSADDR,
+ (u8 *)&dma);
+ dma_unmap_single(ionic->dev, v->stats_pa,
+ sizeof(v->stats), DMA_FROM_DEVICE);
+ v->stats_pa = 0;
+ }
+ }
+
+ kfree(ionic->vfs);
+ ionic->vfs = NULL;
+ ionic->num_vfs = 0;
+}
+
+static void ionic_vf_dealloc(struct ionic *ionic)
+{
+ down_write(&ionic->vf_op_lock);
+ ionic_vf_dealloc_locked(ionic);
+ up_write(&ionic->vf_op_lock);
+}
+
+static int ionic_vf_alloc(struct ionic *ionic, int num_vfs)
+{
+ struct ionic_vf *v;
+ int err = 0;
+ int i;
+
+ down_write(&ionic->vf_op_lock);
+
+ ionic->vfs = kcalloc(num_vfs, sizeof(struct ionic_vf), GFP_KERNEL);
+ if (!ionic->vfs) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0; i < num_vfs; i++) {
+ v = &ionic->vfs[i];
+ v->stats_pa = dma_map_single(ionic->dev, &v->stats,
+ sizeof(v->stats), DMA_FROM_DEVICE);
+ if (dma_mapping_error(ionic->dev, v->stats_pa)) {
+ v->stats_pa = 0;
+ err = -ENODEV;
+ goto out;
+ }
+
+ /* ignore failures from older FW, we just won't get stats */
+ (void)ionic_set_vf_config(ionic, i, IONIC_VF_ATTR_STATSADDR,
+ (u8 *)&v->stats_pa);
+ ionic->num_vfs++;
+ }
+
+out:
+ if (err)
+ ionic_vf_dealloc_locked(ionic);
+ up_write(&ionic->vf_op_lock);
+ return err;
+}
+
+static int ionic_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+ struct ionic *ionic = pci_get_drvdata(pdev);
+ struct device *dev = ionic->dev;
+ int ret = 0;
+
+ if (num_vfs > 0) {
+ ret = pci_enable_sriov(pdev, num_vfs);
+ if (ret) {
+ dev_err(dev, "Cannot enable SRIOV: %d\n", ret);
+ goto out;
+ }
+
+ ret = ionic_vf_alloc(ionic, num_vfs);
+ if (ret) {
+ dev_err(dev, "Cannot alloc VFs: %d\n", ret);
+ pci_disable_sriov(pdev);
+ goto out;
+ }
+
+ ret = num_vfs;
+ } else {
+ pci_disable_sriov(pdev);
+ ionic_vf_dealloc(ionic);
+ }
+
+out:
+ return ret;
+}
+
static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
{
struct device *dev = &pdev->dev;
struct ionic *ionic;
+ int num_vfs;
int err;
ionic = ionic_devlink_alloc(dev);
@@ -206,6 +308,15 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err_out_free_lifs;
}
+ init_rwsem(&ionic->vf_op_lock);
+ num_vfs = pci_num_vf(pdev);
+ if (num_vfs) {
+ dev_info(dev, "%d VFs found already enabled\n", num_vfs);
+ err = ionic_vf_alloc(ionic, num_vfs);
+ if (err)
+ dev_err(dev, "Cannot enable existing VFs: %d\n", err);
+ }
+
err = ionic_lifs_register(ionic);
if (err) {
dev_err(dev, "Cannot register LIFs: %d, aborting\n", err);
@@ -223,6 +334,7 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
err_out_deregister_lifs:
ionic_lifs_unregister(ionic);
err_out_deinit_lifs:
+ ionic_vf_dealloc(ionic);
ionic_lifs_deinit(ionic);
err_out_free_lifs:
ionic_lifs_free(ionic);
@@ -279,6 +391,7 @@ static struct pci_driver ionic_driver = {
.id_table = ionic_id_table,
.probe = ionic_probe,
.remove = ionic_remove,
+ .sriov_configure = ionic_sriov_configure,
};
int ionic_bus_register_driver(void)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 5f9d2ec..87f82f3 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -286,6 +286,64 @@ void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type)
ionic_dev_cmd_go(idev, &cmd);
}
+/* VF commands */
+int ionic_set_vf_config(struct ionic *ionic, int vf, u8 attr, u8 *data)
+{
+ union ionic_dev_cmd cmd = {
+ .vf_setattr.opcode = IONIC_CMD_VF_SETATTR,
+ .vf_setattr.attr = attr,
+ .vf_setattr.vf_index = vf,
+ };
+ int err;
+
+ switch (attr) {
+ case IONIC_VF_ATTR_SPOOFCHK:
+ cmd.vf_setattr.spoofchk = *data;
+ dev_dbg(ionic->dev, "%s: vf %d spoof %d\n",
+ __func__, vf, *data);
+ break;
+ case IONIC_VF_ATTR_TRUST:
+ cmd.vf_setattr.trust = *data;
+ dev_dbg(ionic->dev, "%s: vf %d trust %d\n",
+ __func__, vf, *data);
+ break;
+ case IONIC_VF_ATTR_LINKSTATE:
+ cmd.vf_setattr.linkstate = *data;
+ dev_dbg(ionic->dev, "%s: vf %d linkstate %d\n",
+ __func__, vf, *data);
+ break;
+ case IONIC_VF_ATTR_MAC:
+ ether_addr_copy(cmd.vf_setattr.macaddr, data);
+ dev_dbg(ionic->dev, "%s: vf %d macaddr %pM\n",
+ __func__, vf, data);
+ break;
+ case IONIC_VF_ATTR_VLAN:
+ cmd.vf_setattr.vlanid = cpu_to_le16(*(u16 *)data);
+ dev_dbg(ionic->dev, "%s: vf %d vlan %d\n",
+ __func__, vf, *(u16 *)data);
+ break;
+ case IONIC_VF_ATTR_RATE:
+ cmd.vf_setattr.maxrate = cpu_to_le32(*(u32 *)data);
+ dev_dbg(ionic->dev, "%s: vf %d maxrate %d\n",
+ __func__, vf, *(u32 *)data);
+ break;
+ case IONIC_VF_ATTR_STATSADDR:
+ cmd.vf_setattr.stats_pa = cpu_to_le64(*(u64 *)data);
+ dev_dbg(ionic->dev, "%s: vf %d stats_pa 0x%08llx\n",
+ __func__, vf, *(u64 *)data);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ mutex_lock(&ionic->dev_cmd_lock);
+ ionic_dev_cmd_go(&ionic->idev, &cmd);
+ err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
+ mutex_unlock(&ionic->dev_cmd_lock);
+
+ return err;
+}
+
/* LIF commands */
void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver)
{
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index 4665c5d..7838e34 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -113,6 +113,12 @@ static_assert(sizeof(struct ionic_rxq_desc) == 16);
static_assert(sizeof(struct ionic_rxq_sg_desc) == 128);
static_assert(sizeof(struct ionic_rxq_comp) == 16);
+/* SR/IOV */
+static_assert(sizeof(struct ionic_vf_setattr_cmd) == 64);
+static_assert(sizeof(struct ionic_vf_setattr_comp) == 16);
+static_assert(sizeof(struct ionic_vf_getattr_cmd) == 64);
+static_assert(sizeof(struct ionic_vf_getattr_comp) == 16);
+
struct ionic_devinfo {
u8 asic_type;
u8 asic_rev;
@@ -275,6 +281,7 @@ void ionic_dev_cmd_port_autoneg(struct ionic_dev *idev, u8 an_enable);
void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type);
void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type);
+int ionic_set_vf_config(struct ionic *ionic, int vf, u8 attr, u8 *data);
void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver);
void ionic_dev_cmd_lif_init(struct ionic_dev *idev, u16 lif_index,
dma_addr_t addr);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index 39317cdf..f131ada 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -51,6 +51,10 @@ enum ionic_cmd_opcode {
IONIC_CMD_RDMA_CREATE_CQ = 52,
IONIC_CMD_RDMA_CREATE_ADMINQ = 53,
+ /* SR/IOV commands */
+ IONIC_CMD_VF_GETATTR = 60,
+ IONIC_CMD_VF_SETATTR = 61,
+
/* QoS commands */
IONIC_CMD_QOS_CLASS_IDENTIFY = 240,
IONIC_CMD_QOS_CLASS_INIT = 241,
@@ -1639,6 +1643,93 @@ enum ionic_qos_sched_type {
IONIC_QOS_SCHED_TYPE_DWRR = 1, /* Deficit weighted round-robin */
};
+enum ionic_vf_attr {
+ IONIC_VF_ATTR_SPOOFCHK = 1,
+ IONIC_VF_ATTR_TRUST = 2,
+ IONIC_VF_ATTR_MAC = 3,
+ IONIC_VF_ATTR_LINKSTATE = 4,
+ IONIC_VF_ATTR_VLAN = 5,
+ IONIC_VF_ATTR_RATE = 6,
+ IONIC_VF_ATTR_STATSADDR = 7,
+};
+
+/**
+ * VF link status
+ */
+enum ionic_vf_link_status {
+ IONIC_VF_LINK_STATUS_AUTO = 0, /* link state of the uplink */
+ IONIC_VF_LINK_STATUS_UP = 1, /* link is always up */
+ IONIC_VF_LINK_STATUS_DOWN = 2, /* link is always down */
+};
+
+/**
+ * struct ionic_vf_setattr_cmd - Set VF attributes on the NIC
+ * @opcode: Opcode
+ * @index: VF index
+ * @attr: Attribute type (enum ionic_vf_attr)
+ * macaddr mac address
+ * vlanid vlan ID
+ * maxrate max Tx rate in Mbps
+ * spoofchk enable address spoof checking
+ * trust enable VF trust
+ * linkstate set link up or down
+ * stats_pa set DMA address for VF stats
+ */
+struct ionic_vf_setattr_cmd {
+ u8 opcode;
+ u8 attr;
+ __le16 vf_index;
+ union {
+ u8 macaddr[6];
+ __le16 vlanid;
+ __le32 maxrate;
+ u8 spoofchk;
+ u8 trust;
+ u8 linkstate;
+ __le64 stats_pa;
+ u8 pad[60];
+ };
+};
+
+struct ionic_vf_setattr_comp {
+ u8 status;
+ u8 attr;
+ __le16 vf_index;
+ __le16 comp_index;
+ u8 rsvd[9];
+ u8 color;
+};
+
+/**
+ * struct ionic_vf_getattr_cmd - Get VF attributes from the NIC
+ * @opcode: Opcode
+ * @index: VF index
+ * @attr: Attribute type (enum ionic_vf_attr)
+ */
+struct ionic_vf_getattr_cmd {
+ u8 opcode;
+ u8 attr;
+ __le16 vf_index;
+ u8 rsvd[60];
+};
+
+struct ionic_vf_getattr_comp {
+ u8 status;
+ u8 attr;
+ __le16 vf_index;
+ union {
+ u8 macaddr[6];
+ __le16 vlanid;
+ __le32 maxrate;
+ u8 spoofchk;
+ u8 trust;
+ u8 linkstate;
+ __le64 stats_pa;
+ u8 pad[11];
+ };
+ u8 color;
+};
+
/**
* union ionic_qos_config - Qos configuration structure
* @flags: Configuration flags
@@ -2289,6 +2380,9 @@ union ionic_dev_cmd {
struct ionic_port_getattr_cmd port_getattr;
struct ionic_port_setattr_cmd port_setattr;
+ struct ionic_vf_setattr_cmd vf_setattr;
+ struct ionic_vf_getattr_cmd vf_getattr;
+
struct ionic_lif_identify_cmd lif_identify;
struct ionic_lif_init_cmd lif_init;
struct ionic_lif_reset_cmd lif_reset;
@@ -2318,6 +2412,9 @@ union ionic_dev_cmd_comp {
struct ionic_port_getattr_comp port_getattr;
struct ionic_port_setattr_comp port_setattr;
+ struct ionic_vf_setattr_comp vf_setattr;
+ struct ionic_vf_getattr_comp vf_getattr;
+
struct ionic_lif_identify_comp lif_identify;
struct ionic_lif_init_comp lif_init;
ionic_lif_reset_comp lif_reset;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index a76108a..191271f 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1619,6 +1619,227 @@ int ionic_stop(struct net_device *netdev)
return err;
}
+static int ionic_get_vf_config(struct net_device *netdev,
+ int vf, struct ifla_vf_info *ivf)
+{
+ struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic *ionic = lif->ionic;
+ int ret = 0;
+
+ down_read(&ionic->vf_op_lock);
+
+ if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
+ ret = -EINVAL;
+ } else {
+ ivf->vf = vf;
+ ivf->vlan = ionic->vfs[vf].vlanid;
+ ivf->qos = 0;
+ ivf->spoofchk = ionic->vfs[vf].spoofchk;
+ ivf->linkstate = ionic->vfs[vf].linkstate;
+ ivf->max_tx_rate = ionic->vfs[vf].maxrate;
+ ivf->trusted = ionic->vfs[vf].trusted;
+ ether_addr_copy(ivf->mac, ionic->vfs[vf].macaddr);
+ }
+
+ up_read(&ionic->vf_op_lock);
+ return ret;
+}
+
+static int ionic_get_vf_stats(struct net_device *netdev, int vf,
+ struct ifla_vf_stats *vf_stats)
+{
+ struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic *ionic = lif->ionic;
+ struct ionic_lif_stats *vs;
+ int ret = 0;
+
+ down_read(&ionic->vf_op_lock);
+
+ if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
+ ret = -EINVAL;
+ } else {
+ memset(vf_stats, 0, sizeof(*vf_stats));
+ vs = &ionic->vfs[vf].stats;
+
+ vf_stats->rx_packets = le64_to_cpu(vs->rx_ucast_packets);
+ vf_stats->tx_packets = le64_to_cpu(vs->tx_ucast_packets);
+ vf_stats->rx_bytes = le64_to_cpu(vs->rx_ucast_bytes);
+ vf_stats->tx_bytes = le64_to_cpu(vs->tx_ucast_bytes);
+ vf_stats->broadcast = le64_to_cpu(vs->rx_bcast_packets);
+ vf_stats->multicast = le64_to_cpu(vs->rx_mcast_packets);
+ vf_stats->rx_dropped = le64_to_cpu(vs->rx_ucast_drop_packets) +
+ le64_to_cpu(vs->rx_mcast_drop_packets) +
+ le64_to_cpu(vs->rx_bcast_drop_packets);
+ vf_stats->tx_dropped = le64_to_cpu(vs->tx_ucast_drop_packets) +
+ le64_to_cpu(vs->tx_mcast_drop_packets) +
+ le64_to_cpu(vs->tx_bcast_drop_packets);
+ }
+
+ up_read(&ionic->vf_op_lock);
+ return ret;
+}
+
+static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
+{
+ struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic *ionic = lif->ionic;
+ int ret;
+
+ if (!(is_zero_ether_addr(mac) || is_valid_ether_addr(mac)))
+ return -EINVAL;
+
+ down_read(&ionic->vf_op_lock);
+
+ if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
+ ret = -EINVAL;
+ } else {
+ ret = ionic_set_vf_config(ionic, vf, IONIC_VF_ATTR_MAC, mac);
+ if (!ret)
+ ether_addr_copy(ionic->vfs[vf].macaddr, mac);
+ }
+
+ up_read(&ionic->vf_op_lock);
+ return ret;
+}
+
+static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
+ u8 qos, __be16 proto)
+{
+ struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic *ionic = lif->ionic;
+ int ret;
+
+ /* until someday when we support qos */
+ if (qos)
+ return -EINVAL;
+
+ if (vlan > 4095)
+ return -EINVAL;
+
+ if (proto != htons(ETH_P_8021Q))
+ return -EPROTONOSUPPORT;
+
+ down_read(&ionic->vf_op_lock);
+
+ if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
+ ret = -EINVAL;
+ } else {
+ ret = ionic_set_vf_config(ionic, vf,
+ IONIC_VF_ATTR_VLAN, (u8 *)&vlan);
+ if (!ret)
+ ionic->vfs[vf].vlanid = vlan;
+ }
+
+ up_read(&ionic->vf_op_lock);
+ return ret;
+}
+
+static int ionic_set_vf_rate(struct net_device *netdev, int vf,
+ int tx_min, int tx_max)
+{
+ struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic *ionic = lif->ionic;
+ int ret;
+
+ /* setting the min just seems silly */
+ if (tx_min)
+ return -EINVAL;
+
+ down_write(&ionic->vf_op_lock);
+
+ if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
+ ret = -EINVAL;
+ } else {
+ ret = ionic_set_vf_config(ionic, vf,
+ IONIC_VF_ATTR_RATE, (u8 *)&tx_max);
+ if (!ret)
+ lif->ionic->vfs[vf].maxrate = tx_max;
+ }
+
+ up_write(&ionic->vf_op_lock);
+ return ret;
+}
+
+static int ionic_set_vf_spoofchk(struct net_device *netdev, int vf, bool set)
+{
+ struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic *ionic = lif->ionic;
+ u8 data = set; /* convert to u8 for config */
+ int ret;
+
+ down_write(&ionic->vf_op_lock);
+
+ if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
+ ret = -EINVAL;
+ } else {
+ ret = ionic_set_vf_config(ionic, vf,
+ IONIC_VF_ATTR_SPOOFCHK, &data);
+ if (!ret)
+ ionic->vfs[vf].spoofchk = data;
+ }
+
+ up_write(&ionic->vf_op_lock);
+ return ret;
+}
+
+static int ionic_set_vf_trust(struct net_device *netdev, int vf, bool set)
+{
+ struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic *ionic = lif->ionic;
+ u8 data = set; /* convert to u8 for config */
+ int ret;
+
+ down_write(&ionic->vf_op_lock);
+
+ if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
+ ret = -EINVAL;
+ } else {
+ ret = ionic_set_vf_config(ionic, vf,
+ IONIC_VF_ATTR_TRUST, &data);
+ if (!ret)
+ ionic->vfs[vf].trusted = data;
+ }
+
+ up_write(&ionic->vf_op_lock);
+ return ret;
+}
+
+static int ionic_set_vf_link_state(struct net_device *netdev, int vf, int set)
+{
+ struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic *ionic = lif->ionic;
+ u8 data;
+ int ret;
+
+ switch (set) {
+ case IFLA_VF_LINK_STATE_ENABLE:
+ data = IONIC_VF_LINK_STATUS_UP;
+ break;
+ case IFLA_VF_LINK_STATE_DISABLE:
+ data = IONIC_VF_LINK_STATUS_DOWN;
+ break;
+ case IFLA_VF_LINK_STATE_AUTO:
+ data = IONIC_VF_LINK_STATUS_AUTO;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ down_write(&ionic->vf_op_lock);
+
+ if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
+ ret = -EINVAL;
+ } else {
+ ret = ionic_set_vf_config(ionic, vf,
+ IONIC_VF_ATTR_LINKSTATE, &data);
+ if (!ret)
+ ionic->vfs[vf].linkstate = set;
+ }
+
+ up_write(&ionic->vf_op_lock);
+ return ret;
+}
+
static const struct net_device_ops ionic_netdev_ops = {
.ndo_open = ionic_open,
.ndo_stop = ionic_stop,
@@ -1632,6 +1853,14 @@ static const struct net_device_ops ionic_netdev_ops = {
.ndo_change_mtu = ionic_change_mtu,
.ndo_vlan_rx_add_vid = ionic_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = ionic_vlan_rx_kill_vid,
+ .ndo_set_vf_vlan = ionic_set_vf_vlan,
+ .ndo_set_vf_trust = ionic_set_vf_trust,
+ .ndo_set_vf_mac = ionic_set_vf_mac,
+ .ndo_set_vf_rate = ionic_set_vf_rate,
+ .ndo_set_vf_spoofchk = ionic_set_vf_spoofchk,
+ .ndo_get_vf_config = ionic_get_vf_config,
+ .ndo_set_vf_link_state = ionic_set_vf_link_state,
+ .ndo_get_vf_stats = ionic_get_vf_stats,
};
int ionic_reset_queues(struct ionic_lif *lif)
@@ -1965,18 +2194,22 @@ static int ionic_station_set(struct ionic_lif *lif)
if (err)
return err;
+ if (is_zero_ether_addr(ctx.comp.lif_getattr.mac))
+ return 0;
+
memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
addr.sa_family = AF_INET;
err = eth_prepare_mac_addr_change(netdev, &addr);
- if (err)
- return err;
-
- if (!is_zero_ether_addr(netdev->dev_addr)) {
- netdev_dbg(lif->netdev, "deleting station MAC addr %pM\n",
- netdev->dev_addr);
- ionic_lif_addr(lif, netdev->dev_addr, false);
+ if (err) {
+ netdev_warn(lif->netdev, "ignoring bad MAC addr from NIC %pM\n",
+ addr.sa_data);
+ return 0;
}
+ netdev_dbg(lif->netdev, "deleting station MAC addr %pM\n",
+ netdev->dev_addr);
+ ionic_lif_addr(lif, netdev->dev_addr, false);
+
eth_commit_mac_addr_change(netdev, &addr);
netdev_dbg(lif->netdev, "adding station MAC addr %pM\n",
netdev->dev_addr);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index a55fd1f..9c5a7dd 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -37,6 +37,7 @@ struct ionic_rx_stats {
u64 csum_complete;
u64 csum_error;
u64 buffers_posted;
+ u64 dropped;
};
#define IONIC_QCQ_F_INITED BIT(0)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 3590ea7..a8e3fb7 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -165,6 +165,10 @@ static const char *ionic_opcode_to_str(enum ionic_cmd_opcode opcode)
return "IONIC_CMD_FW_DOWNLOAD";
case IONIC_CMD_FW_CONTROL:
return "IONIC_CMD_FW_CONTROL";
+ case IONIC_CMD_VF_GETATTR:
+ return "IONIC_CMD_VF_GETATTR";
+ case IONIC_CMD_VF_SETATTR:
+ return "IONIC_CMD_VF_SETATTR";
default:
return "DEVCMD_UNKNOWN";
}
@@ -326,9 +330,9 @@ int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds)
unsigned long max_wait;
unsigned long duration;
int opcode;
+ int hb = 0;
int done;
int err;
- int hb;
WARN_ON(in_interrupt());
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
index 03916b6..a1e9796 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
@@ -39,6 +39,7 @@ static const struct ionic_stat_desc ionic_rx_stats_desc[] = {
IONIC_RX_STAT_DESC(csum_none),
IONIC_RX_STAT_DESC(csum_complete),
IONIC_RX_STAT_DESC(csum_error),
+ IONIC_RX_STAT_DESC(dropped),
};
static const struct ionic_stat_desc ionic_txq_stats_desc[] = {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 97e7994..e452f42 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -152,12 +152,16 @@ static void ionic_rx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_i
stats = q_to_rx_stats(q);
netdev = q->lif->netdev;
- if (comp->status)
+ if (comp->status) {
+ stats->dropped++;
return;
+ }
/* no packet processing while resetting */
- if (unlikely(test_bit(IONIC_LIF_QUEUE_RESET, q->lif->state)))
+ if (unlikely(test_bit(IONIC_LIF_QUEUE_RESET, q->lif->state))) {
+ stats->dropped++;
return;
+ }
stats->pkts++;
stats->bytes += le16_to_cpu(comp->len);
@@ -167,8 +171,10 @@ static void ionic_rx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_i
else
skb = ionic_rx_frags(q, desc_info, cq_info);
- if (unlikely(!skb))
+ if (unlikely(!skb)) {
+ stats->dropped++;
return;
+ }
skb_record_rx_queue(skb, q->index);
@@ -337,6 +343,8 @@ void ionic_rx_fill(struct ionic_queue *q)
struct ionic_rxq_sg_desc *sg_desc;
struct ionic_rxq_sg_elem *sg_elem;
struct ionic_rxq_desc *desc;
+ unsigned int remain_len;
+ unsigned int seg_len;
unsigned int nfrags;
bool ring_doorbell;
unsigned int i, j;
@@ -346,6 +354,7 @@ void ionic_rx_fill(struct ionic_queue *q)
nfrags = round_up(len, PAGE_SIZE) / PAGE_SIZE;
for (i = ionic_q_space_avail(q); i; i--) {
+ remain_len = len;
desc_info = q->head;
desc = desc_info->desc;
sg_desc = desc_info->sg_desc;
@@ -369,7 +378,9 @@ void ionic_rx_fill(struct ionic_queue *q)
return;
}
desc->addr = cpu_to_le64(page_info->dma_addr);
- desc->len = cpu_to_le16(PAGE_SIZE);
+ seg_len = min_t(unsigned int, PAGE_SIZE, len);
+ desc->len = cpu_to_le16(seg_len);
+ remain_len -= seg_len;
page_info++;
/* fill sg descriptors - pages[1..n] */
@@ -385,7 +396,9 @@ void ionic_rx_fill(struct ionic_queue *q)
return;
}
sg_elem->addr = cpu_to_le64(page_info->dma_addr);
- sg_elem->len = cpu_to_le16(PAGE_SIZE);
+ seg_len = min_t(unsigned int, PAGE_SIZE, remain_len);
+ sg_elem->len = cpu_to_le16(seg_len);
+ remain_len -= seg_len;
page_info++;
}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index a496390..07f9067 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -2043,6 +2043,7 @@ static void qlcnic_83xx_exec_template_cmd(struct qlcnic_adapter *p_dev,
break;
}
entry += p_hdr->size;
+ cond_resched();
}
p_dev->ahw->reset.seq_index = index;
}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
index afa10a1..f34ae8c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
@@ -703,6 +703,7 @@ static u32 qlcnic_read_memory_test_agent(struct qlcnic_adapter *adapter,
addr += 16;
reg_read -= 16;
ret += 16;
+ cond_resched();
}
out:
mutex_unlock(&adapter->ahw->mem_lock);
@@ -1383,6 +1384,7 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter)
buf_offset += entry->hdr.cap_size;
entry_offset += entry->hdr.offset;
buffer = fw_dump->data + buf_offset;
+ cond_resched();
}
fw_dump->clr = 1;
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 522fad4..18b0c7a 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -289,18 +289,6 @@ static void emac_tx_timeout(struct net_device *netdev, unsigned int txqueue)
schedule_work(&adpt->work_thread);
}
-/* IOCTL support for the interface */
-static int emac_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
- if (!netif_running(netdev))
- return -EINVAL;
-
- if (!netdev->phydev)
- return -ENODEV;
-
- return phy_mii_ioctl(netdev->phydev, ifr, cmd);
-}
-
/**
* emac_update_hw_stats - read the EMAC stat registers
*
@@ -387,7 +375,7 @@ static const struct net_device_ops emac_netdev_ops = {
.ndo_start_xmit = emac_start_xmit,
.ndo_set_mac_address = eth_mac_addr,
.ndo_change_mtu = emac_change_mtu,
- .ndo_do_ioctl = emac_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_tx_timeout = emac_tx_timeout,
.ndo_get_stats64 = emac_get_stats64,
.ndo_set_features = emac_set_features,
diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c
index c23cb61..f5ecc410 100644
--- a/drivers/net/ethernet/rdc/r6040.c
+++ b/drivers/net/ethernet/rdc/r6040.c
@@ -498,14 +498,6 @@ static int r6040_close(struct net_device *dev)
return 0;
}
-static int r6040_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- if (!dev->phydev)
- return -EINVAL;
-
- return phy_mii_ioctl(dev->phydev, rq, cmd);
-}
-
static int r6040_rx(struct net_device *dev, int limit)
{
struct r6040_private *priv = netdev_priv(dev);
@@ -957,7 +949,7 @@ static const struct net_device_ops r6040_netdev_ops = {
.ndo_set_rx_mode = r6040_multicast_list,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
- .ndo_do_ioctl = r6040_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl,
.ndo_tx_timeout = r6040_tx_timeout,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = r6040_poll_controller,
diff --git a/drivers/net/ethernet/realtek/Makefile b/drivers/net/ethernet/realtek/Makefile
index d5304ba..2e1d78b 100644
--- a/drivers/net/ethernet/realtek/Makefile
+++ b/drivers/net/ethernet/realtek/Makefile
@@ -6,5 +6,5 @@
obj-$(CONFIG_8139CP) += 8139cp.o
obj-$(CONFIG_8139TOO) += 8139too.o
obj-$(CONFIG_ATP) += atp.o
-r8169-objs += r8169_main.o r8169_firmware.o
+r8169-objs += r8169_main.o r8169_firmware.o r8169_phy_config.o
obj-$(CONFIG_R8169) += r8169.o
diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h
new file mode 100644
index 0000000..22a6a05
--- /dev/null
+++ b/drivers/net/ethernet/realtek/r8169.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* r8169.h: RealTek 8169/8168/8101 ethernet driver.
+ *
+ * Copyright (c) 2002 ShuChen <shuchen@realtek.com.tw>
+ * Copyright (c) 2003 - 2007 Francois Romieu <romieu@fr.zoreil.com>
+ * Copyright (c) a lot of people too. Please respect their work.
+ *
+ * See MAINTAINERS file for support contact information.
+ */
+
+#include <linux/types.h>
+#include <linux/phy.h>
+
+enum mac_version {
+ /* support for ancient RTL_GIGA_MAC_VER_01 has been removed */
+ RTL_GIGA_MAC_VER_02,
+ RTL_GIGA_MAC_VER_03,
+ RTL_GIGA_MAC_VER_04,
+ RTL_GIGA_MAC_VER_05,
+ RTL_GIGA_MAC_VER_06,
+ RTL_GIGA_MAC_VER_07,
+ RTL_GIGA_MAC_VER_08,
+ RTL_GIGA_MAC_VER_09,
+ RTL_GIGA_MAC_VER_10,
+ RTL_GIGA_MAC_VER_11,
+ RTL_GIGA_MAC_VER_12,
+ RTL_GIGA_MAC_VER_13,
+ RTL_GIGA_MAC_VER_14,
+ RTL_GIGA_MAC_VER_15,
+ RTL_GIGA_MAC_VER_16,
+ RTL_GIGA_MAC_VER_17,
+ RTL_GIGA_MAC_VER_18,
+ RTL_GIGA_MAC_VER_19,
+ RTL_GIGA_MAC_VER_20,
+ RTL_GIGA_MAC_VER_21,
+ RTL_GIGA_MAC_VER_22,
+ RTL_GIGA_MAC_VER_23,
+ RTL_GIGA_MAC_VER_24,
+ RTL_GIGA_MAC_VER_25,
+ RTL_GIGA_MAC_VER_26,
+ RTL_GIGA_MAC_VER_27,
+ RTL_GIGA_MAC_VER_28,
+ RTL_GIGA_MAC_VER_29,
+ RTL_GIGA_MAC_VER_30,
+ RTL_GIGA_MAC_VER_31,
+ RTL_GIGA_MAC_VER_32,
+ RTL_GIGA_MAC_VER_33,
+ RTL_GIGA_MAC_VER_34,
+ RTL_GIGA_MAC_VER_35,
+ RTL_GIGA_MAC_VER_36,
+ RTL_GIGA_MAC_VER_37,
+ RTL_GIGA_MAC_VER_38,
+ RTL_GIGA_MAC_VER_39,
+ RTL_GIGA_MAC_VER_40,
+ RTL_GIGA_MAC_VER_41,
+ RTL_GIGA_MAC_VER_42,
+ RTL_GIGA_MAC_VER_43,
+ RTL_GIGA_MAC_VER_44,
+ RTL_GIGA_MAC_VER_45,
+ RTL_GIGA_MAC_VER_46,
+ RTL_GIGA_MAC_VER_47,
+ RTL_GIGA_MAC_VER_48,
+ RTL_GIGA_MAC_VER_49,
+ RTL_GIGA_MAC_VER_50,
+ RTL_GIGA_MAC_VER_51,
+ RTL_GIGA_MAC_VER_52,
+ RTL_GIGA_MAC_VER_60,
+ RTL_GIGA_MAC_VER_61,
+ RTL_GIGA_MAC_NONE
+};
+
+struct rtl8169_private;
+
+void r8169_apply_firmware(struct rtl8169_private *tp);
+u16 rtl8168h_2_get_adc_bias_ioffset(struct rtl8169_private *tp);
+u8 rtl8168d_efuse_read(struct rtl8169_private *tp, int reg_addr);
+void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
+ enum mac_version ver);
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 0161d83..aaa316b 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -31,6 +31,7 @@
#include <linux/ipv6.h>
#include <net/ip6_checksum.h>
+#include "r8169.h"
#include "r8169_firmware.h"
#define MODULENAME "r8169"
@@ -84,65 +85,6 @@
#define RTL_R16(tp, reg) readw(tp->mmio_addr + (reg))
#define RTL_R32(tp, reg) readl(tp->mmio_addr + (reg))
-enum mac_version {
- /* support for ancient RTL_GIGA_MAC_VER_01 has been removed */
- RTL_GIGA_MAC_VER_02,
- RTL_GIGA_MAC_VER_03,
- RTL_GIGA_MAC_VER_04,
- RTL_GIGA_MAC_VER_05,
- RTL_GIGA_MAC_VER_06,
- RTL_GIGA_MAC_VER_07,
- RTL_GIGA_MAC_VER_08,
- RTL_GIGA_MAC_VER_09,
- RTL_GIGA_MAC_VER_10,
- RTL_GIGA_MAC_VER_11,
- RTL_GIGA_MAC_VER_12,
- RTL_GIGA_MAC_VER_13,
- RTL_GIGA_MAC_VER_14,
- RTL_GIGA_MAC_VER_15,
- RTL_GIGA_MAC_VER_16,
- RTL_GIGA_MAC_VER_17,
- RTL_GIGA_MAC_VER_18,
- RTL_GIGA_MAC_VER_19,
- RTL_GIGA_MAC_VER_20,
- RTL_GIGA_MAC_VER_21,
- RTL_GIGA_MAC_VER_22,
- RTL_GIGA_MAC_VER_23,
- RTL_GIGA_MAC_VER_24,
- RTL_GIGA_MAC_VER_25,
- RTL_GIGA_MAC_VER_26,
- RTL_GIGA_MAC_VER_27,
- RTL_GIGA_MAC_VER_28,
- RTL_GIGA_MAC_VER_29,
- RTL_GIGA_MAC_VER_30,
- RTL_GIGA_MAC_VER_31,
- RTL_GIGA_MAC_VER_32,
- RTL_GIGA_MAC_VER_33,
- RTL_GIGA_MAC_VER_34,
- RTL_GIGA_MAC_VER_35,
- RTL_GIGA_MAC_VER_36,
- RTL_GIGA_MAC_VER_37,
- RTL_GIGA_MAC_VER_38,
- RTL_GIGA_MAC_VER_39,
- RTL_GIGA_MAC_VER_40,
- RTL_GIGA_MAC_VER_41,
- RTL_GIGA_MAC_VER_42,
- RTL_GIGA_MAC_VER_43,
- RTL_GIGA_MAC_VER_44,
- RTL_GIGA_MAC_VER_45,
- RTL_GIGA_MAC_VER_46,
- RTL_GIGA_MAC_VER_47,
- RTL_GIGA_MAC_VER_48,
- RTL_GIGA_MAC_VER_49,
- RTL_GIGA_MAC_VER_50,
- RTL_GIGA_MAC_VER_51,
- RTL_GIGA_MAC_VER_52,
- RTL_GIGA_MAC_VER_60,
- RTL_GIGA_MAC_VER_61,
- RTL_GIGA_MAC_NONE
-};
-
-#define JUMBO_1K ETH_DATA_LEN
#define JUMBO_4K (4*1024 - ETH_HLEN - 2)
#define JUMBO_6K (6*1024 - ETH_HLEN - 2)
#define JUMBO_7K (7*1024 - ETH_HLEN - 2)
@@ -492,6 +434,7 @@ enum rtl_register_content {
/* CPlusCmd p.31 */
EnableBist = (1 << 15), // 8168 8101
Mac_dbgo_oe = (1 << 14), // 8168 8101
+ EnAnaPLL = (1 << 14), // 8169
Normal_mode = (1 << 13), // unused
Force_half_dup = (1 << 12), // 8168 8101
Force_rxflow_en = (1 << 11), // 8168 8101
@@ -1078,52 +1021,6 @@ static int rtl_readphy(struct rtl8169_private *tp, int location)
}
}
-static void rtl_patchphy(struct rtl8169_private *tp, int reg_addr, int value)
-{
- rtl_writephy(tp, reg_addr, rtl_readphy(tp, reg_addr) | value);
-}
-
-static void rtl_w0w1_phy(struct rtl8169_private *tp, int reg_addr, int p, int m)
-{
- int val;
-
- val = rtl_readphy(tp, reg_addr);
- rtl_writephy(tp, reg_addr, (val & ~m) | p);
-}
-
-static void r8168d_modify_extpage(struct phy_device *phydev, int extpage,
- int reg, u16 mask, u16 val)
-{
- int oldpage = phy_select_page(phydev, 0x0007);
-
- __phy_write(phydev, 0x1e, extpage);
- __phy_modify(phydev, reg, mask, val);
-
- phy_restore_page(phydev, oldpage, 0);
-}
-
-static void r8168d_phy_param(struct phy_device *phydev, u16 parm,
- u16 mask, u16 val)
-{
- int oldpage = phy_select_page(phydev, 0x0005);
-
- __phy_write(phydev, 0x05, parm);
- __phy_modify(phydev, 0x06, mask, val);
-
- phy_restore_page(phydev, oldpage, 0);
-}
-
-static void r8168g_phy_param(struct phy_device *phydev, u16 parm,
- u16 mask, u16 val)
-{
- int oldpage = phy_select_page(phydev, 0x0a43);
-
- __phy_write(phydev, 0x13, parm);
- __phy_modify(phydev, 0x14, mask, val);
-
- phy_restore_page(phydev, oldpage, 0);
-}
-
DECLARE_RTL_COND(rtl_ephyar_cond)
{
return RTL_R32(tp, EPHYAR) & EPHYAR_FLAG;
@@ -1372,7 +1269,7 @@ DECLARE_RTL_COND(rtl_efusear_cond)
return RTL_R32(tp, EFUSEAR) & EFUSEAR_FLAG;
}
-static u8 rtl8168d_efuse_read(struct rtl8169_private *tp, int reg_addr)
+u8 rtl8168d_efuse_read(struct rtl8169_private *tp, int reg_addr)
{
RTL_W32(tp, EFUSEAR, (reg_addr & EFUSEAR_REG_MASK) << EFUSEAR_REG_SHIFT);
@@ -1596,7 +1493,7 @@ static netdev_features_t rtl8169_fix_features(struct net_device *dev,
if (dev->mtu > TD_MSS_MAX)
features &= ~NETIF_F_ALL_TSO;
- if (dev->mtu > JUMBO_1K &&
+ if (dev->mtu > ETH_DATA_LEN &&
tp->mac_version > RTL_GIGA_MAC_VER_06)
features &= ~(NETIF_F_CSUM_MASK | NETIF_F_ALL_TSO);
@@ -2268,22 +2165,6 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp)
}
}
-struct phy_reg {
- u16 reg;
- u16 val;
-};
-
-static void __rtl_writephy_batch(struct rtl8169_private *tp,
- const struct phy_reg *regs, int len)
-{
- while (len-- > 0) {
- rtl_writephy(tp, regs->reg, regs->val);
- regs++;
- }
-}
-
-#define rtl_writephy_batch(tp, a) __rtl_writephy_batch(tp, a, ARRAY_SIZE(a))
-
static void rtl_release_firmware(struct rtl8169_private *tp)
{
if (tp->rtl_fw) {
@@ -2293,7 +2174,7 @@ static void rtl_release_firmware(struct rtl8169_private *tp)
}
}
-static void rtl_apply_firmware(struct rtl8169_private *tp)
+void r8169_apply_firmware(struct rtl8169_private *tp)
{
/* TODO: release firmware if rtl_fw_write_firmware signals failure. */
if (tp->rtl_fw)
@@ -2315,594 +2196,6 @@ static void rtl8125_config_eee_mac(struct rtl8169_private *tp)
r8168_mac_ocp_modify(tp, 0xeb62, 0, BIT(2) | BIT(1));
}
-static void rtl8168f_config_eee_phy(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- r8168d_modify_extpage(phydev, 0x0020, 0x15, 0, BIT(8));
- r8168d_phy_param(phydev, 0x8b85, 0, BIT(13));
-}
-
-static void rtl8168g_config_eee_phy(struct rtl8169_private *tp)
-{
- phy_modify_paged(tp->phydev, 0x0a43, 0x11, 0, BIT(4));
-}
-
-static void rtl8168h_config_eee_phy(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- rtl8168g_config_eee_phy(tp);
-
- phy_modify_paged(phydev, 0xa4a, 0x11, 0x0000, 0x0200);
- phy_modify_paged(phydev, 0xa42, 0x14, 0x0000, 0x0080);
-}
-
-static void rtl8125_config_eee_phy(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- rtl8168h_config_eee_phy(tp);
-
- phy_modify_paged(phydev, 0xa6d, 0x12, 0x0001, 0x0000);
- phy_modify_paged(phydev, 0xa6d, 0x14, 0x0010, 0x0000);
-}
-
-static void rtl8169s_hw_phy_config(struct rtl8169_private *tp)
-{
- static const struct phy_reg phy_reg_init[] = {
- { 0x1f, 0x0001 },
- { 0x06, 0x006e },
- { 0x08, 0x0708 },
- { 0x15, 0x4000 },
- { 0x18, 0x65c7 },
-
- { 0x1f, 0x0001 },
- { 0x03, 0x00a1 },
- { 0x02, 0x0008 },
- { 0x01, 0x0120 },
- { 0x00, 0x1000 },
- { 0x04, 0x0800 },
- { 0x04, 0x0000 },
-
- { 0x03, 0xff41 },
- { 0x02, 0xdf60 },
- { 0x01, 0x0140 },
- { 0x00, 0x0077 },
- { 0x04, 0x7800 },
- { 0x04, 0x7000 },
-
- { 0x03, 0x802f },
- { 0x02, 0x4f02 },
- { 0x01, 0x0409 },
- { 0x00, 0xf0f9 },
- { 0x04, 0x9800 },
- { 0x04, 0x9000 },
-
- { 0x03, 0xdf01 },
- { 0x02, 0xdf20 },
- { 0x01, 0xff95 },
- { 0x00, 0xba00 },
- { 0x04, 0xa800 },
- { 0x04, 0xa000 },
-
- { 0x03, 0xff41 },
- { 0x02, 0xdf20 },
- { 0x01, 0x0140 },
- { 0x00, 0x00bb },
- { 0x04, 0xb800 },
- { 0x04, 0xb000 },
-
- { 0x03, 0xdf41 },
- { 0x02, 0xdc60 },
- { 0x01, 0x6340 },
- { 0x00, 0x007d },
- { 0x04, 0xd800 },
- { 0x04, 0xd000 },
-
- { 0x03, 0xdf01 },
- { 0x02, 0xdf20 },
- { 0x01, 0x100a },
- { 0x00, 0xa0ff },
- { 0x04, 0xf800 },
- { 0x04, 0xf000 },
-
- { 0x1f, 0x0000 },
- { 0x0b, 0x0000 },
- { 0x00, 0x9200 }
- };
-
- rtl_writephy_batch(tp, phy_reg_init);
-}
-
-static void rtl8169sb_hw_phy_config(struct rtl8169_private *tp)
-{
- phy_write_paged(tp->phydev, 0x0002, 0x01, 0x90d0);
-}
-
-static void rtl8169scd_hw_phy_config_quirk(struct rtl8169_private *tp)
-{
- struct pci_dev *pdev = tp->pci_dev;
-
- if ((pdev->subsystem_vendor != PCI_VENDOR_ID_GIGABYTE) ||
- (pdev->subsystem_device != 0xe000))
- return;
-
- phy_write_paged(tp->phydev, 0x0001, 0x10, 0xf01b);
-}
-
-static void rtl8169scd_hw_phy_config(struct rtl8169_private *tp)
-{
- static const struct phy_reg phy_reg_init[] = {
- { 0x1f, 0x0001 },
- { 0x04, 0x0000 },
- { 0x03, 0x00a1 },
- { 0x02, 0x0008 },
- { 0x01, 0x0120 },
- { 0x00, 0x1000 },
- { 0x04, 0x0800 },
- { 0x04, 0x9000 },
- { 0x03, 0x802f },
- { 0x02, 0x4f02 },
- { 0x01, 0x0409 },
- { 0x00, 0xf099 },
- { 0x04, 0x9800 },
- { 0x04, 0xa000 },
- { 0x03, 0xdf01 },
- { 0x02, 0xdf20 },
- { 0x01, 0xff95 },
- { 0x00, 0xba00 },
- { 0x04, 0xa800 },
- { 0x04, 0xf000 },
- { 0x03, 0xdf01 },
- { 0x02, 0xdf20 },
- { 0x01, 0x101a },
- { 0x00, 0xa0ff },
- { 0x04, 0xf800 },
- { 0x04, 0x0000 },
- { 0x1f, 0x0000 },
-
- { 0x1f, 0x0001 },
- { 0x10, 0xf41b },
- { 0x14, 0xfb54 },
- { 0x18, 0xf5c7 },
- { 0x1f, 0x0000 },
-
- { 0x1f, 0x0001 },
- { 0x17, 0x0cc0 },
- { 0x1f, 0x0000 }
- };
-
- rtl_writephy_batch(tp, phy_reg_init);
-
- rtl8169scd_hw_phy_config_quirk(tp);
-}
-
-static void rtl8169sce_hw_phy_config(struct rtl8169_private *tp)
-{
- static const struct phy_reg phy_reg_init[] = {
- { 0x1f, 0x0001 },
- { 0x04, 0x0000 },
- { 0x03, 0x00a1 },
- { 0x02, 0x0008 },
- { 0x01, 0x0120 },
- { 0x00, 0x1000 },
- { 0x04, 0x0800 },
- { 0x04, 0x9000 },
- { 0x03, 0x802f },
- { 0x02, 0x4f02 },
- { 0x01, 0x0409 },
- { 0x00, 0xf099 },
- { 0x04, 0x9800 },
- { 0x04, 0xa000 },
- { 0x03, 0xdf01 },
- { 0x02, 0xdf20 },
- { 0x01, 0xff95 },
- { 0x00, 0xba00 },
- { 0x04, 0xa800 },
- { 0x04, 0xf000 },
- { 0x03, 0xdf01 },
- { 0x02, 0xdf20 },
- { 0x01, 0x101a },
- { 0x00, 0xa0ff },
- { 0x04, 0xf800 },
- { 0x04, 0x0000 },
- { 0x1f, 0x0000 },
-
- { 0x1f, 0x0001 },
- { 0x0b, 0x8480 },
- { 0x1f, 0x0000 },
-
- { 0x1f, 0x0001 },
- { 0x18, 0x67c7 },
- { 0x04, 0x2000 },
- { 0x03, 0x002f },
- { 0x02, 0x4360 },
- { 0x01, 0x0109 },
- { 0x00, 0x3022 },
- { 0x04, 0x2800 },
- { 0x1f, 0x0000 },
-
- { 0x1f, 0x0001 },
- { 0x17, 0x0cc0 },
- { 0x1f, 0x0000 }
- };
-
- rtl_writephy_batch(tp, phy_reg_init);
-}
-
-static void rtl8168bb_hw_phy_config(struct rtl8169_private *tp)
-{
- rtl_writephy(tp, 0x1f, 0x0001);
- rtl_patchphy(tp, 0x16, 1 << 0);
- rtl_writephy(tp, 0x10, 0xf41b);
- rtl_writephy(tp, 0x1f, 0x0000);
-}
-
-static void rtl8168bef_hw_phy_config(struct rtl8169_private *tp)
-{
- phy_write_paged(tp->phydev, 0x0001, 0x10, 0xf41b);
-}
-
-static void rtl8168cp_1_hw_phy_config(struct rtl8169_private *tp)
-{
- phy_write(tp->phydev, 0x1d, 0x0f00);
- phy_write_paged(tp->phydev, 0x0002, 0x0c, 0x1ec8);
-}
-
-static void rtl8168cp_2_hw_phy_config(struct rtl8169_private *tp)
-{
- phy_set_bits(tp->phydev, 0x14, BIT(5));
- phy_set_bits(tp->phydev, 0x0d, BIT(5));
- phy_write_paged(tp->phydev, 0x0001, 0x1d, 0x3d98);
-}
-
-static void rtl8168c_1_hw_phy_config(struct rtl8169_private *tp)
-{
- static const struct phy_reg phy_reg_init[] = {
- { 0x1f, 0x0001 },
- { 0x12, 0x2300 },
- { 0x1f, 0x0002 },
- { 0x00, 0x88d4 },
- { 0x01, 0x82b1 },
- { 0x03, 0x7002 },
- { 0x08, 0x9e30 },
- { 0x09, 0x01f0 },
- { 0x0a, 0x5500 },
- { 0x0c, 0x00c8 },
- { 0x1f, 0x0003 },
- { 0x12, 0xc096 },
- { 0x16, 0x000a },
- { 0x1f, 0x0000 },
- { 0x1f, 0x0000 },
- { 0x09, 0x2000 },
- { 0x09, 0x0000 }
- };
-
- rtl_writephy_batch(tp, phy_reg_init);
-
- rtl_patchphy(tp, 0x14, 1 << 5);
- rtl_patchphy(tp, 0x0d, 1 << 5);
- rtl_writephy(tp, 0x1f, 0x0000);
-}
-
-static void rtl8168c_2_hw_phy_config(struct rtl8169_private *tp)
-{
- static const struct phy_reg phy_reg_init[] = {
- { 0x1f, 0x0001 },
- { 0x12, 0x2300 },
- { 0x03, 0x802f },
- { 0x02, 0x4f02 },
- { 0x01, 0x0409 },
- { 0x00, 0xf099 },
- { 0x04, 0x9800 },
- { 0x04, 0x9000 },
- { 0x1d, 0x3d98 },
- { 0x1f, 0x0002 },
- { 0x0c, 0x7eb8 },
- { 0x06, 0x0761 },
- { 0x1f, 0x0003 },
- { 0x16, 0x0f0a },
- { 0x1f, 0x0000 }
- };
-
- rtl_writephy_batch(tp, phy_reg_init);
-
- rtl_patchphy(tp, 0x16, 1 << 0);
- rtl_patchphy(tp, 0x14, 1 << 5);
- rtl_patchphy(tp, 0x0d, 1 << 5);
- rtl_writephy(tp, 0x1f, 0x0000);
-}
-
-static void rtl8168c_3_hw_phy_config(struct rtl8169_private *tp)
-{
- static const struct phy_reg phy_reg_init[] = {
- { 0x1f, 0x0001 },
- { 0x12, 0x2300 },
- { 0x1d, 0x3d98 },
- { 0x1f, 0x0002 },
- { 0x0c, 0x7eb8 },
- { 0x06, 0x5461 },
- { 0x1f, 0x0003 },
- { 0x16, 0x0f0a },
- { 0x1f, 0x0000 }
- };
-
- rtl_writephy_batch(tp, phy_reg_init);
-
- rtl_patchphy(tp, 0x16, 1 << 0);
- rtl_patchphy(tp, 0x14, 1 << 5);
- rtl_patchphy(tp, 0x0d, 1 << 5);
- rtl_writephy(tp, 0x1f, 0x0000);
-}
-
-static const struct phy_reg rtl8168d_1_phy_reg_init_0[] = {
- /* Channel Estimation */
- { 0x1f, 0x0001 },
- { 0x06, 0x4064 },
- { 0x07, 0x2863 },
- { 0x08, 0x059c },
- { 0x09, 0x26b4 },
- { 0x0a, 0x6a19 },
- { 0x0b, 0xdcc8 },
- { 0x10, 0xf06d },
- { 0x14, 0x7f68 },
- { 0x18, 0x7fd9 },
- { 0x1c, 0xf0ff },
- { 0x1d, 0x3d9c },
- { 0x1f, 0x0003 },
- { 0x12, 0xf49f },
- { 0x13, 0x070b },
- { 0x1a, 0x05ad },
- { 0x14, 0x94c0 },
-
- /*
- * Tx Error Issue
- * Enhance line driver power
- */
- { 0x1f, 0x0002 },
- { 0x06, 0x5561 },
- { 0x1f, 0x0005 },
- { 0x05, 0x8332 },
- { 0x06, 0x5561 },
-
- /*
- * Can not link to 1Gbps with bad cable
- * Decrease SNR threshold form 21.07dB to 19.04dB
- */
- { 0x1f, 0x0001 },
- { 0x17, 0x0cc0 },
-
- { 0x1f, 0x0000 },
- { 0x0d, 0xf880 }
-};
-
-static const struct phy_reg rtl8168d_1_phy_reg_init_1[] = {
- { 0x1f, 0x0002 },
- { 0x05, 0x669a },
- { 0x1f, 0x0005 },
- { 0x05, 0x8330 },
- { 0x06, 0x669a },
- { 0x1f, 0x0002 }
-};
-
-static void rtl8168d_apply_firmware_cond(struct rtl8169_private *tp, u16 val)
-{
- u16 reg_val;
-
- rtl_writephy(tp, 0x1f, 0x0005);
- rtl_writephy(tp, 0x05, 0x001b);
- reg_val = rtl_readphy(tp, 0x06);
- rtl_writephy(tp, 0x1f, 0x0000);
-
- if (reg_val != val)
- netif_warn(tp, hw, tp->dev, "chipset not ready for firmware\n");
- else
- rtl_apply_firmware(tp);
-}
-
-static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp)
-{
- rtl_writephy_batch(tp, rtl8168d_1_phy_reg_init_0);
-
- /*
- * Rx Error Issue
- * Fine Tune Switching regulator parameter
- */
- rtl_writephy(tp, 0x1f, 0x0002);
- rtl_w0w1_phy(tp, 0x0b, 0x0010, 0x00ef);
- rtl_w0w1_phy(tp, 0x0c, 0xa200, 0x5d00);
-
- if (rtl8168d_efuse_read(tp, 0x01) == 0xb1) {
- int val;
-
- rtl_writephy_batch(tp, rtl8168d_1_phy_reg_init_1);
-
- val = rtl_readphy(tp, 0x0d);
-
- if ((val & 0x00ff) != 0x006c) {
- static const u32 set[] = {
- 0x0065, 0x0066, 0x0067, 0x0068,
- 0x0069, 0x006a, 0x006b, 0x006c
- };
- int i;
-
- rtl_writephy(tp, 0x1f, 0x0002);
-
- val &= 0xff00;
- for (i = 0; i < ARRAY_SIZE(set); i++)
- rtl_writephy(tp, 0x0d, val | set[i]);
- }
- } else {
- phy_write_paged(tp->phydev, 0x0002, 0x05, 0x6662);
- r8168d_phy_param(tp->phydev, 0x8330, 0xffff, 0x6662);
- }
-
- /* RSET couple improve */
- rtl_writephy(tp, 0x1f, 0x0002);
- rtl_patchphy(tp, 0x0d, 0x0300);
- rtl_patchphy(tp, 0x0f, 0x0010);
-
- /* Fine tune PLL performance */
- rtl_writephy(tp, 0x1f, 0x0002);
- rtl_w0w1_phy(tp, 0x02, 0x0100, 0x0600);
- rtl_w0w1_phy(tp, 0x03, 0x0000, 0xe000);
- rtl_writephy(tp, 0x1f, 0x0000);
-
- rtl8168d_apply_firmware_cond(tp, 0xbf00);
-}
-
-static void rtl8168d_2_hw_phy_config(struct rtl8169_private *tp)
-{
- rtl_writephy_batch(tp, rtl8168d_1_phy_reg_init_0);
-
- if (rtl8168d_efuse_read(tp, 0x01) == 0xb1) {
- int val;
-
- rtl_writephy_batch(tp, rtl8168d_1_phy_reg_init_1);
-
- val = rtl_readphy(tp, 0x0d);
- if ((val & 0x00ff) != 0x006c) {
- static const u32 set[] = {
- 0x0065, 0x0066, 0x0067, 0x0068,
- 0x0069, 0x006a, 0x006b, 0x006c
- };
- int i;
-
- rtl_writephy(tp, 0x1f, 0x0002);
-
- val &= 0xff00;
- for (i = 0; i < ARRAY_SIZE(set); i++)
- rtl_writephy(tp, 0x0d, val | set[i]);
- }
- } else {
- phy_write_paged(tp->phydev, 0x0002, 0x05, 0x2642);
- r8168d_phy_param(tp->phydev, 0x8330, 0xffff, 0x2642);
- }
-
- /* Fine tune PLL performance */
- rtl_writephy(tp, 0x1f, 0x0002);
- rtl_w0w1_phy(tp, 0x02, 0x0100, 0x0600);
- rtl_w0w1_phy(tp, 0x03, 0x0000, 0xe000);
-
- /* Switching regulator Slew rate */
- rtl_writephy(tp, 0x1f, 0x0002);
- rtl_patchphy(tp, 0x0f, 0x0017);
- rtl_writephy(tp, 0x1f, 0x0000);
-
- rtl8168d_apply_firmware_cond(tp, 0xb300);
-}
-
-static void rtl8168d_3_hw_phy_config(struct rtl8169_private *tp)
-{
- static const struct phy_reg phy_reg_init[] = {
- { 0x1f, 0x0002 },
- { 0x10, 0x0008 },
- { 0x0d, 0x006c },
-
- { 0x1f, 0x0000 },
- { 0x0d, 0xf880 },
-
- { 0x1f, 0x0001 },
- { 0x17, 0x0cc0 },
-
- { 0x1f, 0x0001 },
- { 0x0b, 0xa4d8 },
- { 0x09, 0x281c },
- { 0x07, 0x2883 },
- { 0x0a, 0x6b35 },
- { 0x1d, 0x3da4 },
- { 0x1c, 0xeffd },
- { 0x14, 0x7f52 },
- { 0x18, 0x7fc6 },
- { 0x08, 0x0601 },
- { 0x06, 0x4063 },
- { 0x10, 0xf074 },
- { 0x1f, 0x0003 },
- { 0x13, 0x0789 },
- { 0x12, 0xf4bd },
- { 0x1a, 0x04fd },
- { 0x14, 0x84b0 },
- { 0x1f, 0x0000 },
- { 0x00, 0x9200 },
-
- { 0x1f, 0x0005 },
- { 0x01, 0x0340 },
- { 0x1f, 0x0001 },
- { 0x04, 0x4000 },
- { 0x03, 0x1d21 },
- { 0x02, 0x0c32 },
- { 0x01, 0x0200 },
- { 0x00, 0x5554 },
- { 0x04, 0x4800 },
- { 0x04, 0x4000 },
- { 0x04, 0xf000 },
- { 0x03, 0xdf01 },
- { 0x02, 0xdf20 },
- { 0x01, 0x101a },
- { 0x00, 0xa0ff },
- { 0x04, 0xf800 },
- { 0x04, 0xf000 },
- { 0x1f, 0x0000 },
- };
-
- rtl_writephy_batch(tp, phy_reg_init);
-
- r8168d_modify_extpage(tp->phydev, 0x0023, 0x16, 0xffff, 0x0000);
-}
-
-static void rtl8168d_4_hw_phy_config(struct rtl8169_private *tp)
-{
- phy_write_paged(tp->phydev, 0x0001, 0x17, 0x0cc0);
- r8168d_modify_extpage(tp->phydev, 0x002d, 0x18, 0xffff, 0x0040);
- phy_set_bits(tp->phydev, 0x0d, BIT(5));
-}
-
-static void rtl8168e_1_hw_phy_config(struct rtl8169_private *tp)
-{
- static const struct phy_reg phy_reg_init[] = {
- /* Channel estimation fine tune */
- { 0x1f, 0x0001 },
- { 0x0b, 0x6c20 },
- { 0x07, 0x2872 },
- { 0x1c, 0xefff },
- { 0x1f, 0x0003 },
- { 0x14, 0x6420 },
- { 0x1f, 0x0000 },
- };
- struct phy_device *phydev = tp->phydev;
-
- rtl_apply_firmware(tp);
-
- /* Enable Delay cap */
- r8168d_phy_param(phydev, 0x8b80, 0xffff, 0xc896);
-
- rtl_writephy_batch(tp, phy_reg_init);
-
- /* Update PFM & 10M TX idle timer */
- r8168d_modify_extpage(phydev, 0x002f, 0x15, 0xffff, 0x1919);
-
- r8168d_modify_extpage(phydev, 0x00ac, 0x18, 0xffff, 0x0006);
-
- /* DCO enable for 10M IDLE Power */
- r8168d_modify_extpage(phydev, 0x0023, 0x17, 0x0000, 0x0006);
-
- /* For impedance matching */
- phy_modify_paged(phydev, 0x0002, 0x08, 0x7f00, 0x8000);
-
- /* PHY auto speed down */
- r8168d_modify_extpage(phydev, 0x002d, 0x18, 0x0000, 0x0050);
- phy_set_bits(phydev, 0x14, BIT(15));
-
- r8168d_phy_param(phydev, 0x8b86, 0x0000, 0x0001);
- r8168d_phy_param(phydev, 0x8b85, 0x2000, 0x0000);
-
- r8168d_modify_extpage(phydev, 0x0020, 0x15, 0x1100, 0x0000);
- phy_write_paged(phydev, 0x0006, 0x00, 0x5a00);
-
- phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, 0x0000);
-}
-
static void rtl_rar_exgmac_set(struct rtl8169_private *tp, u8 *addr)
{
const u16 w[] = {
@@ -2917,286 +2210,7 @@ static void rtl_rar_exgmac_set(struct rtl8169_private *tp, u8 *addr)
rtl_eri_write(tp, 0xf4, ERIAR_MASK_1111, w[1] | (w[2] << 16));
}
-static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- rtl_apply_firmware(tp);
-
- /* Enable Delay cap */
- r8168d_modify_extpage(phydev, 0x00ac, 0x18, 0xffff, 0x0006);
-
- /* Channel estimation fine tune */
- phy_write_paged(phydev, 0x0003, 0x09, 0xa20f);
-
- /* Green Setting */
- r8168d_phy_param(phydev, 0x8b5b, 0xffff, 0x9222);
- r8168d_phy_param(phydev, 0x8b6d, 0xffff, 0x8000);
- r8168d_phy_param(phydev, 0x8b76, 0xffff, 0x8000);
-
- /* For 4-corner performance improve */
- rtl_writephy(tp, 0x1f, 0x0005);
- rtl_writephy(tp, 0x05, 0x8b80);
- rtl_w0w1_phy(tp, 0x17, 0x0006, 0x0000);
- rtl_writephy(tp, 0x1f, 0x0000);
-
- /* PHY auto speed down */
- r8168d_modify_extpage(phydev, 0x002d, 0x18, 0x0000, 0x0010);
- phy_set_bits(phydev, 0x14, BIT(15));
-
- /* improve 10M EEE waveform */
- r8168d_phy_param(phydev, 0x8b86, 0x0000, 0x0001);
-
- /* Improve 2-pair detection performance */
- r8168d_phy_param(phydev, 0x8b85, 0x0000, 0x4000);
-
- rtl8168f_config_eee_phy(tp);
-
- /* Green feature */
- rtl_writephy(tp, 0x1f, 0x0003);
- rtl_w0w1_phy(tp, 0x19, 0x0001, 0x0000);
- rtl_w0w1_phy(tp, 0x10, 0x0400, 0x0000);
- rtl_writephy(tp, 0x1f, 0x0000);
- rtl_writephy(tp, 0x1f, 0x0005);
- rtl_w0w1_phy(tp, 0x01, 0x0100, 0x0000);
- rtl_writephy(tp, 0x1f, 0x0000);
-}
-
-static void rtl8168f_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- /* For 4-corner performance improve */
- r8168d_phy_param(phydev, 0x8b80, 0x0000, 0x0006);
-
- /* PHY auto speed down */
- r8168d_modify_extpage(phydev, 0x002d, 0x18, 0x0000, 0x0010);
- phy_set_bits(phydev, 0x14, BIT(15));
-
- /* Improve 10M EEE waveform */
- r8168d_phy_param(phydev, 0x8b86, 0x0000, 0x0001);
-
- rtl8168f_config_eee_phy(tp);
-}
-
-static void rtl8168f_1_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- rtl_apply_firmware(tp);
-
- /* Channel estimation fine tune */
- phy_write_paged(phydev, 0x0003, 0x09, 0xa20f);
-
- /* Modify green table for giga & fnet */
- r8168d_phy_param(phydev, 0x8b55, 0xffff, 0x0000);
- r8168d_phy_param(phydev, 0x8b5e, 0xffff, 0x0000);
- r8168d_phy_param(phydev, 0x8b67, 0xffff, 0x0000);
- r8168d_phy_param(phydev, 0x8b70, 0xffff, 0x0000);
- r8168d_modify_extpage(phydev, 0x0078, 0x17, 0xffff, 0x0000);
- r8168d_modify_extpage(phydev, 0x0078, 0x19, 0xffff, 0x00fb);
-
- /* Modify green table for 10M */
- r8168d_phy_param(phydev, 0x8b79, 0xffff, 0xaa00);
-
- /* Disable hiimpedance detection (RTCT) */
- phy_write_paged(phydev, 0x0003, 0x01, 0x328a);
-
- rtl8168f_hw_phy_config(tp);
-
- /* Improve 2-pair detection performance */
- r8168d_phy_param(phydev, 0x8b85, 0x0000, 0x4000);
-}
-
-static void rtl8168f_2_hw_phy_config(struct rtl8169_private *tp)
-{
- rtl_apply_firmware(tp);
-
- rtl8168f_hw_phy_config(tp);
-}
-
-static void rtl8411_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- rtl_apply_firmware(tp);
-
- rtl8168f_hw_phy_config(tp);
-
- /* Improve 2-pair detection performance */
- r8168d_phy_param(phydev, 0x8b85, 0x0000, 0x4000);
-
- /* Channel estimation fine tune */
- phy_write_paged(phydev, 0x0003, 0x09, 0xa20f);
-
- /* Modify green table for giga & fnet */
- r8168d_phy_param(phydev, 0x8b55, 0xffff, 0x0000);
- r8168d_phy_param(phydev, 0x8b5e, 0xffff, 0x0000);
- r8168d_phy_param(phydev, 0x8b67, 0xffff, 0x0000);
- r8168d_phy_param(phydev, 0x8b70, 0xffff, 0x0000);
- r8168d_modify_extpage(phydev, 0x0078, 0x17, 0xffff, 0x0000);
- r8168d_modify_extpage(phydev, 0x0078, 0x19, 0xffff, 0x00aa);
-
- /* Modify green table for 10M */
- r8168d_phy_param(phydev, 0x8b79, 0xffff, 0xaa00);
-
- /* Disable hiimpedance detection (RTCT) */
- phy_write_paged(phydev, 0x0003, 0x01, 0x328a);
-
- /* Modify green table for giga */
- r8168d_phy_param(phydev, 0x8b54, 0x0800, 0x0000);
- r8168d_phy_param(phydev, 0x8b5d, 0x0800, 0x0000);
- r8168d_phy_param(phydev, 0x8a7c, 0x0100, 0x0000);
- r8168d_phy_param(phydev, 0x8a7f, 0x0000, 0x0100);
- r8168d_phy_param(phydev, 0x8a82, 0x0100, 0x0000);
- r8168d_phy_param(phydev, 0x8a85, 0x0100, 0x0000);
- r8168d_phy_param(phydev, 0x8a88, 0x0100, 0x0000);
-
- /* uc same-seed solution */
- r8168d_phy_param(phydev, 0x8b85, 0x0000, 0x8000);
-
- /* Green feature */
- rtl_writephy(tp, 0x1f, 0x0003);
- rtl_w0w1_phy(tp, 0x19, 0x0000, 0x0001);
- rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0400);
- rtl_writephy(tp, 0x1f, 0x0000);
-}
-
-static void rtl8168g_disable_aldps(struct rtl8169_private *tp)
-{
- phy_modify_paged(tp->phydev, 0x0a43, 0x10, BIT(2), 0);
-}
-
-static void rtl8168g_phy_adjust_10m_aldps(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- phy_modify_paged(phydev, 0x0bcc, 0x14, BIT(8), 0);
- phy_modify_paged(phydev, 0x0a44, 0x11, 0, BIT(7) | BIT(6));
- r8168g_phy_param(phydev, 0x8084, 0x6000, 0x0000);
- phy_modify_paged(phydev, 0x0a43, 0x10, 0x0000, 0x1003);
-}
-
-static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp)
-{
- int ret;
-
- rtl_apply_firmware(tp);
-
- ret = phy_read_paged(tp->phydev, 0x0a46, 0x10);
- if (ret & BIT(8))
- phy_modify_paged(tp->phydev, 0x0bcc, 0x12, BIT(15), 0);
- else
- phy_modify_paged(tp->phydev, 0x0bcc, 0x12, 0, BIT(15));
-
- ret = phy_read_paged(tp->phydev, 0x0a46, 0x13);
- if (ret & BIT(8))
- phy_modify_paged(tp->phydev, 0x0c41, 0x15, 0, BIT(1));
- else
- phy_modify_paged(tp->phydev, 0x0c41, 0x15, BIT(1), 0);
-
- /* Enable PHY auto speed down */
- phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(3) | BIT(2));
-
- rtl8168g_phy_adjust_10m_aldps(tp);
-
- /* EEE auto-fallback function */
- phy_modify_paged(tp->phydev, 0x0a4b, 0x11, 0, BIT(2));
-
- /* Enable UC LPF tune function */
- r8168g_phy_param(tp->phydev, 0x8012, 0x0000, 0x8000);
-
- phy_modify_paged(tp->phydev, 0x0c42, 0x11, BIT(13), BIT(14));
-
- /* Improve SWR Efficiency */
- rtl_writephy(tp, 0x1f, 0x0bcd);
- rtl_writephy(tp, 0x14, 0x5065);
- rtl_writephy(tp, 0x14, 0xd065);
- rtl_writephy(tp, 0x1f, 0x0bc8);
- rtl_writephy(tp, 0x11, 0x5655);
- rtl_writephy(tp, 0x1f, 0x0bcd);
- rtl_writephy(tp, 0x14, 0x1065);
- rtl_writephy(tp, 0x14, 0x9065);
- rtl_writephy(tp, 0x14, 0x1065);
- rtl_writephy(tp, 0x1f, 0x0000);
-
- rtl8168g_disable_aldps(tp);
- rtl8168g_config_eee_phy(tp);
-}
-
-static void rtl8168g_2_hw_phy_config(struct rtl8169_private *tp)
-{
- rtl_apply_firmware(tp);
- rtl8168g_config_eee_phy(tp);
-}
-
-static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
- u16 dout_tapbin;
- u32 data;
-
- rtl_apply_firmware(tp);
-
- /* CHN EST parameters adjust - giga master */
- r8168g_phy_param(phydev, 0x809b, 0xf800, 0x8000);
- r8168g_phy_param(phydev, 0x80a2, 0xff00, 0x8000);
- r8168g_phy_param(phydev, 0x80a4, 0xff00, 0x8500);
- r8168g_phy_param(phydev, 0x809c, 0xff00, 0xbd00);
-
- /* CHN EST parameters adjust - giga slave */
- r8168g_phy_param(phydev, 0x80ad, 0xf800, 0x7000);
- r8168g_phy_param(phydev, 0x80b4, 0xff00, 0x5000);
- r8168g_phy_param(phydev, 0x80ac, 0xff00, 0x4000);
-
- /* CHN EST parameters adjust - fnet */
- r8168g_phy_param(phydev, 0x808e, 0xff00, 0x1200);
- r8168g_phy_param(phydev, 0x8090, 0xff00, 0xe500);
- r8168g_phy_param(phydev, 0x8092, 0xff00, 0x9f00);
-
- /* enable R-tune & PGA-retune function */
- dout_tapbin = 0;
- data = phy_read_paged(phydev, 0x0a46, 0x13);
- data &= 3;
- data <<= 2;
- dout_tapbin |= data;
- data = phy_read_paged(phydev, 0x0a46, 0x12);
- data &= 0xc000;
- data >>= 14;
- dout_tapbin |= data;
- dout_tapbin = ~(dout_tapbin^0x08);
- dout_tapbin <<= 12;
- dout_tapbin &= 0xf000;
-
- r8168g_phy_param(phydev, 0x827a, 0xf000, dout_tapbin);
- r8168g_phy_param(phydev, 0x827b, 0xf000, dout_tapbin);
- r8168g_phy_param(phydev, 0x827c, 0xf000, dout_tapbin);
- r8168g_phy_param(phydev, 0x827d, 0xf000, dout_tapbin);
- r8168g_phy_param(phydev, 0x0811, 0x0000, 0x0800);
- phy_modify_paged(phydev, 0x0a42, 0x16, 0x0000, 0x0002);
-
- /* enable GPHY 10M */
- phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(11));
-
- /* SAR ADC performance */
- phy_modify_paged(tp->phydev, 0x0bca, 0x17, BIT(12) | BIT(13), BIT(14));
-
- r8168g_phy_param(phydev, 0x803f, 0x3000, 0x0000);
- r8168g_phy_param(phydev, 0x8047, 0x3000, 0x0000);
- r8168g_phy_param(phydev, 0x804f, 0x3000, 0x0000);
- r8168g_phy_param(phydev, 0x8057, 0x3000, 0x0000);
- r8168g_phy_param(phydev, 0x805f, 0x3000, 0x0000);
- r8168g_phy_param(phydev, 0x8067, 0x3000, 0x0000);
- r8168g_phy_param(phydev, 0x806f, 0x3000, 0x0000);
-
- /* disable phy pfm mode */
- phy_modify_paged(tp->phydev, 0x0a44, 0x11, BIT(7), 0);
-
- rtl8168g_disable_aldps(tp);
- rtl8168h_config_eee_phy(tp);
-}
-
-static u16 rtl8168h_2_get_adc_bias_ioffset(struct rtl8169_private *tp)
+u16 rtl8168h_2_get_adc_bias_ioffset(struct rtl8169_private *tp)
{
u16 data1, data2, ioffset;
@@ -3212,410 +2226,28 @@ static u16 rtl8168h_2_get_adc_bias_ioffset(struct rtl8169_private *tp)
return ioffset;
}
-static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
- u16 ioffset, rlen;
- u32 data;
-
- rtl_apply_firmware(tp);
-
- /* CHIN EST parameter update */
- r8168g_phy_param(phydev, 0x808a, 0x003f, 0x000a);
-
- /* enable R-tune & PGA-retune function */
- r8168g_phy_param(phydev, 0x0811, 0x0000, 0x0800);
- phy_modify_paged(phydev, 0x0a42, 0x16, 0x0000, 0x0002);
-
- /* enable GPHY 10M */
- phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(11));
-
- ioffset = rtl8168h_2_get_adc_bias_ioffset(tp);
- if (ioffset != 0xffff)
- phy_write_paged(phydev, 0x0bcf, 0x16, ioffset);
-
- /* Modify rlen (TX LPF corner frequency) level */
- data = phy_read_paged(phydev, 0x0bcd, 0x16);
- data &= 0x000f;
- rlen = 0;
- if (data > 3)
- rlen = data - 3;
- data = rlen | (rlen<<4) | (rlen<<8) | (rlen<<12);
- phy_write_paged(phydev, 0x0bcd, 0x17, data);
-
- /* disable phy pfm mode */
- phy_modify_paged(phydev, 0x0a44, 0x11, BIT(7), 0);
-
- rtl8168g_disable_aldps(tp);
- rtl8168g_config_eee_phy(tp);
-}
-
-static void rtl8168ep_1_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- /* Enable PHY auto speed down */
- phy_modify_paged(phydev, 0x0a44, 0x11, 0, BIT(3) | BIT(2));
-
- rtl8168g_phy_adjust_10m_aldps(tp);
-
- /* Enable EEE auto-fallback function */
- phy_modify_paged(phydev, 0x0a4b, 0x11, 0, BIT(2));
-
- /* Enable UC LPF tune function */
- r8168g_phy_param(phydev, 0x8012, 0x0000, 0x8000);
-
- /* set rg_sel_sdm_rate */
- phy_modify_paged(phydev, 0x0c42, 0x11, BIT(13), BIT(14));
-
- rtl8168g_disable_aldps(tp);
- rtl8168g_config_eee_phy(tp);
-}
-
-static void rtl8168ep_2_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- rtl8168g_phy_adjust_10m_aldps(tp);
-
- /* Enable UC LPF tune function */
- r8168g_phy_param(phydev, 0x8012, 0x0000, 0x8000);
-
- /* Set rg_sel_sdm_rate */
- phy_modify_paged(tp->phydev, 0x0c42, 0x11, BIT(13), BIT(14));
-
- /* Channel estimation parameters */
- r8168g_phy_param(phydev, 0x80f3, 0xff00, 0x8b00);
- r8168g_phy_param(phydev, 0x80f0, 0xff00, 0x3a00);
- r8168g_phy_param(phydev, 0x80ef, 0xff00, 0x0500);
- r8168g_phy_param(phydev, 0x80f6, 0xff00, 0x6e00);
- r8168g_phy_param(phydev, 0x80ec, 0xff00, 0x6800);
- r8168g_phy_param(phydev, 0x80ed, 0xff00, 0x7c00);
- r8168g_phy_param(phydev, 0x80f2, 0xff00, 0xf400);
- r8168g_phy_param(phydev, 0x80f4, 0xff00, 0x8500);
- r8168g_phy_param(phydev, 0x8110, 0xff00, 0xa800);
- r8168g_phy_param(phydev, 0x810f, 0xff00, 0x1d00);
- r8168g_phy_param(phydev, 0x8111, 0xff00, 0xf500);
- r8168g_phy_param(phydev, 0x8113, 0xff00, 0x6100);
- r8168g_phy_param(phydev, 0x8115, 0xff00, 0x9200);
- r8168g_phy_param(phydev, 0x810e, 0xff00, 0x0400);
- r8168g_phy_param(phydev, 0x810c, 0xff00, 0x7c00);
- r8168g_phy_param(phydev, 0x810b, 0xff00, 0x5a00);
- r8168g_phy_param(phydev, 0x80d1, 0xff00, 0xff00);
- r8168g_phy_param(phydev, 0x80cd, 0xff00, 0x9e00);
- r8168g_phy_param(phydev, 0x80d3, 0xff00, 0x0e00);
- r8168g_phy_param(phydev, 0x80d5, 0xff00, 0xca00);
- r8168g_phy_param(phydev, 0x80d7, 0xff00, 0x8400);
-
- /* Force PWM-mode */
- rtl_writephy(tp, 0x1f, 0x0bcd);
- rtl_writephy(tp, 0x14, 0x5065);
- rtl_writephy(tp, 0x14, 0xd065);
- rtl_writephy(tp, 0x1f, 0x0bc8);
- rtl_writephy(tp, 0x12, 0x00ed);
- rtl_writephy(tp, 0x1f, 0x0bcd);
- rtl_writephy(tp, 0x14, 0x1065);
- rtl_writephy(tp, 0x14, 0x9065);
- rtl_writephy(tp, 0x14, 0x1065);
- rtl_writephy(tp, 0x1f, 0x0000);
-
- rtl8168g_disable_aldps(tp);
- rtl8168g_config_eee_phy(tp);
-}
-
-static void rtl8117_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- /* CHN EST parameters adjust - fnet */
- r8168g_phy_param(phydev, 0x808e, 0xff00, 0x4800);
- r8168g_phy_param(phydev, 0x8090, 0xff00, 0xcc00);
- r8168g_phy_param(phydev, 0x8092, 0xff00, 0xb000);
-
- r8168g_phy_param(phydev, 0x8088, 0xff00, 0x6000);
- r8168g_phy_param(phydev, 0x808b, 0x3f00, 0x0b00);
- r8168g_phy_param(phydev, 0x808d, 0x1f00, 0x0600);
- r8168g_phy_param(phydev, 0x808c, 0xff00, 0xb000);
- r8168g_phy_param(phydev, 0x80a0, 0xff00, 0x2800);
- r8168g_phy_param(phydev, 0x80a2, 0xff00, 0x5000);
- r8168g_phy_param(phydev, 0x809b, 0xf800, 0xb000);
- r8168g_phy_param(phydev, 0x809a, 0xff00, 0x4b00);
- r8168g_phy_param(phydev, 0x809d, 0x3f00, 0x0800);
- r8168g_phy_param(phydev, 0x80a1, 0xff00, 0x7000);
- r8168g_phy_param(phydev, 0x809f, 0x1f00, 0x0300);
- r8168g_phy_param(phydev, 0x809e, 0xff00, 0x8800);
- r8168g_phy_param(phydev, 0x80b2, 0xff00, 0x2200);
- r8168g_phy_param(phydev, 0x80ad, 0xf800, 0x9800);
- r8168g_phy_param(phydev, 0x80af, 0x3f00, 0x0800);
- r8168g_phy_param(phydev, 0x80b3, 0xff00, 0x6f00);
- r8168g_phy_param(phydev, 0x80b1, 0x1f00, 0x0300);
- r8168g_phy_param(phydev, 0x80b0, 0xff00, 0x9300);
-
- r8168g_phy_param(phydev, 0x8011, 0x0000, 0x0800);
-
- /* enable GPHY 10M */
- phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(11));
-
- r8168g_phy_param(phydev, 0x8016, 0x0000, 0x0400);
-
- rtl8168g_disable_aldps(tp);
- rtl8168h_config_eee_phy(tp);
-}
-
-static void rtl8102e_hw_phy_config(struct rtl8169_private *tp)
-{
- static const struct phy_reg phy_reg_init[] = {
- { 0x1f, 0x0003 },
- { 0x08, 0x441d },
- { 0x01, 0x9100 },
- { 0x1f, 0x0000 }
- };
-
- rtl_writephy(tp, 0x1f, 0x0000);
- rtl_patchphy(tp, 0x11, 1 << 12);
- rtl_patchphy(tp, 0x19, 1 << 13);
- rtl_patchphy(tp, 0x10, 1 << 15);
-
- rtl_writephy_batch(tp, phy_reg_init);
-}
-
-static void rtl8105e_hw_phy_config(struct rtl8169_private *tp)
-{
- /* Disable ALDPS before ram code */
- phy_write(tp->phydev, 0x18, 0x0310);
- msleep(100);
-
- rtl_apply_firmware(tp);
-
- phy_write_paged(tp->phydev, 0x0005, 0x1a, 0x0000);
- phy_write_paged(tp->phydev, 0x0004, 0x1c, 0x0000);
- phy_write_paged(tp->phydev, 0x0001, 0x15, 0x7701);
-}
-
-static void rtl8402_hw_phy_config(struct rtl8169_private *tp)
-{
- /* Disable ALDPS before setting firmware */
- phy_write(tp->phydev, 0x18, 0x0310);
- msleep(20);
-
- rtl_apply_firmware(tp);
-
- /* EEE setting */
- rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000);
- rtl_writephy(tp, 0x1f, 0x0004);
- rtl_writephy(tp, 0x10, 0x401f);
- rtl_writephy(tp, 0x19, 0x7030);
- rtl_writephy(tp, 0x1f, 0x0000);
-}
-
-static void rtl8106e_hw_phy_config(struct rtl8169_private *tp)
-{
- static const struct phy_reg phy_reg_init[] = {
- { 0x1f, 0x0004 },
- { 0x10, 0xc07f },
- { 0x19, 0x7030 },
- { 0x1f, 0x0000 }
- };
-
- /* Disable ALDPS before ram code */
- phy_write(tp->phydev, 0x18, 0x0310);
- msleep(100);
-
- rtl_apply_firmware(tp);
-
- rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000);
- rtl_writephy_batch(tp, phy_reg_init);
-
- rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000);
-}
-
-static void rtl8125_1_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
-
- phy_modify_paged(phydev, 0xad4, 0x10, 0x03ff, 0x0084);
- phy_modify_paged(phydev, 0xad4, 0x17, 0x0000, 0x0010);
- phy_modify_paged(phydev, 0xad1, 0x13, 0x03ff, 0x0006);
- phy_modify_paged(phydev, 0xad3, 0x11, 0x003f, 0x0006);
- phy_modify_paged(phydev, 0xac0, 0x14, 0x0000, 0x1100);
- phy_modify_paged(phydev, 0xac8, 0x15, 0xf000, 0x7000);
- phy_modify_paged(phydev, 0xad1, 0x14, 0x0000, 0x0400);
- phy_modify_paged(phydev, 0xad1, 0x15, 0x0000, 0x03ff);
- phy_modify_paged(phydev, 0xad1, 0x16, 0x0000, 0x03ff);
-
- r8168g_phy_param(phydev, 0x80ea, 0xff00, 0xc400);
- r8168g_phy_param(phydev, 0x80eb, 0x0700, 0x0300);
- r8168g_phy_param(phydev, 0x80f8, 0xff00, 0x1c00);
- r8168g_phy_param(phydev, 0x80f1, 0xff00, 0x3000);
- r8168g_phy_param(phydev, 0x80fe, 0xff00, 0xa500);
- r8168g_phy_param(phydev, 0x8102, 0xff00, 0x5000);
- r8168g_phy_param(phydev, 0x8105, 0xff00, 0x3300);
- r8168g_phy_param(phydev, 0x8100, 0xff00, 0x7000);
- r8168g_phy_param(phydev, 0x8104, 0xff00, 0xf000);
- r8168g_phy_param(phydev, 0x8106, 0xff00, 0x6500);
- r8168g_phy_param(phydev, 0x80dc, 0xff00, 0xed00);
- r8168g_phy_param(phydev, 0x80df, 0x0000, 0x0100);
- r8168g_phy_param(phydev, 0x80e1, 0x0100, 0x0000);
-
- phy_modify_paged(phydev, 0xbf0, 0x13, 0x003f, 0x0038);
- r8168g_phy_param(phydev, 0x819f, 0xffff, 0xd0b6);
-
- phy_write_paged(phydev, 0xbc3, 0x12, 0x5555);
- phy_modify_paged(phydev, 0xbf0, 0x15, 0x0e00, 0x0a00);
- phy_modify_paged(phydev, 0xa5c, 0x10, 0x0400, 0x0000);
- phy_modify_paged(phydev, 0xa44, 0x11, 0x0000, 0x0800);
-
- rtl8125_config_eee_phy(tp);
-}
-
-static void rtl8125_2_hw_phy_config(struct rtl8169_private *tp)
-{
- struct phy_device *phydev = tp->phydev;
- int i;
-
- phy_modify_paged(phydev, 0xad4, 0x17, 0x0000, 0x0010);
- phy_modify_paged(phydev, 0xad1, 0x13, 0x03ff, 0x03ff);
- phy_modify_paged(phydev, 0xad3, 0x11, 0x003f, 0x0006);
- phy_modify_paged(phydev, 0xac0, 0x14, 0x1100, 0x0000);
- phy_modify_paged(phydev, 0xacc, 0x10, 0x0003, 0x0002);
- phy_modify_paged(phydev, 0xad4, 0x10, 0x00e7, 0x0044);
- phy_modify_paged(phydev, 0xac1, 0x12, 0x0080, 0x0000);
- phy_modify_paged(phydev, 0xac8, 0x10, 0x0300, 0x0000);
- phy_modify_paged(phydev, 0xac5, 0x17, 0x0007, 0x0002);
- phy_write_paged(phydev, 0xad4, 0x16, 0x00a8);
- phy_write_paged(phydev, 0xac5, 0x16, 0x01ff);
- phy_modify_paged(phydev, 0xac8, 0x15, 0x00f0, 0x0030);
-
- phy_write(phydev, 0x1f, 0x0b87);
- phy_write(phydev, 0x16, 0x80a2);
- phy_write(phydev, 0x17, 0x0153);
- phy_write(phydev, 0x16, 0x809c);
- phy_write(phydev, 0x17, 0x0153);
- phy_write(phydev, 0x1f, 0x0000);
-
- phy_write(phydev, 0x1f, 0x0a43);
- phy_write(phydev, 0x13, 0x81B3);
- phy_write(phydev, 0x14, 0x0043);
- phy_write(phydev, 0x14, 0x00A7);
- phy_write(phydev, 0x14, 0x00D6);
- phy_write(phydev, 0x14, 0x00EC);
- phy_write(phydev, 0x14, 0x00F6);
- phy_write(phydev, 0x14, 0x00FB);
- phy_write(phydev, 0x14, 0x00FD);
- phy_write(phydev, 0x14, 0x00FF);
- phy_write(phydev, 0x14, 0x00BB);
- phy_write(phydev, 0x14, 0x0058);
- phy_write(phydev, 0x14, 0x0029);
- phy_write(phydev, 0x14, 0x0013);
- phy_write(phydev, 0x14, 0x0009);
- phy_write(phydev, 0x14, 0x0004);
- phy_write(phydev, 0x14, 0x0002);
- for (i = 0; i < 25; i++)
- phy_write(phydev, 0x14, 0x0000);
- phy_write(phydev, 0x1f, 0x0000);
-
- r8168g_phy_param(phydev, 0x8257, 0xffff, 0x020F);
- r8168g_phy_param(phydev, 0x80ea, 0xffff, 0x7843);
-
- rtl_apply_firmware(tp);
-
- phy_modify_paged(phydev, 0xd06, 0x14, 0x0000, 0x2000);
-
- r8168g_phy_param(phydev, 0x81a2, 0x0000, 0x0100);
-
- phy_modify_paged(phydev, 0xb54, 0x16, 0xff00, 0xdb00);
- phy_modify_paged(phydev, 0xa45, 0x12, 0x0001, 0x0000);
- phy_modify_paged(phydev, 0xa5d, 0x12, 0x0000, 0x0020);
- phy_modify_paged(phydev, 0xad4, 0x17, 0x0010, 0x0000);
- phy_modify_paged(phydev, 0xa86, 0x15, 0x0001, 0x0000);
- phy_modify_paged(phydev, 0xa44, 0x11, 0x0000, 0x0800);
-
- rtl8125_config_eee_phy(tp);
-}
-
-static void rtl_hw_phy_config(struct net_device *dev)
-{
- static const rtl_generic_fct phy_configs[] = {
- /* PCI devices. */
- [RTL_GIGA_MAC_VER_02] = rtl8169s_hw_phy_config,
- [RTL_GIGA_MAC_VER_03] = rtl8169s_hw_phy_config,
- [RTL_GIGA_MAC_VER_04] = rtl8169sb_hw_phy_config,
- [RTL_GIGA_MAC_VER_05] = rtl8169scd_hw_phy_config,
- [RTL_GIGA_MAC_VER_06] = rtl8169sce_hw_phy_config,
- /* PCI-E devices. */
- [RTL_GIGA_MAC_VER_07] = rtl8102e_hw_phy_config,
- [RTL_GIGA_MAC_VER_08] = rtl8102e_hw_phy_config,
- [RTL_GIGA_MAC_VER_09] = rtl8102e_hw_phy_config,
- [RTL_GIGA_MAC_VER_10] = NULL,
- [RTL_GIGA_MAC_VER_11] = rtl8168bb_hw_phy_config,
- [RTL_GIGA_MAC_VER_12] = rtl8168bef_hw_phy_config,
- [RTL_GIGA_MAC_VER_13] = NULL,
- [RTL_GIGA_MAC_VER_14] = NULL,
- [RTL_GIGA_MAC_VER_15] = NULL,
- [RTL_GIGA_MAC_VER_16] = NULL,
- [RTL_GIGA_MAC_VER_17] = rtl8168bef_hw_phy_config,
- [RTL_GIGA_MAC_VER_18] = rtl8168cp_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_19] = rtl8168c_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_20] = rtl8168c_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_21] = rtl8168c_3_hw_phy_config,
- [RTL_GIGA_MAC_VER_22] = rtl8168c_3_hw_phy_config,
- [RTL_GIGA_MAC_VER_23] = rtl8168cp_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_24] = rtl8168cp_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_25] = rtl8168d_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_26] = rtl8168d_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_27] = rtl8168d_3_hw_phy_config,
- [RTL_GIGA_MAC_VER_28] = rtl8168d_4_hw_phy_config,
- [RTL_GIGA_MAC_VER_29] = rtl8105e_hw_phy_config,
- [RTL_GIGA_MAC_VER_30] = rtl8105e_hw_phy_config,
- [RTL_GIGA_MAC_VER_31] = NULL,
- [RTL_GIGA_MAC_VER_32] = rtl8168e_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_33] = rtl8168e_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_34] = rtl8168e_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_35] = rtl8168f_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_36] = rtl8168f_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_37] = rtl8402_hw_phy_config,
- [RTL_GIGA_MAC_VER_38] = rtl8411_hw_phy_config,
- [RTL_GIGA_MAC_VER_39] = rtl8106e_hw_phy_config,
- [RTL_GIGA_MAC_VER_40] = rtl8168g_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_41] = NULL,
- [RTL_GIGA_MAC_VER_42] = rtl8168g_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_43] = rtl8168g_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_44] = rtl8168g_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_45] = rtl8168h_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_46] = rtl8168h_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_47] = rtl8168h_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_48] = rtl8168h_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_49] = rtl8168ep_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_50] = rtl8168ep_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_51] = rtl8168ep_2_hw_phy_config,
- [RTL_GIGA_MAC_VER_52] = rtl8117_hw_phy_config,
- [RTL_GIGA_MAC_VER_60] = rtl8125_1_hw_phy_config,
- [RTL_GIGA_MAC_VER_61] = rtl8125_2_hw_phy_config,
- };
- struct rtl8169_private *tp = netdev_priv(dev);
-
- if (phy_configs[tp->mac_version])
- phy_configs[tp->mac_version](tp);
-}
-
static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
{
if (!test_and_set_bit(flag, tp->wk.flags))
schedule_work(&tp->wk.work);
}
-static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
+static void rtl8169_init_phy(struct rtl8169_private *tp)
{
- rtl_hw_phy_config(dev);
+ r8169_hw_phy_config(tp, tp->phydev, tp->mac_version);
if (tp->mac_version <= RTL_GIGA_MAC_VER_06) {
pci_write_config_byte(tp->pci_dev, PCI_LATENCY_TIMER, 0x40);
pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08);
- netif_dbg(tp, drv, dev,
- "Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
+ /* set undocumented MAC Reg C+CR Offset 0x82h */
RTL_W8(tp, 0x82, 0x01);
}
+ if (tp->mac_version == RTL_GIGA_MAC_VER_05 &&
+ tp->pci_dev->subsystem_vendor == PCI_VENDOR_ID_GIGABYTE &&
+ tp->pci_dev->subsystem_device == 0xe000)
+ phy_write_paged(tp->phydev, 0x0001, 0x10, 0xf01b);
+
/* We may have called phy_speed_down before */
phy_speed_up(tp->phydev);
@@ -3665,16 +2297,6 @@ static int rtl_set_mac_address(struct net_device *dev, void *p)
return 0;
}
-static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
-
- if (!netif_running(dev))
- return -ENODEV;
-
- return phy_mii_ioctl(tp->phydev, ifr, cmd);
-}
-
static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
{
switch (tp->mac_version) {
@@ -4700,9 +3322,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
rtl_pcie_state_l2l3_disable(tp);
- rtl_writephy(tp, 0x1f, 0x0c42);
- rg_saw_cnt = (rtl_readphy(tp, 0x13) & 0x3fff);
- rtl_writephy(tp, 0x1f, 0x0000);
+ rg_saw_cnt = phy_read_paged(tp->phydev, 0x0c42, 0x13) & 0x3fff;
if (rg_saw_cnt > 0) {
u16 sw_cnt_1ms_ini;
@@ -4877,7 +3497,7 @@ static void rtl_hw_start_8117(struct rtl8169_private *tp)
r8168_mac_ocp_write(tp, 0xc09e, 0x0000);
/* firmware is for MAC only */
- rtl_apply_firmware(tp);
+ r8169_apply_firmware(tp);
rtl_hw_aspm_clkreq_enable(tp, true);
}
@@ -4981,6 +3601,9 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp)
rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0e00, 0xff00);
+ /* disable EEE */
+ rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000);
+
rtl_pcie_state_l2l3_disable(tp);
}
@@ -4995,6 +3618,11 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp)
RTL_W8(tp, MCU, RTL_R8(tp, MCU) | EN_NDP | EN_OOB_RESET);
RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN);
+ rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000);
+
+ /* disable EEE */
+ rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000);
+
rtl_pcie_state_l2l3_disable(tp);
rtl_hw_aspm_clkreq_enable(tp, true);
}
@@ -5212,11 +3840,8 @@ static void rtl_hw_start_8169(struct rtl8169_private *tp)
tp->cp_cmd |= PCIMulRW;
if (tp->mac_version == RTL_GIGA_MAC_VER_02 ||
- tp->mac_version == RTL_GIGA_MAC_VER_03) {
- netif_dbg(tp, drv, tp->dev,
- "Set MAC Reg C+CR Offset 0xe0. Bit 3 and Bit 14 MUST be 1\n");
- tp->cp_cmd |= (1 << 14);
- }
+ tp->mac_version == RTL_GIGA_MAC_VER_03)
+ tp->cp_cmd |= EnAnaPLL;
RTL_W16(tp, CPlusCmd, tp->cp_cmd);
@@ -6230,7 +4855,7 @@ static int rtl_open(struct net_device *dev)
napi_enable(&tp->napi);
- rtl8169_init_phy(dev, tp);
+ rtl8169_init_phy(tp);
rtl_pll_power_up(tp);
@@ -6361,7 +4986,7 @@ static void __rtl8169_resume(struct net_device *dev)
netif_device_attach(dev);
rtl_pll_power_up(tp);
- rtl8169_init_phy(dev, tp);
+ rtl8169_init_phy(tp);
phy_start(tp->phydev);
@@ -6532,7 +5157,7 @@ static const struct net_device_ops rtl_netdev_ops = {
.ndo_fix_features = rtl8169_fix_features,
.ndo_set_features = rtl8169_set_features,
.ndo_set_mac_address = rtl_set_mac_address,
- .ndo_do_ioctl = rtl8169_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_set_rx_mode = rtl_set_rx_mode,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = rtl8169_netpoll,
@@ -6734,7 +5359,7 @@ static int rtl_jumbo_max(struct rtl8169_private *tp)
{
/* Non-GBit versions don't support jumbo frames */
if (!tp->supports_gmii)
- return JUMBO_1K;
+ return 0;
switch (tp->mac_version) {
/* RTL8169 */
@@ -6965,10 +5590,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
dev->hw_features |= NETIF_F_RXALL;
dev->hw_features |= NETIF_F_RXFCS;
- /* MTU range: 60 - hw-specific max */
- dev->min_mtu = ETH_ZLEN;
jumbo_max = rtl_jumbo_max(tp);
- dev->max_mtu = jumbo_max;
+ if (jumbo_max)
+ dev->max_mtu = jumbo_max;
rtl_set_irq_mask(tp);
@@ -6998,7 +5622,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
(RTL_R32(tp, TxConfig) >> 20) & 0xfcf,
pci_irq_vector(pdev, 0));
- if (jumbo_max > JUMBO_1K)
+ if (jumbo_max)
netif_info(tp, probe, dev,
"jumbo features [frames: %d bytes, tx checksumming: %s]\n",
jumbo_max, tp->mac_version <= RTL_GIGA_MAC_VER_06 ?
diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c
new file mode 100644
index 0000000..e367e77
--- /dev/null
+++ b/drivers/net/ethernet/realtek/r8169_phy_config.c
@@ -0,0 +1,1307 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * r8169_phy_config.c: RealTek 8169/8168/8101 ethernet driver.
+ *
+ * Copyright (c) 2002 ShuChen <shuchen@realtek.com.tw>
+ * Copyright (c) 2003 - 2007 Francois Romieu <romieu@fr.zoreil.com>
+ * Copyright (c) a lot of people too. Please respect their work.
+ *
+ * See MAINTAINERS file for support contact information.
+ */
+
+#include <linux/delay.h>
+#include <linux/phy.h>
+
+#include "r8169.h"
+
+typedef void (*rtl_phy_cfg_fct)(struct rtl8169_private *tp,
+ struct phy_device *phydev);
+
+static void r8168d_modify_extpage(struct phy_device *phydev, int extpage,
+ int reg, u16 mask, u16 val)
+{
+ int oldpage = phy_select_page(phydev, 0x0007);
+
+ __phy_write(phydev, 0x1e, extpage);
+ __phy_modify(phydev, reg, mask, val);
+
+ phy_restore_page(phydev, oldpage, 0);
+}
+
+static void r8168d_phy_param(struct phy_device *phydev, u16 parm,
+ u16 mask, u16 val)
+{
+ int oldpage = phy_select_page(phydev, 0x0005);
+
+ __phy_write(phydev, 0x05, parm);
+ __phy_modify(phydev, 0x06, mask, val);
+
+ phy_restore_page(phydev, oldpage, 0);
+}
+
+static void r8168g_phy_param(struct phy_device *phydev, u16 parm,
+ u16 mask, u16 val)
+{
+ int oldpage = phy_select_page(phydev, 0x0a43);
+
+ __phy_write(phydev, 0x13, parm);
+ __phy_modify(phydev, 0x14, mask, val);
+
+ phy_restore_page(phydev, oldpage, 0);
+}
+
+struct phy_reg {
+ u16 reg;
+ u16 val;
+};
+
+static void __rtl_writephy_batch(struct phy_device *phydev,
+ const struct phy_reg *regs, int len)
+{
+ phy_lock_mdio_bus(phydev);
+
+ while (len-- > 0) {
+ __phy_write(phydev, regs->reg, regs->val);
+ regs++;
+ }
+
+ phy_unlock_mdio_bus(phydev);
+}
+
+#define rtl_writephy_batch(p, a) __rtl_writephy_batch(p, a, ARRAY_SIZE(a))
+
+static void rtl8168f_config_eee_phy(struct phy_device *phydev)
+{
+ r8168d_modify_extpage(phydev, 0x0020, 0x15, 0, BIT(8));
+ r8168d_phy_param(phydev, 0x8b85, 0, BIT(13));
+}
+
+static void rtl8168g_config_eee_phy(struct phy_device *phydev)
+{
+ phy_modify_paged(phydev, 0x0a43, 0x11, 0, BIT(4));
+}
+
+static void rtl8168h_config_eee_phy(struct phy_device *phydev)
+{
+ rtl8168g_config_eee_phy(phydev);
+
+ phy_modify_paged(phydev, 0xa4a, 0x11, 0x0000, 0x0200);
+ phy_modify_paged(phydev, 0xa42, 0x14, 0x0000, 0x0080);
+}
+
+static void rtl8125_config_eee_phy(struct phy_device *phydev)
+{
+ rtl8168h_config_eee_phy(phydev);
+
+ phy_modify_paged(phydev, 0xa6d, 0x12, 0x0001, 0x0000);
+ phy_modify_paged(phydev, 0xa6d, 0x14, 0x0010, 0x0000);
+}
+
+static void rtl8169s_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ static const struct phy_reg phy_reg_init[] = {
+ { 0x1f, 0x0001 },
+ { 0x06, 0x006e },
+ { 0x08, 0x0708 },
+ { 0x15, 0x4000 },
+ { 0x18, 0x65c7 },
+
+ { 0x1f, 0x0001 },
+ { 0x03, 0x00a1 },
+ { 0x02, 0x0008 },
+ { 0x01, 0x0120 },
+ { 0x00, 0x1000 },
+ { 0x04, 0x0800 },
+ { 0x04, 0x0000 },
+
+ { 0x03, 0xff41 },
+ { 0x02, 0xdf60 },
+ { 0x01, 0x0140 },
+ { 0x00, 0x0077 },
+ { 0x04, 0x7800 },
+ { 0x04, 0x7000 },
+
+ { 0x03, 0x802f },
+ { 0x02, 0x4f02 },
+ { 0x01, 0x0409 },
+ { 0x00, 0xf0f9 },
+ { 0x04, 0x9800 },
+ { 0x04, 0x9000 },
+
+ { 0x03, 0xdf01 },
+ { 0x02, 0xdf20 },
+ { 0x01, 0xff95 },
+ { 0x00, 0xba00 },
+ { 0x04, 0xa800 },
+ { 0x04, 0xa000 },
+
+ { 0x03, 0xff41 },
+ { 0x02, 0xdf20 },
+ { 0x01, 0x0140 },
+ { 0x00, 0x00bb },
+ { 0x04, 0xb800 },
+ { 0x04, 0xb000 },
+
+ { 0x03, 0xdf41 },
+ { 0x02, 0xdc60 },
+ { 0x01, 0x6340 },
+ { 0x00, 0x007d },
+ { 0x04, 0xd800 },
+ { 0x04, 0xd000 },
+
+ { 0x03, 0xdf01 },
+ { 0x02, 0xdf20 },
+ { 0x01, 0x100a },
+ { 0x00, 0xa0ff },
+ { 0x04, 0xf800 },
+ { 0x04, 0xf000 },
+
+ { 0x1f, 0x0000 },
+ { 0x0b, 0x0000 },
+ { 0x00, 0x9200 }
+ };
+
+ rtl_writephy_batch(phydev, phy_reg_init);
+}
+
+static void rtl8169sb_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ phy_write_paged(phydev, 0x0002, 0x01, 0x90d0);
+}
+
+static void rtl8169scd_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ static const struct phy_reg phy_reg_init[] = {
+ { 0x1f, 0x0001 },
+ { 0x04, 0x0000 },
+ { 0x03, 0x00a1 },
+ { 0x02, 0x0008 },
+ { 0x01, 0x0120 },
+ { 0x00, 0x1000 },
+ { 0x04, 0x0800 },
+ { 0x04, 0x9000 },
+ { 0x03, 0x802f },
+ { 0x02, 0x4f02 },
+ { 0x01, 0x0409 },
+ { 0x00, 0xf099 },
+ { 0x04, 0x9800 },
+ { 0x04, 0xa000 },
+ { 0x03, 0xdf01 },
+ { 0x02, 0xdf20 },
+ { 0x01, 0xff95 },
+ { 0x00, 0xba00 },
+ { 0x04, 0xa800 },
+ { 0x04, 0xf000 },
+ { 0x03, 0xdf01 },
+ { 0x02, 0xdf20 },
+ { 0x01, 0x101a },
+ { 0x00, 0xa0ff },
+ { 0x04, 0xf800 },
+ { 0x04, 0x0000 },
+ { 0x1f, 0x0000 },
+
+ { 0x1f, 0x0001 },
+ { 0x10, 0xf41b },
+ { 0x14, 0xfb54 },
+ { 0x18, 0xf5c7 },
+ { 0x1f, 0x0000 },
+
+ { 0x1f, 0x0001 },
+ { 0x17, 0x0cc0 },
+ { 0x1f, 0x0000 }
+ };
+
+ rtl_writephy_batch(phydev, phy_reg_init);
+}
+
+static void rtl8169sce_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ static const struct phy_reg phy_reg_init[] = {
+ { 0x1f, 0x0001 },
+ { 0x04, 0x0000 },
+ { 0x03, 0x00a1 },
+ { 0x02, 0x0008 },
+ { 0x01, 0x0120 },
+ { 0x00, 0x1000 },
+ { 0x04, 0x0800 },
+ { 0x04, 0x9000 },
+ { 0x03, 0x802f },
+ { 0x02, 0x4f02 },
+ { 0x01, 0x0409 },
+ { 0x00, 0xf099 },
+ { 0x04, 0x9800 },
+ { 0x04, 0xa000 },
+ { 0x03, 0xdf01 },
+ { 0x02, 0xdf20 },
+ { 0x01, 0xff95 },
+ { 0x00, 0xba00 },
+ { 0x04, 0xa800 },
+ { 0x04, 0xf000 },
+ { 0x03, 0xdf01 },
+ { 0x02, 0xdf20 },
+ { 0x01, 0x101a },
+ { 0x00, 0xa0ff },
+ { 0x04, 0xf800 },
+ { 0x04, 0x0000 },
+ { 0x1f, 0x0000 },
+
+ { 0x1f, 0x0001 },
+ { 0x0b, 0x8480 },
+ { 0x1f, 0x0000 },
+
+ { 0x1f, 0x0001 },
+ { 0x18, 0x67c7 },
+ { 0x04, 0x2000 },
+ { 0x03, 0x002f },
+ { 0x02, 0x4360 },
+ { 0x01, 0x0109 },
+ { 0x00, 0x3022 },
+ { 0x04, 0x2800 },
+ { 0x1f, 0x0000 },
+
+ { 0x1f, 0x0001 },
+ { 0x17, 0x0cc0 },
+ { 0x1f, 0x0000 }
+ };
+
+ rtl_writephy_batch(phydev, phy_reg_init);
+}
+
+static void rtl8168bb_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ phy_write(phydev, 0x1f, 0x0001);
+ phy_set_bits(phydev, 0x16, BIT(0));
+ phy_write(phydev, 0x10, 0xf41b);
+ phy_write(phydev, 0x1f, 0x0000);
+}
+
+static void rtl8168bef_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ phy_write_paged(phydev, 0x0001, 0x10, 0xf41b);
+}
+
+static void rtl8168cp_1_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ phy_write(phydev, 0x1d, 0x0f00);
+ phy_write_paged(phydev, 0x0002, 0x0c, 0x1ec8);
+}
+
+static void rtl8168cp_2_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ phy_set_bits(phydev, 0x14, BIT(5));
+ phy_set_bits(phydev, 0x0d, BIT(5));
+ phy_write_paged(phydev, 0x0001, 0x1d, 0x3d98);
+}
+
+static void rtl8168c_1_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ static const struct phy_reg phy_reg_init[] = {
+ { 0x1f, 0x0001 },
+ { 0x12, 0x2300 },
+ { 0x1f, 0x0002 },
+ { 0x00, 0x88d4 },
+ { 0x01, 0x82b1 },
+ { 0x03, 0x7002 },
+ { 0x08, 0x9e30 },
+ { 0x09, 0x01f0 },
+ { 0x0a, 0x5500 },
+ { 0x0c, 0x00c8 },
+ { 0x1f, 0x0003 },
+ { 0x12, 0xc096 },
+ { 0x16, 0x000a },
+ { 0x1f, 0x0000 },
+ { 0x1f, 0x0000 },
+ { 0x09, 0x2000 },
+ { 0x09, 0x0000 }
+ };
+
+ rtl_writephy_batch(phydev, phy_reg_init);
+
+ phy_set_bits(phydev, 0x14, BIT(5));
+ phy_set_bits(phydev, 0x0d, BIT(5));
+}
+
+static void rtl8168c_2_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ static const struct phy_reg phy_reg_init[] = {
+ { 0x1f, 0x0001 },
+ { 0x12, 0x2300 },
+ { 0x03, 0x802f },
+ { 0x02, 0x4f02 },
+ { 0x01, 0x0409 },
+ { 0x00, 0xf099 },
+ { 0x04, 0x9800 },
+ { 0x04, 0x9000 },
+ { 0x1d, 0x3d98 },
+ { 0x1f, 0x0002 },
+ { 0x0c, 0x7eb8 },
+ { 0x06, 0x0761 },
+ { 0x1f, 0x0003 },
+ { 0x16, 0x0f0a },
+ { 0x1f, 0x0000 }
+ };
+
+ rtl_writephy_batch(phydev, phy_reg_init);
+
+ phy_set_bits(phydev, 0x16, BIT(0));
+ phy_set_bits(phydev, 0x14, BIT(5));
+ phy_set_bits(phydev, 0x0d, BIT(5));
+}
+
+static void rtl8168c_3_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ static const struct phy_reg phy_reg_init[] = {
+ { 0x1f, 0x0001 },
+ { 0x12, 0x2300 },
+ { 0x1d, 0x3d98 },
+ { 0x1f, 0x0002 },
+ { 0x0c, 0x7eb8 },
+ { 0x06, 0x5461 },
+ { 0x1f, 0x0003 },
+ { 0x16, 0x0f0a },
+ { 0x1f, 0x0000 }
+ };
+
+ rtl_writephy_batch(phydev, phy_reg_init);
+
+ phy_set_bits(phydev, 0x16, BIT(0));
+ phy_set_bits(phydev, 0x14, BIT(5));
+ phy_set_bits(phydev, 0x0d, BIT(5));
+}
+
+static const struct phy_reg rtl8168d_1_phy_reg_init_0[] = {
+ /* Channel Estimation */
+ { 0x1f, 0x0001 },
+ { 0x06, 0x4064 },
+ { 0x07, 0x2863 },
+ { 0x08, 0x059c },
+ { 0x09, 0x26b4 },
+ { 0x0a, 0x6a19 },
+ { 0x0b, 0xdcc8 },
+ { 0x10, 0xf06d },
+ { 0x14, 0x7f68 },
+ { 0x18, 0x7fd9 },
+ { 0x1c, 0xf0ff },
+ { 0x1d, 0x3d9c },
+ { 0x1f, 0x0003 },
+ { 0x12, 0xf49f },
+ { 0x13, 0x070b },
+ { 0x1a, 0x05ad },
+ { 0x14, 0x94c0 },
+
+ /*
+ * Tx Error Issue
+ * Enhance line driver power
+ */
+ { 0x1f, 0x0002 },
+ { 0x06, 0x5561 },
+ { 0x1f, 0x0005 },
+ { 0x05, 0x8332 },
+ { 0x06, 0x5561 },
+
+ /*
+ * Can not link to 1Gbps with bad cable
+ * Decrease SNR threshold form 21.07dB to 19.04dB
+ */
+ { 0x1f, 0x0001 },
+ { 0x17, 0x0cc0 },
+
+ { 0x1f, 0x0000 },
+ { 0x0d, 0xf880 }
+};
+
+static const struct phy_reg rtl8168d_1_phy_reg_init_1[] = {
+ { 0x1f, 0x0002 },
+ { 0x05, 0x669a },
+ { 0x1f, 0x0005 },
+ { 0x05, 0x8330 },
+ { 0x06, 0x669a },
+ { 0x1f, 0x0002 }
+};
+
+static void rtl8168d_apply_firmware_cond(struct rtl8169_private *tp,
+ struct phy_device *phydev,
+ u16 val)
+{
+ u16 reg_val;
+
+ phy_write(phydev, 0x1f, 0x0005);
+ phy_write(phydev, 0x05, 0x001b);
+ reg_val = phy_read(phydev, 0x06);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ if (reg_val != val)
+ phydev_warn(phydev, "chipset not ready for firmware\n");
+ else
+ r8169_apply_firmware(tp);
+}
+
+static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ rtl_writephy_batch(phydev, rtl8168d_1_phy_reg_init_0);
+
+ /*
+ * Rx Error Issue
+ * Fine Tune Switching regulator parameter
+ */
+ phy_write(phydev, 0x1f, 0x0002);
+ phy_modify(phydev, 0x0b, 0x00ef, 0x0010);
+ phy_modify(phydev, 0x0c, 0x5d00, 0xa200);
+
+ if (rtl8168d_efuse_read(tp, 0x01) == 0xb1) {
+ int val;
+
+ rtl_writephy_batch(phydev, rtl8168d_1_phy_reg_init_1);
+
+ val = phy_read(phydev, 0x0d);
+
+ if ((val & 0x00ff) != 0x006c) {
+ static const u32 set[] = {
+ 0x0065, 0x0066, 0x0067, 0x0068,
+ 0x0069, 0x006a, 0x006b, 0x006c
+ };
+ int i;
+
+ phy_write(phydev, 0x1f, 0x0002);
+
+ val &= 0xff00;
+ for (i = 0; i < ARRAY_SIZE(set); i++)
+ phy_write(phydev, 0x0d, val | set[i]);
+ }
+ } else {
+ phy_write_paged(phydev, 0x0002, 0x05, 0x6662);
+ r8168d_phy_param(phydev, 0x8330, 0xffff, 0x6662);
+ }
+
+ /* RSET couple improve */
+ phy_write(phydev, 0x1f, 0x0002);
+ phy_set_bits(phydev, 0x0d, 0x0300);
+ phy_set_bits(phydev, 0x0f, 0x0010);
+
+ /* Fine tune PLL performance */
+ phy_write(phydev, 0x1f, 0x0002);
+ phy_modify(phydev, 0x02, 0x0600, 0x0100);
+ phy_clear_bits(phydev, 0x03, 0xe000);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ rtl8168d_apply_firmware_cond(tp, phydev, 0xbf00);
+}
+
+static void rtl8168d_2_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ rtl_writephy_batch(phydev, rtl8168d_1_phy_reg_init_0);
+
+ if (rtl8168d_efuse_read(tp, 0x01) == 0xb1) {
+ int val;
+
+ rtl_writephy_batch(phydev, rtl8168d_1_phy_reg_init_1);
+
+ val = phy_read(phydev, 0x0d);
+ if ((val & 0x00ff) != 0x006c) {
+ static const u32 set[] = {
+ 0x0065, 0x0066, 0x0067, 0x0068,
+ 0x0069, 0x006a, 0x006b, 0x006c
+ };
+ int i;
+
+ phy_write(phydev, 0x1f, 0x0002);
+
+ val &= 0xff00;
+ for (i = 0; i < ARRAY_SIZE(set); i++)
+ phy_write(phydev, 0x0d, val | set[i]);
+ }
+ } else {
+ phy_write_paged(phydev, 0x0002, 0x05, 0x2642);
+ r8168d_phy_param(phydev, 0x8330, 0xffff, 0x2642);
+ }
+
+ /* Fine tune PLL performance */
+ phy_write(phydev, 0x1f, 0x0002);
+ phy_modify(phydev, 0x02, 0x0600, 0x0100);
+ phy_clear_bits(phydev, 0x03, 0xe000);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ /* Switching regulator Slew rate */
+ phy_modify_paged(phydev, 0x0002, 0x0f, 0x0000, 0x0017);
+
+ rtl8168d_apply_firmware_cond(tp, phydev, 0xb300);
+}
+
+static void rtl8168d_3_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ static const struct phy_reg phy_reg_init[] = {
+ { 0x1f, 0x0002 },
+ { 0x10, 0x0008 },
+ { 0x0d, 0x006c },
+
+ { 0x1f, 0x0000 },
+ { 0x0d, 0xf880 },
+
+ { 0x1f, 0x0001 },
+ { 0x17, 0x0cc0 },
+
+ { 0x1f, 0x0001 },
+ { 0x0b, 0xa4d8 },
+ { 0x09, 0x281c },
+ { 0x07, 0x2883 },
+ { 0x0a, 0x6b35 },
+ { 0x1d, 0x3da4 },
+ { 0x1c, 0xeffd },
+ { 0x14, 0x7f52 },
+ { 0x18, 0x7fc6 },
+ { 0x08, 0x0601 },
+ { 0x06, 0x4063 },
+ { 0x10, 0xf074 },
+ { 0x1f, 0x0003 },
+ { 0x13, 0x0789 },
+ { 0x12, 0xf4bd },
+ { 0x1a, 0x04fd },
+ { 0x14, 0x84b0 },
+ { 0x1f, 0x0000 },
+ { 0x00, 0x9200 },
+
+ { 0x1f, 0x0005 },
+ { 0x01, 0x0340 },
+ { 0x1f, 0x0001 },
+ { 0x04, 0x4000 },
+ { 0x03, 0x1d21 },
+ { 0x02, 0x0c32 },
+ { 0x01, 0x0200 },
+ { 0x00, 0x5554 },
+ { 0x04, 0x4800 },
+ { 0x04, 0x4000 },
+ { 0x04, 0xf000 },
+ { 0x03, 0xdf01 },
+ { 0x02, 0xdf20 },
+ { 0x01, 0x101a },
+ { 0x00, 0xa0ff },
+ { 0x04, 0xf800 },
+ { 0x04, 0xf000 },
+ { 0x1f, 0x0000 },
+ };
+
+ rtl_writephy_batch(phydev, phy_reg_init);
+ r8168d_modify_extpage(phydev, 0x0023, 0x16, 0xffff, 0x0000);
+}
+
+static void rtl8168d_4_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ phy_write_paged(phydev, 0x0001, 0x17, 0x0cc0);
+ r8168d_modify_extpage(phydev, 0x002d, 0x18, 0xffff, 0x0040);
+ phy_set_bits(phydev, 0x0d, BIT(5));
+}
+
+static void rtl8168e_1_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ static const struct phy_reg phy_reg_init[] = {
+ /* Channel estimation fine tune */
+ { 0x1f, 0x0001 },
+ { 0x0b, 0x6c20 },
+ { 0x07, 0x2872 },
+ { 0x1c, 0xefff },
+ { 0x1f, 0x0003 },
+ { 0x14, 0x6420 },
+ { 0x1f, 0x0000 },
+ };
+
+ r8169_apply_firmware(tp);
+
+ /* Enable Delay cap */
+ r8168d_phy_param(phydev, 0x8b80, 0xffff, 0xc896);
+
+ rtl_writephy_batch(phydev, phy_reg_init);
+
+ /* Update PFM & 10M TX idle timer */
+ r8168d_modify_extpage(phydev, 0x002f, 0x15, 0xffff, 0x1919);
+
+ r8168d_modify_extpage(phydev, 0x00ac, 0x18, 0xffff, 0x0006);
+
+ /* DCO enable for 10M IDLE Power */
+ r8168d_modify_extpage(phydev, 0x0023, 0x17, 0x0000, 0x0006);
+
+ /* For impedance matching */
+ phy_modify_paged(phydev, 0x0002, 0x08, 0x7f00, 0x8000);
+
+ /* PHY auto speed down */
+ r8168d_modify_extpage(phydev, 0x002d, 0x18, 0x0000, 0x0050);
+ phy_set_bits(phydev, 0x14, BIT(15));
+
+ r8168d_phy_param(phydev, 0x8b86, 0x0000, 0x0001);
+ r8168d_phy_param(phydev, 0x8b85, 0x2000, 0x0000);
+
+ r8168d_modify_extpage(phydev, 0x0020, 0x15, 0x1100, 0x0000);
+ phy_write_paged(phydev, 0x0006, 0x00, 0x5a00);
+
+ phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, 0x0000);
+}
+
+static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ r8169_apply_firmware(tp);
+
+ /* Enable Delay cap */
+ r8168d_modify_extpage(phydev, 0x00ac, 0x18, 0xffff, 0x0006);
+
+ /* Channel estimation fine tune */
+ phy_write_paged(phydev, 0x0003, 0x09, 0xa20f);
+
+ /* Green Setting */
+ r8168d_phy_param(phydev, 0x8b5b, 0xffff, 0x9222);
+ r8168d_phy_param(phydev, 0x8b6d, 0xffff, 0x8000);
+ r8168d_phy_param(phydev, 0x8b76, 0xffff, 0x8000);
+
+ /* For 4-corner performance improve */
+ phy_write(phydev, 0x1f, 0x0005);
+ phy_write(phydev, 0x05, 0x8b80);
+ phy_set_bits(phydev, 0x17, 0x0006);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ /* PHY auto speed down */
+ r8168d_modify_extpage(phydev, 0x002d, 0x18, 0x0000, 0x0010);
+ phy_set_bits(phydev, 0x14, BIT(15));
+
+ /* improve 10M EEE waveform */
+ r8168d_phy_param(phydev, 0x8b86, 0x0000, 0x0001);
+
+ /* Improve 2-pair detection performance */
+ r8168d_phy_param(phydev, 0x8b85, 0x0000, 0x4000);
+
+ rtl8168f_config_eee_phy(phydev);
+
+ /* Green feature */
+ phy_write(phydev, 0x1f, 0x0003);
+ phy_set_bits(phydev, 0x19, BIT(0));
+ phy_set_bits(phydev, 0x10, BIT(10));
+ phy_write(phydev, 0x1f, 0x0000);
+ phy_modify_paged(phydev, 0x0005, 0x01, 0, BIT(8));
+}
+
+static void rtl8168f_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ /* For 4-corner performance improve */
+ r8168d_phy_param(phydev, 0x8b80, 0x0000, 0x0006);
+
+ /* PHY auto speed down */
+ r8168d_modify_extpage(phydev, 0x002d, 0x18, 0x0000, 0x0010);
+ phy_set_bits(phydev, 0x14, BIT(15));
+
+ /* Improve 10M EEE waveform */
+ r8168d_phy_param(phydev, 0x8b86, 0x0000, 0x0001);
+
+ rtl8168f_config_eee_phy(phydev);
+}
+
+static void rtl8168f_1_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ r8169_apply_firmware(tp);
+
+ /* Channel estimation fine tune */
+ phy_write_paged(phydev, 0x0003, 0x09, 0xa20f);
+
+ /* Modify green table for giga & fnet */
+ r8168d_phy_param(phydev, 0x8b55, 0xffff, 0x0000);
+ r8168d_phy_param(phydev, 0x8b5e, 0xffff, 0x0000);
+ r8168d_phy_param(phydev, 0x8b67, 0xffff, 0x0000);
+ r8168d_phy_param(phydev, 0x8b70, 0xffff, 0x0000);
+ r8168d_modify_extpage(phydev, 0x0078, 0x17, 0xffff, 0x0000);
+ r8168d_modify_extpage(phydev, 0x0078, 0x19, 0xffff, 0x00fb);
+
+ /* Modify green table for 10M */
+ r8168d_phy_param(phydev, 0x8b79, 0xffff, 0xaa00);
+
+ /* Disable hiimpedance detection (RTCT) */
+ phy_write_paged(phydev, 0x0003, 0x01, 0x328a);
+
+ rtl8168f_hw_phy_config(tp, phydev);
+
+ /* Improve 2-pair detection performance */
+ r8168d_phy_param(phydev, 0x8b85, 0x0000, 0x4000);
+}
+
+static void rtl8168f_2_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ r8169_apply_firmware(tp);
+
+ rtl8168f_hw_phy_config(tp, phydev);
+}
+
+static void rtl8411_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ r8169_apply_firmware(tp);
+
+ rtl8168f_hw_phy_config(tp, phydev);
+
+ /* Improve 2-pair detection performance */
+ r8168d_phy_param(phydev, 0x8b85, 0x0000, 0x4000);
+
+ /* Channel estimation fine tune */
+ phy_write_paged(phydev, 0x0003, 0x09, 0xa20f);
+
+ /* Modify green table for giga & fnet */
+ r8168d_phy_param(phydev, 0x8b55, 0xffff, 0x0000);
+ r8168d_phy_param(phydev, 0x8b5e, 0xffff, 0x0000);
+ r8168d_phy_param(phydev, 0x8b67, 0xffff, 0x0000);
+ r8168d_phy_param(phydev, 0x8b70, 0xffff, 0x0000);
+ r8168d_modify_extpage(phydev, 0x0078, 0x17, 0xffff, 0x0000);
+ r8168d_modify_extpage(phydev, 0x0078, 0x19, 0xffff, 0x00aa);
+
+ /* Modify green table for 10M */
+ r8168d_phy_param(phydev, 0x8b79, 0xffff, 0xaa00);
+
+ /* Disable hiimpedance detection (RTCT) */
+ phy_write_paged(phydev, 0x0003, 0x01, 0x328a);
+
+ /* Modify green table for giga */
+ r8168d_phy_param(phydev, 0x8b54, 0x0800, 0x0000);
+ r8168d_phy_param(phydev, 0x8b5d, 0x0800, 0x0000);
+ r8168d_phy_param(phydev, 0x8a7c, 0x0100, 0x0000);
+ r8168d_phy_param(phydev, 0x8a7f, 0x0000, 0x0100);
+ r8168d_phy_param(phydev, 0x8a82, 0x0100, 0x0000);
+ r8168d_phy_param(phydev, 0x8a85, 0x0100, 0x0000);
+ r8168d_phy_param(phydev, 0x8a88, 0x0100, 0x0000);
+
+ /* uc same-seed solution */
+ r8168d_phy_param(phydev, 0x8b85, 0x0000, 0x8000);
+
+ /* Green feature */
+ phy_write(phydev, 0x1f, 0x0003);
+ phy_clear_bits(phydev, 0x19, BIT(0));
+ phy_clear_bits(phydev, 0x10, BIT(10));
+ phy_write(phydev, 0x1f, 0x0000);
+}
+
+static void rtl8168g_disable_aldps(struct phy_device *phydev)
+{
+ phy_modify_paged(phydev, 0x0a43, 0x10, BIT(2), 0);
+}
+
+static void rtl8168g_phy_adjust_10m_aldps(struct phy_device *phydev)
+{
+ phy_modify_paged(phydev, 0x0bcc, 0x14, BIT(8), 0);
+ phy_modify_paged(phydev, 0x0a44, 0x11, 0, BIT(7) | BIT(6));
+ r8168g_phy_param(phydev, 0x8084, 0x6000, 0x0000);
+ phy_modify_paged(phydev, 0x0a43, 0x10, 0x0000, 0x1003);
+}
+
+static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ int ret;
+
+ r8169_apply_firmware(tp);
+
+ ret = phy_read_paged(phydev, 0x0a46, 0x10);
+ if (ret & BIT(8))
+ phy_modify_paged(phydev, 0x0bcc, 0x12, BIT(15), 0);
+ else
+ phy_modify_paged(phydev, 0x0bcc, 0x12, 0, BIT(15));
+
+ ret = phy_read_paged(phydev, 0x0a46, 0x13);
+ if (ret & BIT(8))
+ phy_modify_paged(phydev, 0x0c41, 0x15, 0, BIT(1));
+ else
+ phy_modify_paged(phydev, 0x0c41, 0x15, BIT(1), 0);
+
+ /* Enable PHY auto speed down */
+ phy_modify_paged(phydev, 0x0a44, 0x11, 0, BIT(3) | BIT(2));
+
+ rtl8168g_phy_adjust_10m_aldps(phydev);
+
+ /* EEE auto-fallback function */
+ phy_modify_paged(phydev, 0x0a4b, 0x11, 0, BIT(2));
+
+ /* Enable UC LPF tune function */
+ r8168g_phy_param(phydev, 0x8012, 0x0000, 0x8000);
+
+ phy_modify_paged(phydev, 0x0c42, 0x11, BIT(13), BIT(14));
+
+ /* Improve SWR Efficiency */
+ phy_write(phydev, 0x1f, 0x0bcd);
+ phy_write(phydev, 0x14, 0x5065);
+ phy_write(phydev, 0x14, 0xd065);
+ phy_write(phydev, 0x1f, 0x0bc8);
+ phy_write(phydev, 0x11, 0x5655);
+ phy_write(phydev, 0x1f, 0x0bcd);
+ phy_write(phydev, 0x14, 0x1065);
+ phy_write(phydev, 0x14, 0x9065);
+ phy_write(phydev, 0x14, 0x1065);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ rtl8168g_disable_aldps(phydev);
+ rtl8168g_config_eee_phy(phydev);
+}
+
+static void rtl8168g_2_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ r8169_apply_firmware(tp);
+ rtl8168g_config_eee_phy(phydev);
+}
+
+static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ u16 dout_tapbin;
+ u32 data;
+
+ r8169_apply_firmware(tp);
+
+ /* CHN EST parameters adjust - giga master */
+ r8168g_phy_param(phydev, 0x809b, 0xf800, 0x8000);
+ r8168g_phy_param(phydev, 0x80a2, 0xff00, 0x8000);
+ r8168g_phy_param(phydev, 0x80a4, 0xff00, 0x8500);
+ r8168g_phy_param(phydev, 0x809c, 0xff00, 0xbd00);
+
+ /* CHN EST parameters adjust - giga slave */
+ r8168g_phy_param(phydev, 0x80ad, 0xf800, 0x7000);
+ r8168g_phy_param(phydev, 0x80b4, 0xff00, 0x5000);
+ r8168g_phy_param(phydev, 0x80ac, 0xff00, 0x4000);
+
+ /* CHN EST parameters adjust - fnet */
+ r8168g_phy_param(phydev, 0x808e, 0xff00, 0x1200);
+ r8168g_phy_param(phydev, 0x8090, 0xff00, 0xe500);
+ r8168g_phy_param(phydev, 0x8092, 0xff00, 0x9f00);
+
+ /* enable R-tune & PGA-retune function */
+ dout_tapbin = 0;
+ data = phy_read_paged(phydev, 0x0a46, 0x13);
+ data &= 3;
+ data <<= 2;
+ dout_tapbin |= data;
+ data = phy_read_paged(phydev, 0x0a46, 0x12);
+ data &= 0xc000;
+ data >>= 14;
+ dout_tapbin |= data;
+ dout_tapbin = ~(dout_tapbin ^ 0x08);
+ dout_tapbin <<= 12;
+ dout_tapbin &= 0xf000;
+
+ r8168g_phy_param(phydev, 0x827a, 0xf000, dout_tapbin);
+ r8168g_phy_param(phydev, 0x827b, 0xf000, dout_tapbin);
+ r8168g_phy_param(phydev, 0x827c, 0xf000, dout_tapbin);
+ r8168g_phy_param(phydev, 0x827d, 0xf000, dout_tapbin);
+ r8168g_phy_param(phydev, 0x0811, 0x0000, 0x0800);
+ phy_modify_paged(phydev, 0x0a42, 0x16, 0x0000, 0x0002);
+
+ /* enable GPHY 10M */
+ phy_modify_paged(phydev, 0x0a44, 0x11, 0, BIT(11));
+
+ /* SAR ADC performance */
+ phy_modify_paged(phydev, 0x0bca, 0x17, BIT(12) | BIT(13), BIT(14));
+
+ r8168g_phy_param(phydev, 0x803f, 0x3000, 0x0000);
+ r8168g_phy_param(phydev, 0x8047, 0x3000, 0x0000);
+ r8168g_phy_param(phydev, 0x804f, 0x3000, 0x0000);
+ r8168g_phy_param(phydev, 0x8057, 0x3000, 0x0000);
+ r8168g_phy_param(phydev, 0x805f, 0x3000, 0x0000);
+ r8168g_phy_param(phydev, 0x8067, 0x3000, 0x0000);
+ r8168g_phy_param(phydev, 0x806f, 0x3000, 0x0000);
+
+ /* disable phy pfm mode */
+ phy_modify_paged(phydev, 0x0a44, 0x11, BIT(7), 0);
+
+ rtl8168g_disable_aldps(phydev);
+ rtl8168h_config_eee_phy(phydev);
+}
+
+static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ u16 ioffset, rlen;
+ u32 data;
+
+ r8169_apply_firmware(tp);
+
+ /* CHIN EST parameter update */
+ r8168g_phy_param(phydev, 0x808a, 0x003f, 0x000a);
+
+ /* enable R-tune & PGA-retune function */
+ r8168g_phy_param(phydev, 0x0811, 0x0000, 0x0800);
+ phy_modify_paged(phydev, 0x0a42, 0x16, 0x0000, 0x0002);
+
+ /* enable GPHY 10M */
+ phy_modify_paged(phydev, 0x0a44, 0x11, 0, BIT(11));
+
+ ioffset = rtl8168h_2_get_adc_bias_ioffset(tp);
+ if (ioffset != 0xffff)
+ phy_write_paged(phydev, 0x0bcf, 0x16, ioffset);
+
+ /* Modify rlen (TX LPF corner frequency) level */
+ data = phy_read_paged(phydev, 0x0bcd, 0x16);
+ data &= 0x000f;
+ rlen = 0;
+ if (data > 3)
+ rlen = data - 3;
+ data = rlen | (rlen << 4) | (rlen << 8) | (rlen << 12);
+ phy_write_paged(phydev, 0x0bcd, 0x17, data);
+
+ /* disable phy pfm mode */
+ phy_modify_paged(phydev, 0x0a44, 0x11, BIT(7), 0);
+
+ rtl8168g_disable_aldps(phydev);
+ rtl8168g_config_eee_phy(phydev);
+}
+
+static void rtl8168ep_1_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ /* Enable PHY auto speed down */
+ phy_modify_paged(phydev, 0x0a44, 0x11, 0, BIT(3) | BIT(2));
+
+ rtl8168g_phy_adjust_10m_aldps(phydev);
+
+ /* Enable EEE auto-fallback function */
+ phy_modify_paged(phydev, 0x0a4b, 0x11, 0, BIT(2));
+
+ /* Enable UC LPF tune function */
+ r8168g_phy_param(phydev, 0x8012, 0x0000, 0x8000);
+
+ /* set rg_sel_sdm_rate */
+ phy_modify_paged(phydev, 0x0c42, 0x11, BIT(13), BIT(14));
+
+ rtl8168g_disable_aldps(phydev);
+ rtl8168g_config_eee_phy(phydev);
+}
+
+static void rtl8168ep_2_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ rtl8168g_phy_adjust_10m_aldps(phydev);
+
+ /* Enable UC LPF tune function */
+ r8168g_phy_param(phydev, 0x8012, 0x0000, 0x8000);
+
+ /* Set rg_sel_sdm_rate */
+ phy_modify_paged(phydev, 0x0c42, 0x11, BIT(13), BIT(14));
+
+ /* Channel estimation parameters */
+ r8168g_phy_param(phydev, 0x80f3, 0xff00, 0x8b00);
+ r8168g_phy_param(phydev, 0x80f0, 0xff00, 0x3a00);
+ r8168g_phy_param(phydev, 0x80ef, 0xff00, 0x0500);
+ r8168g_phy_param(phydev, 0x80f6, 0xff00, 0x6e00);
+ r8168g_phy_param(phydev, 0x80ec, 0xff00, 0x6800);
+ r8168g_phy_param(phydev, 0x80ed, 0xff00, 0x7c00);
+ r8168g_phy_param(phydev, 0x80f2, 0xff00, 0xf400);
+ r8168g_phy_param(phydev, 0x80f4, 0xff00, 0x8500);
+ r8168g_phy_param(phydev, 0x8110, 0xff00, 0xa800);
+ r8168g_phy_param(phydev, 0x810f, 0xff00, 0x1d00);
+ r8168g_phy_param(phydev, 0x8111, 0xff00, 0xf500);
+ r8168g_phy_param(phydev, 0x8113, 0xff00, 0x6100);
+ r8168g_phy_param(phydev, 0x8115, 0xff00, 0x9200);
+ r8168g_phy_param(phydev, 0x810e, 0xff00, 0x0400);
+ r8168g_phy_param(phydev, 0x810c, 0xff00, 0x7c00);
+ r8168g_phy_param(phydev, 0x810b, 0xff00, 0x5a00);
+ r8168g_phy_param(phydev, 0x80d1, 0xff00, 0xff00);
+ r8168g_phy_param(phydev, 0x80cd, 0xff00, 0x9e00);
+ r8168g_phy_param(phydev, 0x80d3, 0xff00, 0x0e00);
+ r8168g_phy_param(phydev, 0x80d5, 0xff00, 0xca00);
+ r8168g_phy_param(phydev, 0x80d7, 0xff00, 0x8400);
+
+ /* Force PWM-mode */
+ phy_write(phydev, 0x1f, 0x0bcd);
+ phy_write(phydev, 0x14, 0x5065);
+ phy_write(phydev, 0x14, 0xd065);
+ phy_write(phydev, 0x1f, 0x0bc8);
+ phy_write(phydev, 0x12, 0x00ed);
+ phy_write(phydev, 0x1f, 0x0bcd);
+ phy_write(phydev, 0x14, 0x1065);
+ phy_write(phydev, 0x14, 0x9065);
+ phy_write(phydev, 0x14, 0x1065);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ rtl8168g_disable_aldps(phydev);
+ rtl8168g_config_eee_phy(phydev);
+}
+
+static void rtl8117_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ /* CHN EST parameters adjust - fnet */
+ r8168g_phy_param(phydev, 0x808e, 0xff00, 0x4800);
+ r8168g_phy_param(phydev, 0x8090, 0xff00, 0xcc00);
+ r8168g_phy_param(phydev, 0x8092, 0xff00, 0xb000);
+
+ r8168g_phy_param(phydev, 0x8088, 0xff00, 0x6000);
+ r8168g_phy_param(phydev, 0x808b, 0x3f00, 0x0b00);
+ r8168g_phy_param(phydev, 0x808d, 0x1f00, 0x0600);
+ r8168g_phy_param(phydev, 0x808c, 0xff00, 0xb000);
+ r8168g_phy_param(phydev, 0x80a0, 0xff00, 0x2800);
+ r8168g_phy_param(phydev, 0x80a2, 0xff00, 0x5000);
+ r8168g_phy_param(phydev, 0x809b, 0xf800, 0xb000);
+ r8168g_phy_param(phydev, 0x809a, 0xff00, 0x4b00);
+ r8168g_phy_param(phydev, 0x809d, 0x3f00, 0x0800);
+ r8168g_phy_param(phydev, 0x80a1, 0xff00, 0x7000);
+ r8168g_phy_param(phydev, 0x809f, 0x1f00, 0x0300);
+ r8168g_phy_param(phydev, 0x809e, 0xff00, 0x8800);
+ r8168g_phy_param(phydev, 0x80b2, 0xff00, 0x2200);
+ r8168g_phy_param(phydev, 0x80ad, 0xf800, 0x9800);
+ r8168g_phy_param(phydev, 0x80af, 0x3f00, 0x0800);
+ r8168g_phy_param(phydev, 0x80b3, 0xff00, 0x6f00);
+ r8168g_phy_param(phydev, 0x80b1, 0x1f00, 0x0300);
+ r8168g_phy_param(phydev, 0x80b0, 0xff00, 0x9300);
+
+ r8168g_phy_param(phydev, 0x8011, 0x0000, 0x0800);
+
+ /* enable GPHY 10M */
+ phy_modify_paged(phydev, 0x0a44, 0x11, 0, BIT(11));
+
+ r8168g_phy_param(phydev, 0x8016, 0x0000, 0x0400);
+
+ rtl8168g_disable_aldps(phydev);
+ rtl8168h_config_eee_phy(phydev);
+}
+
+static void rtl8102e_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ static const struct phy_reg phy_reg_init[] = {
+ { 0x1f, 0x0003 },
+ { 0x08, 0x441d },
+ { 0x01, 0x9100 },
+ { 0x1f, 0x0000 }
+ };
+
+ phy_set_bits(phydev, 0x11, BIT(12));
+ phy_set_bits(phydev, 0x19, BIT(13));
+ phy_set_bits(phydev, 0x10, BIT(15));
+
+ rtl_writephy_batch(phydev, phy_reg_init);
+}
+
+static void rtl8105e_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ /* Disable ALDPS before ram code */
+ phy_write(phydev, 0x18, 0x0310);
+ msleep(100);
+
+ r8169_apply_firmware(tp);
+
+ phy_write_paged(phydev, 0x0005, 0x1a, 0x0000);
+ phy_write_paged(phydev, 0x0004, 0x1c, 0x0000);
+ phy_write_paged(phydev, 0x0001, 0x15, 0x7701);
+}
+
+static void rtl8402_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ /* Disable ALDPS before setting firmware */
+ phy_write(phydev, 0x18, 0x0310);
+ msleep(20);
+
+ r8169_apply_firmware(tp);
+
+ /* EEE setting */
+ phy_write(phydev, 0x1f, 0x0004);
+ phy_write(phydev, 0x10, 0x401f);
+ phy_write(phydev, 0x19, 0x7030);
+ phy_write(phydev, 0x1f, 0x0000);
+}
+
+static void rtl8106e_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ static const struct phy_reg phy_reg_init[] = {
+ { 0x1f, 0x0004 },
+ { 0x10, 0xc07f },
+ { 0x19, 0x7030 },
+ { 0x1f, 0x0000 }
+ };
+
+ /* Disable ALDPS before ram code */
+ phy_write(phydev, 0x18, 0x0310);
+ msleep(100);
+
+ r8169_apply_firmware(tp);
+
+ rtl_writephy_batch(phydev, phy_reg_init);
+}
+
+static void rtl8125_1_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ phy_modify_paged(phydev, 0xad4, 0x10, 0x03ff, 0x0084);
+ phy_modify_paged(phydev, 0xad4, 0x17, 0x0000, 0x0010);
+ phy_modify_paged(phydev, 0xad1, 0x13, 0x03ff, 0x0006);
+ phy_modify_paged(phydev, 0xad3, 0x11, 0x003f, 0x0006);
+ phy_modify_paged(phydev, 0xac0, 0x14, 0x0000, 0x1100);
+ phy_modify_paged(phydev, 0xac8, 0x15, 0xf000, 0x7000);
+ phy_modify_paged(phydev, 0xad1, 0x14, 0x0000, 0x0400);
+ phy_modify_paged(phydev, 0xad1, 0x15, 0x0000, 0x03ff);
+ phy_modify_paged(phydev, 0xad1, 0x16, 0x0000, 0x03ff);
+
+ r8168g_phy_param(phydev, 0x80ea, 0xff00, 0xc400);
+ r8168g_phy_param(phydev, 0x80eb, 0x0700, 0x0300);
+ r8168g_phy_param(phydev, 0x80f8, 0xff00, 0x1c00);
+ r8168g_phy_param(phydev, 0x80f1, 0xff00, 0x3000);
+ r8168g_phy_param(phydev, 0x80fe, 0xff00, 0xa500);
+ r8168g_phy_param(phydev, 0x8102, 0xff00, 0x5000);
+ r8168g_phy_param(phydev, 0x8105, 0xff00, 0x3300);
+ r8168g_phy_param(phydev, 0x8100, 0xff00, 0x7000);
+ r8168g_phy_param(phydev, 0x8104, 0xff00, 0xf000);
+ r8168g_phy_param(phydev, 0x8106, 0xff00, 0x6500);
+ r8168g_phy_param(phydev, 0x80dc, 0xff00, 0xed00);
+ r8168g_phy_param(phydev, 0x80df, 0x0000, 0x0100);
+ r8168g_phy_param(phydev, 0x80e1, 0x0100, 0x0000);
+
+ phy_modify_paged(phydev, 0xbf0, 0x13, 0x003f, 0x0038);
+ r8168g_phy_param(phydev, 0x819f, 0xffff, 0xd0b6);
+
+ phy_write_paged(phydev, 0xbc3, 0x12, 0x5555);
+ phy_modify_paged(phydev, 0xbf0, 0x15, 0x0e00, 0x0a00);
+ phy_modify_paged(phydev, 0xa5c, 0x10, 0x0400, 0x0000);
+ phy_modify_paged(phydev, 0xa44, 0x11, 0x0000, 0x0800);
+
+ rtl8125_config_eee_phy(phydev);
+}
+
+static void rtl8125_2_hw_phy_config(struct rtl8169_private *tp,
+ struct phy_device *phydev)
+{
+ int i;
+
+ phy_modify_paged(phydev, 0xad4, 0x17, 0x0000, 0x0010);
+ phy_modify_paged(phydev, 0xad1, 0x13, 0x03ff, 0x03ff);
+ phy_modify_paged(phydev, 0xad3, 0x11, 0x003f, 0x0006);
+ phy_modify_paged(phydev, 0xac0, 0x14, 0x1100, 0x0000);
+ phy_modify_paged(phydev, 0xacc, 0x10, 0x0003, 0x0002);
+ phy_modify_paged(phydev, 0xad4, 0x10, 0x00e7, 0x0044);
+ phy_modify_paged(phydev, 0xac1, 0x12, 0x0080, 0x0000);
+ phy_modify_paged(phydev, 0xac8, 0x10, 0x0300, 0x0000);
+ phy_modify_paged(phydev, 0xac5, 0x17, 0x0007, 0x0002);
+ phy_write_paged(phydev, 0xad4, 0x16, 0x00a8);
+ phy_write_paged(phydev, 0xac5, 0x16, 0x01ff);
+ phy_modify_paged(phydev, 0xac8, 0x15, 0x00f0, 0x0030);
+
+ phy_write(phydev, 0x1f, 0x0b87);
+ phy_write(phydev, 0x16, 0x80a2);
+ phy_write(phydev, 0x17, 0x0153);
+ phy_write(phydev, 0x16, 0x809c);
+ phy_write(phydev, 0x17, 0x0153);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ phy_write(phydev, 0x1f, 0x0a43);
+ phy_write(phydev, 0x13, 0x81B3);
+ phy_write(phydev, 0x14, 0x0043);
+ phy_write(phydev, 0x14, 0x00A7);
+ phy_write(phydev, 0x14, 0x00D6);
+ phy_write(phydev, 0x14, 0x00EC);
+ phy_write(phydev, 0x14, 0x00F6);
+ phy_write(phydev, 0x14, 0x00FB);
+ phy_write(phydev, 0x14, 0x00FD);
+ phy_write(phydev, 0x14, 0x00FF);
+ phy_write(phydev, 0x14, 0x00BB);
+ phy_write(phydev, 0x14, 0x0058);
+ phy_write(phydev, 0x14, 0x0029);
+ phy_write(phydev, 0x14, 0x0013);
+ phy_write(phydev, 0x14, 0x0009);
+ phy_write(phydev, 0x14, 0x0004);
+ phy_write(phydev, 0x14, 0x0002);
+ for (i = 0; i < 25; i++)
+ phy_write(phydev, 0x14, 0x0000);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ r8168g_phy_param(phydev, 0x8257, 0xffff, 0x020F);
+ r8168g_phy_param(phydev, 0x80ea, 0xffff, 0x7843);
+
+ r8169_apply_firmware(tp);
+
+ phy_modify_paged(phydev, 0xd06, 0x14, 0x0000, 0x2000);
+
+ r8168g_phy_param(phydev, 0x81a2, 0x0000, 0x0100);
+
+ phy_modify_paged(phydev, 0xb54, 0x16, 0xff00, 0xdb00);
+ phy_modify_paged(phydev, 0xa45, 0x12, 0x0001, 0x0000);
+ phy_modify_paged(phydev, 0xa5d, 0x12, 0x0000, 0x0020);
+ phy_modify_paged(phydev, 0xad4, 0x17, 0x0010, 0x0000);
+ phy_modify_paged(phydev, 0xa86, 0x15, 0x0001, 0x0000);
+ phy_modify_paged(phydev, 0xa44, 0x11, 0x0000, 0x0800);
+
+ rtl8125_config_eee_phy(phydev);
+}
+
+void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
+ enum mac_version ver)
+{
+ static const rtl_phy_cfg_fct phy_configs[] = {
+ /* PCI devices. */
+ [RTL_GIGA_MAC_VER_02] = rtl8169s_hw_phy_config,
+ [RTL_GIGA_MAC_VER_03] = rtl8169s_hw_phy_config,
+ [RTL_GIGA_MAC_VER_04] = rtl8169sb_hw_phy_config,
+ [RTL_GIGA_MAC_VER_05] = rtl8169scd_hw_phy_config,
+ [RTL_GIGA_MAC_VER_06] = rtl8169sce_hw_phy_config,
+ /* PCI-E devices. */
+ [RTL_GIGA_MAC_VER_07] = rtl8102e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_08] = rtl8102e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_09] = rtl8102e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_10] = NULL,
+ [RTL_GIGA_MAC_VER_11] = rtl8168bb_hw_phy_config,
+ [RTL_GIGA_MAC_VER_12] = rtl8168bef_hw_phy_config,
+ [RTL_GIGA_MAC_VER_13] = NULL,
+ [RTL_GIGA_MAC_VER_14] = NULL,
+ [RTL_GIGA_MAC_VER_15] = NULL,
+ [RTL_GIGA_MAC_VER_16] = NULL,
+ [RTL_GIGA_MAC_VER_17] = rtl8168bef_hw_phy_config,
+ [RTL_GIGA_MAC_VER_18] = rtl8168cp_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_19] = rtl8168c_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_20] = rtl8168c_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_21] = rtl8168c_3_hw_phy_config,
+ [RTL_GIGA_MAC_VER_22] = rtl8168c_3_hw_phy_config,
+ [RTL_GIGA_MAC_VER_23] = rtl8168cp_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_24] = rtl8168cp_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_25] = rtl8168d_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_26] = rtl8168d_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_27] = rtl8168d_3_hw_phy_config,
+ [RTL_GIGA_MAC_VER_28] = rtl8168d_4_hw_phy_config,
+ [RTL_GIGA_MAC_VER_29] = rtl8105e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_30] = rtl8105e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_31] = NULL,
+ [RTL_GIGA_MAC_VER_32] = rtl8168e_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_33] = rtl8168e_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_34] = rtl8168e_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_35] = rtl8168f_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_36] = rtl8168f_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_37] = rtl8402_hw_phy_config,
+ [RTL_GIGA_MAC_VER_38] = rtl8411_hw_phy_config,
+ [RTL_GIGA_MAC_VER_39] = rtl8106e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_40] = rtl8168g_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_41] = NULL,
+ [RTL_GIGA_MAC_VER_42] = rtl8168g_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_43] = rtl8168g_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_44] = rtl8168g_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_45] = rtl8168h_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_46] = rtl8168h_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_47] = rtl8168h_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_48] = rtl8168h_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_49] = rtl8168ep_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_50] = rtl8168ep_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_51] = rtl8168ep_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_52] = rtl8117_hw_phy_config,
+ [RTL_GIGA_MAC_VER_60] = rtl8125_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_61] = rtl8125_2_hw_phy_config,
+ };
+
+ if (phy_configs[ver])
+ phy_configs[ver](tp, phydev);
+}
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index cdd8ab2e..58ca126 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2204,24 +2204,28 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf)
if (cd->tsu) {
add_tsu_reg(ARSTR);
add_tsu_reg(TSU_CTRST);
- add_tsu_reg(TSU_FWEN0);
- add_tsu_reg(TSU_FWEN1);
- add_tsu_reg(TSU_FCM);
- add_tsu_reg(TSU_BSYSL0);
- add_tsu_reg(TSU_BSYSL1);
- add_tsu_reg(TSU_PRISL0);
- add_tsu_reg(TSU_PRISL1);
- add_tsu_reg(TSU_FWSL0);
- add_tsu_reg(TSU_FWSL1);
+ if (cd->dual_port) {
+ add_tsu_reg(TSU_FWEN0);
+ add_tsu_reg(TSU_FWEN1);
+ add_tsu_reg(TSU_FCM);
+ add_tsu_reg(TSU_BSYSL0);
+ add_tsu_reg(TSU_BSYSL1);
+ add_tsu_reg(TSU_PRISL0);
+ add_tsu_reg(TSU_PRISL1);
+ add_tsu_reg(TSU_FWSL0);
+ add_tsu_reg(TSU_FWSL1);
+ }
add_tsu_reg(TSU_FWSLC);
- add_tsu_reg(TSU_QTAGM0);
- add_tsu_reg(TSU_QTAGM1);
- add_tsu_reg(TSU_FWSR);
- add_tsu_reg(TSU_FWINMK);
- add_tsu_reg(TSU_ADQT0);
- add_tsu_reg(TSU_ADQT1);
- add_tsu_reg(TSU_VTAG0);
- add_tsu_reg(TSU_VTAG1);
+ if (cd->dual_port) {
+ add_tsu_reg(TSU_QTAGM0);
+ add_tsu_reg(TSU_QTAGM1);
+ add_tsu_reg(TSU_FWSR);
+ add_tsu_reg(TSU_FWINMK);
+ add_tsu_reg(TSU_ADQT0);
+ add_tsu_reg(TSU_ADQT1);
+ add_tsu_reg(TSU_VTAG0);
+ add_tsu_reg(TSU_VTAG1);
+ }
add_tsu_reg(TSU_ADSBSY);
add_tsu_reg(TSU_TEN);
add_tsu_reg(TSU_POST1);
@@ -2643,20 +2647,6 @@ static int sh_eth_close(struct net_device *ndev)
return 0;
}
-/* ioctl to device function */
-static int sh_eth_do_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
-{
- struct phy_device *phydev = ndev->phydev;
-
- if (!netif_running(ndev))
- return -EINVAL;
-
- if (!phydev)
- return -ENODEV;
-
- return phy_mii_ioctl(phydev, rq, cmd);
-}
-
static int sh_eth_change_mtu(struct net_device *ndev, int new_mtu)
{
if (netif_running(ndev))
@@ -3155,7 +3145,7 @@ static const struct net_device_ops sh_eth_netdev_ops = {
.ndo_get_stats = sh_eth_get_stats,
.ndo_set_rx_mode = sh_eth_set_rx_mode,
.ndo_tx_timeout = sh_eth_tx_timeout,
- .ndo_do_ioctl = sh_eth_do_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_change_mtu = sh_eth_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
@@ -3171,7 +3161,7 @@ static const struct net_device_ops sh_eth_netdev_ops_tsu = {
.ndo_vlan_rx_add_vid = sh_eth_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = sh_eth_vlan_rx_kill_vid,
.ndo_tx_timeout = sh_eth_tx_timeout,
- .ndo_do_ioctl = sh_eth_do_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_change_mtu = sh_eth_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index cd6e0de..c705743 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -1939,9 +1939,7 @@ static int sxgbe_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
case SIOCGMIIPHY:
case SIOCGMIIREG:
case SIOCSMIIREG:
- if (!dev->phydev)
- return -EINVAL;
- ret = phy_mii_ioctl(dev->phydev, rq, cmd);
+ ret = phy_do_ioctl(dev, rq, cmd);
break;
default:
break;
@@ -2296,7 +2294,7 @@ __setup("sxgbeeth=", sxgbe_cmdline_opt);
-MODULE_DESCRIPTION("SAMSUNG 10G/2.5G/1G Ethernet PLATFORM driver");
+MODULE_DESCRIPTION("Samsung 10G/2.5G/1G Ethernet PLATFORM driver");
MODULE_PARM_DESC(debug, "Message Level (-1: default, 0: no output, 16: all)");
MODULE_PARM_DESC(eee_timer, "EEE-LPI Default LS timer value");
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index c5c297e..890fd65 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -1,7 +1,10 @@
# SPDX-License-Identifier: GPL-2.0
-sfc-y += efx.o nic.o farch.o siena.o ef10.o tx.o rx.o \
- selftest.o ethtool.o ptp.o tx_tso.o \
- mcdi.o mcdi_port.o mcdi_mon.o
+sfc-y += efx.o efx_common.o efx_channels.o nic.o \
+ farch.o siena.o ef10.o \
+ tx.o tx_common.o tx_tso.o rx.o rx_common.o \
+ selftest.o ethtool.o ethtool_common.o ptp.o \
+ mcdi.o mcdi_port.o mcdi_port_common.o \
+ mcdi_functions.o mcdi_mon.o
sfc-$(CONFIG_SFC_MTD) += mtd.o
sfc-$(CONFIG_SFC_SRIOV) += sriov.o siena_sriov.o ef10_sriov.o
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 4d9bbcc..4997f61 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -5,10 +5,13 @@
*/
#include "net_driver.h"
+#include "rx_common.h"
#include "ef10_regs.h"
#include "io.h"
#include "mcdi.h"
#include "mcdi_pcol.h"
+#include "mcdi_port_common.h"
+#include "mcdi_functions.h"
#include "nic.h"
#include "workarounds.h"
#include "selftest.h"
@@ -185,24 +188,6 @@ static bool efx_ef10_is_vf(struct efx_nic *efx)
return efx->type->is_vf;
}
-static int efx_ef10_get_pf_index(struct efx_nic *efx)
-{
- MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_FUNCTION_INFO_OUT_LEN);
- struct efx_ef10_nic_data *nic_data = efx->nic_data;
- size_t outlen;
- int rc;
-
- rc = efx_mcdi_rpc(efx, MC_CMD_GET_FUNCTION_INFO, NULL, 0, outbuf,
- sizeof(outbuf), &outlen);
- if (rc)
- return rc;
- if (outlen < sizeof(outbuf))
- return -EIO;
-
- nic_data->pf_index = MCDI_DWORD(outbuf, GET_FUNCTION_INFO_OUT_PF);
- return 0;
-}
-
#ifdef CONFIG_SFC_SRIOV
static int efx_ef10_get_vf_index(struct efx_nic *efx)
{
@@ -273,24 +258,9 @@ static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
u8 vi_window_mode = MCDI_BYTE(outbuf,
GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE);
- switch (vi_window_mode) {
- case MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_8K:
- efx->vi_stride = 8192;
- break;
- case MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_16K:
- efx->vi_stride = 16384;
- break;
- case MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_64K:
- efx->vi_stride = 65536;
- break;
- default:
- netif_err(efx, probe, efx->net_dev,
- "Unrecognised VI window mode %d\n",
- vi_window_mode);
- return -EIO;
- }
- netif_dbg(efx, probe, efx->net_dev, "vi_stride = %u\n",
- efx->vi_stride);
+ rc = efx_mcdi_window_mode_to_stride(efx, vi_window_mode);
+ if (rc)
+ return rc;
} else {
/* keep default VI stride */
netif_dbg(efx, probe, efx->net_dev,
@@ -689,7 +659,7 @@ static int efx_ef10_probe(struct efx_nic *efx)
}
nic_data->warm_boot_count = rc;
- efx->rss_context.context_id = EFX_EF10_RSS_CONTEXT_INVALID;
+ efx->rss_context.context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
nic_data->vport_id = EVB_PORT_ID_ASSIGNED;
@@ -725,7 +695,7 @@ static int efx_ef10_probe(struct efx_nic *efx)
if (rc)
goto fail4;
- rc = efx_ef10_get_pf_index(efx);
+ rc = efx_get_pf_index(efx, &nic_data->pf_index);
if (rc)
goto fail5;
@@ -831,22 +801,6 @@ static int efx_ef10_probe(struct efx_nic *efx)
return rc;
}
-static int efx_ef10_free_vis(struct efx_nic *efx)
-{
- MCDI_DECLARE_BUF_ERR(outbuf);
- size_t outlen;
- int rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FREE_VIS, NULL, 0,
- outbuf, sizeof(outbuf), &outlen);
-
- /* -EALREADY means nothing to free, so ignore */
- if (rc == -EALREADY)
- rc = 0;
- if (rc)
- efx_mcdi_display_error(efx, MC_CMD_FREE_VIS, 0, outbuf, outlen,
- rc);
- return rc;
-}
-
#ifdef EFX_USE_PIO
static void efx_ef10_free_piobufs(struct efx_nic *efx)
@@ -1089,7 +1043,7 @@ static void efx_ef10_remove(struct efx_nic *efx)
if (nic_data->wc_membase)
iounmap(nic_data->wc_membase);
- rc = efx_ef10_free_vis(efx);
+ rc = efx_mcdi_free_vis(efx);
WARN_ON(rc != 0);
if (!nic_data->must_restore_piobufs)
@@ -1260,28 +1214,10 @@ static int efx_ef10_probe_vf(struct efx_nic *efx __attribute__ ((unused)))
static int efx_ef10_alloc_vis(struct efx_nic *efx,
unsigned int min_vis, unsigned int max_vis)
{
- MCDI_DECLARE_BUF(inbuf, MC_CMD_ALLOC_VIS_IN_LEN);
- MCDI_DECLARE_BUF(outbuf, MC_CMD_ALLOC_VIS_OUT_LEN);
struct efx_ef10_nic_data *nic_data = efx->nic_data;
- size_t outlen;
- int rc;
- MCDI_SET_DWORD(inbuf, ALLOC_VIS_IN_MIN_VI_COUNT, min_vis);
- MCDI_SET_DWORD(inbuf, ALLOC_VIS_IN_MAX_VI_COUNT, max_vis);
- rc = efx_mcdi_rpc(efx, MC_CMD_ALLOC_VIS, inbuf, sizeof(inbuf),
- outbuf, sizeof(outbuf), &outlen);
- if (rc != 0)
- return rc;
-
- if (outlen < MC_CMD_ALLOC_VIS_OUT_LEN)
- return -EIO;
-
- netif_dbg(efx, drv, efx->net_dev, "base VI is A0x%03x\n",
- MCDI_DWORD(outbuf, ALLOC_VIS_OUT_VI_BASE));
-
- nic_data->vi_base = MCDI_DWORD(outbuf, ALLOC_VIS_OUT_VI_BASE);
- nic_data->n_allocated_vis = MCDI_DWORD(outbuf, ALLOC_VIS_OUT_VI_COUNT);
- return 0;
+ return efx_mcdi_alloc_vis(efx, min_vis, max_vis, &nic_data->vi_base,
+ &nic_data->n_allocated_vis);
}
/* Note that the failure path of this function does not free
@@ -1363,7 +1299,7 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx)
}
/* In case the last attached driver failed to free VIs, do it now */
- rc = efx_ef10_free_vis(efx);
+ rc = efx_mcdi_free_vis(efx);
if (rc != 0)
return rc;
@@ -1384,7 +1320,7 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx)
efx->max_tx_channels =
nic_data->n_allocated_vis / EFX_TXQ_TYPES;
- efx_ef10_free_vis(efx);
+ efx_mcdi_free_vis(efx);
return -EAGAIN;
}
@@ -1503,7 +1439,7 @@ static void efx_ef10_reset_mc_allocations(struct efx_nic *efx)
nic_data->must_restore_filters = true;
nic_data->must_restore_piobufs = true;
efx_ef10_forget_old_piobufs(efx);
- efx->rss_context.context_id = EFX_EF10_RSS_CONTEXT_INVALID;
+ efx->rss_context.context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
/* Driver-created vswitches and vports must be re-created */
nic_data->must_probe_vswitching = true;
@@ -2408,20 +2344,15 @@ static u32 efx_ef10_tso_versions(struct efx_nic *efx)
static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
{
- MCDI_DECLARE_BUF(inbuf, MC_CMD_INIT_TXQ_IN_LEN(EFX_MAX_DMAQ_SIZE * 8 /
- EFX_BUF_SIZE));
bool csum_offload = tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD;
- size_t entries = tx_queue->txd.buf.len / EFX_BUF_SIZE;
struct efx_channel *channel = tx_queue->channel;
struct efx_nic *efx = tx_queue->efx;
- struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ struct efx_ef10_nic_data *nic_data;
bool tso_v2 = false;
- size_t inlen;
- dma_addr_t dma_addr;
efx_qword_t *txd;
int rc;
- int i;
- BUILD_BUG_ON(MC_CMD_INIT_TXQ_OUT_LEN != 0);
+
+ nic_data = efx->nic_data;
/* Only attempt to enable TX timestamping if we have the license for it,
* otherwise TXQ init will fail
@@ -2448,51 +2379,9 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
channel->channel);
}
- MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_SIZE, tx_queue->ptr_mask + 1);
- MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_TARGET_EVQ, channel->channel);
- MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_LABEL, tx_queue->queue);
- MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_INSTANCE, tx_queue->queue);
- MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_OWNER_ID, 0);
- MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_PORT_ID, nic_data->vport_id);
-
- dma_addr = tx_queue->txd.buf.dma_addr;
-
- netif_dbg(efx, hw, efx->net_dev, "pushing TXQ %d. %zu entries (%llx)\n",
- tx_queue->queue, entries, (u64)dma_addr);
-
- for (i = 0; i < entries; ++i) {
- MCDI_SET_ARRAY_QWORD(inbuf, INIT_TXQ_IN_DMA_ADDR, i, dma_addr);
- dma_addr += EFX_BUF_SIZE;
- }
-
- inlen = MC_CMD_INIT_TXQ_IN_LEN(entries);
-
- do {
- MCDI_POPULATE_DWORD_4(inbuf, INIT_TXQ_IN_FLAGS,
- /* This flag was removed from mcdi_pcol.h for
- * the non-_EXT version of INIT_TXQ. However,
- * firmware still honours it.
- */
- INIT_TXQ_EXT_IN_FLAG_TSOV2_EN, tso_v2,
- INIT_TXQ_IN_FLAG_IP_CSUM_DIS, !csum_offload,
- INIT_TXQ_IN_FLAG_TCP_CSUM_DIS, !csum_offload,
- INIT_TXQ_EXT_IN_FLAG_TIMESTAMP,
- tx_queue->timestamping);
-
- rc = efx_mcdi_rpc_quiet(efx, MC_CMD_INIT_TXQ, inbuf, inlen,
- NULL, 0, NULL);
- if (rc == -ENOSPC && tso_v2) {
- /* Retry without TSOv2 if we're short on contexts. */
- tso_v2 = false;
- netif_warn(efx, probe, efx->net_dev,
- "TSOv2 context not available to segment in hardware. TCP performance may be reduced.\n");
- } else if (rc) {
- efx_mcdi_display_error(efx, MC_CMD_INIT_TXQ,
- MC_CMD_INIT_TXQ_EXT_IN_LEN,
- NULL, 0, rc);
- goto fail;
- }
- } while (rc);
+ rc = efx_mcdi_tx_init(tx_queue, tso_v2);
+ if (rc)
+ goto fail;
/* A previous user of this TX queue might have set us up the
* bomb by writing a descriptor to the TX push collector but
@@ -2530,35 +2419,6 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
tx_queue->queue);
}
-static void efx_ef10_tx_fini(struct efx_tx_queue *tx_queue)
-{
- MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_TXQ_IN_LEN);
- MCDI_DECLARE_BUF_ERR(outbuf);
- struct efx_nic *efx = tx_queue->efx;
- size_t outlen;
- int rc;
-
- MCDI_SET_DWORD(inbuf, FINI_TXQ_IN_INSTANCE,
- tx_queue->queue);
-
- rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_TXQ, inbuf, sizeof(inbuf),
- outbuf, sizeof(outbuf), &outlen);
-
- if (rc && rc != -EALREADY)
- goto fail;
-
- return;
-
-fail:
- efx_mcdi_display_error(efx, MC_CMD_FINI_TXQ, MC_CMD_FINI_TXQ_IN_LEN,
- outbuf, outlen, rc);
-}
-
-static void efx_ef10_tx_remove(struct efx_tx_queue *tx_queue)
-{
- efx_nic_free_buffer(tx_queue->efx, &tx_queue->txd.buf);
-}
-
/* This writes to the TX_DESC_WPTR; write pointer for TX descriptor ring */
static inline void efx_ef10_notify_tx_desc(struct efx_tx_queue *tx_queue)
{
@@ -2737,7 +2597,7 @@ static int efx_ef10_alloc_rss_context(struct efx_nic *efx, bool exclusive,
EFX_EF10_MAX_SHARED_RSS_CONTEXT_SIZE);
if (!exclusive && rss_spread == 1) {
- ctx->context_id = EFX_EF10_RSS_CONTEXT_INVALID;
+ ctx->context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
if (context_size)
*context_size = 1;
return 0;
@@ -2824,11 +2684,11 @@ static void efx_ef10_rx_free_indir_table(struct efx_nic *efx)
{
int rc;
- if (efx->rss_context.context_id != EFX_EF10_RSS_CONTEXT_INVALID) {
+ if (efx->rss_context.context_id != EFX_MCDI_RSS_CONTEXT_INVALID) {
rc = efx_ef10_free_rss_context(efx, efx->rss_context.context_id);
WARN_ON(rc != 0);
}
- efx->rss_context.context_id = EFX_EF10_RSS_CONTEXT_INVALID;
+ efx->rss_context.context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
}
static int efx_ef10_rx_push_shared_rss_config(struct efx_nic *efx,
@@ -2854,7 +2714,7 @@ static int efx_ef10_rx_push_exclusive_rss_config(struct efx_nic *efx,
struct efx_ef10_nic_data *nic_data = efx->nic_data;
int rc;
- if (efx->rss_context.context_id == EFX_EF10_RSS_CONTEXT_INVALID ||
+ if (efx->rss_context.context_id == EFX_MCDI_RSS_CONTEXT_INVALID ||
!nic_data->rx_rss_context_exclusive) {
rc = efx_ef10_alloc_rss_context(efx, true, &efx->rss_context,
NULL);
@@ -2870,7 +2730,7 @@ static int efx_ef10_rx_push_exclusive_rss_config(struct efx_nic *efx,
goto fail2;
if (efx->rss_context.context_id != old_rx_rss_context &&
- old_rx_rss_context != EFX_EF10_RSS_CONTEXT_INVALID)
+ old_rx_rss_context != EFX_MCDI_RSS_CONTEXT_INVALID)
WARN_ON(efx_ef10_free_rss_context(efx, old_rx_rss_context) != 0);
nic_data->rx_rss_context_exclusive = true;
if (rx_indir_table != efx->rss_context.rx_indir_table)
@@ -2901,7 +2761,7 @@ static int efx_ef10_rx_push_rss_context_config(struct efx_nic *efx,
WARN_ON(!mutex_is_locked(&efx->rss_lock));
- if (ctx->context_id == EFX_EF10_RSS_CONTEXT_INVALID) {
+ if (ctx->context_id == EFX_MCDI_RSS_CONTEXT_INVALID) {
rc = efx_ef10_alloc_rss_context(efx, true, ctx, NULL);
if (rc)
return rc;
@@ -2936,7 +2796,7 @@ static int efx_ef10_rx_pull_rss_context_config(struct efx_nic *efx,
BUILD_BUG_ON(MC_CMD_RSS_CONTEXT_GET_TABLE_IN_LEN !=
MC_CMD_RSS_CONTEXT_GET_KEY_IN_LEN);
- if (ctx->context_id == EFX_EF10_RSS_CONTEXT_INVALID)
+ if (ctx->context_id == EFX_MCDI_RSS_CONTEXT_INVALID)
return -ENOENT;
MCDI_SET_DWORD(inbuf, RSS_CONTEXT_GET_TABLE_IN_RSS_CONTEXT_ID,
@@ -2997,7 +2857,7 @@ static void efx_ef10_rx_restore_rss_contexts(struct efx_nic *efx)
list_for_each_entry(ctx, &efx->rss_context.list, list) {
/* previous NIC RSS context is gone */
- ctx->context_id = EFX_EF10_RSS_CONTEXT_INVALID;
+ ctx->context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
/* so try to allocate a new one */
rc = efx_ef10_rx_push_rss_context_config(efx, ctx,
ctx->rx_indir_table,
@@ -3068,96 +2928,11 @@ static int efx_ef10_vf_rx_push_rss_config(struct efx_nic *efx, bool user,
{
if (user)
return -EOPNOTSUPP;
- if (efx->rss_context.context_id != EFX_EF10_RSS_CONTEXT_INVALID)
+ if (efx->rss_context.context_id != EFX_MCDI_RSS_CONTEXT_INVALID)
return 0;
return efx_ef10_rx_push_shared_rss_config(efx, NULL);
}
-static int efx_ef10_rx_probe(struct efx_rx_queue *rx_queue)
-{
- return efx_nic_alloc_buffer(rx_queue->efx, &rx_queue->rxd.buf,
- (rx_queue->ptr_mask + 1) *
- sizeof(efx_qword_t),
- GFP_KERNEL);
-}
-
-static void efx_ef10_rx_init(struct efx_rx_queue *rx_queue)
-{
- MCDI_DECLARE_BUF(inbuf,
- MC_CMD_INIT_RXQ_IN_LEN(EFX_MAX_DMAQ_SIZE * 8 /
- EFX_BUF_SIZE));
- struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
- size_t entries = rx_queue->rxd.buf.len / EFX_BUF_SIZE;
- struct efx_nic *efx = rx_queue->efx;
- struct efx_ef10_nic_data *nic_data = efx->nic_data;
- size_t inlen;
- dma_addr_t dma_addr;
- int rc;
- int i;
- BUILD_BUG_ON(MC_CMD_INIT_RXQ_OUT_LEN != 0);
-
- rx_queue->scatter_n = 0;
- rx_queue->scatter_len = 0;
-
- MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_SIZE, rx_queue->ptr_mask + 1);
- MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_TARGET_EVQ, channel->channel);
- MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_LABEL, efx_rx_queue_index(rx_queue));
- MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_INSTANCE,
- efx_rx_queue_index(rx_queue));
- MCDI_POPULATE_DWORD_2(inbuf, INIT_RXQ_IN_FLAGS,
- INIT_RXQ_IN_FLAG_PREFIX, 1,
- INIT_RXQ_IN_FLAG_TIMESTAMP, 1);
- MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_OWNER_ID, 0);
- MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_PORT_ID, nic_data->vport_id);
-
- dma_addr = rx_queue->rxd.buf.dma_addr;
-
- netif_dbg(efx, hw, efx->net_dev, "pushing RXQ %d. %zu entries (%llx)\n",
- efx_rx_queue_index(rx_queue), entries, (u64)dma_addr);
-
- for (i = 0; i < entries; ++i) {
- MCDI_SET_ARRAY_QWORD(inbuf, INIT_RXQ_IN_DMA_ADDR, i, dma_addr);
- dma_addr += EFX_BUF_SIZE;
- }
-
- inlen = MC_CMD_INIT_RXQ_IN_LEN(entries);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_INIT_RXQ, inbuf, inlen,
- NULL, 0, NULL);
- if (rc)
- netdev_WARN(efx->net_dev, "failed to initialise RXQ %d\n",
- efx_rx_queue_index(rx_queue));
-}
-
-static void efx_ef10_rx_fini(struct efx_rx_queue *rx_queue)
-{
- MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_RXQ_IN_LEN);
- MCDI_DECLARE_BUF_ERR(outbuf);
- struct efx_nic *efx = rx_queue->efx;
- size_t outlen;
- int rc;
-
- MCDI_SET_DWORD(inbuf, FINI_RXQ_IN_INSTANCE,
- efx_rx_queue_index(rx_queue));
-
- rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_RXQ, inbuf, sizeof(inbuf),
- outbuf, sizeof(outbuf), &outlen);
-
- if (rc && rc != -EALREADY)
- goto fail;
-
- return;
-
-fail:
- efx_mcdi_display_error(efx, MC_CMD_FINI_RXQ, MC_CMD_FINI_RXQ_IN_LEN,
- outbuf, outlen, rc);
-}
-
-static void efx_ef10_rx_remove(struct efx_rx_queue *rx_queue)
-{
- efx_nic_free_buffer(rx_queue->efx, &rx_queue->rxd.buf);
-}
-
/* This creates an entry in the RX descriptor queue */
static inline void
efx_ef10_build_rx_desc(struct efx_rx_queue *rx_queue, unsigned int index)
@@ -3229,106 +3004,20 @@ efx_ef10_rx_defer_refill_complete(struct efx_nic *efx, unsigned long cookie,
/* nothing to do */
}
-static int efx_ef10_ev_probe(struct efx_channel *channel)
-{
- return efx_nic_alloc_buffer(channel->efx, &channel->eventq.buf,
- (channel->eventq_mask + 1) *
- sizeof(efx_qword_t),
- GFP_KERNEL);
-}
-
-static void efx_ef10_ev_fini(struct efx_channel *channel)
-{
- MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_EVQ_IN_LEN);
- MCDI_DECLARE_BUF_ERR(outbuf);
- struct efx_nic *efx = channel->efx;
- size_t outlen;
- int rc;
-
- MCDI_SET_DWORD(inbuf, FINI_EVQ_IN_INSTANCE, channel->channel);
-
- rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_EVQ, inbuf, sizeof(inbuf),
- outbuf, sizeof(outbuf), &outlen);
-
- if (rc && rc != -EALREADY)
- goto fail;
-
- return;
-
-fail:
- efx_mcdi_display_error(efx, MC_CMD_FINI_EVQ, MC_CMD_FINI_EVQ_IN_LEN,
- outbuf, outlen, rc);
-}
-
static int efx_ef10_ev_init(struct efx_channel *channel)
{
- MCDI_DECLARE_BUF(inbuf,
- MC_CMD_INIT_EVQ_V2_IN_LEN(EFX_MAX_EVQ_SIZE * 8 /
- EFX_BUF_SIZE));
- MCDI_DECLARE_BUF(outbuf, MC_CMD_INIT_EVQ_V2_OUT_LEN);
- size_t entries = channel->eventq.buf.len / EFX_BUF_SIZE;
struct efx_nic *efx = channel->efx;
struct efx_ef10_nic_data *nic_data;
- size_t inlen, outlen;
unsigned int enabled, implemented;
- dma_addr_t dma_addr;
+ bool use_v2, cut_thru;
int rc;
- int i;
nic_data = efx->nic_data;
-
- /* Fill event queue with all ones (i.e. empty events) */
- memset(channel->eventq.buf.addr, 0xff, channel->eventq.buf.len);
-
- MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_SIZE, channel->eventq_mask + 1);
- MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_INSTANCE, channel->channel);
- /* INIT_EVQ expects index in vector table, not absolute */
- MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_IRQ_NUM, channel->channel);
- MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_MODE,
- MC_CMD_INIT_EVQ_IN_TMR_MODE_DIS);
- MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_LOAD, 0);
- MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_RELOAD, 0);
- MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_COUNT_MODE,
- MC_CMD_INIT_EVQ_IN_COUNT_MODE_DIS);
- MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_COUNT_THRSHLD, 0);
-
- if (nic_data->datapath_caps2 &
- 1 << MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_LBN) {
- /* Use the new generic approach to specifying event queue
- * configuration, requesting lower latency or higher throughput.
- * The options that actually get used appear in the output.
- */
- MCDI_POPULATE_DWORD_2(inbuf, INIT_EVQ_V2_IN_FLAGS,
- INIT_EVQ_V2_IN_FLAG_INTERRUPTING, 1,
- INIT_EVQ_V2_IN_FLAG_TYPE,
- MC_CMD_INIT_EVQ_V2_IN_FLAG_TYPE_AUTO);
- } else {
- bool cut_thru = !(nic_data->datapath_caps &
- 1 << MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN);
-
- MCDI_POPULATE_DWORD_4(inbuf, INIT_EVQ_IN_FLAGS,
- INIT_EVQ_IN_FLAG_INTERRUPTING, 1,
- INIT_EVQ_IN_FLAG_RX_MERGE, 1,
- INIT_EVQ_IN_FLAG_TX_MERGE, 1,
- INIT_EVQ_IN_FLAG_CUT_THRU, cut_thru);
- }
-
- dma_addr = channel->eventq.buf.dma_addr;
- for (i = 0; i < entries; ++i) {
- MCDI_SET_ARRAY_QWORD(inbuf, INIT_EVQ_IN_DMA_ADDR, i, dma_addr);
- dma_addr += EFX_BUF_SIZE;
- }
-
- inlen = MC_CMD_INIT_EVQ_IN_LEN(entries);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_INIT_EVQ, inbuf, inlen,
- outbuf, sizeof(outbuf), &outlen);
-
- if (outlen >= MC_CMD_INIT_EVQ_V2_OUT_LEN)
- netif_dbg(efx, drv, efx->net_dev,
- "Channel %d using event queue flags %08x\n",
- channel->channel,
- MCDI_DWORD(outbuf, INIT_EVQ_V2_OUT_FLAGS));
+ use_v2 = nic_data->datapath_caps2 &
+ 1 << MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_LBN;
+ cut_thru = !(nic_data->datapath_caps &
+ 1 << MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN);
+ rc = efx_mcdi_ev_init(channel, cut_thru, use_v2);
/* IRQ return is ignored */
if (channel->channel || rc)
@@ -3386,15 +3075,10 @@ static int efx_ef10_ev_init(struct efx_channel *channel)
return 0;
fail:
- efx_ef10_ev_fini(channel);
+ efx_mcdi_ev_fini(channel);
return rc;
}
-static void efx_ef10_ev_remove(struct efx_channel *channel)
-{
- efx_nic_free_buffer(channel->efx, &channel->eventq.buf);
-}
-
static void efx_ef10_handle_rx_wrong_queue(struct efx_rx_queue *rx_queue,
unsigned int rx_queue_label)
{
@@ -3976,9 +3660,9 @@ static int efx_ef10_fini_dmaq(struct efx_nic *efx)
if (efx->state != STATE_RECOVERY) {
efx_for_each_channel(channel, efx) {
efx_for_each_channel_rx_queue(rx_queue, channel)
- efx_ef10_rx_fini(rx_queue);
+ efx_mcdi_rx_fini(rx_queue);
efx_for_each_channel_tx_queue(tx_queue, channel)
- efx_ef10_tx_fini(tx_queue);
+ efx_mcdi_tx_fini(tx_queue);
}
wait_event_timeout(efx->flush_wq,
@@ -4165,7 +3849,7 @@ static void efx_ef10_filter_push_prep(struct efx_nic *efx,
*/
if (WARN_ON_ONCE(!ctx))
flags &= ~EFX_FILTER_FLAG_RX_RSS;
- else if (WARN_ON_ONCE(ctx->context_id == EFX_EF10_RSS_CONTEXT_INVALID))
+ else if (WARN_ON_ONCE(ctx->context_id == EFX_MCDI_RSS_CONTEXT_INVALID))
flags &= ~EFX_FILTER_FLAG_RX_RSS;
}
@@ -4344,7 +4028,7 @@ static s32 efx_ef10_filter_insert_locked(struct efx_nic *efx,
rc = -ENOENT;
goto out_unlock;
}
- if (ctx->context_id == EFX_EF10_RSS_CONTEXT_INVALID) {
+ if (ctx->context_id == EFX_MCDI_RSS_CONTEXT_INVALID) {
rc = -EOPNOTSUPP;
goto out_unlock;
}
@@ -5085,7 +4769,7 @@ static void efx_ef10_filter_table_restore(struct efx_nic *efx)
invalid_filters++;
goto not_restored;
}
- if (ctx->context_id == EFX_EF10_RSS_CONTEXT_INVALID) {
+ if (ctx->context_id == EFX_MCDI_RSS_CONTEXT_INVALID) {
netif_warn(efx, drv, efx->net_dev,
"Warning: unable to restore a filter with RSS context %u as it was not created.\n",
spec->rss_context);
@@ -6650,20 +6334,20 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
.irq_handle_legacy = efx_ef10_legacy_interrupt,
.tx_probe = efx_ef10_tx_probe,
.tx_init = efx_ef10_tx_init,
- .tx_remove = efx_ef10_tx_remove,
+ .tx_remove = efx_mcdi_tx_remove,
.tx_write = efx_ef10_tx_write,
.tx_limit_len = efx_ef10_tx_limit_len,
.rx_push_rss_config = efx_ef10_vf_rx_push_rss_config,
.rx_pull_rss_config = efx_ef10_rx_pull_rss_config,
- .rx_probe = efx_ef10_rx_probe,
- .rx_init = efx_ef10_rx_init,
- .rx_remove = efx_ef10_rx_remove,
+ .rx_probe = efx_mcdi_rx_probe,
+ .rx_init = efx_mcdi_rx_init,
+ .rx_remove = efx_mcdi_rx_remove,
.rx_write = efx_ef10_rx_write,
.rx_defer_refill = efx_ef10_rx_defer_refill,
- .ev_probe = efx_ef10_ev_probe,
+ .ev_probe = efx_mcdi_ev_probe,
.ev_init = efx_ef10_ev_init,
- .ev_fini = efx_ef10_ev_fini,
- .ev_remove = efx_ef10_ev_remove,
+ .ev_fini = efx_mcdi_ev_fini,
+ .ev_remove = efx_mcdi_ev_remove,
.ev_process = efx_ef10_ev_process,
.ev_read_ack = efx_ef10_ev_read_ack,
.ev_test_generate = efx_ef10_ev_test_generate,
@@ -6759,7 +6443,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
.irq_handle_legacy = efx_ef10_legacy_interrupt,
.tx_probe = efx_ef10_tx_probe,
.tx_init = efx_ef10_tx_init,
- .tx_remove = efx_ef10_tx_remove,
+ .tx_remove = efx_mcdi_tx_remove,
.tx_write = efx_ef10_tx_write,
.tx_limit_len = efx_ef10_tx_limit_len,
.rx_push_rss_config = efx_ef10_pf_rx_push_rss_config,
@@ -6767,15 +6451,15 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
.rx_push_rss_context_config = efx_ef10_rx_push_rss_context_config,
.rx_pull_rss_context_config = efx_ef10_rx_pull_rss_context_config,
.rx_restore_rss_contexts = efx_ef10_rx_restore_rss_contexts,
- .rx_probe = efx_ef10_rx_probe,
- .rx_init = efx_ef10_rx_init,
- .rx_remove = efx_ef10_rx_remove,
+ .rx_probe = efx_mcdi_rx_probe,
+ .rx_init = efx_mcdi_rx_init,
+ .rx_remove = efx_mcdi_rx_remove,
.rx_write = efx_ef10_rx_write,
.rx_defer_refill = efx_ef10_rx_defer_refill,
- .ev_probe = efx_ef10_ev_probe,
+ .ev_probe = efx_mcdi_ev_probe,
.ev_init = efx_ef10_ev_init,
- .ev_fini = efx_ef10_ev_fini,
- .ev_remove = efx_ef10_ev_remove,
+ .ev_fini = efx_mcdi_ev_fini,
+ .ev_remove = efx_mcdi_ev_remove,
.ev_process = efx_ef10_ev_process,
.ev_read_ack = efx_ef10_ev_read_ack,
.ev_test_generate = efx_ef10_ev_test_generate,
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 033907e..4481f21 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -23,6 +23,10 @@
#include <net/gre.h>
#include <net/udp_tunnel.h>
#include "efx.h"
+#include "efx_common.h"
+#include "efx_channels.h"
+#include "rx_common.h"
+#include "tx_common.h"
#include "nic.h"
#include "io.h"
#include "selftest.h"
@@ -39,56 +43,6 @@
**************************************************************************
*/
-/* Loopback mode names (see LOOPBACK_MODE()) */
-const unsigned int efx_loopback_mode_max = LOOPBACK_MAX;
-const char *const efx_loopback_mode_names[] = {
- [LOOPBACK_NONE] = "NONE",
- [LOOPBACK_DATA] = "DATAPATH",
- [LOOPBACK_GMAC] = "GMAC",
- [LOOPBACK_XGMII] = "XGMII",
- [LOOPBACK_XGXS] = "XGXS",
- [LOOPBACK_XAUI] = "XAUI",
- [LOOPBACK_GMII] = "GMII",
- [LOOPBACK_SGMII] = "SGMII",
- [LOOPBACK_XGBR] = "XGBR",
- [LOOPBACK_XFI] = "XFI",
- [LOOPBACK_XAUI_FAR] = "XAUI_FAR",
- [LOOPBACK_GMII_FAR] = "GMII_FAR",
- [LOOPBACK_SGMII_FAR] = "SGMII_FAR",
- [LOOPBACK_XFI_FAR] = "XFI_FAR",
- [LOOPBACK_GPHY] = "GPHY",
- [LOOPBACK_PHYXS] = "PHYXS",
- [LOOPBACK_PCS] = "PCS",
- [LOOPBACK_PMAPMD] = "PMA/PMD",
- [LOOPBACK_XPORT] = "XPORT",
- [LOOPBACK_XGMII_WS] = "XGMII_WS",
- [LOOPBACK_XAUI_WS] = "XAUI_WS",
- [LOOPBACK_XAUI_WS_FAR] = "XAUI_WS_FAR",
- [LOOPBACK_XAUI_WS_NEAR] = "XAUI_WS_NEAR",
- [LOOPBACK_GMII_WS] = "GMII_WS",
- [LOOPBACK_XFI_WS] = "XFI_WS",
- [LOOPBACK_XFI_WS_FAR] = "XFI_WS_FAR",
- [LOOPBACK_PHYXS_WS] = "PHYXS_WS",
-};
-
-const unsigned int efx_reset_type_max = RESET_TYPE_MAX;
-const char *const efx_reset_type_names[] = {
- [RESET_TYPE_INVISIBLE] = "INVISIBLE",
- [RESET_TYPE_ALL] = "ALL",
- [RESET_TYPE_RECOVER_OR_ALL] = "RECOVER_OR_ALL",
- [RESET_TYPE_WORLD] = "WORLD",
- [RESET_TYPE_RECOVER_OR_DISABLE] = "RECOVER_OR_DISABLE",
- [RESET_TYPE_DATAPATH] = "DATAPATH",
- [RESET_TYPE_MC_BIST] = "MC_BIST",
- [RESET_TYPE_DISABLE] = "DISABLE",
- [RESET_TYPE_TX_WATCHDOG] = "TX_WATCHDOG",
- [RESET_TYPE_INT_ERROR] = "INT_ERROR",
- [RESET_TYPE_DMA_ERROR] = "DMA_ERROR",
- [RESET_TYPE_TX_SKIP] = "TX_SKIP",
- [RESET_TYPE_MC_FAILURE] = "MC_FAILURE",
- [RESET_TYPE_MCDI_TIMEOUT] = "MCDI_TIMEOUT (FLR)",
-};
-
/* UDP tunnel type names */
static const char *const efx_udp_tunnel_type_names[] = {
[TUNNEL_ENCAP_UDP_PORT_ENTRY_VXLAN] = "vxlan",
@@ -104,18 +58,6 @@ void efx_get_udp_tunnel_type_name(u16 type, char *buf, size_t buflen)
snprintf(buf, buflen, "type %d", type);
}
-/* Reset workqueue. If any NIC has a hardware failure then a reset will be
- * queued onto this work queue. This is not a per-nic work queue, because
- * efx_reset_work() acquires the rtnl lock, so resets are naturally serialised.
- */
-static struct workqueue_struct *reset_workqueue;
-
-/* How often and how many times to poll for a reset while waiting for a
- * BIST that another function started to complete.
- */
-#define BIST_WAIT_DELAY_MS 100
-#define BIST_WAIT_DELAY_COUNT 100
-
/**************************************************************************
*
* Configurable values
@@ -135,21 +77,6 @@ module_param(efx_separate_tx_channels, bool, 0444);
MODULE_PARM_DESC(efx_separate_tx_channels,
"Use separate channels for TX and RX");
-/* This is the weight assigned to each of the (per-channel) virtual
- * NAPI devices.
- */
-static int napi_weight = 64;
-
-/* This is the time (in jiffies) between invocations of the hardware
- * monitor.
- * On Falcon-based NICs, this will:
- * - Check the on-board hardware monitor;
- * - Poll the link state and reconfigure the hardware as necessary.
- * On Siena-based NICs for power systems with EEH support, this will give EEH a
- * chance to start.
- */
-static unsigned int efx_monitor_interval = 1 * HZ;
-
/* Initial interrupt moderation settings. They can be modified after
* module load with ethtool.
*
@@ -169,38 +96,10 @@ static unsigned int rx_irq_mod_usec = 60;
*/
static unsigned int tx_irq_mod_usec = 150;
-/* This is the first interrupt mode to try out of:
- * 0 => MSI-X
- * 1 => MSI
- * 2 => legacy
- */
-static unsigned int interrupt_mode;
-
-/* This is the requested number of CPUs to use for Receive-Side Scaling (RSS),
- * i.e. the number of CPUs among which we may distribute simultaneous
- * interrupt handling.
- *
- * Cards without MSI-X will only target one CPU via legacy or MSI interrupt.
- * The default (0) means to assign an interrupt to each core.
- */
-static unsigned int rss_cpus;
-module_param(rss_cpus, uint, 0444);
-MODULE_PARM_DESC(rss_cpus, "Number of CPUs to use for Receive-Side Scaling");
-
static bool phy_flash_cfg;
module_param(phy_flash_cfg, bool, 0644);
MODULE_PARM_DESC(phy_flash_cfg, "Set PHYs into reflash mode initially");
-static unsigned irq_adapt_low_thresh = 8000;
-module_param(irq_adapt_low_thresh, uint, 0644);
-MODULE_PARM_DESC(irq_adapt_low_thresh,
- "Threshold score for reducing IRQ moderation");
-
-static unsigned irq_adapt_high_thresh = 16000;
-module_param(irq_adapt_high_thresh, uint, 0644);
-MODULE_PARM_DESC(irq_adapt_high_thresh,
- "Threshold score for increasing IRQ moderation");
-
static unsigned debug = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
NETIF_MSG_LINK | NETIF_MSG_IFDOWN |
NETIF_MSG_IFUP | NETIF_MSG_RX_ERR |
@@ -214,18 +113,8 @@ MODULE_PARM_DESC(debug, "Bitmapped debugging message enable value");
*
*************************************************************************/
-static int efx_soft_enable_interrupts(struct efx_nic *efx);
-static void efx_soft_disable_interrupts(struct efx_nic *efx);
-static void efx_remove_channel(struct efx_channel *channel);
-static void efx_remove_channels(struct efx_nic *efx);
static const struct efx_channel_type efx_default_channel_type;
static void efx_remove_port(struct efx_nic *efx);
-static void efx_init_napi_channel(struct efx_channel *channel);
-static void efx_fini_napi(struct efx_nic *efx);
-static void efx_fini_napi_channel(struct efx_channel *channel);
-static void efx_fini_struct(struct efx_nic *efx);
-static void efx_start_all(struct efx_nic *efx);
-static void efx_stop_all(struct efx_nic *efx);
static int efx_xdp_setup_prog(struct efx_nic *efx, struct bpf_prog *prog);
static int efx_xdp(struct net_device *dev, struct netdev_bpf *xdp);
static int efx_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **xdpfs,
@@ -239,776 +128,12 @@ static int efx_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **xdpfs,
ASSERT_RTNL(); \
} while (0)
-static int efx_check_disabled(struct efx_nic *efx)
-{
- if (efx->state == STATE_DISABLED || efx->state == STATE_RECOVERY) {
- netif_err(efx, drv, efx->net_dev,
- "device is disabled due to earlier errors\n");
- return -EIO;
- }
- return 0;
-}
-
-/**************************************************************************
- *
- * Event queue processing
- *
- *************************************************************************/
-
-/* Process channel's event queue
- *
- * This function is responsible for processing the event queue of a
- * single channel. The caller must guarantee that this function will
- * never be concurrently called more than once on the same channel,
- * though different channels may be being processed concurrently.
- */
-static int efx_process_channel(struct efx_channel *channel, int budget)
-{
- struct efx_tx_queue *tx_queue;
- struct list_head rx_list;
- int spent;
-
- if (unlikely(!channel->enabled))
- return 0;
-
- /* Prepare the batch receive list */
- EFX_WARN_ON_PARANOID(channel->rx_list != NULL);
- INIT_LIST_HEAD(&rx_list);
- channel->rx_list = &rx_list;
-
- efx_for_each_channel_tx_queue(tx_queue, channel) {
- tx_queue->pkts_compl = 0;
- tx_queue->bytes_compl = 0;
- }
-
- spent = efx_nic_process_eventq(channel, budget);
- if (spent && efx_channel_has_rx_queue(channel)) {
- struct efx_rx_queue *rx_queue =
- efx_channel_get_rx_queue(channel);
-
- efx_rx_flush_packet(channel);
- efx_fast_push_rx_descriptors(rx_queue, true);
- }
-
- /* Update BQL */
- efx_for_each_channel_tx_queue(tx_queue, channel) {
- if (tx_queue->bytes_compl) {
- netdev_tx_completed_queue(tx_queue->core_txq,
- tx_queue->pkts_compl, tx_queue->bytes_compl);
- }
- }
-
- /* Receive any packets we queued up */
- netif_receive_skb_list(channel->rx_list);
- channel->rx_list = NULL;
-
- return spent;
-}
-
-/* NAPI poll handler
- *
- * NAPI guarantees serialisation of polls of the same device, which
- * provides the guarantee required by efx_process_channel().
- */
-static void efx_update_irq_mod(struct efx_nic *efx, struct efx_channel *channel)
-{
- int step = efx->irq_mod_step_us;
-
- if (channel->irq_mod_score < irq_adapt_low_thresh) {
- if (channel->irq_moderation_us > step) {
- channel->irq_moderation_us -= step;
- efx->type->push_irq_moderation(channel);
- }
- } else if (channel->irq_mod_score > irq_adapt_high_thresh) {
- if (channel->irq_moderation_us <
- efx->irq_rx_moderation_us) {
- channel->irq_moderation_us += step;
- efx->type->push_irq_moderation(channel);
- }
- }
-
- channel->irq_count = 0;
- channel->irq_mod_score = 0;
-}
-
-static int efx_poll(struct napi_struct *napi, int budget)
-{
- struct efx_channel *channel =
- container_of(napi, struct efx_channel, napi_str);
- struct efx_nic *efx = channel->efx;
- int spent;
-
- netif_vdbg(efx, intr, efx->net_dev,
- "channel %d NAPI poll executing on CPU %d\n",
- channel->channel, raw_smp_processor_id());
-
- spent = efx_process_channel(channel, budget);
-
- xdp_do_flush_map();
-
- if (spent < budget) {
- if (efx_channel_has_rx_queue(channel) &&
- efx->irq_rx_adaptive &&
- unlikely(++channel->irq_count == 1000)) {
- efx_update_irq_mod(efx, channel);
- }
-
-#ifdef CONFIG_RFS_ACCEL
- /* Perhaps expire some ARFS filters */
- mod_delayed_work(system_wq, &channel->filter_work, 0);
-#endif
-
- /* There is no race here; although napi_disable() will
- * only wait for napi_complete(), this isn't a problem
- * since efx_nic_eventq_read_ack() will have no effect if
- * interrupts have already been disabled.
- */
- if (napi_complete_done(napi, spent))
- efx_nic_eventq_read_ack(channel);
- }
-
- return spent;
-}
-
-/* Create event queue
- * Event queue memory allocations are done only once. If the channel
- * is reset, the memory buffer will be reused; this guards against
- * errors during channel reset and also simplifies interrupt handling.
- */
-static int efx_probe_eventq(struct efx_channel *channel)
-{
- struct efx_nic *efx = channel->efx;
- unsigned long entries;
-
- netif_dbg(efx, probe, efx->net_dev,
- "chan %d create event queue\n", channel->channel);
-
- /* Build an event queue with room for one event per tx and rx buffer,
- * plus some extra for link state events and MCDI completions. */
- entries = roundup_pow_of_two(efx->rxq_entries + efx->txq_entries + 128);
- EFX_WARN_ON_PARANOID(entries > EFX_MAX_EVQ_SIZE);
- channel->eventq_mask = max(entries, EFX_MIN_EVQ_SIZE) - 1;
-
- return efx_nic_probe_eventq(channel);
-}
-
-/* Prepare channel's event queue */
-static int efx_init_eventq(struct efx_channel *channel)
-{
- struct efx_nic *efx = channel->efx;
- int rc;
-
- EFX_WARN_ON_PARANOID(channel->eventq_init);
-
- netif_dbg(efx, drv, efx->net_dev,
- "chan %d init event queue\n", channel->channel);
-
- rc = efx_nic_init_eventq(channel);
- if (rc == 0) {
- efx->type->push_irq_moderation(channel);
- channel->eventq_read_ptr = 0;
- channel->eventq_init = true;
- }
- return rc;
-}
-
-/* Enable event queue processing and NAPI */
-void efx_start_eventq(struct efx_channel *channel)
-{
- netif_dbg(channel->efx, ifup, channel->efx->net_dev,
- "chan %d start event queue\n", channel->channel);
-
- /* Make sure the NAPI handler sees the enabled flag set */
- channel->enabled = true;
- smp_wmb();
-
- napi_enable(&channel->napi_str);
- efx_nic_eventq_read_ack(channel);
-}
-
-/* Disable event queue processing and NAPI */
-void efx_stop_eventq(struct efx_channel *channel)
-{
- if (!channel->enabled)
- return;
-
- napi_disable(&channel->napi_str);
- channel->enabled = false;
-}
-
-static void efx_fini_eventq(struct efx_channel *channel)
-{
- if (!channel->eventq_init)
- return;
-
- netif_dbg(channel->efx, drv, channel->efx->net_dev,
- "chan %d fini event queue\n", channel->channel);
-
- efx_nic_fini_eventq(channel);
- channel->eventq_init = false;
-}
-
-static void efx_remove_eventq(struct efx_channel *channel)
-{
- netif_dbg(channel->efx, drv, channel->efx->net_dev,
- "chan %d remove event queue\n", channel->channel);
-
- efx_nic_remove_eventq(channel);
-}
-
-/**************************************************************************
- *
- * Channel handling
- *
- *************************************************************************/
-
-/* Allocate and initialise a channel structure. */
-static struct efx_channel *
-efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel)
-{
- struct efx_channel *channel;
- struct efx_rx_queue *rx_queue;
- struct efx_tx_queue *tx_queue;
- int j;
-
- channel = kzalloc(sizeof(*channel), GFP_KERNEL);
- if (!channel)
- return NULL;
-
- channel->efx = efx;
- channel->channel = i;
- channel->type = &efx_default_channel_type;
-
- for (j = 0; j < EFX_TXQ_TYPES; j++) {
- tx_queue = &channel->tx_queue[j];
- tx_queue->efx = efx;
- tx_queue->queue = i * EFX_TXQ_TYPES + j;
- tx_queue->channel = channel;
- }
-
-#ifdef CONFIG_RFS_ACCEL
- INIT_DELAYED_WORK(&channel->filter_work, efx_filter_rfs_expire);
-#endif
-
- rx_queue = &channel->rx_queue;
- rx_queue->efx = efx;
- timer_setup(&rx_queue->slow_fill, efx_rx_slow_fill, 0);
-
- return channel;
-}
-
-/* Allocate and initialise a channel structure, copying parameters
- * (but not resources) from an old channel structure.
- */
-static struct efx_channel *
-efx_copy_channel(const struct efx_channel *old_channel)
-{
- struct efx_channel *channel;
- struct efx_rx_queue *rx_queue;
- struct efx_tx_queue *tx_queue;
- int j;
-
- channel = kmalloc(sizeof(*channel), GFP_KERNEL);
- if (!channel)
- return NULL;
-
- *channel = *old_channel;
-
- channel->napi_dev = NULL;
- INIT_HLIST_NODE(&channel->napi_str.napi_hash_node);
- channel->napi_str.napi_id = 0;
- channel->napi_str.state = 0;
- memset(&channel->eventq, 0, sizeof(channel->eventq));
-
- for (j = 0; j < EFX_TXQ_TYPES; j++) {
- tx_queue = &channel->tx_queue[j];
- if (tx_queue->channel)
- tx_queue->channel = channel;
- tx_queue->buffer = NULL;
- memset(&tx_queue->txd, 0, sizeof(tx_queue->txd));
- }
-
- rx_queue = &channel->rx_queue;
- rx_queue->buffer = NULL;
- memset(&rx_queue->rxd, 0, sizeof(rx_queue->rxd));
- timer_setup(&rx_queue->slow_fill, efx_rx_slow_fill, 0);
-#ifdef CONFIG_RFS_ACCEL
- INIT_DELAYED_WORK(&channel->filter_work, efx_filter_rfs_expire);
-#endif
-
- return channel;
-}
-
-static int efx_probe_channel(struct efx_channel *channel)
-{
- struct efx_tx_queue *tx_queue;
- struct efx_rx_queue *rx_queue;
- int rc;
-
- netif_dbg(channel->efx, probe, channel->efx->net_dev,
- "creating channel %d\n", channel->channel);
-
- rc = channel->type->pre_probe(channel);
- if (rc)
- goto fail;
-
- rc = efx_probe_eventq(channel);
- if (rc)
- goto fail;
-
- efx_for_each_channel_tx_queue(tx_queue, channel) {
- rc = efx_probe_tx_queue(tx_queue);
- if (rc)
- goto fail;
- }
-
- efx_for_each_channel_rx_queue(rx_queue, channel) {
- rc = efx_probe_rx_queue(rx_queue);
- if (rc)
- goto fail;
- }
-
- channel->rx_list = NULL;
-
- return 0;
-
-fail:
- efx_remove_channel(channel);
- return rc;
-}
-
-static void
-efx_get_channel_name(struct efx_channel *channel, char *buf, size_t len)
-{
- struct efx_nic *efx = channel->efx;
- const char *type;
- int number;
-
- number = channel->channel;
-
- if (number >= efx->xdp_channel_offset &&
- !WARN_ON_ONCE(!efx->n_xdp_channels)) {
- type = "-xdp";
- number -= efx->xdp_channel_offset;
- } else if (efx->tx_channel_offset == 0) {
- type = "";
- } else if (number < efx->tx_channel_offset) {
- type = "-rx";
- } else {
- type = "-tx";
- number -= efx->tx_channel_offset;
- }
- snprintf(buf, len, "%s%s-%d", efx->name, type, number);
-}
-
-static void efx_set_channel_names(struct efx_nic *efx)
-{
- struct efx_channel *channel;
-
- efx_for_each_channel(channel, efx)
- channel->type->get_name(channel,
- efx->msi_context[channel->channel].name,
- sizeof(efx->msi_context[0].name));
-}
-
-static int efx_probe_channels(struct efx_nic *efx)
-{
- struct efx_channel *channel;
- int rc;
-
- /* Restart special buffer allocation */
- efx->next_buffer_table = 0;
-
- /* Probe channels in reverse, so that any 'extra' channels
- * use the start of the buffer table. This allows the traffic
- * channels to be resized without moving them or wasting the
- * entries before them.
- */
- efx_for_each_channel_rev(channel, efx) {
- rc = efx_probe_channel(channel);
- if (rc) {
- netif_err(efx, probe, efx->net_dev,
- "failed to create channel %d\n",
- channel->channel);
- goto fail;
- }
- }
- efx_set_channel_names(efx);
-
- return 0;
-
-fail:
- efx_remove_channels(efx);
- return rc;
-}
-
-/* Channels are shutdown and reinitialised whilst the NIC is running
- * to propagate configuration changes (mtu, checksum offload), or
- * to clear hardware error conditions
- */
-static void efx_start_datapath(struct efx_nic *efx)
-{
- netdev_features_t old_features = efx->net_dev->features;
- bool old_rx_scatter = efx->rx_scatter;
- struct efx_tx_queue *tx_queue;
- struct efx_rx_queue *rx_queue;
- struct efx_channel *channel;
- size_t rx_buf_len;
-
- /* Calculate the rx buffer allocation parameters required to
- * support the current MTU, including padding for header
- * alignment and overruns.
- */
- efx->rx_dma_len = (efx->rx_prefix_size +
- EFX_MAX_FRAME_LEN(efx->net_dev->mtu) +
- efx->type->rx_buffer_padding);
- rx_buf_len = (sizeof(struct efx_rx_page_state) + XDP_PACKET_HEADROOM +
- efx->rx_ip_align + efx->rx_dma_len);
- if (rx_buf_len <= PAGE_SIZE) {
- efx->rx_scatter = efx->type->always_rx_scatter;
- efx->rx_buffer_order = 0;
- } else if (efx->type->can_rx_scatter) {
- BUILD_BUG_ON(EFX_RX_USR_BUF_SIZE % L1_CACHE_BYTES);
- BUILD_BUG_ON(sizeof(struct efx_rx_page_state) +
- 2 * ALIGN(NET_IP_ALIGN + EFX_RX_USR_BUF_SIZE,
- EFX_RX_BUF_ALIGNMENT) >
- PAGE_SIZE);
- efx->rx_scatter = true;
- efx->rx_dma_len = EFX_RX_USR_BUF_SIZE;
- efx->rx_buffer_order = 0;
- } else {
- efx->rx_scatter = false;
- efx->rx_buffer_order = get_order(rx_buf_len);
- }
-
- efx_rx_config_page_split(efx);
- if (efx->rx_buffer_order)
- netif_dbg(efx, drv, efx->net_dev,
- "RX buf len=%u; page order=%u batch=%u\n",
- efx->rx_dma_len, efx->rx_buffer_order,
- efx->rx_pages_per_batch);
- else
- netif_dbg(efx, drv, efx->net_dev,
- "RX buf len=%u step=%u bpp=%u; page batch=%u\n",
- efx->rx_dma_len, efx->rx_page_buf_step,
- efx->rx_bufs_per_page, efx->rx_pages_per_batch);
-
- /* Restore previously fixed features in hw_features and remove
- * features which are fixed now
- */
- efx->net_dev->hw_features |= efx->net_dev->features;
- efx->net_dev->hw_features &= ~efx->fixed_features;
- efx->net_dev->features |= efx->fixed_features;
- if (efx->net_dev->features != old_features)
- netdev_features_change(efx->net_dev);
-
- /* RX filters may also have scatter-enabled flags */
- if (efx->rx_scatter != old_rx_scatter)
- efx->type->filter_update_rx_scatter(efx);
-
- /* We must keep at least one descriptor in a TX ring empty.
- * We could avoid this when the queue size does not exactly
- * match the hardware ring size, but it's not that important.
- * Therefore we stop the queue when one more skb might fill
- * the ring completely. We wake it when half way back to
- * empty.
- */
- efx->txq_stop_thresh = efx->txq_entries - efx_tx_max_skb_descs(efx);
- efx->txq_wake_thresh = efx->txq_stop_thresh / 2;
-
- /* Initialise the channels */
- efx_for_each_channel(channel, efx) {
- efx_for_each_channel_tx_queue(tx_queue, channel) {
- efx_init_tx_queue(tx_queue);
- atomic_inc(&efx->active_queues);
- }
-
- efx_for_each_channel_rx_queue(rx_queue, channel) {
- efx_init_rx_queue(rx_queue);
- atomic_inc(&efx->active_queues);
- efx_stop_eventq(channel);
- efx_fast_push_rx_descriptors(rx_queue, false);
- efx_start_eventq(channel);
- }
-
- WARN_ON(channel->rx_pkt_n_frags);
- }
-
- efx_ptp_start_datapath(efx);
-
- if (netif_device_present(efx->net_dev))
- netif_tx_wake_all_queues(efx->net_dev);
-}
-
-static void efx_stop_datapath(struct efx_nic *efx)
-{
- struct efx_channel *channel;
- struct efx_tx_queue *tx_queue;
- struct efx_rx_queue *rx_queue;
- int rc;
-
- EFX_ASSERT_RESET_SERIALISED(efx);
- BUG_ON(efx->port_enabled);
-
- efx_ptp_stop_datapath(efx);
-
- /* Stop RX refill */
- efx_for_each_channel(channel, efx) {
- efx_for_each_channel_rx_queue(rx_queue, channel)
- rx_queue->refill_enabled = false;
- }
-
- efx_for_each_channel(channel, efx) {
- /* RX packet processing is pipelined, so wait for the
- * NAPI handler to complete. At least event queue 0
- * might be kept active by non-data events, so don't
- * use napi_synchronize() but actually disable NAPI
- * temporarily.
- */
- if (efx_channel_has_rx_queue(channel)) {
- efx_stop_eventq(channel);
- efx_start_eventq(channel);
- }
- }
-
- rc = efx->type->fini_dmaq(efx);
- if (rc) {
- netif_err(efx, drv, efx->net_dev, "failed to flush queues\n");
- } else {
- netif_dbg(efx, drv, efx->net_dev,
- "successfully flushed all queues\n");
- }
-
- efx_for_each_channel(channel, efx) {
- efx_for_each_channel_rx_queue(rx_queue, channel)
- efx_fini_rx_queue(rx_queue);
- efx_for_each_possible_channel_tx_queue(tx_queue, channel)
- efx_fini_tx_queue(tx_queue);
- }
- efx->xdp_rxq_info_failed = false;
-}
-
-static void efx_remove_channel(struct efx_channel *channel)
-{
- struct efx_tx_queue *tx_queue;
- struct efx_rx_queue *rx_queue;
-
- netif_dbg(channel->efx, drv, channel->efx->net_dev,
- "destroy chan %d\n", channel->channel);
-
- efx_for_each_channel_rx_queue(rx_queue, channel)
- efx_remove_rx_queue(rx_queue);
- efx_for_each_possible_channel_tx_queue(tx_queue, channel)
- efx_remove_tx_queue(tx_queue);
- efx_remove_eventq(channel);
- channel->type->post_remove(channel);
-}
-
-static void efx_remove_channels(struct efx_nic *efx)
-{
- struct efx_channel *channel;
-
- efx_for_each_channel(channel, efx)
- efx_remove_channel(channel);
-
- kfree(efx->xdp_tx_queues);
-}
-
-int
-efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
-{
- struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel;
- u32 old_rxq_entries, old_txq_entries;
- unsigned i, next_buffer_table = 0;
- int rc, rc2;
-
- rc = efx_check_disabled(efx);
- if (rc)
- return rc;
-
- /* Not all channels should be reallocated. We must avoid
- * reallocating their buffer table entries.
- */
- efx_for_each_channel(channel, efx) {
- struct efx_rx_queue *rx_queue;
- struct efx_tx_queue *tx_queue;
-
- if (channel->type->copy)
- continue;
- next_buffer_table = max(next_buffer_table,
- channel->eventq.index +
- channel->eventq.entries);
- efx_for_each_channel_rx_queue(rx_queue, channel)
- next_buffer_table = max(next_buffer_table,
- rx_queue->rxd.index +
- rx_queue->rxd.entries);
- efx_for_each_channel_tx_queue(tx_queue, channel)
- next_buffer_table = max(next_buffer_table,
- tx_queue->txd.index +
- tx_queue->txd.entries);
- }
-
- efx_device_detach_sync(efx);
- efx_stop_all(efx);
- efx_soft_disable_interrupts(efx);
-
- /* Clone channels (where possible) */
- memset(other_channel, 0, sizeof(other_channel));
- for (i = 0; i < efx->n_channels; i++) {
- channel = efx->channel[i];
- if (channel->type->copy)
- channel = channel->type->copy(channel);
- if (!channel) {
- rc = -ENOMEM;
- goto out;
- }
- other_channel[i] = channel;
- }
-
- /* Swap entry counts and channel pointers */
- old_rxq_entries = efx->rxq_entries;
- old_txq_entries = efx->txq_entries;
- efx->rxq_entries = rxq_entries;
- efx->txq_entries = txq_entries;
- for (i = 0; i < efx->n_channels; i++) {
- channel = efx->channel[i];
- efx->channel[i] = other_channel[i];
- other_channel[i] = channel;
- }
-
- /* Restart buffer table allocation */
- efx->next_buffer_table = next_buffer_table;
-
- for (i = 0; i < efx->n_channels; i++) {
- channel = efx->channel[i];
- if (!channel->type->copy)
- continue;
- rc = efx_probe_channel(channel);
- if (rc)
- goto rollback;
- efx_init_napi_channel(efx->channel[i]);
- }
-
-out:
- /* Destroy unused channel structures */
- for (i = 0; i < efx->n_channels; i++) {
- channel = other_channel[i];
- if (channel && channel->type->copy) {
- efx_fini_napi_channel(channel);
- efx_remove_channel(channel);
- kfree(channel);
- }
- }
-
- rc2 = efx_soft_enable_interrupts(efx);
- if (rc2) {
- rc = rc ? rc : rc2;
- netif_err(efx, drv, efx->net_dev,
- "unable to restart interrupts on channel reallocation\n");
- efx_schedule_reset(efx, RESET_TYPE_DISABLE);
- } else {
- efx_start_all(efx);
- efx_device_attach_if_not_resetting(efx);
- }
- return rc;
-
-rollback:
- /* Swap back */
- efx->rxq_entries = old_rxq_entries;
- efx->txq_entries = old_txq_entries;
- for (i = 0; i < efx->n_channels; i++) {
- channel = efx->channel[i];
- efx->channel[i] = other_channel[i];
- other_channel[i] = channel;
- }
- goto out;
-}
-
-void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue)
-{
- mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(10));
-}
-
-static bool efx_default_channel_want_txqs(struct efx_channel *channel)
-{
- return channel->channel - channel->efx->tx_channel_offset <
- channel->efx->n_tx_channels;
-}
-
-static const struct efx_channel_type efx_default_channel_type = {
- .pre_probe = efx_channel_dummy_op_int,
- .post_remove = efx_channel_dummy_op_void,
- .get_name = efx_get_channel_name,
- .copy = efx_copy_channel,
- .want_txqs = efx_default_channel_want_txqs,
- .keep_eventq = false,
- .want_pio = true,
-};
-
-int efx_channel_dummy_op_int(struct efx_channel *channel)
-{
- return 0;
-}
-
-void efx_channel_dummy_op_void(struct efx_channel *channel)
-{
-}
-
/**************************************************************************
*
* Port handling
*
**************************************************************************/
-/* This ensures that the kernel is kept informed (via
- * netif_carrier_on/off) of the link status, and also maintains the
- * link status's stop on the port's TX queue.
- */
-void efx_link_status_changed(struct efx_nic *efx)
-{
- struct efx_link_state *link_state = &efx->link_state;
-
- /* SFC Bug 5356: A net_dev notifier is registered, so we must ensure
- * that no events are triggered between unregister_netdev() and the
- * driver unloading. A more general condition is that NETDEV_CHANGE
- * can only be generated between NETDEV_UP and NETDEV_DOWN */
- if (!netif_running(efx->net_dev))
- return;
-
- if (link_state->up != netif_carrier_ok(efx->net_dev)) {
- efx->n_link_state_changes++;
-
- if (link_state->up)
- netif_carrier_on(efx->net_dev);
- else
- netif_carrier_off(efx->net_dev);
- }
-
- /* Status message for kernel log */
- if (link_state->up)
- netif_info(efx, link, efx->net_dev,
- "link up at %uMbps %s-duplex (MTU %d)\n",
- link_state->speed, link_state->fd ? "full" : "half",
- efx->net_dev->mtu);
- else
- netif_info(efx, link, efx->net_dev, "link down\n");
-}
-
-void efx_link_set_advertising(struct efx_nic *efx,
- const unsigned long *advertising)
-{
- memcpy(efx->link_advertising, advertising,
- sizeof(__ETHTOOL_DECLARE_LINK_MODE_MASK()));
-
- efx->link_advertising[0] |= ADVERTISED_Autoneg;
- if (advertising[0] & ADVERTISED_Pause)
- efx->wanted_fc |= (EFX_FC_TX | EFX_FC_RX);
- else
- efx->wanted_fc &= ~(EFX_FC_TX | EFX_FC_RX);
- if (advertising[0] & ADVERTISED_Asym_Pause)
- efx->wanted_fc ^= EFX_FC_TX;
-}
-
/* Equivalent to efx_link_set_advertising with all-zeroes, except does not
* force the Autoneg bit on.
*/
@@ -1035,73 +160,6 @@ void efx_link_set_wanted_fc(struct efx_nic *efx, u8 wanted_fc)
static void efx_fini_port(struct efx_nic *efx);
-/* We assume that efx->type->reconfigure_mac will always try to sync RX
- * filters and therefore needs to read-lock the filter table against freeing
- */
-void efx_mac_reconfigure(struct efx_nic *efx)
-{
- down_read(&efx->filter_sem);
- efx->type->reconfigure_mac(efx);
- up_read(&efx->filter_sem);
-}
-
-/* Push loopback/power/transmit disable settings to the PHY, and reconfigure
- * the MAC appropriately. All other PHY configuration changes are pushed
- * through phy_op->set_settings(), and pushed asynchronously to the MAC
- * through efx_monitor().
- *
- * Callers must hold the mac_lock
- */
-int __efx_reconfigure_port(struct efx_nic *efx)
-{
- enum efx_phy_mode phy_mode;
- int rc;
-
- WARN_ON(!mutex_is_locked(&efx->mac_lock));
-
- /* Disable PHY transmit in mac level loopbacks */
- phy_mode = efx->phy_mode;
- if (LOOPBACK_INTERNAL(efx))
- efx->phy_mode |= PHY_MODE_TX_DISABLED;
- else
- efx->phy_mode &= ~PHY_MODE_TX_DISABLED;
-
- rc = efx->type->reconfigure_port(efx);
-
- if (rc)
- efx->phy_mode = phy_mode;
-
- return rc;
-}
-
-/* Reinitialise the MAC to pick up new PHY settings, even if the port is
- * disabled. */
-int efx_reconfigure_port(struct efx_nic *efx)
-{
- int rc;
-
- EFX_ASSERT_RESET_SERIALISED(efx);
-
- mutex_lock(&efx->mac_lock);
- rc = __efx_reconfigure_port(efx);
- mutex_unlock(&efx->mac_lock);
-
- return rc;
-}
-
-/* Asynchronous work item for changing MAC promiscuity and multicast
- * hash. Avoid a drain/rx_ingress enable by reconfiguring the current
- * MAC directly. */
-static void efx_mac_work(struct work_struct *data)
-{
- struct efx_nic *efx = container_of(data, struct efx_nic, mac_work);
-
- mutex_lock(&efx->mac_lock);
- if (efx->port_enabled)
- efx_mac_reconfigure(efx);
- mutex_unlock(&efx->mac_lock);
-}
-
static int efx_probe_port(struct efx_nic *efx)
{
int rc;
@@ -1155,44 +213,6 @@ static int efx_init_port(struct efx_nic *efx)
return rc;
}
-static void efx_start_port(struct efx_nic *efx)
-{
- netif_dbg(efx, ifup, efx->net_dev, "start port\n");
- BUG_ON(efx->port_enabled);
-
- mutex_lock(&efx->mac_lock);
- efx->port_enabled = true;
-
- /* Ensure MAC ingress/egress is enabled */
- efx_mac_reconfigure(efx);
-
- mutex_unlock(&efx->mac_lock);
-}
-
-/* Cancel work for MAC reconfiguration, periodic hardware monitoring
- * and the async self-test, wait for them to finish and prevent them
- * being scheduled again. This doesn't cover online resets, which
- * should only be cancelled when removing the device.
- */
-static void efx_stop_port(struct efx_nic *efx)
-{
- netif_dbg(efx, ifdown, efx->net_dev, "stop port\n");
-
- EFX_ASSERT_RESET_SERIALISED(efx);
-
- mutex_lock(&efx->mac_lock);
- efx->port_enabled = false;
- mutex_unlock(&efx->mac_lock);
-
- /* Serialise against efx_set_multicast_list() */
- netif_addr_lock_bh(efx->net_dev);
- netif_addr_unlock_bh(efx->net_dev);
-
- cancel_delayed_work_sync(&efx->monitor_work);
- efx_selftest_async_cancel(efx);
- cancel_work_sync(&efx->mac_work);
-}
-
static void efx_fini_port(struct efx_nic *efx)
{
netif_dbg(efx, drv, efx->net_dev, "shut down port\n");
@@ -1291,582 +311,6 @@ static void efx_dissociate(struct efx_nic *efx)
}
}
-/* This configures the PCI device to enable I/O and DMA. */
-static int efx_init_io(struct efx_nic *efx)
-{
- struct pci_dev *pci_dev = efx->pci_dev;
- dma_addr_t dma_mask = efx->type->max_dma_mask;
- unsigned int mem_map_size = efx->type->mem_map_size(efx);
- int rc, bar;
-
- netif_dbg(efx, probe, efx->net_dev, "initialising I/O\n");
-
- bar = efx->type->mem_bar(efx);
-
- rc = pci_enable_device(pci_dev);
- if (rc) {
- netif_err(efx, probe, efx->net_dev,
- "failed to enable PCI device\n");
- goto fail1;
- }
-
- pci_set_master(pci_dev);
-
- /* Set the PCI DMA mask. Try all possibilities from our genuine mask
- * down to 32 bits, because some architectures will allow 40 bit
- * masks event though they reject 46 bit masks.
- */
- while (dma_mask > 0x7fffffffUL) {
- rc = dma_set_mask_and_coherent(&pci_dev->dev, dma_mask);
- if (rc == 0)
- break;
- dma_mask >>= 1;
- }
- if (rc) {
- netif_err(efx, probe, efx->net_dev,
- "could not find a suitable DMA mask\n");
- goto fail2;
- }
- netif_dbg(efx, probe, efx->net_dev,
- "using DMA mask %llx\n", (unsigned long long) dma_mask);
-
- efx->membase_phys = pci_resource_start(efx->pci_dev, bar);
- rc = pci_request_region(pci_dev, bar, "sfc");
- if (rc) {
- netif_err(efx, probe, efx->net_dev,
- "request for memory BAR failed\n");
- rc = -EIO;
- goto fail3;
- }
- efx->membase = ioremap_nocache(efx->membase_phys, mem_map_size);
- if (!efx->membase) {
- netif_err(efx, probe, efx->net_dev,
- "could not map memory BAR at %llx+%x\n",
- (unsigned long long)efx->membase_phys, mem_map_size);
- rc = -ENOMEM;
- goto fail4;
- }
- netif_dbg(efx, probe, efx->net_dev,
- "memory BAR at %llx+%x (virtual %p)\n",
- (unsigned long long)efx->membase_phys, mem_map_size,
- efx->membase);
-
- return 0;
-
- fail4:
- pci_release_region(efx->pci_dev, bar);
- fail3:
- efx->membase_phys = 0;
- fail2:
- pci_disable_device(efx->pci_dev);
- fail1:
- return rc;
-}
-
-static void efx_fini_io(struct efx_nic *efx)
-{
- int bar;
-
- netif_dbg(efx, drv, efx->net_dev, "shutting down I/O\n");
-
- if (efx->membase) {
- iounmap(efx->membase);
- efx->membase = NULL;
- }
-
- if (efx->membase_phys) {
- bar = efx->type->mem_bar(efx);
- pci_release_region(efx->pci_dev, bar);
- efx->membase_phys = 0;
- }
-
- /* Don't disable bus-mastering if VFs are assigned */
- if (!pci_vfs_assigned(efx->pci_dev))
- pci_disable_device(efx->pci_dev);
-}
-
-void efx_set_default_rx_indir_table(struct efx_nic *efx,
- struct efx_rss_context *ctx)
-{
- size_t i;
-
- for (i = 0; i < ARRAY_SIZE(ctx->rx_indir_table); i++)
- ctx->rx_indir_table[i] =
- ethtool_rxfh_indir_default(i, efx->rss_spread);
-}
-
-static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
-{
- cpumask_var_t thread_mask;
- unsigned int count;
- int cpu;
-
- if (rss_cpus) {
- count = rss_cpus;
- } else {
- if (unlikely(!zalloc_cpumask_var(&thread_mask, GFP_KERNEL))) {
- netif_warn(efx, probe, efx->net_dev,
- "RSS disabled due to allocation failure\n");
- return 1;
- }
-
- count = 0;
- for_each_online_cpu(cpu) {
- if (!cpumask_test_cpu(cpu, thread_mask)) {
- ++count;
- cpumask_or(thread_mask, thread_mask,
- topology_sibling_cpumask(cpu));
- }
- }
-
- free_cpumask_var(thread_mask);
- }
-
- if (count > EFX_MAX_RX_QUEUES) {
- netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn,
- "Reducing number of rx queues from %u to %u.\n",
- count, EFX_MAX_RX_QUEUES);
- count = EFX_MAX_RX_QUEUES;
- }
-
- /* If RSS is requested for the PF *and* VFs then we can't write RSS
- * table entries that are inaccessible to VFs
- */
-#ifdef CONFIG_SFC_SRIOV
- if (efx->type->sriov_wanted) {
- if (efx->type->sriov_wanted(efx) && efx_vf_size(efx) > 1 &&
- count > efx_vf_size(efx)) {
- netif_warn(efx, probe, efx->net_dev,
- "Reducing number of RSS channels from %u to %u for "
- "VF support. Increase vf-msix-limit to use more "
- "channels on the PF.\n",
- count, efx_vf_size(efx));
- count = efx_vf_size(efx);
- }
- }
-#endif
-
- return count;
-}
-
-static int efx_allocate_msix_channels(struct efx_nic *efx,
- unsigned int max_channels,
- unsigned int extra_channels,
- unsigned int parallelism)
-{
- unsigned int n_channels = parallelism;
- int vec_count;
- int n_xdp_tx;
- int n_xdp_ev;
-
- if (efx_separate_tx_channels)
- n_channels *= 2;
- n_channels += extra_channels;
-
- /* To allow XDP transmit to happen from arbitrary NAPI contexts
- * we allocate a TX queue per CPU. We share event queues across
- * multiple tx queues, assuming tx and ev queues are both
- * maximum size.
- */
-
- n_xdp_tx = num_possible_cpus();
- n_xdp_ev = DIV_ROUND_UP(n_xdp_tx, EFX_TXQ_TYPES);
-
- vec_count = pci_msix_vec_count(efx->pci_dev);
- if (vec_count < 0)
- return vec_count;
-
- max_channels = min_t(unsigned int, vec_count, max_channels);
-
- /* Check resources.
- * We need a channel per event queue, plus a VI per tx queue.
- * This may be more pessimistic than it needs to be.
- */
- if (n_channels + n_xdp_ev > max_channels) {
- netif_err(efx, drv, efx->net_dev,
- "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n",
- n_xdp_ev, n_channels, max_channels);
- efx->n_xdp_channels = 0;
- efx->xdp_tx_per_channel = 0;
- efx->xdp_tx_queue_count = 0;
- } else {
- efx->n_xdp_channels = n_xdp_ev;
- efx->xdp_tx_per_channel = EFX_TXQ_TYPES;
- efx->xdp_tx_queue_count = n_xdp_tx;
- n_channels += n_xdp_ev;
- netif_dbg(efx, drv, efx->net_dev,
- "Allocating %d TX and %d event queues for XDP\n",
- n_xdp_tx, n_xdp_ev);
- }
-
- if (vec_count < n_channels) {
- netif_err(efx, drv, efx->net_dev,
- "WARNING: Insufficient MSI-X vectors available (%d < %u).\n",
- vec_count, n_channels);
- netif_err(efx, drv, efx->net_dev,
- "WARNING: Performance may be reduced.\n");
- n_channels = vec_count;
- }
-
- n_channels = min(n_channels, max_channels);
-
- efx->n_channels = n_channels;
-
- /* Ignore XDP tx channels when creating rx channels. */
- n_channels -= efx->n_xdp_channels;
-
- if (efx_separate_tx_channels) {
- efx->n_tx_channels =
- min(max(n_channels / 2, 1U),
- efx->max_tx_channels);
- efx->tx_channel_offset =
- n_channels - efx->n_tx_channels;
- efx->n_rx_channels =
- max(n_channels -
- efx->n_tx_channels, 1U);
- } else {
- efx->n_tx_channels = min(n_channels, efx->max_tx_channels);
- efx->tx_channel_offset = 0;
- efx->n_rx_channels = n_channels;
- }
-
- efx->n_rx_channels = min(efx->n_rx_channels, parallelism);
- efx->n_tx_channels = min(efx->n_tx_channels, parallelism);
-
- efx->xdp_channel_offset = n_channels;
-
- netif_dbg(efx, drv, efx->net_dev,
- "Allocating %u RX channels\n",
- efx->n_rx_channels);
-
- return efx->n_channels;
-}
-
-/* Probe the number and type of interrupts we are able to obtain, and
- * the resulting numbers of channels and RX queues.
- */
-static int efx_probe_interrupts(struct efx_nic *efx)
-{
- unsigned int extra_channels = 0;
- unsigned int rss_spread;
- unsigned int i, j;
- int rc;
-
- for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++)
- if (efx->extra_channel_type[i])
- ++extra_channels;
-
- if (efx->interrupt_mode == EFX_INT_MODE_MSIX) {
- unsigned int parallelism = efx_wanted_parallelism(efx);
- struct msix_entry xentries[EFX_MAX_CHANNELS];
- unsigned int n_channels;
-
- rc = efx_allocate_msix_channels(efx, efx->max_channels,
- extra_channels, parallelism);
- if (rc >= 0) {
- n_channels = rc;
- for (i = 0; i < n_channels; i++)
- xentries[i].entry = i;
- rc = pci_enable_msix_range(efx->pci_dev, xentries, 1,
- n_channels);
- }
- if (rc < 0) {
- /* Fall back to single channel MSI */
- netif_err(efx, drv, efx->net_dev,
- "could not enable MSI-X\n");
- if (efx->type->min_interrupt_mode >= EFX_INT_MODE_MSI)
- efx->interrupt_mode = EFX_INT_MODE_MSI;
- else
- return rc;
- } else if (rc < n_channels) {
- netif_err(efx, drv, efx->net_dev,
- "WARNING: Insufficient MSI-X vectors"
- " available (%d < %u).\n", rc, n_channels);
- netif_err(efx, drv, efx->net_dev,
- "WARNING: Performance may be reduced.\n");
- n_channels = rc;
- }
-
- if (rc > 0) {
- for (i = 0; i < efx->n_channels; i++)
- efx_get_channel(efx, i)->irq =
- xentries[i].vector;
- }
- }
-
- /* Try single interrupt MSI */
- if (efx->interrupt_mode == EFX_INT_MODE_MSI) {
- efx->n_channels = 1;
- efx->n_rx_channels = 1;
- efx->n_tx_channels = 1;
- efx->n_xdp_channels = 0;
- efx->xdp_channel_offset = efx->n_channels;
- rc = pci_enable_msi(efx->pci_dev);
- if (rc == 0) {
- efx_get_channel(efx, 0)->irq = efx->pci_dev->irq;
- } else {
- netif_err(efx, drv, efx->net_dev,
- "could not enable MSI\n");
- if (efx->type->min_interrupt_mode >= EFX_INT_MODE_LEGACY)
- efx->interrupt_mode = EFX_INT_MODE_LEGACY;
- else
- return rc;
- }
- }
-
- /* Assume legacy interrupts */
- if (efx->interrupt_mode == EFX_INT_MODE_LEGACY) {
- efx->n_channels = 1 + (efx_separate_tx_channels ? 1 : 0);
- efx->n_rx_channels = 1;
- efx->n_tx_channels = 1;
- efx->n_xdp_channels = 0;
- efx->xdp_channel_offset = efx->n_channels;
- efx->legacy_irq = efx->pci_dev->irq;
- }
-
- /* Assign extra channels if possible, before XDP channels */
- efx->n_extra_tx_channels = 0;
- j = efx->xdp_channel_offset;
- for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++) {
- if (!efx->extra_channel_type[i])
- continue;
- if (j <= efx->tx_channel_offset + efx->n_tx_channels) {
- efx->extra_channel_type[i]->handle_no_channel(efx);
- } else {
- --j;
- efx_get_channel(efx, j)->type =
- efx->extra_channel_type[i];
- if (efx_channel_has_tx_queues(efx_get_channel(efx, j)))
- efx->n_extra_tx_channels++;
- }
- }
-
- rss_spread = efx->n_rx_channels;
- /* RSS might be usable on VFs even if it is disabled on the PF */
-#ifdef CONFIG_SFC_SRIOV
- if (efx->type->sriov_wanted) {
- efx->rss_spread = ((rss_spread > 1 ||
- !efx->type->sriov_wanted(efx)) ?
- rss_spread : efx_vf_size(efx));
- return 0;
- }
-#endif
- efx->rss_spread = rss_spread;
-
- return 0;
-}
-
-#if defined(CONFIG_SMP)
-static void efx_set_interrupt_affinity(struct efx_nic *efx)
-{
- struct efx_channel *channel;
- unsigned int cpu;
-
- efx_for_each_channel(channel, efx) {
- cpu = cpumask_local_spread(channel->channel,
- pcibus_to_node(efx->pci_dev->bus));
- irq_set_affinity_hint(channel->irq, cpumask_of(cpu));
- }
-}
-
-static void efx_clear_interrupt_affinity(struct efx_nic *efx)
-{
- struct efx_channel *channel;
-
- efx_for_each_channel(channel, efx)
- irq_set_affinity_hint(channel->irq, NULL);
-}
-#else
-static void
-efx_set_interrupt_affinity(struct efx_nic *efx __attribute__ ((unused)))
-{
-}
-
-static void
-efx_clear_interrupt_affinity(struct efx_nic *efx __attribute__ ((unused)))
-{
-}
-#endif /* CONFIG_SMP */
-
-static int efx_soft_enable_interrupts(struct efx_nic *efx)
-{
- struct efx_channel *channel, *end_channel;
- int rc;
-
- BUG_ON(efx->state == STATE_DISABLED);
-
- efx->irq_soft_enabled = true;
- smp_wmb();
-
- efx_for_each_channel(channel, efx) {
- if (!channel->type->keep_eventq) {
- rc = efx_init_eventq(channel);
- if (rc)
- goto fail;
- }
- efx_start_eventq(channel);
- }
-
- efx_mcdi_mode_event(efx);
-
- return 0;
-fail:
- end_channel = channel;
- efx_for_each_channel(channel, efx) {
- if (channel == end_channel)
- break;
- efx_stop_eventq(channel);
- if (!channel->type->keep_eventq)
- efx_fini_eventq(channel);
- }
-
- return rc;
-}
-
-static void efx_soft_disable_interrupts(struct efx_nic *efx)
-{
- struct efx_channel *channel;
-
- if (efx->state == STATE_DISABLED)
- return;
-
- efx_mcdi_mode_poll(efx);
-
- efx->irq_soft_enabled = false;
- smp_wmb();
-
- if (efx->legacy_irq)
- synchronize_irq(efx->legacy_irq);
-
- efx_for_each_channel(channel, efx) {
- if (channel->irq)
- synchronize_irq(channel->irq);
-
- efx_stop_eventq(channel);
- if (!channel->type->keep_eventq)
- efx_fini_eventq(channel);
- }
-
- /* Flush the asynchronous MCDI request queue */
- efx_mcdi_flush_async(efx);
-}
-
-static int efx_enable_interrupts(struct efx_nic *efx)
-{
- struct efx_channel *channel, *end_channel;
- int rc;
-
- BUG_ON(efx->state == STATE_DISABLED);
-
- if (efx->eeh_disabled_legacy_irq) {
- enable_irq(efx->legacy_irq);
- efx->eeh_disabled_legacy_irq = false;
- }
-
- efx->type->irq_enable_master(efx);
-
- efx_for_each_channel(channel, efx) {
- if (channel->type->keep_eventq) {
- rc = efx_init_eventq(channel);
- if (rc)
- goto fail;
- }
- }
-
- rc = efx_soft_enable_interrupts(efx);
- if (rc)
- goto fail;
-
- return 0;
-
-fail:
- end_channel = channel;
- efx_for_each_channel(channel, efx) {
- if (channel == end_channel)
- break;
- if (channel->type->keep_eventq)
- efx_fini_eventq(channel);
- }
-
- efx->type->irq_disable_non_ev(efx);
-
- return rc;
-}
-
-static void efx_disable_interrupts(struct efx_nic *efx)
-{
- struct efx_channel *channel;
-
- efx_soft_disable_interrupts(efx);
-
- efx_for_each_channel(channel, efx) {
- if (channel->type->keep_eventq)
- efx_fini_eventq(channel);
- }
-
- efx->type->irq_disable_non_ev(efx);
-}
-
-static void efx_remove_interrupts(struct efx_nic *efx)
-{
- struct efx_channel *channel;
-
- /* Remove MSI/MSI-X interrupts */
- efx_for_each_channel(channel, efx)
- channel->irq = 0;
- pci_disable_msi(efx->pci_dev);
- pci_disable_msix(efx->pci_dev);
-
- /* Remove legacy interrupt */
- efx->legacy_irq = 0;
-}
-
-static int efx_set_channels(struct efx_nic *efx)
-{
- struct efx_channel *channel;
- struct efx_tx_queue *tx_queue;
- int xdp_queue_number;
-
- efx->tx_channel_offset =
- efx_separate_tx_channels ?
- efx->n_channels - efx->n_tx_channels : 0;
-
- if (efx->xdp_tx_queue_count) {
- EFX_WARN_ON_PARANOID(efx->xdp_tx_queues);
-
- /* Allocate array for XDP TX queue lookup. */
- efx->xdp_tx_queues = kcalloc(efx->xdp_tx_queue_count,
- sizeof(*efx->xdp_tx_queues),
- GFP_KERNEL);
- if (!efx->xdp_tx_queues)
- return -ENOMEM;
- }
-
- /* We need to mark which channels really have RX and TX
- * queues, and adjust the TX queue numbers if we have separate
- * RX-only and TX-only channels.
- */
- xdp_queue_number = 0;
- efx_for_each_channel(channel, efx) {
- if (channel->channel < efx->n_rx_channels)
- channel->rx_queue.core_index = channel->channel;
- else
- channel->rx_queue.core_index = -1;
-
- efx_for_each_channel_tx_queue(tx_queue, channel) {
- tx_queue->queue -= (efx->tx_channel_offset *
- EFX_TXQ_TYPES);
-
- if (efx_channel_is_xdp_tx(channel) &&
- xdp_queue_number < efx->xdp_tx_queue_count) {
- efx->xdp_tx_queues[xdp_queue_number] = tx_queue;
- xdp_queue_number++;
- }
- }
- }
- return 0;
-}
-
static int efx_probe_nic(struct efx_nic *efx)
{
int rc;
@@ -1939,70 +383,6 @@ static void efx_remove_nic(struct efx_nic *efx)
efx->type->remove(efx);
}
-static int efx_probe_filters(struct efx_nic *efx)
-{
- int rc;
-
- init_rwsem(&efx->filter_sem);
- mutex_lock(&efx->mac_lock);
- down_write(&efx->filter_sem);
- rc = efx->type->filter_table_probe(efx);
- if (rc)
- goto out_unlock;
-
-#ifdef CONFIG_RFS_ACCEL
- if (efx->type->offload_features & NETIF_F_NTUPLE) {
- struct efx_channel *channel;
- int i, success = 1;
-
- efx_for_each_channel(channel, efx) {
- channel->rps_flow_id =
- kcalloc(efx->type->max_rx_ip_filters,
- sizeof(*channel->rps_flow_id),
- GFP_KERNEL);
- if (!channel->rps_flow_id)
- success = 0;
- else
- for (i = 0;
- i < efx->type->max_rx_ip_filters;
- ++i)
- channel->rps_flow_id[i] =
- RPS_FLOW_ID_INVALID;
- channel->rfs_expire_index = 0;
- channel->rfs_filter_count = 0;
- }
-
- if (!success) {
- efx_for_each_channel(channel, efx)
- kfree(channel->rps_flow_id);
- efx->type->filter_table_remove(efx);
- rc = -ENOMEM;
- goto out_unlock;
- }
- }
-#endif
-out_unlock:
- up_write(&efx->filter_sem);
- mutex_unlock(&efx->mac_lock);
- return rc;
-}
-
-static void efx_remove_filters(struct efx_nic *efx)
-{
-#ifdef CONFIG_RFS_ACCEL
- struct efx_channel *channel;
-
- efx_for_each_channel(channel, efx) {
- cancel_delayed_work_sync(&channel->filter_work);
- kfree(channel->rps_flow_id);
- }
-#endif
- down_write(&efx->filter_sem);
- efx->type->filter_table_remove(efx);
- up_write(&efx->filter_sem);
-}
-
-
/**************************************************************************
*
* NIC startup/shutdown
@@ -2067,81 +447,6 @@ static int efx_probe_all(struct efx_nic *efx)
return rc;
}
-/* If the interface is supposed to be running but is not, start
- * the hardware and software data path, regular activity for the port
- * (MAC statistics, link polling, etc.) and schedule the port to be
- * reconfigured. Interrupts must already be enabled. This function
- * is safe to call multiple times, so long as the NIC is not disabled.
- * Requires the RTNL lock.
- */
-static void efx_start_all(struct efx_nic *efx)
-{
- EFX_ASSERT_RESET_SERIALISED(efx);
- BUG_ON(efx->state == STATE_DISABLED);
-
- /* Check that it is appropriate to restart the interface. All
- * of these flags are safe to read under just the rtnl lock */
- if (efx->port_enabled || !netif_running(efx->net_dev) ||
- efx->reset_pending)
- return;
-
- efx_start_port(efx);
- efx_start_datapath(efx);
-
- /* Start the hardware monitor if there is one */
- if (efx->type->monitor != NULL)
- queue_delayed_work(efx->workqueue, &efx->monitor_work,
- efx_monitor_interval);
-
- /* Link state detection is normally event-driven; we have
- * to poll now because we could have missed a change
- */
- mutex_lock(&efx->mac_lock);
- if (efx->phy_op->poll(efx))
- efx_link_status_changed(efx);
- mutex_unlock(&efx->mac_lock);
-
- efx->type->start_stats(efx);
- efx->type->pull_stats(efx);
- spin_lock_bh(&efx->stats_lock);
- efx->type->update_stats(efx, NULL, NULL);
- spin_unlock_bh(&efx->stats_lock);
-}
-
-/* Quiesce the hardware and software data path, and regular activity
- * for the port without bringing the link down. Safe to call multiple
- * times with the NIC in almost any state, but interrupts should be
- * enabled. Requires the RTNL lock.
- */
-static void efx_stop_all(struct efx_nic *efx)
-{
- EFX_ASSERT_RESET_SERIALISED(efx);
-
- /* port_enabled can be read safely under the rtnl lock */
- if (!efx->port_enabled)
- return;
-
- /* update stats before we go down so we can accurately count
- * rx_nodesc_drops
- */
- efx->type->pull_stats(efx);
- spin_lock_bh(&efx->stats_lock);
- efx->type->update_stats(efx, NULL, NULL);
- spin_unlock_bh(&efx->stats_lock);
- efx->type->stop_stats(efx);
- efx_stop_port(efx);
-
- /* Stop the kernel transmit interface. This is only valid if
- * the device is stopped or detached; otherwise the watchdog
- * may fire immediately.
- */
- WARN_ON(netif_running(efx->net_dev) &&
- netif_device_present(efx->net_dev));
- netif_tx_disable(efx->net_dev);
-
- efx_stop_datapath(efx);
-}
-
static void efx_remove_all(struct efx_nic *efx)
{
rtnl_lock();
@@ -2237,36 +542,6 @@ void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
/**************************************************************************
*
- * Hardware monitor
- *
- **************************************************************************/
-
-/* Run periodically off the general workqueue */
-static void efx_monitor(struct work_struct *data)
-{
- struct efx_nic *efx = container_of(data, struct efx_nic,
- monitor_work.work);
-
- netif_vdbg(efx, timer, efx->net_dev,
- "hardware monitor executing on CPU %d\n",
- raw_smp_processor_id());
- BUG_ON(efx->type->monitor == NULL);
-
- /* If the mac_lock is already held then it is likely a port
- * reconfiguration is already in place, which will likely do
- * most of the work of monitor() anyway. */
- if (mutex_trylock(&efx->mac_lock)) {
- if (efx->port_enabled)
- efx->type->monitor(efx);
- mutex_unlock(&efx->mac_lock);
- }
-
- queue_delayed_work(efx->workqueue, &efx->monitor_work,
- efx_monitor_interval);
-}
-
-/**************************************************************************
- *
* ioctls
*
*************************************************************************/
@@ -2294,45 +569,6 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
/**************************************************************************
*
- * NAPI interface
- *
- **************************************************************************/
-
-static void efx_init_napi_channel(struct efx_channel *channel)
-{
- struct efx_nic *efx = channel->efx;
-
- channel->napi_dev = efx->net_dev;
- netif_napi_add(channel->napi_dev, &channel->napi_str,
- efx_poll, napi_weight);
-}
-
-static void efx_init_napi(struct efx_nic *efx)
-{
- struct efx_channel *channel;
-
- efx_for_each_channel(channel, efx)
- efx_init_napi_channel(channel);
-}
-
-static void efx_fini_napi_channel(struct efx_channel *channel)
-{
- if (channel->napi_dev)
- netif_napi_del(&channel->napi_str);
-
- channel->napi_dev = NULL;
-}
-
-static void efx_fini_napi(struct efx_nic *efx)
-{
- struct efx_channel *channel;
-
- efx_for_each_channel(channel, efx)
- efx_fini_napi_channel(channel);
-}
-
-/**************************************************************************
- *
* Kernel net device interface
*
*************************************************************************/
@@ -2382,17 +618,6 @@ int efx_net_stop(struct net_device *net_dev)
return 0;
}
-/* Context: process, dev_base_lock or RTNL held, non-blocking. */
-static void efx_net_stats(struct net_device *net_dev,
- struct rtnl_link_stats64 *stats)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
-
- spin_lock_bh(&efx->stats_lock);
- efx->type->update_stats(efx, NULL, stats);
- spin_unlock_bh(&efx->stats_lock);
-}
-
/* Context: netif_tx_lock held, BHs disabled. */
static void efx_watchdog(struct net_device *net_dev, unsigned int txqueue)
{
@@ -2405,51 +630,6 @@ static void efx_watchdog(struct net_device *net_dev, unsigned int txqueue)
efx_schedule_reset(efx, RESET_TYPE_TX_WATCHDOG);
}
-static unsigned int efx_xdp_max_mtu(struct efx_nic *efx)
-{
- /* The maximum MTU that we can fit in a single page, allowing for
- * framing, overhead and XDP headroom.
- */
- int overhead = EFX_MAX_FRAME_LEN(0) + sizeof(struct efx_rx_page_state) +
- efx->rx_prefix_size + efx->type->rx_buffer_padding +
- efx->rx_ip_align + XDP_PACKET_HEADROOM;
-
- return PAGE_SIZE - overhead;
-}
-
-/* Context: process, rtnl_lock() held. */
-static int efx_change_mtu(struct net_device *net_dev, int new_mtu)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
- int rc;
-
- rc = efx_check_disabled(efx);
- if (rc)
- return rc;
-
- if (rtnl_dereference(efx->xdp_prog) &&
- new_mtu > efx_xdp_max_mtu(efx)) {
- netif_err(efx, drv, efx->net_dev,
- "Requested MTU of %d too big for XDP (max: %d)\n",
- new_mtu, efx_xdp_max_mtu(efx));
- return -EINVAL;
- }
-
- netif_dbg(efx, drv, efx->net_dev, "changing MTU to %d\n", new_mtu);
-
- efx_device_detach_sync(efx);
- efx_stop_all(efx);
-
- mutex_lock(&efx->mac_lock);
- net_dev->mtu = new_mtu;
- efx_mac_reconfigure(efx);
- mutex_unlock(&efx->mac_lock);
-
- efx_start_all(efx);
- efx_device_attach_if_not_resetting(efx);
- return 0;
-}
-
static int efx_set_mac_address(struct net_device *net_dev, void *data)
{
struct efx_nic *efx = netdev_priv(net_dev);
@@ -2726,28 +906,6 @@ show_phy_type(struct device *dev, struct device_attribute *attr, char *buf)
}
static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL);
-#ifdef CONFIG_SFC_MCDI_LOGGING
-static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct efx_nic *efx = dev_get_drvdata(dev);
- struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
-
- return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled);
-}
-static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct efx_nic *efx = dev_get_drvdata(dev);
- struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
- bool enable = count > 0 && *buf != '0';
-
- mcdi->logging_enabled = enable;
- return count;
-}
-static DEVICE_ATTR(mcdi_logging, 0644, show_mcdi_log, set_mcdi_log);
-#endif
-
static int efx_register_netdev(struct efx_nic *efx)
{
struct net_device *net_dev = efx->net_dev;
@@ -2807,21 +965,11 @@ static int efx_register_netdev(struct efx_nic *efx)
"failed to init net dev attributes\n");
goto fail_registered;
}
-#ifdef CONFIG_SFC_MCDI_LOGGING
- rc = device_create_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging);
- if (rc) {
- netif_err(efx, drv, efx->net_dev,
- "failed to init net dev attributes\n");
- goto fail_attr_mcdi_logging;
- }
-#endif
+
+ efx_init_mcdi_logging(efx);
return 0;
-#ifdef CONFIG_SFC_MCDI_LOGGING
-fail_attr_mcdi_logging:
- device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
-#endif
fail_registered:
rtnl_lock();
efx_dissociate(efx);
@@ -2842,9 +990,7 @@ static void efx_unregister_netdev(struct efx_nic *efx)
if (efx_dev_registered(efx)) {
strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
-#ifdef CONFIG_SFC_MCDI_LOGGING
- device_remove_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging);
-#endif
+ efx_fini_mcdi_logging(efx);
device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
unregister_netdev(efx->net_dev);
}
@@ -2852,292 +998,6 @@ static void efx_unregister_netdev(struct efx_nic *efx)
/**************************************************************************
*
- * Device reset and suspend
- *
- **************************************************************************/
-
-/* Tears down the entire software state and most of the hardware state
- * before reset. */
-void efx_reset_down(struct efx_nic *efx, enum reset_type method)
-{
- EFX_ASSERT_RESET_SERIALISED(efx);
-
- if (method == RESET_TYPE_MCDI_TIMEOUT)
- efx->type->prepare_flr(efx);
-
- efx_stop_all(efx);
- efx_disable_interrupts(efx);
-
- mutex_lock(&efx->mac_lock);
- down_write(&efx->filter_sem);
- mutex_lock(&efx->rss_lock);
- if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
- method != RESET_TYPE_DATAPATH)
- efx->phy_op->fini(efx);
- efx->type->fini(efx);
-}
-
-/* This function will always ensure that the locks acquired in
- * efx_reset_down() are released. A failure return code indicates
- * that we were unable to reinitialise the hardware, and the
- * driver should be disabled. If ok is false, then the rx and tx
- * engines are not restarted, pending a RESET_DISABLE. */
-int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
-{
- int rc;
-
- EFX_ASSERT_RESET_SERIALISED(efx);
-
- if (method == RESET_TYPE_MCDI_TIMEOUT)
- efx->type->finish_flr(efx);
-
- /* Ensure that SRAM is initialised even if we're disabling the device */
- rc = efx->type->init(efx);
- if (rc) {
- netif_err(efx, drv, efx->net_dev, "failed to initialise NIC\n");
- goto fail;
- }
-
- if (!ok)
- goto fail;
-
- if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
- method != RESET_TYPE_DATAPATH) {
- rc = efx->phy_op->init(efx);
- if (rc)
- goto fail;
- rc = efx->phy_op->reconfigure(efx);
- if (rc && rc != -EPERM)
- netif_err(efx, drv, efx->net_dev,
- "could not restore PHY settings\n");
- }
-
- rc = efx_enable_interrupts(efx);
- if (rc)
- goto fail;
-
-#ifdef CONFIG_SFC_SRIOV
- rc = efx->type->vswitching_restore(efx);
- if (rc) /* not fatal; the PF will still work fine */
- netif_warn(efx, probe, efx->net_dev,
- "failed to restore vswitching rc=%d;"
- " VFs may not function\n", rc);
-#endif
-
- if (efx->type->rx_restore_rss_contexts)
- efx->type->rx_restore_rss_contexts(efx);
- mutex_unlock(&efx->rss_lock);
- efx->type->filter_table_restore(efx);
- up_write(&efx->filter_sem);
- if (efx->type->sriov_reset)
- efx->type->sriov_reset(efx);
-
- mutex_unlock(&efx->mac_lock);
-
- efx_start_all(efx);
-
- if (efx->type->udp_tnl_push_ports)
- efx->type->udp_tnl_push_ports(efx);
-
- return 0;
-
-fail:
- efx->port_initialized = false;
-
- mutex_unlock(&efx->rss_lock);
- up_write(&efx->filter_sem);
- mutex_unlock(&efx->mac_lock);
-
- return rc;
-}
-
-/* Reset the NIC using the specified method. Note that the reset may
- * fail, in which case the card will be left in an unusable state.
- *
- * Caller must hold the rtnl_lock.
- */
-int efx_reset(struct efx_nic *efx, enum reset_type method)
-{
- int rc, rc2;
- bool disabled;
-
- netif_info(efx, drv, efx->net_dev, "resetting (%s)\n",
- RESET_TYPE(method));
-
- efx_device_detach_sync(efx);
- efx_reset_down(efx, method);
-
- rc = efx->type->reset(efx, method);
- if (rc) {
- netif_err(efx, drv, efx->net_dev, "failed to reset hardware\n");
- goto out;
- }
-
- /* Clear flags for the scopes we covered. We assume the NIC and
- * driver are now quiescent so that there is no race here.
- */
- if (method < RESET_TYPE_MAX_METHOD)
- efx->reset_pending &= -(1 << (method + 1));
- else /* it doesn't fit into the well-ordered scope hierarchy */
- __clear_bit(method, &efx->reset_pending);
-
- /* Reinitialise bus-mastering, which may have been turned off before
- * the reset was scheduled. This is still appropriate, even in the
- * RESET_TYPE_DISABLE since this driver generally assumes the hardware
- * can respond to requests. */
- pci_set_master(efx->pci_dev);
-
-out:
- /* Leave device stopped if necessary */
- disabled = rc ||
- method == RESET_TYPE_DISABLE ||
- method == RESET_TYPE_RECOVER_OR_DISABLE;
- rc2 = efx_reset_up(efx, method, !disabled);
- if (rc2) {
- disabled = true;
- if (!rc)
- rc = rc2;
- }
-
- if (disabled) {
- dev_close(efx->net_dev);
- netif_err(efx, drv, efx->net_dev, "has been disabled\n");
- efx->state = STATE_DISABLED;
- } else {
- netif_dbg(efx, drv, efx->net_dev, "reset complete\n");
- efx_device_attach_if_not_resetting(efx);
- }
- return rc;
-}
-
-/* Try recovery mechanisms.
- * For now only EEH is supported.
- * Returns 0 if the recovery mechanisms are unsuccessful.
- * Returns a non-zero value otherwise.
- */
-int efx_try_recovery(struct efx_nic *efx)
-{
-#ifdef CONFIG_EEH
- /* A PCI error can occur and not be seen by EEH because nothing
- * happens on the PCI bus. In this case the driver may fail and
- * schedule a 'recover or reset', leading to this recovery handler.
- * Manually call the eeh failure check function.
- */
- struct eeh_dev *eehdev = pci_dev_to_eeh_dev(efx->pci_dev);
- if (eeh_dev_check_failure(eehdev)) {
- /* The EEH mechanisms will handle the error and reset the
- * device if necessary.
- */
- return 1;
- }
-#endif
- return 0;
-}
-
-static void efx_wait_for_bist_end(struct efx_nic *efx)
-{
- int i;
-
- for (i = 0; i < BIST_WAIT_DELAY_COUNT; ++i) {
- if (efx_mcdi_poll_reboot(efx))
- goto out;
- msleep(BIST_WAIT_DELAY_MS);
- }
-
- netif_err(efx, drv, efx->net_dev, "Warning: No MC reboot after BIST mode\n");
-out:
- /* Either way unset the BIST flag. If we found no reboot we probably
- * won't recover, but we should try.
- */
- efx->mc_bist_for_other_fn = false;
-}
-
-/* The worker thread exists so that code that cannot sleep can
- * schedule a reset for later.
- */
-static void efx_reset_work(struct work_struct *data)
-{
- struct efx_nic *efx = container_of(data, struct efx_nic, reset_work);
- unsigned long pending;
- enum reset_type method;
-
- pending = READ_ONCE(efx->reset_pending);
- method = fls(pending) - 1;
-
- if (method == RESET_TYPE_MC_BIST)
- efx_wait_for_bist_end(efx);
-
- if ((method == RESET_TYPE_RECOVER_OR_DISABLE ||
- method == RESET_TYPE_RECOVER_OR_ALL) &&
- efx_try_recovery(efx))
- return;
-
- if (!pending)
- return;
-
- rtnl_lock();
-
- /* We checked the state in efx_schedule_reset() but it may
- * have changed by now. Now that we have the RTNL lock,
- * it cannot change again.
- */
- if (efx->state == STATE_READY)
- (void)efx_reset(efx, method);
-
- rtnl_unlock();
-}
-
-void efx_schedule_reset(struct efx_nic *efx, enum reset_type type)
-{
- enum reset_type method;
-
- if (efx->state == STATE_RECOVERY) {
- netif_dbg(efx, drv, efx->net_dev,
- "recovering: skip scheduling %s reset\n",
- RESET_TYPE(type));
- return;
- }
-
- switch (type) {
- case RESET_TYPE_INVISIBLE:
- case RESET_TYPE_ALL:
- case RESET_TYPE_RECOVER_OR_ALL:
- case RESET_TYPE_WORLD:
- case RESET_TYPE_DISABLE:
- case RESET_TYPE_RECOVER_OR_DISABLE:
- case RESET_TYPE_DATAPATH:
- case RESET_TYPE_MC_BIST:
- case RESET_TYPE_MCDI_TIMEOUT:
- method = type;
- netif_dbg(efx, drv, efx->net_dev, "scheduling %s reset\n",
- RESET_TYPE(method));
- break;
- default:
- method = efx->type->map_reset_reason(type);
- netif_dbg(efx, drv, efx->net_dev,
- "scheduling %s reset for %s\n",
- RESET_TYPE(method), RESET_TYPE(type));
- break;
- }
-
- set_bit(method, &efx->reset_pending);
- smp_mb(); /* ensure we change reset_pending before checking state */
-
- /* If we're not READY then just leave the flags set as the cue
- * to abort probing or reschedule the reset later.
- */
- if (READ_ONCE(efx->state) != STATE_READY)
- return;
-
- /* efx_process_channel() will no longer read events once a
- * reset is scheduled. So switch back to poll'd MCDI completions. */
- efx_mcdi_mode_poll(efx);
-
- queue_work(reset_workqueue, &efx->reset_work);
-}
-
-/**************************************************************************
- *
* List of NICs we support
*
**************************************************************************/
@@ -3169,139 +1029,10 @@ static const struct pci_device_id efx_pci_table[] = {
/**************************************************************************
*
- * Dummy PHY/MAC operations
- *
- * Can be used for some unimplemented operations
- * Needed so all function pointers are valid and do not have to be tested
- * before use
- *
- **************************************************************************/
-int efx_port_dummy_op_int(struct efx_nic *efx)
-{
- return 0;
-}
-void efx_port_dummy_op_void(struct efx_nic *efx) {}
-
-static bool efx_port_dummy_op_poll(struct efx_nic *efx)
-{
- return false;
-}
-
-static const struct efx_phy_operations efx_dummy_phy_operations = {
- .init = efx_port_dummy_op_int,
- .reconfigure = efx_port_dummy_op_int,
- .poll = efx_port_dummy_op_poll,
- .fini = efx_port_dummy_op_void,
-};
-
-/**************************************************************************
- *
* Data housekeeping
*
**************************************************************************/
-/* This zeroes out and then fills in the invariants in a struct
- * efx_nic (including all sub-structures).
- */
-static int efx_init_struct(struct efx_nic *efx,
- struct pci_dev *pci_dev, struct net_device *net_dev)
-{
- int rc = -ENOMEM, i;
-
- /* Initialise common structures */
- INIT_LIST_HEAD(&efx->node);
- INIT_LIST_HEAD(&efx->secondary_list);
- spin_lock_init(&efx->biu_lock);
-#ifdef CONFIG_SFC_MTD
- INIT_LIST_HEAD(&efx->mtd_list);
-#endif
- INIT_WORK(&efx->reset_work, efx_reset_work);
- INIT_DELAYED_WORK(&efx->monitor_work, efx_monitor);
- INIT_DELAYED_WORK(&efx->selftest_work, efx_selftest_async_work);
- efx->pci_dev = pci_dev;
- efx->msg_enable = debug;
- efx->state = STATE_UNINIT;
- strlcpy(efx->name, pci_name(pci_dev), sizeof(efx->name));
-
- efx->net_dev = net_dev;
- efx->rx_prefix_size = efx->type->rx_prefix_size;
- efx->rx_ip_align =
- NET_IP_ALIGN ? (efx->rx_prefix_size + NET_IP_ALIGN) % 4 : 0;
- efx->rx_packet_hash_offset =
- efx->type->rx_hash_offset - efx->type->rx_prefix_size;
- efx->rx_packet_ts_offset =
- efx->type->rx_ts_offset - efx->type->rx_prefix_size;
- INIT_LIST_HEAD(&efx->rss_context.list);
- mutex_init(&efx->rss_lock);
- spin_lock_init(&efx->stats_lock);
- efx->vi_stride = EFX_DEFAULT_VI_STRIDE;
- efx->num_mac_stats = MC_CMD_MAC_NSTATS;
- BUILD_BUG_ON(MC_CMD_MAC_NSTATS - 1 != MC_CMD_MAC_GENERATION_END);
- mutex_init(&efx->mac_lock);
-#ifdef CONFIG_RFS_ACCEL
- mutex_init(&efx->rps_mutex);
- spin_lock_init(&efx->rps_hash_lock);
- /* Failure to allocate is not fatal, but may degrade ARFS performance */
- efx->rps_hash_table = kcalloc(EFX_ARFS_HASH_TABLE_SIZE,
- sizeof(*efx->rps_hash_table), GFP_KERNEL);
-#endif
- efx->phy_op = &efx_dummy_phy_operations;
- efx->mdio.dev = net_dev;
- INIT_WORK(&efx->mac_work, efx_mac_work);
- init_waitqueue_head(&efx->flush_wq);
-
- for (i = 0; i < EFX_MAX_CHANNELS; i++) {
- efx->channel[i] = efx_alloc_channel(efx, i, NULL);
- if (!efx->channel[i])
- goto fail;
- efx->msi_context[i].efx = efx;
- efx->msi_context[i].index = i;
- }
-
- /* Higher numbered interrupt modes are less capable! */
- if (WARN_ON_ONCE(efx->type->max_interrupt_mode >
- efx->type->min_interrupt_mode)) {
- rc = -EIO;
- goto fail;
- }
- efx->interrupt_mode = max(efx->type->max_interrupt_mode,
- interrupt_mode);
- efx->interrupt_mode = min(efx->type->min_interrupt_mode,
- interrupt_mode);
-
- /* Would be good to use the net_dev name, but we're too early */
- snprintf(efx->workqueue_name, sizeof(efx->workqueue_name), "sfc%s",
- pci_name(pci_dev));
- efx->workqueue = create_singlethread_workqueue(efx->workqueue_name);
- if (!efx->workqueue)
- goto fail;
-
- return 0;
-
-fail:
- efx_fini_struct(efx);
- return rc;
-}
-
-static void efx_fini_struct(struct efx_nic *efx)
-{
- int i;
-
-#ifdef CONFIG_RFS_ACCEL
- kfree(efx->rps_hash_table);
-#endif
-
- for (i = 0; i < EFX_MAX_CHANNELS; i++)
- kfree(efx->channel[i]);
-
- kfree(efx->vpd_sn);
-
- if (efx->workqueue) {
- destroy_workqueue(efx->workqueue);
- efx->workqueue = NULL;
- }
-}
-
void efx_update_sw_stats(struct efx_nic *efx, u64 *stats)
{
u64 n_rx_nodesc_trunc = 0;
@@ -3313,197 +1044,6 @@ void efx_update_sw_stats(struct efx_nic *efx, u64 *stats)
stats[GENERIC_STAT_rx_noskb_drops] = atomic_read(&efx->n_rx_noskb_drops);
}
-bool efx_filter_spec_equal(const struct efx_filter_spec *left,
- const struct efx_filter_spec *right)
-{
- if ((left->match_flags ^ right->match_flags) |
- ((left->flags ^ right->flags) &
- (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
- return false;
-
- return memcmp(&left->outer_vid, &right->outer_vid,
- sizeof(struct efx_filter_spec) -
- offsetof(struct efx_filter_spec, outer_vid)) == 0;
-}
-
-u32 efx_filter_spec_hash(const struct efx_filter_spec *spec)
-{
- BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
- return jhash2((const u32 *)&spec->outer_vid,
- (sizeof(struct efx_filter_spec) -
- offsetof(struct efx_filter_spec, outer_vid)) / 4,
- 0);
-}
-
-#ifdef CONFIG_RFS_ACCEL
-bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
- bool *force)
-{
- if (rule->filter_id == EFX_ARFS_FILTER_ID_PENDING) {
- /* ARFS is currently updating this entry, leave it */
- return false;
- }
- if (rule->filter_id == EFX_ARFS_FILTER_ID_ERROR) {
- /* ARFS tried and failed to update this, so it's probably out
- * of date. Remove the filter and the ARFS rule entry.
- */
- rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
- *force = true;
- return true;
- } else if (WARN_ON(rule->filter_id != filter_idx)) { /* can't happen */
- /* ARFS has moved on, so old filter is not needed. Since we did
- * not mark the rule with EFX_ARFS_FILTER_ID_REMOVING, it will
- * not be removed by efx_rps_hash_del() subsequently.
- */
- *force = true;
- return true;
- }
- /* Remove it iff ARFS wants to. */
- return true;
-}
-
-static
-struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
- const struct efx_filter_spec *spec)
-{
- u32 hash = efx_filter_spec_hash(spec);
-
- lockdep_assert_held(&efx->rps_hash_lock);
- if (!efx->rps_hash_table)
- return NULL;
- return &efx->rps_hash_table[hash % EFX_ARFS_HASH_TABLE_SIZE];
-}
-
-struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
- const struct efx_filter_spec *spec)
-{
- struct efx_arfs_rule *rule;
- struct hlist_head *head;
- struct hlist_node *node;
-
- head = efx_rps_hash_bucket(efx, spec);
- if (!head)
- return NULL;
- hlist_for_each(node, head) {
- rule = container_of(node, struct efx_arfs_rule, node);
- if (efx_filter_spec_equal(spec, &rule->spec))
- return rule;
- }
- return NULL;
-}
-
-struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
- const struct efx_filter_spec *spec,
- bool *new)
-{
- struct efx_arfs_rule *rule;
- struct hlist_head *head;
- struct hlist_node *node;
-
- head = efx_rps_hash_bucket(efx, spec);
- if (!head)
- return NULL;
- hlist_for_each(node, head) {
- rule = container_of(node, struct efx_arfs_rule, node);
- if (efx_filter_spec_equal(spec, &rule->spec)) {
- *new = false;
- return rule;
- }
- }
- rule = kmalloc(sizeof(*rule), GFP_ATOMIC);
- *new = true;
- if (rule) {
- memcpy(&rule->spec, spec, sizeof(rule->spec));
- hlist_add_head(&rule->node, head);
- }
- return rule;
-}
-
-void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec)
-{
- struct efx_arfs_rule *rule;
- struct hlist_head *head;
- struct hlist_node *node;
-
- head = efx_rps_hash_bucket(efx, spec);
- if (WARN_ON(!head))
- return;
- hlist_for_each(node, head) {
- rule = container_of(node, struct efx_arfs_rule, node);
- if (efx_filter_spec_equal(spec, &rule->spec)) {
- /* Someone already reused the entry. We know that if
- * this check doesn't fire (i.e. filter_id == REMOVING)
- * then the REMOVING mark was put there by our caller,
- * because caller is holding a lock on filter table and
- * only holders of that lock set REMOVING.
- */
- if (rule->filter_id != EFX_ARFS_FILTER_ID_REMOVING)
- return;
- hlist_del(node);
- kfree(rule);
- return;
- }
- }
- /* We didn't find it. */
- WARN_ON(1);
-}
-#endif
-
-/* RSS contexts. We're using linked lists and crappy O(n) algorithms, because
- * (a) this is an infrequent control-plane operation and (b) n is small (max 64)
- */
-struct efx_rss_context *efx_alloc_rss_context_entry(struct efx_nic *efx)
-{
- struct list_head *head = &efx->rss_context.list;
- struct efx_rss_context *ctx, *new;
- u32 id = 1; /* Don't use zero, that refers to the master RSS context */
-
- WARN_ON(!mutex_is_locked(&efx->rss_lock));
-
- /* Search for first gap in the numbering */
- list_for_each_entry(ctx, head, list) {
- if (ctx->user_id != id)
- break;
- id++;
- /* Check for wrap. If this happens, we have nearly 2^32
- * allocated RSS contexts, which seems unlikely.
- */
- if (WARN_ON_ONCE(!id))
- return NULL;
- }
-
- /* Create the new entry */
- new = kmalloc(sizeof(struct efx_rss_context), GFP_KERNEL);
- if (!new)
- return NULL;
- new->context_id = EFX_EF10_RSS_CONTEXT_INVALID;
- new->rx_hash_udp_4tuple = false;
-
- /* Insert the new entry into the gap */
- new->user_id = id;
- list_add_tail(&new->list, &ctx->list);
- return new;
-}
-
-struct efx_rss_context *efx_find_rss_context_entry(struct efx_nic *efx, u32 id)
-{
- struct list_head *head = &efx->rss_context.list;
- struct efx_rss_context *ctx;
-
- WARN_ON(!mutex_is_locked(&efx->rss_lock));
-
- list_for_each_entry(ctx, head, list)
- if (ctx->user_id == id)
- return ctx;
- return NULL;
-}
-
-void efx_free_rss_context_entry(struct efx_rss_context *ctx)
-{
- list_del(&ctx->list);
- kfree(ctx);
-}
-
/**************************************************************************
*
* PCI interface
@@ -3519,7 +1059,7 @@ static void efx_pci_remove_main(struct efx_nic *efx)
* are not READY.
*/
BUG_ON(efx->state == STATE_READY);
- cancel_work_sync(&efx->reset_work);
+ efx_flush_reset_workqueue(efx);
efx_disable_interrupts(efx);
efx_clear_interrupt_affinity(efx);
@@ -3559,7 +1099,7 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
efx_pci_remove_main(efx);
- efx_fini_io(efx);
+ efx_fini_io(efx, efx->type->mem_bar(efx));
netif_dbg(efx, drv, efx->net_dev, "shutdown successful\n");
efx_fini_struct(efx);
@@ -3782,7 +1322,8 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
efx_probe_vpd_strings(efx);
/* Set up basic I/O (BAR mappings etc) */
- rc = efx_init_io(efx);
+ rc = efx_init_io(efx, efx->type->mem_bar(efx), efx->type->max_dma_mask,
+ efx->type->mem_map_size(efx));
if (rc)
goto fail2;
@@ -3826,7 +1367,7 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
return 0;
fail3:
- efx_fini_io(efx);
+ efx_fini_io(efx, efx->type->mem_bar(efx));
fail2:
efx_fini_struct(efx);
fail1:
@@ -3904,7 +1445,7 @@ static int efx_pm_thaw(struct device *dev)
rtnl_unlock();
/* Reschedule any quenched resets scheduled during efx_pm_freeze() */
- queue_work(reset_workqueue, &efx->reset_work);
+ efx_queue_reset_work(efx);
return 0;
@@ -4083,10 +1624,6 @@ static struct pci_driver efx_pci_driver = {
*
*************************************************************************/
-module_param(interrupt_mode, uint, 0444);
-MODULE_PARM_DESC(interrupt_mode,
- "Interrupt mode (0=>MSIX 1=>MSI 2=>legacy)");
-
static int __init efx_init_module(void)
{
int rc;
@@ -4103,11 +1640,9 @@ static int __init efx_init_module(void)
goto err_sriov;
#endif
- reset_workqueue = create_singlethread_workqueue("sfc_reset");
- if (!reset_workqueue) {
- rc = -ENOMEM;
+ rc = efx_create_reset_workqueue();
+ if (rc)
goto err_reset;
- }
rc = pci_register_driver(&efx_pci_driver);
if (rc < 0)
@@ -4116,7 +1651,7 @@ static int __init efx_init_module(void)
return 0;
err_pci:
- destroy_workqueue(reset_workqueue);
+ efx_destroy_reset_workqueue();
err_reset:
#ifdef CONFIG_SFC_SRIOV
efx_fini_sriov();
@@ -4132,7 +1667,7 @@ static void __exit efx_exit_module(void)
printk(KERN_INFO "Solarflare NET driver unloading\n");
pci_unregister_driver(&efx_pci_driver);
- destroy_workqueue(reset_workqueue);
+ efx_destroy_reset_workqueue();
#ifdef CONFIG_SFC_SRIOV
efx_fini_sriov();
#endif
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 2dd8d50..f1bdb04 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -15,31 +15,17 @@ int efx_net_open(struct net_device *net_dev);
int efx_net_stop(struct net_device *net_dev);
/* TX */
-int efx_probe_tx_queue(struct efx_tx_queue *tx_queue);
-void efx_remove_tx_queue(struct efx_tx_queue *tx_queue);
-void efx_init_tx_queue(struct efx_tx_queue *tx_queue);
void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue);
-void efx_fini_tx_queue(struct efx_tx_queue *tx_queue);
netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb,
struct net_device *net_dev);
netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb);
void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index);
int efx_setup_tc(struct net_device *net_dev, enum tc_setup_type type,
void *type_data);
-unsigned int efx_tx_max_skb_descs(struct efx_nic *efx);
extern unsigned int efx_piobuf_size;
extern bool efx_separate_tx_channels;
/* RX */
-void efx_set_default_rx_indir_table(struct efx_nic *efx,
- struct efx_rss_context *ctx);
-void efx_rx_config_page_split(struct efx_nic *efx);
-int efx_probe_rx_queue(struct efx_rx_queue *rx_queue);
-void efx_remove_rx_queue(struct efx_rx_queue *rx_queue);
-void efx_init_rx_queue(struct efx_rx_queue *rx_queue);
-void efx_fini_rx_queue(struct efx_rx_queue *rx_queue);
-void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic);
-void efx_rx_slow_fill(struct timer_list *t);
void __efx_rx_packet(struct efx_channel *channel);
void efx_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index,
unsigned int n_frags, unsigned int len, u16 flags);
@@ -48,7 +34,6 @@ static inline void efx_rx_flush_packet(struct efx_channel *channel)
if (channel->rx_pkt_n_frags)
__efx_rx_packet(channel);
}
-void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue);
#define EFX_MAX_DMAQ_SIZE 4096UL
#define EFX_DEFAULT_DMAQ_SIZE 1024UL
@@ -80,8 +65,6 @@ static inline bool efx_rss_enabled(struct efx_nic *efx)
/* Filters */
-void efx_mac_reconfigure(struct efx_nic *efx);
-
/**
* efx_filter_insert_filter - add or replace a filter
* @efx: NIC in which to insert the filter
@@ -186,58 +169,17 @@ static inline void efx_filter_rfs_expire(struct work_struct *data)
static inline void efx_filter_rfs_expire(struct work_struct *data) {}
#define efx_filter_rfs_enabled() 0
#endif
-bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec);
-
-bool efx_filter_spec_equal(const struct efx_filter_spec *left,
- const struct efx_filter_spec *right);
-u32 efx_filter_spec_hash(const struct efx_filter_spec *spec);
-
-#ifdef CONFIG_RFS_ACCEL
-bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
- bool *force);
-
-struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
- const struct efx_filter_spec *spec);
-
-/* @new is written to indicate if entry was newly added (true) or if an old
- * entry was found and returned (false).
- */
-struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
- const struct efx_filter_spec *spec,
- bool *new);
-
-void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec);
-#endif
/* RSS contexts */
-struct efx_rss_context *efx_alloc_rss_context_entry(struct efx_nic *efx);
-struct efx_rss_context *efx_find_rss_context_entry(struct efx_nic *efx, u32 id);
-void efx_free_rss_context_entry(struct efx_rss_context *ctx);
static inline bool efx_rss_active(struct efx_rss_context *ctx)
{
- return ctx->context_id != EFX_EF10_RSS_CONTEXT_INVALID;
+ return ctx->context_id != EFX_MCDI_RSS_CONTEXT_INVALID;
}
-/* Channels */
-int efx_channel_dummy_op_int(struct efx_channel *channel);
-void efx_channel_dummy_op_void(struct efx_channel *channel);
-int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries);
-
-/* Ports */
-int efx_reconfigure_port(struct efx_nic *efx);
-int __efx_reconfigure_port(struct efx_nic *efx);
-
/* Ethtool support */
extern const struct ethtool_ops efx_ethtool_ops;
-/* Reset handling */
-int efx_reset(struct efx_nic *efx, enum reset_type method);
-void efx_reset_down(struct efx_nic *efx, enum reset_type method);
-int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok);
-int efx_try_recovery(struct efx_nic *efx);
-
/* Global */
-void efx_schedule_reset(struct efx_nic *efx, enum reset_type type);
unsigned int efx_usecs_to_ticks(struct efx_nic *efx, unsigned int usecs);
unsigned int efx_ticks_to_usecs(struct efx_nic *efx, unsigned int ticks);
int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
@@ -245,8 +187,6 @@ int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
bool rx_may_override_tx);
void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
unsigned int *rx_usecs, bool *rx_adaptive);
-void efx_stop_eventq(struct efx_channel *channel);
-void efx_start_eventq(struct efx_channel *channel);
/* Dummy PHY ops for PHY drivers */
int efx_port_dummy_op_int(struct efx_nic *efx);
@@ -293,9 +233,6 @@ static inline void efx_schedule_channel_irq(struct efx_channel *channel)
efx_schedule_channel(channel);
}
-void efx_link_status_changed(struct efx_nic *efx);
-void efx_link_set_advertising(struct efx_nic *efx,
- const unsigned long *advertising);
void efx_link_clear_advertising(struct efx_nic *efx);
void efx_link_set_wanted_fc(struct efx_nic *efx, u8);
diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c
new file mode 100644
index 0000000..aeb5e8a
--- /dev/null
+++ b/drivers/net/ethernet/sfc/efx_channels.c
@@ -0,0 +1,1234 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include "net_driver.h"
+#include <linux/module.h>
+#include "efx_channels.h"
+#include "efx.h"
+#include "efx_common.h"
+#include "tx_common.h"
+#include "rx_common.h"
+#include "nic.h"
+#include "sriov.h"
+
+/* This is the first interrupt mode to try out of:
+ * 0 => MSI-X
+ * 1 => MSI
+ * 2 => legacy
+ */
+static unsigned int interrupt_mode;
+module_param(interrupt_mode, uint, 0444);
+MODULE_PARM_DESC(interrupt_mode,
+ "Interrupt mode (0=>MSIX 1=>MSI 2=>legacy)");
+
+/* This is the requested number of CPUs to use for Receive-Side Scaling (RSS),
+ * i.e. the number of CPUs among which we may distribute simultaneous
+ * interrupt handling.
+ *
+ * Cards without MSI-X will only target one CPU via legacy or MSI interrupt.
+ * The default (0) means to assign an interrupt to each core.
+ */
+static unsigned int rss_cpus;
+module_param(rss_cpus, uint, 0444);
+MODULE_PARM_DESC(rss_cpus, "Number of CPUs to use for Receive-Side Scaling");
+
+static unsigned int irq_adapt_low_thresh = 8000;
+module_param(irq_adapt_low_thresh, uint, 0644);
+MODULE_PARM_DESC(irq_adapt_low_thresh,
+ "Threshold score for reducing IRQ moderation");
+
+static unsigned int irq_adapt_high_thresh = 16000;
+module_param(irq_adapt_high_thresh, uint, 0644);
+MODULE_PARM_DESC(irq_adapt_high_thresh,
+ "Threshold score for increasing IRQ moderation");
+
+/* This is the weight assigned to each of the (per-channel) virtual
+ * NAPI devices.
+ */
+static int napi_weight = 64;
+
+/***************
+ * Housekeeping
+ ***************/
+
+int efx_channel_dummy_op_int(struct efx_channel *channel)
+{
+ return 0;
+}
+
+void efx_channel_dummy_op_void(struct efx_channel *channel)
+{
+}
+
+static const struct efx_channel_type efx_default_channel_type = {
+ .pre_probe = efx_channel_dummy_op_int,
+ .post_remove = efx_channel_dummy_op_void,
+ .get_name = efx_get_channel_name,
+ .copy = efx_copy_channel,
+ .want_txqs = efx_default_channel_want_txqs,
+ .keep_eventq = false,
+ .want_pio = true,
+};
+
+/*************
+ * INTERRUPTS
+ *************/
+
+static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
+{
+ cpumask_var_t thread_mask;
+ unsigned int count;
+ int cpu;
+
+ if (rss_cpus) {
+ count = rss_cpus;
+ } else {
+ if (unlikely(!zalloc_cpumask_var(&thread_mask, GFP_KERNEL))) {
+ netif_warn(efx, probe, efx->net_dev,
+ "RSS disabled due to allocation failure\n");
+ return 1;
+ }
+
+ count = 0;
+ for_each_online_cpu(cpu) {
+ if (!cpumask_test_cpu(cpu, thread_mask)) {
+ ++count;
+ cpumask_or(thread_mask, thread_mask,
+ topology_sibling_cpumask(cpu));
+ }
+ }
+
+ free_cpumask_var(thread_mask);
+ }
+
+ if (count > EFX_MAX_RX_QUEUES) {
+ netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn,
+ "Reducing number of rx queues from %u to %u.\n",
+ count, EFX_MAX_RX_QUEUES);
+ count = EFX_MAX_RX_QUEUES;
+ }
+
+ /* If RSS is requested for the PF *and* VFs then we can't write RSS
+ * table entries that are inaccessible to VFs
+ */
+#ifdef CONFIG_SFC_SRIOV
+ if (efx->type->sriov_wanted) {
+ if (efx->type->sriov_wanted(efx) && efx_vf_size(efx) > 1 &&
+ count > efx_vf_size(efx)) {
+ netif_warn(efx, probe, efx->net_dev,
+ "Reducing number of RSS channels from %u to %u for "
+ "VF support. Increase vf-msix-limit to use more "
+ "channels on the PF.\n",
+ count, efx_vf_size(efx));
+ count = efx_vf_size(efx);
+ }
+ }
+#endif
+
+ return count;
+}
+
+static int efx_allocate_msix_channels(struct efx_nic *efx,
+ unsigned int max_channels,
+ unsigned int extra_channels,
+ unsigned int parallelism)
+{
+ unsigned int n_channels = parallelism;
+ int vec_count;
+ int n_xdp_tx;
+ int n_xdp_ev;
+
+ if (efx_separate_tx_channels)
+ n_channels *= 2;
+ n_channels += extra_channels;
+
+ /* To allow XDP transmit to happen from arbitrary NAPI contexts
+ * we allocate a TX queue per CPU. We share event queues across
+ * multiple tx queues, assuming tx and ev queues are both
+ * maximum size.
+ */
+
+ n_xdp_tx = num_possible_cpus();
+ n_xdp_ev = DIV_ROUND_UP(n_xdp_tx, EFX_TXQ_TYPES);
+
+ vec_count = pci_msix_vec_count(efx->pci_dev);
+ if (vec_count < 0)
+ return vec_count;
+
+ max_channels = min_t(unsigned int, vec_count, max_channels);
+
+ /* Check resources.
+ * We need a channel per event queue, plus a VI per tx queue.
+ * This may be more pessimistic than it needs to be.
+ */
+ if (n_channels + n_xdp_ev > max_channels) {
+ netif_err(efx, drv, efx->net_dev,
+ "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n",
+ n_xdp_ev, n_channels, max_channels);
+ efx->n_xdp_channels = 0;
+ efx->xdp_tx_per_channel = 0;
+ efx->xdp_tx_queue_count = 0;
+ } else {
+ efx->n_xdp_channels = n_xdp_ev;
+ efx->xdp_tx_per_channel = EFX_TXQ_TYPES;
+ efx->xdp_tx_queue_count = n_xdp_tx;
+ n_channels += n_xdp_ev;
+ netif_dbg(efx, drv, efx->net_dev,
+ "Allocating %d TX and %d event queues for XDP\n",
+ n_xdp_tx, n_xdp_ev);
+ }
+
+ if (vec_count < n_channels) {
+ netif_err(efx, drv, efx->net_dev,
+ "WARNING: Insufficient MSI-X vectors available (%d < %u).\n",
+ vec_count, n_channels);
+ netif_err(efx, drv, efx->net_dev,
+ "WARNING: Performance may be reduced.\n");
+ n_channels = vec_count;
+ }
+
+ n_channels = min(n_channels, max_channels);
+
+ efx->n_channels = n_channels;
+
+ /* Ignore XDP tx channels when creating rx channels. */
+ n_channels -= efx->n_xdp_channels;
+
+ if (efx_separate_tx_channels) {
+ efx->n_tx_channels =
+ min(max(n_channels / 2, 1U),
+ efx->max_tx_channels);
+ efx->tx_channel_offset =
+ n_channels - efx->n_tx_channels;
+ efx->n_rx_channels =
+ max(n_channels -
+ efx->n_tx_channels, 1U);
+ } else {
+ efx->n_tx_channels = min(n_channels, efx->max_tx_channels);
+ efx->tx_channel_offset = 0;
+ efx->n_rx_channels = n_channels;
+ }
+
+ efx->n_rx_channels = min(efx->n_rx_channels, parallelism);
+ efx->n_tx_channels = min(efx->n_tx_channels, parallelism);
+
+ efx->xdp_channel_offset = n_channels;
+
+ netif_dbg(efx, drv, efx->net_dev,
+ "Allocating %u RX channels\n",
+ efx->n_rx_channels);
+
+ return efx->n_channels;
+}
+
+/* Probe the number and type of interrupts we are able to obtain, and
+ * the resulting numbers of channels and RX queues.
+ */
+int efx_probe_interrupts(struct efx_nic *efx)
+{
+ unsigned int extra_channels = 0;
+ unsigned int rss_spread;
+ unsigned int i, j;
+ int rc;
+
+ for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++)
+ if (efx->extra_channel_type[i])
+ ++extra_channels;
+
+ if (efx->interrupt_mode == EFX_INT_MODE_MSIX) {
+ unsigned int parallelism = efx_wanted_parallelism(efx);
+ struct msix_entry xentries[EFX_MAX_CHANNELS];
+ unsigned int n_channels;
+
+ rc = efx_allocate_msix_channels(efx, efx->max_channels,
+ extra_channels, parallelism);
+ if (rc >= 0) {
+ n_channels = rc;
+ for (i = 0; i < n_channels; i++)
+ xentries[i].entry = i;
+ rc = pci_enable_msix_range(efx->pci_dev, xentries, 1,
+ n_channels);
+ }
+ if (rc < 0) {
+ /* Fall back to single channel MSI */
+ netif_err(efx, drv, efx->net_dev,
+ "could not enable MSI-X\n");
+ if (efx->type->min_interrupt_mode >= EFX_INT_MODE_MSI)
+ efx->interrupt_mode = EFX_INT_MODE_MSI;
+ else
+ return rc;
+ } else if (rc < n_channels) {
+ netif_err(efx, drv, efx->net_dev,
+ "WARNING: Insufficient MSI-X vectors"
+ " available (%d < %u).\n", rc, n_channels);
+ netif_err(efx, drv, efx->net_dev,
+ "WARNING: Performance may be reduced.\n");
+ n_channels = rc;
+ }
+
+ if (rc > 0) {
+ for (i = 0; i < efx->n_channels; i++)
+ efx_get_channel(efx, i)->irq =
+ xentries[i].vector;
+ }
+ }
+
+ /* Try single interrupt MSI */
+ if (efx->interrupt_mode == EFX_INT_MODE_MSI) {
+ efx->n_channels = 1;
+ efx->n_rx_channels = 1;
+ efx->n_tx_channels = 1;
+ efx->n_xdp_channels = 0;
+ efx->xdp_channel_offset = efx->n_channels;
+ rc = pci_enable_msi(efx->pci_dev);
+ if (rc == 0) {
+ efx_get_channel(efx, 0)->irq = efx->pci_dev->irq;
+ } else {
+ netif_err(efx, drv, efx->net_dev,
+ "could not enable MSI\n");
+ if (efx->type->min_interrupt_mode >= EFX_INT_MODE_LEGACY)
+ efx->interrupt_mode = EFX_INT_MODE_LEGACY;
+ else
+ return rc;
+ }
+ }
+
+ /* Assume legacy interrupts */
+ if (efx->interrupt_mode == EFX_INT_MODE_LEGACY) {
+ efx->n_channels = 1 + (efx_separate_tx_channels ? 1 : 0);
+ efx->n_rx_channels = 1;
+ efx->n_tx_channels = 1;
+ efx->n_xdp_channels = 0;
+ efx->xdp_channel_offset = efx->n_channels;
+ efx->legacy_irq = efx->pci_dev->irq;
+ }
+
+ /* Assign extra channels if possible, before XDP channels */
+ efx->n_extra_tx_channels = 0;
+ j = efx->xdp_channel_offset;
+ for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++) {
+ if (!efx->extra_channel_type[i])
+ continue;
+ if (j <= efx->tx_channel_offset + efx->n_tx_channels) {
+ efx->extra_channel_type[i]->handle_no_channel(efx);
+ } else {
+ --j;
+ efx_get_channel(efx, j)->type =
+ efx->extra_channel_type[i];
+ if (efx_channel_has_tx_queues(efx_get_channel(efx, j)))
+ efx->n_extra_tx_channels++;
+ }
+ }
+
+ rss_spread = efx->n_rx_channels;
+ /* RSS might be usable on VFs even if it is disabled on the PF */
+#ifdef CONFIG_SFC_SRIOV
+ if (efx->type->sriov_wanted) {
+ efx->rss_spread = ((rss_spread > 1 ||
+ !efx->type->sriov_wanted(efx)) ?
+ rss_spread : efx_vf_size(efx));
+ return 0;
+ }
+#endif
+ efx->rss_spread = rss_spread;
+
+ return 0;
+}
+
+#if defined(CONFIG_SMP)
+void efx_set_interrupt_affinity(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+ unsigned int cpu;
+
+ efx_for_each_channel(channel, efx) {
+ cpu = cpumask_local_spread(channel->channel,
+ pcibus_to_node(efx->pci_dev->bus));
+ irq_set_affinity_hint(channel->irq, cpumask_of(cpu));
+ }
+}
+
+void efx_clear_interrupt_affinity(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ efx_for_each_channel(channel, efx)
+ irq_set_affinity_hint(channel->irq, NULL);
+}
+#else
+void
+efx_set_interrupt_affinity(struct efx_nic *efx __attribute__ ((unused)))
+{
+}
+
+void
+efx_clear_interrupt_affinity(struct efx_nic *efx __attribute__ ((unused)))
+{
+}
+#endif /* CONFIG_SMP */
+
+void efx_remove_interrupts(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ /* Remove MSI/MSI-X interrupts */
+ efx_for_each_channel(channel, efx)
+ channel->irq = 0;
+ pci_disable_msi(efx->pci_dev);
+ pci_disable_msix(efx->pci_dev);
+
+ /* Remove legacy interrupt */
+ efx->legacy_irq = 0;
+}
+
+/***************
+ * EVENT QUEUES
+ ***************/
+
+/* Create event queue
+ * Event queue memory allocations are done only once. If the channel
+ * is reset, the memory buffer will be reused; this guards against
+ * errors during channel reset and also simplifies interrupt handling.
+ */
+int efx_probe_eventq(struct efx_channel *channel)
+{
+ struct efx_nic *efx = channel->efx;
+ unsigned long entries;
+
+ netif_dbg(efx, probe, efx->net_dev,
+ "chan %d create event queue\n", channel->channel);
+
+ /* Build an event queue with room for one event per tx and rx buffer,
+ * plus some extra for link state events and MCDI completions.
+ */
+ entries = roundup_pow_of_two(efx->rxq_entries + efx->txq_entries + 128);
+ EFX_WARN_ON_PARANOID(entries > EFX_MAX_EVQ_SIZE);
+ channel->eventq_mask = max(entries, EFX_MIN_EVQ_SIZE) - 1;
+
+ return efx_nic_probe_eventq(channel);
+}
+
+/* Prepare channel's event queue */
+int efx_init_eventq(struct efx_channel *channel)
+{
+ struct efx_nic *efx = channel->efx;
+ int rc;
+
+ EFX_WARN_ON_PARANOID(channel->eventq_init);
+
+ netif_dbg(efx, drv, efx->net_dev,
+ "chan %d init event queue\n", channel->channel);
+
+ rc = efx_nic_init_eventq(channel);
+ if (rc == 0) {
+ efx->type->push_irq_moderation(channel);
+ channel->eventq_read_ptr = 0;
+ channel->eventq_init = true;
+ }
+ return rc;
+}
+
+/* Enable event queue processing and NAPI */
+void efx_start_eventq(struct efx_channel *channel)
+{
+ netif_dbg(channel->efx, ifup, channel->efx->net_dev,
+ "chan %d start event queue\n", channel->channel);
+
+ /* Make sure the NAPI handler sees the enabled flag set */
+ channel->enabled = true;
+ smp_wmb();
+
+ napi_enable(&channel->napi_str);
+ efx_nic_eventq_read_ack(channel);
+}
+
+/* Disable event queue processing and NAPI */
+void efx_stop_eventq(struct efx_channel *channel)
+{
+ if (!channel->enabled)
+ return;
+
+ napi_disable(&channel->napi_str);
+ channel->enabled = false;
+}
+
+void efx_fini_eventq(struct efx_channel *channel)
+{
+ if (!channel->eventq_init)
+ return;
+
+ netif_dbg(channel->efx, drv, channel->efx->net_dev,
+ "chan %d fini event queue\n", channel->channel);
+
+ efx_nic_fini_eventq(channel);
+ channel->eventq_init = false;
+}
+
+void efx_remove_eventq(struct efx_channel *channel)
+{
+ netif_dbg(channel->efx, drv, channel->efx->net_dev,
+ "chan %d remove event queue\n", channel->channel);
+
+ efx_nic_remove_eventq(channel);
+}
+
+/**************************************************************************
+ *
+ * Channel handling
+ *
+ *************************************************************************/
+
+/* Allocate and initialise a channel structure. */
+struct efx_channel *
+efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel)
+{
+ struct efx_rx_queue *rx_queue;
+ struct efx_tx_queue *tx_queue;
+ struct efx_channel *channel;
+ int j;
+
+ channel = kzalloc(sizeof(*channel), GFP_KERNEL);
+ if (!channel)
+ return NULL;
+
+ channel->efx = efx;
+ channel->channel = i;
+ channel->type = &efx_default_channel_type;
+
+ for (j = 0; j < EFX_TXQ_TYPES; j++) {
+ tx_queue = &channel->tx_queue[j];
+ tx_queue->efx = efx;
+ tx_queue->queue = i * EFX_TXQ_TYPES + j;
+ tx_queue->channel = channel;
+ }
+
+#ifdef CONFIG_RFS_ACCEL
+ INIT_DELAYED_WORK(&channel->filter_work, efx_filter_rfs_expire);
+#endif
+
+ rx_queue = &channel->rx_queue;
+ rx_queue->efx = efx;
+ timer_setup(&rx_queue->slow_fill, efx_rx_slow_fill, 0);
+
+ return channel;
+}
+
+int efx_init_channels(struct efx_nic *efx)
+{
+ unsigned int i;
+
+ for (i = 0; i < EFX_MAX_CHANNELS; i++) {
+ efx->channel[i] = efx_alloc_channel(efx, i, NULL);
+ if (!efx->channel[i])
+ return -ENOMEM;
+ efx->msi_context[i].efx = efx;
+ efx->msi_context[i].index = i;
+ }
+
+ /* Higher numbered interrupt modes are less capable! */
+ if (WARN_ON_ONCE(efx->type->max_interrupt_mode >
+ efx->type->min_interrupt_mode)) {
+ return -EIO;
+ }
+ efx->interrupt_mode = max(efx->type->max_interrupt_mode,
+ interrupt_mode);
+ efx->interrupt_mode = min(efx->type->min_interrupt_mode,
+ interrupt_mode);
+
+ return 0;
+}
+
+void efx_fini_channels(struct efx_nic *efx)
+{
+ unsigned int i;
+
+ for (i = 0; i < EFX_MAX_CHANNELS; i++)
+ if (efx->channel[i]) {
+ kfree(efx->channel[i]);
+ efx->channel[i] = NULL;
+ }
+}
+
+/* Allocate and initialise a channel structure, copying parameters
+ * (but not resources) from an old channel structure.
+ */
+struct efx_channel *efx_copy_channel(const struct efx_channel *old_channel)
+{
+ struct efx_rx_queue *rx_queue;
+ struct efx_tx_queue *tx_queue;
+ struct efx_channel *channel;
+ int j;
+
+ channel = kmalloc(sizeof(*channel), GFP_KERNEL);
+ if (!channel)
+ return NULL;
+
+ *channel = *old_channel;
+
+ channel->napi_dev = NULL;
+ INIT_HLIST_NODE(&channel->napi_str.napi_hash_node);
+ channel->napi_str.napi_id = 0;
+ channel->napi_str.state = 0;
+ memset(&channel->eventq, 0, sizeof(channel->eventq));
+
+ for (j = 0; j < EFX_TXQ_TYPES; j++) {
+ tx_queue = &channel->tx_queue[j];
+ if (tx_queue->channel)
+ tx_queue->channel = channel;
+ tx_queue->buffer = NULL;
+ memset(&tx_queue->txd, 0, sizeof(tx_queue->txd));
+ }
+
+ rx_queue = &channel->rx_queue;
+ rx_queue->buffer = NULL;
+ memset(&rx_queue->rxd, 0, sizeof(rx_queue->rxd));
+ timer_setup(&rx_queue->slow_fill, efx_rx_slow_fill, 0);
+#ifdef CONFIG_RFS_ACCEL
+ INIT_DELAYED_WORK(&channel->filter_work, efx_filter_rfs_expire);
+#endif
+
+ return channel;
+}
+
+static int efx_probe_channel(struct efx_channel *channel)
+{
+ struct efx_tx_queue *tx_queue;
+ struct efx_rx_queue *rx_queue;
+ int rc;
+
+ netif_dbg(channel->efx, probe, channel->efx->net_dev,
+ "creating channel %d\n", channel->channel);
+
+ rc = channel->type->pre_probe(channel);
+ if (rc)
+ goto fail;
+
+ rc = efx_probe_eventq(channel);
+ if (rc)
+ goto fail;
+
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ rc = efx_probe_tx_queue(tx_queue);
+ if (rc)
+ goto fail;
+ }
+
+ efx_for_each_channel_rx_queue(rx_queue, channel) {
+ rc = efx_probe_rx_queue(rx_queue);
+ if (rc)
+ goto fail;
+ }
+
+ channel->rx_list = NULL;
+
+ return 0;
+
+fail:
+ efx_remove_channel(channel);
+ return rc;
+}
+
+void efx_get_channel_name(struct efx_channel *channel, char *buf, size_t len)
+{
+ struct efx_nic *efx = channel->efx;
+ const char *type;
+ int number;
+
+ number = channel->channel;
+
+ if (number >= efx->xdp_channel_offset &&
+ !WARN_ON_ONCE(!efx->n_xdp_channels)) {
+ type = "-xdp";
+ number -= efx->xdp_channel_offset;
+ } else if (efx->tx_channel_offset == 0) {
+ type = "";
+ } else if (number < efx->tx_channel_offset) {
+ type = "-rx";
+ } else {
+ type = "-tx";
+ number -= efx->tx_channel_offset;
+ }
+ snprintf(buf, len, "%s%s-%d", efx->name, type, number);
+}
+
+void efx_set_channel_names(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ efx_for_each_channel(channel, efx)
+ channel->type->get_name(channel,
+ efx->msi_context[channel->channel].name,
+ sizeof(efx->msi_context[0].name));
+}
+
+int efx_probe_channels(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+ int rc;
+
+ /* Restart special buffer allocation */
+ efx->next_buffer_table = 0;
+
+ /* Probe channels in reverse, so that any 'extra' channels
+ * use the start of the buffer table. This allows the traffic
+ * channels to be resized without moving them or wasting the
+ * entries before them.
+ */
+ efx_for_each_channel_rev(channel, efx) {
+ rc = efx_probe_channel(channel);
+ if (rc) {
+ netif_err(efx, probe, efx->net_dev,
+ "failed to create channel %d\n",
+ channel->channel);
+ goto fail;
+ }
+ }
+ efx_set_channel_names(efx);
+
+ return 0;
+
+fail:
+ efx_remove_channels(efx);
+ return rc;
+}
+
+void efx_remove_channel(struct efx_channel *channel)
+{
+ struct efx_tx_queue *tx_queue;
+ struct efx_rx_queue *rx_queue;
+
+ netif_dbg(channel->efx, drv, channel->efx->net_dev,
+ "destroy chan %d\n", channel->channel);
+
+ efx_for_each_channel_rx_queue(rx_queue, channel)
+ efx_remove_rx_queue(rx_queue);
+ efx_for_each_possible_channel_tx_queue(tx_queue, channel)
+ efx_remove_tx_queue(tx_queue);
+ efx_remove_eventq(channel);
+ channel->type->post_remove(channel);
+}
+
+void efx_remove_channels(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ efx_for_each_channel(channel, efx)
+ efx_remove_channel(channel);
+
+ kfree(efx->xdp_tx_queues);
+}
+
+int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
+{
+ struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel;
+ unsigned int i, next_buffer_table = 0;
+ u32 old_rxq_entries, old_txq_entries;
+ int rc, rc2;
+
+ rc = efx_check_disabled(efx);
+ if (rc)
+ return rc;
+
+ /* Not all channels should be reallocated. We must avoid
+ * reallocating their buffer table entries.
+ */
+ efx_for_each_channel(channel, efx) {
+ struct efx_rx_queue *rx_queue;
+ struct efx_tx_queue *tx_queue;
+
+ if (channel->type->copy)
+ continue;
+ next_buffer_table = max(next_buffer_table,
+ channel->eventq.index +
+ channel->eventq.entries);
+ efx_for_each_channel_rx_queue(rx_queue, channel)
+ next_buffer_table = max(next_buffer_table,
+ rx_queue->rxd.index +
+ rx_queue->rxd.entries);
+ efx_for_each_channel_tx_queue(tx_queue, channel)
+ next_buffer_table = max(next_buffer_table,
+ tx_queue->txd.index +
+ tx_queue->txd.entries);
+ }
+
+ efx_device_detach_sync(efx);
+ efx_stop_all(efx);
+ efx_soft_disable_interrupts(efx);
+
+ /* Clone channels (where possible) */
+ memset(other_channel, 0, sizeof(other_channel));
+ for (i = 0; i < efx->n_channels; i++) {
+ channel = efx->channel[i];
+ if (channel->type->copy)
+ channel = channel->type->copy(channel);
+ if (!channel) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ other_channel[i] = channel;
+ }
+
+ /* Swap entry counts and channel pointers */
+ old_rxq_entries = efx->rxq_entries;
+ old_txq_entries = efx->txq_entries;
+ efx->rxq_entries = rxq_entries;
+ efx->txq_entries = txq_entries;
+ for (i = 0; i < efx->n_channels; i++) {
+ channel = efx->channel[i];
+ efx->channel[i] = other_channel[i];
+ other_channel[i] = channel;
+ }
+
+ /* Restart buffer table allocation */
+ efx->next_buffer_table = next_buffer_table;
+
+ for (i = 0; i < efx->n_channels; i++) {
+ channel = efx->channel[i];
+ if (!channel->type->copy)
+ continue;
+ rc = efx_probe_channel(channel);
+ if (rc)
+ goto rollback;
+ efx_init_napi_channel(efx->channel[i]);
+ }
+
+out:
+ /* Destroy unused channel structures */
+ for (i = 0; i < efx->n_channels; i++) {
+ channel = other_channel[i];
+ if (channel && channel->type->copy) {
+ efx_fini_napi_channel(channel);
+ efx_remove_channel(channel);
+ kfree(channel);
+ }
+ }
+
+ rc2 = efx_soft_enable_interrupts(efx);
+ if (rc2) {
+ rc = rc ? rc : rc2;
+ netif_err(efx, drv, efx->net_dev,
+ "unable to restart interrupts on channel reallocation\n");
+ efx_schedule_reset(efx, RESET_TYPE_DISABLE);
+ } else {
+ efx_start_all(efx);
+ efx_device_attach_if_not_resetting(efx);
+ }
+ return rc;
+
+rollback:
+ /* Swap back */
+ efx->rxq_entries = old_rxq_entries;
+ efx->txq_entries = old_txq_entries;
+ for (i = 0; i < efx->n_channels; i++) {
+ channel = efx->channel[i];
+ efx->channel[i] = other_channel[i];
+ other_channel[i] = channel;
+ }
+ goto out;
+}
+
+int efx_set_channels(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+ struct efx_tx_queue *tx_queue;
+ int xdp_queue_number;
+
+ efx->tx_channel_offset =
+ efx_separate_tx_channels ?
+ efx->n_channels - efx->n_tx_channels : 0;
+
+ if (efx->xdp_tx_queue_count) {
+ EFX_WARN_ON_PARANOID(efx->xdp_tx_queues);
+
+ /* Allocate array for XDP TX queue lookup. */
+ efx->xdp_tx_queues = kcalloc(efx->xdp_tx_queue_count,
+ sizeof(*efx->xdp_tx_queues),
+ GFP_KERNEL);
+ if (!efx->xdp_tx_queues)
+ return -ENOMEM;
+ }
+
+ /* We need to mark which channels really have RX and TX
+ * queues, and adjust the TX queue numbers if we have separate
+ * RX-only and TX-only channels.
+ */
+ xdp_queue_number = 0;
+ efx_for_each_channel(channel, efx) {
+ if (channel->channel < efx->n_rx_channels)
+ channel->rx_queue.core_index = channel->channel;
+ else
+ channel->rx_queue.core_index = -1;
+
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ tx_queue->queue -= (efx->tx_channel_offset *
+ EFX_TXQ_TYPES);
+
+ if (efx_channel_is_xdp_tx(channel) &&
+ xdp_queue_number < efx->xdp_tx_queue_count) {
+ efx->xdp_tx_queues[xdp_queue_number] = tx_queue;
+ xdp_queue_number++;
+ }
+ }
+ }
+ return 0;
+}
+
+bool efx_default_channel_want_txqs(struct efx_channel *channel)
+{
+ return channel->channel - channel->efx->tx_channel_offset <
+ channel->efx->n_tx_channels;
+}
+
+/*************
+ * START/STOP
+ *************/
+
+int efx_soft_enable_interrupts(struct efx_nic *efx)
+{
+ struct efx_channel *channel, *end_channel;
+ int rc;
+
+ BUG_ON(efx->state == STATE_DISABLED);
+
+ efx->irq_soft_enabled = true;
+ smp_wmb();
+
+ efx_for_each_channel(channel, efx) {
+ if (!channel->type->keep_eventq) {
+ rc = efx_init_eventq(channel);
+ if (rc)
+ goto fail;
+ }
+ efx_start_eventq(channel);
+ }
+
+ efx_mcdi_mode_event(efx);
+
+ return 0;
+fail:
+ end_channel = channel;
+ efx_for_each_channel(channel, efx) {
+ if (channel == end_channel)
+ break;
+ efx_stop_eventq(channel);
+ if (!channel->type->keep_eventq)
+ efx_fini_eventq(channel);
+ }
+
+ return rc;
+}
+
+void efx_soft_disable_interrupts(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ if (efx->state == STATE_DISABLED)
+ return;
+
+ efx_mcdi_mode_poll(efx);
+
+ efx->irq_soft_enabled = false;
+ smp_wmb();
+
+ if (efx->legacy_irq)
+ synchronize_irq(efx->legacy_irq);
+
+ efx_for_each_channel(channel, efx) {
+ if (channel->irq)
+ synchronize_irq(channel->irq);
+
+ efx_stop_eventq(channel);
+ if (!channel->type->keep_eventq)
+ efx_fini_eventq(channel);
+ }
+
+ /* Flush the asynchronous MCDI request queue */
+ efx_mcdi_flush_async(efx);
+}
+
+int efx_enable_interrupts(struct efx_nic *efx)
+{
+ struct efx_channel *channel, *end_channel;
+ int rc;
+
+ /* TODO: Is this really a bug? */
+ BUG_ON(efx->state == STATE_DISABLED);
+
+ if (efx->eeh_disabled_legacy_irq) {
+ enable_irq(efx->legacy_irq);
+ efx->eeh_disabled_legacy_irq = false;
+ }
+
+ efx->type->irq_enable_master(efx);
+
+ efx_for_each_channel(channel, efx) {
+ if (channel->type->keep_eventq) {
+ rc = efx_init_eventq(channel);
+ if (rc)
+ goto fail;
+ }
+ }
+
+ rc = efx_soft_enable_interrupts(efx);
+ if (rc)
+ goto fail;
+
+ return 0;
+
+fail:
+ end_channel = channel;
+ efx_for_each_channel(channel, efx) {
+ if (channel == end_channel)
+ break;
+ if (channel->type->keep_eventq)
+ efx_fini_eventq(channel);
+ }
+
+ efx->type->irq_disable_non_ev(efx);
+
+ return rc;
+}
+
+void efx_disable_interrupts(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ efx_soft_disable_interrupts(efx);
+
+ efx_for_each_channel(channel, efx) {
+ if (channel->type->keep_eventq)
+ efx_fini_eventq(channel);
+ }
+
+ efx->type->irq_disable_non_ev(efx);
+}
+
+void efx_start_channels(struct efx_nic *efx)
+{
+ struct efx_tx_queue *tx_queue;
+ struct efx_rx_queue *rx_queue;
+ struct efx_channel *channel;
+
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ efx_init_tx_queue(tx_queue);
+ atomic_inc(&efx->active_queues);
+ }
+
+ efx_for_each_channel_rx_queue(rx_queue, channel) {
+ efx_init_rx_queue(rx_queue);
+ atomic_inc(&efx->active_queues);
+ efx_stop_eventq(channel);
+ efx_fast_push_rx_descriptors(rx_queue, false);
+ efx_start_eventq(channel);
+ }
+
+ WARN_ON(channel->rx_pkt_n_frags);
+ }
+}
+
+void efx_stop_channels(struct efx_nic *efx)
+{
+ struct efx_tx_queue *tx_queue;
+ struct efx_rx_queue *rx_queue;
+ struct efx_channel *channel;
+ int rc = 0;
+
+ /* Stop RX refill */
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_rx_queue(rx_queue, channel)
+ rx_queue->refill_enabled = false;
+ }
+
+ efx_for_each_channel(channel, efx) {
+ /* RX packet processing is pipelined, so wait for the
+ * NAPI handler to complete. At least event queue 0
+ * might be kept active by non-data events, so don't
+ * use napi_synchronize() but actually disable NAPI
+ * temporarily.
+ */
+ if (efx_channel_has_rx_queue(channel)) {
+ efx_stop_eventq(channel);
+ efx_start_eventq(channel);
+ }
+ }
+
+ if (efx->type->fini_dmaq)
+ rc = efx->type->fini_dmaq(efx);
+
+ if (rc) {
+ netif_err(efx, drv, efx->net_dev, "failed to flush queues\n");
+ } else {
+ netif_dbg(efx, drv, efx->net_dev,
+ "successfully flushed all queues\n");
+ }
+
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_rx_queue(rx_queue, channel)
+ efx_fini_rx_queue(rx_queue);
+ efx_for_each_possible_channel_tx_queue(tx_queue, channel)
+ efx_fini_tx_queue(tx_queue);
+ }
+}
+
+/**************************************************************************
+ *
+ * NAPI interface
+ *
+ *************************************************************************/
+
+/* Process channel's event queue
+ *
+ * This function is responsible for processing the event queue of a
+ * single channel. The caller must guarantee that this function will
+ * never be concurrently called more than once on the same channel,
+ * though different channels may be being processed concurrently.
+ */
+static int efx_process_channel(struct efx_channel *channel, int budget)
+{
+ struct efx_tx_queue *tx_queue;
+ struct list_head rx_list;
+ int spent;
+
+ if (unlikely(!channel->enabled))
+ return 0;
+
+ /* Prepare the batch receive list */
+ EFX_WARN_ON_PARANOID(channel->rx_list != NULL);
+ INIT_LIST_HEAD(&rx_list);
+ channel->rx_list = &rx_list;
+
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ tx_queue->pkts_compl = 0;
+ tx_queue->bytes_compl = 0;
+ }
+
+ spent = efx_nic_process_eventq(channel, budget);
+ if (spent && efx_channel_has_rx_queue(channel)) {
+ struct efx_rx_queue *rx_queue =
+ efx_channel_get_rx_queue(channel);
+
+ efx_rx_flush_packet(channel);
+ efx_fast_push_rx_descriptors(rx_queue, true);
+ }
+
+ /* Update BQL */
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ if (tx_queue->bytes_compl) {
+ netdev_tx_completed_queue(tx_queue->core_txq,
+ tx_queue->pkts_compl,
+ tx_queue->bytes_compl);
+ }
+ }
+
+ /* Receive any packets we queued up */
+ netif_receive_skb_list(channel->rx_list);
+ channel->rx_list = NULL;
+
+ return spent;
+}
+
+static void efx_update_irq_mod(struct efx_nic *efx, struct efx_channel *channel)
+{
+ int step = efx->irq_mod_step_us;
+
+ if (channel->irq_mod_score < irq_adapt_low_thresh) {
+ if (channel->irq_moderation_us > step) {
+ channel->irq_moderation_us -= step;
+ efx->type->push_irq_moderation(channel);
+ }
+ } else if (channel->irq_mod_score > irq_adapt_high_thresh) {
+ if (channel->irq_moderation_us <
+ efx->irq_rx_moderation_us) {
+ channel->irq_moderation_us += step;
+ efx->type->push_irq_moderation(channel);
+ }
+ }
+
+ channel->irq_count = 0;
+ channel->irq_mod_score = 0;
+}
+
+/* NAPI poll handler
+ *
+ * NAPI guarantees serialisation of polls of the same device, which
+ * provides the guarantee required by efx_process_channel().
+ */
+static int efx_poll(struct napi_struct *napi, int budget)
+{
+ struct efx_channel *channel =
+ container_of(napi, struct efx_channel, napi_str);
+ struct efx_nic *efx = channel->efx;
+ int spent;
+
+ netif_vdbg(efx, intr, efx->net_dev,
+ "channel %d NAPI poll executing on CPU %d\n",
+ channel->channel, raw_smp_processor_id());
+
+ spent = efx_process_channel(channel, budget);
+
+ xdp_do_flush_map();
+
+ if (spent < budget) {
+ if (efx_channel_has_rx_queue(channel) &&
+ efx->irq_rx_adaptive &&
+ unlikely(++channel->irq_count == 1000)) {
+ efx_update_irq_mod(efx, channel);
+ }
+
+#ifdef CONFIG_RFS_ACCEL
+ /* Perhaps expire some ARFS filters */
+ mod_delayed_work(system_wq, &channel->filter_work, 0);
+#endif
+
+ /* There is no race here; although napi_disable() will
+ * only wait for napi_complete(), this isn't a problem
+ * since efx_nic_eventq_read_ack() will have no effect if
+ * interrupts have already been disabled.
+ */
+ if (napi_complete_done(napi, spent))
+ efx_nic_eventq_read_ack(channel);
+ }
+
+ return spent;
+}
+
+void efx_init_napi_channel(struct efx_channel *channel)
+{
+ struct efx_nic *efx = channel->efx;
+
+ channel->napi_dev = efx->net_dev;
+ netif_napi_add(channel->napi_dev, &channel->napi_str,
+ efx_poll, napi_weight);
+}
+
+void efx_init_napi(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ efx_for_each_channel(channel, efx)
+ efx_init_napi_channel(channel);
+}
+
+void efx_fini_napi_channel(struct efx_channel *channel)
+{
+ if (channel->napi_dev)
+ netif_napi_del(&channel->napi_str);
+
+ channel->napi_dev = NULL;
+}
+
+void efx_fini_napi(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ efx_for_each_channel(channel, efx)
+ efx_fini_napi_channel(channel);
+}
diff --git a/drivers/net/ethernet/sfc/efx_channels.h b/drivers/net/ethernet/sfc/efx_channels.h
new file mode 100644
index 0000000..8d7b8c4
--- /dev/null
+++ b/drivers/net/ethernet/sfc/efx_channels.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EFX_CHANNELS_H
+#define EFX_CHANNELS_H
+
+int efx_probe_interrupts(struct efx_nic *efx);
+void efx_remove_interrupts(struct efx_nic *efx);
+int efx_soft_enable_interrupts(struct efx_nic *efx);
+void efx_soft_disable_interrupts(struct efx_nic *efx);
+int efx_enable_interrupts(struct efx_nic *efx);
+void efx_disable_interrupts(struct efx_nic *efx);
+
+void efx_set_interrupt_affinity(struct efx_nic *efx);
+void efx_clear_interrupt_affinity(struct efx_nic *efx);
+
+int efx_probe_eventq(struct efx_channel *channel);
+int efx_init_eventq(struct efx_channel *channel);
+void efx_start_eventq(struct efx_channel *channel);
+void efx_stop_eventq(struct efx_channel *channel);
+void efx_fini_eventq(struct efx_channel *channel);
+void efx_remove_eventq(struct efx_channel *channel);
+
+struct efx_channel *
+efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel);
+int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries);
+void efx_get_channel_name(struct efx_channel *channel, char *buf, size_t len);
+void efx_set_channel_names(struct efx_nic *efx);
+int efx_init_channels(struct efx_nic *efx);
+int efx_probe_channels(struct efx_nic *efx);
+int efx_set_channels(struct efx_nic *efx);
+bool efx_default_channel_want_txqs(struct efx_channel *channel);
+void efx_remove_channel(struct efx_channel *channel);
+void efx_remove_channels(struct efx_nic *efx);
+void efx_fini_channels(struct efx_nic *efx);
+struct efx_channel *efx_copy_channel(const struct efx_channel *old_channel);
+void efx_start_channels(struct efx_nic *efx);
+void efx_stop_channels(struct efx_nic *efx);
+
+void efx_init_napi_channel(struct efx_channel *channel);
+void efx_init_napi(struct efx_nic *efx);
+void efx_fini_napi_channel(struct efx_channel *channel);
+void efx_fini_napi(struct efx_nic *efx);
+
+int efx_channel_dummy_op_int(struct efx_channel *channel);
+void efx_channel_dummy_op_void(struct efx_channel *channel);
+
+#endif
diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
new file mode 100644
index 0000000..ab0ce62
--- /dev/null
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -0,0 +1,1102 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include "net_driver.h"
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include "efx_common.h"
+#include "efx_channels.h"
+#include "efx.h"
+#include "mcdi.h"
+#include "selftest.h"
+#include "rx_common.h"
+#include "tx_common.h"
+#include "nic.h"
+#include "io.h"
+#include "mcdi_pcol.h"
+
+static unsigned int debug = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
+ NETIF_MSG_LINK | NETIF_MSG_IFDOWN |
+ NETIF_MSG_IFUP | NETIF_MSG_RX_ERR |
+ NETIF_MSG_TX_ERR | NETIF_MSG_HW);
+module_param(debug, uint, 0);
+MODULE_PARM_DESC(debug, "Bitmapped debugging message enable value");
+
+/* This is the time (in jiffies) between invocations of the hardware
+ * monitor.
+ * On Falcon-based NICs, this will:
+ * - Check the on-board hardware monitor;
+ * - Poll the link state and reconfigure the hardware as necessary.
+ * On Siena-based NICs for power systems with EEH support, this will give EEH a
+ * chance to start.
+ */
+static unsigned int efx_monitor_interval = 1 * HZ;
+
+/* How often and how many times to poll for a reset while waiting for a
+ * BIST that another function started to complete.
+ */
+#define BIST_WAIT_DELAY_MS 100
+#define BIST_WAIT_DELAY_COUNT 100
+
+/* Default stats update time */
+#define STATS_PERIOD_MS_DEFAULT 1000
+
+const unsigned int efx_reset_type_max = RESET_TYPE_MAX;
+const char *const efx_reset_type_names[] = {
+ [RESET_TYPE_INVISIBLE] = "INVISIBLE",
+ [RESET_TYPE_ALL] = "ALL",
+ [RESET_TYPE_RECOVER_OR_ALL] = "RECOVER_OR_ALL",
+ [RESET_TYPE_WORLD] = "WORLD",
+ [RESET_TYPE_RECOVER_OR_DISABLE] = "RECOVER_OR_DISABLE",
+ [RESET_TYPE_DATAPATH] = "DATAPATH",
+ [RESET_TYPE_MC_BIST] = "MC_BIST",
+ [RESET_TYPE_DISABLE] = "DISABLE",
+ [RESET_TYPE_TX_WATCHDOG] = "TX_WATCHDOG",
+ [RESET_TYPE_INT_ERROR] = "INT_ERROR",
+ [RESET_TYPE_DMA_ERROR] = "DMA_ERROR",
+ [RESET_TYPE_TX_SKIP] = "TX_SKIP",
+ [RESET_TYPE_MC_FAILURE] = "MC_FAILURE",
+ [RESET_TYPE_MCDI_TIMEOUT] = "MCDI_TIMEOUT (FLR)",
+};
+
+#define RESET_TYPE(type) \
+ STRING_TABLE_LOOKUP(type, efx_reset_type)
+
+/* Loopback mode names (see LOOPBACK_MODE()) */
+const unsigned int efx_loopback_mode_max = LOOPBACK_MAX;
+const char *const efx_loopback_mode_names[] = {
+ [LOOPBACK_NONE] = "NONE",
+ [LOOPBACK_DATA] = "DATAPATH",
+ [LOOPBACK_GMAC] = "GMAC",
+ [LOOPBACK_XGMII] = "XGMII",
+ [LOOPBACK_XGXS] = "XGXS",
+ [LOOPBACK_XAUI] = "XAUI",
+ [LOOPBACK_GMII] = "GMII",
+ [LOOPBACK_SGMII] = "SGMII",
+ [LOOPBACK_XGBR] = "XGBR",
+ [LOOPBACK_XFI] = "XFI",
+ [LOOPBACK_XAUI_FAR] = "XAUI_FAR",
+ [LOOPBACK_GMII_FAR] = "GMII_FAR",
+ [LOOPBACK_SGMII_FAR] = "SGMII_FAR",
+ [LOOPBACK_XFI_FAR] = "XFI_FAR",
+ [LOOPBACK_GPHY] = "GPHY",
+ [LOOPBACK_PHYXS] = "PHYXS",
+ [LOOPBACK_PCS] = "PCS",
+ [LOOPBACK_PMAPMD] = "PMA/PMD",
+ [LOOPBACK_XPORT] = "XPORT",
+ [LOOPBACK_XGMII_WS] = "XGMII_WS",
+ [LOOPBACK_XAUI_WS] = "XAUI_WS",
+ [LOOPBACK_XAUI_WS_FAR] = "XAUI_WS_FAR",
+ [LOOPBACK_XAUI_WS_NEAR] = "XAUI_WS_NEAR",
+ [LOOPBACK_GMII_WS] = "GMII_WS",
+ [LOOPBACK_XFI_WS] = "XFI_WS",
+ [LOOPBACK_XFI_WS_FAR] = "XFI_WS_FAR",
+ [LOOPBACK_PHYXS_WS] = "PHYXS_WS",
+};
+
+/* Reset workqueue. If any NIC has a hardware failure then a reset will be
+ * queued onto this work queue. This is not a per-nic work queue, because
+ * efx_reset_work() acquires the rtnl lock, so resets are naturally serialised.
+ */
+static struct workqueue_struct *reset_workqueue;
+
+int efx_create_reset_workqueue(void)
+{
+ reset_workqueue = create_singlethread_workqueue("sfc_reset");
+ if (!reset_workqueue) {
+ printk(KERN_ERR "Failed to create reset workqueue\n");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+void efx_queue_reset_work(struct efx_nic *efx)
+{
+ queue_work(reset_workqueue, &efx->reset_work);
+}
+
+void efx_flush_reset_workqueue(struct efx_nic *efx)
+{
+ cancel_work_sync(&efx->reset_work);
+}
+
+void efx_destroy_reset_workqueue(void)
+{
+ if (reset_workqueue) {
+ destroy_workqueue(reset_workqueue);
+ reset_workqueue = NULL;
+ }
+}
+
+/* We assume that efx->type->reconfigure_mac will always try to sync RX
+ * filters and therefore needs to read-lock the filter table against freeing
+ */
+void efx_mac_reconfigure(struct efx_nic *efx)
+{
+ if (efx->type->reconfigure_mac) {
+ down_read(&efx->filter_sem);
+ efx->type->reconfigure_mac(efx);
+ up_read(&efx->filter_sem);
+ }
+}
+
+/* Asynchronous work item for changing MAC promiscuity and multicast
+ * hash. Avoid a drain/rx_ingress enable by reconfiguring the current
+ * MAC directly.
+ */
+static void efx_mac_work(struct work_struct *data)
+{
+ struct efx_nic *efx = container_of(data, struct efx_nic, mac_work);
+
+ mutex_lock(&efx->mac_lock);
+ if (efx->port_enabled)
+ efx_mac_reconfigure(efx);
+ mutex_unlock(&efx->mac_lock);
+}
+
+/* This ensures that the kernel is kept informed (via
+ * netif_carrier_on/off) of the link status, and also maintains the
+ * link status's stop on the port's TX queue.
+ */
+void efx_link_status_changed(struct efx_nic *efx)
+{
+ struct efx_link_state *link_state = &efx->link_state;
+
+ /* SFC Bug 5356: A net_dev notifier is registered, so we must ensure
+ * that no events are triggered between unregister_netdev() and the
+ * driver unloading. A more general condition is that NETDEV_CHANGE
+ * can only be generated between NETDEV_UP and NETDEV_DOWN
+ */
+ if (!netif_running(efx->net_dev))
+ return;
+
+ if (link_state->up != netif_carrier_ok(efx->net_dev)) {
+ efx->n_link_state_changes++;
+
+ if (link_state->up)
+ netif_carrier_on(efx->net_dev);
+ else
+ netif_carrier_off(efx->net_dev);
+ }
+
+ /* Status message for kernel log */
+ if (link_state->up)
+ netif_info(efx, link, efx->net_dev,
+ "link up at %uMbps %s-duplex (MTU %d)\n",
+ link_state->speed, link_state->fd ? "full" : "half",
+ efx->net_dev->mtu);
+ else
+ netif_info(efx, link, efx->net_dev, "link down\n");
+}
+
+unsigned int efx_xdp_max_mtu(struct efx_nic *efx)
+{
+ /* The maximum MTU that we can fit in a single page, allowing for
+ * framing, overhead and XDP headroom.
+ */
+ int overhead = EFX_MAX_FRAME_LEN(0) + sizeof(struct efx_rx_page_state) +
+ efx->rx_prefix_size + efx->type->rx_buffer_padding +
+ efx->rx_ip_align + XDP_PACKET_HEADROOM;
+
+ return PAGE_SIZE - overhead;
+}
+
+/* Context: process, rtnl_lock() held. */
+int efx_change_mtu(struct net_device *net_dev, int new_mtu)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+ int rc;
+
+ rc = efx_check_disabled(efx);
+ if (rc)
+ return rc;
+
+ if (rtnl_dereference(efx->xdp_prog) &&
+ new_mtu > efx_xdp_max_mtu(efx)) {
+ netif_err(efx, drv, efx->net_dev,
+ "Requested MTU of %d too big for XDP (max: %d)\n",
+ new_mtu, efx_xdp_max_mtu(efx));
+ return -EINVAL;
+ }
+
+ netif_dbg(efx, drv, efx->net_dev, "changing MTU to %d\n", new_mtu);
+
+ efx_device_detach_sync(efx);
+ efx_stop_all(efx);
+
+ mutex_lock(&efx->mac_lock);
+ net_dev->mtu = new_mtu;
+ efx_mac_reconfigure(efx);
+ mutex_unlock(&efx->mac_lock);
+
+ efx_start_all(efx);
+ efx_device_attach_if_not_resetting(efx);
+ return 0;
+}
+
+/**************************************************************************
+ *
+ * Hardware monitor
+ *
+ **************************************************************************/
+
+/* Run periodically off the general workqueue */
+static void efx_monitor(struct work_struct *data)
+{
+ struct efx_nic *efx = container_of(data, struct efx_nic,
+ monitor_work.work);
+
+ netif_vdbg(efx, timer, efx->net_dev,
+ "hardware monitor executing on CPU %d\n",
+ raw_smp_processor_id());
+ BUG_ON(efx->type->monitor == NULL);
+
+ /* If the mac_lock is already held then it is likely a port
+ * reconfiguration is already in place, which will likely do
+ * most of the work of monitor() anyway.
+ */
+ if (mutex_trylock(&efx->mac_lock)) {
+ if (efx->port_enabled && efx->type->monitor)
+ efx->type->monitor(efx);
+ mutex_unlock(&efx->mac_lock);
+ }
+
+ efx_start_monitor(efx);
+}
+
+void efx_start_monitor(struct efx_nic *efx)
+{
+ if (efx->type->monitor)
+ queue_delayed_work(efx->workqueue, &efx->monitor_work,
+ efx_monitor_interval);
+}
+
+/**************************************************************************
+ *
+ * Event queue processing
+ *
+ *************************************************************************/
+
+/* Channels are shutdown and reinitialised whilst the NIC is running
+ * to propagate configuration changes (mtu, checksum offload), or
+ * to clear hardware error conditions
+ */
+static void efx_start_datapath(struct efx_nic *efx)
+{
+ netdev_features_t old_features = efx->net_dev->features;
+ bool old_rx_scatter = efx->rx_scatter;
+ size_t rx_buf_len;
+
+ /* Calculate the rx buffer allocation parameters required to
+ * support the current MTU, including padding for header
+ * alignment and overruns.
+ */
+ efx->rx_dma_len = (efx->rx_prefix_size +
+ EFX_MAX_FRAME_LEN(efx->net_dev->mtu) +
+ efx->type->rx_buffer_padding);
+ rx_buf_len = (sizeof(struct efx_rx_page_state) + XDP_PACKET_HEADROOM +
+ efx->rx_ip_align + efx->rx_dma_len);
+ if (rx_buf_len <= PAGE_SIZE) {
+ efx->rx_scatter = efx->type->always_rx_scatter;
+ efx->rx_buffer_order = 0;
+ } else if (efx->type->can_rx_scatter) {
+ BUILD_BUG_ON(EFX_RX_USR_BUF_SIZE % L1_CACHE_BYTES);
+ BUILD_BUG_ON(sizeof(struct efx_rx_page_state) +
+ 2 * ALIGN(NET_IP_ALIGN + EFX_RX_USR_BUF_SIZE,
+ EFX_RX_BUF_ALIGNMENT) >
+ PAGE_SIZE);
+ efx->rx_scatter = true;
+ efx->rx_dma_len = EFX_RX_USR_BUF_SIZE;
+ efx->rx_buffer_order = 0;
+ } else {
+ efx->rx_scatter = false;
+ efx->rx_buffer_order = get_order(rx_buf_len);
+ }
+
+ efx_rx_config_page_split(efx);
+ if (efx->rx_buffer_order)
+ netif_dbg(efx, drv, efx->net_dev,
+ "RX buf len=%u; page order=%u batch=%u\n",
+ efx->rx_dma_len, efx->rx_buffer_order,
+ efx->rx_pages_per_batch);
+ else
+ netif_dbg(efx, drv, efx->net_dev,
+ "RX buf len=%u step=%u bpp=%u; page batch=%u\n",
+ efx->rx_dma_len, efx->rx_page_buf_step,
+ efx->rx_bufs_per_page, efx->rx_pages_per_batch);
+
+ /* Restore previously fixed features in hw_features and remove
+ * features which are fixed now
+ */
+ efx->net_dev->hw_features |= efx->net_dev->features;
+ efx->net_dev->hw_features &= ~efx->fixed_features;
+ efx->net_dev->features |= efx->fixed_features;
+ if (efx->net_dev->features != old_features)
+ netdev_features_change(efx->net_dev);
+
+ /* RX filters may also have scatter-enabled flags */
+ if ((efx->rx_scatter != old_rx_scatter) &&
+ efx->type->filter_update_rx_scatter)
+ efx->type->filter_update_rx_scatter(efx);
+
+ /* We must keep at least one descriptor in a TX ring empty.
+ * We could avoid this when the queue size does not exactly
+ * match the hardware ring size, but it's not that important.
+ * Therefore we stop the queue when one more skb might fill
+ * the ring completely. We wake it when half way back to
+ * empty.
+ */
+ efx->txq_stop_thresh = efx->txq_entries - efx_tx_max_skb_descs(efx);
+ efx->txq_wake_thresh = efx->txq_stop_thresh / 2;
+
+ /* Initialise the channels */
+ efx_start_channels(efx);
+
+ efx_ptp_start_datapath(efx);
+
+ if (netif_device_present(efx->net_dev))
+ netif_tx_wake_all_queues(efx->net_dev);
+}
+
+static void efx_stop_datapath(struct efx_nic *efx)
+{
+ EFX_ASSERT_RESET_SERIALISED(efx);
+ BUG_ON(efx->port_enabled);
+
+ efx_ptp_stop_datapath(efx);
+
+ efx_stop_channels(efx);
+}
+
+/**************************************************************************
+ *
+ * Port handling
+ *
+ **************************************************************************/
+
+static void efx_start_port(struct efx_nic *efx)
+{
+ netif_dbg(efx, ifup, efx->net_dev, "start port\n");
+ BUG_ON(efx->port_enabled);
+
+ mutex_lock(&efx->mac_lock);
+ efx->port_enabled = true;
+
+ /* Ensure MAC ingress/egress is enabled */
+ efx_mac_reconfigure(efx);
+
+ mutex_unlock(&efx->mac_lock);
+}
+
+/* Cancel work for MAC reconfiguration, periodic hardware monitoring
+ * and the async self-test, wait for them to finish and prevent them
+ * being scheduled again. This doesn't cover online resets, which
+ * should only be cancelled when removing the device.
+ */
+static void efx_stop_port(struct efx_nic *efx)
+{
+ netif_dbg(efx, ifdown, efx->net_dev, "stop port\n");
+
+ EFX_ASSERT_RESET_SERIALISED(efx);
+
+ mutex_lock(&efx->mac_lock);
+ efx->port_enabled = false;
+ mutex_unlock(&efx->mac_lock);
+
+ /* Serialise against efx_set_multicast_list() */
+ netif_addr_lock_bh(efx->net_dev);
+ netif_addr_unlock_bh(efx->net_dev);
+
+ cancel_delayed_work_sync(&efx->monitor_work);
+ efx_selftest_async_cancel(efx);
+ cancel_work_sync(&efx->mac_work);
+}
+
+/* If the interface is supposed to be running but is not, start
+ * the hardware and software data path, regular activity for the port
+ * (MAC statistics, link polling, etc.) and schedule the port to be
+ * reconfigured. Interrupts must already be enabled. This function
+ * is safe to call multiple times, so long as the NIC is not disabled.
+ * Requires the RTNL lock.
+ */
+void efx_start_all(struct efx_nic *efx)
+{
+ EFX_ASSERT_RESET_SERIALISED(efx);
+ BUG_ON(efx->state == STATE_DISABLED);
+
+ /* Check that it is appropriate to restart the interface. All
+ * of these flags are safe to read under just the rtnl lock
+ */
+ if (efx->port_enabled || !netif_running(efx->net_dev) ||
+ efx->reset_pending)
+ return;
+
+ efx_start_port(efx);
+ efx_start_datapath(efx);
+
+ /* Start the hardware monitor if there is one */
+ efx_start_monitor(efx);
+
+ /* Link state detection is normally event-driven; we have
+ * to poll now because we could have missed a change
+ */
+ mutex_lock(&efx->mac_lock);
+ if (efx->phy_op->poll(efx))
+ efx_link_status_changed(efx);
+ mutex_unlock(&efx->mac_lock);
+
+ if (efx->type->start_stats) {
+ efx->type->start_stats(efx);
+ efx->type->pull_stats(efx);
+ spin_lock_bh(&efx->stats_lock);
+ efx->type->update_stats(efx, NULL, NULL);
+ spin_unlock_bh(&efx->stats_lock);
+ }
+}
+
+/* Quiesce the hardware and software data path, and regular activity
+ * for the port without bringing the link down. Safe to call multiple
+ * times with the NIC in almost any state, but interrupts should be
+ * enabled. Requires the RTNL lock.
+ */
+void efx_stop_all(struct efx_nic *efx)
+{
+ EFX_ASSERT_RESET_SERIALISED(efx);
+
+ /* port_enabled can be read safely under the rtnl lock */
+ if (!efx->port_enabled)
+ return;
+
+ if (efx->type->update_stats) {
+ /* update stats before we go down so we can accurately count
+ * rx_nodesc_drops
+ */
+ efx->type->pull_stats(efx);
+ spin_lock_bh(&efx->stats_lock);
+ efx->type->update_stats(efx, NULL, NULL);
+ spin_unlock_bh(&efx->stats_lock);
+ efx->type->stop_stats(efx);
+ }
+
+ efx_stop_port(efx);
+
+ /* Stop the kernel transmit interface. This is only valid if
+ * the device is stopped or detached; otherwise the watchdog
+ * may fire immediately.
+ */
+ WARN_ON(netif_running(efx->net_dev) &&
+ netif_device_present(efx->net_dev));
+ netif_tx_disable(efx->net_dev);
+
+ efx_stop_datapath(efx);
+}
+
+/* Context: process, dev_base_lock or RTNL held, non-blocking. */
+void efx_net_stats(struct net_device *net_dev, struct rtnl_link_stats64 *stats)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+
+ spin_lock_bh(&efx->stats_lock);
+ efx->type->update_stats(efx, NULL, stats);
+ spin_unlock_bh(&efx->stats_lock);
+}
+
+/* Push loopback/power/transmit disable settings to the PHY, and reconfigure
+ * the MAC appropriately. All other PHY configuration changes are pushed
+ * through phy_op->set_settings(), and pushed asynchronously to the MAC
+ * through efx_monitor().
+ *
+ * Callers must hold the mac_lock
+ */
+int __efx_reconfigure_port(struct efx_nic *efx)
+{
+ enum efx_phy_mode phy_mode;
+ int rc = 0;
+
+ WARN_ON(!mutex_is_locked(&efx->mac_lock));
+
+ /* Disable PHY transmit in mac level loopbacks */
+ phy_mode = efx->phy_mode;
+ if (LOOPBACK_INTERNAL(efx))
+ efx->phy_mode |= PHY_MODE_TX_DISABLED;
+ else
+ efx->phy_mode &= ~PHY_MODE_TX_DISABLED;
+
+ if (efx->type->reconfigure_port)
+ rc = efx->type->reconfigure_port(efx);
+
+ if (rc)
+ efx->phy_mode = phy_mode;
+
+ return rc;
+}
+
+/* Reinitialise the MAC to pick up new PHY settings, even if the port is
+ * disabled.
+ */
+int efx_reconfigure_port(struct efx_nic *efx)
+{
+ int rc;
+
+ EFX_ASSERT_RESET_SERIALISED(efx);
+
+ mutex_lock(&efx->mac_lock);
+ rc = __efx_reconfigure_port(efx);
+ mutex_unlock(&efx->mac_lock);
+
+ return rc;
+}
+
+/**************************************************************************
+ *
+ * Device reset and suspend
+ *
+ **************************************************************************/
+
+static void efx_wait_for_bist_end(struct efx_nic *efx)
+{
+ int i;
+
+ for (i = 0; i < BIST_WAIT_DELAY_COUNT; ++i) {
+ if (efx_mcdi_poll_reboot(efx))
+ goto out;
+ msleep(BIST_WAIT_DELAY_MS);
+ }
+
+ netif_err(efx, drv, efx->net_dev, "Warning: No MC reboot after BIST mode\n");
+out:
+ /* Either way unset the BIST flag. If we found no reboot we probably
+ * won't recover, but we should try.
+ */
+ efx->mc_bist_for_other_fn = false;
+}
+
+/* Try recovery mechanisms.
+ * For now only EEH is supported.
+ * Returns 0 if the recovery mechanisms are unsuccessful.
+ * Returns a non-zero value otherwise.
+ */
+int efx_try_recovery(struct efx_nic *efx)
+{
+#ifdef CONFIG_EEH
+ /* A PCI error can occur and not be seen by EEH because nothing
+ * happens on the PCI bus. In this case the driver may fail and
+ * schedule a 'recover or reset', leading to this recovery handler.
+ * Manually call the eeh failure check function.
+ */
+ struct eeh_dev *eehdev = pci_dev_to_eeh_dev(efx->pci_dev);
+ if (eeh_dev_check_failure(eehdev)) {
+ /* The EEH mechanisms will handle the error and reset the
+ * device if necessary.
+ */
+ return 1;
+ }
+#endif
+ return 0;
+}
+
+/* Tears down the entire software state and most of the hardware state
+ * before reset.
+ */
+void efx_reset_down(struct efx_nic *efx, enum reset_type method)
+{
+ EFX_ASSERT_RESET_SERIALISED(efx);
+
+ if (method == RESET_TYPE_MCDI_TIMEOUT)
+ efx->type->prepare_flr(efx);
+
+ efx_stop_all(efx);
+ efx_disable_interrupts(efx);
+
+ mutex_lock(&efx->mac_lock);
+ down_write(&efx->filter_sem);
+ mutex_lock(&efx->rss_lock);
+ if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
+ method != RESET_TYPE_DATAPATH)
+ efx->phy_op->fini(efx);
+ efx->type->fini(efx);
+}
+
+/* This function will always ensure that the locks acquired in
+ * efx_reset_down() are released. A failure return code indicates
+ * that we were unable to reinitialise the hardware, and the
+ * driver should be disabled. If ok is false, then the rx and tx
+ * engines are not restarted, pending a RESET_DISABLE.
+ */
+int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
+{
+ int rc;
+
+ EFX_ASSERT_RESET_SERIALISED(efx);
+
+ if (method == RESET_TYPE_MCDI_TIMEOUT)
+ efx->type->finish_flr(efx);
+
+ /* Ensure that SRAM is initialised even if we're disabling the device */
+ rc = efx->type->init(efx);
+ if (rc) {
+ netif_err(efx, drv, efx->net_dev, "failed to initialise NIC\n");
+ goto fail;
+ }
+
+ if (!ok)
+ goto fail;
+
+ if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
+ method != RESET_TYPE_DATAPATH) {
+ rc = efx->phy_op->init(efx);
+ if (rc)
+ goto fail;
+ rc = efx->phy_op->reconfigure(efx);
+ if (rc && rc != -EPERM)
+ netif_err(efx, drv, efx->net_dev,
+ "could not restore PHY settings\n");
+ }
+
+ rc = efx_enable_interrupts(efx);
+ if (rc)
+ goto fail;
+
+#ifdef CONFIG_SFC_SRIOV
+ rc = efx->type->vswitching_restore(efx);
+ if (rc) /* not fatal; the PF will still work fine */
+ netif_warn(efx, probe, efx->net_dev,
+ "failed to restore vswitching rc=%d;"
+ " VFs may not function\n", rc);
+#endif
+
+ if (efx->type->rx_restore_rss_contexts)
+ efx->type->rx_restore_rss_contexts(efx);
+ mutex_unlock(&efx->rss_lock);
+ efx->type->filter_table_restore(efx);
+ up_write(&efx->filter_sem);
+ if (efx->type->sriov_reset)
+ efx->type->sriov_reset(efx);
+
+ mutex_unlock(&efx->mac_lock);
+
+ efx_start_all(efx);
+
+ if (efx->type->udp_tnl_push_ports)
+ efx->type->udp_tnl_push_ports(efx);
+
+ return 0;
+
+fail:
+ efx->port_initialized = false;
+
+ mutex_unlock(&efx->rss_lock);
+ up_write(&efx->filter_sem);
+ mutex_unlock(&efx->mac_lock);
+
+ return rc;
+}
+
+/* Reset the NIC using the specified method. Note that the reset may
+ * fail, in which case the card will be left in an unusable state.
+ *
+ * Caller must hold the rtnl_lock.
+ */
+int efx_reset(struct efx_nic *efx, enum reset_type method)
+{
+ bool disabled;
+ int rc, rc2;
+
+ netif_info(efx, drv, efx->net_dev, "resetting (%s)\n",
+ RESET_TYPE(method));
+
+ efx_device_detach_sync(efx);
+ efx_reset_down(efx, method);
+
+ rc = efx->type->reset(efx, method);
+ if (rc) {
+ netif_err(efx, drv, efx->net_dev, "failed to reset hardware\n");
+ goto out;
+ }
+
+ /* Clear flags for the scopes we covered. We assume the NIC and
+ * driver are now quiescent so that there is no race here.
+ */
+ if (method < RESET_TYPE_MAX_METHOD)
+ efx->reset_pending &= -(1 << (method + 1));
+ else /* it doesn't fit into the well-ordered scope hierarchy */
+ __clear_bit(method, &efx->reset_pending);
+
+ /* Reinitialise bus-mastering, which may have been turned off before
+ * the reset was scheduled. This is still appropriate, even in the
+ * RESET_TYPE_DISABLE since this driver generally assumes the hardware
+ * can respond to requests.
+ */
+ pci_set_master(efx->pci_dev);
+
+out:
+ /* Leave device stopped if necessary */
+ disabled = rc ||
+ method == RESET_TYPE_DISABLE ||
+ method == RESET_TYPE_RECOVER_OR_DISABLE;
+ rc2 = efx_reset_up(efx, method, !disabled);
+ if (rc2) {
+ disabled = true;
+ if (!rc)
+ rc = rc2;
+ }
+
+ if (disabled) {
+ dev_close(efx->net_dev);
+ netif_err(efx, drv, efx->net_dev, "has been disabled\n");
+ efx->state = STATE_DISABLED;
+ } else {
+ netif_dbg(efx, drv, efx->net_dev, "reset complete\n");
+ efx_device_attach_if_not_resetting(efx);
+ }
+ return rc;
+}
+
+/* The worker thread exists so that code that cannot sleep can
+ * schedule a reset for later.
+ */
+static void efx_reset_work(struct work_struct *data)
+{
+ struct efx_nic *efx = container_of(data, struct efx_nic, reset_work);
+ unsigned long pending;
+ enum reset_type method;
+
+ pending = READ_ONCE(efx->reset_pending);
+ method = fls(pending) - 1;
+
+ if (method == RESET_TYPE_MC_BIST)
+ efx_wait_for_bist_end(efx);
+
+ if ((method == RESET_TYPE_RECOVER_OR_DISABLE ||
+ method == RESET_TYPE_RECOVER_OR_ALL) &&
+ efx_try_recovery(efx))
+ return;
+
+ if (!pending)
+ return;
+
+ rtnl_lock();
+
+ /* We checked the state in efx_schedule_reset() but it may
+ * have changed by now. Now that we have the RTNL lock,
+ * it cannot change again.
+ */
+ if (efx->state == STATE_READY)
+ (void)efx_reset(efx, method);
+
+ rtnl_unlock();
+}
+
+void efx_schedule_reset(struct efx_nic *efx, enum reset_type type)
+{
+ enum reset_type method;
+
+ if (efx->state == STATE_RECOVERY) {
+ netif_dbg(efx, drv, efx->net_dev,
+ "recovering: skip scheduling %s reset\n",
+ RESET_TYPE(type));
+ return;
+ }
+
+ switch (type) {
+ case RESET_TYPE_INVISIBLE:
+ case RESET_TYPE_ALL:
+ case RESET_TYPE_RECOVER_OR_ALL:
+ case RESET_TYPE_WORLD:
+ case RESET_TYPE_DISABLE:
+ case RESET_TYPE_RECOVER_OR_DISABLE:
+ case RESET_TYPE_DATAPATH:
+ case RESET_TYPE_MC_BIST:
+ case RESET_TYPE_MCDI_TIMEOUT:
+ method = type;
+ netif_dbg(efx, drv, efx->net_dev, "scheduling %s reset\n",
+ RESET_TYPE(method));
+ break;
+ default:
+ method = efx->type->map_reset_reason(type);
+ netif_dbg(efx, drv, efx->net_dev,
+ "scheduling %s reset for %s\n",
+ RESET_TYPE(method), RESET_TYPE(type));
+ break;
+ }
+
+ set_bit(method, &efx->reset_pending);
+ smp_mb(); /* ensure we change reset_pending before checking state */
+
+ /* If we're not READY then just leave the flags set as the cue
+ * to abort probing or reschedule the reset later.
+ */
+ if (READ_ONCE(efx->state) != STATE_READY)
+ return;
+
+ /* efx_process_channel() will no longer read events once a
+ * reset is scheduled. So switch back to poll'd MCDI completions.
+ */
+ efx_mcdi_mode_poll(efx);
+
+ efx_queue_reset_work(efx);
+}
+
+/**************************************************************************
+ *
+ * Dummy PHY/MAC operations
+ *
+ * Can be used for some unimplemented operations
+ * Needed so all function pointers are valid and do not have to be tested
+ * before use
+ *
+ **************************************************************************/
+int efx_port_dummy_op_int(struct efx_nic *efx)
+{
+ return 0;
+}
+void efx_port_dummy_op_void(struct efx_nic *efx) {}
+
+static bool efx_port_dummy_op_poll(struct efx_nic *efx)
+{
+ return false;
+}
+
+static const struct efx_phy_operations efx_dummy_phy_operations = {
+ .init = efx_port_dummy_op_int,
+ .reconfigure = efx_port_dummy_op_int,
+ .poll = efx_port_dummy_op_poll,
+ .fini = efx_port_dummy_op_void,
+};
+
+/**************************************************************************
+ *
+ * Data housekeeping
+ *
+ **************************************************************************/
+
+/* This zeroes out and then fills in the invariants in a struct
+ * efx_nic (including all sub-structures).
+ */
+int efx_init_struct(struct efx_nic *efx,
+ struct pci_dev *pci_dev, struct net_device *net_dev)
+{
+ int rc = -ENOMEM;
+
+ /* Initialise common structures */
+ INIT_LIST_HEAD(&efx->node);
+ INIT_LIST_HEAD(&efx->secondary_list);
+ spin_lock_init(&efx->biu_lock);
+#ifdef CONFIG_SFC_MTD
+ INIT_LIST_HEAD(&efx->mtd_list);
+#endif
+ INIT_WORK(&efx->reset_work, efx_reset_work);
+ INIT_DELAYED_WORK(&efx->monitor_work, efx_monitor);
+ efx_selftest_async_init(efx);
+ efx->pci_dev = pci_dev;
+ efx->msg_enable = debug;
+ efx->state = STATE_UNINIT;
+ strlcpy(efx->name, pci_name(pci_dev), sizeof(efx->name));
+
+ efx->net_dev = net_dev;
+ efx->rx_prefix_size = efx->type->rx_prefix_size;
+ efx->rx_ip_align =
+ NET_IP_ALIGN ? (efx->rx_prefix_size + NET_IP_ALIGN) % 4 : 0;
+ efx->rx_packet_hash_offset =
+ efx->type->rx_hash_offset - efx->type->rx_prefix_size;
+ efx->rx_packet_ts_offset =
+ efx->type->rx_ts_offset - efx->type->rx_prefix_size;
+ INIT_LIST_HEAD(&efx->rss_context.list);
+ mutex_init(&efx->rss_lock);
+ spin_lock_init(&efx->stats_lock);
+ efx->vi_stride = EFX_DEFAULT_VI_STRIDE;
+ efx->num_mac_stats = MC_CMD_MAC_NSTATS;
+ BUILD_BUG_ON(MC_CMD_MAC_NSTATS - 1 != MC_CMD_MAC_GENERATION_END);
+ mutex_init(&efx->mac_lock);
+#ifdef CONFIG_RFS_ACCEL
+ mutex_init(&efx->rps_mutex);
+ spin_lock_init(&efx->rps_hash_lock);
+ /* Failure to allocate is not fatal, but may degrade ARFS performance */
+ efx->rps_hash_table = kcalloc(EFX_ARFS_HASH_TABLE_SIZE,
+ sizeof(*efx->rps_hash_table), GFP_KERNEL);
+#endif
+ efx->phy_op = &efx_dummy_phy_operations;
+ efx->mdio.dev = net_dev;
+ INIT_WORK(&efx->mac_work, efx_mac_work);
+ init_waitqueue_head(&efx->flush_wq);
+
+ rc = efx_init_channels(efx);
+ if (rc)
+ goto fail;
+
+ /* Would be good to use the net_dev name, but we're too early */
+ snprintf(efx->workqueue_name, sizeof(efx->workqueue_name), "sfc%s",
+ pci_name(pci_dev));
+ efx->workqueue = create_singlethread_workqueue(efx->workqueue_name);
+ if (!efx->workqueue) {
+ rc = -ENOMEM;
+ goto fail;
+ }
+
+ return 0;
+
+fail:
+ efx_fini_struct(efx);
+ return rc;
+}
+
+void efx_fini_struct(struct efx_nic *efx)
+{
+#ifdef CONFIG_RFS_ACCEL
+ kfree(efx->rps_hash_table);
+#endif
+
+ efx_fini_channels(efx);
+
+ kfree(efx->vpd_sn);
+
+ if (efx->workqueue) {
+ destroy_workqueue(efx->workqueue);
+ efx->workqueue = NULL;
+ }
+}
+
+/* This configures the PCI device to enable I/O and DMA. */
+int efx_init_io(struct efx_nic *efx, int bar, dma_addr_t dma_mask,
+ unsigned int mem_map_size)
+{
+ struct pci_dev *pci_dev = efx->pci_dev;
+ int rc;
+
+ netif_dbg(efx, probe, efx->net_dev, "initialising I/O\n");
+
+ rc = pci_enable_device(pci_dev);
+ if (rc) {
+ netif_err(efx, probe, efx->net_dev,
+ "failed to enable PCI device\n");
+ goto fail1;
+ }
+
+ pci_set_master(pci_dev);
+
+ /* Set the PCI DMA mask. Try all possibilities from our
+ * genuine mask down to 32 bits, because some architectures
+ * (e.g. x86_64 with iommu_sac_force set) will allow 40 bit
+ * masks event though they reject 46 bit masks.
+ */
+ while (dma_mask > 0x7fffffffUL) {
+ rc = dma_set_mask_and_coherent(&pci_dev->dev, dma_mask);
+ if (rc == 0)
+ break;
+ dma_mask >>= 1;
+ }
+ if (rc) {
+ netif_err(efx, probe, efx->net_dev,
+ "could not find a suitable DMA mask\n");
+ goto fail2;
+ }
+ netif_dbg(efx, probe, efx->net_dev,
+ "using DMA mask %llx\n", (unsigned long long)dma_mask);
+
+ efx->membase_phys = pci_resource_start(efx->pci_dev, bar);
+ if (!efx->membase_phys) {
+ netif_err(efx, probe, efx->net_dev,
+ "ERROR: No BAR%d mapping from the BIOS. "
+ "Try pci=realloc on the kernel command line\n", bar);
+ rc = -ENODEV;
+ goto fail3;
+ }
+
+ rc = pci_request_region(pci_dev, bar, "sfc");
+ if (rc) {
+ netif_err(efx, probe, efx->net_dev,
+ "request for memory BAR failed\n");
+ rc = -EIO;
+ goto fail3;
+ }
+
+ efx->membase = ioremap_nocache(efx->membase_phys, mem_map_size);
+ if (!efx->membase) {
+ netif_err(efx, probe, efx->net_dev,
+ "could not map memory BAR at %llx+%x\n",
+ (unsigned long long)efx->membase_phys, mem_map_size);
+ rc = -ENOMEM;
+ goto fail4;
+ }
+ netif_dbg(efx, probe, efx->net_dev,
+ "memory BAR at %llx+%x (virtual %p)\n",
+ (unsigned long long)efx->membase_phys, mem_map_size,
+ efx->membase);
+
+ return 0;
+
+fail4:
+ pci_release_region(efx->pci_dev, bar);
+fail3:
+ efx->membase_phys = 0;
+fail2:
+ pci_disable_device(efx->pci_dev);
+fail1:
+ return rc;
+}
+
+void efx_fini_io(struct efx_nic *efx, int bar)
+{
+ netif_dbg(efx, drv, efx->net_dev, "shutting down I/O\n");
+
+ if (efx->membase) {
+ iounmap(efx->membase);
+ efx->membase = NULL;
+ }
+
+ if (efx->membase_phys) {
+ pci_release_region(efx->pci_dev, bar);
+ efx->membase_phys = 0;
+ }
+
+ /* Don't disable bus-mastering if VFs are assigned */
+ if (!pci_vfs_assigned(efx->pci_dev))
+ pci_disable_device(efx->pci_dev);
+}
+
+#ifdef CONFIG_SFC_MCDI_LOGGING
+static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct efx_nic *efx = dev_get_drvdata(dev);
+ struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+
+ return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled);
+}
+
+static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct efx_nic *efx = dev_get_drvdata(dev);
+ struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+ bool enable = count > 0 && *buf != '0';
+
+ mcdi->logging_enabled = enable;
+ return count;
+}
+
+static DEVICE_ATTR(mcdi_logging, 0644, show_mcdi_log, set_mcdi_log);
+
+void efx_init_mcdi_logging(struct efx_nic *efx)
+{
+ int rc = device_create_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging);
+
+ if (rc) {
+ netif_warn(efx, drv, efx->net_dev,
+ "failed to init net dev attributes\n");
+ }
+}
+
+void efx_fini_mcdi_logging(struct efx_nic *efx)
+{
+ device_remove_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging);
+}
+#endif
diff --git a/drivers/net/ethernet/sfc/efx_common.h b/drivers/net/ethernet/sfc/efx_common.h
new file mode 100644
index 0000000..fa2fc68
--- /dev/null
+++ b/drivers/net/ethernet/sfc/efx_common.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EFX_COMMON_H
+#define EFX_COMMON_H
+
+int efx_init_io(struct efx_nic *efx, int bar, dma_addr_t dma_mask,
+ unsigned int mem_map_size);
+void efx_fini_io(struct efx_nic *efx, int bar);
+int efx_init_struct(struct efx_nic *efx, struct pci_dev *pci_dev,
+ struct net_device *net_dev);
+void efx_fini_struct(struct efx_nic *efx);
+
+void efx_start_all(struct efx_nic *efx);
+void efx_stop_all(struct efx_nic *efx);
+
+void efx_net_stats(struct net_device *net_dev, struct rtnl_link_stats64 *stats);
+
+int efx_create_reset_workqueue(void);
+void efx_queue_reset_work(struct efx_nic *efx);
+void efx_flush_reset_workqueue(struct efx_nic *efx);
+void efx_destroy_reset_workqueue(void);
+
+void efx_start_monitor(struct efx_nic *efx);
+
+int __efx_reconfigure_port(struct efx_nic *efx);
+int efx_reconfigure_port(struct efx_nic *efx);
+
+#define EFX_ASSERT_RESET_SERIALISED(efx) \
+ do { \
+ if ((efx->state == STATE_READY) || \
+ (efx->state == STATE_RECOVERY) || \
+ (efx->state == STATE_DISABLED)) \
+ ASSERT_RTNL(); \
+ } while (0)
+
+int efx_try_recovery(struct efx_nic *efx);
+void efx_reset_down(struct efx_nic *efx, enum reset_type method);
+int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok);
+int efx_reset(struct efx_nic *efx, enum reset_type method);
+void efx_schedule_reset(struct efx_nic *efx, enum reset_type type);
+
+static inline int efx_check_disabled(struct efx_nic *efx)
+{
+ if (efx->state == STATE_DISABLED || efx->state == STATE_RECOVERY) {
+ netif_err(efx, drv, efx->net_dev,
+ "device is disabled due to earlier errors\n");
+ return -EIO;
+ }
+ return 0;
+}
+
+#ifdef CONFIG_SFC_MCDI_LOGGING
+void efx_init_mcdi_logging(struct efx_nic *efx);
+void efx_fini_mcdi_logging(struct efx_nic *efx);
+#else
+static inline void efx_init_mcdi_logging(struct efx_nic *efx) {}
+static inline void efx_fini_mcdi_logging(struct efx_nic *efx) {}
+#endif
+
+void efx_mac_reconfigure(struct efx_nic *efx);
+void efx_link_status_changed(struct efx_nic *efx);
+unsigned int efx_xdp_max_mtu(struct efx_nic *efx);
+int efx_change_mtu(struct net_device *net_dev, int new_mtu);
+
+#endif
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index b31032d..993b576 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -13,92 +13,13 @@
#include "workarounds.h"
#include "selftest.h"
#include "efx.h"
+#include "efx_channels.h"
+#include "rx_common.h"
+#include "tx_common.h"
+#include "ethtool_common.h"
#include "filter.h"
#include "nic.h"
-struct efx_sw_stat_desc {
- const char *name;
- enum {
- EFX_ETHTOOL_STAT_SOURCE_nic,
- EFX_ETHTOOL_STAT_SOURCE_channel,
- EFX_ETHTOOL_STAT_SOURCE_tx_queue
- } source;
- unsigned offset;
- u64(*get_stat) (void *field); /* Reader function */
-};
-
-/* Initialiser for a struct efx_sw_stat_desc with type-checking */
-#define EFX_ETHTOOL_STAT(stat_name, source_name, field, field_type, \
- get_stat_function) { \
- .name = #stat_name, \
- .source = EFX_ETHTOOL_STAT_SOURCE_##source_name, \
- .offset = ((((field_type *) 0) == \
- &((struct efx_##source_name *)0)->field) ? \
- offsetof(struct efx_##source_name, field) : \
- offsetof(struct efx_##source_name, field)), \
- .get_stat = get_stat_function, \
-}
-
-static u64 efx_get_uint_stat(void *field)
-{
- return *(unsigned int *)field;
-}
-
-static u64 efx_get_atomic_stat(void *field)
-{
- return atomic_read((atomic_t *) field);
-}
-
-#define EFX_ETHTOOL_ATOMIC_NIC_ERROR_STAT(field) \
- EFX_ETHTOOL_STAT(field, nic, field, \
- atomic_t, efx_get_atomic_stat)
-
-#define EFX_ETHTOOL_UINT_CHANNEL_STAT(field) \
- EFX_ETHTOOL_STAT(field, channel, n_##field, \
- unsigned int, efx_get_uint_stat)
-#define EFX_ETHTOOL_UINT_CHANNEL_STAT_NO_N(field) \
- EFX_ETHTOOL_STAT(field, channel, field, \
- unsigned int, efx_get_uint_stat)
-
-#define EFX_ETHTOOL_UINT_TXQ_STAT(field) \
- EFX_ETHTOOL_STAT(tx_##field, tx_queue, field, \
- unsigned int, efx_get_uint_stat)
-
-static const struct efx_sw_stat_desc efx_sw_stat_desc[] = {
- EFX_ETHTOOL_UINT_TXQ_STAT(merge_events),
- EFX_ETHTOOL_UINT_TXQ_STAT(tso_bursts),
- EFX_ETHTOOL_UINT_TXQ_STAT(tso_long_headers),
- EFX_ETHTOOL_UINT_TXQ_STAT(tso_packets),
- EFX_ETHTOOL_UINT_TXQ_STAT(tso_fallbacks),
- EFX_ETHTOOL_UINT_TXQ_STAT(pushes),
- EFX_ETHTOOL_UINT_TXQ_STAT(pio_packets),
- EFX_ETHTOOL_UINT_TXQ_STAT(cb_packets),
- EFX_ETHTOOL_ATOMIC_NIC_ERROR_STAT(rx_reset),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tobe_disc),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_ip_hdr_chksum_err),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tcp_udp_chksum_err),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_inner_ip_hdr_chksum_err),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_inner_tcp_udp_chksum_err),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_outer_ip_hdr_chksum_err),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_outer_tcp_udp_chksum_err),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_eth_crc_err),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_mcast_mismatch),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_frm_trunc),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_merge_events),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_merge_packets),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_xdp_drops),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_xdp_bad_drops),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_xdp_tx),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_xdp_redirect),
-#ifdef CONFIG_RFS_ACCEL
- EFX_ETHTOOL_UINT_CHANNEL_STAT_NO_N(rfs_filter_count),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rfs_succeeded),
- EFX_ETHTOOL_UINT_CHANNEL_STAT(rfs_failed),
-#endif
-};
-
-#define EFX_ETHTOOL_SW_STAT_COUNT ARRAY_SIZE(efx_sw_stat_desc)
-
#define EFX_ETHTOOL_EEPROM_MAGIC 0xEFAB
/**************************************************************************
@@ -185,18 +106,6 @@ efx_ethtool_set_link_ksettings(struct net_device *net_dev,
return rc;
}
-static void efx_ethtool_get_drvinfo(struct net_device *net_dev,
- struct ethtool_drvinfo *info)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
-
- strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
- strlcpy(info->version, EFX_DRIVER_VERSION, sizeof(info->version));
- efx_mcdi_print_fwver(efx, info->fw_version,
- sizeof(info->fw_version));
- strlcpy(info->bus_info, pci_name(efx->pci_dev), sizeof(info->bus_info));
-}
-
static int efx_ethtool_get_regs_len(struct net_device *net_dev)
{
return efx_nic_get_regs_len(netdev_priv(net_dev));
@@ -211,341 +120,6 @@ static void efx_ethtool_get_regs(struct net_device *net_dev,
efx_nic_get_regs(efx, buf);
}
-static u32 efx_ethtool_get_msglevel(struct net_device *net_dev)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
- return efx->msg_enable;
-}
-
-static void efx_ethtool_set_msglevel(struct net_device *net_dev, u32 msg_enable)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
- efx->msg_enable = msg_enable;
-}
-
-/**
- * efx_fill_test - fill in an individual self-test entry
- * @test_index: Index of the test
- * @strings: Ethtool strings, or %NULL
- * @data: Ethtool test results, or %NULL
- * @test: Pointer to test result (used only if data != %NULL)
- * @unit_format: Unit name format (e.g. "chan\%d")
- * @unit_id: Unit id (e.g. 0 for "chan0")
- * @test_format: Test name format (e.g. "loopback.\%s.tx.sent")
- * @test_id: Test id (e.g. "PHYXS" for "loopback.PHYXS.tx_sent")
- *
- * Fill in an individual self-test entry.
- */
-static void efx_fill_test(unsigned int test_index, u8 *strings, u64 *data,
- int *test, const char *unit_format, int unit_id,
- const char *test_format, const char *test_id)
-{
- char unit_str[ETH_GSTRING_LEN], test_str[ETH_GSTRING_LEN];
-
- /* Fill data value, if applicable */
- if (data)
- data[test_index] = *test;
-
- /* Fill string, if applicable */
- if (strings) {
- if (strchr(unit_format, '%'))
- snprintf(unit_str, sizeof(unit_str),
- unit_format, unit_id);
- else
- strcpy(unit_str, unit_format);
- snprintf(test_str, sizeof(test_str), test_format, test_id);
- snprintf(strings + test_index * ETH_GSTRING_LEN,
- ETH_GSTRING_LEN,
- "%-6s %-24s", unit_str, test_str);
- }
-}
-
-#define EFX_CHANNEL_NAME(_channel) "chan%d", _channel->channel
-#define EFX_TX_QUEUE_NAME(_tx_queue) "txq%d", _tx_queue->queue
-#define EFX_RX_QUEUE_NAME(_rx_queue) "rxq%d", _rx_queue->queue
-#define EFX_LOOPBACK_NAME(_mode, _counter) \
- "loopback.%s." _counter, STRING_TABLE_LOOKUP(_mode, efx_loopback_mode)
-
-/**
- * efx_fill_loopback_test - fill in a block of loopback self-test entries
- * @efx: Efx NIC
- * @lb_tests: Efx loopback self-test results structure
- * @mode: Loopback test mode
- * @test_index: Starting index of the test
- * @strings: Ethtool strings, or %NULL
- * @data: Ethtool test results, or %NULL
- *
- * Fill in a block of loopback self-test entries. Return new test
- * index.
- */
-static int efx_fill_loopback_test(struct efx_nic *efx,
- struct efx_loopback_self_tests *lb_tests,
- enum efx_loopback_mode mode,
- unsigned int test_index,
- u8 *strings, u64 *data)
-{
- struct efx_channel *channel =
- efx_get_channel(efx, efx->tx_channel_offset);
- struct efx_tx_queue *tx_queue;
-
- efx_for_each_channel_tx_queue(tx_queue, channel) {
- efx_fill_test(test_index++, strings, data,
- &lb_tests->tx_sent[tx_queue->queue],
- EFX_TX_QUEUE_NAME(tx_queue),
- EFX_LOOPBACK_NAME(mode, "tx_sent"));
- efx_fill_test(test_index++, strings, data,
- &lb_tests->tx_done[tx_queue->queue],
- EFX_TX_QUEUE_NAME(tx_queue),
- EFX_LOOPBACK_NAME(mode, "tx_done"));
- }
- efx_fill_test(test_index++, strings, data,
- &lb_tests->rx_good,
- "rx", 0,
- EFX_LOOPBACK_NAME(mode, "rx_good"));
- efx_fill_test(test_index++, strings, data,
- &lb_tests->rx_bad,
- "rx", 0,
- EFX_LOOPBACK_NAME(mode, "rx_bad"));
-
- return test_index;
-}
-
-/**
- * efx_ethtool_fill_self_tests - get self-test details
- * @efx: Efx NIC
- * @tests: Efx self-test results structure, or %NULL
- * @strings: Ethtool strings, or %NULL
- * @data: Ethtool test results, or %NULL
- *
- * Get self-test number of strings, strings, and/or test results.
- * Return number of strings (== number of test results).
- *
- * The reason for merging these three functions is to make sure that
- * they can never be inconsistent.
- */
-static int efx_ethtool_fill_self_tests(struct efx_nic *efx,
- struct efx_self_tests *tests,
- u8 *strings, u64 *data)
-{
- struct efx_channel *channel;
- unsigned int n = 0, i;
- enum efx_loopback_mode mode;
-
- efx_fill_test(n++, strings, data, &tests->phy_alive,
- "phy", 0, "alive", NULL);
- efx_fill_test(n++, strings, data, &tests->nvram,
- "core", 0, "nvram", NULL);
- efx_fill_test(n++, strings, data, &tests->interrupt,
- "core", 0, "interrupt", NULL);
-
- /* Event queues */
- efx_for_each_channel(channel, efx) {
- efx_fill_test(n++, strings, data,
- &tests->eventq_dma[channel->channel],
- EFX_CHANNEL_NAME(channel),
- "eventq.dma", NULL);
- efx_fill_test(n++, strings, data,
- &tests->eventq_int[channel->channel],
- EFX_CHANNEL_NAME(channel),
- "eventq.int", NULL);
- }
-
- efx_fill_test(n++, strings, data, &tests->memory,
- "core", 0, "memory", NULL);
- efx_fill_test(n++, strings, data, &tests->registers,
- "core", 0, "registers", NULL);
-
- if (efx->phy_op->run_tests != NULL) {
- EFX_WARN_ON_PARANOID(efx->phy_op->test_name == NULL);
-
- for (i = 0; true; ++i) {
- const char *name;
-
- EFX_WARN_ON_PARANOID(i >= EFX_MAX_PHY_TESTS);
- name = efx->phy_op->test_name(efx, i);
- if (name == NULL)
- break;
-
- efx_fill_test(n++, strings, data, &tests->phy_ext[i],
- "phy", 0, name, NULL);
- }
- }
-
- /* Loopback tests */
- for (mode = LOOPBACK_NONE; mode <= LOOPBACK_TEST_MAX; mode++) {
- if (!(efx->loopback_modes & (1 << mode)))
- continue;
- n = efx_fill_loopback_test(efx,
- &tests->loopback[mode], mode, n,
- strings, data);
- }
-
- return n;
-}
-
-static size_t efx_describe_per_queue_stats(struct efx_nic *efx, u8 *strings)
-{
- size_t n_stats = 0;
- struct efx_channel *channel;
-
- efx_for_each_channel(channel, efx) {
- if (efx_channel_has_tx_queues(channel)) {
- n_stats++;
- if (strings != NULL) {
- snprintf(strings, ETH_GSTRING_LEN,
- "tx-%u.tx_packets",
- channel->tx_queue[0].queue /
- EFX_TXQ_TYPES);
-
- strings += ETH_GSTRING_LEN;
- }
- }
- }
- efx_for_each_channel(channel, efx) {
- if (efx_channel_has_rx_queue(channel)) {
- n_stats++;
- if (strings != NULL) {
- snprintf(strings, ETH_GSTRING_LEN,
- "rx-%d.rx_packets", channel->channel);
- strings += ETH_GSTRING_LEN;
- }
- }
- }
- if (efx->xdp_tx_queue_count && efx->xdp_tx_queues) {
- unsigned short xdp;
-
- for (xdp = 0; xdp < efx->xdp_tx_queue_count; xdp++) {
- n_stats++;
- if (strings) {
- snprintf(strings, ETH_GSTRING_LEN,
- "tx-xdp-cpu-%hu.tx_packets", xdp);
- strings += ETH_GSTRING_LEN;
- }
- }
- }
-
- return n_stats;
-}
-
-static int efx_ethtool_get_sset_count(struct net_device *net_dev,
- int string_set)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
-
- switch (string_set) {
- case ETH_SS_STATS:
- return efx->type->describe_stats(efx, NULL) +
- EFX_ETHTOOL_SW_STAT_COUNT +
- efx_describe_per_queue_stats(efx, NULL) +
- efx_ptp_describe_stats(efx, NULL);
- case ETH_SS_TEST:
- return efx_ethtool_fill_self_tests(efx, NULL, NULL, NULL);
- default:
- return -EINVAL;
- }
-}
-
-static void efx_ethtool_get_strings(struct net_device *net_dev,
- u32 string_set, u8 *strings)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
- int i;
-
- switch (string_set) {
- case ETH_SS_STATS:
- strings += (efx->type->describe_stats(efx, strings) *
- ETH_GSTRING_LEN);
- for (i = 0; i < EFX_ETHTOOL_SW_STAT_COUNT; i++)
- strlcpy(strings + i * ETH_GSTRING_LEN,
- efx_sw_stat_desc[i].name, ETH_GSTRING_LEN);
- strings += EFX_ETHTOOL_SW_STAT_COUNT * ETH_GSTRING_LEN;
- strings += (efx_describe_per_queue_stats(efx, strings) *
- ETH_GSTRING_LEN);
- efx_ptp_describe_stats(efx, strings);
- break;
- case ETH_SS_TEST:
- efx_ethtool_fill_self_tests(efx, NULL, strings, NULL);
- break;
- default:
- /* No other string sets */
- break;
- }
-}
-
-static void efx_ethtool_get_stats(struct net_device *net_dev,
- struct ethtool_stats *stats,
- u64 *data)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
- const struct efx_sw_stat_desc *stat;
- struct efx_channel *channel;
- struct efx_tx_queue *tx_queue;
- struct efx_rx_queue *rx_queue;
- int i;
-
- spin_lock_bh(&efx->stats_lock);
-
- /* Get NIC statistics */
- data += efx->type->update_stats(efx, data, NULL);
-
- /* Get software statistics */
- for (i = 0; i < EFX_ETHTOOL_SW_STAT_COUNT; i++) {
- stat = &efx_sw_stat_desc[i];
- switch (stat->source) {
- case EFX_ETHTOOL_STAT_SOURCE_nic:
- data[i] = stat->get_stat((void *)efx + stat->offset);
- break;
- case EFX_ETHTOOL_STAT_SOURCE_channel:
- data[i] = 0;
- efx_for_each_channel(channel, efx)
- data[i] += stat->get_stat((void *)channel +
- stat->offset);
- break;
- case EFX_ETHTOOL_STAT_SOURCE_tx_queue:
- data[i] = 0;
- efx_for_each_channel(channel, efx) {
- efx_for_each_channel_tx_queue(tx_queue, channel)
- data[i] +=
- stat->get_stat((void *)tx_queue
- + stat->offset);
- }
- break;
- }
- }
- data += EFX_ETHTOOL_SW_STAT_COUNT;
-
- spin_unlock_bh(&efx->stats_lock);
-
- efx_for_each_channel(channel, efx) {
- if (efx_channel_has_tx_queues(channel)) {
- *data = 0;
- efx_for_each_channel_tx_queue(tx_queue, channel) {
- *data += tx_queue->tx_packets;
- }
- data++;
- }
- }
- efx_for_each_channel(channel, efx) {
- if (efx_channel_has_rx_queue(channel)) {
- *data = 0;
- efx_for_each_channel_rx_queue(rx_queue, channel) {
- *data += rx_queue->rx_packets;
- }
- data++;
- }
- }
- if (efx->xdp_tx_queue_count && efx->xdp_tx_queues) {
- int xdp;
-
- for (xdp = 0; xdp < efx->xdp_tx_queue_count; xdp++) {
- data[0] = efx->xdp_tx_queues[xdp]->tx_packets;
- data++;
- }
- }
-
- efx_ptp_update_stats(efx, data);
-}
-
static void efx_ethtool_self_test(struct net_device *net_dev,
struct ethtool_test *test, u64 *data)
{
@@ -787,16 +361,6 @@ static int efx_ethtool_set_pauseparam(struct net_device *net_dev,
return rc;
}
-static void efx_ethtool_get_pauseparam(struct net_device *net_dev,
- struct ethtool_pauseparam *pause)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
-
- pause->rx_pause = !!(efx->wanted_fc & EFX_FC_RX);
- pause->tx_pause = !!(efx->wanted_fc & EFX_FC_TX);
- pause->autoneg = !!(efx->wanted_fc & EFX_FC_AUTO);
-}
-
static void efx_ethtool_get_wol(struct net_device *net_dev,
struct ethtool_wolinfo *wol)
{
@@ -1456,7 +1020,7 @@ static int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
rc = -ENOMEM;
goto out_unlock;
}
- ctx->context_id = EFX_EF10_RSS_CONTEXT_INVALID;
+ ctx->context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
/* Initialise indir table and key to defaults */
efx_set_default_rx_indir_table(efx, ctx);
netdev_rss_key_fill(ctx->rx_hash_key, sizeof(ctx->rx_hash_key));
diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c
new file mode 100644
index 0000000..b8d281a
--- /dev/null
+++ b/drivers/net/ethernet/sfc/ethtool_common.c
@@ -0,0 +1,457 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2019 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include "net_driver.h"
+#include "mcdi.h"
+#include "nic.h"
+#include "selftest.h"
+#include "ethtool_common.h"
+
+struct efx_sw_stat_desc {
+ const char *name;
+ enum {
+ EFX_ETHTOOL_STAT_SOURCE_nic,
+ EFX_ETHTOOL_STAT_SOURCE_channel,
+ EFX_ETHTOOL_STAT_SOURCE_tx_queue
+ } source;
+ unsigned int offset;
+ u64 (*get_stat)(void *field); /* Reader function */
+};
+
+/* Initialiser for a struct efx_sw_stat_desc with type-checking */
+#define EFX_ETHTOOL_STAT(stat_name, source_name, field, field_type, \
+ get_stat_function) { \
+ .name = #stat_name, \
+ .source = EFX_ETHTOOL_STAT_SOURCE_##source_name, \
+ .offset = ((((field_type *) 0) == \
+ &((struct efx_##source_name *)0)->field) ? \
+ offsetof(struct efx_##source_name, field) : \
+ offsetof(struct efx_##source_name, field)), \
+ .get_stat = get_stat_function, \
+}
+
+static u64 efx_get_uint_stat(void *field)
+{
+ return *(unsigned int *)field;
+}
+
+static u64 efx_get_atomic_stat(void *field)
+{
+ return atomic_read((atomic_t *) field);
+}
+
+#define EFX_ETHTOOL_ATOMIC_NIC_ERROR_STAT(field) \
+ EFX_ETHTOOL_STAT(field, nic, field, \
+ atomic_t, efx_get_atomic_stat)
+
+#define EFX_ETHTOOL_UINT_CHANNEL_STAT(field) \
+ EFX_ETHTOOL_STAT(field, channel, n_##field, \
+ unsigned int, efx_get_uint_stat)
+#define EFX_ETHTOOL_UINT_CHANNEL_STAT_NO_N(field) \
+ EFX_ETHTOOL_STAT(field, channel, field, \
+ unsigned int, efx_get_uint_stat)
+
+#define EFX_ETHTOOL_UINT_TXQ_STAT(field) \
+ EFX_ETHTOOL_STAT(tx_##field, tx_queue, field, \
+ unsigned int, efx_get_uint_stat)
+
+static const struct efx_sw_stat_desc efx_sw_stat_desc[] = {
+ EFX_ETHTOOL_UINT_TXQ_STAT(merge_events),
+ EFX_ETHTOOL_UINT_TXQ_STAT(tso_bursts),
+ EFX_ETHTOOL_UINT_TXQ_STAT(tso_long_headers),
+ EFX_ETHTOOL_UINT_TXQ_STAT(tso_packets),
+ EFX_ETHTOOL_UINT_TXQ_STAT(tso_fallbacks),
+ EFX_ETHTOOL_UINT_TXQ_STAT(pushes),
+ EFX_ETHTOOL_UINT_TXQ_STAT(pio_packets),
+ EFX_ETHTOOL_UINT_TXQ_STAT(cb_packets),
+ EFX_ETHTOOL_ATOMIC_NIC_ERROR_STAT(rx_reset),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tobe_disc),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_ip_hdr_chksum_err),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tcp_udp_chksum_err),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_inner_ip_hdr_chksum_err),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_inner_tcp_udp_chksum_err),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_outer_ip_hdr_chksum_err),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_outer_tcp_udp_chksum_err),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_eth_crc_err),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_mcast_mismatch),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_frm_trunc),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_merge_events),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_merge_packets),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_xdp_drops),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_xdp_bad_drops),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_xdp_tx),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_xdp_redirect),
+#ifdef CONFIG_RFS_ACCEL
+ EFX_ETHTOOL_UINT_CHANNEL_STAT_NO_N(rfs_filter_count),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rfs_succeeded),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rfs_failed),
+#endif
+};
+
+#define EFX_ETHTOOL_SW_STAT_COUNT ARRAY_SIZE(efx_sw_stat_desc)
+
+void efx_ethtool_get_drvinfo(struct net_device *net_dev,
+ struct ethtool_drvinfo *info)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+
+ strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+ strlcpy(info->version, EFX_DRIVER_VERSION, sizeof(info->version));
+ efx_mcdi_print_fwver(efx, info->fw_version,
+ sizeof(info->fw_version));
+ strlcpy(info->bus_info, pci_name(efx->pci_dev), sizeof(info->bus_info));
+}
+
+u32 efx_ethtool_get_msglevel(struct net_device *net_dev)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+
+ return efx->msg_enable;
+}
+
+void efx_ethtool_set_msglevel(struct net_device *net_dev, u32 msg_enable)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+
+ efx->msg_enable = msg_enable;
+}
+
+void efx_ethtool_get_pauseparam(struct net_device *net_dev,
+ struct ethtool_pauseparam *pause)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+
+ pause->rx_pause = !!(efx->wanted_fc & EFX_FC_RX);
+ pause->tx_pause = !!(efx->wanted_fc & EFX_FC_TX);
+ pause->autoneg = !!(efx->wanted_fc & EFX_FC_AUTO);
+}
+
+/**
+ * efx_fill_test - fill in an individual self-test entry
+ * @test_index: Index of the test
+ * @strings: Ethtool strings, or %NULL
+ * @data: Ethtool test results, or %NULL
+ * @test: Pointer to test result (used only if data != %NULL)
+ * @unit_format: Unit name format (e.g. "chan\%d")
+ * @unit_id: Unit id (e.g. 0 for "chan0")
+ * @test_format: Test name format (e.g. "loopback.\%s.tx.sent")
+ * @test_id: Test id (e.g. "PHYXS" for "loopback.PHYXS.tx_sent")
+ *
+ * Fill in an individual self-test entry.
+ */
+static void efx_fill_test(unsigned int test_index, u8 *strings, u64 *data,
+ int *test, const char *unit_format, int unit_id,
+ const char *test_format, const char *test_id)
+{
+ char unit_str[ETH_GSTRING_LEN], test_str[ETH_GSTRING_LEN];
+
+ /* Fill data value, if applicable */
+ if (data)
+ data[test_index] = *test;
+
+ /* Fill string, if applicable */
+ if (strings) {
+ if (strchr(unit_format, '%'))
+ snprintf(unit_str, sizeof(unit_str),
+ unit_format, unit_id);
+ else
+ strcpy(unit_str, unit_format);
+ snprintf(test_str, sizeof(test_str), test_format, test_id);
+ snprintf(strings + test_index * ETH_GSTRING_LEN,
+ ETH_GSTRING_LEN,
+ "%-6s %-24s", unit_str, test_str);
+ }
+}
+
+#define EFX_CHANNEL_NAME(_channel) "chan%d", _channel->channel
+#define EFX_TX_QUEUE_NAME(_tx_queue) "txq%d", _tx_queue->queue
+#define EFX_RX_QUEUE_NAME(_rx_queue) "rxq%d", _rx_queue->queue
+#define EFX_LOOPBACK_NAME(_mode, _counter) \
+ "loopback.%s." _counter, STRING_TABLE_LOOKUP(_mode, efx_loopback_mode)
+
+/**
+ * efx_fill_loopback_test - fill in a block of loopback self-test entries
+ * @efx: Efx NIC
+ * @lb_tests: Efx loopback self-test results structure
+ * @mode: Loopback test mode
+ * @test_index: Starting index of the test
+ * @strings: Ethtool strings, or %NULL
+ * @data: Ethtool test results, or %NULL
+ *
+ * Fill in a block of loopback self-test entries. Return new test
+ * index.
+ */
+static int efx_fill_loopback_test(struct efx_nic *efx,
+ struct efx_loopback_self_tests *lb_tests,
+ enum efx_loopback_mode mode,
+ unsigned int test_index,
+ u8 *strings, u64 *data)
+{
+ struct efx_channel *channel =
+ efx_get_channel(efx, efx->tx_channel_offset);
+ struct efx_tx_queue *tx_queue;
+
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ efx_fill_test(test_index++, strings, data,
+ &lb_tests->tx_sent[tx_queue->queue],
+ EFX_TX_QUEUE_NAME(tx_queue),
+ EFX_LOOPBACK_NAME(mode, "tx_sent"));
+ efx_fill_test(test_index++, strings, data,
+ &lb_tests->tx_done[tx_queue->queue],
+ EFX_TX_QUEUE_NAME(tx_queue),
+ EFX_LOOPBACK_NAME(mode, "tx_done"));
+ }
+ efx_fill_test(test_index++, strings, data,
+ &lb_tests->rx_good,
+ "rx", 0,
+ EFX_LOOPBACK_NAME(mode, "rx_good"));
+ efx_fill_test(test_index++, strings, data,
+ &lb_tests->rx_bad,
+ "rx", 0,
+ EFX_LOOPBACK_NAME(mode, "rx_bad"));
+
+ return test_index;
+}
+
+/**
+ * efx_ethtool_fill_self_tests - get self-test details
+ * @efx: Efx NIC
+ * @tests: Efx self-test results structure, or %NULL
+ * @strings: Ethtool strings, or %NULL
+ * @data: Ethtool test results, or %NULL
+ *
+ * Get self-test number of strings, strings, and/or test results.
+ * Return number of strings (== number of test results).
+ *
+ * The reason for merging these three functions is to make sure that
+ * they can never be inconsistent.
+ */
+int efx_ethtool_fill_self_tests(struct efx_nic *efx,
+ struct efx_self_tests *tests,
+ u8 *strings, u64 *data)
+{
+ struct efx_channel *channel;
+ unsigned int n = 0, i;
+ enum efx_loopback_mode mode;
+
+ efx_fill_test(n++, strings, data, &tests->phy_alive,
+ "phy", 0, "alive", NULL);
+ efx_fill_test(n++, strings, data, &tests->nvram,
+ "core", 0, "nvram", NULL);
+ efx_fill_test(n++, strings, data, &tests->interrupt,
+ "core", 0, "interrupt", NULL);
+
+ /* Event queues */
+ efx_for_each_channel(channel, efx) {
+ efx_fill_test(n++, strings, data,
+ &tests->eventq_dma[channel->channel],
+ EFX_CHANNEL_NAME(channel),
+ "eventq.dma", NULL);
+ efx_fill_test(n++, strings, data,
+ &tests->eventq_int[channel->channel],
+ EFX_CHANNEL_NAME(channel),
+ "eventq.int", NULL);
+ }
+
+ efx_fill_test(n++, strings, data, &tests->memory,
+ "core", 0, "memory", NULL);
+ efx_fill_test(n++, strings, data, &tests->registers,
+ "core", 0, "registers", NULL);
+
+ if (efx->phy_op->run_tests != NULL) {
+ EFX_WARN_ON_PARANOID(efx->phy_op->test_name == NULL);
+
+ for (i = 0; true; ++i) {
+ const char *name;
+
+ EFX_WARN_ON_PARANOID(i >= EFX_MAX_PHY_TESTS);
+ name = efx->phy_op->test_name(efx, i);
+ if (name == NULL)
+ break;
+
+ efx_fill_test(n++, strings, data, &tests->phy_ext[i],
+ "phy", 0, name, NULL);
+ }
+ }
+
+ /* Loopback tests */
+ for (mode = LOOPBACK_NONE; mode <= LOOPBACK_TEST_MAX; mode++) {
+ if (!(efx->loopback_modes & (1 << mode)))
+ continue;
+ n = efx_fill_loopback_test(efx,
+ &tests->loopback[mode], mode, n,
+ strings, data);
+ }
+
+ return n;
+}
+
+static size_t efx_describe_per_queue_stats(struct efx_nic *efx, u8 *strings)
+{
+ size_t n_stats = 0;
+ struct efx_channel *channel;
+
+ efx_for_each_channel(channel, efx) {
+ if (efx_channel_has_tx_queues(channel)) {
+ n_stats++;
+ if (strings != NULL) {
+ snprintf(strings, ETH_GSTRING_LEN,
+ "tx-%u.tx_packets",
+ channel->tx_queue[0].queue /
+ EFX_TXQ_TYPES);
+
+ strings += ETH_GSTRING_LEN;
+ }
+ }
+ }
+ efx_for_each_channel(channel, efx) {
+ if (efx_channel_has_rx_queue(channel)) {
+ n_stats++;
+ if (strings != NULL) {
+ snprintf(strings, ETH_GSTRING_LEN,
+ "rx-%d.rx_packets", channel->channel);
+ strings += ETH_GSTRING_LEN;
+ }
+ }
+ }
+ if (efx->xdp_tx_queue_count && efx->xdp_tx_queues) {
+ unsigned short xdp;
+
+ for (xdp = 0; xdp < efx->xdp_tx_queue_count; xdp++) {
+ n_stats++;
+ if (strings) {
+ snprintf(strings, ETH_GSTRING_LEN,
+ "tx-xdp-cpu-%hu.tx_packets", xdp);
+ strings += ETH_GSTRING_LEN;
+ }
+ }
+ }
+
+ return n_stats;
+}
+
+int efx_ethtool_get_sset_count(struct net_device *net_dev, int string_set)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+
+ switch (string_set) {
+ case ETH_SS_STATS:
+ return efx->type->describe_stats(efx, NULL) +
+ EFX_ETHTOOL_SW_STAT_COUNT +
+ efx_describe_per_queue_stats(efx, NULL) +
+ efx_ptp_describe_stats(efx, NULL);
+ case ETH_SS_TEST:
+ return efx_ethtool_fill_self_tests(efx, NULL, NULL, NULL);
+ default:
+ return -EINVAL;
+ }
+}
+
+void efx_ethtool_get_strings(struct net_device *net_dev,
+ u32 string_set, u8 *strings)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+ int i;
+
+ switch (string_set) {
+ case ETH_SS_STATS:
+ strings += (efx->type->describe_stats(efx, strings) *
+ ETH_GSTRING_LEN);
+ for (i = 0; i < EFX_ETHTOOL_SW_STAT_COUNT; i++)
+ strlcpy(strings + i * ETH_GSTRING_LEN,
+ efx_sw_stat_desc[i].name, ETH_GSTRING_LEN);
+ strings += EFX_ETHTOOL_SW_STAT_COUNT * ETH_GSTRING_LEN;
+ strings += (efx_describe_per_queue_stats(efx, strings) *
+ ETH_GSTRING_LEN);
+ efx_ptp_describe_stats(efx, strings);
+ break;
+ case ETH_SS_TEST:
+ efx_ethtool_fill_self_tests(efx, NULL, strings, NULL);
+ break;
+ default:
+ /* No other string sets */
+ break;
+ }
+}
+
+void efx_ethtool_get_stats(struct net_device *net_dev,
+ struct ethtool_stats *stats,
+ u64 *data)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+ const struct efx_sw_stat_desc *stat;
+ struct efx_channel *channel;
+ struct efx_tx_queue *tx_queue;
+ struct efx_rx_queue *rx_queue;
+ int i;
+
+ spin_lock_bh(&efx->stats_lock);
+
+ /* Get NIC statistics */
+ data += efx->type->update_stats(efx, data, NULL);
+
+ /* Get software statistics */
+ for (i = 0; i < EFX_ETHTOOL_SW_STAT_COUNT; i++) {
+ stat = &efx_sw_stat_desc[i];
+ switch (stat->source) {
+ case EFX_ETHTOOL_STAT_SOURCE_nic:
+ data[i] = stat->get_stat((void *)efx + stat->offset);
+ break;
+ case EFX_ETHTOOL_STAT_SOURCE_channel:
+ data[i] = 0;
+ efx_for_each_channel(channel, efx)
+ data[i] += stat->get_stat((void *)channel +
+ stat->offset);
+ break;
+ case EFX_ETHTOOL_STAT_SOURCE_tx_queue:
+ data[i] = 0;
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_tx_queue(tx_queue, channel)
+ data[i] +=
+ stat->get_stat((void *)tx_queue
+ + stat->offset);
+ }
+ break;
+ }
+ }
+ data += EFX_ETHTOOL_SW_STAT_COUNT;
+
+ spin_unlock_bh(&efx->stats_lock);
+
+ efx_for_each_channel(channel, efx) {
+ if (efx_channel_has_tx_queues(channel)) {
+ *data = 0;
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ *data += tx_queue->tx_packets;
+ }
+ data++;
+ }
+ }
+ efx_for_each_channel(channel, efx) {
+ if (efx_channel_has_rx_queue(channel)) {
+ *data = 0;
+ efx_for_each_channel_rx_queue(rx_queue, channel) {
+ *data += rx_queue->rx_packets;
+ }
+ data++;
+ }
+ }
+ if (efx->xdp_tx_queue_count && efx->xdp_tx_queues) {
+ int xdp;
+
+ for (xdp = 0; xdp < efx->xdp_tx_queue_count; xdp++) {
+ data[0] = efx->xdp_tx_queues[xdp]->tx_packets;
+ data++;
+ }
+ }
+
+ efx_ptp_update_stats(efx, data);
+}
diff --git a/drivers/net/ethernet/sfc/ethtool_common.h b/drivers/net/ethernet/sfc/ethtool_common.h
new file mode 100644
index 0000000..fa62431
--- /dev/null
+++ b/drivers/net/ethernet/sfc/ethtool_common.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2019 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EFX_ETHTOOL_COMMON_H
+#define EFX_ETHTOOL_COMMON_H
+
+void efx_ethtool_get_drvinfo(struct net_device *net_dev,
+ struct ethtool_drvinfo *info);
+u32 efx_ethtool_get_msglevel(struct net_device *net_dev);
+void efx_ethtool_set_msglevel(struct net_device *net_dev, u32 msg_enable);
+void efx_ethtool_get_pauseparam(struct net_device *net_dev,
+ struct ethtool_pauseparam *pause);
+int efx_ethtool_fill_self_tests(struct efx_nic *efx,
+ struct efx_self_tests *tests,
+ u8 *strings, u64 *data);
+int efx_ethtool_get_sset_count(struct net_device *net_dev, int string_set);
+void efx_ethtool_get_strings(struct net_device *net_dev, u32 string_set,
+ u8 *strings);
+void efx_ethtool_get_stats(struct net_device *net_dev,
+ struct ethtool_stats *stats __attribute__ ((unused)),
+ u64 *data);
+
+#endif
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index eedd32e..dbbb898 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -15,6 +15,7 @@
#include "net_driver.h"
#include "bitfield.h"
#include "efx.h"
+#include "rx_common.h"
#include "nic.h"
#include "farch_regs.h"
#include "sriov.h"
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index 9081f84..54a4501 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -346,11 +346,8 @@ int efx_mcdi_flush_rxqs(struct efx_nic *efx);
int efx_mcdi_port_probe(struct efx_nic *efx);
void efx_mcdi_port_remove(struct efx_nic *efx);
int efx_mcdi_port_reconfigure(struct efx_nic *efx);
-int efx_mcdi_port_get_number(struct efx_nic *efx);
u32 efx_mcdi_phy_get_caps(struct efx_nic *efx);
void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev);
-int efx_mcdi_set_mac(struct efx_nic *efx);
-#define EFX_MC_STATS_GENERATION_INVALID ((__force __le64)(-1))
void efx_mcdi_mac_start_stats(struct efx_nic *efx);
void efx_mcdi_mac_stop_stats(struct efx_nic *efx);
void efx_mcdi_mac_pull_stats(struct efx_nic *efx);
diff --git a/drivers/net/ethernet/sfc/mcdi_functions.c b/drivers/net/ethernet/sfc/mcdi_functions.c
new file mode 100644
index 0000000..dcfe78b
--- /dev/null
+++ b/drivers/net/ethernet/sfc/mcdi_functions.c
@@ -0,0 +1,386 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2019 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include "net_driver.h"
+#include "efx.h"
+#include "nic.h"
+#include "mcdi_functions.h"
+#include "mcdi.h"
+#include "mcdi_pcol.h"
+
+int efx_mcdi_free_vis(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF_ERR(outbuf);
+ size_t outlen;
+ int rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FREE_VIS, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+
+ /* -EALREADY means nothing to free, so ignore */
+ if (rc == -EALREADY)
+ rc = 0;
+ if (rc)
+ efx_mcdi_display_error(efx, MC_CMD_FREE_VIS, 0, outbuf, outlen,
+ rc);
+ return rc;
+}
+
+int efx_mcdi_alloc_vis(struct efx_nic *efx, unsigned int min_vis,
+ unsigned int max_vis, unsigned int *vi_base,
+ unsigned int *allocated_vis)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_ALLOC_VIS_OUT_LEN);
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_ALLOC_VIS_IN_LEN);
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, ALLOC_VIS_IN_MIN_VI_COUNT, min_vis);
+ MCDI_SET_DWORD(inbuf, ALLOC_VIS_IN_MAX_VI_COUNT, max_vis);
+ rc = efx_mcdi_rpc(efx, MC_CMD_ALLOC_VIS, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc != 0)
+ return rc;
+
+ if (outlen < MC_CMD_ALLOC_VIS_OUT_LEN)
+ return -EIO;
+
+ netif_dbg(efx, drv, efx->net_dev, "base VI is A0x%03x\n",
+ MCDI_DWORD(outbuf, ALLOC_VIS_OUT_VI_BASE));
+
+ if (vi_base)
+ *vi_base = MCDI_DWORD(outbuf, ALLOC_VIS_OUT_VI_BASE);
+ if (allocated_vis)
+ *allocated_vis = MCDI_DWORD(outbuf, ALLOC_VIS_OUT_VI_COUNT);
+ return 0;
+}
+
+int efx_mcdi_ev_probe(struct efx_channel *channel)
+{
+ return efx_nic_alloc_buffer(channel->efx, &channel->eventq.buf,
+ (channel->eventq_mask + 1) *
+ sizeof(efx_qword_t),
+ GFP_KERNEL);
+}
+
+int efx_mcdi_ev_init(struct efx_channel *channel, bool v1_cut_thru, bool v2)
+{
+ MCDI_DECLARE_BUF(inbuf,
+ MC_CMD_INIT_EVQ_V2_IN_LEN(EFX_MAX_EVQ_SIZE * 8 /
+ EFX_BUF_SIZE));
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_INIT_EVQ_V2_OUT_LEN);
+ size_t entries = channel->eventq.buf.len / EFX_BUF_SIZE;
+ struct efx_nic *efx = channel->efx;
+ size_t inlen, outlen;
+ dma_addr_t dma_addr;
+ int rc, i;
+
+ /* Fill event queue with all ones (i.e. empty events) */
+ memset(channel->eventq.buf.addr, 0xff, channel->eventq.buf.len);
+
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_SIZE, channel->eventq_mask + 1);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_INSTANCE, channel->channel);
+ /* INIT_EVQ expects index in vector table, not absolute */
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_IRQ_NUM, channel->channel);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_MODE,
+ MC_CMD_INIT_EVQ_IN_TMR_MODE_DIS);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_LOAD, 0);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_RELOAD, 0);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_COUNT_MODE,
+ MC_CMD_INIT_EVQ_IN_COUNT_MODE_DIS);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_COUNT_THRSHLD, 0);
+
+ if (v2) {
+ /* Use the new generic approach to specifying event queue
+ * configuration, requesting lower latency or higher throughput.
+ * The options that actually get used appear in the output.
+ */
+ MCDI_POPULATE_DWORD_2(inbuf, INIT_EVQ_V2_IN_FLAGS,
+ INIT_EVQ_V2_IN_FLAG_INTERRUPTING, 1,
+ INIT_EVQ_V2_IN_FLAG_TYPE,
+ MC_CMD_INIT_EVQ_V2_IN_FLAG_TYPE_AUTO);
+ } else {
+ MCDI_POPULATE_DWORD_4(inbuf, INIT_EVQ_IN_FLAGS,
+ INIT_EVQ_IN_FLAG_INTERRUPTING, 1,
+ INIT_EVQ_IN_FLAG_RX_MERGE, 1,
+ INIT_EVQ_IN_FLAG_TX_MERGE, 1,
+ INIT_EVQ_IN_FLAG_CUT_THRU, v1_cut_thru);
+ }
+
+ dma_addr = channel->eventq.buf.dma_addr;
+ for (i = 0; i < entries; ++i) {
+ MCDI_SET_ARRAY_QWORD(inbuf, INIT_EVQ_IN_DMA_ADDR, i, dma_addr);
+ dma_addr += EFX_BUF_SIZE;
+ }
+
+ inlen = MC_CMD_INIT_EVQ_IN_LEN(entries);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_INIT_EVQ, inbuf, inlen,
+ outbuf, sizeof(outbuf), &outlen);
+
+ if (outlen >= MC_CMD_INIT_EVQ_V2_OUT_LEN)
+ netif_dbg(efx, drv, efx->net_dev,
+ "Channel %d using event queue flags %08x\n",
+ channel->channel,
+ MCDI_DWORD(outbuf, INIT_EVQ_V2_OUT_FLAGS));
+
+ return rc;
+}
+
+void efx_mcdi_ev_remove(struct efx_channel *channel)
+{
+ efx_nic_free_buffer(channel->efx, &channel->eventq.buf);
+}
+
+void efx_mcdi_ev_fini(struct efx_channel *channel)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_EVQ_IN_LEN);
+ MCDI_DECLARE_BUF_ERR(outbuf);
+ struct efx_nic *efx = channel->efx;
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, FINI_EVQ_IN_INSTANCE, channel->channel);
+
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_EVQ, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+
+ if (rc && rc != -EALREADY)
+ goto fail;
+
+ return;
+
+fail:
+ efx_mcdi_display_error(efx, MC_CMD_FINI_EVQ, MC_CMD_FINI_EVQ_IN_LEN,
+ outbuf, outlen, rc);
+}
+
+int efx_mcdi_tx_init(struct efx_tx_queue *tx_queue, bool tso_v2)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_INIT_TXQ_IN_LEN(EFX_MAX_DMAQ_SIZE * 8 /
+ EFX_BUF_SIZE));
+ bool csum_offload = tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD;
+ size_t entries = tx_queue->txd.buf.len / EFX_BUF_SIZE;
+ struct efx_channel *channel = tx_queue->channel;
+ struct efx_nic *efx = tx_queue->efx;
+ struct efx_ef10_nic_data *nic_data;
+ dma_addr_t dma_addr;
+ size_t inlen;
+ int rc, i;
+
+ BUILD_BUG_ON(MC_CMD_INIT_TXQ_OUT_LEN != 0);
+
+ nic_data = efx->nic_data;
+
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_SIZE, tx_queue->ptr_mask + 1);
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_TARGET_EVQ, channel->channel);
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_LABEL, tx_queue->queue);
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_INSTANCE, tx_queue->queue);
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_OWNER_ID, 0);
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_PORT_ID, nic_data->vport_id);
+
+ dma_addr = tx_queue->txd.buf.dma_addr;
+
+ netif_dbg(efx, hw, efx->net_dev, "pushing TXQ %d. %zu entries (%llx)\n",
+ tx_queue->queue, entries, (u64)dma_addr);
+
+ for (i = 0; i < entries; ++i) {
+ MCDI_SET_ARRAY_QWORD(inbuf, INIT_TXQ_IN_DMA_ADDR, i, dma_addr);
+ dma_addr += EFX_BUF_SIZE;
+ }
+
+ inlen = MC_CMD_INIT_TXQ_IN_LEN(entries);
+
+ do {
+ MCDI_POPULATE_DWORD_4(inbuf, INIT_TXQ_IN_FLAGS,
+ /* This flag was removed from mcdi_pcol.h for
+ * the non-_EXT version of INIT_TXQ. However,
+ * firmware still honours it.
+ */
+ INIT_TXQ_EXT_IN_FLAG_TSOV2_EN, tso_v2,
+ INIT_TXQ_IN_FLAG_IP_CSUM_DIS, !csum_offload,
+ INIT_TXQ_IN_FLAG_TCP_CSUM_DIS, !csum_offload,
+ INIT_TXQ_EXT_IN_FLAG_TIMESTAMP,
+ tx_queue->timestamping);
+
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_INIT_TXQ, inbuf, inlen,
+ NULL, 0, NULL);
+ if (rc == -ENOSPC && tso_v2) {
+ /* Retry without TSOv2 if we're short on contexts. */
+ tso_v2 = false;
+ netif_warn(efx, probe, efx->net_dev,
+ "TSOv2 context not available to segment in "
+ "hardware. TCP performance may be reduced.\n"
+ );
+ } else if (rc) {
+ efx_mcdi_display_error(efx, MC_CMD_INIT_TXQ,
+ MC_CMD_INIT_TXQ_EXT_IN_LEN,
+ NULL, 0, rc);
+ goto fail;
+ }
+ } while (rc);
+
+ return 0;
+
+fail:
+ return rc;
+}
+
+void efx_mcdi_tx_remove(struct efx_tx_queue *tx_queue)
+{
+ efx_nic_free_buffer(tx_queue->efx, &tx_queue->txd.buf);
+}
+
+void efx_mcdi_tx_fini(struct efx_tx_queue *tx_queue)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_TXQ_IN_LEN);
+ MCDI_DECLARE_BUF_ERR(outbuf);
+ struct efx_nic *efx = tx_queue->efx;
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, FINI_TXQ_IN_INSTANCE,
+ tx_queue->queue);
+
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_TXQ, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+
+ if (rc && rc != -EALREADY)
+ goto fail;
+
+ return;
+
+fail:
+ efx_mcdi_display_error(efx, MC_CMD_FINI_TXQ, MC_CMD_FINI_TXQ_IN_LEN,
+ outbuf, outlen, rc);
+}
+
+int efx_mcdi_rx_probe(struct efx_rx_queue *rx_queue)
+{
+ return efx_nic_alloc_buffer(rx_queue->efx, &rx_queue->rxd.buf,
+ (rx_queue->ptr_mask + 1) *
+ sizeof(efx_qword_t),
+ GFP_KERNEL);
+}
+
+void efx_mcdi_rx_init(struct efx_rx_queue *rx_queue)
+{
+ MCDI_DECLARE_BUF(inbuf,
+ MC_CMD_INIT_RXQ_IN_LEN(EFX_MAX_DMAQ_SIZE * 8 /
+ EFX_BUF_SIZE));
+ struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
+ size_t entries = rx_queue->rxd.buf.len / EFX_BUF_SIZE;
+ struct efx_nic *efx = rx_queue->efx;
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ dma_addr_t dma_addr;
+ size_t inlen;
+ int rc;
+ int i;
+ BUILD_BUG_ON(MC_CMD_INIT_RXQ_OUT_LEN != 0);
+
+ rx_queue->scatter_n = 0;
+ rx_queue->scatter_len = 0;
+
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_SIZE, rx_queue->ptr_mask + 1);
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_TARGET_EVQ, channel->channel);
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_LABEL, efx_rx_queue_index(rx_queue));
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_INSTANCE,
+ efx_rx_queue_index(rx_queue));
+ MCDI_POPULATE_DWORD_2(inbuf, INIT_RXQ_IN_FLAGS,
+ INIT_RXQ_IN_FLAG_PREFIX, 1,
+ INIT_RXQ_IN_FLAG_TIMESTAMP, 1);
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_OWNER_ID, 0);
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_PORT_ID, nic_data->vport_id);
+
+ dma_addr = rx_queue->rxd.buf.dma_addr;
+
+ netif_dbg(efx, hw, efx->net_dev, "pushing RXQ %d. %zu entries (%llx)\n",
+ efx_rx_queue_index(rx_queue), entries, (u64)dma_addr);
+
+ for (i = 0; i < entries; ++i) {
+ MCDI_SET_ARRAY_QWORD(inbuf, INIT_RXQ_IN_DMA_ADDR, i, dma_addr);
+ dma_addr += EFX_BUF_SIZE;
+ }
+
+ inlen = MC_CMD_INIT_RXQ_IN_LEN(entries);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_INIT_RXQ, inbuf, inlen,
+ NULL, 0, NULL);
+ if (rc)
+ netdev_WARN(efx->net_dev, "failed to initialise RXQ %d\n",
+ efx_rx_queue_index(rx_queue));
+}
+
+void efx_mcdi_rx_remove(struct efx_rx_queue *rx_queue)
+{
+ efx_nic_free_buffer(rx_queue->efx, &rx_queue->rxd.buf);
+}
+
+void efx_mcdi_rx_fini(struct efx_rx_queue *rx_queue)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_RXQ_IN_LEN);
+ MCDI_DECLARE_BUF_ERR(outbuf);
+ struct efx_nic *efx = rx_queue->efx;
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, FINI_RXQ_IN_INSTANCE,
+ efx_rx_queue_index(rx_queue));
+
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_RXQ, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+
+ if (rc && rc != -EALREADY)
+ goto fail;
+
+ return;
+
+fail:
+ efx_mcdi_display_error(efx, MC_CMD_FINI_RXQ, MC_CMD_FINI_RXQ_IN_LEN,
+ outbuf, outlen, rc);
+}
+
+int efx_mcdi_window_mode_to_stride(struct efx_nic *efx, u8 vi_window_mode)
+{
+ switch (vi_window_mode) {
+ case MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_8K:
+ efx->vi_stride = 8192;
+ break;
+ case MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_16K:
+ efx->vi_stride = 16384;
+ break;
+ case MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_64K:
+ efx->vi_stride = 65536;
+ break;
+ default:
+ netif_err(efx, probe, efx->net_dev,
+ "Unrecognised VI window mode %d\n",
+ vi_window_mode);
+ return -EIO;
+ }
+ netif_dbg(efx, probe, efx->net_dev, "vi_stride = %u\n",
+ efx->vi_stride);
+ return 0;
+}
+
+int efx_get_pf_index(struct efx_nic *efx, unsigned int *pf_index)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_FUNCTION_INFO_OUT_LEN);
+ size_t outlen;
+ int rc;
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_FUNCTION_INFO, NULL, 0, outbuf,
+ sizeof(outbuf), &outlen);
+ if (rc)
+ return rc;
+ if (outlen < sizeof(outbuf))
+ return -EIO;
+
+ *pf_index = MCDI_DWORD(outbuf, GET_FUNCTION_INFO_OUT_PF);
+ return 0;
+}
diff --git a/drivers/net/ethernet/sfc/mcdi_functions.h b/drivers/net/ethernet/sfc/mcdi_functions.h
new file mode 100644
index 0000000..ca4a5ac
--- /dev/null
+++ b/drivers/net/ethernet/sfc/mcdi_functions.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+#ifndef EFX_MCDI_FUNCTIONS_H
+#define EFX_MCDI_FUNCTIONS_H
+
+int efx_mcdi_alloc_vis(struct efx_nic *efx, unsigned int min_vis,
+ unsigned int max_vis, unsigned int *vi_base,
+ unsigned int *allocated_vis);
+int efx_mcdi_free_vis(struct efx_nic *efx);
+
+int efx_mcdi_ev_probe(struct efx_channel *channel);
+int efx_mcdi_ev_init(struct efx_channel *channel, bool v1_cut_thru, bool v2);
+void efx_mcdi_ev_remove(struct efx_channel *channel);
+void efx_mcdi_ev_fini(struct efx_channel *channel);
+int efx_mcdi_tx_init(struct efx_tx_queue *tx_queue, bool tso_v2);
+void efx_mcdi_tx_remove(struct efx_tx_queue *tx_queue);
+void efx_mcdi_tx_fini(struct efx_tx_queue *tx_queue);
+int efx_mcdi_rx_probe(struct efx_rx_queue *rx_queue);
+void efx_mcdi_rx_init(struct efx_rx_queue *rx_queue);
+void efx_mcdi_rx_remove(struct efx_rx_queue *rx_queue);
+void efx_mcdi_rx_fini(struct efx_rx_queue *rx_queue);
+int efx_mcdi_window_mode_to_stride(struct efx_nic *efx, u8 vi_window_mode);
+int efx_get_pf_index(struct efx_nic *efx, unsigned int *pf_index);
+
+#endif
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index fb7cde4..ab5227b 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -14,106 +14,7 @@
#include "mcdi_pcol.h"
#include "nic.h"
#include "selftest.h"
-
-struct efx_mcdi_phy_data {
- u32 flags;
- u32 type;
- u32 supported_cap;
- u32 channel;
- u32 port;
- u32 stats_mask;
- u8 name[20];
- u32 media;
- u32 mmd_mask;
- u8 revision[20];
- u32 forced_cap;
-};
-
-static int
-efx_mcdi_get_phy_cfg(struct efx_nic *efx, struct efx_mcdi_phy_data *cfg)
-{
- MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_CFG_OUT_LEN);
- size_t outlen;
- int rc;
-
- BUILD_BUG_ON(MC_CMD_GET_PHY_CFG_IN_LEN != 0);
- BUILD_BUG_ON(MC_CMD_GET_PHY_CFG_OUT_NAME_LEN != sizeof(cfg->name));
-
- rc = efx_mcdi_rpc(efx, MC_CMD_GET_PHY_CFG, NULL, 0,
- outbuf, sizeof(outbuf), &outlen);
- if (rc)
- goto fail;
-
- if (outlen < MC_CMD_GET_PHY_CFG_OUT_LEN) {
- rc = -EIO;
- goto fail;
- }
-
- cfg->flags = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_FLAGS);
- cfg->type = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_TYPE);
- cfg->supported_cap =
- MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_SUPPORTED_CAP);
- cfg->channel = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_CHANNEL);
- cfg->port = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_PRT);
- cfg->stats_mask = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_STATS_MASK);
- memcpy(cfg->name, MCDI_PTR(outbuf, GET_PHY_CFG_OUT_NAME),
- sizeof(cfg->name));
- cfg->media = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_MEDIA_TYPE);
- cfg->mmd_mask = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_MMD_MASK);
- memcpy(cfg->revision, MCDI_PTR(outbuf, GET_PHY_CFG_OUT_REVISION),
- sizeof(cfg->revision));
-
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
- return rc;
-}
-
-static int efx_mcdi_set_link(struct efx_nic *efx, u32 capabilities,
- u32 flags, u32 loopback_mode,
- u32 loopback_speed)
-{
- MCDI_DECLARE_BUF(inbuf, MC_CMD_SET_LINK_IN_LEN);
- int rc;
-
- BUILD_BUG_ON(MC_CMD_SET_LINK_OUT_LEN != 0);
-
- MCDI_SET_DWORD(inbuf, SET_LINK_IN_CAP, capabilities);
- MCDI_SET_DWORD(inbuf, SET_LINK_IN_FLAGS, flags);
- MCDI_SET_DWORD(inbuf, SET_LINK_IN_LOOPBACK_MODE, loopback_mode);
- MCDI_SET_DWORD(inbuf, SET_LINK_IN_LOOPBACK_SPEED, loopback_speed);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_SET_LINK, inbuf, sizeof(inbuf),
- NULL, 0, NULL);
- return rc;
-}
-
-static int efx_mcdi_loopback_modes(struct efx_nic *efx, u64 *loopback_modes)
-{
- MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LOOPBACK_MODES_OUT_LEN);
- size_t outlen;
- int rc;
-
- rc = efx_mcdi_rpc(efx, MC_CMD_GET_LOOPBACK_MODES, NULL, 0,
- outbuf, sizeof(outbuf), &outlen);
- if (rc)
- goto fail;
-
- if (outlen < (MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_OFST +
- MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_LEN)) {
- rc = -EIO;
- goto fail;
- }
-
- *loopback_modes = MCDI_QWORD(outbuf, GET_LOOPBACK_MODES_OUT_SUGGESTED);
-
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
- return rc;
-}
+#include "mcdi_port_common.h"
static int efx_mcdi_mdio_read(struct net_device *net_dev,
int prtad, int devad, u16 addr)
@@ -168,246 +69,6 @@ static int efx_mcdi_mdio_write(struct net_device *net_dev,
return 0;
}
-static void mcdi_to_ethtool_linkset(u32 media, u32 cap, unsigned long *linkset)
-{
- #define SET_BIT(name) __set_bit(ETHTOOL_LINK_MODE_ ## name ## _BIT, \
- linkset)
-
- bitmap_zero(linkset, __ETHTOOL_LINK_MODE_MASK_NBITS);
- switch (media) {
- case MC_CMD_MEDIA_KX4:
- SET_BIT(Backplane);
- if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN))
- SET_BIT(1000baseKX_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN))
- SET_BIT(10000baseKX4_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN))
- SET_BIT(40000baseKR4_Full);
- break;
-
- case MC_CMD_MEDIA_XFP:
- case MC_CMD_MEDIA_SFP_PLUS:
- case MC_CMD_MEDIA_QSFP_PLUS:
- SET_BIT(FIBRE);
- if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN))
- SET_BIT(1000baseT_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN))
- SET_BIT(10000baseT_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN))
- SET_BIT(40000baseCR4_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_100000FDX_LBN))
- SET_BIT(100000baseCR4_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_25000FDX_LBN))
- SET_BIT(25000baseCR_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_50000FDX_LBN))
- SET_BIT(50000baseCR2_Full);
- break;
-
- case MC_CMD_MEDIA_BASE_T:
- SET_BIT(TP);
- if (cap & (1 << MC_CMD_PHY_CAP_10HDX_LBN))
- SET_BIT(10baseT_Half);
- if (cap & (1 << MC_CMD_PHY_CAP_10FDX_LBN))
- SET_BIT(10baseT_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_100HDX_LBN))
- SET_BIT(100baseT_Half);
- if (cap & (1 << MC_CMD_PHY_CAP_100FDX_LBN))
- SET_BIT(100baseT_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_1000HDX_LBN))
- SET_BIT(1000baseT_Half);
- if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN))
- SET_BIT(1000baseT_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN))
- SET_BIT(10000baseT_Full);
- break;
- }
-
- if (cap & (1 << MC_CMD_PHY_CAP_PAUSE_LBN))
- SET_BIT(Pause);
- if (cap & (1 << MC_CMD_PHY_CAP_ASYM_LBN))
- SET_BIT(Asym_Pause);
- if (cap & (1 << MC_CMD_PHY_CAP_AN_LBN))
- SET_BIT(Autoneg);
-
- #undef SET_BIT
-}
-
-static u32 ethtool_linkset_to_mcdi_cap(const unsigned long *linkset)
-{
- u32 result = 0;
-
- #define TEST_BIT(name) test_bit(ETHTOOL_LINK_MODE_ ## name ## _BIT, \
- linkset)
-
- if (TEST_BIT(10baseT_Half))
- result |= (1 << MC_CMD_PHY_CAP_10HDX_LBN);
- if (TEST_BIT(10baseT_Full))
- result |= (1 << MC_CMD_PHY_CAP_10FDX_LBN);
- if (TEST_BIT(100baseT_Half))
- result |= (1 << MC_CMD_PHY_CAP_100HDX_LBN);
- if (TEST_BIT(100baseT_Full))
- result |= (1 << MC_CMD_PHY_CAP_100FDX_LBN);
- if (TEST_BIT(1000baseT_Half))
- result |= (1 << MC_CMD_PHY_CAP_1000HDX_LBN);
- if (TEST_BIT(1000baseT_Full) || TEST_BIT(1000baseKX_Full))
- result |= (1 << MC_CMD_PHY_CAP_1000FDX_LBN);
- if (TEST_BIT(10000baseT_Full) || TEST_BIT(10000baseKX4_Full))
- result |= (1 << MC_CMD_PHY_CAP_10000FDX_LBN);
- if (TEST_BIT(40000baseCR4_Full) || TEST_BIT(40000baseKR4_Full))
- result |= (1 << MC_CMD_PHY_CAP_40000FDX_LBN);
- if (TEST_BIT(100000baseCR4_Full))
- result |= (1 << MC_CMD_PHY_CAP_100000FDX_LBN);
- if (TEST_BIT(25000baseCR_Full))
- result |= (1 << MC_CMD_PHY_CAP_25000FDX_LBN);
- if (TEST_BIT(50000baseCR2_Full))
- result |= (1 << MC_CMD_PHY_CAP_50000FDX_LBN);
- if (TEST_BIT(Pause))
- result |= (1 << MC_CMD_PHY_CAP_PAUSE_LBN);
- if (TEST_BIT(Asym_Pause))
- result |= (1 << MC_CMD_PHY_CAP_ASYM_LBN);
- if (TEST_BIT(Autoneg))
- result |= (1 << MC_CMD_PHY_CAP_AN_LBN);
-
- #undef TEST_BIT
-
- return result;
-}
-
-static u32 efx_get_mcdi_phy_flags(struct efx_nic *efx)
-{
- struct efx_mcdi_phy_data *phy_cfg = efx->phy_data;
- enum efx_phy_mode mode, supported;
- u32 flags;
-
- /* TODO: Advertise the capabilities supported by this PHY */
- supported = 0;
- if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_TXDIS_LBN))
- supported |= PHY_MODE_TX_DISABLED;
- if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_LOWPOWER_LBN))
- supported |= PHY_MODE_LOW_POWER;
- if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_POWEROFF_LBN))
- supported |= PHY_MODE_OFF;
-
- mode = efx->phy_mode & supported;
-
- flags = 0;
- if (mode & PHY_MODE_TX_DISABLED)
- flags |= (1 << MC_CMD_SET_LINK_IN_TXDIS_LBN);
- if (mode & PHY_MODE_LOW_POWER)
- flags |= (1 << MC_CMD_SET_LINK_IN_LOWPOWER_LBN);
- if (mode & PHY_MODE_OFF)
- flags |= (1 << MC_CMD_SET_LINK_IN_POWEROFF_LBN);
-
- return flags;
-}
-
-static u8 mcdi_to_ethtool_media(u32 media)
-{
- switch (media) {
- case MC_CMD_MEDIA_XAUI:
- case MC_CMD_MEDIA_CX4:
- case MC_CMD_MEDIA_KX4:
- return PORT_OTHER;
-
- case MC_CMD_MEDIA_XFP:
- case MC_CMD_MEDIA_SFP_PLUS:
- case MC_CMD_MEDIA_QSFP_PLUS:
- return PORT_FIBRE;
-
- case MC_CMD_MEDIA_BASE_T:
- return PORT_TP;
-
- default:
- return PORT_OTHER;
- }
-}
-
-static void efx_mcdi_phy_decode_link(struct efx_nic *efx,
- struct efx_link_state *link_state,
- u32 speed, u32 flags, u32 fcntl)
-{
- switch (fcntl) {
- case MC_CMD_FCNTL_AUTO:
- WARN_ON(1); /* This is not a link mode */
- link_state->fc = EFX_FC_AUTO | EFX_FC_TX | EFX_FC_RX;
- break;
- case MC_CMD_FCNTL_BIDIR:
- link_state->fc = EFX_FC_TX | EFX_FC_RX;
- break;
- case MC_CMD_FCNTL_RESPOND:
- link_state->fc = EFX_FC_RX;
- break;
- default:
- WARN_ON(1);
- /* Fall through */
- case MC_CMD_FCNTL_OFF:
- link_state->fc = 0;
- break;
- }
-
- link_state->up = !!(flags & (1 << MC_CMD_GET_LINK_OUT_LINK_UP_LBN));
- link_state->fd = !!(flags & (1 << MC_CMD_GET_LINK_OUT_FULL_DUPLEX_LBN));
- link_state->speed = speed;
-}
-
-/* The semantics of the ethtool FEC mode bitmask are not well defined,
- * particularly the meaning of combinations of bits. Which means we get to
- * define our own semantics, as follows:
- * OFF overrides any other bits, and means "disable all FEC" (with the
- * exception of 25G KR4/CR4, where it is not possible to reject it if AN
- * partner requests it).
- * AUTO on its own means use cable requirements and link partner autoneg with
- * fw-default preferences for the cable type.
- * AUTO and either RS or BASER means use the specified FEC type if cable and
- * link partner support it, otherwise autoneg/fw-default.
- * RS or BASER alone means use the specified FEC type if cable and link partner
- * support it and either requests it, otherwise no FEC.
- * Both RS and BASER (whether AUTO or not) means use FEC if cable and link
- * partner support it, preferring RS to BASER.
- */
-static u32 ethtool_fec_caps_to_mcdi(u32 ethtool_cap)
-{
- u32 ret = 0;
-
- if (ethtool_cap & ETHTOOL_FEC_OFF)
- return 0;
-
- if (ethtool_cap & ETHTOOL_FEC_AUTO)
- ret |= (1 << MC_CMD_PHY_CAP_BASER_FEC_LBN) |
- (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN) |
- (1 << MC_CMD_PHY_CAP_RS_FEC_LBN);
- if (ethtool_cap & ETHTOOL_FEC_RS)
- ret |= (1 << MC_CMD_PHY_CAP_RS_FEC_LBN) |
- (1 << MC_CMD_PHY_CAP_RS_FEC_REQUESTED_LBN);
- if (ethtool_cap & ETHTOOL_FEC_BASER)
- ret |= (1 << MC_CMD_PHY_CAP_BASER_FEC_LBN) |
- (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN) |
- (1 << MC_CMD_PHY_CAP_BASER_FEC_REQUESTED_LBN) |
- (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_LBN);
- return ret;
-}
-
-/* Invert ethtool_fec_caps_to_mcdi. There are two combinations that function
- * can never produce, (baser xor rs) and neither req; the implementation below
- * maps both of those to AUTO. This should never matter, and it's not clear
- * what a better mapping would be anyway.
- */
-static u32 mcdi_fec_caps_to_ethtool(u32 caps, bool is_25g)
-{
- bool rs = caps & (1 << MC_CMD_PHY_CAP_RS_FEC_LBN),
- rs_req = caps & (1 << MC_CMD_PHY_CAP_RS_FEC_REQUESTED_LBN),
- baser = is_25g ? caps & (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN)
- : caps & (1 << MC_CMD_PHY_CAP_BASER_FEC_LBN),
- baser_req = is_25g ? caps & (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_LBN)
- : caps & (1 << MC_CMD_PHY_CAP_BASER_FEC_REQUESTED_LBN);
-
- if (!baser && !rs)
- return ETHTOOL_FEC_OFF;
- return (rs_req ? ETHTOOL_FEC_RS : 0) |
- (baser_req ? ETHTOOL_FEC_BASER : 0) |
- (baser == baser_req && rs == rs_req ? 0 : ETHTOOL_FEC_AUTO);
-}
-
static int efx_mcdi_phy_probe(struct efx_nic *efx)
{
struct efx_mcdi_phy_data *phy_data;
@@ -527,58 +188,6 @@ int efx_mcdi_port_reconfigure(struct efx_nic *efx)
efx->loopback_mode, 0);
}
-/* Verify that the forced flow control settings (!EFX_FC_AUTO) are
- * supported by the link partner. Warn the user if this isn't the case
- */
-static void efx_mcdi_phy_check_fcntl(struct efx_nic *efx, u32 lpa)
-{
- struct efx_mcdi_phy_data *phy_cfg = efx->phy_data;
- u32 rmtadv;
-
- /* The link partner capabilities are only relevant if the
- * link supports flow control autonegotiation */
- if (~phy_cfg->supported_cap & (1 << MC_CMD_PHY_CAP_AN_LBN))
- return;
-
- /* If flow control autoneg is supported and enabled, then fine */
- if (efx->wanted_fc & EFX_FC_AUTO)
- return;
-
- rmtadv = 0;
- if (lpa & (1 << MC_CMD_PHY_CAP_PAUSE_LBN))
- rmtadv |= ADVERTISED_Pause;
- if (lpa & (1 << MC_CMD_PHY_CAP_ASYM_LBN))
- rmtadv |= ADVERTISED_Asym_Pause;
-
- if ((efx->wanted_fc & EFX_FC_TX) && rmtadv == ADVERTISED_Asym_Pause)
- netif_err(efx, link, efx->net_dev,
- "warning: link partner doesn't support pause frames");
-}
-
-static bool efx_mcdi_phy_poll(struct efx_nic *efx)
-{
- struct efx_link_state old_state = efx->link_state;
- MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN);
- int rc;
-
- WARN_ON(!mutex_is_locked(&efx->mac_lock));
-
- BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0,
- outbuf, sizeof(outbuf), NULL);
- if (rc)
- efx->link_state.up = false;
- else
- efx_mcdi_phy_decode_link(
- efx, &efx->link_state,
- MCDI_DWORD(outbuf, GET_LINK_OUT_LINK_SPEED),
- MCDI_DWORD(outbuf, GET_LINK_OUT_FLAGS),
- MCDI_DWORD(outbuf, GET_LINK_OUT_FCNTL));
-
- return !efx_link_state_equal(&efx->link_state, &old_state);
-}
-
static void efx_mcdi_phy_remove(struct efx_nic *efx)
{
struct efx_mcdi_phy_data *phy_data = efx->phy_data;
@@ -666,58 +275,6 @@ efx_mcdi_phy_set_link_ksettings(struct efx_nic *efx,
return 0;
}
-static int efx_mcdi_phy_get_fecparam(struct efx_nic *efx,
- struct ethtool_fecparam *fec)
-{
- MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_V2_LEN);
- u32 caps, active, speed; /* MCDI format */
- bool is_25g = false;
- size_t outlen;
- int rc;
-
- BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0);
- rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0,
- outbuf, sizeof(outbuf), &outlen);
- if (rc)
- return rc;
- if (outlen < MC_CMD_GET_LINK_OUT_V2_LEN)
- return -EOPNOTSUPP;
-
- /* behaviour for 25G/50G links depends on 25G BASER bit */
- speed = MCDI_DWORD(outbuf, GET_LINK_OUT_V2_LINK_SPEED);
- is_25g = speed == 25000 || speed == 50000;
-
- caps = MCDI_DWORD(outbuf, GET_LINK_OUT_V2_CAP);
- fec->fec = mcdi_fec_caps_to_ethtool(caps, is_25g);
- /* BASER is never supported on 100G */
- if (speed == 100000)
- fec->fec &= ~ETHTOOL_FEC_BASER;
-
- active = MCDI_DWORD(outbuf, GET_LINK_OUT_V2_FEC_TYPE);
- switch (active) {
- case MC_CMD_FEC_NONE:
- fec->active_fec = ETHTOOL_FEC_OFF;
- break;
- case MC_CMD_FEC_BASER:
- fec->active_fec = ETHTOOL_FEC_BASER;
- break;
- case MC_CMD_FEC_RS:
- fec->active_fec = ETHTOOL_FEC_RS;
- break;
- default:
- netif_warn(efx, hw, efx->net_dev,
- "Firmware reports unrecognised FEC_TYPE %u\n",
- active);
- /* We don't know what firmware has picked. AUTO is as good a
- * "can't happen" value as any other.
- */
- fec->active_fec = ETHTOOL_FEC_AUTO;
- break;
- }
-
- return 0;
-}
-
static int efx_mcdi_phy_set_fecparam(struct efx_nic *efx,
const struct ethtool_fecparam *fec)
{
@@ -745,27 +302,6 @@ static int efx_mcdi_phy_set_fecparam(struct efx_nic *efx,
return 0;
}
-static int efx_mcdi_phy_test_alive(struct efx_nic *efx)
-{
- MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_STATE_OUT_LEN);
- size_t outlen;
- int rc;
-
- BUILD_BUG_ON(MC_CMD_GET_PHY_STATE_IN_LEN != 0);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_GET_PHY_STATE, NULL, 0,
- outbuf, sizeof(outbuf), &outlen);
- if (rc)
- return rc;
-
- if (outlen < MC_CMD_GET_PHY_STATE_OUT_LEN)
- return -EIO;
- if (MCDI_DWORD(outbuf, GET_PHY_STATE_OUT_STATE) != MC_CMD_PHY_STATE_OK)
- return -EINVAL;
-
- return 0;
-}
-
static const char *const mcdi_sft9001_cable_diag_names[] = {
"cable.pairA.length",
"cable.pairB.length",
@@ -1139,84 +675,6 @@ u32 efx_mcdi_phy_get_caps(struct efx_nic *efx)
return phy_data->supported_cap;
}
-static unsigned int efx_mcdi_event_link_speed[] = {
- [MCDI_EVENT_LINKCHANGE_SPEED_100M] = 100,
- [MCDI_EVENT_LINKCHANGE_SPEED_1G] = 1000,
- [MCDI_EVENT_LINKCHANGE_SPEED_10G] = 10000,
- [MCDI_EVENT_LINKCHANGE_SPEED_40G] = 40000,
- [MCDI_EVENT_LINKCHANGE_SPEED_25G] = 25000,
- [MCDI_EVENT_LINKCHANGE_SPEED_50G] = 50000,
- [MCDI_EVENT_LINKCHANGE_SPEED_100G] = 100000,
-};
-
-void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev)
-{
- u32 flags, fcntl, speed, lpa;
-
- speed = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_SPEED);
- EFX_WARN_ON_PARANOID(speed >= ARRAY_SIZE(efx_mcdi_event_link_speed));
- speed = efx_mcdi_event_link_speed[speed];
-
- flags = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_LINK_FLAGS);
- fcntl = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_FCNTL);
- lpa = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_LP_CAP);
-
- /* efx->link_state is only modified by efx_mcdi_phy_get_link(),
- * which is only run after flushing the event queues. Therefore, it
- * is safe to modify the link state outside of the mac_lock here.
- */
- efx_mcdi_phy_decode_link(efx, &efx->link_state, speed, flags, fcntl);
-
- efx_mcdi_phy_check_fcntl(efx, lpa);
-
- efx_link_status_changed(efx);
-}
-
-int efx_mcdi_set_mac(struct efx_nic *efx)
-{
- u32 fcntl;
- MCDI_DECLARE_BUF(cmdbytes, MC_CMD_SET_MAC_IN_LEN);
-
- BUILD_BUG_ON(MC_CMD_SET_MAC_OUT_LEN != 0);
-
- /* This has no effect on EF10 */
- ether_addr_copy(MCDI_PTR(cmdbytes, SET_MAC_IN_ADDR),
- efx->net_dev->dev_addr);
-
- MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_MTU,
- EFX_MAX_FRAME_LEN(efx->net_dev->mtu));
- MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_DRAIN, 0);
-
- /* Set simple MAC filter for Siena */
- MCDI_POPULATE_DWORD_1(cmdbytes, SET_MAC_IN_REJECT,
- SET_MAC_IN_REJECT_UNCST, efx->unicast_filter);
-
- MCDI_POPULATE_DWORD_1(cmdbytes, SET_MAC_IN_FLAGS,
- SET_MAC_IN_FLAG_INCLUDE_FCS,
- !!(efx->net_dev->features & NETIF_F_RXFCS));
-
- switch (efx->wanted_fc) {
- case EFX_FC_RX | EFX_FC_TX:
- fcntl = MC_CMD_FCNTL_BIDIR;
- break;
- case EFX_FC_RX:
- fcntl = MC_CMD_FCNTL_RESPOND;
- break;
- default:
- fcntl = MC_CMD_FCNTL_OFF;
- break;
- }
- if (efx->wanted_fc & EFX_FC_AUTO)
- fcntl = MC_CMD_FCNTL_AUTO;
- if (efx->fc_disable)
- fcntl = MC_CMD_FCNTL_OFF;
-
- MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_FCNTL, fcntl);
-
- return efx_mcdi_rpc(efx, MC_CMD_SET_MAC, cmdbytes, sizeof(cmdbytes),
- NULL, 0, NULL);
-}
-
bool efx_mcdi_mac_check_fault(struct efx_nic *efx)
{
MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN);
@@ -1348,17 +806,3 @@ void efx_mcdi_port_remove(struct efx_nic *efx)
efx->phy_op->remove(efx);
efx_nic_free_buffer(efx, &efx->stats_buffer);
}
-
-/* Get physical port number (EF10 only; on Siena it is same as PF number) */
-int efx_mcdi_port_get_number(struct efx_nic *efx)
-{
- MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PORT_ASSIGNMENT_OUT_LEN);
- int rc;
-
- rc = efx_mcdi_rpc(efx, MC_CMD_GET_PORT_ASSIGNMENT, NULL, 0,
- outbuf, sizeof(outbuf), NULL);
- if (rc)
- return rc;
-
- return MCDI_DWORD(outbuf, GET_PORT_ASSIGNMENT_OUT_PORT);
-}
diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.c b/drivers/net/ethernet/sfc/mcdi_port_common.c
new file mode 100644
index 0000000..a6a072b
--- /dev/null
+++ b/drivers/net/ethernet/sfc/mcdi_port_common.c
@@ -0,0 +1,568 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include "mcdi_port_common.h"
+#include "efx_common.h"
+
+int efx_mcdi_get_phy_cfg(struct efx_nic *efx, struct efx_mcdi_phy_data *cfg)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_CFG_OUT_LEN);
+ size_t outlen;
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_GET_PHY_CFG_IN_LEN != 0);
+ BUILD_BUG_ON(MC_CMD_GET_PHY_CFG_OUT_NAME_LEN != sizeof(cfg->name));
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_PHY_CFG, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ goto fail;
+
+ if (outlen < MC_CMD_GET_PHY_CFG_OUT_LEN) {
+ rc = -EIO;
+ goto fail;
+ }
+
+ cfg->flags = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_FLAGS);
+ cfg->type = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_TYPE);
+ cfg->supported_cap =
+ MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_SUPPORTED_CAP);
+ cfg->channel = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_CHANNEL);
+ cfg->port = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_PRT);
+ cfg->stats_mask = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_STATS_MASK);
+ memcpy(cfg->name, MCDI_PTR(outbuf, GET_PHY_CFG_OUT_NAME),
+ sizeof(cfg->name));
+ cfg->media = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_MEDIA_TYPE);
+ cfg->mmd_mask = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_MMD_MASK);
+ memcpy(cfg->revision, MCDI_PTR(outbuf, GET_PHY_CFG_OUT_REVISION),
+ sizeof(cfg->revision));
+
+ return 0;
+
+fail:
+ netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
+ return rc;
+}
+
+void efx_link_set_advertising(struct efx_nic *efx,
+ const unsigned long *advertising)
+{
+ memcpy(efx->link_advertising, advertising,
+ sizeof(__ETHTOOL_DECLARE_LINK_MODE_MASK()));
+
+ efx->link_advertising[0] |= ADVERTISED_Autoneg;
+ if (advertising[0] & ADVERTISED_Pause)
+ efx->wanted_fc |= (EFX_FC_TX | EFX_FC_RX);
+ else
+ efx->wanted_fc &= ~(EFX_FC_TX | EFX_FC_RX);
+ if (advertising[0] & ADVERTISED_Asym_Pause)
+ efx->wanted_fc ^= EFX_FC_TX;
+}
+
+int efx_mcdi_set_link(struct efx_nic *efx, u32 capabilities,
+ u32 flags, u32 loopback_mode, u32 loopback_speed)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_SET_LINK_IN_LEN);
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_SET_LINK_OUT_LEN != 0);
+
+ MCDI_SET_DWORD(inbuf, SET_LINK_IN_CAP, capabilities);
+ MCDI_SET_DWORD(inbuf, SET_LINK_IN_FLAGS, flags);
+ MCDI_SET_DWORD(inbuf, SET_LINK_IN_LOOPBACK_MODE, loopback_mode);
+ MCDI_SET_DWORD(inbuf, SET_LINK_IN_LOOPBACK_SPEED, loopback_speed);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_SET_LINK, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+ return rc;
+}
+
+int efx_mcdi_loopback_modes(struct efx_nic *efx, u64 *loopback_modes)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LOOPBACK_MODES_OUT_LEN);
+ size_t outlen;
+ int rc;
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_LOOPBACK_MODES, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ goto fail;
+
+ if (outlen < (MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_OFST +
+ MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_LEN)) {
+ rc = -EIO;
+ goto fail;
+ }
+
+ *loopback_modes = MCDI_QWORD(outbuf, GET_LOOPBACK_MODES_OUT_SUGGESTED);
+
+ return 0;
+
+fail:
+ netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
+ return rc;
+}
+
+void mcdi_to_ethtool_linkset(u32 media, u32 cap, unsigned long *linkset)
+{
+ #define SET_BIT(name) __set_bit(ETHTOOL_LINK_MODE_ ## name ## _BIT, \
+ linkset)
+
+ bitmap_zero(linkset, __ETHTOOL_LINK_MODE_MASK_NBITS);
+ switch (media) {
+ case MC_CMD_MEDIA_KX4:
+ SET_BIT(Backplane);
+ if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN))
+ SET_BIT(1000baseKX_Full);
+ if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN))
+ SET_BIT(10000baseKX4_Full);
+ if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN))
+ SET_BIT(40000baseKR4_Full);
+ break;
+
+ case MC_CMD_MEDIA_XFP:
+ case MC_CMD_MEDIA_SFP_PLUS:
+ case MC_CMD_MEDIA_QSFP_PLUS:
+ SET_BIT(FIBRE);
+ if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN))
+ SET_BIT(1000baseT_Full);
+ if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN))
+ SET_BIT(10000baseT_Full);
+ if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN))
+ SET_BIT(40000baseCR4_Full);
+ if (cap & (1 << MC_CMD_PHY_CAP_100000FDX_LBN))
+ SET_BIT(100000baseCR4_Full);
+ if (cap & (1 << MC_CMD_PHY_CAP_25000FDX_LBN))
+ SET_BIT(25000baseCR_Full);
+ if (cap & (1 << MC_CMD_PHY_CAP_50000FDX_LBN))
+ SET_BIT(50000baseCR2_Full);
+ break;
+
+ case MC_CMD_MEDIA_BASE_T:
+ SET_BIT(TP);
+ if (cap & (1 << MC_CMD_PHY_CAP_10HDX_LBN))
+ SET_BIT(10baseT_Half);
+ if (cap & (1 << MC_CMD_PHY_CAP_10FDX_LBN))
+ SET_BIT(10baseT_Full);
+ if (cap & (1 << MC_CMD_PHY_CAP_100HDX_LBN))
+ SET_BIT(100baseT_Half);
+ if (cap & (1 << MC_CMD_PHY_CAP_100FDX_LBN))
+ SET_BIT(100baseT_Full);
+ if (cap & (1 << MC_CMD_PHY_CAP_1000HDX_LBN))
+ SET_BIT(1000baseT_Half);
+ if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN))
+ SET_BIT(1000baseT_Full);
+ if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN))
+ SET_BIT(10000baseT_Full);
+ break;
+ }
+
+ if (cap & (1 << MC_CMD_PHY_CAP_PAUSE_LBN))
+ SET_BIT(Pause);
+ if (cap & (1 << MC_CMD_PHY_CAP_ASYM_LBN))
+ SET_BIT(Asym_Pause);
+ if (cap & (1 << MC_CMD_PHY_CAP_AN_LBN))
+ SET_BIT(Autoneg);
+
+ #undef SET_BIT
+}
+
+u32 ethtool_linkset_to_mcdi_cap(const unsigned long *linkset)
+{
+ u32 result = 0;
+
+ #define TEST_BIT(name) test_bit(ETHTOOL_LINK_MODE_ ## name ## _BIT, \
+ linkset)
+
+ if (TEST_BIT(10baseT_Half))
+ result |= (1 << MC_CMD_PHY_CAP_10HDX_LBN);
+ if (TEST_BIT(10baseT_Full))
+ result |= (1 << MC_CMD_PHY_CAP_10FDX_LBN);
+ if (TEST_BIT(100baseT_Half))
+ result |= (1 << MC_CMD_PHY_CAP_100HDX_LBN);
+ if (TEST_BIT(100baseT_Full))
+ result |= (1 << MC_CMD_PHY_CAP_100FDX_LBN);
+ if (TEST_BIT(1000baseT_Half))
+ result |= (1 << MC_CMD_PHY_CAP_1000HDX_LBN);
+ if (TEST_BIT(1000baseT_Full) || TEST_BIT(1000baseKX_Full))
+ result |= (1 << MC_CMD_PHY_CAP_1000FDX_LBN);
+ if (TEST_BIT(10000baseT_Full) || TEST_BIT(10000baseKX4_Full))
+ result |= (1 << MC_CMD_PHY_CAP_10000FDX_LBN);
+ if (TEST_BIT(40000baseCR4_Full) || TEST_BIT(40000baseKR4_Full))
+ result |= (1 << MC_CMD_PHY_CAP_40000FDX_LBN);
+ if (TEST_BIT(100000baseCR4_Full))
+ result |= (1 << MC_CMD_PHY_CAP_100000FDX_LBN);
+ if (TEST_BIT(25000baseCR_Full))
+ result |= (1 << MC_CMD_PHY_CAP_25000FDX_LBN);
+ if (TEST_BIT(50000baseCR2_Full))
+ result |= (1 << MC_CMD_PHY_CAP_50000FDX_LBN);
+ if (TEST_BIT(Pause))
+ result |= (1 << MC_CMD_PHY_CAP_PAUSE_LBN);
+ if (TEST_BIT(Asym_Pause))
+ result |= (1 << MC_CMD_PHY_CAP_ASYM_LBN);
+ if (TEST_BIT(Autoneg))
+ result |= (1 << MC_CMD_PHY_CAP_AN_LBN);
+
+ #undef TEST_BIT
+
+ return result;
+}
+
+u32 efx_get_mcdi_phy_flags(struct efx_nic *efx)
+{
+ struct efx_mcdi_phy_data *phy_cfg = efx->phy_data;
+ enum efx_phy_mode mode, supported;
+ u32 flags;
+
+ /* TODO: Advertise the capabilities supported by this PHY */
+ supported = 0;
+ if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_TXDIS_LBN))
+ supported |= PHY_MODE_TX_DISABLED;
+ if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_LOWPOWER_LBN))
+ supported |= PHY_MODE_LOW_POWER;
+ if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_POWEROFF_LBN))
+ supported |= PHY_MODE_OFF;
+
+ mode = efx->phy_mode & supported;
+
+ flags = 0;
+ if (mode & PHY_MODE_TX_DISABLED)
+ flags |= (1 << MC_CMD_SET_LINK_IN_TXDIS_LBN);
+ if (mode & PHY_MODE_LOW_POWER)
+ flags |= (1 << MC_CMD_SET_LINK_IN_LOWPOWER_LBN);
+ if (mode & PHY_MODE_OFF)
+ flags |= (1 << MC_CMD_SET_LINK_IN_POWEROFF_LBN);
+
+ return flags;
+}
+
+u8 mcdi_to_ethtool_media(u32 media)
+{
+ switch (media) {
+ case MC_CMD_MEDIA_XAUI:
+ case MC_CMD_MEDIA_CX4:
+ case MC_CMD_MEDIA_KX4:
+ return PORT_OTHER;
+
+ case MC_CMD_MEDIA_XFP:
+ case MC_CMD_MEDIA_SFP_PLUS:
+ case MC_CMD_MEDIA_QSFP_PLUS:
+ return PORT_FIBRE;
+
+ case MC_CMD_MEDIA_BASE_T:
+ return PORT_TP;
+
+ default:
+ return PORT_OTHER;
+ }
+}
+
+void efx_mcdi_phy_decode_link(struct efx_nic *efx,
+ struct efx_link_state *link_state,
+ u32 speed, u32 flags, u32 fcntl)
+{
+ switch (fcntl) {
+ case MC_CMD_FCNTL_AUTO:
+ WARN_ON(1); /* This is not a link mode */
+ link_state->fc = EFX_FC_AUTO | EFX_FC_TX | EFX_FC_RX;
+ break;
+ case MC_CMD_FCNTL_BIDIR:
+ link_state->fc = EFX_FC_TX | EFX_FC_RX;
+ break;
+ case MC_CMD_FCNTL_RESPOND:
+ link_state->fc = EFX_FC_RX;
+ break;
+ default:
+ WARN_ON(1);
+ /* Fall through */
+ case MC_CMD_FCNTL_OFF:
+ link_state->fc = 0;
+ break;
+ }
+
+ link_state->up = !!(flags & (1 << MC_CMD_GET_LINK_OUT_LINK_UP_LBN));
+ link_state->fd = !!(flags & (1 << MC_CMD_GET_LINK_OUT_FULL_DUPLEX_LBN));
+ link_state->speed = speed;
+}
+
+/* The semantics of the ethtool FEC mode bitmask are not well defined,
+ * particularly the meaning of combinations of bits. Which means we get to
+ * define our own semantics, as follows:
+ * OFF overrides any other bits, and means "disable all FEC" (with the
+ * exception of 25G KR4/CR4, where it is not possible to reject it if AN
+ * partner requests it).
+ * AUTO on its own means use cable requirements and link partner autoneg with
+ * fw-default preferences for the cable type.
+ * AUTO and either RS or BASER means use the specified FEC type if cable and
+ * link partner support it, otherwise autoneg/fw-default.
+ * RS or BASER alone means use the specified FEC type if cable and link partner
+ * support it and either requests it, otherwise no FEC.
+ * Both RS and BASER (whether AUTO or not) means use FEC if cable and link
+ * partner support it, preferring RS to BASER.
+ */
+u32 ethtool_fec_caps_to_mcdi(u32 ethtool_cap)
+{
+ u32 ret = 0;
+
+ if (ethtool_cap & ETHTOOL_FEC_OFF)
+ return 0;
+
+ if (ethtool_cap & ETHTOOL_FEC_AUTO)
+ ret |= (1 << MC_CMD_PHY_CAP_BASER_FEC_LBN) |
+ (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN) |
+ (1 << MC_CMD_PHY_CAP_RS_FEC_LBN);
+ if (ethtool_cap & ETHTOOL_FEC_RS)
+ ret |= (1 << MC_CMD_PHY_CAP_RS_FEC_LBN) |
+ (1 << MC_CMD_PHY_CAP_RS_FEC_REQUESTED_LBN);
+ if (ethtool_cap & ETHTOOL_FEC_BASER)
+ ret |= (1 << MC_CMD_PHY_CAP_BASER_FEC_LBN) |
+ (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN) |
+ (1 << MC_CMD_PHY_CAP_BASER_FEC_REQUESTED_LBN) |
+ (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_LBN);
+ return ret;
+}
+
+/* Invert ethtool_fec_caps_to_mcdi. There are two combinations that function
+ * can never produce, (baser xor rs) and neither req; the implementation below
+ * maps both of those to AUTO. This should never matter, and it's not clear
+ * what a better mapping would be anyway.
+ */
+u32 mcdi_fec_caps_to_ethtool(u32 caps, bool is_25g)
+{
+ bool rs = caps & (1 << MC_CMD_PHY_CAP_RS_FEC_LBN),
+ rs_req = caps & (1 << MC_CMD_PHY_CAP_RS_FEC_REQUESTED_LBN),
+ baser = is_25g ? caps & (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_LBN)
+ : caps & (1 << MC_CMD_PHY_CAP_BASER_FEC_LBN),
+ baser_req = is_25g ? caps & (1 << MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_LBN)
+ : caps & (1 << MC_CMD_PHY_CAP_BASER_FEC_REQUESTED_LBN);
+
+ if (!baser && !rs)
+ return ETHTOOL_FEC_OFF;
+ return (rs_req ? ETHTOOL_FEC_RS : 0) |
+ (baser_req ? ETHTOOL_FEC_BASER : 0) |
+ (baser == baser_req && rs == rs_req ? 0 : ETHTOOL_FEC_AUTO);
+}
+
+/* Verify that the forced flow control settings (!EFX_FC_AUTO) are
+ * supported by the link partner. Warn the user if this isn't the case
+ */
+void efx_mcdi_phy_check_fcntl(struct efx_nic *efx, u32 lpa)
+{
+ struct efx_mcdi_phy_data *phy_cfg = efx->phy_data;
+ u32 rmtadv;
+
+ /* The link partner capabilities are only relevant if the
+ * link supports flow control autonegotiation
+ */
+ if (~phy_cfg->supported_cap & (1 << MC_CMD_PHY_CAP_AN_LBN))
+ return;
+
+ /* If flow control autoneg is supported and enabled, then fine */
+ if (efx->wanted_fc & EFX_FC_AUTO)
+ return;
+
+ rmtadv = 0;
+ if (lpa & (1 << MC_CMD_PHY_CAP_PAUSE_LBN))
+ rmtadv |= ADVERTISED_Pause;
+ if (lpa & (1 << MC_CMD_PHY_CAP_ASYM_LBN))
+ rmtadv |= ADVERTISED_Asym_Pause;
+
+ if ((efx->wanted_fc & EFX_FC_TX) && rmtadv == ADVERTISED_Asym_Pause)
+ netif_err(efx, link, efx->net_dev,
+ "warning: link partner doesn't support pause frames");
+}
+
+bool efx_mcdi_phy_poll(struct efx_nic *efx)
+{
+ struct efx_link_state old_state = efx->link_state;
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN);
+ int rc;
+
+ WARN_ON(!mutex_is_locked(&efx->mac_lock));
+
+ BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0,
+ outbuf, sizeof(outbuf), NULL);
+ if (rc)
+ efx->link_state.up = false;
+ else
+ efx_mcdi_phy_decode_link(
+ efx, &efx->link_state,
+ MCDI_DWORD(outbuf, GET_LINK_OUT_LINK_SPEED),
+ MCDI_DWORD(outbuf, GET_LINK_OUT_FLAGS),
+ MCDI_DWORD(outbuf, GET_LINK_OUT_FCNTL));
+
+ return !efx_link_state_equal(&efx->link_state, &old_state);
+}
+
+int efx_mcdi_phy_get_fecparam(struct efx_nic *efx, struct ethtool_fecparam *fec)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_V2_LEN);
+ u32 caps, active, speed; /* MCDI format */
+ bool is_25g = false;
+ size_t outlen;
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0);
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ return rc;
+ if (outlen < MC_CMD_GET_LINK_OUT_V2_LEN)
+ return -EOPNOTSUPP;
+
+ /* behaviour for 25G/50G links depends on 25G BASER bit */
+ speed = MCDI_DWORD(outbuf, GET_LINK_OUT_V2_LINK_SPEED);
+ is_25g = speed == 25000 || speed == 50000;
+
+ caps = MCDI_DWORD(outbuf, GET_LINK_OUT_V2_CAP);
+ fec->fec = mcdi_fec_caps_to_ethtool(caps, is_25g);
+ /* BASER is never supported on 100G */
+ if (speed == 100000)
+ fec->fec &= ~ETHTOOL_FEC_BASER;
+
+ active = MCDI_DWORD(outbuf, GET_LINK_OUT_V2_FEC_TYPE);
+ switch (active) {
+ case MC_CMD_FEC_NONE:
+ fec->active_fec = ETHTOOL_FEC_OFF;
+ break;
+ case MC_CMD_FEC_BASER:
+ fec->active_fec = ETHTOOL_FEC_BASER;
+ break;
+ case MC_CMD_FEC_RS:
+ fec->active_fec = ETHTOOL_FEC_RS;
+ break;
+ default:
+ netif_warn(efx, hw, efx->net_dev,
+ "Firmware reports unrecognised FEC_TYPE %u\n",
+ active);
+ /* We don't know what firmware has picked. AUTO is as good a
+ * "can't happen" value as any other.
+ */
+ fec->active_fec = ETHTOOL_FEC_AUTO;
+ break;
+ }
+
+ return 0;
+}
+
+int efx_mcdi_phy_test_alive(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_STATE_OUT_LEN);
+ size_t outlen;
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_GET_PHY_STATE_IN_LEN != 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_PHY_STATE, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ return rc;
+
+ if (outlen < MC_CMD_GET_PHY_STATE_OUT_LEN)
+ return -EIO;
+ if (MCDI_DWORD(outbuf, GET_PHY_STATE_OUT_STATE) != MC_CMD_PHY_STATE_OK)
+ return -EINVAL;
+
+ return 0;
+}
+
+int efx_mcdi_set_mac(struct efx_nic *efx)
+{
+ u32 fcntl;
+ MCDI_DECLARE_BUF(cmdbytes, MC_CMD_SET_MAC_IN_LEN);
+
+ BUILD_BUG_ON(MC_CMD_SET_MAC_OUT_LEN != 0);
+
+ /* This has no effect on EF10 */
+ ether_addr_copy(MCDI_PTR(cmdbytes, SET_MAC_IN_ADDR),
+ efx->net_dev->dev_addr);
+
+ MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_MTU,
+ EFX_MAX_FRAME_LEN(efx->net_dev->mtu));
+ MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_DRAIN, 0);
+
+ /* Set simple MAC filter for Siena */
+ MCDI_POPULATE_DWORD_1(cmdbytes, SET_MAC_IN_REJECT,
+ SET_MAC_IN_REJECT_UNCST, efx->unicast_filter);
+
+ MCDI_POPULATE_DWORD_1(cmdbytes, SET_MAC_IN_FLAGS,
+ SET_MAC_IN_FLAG_INCLUDE_FCS,
+ !!(efx->net_dev->features & NETIF_F_RXFCS));
+
+ switch (efx->wanted_fc) {
+ case EFX_FC_RX | EFX_FC_TX:
+ fcntl = MC_CMD_FCNTL_BIDIR;
+ break;
+ case EFX_FC_RX:
+ fcntl = MC_CMD_FCNTL_RESPOND;
+ break;
+ default:
+ fcntl = MC_CMD_FCNTL_OFF;
+ break;
+ }
+ if (efx->wanted_fc & EFX_FC_AUTO)
+ fcntl = MC_CMD_FCNTL_AUTO;
+ if (efx->fc_disable)
+ fcntl = MC_CMD_FCNTL_OFF;
+
+ MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_FCNTL, fcntl);
+
+ return efx_mcdi_rpc(efx, MC_CMD_SET_MAC, cmdbytes, sizeof(cmdbytes),
+ NULL, 0, NULL);
+}
+
+/* Get physical port number (EF10 only; on Siena it is same as PF number) */
+int efx_mcdi_port_get_number(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PORT_ASSIGNMENT_OUT_LEN);
+ int rc;
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_PORT_ASSIGNMENT, NULL, 0,
+ outbuf, sizeof(outbuf), NULL);
+ if (rc)
+ return rc;
+
+ return MCDI_DWORD(outbuf, GET_PORT_ASSIGNMENT_OUT_PORT);
+}
+
+static unsigned int efx_mcdi_event_link_speed[] = {
+ [MCDI_EVENT_LINKCHANGE_SPEED_100M] = 100,
+ [MCDI_EVENT_LINKCHANGE_SPEED_1G] = 1000,
+ [MCDI_EVENT_LINKCHANGE_SPEED_10G] = 10000,
+ [MCDI_EVENT_LINKCHANGE_SPEED_40G] = 40000,
+ [MCDI_EVENT_LINKCHANGE_SPEED_25G] = 25000,
+ [MCDI_EVENT_LINKCHANGE_SPEED_50G] = 50000,
+ [MCDI_EVENT_LINKCHANGE_SPEED_100G] = 100000,
+};
+
+void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev)
+{
+ u32 flags, fcntl, speed, lpa;
+
+ speed = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_SPEED);
+ EFX_WARN_ON_PARANOID(speed >= ARRAY_SIZE(efx_mcdi_event_link_speed));
+ speed = efx_mcdi_event_link_speed[speed];
+
+ flags = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_LINK_FLAGS);
+ fcntl = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_FCNTL);
+ lpa = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_LP_CAP);
+
+ /* efx->link_state is only modified by efx_mcdi_phy_get_link(),
+ * which is only run after flushing the event queues. Therefore, it
+ * is safe to modify the link state outside of the mac_lock here.
+ */
+ efx_mcdi_phy_decode_link(efx, &efx->link_state, speed, flags, fcntl);
+
+ efx_mcdi_phy_check_fcntl(efx, lpa);
+
+ efx_link_status_changed(efx);
+}
diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.h b/drivers/net/ethernet/sfc/mcdi_port_common.h
new file mode 100644
index 0000000..b16f112
--- /dev/null
+++ b/drivers/net/ethernet/sfc/mcdi_port_common.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+#ifndef EFX_MCDI_PORT_COMMON_H
+#define EFX_MCDI_PORT_COMMON_H
+
+#include "net_driver.h"
+#include "mcdi.h"
+#include "mcdi_pcol.h"
+
+struct efx_mcdi_phy_data {
+ u32 flags;
+ u32 type;
+ u32 supported_cap;
+ u32 channel;
+ u32 port;
+ u32 stats_mask;
+ u8 name[20];
+ u32 media;
+ u32 mmd_mask;
+ u8 revision[20];
+ u32 forced_cap;
+};
+
+#define EFX_MC_STATS_GENERATION_INVALID ((__force __le64)(-1))
+
+int efx_mcdi_get_phy_cfg(struct efx_nic *efx, struct efx_mcdi_phy_data *cfg);
+void efx_link_set_advertising(struct efx_nic *efx,
+ const unsigned long *advertising);
+int efx_mcdi_set_link(struct efx_nic *efx, u32 capabilities,
+ u32 flags, u32 loopback_mode, u32 loopback_speed);
+int efx_mcdi_loopback_modes(struct efx_nic *efx, u64 *loopback_modes);
+void mcdi_to_ethtool_linkset(u32 media, u32 cap, unsigned long *linkset);
+u32 ethtool_linkset_to_mcdi_cap(const unsigned long *linkset);
+u32 efx_get_mcdi_phy_flags(struct efx_nic *efx);
+u8 mcdi_to_ethtool_media(u32 media);
+void efx_mcdi_phy_decode_link(struct efx_nic *efx,
+ struct efx_link_state *link_state,
+ u32 speed, u32 flags, u32 fcntl);
+u32 ethtool_fec_caps_to_mcdi(u32 ethtool_cap);
+u32 mcdi_fec_caps_to_ethtool(u32 caps, bool is_25g);
+void efx_mcdi_phy_check_fcntl(struct efx_nic *efx, u32 lpa);
+bool efx_mcdi_phy_poll(struct efx_nic *efx);
+int efx_mcdi_phy_get_fecparam(struct efx_nic *efx,
+ struct ethtool_fecparam *fec);
+int efx_mcdi_phy_test_alive(struct efx_nic *efx);
+int efx_mcdi_set_mac(struct efx_nic *efx);
+int efx_mcdi_port_get_number(struct efx_nic *efx);
+void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev);
+
+#endif
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 709172a..9f9886f 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -138,6 +138,8 @@ struct efx_special_buffer {
* freed when descriptor completes
* @xdpf: When @flags & %EFX_TX_BUF_XDP, the XDP frame information; its @data
* member is the associated buffer to drop a page reference on.
+ * @option: When @flags & %EFX_TX_BUF_OPTION, an EF10-specific option
+ * descriptor.
* @dma_addr: DMA address of the fragment.
* @flags: Flags for allocation and DMA mapping type
* @len: Length of this fragment.
@@ -152,7 +154,7 @@ struct efx_tx_buffer {
struct xdp_frame *xdpf;
};
union {
- efx_qword_t option;
+ efx_qword_t option; /* EF10 */
dma_addr_t dma_addr;
};
unsigned short flags;
@@ -742,13 +744,13 @@ union efx_multicast_hash {
struct vfdi_status;
/* The reserved RSS context value */
-#define EFX_EF10_RSS_CONTEXT_INVALID 0xffffffff
+#define EFX_MCDI_RSS_CONTEXT_INVALID 0xffffffff
/**
* struct efx_rss_context - A user-defined RSS context for filtering
* @list: node of linked list on which this struct is stored
* @context_id: the RSS_CONTEXT_ID returned by MC firmware, or
- * %EFX_EF10_RSS_CONTEXT_INVALID if this context is not present on the NIC.
- * For Siena, 0 if RSS is active, else %EFX_EF10_RSS_CONTEXT_INVALID.
+ * %EFX_MCDI_RSS_CONTEXT_INVALID if this context is not present on the NIC.
+ * For Siena, 0 if RSS is active, else %EFX_MCDI_RSS_CONTEXT_INVALID.
* @user_id: the rss_context ID exposed to userspace over ethtool.
* @rx_hash_udp_4tuple: UDP 4-tuple hashing enabled
* @rx_hash_key: Toeplitz hash key for this RSS context
@@ -1610,6 +1612,15 @@ static inline struct efx_rx_buffer *efx_rx_buffer(struct efx_rx_queue *rx_queue,
return &rx_queue->buffer[index];
}
+static inline struct efx_rx_buffer *
+efx_rx_buf_next(struct efx_rx_queue *rx_queue, struct efx_rx_buffer *rx_buf)
+{
+ if (unlikely(rx_buf == efx_rx_buffer(rx_queue, rx_queue->ptr_mask)))
+ return efx_rx_buffer(rx_queue, 0);
+ else
+ return rx_buf + 1;
+}
+
/**
* EFX_MAX_FRAME_LEN - calculate maximum frame length
*
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index bf0bdb2..6670fda 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -11,6 +11,7 @@
#include <linux/net_tstamp.h>
#include "net_driver.h"
#include "efx.h"
+#include "efx_common.h"
#include "mcdi.h"
enum {
@@ -505,6 +506,9 @@ static inline void efx_nic_push_buffers(struct efx_tx_queue *tx_queue)
tx_queue->efx->type->tx_write(tx_queue);
}
+int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
+ bool *data_mapped);
+
/* RX data path */
static inline int efx_nic_probe_rx(struct efx_rx_queue *rx_queue)
{
@@ -553,6 +557,7 @@ static inline void efx_nic_eventq_read_ack(struct efx_channel *channel)
{
channel->efx->type->ev_read_ack(channel);
}
+
void efx_nic_event_test_start(struct efx_channel *channel);
/* Falcon/Siena queue operations */
@@ -670,6 +675,7 @@ struct efx_farch_register_test {
unsigned address;
efx_oword_t mask;
};
+
int efx_farch_test_registers(struct efx_nic *efx,
const struct efx_farch_register_test *regs,
size_t n_regs);
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index c29bf86..a2042f1 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -21,6 +21,7 @@
#include <linux/bpf_trace.h>
#include "net_driver.h"
#include "efx.h"
+#include "rx_common.h"
#include "filter.h"
#include "nic.h"
#include "selftest.h"
@@ -32,60 +33,13 @@
/* Maximum rx prefix used by any architecture. */
#define EFX_MAX_RX_PREFIX_SIZE 16
-/* Number of RX buffers to recycle pages for. When creating the RX page recycle
- * ring, this number is divided by the number of buffers per page to calculate
- * the number of pages to store in the RX page recycle ring.
- */
-#define EFX_RECYCLE_RING_SIZE_IOMMU 4096
-#define EFX_RECYCLE_RING_SIZE_NOIOMMU (2 * EFX_RX_PREFERRED_BATCH)
-
/* Size of buffer allocated for skb header area. */
#define EFX_SKB_HEADERS 128u
-/* This is the percentage fill level below which new RX descriptors
- * will be added to the RX descriptor ring.
- */
-static unsigned int rx_refill_threshold;
-
/* Each packet can consume up to ceil(max_frame_len / buffer_size) buffers */
#define EFX_RX_MAX_FRAGS DIV_ROUND_UP(EFX_MAX_FRAME_LEN(EFX_MAX_MTU), \
EFX_RX_USR_BUF_SIZE)
-/*
- * RX maximum head room required.
- *
- * This must be at least 1 to prevent overflow, plus one packet-worth
- * to allow pipelined receives.
- */
-#define EFX_RXD_HEAD_ROOM (1 + EFX_RX_MAX_FRAGS)
-
-static inline u8 *efx_rx_buf_va(struct efx_rx_buffer *buf)
-{
- return page_address(buf->page) + buf->page_offset;
-}
-
-static inline u32 efx_rx_buf_hash(struct efx_nic *efx, const u8 *eh)
-{
-#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
- return __le32_to_cpup((const __le32 *)(eh + efx->rx_packet_hash_offset));
-#else
- const u8 *data = eh + efx->rx_packet_hash_offset;
- return (u32)data[0] |
- (u32)data[1] << 8 |
- (u32)data[2] << 16 |
- (u32)data[3] << 24;
-#endif
-}
-
-static inline struct efx_rx_buffer *
-efx_rx_buf_next(struct efx_rx_queue *rx_queue, struct efx_rx_buffer *rx_buf)
-{
- if (unlikely(rx_buf == efx_rx_buffer(rx_queue, rx_queue->ptr_mask)))
- return efx_rx_buffer(rx_queue, 0);
- else
- return rx_buf + 1;
-}
-
static inline void efx_sync_rx_buffer(struct efx_nic *efx,
struct efx_rx_buffer *rx_buf,
unsigned int len)
@@ -94,301 +48,6 @@ static inline void efx_sync_rx_buffer(struct efx_nic *efx,
DMA_FROM_DEVICE);
}
-void efx_rx_config_page_split(struct efx_nic *efx)
-{
- efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + efx->rx_ip_align +
- XDP_PACKET_HEADROOM,
- EFX_RX_BUF_ALIGNMENT);
- efx->rx_bufs_per_page = efx->rx_buffer_order ? 1 :
- ((PAGE_SIZE - sizeof(struct efx_rx_page_state)) /
- efx->rx_page_buf_step);
- efx->rx_buffer_truesize = (PAGE_SIZE << efx->rx_buffer_order) /
- efx->rx_bufs_per_page;
- efx->rx_pages_per_batch = DIV_ROUND_UP(EFX_RX_PREFERRED_BATCH,
- efx->rx_bufs_per_page);
-}
-
-/* Check the RX page recycle ring for a page that can be reused. */
-static struct page *efx_reuse_page(struct efx_rx_queue *rx_queue)
-{
- struct efx_nic *efx = rx_queue->efx;
- struct page *page;
- struct efx_rx_page_state *state;
- unsigned index;
-
- index = rx_queue->page_remove & rx_queue->page_ptr_mask;
- page = rx_queue->page_ring[index];
- if (page == NULL)
- return NULL;
-
- rx_queue->page_ring[index] = NULL;
- /* page_remove cannot exceed page_add. */
- if (rx_queue->page_remove != rx_queue->page_add)
- ++rx_queue->page_remove;
-
- /* If page_count is 1 then we hold the only reference to this page. */
- if (page_count(page) == 1) {
- ++rx_queue->page_recycle_count;
- return page;
- } else {
- state = page_address(page);
- dma_unmap_page(&efx->pci_dev->dev, state->dma_addr,
- PAGE_SIZE << efx->rx_buffer_order,
- DMA_FROM_DEVICE);
- put_page(page);
- ++rx_queue->page_recycle_failed;
- }
-
- return NULL;
-}
-
-/**
- * efx_init_rx_buffers - create EFX_RX_BATCH page-based RX buffers
- *
- * @rx_queue: Efx RX queue
- *
- * This allocates a batch of pages, maps them for DMA, and populates
- * struct efx_rx_buffers for each one. Return a negative error code or
- * 0 on success. If a single page can be used for multiple buffers,
- * then the page will either be inserted fully, or not at all.
- */
-static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue, bool atomic)
-{
- struct efx_nic *efx = rx_queue->efx;
- struct efx_rx_buffer *rx_buf;
- struct page *page;
- unsigned int page_offset;
- struct efx_rx_page_state *state;
- dma_addr_t dma_addr;
- unsigned index, count;
-
- count = 0;
- do {
- page = efx_reuse_page(rx_queue);
- if (page == NULL) {
- page = alloc_pages(__GFP_COMP |
- (atomic ? GFP_ATOMIC : GFP_KERNEL),
- efx->rx_buffer_order);
- if (unlikely(page == NULL))
- return -ENOMEM;
- dma_addr =
- dma_map_page(&efx->pci_dev->dev, page, 0,
- PAGE_SIZE << efx->rx_buffer_order,
- DMA_FROM_DEVICE);
- if (unlikely(dma_mapping_error(&efx->pci_dev->dev,
- dma_addr))) {
- __free_pages(page, efx->rx_buffer_order);
- return -EIO;
- }
- state = page_address(page);
- state->dma_addr = dma_addr;
- } else {
- state = page_address(page);
- dma_addr = state->dma_addr;
- }
-
- dma_addr += sizeof(struct efx_rx_page_state);
- page_offset = sizeof(struct efx_rx_page_state);
-
- do {
- index = rx_queue->added_count & rx_queue->ptr_mask;
- rx_buf = efx_rx_buffer(rx_queue, index);
- rx_buf->dma_addr = dma_addr + efx->rx_ip_align +
- XDP_PACKET_HEADROOM;
- rx_buf->page = page;
- rx_buf->page_offset = page_offset + efx->rx_ip_align +
- XDP_PACKET_HEADROOM;
- rx_buf->len = efx->rx_dma_len;
- rx_buf->flags = 0;
- ++rx_queue->added_count;
- get_page(page);
- dma_addr += efx->rx_page_buf_step;
- page_offset += efx->rx_page_buf_step;
- } while (page_offset + efx->rx_page_buf_step <= PAGE_SIZE);
-
- rx_buf->flags = EFX_RX_BUF_LAST_IN_PAGE;
- } while (++count < efx->rx_pages_per_batch);
-
- return 0;
-}
-
-/* Unmap a DMA-mapped page. This function is only called for the final RX
- * buffer in a page.
- */
-static void efx_unmap_rx_buffer(struct efx_nic *efx,
- struct efx_rx_buffer *rx_buf)
-{
- struct page *page = rx_buf->page;
-
- if (page) {
- struct efx_rx_page_state *state = page_address(page);
- dma_unmap_page(&efx->pci_dev->dev,
- state->dma_addr,
- PAGE_SIZE << efx->rx_buffer_order,
- DMA_FROM_DEVICE);
- }
-}
-
-static void efx_free_rx_buffers(struct efx_rx_queue *rx_queue,
- struct efx_rx_buffer *rx_buf,
- unsigned int num_bufs)
-{
- do {
- if (rx_buf->page) {
- put_page(rx_buf->page);
- rx_buf->page = NULL;
- }
- rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
- } while (--num_bufs);
-}
-
-/* Attempt to recycle the page if there is an RX recycle ring; the page can
- * only be added if this is the final RX buffer, to prevent pages being used in
- * the descriptor ring and appearing in the recycle ring simultaneously.
- */
-static void efx_recycle_rx_page(struct efx_channel *channel,
- struct efx_rx_buffer *rx_buf)
-{
- struct page *page = rx_buf->page;
- struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
- struct efx_nic *efx = rx_queue->efx;
- unsigned index;
-
- /* Only recycle the page after processing the final buffer. */
- if (!(rx_buf->flags & EFX_RX_BUF_LAST_IN_PAGE))
- return;
-
- index = rx_queue->page_add & rx_queue->page_ptr_mask;
- if (rx_queue->page_ring[index] == NULL) {
- unsigned read_index = rx_queue->page_remove &
- rx_queue->page_ptr_mask;
-
- /* The next slot in the recycle ring is available, but
- * increment page_remove if the read pointer currently
- * points here.
- */
- if (read_index == index)
- ++rx_queue->page_remove;
- rx_queue->page_ring[index] = page;
- ++rx_queue->page_add;
- return;
- }
- ++rx_queue->page_recycle_full;
- efx_unmap_rx_buffer(efx, rx_buf);
- put_page(rx_buf->page);
-}
-
-static void efx_fini_rx_buffer(struct efx_rx_queue *rx_queue,
- struct efx_rx_buffer *rx_buf)
-{
- /* Release the page reference we hold for the buffer. */
- if (rx_buf->page)
- put_page(rx_buf->page);
-
- /* If this is the last buffer in a page, unmap and free it. */
- if (rx_buf->flags & EFX_RX_BUF_LAST_IN_PAGE) {
- efx_unmap_rx_buffer(rx_queue->efx, rx_buf);
- efx_free_rx_buffers(rx_queue, rx_buf, 1);
- }
- rx_buf->page = NULL;
-}
-
-/* Recycle the pages that are used by buffers that have just been received. */
-static void efx_recycle_rx_pages(struct efx_channel *channel,
- struct efx_rx_buffer *rx_buf,
- unsigned int n_frags)
-{
- struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
-
- do {
- efx_recycle_rx_page(channel, rx_buf);
- rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
- } while (--n_frags);
-}
-
-static void efx_discard_rx_packet(struct efx_channel *channel,
- struct efx_rx_buffer *rx_buf,
- unsigned int n_frags)
-{
- struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
-
- efx_recycle_rx_pages(channel, rx_buf, n_frags);
-
- efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
-}
-
-/**
- * efx_fast_push_rx_descriptors - push new RX descriptors quickly
- * @rx_queue: RX descriptor queue
- *
- * This will aim to fill the RX descriptor queue up to
- * @rx_queue->@max_fill. If there is insufficient atomic
- * memory to do so, a slow fill will be scheduled.
- *
- * The caller must provide serialisation (none is used here). In practise,
- * this means this function must run from the NAPI handler, or be called
- * when NAPI is disabled.
- */
-void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic)
-{
- struct efx_nic *efx = rx_queue->efx;
- unsigned int fill_level, batch_size;
- int space, rc = 0;
-
- if (!rx_queue->refill_enabled)
- return;
-
- /* Calculate current fill level, and exit if we don't need to fill */
- fill_level = (rx_queue->added_count - rx_queue->removed_count);
- EFX_WARN_ON_ONCE_PARANOID(fill_level > rx_queue->efx->rxq_entries);
- if (fill_level >= rx_queue->fast_fill_trigger)
- goto out;
-
- /* Record minimum fill level */
- if (unlikely(fill_level < rx_queue->min_fill)) {
- if (fill_level)
- rx_queue->min_fill = fill_level;
- }
-
- batch_size = efx->rx_pages_per_batch * efx->rx_bufs_per_page;
- space = rx_queue->max_fill - fill_level;
- EFX_WARN_ON_ONCE_PARANOID(space < batch_size);
-
- netif_vdbg(rx_queue->efx, rx_status, rx_queue->efx->net_dev,
- "RX queue %d fast-filling descriptor ring from"
- " level %d to level %d\n",
- efx_rx_queue_index(rx_queue), fill_level,
- rx_queue->max_fill);
-
-
- do {
- rc = efx_init_rx_buffers(rx_queue, atomic);
- if (unlikely(rc)) {
- /* Ensure that we don't leave the rx queue empty */
- efx_schedule_slow_fill(rx_queue);
- goto out;
- }
- } while ((space -= batch_size) >= batch_size);
-
- netif_vdbg(rx_queue->efx, rx_status, rx_queue->efx->net_dev,
- "RX queue %d fast-filled descriptor ring "
- "to level %d\n", efx_rx_queue_index(rx_queue),
- rx_queue->added_count - rx_queue->removed_count);
-
- out:
- if (rx_queue->notified_count != rx_queue->added_count)
- efx_nic_notify_rx_desc(rx_queue);
-}
-
-void efx_rx_slow_fill(struct timer_list *t)
-{
- struct efx_rx_queue *rx_queue = from_timer(rx_queue, t, slow_fill);
-
- /* Post an event to cause NAPI to run and refill the queue */
- efx_nic_generate_fill_event(rx_queue);
- ++rx_queue->slow_fill_count;
-}
-
static void efx_rx_packet__check_len(struct efx_rx_queue *rx_queue,
struct efx_rx_buffer *rx_buf,
int len)
@@ -412,53 +71,6 @@ static void efx_rx_packet__check_len(struct efx_rx_queue *rx_queue,
efx_rx_queue_channel(rx_queue)->n_rx_overlength++;
}
-/* Pass a received packet up through GRO. GRO can handle pages
- * regardless of checksum state and skbs with a good checksum.
- */
-static void
-efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf,
- unsigned int n_frags, u8 *eh)
-{
- struct napi_struct *napi = &channel->napi_str;
- struct efx_nic *efx = channel->efx;
- struct sk_buff *skb;
-
- skb = napi_get_frags(napi);
- if (unlikely(!skb)) {
- struct efx_rx_queue *rx_queue;
-
- rx_queue = efx_channel_get_rx_queue(channel);
- efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
- return;
- }
-
- if (efx->net_dev->features & NETIF_F_RXHASH)
- skb_set_hash(skb, efx_rx_buf_hash(efx, eh),
- PKT_HASH_TYPE_L3);
- skb->ip_summed = ((rx_buf->flags & EFX_RX_PKT_CSUMMED) ?
- CHECKSUM_UNNECESSARY : CHECKSUM_NONE);
- skb->csum_level = !!(rx_buf->flags & EFX_RX_PKT_CSUM_LEVEL);
-
- for (;;) {
- skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
- rx_buf->page, rx_buf->page_offset,
- rx_buf->len);
- rx_buf->page = NULL;
- skb->len += rx_buf->len;
- if (skb_shinfo(skb)->nr_frags == n_frags)
- break;
-
- rx_buf = efx_rx_buf_next(&channel->rx_queue, rx_buf);
- }
-
- skb->data_len = skb->len;
- skb->truesize += n_frags * efx->rx_buffer_truesize;
-
- skb_record_rx_queue(skb, channel->rx_queue.core_index);
-
- napi_gro_frags(napi);
-}
-
/* Allocate and construct an SKB around page fragments */
static struct sk_buff *efx_rx_mk_skb(struct efx_channel *channel,
struct efx_rx_buffer *rx_buf,
@@ -805,174 +417,6 @@ void __efx_rx_packet(struct efx_channel *channel)
channel->rx_pkt_n_frags = 0;
}
-int efx_probe_rx_queue(struct efx_rx_queue *rx_queue)
-{
- struct efx_nic *efx = rx_queue->efx;
- unsigned int entries;
- int rc;
-
- /* Create the smallest power-of-two aligned ring */
- entries = max(roundup_pow_of_two(efx->rxq_entries), EFX_MIN_DMAQ_SIZE);
- EFX_WARN_ON_PARANOID(entries > EFX_MAX_DMAQ_SIZE);
- rx_queue->ptr_mask = entries - 1;
-
- netif_dbg(efx, probe, efx->net_dev,
- "creating RX queue %d size %#x mask %#x\n",
- efx_rx_queue_index(rx_queue), efx->rxq_entries,
- rx_queue->ptr_mask);
-
- /* Allocate RX buffers */
- rx_queue->buffer = kcalloc(entries, sizeof(*rx_queue->buffer),
- GFP_KERNEL);
- if (!rx_queue->buffer)
- return -ENOMEM;
-
- rc = efx_nic_probe_rx(rx_queue);
- if (rc) {
- kfree(rx_queue->buffer);
- rx_queue->buffer = NULL;
- }
-
- return rc;
-}
-
-static void efx_init_rx_recycle_ring(struct efx_nic *efx,
- struct efx_rx_queue *rx_queue)
-{
- unsigned int bufs_in_recycle_ring, page_ring_size;
-
- /* Set the RX recycle ring size */
-#ifdef CONFIG_PPC64
- bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU;
-#else
- if (iommu_present(&pci_bus_type))
- bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU;
- else
- bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_NOIOMMU;
-#endif /* CONFIG_PPC64 */
-
- page_ring_size = roundup_pow_of_two(bufs_in_recycle_ring /
- efx->rx_bufs_per_page);
- rx_queue->page_ring = kcalloc(page_ring_size,
- sizeof(*rx_queue->page_ring), GFP_KERNEL);
- rx_queue->page_ptr_mask = page_ring_size - 1;
-}
-
-void efx_init_rx_queue(struct efx_rx_queue *rx_queue)
-{
- struct efx_nic *efx = rx_queue->efx;
- unsigned int max_fill, trigger, max_trigger;
- int rc = 0;
-
- netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
- "initialising RX queue %d\n", efx_rx_queue_index(rx_queue));
-
- /* Initialise ptr fields */
- rx_queue->added_count = 0;
- rx_queue->notified_count = 0;
- rx_queue->removed_count = 0;
- rx_queue->min_fill = -1U;
- efx_init_rx_recycle_ring(efx, rx_queue);
-
- rx_queue->page_remove = 0;
- rx_queue->page_add = rx_queue->page_ptr_mask + 1;
- rx_queue->page_recycle_count = 0;
- rx_queue->page_recycle_failed = 0;
- rx_queue->page_recycle_full = 0;
-
- /* Initialise limit fields */
- max_fill = efx->rxq_entries - EFX_RXD_HEAD_ROOM;
- max_trigger =
- max_fill - efx->rx_pages_per_batch * efx->rx_bufs_per_page;
- if (rx_refill_threshold != 0) {
- trigger = max_fill * min(rx_refill_threshold, 100U) / 100U;
- if (trigger > max_trigger)
- trigger = max_trigger;
- } else {
- trigger = max_trigger;
- }
-
- rx_queue->max_fill = max_fill;
- rx_queue->fast_fill_trigger = trigger;
- rx_queue->refill_enabled = true;
-
- /* Initialise XDP queue information */
- rc = xdp_rxq_info_reg(&rx_queue->xdp_rxq_info, efx->net_dev,
- rx_queue->core_index);
-
- if (rc) {
- netif_err(efx, rx_err, efx->net_dev,
- "Failure to initialise XDP queue information rc=%d\n",
- rc);
- efx->xdp_rxq_info_failed = true;
- } else {
- rx_queue->xdp_rxq_info_valid = true;
- }
-
- /* Set up RX descriptor ring */
- efx_nic_init_rx(rx_queue);
-}
-
-void efx_fini_rx_queue(struct efx_rx_queue *rx_queue)
-{
- int i;
- struct efx_nic *efx = rx_queue->efx;
- struct efx_rx_buffer *rx_buf;
-
- netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
- "shutting down RX queue %d\n", efx_rx_queue_index(rx_queue));
-
- del_timer_sync(&rx_queue->slow_fill);
-
- /* Release RX buffers from the current read ptr to the write ptr */
- if (rx_queue->buffer) {
- for (i = rx_queue->removed_count; i < rx_queue->added_count;
- i++) {
- unsigned index = i & rx_queue->ptr_mask;
- rx_buf = efx_rx_buffer(rx_queue, index);
- efx_fini_rx_buffer(rx_queue, rx_buf);
- }
- }
-
- /* Unmap and release the pages in the recycle ring. Remove the ring. */
- for (i = 0; i <= rx_queue->page_ptr_mask; i++) {
- struct page *page = rx_queue->page_ring[i];
- struct efx_rx_page_state *state;
-
- if (page == NULL)
- continue;
-
- state = page_address(page);
- dma_unmap_page(&efx->pci_dev->dev, state->dma_addr,
- PAGE_SIZE << efx->rx_buffer_order,
- DMA_FROM_DEVICE);
- put_page(page);
- }
- kfree(rx_queue->page_ring);
- rx_queue->page_ring = NULL;
-
- if (rx_queue->xdp_rxq_info_valid)
- xdp_rxq_info_unreg(&rx_queue->xdp_rxq_info);
-
- rx_queue->xdp_rxq_info_valid = false;
-}
-
-void efx_remove_rx_queue(struct efx_rx_queue *rx_queue)
-{
- netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
- "destroying RX queue %d\n", efx_rx_queue_index(rx_queue));
-
- efx_nic_remove_rx(rx_queue);
-
- kfree(rx_queue->buffer);
- rx_queue->buffer = NULL;
-}
-
-
-module_param(rx_refill_threshold, uint, 0444);
-MODULE_PARM_DESC(rx_refill_threshold,
- "RX descriptor ring refill threshold (%)");
-
#ifdef CONFIG_RFS_ACCEL
static void efx_filter_rfs_work(struct work_struct *data)
@@ -1206,37 +650,3 @@ bool __efx_filter_rfs_expire(struct efx_channel *channel, unsigned int quota)
}
#endif /* CONFIG_RFS_ACCEL */
-
-/**
- * efx_filter_is_mc_recipient - test whether spec is a multicast recipient
- * @spec: Specification to test
- *
- * Return: %true if the specification is a non-drop RX filter that
- * matches a local MAC address I/G bit value of 1 or matches a local
- * IPv4 or IPv6 address value in the respective multicast address
- * range. Otherwise %false.
- */
-bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec)
-{
- if (!(spec->flags & EFX_FILTER_FLAG_RX) ||
- spec->dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP)
- return false;
-
- if (spec->match_flags &
- (EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_LOC_MAC_IG) &&
- is_multicast_ether_addr(spec->loc_mac))
- return true;
-
- if ((spec->match_flags &
- (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_LOC_HOST)) ==
- (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_LOC_HOST)) {
- if (spec->ether_type == htons(ETH_P_IP) &&
- ipv4_is_multicast(spec->loc_host[0]))
- return true;
- if (spec->ether_type == htons(ETH_P_IPV6) &&
- ((const u8 *)spec->loc_host)[0] == 0xff)
- return true;
- }
-
- return false;
-}
diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c
new file mode 100644
index 0000000..ee8beb87
--- /dev/null
+++ b/drivers/net/ethernet/sfc/rx_common.c
@@ -0,0 +1,851 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include "net_driver.h"
+#include <linux/module.h>
+#include <linux/iommu.h>
+#include "efx.h"
+#include "nic.h"
+#include "rx_common.h"
+
+/* This is the percentage fill level below which new RX descriptors
+ * will be added to the RX descriptor ring.
+ */
+static unsigned int rx_refill_threshold;
+module_param(rx_refill_threshold, uint, 0444);
+MODULE_PARM_DESC(rx_refill_threshold,
+ "RX descriptor ring refill threshold (%)");
+
+/* Number of RX buffers to recycle pages for. When creating the RX page recycle
+ * ring, this number is divided by the number of buffers per page to calculate
+ * the number of pages to store in the RX page recycle ring.
+ */
+#define EFX_RECYCLE_RING_SIZE_IOMMU 4096
+#define EFX_RECYCLE_RING_SIZE_NOIOMMU (2 * EFX_RX_PREFERRED_BATCH)
+
+/* RX maximum head room required.
+ *
+ * This must be at least 1 to prevent overflow, plus one packet-worth
+ * to allow pipelined receives.
+ */
+#define EFX_RXD_HEAD_ROOM (1 + EFX_RX_MAX_FRAGS)
+
+/* Check the RX page recycle ring for a page that can be reused. */
+static struct page *efx_reuse_page(struct efx_rx_queue *rx_queue)
+{
+ struct efx_nic *efx = rx_queue->efx;
+ struct efx_rx_page_state *state;
+ unsigned int index;
+ struct page *page;
+
+ index = rx_queue->page_remove & rx_queue->page_ptr_mask;
+ page = rx_queue->page_ring[index];
+ if (page == NULL)
+ return NULL;
+
+ rx_queue->page_ring[index] = NULL;
+ /* page_remove cannot exceed page_add. */
+ if (rx_queue->page_remove != rx_queue->page_add)
+ ++rx_queue->page_remove;
+
+ /* If page_count is 1 then we hold the only reference to this page. */
+ if (page_count(page) == 1) {
+ ++rx_queue->page_recycle_count;
+ return page;
+ } else {
+ state = page_address(page);
+ dma_unmap_page(&efx->pci_dev->dev, state->dma_addr,
+ PAGE_SIZE << efx->rx_buffer_order,
+ DMA_FROM_DEVICE);
+ put_page(page);
+ ++rx_queue->page_recycle_failed;
+ }
+
+ return NULL;
+}
+
+/* Attempt to recycle the page if there is an RX recycle ring; the page can
+ * only be added if this is the final RX buffer, to prevent pages being used in
+ * the descriptor ring and appearing in the recycle ring simultaneously.
+ */
+static void efx_recycle_rx_page(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf)
+{
+ struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
+ struct efx_nic *efx = rx_queue->efx;
+ struct page *page = rx_buf->page;
+ unsigned int index;
+
+ /* Only recycle the page after processing the final buffer. */
+ if (!(rx_buf->flags & EFX_RX_BUF_LAST_IN_PAGE))
+ return;
+
+ index = rx_queue->page_add & rx_queue->page_ptr_mask;
+ if (rx_queue->page_ring[index] == NULL) {
+ unsigned int read_index = rx_queue->page_remove &
+ rx_queue->page_ptr_mask;
+
+ /* The next slot in the recycle ring is available, but
+ * increment page_remove if the read pointer currently
+ * points here.
+ */
+ if (read_index == index)
+ ++rx_queue->page_remove;
+ rx_queue->page_ring[index] = page;
+ ++rx_queue->page_add;
+ return;
+ }
+ ++rx_queue->page_recycle_full;
+ efx_unmap_rx_buffer(efx, rx_buf);
+ put_page(rx_buf->page);
+}
+
+/* Recycle the pages that are used by buffers that have just been received. */
+void efx_recycle_rx_pages(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags)
+{
+ struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
+
+ do {
+ efx_recycle_rx_page(channel, rx_buf);
+ rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
+ } while (--n_frags);
+}
+
+void efx_discard_rx_packet(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags)
+{
+ struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
+
+ efx_recycle_rx_pages(channel, rx_buf, n_frags);
+
+ efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
+}
+
+static void efx_init_rx_recycle_ring(struct efx_rx_queue *rx_queue)
+{
+ unsigned int bufs_in_recycle_ring, page_ring_size;
+ struct efx_nic *efx = rx_queue->efx;
+
+ /* Set the RX recycle ring size */
+#ifdef CONFIG_PPC64
+ bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU;
+#else
+ if (iommu_present(&pci_bus_type))
+ bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU;
+ else
+ bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_NOIOMMU;
+#endif /* CONFIG_PPC64 */
+
+ page_ring_size = roundup_pow_of_two(bufs_in_recycle_ring /
+ efx->rx_bufs_per_page);
+ rx_queue->page_ring = kcalloc(page_ring_size,
+ sizeof(*rx_queue->page_ring), GFP_KERNEL);
+ rx_queue->page_ptr_mask = page_ring_size - 1;
+}
+
+static void efx_fini_rx_recycle_ring(struct efx_rx_queue *rx_queue)
+{
+ struct efx_nic *efx = rx_queue->efx;
+ int i;
+
+ /* Unmap and release the pages in the recycle ring. Remove the ring. */
+ for (i = 0; i <= rx_queue->page_ptr_mask; i++) {
+ struct page *page = rx_queue->page_ring[i];
+ struct efx_rx_page_state *state;
+
+ if (page == NULL)
+ continue;
+
+ state = page_address(page);
+ dma_unmap_page(&efx->pci_dev->dev, state->dma_addr,
+ PAGE_SIZE << efx->rx_buffer_order,
+ DMA_FROM_DEVICE);
+ put_page(page);
+ }
+ kfree(rx_queue->page_ring);
+ rx_queue->page_ring = NULL;
+}
+
+static void efx_fini_rx_buffer(struct efx_rx_queue *rx_queue,
+ struct efx_rx_buffer *rx_buf)
+{
+ /* Release the page reference we hold for the buffer. */
+ if (rx_buf->page)
+ put_page(rx_buf->page);
+
+ /* If this is the last buffer in a page, unmap and free it. */
+ if (rx_buf->flags & EFX_RX_BUF_LAST_IN_PAGE) {
+ efx_unmap_rx_buffer(rx_queue->efx, rx_buf);
+ efx_free_rx_buffers(rx_queue, rx_buf, 1);
+ }
+ rx_buf->page = NULL;
+}
+
+int efx_probe_rx_queue(struct efx_rx_queue *rx_queue)
+{
+ struct efx_nic *efx = rx_queue->efx;
+ unsigned int entries;
+ int rc;
+
+ /* Create the smallest power-of-two aligned ring */
+ entries = max(roundup_pow_of_two(efx->rxq_entries), EFX_MIN_DMAQ_SIZE);
+ EFX_WARN_ON_PARANOID(entries > EFX_MAX_DMAQ_SIZE);
+ rx_queue->ptr_mask = entries - 1;
+
+ netif_dbg(efx, probe, efx->net_dev,
+ "creating RX queue %d size %#x mask %#x\n",
+ efx_rx_queue_index(rx_queue), efx->rxq_entries,
+ rx_queue->ptr_mask);
+
+ /* Allocate RX buffers */
+ rx_queue->buffer = kcalloc(entries, sizeof(*rx_queue->buffer),
+ GFP_KERNEL);
+ if (!rx_queue->buffer)
+ return -ENOMEM;
+
+ rc = efx_nic_probe_rx(rx_queue);
+ if (rc) {
+ kfree(rx_queue->buffer);
+ rx_queue->buffer = NULL;
+ }
+
+ return rc;
+}
+
+void efx_init_rx_queue(struct efx_rx_queue *rx_queue)
+{
+ unsigned int max_fill, trigger, max_trigger;
+ struct efx_nic *efx = rx_queue->efx;
+ int rc = 0;
+
+ netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
+ "initialising RX queue %d\n", efx_rx_queue_index(rx_queue));
+
+ /* Initialise ptr fields */
+ rx_queue->added_count = 0;
+ rx_queue->notified_count = 0;
+ rx_queue->removed_count = 0;
+ rx_queue->min_fill = -1U;
+ efx_init_rx_recycle_ring(rx_queue);
+
+ rx_queue->page_remove = 0;
+ rx_queue->page_add = rx_queue->page_ptr_mask + 1;
+ rx_queue->page_recycle_count = 0;
+ rx_queue->page_recycle_failed = 0;
+ rx_queue->page_recycle_full = 0;
+
+ /* Initialise limit fields */
+ max_fill = efx->rxq_entries - EFX_RXD_HEAD_ROOM;
+ max_trigger =
+ max_fill - efx->rx_pages_per_batch * efx->rx_bufs_per_page;
+ if (rx_refill_threshold != 0) {
+ trigger = max_fill * min(rx_refill_threshold, 100U) / 100U;
+ if (trigger > max_trigger)
+ trigger = max_trigger;
+ } else {
+ trigger = max_trigger;
+ }
+
+ rx_queue->max_fill = max_fill;
+ rx_queue->fast_fill_trigger = trigger;
+ rx_queue->refill_enabled = true;
+
+ /* Initialise XDP queue information */
+ rc = xdp_rxq_info_reg(&rx_queue->xdp_rxq_info, efx->net_dev,
+ rx_queue->core_index);
+
+ if (rc) {
+ netif_err(efx, rx_err, efx->net_dev,
+ "Failure to initialise XDP queue information rc=%d\n",
+ rc);
+ efx->xdp_rxq_info_failed = true;
+ } else {
+ rx_queue->xdp_rxq_info_valid = true;
+ }
+
+ /* Set up RX descriptor ring */
+ efx_nic_init_rx(rx_queue);
+}
+
+void efx_fini_rx_queue(struct efx_rx_queue *rx_queue)
+{
+ struct efx_rx_buffer *rx_buf;
+ int i;
+
+ netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
+ "shutting down RX queue %d\n", efx_rx_queue_index(rx_queue));
+
+ del_timer_sync(&rx_queue->slow_fill);
+
+ /* Release RX buffers from the current read ptr to the write ptr */
+ if (rx_queue->buffer) {
+ for (i = rx_queue->removed_count; i < rx_queue->added_count;
+ i++) {
+ unsigned int index = i & rx_queue->ptr_mask;
+
+ rx_buf = efx_rx_buffer(rx_queue, index);
+ efx_fini_rx_buffer(rx_queue, rx_buf);
+ }
+ }
+
+ efx_fini_rx_recycle_ring(rx_queue);
+
+ if (rx_queue->xdp_rxq_info_valid)
+ xdp_rxq_info_unreg(&rx_queue->xdp_rxq_info);
+
+ rx_queue->xdp_rxq_info_valid = false;
+}
+
+void efx_remove_rx_queue(struct efx_rx_queue *rx_queue)
+{
+ netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
+ "destroying RX queue %d\n", efx_rx_queue_index(rx_queue));
+
+ efx_nic_remove_rx(rx_queue);
+
+ kfree(rx_queue->buffer);
+ rx_queue->buffer = NULL;
+}
+
+/* Unmap a DMA-mapped page. This function is only called for the final RX
+ * buffer in a page.
+ */
+void efx_unmap_rx_buffer(struct efx_nic *efx,
+ struct efx_rx_buffer *rx_buf)
+{
+ struct page *page = rx_buf->page;
+
+ if (page) {
+ struct efx_rx_page_state *state = page_address(page);
+
+ dma_unmap_page(&efx->pci_dev->dev,
+ state->dma_addr,
+ PAGE_SIZE << efx->rx_buffer_order,
+ DMA_FROM_DEVICE);
+ }
+}
+
+void efx_free_rx_buffers(struct efx_rx_queue *rx_queue,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int num_bufs)
+{
+ do {
+ if (rx_buf->page) {
+ put_page(rx_buf->page);
+ rx_buf->page = NULL;
+ }
+ rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
+ } while (--num_bufs);
+}
+
+void efx_rx_slow_fill(struct timer_list *t)
+{
+ struct efx_rx_queue *rx_queue = from_timer(rx_queue, t, slow_fill);
+
+ /* Post an event to cause NAPI to run and refill the queue */
+ efx_nic_generate_fill_event(rx_queue);
+ ++rx_queue->slow_fill_count;
+}
+
+void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue)
+{
+ mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(10));
+}
+
+/* efx_init_rx_buffers - create EFX_RX_BATCH page-based RX buffers
+ *
+ * @rx_queue: Efx RX queue
+ *
+ * This allocates a batch of pages, maps them for DMA, and populates
+ * struct efx_rx_buffers for each one. Return a negative error code or
+ * 0 on success. If a single page can be used for multiple buffers,
+ * then the page will either be inserted fully, or not at all.
+ */
+static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue, bool atomic)
+{
+ unsigned int page_offset, index, count;
+ struct efx_nic *efx = rx_queue->efx;
+ struct efx_rx_page_state *state;
+ struct efx_rx_buffer *rx_buf;
+ dma_addr_t dma_addr;
+ struct page *page;
+
+ count = 0;
+ do {
+ page = efx_reuse_page(rx_queue);
+ if (page == NULL) {
+ page = alloc_pages(__GFP_COMP |
+ (atomic ? GFP_ATOMIC : GFP_KERNEL),
+ efx->rx_buffer_order);
+ if (unlikely(page == NULL))
+ return -ENOMEM;
+ dma_addr =
+ dma_map_page(&efx->pci_dev->dev, page, 0,
+ PAGE_SIZE << efx->rx_buffer_order,
+ DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(&efx->pci_dev->dev,
+ dma_addr))) {
+ __free_pages(page, efx->rx_buffer_order);
+ return -EIO;
+ }
+ state = page_address(page);
+ state->dma_addr = dma_addr;
+ } else {
+ state = page_address(page);
+ dma_addr = state->dma_addr;
+ }
+
+ dma_addr += sizeof(struct efx_rx_page_state);
+ page_offset = sizeof(struct efx_rx_page_state);
+
+ do {
+ index = rx_queue->added_count & rx_queue->ptr_mask;
+ rx_buf = efx_rx_buffer(rx_queue, index);
+ rx_buf->dma_addr = dma_addr + efx->rx_ip_align +
+ XDP_PACKET_HEADROOM;
+ rx_buf->page = page;
+ rx_buf->page_offset = page_offset + efx->rx_ip_align +
+ XDP_PACKET_HEADROOM;
+ rx_buf->len = efx->rx_dma_len;
+ rx_buf->flags = 0;
+ ++rx_queue->added_count;
+ get_page(page);
+ dma_addr += efx->rx_page_buf_step;
+ page_offset += efx->rx_page_buf_step;
+ } while (page_offset + efx->rx_page_buf_step <= PAGE_SIZE);
+
+ rx_buf->flags = EFX_RX_BUF_LAST_IN_PAGE;
+ } while (++count < efx->rx_pages_per_batch);
+
+ return 0;
+}
+
+void efx_rx_config_page_split(struct efx_nic *efx)
+{
+ efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + efx->rx_ip_align +
+ XDP_PACKET_HEADROOM,
+ EFX_RX_BUF_ALIGNMENT);
+ efx->rx_bufs_per_page = efx->rx_buffer_order ? 1 :
+ ((PAGE_SIZE - sizeof(struct efx_rx_page_state)) /
+ efx->rx_page_buf_step);
+ efx->rx_buffer_truesize = (PAGE_SIZE << efx->rx_buffer_order) /
+ efx->rx_bufs_per_page;
+ efx->rx_pages_per_batch = DIV_ROUND_UP(EFX_RX_PREFERRED_BATCH,
+ efx->rx_bufs_per_page);
+}
+
+/* efx_fast_push_rx_descriptors - push new RX descriptors quickly
+ * @rx_queue: RX descriptor queue
+ *
+ * This will aim to fill the RX descriptor queue up to
+ * @rx_queue->@max_fill. If there is insufficient atomic
+ * memory to do so, a slow fill will be scheduled.
+ *
+ * The caller must provide serialisation (none is used here). In practise,
+ * this means this function must run from the NAPI handler, or be called
+ * when NAPI is disabled.
+ */
+void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic)
+{
+ struct efx_nic *efx = rx_queue->efx;
+ unsigned int fill_level, batch_size;
+ int space, rc = 0;
+
+ if (!rx_queue->refill_enabled)
+ return;
+
+ /* Calculate current fill level, and exit if we don't need to fill */
+ fill_level = (rx_queue->added_count - rx_queue->removed_count);
+ EFX_WARN_ON_ONCE_PARANOID(fill_level > rx_queue->efx->rxq_entries);
+ if (fill_level >= rx_queue->fast_fill_trigger)
+ goto out;
+
+ /* Record minimum fill level */
+ if (unlikely(fill_level < rx_queue->min_fill)) {
+ if (fill_level)
+ rx_queue->min_fill = fill_level;
+ }
+
+ batch_size = efx->rx_pages_per_batch * efx->rx_bufs_per_page;
+ space = rx_queue->max_fill - fill_level;
+ EFX_WARN_ON_ONCE_PARANOID(space < batch_size);
+
+ netif_vdbg(rx_queue->efx, rx_status, rx_queue->efx->net_dev,
+ "RX queue %d fast-filling descriptor ring from"
+ " level %d to level %d\n",
+ efx_rx_queue_index(rx_queue), fill_level,
+ rx_queue->max_fill);
+
+ do {
+ rc = efx_init_rx_buffers(rx_queue, atomic);
+ if (unlikely(rc)) {
+ /* Ensure that we don't leave the rx queue empty */
+ efx_schedule_slow_fill(rx_queue);
+ goto out;
+ }
+ } while ((space -= batch_size) >= batch_size);
+
+ netif_vdbg(rx_queue->efx, rx_status, rx_queue->efx->net_dev,
+ "RX queue %d fast-filled descriptor ring "
+ "to level %d\n", efx_rx_queue_index(rx_queue),
+ rx_queue->added_count - rx_queue->removed_count);
+
+ out:
+ if (rx_queue->notified_count != rx_queue->added_count)
+ efx_nic_notify_rx_desc(rx_queue);
+}
+
+/* Pass a received packet up through GRO. GRO can handle pages
+ * regardless of checksum state and skbs with a good checksum.
+ */
+void
+efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags, u8 *eh)
+{
+ struct napi_struct *napi = &channel->napi_str;
+ struct efx_nic *efx = channel->efx;
+ struct sk_buff *skb;
+
+ skb = napi_get_frags(napi);
+ if (unlikely(!skb)) {
+ struct efx_rx_queue *rx_queue;
+
+ rx_queue = efx_channel_get_rx_queue(channel);
+ efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
+ return;
+ }
+
+ if (efx->net_dev->features & NETIF_F_RXHASH)
+ skb_set_hash(skb, efx_rx_buf_hash(efx, eh),
+ PKT_HASH_TYPE_L3);
+ skb->ip_summed = ((rx_buf->flags & EFX_RX_PKT_CSUMMED) ?
+ CHECKSUM_UNNECESSARY : CHECKSUM_NONE);
+ skb->csum_level = !!(rx_buf->flags & EFX_RX_PKT_CSUM_LEVEL);
+
+ for (;;) {
+ skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
+ rx_buf->page, rx_buf->page_offset,
+ rx_buf->len);
+ rx_buf->page = NULL;
+ skb->len += rx_buf->len;
+ if (skb_shinfo(skb)->nr_frags == n_frags)
+ break;
+
+ rx_buf = efx_rx_buf_next(&channel->rx_queue, rx_buf);
+ }
+
+ skb->data_len = skb->len;
+ skb->truesize += n_frags * efx->rx_buffer_truesize;
+
+ skb_record_rx_queue(skb, channel->rx_queue.core_index);
+
+ napi_gro_frags(napi);
+}
+
+/* RSS contexts. We're using linked lists and crappy O(n) algorithms, because
+ * (a) this is an infrequent control-plane operation and (b) n is small (max 64)
+ */
+struct efx_rss_context *efx_alloc_rss_context_entry(struct efx_nic *efx)
+{
+ struct list_head *head = &efx->rss_context.list;
+ struct efx_rss_context *ctx, *new;
+ u32 id = 1; /* Don't use zero, that refers to the master RSS context */
+
+ WARN_ON(!mutex_is_locked(&efx->rss_lock));
+
+ /* Search for first gap in the numbering */
+ list_for_each_entry(ctx, head, list) {
+ if (ctx->user_id != id)
+ break;
+ id++;
+ /* Check for wrap. If this happens, we have nearly 2^32
+ * allocated RSS contexts, which seems unlikely.
+ */
+ if (WARN_ON_ONCE(!id))
+ return NULL;
+ }
+
+ /* Create the new entry */
+ new = kmalloc(sizeof(*new), GFP_KERNEL);
+ if (!new)
+ return NULL;
+ new->context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
+ new->rx_hash_udp_4tuple = false;
+
+ /* Insert the new entry into the gap */
+ new->user_id = id;
+ list_add_tail(&new->list, &ctx->list);
+ return new;
+}
+
+struct efx_rss_context *efx_find_rss_context_entry(struct efx_nic *efx, u32 id)
+{
+ struct list_head *head = &efx->rss_context.list;
+ struct efx_rss_context *ctx;
+
+ WARN_ON(!mutex_is_locked(&efx->rss_lock));
+
+ list_for_each_entry(ctx, head, list)
+ if (ctx->user_id == id)
+ return ctx;
+ return NULL;
+}
+
+void efx_free_rss_context_entry(struct efx_rss_context *ctx)
+{
+ list_del(&ctx->list);
+ kfree(ctx);
+}
+
+void efx_set_default_rx_indir_table(struct efx_nic *efx,
+ struct efx_rss_context *ctx)
+{
+ size_t i;
+
+ for (i = 0; i < ARRAY_SIZE(ctx->rx_indir_table); i++)
+ ctx->rx_indir_table[i] =
+ ethtool_rxfh_indir_default(i, efx->rss_spread);
+}
+
+/**
+ * efx_filter_is_mc_recipient - test whether spec is a multicast recipient
+ * @spec: Specification to test
+ *
+ * Return: %true if the specification is a non-drop RX filter that
+ * matches a local MAC address I/G bit value of 1 or matches a local
+ * IPv4 or IPv6 address value in the respective multicast address
+ * range. Otherwise %false.
+ */
+bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec)
+{
+ if (!(spec->flags & EFX_FILTER_FLAG_RX) ||
+ spec->dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP)
+ return false;
+
+ if (spec->match_flags &
+ (EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_LOC_MAC_IG) &&
+ is_multicast_ether_addr(spec->loc_mac))
+ return true;
+
+ if ((spec->match_flags &
+ (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_LOC_HOST)) ==
+ (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_LOC_HOST)) {
+ if (spec->ether_type == htons(ETH_P_IP) &&
+ ipv4_is_multicast(spec->loc_host[0]))
+ return true;
+ if (spec->ether_type == htons(ETH_P_IPV6) &&
+ ((const u8 *)spec->loc_host)[0] == 0xff)
+ return true;
+ }
+
+ return false;
+}
+
+bool efx_filter_spec_equal(const struct efx_filter_spec *left,
+ const struct efx_filter_spec *right)
+{
+ if ((left->match_flags ^ right->match_flags) |
+ ((left->flags ^ right->flags) &
+ (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
+ return false;
+
+ return memcmp(&left->outer_vid, &right->outer_vid,
+ sizeof(struct efx_filter_spec) -
+ offsetof(struct efx_filter_spec, outer_vid)) == 0;
+}
+
+u32 efx_filter_spec_hash(const struct efx_filter_spec *spec)
+{
+ BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
+ return jhash2((const u32 *)&spec->outer_vid,
+ (sizeof(struct efx_filter_spec) -
+ offsetof(struct efx_filter_spec, outer_vid)) / 4,
+ 0);
+}
+
+#ifdef CONFIG_RFS_ACCEL
+bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
+ bool *force)
+{
+ if (rule->filter_id == EFX_ARFS_FILTER_ID_PENDING) {
+ /* ARFS is currently updating this entry, leave it */
+ return false;
+ }
+ if (rule->filter_id == EFX_ARFS_FILTER_ID_ERROR) {
+ /* ARFS tried and failed to update this, so it's probably out
+ * of date. Remove the filter and the ARFS rule entry.
+ */
+ rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+ *force = true;
+ return true;
+ } else if (WARN_ON(rule->filter_id != filter_idx)) { /* can't happen */
+ /* ARFS has moved on, so old filter is not needed. Since we did
+ * not mark the rule with EFX_ARFS_FILTER_ID_REMOVING, it will
+ * not be removed by efx_rps_hash_del() subsequently.
+ */
+ *force = true;
+ return true;
+ }
+ /* Remove it iff ARFS wants to. */
+ return true;
+}
+
+static
+struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
+ const struct efx_filter_spec *spec)
+{
+ u32 hash = efx_filter_spec_hash(spec);
+
+ lockdep_assert_held(&efx->rps_hash_lock);
+ if (!efx->rps_hash_table)
+ return NULL;
+ return &efx->rps_hash_table[hash % EFX_ARFS_HASH_TABLE_SIZE];
+}
+
+struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
+ const struct efx_filter_spec *spec)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (!head)
+ return NULL;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec))
+ return rule;
+ }
+ return NULL;
+}
+
+struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
+ const struct efx_filter_spec *spec,
+ bool *new)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (!head)
+ return NULL;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec)) {
+ *new = false;
+ return rule;
+ }
+ }
+ rule = kmalloc(sizeof(*rule), GFP_ATOMIC);
+ *new = true;
+ if (rule) {
+ memcpy(&rule->spec, spec, sizeof(rule->spec));
+ hlist_add_head(&rule->node, head);
+ }
+ return rule;
+}
+
+void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (WARN_ON(!head))
+ return;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec)) {
+ /* Someone already reused the entry. We know that if
+ * this check doesn't fire (i.e. filter_id == REMOVING)
+ * then the REMOVING mark was put there by our caller,
+ * because caller is holding a lock on filter table and
+ * only holders of that lock set REMOVING.
+ */
+ if (rule->filter_id != EFX_ARFS_FILTER_ID_REMOVING)
+ return;
+ hlist_del(node);
+ kfree(rule);
+ return;
+ }
+ }
+ /* We didn't find it. */
+ WARN_ON(1);
+}
+#endif
+
+int efx_probe_filters(struct efx_nic *efx)
+{
+ int rc;
+
+ init_rwsem(&efx->filter_sem);
+ mutex_lock(&efx->mac_lock);
+ down_write(&efx->filter_sem);
+ rc = efx->type->filter_table_probe(efx);
+ if (rc)
+ goto out_unlock;
+
+#ifdef CONFIG_RFS_ACCEL
+ if (efx->type->offload_features & NETIF_F_NTUPLE) {
+ struct efx_channel *channel;
+ int i, success = 1;
+
+ efx_for_each_channel(channel, efx) {
+ channel->rps_flow_id =
+ kcalloc(efx->type->max_rx_ip_filters,
+ sizeof(*channel->rps_flow_id),
+ GFP_KERNEL);
+ if (!channel->rps_flow_id)
+ success = 0;
+ else
+ for (i = 0;
+ i < efx->type->max_rx_ip_filters;
+ ++i)
+ channel->rps_flow_id[i] =
+ RPS_FLOW_ID_INVALID;
+ channel->rfs_expire_index = 0;
+ channel->rfs_filter_count = 0;
+ }
+
+ if (!success) {
+ efx_for_each_channel(channel, efx)
+ kfree(channel->rps_flow_id);
+ efx->type->filter_table_remove(efx);
+ rc = -ENOMEM;
+ goto out_unlock;
+ }
+ }
+#endif
+out_unlock:
+ up_write(&efx->filter_sem);
+ mutex_unlock(&efx->mac_lock);
+ return rc;
+}
+
+void efx_remove_filters(struct efx_nic *efx)
+{
+#ifdef CONFIG_RFS_ACCEL
+ struct efx_channel *channel;
+
+ efx_for_each_channel(channel, efx) {
+ cancel_delayed_work_sync(&channel->filter_work);
+ kfree(channel->rps_flow_id);
+ }
+#endif
+ down_write(&efx->filter_sem);
+ efx->type->filter_table_remove(efx);
+ up_write(&efx->filter_sem);
+}
diff --git a/drivers/net/ethernet/sfc/rx_common.h b/drivers/net/ethernet/sfc/rx_common.h
new file mode 100644
index 0000000..c41f12a
--- /dev/null
+++ b/drivers/net/ethernet/sfc/rx_common.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EFX_RX_COMMON_H
+#define EFX_RX_COMMON_H
+
+/* Preferred number of descriptors to fill at once */
+#define EFX_RX_PREFERRED_BATCH 8U
+
+/* Each packet can consume up to ceil(max_frame_len / buffer_size) buffers */
+#define EFX_RX_MAX_FRAGS DIV_ROUND_UP(EFX_MAX_FRAME_LEN(EFX_MAX_MTU), \
+ EFX_RX_USR_BUF_SIZE)
+
+static inline u8 *efx_rx_buf_va(struct efx_rx_buffer *buf)
+{
+ return page_address(buf->page) + buf->page_offset;
+}
+
+static inline u32 efx_rx_buf_hash(struct efx_nic *efx, const u8 *eh)
+{
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+ return __le32_to_cpup((const __le32 *)(eh + efx->rx_packet_hash_offset));
+#else
+ const u8 *data = eh + efx->rx_packet_hash_offset;
+
+ return (u32)data[0] |
+ (u32)data[1] << 8 |
+ (u32)data[2] << 16 |
+ (u32)data[3] << 24;
+#endif
+}
+
+void efx_rx_slow_fill(struct timer_list *t);
+
+void efx_recycle_rx_pages(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags);
+void efx_discard_rx_packet(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags);
+
+int efx_probe_rx_queue(struct efx_rx_queue *rx_queue);
+void efx_init_rx_queue(struct efx_rx_queue *rx_queue);
+void efx_fini_rx_queue(struct efx_rx_queue *rx_queue);
+void efx_remove_rx_queue(struct efx_rx_queue *rx_queue);
+void efx_destroy_rx_queue(struct efx_rx_queue *rx_queue);
+
+void efx_init_rx_buffer(struct efx_rx_queue *rx_queue,
+ struct page *page,
+ unsigned int page_offset,
+ u16 flags);
+void efx_unmap_rx_buffer(struct efx_nic *efx, struct efx_rx_buffer *rx_buf);
+void efx_free_rx_buffers(struct efx_rx_queue *rx_queue,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int num_bufs);
+
+void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue);
+void efx_rx_config_page_split(struct efx_nic *efx);
+void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic);
+
+void
+efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags, u8 *eh);
+
+struct efx_rss_context *efx_alloc_rss_context_entry(struct efx_nic *efx);
+struct efx_rss_context *efx_find_rss_context_entry(struct efx_nic *efx, u32 id);
+void efx_free_rss_context_entry(struct efx_rss_context *ctx);
+void efx_set_default_rx_indir_table(struct efx_nic *efx,
+ struct efx_rss_context *ctx);
+
+bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec);
+bool efx_filter_spec_equal(const struct efx_filter_spec *left,
+ const struct efx_filter_spec *right);
+u32 efx_filter_spec_hash(const struct efx_filter_spec *spec);
+
+#ifdef CONFIG_RFS_ACCEL
+bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
+ bool *force);
+struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
+ const struct efx_filter_spec *spec);
+struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
+ const struct efx_filter_spec *spec,
+ bool *new);
+void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec);
+#endif
+
+int efx_probe_filters(struct efx_nic *efx);
+void efx_remove_filters(struct efx_nic *efx);
+
+#endif
diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c
index 8474cf8..1ae3690 100644
--- a/drivers/net/ethernet/sfc/selftest.c
+++ b/drivers/net/ethernet/sfc/selftest.c
@@ -18,6 +18,8 @@
#include <linux/slab.h>
#include "net_driver.h"
#include "efx.h"
+#include "efx_common.h"
+#include "efx_channels.h"
#include "nic.h"
#include "selftest.h"
#include "workarounds.h"
@@ -783,7 +785,7 @@ void efx_selftest_async_cancel(struct efx_nic *efx)
cancel_delayed_work_sync(&efx->selftest_work);
}
-void efx_selftest_async_work(struct work_struct *data)
+static void efx_selftest_async_work(struct work_struct *data)
{
struct efx_nic *efx = container_of(data, struct efx_nic,
selftest_work.work);
@@ -802,3 +804,8 @@ void efx_selftest_async_work(struct work_struct *data)
channel->channel, cpu);
}
}
+
+void efx_selftest_async_init(struct efx_nic *efx)
+{
+ INIT_DELAYED_WORK(&efx->selftest_work, efx_selftest_async_work);
+}
diff --git a/drivers/net/ethernet/sfc/selftest.h b/drivers/net/ethernet/sfc/selftest.h
index a355381..ca88ebb 100644
--- a/drivers/net/ethernet/sfc/selftest.h
+++ b/drivers/net/ethernet/sfc/selftest.h
@@ -45,8 +45,8 @@ void efx_loopback_rx_packet(struct efx_nic *efx, const char *buf_ptr,
int pkt_len);
int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests,
unsigned flags);
+void efx_selftest_async_init(struct efx_nic *efx);
void efx_selftest_async_start(struct efx_nic *efx);
void efx_selftest_async_cancel(struct efx_nic *efx);
-void efx_selftest_async_work(struct work_struct *data);
#endif /* EFX_SELFTEST_H */
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index 8149924..baa4641 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -14,12 +14,14 @@
#include "net_driver.h"
#include "bitfield.h"
#include "efx.h"
+#include "efx_common.h"
#include "nic.h"
#include "farch_regs.h"
#include "io.h"
#include "workarounds.h"
#include "mcdi.h"
#include "mcdi_pcol.h"
+#include "mcdi_port_common.h"
#include "selftest.h"
#include "siena_sriov.h"
diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c
index dfbdf05..83dcfca 100644
--- a/drivers/net/ethernet/sfc/siena_sriov.c
+++ b/drivers/net/ethernet/sfc/siena_sriov.c
@@ -7,6 +7,7 @@
#include <linux/module.h>
#include "net_driver.h"
#include "efx.h"
+#include "efx_channels.h"
#include "nic.h"
#include "io.h"
#include "mcdi.h"
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 00c1c44..04d7f41 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -20,6 +20,7 @@
#include "io.h"
#include "nic.h"
#include "tx.h"
+#include "tx_common.h"
#include "workarounds.h"
#include "ef10_regs.h"
@@ -56,72 +57,6 @@ u8 *efx_tx_get_copy_buffer_limited(struct efx_tx_queue *tx_queue,
return efx_tx_get_copy_buffer(tx_queue, buffer);
}
-static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
- struct efx_tx_buffer *buffer,
- unsigned int *pkts_compl,
- unsigned int *bytes_compl)
-{
- if (buffer->unmap_len) {
- struct device *dma_dev = &tx_queue->efx->pci_dev->dev;
- dma_addr_t unmap_addr = buffer->dma_addr - buffer->dma_offset;
- if (buffer->flags & EFX_TX_BUF_MAP_SINGLE)
- dma_unmap_single(dma_dev, unmap_addr, buffer->unmap_len,
- DMA_TO_DEVICE);
- else
- dma_unmap_page(dma_dev, unmap_addr, buffer->unmap_len,
- DMA_TO_DEVICE);
- buffer->unmap_len = 0;
- }
-
- if (buffer->flags & EFX_TX_BUF_SKB) {
- struct sk_buff *skb = (struct sk_buff *)buffer->skb;
-
- EFX_WARN_ON_PARANOID(!pkts_compl || !bytes_compl);
- (*pkts_compl)++;
- (*bytes_compl) += skb->len;
- if (tx_queue->timestamping &&
- (tx_queue->completed_timestamp_major ||
- tx_queue->completed_timestamp_minor)) {
- struct skb_shared_hwtstamps hwtstamp;
-
- hwtstamp.hwtstamp =
- efx_ptp_nic_to_kernel_time(tx_queue);
- skb_tstamp_tx(skb, &hwtstamp);
-
- tx_queue->completed_timestamp_major = 0;
- tx_queue->completed_timestamp_minor = 0;
- }
- dev_consume_skb_any((struct sk_buff *)buffer->skb);
- netif_vdbg(tx_queue->efx, tx_done, tx_queue->efx->net_dev,
- "TX queue %d transmission id %x complete\n",
- tx_queue->queue, tx_queue->read_count);
- } else if (buffer->flags & EFX_TX_BUF_XDP) {
- xdp_return_frame_rx_napi(buffer->xdpf);
- }
-
- buffer->len = 0;
- buffer->flags = 0;
-}
-
-unsigned int efx_tx_max_skb_descs(struct efx_nic *efx)
-{
- /* Header and payload descriptor for each output segment, plus
- * one for every input fragment boundary within a segment
- */
- unsigned int max_descs = EFX_TSO_MAX_SEGS * 2 + MAX_SKB_FRAGS;
-
- /* Possibly one more per segment for option descriptors */
- if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0)
- max_descs += EFX_TSO_MAX_SEGS;
-
- /* Possibly more for PCIe page boundaries within input fragments */
- if (PAGE_SIZE > EFX_PAGE_SIZE)
- max_descs += max_t(unsigned int, MAX_SKB_FRAGS,
- DIV_ROUND_UP(GSO_MAX_SIZE, EFX_PAGE_SIZE));
-
- return max_descs;
-}
-
static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1)
{
/* We need to consider both queues that the net core sees as one */
@@ -333,125 +268,6 @@ static int efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue,
}
#endif /* EFX_USE_PIO */
-static struct efx_tx_buffer *efx_tx_map_chunk(struct efx_tx_queue *tx_queue,
- dma_addr_t dma_addr,
- size_t len)
-{
- const struct efx_nic_type *nic_type = tx_queue->efx->type;
- struct efx_tx_buffer *buffer;
- unsigned int dma_len;
-
- /* Map the fragment taking account of NIC-dependent DMA limits. */
- do {
- buffer = efx_tx_queue_get_insert_buffer(tx_queue);
- dma_len = nic_type->tx_limit_len(tx_queue, dma_addr, len);
-
- buffer->len = dma_len;
- buffer->dma_addr = dma_addr;
- buffer->flags = EFX_TX_BUF_CONT;
- len -= dma_len;
- dma_addr += dma_len;
- ++tx_queue->insert_count;
- } while (len);
-
- return buffer;
-}
-
-/* Map all data from an SKB for DMA and create descriptors on the queue.
- */
-static int efx_tx_map_data(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
- unsigned int segment_count)
-{
- struct efx_nic *efx = tx_queue->efx;
- struct device *dma_dev = &efx->pci_dev->dev;
- unsigned int frag_index, nr_frags;
- dma_addr_t dma_addr, unmap_addr;
- unsigned short dma_flags;
- size_t len, unmap_len;
-
- nr_frags = skb_shinfo(skb)->nr_frags;
- frag_index = 0;
-
- /* Map header data. */
- len = skb_headlen(skb);
- dma_addr = dma_map_single(dma_dev, skb->data, len, DMA_TO_DEVICE);
- dma_flags = EFX_TX_BUF_MAP_SINGLE;
- unmap_len = len;
- unmap_addr = dma_addr;
-
- if (unlikely(dma_mapping_error(dma_dev, dma_addr)))
- return -EIO;
-
- if (segment_count) {
- /* For TSO we need to put the header in to a separate
- * descriptor. Map this separately if necessary.
- */
- size_t header_len = skb_transport_header(skb) - skb->data +
- (tcp_hdr(skb)->doff << 2u);
-
- if (header_len != len) {
- tx_queue->tso_long_headers++;
- efx_tx_map_chunk(tx_queue, dma_addr, header_len);
- len -= header_len;
- dma_addr += header_len;
- }
- }
-
- /* Add descriptors for each fragment. */
- do {
- struct efx_tx_buffer *buffer;
- skb_frag_t *fragment;
-
- buffer = efx_tx_map_chunk(tx_queue, dma_addr, len);
-
- /* The final descriptor for a fragment is responsible for
- * unmapping the whole fragment.
- */
- buffer->flags = EFX_TX_BUF_CONT | dma_flags;
- buffer->unmap_len = unmap_len;
- buffer->dma_offset = buffer->dma_addr - unmap_addr;
-
- if (frag_index >= nr_frags) {
- /* Store SKB details with the final buffer for
- * the completion.
- */
- buffer->skb = skb;
- buffer->flags = EFX_TX_BUF_SKB | dma_flags;
- return 0;
- }
-
- /* Move on to the next fragment. */
- fragment = &skb_shinfo(skb)->frags[frag_index++];
- len = skb_frag_size(fragment);
- dma_addr = skb_frag_dma_map(dma_dev, fragment,
- 0, len, DMA_TO_DEVICE);
- dma_flags = 0;
- unmap_len = len;
- unmap_addr = dma_addr;
-
- if (unlikely(dma_mapping_error(dma_dev, dma_addr)))
- return -EIO;
- } while (1);
-}
-
-/* Remove buffers put into a tx_queue for the current packet.
- * None of the buffers must have an skb attached.
- */
-static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue,
- unsigned int insert_count)
-{
- struct efx_tx_buffer *buffer;
- unsigned int bytes_compl = 0;
- unsigned int pkts_compl = 0;
-
- /* Work backwards until we hit the original insert pointer value */
- while (tx_queue->insert_count != insert_count) {
- --tx_queue->insert_count;
- buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
- efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
- }
-}
-
/*
* Fallback to software TSO.
*
@@ -473,12 +289,9 @@ static int efx_tx_tso_fallback(struct efx_tx_queue *tx_queue,
dev_consume_skb_any(skb);
skb = segments;
- while (skb) {
- next = skb->next;
- skb->next = NULL;
-
+ skb_list_walk_safe(skb, skb, next) {
+ skb_mark_not_on_list(skb);
efx_enqueue_skb(tx_queue, skb);
- skb = next;
}
return 0;
@@ -687,41 +500,6 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs,
return i;
}
-/* Remove packets from the TX queue
- *
- * This removes packets from the TX queue, up to and including the
- * specified index.
- */
-static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue,
- unsigned int index,
- unsigned int *pkts_compl,
- unsigned int *bytes_compl)
-{
- struct efx_nic *efx = tx_queue->efx;
- unsigned int stop_index, read_ptr;
-
- stop_index = (index + 1) & tx_queue->ptr_mask;
- read_ptr = tx_queue->read_count & tx_queue->ptr_mask;
-
- while (read_ptr != stop_index) {
- struct efx_tx_buffer *buffer = &tx_queue->buffer[read_ptr];
-
- if (!(buffer->flags & EFX_TX_BUF_OPTION) &&
- unlikely(buffer->len == 0)) {
- netif_err(efx, tx_err, efx->net_dev,
- "TX queue %d spurious TX completion id %x\n",
- tx_queue->queue, read_ptr);
- efx_schedule_reset(efx, RESET_TYPE_TX_SKIP);
- return;
- }
-
- efx_dequeue_buffer(tx_queue, buffer, pkts_compl, bytes_compl);
-
- ++tx_queue->read_count;
- read_ptr = tx_queue->read_count & tx_queue->ptr_mask;
- }
-}
-
/* Initiate a packet transmission. We use one channel per CPU
* (sharing when we have more CPUs than channels). On Falcon, the TX
* completion events will be directed back to the CPU that transmitted
@@ -834,173 +612,3 @@ int efx_setup_tc(struct net_device *net_dev, enum tc_setup_type type,
net_dev->num_tc = num_tc;
return 0;
}
-
-void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
-{
- unsigned fill_level;
- struct efx_nic *efx = tx_queue->efx;
- struct efx_tx_queue *txq2;
- unsigned int pkts_compl = 0, bytes_compl = 0;
-
- EFX_WARN_ON_ONCE_PARANOID(index > tx_queue->ptr_mask);
-
- efx_dequeue_buffers(tx_queue, index, &pkts_compl, &bytes_compl);
- tx_queue->pkts_compl += pkts_compl;
- tx_queue->bytes_compl += bytes_compl;
-
- if (pkts_compl > 1)
- ++tx_queue->merge_events;
-
- /* See if we need to restart the netif queue. This memory
- * barrier ensures that we write read_count (inside
- * efx_dequeue_buffers()) before reading the queue status.
- */
- smp_mb();
- if (unlikely(netif_tx_queue_stopped(tx_queue->core_txq)) &&
- likely(efx->port_enabled) &&
- likely(netif_device_present(efx->net_dev))) {
- txq2 = efx_tx_queue_partner(tx_queue);
- fill_level = max(tx_queue->insert_count - tx_queue->read_count,
- txq2->insert_count - txq2->read_count);
- if (fill_level <= efx->txq_wake_thresh)
- netif_tx_wake_queue(tx_queue->core_txq);
- }
-
- /* Check whether the hardware queue is now empty */
- if ((int)(tx_queue->read_count - tx_queue->old_write_count) >= 0) {
- tx_queue->old_write_count = READ_ONCE(tx_queue->write_count);
- if (tx_queue->read_count == tx_queue->old_write_count) {
- smp_mb();
- tx_queue->empty_read_count =
- tx_queue->read_count | EFX_EMPTY_COUNT_VALID;
- }
- }
-}
-
-static unsigned int efx_tx_cb_page_count(struct efx_tx_queue *tx_queue)
-{
- return DIV_ROUND_UP(tx_queue->ptr_mask + 1, PAGE_SIZE >> EFX_TX_CB_ORDER);
-}
-
-int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
-{
- struct efx_nic *efx = tx_queue->efx;
- unsigned int entries;
- int rc;
-
- /* Create the smallest power-of-two aligned ring */
- entries = max(roundup_pow_of_two(efx->txq_entries), EFX_MIN_DMAQ_SIZE);
- EFX_WARN_ON_PARANOID(entries > EFX_MAX_DMAQ_SIZE);
- tx_queue->ptr_mask = entries - 1;
-
- netif_dbg(efx, probe, efx->net_dev,
- "creating TX queue %d size %#x mask %#x\n",
- tx_queue->queue, efx->txq_entries, tx_queue->ptr_mask);
-
- /* Allocate software ring */
- tx_queue->buffer = kcalloc(entries, sizeof(*tx_queue->buffer),
- GFP_KERNEL);
- if (!tx_queue->buffer)
- return -ENOMEM;
-
- tx_queue->cb_page = kcalloc(efx_tx_cb_page_count(tx_queue),
- sizeof(tx_queue->cb_page[0]), GFP_KERNEL);
- if (!tx_queue->cb_page) {
- rc = -ENOMEM;
- goto fail1;
- }
-
- /* Allocate hardware ring */
- rc = efx_nic_probe_tx(tx_queue);
- if (rc)
- goto fail2;
-
- return 0;
-
-fail2:
- kfree(tx_queue->cb_page);
- tx_queue->cb_page = NULL;
-fail1:
- kfree(tx_queue->buffer);
- tx_queue->buffer = NULL;
- return rc;
-}
-
-void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
-{
- struct efx_nic *efx = tx_queue->efx;
-
- netif_dbg(efx, drv, efx->net_dev,
- "initialising TX queue %d\n", tx_queue->queue);
-
- tx_queue->insert_count = 0;
- tx_queue->write_count = 0;
- tx_queue->packet_write_count = 0;
- tx_queue->old_write_count = 0;
- tx_queue->read_count = 0;
- tx_queue->old_read_count = 0;
- tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID;
- tx_queue->xmit_more_available = false;
- tx_queue->timestamping = (efx_ptp_use_mac_tx_timestamps(efx) &&
- tx_queue->channel == efx_ptp_channel(efx));
- tx_queue->completed_desc_ptr = tx_queue->ptr_mask;
- tx_queue->completed_timestamp_major = 0;
- tx_queue->completed_timestamp_minor = 0;
-
- tx_queue->xdp_tx = efx_channel_is_xdp_tx(tx_queue->channel);
-
- /* Set up default function pointers. These may get replaced by
- * efx_nic_init_tx() based off NIC/queue capabilities.
- */
- tx_queue->handle_tso = efx_enqueue_skb_tso;
-
- /* Set up TX descriptor ring */
- efx_nic_init_tx(tx_queue);
-
- tx_queue->initialised = true;
-}
-
-void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
-{
- struct efx_tx_buffer *buffer;
-
- netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev,
- "shutting down TX queue %d\n", tx_queue->queue);
-
- if (!tx_queue->buffer)
- return;
-
- /* Free any buffers left in the ring */
- while (tx_queue->read_count != tx_queue->write_count) {
- unsigned int pkts_compl = 0, bytes_compl = 0;
- buffer = &tx_queue->buffer[tx_queue->read_count & tx_queue->ptr_mask];
- efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
-
- ++tx_queue->read_count;
- }
- tx_queue->xmit_more_available = false;
- netdev_tx_reset_queue(tx_queue->core_txq);
-}
-
-void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
-{
- int i;
-
- if (!tx_queue->buffer)
- return;
-
- netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev,
- "destroying TX queue %d\n", tx_queue->queue);
- efx_nic_remove_tx(tx_queue);
-
- if (tx_queue->cb_page) {
- for (i = 0; i < efx_tx_cb_page_count(tx_queue); i++)
- efx_nic_free_buffer(tx_queue->efx,
- &tx_queue->cb_page[i]);
- kfree(tx_queue->cb_page);
- tx_queue->cb_page = NULL;
- }
-
- kfree(tx_queue->buffer);
- tx_queue->buffer = NULL;
-}
diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c
new file mode 100644
index 0000000..b1571e9
--- /dev/null
+++ b/drivers/net/ethernet/sfc/tx_common.c
@@ -0,0 +1,404 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include "net_driver.h"
+#include "efx.h"
+#include "nic.h"
+#include "tx_common.h"
+
+static unsigned int efx_tx_cb_page_count(struct efx_tx_queue *tx_queue)
+{
+ return DIV_ROUND_UP(tx_queue->ptr_mask + 1,
+ PAGE_SIZE >> EFX_TX_CB_ORDER);
+}
+
+int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
+{
+ struct efx_nic *efx = tx_queue->efx;
+ unsigned int entries;
+ int rc;
+
+ /* Create the smallest power-of-two aligned ring */
+ entries = max(roundup_pow_of_two(efx->txq_entries), EFX_MIN_DMAQ_SIZE);
+ EFX_WARN_ON_PARANOID(entries > EFX_MAX_DMAQ_SIZE);
+ tx_queue->ptr_mask = entries - 1;
+
+ netif_dbg(efx, probe, efx->net_dev,
+ "creating TX queue %d size %#x mask %#x\n",
+ tx_queue->queue, efx->txq_entries, tx_queue->ptr_mask);
+
+ /* Allocate software ring */
+ tx_queue->buffer = kcalloc(entries, sizeof(*tx_queue->buffer),
+ GFP_KERNEL);
+ if (!tx_queue->buffer)
+ return -ENOMEM;
+
+ tx_queue->cb_page = kcalloc(efx_tx_cb_page_count(tx_queue),
+ sizeof(tx_queue->cb_page[0]), GFP_KERNEL);
+ if (!tx_queue->cb_page) {
+ rc = -ENOMEM;
+ goto fail1;
+ }
+
+ /* Allocate hardware ring */
+ rc = efx_nic_probe_tx(tx_queue);
+ if (rc)
+ goto fail2;
+
+ return 0;
+
+fail2:
+ kfree(tx_queue->cb_page);
+ tx_queue->cb_page = NULL;
+fail1:
+ kfree(tx_queue->buffer);
+ tx_queue->buffer = NULL;
+ return rc;
+}
+
+void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
+{
+ struct efx_nic *efx = tx_queue->efx;
+
+ netif_dbg(efx, drv, efx->net_dev,
+ "initialising TX queue %d\n", tx_queue->queue);
+
+ tx_queue->insert_count = 0;
+ tx_queue->write_count = 0;
+ tx_queue->packet_write_count = 0;
+ tx_queue->old_write_count = 0;
+ tx_queue->read_count = 0;
+ tx_queue->old_read_count = 0;
+ tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID;
+ tx_queue->xmit_more_available = false;
+ tx_queue->timestamping = (efx_ptp_use_mac_tx_timestamps(efx) &&
+ tx_queue->channel == efx_ptp_channel(efx));
+ tx_queue->completed_desc_ptr = tx_queue->ptr_mask;
+ tx_queue->completed_timestamp_major = 0;
+ tx_queue->completed_timestamp_minor = 0;
+
+ tx_queue->xdp_tx = efx_channel_is_xdp_tx(tx_queue->channel);
+
+ /* Set up default function pointers. These may get replaced by
+ * efx_nic_init_tx() based off NIC/queue capabilities.
+ */
+ tx_queue->handle_tso = efx_enqueue_skb_tso;
+
+ /* Set up TX descriptor ring */
+ efx_nic_init_tx(tx_queue);
+
+ tx_queue->initialised = true;
+}
+
+void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
+{
+ struct efx_tx_buffer *buffer;
+
+ netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev,
+ "shutting down TX queue %d\n", tx_queue->queue);
+
+ if (!tx_queue->buffer)
+ return;
+
+ /* Free any buffers left in the ring */
+ while (tx_queue->read_count != tx_queue->write_count) {
+ unsigned int pkts_compl = 0, bytes_compl = 0;
+
+ buffer = &tx_queue->buffer[tx_queue->read_count & tx_queue->ptr_mask];
+ efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
+
+ ++tx_queue->read_count;
+ }
+ tx_queue->xmit_more_available = false;
+ netdev_tx_reset_queue(tx_queue->core_txq);
+}
+
+void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
+{
+ int i;
+
+ if (!tx_queue->buffer)
+ return;
+
+ netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev,
+ "destroying TX queue %d\n", tx_queue->queue);
+ efx_nic_remove_tx(tx_queue);
+
+ if (tx_queue->cb_page) {
+ for (i = 0; i < efx_tx_cb_page_count(tx_queue); i++)
+ efx_nic_free_buffer(tx_queue->efx,
+ &tx_queue->cb_page[i]);
+ kfree(tx_queue->cb_page);
+ tx_queue->cb_page = NULL;
+ }
+
+ kfree(tx_queue->buffer);
+ tx_queue->buffer = NULL;
+}
+
+void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
+ struct efx_tx_buffer *buffer,
+ unsigned int *pkts_compl,
+ unsigned int *bytes_compl)
+{
+ if (buffer->unmap_len) {
+ struct device *dma_dev = &tx_queue->efx->pci_dev->dev;
+ dma_addr_t unmap_addr = buffer->dma_addr - buffer->dma_offset;
+
+ if (buffer->flags & EFX_TX_BUF_MAP_SINGLE)
+ dma_unmap_single(dma_dev, unmap_addr, buffer->unmap_len,
+ DMA_TO_DEVICE);
+ else
+ dma_unmap_page(dma_dev, unmap_addr, buffer->unmap_len,
+ DMA_TO_DEVICE);
+ buffer->unmap_len = 0;
+ }
+
+ if (buffer->flags & EFX_TX_BUF_SKB) {
+ struct sk_buff *skb = (struct sk_buff *)buffer->skb;
+
+ EFX_WARN_ON_PARANOID(!pkts_compl || !bytes_compl);
+ (*pkts_compl)++;
+ (*bytes_compl) += skb->len;
+ if (tx_queue->timestamping &&
+ (tx_queue->completed_timestamp_major ||
+ tx_queue->completed_timestamp_minor)) {
+ struct skb_shared_hwtstamps hwtstamp;
+
+ hwtstamp.hwtstamp =
+ efx_ptp_nic_to_kernel_time(tx_queue);
+ skb_tstamp_tx(skb, &hwtstamp);
+
+ tx_queue->completed_timestamp_major = 0;
+ tx_queue->completed_timestamp_minor = 0;
+ }
+ dev_consume_skb_any((struct sk_buff *)buffer->skb);
+ netif_vdbg(tx_queue->efx, tx_done, tx_queue->efx->net_dev,
+ "TX queue %d transmission id %x complete\n",
+ tx_queue->queue, tx_queue->read_count);
+ } else if (buffer->flags & EFX_TX_BUF_XDP) {
+ xdp_return_frame_rx_napi(buffer->xdpf);
+ }
+
+ buffer->len = 0;
+ buffer->flags = 0;
+}
+
+/* Remove packets from the TX queue
+ *
+ * This removes packets from the TX queue, up to and including the
+ * specified index.
+ */
+static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue,
+ unsigned int index,
+ unsigned int *pkts_compl,
+ unsigned int *bytes_compl)
+{
+ struct efx_nic *efx = tx_queue->efx;
+ unsigned int stop_index, read_ptr;
+
+ stop_index = (index + 1) & tx_queue->ptr_mask;
+ read_ptr = tx_queue->read_count & tx_queue->ptr_mask;
+
+ while (read_ptr != stop_index) {
+ struct efx_tx_buffer *buffer = &tx_queue->buffer[read_ptr];
+
+ if (!(buffer->flags & EFX_TX_BUF_OPTION) &&
+ unlikely(buffer->len == 0)) {
+ netif_err(efx, tx_err, efx->net_dev,
+ "TX queue %d spurious TX completion id %x\n",
+ tx_queue->queue, read_ptr);
+ efx_schedule_reset(efx, RESET_TYPE_TX_SKIP);
+ return;
+ }
+
+ efx_dequeue_buffer(tx_queue, buffer, pkts_compl, bytes_compl);
+
+ ++tx_queue->read_count;
+ read_ptr = tx_queue->read_count & tx_queue->ptr_mask;
+ }
+}
+
+void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
+{
+ unsigned int fill_level, pkts_compl = 0, bytes_compl = 0;
+ struct efx_nic *efx = tx_queue->efx;
+ struct efx_tx_queue *txq2;
+
+ EFX_WARN_ON_ONCE_PARANOID(index > tx_queue->ptr_mask);
+
+ efx_dequeue_buffers(tx_queue, index, &pkts_compl, &bytes_compl);
+ tx_queue->pkts_compl += pkts_compl;
+ tx_queue->bytes_compl += bytes_compl;
+
+ if (pkts_compl > 1)
+ ++tx_queue->merge_events;
+
+ /* See if we need to restart the netif queue. This memory
+ * barrier ensures that we write read_count (inside
+ * efx_dequeue_buffers()) before reading the queue status.
+ */
+ smp_mb();
+ if (unlikely(netif_tx_queue_stopped(tx_queue->core_txq)) &&
+ likely(efx->port_enabled) &&
+ likely(netif_device_present(efx->net_dev))) {
+ txq2 = efx_tx_queue_partner(tx_queue);
+ fill_level = max(tx_queue->insert_count - tx_queue->read_count,
+ txq2->insert_count - txq2->read_count);
+ if (fill_level <= efx->txq_wake_thresh)
+ netif_tx_wake_queue(tx_queue->core_txq);
+ }
+
+ /* Check whether the hardware queue is now empty */
+ if ((int)(tx_queue->read_count - tx_queue->old_write_count) >= 0) {
+ tx_queue->old_write_count = READ_ONCE(tx_queue->write_count);
+ if (tx_queue->read_count == tx_queue->old_write_count) {
+ smp_mb();
+ tx_queue->empty_read_count =
+ tx_queue->read_count | EFX_EMPTY_COUNT_VALID;
+ }
+ }
+}
+
+/* Remove buffers put into a tx_queue for the current packet.
+ * None of the buffers must have an skb attached.
+ */
+void efx_enqueue_unwind(struct efx_tx_queue *tx_queue,
+ unsigned int insert_count)
+{
+ struct efx_tx_buffer *buffer;
+ unsigned int bytes_compl = 0;
+ unsigned int pkts_compl = 0;
+
+ /* Work backwards until we hit the original insert pointer value */
+ while (tx_queue->insert_count != insert_count) {
+ --tx_queue->insert_count;
+ buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
+ efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
+ }
+}
+
+struct efx_tx_buffer *efx_tx_map_chunk(struct efx_tx_queue *tx_queue,
+ dma_addr_t dma_addr, size_t len)
+{
+ const struct efx_nic_type *nic_type = tx_queue->efx->type;
+ struct efx_tx_buffer *buffer;
+ unsigned int dma_len;
+
+ /* Map the fragment taking account of NIC-dependent DMA limits. */
+ do {
+ buffer = efx_tx_queue_get_insert_buffer(tx_queue);
+ dma_len = nic_type->tx_limit_len(tx_queue, dma_addr, len);
+
+ buffer->len = dma_len;
+ buffer->dma_addr = dma_addr;
+ buffer->flags = EFX_TX_BUF_CONT;
+ len -= dma_len;
+ dma_addr += dma_len;
+ ++tx_queue->insert_count;
+ } while (len);
+
+ return buffer;
+}
+
+/* Map all data from an SKB for DMA and create descriptors on the queue. */
+int efx_tx_map_data(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
+ unsigned int segment_count)
+{
+ struct efx_nic *efx = tx_queue->efx;
+ struct device *dma_dev = &efx->pci_dev->dev;
+ unsigned int frag_index, nr_frags;
+ dma_addr_t dma_addr, unmap_addr;
+ unsigned short dma_flags;
+ size_t len, unmap_len;
+
+ nr_frags = skb_shinfo(skb)->nr_frags;
+ frag_index = 0;
+
+ /* Map header data. */
+ len = skb_headlen(skb);
+ dma_addr = dma_map_single(dma_dev, skb->data, len, DMA_TO_DEVICE);
+ dma_flags = EFX_TX_BUF_MAP_SINGLE;
+ unmap_len = len;
+ unmap_addr = dma_addr;
+
+ if (unlikely(dma_mapping_error(dma_dev, dma_addr)))
+ return -EIO;
+
+ if (segment_count) {
+ /* For TSO we need to put the header in to a separate
+ * descriptor. Map this separately if necessary.
+ */
+ size_t header_len = skb_transport_header(skb) - skb->data +
+ (tcp_hdr(skb)->doff << 2u);
+
+ if (header_len != len) {
+ tx_queue->tso_long_headers++;
+ efx_tx_map_chunk(tx_queue, dma_addr, header_len);
+ len -= header_len;
+ dma_addr += header_len;
+ }
+ }
+
+ /* Add descriptors for each fragment. */
+ do {
+ struct efx_tx_buffer *buffer;
+ skb_frag_t *fragment;
+
+ buffer = efx_tx_map_chunk(tx_queue, dma_addr, len);
+
+ /* The final descriptor for a fragment is responsible for
+ * unmapping the whole fragment.
+ */
+ buffer->flags = EFX_TX_BUF_CONT | dma_flags;
+ buffer->unmap_len = unmap_len;
+ buffer->dma_offset = buffer->dma_addr - unmap_addr;
+
+ if (frag_index >= nr_frags) {
+ /* Store SKB details with the final buffer for
+ * the completion.
+ */
+ buffer->skb = skb;
+ buffer->flags = EFX_TX_BUF_SKB | dma_flags;
+ return 0;
+ }
+
+ /* Move on to the next fragment. */
+ fragment = &skb_shinfo(skb)->frags[frag_index++];
+ len = skb_frag_size(fragment);
+ dma_addr = skb_frag_dma_map(dma_dev, fragment, 0, len,
+ DMA_TO_DEVICE);
+ dma_flags = 0;
+ unmap_len = len;
+ unmap_addr = dma_addr;
+
+ if (unlikely(dma_mapping_error(dma_dev, dma_addr)))
+ return -EIO;
+ } while (1);
+}
+
+unsigned int efx_tx_max_skb_descs(struct efx_nic *efx)
+{
+ /* Header and payload descriptor for each output segment, plus
+ * one for every input fragment boundary within a segment
+ */
+ unsigned int max_descs = EFX_TSO_MAX_SEGS * 2 + MAX_SKB_FRAGS;
+
+ /* Possibly one more per segment for option descriptors */
+ if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0)
+ max_descs += EFX_TSO_MAX_SEGS;
+
+ /* Possibly more for PCIe page boundaries within input fragments */
+ if (PAGE_SIZE > EFX_PAGE_SIZE)
+ max_descs += max_t(unsigned int, MAX_SKB_FRAGS,
+ DIV_ROUND_UP(GSO_MAX_SIZE, EFX_PAGE_SIZE));
+
+ return max_descs;
+}
diff --git a/drivers/net/ethernet/sfc/tx_common.h b/drivers/net/ethernet/sfc/tx_common.h
new file mode 100644
index 0000000..f92f1fe
--- /dev/null
+++ b/drivers/net/ethernet/sfc/tx_common.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2018 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EFX_TX_COMMON_H
+#define EFX_TX_COMMON_H
+
+int efx_probe_tx_queue(struct efx_tx_queue *tx_queue);
+void efx_init_tx_queue(struct efx_tx_queue *tx_queue);
+void efx_fini_tx_queue(struct efx_tx_queue *tx_queue);
+void efx_remove_tx_queue(struct efx_tx_queue *tx_queue);
+
+void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
+ struct efx_tx_buffer *buffer,
+ unsigned int *pkts_compl,
+ unsigned int *bytes_compl);
+
+void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index);
+
+void efx_enqueue_unwind(struct efx_tx_queue *tx_queue,
+ unsigned int insert_count);
+
+struct efx_tx_buffer *efx_tx_map_chunk(struct efx_tx_queue *tx_queue,
+ dma_addr_t dma_addr, size_t len);
+int efx_tx_map_data(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
+ unsigned int segment_count);
+
+unsigned int efx_tx_max_skb_descs(struct efx_nic *efx);
+
+#endif
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 912760e8..61ddee0 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -280,6 +280,7 @@ struct epic_private {
signed char phys[4]; /* MII device addresses. */
u16 advertising; /* NWay media advertisement */
int mii_phy_cnt;
+ u32 ethtool_ops_nesting;
struct mii_if_info mii;
unsigned int tx_full:1; /* The Tx queue is full. */
unsigned int default_port:4; /* Last dev->if_port value. */
@@ -1435,8 +1436,10 @@ static int ethtool_begin(struct net_device *dev)
struct epic_private *ep = netdev_priv(dev);
void __iomem *ioaddr = ep->ioaddr;
+ if (ep->ethtool_ops_nesting == U32_MAX)
+ return -EBUSY;
/* power-up, if interface is down */
- if (!netif_running(dev)) {
+ if (!ep->ethtool_ops_nesting++ && !netif_running(dev)) {
ew32(GENCTL, 0x0200);
ew32(NVCTL, (er32(NVCTL) & ~0x003c) | 0x4800);
}
@@ -1449,7 +1452,7 @@ static void ethtool_complete(struct net_device *dev)
void __iomem *ioaddr = ep->ioaddr;
/* power-down, if interface is down */
- if (!netif_running(dev)) {
+ if (!--ep->ethtool_ops_nesting && !netif_running(dev)) {
ew32(GENCTL, 0x0008);
ew32(NVCTL, (er32(NVCTL) & ~0x483c) | 0x0000);
}
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 38068fc..7dc2154 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -1943,15 +1943,6 @@ static int smsc911x_set_mac_address(struct net_device *dev, void *p)
return 0;
}
-/* Standard ioctls for mii-tool */
-static int smsc911x_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
- if (!netif_running(dev) || !dev->phydev)
- return -EINVAL;
-
- return phy_mii_ioctl(dev->phydev, ifr, cmd);
-}
-
static void smsc911x_ethtool_getdrvinfo(struct net_device *dev,
struct ethtool_drvinfo *info)
{
@@ -2151,7 +2142,7 @@ static const struct net_device_ops smsc911x_netdev_ops = {
.ndo_start_xmit = smsc911x_hard_start_xmit,
.ndo_get_stats = smsc911x_get_stats,
.ndo_set_rx_mode = smsc911x_set_multicast_list,
- .ndo_do_ioctl = smsc911x_do_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = smsc911x_set_mac_address,
#ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c
index a6962a4..7312e52 100644
--- a/drivers/net/ethernet/smsc/smsc9420.c
+++ b/drivers/net/ethernet/smsc/smsc9420.c
@@ -210,15 +210,6 @@ static int smsc9420_eeprom_reload(struct smsc9420_pdata *pd)
return -EIO;
}
-/* Standard ioctls for mii-tool */
-static int smsc9420_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
- if (!netif_running(dev) || !dev->phydev)
- return -EINVAL;
-
- return phy_mii_ioctl(dev->phydev, ifr, cmd);
-}
-
static void smsc9420_ethtool_get_drvinfo(struct net_device *netdev,
struct ethtool_drvinfo *drvinfo)
{
@@ -1504,7 +1495,7 @@ static const struct net_device_ops smsc9420_netdev_ops = {
.ndo_start_xmit = smsc9420_hard_start_xmit,
.ndo_get_stats = smsc9420_get_stats,
.ndo_set_rx_mode = smsc9420_set_multicast_list,
- .ndo_do_ioctl = smsc9420_do_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
#ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index b5a9e94..e8224b5 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -243,6 +243,7 @@
NET_IP_ALIGN)
#define NETSEC_RX_BUF_NON_DATA (NETSEC_RXBUF_HEADROOM + \
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define NETSEC_RX_BUF_SIZE (PAGE_SIZE - NETSEC_RX_BUF_NON_DATA)
#define DESC_SZ sizeof(struct netsec_de)
@@ -719,7 +720,6 @@ static void *netsec_alloc_rx_data(struct netsec_priv *priv,
{
struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
- enum dma_data_direction dma_dir;
struct page *page;
page = page_pool_dev_alloc_pages(dring->page_pool);
@@ -734,9 +734,7 @@ static void *netsec_alloc_rx_data(struct netsec_priv *priv,
/* Make sure the incoming payload fits in the page for XDP and non-XDP
* cases and reserve enough space for headroom + skb_shared_info
*/
- *desc_len = PAGE_SIZE - NETSEC_RX_BUF_NON_DATA;
- dma_dir = page_pool_get_dma_dir(dring->page_pool);
- dma_sync_single_for_device(priv->dev, *dma_handle, *desc_len, dma_dir);
+ *desc_len = NETSEC_RX_BUF_SIZE;
return page_address(page);
}
@@ -883,6 +881,8 @@ static u32 netsec_xdp_xmit_back(struct netsec_priv *priv, struct xdp_buff *xdp)
static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
struct xdp_buff *xdp)
{
+ struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
+ unsigned int len = xdp->data_end - xdp->data;
u32 ret = NETSEC_XDP_PASS;
int err;
u32 act;
@@ -896,7 +896,9 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
case XDP_TX:
ret = netsec_xdp_xmit_back(priv, xdp);
if (ret != NETSEC_XDP_TX)
- xdp_return_buff(xdp);
+ __page_pool_put_page(dring->page_pool,
+ virt_to_head_page(xdp->data),
+ len, true);
break;
case XDP_REDIRECT:
err = xdp_do_redirect(priv->ndev, xdp, prog);
@@ -904,7 +906,9 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
ret = NETSEC_XDP_REDIR;
} else {
ret = NETSEC_XDP_CONSUMED;
- xdp_return_buff(xdp);
+ __page_pool_put_page(dring->page_pool,
+ virt_to_head_page(xdp->data),
+ len, true);
}
break;
default:
@@ -915,7 +919,9 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
/* fall through -- handle aborts by dropping packet */
case XDP_DROP:
ret = NETSEC_XDP_CONSUMED;
- xdp_return_buff(xdp);
+ __page_pool_put_page(dring->page_pool,
+ virt_to_head_page(xdp->data),
+ len, true);
break;
}
@@ -929,7 +935,6 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
struct netsec_rx_pkt_info rx_info;
enum dma_data_direction dma_dir;
struct bpf_prog *xdp_prog;
- struct sk_buff *skb = NULL;
u16 xdp_xmit = 0;
u32 xdp_act = 0;
int done = 0;
@@ -943,7 +948,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
struct netsec_desc *desc = &dring->desc[idx];
struct page *page = virt_to_page(desc->addr);
- u32 xdp_result = XDP_PASS;
+ u32 xdp_result = NETSEC_XDP_PASS;
+ struct sk_buff *skb = NULL;
u16 pkt_len, desc_len;
dma_addr_t dma_handle;
struct xdp_buff xdp;
@@ -1014,7 +1020,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
* cache state. Since we paid the allocation cost if
* building an skb fails try to put the page into cache
*/
- page_pool_recycle_direct(dring->page_pool, page);
+ __page_pool_put_page(dring->page_pool, page,
+ pkt_len, true);
netif_err(priv, drv, priv->ndev,
"rx failed to build skb\n");
break;
@@ -1272,17 +1279,19 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
{
struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
struct bpf_prog *xdp_prog = READ_ONCE(priv->xdp_prog);
- struct page_pool_params pp_params = { 0 };
+ struct page_pool_params pp_params = {
+ .order = 0,
+ /* internal DMA mapping in page_pool */
+ .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+ .pool_size = DESC_NUM,
+ .nid = NUMA_NO_NODE,
+ .dev = priv->dev,
+ .dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
+ .offset = NETSEC_RXBUF_HEADROOM,
+ .max_len = NETSEC_RX_BUF_SIZE,
+ };
int i, err;
- pp_params.order = 0;
- /* internal DMA mapping in page_pool */
- pp_params.flags = PP_FLAG_DMA_MAP;
- pp_params.pool_size = DESC_NUM;
- pp_params.nid = NUMA_NO_NODE;
- pp_params.dev = priv->dev;
- pp_params.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-
dring->page_pool = page_pool_create(&pp_params);
if (IS_ERR(dring->page_pool)) {
err = PTR_ERR(dring->page_pool);
@@ -1731,12 +1740,6 @@ static int netsec_netdev_set_features(struct net_device *ndev,
return 0;
}
-static int netsec_netdev_ioctl(struct net_device *ndev, struct ifreq *ifr,
- int cmd)
-{
- return phy_mii_ioctl(ndev->phydev, ifr, cmd);
-}
-
static int netsec_xdp_xmit(struct net_device *ndev, int n,
struct xdp_frame **frames, u32 flags)
{
@@ -1821,7 +1824,7 @@ static const struct net_device_ops netsec_netdev_ops = {
.ndo_set_features = netsec_netdev_set_features,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
- .ndo_do_ioctl = netsec_netdev_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl,
.ndo_xdp_xmit = netsec_xdp_xmit,
.ndo_bpf = netsec_xdp,
};
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index f7e927a..b703242 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -424,16 +424,22 @@ static void ave_ethtool_get_wol(struct net_device *ndev,
phy_ethtool_get_wol(ndev->phydev, wol);
}
+static int __ave_ethtool_set_wol(struct net_device *ndev,
+ struct ethtool_wolinfo *wol)
+{
+ if (!ndev->phydev ||
+ (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE)))
+ return -EOPNOTSUPP;
+
+ return phy_ethtool_set_wol(ndev->phydev, wol);
+}
+
static int ave_ethtool_set_wol(struct net_device *ndev,
struct ethtool_wolinfo *wol)
{
int ret;
- if (!ndev->phydev ||
- (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE)))
- return -EOPNOTSUPP;
-
- ret = phy_ethtool_set_wol(ndev->phydev, wol);
+ ret = __ave_ethtool_set_wol(ndev, wol);
if (!ret)
device_set_wakeup_enable(&ndev->dev, !!wol->wolopts);
@@ -1216,7 +1222,7 @@ static int ave_init(struct net_device *ndev)
/* set wol initial state disabled */
wol.wolopts = 0;
- ave_ethtool_set_wol(ndev, &wol);
+ __ave_ethtool_set_wol(ndev, &wol);
if (!phy_interface_is_rgmii(phydev))
phy_set_max_speed(phydev, SPEED_100);
@@ -1768,7 +1774,7 @@ static int ave_resume(struct device *dev)
ave_ethtool_get_wol(ndev, &wol);
wol.wolopts = priv->wolopts;
- ave_ethtool_set_wol(ndev, &wol);
+ __ave_ethtool_set_wol(ndev, &wol);
if (ndev->phydev) {
ret = phy_resume(ndev->phydev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 31003b6..4870990 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -368,6 +368,7 @@ struct dma_features {
unsigned int estdep;
unsigned int estsel;
unsigned int fpesel;
+ unsigned int tbssel;
};
/* RX Buffer size must be multiple of 4/8/16 bytes */
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h
index 9f0b9a9..49d6a86 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs.h
@@ -171,6 +171,15 @@ struct dma_extended_desc {
__le32 des7; /* Tx/Rx Timestamp High */
};
+/* Enhanced descriptor for TBS */
+struct dma_edesc {
+ __le32 des4;
+ __le32 des5;
+ __le32 des6;
+ __le32 des7;
+ struct dma_desc basic;
+};
+
/* Transmit checksum insertion control */
#define TX_CIC_FULL 3 /* Include IP header and pseudoheader */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 6f83430..58e0511 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -973,6 +973,9 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
/* default */
break;
case PHY_INTERFACE_MODE_RGMII:
+ case PHY_INTERFACE_MODE_RGMII_ID:
+ case PHY_INTERFACE_MODE_RGMII_RXID:
+ case PHY_INTERFACE_MODE_RGMII_TXID:
reg |= SYSCON_EPIT | SYSCON_ETCS_INT_GMII;
break;
case PHY_INTERFACE_MODE_RMII:
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 26353ef..7d40760 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -44,7 +44,7 @@ static int sun7i_gmac_init(struct platform_device *pdev, void *priv)
* rate, which then uses the auto-reparenting feature of the
* clock driver, and enabling/disabling the clock.
*/
- if (gmac->interface == PHY_INTERFACE_MODE_RGMII) {
+ if (phy_interface_mode_is_rgmii(gmac->interface)) {
clk_set_rate(gmac->tx_clk, SUN7I_GMAC_GMII_RGMII_RATE);
clk_prepare_enable(gmac->tx_clk);
gmac->clk_enabled = 1;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 2e6b60a..af50af2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -239,6 +239,7 @@ enum power_event {
/* MAC HW features3 bitmap */
#define GMAC_HW_FEAT_ASP GENMASK(29, 28)
+#define GMAC_HW_FEAT_TBSSEL BIT(27)
#define GMAC_HW_FEAT_FPESEL BIT(26)
#define GMAC_HW_FEAT_ESTWID GENMASK(21, 20)
#define GMAC_HW_FEAT_ESTDEP GENMASK(19, 17)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 3e14da6..eff8206 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -10,6 +10,7 @@
#include <linux/stmmac.h>
#include "common.h"
+#include "dwmac4.h"
#include "dwmac4_descs.h"
static int dwmac4_wrback_get_tx_status(void *data, struct stmmac_extra_stats *x,
@@ -505,6 +506,14 @@ static void dwmac4_set_sec_addr(struct dma_desc *p, dma_addr_t addr)
p->des3 = cpu_to_le32(upper_32_bits(addr) | RDES3_BUFFER2_VALID_ADDR);
}
+static void dwmac4_set_tbs(struct dma_edesc *p, u32 sec, u32 nsec)
+{
+ p->des4 = cpu_to_le32((sec & TDES4_LT) | TDES4_LTV);
+ p->des5 = cpu_to_le32(nsec & TDES5_LT);
+ p->des6 = 0;
+ p->des7 = 0;
+}
+
const struct stmmac_desc_ops dwmac4_desc_ops = {
.tx_status = dwmac4_wrback_get_tx_status,
.rx_status = dwmac4_wrback_get_rx_status,
@@ -534,6 +543,7 @@ const struct stmmac_desc_ops dwmac4_desc_ops = {
.set_vlan = dwmac4_set_vlan,
.get_rx_header_len = dwmac4_get_rx_header_len,
.set_sec_addr = dwmac4_set_sec_addr,
+ .set_tbs = dwmac4_set_tbs,
};
const struct stmmac_mode_ops dwmac4_ring_mode_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
index 6d92109..6da070c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
@@ -73,6 +73,13 @@
#define TDES3_CONTEXT_TYPE BIT(30)
#define TDES3_CONTEXT_TYPE_SHIFT 30
+/* TDES4 */
+#define TDES4_LTV BIT(31)
+#define TDES4_LT GENMASK(7, 0)
+
+/* TDES5 */
+#define TDES5_LT GENMASK(31, 8)
+
/* TDS3 use for both format (read and write back) */
#define TDES3_OWN BIT(31)
#define TDES3_OWN_SHIFT 31
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index 213d444..bb29bfc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -404,6 +404,7 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr,
/* 5.10 Features */
dma_cap->asp = (hw_cap & GMAC_HW_FEAT_ASP) >> 28;
+ dma_cap->tbssel = (hw_cap & GMAC_HW_FEAT_TBSSEL) >> 27;
dma_cap->fpesel = (hw_cap & GMAC_HW_FEAT_FPESEL) >> 26;
dma_cap->estwid = (hw_cap & GMAC_HW_FEAT_ESTWID) >> 20;
dma_cap->estdep = (hw_cap & GMAC_HW_FEAT_ESTDEP) >> 17;
@@ -471,6 +472,25 @@ static void dwmac4_enable_sph(void __iomem *ioaddr, bool en, u32 chan)
writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
}
+static int dwmac4_enable_tbs(void __iomem *ioaddr, bool en, u32 chan)
+{
+ u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
+
+ if (en)
+ value |= DMA_CONTROL_EDSE;
+ else
+ value &= ~DMA_CONTROL_EDSE;
+
+ writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
+
+ value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan)) & DMA_CONTROL_EDSE;
+ if (en && !value)
+ return -EIO;
+
+ writel(DMA_TBS_DEF_FTOS, ioaddr + DMA_TBS_CTRL);
+ return 0;
+}
+
const struct stmmac_dma_ops dwmac4_dma_ops = {
.reset = dwmac4_dma_reset,
.init = dwmac4_dma_init,
@@ -527,4 +547,5 @@ const struct stmmac_dma_ops dwmac410_dma_ops = {
.qmode = dwmac4_qmode,
.set_bfsize = dwmac4_set_bfsize,
.enable_sph = dwmac4_enable_sph,
+ .enable_tbs = dwmac4_enable_tbs,
};
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index bcb6d51..8391ca6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -22,6 +22,7 @@
#define DMA_DEBUG_STATUS_1 0x00001010
#define DMA_DEBUG_STATUS_2 0x00001014
#define DMA_AXI_BUS_MODE 0x00001028
+#define DMA_TBS_CTRL 0x00001050
/* DMA Bus Mode bitmap */
#define DMA_BUS_MODE_SFT_RESET BIT(0)
@@ -82,6 +83,11 @@
#define DMA_AXI_BURST_LEN_MASK 0x000000FE
+/* DMA TBS Control */
+#define DMA_TBS_FTOS GENMASK(31, 8)
+#define DMA_TBS_FTOV BIT(0)
+#define DMA_TBS_DEF_FTOS (DMA_TBS_FTOS | DMA_TBS_FTOV)
+
/* Following DMA defines are chanels oriented */
#define DMA_CHAN_BASE_ADDR 0x00001100
#define DMA_CHAN_BASE_OFFSET 0x80
@@ -114,6 +120,7 @@
#define DMA_CONTROL_MSS_MASK GENMASK(13, 0)
/* DMA Tx Channel X Control register defines */
+#define DMA_CONTROL_EDSE BIT(28)
#define DMA_CONTROL_TSE BIT(12)
#define DMA_CONTROL_OSP BIT(4)
#define DMA_CONTROL_ST BIT(0)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index 5d4a3c2..494c859 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -657,6 +657,7 @@ void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq,
value &= ~EFPE;
writel(value, ioaddr + MAC_FPE_CTRL_STS);
+ return;
}
value = readl(ioaddr + GMAC_RXQ_CTRL1);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 64d13e5..6c3b8a9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -139,6 +139,7 @@
#define XGMAC_HWFEAT_TXQCNT GENMASK(9, 6)
#define XGMAC_HWFEAT_RXQCNT GENMASK(3, 0)
#define XGMAC_HW_FEATURE3 0x00000128
+#define XGMAC_HWFEAT_TBSSEL BIT(27)
#define XGMAC_HWFEAT_FPESEL BIT(26)
#define XGMAC_HWFEAT_ESTWID GENMASK(24, 23)
#define XGMAC_HWFEAT_ESTDEP GENMASK(22, 20)
@@ -346,6 +347,13 @@
#define XGMAC_TDPS GENMASK(29, 0)
#define XGMAC_RX_EDMA_CTRL 0x00003044
#define XGMAC_RDPS GENMASK(29, 0)
+#define XGMAC_DMA_TBS_CTRL0 0x00003054
+#define XGMAC_DMA_TBS_CTRL1 0x00003058
+#define XGMAC_DMA_TBS_CTRL2 0x0000305c
+#define XGMAC_DMA_TBS_CTRL3 0x00003060
+#define XGMAC_FTOS GENMASK(31, 8)
+#define XGMAC_FTOV BIT(0)
+#define XGMAC_DEF_FTOS (XGMAC_FTOS | XGMAC_FTOV)
#define XGMAC_DMA_SAFETY_INT_STATUS 0x00003064
#define XGMAC_MCSIS BIT(31)
#define XGMAC_MSUIS BIT(29)
@@ -360,6 +368,7 @@
#define XGMAC_SPH BIT(24)
#define XGMAC_PBLx8 BIT(16)
#define XGMAC_DMA_CH_TX_CONTROL(x) (0x00003104 + (0x80 * (x)))
+#define XGMAC_EDSE BIT(28)
#define XGMAC_TxPBL GENMASK(21, 16)
#define XGMAC_TxPBL_SHIFT 16
#define XGMAC_TSE BIT(12)
@@ -404,6 +413,9 @@
#define XGMAC_REGSIZE ((0x0000317c + (0x80 * 15)) / 4)
/* Descriptors */
+#define XGMAC_TDES0_LTV BIT(31)
+#define XGMAC_TDES0_LT GENMASK(7, 0)
+#define XGMAC_TDES1_LT GENMASK(31, 8)
#define XGMAC_TDES2_IVT GENMASK(31, 16)
#define XGMAC_TDES2_IVT_SHIFT 16
#define XGMAC_TDES2_IOC BIT(31)
@@ -422,6 +434,7 @@
#define XGMAC_TDES3_TCMSSV BIT(26)
#define XGMAC_TDES3_SAIC GENMASK(25, 23)
#define XGMAC_TDES3_SAIC_SHIFT 23
+#define XGMAC_TDES3_TBSV BIT(24)
#define XGMAC_TDES3_THL GENMASK(22, 19)
#define XGMAC_TDES3_THL_SHIFT 19
#define XGMAC_TDES3_IVTIR GENMASK(19, 18)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 307105e..2af3ac5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -1421,6 +1421,7 @@ static void dwxgmac3_fpe_configure(void __iomem *ioaddr, u32 num_txq,
value &= ~XGMAC_EFPE;
writel(value, ioaddr + XGMAC_FPE_CTRL_STS);
+ return;
}
value = readl(ioaddr + XGMAC_RXQ_CTRL1);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
index bd5838ce..c3d654c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -339,6 +339,14 @@ static void dwxgmac2_set_vlan(struct dma_desc *p, u32 type)
p->des2 |= cpu_to_le32(type & XGMAC_TDES2_VTIR);
}
+static void dwxgmac2_set_tbs(struct dma_edesc *p, u32 sec, u32 nsec)
+{
+ p->des4 = cpu_to_le32((sec & XGMAC_TDES0_LT) | XGMAC_TDES0_LTV);
+ p->des5 = cpu_to_le32(nsec & XGMAC_TDES1_LT);
+ p->des6 = 0;
+ p->des7 = 0;
+}
+
const struct stmmac_desc_ops dwxgmac210_desc_ops = {
.tx_status = dwxgmac2_get_tx_status,
.rx_status = dwxgmac2_get_rx_status,
@@ -368,4 +376,5 @@ const struct stmmac_desc_ops dwxgmac210_desc_ops = {
.set_sarc = dwxgmac2_set_sarc,
.set_vlan_tag = dwxgmac2_set_vlan_tag,
.set_vlan = dwxgmac2_set_vlan,
+ .set_tbs = dwxgmac2_set_tbs,
};
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index bbbfa79..77308c5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -429,6 +429,7 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr,
/* MAC HW feature 3 */
hw_cap = readl(ioaddr + XGMAC_HW_FEATURE3);
+ dma_cap->tbssel = (hw_cap & XGMAC_HWFEAT_TBSSEL) >> 27;
dma_cap->fpesel = (hw_cap & XGMAC_HWFEAT_FPESEL) >> 26;
dma_cap->estwid = (hw_cap & XGMAC_HWFEAT_ESTWID) >> 23;
dma_cap->estdep = (hw_cap & XGMAC_HWFEAT_ESTDEP) >> 20;
@@ -523,6 +524,28 @@ static void dwxgmac2_enable_sph(void __iomem *ioaddr, bool en, u32 chan)
writel(value, ioaddr + XGMAC_DMA_CH_CONTROL(chan));
}
+static int dwxgmac2_enable_tbs(void __iomem *ioaddr, bool en, u32 chan)
+{
+ u32 value = readl(ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+
+ if (en)
+ value |= XGMAC_EDSE;
+ else
+ value &= ~XGMAC_EDSE;
+
+ writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+
+ value = readl(ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan)) & XGMAC_EDSE;
+ if (en && !value)
+ return -EIO;
+
+ writel(XGMAC_DEF_FTOS, ioaddr + XGMAC_DMA_TBS_CTRL0);
+ writel(XGMAC_DEF_FTOS, ioaddr + XGMAC_DMA_TBS_CTRL1);
+ writel(XGMAC_DEF_FTOS, ioaddr + XGMAC_DMA_TBS_CTRL2);
+ writel(XGMAC_DEF_FTOS, ioaddr + XGMAC_DMA_TBS_CTRL3);
+ return 0;
+}
+
const struct stmmac_dma_ops dwxgmac210_dma_ops = {
.reset = dwxgmac2_dma_reset,
.init = dwxgmac2_dma_init,
@@ -550,4 +573,5 @@ const struct stmmac_dma_ops dwxgmac210_dma_ops = {
.qmode = dwxgmac2_qmode,
.set_bfsize = dwxgmac2_set_bfsize,
.enable_sph = dwxgmac2_enable_sph,
+ .enable_tbs = dwxgmac2_enable_tbs,
};
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 905a6f0..df63b03 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -29,6 +29,7 @@ struct stmmac_extra_stats;
struct stmmac_safety_stats;
struct dma_desc;
struct dma_extended_desc;
+struct dma_edesc;
/* Descriptors helpers */
struct stmmac_desc_ops {
@@ -95,6 +96,7 @@ struct stmmac_desc_ops {
void (*set_vlan_tag)(struct dma_desc *p, u16 tag, u16 inner_tag,
u32 inner_type);
void (*set_vlan)(struct dma_desc *p, u32 type);
+ void (*set_tbs)(struct dma_edesc *p, u32 sec, u32 nsec);
};
#define stmmac_init_rx_desc(__priv, __args...) \
@@ -157,6 +159,8 @@ struct stmmac_desc_ops {
stmmac_do_void_callback(__priv, desc, set_vlan_tag, __args)
#define stmmac_set_desc_vlan(__priv, __args...) \
stmmac_do_void_callback(__priv, desc, set_vlan, __args)
+#define stmmac_set_desc_tbs(__priv, __args...) \
+ stmmac_do_void_callback(__priv, desc, set_tbs, __args)
struct stmmac_dma_cfg;
struct dma_features;
@@ -210,6 +214,7 @@ struct stmmac_dma_ops {
void (*qmode)(void __iomem *ioaddr, u32 channel, u8 qmode);
void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan);
void (*enable_sph)(void __iomem *ioaddr, bool en, u32 chan);
+ int (*enable_tbs)(void __iomem *ioaddr, bool en, u32 chan);
};
#define stmmac_reset(__priv, __args...) \
@@ -268,6 +273,8 @@ struct stmmac_dma_ops {
stmmac_do_void_callback(__priv, dma, set_bfsize, __args)
#define stmmac_enable_sph(__priv, __args...) \
stmmac_do_void_callback(__priv, dma, enable_sph, __args)
+#define stmmac_enable_tbs(__priv, __args...) \
+ stmmac_do_callback(__priv, dma, enable_tbs, __args)
struct mac_device_info;
struct net_device;
@@ -526,6 +533,7 @@ struct tc_cls_u32_offload;
struct tc_cbs_qopt_offload;
struct flow_cls_offload;
struct tc_taprio_qopt_offload;
+struct tc_etf_qopt_offload;
struct stmmac_tc_ops {
int (*init)(struct stmmac_priv *priv);
@@ -537,6 +545,8 @@ struct stmmac_tc_ops {
struct flow_cls_offload *cls);
int (*setup_taprio)(struct stmmac_priv *priv,
struct tc_taprio_qopt_offload *qopt);
+ int (*setup_etf)(struct stmmac_priv *priv,
+ struct tc_etf_qopt_offload *qopt);
};
#define stmmac_tc_init(__priv, __args...) \
@@ -549,6 +559,8 @@ struct stmmac_tc_ops {
stmmac_do_callback(__priv, tc, setup_cls, __args)
#define stmmac_tc_setup_taprio(__priv, __args...) \
stmmac_do_callback(__priv, tc, setup_taprio, __args)
+#define stmmac_tc_setup_etf(__priv, __args...) \
+ stmmac_do_callback(__priv, tc, setup_etf, __args)
struct stmmac_counters;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index f98c5ee..9c02fc7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -39,13 +39,18 @@ struct stmmac_tx_info {
bool is_jumbo;
};
+#define STMMAC_TBS_AVAIL BIT(0)
+#define STMMAC_TBS_EN BIT(1)
+
/* Frequently used values are kept adjacent for cache effect */
struct stmmac_tx_queue {
u32 tx_count_frames;
+ int tbs;
struct timer_list txtimer;
u32 queue_index;
struct stmmac_priv *priv_data;
struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp;
+ struct dma_edesc *dma_entx;
struct dma_desc *dma_tx;
struct sk_buff **tx_skbuff;
struct stmmac_tx_info *tx_skbuff_dma;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index f19b8b1..ff1cbfc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -106,6 +106,7 @@ MODULE_PARM_DESC(chain_mode, "To use chain instead of ring mode");
static irqreturn_t stmmac_interrupt(int irq, void *dev_id);
#ifdef CONFIG_DEBUG_FS
+static const struct net_device_ops stmmac_netdev_ops;
static void stmmac_init_fs(struct net_device *dev);
static void stmmac_exit_fs(struct net_device *dev);
#endif
@@ -387,9 +388,8 @@ bool stmmac_eee_init(struct stmmac_priv *priv)
/* Using PCS we cannot dial with the phy registers at this stage
* so we do not support extra feature like EEE.
*/
- if ((priv->hw->pcs == STMMAC_PCS_RGMII) ||
- (priv->hw->pcs == STMMAC_PCS_TBI) ||
- (priv->hw->pcs == STMMAC_PCS_RTBI))
+ if (priv->hw->pcs == STMMAC_PCS_TBI ||
+ priv->hw->pcs == STMMAC_PCS_RTBI)
return false;
/* Check if MAC core supports the EEE feature. */
@@ -1089,6 +1089,8 @@ static void stmmac_display_tx_rings(struct stmmac_priv *priv)
if (priv->extend_desc)
head_tx = (void *)tx_q->dma_etx;
+ else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ head_tx = (void *)tx_q->dma_entx;
else
head_tx = (void *)tx_q->dma_tx;
@@ -1162,13 +1164,19 @@ static void stmmac_clear_tx_descriptors(struct stmmac_priv *priv, u32 queue)
int i;
/* Clear the TX descriptors */
- for (i = 0; i < DMA_TX_SIZE; i++)
+ for (i = 0; i < DMA_TX_SIZE; i++) {
+ int last = (i == (DMA_TX_SIZE - 1));
+ struct dma_desc *p;
+
if (priv->extend_desc)
- stmmac_init_tx_desc(priv, &tx_q->dma_etx[i].basic,
- priv->mode, (i == DMA_TX_SIZE - 1));
+ p = &tx_q->dma_etx[i].basic;
+ else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ p = &tx_q->dma_entx[i].basic;
else
- stmmac_init_tx_desc(priv, &tx_q->dma_tx[i],
- priv->mode, (i == DMA_TX_SIZE - 1));
+ p = &tx_q->dma_tx[i];
+
+ stmmac_init_tx_desc(priv, p, priv->mode, last);
+ }
}
/**
@@ -1382,7 +1390,7 @@ static int init_dma_tx_desc_rings(struct net_device *dev)
if (priv->extend_desc)
stmmac_mode_init(priv, tx_q->dma_etx,
tx_q->dma_tx_phy, DMA_TX_SIZE, 1);
- else
+ else if (!(tx_q->tbs & STMMAC_TBS_AVAIL))
stmmac_mode_init(priv, tx_q->dma_tx,
tx_q->dma_tx_phy, DMA_TX_SIZE, 0);
}
@@ -1391,6 +1399,8 @@ static int init_dma_tx_desc_rings(struct net_device *dev)
struct dma_desc *p;
if (priv->extend_desc)
p = &((tx_q->dma_etx + i)->basic);
+ else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ p = &((tx_q->dma_entx + i)->basic);
else
p = tx_q->dma_tx + i;
@@ -1510,19 +1520,26 @@ static void free_dma_tx_desc_resources(struct stmmac_priv *priv)
/* Free TX queue resources */
for (queue = 0; queue < tx_count; queue++) {
struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+ size_t size;
+ void *addr;
/* Release the DMA TX socket buffers */
dma_free_tx_skbufs(priv, queue);
- /* Free DMA regions of consistent memory previously allocated */
- if (!priv->extend_desc)
- dma_free_coherent(priv->device,
- DMA_TX_SIZE * sizeof(struct dma_desc),
- tx_q->dma_tx, tx_q->dma_tx_phy);
- else
- dma_free_coherent(priv->device, DMA_TX_SIZE *
- sizeof(struct dma_extended_desc),
- tx_q->dma_etx, tx_q->dma_tx_phy);
+ if (priv->extend_desc) {
+ size = sizeof(struct dma_extended_desc);
+ addr = tx_q->dma_etx;
+ } else if (tx_q->tbs & STMMAC_TBS_AVAIL) {
+ size = sizeof(struct dma_edesc);
+ addr = tx_q->dma_entx;
+ } else {
+ size = sizeof(struct dma_desc);
+ addr = tx_q->dma_tx;
+ }
+
+ size *= DMA_TX_SIZE;
+
+ dma_free_coherent(priv->device, size, addr, tx_q->dma_tx_phy);
kfree(tx_q->tx_skbuff_dma);
kfree(tx_q->tx_skbuff);
@@ -1615,6 +1632,8 @@ static int alloc_dma_tx_desc_resources(struct stmmac_priv *priv)
/* TX queues buffers and DMA */
for (queue = 0; queue < tx_count; queue++) {
struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+ size_t size;
+ void *addr;
tx_q->queue_index = queue;
tx_q->priv_data = priv;
@@ -1631,28 +1650,32 @@ static int alloc_dma_tx_desc_resources(struct stmmac_priv *priv)
if (!tx_q->tx_skbuff)
goto err_dma;
- if (priv->extend_desc) {
- tx_q->dma_etx = dma_alloc_coherent(priv->device,
- DMA_TX_SIZE * sizeof(struct dma_extended_desc),
- &tx_q->dma_tx_phy,
- GFP_KERNEL);
- if (!tx_q->dma_etx)
- goto err_dma;
- } else {
- tx_q->dma_tx = dma_alloc_coherent(priv->device,
- DMA_TX_SIZE * sizeof(struct dma_desc),
- &tx_q->dma_tx_phy,
- GFP_KERNEL);
- if (!tx_q->dma_tx)
- goto err_dma;
- }
+ if (priv->extend_desc)
+ size = sizeof(struct dma_extended_desc);
+ else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ size = sizeof(struct dma_edesc);
+ else
+ size = sizeof(struct dma_desc);
+
+ size *= DMA_TX_SIZE;
+
+ addr = dma_alloc_coherent(priv->device, size,
+ &tx_q->dma_tx_phy, GFP_KERNEL);
+ if (!addr)
+ goto err_dma;
+
+ if (priv->extend_desc)
+ tx_q->dma_etx = addr;
+ else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ tx_q->dma_entx = addr;
+ else
+ tx_q->dma_tx = addr;
}
return 0;
err_dma:
free_dma_tx_desc_resources(priv);
-
return ret;
}
@@ -1884,6 +1907,8 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
if (priv->extend_desc)
p = (struct dma_desc *)(tx_q->dma_etx + entry);
+ else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ p = &tx_q->dma_entx[entry].basic;
else
p = tx_q->dma_tx + entry;
@@ -1982,19 +2007,12 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan)
{
struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
- int i;
netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, chan));
stmmac_stop_tx_dma(priv, chan);
dma_free_tx_skbufs(priv, chan);
- for (i = 0; i < DMA_TX_SIZE; i++)
- if (priv->extend_desc)
- stmmac_init_tx_desc(priv, &tx_q->dma_etx[i].basic,
- priv->mode, (i == DMA_TX_SIZE - 1));
- else
- stmmac_init_tx_desc(priv, &tx_q->dma_tx[i],
- priv->mode, (i == DMA_TX_SIZE - 1));
+ stmmac_clear_tx_descriptors(priv, chan);
tx_q->dirty_tx = 0;
tx_q->cur_tx = 0;
tx_q->mss = 0;
@@ -2631,6 +2649,14 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
if (priv->dma_cap.vlins)
stmmac_enable_vlan(priv, priv->hw, STMMAC_VLAN_INSERT);
+ /* TBS */
+ for (chan = 0; chan < tx_cnt; chan++) {
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
+ int enable = tx_q->tbs & STMMAC_TBS_AVAIL;
+
+ stmmac_enable_tbs(priv, priv->ioaddr, enable, chan);
+ }
+
/* Start the ball rolling... */
stmmac_start_all_dma(priv);
@@ -2660,8 +2686,7 @@ static int stmmac_open(struct net_device *dev)
u32 chan;
int ret;
- if (priv->hw->pcs != STMMAC_PCS_RGMII &&
- priv->hw->pcs != STMMAC_PCS_TBI &&
+ if (priv->hw->pcs != STMMAC_PCS_TBI &&
priv->hw->pcs != STMMAC_PCS_RTBI) {
ret = stmmac_init_phy(dev);
if (ret) {
@@ -2688,6 +2713,16 @@ static int stmmac_open(struct net_device *dev)
priv->rx_copybreak = STMMAC_RX_COPYBREAK;
+ /* Earlier check for TBS */
+ for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) {
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
+ int tbs_en = priv->plat->tx_queues_cfg[chan].tbs_en;
+
+ tx_q->tbs |= tbs_en ? STMMAC_TBS_AVAIL : 0;
+ if (stmmac_enable_tbs(priv, priv->ioaddr, tbs_en, chan))
+ tx_q->tbs &= ~STMMAC_TBS_AVAIL;
+ }
+
ret = alloc_dma_desc_resources(priv);
if (ret < 0) {
netdev_err(priv->dev, "%s: DMA descriptors allocation failed\n",
@@ -2836,7 +2871,11 @@ static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb,
tag = skb_vlan_tag_get(skb);
- p = tx_q->dma_tx + tx_q->cur_tx;
+ if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ p = &tx_q->dma_entx[tx_q->cur_tx].basic;
+ else
+ p = &tx_q->dma_tx[tx_q->cur_tx];
+
if (stmmac_set_desc_vlan_tag(priv, p, tag, inner_tag, inner_type))
return false;
@@ -2871,7 +2910,11 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des,
tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]);
- desc = tx_q->dma_tx + tx_q->cur_tx;
+
+ if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ desc = &tx_q->dma_entx[tx_q->cur_tx].basic;
+ else
+ desc = &tx_q->dma_tx[tx_q->cur_tx];
curr_addr = des + (total_len - tmp_len);
if (priv->dma_cap.addr64 <= 32)
@@ -2922,13 +2965,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dma_desc *desc, *first, *mss_desc = NULL;
struct stmmac_priv *priv = netdev_priv(dev);
+ int desc_size, tmp_pay_len = 0, first_tx;
int nfrags = skb_shinfo(skb)->nr_frags;
u32 queue = skb_get_queue_mapping(skb);
unsigned int first_entry, tx_packets;
- int tmp_pay_len = 0, first_tx;
struct stmmac_tx_queue *tx_q;
- u8 proto_hdr_len, hdr;
bool has_vlan, set_ic;
+ u8 proto_hdr_len, hdr;
u32 pay_len, mss;
dma_addr_t des;
int i;
@@ -2965,7 +3008,11 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
/* set new MSS value if needed */
if (mss != tx_q->mss) {
- mss_desc = tx_q->dma_tx + tx_q->cur_tx;
+ if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ mss_desc = &tx_q->dma_entx[tx_q->cur_tx].basic;
+ else
+ mss_desc = &tx_q->dma_tx[tx_q->cur_tx];
+
stmmac_set_mss(priv, mss_desc, mss);
tx_q->mss = mss;
tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
@@ -2985,7 +3032,10 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
first_entry = tx_q->cur_tx;
WARN_ON(tx_q->tx_skbuff[first_entry]);
- desc = tx_q->dma_tx + first_entry;
+ if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ desc = &tx_q->dma_entx[first_entry].basic;
+ else
+ desc = &tx_q->dma_tx[first_entry];
first = desc;
if (has_vlan)
@@ -3057,7 +3107,11 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
set_ic = false;
if (set_ic) {
- desc = &tx_q->dma_tx[tx_q->cur_tx];
+ if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ desc = &tx_q->dma_entx[tx_q->cur_tx].basic;
+ else
+ desc = &tx_q->dma_tx[tx_q->cur_tx];
+
tx_q->tx_count_frames = 0;
stmmac_set_tx_ic(priv, desc);
priv->xstats.tx_set_ic_bit++;
@@ -3120,16 +3174,18 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
pr_info("%s: curr=%d dirty=%d f=%d, e=%d, f_p=%p, nfrags %d\n",
__func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry,
tx_q->cur_tx, first, nfrags);
-
- stmmac_display_ring(priv, (void *)tx_q->dma_tx, DMA_TX_SIZE, 0);
-
pr_info(">>> frame to be transmitted: ");
print_pkt(skb->data, skb_headlen(skb));
}
netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
- tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc));
+ if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ desc_size = sizeof(struct dma_edesc);
+ else
+ desc_size = sizeof(struct dma_desc);
+
+ tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * desc_size);
stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue);
stmmac_tx_timer_arm(priv, queue);
@@ -3159,10 +3215,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
u32 queue = skb_get_queue_mapping(skb);
int nfrags = skb_shinfo(skb)->nr_frags;
int gso = skb_shinfo(skb)->gso_type;
+ struct dma_edesc *tbs_desc = NULL;
+ int entry, desc_size, first_tx;
struct dma_desc *desc, *first;
struct stmmac_tx_queue *tx_q;
bool has_vlan, set_ic;
- int entry, first_tx;
dma_addr_t des;
tx_q = &priv->tx_queue[queue];
@@ -3202,6 +3259,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
if (likely(priv->extend_desc))
desc = (struct dma_desc *)(tx_q->dma_etx + entry);
+ else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ desc = &tx_q->dma_entx[entry].basic;
else
desc = tx_q->dma_tx + entry;
@@ -3231,6 +3290,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
if (likely(priv->extend_desc))
desc = (struct dma_desc *)(tx_q->dma_etx + entry);
+ else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ desc = &tx_q->dma_entx[entry].basic;
else
desc = tx_q->dma_tx + entry;
@@ -3277,6 +3338,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
if (set_ic) {
if (likely(priv->extend_desc))
desc = &tx_q->dma_etx[entry].basic;
+ else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ desc = &tx_q->dma_entx[entry].basic;
else
desc = &tx_q->dma_tx[entry];
@@ -3294,20 +3357,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
tx_q->cur_tx = entry;
if (netif_msg_pktdata(priv)) {
- void *tx_head;
-
netdev_dbg(priv->dev,
"%s: curr=%d dirty=%d f=%d, e=%d, first=%p, nfrags=%d",
__func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry,
entry, first, nfrags);
- if (priv->extend_desc)
- tx_head = (void *)tx_q->dma_etx;
- else
- tx_head = (void *)tx_q->dma_tx;
-
- stmmac_display_ring(priv, tx_head, DMA_TX_SIZE, false);
-
netdev_dbg(priv->dev, ">>> frame to be transmitted: ");
print_pkt(skb->data, skb->len);
}
@@ -3353,12 +3407,19 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
/* Prepare the first descriptor setting the OWN bit too */
stmmac_prepare_tx_desc(priv, first, 1, nopaged_len,
- csum_insertion, priv->mode, 1, last_segment,
+ csum_insertion, priv->mode, 0, last_segment,
skb->len);
- } else {
- stmmac_set_tx_owner(priv, first);
}
+ if (tx_q->tbs & STMMAC_TBS_EN) {
+ struct timespec64 ts = ns_to_timespec64(skb->tstamp);
+
+ tbs_desc = &tx_q->dma_entx[first_entry];
+ stmmac_set_desc_tbs(priv, tbs_desc, ts.tv_sec, ts.tv_nsec);
+ }
+
+ stmmac_set_tx_owner(priv, first);
+
/* The own bit must be the latest setting done when prepare the
* descriptor and then barrier is needed to make sure that
* all is coherent before granting the DMA engine.
@@ -3369,7 +3430,14 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
stmmac_enable_dma_transmission(priv, priv->ioaddr);
- tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc));
+ if (likely(priv->extend_desc))
+ desc_size = sizeof(struct dma_extended_desc);
+ else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ desc_size = sizeof(struct dma_edesc);
+ else
+ desc_size = sizeof(struct dma_desc);
+
+ tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * desc_size);
stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue);
stmmac_tx_timer_arm(priv, queue);
@@ -4089,6 +4157,8 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
return stmmac_tc_setup_cbs(priv, priv, type_data);
case TC_SETUP_QDISC_TAPRIO:
return stmmac_tc_setup_taprio(priv, priv, type_data);
+ case TC_SETUP_QDISC_ETF:
+ return stmmac_tc_setup_etf(priv, priv, type_data);
default:
return -EOPNOTSUPP;
}
@@ -4192,7 +4262,7 @@ static int stmmac_rings_status_show(struct seq_file *seq, void *v)
seq_printf(seq, "Extended descriptor ring:\n");
sysfs_display_ring((void *)tx_q->dma_etx,
DMA_TX_SIZE, 1, seq);
- } else {
+ } else if (!(tx_q->tbs & STMMAC_TBS_AVAIL)) {
seq_printf(seq, "Descriptor ring:\n");
sysfs_display_ring((void *)tx_q->dma_tx,
DMA_TX_SIZE, 0, seq);
@@ -4293,10 +4363,44 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
priv->dma_cap.l3l4fnum);
seq_printf(seq, "\tARP Offloading: %s\n",
priv->dma_cap.arpoffsel ? "Y" : "N");
+ seq_printf(seq, "\tEnhancements to Scheduled Traffic (EST): %s\n",
+ priv->dma_cap.estsel ? "Y" : "N");
+ seq_printf(seq, "\tFrame Preemption (FPE): %s\n",
+ priv->dma_cap.fpesel ? "Y" : "N");
+ seq_printf(seq, "\tTime-Based Scheduling (TBS): %s\n",
+ priv->dma_cap.tbssel ? "Y" : "N");
return 0;
}
DEFINE_SHOW_ATTRIBUTE(stmmac_dma_cap);
+/* Use network device events to rename debugfs file entries.
+ */
+static int stmmac_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct stmmac_priv *priv = netdev_priv(dev);
+
+ if (dev->netdev_ops != &stmmac_netdev_ops)
+ goto done;
+
+ switch (event) {
+ case NETDEV_CHANGENAME:
+ if (priv->dbgfs_dir)
+ priv->dbgfs_dir = debugfs_rename(stmmac_fs_dir,
+ priv->dbgfs_dir,
+ stmmac_fs_dir,
+ dev->name);
+ break;
+ }
+done:
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block stmmac_notifier = {
+ .notifier_call = stmmac_device_event,
+};
+
static void stmmac_init_fs(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
@@ -4311,12 +4415,15 @@ static void stmmac_init_fs(struct net_device *dev)
/* Entry to report the DMA HW features */
debugfs_create_file("dma_cap", 0444, priv->dbgfs_dir, dev,
&stmmac_dma_cap_fops);
+
+ register_netdevice_notifier(&stmmac_notifier);
}
static void stmmac_exit_fs(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
+ unregister_netdevice_notifier(&stmmac_notifier);
debugfs_remove_recursive(priv->dbgfs_dir);
}
#endif /* CONFIG_DEBUG_FS */
@@ -4767,8 +4874,7 @@ int stmmac_dvr_probe(struct device *device,
stmmac_check_pcs_mode(priv);
- if (priv->hw->pcs != STMMAC_PCS_RGMII &&
- priv->hw->pcs != STMMAC_PCS_TBI &&
+ if (priv->hw->pcs != STMMAC_PCS_TBI &&
priv->hw->pcs != STMMAC_PCS_RTBI) {
/* MDIO bus Registration */
ret = stmmac_mdio_register(ndev);
@@ -4802,8 +4908,7 @@ int stmmac_dvr_probe(struct device *device,
error_netdev_register:
phylink_destroy(priv->phylink);
error_phy_setup:
- if (priv->hw->pcs != STMMAC_PCS_RGMII &&
- priv->hw->pcs != STMMAC_PCS_TBI &&
+ if (priv->hw->pcs != STMMAC_PCS_TBI &&
priv->hw->pcs != STMMAC_PCS_RTBI)
stmmac_mdio_unregister(ndev);
error_mdio_register:
@@ -4848,8 +4953,7 @@ int stmmac_dvr_remove(struct device *dev)
reset_control_assert(priv->plat->stmmac_rst);
clk_disable_unprepare(priv->plat->pclk);
clk_disable_unprepare(priv->plat->stmmac_clk);
- if (priv->hw->pcs != STMMAC_PCS_RGMII &&
- priv->hw->pcs != STMMAC_PCS_TBI &&
+ if (priv->hw->pcs != STMMAC_PCS_TBI &&
priv->hw->pcs != STMMAC_PCS_RTBI)
stmmac_mdio_unregister(ndev);
destroy_workqueue(priv->wq);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 8237dbc..6235210 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -65,7 +65,6 @@ static void common_default_data(struct plat_stmmacenet_data *plat)
plat->force_sf_dma_mode = 1;
plat->mdio_bus_data->needs_reset = true;
- plat->mdio_bus_data->phy_mask = 0;
/* Set default value for multicast hash bins */
plat->multicast_filter_bins = HASH_TABLE_SIZE;
@@ -154,8 +153,6 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
plat->tx_queues_cfg[6].weight = 0x0F;
plat->tx_queues_cfg[7].weight = 0x10;
- plat->mdio_bus_data->phy_mask = 0;
-
plat->dma_cfg->pbl = 32;
plat->dma_cfg->pblx8 = true;
plat->dma_cfg->fixed_burst = 0;
@@ -386,8 +383,6 @@ static int snps_gmac5_default_data(struct pci_dev *pdev,
plat->tso_en = 1;
plat->pmt = 1;
- plat->mdio_bus_data->phy_mask = 0;
-
/* Set default value for multicast hash bins */
plat->multicast_filter_bins = HASH_TABLE_SIZE;
@@ -406,6 +401,8 @@ static int snps_gmac5_default_data(struct pci_dev *pdev,
plat->tx_queues_cfg[i].use_prio = false;
plat->tx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB;
plat->tx_queues_cfg[i].weight = 25;
+ if (i > 0)
+ plat->tx_queues_cfg[i].tbs_en = 1;
}
plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index cc8d7e7..d10ac54 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -320,7 +320,7 @@ static int stmmac_mtl_setup(struct platform_device *pdev,
static int stmmac_dt_phy(struct plat_stmmacenet_data *plat,
struct device_node *np, struct device *dev)
{
- bool mdio = false;
+ bool mdio = !of_phy_is_fixed_link(np);
static const struct of_device_id need_mdio_ids[] = {
{ .compatible = "snps,dwc-qos-ethernet-4.10" },
{},
@@ -412,9 +412,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
*mac = NULL;
}
- rc = of_get_phy_mode(np, &plat->phy_interface);
- if (rc)
- return ERR_PTR(rc);
+ plat->phy_interface = device_get_phy_mode(&pdev->dev);
+ if (plat->phy_interface < 0)
+ return ERR_PTR(plat->phy_interface);
plat->interface = stmmac_of_get_mac_mode(np);
if (plat->interface < 0)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index 1322790..2aba267 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -14,6 +14,7 @@
#include <linux/phy.h>
#include <linux/udp.h>
#include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/tc_act/tc_gact.h>
@@ -50,6 +51,7 @@ struct stmmac_packet_attrs {
u8 id;
int sarc;
u16 queue_mapping;
+ u64 timestamp;
};
static u8 stmmac_test_next_id;
@@ -80,7 +82,7 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv,
if (attr->max_size && (attr->max_size > size))
size = attr->max_size;
- skb = netdev_alloc_skb_ip_align(priv->dev, size);
+ skb = netdev_alloc_skb(priv->dev, size);
if (!skb)
return NULL;
@@ -208,6 +210,9 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv,
skb->pkt_type = PACKET_HOST;
skb->dev = priv->dev;
+ if (attr->timestamp)
+ skb->tstamp = ns_to_ktime(attr->timestamp);
+
return skb;
}
@@ -244,6 +249,8 @@ static int stmmac_test_loopback_validate(struct sk_buff *skb,
struct net_device *orig_ndev)
{
struct stmmac_test_priv *tpriv = pt->af_packet_priv;
+ unsigned char *src = tpriv->packet->src;
+ unsigned char *dst = tpriv->packet->dst;
struct stmmachdr *shdr;
struct ethhdr *ehdr;
struct udphdr *uhdr;
@@ -260,15 +267,15 @@ static int stmmac_test_loopback_validate(struct sk_buff *skb,
goto out;
ehdr = (struct ethhdr *)skb_mac_header(skb);
- if (tpriv->packet->dst) {
- if (!ether_addr_equal(ehdr->h_dest, tpriv->packet->dst))
+ if (dst) {
+ if (!ether_addr_equal_unaligned(ehdr->h_dest, dst))
goto out;
}
if (tpriv->packet->sarc) {
- if (!ether_addr_equal(ehdr->h_source, ehdr->h_dest))
+ if (!ether_addr_equal_unaligned(ehdr->h_source, ehdr->h_dest))
goto out;
- } else if (tpriv->packet->src) {
- if (!ether_addr_equal(ehdr->h_source, tpriv->packet->src))
+ } else if (src) {
+ if (!ether_addr_equal_unaligned(ehdr->h_source, src))
goto out;
}
@@ -339,8 +346,7 @@ static int __stmmac_test_loopback(struct stmmac_priv *priv,
goto cleanup;
}
- skb_set_queue_mapping(skb, attr->queue_mapping);
- ret = dev_queue_xmit(skb);
+ ret = dev_direct_xmit(skb, attr->queue_mapping);
if (ret)
goto cleanup;
@@ -714,7 +720,7 @@ static int stmmac_test_flowctrl_validate(struct sk_buff *skb,
struct ethhdr *ehdr;
ehdr = (struct ethhdr *)skb_mac_header(skb);
- if (!ether_addr_equal(ehdr->h_source, orig_ndev->dev_addr))
+ if (!ether_addr_equal_unaligned(ehdr->h_source, orig_ndev->dev_addr))
goto out;
if (ehdr->h_proto != htons(ETH_P_PAUSE))
goto out;
@@ -851,12 +857,16 @@ static int stmmac_test_vlan_validate(struct sk_buff *skb,
if (tpriv->vlan_id) {
if (skb->vlan_proto != htons(proto))
goto out;
- if (skb->vlan_tci != tpriv->vlan_id)
+ if (skb->vlan_tci != tpriv->vlan_id) {
+ /* Means filter did not work. */
+ tpriv->ok = false;
+ complete(&tpriv->comp);
goto out;
+ }
}
ehdr = (struct ethhdr *)skb_mac_header(skb);
- if (!ether_addr_equal(ehdr->h_dest, tpriv->packet->dst))
+ if (!ether_addr_equal_unaligned(ehdr->h_dest, tpriv->packet->dst))
goto out;
ihdr = ip_hdr(skb);
@@ -926,8 +936,7 @@ static int __stmmac_test_vlanfilt(struct stmmac_priv *priv)
goto vlan_del;
}
- skb_set_queue_mapping(skb, 0);
- ret = dev_queue_xmit(skb);
+ ret = dev_direct_xmit(skb, 0);
if (ret)
goto vlan_del;
@@ -965,6 +974,9 @@ static int stmmac_test_vlanfilt_perfect(struct stmmac_priv *priv)
{
int ret, prev_cap = priv->dma_cap.vlhash;
+ if (!(priv->dev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+ return -EOPNOTSUPP;
+
priv->dma_cap.vlhash = 0;
ret = __stmmac_test_vlanfilt(priv);
priv->dma_cap.vlhash = prev_cap;
@@ -1018,8 +1030,7 @@ static int __stmmac_test_dvlanfilt(struct stmmac_priv *priv)
goto vlan_del;
}
- skb_set_queue_mapping(skb, 0);
- ret = dev_queue_xmit(skb);
+ ret = dev_direct_xmit(skb, 0);
if (ret)
goto vlan_del;
@@ -1057,6 +1068,9 @@ static int stmmac_test_dvlanfilt_perfect(struct stmmac_priv *priv)
{
int ret, prev_cap = priv->dma_cap.vlhash;
+ if (!(priv->dev->features & NETIF_F_HW_VLAN_STAG_FILTER))
+ return -EOPNOTSUPP;
+
priv->dma_cap.vlhash = 0;
ret = __stmmac_test_dvlanfilt(priv);
priv->dma_cap.vlhash = prev_cap;
@@ -1286,8 +1300,7 @@ static int stmmac_test_vlanoff_common(struct stmmac_priv *priv, bool svlan)
__vlan_hwaccel_put_tag(skb, htons(proto), tpriv->vlan_id);
skb->protocol = htons(proto);
- skb_set_queue_mapping(skb, 0);
- ret = dev_queue_xmit(skb);
+ ret = dev_direct_xmit(skb, 0);
if (ret)
goto vlan_del;
@@ -1323,16 +1336,19 @@ static int __stmmac_test_l3filt(struct stmmac_priv *priv, u32 dst, u32 src,
struct stmmac_packet_attrs attr = { };
struct flow_dissector *dissector;
struct flow_cls_offload *cls;
+ int ret, old_enable = 0;
struct flow_rule *rule;
- int ret;
if (!tc_can_offload(priv->dev))
return -EOPNOTSUPP;
if (!priv->dma_cap.l3l4fnum)
return -EOPNOTSUPP;
- if (priv->rss.enable)
+ if (priv->rss.enable) {
+ old_enable = priv->rss.enable;
+ priv->rss.enable = false;
stmmac_rss_configure(priv, priv->hw, NULL,
priv->plat->rx_queues_to_use);
+ }
dissector = kzalloc(sizeof(*dissector), GFP_KERNEL);
if (!dissector) {
@@ -1399,7 +1415,8 @@ static int __stmmac_test_l3filt(struct stmmac_priv *priv, u32 dst, u32 src,
cleanup_dissector:
kfree(dissector);
cleanup_rss:
- if (priv->rss.enable) {
+ if (old_enable) {
+ priv->rss.enable = old_enable;
stmmac_rss_configure(priv, priv->hw, &priv->rss,
priv->plat->rx_queues_to_use);
}
@@ -1444,16 +1461,19 @@ static int __stmmac_test_l4filt(struct stmmac_priv *priv, u32 dst, u32 src,
struct stmmac_packet_attrs attr = { };
struct flow_dissector *dissector;
struct flow_cls_offload *cls;
+ int ret, old_enable = 0;
struct flow_rule *rule;
- int ret;
if (!tc_can_offload(priv->dev))
return -EOPNOTSUPP;
if (!priv->dma_cap.l3l4fnum)
return -EOPNOTSUPP;
- if (priv->rss.enable)
+ if (priv->rss.enable) {
+ old_enable = priv->rss.enable;
+ priv->rss.enable = false;
stmmac_rss_configure(priv, priv->hw, NULL,
priv->plat->rx_queues_to_use);
+ }
dissector = kzalloc(sizeof(*dissector), GFP_KERNEL);
if (!dissector) {
@@ -1525,7 +1545,8 @@ static int __stmmac_test_l4filt(struct stmmac_priv *priv, u32 dst, u32 src,
cleanup_dissector:
kfree(dissector);
cleanup_rss:
- if (priv->rss.enable) {
+ if (old_enable) {
+ priv->rss.enable = old_enable;
stmmac_rss_configure(priv, priv->hw, &priv->rss,
priv->plat->rx_queues_to_use);
}
@@ -1578,7 +1599,7 @@ static int stmmac_test_arp_validate(struct sk_buff *skb,
struct arphdr *ahdr;
ehdr = (struct ethhdr *)skb_mac_header(skb);
- if (!ether_addr_equal(ehdr->h_dest, tpriv->packet->src))
+ if (!ether_addr_equal_unaligned(ehdr->h_dest, tpriv->packet->src))
goto out;
ahdr = arp_hdr(skb);
@@ -1639,8 +1660,7 @@ static int stmmac_test_arpoffload(struct stmmac_priv *priv)
if (ret)
goto cleanup;
- skb_set_queue_mapping(skb, 0);
- ret = dev_queue_xmit(skb);
+ ret = dev_direct_xmit(skb, 0);
if (ret)
goto cleanup_promisc;
@@ -1728,6 +1748,68 @@ static int stmmac_test_sph(struct stmmac_priv *priv)
return 0;
}
+static int stmmac_test_tbs(struct stmmac_priv *priv)
+{
+#define STMMAC_TBS_LT_OFFSET (500 * 1000 * 1000) /* 500 ms*/
+ struct stmmac_packet_attrs attr = { };
+ struct tc_etf_qopt_offload qopt;
+ u64 start_time, curr_time = 0;
+ unsigned long flags;
+ int ret, i;
+
+ if (!priv->hwts_tx_en)
+ return -EOPNOTSUPP;
+
+ /* Find first TBS enabled Queue, if any */
+ for (i = 0; i < priv->plat->tx_queues_to_use; i++)
+ if (priv->tx_queue[i].tbs & STMMAC_TBS_AVAIL)
+ break;
+
+ if (i >= priv->plat->tx_queues_to_use)
+ return -EOPNOTSUPP;
+
+ qopt.enable = true;
+ qopt.queue = i;
+
+ ret = stmmac_tc_setup_etf(priv, priv, &qopt);
+ if (ret)
+ return ret;
+
+ spin_lock_irqsave(&priv->ptp_lock, flags);
+ stmmac_get_systime(priv, priv->ptpaddr, &curr_time);
+ spin_unlock_irqrestore(&priv->ptp_lock, flags);
+
+ if (!curr_time) {
+ ret = -EOPNOTSUPP;
+ goto fail_disable;
+ }
+
+ start_time = curr_time;
+ curr_time += STMMAC_TBS_LT_OFFSET;
+
+ attr.dst = priv->dev->dev_addr;
+ attr.timestamp = curr_time;
+ attr.timeout = nsecs_to_jiffies(2 * STMMAC_TBS_LT_OFFSET);
+ attr.queue_mapping = i;
+
+ ret = __stmmac_test_loopback(priv, &attr);
+ if (ret)
+ goto fail_disable;
+
+ /* Check if expected time has elapsed */
+ spin_lock_irqsave(&priv->ptp_lock, flags);
+ stmmac_get_systime(priv, priv->ptpaddr, &curr_time);
+ spin_unlock_irqrestore(&priv->ptp_lock, flags);
+
+ if ((curr_time - start_time) < STMMAC_TBS_LT_OFFSET)
+ ret = -EINVAL;
+
+fail_disable:
+ qopt.enable = false;
+ stmmac_tc_setup_etf(priv, priv, &qopt);
+ return ret;
+}
+
#define STMMAC_LOOPBACK_NONE 0
#define STMMAC_LOOPBACK_MAC 1
#define STMMAC_LOOPBACK_PHY 2
@@ -1861,6 +1943,10 @@ static const struct stmmac_test {
.name = "Split Header ",
.lb = STMMAC_LOOPBACK_PHY,
.fn = stmmac_test_sph,
+ }, {
+ .name = "TBS (ETF Scheduler) ",
+ .lb = STMMAC_LOOPBACK_PHY,
+ .fn = stmmac_test_tbs,
},
};
@@ -1869,7 +1955,6 @@ void stmmac_selftest_run(struct net_device *dev,
{
struct stmmac_priv *priv = netdev_priv(dev);
int count = stmmac_selftest_get_count(priv);
- int carrier = netif_carrier_ok(dev);
int i, ret;
memset(buf, 0, sizeof(*buf) * count);
@@ -1879,15 +1964,12 @@ void stmmac_selftest_run(struct net_device *dev,
netdev_err(priv->dev, "Only offline tests are supported\n");
etest->flags |= ETH_TEST_FL_FAILED;
return;
- } else if (!carrier) {
+ } else if (!netif_carrier_ok(dev)) {
netdev_err(priv->dev, "You need valid Link to execute tests\n");
etest->flags |= ETH_TEST_FL_FAILED;
return;
}
- /* We don't want extra traffic */
- netif_carrier_off(dev);
-
/* Wait for queues drain */
msleep(200);
@@ -1942,10 +2024,6 @@ void stmmac_selftest_run(struct net_device *dev,
break;
}
}
-
- /* Restart everything */
- if (carrier)
- netif_carrier_on(dev);
}
void stmmac_selftest_get_strings(struct stmmac_priv *priv, u8 *data)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 6c4686b..7a01dee 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -577,6 +577,10 @@ static int tc_setup_cls(struct stmmac_priv *priv,
{
int ret = 0;
+ /* When RSS is enabled, the filtering will be bypassed */
+ if (priv->rss.enable)
+ return -EBUSY;
+
switch (cls->command) {
case FLOW_CLS_REPLACE:
ret = tc_add_flow(priv, cls);
@@ -727,10 +731,31 @@ static int tc_setup_taprio(struct stmmac_priv *priv,
return ret;
}
+static int tc_setup_etf(struct stmmac_priv *priv,
+ struct tc_etf_qopt_offload *qopt)
+{
+ if (!priv->dma_cap.tbssel)
+ return -EOPNOTSUPP;
+ if (qopt->queue >= priv->plat->tx_queues_to_use)
+ return -EINVAL;
+ if (!(priv->tx_queue[qopt->queue].tbs & STMMAC_TBS_AVAIL))
+ return -EINVAL;
+
+ if (qopt->enable)
+ priv->tx_queue[qopt->queue].tbs |= STMMAC_TBS_EN;
+ else
+ priv->tx_queue[qopt->queue].tbs &= ~STMMAC_TBS_EN;
+
+ netdev_info(priv->dev, "%s ETF for Queue %d\n",
+ qopt->enable ? "enabled" : "disabled", qopt->queue);
+ return 0;
+}
+
const struct stmmac_tc_ops dwmac510_tc_ops = {
.init = tc_init,
.setup_cls_u32 = tc_setup_cls_u32,
.setup_cbs = tc_setup_cbs,
.setup_cls = tc_setup_cls,
.setup_taprio = tc_setup_taprio,
+ .setup_etf = tc_setup_etf,
};
diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c
index a601a30..c23ce83 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.c
+++ b/drivers/net/ethernet/sun/sunvnet_common.c
@@ -1223,7 +1223,7 @@ vnet_handle_offloads(struct vnet_port *port, struct sk_buff *skb,
{
struct net_device *dev = VNET_PORT_TO_NET_DEVICE(port);
struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
- struct sk_buff *segs;
+ struct sk_buff *segs, *curr, *next;
int maclen, datalen;
int status;
int gso_size, gso_type, gso_segs;
@@ -1282,11 +1282,8 @@ vnet_handle_offloads(struct vnet_port *port, struct sk_buff *skb,
skb_reset_mac_header(skb);
status = 0;
- while (segs) {
- struct sk_buff *curr = segs;
-
- segs = segs->next;
- curr->next = NULL;
+ skb_list_walk_safe(segs, curr, next) {
+ skb_mark_not_on_list(curr);
if (port->tso && curr->len > dev->mtu) {
skb_shinfo(curr)->gso_size = gso_size;
skb_shinfo(curr)->gso_type = gso_type;
diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index 5e1b829..a530afe 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -816,16 +816,6 @@ static void cpmac_tx_timeout(struct net_device *dev, unsigned int txqueue)
netif_tx_wake_all_queues(priv->dev);
}
-static int cpmac_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
- if (!(netif_running(dev)))
- return -EINVAL;
- if (!dev->phydev)
- return -EINVAL;
-
- return phy_mii_ioctl(dev->phydev, ifr, cmd);
-}
-
static void cpmac_get_ringparam(struct net_device *dev,
struct ethtool_ringparam *ring)
{
@@ -1054,7 +1044,7 @@ static const struct net_device_ops cpmac_netdev_ops = {
.ndo_start_xmit = cpmac_start_xmit,
.ndo_tx_timeout = cpmac_tx_timeout,
.ndo_set_rx_mode = cpmac_set_multicast_list,
- .ndo_do_ioctl = cpmac_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
};
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index 708de82..3fd43d3 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -484,7 +484,6 @@ static int tc35815_close(struct net_device *dev);
static struct net_device_stats *tc35815_get_stats(struct net_device *dev);
static void tc35815_set_multicast_list(struct net_device *dev);
static void tc35815_tx_timeout(struct net_device *dev, unsigned int txqueue);
-static int tc35815_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
#ifdef CONFIG_NET_POLL_CONTROLLER
static void tc35815_poll_controller(struct net_device *dev);
#endif
@@ -751,7 +750,7 @@ static const struct net_device_ops tc35815_netdev_ops = {
.ndo_get_stats = tc35815_get_stats,
.ndo_set_rx_mode = tc35815_set_multicast_list,
.ndo_tx_timeout = tc35815_tx_timeout,
- .ndo_do_ioctl = tc35815_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
#ifdef CONFIG_NET_POLL_CONTROLLER
@@ -2009,15 +2008,6 @@ static const struct ethtool_ops tc35815_ethtool_ops = {
.set_link_ksettings = phy_ethtool_set_link_ksettings,
};
-static int tc35815_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
- if (!netif_running(dev))
- return -EINVAL;
- if (!dev->phydev)
- return -ENODEV;
- return phy_mii_ioctl(dev->phydev, rq, cmd);
-}
-
static void tc35815_chip_reset(struct net_device *dev)
{
struct tc35815_regs __iomem *tr =
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 346e441..4b556b7 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -3257,12 +3257,16 @@ static struct platform_driver velocity_platform_driver = {
* @dev: network device
*
* Called before an ethtool operation. We need to make sure the
- * chip is out of D3 state before we poke at it.
+ * chip is out of D3 state before we poke at it. In case of ethtool
+ * ops nesting, only wake the device up in the outermost block.
*/
static int velocity_ethtool_up(struct net_device *dev)
{
struct velocity_info *vptr = netdev_priv(dev);
- if (!netif_running(dev))
+
+ if (vptr->ethtool_ops_nesting == U32_MAX)
+ return -EBUSY;
+ if (!vptr->ethtool_ops_nesting++ && !netif_running(dev))
velocity_set_power_state(vptr, PCI_D0);
return 0;
}
@@ -3272,12 +3276,14 @@ static int velocity_ethtool_up(struct net_device *dev)
* @dev: network device
*
* Called after an ethtool operation. Restore the chip back to D3
- * state if it isn't running.
+ * state if it isn't running. In case of ethtool ops nesting, only
+ * put the device to sleep in the outermost block.
*/
static void velocity_ethtool_down(struct net_device *dev)
{
struct velocity_info *vptr = netdev_priv(dev);
- if (!netif_running(dev))
+
+ if (!--vptr->ethtool_ops_nesting && !netif_running(dev))
velocity_set_power_state(vptr, PCI_D3hot);
}
diff --git a/drivers/net/ethernet/via/via-velocity.h b/drivers/net/ethernet/via/via-velocity.h
index cdfe780..f196e71 100644
--- a/drivers/net/ethernet/via/via-velocity.h
+++ b/drivers/net/ethernet/via/via-velocity.h
@@ -1483,6 +1483,7 @@ struct velocity_info {
struct velocity_context context;
u32 ticks;
+ u32 ethtool_ops_nesting;
u8 rev_id;
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 21c1b43..f5bbb19 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -1080,17 +1080,6 @@ temac_poll_controller(struct net_device *ndev)
}
#endif
-static int temac_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
-{
- if (!netif_running(ndev))
- return -EINVAL;
-
- if (!ndev->phydev)
- return -EINVAL;
-
- return phy_mii_ioctl(ndev->phydev, rq, cmd);
-}
-
static const struct net_device_ops temac_netdev_ops = {
.ndo_open = temac_open,
.ndo_stop = temac_stop,
@@ -1098,7 +1087,7 @@ static const struct net_device_ops temac_netdev_ops = {
.ndo_set_rx_mode = temac_set_multicast_list,
.ndo_set_mac_address = temac_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
- .ndo_do_ioctl = temac_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = temac_poll_controller,
#endif
diff --git a/drivers/net/ethernet/xscale/Kconfig b/drivers/net/ethernet/xscale/Kconfig
index cd0a8f4..98aa7b8 100644
--- a/drivers/net/ethernet/xscale/Kconfig
+++ b/drivers/net/ethernet/xscale/Kconfig
@@ -27,4 +27,18 @@
Say Y here if you want to use built-in Ethernet ports
on IXP4xx processor.
+config PTP_1588_CLOCK_IXP46X
+ tristate "Intel IXP46x as PTP clock"
+ depends on IXP4XX_ETH
+ depends on PTP_1588_CLOCK
+ default y
+ help
+ This driver adds support for using the IXP46X as a PTP
+ clock. This clock is only useful if your PTP programs are
+ getting hardware time stamps on the PTP Ethernet packets
+ using the SO_TIMESTAMPING API.
+
+ To compile this driver as a module, choose M here: the module
+ will be called ptp_ixp46x.
+
endif # NET_VENDOR_XSCALE
diff --git a/drivers/net/ethernet/xscale/Makefile b/drivers/net/ethernet/xscale/Makefile
index 794a519..607f91b 100644
--- a/drivers/net/ethernet/xscale/Makefile
+++ b/drivers/net/ethernet/xscale/Makefile
@@ -3,4 +3,5 @@
# Makefile for the Intel XScale IXP device drivers.
#
-obj-$(CONFIG_IXP4XX_ETH) += ixp4xx_eth.o
+obj-$(CONFIG_IXP4XX_ETH) += ixp4xx_eth.o
+obj-$(CONFIG_PTP_1588_CLOCK_IXP46X) += ptp_ixp46x.o
diff --git a/arch/arm/mach-ixp4xx/include/mach/ixp46x_ts.h b/drivers/net/ethernet/xscale/ixp46x_ts.h
similarity index 100%
rename from arch/arm/mach-ixp4xx/include/mach/ixp46x_ts.h
rename to drivers/net/ethernet/xscale/ixp46x_ts.h
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 6fc04ff..269596c 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -29,14 +29,16 @@
#include <linux/net_tstamp.h>
#include <linux/of.h>
#include <linux/phy.h>
+#include <linux/platform_data/eth_ixp4xx.h>
#include <linux/platform_device.h>
#include <linux/ptp_classify.h>
#include <linux/slab.h>
#include <linux/module.h>
-#include <mach/ixp46x_ts.h>
#include <linux/soc/ixp4xx/npe.h>
#include <linux/soc/ixp4xx/qmgr.h>
+#include "ixp46x_ts.h"
+
#define DEBUG_DESC 0
#define DEBUG_RX 0
#define DEBUG_TX 0
@@ -517,25 +519,14 @@ static int ixp4xx_mdio_write(struct mii_bus *bus, int phy_id, int location,
return ret;
}
-static int ixp4xx_mdio_register(void)
+static int ixp4xx_mdio_register(struct eth_regs __iomem *regs)
{
int err;
if (!(mdio_bus = mdiobus_alloc()))
return -ENOMEM;
- if (cpu_is_ixp43x()) {
- /* IXP43x lacks NPE-B and uses NPE-C for MII PHY access */
- if (!(ixp4xx_read_feature_bits() & IXP4XX_FEATURE_NPEC_ETH))
- return -ENODEV;
- mdio_regs = (struct eth_regs __iomem *)IXP4XX_EthC_BASE_VIRT;
- } else {
- /* All MII PHY accesses use NPE-B Ethernet registers */
- if (!(ixp4xx_read_feature_bits() & IXP4XX_FEATURE_NPEB_ETH0))
- return -ENODEV;
- mdio_regs = (struct eth_regs __iomem *)IXP4XX_EthB_BASE_VIRT;
- }
-
+ mdio_regs = regs;
__raw_writel(DEFAULT_CORE_CNTRL, &mdio_regs->core_control);
spin_lock_init(&mdio_lock);
mdio_bus->name = "IXP4xx MII Bus";
@@ -581,8 +572,8 @@ static void ixp4xx_adjust_link(struct net_device *dev)
__raw_writel(DEFAULT_TX_CNTRL0 | TX_CNTRL0_HALFDUPLEX,
&port->regs->tx_control[0]);
- printk(KERN_INFO "%s: link up, speed %u Mb/s, %s duplex\n",
- dev->name, port->speed, port->duplex ? "full" : "half");
+ netdev_info(dev, "%s: link up, speed %u Mb/s, %s duplex\n",
+ dev->name, port->speed, port->duplex ? "full" : "half");
}
@@ -592,7 +583,7 @@ static inline void debug_pkt(struct net_device *dev, const char *func,
#if DEBUG_PKT_BYTES
int i;
- printk(KERN_DEBUG "%s: %s(%i) ", dev->name, func, len);
+ netdev_debug(dev, "%s(%i) ", func, len);
for (i = 0; i < len; i++) {
if (i >= DEBUG_PKT_BYTES)
break;
@@ -683,7 +674,7 @@ static int eth_poll(struct napi_struct *napi, int budget)
int received = 0;
#if DEBUG_RX
- printk(KERN_DEBUG "%s: eth_poll\n", dev->name);
+ netdev_debug(dev, "eth_poll\n");
#endif
while (received < budget) {
@@ -697,23 +688,20 @@ static int eth_poll(struct napi_struct *napi, int budget)
if ((n = queue_get_desc(rxq, port, 0)) < 0) {
#if DEBUG_RX
- printk(KERN_DEBUG "%s: eth_poll napi_complete\n",
- dev->name);
+ netdev_debug(dev, "eth_poll napi_complete\n");
#endif
napi_complete(napi);
qmgr_enable_irq(rxq);
if (!qmgr_stat_below_low_watermark(rxq) &&
napi_reschedule(napi)) { /* not empty again */
#if DEBUG_RX
- printk(KERN_DEBUG "%s: eth_poll napi_reschedule succeeded\n",
- dev->name);
+ netdev_debug(dev, "eth_poll napi_reschedule succeeded\n");
#endif
qmgr_disable_irq(rxq);
continue;
}
#if DEBUG_RX
- printk(KERN_DEBUG "%s: eth_poll all done\n",
- dev->name);
+ netdev_debug(dev, "eth_poll all done\n");
#endif
return received; /* all work done */
}
@@ -778,7 +766,7 @@ static int eth_poll(struct napi_struct *napi, int budget)
}
#if DEBUG_RX
- printk(KERN_DEBUG "eth_poll(): end, not all work done\n");
+ netdev_debug(dev, "eth_poll(): end, not all work done\n");
#endif
return received; /* not all work done */
}
@@ -842,7 +830,7 @@ static int eth_xmit(struct sk_buff *skb, struct net_device *dev)
struct desc *desc;
#if DEBUG_TX
- printk(KERN_DEBUG "%s: eth_xmit\n", dev->name);
+ netdev_debug(dev, "eth_xmit\n");
#endif
if (unlikely(skb->len > MAX_MRU)) {
@@ -897,22 +885,21 @@ static int eth_xmit(struct sk_buff *skb, struct net_device *dev)
if (qmgr_stat_below_low_watermark(txreadyq)) { /* empty */
#if DEBUG_TX
- printk(KERN_DEBUG "%s: eth_xmit queue full\n", dev->name);
+ netdev_debug(dev, "eth_xmit queue full\n");
#endif
netif_stop_queue(dev);
/* we could miss TX ready interrupt */
/* really empty in fact */
if (!qmgr_stat_below_low_watermark(txreadyq)) {
#if DEBUG_TX
- printk(KERN_DEBUG "%s: eth_xmit ready again\n",
- dev->name);
+ netdev_debug(dev, "eth_xmit ready again\n");
#endif
netif_wake_queue(dev);
}
}
#if DEBUG_TX
- printk(KERN_DEBUG "%s: eth_xmit end\n", dev->name);
+ netdev_debug(dev, "eth_xmit end\n");
#endif
ixp_tx_timestamp(port, skb);
@@ -1099,7 +1086,7 @@ static int init_queues(struct port *port)
int i;
if (!ports_open) {
- dma_pool = dma_pool_create(DRV_NAME, &port->netdev->dev,
+ dma_pool = dma_pool_create(DRV_NAME, port->netdev->dev.parent,
POOL_ALLOC_SIZE, 32, 0);
if (!dma_pool)
return -ENOMEM;
@@ -1186,8 +1173,7 @@ static int eth_open(struct net_device *dev)
return err;
if (npe_recv_message(npe, &msg, "ETH_GET_STATUS")) {
- printk(KERN_ERR "%s: %s not responding\n", dev->name,
- npe_name(npe));
+ netdev_err(dev, "%s not responding\n", npe_name(npe));
return -EIO;
}
port->firmware[0] = msg.byte4;
@@ -1299,7 +1285,7 @@ static int eth_close(struct net_device *dev)
msg.eth_id = port->id;
msg.byte3 = 1;
if (npe_send_recv_message(port->npe, &msg, "ETH_ENABLE_LOOPBACK"))
- printk(KERN_CRIT "%s: unable to enable loopback\n", dev->name);
+ netdev_crit(dev, "unable to enable loopback\n");
i = 0;
do { /* drain RX buffers */
@@ -1323,11 +1309,11 @@ static int eth_close(struct net_device *dev)
} while (++i < MAX_CLOSE_WAIT);
if (buffs)
- printk(KERN_CRIT "%s: unable to drain RX queue, %i buffer(s)"
- " left in NPE\n", dev->name, buffs);
+ netdev_crit(dev, "unable to drain RX queue, %i buffer(s)"
+ " left in NPE\n", buffs);
#if DEBUG_CLOSE
if (!buffs)
- printk(KERN_DEBUG "Draining RX queue took %i cycles\n", i);
+ netdev_debug(dev, "draining RX queue took %i cycles\n", i);
#endif
buffs = TX_DESCS;
@@ -1343,17 +1329,16 @@ static int eth_close(struct net_device *dev)
} while (++i < MAX_CLOSE_WAIT);
if (buffs)
- printk(KERN_CRIT "%s: unable to drain TX queue, %i buffer(s) "
- "left in NPE\n", dev->name, buffs);
+ netdev_crit(dev, "unable to drain TX queue, %i buffer(s) "
+ "left in NPE\n", buffs);
#if DEBUG_CLOSE
if (!buffs)
- printk(KERN_DEBUG "Draining TX queues took %i cycles\n", i);
+ netdev_debug(dev, "draining TX queues took %i cycles\n", i);
#endif
msg.byte3 = 0;
if (npe_send_recv_message(port->npe, &msg, "ETH_DISABLE_LOOPBACK"))
- printk(KERN_CRIT "%s: unable to disable loopback\n",
- dev->name);
+ netdev_crit(dev, "unable to disable loopback\n");
phy_stop(dev->phydev);
@@ -1374,54 +1359,88 @@ static const struct net_device_ops ixp4xx_netdev_ops = {
.ndo_validate_addr = eth_validate_addr,
};
-static int eth_init_one(struct platform_device *pdev)
+static int ixp4xx_eth_probe(struct platform_device *pdev)
{
- struct port *port;
- struct net_device *dev;
- struct eth_plat_info *plat = dev_get_platdata(&pdev->dev);
- struct phy_device *phydev = NULL;
- u32 regs_phys;
char phy_id[MII_BUS_ID_SIZE + 3];
+ struct phy_device *phydev = NULL;
+ struct device *dev = &pdev->dev;
+ struct eth_plat_info *plat;
+ resource_size_t regs_phys;
+ struct net_device *ndev;
+ struct resource *res;
+ struct port *port;
int err;
- if (!(dev = alloc_etherdev(sizeof(struct port))))
+ plat = dev_get_platdata(dev);
+
+ if (!(ndev = devm_alloc_etherdev(dev, sizeof(struct port))))
return -ENOMEM;
- SET_NETDEV_DEV(dev, &pdev->dev);
- port = netdev_priv(dev);
- port->netdev = dev;
+ SET_NETDEV_DEV(ndev, dev);
+ port = netdev_priv(ndev);
+ port->netdev = ndev;
port->id = pdev->id;
+ /* Get the port resource and remap */
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENODEV;
+ regs_phys = res->start;
+ port->regs = devm_ioremap_resource(dev, res);
+
switch (port->id) {
case IXP4XX_ETH_NPEA:
- port->regs = (struct eth_regs __iomem *)IXP4XX_EthA_BASE_VIRT;
- regs_phys = IXP4XX_EthA_BASE_PHYS;
+ /* If the MDIO bus is not up yet, defer probe */
+ if (!mdio_bus)
+ return -EPROBE_DEFER;
break;
case IXP4XX_ETH_NPEB:
- port->regs = (struct eth_regs __iomem *)IXP4XX_EthB_BASE_VIRT;
- regs_phys = IXP4XX_EthB_BASE_PHYS;
+ /*
+ * On all except IXP43x, NPE-B is used for the MDIO bus.
+ * If there is no NPE-B in the feature set, bail out, else
+ * register the MDIO bus.
+ */
+ if (!cpu_is_ixp43x()) {
+ if (!(ixp4xx_read_feature_bits() &
+ IXP4XX_FEATURE_NPEB_ETH0))
+ return -ENODEV;
+ /* Else register the MDIO bus on NPE-B */
+ if ((err = ixp4xx_mdio_register(port->regs)))
+ return err;
+ }
+ if (!mdio_bus)
+ return -EPROBE_DEFER;
break;
case IXP4XX_ETH_NPEC:
- port->regs = (struct eth_regs __iomem *)IXP4XX_EthC_BASE_VIRT;
- regs_phys = IXP4XX_EthC_BASE_PHYS;
+ /*
+ * IXP43x lacks NPE-B and uses NPE-C for the MDIO bus access,
+ * of there is no NPE-C, no bus, nothing works, so bail out.
+ */
+ if (cpu_is_ixp43x()) {
+ if (!(ixp4xx_read_feature_bits() &
+ IXP4XX_FEATURE_NPEC_ETH))
+ return -ENODEV;
+ /* Else register the MDIO bus on NPE-C */
+ if ((err = ixp4xx_mdio_register(port->regs)))
+ return err;
+ }
+ if (!mdio_bus)
+ return -EPROBE_DEFER;
break;
default:
- err = -ENODEV;
- goto err_free;
+ return -ENODEV;
}
- dev->netdev_ops = &ixp4xx_netdev_ops;
- dev->ethtool_ops = &ixp4xx_ethtool_ops;
- dev->tx_queue_len = 100;
+ ndev->netdev_ops = &ixp4xx_netdev_ops;
+ ndev->ethtool_ops = &ixp4xx_ethtool_ops;
+ ndev->tx_queue_len = 100;
- netif_napi_add(dev, &port->napi, eth_poll, NAPI_WEIGHT);
+ netif_napi_add(ndev, &port->napi, eth_poll, NAPI_WEIGHT);
- if (!(port->npe = npe_request(NPE_ID(port->id)))) {
- err = -EIO;
- goto err_free;
- }
+ if (!(port->npe = npe_request(NPE_ID(port->id))))
+ return -EIO;
- port->mem_res = request_mem_region(regs_phys, REGS_SIZE, dev->name);
+ port->mem_res = request_mem_region(regs_phys, REGS_SIZE, ndev->name);
if (!port->mem_res) {
err = -EBUSY;
goto err_npe_rel;
@@ -1429,9 +1448,9 @@ static int eth_init_one(struct platform_device *pdev)
port->plat = plat;
npe_port_tab[NPE_ID(port->id)] = port;
- memcpy(dev->dev_addr, plat->hwaddr, ETH_ALEN);
+ memcpy(ndev->dev_addr, plat->hwaddr, ETH_ALEN);
- platform_set_drvdata(pdev, dev);
+ platform_set_drvdata(pdev, ndev);
__raw_writel(DEFAULT_CORE_CNTRL | CORE_RESET,
&port->regs->core_control);
@@ -1441,7 +1460,7 @@ static int eth_init_one(struct platform_device *pdev)
snprintf(phy_id, MII_BUS_ID_SIZE + 3, PHY_ID_FMT,
mdio_bus->id, plat->phy);
- phydev = phy_connect(dev, phy_id, &ixp4xx_adjust_link,
+ phydev = phy_connect(ndev, phy_id, &ixp4xx_adjust_link,
PHY_INTERFACE_MODE_MII);
if (IS_ERR(phydev)) {
err = PTR_ERR(phydev);
@@ -1450,11 +1469,11 @@ static int eth_init_one(struct platform_device *pdev)
phydev->irq = PHY_POLL;
- if ((err = register_netdev(dev)))
+ if ((err = register_netdev(ndev)))
goto err_phy_dis;
- printk(KERN_INFO "%s: MII PHY %i on %s\n", dev->name, plat->phy,
- npe_name(port->npe));
+ netdev_info(ndev, "%s: MII PHY %i on %s\n", ndev->name, plat->phy,
+ npe_name(port->npe));
return 0;
@@ -1465,58 +1484,32 @@ static int eth_init_one(struct platform_device *pdev)
release_resource(port->mem_res);
err_npe_rel:
npe_release(port->npe);
-err_free:
- free_netdev(dev);
return err;
}
-static int eth_remove_one(struct platform_device *pdev)
+static int ixp4xx_eth_remove(struct platform_device *pdev)
{
- struct net_device *dev = platform_get_drvdata(pdev);
- struct phy_device *phydev = dev->phydev;
- struct port *port = netdev_priv(dev);
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct phy_device *phydev = ndev->phydev;
+ struct port *port = netdev_priv(ndev);
- unregister_netdev(dev);
+ unregister_netdev(ndev);
phy_disconnect(phydev);
+ ixp4xx_mdio_remove();
npe_port_tab[NPE_ID(port->id)] = NULL;
npe_release(port->npe);
release_resource(port->mem_res);
- free_netdev(dev);
return 0;
}
static struct platform_driver ixp4xx_eth_driver = {
.driver.name = DRV_NAME,
- .probe = eth_init_one,
- .remove = eth_remove_one,
+ .probe = ixp4xx_eth_probe,
+ .remove = ixp4xx_eth_remove,
};
-
-static int __init eth_init_module(void)
-{
- int err;
-
- /*
- * FIXME: we bail out on device tree boot but this really needs
- * to be fixed in a nicer way: this registers the MDIO bus before
- * even matching the driver infrastructure, we should only probe
- * detected hardware.
- */
- if (of_have_populated_dt())
- return -ENODEV;
- if ((err = ixp4xx_mdio_register()))
- return err;
- return platform_driver_register(&ixp4xx_eth_driver);
-}
-
-static void __exit eth_cleanup_module(void)
-{
- platform_driver_unregister(&ixp4xx_eth_driver);
- ixp4xx_mdio_remove();
-}
+module_platform_driver(ixp4xx_eth_driver);
MODULE_AUTHOR("Krzysztof Halasa");
MODULE_DESCRIPTION("Intel IXP4xx Ethernet driver");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS("platform:ixp4xx_eth");
-module_init(eth_init_module);
-module_exit(eth_cleanup_module);
diff --git a/drivers/ptp/ptp_ixp46x.c b/drivers/net/ethernet/xscale/ptp_ixp46x.c
similarity index 99%
rename from drivers/ptp/ptp_ixp46x.c
rename to drivers/net/ethernet/xscale/ptp_ixp46x.c
index 6702848..9ecc395 100644
--- a/drivers/ptp/ptp_ixp46x.c
+++ b/drivers/net/ethernet/xscale/ptp_ixp46x.c
@@ -15,7 +15,8 @@
#include <linux/module.h>
#include <linux/ptp_clock_kernel.h>
-#include <mach/ixp46x_ts.h>
+
+#include "ixp46x_ts.h"
#define DRIVER "ptp_ixp46x"
#define N_EXT_TS 2
diff --git a/drivers/net/fddi/skfp/skfddi.c b/drivers/net/fddi/skfp/skfddi.c
index 1575445..69c29a2 100644
--- a/drivers/net/fddi/skfp/skfddi.c
+++ b/drivers/net/fddi/skfp/skfddi.c
@@ -1520,22 +1520,8 @@ void mac_drv_tx_complete(struct s_smc *smc, volatile struct s_smt_fp_txd *txd)
#ifdef DUMPPACKETS
void dump_data(unsigned char *Data, int length)
{
- int i, j;
- unsigned char s[255], sh[10];
- if (length > 64) {
- length = 64;
- }
printk(KERN_INFO "---Packet start---\n");
- for (i = 0, j = 0; i < length / 8; i++, j += 8)
- printk(KERN_INFO "%02x %02x %02x %02x %02x %02x %02x %02x\n",
- Data[j + 0], Data[j + 1], Data[j + 2], Data[j + 3],
- Data[j + 4], Data[j + 5], Data[j + 6], Data[j + 7]);
- strcpy(s, "");
- for (i = 0; i < length % 8; i++) {
- sprintf(sh, "%02x ", Data[j + i]);
- strcat(s, sh);
- }
- printk(KERN_INFO "%s\n", s);
+ print_hex_dump(KERN_INFO, "", DUMP_PREFIX_NONE, 16, 1, Data, min_t(size_t, length, 64), false);
printk(KERN_INFO "------------------\n");
} // dump_data
#else
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index fca471e..7032a24 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -804,19 +804,21 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
return NULL;
}
- if (sock->sk->sk_protocol != IPPROTO_UDP) {
+ sk = sock->sk;
+ if (sk->sk_protocol != IPPROTO_UDP ||
+ sk->sk_type != SOCK_DGRAM ||
+ (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) {
pr_debug("socket fd=%d not UDP\n", fd);
sk = ERR_PTR(-EINVAL);
goto out_sock;
}
- lock_sock(sock->sk);
- if (sock->sk->sk_user_data) {
+ lock_sock(sk);
+ if (sk->sk_user_data) {
sk = ERR_PTR(-EBUSY);
- goto out_sock;
+ goto out_rel_sock;
}
- sk = sock->sk;
sock_hold(sk);
tuncfg.sk_user_data = gtp;
@@ -826,8 +828,9 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg);
-out_sock:
+out_rel_sock:
release_sock(sock->sk);
+out_sock:
sockfd_put(sock);
return sk;
}
@@ -851,8 +854,7 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[])
sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp);
if (IS_ERR(sk1u)) {
- if (sk0)
- gtp_encap_disable_sock(sk0);
+ gtp_encap_disable_sock(sk0);
return PTR_ERR(sk1u);
}
}
@@ -860,10 +862,8 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[])
if (data[IFLA_GTP_ROLE]) {
role = nla_get_u32(data[IFLA_GTP_ROLE]);
if (role > GTP_ROLE_SGSN) {
- if (sk0)
- gtp_encap_disable_sock(sk0);
- if (sk1u)
- gtp_encap_disable_sock(sk1u);
+ gtp_encap_disable_sock(sk0);
+ gtp_encap_disable_sock(sk1u);
return -EINVAL;
}
}
diff --git a/drivers/net/hyperv/Makefile b/drivers/net/hyperv/Makefile
index 3a2aa07..0db7cca 100644
--- a/drivers/net/hyperv/Makefile
+++ b/drivers/net/hyperv/Makefile
@@ -1,4 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_HYPERV_NET) += hv_netvsc.o
-hv_netvsc-y := netvsc_drv.o netvsc.o rndis_filter.o netvsc_trace.o
+hv_netvsc-y := netvsc_drv.o netvsc.o rndis_filter.o netvsc_trace.o netvsc_bpf.o
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index dc44819..abda736 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -142,6 +142,8 @@ struct netvsc_device_info {
u32 send_section_size;
u32 recv_section_size;
+ struct bpf_prog *bprog;
+
u8 rss_key[NETVSC_HASH_KEYLEN];
};
@@ -189,7 +191,8 @@ int netvsc_send(struct net_device *net,
struct hv_netvsc_packet *packet,
struct rndis_message *rndis_msg,
struct hv_page_buffer *page_buffer,
- struct sk_buff *skb);
+ struct sk_buff *skb,
+ bool xdp_tx);
void netvsc_linkstatus_callback(struct net_device *net,
struct rndis_message *resp);
int netvsc_recv_callback(struct net_device *net,
@@ -198,6 +201,16 @@ int netvsc_recv_callback(struct net_device *net,
void netvsc_channel_cb(void *context);
int netvsc_poll(struct napi_struct *napi, int budget);
+u32 netvsc_run_xdp(struct net_device *ndev, struct netvsc_channel *nvchan,
+ struct xdp_buff *xdp);
+unsigned int netvsc_xdp_fraglen(unsigned int len);
+struct bpf_prog *netvsc_xdp_get(struct netvsc_device *nvdev);
+int netvsc_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+ struct netlink_ext_ack *extack,
+ struct netvsc_device *nvdev);
+int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog);
+int netvsc_bpf(struct net_device *dev, struct netdev_bpf *bpf);
+
int rndis_set_subchannel(struct net_device *ndev,
struct netvsc_device *nvdev,
struct netvsc_device_info *dev_info);
@@ -832,6 +845,8 @@ struct nvsp_message {
#define RNDIS_MAX_PKT_DEFAULT 8
#define RNDIS_PKT_ALIGN_DEFAULT 8
+#define NETVSC_XDP_HDRM 256
+
struct multi_send_data {
struct sk_buff *skb; /* skb containing the pkt */
struct hv_netvsc_packet *pkt; /* netvsc pkt pending */
@@ -867,6 +882,7 @@ struct netvsc_stats {
u64 bytes;
u64 broadcast;
u64 multicast;
+ u64 xdp_drop;
struct u64_stats_sync syncp;
};
@@ -972,6 +988,9 @@ struct netvsc_channel {
atomic_t queue_sends;
struct nvsc_rsc rsc;
+ struct bpf_prog __rcu *bpf_prog;
+ struct xdp_rxq_info xdp_rxq;
+
struct netvsc_stats tx_stats;
struct netvsc_stats rx_stats;
};
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index eab83e7..ae3f308 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -122,8 +122,10 @@ static void free_netvsc_device(struct rcu_head *head)
vfree(nvdev->send_buf);
kfree(nvdev->send_section_map);
- for (i = 0; i < VRSS_CHANNEL_MAX; i++)
+ for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
+ xdp_rxq_info_unreg(&nvdev->chan_table[i].xdp_rxq);
vfree(nvdev->chan_table[i].mrc.slots);
+ }
kfree(nvdev);
}
@@ -900,7 +902,8 @@ int netvsc_send(struct net_device *ndev,
struct hv_netvsc_packet *packet,
struct rndis_message *rndis_msg,
struct hv_page_buffer *pb,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ bool xdp_tx)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
struct netvsc_device *net_device
@@ -923,10 +926,11 @@ int netvsc_send(struct net_device *ndev,
packet->send_buf_index = NETVSC_INVALID_INDEX;
packet->cp_partial = false;
- /* Send control message directly without accessing msd (Multi-Send
- * Data) field which may be changed during data packet processing.
+ /* Send a control message or XDP packet directly without accessing
+ * msd (Multi-Send Data) field which may be changed during data packet
+ * processing.
*/
- if (!skb)
+ if (!skb || xdp_tx)
return netvsc_send_pkt(device, packet, net_device, pb, skb);
/* batch packets in send buffer if possible */
@@ -1392,6 +1396,21 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
nvchan->net_device = net_device;
u64_stats_init(&nvchan->tx_stats.syncp);
u64_stats_init(&nvchan->rx_stats.syncp);
+
+ ret = xdp_rxq_info_reg(&nvchan->xdp_rxq, ndev, i);
+
+ if (ret) {
+ netdev_err(ndev, "xdp_rxq_info_reg fail: %d\n", ret);
+ goto cleanup2;
+ }
+
+ ret = xdp_rxq_info_reg_mem_model(&nvchan->xdp_rxq,
+ MEM_TYPE_PAGE_SHARED, NULL);
+
+ if (ret) {
+ netdev_err(ndev, "xdp reg_mem_model fail: %d\n", ret);
+ goto cleanup2;
+ }
}
/* Enable NAPI handler before init callbacks */
@@ -1437,6 +1456,8 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
cleanup:
netif_napi_del(&net_device->chan_table[0].napi);
+
+cleanup2:
free_netvsc_device(&net_device->rcu);
return ERR_PTR(ret);
diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c
new file mode 100644
index 0000000..20adfe5
--- /dev/null
+++ b/drivers/net/hyperv/netvsc_bpf.c
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2019, Microsoft Corporation.
+ *
+ * Author:
+ * Haiyang Zhang <haiyangz@microsoft.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/kernel.h>
+#include <net/xdp.h>
+
+#include <linux/mutex.h>
+#include <linux/rtnetlink.h>
+
+#include "hyperv_net.h"
+
+u32 netvsc_run_xdp(struct net_device *ndev, struct netvsc_channel *nvchan,
+ struct xdp_buff *xdp)
+{
+ void *data = nvchan->rsc.data[0];
+ u32 len = nvchan->rsc.len[0];
+ struct page *page = NULL;
+ struct bpf_prog *prog;
+ u32 act = XDP_PASS;
+
+ xdp->data_hard_start = NULL;
+
+ rcu_read_lock();
+ prog = rcu_dereference(nvchan->bpf_prog);
+
+ if (!prog)
+ goto out;
+
+ /* allocate page buffer for data */
+ page = alloc_page(GFP_ATOMIC);
+ if (!page) {
+ act = XDP_DROP;
+ goto out;
+ }
+
+ xdp->data_hard_start = page_address(page);
+ xdp->data = xdp->data_hard_start + NETVSC_XDP_HDRM;
+ xdp_set_data_meta_invalid(xdp);
+ xdp->data_end = xdp->data + len;
+ xdp->rxq = &nvchan->xdp_rxq;
+ xdp->handle = 0;
+
+ memcpy(xdp->data, data, len);
+
+ act = bpf_prog_run_xdp(prog, xdp);
+
+ switch (act) {
+ case XDP_PASS:
+ case XDP_TX:
+ case XDP_DROP:
+ break;
+
+ case XDP_ABORTED:
+ trace_xdp_exception(ndev, prog, act);
+ break;
+
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ }
+
+out:
+ rcu_read_unlock();
+
+ if (page && act != XDP_PASS && act != XDP_TX) {
+ __free_page(page);
+ xdp->data_hard_start = NULL;
+ }
+
+ return act;
+}
+
+unsigned int netvsc_xdp_fraglen(unsigned int len)
+{
+ return SKB_DATA_ALIGN(len) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+}
+
+struct bpf_prog *netvsc_xdp_get(struct netvsc_device *nvdev)
+{
+ return rtnl_dereference(nvdev->chan_table[0].bpf_prog);
+}
+
+int netvsc_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+ struct netlink_ext_ack *extack,
+ struct netvsc_device *nvdev)
+{
+ struct bpf_prog *old_prog;
+ int buf_max, i;
+
+ old_prog = netvsc_xdp_get(nvdev);
+
+ if (!old_prog && !prog)
+ return 0;
+
+ buf_max = NETVSC_XDP_HDRM + netvsc_xdp_fraglen(dev->mtu + ETH_HLEN);
+ if (prog && buf_max > PAGE_SIZE) {
+ netdev_err(dev, "XDP: mtu:%u too large, buf_max:%u\n",
+ dev->mtu, buf_max);
+ NL_SET_ERR_MSG_MOD(extack, "XDP: mtu too large");
+
+ return -EOPNOTSUPP;
+ }
+
+ if (prog && (dev->features & NETIF_F_LRO)) {
+ netdev_err(dev, "XDP: not support LRO\n");
+ NL_SET_ERR_MSG_MOD(extack, "XDP: not support LRO");
+
+ return -EOPNOTSUPP;
+ }
+
+ if (prog)
+ bpf_prog_add(prog, nvdev->num_chn);
+
+ for (i = 0; i < nvdev->num_chn; i++)
+ rcu_assign_pointer(nvdev->chan_table[i].bpf_prog, prog);
+
+ if (old_prog)
+ for (i = 0; i < nvdev->num_chn; i++)
+ bpf_prog_put(old_prog);
+
+ return 0;
+}
+
+int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog)
+{
+ struct netdev_bpf xdp;
+ bpf_op_t ndo_bpf;
+
+ ASSERT_RTNL();
+
+ if (!vf_netdev)
+ return 0;
+
+ ndo_bpf = vf_netdev->netdev_ops->ndo_bpf;
+ if (!ndo_bpf)
+ return 0;
+
+ memset(&xdp, 0, sizeof(xdp));
+
+ xdp.command = XDP_SETUP_PROG;
+ xdp.prog = prog;
+
+ return ndo_bpf(vf_netdev, &xdp);
+}
+
+static u32 netvsc_xdp_query(struct netvsc_device *nvdev)
+{
+ struct bpf_prog *prog = netvsc_xdp_get(nvdev);
+
+ if (prog)
+ return prog->aux->id;
+
+ return 0;
+}
+
+int netvsc_bpf(struct net_device *dev, struct netdev_bpf *bpf)
+{
+ struct net_device_context *ndevctx = netdev_priv(dev);
+ struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
+ struct net_device *vf_netdev = rtnl_dereference(ndevctx->vf_netdev);
+ struct netlink_ext_ack *extack = bpf->extack;
+ int ret;
+
+ if (!nvdev || nvdev->destroy) {
+ if (bpf->command == XDP_QUERY_PROG) {
+ bpf->prog_id = 0;
+ return 0; /* Query must always succeed */
+ } else {
+ return -ENODEV;
+ }
+ }
+
+ switch (bpf->command) {
+ case XDP_SETUP_PROG:
+ ret = netvsc_xdp_set(dev, bpf->prog, extack, nvdev);
+
+ if (ret)
+ return ret;
+
+ ret = netvsc_vf_setxdp(vf_netdev, bpf->prog);
+
+ if (ret) {
+ netdev_err(dev, "vf_setxdp failed:%d\n", ret);
+ NL_SET_ERR_MSG_MOD(extack, "vf_setxdp failed");
+
+ netvsc_xdp_set(dev, NULL, extack, nvdev);
+ }
+
+ return ret;
+
+ case XDP_QUERY_PROG:
+ bpf->prog_id = netvsc_xdp_query(nvdev);
+ return 0;
+
+ default:
+ return -EINVAL;
+ }
+}
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index f3f9eb8..8fc71bd 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -25,6 +25,7 @@
#include <linux/slab.h>
#include <linux/rtnetlink.h>
#include <linux/netpoll.h>
+#include <linux/bpf.h>
#include <net/arp.h>
#include <net/route.h>
@@ -519,7 +520,7 @@ static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev,
return rc;
}
-static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
+static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct hv_netvsc_packet *packet = NULL;
@@ -686,7 +687,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
/* timestamp packet in software */
skb_tx_timestamp(skb);
- ret = netvsc_send(net, packet, rndis_msg, pb, skb);
+ ret = netvsc_send(net, packet, rndis_msg, pb, skb, xdp_tx);
if (likely(ret == 0))
return NETDEV_TX_OK;
@@ -709,6 +710,11 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
goto drop;
}
+static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+ return netvsc_xmit(skb, ndev, false);
+}
+
/*
* netvsc_linkstatus_callback - Link up/down notification
*/
@@ -751,6 +757,22 @@ void netvsc_linkstatus_callback(struct net_device *net,
schedule_delayed_work(&ndev_ctx->dwork, 0);
}
+static void netvsc_xdp_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+ int rc;
+
+ skb->queue_mapping = skb_get_rx_queue(skb);
+ __skb_push(skb, ETH_HLEN);
+
+ rc = netvsc_xmit(skb, ndev, true);
+
+ if (dev_xmit_complete(rc))
+ return;
+
+ dev_kfree_skb_any(skb);
+ ndev->stats.tx_dropped++;
+}
+
static void netvsc_comp_ipcsum(struct sk_buff *skb)
{
struct iphdr *iph = (struct iphdr *)skb->data;
@@ -760,7 +782,8 @@ static void netvsc_comp_ipcsum(struct sk_buff *skb)
}
static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
- struct netvsc_channel *nvchan)
+ struct netvsc_channel *nvchan,
+ struct xdp_buff *xdp)
{
struct napi_struct *napi = &nvchan->napi;
const struct ndis_pkt_8021q_info *vlan = nvchan->rsc.vlan;
@@ -768,18 +791,37 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
nvchan->rsc.csum_info;
const u32 *hash_info = nvchan->rsc.hash_info;
struct sk_buff *skb;
+ void *xbuf = xdp->data_hard_start;
int i;
- skb = napi_alloc_skb(napi, nvchan->rsc.pktlen);
- if (!skb)
- return skb;
+ if (xbuf) {
+ unsigned int hdroom = xdp->data - xdp->data_hard_start;
+ unsigned int xlen = xdp->data_end - xdp->data;
+ unsigned int frag_size = netvsc_xdp_fraglen(hdroom + xlen);
- /*
- * Copy to skb. This copy is needed here since the memory pointed by
- * hv_netvsc_packet cannot be deallocated
- */
- for (i = 0; i < nvchan->rsc.cnt; i++)
- skb_put_data(skb, nvchan->rsc.data[i], nvchan->rsc.len[i]);
+ skb = build_skb(xbuf, frag_size);
+
+ if (!skb) {
+ __free_page(virt_to_page(xbuf));
+ return NULL;
+ }
+
+ skb_reserve(skb, hdroom);
+ skb_put(skb, xlen);
+ skb->dev = napi->dev;
+ } else {
+ skb = napi_alloc_skb(napi, nvchan->rsc.pktlen);
+
+ if (!skb)
+ return NULL;
+
+ /* Copy to skb. This copy is needed here since the memory
+ * pointed by hv_netvsc_packet cannot be deallocated.
+ */
+ for (i = 0; i < nvchan->rsc.cnt; i++)
+ skb_put_data(skb, nvchan->rsc.data[i],
+ nvchan->rsc.len[i]);
+ }
skb->protocol = eth_type_trans(skb, net);
@@ -829,13 +871,25 @@ int netvsc_recv_callback(struct net_device *net,
struct vmbus_channel *channel = nvchan->channel;
u16 q_idx = channel->offermsg.offer.sub_channel_index;
struct sk_buff *skb;
- struct netvsc_stats *rx_stats;
+ struct netvsc_stats *rx_stats = &nvchan->rx_stats;
+ struct xdp_buff xdp;
+ u32 act;
if (net->reg_state != NETREG_REGISTERED)
return NVSP_STAT_FAIL;
+ act = netvsc_run_xdp(net, nvchan, &xdp);
+
+ if (act != XDP_PASS && act != XDP_TX) {
+ u64_stats_update_begin(&rx_stats->syncp);
+ rx_stats->xdp_drop++;
+ u64_stats_update_end(&rx_stats->syncp);
+
+ return NVSP_STAT_SUCCESS; /* consumed by XDP */
+ }
+
/* Allocate a skb - TODO direct I/O to pages? */
- skb = netvsc_alloc_recv_skb(net, nvchan);
+ skb = netvsc_alloc_recv_skb(net, nvchan, &xdp);
if (unlikely(!skb)) {
++net_device_ctx->eth_stats.rx_no_memory;
@@ -849,7 +903,6 @@ int netvsc_recv_callback(struct net_device *net,
* on the synthetic device because modifying the VF device
* statistics will not work correctly.
*/
- rx_stats = &nvchan->rx_stats;
u64_stats_update_begin(&rx_stats->syncp);
rx_stats->packets++;
rx_stats->bytes += nvchan->rsc.pktlen;
@@ -860,6 +913,11 @@ int netvsc_recv_callback(struct net_device *net,
++rx_stats->multicast;
u64_stats_update_end(&rx_stats->syncp);
+ if (act == XDP_TX) {
+ netvsc_xdp_xmit(skb, net);
+ return NVSP_STAT_SUCCESS;
+ }
+
napi_gro_receive(&nvchan->napi, skb);
return NVSP_STAT_SUCCESS;
}
@@ -886,10 +944,11 @@ static void netvsc_get_channels(struct net_device *net,
/* Alloc struct netvsc_device_info, and initialize it from either existing
* struct netvsc_device, or from default values.
*/
-static struct netvsc_device_info *netvsc_devinfo_get
- (struct netvsc_device *nvdev)
+static
+struct netvsc_device_info *netvsc_devinfo_get(struct netvsc_device *nvdev)
{
struct netvsc_device_info *dev_info;
+ struct bpf_prog *prog;
dev_info = kzalloc(sizeof(*dev_info), GFP_ATOMIC);
@@ -897,6 +956,8 @@ static struct netvsc_device_info *netvsc_devinfo_get
return NULL;
if (nvdev) {
+ ASSERT_RTNL();
+
dev_info->num_chn = nvdev->num_chn;
dev_info->send_sections = nvdev->send_section_cnt;
dev_info->send_section_size = nvdev->send_section_size;
@@ -905,6 +966,12 @@ static struct netvsc_device_info *netvsc_devinfo_get
memcpy(dev_info->rss_key, nvdev->extension->rss_key,
NETVSC_HASH_KEYLEN);
+
+ prog = netvsc_xdp_get(nvdev);
+ if (prog) {
+ bpf_prog_inc(prog);
+ dev_info->bprog = prog;
+ }
} else {
dev_info->num_chn = VRSS_CHANNEL_DEFAULT;
dev_info->send_sections = NETVSC_DEFAULT_TX;
@@ -916,6 +983,17 @@ static struct netvsc_device_info *netvsc_devinfo_get
return dev_info;
}
+/* Free struct netvsc_device_info */
+static void netvsc_devinfo_put(struct netvsc_device_info *dev_info)
+{
+ if (dev_info->bprog) {
+ ASSERT_RTNL();
+ bpf_prog_put(dev_info->bprog);
+ }
+
+ kfree(dev_info);
+}
+
static int netvsc_detach(struct net_device *ndev,
struct netvsc_device *nvdev)
{
@@ -927,6 +1005,8 @@ static int netvsc_detach(struct net_device *ndev,
if (cancel_work_sync(&nvdev->subchan_work))
nvdev->num_chn = 1;
+ netvsc_xdp_set(ndev, NULL, NULL, nvdev);
+
/* If device was up (receiving) then shutdown */
if (netif_running(ndev)) {
netvsc_tx_disable(nvdev, ndev);
@@ -960,7 +1040,8 @@ static int netvsc_attach(struct net_device *ndev,
struct hv_device *hdev = ndev_ctx->device_ctx;
struct netvsc_device *nvdev;
struct rndis_device *rdev;
- int ret;
+ struct bpf_prog *prog;
+ int ret = 0;
nvdev = rndis_filter_device_add(hdev, dev_info);
if (IS_ERR(nvdev))
@@ -976,6 +1057,13 @@ static int netvsc_attach(struct net_device *ndev,
}
}
+ prog = dev_info->bprog;
+ if (prog) {
+ ret = netvsc_xdp_set(ndev, prog, NULL, nvdev);
+ if (ret)
+ goto err1;
+ }
+
/* In any case device is now ready */
netif_device_attach(ndev);
@@ -985,7 +1073,7 @@ static int netvsc_attach(struct net_device *ndev,
if (netif_running(ndev)) {
ret = rndis_filter_open(nvdev);
if (ret)
- goto err;
+ goto err2;
rdev = nvdev->extension;
if (!rdev->link_state)
@@ -994,9 +1082,10 @@ static int netvsc_attach(struct net_device *ndev,
return 0;
-err:
+err2:
netif_device_detach(ndev);
+err1:
rndis_filter_device_remove(hdev, nvdev);
return ret;
@@ -1046,7 +1135,7 @@ static int netvsc_set_channels(struct net_device *net,
}
out:
- kfree(device_info);
+ netvsc_devinfo_put(device_info);
return ret;
}
@@ -1153,7 +1242,7 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
dev_set_mtu(vf_netdev, orig_mtu);
out:
- kfree(device_info);
+ netvsc_devinfo_put(device_info);
return ret;
}
@@ -1378,8 +1467,8 @@ static const struct {
/* statistics per queue (rx/tx packets/bytes) */
#define NETVSC_PCPU_STATS_LEN (num_present_cpus() * ARRAY_SIZE(pcpu_stats))
-/* 4 statistics per queue (rx/tx packets/bytes) */
-#define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 4)
+/* 5 statistics per queue (rx/tx packets/bytes, rx xdp_drop) */
+#define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 5)
static int netvsc_get_sset_count(struct net_device *dev, int string_set)
{
@@ -1411,6 +1500,7 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
struct netvsc_ethtool_pcpu_stats *pcpu_sum;
unsigned int start;
u64 packets, bytes;
+ u64 xdp_drop;
int i, j, cpu;
if (!nvdev)
@@ -1439,9 +1529,11 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
start = u64_stats_fetch_begin_irq(&qstats->syncp);
packets = qstats->packets;
bytes = qstats->bytes;
+ xdp_drop = qstats->xdp_drop;
} while (u64_stats_fetch_retry_irq(&qstats->syncp, start));
data[i++] = packets;
data[i++] = bytes;
+ data[i++] = xdp_drop;
}
pcpu_sum = kvmalloc_array(num_possible_cpus(),
@@ -1489,6 +1581,8 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
p += ETH_GSTRING_LEN;
sprintf(p, "rx_queue_%u_bytes", i);
p += ETH_GSTRING_LEN;
+ sprintf(p, "rx_queue_%u_xdp_drop", i);
+ p += ETH_GSTRING_LEN;
}
for_each_present_cpu(cpu) {
@@ -1785,10 +1879,27 @@ static int netvsc_set_ringparam(struct net_device *ndev,
}
out:
- kfree(device_info);
+ netvsc_devinfo_put(device_info);
return ret;
}
+static netdev_features_t netvsc_fix_features(struct net_device *ndev,
+ netdev_features_t features)
+{
+ struct net_device_context *ndevctx = netdev_priv(ndev);
+ struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
+
+ if (!nvdev || nvdev->destroy)
+ return features;
+
+ if ((features & NETIF_F_LRO) && netvsc_xdp_get(nvdev)) {
+ features ^= NETIF_F_LRO;
+ netdev_info(ndev, "Skip LRO - unsupported with XDP\n");
+ }
+
+ return features;
+}
+
static int netvsc_set_features(struct net_device *ndev,
netdev_features_t features)
{
@@ -1875,12 +1986,14 @@ static const struct net_device_ops device_ops = {
.ndo_start_xmit = netvsc_start_xmit,
.ndo_change_rx_flags = netvsc_change_rx_flags,
.ndo_set_rx_mode = netvsc_set_rx_mode,
+ .ndo_fix_features = netvsc_fix_features,
.ndo_set_features = netvsc_set_features,
.ndo_change_mtu = netvsc_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = netvsc_set_mac_addr,
.ndo_select_queue = netvsc_select_queue,
.ndo_get_stats64 = netvsc_get_stats64,
+ .ndo_bpf = netvsc_bpf,
};
/*
@@ -2167,6 +2280,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
{
struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev;
+ struct bpf_prog *prog;
struct net_device *ndev;
int ret;
@@ -2211,6 +2325,9 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
vf_netdev->wanted_features = ndev->features;
netdev_update_features(vf_netdev);
+ prog = netvsc_xdp_get(netvsc_dev);
+ netvsc_vf_setxdp(vf_netdev, prog);
+
return NOTIFY_OK;
}
@@ -2252,6 +2369,8 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
+ netvsc_vf_setxdp(vf_netdev, NULL);
+
netdev_rx_handler_unregister(vf_netdev);
netdev_upper_dev_unlink(vf_netdev, ndev);
RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
@@ -2363,14 +2482,14 @@ static int netvsc_probe(struct hv_device *dev,
list_add(&net_device_ctx->list, &netvsc_dev_list);
rtnl_unlock();
- kfree(device_info);
+ netvsc_devinfo_put(device_info);
return 0;
register_failed:
rtnl_unlock();
rndis_filter_device_remove(dev, nvdev);
rndis_failed:
- kfree(device_info);
+ netvsc_devinfo_put(device_info);
devinfo_failed:
free_percpu(net_device_ctx->vf_stats);
no_stats:
@@ -2398,8 +2517,10 @@ static int netvsc_remove(struct hv_device *dev)
rtnl_lock();
nvdev = rtnl_dereference(ndev_ctx->nvdev);
- if (nvdev)
+ if (nvdev) {
cancel_work_sync(&nvdev->subchan_work);
+ netvsc_xdp_set(net, NULL, NULL, nvdev);
+ }
/*
* Call to the vsc driver to let it know that the device is being
@@ -2472,11 +2593,11 @@ static int netvsc_resume(struct hv_device *dev)
ret = netvsc_attach(net, device_info);
- rtnl_unlock();
-
- kfree(device_info);
+ netvsc_devinfo_put(device_info);
net_device_ctx->saved_netvsc_dev_info = NULL;
+ rtnl_unlock();
+
return ret;
}
static const struct hv_vmbus_device_id id_table[] = {
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 857c4be..b81ceba 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -235,7 +235,7 @@ static int rndis_filter_send_request(struct rndis_device *dev,
trace_rndis_send(dev->ndev, 0, &req->request_msg);
rcu_read_lock_bh();
- ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL);
+ ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL, false);
rcu_read_unlock_bh();
return ret;
@@ -1443,8 +1443,6 @@ void rndis_filter_device_remove(struct hv_device *dev,
/* Halt and release the rndis device */
rndis_filter_halt_device(net_dev, rndis_dev);
- net_dev->extension = NULL;
-
netvsc_device_remove(dev);
}
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index afd8b2a..45bfd99 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -11,16 +11,17 @@
#include <linux/module.h>
#include <crypto/aead.h>
#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/refcount.h>
#include <net/genetlink.h>
#include <net/sock.h>
#include <net/gro_cells.h>
+#include <net/macsec.h>
+#include <linux/phy.h>
#include <uapi/linux/if_macsec.h>
-typedef u64 __bitwise sci_t;
-
#define MACSEC_SCI_LEN 8
/* SecTAG length = macsec_eth_header without the optional SCI */
@@ -58,8 +59,6 @@ struct macsec_eth_header {
#define GCM_AES_IV_LEN 12
#define DEFAULT_ICV_LEN 16
-#define MACSEC_NUM_AN 4 /* 2 bits for the association number */
-
#define for_each_rxsc(secy, sc) \
for (sc = rcu_dereference_bh(secy->rx_sc); \
sc; \
@@ -77,49 +76,6 @@ struct gcm_iv {
__be32 pn;
};
-/**
- * struct macsec_key - SA key
- * @id: user-provided key identifier
- * @tfm: crypto struct, key storage
- */
-struct macsec_key {
- u8 id[MACSEC_KEYID_LEN];
- struct crypto_aead *tfm;
-};
-
-struct macsec_rx_sc_stats {
- __u64 InOctetsValidated;
- __u64 InOctetsDecrypted;
- __u64 InPktsUnchecked;
- __u64 InPktsDelayed;
- __u64 InPktsOK;
- __u64 InPktsInvalid;
- __u64 InPktsLate;
- __u64 InPktsNotValid;
- __u64 InPktsNotUsingSA;
- __u64 InPktsUnusedSA;
-};
-
-struct macsec_rx_sa_stats {
- __u32 InPktsOK;
- __u32 InPktsInvalid;
- __u32 InPktsNotValid;
- __u32 InPktsNotUsingSA;
- __u32 InPktsUnusedSA;
-};
-
-struct macsec_tx_sa_stats {
- __u32 OutPktsProtected;
- __u32 OutPktsEncrypted;
-};
-
-struct macsec_tx_sc_stats {
- __u64 OutPktsProtected;
- __u64 OutPktsEncrypted;
- __u64 OutOctetsProtected;
- __u64 OutOctetsEncrypted;
-};
-
struct macsec_dev_stats {
__u64 OutPktsUntagged;
__u64 InPktsUntagged;
@@ -131,124 +87,8 @@ struct macsec_dev_stats {
__u64 InPktsOverrun;
};
-/**
- * struct macsec_rx_sa - receive secure association
- * @active:
- * @next_pn: packet number expected for the next packet
- * @lock: protects next_pn manipulations
- * @key: key structure
- * @stats: per-SA stats
- */
-struct macsec_rx_sa {
- struct macsec_key key;
- spinlock_t lock;
- u32 next_pn;
- refcount_t refcnt;
- bool active;
- struct macsec_rx_sa_stats __percpu *stats;
- struct macsec_rx_sc *sc;
- struct rcu_head rcu;
-};
-
-struct pcpu_rx_sc_stats {
- struct macsec_rx_sc_stats stats;
- struct u64_stats_sync syncp;
-};
-
-/**
- * struct macsec_rx_sc - receive secure channel
- * @sci: secure channel identifier for this SC
- * @active: channel is active
- * @sa: array of secure associations
- * @stats: per-SC stats
- */
-struct macsec_rx_sc {
- struct macsec_rx_sc __rcu *next;
- sci_t sci;
- bool active;
- struct macsec_rx_sa __rcu *sa[MACSEC_NUM_AN];
- struct pcpu_rx_sc_stats __percpu *stats;
- refcount_t refcnt;
- struct rcu_head rcu_head;
-};
-
-/**
- * struct macsec_tx_sa - transmit secure association
- * @active:
- * @next_pn: packet number to use for the next packet
- * @lock: protects next_pn manipulations
- * @key: key structure
- * @stats: per-SA stats
- */
-struct macsec_tx_sa {
- struct macsec_key key;
- spinlock_t lock;
- u32 next_pn;
- refcount_t refcnt;
- bool active;
- struct macsec_tx_sa_stats __percpu *stats;
- struct rcu_head rcu;
-};
-
-struct pcpu_tx_sc_stats {
- struct macsec_tx_sc_stats stats;
- struct u64_stats_sync syncp;
-};
-
-/**
- * struct macsec_tx_sc - transmit secure channel
- * @active:
- * @encoding_sa: association number of the SA currently in use
- * @encrypt: encrypt packets on transmit, or authenticate only
- * @send_sci: always include the SCI in the SecTAG
- * @end_station:
- * @scb: single copy broadcast flag
- * @sa: array of secure associations
- * @stats: stats for this TXSC
- */
-struct macsec_tx_sc {
- bool active;
- u8 encoding_sa;
- bool encrypt;
- bool send_sci;
- bool end_station;
- bool scb;
- struct macsec_tx_sa __rcu *sa[MACSEC_NUM_AN];
- struct pcpu_tx_sc_stats __percpu *stats;
-};
-
#define MACSEC_VALIDATE_DEFAULT MACSEC_VALIDATE_STRICT
-/**
- * struct macsec_secy - MACsec Security Entity
- * @netdev: netdevice for this SecY
- * @n_rx_sc: number of receive secure channels configured on this SecY
- * @sci: secure channel identifier used for tx
- * @key_len: length of keys used by the cipher suite
- * @icv_len: length of ICV used by the cipher suite
- * @validate_frames: validation mode
- * @operational: MAC_Operational flag
- * @protect_frames: enable protection for this SecY
- * @replay_protect: enable packet number checks on receive
- * @replay_window: size of the replay window
- * @tx_sc: transmit secure channel
- * @rx_sc: linked list of receive secure channels
- */
-struct macsec_secy {
- struct net_device *netdev;
- unsigned int n_rx_sc;
- sci_t sci;
- u16 key_len;
- u16 icv_len;
- enum macsec_validation_type validate_frames;
- bool operational;
- bool protect_frames;
- bool replay_protect;
- u32 replay_window;
- struct macsec_tx_sc tx_sc;
- struct macsec_rx_sc __rcu *rx_sc;
-};
-
struct pcpu_secy_stats {
struct macsec_dev_stats stats;
struct u64_stats_sync syncp;
@@ -260,6 +100,7 @@ struct pcpu_secy_stats {
* @real_dev: pointer to underlying netdevice
* @stats: MACsec device stats
* @secys: linked list of SecY's on the underlying device
+ * @offload: status of offloading on the MACsec device
*/
struct macsec_dev {
struct macsec_secy secy;
@@ -267,6 +108,7 @@ struct macsec_dev {
struct pcpu_secy_stats __percpu *stats;
struct list_head secys;
struct gro_cells gro_cells;
+ enum macsec_offload offload;
};
/**
@@ -480,6 +322,56 @@ static void macsec_set_shortlen(struct macsec_eth_header *h, size_t data_len)
h->short_length = data_len;
}
+/* Checks if a MACsec interface is being offloaded to an hardware engine */
+static bool macsec_is_offloaded(struct macsec_dev *macsec)
+{
+ if (macsec->offload == MACSEC_OFFLOAD_PHY)
+ return true;
+
+ return false;
+}
+
+/* Checks if underlying layers implement MACsec offloading functions. */
+static bool macsec_check_offload(enum macsec_offload offload,
+ struct macsec_dev *macsec)
+{
+ if (!macsec || !macsec->real_dev)
+ return false;
+
+ if (offload == MACSEC_OFFLOAD_PHY)
+ return macsec->real_dev->phydev &&
+ macsec->real_dev->phydev->macsec_ops;
+
+ return false;
+}
+
+static const struct macsec_ops *__macsec_get_ops(enum macsec_offload offload,
+ struct macsec_dev *macsec,
+ struct macsec_context *ctx)
+{
+ if (ctx) {
+ memset(ctx, 0, sizeof(*ctx));
+ ctx->offload = offload;
+
+ if (offload == MACSEC_OFFLOAD_PHY)
+ ctx->phydev = macsec->real_dev->phydev;
+ }
+
+ return macsec->real_dev->phydev->macsec_ops;
+}
+
+/* Returns a pointer to the MACsec ops struct if any and updates the MACsec
+ * context device reference if provided.
+ */
+static const struct macsec_ops *macsec_get_ops(struct macsec_dev *macsec,
+ struct macsec_context *ctx)
+{
+ if (!macsec_check_offload(macsec->offload, macsec))
+ return NULL;
+
+ return __macsec_get_ops(macsec->offload, macsec, ctx);
+}
+
/* validate MACsec packet according to IEEE 802.1AE-2006 9.12 */
static bool macsec_validate_skb(struct sk_buff *skb, u16 icv_len)
{
@@ -532,6 +424,23 @@ static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb)
return (struct macsec_eth_header *)skb_mac_header(skb);
}
+static void __macsec_pn_wrapped(struct macsec_secy *secy,
+ struct macsec_tx_sa *tx_sa)
+{
+ pr_debug("PN wrapped, transitioning to !oper\n");
+ tx_sa->active = false;
+ if (secy->protect_frames)
+ secy->operational = false;
+}
+
+void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa)
+{
+ spin_lock_bh(&tx_sa->lock);
+ __macsec_pn_wrapped(secy, tx_sa);
+ spin_unlock_bh(&tx_sa->lock);
+}
+EXPORT_SYMBOL_GPL(macsec_pn_wrapped);
+
static u32 tx_sa_update_pn(struct macsec_tx_sa *tx_sa, struct macsec_secy *secy)
{
u32 pn;
@@ -540,12 +449,8 @@ static u32 tx_sa_update_pn(struct macsec_tx_sa *tx_sa, struct macsec_secy *secy)
pn = tx_sa->next_pn;
tx_sa->next_pn++;
- if (tx_sa->next_pn == 0) {
- pr_debug("PN wrapped, transitioning to !oper\n");
- tx_sa->active = false;
- if (secy->protect_frames)
- secy->operational = false;
- }
+ if (tx_sa->next_pn == 0)
+ __macsec_pn_wrapped(secy, tx_sa);
spin_unlock_bh(&tx_sa->lock);
return pn;
@@ -1029,8 +934,10 @@ static struct macsec_rx_sc *find_rx_sc_rtnl(struct macsec_secy *secy, sci_t sci)
return NULL;
}
-static void handle_not_macsec(struct sk_buff *skb)
+static enum rx_handler_result handle_not_macsec(struct sk_buff *skb)
{
+ /* Deliver to the uncontrolled port by default */
+ enum rx_handler_result ret = RX_HANDLER_PASS;
struct macsec_rxh_data *rxd;
struct macsec_dev *macsec;
@@ -1045,7 +952,8 @@ static void handle_not_macsec(struct sk_buff *skb)
struct sk_buff *nskb;
struct pcpu_secy_stats *secy_stats = this_cpu_ptr(macsec->stats);
- if (macsec->secy.validate_frames == MACSEC_VALIDATE_STRICT) {
+ if (!macsec_is_offloaded(macsec) &&
+ macsec->secy.validate_frames == MACSEC_VALIDATE_STRICT) {
u64_stats_update_begin(&secy_stats->syncp);
secy_stats->stats.InPktsNoTag++;
u64_stats_update_end(&secy_stats->syncp);
@@ -1064,9 +972,17 @@ static void handle_not_macsec(struct sk_buff *skb)
secy_stats->stats.InPktsUntagged++;
u64_stats_update_end(&secy_stats->syncp);
}
+
+ if (netif_running(macsec->secy.netdev) &&
+ macsec_is_offloaded(macsec)) {
+ ret = RX_HANDLER_EXACT;
+ goto out;
+ }
}
+out:
rcu_read_unlock();
+ return ret;
}
static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
@@ -1091,12 +1007,8 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
goto drop_direct;
hdr = macsec_ethhdr(skb);
- if (hdr->eth.h_proto != htons(ETH_P_MACSEC)) {
- handle_not_macsec(skb);
-
- /* and deliver to the uncontrolled port */
- return RX_HANDLER_PASS;
- }
+ if (hdr->eth.h_proto != htons(ETH_P_MACSEC))
+ return handle_not_macsec(skb);
skb = skb_unshare(skb, GFP_ATOMIC);
*pskb = skb;
@@ -1585,6 +1497,7 @@ static const struct nla_policy macsec_genl_policy[NUM_MACSEC_ATTR] = {
[MACSEC_ATTR_IFINDEX] = { .type = NLA_U32 },
[MACSEC_ATTR_RXSC_CONFIG] = { .type = NLA_NESTED },
[MACSEC_ATTR_SA_CONFIG] = { .type = NLA_NESTED },
+ [MACSEC_ATTR_OFFLOAD] = { .type = NLA_NESTED },
};
static const struct nla_policy macsec_genl_rxsc_policy[NUM_MACSEC_RXSC_ATTR] = {
@@ -1602,6 +1515,44 @@ static const struct nla_policy macsec_genl_sa_policy[NUM_MACSEC_SA_ATTR] = {
.len = MACSEC_MAX_KEY_LEN, },
};
+static const struct nla_policy macsec_genl_offload_policy[NUM_MACSEC_OFFLOAD_ATTR] = {
+ [MACSEC_OFFLOAD_ATTR_TYPE] = { .type = NLA_U8 },
+};
+
+/* Offloads an operation to a device driver */
+static int macsec_offload(int (* const func)(struct macsec_context *),
+ struct macsec_context *ctx)
+{
+ int ret;
+
+ if (unlikely(!func))
+ return 0;
+
+ if (ctx->offload == MACSEC_OFFLOAD_PHY)
+ mutex_lock(&ctx->phydev->lock);
+
+ /* Phase I: prepare. The drive should fail here if there are going to be
+ * issues in the commit phase.
+ */
+ ctx->prepare = true;
+ ret = (*func)(ctx);
+ if (ret)
+ goto phy_unlock;
+
+ /* Phase II: commit. This step cannot fail. */
+ ctx->prepare = false;
+ ret = (*func)(ctx);
+ /* This should never happen: commit is not allowed to fail */
+ if (unlikely(ret))
+ WARN(1, "MACsec offloading commit failed (%d)\n", ret);
+
+phy_unlock:
+ if (ctx->offload == MACSEC_OFFLOAD_PHY)
+ mutex_unlock(&ctx->phydev->lock);
+
+ return ret;
+}
+
static int parse_sa_config(struct nlattr **attrs, struct nlattr **tb_sa)
{
if (!attrs[MACSEC_ATTR_SA_CONFIG])
@@ -1717,13 +1668,40 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
if (tb_sa[MACSEC_SA_ATTR_ACTIVE])
rx_sa->active = !!nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]);
- nla_memcpy(rx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN);
rx_sa->sc = rx_sc;
+
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(netdev_priv(dev))) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ err = -EOPNOTSUPP;
+ goto cleanup;
+ }
+
+ ctx.sa.assoc_num = assoc_num;
+ ctx.sa.rx_sa = rx_sa;
+ memcpy(ctx.sa.key, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]),
+ MACSEC_KEYID_LEN);
+
+ err = macsec_offload(ops->mdo_add_rxsa, &ctx);
+ if (err)
+ goto cleanup;
+ }
+
+ nla_memcpy(rx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN);
rcu_assign_pointer(rx_sc->sa[assoc_num], rx_sa);
rtnl_unlock();
return 0;
+
+cleanup:
+ kfree(rx_sa);
+ rtnl_unlock();
+ return err;
}
static bool validate_add_rxsc(struct nlattr **attrs)
@@ -1746,6 +1724,8 @@ static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info)
struct nlattr **attrs = info->attrs;
struct macsec_rx_sc *rx_sc;
struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1];
+ bool was_active;
+ int ret;
if (!attrs[MACSEC_ATTR_IFINDEX])
return -EINVAL;
@@ -1771,12 +1751,35 @@ static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info)
return PTR_ERR(rx_sc);
}
+ was_active = rx_sc->active;
if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE])
rx_sc->active = !!nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]);
+ if (macsec_is_offloaded(netdev_priv(dev))) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ ret = -EOPNOTSUPP;
+ goto cleanup;
+ }
+
+ ctx.rx_sc = rx_sc;
+
+ ret = macsec_offload(ops->mdo_add_rxsc, &ctx);
+ if (ret)
+ goto cleanup;
+ }
+
rtnl_unlock();
return 0;
+
+cleanup:
+ rx_sc->active = was_active;
+ rtnl_unlock();
+ return ret;
}
static bool validate_add_txsa(struct nlattr **attrs)
@@ -1813,6 +1816,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
struct macsec_tx_sa *tx_sa;
unsigned char assoc_num;
struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1];
+ bool was_operational;
int err;
if (!attrs[MACSEC_ATTR_IFINDEX])
@@ -1863,8 +1867,6 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
return err;
}
- nla_memcpy(tx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN);
-
spin_lock_bh(&tx_sa->lock);
tx_sa->next_pn = nla_get_u32(tb_sa[MACSEC_SA_ATTR_PN]);
spin_unlock_bh(&tx_sa->lock);
@@ -1872,14 +1874,43 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
if (tb_sa[MACSEC_SA_ATTR_ACTIVE])
tx_sa->active = !!nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]);
+ was_operational = secy->operational;
if (assoc_num == tx_sc->encoding_sa && tx_sa->active)
secy->operational = true;
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(netdev_priv(dev))) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ err = -EOPNOTSUPP;
+ goto cleanup;
+ }
+
+ ctx.sa.assoc_num = assoc_num;
+ ctx.sa.tx_sa = tx_sa;
+ memcpy(ctx.sa.key, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]),
+ MACSEC_KEYID_LEN);
+
+ err = macsec_offload(ops->mdo_add_txsa, &ctx);
+ if (err)
+ goto cleanup;
+ }
+
+ nla_memcpy(tx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN);
rcu_assign_pointer(tx_sc->sa[assoc_num], tx_sa);
rtnl_unlock();
return 0;
+
+cleanup:
+ secy->operational = was_operational;
+ kfree(tx_sa);
+ rtnl_unlock();
+ return err;
}
static int macsec_del_rxsa(struct sk_buff *skb, struct genl_info *info)
@@ -1892,6 +1923,7 @@ static int macsec_del_rxsa(struct sk_buff *skb, struct genl_info *info)
u8 assoc_num;
struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1];
struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1];
+ int ret;
if (!attrs[MACSEC_ATTR_IFINDEX])
return -EINVAL;
@@ -1915,12 +1947,35 @@ static int macsec_del_rxsa(struct sk_buff *skb, struct genl_info *info)
return -EBUSY;
}
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(netdev_priv(dev))) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ ret = -EOPNOTSUPP;
+ goto cleanup;
+ }
+
+ ctx.sa.assoc_num = assoc_num;
+ ctx.sa.rx_sa = rx_sa;
+
+ ret = macsec_offload(ops->mdo_del_rxsa, &ctx);
+ if (ret)
+ goto cleanup;
+ }
+
RCU_INIT_POINTER(rx_sc->sa[assoc_num], NULL);
clear_rx_sa(rx_sa);
rtnl_unlock();
return 0;
+
+cleanup:
+ rtnl_unlock();
+ return ret;
}
static int macsec_del_rxsc(struct sk_buff *skb, struct genl_info *info)
@@ -1931,6 +1986,7 @@ static int macsec_del_rxsc(struct sk_buff *skb, struct genl_info *info)
struct macsec_rx_sc *rx_sc;
sci_t sci;
struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1];
+ int ret;
if (!attrs[MACSEC_ATTR_IFINDEX])
return -EINVAL;
@@ -1957,10 +2013,31 @@ static int macsec_del_rxsc(struct sk_buff *skb, struct genl_info *info)
return -ENODEV;
}
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(netdev_priv(dev))) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ ret = -EOPNOTSUPP;
+ goto cleanup;
+ }
+
+ ctx.rx_sc = rx_sc;
+ ret = macsec_offload(ops->mdo_del_rxsc, &ctx);
+ if (ret)
+ goto cleanup;
+ }
+
free_rx_sc(rx_sc);
rtnl_unlock();
return 0;
+
+cleanup:
+ rtnl_unlock();
+ return ret;
}
static int macsec_del_txsa(struct sk_buff *skb, struct genl_info *info)
@@ -1972,6 +2049,7 @@ static int macsec_del_txsa(struct sk_buff *skb, struct genl_info *info)
struct macsec_tx_sa *tx_sa;
u8 assoc_num;
struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1];
+ int ret;
if (!attrs[MACSEC_ATTR_IFINDEX])
return -EINVAL;
@@ -1992,12 +2070,35 @@ static int macsec_del_txsa(struct sk_buff *skb, struct genl_info *info)
return -EBUSY;
}
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(netdev_priv(dev))) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ ret = -EOPNOTSUPP;
+ goto cleanup;
+ }
+
+ ctx.sa.assoc_num = assoc_num;
+ ctx.sa.tx_sa = tx_sa;
+
+ ret = macsec_offload(ops->mdo_del_txsa, &ctx);
+ if (ret)
+ goto cleanup;
+ }
+
RCU_INIT_POINTER(tx_sc->sa[assoc_num], NULL);
clear_tx_sa(tx_sa);
rtnl_unlock();
return 0;
+
+cleanup:
+ rtnl_unlock();
+ return ret;
}
static bool validate_upd_sa(struct nlattr **attrs)
@@ -2030,6 +2131,9 @@ static int macsec_upd_txsa(struct sk_buff *skb, struct genl_info *info)
struct macsec_tx_sa *tx_sa;
u8 assoc_num;
struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1];
+ bool was_operational, was_active;
+ u32 prev_pn = 0;
+ int ret = 0;
if (!attrs[MACSEC_ATTR_IFINDEX])
return -EINVAL;
@@ -2050,19 +2154,52 @@ static int macsec_upd_txsa(struct sk_buff *skb, struct genl_info *info)
if (tb_sa[MACSEC_SA_ATTR_PN]) {
spin_lock_bh(&tx_sa->lock);
+ prev_pn = tx_sa->next_pn;
tx_sa->next_pn = nla_get_u32(tb_sa[MACSEC_SA_ATTR_PN]);
spin_unlock_bh(&tx_sa->lock);
}
+ was_active = tx_sa->active;
if (tb_sa[MACSEC_SA_ATTR_ACTIVE])
tx_sa->active = nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]);
+ was_operational = secy->operational;
if (assoc_num == tx_sc->encoding_sa)
secy->operational = tx_sa->active;
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(netdev_priv(dev))) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ ret = -EOPNOTSUPP;
+ goto cleanup;
+ }
+
+ ctx.sa.assoc_num = assoc_num;
+ ctx.sa.tx_sa = tx_sa;
+
+ ret = macsec_offload(ops->mdo_upd_txsa, &ctx);
+ if (ret)
+ goto cleanup;
+ }
+
rtnl_unlock();
return 0;
+
+cleanup:
+ if (tb_sa[MACSEC_SA_ATTR_PN]) {
+ spin_lock_bh(&tx_sa->lock);
+ tx_sa->next_pn = prev_pn;
+ spin_unlock_bh(&tx_sa->lock);
+ }
+ tx_sa->active = was_active;
+ secy->operational = was_operational;
+ rtnl_unlock();
+ return ret;
}
static int macsec_upd_rxsa(struct sk_buff *skb, struct genl_info *info)
@@ -2075,6 +2212,9 @@ static int macsec_upd_rxsa(struct sk_buff *skb, struct genl_info *info)
u8 assoc_num;
struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1];
struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1];
+ bool was_active;
+ u32 prev_pn = 0;
+ int ret = 0;
if (!attrs[MACSEC_ATTR_IFINDEX])
return -EINVAL;
@@ -2098,15 +2238,46 @@ static int macsec_upd_rxsa(struct sk_buff *skb, struct genl_info *info)
if (tb_sa[MACSEC_SA_ATTR_PN]) {
spin_lock_bh(&rx_sa->lock);
+ prev_pn = rx_sa->next_pn;
rx_sa->next_pn = nla_get_u32(tb_sa[MACSEC_SA_ATTR_PN]);
spin_unlock_bh(&rx_sa->lock);
}
+ was_active = rx_sa->active;
if (tb_sa[MACSEC_SA_ATTR_ACTIVE])
rx_sa->active = nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]);
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(netdev_priv(dev))) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ ret = -EOPNOTSUPP;
+ goto cleanup;
+ }
+
+ ctx.sa.assoc_num = assoc_num;
+ ctx.sa.rx_sa = rx_sa;
+
+ ret = macsec_offload(ops->mdo_upd_rxsa, &ctx);
+ if (ret)
+ goto cleanup;
+ }
+
rtnl_unlock();
return 0;
+
+cleanup:
+ if (tb_sa[MACSEC_SA_ATTR_PN]) {
+ spin_lock_bh(&rx_sa->lock);
+ rx_sa->next_pn = prev_pn;
+ spin_unlock_bh(&rx_sa->lock);
+ }
+ rx_sa->active = was_active;
+ rtnl_unlock();
+ return ret;
}
static int macsec_upd_rxsc(struct sk_buff *skb, struct genl_info *info)
@@ -2116,6 +2287,9 @@ static int macsec_upd_rxsc(struct sk_buff *skb, struct genl_info *info)
struct macsec_secy *secy;
struct macsec_rx_sc *rx_sc;
struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1];
+ unsigned int prev_n_rx_sc;
+ bool was_active;
+ int ret;
if (!attrs[MACSEC_ATTR_IFINDEX])
return -EINVAL;
@@ -2133,6 +2307,8 @@ static int macsec_upd_rxsc(struct sk_buff *skb, struct genl_info *info)
return PTR_ERR(rx_sc);
}
+ was_active = rx_sc->active;
+ prev_n_rx_sc = secy->n_rx_sc;
if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) {
bool new = !!nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]);
@@ -2142,9 +2318,153 @@ static int macsec_upd_rxsc(struct sk_buff *skb, struct genl_info *info)
rx_sc->active = new;
}
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(netdev_priv(dev))) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ ret = -EOPNOTSUPP;
+ goto cleanup;
+ }
+
+ ctx.rx_sc = rx_sc;
+
+ ret = macsec_offload(ops->mdo_upd_rxsc, &ctx);
+ if (ret)
+ goto cleanup;
+ }
+
rtnl_unlock();
return 0;
+
+cleanup:
+ secy->n_rx_sc = prev_n_rx_sc;
+ rx_sc->active = was_active;
+ rtnl_unlock();
+ return ret;
+}
+
+static bool macsec_is_configured(struct macsec_dev *macsec)
+{
+ struct macsec_secy *secy = &macsec->secy;
+ struct macsec_tx_sc *tx_sc = &secy->tx_sc;
+ int i;
+
+ if (secy->n_rx_sc > 0)
+ return true;
+
+ for (i = 0; i < MACSEC_NUM_AN; i++)
+ if (tx_sc->sa[i])
+ return true;
+
+ return false;
+}
+
+static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr *tb_offload[MACSEC_OFFLOAD_ATTR_MAX + 1];
+ enum macsec_offload offload, prev_offload;
+ int (*func)(struct macsec_context *ctx);
+ struct nlattr **attrs = info->attrs;
+ struct net_device *dev, *loop_dev;
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+ struct macsec_dev *macsec;
+ struct net *loop_net;
+ int ret;
+
+ if (!attrs[MACSEC_ATTR_IFINDEX])
+ return -EINVAL;
+
+ if (!attrs[MACSEC_ATTR_OFFLOAD])
+ return -EINVAL;
+
+ if (nla_parse_nested_deprecated(tb_offload, MACSEC_OFFLOAD_ATTR_MAX,
+ attrs[MACSEC_ATTR_OFFLOAD],
+ macsec_genl_offload_policy, NULL))
+ return -EINVAL;
+
+ dev = get_dev_from_nl(genl_info_net(info), attrs);
+ if (IS_ERR(dev))
+ return PTR_ERR(dev);
+ macsec = macsec_priv(dev);
+
+ offload = nla_get_u8(tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]);
+ if (macsec->offload == offload)
+ return 0;
+
+ /* Check if the offloading mode is supported by the underlying layers */
+ if (offload != MACSEC_OFFLOAD_OFF &&
+ !macsec_check_offload(offload, macsec))
+ return -EOPNOTSUPP;
+
+ if (offload == MACSEC_OFFLOAD_OFF)
+ goto skip_limitation;
+
+ /* Check the physical interface isn't offloading another interface
+ * first.
+ */
+ for_each_net(loop_net) {
+ for_each_netdev(loop_net, loop_dev) {
+ struct macsec_dev *priv;
+
+ if (!netif_is_macsec(loop_dev))
+ continue;
+
+ priv = macsec_priv(loop_dev);
+
+ if (priv->real_dev == macsec->real_dev &&
+ priv->offload != MACSEC_OFFLOAD_OFF)
+ return -EBUSY;
+ }
+ }
+
+skip_limitation:
+ /* Check if the net device is busy. */
+ if (netif_running(dev))
+ return -EBUSY;
+
+ rtnl_lock();
+
+ prev_offload = macsec->offload;
+ macsec->offload = offload;
+
+ /* Check if the device already has rules configured: we do not support
+ * rules migration.
+ */
+ if (macsec_is_configured(macsec)) {
+ ret = -EBUSY;
+ goto rollback;
+ }
+
+ ops = __macsec_get_ops(offload == MACSEC_OFFLOAD_OFF ? prev_offload : offload,
+ macsec, &ctx);
+ if (!ops) {
+ ret = -EOPNOTSUPP;
+ goto rollback;
+ }
+
+ if (prev_offload == MACSEC_OFFLOAD_OFF)
+ func = ops->mdo_add_secy;
+ else
+ func = ops->mdo_del_secy;
+
+ ctx.secy = &macsec->secy;
+ ret = macsec_offload(func, &ctx);
+ if (ret)
+ goto rollback;
+
+ rtnl_unlock();
+ return 0;
+
+rollback:
+ macsec->offload = prev_offload;
+
+ rtnl_unlock();
+ return ret;
}
static int copy_tx_sa_stats(struct sk_buff *skb,
@@ -2408,12 +2728,13 @@ static noinline_for_stack int
dump_secy(struct macsec_secy *secy, struct net_device *dev,
struct sk_buff *skb, struct netlink_callback *cb)
{
- struct macsec_rx_sc *rx_sc;
+ struct macsec_dev *macsec = netdev_priv(dev);
struct macsec_tx_sc *tx_sc = &secy->tx_sc;
struct nlattr *txsa_list, *rxsc_list;
- int i, j;
- void *hdr;
+ struct macsec_rx_sc *rx_sc;
struct nlattr *attr;
+ void *hdr;
+ int i, j;
hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
&macsec_fam, NLM_F_MULTI, MACSEC_CMD_GET_TXSC);
@@ -2425,6 +2746,13 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
if (nla_put_u32(skb, MACSEC_ATTR_IFINDEX, dev->ifindex))
goto nla_put_failure;
+ attr = nla_nest_start_noflag(skb, MACSEC_ATTR_OFFLOAD);
+ if (!attr)
+ goto nla_put_failure;
+ if (nla_put_u8(skb, MACSEC_OFFLOAD_ATTR_TYPE, macsec->offload))
+ goto nla_put_failure;
+ nla_nest_end(skb, attr);
+
if (nla_put_secy(secy, skb))
goto nla_put_failure;
@@ -2690,6 +3018,12 @@ static const struct genl_ops macsec_genl_ops[] = {
.doit = macsec_upd_rxsa,
.flags = GENL_ADMIN_PERM,
},
+ {
+ .cmd = MACSEC_CMD_UPD_OFFLOAD,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .doit = macsec_upd_offload,
+ .flags = GENL_ADMIN_PERM,
+ },
};
static struct genl_family macsec_fam __ro_after_init = {
@@ -2712,6 +3046,11 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
struct pcpu_secy_stats *secy_stats;
int ret, len;
+ if (macsec_is_offloaded(netdev_priv(dev))) {
+ skb->dev = macsec->real_dev;
+ return dev_queue_xmit(skb);
+ }
+
/* 10.5 */
if (!secy->protect_frames) {
secy_stats = this_cpu_ptr(macsec->stats);
@@ -2825,6 +3164,22 @@ static int macsec_dev_open(struct net_device *dev)
goto clear_allmulti;
}
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(macsec)) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ err = -EOPNOTSUPP;
+ goto clear_allmulti;
+ }
+
+ err = macsec_offload(ops->mdo_dev_open, &ctx);
+ if (err)
+ goto clear_allmulti;
+ }
+
if (netif_carrier_ok(real_dev))
netif_carrier_on(dev);
@@ -2845,6 +3200,16 @@ static int macsec_dev_stop(struct net_device *dev)
netif_carrier_off(dev);
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(macsec)) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(macsec, &ctx);
+ if (ops)
+ macsec_offload(ops->mdo_dev_stop, &ctx);
+ }
+
dev_mc_unsync(real_dev, dev);
dev_uc_unsync(real_dev, dev);
@@ -3076,6 +3441,11 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
+ struct macsec_dev *macsec = macsec_priv(dev);
+ struct macsec_tx_sa tx_sc;
+ struct macsec_secy secy;
+ int ret;
+
if (!data)
return 0;
@@ -3085,7 +3455,41 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[],
data[IFLA_MACSEC_PORT])
return -EINVAL;
- return macsec_changelink_common(dev, data);
+ /* Keep a copy of unmodified secy and tx_sc, in case the offload
+ * propagation fails, to revert macsec_changelink_common.
+ */
+ memcpy(&secy, &macsec->secy, sizeof(secy));
+ memcpy(&tx_sc, &macsec->secy.tx_sc, sizeof(tx_sc));
+
+ ret = macsec_changelink_common(dev, data);
+ if (ret)
+ return ret;
+
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(macsec)) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+ int ret;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (!ops) {
+ ret = -EOPNOTSUPP;
+ goto cleanup;
+ }
+
+ ctx.secy = &macsec->secy;
+ ret = macsec_offload(ops->mdo_upd_secy, &ctx);
+ if (ret)
+ goto cleanup;
+ }
+
+ return 0;
+
+cleanup:
+ memcpy(&macsec->secy.tx_sc, &tx_sc, sizeof(tx_sc));
+ memcpy(&macsec->secy, &secy, sizeof(secy));
+
+ return ret;
}
static void macsec_del_dev(struct macsec_dev *macsec)
@@ -3128,6 +3532,18 @@ static void macsec_dellink(struct net_device *dev, struct list_head *head)
struct net_device *real_dev = macsec->real_dev;
struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev);
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(macsec)) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (ops) {
+ ctx.secy = &macsec->secy;
+ macsec_offload(ops->mdo_del_secy, &ctx);
+ }
+ }
+
macsec_common_dellink(dev, head);
if (list_empty(&rxd->secys)) {
@@ -3239,6 +3655,9 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
macsec->real_dev = real_dev;
+ /* MACsec offloading is off by default */
+ macsec->offload = MACSEC_OFFLOAD_OFF;
+
if (data && data[IFLA_MACSEC_ICV_LEN])
icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]);
dev->mtu = real_dev->mtu - icv_len - macsec_extra_len(true);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index d066cf58..81aa7ad 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -513,10 +513,11 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
const struct macvlan_dev *dest;
if (vlan->mode == MACVLAN_MODE_BRIDGE) {
- const struct ethhdr *eth = (void *)skb->data;
+ const struct ethhdr *eth = skb_eth_hdr(skb);
/* send to other bridge ports directly */
if (is_multicast_ether_addr(eth->h_dest)) {
+ skb_reset_mac_header(skb);
macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE);
goto xmit_world;
}
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 059711e..b53fbc0 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -53,7 +53,7 @@ static ssize_t nsim_dev_take_snapshot_write(struct file *file,
get_random_bytes(dummy_data, NSIM_DEV_DUMMY_REGION_SIZE);
- id = devlink_region_shapshot_id_get(priv_to_devlink(nsim_dev));
+ id = devlink_region_snapshot_id_get(priv_to_devlink(nsim_dev));
err = devlink_region_snapshot_create(nsim_dev->dummy_region,
dummy_data, id, kfree);
if (err) {
@@ -270,7 +270,7 @@ struct nsim_trap_data {
};
/* All driver-specific traps must be documented in
- * Documentation/networking/devlink-trap-netdevsim.rst
+ * Documentation/networking/devlink/netdevsim.rst
*/
enum {
NSIM_TRAP_ID_BASE = DEVLINK_TRAP_GENERIC_ID_MAX,
diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c
index b5df308..f32d56a 100644
--- a/drivers/net/netdevsim/fib.c
+++ b/drivers/net/netdevsim/fib.c
@@ -14,6 +14,12 @@
* THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
*/
+#include <linux/in6.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/rhashtable.h>
+#include <linux/spinlock_types.h>
+#include <linux/types.h>
#include <net/fib_notifier.h>
#include <net/ip_fib.h>
#include <net/ip6_fib.h>
@@ -36,6 +42,48 @@ struct nsim_fib_data {
struct notifier_block fib_nb;
struct nsim_per_fib_data ipv4;
struct nsim_per_fib_data ipv6;
+ struct rhashtable fib_rt_ht;
+ struct list_head fib_rt_list;
+ spinlock_t fib_lock; /* Protects hashtable, list and accounting */
+ struct devlink *devlink;
+};
+
+struct nsim_fib_rt_key {
+ unsigned char addr[sizeof(struct in6_addr)];
+ unsigned char prefix_len;
+ int family;
+ u32 tb_id;
+};
+
+struct nsim_fib_rt {
+ struct nsim_fib_rt_key key;
+ struct rhash_head ht_node;
+ struct list_head list; /* Member of fib_rt_list */
+};
+
+struct nsim_fib4_rt {
+ struct nsim_fib_rt common;
+ struct fib_info *fi;
+ u8 tos;
+ u8 type;
+};
+
+struct nsim_fib6_rt {
+ struct nsim_fib_rt common;
+ struct list_head nh_list;
+ unsigned int nhs;
+};
+
+struct nsim_fib6_rt_nh {
+ struct list_head list; /* Member of nh_list */
+ struct fib6_info *rt;
+};
+
+static const struct rhashtable_params nsim_fib_rt_ht_params = {
+ .key_offset = offsetof(struct nsim_fib_rt, key),
+ .head_offset = offsetof(struct nsim_fib_rt, ht_node),
+ .key_len = sizeof(struct nsim_fib_rt_key),
+ .automatic_shrinking = true,
};
u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
@@ -144,18 +192,556 @@ static int nsim_fib_account(struct nsim_fib_entry *entry, bool add,
return err;
}
-static int nsim_fib_event(struct nsim_fib_data *data,
- struct fib_notifier_info *info, bool add)
+static void nsim_fib_rt_init(struct nsim_fib_data *data,
+ struct nsim_fib_rt *fib_rt, const void *addr,
+ size_t addr_len, unsigned int prefix_len,
+ int family, u32 tb_id)
{
- struct netlink_ext_ack *extack = info->extack;
+ memcpy(fib_rt->key.addr, addr, addr_len);
+ fib_rt->key.prefix_len = prefix_len;
+ fib_rt->key.family = family;
+ fib_rt->key.tb_id = tb_id;
+ list_add(&fib_rt->list, &data->fib_rt_list);
+}
+
+static void nsim_fib_rt_fini(struct nsim_fib_rt *fib_rt)
+{
+ list_del(&fib_rt->list);
+}
+
+static struct nsim_fib_rt *nsim_fib_rt_lookup(struct rhashtable *fib_rt_ht,
+ const void *addr, size_t addr_len,
+ unsigned int prefix_len,
+ int family, u32 tb_id)
+{
+ struct nsim_fib_rt_key key;
+
+ memset(&key, 0, sizeof(key));
+ memcpy(key.addr, addr, addr_len);
+ key.prefix_len = prefix_len;
+ key.family = family;
+ key.tb_id = tb_id;
+
+ return rhashtable_lookup_fast(fib_rt_ht, &key, nsim_fib_rt_ht_params);
+}
+
+static struct nsim_fib4_rt *
+nsim_fib4_rt_create(struct nsim_fib_data *data,
+ struct fib_entry_notifier_info *fen_info)
+{
+ struct nsim_fib4_rt *fib4_rt;
+
+ fib4_rt = kzalloc(sizeof(*fib4_rt), GFP_ATOMIC);
+ if (!fib4_rt)
+ return NULL;
+
+ nsim_fib_rt_init(data, &fib4_rt->common, &fen_info->dst, sizeof(u32),
+ fen_info->dst_len, AF_INET, fen_info->tb_id);
+
+ fib4_rt->fi = fen_info->fi;
+ fib_info_hold(fib4_rt->fi);
+ fib4_rt->tos = fen_info->tos;
+ fib4_rt->type = fen_info->type;
+
+ return fib4_rt;
+}
+
+static void nsim_fib4_rt_destroy(struct nsim_fib4_rt *fib4_rt)
+{
+ fib_info_put(fib4_rt->fi);
+ nsim_fib_rt_fini(&fib4_rt->common);
+ kfree(fib4_rt);
+}
+
+static struct nsim_fib4_rt *
+nsim_fib4_rt_lookup(struct rhashtable *fib_rt_ht,
+ const struct fib_entry_notifier_info *fen_info)
+{
+ struct nsim_fib_rt *fib_rt;
+
+ fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &fen_info->dst, sizeof(u32),
+ fen_info->dst_len, AF_INET,
+ fen_info->tb_id);
+ if (!fib_rt)
+ return NULL;
+
+ return container_of(fib_rt, struct nsim_fib4_rt, common);
+}
+
+static void nsim_fib4_rt_hw_flags_set(struct net *net,
+ const struct nsim_fib4_rt *fib4_rt,
+ bool trap)
+{
+ u32 *p_dst = (u32 *) fib4_rt->common.key.addr;
+ int dst_len = fib4_rt->common.key.prefix_len;
+ struct fib_rt_info fri;
+
+ fri.fi = fib4_rt->fi;
+ fri.tb_id = fib4_rt->common.key.tb_id;
+ fri.dst = cpu_to_be32(*p_dst);
+ fri.dst_len = dst_len;
+ fri.tos = fib4_rt->tos;
+ fri.type = fib4_rt->type;
+ fri.offload = false;
+ fri.trap = trap;
+ fib_alias_hw_flags_set(net, &fri);
+}
+
+static int nsim_fib4_rt_add(struct nsim_fib_data *data,
+ struct nsim_fib4_rt *fib4_rt,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = devlink_net(data->devlink);
+ int err;
+
+ err = nsim_fib_account(&data->ipv4.fib, true, extack);
+ if (err)
+ return err;
+
+ err = rhashtable_insert_fast(&data->fib_rt_ht,
+ &fib4_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to insert IPv4 route");
+ goto err_fib_dismiss;
+ }
+
+ nsim_fib4_rt_hw_flags_set(net, fib4_rt, true);
+
+ return 0;
+
+err_fib_dismiss:
+ nsim_fib_account(&data->ipv4.fib, false, extack);
+ return err;
+}
+
+static int nsim_fib4_rt_replace(struct nsim_fib_data *data,
+ struct nsim_fib4_rt *fib4_rt,
+ struct nsim_fib4_rt *fib4_rt_old,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = devlink_net(data->devlink);
+ int err;
+
+ /* We are replacing a route, so no need to change the accounting. */
+ err = rhashtable_replace_fast(&data->fib_rt_ht,
+ &fib4_rt_old->common.ht_node,
+ &fib4_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to replace IPv4 route");
+ return err;
+ }
+
+ nsim_fib4_rt_hw_flags_set(net, fib4_rt, true);
+
+ nsim_fib4_rt_hw_flags_set(net, fib4_rt_old, false);
+ nsim_fib4_rt_destroy(fib4_rt_old);
+
+ return 0;
+}
+
+static int nsim_fib4_rt_insert(struct nsim_fib_data *data,
+ struct fib_entry_notifier_info *fen_info)
+{
+ struct netlink_ext_ack *extack = fen_info->info.extack;
+ struct nsim_fib4_rt *fib4_rt, *fib4_rt_old;
+ int err;
+
+ fib4_rt = nsim_fib4_rt_create(data, fen_info);
+ if (!fib4_rt)
+ return -ENOMEM;
+
+ fib4_rt_old = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info);
+ if (!fib4_rt_old)
+ err = nsim_fib4_rt_add(data, fib4_rt, extack);
+ else
+ err = nsim_fib4_rt_replace(data, fib4_rt, fib4_rt_old, extack);
+
+ if (err)
+ nsim_fib4_rt_destroy(fib4_rt);
+
+ return err;
+}
+
+static void nsim_fib4_rt_remove(struct nsim_fib_data *data,
+ const struct fib_entry_notifier_info *fen_info)
+{
+ struct netlink_ext_ack *extack = fen_info->info.extack;
+ struct nsim_fib4_rt *fib4_rt;
+
+ fib4_rt = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info);
+ if (WARN_ON_ONCE(!fib4_rt))
+ return;
+
+ rhashtable_remove_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ nsim_fib_account(&data->ipv4.fib, false, extack);
+ nsim_fib4_rt_destroy(fib4_rt);
+}
+
+static int nsim_fib4_event(struct nsim_fib_data *data,
+ struct fib_notifier_info *info,
+ unsigned long event)
+{
+ struct fib_entry_notifier_info *fen_info;
+ int err = 0;
+
+ fen_info = container_of(info, struct fib_entry_notifier_info, info);
+
+ if (fen_info->fi->nh) {
+ NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported");
+ return 0;
+ }
+
+ switch (event) {
+ case FIB_EVENT_ENTRY_REPLACE:
+ err = nsim_fib4_rt_insert(data, fen_info);
+ break;
+ case FIB_EVENT_ENTRY_DEL:
+ nsim_fib4_rt_remove(data, fen_info);
+ break;
+ default:
+ break;
+ }
+
+ return err;
+}
+
+static struct nsim_fib6_rt_nh *
+nsim_fib6_rt_nh_find(const struct nsim_fib6_rt *fib6_rt,
+ const struct fib6_info *rt)
+{
+ struct nsim_fib6_rt_nh *fib6_rt_nh;
+
+ list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list) {
+ if (fib6_rt_nh->rt == rt)
+ return fib6_rt_nh;
+ }
+
+ return NULL;
+}
+
+static int nsim_fib6_rt_nh_add(struct nsim_fib6_rt *fib6_rt,
+ struct fib6_info *rt)
+{
+ struct nsim_fib6_rt_nh *fib6_rt_nh;
+
+ fib6_rt_nh = kzalloc(sizeof(*fib6_rt_nh), GFP_ATOMIC);
+ if (!fib6_rt_nh)
+ return -ENOMEM;
+
+ fib6_info_hold(rt);
+ fib6_rt_nh->rt = rt;
+ list_add_tail(&fib6_rt_nh->list, &fib6_rt->nh_list);
+ fib6_rt->nhs++;
+
+ return 0;
+}
+
+static void nsim_fib6_rt_nh_del(struct nsim_fib6_rt *fib6_rt,
+ const struct fib6_info *rt)
+{
+ struct nsim_fib6_rt_nh *fib6_rt_nh;
+
+ fib6_rt_nh = nsim_fib6_rt_nh_find(fib6_rt, rt);
+ if (WARN_ON_ONCE(!fib6_rt_nh))
+ return;
+
+ fib6_rt->nhs--;
+ list_del(&fib6_rt_nh->list);
+#if IS_ENABLED(CONFIG_IPV6)
+ fib6_info_release(fib6_rt_nh->rt);
+#endif
+ kfree(fib6_rt_nh);
+}
+
+static struct nsim_fib6_rt *
+nsim_fib6_rt_create(struct nsim_fib_data *data,
+ struct fib6_entry_notifier_info *fen6_info)
+{
+ struct fib6_info *iter, *rt = fen6_info->rt;
+ struct nsim_fib6_rt *fib6_rt;
+ int i = 0;
+ int err;
+
+ fib6_rt = kzalloc(sizeof(*fib6_rt), GFP_ATOMIC);
+ if (!fib6_rt)
+ return ERR_PTR(-ENOMEM);
+
+ nsim_fib_rt_init(data, &fib6_rt->common, &rt->fib6_dst.addr,
+ sizeof(rt->fib6_dst.addr), rt->fib6_dst.plen, AF_INET6,
+ rt->fib6_table->tb6_id);
+
+ /* We consider a multipath IPv6 route as one entry, but it can be made
+ * up from several fib6_info structs (one for each nexthop), so we
+ * add them all to the same list under the entry.
+ */
+ INIT_LIST_HEAD(&fib6_rt->nh_list);
+
+ err = nsim_fib6_rt_nh_add(fib6_rt, rt);
+ if (err)
+ goto err_fib_rt_fini;
+
+ if (!fen6_info->nsiblings)
+ return fib6_rt;
+
+ list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
+ if (i == fen6_info->nsiblings)
+ break;
+
+ err = nsim_fib6_rt_nh_add(fib6_rt, iter);
+ if (err)
+ goto err_fib6_rt_nh_del;
+ i++;
+ }
+ WARN_ON_ONCE(i != fen6_info->nsiblings);
+
+ return fib6_rt;
+
+err_fib6_rt_nh_del:
+ list_for_each_entry_continue_reverse(iter, &rt->fib6_siblings,
+ fib6_siblings)
+ nsim_fib6_rt_nh_del(fib6_rt, iter);
+ nsim_fib6_rt_nh_del(fib6_rt, rt);
+err_fib_rt_fini:
+ nsim_fib_rt_fini(&fib6_rt->common);
+ kfree(fib6_rt);
+ return ERR_PTR(err);
+}
+
+static void nsim_fib6_rt_destroy(struct nsim_fib6_rt *fib6_rt)
+{
+ struct nsim_fib6_rt_nh *iter, *tmp;
+
+ list_for_each_entry_safe(iter, tmp, &fib6_rt->nh_list, list)
+ nsim_fib6_rt_nh_del(fib6_rt, iter->rt);
+ WARN_ON_ONCE(!list_empty(&fib6_rt->nh_list));
+ nsim_fib_rt_fini(&fib6_rt->common);
+ kfree(fib6_rt);
+}
+
+static struct nsim_fib6_rt *
+nsim_fib6_rt_lookup(struct rhashtable *fib_rt_ht, const struct fib6_info *rt)
+{
+ struct nsim_fib_rt *fib_rt;
+
+ fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &rt->fib6_dst.addr,
+ sizeof(rt->fib6_dst.addr),
+ rt->fib6_dst.plen, AF_INET6,
+ rt->fib6_table->tb6_id);
+ if (!fib_rt)
+ return NULL;
+
+ return container_of(fib_rt, struct nsim_fib6_rt, common);
+}
+
+static int nsim_fib6_rt_append(struct nsim_fib_data *data,
+ struct fib6_entry_notifier_info *fen6_info)
+{
+ struct fib6_info *iter, *rt = fen6_info->rt;
+ struct nsim_fib6_rt *fib6_rt;
+ int i = 0;
+ int err;
+
+ fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt);
+ if (WARN_ON_ONCE(!fib6_rt))
+ return -EINVAL;
+
+ err = nsim_fib6_rt_nh_add(fib6_rt, rt);
+ if (err)
+ return err;
+ rt->trap = true;
+
+ if (!fen6_info->nsiblings)
+ return 0;
+
+ list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
+ if (i == fen6_info->nsiblings)
+ break;
+
+ err = nsim_fib6_rt_nh_add(fib6_rt, iter);
+ if (err)
+ goto err_fib6_rt_nh_del;
+ iter->trap = true;
+ i++;
+ }
+ WARN_ON_ONCE(i != fen6_info->nsiblings);
+
+ return 0;
+
+err_fib6_rt_nh_del:
+ list_for_each_entry_continue_reverse(iter, &rt->fib6_siblings,
+ fib6_siblings) {
+ iter->trap = false;
+ nsim_fib6_rt_nh_del(fib6_rt, iter);
+ }
+ rt->trap = false;
+ nsim_fib6_rt_nh_del(fib6_rt, rt);
+ return err;
+}
+
+static void nsim_fib6_rt_hw_flags_set(const struct nsim_fib6_rt *fib6_rt,
+ bool trap)
+{
+ struct nsim_fib6_rt_nh *fib6_rt_nh;
+
+ list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list)
+ fib6_info_hw_flags_set(fib6_rt_nh->rt, false, trap);
+}
+
+static int nsim_fib6_rt_add(struct nsim_fib_data *data,
+ struct nsim_fib6_rt *fib6_rt,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ err = nsim_fib_account(&data->ipv6.fib, true, extack);
+ if (err)
+ return err;
+
+ err = rhashtable_insert_fast(&data->fib_rt_ht,
+ &fib6_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to insert IPv6 route");
+ goto err_fib_dismiss;
+ }
+
+ nsim_fib6_rt_hw_flags_set(fib6_rt, true);
+
+ return 0;
+
+err_fib_dismiss:
+ nsim_fib_account(&data->ipv6.fib, false, extack);
+ return err;
+}
+
+static int nsim_fib6_rt_replace(struct nsim_fib_data *data,
+ struct nsim_fib6_rt *fib6_rt,
+ struct nsim_fib6_rt *fib6_rt_old,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ /* We are replacing a route, so no need to change the accounting. */
+ err = rhashtable_replace_fast(&data->fib_rt_ht,
+ &fib6_rt_old->common.ht_node,
+ &fib6_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to replace IPv6 route");
+ return err;
+ }
+
+ nsim_fib6_rt_hw_flags_set(fib6_rt, true);
+
+ nsim_fib6_rt_hw_flags_set(fib6_rt_old, false);
+ nsim_fib6_rt_destroy(fib6_rt_old);
+
+ return 0;
+}
+
+static int nsim_fib6_rt_insert(struct nsim_fib_data *data,
+ struct fib6_entry_notifier_info *fen6_info)
+{
+ struct netlink_ext_ack *extack = fen6_info->info.extack;
+ struct nsim_fib6_rt *fib6_rt, *fib6_rt_old;
+ int err;
+
+ fib6_rt = nsim_fib6_rt_create(data, fen6_info);
+ if (IS_ERR(fib6_rt))
+ return PTR_ERR(fib6_rt);
+
+ fib6_rt_old = nsim_fib6_rt_lookup(&data->fib_rt_ht, fen6_info->rt);
+ if (!fib6_rt_old)
+ err = nsim_fib6_rt_add(data, fib6_rt, extack);
+ else
+ err = nsim_fib6_rt_replace(data, fib6_rt, fib6_rt_old, extack);
+
+ if (err)
+ nsim_fib6_rt_destroy(fib6_rt);
+
+ return err;
+}
+
+static void
+nsim_fib6_rt_remove(struct nsim_fib_data *data,
+ const struct fib6_entry_notifier_info *fen6_info)
+{
+ struct netlink_ext_ack *extack = fen6_info->info.extack;
+ struct nsim_fib6_rt *fib6_rt;
+
+ /* Multipath routes are first added to the FIB trie and only then
+ * notified. If we vetoed the addition, we will get a delete
+ * notification for a route we do not have. Therefore, do not warn if
+ * route was not found.
+ */
+ fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, fen6_info->rt);
+ if (!fib6_rt)
+ return;
+
+ /* If not all the nexthops are deleted, then only reduce the nexthop
+ * group.
+ */
+ if (fen6_info->nsiblings + 1 != fib6_rt->nhs) {
+ nsim_fib6_rt_nh_del(fib6_rt, fen6_info->rt);
+ return;
+ }
+
+ rhashtable_remove_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ nsim_fib_account(&data->ipv6.fib, false, extack);
+ nsim_fib6_rt_destroy(fib6_rt);
+}
+
+static int nsim_fib6_event(struct nsim_fib_data *data,
+ struct fib_notifier_info *info,
+ unsigned long event)
+{
+ struct fib6_entry_notifier_info *fen6_info;
+ int err = 0;
+
+ fen6_info = container_of(info, struct fib6_entry_notifier_info, info);
+
+ if (fen6_info->rt->nh) {
+ NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported");
+ return 0;
+ }
+
+ if (fen6_info->rt->fib6_src.plen) {
+ NL_SET_ERR_MSG_MOD(info->extack, "IPv6 source-specific route is not supported");
+ return 0;
+ }
+
+ switch (event) {
+ case FIB_EVENT_ENTRY_REPLACE:
+ err = nsim_fib6_rt_insert(data, fen6_info);
+ break;
+ case FIB_EVENT_ENTRY_APPEND:
+ err = nsim_fib6_rt_append(data, fen6_info);
+ break;
+ case FIB_EVENT_ENTRY_DEL:
+ nsim_fib6_rt_remove(data, fen6_info);
+ break;
+ default:
+ break;
+ }
+
+ return err;
+}
+
+static int nsim_fib_event(struct nsim_fib_data *data,
+ struct fib_notifier_info *info, unsigned long event)
+{
int err = 0;
switch (info->family) {
case AF_INET:
- err = nsim_fib_account(&data->ipv4.fib, add, extack);
+ err = nsim_fib4_event(data, info, event);
break;
case AF_INET6:
- err = nsim_fib_account(&data->ipv6.fib, add, extack);
+ err = nsim_fib6_event(data, info, event);
break;
}
@@ -170,6 +756,9 @@ static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event,
struct fib_notifier_info *info = ptr;
int err = 0;
+ /* IPv6 routes can be added via RAs from softIRQ. */
+ spin_lock_bh(&data->fib_lock);
+
switch (event) {
case FIB_EVENT_RULE_ADD: /* fall through */
case FIB_EVENT_RULE_DEL:
@@ -178,23 +767,74 @@ static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event,
break;
case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+ case FIB_EVENT_ENTRY_APPEND: /* fall through */
case FIB_EVENT_ENTRY_DEL:
- err = nsim_fib_event(data, info, event != FIB_EVENT_ENTRY_DEL);
+ err = nsim_fib_event(data, info, event);
break;
}
+ spin_unlock_bh(&data->fib_lock);
+
return notifier_from_errno(err);
}
+static void nsim_fib4_rt_free(struct nsim_fib_rt *fib_rt,
+ struct nsim_fib_data *data)
+{
+ struct devlink *devlink = data->devlink;
+ struct nsim_fib4_rt *fib4_rt;
+
+ fib4_rt = container_of(fib_rt, struct nsim_fib4_rt, common);
+ nsim_fib4_rt_hw_flags_set(devlink_net(devlink), fib4_rt, false);
+ nsim_fib_account(&data->ipv4.fib, false, NULL);
+ nsim_fib4_rt_destroy(fib4_rt);
+}
+
+static void nsim_fib6_rt_free(struct nsim_fib_rt *fib_rt,
+ struct nsim_fib_data *data)
+{
+ struct nsim_fib6_rt *fib6_rt;
+
+ fib6_rt = container_of(fib_rt, struct nsim_fib6_rt, common);
+ nsim_fib6_rt_hw_flags_set(fib6_rt, false);
+ nsim_fib_account(&data->ipv6.fib, false, NULL);
+ nsim_fib6_rt_destroy(fib6_rt);
+}
+
+static void nsim_fib_rt_free(void *ptr, void *arg)
+{
+ struct nsim_fib_rt *fib_rt = ptr;
+ struct nsim_fib_data *data = arg;
+
+ switch (fib_rt->key.family) {
+ case AF_INET:
+ nsim_fib4_rt_free(fib_rt, data);
+ break;
+ case AF_INET6:
+ nsim_fib6_rt_free(fib_rt, data);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ }
+}
+
/* inconsistent dump, trying again */
static void nsim_fib_dump_inconsistent(struct notifier_block *nb)
{
struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data,
fib_nb);
+ struct nsim_fib_rt *fib_rt, *fib_rt_tmp;
- data->ipv4.fib.num = 0ULL;
+ /* The notifier block is still not registered, so we do not need to
+ * take any locks here.
+ */
+ list_for_each_entry_safe(fib_rt, fib_rt_tmp, &data->fib_rt_list, list) {
+ rhashtable_remove_fast(&data->fib_rt_ht, &fib_rt->ht_node,
+ nsim_fib_rt_ht_params);
+ nsim_fib_rt_free(fib_rt, data);
+ }
+
data->ipv4.rules.num = 0ULL;
- data->ipv6.fib.num = 0ULL;
data->ipv6.rules.num = 0ULL;
}
@@ -255,6 +895,13 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
return ERR_PTR(-ENOMEM);
+ data->devlink = devlink;
+
+ spin_lock_init(&data->fib_lock);
+ INIT_LIST_HEAD(&data->fib_rt_list);
+ err = rhashtable_init(&data->fib_rt_ht, &nsim_fib_rt_ht_params);
+ if (err)
+ goto err_data_free;
nsim_fib_set_max_all(data, devlink);
@@ -263,7 +910,7 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
nsim_fib_dump_inconsistent, extack);
if (err) {
pr_err("Failed to register fib notifier\n");
- goto err_out;
+ goto err_rhashtable_destroy;
}
devlink_resource_occ_get_register(devlink,
@@ -284,7 +931,10 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
data);
return data;
-err_out:
+err_rhashtable_destroy:
+ rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free,
+ data);
+err_data_free:
kfree(data);
return ERR_PTR(err);
}
@@ -300,5 +950,8 @@ void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data)
devlink_resource_occ_get_unregister(devlink,
NSIM_RESOURCE_IPV4_FIB);
unregister_fib_notifier(devlink_net(devlink), &data->fib_nb);
+ rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free,
+ data);
+ WARN_ON_ONCE(!list_empty(&data->fib_rt_list));
kfree(data);
}
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 2e01627..71fc778 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -346,14 +346,15 @@
Currently supports dm9161e and dm9131
config DP83822_PHY
- tristate "Texas Instruments DP83822 PHY"
+ tristate "Texas Instruments DP83822/825/826 PHYs"
---help---
- Supports the DP83822 PHY.
+ Supports the DP83822, DP83825I, DP83825CM, DP83825CS, DP83825S,
+ DP83826C and DP83826NC PHYs.
config DP83TC811_PHY
- tristate "Texas Instruments DP83TC822 PHY"
+ tristate "Texas Instruments DP83TC811 PHY"
---help---
- Supports the DP83TC822 PHY.
+ Supports the DP83TC811 PHY.
config DP83848_PHY
tristate "Texas Instruments DP83848 PHY"
@@ -437,6 +438,9 @@
config MICROSEMI_PHY
tristate "Microsemi PHYs"
+ depends on MACSEC || MACSEC=n
+ select CRYPTO_AES
+ select CRYPTO_ECB
---help---
Currently supports VSC8514, VSC8530, VSC8531, VSC8540 and VSC8541 PHYs
diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index cf5a391..c7eabe4 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -145,7 +145,7 @@ struct adin_clause45_mmd_map {
u16 adin_regnum;
};
-static struct adin_clause45_mmd_map adin_clause45_mmd_map[] = {
+static const struct adin_clause45_mmd_map adin_clause45_mmd_map[] = {
{ MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE, ADIN1300_EEE_CAP_REG },
{ MDIO_MMD_AN, MDIO_AN_EEE_LPABLE, ADIN1300_EEE_LPABLE_REG },
{ MDIO_MMD_AN, MDIO_AN_EEE_ADV, ADIN1300_EEE_ADV_REG },
@@ -159,7 +159,7 @@ struct adin_hw_stat {
u16 reg2;
};
-static struct adin_hw_stat adin_hw_stats[] = {
+static const struct adin_hw_stat adin_hw_stats[] = {
{ "total_frames_checked_count", 0x940A, 0x940B }, /* hi + lo */
{ "length_error_frames_count", 0x940C },
{ "alignment_error_frames_count", 0x940D },
@@ -456,7 +456,7 @@ static int adin_phy_config_intr(struct phy_device *phydev)
static int adin_cl45_to_adin_reg(struct phy_device *phydev, int devad,
u16 cl45_regnum)
{
- struct adin_clause45_mmd_map *m;
+ const struct adin_clause45_mmd_map *m;
int i;
if (devad == MDIO_MMD_VEND1)
@@ -625,7 +625,7 @@ static int adin_soft_reset(struct phy_device *phydev)
if (rc < 0)
return rc;
- msleep(10);
+ msleep(20);
/* If we get a read error something may be wrong */
rc = phy_read_mmd(phydev, MDIO_MMD_VEND1,
@@ -650,7 +650,7 @@ static void adin_get_strings(struct phy_device *phydev, u8 *data)
}
static int adin_read_mmd_stat_regs(struct phy_device *phydev,
- struct adin_hw_stat *stat,
+ const struct adin_hw_stat *stat,
u32 *val)
{
int ret;
@@ -676,7 +676,7 @@ static int adin_read_mmd_stat_regs(struct phy_device *phydev,
static u64 adin_get_stat(struct phy_device *phydev, int i)
{
- struct adin_hw_stat *stat = &adin_hw_stats[i];
+ const struct adin_hw_stat *stat = &adin_hw_stats[i];
struct adin_priv *priv = phydev->priv;
u32 val;
int ret;
diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c
index 975789d..31927b2 100644
--- a/drivers/net/phy/aquantia_main.c
+++ b/drivers/net/phy/aquantia_main.c
@@ -358,9 +358,11 @@ static int aqr107_read_status(struct phy_device *phydev)
switch (FIELD_GET(MDIO_PHYXS_VEND_IF_STATUS_TYPE_MASK, val)) {
case MDIO_PHYXS_VEND_IF_STATUS_TYPE_KR:
- case MDIO_PHYXS_VEND_IF_STATUS_TYPE_XFI:
phydev->interface = PHY_INTERFACE_MODE_10GKR;
break;
+ case MDIO_PHYXS_VEND_IF_STATUS_TYPE_XFI:
+ phydev->interface = PHY_INTERFACE_MODE_10GBASER;
+ break;
case MDIO_PHYXS_VEND_IF_STATUS_TYPE_USXGMII:
phydev->interface = PHY_INTERFACE_MODE_USXGMII;
break;
@@ -493,7 +495,8 @@ static int aqr107_config_init(struct phy_device *phydev)
phydev->interface != PHY_INTERFACE_MODE_2500BASEX &&
phydev->interface != PHY_INTERFACE_MODE_XGMII &&
phydev->interface != PHY_INTERFACE_MODE_USXGMII &&
- phydev->interface != PHY_INTERFACE_MODE_10GKR)
+ phydev->interface != PHY_INTERFACE_MODE_10GKR &&
+ phydev->interface != PHY_INTERFACE_MODE_10GBASER)
return -ENODEV;
WARN(phydev->interface == PHY_INTERFACE_MODE_XGMII,
diff --git a/drivers/net/phy/bcm84881.c b/drivers/net/phy/bcm84881.c
index db59911..14d55a7 100644
--- a/drivers/net/phy/bcm84881.c
+++ b/drivers/net/phy/bcm84881.c
@@ -53,7 +53,7 @@ static int bcm84881_config_init(struct phy_device *phydev)
switch (phydev->interface) {
case PHY_INTERFACE_MODE_SGMII:
case PHY_INTERFACE_MODE_2500BASEX:
- case PHY_INTERFACE_MODE_10GKR:
+ case PHY_INTERFACE_MODE_10GBASER:
break;
default:
return -ENODEV;
@@ -218,7 +218,7 @@ static int bcm84881_read_status(struct phy_device *phydev)
if (mode == 1 || mode == 2)
phydev->interface = PHY_INTERFACE_MODE_SGMII;
else if (mode == 3)
- phydev->interface = PHY_INTERFACE_MODE_10GKR;
+ phydev->interface = PHY_INTERFACE_MODE_10GBASER;
else if (mode == 4)
phydev->interface = PHY_INTERFACE_MODE_2500BASEX;
switch (mode & 7) {
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index 8a4b1d1..fe9aa3a 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -1,6 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/*
- * Driver for the Texas Instruments DP83822 PHY
+/* Driver for the Texas Instruments DP83822, DP83825 and DP83826 PHYs.
*
* Copyright (C) 2017 Texas Instruments Inc.
*/
@@ -15,7 +14,12 @@
#include <linux/netdevice.h>
#define DP83822_PHY_ID 0x2000a240
+#define DP83825S_PHY_ID 0x2000a140
#define DP83825I_PHY_ID 0x2000a150
+#define DP83825CM_PHY_ID 0x2000a160
+#define DP83825CS_PHY_ID 0x2000a170
+#define DP83826C_PHY_ID 0x2000a130
+#define DP83826NC_PHY_ID 0x2000a110
#define DP83822_DEVADDR 0x1f
@@ -319,12 +323,22 @@ static int dp83822_resume(struct phy_device *phydev)
static struct phy_driver dp83822_driver[] = {
DP83822_PHY_DRIVER(DP83822_PHY_ID, "TI DP83822"),
DP83822_PHY_DRIVER(DP83825I_PHY_ID, "TI DP83825I"),
+ DP83822_PHY_DRIVER(DP83826C_PHY_ID, "TI DP83826C"),
+ DP83822_PHY_DRIVER(DP83826NC_PHY_ID, "TI DP83826NC"),
+ DP83822_PHY_DRIVER(DP83825S_PHY_ID, "TI DP83825S"),
+ DP83822_PHY_DRIVER(DP83825CM_PHY_ID, "TI DP83825M"),
+ DP83822_PHY_DRIVER(DP83825CS_PHY_ID, "TI DP83825CS"),
};
module_phy_driver(dp83822_driver);
static struct mdio_device_id __maybe_unused dp83822_tbl[] = {
{ DP83822_PHY_ID, 0xfffffff0 },
{ DP83825I_PHY_ID, 0xfffffff0 },
+ { DP83826C_PHY_ID, 0xfffffff0 },
+ { DP83826NC_PHY_ID, 0xfffffff0 },
+ { DP83825S_PHY_ID, 0xfffffff0 },
+ { DP83825CM_PHY_ID, 0xfffffff0 },
+ { DP83825CS_PHY_ID, 0xfffffff0 },
{ },
};
MODULE_DEVICE_TABLE(mdio, dp83822_tbl);
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index adda0d0..967f57e 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -99,6 +99,7 @@
#define DP83867_PHYCR_TX_FIFO_DEPTH_MASK GENMASK(15, 14)
#define DP83867_PHYCR_RX_FIFO_DEPTH_MASK GENMASK(13, 12)
#define DP83867_PHYCR_RESERVED_MASK BIT(11)
+#define DP83867_PHYCR_FORCE_LINK_GOOD BIT(10)
/* RGMIIDCTL bits */
#define DP83867_RGMII_TX_CLK_DELAY_MAX 0xf
@@ -635,7 +636,12 @@ static int dp83867_phy_reset(struct phy_device *phydev)
usleep_range(10, 20);
- return 0;
+ /* After reset FORCE_LINK_GOOD bit is set. Although the
+ * default value should be unset. Disable FORCE_LINK_GOOD
+ * for the phy to work properly.
+ */
+ return phy_modify(phydev, MII_DP83867_PHYCTRL,
+ DP83867_PHYCR_FORCE_LINK_GOOD, 0);
}
static struct phy_driver dp83867_driver[] = {
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 7c5265f..4a3d34f 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -210,18 +210,15 @@ static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np)
* Linux device associated with it, we simply have obtain
* the GPIO descriptor from the device tree like this.
*/
- gpiod = gpiod_get_from_of_node(fixed_link_node, "link-gpios", 0,
- GPIOD_IN, "mdio");
- of_node_put(fixed_link_node);
- if (IS_ERR(gpiod)) {
- if (PTR_ERR(gpiod) == -EPROBE_DEFER)
- return gpiod;
-
+ gpiod = fwnode_gpiod_get_index(of_fwnode_handle(fixed_link_node),
+ "link", 0, GPIOD_IN, "mdio");
+ if (IS_ERR(gpiod) && PTR_ERR(gpiod) != -EPROBE_DEFER) {
if (PTR_ERR(gpiod) != -ENOENT)
pr_err("error getting GPIO for fixed link %pOF, proceed without\n",
fixed_link_node);
gpiod = NULL;
}
+ of_node_put(fixed_link_node);
return gpiod;
}
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 512f27b..64c9f3bb 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -216,7 +216,7 @@ static int mv3310_sfp_insert(void *upstream, const struct sfp_eeprom_id *id)
sfp_parse_support(phydev->sfp_bus, id, support);
iface = sfp_select_interface(phydev->sfp_bus, support);
- if (iface != PHY_INTERFACE_MODE_10GKR) {
+ if (iface != PHY_INTERFACE_MODE_10GBASER) {
dev_err(&phydev->mdio.dev, "incompatible SFP module inserted\n");
return -EINVAL;
}
@@ -304,7 +304,7 @@ static int mv3310_config_init(struct phy_device *phydev)
phydev->interface != PHY_INTERFACE_MODE_2500BASEX &&
phydev->interface != PHY_INTERFACE_MODE_XAUI &&
phydev->interface != PHY_INTERFACE_MODE_RXAUI &&
- phydev->interface != PHY_INTERFACE_MODE_10GKR)
+ phydev->interface != PHY_INTERFACE_MODE_10GBASER)
return -ENODEV;
return 0;
@@ -386,16 +386,17 @@ static void mv3310_update_interface(struct phy_device *phydev)
{
if ((phydev->interface == PHY_INTERFACE_MODE_SGMII ||
phydev->interface == PHY_INTERFACE_MODE_2500BASEX ||
- phydev->interface == PHY_INTERFACE_MODE_10GKR) && phydev->link) {
+ phydev->interface == PHY_INTERFACE_MODE_10GBASER) &&
+ phydev->link) {
/* The PHY automatically switches its serdes interface (and
- * active PHYXS instance) between Cisco SGMII, 10GBase-KR and
+ * active PHYXS instance) between Cisco SGMII, 10GBase-R and
* 2500BaseX modes according to the speed. Florian suggests
* setting phydev->interface to communicate this to the MAC.
* Only do this if we are already in one of the above modes.
*/
switch (phydev->speed) {
case SPEED_10000:
- phydev->interface = PHY_INTERFACE_MODE_10GKR;
+ phydev->interface = PHY_INTERFACE_MODE_10GBASER;
break;
case SPEED_2500:
phydev->interface = PHY_INTERFACE_MODE_2500BASEX;
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 229e480..9bb9f37 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -59,17 +59,11 @@ static int mdiobus_register_gpiod(struct mdio_device *mdiodev)
static int mdiobus_register_reset(struct mdio_device *mdiodev)
{
- struct reset_control *reset = NULL;
+ struct reset_control *reset;
- if (mdiodev->dev.of_node)
- reset = of_reset_control_get_exclusive(mdiodev->dev.of_node,
- "phy");
- if (IS_ERR(reset)) {
- if (PTR_ERR(reset) == -ENOENT || PTR_ERR(reset) == -ENOTSUPP)
- reset = NULL;
- else
- return PTR_ERR(reset);
- }
+ reset = reset_control_get_optional_exclusive(&mdiodev->dev, "phy");
+ if (IS_ERR(reset))
+ return PTR_ERR(reset);
mdiodev->reset_ctrl = reset;
@@ -164,9 +158,11 @@ struct mii_bus *mdiobus_alloc_size(size_t size)
if (size)
bus->priv = (void *)bus + aligned_size;
- /* Initialise the interrupts to polling */
- for (i = 0; i < PHY_MAX_ADDR; i++)
+ /* Initialise the interrupts to polling and 64-bit seqcounts */
+ for (i = 0; i < PHY_MAX_ADDR; i++) {
bus->irq[i] = PHY_POLL;
+ u64_stats_init(&bus->stats[i].syncp);
+ }
return bus;
}
@@ -255,9 +251,215 @@ static void mdiobus_release(struct device *d)
kfree(bus);
}
+struct mdio_bus_stat_attr {
+ int addr;
+ unsigned int field_offset;
+};
+
+static u64 mdio_bus_get_stat(struct mdio_bus_stats *s, unsigned int offset)
+{
+ const char *p = (const char *)s + offset;
+ unsigned int start;
+ u64 val = 0;
+
+ do {
+ start = u64_stats_fetch_begin(&s->syncp);
+ val = u64_stats_read((const u64_stats_t *)p);
+ } while (u64_stats_fetch_retry(&s->syncp, start));
+
+ return val;
+}
+
+static u64 mdio_bus_get_global_stat(struct mii_bus *bus, unsigned int offset)
+{
+ unsigned int i;
+ u64 val = 0;
+
+ for (i = 0; i < PHY_MAX_ADDR; i++)
+ val += mdio_bus_get_stat(&bus->stats[i], offset);
+
+ return val;
+}
+
+static ssize_t mdio_bus_stat_field_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct mii_bus *bus = to_mii_bus(dev);
+ struct mdio_bus_stat_attr *sattr;
+ struct dev_ext_attribute *eattr;
+ u64 val;
+
+ eattr = container_of(attr, struct dev_ext_attribute, attr);
+ sattr = eattr->var;
+
+ if (sattr->addr < 0)
+ val = mdio_bus_get_global_stat(bus, sattr->field_offset);
+ else
+ val = mdio_bus_get_stat(&bus->stats[sattr->addr],
+ sattr->field_offset);
+
+ return sprintf(buf, "%llu\n", val);
+}
+
+static ssize_t mdio_bus_device_stat_field_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct mdio_device *mdiodev = to_mdio_device(dev);
+ struct mii_bus *bus = mdiodev->bus;
+ struct mdio_bus_stat_attr *sattr;
+ struct dev_ext_attribute *eattr;
+ int addr = mdiodev->addr;
+ u64 val;
+
+ eattr = container_of(attr, struct dev_ext_attribute, attr);
+ sattr = eattr->var;
+
+ val = mdio_bus_get_stat(&bus->stats[addr], sattr->field_offset);
+
+ return sprintf(buf, "%llu\n", val);
+}
+
+#define MDIO_BUS_STATS_ATTR_DECL(field, file) \
+static struct dev_ext_attribute dev_attr_mdio_bus_##field = { \
+ .attr = { .attr = { .name = file, .mode = 0444 }, \
+ .show = mdio_bus_stat_field_show, \
+ }, \
+ .var = &((struct mdio_bus_stat_attr) { \
+ -1, offsetof(struct mdio_bus_stats, field) \
+ }), \
+}; \
+static struct dev_ext_attribute dev_attr_mdio_bus_device_##field = { \
+ .attr = { .attr = { .name = file, .mode = 0444 }, \
+ .show = mdio_bus_device_stat_field_show, \
+ }, \
+ .var = &((struct mdio_bus_stat_attr) { \
+ -1, offsetof(struct mdio_bus_stats, field) \
+ }), \
+};
+
+#define MDIO_BUS_STATS_ATTR(field) \
+ MDIO_BUS_STATS_ATTR_DECL(field, __stringify(field))
+
+MDIO_BUS_STATS_ATTR(transfers);
+MDIO_BUS_STATS_ATTR(errors);
+MDIO_BUS_STATS_ATTR(writes);
+MDIO_BUS_STATS_ATTR(reads);
+
+#define MDIO_BUS_STATS_ADDR_ATTR_DECL(field, addr, file) \
+static struct dev_ext_attribute dev_attr_mdio_bus_addr_##field##_##addr = { \
+ .attr = { .attr = { .name = file, .mode = 0444 }, \
+ .show = mdio_bus_stat_field_show, \
+ }, \
+ .var = &((struct mdio_bus_stat_attr) { \
+ addr, offsetof(struct mdio_bus_stats, field) \
+ }), \
+}
+
+#define MDIO_BUS_STATS_ADDR_ATTR(field, addr) \
+ MDIO_BUS_STATS_ADDR_ATTR_DECL(field, addr, \
+ __stringify(field) "_" __stringify(addr))
+
+#define MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(addr) \
+ MDIO_BUS_STATS_ADDR_ATTR(transfers, addr); \
+ MDIO_BUS_STATS_ADDR_ATTR(errors, addr); \
+ MDIO_BUS_STATS_ADDR_ATTR(writes, addr); \
+ MDIO_BUS_STATS_ADDR_ATTR(reads, addr) \
+
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(0);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(1);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(2);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(3);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(4);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(5);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(6);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(7);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(8);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(9);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(10);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(11);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(12);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(13);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(14);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(15);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(16);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(17);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(18);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(19);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(20);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(21);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(22);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(23);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(24);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(25);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(26);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(27);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(28);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(29);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(30);
+MDIO_BUS_STATS_ADDR_ATTR_GROUP_DECL(31);
+
+#define MDIO_BUS_STATS_ADDR_ATTR_GROUP(addr) \
+ &dev_attr_mdio_bus_addr_transfers_##addr.attr.attr, \
+ &dev_attr_mdio_bus_addr_errors_##addr.attr.attr, \
+ &dev_attr_mdio_bus_addr_writes_##addr.attr.attr, \
+ &dev_attr_mdio_bus_addr_reads_##addr.attr.attr \
+
+static struct attribute *mdio_bus_statistics_attrs[] = {
+ &dev_attr_mdio_bus_transfers.attr.attr,
+ &dev_attr_mdio_bus_errors.attr.attr,
+ &dev_attr_mdio_bus_writes.attr.attr,
+ &dev_attr_mdio_bus_reads.attr.attr,
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(0),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(1),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(2),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(3),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(4),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(5),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(6),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(7),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(8),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(9),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(10),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(11),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(12),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(13),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(14),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(15),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(16),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(17),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(18),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(19),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(20),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(21),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(22),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(23),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(24),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(25),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(26),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(27),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(28),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(29),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(30),
+ MDIO_BUS_STATS_ADDR_ATTR_GROUP(31),
+ NULL,
+};
+
+static const struct attribute_group mdio_bus_statistics_group = {
+ .name = "statistics",
+ .attrs = mdio_bus_statistics_attrs,
+};
+
+static const struct attribute_group *mdio_bus_groups[] = {
+ &mdio_bus_statistics_group,
+ NULL,
+};
+
static struct class mdio_bus_class = {
.name = "mdio_bus",
.dev_release = mdiobus_release,
+ .dev_groups = mdio_bus_groups,
};
#if IS_ENABLED(CONFIG_OF_MDIO)
@@ -536,6 +738,24 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr)
}
EXPORT_SYMBOL(mdiobus_scan);
+static void mdiobus_stats_acct(struct mdio_bus_stats *stats, bool op, int ret)
+{
+ u64_stats_update_begin(&stats->syncp);
+
+ u64_stats_inc(&stats->transfers);
+ if (ret < 0) {
+ u64_stats_inc(&stats->errors);
+ goto out;
+ }
+
+ if (op)
+ u64_stats_inc(&stats->reads);
+ else
+ u64_stats_inc(&stats->writes);
+out:
+ u64_stats_update_end(&stats->syncp);
+}
+
/**
* __mdiobus_read - Unlocked version of the mdiobus_read function
* @bus: the mii_bus struct
@@ -555,6 +775,7 @@ int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum)
retval = bus->read(bus, addr, regnum);
trace_mdio_access(bus, 1, addr, regnum, retval, retval);
+ mdiobus_stats_acct(&bus->stats[addr], true, retval);
return retval;
}
@@ -580,6 +801,7 @@ int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val)
err = bus->write(bus, addr, regnum, val);
trace_mdio_access(bus, 0, addr, regnum, val, err);
+ mdiobus_stats_acct(&bus->stats[addr], false, err);
return err;
}
@@ -725,8 +947,27 @@ static int mdio_uevent(struct device *dev, struct kobj_uevent_env *env)
return 0;
}
+static struct attribute *mdio_bus_device_statistics_attrs[] = {
+ &dev_attr_mdio_bus_device_transfers.attr.attr,
+ &dev_attr_mdio_bus_device_errors.attr.attr,
+ &dev_attr_mdio_bus_device_writes.attr.attr,
+ &dev_attr_mdio_bus_device_reads.attr.attr,
+ NULL,
+};
+
+static const struct attribute_group mdio_bus_device_statistics_group = {
+ .name = "statistics",
+ .attrs = mdio_bus_device_statistics_attrs,
+};
+
+static const struct attribute_group *mdio_bus_dev_groups[] = {
+ &mdio_bus_device_statistics_group,
+ NULL,
+};
+
struct bus_type mdio_bus_type = {
.name = "mdio_bus",
+ .dev_groups = mdio_bus_dev_groups,
.match = mdio_bus_match,
.uevent = mdio_uevent,
};
diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c
index 50214c0..937ac7d 100644
--- a/drivers/net/phy/mscc.c
+++ b/drivers/net/phy/mscc.c
@@ -18,6 +18,17 @@
#include <linux/netdevice.h>
#include <dt-bindings/net/mscc-phy-vsc8531.h>
+#include <linux/scatterlist.h>
+#include <crypto/skcipher.h>
+
+#if IS_ENABLED(CONFIG_MACSEC)
+#include <net/macsec.h>
+#endif
+
+#include "mscc_macsec.h"
+#include "mscc_mac.h"
+#include "mscc_fc_buffer.h"
+
enum rgmii_rx_clock_delay {
RGMII_RX_CLK_DELAY_0_2_NS = 0,
RGMII_RX_CLK_DELAY_0_8_NS = 1,
@@ -69,7 +80,7 @@ enum rgmii_rx_clock_delay {
#define MSCC_PHY_EXT_PHY_CNTL_2 24
#define MII_VSC85XX_INT_MASK 25
-#define MII_VSC85XX_INT_MASK_MASK 0xa000
+#define MII_VSC85XX_INT_MASK_MASK 0xa020
#define MII_VSC85XX_INT_MASK_WOL 0x0040
#define MII_VSC85XX_INT_STATUS 26
@@ -121,6 +132,26 @@ enum rgmii_rx_clock_delay {
#define PHY_S6G_PLL_FSM_CTRL_DATA_POS 8
#define PHY_S6G_PLL_FSM_ENA_POS 7
+#define MSCC_EXT_PAGE_MACSEC_17 17
+#define MSCC_EXT_PAGE_MACSEC_18 18
+
+#define MSCC_EXT_PAGE_MACSEC_19 19
+#define MSCC_PHY_MACSEC_19_REG_ADDR(x) (x)
+#define MSCC_PHY_MACSEC_19_TARGET(x) ((x) << 12)
+#define MSCC_PHY_MACSEC_19_READ BIT(14)
+#define MSCC_PHY_MACSEC_19_CMD BIT(15)
+
+#define MSCC_EXT_PAGE_MACSEC_20 20
+#define MSCC_PHY_MACSEC_20_TARGET(x) (x)
+enum macsec_bank {
+ FC_BUFFER = 0x04,
+ HOST_MAC = 0x05,
+ LINE_MAC = 0x06,
+ IP_1588 = 0x0e,
+ MACSEC_INGR = 0x38,
+ MACSEC_EGR = 0x3c,
+};
+
#define MSCC_EXT_PAGE_ACCESS 31
#define MSCC_PHY_PAGE_STANDARD 0x0000 /* Standard registers */
#define MSCC_PHY_PAGE_EXTENDED 0x0001 /* Extended registers */
@@ -128,6 +159,7 @@ enum rgmii_rx_clock_delay {
#define MSCC_PHY_PAGE_EXTENDED_3 0x0003 /* Extended reg - page 3 */
#define MSCC_PHY_PAGE_EXTENDED_4 0x0004 /* Extended reg - page 4 */
#define MSCC_PHY_PAGE_CSR_CNTL MSCC_PHY_PAGE_EXTENDED_4
+#define MSCC_PHY_PAGE_MACSEC MSCC_PHY_PAGE_EXTENDED_4
/* Extended reg - GPIO; this is a bank of registers that are shared for all PHYs
* in the same package.
*/
@@ -175,6 +207,9 @@ enum rgmii_rx_clock_delay {
#define SECURE_ON_ENABLE 0x8000
#define SECURE_ON_PASSWD_LEN_4 0x4000
+#define MSCC_PHY_EXTENDED_INT 28
+#define MSCC_PHY_EXTENDED_INT_MS_EGR BIT(9)
+
/* Extended Page 3 Registers */
#define MSCC_PHY_SERDES_TX_VALID_CNT 21
#define MSCC_PHY_SERDES_TX_CRC_ERR_CNT 22
@@ -411,6 +446,44 @@ static const struct vsc85xx_hw_stat vsc8584_hw_stats[] = {
},
};
+#if IS_ENABLED(CONFIG_MACSEC)
+struct macsec_flow {
+ struct list_head list;
+ enum mscc_macsec_destination_ports port;
+ enum macsec_bank bank;
+ u32 index;
+ int assoc_num;
+ bool has_transformation;
+
+ /* Highest takes precedence [0..15] */
+ u8 priority;
+
+ u8 key[MACSEC_KEYID_LEN];
+
+ union {
+ struct macsec_rx_sa *rx_sa;
+ struct macsec_tx_sa *tx_sa;
+ };
+
+ /* Matching */
+ struct {
+ u8 sci:1;
+ u8 tagged:1;
+ u8 untagged:1;
+ u8 etype:1;
+ } match;
+
+ u16 etype;
+
+ /* Action */
+ struct {
+ u8 bypass:1;
+ u8 drop:1;
+ } action;
+
+};
+#endif
+
struct vsc8531_private {
int rate_magic;
u16 supp_led_modes;
@@ -424,6 +497,19 @@ struct vsc8531_private {
* package.
*/
unsigned int base_addr;
+
+#if IS_ENABLED(CONFIG_MACSEC)
+ /* MACsec fields:
+ * - One SecY per device (enforced at the s/w implementation level)
+ * - macsec_flows: list of h/w flows
+ * - ingr_flows: bitmap of ingress flows
+ * - egr_flows: bitmap of egress flows
+ */
+ struct macsec_secy *secy;
+ struct list_head macsec_flows;
+ unsigned long ingr_flows;
+ unsigned long egr_flows;
+#endif
};
#ifdef CONFIG_OF_MDIO
@@ -1584,6 +1670,978 @@ static int vsc8584_config_pre_init(struct phy_device *phydev)
return ret;
}
+#if IS_ENABLED(CONFIG_MACSEC)
+static u32 vsc8584_macsec_phy_read(struct phy_device *phydev,
+ enum macsec_bank bank, u32 reg)
+{
+ u32 val, val_l = 0, val_h = 0;
+ unsigned long deadline;
+ int rc;
+
+ rc = phy_select_page(phydev, MSCC_PHY_PAGE_MACSEC);
+ if (rc < 0)
+ goto failed;
+
+ __phy_write(phydev, MSCC_EXT_PAGE_MACSEC_20,
+ MSCC_PHY_MACSEC_20_TARGET(bank >> 2));
+
+ if (bank >> 2 == 0x1)
+ /* non-MACsec access */
+ bank &= 0x3;
+ else
+ bank = 0;
+
+ __phy_write(phydev, MSCC_EXT_PAGE_MACSEC_19,
+ MSCC_PHY_MACSEC_19_CMD | MSCC_PHY_MACSEC_19_READ |
+ MSCC_PHY_MACSEC_19_REG_ADDR(reg) |
+ MSCC_PHY_MACSEC_19_TARGET(bank));
+
+ deadline = jiffies + msecs_to_jiffies(PROC_CMD_NCOMPLETED_TIMEOUT_MS);
+ do {
+ val = __phy_read(phydev, MSCC_EXT_PAGE_MACSEC_19);
+ } while (time_before(jiffies, deadline) && !(val & MSCC_PHY_MACSEC_19_CMD));
+
+ val_l = __phy_read(phydev, MSCC_EXT_PAGE_MACSEC_17);
+ val_h = __phy_read(phydev, MSCC_EXT_PAGE_MACSEC_18);
+
+failed:
+ phy_restore_page(phydev, rc, rc);
+
+ return (val_h << 16) | val_l;
+}
+
+static void vsc8584_macsec_phy_write(struct phy_device *phydev,
+ enum macsec_bank bank, u32 reg, u32 val)
+{
+ unsigned long deadline;
+ int rc;
+
+ rc = phy_select_page(phydev, MSCC_PHY_PAGE_MACSEC);
+ if (rc < 0)
+ goto failed;
+
+ __phy_write(phydev, MSCC_EXT_PAGE_MACSEC_20,
+ MSCC_PHY_MACSEC_20_TARGET(bank >> 2));
+
+ if ((bank >> 2 == 0x1) || (bank >> 2 == 0x3))
+ bank &= 0x3;
+ else
+ /* MACsec access */
+ bank = 0;
+
+ __phy_write(phydev, MSCC_EXT_PAGE_MACSEC_17, (u16)val);
+ __phy_write(phydev, MSCC_EXT_PAGE_MACSEC_18, (u16)(val >> 16));
+
+ __phy_write(phydev, MSCC_EXT_PAGE_MACSEC_19,
+ MSCC_PHY_MACSEC_19_CMD | MSCC_PHY_MACSEC_19_REG_ADDR(reg) |
+ MSCC_PHY_MACSEC_19_TARGET(bank));
+
+ deadline = jiffies + msecs_to_jiffies(PROC_CMD_NCOMPLETED_TIMEOUT_MS);
+ do {
+ val = __phy_read(phydev, MSCC_EXT_PAGE_MACSEC_19);
+ } while (time_before(jiffies, deadline) && !(val & MSCC_PHY_MACSEC_19_CMD));
+
+failed:
+ phy_restore_page(phydev, rc, rc);
+}
+
+static void vsc8584_macsec_classification(struct phy_device *phydev,
+ enum macsec_bank bank)
+{
+ /* enable VLAN tag parsing */
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_CP_TAG,
+ MSCC_MS_SAM_CP_TAG_PARSE_STAG |
+ MSCC_MS_SAM_CP_TAG_PARSE_QTAG |
+ MSCC_MS_SAM_CP_TAG_PARSE_QINQ);
+}
+
+static void vsc8584_macsec_flow_default_action(struct phy_device *phydev,
+ enum macsec_bank bank,
+ bool block)
+{
+ u32 port = (bank == MACSEC_INGR) ?
+ MSCC_MS_PORT_UNCONTROLLED : MSCC_MS_PORT_COMMON;
+ u32 action = MSCC_MS_FLOW_BYPASS;
+
+ if (block)
+ action = MSCC_MS_FLOW_DROP;
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_NM_FLOW_NCP,
+ /* MACsec untagged */
+ MSCC_MS_SAM_NM_FLOW_NCP_UNTAGGED_FLOW_TYPE(action) |
+ MSCC_MS_SAM_NM_FLOW_NCP_UNTAGGED_DROP_ACTION(MSCC_MS_ACTION_DROP) |
+ MSCC_MS_SAM_NM_FLOW_NCP_UNTAGGED_DEST_PORT(port) |
+ /* MACsec tagged */
+ MSCC_MS_SAM_NM_FLOW_NCP_TAGGED_FLOW_TYPE(action) |
+ MSCC_MS_SAM_NM_FLOW_NCP_TAGGED_DROP_ACTION(MSCC_MS_ACTION_DROP) |
+ MSCC_MS_SAM_NM_FLOW_NCP_TAGGED_DEST_PORT(port) |
+ /* Bad tag */
+ MSCC_MS_SAM_NM_FLOW_NCP_BADTAG_FLOW_TYPE(action) |
+ MSCC_MS_SAM_NM_FLOW_NCP_BADTAG_DROP_ACTION(MSCC_MS_ACTION_DROP) |
+ MSCC_MS_SAM_NM_FLOW_NCP_BADTAG_DEST_PORT(port) |
+ /* Kay tag */
+ MSCC_MS_SAM_NM_FLOW_NCP_KAY_FLOW_TYPE(action) |
+ MSCC_MS_SAM_NM_FLOW_NCP_KAY_DROP_ACTION(MSCC_MS_ACTION_DROP) |
+ MSCC_MS_SAM_NM_FLOW_NCP_KAY_DEST_PORT(port));
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_NM_FLOW_CP,
+ /* MACsec untagged */
+ MSCC_MS_SAM_NM_FLOW_NCP_UNTAGGED_FLOW_TYPE(action) |
+ MSCC_MS_SAM_NM_FLOW_CP_UNTAGGED_DROP_ACTION(MSCC_MS_ACTION_DROP) |
+ MSCC_MS_SAM_NM_FLOW_CP_UNTAGGED_DEST_PORT(port) |
+ /* MACsec tagged */
+ MSCC_MS_SAM_NM_FLOW_NCP_TAGGED_FLOW_TYPE(action) |
+ MSCC_MS_SAM_NM_FLOW_CP_TAGGED_DROP_ACTION(MSCC_MS_ACTION_DROP) |
+ MSCC_MS_SAM_NM_FLOW_CP_TAGGED_DEST_PORT(port) |
+ /* Bad tag */
+ MSCC_MS_SAM_NM_FLOW_NCP_BADTAG_FLOW_TYPE(action) |
+ MSCC_MS_SAM_NM_FLOW_CP_BADTAG_DROP_ACTION(MSCC_MS_ACTION_DROP) |
+ MSCC_MS_SAM_NM_FLOW_CP_BADTAG_DEST_PORT(port) |
+ /* Kay tag */
+ MSCC_MS_SAM_NM_FLOW_NCP_KAY_FLOW_TYPE(action) |
+ MSCC_MS_SAM_NM_FLOW_CP_KAY_DROP_ACTION(MSCC_MS_ACTION_DROP) |
+ MSCC_MS_SAM_NM_FLOW_CP_KAY_DEST_PORT(port));
+}
+
+static void vsc8584_macsec_integrity_checks(struct phy_device *phydev,
+ enum macsec_bank bank)
+{
+ u32 val;
+
+ if (bank != MACSEC_INGR)
+ return;
+
+ /* Set default rules to pass unmatched frames */
+ val = vsc8584_macsec_phy_read(phydev, bank,
+ MSCC_MS_PARAMS2_IG_CC_CONTROL);
+ val |= MSCC_MS_PARAMS2_IG_CC_CONTROL_NON_MATCH_CTRL_ACT |
+ MSCC_MS_PARAMS2_IG_CC_CONTROL_NON_MATCH_ACT;
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_PARAMS2_IG_CC_CONTROL,
+ val);
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_PARAMS2_IG_CP_TAG,
+ MSCC_MS_PARAMS2_IG_CP_TAG_PARSE_STAG |
+ MSCC_MS_PARAMS2_IG_CP_TAG_PARSE_QTAG |
+ MSCC_MS_PARAMS2_IG_CP_TAG_PARSE_QINQ);
+}
+
+static void vsc8584_macsec_block_init(struct phy_device *phydev,
+ enum macsec_bank bank)
+{
+ u32 val;
+ int i;
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_ENA_CFG,
+ MSCC_MS_ENA_CFG_SW_RST |
+ MSCC_MS_ENA_CFG_MACSEC_BYPASS_ENA);
+
+ /* Set the MACsec block out of s/w reset and enable clocks */
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_ENA_CFG,
+ MSCC_MS_ENA_CFG_CLK_ENA);
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_STATUS_CONTEXT_CTRL,
+ bank == MACSEC_INGR ? 0xe5880214 : 0xe5880218);
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_MISC_CONTROL,
+ MSCC_MS_MISC_CONTROL_MC_LATENCY_FIX(bank == MACSEC_INGR ? 57 : 40) |
+ MSCC_MS_MISC_CONTROL_XFORM_REC_SIZE(bank == MACSEC_INGR ? 1 : 2));
+
+ /* Clear the counters */
+ val = vsc8584_macsec_phy_read(phydev, bank, MSCC_MS_COUNT_CONTROL);
+ val |= MSCC_MS_COUNT_CONTROL_AUTO_CNTR_RESET;
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_COUNT_CONTROL, val);
+
+ /* Enable octet increment mode */
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_PP_CTRL,
+ MSCC_MS_PP_CTRL_MACSEC_OCTET_INCR_MODE);
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_BLOCK_CTX_UPDATE, 0x3);
+
+ val = vsc8584_macsec_phy_read(phydev, bank, MSCC_MS_COUNT_CONTROL);
+ val |= MSCC_MS_COUNT_CONTROL_RESET_ALL;
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_COUNT_CONTROL, val);
+
+ /* Set the MTU */
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_NON_VLAN_MTU_CHECK,
+ MSCC_MS_NON_VLAN_MTU_CHECK_NV_MTU_COMPARE(32761) |
+ MSCC_MS_NON_VLAN_MTU_CHECK_NV_MTU_COMP_DROP);
+
+ for (i = 0; i < 8; i++)
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_VLAN_MTU_CHECK(i),
+ MSCC_MS_VLAN_MTU_CHECK_MTU_COMPARE(32761) |
+ MSCC_MS_VLAN_MTU_CHECK_MTU_COMP_DROP);
+
+ if (bank == MACSEC_EGR) {
+ val = vsc8584_macsec_phy_read(phydev, bank, MSCC_MS_INTR_CTRL_STATUS);
+ val &= ~MSCC_MS_INTR_CTRL_STATUS_INTR_ENABLE_M;
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_INTR_CTRL_STATUS, val);
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_FC_CFG,
+ MSCC_MS_FC_CFG_FCBUF_ENA |
+ MSCC_MS_FC_CFG_LOW_THRESH(0x1) |
+ MSCC_MS_FC_CFG_HIGH_THRESH(0x4) |
+ MSCC_MS_FC_CFG_LOW_BYTES_VAL(0x4) |
+ MSCC_MS_FC_CFG_HIGH_BYTES_VAL(0x6));
+ }
+
+ vsc8584_macsec_classification(phydev, bank);
+ vsc8584_macsec_flow_default_action(phydev, bank, false);
+ vsc8584_macsec_integrity_checks(phydev, bank);
+
+ /* Enable the MACsec block */
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_ENA_CFG,
+ MSCC_MS_ENA_CFG_CLK_ENA |
+ MSCC_MS_ENA_CFG_MACSEC_ENA |
+ MSCC_MS_ENA_CFG_MACSEC_SPEED_MODE(0x5));
+}
+
+static void vsc8584_macsec_mac_init(struct phy_device *phydev,
+ enum macsec_bank bank)
+{
+ u32 val;
+ int i;
+
+ /* Clear host & line stats */
+ for (i = 0; i < 36; i++)
+ vsc8584_macsec_phy_write(phydev, bank, 0x1c + i, 0);
+
+ val = vsc8584_macsec_phy_read(phydev, bank,
+ MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL);
+ val &= ~MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_PAUSE_MODE_M;
+ val |= MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_PAUSE_MODE(2) |
+ MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_PAUSE_VALUE(0xffff);
+ vsc8584_macsec_phy_write(phydev, bank,
+ MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL, val);
+
+ val = vsc8584_macsec_phy_read(phydev, bank,
+ MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_2);
+ val |= 0xffff;
+ vsc8584_macsec_phy_write(phydev, bank,
+ MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_2, val);
+
+ val = vsc8584_macsec_phy_read(phydev, bank,
+ MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL);
+ if (bank == HOST_MAC)
+ val |= MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_PAUSE_TIMER_ENA |
+ MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_PAUSE_FRAME_DROP_ENA;
+ else
+ val |= MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_PAUSE_REACT_ENA |
+ MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_PAUSE_FRAME_DROP_ENA |
+ MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_PAUSE_MODE |
+ MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_EARLY_PAUSE_DETECT_ENA;
+ vsc8584_macsec_phy_write(phydev, bank,
+ MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL, val);
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MAC_CFG_PKTINF_CFG,
+ MSCC_MAC_CFG_PKTINF_CFG_STRIP_FCS_ENA |
+ MSCC_MAC_CFG_PKTINF_CFG_INSERT_FCS_ENA |
+ MSCC_MAC_CFG_PKTINF_CFG_LPI_RELAY_ENA |
+ MSCC_MAC_CFG_PKTINF_CFG_STRIP_PREAMBLE_ENA |
+ MSCC_MAC_CFG_PKTINF_CFG_INSERT_PREAMBLE_ENA |
+ (bank == HOST_MAC ?
+ MSCC_MAC_CFG_PKTINF_CFG_ENABLE_TX_PADDING : 0));
+
+ val = vsc8584_macsec_phy_read(phydev, bank, MSCC_MAC_CFG_MODE_CFG);
+ val &= ~MSCC_MAC_CFG_MODE_CFG_DISABLE_DIC;
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MAC_CFG_MODE_CFG, val);
+
+ val = vsc8584_macsec_phy_read(phydev, bank, MSCC_MAC_CFG_MAXLEN_CFG);
+ val &= ~MSCC_MAC_CFG_MAXLEN_CFG_MAX_LEN_M;
+ val |= MSCC_MAC_CFG_MAXLEN_CFG_MAX_LEN(10240);
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MAC_CFG_MAXLEN_CFG, val);
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MAC_CFG_ADV_CHK_CFG,
+ MSCC_MAC_CFG_ADV_CHK_CFG_SFD_CHK_ENA |
+ MSCC_MAC_CFG_ADV_CHK_CFG_PRM_CHK_ENA |
+ MSCC_MAC_CFG_ADV_CHK_CFG_OOR_ERR_ENA |
+ MSCC_MAC_CFG_ADV_CHK_CFG_INR_ERR_ENA);
+
+ val = vsc8584_macsec_phy_read(phydev, bank, MSCC_MAC_CFG_LFS_CFG);
+ val &= ~MSCC_MAC_CFG_LFS_CFG_LFS_MODE_ENA;
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MAC_CFG_LFS_CFG, val);
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MAC_CFG_ENA_CFG,
+ MSCC_MAC_CFG_ENA_CFG_RX_CLK_ENA |
+ MSCC_MAC_CFG_ENA_CFG_TX_CLK_ENA |
+ MSCC_MAC_CFG_ENA_CFG_RX_ENA |
+ MSCC_MAC_CFG_ENA_CFG_TX_ENA);
+}
+
+/* Must be called with mdio_lock taken */
+static int vsc8584_macsec_init(struct phy_device *phydev)
+{
+ u32 val;
+
+ vsc8584_macsec_block_init(phydev, MACSEC_INGR);
+ vsc8584_macsec_block_init(phydev, MACSEC_EGR);
+ vsc8584_macsec_mac_init(phydev, HOST_MAC);
+ vsc8584_macsec_mac_init(phydev, LINE_MAC);
+
+ vsc8584_macsec_phy_write(phydev, FC_BUFFER,
+ MSCC_FCBUF_FC_READ_THRESH_CFG,
+ MSCC_FCBUF_FC_READ_THRESH_CFG_TX_THRESH(4) |
+ MSCC_FCBUF_FC_READ_THRESH_CFG_RX_THRESH(5));
+
+ val = vsc8584_macsec_phy_read(phydev, FC_BUFFER, MSCC_FCBUF_MODE_CFG);
+ val |= MSCC_FCBUF_MODE_CFG_PAUSE_GEN_ENA |
+ MSCC_FCBUF_MODE_CFG_RX_PPM_RATE_ADAPT_ENA |
+ MSCC_FCBUF_MODE_CFG_TX_PPM_RATE_ADAPT_ENA;
+ vsc8584_macsec_phy_write(phydev, FC_BUFFER, MSCC_FCBUF_MODE_CFG, val);
+
+ vsc8584_macsec_phy_write(phydev, FC_BUFFER, MSCC_FCBUF_PPM_RATE_ADAPT_THRESH_CFG,
+ MSCC_FCBUF_PPM_RATE_ADAPT_THRESH_CFG_TX_THRESH(8) |
+ MSCC_FCBUF_PPM_RATE_ADAPT_THRESH_CFG_TX_OFFSET(9));
+
+ val = vsc8584_macsec_phy_read(phydev, FC_BUFFER,
+ MSCC_FCBUF_TX_DATA_QUEUE_CFG);
+ val &= ~(MSCC_FCBUF_TX_DATA_QUEUE_CFG_START_M |
+ MSCC_FCBUF_TX_DATA_QUEUE_CFG_END_M);
+ val |= MSCC_FCBUF_TX_DATA_QUEUE_CFG_START(0) |
+ MSCC_FCBUF_TX_DATA_QUEUE_CFG_END(5119);
+ vsc8584_macsec_phy_write(phydev, FC_BUFFER,
+ MSCC_FCBUF_TX_DATA_QUEUE_CFG, val);
+
+ val = vsc8584_macsec_phy_read(phydev, FC_BUFFER, MSCC_FCBUF_ENA_CFG);
+ val |= MSCC_FCBUF_ENA_CFG_TX_ENA | MSCC_FCBUF_ENA_CFG_RX_ENA;
+ vsc8584_macsec_phy_write(phydev, FC_BUFFER, MSCC_FCBUF_ENA_CFG, val);
+
+ val = vsc8584_macsec_phy_read(phydev, IP_1588,
+ MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL);
+ val &= ~MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE_M;
+ val |= MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE(4);
+ vsc8584_macsec_phy_write(phydev, IP_1588,
+ MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL, val);
+
+ return 0;
+}
+
+static void vsc8584_macsec_flow(struct phy_device *phydev,
+ struct macsec_flow *flow)
+{
+ struct vsc8531_private *priv = phydev->priv;
+ enum macsec_bank bank = flow->bank;
+ u32 val, match = 0, mask = 0, action = 0, idx = flow->index;
+
+ if (flow->match.tagged)
+ match |= MSCC_MS_SAM_MISC_MATCH_TAGGED;
+ if (flow->match.untagged)
+ match |= MSCC_MS_SAM_MISC_MATCH_UNTAGGED;
+
+ if (bank == MACSEC_INGR && flow->assoc_num >= 0) {
+ match |= MSCC_MS_SAM_MISC_MATCH_AN(flow->assoc_num);
+ mask |= MSCC_MS_SAM_MASK_AN_MASK(0x3);
+ }
+
+ if (bank == MACSEC_INGR && flow->match.sci && flow->rx_sa->sc->sci) {
+ match |= MSCC_MS_SAM_MISC_MATCH_TCI(BIT(3));
+ mask |= MSCC_MS_SAM_MASK_TCI_MASK(BIT(3)) |
+ MSCC_MS_SAM_MASK_SCI_MASK;
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_MATCH_SCI_LO(idx),
+ lower_32_bits(flow->rx_sa->sc->sci));
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_MATCH_SCI_HI(idx),
+ upper_32_bits(flow->rx_sa->sc->sci));
+ }
+
+ if (flow->match.etype) {
+ mask |= MSCC_MS_SAM_MASK_MAC_ETYPE_MASK;
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_MAC_SA_MATCH_HI(idx),
+ MSCC_MS_SAM_MAC_SA_MATCH_HI_ETYPE(htons(flow->etype)));
+ }
+
+ match |= MSCC_MS_SAM_MISC_MATCH_PRIORITY(flow->priority);
+
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_MISC_MATCH(idx), match);
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_MASK(idx), mask);
+
+ /* Action for matching packets */
+ if (flow->action.drop)
+ action = MSCC_MS_FLOW_DROP;
+ else if (flow->action.bypass || flow->port == MSCC_MS_PORT_UNCONTROLLED)
+ action = MSCC_MS_FLOW_BYPASS;
+ else
+ action = (bank == MACSEC_INGR) ?
+ MSCC_MS_FLOW_INGRESS : MSCC_MS_FLOW_EGRESS;
+
+ val = MSCC_MS_SAM_FLOW_CTRL_FLOW_TYPE(action) |
+ MSCC_MS_SAM_FLOW_CTRL_DROP_ACTION(MSCC_MS_ACTION_DROP) |
+ MSCC_MS_SAM_FLOW_CTRL_DEST_PORT(flow->port);
+
+ if (action == MSCC_MS_FLOW_BYPASS)
+ goto write_ctrl;
+
+ if (bank == MACSEC_INGR) {
+ if (priv->secy->replay_protect)
+ val |= MSCC_MS_SAM_FLOW_CTRL_REPLAY_PROTECT;
+ if (priv->secy->validate_frames == MACSEC_VALIDATE_STRICT)
+ val |= MSCC_MS_SAM_FLOW_CTRL_VALIDATE_FRAMES(MSCC_MS_VALIDATE_STRICT);
+ else if (priv->secy->validate_frames == MACSEC_VALIDATE_CHECK)
+ val |= MSCC_MS_SAM_FLOW_CTRL_VALIDATE_FRAMES(MSCC_MS_VALIDATE_CHECK);
+ } else if (bank == MACSEC_EGR) {
+ if (priv->secy->protect_frames)
+ val |= MSCC_MS_SAM_FLOW_CTRL_PROTECT_FRAME;
+ if (priv->secy->tx_sc.encrypt)
+ val |= MSCC_MS_SAM_FLOW_CTRL_CONF_PROTECT;
+ if (priv->secy->tx_sc.send_sci)
+ val |= MSCC_MS_SAM_FLOW_CTRL_INCLUDE_SCI;
+ }
+
+write_ctrl:
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_FLOW_CTRL(idx), val);
+}
+
+static struct macsec_flow *vsc8584_macsec_find_flow(struct macsec_context *ctx,
+ enum macsec_bank bank)
+{
+ struct vsc8531_private *priv = ctx->phydev->priv;
+ struct macsec_flow *pos, *tmp;
+
+ list_for_each_entry_safe(pos, tmp, &priv->macsec_flows, list)
+ if (pos->assoc_num == ctx->sa.assoc_num && pos->bank == bank)
+ return pos;
+
+ return ERR_PTR(-ENOENT);
+}
+
+static void vsc8584_macsec_flow_enable(struct phy_device *phydev,
+ struct macsec_flow *flow)
+{
+ enum macsec_bank bank = flow->bank;
+ u32 val, idx = flow->index;
+
+ if ((flow->bank == MACSEC_INGR && flow->rx_sa && !flow->rx_sa->active) ||
+ (flow->bank == MACSEC_EGR && flow->tx_sa && !flow->tx_sa->active))
+ return;
+
+ /* Enable */
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_ENTRY_SET1, BIT(idx));
+
+ /* Set in-use */
+ val = vsc8584_macsec_phy_read(phydev, bank, MSCC_MS_SAM_FLOW_CTRL(idx));
+ val |= MSCC_MS_SAM_FLOW_CTRL_SA_IN_USE;
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_FLOW_CTRL(idx), val);
+}
+
+static void vsc8584_macsec_flow_disable(struct phy_device *phydev,
+ struct macsec_flow *flow)
+{
+ enum macsec_bank bank = flow->bank;
+ u32 val, idx = flow->index;
+
+ /* Disable */
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_ENTRY_CLEAR1, BIT(idx));
+
+ /* Clear in-use */
+ val = vsc8584_macsec_phy_read(phydev, bank, MSCC_MS_SAM_FLOW_CTRL(idx));
+ val &= ~MSCC_MS_SAM_FLOW_CTRL_SA_IN_USE;
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_SAM_FLOW_CTRL(idx), val);
+}
+
+static u32 vsc8584_macsec_flow_context_id(struct macsec_flow *flow)
+{
+ if (flow->bank == MACSEC_INGR)
+ return flow->index + MSCC_MS_MAX_FLOWS;
+
+ return flow->index;
+}
+
+/* Derive the AES key to get a key for the hash autentication */
+static int vsc8584_macsec_derive_key(const u8 key[MACSEC_KEYID_LEN],
+ u16 key_len, u8 hkey[16])
+{
+ struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
+ struct skcipher_request *req = NULL;
+ struct scatterlist src, dst;
+ DECLARE_CRYPTO_WAIT(wait);
+ u32 input[4] = {0};
+ int ret;
+
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+
+ req = skcipher_request_alloc(tfm, GFP_KERNEL);
+ if (!req) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG |
+ CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done,
+ &wait);
+ ret = crypto_skcipher_setkey(tfm, key, key_len);
+ if (ret < 0)
+ goto out;
+
+ sg_init_one(&src, input, 16);
+ sg_init_one(&dst, hkey, 16);
+ skcipher_request_set_crypt(req, &src, &dst, 16, NULL);
+
+ ret = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+
+out:
+ skcipher_request_free(req);
+ crypto_free_skcipher(tfm);
+ return ret;
+}
+
+static int vsc8584_macsec_transformation(struct phy_device *phydev,
+ struct macsec_flow *flow)
+{
+ struct vsc8531_private *priv = phydev->priv;
+ enum macsec_bank bank = flow->bank;
+ int i, ret, index = flow->index;
+ u32 rec = 0, control = 0;
+ u8 hkey[16];
+ sci_t sci;
+
+ ret = vsc8584_macsec_derive_key(flow->key, priv->secy->key_len, hkey);
+ if (ret)
+ return ret;
+
+ switch (priv->secy->key_len) {
+ case 16:
+ control |= CONTROL_CRYPTO_ALG(CTRYPTO_ALG_AES_CTR_128);
+ break;
+ case 32:
+ control |= CONTROL_CRYPTO_ALG(CTRYPTO_ALG_AES_CTR_256);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ control |= (bank == MACSEC_EGR) ?
+ (CONTROL_TYPE_EGRESS | CONTROL_AN(priv->secy->tx_sc.encoding_sa)) :
+ (CONTROL_TYPE_INGRESS | CONTROL_SEQ_MASK);
+
+ control |= CONTROL_UPDATE_SEQ | CONTROL_ENCRYPT_AUTH | CONTROL_KEY_IN_CTX |
+ CONTROL_IV0 | CONTROL_IV1 | CONTROL_IV_IN_SEQ |
+ CONTROL_DIGEST_TYPE(0x2) | CONTROL_SEQ_TYPE(0x1) |
+ CONTROL_AUTH_ALG(AUTH_ALG_AES_GHAS) | CONTROL_CONTEXT_ID;
+
+ /* Set the control word */
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_XFORM_REC(index, rec++),
+ control);
+
+ /* Set the context ID. Must be unique. */
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_XFORM_REC(index, rec++),
+ vsc8584_macsec_flow_context_id(flow));
+
+ /* Set the encryption/decryption key */
+ for (i = 0; i < priv->secy->key_len / sizeof(u32); i++)
+ vsc8584_macsec_phy_write(phydev, bank,
+ MSCC_MS_XFORM_REC(index, rec++),
+ ((u32 *)flow->key)[i]);
+
+ /* Set the authentication key */
+ for (i = 0; i < 4; i++)
+ vsc8584_macsec_phy_write(phydev, bank,
+ MSCC_MS_XFORM_REC(index, rec++),
+ ((u32 *)hkey)[i]);
+
+ /* Initial sequence number */
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_XFORM_REC(index, rec++),
+ bank == MACSEC_INGR ?
+ flow->rx_sa->next_pn : flow->tx_sa->next_pn);
+
+ if (bank == MACSEC_INGR)
+ /* Set the mask (replay window size) */
+ vsc8584_macsec_phy_write(phydev, bank,
+ MSCC_MS_XFORM_REC(index, rec++),
+ priv->secy->replay_window);
+
+ /* Set the input vectors */
+ sci = bank == MACSEC_INGR ? flow->rx_sa->sc->sci : priv->secy->sci;
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_XFORM_REC(index, rec++),
+ lower_32_bits(sci));
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_XFORM_REC(index, rec++),
+ upper_32_bits(sci));
+
+ while (rec < 20)
+ vsc8584_macsec_phy_write(phydev, bank, MSCC_MS_XFORM_REC(index, rec++),
+ 0);
+
+ flow->has_transformation = true;
+ return 0;
+}
+
+static struct macsec_flow *vsc8584_macsec_alloc_flow(struct vsc8531_private *priv,
+ enum macsec_bank bank)
+{
+ unsigned long *bitmap = bank == MACSEC_INGR ?
+ &priv->ingr_flows : &priv->egr_flows;
+ struct macsec_flow *flow;
+ int index;
+
+ index = find_first_zero_bit(bitmap, MSCC_MS_MAX_FLOWS);
+
+ if (index == MSCC_MS_MAX_FLOWS)
+ return ERR_PTR(-ENOMEM);
+
+ flow = kzalloc(sizeof(*flow), GFP_KERNEL);
+ if (!flow)
+ return ERR_PTR(-ENOMEM);
+
+ set_bit(index, bitmap);
+ flow->index = index;
+ flow->bank = bank;
+ flow->priority = 8;
+ flow->assoc_num = -1;
+
+ list_add_tail(&flow->list, &priv->macsec_flows);
+ return flow;
+}
+
+static void vsc8584_macsec_free_flow(struct vsc8531_private *priv,
+ struct macsec_flow *flow)
+{
+ unsigned long *bitmap = flow->bank == MACSEC_INGR ?
+ &priv->ingr_flows : &priv->egr_flows;
+
+ list_del(&flow->list);
+ clear_bit(flow->index, bitmap);
+ kfree(flow);
+}
+
+static int vsc8584_macsec_add_flow(struct phy_device *phydev,
+ struct macsec_flow *flow, bool update)
+{
+ int ret;
+
+ flow->port = MSCC_MS_PORT_CONTROLLED;
+ vsc8584_macsec_flow(phydev, flow);
+
+ if (update)
+ return 0;
+
+ ret = vsc8584_macsec_transformation(phydev, flow);
+ if (ret) {
+ vsc8584_macsec_free_flow(phydev->priv, flow);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int vsc8584_macsec_default_flows(struct phy_device *phydev)
+{
+ struct macsec_flow *flow;
+
+ /* Add a rule to let the MKA traffic go through, ingress */
+ flow = vsc8584_macsec_alloc_flow(phydev->priv, MACSEC_INGR);
+ if (IS_ERR(flow))
+ return PTR_ERR(flow);
+
+ flow->priority = 15;
+ flow->port = MSCC_MS_PORT_UNCONTROLLED;
+ flow->match.tagged = 1;
+ flow->match.untagged = 1;
+ flow->match.etype = 1;
+ flow->etype = ETH_P_PAE;
+ flow->action.bypass = 1;
+
+ vsc8584_macsec_flow(phydev, flow);
+ vsc8584_macsec_flow_enable(phydev, flow);
+
+ /* Add a rule to let the MKA traffic go through, egress */
+ flow = vsc8584_macsec_alloc_flow(phydev->priv, MACSEC_EGR);
+ if (IS_ERR(flow))
+ return PTR_ERR(flow);
+
+ flow->priority = 15;
+ flow->port = MSCC_MS_PORT_COMMON;
+ flow->match.untagged = 1;
+ flow->match.etype = 1;
+ flow->etype = ETH_P_PAE;
+ flow->action.bypass = 1;
+
+ vsc8584_macsec_flow(phydev, flow);
+ vsc8584_macsec_flow_enable(phydev, flow);
+
+ return 0;
+}
+
+static void vsc8584_macsec_del_flow(struct phy_device *phydev,
+ struct macsec_flow *flow)
+{
+ vsc8584_macsec_flow_disable(phydev, flow);
+ vsc8584_macsec_free_flow(phydev->priv, flow);
+}
+
+static int __vsc8584_macsec_add_rxsa(struct macsec_context *ctx,
+ struct macsec_flow *flow, bool update)
+{
+ struct phy_device *phydev = ctx->phydev;
+ struct vsc8531_private *priv = phydev->priv;
+
+ if (!flow) {
+ flow = vsc8584_macsec_alloc_flow(priv, MACSEC_INGR);
+ if (IS_ERR(flow))
+ return PTR_ERR(flow);
+
+ memcpy(flow->key, ctx->sa.key, priv->secy->key_len);
+ }
+
+ flow->assoc_num = ctx->sa.assoc_num;
+ flow->rx_sa = ctx->sa.rx_sa;
+
+ /* Always match tagged packets on ingress */
+ flow->match.tagged = 1;
+ flow->match.sci = 1;
+
+ if (priv->secy->validate_frames != MACSEC_VALIDATE_DISABLED)
+ flow->match.untagged = 1;
+
+ return vsc8584_macsec_add_flow(phydev, flow, update);
+}
+
+static int __vsc8584_macsec_add_txsa(struct macsec_context *ctx,
+ struct macsec_flow *flow, bool update)
+{
+ struct phy_device *phydev = ctx->phydev;
+ struct vsc8531_private *priv = phydev->priv;
+
+ if (!flow) {
+ flow = vsc8584_macsec_alloc_flow(priv, MACSEC_EGR);
+ if (IS_ERR(flow))
+ return PTR_ERR(flow);
+
+ memcpy(flow->key, ctx->sa.key, priv->secy->key_len);
+ }
+
+ flow->assoc_num = ctx->sa.assoc_num;
+ flow->tx_sa = ctx->sa.tx_sa;
+
+ /* Always match untagged packets on egress */
+ flow->match.untagged = 1;
+
+ return vsc8584_macsec_add_flow(phydev, flow, update);
+}
+
+static int vsc8584_macsec_dev_open(struct macsec_context *ctx)
+{
+ struct vsc8531_private *priv = ctx->phydev->priv;
+ struct macsec_flow *flow, *tmp;
+
+ /* No operation to perform before the commit step */
+ if (ctx->prepare)
+ return 0;
+
+ list_for_each_entry_safe(flow, tmp, &priv->macsec_flows, list)
+ vsc8584_macsec_flow_enable(ctx->phydev, flow);
+
+ return 0;
+}
+
+static int vsc8584_macsec_dev_stop(struct macsec_context *ctx)
+{
+ struct vsc8531_private *priv = ctx->phydev->priv;
+ struct macsec_flow *flow, *tmp;
+
+ /* No operation to perform before the commit step */
+ if (ctx->prepare)
+ return 0;
+
+ list_for_each_entry_safe(flow, tmp, &priv->macsec_flows, list)
+ vsc8584_macsec_flow_disable(ctx->phydev, flow);
+
+ return 0;
+}
+
+static int vsc8584_macsec_add_secy(struct macsec_context *ctx)
+{
+ struct vsc8531_private *priv = ctx->phydev->priv;
+ struct macsec_secy *secy = ctx->secy;
+
+ if (ctx->prepare) {
+ if (priv->secy)
+ return -EEXIST;
+
+ return 0;
+ }
+
+ priv->secy = secy;
+
+ vsc8584_macsec_flow_default_action(ctx->phydev, MACSEC_EGR,
+ secy->validate_frames != MACSEC_VALIDATE_DISABLED);
+ vsc8584_macsec_flow_default_action(ctx->phydev, MACSEC_INGR,
+ secy->validate_frames != MACSEC_VALIDATE_DISABLED);
+
+ return vsc8584_macsec_default_flows(ctx->phydev);
+}
+
+static int vsc8584_macsec_del_secy(struct macsec_context *ctx)
+{
+ struct vsc8531_private *priv = ctx->phydev->priv;
+ struct macsec_flow *flow, *tmp;
+
+ /* No operation to perform before the commit step */
+ if (ctx->prepare)
+ return 0;
+
+ list_for_each_entry_safe(flow, tmp, &priv->macsec_flows, list)
+ vsc8584_macsec_del_flow(ctx->phydev, flow);
+
+ vsc8584_macsec_flow_default_action(ctx->phydev, MACSEC_EGR, false);
+ vsc8584_macsec_flow_default_action(ctx->phydev, MACSEC_INGR, false);
+
+ priv->secy = NULL;
+ return 0;
+}
+
+static int vsc8584_macsec_upd_secy(struct macsec_context *ctx)
+{
+ /* No operation to perform before the commit step */
+ if (ctx->prepare)
+ return 0;
+
+ vsc8584_macsec_del_secy(ctx);
+ return vsc8584_macsec_add_secy(ctx);
+}
+
+static int vsc8584_macsec_add_rxsc(struct macsec_context *ctx)
+{
+ /* Nothing to do */
+ return 0;
+}
+
+static int vsc8584_macsec_upd_rxsc(struct macsec_context *ctx)
+{
+ return -EOPNOTSUPP;
+}
+
+static int vsc8584_macsec_del_rxsc(struct macsec_context *ctx)
+{
+ struct vsc8531_private *priv = ctx->phydev->priv;
+ struct macsec_flow *flow, *tmp;
+
+ /* No operation to perform before the commit step */
+ if (ctx->prepare)
+ return 0;
+
+ list_for_each_entry_safe(flow, tmp, &priv->macsec_flows, list) {
+ if (flow->bank == MACSEC_INGR && flow->rx_sa &&
+ flow->rx_sa->sc->sci == ctx->rx_sc->sci)
+ vsc8584_macsec_del_flow(ctx->phydev, flow);
+ }
+
+ return 0;
+}
+
+static int vsc8584_macsec_add_rxsa(struct macsec_context *ctx)
+{
+ struct macsec_flow *flow = NULL;
+
+ if (ctx->prepare)
+ return __vsc8584_macsec_add_rxsa(ctx, flow, false);
+
+ flow = vsc8584_macsec_find_flow(ctx, MACSEC_INGR);
+ if (IS_ERR(flow))
+ return PTR_ERR(flow);
+
+ vsc8584_macsec_flow_enable(ctx->phydev, flow);
+ return 0;
+}
+
+static int vsc8584_macsec_upd_rxsa(struct macsec_context *ctx)
+{
+ struct macsec_flow *flow;
+
+ flow = vsc8584_macsec_find_flow(ctx, MACSEC_INGR);
+ if (IS_ERR(flow))
+ return PTR_ERR(flow);
+
+ if (ctx->prepare) {
+ /* Make sure the flow is disabled before updating it */
+ vsc8584_macsec_flow_disable(ctx->phydev, flow);
+
+ return __vsc8584_macsec_add_rxsa(ctx, flow, true);
+ }
+
+ vsc8584_macsec_flow_enable(ctx->phydev, flow);
+ return 0;
+}
+
+static int vsc8584_macsec_del_rxsa(struct macsec_context *ctx)
+{
+ struct macsec_flow *flow;
+
+ flow = vsc8584_macsec_find_flow(ctx, MACSEC_INGR);
+
+ if (IS_ERR(flow))
+ return PTR_ERR(flow);
+ if (ctx->prepare)
+ return 0;
+
+ vsc8584_macsec_del_flow(ctx->phydev, flow);
+ return 0;
+}
+
+static int vsc8584_macsec_add_txsa(struct macsec_context *ctx)
+{
+ struct macsec_flow *flow = NULL;
+
+ if (ctx->prepare)
+ return __vsc8584_macsec_add_txsa(ctx, flow, false);
+
+ flow = vsc8584_macsec_find_flow(ctx, MACSEC_EGR);
+ if (IS_ERR(flow))
+ return PTR_ERR(flow);
+
+ vsc8584_macsec_flow_enable(ctx->phydev, flow);
+ return 0;
+}
+
+static int vsc8584_macsec_upd_txsa(struct macsec_context *ctx)
+{
+ struct macsec_flow *flow;
+
+ flow = vsc8584_macsec_find_flow(ctx, MACSEC_EGR);
+ if (IS_ERR(flow))
+ return PTR_ERR(flow);
+
+ if (ctx->prepare) {
+ /* Make sure the flow is disabled before updating it */
+ vsc8584_macsec_flow_disable(ctx->phydev, flow);
+
+ return __vsc8584_macsec_add_txsa(ctx, flow, true);
+ }
+
+ vsc8584_macsec_flow_enable(ctx->phydev, flow);
+ return 0;
+}
+
+static int vsc8584_macsec_del_txsa(struct macsec_context *ctx)
+{
+ struct macsec_flow *flow;
+
+ flow = vsc8584_macsec_find_flow(ctx, MACSEC_EGR);
+
+ if (IS_ERR(flow))
+ return PTR_ERR(flow);
+ if (ctx->prepare)
+ return 0;
+
+ vsc8584_macsec_del_flow(ctx->phydev, flow);
+ return 0;
+}
+
+static struct macsec_ops vsc8584_macsec_ops = {
+ .mdo_dev_open = vsc8584_macsec_dev_open,
+ .mdo_dev_stop = vsc8584_macsec_dev_stop,
+ .mdo_add_secy = vsc8584_macsec_add_secy,
+ .mdo_upd_secy = vsc8584_macsec_upd_secy,
+ .mdo_del_secy = vsc8584_macsec_del_secy,
+ .mdo_add_rxsc = vsc8584_macsec_add_rxsc,
+ .mdo_upd_rxsc = vsc8584_macsec_upd_rxsc,
+ .mdo_del_rxsc = vsc8584_macsec_del_rxsc,
+ .mdo_add_rxsa = vsc8584_macsec_add_rxsa,
+ .mdo_upd_rxsa = vsc8584_macsec_upd_rxsa,
+ .mdo_del_rxsa = vsc8584_macsec_del_rxsa,
+ .mdo_add_txsa = vsc8584_macsec_add_txsa,
+ .mdo_upd_txsa = vsc8584_macsec_upd_txsa,
+ .mdo_del_txsa = vsc8584_macsec_del_txsa,
+};
+#endif /* CONFIG_MACSEC */
+
/* Check if one PHY has already done the init of the parts common to all PHYs
* in the Quad PHY package.
*/
@@ -1733,6 +2791,24 @@ static int vsc8584_config_init(struct phy_device *phydev)
mutex_unlock(&phydev->mdio.bus->mdio_lock);
+#if IS_ENABLED(CONFIG_MACSEC)
+ /* MACsec */
+ switch (phydev->phy_id & phydev->drv->phy_id_mask) {
+ case PHY_ID_VSC856X:
+ case PHY_ID_VSC8575:
+ case PHY_ID_VSC8582:
+ case PHY_ID_VSC8584:
+ INIT_LIST_HEAD(&vsc8531->macsec_flows);
+ vsc8531->secy = NULL;
+
+ phydev->macsec_ops = &vsc8584_macsec_ops;
+
+ ret = vsc8584_macsec_init(phydev);
+ if (ret)
+ goto err;
+ }
+#endif
+
phy_write(phydev, MSCC_EXT_PAGE_ACCESS, MSCC_PHY_PAGE_STANDARD);
val = phy_read(phydev, MSCC_PHY_EXT_PHY_CNTL_1);
@@ -1758,6 +2834,43 @@ static int vsc8584_config_init(struct phy_device *phydev)
return ret;
}
+static int vsc8584_handle_interrupt(struct phy_device *phydev)
+{
+#if IS_ENABLED(CONFIG_MACSEC)
+ struct vsc8531_private *priv = phydev->priv;
+ struct macsec_flow *flow, *tmp;
+ u32 cause, rec;
+
+ /* Check MACsec PN rollover */
+ cause = vsc8584_macsec_phy_read(phydev, MACSEC_EGR,
+ MSCC_MS_INTR_CTRL_STATUS);
+ cause &= MSCC_MS_INTR_CTRL_STATUS_INTR_CLR_STATUS_M;
+ if (!(cause & MACSEC_INTR_CTRL_STATUS_ROLLOVER))
+ goto skip_rollover;
+
+ rec = 6 + priv->secy->key_len / sizeof(u32);
+ list_for_each_entry_safe(flow, tmp, &priv->macsec_flows, list) {
+ u32 val;
+
+ if (flow->bank != MACSEC_EGR || !flow->has_transformation)
+ continue;
+
+ val = vsc8584_macsec_phy_read(phydev, MACSEC_EGR,
+ MSCC_MS_XFORM_REC(flow->index, rec));
+ if (val == 0xffffffff) {
+ vsc8584_macsec_flow_disable(phydev, flow);
+ macsec_pn_wrapped(priv->secy, flow->tx_sa);
+ break;
+ }
+ }
+
+skip_rollover:
+#endif
+
+ phy_mac_interrupt(phydev);
+ return 0;
+}
+
static int vsc85xx_config_init(struct phy_device *phydev)
{
int rc, i, phy_id;
@@ -2201,6 +3314,20 @@ static int vsc85xx_config_intr(struct phy_device *phydev)
int rc;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+#if IS_ENABLED(CONFIG_MACSEC)
+ phy_write(phydev, MSCC_EXT_PAGE_ACCESS,
+ MSCC_PHY_PAGE_EXTENDED_2);
+ phy_write(phydev, MSCC_PHY_EXTENDED_INT,
+ MSCC_PHY_EXTENDED_INT_MS_EGR);
+ phy_write(phydev, MSCC_EXT_PAGE_ACCESS,
+ MSCC_PHY_PAGE_STANDARD);
+
+ vsc8584_macsec_phy_write(phydev, MACSEC_EGR,
+ MSCC_MS_AIC_CTRL, 0xf);
+ vsc8584_macsec_phy_write(phydev, MACSEC_EGR,
+ MSCC_MS_INTR_CTRL_STATUS,
+ MSCC_MS_INTR_CTRL_STATUS_INTR_ENABLE(MACSEC_INTR_CTRL_STATUS_ROLLOVER));
+#endif
rc = phy_write(phydev, MII_VSC85XX_INT_MASK,
MII_VSC85XX_INT_MASK_MASK);
} else {
@@ -2550,6 +3677,7 @@ static struct phy_driver vsc85xx_driver[] = {
.config_aneg = &vsc85xx_config_aneg,
.aneg_done = &genphy_aneg_done,
.read_status = &vsc85xx_read_status,
+ .handle_interrupt = &vsc8584_handle_interrupt,
.ack_interrupt = &vsc85xx_ack_interrupt,
.config_intr = &vsc85xx_config_intr,
.did_interrupt = &vsc8584_did_interrupt,
@@ -2602,6 +3730,7 @@ static struct phy_driver vsc85xx_driver[] = {
.config_aneg = &vsc85xx_config_aneg,
.aneg_done = &genphy_aneg_done,
.read_status = &vsc85xx_read_status,
+ .handle_interrupt = &vsc8584_handle_interrupt,
.ack_interrupt = &vsc85xx_ack_interrupt,
.config_intr = &vsc85xx_config_intr,
.did_interrupt = &vsc8584_did_interrupt,
@@ -2626,6 +3755,7 @@ static struct phy_driver vsc85xx_driver[] = {
.config_aneg = &vsc85xx_config_aneg,
.aneg_done = &genphy_aneg_done,
.read_status = &vsc85xx_read_status,
+ .handle_interrupt = &vsc8584_handle_interrupt,
.ack_interrupt = &vsc85xx_ack_interrupt,
.config_intr = &vsc85xx_config_intr,
.did_interrupt = &vsc8584_did_interrupt,
@@ -2650,6 +3780,7 @@ static struct phy_driver vsc85xx_driver[] = {
.config_aneg = &vsc85xx_config_aneg,
.aneg_done = &genphy_aneg_done,
.read_status = &vsc85xx_read_status,
+ .handle_interrupt = &vsc8584_handle_interrupt,
.ack_interrupt = &vsc85xx_ack_interrupt,
.config_intr = &vsc85xx_config_intr,
.did_interrupt = &vsc8584_did_interrupt,
diff --git a/drivers/net/phy/mscc_fc_buffer.h b/drivers/net/phy/mscc_fc_buffer.h
new file mode 100644
index 0000000..7e9c0e8
--- /dev/null
+++ b/drivers/net/phy/mscc_fc_buffer.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (C) 2019 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_FC_BUFFER_H_
+#define _MSCC_OCELOT_FC_BUFFER_H_
+
+#define MSCC_FCBUF_ENA_CFG 0x00
+#define MSCC_FCBUF_MODE_CFG 0x01
+#define MSCC_FCBUF_PPM_RATE_ADAPT_THRESH_CFG 0x02
+#define MSCC_FCBUF_TX_CTRL_QUEUE_CFG 0x03
+#define MSCC_FCBUF_TX_DATA_QUEUE_CFG 0x04
+#define MSCC_FCBUF_RX_DATA_QUEUE_CFG 0x05
+#define MSCC_FCBUF_TX_BUFF_XON_XOFF_THRESH_CFG 0x06
+#define MSCC_FCBUF_FC_READ_THRESH_CFG 0x07
+#define MSCC_FCBUF_TX_FRM_GAP_COMP 0x08
+
+#define MSCC_FCBUF_ENA_CFG_TX_ENA BIT(0)
+#define MSCC_FCBUF_ENA_CFG_RX_ENA BIT(4)
+
+#define MSCC_FCBUF_MODE_CFG_DROP_BEHAVIOUR BIT(4)
+#define MSCC_FCBUF_MODE_CFG_PAUSE_REACT_ENA BIT(8)
+#define MSCC_FCBUF_MODE_CFG_RX_PPM_RATE_ADAPT_ENA BIT(12)
+#define MSCC_FCBUF_MODE_CFG_TX_PPM_RATE_ADAPT_ENA BIT(16)
+#define MSCC_FCBUF_MODE_CFG_TX_CTRL_QUEUE_ENA BIT(20)
+#define MSCC_FCBUF_MODE_CFG_PAUSE_GEN_ENA BIT(24)
+#define MSCC_FCBUF_MODE_CFG_INCLUDE_PAUSE_RCVD_IN_PAUSE_GEN BIT(28)
+
+#define MSCC_FCBUF_PPM_RATE_ADAPT_THRESH_CFG_TX_THRESH(x) (x)
+#define MSCC_FCBUF_PPM_RATE_ADAPT_THRESH_CFG_TX_THRESH_M GENMASK(15, 0)
+#define MSCC_FCBUF_PPM_RATE_ADAPT_THRESH_CFG_TX_OFFSET(x) ((x) << 16)
+#define MSCC_FCBUF_PPM_RATE_ADAPT_THRESH_CFG_TX_OFFSET_M GENMASK(19, 16)
+#define MSCC_FCBUF_PPM_RATE_ADAPT_THRESH_CFG_RX_THRESH(x) ((x) << 20)
+#define MSCC_FCBUF_PPM_RATE_ADAPT_THRESH_CFG_RX_THRESH_M GENMASK(31, 20)
+
+#define MSCC_FCBUF_TX_CTRL_QUEUE_CFG_START(x) (x)
+#define MSCC_FCBUF_TX_CTRL_QUEUE_CFG_START_M GENMASK(15, 0)
+#define MSCC_FCBUF_TX_CTRL_QUEUE_CFG_END(x) ((x) << 16)
+#define MSCC_FCBUF_TX_CTRL_QUEUE_CFG_END_M GENMASK(31, 16)
+
+#define MSCC_FCBUF_TX_DATA_QUEUE_CFG_START(x) (x)
+#define MSCC_FCBUF_TX_DATA_QUEUE_CFG_START_M GENMASK(15, 0)
+#define MSCC_FCBUF_TX_DATA_QUEUE_CFG_END(x) ((x) << 16)
+#define MSCC_FCBUF_TX_DATA_QUEUE_CFG_END_M GENMASK(31, 16)
+
+#define MSCC_FCBUF_RX_DATA_QUEUE_CFG_START(x) (x)
+#define MSCC_FCBUF_RX_DATA_QUEUE_CFG_START_M GENMASK(15, 0)
+#define MSCC_FCBUF_RX_DATA_QUEUE_CFG_END(x) ((x) << 16)
+#define MSCC_FCBUF_RX_DATA_QUEUE_CFG_END_M GENMASK(31, 16)
+
+#define MSCC_FCBUF_TX_BUFF_XON_XOFF_THRESH_CFG_XOFF_THRESH(x) (x)
+#define MSCC_FCBUF_TX_BUFF_XON_XOFF_THRESH_CFG_XOFF_THRESH_M GENMASK(15, 0)
+#define MSCC_FCBUF_TX_BUFF_XON_XOFF_THRESH_CFG_XON_THRESH(x) ((x) << 16)
+#define MSCC_FCBUF_TX_BUFF_XON_XOFF_THRESH_CFG_XON_THRESH_M GENMASK(31, 16)
+
+#define MSCC_FCBUF_FC_READ_THRESH_CFG_TX_THRESH(x) (x)
+#define MSCC_FCBUF_FC_READ_THRESH_CFG_TX_THRESH_M GENMASK(15, 0)
+#define MSCC_FCBUF_FC_READ_THRESH_CFG_RX_THRESH(x) ((x) << 16)
+#define MSCC_FCBUF_FC_READ_THRESH_CFG_RX_THRESH_M GENMASK(31, 16)
+
+#endif
diff --git a/drivers/net/phy/mscc_mac.h b/drivers/net/phy/mscc_mac.h
new file mode 100644
index 0000000..9420ee5
--- /dev/null
+++ b/drivers/net/phy/mscc_mac.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_LINE_MAC_H_
+#define _MSCC_OCELOT_LINE_MAC_H_
+
+#define MSCC_MAC_CFG_ENA_CFG 0x00
+#define MSCC_MAC_CFG_MODE_CFG 0x01
+#define MSCC_MAC_CFG_MAXLEN_CFG 0x02
+#define MSCC_MAC_CFG_NUM_TAGS_CFG 0x03
+#define MSCC_MAC_CFG_TAGS_CFG 0x04
+#define MSCC_MAC_CFG_ADV_CHK_CFG 0x07
+#define MSCC_MAC_CFG_LFS_CFG 0x08
+#define MSCC_MAC_CFG_LB_CFG 0x09
+#define MSCC_MAC_CFG_PKTINF_CFG 0x0a
+#define MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL 0x0b
+#define MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_2 0x0c
+#define MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL 0x0d
+#define MSCC_MAC_PAUSE_CFG_STATE 0x0e
+#define MSCC_MAC_PAUSE_CFG_MAC_ADDRESS_LSB 0x0f
+#define MSCC_MAC_PAUSE_CFG_MAC_ADDRESS_MSB 0x10
+#define MSCC_MAC_STATUS_RX_LANE_STICKY_0 0x11
+#define MSCC_MAC_STATUS_RX_LANE_STICKY_1 0x12
+#define MSCC_MAC_STATUS_TX_MONITOR_STICKY 0x13
+#define MSCC_MAC_STATUS_TX_MONITOR_STICKY_MASK 0x14
+#define MSCC_MAC_STATUS_STICKY 0x15
+#define MSCC_MAC_STATUS_STICKY_MASK 0x16
+#define MSCC_MAC_STATS_32BIT_RX_HIH_CKSM_ERR_CNT 0x17
+#define MSCC_MAC_STATS_32BIT_RX_XGMII_PROT_ERR_CNT 0x18
+#define MSCC_MAC_STATS_32BIT_RX_SYMBOL_ERR_CNT 0x19
+#define MSCC_MAC_STATS_32BIT_RX_PAUSE_CNT 0x1a
+#define MSCC_MAC_STATS_32BIT_RX_UNSUP_OPCODE_CNT 0x1b
+#define MSCC_MAC_STATS_32BIT_RX_UC_CNT 0x1c
+#define MSCC_MAC_STATS_32BIT_RX_MC_CNT 0x1d
+#define MSCC_MAC_STATS_32BIT_RX_BC_CNT 0x1e
+#define MSCC_MAC_STATS_32BIT_RX_CRC_ERR_CNT 0x1f
+#define MSCC_MAC_STATS_32BIT_RX_UNDERSIZE_CNT 0x20
+#define MSCC_MAC_STATS_32BIT_RX_FRAGMENTS_CNT 0x21
+#define MSCC_MAC_STATS_32BIT_RX_IN_RANGE_LEN_ERR_CNT 0x22
+#define MSCC_MAC_STATS_32BIT_RX_OUT_OF_RANGE_LEN_ERR_CNT 0x23
+#define MSCC_MAC_STATS_32BIT_RX_OVERSIZE_CNT 0x24
+#define MSCC_MAC_STATS_32BIT_RX_JABBERS_CNT 0x25
+#define MSCC_MAC_STATS_32BIT_RX_SIZE64_CNT 0x26
+#define MSCC_MAC_STATS_32BIT_RX_SIZE65TO127_CNT 0x27
+#define MSCC_MAC_STATS_32BIT_RX_SIZE128TO255_CNT 0x28
+#define MSCC_MAC_STATS_32BIT_RX_SIZE256TO511_CNT 0x29
+#define MSCC_MAC_STATS_32BIT_RX_SIZE512TO1023_CNT 0x2a
+#define MSCC_MAC_STATS_32BIT_RX_SIZE1024TO1518_CNT 0x2b
+#define MSCC_MAC_STATS_32BIT_RX_SIZE1519TOMAX_CNT 0x2c
+#define MSCC_MAC_STATS_32BIT_RX_IPG_SHRINK_CNT 0x2d
+#define MSCC_MAC_STATS_32BIT_TX_PAUSE_CNT 0x2e
+#define MSCC_MAC_STATS_32BIT_TX_UC_CNT 0x2f
+#define MSCC_MAC_STATS_32BIT_TX_MC_CNT 0x30
+#define MSCC_MAC_STATS_32BIT_TX_BC_CNT 0x31
+#define MSCC_MAC_STATS_32BIT_TX_SIZE64_CNT 0x32
+#define MSCC_MAC_STATS_32BIT_TX_SIZE65TO127_CNT 0x33
+#define MSCC_MAC_STATS_32BIT_TX_SIZE128TO255_CNT 0x34
+#define MSCC_MAC_STATS_32BIT_TX_SIZE256TO511_CNT 0x35
+#define MSCC_MAC_STATS_32BIT_TX_SIZE512TO1023_CNT 0x36
+#define MSCC_MAC_STATS_32BIT_TX_SIZE1024TO1518_CNT 0x37
+#define MSCC_MAC_STATS_32BIT_TX_SIZE1519TOMAX_CNT 0x38
+#define MSCC_MAC_STATS_40BIT_RX_BAD_BYTES_CNT 0x39
+#define MSCC_MAC_STATS_40BIT_RX_BAD_BYTES_MSB_CNT 0x3a
+#define MSCC_MAC_STATS_40BIT_RX_OK_BYTES_CNT 0x3b
+#define MSCC_MAC_STATS_40BIT_RX_OK_BYTES_MSB_CNT 0x3c
+#define MSCC_MAC_STATS_40BIT_RX_IN_BYTES_CNT 0x3d
+#define MSCC_MAC_STATS_40BIT_RX_IN_BYTES_MSB_CNT 0x3e
+#define MSCC_MAC_STATS_40BIT_TX_OK_BYTES_CNT 0x3f
+#define MSCC_MAC_STATS_40BIT_TX_OK_BYTES_MSB_CNT 0x40
+#define MSCC_MAC_STATS_40BIT_TX_OUT_BYTES_CNT 0x41
+#define MSCC_MAC_STATS_40BIT_TX_OUT_BYTES_MSB_CNT 0x42
+
+#define MSCC_MAC_CFG_ENA_CFG_RX_CLK_ENA BIT(0)
+#define MSCC_MAC_CFG_ENA_CFG_TX_CLK_ENA BIT(4)
+#define MSCC_MAC_CFG_ENA_CFG_RX_SW_RST BIT(8)
+#define MSCC_MAC_CFG_ENA_CFG_TX_SW_RST BIT(12)
+#define MSCC_MAC_CFG_ENA_CFG_RX_ENA BIT(16)
+#define MSCC_MAC_CFG_ENA_CFG_TX_ENA BIT(20)
+
+#define MSCC_MAC_CFG_MODE_CFG_FORCE_CW_UPDATE_INTERVAL(x) ((x) << 20)
+#define MSCC_MAC_CFG_MODE_CFG_FORCE_CW_UPDATE_INTERVAL_M GENMASK(29, 20)
+#define MSCC_MAC_CFG_MODE_CFG_FORCE_CW_UPDATE BIT(16)
+#define MSCC_MAC_CFG_MODE_CFG_TUNNEL_PAUSE_FRAMES BIT(14)
+#define MSCC_MAC_CFG_MODE_CFG_MAC_PREAMBLE_CFG(x) ((x) << 10)
+#define MSCC_MAC_CFG_MODE_CFG_MAC_PREAMBLE_CFG_M GENMASK(12, 10)
+#define MSCC_MAC_CFG_MODE_CFG_MAC_IPG_CFG BIT(6)
+#define MSCC_MAC_CFG_MODE_CFG_XGMII_GEN_MODE_ENA BIT(4)
+#define MSCC_MAC_CFG_MODE_CFG_HIH_CRC_CHECK BIT(2)
+#define MSCC_MAC_CFG_MODE_CFG_UNDERSIZED_FRAME_DROP_DIS BIT(1)
+#define MSCC_MAC_CFG_MODE_CFG_DISABLE_DIC BIT(0)
+
+#define MSCC_MAC_CFG_MAXLEN_CFG_MAX_LEN_TAG_CHK BIT(16)
+#define MSCC_MAC_CFG_MAXLEN_CFG_MAX_LEN(x) (x)
+#define MSCC_MAC_CFG_MAXLEN_CFG_MAX_LEN_M GENMASK(15, 0)
+
+#define MSCC_MAC_CFG_TAGS_CFG_RSZ 0x4
+#define MSCC_MAC_CFG_TAGS_CFG_TAG_ID(x) ((x) << 16)
+#define MSCC_MAC_CFG_TAGS_CFG_TAG_ID_M GENMASK(31, 16)
+#define MSCC_MAC_CFG_TAGS_CFG_TAG_ENA BIT(4)
+
+#define MSCC_MAC_CFG_ADV_CHK_CFG_EXT_EOP_CHK_ENA BIT(24)
+#define MSCC_MAC_CFG_ADV_CHK_CFG_EXT_SOP_CHK_ENA BIT(20)
+#define MSCC_MAC_CFG_ADV_CHK_CFG_SFD_CHK_ENA BIT(16)
+#define MSCC_MAC_CFG_ADV_CHK_CFG_PRM_SHK_CHK_DIS BIT(12)
+#define MSCC_MAC_CFG_ADV_CHK_CFG_PRM_CHK_ENA BIT(8)
+#define MSCC_MAC_CFG_ADV_CHK_CFG_OOR_ERR_ENA BIT(4)
+#define MSCC_MAC_CFG_ADV_CHK_CFG_INR_ERR_ENA BIT(0)
+
+#define MSCC_MAC_CFG_LFS_CFG_LFS_INH_TX BIT(8)
+#define MSCC_MAC_CFG_LFS_CFG_LFS_DIS_TX BIT(4)
+#define MSCC_MAC_CFG_LFS_CFG_LFS_UNIDIR_ENA BIT(3)
+#define MSCC_MAC_CFG_LFS_CFG_USE_LEADING_EDGE_DETECT BIT(2)
+#define MSCC_MAC_CFG_LFS_CFG_SPURIOUS_Q_DIS BIT(1)
+#define MSCC_MAC_CFG_LFS_CFG_LFS_MODE_ENA BIT(0)
+
+#define MSCC_MAC_CFG_LB_CFG_XGMII_HOST_LB_ENA BIT(4)
+#define MSCC_MAC_CFG_LB_CFG_XGMII_PHY_LB_ENA BIT(0)
+
+#define MSCC_MAC_CFG_PKTINF_CFG_STRIP_FCS_ENA BIT(0)
+#define MSCC_MAC_CFG_PKTINF_CFG_INSERT_FCS_ENA BIT(4)
+#define MSCC_MAC_CFG_PKTINF_CFG_STRIP_PREAMBLE_ENA BIT(8)
+#define MSCC_MAC_CFG_PKTINF_CFG_INSERT_PREAMBLE_ENA BIT(12)
+#define MSCC_MAC_CFG_PKTINF_CFG_LPI_RELAY_ENA BIT(16)
+#define MSCC_MAC_CFG_PKTINF_CFG_LF_RELAY_ENA BIT(20)
+#define MSCC_MAC_CFG_PKTINF_CFG_RF_RELAY_ENA BIT(24)
+#define MSCC_MAC_CFG_PKTINF_CFG_ENABLE_TX_PADDING BIT(25)
+#define MSCC_MAC_CFG_PKTINF_CFG_ENABLE_RX_PADDING BIT(26)
+#define MSCC_MAC_CFG_PKTINF_CFG_ENABLE_4BYTE_PREAMBLE BIT(27)
+#define MSCC_MAC_CFG_PKTINF_CFG_MACSEC_BYPASS_NUM_PTP_STALL_CLKS(x) ((x) << 28)
+#define MSCC_MAC_CFG_PKTINF_CFG_MACSEC_BYPASS_NUM_PTP_STALL_CLKS_M GENMASK(30, 28)
+
+#define MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_PAUSE_VALUE(x) ((x) << 16)
+#define MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_PAUSE_VALUE_M GENMASK(31, 16)
+#define MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_WAIT_FOR_LPI_LOW BIT(12)
+#define MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_USE_PAUSE_STALL_ENA BIT(8)
+#define MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_PAUSE_REPL_MODE BIT(4)
+#define MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_PAUSE_FRC_FRAME BIT(2)
+#define MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_PAUSE_MODE(x) (x)
+#define MSCC_MAC_PAUSE_CFG_TX_FRAME_CTRL_PAUSE_MODE_M GENMASK(1, 0)
+
+#define MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_EARLY_PAUSE_DETECT_ENA BIT(16)
+#define MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_PRE_CRC_MODE BIT(20)
+#define MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_PAUSE_TIMER_ENA BIT(12)
+#define MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_PAUSE_REACT_ENA BIT(8)
+#define MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_PAUSE_FRAME_DROP_ENA BIT(4)
+#define MSCC_MAC_PAUSE_CFG_RX_FRAME_CTRL_PAUSE_MODE BIT(0)
+
+#define MSCC_MAC_PAUSE_CFG_STATE_PAUSE_STATE BIT(0)
+#define MSCC_MAC_PAUSE_CFG_STATE_MAC_TX_PAUSE_GEN BIT(4)
+
+#define MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL 0x2
+#define MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE(x) (x)
+#define MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE_M GENMASK(2, 0)
+
+#endif /* _MSCC_OCELOT_LINE_MAC_H_ */
diff --git a/drivers/net/phy/mscc_macsec.h b/drivers/net/phy/mscc_macsec.h
new file mode 100644
index 0000000..d9ab6ab
--- /dev/null
+++ b/drivers/net/phy/mscc_macsec.h
@@ -0,0 +1,266 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2018 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_MACSEC_H_
+#define _MSCC_OCELOT_MACSEC_H_
+
+#define MSCC_MS_MAX_FLOWS 16
+
+#define CONTROL_TYPE_EGRESS 0x6
+#define CONTROL_TYPE_INGRESS 0xf
+#define CONTROL_IV0 BIT(5)
+#define CONTROL_IV1 BIT(6)
+#define CONTROL_IV2 BIT(7)
+#define CONTROL_UPDATE_SEQ BIT(13)
+#define CONTROL_IV_IN_SEQ BIT(14)
+#define CONTROL_ENCRYPT_AUTH BIT(15)
+#define CONTROL_KEY_IN_CTX BIT(16)
+#define CONTROL_CRYPTO_ALG(x) ((x) << 17)
+#define CTRYPTO_ALG_AES_CTR_128 0x5
+#define CTRYPTO_ALG_AES_CTR_192 0x6
+#define CTRYPTO_ALG_AES_CTR_256 0x7
+#define CONTROL_DIGEST_TYPE(x) ((x) << 21)
+#define CONTROL_AUTH_ALG(x) ((x) << 23)
+#define AUTH_ALG_AES_GHAS 0x4
+#define CONTROL_AN(x) ((x) << 26)
+#define CONTROL_SEQ_TYPE(x) ((x) << 28)
+#define CONTROL_SEQ_MASK BIT(30)
+#define CONTROL_CONTEXT_ID BIT(31)
+
+enum mscc_macsec_destination_ports {
+ MSCC_MS_PORT_COMMON = 0,
+ MSCC_MS_PORT_RSVD = 1,
+ MSCC_MS_PORT_CONTROLLED = 2,
+ MSCC_MS_PORT_UNCONTROLLED = 3,
+};
+
+enum mscc_macsec_drop_actions {
+ MSCC_MS_ACTION_BYPASS_CRC = 0,
+ MSCC_MS_ACTION_BYPASS_BAD = 1,
+ MSCC_MS_ACTION_DROP = 2,
+ MSCC_MS_ACTION_BYPASS = 3,
+};
+
+enum mscc_macsec_flow_types {
+ MSCC_MS_FLOW_BYPASS = 0,
+ MSCC_MS_FLOW_DROP = 1,
+ MSCC_MS_FLOW_INGRESS = 2,
+ MSCC_MS_FLOW_EGRESS = 3,
+};
+
+enum mscc_macsec_validate_levels {
+ MSCC_MS_VALIDATE_DISABLED = 0,
+ MSCC_MS_VALIDATE_CHECK = 1,
+ MSCC_MS_VALIDATE_STRICT = 2,
+};
+
+#define MSCC_MS_XFORM_REC(x, y) (((x) << 5) + (y))
+#define MSCC_MS_ENA_CFG 0x800
+#define MSCC_MS_FC_CFG 0x804
+#define MSCC_MS_SAM_MAC_SA_MATCH_LO(x) (0x1000 + ((x) << 4))
+#define MSCC_MS_SAM_MAC_SA_MATCH_HI(x) (0x1001 + ((x) << 4))
+#define MSCC_MS_SAM_MISC_MATCH(x) (0x1004 + ((x) << 4))
+#define MSCC_MS_SAM_MATCH_SCI_LO(x) (0x1005 + ((x) << 4))
+#define MSCC_MS_SAM_MATCH_SCI_HI(x) (0x1006 + ((x) << 4))
+#define MSCC_MS_SAM_MASK(x) (0x1007 + ((x) << 4))
+#define MSCC_MS_SAM_ENTRY_SET1 0x1808
+#define MSCC_MS_SAM_ENTRY_CLEAR1 0x180c
+#define MSCC_MS_SAM_FLOW_CTRL(x) (0x1c00 + (x))
+#define MSCC_MS_SAM_CP_TAG 0x1e40
+#define MSCC_MS_SAM_NM_FLOW_NCP 0x1e51
+#define MSCC_MS_SAM_NM_FLOW_CP 0x1e52
+#define MSCC_MS_MISC_CONTROL 0x1e5f
+#define MSCC_MS_COUNT_CONTROL 0x3204
+#define MSCC_MS_PARAMS2_IG_CC_CONTROL 0x3a10
+#define MSCC_MS_PARAMS2_IG_CP_TAG 0x3a14
+#define MSCC_MS_VLAN_MTU_CHECK(x) (0x3c40 + (x))
+#define MSCC_MS_NON_VLAN_MTU_CHECK 0x3c48
+#define MSCC_MS_PP_CTRL 0x3c4b
+#define MSCC_MS_STATUS_CONTEXT_CTRL 0x3d02
+#define MSCC_MS_INTR_CTRL_STATUS 0x3d04
+#define MSCC_MS_BLOCK_CTX_UPDATE 0x3d0c
+#define MSCC_MS_AIC_CTRL 0x3e02
+
+/* MACSEC_ENA_CFG */
+#define MSCC_MS_ENA_CFG_CLK_ENA BIT(0)
+#define MSCC_MS_ENA_CFG_SW_RST BIT(1)
+#define MSCC_MS_ENA_CFG_MACSEC_BYPASS_ENA BIT(8)
+#define MSCC_MS_ENA_CFG_MACSEC_ENA BIT(9)
+#define MSCC_MS_ENA_CFG_MACSEC_SPEED_MODE(x) ((x) << 10)
+#define MSCC_MS_ENA_CFG_MACSEC_SPEED_MODE_M GENMASK(12, 10)
+
+/* MACSEC_FC_CFG */
+#define MSCC_MS_FC_CFG_FCBUF_ENA BIT(0)
+#define MSCC_MS_FC_CFG_USE_PKT_EXPANSION_INDICATION BIT(1)
+#define MSCC_MS_FC_CFG_LOW_THRESH(x) ((x) << 4)
+#define MSCC_MS_FC_CFG_LOW_THRESH_M GENMASK(7, 4)
+#define MSCC_MS_FC_CFG_HIGH_THRESH(x) ((x) << 8)
+#define MSCC_MS_FC_CFG_HIGH_THRESH_M GENMASK(11, 8)
+#define MSCC_MS_FC_CFG_LOW_BYTES_VAL(x) ((x) << 12)
+#define MSCC_MS_FC_CFG_LOW_BYTES_VAL_M GENMASK(14, 12)
+#define MSCC_MS_FC_CFG_HIGH_BYTES_VAL(x) ((x) << 16)
+#define MSCC_MS_FC_CFG_HIGH_BYTES_VAL_M GENMASK(18, 16)
+
+/* MSCC_MS_SAM_MAC_SA_MATCH_HI */
+#define MSCC_MS_SAM_MAC_SA_MATCH_HI_ETYPE(x) ((x) << 16)
+#define MSCC_MS_SAM_MAC_SA_MATCH_HI_ETYPE_M GENMASK(31, 16)
+
+/* MACSEC_SAM_MISC_MATCH */
+#define MSCC_MS_SAM_MISC_MATCH_VLAN_VALID BIT(0)
+#define MSCC_MS_SAM_MISC_MATCH_QINQ_FOUND BIT(1)
+#define MSCC_MS_SAM_MISC_MATCH_STAG_VALID BIT(2)
+#define MSCC_MS_SAM_MISC_MATCH_QTAG_VALID BIT(3)
+#define MSCC_MS_SAM_MISC_MATCH_VLAN_UP(x) ((x) << 4)
+#define MSCC_MS_SAM_MISC_MATCH_VLAN_UP_M GENMASK(6, 4)
+#define MSCC_MS_SAM_MISC_MATCH_CONTROL_PACKET BIT(7)
+#define MSCC_MS_SAM_MISC_MATCH_UNTAGGED BIT(8)
+#define MSCC_MS_SAM_MISC_MATCH_TAGGED BIT(9)
+#define MSCC_MS_SAM_MISC_MATCH_BAD_TAG BIT(10)
+#define MSCC_MS_SAM_MISC_MATCH_KAY_TAG BIT(11)
+#define MSCC_MS_SAM_MISC_MATCH_SOURCE_PORT(x) ((x) << 12)
+#define MSCC_MS_SAM_MISC_MATCH_SOURCE_PORT_M GENMASK(13, 12)
+#define MSCC_MS_SAM_MISC_MATCH_PRIORITY(x) ((x) << 16)
+#define MSCC_MS_SAM_MISC_MATCH_PRIORITY_M GENMASK(19, 16)
+#define MSCC_MS_SAM_MISC_MATCH_AN(x) ((x) << 24)
+#define MSCC_MS_SAM_MISC_MATCH_TCI(x) ((x) << 26)
+
+/* MACSEC_SAM_MASK */
+#define MSCC_MS_SAM_MASK_MAC_SA_MASK(x) (x)
+#define MSCC_MS_SAM_MASK_MAC_SA_MASK_M GENMASK(5, 0)
+#define MSCC_MS_SAM_MASK_MAC_DA_MASK(x) ((x) << 6)
+#define MSCC_MS_SAM_MASK_MAC_DA_MASK_M GENMASK(11, 6)
+#define MSCC_MS_SAM_MASK_MAC_ETYPE_MASK BIT(12)
+#define MSCC_MS_SAM_MASK_VLAN_VLD_MASK BIT(13)
+#define MSCC_MS_SAM_MASK_QINQ_FOUND_MASK BIT(14)
+#define MSCC_MS_SAM_MASK_STAG_VLD_MASK BIT(15)
+#define MSCC_MS_SAM_MASK_QTAG_VLD_MASK BIT(16)
+#define MSCC_MS_SAM_MASK_VLAN_UP_MASK BIT(17)
+#define MSCC_MS_SAM_MASK_VLAN_ID_MASK BIT(18)
+#define MSCC_MS_SAM_MASK_SOURCE_PORT_MASK BIT(19)
+#define MSCC_MS_SAM_MASK_CTL_PACKET_MASK BIT(20)
+#define MSCC_MS_SAM_MASK_VLAN_UP_INNER_MASK BIT(21)
+#define MSCC_MS_SAM_MASK_VLAN_ID_INNER_MASK BIT(22)
+#define MSCC_MS_SAM_MASK_SCI_MASK BIT(23)
+#define MSCC_MS_SAM_MASK_AN_MASK(x) ((x) << 24)
+#define MSCC_MS_SAM_MASK_TCI_MASK(x) ((x) << 26)
+
+/* MACSEC_SAM_FLOW_CTRL_EGR */
+#define MSCC_MS_SAM_FLOW_CTRL_FLOW_TYPE(x) (x)
+#define MSCC_MS_SAM_FLOW_CTRL_FLOW_TYPE_M GENMASK(1, 0)
+#define MSCC_MS_SAM_FLOW_CTRL_DEST_PORT(x) ((x) << 2)
+#define MSCC_MS_SAM_FLOW_CTRL_DEST_PORT_M GENMASK(3, 2)
+#define MSCC_MS_SAM_FLOW_CTRL_RESV_4 BIT(4)
+#define MSCC_MS_SAM_FLOW_CTRL_FLOW_CRYPT_AUTH BIT(5)
+#define MSCC_MS_SAM_FLOW_CTRL_DROP_ACTION(x) ((x) << 6)
+#define MSCC_MS_SAM_FLOW_CTRL_DROP_ACTION_M GENMASK(7, 6)
+#define MSCC_MS_SAM_FLOW_CTRL_RESV_15_TO_8(x) ((x) << 8)
+#define MSCC_MS_SAM_FLOW_CTRL_RESV_15_TO_8_M GENMASK(15, 8)
+#define MSCC_MS_SAM_FLOW_CTRL_PROTECT_FRAME BIT(16)
+#define MSCC_MS_SAM_FLOW_CTRL_REPLAY_PROTECT BIT(16)
+#define MSCC_MS_SAM_FLOW_CTRL_SA_IN_USE BIT(17)
+#define MSCC_MS_SAM_FLOW_CTRL_INCLUDE_SCI BIT(18)
+#define MSCC_MS_SAM_FLOW_CTRL_USE_ES BIT(19)
+#define MSCC_MS_SAM_FLOW_CTRL_USE_SCB BIT(20)
+#define MSCC_MS_SAM_FLOW_CTRL_VALIDATE_FRAMES(x) ((x) << 19)
+#define MSCC_MS_SAM_FLOW_CTRL_TAG_BYPASS_SIZE(x) ((x) << 21)
+#define MSCC_MS_SAM_FLOW_CTRL_TAG_BYPASS_SIZE_M GENMASK(22, 21)
+#define MSCC_MS_SAM_FLOW_CTRL_RESV_23 BIT(23)
+#define MSCC_MS_SAM_FLOW_CTRL_CONFIDENTIALITY_OFFSET(x) ((x) << 24)
+#define MSCC_MS_SAM_FLOW_CTRL_CONFIDENTIALITY_OFFSET_M GENMASK(30, 24)
+#define MSCC_MS_SAM_FLOW_CTRL_CONF_PROTECT BIT(31)
+
+/* MACSEC_SAM_CP_TAG */
+#define MSCC_MS_SAM_CP_TAG_MAP_TBL(x) (x)
+#define MSCC_MS_SAM_CP_TAG_MAP_TBL_M GENMASK(23, 0)
+#define MSCC_MS_SAM_CP_TAG_DEF_UP(x) ((x) << 24)
+#define MSCC_MS_SAM_CP_TAG_DEF_UP_M GENMASK(26, 24)
+#define MSCC_MS_SAM_CP_TAG_STAG_UP_EN BIT(27)
+#define MSCC_MS_SAM_CP_TAG_QTAG_UP_EN BIT(28)
+#define MSCC_MS_SAM_CP_TAG_PARSE_QINQ BIT(29)
+#define MSCC_MS_SAM_CP_TAG_PARSE_STAG BIT(30)
+#define MSCC_MS_SAM_CP_TAG_PARSE_QTAG BIT(31)
+
+/* MACSEC_SAM_NM_FLOW_NCP */
+#define MSCC_MS_SAM_NM_FLOW_NCP_UNTAGGED_FLOW_TYPE(x) (x)
+#define MSCC_MS_SAM_NM_FLOW_NCP_UNTAGGED_DEST_PORT(x) ((x) << 2)
+#define MSCC_MS_SAM_NM_FLOW_NCP_UNTAGGED_DROP_ACTION(x) ((x) << 6)
+#define MSCC_MS_SAM_NM_FLOW_NCP_TAGGED_FLOW_TYPE(x) ((x) << 8)
+#define MSCC_MS_SAM_NM_FLOW_NCP_TAGGED_DEST_PORT(x) ((x) << 10)
+#define MSCC_MS_SAM_NM_FLOW_NCP_TAGGED_DROP_ACTION(x) ((x) << 14)
+#define MSCC_MS_SAM_NM_FLOW_NCP_BADTAG_FLOW_TYPE(x) ((x) << 16)
+#define MSCC_MS_SAM_NM_FLOW_NCP_BADTAG_DEST_PORT(x) ((x) << 18)
+#define MSCC_MS_SAM_NM_FLOW_NCP_BADTAG_DROP_ACTION(x) ((x) << 22)
+#define MSCC_MS_SAM_NM_FLOW_NCP_KAY_FLOW_TYPE(x) ((x) << 24)
+#define MSCC_MS_SAM_NM_FLOW_NCP_KAY_DEST_PORT(x) ((x) << 26)
+#define MSCC_MS_SAM_NM_FLOW_NCP_KAY_DROP_ACTION(x) ((x) << 30)
+
+/* MACSEC_SAM_NM_FLOW_CP */
+#define MSCC_MS_SAM_NM_FLOW_CP_UNTAGGED_FLOW_TYPE(x) (x)
+#define MSCC_MS_SAM_NM_FLOW_CP_UNTAGGED_DEST_PORT(x) ((x) << 2)
+#define MSCC_MS_SAM_NM_FLOW_CP_UNTAGGED_DROP_ACTION(x) ((x) << 6)
+#define MSCC_MS_SAM_NM_FLOW_CP_TAGGED_FLOW_TYPE(x) ((x) << 8)
+#define MSCC_MS_SAM_NM_FLOW_CP_TAGGED_DEST_PORT(x) ((x) << 10)
+#define MSCC_MS_SAM_NM_FLOW_CP_TAGGED_DROP_ACTION(x) ((x) << 14)
+#define MSCC_MS_SAM_NM_FLOW_CP_BADTAG_FLOW_TYPE(x) ((x) << 16)
+#define MSCC_MS_SAM_NM_FLOW_CP_BADTAG_DEST_PORT(x) ((x) << 18)
+#define MSCC_MS_SAM_NM_FLOW_CP_BADTAG_DROP_ACTION(x) ((x) << 22)
+#define MSCC_MS_SAM_NM_FLOW_CP_KAY_FLOW_TYPE(x) ((x) << 24)
+#define MSCC_MS_SAM_NM_FLOW_CP_KAY_DEST_PORT(x) ((x) << 26)
+#define MSCC_MS_SAM_NM_FLOW_CP_KAY_DROP_ACTION(x) ((x) << 30)
+
+/* MACSEC_MISC_CONTROL */
+#define MSCC_MS_MISC_CONTROL_MC_LATENCY_FIX(x) (x)
+#define MSCC_MS_MISC_CONTROL_MC_LATENCY_FIX_M GENMASK(5, 0)
+#define MSCC_MS_MISC_CONTROL_STATIC_BYPASS BIT(8)
+#define MSCC_MS_MISC_CONTROL_NM_MACSEC_EN BIT(9)
+#define MSCC_MS_MISC_CONTROL_VALIDATE_FRAMES(x) ((x) << 10)
+#define MSCC_MS_MISC_CONTROL_VALIDATE_FRAMES_M GENMASK(11, 10)
+#define MSCC_MS_MISC_CONTROL_XFORM_REC_SIZE(x) ((x) << 24)
+#define MSCC_MS_MISC_CONTROL_XFORM_REC_SIZE_M GENMASK(25, 24)
+
+/* MACSEC_COUNT_CONTROL */
+#define MSCC_MS_COUNT_CONTROL_RESET_ALL BIT(0)
+#define MSCC_MS_COUNT_CONTROL_DEBUG_ACCESS BIT(1)
+#define MSCC_MS_COUNT_CONTROL_SATURATE_CNTRS BIT(2)
+#define MSCC_MS_COUNT_CONTROL_AUTO_CNTR_RESET BIT(3)
+
+/* MACSEC_PARAMS2_IG_CC_CONTROL */
+#define MSCC_MS_PARAMS2_IG_CC_CONTROL_NON_MATCH_CTRL_ACT BIT(14)
+#define MSCC_MS_PARAMS2_IG_CC_CONTROL_NON_MATCH_ACT BIT(15)
+
+/* MACSEC_PARAMS2_IG_CP_TAG */
+#define MSCC_MS_PARAMS2_IG_CP_TAG_MAP_TBL(x) (x)
+#define MSCC_MS_PARAMS2_IG_CP_TAG_MAP_TBL_M GENMASK(23, 0)
+#define MSCC_MS_PARAMS2_IG_CP_TAG_DEF_UP(x) ((x) << 24)
+#define MSCC_MS_PARAMS2_IG_CP_TAG_DEF_UP_M GENMASK(26, 24)
+#define MSCC_MS_PARAMS2_IG_CP_TAG_STAG_UP_EN BIT(27)
+#define MSCC_MS_PARAMS2_IG_CP_TAG_QTAG_UP_EN BIT(28)
+#define MSCC_MS_PARAMS2_IG_CP_TAG_PARSE_QINQ BIT(29)
+#define MSCC_MS_PARAMS2_IG_CP_TAG_PARSE_STAG BIT(30)
+#define MSCC_MS_PARAMS2_IG_CP_TAG_PARSE_QTAG BIT(31)
+
+/* MACSEC_VLAN_MTU_CHECK */
+#define MSCC_MS_VLAN_MTU_CHECK_MTU_COMPARE(x) (x)
+#define MSCC_MS_VLAN_MTU_CHECK_MTU_COMPARE_M GENMASK(14, 0)
+#define MSCC_MS_VLAN_MTU_CHECK_MTU_COMP_DROP BIT(15)
+
+/* MACSEC_NON_VLAN_MTU_CHECK */
+#define MSCC_MS_NON_VLAN_MTU_CHECK_NV_MTU_COMPARE(x) (x)
+#define MSCC_MS_NON_VLAN_MTU_CHECK_NV_MTU_COMPARE_M GENMASK(14, 0)
+#define MSCC_MS_NON_VLAN_MTU_CHECK_NV_MTU_COMP_DROP BIT(15)
+
+/* MACSEC_PP_CTRL */
+#define MSCC_MS_PP_CTRL_MACSEC_OCTET_INCR_MODE BIT(0)
+
+/* MACSEC_INTR_CTRL_STATUS */
+#define MSCC_MS_INTR_CTRL_STATUS_INTR_CLR_STATUS(x) (x)
+#define MSCC_MS_INTR_CTRL_STATUS_INTR_CLR_STATUS_M GENMASK(15, 0)
+#define MSCC_MS_INTR_CTRL_STATUS_INTR_ENABLE(x) ((x) << 16)
+#define MSCC_MS_INTR_CTRL_STATUS_INTR_ENABLE_M GENMASK(31, 16)
+#define MACSEC_INTR_CTRL_STATUS_ROLLOVER BIT(5)
+
+#endif
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 769a076..a4d2d59 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -387,7 +387,7 @@ int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum)
if (regnum > (u16)~0 || devad > 32)
return -EINVAL;
- if (phydev->drv->read_mmd) {
+ if (phydev->drv && phydev->drv->read_mmd) {
val = phydev->drv->read_mmd(phydev, devad, regnum);
} else if (phydev->is_c45) {
u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff);
@@ -444,7 +444,7 @@ int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val)
if (regnum > (u16)~0 || devad > 32)
return -EINVAL;
- if (phydev->drv->write_mmd) {
+ if (phydev->drv && phydev->drv->write_mmd) {
ret = phydev->drv->write_mmd(phydev, devad, regnum, val);
} else if (phydev->is_c45) {
u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 541ed01..d76e038 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -432,6 +432,31 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
}
EXPORT_SYMBOL(phy_mii_ioctl);
+/**
+ * phy_do_ioctl - generic ndo_do_ioctl implementation
+ * @dev: the net_device struct
+ * @ifr: &struct ifreq for socket ioctl's
+ * @cmd: ioctl cmd to execute
+ */
+int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+ if (!dev->phydev)
+ return -ENODEV;
+
+ return phy_mii_ioctl(dev->phydev, ifr, cmd);
+}
+EXPORT_SYMBOL(phy_do_ioctl);
+
+/* same as phy_do_ioctl, but ensures that net_device is running */
+int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+ if (!netif_running(dev))
+ return -ENODEV;
+
+ return phy_do_ioctl(dev, ifr, cmd);
+}
+EXPORT_SYMBOL(phy_do_ioctl_running);
+
void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies)
{
mod_delayed_work(system_power_efficient_wq, &phydev->state_queue,
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index e5dc9f8..6a5056e 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1107,9 +1107,8 @@ void phy_attached_info(struct phy_device *phydev)
EXPORT_SYMBOL(phy_attached_info);
#define ATTACHED_FMT "attached PHY driver [%s] (mii_bus:phy_addr=%s, irq=%s)"
-void phy_attached_print(struct phy_device *phydev, const char *fmt, ...)
+char *phy_attached_info_irq(struct phy_device *phydev)
{
- const char *drv_name = phydev->drv ? phydev->drv->name : "unbound";
char *irq_str;
char irq_num[8];
@@ -1126,6 +1125,14 @@ void phy_attached_print(struct phy_device *phydev, const char *fmt, ...)
break;
}
+ return kasprintf(GFP_KERNEL, "%s", irq_str);
+}
+EXPORT_SYMBOL(phy_attached_info_irq);
+
+void phy_attached_print(struct phy_device *phydev, const char *fmt, ...)
+{
+ const char *drv_name = phydev->drv ? phydev->drv->name : "unbound";
+ char *irq_str = phy_attached_info_irq(phydev);
if (!fmt) {
phydev_info(phydev, ATTACHED_FMT "\n",
@@ -1142,6 +1149,7 @@ void phy_attached_print(struct phy_device *phydev, const char *fmt, ...)
vprintk(fmt, ap);
va_end(ap);
}
+ kfree(irq_str);
}
EXPORT_SYMBOL(phy_attached_print);
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index ba9468c..70b9a14 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -186,8 +186,8 @@ static int phylink_parse_fixedlink(struct phylink *pl,
pl->link_config.pause |= MLO_PAUSE_ASYM;
if (ret == 0) {
- desc = fwnode_get_named_gpiod(fixed_node, "link-gpios",
- 0, GPIOD_IN, "?");
+ desc = fwnode_gpiod_get_index(fixed_node, "link", 0,
+ GPIOD_IN, "?");
if (!IS_ERR(desc))
pl->link_gpio = desc;
@@ -281,6 +281,7 @@ static int phylink_parse_mode(struct phylink *pl, struct fwnode_handle *fwnode)
switch (pl->link_config.interface) {
case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_QSGMII:
phylink_set(pl->supported, 10baseT_Half);
phylink_set(pl->supported, 10baseT_Full);
phylink_set(pl->supported, 100baseT_Half);
@@ -297,7 +298,9 @@ static int phylink_parse_mode(struct phylink *pl, struct fwnode_handle *fwnode)
phylink_set(pl->supported, 2500baseX_Full);
break;
+ case PHY_INTERFACE_MODE_USXGMII:
case PHY_INTERFACE_MODE_10GKR:
+ case PHY_INTERFACE_MODE_10GBASER:
phylink_set(pl->supported, 10baseT_Half);
phylink_set(pl->supported, 10baseT_Full);
phylink_set(pl->supported, 100baseT_Half);
@@ -305,6 +308,10 @@ static int phylink_parse_mode(struct phylink *pl, struct fwnode_handle *fwnode)
phylink_set(pl->supported, 1000baseT_Half);
phylink_set(pl->supported, 1000baseT_Full);
phylink_set(pl->supported, 1000baseX_Full);
+ phylink_set(pl->supported, 2500baseT_Full);
+ phylink_set(pl->supported, 2500baseX_Full);
+ phylink_set(pl->supported, 5000baseT_Full);
+ phylink_set(pl->supported, 10000baseT_Full);
phylink_set(pl->supported, 10000baseKR_Full);
phylink_set(pl->supported, 10000baseCR_Full);
phylink_set(pl->supported, 10000baseSR_Full);
@@ -570,6 +577,9 @@ static int phylink_register_sfp(struct phylink *pl,
struct sfp_bus *bus;
int ret;
+ if (!fwnode)
+ return 0;
+
bus = sfp_bus_find_fwnode(fwnode);
if (IS_ERR(bus)) {
ret = PTR_ERR(bus);
@@ -721,6 +731,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
{
struct phylink_link_state config;
__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
+ char *irq_str;
int ret;
/*
@@ -756,9 +767,11 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
phy->phylink = pl;
phy->phy_link_change = phylink_phy_change;
+ irq_str = phy_attached_info_irq(phy);
phylink_info(pl,
- "PHY [%s] driver [%s]\n", dev_name(&phy->mdio.dev),
- phy->drv->name);
+ "PHY [%s] driver [%s] (irq=%s)\n",
+ dev_name(&phy->mdio.dev), phy->drv->name, irq_str);
+ kfree(irq_str);
mutex_lock(&phy->lock);
mutex_lock(&pl->state_mutex);
@@ -1020,7 +1033,8 @@ void phylink_start(struct phylink *pl)
if (irq <= 0)
mod_timer(&pl->link_poll, jiffies + HZ);
}
- if (pl->cfg_link_an_mode == MLO_AN_FIXED && pl->get_fixed_state)
+ if ((pl->cfg_link_an_mode == MLO_AN_FIXED && pl->get_fixed_state) ||
+ pl->config->pcs_poll)
mod_timer(&pl->link_poll, jiffies + HZ);
if (pl->phydev)
phy_start(pl->phydev);
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 06e6429..d949ea7 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -373,7 +373,7 @@ phy_interface_t sfp_select_interface(struct sfp_bus *bus,
phylink_test(link_modes, 10000baseLRM_Full) ||
phylink_test(link_modes, 10000baseER_Full) ||
phylink_test(link_modes, 10000baseT_Full))
- return PHY_INTERFACE_MODE_10GKR;
+ return PHY_INTERFACE_MODE_10GBASER;
if (phylink_test(link_modes, 2500baseX_Full))
return PHY_INTERFACE_MODE_2500BASEX;
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index e1fabb3..acccb74 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -155,7 +155,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
opt->dst_addr.sin_addr.s_addr,
opt->src_addr.sin_addr.s_addr,
0, 0, IPPROTO_GRE,
- RT_TOS(0), 0);
+ RT_TOS(0), sk->sk_bound_dev_if);
if (IS_ERR(rt))
goto tx_error;
@@ -444,7 +444,8 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
opt->dst_addr.sin_addr.s_addr,
opt->src_addr.sin_addr.s_addr,
0, 0,
- IPPROTO_GRE, RT_CONN_FLAGS(sk), 0);
+ IPPROTO_GRE, RT_CONN_FLAGS(sk),
+ sk->sk_bound_dev_if);
if (IS_ERR(rt)) {
error = -EHOSTUNREACH;
goto end;
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 317d3a8..6f4d7ba 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -452,9 +452,16 @@ static void slip_transmit(struct work_struct *work)
*/
static void slip_write_wakeup(struct tty_struct *tty)
{
- struct slip *sl = tty->disc_data;
+ struct slip *sl;
+
+ rcu_read_lock();
+ sl = rcu_dereference(tty->disc_data);
+ if (!sl)
+ goto out;
schedule_work(&sl->tx_work);
+out:
+ rcu_read_unlock();
}
static void sl_tx_timeout(struct net_device *dev, unsigned int txqueue)
@@ -882,10 +889,11 @@ static void slip_close(struct tty_struct *tty)
return;
spin_lock_bh(&sl->lock);
- tty->disc_data = NULL;
+ rcu_assign_pointer(tty->disc_data, NULL);
sl->tty = NULL;
spin_unlock_bh(&sl->lock);
+ synchronize_rcu();
flush_work(&sl->tx_work);
/* VSV = very important to remove timers */
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index a6d63665..1f4bdd9 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -341,6 +341,7 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
features |= tap->tap_features;
if (netif_needs_gso(skb, features)) {
struct sk_buff *segs = __skb_gso_segment(skb, features, false);
+ struct sk_buff *next;
if (IS_ERR(segs))
goto drop;
@@ -352,16 +353,13 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
}
consume_skb(skb);
- while (segs) {
- struct sk_buff *nskb = segs->next;
-
- segs->next = NULL;
- if (ptr_ring_produce(&q->ring, segs)) {
- kfree_skb(segs);
- kfree_skb_list(nskb);
+ skb_list_walk_safe(segs, skb, next) {
+ skb_mark_not_on_list(skb);
+ if (ptr_ring_produce(&q->ring, skb)) {
+ kfree_skb(skb);
+ kfree_skb_list(next);
break;
}
- segs = nskb;
}
} else {
/* If we receive a partial checksum and the tap side
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 683d371..650c937 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1718,7 +1718,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
if (err < 0)
goto err_xdp;
if (err == XDP_REDIRECT)
- xdp_do_flush_map();
+ xdp_do_flush();
if (err != XDP_PASS)
goto out;
@@ -1936,6 +1936,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
if (ret != XDP_PASS) {
rcu_read_unlock();
local_bh_enable();
+ if (frags) {
+ tfile->napi.skb = NULL;
+ mutex_unlock(&tfile->napi_mutex);
+ }
return total_len;
}
}
@@ -2549,7 +2553,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
}
if (flush)
- xdp_do_flush_map();
+ xdp_do_flush();
rcu_read_unlock();
local_bh_enable();
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index af3994e..4e514f5 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -39,17 +39,6 @@ static int asix_mdio_bus_write(struct mii_bus *bus, int phy_id, int regnum,
return 0;
}
-static int ax88172a_ioctl(struct net_device *net, struct ifreq *rq, int cmd)
-{
- if (!netif_running(net))
- return -EINVAL;
-
- if (!net->phydev)
- return -ENODEV;
-
- return phy_mii_ioctl(net->phydev, rq, cmd);
-}
-
/* set MAC link settings according to information from phylib */
static void ax88172a_adjust_link(struct net_device *netdev)
{
@@ -134,7 +123,7 @@ static const struct net_device_ops ax88172a_netdev_ops = {
.ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = asix_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
- .ndo_do_ioctl = ax88172a_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_set_rx_mode = asix_set_multicast,
};
diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
index 9df3c1f..d7f3b70 100644
--- a/drivers/net/usb/ch9200.c
+++ b/drivers/net/usb/ch9200.c
@@ -111,8 +111,8 @@ static int control_read(struct usbnet *dev,
request_type = (USB_DIR_IN | USB_TYPE_VENDOR |
USB_RECIP_DEVICE);
- netdev_dbg(dev->net, "Control_read() index=0x%02x size=%d\n",
- index, size);
+ netdev_dbg(dev->net, "%s() index=0x%02x size=%d\n",
+ __func__, index, size);
buf = kmalloc(size, GFP_KERNEL);
if (!buf) {
@@ -130,8 +130,6 @@ static int control_read(struct usbnet *dev,
err = -EINVAL;
kfree(buf);
- return err;
-
err_out:
return err;
}
@@ -151,8 +149,8 @@ static int control_write(struct usbnet *dev, unsigned char request,
request_type = (USB_DIR_OUT | USB_TYPE_VENDOR |
USB_RECIP_DEVICE);
- netdev_dbg(dev->net, "Control_write() index=0x%02x size=%d\n",
- index, size);
+ netdev_dbg(dev->net, "%s() index=0x%02x size=%d\n",
+ __func__, index, size);
if (data) {
buf = kmemdup(data, size, GFP_KERNEL);
@@ -181,8 +179,8 @@ static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc)
struct usbnet *dev = netdev_priv(netdev);
unsigned char buff[2];
- netdev_dbg(netdev, "ch9200_mdio_read phy_id:%02x loc:%02x\n",
- phy_id, loc);
+ netdev_dbg(netdev, "%s phy_id:%02x loc:%02x\n",
+ __func__, phy_id, loc);
if (phy_id != 0)
return -ENODEV;
@@ -199,8 +197,8 @@ static void ch9200_mdio_write(struct net_device *netdev,
struct usbnet *dev = netdev_priv(netdev);
unsigned char buff[2];
- netdev_dbg(netdev, "ch9200_mdio_write() phy_id=%02x loc:%02x\n",
- phy_id, loc);
+ netdev_dbg(netdev, "%s() phy_id=%02x loc:%02x\n",
+ __func__, phy_id, loc);
if (phy_id != 0)
return;
@@ -219,8 +217,8 @@ static int ch9200_link_reset(struct usbnet *dev)
mii_check_media(&dev->mii, 1, 1);
mii_ethtool_gset(&dev->mii, &ecmd);
- netdev_dbg(dev->net, "link_reset() speed:%d duplex:%d\n",
- ecmd.speed, ecmd.duplex);
+ netdev_dbg(dev->net, "%s() speed:%d duplex:%d\n",
+ __func__, ecmd.speed, ecmd.duplex);
return 0;
}
@@ -309,7 +307,7 @@ static int get_mac_address(struct usbnet *dev, unsigned char *data)
unsigned char mac_addr[0x06];
int rd_mac_len = 0;
- netdev_dbg(dev->net, "get_mac_address:\n\tusbnet VID:%0x PID:%0x\n",
+ netdev_dbg(dev->net, "%s:\n\tusbnet VID:%0x PID:%0x\n", __func__,
le16_to_cpu(dev->udev->descriptor.idVendor),
le16_to_cpu(dev->udev->descriptor.idProduct));
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index f1a6349..eccbf4c 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -20,6 +20,7 @@
#include <linux/mdio.h>
#include <linux/phy.h>
#include <net/ip6_checksum.h>
+#include <net/vxlan.h>
#include <linux/interrupt.h>
#include <linux/irqdomain.h>
#include <linux/irq.h>
@@ -1663,14 +1664,6 @@ static const struct ethtool_ops lan78xx_ethtool_ops = {
.get_regs = lan78xx_get_regs,
};
-static int lan78xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
-{
- if (!netif_running(netdev))
- return -EINVAL;
-
- return phy_mii_ioctl(netdev->phydev, rq, cmd);
-}
-
static void lan78xx_init_mac_address(struct lan78xx_net *dev)
{
u32 addr_lo, addr_hi;
@@ -2724,11 +2717,6 @@ static int lan78xx_stop(struct net_device *net)
return 0;
}
-static int lan78xx_linearize(struct sk_buff *skb)
-{
- return skb_linearize(skb);
-}
-
static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev,
struct sk_buff *skb, gfp_t flags)
{
@@ -2740,8 +2728,10 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev,
return NULL;
}
- if (lan78xx_linearize(skb) < 0)
+ if (skb_linearize(skb)) {
+ dev_kfree_skb_any(skb);
return NULL;
+ }
tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN_MASK_) | TX_CMD_A_FCS_;
@@ -3671,6 +3661,19 @@ static void lan78xx_tx_timeout(struct net_device *net, unsigned int txqueue)
tasklet_schedule(&dev->bh);
}
+static netdev_features_t lan78xx_features_check(struct sk_buff *skb,
+ struct net_device *netdev,
+ netdev_features_t features)
+{
+ if (skb->len + TX_OVERHEAD > MAX_SINGLE_PACKET_SIZE)
+ features &= ~NETIF_F_GSO_MASK;
+
+ features = vlan_features_check(skb, features);
+ features = vxlan_features_check(skb, features);
+
+ return features;
+}
+
static const struct net_device_ops lan78xx_netdev_ops = {
.ndo_open = lan78xx_open,
.ndo_stop = lan78xx_stop,
@@ -3679,11 +3682,12 @@ static const struct net_device_ops lan78xx_netdev_ops = {
.ndo_change_mtu = lan78xx_change_mtu,
.ndo_set_mac_address = lan78xx_set_mac_addr,
.ndo_validate_addr = eth_validate_addr,
- .ndo_do_ioctl = lan78xx_ioctl,
+ .ndo_do_ioctl = phy_do_ioctl_running,
.ndo_set_rx_mode = lan78xx_set_multicast,
.ndo_set_features = lan78xx_set_features,
.ndo_vlan_rx_add_vid = lan78xx_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = lan78xx_vlan_rx_kill_vid,
+ .ndo_features_check = lan78xx_features_check,
};
static void lan78xx_stat_monitor(struct timer_list *t)
@@ -3753,6 +3757,7 @@ static int lan78xx_probe(struct usb_interface *intf,
/* MTU range: 68 - 9000 */
netdev->max_mtu = MAX_SINGLE_PACKET_SIZE;
+ netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER);
dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0;
dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1;
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 4196c0e..9485c8d 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1062,6 +1062,7 @@ static const struct usb_device_id products[] = {
{QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */
{QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */
{QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */
+ {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0800)}, /* Quectel RM500Q-GL */
/* 3. Combined interface devices matching on interface number */
{QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 9ec1da4..e8cd8c0 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -31,7 +31,7 @@
#define NETNEXT_VERSION "11"
/* Information for net */
-#define NET_VERSION "10"
+#define NET_VERSION "11"
#define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION
#define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -68,6 +68,7 @@
#define PLA_LED_FEATURE 0xdd92
#define PLA_PHYAR 0xde00
#define PLA_BOOT_CTRL 0xe004
+#define PLA_LWAKE_CTRL_REG 0xe007
#define PLA_GPHY_INTR_IMR 0xe022
#define PLA_EEE_CR 0xe040
#define PLA_EEEP_CR 0xe080
@@ -95,6 +96,7 @@
#define PLA_TALLYCNT 0xe890
#define PLA_SFF_STS_7 0xe8de
#define PLA_PHYSTATUS 0xe908
+#define PLA_CONFIG6 0xe90a /* CONFIG6 */
#define PLA_BP_BA 0xfc26
#define PLA_BP_0 0xfc28
#define PLA_BP_1 0xfc2a
@@ -107,6 +109,7 @@
#define PLA_BP_EN 0xfc38
#define USB_USB2PHY 0xb41e
+#define USB_SSPHYLINK1 0xb426
#define USB_SSPHYLINK2 0xb428
#define USB_U2P3_CTRL 0xb460
#define USB_CSR_DUMMY1 0xb464
@@ -300,6 +303,9 @@
#define LINK_ON_WAKE_EN 0x0010
#define LINK_OFF_WAKE_EN 0x0008
+/* PLA_CONFIG6 */
+#define LANWAKE_CLR_EN BIT(0)
+
/* PLA_CONFIG5 */
#define BWF_EN 0x0040
#define MWF_EN 0x0020
@@ -312,6 +318,7 @@
/* PLA_PHY_PWR */
#define TX_10M_IDLE_EN 0x0080
#define PFM_PWM_SWITCH 0x0040
+#define TEST_IO_OFF BIT(4)
/* PLA_MAC_PWR_CTRL */
#define D3_CLK_GATED_EN 0x00004000
@@ -324,6 +331,7 @@
#define MAC_CLK_SPDWN_EN BIT(15)
/* PLA_MAC_PWR_CTRL3 */
+#define PLA_MCU_SPDWN_EN BIT(14)
#define PKT_AVAIL_SPDWN_EN 0x0100
#define SUSPEND_SPDWN_EN 0x0004
#define U1U2_SPDWN_EN 0x0002
@@ -354,6 +362,9 @@
/* PLA_BOOT_CTRL */
#define AUTOLOAD_DONE 0x0002
+/* PLA_LWAKE_CTRL_REG */
+#define LANWAKE_PIN BIT(7)
+
/* PLA_SUSPEND_FLAG */
#define LINK_CHG_EVENT BIT(0)
@@ -365,13 +376,18 @@
#define DEBUG_LTSSM 0x0082
/* PLA_EXTRA_STATUS */
+#define CUR_LINK_OK BIT(15)
#define U3P3_CHECK_EN BIT(7) /* RTL_VER_05 only */
#define LINK_CHANGE_FLAG BIT(8)
+#define POLL_LINK_CHG BIT(0)
/* USB_USB2PHY */
#define USB2PHY_SUSPEND 0x0001
#define USB2PHY_L1 0x0002
+/* USB_SSPHYLINK1 */
+#define DELAY_PHY_PWR_CHG BIT(1)
+
/* USB_SSPHYLINK2 */
#define pwd_dn_scale_mask 0x3ffe
#define pwd_dn_scale(x) ((x) << 1)
@@ -1897,8 +1913,8 @@ static void r8152_csum_workaround(struct r8152 *tp, struct sk_buff *skb,
{
if (skb_shinfo(skb)->gso_size) {
netdev_features_t features = tp->netdev->features;
+ struct sk_buff *segs, *seg, *next;
struct sk_buff_head seg_list;
- struct sk_buff *segs, *nskb;
features &= ~(NETIF_F_SG | NETIF_F_IPV6_CSUM | NETIF_F_TSO6);
segs = skb_gso_segment(skb, features);
@@ -1907,12 +1923,10 @@ static void r8152_csum_workaround(struct r8152 *tp, struct sk_buff *skb,
__skb_queue_head_init(&seg_list);
- do {
- nskb = segs;
- segs = segs->next;
- nskb->next = NULL;
- __skb_queue_tail(&seg_list, nskb);
- } while (segs);
+ skb_list_walk_safe(segs, seg, next) {
+ skb_mark_not_on_list(seg);
+ __skb_queue_tail(&seg_list, seg);
+ }
skb_queue_splice(&seg_list, list);
dev_kfree_skb(skb);
@@ -2863,6 +2877,17 @@ static int rtl8153_enable(struct r8152 *tp)
r8153_set_rx_early_timeout(tp);
r8153_set_rx_early_size(tp);
+ if (tp->version == RTL_VER_09) {
+ u32 ocp_data;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_FW_TASK);
+ ocp_data &= ~FC_PATCH_TASK;
+ ocp_write_word(tp, MCU_TYPE_USB, USB_FW_TASK, ocp_data);
+ usleep_range(1000, 2000);
+ ocp_data |= FC_PATCH_TASK;
+ ocp_write_word(tp, MCU_TYPE_USB, USB_FW_TASK, ocp_data);
+ }
+
return rtl_enable(tp);
}
@@ -3376,8 +3401,8 @@ static void rtl8153b_runtime_enable(struct r8152 *tp, bool enable)
r8153b_ups_en(tp, false);
r8153_queue_wake(tp, false);
rtl_runtime_suspend_enable(tp, false);
- r8153_u2p3en(tp, true);
- r8153b_u1u2en(tp, true);
+ if (tp->udev->speed != USB_SPEED_HIGH)
+ r8153b_u1u2en(tp, true);
}
}
@@ -4675,7 +4700,6 @@ static void r8153b_hw_phy_cfg(struct r8152 *tp)
r8153_aldps_en(tp, true);
r8152b_enable_fc(tp);
- r8153_u2p3en(tp, true);
set_bit(PHY_RESET, &tp->flags);
}
@@ -4954,6 +4978,8 @@ static void rtl8152_down(struct r8152 *tp)
static void rtl8153_up(struct r8152 *tp)
{
+ u32 ocp_data;
+
if (test_bit(RTL8152_UNPLUG, &tp->flags))
return;
@@ -4961,6 +4987,19 @@ static void rtl8153_up(struct r8152 *tp)
r8153_u2p3en(tp, false);
r8153_aldps_en(tp, false);
r8153_first_init(tp);
+
+ ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);
+ ocp_data |= LANWAKE_CLR_EN;
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data);
+
+ ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG);
+ ocp_data &= ~LANWAKE_PIN;
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG, ocp_data);
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_SSPHYLINK1);
+ ocp_data &= ~DELAY_PHY_PWR_CHG;
+ ocp_write_word(tp, MCU_TYPE_USB, USB_SSPHYLINK1, ocp_data);
+
r8153_aldps_en(tp, true);
switch (tp->version) {
@@ -4979,11 +5018,17 @@ static void rtl8153_up(struct r8152 *tp)
static void rtl8153_down(struct r8152 *tp)
{
+ u32 ocp_data;
+
if (test_bit(RTL8152_UNPLUG, &tp->flags)) {
rtl_drop_queued_tx(tp);
return;
}
+ ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);
+ ocp_data &= ~LANWAKE_CLR_EN;
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data);
+
r8153_u1u2en(tp, false);
r8153_u2p3en(tp, false);
r8153_power_cut_en(tp, false);
@@ -4994,6 +5039,8 @@ static void rtl8153_down(struct r8152 *tp)
static void rtl8153b_up(struct r8152 *tp)
{
+ u32 ocp_data;
+
if (test_bit(RTL8152_UNPLUG, &tp->flags))
return;
@@ -5004,18 +5051,29 @@ static void rtl8153b_up(struct r8152 *tp)
r8153_first_init(tp);
ocp_write_dword(tp, MCU_TYPE_USB, USB_RX_BUF_TH, RX_THR_B);
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3);
+ ocp_data &= ~PLA_MCU_SPDWN_EN;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
+
r8153_aldps_en(tp, true);
- r8153_u2p3en(tp, true);
- r8153b_u1u2en(tp, true);
+
+ if (tp->udev->speed != USB_SPEED_HIGH)
+ r8153b_u1u2en(tp, true);
}
static void rtl8153b_down(struct r8152 *tp)
{
+ u32 ocp_data;
+
if (test_bit(RTL8152_UNPLUG, &tp->flags)) {
rtl_drop_queued_tx(tp);
return;
}
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3);
+ ocp_data |= PLA_MCU_SPDWN_EN;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
+
r8153b_u1u2en(tp, false);
r8153_u2p3en(tp, false);
r8153b_power_cut_en(tp, false);
@@ -5387,6 +5445,16 @@ static void r8153_init(struct r8152 *tp)
else
ocp_data |= DYNAMIC_BURST;
ocp_write_byte(tp, MCU_TYPE_USB, USB_CSR_DUMMY1, ocp_data);
+
+ r8153_queue_wake(tp, false);
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS);
+ if (rtl8152_get_speed(tp) & LINK_STATUS)
+ ocp_data |= CUR_LINK_OK;
+ else
+ ocp_data &= ~CUR_LINK_OK;
+ ocp_data |= POLL_LINK_CHG;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS, ocp_data);
}
ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_CSR_DUMMY2);
@@ -5416,10 +5484,19 @@ static void r8153_init(struct r8152 *tp)
ocp_write_word(tp, MCU_TYPE_USB, USB_CONNECT_TIMER, 0x0001);
r8153_power_cut_en(tp, false);
+ rtl_runtime_suspend_enable(tp, false);
r8153_u1u2en(tp, true);
r8153_mac_clk_spd(tp, false);
usb_enable_lpm(tp->udev);
+ ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);
+ ocp_data |= LANWAKE_CLR_EN;
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data);
+
+ ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG);
+ ocp_data &= ~LANWAKE_PIN;
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG, ocp_data);
+
/* rx aggregation */
ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_USB_CTRL);
ocp_data &= ~(RX_AGG_DISABLE | RX_ZERO_EN);
@@ -5484,7 +5561,17 @@ static void r8153b_init(struct r8152 *tp)
r8153b_ups_en(tp, false);
r8153_queue_wake(tp, false);
rtl_runtime_suspend_enable(tp, false);
- r8153b_u1u2en(tp, true);
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS);
+ if (rtl8152_get_speed(tp) & LINK_STATUS)
+ ocp_data |= CUR_LINK_OK;
+ else
+ ocp_data &= ~CUR_LINK_OK;
+ ocp_data |= POLL_LINK_CHG;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS, ocp_data);
+
+ if (tp->udev->speed != USB_SPEED_HIGH)
+ r8153b_u1u2en(tp, true);
usb_enable_lpm(tp->udev);
/* MAC clock speed down */
@@ -5492,6 +5579,19 @@ static void r8153b_init(struct r8152 *tp)
ocp_data |= MAC_CLK_SPDWN_EN;
ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, ocp_data);
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3);
+ ocp_data &= ~PLA_MCU_SPDWN_EN;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
+
+ if (tp->version == RTL_VER_09) {
+ /* Disable Test IO for 32QFN */
+ if (ocp_read_byte(tp, MCU_TYPE_PLA, 0xdc00) & BIT(5)) {
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_PHY_PWR);
+ ocp_data |= TEST_IO_OFF;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_PHY_PWR, ocp_data);
+ }
+ }
+
set_bit(GREEN_ETHERNET, &tp->flags);
/* rx aggregation */
@@ -6597,6 +6697,9 @@ static int rtl8152_probe(struct usb_interface *intf,
return -ENODEV;
}
+ if (intf->cur_altsetting->desc.bNumEndpoints < 3)
+ return -ENODEV;
+
usb_reset_device(udev);
netdev = alloc_etherdev(sizeof(struct r8152));
if (!netdev) {
@@ -6704,6 +6807,11 @@ static int rtl8152_probe(struct usb_interface *intf,
intf->needs_remote_wakeup = 1;
+ if (!rtl_can_wakeup(tp))
+ __rtl_set_wol(tp, 0);
+ else
+ tp->saved_wolopts = __rtl_get_wol(tp);
+
tp->rtl_ops.init(tp);
#if IS_BUILTIN(CONFIG_USB_RTL8152)
/* Retry in case request_firmware() is not ready yet. */
@@ -6721,10 +6829,6 @@ static int rtl8152_probe(struct usb_interface *intf,
goto out1;
}
- if (!rtl_can_wakeup(tp))
- __rtl_set_wol(tp, 0);
-
- tp->saved_wolopts = __rtl_get_wol(tp);
if (tp->saved_wolopts)
device_set_wakeup_enable(&udev->dev, true);
else
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index a552df3..1c89017 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -769,7 +769,7 @@ static int veth_poll(struct napi_struct *napi, int budget)
if (xdp_xmit & VETH_XDP_TX)
veth_xdp_flush(rq->dev, &bq);
if (xdp_xmit & VETH_XDP_REDIR)
- xdp_do_flush_map();
+ xdp_do_flush();
xdp_clear_return_frame_no_direct();
return done;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 4d7d5434..c458cd3 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1432,7 +1432,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
virtqueue_napi_complete(napi, rq->vq, received);
if (xdp_xmit & VIRTIO_XDP_REDIR)
- xdp_do_flush_map();
+ xdp_do_flush();
if (xdp_xmit & VIRTIO_XDP_TX) {
sq = virtnet_xdp_sq(vi);
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 0a38c76..1e4b9ba 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -555,10 +555,8 @@ vmxnet3_set_ringparam(struct net_device *netdev,
}
if (VMXNET3_VERSION_GE_3(adapter)) {
- if (param->rx_mini_pending < 0 ||
- param->rx_mini_pending > VMXNET3_RXDATA_DESC_MAX_SIZE) {
+ if (param->rx_mini_pending > VMXNET3_RXDATA_DESC_MAX_SIZE)
return -EINVAL;
- }
} else if (param->rx_mini_pending != 0) {
return -EINVAL;
}
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e95e658..d3b08b7 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2542,7 +2542,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
ndst = &rt->dst;
skb_tunnel_check_pmtu(skb, ndst, VXLAN_HEADROOM);
- tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+ tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr),
vni, md, flags, udp_sum);
@@ -2582,7 +2582,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
skb_tunnel_check_pmtu(skb, ndst, VXLAN6_HEADROOM);
- tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+ tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
ttl = ttl ? : ip6_dst_hoplimit(ndst);
skb_scrub_packet(skb, xnet);
err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index dd1a147..4530840 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -315,7 +315,8 @@
config IXP4XX_HSS
tristate "Intel IXP4xx HSS (synchronous serial port) support"
- depends on HDLC && ARM && ARCH_IXP4XX && IXP4XX_NPE && IXP4XX_QMGR
+ depends on HDLC && IXP4XX_NPE && IXP4XX_QMGR
+ depends on ARCH_IXP4XX
help
Say Y here if you want to use built-in HSS ports
on IXP4xx processor.
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index c28f840..3998cac 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -73,7 +73,7 @@ static struct ucc_tdm_info utdm_primary_info = {
},
};
-static struct ucc_tdm_info utdm_info[MAX_HDLC_NUM];
+static struct ucc_tdm_info utdm_info[UCC_MAX_NUM];
static int uhdlc_init(struct ucc_hdlc_private *priv)
{
diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c
index a030f5a..d8cba36 100644
--- a/drivers/net/wan/hdlc_cisco.c
+++ b/drivers/net/wan/hdlc_cisco.c
@@ -75,7 +75,7 @@ static int cisco_hard_header(struct sk_buff *skb, struct net_device *dev,
{
struct hdlc_header *data;
#ifdef DEBUG_HARD_HEADER
- printk(KERN_DEBUG "%s: cisco_hard_header called\n", dev->name);
+ netdev_dbg(dev, "%s called\n", __func__);
#endif
skb_push(skb, sizeof(struct hdlc_header));
@@ -101,7 +101,7 @@ static void cisco_keepalive_send(struct net_device *dev, u32 type,
skb = dev_alloc_skb(sizeof(struct hdlc_header) +
sizeof(struct cisco_packet));
if (!skb) {
- netdev_warn(dev, "Memory squeeze on cisco_keepalive_send()\n");
+ netdev_warn(dev, "Memory squeeze on %s()\n", __func__);
return;
}
skb_reserve(skb, 4);
diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c
index 5643675..c84536b 100644
--- a/drivers/net/wan/hdlc_x25.c
+++ b/drivers/net/wan/hdlc_x25.c
@@ -21,8 +21,17 @@
#include <linux/skbuff.h>
#include <net/x25device.h>
+struct x25_state {
+ x25_hdlc_proto settings;
+};
+
static int x25_ioctl(struct net_device *dev, struct ifreq *ifr);
+static struct x25_state *state(hdlc_device *hdlc)
+{
+ return hdlc->state;
+}
+
/* These functions are callbacks called by LAPB layer */
static void x25_connect_disconnect(struct net_device *dev, int reason, int code)
@@ -62,11 +71,12 @@ static int x25_data_indication(struct net_device *dev, struct sk_buff *skb)
{
unsigned char *ptr;
- skb_push(skb, 1);
-
if (skb_cow(skb, 1))
return NET_RX_DROP;
+ skb_push(skb, 1);
+ skb_reset_network_header(skb);
+
ptr = skb->data;
*ptr = X25_IFACE_DATA;
@@ -79,6 +89,13 @@ static int x25_data_indication(struct net_device *dev, struct sk_buff *skb)
static void x25_data_transmit(struct net_device *dev, struct sk_buff *skb)
{
hdlc_device *hdlc = dev_to_hdlc(dev);
+
+ skb_reset_network_header(skb);
+ skb->protocol = hdlc_type_trans(skb, dev);
+
+ if (dev_nit_active(dev))
+ dev_queue_xmit_nit(skb, dev);
+
hdlc->xmit(skb, dev); /* Ignore return value :-( */
}
@@ -93,6 +110,7 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
switch (skb->data[0]) {
case X25_IFACE_DATA: /* Data to be transmitted */
skb_pull(skb, 1);
+ skb_reset_network_header(skb);
if ((result = lapb_data_request(dev, skb)) != LAPB_OK)
dev_kfree_skb(skb);
return NETDEV_TX_OK;
@@ -131,7 +149,6 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
static int x25_open(struct net_device *dev)
{
- int result;
static const struct lapb_register_struct cb = {
.connect_confirmation = x25_connected,
.connect_indication = x25_connected,
@@ -140,10 +157,33 @@ static int x25_open(struct net_device *dev)
.data_indication = x25_data_indication,
.data_transmit = x25_data_transmit,
};
+ hdlc_device *hdlc = dev_to_hdlc(dev);
+ struct lapb_parms_struct params;
+ int result;
result = lapb_register(dev, &cb);
if (result != LAPB_OK)
return result;
+
+ result = lapb_getparms(dev, ¶ms);
+ if (result != LAPB_OK)
+ return result;
+
+ if (state(hdlc)->settings.dce)
+ params.mode = params.mode | LAPB_DCE;
+
+ if (state(hdlc)->settings.modulo == 128)
+ params.mode = params.mode | LAPB_EXTENDED;
+
+ params.window = state(hdlc)->settings.window;
+ params.t1 = state(hdlc)->settings.t1;
+ params.t2 = state(hdlc)->settings.t2;
+ params.n2 = state(hdlc)->settings.n2;
+
+ result = lapb_setparms(dev, ¶ms);
+ if (result != LAPB_OK)
+ return result;
+
return 0;
}
@@ -186,7 +226,10 @@ static struct hdlc_proto proto = {
static int x25_ioctl(struct net_device *dev, struct ifreq *ifr)
{
+ x25_hdlc_proto __user *x25_s = ifr->ifr_settings.ifs_ifsu.x25;
+ const size_t size = sizeof(x25_hdlc_proto);
hdlc_device *hdlc = dev_to_hdlc(dev);
+ x25_hdlc_proto new_settings;
int result;
switch (ifr->ifr_settings.type) {
@@ -194,7 +237,13 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr)
if (dev_to_hdlc(dev)->proto != &proto)
return -EINVAL;
ifr->ifr_settings.type = IF_PROTO_X25;
- return 0; /* return protocol only, no settable parameters */
+ if (ifr->ifr_settings.size < size) {
+ ifr->ifr_settings.size = size; /* data size wanted */
+ return -ENOBUFS;
+ }
+ if (copy_to_user(x25_s, &state(hdlc)->settings, size))
+ return -EFAULT;
+ return 0;
case IF_PROTO_X25:
if (!capable(CAP_NET_ADMIN))
@@ -203,12 +252,46 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr)
if (dev->flags & IFF_UP)
return -EBUSY;
+ /* backward compatibility */
+ if (ifr->ifr_settings.size == 0) {
+ new_settings.dce = 0;
+ new_settings.modulo = 8;
+ new_settings.window = 7;
+ new_settings.t1 = 3;
+ new_settings.t2 = 1;
+ new_settings.n2 = 10;
+ }
+ else {
+ if (copy_from_user(&new_settings, x25_s, size))
+ return -EFAULT;
+
+ if ((new_settings.dce != 0 &&
+ new_settings.dce != 1) ||
+ (new_settings.modulo != 8 &&
+ new_settings.modulo != 128) ||
+ new_settings.window < 1 ||
+ (new_settings.modulo == 8 &&
+ new_settings.window > 7) ||
+ (new_settings.modulo == 128 &&
+ new_settings.window > 127) ||
+ new_settings.t1 < 1 ||
+ new_settings.t1 > 255 ||
+ new_settings.t2 < 1 ||
+ new_settings.t2 > 255 ||
+ new_settings.n2 < 1 ||
+ new_settings.n2 > 255)
+ return -EINVAL;
+ }
+
result=hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT);
if (result)
return result;
- if ((result = attach_hdlc_protocol(dev, &proto, 0)))
+ if ((result = attach_hdlc_protocol(dev, &proto,
+ sizeof(struct x25_state))))
return result;
+
+ memcpy(&state(hdlc)->settings, &new_settings, size);
dev->type = ARPHRD_X25;
call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev);
netif_dormant_off(dev);
diff --git a/drivers/net/wan/ixp4xx_hss.c b/drivers/net/wan/ixp4xx_hss.c
index ea6ee6a..7c5cf77 100644
--- a/drivers/net/wan/ixp4xx_hss.c
+++ b/drivers/net/wan/ixp4xx_hss.c
@@ -17,6 +17,7 @@
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/platform_device.h>
+#include <linux/platform_data/wan_ixp4xx_hss.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/soc/ixp4xx/npe.h>
@@ -258,7 +259,7 @@ struct port {
struct hss_plat_info *plat;
buffer_t *rx_buff_tab[RX_DESCS], *tx_buff_tab[TX_DESCS];
struct desc *desc_tab; /* coherent */
- u32 desc_tab_phys;
+ dma_addr_t desc_tab_phys;
unsigned int id;
unsigned int clock_type, clock_rate, loopback;
unsigned int initialized, carrier;
@@ -858,7 +859,7 @@ static int hss_hdlc_xmit(struct sk_buff *skb, struct net_device *dev)
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
- memcpy_swab32(mem, (u32 *)((int)skb->data & ~3), bytes / 4);
+ memcpy_swab32(mem, (u32 *)((uintptr_t)skb->data & ~3), bytes / 4);
dev_kfree_skb(skb);
#endif
@@ -1182,14 +1183,14 @@ static int hss_hdlc_attach(struct net_device *dev, unsigned short encoding,
}
}
-static u32 check_clock(u32 rate, u32 a, u32 b, u32 c,
+static u32 check_clock(u32 timer_freq, u32 rate, u32 a, u32 b, u32 c,
u32 *best, u32 *best_diff, u32 *reg)
{
/* a is 10-bit, b is 10-bit, c is 12-bit */
u64 new_rate;
u32 new_diff;
- new_rate = ixp4xx_timer_freq * (u64)(c + 1);
+ new_rate = timer_freq * (u64)(c + 1);
do_div(new_rate, a * (c + 1) + b + 1);
new_diff = abs((u32)new_rate - rate);
@@ -1201,40 +1202,43 @@ static u32 check_clock(u32 rate, u32 a, u32 b, u32 c,
return new_diff;
}
-static void find_best_clock(u32 rate, u32 *best, u32 *reg)
+static void find_best_clock(u32 timer_freq, u32 rate, u32 *best, u32 *reg)
{
u32 a, b, diff = 0xFFFFFFFF;
- a = ixp4xx_timer_freq / rate;
+ a = timer_freq / rate;
if (a > 0x3FF) { /* 10-bit value - we can go as slow as ca. 65 kb/s */
- check_clock(rate, 0x3FF, 1, 1, best, &diff, reg);
+ check_clock(timer_freq, rate, 0x3FF, 1, 1, best, &diff, reg);
return;
}
if (a == 0) { /* > 66.666 MHz */
a = 1; /* minimum divider is 1 (a = 0, b = 1, c = 1) */
- rate = ixp4xx_timer_freq;
+ rate = timer_freq;
}
- if (rate * a == ixp4xx_timer_freq) { /* don't divide by 0 later */
- check_clock(rate, a - 1, 1, 1, best, &diff, reg);
+ if (rate * a == timer_freq) { /* don't divide by 0 later */
+ check_clock(timer_freq, rate, a - 1, 1, 1, best, &diff, reg);
return;
}
for (b = 0; b < 0x400; b++) {
u64 c = (b + 1) * (u64)rate;
- do_div(c, ixp4xx_timer_freq - rate * a);
+ do_div(c, timer_freq - rate * a);
c--;
if (c >= 0xFFF) { /* 12-bit - no need to check more 'b's */
if (b == 0 && /* also try a bit higher rate */
- !check_clock(rate, a - 1, 1, 1, best, &diff, reg))
+ !check_clock(timer_freq, rate, a - 1, 1, 1, best,
+ &diff, reg))
return;
- check_clock(rate, a, b, 0xFFF, best, &diff, reg);
+ check_clock(timer_freq, rate, a, b, 0xFFF, best,
+ &diff, reg);
return;
}
- if (!check_clock(rate, a, b, c, best, &diff, reg))
+ if (!check_clock(timer_freq, rate, a, b, c, best, &diff, reg))
return;
- if (!check_clock(rate, a, b, c + 1, best, &diff, reg))
+ if (!check_clock(timer_freq, rate, a, b, c + 1, best, &diff,
+ reg))
return;
}
}
@@ -1285,8 +1289,9 @@ static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
port->clock_type = clk; /* Update settings */
if (clk == CLOCK_INT)
- find_best_clock(new_line.clock_rate, &port->clock_rate,
- &port->clock_reg);
+ find_best_clock(port->plat->timer_freq,
+ new_line.clock_rate,
+ &port->clock_rate, &port->clock_reg);
else {
port->clock_rate = 0;
port->clock_reg = CLK42X_SPEED_2048KHZ;
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 0f1217b..e30d91a 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -64,7 +64,7 @@ static struct lapbethdev *lapbeth_get_x25_dev(struct net_device *dev)
{
struct lapbethdev *lapbeth;
- list_for_each_entry_rcu(lapbeth, &lapbeth_devices, node) {
+ list_for_each_entry_rcu(lapbeth, &lapbeth_devices, node, lockdep_rtnl_is_held()) {
if (lapbeth->ethdev == dev)
return lapbeth;
}
diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c
index e2e679a..77ccf36 100644
--- a/drivers/net/wan/sdla.c
+++ b/drivers/net/wan/sdla.c
@@ -708,7 +708,7 @@ static netdev_tx_t sdla_transmit(struct sk_buff *skb,
spin_lock_irqsave(&sdla_lock, flags);
SDLA_WINDOW(dev, addr);
- pbuf = (void *)(((int) dev->mem_start) + (addr & SDLA_ADDR_MASK));
+ pbuf = (void *)(dev->mem_start + (addr & SDLA_ADDR_MASK));
__sdla_write(dev, pbuf->buf_addr, skb->data, skb->len);
SDLA_WINDOW(dev, addr);
pbuf->opp_flag = 1;
diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h
index c91f305..b15a8be 100644
--- a/drivers/net/wireguard/device.h
+++ b/drivers/net/wireguard/device.h
@@ -62,12 +62,4 @@ struct wg_device {
int wg_device_init(void);
void wg_device_uninit(void);
-/* Later after the dust settles, this can be moved into include/linux/skbuff.h,
- * where virtually all code that deals with GSO segs can benefit, around ~30
- * drivers as of writing.
- */
-#define skb_list_walk_safe(first, skb, next) \
- for (skb = first, next = skb->next; skb; \
- skb = next, next = skb ? skb->next : NULL)
-
#endif /* _WG_DEVICE_H */
diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h
index e49a464..fecb559 100644
--- a/drivers/net/wireguard/queueing.h
+++ b/drivers/net/wireguard/queueing.h
@@ -83,13 +83,10 @@ static inline __be16 wg_skb_examine_untrusted_ip_hdr(struct sk_buff *skb)
static inline void wg_reset_packet(struct sk_buff *skb)
{
- const int pfmemalloc = skb->pfmemalloc;
-
skb_scrub_packet(skb, true);
memset(&skb->headers_start, 0,
offsetof(struct sk_buff, headers_end) -
offsetof(struct sk_buff, headers_start));
- skb->pfmemalloc = pfmemalloc;
skb->queue_mapping = 0;
skb->nohdr = 0;
skb->peeked = 0;
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index c46256d..262f3b5 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -333,6 +333,7 @@ static int wg_receive(struct sock *sk, struct sk_buff *skb)
wg = sk->sk_user_data;
if (unlikely(!wg))
goto err;
+ skb_mark_not_on_list(skb);
wg_packet_receive(wg, skb);
return 0;
diff --git a/drivers/net/wireless/ath/wil6210/ethtool.c b/drivers/net/wireless/ath/wil6210/ethtool.c
index 912c4ea..fef1088 100644
--- a/drivers/net/wireless/ath/wil6210/ethtool.c
+++ b/drivers/net/wireless/ath/wil6210/ethtool.c
@@ -11,26 +11,6 @@
#include "wil6210.h"
-static int wil_ethtoolops_begin(struct net_device *ndev)
-{
- struct wil6210_priv *wil = ndev_to_wil(ndev);
-
- mutex_lock(&wil->mutex);
-
- wil_dbg_misc(wil, "ethtoolops_begin\n");
-
- return 0;
-}
-
-static void wil_ethtoolops_complete(struct net_device *ndev)
-{
- struct wil6210_priv *wil = ndev_to_wil(ndev);
-
- wil_dbg_misc(wil, "ethtoolops_complete\n");
-
- mutex_unlock(&wil->mutex);
-}
-
static int wil_ethtoolops_get_coalesce(struct net_device *ndev,
struct ethtool_coalesce *cp)
{
@@ -39,11 +19,12 @@ static int wil_ethtoolops_get_coalesce(struct net_device *ndev,
u32 rx_itr_en, rx_itr_val = 0;
int ret;
+ mutex_lock(&wil->mutex);
wil_dbg_misc(wil, "ethtoolops_get_coalesce\n");
ret = wil_pm_runtime_get(wil);
if (ret < 0)
- return ret;
+ goto out;
tx_itr_en = wil_r(wil, RGF_DMA_ITR_TX_CNT_CTL);
if (tx_itr_en & BIT_DMA_ITR_TX_CNT_CTL_EN)
@@ -57,7 +38,11 @@ static int wil_ethtoolops_get_coalesce(struct net_device *ndev,
cp->tx_coalesce_usecs = tx_itr_val;
cp->rx_coalesce_usecs = rx_itr_val;
- return 0;
+ ret = 0;
+
+out:
+ mutex_unlock(&wil->mutex);
+ return ret;
}
static int wil_ethtoolops_set_coalesce(struct net_device *ndev,
@@ -67,12 +52,14 @@ static int wil_ethtoolops_set_coalesce(struct net_device *ndev,
struct wireless_dev *wdev = ndev->ieee80211_ptr;
int ret;
+ mutex_lock(&wil->mutex);
wil_dbg_misc(wil, "ethtoolops_set_coalesce: rx %d usec, tx %d usec\n",
cp->rx_coalesce_usecs, cp->tx_coalesce_usecs);
if (wdev->iftype == NL80211_IFTYPE_MONITOR) {
wil_dbg_misc(wil, "No IRQ coalescing in monitor mode\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
/* only @rx_coalesce_usecs and @tx_coalesce_usecs supported,
@@ -88,24 +75,26 @@ static int wil_ethtoolops_set_coalesce(struct net_device *ndev,
ret = wil_pm_runtime_get(wil);
if (ret < 0)
- return ret;
+ goto out;
wil->txrx_ops.configure_interrupt_moderation(wil);
wil_pm_runtime_put(wil);
+ ret = 0;
- return 0;
+out:
+ mutex_unlock(&wil->mutex);
+ return ret;
out_bad:
wil_dbg_misc(wil, "Unsupported coalescing params. Raw command:\n");
print_hex_dump_debug("DBG[MISC] coal ", DUMP_PREFIX_OFFSET, 16, 4,
cp, sizeof(*cp), false);
+ mutex_unlock(&wil->mutex);
return -EINVAL;
}
static const struct ethtool_ops wil_ethtool_ops = {
- .begin = wil_ethtoolops_begin,
- .complete = wil_ethtoolops_complete,
.get_drvinfo = cfg80211_get_drvinfo,
.get_coalesce = wil_ethtoolops_get_coalesce,
.set_coalesce = wil_ethtoolops_set_coalesce,
diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index f43c065..c4c8f1b 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -7790,16 +7790,8 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) {
case AIROGVLIST: ridcode = RID_APLIST; break;
case AIROGDRVNAM: ridcode = RID_DRVNAME; break;
case AIROGEHTENC: ridcode = RID_ETHERENCAP; break;
- case AIROGWEPKTMP: ridcode = RID_WEP_TEMP;
- /* Only super-user can read WEP keys */
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- break;
- case AIROGWEPKNV: ridcode = RID_WEP_PERM;
- /* Only super-user can read WEP keys */
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- break;
+ case AIROGWEPKTMP: ridcode = RID_WEP_TEMP; break;
+ case AIROGWEPKNV: ridcode = RID_WEP_PERM; break;
case AIROGSTAT: ridcode = RID_STATUS; break;
case AIROGSTATSD32: ridcode = RID_STATSDELTA; break;
case AIROGSTATSC32: ridcode = RID_STATS; break;
@@ -7813,7 +7805,13 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) {
return -EINVAL;
}
- if ((iobuf = kmalloc(RIDSIZE, GFP_KERNEL)) == NULL)
+ if (ridcode == RID_WEP_TEMP || ridcode == RID_WEP_PERM) {
+ /* Only super-user can read WEP keys */
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ }
+
+ if ((iobuf = kzalloc(RIDSIZE, GFP_KERNEL)) == NULL)
return -ENOMEM;
PC4500_readrid(ai,ridcode,iobuf,RIDSIZE, 1);
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/tx.c b/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
index cd73fc5c..fd45483 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
@@ -267,7 +267,7 @@ int iwlagn_tx_skb(struct iwl_priv *priv,
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
struct iwl_station_priv *sta_priv = NULL;
struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS];
- struct iwl_device_cmd *dev_cmd;
+ struct iwl_device_tx_cmd *dev_cmd;
struct iwl_tx_cmd *tx_cmd;
__le16 fc;
u8 hdr_len;
@@ -348,7 +348,6 @@ int iwlagn_tx_skb(struct iwl_priv *priv,
if (unlikely(!dev_cmd))
goto drop_unlock_priv;
- memset(dev_cmd, 0, sizeof(*dev_cmd));
dev_cmd->hdr.cmd = REPLY_TX;
tx_cmd = (struct iwl_tx_cmd *) dev_cmd->payload;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index 40fe2d6..48d375a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -357,8 +357,8 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
{
union acpi_object *wifi_pkg, *data;
bool enabled;
- int i, n_profiles, tbl_rev;
- int ret = 0;
+ int i, n_profiles, tbl_rev, pos;
+ int ret = 0;
data = iwl_acpi_get_object(fwrt->dev, ACPI_EWRD_METHOD);
if (IS_ERR(data))
@@ -390,10 +390,10 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
goto out_free;
}
- for (i = 0; i < n_profiles; i++) {
- /* the tables start at element 3 */
- int pos = 3;
+ /* the tables start at element 3 */
+ pos = 3;
+ for (i = 0; i < n_profiles; i++) {
/* The EWRD profiles officially go from 2 to 4, but we
* save them in sar_profiles[1-3] (because we don't
* have profile 0). So in the array we start from 1.
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index ed90dd1..4c60f99 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -2669,12 +2669,7 @@ int iwl_fw_dbg_stop_restart_recording(struct iwl_fw_runtime *fwrt,
{
int ret = 0;
- /* if the FW crashed or not debug monitor cfg was given, there is
- * no point in changing the recording state
- */
- if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status) ||
- (!fwrt->trans->dbg.dest_tlv &&
- fwrt->trans->dbg.ini_dest == IWL_FW_INI_LOCATION_INVALID))
+ if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status))
return 0;
if (fw_has_capa(&fwrt->fw->ucode_capa,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index 92d9898..c2f7252 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -379,7 +379,7 @@ enum {
/* CSR GIO */
-#define CSR_GIO_REG_VAL_L0S_ENABLED (0x00000002)
+#define CSR_GIO_REG_VAL_L0S_DISABLED (0x00000002)
/*
* UCODE-DRIVER GP (general purpose) mailbox register 1
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index f266647..ce8f248 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -480,7 +480,14 @@ static int iwl_dbg_tlv_alloc_fragment(struct iwl_fw_runtime *fwrt,
if (!frag || frag->size || !pages)
return -EIO;
- while (pages) {
+ /*
+ * We try to allocate as many pages as we can, starting with
+ * the requested amount and going down until we can allocate
+ * something. Because of DIV_ROUND_UP(), pages will never go
+ * down to 0 and stop the loop, so stop when pages reaches 1,
+ * which is too small anyway.
+ */
+ while (pages > 1) {
block = dma_alloc_coherent(fwrt->dev, pages * PAGE_SIZE,
&physical,
GFP_KERNEL | __GFP_NOWARN);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 4096ccf..bc8c959 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1817,9 +1817,6 @@ MODULE_PARM_DESC(antenna_coupling,
module_param_named(nvm_file, iwlwifi_mod_params.nvm_file, charp, 0444);
MODULE_PARM_DESC(nvm_file, "NVM file name");
-module_param_named(lar_disable, iwlwifi_mod_params.lar_disable, bool, 0444);
-MODULE_PARM_DESC(lar_disable, "disable LAR functionality (default: N)");
-
module_param_named(uapsd_disable, iwlwifi_mod_params.uapsd_disable, uint, 0644);
MODULE_PARM_DESC(uapsd_disable,
"disable U-APSD functionality bitmap 1: BSS 2: P2P Client (default: 3)");
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
index ebea3f3..82e5cac 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
@@ -115,7 +115,6 @@ enum iwl_uapsd_disable {
* @nvm_file: specifies a external NVM file
* @uapsd_disable: disable U-APSD, see &enum iwl_uapsd_disable, default =
* IWL_DISABLE_UAPSD_BSS | IWL_DISABLE_UAPSD_P2P_CLIENT
- * @lar_disable: disable LAR (regulatory), default = 0
* @fw_monitor: allow to use firmware monitor
* @disable_11ac: disable VHT capabilities, default = false.
* @remove_when_gone: remove an inaccessible device from the PCIe bus.
@@ -136,7 +135,6 @@ struct iwl_mod_params {
int antenna_coupling;
char *nvm_file;
u32 uapsd_disable;
- bool lar_disable;
bool fw_monitor;
bool disable_11ac;
/**
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 1e240a2..d4f834b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -224,6 +224,34 @@ enum iwl_nvm_channel_flags {
NVM_CHANNEL_DC_HIGH = BIT(12),
};
+/**
+ * enum iwl_reg_capa_flags - global flags applied for the whole regulatory
+ * domain.
+ * @REG_CAPA_BF_CCD_LOW_BAND: Beam-forming or Cyclic Delay Diversity in the
+ * 2.4Ghz band is allowed.
+ * @REG_CAPA_BF_CCD_HIGH_BAND: Beam-forming or Cyclic Delay Diversity in the
+ * 5Ghz band is allowed.
+ * @REG_CAPA_160MHZ_ALLOWED: 11ac channel with a width of 160Mhz is allowed
+ * for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_80MHZ_ALLOWED: 11ac channel with a width of 80Mhz is allowed
+ * for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_MCS_8_ALLOWED: 11ac with MCS 8 is allowed.
+ * @REG_CAPA_MCS_9_ALLOWED: 11ac with MCS 9 is allowed.
+ * @REG_CAPA_40MHZ_FORBIDDEN: 11n channel with a width of 40Mhz is forbidden
+ * for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_DC_HIGH_ENABLED: DC HIGH allowed.
+ */
+enum iwl_reg_capa_flags {
+ REG_CAPA_BF_CCD_LOW_BAND = BIT(0),
+ REG_CAPA_BF_CCD_HIGH_BAND = BIT(1),
+ REG_CAPA_160MHZ_ALLOWED = BIT(2),
+ REG_CAPA_80MHZ_ALLOWED = BIT(3),
+ REG_CAPA_MCS_8_ALLOWED = BIT(4),
+ REG_CAPA_MCS_9_ALLOWED = BIT(5),
+ REG_CAPA_40MHZ_FORBIDDEN = BIT(7),
+ REG_CAPA_DC_HIGH_ENABLED = BIT(9),
+};
+
static inline void iwl_nvm_print_channel_flags(struct device *dev, u32 level,
int chan, u32 flags)
{
@@ -939,10 +967,11 @@ iwl_nvm_no_wide_in_5ghz(struct iwl_trans *trans, const struct iwl_cfg *cfg,
struct iwl_nvm_data *
iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+ const struct iwl_fw *fw,
const __be16 *nvm_hw, const __le16 *nvm_sw,
const __le16 *nvm_calib, const __le16 *regulatory,
const __le16 *mac_override, const __le16 *phy_sku,
- u8 tx_chains, u8 rx_chains, bool lar_fw_supported)
+ u8 tx_chains, u8 rx_chains)
{
struct iwl_nvm_data *data;
bool lar_enabled;
@@ -1022,7 +1051,8 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
return NULL;
}
- if (lar_fw_supported && lar_enabled)
+ if (lar_enabled &&
+ fw_has_capa(&fw->ucode_capa, IWL_UCODE_TLV_CAPA_LAR_SUPPORT))
sbands_flags |= IWL_NVM_SBANDS_FLAGS_LAR;
if (iwl_nvm_no_wide_in_5ghz(trans, cfg, nvm_hw))
@@ -1038,6 +1068,7 @@ IWL_EXPORT_SYMBOL(iwl_parse_nvm_data);
static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
int ch_idx, u16 nvm_flags,
+ u16 cap_flags,
const struct iwl_cfg *cfg)
{
u32 flags = NL80211_RRF_NO_HT40;
@@ -1076,13 +1107,27 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
(flags & NL80211_RRF_NO_IR))
flags |= NL80211_RRF_GO_CONCURRENT;
+ /*
+ * cap_flags is per regulatory domain so apply it for every channel
+ */
+ if (ch_idx >= NUM_2GHZ_CHANNELS) {
+ if (cap_flags & REG_CAPA_40MHZ_FORBIDDEN)
+ flags |= NL80211_RRF_NO_HT40;
+
+ if (!(cap_flags & REG_CAPA_80MHZ_ALLOWED))
+ flags |= NL80211_RRF_NO_80MHZ;
+
+ if (!(cap_flags & REG_CAPA_160MHZ_ALLOWED))
+ flags |= NL80211_RRF_NO_160MHZ;
+ }
+
return flags;
}
struct ieee80211_regdomain *
iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
int num_of_ch, __le32 *channels, u16 fw_mcc,
- u16 geo_info)
+ u16 geo_info, u16 cap)
{
int ch_idx;
u16 ch_flags;
@@ -1140,7 +1185,8 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
}
reg_rule_flags = iwl_nvm_get_regdom_bw_flags(nvm_chan, ch_idx,
- ch_flags, cfg);
+ ch_flags, cap,
+ cfg);
/* we can't continue the same rule */
if (ch_idx == 0 || prev_reg_rule_flags != reg_rule_flags ||
@@ -1405,9 +1451,6 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans,
.id = WIDE_ID(REGULATORY_AND_NVM_GROUP, NVM_GET_INFO)
};
int ret;
- bool lar_fw_supported = !iwlwifi_mod_params.lar_disable &&
- fw_has_capa(&fw->ucode_capa,
- IWL_UCODE_TLV_CAPA_LAR_SUPPORT);
bool empty_otp;
u32 mac_flags;
u32 sbands_flags = 0;
@@ -1485,7 +1528,9 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans,
nvm->valid_tx_ant = (u8)le32_to_cpu(rsp->phy_sku.tx_chains);
nvm->valid_rx_ant = (u8)le32_to_cpu(rsp->phy_sku.rx_chains);
- if (le32_to_cpu(rsp->regulatory.lar_enabled) && lar_fw_supported) {
+ if (le32_to_cpu(rsp->regulatory.lar_enabled) &&
+ fw_has_capa(&fw->ucode_capa,
+ IWL_UCODE_TLV_CAPA_LAR_SUPPORT)) {
nvm->lar_enabled = true;
sbands_flags |= IWL_NVM_SBANDS_FLAGS_LAR;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index b7e1ddf..fb0b385 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -7,7 +7,7 @@
*
* Copyright(c) 2008 - 2015 Intel Corporation. All rights reserved.
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
@@ -29,7 +29,7 @@
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -85,10 +85,11 @@ enum iwl_nvm_sbands_flags {
*/
struct iwl_nvm_data *
iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+ const struct iwl_fw *fw,
const __be16 *nvm_hw, const __le16 *nvm_sw,
const __le16 *nvm_calib, const __le16 *regulatory,
const __le16 *mac_override, const __le16 *phy_sku,
- u8 tx_chains, u8 rx_chains, bool lar_fw_supported);
+ u8 tx_chains, u8 rx_chains);
/**
* iwl_parse_mcc_info - parse MCC (mobile country code) info coming from FW
@@ -103,7 +104,7 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
struct ieee80211_regdomain *
iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
int num_of_ch, __le32 *channels, u16 fw_mcc,
- u16 geo_info);
+ u16 geo_info, u16 cap);
/**
* struct iwl_nvm_section - describes an NVM section in memory.
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index 28bdc9a..f91197e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -66,7 +66,9 @@
struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
struct device *dev,
- const struct iwl_trans_ops *ops)
+ const struct iwl_trans_ops *ops,
+ unsigned int cmd_pool_size,
+ unsigned int cmd_pool_align)
{
struct iwl_trans *trans;
#ifdef CONFIG_LOCKDEP
@@ -90,10 +92,8 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
"iwl_cmd_pool:%s", dev_name(trans->dev));
trans->dev_cmd_pool =
kmem_cache_create(trans->dev_cmd_pool_name,
- sizeof(struct iwl_device_cmd),
- sizeof(void *),
- SLAB_HWCACHE_ALIGN,
- NULL);
+ cmd_pool_size, cmd_pool_align,
+ SLAB_HWCACHE_ALIGN, NULL);
if (!trans->dev_cmd_pool)
return NULL;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 8cadad7..e33df5a 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -193,6 +193,18 @@ struct iwl_device_cmd {
};
} __packed;
+/**
+ * struct iwl_device_tx_cmd - buffer for TX command
+ * @hdr: the header
+ * @payload: the payload placeholder
+ *
+ * The actual structure is sized dynamically according to need.
+ */
+struct iwl_device_tx_cmd {
+ struct iwl_cmd_header hdr;
+ u8 payload[];
+} __packed;
+
#define TFD_MAX_PAYLOAD_SIZE (sizeof(struct iwl_device_cmd))
/*
@@ -544,7 +556,7 @@ struct iwl_trans_ops {
int (*send_cmd)(struct iwl_trans *trans, struct iwl_host_cmd *cmd);
int (*tx)(struct iwl_trans *trans, struct sk_buff *skb,
- struct iwl_device_cmd *dev_cmd, int queue);
+ struct iwl_device_tx_cmd *dev_cmd, int queue);
void (*reclaim)(struct iwl_trans *trans, int queue, int ssn,
struct sk_buff_head *skbs);
@@ -948,22 +960,22 @@ iwl_trans_dump_data(struct iwl_trans *trans, u32 dump_mask)
return trans->ops->dump_data(trans, dump_mask);
}
-static inline struct iwl_device_cmd *
+static inline struct iwl_device_tx_cmd *
iwl_trans_alloc_tx_cmd(struct iwl_trans *trans)
{
- return kmem_cache_alloc(trans->dev_cmd_pool, GFP_ATOMIC);
+ return kmem_cache_zalloc(trans->dev_cmd_pool, GFP_ATOMIC);
}
int iwl_trans_send_cmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd);
static inline void iwl_trans_free_tx_cmd(struct iwl_trans *trans,
- struct iwl_device_cmd *dev_cmd)
+ struct iwl_device_tx_cmd *dev_cmd)
{
kmem_cache_free(trans->dev_cmd_pool, dev_cmd);
}
static inline int iwl_trans_tx(struct iwl_trans *trans, struct sk_buff *skb,
- struct iwl_device_cmd *dev_cmd, int queue)
+ struct iwl_device_tx_cmd *dev_cmd, int queue)
{
if (unlikely(test_bit(STATUS_FW_ERROR, &trans->status)))
return -EIO;
@@ -1271,7 +1283,9 @@ static inline bool iwl_trans_dbg_ini_valid(struct iwl_trans *trans)
*****************************************************/
struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
struct device *dev,
- const struct iwl_trans_ops *ops);
+ const struct iwl_trans_ops *ops,
+ unsigned int cmd_pool_size,
+ unsigned int cmd_pool_align);
void iwl_trans_free(struct iwl_trans *trans);
/*****************************************************
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
index 60aff2e..58df25e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
@@ -154,5 +154,6 @@
#define IWL_MVM_D3_DEBUG false
#define IWL_MVM_USE_TWT false
#define IWL_MVM_AMPDU_CONSEC_DROPS_DELBA 10
+#define IWL_MVM_USE_NSSN_SYNC 0
#endif /* __MVM_CONSTANTS_H */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index dd685f7..c09624d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -841,9 +841,13 @@ int iwl_mvm_ppag_send_cmd(struct iwl_mvm *mvm)
return 0;
}
+ if (!mvm->fwrt.ppag_table.enabled) {
+ IWL_DEBUG_RADIO(mvm,
+ "PPAG not enabled, command not sent.\n");
+ return 0;
+ }
+
IWL_DEBUG_RADIO(mvm, "Sending PER_PLATFORM_ANT_GAIN_CMD\n");
- IWL_DEBUG_RADIO(mvm, "PPAG is %s\n",
- mvm->fwrt.ppag_table.enabled ? "enabled" : "disabled");
for (i = 0; i < ACPI_PPAG_NUM_CHAINS; i++) {
for (j = 0; j < ACPI_PPAG_NUM_SUB_BANDS; j++) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 32dc9d6..6717f25 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -256,7 +256,8 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy,
__le32_to_cpu(resp->n_channels),
resp->channels,
__le16_to_cpu(resp->mcc),
- __le16_to_cpu(resp->geo_info));
+ __le16_to_cpu(resp->geo_info),
+ __le16_to_cpu(resp->cap));
/* Store the return source id */
src_id = resp->source_id;
kfree(resp);
@@ -754,6 +755,20 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
return ret;
}
+static void iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
+ struct ieee80211_sta *sta)
+{
+ if (likely(sta)) {
+ if (likely(iwl_mvm_tx_skb_sta(mvm, skb, sta) == 0))
+ return;
+ } else {
+ if (likely(iwl_mvm_tx_skb_non_sta(mvm, skb) == 0))
+ return;
+ }
+
+ ieee80211_free_txskb(mvm->hw, skb);
+}
+
static void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
struct ieee80211_tx_control *control,
struct sk_buff *skb)
@@ -797,14 +812,7 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
}
}
- if (sta) {
- if (iwl_mvm_tx_skb(mvm, skb, sta))
- goto drop;
- return;
- }
-
- if (iwl_mvm_tx_skb_non_sta(mvm, skb))
- goto drop;
+ iwl_mvm_tx_skb(mvm, skb, sta);
return;
drop:
ieee80211_free_txskb(hw, skb);
@@ -854,10 +862,7 @@ void iwl_mvm_mac_itxq_xmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
break;
}
- if (!txq->sta)
- iwl_mvm_tx_skb_non_sta(mvm, skb);
- else
- iwl_mvm_tx_skb(mvm, skb, txq->sta);
+ iwl_mvm_tx_skb(mvm, skb, txq->sta);
}
} while (atomic_dec_return(&mvmtxq->tx_request));
rcu_read_unlock();
@@ -4771,6 +4776,125 @@ static int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx,
return ret;
}
+static void iwl_mvm_set_sta_rate(u32 rate_n_flags, struct rate_info *rinfo)
+{
+ switch (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) {
+ case RATE_MCS_CHAN_WIDTH_20:
+ rinfo->bw = RATE_INFO_BW_20;
+ break;
+ case RATE_MCS_CHAN_WIDTH_40:
+ rinfo->bw = RATE_INFO_BW_40;
+ break;
+ case RATE_MCS_CHAN_WIDTH_80:
+ rinfo->bw = RATE_INFO_BW_80;
+ break;
+ case RATE_MCS_CHAN_WIDTH_160:
+ rinfo->bw = RATE_INFO_BW_160;
+ break;
+ }
+
+ if (rate_n_flags & RATE_MCS_HT_MSK) {
+ rinfo->flags |= RATE_INFO_FLAGS_MCS;
+ rinfo->mcs = u32_get_bits(rate_n_flags, RATE_HT_MCS_INDEX_MSK);
+ rinfo->nss = u32_get_bits(rate_n_flags,
+ RATE_HT_MCS_NSS_MSK) + 1;
+ if (rate_n_flags & RATE_MCS_SGI_MSK)
+ rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
+ } else if (rate_n_flags & RATE_MCS_VHT_MSK) {
+ rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS;
+ rinfo->mcs = u32_get_bits(rate_n_flags,
+ RATE_VHT_MCS_RATE_CODE_MSK);
+ rinfo->nss = u32_get_bits(rate_n_flags,
+ RATE_VHT_MCS_NSS_MSK) + 1;
+ if (rate_n_flags & RATE_MCS_SGI_MSK)
+ rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
+ } else if (rate_n_flags & RATE_MCS_HE_MSK) {
+ u32 gi_ltf = u32_get_bits(rate_n_flags,
+ RATE_MCS_HE_GI_LTF_MSK);
+
+ rinfo->flags |= RATE_INFO_FLAGS_HE_MCS;
+ rinfo->mcs = u32_get_bits(rate_n_flags,
+ RATE_VHT_MCS_RATE_CODE_MSK);
+ rinfo->nss = u32_get_bits(rate_n_flags,
+ RATE_VHT_MCS_NSS_MSK) + 1;
+
+ if (rate_n_flags & RATE_MCS_HE_106T_MSK) {
+ rinfo->bw = RATE_INFO_BW_HE_RU;
+ rinfo->he_ru_alloc = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+ }
+
+ switch (rate_n_flags & RATE_MCS_HE_TYPE_MSK) {
+ case RATE_MCS_HE_TYPE_SU:
+ case RATE_MCS_HE_TYPE_EXT_SU:
+ if (gi_ltf == 0 || gi_ltf == 1)
+ rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+ else if (gi_ltf == 2)
+ rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+ else if (rate_n_flags & RATE_MCS_SGI_MSK)
+ rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+ else
+ rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+ break;
+ case RATE_MCS_HE_TYPE_MU:
+ if (gi_ltf == 0 || gi_ltf == 1)
+ rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+ else if (gi_ltf == 2)
+ rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+ else
+ rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+ break;
+ case RATE_MCS_HE_TYPE_TRIG:
+ if (gi_ltf == 0 || gi_ltf == 1)
+ rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+ else
+ rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+ break;
+ }
+
+ if (rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK)
+ rinfo->he_dcm = 1;
+ } else {
+ switch (u32_get_bits(rate_n_flags, RATE_LEGACY_RATE_MSK)) {
+ case IWL_RATE_1M_PLCP:
+ rinfo->legacy = 10;
+ break;
+ case IWL_RATE_2M_PLCP:
+ rinfo->legacy = 20;
+ break;
+ case IWL_RATE_5M_PLCP:
+ rinfo->legacy = 55;
+ break;
+ case IWL_RATE_11M_PLCP:
+ rinfo->legacy = 110;
+ break;
+ case IWL_RATE_6M_PLCP:
+ rinfo->legacy = 60;
+ break;
+ case IWL_RATE_9M_PLCP:
+ rinfo->legacy = 90;
+ break;
+ case IWL_RATE_12M_PLCP:
+ rinfo->legacy = 120;
+ break;
+ case IWL_RATE_18M_PLCP:
+ rinfo->legacy = 180;
+ break;
+ case IWL_RATE_24M_PLCP:
+ rinfo->legacy = 240;
+ break;
+ case IWL_RATE_36M_PLCP:
+ rinfo->legacy = 360;
+ break;
+ case IWL_RATE_48M_PLCP:
+ rinfo->legacy = 480;
+ break;
+ case IWL_RATE_54M_PLCP:
+ rinfo->legacy = 540;
+ break;
+ }
+ }
+}
+
static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
struct ieee80211_sta *sta,
@@ -4785,6 +4909,13 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
}
+ if (iwl_mvm_has_tlc_offload(mvm)) {
+ struct iwl_lq_sta_rs_fw *lq_sta = &mvmsta->lq_sta.rs_fw;
+
+ iwl_mvm_set_sta_rate(lq_sta->last_rate_n_flags, &sinfo->txrate);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
+ }
+
/* if beacon filtering isn't on mac80211 does it anyway */
if (!(vif->driver_flags & IEEE80211_VIF_BEACON_FILTER))
return;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 3ec8de0..67ab7e7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1298,9 +1298,6 @@ static inline bool iwl_mvm_is_lar_supported(struct iwl_mvm *mvm)
bool tlv_lar = fw_has_capa(&mvm->fw->ucode_capa,
IWL_UCODE_TLV_CAPA_LAR_SUPPORT);
- if (iwlwifi_mod_params.lar_disable)
- return false;
-
/*
* Enable LAR only if it is supported by the FW (TLV) &&
* enabled in the NVM
@@ -1508,8 +1505,8 @@ int __must_check iwl_mvm_send_cmd_status(struct iwl_mvm *mvm,
int __must_check iwl_mvm_send_cmd_pdu_status(struct iwl_mvm *mvm, u32 id,
u16 len, const void *data,
u32 *status);
-int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
- struct ieee80211_sta *sta);
+int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
+ struct ieee80211_sta *sta);
int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb);
void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb,
struct iwl_tx_cmd *tx_cmd,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index 945c1ea..46128a2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -277,11 +277,10 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
struct iwl_nvm_section *sections = mvm->nvm_sections;
const __be16 *hw;
const __le16 *sw, *calib, *regulatory, *mac_override, *phy_sku;
- bool lar_enabled;
int regulatory_type;
/* Checking for required sections */
- if (mvm->trans->cfg->nvm_type != IWL_NVM_EXT) {
+ if (mvm->trans->cfg->nvm_type == IWL_NVM) {
if (!mvm->nvm_sections[NVM_SECTION_TYPE_SW].data ||
!mvm->nvm_sections[mvm->cfg->nvm_hw_section_num].data) {
IWL_ERR(mvm, "Can't parse empty OTP/NVM sections\n");
@@ -327,14 +326,9 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
(const __le16 *)sections[NVM_SECTION_TYPE_REGULATORY_SDP].data :
(const __le16 *)sections[NVM_SECTION_TYPE_REGULATORY].data;
- lar_enabled = !iwlwifi_mod_params.lar_disable &&
- fw_has_capa(&mvm->fw->ucode_capa,
- IWL_UCODE_TLV_CAPA_LAR_SUPPORT);
-
- return iwl_parse_nvm_data(mvm->trans, mvm->cfg, hw, sw, calib,
+ return iwl_parse_nvm_data(mvm->trans, mvm->cfg, mvm->fw, hw, sw, calib,
regulatory, mac_override, phy_sku,
- mvm->fw->valid_tx_ant, mvm->fw->valid_rx_ant,
- lar_enabled);
+ mvm->fw->valid_tx_ant, mvm->fw->valid_rx_ant);
}
/* Loads the NVM data stored in mvm->nvm_sections into the NIC */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index ef99c49..c15f7db 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -514,14 +514,17 @@ static bool iwl_mvm_is_sn_less(u16 sn1, u16 sn2, u16 buffer_size)
static void iwl_mvm_sync_nssn(struct iwl_mvm *mvm, u8 baid, u16 nssn)
{
- struct iwl_mvm_rss_sync_notif notif = {
- .metadata.type = IWL_MVM_RXQ_NSSN_SYNC,
- .metadata.sync = 0,
- .nssn_sync.baid = baid,
- .nssn_sync.nssn = nssn,
- };
+ if (IWL_MVM_USE_NSSN_SYNC) {
+ struct iwl_mvm_rss_sync_notif notif = {
+ .metadata.type = IWL_MVM_RXQ_NSSN_SYNC,
+ .metadata.sync = 0,
+ .nssn_sync.baid = baid,
+ .nssn_sync.nssn = nssn,
+ };
- iwl_mvm_sync_rx_queues_internal(mvm, (void *)¬if, sizeof(notif));
+ iwl_mvm_sync_rx_queues_internal(mvm, (void *)¬if,
+ sizeof(notif));
+ }
}
#define RX_REORDER_BUF_TIMEOUT_MQ (HZ / 10)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index a046ac9..a5af8f4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1213,7 +1213,7 @@ static int iwl_mvm_legacy_config_scan(struct iwl_mvm *mvm)
cmd_size = sizeof(struct iwl_scan_config_v2);
else
cmd_size = sizeof(struct iwl_scan_config_v1);
- cmd_size += num_channels;
+ cmd_size += mvm->fw->ucode_capa.n_scan_channels;
cfg = kzalloc(cmd_size, GFP_KERNEL);
if (!cfg)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index dc5c02f..a8d0d17 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -490,13 +490,13 @@ static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm,
/*
* Allocates and sets the Tx cmd the driver data pointers in the skb
*/
-static struct iwl_device_cmd *
+static struct iwl_device_tx_cmd *
iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
struct ieee80211_tx_info *info, int hdrlen,
struct ieee80211_sta *sta, u8 sta_id)
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
- struct iwl_device_cmd *dev_cmd;
+ struct iwl_device_tx_cmd *dev_cmd;
struct iwl_tx_cmd *tx_cmd;
dev_cmd = iwl_trans_alloc_tx_cmd(mvm->trans);
@@ -504,11 +504,6 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
if (unlikely(!dev_cmd))
return NULL;
- /* Make sure we zero enough of dev_cmd */
- BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) > sizeof(*tx_cmd));
- BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen3) > sizeof(*tx_cmd));
-
- memset(dev_cmd, 0, sizeof(dev_cmd->hdr) + sizeof(*tx_cmd));
dev_cmd->hdr.cmd = TX_CMD;
if (iwl_mvm_has_new_tx_api(mvm)) {
@@ -597,7 +592,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
}
static void iwl_mvm_skb_prepare_status(struct sk_buff *skb,
- struct iwl_device_cmd *cmd)
+ struct iwl_device_tx_cmd *cmd)
{
struct ieee80211_tx_info *skb_info = IEEE80211_SKB_CB(skb);
@@ -716,7 +711,7 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
struct ieee80211_tx_info info;
- struct iwl_device_cmd *dev_cmd;
+ struct iwl_device_tx_cmd *dev_cmd;
u8 sta_id;
int hdrlen = ieee80211_hdrlen(hdr->frame_control);
__le16 fc = hdr->frame_control;
@@ -847,10 +842,7 @@ iwl_mvm_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes,
else if (next)
consume_skb(skb);
- while (next) {
- tmp = next;
- next = tmp->next;
-
+ skb_list_walk_safe(next, tmp, next) {
memcpy(tmp->cb, cb, sizeof(tmp->cb));
/*
* Compute the length of all the data added for the A-MSDU.
@@ -880,9 +872,7 @@ iwl_mvm_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes,
skb_shinfo(tmp)->gso_size = 0;
}
- tmp->prev = NULL;
- tmp->next = NULL;
-
+ skb_mark_not_on_list(tmp);
__skb_queue_tail(mpdus_skb, tmp);
i++;
}
@@ -1078,7 +1068,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
struct iwl_mvm_sta *mvmsta;
- struct iwl_device_cmd *dev_cmd;
+ struct iwl_device_tx_cmd *dev_cmd;
__le16 fc;
u16 seq_number = 0;
u8 tid = IWL_MAX_TID_COUNT;
@@ -1154,7 +1144,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
if (WARN_ONCE(txq_id == IWL_MVM_INVALID_QUEUE, "Invalid TXQ id")) {
iwl_trans_free_tx_cmd(mvm->trans, dev_cmd);
spin_unlock(&mvmsta->lock);
- return 0;
+ return -1;
}
if (!iwl_mvm_has_new_tx_api(mvm)) {
@@ -1206,8 +1196,8 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
return -1;
}
-int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
- struct ieee80211_sta *sta)
+int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
+ struct ieee80211_sta *sta)
{
struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
struct ieee80211_tx_info info;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index d38cefb..e249e3f 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -57,6 +57,42 @@
#include "internal.h"
#include "iwl-prph.h"
+static void *_iwl_pcie_ctxt_info_dma_alloc_coherent(struct iwl_trans *trans,
+ size_t size,
+ dma_addr_t *phys,
+ int depth)
+{
+ void *result;
+
+ if (WARN(depth > 2,
+ "failed to allocate DMA memory not crossing 2^32 boundary"))
+ return NULL;
+
+ result = dma_alloc_coherent(trans->dev, size, phys, GFP_KERNEL);
+
+ if (!result)
+ return NULL;
+
+ if (unlikely(iwl_pcie_crosses_4g_boundary(*phys, size))) {
+ void *old = result;
+ dma_addr_t oldphys = *phys;
+
+ result = _iwl_pcie_ctxt_info_dma_alloc_coherent(trans, size,
+ phys,
+ depth + 1);
+ dma_free_coherent(trans->dev, size, old, oldphys);
+ }
+
+ return result;
+}
+
+static void *iwl_pcie_ctxt_info_dma_alloc_coherent(struct iwl_trans *trans,
+ size_t size,
+ dma_addr_t *phys)
+{
+ return _iwl_pcie_ctxt_info_dma_alloc_coherent(trans, size, phys, 0);
+}
+
void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans)
{
struct iwl_self_init_dram *dram = &trans->init_dram;
@@ -161,14 +197,17 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
struct iwl_context_info *ctxt_info;
struct iwl_context_info_rbd_cfg *rx_cfg;
u32 control_flags = 0, rb_size;
+ dma_addr_t phys;
int ret;
- ctxt_info = dma_alloc_coherent(trans->dev, sizeof(*ctxt_info),
- &trans_pcie->ctxt_info_dma_addr,
- GFP_KERNEL);
+ ctxt_info = iwl_pcie_ctxt_info_dma_alloc_coherent(trans,
+ sizeof(*ctxt_info),
+ &phys);
if (!ctxt_info)
return -ENOMEM;
+ trans_pcie->ctxt_info_dma_addr = phys;
+
ctxt_info->version.version = 0;
ctxt_info->version.mac_id =
cpu_to_le16((u16)iwl_read32(trans, CSR_HW_REV));
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index a091690..f14bcef 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -305,7 +305,7 @@ struct iwl_cmd_meta {
#define IWL_FIRST_TB_SIZE_ALIGN ALIGN(IWL_FIRST_TB_SIZE, 64)
struct iwl_pcie_txq_entry {
- struct iwl_device_cmd *cmd;
+ void *cmd;
struct sk_buff *skb;
/* buffer to free after command completes */
const void *free_buf;
@@ -672,6 +672,16 @@ void iwl_pcie_disable_ict(struct iwl_trans *trans);
/*****************************************************
* TX / HCMD
******************************************************/
+/*
+ * We need this inline in case dma_addr_t is only 32-bits - since the
+ * hardware is always 64-bit, the issue can still occur in that case,
+ * so use u64 for 'phys' here to force the addition in 64-bit.
+ */
+static inline bool iwl_pcie_crosses_4g_boundary(u64 phys, u16 len)
+{
+ return upper_32_bits(phys) != upper_32_bits(phys + len);
+}
+
int iwl_pcie_tx_init(struct iwl_trans *trans);
int iwl_pcie_gen2_tx_init(struct iwl_trans *trans, int txq_id,
int queue_size);
@@ -688,7 +698,7 @@ void iwl_trans_pcie_txq_set_shared_mode(struct iwl_trans *trans, u32 txq_id,
void iwl_trans_pcie_log_scd_error(struct iwl_trans *trans,
struct iwl_txq *txq);
int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
- struct iwl_device_cmd *dev_cmd, int txq_id);
+ struct iwl_device_tx_cmd *dev_cmd, int txq_id);
void iwl_pcie_txq_check_wrptrs(struct iwl_trans *trans);
int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd);
void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx);
@@ -1082,7 +1092,8 @@ void iwl_pcie_apply_destination(struct iwl_trans *trans);
void iwl_pcie_free_tso_page(struct iwl_trans_pcie *trans_pcie,
struct sk_buff *skb);
#ifdef CONFIG_INET
-struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len);
+struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
+ struct sk_buff *skb);
#endif
/* common functions that are used by gen3 transport */
@@ -1106,7 +1117,7 @@ int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans,
unsigned int timeout);
void iwl_trans_pcie_dyn_txq_free(struct iwl_trans *trans, int queue);
int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
- struct iwl_device_cmd *dev_cmd, int txq_id);
+ struct iwl_device_tx_cmd *dev_cmd, int txq_id);
int iwl_trans_pcie_gen2_send_hcmd(struct iwl_trans *trans,
struct iwl_host_cmd *cmd);
void iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 452da44..f0b8ff6 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1529,13 +1529,13 @@ static void iwl_pcie_rx_handle(struct iwl_trans *trans, int queue)
napi = &rxq->napi;
if (napi->poll) {
+ napi_gro_flush(napi, false);
+
if (napi->rx_count) {
netif_receive_skb_list(&napi->rx_list);
INIT_LIST_HEAD(&napi->rx_list);
napi->rx_count = 0;
}
-
- napi_gro_flush(napi, false);
}
iwl_pcie_rxq_restock(trans, rxq);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index a0677131..f60d66f 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -79,6 +79,7 @@
#include "iwl-agn-hw.h"
#include "fw/error-dump.h"
#include "fw/dbg.h"
+#include "fw/api/tx.h"
#include "internal.h"
#include "iwl-fh.h"
@@ -301,18 +302,13 @@ void iwl_pcie_apm_config(struct iwl_trans *trans)
u16 cap;
/*
- * HW bug W/A for instability in PCIe bus L0S->L1 transition.
- * Check if BIOS (or OS) enabled L1-ASPM on this device.
- * If so (likely), disable L0S, so device moves directly L0->L1;
- * costs negligible amount of power savings.
- * If not (unlikely), enable L0S, so there is at least some
- * power savings, even without L1.
+ * L0S states have been found to be unstable with our devices
+ * and in newer hardware they are not officially supported at
+ * all, so we must always set the L0S_DISABLED bit.
*/
+ iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_DISABLED);
+
pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl);
- if (lctl & PCI_EXP_LNKCTL_ASPM_L1)
- iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
- else
- iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S);
pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap);
@@ -3460,19 +3456,34 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
{
struct iwl_trans_pcie *trans_pcie;
struct iwl_trans *trans;
- int ret, addr_size;
+ int ret, addr_size, txcmd_size, txcmd_align;
+ const struct iwl_trans_ops *ops = &trans_ops_pcie_gen2;
+
+ if (!cfg_trans->gen2) {
+ ops = &trans_ops_pcie;
+ txcmd_size = sizeof(struct iwl_tx_cmd);
+ txcmd_align = sizeof(void *);
+ } else if (cfg_trans->device_family < IWL_DEVICE_FAMILY_AX210) {
+ txcmd_size = sizeof(struct iwl_tx_cmd_gen2);
+ txcmd_align = 64;
+ } else {
+ txcmd_size = sizeof(struct iwl_tx_cmd_gen3);
+ txcmd_align = 128;
+ }
+
+ txcmd_size += sizeof(struct iwl_cmd_header);
+ txcmd_size += 36; /* biggest possible 802.11 header */
+
+ /* Ensure device TX cmd cannot reach/cross a page boundary in gen2 */
+ if (WARN_ON(cfg_trans->gen2 && txcmd_size >= txcmd_align))
+ return ERR_PTR(-EINVAL);
ret = pcim_enable_device(pdev);
if (ret)
return ERR_PTR(ret);
- if (cfg_trans->gen2)
- trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie),
- &pdev->dev, &trans_ops_pcie_gen2);
- else
- trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie),
- &pdev->dev, &trans_ops_pcie);
-
+ trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie), &pdev->dev, ops,
+ txcmd_size, txcmd_align);
if (!trans)
return ERR_PTR(-ENOMEM);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 8ca0250..bfb984b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -221,6 +221,17 @@ static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans,
int idx = iwl_pcie_gen2_get_num_tbs(trans, tfd);
struct iwl_tfh_tb *tb;
+ /*
+ * Only WARN here so we know about the issue, but we mess up our
+ * unmap path because not every place currently checks for errors
+ * returned from this function - it can only return an error if
+ * there's no more space, and so when we know there is enough we
+ * don't always check ...
+ */
+ WARN(iwl_pcie_crosses_4g_boundary(addr, len),
+ "possible DMA problem with iova:0x%llx, len:%d\n",
+ (unsigned long long)addr, len);
+
if (WARN_ON(idx >= IWL_TFH_NUM_TBS))
return -EINVAL;
tb = &tfd->tbs[idx];
@@ -240,13 +251,114 @@ static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans,
return idx;
}
+static struct page *get_workaround_page(struct iwl_trans *trans,
+ struct sk_buff *skb)
+{
+ struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+ struct page **page_ptr;
+ struct page *ret;
+
+ page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
+
+ ret = alloc_page(GFP_ATOMIC);
+ if (!ret)
+ return NULL;
+
+ /* set the chaining pointer to the previous page if there */
+ *(void **)(page_address(ret) + PAGE_SIZE - sizeof(void *)) = *page_ptr;
+ *page_ptr = ret;
+
+ return ret;
+}
+
+/*
+ * Add a TB and if needed apply the FH HW bug workaround;
+ * meta != NULL indicates that it's a page mapping and we
+ * need to dma_unmap_page() and set the meta->tbs bit in
+ * this case.
+ */
+static int iwl_pcie_gen2_set_tb_with_wa(struct iwl_trans *trans,
+ struct sk_buff *skb,
+ struct iwl_tfh_tfd *tfd,
+ dma_addr_t phys, void *virt,
+ u16 len, struct iwl_cmd_meta *meta)
+{
+ dma_addr_t oldphys = phys;
+ struct page *page;
+ int ret;
+
+ if (unlikely(dma_mapping_error(trans->dev, phys)))
+ return -ENOMEM;
+
+ if (likely(!iwl_pcie_crosses_4g_boundary(phys, len))) {
+ ret = iwl_pcie_gen2_set_tb(trans, tfd, phys, len);
+
+ if (ret < 0)
+ goto unmap;
+
+ if (meta)
+ meta->tbs |= BIT(ret);
+
+ ret = 0;
+ goto trace;
+ }
+
+ /*
+ * Work around a hardware bug. If (as expressed in the
+ * condition above) the TB ends on a 32-bit boundary,
+ * then the next TB may be accessed with the wrong
+ * address.
+ * To work around it, copy the data elsewhere and make
+ * a new mapping for it so the device will not fail.
+ */
+
+ if (WARN_ON(len > PAGE_SIZE - sizeof(void *))) {
+ ret = -ENOBUFS;
+ goto unmap;
+ }
+
+ page = get_workaround_page(trans, skb);
+ if (!page) {
+ ret = -ENOMEM;
+ goto unmap;
+ }
+
+ memcpy(page_address(page), virt, len);
+
+ phys = dma_map_single(trans->dev, page_address(page), len,
+ DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(trans->dev, phys)))
+ return -ENOMEM;
+ ret = iwl_pcie_gen2_set_tb(trans, tfd, phys, len);
+ if (ret < 0) {
+ /* unmap the new allocation as single */
+ oldphys = phys;
+ meta = NULL;
+ goto unmap;
+ }
+ IWL_WARN(trans,
+ "TB bug workaround: copied %d bytes from 0x%llx to 0x%llx\n",
+ len, (unsigned long long)oldphys, (unsigned long long)phys);
+
+ ret = 0;
+unmap:
+ if (meta)
+ dma_unmap_page(trans->dev, oldphys, len, DMA_TO_DEVICE);
+ else
+ dma_unmap_single(trans->dev, oldphys, len, DMA_TO_DEVICE);
+trace:
+ trace_iwlwifi_dev_tx_tb(trans->dev, skb, virt, phys, len);
+
+ return ret;
+}
+
static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
struct sk_buff *skb,
struct iwl_tfh_tfd *tfd, int start_len,
- u8 hdr_len, struct iwl_device_cmd *dev_cmd)
+ u8 hdr_len,
+ struct iwl_device_tx_cmd *dev_cmd)
{
#ifdef CONFIG_INET
- struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
struct ieee80211_hdr *hdr = (void *)skb->data;
unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room;
@@ -254,7 +366,6 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
u16 length, amsdu_pad;
u8 *start_hdr;
struct iwl_tso_hdr_page *hdr_page;
- struct page **page_ptr;
struct tso_t tso;
trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd),
@@ -270,14 +381,11 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr));
/* Our device supports 9 segments at most, it will fit in 1 page */
- hdr_page = get_page_hdr(trans, hdr_room);
+ hdr_page = get_page_hdr(trans, hdr_room, skb);
if (!hdr_page)
return -ENOMEM;
- get_page(hdr_page->page);
start_hdr = hdr_page->pos;
- page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
- *page_ptr = hdr_page->page;
/*
* Pull the ieee80211 header to be able to use TSO core,
@@ -332,6 +440,11 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
dev_kfree_skb(csum_skb);
goto out_err;
}
+ /*
+ * No need for _with_wa, this is from the TSO page and
+ * we leave some space at the end of it so can't hit
+ * the buggy scenario.
+ */
iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb_len);
trace_iwlwifi_dev_tx_tb(trans->dev, skb, start_hdr,
tb_phys, tb_len);
@@ -343,16 +456,18 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
/* put the payload */
while (data_left) {
+ int ret;
+
tb_len = min_t(unsigned int, tso.size, data_left);
tb_phys = dma_map_single(trans->dev, tso.data,
tb_len, DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(trans->dev, tb_phys))) {
+ ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd,
+ tb_phys, tso.data,
+ tb_len, NULL);
+ if (ret) {
dev_kfree_skb(csum_skb);
goto out_err;
}
- iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb_len);
- trace_iwlwifi_dev_tx_tb(trans->dev, skb, tso.data,
- tb_phys, tb_len);
data_left -= tb_len;
tso_build_data(skb, &tso, tb_len);
@@ -372,7 +487,7 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
static struct
iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans,
struct iwl_txq *txq,
- struct iwl_device_cmd *dev_cmd,
+ struct iwl_device_tx_cmd *dev_cmd,
struct sk_buff *skb,
struct iwl_cmd_meta *out_meta,
int hdr_len,
@@ -386,6 +501,11 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans,
tb_phys = iwl_pcie_get_first_tb_dma(txq, idx);
+ /*
+ * No need for _with_wa, the first TB allocation is aligned up
+ * to a 64-byte boundary and thus can't be at the end or cross
+ * a page boundary (much less a 2^32 boundary).
+ */
iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
/*
@@ -404,6 +524,10 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans,
tb_phys = dma_map_single(trans->dev, tb1_addr, len, DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
goto out_err;
+ /*
+ * No need for _with_wa(), we ensure (via alignment) that the data
+ * here can never cross or end at a page boundary.
+ */
iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, len);
if (iwl_pcie_gen2_build_amsdu(trans, skb, tfd,
@@ -430,24 +554,19 @@ static int iwl_pcie_gen2_tx_add_frags(struct iwl_trans *trans,
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
dma_addr_t tb_phys;
- int tb_idx;
+ unsigned int fragsz = skb_frag_size(frag);
+ int ret;
- if (!skb_frag_size(frag))
+ if (!fragsz)
continue;
tb_phys = skb_frag_dma_map(trans->dev, frag, 0,
- skb_frag_size(frag), DMA_TO_DEVICE);
-
- if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
- return -ENOMEM;
- tb_idx = iwl_pcie_gen2_set_tb(trans, tfd, tb_phys,
- skb_frag_size(frag));
- trace_iwlwifi_dev_tx_tb(trans->dev, skb, skb_frag_address(frag),
- tb_phys, skb_frag_size(frag));
- if (tb_idx < 0)
- return tb_idx;
-
- out_meta->tbs |= BIT(tb_idx);
+ fragsz, DMA_TO_DEVICE);
+ ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
+ skb_frag_address(frag),
+ fragsz, out_meta);
+ if (ret)
+ return ret;
}
return 0;
@@ -456,7 +575,7 @@ static int iwl_pcie_gen2_tx_add_frags(struct iwl_trans *trans,
static struct
iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
struct iwl_txq *txq,
- struct iwl_device_cmd *dev_cmd,
+ struct iwl_device_tx_cmd *dev_cmd,
struct sk_buff *skb,
struct iwl_cmd_meta *out_meta,
int hdr_len,
@@ -475,6 +594,11 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
/* The first TB points to bi-directional DMA data */
memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE);
+ /*
+ * No need for _with_wa, the first TB allocation is aligned up
+ * to a 64-byte boundary and thus can't be at the end or cross
+ * a page boundary (much less a 2^32 boundary).
+ */
iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
/*
@@ -496,6 +620,10 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
tb_phys = dma_map_single(trans->dev, tb1_addr, tb1_len, DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
goto out_err;
+ /*
+ * No need for _with_wa(), we ensure (via alignment) that the data
+ * here can never cross or end at a page boundary.
+ */
iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb1_len);
trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr,
IWL_FIRST_TB_SIZE + tb1_len, hdr_len);
@@ -504,26 +632,30 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
tb2_len = skb_headlen(skb) - hdr_len;
if (tb2_len > 0) {
+ int ret;
+
tb_phys = dma_map_single(trans->dev, skb->data + hdr_len,
tb2_len, DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+ ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
+ skb->data + hdr_len, tb2_len,
+ NULL);
+ if (ret)
goto out_err;
- iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb2_len);
- trace_iwlwifi_dev_tx_tb(trans->dev, skb, skb->data + hdr_len,
- tb_phys, tb2_len);
}
if (iwl_pcie_gen2_tx_add_frags(trans, skb, tfd, out_meta))
goto out_err;
skb_walk_frags(skb, frag) {
+ int ret;
+
tb_phys = dma_map_single(trans->dev, frag->data,
skb_headlen(frag), DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+ ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
+ frag->data,
+ skb_headlen(frag), NULL);
+ if (ret)
goto out_err;
- iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, skb_headlen(frag));
- trace_iwlwifi_dev_tx_tb(trans->dev, skb, frag->data,
- tb_phys, skb_headlen(frag));
if (iwl_pcie_gen2_tx_add_frags(trans, frag, tfd, out_meta))
goto out_err;
}
@@ -538,7 +670,7 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
static
struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
struct iwl_txq *txq,
- struct iwl_device_cmd *dev_cmd,
+ struct iwl_device_tx_cmd *dev_cmd,
struct sk_buff *skb,
struct iwl_cmd_meta *out_meta)
{
@@ -578,7 +710,7 @@ struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
}
int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
- struct iwl_device_cmd *dev_cmd, int txq_id)
+ struct iwl_device_tx_cmd *dev_cmd, int txq_id)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
struct iwl_cmd_meta *out_meta;
@@ -603,7 +735,7 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
/* don't put the packet on the ring, if there is no room */
if (unlikely(iwl_queue_space(trans, txq) < 3)) {
- struct iwl_device_cmd **dev_cmd_ptr;
+ struct iwl_device_tx_cmd **dev_cmd_ptr;
dev_cmd_ptr = (void *)((u8 *)skb->cb +
trans_pcie->dev_cmd_offs);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index f21f16a..b0eb52b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -213,8 +213,8 @@ static void iwl_pcie_txq_update_byte_cnt_tbl(struct iwl_trans *trans,
u8 sec_ctl = 0;
u16 len = byte_cnt + IWL_TX_CRC_SIZE + IWL_TX_DELIMITER_SIZE;
__le16 bc_ent;
- struct iwl_tx_cmd *tx_cmd =
- (void *)txq->entries[txq->write_ptr].cmd->payload;
+ struct iwl_device_tx_cmd *dev_cmd = txq->entries[txq->write_ptr].cmd;
+ struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
u8 sta_id = tx_cmd->sta_id;
scd_bc_tbl = trans_pcie->scd_bc_tbls.addr;
@@ -257,8 +257,8 @@ static void iwl_pcie_txq_inval_byte_cnt_tbl(struct iwl_trans *trans,
int read_ptr = txq->read_ptr;
u8 sta_id = 0;
__le16 bc_ent;
- struct iwl_tx_cmd *tx_cmd =
- (void *)txq->entries[read_ptr].cmd->payload;
+ struct iwl_device_tx_cmd *dev_cmd = txq->entries[read_ptr].cmd;
+ struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
WARN_ON(read_ptr >= TFD_QUEUE_SIZE_MAX);
@@ -624,12 +624,18 @@ void iwl_pcie_free_tso_page(struct iwl_trans_pcie *trans_pcie,
struct sk_buff *skb)
{
struct page **page_ptr;
+ struct page *next;
page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
+ next = *page_ptr;
+ *page_ptr = NULL;
- if (*page_ptr) {
- __free_page(*page_ptr);
- *page_ptr = NULL;
+ while (next) {
+ struct page *tmp = next;
+
+ next = *(void **)(page_address(next) + PAGE_SIZE -
+ sizeof(void *));
+ __free_page(tmp);
}
}
@@ -1196,7 +1202,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
while (!skb_queue_empty(&overflow_skbs)) {
struct sk_buff *skb = __skb_dequeue(&overflow_skbs);
- struct iwl_device_cmd *dev_cmd_ptr;
+ struct iwl_device_tx_cmd *dev_cmd_ptr;
dev_cmd_ptr = *(void **)((u8 *)skb->cb +
trans_pcie->dev_cmd_offs);
@@ -2052,17 +2058,34 @@ static int iwl_fill_data_tbs(struct iwl_trans *trans, struct sk_buff *skb,
}
#ifdef CONFIG_INET
-struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len)
+struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
+ struct sk_buff *skb)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
struct iwl_tso_hdr_page *p = this_cpu_ptr(trans_pcie->tso_hdr_page);
+ struct page **page_ptr;
+
+ page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
+
+ if (WARN_ON(*page_ptr))
+ return NULL;
if (!p->page)
goto alloc;
- /* enough room on this page */
- if (p->pos + len < (u8 *)page_address(p->page) + PAGE_SIZE)
- return p;
+ /*
+ * Check if there's enough room on this page
+ *
+ * Note that we put a page chaining pointer *last* in the
+ * page - we need it somewhere, and if it's there then we
+ * avoid DMA mapping the last bits of the page which may
+ * trigger the 32-bit boundary hardware bug.
+ *
+ * (see also get_workaround_page() in tx-gen2.c)
+ */
+ if (p->pos + len < (u8 *)page_address(p->page) + PAGE_SIZE -
+ sizeof(void *))
+ goto out;
/* We don't have enough room on this page, get a new one. */
__free_page(p->page);
@@ -2072,6 +2095,11 @@ struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len)
if (!p->page)
return NULL;
p->pos = page_address(p->page);
+ /* set the chaining pointer to NULL */
+ *(void **)(page_address(p->page) + PAGE_SIZE - sizeof(void *)) = NULL;
+out:
+ *page_ptr = p->page;
+ get_page(p->page);
return p;
}
@@ -2097,7 +2125,8 @@ static void iwl_compute_pseudo_hdr_csum(void *iph, struct tcphdr *tcph,
static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
struct iwl_txq *txq, u8 hdr_len,
struct iwl_cmd_meta *out_meta,
- struct iwl_device_cmd *dev_cmd, u16 tb1_len)
+ struct iwl_device_tx_cmd *dev_cmd,
+ u16 tb1_len)
{
struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
struct iwl_trans_pcie *trans_pcie = txq->trans_pcie;
@@ -2107,7 +2136,6 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
u16 length, iv_len, amsdu_pad;
u8 *start_hdr;
struct iwl_tso_hdr_page *hdr_page;
- struct page **page_ptr;
struct tso_t tso;
/* if the packet is protected, then it must be CCMP or GCMP */
@@ -2130,14 +2158,11 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)) + iv_len;
/* Our device supports 9 segments at most, it will fit in 1 page */
- hdr_page = get_page_hdr(trans, hdr_room);
+ hdr_page = get_page_hdr(trans, hdr_room, skb);
if (!hdr_page)
return -ENOMEM;
- get_page(hdr_page->page);
start_hdr = hdr_page->pos;
- page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
- *page_ptr = hdr_page->page;
memcpy(hdr_page->pos, skb->data + hdr_len, iv_len);
hdr_page->pos += iv_len;
@@ -2279,7 +2304,8 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
struct iwl_txq *txq, u8 hdr_len,
struct iwl_cmd_meta *out_meta,
- struct iwl_device_cmd *dev_cmd, u16 tb1_len)
+ struct iwl_device_tx_cmd *dev_cmd,
+ u16 tb1_len)
{
/* No A-MSDU without CONFIG_INET */
WARN_ON(1);
@@ -2289,7 +2315,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
#endif /* CONFIG_INET */
int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
- struct iwl_device_cmd *dev_cmd, int txq_id)
+ struct iwl_device_tx_cmd *dev_cmd, int txq_id)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
struct ieee80211_hdr *hdr;
@@ -2346,7 +2372,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
/* don't put the packet on the ring, if there is no room */
if (unlikely(iwl_queue_space(trans, txq) < 3)) {
- struct iwl_device_cmd **dev_cmd_ptr;
+ struct iwl_device_tx_cmd **dev_cmd_ptr;
dev_cmd_ptr = (void *)((u8 *)skb->cb +
trans_pcie->dev_cmd_offs);
diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c
index 57edfad..c9401c1 100644
--- a/drivers/net/wireless/marvell/libertas/cfg.c
+++ b/drivers/net/wireless/marvell/libertas/cfg.c
@@ -273,6 +273,10 @@ add_ie_rates(u8 *tlv, const u8 *ie, int *nrates)
int hw, ap, ap_max = ie[1];
u8 hw_rate;
+ if (ap_max > MAX_RATES) {
+ lbs_deb_assoc("invalid rates\n");
+ return tlv;
+ }
/* Advance past IE header */
ie += 2;
@@ -1717,6 +1721,9 @@ static int lbs_ibss_join_existing(struct lbs_private *priv,
struct cmd_ds_802_11_ad_hoc_join cmd;
u8 preamble = RADIO_PREAMBLE_SHORT;
int ret = 0;
+ int hw, i;
+ u8 rates_max;
+ u8 *rates;
/* TODO: set preamble based on scan result */
ret = lbs_set_radio(priv, preamble, 1);
@@ -1775,9 +1782,12 @@ static int lbs_ibss_join_existing(struct lbs_private *priv,
if (!rates_eid) {
lbs_add_rates(cmd.bss.rates);
} else {
- int hw, i;
- u8 rates_max = rates_eid[1];
- u8 *rates = cmd.bss.rates;
+ rates_max = rates_eid[1];
+ if (rates_max > MAX_RATES) {
+ lbs_deb_join("invalid rates");
+ goto out;
+ }
+ rates = cmd.bss.rates;
for (hw = 0; hw < ARRAY_SIZE(lbs_rates); hw++) {
u8 hw_rate = lbs_rates[hw].bitrate / 5;
for (i = 0; i < rates_max; i++) {
diff --git a/drivers/net/wireless/mediatek/mt76/airtime.c b/drivers/net/wireless/mediatek/mt76/airtime.c
index 55116f3..a4a7854 100644
--- a/drivers/net/wireless/mediatek/mt76/airtime.c
+++ b/drivers/net/wireless/mediatek/mt76/airtime.c
@@ -242,7 +242,7 @@ u32 mt76_calc_rx_airtime(struct mt76_dev *dev, struct mt76_rx_status *status,
return 0;
sband = dev->hw->wiphy->bands[status->band];
- if (!sband || status->rate_idx > sband->n_bitrates)
+ if (!sband || status->rate_idx >= sband->n_bitrates)
return 0;
rate = &sband->bitrates[status->rate_idx];
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index b9f2a40..96018fd6 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -378,7 +378,8 @@ void mt76_unregister_device(struct mt76_dev *dev)
{
struct ieee80211_hw *hw = dev->hw;
- mt76_led_cleanup(dev);
+ if (IS_ENABLED(CONFIG_MT76_LEDS))
+ mt76_led_cleanup(dev);
mt76_tx_status_check(dev, NULL, true);
ieee80211_unregister_hw(hw);
}
diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c
index 10d580c..6b7532f 100644
--- a/drivers/net/xen-netback/hash.c
+++ b/drivers/net/xen-netback/hash.c
@@ -51,7 +51,8 @@ static void xenvif_add_hash(struct xenvif *vif, const u8 *tag,
found = false;
oldest = NULL;
- list_for_each_entry_rcu(entry, &vif->hash.cache.list, link) {
+ list_for_each_entry_rcu(entry, &vif->hash.cache.list, link,
+ lockdep_is_held(&vif->hash.cache.lock)) {
/* Make sure we don't add duplicate entries */
if (entry->len == len &&
memcmp(entry->tag, tag, len) == 0)
@@ -102,7 +103,8 @@ static void xenvif_flush_hash(struct xenvif *vif)
spin_lock_irqsave(&vif->hash.cache.lock, flags);
- list_for_each_entry_rcu(entry, &vif->hash.cache.list, link) {
+ list_for_each_entry_rcu(entry, &vif->hash.cache.list, link,
+ lockdep_is_held(&vif->hash.cache.lock)) {
list_del_rcu(&entry->link);
vif->hash.cache.count--;
kfree_rcu(entry, rcu);
diff --git a/drivers/nfc/pn533/i2c.c b/drivers/nfc/pn533/i2c.c
index 7507176..0207e66 100644
--- a/drivers/nfc/pn533/i2c.c
+++ b/drivers/nfc/pn533/i2c.c
@@ -274,7 +274,6 @@ MODULE_DEVICE_TABLE(i2c, pn533_i2c_id_table);
static struct i2c_driver pn533_i2c_driver = {
.driver = {
.name = PN533_I2C_DRIVER_NAME,
- .owner = THIS_MODULE,
.of_match_table = of_match_ptr(of_pn533_i2c_match),
},
.probe = pn533_i2c_probe,
diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index 4590fbf..f5bb7ac 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -391,7 +391,7 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy)
cmd, sizeof(cmd), false);
rc = usb_bulk_msg(phy->udev, phy->out_urb->pipe, buffer, sizeof(cmd),
- &transferred, 0);
+ &transferred, 5000);
kfree(buffer);
if (rc || (transferred != sizeof(cmd))) {
nfc_err(&phy->udev->dev,
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 667f18f..5dc32b7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -222,6 +222,8 @@ static blk_status_t nvme_error_status(u16 status)
case NVME_SC_CAP_EXCEEDED:
return BLK_STS_NOSPC;
case NVME_SC_LBA_RANGE:
+ case NVME_SC_CMD_INTERRUPTED:
+ case NVME_SC_NS_NOT_READY:
return BLK_STS_TARGET;
case NVME_SC_BAD_ATTRIBUTES:
case NVME_SC_ONCS_NOT_SUPPORTED:
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 56c21b50..72a7e41 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -24,6 +24,16 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd)
return len;
}
+static u32 nvmet_feat_data_len(struct nvmet_req *req, u32 cdw10)
+{
+ switch (cdw10 & 0xff) {
+ case NVME_FEAT_HOST_ID:
+ return sizeof(req->sq->ctrl->hostid);
+ default:
+ return 0;
+ }
+}
+
u64 nvmet_get_log_page_offset(struct nvme_command *cmd)
{
return le64_to_cpu(cmd->get_log_page.lpo);
@@ -778,7 +788,7 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
u16 status = 0;
- if (!nvmet_check_data_len(req, 0))
+ if (!nvmet_check_data_len(req, nvmet_feat_data_len(req, cdw10)))
return;
switch (cdw10 & 0xff) {
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 4937a08..fbeb9f7 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -5074,18 +5074,25 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags);
#ifdef CONFIG_PCI_ATS
/*
- * Some devices have a broken ATS implementation causing IOMMU stalls.
- * Don't use ATS for those devices.
+ * Some devices require additional driver setup to enable ATS. Don't use
+ * ATS for those devices as ATS will be enabled before the driver has had a
+ * chance to load and configure the device.
*/
-static void quirk_no_ats(struct pci_dev *pdev)
+static void quirk_amd_harvest_no_ats(struct pci_dev *pdev)
{
- pci_info(pdev, "disabling ATS (broken on this device)\n");
+ if (pdev->device == 0x7340 && pdev->revision != 0xc5)
+ return;
+
+ pci_info(pdev, "disabling ATS\n");
pdev->ats_cap = 0;
}
/* AMD Stoney platform GPU */
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_no_ats);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats);
+/* AMD Iceland dGPU */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats);
+/* AMD Navi14 dGPU */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats);
#endif /* CONFIG_PCI_ATS */
/* Freescale PCIe doesn't support MSI in RC mode */
diff --git a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
index e3b87c9..e41367f 100644
--- a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
+++ b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
@@ -221,7 +221,7 @@ static const struct mvebu_comphy_conf mvebu_comphy_cp110_modes[] = {
ETH_CONF(2, 0, PHY_INTERFACE_MODE_SGMII, 0x1, COMPHY_FW_MODE_SGMII),
ETH_CONF(2, 0, PHY_INTERFACE_MODE_2500BASEX, 0x1, COMPHY_FW_MODE_HS_SGMII),
ETH_CONF(2, 0, PHY_INTERFACE_MODE_RXAUI, 0x1, COMPHY_FW_MODE_RXAUI),
- ETH_CONF(2, 0, PHY_INTERFACE_MODE_10GKR, 0x1, COMPHY_FW_MODE_XFI),
+ ETH_CONF(2, 0, PHY_INTERFACE_MODE_10GBASER, 0x1, COMPHY_FW_MODE_XFI),
GEN_CONF(2, 0, PHY_MODE_USB_HOST_SS, COMPHY_FW_MODE_USB3H),
GEN_CONF(2, 0, PHY_MODE_SATA, COMPHY_FW_MODE_SATA),
GEN_CONF(2, 0, PHY_MODE_PCIE, COMPHY_FW_MODE_PCIE),
@@ -235,14 +235,14 @@ static const struct mvebu_comphy_conf mvebu_comphy_cp110_modes[] = {
/* lane 4 */
ETH_CONF(4, 0, PHY_INTERFACE_MODE_SGMII, 0x2, COMPHY_FW_MODE_SGMII),
ETH_CONF(4, 0, PHY_INTERFACE_MODE_2500BASEX, 0x2, COMPHY_FW_MODE_HS_SGMII),
- ETH_CONF(4, 0, PHY_INTERFACE_MODE_10GKR, 0x2, COMPHY_FW_MODE_XFI),
+ ETH_CONF(4, 0, PHY_INTERFACE_MODE_10GBASER, 0x2, COMPHY_FW_MODE_XFI),
ETH_CONF(4, 0, PHY_INTERFACE_MODE_RXAUI, 0x2, COMPHY_FW_MODE_RXAUI),
GEN_CONF(4, 0, PHY_MODE_USB_DEVICE_SS, COMPHY_FW_MODE_USB3D),
GEN_CONF(4, 1, PHY_MODE_USB_HOST_SS, COMPHY_FW_MODE_USB3H),
GEN_CONF(4, 1, PHY_MODE_PCIE, COMPHY_FW_MODE_PCIE),
ETH_CONF(4, 1, PHY_INTERFACE_MODE_SGMII, 0x1, COMPHY_FW_MODE_SGMII),
ETH_CONF(4, 1, PHY_INTERFACE_MODE_2500BASEX, -1, COMPHY_FW_MODE_HS_SGMII),
- ETH_CONF(4, 1, PHY_INTERFACE_MODE_10GKR, -1, COMPHY_FW_MODE_XFI),
+ ETH_CONF(4, 1, PHY_INTERFACE_MODE_10GBASER, -1, COMPHY_FW_MODE_XFI),
/* lane 5 */
ETH_CONF(5, 1, PHY_INTERFACE_MODE_RXAUI, 0x2, COMPHY_FW_MODE_RXAUI),
GEN_CONF(5, 1, PHY_MODE_SATA, COMPHY_FW_MODE_SATA),
@@ -342,7 +342,7 @@ static int mvebu_comphy_ethernet_init_reset(struct mvebu_comphy_lane *lane)
MVEBU_COMPHY_SERDES_CFG0_RXAUI_MODE);
switch (lane->submode) {
- case PHY_INTERFACE_MODE_10GKR:
+ case PHY_INTERFACE_MODE_10GBASER:
val |= MVEBU_COMPHY_SERDES_CFG0_GEN_RX(0xe) |
MVEBU_COMPHY_SERDES_CFG0_GEN_TX(0xe);
break;
@@ -417,7 +417,7 @@ static int mvebu_comphy_ethernet_init_reset(struct mvebu_comphy_lane *lane)
/* refclk selection */
val = readl(priv->base + MVEBU_COMPHY_MISC_CTRL0(lane->id));
val &= ~MVEBU_COMPHY_MISC_CTRL0_REFCLK_SEL;
- if (lane->submode == PHY_INTERFACE_MODE_10GKR)
+ if (lane->submode == PHY_INTERFACE_MODE_10GBASER)
val |= MVEBU_COMPHY_MISC_CTRL0_ICP_FORCE;
writel(val, priv->base + MVEBU_COMPHY_MISC_CTRL0(lane->id));
@@ -564,7 +564,7 @@ static int mvebu_comphy_set_mode_rxaui(struct phy *phy)
return mvebu_comphy_init_plls(lane);
}
-static int mvebu_comphy_set_mode_10gkr(struct phy *phy)
+static int mvebu_comphy_set_mode_10gbaser(struct phy *phy)
{
struct mvebu_comphy_lane *lane = phy_get_drvdata(phy);
struct mvebu_comphy_priv *priv = lane->priv;
@@ -735,8 +735,8 @@ static int mvebu_comphy_power_on_legacy(struct phy *phy)
case PHY_INTERFACE_MODE_RXAUI:
ret = mvebu_comphy_set_mode_rxaui(phy);
break;
- case PHY_INTERFACE_MODE_10GKR:
- ret = mvebu_comphy_set_mode_10gkr(phy);
+ case PHY_INTERFACE_MODE_10GBASER:
+ ret = mvebu_comphy_set_mode_10gbaser(phy);
break;
default:
return -ENOTSUPP;
@@ -782,8 +782,8 @@ static int mvebu_comphy_power_on(struct phy *phy)
lane->id);
fw_speed = COMPHY_FW_SPEED_3125;
break;
- case PHY_INTERFACE_MODE_10GKR:
- dev_dbg(priv->dev, "set lane %d to 10G-KR mode\n",
+ case PHY_INTERFACE_MODE_10GBASER:
+ dev_dbg(priv->dev, "set lane %d to 10GBASE-R mode\n",
lane->id);
fw_speed = COMPHY_FW_SPEED_103125;
break;
diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c
index ead06c6..12e71a3 100644
--- a/drivers/phy/motorola/phy-cpcap-usb.c
+++ b/drivers/phy/motorola/phy-cpcap-usb.c
@@ -115,7 +115,7 @@ struct cpcap_usb_ints_state {
enum cpcap_gpio_mode {
CPCAP_DM_DP,
CPCAP_MDM_RX_TX,
- CPCAP_UNKNOWN,
+ CPCAP_UNKNOWN_DISABLED, /* Seems to disable USB lines */
CPCAP_OTG_DM_DP,
};
@@ -134,6 +134,8 @@ struct cpcap_phy_ddata {
struct iio_channel *id;
struct regulator *vusb;
atomic_t active;
+ unsigned int vbus_provider:1;
+ unsigned int docked:1;
};
static bool cpcap_usb_vbus_valid(struct cpcap_phy_ddata *ddata)
@@ -207,6 +209,19 @@ static int cpcap_phy_get_ints_state(struct cpcap_phy_ddata *ddata,
static int cpcap_usb_set_uart_mode(struct cpcap_phy_ddata *ddata);
static int cpcap_usb_set_usb_mode(struct cpcap_phy_ddata *ddata);
+static void cpcap_usb_try_musb_mailbox(struct cpcap_phy_ddata *ddata,
+ enum musb_vbus_id_status status)
+{
+ int error;
+
+ error = musb_mailbox(status);
+ if (!error)
+ return;
+
+ dev_dbg(ddata->dev, "%s: musb_mailbox failed: %i\n",
+ __func__, error);
+}
+
static void cpcap_usb_detect(struct work_struct *work)
{
struct cpcap_phy_ddata *ddata;
@@ -220,16 +235,66 @@ static void cpcap_usb_detect(struct work_struct *work)
if (error)
return;
- if (s.id_ground) {
- dev_dbg(ddata->dev, "id ground, USB host mode\n");
+ vbus = cpcap_usb_vbus_valid(ddata);
+
+ /* We need to kick the VBUS as USB A-host */
+ if (s.id_ground && ddata->vbus_provider) {
+ dev_dbg(ddata->dev, "still in USB A-host mode, kicking VBUS\n");
+
+ cpcap_usb_try_musb_mailbox(ddata, MUSB_ID_GROUND);
+
+ error = regmap_update_bits(ddata->reg, CPCAP_REG_USBC3,
+ CPCAP_BIT_VBUSSTBY_EN |
+ CPCAP_BIT_VBUSEN_SPI,
+ CPCAP_BIT_VBUSEN_SPI);
+ if (error)
+ goto out_err;
+
+ return;
+ }
+
+ if (vbus && s.id_ground && ddata->docked) {
+ dev_dbg(ddata->dev, "still docked as A-host, signal ID down\n");
+
+ cpcap_usb_try_musb_mailbox(ddata, MUSB_ID_GROUND);
+
+ return;
+ }
+
+ /* No VBUS needed with docks */
+ if (vbus && s.id_ground && !ddata->vbus_provider) {
+ dev_dbg(ddata->dev, "connected to a dock\n");
+
+ ddata->docked = true;
+
error = cpcap_usb_set_usb_mode(ddata);
if (error)
goto out_err;
- error = musb_mailbox(MUSB_ID_GROUND);
+ cpcap_usb_try_musb_mailbox(ddata, MUSB_ID_GROUND);
+
+ /*
+ * Force check state again after musb has reoriented,
+ * otherwise devices won't enumerate after loading PHY
+ * driver.
+ */
+ schedule_delayed_work(&ddata->detect_work,
+ msecs_to_jiffies(1000));
+
+ return;
+ }
+
+ if (s.id_ground && !ddata->docked) {
+ dev_dbg(ddata->dev, "id ground, USB host mode\n");
+
+ ddata->vbus_provider = true;
+
+ error = cpcap_usb_set_usb_mode(ddata);
if (error)
goto out_err;
+ cpcap_usb_try_musb_mailbox(ddata, MUSB_ID_GROUND);
+
error = regmap_update_bits(ddata->reg, CPCAP_REG_USBC3,
CPCAP_BIT_VBUSSTBY_EN |
CPCAP_BIT_VBUSEN_SPI,
@@ -248,43 +313,26 @@ static void cpcap_usb_detect(struct work_struct *work)
vbus = cpcap_usb_vbus_valid(ddata);
+ /* Otherwise assume we're connected to a USB host */
if (vbus) {
- /* Are we connected to a docking station with vbus? */
- if (s.id_ground) {
- dev_dbg(ddata->dev, "connected to a dock\n");
-
- /* No VBUS needed with docks */
- error = cpcap_usb_set_usb_mode(ddata);
- if (error)
- goto out_err;
- error = musb_mailbox(MUSB_ID_GROUND);
- if (error)
- goto out_err;
-
- return;
- }
-
- /* Otherwise assume we're connected to a USB host */
dev_dbg(ddata->dev, "connected to USB host\n");
error = cpcap_usb_set_usb_mode(ddata);
if (error)
goto out_err;
- error = musb_mailbox(MUSB_VBUS_VALID);
- if (error)
- goto out_err;
+ cpcap_usb_try_musb_mailbox(ddata, MUSB_VBUS_VALID);
return;
}
+ ddata->vbus_provider = false;
+ ddata->docked = false;
+ cpcap_usb_try_musb_mailbox(ddata, MUSB_VBUS_OFF);
+
/* Default to debug UART mode */
error = cpcap_usb_set_uart_mode(ddata);
if (error)
goto out_err;
- error = musb_mailbox(MUSB_VBUS_OFF);
- if (error)
- goto out_err;
-
dev_dbg(ddata->dev, "set UART mode\n");
return;
@@ -376,7 +424,8 @@ static int cpcap_usb_set_uart_mode(struct cpcap_phy_ddata *ddata)
{
int error;
- error = cpcap_usb_gpio_set_mode(ddata, CPCAP_DM_DP);
+ /* Disable lines to prevent glitches from waking up mdm6600 */
+ error = cpcap_usb_gpio_set_mode(ddata, CPCAP_UNKNOWN_DISABLED);
if (error)
goto out_err;
@@ -403,6 +452,11 @@ static int cpcap_usb_set_uart_mode(struct cpcap_phy_ddata *ddata)
if (error)
goto out_err;
+ /* Enable UART mode */
+ error = cpcap_usb_gpio_set_mode(ddata, CPCAP_DM_DP);
+ if (error)
+ goto out_err;
+
return 0;
out_err:
@@ -415,7 +469,8 @@ static int cpcap_usb_set_usb_mode(struct cpcap_phy_ddata *ddata)
{
int error;
- error = cpcap_usb_gpio_set_mode(ddata, CPCAP_OTG_DM_DP);
+ /* Disable lines to prevent glitches from waking up mdm6600 */
+ error = cpcap_usb_gpio_set_mode(ddata, CPCAP_UNKNOWN_DISABLED);
if (error)
return error;
@@ -434,12 +489,6 @@ static int cpcap_usb_set_usb_mode(struct cpcap_phy_ddata *ddata)
if (error)
goto out_err;
- error = regmap_update_bits(ddata->reg, CPCAP_REG_USBC2,
- CPCAP_BIT_USBXCVREN,
- CPCAP_BIT_USBXCVREN);
- if (error)
- goto out_err;
-
error = regmap_update_bits(ddata->reg, CPCAP_REG_USBC3,
CPCAP_BIT_PU_SPI |
CPCAP_BIT_DMPD_SPI |
@@ -455,6 +504,11 @@ static int cpcap_usb_set_usb_mode(struct cpcap_phy_ddata *ddata)
if (error)
goto out_err;
+ /* Enable USB mode */
+ error = cpcap_usb_gpio_set_mode(ddata, CPCAP_OTG_DM_DP);
+ if (error)
+ goto out_err;
+
return 0;
out_err:
@@ -649,9 +703,7 @@ static int cpcap_usb_phy_remove(struct platform_device *pdev)
if (error)
dev_err(ddata->dev, "could not set UART mode\n");
- error = musb_mailbox(MUSB_VBUS_OFF);
- if (error)
- dev_err(ddata->dev, "could not set mailbox\n");
+ cpcap_usb_try_musb_mailbox(ddata, MUSB_VBUS_OFF);
usb_remove_phy(&ddata->phy);
cancel_delayed_work_sync(&ddata->detect_work);
diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c
index ee184d5..f20524f 100644
--- a/drivers/phy/motorola/phy-mapphone-mdm6600.c
+++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c
@@ -200,7 +200,7 @@ static void phy_mdm6600_status(struct work_struct *work)
struct phy_mdm6600 *ddata;
struct device *dev;
DECLARE_BITMAP(values, PHY_MDM6600_NR_STATUS_LINES);
- int error, i, val = 0;
+ int error;
ddata = container_of(work, struct phy_mdm6600, status_work.work);
dev = ddata->dev;
@@ -212,16 +212,11 @@ static void phy_mdm6600_status(struct work_struct *work)
if (error)
return;
- for (i = 0; i < PHY_MDM6600_NR_STATUS_LINES; i++) {
- val |= test_bit(i, values) << i;
- dev_dbg(ddata->dev, "XXX %s: i: %i values[i]: %i val: %i\n",
- __func__, i, test_bit(i, values), val);
- }
- ddata->status = values[0];
+ ddata->status = values[0] & ((1 << PHY_MDM6600_NR_STATUS_LINES) - 1);
dev_info(dev, "modem status: %i %s\n",
ddata->status,
- phy_mdm6600_status_name[ddata->status & 7]);
+ phy_mdm6600_status_name[ddata->status]);
complete(&ddata->ack);
}
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c
index 091e203..66f9172 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.c
@@ -66,7 +66,7 @@
/* QPHY_V3_PCS_MISC_CLAMP_ENABLE register bits */
#define CLAMP_EN BIT(0) /* enables i/o clamp_n */
-#define PHY_INIT_COMPLETE_TIMEOUT 1000
+#define PHY_INIT_COMPLETE_TIMEOUT 10000
#define POWER_DOWN_DELAY_US_MIN 10
#define POWER_DOWN_DELAY_US_MAX 11
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c
index 2b97fb1..9ca20c9 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c
@@ -603,6 +603,8 @@ static long inno_hdmi_phy_rk3228_clk_round_rate(struct clk_hw *hw,
{
const struct pre_pll_config *cfg = pre_pll_cfg_table;
+ rate = (rate / 1000) * 1000;
+
for (; cfg->pixclock != 0; cfg++)
if (cfg->pixclock == rate && !cfg->fracdiv)
break;
@@ -755,6 +757,8 @@ static long inno_hdmi_phy_rk3328_clk_round_rate(struct clk_hw *hw,
{
const struct pre_pll_config *cfg = pre_pll_cfg_table;
+ rate = (rate / 1000) * 1000;
+
for (; cfg->pixclock != 0; cfg++)
if (cfg->pixclock == rate)
break;
diff --git a/drivers/pinctrl/cirrus/Kconfig b/drivers/pinctrl/cirrus/Kconfig
index f1806fd..530426a 100644
--- a/drivers/pinctrl/cirrus/Kconfig
+++ b/drivers/pinctrl/cirrus/Kconfig
@@ -2,6 +2,7 @@
config PINCTRL_LOCHNAGAR
tristate "Cirrus Logic Lochnagar pinctrl driver"
depends on MFD_LOCHNAGAR
+ select GPIOLIB
select PINMUX
select PINCONF
select GENERIC_PINCONF
diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
index 44d7f50..d936e7a 100644
--- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
+++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
@@ -49,6 +49,7 @@
.padown_offset = SPT_PAD_OWN, \
.padcfglock_offset = SPT_PADCFGLOCK, \
.hostown_offset = SPT_HOSTSW_OWN, \
+ .is_offset = SPT_GPI_IS, \
.ie_offset = SPT_GPI_IE, \
.pin_base = (s), \
.npins = ((e) - (s) + 1), \
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
index 3c80828..bbc919b 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.c
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -441,6 +441,7 @@ static int meson_pinconf_get_drive_strength(struct meson_pinctrl *pc,
return ret;
meson_calc_reg_and_bit(bank, pin, REG_DS, ®, &bit);
+ bit = bit << 1;
ret = regmap_read(pc->reg_ds, reg, &val);
if (ret)
diff --git a/drivers/platform/chrome/wilco_ec/keyboard_leds.c b/drivers/platform/chrome/wilco_ec/keyboard_leds.c
index bb0edf5..5731d1b 100644
--- a/drivers/platform/chrome/wilco_ec/keyboard_leds.c
+++ b/drivers/platform/chrome/wilco_ec/keyboard_leds.c
@@ -73,13 +73,6 @@ static int send_kbbl_msg(struct wilco_ec_device *ec,
return ret;
}
- if (response->status) {
- dev_err(ec->dev,
- "EC reported failure sending keyboard LEDs command: %d",
- response->status);
- return -EIO;
- }
-
return 0;
}
@@ -87,6 +80,7 @@ static int set_kbbl(struct wilco_ec_device *ec, enum led_brightness brightness)
{
struct wilco_keyboard_leds_msg request;
struct wilco_keyboard_leds_msg response;
+ int ret;
memset(&request, 0, sizeof(request));
request.command = WILCO_EC_COMMAND_KBBL;
@@ -94,7 +88,18 @@ static int set_kbbl(struct wilco_ec_device *ec, enum led_brightness brightness)
request.mode = WILCO_KBBL_MODE_FLAG_PWM;
request.percent = brightness;
- return send_kbbl_msg(ec, &request, &response);
+ ret = send_kbbl_msg(ec, &request, &response);
+ if (ret < 0)
+ return ret;
+
+ if (response.status) {
+ dev_err(ec->dev,
+ "EC reported failure sending keyboard LEDs command: %d",
+ response.status);
+ return -EIO;
+ }
+
+ return 0;
}
static int kbbl_exist(struct wilco_ec_device *ec, bool *exists)
@@ -140,6 +145,13 @@ static int kbbl_init(struct wilco_ec_device *ec)
if (ret < 0)
return ret;
+ if (response.status) {
+ dev_err(ec->dev,
+ "EC reported failure sending keyboard LEDs command: %d",
+ response.status);
+ return -EIO;
+ }
+
if (response.mode & WILCO_KBBL_MODE_FLAG_PWM)
return response.percent;
diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index 9a5c9fd..5739a966 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -149,7 +149,7 @@ struct mlxbf_tmfifo_irq_info {
* @work: work struct for deferred process
* @timer: background timer
* @vring: Tx/Rx ring
- * @spin_lock: spin lock
+ * @spin_lock: Tx/Rx spin lock
* @is_ready: ready flag
*/
struct mlxbf_tmfifo {
@@ -164,7 +164,7 @@ struct mlxbf_tmfifo {
struct work_struct work;
struct timer_list timer;
struct mlxbf_tmfifo_vring *vring[2];
- spinlock_t spin_lock; /* spin lock */
+ spinlock_t spin_lock[2]; /* spin lock */
bool is_ready;
};
@@ -525,7 +525,7 @@ static void mlxbf_tmfifo_console_tx(struct mlxbf_tmfifo *fifo, int avail)
writeq(*(u64 *)&hdr, fifo->tx_base + MLXBF_TMFIFO_TX_DATA);
/* Use spin-lock to protect the 'cons->tx_buf'. */
- spin_lock_irqsave(&fifo->spin_lock, flags);
+ spin_lock_irqsave(&fifo->spin_lock[0], flags);
while (size > 0) {
addr = cons->tx_buf.buf + cons->tx_buf.tail;
@@ -552,7 +552,7 @@ static void mlxbf_tmfifo_console_tx(struct mlxbf_tmfifo *fifo, int avail)
}
}
- spin_unlock_irqrestore(&fifo->spin_lock, flags);
+ spin_unlock_irqrestore(&fifo->spin_lock[0], flags);
}
/* Rx/Tx one word in the descriptor buffer. */
@@ -731,9 +731,9 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring,
fifo->vring[is_rx] = NULL;
/* Notify upper layer that packet is done. */
- spin_lock_irqsave(&fifo->spin_lock, flags);
+ spin_lock_irqsave(&fifo->spin_lock[is_rx], flags);
vring_interrupt(0, vring->vq);
- spin_unlock_irqrestore(&fifo->spin_lock, flags);
+ spin_unlock_irqrestore(&fifo->spin_lock[is_rx], flags);
}
mlxbf_tmfifo_desc_done:
@@ -852,10 +852,10 @@ static bool mlxbf_tmfifo_virtio_notify(struct virtqueue *vq)
* worker handler.
*/
if (vring->vdev_id == VIRTIO_ID_CONSOLE) {
- spin_lock_irqsave(&fifo->spin_lock, flags);
+ spin_lock_irqsave(&fifo->spin_lock[0], flags);
tm_vdev = fifo->vdev[VIRTIO_ID_CONSOLE];
mlxbf_tmfifo_console_output(tm_vdev, vring);
- spin_unlock_irqrestore(&fifo->spin_lock, flags);
+ spin_unlock_irqrestore(&fifo->spin_lock[0], flags);
} else if (test_and_set_bit(MLXBF_TM_TX_LWM_IRQ,
&fifo->pend_events)) {
return true;
@@ -1189,7 +1189,8 @@ static int mlxbf_tmfifo_probe(struct platform_device *pdev)
if (!fifo)
return -ENOMEM;
- spin_lock_init(&fifo->spin_lock);
+ spin_lock_init(&fifo->spin_lock[0]);
+ spin_lock_init(&fifo->spin_lock[1]);
INIT_WORK(&fifo->work, mlxbf_tmfifo_work_handler);
mutex_init(&fifo->lock);
diff --git a/drivers/platform/mips/Kconfig b/drivers/platform/mips/Kconfig
index f4d0a86..5e77b0d 100644
--- a/drivers/platform/mips/Kconfig
+++ b/drivers/platform/mips/Kconfig
@@ -18,7 +18,7 @@
config CPU_HWMON
tristate "Loongson-3 CPU HWMon Driver"
- depends on CONFIG_MACH_LOONGSON64
+ depends on MACH_LOONGSON64
select HWMON
default y
help
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 821b08e..982f0cc 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -512,13 +512,7 @@ static void kbd_led_update(struct asus_wmi *asus)
{
int ctrl_param = 0;
- /*
- * bits 0-2: level
- * bit 7: light on/off
- */
- if (asus->kbd_led_wk > 0)
- ctrl_param = 0x80 | (asus->kbd_led_wk & 0x7F);
-
+ ctrl_param = 0x80 | (asus->kbd_led_wk & 0x7F);
asus_wmi_set_devstate(ASUS_WMI_DEVID_KBD_BACKLIGHT, ctrl_param, NULL);
}
diff --git a/drivers/platform/x86/gpd-pocket-fan.c b/drivers/platform/x86/gpd-pocket-fan.c
index be85ed9..b471b86 100644
--- a/drivers/platform/x86/gpd-pocket-fan.c
+++ b/drivers/platform/x86/gpd-pocket-fan.c
@@ -16,17 +16,27 @@
#define MAX_SPEED 3
-static int temp_limits[3] = { 55000, 60000, 65000 };
+#define TEMP_LIMIT0_DEFAULT 55000
+#define TEMP_LIMIT1_DEFAULT 60000
+#define TEMP_LIMIT2_DEFAULT 65000
+
+#define HYSTERESIS_DEFAULT 3000
+
+#define SPEED_ON_AC_DEFAULT 2
+
+static int temp_limits[3] = {
+ TEMP_LIMIT0_DEFAULT, TEMP_LIMIT1_DEFAULT, TEMP_LIMIT2_DEFAULT,
+};
module_param_array(temp_limits, int, NULL, 0444);
MODULE_PARM_DESC(temp_limits,
"Millicelsius values above which the fan speed increases");
-static int hysteresis = 3000;
+static int hysteresis = HYSTERESIS_DEFAULT;
module_param(hysteresis, int, 0444);
MODULE_PARM_DESC(hysteresis,
"Hysteresis in millicelsius before lowering the fan speed");
-static int speed_on_ac = 2;
+static int speed_on_ac = SPEED_ON_AC_DEFAULT;
module_param(speed_on_ac, int, 0444);
MODULE_PARM_DESC(speed_on_ac,
"minimum fan speed to allow when system is powered by AC");
@@ -117,21 +127,24 @@ static int gpd_pocket_fan_probe(struct platform_device *pdev)
int i;
for (i = 0; i < ARRAY_SIZE(temp_limits); i++) {
- if (temp_limits[i] < 40000 || temp_limits[i] > 70000) {
+ if (temp_limits[i] < 20000 || temp_limits[i] > 90000) {
dev_err(&pdev->dev, "Invalid temp-limit %d (must be between 40000 and 70000)\n",
temp_limits[i]);
- return -EINVAL;
+ temp_limits[0] = TEMP_LIMIT0_DEFAULT;
+ temp_limits[1] = TEMP_LIMIT1_DEFAULT;
+ temp_limits[2] = TEMP_LIMIT2_DEFAULT;
+ break;
}
}
if (hysteresis < 1000 || hysteresis > 10000) {
dev_err(&pdev->dev, "Invalid hysteresis %d (must be between 1000 and 10000)\n",
hysteresis);
- return -EINVAL;
+ hysteresis = HYSTERESIS_DEFAULT;
}
if (speed_on_ac < 0 || speed_on_ac > MAX_SPEED) {
dev_err(&pdev->dev, "Invalid speed_on_ac %d (must be between 0 and 3)\n",
speed_on_ac);
- return -EINVAL;
+ speed_on_ac = SPEED_ON_AC_DEFAULT;
}
fan = devm_kzalloc(&pdev->dev, sizeof(*fan), GFP_KERNEL);
diff --git a/drivers/platform/x86/intel_ips.h b/drivers/platform/x86/intel_ips.h
index 512ad23..35ed971 100644
--- a/drivers/platform/x86/intel_ips.h
+++ b/drivers/platform/x86/intel_ips.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2010 Intel Corporation
*/
diff --git a/drivers/platform/x86/intel_pmc_core.h b/drivers/platform/x86/intel_pmc_core.h
index fdee577..8203ae3 100644
--- a/drivers/platform/x86/intel_pmc_core.h
+++ b/drivers/platform/x86/intel_pmc_core.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Intel Core SoC Power Management Controller Header File
*
diff --git a/drivers/platform/x86/intel_pmc_core_pltdrv.c b/drivers/platform/x86/intel_pmc_core_pltdrv.c
index 6fe829f..e1266f5 100644
--- a/drivers/platform/x86/intel_pmc_core_pltdrv.c
+++ b/drivers/platform/x86/intel_pmc_core_pltdrv.c
@@ -44,6 +44,8 @@ static const struct x86_cpu_id intel_pmc_core_platform_ids[] = {
INTEL_CPU_FAM6(KABYLAKE, pmc_core_device),
INTEL_CPU_FAM6(CANNONLAKE_L, pmc_core_device),
INTEL_CPU_FAM6(ICELAKE_L, pmc_core_device),
+ INTEL_CPU_FAM6(COMETLAKE, pmc_core_device),
+ INTEL_CPU_FAM6(COMETLAKE_L, pmc_core_device),
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_pmc_core_platform_ids);
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index a67701ed..2e5b6a6 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -1295,6 +1295,9 @@ struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv)
struct cpuinfo_x86 *c = &cpu_data(cpu);
int ret;
+ if (!rapl_defaults)
+ return ERR_PTR(-ENODEV);
+
rp = kzalloc(sizeof(struct rapl_package), GFP_KERNEL);
if (!rp)
return ERR_PTR(-ENOMEM);
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index c382158f5..475c60d 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -56,20 +56,6 @@
To compile this driver as a module, choose M here: the module
will be called ptp-qoriq.
-config PTP_1588_CLOCK_IXP46X
- tristate "Intel IXP46x as PTP clock"
- depends on IXP4XX_ETH
- depends on PTP_1588_CLOCK
- default y
- help
- This driver adds support for using the IXP46X as a PTP
- clock. This clock is only useful if your PTP programs are
- getting hardware time stamps on the PTP Ethernet packets
- using the SO_TIMESTAMPING API.
-
- To compile this driver as a module, choose M here: the module
- will be called ptp_ixp46x.
-
comment "Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks."
depends on PHYLIB=n || NETWORK_PHY_TIMESTAMPING=n
diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile
index 3fb91be..8c83033 100644
--- a/drivers/ptp/Makefile
+++ b/drivers/ptp/Makefile
@@ -7,10 +7,9 @@
obj-$(CONFIG_PTP_1588_CLOCK) += ptp.o
obj-$(CONFIG_PTP_1588_CLOCK_DTE) += ptp_dte.o
obj-$(CONFIG_PTP_1588_CLOCK_INES) += ptp_ines.o
-obj-$(CONFIG_PTP_1588_CLOCK_IXP46X) += ptp_ixp46x.o
obj-$(CONFIG_PTP_1588_CLOCK_PCH) += ptp_pch.o
obj-$(CONFIG_PTP_1588_CLOCK_KVM) += ptp_kvm.o
obj-$(CONFIG_PTP_1588_CLOCK_QORIQ) += ptp-qoriq.o
ptp-qoriq-y += ptp_qoriq.o
ptp-qoriq-$(CONFIG_DEBUG_FS) += ptp_qoriq_debugfs.o
-obj-$(CONFIG_PTP_1588_CLOCK_IDTCM) += ptp_clockmatrix.o
\ No newline at end of file
+obj-$(CONFIG_PTP_1588_CLOCK_IDTCM) += ptp_clockmatrix.o
diff --git a/drivers/ptp/idt8a340_reg.h b/drivers/ptp/idt8a340_reg.h
index 9263bc3..69eedda 100644
--- a/drivers/ptp/idt8a340_reg.h
+++ b/drivers/ptp/idt8a340_reg.h
@@ -77,6 +77,8 @@
#define JTAG_DEVICE_ID 0x001c
#define PRODUCT_ID 0x001e
+#define OTP_SCSR_CONFIG_SELECT 0x0022
+
#define STATUS 0xc03c
#define USER_GPIO0_TO_7_STATUS 0x008a
#define USER_GPIO8_TO_15_STATUS 0x008b
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index da97a5b..ac1f2bf 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -170,6 +170,7 @@ static void ptp_clock_release(struct device *dev)
{
struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev);
+ ptp_cleanup_pin_groups(ptp);
mutex_destroy(&ptp->tsevq_mux);
mutex_destroy(&ptp->pincfg_mux);
ida_simple_remove(&ptp_clocks_map, ptp->index);
@@ -302,9 +303,8 @@ int ptp_clock_unregister(struct ptp_clock *ptp)
if (ptp->pps_source)
pps_unregister_source(ptp->pps_source);
- ptp_cleanup_pin_groups(ptp);
-
posix_clock_unregister(&ptp->clock);
+
return 0;
}
EXPORT_SYMBOL(ptp_clock_unregister);
diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c
index e858367..032e112 100644
--- a/drivers/ptp/ptp_clockmatrix.c
+++ b/drivers/ptp/ptp_clockmatrix.c
@@ -405,6 +405,7 @@ static int _idtcm_set_dpll_tod(struct idtcm_channel *channel,
if (wr_trig == HW_TOD_WR_TRIG_SEL_MSB) {
if (idtcm->calculate_overhead_flag) {
+ /* Assumption: I2C @ 400KHz */
total_overhead_ns = ktime_to_ns(ktime_get_raw()
- idtcm->start_time)
+ idtcm->tod_write_overhead_ns
@@ -596,44 +597,7 @@ static int idtcm_state_machine_reset(struct idtcm *idtcm)
static int idtcm_read_hw_rev_id(struct idtcm *idtcm, u8 *hw_rev_id)
{
- return idtcm_read(idtcm,
- GENERAL_STATUS,
- HW_REV_ID,
- hw_rev_id,
- sizeof(u8));
-}
-
-static int idtcm_read_bond_id(struct idtcm *idtcm, u8 *bond_id)
-{
- return idtcm_read(idtcm,
- GENERAL_STATUS,
- BOND_ID,
- bond_id,
- sizeof(u8));
-}
-
-static int idtcm_read_hw_csr_id(struct idtcm *idtcm, u16 *hw_csr_id)
-{
- int err;
- u8 buf[2] = {0};
-
- err = idtcm_read(idtcm, GENERAL_STATUS, HW_CSR_ID, buf, sizeof(buf));
-
- *hw_csr_id = (buf[1] << 8) | buf[0];
-
- return err;
-}
-
-static int idtcm_read_hw_irq_id(struct idtcm *idtcm, u16 *hw_irq_id)
-{
- int err;
- u8 buf[2] = {0};
-
- err = idtcm_read(idtcm, GENERAL_STATUS, HW_IRQ_ID, buf, sizeof(buf));
-
- *hw_irq_id = (buf[1] << 8) | buf[0];
-
- return err;
+ return idtcm_read(idtcm, HW_REVISION, REV_ID, hw_rev_id, sizeof(u8));
}
static int idtcm_read_product_id(struct idtcm *idtcm, u16 *product_id)
@@ -674,20 +638,11 @@ static int idtcm_read_hotfix_release(struct idtcm *idtcm, u8 *hotfix)
sizeof(u8));
}
-static int idtcm_read_pipeline(struct idtcm *idtcm, u32 *pipeline)
+static int idtcm_read_otp_scsr_config_select(struct idtcm *idtcm,
+ u8 *config_select)
{
- int err;
- u8 buf[4] = {0};
-
- err = idtcm_read(idtcm,
- GENERAL_STATUS,
- PIPELINE_ID,
- &buf[0],
- sizeof(buf));
-
- *pipeline = (buf[3] << 24) | (buf[2] << 16) | (buf[1] << 8) | buf[0];
-
- return err;
+ return idtcm_read(idtcm, GENERAL_STATUS, OTP_SCSR_CONFIG_SELECT,
+ config_select, sizeof(u8));
}
static int process_pll_mask(struct idtcm *idtcm, u32 addr, u8 val, u8 *mask)
@@ -1078,28 +1033,22 @@ static void idtcm_display_version_info(struct idtcm *idtcm)
u8 major;
u8 minor;
u8 hotfix;
- u32 pipeline;
u16 product_id;
- u16 csr_id;
- u16 irq_id;
u8 hw_rev_id;
- u8 bond_id;
+ u8 config_select;
+ char *fmt = "%d.%d.%d, Id: 0x%04x HW Rev: %d OTP Config Select: %d\n";
idtcm_read_major_release(idtcm, &major);
idtcm_read_minor_release(idtcm, &minor);
idtcm_read_hotfix_release(idtcm, &hotfix);
- idtcm_read_pipeline(idtcm, &pipeline);
idtcm_read_product_id(idtcm, &product_id);
idtcm_read_hw_rev_id(idtcm, &hw_rev_id);
- idtcm_read_bond_id(idtcm, &bond_id);
- idtcm_read_hw_csr_id(idtcm, &csr_id);
- idtcm_read_hw_irq_id(idtcm, &irq_id);
- dev_info(&idtcm->client->dev, "Version: %d.%d.%d, Pipeline %u\t"
- "0x%04x, Rev %d, Bond %d, CSR %d, IRQ %d\n",
- major, minor, hotfix, pipeline,
- product_id, hw_rev_id, bond_id, csr_id, irq_id);
+ idtcm_read_otp_scsr_config_select(idtcm, &config_select);
+
+ dev_info(&idtcm->client->dev, fmt, major, minor, hotfix,
+ product_id, hw_rev_id, config_select);
}
static const struct ptp_clock_info idtcm_caps = {
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index 989506b..16f0c85 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -413,10 +413,13 @@ static int axp20x_set_ramp_delay(struct regulator_dev *rdev, int ramp)
int i;
for (i = 0; i < rate_count; i++) {
- if (ramp <= slew_rates[i])
- cfg = AXP20X_DCDC2_LDO3_V_RAMP_LDO3_RATE(i);
- else
+ if (ramp > slew_rates[i])
break;
+
+ if (id == AXP20X_DCDC2)
+ cfg = AXP20X_DCDC2_LDO3_V_RAMP_DCDC2_RATE(i);
+ else
+ cfg = AXP20X_DCDC2_LDO3_V_RAMP_LDO3_RATE(i);
}
if (cfg == 0xff) {
@@ -605,7 +608,7 @@ static const struct regulator_desc axp22x_regulators[] = {
AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO1_MASK),
AXP_DESC(AXP22X, ELDO2, "eldo2", "eldoin", 700, 3300, 100,
AXP22X_ELDO2_V_OUT, AXP22X_ELDO2_V_OUT_MASK,
- AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO1_MASK),
+ AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO2_MASK),
AXP_DESC(AXP22X, ELDO3, "eldo3", "eldoin", 700, 3300, 100,
AXP22X_ELDO3_V_OUT, AXP22X_ELDO3_V_OUT_MASK,
AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO3_MASK),
diff --git a/drivers/regulator/bd70528-regulator.c b/drivers/regulator/bd70528-regulator.c
index ec76402..5bf8a2d 100644
--- a/drivers/regulator/bd70528-regulator.c
+++ b/drivers/regulator/bd70528-regulator.c
@@ -101,7 +101,6 @@ static const struct regulator_ops bd70528_ldo_ops = {
.set_voltage_sel = regulator_set_voltage_sel_regmap,
.get_voltage_sel = regulator_get_voltage_sel_regmap,
.set_voltage_time_sel = regulator_set_voltage_time_sel,
- .set_ramp_delay = bd70528_set_ramp_delay,
};
static const struct regulator_ops bd70528_led_ops = {
diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c
index df2829d..2ecd875 100644
--- a/drivers/rtc/rtc-mc146818-lib.c
+++ b/drivers/rtc/rtc-mc146818-lib.c
@@ -172,20 +172,7 @@ int mc146818_set_time(struct rtc_time *time)
save_control = CMOS_READ(RTC_CONTROL);
CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
-
-#ifdef CONFIG_X86
- if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
- boot_cpu_data.x86 == 0x17) ||
- boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
- CMOS_WRITE((save_freq_select & (~RTC_DIV_RESET2)),
- RTC_FREQ_SELECT);
- save_freq_select &= ~RTC_DIV_RESET2;
- } else
- CMOS_WRITE((save_freq_select | RTC_DIV_RESET2),
- RTC_FREQ_SELECT);
-#else
- CMOS_WRITE((save_freq_select | RTC_DIV_RESET2), RTC_FREQ_SELECT);
-#endif
+ CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
#ifdef CONFIG_MACH_DECSTATION
CMOS_WRITE(real_yrs, RTC_DEC_YEAR);
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index 5249fc9..9135e21 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -47,7 +47,7 @@ static irqreturn_t mtk_rtc_irq_handler_thread(int irq, void *data)
irqen = irqsta & ~RTC_IRQ_EN_AL;
mutex_lock(&rtc->lock);
if (regmap_write(rtc->regmap, rtc->addr_base + RTC_IRQ_EN,
- irqen) < 0)
+ irqen) == 0)
mtk_rtc_write_trigger(rtc);
mutex_unlock(&rtc->lock);
@@ -169,12 +169,12 @@ static int mtk_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
alm->pending = !!(pdn2 & RTC_PDN2_PWRON_ALARM);
mutex_unlock(&rtc->lock);
- tm->tm_sec = data[RTC_OFFSET_SEC];
- tm->tm_min = data[RTC_OFFSET_MIN];
- tm->tm_hour = data[RTC_OFFSET_HOUR];
- tm->tm_mday = data[RTC_OFFSET_DOM];
- tm->tm_mon = data[RTC_OFFSET_MTH];
- tm->tm_year = data[RTC_OFFSET_YEAR];
+ tm->tm_sec = data[RTC_OFFSET_SEC] & RTC_AL_SEC_MASK;
+ tm->tm_min = data[RTC_OFFSET_MIN] & RTC_AL_MIN_MASK;
+ tm->tm_hour = data[RTC_OFFSET_HOUR] & RTC_AL_HOU_MASK;
+ tm->tm_mday = data[RTC_OFFSET_DOM] & RTC_AL_DOM_MASK;
+ tm->tm_mon = data[RTC_OFFSET_MTH] & RTC_AL_MTH_MASK;
+ tm->tm_year = data[RTC_OFFSET_YEAR] & RTC_AL_YEA_MASK;
tm->tm_year += RTC_MIN_YEAR_OFFSET;
tm->tm_mon--;
@@ -195,14 +195,25 @@ static int mtk_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
tm->tm_year -= RTC_MIN_YEAR_OFFSET;
tm->tm_mon++;
- data[RTC_OFFSET_SEC] = tm->tm_sec;
- data[RTC_OFFSET_MIN] = tm->tm_min;
- data[RTC_OFFSET_HOUR] = tm->tm_hour;
- data[RTC_OFFSET_DOM] = tm->tm_mday;
- data[RTC_OFFSET_MTH] = tm->tm_mon;
- data[RTC_OFFSET_YEAR] = tm->tm_year;
-
mutex_lock(&rtc->lock);
+ ret = regmap_bulk_read(rtc->regmap, rtc->addr_base + RTC_AL_SEC,
+ data, RTC_OFFSET_COUNT);
+ if (ret < 0)
+ goto exit;
+
+ data[RTC_OFFSET_SEC] = ((data[RTC_OFFSET_SEC] & ~(RTC_AL_SEC_MASK)) |
+ (tm->tm_sec & RTC_AL_SEC_MASK));
+ data[RTC_OFFSET_MIN] = ((data[RTC_OFFSET_MIN] & ~(RTC_AL_MIN_MASK)) |
+ (tm->tm_min & RTC_AL_MIN_MASK));
+ data[RTC_OFFSET_HOUR] = ((data[RTC_OFFSET_HOUR] & ~(RTC_AL_HOU_MASK)) |
+ (tm->tm_hour & RTC_AL_HOU_MASK));
+ data[RTC_OFFSET_DOM] = ((data[RTC_OFFSET_DOM] & ~(RTC_AL_DOM_MASK)) |
+ (tm->tm_mday & RTC_AL_DOM_MASK));
+ data[RTC_OFFSET_MTH] = ((data[RTC_OFFSET_MTH] & ~(RTC_AL_MTH_MASK)) |
+ (tm->tm_mon & RTC_AL_MTH_MASK));
+ data[RTC_OFFSET_YEAR] = ((data[RTC_OFFSET_YEAR] & ~(RTC_AL_YEA_MASK)) |
+ (tm->tm_year & RTC_AL_YEA_MASK));
+
if (alm->enabled) {
ret = regmap_bulk_write(rtc->regmap,
rtc->addr_base + RTC_AL_SEC,
diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c
index 8dcd20b..852f5f3 100644
--- a/drivers/rtc/rtc-sun6i.c
+++ b/drivers/rtc/rtc-sun6i.c
@@ -379,6 +379,22 @@ static void __init sun50i_h6_rtc_clk_init(struct device_node *node)
CLK_OF_DECLARE_DRIVER(sun50i_h6_rtc_clk, "allwinner,sun50i-h6-rtc",
sun50i_h6_rtc_clk_init);
+/*
+ * The R40 user manual is self-conflicting on whether the prescaler is
+ * fixed or configurable. The clock diagram shows it as fixed, but there
+ * is also a configurable divider in the RTC block.
+ */
+static const struct sun6i_rtc_clk_data sun8i_r40_rtc_data = {
+ .rc_osc_rate = 16000000,
+ .fixed_prescaler = 512,
+};
+static void __init sun8i_r40_rtc_clk_init(struct device_node *node)
+{
+ sun6i_rtc_clk_init(node, &sun8i_r40_rtc_data);
+}
+CLK_OF_DECLARE_DRIVER(sun8i_r40_rtc_clk, "allwinner,sun8i-r40-rtc",
+ sun8i_r40_rtc_clk_init);
+
static const struct sun6i_rtc_clk_data sun8i_v3_rtc_data = {
.rc_osc_rate = 32000,
.has_out_clk = 1,
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index a191506..5256e3c 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -793,8 +793,6 @@ static int ap_device_probe(struct device *dev)
drvres = ap_drv->flags & AP_DRIVER_FLAG_DEFAULT;
if (!!devres != !!drvres)
return -ENODEV;
- /* (re-)init queue's state machine */
- ap_queue_reinit_state(to_ap_queue(dev));
}
/* Add queue/card to list of active queues/cards */
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 433b7b6..bb35ba4 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -261,7 +261,7 @@ void ap_queue_prepare_remove(struct ap_queue *aq);
void ap_queue_remove(struct ap_queue *aq);
void ap_queue_suspend(struct ap_device *ap_dev);
void ap_queue_resume(struct ap_device *ap_dev);
-void ap_queue_reinit_state(struct ap_queue *aq);
+void ap_queue_init_state(struct ap_queue *aq);
struct ap_card *ap_card_create(int id, int queue_depth, int raw_device_type,
int comp_device_type, unsigned int functions);
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index dad2be3..37c3bdc 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -638,7 +638,7 @@ struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type)
aq->ap_dev.device.type = &ap_queue_type;
aq->ap_dev.device_type = device_type;
aq->qid = qid;
- aq->state = AP_STATE_RESET_START;
+ aq->state = AP_STATE_UNBOUND;
aq->interrupt = AP_INTR_DISABLED;
spin_lock_init(&aq->lock);
INIT_LIST_HEAD(&aq->list);
@@ -771,10 +771,11 @@ void ap_queue_remove(struct ap_queue *aq)
spin_unlock_bh(&aq->lock);
}
-void ap_queue_reinit_state(struct ap_queue *aq)
+void ap_queue_init_state(struct ap_queue *aq)
{
spin_lock_bh(&aq->lock);
aq->state = AP_STATE_RESET_START;
ap_wait(ap_sm_event(aq, AP_EVENT_POLL));
spin_unlock_bh(&aq->lock);
}
+EXPORT_SYMBOL(ap_queue_init_state);
diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c
index c1db64a..110fe9d 100644
--- a/drivers/s390/crypto/zcrypt_ccamisc.c
+++ b/drivers/s390/crypto/zcrypt_ccamisc.c
@@ -1037,8 +1037,8 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain,
prepparm = (struct iprepparm *) prepcblk->rpl_parmb;
/* do some plausibility checks on the key block */
- if (prepparm->kb.len < 120 + 5 * sizeof(uint16_t) ||
- prepparm->kb.len > 136 + 5 * sizeof(uint16_t)) {
+ if (prepparm->kb.len < 120 + 3 * sizeof(uint16_t) ||
+ prepparm->kb.len > 136 + 3 * sizeof(uint16_t)) {
DEBUG_ERR("%s reply with invalid or unknown key block\n",
__func__);
rc = -EIO;
diff --git a/drivers/s390/crypto/zcrypt_cex2a.c b/drivers/s390/crypto/zcrypt_cex2a.c
index c50f3e8..7cbb384 100644
--- a/drivers/s390/crypto/zcrypt_cex2a.c
+++ b/drivers/s390/crypto/zcrypt_cex2a.c
@@ -175,6 +175,7 @@ static int zcrypt_cex2a_queue_probe(struct ap_device *ap_dev)
zq->queue = aq;
zq->online = 1;
atomic_set(&zq->load, 0);
+ ap_queue_init_state(aq);
ap_queue_init_reply(aq, &zq->reply);
aq->request_timeout = CEX2A_CLEANUP_TIME,
aq->private = zq;
diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c
index 35c7c66..c78c0d1 100644
--- a/drivers/s390/crypto/zcrypt_cex2c.c
+++ b/drivers/s390/crypto/zcrypt_cex2c.c
@@ -220,6 +220,7 @@ static int zcrypt_cex2c_queue_probe(struct ap_device *ap_dev)
zq->queue = aq;
zq->online = 1;
atomic_set(&zq->load, 0);
+ ap_rapq(aq->qid);
rc = zcrypt_cex2c_rng_supported(aq);
if (rc < 0) {
zcrypt_queue_free(zq);
@@ -231,6 +232,7 @@ static int zcrypt_cex2c_queue_probe(struct ap_device *ap_dev)
else
zq->ops = zcrypt_msgtype(MSGTYPE06_NAME,
MSGTYPE06_VARIANT_NORNG);
+ ap_queue_init_state(aq);
ap_queue_init_reply(aq, &zq->reply);
aq->request_timeout = CEX2C_CLEANUP_TIME;
aq->private = zq;
diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c
index 442e3d6..6fabc90 100644
--- a/drivers/s390/crypto/zcrypt_cex4.c
+++ b/drivers/s390/crypto/zcrypt_cex4.c
@@ -381,6 +381,7 @@ static int zcrypt_cex4_queue_probe(struct ap_device *ap_dev)
zq->queue = aq;
zq->online = 1;
atomic_set(&zq->load, 0);
+ ap_queue_init_state(aq);
ap_queue_init_reply(aq, &zq->reply);
aq->request_timeout = CEX4_CLEANUP_TIME,
aq->private = zq;
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 7c37e94..9575a62 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -558,7 +558,6 @@ enum qeth_channel_states {
*/
enum qeth_card_states {
CARD_STATE_DOWN,
- CARD_STATE_HARDSETUP,
CARD_STATE_SOFTSETUP,
};
@@ -608,6 +607,8 @@ struct qeth_cmd_buffer {
long timeout;
unsigned char *data;
void (*finalize)(struct qeth_card *card, struct qeth_cmd_buffer *iob);
+ bool (*match)(struct qeth_cmd_buffer *iob,
+ struct qeth_cmd_buffer *reply);
void (*callback)(struct qeth_card *card, struct qeth_cmd_buffer *iob,
unsigned int data_length);
int rc;
@@ -618,6 +619,14 @@ static inline void qeth_get_cmd(struct qeth_cmd_buffer *iob)
refcount_inc(&iob->ref_count);
}
+static inline struct qeth_ipa_cmd *__ipa_reply(struct qeth_cmd_buffer *iob)
+{
+ if (!IS_IPA(iob->data))
+ return NULL;
+
+ return (struct qeth_ipa_cmd *) PDU_ENCAPSULATION(iob->data);
+}
+
static inline struct qeth_ipa_cmd *__ipa_cmd(struct qeth_cmd_buffer *iob)
{
return (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE);
@@ -727,11 +736,10 @@ struct qeth_osn_info {
struct qeth_discipline {
const struct device_type *devtype;
- int (*recover)(void *ptr);
int (*setup) (struct ccwgroup_device *);
void (*remove) (struct ccwgroup_device *);
- int (*set_online) (struct ccwgroup_device *);
- int (*set_offline) (struct ccwgroup_device *);
+ int (*set_online)(struct qeth_card *card);
+ void (*set_offline)(struct qeth_card *card);
int (*do_ioctl)(struct net_device *dev, struct ifreq *rq, int cmd);
int (*control_event_handler)(struct qeth_card *card,
struct qeth_ipa_cmd *cmd);
@@ -987,14 +995,11 @@ struct net_device *qeth_clone_netdev(struct net_device *orig);
struct qeth_card *qeth_get_card_by_busid(char *bus_id);
void qeth_set_allowed_threads(struct qeth_card *, unsigned long , int);
int qeth_threads_running(struct qeth_card *, unsigned long);
-int qeth_do_run_thread(struct qeth_card *, unsigned long);
-void qeth_clear_thread_start_bit(struct qeth_card *, unsigned long);
-void qeth_clear_thread_running_bit(struct qeth_card *, unsigned long);
int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok);
int qeth_stop_channel(struct qeth_channel *channel);
+int qeth_set_offline(struct qeth_card *card, bool resetting);
void qeth_print_status_message(struct qeth_card *);
-int qeth_init_qdio_queues(struct qeth_card *);
int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *,
int (*reply_cb)
(struct qeth_card *, struct qeth_reply *, unsigned long),
@@ -1027,7 +1032,9 @@ void qeth_setadp_promisc_mode(struct qeth_card *card, bool enable);
int qeth_setadpparms_change_macaddr(struct qeth_card *);
void qeth_tx_timeout(struct net_device *, unsigned int txqueue);
void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob,
- u16 cmd_length);
+ u16 cmd_length,
+ bool (*match)(struct qeth_cmd_buffer *iob,
+ struct qeth_cmd_buffer *reply));
int qeth_query_switch_attributes(struct qeth_card *card,
struct qeth_switch_info *sw_info);
int qeth_query_card_info(struct qeth_card *card,
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index c19cc39..9639938 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -247,9 +247,6 @@ int qeth_realloc_buffer_pool(struct qeth_card *card, int bufcnt)
{
QETH_CARD_TEXT(card, 2, "realcbp");
- if (card->state != CARD_STATE_DOWN)
- return -EPERM;
-
/* TODO: steel/add buffers from/to a running card's buffer pool (?) */
qeth_clear_working_pool_list(card);
qeth_free_buffer_pool(card);
@@ -748,8 +745,8 @@ static void qeth_issue_next_read_cb(struct qeth_card *card,
goto out;
}
- if (IS_IPA(iob->data)) {
- cmd = (struct qeth_ipa_cmd *) PDU_ENCAPSULATION(iob->data);
+ cmd = __ipa_reply(iob);
+ if (cmd) {
cmd = qeth_check_ipa_data(card, cmd);
if (!cmd)
goto out;
@@ -758,17 +755,12 @@ static void qeth_issue_next_read_cb(struct qeth_card *card,
card->osn_info.assist_cb(card->dev, cmd);
goto out;
}
- } else {
- /* non-IPA commands should only flow during initialization */
- if (card->state != CARD_STATE_DOWN)
- goto out;
}
/* match against pending cmd requests */
spin_lock_irqsave(&card->lock, flags);
list_for_each_entry(tmp, &card->cmd_waiter_list, list) {
- if (!IS_IPA(tmp->data) ||
- __ipa_cmd(tmp)->hdr.seqno == cmd->hdr.seqno) {
+ if (tmp->match && tmp->match(tmp, iob)) {
request = tmp;
/* take the object outside the lock */
qeth_get_cmd(request);
@@ -823,7 +815,8 @@ static int qeth_set_thread_start_bit(struct qeth_card *card,
return 0;
}
-void qeth_clear_thread_start_bit(struct qeth_card *card, unsigned long thread)
+static void qeth_clear_thread_start_bit(struct qeth_card *card,
+ unsigned long thread)
{
unsigned long flags;
@@ -832,9 +825,9 @@ void qeth_clear_thread_start_bit(struct qeth_card *card, unsigned long thread)
spin_unlock_irqrestore(&card->thread_mask_lock, flags);
wake_up(&card->wait_q);
}
-EXPORT_SYMBOL_GPL(qeth_clear_thread_start_bit);
-void qeth_clear_thread_running_bit(struct qeth_card *card, unsigned long thread)
+static void qeth_clear_thread_running_bit(struct qeth_card *card,
+ unsigned long thread)
{
unsigned long flags;
@@ -843,7 +836,6 @@ void qeth_clear_thread_running_bit(struct qeth_card *card, unsigned long thread)
spin_unlock_irqrestore(&card->thread_mask_lock, flags);
wake_up_all(&card->wait_q);
}
-EXPORT_SYMBOL_GPL(qeth_clear_thread_running_bit);
static int __qeth_do_run_thread(struct qeth_card *card, unsigned long thread)
{
@@ -864,7 +856,7 @@ static int __qeth_do_run_thread(struct qeth_card *card, unsigned long thread)
return rc;
}
-int qeth_do_run_thread(struct qeth_card *card, unsigned long thread)
+static int qeth_do_run_thread(struct qeth_card *card, unsigned long thread)
{
int rc = 0;
@@ -872,7 +864,6 @@ int qeth_do_run_thread(struct qeth_card *card, unsigned long thread)
(rc = __qeth_do_run_thread(card, thread)) >= 0);
return rc;
}
-EXPORT_SYMBOL_GPL(qeth_do_run_thread);
void qeth_schedule_recovery(struct qeth_card *card)
{
@@ -880,7 +871,6 @@ void qeth_schedule_recovery(struct qeth_card *card)
if (qeth_set_thread_start_bit(card, QETH_RECOVER_THREAD) == 0)
schedule_work(&card->kernel_thread_starter);
}
-EXPORT_SYMBOL_GPL(qeth_schedule_recovery);
static int qeth_get_problem(struct qeth_card *card, struct ccw_device *cdev,
struct irb *irb)
@@ -1287,6 +1277,7 @@ static int qeth_do_start_thread(struct qeth_card *card, unsigned long thread)
return rc;
}
+static int qeth_do_reset(void *data);
static void qeth_start_kernel_thread(struct work_struct *work)
{
struct task_struct *ts;
@@ -1298,8 +1289,7 @@ static void qeth_start_kernel_thread(struct work_struct *work)
card->write.state != CH_STATE_UP)
return;
if (qeth_do_start_thread(card, QETH_RECOVER_THREAD)) {
- ts = kthread_run(card->discipline->recover, (void *)card,
- "qeth_recover");
+ ts = kthread_run(qeth_do_reset, card, "qeth_recover");
if (IS_ERR(ts)) {
qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD);
qeth_clear_thread_running_bit(card,
@@ -1690,6 +1680,13 @@ static void qeth_mpc_finalize_cmd(struct qeth_card *card,
iob->callback = qeth_release_buffer_cb;
}
+static bool qeth_mpc_match_reply(struct qeth_cmd_buffer *iob,
+ struct qeth_cmd_buffer *reply)
+{
+ /* MPC cmds are issued strictly in sequence. */
+ return !IS_IPA(reply->data);
+}
+
static struct qeth_cmd_buffer *qeth_mpc_alloc_cmd(struct qeth_card *card,
void *data,
unsigned int data_length)
@@ -1704,6 +1701,7 @@ static struct qeth_cmd_buffer *qeth_mpc_alloc_cmd(struct qeth_card *card,
qeth_setup_ccw(__ccw_from_cmd(iob), CCW_CMD_WRITE, 0, data_length,
iob->data);
iob->finalize = qeth_mpc_finalize_cmd;
+ iob->match = qeth_mpc_match_reply;
return iob;
}
@@ -2665,7 +2663,7 @@ static unsigned int qeth_tx_select_bulk_max(struct qeth_card *card,
return card->ssqd.mmwc ? card->ssqd.mmwc : 1;
}
-int qeth_init_qdio_queues(struct qeth_card *card)
+static int qeth_init_qdio_queues(struct qeth_card *card)
{
unsigned int i;
int rc;
@@ -2713,7 +2711,6 @@ int qeth_init_qdio_queues(struct qeth_card *card)
}
return 0;
}
-EXPORT_SYMBOL_GPL(qeth_init_qdio_queues);
static void qeth_ipa_finalize_cmd(struct qeth_card *card,
struct qeth_cmd_buffer *iob)
@@ -2725,7 +2722,9 @@ static void qeth_ipa_finalize_cmd(struct qeth_card *card,
}
void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob,
- u16 cmd_length)
+ u16 cmd_length,
+ bool (*match)(struct qeth_cmd_buffer *iob,
+ struct qeth_cmd_buffer *reply))
{
u8 prot_type = qeth_mpc_select_prot_type(card);
u16 total_length = iob->length;
@@ -2733,6 +2732,7 @@ void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob,
qeth_setup_ccw(__ccw_from_cmd(iob), CCW_CMD_WRITE, 0, total_length,
iob->data);
iob->finalize = qeth_ipa_finalize_cmd;
+ iob->match = match;
memcpy(iob->data, IPA_PDU_HEADER, IPA_PDU_HEADER_SIZE);
memcpy(QETH_IPA_PDU_LEN_TOTAL(iob->data), &total_length, 2);
@@ -2745,6 +2745,14 @@ void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob,
}
EXPORT_SYMBOL_GPL(qeth_prepare_ipa_cmd);
+static bool qeth_ipa_match_reply(struct qeth_cmd_buffer *iob,
+ struct qeth_cmd_buffer *reply)
+{
+ struct qeth_ipa_cmd *ipa_reply = __ipa_reply(reply);
+
+ return ipa_reply && (__ipa_cmd(iob)->hdr.seqno == ipa_reply->hdr.seqno);
+}
+
struct qeth_cmd_buffer *qeth_ipa_alloc_cmd(struct qeth_card *card,
enum qeth_ipa_cmds cmd_code,
enum qeth_prot_versions prot,
@@ -2760,7 +2768,7 @@ struct qeth_cmd_buffer *qeth_ipa_alloc_cmd(struct qeth_card *card,
if (!iob)
return NULL;
- qeth_prepare_ipa_cmd(card, iob, data_length);
+ qeth_prepare_ipa_cmd(card, iob, data_length, qeth_ipa_match_reply);
hdr = &__ipa_cmd(iob)->hdr;
hdr->command = cmd_code;
@@ -3096,7 +3104,6 @@ int qeth_hw_trap(struct qeth_card *card, enum qeth_diags_trap_action action)
}
return qeth_send_ipa_cmd(card, iob, qeth_hw_trap_cb, NULL);
}
-EXPORT_SYMBOL_GPL(qeth_hw_trap);
static int qeth_check_qdio_errors(struct qeth_card *card,
struct qdio_buffer *buf,
@@ -5026,6 +5033,12 @@ int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok)
if (rc)
goto out;
+ rc = qeth_init_qdio_queues(card);
+ if (rc) {
+ QETH_CARD_TEXT_(card, 2, "9err%d", rc);
+ goto out;
+ }
+
return 0;
out:
dev_warn(&card->gdev->dev, "The qeth device driver failed to recover "
@@ -5036,6 +5049,89 @@ int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok)
}
EXPORT_SYMBOL_GPL(qeth_core_hardsetup_card);
+static int qeth_set_online(struct qeth_card *card)
+{
+ int rc;
+
+ mutex_lock(&card->discipline_mutex);
+ mutex_lock(&card->conf_mutex);
+ QETH_CARD_TEXT(card, 2, "setonlin");
+
+ rc = card->discipline->set_online(card);
+
+ mutex_unlock(&card->conf_mutex);
+ mutex_unlock(&card->discipline_mutex);
+
+ return rc;
+}
+
+int qeth_set_offline(struct qeth_card *card, bool resetting)
+{
+ int rc, rc2, rc3;
+
+ mutex_lock(&card->discipline_mutex);
+ mutex_lock(&card->conf_mutex);
+ QETH_CARD_TEXT(card, 3, "setoffl");
+
+ if ((!resetting && card->info.hwtrap) || card->info.hwtrap == 2) {
+ qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
+ card->info.hwtrap = 1;
+ }
+
+ rtnl_lock();
+ card->info.open_when_online = card->dev->flags & IFF_UP;
+ dev_close(card->dev);
+ netif_device_detach(card->dev);
+ netif_carrier_off(card->dev);
+ rtnl_unlock();
+
+ card->discipline->set_offline(card);
+
+ rc = qeth_stop_channel(&card->data);
+ rc2 = qeth_stop_channel(&card->write);
+ rc3 = qeth_stop_channel(&card->read);
+ if (!rc)
+ rc = (rc2) ? rc2 : rc3;
+ if (rc)
+ QETH_CARD_TEXT_(card, 2, "1err%d", rc);
+ qdio_free(CARD_DDEV(card));
+
+ /* let user_space know that device is offline */
+ kobject_uevent(&card->gdev->dev.kobj, KOBJ_CHANGE);
+
+ mutex_unlock(&card->conf_mutex);
+ mutex_unlock(&card->discipline_mutex);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(qeth_set_offline);
+
+static int qeth_do_reset(void *data)
+{
+ struct qeth_card *card = data;
+ int rc;
+
+ QETH_CARD_TEXT(card, 2, "recover1");
+ if (!qeth_do_run_thread(card, QETH_RECOVER_THREAD))
+ return 0;
+ QETH_CARD_TEXT(card, 2, "recover2");
+ dev_warn(&card->gdev->dev,
+ "A recovery process has been started for the device\n");
+
+ qeth_set_offline(card, true);
+ rc = qeth_set_online(card);
+ if (!rc) {
+ dev_info(&card->gdev->dev,
+ "Device successfully recovered!\n");
+ } else {
+ ccwgroup_set_offline(card->gdev);
+ dev_warn(&card->gdev->dev,
+ "The qeth device driver failed to recover an error on the device\n");
+ }
+ qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD);
+ qeth_clear_thread_running_bit(card, QETH_RECOVER_THREAD);
+ return 0;
+}
+
#if IS_ENABLED(CONFIG_QETH_L3)
static void qeth_l3_rebuild_skb(struct qeth_card *card, struct sk_buff *skb,
struct qeth_hdr *hdr)
@@ -5972,7 +6068,8 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev)
goto err;
}
}
- rc = card->discipline->set_online(gdev);
+
+ rc = qeth_set_online(card);
err:
return rc;
}
@@ -5980,7 +6077,8 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev)
static int qeth_core_set_offline(struct ccwgroup_device *gdev)
{
struct qeth_card *card = dev_get_drvdata(&gdev->dev);
- return card->discipline->set_offline(gdev);
+
+ return qeth_set_offline(card, false);
}
static void qeth_core_shutdown(struct ccwgroup_device *gdev)
@@ -6003,7 +6101,7 @@ static int qeth_suspend(struct ccwgroup_device *gdev)
if (gdev->state == CCWGROUP_OFFLINE)
return 0;
- card->discipline->set_offline(gdev);
+ qeth_set_offline(card, false);
return 0;
}
@@ -6012,7 +6110,7 @@ static int qeth_resume(struct ccwgroup_device *gdev)
struct qeth_card *card = dev_get_drvdata(&gdev->dev);
int rc;
- rc = card->discipline->set_online(gdev);
+ rc = qeth_set_online(card);
qeth_set_allowed_threads(card, 0xffffffff, 0);
if (rc)
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 7bd8602..2bd9993 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -24,8 +24,6 @@ static ssize_t qeth_dev_state_show(struct device *dev,
switch (card->state) {
case CARD_STATE_DOWN:
return sprintf(buf, "DOWN\n");
- case CARD_STATE_HARDSETUP:
- return sprintf(buf, "HARDSETUP\n");
case CARD_STATE_SOFTSETUP:
if (card->dev->flags & IFF_UP)
return sprintf(buf, "UP (LAN %s)\n",
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index ddc615b..adf25c9 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -13,7 +13,6 @@ extern const struct attribute_group *qeth_l2_attr_groups[];
int qeth_l2_create_device_attributes(struct device *);
void qeth_l2_remove_device_attributes(struct device *);
-void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
int qeth_bridgeport_query_ports(struct qeth_card *card,
enum qeth_sbp_roles *role,
enum qeth_sbp_states *state);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 7175b5d..692bd26 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -24,7 +24,6 @@
#include "qeth_core.h"
#include "qeth_l2.h"
-static int qeth_l2_set_offline(struct ccwgroup_device *);
static void qeth_bridgeport_query_support(struct qeth_card *card);
static void qeth_bridge_state_change(struct qeth_card *card,
struct qeth_ipa_cmd *cmd);
@@ -284,15 +283,12 @@ static void qeth_l2_stop_card(struct qeth_card *card)
if (card->state == CARD_STATE_SOFTSETUP) {
qeth_clear_ipacmd_list(card);
- card->state = CARD_STATE_HARDSETUP;
- }
- if (card->state == CARD_STATE_HARDSETUP) {
qeth_drain_output_queues(card);
- qeth_clear_working_pool_list(card);
card->state = CARD_STATE_DOWN;
}
qeth_qdio_clear_card(card, 0);
+ qeth_clear_working_pool_list(card);
flush_workqueue(card->event_wq);
card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
card->info.promisc_mode = 0;
@@ -610,7 +606,7 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
if (cgdev->state == CCWGROUP_ONLINE)
- qeth_l2_set_offline(cgdev);
+ qeth_set_offline(card, false);
cancel_work_sync(&card->close_dev_work);
if (qeth_netdev_is_registered(card->dev))
@@ -728,17 +724,31 @@ static void qeth_l2_trace_features(struct qeth_card *card)
sizeof(card->options.vnicc.sup_chars));
}
-static int qeth_l2_set_online(struct ccwgroup_device *gdev)
+static void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card)
{
- struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+ if (!card->options.sbp.reflect_promisc &&
+ card->options.sbp.role != QETH_SBP_ROLE_NONE) {
+ /* Conditional to avoid spurious error messages */
+ qeth_bridgeport_setrole(card, card->options.sbp.role);
+ /* Let the callback function refresh the stored role value. */
+ qeth_bridgeport_query_ports(card, &card->options.sbp.role,
+ NULL);
+ }
+ if (card->options.sbp.hostnotification) {
+ if (qeth_bridgeport_an_set(card, 1))
+ card->options.sbp.hostnotification = 0;
+ } else {
+ qeth_bridgeport_an_set(card, 0);
+ }
+}
+
+static int qeth_l2_set_online(struct qeth_card *card)
+{
+ struct ccwgroup_device *gdev = card->gdev;
struct net_device *dev = card->dev;
int rc = 0;
bool carrier_ok;
- mutex_lock(&card->discipline_mutex);
- mutex_lock(&card->conf_mutex);
- QETH_CARD_TEXT(card, 2, "setonlin");
-
rc = qeth_core_hardsetup_card(card, &carrier_ok);
if (rc) {
QETH_CARD_TEXT_(card, 2, "2err%04x", rc);
@@ -748,9 +758,11 @@ static int qeth_l2_set_online(struct ccwgroup_device *gdev)
mutex_lock(&card->sbp_lock);
qeth_bridgeport_query_support(card);
- if (card->options.sbp.supported_funcs)
+ if (card->options.sbp.supported_funcs) {
+ qeth_l2_setup_bridgeport_attrs(card);
dev_info(&card->gdev->dev,
- "The device represents a Bridge Capable Port\n");
+ "The device represents a Bridge Capable Port\n");
+ }
mutex_unlock(&card->sbp_lock);
qeth_l2_register_dev_addr(card);
@@ -761,20 +773,11 @@ static int qeth_l2_set_online(struct ccwgroup_device *gdev)
qeth_trace_features(card);
qeth_l2_trace_features(card);
- qeth_l2_setup_bridgeport_attrs(card);
-
- card->state = CARD_STATE_HARDSETUP;
qeth_print_status_message(card);
/* softsetup */
QETH_CARD_TEXT(card, 2, "softsetp");
- rc = qeth_init_qdio_queues(card);
- if (rc) {
- QETH_CARD_TEXT_(card, 2, "6err%d", rc);
- rc = -ENODEV;
- goto out_remove;
- }
card->state = CARD_STATE_SOFTSETUP;
qeth_set_allowed_threads(card, 0xffffffff, 0);
@@ -801,8 +804,6 @@ static int qeth_l2_set_online(struct ccwgroup_device *gdev)
}
/* let user_space know that device is online */
kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
- mutex_unlock(&card->conf_mutex);
- mutex_unlock(&card->discipline_mutex);
return 0;
out_remove:
@@ -811,81 +812,12 @@ static int qeth_l2_set_online(struct ccwgroup_device *gdev)
qeth_stop_channel(&card->write);
qeth_stop_channel(&card->read);
qdio_free(CARD_DDEV(card));
-
- mutex_unlock(&card->conf_mutex);
- mutex_unlock(&card->discipline_mutex);
return rc;
}
-static int __qeth_l2_set_offline(struct ccwgroup_device *cgdev,
- int recovery_mode)
+static void qeth_l2_set_offline(struct qeth_card *card)
{
- struct qeth_card *card = dev_get_drvdata(&cgdev->dev);
- int rc = 0, rc2 = 0, rc3 = 0;
-
- mutex_lock(&card->discipline_mutex);
- mutex_lock(&card->conf_mutex);
- QETH_CARD_TEXT(card, 3, "setoffl");
-
- if ((!recovery_mode && card->info.hwtrap) || card->info.hwtrap == 2) {
- qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
- card->info.hwtrap = 1;
- }
-
- rtnl_lock();
- card->info.open_when_online = card->dev->flags & IFF_UP;
- dev_close(card->dev);
- netif_device_detach(card->dev);
- netif_carrier_off(card->dev);
- rtnl_unlock();
-
qeth_l2_stop_card(card);
- rc = qeth_stop_channel(&card->data);
- rc2 = qeth_stop_channel(&card->write);
- rc3 = qeth_stop_channel(&card->read);
- if (!rc)
- rc = (rc2) ? rc2 : rc3;
- if (rc)
- QETH_CARD_TEXT_(card, 2, "1err%d", rc);
- qdio_free(CARD_DDEV(card));
-
- /* let user_space know that device is offline */
- kobject_uevent(&cgdev->dev.kobj, KOBJ_CHANGE);
- mutex_unlock(&card->conf_mutex);
- mutex_unlock(&card->discipline_mutex);
- return 0;
-}
-
-static int qeth_l2_set_offline(struct ccwgroup_device *cgdev)
-{
- return __qeth_l2_set_offline(cgdev, 0);
-}
-
-static int qeth_l2_recover(void *ptr)
-{
- struct qeth_card *card;
- int rc = 0;
-
- card = (struct qeth_card *) ptr;
- QETH_CARD_TEXT(card, 2, "recover1");
- if (!qeth_do_run_thread(card, QETH_RECOVER_THREAD))
- return 0;
- QETH_CARD_TEXT(card, 2, "recover2");
- dev_warn(&card->gdev->dev,
- "A recovery process has been started for the device\n");
- __qeth_l2_set_offline(card->gdev, 1);
- rc = qeth_l2_set_online(card->gdev);
- if (!rc)
- dev_info(&card->gdev->dev,
- "Device successfully recovered!\n");
- else {
- ccwgroup_set_offline(card->gdev);
- dev_warn(&card->gdev->dev, "The qeth device driver "
- "failed to recover an error on the device\n");
- }
- qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD);
- qeth_clear_thread_running_bit(card, QETH_RECOVER_THREAD);
- return 0;
}
static int __init qeth_l2_init(void)
@@ -922,7 +854,6 @@ static int qeth_l2_control_event(struct qeth_card *card,
struct qeth_discipline qeth_l2_discipline = {
.devtype = &qeth_l2_devtype,
- .recover = qeth_l2_recover,
.setup = qeth_l2_probe_device,
.remove = qeth_l2_remove_device,
.set_online = qeth_l2_set_online,
@@ -961,7 +892,8 @@ int qeth_osn_assist(struct net_device *dev, void *data, int data_len)
if (!iob)
return -ENOMEM;
- qeth_prepare_ipa_cmd(card, iob, (u16) data_len);
+ qeth_prepare_ipa_cmd(card, iob, (u16) data_len, NULL);
+
memcpy(__ipa_cmd(iob), data, data_len);
iob->callback = qeth_osn_assist_cb;
return qeth_send_ipa_cmd(card, iob, NULL, NULL);
diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c
index 7fa325c..86bcae9 100644
--- a/drivers/s390/net/qeth_l2_sys.c
+++ b/drivers/s390/net/qeth_l2_sys.c
@@ -246,40 +246,6 @@ static struct attribute_group qeth_l2_bridgeport_attr_group = {
.attrs = qeth_l2_bridgeport_attrs,
};
-/**
- * qeth_l2_setup_bridgeport_attrs() - set/restore attrs when turning online.
- * @card: qeth_card structure pointer
- *
- * Note: this function is called with conf_mutex held by the caller
- */
-void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card)
-{
- int rc;
-
- if (!card)
- return;
- if (!card->options.sbp.supported_funcs)
- return;
-
- mutex_lock(&card->sbp_lock);
- if (!card->options.sbp.reflect_promisc &&
- card->options.sbp.role != QETH_SBP_ROLE_NONE) {
- /* Conditional to avoid spurious error messages */
- qeth_bridgeport_setrole(card, card->options.sbp.role);
- /* Let the callback function refresh the stored role value. */
- qeth_bridgeport_query_ports(card,
- &card->options.sbp.role, NULL);
- }
- if (card->options.sbp.hostnotification) {
- rc = qeth_bridgeport_an_set(card, 1);
- if (rc)
- card->options.sbp.hostnotification = 0;
- } else {
- qeth_bridgeport_an_set(card, 0);
- }
- mutex_unlock(&card->sbp_lock);
-}
-
/* VNIC CHARS support */
/* convert sysfs attr name to VNIC characteristic */
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 6c0bffd..317d5664 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -37,8 +37,6 @@
#include "qeth_l3.h"
-
-static int qeth_l3_set_offline(struct ccwgroup_device *);
static int qeth_l3_register_addr_entry(struct qeth_card *,
struct qeth_ipaddr *);
static int qeth_l3_deregister_addr_entry(struct qeth_card *,
@@ -903,7 +901,7 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card)
return rc;
}
-static int qeth_l3_start_ipassists(struct qeth_card *card)
+static void qeth_l3_start_ipassists(struct qeth_card *card)
{
QETH_CARD_TEXT(card, 3, "strtipas");
@@ -913,7 +911,6 @@ static int qeth_l3_start_ipassists(struct qeth_card *card)
qeth_l3_start_ipa_multicast(card); /* go on*/
qeth_l3_start_ipa_ipv6(card); /* go on*/
qeth_l3_start_ipa_broadcast(card); /* go on*/
- return 0;
}
static int qeth_l3_iqd_read_initial_mac_cb(struct qeth_card *card,
@@ -1180,15 +1177,12 @@ static void qeth_l3_stop_card(struct qeth_card *card)
if (card->state == CARD_STATE_SOFTSETUP) {
qeth_l3_clear_ip_htable(card, 1);
qeth_clear_ipacmd_list(card);
- card->state = CARD_STATE_HARDSETUP;
- }
- if (card->state == CARD_STATE_HARDSETUP) {
qeth_drain_output_queues(card);
- qeth_clear_working_pool_list(card);
card->state = CARD_STATE_DOWN;
}
qeth_qdio_clear_card(card, 0);
+ qeth_clear_working_pool_list(card);
flush_workqueue(card->event_wq);
card->info.promisc_mode = 0;
}
@@ -2044,7 +2038,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
if (cgdev->state == CCWGROUP_ONLINE)
- qeth_l3_set_offline(cgdev);
+ qeth_set_offline(card, false);
cancel_work_sync(&card->close_dev_work);
if (qeth_netdev_is_registered(card->dev))
@@ -2056,17 +2050,13 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
qeth_l3_clear_ipato_list(card);
}
-static int qeth_l3_set_online(struct ccwgroup_device *gdev)
+static int qeth_l3_set_online(struct qeth_card *card)
{
- struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+ struct ccwgroup_device *gdev = card->gdev;
struct net_device *dev = card->dev;
int rc = 0;
bool carrier_ok;
- mutex_lock(&card->discipline_mutex);
- mutex_lock(&card->conf_mutex);
- QETH_CARD_TEXT(card, 2, "setonlin");
-
rc = qeth_core_hardsetup_card(card, &carrier_ok);
if (rc) {
QETH_CARD_TEXT_(card, 2, "2err%04x", rc);
@@ -2074,7 +2064,6 @@ static int qeth_l3_set_online(struct ccwgroup_device *gdev)
goto out_remove;
}
- card->state = CARD_STATE_HARDSETUP;
qeth_print_status_message(card);
/* softsetup */
@@ -2084,11 +2073,8 @@ static int qeth_l3_set_online(struct ccwgroup_device *gdev)
if (rc)
QETH_CARD_TEXT_(card, 2, "2err%04x", rc);
if (!card->options.sniffer) {
- rc = qeth_l3_start_ipassists(card);
- if (rc) {
- QETH_CARD_TEXT_(card, 2, "3err%d", rc);
- goto out_remove;
- }
+ qeth_l3_start_ipassists(card);
+
rc = qeth_l3_setrouting_v4(card);
if (rc)
QETH_CARD_TEXT_(card, 2, "4err%04x", rc);
@@ -2097,12 +2083,6 @@ static int qeth_l3_set_online(struct ccwgroup_device *gdev)
QETH_CARD_TEXT_(card, 2, "5err%04x", rc);
}
- rc = qeth_init_qdio_queues(card);
- if (rc) {
- QETH_CARD_TEXT_(card, 2, "6err%d", rc);
- rc = -ENODEV;
- goto out_remove;
- }
card->state = CARD_STATE_SOFTSETUP;
qeth_set_allowed_threads(card, 0xffffffff, 0);
@@ -2131,8 +2111,6 @@ static int qeth_l3_set_online(struct ccwgroup_device *gdev)
qeth_trace_features(card);
/* let user_space know that device is online */
kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
- mutex_unlock(&card->conf_mutex);
- mutex_unlock(&card->discipline_mutex);
return 0;
out_remove:
qeth_l3_stop_card(card);
@@ -2140,82 +2118,12 @@ static int qeth_l3_set_online(struct ccwgroup_device *gdev)
qeth_stop_channel(&card->write);
qeth_stop_channel(&card->read);
qdio_free(CARD_DDEV(card));
-
- mutex_unlock(&card->conf_mutex);
- mutex_unlock(&card->discipline_mutex);
return rc;
}
-static int __qeth_l3_set_offline(struct ccwgroup_device *cgdev,
- int recovery_mode)
+static void qeth_l3_set_offline(struct qeth_card *card)
{
- struct qeth_card *card = dev_get_drvdata(&cgdev->dev);
- int rc = 0, rc2 = 0, rc3 = 0;
-
- mutex_lock(&card->discipline_mutex);
- mutex_lock(&card->conf_mutex);
- QETH_CARD_TEXT(card, 3, "setoffl");
-
- if ((!recovery_mode && card->info.hwtrap) || card->info.hwtrap == 2) {
- qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
- card->info.hwtrap = 1;
- }
-
- rtnl_lock();
- card->info.open_when_online = card->dev->flags & IFF_UP;
- dev_close(card->dev);
- netif_device_detach(card->dev);
- netif_carrier_off(card->dev);
- rtnl_unlock();
-
qeth_l3_stop_card(card);
- rc = qeth_stop_channel(&card->data);
- rc2 = qeth_stop_channel(&card->write);
- rc3 = qeth_stop_channel(&card->read);
- if (!rc)
- rc = (rc2) ? rc2 : rc3;
- if (rc)
- QETH_CARD_TEXT_(card, 2, "1err%d", rc);
- qdio_free(CARD_DDEV(card));
-
- /* let user_space know that device is offline */
- kobject_uevent(&cgdev->dev.kobj, KOBJ_CHANGE);
- mutex_unlock(&card->conf_mutex);
- mutex_unlock(&card->discipline_mutex);
- return 0;
-}
-
-static int qeth_l3_set_offline(struct ccwgroup_device *cgdev)
-{
- return __qeth_l3_set_offline(cgdev, 0);
-}
-
-static int qeth_l3_recover(void *ptr)
-{
- struct qeth_card *card;
- int rc = 0;
-
- card = (struct qeth_card *) ptr;
- QETH_CARD_TEXT(card, 2, "recover1");
- QETH_CARD_HEX(card, 2, &card, sizeof(void *));
- if (!qeth_do_run_thread(card, QETH_RECOVER_THREAD))
- return 0;
- QETH_CARD_TEXT(card, 2, "recover2");
- dev_warn(&card->gdev->dev,
- "A recovery process has been started for the device\n");
- __qeth_l3_set_offline(card->gdev, 1);
- rc = qeth_l3_set_online(card->gdev);
- if (!rc)
- dev_info(&card->gdev->dev,
- "Device successfully recovered!\n");
- else {
- ccwgroup_set_offline(card->gdev);
- dev_warn(&card->gdev->dev, "The qeth device driver "
- "failed to recover an error on the device\n");
- }
- qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD);
- qeth_clear_thread_running_bit(card, QETH_RECOVER_THREAD);
- return 0;
}
/* Returns zero if the command is successfully "consumed" */
@@ -2227,7 +2135,6 @@ static int qeth_l3_control_event(struct qeth_card *card,
struct qeth_discipline qeth_l3_discipline = {
.devtype = &qeth_l3_devtype,
- .recover = qeth_l3_recover,
.setup = qeth_l3_probe_device,
.remove = qeth_l3_remove_device,
.set_online = qeth_l3_set_online,
diff --git a/drivers/scsi/fnic/vnic_dev.c b/drivers/scsi/fnic/vnic_dev.c
index 1f55b9e..1b88a3b 100644
--- a/drivers/scsi/fnic/vnic_dev.c
+++ b/drivers/scsi/fnic/vnic_dev.c
@@ -688,26 +688,26 @@ int vnic_dev_soft_reset_done(struct vnic_dev *vdev, int *done)
int vnic_dev_hang_notify(struct vnic_dev *vdev)
{
- u64 a0, a1;
+ u64 a0 = 0, a1 = 0;
int wait = 1000;
return vnic_dev_cmd(vdev, CMD_HANG_NOTIFY, &a0, &a1, wait);
}
int vnic_dev_mac_addr(struct vnic_dev *vdev, u8 *mac_addr)
{
- u64 a0, a1;
+ u64 a[2] = {};
int wait = 1000;
int err, i;
for (i = 0; i < ETH_ALEN; i++)
mac_addr[i] = 0;
- err = vnic_dev_cmd(vdev, CMD_MAC_ADDR, &a0, &a1, wait);
+ err = vnic_dev_cmd(vdev, CMD_MAC_ADDR, &a[0], &a[1], wait);
if (err)
return err;
for (i = 0; i < ETH_ALEN; i++)
- mac_addr[i] = ((u8 *)&a0)[i];
+ mac_addr[i] = ((u8 *)&a)[i];
return 0;
}
@@ -732,30 +732,30 @@ void vnic_dev_packet_filter(struct vnic_dev *vdev, int directed, int multicast,
void vnic_dev_add_addr(struct vnic_dev *vdev, u8 *addr)
{
- u64 a0 = 0, a1 = 0;
+ u64 a[2] = {};
int wait = 1000;
int err;
int i;
for (i = 0; i < ETH_ALEN; i++)
- ((u8 *)&a0)[i] = addr[i];
+ ((u8 *)&a)[i] = addr[i];
- err = vnic_dev_cmd(vdev, CMD_ADDR_ADD, &a0, &a1, wait);
+ err = vnic_dev_cmd(vdev, CMD_ADDR_ADD, &a[0], &a[1], wait);
if (err)
pr_err("Can't add addr [%pM], %d\n", addr, err);
}
void vnic_dev_del_addr(struct vnic_dev *vdev, u8 *addr)
{
- u64 a0 = 0, a1 = 0;
+ u64 a[2] = {};
int wait = 1000;
int err;
int i;
for (i = 0; i < ETH_ALEN; i++)
- ((u8 *)&a0)[i] = addr[i];
+ ((u8 *)&a)[i] = addr[i];
- err = vnic_dev_cmd(vdev, CMD_ADDR_DEL, &a0, &a1, wait);
+ err = vnic_dev_cmd(vdev, CMD_ADDR_DEL, &a[0], &a[1], wait);
if (err)
pr_err("Can't del addr [%pM], %d\n", addr, err);
}
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index cea6259..65ce10c 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2211,8 +2211,10 @@ static int sd_read_protection_type(struct scsi_disk *sdkp, unsigned char *buffer
u8 type;
int ret = 0;
- if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0)
+ if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0) {
+ sdkp->protection_type = 0;
return ret;
+ }
type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index f8faf8b..fb41636 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1842,9 +1842,11 @@ static int storvsc_probe(struct hv_device *device,
*/
host->sg_tablesize = (stor_device->max_transfer_bytes >> PAGE_SHIFT);
/*
+ * For non-IDE disks, the host supports multiple channels.
* Set the number of HW queues we are supporting.
*/
- host->nr_hw_queues = num_present_cpus();
+ if (!dev_is_ide)
+ host->nr_hw_queues = num_present_cpus();
/*
* Set the error handler work queue.
diff --git a/drivers/soc/amlogic/meson-ee-pwrc.c b/drivers/soc/amlogic/meson-ee-pwrc.c
index 5823f5b..3f0261d 100644
--- a/drivers/soc/amlogic/meson-ee-pwrc.c
+++ b/drivers/soc/amlogic/meson-ee-pwrc.c
@@ -323,6 +323,8 @@ static int meson_ee_pwrc_init_domain(struct platform_device *pdev,
struct meson_ee_pwrc *pwrc,
struct meson_ee_pwrc_domain *dom)
{
+ int ret;
+
dom->pwrc = pwrc;
dom->num_rstc = dom->desc.reset_names_count;
dom->num_clks = dom->desc.clk_names_count;
@@ -368,15 +370,21 @@ static int meson_ee_pwrc_init_domain(struct platform_device *pdev,
* prepare/enable counters won't be in sync.
*/
if (dom->num_clks && dom->desc.get_power && !dom->desc.get_power(dom)) {
- int ret = clk_bulk_prepare_enable(dom->num_clks, dom->clks);
+ ret = clk_bulk_prepare_enable(dom->num_clks, dom->clks);
if (ret)
return ret;
- pm_genpd_init(&dom->base, &pm_domain_always_on_gov, false);
- } else
- pm_genpd_init(&dom->base, NULL,
- (dom->desc.get_power ?
- dom->desc.get_power(dom) : true));
+ ret = pm_genpd_init(&dom->base, &pm_domain_always_on_gov,
+ false);
+ if (ret)
+ return ret;
+ } else {
+ ret = pm_genpd_init(&dom->base, NULL,
+ (dom->desc.get_power ?
+ dom->desc.get_power(dom) : true));
+ if (ret)
+ return ret;
+ }
return 0;
}
@@ -441,9 +449,7 @@ static int meson_ee_pwrc_probe(struct platform_device *pdev)
pwrc->xlate.domains[i] = &dom->base;
}
- of_genpd_add_provider_onecell(pdev->dev.of_node, &pwrc->xlate);
-
- return 0;
+ return of_genpd_add_provider_onecell(pdev->dev.of_node, &pwrc->xlate);
}
static void meson_ee_pwrc_shutdown(struct platform_device *pdev)
diff --git a/drivers/soc/sifive/sifive_l2_cache.c b/drivers/soc/sifive/sifive_l2_cache.c
index a9ffff3..a506939 100644
--- a/drivers/soc/sifive/sifive_l2_cache.c
+++ b/drivers/soc/sifive/sifive_l2_cache.c
@@ -9,7 +9,7 @@
#include <linux/interrupt.h>
#include <linux/of_irq.h>
#include <linux/of_address.h>
-#include <asm/sifive_l2_cache.h>
+#include <soc/sifive/sifive_l2_cache.h>
#define SIFIVE_L2_DIRECCFIX_LOW 0x100
#define SIFIVE_L2_DIRECCFIX_HIGH 0x104
diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c
index 378369d..e9ece45 100644
--- a/drivers/soc/ti/wkup_m3_ipc.c
+++ b/drivers/soc/ti/wkup_m3_ipc.c
@@ -419,6 +419,8 @@ static void wkup_m3_rproc_boot_thread(struct wkup_m3_ipc *m3_ipc)
ret = rproc_boot(m3_ipc->rproc);
if (ret)
dev_err(dev, "rproc_boot failed\n");
+ else
+ m3_ipc_state = m3_ipc;
do_exit(0);
}
@@ -505,8 +507,6 @@ static int wkup_m3_ipc_probe(struct platform_device *pdev)
goto err_put_rproc;
}
- m3_ipc_state = m3_ipc;
-
return 0;
err_put_rproc:
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index 76d6b94..5a25da3 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -172,9 +172,11 @@ static inline u32 rx_max(struct dw_spi *dws)
static void dw_writer(struct dw_spi *dws)
{
- u32 max = tx_max(dws);
+ u32 max;
u16 txw = 0;
+ spin_lock(&dws->buf_lock);
+ max = tx_max(dws);
while (max--) {
/* Set the tx word if the transfer's original "tx" is not null */
if (dws->tx_end - dws->len) {
@@ -186,13 +188,16 @@ static void dw_writer(struct dw_spi *dws)
dw_write_io_reg(dws, DW_SPI_DR, txw);
dws->tx += dws->n_bytes;
}
+ spin_unlock(&dws->buf_lock);
}
static void dw_reader(struct dw_spi *dws)
{
- u32 max = rx_max(dws);
+ u32 max;
u16 rxw;
+ spin_lock(&dws->buf_lock);
+ max = rx_max(dws);
while (max--) {
rxw = dw_read_io_reg(dws, DW_SPI_DR);
/* Care rx only if the transfer's original "rx" is not null */
@@ -204,6 +209,7 @@ static void dw_reader(struct dw_spi *dws)
}
dws->rx += dws->n_bytes;
}
+ spin_unlock(&dws->buf_lock);
}
static void int_error_stop(struct dw_spi *dws, const char *msg)
@@ -276,18 +282,20 @@ static int dw_spi_transfer_one(struct spi_controller *master,
{
struct dw_spi *dws = spi_controller_get_devdata(master);
struct chip_data *chip = spi_get_ctldata(spi);
+ unsigned long flags;
u8 imask = 0;
u16 txlevel = 0;
u32 cr0;
int ret;
dws->dma_mapped = 0;
-
+ spin_lock_irqsave(&dws->buf_lock, flags);
dws->tx = (void *)transfer->tx_buf;
dws->tx_end = dws->tx + transfer->len;
dws->rx = transfer->rx_buf;
dws->rx_end = dws->rx + transfer->len;
dws->len = transfer->len;
+ spin_unlock_irqrestore(&dws->buf_lock, flags);
spi_enable_chip(dws, 0);
@@ -471,6 +479,7 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
dws->type = SSI_MOTO_SPI;
dws->dma_inited = 0;
dws->dma_addr = (dma_addr_t)(dws->paddr + DW_SPI_DR);
+ spin_lock_init(&dws->buf_lock);
spi_controller_set_devdata(master, dws);
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index 38c7de1..1bf5713 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -119,6 +119,7 @@ struct dw_spi {
size_t len;
void *tx;
void *tx_end;
+ spinlock_t buf_lock;
void *rx;
void *rx_end;
int dma_mapped;
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 442cff7..8428b69 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -185,6 +185,7 @@ struct fsl_dspi {
struct spi_transfer *cur_transfer;
struct spi_message *cur_msg;
struct chip_data *cur_chip;
+ size_t progress;
size_t len;
const void *tx;
void *rx;
@@ -586,21 +587,14 @@ static void dspi_tcfq_write(struct fsl_dspi *dspi)
dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
if (dspi->devtype_data->xspi_mode && dspi->bits_per_word > 16) {
- /* Write two TX FIFO entries first, and then the corresponding
- * CMD FIFO entry.
+ /* Write the CMD FIFO entry first, and then the two
+ * corresponding TX FIFO entries.
*/
u32 data = dspi_pop_tx(dspi);
- if (dspi->cur_chip->ctar_val & SPI_CTAR_LSBFE) {
- /* LSB */
- tx_fifo_write(dspi, data & 0xFFFF);
- tx_fifo_write(dspi, data >> 16);
- } else {
- /* MSB */
- tx_fifo_write(dspi, data >> 16);
- tx_fifo_write(dspi, data & 0xFFFF);
- }
cmd_fifo_write(dspi);
+ tx_fifo_write(dspi, data & 0xFFFF);
+ tx_fifo_write(dspi, data >> 16);
} else {
/* Write one entry to both TX FIFO and CMD FIFO
* simultaneously.
@@ -658,7 +652,7 @@ static int dspi_rxtx(struct fsl_dspi *dspi)
u32 spi_tcr;
spi_take_timestamp_post(dspi->ctlr, dspi->cur_transfer,
- dspi->tx - dspi->bytes_per_word, !dspi->irq);
+ dspi->progress, !dspi->irq);
/* Get transfer counter (in number of SPI transfers). It was
* reset to 0 when transfer(s) were started.
@@ -667,6 +661,7 @@ static int dspi_rxtx(struct fsl_dspi *dspi)
spi_tcnt = SPI_TCR_GET_TCNT(spi_tcr);
/* Update total number of bytes that were transferred */
msg->actual_length += spi_tcnt * dspi->bytes_per_word;
+ dspi->progress += spi_tcnt;
trans_mode = dspi->devtype_data->trans_mode;
if (trans_mode == DSPI_EOQ_MODE)
@@ -679,7 +674,7 @@ static int dspi_rxtx(struct fsl_dspi *dspi)
return 0;
spi_take_timestamp_pre(dspi->ctlr, dspi->cur_transfer,
- dspi->tx, !dspi->irq);
+ dspi->progress, !dspi->irq);
if (trans_mode == DSPI_EOQ_MODE)
dspi_eoq_write(dspi);
@@ -768,6 +763,7 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr,
dspi->rx = transfer->rx_buf;
dspi->rx_end = dspi->rx + transfer->len;
dspi->len = transfer->len;
+ dspi->progress = 0;
/* Validated transfer specific frame size (defaults applied) */
dspi->bits_per_word = transfer->bits_per_word;
if (transfer->bits_per_word <= 8)
@@ -789,7 +785,7 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr,
SPI_CTARE_DTCP(1));
spi_take_timestamp_pre(dspi->ctlr, dspi->cur_transfer,
- dspi->tx, !dspi->irq);
+ dspi->progress, !dspi->irq);
trans_mode = dspi->devtype_data->trans_mode;
switch (trans_mode) {
diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c
index 47cde186..ce9b301 100644
--- a/drivers/spi/spi-uniphier.c
+++ b/drivers/spi/spi-uniphier.c
@@ -290,25 +290,32 @@ static void uniphier_spi_recv(struct uniphier_spi_priv *priv)
}
}
-static void uniphier_spi_fill_tx_fifo(struct uniphier_spi_priv *priv)
+static void uniphier_spi_set_fifo_threshold(struct uniphier_spi_priv *priv,
+ unsigned int threshold)
{
- unsigned int fifo_threshold, fill_bytes;
u32 val;
- fifo_threshold = DIV_ROUND_UP(priv->rx_bytes,
- bytes_per_word(priv->bits_per_word));
- fifo_threshold = min(fifo_threshold, SSI_FIFO_DEPTH);
-
- fill_bytes = fifo_threshold - (priv->rx_bytes - priv->tx_bytes);
-
- /* set fifo threshold */
val = readl(priv->base + SSI_FC);
val &= ~(SSI_FC_TXFTH_MASK | SSI_FC_RXFTH_MASK);
- val |= FIELD_PREP(SSI_FC_TXFTH_MASK, fifo_threshold);
- val |= FIELD_PREP(SSI_FC_RXFTH_MASK, fifo_threshold);
+ val |= FIELD_PREP(SSI_FC_TXFTH_MASK, SSI_FIFO_DEPTH - threshold);
+ val |= FIELD_PREP(SSI_FC_RXFTH_MASK, threshold);
writel(val, priv->base + SSI_FC);
+}
- while (fill_bytes--)
+static void uniphier_spi_fill_tx_fifo(struct uniphier_spi_priv *priv)
+{
+ unsigned int fifo_threshold, fill_words;
+ unsigned int bpw = bytes_per_word(priv->bits_per_word);
+
+ fifo_threshold = DIV_ROUND_UP(priv->rx_bytes, bpw);
+ fifo_threshold = min(fifo_threshold, SSI_FIFO_DEPTH);
+
+ uniphier_spi_set_fifo_threshold(priv, fifo_threshold);
+
+ fill_words = fifo_threshold -
+ DIV_ROUND_UP(priv->rx_bytes - priv->tx_bytes, bpw);
+
+ while (fill_words--)
uniphier_spi_send(priv);
}
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 5e4c453..8994545 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1499,8 +1499,7 @@ static void spi_pump_messages(struct kthread_work *work)
* advances its @tx buffer pointer monotonically.
* @ctlr: Pointer to the spi_controller structure of the driver
* @xfer: Pointer to the transfer being timestamped
- * @tx: Pointer to the current word within the xfer->tx_buf that the driver is
- * preparing to transmit right now.
+ * @progress: How many words (not bytes) have been transferred so far
* @irqs_off: If true, will disable IRQs and preemption for the duration of the
* transfer, for less jitter in time measurement. Only compatible
* with PIO drivers. If true, must follow up with
@@ -1510,21 +1509,19 @@ static void spi_pump_messages(struct kthread_work *work)
*/
void spi_take_timestamp_pre(struct spi_controller *ctlr,
struct spi_transfer *xfer,
- const void *tx, bool irqs_off)
+ size_t progress, bool irqs_off)
{
- u8 bytes_per_word = DIV_ROUND_UP(xfer->bits_per_word, 8);
-
if (!xfer->ptp_sts)
return;
if (xfer->timestamped_pre)
return;
- if (tx < (xfer->tx_buf + xfer->ptp_sts_word_pre * bytes_per_word))
+ if (progress < xfer->ptp_sts_word_pre)
return;
/* Capture the resolution of the timestamp */
- xfer->ptp_sts_word_pre = (tx - xfer->tx_buf) / bytes_per_word;
+ xfer->ptp_sts_word_pre = progress;
xfer->timestamped_pre = true;
@@ -1546,23 +1543,20 @@ EXPORT_SYMBOL_GPL(spi_take_timestamp_pre);
* timestamped.
* @ctlr: Pointer to the spi_controller structure of the driver
* @xfer: Pointer to the transfer being timestamped
- * @tx: Pointer to the current word within the xfer->tx_buf that the driver has
- * just transmitted.
+ * @progress: How many words (not bytes) have been transferred so far
* @irqs_off: If true, will re-enable IRQs and preemption for the local CPU.
*/
void spi_take_timestamp_post(struct spi_controller *ctlr,
struct spi_transfer *xfer,
- const void *tx, bool irqs_off)
+ size_t progress, bool irqs_off)
{
- u8 bytes_per_word = DIV_ROUND_UP(xfer->bits_per_word, 8);
-
if (!xfer->ptp_sts)
return;
if (xfer->timestamped_post)
return;
- if (tx < (xfer->tx_buf + xfer->ptp_sts_word_post * bytes_per_word))
+ if (progress < xfer->ptp_sts_word_post)
return;
ptp_read_system_postts(xfer->ptp_sts);
@@ -1573,7 +1567,7 @@ void spi_take_timestamp_post(struct spi_controller *ctlr,
}
/* Capture the resolution of the timestamp */
- xfer->ptp_sts_word_post = (tx - xfer->tx_buf) / bytes_per_word;
+ xfer->ptp_sts_word_post = progress;
xfer->timestamped_post = true;
}
diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c
index dbff0f7..ddc0dc9 100644
--- a/drivers/staging/comedi/drivers/adv_pci1710.c
+++ b/drivers/staging/comedi/drivers/adv_pci1710.c
@@ -46,8 +46,8 @@
#define PCI171X_RANGE_UNI BIT(4)
#define PCI171X_RANGE_GAIN(x) (((x) & 0x7) << 0)
#define PCI171X_MUX_REG 0x04 /* W: A/D multiplexor control */
-#define PCI171X_MUX_CHANH(x) (((x) & 0xf) << 8)
-#define PCI171X_MUX_CHANL(x) (((x) & 0xf) << 0)
+#define PCI171X_MUX_CHANH(x) (((x) & 0xff) << 8)
+#define PCI171X_MUX_CHANL(x) (((x) & 0xff) << 0)
#define PCI171X_MUX_CHAN(x) (PCI171X_MUX_CHANH(x) | PCI171X_MUX_CHANL(x))
#define PCI171X_STATUS_REG 0x06 /* R: status register */
#define PCI171X_STATUS_IRQ BIT(11) /* 1=IRQ occurred */
diff --git a/drivers/staging/comedi/drivers/ni_routes.c b/drivers/staging/comedi/drivers/ni_routes.c
index 673d732..8f398b3 100644
--- a/drivers/staging/comedi/drivers/ni_routes.c
+++ b/drivers/staging/comedi/drivers/ni_routes.c
@@ -72,9 +72,6 @@ static int ni_find_device_routes(const char *device_family,
}
}
- if (!rv)
- return -ENODATA;
-
/* Second, find the set of routes valid for this device. */
for (i = 0; ni_device_routes_list[i]; ++i) {
if (memcmp(ni_device_routes_list[i]->device, board_name,
@@ -84,12 +81,12 @@ static int ni_find_device_routes(const char *device_family,
}
}
- if (!dr)
- return -ENODATA;
-
tables->route_values = rv;
tables->valid_routes = dr;
+ if (!rv || !dr)
+ return -ENODATA;
+
return 0;
}
@@ -487,6 +484,9 @@ int ni_find_route_source(const u8 src_sel_reg_value, int dest,
{
int src;
+ if (!tables->route_values)
+ return -EINVAL;
+
dest = B(dest); /* subtract NI names offset */
/* ensure we are not going to under/over run the route value table */
if (dest < 0 || dest >= NI_NUM_NAMES)
diff --git a/drivers/staging/media/ipu3/include/intel-ipu3.h b/drivers/staging/media/ipu3/include/intel-ipu3.h
index 08eaa0b..1c9c3ba 100644
--- a/drivers/staging/media/ipu3/include/intel-ipu3.h
+++ b/drivers/staging/media/ipu3/include/intel-ipu3.h
@@ -449,7 +449,7 @@ struct ipu3_uapi_awb_fr_config_s {
__u16 reserved1;
__u32 bayer_sign;
__u8 bayer_nf;
- __u8 reserved2[3];
+ __u8 reserved2[7];
} __attribute__((aligned(32))) __packed;
/**
diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
index a7cac07..b5d42f4 100644
--- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
@@ -37,6 +37,7 @@ static const struct usb_device_id rtw_usb_id_tbl[] = {
{USB_DEVICE(0x2001, 0x3311)}, /* DLink GO-USB-N150 REV B1 */
{USB_DEVICE(0x2001, 0x331B)}, /* D-Link DWA-121 rev B1 */
{USB_DEVICE(0x2357, 0x010c)}, /* TP-Link TL-WN722N v2 */
+ {USB_DEVICE(0x2357, 0x0111)}, /* TP-Link TL-WN727N v5.21 */
{USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */
{USB_DEVICE(USB_VENDER_ID_REALTEK, 0xffef)}, /* Rosewill RNX-N150NUB */
{} /* Terminating entry */
diff --git a/drivers/staging/vt6656/baseband.c b/drivers/staging/vt6656/baseband.c
index 8d19ae7..4e651b6 100644
--- a/drivers/staging/vt6656/baseband.c
+++ b/drivers/staging/vt6656/baseband.c
@@ -449,8 +449,8 @@ int vnt_vt3184_init(struct vnt_private *priv)
memcpy(array, addr, length);
- ret = vnt_control_out(priv, MESSAGE_TYPE_WRITE, 0,
- MESSAGE_REQUEST_BBREG, length, array);
+ ret = vnt_control_out_blocks(priv, VNT_REG_BLOCK_SIZE,
+ MESSAGE_REQUEST_BBREG, length, array);
if (ret)
goto end;
diff --git a/drivers/staging/vt6656/card.c b/drivers/staging/vt6656/card.c
index 56cd77f..7958fc1 100644
--- a/drivers/staging/vt6656/card.c
+++ b/drivers/staging/vt6656/card.c
@@ -719,7 +719,7 @@ int vnt_radio_power_off(struct vnt_private *priv)
*/
int vnt_radio_power_on(struct vnt_private *priv)
{
- int ret = true;
+ int ret = 0;
vnt_exit_deep_sleep(priv);
diff --git a/drivers/staging/vt6656/device.h b/drivers/staging/vt6656/device.h
index 6074ceda..50e1c89 100644
--- a/drivers/staging/vt6656/device.h
+++ b/drivers/staging/vt6656/device.h
@@ -259,6 +259,7 @@ struct vnt_private {
u8 mac_hw;
/* netdev */
struct usb_device *usb;
+ struct usb_interface *intf;
u64 tsf_time;
u8 rx_rate;
diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c
index 4ac85ec..9cb924c 100644
--- a/drivers/staging/vt6656/main_usb.c
+++ b/drivers/staging/vt6656/main_usb.c
@@ -949,7 +949,7 @@ static const struct ieee80211_ops vnt_mac_ops = {
int vnt_init(struct vnt_private *priv)
{
- if (!(vnt_init_registers(priv)))
+ if (vnt_init_registers(priv))
return -EAGAIN;
SET_IEEE80211_PERM_ADDR(priv->hw, priv->permanent_net_addr);
@@ -992,6 +992,7 @@ vt6656_probe(struct usb_interface *intf, const struct usb_device_id *id)
priv = hw->priv;
priv->hw = hw;
priv->usb = udev;
+ priv->intf = intf;
vnt_set_options(priv);
diff --git a/drivers/staging/vt6656/usbpipe.c b/drivers/staging/vt6656/usbpipe.c
index d3304df..d977d47 100644
--- a/drivers/staging/vt6656/usbpipe.c
+++ b/drivers/staging/vt6656/usbpipe.c
@@ -59,7 +59,9 @@ int vnt_control_out(struct vnt_private *priv, u8 request, u16 value,
kfree(usb_buffer);
- if (ret >= 0 && ret < (int)length)
+ if (ret == (int)length)
+ ret = 0;
+ else
ret = -EIO;
end_unlock:
@@ -74,6 +76,23 @@ int vnt_control_out_u8(struct vnt_private *priv, u8 reg, u8 reg_off, u8 data)
reg_off, reg, sizeof(u8), &data);
}
+int vnt_control_out_blocks(struct vnt_private *priv,
+ u16 block, u8 reg, u16 length, u8 *data)
+{
+ int ret = 0, i;
+
+ for (i = 0; i < length; i += block) {
+ u16 len = min_t(int, length - i, block);
+
+ ret = vnt_control_out(priv, MESSAGE_TYPE_WRITE,
+ i, reg, len, data + i);
+ if (ret)
+ goto end;
+ }
+end:
+ return ret;
+}
+
int vnt_control_in(struct vnt_private *priv, u8 request, u16 value,
u16 index, u16 length, u8 *buffer)
{
@@ -103,7 +122,9 @@ int vnt_control_in(struct vnt_private *priv, u8 request, u16 value,
kfree(usb_buffer);
- if (ret >= 0 && ret < (int)length)
+ if (ret == (int)length)
+ ret = 0;
+ else
ret = -EIO;
end_unlock:
diff --git a/drivers/staging/vt6656/usbpipe.h b/drivers/staging/vt6656/usbpipe.h
index 95147ec..b65d9c0 100644
--- a/drivers/staging/vt6656/usbpipe.h
+++ b/drivers/staging/vt6656/usbpipe.h
@@ -18,6 +18,8 @@
#include "device.h"
+#define VNT_REG_BLOCK_SIZE 64
+
int vnt_control_out(struct vnt_private *priv, u8 request, u16 value,
u16 index, u16 length, u8 *buffer);
int vnt_control_in(struct vnt_private *priv, u8 request, u16 value,
@@ -26,6 +28,9 @@ int vnt_control_in(struct vnt_private *priv, u8 request, u16 value,
int vnt_control_out_u8(struct vnt_private *priv, u8 reg, u8 ref_off, u8 data);
int vnt_control_in_u8(struct vnt_private *priv, u8 reg, u8 reg_off, u8 *data);
+int vnt_control_out_blocks(struct vnt_private *priv,
+ u16 block, u8 reg, u16 len, u8 *data);
+
int vnt_start_interrupt_urb(struct vnt_private *priv);
int vnt_submit_rx_urb(struct vnt_private *priv, struct vnt_rcb *rcb);
int vnt_tx_context(struct vnt_private *priv,
diff --git a/drivers/staging/vt6656/wcmd.c b/drivers/staging/vt6656/wcmd.c
index 3eb2f11..2c5250c 100644
--- a/drivers/staging/vt6656/wcmd.c
+++ b/drivers/staging/vt6656/wcmd.c
@@ -99,6 +99,7 @@ void vnt_run_command(struct work_struct *work)
if (vnt_init(priv)) {
/* If fail all ends TODO retry */
dev_err(&priv->usb->dev, "failed to start\n");
+ usb_set_intfdata(priv->intf, NULL);
ieee80211_free_hw(priv->hw);
return;
}
diff --git a/drivers/tee/optee/Kconfig b/drivers/tee/optee/Kconfig
index d1ad512..3ca71e3 100644
--- a/drivers/tee/optee/Kconfig
+++ b/drivers/tee/optee/Kconfig
@@ -3,6 +3,7 @@
config OPTEE
tristate "OP-TEE"
depends on HAVE_ARM_SMCCC
+ depends on MMU
help
This implements the OP-TEE Trusted Execution Environment (TEE)
driver.
diff --git a/drivers/tee/optee/shm_pool.c b/drivers/tee/optee/shm_pool.c
index 0332a53..d767eeb 100644
--- a/drivers/tee/optee/shm_pool.c
+++ b/drivers/tee/optee/shm_pool.c
@@ -28,9 +28,22 @@ static int pool_op_alloc(struct tee_shm_pool_mgr *poolm,
shm->size = PAGE_SIZE << order;
if (shm->flags & TEE_SHM_DMA_BUF) {
+ unsigned int nr_pages = 1 << order, i;
+ struct page **pages;
+
+ pages = kcalloc(nr_pages, sizeof(pages), GFP_KERNEL);
+ if (!pages)
+ return -ENOMEM;
+
+ for (i = 0; i < nr_pages; i++) {
+ pages[i] = page;
+ page++;
+ }
+
shm->flags |= TEE_SHM_REGISTER;
- rc = optee_shm_register(shm->ctx, shm, &page, 1 << order,
+ rc = optee_shm_register(shm->ctx, shm, pages, nr_pages,
(unsigned long)shm->kaddr);
+ kfree(pages);
}
return rc;
diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c
index 015e7d2..0e7cf52 100644
--- a/drivers/thermal/qcom/tsens.c
+++ b/drivers/thermal/qcom/tsens.c
@@ -110,6 +110,9 @@ static int tsens_register(struct tsens_priv *priv)
irq = platform_get_irq_byname(pdev, "uplow");
if (irq < 0) {
ret = irq;
+ /* For old DTs with no IRQ defined */
+ if (irq == -ENXIO)
+ ret = 0;
goto err_put_device;
}
diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index 226adee..ce5309d 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -663,6 +663,12 @@ static acpi_status acpi_serdev_register_device(struct serdev_controller *ctrl,
return AE_OK;
}
+static const struct acpi_device_id serdev_acpi_devices_blacklist[] = {
+ { "INT3511", 0 },
+ { "INT3512", 0 },
+ { },
+};
+
static acpi_status acpi_serdev_add_device(acpi_handle handle, u32 level,
void *data, void **return_value)
{
@@ -675,6 +681,10 @@ static acpi_status acpi_serdev_add_device(acpi_handle handle, u32 level,
if (acpi_device_enumerated(adev))
return AE_OK;
+ /* Skip if black listed */
+ if (!acpi_match_device_ids(adev, serdev_acpi_devices_blacklist))
+ return AE_OK;
+
if (acpi_serdev_check_resources(ctrl, adev))
return AE_OK;
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 5023c85..044c3cb 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -89,8 +89,7 @@ void tty_port_link_device(struct tty_port *port,
{
if (WARN_ON(index >= driver->num))
return;
- if (!driver->ports[index])
- driver->ports[index] = port;
+ driver->ports[index] = port;
}
EXPORT_SYMBOL_GPL(tty_port_link_device);
diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c
index 4c1e755..02f6ca2 100644
--- a/drivers/usb/cdns3/gadget.c
+++ b/drivers/usb/cdns3/gadget.c
@@ -1375,13 +1375,10 @@ static void cdns3_check_usb_interrupt_proceed(struct cdns3_device *priv_dev,
*/
static irqreturn_t cdns3_device_irq_handler(int irq, void *data)
{
- struct cdns3_device *priv_dev;
- struct cdns3 *cdns = data;
+ struct cdns3_device *priv_dev = data;
irqreturn_t ret = IRQ_NONE;
u32 reg;
- priv_dev = cdns->gadget_dev;
-
/* check USB device interrupt */
reg = readl(&priv_dev->regs->usb_ists);
if (reg) {
@@ -1419,14 +1416,12 @@ static irqreturn_t cdns3_device_irq_handler(int irq, void *data)
*/
static irqreturn_t cdns3_device_thread_irq_handler(int irq, void *data)
{
- struct cdns3_device *priv_dev;
- struct cdns3 *cdns = data;
+ struct cdns3_device *priv_dev = data;
irqreturn_t ret = IRQ_NONE;
unsigned long flags;
int bit;
u32 reg;
- priv_dev = cdns->gadget_dev;
spin_lock_irqsave(&priv_dev->lock, flags);
reg = readl(&priv_dev->regs->usb_ists);
@@ -2539,7 +2534,7 @@ void cdns3_gadget_exit(struct cdns3 *cdns)
priv_dev = cdns->gadget_dev;
- devm_free_irq(cdns->dev, cdns->dev_irq, cdns);
+ devm_free_irq(cdns->dev, cdns->dev_irq, priv_dev);
pm_runtime_mark_last_busy(cdns->dev);
pm_runtime_put_autosuspend(cdns->dev);
@@ -2710,7 +2705,8 @@ static int __cdns3_gadget_init(struct cdns3 *cdns)
ret = devm_request_threaded_irq(cdns->dev, cdns->dev_irq,
cdns3_device_irq_handler,
cdns3_device_thread_irq_handler,
- IRQF_SHARED, dev_name(cdns->dev), cdns);
+ IRQF_SHARED, dev_name(cdns->dev),
+ cdns->gadget_dev);
if (ret)
goto err0;
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index b45ceb9..48e4a5c 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -26,6 +26,7 @@ static int (*orig_bus_suspend)(struct usb_hcd *hcd);
struct ehci_ci_priv {
struct regulator *reg_vbus;
+ bool enabled;
};
static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable)
@@ -37,7 +38,7 @@ static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable)
int ret = 0;
int port = HCS_N_PORTS(ehci->hcs_params);
- if (priv->reg_vbus) {
+ if (priv->reg_vbus && enable != priv->enabled) {
if (port > 1) {
dev_warn(dev,
"Not support multi-port regulator control\n");
@@ -53,6 +54,7 @@ static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable)
enable ? "enable" : "disable", ret);
return ret;
}
+ priv->enabled = enable;
}
if (enable && (ci->platdata->phy_mode == USBPHY_INTERFACE_MODE_HSIC)) {
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 5f40117..26bc05e 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -203,9 +203,58 @@ static const unsigned short super_speed_maxpacket_maxes[4] = {
[USB_ENDPOINT_XFER_INT] = 1024,
};
-static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
- int asnum, struct usb_host_interface *ifp, int num_ep,
- unsigned char *buffer, int size)
+static bool endpoint_is_duplicate(struct usb_endpoint_descriptor *e1,
+ struct usb_endpoint_descriptor *e2)
+{
+ if (e1->bEndpointAddress == e2->bEndpointAddress)
+ return true;
+
+ if (usb_endpoint_xfer_control(e1) || usb_endpoint_xfer_control(e2)) {
+ if (usb_endpoint_num(e1) == usb_endpoint_num(e2))
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Check for duplicate endpoint addresses in other interfaces and in the
+ * altsetting currently being parsed.
+ */
+static bool config_endpoint_is_duplicate(struct usb_host_config *config,
+ int inum, int asnum, struct usb_endpoint_descriptor *d)
+{
+ struct usb_endpoint_descriptor *epd;
+ struct usb_interface_cache *intfc;
+ struct usb_host_interface *alt;
+ int i, j, k;
+
+ for (i = 0; i < config->desc.bNumInterfaces; ++i) {
+ intfc = config->intf_cache[i];
+
+ for (j = 0; j < intfc->num_altsetting; ++j) {
+ alt = &intfc->altsetting[j];
+
+ if (alt->desc.bInterfaceNumber == inum &&
+ alt->desc.bAlternateSetting != asnum)
+ continue;
+
+ for (k = 0; k < alt->desc.bNumEndpoints; ++k) {
+ epd = &alt->endpoint[k].desc;
+
+ if (endpoint_is_duplicate(epd, d))
+ return true;
+ }
+ }
+ }
+
+ return false;
+}
+
+static int usb_parse_endpoint(struct device *ddev, int cfgno,
+ struct usb_host_config *config, int inum, int asnum,
+ struct usb_host_interface *ifp, int num_ep,
+ unsigned char *buffer, int size)
{
unsigned char *buffer0 = buffer;
struct usb_endpoint_descriptor *d;
@@ -242,13 +291,10 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
goto skip_to_next_endpoint_or_interface_descriptor;
/* Check for duplicate endpoint addresses */
- for (i = 0; i < ifp->desc.bNumEndpoints; ++i) {
- if (ifp->endpoint[i].desc.bEndpointAddress ==
- d->bEndpointAddress) {
- dev_warn(ddev, "config %d interface %d altsetting %d has a duplicate endpoint with address 0x%X, skipping\n",
- cfgno, inum, asnum, d->bEndpointAddress);
- goto skip_to_next_endpoint_or_interface_descriptor;
- }
+ if (config_endpoint_is_duplicate(config, inum, asnum, d)) {
+ dev_warn(ddev, "config %d interface %d altsetting %d has a duplicate endpoint with address 0x%X, skipping\n",
+ cfgno, inum, asnum, d->bEndpointAddress);
+ goto skip_to_next_endpoint_or_interface_descriptor;
}
endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints];
@@ -346,12 +392,16 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
endpoint->desc.wMaxPacketSize = cpu_to_le16(8);
}
- /* Validate the wMaxPacketSize field */
+ /*
+ * Validate the wMaxPacketSize field.
+ * Some devices have isochronous endpoints in altsetting 0;
+ * the USB-2 spec requires such endpoints to have wMaxPacketSize = 0
+ * (see the end of section 5.6.3), so don't warn about them.
+ */
maxp = usb_endpoint_maxp(&endpoint->desc);
- if (maxp == 0) {
- dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has wMaxPacketSize 0, skipping\n",
+ if (maxp == 0 && !(usb_endpoint_xfer_isoc(d) && asnum == 0)) {
+ dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid wMaxPacketSize 0\n",
cfgno, inum, asnum, d->bEndpointAddress);
- goto skip_to_next_endpoint_or_interface_descriptor;
}
/* Find the highest legal maxpacket size for this endpoint */
@@ -522,8 +572,8 @@ static int usb_parse_interface(struct device *ddev, int cfgno,
if (((struct usb_descriptor_header *) buffer)->bDescriptorType
== USB_DT_INTERFACE)
break;
- retval = usb_parse_endpoint(ddev, cfgno, inum, asnum, alt,
- num_ep, buffer, size);
+ retval = usb_parse_endpoint(ddev, cfgno, config, inum, asnum,
+ alt, num_ep, buffer, size);
if (retval < 0)
return retval;
++n;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index f229ad6..3405b14 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1192,6 +1192,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
* PORT_OVER_CURRENT is not. So check for any of them.
*/
if (udev || (portstatus & USB_PORT_STAT_CONNECTION) ||
+ (portchange & USB_PORT_STAT_C_CONNECTION) ||
(portstatus & USB_PORT_STAT_OVERCURRENT) ||
(portchange & USB_PORT_STAT_C_OVERCURRENT))
set_bit(port1, hub->change_bits);
@@ -2692,7 +2693,7 @@ static unsigned hub_is_wusb(struct usb_hub *hub)
#define SET_ADDRESS_TRIES 2
#define GET_DESCRIPTOR_TRIES 2
#define SET_CONFIG_TRIES (2 * (use_both_schemes + 1))
-#define USE_NEW_SCHEME(i, scheme) ((i) / 2 == (int)scheme)
+#define USE_NEW_SCHEME(i, scheme) ((i) / 2 == (int)(scheme))
#define HUB_ROOT_RESET_TIME 60 /* times are in msec */
#define HUB_SHORT_RESET_TIME 10
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 0c960a9..154f3f3 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2467,6 +2467,13 @@ static int dwc3_gadget_ep_reclaim_trb_linear(struct dwc3_ep *dep,
static bool dwc3_gadget_ep_request_completed(struct dwc3_request *req)
{
+ /*
+ * For OUT direction, host may send less than the setup
+ * length. Return true for all OUT requests.
+ */
+ if (!req->direction)
+ return true;
+
return req->request.actual == req->request.length;
}
diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig
index ae70ce2..797d6ac 100644
--- a/drivers/usb/gadget/udc/Kconfig
+++ b/drivers/usb/gadget/udc/Kconfig
@@ -445,6 +445,7 @@
tristate "NVIDIA Tegra Superspeed USB 3.0 Device Controller"
depends on ARCH_TEGRA || COMPILE_TEST
depends on PHY_TEGRA_XUSB
+ select USB_ROLE_SWITCH
help
Enables NVIDIA Tegra USB 3.0 device mode controller driver.
diff --git a/drivers/usb/host/ohci-da8xx.c b/drivers/usb/host/ohci-da8xx.c
index 38183ac..1371b0c 100644
--- a/drivers/usb/host/ohci-da8xx.c
+++ b/drivers/usb/host/ohci-da8xx.c
@@ -415,13 +415,17 @@ static int ohci_da8xx_probe(struct platform_device *pdev)
}
da8xx_ohci->oc_gpio = devm_gpiod_get_optional(dev, "oc", GPIOD_IN);
- if (IS_ERR(da8xx_ohci->oc_gpio))
+ if (IS_ERR(da8xx_ohci->oc_gpio)) {
+ error = PTR_ERR(da8xx_ohci->oc_gpio);
goto err;
+ }
if (da8xx_ohci->oc_gpio) {
oc_irq = gpiod_to_irq(da8xx_ohci->oc_gpio);
- if (oc_irq < 0)
+ if (oc_irq < 0) {
+ error = oc_irq;
goto err;
+ }
error = devm_request_threaded_irq(dev, oc_irq, NULL,
ohci_da8xx_oc_thread, IRQF_TRIGGER_RISING |
diff --git a/drivers/usb/musb/jz4740.c b/drivers/usb/musb/jz4740.c
index 5261f8d..e3b8c84 100644
--- a/drivers/usb/musb/jz4740.c
+++ b/drivers/usb/musb/jz4740.c
@@ -75,14 +75,17 @@ static struct musb_hdrc_platform_data jz4740_musb_platform_data = {
static int jz4740_musb_init(struct musb *musb)
{
struct device *dev = musb->controller->parent;
+ int err;
if (dev->of_node)
musb->xceiv = devm_usb_get_phy_by_phandle(dev, "phys", 0);
else
musb->xceiv = devm_usb_get_phy(dev, USB_PHY_TYPE_USB2);
if (IS_ERR(musb->xceiv)) {
- dev_err(dev, "No transceiver configured\n");
- return PTR_ERR(musb->xceiv);
+ err = PTR_ERR(musb->xceiv);
+ if (err != -EPROBE_DEFER)
+ dev_err(dev, "No transceiver configured: %d", err);
+ return err;
}
/* Silicon does not implement ConfigData register.
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 15cca91..5ebf30b 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1840,6 +1840,9 @@ ATTRIBUTE_GROUPS(musb);
#define MUSB_QUIRK_B_INVALID_VBUS_91 (MUSB_DEVCTL_BDEVICE | \
(2 << MUSB_DEVCTL_VBUS_SHIFT) | \
MUSB_DEVCTL_SESSION)
+#define MUSB_QUIRK_B_DISCONNECT_99 (MUSB_DEVCTL_BDEVICE | \
+ (3 << MUSB_DEVCTL_VBUS_SHIFT) | \
+ MUSB_DEVCTL_SESSION)
#define MUSB_QUIRK_A_DISCONNECT_19 ((3 << MUSB_DEVCTL_VBUS_SHIFT) | \
MUSB_DEVCTL_SESSION)
@@ -1862,6 +1865,11 @@ static void musb_pm_runtime_check_session(struct musb *musb)
s = MUSB_DEVCTL_FSDEV | MUSB_DEVCTL_LSDEV |
MUSB_DEVCTL_HR;
switch (devctl & ~s) {
+ case MUSB_QUIRK_B_DISCONNECT_99:
+ musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n");
+ schedule_delayed_work(&musb->irq_work,
+ msecs_to_jiffies(1000));
+ break;
case MUSB_QUIRK_B_INVALID_VBUS_91:
if (musb->quirk_retries && !musb->flush_irq_work) {
musb_dbg(musb,
@@ -2310,6 +2318,9 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
musb_disable_interrupts(musb);
musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
+ /* MUSB_POWER_SOFTCONN might be already set, JZ4740 does this. */
+ musb_writeb(musb->mregs, MUSB_POWER, 0);
+
/* Init IRQ workqueue before request_irq */
INIT_DELAYED_WORK(&musb->irq_work, musb_irq_work);
INIT_DELAYED_WORK(&musb->deassert_reset_work, musb_deassert_reset);
diff --git a/drivers/usb/musb/musbhsdma.c b/drivers/usb/musb/musbhsdma.c
index 5fc6825..2d3751d 100644
--- a/drivers/usb/musb/musbhsdma.c
+++ b/drivers/usb/musb/musbhsdma.c
@@ -425,7 +425,7 @@ struct dma_controller *musbhs_dma_controller_create(struct musb *musb,
controller->controller.channel_abort = dma_channel_abort;
if (request_irq(irq, dma_controller_irq, 0,
- dev_name(musb->controller), &controller->controller)) {
+ dev_name(musb->controller), controller)) {
dev_err(dev, "request_irq %d failed!\n", irq);
musb_dma_controller_destroy(&controller->controller);
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index df582fe..d3f420f 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -642,9 +642,13 @@ static int ch341_tiocmget(struct tty_struct *tty)
static int ch341_reset_resume(struct usb_serial *serial)
{
struct usb_serial_port *port = serial->port[0];
- struct ch341_private *priv = usb_get_serial_port_data(port);
+ struct ch341_private *priv;
int ret;
+ priv = usb_get_serial_port_data(port);
+ if (!priv)
+ return 0;
+
/* reconfigure ch341 serial port after bus-reset */
ch341_configure(serial->dev, priv);
diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index 9690a5f..5737add 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -716,7 +716,7 @@ static void edge_interrupt_callback(struct urb *urb)
if (txCredits) {
port = edge_serial->serial->port[portNumber];
edge_port = usb_get_serial_port_data(port);
- if (edge_port->open) {
+ if (edge_port && edge_port->open) {
spin_lock_irqsave(&edge_port->ep_lock,
flags);
edge_port->txCredits += txCredits;
@@ -1725,7 +1725,8 @@ static void edge_break(struct tty_struct *tty, int break_state)
static void process_rcvd_data(struct edgeport_serial *edge_serial,
unsigned char *buffer, __u16 bufferLength)
{
- struct device *dev = &edge_serial->serial->dev->dev;
+ struct usb_serial *serial = edge_serial->serial;
+ struct device *dev = &serial->dev->dev;
struct usb_serial_port *port;
struct edgeport_port *edge_port;
__u16 lastBufferLength;
@@ -1821,11 +1822,10 @@ static void process_rcvd_data(struct edgeport_serial *edge_serial,
/* spit this data back into the tty driver if this
port is open */
- if (rxLen) {
- port = edge_serial->serial->port[
- edge_serial->rxPort];
+ if (rxLen && edge_serial->rxPort < serial->num_ports) {
+ port = serial->port[edge_serial->rxPort];
edge_port = usb_get_serial_port_data(port);
- if (edge_port->open) {
+ if (edge_port && edge_port->open) {
dev_dbg(dev, "%s - Sending %d bytes to TTY for port %d\n",
__func__, rxLen,
edge_serial->rxPort);
@@ -1833,8 +1833,8 @@ static void process_rcvd_data(struct edgeport_serial *edge_serial,
rxLen);
edge_port->port->icount.rx += rxLen;
}
- buffer += rxLen;
}
+ buffer += rxLen;
break;
case EXPECT_HDR3: /* Expect 3rd byte of status header */
@@ -1869,6 +1869,8 @@ static void process_rcvd_status(struct edgeport_serial *edge_serial,
__u8 code = edge_serial->rxStatusCode;
/* switch the port pointer to the one being currently talked about */
+ if (edge_serial->rxPort >= edge_serial->serial->num_ports)
+ return;
port = edge_serial->serial->port[edge_serial->rxPort];
edge_port = usb_get_serial_port_data(port);
if (edge_port == NULL) {
diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index e66a59e..aa3dbce 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -1058,6 +1058,8 @@ static void usa49_glocont_callback(struct urb *urb)
for (i = 0; i < serial->num_ports; ++i) {
port = serial->port[i];
p_priv = usb_get_serial_port_data(port);
+ if (!p_priv)
+ continue;
if (p_priv->resend_cont) {
dev_dbg(&port->dev, "%s - sending setup\n", __func__);
@@ -1459,6 +1461,8 @@ static void usa67_glocont_callback(struct urb *urb)
for (i = 0; i < serial->num_ports; ++i) {
port = serial->port[i];
p_priv = usb_get_serial_port_data(port);
+ if (!p_priv)
+ continue;
if (p_priv->resend_cont) {
dev_dbg(&port->dev, "%s - sending setup\n", __func__);
diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c
index cb7aac9..ed2b4e6 100644
--- a/drivers/usb/serial/opticon.c
+++ b/drivers/usb/serial/opticon.c
@@ -113,7 +113,7 @@ static int send_control_msg(struct usb_serial_port *port, u8 requesttype,
retval = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0),
requesttype,
USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
- 0, 0, buffer, 1, 0);
+ 0, 0, buffer, 1, USB_CTRL_SET_TIMEOUT);
kfree(buffer);
if (retval < 0)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index e9491d4..084cc2f 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -248,6 +248,7 @@ static void option_instat_callback(struct urb *urb);
#define QUECTEL_PRODUCT_BG96 0x0296
#define QUECTEL_PRODUCT_EP06 0x0306
#define QUECTEL_PRODUCT_EM12 0x0512
+#define QUECTEL_PRODUCT_RM500Q 0x0800
#define CMOTECH_VENDOR_ID 0x16d8
#define CMOTECH_PRODUCT_6001 0x6001
@@ -567,6 +568,9 @@ static void option_instat_callback(struct urb *urb);
/* Interface must have two endpoints */
#define NUMEP2 BIT(16)
+/* Device needs ZLP */
+#define ZLP BIT(17)
+
static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
@@ -1101,6 +1105,11 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0xff, 0xff),
.driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x30) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10),
+ .driver_info = ZLP },
+
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),
@@ -1172,6 +1181,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = NCTRL(0) | RSVD(3) },
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1102, 0xff), /* Telit ME910 (ECM) */
.driver_info = NCTRL(0) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x110a, 0xff), /* Telit ME910G1 */
+ .driver_info = NCTRL(0) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
@@ -1196,6 +1207,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = NCTRL(0) | RSVD(1) },
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1901, 0xff), /* Telit LN940 (MBIM) */
.driver_info = NCTRL(0) },
+ { USB_DEVICE(TELIT_VENDOR_ID, 0x9010), /* Telit SBL FN980 flashing device */
+ .driver_info = NCTRL(0) | ZLP },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff),
.driver_info = RSVD(1) },
@@ -2097,6 +2110,9 @@ static int option_attach(struct usb_serial *serial)
if (!(device_flags & NCTRL(iface_desc->bInterfaceNumber)))
data->use_send_setup = 1;
+ if (device_flags & ZLP)
+ data->use_zlp = 1;
+
spin_lock_init(&data->susp_lock);
usb_set_serial_data(serial, data);
diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c
index a62981c..f93b81a 100644
--- a/drivers/usb/serial/quatech2.c
+++ b/drivers/usb/serial/quatech2.c
@@ -841,7 +841,10 @@ static void qt2_update_msr(struct usb_serial_port *port, unsigned char *ch)
u8 newMSR = (u8) *ch;
unsigned long flags;
+ /* May be called from qt2_process_read_urb() for an unbound port. */
port_priv = usb_get_serial_port_data(port);
+ if (!port_priv)
+ return;
spin_lock_irqsave(&port_priv->lock, flags);
port_priv->shadowMSR = newMSR;
@@ -869,7 +872,10 @@ static void qt2_update_lsr(struct usb_serial_port *port, unsigned char *ch)
unsigned long flags;
u8 newLSR = (u8) *ch;
+ /* May be called from qt2_process_read_urb() for an unbound port. */
port_priv = usb_get_serial_port_data(port);
+ if (!port_priv)
+ return;
if (newLSR & UART_LSR_BI)
newLSR &= (u8) (UART_LSR_OE | UART_LSR_BI);
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index edbbb13..bd23a7c 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -86,6 +86,8 @@ DEVICE(moto_modem, MOTO_IDS);
#define MOTOROLA_TETRA_IDS() \
{ USB_DEVICE(0x0cad, 0x9011) }, /* Motorola Solutions TETRA PEI */ \
{ USB_DEVICE(0x0cad, 0x9012) }, /* MTP6550 */ \
+ { USB_DEVICE(0x0cad, 0x9013) }, /* MTP3xxx */ \
+ { USB_DEVICE(0x0cad, 0x9015) }, /* MTP85xx */ \
{ USB_DEVICE(0x0cad, 0x9016) } /* TPG2200 */
DEVICE(motorola_tetra, MOTOROLA_TETRA_IDS);
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 8f066bb..dc7a65b 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -1317,6 +1317,9 @@ static int usb_serial_register(struct usb_serial_driver *driver)
return -EINVAL;
}
+ /* Prevent individual ports from being unbound. */
+ driver->driver.suppress_bind_attrs = true;
+
usb_serial_operations_init(driver);
/* Add this device to our list of devices */
diff --git a/drivers/usb/serial/usb-wwan.h b/drivers/usb/serial/usb-wwan.h
index 1c120ea..934e936 100644
--- a/drivers/usb/serial/usb-wwan.h
+++ b/drivers/usb/serial/usb-wwan.h
@@ -38,6 +38,7 @@ struct usb_wwan_intf_private {
spinlock_t susp_lock;
unsigned int suspended:1;
unsigned int use_send_setup:1;
+ unsigned int use_zlp:1;
int in_flight;
unsigned int open_ports;
void *private;
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index 7e855c8..13be21a 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -461,6 +461,7 @@ static struct urb *usb_wwan_setup_urb(struct usb_serial_port *port,
void (*callback) (struct urb *))
{
struct usb_serial *serial = port->serial;
+ struct usb_wwan_intf_private *intfdata = usb_get_serial_data(serial);
struct urb *urb;
urb = usb_alloc_urb(0, GFP_KERNEL); /* No ISO */
@@ -471,6 +472,9 @@ static struct urb *usb_wwan_setup_urb(struct usb_serial_port *port,
usb_sndbulkpipe(serial->dev, endpoint) | dir,
buf, len, callback, ctx);
+ if (intfdata->use_zlp && dir == USB_DIR_OUT)
+ urb->transfer_flags |= URB_ZERO_PACKET;
+
return urb;
}
diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c
index c1f7073..8b4ff9ff 100644
--- a/drivers/usb/typec/tcpm/tcpci.c
+++ b/drivers/usb/typec/tcpm/tcpci.c
@@ -432,20 +432,30 @@ irqreturn_t tcpci_irq(struct tcpci *tcpci)
if (status & TCPC_ALERT_RX_STATUS) {
struct pd_message msg;
- unsigned int cnt;
+ unsigned int cnt, payload_cnt;
u16 header;
regmap_read(tcpci->regmap, TCPC_RX_BYTE_CNT, &cnt);
+ /*
+ * 'cnt' corresponds to READABLE_BYTE_COUNT in section 4.4.14
+ * of the TCPCI spec [Rev 2.0 Ver 1.0 October 2017] and is
+ * defined in table 4-36 as one greater than the number of
+ * bytes received. And that number includes the header. So:
+ */
+ if (cnt > 3)
+ payload_cnt = cnt - (1 + sizeof(msg.header));
+ else
+ payload_cnt = 0;
tcpci_read16(tcpci, TCPC_RX_HDR, &header);
msg.header = cpu_to_le16(header);
- if (WARN_ON(cnt > sizeof(msg.payload)))
- cnt = sizeof(msg.payload);
+ if (WARN_ON(payload_cnt > sizeof(msg.payload)))
+ payload_cnt = sizeof(msg.payload);
- if (cnt > 0)
+ if (payload_cnt > 0)
regmap_raw_read(tcpci->regmap, TCPC_RX_DATA,
- &msg.payload, cnt);
+ &msg.payload, payload_cnt);
/* Read complete, clear RX status alert bit */
tcpci_write16(tcpci, TCPC_ALERT, TCPC_ALERT_RX_STATUS);
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index 8569bbd..831c947 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -94,15 +94,15 @@ void ucsi_connector_change(struct ucsi *ucsi, u8 num);
#define UCSI_ENABLE_NTFY_CMD_COMPLETE BIT(16)
#define UCSI_ENABLE_NTFY_EXT_PWR_SRC_CHANGE BIT(17)
#define UCSI_ENABLE_NTFY_PWR_OPMODE_CHANGE BIT(18)
-#define UCSI_ENABLE_NTFY_CAP_CHANGE BIT(19)
-#define UCSI_ENABLE_NTFY_PWR_LEVEL_CHANGE BIT(20)
-#define UCSI_ENABLE_NTFY_PD_RESET_COMPLETE BIT(21)
-#define UCSI_ENABLE_NTFY_CAM_CHANGE BIT(22)
-#define UCSI_ENABLE_NTFY_BAT_STATUS_CHANGE BIT(23)
-#define UCSI_ENABLE_NTFY_PARTNER_CHANGE BIT(24)
-#define UCSI_ENABLE_NTFY_PWR_DIR_CHANGE BIT(25)
-#define UCSI_ENABLE_NTFY_CONNECTOR_CHANGE BIT(26)
-#define UCSI_ENABLE_NTFY_ERROR BIT(27)
+#define UCSI_ENABLE_NTFY_CAP_CHANGE BIT(21)
+#define UCSI_ENABLE_NTFY_PWR_LEVEL_CHANGE BIT(22)
+#define UCSI_ENABLE_NTFY_PD_RESET_COMPLETE BIT(23)
+#define UCSI_ENABLE_NTFY_CAM_CHANGE BIT(24)
+#define UCSI_ENABLE_NTFY_BAT_STATUS_CHANGE BIT(25)
+#define UCSI_ENABLE_NTFY_PARTNER_CHANGE BIT(27)
+#define UCSI_ENABLE_NTFY_PWR_DIR_CHANGE BIT(28)
+#define UCSI_ENABLE_NTFY_CONNECTOR_CHANGE BIT(30)
+#define UCSI_ENABLE_NTFY_ERROR BIT(31)
#define UCSI_ENABLE_NTFY_ALL 0xdbe70000
/* SET_UOR command bits */
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 1679e0d..cec868f 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -687,6 +687,7 @@
config MAX77620_WATCHDOG
tristate "Maxim Max77620 Watchdog Timer"
depends on MFD_MAX77620 || COMPILE_TEST
+ select WATCHDOG_CORE
help
This is the driver for the Max77620 watchdog timer.
Say 'Y' here to enable the watchdog timer support for
@@ -1444,6 +1445,7 @@
config TQMX86_WDT
tristate "TQ-Systems TQMX86 Watchdog Timer"
depends on X86
+ select WATCHDOG_CORE
help
This is the driver for the hardware watchdog timer in the TQMX86 IO
controller found on some of their ComExpress Modules.
diff --git a/drivers/watchdog/imx7ulp_wdt.c b/drivers/watchdog/imx7ulp_wdt.c
index 0a87c6f4..11b9e7c 100644
--- a/drivers/watchdog/imx7ulp_wdt.c
+++ b/drivers/watchdog/imx7ulp_wdt.c
@@ -112,7 +112,7 @@ static int imx7ulp_wdt_restart(struct watchdog_device *wdog,
{
struct imx7ulp_wdt_device *wdt = watchdog_get_drvdata(wdog);
- imx7ulp_wdt_enable(wdt->base, true);
+ imx7ulp_wdt_enable(wdog, true);
imx7ulp_wdt_set_timeout(&wdt->wdd, 1);
/* wait for wdog to fire */
diff --git a/drivers/watchdog/orion_wdt.c b/drivers/watchdog/orion_wdt.c
index 1cccf8e..8e6dfe7 100644
--- a/drivers/watchdog/orion_wdt.c
+++ b/drivers/watchdog/orion_wdt.c
@@ -602,7 +602,7 @@ static int orion_wdt_probe(struct platform_device *pdev)
set_bit(WDOG_HW_RUNNING, &dev->wdt.status);
/* Request the IRQ only after the watchdog is disabled */
- irq = platform_get_irq(pdev, 0);
+ irq = platform_get_irq_optional(pdev, 0);
if (irq > 0) {
/*
* Not all supported platforms specify an interrupt for the
@@ -617,7 +617,7 @@ static int orion_wdt_probe(struct platform_device *pdev)
}
/* Optional 2nd interrupt for pretimeout */
- irq = platform_get_irq(pdev, 1);
+ irq = platform_get_irq_optional(pdev, 1);
if (irq > 0) {
orion_wdt_info.options |= WDIOF_PRETIMEOUT;
ret = devm_request_irq(&pdev->dev, irq, orion_wdt_pre_irq,
diff --git a/drivers/watchdog/rn5t618_wdt.c b/drivers/watchdog/rn5t618_wdt.c
index 2348760..6e524c8 100644
--- a/drivers/watchdog/rn5t618_wdt.c
+++ b/drivers/watchdog/rn5t618_wdt.c
@@ -188,6 +188,7 @@ static struct platform_driver rn5t618_wdt_driver = {
module_platform_driver(rn5t618_wdt_driver);
+MODULE_ALIAS("platform:rn5t618-wdt");
MODULE_AUTHOR("Beniamino Galvani <b.galvani@gmail.com>");
MODULE_DESCRIPTION("RN5T618 watchdog driver");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/watchdog/w83627hf_wdt.c b/drivers/watchdog/w83627hf_wdt.c
index fdf533f..56a4a40 100644
--- a/drivers/watchdog/w83627hf_wdt.c
+++ b/drivers/watchdog/w83627hf_wdt.c
@@ -420,7 +420,7 @@ static int wdt_find(int addr)
cr_wdt_csr = NCT6102D_WDT_CSR;
break;
case NCT6116_ID:
- ret = nct6102;
+ ret = nct6116;
cr_wdt_timeout = NCT6102D_WDT_TIMEOUT;
cr_wdt_control = NCT6102D_WDT_CONTROL;
cr_wdt_csr = NCT6102D_WDT_CSR;
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 497f979..5c794f4 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -908,6 +908,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
struct afs_vnode *dvnode = AFS_FS_I(dir);
+ struct afs_fid fid = {};
struct inode *inode;
struct dentry *d;
struct key *key;
@@ -951,21 +952,18 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
afs_stat_v(dvnode, n_lookup);
inode = afs_do_lookup(dir, dentry, key);
key_put(key);
- if (inode == ERR_PTR(-ENOENT)) {
+ if (inode == ERR_PTR(-ENOENT))
inode = afs_try_auto_mntpt(dentry, dir);
- } else {
- dentry->d_fsdata =
- (void *)(unsigned long)dvnode->status.data_version;
- }
+
+ if (!IS_ERR_OR_NULL(inode))
+ fid = AFS_FS_I(inode)->fid;
+
d = d_splice_alias(inode, dentry);
if (!IS_ERR_OR_NULL(d)) {
d->d_fsdata = dentry->d_fsdata;
- trace_afs_lookup(dvnode, &d->d_name,
- inode ? AFS_FS_I(inode) : NULL);
+ trace_afs_lookup(dvnode, &d->d_name, &fid);
} else {
- trace_afs_lookup(dvnode, &dentry->d_name,
- IS_ERR_OR_NULL(inode) ? NULL
- : AFS_FS_I(inode));
+ trace_afs_lookup(dvnode, &dentry->d_name, &fid);
}
return d;
}
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index ee834ef..43e1660 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -447,7 +447,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
if (blkcg_css) {
bio->bi_opf |= REQ_CGROUP_PUNT;
- bio_associate_blkg_from_css(bio, blkcg_css);
+ kthread_associate_blkcg(blkcg_css);
}
refcount_set(&cb->pending_bios, 1);
@@ -491,6 +491,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
bio->bi_opf = REQ_OP_WRITE | write_flags;
bio->bi_private = cb;
bio->bi_end_io = end_compressed_bio_write;
+ if (blkcg_css)
+ bio->bi_opf |= REQ_CGROUP_PUNT;
bio_add_page(bio, page, PAGE_SIZE, 0);
}
if (bytes_left < PAGE_SIZE) {
@@ -517,6 +519,9 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
bio_endio(bio);
}
+ if (blkcg_css)
+ kthread_associate_blkcg(NULL);
+
return 0;
}
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f639dde..ba4d8f37 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -500,11 +500,8 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
&dev_replace->scrub_progress, 0, 1);
ret = btrfs_dev_replace_finishing(fs_info, ret);
- if (ret == -EINPROGRESS) {
+ if (ret == -EINPROGRESS)
ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
- } else if (ret != -ECANCELED) {
- WARN_ON(ret);
- }
return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e3c7664..c70baaf 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1479,10 +1479,10 @@ static noinline int run_delalloc_nocow(struct inode *inode,
disk_num_bytes =
btrfs_file_extent_disk_num_bytes(leaf, fi);
/*
- * If extent we got ends before our range starts, skip
- * to next extent
+ * If the extent we got ends before our current offset,
+ * skip to the next extent.
*/
- if (extent_end <= start) {
+ if (extent_end <= cur_offset) {
path->slots[0]++;
goto next_slot;
}
@@ -4238,18 +4238,30 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
}
static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
- struct inode *dir, u64 objectid,
- const char *name, int name_len)
+ struct inode *dir, struct dentry *dentry)
{
struct btrfs_root *root = BTRFS_I(dir)->root;
+ struct btrfs_inode *inode = BTRFS_I(d_inode(dentry));
struct btrfs_path *path;
struct extent_buffer *leaf;
struct btrfs_dir_item *di;
struct btrfs_key key;
+ const char *name = dentry->d_name.name;
+ int name_len = dentry->d_name.len;
u64 index;
int ret;
+ u64 objectid;
u64 dir_ino = btrfs_ino(BTRFS_I(dir));
+ if (btrfs_ino(inode) == BTRFS_FIRST_FREE_OBJECTID) {
+ objectid = inode->root->root_key.objectid;
+ } else if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) {
+ objectid = inode->location.objectid;
+ } else {
+ WARN_ON(1);
+ return -EINVAL;
+ }
+
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
@@ -4271,13 +4283,16 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
}
btrfs_release_path(path);
- ret = btrfs_del_root_ref(trans, objectid, root->root_key.objectid,
- dir_ino, &index, name, name_len);
- if (ret < 0) {
- if (ret != -ENOENT) {
- btrfs_abort_transaction(trans, ret);
- goto out;
- }
+ /*
+ * This is a placeholder inode for a subvolume we didn't have a
+ * reference to at the time of the snapshot creation. In the meantime
+ * we could have renamed the real subvol link into our snapshot, so
+ * depending on btrfs_del_root_ref to return -ENOENT here is incorret.
+ * Instead simply lookup the dir_index_item for this entry so we can
+ * remove it. Otherwise we know we have a ref to the root and we can
+ * call btrfs_del_root_ref, and it _shouldn't_ fail.
+ */
+ if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) {
di = btrfs_search_dir_index_item(root, path, dir_ino,
name, name_len);
if (IS_ERR_OR_NULL(di)) {
@@ -4292,8 +4307,16 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
index = key.offset;
+ btrfs_release_path(path);
+ } else {
+ ret = btrfs_del_root_ref(trans, objectid,
+ root->root_key.objectid, dir_ino,
+ &index, name, name_len);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
}
- btrfs_release_path(path);
ret = btrfs_delete_delayed_dir_index(trans, BTRFS_I(dir), index);
if (ret) {
@@ -4487,8 +4510,7 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
- ret = btrfs_unlink_subvol(trans, dir, dest->root_key.objectid,
- dentry->d_name.name, dentry->d_name.len);
+ ret = btrfs_unlink_subvol(trans, dir, dentry);
if (ret) {
err = ret;
btrfs_abort_transaction(trans, ret);
@@ -4583,10 +4605,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
return PTR_ERR(trans);
if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
- err = btrfs_unlink_subvol(trans, dir,
- BTRFS_I(inode)->location.objectid,
- dentry->d_name.name,
- dentry->d_name.len);
+ err = btrfs_unlink_subvol(trans, dir, dentry);
goto out;
}
@@ -9536,7 +9555,6 @@ static int btrfs_rename_exchange(struct inode *old_dir,
u64 new_ino = btrfs_ino(BTRFS_I(new_inode));
u64 old_idx = 0;
u64 new_idx = 0;
- u64 root_objectid;
int ret;
bool root_log_pinned = false;
bool dest_log_pinned = false;
@@ -9642,10 +9660,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
/* src is a subvolume */
if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
- root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
- ret = btrfs_unlink_subvol(trans, old_dir, root_objectid,
- old_dentry->d_name.name,
- old_dentry->d_name.len);
+ ret = btrfs_unlink_subvol(trans, old_dir, old_dentry);
} else { /* src is an inode */
ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir),
BTRFS_I(old_dentry->d_inode),
@@ -9661,10 +9676,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
/* dest is a subvolume */
if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
- root_objectid = BTRFS_I(new_inode)->root->root_key.objectid;
- ret = btrfs_unlink_subvol(trans, new_dir, root_objectid,
- new_dentry->d_name.name,
- new_dentry->d_name.len);
+ ret = btrfs_unlink_subvol(trans, new_dir, new_dentry);
} else { /* dest is an inode */
ret = __btrfs_unlink_inode(trans, dest, BTRFS_I(new_dir),
BTRFS_I(new_dentry->d_inode),
@@ -9862,7 +9874,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_inode = d_inode(new_dentry);
struct inode *old_inode = d_inode(old_dentry);
u64 index = 0;
- u64 root_objectid;
int ret;
u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
bool log_pinned = false;
@@ -9970,10 +9981,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
BTRFS_I(old_inode), 1);
if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
- root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
- ret = btrfs_unlink_subvol(trans, old_dir, root_objectid,
- old_dentry->d_name.name,
- old_dentry->d_name.len);
+ ret = btrfs_unlink_subvol(trans, old_dir, old_dentry);
} else {
ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir),
BTRFS_I(d_inode(old_dentry)),
@@ -9992,10 +10000,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
new_inode->i_ctime = current_time(new_inode);
if (unlikely(btrfs_ino(BTRFS_I(new_inode)) ==
BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
- root_objectid = BTRFS_I(new_inode)->location.objectid;
- ret = btrfs_unlink_subvol(trans, new_dir, root_objectid,
- new_dentry->d_name.name,
- new_dentry->d_name.len);
+ ret = btrfs_unlink_subvol(trans, new_dir, new_dentry);
BUG_ON(new_inode->i_nlink == 0);
} else {
ret = btrfs_unlink_inode(trans, dest, BTRFS_I(new_dir),
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 18e328c..12ae31e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4252,7 +4252,19 @@ static long btrfs_ioctl_scrub(struct file *file, void __user *arg)
&sa->progress, sa->flags & BTRFS_SCRUB_READONLY,
0);
- if (ret == 0 && copy_to_user(arg, sa, sizeof(*sa)))
+ /*
+ * Copy scrub args to user space even if btrfs_scrub_dev() returned an
+ * error. This is important as it allows user space to know how much
+ * progress scrub has done. For example, if scrub is canceled we get
+ * -ECANCELED from btrfs_scrub_dev() and return that error back to user
+ * space. Later user space can inspect the progress from the structure
+ * btrfs_ioctl_scrub_args and resume scrub from where it left off
+ * previously (btrfs-progs does this).
+ * If we fail to copy the btrfs_ioctl_scrub_args structure to user space
+ * then return -EFAULT to signal the structure was not copied or it may
+ * be corrupt and unreliable due to a partial copy.
+ */
+ if (copy_to_user(arg, sa, sizeof(*sa)))
ret = -EFAULT;
if (!(sa->flags & BTRFS_SCRUB_READONLY))
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d4282e1..39fc8c3 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2423,8 +2423,12 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
u64 nr_old_roots = 0;
int ret = 0;
+ /*
+ * If quotas get disabled meanwhile, the resouces need to be freed and
+ * we can't just exit here.
+ */
if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
- return 0;
+ goto out_free;
if (new_roots) {
if (!maybe_fs_roots(new_roots))
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index c582457..da5abd6 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -517,6 +517,34 @@ static int update_backref_cache(struct btrfs_trans_handle *trans,
return 1;
}
+static bool reloc_root_is_dead(struct btrfs_root *root)
+{
+ /*
+ * Pair with set_bit/clear_bit in clean_dirty_subvols and
+ * btrfs_update_reloc_root. We need to see the updated bit before
+ * trying to access reloc_root
+ */
+ smp_rmb();
+ if (test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state))
+ return true;
+ return false;
+}
+
+/*
+ * Check if this subvolume tree has valid reloc tree.
+ *
+ * Reloc tree after swap is considered dead, thus not considered as valid.
+ * This is enough for most callers, as they don't distinguish dead reloc root
+ * from no reloc root. But should_ignore_root() below is a special case.
+ */
+static bool have_reloc_root(struct btrfs_root *root)
+{
+ if (reloc_root_is_dead(root))
+ return false;
+ if (!root->reloc_root)
+ return false;
+ return true;
+}
static int should_ignore_root(struct btrfs_root *root)
{
@@ -525,6 +553,10 @@ static int should_ignore_root(struct btrfs_root *root)
if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
return 0;
+ /* This root has been merged with its reloc tree, we can ignore it */
+ if (reloc_root_is_dead(root))
+ return 1;
+
reloc_root = root->reloc_root;
if (!reloc_root)
return 0;
@@ -1439,7 +1471,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
* The subvolume has reloc tree but the swap is finished, no need to
* create/update the dead reloc tree
*/
- if (test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state))
+ if (reloc_root_is_dead(root))
return 0;
if (root->reloc_root) {
@@ -1478,8 +1510,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
struct btrfs_root_item *root_item;
int ret;
- if (test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state) ||
- !root->reloc_root)
+ if (!have_reloc_root(root))
goto out;
reloc_root = root->reloc_root;
@@ -1489,6 +1520,11 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
if (fs_info->reloc_ctl->merge_reloc_tree &&
btrfs_root_refs(root_item) == 0) {
set_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state);
+ /*
+ * Mark the tree as dead before we change reloc_root so
+ * have_reloc_root will not touch it from now on.
+ */
+ smp_wmb();
__del_reloc_root(reloc_root);
}
@@ -2201,6 +2237,11 @@ static int clean_dirty_subvols(struct reloc_control *rc)
if (ret2 < 0 && !ret)
ret = ret2;
}
+ /*
+ * Need barrier to ensure clear_bit() only happens after
+ * root->reloc_root = NULL. Pairs with have_reloc_root.
+ */
+ smp_wmb();
clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state);
btrfs_put_fs_root(root);
} else {
@@ -4718,7 +4759,7 @@ void btrfs_reloc_pre_snapshot(struct btrfs_pending_snapshot *pending,
struct btrfs_root *root = pending->root;
struct reloc_control *rc = root->fs_info->reloc_ctl;
- if (!root->reloc_root || !rc)
+ if (!rc || !have_reloc_root(root))
return;
if (!rc->merge_reloc_tree)
@@ -4752,7 +4793,7 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
struct reloc_control *rc = root->fs_info->reloc_ctl;
int ret;
- if (!root->reloc_root || !rc)
+ if (!rc || !have_reloc_root(root))
return 0;
rc = root->fs_info->reloc_ctl;
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 3b17b64..612411c7 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -376,11 +376,13 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
leaf = path->nodes[0];
ref = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_root_ref);
-
- WARN_ON(btrfs_root_ref_dirid(leaf, ref) != dirid);
- WARN_ON(btrfs_root_ref_name_len(leaf, ref) != name_len);
ptr = (unsigned long)(ref + 1);
- WARN_ON(memcmp_extent_buffer(leaf, name, ptr, name_len));
+ if ((btrfs_root_ref_dirid(leaf, ref) != dirid) ||
+ (btrfs_root_ref_name_len(leaf, ref) != name_len) ||
+ memcmp_extent_buffer(leaf, name, ptr, name_len)) {
+ err = -ENOENT;
+ goto out;
+ }
*sequence = btrfs_root_ref_sequence(leaf, ref);
ret = btrfs_del_item(trans, tree_root, path);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 21de630..fd266a2 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3577,17 +3577,27 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
* This can easily boost the amount of SYSTEM chunks if cleaner
* thread can't be triggered fast enough, and use up all space
* of btrfs_super_block::sys_chunk_array
+ *
+ * While for dev replace, we need to try our best to mark block
+ * group RO, to prevent race between:
+ * - Write duplication
+ * Contains latest data
+ * - Scrub copy
+ * Contains data from commit tree
+ *
+ * If target block group is not marked RO, nocow writes can
+ * be overwritten by scrub copy, causing data corruption.
+ * So for dev-replace, it's not allowed to continue if a block
+ * group is not RO.
*/
- ret = btrfs_inc_block_group_ro(cache, false);
- scrub_pause_off(fs_info);
-
+ ret = btrfs_inc_block_group_ro(cache, sctx->is_dev_replace);
if (ret == 0) {
ro_set = 1;
- } else if (ret == -ENOSPC) {
+ } else if (ret == -ENOSPC && !sctx->is_dev_replace) {
/*
* btrfs_inc_block_group_ro return -ENOSPC when it
* failed in creating new chunk for metadata.
- * It is not a problem for scrub/replace, because
+ * It is not a problem for scrub, because
* metadata are always cowed, and our scrub paused
* commit_transactions.
*/
@@ -3596,9 +3606,22 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
btrfs_warn(fs_info,
"failed setting block group ro: %d", ret);
btrfs_put_block_group(cache);
+ scrub_pause_off(fs_info);
break;
}
+ /*
+ * Now the target block is marked RO, wait for nocow writes to
+ * finish before dev-replace.
+ * COW is fine, as COW never overwrites extents in commit tree.
+ */
+ if (sctx->is_dev_replace) {
+ btrfs_wait_nocow_writers(cache);
+ btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->start,
+ cache->length);
+ }
+
+ scrub_pause_off(fs_info);
down_write(&dev_replace->rwsem);
dev_replace->cursor_right = found_key.offset + length;
dev_replace->cursor_left = found_key.offset;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a6d3f08..9b78e72 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3881,7 +3881,11 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
}
}
- num_devices = btrfs_num_devices(fs_info);
+ /*
+ * rw_devices will not change at the moment, device add/delete/replace
+ * are excluded by EXCL_OP
+ */
+ num_devices = fs_info->fs_devices->rw_devices;
/*
* SINGLE profile on-disk has no profile bit, but in-memory we have a
diff --git a/fs/buffer.c b/fs/buffer.c
index d8c7242..18a87ec 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3031,11 +3031,9 @@ static void end_bio_bh_io_sync(struct bio *bio)
* errors, this only handles the "we need to be able to
* do IO at the final sector" case.
*/
-void guard_bio_eod(int op, struct bio *bio)
+void guard_bio_eod(struct bio *bio)
{
sector_t maxsector;
- struct bio_vec *bvec = bio_last_bvec_all(bio);
- unsigned truncated_bytes;
struct hd_struct *part;
rcu_read_lock();
@@ -3061,28 +3059,7 @@ void guard_bio_eod(int op, struct bio *bio)
if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
return;
- /* Uhhuh. We've got a bio that straddles the device size! */
- truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
-
- /*
- * The bio contains more than one segment which spans EOD, just return
- * and let IO layer turn it into an EIO
- */
- if (truncated_bytes > bvec->bv_len)
- return;
-
- /* Truncate the bio.. */
- bio->bi_iter.bi_size -= truncated_bytes;
- bvec->bv_len -= truncated_bytes;
-
- /* ..and clear the end of the buffer for reads */
- if (op == REQ_OP_READ) {
- struct bio_vec bv;
-
- mp_bvec_last_segment(bvec, &bv);
- zero_user(bv.bv_page, bv.bv_offset + bv.bv_len,
- truncated_bytes);
- }
+ bio_truncate(bio, maxsector << 9);
}
static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
@@ -3118,15 +3095,15 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
- /* Take care of bh's that straddle the end of the device */
- guard_bio_eod(op, bio);
-
if (buffer_meta(bh))
op_flags |= REQ_META;
if (buffer_prio(bh))
op_flags |= REQ_PRIO;
bio_set_op_attrs(bio, op, op_flags);
+ /* Take care of bh's that straddle the end of the device */
+ guard_bio_eod(bio);
+
if (wbc) {
wbc_init_bio(wbc, bio);
wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 374db1b..145d46b 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -708,8 +708,10 @@ void ceph_mdsc_release_request(struct kref *kref)
/* avoid calling iput_final() in mds dispatch threads */
ceph_async_iput(req->r_inode);
}
- if (req->r_parent)
+ if (req->r_parent) {
ceph_put_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN);
+ ceph_async_iput(req->r_parent);
+ }
ceph_async_iput(req->r_target_inode);
if (req->r_dentry)
dput(req->r_dentry);
@@ -2676,8 +2678,10 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir,
/* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */
if (req->r_inode)
ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN);
- if (req->r_parent)
+ if (req->r_parent) {
ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN);
+ ihold(req->r_parent);
+ }
if (req->r_old_dentry_dir)
ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir),
CEPH_CAP_PIN);
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 00dfe17..c5e6eff 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -352,7 +352,7 @@ static struct kobject *cdev_get(struct cdev *p)
if (owner && !try_module_get(owner))
return NULL;
- kobj = kobject_get(&p->kobj);
+ kobj = kobject_get_unless_zero(&p->kobj);
if (!kobj)
module_put(owner);
return kobj;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 0ec4f27..00b4d15 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -39,6 +39,8 @@
#include <linux/atomic.h>
#include <linux/prefetch.h>
+#include "internal.h"
+
/*
* How many user pages to map in one call to get_user_pages(). This determines
* the size of a structure in the slab cache
diff --git a/fs/file.c b/fs/file.c
index 2f4fcf9..3da91a1 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -960,7 +960,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
return ksys_dup3(oldfd, newfd, 0);
}
-SYSCALL_DEFINE1(dup, unsigned int, fildes)
+int ksys_dup(unsigned int fildes)
{
int ret = -EBADF;
struct file *file = fget_raw(fildes);
@@ -975,6 +975,11 @@ SYSCALL_DEFINE1(dup, unsigned int, fildes)
return ret;
}
+SYSCALL_DEFINE1(dup, unsigned int, fildes)
+{
+ return ksys_dup(fildes);
+}
+
int f_dupfd(unsigned int from, struct file *file, unsigned flags)
{
int err;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index a63d779..ce71538 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -882,6 +882,7 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
struct fuse_args_pages *ap = &ia->ap;
loff_t pos = page_offset(ap->pages[0]);
size_t count = ap->num_pages << PAGE_SHIFT;
+ ssize_t res;
int err;
ap->args.out_pages = true;
@@ -896,7 +897,8 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
if (!err)
return;
} else {
- err = fuse_simple_request(fc, &ap->args);
+ res = fuse_simple_request(fc, &ap->args);
+ err = res < 0 ? res : 0;
}
fuse_readpages_end(fc, &ap->args, err);
}
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d5c2a31..a66e425 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1498,8 +1498,10 @@ static int __init init_hugetlbfs_fs(void)
/* other hstates are optional */
i = 0;
for_each_hstate(h) {
- if (i == default_hstate_idx)
+ if (i == default_hstate_idx) {
+ i++;
continue;
+ }
mnt = mount_one_hugetlbfs(h);
if (IS_ERR(mnt))
diff --git a/fs/internal.h b/fs/internal.h
index 4a7da1d..e3fa695 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -38,7 +38,7 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait)
/*
* buffer.c
*/
-extern void guard_bio_eod(int rw, struct bio *bio);
+extern void guard_bio_eod(struct bio *bio);
extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
get_block_t *get_block, struct iomap *iomap);
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 541c8a3..5147d22 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -445,10 +445,14 @@ static void io_worker_handle_work(struct io_worker *worker)
task_unlock(current);
}
if ((work->flags & IO_WQ_WORK_NEEDS_USER) && !worker->mm &&
- wq->mm && mmget_not_zero(wq->mm)) {
- use_mm(wq->mm);
- set_fs(USER_DS);
- worker->mm = wq->mm;
+ wq->mm) {
+ if (mmget_not_zero(wq->mm)) {
+ use_mm(wq->mm);
+ set_fs(USER_DS);
+ worker->mm = wq->mm;
+ } else {
+ work->flags |= IO_WQ_WORK_CANCEL;
+ }
}
if (!worker->creds)
worker->creds = override_creds(wq->creds);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 562e3a1..5953d7f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1786,6 +1786,9 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
struct iovec *iovec, struct iovec *fast_iov,
struct iov_iter *iter)
{
+ if (req->opcode == IORING_OP_READ_FIXED ||
+ req->opcode == IORING_OP_WRITE_FIXED)
+ return 0;
if (!req->io && io_alloc_async_ctx(req))
return -ENOMEM;
@@ -1840,6 +1843,7 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt,
if (!force_nonblock)
req->rw.kiocb.ki_flags &= ~IOCB_NOWAIT;
+ req->result = 0;
io_size = ret;
if (req->flags & REQ_F_LINK)
req->result = io_size;
@@ -1863,18 +1867,6 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt,
else
ret2 = loop_rw_iter(READ, req->file, kiocb, &iter);
- /*
- * In case of a short read, punt to async. This can happen
- * if we have data partially cached. Alternatively we can
- * return the short read, in which case the application will
- * need to issue another SQE and wait for it. That SQE will
- * need async punt anyway, so it's more efficient to do it
- * here.
- */
- if (force_nonblock && !(req->flags & REQ_F_NOWAIT) &&
- (req->flags & REQ_F_ISREG) &&
- ret2 > 0 && ret2 < io_size)
- ret2 = -EAGAIN;
/* Catch -EAGAIN return for forced non-blocking submission */
if (!force_nonblock || ret2 != -EAGAIN) {
kiocb_done(kiocb, ret2, nxt, req->in_async);
@@ -1939,6 +1931,7 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt,
if (!force_nonblock)
req->rw.kiocb.ki_flags &= ~IOCB_NOWAIT;
+ req->result = 0;
io_size = ret;
if (req->flags & REQ_F_LINK)
req->result = io_size;
@@ -2046,6 +2039,28 @@ static bool io_req_cancelled(struct io_kiocb *req)
return false;
}
+static void io_link_work_cb(struct io_wq_work **workptr)
+{
+ struct io_wq_work *work = *workptr;
+ struct io_kiocb *link = work->data;
+
+ io_queue_linked_timeout(link);
+ work->func = io_wq_submit_work;
+}
+
+static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt)
+{
+ struct io_kiocb *link;
+
+ io_prep_async_work(nxt, &link);
+ *workptr = &nxt->work;
+ if (link) {
+ nxt->work.flags |= IO_WQ_WORK_CB;
+ nxt->work.func = io_link_work_cb;
+ nxt->work.data = link;
+ }
+}
+
static void io_fsync_finish(struct io_wq_work **workptr)
{
struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
@@ -2064,7 +2079,7 @@ static void io_fsync_finish(struct io_wq_work **workptr)
io_cqring_add_event(req, ret);
io_put_req_find_next(req, &nxt);
if (nxt)
- *workptr = &nxt->work;
+ io_wq_assign_next(workptr, nxt);
}
static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt,
@@ -2120,7 +2135,7 @@ static void io_sync_file_range_finish(struct io_wq_work **workptr)
io_cqring_add_event(req, ret);
io_put_req_find_next(req, &nxt);
if (nxt)
- *workptr = &nxt->work;
+ io_wq_assign_next(workptr, nxt);
}
static int io_sync_file_range(struct io_kiocb *req, struct io_kiocb **nxt,
@@ -2386,7 +2401,7 @@ static void io_accept_finish(struct io_wq_work **workptr)
return;
__io_accept(req, &nxt, false);
if (nxt)
- *workptr = &nxt->work;
+ io_wq_assign_next(workptr, nxt);
}
#endif
@@ -2617,7 +2632,7 @@ static void io_poll_complete_work(struct io_wq_work **workptr)
req_set_fail_links(req);
io_put_req_find_next(req, &nxt);
if (nxt)
- *workptr = &nxt->work;
+ io_wq_assign_next(workptr, nxt);
}
static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
@@ -3271,24 +3286,24 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
return ret;
if (ctx->flags & IORING_SETUP_IOPOLL) {
+ const bool in_async = io_wq_current_is_worker();
+
if (req->result == -EAGAIN)
return -EAGAIN;
+ /* workqueue context doesn't hold uring_lock, grab it now */
+ if (in_async)
+ mutex_lock(&ctx->uring_lock);
+
io_iopoll_req_issued(req);
+
+ if (in_async)
+ mutex_unlock(&ctx->uring_lock);
}
return 0;
}
-static void io_link_work_cb(struct io_wq_work **workptr)
-{
- struct io_wq_work *work = *workptr;
- struct io_kiocb *link = work->data;
-
- io_queue_linked_timeout(link);
- work->func = io_wq_submit_work;
-}
-
static void io_wq_submit_work(struct io_wq_work **workptr)
{
struct io_wq_work *work = *workptr;
@@ -3325,17 +3340,8 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
}
/* if a dependent link is ready, pass it back */
- if (!ret && nxt) {
- struct io_kiocb *link;
-
- io_prep_async_work(nxt, &link);
- *workptr = &nxt->work;
- if (link) {
- nxt->work.flags |= IO_WQ_WORK_CB;
- nxt->work.func = io_link_work_cb;
- nxt->work.data = link;
- }
- }
+ if (!ret && nxt)
+ io_wq_assign_next(workptr, nxt);
}
static bool io_req_op_valid(int op)
@@ -4457,13 +4463,15 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
return -EINVAL;
if (copy_from_user(&up, arg, sizeof(up)))
return -EFAULT;
+ if (up.resv)
+ return -EINVAL;
if (check_add_overflow(up.offset, nr_args, &done))
return -EOVERFLOW;
if (done > ctx->nr_user_files)
return -EINVAL;
done = 0;
- fds = (__s32 __user *) up.fds;
+ fds = u64_to_user_ptr(up.fds);
while (nr_args) {
struct fixed_file_table *table;
unsigned index;
@@ -5153,6 +5161,12 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
} else if (to_submit) {
struct mm_struct *cur_mm;
+ if (current->mm != ctx->sqo_mm ||
+ current_cred() != ctx->creds) {
+ ret = -EPERM;
+ goto out;
+ }
+
to_submit = min(to_submit, ctx->sq_entries);
mutex_lock(&ctx->uring_lock);
/* already have mm, so io_submit_sqes() won't try to grab it */
diff --git a/fs/mpage.c b/fs/mpage.c
index a63620c..ccba3c4 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -62,7 +62,7 @@ static struct bio *mpage_bio_submit(int op, int op_flags, struct bio *bio)
{
bio->bi_end_io = mpage_end_io;
bio_set_op_attrs(bio, op, op_flags);
- guard_bio_eod(op, bio);
+ guard_bio_eod(bio);
submit_bio(bio);
return NULL;
}
diff --git a/fs/namei.c b/fs/namei.c
index d6c91d1..d2720dc 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1232,6 +1232,7 @@ static int follow_managed(struct path *path, struct nameidata *nd)
BUG_ON(!path->dentry->d_op);
BUG_ON(!path->dentry->d_op->d_manage);
ret = path->dentry->d_op->d_manage(path, false);
+ flags = smp_load_acquire(&path->dentry->d_flags);
if (ret < 0)
break;
}
@@ -1649,17 +1650,15 @@ static struct dentry *__lookup_slow(const struct qstr *name,
if (IS_ERR(dentry))
return dentry;
if (unlikely(!d_in_lookup(dentry))) {
- if (!(flags & LOOKUP_NO_REVAL)) {
- int error = d_revalidate(dentry, flags);
- if (unlikely(error <= 0)) {
- if (!error) {
- d_invalidate(dentry);
- dput(dentry);
- goto again;
- }
+ int error = d_revalidate(dentry, flags);
+ if (unlikely(error <= 0)) {
+ if (!error) {
+ d_invalidate(dentry);
dput(dentry);
- dentry = ERR_PTR(error);
+ goto again;
}
+ dput(dentry);
+ dentry = ERR_PTR(error);
}
} else {
old = inode->i_op->lookup(inode, dentry, flags);
@@ -2618,72 +2617,6 @@ int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
EXPORT_SYMBOL(user_path_at_empty);
/**
- * mountpoint_last - look up last component for umount
- * @nd: pathwalk nameidata - currently pointing at parent directory of "last"
- *
- * This is a special lookup_last function just for umount. In this case, we
- * need to resolve the path without doing any revalidation.
- *
- * The nameidata should be the result of doing a LOOKUP_PARENT pathwalk. Since
- * mountpoints are always pinned in the dcache, their ancestors are too. Thus,
- * in almost all cases, this lookup will be served out of the dcache. The only
- * cases where it won't are if nd->last refers to a symlink or the path is
- * bogus and it doesn't exist.
- *
- * Returns:
- * -error: if there was an error during lookup. This includes -ENOENT if the
- * lookup found a negative dentry.
- *
- * 0: if we successfully resolved nd->last and found it to not to be a
- * symlink that needs to be followed.
- *
- * 1: if we successfully resolved nd->last and found it to be a symlink
- * that needs to be followed.
- */
-static int
-mountpoint_last(struct nameidata *nd)
-{
- int error = 0;
- struct dentry *dir = nd->path.dentry;
- struct path path;
-
- /* If we're in rcuwalk, drop out of it to handle last component */
- if (nd->flags & LOOKUP_RCU) {
- if (unlazy_walk(nd))
- return -ECHILD;
- }
-
- nd->flags &= ~LOOKUP_PARENT;
-
- if (unlikely(nd->last_type != LAST_NORM)) {
- error = handle_dots(nd, nd->last_type);
- if (error)
- return error;
- path.dentry = dget(nd->path.dentry);
- } else {
- path.dentry = d_lookup(dir, &nd->last);
- if (!path.dentry) {
- /*
- * No cached dentry. Mounted dentries are pinned in the
- * cache, so that means that this dentry is probably
- * a symlink or the path doesn't actually point
- * to a mounted dentry.
- */
- path.dentry = lookup_slow(&nd->last, dir,
- nd->flags | LOOKUP_NO_REVAL);
- if (IS_ERR(path.dentry))
- return PTR_ERR(path.dentry);
- }
- }
- if (d_flags_negative(smp_load_acquire(&path.dentry->d_flags))) {
- dput(path.dentry);
- return -ENOENT;
- }
- path.mnt = nd->path.mnt;
- return step_into(nd, &path, 0, d_backing_inode(path.dentry), 0);
-}
-
-/**
* path_mountpoint - look up a path to be umounted
* @nd: lookup context
* @flags: lookup flags
@@ -2699,14 +2632,17 @@ path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path)
int err;
while (!(err = link_path_walk(s, nd)) &&
- (err = mountpoint_last(nd)) > 0) {
+ (err = lookup_last(nd)) > 0) {
s = trailing_symlink(nd);
}
+ if (!err && (nd->flags & LOOKUP_RCU))
+ err = unlazy_walk(nd);
+ if (!err)
+ err = handle_lookup_down(nd);
if (!err) {
*path = nd->path;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
- follow_mount(path);
}
terminate_walk(nd);
return err;
diff --git a/fs/namespace.c b/fs/namespace.c
index be601d3..5e1bf61 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1728,7 +1728,7 @@ static bool is_mnt_ns_file(struct dentry *dentry)
dentry->d_fsdata == &mntns_operations;
}
-struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
+static struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
{
return container_of(ns, struct mnt_namespace, ns);
}
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index f64a33d..2a82dcc 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -206,7 +206,6 @@ TRACE_DEFINE_ENUM(LOOKUP_AUTOMOUNT);
TRACE_DEFINE_ENUM(LOOKUP_PARENT);
TRACE_DEFINE_ENUM(LOOKUP_REVAL);
TRACE_DEFINE_ENUM(LOOKUP_RCU);
-TRACE_DEFINE_ENUM(LOOKUP_NO_REVAL);
TRACE_DEFINE_ENUM(LOOKUP_OPEN);
TRACE_DEFINE_ENUM(LOOKUP_CREATE);
TRACE_DEFINE_ENUM(LOOKUP_EXCL);
@@ -224,7 +223,6 @@ TRACE_DEFINE_ENUM(LOOKUP_DOWN);
{ LOOKUP_PARENT, "PARENT" }, \
{ LOOKUP_REVAL, "REVAL" }, \
{ LOOKUP_RCU, "RCU" }, \
- { LOOKUP_NO_REVAL, "NO_REVAL" }, \
{ LOOKUP_OPEN, "OPEN" }, \
{ LOOKUP_CREATE, "CREATE" }, \
{ LOOKUP_EXCL, "EXCL" }, \
diff --git a/fs/nsfs.c b/fs/nsfs.c
index a043164..f75767b 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -3,6 +3,7 @@
#include <linux/pseudo_fs.h>
#include <linux/file.h>
#include <linux/fs.h>
+#include <linux/proc_fs.h>
#include <linux/proc_ns.h>
#include <linux/magic.h>
#include <linux/ktime.h>
@@ -11,6 +12,8 @@
#include <linux/nsfs.h>
#include <linux/uaccess.h>
+#include "internal.h"
+
static struct vfsmount *nsfs_mnt;
static long ns_ioctl(struct file *filp, unsigned int ioctl,
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 1c4c51f..cda1027 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3282,6 +3282,7 @@ static void ocfs2_dlm_init_debug(struct ocfs2_super *osb)
debugfs_create_u32("locking_filter", 0600, osb->osb_debug_root,
&dlm_debug->d_filter_secs);
+ ocfs2_get_dlm_debug(dlm_debug);
}
static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb)
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 1afe57f..68ba354 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1066,6 +1066,14 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
ocfs2_clear_journal_error(osb->sb, journal->j_journal, osb->slot_num);
+ if (replayed) {
+ jbd2_journal_lock_updates(journal->j_journal);
+ status = jbd2_journal_flush(journal->j_journal);
+ jbd2_journal_unlock_updates(journal->j_journal);
+ if (status < 0)
+ mlog_errno(status);
+ }
+
status = ocfs2_journal_toggle_dirty(osb, 1, replayed);
if (status < 0) {
mlog_errno(status);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 84ad1c9..249672b 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -631,12 +631,15 @@ EXPORT_SYMBOL_GPL(posix_acl_create);
/**
* posix_acl_update_mode - update mode in set_acl
+ * @inode: target inode
+ * @mode_p: mode (pointer) for update
+ * @acl: acl pointer
*
* Update the file mode when setting an ACL: compute the new file permission
* bits based on the ACL. In addition, if the ACL is equivalent to the new
- * file mode, set *acl to NULL to indicate that no ACL should be set.
+ * file mode, set *@acl to NULL to indicate that no ACL should be set.
*
- * As with chmod, clear the setgit bit if the caller is not in the owning group
+ * As with chmod, clear the setgid bit if the caller is not in the owning group
* or capable of CAP_FSETID (see inode_change_ok).
*
* Called from set_acl inode operations.
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 8caff83..013486b 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -407,6 +407,17 @@ static int notrace ramoops_pstore_write(struct pstore_record *record)
prz = cxt->dprzs[cxt->dump_write_cnt];
+ /*
+ * Since this is a new crash dump, we need to reset the buffer in
+ * case it still has an old dump present. Without this, the new dump
+ * will get appended, which would seriously confuse anything trying
+ * to check dump file contents. Specifically, ramoops_read_kmsg_hdr()
+ * expects to find a dump header in the beginning of buffer data, so
+ * we must to reset the buffer values, in order to ensure that the
+ * header will be written to the beginning of the buffer.
+ */
+ persistent_ram_zap(prz);
+
/* Build header and append record contents. */
hlen = ramoops_write_kmsg_hdr(prz, record);
if (!hlen)
@@ -572,6 +583,7 @@ static int ramoops_init_przs(const char *name,
prz_ar[i] = persistent_ram_new(*paddr, zone_sz, sig,
&cxt->ecc_info,
cxt->memtype, flags, label);
+ kfree(label);
if (IS_ERR(prz_ar[i])) {
err = PTR_ERR(prz_ar[i]);
dev_err(dev, "failed to request %s mem region (0x%zx@0x%llx): %d\n",
@@ -617,6 +629,7 @@ static int ramoops_init_prz(const char *name,
label = kasprintf(GFP_KERNEL, "ramoops:%s", name);
*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info,
cxt->memtype, PRZ_FLAG_ZAP_OLD, label);
+ kfree(label);
if (IS_ERR(*prz)) {
int err = PTR_ERR(*prz);
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index 8823f65..1f4d8c0 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -574,7 +574,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
/* Initialize general buffer state. */
raw_spin_lock_init(&prz->buffer_lock);
prz->flags = flags;
- prz->label = label;
+ prz->label = kstrdup(label, GFP_KERNEL);
ret = persistent_ram_buffer_map(start, size, prz, memtype);
if (ret)
diff --git a/fs/readdir.c b/fs/readdir.c
index d26d5ea..de2ecef 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -102,10 +102,14 @@ EXPORT_SYMBOL(iterate_dir);
* filename length, and the above "soft error" worry means
* that it's probably better left alone until we have that
* issue clarified.
+ *
+ * Note the PATH_MAX check - it's arbitrary but the real
+ * kernel limit on a possible path component, not NAME_MAX,
+ * which is the technical standard limit.
*/
static int verify_dirent_name(const char *name, int len)
{
- if (!len)
+ if (len <= 0 || len >= PATH_MAX)
return -EIO;
if (memchr(name, '/', len))
return -EIO;
@@ -206,7 +210,7 @@ struct linux_dirent {
struct getdents_callback {
struct dir_context ctx;
struct linux_dirent __user * current_dir;
- struct linux_dirent __user * previous;
+ int prev_reclen;
int count;
int error;
};
@@ -214,12 +218,13 @@ struct getdents_callback {
static int filldir(struct dir_context *ctx, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
- struct linux_dirent __user * dirent;
+ struct linux_dirent __user *dirent, *prev;
struct getdents_callback *buf =
container_of(ctx, struct getdents_callback, ctx);
unsigned long d_ino;
int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2,
sizeof(long));
+ int prev_reclen;
buf->error = verify_dirent_name(name, namlen);
if (unlikely(buf->error))
@@ -232,28 +237,24 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen,
buf->error = -EOVERFLOW;
return -EOVERFLOW;
}
- dirent = buf->previous;
- if (dirent && signal_pending(current))
+ prev_reclen = buf->prev_reclen;
+ if (prev_reclen && signal_pending(current))
return -EINTR;
-
- /*
- * Note! This range-checks 'previous' (which may be NULL).
- * The real range was checked in getdents
- */
- if (!user_access_begin(dirent, sizeof(*dirent)))
- goto efault;
- if (dirent)
- unsafe_put_user(offset, &dirent->d_off, efault_end);
dirent = buf->current_dir;
+ prev = (void __user *) dirent - prev_reclen;
+ if (!user_access_begin(prev, reclen + prev_reclen))
+ goto efault;
+
+ /* This might be 'dirent->d_off', but if so it will get overwritten */
+ unsafe_put_user(offset, &prev->d_off, efault_end);
unsafe_put_user(d_ino, &dirent->d_ino, efault_end);
unsafe_put_user(reclen, &dirent->d_reclen, efault_end);
unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end);
unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end);
user_access_end();
- buf->previous = dirent;
- dirent = (void __user *)dirent + reclen;
- buf->current_dir = dirent;
+ buf->current_dir = (void __user *)dirent + reclen;
+ buf->prev_reclen = reclen;
buf->count -= reclen;
return 0;
efault_end:
@@ -267,7 +268,6 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
struct linux_dirent __user *, dirent, unsigned int, count)
{
struct fd f;
- struct linux_dirent __user * lastdirent;
struct getdents_callback buf = {
.ctx.actor = filldir,
.count = count,
@@ -285,8 +285,10 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
error = iterate_dir(f.file, &buf.ctx);
if (error >= 0)
error = buf.error;
- lastdirent = buf.previous;
- if (lastdirent) {
+ if (buf.prev_reclen) {
+ struct linux_dirent __user * lastdirent;
+ lastdirent = (void __user *)buf.current_dir - buf.prev_reclen;
+
if (put_user(buf.ctx.pos, &lastdirent->d_off))
error = -EFAULT;
else
@@ -299,7 +301,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
struct getdents_callback64 {
struct dir_context ctx;
struct linux_dirent64 __user * current_dir;
- struct linux_dirent64 __user * previous;
+ int prev_reclen;
int count;
int error;
};
@@ -307,11 +309,12 @@ struct getdents_callback64 {
static int filldir64(struct dir_context *ctx, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
- struct linux_dirent64 __user *dirent;
+ struct linux_dirent64 __user *dirent, *prev;
struct getdents_callback64 *buf =
container_of(ctx, struct getdents_callback64, ctx);
int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
sizeof(u64));
+ int prev_reclen;
buf->error = verify_dirent_name(name, namlen);
if (unlikely(buf->error))
@@ -319,30 +322,27 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen,
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
return -EINVAL;
- dirent = buf->previous;
- if (dirent && signal_pending(current))
+ prev_reclen = buf->prev_reclen;
+ if (prev_reclen && signal_pending(current))
return -EINTR;
-
- /*
- * Note! This range-checks 'previous' (which may be NULL).
- * The real range was checked in getdents
- */
- if (!user_access_begin(dirent, sizeof(*dirent)))
- goto efault;
- if (dirent)
- unsafe_put_user(offset, &dirent->d_off, efault_end);
dirent = buf->current_dir;
+ prev = (void __user *)dirent - prev_reclen;
+ if (!user_access_begin(prev, reclen + prev_reclen))
+ goto efault;
+
+ /* This might be 'dirent->d_off', but if so it will get overwritten */
+ unsafe_put_user(offset, &prev->d_off, efault_end);
unsafe_put_user(ino, &dirent->d_ino, efault_end);
unsafe_put_user(reclen, &dirent->d_reclen, efault_end);
unsafe_put_user(d_type, &dirent->d_type, efault_end);
unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end);
user_access_end();
- buf->previous = dirent;
- dirent = (void __user *)dirent + reclen;
- buf->current_dir = dirent;
+ buf->prev_reclen = reclen;
+ buf->current_dir = (void __user *)dirent + reclen;
buf->count -= reclen;
return 0;
+
efault_end:
user_access_end();
efault:
@@ -354,7 +354,6 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent,
unsigned int count)
{
struct fd f;
- struct linux_dirent64 __user * lastdirent;
struct getdents_callback64 buf = {
.ctx.actor = filldir64,
.count = count,
@@ -372,9 +371,11 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent,
error = iterate_dir(f.file, &buf.ctx);
if (error >= 0)
error = buf.error;
- lastdirent = buf.previous;
- if (lastdirent) {
+ if (buf.prev_reclen) {
+ struct linux_dirent64 __user * lastdirent;
typeof(lastdirent->d_off) d_off = buf.ctx.pos;
+
+ lastdirent = (void __user *) buf.current_dir - buf.prev_reclen;
if (__put_user(d_off, &lastdirent->d_off))
error = -EFAULT;
else
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 62b40df3..28b241c 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -319,8 +319,12 @@ static int reiserfs_for_each_xattr(struct inode *inode,
out_dir:
dput(dir);
out:
- /* -ENODATA isn't an error */
- if (err == -ENODATA)
+ /*
+ * -ENODATA: this object doesn't have any xattrs
+ * -EOPNOTSUPP: this file system doesn't have xattrs enabled on disk.
+ * Neither are errors
+ */
+ if (err == -ENODATA || err == -EOPNOTSUPP)
err = 0;
return err;
}
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index a950a22..cac7404 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -11,71 +11,102 @@
* The cache doesn't need to be flushed when TLB entries change when
* the cache is mapped to physical memory, not virtual memory
*/
+#ifndef flush_cache_all
static inline void flush_cache_all(void)
{
}
+#endif
+#ifndef flush_cache_mm
static inline void flush_cache_mm(struct mm_struct *mm)
{
}
+#endif
+#ifndef flush_cache_dup_mm
static inline void flush_cache_dup_mm(struct mm_struct *mm)
{
}
+#endif
+#ifndef flush_cache_range
static inline void flush_cache_range(struct vm_area_struct *vma,
unsigned long start,
unsigned long end)
{
}
+#endif
+#ifndef flush_cache_page
static inline void flush_cache_page(struct vm_area_struct *vma,
unsigned long vmaddr,
unsigned long pfn)
{
}
+#endif
+#ifndef flush_dcache_page
static inline void flush_dcache_page(struct page *page)
{
}
+#endif
+#ifndef flush_dcache_mmap_lock
static inline void flush_dcache_mmap_lock(struct address_space *mapping)
{
}
+#endif
+#ifndef flush_dcache_mmap_unlock
static inline void flush_dcache_mmap_unlock(struct address_space *mapping)
{
}
+#endif
+#ifndef flush_icache_range
static inline void flush_icache_range(unsigned long start, unsigned long end)
{
}
+#endif
+#ifndef flush_icache_page
static inline void flush_icache_page(struct vm_area_struct *vma,
struct page *page)
{
}
+#endif
+#ifndef flush_icache_user_range
static inline void flush_icache_user_range(struct vm_area_struct *vma,
struct page *page,
unsigned long addr, int len)
{
}
+#endif
+#ifndef flush_cache_vmap
static inline void flush_cache_vmap(unsigned long start, unsigned long end)
{
}
+#endif
+#ifndef flush_cache_vunmap
static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
{
}
+#endif
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+#ifndef copy_to_user_page
+#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
do { \
memcpy(dst, src, len); \
flush_icache_user_range(vma, page, vaddr, len); \
} while (0)
+#endif
+
+#ifndef copy_from_user_page
#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
memcpy(dst, src, len)
+#endif
#endif /* __ASM_CACHEFLUSH_H */
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index d5fc90b..c1bda70 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -605,6 +605,12 @@ struct drm_dp_mst_topology_mgr {
* &drm_dp_sideband_msg_tx.state once they are queued
*/
struct mutex qlock;
+
+ /**
+ * @is_waiting_for_dwn_reply: indicate whether is waiting for down reply
+ */
+ bool is_waiting_for_dwn_reply;
+
/**
* @tx_msg_downq: List of pending down replies.
*/
diff --git a/include/dt-bindings/reset/amlogic,meson8b-reset.h b/include/dt-bindings/reset/amlogic,meson8b-reset.h
index c614438..fbc524a 100644
--- a/include/dt-bindings/reset/amlogic,meson8b-reset.h
+++ b/include/dt-bindings/reset/amlogic,meson8b-reset.h
@@ -46,9 +46,9 @@
#define RESET_VD_RMEM 64
#define RESET_AUDIN 65
#define RESET_DBLK 66
-#define RESET_PIC_DC 66
-#define RESET_PSC 66
-#define RESET_NAND 66
+#define RESET_PIC_DC 67
+#define RESET_PSC 68
+#define RESET_NAND 69
#define RESET_GE2D 70
#define RESET_PARSER_REG 71
#define RESET_PARSER_FETCH 72
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 3cdb84c..853d92c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -470,6 +470,7 @@ extern struct bio *bio_copy_user_iov(struct request_queue *,
gfp_t);
extern int bio_uncopy_user(struct bio *);
void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter);
+void bio_truncate(struct bio *bio, unsigned new_size);
static inline void zero_fill_bio(struct bio *bio)
{
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index ff335b2..f0f3a9f 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -53,6 +53,7 @@
* bitmap_find_next_zero_area_off(buf, len, pos, n, mask) as above
* bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n
* bitmap_shift_left(dst, src, n, nbits) *dst = *src << n
+ * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest
* bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask)
* bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src)
* bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit)
@@ -133,6 +134,9 @@ extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src,
unsigned int shift, unsigned int nbits);
extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src,
unsigned int shift, unsigned int nbits);
+extern void bitmap_cut(unsigned long *dst, const unsigned long *src,
+ unsigned int first, unsigned int cut,
+ unsigned int nbits);
extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 47eb22a..4c636c4 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -328,6 +328,7 @@ struct queue_limits {
unsigned int max_sectors;
unsigned int max_segment_size;
unsigned int physical_block_size;
+ unsigned int logical_block_size;
unsigned int alignment_offset;
unsigned int io_min;
unsigned int io_opt;
@@ -338,7 +339,6 @@ struct queue_limits {
unsigned int discard_granularity;
unsigned int discard_alignment;
- unsigned short logical_block_size;
unsigned short max_segments;
unsigned short max_integrity_segments;
unsigned short max_discard_segments;
@@ -1077,7 +1077,7 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q,
unsigned int max_write_same_sectors);
extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
unsigned int max_write_same_sectors);
-extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
+extern void blk_queue_logical_block_size(struct request_queue *, unsigned int);
extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
extern void blk_queue_alignment_offset(struct request_queue *q,
unsigned int alignment);
@@ -1291,7 +1291,7 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
return q->limits.max_segment_size;
}
-static inline unsigned short queue_logical_block_size(const struct request_queue *q)
+static inline unsigned queue_logical_block_size(const struct request_queue *q)
{
int retval = 512;
@@ -1301,7 +1301,7 @@ static inline unsigned short queue_logical_block_size(const struct request_queue
return retval;
}
-static inline unsigned short bdev_logical_block_size(struct block_device *bdev)
+static inline unsigned int bdev_logical_block_size(struct block_device *bdev)
{
return queue_logical_block_size(bdev_get_queue(bdev));
}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b14e51d..a968786 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -17,6 +17,7 @@
#include <linux/u64_stats_sync.h>
#include <linux/refcount.h>
#include <linux/mutex.h>
+#include <linux/module.h>
struct bpf_verifier_env;
struct bpf_verifier_log;
@@ -43,6 +44,15 @@ struct bpf_map_ops {
int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
void (*map_release_uref)(struct bpf_map *map);
void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key);
+ int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
+ int (*map_lookup_and_delete_batch)(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
+ int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
+ int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
/* funcs callable from userspace and from eBPF programs */
void *(*map_lookup_elem)(struct bpf_map *map, void *key);
@@ -106,6 +116,7 @@ struct bpf_map {
struct btf *btf;
struct bpf_map_memory memory;
char name[BPF_OBJ_NAME_LEN];
+ u32 btf_vmlinux_value_type_id;
bool unpriv_array;
bool frozen; /* write-once; write-protected by freeze_mutex */
/* 22 bytes hole */
@@ -183,7 +194,8 @@ static inline bool bpf_map_offload_neutral(const struct bpf_map *map)
static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
{
- return map->btf && map->ops->map_seq_show_elem;
+ return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) &&
+ map->ops->map_seq_show_elem;
}
int map_check_no_btf(const struct bpf_map *map,
@@ -349,6 +361,10 @@ struct bpf_verifier_ops {
const struct bpf_insn *src,
struct bpf_insn *dst,
struct bpf_prog *prog, u32 *target_size);
+ int (*btf_struct_access)(struct bpf_verifier_log *log,
+ const struct btf_type *t, int off, int size,
+ enum bpf_access_type atype,
+ u32 *next_btf_id);
};
struct bpf_prog_offload_ops {
@@ -437,7 +453,8 @@ struct btf_func_model {
* fentry = a set of program to run before calling original function
* fexit = a set of program to run after original function
*/
-int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
+int arch_prepare_bpf_trampoline(void *image, void *image_end,
+ const struct btf_func_model *m, u32 flags,
struct bpf_prog **fentry_progs, int fentry_cnt,
struct bpf_prog **fexit_progs, int fexit_cnt,
void *orig_call);
@@ -448,7 +465,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
enum bpf_tramp_prog_type {
BPF_TRAMP_FENTRY,
BPF_TRAMP_FEXIT,
- BPF_TRAMP_MAX
+ BPF_TRAMP_MAX,
+ BPF_TRAMP_REPLACE, /* more than MAX */
};
struct bpf_trampoline {
@@ -463,6 +481,11 @@ struct bpf_trampoline {
void *addr;
bool ftrace_managed;
} func;
+ /* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF
+ * program by replacing one of its functions. func.addr is the address
+ * of the function it replaced.
+ */
+ struct bpf_prog *extension_prog;
/* list of BPF programs using this trampoline */
struct hlist_head progs_hlist[BPF_TRAMP_MAX];
/* Number of attached programs. A counter per kind. */
@@ -558,6 +581,7 @@ static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d,
#endif
struct bpf_func_info_aux {
+ u16 linkage;
bool unreliable;
};
@@ -668,6 +692,73 @@ struct bpf_array_aux {
struct work_struct work;
};
+struct bpf_struct_ops_value;
+struct btf_type;
+struct btf_member;
+
+#define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64
+struct bpf_struct_ops {
+ const struct bpf_verifier_ops *verifier_ops;
+ int (*init)(struct btf *btf);
+ int (*check_member)(const struct btf_type *t,
+ const struct btf_member *member);
+ int (*init_member)(const struct btf_type *t,
+ const struct btf_member *member,
+ void *kdata, const void *udata);
+ int (*reg)(void *kdata);
+ void (*unreg)(void *kdata);
+ const struct btf_type *type;
+ const struct btf_type *value_type;
+ const char *name;
+ struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
+ u32 type_id;
+ u32 value_id;
+};
+
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
+#define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA))
+const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id);
+void bpf_struct_ops_init(struct btf *btf);
+bool bpf_struct_ops_get(const void *kdata);
+void bpf_struct_ops_put(const void *kdata);
+int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
+ void *value);
+static inline bool bpf_try_module_get(const void *data, struct module *owner)
+{
+ if (owner == BPF_MODULE_OWNER)
+ return bpf_struct_ops_get(data);
+ else
+ return try_module_get(owner);
+}
+static inline void bpf_module_put(const void *data, struct module *owner)
+{
+ if (owner == BPF_MODULE_OWNER)
+ bpf_struct_ops_put(data);
+ else
+ module_put(owner);
+}
+#else
+static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
+{
+ return NULL;
+}
+static inline void bpf_struct_ops_init(struct btf *btf) { }
+static inline bool bpf_try_module_get(const void *data, struct module *owner)
+{
+ return try_module_get(owner);
+}
+static inline void bpf_module_put(const void *data, struct module *owner)
+{
+ module_put(owner);
+}
+static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map,
+ void *key,
+ void *value)
+{
+ return -EINVAL;
+}
+#endif
+
struct bpf_array {
struct bpf_map map;
u32 elem_size;
@@ -906,6 +997,15 @@ void *bpf_map_area_alloc(u64 size, int numa_node);
void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
void bpf_map_area_free(void *base);
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
+int generic_map_lookup_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
+int generic_map_update_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
+int generic_map_delete_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
extern int sysctl_unprivileged_bpf_disabled;
@@ -962,7 +1062,9 @@ struct sk_buff;
struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key);
-void __dev_map_flush(void);
+void __dev_flush(void);
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+ struct net_device *dev_rx);
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx);
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
@@ -1006,7 +1108,13 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
const char *func_name,
struct btf_func_model *m);
-int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog);
+struct bpf_reg_state;
+int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
+ struct bpf_reg_state *regs);
+int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
+ struct bpf_reg_state *reg);
+int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
+ struct btf *btf, const struct btf_type *t);
struct bpf_prog *bpf_prog_by_id(u32 id);
@@ -1071,7 +1179,7 @@ static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map
return NULL;
}
-static inline void __dev_map_flush(void)
+static inline void __dev_flush(void)
{
}
@@ -1079,6 +1187,13 @@ struct xdp_buff;
struct bpf_dtab_netdev;
static inline
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ return 0;
+}
+
+static inline
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
@@ -1299,6 +1414,7 @@ extern const struct bpf_func_proto bpf_get_local_storage_proto;
extern const struct bpf_func_proto bpf_strtol_proto;
extern const struct bpf_func_proto bpf_strtoul_proto;
extern const struct bpf_func_proto bpf_tcp_sock_proto;
+extern const struct bpf_func_proto bpf_jiffies64_proto;
/* Shared helpers among cBPF and eBPF. */
void bpf_user_rnd_init_once(void);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 93740b3..c81d4ec 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -65,6 +65,12 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2,
BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport,
struct sk_reuseport_md, struct sk_reuseport_kern)
#endif
+#if defined(CONFIG_BPF_JIT)
+BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops,
+ void *, void *)
+BPF_PROG_TYPE(BPF_PROG_TYPE_EXT, bpf_extension,
+ void *, void *)
+#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)
@@ -105,3 +111,6 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops)
+#if defined(CONFIG_BPF_JIT)
+BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops)
+#endif
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 26e40de..5406e6e 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -304,11 +304,13 @@ struct bpf_insn_aux_data {
u64 map_key_state; /* constant (32 bit) key tracking for maps */
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
int sanitize_stack_off; /* stack slot to be cleared */
- bool seen; /* this insn was processed by the verifier */
+ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
bool zext_dst; /* this insn zero extends dst reg */
u8 alu_state; /* used in combination with alu_limit */
- bool prune_point;
+
+ /* below fields are initialized once */
unsigned int orig_idx; /* original instruction index */
+ bool prune_point;
};
#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
@@ -379,6 +381,7 @@ struct bpf_verifier_env {
int *insn_stack;
int cur_stack;
} cfg;
+ u32 pass_cnt; /* number of times do_check() was called */
u32 subprog_cnt;
/* number of instructions analyzed by the verifier */
u32 prev_insn_processed, insn_processed;
@@ -428,4 +431,7 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
void
bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
+int check_ctx_reg(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg, int regno);
+
#endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 79d4abc..5c1ea99 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -7,6 +7,8 @@
#include <linux/types.h>
#include <uapi/linux/btf.h>
+#define BTF_TYPE_EMIT(type) ((void)(type *)0)
+
struct btf;
struct btf_member;
struct btf_type;
@@ -53,6 +55,22 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
u32 expected_offset, u32 expected_size);
int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
bool btf_type_is_void(const struct btf_type *t);
+s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind);
+const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
+ u32 id, u32 *res_id);
+const struct btf_type *btf_type_resolve_ptr(const struct btf *btf,
+ u32 id, u32 *res_id);
+const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
+ u32 id, u32 *res_id);
+const struct btf_type *
+btf_resolve_size(const struct btf *btf, const struct btf_type *type,
+ u32 *type_size, const struct btf_type **elem_type,
+ u32 *total_nelems);
+
+#define for_each_member(i, struct_type, member) \
+ for (i = 0, member = btf_type_member(struct_type); \
+ i < btf_type_vlen(struct_type); \
+ i++, member++)
static inline bool btf_type_is_ptr(const struct btf_type *t)
{
@@ -84,6 +102,40 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t)
return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
}
+static inline u16 btf_type_vlen(const struct btf_type *t)
+{
+ return BTF_INFO_VLEN(t->info);
+}
+
+static inline u16 btf_func_linkage(const struct btf_type *t)
+{
+ return BTF_INFO_VLEN(t->info);
+}
+
+static inline bool btf_type_kflag(const struct btf_type *t)
+{
+ return BTF_INFO_KFLAG(t->info);
+}
+
+static inline u32 btf_member_bit_offset(const struct btf_type *struct_type,
+ const struct btf_member *member)
+{
+ return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset)
+ : member->offset;
+}
+
+static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type,
+ const struct btf_member *member)
+{
+ return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
+ : 0;
+}
+
+static inline const struct btf_member *btf_type_member(const struct btf_type *t)
+{
+ return (const struct btf_member *)(t + 1);
+}
+
#ifdef CONFIG_BPF_SYSCALL
const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
const char *btf_name_by_offset(const struct btf *btf, u32 offset);
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 679a422..a81c13a 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -153,26 +153,4 @@ static inline void bvec_advance(const struct bio_vec *bvec,
}
}
-/*
- * Get the last single-page segment from the multi-page bvec and store it
- * in @seg
- */
-static inline void mp_bvec_last_segment(const struct bio_vec *bvec,
- struct bio_vec *seg)
-{
- unsigned total = bvec->bv_offset + bvec->bv_len;
- unsigned last_page = (total - 1) / PAGE_SIZE;
-
- seg->bv_page = bvec->bv_page + last_page;
-
- /* the whole segment is inside the last page */
- if (bvec->bv_offset >= last_page * PAGE_SIZE) {
- seg->bv_offset = bvec->bv_offset % PAGE_SIZE;
- seg->bv_len = bvec->bv_len;
- } else {
- seg->bv_offset = 0;
- seg->bv_len = total - last_page * PAGE_SIZE;
- }
-}
-
#endif /* __LINUX_BVEC_ITER_H */
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 9b3c720..5e3d455 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -18,6 +18,7 @@
#include <linux/can/error.h>
#include <linux/can/led.h>
#include <linux/can/netlink.h>
+#include <linux/can/skb.h>
#include <linux/netdevice.h>
/*
@@ -91,6 +92,36 @@ struct can_priv {
#define get_can_dlc(i) (min_t(__u8, (i), CAN_MAX_DLC))
#define get_canfd_dlc(i) (min_t(__u8, (i), CANFD_MAX_DLC))
+/* Check for outgoing skbs that have not been created by the CAN subsystem */
+static inline bool can_skb_headroom_valid(struct net_device *dev,
+ struct sk_buff *skb)
+{
+ /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */
+ if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv)))
+ return false;
+
+ /* af_packet does not apply CAN skb specific settings */
+ if (skb->ip_summed == CHECKSUM_NONE) {
+ /* init headroom */
+ can_skb_prv(skb)->ifindex = dev->ifindex;
+ can_skb_prv(skb)->skbcnt = 0;
+
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ /* preform proper loopback on capable devices */
+ if (dev->flags & IFF_ECHO)
+ skb->pkt_type = PACKET_LOOPBACK;
+ else
+ skb->pkt_type = PACKET_HOST;
+
+ skb_reset_mac_header(skb);
+ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+ }
+
+ return true;
+}
+
/* Drop a given socketbuffer if it does not contain a valid CAN frame. */
static inline bool can_dropped_invalid_skb(struct net_device *dev,
struct sk_buff *skb)
@@ -108,6 +139,9 @@ static inline bool can_dropped_invalid_skb(struct net_device *dev,
} else
goto inval_skb;
+ if (!can_skb_headroom_valid(dev, skb))
+ goto inval_skb;
+
return false;
inval_skb:
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 8fcdee1..dad4a68 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -1364,8 +1364,11 @@ static inline int dma_get_slave_caps(struct dma_chan *chan,
static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx)
{
struct dma_slave_caps caps;
+ int ret;
- dma_get_slave_caps(tx->chan, &caps);
+ ret = dma_get_slave_caps(tx->chan, &caps);
+ if (ret)
+ return ret;
if (caps.descriptor_reuse) {
tx->flags |= DMA_CTRL_REUSE;
diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h
index c0b6a60..fa5735c 100644
--- a/include/linux/dsa/sja1105.h
+++ b/include/linux/dsa/sja1105.h
@@ -53,10 +53,12 @@ struct sja1105_skb_cb {
((struct sja1105_skb_cb *)DSA_SKB_CB_PRIV(skb))
struct sja1105_port {
+ struct kthread_worker *xmit_worker;
+ struct kthread_work xmit_work;
+ struct sk_buff_head xmit_queue;
struct sja1105_tagger_data *data;
struct dsa_port *dp;
bool hwts_tx_en;
- int mgmt_slot;
};
#endif /* _NET_DSA_SJA1105_H */
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index f6564b5..8801f1f 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -43,7 +43,6 @@ __be16 eth_header_parse_protocol(const struct sk_buff *skb);
int eth_prepare_mac_addr_change(struct net_device *dev, void *p);
void eth_commit_mac_addr_change(struct net_device *dev, void *p);
int eth_mac_addr(struct net_device *dev, void *p);
-int eth_change_mtu(struct net_device *dev, int new_mtu);
int eth_validate_addr(struct net_device *dev);
struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 70e6dd9..f349e2c 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -843,6 +843,8 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
bpf_aux_classic_check_t trans, bool save_orig);
void bpf_prog_destroy(struct bpf_prog *fp);
+const struct bpf_func_proto *
+bpf_base_func_proto(enum bpf_func_id func_id);
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
int sk_attach_bpf(u32 ufd, struct sock *sk);
@@ -916,7 +918,7 @@ static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
return 0;
}
-/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the
+/* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the
* same cpu context. Further for best results no more than a single map
* for the do_redirect/do_flush pair should be used. This limitation is
* because we only track one map and force a flush when the map changes.
@@ -927,7 +929,13 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
int xdp_do_redirect(struct net_device *dev,
struct xdp_buff *xdp,
struct bpf_prog *prog);
-void xdp_do_flush_map(void);
+void xdp_do_flush(void);
+
+/* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as
+ * it is no longer only flushing maps. Keep this define for compatibility
+ * until all drivers are updated - do not use xdp_do_flush_map() in new code!
+ */
+#define xdp_do_flush_map xdp_do_flush
void bpf_warn_invalid_xdp_action(u32 act);
diff --git a/include/linux/fsl/enetc_mdio.h b/include/linux/fsl/enetc_mdio.h
new file mode 100644
index 0000000..4875dd3
--- /dev/null
+++ b/include/linux/fsl/enetc_mdio.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2019 NXP */
+
+#ifndef _FSL_ENETC_MDIO_H_
+#define _FSL_ENETC_MDIO_H_
+
+#include <linux/phy.h>
+
+/* PCS registers */
+#define ENETC_PCS_LINK_TIMER1 0x12
+#define ENETC_PCS_LINK_TIMER1_VAL 0x06a0
+#define ENETC_PCS_LINK_TIMER2 0x13
+#define ENETC_PCS_LINK_TIMER2_VAL 0x0003
+#define ENETC_PCS_IF_MODE 0x14
+#define ENETC_PCS_IF_MODE_SGMII_EN BIT(0)
+#define ENETC_PCS_IF_MODE_USE_SGMII_AN BIT(1)
+#define ENETC_PCS_IF_MODE_SGMII_SPEED(x) (((x) << 2) & GENMASK(3, 2))
+
+/* Not a mistake, the SerDes PLL needs to be set at 3.125 GHz by Reset
+ * Configuration Word (RCW, outside Linux control) for 2.5G SGMII mode. The PCS
+ * still thinks it's at gigabit.
+ */
+enum enetc_pcs_speed {
+ ENETC_PCS_SPEED_10 = 0,
+ ENETC_PCS_SPEED_100 = 1,
+ ENETC_PCS_SPEED_1000 = 2,
+ ENETC_PCS_SPEED_2500 = 2,
+};
+
+struct enetc_hw;
+
+struct enetc_mdio_priv {
+ struct enetc_hw *hw;
+ int mdio_base;
+};
+
+#if IS_REACHABLE(CONFIG_FSL_ENETC_MDIO)
+
+int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum);
+int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value);
+struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs);
+
+#else
+
+static inline int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
+{ return -EINVAL; }
+static inline int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum,
+ u16 value)
+{ return -EINVAL; }
+struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs)
+{ return ERR_PTR(-EINVAL); }
+
+#endif
+
+#endif
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index 76cf11e..8a9792a 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -24,6 +24,14 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb)
return (struct ethhdr *)skb_mac_header(skb);
}
+/* Prefer this version in TX path, instead of
+ * skb_reset_mac_header() + eth_hdr()
+ */
+static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb)
+{
+ return (struct ethhdr *)skb->data;
+}
+
static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb)
{
return (struct ethhdr *)skb_inner_mac_header(skb);
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3adcb39..0d9db2a 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -79,15 +79,6 @@
*/
#define round_down(x, y) ((x) & ~__round_mask(x, y))
-/**
- * FIELD_SIZEOF - get the size of a struct's field
- * @t: the target struct
- * @f: the target struct's field
- * Return: the size of @f in the struct definition without having a
- * declared instance of @t.
- */
-#define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
-
#define typeof_member(T, m) typeof(((T*)0)->m)
#define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 3a08ecd..ba0dca6 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -122,8 +122,8 @@ static inline bool movable_node_is_enabled(void)
extern void arch_remove_memory(int nid, u64 start, u64 size,
struct vmem_altmap *altmap);
-extern void __remove_pages(struct zone *zone, unsigned long start_pfn,
- unsigned long nr_pages, struct vmem_altmap *altmap);
+extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
+ struct vmem_altmap *altmap);
/* reasonably generic interface to expand the physical pages */
extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
@@ -342,6 +342,9 @@ extern int add_memory(int nid, u64 start, u64 size);
extern int add_memory_resource(int nid, struct resource *resource);
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
unsigned long nr_pages, struct vmem_altmap *altmap);
+extern void remove_pfn_range_from_zone(struct zone *zone,
+ unsigned long start_pfn,
+ unsigned long nr_pages);
extern bool is_memblock_offlined(struct memory_block *mem);
extern int sparse_add_section(int nid, unsigned long pfn,
unsigned long nr_pages, struct vmem_altmap *altmap);
diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h
index f84b916..7dfb63b 100644
--- a/include/linux/mfd/mt6397/rtc.h
+++ b/include/linux/mfd/mt6397/rtc.h
@@ -46,6 +46,14 @@
#define RTC_AL_SEC 0x0018
+#define RTC_AL_SEC_MASK 0x003f
+#define RTC_AL_MIN_MASK 0x003f
+#define RTC_AL_HOU_MASK 0x001f
+#define RTC_AL_DOM_MASK 0x001f
+#define RTC_AL_DOW_MASK 0x0007
+#define RTC_AL_MTH_MASK 0x000f
+#define RTC_AL_YEA_MASK 0x007f
+
#define RTC_PDN2 0x002e
#define RTC_PDN2_PWRON_ALARM BIT(4)
diff --git a/include/linux/mii.h b/include/linux/mii.h
index 4ce8901..18c6208 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -373,6 +373,56 @@ static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa)
}
/**
+ * mii_lpa_mod_linkmode_adv_sgmii
+ * @lp_advertising: pointer to destination link mode.
+ * @lpa: value of the MII_LPA register
+ *
+ * A small helper function that translates MII_LPA bits to
+ * linkmode advertisement settings for SGMII.
+ * Leaves other bits unchanged.
+ */
+static inline void
+mii_lpa_mod_linkmode_lpa_sgmii(unsigned long *lp_advertising, u32 lpa)
+{
+ u32 speed_duplex = lpa & LPA_SGMII_DPX_SPD_MASK;
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, lp_advertising,
+ speed_duplex == LPA_SGMII_1000HALF);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, lp_advertising,
+ speed_duplex == LPA_SGMII_1000FULL);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, lp_advertising,
+ speed_duplex == LPA_SGMII_100HALF);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, lp_advertising,
+ speed_duplex == LPA_SGMII_100FULL);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, lp_advertising,
+ speed_duplex == LPA_SGMII_10HALF);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, lp_advertising,
+ speed_duplex == LPA_SGMII_10FULL);
+}
+
+/**
+ * mii_lpa_to_linkmode_adv_sgmii
+ * @advertising: pointer to destination link mode.
+ * @lpa: value of the MII_LPA register
+ *
+ * A small helper function that translates MII_ADVERTISE bits
+ * to linkmode advertisement settings when in SGMII mode.
+ * Clears the old value of advertising.
+ */
+static inline void mii_lpa_to_linkmode_lpa_sgmii(unsigned long *lp_advertising,
+ u32 lpa)
+{
+ linkmode_zero(lp_advertising);
+
+ mii_lpa_mod_linkmode_lpa_sgmii(lp_advertising, lpa);
+}
+
+/**
* mii_adv_mod_linkmode_adv_t
* @advertising:pointer to destination link mode.
* @adv: value of the MII_ADVERTISE register
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 36e412c..20372de 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -47,7 +47,7 @@
#define DEFAULT_UAR_PAGE_SHIFT 12
#define MAX_MSIX_P_PORT 17
-#define MAX_MSIX 64
+#define MAX_MSIX 128
#define MIN_MSIX_P_PORT 5
#define MLX4_IS_LEGACY_EQ_MODE(dev_cap) ((dev_cap).num_comp_vectors < \
(dev_cap).num_ports * MIN_MSIX_P_PORT)
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index cc1c230..0e62c3d 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1105,6 +1105,7 @@ enum mlx5_cap_type {
MLX5_CAP_DEV_MEM,
MLX5_CAP_RESERVED_16,
MLX5_CAP_TLS,
+ MLX5_CAP_VDPA_EMULATION = 0x13,
MLX5_CAP_DEV_EVENT = 0x14,
/* NUM OF CAP Types */
MLX5_CAP_NUM
@@ -1120,6 +1121,9 @@ enum mlx5_pcam_feature_groups {
enum mlx5_mcam_reg_groups {
MLX5_MCAM_REGS_FIRST_128 = 0x0,
+ MLX5_MCAM_REGS_0x9080_0x90FF = 0x1,
+ MLX5_MCAM_REGS_0x9100_0x917F = 0x2,
+ MLX5_MCAM_REGS_NUM = 0x3,
};
enum mlx5_mcam_feature_groups {
@@ -1268,7 +1272,16 @@ enum mlx5_qcam_feature_groups {
MLX5_GET(pcam_reg, (mdev)->caps.pcam, port_access_reg_cap_mask.regs_5000_to_507f.reg)
#define MLX5_CAP_MCAM_REG(mdev, reg) \
- MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_access_reg_cap_mask.access_regs.reg)
+ MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_FIRST_128], \
+ mng_access_reg_cap_mask.access_regs.reg)
+
+#define MLX5_CAP_MCAM_REG1(mdev, reg) \
+ MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9080_0x90FF], \
+ mng_access_reg_cap_mask.access_regs1.reg)
+
+#define MLX5_CAP_MCAM_REG2(mdev, reg) \
+ MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \
+ mng_access_reg_cap_mask.access_regs2.reg)
#define MLX5_CAP_MCAM_FEATURE(mdev, fld) \
MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld)
@@ -1297,6 +1310,14 @@ enum mlx5_qcam_feature_groups {
#define MLX5_CAP_DEV_EVENT(mdev, cap)\
MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap)
+#define MLX5_CAP_DEV_VDPA_EMULATION(mdev, cap)\
+ MLX5_GET(device_virtio_emulation_cap, \
+ (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap)
+
+#define MLX5_CAP64_DEV_VDPA_EMULATION(mdev, cap)\
+ MLX5_GET64(device_virtio_emulation_cap, \
+ (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap)
+
enum {
MLX5_CMD_STAT_OK = 0x0,
MLX5_CMD_STAT_INT_ERR = 0x1,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 27200de..22bd0d5 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -145,6 +145,8 @@ enum {
MLX5_REG_MCC = 0x9062,
MLX5_REG_MCDA = 0x9063,
MLX5_REG_MCAM = 0x907f,
+ MLX5_REG_MIRC = 0x9162,
+ MLX5_REG_RESOURCE_DUMP = 0xC000,
};
enum mlx5_qpts_trust_state {
@@ -684,7 +686,7 @@ struct mlx5_core_dev {
u32 hca_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)];
u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)];
u32 pcam[MLX5_ST_SZ_DW(pcam_reg)];
- u32 mcam[MLX5_ST_SZ_DW(mcam_reg)];
+ u32 mcam[MLX5_MCAM_REGS_NUM][MLX5_ST_SZ_DW(mcam_reg)];
u32 fpga[MLX5_ST_SZ_DW(fpga_cap)];
u32 qcam[MLX5_ST_SZ_DW(qcam_reg)];
u8 embedded_cpu;
@@ -928,8 +930,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev);
void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health);
void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
-int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
- struct mlx5_frag_buf *buf, int node);
int mlx5_buf_alloc(struct mlx5_core_dev *dev,
int size, struct mlx5_frag_buf *buf);
void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf);
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 4e5b84e..4cae160 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -48,6 +48,7 @@ enum {
MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT = BIT(0),
MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1),
MLX5_FLOW_TABLE_TERMINATION = BIT(2),
+ MLX5_FLOW_TABLE_UNMANAGED = BIT(3),
};
#define LEFTOVERS_RULE_NUM 2
@@ -145,19 +146,17 @@ mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev,
enum mlx5_flow_namespace_type type,
int vport);
-struct mlx5_flow_table *
-mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
- int prio,
- int num_flow_table_entries,
- int max_num_groups,
- u32 level,
- u32 flags);
-
struct mlx5_flow_table_attr {
int prio;
int max_fte;
u32 level;
u32 flags;
+ struct mlx5_flow_table *next_ft;
+
+ struct {
+ int max_num_groups;
+ int num_reserved_entries;
+ } autogroup;
};
struct mlx5_flow_table *
@@ -165,6 +164,10 @@ mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
struct mlx5_flow_table_attr *ft_attr);
struct mlx5_flow_table *
+mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
+ struct mlx5_flow_table_attr *ft_attr);
+
+struct mlx5_flow_table *
mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
int prio,
int num_flow_table_entries,
@@ -194,6 +197,7 @@ struct mlx5_fs_vlan {
enum {
FLOW_ACT_NO_APPEND = BIT(0),
+ FLOW_ACT_IGNORE_FLOW_LEVEL = BIT(1),
};
struct mlx5_flow_act {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 5d54fcc..ee0a34d 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -87,6 +87,7 @@ enum {
enum {
MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM),
MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11),
+ MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13),
};
enum {
@@ -374,8 +375,17 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
u8 outer_esp_spi[0x1];
u8 reserved_at_58[0x2];
u8 bth_dst_qp[0x1];
+ u8 reserved_at_5b[0x5];
- u8 reserved_at_5b[0x25];
+ u8 reserved_at_60[0x18];
+ u8 metadata_reg_c_7[0x1];
+ u8 metadata_reg_c_6[0x1];
+ u8 metadata_reg_c_5[0x1];
+ u8 metadata_reg_c_4[0x1];
+ u8 metadata_reg_c_3[0x1];
+ u8 metadata_reg_c_2[0x1];
+ u8 metadata_reg_c_1[0x1];
+ u8 metadata_reg_c_0[0x1];
};
struct mlx5_ifc_flow_table_prop_layout_bits {
@@ -400,7 +410,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
u8 reformat_l3_tunnel_to_l2[0x1];
u8 reformat_l2_to_l3_tunnel[0x1];
u8 reformat_and_modify_action[0x1];
- u8 reserved_at_15[0x2];
+ u8 ignore_flow_level[0x1];
+ u8 reserved_at_16[0x1];
u8 table_miss_action_domain[0x1];
u8 termination_table[0x1];
u8 reserved_at_19[0x7];
@@ -721,7 +732,9 @@ enum {
struct mlx5_ifc_flow_table_eswitch_cap_bits {
u8 fdb_to_vport_reg_c_id[0x8];
- u8 reserved_at_8[0xf];
+ u8 reserved_at_8[0xd];
+ u8 fdb_modify_header_fwd_to_table[0x1];
+ u8 reserved_at_16[0x1];
u8 flow_source[0x1];
u8 reserved_at_18[0x2];
u8 multi_fdb_encap[0x1];
@@ -822,7 +835,9 @@ struct mlx5_ifc_qos_cap_bits {
struct mlx5_ifc_debug_cap_bits {
u8 core_dump_general[0x1];
u8 core_dump_qp[0x1];
- u8 reserved_at_2[0x1e];
+ u8 reserved_at_2[0x7];
+ u8 resource_dump[0x1];
+ u8 reserved_at_a[0x16];
u8 reserved_at_20[0x2];
u8 stall_detect[0x1];
@@ -953,6 +968,19 @@ struct mlx5_ifc_device_event_cap_bits {
u8 user_unaffiliated_events[4][0x40];
};
+struct mlx5_ifc_device_virtio_emulation_cap_bits {
+ u8 reserved_at_0[0x20];
+
+ u8 reserved_at_20[0x13];
+ u8 log_doorbell_stride[0x5];
+ u8 reserved_at_38[0x3];
+ u8 log_doorbell_bar_size[0x5];
+
+ u8 doorbell_bar_offset[0x40];
+
+ u8 reserved_at_80[0x780];
+};
+
enum {
MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_1_BYTE = 0x0,
MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_2_BYTES = 0x2,
@@ -1753,6 +1781,132 @@ struct mlx5_ifc_resize_field_select_bits {
u8 resize_field_select[0x20];
};
+struct mlx5_ifc_resource_dump_bits {
+ u8 more_dump[0x1];
+ u8 inline_dump[0x1];
+ u8 reserved_at_2[0xa];
+ u8 seq_num[0x4];
+ u8 segment_type[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 vhca_id[0x10];
+
+ u8 index1[0x20];
+
+ u8 index2[0x20];
+
+ u8 num_of_obj1[0x10];
+ u8 num_of_obj2[0x10];
+
+ u8 reserved_at_a0[0x20];
+
+ u8 device_opaque[0x40];
+
+ u8 mkey[0x20];
+
+ u8 size[0x20];
+
+ u8 address[0x40];
+
+ u8 inline_data[52][0x20];
+};
+
+struct mlx5_ifc_resource_dump_menu_record_bits {
+ u8 reserved_at_0[0x4];
+ u8 num_of_obj2_supports_active[0x1];
+ u8 num_of_obj2_supports_all[0x1];
+ u8 must_have_num_of_obj2[0x1];
+ u8 support_num_of_obj2[0x1];
+ u8 num_of_obj1_supports_active[0x1];
+ u8 num_of_obj1_supports_all[0x1];
+ u8 must_have_num_of_obj1[0x1];
+ u8 support_num_of_obj1[0x1];
+ u8 must_have_index2[0x1];
+ u8 support_index2[0x1];
+ u8 must_have_index1[0x1];
+ u8 support_index1[0x1];
+ u8 segment_type[0x10];
+
+ u8 segment_name[4][0x20];
+
+ u8 index1_name[4][0x20];
+
+ u8 index2_name[4][0x20];
+};
+
+struct mlx5_ifc_resource_dump_segment_header_bits {
+ u8 length_dw[0x10];
+ u8 segment_type[0x10];
+};
+
+struct mlx5_ifc_resource_dump_command_segment_bits {
+ struct mlx5_ifc_resource_dump_segment_header_bits segment_header;
+
+ u8 segment_called[0x10];
+ u8 vhca_id[0x10];
+
+ u8 index1[0x20];
+
+ u8 index2[0x20];
+
+ u8 num_of_obj1[0x10];
+ u8 num_of_obj2[0x10];
+};
+
+struct mlx5_ifc_resource_dump_error_segment_bits {
+ struct mlx5_ifc_resource_dump_segment_header_bits segment_header;
+
+ u8 reserved_at_20[0x10];
+ u8 syndrome_id[0x10];
+
+ u8 reserved_at_40[0x40];
+
+ u8 error[8][0x20];
+};
+
+struct mlx5_ifc_resource_dump_info_segment_bits {
+ struct mlx5_ifc_resource_dump_segment_header_bits segment_header;
+
+ u8 reserved_at_20[0x18];
+ u8 dump_version[0x8];
+
+ u8 hw_version[0x20];
+
+ u8 fw_version[0x20];
+};
+
+struct mlx5_ifc_resource_dump_menu_segment_bits {
+ struct mlx5_ifc_resource_dump_segment_header_bits segment_header;
+
+ u8 reserved_at_20[0x10];
+ u8 num_of_records[0x10];
+
+ struct mlx5_ifc_resource_dump_menu_record_bits record[0];
+};
+
+struct mlx5_ifc_resource_dump_resource_segment_bits {
+ struct mlx5_ifc_resource_dump_segment_header_bits segment_header;
+
+ u8 reserved_at_20[0x20];
+
+ u8 index1[0x20];
+
+ u8 index2[0x20];
+
+ u8 payload[0][0x20];
+};
+
+struct mlx5_ifc_resource_dump_terminate_segment_bits {
+ struct mlx5_ifc_resource_dump_segment_header_bits segment_header;
+};
+
+struct mlx5_ifc_menu_resource_dump_response_bits {
+ struct mlx5_ifc_resource_dump_info_segment_bits info;
+ struct mlx5_ifc_resource_dump_command_segment_bits cmd;
+ struct mlx5_ifc_resource_dump_menu_segment_bits menu;
+ struct mlx5_ifc_resource_dump_terminate_segment_bits terminate;
+};
+
enum {
MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_CQ_PERIOD = 0x1,
MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_CQ_MAX_COUNT = 0x2,
@@ -2026,7 +2180,9 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits {
u8 rx_pause_transition_low[0x20];
- u8 reserved_at_3c0[0x40];
+ u8 rx_discards_high[0x20];
+
+ u8 rx_discards_low[0x20];
u8 device_stall_minor_watermark_cnt_high[0x20];
@@ -2751,6 +2907,7 @@ union mlx5_ifc_hca_cap_union_bits {
struct mlx5_ifc_fpga_cap_bits fpga_cap;
struct mlx5_ifc_tls_cap_bits tls_cap;
struct mlx5_ifc_device_mem_cap_bits device_mem_cap;
+ struct mlx5_ifc_device_virtio_emulation_cap_bits virtio_emulation_cap;
u8 reserved_at_0[0x8000];
};
@@ -3998,7 +4155,8 @@ struct mlx5_ifc_set_fte_in_bits {
u8 reserved_at_a0[0x8];
u8 table_id[0x18];
- u8 reserved_at_c0[0x18];
+ u8 ignore_flow_level[0x1];
+ u8 reserved_at_c1[0x17];
u8 modify_enable_mask[0x8];
u8 reserved_at_e0[0x20];
@@ -5466,15 +5624,32 @@ struct mlx5_ifc_add_action_in_bits {
u8 data[0x20];
};
+struct mlx5_ifc_copy_action_in_bits {
+ u8 action_type[0x4];
+ u8 src_field[0xc];
+ u8 reserved_at_10[0x3];
+ u8 src_offset[0x5];
+ u8 reserved_at_18[0x3];
+ u8 length[0x5];
+
+ u8 reserved_at_20[0x4];
+ u8 dst_field[0xc];
+ u8 reserved_at_30[0x3];
+ u8 dst_offset[0x5];
+ u8 reserved_at_38[0x8];
+};
+
union mlx5_ifc_set_action_in_add_action_in_auto_bits {
struct mlx5_ifc_set_action_in_bits set_action_in;
struct mlx5_ifc_add_action_in_bits add_action_in;
+ struct mlx5_ifc_copy_action_in_bits copy_action_in;
u8 reserved_at_0[0x40];
};
enum {
MLX5_ACTION_TYPE_SET = 0x1,
MLX5_ACTION_TYPE_ADD = 0x2,
+ MLX5_ACTION_TYPE_COPY = 0x3,
};
enum {
@@ -5510,6 +5685,8 @@ enum {
MLX5_ACTION_IN_FIELD_METADATA_REG_C_3 = 0x54,
MLX5_ACTION_IN_FIELD_METADATA_REG_C_4 = 0x55,
MLX5_ACTION_IN_FIELD_METADATA_REG_C_5 = 0x56,
+ MLX5_ACTION_IN_FIELD_METADATA_REG_C_6 = 0x57,
+ MLX5_ACTION_IN_FIELD_METADATA_REG_C_7 = 0x58,
MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM = 0x59,
MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM = 0x5B,
};
@@ -8406,6 +8583,18 @@ struct mlx5_ifc_pplm_reg_bits {
u8 fec_override_admin_50g[0x4];
u8 fec_override_admin_25g[0x4];
u8 fec_override_admin_10g_40g[0x4];
+
+ u8 fec_override_cap_400g_8x[0x10];
+ u8 fec_override_cap_200g_4x[0x10];
+
+ u8 fec_override_cap_100g_2x[0x10];
+ u8 fec_override_cap_50g_1x[0x10];
+
+ u8 fec_override_admin_400g_8x[0x10];
+ u8 fec_override_admin_200g_4x[0x10];
+
+ u8 fec_override_admin_100g_2x[0x10];
+ u8 fec_override_admin_50g_1x[0x10];
};
struct mlx5_ifc_ppcnt_reg_bits {
@@ -8732,7 +8921,9 @@ struct mlx5_ifc_mpegc_reg_bits {
};
struct mlx5_ifc_pcam_enhanced_features_bits {
- u8 reserved_at_0[0x6d];
+ u8 reserved_at_0[0x68];
+ u8 fec_50G_per_lane_in_pplm[0x1];
+ u8 reserved_at_69[0x4];
u8 rx_icrc_encapsulated_counter[0x1];
u8 reserved_at_6e[0x4];
u8 ptys_extended_ethernet[0x1];
@@ -8817,6 +9008,28 @@ struct mlx5_ifc_mcam_access_reg_bits {
u8 regs_31_to_0[0x20];
};
+struct mlx5_ifc_mcam_access_reg_bits1 {
+ u8 regs_127_to_96[0x20];
+
+ u8 regs_95_to_64[0x20];
+
+ u8 regs_63_to_32[0x20];
+
+ u8 regs_31_to_0[0x20];
+};
+
+struct mlx5_ifc_mcam_access_reg_bits2 {
+ u8 regs_127_to_99[0x1d];
+ u8 mirc[0x1];
+ u8 regs_97_to_96[0x2];
+
+ u8 regs_95_to_64[0x20];
+
+ u8 regs_63_to_32[0x20];
+
+ u8 regs_31_to_0[0x20];
+};
+
struct mlx5_ifc_mcam_reg_bits {
u8 reserved_at_0[0x8];
u8 feature_group[0x8];
@@ -8827,6 +9040,8 @@ struct mlx5_ifc_mcam_reg_bits {
union {
struct mlx5_ifc_mcam_access_reg_bits access_regs;
+ struct mlx5_ifc_mcam_access_reg_bits1 access_regs1;
+ struct mlx5_ifc_mcam_access_reg_bits2 access_regs2;
u8 reserved_at_0[0x80];
} mng_access_reg_cap_mask;
@@ -9432,6 +9647,13 @@ struct mlx5_ifc_mcda_reg_bits {
u8 data[0][0x20];
};
+struct mlx5_ifc_mirc_reg_bits {
+ u8 reserved_at_0[0x18];
+ u8 status_code[0x8];
+
+ u8 reserved_at_20[0x20];
+};
+
union mlx5_ifc_ports_control_registers_document_bits {
struct mlx5_ifc_bufferx_reg_bits bufferx_reg;
struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout;
@@ -9487,6 +9709,7 @@ union mlx5_ifc_ports_control_registers_document_bits {
struct mlx5_ifc_mcqi_reg_bits mcqi_reg;
struct mlx5_ifc_mcc_reg_bits mcc_reg;
struct mlx5_ifc_mcda_reg_bits mcda_reg;
+ struct mlx5_ifc_mirc_reg_bits mirc_reg;
u8 reserved_at_0[0x60e0];
};
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80a9162..cfaa8fe 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2658,14 +2658,26 @@ static inline bool want_init_on_free(void)
!page_poisoning_enabled();
}
-#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT
-DECLARE_STATIC_KEY_TRUE(_debug_pagealloc_enabled);
+#ifdef CONFIG_DEBUG_PAGEALLOC
+extern void init_debug_pagealloc(void);
#else
-DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
+static inline void init_debug_pagealloc(void) {}
#endif
+extern bool _debug_pagealloc_enabled_early;
+DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
static inline bool debug_pagealloc_enabled(void)
{
+ return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) &&
+ _debug_pagealloc_enabled_early;
+}
+
+/*
+ * For use in fast paths after init_debug_pagealloc() has run, or when a
+ * false negative result is not harmful when called too early.
+ */
+static inline bool debug_pagealloc_enabled_static(void)
+{
if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC))
return false;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 89d8ff06..5334ad8 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -215,9 +215,8 @@ enum node_stat_item {
NR_INACTIVE_FILE, /* " " " " " */
NR_ACTIVE_FILE, /* " " " " " */
NR_UNEVICTABLE, /* " " " " " */
- NR_SLAB_RECLAIMABLE, /* Please do not reorder this item */
- NR_SLAB_UNRECLAIMABLE, /* and this one without looking at
- * memcg_flush_percpu_vmstats() first. */
+ NR_SLAB_RECLAIMABLE,
+ NR_SLAB_UNRECLAIMABLE,
NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
WORKINGSET_NODES,
diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h
index ecc88a4..c04f690 100644
--- a/include/linux/mtd/flashchip.h
+++ b/include/linux/mtd/flashchip.h
@@ -40,7 +40,7 @@ typedef enum {
FL_READING,
FL_CACHEDPRG,
/* These 4 come from onenand_state_t, which has been unified here */
- FL_RESETING,
+ FL_RESETTING,
FL_OTPING,
FL_PREPARING_ERASE,
FL_VERIFYING_ERASE,
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 7fe7b87..07bfb08 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -34,7 +34,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
/* internal use only */
#define LOOKUP_PARENT 0x0010
-#define LOOKUP_NO_REVAL 0x0080
#define LOOKUP_JUMPED 0x1000
#define LOOKUP_ROOT 0x2000
#define LOOKUP_ROOT_GRABBED 0x0008
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 4b19c54..34d050b 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -53,8 +53,9 @@ enum {
NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */
NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */
NETIF_F_GSO_UDP_L4_BIT, /* ... UDP payload GSO (not UFO) */
+ NETIF_F_GSO_FRAGLIST_BIT, /* ... Fraglist GSO */
/**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */
- NETIF_F_GSO_UDP_L4_BIT,
+ NETIF_F_GSO_FRAGLIST_BIT,
NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */
NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */
@@ -80,6 +81,7 @@ enum {
NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */
NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */
+ NETIF_F_GRO_FRAGLIST_BIT, /* Fraglist GRO */
/*
* Add your fresh new feature above and remember to update
@@ -150,6 +152,8 @@ enum {
#define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4)
#define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX)
#define NETIF_F_HW_TLS_RX __NETIF_F(HW_TLS_RX)
+#define NETIF_F_GRO_FRAGLIST __NETIF_F(GRO_FRAGLIST)
+#define NETIF_F_GSO_FRAGLIST __NETIF_F(GSO_FRAGLIST)
/* Finds the next feature with the highest number of the range of start till 0.
*/
@@ -226,6 +230,9 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
/* changeable features with no special hardware requirements */
#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO)
+/* Changeable features with no special hardware requirements that defaults to off. */
+#define NETIF_F_SOFT_FEATURES_OFF NETIF_F_GRO_FRAGLIST
+
#define NETIF_F_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \
NETIF_F_HW_VLAN_CTAG_RX | \
NETIF_F_HW_VLAN_CTAG_TX | \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2741aa3..4626188 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -850,6 +850,7 @@ enum tc_setup_type {
TC_SETUP_QDISC_TAPRIO,
TC_SETUP_FT,
TC_SETUP_QDISC_ETS,
+ TC_SETUP_QDISC_TBF,
};
/* These structures hold the attributes of bpf state that are being passed
@@ -876,6 +877,7 @@ enum bpf_netdev_command {
struct bpf_prog_offload_ops;
struct netlink_ext_ack;
struct xdp_umem;
+struct xdp_dev_bulk_queue;
struct netdev_bpf {
enum bpf_netdev_command command;
@@ -937,6 +939,11 @@ struct netdev_name_node {
int netdev_name_node_alt_create(struct net_device *dev, const char *name);
int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
+struct netdev_net_notifier {
+ struct list_head list;
+ struct notifier_block *nb;
+};
+
/*
* This structure defines the management hooks for network devices.
* The following hooks can be defined; unless noted otherwise, they are
@@ -1791,6 +1798,10 @@ enum netdev_priv_flags {
*
* @wol_enabled: Wake-on-LAN is enabled
*
+ * @net_notifier_list: List of per-net netdev notifier block
+ * that follow this device when it is moved
+ * to another network namespace.
+ *
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
@@ -1986,12 +1997,10 @@ struct net_device {
unsigned int num_tx_queues;
unsigned int real_num_tx_queues;
struct Qdisc *qdisc;
-#ifdef CONFIG_NET_SCHED
- DECLARE_HASHTABLE (qdisc_hash, 4);
-#endif
unsigned int tx_queue_len;
spinlock_t tx_global_lock;
- int watchdog_timeo;
+
+ struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
#ifdef CONFIG_XPS
struct xps_dev_maps __rcu *xps_cpus_map;
@@ -2001,11 +2010,15 @@ struct net_device {
struct mini_Qdisc __rcu *miniq_egress;
#endif
+#ifdef CONFIG_NET_SCHED
+ DECLARE_HASHTABLE (qdisc_hash, 4);
+#endif
/* These may be needed for future network-power-down code. */
struct timer_list watchdog_timer;
+ int watchdog_timeo;
- int __percpu *pcpu_refcnt;
struct list_head todo_list;
+ int __percpu *pcpu_refcnt;
struct list_head link_watch_list;
@@ -2081,6 +2094,8 @@ struct net_device {
struct lock_class_key addr_list_lock_key;
bool proto_down;
unsigned wol_enabled:1;
+
+ struct list_head net_notifier_list;
};
#define to_net_dev(d) container_of(d, struct net_device, dev)
@@ -2322,7 +2337,8 @@ struct napi_gro_cb {
/* Number of gro_receive callbacks this packet already went through */
u8 recursion_counter:4;
- /* 1 bit hole */
+ /* GRO is done by frag_list pointer chaining. */
+ u8 is_flist:1;
/* used to support CHECKSUM_COMPLETE for tunneling protocols */
__wsum csum;
@@ -2524,6 +2540,12 @@ int unregister_netdevice_notifier(struct notifier_block *nb);
int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb);
int unregister_netdevice_notifier_net(struct net *net,
struct notifier_block *nb);
+int register_netdevice_notifier_dev_net(struct net_device *dev,
+ struct notifier_block *nb,
+ struct netdev_net_notifier *nn);
+int unregister_netdevice_notifier_dev_net(struct net_device *dev,
+ struct notifier_block *nb,
+ struct netdev_net_notifier *nn);
struct netdev_notifier_info {
struct net_device *dev;
@@ -2690,6 +2712,7 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id);
int netdev_get_name(struct net *net, char *name, int ifindex);
int dev_restart(struct net_device *dev);
int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
+int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb);
static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
{
@@ -3701,6 +3724,8 @@ int dev_set_alias(struct net_device *, const char *, size_t);
int dev_get_alias(const struct net_device *, char *, size_t);
int dev_change_net_namespace(struct net_device *, struct net *, const char *);
int __dev_set_mtu(struct net_device *, int);
+int dev_validate_mtu(struct net_device *dev, int mtu,
+ struct netlink_ext_ack *extack);
int dev_set_mtu_ext(struct net_device *dev, int mtu,
struct netlink_ext_ack *extack);
int dev_set_mtu(struct net_device *, int);
@@ -4564,6 +4589,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT));
return (features & feature) == feature;
}
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 4d8b1ea..908d38d 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -426,13 +426,6 @@ ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr)
sizeof(*addr));
}
-/* Calculate the bytes required to store the inclusive range of a-b */
-static inline int
-bitmap_bytes(u32 a, u32 b)
-{
- return 4 * ((((b - a + 8) / 8) + 3) / 4);
-}
-
/* How often should the gc be run by default */
#define IPSET_GC_TIME (3 * 60)
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index cf09ab3..851425c 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -31,7 +31,7 @@ struct nfnetlink_subsystem {
const struct nfnl_callback *cb; /* callback for individual types */
struct module *owner;
int (*commit)(struct net *net, struct sk_buff *skb);
- int (*abort)(struct net *net, struct sk_buff *skb);
+ int (*abort)(struct net *net, struct sk_buff *skb, bool autoload);
void (*cleanup)(struct net *net);
bool (*valid_genid)(struct net *net, u32 genid);
};
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 30e599c..c570e16 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -22,6 +22,7 @@
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/mod_devicetable.h>
+#include <linux/u64_stats_sync.h>
#include <linux/atomic.h>
@@ -100,9 +101,11 @@ typedef enum {
PHY_INTERFACE_MODE_2500BASEX,
PHY_INTERFACE_MODE_RXAUI,
PHY_INTERFACE_MODE_XAUI,
- /* 10GBASE-KR, XFI, SFI - single lane 10G Serdes */
- PHY_INTERFACE_MODE_10GKR,
+ /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */
+ PHY_INTERFACE_MODE_10GBASER,
PHY_INTERFACE_MODE_USXGMII,
+ /* 10GBASE-KR - with Clause 73 AN */
+ PHY_INTERFACE_MODE_10GKR,
PHY_INTERFACE_MODE_MAX,
} phy_interface_t;
@@ -176,10 +179,12 @@ static inline const char *phy_modes(phy_interface_t interface)
return "rxaui";
case PHY_INTERFACE_MODE_XAUI:
return "xaui";
- case PHY_INTERFACE_MODE_10GKR:
- return "10gbase-kr";
+ case PHY_INTERFACE_MODE_10GBASER:
+ return "10gbase-r";
case PHY_INTERFACE_MODE_USXGMII:
return "usxgmii";
+ case PHY_INTERFACE_MODE_10GKR:
+ return "10gbase-kr";
default:
return "unknown";
}
@@ -208,6 +213,15 @@ struct sfp_bus;
struct sfp_upstream_ops;
struct sk_buff;
+struct mdio_bus_stats {
+ u64_stats_t transfers;
+ u64_stats_t errors;
+ u64_stats_t writes;
+ u64_stats_t reads;
+ /* Must be last, add new statistics above */
+ struct u64_stats_sync syncp;
+};
+
/*
* The Bus class for PHYs. Devices which provide access to
* PHYs should register using this structure
@@ -220,6 +234,7 @@ struct mii_bus {
int (*read)(struct mii_bus *bus, int addr, int regnum);
int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val);
int (*reset)(struct mii_bus *bus);
+ struct mdio_bus_stats stats[PHY_MAX_ADDR];
/*
* A lock to ensure that only one thing can read/write
@@ -328,6 +343,9 @@ struct phy_c45_device_ids {
u32 device_ids[8];
};
+struct macsec_context;
+struct macsec_ops;
+
/* phy_device: An instance of a PHY
*
* drv: Pointer to the driver for this PHY instance
@@ -350,6 +368,7 @@ struct phy_c45_device_ids {
* attached_dev: The attached enet driver's device instance ptr
* adjust_link: Callback for the enet controller to respond to
* changes in the link state.
+ * macsec_ops: MACsec offloading ops.
*
* speed, duplex, pause, supported, advertising, lp_advertising,
* and autoneg are used like in mii_if_info
@@ -449,6 +468,11 @@ struct phy_device {
void (*phy_link_change)(struct phy_device *, bool up, bool do_carrier);
void (*adjust_link)(struct net_device *dev);
+
+#if IS_ENABLED(CONFIG_MACSEC)
+ /* MACsec management functions */
+ const struct macsec_ops *macsec_ops;
+#endif
};
#define to_phy_device(d) container_of(to_mdio_device(d), \
struct phy_device, mdio)
@@ -1127,6 +1151,8 @@ static inline void phy_unlock_mdio_bus(struct phy_device *phydev)
void phy_attached_print(struct phy_device *phydev, const char *fmt, ...)
__printf(2, 3);
+char *phy_attached_info_irq(struct phy_device *phydev)
+ __malloc;
void phy_attached_info(struct phy_device *phydev);
/* Clause 22 PHY */
@@ -1216,6 +1242,8 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev,
int phy_ethtool_ksettings_set(struct phy_device *phydev,
const struct ethtool_link_ksettings *cmd);
int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd);
+int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
+int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd);
void phy_request_interrupt(struct phy_device *phydev);
void phy_free_interrupt(struct phy_device *phydev);
void phy_print_status(struct phy_device *phydev);
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index fed5488..523209e 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -63,10 +63,12 @@ enum phylink_op_type {
* struct phylink_config - PHYLINK configuration structure
* @dev: a pointer to a struct device associated with the MAC
* @type: operation type of PHYLINK instance
+ * @pcs_poll: MAC PCS cannot provide link change interrupt
*/
struct phylink_config {
struct device *dev;
enum phylink_op_type type;
+ bool pcs_poll;
};
/**
diff --git a/include/linux/platform_data/eth_ixp4xx.h b/include/linux/platform_data/eth_ixp4xx.h
new file mode 100644
index 0000000..6f652ea
--- /dev/null
+++ b/include/linux/platform_data/eth_ixp4xx.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PLATFORM_DATA_ETH_IXP4XX
+#define __PLATFORM_DATA_ETH_IXP4XX
+
+#include <linux/types.h>
+
+#define IXP4XX_ETH_NPEA 0x00
+#define IXP4XX_ETH_NPEB 0x10
+#define IXP4XX_ETH_NPEC 0x20
+
+/* Information about built-in Ethernet MAC interfaces */
+struct eth_plat_info {
+ u8 phy; /* MII PHY ID, 0 - 31 */
+ u8 rxq; /* configurable, currently 0 - 31 only */
+ u8 txreadyq;
+ u8 hwaddr[6];
+};
+
+#endif
diff --git a/include/linux/platform_data/wan_ixp4xx_hss.h b/include/linux/platform_data/wan_ixp4xx_hss.h
new file mode 100644
index 0000000..d525a0f
--- /dev/null
+++ b/include/linux/platform_data/wan_ixp4xx_hss.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PLATFORM_DATA_WAN_IXP4XX_HSS_H
+#define __PLATFORM_DATA_WAN_IXP4XX_HSS_H
+
+#include <linux/types.h>
+
+/* Information about built-in HSS (synchronous serial) interfaces */
+struct hss_plat_info {
+ int (*set_clock)(int port, unsigned int clock_type);
+ int (*open)(int port, void *pdev,
+ void (*set_carrier_cb)(void *pdev, int carrier));
+ void (*close)(int port, void *pdev);
+ u8 txreadyq;
+ u32 timer_freq;
+};
+
+#endif
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 0abe9a4..417db0a 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -23,6 +23,7 @@
#include <linux/types.h>
#include <linux/compiler.h>
#include <linux/slab.h>
+#include <linux/mm.h>
#include <asm/errno.h>
#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 467d260..716ad1d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1929,11 +1929,11 @@ static inline void rseq_migrate(struct task_struct *t)
/*
* If parent process has a registered restartable sequences area, the
- * child inherits. Only applies when forking a process, not a thread.
+ * child inherits. Unregister rseq for a clone with CLONE_VM set.
*/
static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
{
- if (clone_flags & CLONE_THREAD) {
+ if (clone_flags & CLONE_VM) {
t->rseq = NULL;
t->rseq_sig = 0;
t->rseq_event_mask = 0;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e9133bc..3d13a4b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -592,6 +592,8 @@ enum {
SKB_GSO_UDP = 1 << 16,
SKB_GSO_UDP_L4 = 1 << 17,
+
+ SKB_GSO_FRAGLIST = 1 << 18,
};
#if BITS_PER_LONG > 32
@@ -1478,6 +1480,11 @@ static inline void skb_mark_not_on_list(struct sk_buff *skb)
skb->next = NULL;
}
+/* Iterate through singly-linked GSO fragments of an skb. */
+#define skb_list_walk_safe(first, skb, next_skb) \
+ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \
+ (skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL)
+
static inline void skb_list_del_init(struct sk_buff *skb)
{
__list_del_entry(&skb->list);
@@ -3459,7 +3466,8 @@ static inline void skb_frag_list_init(struct sk_buff *skb)
for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next)
-int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
+int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue,
+ int *err, long *timeo_p,
const struct sk_buff *skb);
struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
struct sk_buff_head *queue,
@@ -3468,12 +3476,16 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
struct sk_buff *skb),
int *off, int *err,
struct sk_buff **last);
-struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags,
+struct sk_buff *__skb_try_recv_datagram(struct sock *sk,
+ struct sk_buff_head *queue,
+ unsigned int flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb),
int *off, int *err,
struct sk_buff **last);
-struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
+struct sk_buff *__skb_recv_datagram(struct sock *sk,
+ struct sk_buff_head *sk_queue,
+ unsigned int flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb),
int *off, int *err);
@@ -3523,6 +3535,8 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet);
bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu);
bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len);
struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
+struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features,
+ unsigned int offset);
struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
int skb_ensure_writable(struct sk_buff *skb, int write_len);
int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
@@ -4092,6 +4106,9 @@ enum skb_ext_id {
#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
TC_SKB_EXT,
#endif
+#if IS_ENABLED(CONFIG_MPTCP)
+ SKB_EXT_MPTCP,
+#endif
SKB_EXT_NUM, /* must be last */
};
@@ -4112,6 +4129,9 @@ struct skb_ext {
char data[0] __aligned(8);
};
+struct skb_ext *__skb_ext_alloc(void);
+void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id,
+ struct skb_ext *ext);
void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id);
void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id);
void __skb_ext_put(struct skb_ext *ext);
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index ef7031f..14d61bba 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -358,17 +358,22 @@ static inline void sk_psock_update_proto(struct sock *sk,
static inline void sk_psock_restore_proto(struct sock *sk,
struct sk_psock *psock)
{
- sk->sk_write_space = psock->saved_write_space;
+ sk->sk_prot->unhash = psock->saved_unhash;
if (psock->sk_proto) {
struct inet_connection_sock *icsk = inet_csk(sk);
bool has_ulp = !!icsk->icsk_ulp_data;
- if (has_ulp)
- tcp_update_ulp(sk, psock->sk_proto);
- else
+ if (has_ulp) {
+ tcp_update_ulp(sk, psock->sk_proto,
+ psock->saved_write_space);
+ } else {
sk->sk_prot = psock->sk_proto;
+ sk->sk_write_space = psock->saved_write_space;
+ }
psock->sk_proto = NULL;
+ } else {
+ sk->sk_write_space = psock->saved_write_space;
}
}
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 98fe866..3a67a7e 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -689,10 +689,10 @@ extern void spi_finalize_current_transfer(struct spi_controller *ctlr);
/* Helper calls for driver to timestamp transfer */
void spi_take_timestamp_pre(struct spi_controller *ctlr,
struct spi_transfer *xfer,
- const void *tx, bool irqs_off);
+ size_t progress, bool irqs_off);
void spi_take_timestamp_post(struct spi_controller *ctlr,
struct spi_transfer *xfer,
- const void *tx, bool irqs_off);
+ size_t progress, bool irqs_off);
/* the spi driver core manages memory for the spi_controller classdev */
extern struct spi_controller *__spi_alloc_controller(struct device *host,
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 0531afa..19190c6 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -139,6 +139,7 @@ struct stmmac_txq_cfg {
u32 low_credit;
bool use_prio;
u32 prio;
+ int tbs_en;
};
struct plat_stmmacenet_data {
diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h
index 85ec745..966146f 100644
--- a/include/linux/sxgbe_platform.h
+++ b/include/linux/sxgbe_platform.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
- * 10G controller driver for Samsung EXYNOS SoCs
+ * 10G controller driver for Samsung Exynos SoCs
*
* Copyright (C) 2013 Samsung Electronics Co., Ltd.
* http://www.samsung.com
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2960ded..5262b7a 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1232,6 +1232,7 @@ asmlinkage long sys_ni_syscall(void);
*/
int ksys_umount(char __user *name, int flags);
+int ksys_dup(unsigned int fildes);
int ksys_chroot(const char __user *filename);
ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
int ksys_chdir(const char __user *filename);
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index ca6f015..1cf73e6 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -78,6 +78,27 @@ struct tcp_sack_block {
#define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */
#define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/
+#if IS_ENABLED(CONFIG_MPTCP)
+struct mptcp_options_received {
+ u64 sndr_key;
+ u64 rcvr_key;
+ u64 data_ack;
+ u64 data_seq;
+ u32 subflow_seq;
+ u16 data_len;
+ u8 mp_capable : 1,
+ mp_join : 1,
+ dss : 1;
+ u8 use_map:1,
+ dsn64:1,
+ data_fin:1,
+ use_ack:1,
+ ack64:1,
+ mpc_map:1,
+ __unused:2;
+};
+#endif
+
struct tcp_options_received {
/* PAWS/RTTM data */
int ts_recent_stamp;/* Time we stored ts_recent (for aging) */
@@ -95,6 +116,9 @@ struct tcp_options_received {
u8 num_sacks; /* Number of SACK blocks */
u16 user_mss; /* mss requested by user in ioctl */
u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
+#if IS_ENABLED(CONFIG_MPTCP)
+ struct mptcp_options_received mptcp;
+#endif
};
static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
@@ -104,6 +128,11 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
#if IS_ENABLED(CONFIG_SMC)
rx_opt->smc_ok = 0;
#endif
+#if IS_ENABLED(CONFIG_MPTCP)
+ rx_opt->mptcp.mp_capable = 0;
+ rx_opt->mptcp.mp_join = 0;
+ rx_opt->mptcp.dss = 0;
+#endif
}
/* This is the max number of SACKS that we'll generate and process. It's safe
@@ -119,6 +148,9 @@ struct tcp_request_sock {
const struct tcp_request_sock_ops *af_specific;
u64 snt_synack; /* first SYNACK sent time */
bool tfo_listener;
+#if IS_ENABLED(CONFIG_MPTCP)
+ bool is_mptcp;
+#endif
u32 txhash;
u32 rcv_isn;
u32 snt_isn;
@@ -354,6 +386,8 @@ struct tcp_sock {
#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0
#endif
+ u16 timeout_rehash; /* Timeout-triggered rehash attempts */
+
u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */
/* Receiver side RTT estimation */
@@ -379,6 +413,9 @@ struct tcp_sock {
u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG
* while socket was owned by user.
*/
+#if IS_ENABLED(CONFIG_MPTCP)
+ bool is_mptcp;
+#endif
#ifdef CONFIG_TCP_MD5SIG
/* TCP AF-Specific parts; only used by MD5 Signature support so far */
diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index c17af77..ea627d1 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -30,7 +30,7 @@ struct tnum tnum_lshift(struct tnum a, u8 shift);
/* Shift (rsh) a tnum right (by a fixed shift) */
struct tnum tnum_rshift(struct tnum a, u8 shift);
/* Shift (arsh) a tnum right (by a fixed min_shift) */
-struct tnum tnum_arshift(struct tnum a, u8 min_shift);
+struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness);
/* Add two tnums, return @a + @b */
struct tnum tnum_add(struct tnum a, struct tnum b);
/* Subtract two tnums, return @a - @b */
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 86eecbd..f73e177 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -417,6 +417,36 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
}
/**
+ * xa_for_each_range() - Iterate over a portion of an XArray.
+ * @xa: XArray.
+ * @index: Index of @entry.
+ * @entry: Entry retrieved from array.
+ * @start: First index to retrieve from array.
+ * @last: Last index to retrieve from array.
+ *
+ * During the iteration, @entry will have the value of the entry stored
+ * in @xa at @index. You may modify @index during the iteration if you
+ * want to skip or reprocess indices. It is safe to modify the array
+ * during the iteration. At the end of the iteration, @entry will be set
+ * to NULL and @index will have a value less than or equal to max.
+ *
+ * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have
+ * to handle your own locking with xas_for_each(), and if you have to unlock
+ * after each iteration, it will also end up being O(n.log(n)).
+ * xa_for_each_range() will spin if it hits a retry entry; if you intend to
+ * see retry entries, you should use the xas_for_each() iterator instead.
+ * The xas_for_each() iterator will expand into more inline code than
+ * xa_for_each_range().
+ *
+ * Context: Any context. Takes and releases the RCU lock.
+ */
+#define xa_for_each_range(xa, index, entry, start, last) \
+ for (index = start, \
+ entry = xa_find(xa, &index, last, XA_PRESENT); \
+ entry; \
+ entry = xa_find_after(xa, &index, last, XA_PRESENT))
+
+/**
* xa_for_each_start() - Iterate over a portion of an XArray.
* @xa: XArray.
* @index: Index of @entry.
@@ -439,11 +469,8 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
*
* Context: Any context. Takes and releases the RCU lock.
*/
-#define xa_for_each_start(xa, index, entry, start) \
- for (index = start, \
- entry = xa_find(xa, &index, ULONG_MAX, XA_PRESENT); \
- entry; \
- entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT))
+#define xa_for_each_start(xa, index, entry, start) \
+ xa_for_each_range(xa, index, entry, start, ULONG_MAX)
/**
* xa_for_each() - Iterate over present entries in an XArray.
@@ -508,6 +535,14 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
spin_lock_irqsave(&(xa)->xa_lock, flags)
#define xa_unlock_irqrestore(xa, flags) \
spin_unlock_irqrestore(&(xa)->xa_lock, flags)
+#define xa_lock_nested(xa, subclass) \
+ spin_lock_nested(&(xa)->xa_lock, subclass)
+#define xa_lock_bh_nested(xa, subclass) \
+ spin_lock_bh_nested(&(xa)->xa_lock, subclass)
+#define xa_lock_irq_nested(xa, subclass) \
+ spin_lock_irq_nested(&(xa)->xa_lock, subclass)
+#define xa_lock_irqsave_nested(xa, flags, subclass) \
+ spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass)
/*
* Versions of the normal API which require the caller to hold the
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 059524b..f22bd6c 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3548,6 +3548,9 @@ struct cfg80211_update_owe_info {
*
* @start_radar_detection: Start radar detection in the driver.
*
+ * @end_cac: End running CAC, probably because a related CAC
+ * was finished on another phy.
+ *
* @update_ft_ies: Provide updated Fast BSS Transition information to the
* driver. If the SME is in the driver/firmware, this information can be
* used in building Authentication and Reassociation Request frames.
@@ -3874,6 +3877,8 @@ struct cfg80211_ops {
struct net_device *dev,
struct cfg80211_chan_def *chandef,
u32 cac_time_ms);
+ void (*end_cac)(struct wiphy *wiphy,
+ struct net_device *dev);
int (*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev,
struct cfg80211_update_ft_ies_params *ftie);
int (*crit_proto_start)(struct wiphy *wiphy,
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 47f87b2..5e46c24 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -485,6 +485,8 @@ enum devlink_param_generic_id {
#define DEVLINK_INFO_VERSION_GENERIC_FW_UNDI "fw.undi"
/* NCSI support/handler version */
#define DEVLINK_INFO_VERSION_GENERIC_FW_NCSI "fw.ncsi"
+/* FW parameter set id */
+#define DEVLINK_INFO_VERSION_GENERIC_FW_PSID "fw.psid"
struct devlink_region;
struct devlink_info_req;
@@ -562,7 +564,7 @@ struct devlink_trap {
};
/* All traps must be documented in
- * Documentation/networking/devlink-trap.rst
+ * Documentation/networking/devlink/devlink-trap.rst
*/
enum devlink_trap_generic_id {
DEVLINK_TRAP_GENERIC_ID_SMAC_MC,
@@ -589,6 +591,9 @@ enum devlink_trap_generic_id {
DEVLINK_TRAP_GENERIC_ID_REJECT_ROUTE,
DEVLINK_TRAP_GENERIC_ID_IPV4_LPM_UNICAST_MISS,
DEVLINK_TRAP_GENERIC_ID_IPV6_LPM_UNICAST_MISS,
+ DEVLINK_TRAP_GENERIC_ID_NON_ROUTABLE,
+ DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR,
+ DEVLINK_TRAP_GENERIC_ID_OVERLAY_SMAC_MC,
/* Add new generic trap IDs above */
__DEVLINK_TRAP_GENERIC_ID_MAX,
@@ -596,12 +601,13 @@ enum devlink_trap_generic_id {
};
/* All trap groups must be documented in
- * Documentation/networking/devlink-trap.rst
+ * Documentation/networking/devlink/devlink-trap.rst
*/
enum devlink_trap_group_generic_id {
DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS,
DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS,
DEVLINK_TRAP_GROUP_GENERIC_ID_BUFFER_DROPS,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_TUNNEL_DROPS,
/* Add new generic trap group IDs above */
__DEVLINK_TRAP_GROUP_GENERIC_ID_MAX,
@@ -657,6 +663,12 @@ enum devlink_trap_group_generic_id {
"ipv4_lpm_miss"
#define DEVLINK_TRAP_GENERIC_NAME_IPV6_LPM_UNICAST_MISS \
"ipv6_lpm_miss"
+#define DEVLINK_TRAP_GENERIC_NAME_NON_ROUTABLE \
+ "non_routable_packet"
+#define DEVLINK_TRAP_GENERIC_NAME_DECAP_ERROR \
+ "decap_error"
+#define DEVLINK_TRAP_GENERIC_NAME_OVERLAY_SMAC_MC \
+ "overlay_smac_is_mc"
#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \
"l2_drops"
@@ -664,6 +676,8 @@ enum devlink_trap_group_generic_id {
"l3_drops"
#define DEVLINK_TRAP_GROUP_GENERIC_NAME_BUFFER_DROPS \
"buffer_drops"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_TUNNEL_DROPS \
+ "tunnel_drops"
#define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group, _metadata_cap) \
{ \
@@ -938,7 +952,7 @@ struct devlink_region *devlink_region_create(struct devlink *devlink,
u32 region_max_snapshots,
u64 region_size);
void devlink_region_destroy(struct devlink_region *region);
-u32 devlink_region_shapshot_id_get(struct devlink *devlink);
+u32 devlink_region_snapshot_id_get(struct devlink *devlink);
int devlink_region_snapshot_create(struct devlink_region *region,
u8 *data, u32 snapshot_id,
devlink_snapshot_data_dest_t *data_destructor);
@@ -1000,6 +1014,8 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
void
devlink_health_reporter_state_update(struct devlink_health_reporter *reporter,
enum devlink_health_reporter_state state);
+void
+devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter);
bool devlink_is_reload_failed(const struct devlink *devlink);
diff --git a/include/net/dsa.h b/include/net/dsa.h
index da5578d..63495e3 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -90,7 +90,6 @@ struct dsa_device_ops {
struct dsa_skb_cb {
struct sk_buff *clone;
- bool deferred_xmit;
};
struct __dsa_skb_cb {
@@ -192,9 +191,6 @@ struct dsa_port {
struct phylink *pl;
struct phylink_config pl_config;
- struct work_struct xmit_work;
- struct sk_buff_head xmit_queue;
-
struct list_head list;
/*
@@ -283,6 +279,11 @@ struct dsa_switch {
*/
bool vlan_filtering;
+ /* MAC PCS does not provide link state change interrupt, and requires
+ * polling. Flag passed on to PHYLINK.
+ */
+ bool pcs_poll;
+
size_t num_ports;
};
@@ -379,7 +380,8 @@ typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid,
bool is_static, void *data);
struct dsa_switch_ops {
enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds,
- int port);
+ int port,
+ enum dsa_tag_protocol mprot);
int (*setup)(struct dsa_switch *ds);
void (*teardown)(struct dsa_switch *ds);
@@ -564,11 +566,6 @@ struct dsa_switch_ops {
bool (*port_rxtstamp)(struct dsa_switch *ds, int port,
struct sk_buff *skb, unsigned int type);
- /*
- * Deferred frame Tx
- */
- netdev_tx_t (*port_deferred_xmit)(struct dsa_switch *ds, int port,
- struct sk_buff *skb);
/* Devlink parameters */
int (*devlink_param_get)(struct dsa_switch *ds, u32 id,
struct devlink_param_gset_ctx *ctx);
diff --git a/include/net/espintcp.h b/include/net/espintcp.h
new file mode 100644
index 0000000..dd7026a
--- /dev/null
+++ b/include/net/espintcp.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_ESPINTCP_H
+#define _NET_ESPINTCP_H
+
+#include <net/strparser.h>
+#include <linux/skmsg.h>
+
+void __init espintcp_init(void);
+
+int espintcp_push_skb(struct sock *sk, struct sk_buff *skb);
+int espintcp_queue_out(struct sock *sk, struct sk_buff *skb);
+bool tcp_is_ulp_esp(struct sock *sk);
+
+struct espintcp_msg {
+ struct sk_buff *skb;
+ struct sk_msg skmsg;
+ int offset;
+ int len;
+};
+
+struct espintcp_ctx {
+ struct strparser strp;
+ struct sk_buff_head ike_queue;
+ struct sk_buff_head out_queue;
+ struct espintcp_msg partial;
+ void (*saved_data_ready)(struct sock *sk);
+ void (*saved_write_space)(struct sock *sk);
+ struct work_struct work;
+ bool tx_running;
+};
+
+static inline struct espintcp_ctx *espintcp_getctx(const struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ /* RCU is only needed for diag */
+ return (__force void *)icsk->icsk_ulp_data;
+}
+#endif
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index b579fae..fd60a8a 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -192,7 +192,9 @@ struct fib6_info {
dst_nopolicy:1,
dst_host:1,
fib6_destroying:1,
- unused:3;
+ offload:1,
+ trap:1,
+ unused:1;
struct rcu_head rcu;
struct nexthop *nh;
@@ -329,6 +331,13 @@ static inline void fib6_info_release(struct fib6_info *f6i)
call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
}
+static inline void fib6_info_hw_flags_set(struct fib6_info *f6i, bool offload,
+ bool trap)
+{
+ f6i->offload = offload;
+ f6i->trap = trap;
+}
+
enum fib6_walk_state {
#ifdef CONFIG_IPV6_SUBTREES
FWS_S,
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index b9cba41..6a1ae49 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -204,6 +204,18 @@ __be32 fib_result_prefsrc(struct net *net, struct fib_result *res);
#define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev)
#define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif)
+struct fib_rt_info {
+ struct fib_info *fi;
+ u32 tb_id;
+ __be32 dst;
+ int dst_len;
+ u8 tos;
+ u8 type;
+ u8 offload:1,
+ trap:1,
+ unused:6;
+};
+
struct fib_entry_notifier_info {
struct fib_notifier_info info; /* must be first */
u32 dst;
@@ -464,6 +476,7 @@ int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *fc_encap,
void fib_nh_common_release(struct fib_nh_common *nhc);
/* Exported by fib_trie.c */
+void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri);
void fib_trie_init(void);
struct fib_table *fib_trie_table(u32 id, struct fib_table *alias);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4e95f6d..cec1a54 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1113,6 +1113,9 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int inet6_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk);
+int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
+int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+ int flags);
/*
* reassembly.c
diff --git a/include/net/macsec.h b/include/net/macsec.h
new file mode 100644
index 0000000..92e43db
--- /dev/null
+++ b/include/net/macsec.h
@@ -0,0 +1,224 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * MACsec netdev header, used for h/w accelerated implementations.
+ *
+ * Copyright (c) 2015 Sabrina Dubroca <sd@queasysnail.net>
+ */
+#ifndef _NET_MACSEC_H_
+#define _NET_MACSEC_H_
+
+#include <linux/u64_stats_sync.h>
+#include <uapi/linux/if_link.h>
+#include <uapi/linux/if_macsec.h>
+
+typedef u64 __bitwise sci_t;
+
+#define MACSEC_NUM_AN 4 /* 2 bits for the association number */
+
+/**
+ * struct macsec_key - SA key
+ * @id: user-provided key identifier
+ * @tfm: crypto struct, key storage
+ */
+struct macsec_key {
+ u8 id[MACSEC_KEYID_LEN];
+ struct crypto_aead *tfm;
+};
+
+struct macsec_rx_sc_stats {
+ __u64 InOctetsValidated;
+ __u64 InOctetsDecrypted;
+ __u64 InPktsUnchecked;
+ __u64 InPktsDelayed;
+ __u64 InPktsOK;
+ __u64 InPktsInvalid;
+ __u64 InPktsLate;
+ __u64 InPktsNotValid;
+ __u64 InPktsNotUsingSA;
+ __u64 InPktsUnusedSA;
+};
+
+struct macsec_rx_sa_stats {
+ __u32 InPktsOK;
+ __u32 InPktsInvalid;
+ __u32 InPktsNotValid;
+ __u32 InPktsNotUsingSA;
+ __u32 InPktsUnusedSA;
+};
+
+struct macsec_tx_sa_stats {
+ __u32 OutPktsProtected;
+ __u32 OutPktsEncrypted;
+};
+
+struct macsec_tx_sc_stats {
+ __u64 OutPktsProtected;
+ __u64 OutPktsEncrypted;
+ __u64 OutOctetsProtected;
+ __u64 OutOctetsEncrypted;
+};
+
+/**
+ * struct macsec_rx_sa - receive secure association
+ * @active:
+ * @next_pn: packet number expected for the next packet
+ * @lock: protects next_pn manipulations
+ * @key: key structure
+ * @stats: per-SA stats
+ */
+struct macsec_rx_sa {
+ struct macsec_key key;
+ spinlock_t lock;
+ u32 next_pn;
+ refcount_t refcnt;
+ bool active;
+ struct macsec_rx_sa_stats __percpu *stats;
+ struct macsec_rx_sc *sc;
+ struct rcu_head rcu;
+};
+
+struct pcpu_rx_sc_stats {
+ struct macsec_rx_sc_stats stats;
+ struct u64_stats_sync syncp;
+};
+
+struct pcpu_tx_sc_stats {
+ struct macsec_tx_sc_stats stats;
+ struct u64_stats_sync syncp;
+};
+
+/**
+ * struct macsec_rx_sc - receive secure channel
+ * @sci: secure channel identifier for this SC
+ * @active: channel is active
+ * @sa: array of secure associations
+ * @stats: per-SC stats
+ */
+struct macsec_rx_sc {
+ struct macsec_rx_sc __rcu *next;
+ sci_t sci;
+ bool active;
+ struct macsec_rx_sa __rcu *sa[MACSEC_NUM_AN];
+ struct pcpu_rx_sc_stats __percpu *stats;
+ refcount_t refcnt;
+ struct rcu_head rcu_head;
+};
+
+/**
+ * struct macsec_tx_sa - transmit secure association
+ * @active:
+ * @next_pn: packet number to use for the next packet
+ * @lock: protects next_pn manipulations
+ * @key: key structure
+ * @stats: per-SA stats
+ */
+struct macsec_tx_sa {
+ struct macsec_key key;
+ spinlock_t lock;
+ u32 next_pn;
+ refcount_t refcnt;
+ bool active;
+ struct macsec_tx_sa_stats __percpu *stats;
+ struct rcu_head rcu;
+};
+
+/**
+ * struct macsec_tx_sc - transmit secure channel
+ * @active:
+ * @encoding_sa: association number of the SA currently in use
+ * @encrypt: encrypt packets on transmit, or authenticate only
+ * @send_sci: always include the SCI in the SecTAG
+ * @end_station:
+ * @scb: single copy broadcast flag
+ * @sa: array of secure associations
+ * @stats: stats for this TXSC
+ */
+struct macsec_tx_sc {
+ bool active;
+ u8 encoding_sa;
+ bool encrypt;
+ bool send_sci;
+ bool end_station;
+ bool scb;
+ struct macsec_tx_sa __rcu *sa[MACSEC_NUM_AN];
+ struct pcpu_tx_sc_stats __percpu *stats;
+};
+
+/**
+ * struct macsec_secy - MACsec Security Entity
+ * @netdev: netdevice for this SecY
+ * @n_rx_sc: number of receive secure channels configured on this SecY
+ * @sci: secure channel identifier used for tx
+ * @key_len: length of keys used by the cipher suite
+ * @icv_len: length of ICV used by the cipher suite
+ * @validate_frames: validation mode
+ * @operational: MAC_Operational flag
+ * @protect_frames: enable protection for this SecY
+ * @replay_protect: enable packet number checks on receive
+ * @replay_window: size of the replay window
+ * @tx_sc: transmit secure channel
+ * @rx_sc: linked list of receive secure channels
+ */
+struct macsec_secy {
+ struct net_device *netdev;
+ unsigned int n_rx_sc;
+ sci_t sci;
+ u16 key_len;
+ u16 icv_len;
+ enum macsec_validation_type validate_frames;
+ bool operational;
+ bool protect_frames;
+ bool replay_protect;
+ u32 replay_window;
+ struct macsec_tx_sc tx_sc;
+ struct macsec_rx_sc __rcu *rx_sc;
+};
+
+/**
+ * struct macsec_context - MACsec context for hardware offloading
+ */
+struct macsec_context {
+ struct phy_device *phydev;
+ enum macsec_offload offload;
+
+ struct macsec_secy *secy;
+ struct macsec_rx_sc *rx_sc;
+ struct {
+ unsigned char assoc_num;
+ u8 key[MACSEC_KEYID_LEN];
+ union {
+ struct macsec_rx_sa *rx_sa;
+ struct macsec_tx_sa *tx_sa;
+ };
+ } sa;
+
+ u8 prepare:1;
+};
+
+/**
+ * struct macsec_ops - MACsec offloading operations
+ */
+struct macsec_ops {
+ /* Device wide */
+ int (*mdo_dev_open)(struct macsec_context *ctx);
+ int (*mdo_dev_stop)(struct macsec_context *ctx);
+ /* SecY */
+ int (*mdo_add_secy)(struct macsec_context *ctx);
+ int (*mdo_upd_secy)(struct macsec_context *ctx);
+ int (*mdo_del_secy)(struct macsec_context *ctx);
+ /* Security channels */
+ int (*mdo_add_rxsc)(struct macsec_context *ctx);
+ int (*mdo_upd_rxsc)(struct macsec_context *ctx);
+ int (*mdo_del_rxsc)(struct macsec_context *ctx);
+ /* Security associations */
+ int (*mdo_add_rxsa)(struct macsec_context *ctx);
+ int (*mdo_upd_rxsa)(struct macsec_context *ctx);
+ int (*mdo_del_rxsa)(struct macsec_context *ctx);
+ int (*mdo_add_txsa)(struct macsec_context *ctx);
+ int (*mdo_upd_txsa)(struct macsec_context *ctx);
+ int (*mdo_del_txsa)(struct macsec_context *ctx);
+};
+
+void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa);
+
+#endif /* _NET_MACSEC_H_ */
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
new file mode 100644
index 0000000..27627e2
--- /dev/null
+++ b/include/net/mptcp.h
@@ -0,0 +1,188 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#ifndef __NET_MPTCP_H
+#define __NET_MPTCP_H
+
+#include <linux/skbuff.h>
+#include <linux/tcp.h>
+#include <linux/types.h>
+
+/* MPTCP sk_buff extension data */
+struct mptcp_ext {
+ u64 data_ack;
+ u64 data_seq;
+ u32 subflow_seq;
+ u16 data_len;
+ u8 use_map:1,
+ dsn64:1,
+ data_fin:1,
+ use_ack:1,
+ ack64:1,
+ mpc_map:1,
+ __unused:2;
+ /* one byte hole */
+};
+
+struct mptcp_out_options {
+#if IS_ENABLED(CONFIG_MPTCP)
+ u16 suboptions;
+ u64 sndr_key;
+ u64 rcvr_key;
+ struct mptcp_ext ext_copy;
+#endif
+};
+
+#ifdef CONFIG_MPTCP
+
+void mptcp_init(void);
+
+static inline bool sk_is_mptcp(const struct sock *sk)
+{
+ return tcp_sk(sk)->is_mptcp;
+}
+
+static inline bool rsk_is_mptcp(const struct request_sock *req)
+{
+ return tcp_rsk(req)->is_mptcp;
+}
+
+void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
+ int opsize, struct tcp_options_received *opt_rx);
+bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
+ unsigned int *size, struct mptcp_out_options *opts);
+void mptcp_rcv_synsent(struct sock *sk);
+bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
+ struct mptcp_out_options *opts);
+bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
+ unsigned int *size, unsigned int remaining,
+ struct mptcp_out_options *opts);
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
+ struct tcp_options_received *opt_rx);
+
+void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
+
+/* move the skb extension owership, with the assumption that 'to' is
+ * newly allocated
+ */
+static inline void mptcp_skb_ext_move(struct sk_buff *to,
+ struct sk_buff *from)
+{
+ if (!skb_ext_exist(from, SKB_EXT_MPTCP))
+ return;
+
+ if (WARN_ON_ONCE(to->active_extensions))
+ skb_ext_put(to);
+
+ to->active_extensions = from->active_extensions;
+ to->extensions = from->extensions;
+ from->active_extensions = 0;
+}
+
+static inline bool mptcp_ext_matches(const struct mptcp_ext *to_ext,
+ const struct mptcp_ext *from_ext)
+{
+ /* MPTCP always clears the ext when adding it to the skb, so
+ * holes do not bother us here
+ */
+ return !from_ext ||
+ (to_ext && from_ext &&
+ !memcmp(from_ext, to_ext, sizeof(struct mptcp_ext)));
+}
+
+/* check if skbs can be collapsed.
+ * MPTCP collapse is allowed if neither @to or @from carry an mptcp data
+ * mapping, or if the extension of @to is the same as @from.
+ * Collapsing is not possible if @to lacks an extension, but @from carries one.
+ */
+static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
+ const struct sk_buff *from)
+{
+ return mptcp_ext_matches(skb_ext_find(to, SKB_EXT_MPTCP),
+ skb_ext_find(from, SKB_EXT_MPTCP));
+}
+
+#else
+
+static inline void mptcp_init(void)
+{
+}
+
+static inline bool sk_is_mptcp(const struct sock *sk)
+{
+ return false;
+}
+
+static inline bool rsk_is_mptcp(const struct request_sock *req)
+{
+ return false;
+}
+
+static inline void mptcp_parse_option(const struct sk_buff *skb,
+ const unsigned char *ptr, int opsize,
+ struct tcp_options_received *opt_rx)
+{
+}
+
+static inline bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
+ unsigned int *size,
+ struct mptcp_out_options *opts)
+{
+ return false;
+}
+
+static inline void mptcp_rcv_synsent(struct sock *sk)
+{
+}
+
+static inline bool mptcp_synack_options(const struct request_sock *req,
+ unsigned int *size,
+ struct mptcp_out_options *opts)
+{
+ return false;
+}
+
+static inline bool mptcp_established_options(struct sock *sk,
+ struct sk_buff *skb,
+ unsigned int *size,
+ unsigned int remaining,
+ struct mptcp_out_options *opts)
+{
+ return false;
+}
+
+static inline void mptcp_incoming_options(struct sock *sk,
+ struct sk_buff *skb,
+ struct tcp_options_received *opt_rx)
+{
+}
+
+static inline void mptcp_skb_ext_move(struct sk_buff *to,
+ const struct sk_buff *from)
+{
+}
+
+static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
+ const struct sk_buff *from)
+{
+ return true;
+}
+
+#endif /* CONFIG_MPTCP */
+
+void mptcp_handle_ipv6_mapped(struct sock *sk, bool mapped);
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+int mptcpv6_init(void);
+#elif IS_ENABLED(CONFIG_IPV6)
+static inline int mptcpv6_init(void)
+{
+ return 0;
+}
+#endif
+
+#endif /* __NET_MPTCP_H */
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index b8ceaf0..854d39e 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -347,9 +347,9 @@ static inline struct net *read_pnet(const possible_net_t *pnet)
#endif
int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp);
-int peernet2id(struct net *net, struct net *peer);
-bool peernet_has_id(struct net *net, struct net *peer);
-struct net *get_net_ns_by_id(struct net *net, int id);
+int peernet2id(const struct net *net, struct net *peer);
+bool peernet_has_id(const struct net *net, struct net *peer);
+struct net *get_net_ns_by_id(const struct net *net, int id);
struct pernet_operations {
struct list_head list;
@@ -427,7 +427,7 @@ static inline void unregister_net_sysctl_table(struct ctl_table_header *header)
}
#endif
-static inline int rt_genid_ipv4(struct net *net)
+static inline int rt_genid_ipv4(const struct net *net)
{
return atomic_read(&net->ipv4.rt_genid);
}
@@ -459,7 +459,7 @@ static inline void rt_genid_bump_all(struct net *net)
rt_genid_bump_ipv6(net);
}
-static inline int fnhe_genid(struct net *net)
+static inline int fnhe_genid(const struct net *net)
{
return atomic_read(&net->fnhe_genid);
}
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index f0897b3..e0f709d9 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -47,6 +47,11 @@ struct nf_flowtable {
possible_net_t net;
};
+static inline bool nf_flowtable_hw_offload(struct nf_flowtable *flowtable)
+{
+ return flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD;
+}
+
enum flow_offload_tuple_dir {
FLOW_OFFLOAD_DIR_ORIGINAL = IP_CT_DIR_ORIGINAL,
FLOW_OFFLOAD_DIR_REPLY = IP_CT_DIR_REPLY,
@@ -83,13 +88,15 @@ struct flow_offload_tuple_rhash {
struct flow_offload_tuple tuple;
};
-#define FLOW_OFFLOAD_SNAT 0x1
-#define FLOW_OFFLOAD_DNAT 0x2
-#define FLOW_OFFLOAD_DYING 0x4
-#define FLOW_OFFLOAD_TEARDOWN 0x8
-#define FLOW_OFFLOAD_HW 0x10
-#define FLOW_OFFLOAD_HW_DYING 0x20
-#define FLOW_OFFLOAD_HW_DEAD 0x40
+enum nf_flow_flags {
+ NF_FLOW_SNAT,
+ NF_FLOW_DNAT,
+ NF_FLOW_TEARDOWN,
+ NF_FLOW_HW,
+ NF_FLOW_HW_DYING,
+ NF_FLOW_HW_DEAD,
+ NF_FLOW_HW_REFRESH,
+};
enum flow_offload_type {
NF_FLOW_OFFLOAD_UNSPEC = 0,
@@ -99,13 +106,19 @@ enum flow_offload_type {
struct flow_offload {
struct flow_offload_tuple_rhash tuplehash[FLOW_OFFLOAD_DIR_MAX];
struct nf_conn *ct;
- u16 flags;
+ unsigned long flags;
u16 type;
u32 timeout;
struct rcu_head rcu_head;
};
#define NF_FLOW_TIMEOUT (30 * HZ)
+#define nf_flowtable_time_stamp (u32)jiffies
+
+static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
+{
+ return (__s32)(timeout - nf_flowtable_time_stamp);
+}
struct nf_flow_route {
struct {
@@ -128,10 +141,6 @@ int nf_flow_table_init(struct nf_flowtable *flow_table);
void nf_flow_table_free(struct nf_flowtable *flow_table);
void flow_offload_teardown(struct flow_offload *flow);
-static inline void flow_offload_dead(struct flow_offload *flow)
-{
- flow->flags |= FLOW_OFFLOAD_DYING;
-}
int nf_flow_snat_port(const struct flow_offload *flow,
struct sk_buff *skb, unsigned int thoff,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index fe7c50a..4170c03 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -231,6 +231,7 @@ struct nft_userdata {
* struct nft_set_elem - generic representation of set elements
*
* @key: element key
+ * @key_end: closing element key
* @priv: element private data and extensions
*/
struct nft_set_elem {
@@ -238,6 +239,10 @@ struct nft_set_elem {
u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
struct nft_data val;
} key;
+ union {
+ u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
+ struct nft_data val;
+ } key_end;
void *priv;
};
@@ -259,11 +264,15 @@ struct nft_set_iter {
* @klen: key length
* @dlen: data length
* @size: number of set elements
+ * @field_len: length of each field in concatenation, bytes
+ * @field_count: number of concatenated fields in element
*/
struct nft_set_desc {
unsigned int klen;
unsigned int dlen;
unsigned int size;
+ u8 field_len[NFT_REG32_COUNT];
+ u8 field_count;
};
/**
@@ -404,6 +413,8 @@ void nft_unregister_set(struct nft_set_type *type);
* @dtype: data type (verdict or numeric type defined by userspace)
* @objtype: object type (see NFT_OBJECT_* definitions)
* @size: maximum set size
+ * @field_len: length of each field in concatenation, bytes
+ * @field_count: number of concatenated fields in element
* @use: number of rules references to this set
* @nelems: number of elements
* @ndeact: number of deactivated elements queued for removal
@@ -430,6 +441,8 @@ struct nft_set {
u32 dtype;
u32 objtype;
u32 size;
+ u8 field_len[NFT_REG32_COUNT];
+ u8 field_count;
u32 use;
atomic_t nelems;
u32 ndeact;
@@ -502,6 +515,7 @@ void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set);
* enum nft_set_extensions - set extension type IDs
*
* @NFT_SET_EXT_KEY: element key
+ * @NFT_SET_EXT_KEY_END: upper bound element key, for ranges
* @NFT_SET_EXT_DATA: mapping data
* @NFT_SET_EXT_FLAGS: element flags
* @NFT_SET_EXT_TIMEOUT: element timeout
@@ -513,6 +527,7 @@ void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set);
*/
enum nft_set_extensions {
NFT_SET_EXT_KEY,
+ NFT_SET_EXT_KEY_END,
NFT_SET_EXT_DATA,
NFT_SET_EXT_FLAGS,
NFT_SET_EXT_TIMEOUT,
@@ -606,6 +621,11 @@ static inline struct nft_data *nft_set_ext_key(const struct nft_set_ext *ext)
return nft_set_ext(ext, NFT_SET_EXT_KEY);
}
+static inline struct nft_data *nft_set_ext_key_end(const struct nft_set_ext *ext)
+{
+ return nft_set_ext(ext, NFT_SET_EXT_KEY_END);
+}
+
static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext)
{
return nft_set_ext(ext, NFT_SET_EXT_DATA);
@@ -655,7 +675,7 @@ static inline struct nft_object **nft_set_ext_obj(const struct nft_set_ext *ext)
void *nft_set_elem_init(const struct nft_set *set,
const struct nft_set_ext_tmpl *tmpl,
- const u32 *key, const u32 *data,
+ const u32 *key, const u32 *key_end, const u32 *data,
u64 timeout, u64 expiration, gfp_t gfp);
void nft_set_elem_destroy(const struct nft_set *set, void *elem,
bool destroy_expr);
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 2656155..29e7e10 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -74,6 +74,7 @@ extern struct nft_set_type nft_set_hash_type;
extern struct nft_set_type nft_set_hash_fast_type;
extern struct nft_set_type nft_set_rbtree_type;
extern struct nft_set_type nft_set_bitmap_type;
+extern struct nft_set_type nft_set_pipapo_type;
struct nft_expr;
struct nft_regs;
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index 286fd96..a1a8d45 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -7,6 +7,7 @@
struct netns_nftables {
struct list_head tables;
struct list_head commit_list;
+ struct list_head module_list;
struct mutex commit_mutex;
unsigned int base_seq;
u8 gencursor;
diff --git a/include/net/pie.h b/include/net/pie.h
new file mode 100644
index 0000000..fd5a37c
--- /dev/null
+++ b/include/net/pie.h
@@ -0,0 +1,138 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __NET_SCHED_PIE_H
+#define __NET_SCHED_PIE_H
+
+#include <linux/ktime.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <net/inet_ecn.h>
+#include <net/pkt_sched.h>
+
+#define MAX_PROB U64_MAX
+#define DTIME_INVALID U64_MAX
+#define QUEUE_THRESHOLD 16384
+#define DQCOUNT_INVALID -1
+#define PIE_SCALE 8
+
+/**
+ * struct pie_params - contains pie parameters
+ * @target: target delay in pschedtime
+ * @tudpate: interval at which drop probability is calculated
+ * @limit: total number of packets that can be in the queue
+ * @alpha: parameter to control drop probability
+ * @beta: parameter to control drop probability
+ * @ecn: is ECN marking of packets enabled
+ * @bytemode: is drop probability scaled based on pkt size
+ * @dq_rate_estimator: is Little's law used for qdelay calculation
+ */
+struct pie_params {
+ psched_time_t target;
+ u32 tupdate;
+ u32 limit;
+ u32 alpha;
+ u32 beta;
+ u8 ecn;
+ u8 bytemode;
+ u8 dq_rate_estimator;
+};
+
+/**
+ * struct pie_vars - contains pie variables
+ * @qdelay: current queue delay
+ * @qdelay_old: queue delay in previous qdelay calculation
+ * @burst_time: burst time allowance
+ * @dq_tstamp: timestamp at which dq rate was last calculated
+ * @prob: drop probability
+ * @accu_prob: accumulated drop probability
+ * @dq_count: number of bytes dequeued in a measurement cycle
+ * @avg_dq_rate: calculated average dq rate
+ * @qlen_old: queue length during previous qdelay calculation
+ * @accu_prob_overflows: number of times accu_prob overflows
+ */
+struct pie_vars {
+ psched_time_t qdelay;
+ psched_time_t qdelay_old;
+ psched_time_t burst_time;
+ psched_time_t dq_tstamp;
+ u64 prob;
+ u64 accu_prob;
+ u64 dq_count;
+ u32 avg_dq_rate;
+ u32 qlen_old;
+ u8 accu_prob_overflows;
+};
+
+/**
+ * struct pie_stats - contains pie stats
+ * @packets_in: total number of packets enqueued
+ * @dropped: packets dropped due to pie action
+ * @overlimit: packets dropped due to lack of space in queue
+ * @ecn_mark: packets marked with ECN
+ * @maxq: maximum queue size
+ */
+struct pie_stats {
+ u32 packets_in;
+ u32 dropped;
+ u32 overlimit;
+ u32 ecn_mark;
+ u32 maxq;
+};
+
+/**
+ * struct pie_skb_cb - contains private skb vars
+ * @enqueue_time: timestamp when the packet is enqueued
+ * @mem_usage: size of the skb during enqueue
+ */
+struct pie_skb_cb {
+ psched_time_t enqueue_time;
+ u32 mem_usage;
+};
+
+static inline void pie_params_init(struct pie_params *params)
+{
+ params->target = PSCHED_NS2TICKS(15 * NSEC_PER_MSEC); /* 15 ms */
+ params->tupdate = usecs_to_jiffies(15 * USEC_PER_MSEC); /* 15 ms */
+ params->limit = 1000;
+ params->alpha = 2;
+ params->beta = 20;
+ params->ecn = false;
+ params->bytemode = false;
+ params->dq_rate_estimator = false;
+}
+
+static inline void pie_vars_init(struct pie_vars *vars)
+{
+ vars->burst_time = PSCHED_NS2TICKS(150 * NSEC_PER_MSEC); /* 150 ms */
+ vars->dq_tstamp = DTIME_INVALID;
+ vars->accu_prob = 0;
+ vars->dq_count = DQCOUNT_INVALID;
+ vars->avg_dq_rate = 0;
+ vars->accu_prob_overflows = 0;
+}
+
+static inline struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb)
+{
+ qdisc_cb_private_validate(skb, sizeof(struct pie_skb_cb));
+ return (struct pie_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+static inline psched_time_t pie_get_enqueue_time(const struct sk_buff *skb)
+{
+ return get_pie_cb(skb)->enqueue_time;
+}
+
+static inline void pie_set_enqueue_time(struct sk_buff *skb)
+{
+ get_pie_cb(skb)->enqueue_time = psched_get_time();
+}
+
+bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
+ struct pie_vars *vars, u32 qlen, u32 packet_size);
+
+void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params,
+ struct pie_vars *vars, u32 qlen);
+
+void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
+ u32 qlen);
+
+#endif
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 47b115e..a972244 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -141,31 +141,38 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
return xchg(clp, cl);
}
-static inline unsigned long
-cls_set_class(struct Qdisc *q, unsigned long *clp, unsigned long cl)
+static inline void
+__tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base)
{
- unsigned long old_cl;
+ unsigned long cl;
- sch_tree_lock(q);
- old_cl = __cls_set_class(clp, cl);
- sch_tree_unlock(q);
- return old_cl;
+ cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
+ cl = __cls_set_class(&r->class, cl);
+ if (cl)
+ q->ops->cl_ops->unbind_tcf(q, cl);
}
static inline void
tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base)
{
struct Qdisc *q = tp->chain->block->q;
- unsigned long cl;
/* Check q as it is not set for shared blocks. In that case,
* setting class is not supported.
*/
if (!q)
return;
- cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
- cl = cls_set_class(q, &r->class, cl);
- if (cl)
+ sch_tree_lock(q);
+ __tcf_bind_filter(q, r, base);
+ sch_tree_unlock(q);
+}
+
+static inline void
+__tcf_unbind_filter(struct Qdisc *q, struct tcf_result *r)
+{
+ unsigned long cl;
+
+ if ((cl = __cls_set_class(&r->class, 0)) != 0)
q->ops->cl_ops->unbind_tcf(q, cl);
}
@@ -173,12 +180,10 @@ static inline void
tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r)
{
struct Qdisc *q = tp->chain->block->q;
- unsigned long cl;
if (!q)
return;
- if ((cl = __cls_set_class(&r->class, 0)) != 0)
- q->ops->cl_ops->unbind_tcf(q, cl);
+ __tcf_unbind_filter(q, r);
}
struct tcf_exts {
@@ -854,4 +859,26 @@ struct tc_ets_qopt_offload {
};
};
+enum tc_tbf_command {
+ TC_TBF_REPLACE,
+ TC_TBF_DESTROY,
+ TC_TBF_STATS,
+};
+
+struct tc_tbf_qopt_offload_replace_params {
+ struct psched_ratecfg rate;
+ u32 max_size;
+ struct gnet_stats_queue *qstats;
+};
+
+struct tc_tbf_qopt_offload {
+ enum tc_tbf_command command;
+ u32 handle;
+ u32 parent;
+ union {
+ struct tc_tbf_qopt_offload_replace_params replace_params;
+ struct tc_qopt_offload_stats stats;
+ };
+};
+
#endif
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index fceddf8..1512087 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -318,7 +318,8 @@ struct tcf_proto_ops {
void *type_data);
void (*hw_del)(struct tcf_proto *tp,
void *type_data);
- void (*bind_class)(void *, u32, unsigned long);
+ void (*bind_class)(void *, u32, unsigned long,
+ void *, unsigned long);
void * (*tmplt_create)(struct net *net,
struct tcf_chain *chain,
struct nlattr **tca,
diff --git a/include/net/sock.h b/include/net/sock.h
index 8dff68b..02162b0 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -436,31 +436,15 @@ struct sock {
* Because of non atomicity rules, all
* changes are protected by socket lock.
*/
- unsigned int __sk_flags_offset[0];
-#ifdef __BIG_ENDIAN_BITFIELD
-#define SK_FL_PROTO_SHIFT 16
-#define SK_FL_PROTO_MASK 0x00ff0000
-
-#define SK_FL_TYPE_SHIFT 0
-#define SK_FL_TYPE_MASK 0x0000ffff
-#else
-#define SK_FL_PROTO_SHIFT 8
-#define SK_FL_PROTO_MASK 0x0000ff00
-
-#define SK_FL_TYPE_SHIFT 16
-#define SK_FL_TYPE_MASK 0xffff0000
-#endif
-
- unsigned int sk_padding : 1,
+ u8 sk_padding : 1,
sk_kern_sock : 1,
sk_no_check_tx : 1,
sk_no_check_rx : 1,
- sk_userlocks : 4,
- sk_protocol : 8,
- sk_type : 16;
-#define SK_PROTOCOL_MAX U8_MAX
- u16 sk_gso_max_segs;
+ sk_userlocks : 4;
u8 sk_pacing_shift;
+ u16 sk_type;
+ u16 sk_protocol;
+ u16 sk_gso_max_segs;
unsigned long sk_lingertime;
struct proto *sk_prot_creator;
rwlock_t sk_callback_lock;
@@ -1480,6 +1464,7 @@ static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
sk_mem_uncharge(sk, skb->truesize);
if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
!sk->sk_tx_skb_cache && !skb_cloned(skb)) {
+ skb_ext_reset(skb);
skb_zcopy_clear(skb, true);
sk->sk_tx_skb_cache = skb;
return;
@@ -2612,4 +2597,6 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)
return false;
}
+void sock_def_readable(struct sock *sk);
+
#endif /* _SOCK_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7df37e2..a5ea27d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -39,6 +39,7 @@
#include <net/tcp_states.h>
#include <net/inet_ecn.h>
#include <net/dst.h>
+#include <net/mptcp.h>
#include <linux/seq_file.h>
#include <linux/memcontrol.h>
@@ -182,6 +183,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOPT_SACK 5 /* SACK Block */
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
+#define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */
#define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */
#define TCPOPT_EXP 254 /* Experimental */
/* Magic number to be after the option value for sharing TCP
@@ -328,6 +330,9 @@ int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
size_t size, int flags);
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
size_t size, int flags);
+int tcp_send_mss(struct sock *sk, int *size_goal, int flags);
+void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle,
+ int size_goal);
void tcp_release_cb(struct sock *sk);
void tcp_wfree(struct sk_buff *skb);
void tcp_write_timer_handler(struct sock *sk);
@@ -977,6 +982,13 @@ static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb)
return likely(!TCP_SKB_CB(skb)->eor);
}
+static inline bool tcp_skb_can_collapse(const struct sk_buff *to,
+ const struct sk_buff *from)
+{
+ return likely(tcp_skb_can_collapse_to(to) &&
+ mptcp_skb_can_collapse(to, from));
+}
+
/* Events passed to congestion control interface */
enum tcp_ca_event {
CA_EVENT_TX_START, /* first transmit when no packets in flight */
@@ -1007,6 +1019,7 @@ enum tcp_ca_ack_event_flags {
#define TCP_CONG_NON_RESTRICTED 0x1
/* Requires ECN/ECT set on all packets */
#define TCP_CONG_NEEDS_ECN 0x2
+#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN)
union tcp_cc_info;
@@ -1101,6 +1114,7 @@ u32 tcp_reno_undo_cwnd(struct sock *sk);
void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
extern struct tcp_congestion_ops tcp_reno;
+struct tcp_congestion_ops *tcp_ca_find(const char *name);
struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca);
#ifdef CONFIG_INET
@@ -2002,6 +2016,11 @@ struct tcp_request_sock_ops {
enum tcp_synack_type synack_type);
};
+extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops;
+#if IS_ENABLED(CONFIG_IPV6)
+extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops;
+#endif
+
#ifdef CONFIG_SYN_COOKIES
static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
const struct sock *sk, struct sk_buff *skb,
@@ -2147,12 +2166,16 @@ struct tcp_ulp_ops {
/* initialize ulp */
int (*init)(struct sock *sk);
/* update ulp */
- void (*update)(struct sock *sk, struct proto *p);
+ void (*update)(struct sock *sk, struct proto *p,
+ void (*write_space)(struct sock *sk));
/* cleanup ulp */
void (*release)(struct sock *sk);
/* diagnostic */
int (*get_info)(const struct sock *sk, struct sk_buff *skb);
size_t (*get_info_size)(const struct sock *sk);
+ /* clone ulp */
+ void (*clone)(const struct request_sock *req, struct sock *newsk,
+ const gfp_t priority);
char name[TCP_ULP_NAME_MAX];
struct module *owner;
@@ -2162,7 +2185,8 @@ void tcp_unregister_ulp(struct tcp_ulp_ops *type);
int tcp_set_ulp(struct sock *sk, const char *name);
void tcp_get_available_ulp(char *buf, size_t len);
void tcp_cleanup_ulp(struct sock *sk);
-void tcp_update_ulp(struct sock *sk, struct proto *p);
+void tcp_update_ulp(struct sock *sk, struct proto *p,
+ void (*write_space)(struct sock *sk));
#define MODULE_ALIAS_TCP_ULP(name) \
__MODULE_INFO(alias, alias_userspace, name); \
diff --git a/include/net/udp.h b/include/net/udp.h
index bad74f7..44e0e52 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -167,7 +167,7 @@ typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport,
__be16 dport);
struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
- struct udphdr *uh, udp_lookup_t lookup);
+ struct udphdr *uh, struct sock *sk);
int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index dda3c02..8f71c11 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -193,6 +193,7 @@ struct xfrm_state {
/* Data for encapsulator */
struct xfrm_encap_tmpl *encap;
+ struct sock __rcu *encap_sk;
/* Data for care-of address */
xfrm_address_t *coaddr;
@@ -1547,6 +1548,9 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload);
int xfrm_init_state(struct xfrm_state *x);
int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);
int xfrm_input_resume(struct sk_buff *skb, int nexthdr);
+int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
+ int (*finish)(struct net *, struct sock *,
+ struct sk_buff *));
int xfrm_trans_queue(struct sk_buff *skb,
int (*finish)(struct net *, struct sock *,
struct sk_buff *));
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 753f54e..e3518fd 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -69,7 +69,7 @@ static inline size_t ib_umem_num_pages(struct ib_umem *umem)
#ifdef CONFIG_INFINIBAND_USER_MEM
-struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
+struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
size_t size, int access);
void ib_umem_release(struct ib_umem *umem);
int ib_umem_page_count(struct ib_umem *umem);
@@ -83,7 +83,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
#include <linux/err.h>
-static inline struct ib_umem *ib_umem_get(struct ib_udata *udata,
+static inline struct ib_umem *ib_umem_get(struct ib_device *device,
unsigned long addr, size_t size,
int access)
{
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index 81429ac..64314ff 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -114,9 +114,9 @@ static inline size_t ib_umem_odp_num_pages(struct ib_umem_odp *umem_odp)
#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
struct ib_umem_odp *
-ib_umem_odp_get(struct ib_udata *udata, unsigned long addr, size_t size,
+ib_umem_odp_get(struct ib_device *device, unsigned long addr, size_t size,
int access, const struct mmu_interval_notifier_ops *ops);
-struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_udata *udata,
+struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_device *device,
int access);
struct ib_umem_odp *
ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem, unsigned long addr,
@@ -134,7 +134,7 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
static inline struct ib_umem_odp *
-ib_umem_odp_get(struct ib_udata *udata, unsigned long addr, size_t size,
+ib_umem_odp_get(struct ib_device *device, unsigned long addr, size_t size,
int access, const struct mmu_interval_notifier_ops *ops)
{
return ERR_PTR(-EINVAL);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 5608e14..e2cc622 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4153,6 +4153,15 @@ static inline void ib_dma_free_coherent(struct ib_device *dev,
dma_free_coherent(dev->dma_device, size, cpu_addr, dma_handle);
}
+/* ib_reg_user_mr - register a memory region for virtual addresses from kernel
+ * space. This function should be called when 'current' is the owning MM.
+ */
+struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
+ u64 virt_addr, int mr_access_flags);
+
+/* ib_advise_mr - give an advice about an address range in a memory region */
+int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
+ u32 flags, struct ib_sge *sg_list, u32 num_sge);
/**
* ib_dereg_mr_user - Deregisters a memory region and removes it from the
* HCA translation table.
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 64cbbbe..068f96b 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -420,6 +420,8 @@ struct ocelot_port {
u8 ptp_cmd;
struct sk_buff_head tx_skbs;
u8 ts_id;
+
+ phy_interface_t phy_mode;
};
struct ocelot {
diff --git a/drivers/net/ethernet/mscc/ocelot_ana.h b/include/soc/mscc/ocelot_ana.h
similarity index 100%
rename from drivers/net/ethernet/mscc/ocelot_ana.h
rename to include/soc/mscc/ocelot_ana.h
diff --git a/drivers/net/ethernet/mscc/ocelot_dev.h b/include/soc/mscc/ocelot_dev.h
similarity index 100%
rename from drivers/net/ethernet/mscc/ocelot_dev.h
rename to include/soc/mscc/ocelot_dev.h
diff --git a/drivers/net/ethernet/mscc/ocelot_qsys.h b/include/soc/mscc/ocelot_qsys.h
similarity index 100%
rename from drivers/net/ethernet/mscc/ocelot_qsys.h
rename to include/soc/mscc/ocelot_qsys.h
diff --git a/arch/riscv/include/asm/sifive_l2_cache.h b/include/soc/sifive/sifive_l2_cache.h
similarity index 72%
rename from arch/riscv/include/asm/sifive_l2_cache.h
rename to include/soc/sifive/sifive_l2_cache.h
index 04f6748..92ade10 100644
--- a/arch/riscv/include/asm/sifive_l2_cache.h
+++ b/include/soc/sifive/sifive_l2_cache.h
@@ -4,8 +4,8 @@
*
*/
-#ifndef _ASM_RISCV_SIFIVE_L2_CACHE_H
-#define _ASM_RISCV_SIFIVE_L2_CACHE_H
+#ifndef __SOC_SIFIVE_L2_CACHE_H
+#define __SOC_SIFIVE_L2_CACHE_H
extern int register_sifive_l2_error_notifier(struct notifier_block *nb);
extern int unregister_sifive_l2_error_notifier(struct notifier_block *nb);
@@ -13,4 +13,4 @@ extern int unregister_sifive_l2_error_notifier(struct notifier_block *nb);
#define SIFIVE_L2_ERR_TYPE_CE 0
#define SIFIVE_L2_ERR_TYPE_UE 1
-#endif /* _ASM_RISCV_SIFIVE_L2_CACHE_H */
+#endif /* __SOC_SIFIVE_L2_CACHE_H */
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index d5ec4fa..564ba1b 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -915,9 +915,9 @@ TRACE_EVENT(afs_call_state,
TRACE_EVENT(afs_lookup,
TP_PROTO(struct afs_vnode *dvnode, const struct qstr *name,
- struct afs_vnode *vnode),
+ struct afs_fid *fid),
- TP_ARGS(dvnode, name, vnode),
+ TP_ARGS(dvnode, name, fid),
TP_STRUCT__entry(
__field_struct(struct afs_fid, dfid )
@@ -928,13 +928,7 @@ TRACE_EVENT(afs_lookup,
TP_fast_assign(
int __len = min_t(int, name->len, 23);
__entry->dfid = dvnode->fid;
- if (vnode) {
- __entry->fid = vnode->fid;
- } else {
- __entry->fid.vid = 0;
- __entry->fid.vnode = 0;
- __entry->fid.unique = 0;
- }
+ __entry->fid = *fid;
memcpy(__entry->name, name->name, __len);
__entry->name[__len] = 0;
),
diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index dd4db33..d82a0f4 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -31,7 +31,8 @@
EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \
EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \
EM( SCAN_EXCEED_SWAP_PTE, "exceed_swap_pte") \
- EMe(SCAN_TRUNCATED, "truncated") \
+ EM( SCAN_TRUNCATED, "truncated") \
+ EMe(SCAN_PAGE_HAS_PRIVATE, "page_has_private") \
#undef EM
#undef EMe
diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h
index 95fba04..3f249e1 100644
--- a/include/trace/events/preemptirq.h
+++ b/include/trace/events/preemptirq.h
@@ -18,13 +18,13 @@ DECLARE_EVENT_CLASS(preemptirq_template,
TP_ARGS(ip, parent_ip),
TP_STRUCT__entry(
- __field(u32, caller_offs)
- __field(u32, parent_offs)
+ __field(s32, caller_offs)
+ __field(s32, parent_offs)
),
TP_fast_assign(
- __entry->caller_offs = (u32)(ip - (unsigned long)_stext);
- __entry->parent_offs = (u32)(parent_ip - (unsigned long)_stext);
+ __entry->caller_offs = (s32)(ip - (unsigned long)_stext);
+ __entry->parent_offs = (s32)(parent_ip - (unsigned long)_stext);
),
TP_printk("caller=%pS parent=%pS",
diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index 51fe9f6..a966d4b 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -19,7 +19,8 @@
#define inet_protocol_names \
EM(IPPROTO_TCP) \
EM(IPPROTO_DCCP) \
- EMe(IPPROTO_SCTP)
+ EM(IPPROTO_SCTP) \
+ EMe(IPPROTO_MPTCP)
#define tcp_state_names \
EM(TCP_ESTABLISHED) \
@@ -147,7 +148,7 @@ TRACE_EVENT(inet_sock_set_state,
__field(__u16, sport)
__field(__u16, dport)
__field(__u16, family)
- __field(__u8, protocol)
+ __field(__u16, protocol)
__array(__u8, saddr, 4)
__array(__u8, daddr, 4)
__array(__u8, saddr_v6, 16)
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index a7378bc..b95d65e 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -79,14 +79,26 @@ TRACE_EVENT(xdp_bulk_tx,
__entry->sent, __entry->drops, __entry->err)
);
+#ifndef __DEVMAP_OBJ_TYPE
+#define __DEVMAP_OBJ_TYPE
+struct _bpf_dtab_netdev {
+ struct net_device *dev;
+};
+#endif /* __DEVMAP_OBJ_TYPE */
+
+#define devmap_ifindex(tgt, map) \
+ (((map->map_type == BPF_MAP_TYPE_DEVMAP || \
+ map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)) ? \
+ ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex : 0)
+
DECLARE_EVENT_CLASS(xdp_redirect_template,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
- int to_ifindex, int err,
- const struct bpf_map *map, u32 map_index),
+ const void *tgt, int err,
+ const struct bpf_map *map, u32 index),
- TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
+ TP_ARGS(dev, xdp, tgt, err, map, index),
TP_STRUCT__entry(
__field(int, prog_id)
@@ -103,90 +115,65 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
__entry->act = XDP_REDIRECT;
__entry->ifindex = dev->ifindex;
__entry->err = err;
- __entry->to_ifindex = to_ifindex;
+ __entry->to_ifindex = map ? devmap_ifindex(tgt, map) :
+ index;
__entry->map_id = map ? map->id : 0;
- __entry->map_index = map_index;
+ __entry->map_index = map ? index : 0;
),
- TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d",
+ TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
+ " map_id=%d map_index=%d",
__entry->prog_id,
__print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
__entry->ifindex, __entry->to_ifindex,
- __entry->err)
+ __entry->err, __entry->map_id, __entry->map_index)
);
DEFINE_EVENT(xdp_redirect_template, xdp_redirect,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
- int to_ifindex, int err,
- const struct bpf_map *map, u32 map_index),
- TP_ARGS(dev, xdp, to_ifindex, err, map, map_index)
+ const void *tgt, int err,
+ const struct bpf_map *map, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map, index)
);
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
- int to_ifindex, int err,
- const struct bpf_map *map, u32 map_index),
- TP_ARGS(dev, xdp, to_ifindex, err, map, map_index)
+ const void *tgt, int err,
+ const struct bpf_map *map, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map, index)
);
#define _trace_xdp_redirect(dev, xdp, to) \
- trace_xdp_redirect(dev, xdp, to, 0, NULL, 0);
+ trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to);
#define _trace_xdp_redirect_err(dev, xdp, to, err) \
- trace_xdp_redirect_err(dev, xdp, to, err, NULL, 0);
+ trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, to);
-DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map,
+#define _trace_xdp_redirect_map(dev, xdp, to, map, index) \
+ trace_xdp_redirect(dev, xdp, to, 0, map, index);
+
+#define _trace_xdp_redirect_map_err(dev, xdp, to, map, index, err) \
+ trace_xdp_redirect_err(dev, xdp, to, err, map, index);
+
+/* not used anymore, but kept around so as not to break old programs */
+DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
- int to_ifindex, int err,
- const struct bpf_map *map, u32 map_index),
- TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
- TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
- " map_id=%d map_index=%d",
- __entry->prog_id,
- __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
- __entry->ifindex, __entry->to_ifindex,
- __entry->err,
- __entry->map_id, __entry->map_index)
+ const void *tgt, int err,
+ const struct bpf_map *map, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map, index)
);
-DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
+DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
- int to_ifindex, int err,
- const struct bpf_map *map, u32 map_index),
- TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
- TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
- " map_id=%d map_index=%d",
- __entry->prog_id,
- __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
- __entry->ifindex, __entry->to_ifindex,
- __entry->err,
- __entry->map_id, __entry->map_index)
+ const void *tgt, int err,
+ const struct bpf_map *map, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map, index)
);
-#ifndef __DEVMAP_OBJ_TYPE
-#define __DEVMAP_OBJ_TYPE
-struct _bpf_dtab_netdev {
- struct net_device *dev;
-};
-#endif /* __DEVMAP_OBJ_TYPE */
-
-#define devmap_ifindex(fwd, map) \
- ((map->map_type == BPF_MAP_TYPE_DEVMAP || \
- map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) ? \
- ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0)
-
-#define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \
- trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \
- 0, map, idx)
-
-#define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err) \
- trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \
- err, map, idx)
-
TRACE_EVENT(xdp_cpumap_kthread,
TP_PROTO(int map_id, unsigned int processed, unsigned int drops,
@@ -259,43 +246,38 @@ TRACE_EVENT(xdp_cpumap_enqueue,
TRACE_EVENT(xdp_devmap_xmit,
- TP_PROTO(const struct bpf_map *map, u32 map_index,
- int sent, int drops,
- const struct net_device *from_dev,
- const struct net_device *to_dev, int err),
+ TP_PROTO(const struct net_device *from_dev,
+ const struct net_device *to_dev,
+ int sent, int drops, int err),
- TP_ARGS(map, map_index, sent, drops, from_dev, to_dev, err),
+ TP_ARGS(from_dev, to_dev, sent, drops, err),
TP_STRUCT__entry(
- __field(int, map_id)
+ __field(int, from_ifindex)
__field(u32, act)
- __field(u32, map_index)
+ __field(int, to_ifindex)
__field(int, drops)
__field(int, sent)
- __field(int, from_ifindex)
- __field(int, to_ifindex)
__field(int, err)
),
TP_fast_assign(
- __entry->map_id = map->id;
+ __entry->from_ifindex = from_dev->ifindex;
__entry->act = XDP_REDIRECT;
- __entry->map_index = map_index;
+ __entry->to_ifindex = to_dev->ifindex;
__entry->drops = drops;
__entry->sent = sent;
- __entry->from_ifindex = from_dev->ifindex;
- __entry->to_ifindex = to_dev->ifindex;
__entry->err = err;
),
TP_printk("ndo_xdp_xmit"
- " map_id=%d map_index=%d action=%s"
+ " from_ifindex=%d to_ifindex=%d action=%s"
" sent=%d drops=%d"
- " from_ifindex=%d to_ifindex=%d err=%d",
- __entry->map_id, __entry->map_index,
+ " err=%d",
+ __entry->from_ifindex, __entry->to_ifindex,
__print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
__entry->sent, __entry->drops,
- __entry->from_ifindex, __entry->to_ifindex, __entry->err)
+ __entry->err)
);
/* Expect users already include <net/xdp.h>, but not xdp_priv.h */
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index 9a0e8af..a5ccfa67 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -66,7 +66,11 @@ TRACE_EVENT(xen_mc_callback,
TP_PROTO(xen_mc_callback_fn_t fn, void *data),
TP_ARGS(fn, data),
TP_STRUCT__entry(
- __field(xen_mc_callback_fn_t, fn)
+ /*
+ * Use field_struct to avoid is_signed_type()
+ * comparison of a function pointer.
+ */
+ __field_struct(xen_mc_callback_fn_t, fn)
__field(void *, data)
),
TP_fast_assign(
diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h
index 2a15f01..0ae34c8 100644
--- a/include/uapi/linux/batadv_packet.h
+++ b/include/uapi/linux/batadv_packet.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index 67f4636..617c180 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: MIT */
-/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors:
*
* Matthias Schiffer
*/
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7df436d..f1d74a2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -107,6 +107,10 @@ enum bpf_cmd {
BPF_MAP_LOOKUP_AND_DELETE_ELEM,
BPF_MAP_FREEZE,
BPF_BTF_GET_NEXT_ID,
+ BPF_MAP_LOOKUP_BATCH,
+ BPF_MAP_LOOKUP_AND_DELETE_BATCH,
+ BPF_MAP_UPDATE_BATCH,
+ BPF_MAP_DELETE_BATCH,
};
enum bpf_map_type {
@@ -136,6 +140,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_STACK,
BPF_MAP_TYPE_SK_STORAGE,
BPF_MAP_TYPE_DEVMAP_HASH,
+ BPF_MAP_TYPE_STRUCT_OPS,
};
/* Note that tracing related programs such as
@@ -174,6 +179,8 @@ enum bpf_prog_type {
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
BPF_PROG_TYPE_CGROUP_SOCKOPT,
BPF_PROG_TYPE_TRACING,
+ BPF_PROG_TYPE_STRUCT_OPS,
+ BPF_PROG_TYPE_EXT,
};
enum bpf_attach_type {
@@ -357,7 +364,12 @@ enum bpf_attach_type {
/* Enable memory-mapping BPF map */
#define BPF_F_MMAPABLE (1U << 10)
-/* flags for BPF_PROG_QUERY */
+/* Flags for BPF_PROG_QUERY. */
+
+/* Query effective (directly attached + inherited from ancestor cgroups)
+ * programs that will be executed for events within a cgroup.
+ * attach_flags with this flag are returned only for directly attached programs.
+ */
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
enum bpf_stack_build_id_status {
@@ -397,6 +409,10 @@ union bpf_attr {
__u32 btf_fd; /* fd pointing to a BTF type data */
__u32 btf_key_type_id; /* BTF type_id of the key */
__u32 btf_value_type_id; /* BTF type_id of the value */
+ __u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel-
+ * struct stored as the
+ * map value
+ */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -409,6 +425,23 @@ union bpf_attr {
__u64 flags;
};
+ struct { /* struct used by BPF_MAP_*_BATCH commands */
+ __aligned_u64 in_batch; /* start batch,
+ * NULL to start from beginning
+ */
+ __aligned_u64 out_batch; /* output: next start batch */
+ __aligned_u64 keys;
+ __aligned_u64 values;
+ __u32 count; /* input/output:
+ * input: # of key/value
+ * elements
+ * output: # of filled elements
+ */
+ __u32 map_fd;
+ __u64 elem_flags;
+ __u64 flags;
+ } batch;
+
struct { /* anonymous struct used by BPF_PROG_LOAD command */
__u32 prog_type; /* one of enum bpf_prog_type */
__u32 insn_cnt;
@@ -2703,7 +2736,8 @@ union bpf_attr {
*
* int bpf_send_signal(u32 sig)
* Description
- * Send signal *sig* to the current task.
+ * Send signal *sig* to the process of the current task.
+ * The signal may be delivered to any of this process's threads.
* Return
* 0 on success or successfully queued.
*
@@ -2831,6 +2865,33 @@ union bpf_attr {
* Return
* On success, the strictly positive length of the string, including
* the trailing NUL character. On error, a negative value.
+ *
+ * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
+ * Description
+ * Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
+ * *rcv_nxt* is the ack_seq to be sent out.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_send_signal_thread(u32 sig)
+ * Description
+ * Send signal *sig* to the thread corresponding to the current task.
+ * Return
+ * 0 on success or successfully queued.
+ *
+ * **-EBUSY** if work queue under nmi is full.
+ *
+ * **-EINVAL** if *sig* is invalid.
+ *
+ * **-EPERM** if no permission to send the *sig*.
+ *
+ * **-EAGAIN** if bpf program can try again.
+ *
+ * u64 bpf_jiffies64(void)
+ * Description
+ * Obtain the 64bit jiffies
+ * Return
+ * The 64 bit jiffies
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2948,7 +3009,10 @@ union bpf_attr {
FN(probe_read_user), \
FN(probe_read_kernel), \
FN(probe_read_user_str), \
- FN(probe_read_kernel_str),
+ FN(probe_read_kernel_str), \
+ FN(tcp_send_ack), \
+ FN(send_signal_thread), \
+ FN(jiffies64),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -3349,7 +3413,7 @@ struct bpf_map_info {
__u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
- __u32 :32;
+ __u32 btf_vmlinux_value_type_id;
__u64 netns_dev;
__u64 netns_ino;
__u32 btf_id;
diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index 1a2898c..5a66710 100644
--- a/include/uapi/linux/btf.h
+++ b/include/uapi/linux/btf.h
@@ -146,6 +146,12 @@ enum {
BTF_VAR_GLOBAL_EXTERN = 2,
};
+enum btf_func_linkage {
+ BTF_FUNC_STATIC = 0,
+ BTF_FUNC_GLOBAL = 1,
+ BTF_FUNC_EXTERN = 2,
+};
+
/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
* additional information related to the variable such as its linkage.
*/
diff --git a/include/uapi/linux/hdlc/ioctl.h b/include/uapi/linux/hdlc/ioctl.h
index 0fe4238..b06341a 100644
--- a/include/uapi/linux/hdlc/ioctl.h
+++ b/include/uapi/linux/hdlc/ioctl.h
@@ -79,6 +79,15 @@ typedef struct {
unsigned int timeout;
} cisco_proto;
+typedef struct {
+ unsigned short dce; /* 1 for DCE (network side) operation */
+ unsigned int modulo; /* modulo (8 = basic / 128 = extended) */
+ unsigned int window; /* frame window size */
+ unsigned int t1; /* timeout t1 */
+ unsigned int t2; /* timeout t2 */
+ unsigned int n2; /* frame retry counter */
+} x25_hdlc_proto;
+
/* PPP doesn't need any info now - supply length = 0 to ioctl */
#endif /* __ASSEMBLY__ */
diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h
index 4bf3334..be714cd 100644
--- a/include/uapi/linux/if.h
+++ b/include/uapi/linux/if.h
@@ -213,6 +213,7 @@ struct if_settings {
fr_proto __user *fr;
fr_proto_pvc __user *fr_pvc;
fr_proto_pvc_info __user *fr_pvc_info;
+ x25_hdlc_proto __user *x25;
/* interface settings */
sync_serial_settings __user *sync;
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 4a58e3d..42f7ca3 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -130,6 +130,7 @@ enum {
#define BRIDGE_VLAN_INFO_RANGE_BEGIN (1<<3) /* VLAN is start of vlan range */
#define BRIDGE_VLAN_INFO_RANGE_END (1<<4) /* VLAN is end of vlan range */
#define BRIDGE_VLAN_INFO_BRENTRY (1<<5) /* Global bridge VLAN entry */
+#define BRIDGE_VLAN_INFO_ONLY_OPTS (1<<6) /* Skip create/delete/flags */
struct bridge_vlan_info {
__u16 flags;
@@ -165,6 +166,36 @@ struct bridge_stp_xstats {
__u64 tx_tcn;
};
+/* Bridge vlan RTM header */
+struct br_vlan_msg {
+ __u8 family;
+ __u8 reserved1;
+ __u16 reserved2;
+ __u32 ifindex;
+};
+
+/* Bridge vlan RTM attributes
+ * [BRIDGE_VLANDB_ENTRY] = {
+ * [BRIDGE_VLANDB_ENTRY_INFO]
+ * ...
+ * }
+ */
+enum {
+ BRIDGE_VLANDB_UNSPEC,
+ BRIDGE_VLANDB_ENTRY,
+ __BRIDGE_VLANDB_MAX,
+};
+#define BRIDGE_VLANDB_MAX (__BRIDGE_VLANDB_MAX - 1)
+
+enum {
+ BRIDGE_VLANDB_ENTRY_UNSPEC,
+ BRIDGE_VLANDB_ENTRY_INFO,
+ BRIDGE_VLANDB_ENTRY_RANGE,
+ BRIDGE_VLANDB_ENTRY_STATE,
+ __BRIDGE_VLANDB_ENTRY_MAX,
+};
+#define BRIDGE_VLANDB_ENTRY_MAX (__BRIDGE_VLANDB_ENTRY_MAX - 1)
+
/* Bridge multicast database attributes
* [MDBA_MDB] = {
* [MDBA_MDB_ENTRY] = {
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 1d69f63..024af2d1 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -486,6 +486,13 @@ enum macsec_validation_type {
MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1,
};
+enum macsec_offload {
+ MACSEC_OFFLOAD_OFF = 0,
+ MACSEC_OFFLOAD_PHY = 1,
+ __MACSEC_OFFLOAD_END,
+ MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_END - 1,
+};
+
/* IPVLAN section */
enum {
IFLA_IPVLAN_UNSPEC,
diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h
index 98e4d5d..1d63c43 100644
--- a/include/uapi/linux/if_macsec.h
+++ b/include/uapi/linux/if_macsec.h
@@ -45,6 +45,7 @@ enum macsec_attrs {
MACSEC_ATTR_RXSC_LIST, /* dump, nested, macsec_rxsc_attrs for each RXSC */
MACSEC_ATTR_TXSC_STATS, /* dump, nested, macsec_txsc_stats_attr */
MACSEC_ATTR_SECY_STATS, /* dump, nested, macsec_secy_stats_attr */
+ MACSEC_ATTR_OFFLOAD, /* config, nested, macsec_offload_attrs */
__MACSEC_ATTR_END,
NUM_MACSEC_ATTR = __MACSEC_ATTR_END,
MACSEC_ATTR_MAX = __MACSEC_ATTR_END - 1,
@@ -97,6 +98,15 @@ enum macsec_sa_attrs {
MACSEC_SA_ATTR_MAX = __MACSEC_SA_ATTR_END - 1,
};
+enum macsec_offload_attrs {
+ MACSEC_OFFLOAD_ATTR_UNSPEC,
+ MACSEC_OFFLOAD_ATTR_TYPE, /* config/dump, u8 0..2 */
+ MACSEC_OFFLOAD_ATTR_PAD,
+ __MACSEC_OFFLOAD_ATTR_END,
+ NUM_MACSEC_OFFLOAD_ATTR = __MACSEC_OFFLOAD_ATTR_END,
+ MACSEC_OFFLOAD_ATTR_MAX = __MACSEC_OFFLOAD_ATTR_END - 1,
+};
+
enum macsec_nl_commands {
MACSEC_CMD_GET_TXSC,
MACSEC_CMD_ADD_RXSC,
@@ -108,6 +118,7 @@ enum macsec_nl_commands {
MACSEC_CMD_ADD_RXSA,
MACSEC_CMD_DEL_RXSA,
MACSEC_CMD_UPD_RXSA,
+ MACSEC_CMD_UPD_OFFLOAD,
};
/* u64 per-RXSC stats */
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index e7ad9d3..1521073 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -76,6 +76,8 @@ enum {
#define IPPROTO_MPLS IPPROTO_MPLS
IPPROTO_RAW = 255, /* Raw IP packets */
#define IPPROTO_RAW IPPROTO_RAW
+ IPPROTO_MPTCP = 262, /* Multipath TCP connection */
+#define IPPROTO_MPTCP IPPROTO_MPTCP
IPPROTO_MAX
};
#endif
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index f056b2a..9a61c28 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -34,6 +34,7 @@ struct input_event {
__kernel_ulong_t __sec;
#if defined(__sparc__) && defined(__arch64__)
unsigned int __usec;
+ unsigned int __pad;
#else
__kernel_ulong_t __usec;
#endif
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index a3300e1..55cfcb7 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -178,7 +178,8 @@ struct io_uring_params {
struct io_uring_files_update {
__u32 offset;
- __s32 *fds;
+ __u32 resv;
+ __aligned_u64 /* __s32 * */ fds;
};
#endif
diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h
index 409d3ad..1d0350e 100644
--- a/include/uapi/linux/kcov.h
+++ b/include/uapi/linux/kcov.h
@@ -9,11 +9,11 @@
* and the comment before kcov_remote_start() for usage details.
*/
struct kcov_remote_arg {
- unsigned int trace_mode; /* KCOV_TRACE_PC or KCOV_TRACE_CMP */
- unsigned int area_size; /* Length of coverage buffer in words */
- unsigned int num_handles; /* Size of handles array */
- __u64 common_handle;
- __u64 handles[0];
+ __u32 trace_mode; /* KCOV_TRACE_PC or KCOV_TRACE_CMP */
+ __u32 area_size; /* Length of coverage buffer in words */
+ __u32 num_handles; /* Size of handles array */
+ __aligned_u64 common_handle;
+ __aligned_u64 handles[0];
};
#define KCOV_REMOTE_MAX_HANDLES 0x100
diff --git a/include/uapi/linux/mii.h b/include/uapi/linux/mii.h
index 51b48e4..0b9c3be 100644
--- a/include/uapi/linux/mii.h
+++ b/include/uapi/linux/mii.h
@@ -131,6 +131,18 @@
#define NWAYTEST_LOOPBACK 0x0100 /* Enable loopback for N-way */
#define NWAYTEST_RESV2 0xfe00 /* Unused... */
+/* MAC and PHY tx_config_Reg[15:0] for SGMII in-band auto-negotiation.*/
+#define ADVERTISE_SGMII 0x0001 /* MAC can do SGMII */
+#define LPA_SGMII 0x0001 /* PHY can do SGMII */
+#define LPA_SGMII_DPX_SPD_MASK 0x1C00 /* SGMII duplex and speed bits */
+#define LPA_SGMII_10HALF 0x0000 /* Can do 10mbps half-duplex */
+#define LPA_SGMII_10FULL 0x1000 /* Can do 10mbps full-duplex */
+#define LPA_SGMII_100HALF 0x0400 /* Can do 100mbps half-duplex */
+#define LPA_SGMII_100FULL 0x1400 /* Can do 100mbps full-duplex */
+#define LPA_SGMII_1000HALF 0x0800 /* Can do 1000mbps half-duplex */
+#define LPA_SGMII_1000FULL 0x1800 /* Can do 1000mbps full-duplex */
+#define LPA_SGMII_LINK 0x8000 /* PHY link with copper-side partner */
+
/* 1000BASE-T Control register */
#define ADVERTISE_1000FULL 0x0200 /* Advertise 1000BASE-T full duplex */
#define ADVERTISE_1000HALF 0x0100 /* Advertise 1000BASE-T half duplex */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index e237ecb..065218a 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -48,6 +48,7 @@ enum nft_registers {
#define NFT_REG_SIZE 16
#define NFT_REG32_SIZE 4
+#define NFT_REG32_COUNT (NFT_REG32_15 - NFT_REG32_00 + 1)
/**
* enum nft_verdicts - nf_tables internal verdicts
@@ -301,15 +302,29 @@ enum nft_set_policies {
* enum nft_set_desc_attributes - set element description
*
* @NFTA_SET_DESC_SIZE: number of elements in set (NLA_U32)
+ * @NFTA_SET_DESC_CONCAT: description of field concatenation (NLA_NESTED)
*/
enum nft_set_desc_attributes {
NFTA_SET_DESC_UNSPEC,
NFTA_SET_DESC_SIZE,
+ NFTA_SET_DESC_CONCAT,
__NFTA_SET_DESC_MAX
};
#define NFTA_SET_DESC_MAX (__NFTA_SET_DESC_MAX - 1)
/**
+ * enum nft_set_field_attributes - attributes of concatenated fields
+ *
+ * @NFTA_SET_FIELD_LEN: length of single field, in bits (NLA_U32)
+ */
+enum nft_set_field_attributes {
+ NFTA_SET_FIELD_UNSPEC,
+ NFTA_SET_FIELD_LEN,
+ __NFTA_SET_FIELD_MAX
+};
+#define NFTA_SET_FIELD_MAX (__NFTA_SET_FIELD_MAX - 1)
+
+/**
* enum nft_set_attributes - nf_tables set netlink attributes
*
* @NFTA_SET_TABLE: table name (NLA_STRING)
@@ -370,6 +385,7 @@ enum nft_set_elem_flags {
* @NFTA_SET_ELEM_USERDATA: user data (NLA_BINARY)
* @NFTA_SET_ELEM_EXPR: expression (NLA_NESTED: nft_expr_attributes)
* @NFTA_SET_ELEM_OBJREF: stateful object reference (NLA_STRING)
+ * @NFTA_SET_ELEM_KEY_END: closing key value (NLA_NESTED: nft_data)
*/
enum nft_set_elem_attributes {
NFTA_SET_ELEM_UNSPEC,
@@ -382,6 +398,7 @@ enum nft_set_elem_attributes {
NFTA_SET_ELEM_EXPR,
NFTA_SET_ELEM_PAD,
NFTA_SET_ELEM_OBJREF,
+ NFTA_SET_ELEM_KEY_END,
__NFTA_SET_ELEM_MAX
};
#define NFTA_SET_ELEM_MAX (__NFTA_SET_ELEM_MAX - 1)
@@ -485,6 +502,20 @@ enum nft_immediate_attributes {
#define NFTA_IMMEDIATE_MAX (__NFTA_IMMEDIATE_MAX - 1)
/**
+ * enum nft_bitwise_ops - nf_tables bitwise operations
+ *
+ * @NFT_BITWISE_BOOL: mask-and-xor operation used to implement NOT, AND, OR and
+ * XOR boolean operations
+ * @NFT_BITWISE_LSHIFT: left-shift operation
+ * @NFT_BITWISE_RSHIFT: right-shift operation
+ */
+enum nft_bitwise_ops {
+ NFT_BITWISE_BOOL,
+ NFT_BITWISE_LSHIFT,
+ NFT_BITWISE_RSHIFT,
+};
+
+/**
* enum nft_bitwise_attributes - nf_tables bitwise expression netlink attributes
*
* @NFTA_BITWISE_SREG: source register (NLA_U32: nft_registers)
@@ -492,16 +523,20 @@ enum nft_immediate_attributes {
* @NFTA_BITWISE_LEN: length of operands (NLA_U32)
* @NFTA_BITWISE_MASK: mask value (NLA_NESTED: nft_data_attributes)
* @NFTA_BITWISE_XOR: xor value (NLA_NESTED: nft_data_attributes)
+ * @NFTA_BITWISE_OP: type of operation (NLA_U32: nft_bitwise_ops)
+ * @NFTA_BITWISE_DATA: argument for non-boolean operations
+ * (NLA_NESTED: nft_data_attributes)
*
- * The bitwise expression performs the following operation:
+ * The bitwise expression supports boolean and shift operations. It implements
+ * the boolean operations by performing the following operation:
*
* dreg = (sreg & mask) ^ xor
*
- * which allow to express all bitwise operations:
+ * with these mask and xor values:
*
* mask xor
* NOT: 1 1
- * OR: 0 x
+ * OR: ~x x
* XOR: 1 x
* AND: x 0
*/
@@ -512,6 +547,8 @@ enum nft_bitwise_attributes {
NFTA_BITWISE_LEN,
NFTA_BITWISE_MASK,
NFTA_BITWISE_XOR,
+ NFTA_BITWISE_OP,
+ NFTA_BITWISE_DATA,
__NFTA_BITWISE_MAX
};
#define NFTA_BITWISE_MAX (__NFTA_BITWISE_MAX - 1)
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index bf5a5b1..bbe791b 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -971,6 +971,37 @@ struct tc_pie_xstats {
__u32 ecn_mark; /* packets marked with ecn*/
};
+/* FQ PIE */
+enum {
+ TCA_FQ_PIE_UNSPEC,
+ TCA_FQ_PIE_LIMIT,
+ TCA_FQ_PIE_FLOWS,
+ TCA_FQ_PIE_TARGET,
+ TCA_FQ_PIE_TUPDATE,
+ TCA_FQ_PIE_ALPHA,
+ TCA_FQ_PIE_BETA,
+ TCA_FQ_PIE_QUANTUM,
+ TCA_FQ_PIE_MEMORY_LIMIT,
+ TCA_FQ_PIE_ECN_PROB,
+ TCA_FQ_PIE_ECN,
+ TCA_FQ_PIE_BYTEMODE,
+ TCA_FQ_PIE_DQ_RATE_ESTIMATOR,
+ __TCA_FQ_PIE_MAX
+};
+#define TCA_FQ_PIE_MAX (__TCA_FQ_PIE_MAX - 1)
+
+struct tc_fq_pie_xstats {
+ __u32 packets_in; /* total number of packets enqueued */
+ __u32 dropped; /* packets dropped due to fq_pie_action */
+ __u32 overlimit; /* dropped due to lack of space in queue */
+ __u32 overmemory; /* dropped due to lack of memory in queue */
+ __u32 ecn_mark; /* packets marked with ecn */
+ __u32 new_flow_count; /* count of new flows created by packets */
+ __u32 new_flows_len; /* count of flows in new list */
+ __u32 old_flows_len; /* count of flows in old list */
+ __u32 memory_usage; /* total memory across all queues */
+};
+
/* CBS */
struct tc_cbs_qopt {
__u8 offload;
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 1418a83..4a8c5b7 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -171,6 +171,13 @@ enum {
RTM_GETLINKPROP,
#define RTM_GETLINKPROP RTM_GETLINKPROP
+ RTM_NEWVLAN = 112,
+#define RTM_NEWNVLAN RTM_NEWVLAN
+ RTM_DELVLAN,
+#define RTM_DELVLAN RTM_DELVLAN
+ RTM_GETVLAN,
+#define RTM_GETVLAN RTM_GETVLAN
+
__RTM_MAX,
#define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1)
};
@@ -309,6 +316,8 @@ enum rt_scope_t {
#define RTM_F_PREFIX 0x800 /* Prefix addresses */
#define RTM_F_LOOKUP_TABLE 0x1000 /* set rtm_table to FIB lookup result */
#define RTM_F_FIB_MATCH 0x2000 /* return full fib lookup match */
+#define RTM_F_OFFLOAD 0x4000 /* route is offloaded */
+#define RTM_F_TRAP 0x8000 /* route is trapping packets */
/* Reserved table identifiers */
@@ -721,6 +730,8 @@ enum rtnetlink_groups {
#define RTNLGRP_IPV6_MROUTE_R RTNLGRP_IPV6_MROUTE_R
RTNLGRP_NEXTHOP,
#define RTNLGRP_NEXTHOP RTNLGRP_NEXTHOP
+ RTNLGRP_BRVLAN,
+#define RTNLGRP_BRVLAN RTNLGRP_BRVLAN
__RTNLGRP_MAX
};
#define RTNLGRP_MAX (__RTNLGRP_MAX - 1)
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 7eee233..7d91f4d 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -285,6 +285,8 @@ enum
LINUX_MIB_TCPRCVQDROP, /* TCPRcvQDrop */
LINUX_MIB_TCPWQUEUETOOBIG, /* TCPWqueueTooBig */
LINUX_MIB_TCPFASTOPENPASSIVEALTKEY, /* TCPFastOpenPassiveAltKey */
+ LINUX_MIB_TCPTIMEOUTREHASH, /* TCPTimeoutRehash */
+ LINUX_MIB_TCPDUPLICATEDATAREHASH, /* TCPDuplicateDataRehash */
__LINUX_MIB_MAX
};
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index d87184e..fd9eb8f 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -311,6 +311,7 @@ enum {
TCP_NLA_DSACK_DUPS, /* DSACK blocks received */
TCP_NLA_REORD_SEEN, /* reordering events seen */
TCP_NLA_SRTT, /* smoothed RTT in usecs */
+ TCP_NLA_TIMEOUT_REHASH, /* Timeout-triggered rehash attempts */
};
/* for TCP_MD5SIG socket option */
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index 30baccb..4828794 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -42,5 +42,6 @@ struct udphdr {
#define UDP_ENCAP_GTP0 4 /* GSM TS 09.60 */
#define UDP_ENCAP_GTP1U 5 /* 3GPP TS 29.060 */
#define UDP_ENCAP_RXRPC 6
+#define TCP_ENCAP_ESPINTCP 7 /* Yikes, this is really xfrm encap types. */
#endif /* _UAPI_LINUX_UDP_H */
diff --git a/init/main.c b/init/main.c
index 1ecfd43..da1bc0b 100644
--- a/init/main.c
+++ b/init/main.c
@@ -93,7 +93,6 @@
#include <linux/rodata_test.h>
#include <linux/jump_label.h>
#include <linux/mem_encrypt.h>
-#include <linux/file.h>
#include <asm/io.h>
#include <asm/bugs.h>
@@ -554,6 +553,7 @@ static void __init mm_init(void)
* bigger than MAX_ORDER unless SPARSEMEM.
*/
page_ext_init_flatmem();
+ init_debug_pagealloc();
report_meminit();
mem_init();
kmem_cache_init();
@@ -1158,26 +1158,13 @@ static int __ref kernel_init(void *unused)
void console_on_rootfs(void)
{
- struct file *file;
- unsigned int i;
+ /* Open the /dev/console as stdin, this should never fail */
+ if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
+ pr_err("Warning: unable to open an initial console.\n");
- /* Open /dev/console in kernelspace, this should never fail */
- file = filp_open("/dev/console", O_RDWR, 0);
- if (IS_ERR(file))
- goto err_out;
-
- /* create stdin/stdout/stderr, this should never fail */
- for (i = 0; i < 3; i++) {
- if (f_dupfd(i, file, 0) != i)
- goto err_out;
- }
-
- return;
-
-err_out:
- /* no panic -- this might not be fatal */
- pr_err("Warning: unable to open an initial console.\n");
- return;
+ /* create stdout/stderr */
+ (void) ksys_dup(0);
+ (void) ksys_dup(0);
}
static noinline void __init kernel_init_freeable(void)
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index d4f3303..046ce5d 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -27,3 +27,6 @@
ifeq ($(CONFIG_SYSFS),y)
obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
endif
+ifeq ($(CONFIG_BPF_JIT),y)
+obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
+endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index f0d19bb..95d7777 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -503,6 +503,8 @@ const struct bpf_map_ops array_map_ops = {
.map_mmap = array_map_mmap,
.map_seq_show_elem = array_map_seq_show_elem,
.map_check_btf = array_map_check_btf,
+ .map_lookup_batch = generic_map_lookup_batch,
+ .map_update_batch = generic_map_update_batch,
};
const struct bpf_map_ops percpu_array_map_ops = {
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
new file mode 100644
index 0000000..8ad1c9e
--- /dev/null
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -0,0 +1,634 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2019 Facebook */
+
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/btf.h>
+#include <linux/filter.h>
+#include <linux/slab.h>
+#include <linux/numa.h>
+#include <linux/seq_file.h>
+#include <linux/refcount.h>
+#include <linux/mutex.h>
+
+enum bpf_struct_ops_state {
+ BPF_STRUCT_OPS_STATE_INIT,
+ BPF_STRUCT_OPS_STATE_INUSE,
+ BPF_STRUCT_OPS_STATE_TOBEFREE,
+};
+
+#define BPF_STRUCT_OPS_COMMON_VALUE \
+ refcount_t refcnt; \
+ enum bpf_struct_ops_state state
+
+struct bpf_struct_ops_value {
+ BPF_STRUCT_OPS_COMMON_VALUE;
+ char data[0] ____cacheline_aligned_in_smp;
+};
+
+struct bpf_struct_ops_map {
+ struct bpf_map map;
+ const struct bpf_struct_ops *st_ops;
+ /* protect map_update */
+ struct mutex lock;
+ /* progs has all the bpf_prog that is populated
+ * to the func ptr of the kernel's struct
+ * (in kvalue.data).
+ */
+ struct bpf_prog **progs;
+ /* image is a page that has all the trampolines
+ * that stores the func args before calling the bpf_prog.
+ * A PAGE_SIZE "image" is enough to store all trampoline for
+ * "progs[]".
+ */
+ void *image;
+ /* uvalue->data stores the kernel struct
+ * (e.g. tcp_congestion_ops) that is more useful
+ * to userspace than the kvalue. For example,
+ * the bpf_prog's id is stored instead of the kernel
+ * address of a func ptr.
+ */
+ struct bpf_struct_ops_value *uvalue;
+ /* kvalue.data stores the actual kernel's struct
+ * (e.g. tcp_congestion_ops) that will be
+ * registered to the kernel subsystem.
+ */
+ struct bpf_struct_ops_value kvalue;
+};
+
+#define VALUE_PREFIX "bpf_struct_ops_"
+#define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1)
+
+/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is
+ * the map's value exposed to the userspace and its btf-type-id is
+ * stored at the map->btf_vmlinux_value_type_id.
+ *
+ */
+#define BPF_STRUCT_OPS_TYPE(_name) \
+extern struct bpf_struct_ops bpf_##_name; \
+ \
+struct bpf_struct_ops_##_name { \
+ BPF_STRUCT_OPS_COMMON_VALUE; \
+ struct _name data ____cacheline_aligned_in_smp; \
+};
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+
+enum {
+#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name,
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+ __NR_BPF_STRUCT_OPS_TYPE,
+};
+
+static struct bpf_struct_ops * const bpf_struct_ops[] = {
+#define BPF_STRUCT_OPS_TYPE(_name) \
+ [BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name,
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+};
+
+const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = {
+};
+
+const struct bpf_prog_ops bpf_struct_ops_prog_ops = {
+};
+
+static const struct btf_type *module_type;
+
+void bpf_struct_ops_init(struct btf *btf)
+{
+ s32 type_id, value_id, module_id;
+ const struct btf_member *member;
+ struct bpf_struct_ops *st_ops;
+ struct bpf_verifier_log log = {};
+ const struct btf_type *t;
+ char value_name[128];
+ const char *mname;
+ u32 i, j;
+
+ /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */
+#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name);
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+
+ module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT);
+ if (module_id < 0) {
+ pr_warn("Cannot find struct module in btf_vmlinux\n");
+ return;
+ }
+ module_type = btf_type_by_id(btf, module_id);
+
+ for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
+ st_ops = bpf_struct_ops[i];
+
+ if (strlen(st_ops->name) + VALUE_PREFIX_LEN >=
+ sizeof(value_name)) {
+ pr_warn("struct_ops name %s is too long\n",
+ st_ops->name);
+ continue;
+ }
+ sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name);
+
+ value_id = btf_find_by_name_kind(btf, value_name,
+ BTF_KIND_STRUCT);
+ if (value_id < 0) {
+ pr_warn("Cannot find struct %s in btf_vmlinux\n",
+ value_name);
+ continue;
+ }
+
+ type_id = btf_find_by_name_kind(btf, st_ops->name,
+ BTF_KIND_STRUCT);
+ if (type_id < 0) {
+ pr_warn("Cannot find struct %s in btf_vmlinux\n",
+ st_ops->name);
+ continue;
+ }
+ t = btf_type_by_id(btf, type_id);
+ if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) {
+ pr_warn("Cannot support #%u members in struct %s\n",
+ btf_type_vlen(t), st_ops->name);
+ continue;
+ }
+
+ for_each_member(j, t, member) {
+ const struct btf_type *func_proto;
+
+ mname = btf_name_by_offset(btf, member->name_off);
+ if (!*mname) {
+ pr_warn("anon member in struct %s is not supported\n",
+ st_ops->name);
+ break;
+ }
+
+ if (btf_member_bitfield_size(t, member)) {
+ pr_warn("bit field member %s in struct %s is not supported\n",
+ mname, st_ops->name);
+ break;
+ }
+
+ func_proto = btf_type_resolve_func_ptr(btf,
+ member->type,
+ NULL);
+ if (func_proto &&
+ btf_distill_func_proto(&log, btf,
+ func_proto, mname,
+ &st_ops->func_models[j])) {
+ pr_warn("Error in parsing func ptr %s in struct %s\n",
+ mname, st_ops->name);
+ break;
+ }
+ }
+
+ if (j == btf_type_vlen(t)) {
+ if (st_ops->init(btf)) {
+ pr_warn("Error in init bpf_struct_ops %s\n",
+ st_ops->name);
+ } else {
+ st_ops->type_id = type_id;
+ st_ops->type = t;
+ st_ops->value_id = value_id;
+ st_ops->value_type = btf_type_by_id(btf,
+ value_id);
+ }
+ }
+ }
+}
+
+extern struct btf *btf_vmlinux;
+
+static const struct bpf_struct_ops *
+bpf_struct_ops_find_value(u32 value_id)
+{
+ unsigned int i;
+
+ if (!value_id || !btf_vmlinux)
+ return NULL;
+
+ for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
+ if (bpf_struct_ops[i]->value_id == value_id)
+ return bpf_struct_ops[i];
+ }
+
+ return NULL;
+}
+
+const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
+{
+ unsigned int i;
+
+ if (!type_id || !btf_vmlinux)
+ return NULL;
+
+ for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
+ if (bpf_struct_ops[i]->type_id == type_id)
+ return bpf_struct_ops[i];
+ }
+
+ return NULL;
+}
+
+static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key,
+ void *next_key)
+{
+ if (key && *(u32 *)key == 0)
+ return -ENOENT;
+
+ *(u32 *)next_key = 0;
+ return 0;
+}
+
+int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
+ void *value)
+{
+ struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
+ struct bpf_struct_ops_value *uvalue, *kvalue;
+ enum bpf_struct_ops_state state;
+
+ if (unlikely(*(u32 *)key != 0))
+ return -ENOENT;
+
+ kvalue = &st_map->kvalue;
+ /* Pair with smp_store_release() during map_update */
+ state = smp_load_acquire(&kvalue->state);
+ if (state == BPF_STRUCT_OPS_STATE_INIT) {
+ memset(value, 0, map->value_size);
+ return 0;
+ }
+
+ /* No lock is needed. state and refcnt do not need
+ * to be updated together under atomic context.
+ */
+ uvalue = (struct bpf_struct_ops_value *)value;
+ memcpy(uvalue, st_map->uvalue, map->value_size);
+ uvalue->state = state;
+ refcount_set(&uvalue->refcnt, refcount_read(&kvalue->refcnt));
+
+ return 0;
+}
+
+static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ return ERR_PTR(-EINVAL);
+}
+
+static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map)
+{
+ const struct btf_type *t = st_map->st_ops->type;
+ u32 i;
+
+ for (i = 0; i < btf_type_vlen(t); i++) {
+ if (st_map->progs[i]) {
+ bpf_prog_put(st_map->progs[i]);
+ st_map->progs[i] = NULL;
+ }
+ }
+}
+
+static int check_zero_holes(const struct btf_type *t, void *data)
+{
+ const struct btf_member *member;
+ u32 i, moff, msize, prev_mend = 0;
+ const struct btf_type *mtype;
+
+ for_each_member(i, t, member) {
+ moff = btf_member_bit_offset(t, member) / 8;
+ if (moff > prev_mend &&
+ memchr_inv(data + prev_mend, 0, moff - prev_mend))
+ return -EINVAL;
+
+ mtype = btf_type_by_id(btf_vmlinux, member->type);
+ mtype = btf_resolve_size(btf_vmlinux, mtype, &msize,
+ NULL, NULL);
+ if (IS_ERR(mtype))
+ return PTR_ERR(mtype);
+ prev_mend = moff + msize;
+ }
+
+ if (t->size > prev_mend &&
+ memchr_inv(data + prev_mend, 0, t->size - prev_mend))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 flags)
+{
+ struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
+ const struct bpf_struct_ops *st_ops = st_map->st_ops;
+ struct bpf_struct_ops_value *uvalue, *kvalue;
+ const struct btf_member *member;
+ const struct btf_type *t = st_ops->type;
+ void *udata, *kdata;
+ int prog_fd, err = 0;
+ void *image;
+ u32 i;
+
+ if (flags)
+ return -EINVAL;
+
+ if (*(u32 *)key != 0)
+ return -E2BIG;
+
+ err = check_zero_holes(st_ops->value_type, value);
+ if (err)
+ return err;
+
+ uvalue = (struct bpf_struct_ops_value *)value;
+ err = check_zero_holes(t, uvalue->data);
+ if (err)
+ return err;
+
+ if (uvalue->state || refcount_read(&uvalue->refcnt))
+ return -EINVAL;
+
+ uvalue = (struct bpf_struct_ops_value *)st_map->uvalue;
+ kvalue = (struct bpf_struct_ops_value *)&st_map->kvalue;
+
+ mutex_lock(&st_map->lock);
+
+ if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) {
+ err = -EBUSY;
+ goto unlock;
+ }
+
+ memcpy(uvalue, value, map->value_size);
+
+ udata = &uvalue->data;
+ kdata = &kvalue->data;
+ image = st_map->image;
+
+ for_each_member(i, t, member) {
+ const struct btf_type *mtype, *ptype;
+ struct bpf_prog *prog;
+ u32 moff;
+
+ moff = btf_member_bit_offset(t, member) / 8;
+ ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL);
+ if (ptype == module_type) {
+ if (*(void **)(udata + moff))
+ goto reset_unlock;
+ *(void **)(kdata + moff) = BPF_MODULE_OWNER;
+ continue;
+ }
+
+ err = st_ops->init_member(t, member, kdata, udata);
+ if (err < 0)
+ goto reset_unlock;
+
+ /* The ->init_member() has handled this member */
+ if (err > 0)
+ continue;
+
+ /* If st_ops->init_member does not handle it,
+ * we will only handle func ptrs and zero-ed members
+ * here. Reject everything else.
+ */
+
+ /* All non func ptr member must be 0 */
+ if (!ptype || !btf_type_is_func_proto(ptype)) {
+ u32 msize;
+
+ mtype = btf_type_by_id(btf_vmlinux, member->type);
+ mtype = btf_resolve_size(btf_vmlinux, mtype, &msize,
+ NULL, NULL);
+ if (IS_ERR(mtype)) {
+ err = PTR_ERR(mtype);
+ goto reset_unlock;
+ }
+
+ if (memchr_inv(udata + moff, 0, msize)) {
+ err = -EINVAL;
+ goto reset_unlock;
+ }
+
+ continue;
+ }
+
+ prog_fd = (int)(*(unsigned long *)(udata + moff));
+ /* Similar check as the attr->attach_prog_fd */
+ if (!prog_fd)
+ continue;
+
+ prog = bpf_prog_get(prog_fd);
+ if (IS_ERR(prog)) {
+ err = PTR_ERR(prog);
+ goto reset_unlock;
+ }
+ st_map->progs[i] = prog;
+
+ if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
+ prog->aux->attach_btf_id != st_ops->type_id ||
+ prog->expected_attach_type != i) {
+ err = -EINVAL;
+ goto reset_unlock;
+ }
+
+ err = arch_prepare_bpf_trampoline(image,
+ st_map->image + PAGE_SIZE,
+ &st_ops->func_models[i], 0,
+ &prog, 1, NULL, 0, NULL);
+ if (err < 0)
+ goto reset_unlock;
+
+ *(void **)(kdata + moff) = image;
+ image += err;
+
+ /* put prog_id to udata */
+ *(unsigned long *)(udata + moff) = prog->aux->id;
+ }
+
+ refcount_set(&kvalue->refcnt, 1);
+ bpf_map_inc(map);
+
+ set_memory_ro((long)st_map->image, 1);
+ set_memory_x((long)st_map->image, 1);
+ err = st_ops->reg(kdata);
+ if (likely(!err)) {
+ /* Pair with smp_load_acquire() during lookup_elem().
+ * It ensures the above udata updates (e.g. prog->aux->id)
+ * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set.
+ */
+ smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE);
+ goto unlock;
+ }
+
+ /* Error during st_ops->reg(). It is very unlikely since
+ * the above init_member() should have caught it earlier
+ * before reg(). The only possibility is if there was a race
+ * in registering the struct_ops (under the same name) to
+ * a sub-system through different struct_ops's maps.
+ */
+ set_memory_nx((long)st_map->image, 1);
+ set_memory_rw((long)st_map->image, 1);
+ bpf_map_put(map);
+
+reset_unlock:
+ bpf_struct_ops_map_put_progs(st_map);
+ memset(uvalue, 0, map->value_size);
+ memset(kvalue, 0, map->value_size);
+unlock:
+ mutex_unlock(&st_map->lock);
+ return err;
+}
+
+static int bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key)
+{
+ enum bpf_struct_ops_state prev_state;
+ struct bpf_struct_ops_map *st_map;
+
+ st_map = (struct bpf_struct_ops_map *)map;
+ prev_state = cmpxchg(&st_map->kvalue.state,
+ BPF_STRUCT_OPS_STATE_INUSE,
+ BPF_STRUCT_OPS_STATE_TOBEFREE);
+ if (prev_state == BPF_STRUCT_OPS_STATE_INUSE) {
+ st_map->st_ops->unreg(&st_map->kvalue.data);
+ if (refcount_dec_and_test(&st_map->kvalue.refcnt))
+ bpf_map_put(map);
+ }
+
+ return 0;
+}
+
+static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key,
+ struct seq_file *m)
+{
+ void *value;
+ int err;
+
+ value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
+ if (!value)
+ return;
+
+ err = bpf_struct_ops_map_sys_lookup_elem(map, key, value);
+ if (!err) {
+ btf_type_seq_show(btf_vmlinux, map->btf_vmlinux_value_type_id,
+ value, m);
+ seq_puts(m, "\n");
+ }
+
+ kfree(value);
+}
+
+static void bpf_struct_ops_map_free(struct bpf_map *map)
+{
+ struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
+
+ if (st_map->progs)
+ bpf_struct_ops_map_put_progs(st_map);
+ bpf_map_area_free(st_map->progs);
+ bpf_jit_free_exec(st_map->image);
+ bpf_map_area_free(st_map->uvalue);
+ bpf_map_area_free(st_map);
+}
+
+static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr)
+{
+ if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 ||
+ attr->map_flags || !attr->btf_vmlinux_value_type_id)
+ return -EINVAL;
+ return 0;
+}
+
+static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
+{
+ const struct bpf_struct_ops *st_ops;
+ size_t map_total_size, st_map_size;
+ struct bpf_struct_ops_map *st_map;
+ const struct btf_type *t, *vt;
+ struct bpf_map_memory mem;
+ struct bpf_map *map;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id);
+ if (!st_ops)
+ return ERR_PTR(-ENOTSUPP);
+
+ vt = st_ops->value_type;
+ if (attr->value_size != vt->size)
+ return ERR_PTR(-EINVAL);
+
+ t = st_ops->type;
+
+ st_map_size = sizeof(*st_map) +
+ /* kvalue stores the
+ * struct bpf_struct_ops_tcp_congestions_ops
+ */
+ (vt->size - sizeof(struct bpf_struct_ops_value));
+ map_total_size = st_map_size +
+ /* uvalue */
+ sizeof(vt->size) +
+ /* struct bpf_progs **progs */
+ btf_type_vlen(t) * sizeof(struct bpf_prog *);
+ err = bpf_map_charge_init(&mem, map_total_size);
+ if (err < 0)
+ return ERR_PTR(err);
+
+ st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE);
+ if (!st_map) {
+ bpf_map_charge_finish(&mem);
+ return ERR_PTR(-ENOMEM);
+ }
+ st_map->st_ops = st_ops;
+ map = &st_map->map;
+
+ st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
+ st_map->progs =
+ bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_prog *),
+ NUMA_NO_NODE);
+ st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
+ if (!st_map->uvalue || !st_map->progs || !st_map->image) {
+ bpf_struct_ops_map_free(map);
+ bpf_map_charge_finish(&mem);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ mutex_init(&st_map->lock);
+ set_vm_flush_reset_perms(st_map->image);
+ bpf_map_init_from_attr(map, attr);
+ bpf_map_charge_move(&map->memory, &mem);
+
+ return map;
+}
+
+const struct bpf_map_ops bpf_struct_ops_map_ops = {
+ .map_alloc_check = bpf_struct_ops_map_alloc_check,
+ .map_alloc = bpf_struct_ops_map_alloc,
+ .map_free = bpf_struct_ops_map_free,
+ .map_get_next_key = bpf_struct_ops_map_get_next_key,
+ .map_lookup_elem = bpf_struct_ops_map_lookup_elem,
+ .map_delete_elem = bpf_struct_ops_map_delete_elem,
+ .map_update_elem = bpf_struct_ops_map_update_elem,
+ .map_seq_show_elem = bpf_struct_ops_map_seq_show_elem,
+};
+
+/* "const void *" because some subsystem is
+ * passing a const (e.g. const struct tcp_congestion_ops *)
+ */
+bool bpf_struct_ops_get(const void *kdata)
+{
+ struct bpf_struct_ops_value *kvalue;
+
+ kvalue = container_of(kdata, struct bpf_struct_ops_value, data);
+
+ return refcount_inc_not_zero(&kvalue->refcnt);
+}
+
+void bpf_struct_ops_put(const void *kdata)
+{
+ struct bpf_struct_ops_value *kvalue;
+
+ kvalue = container_of(kdata, struct bpf_struct_ops_value, data);
+ if (refcount_dec_and_test(&kvalue->refcnt)) {
+ struct bpf_struct_ops_map *st_map;
+
+ st_map = container_of(kvalue, struct bpf_struct_ops_map,
+ kvalue);
+ bpf_map_put(&st_map->map);
+ }
+}
diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h
new file mode 100644
index 0000000..066d83e
--- /dev/null
+++ b/kernel/bpf/bpf_struct_ops_types.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* internal file - do not include directly */
+
+#ifdef CONFIG_BPF_JIT
+#ifdef CONFIG_INET
+#include <net/tcp.h>
+BPF_STRUCT_OPS_TYPE(tcp_congestion_ops)
+#endif
+#endif
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index ed20758..32963b6 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -180,11 +180,6 @@
*/
#define BTF_MAX_SIZE (16 * 1024 * 1024)
-#define for_each_member(i, struct_type, member) \
- for (i = 0, member = btf_type_member(struct_type); \
- i < btf_type_vlen(struct_type); \
- i++, member++)
-
#define for_each_member_from(i, from, struct_type, member) \
for (i = from, member = btf_type_member(struct_type) + from; \
i < btf_type_vlen(struct_type); \
@@ -281,6 +276,11 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
[BTF_KIND_DATASEC] = "DATASEC",
};
+static const char *btf_type_str(const struct btf_type *t)
+{
+ return btf_kind_str[BTF_INFO_KIND(t->info)];
+}
+
struct btf_kind_operations {
s32 (*check_meta)(struct btf_verifier_env *env,
const struct btf_type *t,
@@ -382,6 +382,65 @@ static bool btf_type_is_datasec(const struct btf_type *t)
return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
}
+s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind)
+{
+ const struct btf_type *t;
+ const char *tname;
+ u32 i;
+
+ for (i = 1; i <= btf->nr_types; i++) {
+ t = btf->types[i];
+ if (BTF_INFO_KIND(t->info) != kind)
+ continue;
+
+ tname = btf_name_by_offset(btf, t->name_off);
+ if (!strcmp(tname, name))
+ return i;
+ }
+
+ return -ENOENT;
+}
+
+const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
+ u32 id, u32 *res_id)
+{
+ const struct btf_type *t = btf_type_by_id(btf, id);
+
+ while (btf_type_is_modifier(t)) {
+ id = t->type;
+ t = btf_type_by_id(btf, t->type);
+ }
+
+ if (res_id)
+ *res_id = id;
+
+ return t;
+}
+
+const struct btf_type *btf_type_resolve_ptr(const struct btf *btf,
+ u32 id, u32 *res_id)
+{
+ const struct btf_type *t;
+
+ t = btf_type_skip_modifiers(btf, id, NULL);
+ if (!btf_type_is_ptr(t))
+ return NULL;
+
+ return btf_type_skip_modifiers(btf, t->type, res_id);
+}
+
+const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
+ u32 id, u32 *res_id)
+{
+ const struct btf_type *ptype;
+
+ ptype = btf_type_resolve_ptr(btf, id, res_id);
+ if (ptype && btf_type_is_func_proto(ptype))
+ return ptype;
+
+ return NULL;
+}
+
/* Types that act only as a source, not sink or intermediate
* type when resolving.
*/
@@ -446,30 +505,6 @@ static const char *btf_int_encoding_str(u8 encoding)
return "UNKN";
}
-static u16 btf_type_vlen(const struct btf_type *t)
-{
- return BTF_INFO_VLEN(t->info);
-}
-
-static bool btf_type_kflag(const struct btf_type *t)
-{
- return BTF_INFO_KFLAG(t->info);
-}
-
-static u32 btf_member_bit_offset(const struct btf_type *struct_type,
- const struct btf_member *member)
-{
- return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset)
- : member->offset;
-}
-
-static u32 btf_member_bitfield_size(const struct btf_type *struct_type,
- const struct btf_member *member)
-{
- return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
- : 0;
-}
-
static u32 btf_type_int(const struct btf_type *t)
{
return *(u32 *)(t + 1);
@@ -480,11 +515,6 @@ static const struct btf_array *btf_type_array(const struct btf_type *t)
return (const struct btf_array *)(t + 1);
}
-static const struct btf_member *btf_type_member(const struct btf_type *t)
-{
- return (const struct btf_member *)(t + 1);
-}
-
static const struct btf_enum *btf_type_enum(const struct btf_type *t)
{
return (const struct btf_enum *)(t + 1);
@@ -1057,7 +1087,7 @@ static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env)
* *elem_type: same as return type ("struct X")
* *total_nelems: 1
*/
-static const struct btf_type *
+const struct btf_type *
btf_resolve_size(const struct btf *btf, const struct btf_type *type,
u32 *type_size, const struct btf_type **elem_type,
u32 *total_nelems)
@@ -1111,8 +1141,10 @@ btf_resolve_size(const struct btf *btf, const struct btf_type *type,
return ERR_PTR(-EINVAL);
*type_size = nelems * size;
- *total_nelems = nelems;
- *elem_type = type;
+ if (total_nelems)
+ *total_nelems = nelems;
+ if (elem_type)
+ *elem_type = type;
return array_type ? : type;
}
@@ -1826,7 +1858,10 @@ static void btf_modifier_seq_show(const struct btf *btf,
u32 type_id, void *data,
u8 bits_offset, struct seq_file *m)
{
- t = btf_type_id_resolve(btf, &type_id);
+ if (btf->resolved_ids)
+ t = btf_type_id_resolve(btf, &type_id);
+ else
+ t = btf_type_skip_modifiers(btf, type_id, NULL);
btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
}
@@ -2621,8 +2656,8 @@ static s32 btf_func_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
- if (btf_type_vlen(t)) {
- btf_verifier_log_type(env, t, "vlen != 0");
+ if (btf_type_vlen(t) > BTF_FUNC_GLOBAL) {
+ btf_verifier_log_type(env, t, "Invalid func linkage");
return -EINVAL;
}
@@ -3476,7 +3511,8 @@ static u8 bpf_ctx_convert_map[] = {
static const struct btf_member *
btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
- const struct btf_type *t, enum bpf_prog_type prog_type)
+ const struct btf_type *t, enum bpf_prog_type prog_type,
+ int arg)
{
const struct btf_type *conv_struct;
const struct btf_type *ctx_struct;
@@ -3497,12 +3533,13 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
* is not supported yet.
* BPF_PROG_TYPE_RAW_TRACEPOINT is fine.
*/
- bpf_log(log, "BPF program ctx type is not a struct\n");
+ if (log->level & BPF_LOG_LEVEL)
+ bpf_log(log, "arg#%d type is not a struct\n", arg);
return NULL;
}
tname = btf_name_by_offset(btf, t->name_off);
if (!tname) {
- bpf_log(log, "BPF program ctx struct doesn't have a name\n");
+ bpf_log(log, "arg#%d struct doesn't have a name\n", arg);
return NULL;
}
/* prog_type is valid bpf program type. No need for bounds check. */
@@ -3535,11 +3572,12 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
struct btf *btf,
const struct btf_type *t,
- enum bpf_prog_type prog_type)
+ enum bpf_prog_type prog_type,
+ int arg)
{
const struct btf_member *prog_ctx_type, *kern_ctx_type;
- prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type);
+ prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg);
if (!prog_ctx_type)
return -ENOENT;
kern_ctx_type = prog_ctx_type + 1;
@@ -3605,6 +3643,8 @@ struct btf *btf_parse_vmlinux(void)
goto errout;
}
+ bpf_struct_ops_init(btf);
+
btf_verifier_env_free(env);
refcount_set(&btf->refcnt, 1);
return btf;
@@ -3677,7 +3717,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
/* skip modifiers */
while (btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
- if (btf_type_is_int(t))
+ if (btf_type_is_int(t) || btf_type_is_enum(t))
/* accessing a scalar */
return true;
if (!btf_type_is_ptr(t)) {
@@ -3697,10 +3737,9 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
/* this is a pointer to another type */
info->reg_type = PTR_TO_BTF_ID;
- info->btf_id = t->type;
if (tgt_prog) {
- ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type);
+ ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type, arg);
if (ret > 0) {
info->btf_id = ret;
return true;
@@ -3708,10 +3747,14 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
return false;
}
}
+
+ info->btf_id = t->type;
t = btf_type_by_id(btf, t->type);
/* skip modifiers */
- while (btf_type_is_modifier(t))
+ while (btf_type_is_modifier(t)) {
+ info->btf_id = t->type;
t = btf_type_by_id(btf, t->type);
+ }
if (!btf_type_is_struct(t)) {
bpf_log(log,
"func '%s' arg%d type %s is not a struct\n",
@@ -3737,23 +3780,57 @@ int btf_struct_access(struct bpf_verifier_log *log,
again:
tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
if (!btf_type_is_struct(t)) {
- bpf_log(log, "Type '%s' is not a struct", tname);
+ bpf_log(log, "Type '%s' is not a struct\n", tname);
return -EINVAL;
}
- for_each_member(i, t, member) {
- if (btf_member_bitfield_size(t, member))
- /* bitfields are not supported yet */
- continue;
+ if (off + size > t->size) {
+ bpf_log(log, "access beyond struct %s at off %u size %u\n",
+ tname, off, size);
+ return -EACCES;
+ }
+ for_each_member(i, t, member) {
/* offset of the field in bytes */
moff = btf_member_bit_offset(t, member) / 8;
if (off + size <= moff)
/* won't find anything, field is already too far */
break;
+
+ if (btf_member_bitfield_size(t, member)) {
+ u32 end_bit = btf_member_bit_offset(t, member) +
+ btf_member_bitfield_size(t, member);
+
+ /* off <= moff instead of off == moff because clang
+ * does not generate a BTF member for anonymous
+ * bitfield like the ":16" here:
+ * struct {
+ * int :16;
+ * int x:8;
+ * };
+ */
+ if (off <= moff &&
+ BITS_ROUNDUP_BYTES(end_bit) <= off + size)
+ return SCALAR_VALUE;
+
+ /* off may be accessing a following member
+ *
+ * or
+ *
+ * Doing partial access at either end of this
+ * bitfield. Continue on this case also to
+ * treat it as not accessing this bitfield
+ * and eventually error out as field not
+ * found to keep it simple.
+ * It could be relaxed if there was a legit
+ * partial access case later.
+ */
+ continue;
+ }
+
/* In case of "off" is pointing to holes of a struct */
if (off < moff)
- continue;
+ break;
/* type of the field */
mtype = btf_type_by_id(btf_vmlinux, member->type);
@@ -4043,11 +4120,158 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
return 0;
}
-int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog)
+/* Compare BTFs of two functions assuming only scalars and pointers to context.
+ * t1 points to BTF_KIND_FUNC in btf1
+ * t2 points to BTF_KIND_FUNC in btf2
+ * Returns:
+ * EINVAL - function prototype mismatch
+ * EFAULT - verifier bug
+ * 0 - 99% match. The last 1% is validated by the verifier.
+ */
+int btf_check_func_type_match(struct bpf_verifier_log *log,
+ struct btf *btf1, const struct btf_type *t1,
+ struct btf *btf2, const struct btf_type *t2)
{
- struct bpf_verifier_state *st = env->cur_state;
- struct bpf_func_state *func = st->frame[st->curframe];
- struct bpf_reg_state *reg = func->regs;
+ const struct btf_param *args1, *args2;
+ const char *fn1, *fn2, *s1, *s2;
+ u32 nargs1, nargs2, i;
+
+ fn1 = btf_name_by_offset(btf1, t1->name_off);
+ fn2 = btf_name_by_offset(btf2, t2->name_off);
+
+ if (btf_func_linkage(t1) != BTF_FUNC_GLOBAL) {
+ bpf_log(log, "%s() is not a global function\n", fn1);
+ return -EINVAL;
+ }
+ if (btf_func_linkage(t2) != BTF_FUNC_GLOBAL) {
+ bpf_log(log, "%s() is not a global function\n", fn2);
+ return -EINVAL;
+ }
+
+ t1 = btf_type_by_id(btf1, t1->type);
+ if (!t1 || !btf_type_is_func_proto(t1))
+ return -EFAULT;
+ t2 = btf_type_by_id(btf2, t2->type);
+ if (!t2 || !btf_type_is_func_proto(t2))
+ return -EFAULT;
+
+ args1 = (const struct btf_param *)(t1 + 1);
+ nargs1 = btf_type_vlen(t1);
+ args2 = (const struct btf_param *)(t2 + 1);
+ nargs2 = btf_type_vlen(t2);
+
+ if (nargs1 != nargs2) {
+ bpf_log(log, "%s() has %d args while %s() has %d args\n",
+ fn1, nargs1, fn2, nargs2);
+ return -EINVAL;
+ }
+
+ t1 = btf_type_skip_modifiers(btf1, t1->type, NULL);
+ t2 = btf_type_skip_modifiers(btf2, t2->type, NULL);
+ if (t1->info != t2->info) {
+ bpf_log(log,
+ "Return type %s of %s() doesn't match type %s of %s()\n",
+ btf_type_str(t1), fn1,
+ btf_type_str(t2), fn2);
+ return -EINVAL;
+ }
+
+ for (i = 0; i < nargs1; i++) {
+ t1 = btf_type_skip_modifiers(btf1, args1[i].type, NULL);
+ t2 = btf_type_skip_modifiers(btf2, args2[i].type, NULL);
+
+ if (t1->info != t2->info) {
+ bpf_log(log, "arg%d in %s() is %s while %s() has %s\n",
+ i, fn1, btf_type_str(t1),
+ fn2, btf_type_str(t2));
+ return -EINVAL;
+ }
+ if (btf_type_has_size(t1) && t1->size != t2->size) {
+ bpf_log(log,
+ "arg%d in %s() has size %d while %s() has %d\n",
+ i, fn1, t1->size,
+ fn2, t2->size);
+ return -EINVAL;
+ }
+
+ /* global functions are validated with scalars and pointers
+ * to context only. And only global functions can be replaced.
+ * Hence type check only those types.
+ */
+ if (btf_type_is_int(t1) || btf_type_is_enum(t1))
+ continue;
+ if (!btf_type_is_ptr(t1)) {
+ bpf_log(log,
+ "arg%d in %s() has unrecognized type\n",
+ i, fn1);
+ return -EINVAL;
+ }
+ t1 = btf_type_skip_modifiers(btf1, t1->type, NULL);
+ t2 = btf_type_skip_modifiers(btf2, t2->type, NULL);
+ if (!btf_type_is_struct(t1)) {
+ bpf_log(log,
+ "arg%d in %s() is not a pointer to context\n",
+ i, fn1);
+ return -EINVAL;
+ }
+ if (!btf_type_is_struct(t2)) {
+ bpf_log(log,
+ "arg%d in %s() is not a pointer to context\n",
+ i, fn2);
+ return -EINVAL;
+ }
+ /* This is an optional check to make program writing easier.
+ * Compare names of structs and report an error to the user.
+ * btf_prepare_func_args() already checked that t2 struct
+ * is a context type. btf_prepare_func_args() will check
+ * later that t1 struct is a context type as well.
+ */
+ s1 = btf_name_by_offset(btf1, t1->name_off);
+ s2 = btf_name_by_offset(btf2, t2->name_off);
+ if (strcmp(s1, s2)) {
+ bpf_log(log,
+ "arg%d %s(struct %s *) doesn't match %s(struct %s *)\n",
+ i, fn1, s1, fn2, s2);
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+/* Compare BTFs of given program with BTF of target program */
+int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
+ struct btf *btf2, const struct btf_type *t2)
+{
+ struct btf *btf1 = prog->aux->btf;
+ const struct btf_type *t1;
+ u32 btf_id = 0;
+
+ if (!prog->aux->func_info) {
+ bpf_log(&env->log, "Program extension requires BTF\n");
+ return -EINVAL;
+ }
+
+ btf_id = prog->aux->func_info[0].type_id;
+ if (!btf_id)
+ return -EFAULT;
+
+ t1 = btf_type_by_id(btf1, btf_id);
+ if (!t1 || !btf_type_is_func(t1))
+ return -EFAULT;
+
+ return btf_check_func_type_match(&env->log, btf1, t1, btf2, t2);
+}
+
+/* Compare BTF of a function with given bpf_reg_state.
+ * Returns:
+ * EFAULT - there is a verifier bug. Abort verification.
+ * EINVAL - there is a type mismatch or BTF is not available.
+ * 0 - BTF matches with what bpf_reg_state expects.
+ * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
+ */
+int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
+ struct bpf_reg_state *reg)
+{
struct bpf_verifier_log *log = &env->log;
struct bpf_prog *prog = env->prog;
struct btf *btf = prog->aux->btf;
@@ -4057,27 +4281,30 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog)
const char *tname;
if (!prog->aux->func_info)
- return 0;
+ return -EINVAL;
btf_id = prog->aux->func_info[subprog].type_id;
if (!btf_id)
- return 0;
+ return -EFAULT;
if (prog->aux->func_info_aux[subprog].unreliable)
- return 0;
+ return -EINVAL;
t = btf_type_by_id(btf, btf_id);
if (!t || !btf_type_is_func(t)) {
- bpf_log(log, "BTF of subprog %d doesn't point to KIND_FUNC\n",
+ /* These checks were already done by the verifier while loading
+ * struct bpf_func_info
+ */
+ bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n",
subprog);
- return -EINVAL;
+ return -EFAULT;
}
tname = btf_name_by_offset(btf, t->name_off);
t = btf_type_by_id(btf, t->type);
if (!t || !btf_type_is_func_proto(t)) {
- bpf_log(log, "Invalid type of func %s\n", tname);
- return -EINVAL;
+ bpf_log(log, "Invalid BTF of func %s\n", tname);
+ return -EFAULT;
}
args = (const struct btf_param *)(t + 1);
nargs = btf_type_vlen(t);
@@ -4103,25 +4330,130 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog)
bpf_log(log, "R%d is not a pointer\n", i + 1);
goto out;
}
- /* If program is passing PTR_TO_CTX into subprogram
- * check that BTF type matches.
+ /* If function expects ctx type in BTF check that caller
+ * is passing PTR_TO_CTX.
*/
- if (reg[i + 1].type == PTR_TO_CTX &&
- !btf_get_prog_ctx_type(log, btf, t, prog->type))
- goto out;
- /* All other pointers are ok */
- continue;
+ if (btf_get_prog_ctx_type(log, btf, t, prog->type, i)) {
+ if (reg[i + 1].type != PTR_TO_CTX) {
+ bpf_log(log,
+ "arg#%d expected pointer to ctx, but got %s\n",
+ i, btf_kind_str[BTF_INFO_KIND(t->info)]);
+ goto out;
+ }
+ if (check_ctx_reg(env, ®[i + 1], i + 1))
+ goto out;
+ continue;
+ }
}
- bpf_log(log, "Unrecognized argument type %s\n",
- btf_kind_str[BTF_INFO_KIND(t->info)]);
+ bpf_log(log, "Unrecognized arg#%d type %s\n",
+ i, btf_kind_str[BTF_INFO_KIND(t->info)]);
goto out;
}
return 0;
out:
- /* LLVM optimizations can remove arguments from static functions. */
- bpf_log(log,
- "Type info disagrees with actual arguments due to compiler optimizations\n");
+ /* Compiler optimizations can remove arguments from static functions
+ * or mismatched type can be passed into a global function.
+ * In such cases mark the function as unreliable from BTF point of view.
+ */
prog->aux->func_info_aux[subprog].unreliable = true;
+ return -EINVAL;
+}
+
+/* Convert BTF of a function into bpf_reg_state if possible
+ * Returns:
+ * EFAULT - there is a verifier bug. Abort verification.
+ * EINVAL - cannot convert BTF.
+ * 0 - Successfully converted BTF into bpf_reg_state
+ * (either PTR_TO_CTX or SCALAR_VALUE).
+ */
+int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
+ struct bpf_reg_state *reg)
+{
+ struct bpf_verifier_log *log = &env->log;
+ struct bpf_prog *prog = env->prog;
+ enum bpf_prog_type prog_type = prog->type;
+ struct btf *btf = prog->aux->btf;
+ const struct btf_param *args;
+ const struct btf_type *t;
+ u32 i, nargs, btf_id;
+ const char *tname;
+
+ if (!prog->aux->func_info ||
+ prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) {
+ bpf_log(log, "Verifier bug\n");
+ return -EFAULT;
+ }
+
+ btf_id = prog->aux->func_info[subprog].type_id;
+ if (!btf_id) {
+ bpf_log(log, "Global functions need valid BTF\n");
+ return -EFAULT;
+ }
+
+ t = btf_type_by_id(btf, btf_id);
+ if (!t || !btf_type_is_func(t)) {
+ /* These checks were already done by the verifier while loading
+ * struct bpf_func_info
+ */
+ bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n",
+ subprog);
+ return -EFAULT;
+ }
+ tname = btf_name_by_offset(btf, t->name_off);
+
+ if (log->level & BPF_LOG_LEVEL)
+ bpf_log(log, "Validating %s() func#%d...\n",
+ tname, subprog);
+
+ if (prog->aux->func_info_aux[subprog].unreliable) {
+ bpf_log(log, "Verifier bug in function %s()\n", tname);
+ return -EFAULT;
+ }
+ if (prog_type == BPF_PROG_TYPE_EXT)
+ prog_type = prog->aux->linked_prog->type;
+
+ t = btf_type_by_id(btf, t->type);
+ if (!t || !btf_type_is_func_proto(t)) {
+ bpf_log(log, "Invalid type of function %s()\n", tname);
+ return -EFAULT;
+ }
+ args = (const struct btf_param *)(t + 1);
+ nargs = btf_type_vlen(t);
+ if (nargs > 5) {
+ bpf_log(log, "Global function %s() with %d > 5 args. Buggy compiler.\n",
+ tname, nargs);
+ return -EINVAL;
+ }
+ /* check that function returns int */
+ t = btf_type_by_id(btf, t->type);
+ while (btf_type_is_modifier(t))
+ t = btf_type_by_id(btf, t->type);
+ if (!btf_type_is_int(t) && !btf_type_is_enum(t)) {
+ bpf_log(log,
+ "Global function %s() doesn't return scalar. Only those are supported.\n",
+ tname);
+ return -EINVAL;
+ }
+ /* Convert BTF function arguments into verifier types.
+ * Only PTR_TO_CTX and SCALAR are supported atm.
+ */
+ for (i = 0; i < nargs; i++) {
+ t = btf_type_by_id(btf, args[i].type);
+ while (btf_type_is_modifier(t))
+ t = btf_type_by_id(btf, t->type);
+ if (btf_type_is_int(t) || btf_type_is_enum(t)) {
+ reg[i + 1].type = SCALAR_VALUE;
+ continue;
+ }
+ if (btf_type_is_ptr(t) &&
+ btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
+ reg[i + 1].type = PTR_TO_CTX;
+ continue;
+ }
+ bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n",
+ i, btf_kind_str[BTF_INFO_KIND(t->info)], tname);
+ return -EINVAL;
+ }
return 0;
}
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ee871d4..9a500fa 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -35,8 +35,8 @@ void cgroup_bpf_offline(struct cgroup *cgrp)
*/
static void cgroup_bpf_release(struct work_struct *work)
{
- struct cgroup *cgrp = container_of(work, struct cgroup,
- bpf.release_work);
+ struct cgroup *p, *cgrp = container_of(work, struct cgroup,
+ bpf.release_work);
enum bpf_cgroup_storage_type stype;
struct bpf_prog_array *old_array;
unsigned int type;
@@ -65,6 +65,9 @@ static void cgroup_bpf_release(struct work_struct *work)
mutex_unlock(&cgroup_mutex);
+ for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
+ cgroup_bpf_put(p);
+
percpu_ref_exit(&cgrp->bpf.refcnt);
cgroup_put(cgrp);
}
@@ -198,6 +201,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
*/
#define NR ARRAY_SIZE(cgrp->bpf.effective)
struct bpf_prog_array *arrays[NR] = {};
+ struct cgroup *p;
int ret, i;
ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0,
@@ -205,6 +209,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
if (ret)
return ret;
+ for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
+ cgroup_bpf_get(p);
+
for (i = 0; i < NR; i++)
INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 29d47aa..973a20d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2137,6 +2137,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
const struct bpf_func_proto bpf_spin_lock_proto __weak;
const struct bpf_func_proto bpf_spin_unlock_proto __weak;
+const struct bpf_func_proto bpf_jiffies64_proto __weak;
const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index da9c832..de630f9 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -53,13 +53,11 @@
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
#define DEV_MAP_BULK_SIZE 16
-struct bpf_dtab_netdev;
-
-struct xdp_bulk_queue {
+struct xdp_dev_bulk_queue {
struct xdp_frame *q[DEV_MAP_BULK_SIZE];
struct list_head flush_node;
+ struct net_device *dev;
struct net_device *dev_rx;
- struct bpf_dtab_netdev *obj;
unsigned int count;
};
@@ -67,9 +65,8 @@ struct bpf_dtab_netdev {
struct net_device *dev; /* must be first member, due to tracepoint */
struct hlist_node index_hlist;
struct bpf_dtab *dtab;
- struct xdp_bulk_queue __percpu *bulkq;
struct rcu_head rcu;
- unsigned int idx; /* keep track of map index for tracepoint */
+ unsigned int idx;
};
struct bpf_dtab {
@@ -84,7 +81,7 @@ struct bpf_dtab {
u32 n_buckets;
};
-static DEFINE_PER_CPU(struct list_head, dev_map_flush_list);
+static DEFINE_PER_CPU(struct list_head, dev_flush_list);
static DEFINE_SPINLOCK(dev_map_lock);
static LIST_HEAD(dev_map_list);
@@ -219,7 +216,6 @@ static void dev_map_free(struct bpf_map *map)
hlist_for_each_entry_safe(dev, next, head, index_hlist) {
hlist_del_rcu(&dev->index_hlist);
- free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
@@ -234,7 +230,6 @@ static void dev_map_free(struct bpf_map *map)
if (!dev)
continue;
- free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
@@ -320,10 +315,9 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
return -ENOENT;
}
-static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
+static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
{
- struct bpf_dtab_netdev *obj = bq->obj;
- struct net_device *dev = obj->dev;
+ struct net_device *dev = bq->dev;
int sent = 0, drops = 0, err = 0;
int i;
@@ -346,8 +340,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
out:
bq->count = 0;
- trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx,
- sent, drops, bq->dev_rx, dev, err);
+ trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err);
bq->dev_rx = NULL;
__list_del_clearprev(&bq->flush_node);
return 0;
@@ -364,17 +357,17 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
goto out;
}
-/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled
+/* __dev_flush is called from xdp_do_flush() which _must_ be signaled
* from the driver before returning from its napi->poll() routine. The poll()
* routine is called either from busy_poll context or net_rx_action signaled
* from NET_RX_SOFTIRQ. Either way the poll routine must complete before the
* net device can be torn down. On devmap tear down we ensure the flush list
* is empty before completing to ensure all flush operations have completed.
*/
-void __dev_map_flush(void)
+void __dev_flush(void)
{
- struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list);
- struct xdp_bulk_queue *bq, *tmp;
+ struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
+ struct xdp_dev_bulk_queue *bq, *tmp;
rcu_read_lock();
list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
@@ -401,12 +394,11 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
/* Runs under RCU-read-side, plus in softirq under NAPI protection.
* Thus, safe percpu variable access.
*/
-static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
+static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
struct net_device *dev_rx)
-
{
- struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list);
- struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
+ struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
+ struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
bq_xmit_all(bq, 0);
@@ -426,10 +418,9 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
return 0;
}
-int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
- struct net_device *dev_rx)
+static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
{
- struct net_device *dev = dst->dev;
struct xdp_frame *xdpf;
int err;
@@ -444,7 +435,21 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
if (unlikely(!xdpf))
return -EOVERFLOW;
- return bq_enqueue(dst, xdpf, dev_rx);
+ return bq_enqueue(dev, xdpf, dev_rx);
+}
+
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ return __xdp_enqueue(dev, xdp, dev_rx);
+}
+
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ struct net_device *dev = dst->dev;
+
+ return __xdp_enqueue(dev, xdp, dev_rx);
}
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
@@ -483,7 +488,6 @@ static void __dev_map_entry_free(struct rcu_head *rcu)
struct bpf_dtab_netdev *dev;
dev = container_of(rcu, struct bpf_dtab_netdev, rcu);
- free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
@@ -538,30 +542,15 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
u32 ifindex,
unsigned int idx)
{
- gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
struct bpf_dtab_netdev *dev;
- struct xdp_bulk_queue *bq;
- int cpu;
- dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node);
+ dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN,
+ dtab->map.numa_node);
if (!dev)
return ERR_PTR(-ENOMEM);
- dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq),
- sizeof(void *), gfp);
- if (!dev->bulkq) {
- kfree(dev);
- return ERR_PTR(-ENOMEM);
- }
-
- for_each_possible_cpu(cpu) {
- bq = per_cpu_ptr(dev->bulkq, cpu);
- bq->obj = dev;
- }
-
dev->dev = dev_get_by_index(net, ifindex);
if (!dev->dev) {
- free_percpu(dev->bulkq);
kfree(dev);
return ERR_PTR(-EINVAL);
}
@@ -721,9 +710,23 @@ static int dev_map_notification(struct notifier_block *notifier,
{
struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
struct bpf_dtab *dtab;
- int i;
+ int i, cpu;
switch (event) {
+ case NETDEV_REGISTER:
+ if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq)
+ break;
+
+ /* will be freed in free_netdev() */
+ netdev->xdp_bulkq =
+ __alloc_percpu_gfp(sizeof(struct xdp_dev_bulk_queue),
+ sizeof(void *), GFP_ATOMIC);
+ if (!netdev->xdp_bulkq)
+ return NOTIFY_BAD;
+
+ for_each_possible_cpu(cpu)
+ per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev;
+ break;
case NETDEV_UNREGISTER:
/* This rcu_read_lock/unlock pair is needed because
* dev_map_list is an RCU list AND to ensure a delete
@@ -771,7 +774,7 @@ static int __init dev_map_init(void)
register_netdevice_notifier(&dev_map_notifier);
for_each_possible_cpu(cpu)
- INIT_LIST_HEAD(&per_cpu(dev_map_flush_list, cpu));
+ INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu));
return 0;
}
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 22066a6..2d182c4 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -17,6 +17,16 @@
(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \
BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED)
+#define BATCH_OPS(_name) \
+ .map_lookup_batch = \
+ _name##_map_lookup_batch, \
+ .map_lookup_and_delete_batch = \
+ _name##_map_lookup_and_delete_batch, \
+ .map_update_batch = \
+ generic_map_update_batch, \
+ .map_delete_batch = \
+ generic_map_delete_batch
+
struct bucket {
struct hlist_nulls_head head;
raw_spinlock_t lock;
@@ -1232,6 +1242,256 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
rcu_read_unlock();
}
+static int
+__htab_map_lookup_and_delete_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr,
+ bool do_delete, bool is_lru_map,
+ bool is_percpu)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ u32 bucket_cnt, total, key_size, value_size, roundup_key_size;
+ void *keys = NULL, *values = NULL, *value, *dst_key, *dst_val;
+ void __user *uvalues = u64_to_user_ptr(attr->batch.values);
+ void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
+ void *ubatch = u64_to_user_ptr(attr->batch.in_batch);
+ u32 batch, max_count, size, bucket_size;
+ u64 elem_map_flags, map_flags;
+ struct hlist_nulls_head *head;
+ struct hlist_nulls_node *n;
+ unsigned long flags;
+ struct htab_elem *l;
+ struct bucket *b;
+ int ret = 0;
+
+ elem_map_flags = attr->batch.elem_flags;
+ if ((elem_map_flags & ~BPF_F_LOCK) ||
+ ((elem_map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
+ return -EINVAL;
+
+ map_flags = attr->batch.flags;
+ if (map_flags)
+ return -EINVAL;
+
+ max_count = attr->batch.count;
+ if (!max_count)
+ return 0;
+
+ if (put_user(0, &uattr->batch.count))
+ return -EFAULT;
+
+ batch = 0;
+ if (ubatch && copy_from_user(&batch, ubatch, sizeof(batch)))
+ return -EFAULT;
+
+ if (batch >= htab->n_buckets)
+ return -ENOENT;
+
+ key_size = htab->map.key_size;
+ roundup_key_size = round_up(htab->map.key_size, 8);
+ value_size = htab->map.value_size;
+ size = round_up(value_size, 8);
+ if (is_percpu)
+ value_size = size * num_possible_cpus();
+ total = 0;
+ /* while experimenting with hash tables with sizes ranging from 10 to
+ * 1000, it was observed that a bucket can have upto 5 entries.
+ */
+ bucket_size = 5;
+
+alloc:
+ /* We cannot do copy_from_user or copy_to_user inside
+ * the rcu_read_lock. Allocate enough space here.
+ */
+ keys = kvmalloc(key_size * bucket_size, GFP_USER | __GFP_NOWARN);
+ values = kvmalloc(value_size * bucket_size, GFP_USER | __GFP_NOWARN);
+ if (!keys || !values) {
+ ret = -ENOMEM;
+ goto after_loop;
+ }
+
+again:
+ preempt_disable();
+ this_cpu_inc(bpf_prog_active);
+ rcu_read_lock();
+again_nocopy:
+ dst_key = keys;
+ dst_val = values;
+ b = &htab->buckets[batch];
+ head = &b->head;
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ bucket_cnt = 0;
+ hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
+ bucket_cnt++;
+
+ if (bucket_cnt > (max_count - total)) {
+ if (total == 0)
+ ret = -ENOSPC;
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ rcu_read_unlock();
+ this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+ goto after_loop;
+ }
+
+ if (bucket_cnt > bucket_size) {
+ bucket_size = bucket_cnt;
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ rcu_read_unlock();
+ this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+ kvfree(keys);
+ kvfree(values);
+ goto alloc;
+ }
+
+ hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+ memcpy(dst_key, l->key, key_size);
+
+ if (is_percpu) {
+ int off = 0, cpu;
+ void __percpu *pptr;
+
+ pptr = htab_elem_get_ptr(l, map->key_size);
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(dst_val + off,
+ per_cpu_ptr(pptr, cpu), size);
+ off += size;
+ }
+ } else {
+ value = l->key + roundup_key_size;
+ if (elem_map_flags & BPF_F_LOCK)
+ copy_map_value_locked(map, dst_val, value,
+ true);
+ else
+ copy_map_value(map, dst_val, value);
+ check_and_init_map_lock(map, dst_val);
+ }
+ if (do_delete) {
+ hlist_nulls_del_rcu(&l->hash_node);
+ if (is_lru_map)
+ bpf_lru_push_free(&htab->lru, &l->lru_node);
+ else
+ free_htab_elem(htab, l);
+ }
+ dst_key += key_size;
+ dst_val += value_size;
+ }
+
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ /* If we are not copying data, we can go to next bucket and avoid
+ * unlocking the rcu.
+ */
+ if (!bucket_cnt && (batch + 1 < htab->n_buckets)) {
+ batch++;
+ goto again_nocopy;
+ }
+
+ rcu_read_unlock();
+ this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+ if (bucket_cnt && (copy_to_user(ukeys + total * key_size, keys,
+ key_size * bucket_cnt) ||
+ copy_to_user(uvalues + total * value_size, values,
+ value_size * bucket_cnt))) {
+ ret = -EFAULT;
+ goto after_loop;
+ }
+
+ total += bucket_cnt;
+ batch++;
+ if (batch >= htab->n_buckets) {
+ ret = -ENOENT;
+ goto after_loop;
+ }
+ goto again;
+
+after_loop:
+ if (ret == -EFAULT)
+ goto out;
+
+ /* copy # of entries and next batch */
+ ubatch = u64_to_user_ptr(attr->batch.out_batch);
+ if (copy_to_user(ubatch, &batch, sizeof(batch)) ||
+ put_user(total, &uattr->batch.count))
+ ret = -EFAULT;
+
+out:
+ kvfree(keys);
+ kvfree(values);
+ return ret;
+}
+
+static int
+htab_percpu_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return __htab_map_lookup_and_delete_batch(map, attr, uattr, false,
+ false, true);
+}
+
+static int
+htab_percpu_map_lookup_and_delete_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return __htab_map_lookup_and_delete_batch(map, attr, uattr, true,
+ false, true);
+}
+
+static int
+htab_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return __htab_map_lookup_and_delete_batch(map, attr, uattr, false,
+ false, false);
+}
+
+static int
+htab_map_lookup_and_delete_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return __htab_map_lookup_and_delete_batch(map, attr, uattr, true,
+ false, false);
+}
+
+static int
+htab_lru_percpu_map_lookup_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return __htab_map_lookup_and_delete_batch(map, attr, uattr, false,
+ true, true);
+}
+
+static int
+htab_lru_percpu_map_lookup_and_delete_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return __htab_map_lookup_and_delete_batch(map, attr, uattr, true,
+ true, true);
+}
+
+static int
+htab_lru_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return __htab_map_lookup_and_delete_batch(map, attr, uattr, false,
+ true, false);
+}
+
+static int
+htab_lru_map_lookup_and_delete_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return __htab_map_lookup_and_delete_batch(map, attr, uattr, true,
+ true, false);
+}
+
const struct bpf_map_ops htab_map_ops = {
.map_alloc_check = htab_map_alloc_check,
.map_alloc = htab_map_alloc,
@@ -1242,6 +1502,7 @@ const struct bpf_map_ops htab_map_ops = {
.map_delete_elem = htab_map_delete_elem,
.map_gen_lookup = htab_map_gen_lookup,
.map_seq_show_elem = htab_map_seq_show_elem,
+ BATCH_OPS(htab),
};
const struct bpf_map_ops htab_lru_map_ops = {
@@ -1255,6 +1516,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
.map_delete_elem = htab_lru_map_delete_elem,
.map_gen_lookup = htab_lru_map_gen_lookup,
.map_seq_show_elem = htab_map_seq_show_elem,
+ BATCH_OPS(htab_lru),
};
/* Called from eBPF program */
@@ -1368,6 +1630,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
.map_update_elem = htab_percpu_map_update_elem,
.map_delete_elem = htab_map_delete_elem,
.map_seq_show_elem = htab_percpu_map_seq_show_elem,
+ BATCH_OPS(htab_percpu),
};
const struct bpf_map_ops htab_lru_percpu_map_ops = {
@@ -1379,6 +1642,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
.map_update_elem = htab_lru_percpu_map_update_elem,
.map_delete_elem = htab_lru_map_delete_elem,
.map_seq_show_elem = htab_percpu_map_seq_show_elem,
+ BATCH_OPS(htab_lru_percpu),
};
static int fd_htab_map_alloc_check(union bpf_attr *attr)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index cada974..d8b7b11 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -11,6 +11,7 @@
#include <linux/uidgid.h>
#include <linux/filter.h>
#include <linux/ctype.h>
+#include <linux/jiffies.h>
#include "../../lib/kstrtox.h"
@@ -312,6 +313,17 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
preempt_enable();
}
+BPF_CALL_0(bpf_jiffies64)
+{
+ return get_jiffies_64();
+}
+
+const struct bpf_func_proto bpf_jiffies64_proto = {
+ .func = bpf_jiffies64,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+};
+
#ifdef CONFIG_CGROUPS
BPF_CALL_0(bpf_get_current_cgroup_id)
{
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index ecf42be..e11059b 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -380,7 +380,7 @@ static const struct inode_operations bpf_dir_iops = {
.unlink = simple_unlink,
};
-static int bpf_obj_do_pin(const struct filename *pathname, void *raw,
+static int bpf_obj_do_pin(const char __user *pathname, void *raw,
enum bpf_type type)
{
struct dentry *dentry;
@@ -389,7 +389,7 @@ static int bpf_obj_do_pin(const struct filename *pathname, void *raw,
umode_t mode;
int ret;
- dentry = kern_path_create(AT_FDCWD, pathname->name, &path, 0);
+ dentry = user_path_create(AT_FDCWD, pathname, &path, 0);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
@@ -422,30 +422,22 @@ static int bpf_obj_do_pin(const struct filename *pathname, void *raw,
int bpf_obj_pin_user(u32 ufd, const char __user *pathname)
{
- struct filename *pname;
enum bpf_type type;
void *raw;
int ret;
- pname = getname(pathname);
- if (IS_ERR(pname))
- return PTR_ERR(pname);
-
raw = bpf_fd_probe_obj(ufd, &type);
- if (IS_ERR(raw)) {
- ret = PTR_ERR(raw);
- goto out;
- }
+ if (IS_ERR(raw))
+ return PTR_ERR(raw);
- ret = bpf_obj_do_pin(pname, raw, type);
+ ret = bpf_obj_do_pin(pathname, raw, type);
if (ret != 0)
bpf_any_put(raw, type);
-out:
- putname(pname);
+
return ret;
}
-static void *bpf_obj_do_get(const struct filename *pathname,
+static void *bpf_obj_do_get(const char __user *pathname,
enum bpf_type *type, int flags)
{
struct inode *inode;
@@ -453,7 +445,7 @@ static void *bpf_obj_do_get(const struct filename *pathname,
void *raw;
int ret;
- ret = kern_path(pathname->name, LOOKUP_FOLLOW, &path);
+ ret = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW, &path);
if (ret)
return ERR_PTR(ret);
@@ -480,36 +472,27 @@ static void *bpf_obj_do_get(const struct filename *pathname,
int bpf_obj_get_user(const char __user *pathname, int flags)
{
enum bpf_type type = BPF_TYPE_UNSPEC;
- struct filename *pname;
- int ret = -ENOENT;
int f_flags;
void *raw;
+ int ret;
f_flags = bpf_get_file_flag(flags);
if (f_flags < 0)
return f_flags;
- pname = getname(pathname);
- if (IS_ERR(pname))
- return PTR_ERR(pname);
-
- raw = bpf_obj_do_get(pname, &type, f_flags);
- if (IS_ERR(raw)) {
- ret = PTR_ERR(raw);
- goto out;
- }
+ raw = bpf_obj_do_get(pathname, &type, f_flags);
+ if (IS_ERR(raw))
+ return PTR_ERR(raw);
if (type == BPF_TYPE_PROG)
ret = bpf_prog_new_fd(raw);
else if (type == BPF_TYPE_MAP)
ret = bpf_map_new_fd(raw, f_flags);
else
- goto out;
+ return -ENOENT;
if (ret < 0)
bpf_any_put(raw, type);
-out:
- putname(pname);
return ret;
}
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 5e9366b..b3c48d1 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -22,7 +22,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
*/
if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE ||
- inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
+ inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE ||
+ inner_map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
fdput(f);
return ERR_PTR(-ENOTSUPP);
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 81ee859..a91ad51 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -129,6 +129,152 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
return map;
}
+static u32 bpf_map_value_size(struct bpf_map *map)
+{
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
+ return round_up(map->value_size, 8) * num_possible_cpus();
+ else if (IS_FD_MAP(map))
+ return sizeof(u32);
+ else
+ return map->value_size;
+}
+
+static void maybe_wait_bpf_programs(struct bpf_map *map)
+{
+ /* Wait for any running BPF programs to complete so that
+ * userspace, when we return to it, knows that all programs
+ * that could be running use the new map value.
+ */
+ if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
+ map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
+ synchronize_rcu();
+}
+
+static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key,
+ void *value, __u64 flags)
+{
+ int err;
+
+ /* Need to create a kthread, thus must support schedule */
+ if (bpf_map_is_dev_bound(map)) {
+ return bpf_map_offload_update_elem(map, key, value, flags);
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+ map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+ map->map_type == BPF_MAP_TYPE_SOCKMAP ||
+ map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
+ return map->ops->map_update_elem(map, key, value, flags);
+ } else if (IS_FD_PROG_ARRAY(map)) {
+ return bpf_fd_array_map_update_elem(map, f.file, key, value,
+ flags);
+ }
+
+ /* must increment bpf_prog_active to avoid kprobe+bpf triggering from
+ * inside bpf map update or delete otherwise deadlocks are possible
+ */
+ preempt_disable();
+ __this_cpu_inc(bpf_prog_active);
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+ err = bpf_percpu_hash_update(map, key, value, flags);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
+ err = bpf_percpu_array_update(map, key, value, flags);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
+ err = bpf_percpu_cgroup_storage_update(map, key, value,
+ flags);
+ } else if (IS_FD_ARRAY(map)) {
+ rcu_read_lock();
+ err = bpf_fd_array_map_update_elem(map, f.file, key, value,
+ flags);
+ rcu_read_unlock();
+ } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+ rcu_read_lock();
+ err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
+ flags);
+ rcu_read_unlock();
+ } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
+ /* rcu_read_lock() is not needed */
+ err = bpf_fd_reuseport_array_update_elem(map, key, value,
+ flags);
+ } else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
+ map->map_type == BPF_MAP_TYPE_STACK) {
+ err = map->ops->map_push_elem(map, value, flags);
+ } else {
+ rcu_read_lock();
+ err = map->ops->map_update_elem(map, key, value, flags);
+ rcu_read_unlock();
+ }
+ __this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+ maybe_wait_bpf_programs(map);
+
+ return err;
+}
+
+static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
+ __u64 flags)
+{
+ void *ptr;
+ int err;
+
+ if (bpf_map_is_dev_bound(map))
+ return bpf_map_offload_lookup_elem(map, key, value);
+
+ preempt_disable();
+ this_cpu_inc(bpf_prog_active);
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+ err = bpf_percpu_hash_copy(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
+ err = bpf_percpu_array_copy(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
+ err = bpf_percpu_cgroup_storage_copy(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
+ err = bpf_stackmap_copy(map, key, value);
+ } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) {
+ err = bpf_fd_array_map_lookup_elem(map, key, value);
+ } else if (IS_FD_HASH(map)) {
+ err = bpf_fd_htab_map_lookup_elem(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
+ err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
+ map->map_type == BPF_MAP_TYPE_STACK) {
+ err = map->ops->map_peek_elem(map, value);
+ } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
+ /* struct_ops map requires directly updating "value" */
+ err = bpf_struct_ops_map_sys_lookup_elem(map, key, value);
+ } else {
+ rcu_read_lock();
+ if (map->ops->map_lookup_elem_sys_only)
+ ptr = map->ops->map_lookup_elem_sys_only(map, key);
+ else
+ ptr = map->ops->map_lookup_elem(map, key);
+ if (IS_ERR(ptr)) {
+ err = PTR_ERR(ptr);
+ } else if (!ptr) {
+ err = -ENOENT;
+ } else {
+ err = 0;
+ if (flags & BPF_F_LOCK)
+ /* lock 'ptr' and copy everything but lock */
+ copy_map_value_locked(map, value, ptr, true);
+ else
+ copy_map_value(map, value, ptr);
+ /* mask lock, since value wasn't zero inited */
+ check_and_init_map_lock(map, value);
+ }
+ rcu_read_unlock();
+ }
+
+ this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+ maybe_wait_bpf_programs(map);
+
+ return err;
+}
+
static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
{
/* We really just want to fail instead of triggering OOM killer
@@ -628,7 +774,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
return ret;
}
-#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id
+#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
@@ -642,6 +788,14 @@ static int map_create(union bpf_attr *attr)
if (err)
return -EINVAL;
+ if (attr->btf_vmlinux_value_type_id) {
+ if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS ||
+ attr->btf_key_type_id || attr->btf_value_type_id)
+ return -EINVAL;
+ } else if (attr->btf_key_type_id && !attr->btf_value_type_id) {
+ return -EINVAL;
+ }
+
f_flags = bpf_get_file_flag(attr->map_flags);
if (f_flags < 0)
return f_flags;
@@ -664,32 +818,35 @@ static int map_create(union bpf_attr *attr)
atomic64_set(&map->usercnt, 1);
mutex_init(&map->freeze_mutex);
- if (attr->btf_key_type_id || attr->btf_value_type_id) {
+ map->spin_lock_off = -EINVAL;
+ if (attr->btf_key_type_id || attr->btf_value_type_id ||
+ /* Even the map's value is a kernel's struct,
+ * the bpf_prog.o must have BTF to begin with
+ * to figure out the corresponding kernel's
+ * counter part. Thus, attr->btf_fd has
+ * to be valid also.
+ */
+ attr->btf_vmlinux_value_type_id) {
struct btf *btf;
- if (!attr->btf_value_type_id) {
- err = -EINVAL;
- goto free_map;
- }
-
btf = btf_get_by_fd(attr->btf_fd);
if (IS_ERR(btf)) {
err = PTR_ERR(btf);
goto free_map;
}
+ map->btf = btf;
- err = map_check_btf(map, btf, attr->btf_key_type_id,
- attr->btf_value_type_id);
- if (err) {
- btf_put(btf);
- goto free_map;
+ if (attr->btf_value_type_id) {
+ err = map_check_btf(map, btf, attr->btf_key_type_id,
+ attr->btf_value_type_id);
+ if (err)
+ goto free_map;
}
- map->btf = btf;
map->btf_key_type_id = attr->btf_key_type_id;
map->btf_value_type_id = attr->btf_value_type_id;
- } else {
- map->spin_lock_off = -EINVAL;
+ map->btf_vmlinux_value_type_id =
+ attr->btf_vmlinux_value_type_id;
}
err = security_bpf_map_alloc(map);
@@ -816,7 +973,7 @@ static int map_lookup_elem(union bpf_attr *attr)
void __user *uvalue = u64_to_user_ptr(attr->value);
int ufd = attr->map_fd;
struct bpf_map *map;
- void *key, *value, *ptr;
+ void *key, *value;
u32 value_size;
struct fd f;
int err;
@@ -848,72 +1005,14 @@ static int map_lookup_elem(union bpf_attr *attr)
goto err_put;
}
- if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
- map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
- map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
- map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
- value_size = round_up(map->value_size, 8) * num_possible_cpus();
- else if (IS_FD_MAP(map))
- value_size = sizeof(u32);
- else
- value_size = map->value_size;
+ value_size = bpf_map_value_size(map);
err = -ENOMEM;
value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value)
goto free_key;
- if (bpf_map_is_dev_bound(map)) {
- err = bpf_map_offload_lookup_elem(map, key, value);
- goto done;
- }
-
- preempt_disable();
- this_cpu_inc(bpf_prog_active);
- if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
- map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
- err = bpf_percpu_hash_copy(map, key, value);
- } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
- err = bpf_percpu_array_copy(map, key, value);
- } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
- err = bpf_percpu_cgroup_storage_copy(map, key, value);
- } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
- err = bpf_stackmap_copy(map, key, value);
- } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) {
- err = bpf_fd_array_map_lookup_elem(map, key, value);
- } else if (IS_FD_HASH(map)) {
- err = bpf_fd_htab_map_lookup_elem(map, key, value);
- } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
- err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
- } else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
- map->map_type == BPF_MAP_TYPE_STACK) {
- err = map->ops->map_peek_elem(map, value);
- } else {
- rcu_read_lock();
- if (map->ops->map_lookup_elem_sys_only)
- ptr = map->ops->map_lookup_elem_sys_only(map, key);
- else
- ptr = map->ops->map_lookup_elem(map, key);
- if (IS_ERR(ptr)) {
- err = PTR_ERR(ptr);
- } else if (!ptr) {
- err = -ENOENT;
- } else {
- err = 0;
- if (attr->flags & BPF_F_LOCK)
- /* lock 'ptr' and copy everything but lock */
- copy_map_value_locked(map, value, ptr, true);
- else
- copy_map_value(map, value, ptr);
- /* mask lock, since value wasn't zero inited */
- check_and_init_map_lock(map, value);
- }
- rcu_read_unlock();
- }
- this_cpu_dec(bpf_prog_active);
- preempt_enable();
-
-done:
+ err = bpf_map_copy_value(map, key, value, attr->flags);
if (err)
goto free_value;
@@ -932,16 +1031,6 @@ static int map_lookup_elem(union bpf_attr *attr)
return err;
}
-static void maybe_wait_bpf_programs(struct bpf_map *map)
-{
- /* Wait for any running BPF programs to complete so that
- * userspace, when we return to it, knows that all programs
- * that could be running use the new map value.
- */
- if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
- map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
- synchronize_rcu();
-}
#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
@@ -997,60 +1086,8 @@ static int map_update_elem(union bpf_attr *attr)
if (copy_from_user(value, uvalue, value_size) != 0)
goto free_value;
- /* Need to create a kthread, thus must support schedule */
- if (bpf_map_is_dev_bound(map)) {
- err = bpf_map_offload_update_elem(map, key, value, attr->flags);
- goto out;
- } else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
- map->map_type == BPF_MAP_TYPE_SOCKHASH ||
- map->map_type == BPF_MAP_TYPE_SOCKMAP) {
- err = map->ops->map_update_elem(map, key, value, attr->flags);
- goto out;
- } else if (IS_FD_PROG_ARRAY(map)) {
- err = bpf_fd_array_map_update_elem(map, f.file, key, value,
- attr->flags);
- goto out;
- }
+ err = bpf_map_update_value(map, f, key, value, attr->flags);
- /* must increment bpf_prog_active to avoid kprobe+bpf triggering from
- * inside bpf map update or delete otherwise deadlocks are possible
- */
- preempt_disable();
- __this_cpu_inc(bpf_prog_active);
- if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
- map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
- err = bpf_percpu_hash_update(map, key, value, attr->flags);
- } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
- err = bpf_percpu_array_update(map, key, value, attr->flags);
- } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
- err = bpf_percpu_cgroup_storage_update(map, key, value,
- attr->flags);
- } else if (IS_FD_ARRAY(map)) {
- rcu_read_lock();
- err = bpf_fd_array_map_update_elem(map, f.file, key, value,
- attr->flags);
- rcu_read_unlock();
- } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
- rcu_read_lock();
- err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
- attr->flags);
- rcu_read_unlock();
- } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
- /* rcu_read_lock() is not needed */
- err = bpf_fd_reuseport_array_update_elem(map, key, value,
- attr->flags);
- } else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
- map->map_type == BPF_MAP_TYPE_STACK) {
- err = map->ops->map_push_elem(map, value, attr->flags);
- } else {
- rcu_read_lock();
- err = map->ops->map_update_elem(map, key, value, attr->flags);
- rcu_read_unlock();
- }
- __this_cpu_dec(bpf_prog_active);
- preempt_enable();
- maybe_wait_bpf_programs(map);
-out:
free_value:
kfree(value);
free_key:
@@ -1092,7 +1129,9 @@ static int map_delete_elem(union bpf_attr *attr)
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_delete_elem(map, key);
goto out;
- } else if (IS_FD_PROG_ARRAY(map)) {
+ } else if (IS_FD_PROG_ARRAY(map) ||
+ map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
+ /* These maps require sleepable context */
err = map->ops->map_delete_elem(map, key);
goto out;
}
@@ -1179,6 +1218,220 @@ static int map_get_next_key(union bpf_attr *attr)
return err;
}
+int generic_map_delete_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ void __user *keys = u64_to_user_ptr(attr->batch.keys);
+ u32 cp, max_count;
+ int err = 0;
+ void *key;
+
+ if (attr->batch.elem_flags & ~BPF_F_LOCK)
+ return -EINVAL;
+
+ if ((attr->batch.elem_flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)) {
+ return -EINVAL;
+ }
+
+ max_count = attr->batch.count;
+ if (!max_count)
+ return 0;
+
+ key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
+ if (!key)
+ return -ENOMEM;
+
+ for (cp = 0; cp < max_count; cp++) {
+ err = -EFAULT;
+ if (copy_from_user(key, keys + cp * map->key_size,
+ map->key_size))
+ break;
+
+ if (bpf_map_is_dev_bound(map)) {
+ err = bpf_map_offload_delete_elem(map, key);
+ break;
+ }
+
+ preempt_disable();
+ __this_cpu_inc(bpf_prog_active);
+ rcu_read_lock();
+ err = map->ops->map_delete_elem(map, key);
+ rcu_read_unlock();
+ __this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+ maybe_wait_bpf_programs(map);
+ if (err)
+ break;
+ }
+ if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
+ err = -EFAULT;
+
+ kfree(key);
+ return err;
+}
+
+int generic_map_update_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ void __user *values = u64_to_user_ptr(attr->batch.values);
+ void __user *keys = u64_to_user_ptr(attr->batch.keys);
+ u32 value_size, cp, max_count;
+ int ufd = attr->map_fd;
+ void *key, *value;
+ struct fd f;
+ int err = 0;
+
+ f = fdget(ufd);
+ if (attr->batch.elem_flags & ~BPF_F_LOCK)
+ return -EINVAL;
+
+ if ((attr->batch.elem_flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)) {
+ return -EINVAL;
+ }
+
+ value_size = bpf_map_value_size(map);
+
+ max_count = attr->batch.count;
+ if (!max_count)
+ return 0;
+
+ key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
+ if (!key)
+ return -ENOMEM;
+
+ value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
+ if (!value) {
+ kfree(key);
+ return -ENOMEM;
+ }
+
+ for (cp = 0; cp < max_count; cp++) {
+ err = -EFAULT;
+ if (copy_from_user(key, keys + cp * map->key_size,
+ map->key_size) ||
+ copy_from_user(value, values + cp * value_size, value_size))
+ break;
+
+ err = bpf_map_update_value(map, f, key, value,
+ attr->batch.elem_flags);
+
+ if (err)
+ break;
+ }
+
+ if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
+ err = -EFAULT;
+
+ kfree(value);
+ kfree(key);
+ return err;
+}
+
+#define MAP_LOOKUP_RETRIES 3
+
+int generic_map_lookup_batch(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch);
+ void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch);
+ void __user *values = u64_to_user_ptr(attr->batch.values);
+ void __user *keys = u64_to_user_ptr(attr->batch.keys);
+ void *buf, *buf_prevkey, *prev_key, *key, *value;
+ int err, retry = MAP_LOOKUP_RETRIES;
+ u32 value_size, cp, max_count;
+
+ if (attr->batch.elem_flags & ~BPF_F_LOCK)
+ return -EINVAL;
+
+ if ((attr->batch.elem_flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map))
+ return -EINVAL;
+
+ value_size = bpf_map_value_size(map);
+
+ max_count = attr->batch.count;
+ if (!max_count)
+ return 0;
+
+ if (put_user(0, &uattr->batch.count))
+ return -EFAULT;
+
+ buf_prevkey = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
+ if (!buf_prevkey)
+ return -ENOMEM;
+
+ buf = kmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN);
+ if (!buf) {
+ kvfree(buf_prevkey);
+ return -ENOMEM;
+ }
+
+ err = -EFAULT;
+ prev_key = NULL;
+ if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size))
+ goto free_buf;
+ key = buf;
+ value = key + map->key_size;
+ if (ubatch)
+ prev_key = buf_prevkey;
+
+ for (cp = 0; cp < max_count;) {
+ rcu_read_lock();
+ err = map->ops->map_get_next_key(map, prev_key, key);
+ rcu_read_unlock();
+ if (err)
+ break;
+ err = bpf_map_copy_value(map, key, value,
+ attr->batch.elem_flags);
+
+ if (err == -ENOENT) {
+ if (retry) {
+ retry--;
+ continue;
+ }
+ err = -EINTR;
+ break;
+ }
+
+ if (err)
+ goto free_buf;
+
+ if (copy_to_user(keys + cp * map->key_size, key,
+ map->key_size)) {
+ err = -EFAULT;
+ goto free_buf;
+ }
+ if (copy_to_user(values + cp * value_size, value, value_size)) {
+ err = -EFAULT;
+ goto free_buf;
+ }
+
+ if (!prev_key)
+ prev_key = buf_prevkey;
+
+ swap(prev_key, key);
+ retry = MAP_LOOKUP_RETRIES;
+ cp++;
+ }
+
+ if (err == -EFAULT)
+ goto free_buf;
+
+ if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) ||
+ (cp && copy_to_user(uobatch, prev_key, map->key_size))))
+ err = -EFAULT;
+
+free_buf:
+ kfree(buf_prevkey);
+ kfree(buf);
+ return err;
+}
+
#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value
static int map_lookup_and_delete_elem(union bpf_attr *attr)
@@ -1672,17 +1925,24 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
enum bpf_attach_type expected_attach_type,
u32 btf_id, u32 prog_fd)
{
- switch (prog_type) {
- case BPF_PROG_TYPE_TRACING:
+ if (btf_id) {
if (btf_id > BTF_MAX_TYPE)
return -EINVAL;
- break;
- default:
- if (btf_id || prog_fd)
+
+ switch (prog_type) {
+ case BPF_PROG_TYPE_TRACING:
+ case BPF_PROG_TYPE_STRUCT_OPS:
+ case BPF_PROG_TYPE_EXT:
+ break;
+ default:
return -EINVAL;
- break;
+ }
}
+ if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING &&
+ prog_type != BPF_PROG_TYPE_EXT)
+ return -EINVAL;
+
switch (prog_type) {
case BPF_PROG_TYPE_CGROUP_SOCK:
switch (expected_attach_type) {
@@ -1723,6 +1983,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
default:
return -EINVAL;
}
+ case BPF_PROG_TYPE_EXT:
+ if (expected_attach_type)
+ return -EINVAL;
+ /* fallthrough */
default:
return 0;
}
@@ -1925,7 +2189,8 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
int tr_fd, err;
if (prog->expected_attach_type != BPF_TRACE_FENTRY &&
- prog->expected_attach_type != BPF_TRACE_FEXIT) {
+ prog->expected_attach_type != BPF_TRACE_FEXIT &&
+ prog->type != BPF_PROG_TYPE_EXT) {
err = -EINVAL;
goto out_put_prog;
}
@@ -1992,12 +2257,14 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT &&
prog->type != BPF_PROG_TYPE_TRACING &&
+ prog->type != BPF_PROG_TYPE_EXT &&
prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
err = -EINVAL;
goto out_put_prog;
}
- if (prog->type == BPF_PROG_TYPE_TRACING) {
+ if (prog->type == BPF_PROG_TYPE_TRACING ||
+ prog->type == BPF_PROG_TYPE_EXT) {
if (attr->raw_tracepoint.name) {
/* The attach point for this category of programs
* should be specified via btf_id during program load.
@@ -2817,6 +3084,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
info.btf_key_type_id = map->btf_key_type_id;
info.btf_value_type_id = map->btf_value_type_id;
}
+ info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id;
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_info_fill(&info, map);
@@ -3029,6 +3297,61 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
return err;
}
+#define BPF_MAP_BATCH_LAST_FIELD batch.flags
+
+#define BPF_DO_BATCH(fn) \
+ do { \
+ if (!fn) { \
+ err = -ENOTSUPP; \
+ goto err_put; \
+ } \
+ err = fn(map, attr, uattr); \
+ } while (0)
+
+static int bpf_map_do_batch(const union bpf_attr *attr,
+ union bpf_attr __user *uattr,
+ int cmd)
+{
+ struct bpf_map *map;
+ int err, ufd;
+ struct fd f;
+
+ if (CHECK_ATTR(BPF_MAP_BATCH))
+ return -EINVAL;
+
+ ufd = attr->batch.map_fd;
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ if ((cmd == BPF_MAP_LOOKUP_BATCH ||
+ cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) &&
+ !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
+ if (cmd != BPF_MAP_LOOKUP_BATCH &&
+ !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
+ if (cmd == BPF_MAP_LOOKUP_BATCH)
+ BPF_DO_BATCH(map->ops->map_lookup_batch);
+ else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH)
+ BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch);
+ else if (cmd == BPF_MAP_UPDATE_BATCH)
+ BPF_DO_BATCH(map->ops->map_update_batch);
+ else
+ BPF_DO_BATCH(map->ops->map_delete_batch);
+
+err_put:
+ fdput(f);
+ return err;
+}
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@@ -3126,6 +3449,19 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_MAP_LOOKUP_AND_DELETE_ELEM:
err = map_lookup_and_delete_elem(&attr);
break;
+ case BPF_MAP_LOOKUP_BATCH:
+ err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH);
+ break;
+ case BPF_MAP_LOOKUP_AND_DELETE_BATCH:
+ err = bpf_map_do_batch(&attr, uattr,
+ BPF_MAP_LOOKUP_AND_DELETE_BATCH);
+ break;
+ case BPF_MAP_UPDATE_BATCH:
+ err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH);
+ break;
+ case BPF_MAP_DELETE_BATCH:
+ err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH);
+ break;
default:
err = -EINVAL;
break;
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index ca52b96..d4f335a9 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -44,14 +44,19 @@ struct tnum tnum_rshift(struct tnum a, u8 shift)
return TNUM(a.value >> shift, a.mask >> shift);
}
-struct tnum tnum_arshift(struct tnum a, u8 min_shift)
+struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness)
{
/* if a.value is negative, arithmetic shifting by minimum shift
* will have larger negative offset compared to more shifting.
* If a.value is nonnegative, arithmetic shifting by minimum shift
* will have larger positive offset compare to more shifting.
*/
- return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift);
+ if (insn_bitness == 32)
+ return TNUM((u32)(((s32)a.value) >> min_shift),
+ (u32)(((s32)a.mask) >> min_shift));
+ else
+ return TNUM((s64)a.value >> min_shift,
+ (s64)a.mask >> min_shift);
}
struct tnum tnum_add(struct tnum a, struct tnum b)
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 505f4e4..eb64c24 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -5,6 +5,12 @@
#include <linux/filter.h>
#include <linux/ftrace.h>
+/* dummy _ops. The verifier will operate on target program's ops. */
+const struct bpf_verifier_ops bpf_extension_verifier_ops = {
+};
+const struct bpf_prog_ops bpf_extension_prog_ops = {
+};
+
/* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */
#define TRAMPOLINE_HASH_BITS 10
#define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS)
@@ -160,11 +166,20 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
if (fexit_cnt)
flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
- err = arch_prepare_bpf_trampoline(new_image, &tr->func.model, flags,
+ /* Though the second half of trampoline page is unused a task could be
+ * preempted in the middle of the first half of trampoline and two
+ * updates to trampoline would change the code from underneath the
+ * preempted task. Hence wait for tasks to voluntarily schedule or go
+ * to userspace.
+ */
+ synchronize_rcu_tasks();
+
+ err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2,
+ &tr->func.model, flags,
fentry, fentry_cnt,
fexit, fexit_cnt,
tr->func.addr);
- if (err)
+ if (err < 0)
goto out;
if (tr->selector)
@@ -185,8 +200,10 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t)
switch (t) {
case BPF_TRACE_FENTRY:
return BPF_TRAMP_FENTRY;
- default:
+ case BPF_TRACE_FEXIT:
return BPF_TRAMP_FEXIT;
+ default:
+ return BPF_TRAMP_REPLACE;
}
}
@@ -195,12 +212,31 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog)
enum bpf_tramp_prog_type kind;
struct bpf_trampoline *tr;
int err = 0;
+ int cnt;
tr = prog->aux->trampoline;
kind = bpf_attach_type_to_tramp(prog->expected_attach_type);
mutex_lock(&tr->mutex);
- if (tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT]
- >= BPF_MAX_TRAMP_PROGS) {
+ if (tr->extension_prog) {
+ /* cannot attach fentry/fexit if extension prog is attached.
+ * cannot overwrite extension prog either.
+ */
+ err = -EBUSY;
+ goto out;
+ }
+ cnt = tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT];
+ if (kind == BPF_TRAMP_REPLACE) {
+ /* Cannot attach extension if fentry/fexit are in use. */
+ if (cnt) {
+ err = -EBUSY;
+ goto out;
+ }
+ tr->extension_prog = prog;
+ err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL,
+ prog->bpf_func);
+ goto out;
+ }
+ if (cnt >= BPF_MAX_TRAMP_PROGS) {
err = -E2BIG;
goto out;
}
@@ -231,9 +267,17 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
tr = prog->aux->trampoline;
kind = bpf_attach_type_to_tramp(prog->expected_attach_type);
mutex_lock(&tr->mutex);
+ if (kind == BPF_TRAMP_REPLACE) {
+ WARN_ON_ONCE(!tr->extension_prog);
+ err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP,
+ tr->extension_prog->bpf_func, NULL);
+ tr->extension_prog = NULL;
+ goto out;
+ }
hlist_del(&prog->aux->tramp_hlist);
tr->progs_cnt[kind]--;
err = bpf_trampoline_update(prog->aux->trampoline);
+out:
mutex_unlock(&tr->mutex);
return err;
}
@@ -250,6 +294,8 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
goto out;
if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT])))
goto out;
+ /* wait for tasks to get out of trampoline before freeing it */
+ synchronize_rcu_tasks();
bpf_jit_free_exec(tr->image);
hlist_del(&tr->hlist);
kfree(tr);
@@ -296,7 +342,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
}
int __weak
-arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
+arch_prepare_bpf_trampoline(void *image, void *image_end,
+ const struct btf_func_model *m, u32 flags,
struct bpf_prog **fentry_progs, int fentry_cnt,
struct bpf_prog **fexit_progs, int fexit_cnt,
void *orig_call)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6f63ae7..1cc945d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1122,10 +1122,6 @@ static void init_reg_state(struct bpf_verifier_env *env,
regs[BPF_REG_FP].type = PTR_TO_STACK;
mark_reg_known_zero(env, regs, BPF_REG_FP);
regs[BPF_REG_FP].frameno = state->frameno;
-
- /* 1st arg to a function */
- regs[BPF_REG_1].type = PTR_TO_CTX;
- mark_reg_known_zero(env, regs, BPF_REG_1);
}
#define BPF_MAIN_FUNC (-1)
@@ -1916,6 +1912,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
case PTR_TO_TCP_SOCK:
case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
+ case PTR_TO_BTF_ID:
return true;
default:
return false;
@@ -2738,8 +2735,8 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env,
}
#endif
-static int check_ctx_reg(struct bpf_verifier_env *env,
- const struct bpf_reg_state *reg, int regno)
+int check_ctx_reg(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg, int regno)
{
/* Access to ctx or passing it to a helper is only allowed in
* its original, unmodified form.
@@ -2858,11 +2855,6 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
u32 btf_id;
int ret;
- if (atype != BPF_READ) {
- verbose(env, "only read is supported\n");
- return -EACCES;
- }
-
if (off < 0) {
verbose(env,
"R%d is ptr_%s invalid negative access: off=%d\n",
@@ -2879,17 +2871,32 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
return -EACCES;
}
- ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id);
+ if (env->ops->btf_struct_access) {
+ ret = env->ops->btf_struct_access(&env->log, t, off, size,
+ atype, &btf_id);
+ } else {
+ if (atype != BPF_READ) {
+ verbose(env, "only read is supported\n");
+ return -EACCES;
+ }
+
+ ret = btf_struct_access(&env->log, t, off, size, atype,
+ &btf_id);
+ }
+
if (ret < 0)
return ret;
- if (ret == SCALAR_VALUE) {
- mark_reg_unknown(env, regs, value_regno);
- return 0;
+ if (atype == BPF_READ) {
+ if (ret == SCALAR_VALUE) {
+ mark_reg_unknown(env, regs, value_regno);
+ return 0;
+ }
+ mark_reg_known_zero(env, regs, value_regno);
+ regs[value_regno].type = PTR_TO_BTF_ID;
+ regs[value_regno].btf_id = btf_id;
}
- mark_reg_known_zero(env, regs, value_regno);
- regs[value_regno].type = PTR_TO_BTF_ID;
- regs[value_regno].btf_id = btf_id;
+
return 0;
}
@@ -3945,12 +3952,26 @@ static int release_reference(struct bpf_verifier_env *env,
return 0;
}
+static void clear_caller_saved_regs(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs)
+{
+ int i;
+
+ /* after the call registers r0 - r5 were scratched */
+ for (i = 0; i < CALLER_SAVED_REGS; i++) {
+ mark_reg_not_init(env, regs, caller_saved[i]);
+ check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+ }
+}
+
static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx)
{
struct bpf_verifier_state *state = env->cur_state;
+ struct bpf_func_info_aux *func_info_aux;
struct bpf_func_state *caller, *callee;
int i, err, subprog, target_insn;
+ bool is_global = false;
if (state->curframe + 1 >= MAX_CALL_FRAMES) {
verbose(env, "the call stack of %d frames is too deep\n",
@@ -3973,6 +3994,32 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return -EFAULT;
}
+ func_info_aux = env->prog->aux->func_info_aux;
+ if (func_info_aux)
+ is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
+ err = btf_check_func_arg_match(env, subprog, caller->regs);
+ if (err == -EFAULT)
+ return err;
+ if (is_global) {
+ if (err) {
+ verbose(env, "Caller passes invalid args into func#%d\n",
+ subprog);
+ return err;
+ } else {
+ if (env->log.level & BPF_LOG_LEVEL)
+ verbose(env,
+ "Func#%d is global and valid. Skipping.\n",
+ subprog);
+ clear_caller_saved_regs(env, caller->regs);
+
+ /* All global functions return SCALAR_VALUE */
+ mark_reg_unknown(env, caller->regs, BPF_REG_0);
+
+ /* continue with next insn after call */
+ return 0;
+ }
+ }
+
callee = kzalloc(sizeof(*callee), GFP_KERNEL);
if (!callee)
return -ENOMEM;
@@ -3999,18 +4046,11 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
for (i = BPF_REG_1; i <= BPF_REG_5; i++)
callee->regs[i] = caller->regs[i];
- /* after the call registers r0 - r5 were scratched */
- for (i = 0; i < CALLER_SAVED_REGS; i++) {
- mark_reg_not_init(env, caller->regs, caller_saved[i]);
- check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
- }
+ clear_caller_saved_regs(env, caller->regs);
/* only increment it after check_reg_arg() finished */
state->curframe++;
- if (btf_check_func_arg_match(env, subprog))
- return -EINVAL;
-
/* and go analyze first insn of the callee */
*insn_idx = target_insn;
@@ -5049,9 +5089,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
/* Upon reaching here, src_known is true and
* umax_val is equal to umin_val.
*/
- dst_reg->smin_value >>= umin_val;
- dst_reg->smax_value >>= umin_val;
- dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val);
+ if (insn_bitness == 32) {
+ dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val);
+ dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val);
+ } else {
+ dst_reg->smin_value >>= umin_val;
+ dst_reg->smax_value >>= umin_val;
+ }
+
+ dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val,
+ insn_bitness);
/* blow away the dst_reg umin_value/umax_value and rely on
* dst_reg var_off to refine the result.
@@ -6264,6 +6311,7 @@ static bool may_access_skb(enum bpf_prog_type type)
static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = cur_regs(env);
+ static const int ctx_reg = BPF_REG_6;
u8 mode = BPF_MODE(insn->code);
int i, err;
@@ -6297,7 +6345,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
/* check whether implicit source operand (register R6) is readable */
- err = check_reg_arg(env, BPF_REG_6, SRC_OP);
+ err = check_reg_arg(env, ctx_reg, SRC_OP);
if (err)
return err;
@@ -6316,7 +6364,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return -EINVAL;
}
- if (regs[BPF_REG_6].type != PTR_TO_CTX) {
+ if (regs[ctx_reg].type != PTR_TO_CTX) {
verbose(env,
"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
return -EINVAL;
@@ -6329,6 +6377,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return err;
}
+ err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg);
+ if (err < 0)
+ return err;
+
/* reset caller saved regs to unreadable */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
@@ -6348,8 +6400,30 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
static int check_return_code(struct bpf_verifier_env *env)
{
struct tnum enforce_attach_type_range = tnum_unknown;
+ const struct bpf_prog *prog = env->prog;
struct bpf_reg_state *reg;
struct tnum range = tnum_range(0, 1);
+ int err;
+
+ /* The struct_ops func-ptr's return type could be "void" */
+ if (env->prog->type == BPF_PROG_TYPE_STRUCT_OPS &&
+ !prog->aux->attach_func_proto->type)
+ return 0;
+
+ /* eBPF calling convetion is such that R0 is used
+ * to return the value from eBPF program.
+ * Make sure that it's readable at this time
+ * of bpf_exit, which means that program wrote
+ * something into it earlier
+ */
+ err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+ if (err)
+ return err;
+
+ if (is_pointer_value(env, BPF_REG_0)) {
+ verbose(env, "R0 leaks addr as return value\n");
+ return -EACCES;
+ }
switch (env->prog->type) {
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
@@ -6738,12 +6812,13 @@ static int check_btf_func(struct bpf_verifier_env *env,
/* check type_id */
type = btf_type_by_id(btf, krecord[i].type_id);
- if (!type || BTF_INFO_KIND(type->info) != BTF_KIND_FUNC) {
+ if (!type || !btf_type_is_func(type)) {
verbose(env, "invalid type id %d in func info",
krecord[i].type_id);
ret = -EINVAL;
goto err_free;
}
+ info_aux[i].linkage = BTF_INFO_VLEN(type->info);
prev_offset = krecord[i].insn_off;
urecord += urec_size;
}
@@ -7723,35 +7798,13 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev)
static int do_check(struct bpf_verifier_env *env)
{
- struct bpf_verifier_state *state;
+ struct bpf_verifier_state *state = env->cur_state;
struct bpf_insn *insns = env->prog->insnsi;
struct bpf_reg_state *regs;
int insn_cnt = env->prog->len;
bool do_print_state = false;
int prev_insn_idx = -1;
- env->prev_linfo = NULL;
-
- state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
- if (!state)
- return -ENOMEM;
- state->curframe = 0;
- state->speculative = false;
- state->branches = 1;
- state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
- if (!state->frame[0]) {
- kfree(state);
- return -ENOMEM;
- }
- env->cur_state = state;
- init_func_state(env, state->frame[0],
- BPF_MAIN_FUNC /* callsite */,
- 0 /* frameno */,
- 0 /* subprogno, zero == main subprog */);
-
- if (btf_check_func_arg_match(env, 0))
- return -EINVAL;
-
for (;;) {
struct bpf_insn *insn;
u8 class;
@@ -7829,7 +7882,7 @@ static int do_check(struct bpf_verifier_env *env)
}
regs = cur_regs(env);
- env->insn_aux_data[env->insn_idx].seen = true;
+ env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
prev_insn_idx = env->insn_idx;
if (class == BPF_ALU || class == BPF_ALU64) {
@@ -8015,21 +8068,6 @@ static int do_check(struct bpf_verifier_env *env)
if (err)
return err;
- /* eBPF calling convetion is such that R0 is used
- * to return the value from eBPF program.
- * Make sure that it's readable at this time
- * of bpf_exit, which means that program wrote
- * something into it earlier
- */
- err = check_reg_arg(env, BPF_REG_0, SRC_OP);
- if (err)
- return err;
-
- if (is_pointer_value(env, BPF_REG_0)) {
- verbose(env, "R0 leaks addr as return value\n");
- return -EACCES;
- }
-
err = check_return_code(env);
if (err)
return err;
@@ -8064,7 +8102,7 @@ static int do_check(struct bpf_verifier_env *env)
return err;
env->insn_idx++;
- env->insn_aux_data[env->insn_idx].seen = true;
+ env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
} else {
verbose(env, "invalid BPF_LD mode\n");
return -EINVAL;
@@ -8077,7 +8115,6 @@ static int do_check(struct bpf_verifier_env *env)
env->insn_idx++;
}
- env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return 0;
}
@@ -8137,6 +8174,11 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
return -EINVAL;
}
+ if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
+ verbose(env, "bpf_struct_ops map cannot be used in prog\n");
+ return -EINVAL;
+ }
+
return 0;
}
@@ -8349,7 +8391,7 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env,
memcpy(new_data + off + cnt - 1, old_data + off,
sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
for (i = off; i < off + cnt - 1; i++) {
- new_data[i].seen = true;
+ new_data[i].seen = env->pass_cnt;
new_data[i].zext_dst = insn_has_def32(env, insn + i);
}
env->insn_aux_data = new_data;
@@ -8828,12 +8870,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
convert_ctx_access = bpf_xdp_sock_convert_ctx_access;
break;
case PTR_TO_BTF_ID:
- if (type == BPF_WRITE) {
+ if (type == BPF_READ) {
+ insn->code = BPF_LDX | BPF_PROBE_MEM |
+ BPF_SIZE((insn)->code);
+ env->prog->aux->num_exentries++;
+ } else if (env->prog->type != BPF_PROG_TYPE_STRUCT_OPS) {
verbose(env, "Writes through BTF pointers are not allowed\n");
return -EINVAL;
}
- insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code);
- env->prog->aux->num_exentries++;
continue;
default:
continue;
@@ -9413,6 +9457,30 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
goto patch_call_imm;
}
+ if (prog->jit_requested && BITS_PER_LONG == 64 &&
+ insn->imm == BPF_FUNC_jiffies64) {
+ struct bpf_insn ld_jiffies_addr[2] = {
+ BPF_LD_IMM64(BPF_REG_0,
+ (unsigned long)&jiffies),
+ };
+
+ insn_buf[0] = ld_jiffies_addr[0];
+ insn_buf[1] = ld_jiffies_addr[1];
+ insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0,
+ BPF_REG_0, 0);
+ cnt = 3;
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
+ cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
patch_call_imm:
fn = env->ops->get_func_proto(insn->imm, env->prog);
/* all functions that have prototype and verifier allowed
@@ -9459,6 +9527,7 @@ static void free_states(struct bpf_verifier_env *env)
kfree(sl);
sl = sln;
}
+ env->free_list = NULL;
if (!env->explored_states)
return;
@@ -9472,11 +9541,164 @@ static void free_states(struct bpf_verifier_env *env)
kfree(sl);
sl = sln;
}
+ env->explored_states[i] = NULL;
+ }
+}
+
+/* The verifier is using insn_aux_data[] to store temporary data during
+ * verification and to store information for passes that run after the
+ * verification like dead code sanitization. do_check_common() for subprogram N
+ * may analyze many other subprograms. sanitize_insn_aux_data() clears all
+ * temporary data after do_check_common() finds that subprogram N cannot be
+ * verified independently. pass_cnt counts the number of times
+ * do_check_common() was run and insn->aux->seen tells the pass number
+ * insn_aux_data was touched. These variables are compared to clear temporary
+ * data from failed pass. For testing and experiments do_check_common() can be
+ * run multiple times even when prior attempt to verify is unsuccessful.
+ */
+static void sanitize_insn_aux_data(struct bpf_verifier_env *env)
+{
+ struct bpf_insn *insn = env->prog->insnsi;
+ struct bpf_insn_aux_data *aux;
+ int i, class;
+
+ for (i = 0; i < env->prog->len; i++) {
+ class = BPF_CLASS(insn[i].code);
+ if (class != BPF_LDX && class != BPF_STX)
+ continue;
+ aux = &env->insn_aux_data[i];
+ if (aux->seen != env->pass_cnt)
+ continue;
+ memset(aux, 0, offsetof(typeof(*aux), orig_idx));
+ }
+}
+
+static int do_check_common(struct bpf_verifier_env *env, int subprog)
+{
+ struct bpf_verifier_state *state;
+ struct bpf_reg_state *regs;
+ int ret, i;
+
+ env->prev_linfo = NULL;
+ env->pass_cnt++;
+
+ state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+ state->curframe = 0;
+ state->speculative = false;
+ state->branches = 1;
+ state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
+ if (!state->frame[0]) {
+ kfree(state);
+ return -ENOMEM;
+ }
+ env->cur_state = state;
+ init_func_state(env, state->frame[0],
+ BPF_MAIN_FUNC /* callsite */,
+ 0 /* frameno */,
+ subprog);
+
+ regs = state->frame[state->curframe]->regs;
+ if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
+ ret = btf_prepare_func_args(env, subprog, regs);
+ if (ret)
+ goto out;
+ for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
+ if (regs[i].type == PTR_TO_CTX)
+ mark_reg_known_zero(env, regs, i);
+ else if (regs[i].type == SCALAR_VALUE)
+ mark_reg_unknown(env, regs, i);
+ }
+ } else {
+ /* 1st arg to a function */
+ regs[BPF_REG_1].type = PTR_TO_CTX;
+ mark_reg_known_zero(env, regs, BPF_REG_1);
+ ret = btf_check_func_arg_match(env, subprog, regs);
+ if (ret == -EFAULT)
+ /* unlikely verifier bug. abort.
+ * ret == 0 and ret < 0 are sadly acceptable for
+ * main() function due to backward compatibility.
+ * Like socket filter program may be written as:
+ * int bpf_prog(struct pt_regs *ctx)
+ * and never dereference that ctx in the program.
+ * 'struct pt_regs' is a type mismatch for socket
+ * filter that should be using 'struct __sk_buff'.
+ */
+ goto out;
}
- kvfree(env->explored_states);
+ ret = do_check(env);
+out:
+ /* check for NULL is necessary, since cur_state can be freed inside
+ * do_check() under memory pressure.
+ */
+ if (env->cur_state) {
+ free_verifier_state(env->cur_state, true);
+ env->cur_state = NULL;
+ }
+ while (!pop_stack(env, NULL, NULL));
+ free_states(env);
+ if (ret)
+ /* clean aux data in case subprog was rejected */
+ sanitize_insn_aux_data(env);
+ return ret;
}
+/* Verify all global functions in a BPF program one by one based on their BTF.
+ * All global functions must pass verification. Otherwise the whole program is rejected.
+ * Consider:
+ * int bar(int);
+ * int foo(int f)
+ * {
+ * return bar(f);
+ * }
+ * int bar(int b)
+ * {
+ * ...
+ * }
+ * foo() will be verified first for R1=any_scalar_value. During verification it
+ * will be assumed that bar() already verified successfully and call to bar()
+ * from foo() will be checked for type match only. Later bar() will be verified
+ * independently to check that it's safe for R1=any_scalar_value.
+ */
+static int do_check_subprogs(struct bpf_verifier_env *env)
+{
+ struct bpf_prog_aux *aux = env->prog->aux;
+ int i, ret;
+
+ if (!aux->func_info)
+ return 0;
+
+ for (i = 1; i < env->subprog_cnt; i++) {
+ if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL)
+ continue;
+ env->insn_idx = env->subprog_info[i].start;
+ WARN_ON_ONCE(env->insn_idx == 0);
+ ret = do_check_common(env, i);
+ if (ret) {
+ return ret;
+ } else if (env->log.level & BPF_LOG_LEVEL) {
+ verbose(env,
+ "Func#%d is safe for any args that match its prototype\n",
+ i);
+ }
+ }
+ return 0;
+}
+
+static int do_check_main(struct bpf_verifier_env *env)
+{
+ int ret;
+
+ env->insn_idx = 0;
+ ret = do_check_common(env, 0);
+ if (!ret)
+ env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
+ return ret;
+}
+
+
static void print_verification_stats(struct bpf_verifier_env *env)
{
int i;
@@ -9501,9 +9723,62 @@ static void print_verification_stats(struct bpf_verifier_env *env)
env->peak_states, env->longest_mark_read_walk);
}
+static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
+{
+ const struct btf_type *t, *func_proto;
+ const struct bpf_struct_ops *st_ops;
+ const struct btf_member *member;
+ struct bpf_prog *prog = env->prog;
+ u32 btf_id, member_idx;
+ const char *mname;
+
+ btf_id = prog->aux->attach_btf_id;
+ st_ops = bpf_struct_ops_find(btf_id);
+ if (!st_ops) {
+ verbose(env, "attach_btf_id %u is not a supported struct\n",
+ btf_id);
+ return -ENOTSUPP;
+ }
+
+ t = st_ops->type;
+ member_idx = prog->expected_attach_type;
+ if (member_idx >= btf_type_vlen(t)) {
+ verbose(env, "attach to invalid member idx %u of struct %s\n",
+ member_idx, st_ops->name);
+ return -EINVAL;
+ }
+
+ member = &btf_type_member(t)[member_idx];
+ mname = btf_name_by_offset(btf_vmlinux, member->name_off);
+ func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type,
+ NULL);
+ if (!func_proto) {
+ verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n",
+ mname, member_idx, st_ops->name);
+ return -EINVAL;
+ }
+
+ if (st_ops->check_member) {
+ int err = st_ops->check_member(t, member);
+
+ if (err) {
+ verbose(env, "attach to unsupported member %s of struct %s\n",
+ mname, st_ops->name);
+ return err;
+ }
+ }
+
+ prog->aux->attach_func_proto = func_proto;
+ prog->aux->attach_func_name = mname;
+ env->ops = st_ops->verifier_ops;
+
+ return 0;
+}
+
static int check_attach_btf_id(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog;
+ bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
struct bpf_prog *tgt_prog = prog->aux->linked_prog;
u32 btf_id = prog->aux->attach_btf_id;
const char prefix[] = "btf_trace_";
@@ -9516,7 +9791,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
long addr;
u64 key;
- if (prog->type != BPF_PROG_TYPE_TRACING)
+ if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
+ return check_struct_ops_btf_id(env);
+
+ if (prog->type != BPF_PROG_TYPE_TRACING && !prog_extension)
return 0;
if (!btf_id) {
@@ -9552,8 +9830,59 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
return -EINVAL;
}
conservative = aux->func_info_aux[subprog].unreliable;
+ if (prog_extension) {
+ if (conservative) {
+ verbose(env,
+ "Cannot replace static functions\n");
+ return -EINVAL;
+ }
+ if (!prog->jit_requested) {
+ verbose(env,
+ "Extension programs should be JITed\n");
+ return -EINVAL;
+ }
+ env->ops = bpf_verifier_ops[tgt_prog->type];
+ }
+ if (!tgt_prog->jited) {
+ verbose(env, "Can attach to only JITed progs\n");
+ return -EINVAL;
+ }
+ if (tgt_prog->type == prog->type) {
+ /* Cannot fentry/fexit another fentry/fexit program.
+ * Cannot attach program extension to another extension.
+ * It's ok to attach fentry/fexit to extension program.
+ */
+ verbose(env, "Cannot recursively attach\n");
+ return -EINVAL;
+ }
+ if (tgt_prog->type == BPF_PROG_TYPE_TRACING &&
+ prog_extension &&
+ (tgt_prog->expected_attach_type == BPF_TRACE_FENTRY ||
+ tgt_prog->expected_attach_type == BPF_TRACE_FEXIT)) {
+ /* Program extensions can extend all program types
+ * except fentry/fexit. The reason is the following.
+ * The fentry/fexit programs are used for performance
+ * analysis, stats and can be attached to any program
+ * type except themselves. When extension program is
+ * replacing XDP function it is necessary to allow
+ * performance analysis of all functions. Both original
+ * XDP program and its program extension. Hence
+ * attaching fentry/fexit to BPF_PROG_TYPE_EXT is
+ * allowed. If extending of fentry/fexit was allowed it
+ * would be possible to create long call chain
+ * fentry->extension->fentry->extension beyond
+ * reasonable stack size. Hence extending fentry is not
+ * allowed.
+ */
+ verbose(env, "Cannot extend fentry/fexit\n");
+ return -EINVAL;
+ }
key = ((u64)aux->id) << 32 | btf_id;
} else {
+ if (prog_extension) {
+ verbose(env, "Cannot replace kernel functions\n");
+ return -EINVAL;
+ }
key = btf_id;
}
@@ -9591,6 +9920,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
prog->aux->attach_func_proto = t;
prog->aux->attach_btf_trace = true;
return 0;
+ default:
+ if (!prog_extension)
+ return -EINVAL;
+ /* fallthrough */
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
if (!btf_type_is_func(t)) {
@@ -9598,6 +9931,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
btf_id);
return -EINVAL;
}
+ if (prog_extension &&
+ btf_check_type_match(env, prog, btf, t))
+ return -EINVAL;
t = btf_type_by_id(btf, t->type);
if (!btf_type_is_func_proto(t))
return -EINVAL;
@@ -9621,18 +9957,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
if (ret < 0)
goto out;
if (tgt_prog) {
- if (!tgt_prog->jited) {
- /* for now */
- verbose(env, "Can trace only JITed BPF progs\n");
- ret = -EINVAL;
- goto out;
- }
- if (tgt_prog->type == BPF_PROG_TYPE_TRACING) {
- /* prevent cycles */
- verbose(env, "Cannot recursively attach\n");
- ret = -EINVAL;
- goto out;
- }
if (subprog == 0)
addr = (long) tgt_prog->bpf_func;
else
@@ -9654,8 +9978,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
if (ret)
bpf_trampoline_put(tr);
return ret;
- default:
- return -EINVAL;
}
}
@@ -9725,10 +10047,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
goto skip_full_check;
}
- ret = check_attach_btf_id(env);
- if (ret)
- goto skip_full_check;
-
env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
env->strict_alignment = true;
@@ -9765,22 +10083,22 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
if (ret < 0)
goto skip_full_check;
+ ret = check_attach_btf_id(env);
+ if (ret)
+ goto skip_full_check;
+
ret = check_cfg(env);
if (ret < 0)
goto skip_full_check;
- ret = do_check(env);
- if (env->cur_state) {
- free_verifier_state(env->cur_state, true);
- env->cur_state = NULL;
- }
+ ret = do_check_subprogs(env);
+ ret = ret ?: do_check_main(env);
if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux))
ret = bpf_prog_offload_finalize(env);
skip_full_check:
- while (!pop_stack(env, NULL, NULL));
- free_states(env);
+ kvfree(env->explored_states);
if (ret == 0)
ret = check_max_stack_depth(env);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index a59cc98..4dc279e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1909,6 +1909,78 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
}
EXPORT_SYMBOL(__cpuhp_remove_state);
+#ifdef CONFIG_HOTPLUG_SMT
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = true;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = false;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ for_each_online_cpu(cpu) {
+ if (topology_is_primary_thread(cpu))
+ continue;
+ ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+ if (ret)
+ break;
+ /*
+ * As this needs to hold the cpu maps lock it's impossible
+ * to call device_offline() because that ends up calling
+ * cpu_down() which takes cpu maps lock. cpu maps lock
+ * needs to be held as this might race against in kernel
+ * abusers of the hotplug machinery (thermal management).
+ *
+ * So nothing would update device:offline state. That would
+ * leave the sysfs entry stale and prevent onlining after
+ * smt control has been changed to 'off' again. This is
+ * called under the sysfs hotplug lock, so it is properly
+ * serialized against the regular offline usage.
+ */
+ cpuhp_offline_cpu_device(cpu);
+ }
+ if (!ret)
+ cpu_smt_control = ctrlval;
+ cpu_maps_update_done();
+ return ret;
+}
+
+int cpuhp_smt_enable(void)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ cpu_smt_control = CPU_SMT_ENABLED;
+ for_each_present_cpu(cpu) {
+ /* Skip online CPUs and CPUs on offline nodes */
+ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+ continue;
+ ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+ if (ret)
+ break;
+ /* See comment in cpuhp_smt_disable() */
+ cpuhp_online_cpu_device(cpu);
+ }
+ cpu_maps_update_done();
+ return ret;
+}
+#endif
+
#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
static ssize_t show_cpuhp_state(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -2063,77 +2135,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
#ifdef CONFIG_HOTPLUG_SMT
-static void cpuhp_offline_cpu_device(unsigned int cpu)
-{
- struct device *dev = get_cpu_device(cpu);
-
- dev->offline = true;
- /* Tell user space about the state change */
- kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
-}
-
-static void cpuhp_online_cpu_device(unsigned int cpu)
-{
- struct device *dev = get_cpu_device(cpu);
-
- dev->offline = false;
- /* Tell user space about the state change */
- kobject_uevent(&dev->kobj, KOBJ_ONLINE);
-}
-
-int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
-{
- int cpu, ret = 0;
-
- cpu_maps_update_begin();
- for_each_online_cpu(cpu) {
- if (topology_is_primary_thread(cpu))
- continue;
- ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
- if (ret)
- break;
- /*
- * As this needs to hold the cpu maps lock it's impossible
- * to call device_offline() because that ends up calling
- * cpu_down() which takes cpu maps lock. cpu maps lock
- * needs to be held as this might race against in kernel
- * abusers of the hotplug machinery (thermal management).
- *
- * So nothing would update device:offline state. That would
- * leave the sysfs entry stale and prevent onlining after
- * smt control has been changed to 'off' again. This is
- * called under the sysfs hotplug lock, so it is properly
- * serialized against the regular offline usage.
- */
- cpuhp_offline_cpu_device(cpu);
- }
- if (!ret)
- cpu_smt_control = ctrlval;
- cpu_maps_update_done();
- return ret;
-}
-
-int cpuhp_smt_enable(void)
-{
- int cpu, ret = 0;
-
- cpu_maps_update_begin();
- cpu_smt_control = CPU_SMT_ENABLED;
- for_each_present_cpu(cpu) {
- /* Skip online CPUs and CPUs on offline nodes */
- if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
- continue;
- ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
- if (ret)
- break;
- /* See comment in cpuhp_smt_disable() */
- cpuhp_online_cpu_device(cpu);
- }
- cpu_maps_update_done();
- return ret;
-}
-
-
static ssize_t
__store_smt_control(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
diff --git a/kernel/cred.c b/kernel/cred.c
index c0a4c12..809a985 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -175,8 +175,8 @@ void exit_creds(struct task_struct *tsk)
put_cred(cred);
#ifdef CONFIG_KEYS_REQUEST_CACHE
- key_put(current->cached_requested_key);
- current->cached_requested_key = NULL;
+ key_put(tsk->cached_requested_key);
+ tsk->cached_requested_key = NULL;
#endif
}
@@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void)
new->magic = CRED_MAGIC;
#endif
- if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
+ if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
goto error;
return new;
@@ -282,7 +282,7 @@ struct cred *prepare_creds(void)
new->security = NULL;
#endif
- if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
validate_creds(new);
return new;
@@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
#ifdef CONFIG_SECURITY
new->security = NULL;
#endif
- if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
put_cred(old);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a1f8bde..2173c23 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11465,8 +11465,10 @@ SYSCALL_DEFINE5(perf_event_open,
}
}
- if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader))
+ if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) {
+ err = -EINVAL;
goto err_locked;
+ }
/*
* Must be under the same ctx::mutex as perf_install_in_context(),
diff --git a/kernel/exit.c b/kernel/exit.c
index bcbd598..2833ffb 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -517,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father,
}
write_unlock_irq(&tasklist_lock);
- if (unlikely(pid_ns == &init_pid_ns)) {
- panic("Attempted to kill init! exitcode=0x%08x\n",
- father->signal->group_exit_code ?: father->exit_code);
- }
list_for_each_entry_safe(p, n, dead, ptrace_entry) {
list_del_init(&p->ptrace_entry);
@@ -766,6 +762,14 @@ void __noreturn do_exit(long code)
acct_update_integrals(tsk);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
+ /*
+ * If the last thread of global init has exited, panic
+ * immediately to get a useable coredump.
+ */
+ if (unlikely(is_global_init(tsk)))
+ panic("Attempted to kill init! exitcode=0x%08x\n",
+ tsk->signal->group_exit_code ?: (int)code);
+
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk->signal);
diff --git a/kernel/fork.c b/kernel/fork.c
index 2508a4f..0808095 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2578,6 +2578,16 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
#endif
#ifdef __ARCH_WANT_SYS_CLONE3
+
+/*
+ * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from
+ * the registers containing the syscall arguments for clone. This doesn't work
+ * with clone3 since the TLS value is passed in clone_args instead.
+ */
+#ifndef CONFIG_HAVE_COPY_THREAD_TLS
+#error clone3 requires copy_thread_tls support in arch
+#endif
+
noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
struct clone_args __user *uargs,
size_t usize)
diff --git a/kernel/futex.c b/kernel/futex.c
index 03c518e..0cf84c8 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1178,6 +1178,7 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
/**
* wait_for_owner_exiting - Block until the owner has exited
+ * @ret: owner's current futex lock status
* @exiting: Pointer to the exiting task
*
* Caller must hold a refcount on @exiting.
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 32282e7..32406ef 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -482,7 +482,7 @@ static struct lock_trace *save_trace(void)
struct lock_trace *trace, *t2;
struct hlist_head *hash_head;
u32 hash;
- unsigned int max_entries;
+ int max_entries;
BUILD_BUG_ON_NOT_POWER_OF_2(STACK_TRACE_HASH_SIZE);
BUILD_BUG_ON(LOCK_TRACE_SIZE_IN_LONGS >= MAX_STACK_TRACE_ENTRIES);
@@ -490,10 +490,8 @@ static struct lock_trace *save_trace(void)
trace = (struct lock_trace *)(stack_trace + nr_stack_trace_entries);
max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries -
LOCK_TRACE_SIZE_IN_LONGS;
- trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3);
- if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES -
- LOCK_TRACE_SIZE_IN_LONGS - 1) {
+ if (max_entries <= 0) {
if (!debug_locks_off_graph_unlock())
return NULL;
@@ -502,6 +500,7 @@ static struct lock_trace *save_trace(void)
return NULL;
}
+ trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3);
hash = jhash(trace->entries, trace->nr_entries *
sizeof(trace->entries[0]), 0);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 44e6876..0d9b6be 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1226,8 +1226,8 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
* In this case, we attempt to acquire the lock again
* without sleeping.
*/
- if ((wstate == WRITER_HANDOFF) &&
- (rwsem_spin_on_owner(sem, 0) == OWNER_NULL))
+ if (wstate == WRITER_HANDOFF &&
+ rwsem_spin_on_owner(sem, RWSEM_NONSPINNABLE) == OWNER_NULL)
goto trylock_again;
/* Block until there are no active lockers. */
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 26b9168..d65f2d5 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1147,24 +1147,24 @@ void free_basic_memory_bitmaps(void)
void clear_free_pages(void)
{
-#ifdef CONFIG_PAGE_POISONING_ZERO
struct memory_bitmap *bm = free_pages_map;
unsigned long pfn;
if (WARN_ON(!(free_pages_map)))
return;
- memory_bm_position_reset(bm);
- pfn = memory_bm_next_pfn(bm);
- while (pfn != BM_END_OF_MAP) {
- if (pfn_valid(pfn))
- clear_highpage(pfn_to_page(pfn));
-
+ if (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) || want_init_on_free()) {
+ memory_bm_position_reset(bm);
pfn = memory_bm_next_pfn(bm);
+ while (pfn != BM_END_OF_MAP) {
+ if (pfn_valid(pfn))
+ clear_highpage(pfn_to_page(pfn));
+
+ pfn = memory_bm_next_pfn(bm);
+ }
+ memory_bm_position_reset(bm);
+ pr_info("free pages cleared after restore\n");
}
- memory_bm_position_reset(bm);
- pr_info("free pages cleared after restore\n");
-#endif /* PAGE_POISONING_ZERO */
}
/**
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index cb9ddcc..43d6179 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -264,12 +264,17 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
return ret;
}
-static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
+static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns,
+ unsigned int mode)
{
+ int ret;
+
if (mode & PTRACE_MODE_NOAUDIT)
- return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
+ ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT);
else
- return has_ns_capability(current, ns, CAP_SYS_PTRACE);
+ ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE);
+
+ return ret == 0;
}
/* Returns 0 on success, -errno on denial. */
@@ -321,7 +326,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
gid_eq(caller_gid, tcred->sgid) &&
gid_eq(caller_gid, tcred->gid))
goto ok;
- if (ptrace_has_cap(tcred->user_ns, mode))
+ if (ptrace_has_cap(cred, tcred->user_ns, mode))
goto ok;
rcu_read_unlock();
return -EPERM;
@@ -340,7 +345,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
mm = task->mm;
if (mm &&
((get_dumpable(mm) != SUID_DUMP_USER) &&
- !ptrace_has_cap(mm->user_ns, mode)))
+ !ptrace_has_cap(cred, mm->user_ns, mode)))
return -EPERM;
return security_ptrace_access_check(task, mode);
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 27c48eb..a4f86a9 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -310,6 +310,8 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
int ret;
if (flags & RSEQ_FLAG_UNREGISTER) {
+ if (flags & ~RSEQ_FLAG_UNREGISTER)
+ return -EINVAL;
/* Unregister rseq for current thread. */
if (current->rseq != rseq || !current->rseq)
return -EINVAL;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 12d2227..b6ea3dc 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1026,6 +1026,13 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
struct seccomp_notif unotif;
ssize_t ret;
+ /* Verify that we're not given garbage to keep struct extensible. */
+ ret = check_zeroed_user(buf, sizeof(unotif));
+ if (ret < 0)
+ return ret;
+ if (!ret)
+ return -EINVAL;
+
memset(&unotif, 0, sizeof(unotif));
ret = down_interruptible(&filter->notif->request);
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 13a0f2e..e2ac0e3 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
{
struct signal_struct *sig = tsk->signal;
- struct taskstats *stats;
+ struct taskstats *stats_new, *stats;
- if (sig->stats || thread_group_empty(tsk))
- goto ret;
+ /* Pairs with smp_store_release() below. */
+ stats = smp_load_acquire(&sig->stats);
+ if (stats || thread_group_empty(tsk))
+ return stats;
/* No problem if kmem_cache_zalloc() fails */
- stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
+ stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
spin_lock_irq(&tsk->sighand->siglock);
- if (!sig->stats) {
- sig->stats = stats;
- stats = NULL;
+ stats = sig->stats;
+ if (!stats) {
+ /*
+ * Pairs with smp_store_release() above and order the
+ * kmem_cache_zalloc().
+ */
+ smp_store_release(&sig->stats, stats_new);
+ stats = stats_new;
+ stats_new = NULL;
}
spin_unlock_irq(&tsk->sighand->siglock);
- if (stats)
- kmem_cache_free(taskstats_cache, stats);
-ret:
- return sig->stats;
+ if (stats_new)
+ kmem_cache_free(taskstats_cache, stats_new);
+
+ return stats;
}
/* Send pid data out on exit */
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 67df65f..20c65a7 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -151,6 +151,9 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
#ifdef CONFIG_COMPAT
COMPAT_SYS_NI(timer_create);
+#endif
+
+#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
COMPAT_SYS_NI(getitimer);
COMPAT_SYS_NI(setitimer);
#endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 8b192e6..a792d21 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -58,8 +58,9 @@ static void tick_do_update_jiffies64(ktime_t now)
/*
* Do a quick check without holding jiffies_lock:
+ * The READ_ONCE() pairs with two updates done later in this function.
*/
- delta = ktime_sub(now, last_jiffies_update);
+ delta = ktime_sub(now, READ_ONCE(last_jiffies_update));
if (delta < tick_period)
return;
@@ -70,8 +71,9 @@ static void tick_do_update_jiffies64(ktime_t now)
if (delta >= tick_period) {
delta = ktime_sub(delta, tick_period);
- last_jiffies_update = ktime_add(last_jiffies_update,
- tick_period);
+ /* Pairs with the lockless read in this function. */
+ WRITE_ONCE(last_jiffies_update,
+ ktime_add(last_jiffies_update, tick_period));
/* Slow path for long timeouts */
if (unlikely(delta >= tick_period)) {
@@ -79,8 +81,10 @@ static void tick_do_update_jiffies64(ktime_t now)
ticks = ktime_divns(delta, incr);
- last_jiffies_update = ktime_add_ns(last_jiffies_update,
- incr * ticks);
+ /* Pairs with the lockless read in this function. */
+ WRITE_ONCE(last_jiffies_update,
+ ktime_add_ns(last_jiffies_update,
+ incr * ticks));
}
do_timer(++ticks);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index e5ef4ae..19e793a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -703,6 +703,7 @@ struct send_signal_irq_work {
struct irq_work irq_work;
struct task_struct *task;
u32 sig;
+ enum pid_type type;
};
static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work);
@@ -712,10 +713,10 @@ static void do_bpf_send_signal(struct irq_work *entry)
struct send_signal_irq_work *work;
work = container_of(entry, struct send_signal_irq_work, irq_work);
- group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, PIDTYPE_TGID);
+ group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type);
}
-BPF_CALL_1(bpf_send_signal, u32, sig)
+static int bpf_send_signal_common(u32 sig, enum pid_type type)
{
struct send_signal_irq_work *work = NULL;
@@ -748,11 +749,17 @@ BPF_CALL_1(bpf_send_signal, u32, sig)
*/
work->task = current;
work->sig = sig;
+ work->type = type;
irq_work_queue(&work->irq_work);
return 0;
}
- return group_send_sig_info(sig, SEND_SIG_PRIV, current, PIDTYPE_TGID);
+ return group_send_sig_info(sig, SEND_SIG_PRIV, current, type);
+}
+
+BPF_CALL_1(bpf_send_signal, u32, sig)
+{
+ return bpf_send_signal_common(sig, PIDTYPE_TGID);
}
static const struct bpf_func_proto bpf_send_signal_proto = {
@@ -762,6 +769,18 @@ static const struct bpf_func_proto bpf_send_signal_proto = {
.arg1_type = ARG_ANYTHING,
};
+BPF_CALL_1(bpf_send_signal_thread, u32, sig)
+{
+ return bpf_send_signal_common(sig, PIDTYPE_PID);
+}
+
+static const struct bpf_func_proto bpf_send_signal_thread_proto = {
+ .func = bpf_send_signal_thread,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_ANYTHING,
+};
+
static const struct bpf_func_proto *
tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
@@ -822,6 +841,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
#endif
case BPF_FUNC_send_signal:
return &bpf_send_signal_proto;
+ case BPF_FUNC_send_signal_thread:
+ return &bpf_send_signal_thread_proto;
default:
return NULL;
}
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index a265973..1af321d 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -96,6 +96,20 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
return 0;
}
+/*
+ * Not all archs define MCOUNT_INSN_SIZE which is used to look for direct
+ * functions. But those archs currently don't support direct functions
+ * anyway, and ftrace_find_rec_direct() is just a stub for them.
+ * Define MCOUNT_INSN_SIZE to keep those archs compiling.
+ */
+#ifndef MCOUNT_INSN_SIZE
+/* Make sure this only works without direct calls */
+# ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+# error MCOUNT_INSN_SIZE not defined with direct calls enabled
+# endif
+# define MCOUNT_INSN_SIZE 0
+#endif
+
int function_graph_enter(unsigned long ret, unsigned long func,
unsigned long frame_pointer, unsigned long *retp)
{
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ac99a35..9bf1f2c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -526,8 +526,7 @@ static int function_stat_show(struct seq_file *m, void *v)
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- avg = rec->time;
- do_div(avg, rec->counter);
+ avg = div64_ul(rec->time, rec->counter);
if (tracing_thresh && (avg < tracing_thresh))
goto out;
#endif
@@ -553,7 +552,8 @@ static int function_stat_show(struct seq_file *m, void *v)
* Divide only 1000 for ns^2 -> us^2 conversion.
* trace_print_graph_duration will divide 1000 again.
*/
- do_div(stddev, rec->counter * (rec->counter - 1) * 1000);
+ stddev = div64_ul(stddev,
+ rec->counter * (rec->counter - 1) * 1000);
}
trace_seq_init(&s);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ddb7e7f..5b6ee4a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9420,6 +9420,11 @@ __init static int tracing_set_default_clock(void)
{
/* sched_clock_stable() is determined in late_initcall */
if (!trace_boot_clock && !sched_clock_stable()) {
+ if (security_locked_down(LOCKDOWN_TRACEFS)) {
+ pr_warn("Can not set tracing clock due to lockdown\n");
+ return -EPERM;
+ }
+
printk(KERN_WARNING
"Unstable clock detected, switching default tracing clock to \"global\"\n"
"If you want to keep using the local clock, then add:\n"
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index f62de5f..6ac35b9 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -116,6 +116,7 @@ struct hist_field {
struct ftrace_event_field *field;
unsigned long flags;
hist_field_fn_t fn;
+ unsigned int ref;
unsigned int size;
unsigned int offset;
unsigned int is_signed;
@@ -1766,11 +1767,13 @@ static struct hist_field *find_var(struct hist_trigger_data *hist_data,
struct event_trigger_data *test;
struct hist_field *hist_field;
+ lockdep_assert_held(&event_mutex);
+
hist_field = find_var_field(hist_data, var_name);
if (hist_field)
return hist_field;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
test_data = test->private_data;
hist_field = find_var_field(test_data, var_name);
@@ -1820,7 +1823,9 @@ static struct hist_field *find_file_var(struct trace_event_file *file,
struct event_trigger_data *test;
struct hist_field *hist_field;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
test_data = test->private_data;
hist_field = find_var_field(test_data, var_name);
@@ -2423,8 +2428,16 @@ static int contains_operator(char *str)
return field_op;
}
+static void get_hist_field(struct hist_field *hist_field)
+{
+ hist_field->ref++;
+}
+
static void __destroy_hist_field(struct hist_field *hist_field)
{
+ if (--hist_field->ref > 1)
+ return;
+
kfree(hist_field->var.name);
kfree(hist_field->name);
kfree(hist_field->type);
@@ -2466,6 +2479,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
if (!hist_field)
return NULL;
+ hist_field->ref = 1;
+
hist_field->hist_data = hist_data;
if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS)
@@ -2661,6 +2676,17 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data,
{
unsigned long flags = HIST_FIELD_FL_VAR_REF;
struct hist_field *ref_field;
+ int i;
+
+ /* Check if the variable already exists */
+ for (i = 0; i < hist_data->n_var_refs; i++) {
+ ref_field = hist_data->var_refs[i];
+ if (ref_field->var.idx == var_field->var.idx &&
+ ref_field->var.hist_data == var_field->hist_data) {
+ get_hist_field(ref_field);
+ return ref_field;
+ }
+ }
ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL);
if (ref_field) {
@@ -3115,7 +3141,9 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data,
{
struct event_trigger_data *test;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (test->private_data == hist_data)
return test->filter_str;
@@ -3166,9 +3194,11 @@ find_compatible_hist(struct hist_trigger_data *target_hist_data,
struct event_trigger_data *test;
unsigned int n_keys;
+ lockdep_assert_held(&event_mutex);
+
n_keys = target_hist_data->n_fields - target_hist_data->n_vals;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
hist_data = test->private_data;
@@ -5528,7 +5558,7 @@ static int hist_show(struct seq_file *m, void *v)
goto out_unlock;
}
- list_for_each_entry_rcu(data, &event_file->triggers, list) {
+ list_for_each_entry(data, &event_file->triggers, list) {
if (data->cmd_ops->trigger_type == ETT_EVENT_HIST)
hist_trigger_show(m, data, n++);
}
@@ -5921,7 +5951,9 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
if (hist_data->attrs->name && !named_data)
goto new;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (!hist_trigger_match(data, test, named_data, false))
continue;
@@ -6005,10 +6037,12 @@ static bool have_hist_trigger_match(struct event_trigger_data *data,
struct event_trigger_data *test, *named_data = NULL;
bool match = false;
+ lockdep_assert_held(&event_mutex);
+
if (hist_data->attrs->name)
named_data = find_named_trigger(hist_data->attrs->name);
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (hist_trigger_match(data, test, named_data, false)) {
match = true;
@@ -6026,10 +6060,12 @@ static bool hist_trigger_check_refs(struct event_trigger_data *data,
struct hist_trigger_data *hist_data = data->private_data;
struct event_trigger_data *test, *named_data = NULL;
+ lockdep_assert_held(&event_mutex);
+
if (hist_data->attrs->name)
named_data = find_named_trigger(hist_data->attrs->name);
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (!hist_trigger_match(data, test, named_data, false))
continue;
@@ -6051,10 +6087,12 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops,
struct event_trigger_data *test, *named_data = NULL;
bool unregistered = false;
+ lockdep_assert_held(&event_mutex);
+
if (hist_data->attrs->name)
named_data = find_named_trigger(hist_data->attrs->name);
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (!hist_trigger_match(data, test, named_data, false))
continue;
@@ -6080,7 +6118,9 @@ static bool hist_file_check_refs(struct trace_event_file *file)
struct hist_trigger_data *hist_data;
struct event_trigger_data *test;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
hist_data = test->private_data;
if (check_var_refs(hist_data))
@@ -6323,7 +6363,8 @@ hist_enable_trigger(struct event_trigger_data *data, void *rec,
struct enable_trigger_data *enable_data = data->private_data;
struct event_trigger_data *test;
- list_for_each_entry_rcu(test, &enable_data->file->triggers, list) {
+ list_for_each_entry_rcu(test, &enable_data->file->triggers, list,
+ lockdep_is_held(&event_mutex)) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
if (enable_data->enable)
test->paused = false;
diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c
index d45079e..22bcf7c 100644
--- a/kernel/trace/trace_events_inject.c
+++ b/kernel/trace/trace_events_inject.c
@@ -195,7 +195,7 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry)
unsigned long irq_flags;
void *entry = NULL;
int entry_size;
- u64 val;
+ u64 val = 0;
int len;
entry = trace_alloc_entry(call, &entry_size);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 2cd53ca..40106ff 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -501,7 +501,9 @@ void update_cond_flag(struct trace_event_file *file)
struct event_trigger_data *data;
bool set_cond = false;
- list_for_each_entry_rcu(data, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(data, &file->triggers, list) {
if (data->filter || event_command_post_trigger(data->cmd_ops) ||
event_command_needs_rec(data->cmd_ops)) {
set_cond = true;
@@ -536,7 +538,9 @@ static int register_trigger(char *glob, struct event_trigger_ops *ops,
struct event_trigger_data *test;
int ret = 0;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) {
ret = -EEXIST;
goto out;
@@ -581,7 +585,9 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
struct event_trigger_data *data;
bool unregistered = false;
- list_for_each_entry_rcu(data, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(data, &file->triggers, list) {
if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
unregistered = true;
list_del_rcu(&data->list);
@@ -1497,7 +1503,9 @@ int event_enable_register_trigger(char *glob,
struct event_trigger_data *test;
int ret = 0;
- list_for_each_entry_rcu(test, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(test, &file->triggers, list) {
test_enable_data = test->private_data;
if (test_enable_data &&
(test->cmd_ops->trigger_type ==
@@ -1537,7 +1545,9 @@ void event_enable_unregister_trigger(char *glob,
struct event_trigger_data *data;
bool unregistered = false;
- list_for_each_entry_rcu(data, &file->triggers, list) {
+ lockdep_assert_held(&event_mutex);
+
+ list_for_each_entry(data, &file->triggers, list) {
enable_data = data->private_data;
if (enable_data &&
(data->cmd_ops->trigger_type ==
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7f89026..3f54dc2 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -290,7 +290,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
INIT_HLIST_NODE(&tk->rp.kp.hlist);
INIT_LIST_HEAD(&tk->rp.kp.list);
- ret = trace_probe_init(&tk->tp, event, group);
+ ret = trace_probe_init(&tk->tp, event, group, false);
if (ret < 0)
goto error;
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 905b10a..9ae87be 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -984,15 +984,19 @@ void trace_probe_cleanup(struct trace_probe *tp)
}
int trace_probe_init(struct trace_probe *tp, const char *event,
- const char *group)
+ const char *group, bool alloc_filter)
{
struct trace_event_call *call;
+ size_t size = sizeof(struct trace_probe_event);
int ret = 0;
if (!event || !group)
return -EINVAL;
- tp->event = kzalloc(sizeof(struct trace_probe_event), GFP_KERNEL);
+ if (alloc_filter)
+ size += sizeof(struct trace_uprobe_filter);
+
+ tp->event = kzalloc(size, GFP_KERNEL);
if (!tp->event)
return -ENOMEM;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 4ee7037..a0ff9e2 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -223,6 +223,12 @@ struct probe_arg {
const struct fetch_type *type; /* Type of this argument */
};
+struct trace_uprobe_filter {
+ rwlock_t rwlock;
+ int nr_systemwide;
+ struct list_head perf_events;
+};
+
/* Event call and class holder */
struct trace_probe_event {
unsigned int flags; /* For TP_FLAG_* */
@@ -230,6 +236,7 @@ struct trace_probe_event {
struct trace_event_call call;
struct list_head files;
struct list_head probes;
+ struct trace_uprobe_filter filter[0];
};
struct trace_probe {
@@ -322,7 +329,7 @@ static inline bool trace_probe_has_single_file(struct trace_probe *tp)
}
int trace_probe_init(struct trace_probe *tp, const char *event,
- const char *group);
+ const char *group, bool alloc_filter);
void trace_probe_cleanup(struct trace_probe *tp);
int trace_probe_append(struct trace_probe *tp, struct trace_probe *to);
void trace_probe_unlink(struct trace_probe *tp);
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 5e43b96..617e297 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -630,7 +630,7 @@ static void start_wakeup_tracer(struct trace_array *tr)
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_migrate_task\n");
- return;
+ goto fail_deprobe_sched_switch;
}
wakeup_reset(tr);
@@ -648,6 +648,8 @@ static void start_wakeup_tracer(struct trace_array *tr)
printk(KERN_ERR "failed to start wakeup tracer\n");
return;
+fail_deprobe_sched_switch:
+ unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
fail_deprobe_wake_new:
unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
fail_deprobe:
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index 344e4c1..87de6ed 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -381,7 +381,7 @@ int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str,
int prefix_type, int rowsize, int groupsize,
const void *buf, size_t len, bool ascii)
{
- unsigned int save_len = s->seq.len;
+ unsigned int save_len = s->seq.len;
if (s->full)
return 0;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 4df9a20..c557f42 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -283,6 +283,11 @@ static void check_stack(unsigned long ip, unsigned long *stack)
local_irq_restore(flags);
}
+/* Some archs may not define MCOUNT_INSN_SIZE */
+#ifndef MCOUNT_INSN_SIZE
+# define MCOUNT_INSN_SIZE 0
+#endif
+
static void
stack_trace_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *pt_regs)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 352073d..2619bc5 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -34,12 +34,6 @@ struct uprobe_trace_entry_head {
#define DATAOF_TRACE_ENTRY(entry, is_return) \
((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return))
-struct trace_uprobe_filter {
- rwlock_t rwlock;
- int nr_systemwide;
- struct list_head perf_events;
-};
-
static int trace_uprobe_create(int argc, const char **argv);
static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev);
static int trace_uprobe_release(struct dyn_event *ev);
@@ -60,7 +54,6 @@ static struct dyn_event_operations trace_uprobe_ops = {
*/
struct trace_uprobe {
struct dyn_event devent;
- struct trace_uprobe_filter filter;
struct uprobe_consumer consumer;
struct path path;
struct inode *inode;
@@ -351,7 +344,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
if (!tu)
return ERR_PTR(-ENOMEM);
- ret = trace_probe_init(&tu->tp, event, group);
+ ret = trace_probe_init(&tu->tp, event, group, true);
if (ret < 0)
goto error;
@@ -359,7 +352,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
tu->consumer.handler = uprobe_dispatcher;
if (is_ret)
tu->consumer.ret_handler = uretprobe_dispatcher;
- init_trace_uprobe_filter(&tu->filter);
+ init_trace_uprobe_filter(tu->tp.event->filter);
return tu;
error:
@@ -1067,13 +1060,14 @@ static void __probe_event_disable(struct trace_probe *tp)
struct trace_probe *pos;
struct trace_uprobe *tu;
+ tu = container_of(tp, struct trace_uprobe, tp);
+ WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter));
+
list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
tu = container_of(pos, struct trace_uprobe, tp);
if (!tu->inode)
continue;
- WARN_ON(!uprobe_filter_is_empty(&tu->filter));
-
uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
tu->inode = NULL;
}
@@ -1108,7 +1102,7 @@ static int probe_event_enable(struct trace_event_call *call,
}
tu = container_of(tp, struct trace_uprobe, tp);
- WARN_ON(!uprobe_filter_is_empty(&tu->filter));
+ WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter));
if (enabled)
return 0;
@@ -1205,39 +1199,39 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
}
static inline bool
-uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
+trace_uprobe_filter_event(struct trace_uprobe_filter *filter,
+ struct perf_event *event)
{
- return __uprobe_perf_filter(&tu->filter, event->hw.target->mm);
+ return __uprobe_perf_filter(filter, event->hw.target->mm);
}
-static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
+static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter,
+ struct perf_event *event)
{
bool done;
- write_lock(&tu->filter.rwlock);
+ write_lock(&filter->rwlock);
if (event->hw.target) {
list_del(&event->hw.tp_list);
- done = tu->filter.nr_systemwide ||
+ done = filter->nr_systemwide ||
(event->hw.target->flags & PF_EXITING) ||
- uprobe_filter_event(tu, event);
+ trace_uprobe_filter_event(filter, event);
} else {
- tu->filter.nr_systemwide--;
- done = tu->filter.nr_systemwide;
+ filter->nr_systemwide--;
+ done = filter->nr_systemwide;
}
- write_unlock(&tu->filter.rwlock);
+ write_unlock(&filter->rwlock);
- if (!done)
- return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
-
- return 0;
+ return done;
}
-static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
+/* This returns true if the filter always covers target mm */
+static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter,
+ struct perf_event *event)
{
bool done;
- int err;
- write_lock(&tu->filter.rwlock);
+ write_lock(&filter->rwlock);
if (event->hw.target) {
/*
* event->parent != NULL means copy_process(), we can avoid
@@ -1247,28 +1241,21 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
* attr.enable_on_exec means that exec/mmap will install the
* breakpoints we need.
*/
- done = tu->filter.nr_systemwide ||
+ done = filter->nr_systemwide ||
event->parent || event->attr.enable_on_exec ||
- uprobe_filter_event(tu, event);
- list_add(&event->hw.tp_list, &tu->filter.perf_events);
+ trace_uprobe_filter_event(filter, event);
+ list_add(&event->hw.tp_list, &filter->perf_events);
} else {
- done = tu->filter.nr_systemwide;
- tu->filter.nr_systemwide++;
+ done = filter->nr_systemwide;
+ filter->nr_systemwide++;
}
- write_unlock(&tu->filter.rwlock);
+ write_unlock(&filter->rwlock);
- err = 0;
- if (!done) {
- err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
- if (err)
- uprobe_perf_close(tu, event);
- }
- return err;
+ return done;
}
-static int uprobe_perf_multi_call(struct trace_event_call *call,
- struct perf_event *event,
- int (*op)(struct trace_uprobe *tu, struct perf_event *event))
+static int uprobe_perf_close(struct trace_event_call *call,
+ struct perf_event *event)
{
struct trace_probe *pos, *tp;
struct trace_uprobe *tu;
@@ -1278,25 +1265,59 @@ static int uprobe_perf_multi_call(struct trace_event_call *call,
if (WARN_ON_ONCE(!tp))
return -ENODEV;
+ tu = container_of(tp, struct trace_uprobe, tp);
+ if (trace_uprobe_filter_remove(tu->tp.event->filter, event))
+ return 0;
+
list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
tu = container_of(pos, struct trace_uprobe, tp);
- ret = op(tu, event);
+ ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
if (ret)
break;
}
return ret;
}
+
+static int uprobe_perf_open(struct trace_event_call *call,
+ struct perf_event *event)
+{
+ struct trace_probe *pos, *tp;
+ struct trace_uprobe *tu;
+ int err = 0;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENODEV;
+
+ tu = container_of(tp, struct trace_uprobe, tp);
+ if (trace_uprobe_filter_add(tu->tp.event->filter, event))
+ return 0;
+
+ list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+ err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+ if (err) {
+ uprobe_perf_close(call, event);
+ break;
+ }
+ }
+
+ return err;
+}
+
static bool uprobe_perf_filter(struct uprobe_consumer *uc,
enum uprobe_filter_ctx ctx, struct mm_struct *mm)
{
+ struct trace_uprobe_filter *filter;
struct trace_uprobe *tu;
int ret;
tu = container_of(uc, struct trace_uprobe, consumer);
- read_lock(&tu->filter.rwlock);
- ret = __uprobe_perf_filter(&tu->filter, mm);
- read_unlock(&tu->filter.rwlock);
+ filter = tu->tp.event->filter;
+
+ read_lock(&filter->rwlock);
+ ret = __uprobe_perf_filter(filter, mm);
+ read_unlock(&filter->rwlock);
return ret;
}
@@ -1419,10 +1440,10 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type,
return 0;
case TRACE_REG_PERF_OPEN:
- return uprobe_perf_multi_call(event, data, uprobe_perf_open);
+ return uprobe_perf_open(event, data);
case TRACE_REG_PERF_CLOSE:
- return uprobe_perf_multi_call(event, data, uprobe_perf_close);
+ return uprobe_perf_close(event, data);
#endif
default:
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 4250519..6e175fb 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -168,6 +168,72 @@ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src,
}
EXPORT_SYMBOL(__bitmap_shift_left);
+/**
+ * bitmap_cut() - remove bit region from bitmap and right shift remaining bits
+ * @dst: destination bitmap, might overlap with src
+ * @src: source bitmap
+ * @first: start bit of region to be removed
+ * @cut: number of bits to remove
+ * @nbits: bitmap size, in bits
+ *
+ * Set the n-th bit of @dst iff the n-th bit of @src is set and
+ * n is less than @first, or the m-th bit of @src is set for any
+ * m such that @first <= n < nbits, and m = n + @cut.
+ *
+ * In pictures, example for a big-endian 32-bit architecture:
+ *
+ * @src:
+ * 31 63
+ * | |
+ * 10000000 11000001 11110010 00010101 10000000 11000001 01110010 00010101
+ * | | | |
+ * 16 14 0 32
+ *
+ * if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is:
+ *
+ * 31 63
+ * | |
+ * 10110000 00011000 00110010 00010101 00010000 00011000 00101110 01000010
+ * | | |
+ * 14 (bit 17 0 32
+ * from @src)
+ *
+ * Note that @dst and @src might overlap partially or entirely.
+ *
+ * This is implemented in the obvious way, with a shift and carry
+ * step for each moved bit. Optimisation is left as an exercise
+ * for the compiler.
+ */
+void bitmap_cut(unsigned long *dst, const unsigned long *src,
+ unsigned int first, unsigned int cut, unsigned int nbits)
+{
+ unsigned int len = BITS_TO_LONGS(nbits);
+ unsigned long keep = 0, carry;
+ int i;
+
+ memmove(dst, src, len * sizeof(*dst));
+
+ if (first % BITS_PER_LONG) {
+ keep = src[first / BITS_PER_LONG] &
+ (~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG));
+ }
+
+ while (cut--) {
+ for (i = first / BITS_PER_LONG; i < len; i++) {
+ if (i < len - 1)
+ carry = dst[i + 1] & 1UL;
+ else
+ carry = 0;
+
+ dst[i] = (dst[i] >> 1) | (carry << (BITS_PER_LONG - 1));
+ }
+ }
+
+ dst[first / BITS_PER_LONG] &= ~0UL << (first % BITS_PER_LONG);
+ dst[first / BITS_PER_LONG] |= keep;
+}
+EXPORT_SYMBOL(bitmap_cut);
+
int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index dccb95a..706020b 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -30,13 +30,6 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src,
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
unsigned long res = 0;
- /*
- * Truncate 'max' to the user-specified limit, so that
- * we only have one limit we need to check in the loop
- */
- if (max > count)
- max = count;
-
if (IS_UNALIGNED(src, dst))
goto byte_at_a_time;
@@ -114,6 +107,13 @@ long strncpy_from_user(char *dst, const char __user *src, long count)
unsigned long max = max_addr - src_addr;
long retval;
+ /*
+ * Truncate 'max' to the user-specified limit, so that
+ * we only have one limit we need to check in the loop
+ */
+ if (max > count)
+ max = count;
+
kasan_check_write(dst, count);
check_object_size(dst, count, false);
if (user_access_begin(src, max)) {
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index 6c0005d..41670d4 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -27,13 +27,6 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count,
unsigned long c;
/*
- * Truncate 'max' to the user-specified limit, so that
- * we only have one limit we need to check in the loop
- */
- if (max > count)
- max = count;
-
- /*
* Do everything aligned. But that means that we
* need to also expand the maximum..
*/
@@ -109,6 +102,13 @@ long strnlen_user(const char __user *str, long count)
unsigned long max = max_addr - src_addr;
long retval;
+ /*
+ * Truncate 'max' to the user-specified limit, so that
+ * we only have one limit we need to check in the loop
+ */
+ if (max > count)
+ max = count;
+
if (user_access_begin(str, max)) {
retval = do_strnlen_user(str, count, max);
user_access_end();
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 7df4f7f..55c14e8 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -2,6 +2,7 @@
/*
* test_xarray.c: Test the XArray API
* Copyright (c) 2017-2018 Microsoft Corporation
+ * Copyright (c) 2019-2020 Oracle
* Author: Matthew Wilcox <willy@infradead.org>
*/
@@ -902,28 +903,34 @@ static noinline void check_store_iter(struct xarray *xa)
XA_BUG_ON(xa, !xa_empty(xa));
}
-static noinline void check_multi_find(struct xarray *xa)
+static noinline void check_multi_find_1(struct xarray *xa, unsigned order)
{
#ifdef CONFIG_XARRAY_MULTI
+ unsigned long multi = 3 << order;
+ unsigned long next = 4 << order;
unsigned long index;
- xa_store_order(xa, 12, 2, xa_mk_value(12), GFP_KERNEL);
- XA_BUG_ON(xa, xa_store_index(xa, 16, GFP_KERNEL) != NULL);
+ xa_store_order(xa, multi, order, xa_mk_value(multi), GFP_KERNEL);
+ XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL) != NULL);
+ XA_BUG_ON(xa, xa_store_index(xa, next + 1, GFP_KERNEL) != NULL);
index = 0;
XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) !=
- xa_mk_value(12));
- XA_BUG_ON(xa, index != 12);
- index = 13;
+ xa_mk_value(multi));
+ XA_BUG_ON(xa, index != multi);
+ index = multi + 1;
XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) !=
- xa_mk_value(12));
- XA_BUG_ON(xa, (index < 12) || (index >= 16));
+ xa_mk_value(multi));
+ XA_BUG_ON(xa, (index < multi) || (index >= next));
XA_BUG_ON(xa, xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT) !=
- xa_mk_value(16));
- XA_BUG_ON(xa, index != 16);
+ xa_mk_value(next));
+ XA_BUG_ON(xa, index != next);
+ XA_BUG_ON(xa, xa_find_after(xa, &index, next, XA_PRESENT) != NULL);
+ XA_BUG_ON(xa, index != next);
- xa_erase_index(xa, 12);
- xa_erase_index(xa, 16);
+ xa_erase_index(xa, multi);
+ xa_erase_index(xa, next);
+ xa_erase_index(xa, next + 1);
XA_BUG_ON(xa, !xa_empty(xa));
#endif
}
@@ -1046,12 +1053,33 @@ static noinline void check_find_3(struct xarray *xa)
xa_destroy(xa);
}
+static noinline void check_find_4(struct xarray *xa)
+{
+ unsigned long index = 0;
+ void *entry;
+
+ xa_store_index(xa, ULONG_MAX, GFP_KERNEL);
+
+ entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT);
+ XA_BUG_ON(xa, entry != xa_mk_index(ULONG_MAX));
+
+ entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT);
+ XA_BUG_ON(xa, entry);
+
+ xa_erase_index(xa, ULONG_MAX);
+}
+
static noinline void check_find(struct xarray *xa)
{
+ unsigned i;
+
check_find_1(xa);
check_find_2(xa);
check_find_3(xa);
- check_multi_find(xa);
+ check_find_4(xa);
+
+ for (i = 2; i < 10; i++)
+ check_multi_find_1(xa, i);
check_multi_find_2(xa);
}
@@ -1132,6 +1160,27 @@ static noinline void check_move_tiny(struct xarray *xa)
XA_BUG_ON(xa, !xa_empty(xa));
}
+static noinline void check_move_max(struct xarray *xa)
+{
+ XA_STATE(xas, xa, 0);
+
+ xa_store_index(xa, ULONG_MAX, GFP_KERNEL);
+ rcu_read_lock();
+ XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != xa_mk_index(ULONG_MAX));
+ XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != NULL);
+ rcu_read_unlock();
+
+ xas_set(&xas, 0);
+ rcu_read_lock();
+ XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != xa_mk_index(ULONG_MAX));
+ xas_pause(&xas);
+ XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != NULL);
+ rcu_read_unlock();
+
+ xa_erase_index(xa, ULONG_MAX);
+ XA_BUG_ON(xa, !xa_empty(xa));
+}
+
static noinline void check_move_small(struct xarray *xa, unsigned long idx)
{
XA_STATE(xas, xa, 0);
@@ -1240,6 +1289,7 @@ static noinline void check_move(struct xarray *xa)
xa_destroy(xa);
check_move_tiny(xa);
+ check_move_max(xa);
for (i = 0; i < 16; i++)
check_move_small(xa, 1UL << i);
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 9ecfd3b..42bd8ab 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -221,6 +221,7 @@ int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res)
return 0;
}
+static __maybe_unused
int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res)
{
int ret = __cvdso_clock_getres_common(clock, res);
diff --git a/lib/xarray.c b/lib/xarray.c
index 1237c21..1d9fab7 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1,7 +1,8 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* XArray implementation
- * Copyright (c) 2017 Microsoft Corporation
+ * Copyright (c) 2017-2018 Microsoft Corporation
+ * Copyright (c) 2018-2020 Oracle
* Author: Matthew Wilcox <willy@infradead.org>
*/
@@ -967,6 +968,7 @@ void xas_pause(struct xa_state *xas)
if (xas_invalid(xas))
return;
+ xas->xa_node = XAS_RESTART;
if (node) {
unsigned int offset = xas->xa_offset;
while (++offset < XA_CHUNK_SIZE) {
@@ -974,10 +976,11 @@ void xas_pause(struct xa_state *xas)
break;
}
xas->xa_index += (offset - xas->xa_offset) << node->shift;
+ if (xas->xa_index == 0)
+ xas->xa_node = XAS_BOUNDS;
} else {
xas->xa_index++;
}
- xas->xa_node = XAS_RESTART;
}
EXPORT_SYMBOL_GPL(xas_pause);
@@ -1079,13 +1082,15 @@ void *xas_find(struct xa_state *xas, unsigned long max)
{
void *entry;
- if (xas_error(xas))
+ if (xas_error(xas) || xas->xa_node == XAS_BOUNDS)
return NULL;
+ if (xas->xa_index > max)
+ return set_bounds(xas);
if (!xas->xa_node) {
xas->xa_index = 1;
return set_bounds(xas);
- } else if (xas_top(xas->xa_node)) {
+ } else if (xas->xa_node == XAS_RESTART) {
entry = xas_load(xas);
if (entry || xas_not_node(xas->xa_node))
return entry;
@@ -1150,6 +1155,8 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark)
if (xas_error(xas))
return NULL;
+ if (xas->xa_index > max)
+ goto max;
if (!xas->xa_node) {
xas->xa_index = 1;
@@ -1824,6 +1831,17 @@ void *xa_find(struct xarray *xa, unsigned long *indexp,
}
EXPORT_SYMBOL(xa_find);
+static bool xas_sibling(struct xa_state *xas)
+{
+ struct xa_node *node = xas->xa_node;
+ unsigned long mask;
+
+ if (!node)
+ return false;
+ mask = (XA_CHUNK_SIZE << node->shift) - 1;
+ return (xas->xa_index & mask) > (xas->xa_offset << node->shift);
+}
+
/**
* xa_find_after() - Search the XArray for a present entry.
* @xa: XArray.
@@ -1847,21 +1865,20 @@ void *xa_find_after(struct xarray *xa, unsigned long *indexp,
XA_STATE(xas, xa, *indexp + 1);
void *entry;
+ if (xas.xa_index == 0)
+ return NULL;
+
rcu_read_lock();
for (;;) {
if ((__force unsigned int)filter < XA_MAX_MARKS)
entry = xas_find_marked(&xas, max, filter);
else
entry = xas_find(&xas, max);
- if (xas.xa_node == XAS_BOUNDS)
+
+ if (xas_invalid(&xas))
break;
- if (xas.xa_shift) {
- if (xas.xa_index & ((1UL << xas.xa_shift) - 1))
- continue;
- } else {
- if (xas.xa_offset < (xas.xa_index & XA_CHUNK_MASK))
- continue;
- }
+ if (xas_sibling(&xas))
+ continue;
if (!xas_retry(&xas, entry))
break;
}
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index 7dd602d..ad9d5b1 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -26,6 +26,7 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
unsigned long i, nr_pages, addr, next;
int nr;
struct page **pages;
+ int ret = 0;
if (gup->size > ULONG_MAX)
return -EINVAL;
@@ -63,7 +64,9 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
NULL);
break;
default:
- return -1;
+ kvfree(pages);
+ ret = -EINVAL;
+ goto out;
}
if (nr <= 0)
@@ -85,7 +88,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
gup->put_delta_usec = ktime_us_delta(end_time, start_time);
kvfree(pages);
- return 0;
+out:
+ return ret;
}
static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 41a0fbd..a880932 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -527,13 +527,13 @@ void prep_transhuge_page(struct page *page)
set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
}
-static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
+static unsigned long __thp_get_unmapped_area(struct file *filp,
+ unsigned long addr, unsigned long len,
loff_t off, unsigned long flags, unsigned long size)
{
- unsigned long addr;
loff_t off_end = off + len;
loff_t off_align = round_up(off, size);
- unsigned long len_pad;
+ unsigned long len_pad, ret;
if (off_end <= off_align || (off_end - off_align) < size)
return 0;
@@ -542,30 +542,40 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long le
if (len_pad < len || (off + len_pad) < off)
return 0;
- addr = current->mm->get_unmapped_area(filp, 0, len_pad,
+ ret = current->mm->get_unmapped_area(filp, addr, len_pad,
off >> PAGE_SHIFT, flags);
- if (IS_ERR_VALUE(addr))
+
+ /*
+ * The failure might be due to length padding. The caller will retry
+ * without the padding.
+ */
+ if (IS_ERR_VALUE(ret))
return 0;
- addr += (off - addr) & (size - 1);
- return addr;
+ /*
+ * Do not try to align to THP boundary if allocation at the address
+ * hint succeeds.
+ */
+ if (ret == addr)
+ return addr;
+
+ ret += (off - ret) & (size - 1);
+ return ret;
}
unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
+ unsigned long ret;
loff_t off = (loff_t)pgoff << PAGE_SHIFT;
- if (addr)
- goto out;
if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD))
goto out;
- addr = __thp_get_unmapped_area(filp, len, off, flags, PMD_SIZE);
- if (addr)
- return addr;
-
- out:
+ ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE);
+ if (ret)
+ return ret;
+out:
return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
}
EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ac65bb5..dd8737a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -27,6 +27,7 @@
#include <linux/swapops.h>
#include <linux/jhash.h>
#include <linux/numa.h>
+#include <linux/llist.h>
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -1136,7 +1137,7 @@ static inline void ClearPageHugeTemporary(struct page *page)
page[2].mapping = NULL;
}
-void free_huge_page(struct page *page)
+static void __free_huge_page(struct page *page)
{
/*
* Can't pass hstate in here because it is called from the
@@ -1199,6 +1200,54 @@ void free_huge_page(struct page *page)
spin_unlock(&hugetlb_lock);
}
+/*
+ * As free_huge_page() can be called from a non-task context, we have
+ * to defer the actual freeing in a workqueue to prevent potential
+ * hugetlb_lock deadlock.
+ *
+ * free_hpage_workfn() locklessly retrieves the linked list of pages to
+ * be freed and frees them one-by-one. As the page->mapping pointer is
+ * going to be cleared in __free_huge_page() anyway, it is reused as the
+ * llist_node structure of a lockless linked list of huge pages to be freed.
+ */
+static LLIST_HEAD(hpage_freelist);
+
+static void free_hpage_workfn(struct work_struct *work)
+{
+ struct llist_node *node;
+ struct page *page;
+
+ node = llist_del_all(&hpage_freelist);
+
+ while (node) {
+ page = container_of((struct address_space **)node,
+ struct page, mapping);
+ node = node->next;
+ __free_huge_page(page);
+ }
+}
+static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
+
+void free_huge_page(struct page *page)
+{
+ /*
+ * Defer freeing if in non-task context to avoid hugetlb_lock deadlock.
+ */
+ if (!in_task()) {
+ /*
+ * Only call schedule_work() if hpage_freelist is previously
+ * empty. Otherwise, schedule_work() had been called but the
+ * workfn hasn't retrieved the list yet.
+ */
+ if (llist_add((struct llist_node *)&page->mapping,
+ &hpage_freelist))
+ schedule_work(&free_hpage_work);
+ return;
+ }
+
+ __free_huge_page(page);
+}
+
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
INIT_LIST_HEAD(&page->lru);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c5b5f74..6c83cf4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3287,49 +3287,34 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
}
}
-static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg, bool slab_only)
+static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg)
{
- unsigned long stat[MEMCG_NR_STAT];
+ unsigned long stat[MEMCG_NR_STAT] = {0};
struct mem_cgroup *mi;
int node, cpu, i;
- int min_idx, max_idx;
-
- if (slab_only) {
- min_idx = NR_SLAB_RECLAIMABLE;
- max_idx = NR_SLAB_UNRECLAIMABLE;
- } else {
- min_idx = 0;
- max_idx = MEMCG_NR_STAT;
- }
-
- for (i = min_idx; i < max_idx; i++)
- stat[i] = 0;
for_each_online_cpu(cpu)
- for (i = min_idx; i < max_idx; i++)
+ for (i = 0; i < MEMCG_NR_STAT; i++)
stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu);
for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
- for (i = min_idx; i < max_idx; i++)
+ for (i = 0; i < MEMCG_NR_STAT; i++)
atomic_long_add(stat[i], &mi->vmstats[i]);
- if (!slab_only)
- max_idx = NR_VM_NODE_STAT_ITEMS;
-
for_each_node(node) {
struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
struct mem_cgroup_per_node *pi;
- for (i = min_idx; i < max_idx; i++)
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
stat[i] = 0;
for_each_online_cpu(cpu)
- for (i = min_idx; i < max_idx; i++)
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
stat[i] += per_cpu(
pn->lruvec_stat_cpu->count[i], cpu);
for (pi = pn; pi; pi = parent_nodeinfo(pi, node))
- for (i = min_idx; i < max_idx; i++)
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
atomic_long_add(stat[i], &pi->lruvec_stat[i]);
}
}
@@ -3403,13 +3388,9 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
parent = root_mem_cgroup;
/*
- * Deactivate and reparent kmem_caches. Then flush percpu
- * slab statistics to have precise values at the parent and
- * all ancestor levels. It's required to keep slab stats
- * accurate after the reparenting of kmem_caches.
+ * Deactivate and reparent kmem_caches.
*/
memcg_deactivate_kmem_caches(memcg, parent);
- memcg_flush_percpu_vmstats(memcg, true);
kmemcg_id = memcg->kmemcg_id;
BUG_ON(kmemcg_id < 0);
@@ -4913,7 +4894,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
* Flush percpu vmstats and vmevents to guarantee the value correctness
* on parent's and all ancestor levels.
*/
- memcg_flush_percpu_vmstats(memcg, false);
+ memcg_flush_percpu_vmstats(memcg);
memcg_flush_percpu_vmevents(memcg);
__mem_cgroup_free(memcg);
}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 55ac23e..a91a072 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -483,8 +483,9 @@ static void update_pgdat_span(struct pglist_data *pgdat)
pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
}
-static void __remove_zone(struct zone *zone, unsigned long start_pfn,
- unsigned long nr_pages)
+void __ref remove_pfn_range_from_zone(struct zone *zone,
+ unsigned long start_pfn,
+ unsigned long nr_pages)
{
struct pglist_data *pgdat = zone->zone_pgdat;
unsigned long flags;
@@ -499,28 +500,30 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn,
return;
#endif
+ clear_zone_contiguous(zone);
+
pgdat_resize_lock(zone->zone_pgdat, &flags);
shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
update_pgdat_span(pgdat);
pgdat_resize_unlock(zone->zone_pgdat, &flags);
+
+ set_zone_contiguous(zone);
}
-static void __remove_section(struct zone *zone, unsigned long pfn,
- unsigned long nr_pages, unsigned long map_offset,
- struct vmem_altmap *altmap)
+static void __remove_section(unsigned long pfn, unsigned long nr_pages,
+ unsigned long map_offset,
+ struct vmem_altmap *altmap)
{
struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn));
if (WARN_ON_ONCE(!valid_section(ms)))
return;
- __remove_zone(zone, pfn, nr_pages);
sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap);
}
/**
- * __remove_pages() - remove sections of pages from a zone
- * @zone: zone from which pages need to be removed
+ * __remove_pages() - remove sections of pages
* @pfn: starting pageframe (must be aligned to start of a section)
* @nr_pages: number of pages to remove (must be multiple of section size)
* @altmap: alternative device page map or %NULL if default memmap is used
@@ -530,16 +533,14 @@ static void __remove_section(struct zone *zone, unsigned long pfn,
* sure that pages are marked reserved and zones are adjust properly by
* calling offline_pages().
*/
-void __remove_pages(struct zone *zone, unsigned long pfn,
- unsigned long nr_pages, struct vmem_altmap *altmap)
+void __remove_pages(unsigned long pfn, unsigned long nr_pages,
+ struct vmem_altmap *altmap)
{
unsigned long map_offset = 0;
unsigned long nr, start_sec, end_sec;
map_offset = vmem_altmap_offset(altmap);
- clear_zone_contiguous(zone);
-
if (check_pfn_span(pfn, nr_pages, "remove"))
return;
@@ -551,13 +552,11 @@ void __remove_pages(struct zone *zone, unsigned long pfn,
cond_resched();
pfns = min(nr_pages, PAGES_PER_SECTION
- (pfn & ~PAGE_SECTION_MASK));
- __remove_section(zone, pfn, pfns, map_offset, altmap);
+ __remove_section(pfn, pfns, map_offset, altmap);
pfn += pfns;
nr_pages -= pfns;
map_offset = 0;
}
-
- set_zone_contiguous(zone);
}
int set_online_page_callback(online_page_callback_t callback)
@@ -869,6 +868,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
(unsigned long long) pfn << PAGE_SHIFT,
(((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
memory_notify(MEM_CANCEL_ONLINE, &arg);
+ remove_pfn_range_from_zone(zone, pfn, nr_pages);
mem_hotplug_done();
return ret;
}
@@ -1628,6 +1628,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
writeback_set_ratelimit();
memory_notify(MEM_OFFLINE, &arg);
+ remove_pfn_range_from_zone(zone, start_pfn, nr_pages);
mem_hotplug_done();
return 0;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 067cf7d..b2920ae 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2148,18 +2148,22 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
nmask = policy_nodemask(gfp, pol);
if (!nmask || node_isset(hpage_node, *nmask)) {
mpol_cond_put(pol);
+ /*
+ * First, try to allocate THP only on local node, but
+ * don't reclaim unnecessarily, just compact.
+ */
page = __alloc_pages_node(hpage_node,
- gfp | __GFP_THISNODE, order);
+ gfp | __GFP_THISNODE | __GFP_NORETRY, order);
/*
* If hugepage allocations are configured to always
* synchronous compact or the vma has been madvised
* to prefer hugepage backing, retry allowing remote
- * memory as well.
+ * memory with both reclaim and compact as well.
*/
if (!page && (gfp & __GFP_DIRECT_RECLAIM))
page = __alloc_pages_node(hpage_node,
- gfp | __GFP_NORETRY, order);
+ gfp, order);
goto out;
}
diff --git a/mm/memremap.c b/mm/memremap.c
index 03ccbdf..c51c6bd 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -120,7 +120,7 @@ void memunmap_pages(struct dev_pagemap *pgmap)
mem_hotplug_begin();
if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- __remove_pages(page_zone(first_page), PHYS_PFN(res->start),
+ __remove_pages(PHYS_PFN(res->start),
PHYS_PFN(resource_size(res)), NULL);
} else {
arch_remove_memory(nid, res->start, resource_size(res),
diff --git a/mm/migrate.c b/mm/migrate.c
index eae1565..86873b6 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1512,9 +1512,11 @@ static int do_move_pages_to_node(struct mm_struct *mm,
/*
* Resolves the given address to a struct page, isolates it from the LRU and
* puts it to the given pagelist.
- * Returns -errno if the page cannot be found/isolated or 0 when it has been
- * queued or the page doesn't need to be migrated because it is already on
- * the target node
+ * Returns:
+ * errno - if the page cannot be found/isolated
+ * 0 - when it doesn't have to be migrated because it is already on the
+ * target node
+ * 1 - when it has been queued
*/
static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
int node, struct list_head *pagelist, bool migrate_all)
@@ -1553,7 +1555,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
if (PageHuge(page)) {
if (PageHead(page)) {
isolate_huge_page(page, pagelist);
- err = 0;
+ err = 1;
}
} else {
struct page *head;
@@ -1563,7 +1565,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
if (err)
goto out_putpage;
- err = 0;
+ err = 1;
list_add_tail(&head->lru, pagelist);
mod_node_page_state(page_pgdat(head),
NR_ISOLATED_ANON + page_is_file_cache(head),
@@ -1640,8 +1642,17 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
*/
err = add_page_for_migration(mm, addr, current_node,
&pagelist, flags & MPOL_MF_MOVE_ALL);
- if (!err)
+
+ if (!err) {
+ /* The page is already on the target node */
+ err = store_status(status, i, current_node, 1);
+ if (err)
+ goto out_flush;
continue;
+ } else if (err > 0) {
+ /* The page is successfully queued for migration */
+ continue;
+ }
err = store_status(status, i, err, 1);
if (err)
diff --git a/mm/mmap.c b/mm/mmap.c
index 9c64852..71e4ffc 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -90,12 +90,6 @@ static void unmap_region(struct mm_struct *mm,
* MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes
* w: (no) no w: (no) no w: (copy) copy w: (no) no
* x: (no) no x: (no) yes x: (no) yes x: (yes) yes
- *
- * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and
- * MAP_PRIVATE:
- * r: (no) no
- * w: (no) no
- * x: (yes) yes
*/
pgprot_t protection_map[16] __ro_after_init = {
__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 71e3ace..d58c481 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -890,7 +890,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message)
K(get_mm_counter(mm, MM_FILEPAGES)),
K(get_mm_counter(mm, MM_SHMEMPAGES)),
from_kuid(&init_user_ns, task_uid(victim)),
- mm_pgtables_bytes(mm), victim->signal->oom_score_adj);
+ mm_pgtables_bytes(mm) >> 10, victim->signal->oom_score_adj);
task_unlock(victim);
/*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 50055d2..2caf780 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -201,11 +201,11 @@ static void wb_min_max_ratio(struct bdi_writeback *wb,
if (this_bw < tot_bw) {
if (min) {
min *= this_bw;
- do_div(min, tot_bw);
+ min = div64_ul(min, tot_bw);
}
if (max < 100) {
max *= this_bw;
- do_div(max, tot_bw);
+ max = div64_ul(max, tot_bw);
}
}
@@ -766,7 +766,7 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc)
struct wb_domain *dom = dtc_dom(dtc);
unsigned long thresh = dtc->thresh;
u64 wb_thresh;
- long numerator, denominator;
+ unsigned long numerator, denominator;
unsigned long wb_min_ratio, wb_max_ratio;
/*
@@ -777,7 +777,7 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc)
wb_thresh = (thresh * (100 - bdi_min_ratio)) / 100;
wb_thresh *= numerator;
- do_div(wb_thresh, denominator);
+ wb_thresh = div64_ul(wb_thresh, denominator);
wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio);
@@ -1102,7 +1102,7 @@ static void wb_update_write_bandwidth(struct bdi_writeback *wb,
bw = written - min(written, wb->written_stamp);
bw *= HZ;
if (unlikely(elapsed > period)) {
- do_div(bw, elapsed);
+ bw = div64_ul(bw, elapsed);
avg = bw;
goto out;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4785a8a..d047bf7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -694,34 +694,27 @@ void prep_compound_page(struct page *page, unsigned int order)
#ifdef CONFIG_DEBUG_PAGEALLOC
unsigned int _debug_guardpage_minorder;
-#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT
-DEFINE_STATIC_KEY_TRUE(_debug_pagealloc_enabled);
-#else
+bool _debug_pagealloc_enabled_early __read_mostly
+ = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
+EXPORT_SYMBOL(_debug_pagealloc_enabled_early);
DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
-#endif
EXPORT_SYMBOL(_debug_pagealloc_enabled);
DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled);
static int __init early_debug_pagealloc(char *buf)
{
- bool enable = false;
-
- if (kstrtobool(buf, &enable))
- return -EINVAL;
-
- if (enable)
- static_branch_enable(&_debug_pagealloc_enabled);
-
- return 0;
+ return kstrtobool(buf, &_debug_pagealloc_enabled_early);
}
early_param("debug_pagealloc", early_debug_pagealloc);
-static void init_debug_guardpage(void)
+void init_debug_pagealloc(void)
{
if (!debug_pagealloc_enabled())
return;
+ static_branch_enable(&_debug_pagealloc_enabled);
+
if (!debug_guardpage_minorder())
return;
@@ -1186,7 +1179,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
*/
arch_free_page(page, order);
- if (debug_pagealloc_enabled())
+ if (debug_pagealloc_enabled_static())
kernel_map_pages(page, 1 << order, 0);
kasan_free_nondeferred_pages(page, order);
@@ -1207,7 +1200,7 @@ static bool free_pcp_prepare(struct page *page)
static bool bulkfree_pcp_prepare(struct page *page)
{
- if (debug_pagealloc_enabled())
+ if (debug_pagealloc_enabled_static())
return free_pages_check(page);
else
return false;
@@ -1221,7 +1214,7 @@ static bool bulkfree_pcp_prepare(struct page *page)
*/
static bool free_pcp_prepare(struct page *page)
{
- if (debug_pagealloc_enabled())
+ if (debug_pagealloc_enabled_static())
return free_pages_prepare(page, 0, true);
else
return free_pages_prepare(page, 0, false);
@@ -1973,10 +1966,6 @@ void __init page_alloc_init_late(void)
for_each_populated_zone(zone)
set_zone_contiguous(zone);
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
- init_debug_guardpage();
-#endif
}
#ifdef CONFIG_CMA
@@ -2106,7 +2095,7 @@ static inline bool free_pages_prezeroed(void)
*/
static inline bool check_pcp_refill(struct page *page)
{
- if (debug_pagealloc_enabled())
+ if (debug_pagealloc_enabled_static())
return check_new_page(page);
else
return false;
@@ -2128,7 +2117,7 @@ static inline bool check_pcp_refill(struct page *page)
}
static inline bool check_new_pcp(struct page *page)
{
- if (debug_pagealloc_enabled())
+ if (debug_pagealloc_enabled_static())
return check_new_page(page);
else
return false;
@@ -2155,7 +2144,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
set_page_refcounted(page);
arch_alloc_page(page, order);
- if (debug_pagealloc_enabled())
+ if (debug_pagealloc_enabled_static())
kernel_map_pages(page, 1 << order, 1);
kasan_alloc_pages(page, order);
kernel_poison_pages(page, 1 << order, 1);
@@ -4476,8 +4465,11 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
if (page)
goto got_pg;
- if (order >= pageblock_order && (gfp_mask & __GFP_IO) &&
- !(gfp_mask & __GFP_RETRY_MAYFAIL)) {
+ /*
+ * Checks for costly allocations with __GFP_NORETRY, which
+ * includes some THP page fault allocations
+ */
+ if (costly_order && (gfp_mask & __GFP_NORETRY)) {
/*
* If allocating entire pageblock(s) and compaction
* failed because all zones are below low watermarks
@@ -4498,23 +4490,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
if (compact_result == COMPACT_SKIPPED ||
compact_result == COMPACT_DEFERRED)
goto nopage;
- }
-
- /*
- * Checks for costly allocations with __GFP_NORETRY, which
- * includes THP page fault allocations
- */
- if (costly_order && (gfp_mask & __GFP_NORETRY)) {
- /*
- * If compaction is deferred for high-order allocations,
- * it is because sync compaction recently failed. If
- * this is the case and the caller requested a THP
- * allocation, we do not want to heavily disrupt the
- * system, so we fail the allocation instead of entering
- * direct reclaim.
- */
- if (compact_result == COMPACT_DEFERRED)
- goto nopage;
/*
* Looks like reclaim/compaction is worth trying, but
diff --git a/mm/shmem.c b/mm/shmem.c
index 165fa63..8793e8c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2107,9 +2107,10 @@ unsigned long shmem_get_unmapped_area(struct file *file,
/*
* Our priority is to support MAP_SHARED mapped hugely;
* and support MAP_PRIVATE mapped hugely too, until it is COWed.
- * But if caller specified an address hint, respect that as before.
+ * But if caller specified an address hint and we allocated area there
+ * successfully, respect that as before.
*/
- if (uaddr)
+ if (uaddr == addr)
return addr;
if (shmem_huge != SHMEM_HUGE_FORCE) {
@@ -2143,7 +2144,7 @@ unsigned long shmem_get_unmapped_area(struct file *file,
if (inflated_len < len)
return addr;
- inflated_addr = get_area(NULL, 0, inflated_len, 0, flags);
+ inflated_addr = get_area(NULL, uaddr, inflated_len, 0, flags);
if (IS_ERR_VALUE(inflated_addr))
return addr;
if (inflated_addr & ~PAGE_MASK)
diff --git a/mm/slab.c b/mm/slab.c
index f1e1840..a896336 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1416,7 +1416,7 @@ static void kmem_rcu_free(struct rcu_head *head)
#if DEBUG
static bool is_debug_pagealloc_cache(struct kmem_cache *cachep)
{
- if (debug_pagealloc_enabled() && OFF_SLAB(cachep) &&
+ if (debug_pagealloc_enabled_static() && OFF_SLAB(cachep) &&
(cachep->size % PAGE_SIZE) == 0)
return true;
@@ -2008,7 +2008,7 @@ int __kmem_cache_create(struct kmem_cache *cachep, slab_flags_t flags)
* to check size >= 256. It guarantees that all necessary small
* sized slab is initialized in current slab initialization sequence.
*/
- if (debug_pagealloc_enabled() && (flags & SLAB_POISON) &&
+ if (debug_pagealloc_enabled_static() && (flags & SLAB_POISON) &&
size >= 256 && cachep->object_size > cache_line_size()) {
if (size < PAGE_SIZE || size % PAGE_SIZE == 0) {
size_t tmp_size = ALIGN(size, PAGE_SIZE);
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f0ab6d4..0d95dde 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -903,7 +903,8 @@ static void flush_memcg_workqueue(struct kmem_cache *s)
* deactivates the memcg kmem_caches through workqueue. Make sure all
* previous workitems on workqueue are processed.
*/
- flush_workqueue(memcg_kmem_cache_wq);
+ if (likely(memcg_kmem_cache_wq))
+ flush_workqueue(memcg_kmem_cache_wq);
/*
* If we're racing with children kmem_cache deactivation, it might
diff --git a/mm/slub.c b/mm/slub.c
index d113897..8eafccf 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -288,7 +288,7 @@ static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
unsigned long freepointer_addr;
void *p;
- if (!debug_pagealloc_enabled())
+ if (!debug_pagealloc_enabled_static())
return get_freepointer(s, object);
freepointer_addr = (unsigned long)object + s->offset;
diff --git a/mm/sparse.c b/mm/sparse.c
index b20ab7c..3822ecb 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -777,7 +777,14 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
if (bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION)) {
unsigned long section_nr = pfn_to_section_nr(pfn);
- if (!section_is_early) {
+ /*
+ * When removing an early section, the usage map is kept (as the
+ * usage maps of other sections fall into the same page). It
+ * will be re-used when re-adding the section - which is then no
+ * longer an early section. If the usage map is PageReserved, it
+ * was allocated during boot.
+ */
+ if (!PageReserved(virt_to_page(ms->usage))) {
kfree(ms->usage);
ms->usage = NULL;
}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e9681dc..b29ad17 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1383,7 +1383,7 @@ static void free_unmap_vmap_area(struct vmap_area *va)
{
flush_cache_vunmap(va->va_start, va->va_end);
unmap_vmap_area(va);
- if (debug_pagealloc_enabled())
+ if (debug_pagealloc_enabled_static())
flush_tlb_kernel_range(va->va_start, va->va_end);
free_vmap_area_noflush(va);
@@ -1681,7 +1681,7 @@ static void vb_free(const void *addr, unsigned long size)
vunmap_page_range((unsigned long)addr, (unsigned long)addr + size);
- if (debug_pagealloc_enabled())
+ if (debug_pagealloc_enabled_static())
flush_tlb_kernel_range((unsigned long)addr,
(unsigned long)addr + size);
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 2b2b9aa..22d17ec 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -2069,6 +2069,11 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage,
zs_pool_dec_isolated(pool);
}
+ if (page_zone(newpage) != page_zone(page)) {
+ dec_zone_page_state(page, NR_ZSPAGES);
+ inc_zone_page_state(newpage, NR_ZSPAGES);
+ }
+
reset_page(page);
put_page(page);
page = newpage;
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index c46daf0..bb7ec1a 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -126,6 +126,7 @@ int vlan_check_real_dev(struct net_device *real_dev,
void vlan_setup(struct net_device *dev);
int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack);
void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
+void vlan_dev_uninit(struct net_device *dev);
bool vlan_dev_inherit_address(struct net_device *dev,
struct net_device *real_dev);
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 5ff8059..990b9fd 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -586,7 +586,8 @@ static int vlan_dev_init(struct net_device *dev)
return 0;
}
-static void vlan_dev_uninit(struct net_device *dev)
+/* Note: this function might be called multiple times for the same device. */
+void vlan_dev_uninit(struct net_device *dev)
{
struct vlan_priority_tci_mapping *pm;
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index c482a6f..0db85ae 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -108,11 +108,13 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
struct ifla_vlan_flags *flags;
struct ifla_vlan_qos_mapping *m;
struct nlattr *attr;
- int rem;
+ int rem, err;
if (data[IFLA_VLAN_FLAGS]) {
flags = nla_data(data[IFLA_VLAN_FLAGS]);
- vlan_dev_change_flags(dev, flags->flags, flags->mask);
+ err = vlan_dev_change_flags(dev, flags->flags, flags->mask);
+ if (err)
+ return err;
}
if (data[IFLA_VLAN_INGRESS_QOS]) {
nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) {
@@ -123,7 +125,9 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
if (data[IFLA_VLAN_EGRESS_QOS]) {
nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) {
m = nla_data(attr);
- vlan_dev_set_egress_priority(dev, m->from, m->to);
+ err = vlan_dev_set_egress_priority(dev, m->from, m->to);
+ if (err)
+ return err;
}
}
return 0;
@@ -179,10 +183,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
return -EINVAL;
err = vlan_changelink(dev, tb, data, extack);
- if (err < 0)
- return err;
-
- return register_vlan_dev(dev, extack);
+ if (!err)
+ err = register_vlan_dev(dev, extack);
+ if (err)
+ vlan_dev_uninit(dev);
+ return err;
}
static inline size_t vlan_qos_map_size(unsigned int n)
diff --git a/net/Kconfig b/net/Kconfig
index 54916b7..b0937a70 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -91,6 +91,7 @@
source "net/ipv4/Kconfig"
source "net/ipv6/Kconfig"
source "net/netlabel/Kconfig"
+source "net/mptcp/Kconfig"
endif # if INET
diff --git a/net/Makefile b/net/Makefile
index 848303d..07ea481 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -87,3 +87,4 @@
obj-$(CONFIG_QRTR) += qrtr/
obj-$(CONFIG_NET_NCSI) += ncsi/
obj-$(CONFIG_XDP_SOCKETS) += xdp/
+obj-$(CONFIG_MPTCP) += mptcp/
diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c
index 39b94ca..aa1b571 100644
--- a/net/atm/atm_sysfs.c
+++ b/net/atm/atm_sysfs.c
@@ -33,23 +33,17 @@ static ssize_t show_atmaddress(struct device *cdev,
unsigned long flags;
struct atm_dev *adev = to_atm_dev(cdev);
struct atm_dev_addr *aaddr;
- int bin[] = { 1, 2, 10, 6, 1 }, *fmt = bin;
- int i, j, count = 0;
+ int count = 0;
spin_lock_irqsave(&adev->lock, flags);
list_for_each_entry(aaddr, &adev->local, entry) {
- for (i = 0, j = 0; i < ATM_ESA_LEN; ++i, ++j) {
- if (j == *fmt) {
- count += scnprintf(buf + count,
- PAGE_SIZE - count, ".");
- ++fmt;
- j = 0;
- }
- count += scnprintf(buf + count,
- PAGE_SIZE - count, "%02x",
- aaddr->addr.sas_addr.prv[i]);
- }
- count += scnprintf(buf + count, PAGE_SIZE - count, "\n");
+ count += scnprintf(buf + count, PAGE_SIZE - count,
+ "%1phN.%2phN.%10phN.%6phN.%1phN\n",
+ &aaddr->addr.sas_addr.prv[0],
+ &aaddr->addr.sas_addr.prv[1],
+ &aaddr->addr.sas_addr.prv[3],
+ &aaddr->addr.sas_addr.prv[13],
+ &aaddr->addr.sas_addr.prv[19]);
}
spin_unlock_irqrestore(&adev->lock, flags);
diff --git a/net/atm/lec.c b/net/atm/lec.c
index b57368e..25fa3a7 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -799,14 +799,9 @@ static const char *lec_arp_get_status_string(unsigned char status)
static void lec_info(struct seq_file *seq, struct lec_arp_table *entry)
{
- int i;
-
- for (i = 0; i < ETH_ALEN; i++)
- seq_printf(seq, "%2.2x", entry->mac_addr[i] & 0xff);
- seq_printf(seq, " ");
- for (i = 0; i < ATM_ESA_LEN; i++)
- seq_printf(seq, "%2.2x", entry->atm_addr[i] & 0xff);
- seq_printf(seq, " %s %4.4x", lec_arp_get_status_string(entry->status),
+ seq_printf(seq, "%pM ", entry->mac_addr);
+ seq_printf(seq, "%*phN ", ATM_ESA_LEN, entry->atm_addr);
+ seq_printf(seq, "%s %4.4x", lec_arp_get_status_string(entry->status),
entry->flags & 0xffff);
if (entry->vcc)
seq_printf(seq, "%3d %3d ", entry->vcc->vpi, entry->vcc->vci);
@@ -1354,7 +1349,7 @@ static void dump_arp_table(struct lec_priv *priv)
{
struct lec_arp_table *rulla;
char buf[256];
- int i, j, offset;
+ int i, offset;
pr_info("Dump %p:\n", priv);
for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) {
@@ -1362,14 +1357,10 @@ static void dump_arp_table(struct lec_priv *priv)
&priv->lec_arp_tables[i], next) {
offset = 0;
offset += sprintf(buf, "%d: %p\n", i, rulla);
- offset += sprintf(buf + offset, "Mac: %pM",
+ offset += sprintf(buf + offset, "Mac: %pM ",
rulla->mac_addr);
- offset += sprintf(buf + offset, " Atm:");
- for (j = 0; j < ATM_ESA_LEN; j++) {
- offset += sprintf(buf + offset,
- "%2.2x ",
- rulla->atm_addr[j] & 0xff);
- }
+ offset += sprintf(buf + offset, "Atm: %*ph ", ATM_ESA_LEN,
+ rulla->atm_addr);
offset += sprintf(buf + offset,
"Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ",
rulla->vcc ? rulla->vcc->vpi : 0,
@@ -1392,12 +1383,9 @@ static void dump_arp_table(struct lec_priv *priv)
pr_info("No forward\n");
hlist_for_each_entry(rulla, &priv->lec_no_forward, next) {
offset = 0;
- offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr);
- offset += sprintf(buf + offset, " Atm:");
- for (j = 0; j < ATM_ESA_LEN; j++) {
- offset += sprintf(buf + offset, "%2.2x ",
- rulla->atm_addr[j] & 0xff);
- }
+ offset += sprintf(buf + offset, "Mac: %pM ", rulla->mac_addr);
+ offset += sprintf(buf + offset, "Atm: %*ph ", ATM_ESA_LEN,
+ rulla->atm_addr);
offset += sprintf(buf + offset,
"Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ",
rulla->vcc ? rulla->vcc->vpi : 0,
@@ -1417,12 +1405,9 @@ static void dump_arp_table(struct lec_priv *priv)
pr_info("Empty ones\n");
hlist_for_each_entry(rulla, &priv->lec_arp_empty_ones, next) {
offset = 0;
- offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr);
- offset += sprintf(buf + offset, " Atm:");
- for (j = 0; j < ATM_ESA_LEN; j++) {
- offset += sprintf(buf + offset, "%2.2x ",
- rulla->atm_addr[j] & 0xff);
- }
+ offset += sprintf(buf + offset, "Mac: %pM ", rulla->mac_addr);
+ offset += sprintf(buf + offset, "Atm: %*ph ", ATM_ESA_LEN,
+ rulla->atm_addr);
offset += sprintf(buf + offset,
"Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ",
rulla->vcc ? rulla->vcc->vpi : 0,
@@ -1442,12 +1427,9 @@ static void dump_arp_table(struct lec_priv *priv)
pr_info("Multicast Forward VCCs\n");
hlist_for_each_entry(rulla, &priv->mcast_fwds, next) {
offset = 0;
- offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr);
- offset += sprintf(buf + offset, " Atm:");
- for (j = 0; j < ATM_ESA_LEN; j++) {
- offset += sprintf(buf + offset, "%2.2x ",
- rulla->atm_addr[j] & 0xff);
- }
+ offset += sprintf(buf + offset, "Mac: %pM ", rulla->mac_addr);
+ offset += sprintf(buf + offset, "Atm: %*ph ", ATM_ESA_LEN,
+ rulla->atm_addr);
offset += sprintf(buf + offset,
"Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ",
rulla->vcc ? rulla->vcc->vpi : 0,
@@ -1973,17 +1955,8 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
* Vcc which we don't want to make default vcc,
* attach it anyway.
*/
- pr_debug("LEC_ARP:Attaching data direct, not default: %2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n",
- ioc_data->atm_addr[0], ioc_data->atm_addr[1],
- ioc_data->atm_addr[2], ioc_data->atm_addr[3],
- ioc_data->atm_addr[4], ioc_data->atm_addr[5],
- ioc_data->atm_addr[6], ioc_data->atm_addr[7],
- ioc_data->atm_addr[8], ioc_data->atm_addr[9],
- ioc_data->atm_addr[10], ioc_data->atm_addr[11],
- ioc_data->atm_addr[12], ioc_data->atm_addr[13],
- ioc_data->atm_addr[14], ioc_data->atm_addr[15],
- ioc_data->atm_addr[16], ioc_data->atm_addr[17],
- ioc_data->atm_addr[18], ioc_data->atm_addr[19]);
+ pr_debug("LEC_ARP:Attaching data direct, not default: %*phN\n",
+ ATM_ESA_LEN, ioc_data->atm_addr);
entry = make_entry(priv, bus_mac);
if (entry == NULL)
goto out;
@@ -1999,17 +1972,8 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
dump_arp_table(priv);
goto out;
}
- pr_debug("LEC_ARP:Attaching data direct, default: %2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n",
- ioc_data->atm_addr[0], ioc_data->atm_addr[1],
- ioc_data->atm_addr[2], ioc_data->atm_addr[3],
- ioc_data->atm_addr[4], ioc_data->atm_addr[5],
- ioc_data->atm_addr[6], ioc_data->atm_addr[7],
- ioc_data->atm_addr[8], ioc_data->atm_addr[9],
- ioc_data->atm_addr[10], ioc_data->atm_addr[11],
- ioc_data->atm_addr[12], ioc_data->atm_addr[13],
- ioc_data->atm_addr[14], ioc_data->atm_addr[15],
- ioc_data->atm_addr[16], ioc_data->atm_addr[17],
- ioc_data->atm_addr[18], ioc_data->atm_addr[19]);
+ pr_debug("LEC_ARP:Attaching data direct, default: %*phN\n",
+ ATM_ESA_LEN, ioc_data->atm_addr);
for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) {
hlist_for_each_entry(entry,
&priv->lec_arp_tables[i], next) {
diff --git a/net/atm/proc.c b/net/atm/proc.c
index d79221fd..c318967 100644
--- a/net/atm/proc.c
+++ b/net/atm/proc.c
@@ -134,8 +134,7 @@ static void vcc_seq_stop(struct seq_file *seq, void *v)
static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
v = vcc_walk(seq, 1);
- if (v)
- (*pos)++;
+ (*pos)++;
return v;
}
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 324306d..ff57ea8 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -808,7 +808,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol,
struct sock *sk;
ax25_cb *ax25;
- if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+ if (protocol < 0 || protocol > U8_MAX)
return -EINVAL;
if (!net_eq(net, &init_net))
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index d5028af7..c762758 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+# Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
#
# Marek Lindner, Simon Wunderlich
@@ -100,7 +100,6 @@
config BATMAN_ADV_SYSFS
bool "batman-adv sysfs entries"
depends on BATMAN_ADV
- default y
help
Say Y here if you want to enable batman-adv device configuration and
status interface through sysfs attributes. It is replaced by the
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index fd63e11..daa49af 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+# Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
#
# Marek Lindner, Simon Wunderlich
diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c
index fa39eaa..382fbe5 100644
--- a/net/batman-adv/bat_algo.c
+++ b/net/batman-adv/bat_algo.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h
index 37898da..686a60b 100644
--- a/net/batman-adv/bat_algo.h
+++ b/net/batman-adv/bat_algo.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Linus Lüssing
*/
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 5b0b20e..f020950 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h
index c7a9ba3..0c57c10 100644
--- a/net/batman-adv/bat_iv_ogm.h
+++ b/net/batman-adv/bat_iv_ogm.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 4ff6cf1..0ecaf1bb0 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors:
*
* Linus Lüssing, Marek Lindner
*/
diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h
index 37833db..5e0be10 100644
--- a/net/batman-adv/bat_v.h
+++ b/net/batman-adv/bat_v.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Linus Lüssing
*/
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index 2614a9c..1e3172d 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors:
*
* Linus Lüssing, Marek Lindner
*/
@@ -107,10 +107,17 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh)
}
if (ret)
goto default_throughput;
- if (!(sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT)))
- goto default_throughput;
- return sinfo.expected_throughput / 100;
+ if (sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT))
+ return sinfo.expected_throughput / 100;
+
+ /* try to estimate the expected throughput based on reported tx
+ * rates
+ */
+ if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE))
+ return cfg80211_calculate_bitrate(&sinfo.txrate) / 3;
+
+ goto default_throughput;
}
/* if not a wifi interface, check if this device provides data via
diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h
index 1a29505..4358d43 100644
--- a/net/batman-adv/bat_v_elp.h
+++ b/net/batman-adv/bat_v_elp.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors:
*
* Linus Lüssing, Marek Lindner
*/
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 714ce56..9694662 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors:
*
* Antonio Quartulli
*/
diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h
index bf16d04..0ae2575 100644
--- a/net/batman-adv/bat_v_ogm.h
+++ b/net/batman-adv/bat_v_ogm.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors:
*
* Antonio Quartulli
*/
diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c
index 7f04a6a..4bc695c 100644
--- a/net/batman-adv/bitarray.c
+++ b/net/batman-adv/bitarray.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*/
diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h
index 84ad2d2..533c6d4 100644
--- a/net/batman-adv/bitarray.h
+++ b/net/batman-adv/bitarray.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*/
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 663a53b..41cc87f 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich
*/
@@ -844,7 +844,7 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr,
/* handle as ANNOUNCE frame */
backbone_gw->lasttime = jiffies;
- crc = ntohs(*((__be16 *)(&an_addr[4])));
+ crc = ntohs(*((__force __be16 *)(&an_addr[4])));
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"%s(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n",
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index 02b24a8..41edb2c 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich
*/
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index 38c4d8e..452856c 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h
index 1c5afd3..7e2e8f5 100644
--- a/net/batman-adv/debugfs.h
+++ b/net/batman-adv/debugfs.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index b0af3a1..3d21dd8 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors:
*
* Antonio Quartulli
*/
@@ -246,7 +246,7 @@ static u8 *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size)
*/
static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size)
{
- return *(__be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN);
+ return *(__force __be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN);
}
/**
@@ -270,7 +270,9 @@ static u8 *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size)
*/
static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size)
{
- return *(__be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN * 2 + 4);
+ u8 *dst = batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN * 2 + 4;
+
+ return *(__force __be32 *)dst;
}
/**
@@ -285,16 +287,18 @@ static u32 batadv_hash_dat(const void *data, u32 size)
u32 hash = 0;
const struct batadv_dat_entry *dat = data;
const unsigned char *key;
+ __be16 vid;
u32 i;
- key = (const unsigned char *)&dat->ip;
+ key = (__force const unsigned char *)&dat->ip;
for (i = 0; i < sizeof(dat->ip); i++) {
hash += key[i];
hash += (hash << 10);
hash ^= (hash >> 6);
}
- key = (const unsigned char *)&dat->vid;
+ vid = htons(dat->vid);
+ key = (__force const unsigned char *)&vid;
for (i = 0; i < sizeof(dat->vid); i++) {
hash += key[i];
hash += (hash << 10);
diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h
index 67c7729..2bff2f4 100644
--- a/net/batman-adv/distributed-arp-table.h
+++ b/net/batman-adv/distributed-arp-table.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors:
*
* Antonio Quartulli
*/
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 385fccd..7cad976 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll <martin@hundeboll.net>
*/
diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h
index abfe8c6..881ef32 100644
--- a/net/batman-adv/fragmentation.h
+++ b/net/batman-adv/fragmentation.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll <martin@hundeboll.net>
*/
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 47df4c6..e22e492 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h
index 0be8e71..88b5dba 100644
--- a/net/batman-adv/gateway_client.h
+++ b/net/batman-adv/gateway_client.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index fc55750..16cd945 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h
index 211b14b..c3a0c5a 100644
--- a/net/batman-adv/gateway_common.h
+++ b/net/batman-adv/gateway_common.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index afb5228..c7e98a4 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index bbb8a6f..bad2e50 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c
index a9d4e17..68638e0 100644
--- a/net/batman-adv/hash.c
+++ b/net/batman-adv/hash.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*/
diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h
index 57877f0..91ae9f3 100644
--- a/net/batman-adv/hash.h
+++ b/net/batman-adv/hash.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*/
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 0a70b66..ccb535c 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h
index 27fafff..6abd0f4 100644
--- a/net/batman-adv/icmp_socket.h
+++ b/net/batman-adv/icmp_socket.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c
index 11941cf..a67b2b0 100644
--- a/net/batman-adv/log.c
+++ b/net/batman-adv/log.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
index 741cfa3..f9884dc 100644
--- a/net/batman-adv/log.h
+++ b/net/batman-adv/log.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
@@ -74,7 +74,7 @@ __printf(2, 3);
* @bat_priv: the bat priv with all the soft interface information
* @ratelimited: whether output should be rate limited
* @fmt: format string
- * @arg...: variable arguments
+ * @arg: variable arguments
*/
#define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...) \
do { \
@@ -98,7 +98,7 @@ static inline void _batadv_dbg(int type __always_unused,
* batadv_dbg() - Store debug output without ratelimiting
* @type: type of debug message
* @bat_priv: the bat priv with all the soft interface information
- * @arg...: format string and variable arguments
+ * @arg: format string and variable arguments
*/
#define batadv_dbg(type, bat_priv, arg...) \
_batadv_dbg(type, bat_priv, 0, ## arg)
@@ -107,7 +107,7 @@ static inline void _batadv_dbg(int type __always_unused,
* batadv_dbg_ratelimited() - Store debug output with ratelimiting
* @type: type of debug message
* @bat_priv: the bat priv with all the soft interface information
- * @arg...: format string and variable arguments
+ * @arg: format string and variable arguments
*/
#define batadv_dbg_ratelimited(type, bat_priv, arg...) \
_batadv_dbg(type, bat_priv, 1, ## arg)
@@ -116,7 +116,7 @@ static inline void _batadv_dbg(int type __always_unused,
* batadv_info() - Store message in debug buffer and print it to kmsg buffer
* @net_dev: the soft interface net device
* @fmt: format string
- * @arg...: variable arguments
+ * @arg: variable arguments
*/
#define batadv_info(net_dev, fmt, arg...) \
do { \
@@ -130,7 +130,7 @@ static inline void _batadv_dbg(int type __always_unused,
* batadv_err() - Store error in debug buffer and print it to kmsg buffer
* @net_dev: the soft interface net device
* @fmt: format string
- * @arg...: variable arguments
+ * @arg: variable arguments
*/
#define batadv_err(net_dev, fmt, arg...) \
do { \
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 4811ec6..d8a255c8 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index c7b340d..692306df 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
@@ -13,7 +13,7 @@
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2019.5"
+#define BATADV_SOURCE_VERSION "2020.0"
#endif
/* B.A.T.M.A.N. parameters */
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index f9ec8e7..9ebdc1e 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2014-2020 B.A.T.M.A.N. contributors:
*
* Linus Lüssing
*/
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index 5d9e2bb..ebf8259 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2014-2020 B.A.T.M.A.N. contributors:
*
* Linus Lüssing
*/
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 7e052d6..02ed073 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors:
*
* Matthias Schiffer
*/
diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h
index ddc674e..7ee48f9 100644
--- a/net/batman-adv/netlink.h
+++ b/net/batman-adv/netlink.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors:
*
* Matthias Schiffer
*/
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 5806093..8f0717c 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll, Jeppe Ledet-Pedersen
*/
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
index 753fa49..3342890 100644
--- a/net/batman-adv/network-coding.h
+++ b/net/batman-adv/network-coding.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll, Jeppe Ledet-Pedersen
*/
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 3861348..5b0c2ff 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index 512a1f9..7bc01c1 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index f0f8648..3632bd9 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h
index c20feac..2ed49db 100644
--- a/net/batman-adv/routing.h
+++ b/net/batman-adv/routing.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 3ce5f7b..7f8ade0 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index 5fc0fd1..0d36e15 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 832e156..5f05a728 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h
index 29139ad..534e08d 100644
--- a/net/batman-adv/soft-interface.h
+++ b/net/batman-adv/soft-interface.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index e5bbc28..c45962d 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h
index 5e46609..d987f8b3 100644
--- a/net/batman-adv/sysfs.h
+++ b/net/batman-adv/sysfs.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*/
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index dd6a9a4..bd2ac57 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors:
*
* Edo Monticelli, Antonio Quartulli
*/
diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h
index 78d310da..1401052 100644
--- a/net/batman-adv/tp_meter.h
+++ b/net/batman-adv/tp_meter.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors:
*
* Edo Monticelli, Antonio Quartulli
*/
diff --git a/net/batman-adv/trace.c b/net/batman-adv/trace.c
index 3cedd2c..3444d9e 100644
--- a/net/batman-adv/trace.c
+++ b/net/batman-adv/trace.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors:
*
* Sven Eckelmann
*/
diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h
index d8f7645..f631b1e 100644
--- a/net/batman-adv/trace.h
+++ b/net/batman-adv/trace.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors:
*
* Sven Eckelmann
*/
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 8a482c5..8529328 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich, Antonio Quartulli
*/
diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h
index 4a98860..b24d35b 100644
--- a/net/batman-adv/translation-table.h
+++ b/net/batman-adv/translation-table.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich, Antonio Quartulli
*/
diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c
index aae63f0..0963a43 100644
--- a/net/batman-adv/tvlv.c
+++ b/net/batman-adv/tvlv.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h
index 3698500..d509d00 100644
--- a/net/batman-adv/tvlv.h
+++ b/net/batman-adv/tvlv.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 47718a8..4a17a66 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*/
@@ -457,7 +457,7 @@ struct batadv_orig_node {
/**
* @tt_lock: prevents from updating the table while reading it. Table
* update is made up by two operations (data structure update and
- * metdata -CRC/TTVN-recalculation) and they have to be executed
+ * metadata -CRC/TTVN-recalculation) and they have to be executed
* atomically in order to avoid another thread to read the
* table/metadata between those.
*/
@@ -1011,7 +1011,7 @@ struct batadv_priv_tt {
/**
* @commit_lock: prevents from executing a local TT commit while reading
* the local table. The local TT commit is made up by two operations
- * (data structure update and metdata -CRC/TTVN- recalculation) and
+ * (data structure update and metadata -CRC/TTVN- recalculation) and
* they have to be executed atomically in order to avoid another thread
* to read the table/metadata between those.
*/
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index ac9ef33..49da7ae 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -20,7 +20,7 @@
bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o
-bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o br_vlan_tunnel.o
+bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o br_vlan_tunnel.o br_vlan_options.o
bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index fb38add..dc3d2c1 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -32,6 +32,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
struct net_bridge_mdb_entry *mdst;
struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
const struct nf_br_ops *nf_ops;
+ u8 state = BR_STATE_FORWARDING;
const unsigned char *dest;
struct ethhdr *eth;
u16 vid = 0;
@@ -56,7 +57,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
eth = eth_hdr(skb);
skb_pull(skb, ETH_HLEN);
- if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid))
+ if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state))
goto out;
if (IS_ENABLED(CONFIG_INET) &&
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 8663700..7629b63 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -25,7 +25,7 @@ static inline int should_deliver(const struct net_bridge_port *p,
vg = nbp_vlan_group_rcu(p);
return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
- br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING &&
+ p->state == BR_STATE_FORWARDING && br_allowed_egress(vg, skb) &&
nbp_switchdev_allowed_egress(p, skb) &&
!br_skb_isolated(p, skb);
}
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 8944ceb..fcc2608 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -76,11 +76,14 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
bool local_rcv, mcast_hit = false;
struct net_bridge *br;
u16 vid = 0;
+ u8 state;
if (!p || p->state == BR_STATE_DISABLED)
goto drop;
- if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid))
+ state = p->state;
+ if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid,
+ &state))
goto out;
nbp_switchdev_frame_mark(p, skb);
@@ -103,7 +106,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
}
}
- if (p->state == BR_STATE_LEARNING)
+ if (state == BR_STATE_LEARNING)
goto drop;
BR_INPUT_SKB_CB(skb)->brdev = br->dev;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 6013657..43dab40 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -561,52 +561,73 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
return err;
}
-static int br_process_vlan_info(struct net_bridge *br,
- struct net_bridge_port *p, int cmd,
- struct bridge_vlan_info *vinfo_curr,
- struct bridge_vlan_info **vinfo_last,
- bool *changed,
- struct netlink_ext_ack *extack)
+int br_process_vlan_info(struct net_bridge *br,
+ struct net_bridge_port *p, int cmd,
+ struct bridge_vlan_info *vinfo_curr,
+ struct bridge_vlan_info **vinfo_last,
+ bool *changed,
+ struct netlink_ext_ack *extack)
{
- if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK)
+ int err, rtm_cmd;
+
+ if (!br_vlan_valid_id(vinfo_curr->vid, extack))
return -EINVAL;
+ /* needed for vlan-only NEWVLAN/DELVLAN notifications */
+ rtm_cmd = br_afspec_cmd_to_rtm(cmd);
+
if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
- /* check if we are already processing a range */
- if (*vinfo_last)
+ if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack))
return -EINVAL;
*vinfo_last = vinfo_curr;
- /* don't allow range of pvids */
- if ((*vinfo_last)->flags & BRIDGE_VLAN_INFO_PVID)
- return -EINVAL;
return 0;
}
if (*vinfo_last) {
struct bridge_vlan_info tmp_vinfo;
- int v, err;
+ int v, v_change_start = 0;
- if (!(vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_END))
- return -EINVAL;
-
- if (vinfo_curr->vid <= (*vinfo_last)->vid)
+ if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack))
return -EINVAL;
memcpy(&tmp_vinfo, *vinfo_last,
sizeof(struct bridge_vlan_info));
for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) {
+ bool curr_change = false;
+
tmp_vinfo.vid = v;
- err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed,
+ err = br_vlan_info(br, p, cmd, &tmp_vinfo, &curr_change,
extack);
if (err)
break;
+ if (curr_change) {
+ *changed = curr_change;
+ if (!v_change_start)
+ v_change_start = v;
+ } else {
+ /* nothing to notify yet */
+ if (!v_change_start)
+ continue;
+ br_vlan_notify(br, p, v_change_start,
+ v - 1, rtm_cmd);
+ v_change_start = 0;
+ }
}
+ /* v_change_start is set only if the last/whole range changed */
+ if (v_change_start)
+ br_vlan_notify(br, p, v_change_start,
+ v - 1, rtm_cmd);
+
*vinfo_last = NULL;
return err;
}
- return br_vlan_info(br, p, cmd, vinfo_curr, changed, extack);
+ err = br_vlan_info(br, p, cmd, vinfo_curr, changed, extack);
+ if (*changed)
+ br_vlan_notify(br, p, vinfo_curr->vid, 0, rtm_cmd);
+
+ return err;
}
static int br_afspec(struct net_bridge *br,
@@ -1664,6 +1685,7 @@ int __init br_netlink_init(void)
int err;
br_mdb_init();
+ br_vlan_rtnl_init();
rtnl_af_register(&br_af_ops);
err = rtnl_link_register(&br_link_ops);
@@ -1681,6 +1703,7 @@ int __init br_netlink_init(void)
void br_netlink_fini(void)
{
br_mdb_uninit();
+ br_vlan_rtnl_uninit();
rtnl_af_unregister(&br_af_ops);
rtnl_link_unregister(&br_link_ops);
}
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index f540f3b..5153ffe 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -113,6 +113,7 @@ enum {
* @vid: VLAN id
* @flags: bridge vlan flags
* @priv_flags: private (in-kernel) bridge vlan flags
+ * @state: STP state (e.g. blocking, learning, forwarding)
* @stats: per-cpu VLAN statistics
* @br: if MASTER flag set, this points to a bridge struct
* @port: if MASTER flag unset, this points to a port struct
@@ -133,6 +134,7 @@ struct net_bridge_vlan {
u16 vid;
u16 flags;
u16 priv_flags;
+ u8 state;
struct br_vlan_stats __percpu *stats;
union {
struct net_bridge *br;
@@ -157,6 +159,7 @@ struct net_bridge_vlan {
* @vlan_list: sorted VLAN entry list
* @num_vlans: number of total VLAN entries
* @pvid: PVID VLAN id
+ * @pvid_state: PVID's STP state (e.g. forwarding, learning, blocking)
*
* IMPORTANT: Be careful when checking if there're VLAN entries using list
* primitives because the bridge can have entries in its list which
@@ -170,6 +173,7 @@ struct net_bridge_vlan_group {
struct list_head vlan_list;
u16 num_vlans;
u16 pvid;
+ u8 pvid_state;
};
/* bridge fdb flags */
@@ -507,6 +511,65 @@ static inline bool nbp_state_should_learn(const struct net_bridge_port *p)
return p->state == BR_STATE_LEARNING || p->state == BR_STATE_FORWARDING;
}
+static inline bool br_vlan_valid_id(u16 vid, struct netlink_ext_ack *extack)
+{
+ bool ret = vid > 0 && vid < VLAN_VID_MASK;
+
+ if (!ret)
+ NL_SET_ERR_MSG_MOD(extack, "Vlan id is invalid");
+
+ return ret;
+}
+
+static inline bool br_vlan_valid_range(const struct bridge_vlan_info *cur,
+ const struct bridge_vlan_info *last,
+ struct netlink_ext_ack *extack)
+{
+ /* pvid flag is not allowed in ranges */
+ if (cur->flags & BRIDGE_VLAN_INFO_PVID) {
+ NL_SET_ERR_MSG_MOD(extack, "Pvid isn't allowed in a range");
+ return false;
+ }
+
+ /* when cur is the range end, check if:
+ * - it has range start flag
+ * - range ids are invalid (end is equal to or before start)
+ */
+ if (last) {
+ if (cur->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
+ NL_SET_ERR_MSG_MOD(extack, "Found a new vlan range start while processing one");
+ return false;
+ } else if (!(cur->flags & BRIDGE_VLAN_INFO_RANGE_END)) {
+ NL_SET_ERR_MSG_MOD(extack, "Vlan range end flag is missing");
+ return false;
+ } else if (cur->vid <= last->vid) {
+ NL_SET_ERR_MSG_MOD(extack, "End vlan id is less than or equal to start vlan id");
+ return false;
+ }
+ }
+
+ /* check for required range flags */
+ if (!(cur->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN |
+ BRIDGE_VLAN_INFO_RANGE_END))) {
+ NL_SET_ERR_MSG_MOD(extack, "Both vlan range flags are missing");
+ return false;
+ }
+
+ return true;
+}
+
+static inline int br_afspec_cmd_to_rtm(int cmd)
+{
+ switch (cmd) {
+ case RTM_SETLINK:
+ return RTM_NEWVLAN;
+ case RTM_DELLINK:
+ return RTM_DELVLAN;
+ }
+
+ return 0;
+}
+
static inline int br_opt_get(const struct net_bridge *br,
enum net_bridge_opts opt)
{
@@ -876,7 +939,7 @@ static inline int br_multicast_igmp_type(const struct sk_buff *skb)
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
bool br_allowed_ingress(const struct net_bridge *br,
struct net_bridge_vlan_group *vg, struct sk_buff *skb,
- u16 *vid);
+ u16 *vid, u8 *state);
bool br_allowed_egress(struct net_bridge_vlan_group *vg,
const struct sk_buff *skb);
bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid);
@@ -911,6 +974,14 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v,
void br_vlan_port_event(struct net_bridge_port *p, unsigned long event);
int br_vlan_bridge_event(struct net_device *dev, unsigned long event,
void *ptr);
+void br_vlan_rtnl_init(void);
+void br_vlan_rtnl_uninit(void);
+void br_vlan_notify(const struct net_bridge *br,
+ const struct net_bridge_port *p,
+ u16 vid, u16 vid_range,
+ int cmd);
+bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr,
+ const struct net_bridge_vlan *range_end);
static inline struct net_bridge_vlan_group *br_vlan_group(
const struct net_bridge *br)
@@ -962,11 +1033,15 @@ static inline u16 br_get_pvid(const struct net_bridge_vlan_group *vg)
return vg->pvid;
}
+static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid)
+{
+ return v->vid == pvid ? v->flags | BRIDGE_VLAN_INFO_PVID : v->flags;
+}
#else
static inline bool br_allowed_ingress(const struct net_bridge *br,
struct net_bridge_vlan_group *vg,
struct sk_buff *skb,
- u16 *vid)
+ u16 *vid, u8 *state)
{
return true;
}
@@ -1105,6 +1180,70 @@ static inline int br_vlan_bridge_event(struct net_device *dev,
{
return 0;
}
+
+static inline void br_vlan_rtnl_init(void)
+{
+}
+
+static inline void br_vlan_rtnl_uninit(void)
+{
+}
+
+static inline void br_vlan_notify(const struct net_bridge *br,
+ const struct net_bridge_port *p,
+ u16 vid, u16 vid_range,
+ int cmd)
+{
+}
+#endif
+
+/* br_vlan_options.c */
+#ifdef CONFIG_BRIDGE_VLAN_FILTERING
+bool br_vlan_opts_eq(const struct net_bridge_vlan *v1,
+ const struct net_bridge_vlan *v2);
+bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v);
+size_t br_vlan_opts_nl_size(void);
+int br_vlan_process_options(const struct net_bridge *br,
+ const struct net_bridge_port *p,
+ struct net_bridge_vlan *range_start,
+ struct net_bridge_vlan *range_end,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack);
+
+/* vlan state manipulation helpers using *_ONCE to annotate lock-free access */
+static inline u8 br_vlan_get_state(const struct net_bridge_vlan *v)
+{
+ return READ_ONCE(v->state);
+}
+
+static inline void br_vlan_set_state(struct net_bridge_vlan *v, u8 state)
+{
+ WRITE_ONCE(v->state, state);
+}
+
+static inline u8 br_vlan_get_pvid_state(const struct net_bridge_vlan_group *vg)
+{
+ return READ_ONCE(vg->pvid_state);
+}
+
+static inline void br_vlan_set_pvid_state(struct net_bridge_vlan_group *vg,
+ u8 state)
+{
+ WRITE_ONCE(vg->pvid_state, state);
+}
+
+/* learn_allow is true at ingress and false at egress */
+static inline bool br_vlan_state_allowed(u8 state, bool learn_allow)
+{
+ switch (state) {
+ case BR_STATE_LEARNING:
+ return learn_allow;
+ case BR_STATE_FORWARDING:
+ return true;
+ default:
+ return false;
+ }
+}
#endif
struct nf_br_ops {
@@ -1176,6 +1315,12 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags,
int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev,
u32 filter_mask, int nlflags);
+int br_process_vlan_info(struct net_bridge *br,
+ struct net_bridge_port *p, int cmd,
+ struct bridge_vlan_info *vinfo_curr,
+ struct bridge_vlan_info **vinfo_last,
+ bool *changed,
+ struct netlink_ext_ack *extack);
#ifdef CONFIG_SYSFS
/* br_sysfs_if.c */
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index bb98984..6b5deca 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -34,13 +34,15 @@ static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid)
return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params);
}
-static bool __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid)
+static bool __vlan_add_pvid(struct net_bridge_vlan_group *vg,
+ const struct net_bridge_vlan *v)
{
- if (vg->pvid == vid)
+ if (vg->pvid == v->vid)
return false;
smp_wmb();
- vg->pvid = vid;
+ br_vlan_set_pvid_state(vg, v->state);
+ vg->pvid = v->vid;
return true;
}
@@ -69,7 +71,7 @@ static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
vg = nbp_vlan_group(v->port);
if (flags & BRIDGE_VLAN_INFO_PVID)
- ret = __vlan_add_pvid(vg, v->vid);
+ ret = __vlan_add_pvid(vg, v);
else
ret = __vlan_delete_pvid(vg, v->vid);
@@ -257,6 +259,10 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags,
&changed, extack);
if (err)
goto out_filt;
+
+ if (changed)
+ br_vlan_notify(br, NULL, v->vid, 0,
+ RTM_NEWVLAN);
}
masterv = br_vlan_get_master(br, v->vid, extack);
@@ -289,6 +295,9 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags,
vg->num_vlans++;
}
+ /* set the state before publishing */
+ v->state = BR_STATE_FORWARDING;
+
err = rhashtable_lookup_insert_fast(&vg->vlan_hash, &v->vnode,
br_vlan_rht_params);
if (err)
@@ -380,13 +389,31 @@ static void __vlan_group_free(struct net_bridge_vlan_group *vg)
kfree(vg);
}
-static void __vlan_flush(struct net_bridge_vlan_group *vg)
+static void __vlan_flush(const struct net_bridge *br,
+ const struct net_bridge_port *p,
+ struct net_bridge_vlan_group *vg)
{
struct net_bridge_vlan *vlan, *tmp;
+ u16 v_start = 0, v_end = 0;
__vlan_delete_pvid(vg, vg->pvid);
- list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist)
+ list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) {
+ /* take care of disjoint ranges */
+ if (!v_start) {
+ v_start = vlan->vid;
+ } else if (vlan->vid - v_end != 1) {
+ /* found range end, notify and start next one */
+ br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN);
+ v_start = vlan->vid;
+ }
+ v_end = vlan->vid;
+
__vlan_del(vlan);
+ }
+
+ /* notify about the last/whole vlan range */
+ if (v_start)
+ br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN);
}
struct sk_buff *br_handle_vlan(struct net_bridge *br,
@@ -444,7 +471,8 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
/* Called under RCU */
static bool __allowed_ingress(const struct net_bridge *br,
struct net_bridge_vlan_group *vg,
- struct sk_buff *skb, u16 *vid)
+ struct sk_buff *skb, u16 *vid,
+ u8 *state)
{
struct br_vlan_stats *stats;
struct net_bridge_vlan *v;
@@ -510,13 +538,25 @@ static bool __allowed_ingress(const struct net_bridge *br,
skb->vlan_tci |= pvid;
/* if stats are disabled we can avoid the lookup */
- if (!br_opt_get(br, BROPT_VLAN_STATS_ENABLED))
- return true;
+ if (!br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) {
+ if (*state == BR_STATE_FORWARDING) {
+ *state = br_vlan_get_pvid_state(vg);
+ return br_vlan_state_allowed(*state, true);
+ } else {
+ return true;
+ }
+ }
}
v = br_vlan_find(vg, *vid);
if (!v || !br_vlan_should_use(v))
goto drop;
+ if (*state == BR_STATE_FORWARDING) {
+ *state = br_vlan_get_state(v);
+ if (!br_vlan_state_allowed(*state, true))
+ goto drop;
+ }
+
if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) {
stats = this_cpu_ptr(v->stats);
u64_stats_update_begin(&stats->syncp);
@@ -534,7 +574,7 @@ static bool __allowed_ingress(const struct net_bridge *br,
bool br_allowed_ingress(const struct net_bridge *br,
struct net_bridge_vlan_group *vg, struct sk_buff *skb,
- u16 *vid)
+ u16 *vid, u8 *state)
{
/* If VLAN filtering is disabled on the bridge, all packets are
* permitted.
@@ -544,7 +584,7 @@ bool br_allowed_ingress(const struct net_bridge *br,
return true;
}
- return __allowed_ingress(br, vg, skb, vid);
+ return __allowed_ingress(br, vg, skb, vid, state);
}
/* Called under RCU. */
@@ -560,7 +600,8 @@ bool br_allowed_egress(struct net_bridge_vlan_group *vg,
br_vlan_get_tag(skb, &vid);
v = br_vlan_find(vg, vid);
- if (v && br_vlan_should_use(v))
+ if (v && br_vlan_should_use(v) &&
+ br_vlan_state_allowed(br_vlan_get_state(v), false))
return true;
return false;
@@ -571,6 +612,7 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
{
struct net_bridge_vlan_group *vg;
struct net_bridge *br = p->br;
+ struct net_bridge_vlan *v;
/* If filtering was disabled at input, let it pass. */
if (!br_opt_get(br, BROPT_VLAN_ENABLED))
@@ -585,13 +627,15 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
if (!*vid) {
*vid = br_get_pvid(vg);
- if (!*vid)
+ if (!*vid ||
+ !br_vlan_state_allowed(br_vlan_get_pvid_state(vg), true))
return false;
return true;
}
- if (br_vlan_find(vg, *vid))
+ v = br_vlan_find(vg, *vid);
+ if (v && br_vlan_state_allowed(br_vlan_get_state(v), true))
return true;
return false;
@@ -716,7 +760,7 @@ void br_vlan_flush(struct net_bridge *br)
ASSERT_RTNL();
vg = br_vlan_group(br);
- __vlan_flush(vg);
+ __vlan_flush(br, NULL, vg);
RCU_INIT_POINTER(br->vlgrp, NULL);
synchronize_rcu();
__vlan_group_free(vg);
@@ -925,12 +969,15 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br)
/* Disable default_pvid on all ports where it is still
* configured.
*/
- if (vlan_default_pvid(br_vlan_group(br), pvid))
- br_vlan_delete(br, pvid);
+ if (vlan_default_pvid(br_vlan_group(br), pvid)) {
+ if (!br_vlan_delete(br, pvid))
+ br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN);
+ }
list_for_each_entry(p, &br->port_list, list) {
- if (vlan_default_pvid(nbp_vlan_group(p), pvid))
- nbp_vlan_delete(p, pvid);
+ if (vlan_default_pvid(nbp_vlan_group(p), pvid) &&
+ !nbp_vlan_delete(p, pvid))
+ br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN);
}
br->default_pvid = 0;
@@ -972,7 +1019,10 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid,
&vlchange, extack);
if (err)
goto out;
- br_vlan_delete(br, old_pvid);
+
+ if (br_vlan_delete(br, old_pvid))
+ br_vlan_notify(br, NULL, old_pvid, 0, RTM_DELVLAN);
+ br_vlan_notify(br, NULL, pvid, 0, RTM_NEWVLAN);
set_bit(0, changed);
}
@@ -992,7 +1042,9 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid,
&vlchange, extack);
if (err)
goto err_port;
- nbp_vlan_delete(p, old_pvid);
+ if (nbp_vlan_delete(p, old_pvid))
+ br_vlan_notify(br, p, old_pvid, 0, RTM_DELVLAN);
+ br_vlan_notify(p->br, p, pvid, 0, RTM_NEWVLAN);
set_bit(p->port_no, changed);
}
@@ -1007,22 +1059,28 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid,
if (!test_bit(p->port_no, changed))
continue;
- if (old_pvid)
+ if (old_pvid) {
nbp_vlan_add(p, old_pvid,
BRIDGE_VLAN_INFO_PVID |
BRIDGE_VLAN_INFO_UNTAGGED,
&vlchange, NULL);
+ br_vlan_notify(p->br, p, old_pvid, 0, RTM_NEWVLAN);
+ }
nbp_vlan_delete(p, pvid);
+ br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN);
}
if (test_bit(0, changed)) {
- if (old_pvid)
+ if (old_pvid) {
br_vlan_add(br, old_pvid,
BRIDGE_VLAN_INFO_PVID |
BRIDGE_VLAN_INFO_UNTAGGED |
BRIDGE_VLAN_INFO_BRENTRY,
&vlchange, NULL);
+ br_vlan_notify(br, NULL, old_pvid, 0, RTM_NEWVLAN);
+ }
br_vlan_delete(br, pvid);
+ br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN);
}
goto out;
}
@@ -1115,6 +1173,7 @@ int nbp_vlan_init(struct net_bridge_port *p, struct netlink_ext_ack *extack)
&changed, extack);
if (ret)
goto err_vlan_add;
+ br_vlan_notify(p->br, p, p->br->default_pvid, 0, RTM_NEWVLAN);
}
out:
return ret;
@@ -1196,7 +1255,7 @@ void nbp_vlan_flush(struct net_bridge_port *port)
ASSERT_RTNL();
vg = nbp_vlan_group(port);
- __vlan_flush(vg);
+ __vlan_flush(port->br, port, vg);
RCU_INIT_POINTER(port->vlgrp, NULL);
synchronize_rcu();
__vlan_group_free(vg);
@@ -1462,8 +1521,8 @@ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr)
{
struct netdev_notifier_changeupper_info *info;
struct net_bridge *br = netdev_priv(dev);
- bool changed;
- int ret = 0;
+ int vlcmd = 0, ret = 0;
+ bool changed = false;
switch (event) {
case NETDEV_REGISTER:
@@ -1471,9 +1530,11 @@ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr)
BRIDGE_VLAN_INFO_PVID |
BRIDGE_VLAN_INFO_UNTAGGED |
BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL);
+ vlcmd = RTM_NEWVLAN;
break;
case NETDEV_UNREGISTER:
- br_vlan_delete(br, br->default_pvid);
+ changed = !br_vlan_delete(br, br->default_pvid);
+ vlcmd = RTM_DELVLAN;
break;
case NETDEV_CHANGEUPPER:
info = ptr;
@@ -1487,6 +1548,8 @@ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr)
br_vlan_link_state_change(dev, br);
break;
}
+ if (changed)
+ br_vlan_notify(br, NULL, br->default_pvid, 0, vlcmd);
return ret;
}
@@ -1505,3 +1568,441 @@ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event)
break;
}
}
+
+/* v_opts is used to dump the options which must be equal in the whole range */
+static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range,
+ const struct net_bridge_vlan *v_opts,
+ u16 flags)
+{
+ struct bridge_vlan_info info;
+ struct nlattr *nest;
+
+ nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY);
+ if (!nest)
+ return false;
+
+ memset(&info, 0, sizeof(info));
+ info.vid = vid;
+ if (flags & BRIDGE_VLAN_INFO_UNTAGGED)
+ info.flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+ if (flags & BRIDGE_VLAN_INFO_PVID)
+ info.flags |= BRIDGE_VLAN_INFO_PVID;
+
+ if (nla_put(skb, BRIDGE_VLANDB_ENTRY_INFO, sizeof(info), &info))
+ goto out_err;
+
+ if (vid_range && vid < vid_range &&
+ !(flags & BRIDGE_VLAN_INFO_PVID) &&
+ nla_put_u16(skb, BRIDGE_VLANDB_ENTRY_RANGE, vid_range))
+ goto out_err;
+
+ if (v_opts && !br_vlan_opts_fill(skb, v_opts))
+ goto out_err;
+
+ nla_nest_end(skb, nest);
+
+ return true;
+
+out_err:
+ nla_nest_cancel(skb, nest);
+ return false;
+}
+
+static size_t rtnl_vlan_nlmsg_size(void)
+{
+ return NLMSG_ALIGN(sizeof(struct br_vlan_msg))
+ + nla_total_size(0) /* BRIDGE_VLANDB_ENTRY */
+ + nla_total_size(sizeof(u16)) /* BRIDGE_VLANDB_ENTRY_RANGE */
+ + nla_total_size(sizeof(struct bridge_vlan_info)) /* BRIDGE_VLANDB_ENTRY_INFO */
+ + br_vlan_opts_nl_size(); /* bridge vlan options */
+}
+
+void br_vlan_notify(const struct net_bridge *br,
+ const struct net_bridge_port *p,
+ u16 vid, u16 vid_range,
+ int cmd)
+{
+ struct net_bridge_vlan_group *vg;
+ struct net_bridge_vlan *v = NULL;
+ struct br_vlan_msg *bvm;
+ struct nlmsghdr *nlh;
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+ struct net *net;
+ u16 flags = 0;
+ int ifindex;
+
+ /* right now notifications are done only with rtnl held */
+ ASSERT_RTNL();
+
+ if (p) {
+ ifindex = p->dev->ifindex;
+ vg = nbp_vlan_group(p);
+ net = dev_net(p->dev);
+ } else {
+ ifindex = br->dev->ifindex;
+ vg = br_vlan_group(br);
+ net = dev_net(br->dev);
+ }
+
+ skb = nlmsg_new(rtnl_vlan_nlmsg_size(), GFP_KERNEL);
+ if (!skb)
+ goto out_err;
+
+ err = -EMSGSIZE;
+ nlh = nlmsg_put(skb, 0, 0, cmd, sizeof(*bvm), 0);
+ if (!nlh)
+ goto out_err;
+ bvm = nlmsg_data(nlh);
+ memset(bvm, 0, sizeof(*bvm));
+ bvm->family = AF_BRIDGE;
+ bvm->ifindex = ifindex;
+
+ switch (cmd) {
+ case RTM_NEWVLAN:
+ /* need to find the vlan due to flags/options */
+ v = br_vlan_find(vg, vid);
+ if (!v || !br_vlan_should_use(v))
+ goto out_kfree;
+
+ flags = v->flags;
+ if (br_get_pvid(vg) == v->vid)
+ flags |= BRIDGE_VLAN_INFO_PVID;
+ break;
+ case RTM_DELVLAN:
+ break;
+ default:
+ goto out_kfree;
+ }
+
+ if (!br_vlan_fill_vids(skb, vid, vid_range, v, flags))
+ goto out_err;
+
+ nlmsg_end(skb, nlh);
+ rtnl_notify(skb, net, 0, RTNLGRP_BRVLAN, NULL, GFP_KERNEL);
+ return;
+
+out_err:
+ rtnl_set_sk_err(net, RTNLGRP_BRVLAN, err);
+out_kfree:
+ kfree_skb(skb);
+}
+
+/* check if v_curr can enter a range ending in range_end */
+bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr,
+ const struct net_bridge_vlan *range_end)
+{
+ return v_curr->vid - range_end->vid == 1 &&
+ range_end->flags == v_curr->flags &&
+ br_vlan_opts_eq(v_curr, range_end);
+}
+
+static int br_vlan_dump_dev(const struct net_device *dev,
+ struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct net_bridge_vlan *v, *range_start = NULL, *range_end = NULL;
+ struct net_bridge_vlan_group *vg;
+ int idx = 0, s_idx = cb->args[1];
+ struct nlmsghdr *nlh = NULL;
+ struct net_bridge_port *p;
+ struct br_vlan_msg *bvm;
+ struct net_bridge *br;
+ int err = 0;
+ u16 pvid;
+
+ if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev))
+ return -EINVAL;
+
+ if (netif_is_bridge_master(dev)) {
+ br = netdev_priv(dev);
+ vg = br_vlan_group_rcu(br);
+ p = NULL;
+ } else {
+ p = br_port_get_rcu(dev);
+ if (WARN_ON(!p))
+ return -EINVAL;
+ vg = nbp_vlan_group_rcu(p);
+ br = p->br;
+ }
+
+ if (!vg)
+ return 0;
+
+ nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ RTM_NEWVLAN, sizeof(*bvm), NLM_F_MULTI);
+ if (!nlh)
+ return -EMSGSIZE;
+ bvm = nlmsg_data(nlh);
+ memset(bvm, 0, sizeof(*bvm));
+ bvm->family = PF_BRIDGE;
+ bvm->ifindex = dev->ifindex;
+ pvid = br_get_pvid(vg);
+
+ /* idx must stay at range's beginning until it is filled in */
+ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) {
+ if (!br_vlan_should_use(v))
+ continue;
+ if (idx < s_idx) {
+ idx++;
+ continue;
+ }
+
+ if (!range_start) {
+ range_start = v;
+ range_end = v;
+ continue;
+ }
+
+ if (v->vid == pvid || !br_vlan_can_enter_range(v, range_end)) {
+ u16 flags = br_vlan_flags(range_start, pvid);
+
+ if (!br_vlan_fill_vids(skb, range_start->vid,
+ range_end->vid, range_start,
+ flags)) {
+ err = -EMSGSIZE;
+ break;
+ }
+ /* advance number of filled vlans */
+ idx += range_end->vid - range_start->vid + 1;
+
+ range_start = v;
+ }
+ range_end = v;
+ }
+
+ /* err will be 0 and range_start will be set in 3 cases here:
+ * - first vlan (range_start == range_end)
+ * - last vlan (range_start == range_end, not in range)
+ * - last vlan range (range_start != range_end, in range)
+ */
+ if (!err && range_start &&
+ !br_vlan_fill_vids(skb, range_start->vid, range_end->vid,
+ range_start, br_vlan_flags(range_start, pvid)))
+ err = -EMSGSIZE;
+
+ cb->args[1] = err ? idx : 0;
+
+ nlmsg_end(skb, nlh);
+
+ return err;
+}
+
+static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ int idx = 0, err = 0, s_idx = cb->args[0];
+ struct net *net = sock_net(skb->sk);
+ struct br_vlan_msg *bvm;
+ struct net_device *dev;
+
+ err = nlmsg_parse(cb->nlh, sizeof(*bvm), NULL, 0, NULL, cb->extack);
+ if (err < 0)
+ return err;
+
+ bvm = nlmsg_data(cb->nlh);
+
+ rcu_read_lock();
+ if (bvm->ifindex) {
+ dev = dev_get_by_index_rcu(net, bvm->ifindex);
+ if (!dev) {
+ err = -ENODEV;
+ goto out_err;
+ }
+ err = br_vlan_dump_dev(dev, skb, cb);
+ if (err && err != -EMSGSIZE)
+ goto out_err;
+ } else {
+ for_each_netdev_rcu(net, dev) {
+ if (idx < s_idx)
+ goto skip;
+
+ err = br_vlan_dump_dev(dev, skb, cb);
+ if (err == -EMSGSIZE)
+ break;
+skip:
+ idx++;
+ }
+ }
+ cb->args[0] = idx;
+ rcu_read_unlock();
+
+ return skb->len;
+
+out_err:
+ rcu_read_unlock();
+
+ return err;
+}
+
+static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = {
+ [BRIDGE_VLANDB_ENTRY_INFO] = { .type = NLA_EXACT_LEN,
+ .len = sizeof(struct bridge_vlan_info) },
+ [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 },
+ [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 },
+};
+
+static int br_vlan_rtm_process_one(struct net_device *dev,
+ const struct nlattr *attr,
+ int cmd, struct netlink_ext_ack *extack)
+{
+ struct bridge_vlan_info *vinfo, vrange_end, *vinfo_last = NULL;
+ struct nlattr *tb[BRIDGE_VLANDB_ENTRY_MAX + 1];
+ bool changed = false, skip_processing = false;
+ struct net_bridge_vlan_group *vg;
+ struct net_bridge_port *p = NULL;
+ int err = 0, cmdmap = 0;
+ struct net_bridge *br;
+
+ if (netif_is_bridge_master(dev)) {
+ br = netdev_priv(dev);
+ vg = br_vlan_group(br);
+ } else {
+ p = br_port_get_rtnl(dev);
+ if (WARN_ON(!p))
+ return -ENODEV;
+ br = p->br;
+ vg = nbp_vlan_group(p);
+ }
+
+ if (WARN_ON(!vg))
+ return -ENODEV;
+
+ err = nla_parse_nested(tb, BRIDGE_VLANDB_ENTRY_MAX, attr,
+ br_vlan_db_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[BRIDGE_VLANDB_ENTRY_INFO]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing vlan entry info");
+ return -EINVAL;
+ }
+ memset(&vrange_end, 0, sizeof(vrange_end));
+
+ vinfo = nla_data(tb[BRIDGE_VLANDB_ENTRY_INFO]);
+ if (vinfo->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN |
+ BRIDGE_VLAN_INFO_RANGE_END)) {
+ NL_SET_ERR_MSG_MOD(extack, "Old-style vlan ranges are not allowed when using RTM vlan calls");
+ return -EINVAL;
+ }
+ if (!br_vlan_valid_id(vinfo->vid, extack))
+ return -EINVAL;
+
+ if (tb[BRIDGE_VLANDB_ENTRY_RANGE]) {
+ vrange_end.vid = nla_get_u16(tb[BRIDGE_VLANDB_ENTRY_RANGE]);
+ /* validate user-provided flags without RANGE_BEGIN */
+ vrange_end.flags = BRIDGE_VLAN_INFO_RANGE_END | vinfo->flags;
+ vinfo->flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN;
+
+ /* vinfo_last is the range start, vinfo the range end */
+ vinfo_last = vinfo;
+ vinfo = &vrange_end;
+
+ if (!br_vlan_valid_id(vinfo->vid, extack) ||
+ !br_vlan_valid_range(vinfo, vinfo_last, extack))
+ return -EINVAL;
+ }
+
+ switch (cmd) {
+ case RTM_NEWVLAN:
+ cmdmap = RTM_SETLINK;
+ skip_processing = !!(vinfo->flags & BRIDGE_VLAN_INFO_ONLY_OPTS);
+ break;
+ case RTM_DELVLAN:
+ cmdmap = RTM_DELLINK;
+ break;
+ }
+
+ if (!skip_processing) {
+ struct bridge_vlan_info *tmp_last = vinfo_last;
+
+ /* br_process_vlan_info may overwrite vinfo_last */
+ err = br_process_vlan_info(br, p, cmdmap, vinfo, &tmp_last,
+ &changed, extack);
+
+ /* notify first if anything changed */
+ if (changed)
+ br_ifinfo_notify(cmdmap, br, p);
+
+ if (err)
+ return err;
+ }
+
+ /* deal with options */
+ if (cmd == RTM_NEWVLAN) {
+ struct net_bridge_vlan *range_start, *range_end;
+
+ if (vinfo_last) {
+ range_start = br_vlan_find(vg, vinfo_last->vid);
+ range_end = br_vlan_find(vg, vinfo->vid);
+ } else {
+ range_start = br_vlan_find(vg, vinfo->vid);
+ range_end = range_start;
+ }
+
+ err = br_vlan_process_options(br, p, range_start, range_end,
+ tb, extack);
+ }
+
+ return err;
+}
+
+static int br_vlan_rtm_process(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = sock_net(skb->sk);
+ struct br_vlan_msg *bvm;
+ struct net_device *dev;
+ struct nlattr *attr;
+ int err, vlans = 0;
+ int rem;
+
+ /* this should validate the header and check for remaining bytes */
+ err = nlmsg_parse(nlh, sizeof(*bvm), NULL, BRIDGE_VLANDB_MAX, NULL,
+ extack);
+ if (err < 0)
+ return err;
+
+ bvm = nlmsg_data(nlh);
+ dev = __dev_get_by_index(net, bvm->ifindex);
+ if (!dev)
+ return -ENODEV;
+
+ if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "The device is not a valid bridge or bridge port");
+ return -EINVAL;
+ }
+
+ nlmsg_for_each_attr(attr, nlh, sizeof(*bvm), rem) {
+ if (nla_type(attr) != BRIDGE_VLANDB_ENTRY)
+ continue;
+
+ vlans++;
+ err = br_vlan_rtm_process_one(dev, attr, nlh->nlmsg_type,
+ extack);
+ if (err)
+ break;
+ }
+ if (!vlans) {
+ NL_SET_ERR_MSG_MOD(extack, "No vlans found to process");
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+void br_vlan_rtnl_init(void)
+{
+ rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_GETVLAN, NULL,
+ br_vlan_rtm_dump, 0);
+ rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_NEWVLAN,
+ br_vlan_rtm_process, NULL, 0);
+ rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_DELVLAN,
+ br_vlan_rtm_process, NULL, 0);
+}
+
+void br_vlan_rtnl_uninit(void)
+{
+ rtnl_unregister(PF_BRIDGE, RTM_GETVLAN);
+ rtnl_unregister(PF_BRIDGE, RTM_NEWVLAN);
+ rtnl_unregister(PF_BRIDGE, RTM_DELVLAN);
+}
diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c
new file mode 100644
index 0000000..cd2eb19
--- /dev/null
+++ b/net/bridge/br_vlan_options.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2020, Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/slab.h>
+
+#include "br_private.h"
+
+/* check if the options between two vlans are equal */
+bool br_vlan_opts_eq(const struct net_bridge_vlan *v1,
+ const struct net_bridge_vlan *v2)
+{
+ return v1->state == v2->state;
+}
+
+bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v)
+{
+ return !nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_STATE,
+ br_vlan_get_state(v));
+}
+
+size_t br_vlan_opts_nl_size(void)
+{
+ return nla_total_size(sizeof(u8)); /* BRIDGE_VLANDB_ENTRY_STATE */
+}
+
+static int br_vlan_modify_state(struct net_bridge_vlan_group *vg,
+ struct net_bridge_vlan *v,
+ u8 state,
+ bool *changed,
+ struct netlink_ext_ack *extack)
+{
+ struct net_bridge *br;
+
+ ASSERT_RTNL();
+
+ if (state > BR_STATE_BLOCKING) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid vlan state");
+ return -EINVAL;
+ }
+
+ if (br_vlan_is_brentry(v))
+ br = v->br;
+ else
+ br = v->port->br;
+
+ if (br->stp_enabled == BR_KERNEL_STP) {
+ NL_SET_ERR_MSG_MOD(extack, "Can't modify vlan state when using kernel STP");
+ return -EBUSY;
+ }
+
+ if (v->state == state)
+ return 0;
+
+ if (v->vid == br_get_pvid(vg))
+ br_vlan_set_pvid_state(vg, state);
+
+ br_vlan_set_state(v, state);
+ *changed = true;
+
+ return 0;
+}
+
+static int br_vlan_process_one_opts(const struct net_bridge *br,
+ const struct net_bridge_port *p,
+ struct net_bridge_vlan_group *vg,
+ struct net_bridge_vlan *v,
+ struct nlattr **tb,
+ bool *changed,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ *changed = false;
+ if (tb[BRIDGE_VLANDB_ENTRY_STATE]) {
+ u8 state = nla_get_u8(tb[BRIDGE_VLANDB_ENTRY_STATE]);
+
+ err = br_vlan_modify_state(vg, v, state, changed, extack);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+int br_vlan_process_options(const struct net_bridge *br,
+ const struct net_bridge_port *p,
+ struct net_bridge_vlan *range_start,
+ struct net_bridge_vlan *range_end,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ struct net_bridge_vlan *v, *curr_start = NULL, *curr_end = NULL;
+ struct net_bridge_vlan_group *vg;
+ int vid, err = 0;
+ u16 pvid;
+
+ if (p)
+ vg = nbp_vlan_group(p);
+ else
+ vg = br_vlan_group(br);
+
+ if (!range_start || !br_vlan_should_use(range_start)) {
+ NL_SET_ERR_MSG_MOD(extack, "Vlan range start doesn't exist, can't process options");
+ return -ENOENT;
+ }
+ if (!range_end || !br_vlan_should_use(range_end)) {
+ NL_SET_ERR_MSG_MOD(extack, "Vlan range end doesn't exist, can't process options");
+ return -ENOENT;
+ }
+
+ pvid = br_get_pvid(vg);
+ for (vid = range_start->vid; vid <= range_end->vid; vid++) {
+ bool changed = false;
+
+ v = br_vlan_find(vg, vid);
+ if (!v || !br_vlan_should_use(v)) {
+ NL_SET_ERR_MSG_MOD(extack, "Vlan in range doesn't exist, can't process options");
+ err = -ENOENT;
+ break;
+ }
+
+ err = br_vlan_process_one_opts(br, p, vg, v, tb, &changed,
+ extack);
+ if (err)
+ break;
+
+ if (changed) {
+ /* vlan options changed, check for range */
+ if (!curr_start) {
+ curr_start = v;
+ curr_end = v;
+ continue;
+ }
+
+ if (v->vid == pvid ||
+ !br_vlan_can_enter_range(v, curr_end)) {
+ br_vlan_notify(br, p, curr_start->vid,
+ curr_end->vid, RTM_NEWVLAN);
+ curr_start = v;
+ }
+ curr_end = v;
+ } else {
+ /* nothing changed and nothing to notify yet */
+ if (!curr_start)
+ continue;
+
+ br_vlan_notify(br, p, curr_start->vid, curr_end->vid,
+ RTM_NEWVLAN);
+ curr_start = NULL;
+ curr_end = NULL;
+ }
+ }
+ if (curr_start)
+ br_vlan_notify(br, p, curr_start->vid, curr_end->vid,
+ RTM_NEWVLAN);
+
+ return err;
+}
diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c
index 76bd678..a0116b9 100644
--- a/net/caif/caif_usb.c
+++ b/net/caif/caif_usb.c
@@ -62,7 +62,7 @@ static int cfusbl_transmit(struct cflayer *layr, struct cfpkt *pkt)
hpad = (info->hdr_len + CFUSB_PAD_DESCR_SZ) & (CFUSB_ALIGNMENT - 1);
if (skb_headroom(skb) < ETH_HLEN + CFUSB_PAD_DESCR_SZ + hpad) {
- pr_warn("Headroom to small\n");
+ pr_warn("Headroom too small\n");
kfree_skb(skb);
return -EIO;
}
diff --git a/net/core/datagram.c b/net/core/datagram.c
index da3c24e..a78e7f8 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -84,7 +84,8 @@ static int receiver_wake_function(wait_queue_entry_t *wait, unsigned int mode, i
/*
* Wait for the last received packet to be different from skb
*/
-int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
+int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue,
+ int *err, long *timeo_p,
const struct sk_buff *skb)
{
int error;
@@ -97,7 +98,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
if (error)
goto out_err;
- if (READ_ONCE(sk->sk_receive_queue.prev) != skb)
+ if (READ_ONCE(queue->prev) != skb)
goto out;
/* Socket shut down? */
@@ -209,6 +210,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
/**
* __skb_try_recv_datagram - Receive a datagram skbuff
* @sk: socket
+ * @queue: socket queue from which to receive
* @flags: MSG\_ flags
* @destructor: invoked under the receive lock on successful dequeue
* @off: an offset in bytes to peek skb from. Returns an offset
@@ -241,13 +243,14 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
* quite explicitly by POSIX 1003.1g, don't change them without having
* the standard around please.
*/
-struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
+struct sk_buff *__skb_try_recv_datagram(struct sock *sk,
+ struct sk_buff_head *queue,
+ unsigned int flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb),
int *off, int *err,
struct sk_buff **last)
{
- struct sk_buff_head *queue = &sk->sk_receive_queue;
struct sk_buff *skb;
unsigned long cpu_flags;
/*
@@ -278,7 +281,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
break;
sk_busy_loop(sk, flags & MSG_DONTWAIT);
- } while (READ_ONCE(sk->sk_receive_queue.prev) != *last);
+ } while (READ_ONCE(queue->prev) != *last);
error = -EAGAIN;
@@ -288,7 +291,9 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
}
EXPORT_SYMBOL(__skb_try_recv_datagram);
-struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
+struct sk_buff *__skb_recv_datagram(struct sock *sk,
+ struct sk_buff_head *sk_queue,
+ unsigned int flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb),
int *off, int *err)
@@ -299,15 +304,16 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
- skb = __skb_try_recv_datagram(sk, flags, destructor, off, err,
- &last);
+ skb = __skb_try_recv_datagram(sk, sk_queue, flags, destructor,
+ off, err, &last);
if (skb)
return skb;
if (*err != -EAGAIN)
break;
} while (timeo &&
- !__skb_wait_for_more_packets(sk, err, &timeo, last));
+ !__skb_wait_for_more_packets(sk, sk_queue, err,
+ &timeo, last));
return NULL;
}
@@ -318,7 +324,8 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
{
int off = 0;
- return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
+ return __skb_recv_datagram(sk, &sk->sk_receive_queue,
+ flags | (noblock ? MSG_DONTWAIT : 0),
NULL, &off, err);
}
EXPORT_SYMBOL(skb_recv_datagram);
diff --git a/net/core/dev.c b/net/core/dev.c
index d99f88c..38bc35d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1764,7 +1764,6 @@ EXPORT_SYMBOL(register_netdevice_notifier);
int unregister_netdevice_notifier(struct notifier_block *nb)
{
- struct net_device *dev;
struct net *net;
int err;
@@ -1775,16 +1774,9 @@ int unregister_netdevice_notifier(struct notifier_block *nb)
if (err)
goto unlock;
- for_each_net(net) {
- for_each_netdev(net, dev) {
- if (dev->flags & IFF_UP) {
- call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
- dev);
- call_netdevice_notifier(nb, NETDEV_DOWN, dev);
- }
- call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
- }
- }
+ for_each_net(net)
+ call_netdevice_unregister_net_notifiers(nb, net);
+
unlock:
rtnl_unlock();
up_write(&pernet_ops_rwsem);
@@ -1792,6 +1784,42 @@ int unregister_netdevice_notifier(struct notifier_block *nb)
}
EXPORT_SYMBOL(unregister_netdevice_notifier);
+static int __register_netdevice_notifier_net(struct net *net,
+ struct notifier_block *nb,
+ bool ignore_call_fail)
+{
+ int err;
+
+ err = raw_notifier_chain_register(&net->netdev_chain, nb);
+ if (err)
+ return err;
+ if (dev_boot_phase)
+ return 0;
+
+ err = call_netdevice_register_net_notifiers(nb, net);
+ if (err && !ignore_call_fail)
+ goto chain_unregister;
+
+ return 0;
+
+chain_unregister:
+ raw_notifier_chain_unregister(&net->netdev_chain, nb);
+ return err;
+}
+
+static int __unregister_netdevice_notifier_net(struct net *net,
+ struct notifier_block *nb)
+{
+ int err;
+
+ err = raw_notifier_chain_unregister(&net->netdev_chain, nb);
+ if (err)
+ return err;
+
+ call_netdevice_unregister_net_notifiers(nb, net);
+ return 0;
+}
+
/**
* register_netdevice_notifier_net - register a per-netns network notifier block
* @net: network namespace
@@ -1812,23 +1840,9 @@ int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb)
int err;
rtnl_lock();
- err = raw_notifier_chain_register(&net->netdev_chain, nb);
- if (err)
- goto unlock;
- if (dev_boot_phase)
- goto unlock;
-
- err = call_netdevice_register_net_notifiers(nb, net);
- if (err)
- goto chain_unregister;
-
-unlock:
+ err = __register_netdevice_notifier_net(net, nb, false);
rtnl_unlock();
return err;
-
-chain_unregister:
- raw_notifier_chain_unregister(&netdev_chain, nb);
- goto unlock;
}
EXPORT_SYMBOL(register_netdevice_notifier_net);
@@ -1854,18 +1868,54 @@ int unregister_netdevice_notifier_net(struct net *net,
int err;
rtnl_lock();
- err = raw_notifier_chain_unregister(&net->netdev_chain, nb);
- if (err)
- goto unlock;
-
- call_netdevice_unregister_net_notifiers(nb, net);
-
-unlock:
+ err = __unregister_netdevice_notifier_net(net, nb);
rtnl_unlock();
return err;
}
EXPORT_SYMBOL(unregister_netdevice_notifier_net);
+int register_netdevice_notifier_dev_net(struct net_device *dev,
+ struct notifier_block *nb,
+ struct netdev_net_notifier *nn)
+{
+ int err;
+
+ rtnl_lock();
+ err = __register_netdevice_notifier_net(dev_net(dev), nb, false);
+ if (!err) {
+ nn->nb = nb;
+ list_add(&nn->list, &dev->net_notifier_list);
+ }
+ rtnl_unlock();
+ return err;
+}
+EXPORT_SYMBOL(register_netdevice_notifier_dev_net);
+
+int unregister_netdevice_notifier_dev_net(struct net_device *dev,
+ struct notifier_block *nb,
+ struct netdev_net_notifier *nn)
+{
+ int err;
+
+ rtnl_lock();
+ list_del(&nn->list);
+ err = __unregister_netdevice_notifier_net(dev_net(dev), nb);
+ rtnl_unlock();
+ return err;
+}
+EXPORT_SYMBOL(unregister_netdevice_notifier_dev_net);
+
+static void move_netdevice_notifiers_dev_net(struct net_device *dev,
+ struct net *net)
+{
+ struct netdev_net_notifier *nn;
+
+ list_for_each_entry(nn, &dev->net_notifier_list, list) {
+ __unregister_netdevice_notifier_net(dev_net(dev), nn->nb);
+ __register_netdevice_notifier_net(net, nn->nb, true);
+ }
+}
+
/**
* call_netdevice_notifiers_info - call all network notifier blocks
* @val: value passed unmodified to notifier function
@@ -3249,7 +3299,7 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
segs = skb_mac_gso_segment(skb, features);
- if (unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs)))
+ if (segs != skb && unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs)))
skb_warn_bad_offload(skb);
return segs;
@@ -5489,9 +5539,29 @@ static void flush_all_backlogs(void)
put_online_cpus();
}
+/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
+static void gro_normal_list(struct napi_struct *napi)
+{
+ if (!napi->rx_count)
+ return;
+ netif_receive_skb_list_internal(&napi->rx_list);
+ INIT_LIST_HEAD(&napi->rx_list);
+ napi->rx_count = 0;
+}
+
+/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
+ * pass the whole batch up to the stack.
+ */
+static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
+{
+ list_add_tail(&skb->list, &napi->rx_list);
+ if (++napi->rx_count >= gro_normal_batch)
+ gro_normal_list(napi);
+}
+
INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int));
INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int));
-static int napi_gro_complete(struct sk_buff *skb)
+static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
{
struct packet_offload *ptype;
__be16 type = skb->protocol;
@@ -5524,7 +5594,8 @@ static int napi_gro_complete(struct sk_buff *skb)
}
out:
- return netif_receive_skb_internal(skb);
+ gro_normal_one(napi, skb);
+ return NET_RX_SUCCESS;
}
static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
@@ -5537,7 +5608,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
return;
skb_list_del_init(skb);
- napi_gro_complete(skb);
+ napi_gro_complete(napi, skb);
napi->gro_hash[index].count--;
}
@@ -5639,7 +5710,7 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
}
}
-static void gro_flush_oldest(struct list_head *head)
+static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
{
struct sk_buff *oldest;
@@ -5655,7 +5726,7 @@ static void gro_flush_oldest(struct list_head *head)
* SKB to the chain.
*/
skb_list_del_init(oldest);
- napi_gro_complete(oldest);
+ napi_gro_complete(napi, oldest);
}
INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *,
@@ -5731,7 +5802,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
if (pp) {
skb_list_del_init(pp);
- napi_gro_complete(pp);
+ napi_gro_complete(napi, pp);
napi->gro_hash[hash].count--;
}
@@ -5742,7 +5813,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
goto normal;
if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) {
- gro_flush_oldest(gro_head);
+ gro_flush_oldest(napi, gro_head);
} else {
napi->gro_hash[hash].count++;
}
@@ -5800,26 +5871,6 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
}
EXPORT_SYMBOL(gro_find_complete_by_type);
-/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
-static void gro_normal_list(struct napi_struct *napi)
-{
- if (!napi->rx_count)
- return;
- netif_receive_skb_list_internal(&napi->rx_list);
- INIT_LIST_HEAD(&napi->rx_list);
- napi->rx_count = 0;
-}
-
-/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
- * pass the whole batch up to the stack.
- */
-static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
-{
- list_add_tail(&skb->list, &napi->rx_list);
- if (++napi->rx_count >= gro_normal_batch)
- gro_normal_list(napi);
-}
-
static void napi_skb_free_stolen_head(struct sk_buff *skb)
{
skb_dst_drop(skb);
@@ -6198,8 +6249,6 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
NAPIF_STATE_IN_BUSY_POLL)))
return false;
- gro_normal_list(n);
-
if (n->gro_bitmask) {
unsigned long timeout = 0;
@@ -6215,6 +6264,9 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
hrtimer_start(&n->timer, ns_to_ktime(timeout),
HRTIMER_MODE_REL_PINNED);
}
+
+ gro_normal_list(n);
+
if (unlikely(!list_empty(&n->poll_list))) {
/* If n->poll_list is not empty, we need to mask irqs */
local_irq_save(flags);
@@ -6546,8 +6598,6 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
goto out_unlock;
}
- gro_normal_list(n);
-
if (n->gro_bitmask) {
/* flush too old packets
* If HZ < 1000, flush all packets.
@@ -6555,6 +6605,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
napi_gro_flush(n, HZ >= 1000);
}
+ gro_normal_list(n);
+
/* Some drivers may have called napi_schedule
* prior to exhausting their budget.
*/
@@ -8192,6 +8244,22 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
}
EXPORT_SYMBOL(__dev_set_mtu);
+int dev_validate_mtu(struct net_device *dev, int new_mtu,
+ struct netlink_ext_ack *extack)
+{
+ /* MTU must be positive, and in range */
+ if (new_mtu < 0 || new_mtu < dev->min_mtu) {
+ NL_SET_ERR_MSG(extack, "mtu less than device minimum");
+ return -EINVAL;
+ }
+
+ if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
+ NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
+ return -EINVAL;
+ }
+ return 0;
+}
+
/**
* dev_set_mtu_ext - Change maximum transfer unit
* @dev: device
@@ -8208,16 +8276,9 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu,
if (new_mtu == dev->mtu)
return 0;
- /* MTU must be positive, and in range */
- if (new_mtu < 0 || new_mtu < dev->min_mtu) {
- NL_SET_ERR_MSG(extack, "mtu less than device minimum");
- return -EINVAL;
- }
-
- if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
- NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
- return -EINVAL;
- }
+ err = dev_validate_mtu(dev, new_mtu, extack);
+ if (err)
+ return err;
if (!netif_device_present(dev))
return -ENODEV;
@@ -9192,22 +9253,10 @@ static void netdev_unregister_lockdep_key(struct net_device *dev)
void netdev_update_lockdep_key(struct net_device *dev)
{
- struct netdev_queue *queue;
- int i;
-
- lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
lockdep_unregister_key(&dev->addr_list_lock_key);
-
- lockdep_register_key(&dev->qdisc_xmit_lock_key);
lockdep_register_key(&dev->addr_list_lock_key);
lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
- for (i = 0; i < dev->num_tx_queues; i++) {
- queue = netdev_get_tx_queue(dev, i);
-
- lockdep_set_class(&queue->_xmit_lock,
- &dev->qdisc_xmit_lock_key);
- }
}
EXPORT_SYMBOL(netdev_update_lockdep_key);
@@ -9284,7 +9333,7 @@ int register_netdevice(struct net_device *dev)
/* Transfer changeable features to wanted_features and enable
* software offloads (GSO and GRO).
*/
- dev->hw_features |= NETIF_F_SOFT_FEATURES;
+ dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF);
dev->features |= NETIF_F_SOFT_FEATURES;
if (dev->netdev_ops->ndo_udp_tunnel_add) {
@@ -9329,8 +9378,10 @@ int register_netdevice(struct net_device *dev)
goto err_uninit;
ret = netdev_register_kobject(dev);
- if (ret)
+ if (ret) {
+ dev->reg_state = NETREG_UNREGISTERED;
goto err_uninit;
+ }
dev->reg_state = NETREG_REGISTERED;
__netdev_update_features(dev);
@@ -9777,6 +9828,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
INIT_LIST_HEAD(&dev->adj_list.lower);
INIT_LIST_HEAD(&dev->ptype_all);
INIT_LIST_HEAD(&dev->ptype_specific);
+ INIT_LIST_HEAD(&dev->net_notifier_list);
#ifdef CONFIG_NET_SCHED
hash_init(dev->qdisc_hash);
#endif
@@ -9847,6 +9899,8 @@ void free_netdev(struct net_device *dev)
free_percpu(dev->pcpu_refcnt);
dev->pcpu_refcnt = NULL;
+ free_percpu(dev->xdp_bulkq);
+ dev->xdp_bulkq = NULL;
netdev_unregister_lockdep_key(dev);
@@ -10038,6 +10092,9 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE);
netdev_adjacent_del_links(dev);
+ /* Move per-net netdevice notifiers that are following the netdevice */
+ move_netdevice_notifiers_dev_net(dev, net);
+
/* Actually switch the network namespace */
dev_net_set(dev, net);
dev->ifindex = new_ifindex;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 4c63c9a..ca1df0e 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4843,22 +4843,100 @@ devlink_health_reporter_destroy(struct devlink_health_reporter *reporter)
}
EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy);
-void
-devlink_health_reporter_state_update(struct devlink_health_reporter *reporter,
- enum devlink_health_reporter_state state)
+static int
+devlink_nl_health_reporter_fill(struct sk_buff *msg,
+ struct devlink *devlink,
+ struct devlink_health_reporter *reporter,
+ enum devlink_command cmd, u32 portid,
+ u32 seq, int flags)
{
- if (WARN_ON(state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY &&
- state != DEVLINK_HEALTH_REPORTER_STATE_ERROR))
- return;
+ struct nlattr *reporter_attr;
+ void *hdr;
- if (reporter->health_state == state)
- return;
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
- reporter->health_state = state;
- trace_devlink_health_reporter_state_update(reporter->devlink,
- reporter->ops->name, state);
+ if (devlink_nl_put_handle(msg, devlink))
+ goto genlmsg_cancel;
+
+ reporter_attr = nla_nest_start_noflag(msg,
+ DEVLINK_ATTR_HEALTH_REPORTER);
+ if (!reporter_attr)
+ goto genlmsg_cancel;
+ if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME,
+ reporter->ops->name))
+ goto reporter_nest_cancel;
+ if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE,
+ reporter->health_state))
+ goto reporter_nest_cancel;
+ if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT,
+ reporter->error_count, DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
+ if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT,
+ reporter->recovery_count, DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
+ if (reporter->ops->recover &&
+ nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD,
+ reporter->graceful_period,
+ DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
+ if (reporter->ops->recover &&
+ nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,
+ reporter->auto_recover))
+ goto reporter_nest_cancel;
+ if (reporter->dump_fmsg &&
+ nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS,
+ jiffies_to_msecs(reporter->dump_ts),
+ DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
+ if (reporter->dump_fmsg &&
+ nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS,
+ reporter->dump_real_ts, DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
+
+ nla_nest_end(msg, reporter_attr);
+ genlmsg_end(msg, hdr);
+ return 0;
+
+reporter_nest_cancel:
+ nla_nest_end(msg, reporter_attr);
+genlmsg_cancel:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
}
-EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update);
+
+static void devlink_recover_notify(struct devlink_health_reporter *reporter,
+ enum devlink_command cmd)
+{
+ struct sk_buff *msg;
+ int err;
+
+ WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ err = devlink_nl_health_reporter_fill(msg, reporter->devlink,
+ reporter, cmd, 0, 0, 0);
+ if (err) {
+ nlmsg_free(msg);
+ return;
+ }
+
+ genlmsg_multicast_netns(&devlink_nl_family,
+ devlink_net(reporter->devlink),
+ msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+void
+devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter)
+{
+ reporter->recovery_count++;
+ reporter->last_recovery_ts = jiffies;
+}
+EXPORT_SYMBOL_GPL(devlink_health_reporter_recovery_done);
static int
devlink_health_reporter_recover(struct devlink_health_reporter *reporter,
@@ -4876,9 +4954,9 @@ devlink_health_reporter_recover(struct devlink_health_reporter *reporter,
if (err)
return err;
- reporter->recovery_count++;
+ devlink_health_reporter_recovery_done(reporter);
reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY;
- reporter->last_recovery_ts = jiffies;
+ devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
return 0;
}
@@ -4945,6 +5023,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
reporter->error_count++;
prev_health_state = reporter->health_state;
reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR;
+ devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
/* abort if the previous error wasn't recovered */
if (reporter->auto_recover &&
@@ -5027,68 +5106,23 @@ devlink_health_reporter_put(struct devlink_health_reporter *reporter)
refcount_dec(&reporter->refcount);
}
-static int
-devlink_nl_health_reporter_fill(struct sk_buff *msg,
- struct devlink *devlink,
- struct devlink_health_reporter *reporter,
- enum devlink_command cmd, u32 portid,
- u32 seq, int flags)
+void
+devlink_health_reporter_state_update(struct devlink_health_reporter *reporter,
+ enum devlink_health_reporter_state state)
{
- struct nlattr *reporter_attr;
- void *hdr;
+ if (WARN_ON(state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY &&
+ state != DEVLINK_HEALTH_REPORTER_STATE_ERROR))
+ return;
- hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
- if (!hdr)
- return -EMSGSIZE;
+ if (reporter->health_state == state)
+ return;
- if (devlink_nl_put_handle(msg, devlink))
- goto genlmsg_cancel;
-
- reporter_attr = nla_nest_start_noflag(msg,
- DEVLINK_ATTR_HEALTH_REPORTER);
- if (!reporter_attr)
- goto genlmsg_cancel;
- if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME,
- reporter->ops->name))
- goto reporter_nest_cancel;
- if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE,
- reporter->health_state))
- goto reporter_nest_cancel;
- if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT,
- reporter->error_count, DEVLINK_ATTR_PAD))
- goto reporter_nest_cancel;
- if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT,
- reporter->recovery_count, DEVLINK_ATTR_PAD))
- goto reporter_nest_cancel;
- if (reporter->ops->recover &&
- nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD,
- reporter->graceful_period,
- DEVLINK_ATTR_PAD))
- goto reporter_nest_cancel;
- if (reporter->ops->recover &&
- nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,
- reporter->auto_recover))
- goto reporter_nest_cancel;
- if (reporter->dump_fmsg &&
- nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS,
- jiffies_to_msecs(reporter->dump_ts),
- DEVLINK_ATTR_PAD))
- goto reporter_nest_cancel;
- if (reporter->dump_fmsg &&
- nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS,
- reporter->dump_real_ts, DEVLINK_ATTR_PAD))
- goto reporter_nest_cancel;
-
- nla_nest_end(msg, reporter_attr);
- genlmsg_end(msg, hdr);
- return 0;
-
-reporter_nest_cancel:
- nla_nest_end(msg, reporter_attr);
-genlmsg_cancel:
- genlmsg_cancel(msg, hdr);
- return -EMSGSIZE;
+ reporter->health_state = state;
+ trace_devlink_health_reporter_state_update(reporter->devlink,
+ reporter->ops->name, state);
+ devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
}
+EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update);
static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb,
struct genl_info *info)
@@ -6406,7 +6440,7 @@ static bool devlink_port_type_should_warn(struct devlink_port *devlink_port)
devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA;
}
-#define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 30)
+#define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600)
static void devlink_port_type_warn_schedule(struct devlink_port *devlink_port)
{
@@ -7563,7 +7597,7 @@ void devlink_region_destroy(struct devlink_region *region)
EXPORT_SYMBOL_GPL(devlink_region_destroy);
/**
- * devlink_region_shapshot_id_get - get snapshot ID
+ * devlink_region_snapshot_id_get - get snapshot ID
*
* This callback should be called when adding a new snapshot,
* Driver should use the same id for multiple snapshots taken
@@ -7571,7 +7605,7 @@ EXPORT_SYMBOL_GPL(devlink_region_destroy);
*
* @devlink: devlink
*/
-u32 devlink_region_shapshot_id_get(struct devlink *devlink)
+u32 devlink_region_snapshot_id_get(struct devlink *devlink)
{
u32 id;
@@ -7581,7 +7615,7 @@ u32 devlink_region_shapshot_id_get(struct devlink *devlink)
return id;
}
-EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get);
+EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get);
/**
* devlink_region_snapshot_create - create a new snapshot
@@ -7674,6 +7708,9 @@ static const struct devlink_trap devlink_trap_generic[] = {
DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION),
DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION),
DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION),
+ DEVLINK_TRAP(NON_ROUTABLE, DROP),
+ DEVLINK_TRAP(DECAP_ERROR, EXCEPTION),
+ DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP),
};
#define DEVLINK_TRAP_GROUP(_id) \
@@ -7686,6 +7723,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = {
DEVLINK_TRAP_GROUP(L2_DROPS),
DEVLINK_TRAP_GROUP(L3_DROPS),
DEVLINK_TRAP_GROUP(BUFFER_DROPS),
+ DEVLINK_TRAP_GROUP(TUNNEL_DROPS),
};
static int devlink_trap_generic_verify(const struct devlink_trap *trap)
diff --git a/net/core/filter.c b/net/core/filter.c
index 42fd17c..792e374 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2231,10 +2231,10 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
/* First find the starting scatterlist element */
i = msg->sg.start;
do {
+ offset += len;
len = sk_msg_elem(msg, i)->length;
if (start < offset + len)
break;
- offset += len;
sk_msg_iter_var_next(i);
} while (i != msg->sg.end);
@@ -2346,7 +2346,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
u32, len, u64, flags)
{
struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge;
- u32 new, i = 0, l, space, copy = 0, offset = 0;
+ u32 new, i = 0, l = 0, space, copy = 0, offset = 0;
u8 *raw, *to, *from;
struct page *page;
@@ -2356,11 +2356,11 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
/* First find the starting scatterlist element */
i = msg->sg.start;
do {
+ offset += l;
l = sk_msg_elem(msg, i)->length;
if (start < offset + l)
break;
- offset += l;
sk_msg_iter_var_next(i);
} while (i != msg->sg.end);
@@ -2415,6 +2415,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
sk_msg_iter_var_next(i);
sg_unmark_end(psge);
+ sg_unmark_end(&rsge);
sk_msg_iter_next(msg, end);
}
@@ -2506,7 +2507,7 @@ static void sk_msg_shift_right(struct sk_msg *msg, int i)
BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
u32, len, u64, flags)
{
- u32 i = 0, l, space, offset = 0;
+ u32 i = 0, l = 0, space, offset = 0;
u64 last = start + len;
int pop;
@@ -2516,11 +2517,11 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
/* First find the starting scatterlist element */
i = msg->sg.start;
do {
+ offset += l;
l = sk_msg_elem(msg, i)->length;
if (start < offset + l)
break;
- offset += l;
sk_msg_iter_var_next(i);
} while (i != msg->sg.end);
@@ -3458,58 +3459,6 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
.arg2_type = ARG_ANYTHING,
};
-static int __bpf_tx_xdp(struct net_device *dev,
- struct bpf_map *map,
- struct xdp_buff *xdp,
- u32 index)
-{
- struct xdp_frame *xdpf;
- int err, sent;
-
- if (!dev->netdev_ops->ndo_xdp_xmit) {
- return -EOPNOTSUPP;
- }
-
- err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
- if (unlikely(err))
- return err;
-
- xdpf = convert_to_xdp_frame(xdp);
- if (unlikely(!xdpf))
- return -EOVERFLOW;
-
- sent = dev->netdev_ops->ndo_xdp_xmit(dev, 1, &xdpf, XDP_XMIT_FLUSH);
- if (sent <= 0)
- return sent;
- return 0;
-}
-
-static noinline int
-xdp_do_redirect_slow(struct net_device *dev, struct xdp_buff *xdp,
- struct bpf_prog *xdp_prog, struct bpf_redirect_info *ri)
-{
- struct net_device *fwd;
- u32 index = ri->tgt_index;
- int err;
-
- fwd = dev_get_by_index_rcu(dev_net(dev), index);
- ri->tgt_index = 0;
- if (unlikely(!fwd)) {
- err = -EINVAL;
- goto err;
- }
-
- err = __bpf_tx_xdp(fwd, NULL, xdp, 0);
- if (unlikely(err))
- goto err;
-
- _trace_xdp_redirect(dev, xdp_prog, index);
- return 0;
-err:
- _trace_xdp_redirect_err(dev, xdp_prog, index, err);
- return err;
-}
-
static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
struct bpf_map *map, struct xdp_buff *xdp)
{
@@ -3522,18 +3471,18 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
case BPF_MAP_TYPE_XSKMAP:
return __xsk_map_redirect(fwd, xdp);
default:
- break;
+ return -EBADRQC;
}
return 0;
}
-void xdp_do_flush_map(void)
+void xdp_do_flush(void)
{
- __dev_map_flush();
+ __dev_flush();
__cpu_map_flush();
__xsk_map_flush();
}
-EXPORT_SYMBOL_GPL(xdp_do_flush_map);
+EXPORT_SYMBOL_GPL(xdp_do_flush);
static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
{
@@ -3568,10 +3517,11 @@ void bpf_clear_redirect_map(struct bpf_map *map)
}
}
-static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
- struct bpf_prog *xdp_prog, struct bpf_map *map,
- struct bpf_redirect_info *ri)
+int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
+ struct bpf_prog *xdp_prog)
{
+ struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+ struct bpf_map *map = READ_ONCE(ri->map);
u32 index = ri->tgt_index;
void *fwd = ri->tgt_value;
int err;
@@ -3580,7 +3530,18 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
ri->tgt_value = NULL;
WRITE_ONCE(ri->map, NULL);
- err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
+ if (unlikely(!map)) {
+ fwd = dev_get_by_index_rcu(dev_net(dev), index);
+ if (unlikely(!fwd)) {
+ err = -EINVAL;
+ goto err;
+ }
+
+ err = dev_xdp_enqueue(fwd, xdp, dev);
+ } else {
+ err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
+ }
+
if (unlikely(err))
goto err;
@@ -3590,18 +3551,6 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
return err;
}
-
-int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
- struct bpf_prog *xdp_prog)
-{
- struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
- struct bpf_map *map = READ_ONCE(ri->map);
-
- if (likely(map))
- return xdp_do_redirect_map(dev, xdp, xdp_prog, map, ri);
-
- return xdp_do_redirect_slow(dev, xdp, xdp_prog, ri);
-}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
static int xdp_do_generic_redirect_map(struct net_device *dev,
@@ -5277,8 +5226,7 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
if (sk) {
sk = sk_to_full_sk(sk);
if (!sk_fullsock(sk)) {
- if (!sock_flag(sk, SOCK_RCU_FREE))
- sock_gen_put(sk);
+ sock_gen_put(sk);
return NULL;
}
}
@@ -5315,8 +5263,7 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
if (sk) {
sk = sk_to_full_sk(sk);
if (!sk_fullsock(sk)) {
- if (!sock_flag(sk, SOCK_RCU_FREE))
- sock_gen_put(sk);
+ sock_gen_put(sk);
return NULL;
}
}
@@ -5383,7 +5330,8 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
BPF_CALL_1(bpf_sk_release, struct sock *, sk)
{
- if (!sock_flag(sk, SOCK_RCU_FREE))
+ /* Only full sockets have sk->sk_flags. */
+ if (!sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE))
sock_gen_put(sk);
return 0;
}
@@ -5935,7 +5883,7 @@ bool bpf_helper_changes_pkt_data(void *func)
return false;
}
-static const struct bpf_func_proto *
+const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
switch (func_id) {
@@ -5975,6 +5923,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_spin_unlock_proto;
case BPF_FUNC_trace_printk:
return bpf_get_trace_printk_proto();
+ case BPF_FUNC_jiffies64:
+ return &bpf_jiffies64_proto;
default:
return NULL;
}
@@ -7607,21 +7557,21 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
break;
case offsetof(struct bpf_sock, type):
- BUILD_BUG_ON(HWEIGHT32(SK_FL_TYPE_MASK) != BITS_PER_BYTE * 2);
- *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
- offsetof(struct sock, __sk_flags_offset));
- *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK);
- *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT);
- *target_size = 2;
+ *insn++ = BPF_LDX_MEM(
+ BPF_FIELD_SIZEOF(struct sock, sk_type),
+ si->dst_reg, si->src_reg,
+ bpf_target_off(struct sock, sk_type,
+ sizeof_field(struct sock, sk_type),
+ target_size));
break;
case offsetof(struct bpf_sock, protocol):
- BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE);
- *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
- offsetof(struct sock, __sk_flags_offset));
- *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
- *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT);
- *target_size = 1;
+ *insn++ = BPF_LDX_MEM(
+ BPF_FIELD_SIZEOF(struct sock, sk_protocol),
+ si->dst_reg, si->src_reg,
+ bpf_target_off(struct sock, sk_protocol,
+ sizeof_field(struct sock, sk_protocol),
+ target_size));
break;
case offsetof(struct bpf_sock, src_ip4):
@@ -7903,20 +7853,13 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
break;
case offsetof(struct bpf_sock_addr, type):
- SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(
- struct bpf_sock_addr_kern, struct sock, sk,
- __sk_flags_offset, BPF_W, 0);
- *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK);
- *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT);
+ SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern,
+ struct sock, sk, sk_type);
break;
case offsetof(struct bpf_sock_addr, protocol):
- SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(
- struct bpf_sock_addr_kern, struct sock, sk,
- __sk_flags_offset, BPF_W, 0);
- *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
- *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg,
- SK_FL_PROTO_SHIFT);
+ SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern,
+ struct sock, sk, sk_protocol);
break;
case offsetof(struct bpf_sock_addr, msg_src_ip4):
@@ -8835,11 +8778,11 @@ sk_reuseport_is_valid_access(int off, int size,
skb, \
SKB_FIELD)
-#define SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(SK_FIELD, BPF_SIZE, EXTRA_OFF) \
- SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(struct sk_reuseport_kern, \
- struct sock, \
- sk, \
- SK_FIELD, BPF_SIZE, EXTRA_OFF)
+#define SK_REUSEPORT_LOAD_SK_FIELD(SK_FIELD) \
+ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \
+ struct sock, \
+ sk, \
+ SK_FIELD)
static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
@@ -8863,16 +8806,7 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
break;
case offsetof(struct sk_reuseport_md, ip_protocol):
- BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE);
- SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset,
- BPF_W, 0);
- *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
- *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg,
- SK_FL_PROTO_SHIFT);
- /* SK_FL_PROTO_MASK and SK_FL_PROTO_SHIFT are endian
- * aware. No further narrowing or masking is needed.
- */
- *target_size = 1;
+ SK_REUSEPORT_LOAD_SK_FIELD(sk_protocol);
break;
case offsetof(struct sk_reuseport_md, data_end):
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2dbbb03..f560b49 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -233,7 +233,7 @@ static bool icmp_has_id(u8 type)
* @skb: sk_buff to extract from
* @key_icmp: struct flow_dissector_key_icmp to fill
* @data: raw buffer pointer to the packet
- * @toff: offset to extract at
+ * @thoff: offset to extract at
* @hlen: packet header length
*/
void skb_flow_get_icmp_tci(const struct sk_buff *skb,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 920784a..789a73a 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3290,6 +3290,7 @@ static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos)
*pos = cpu+1;
return per_cpu_ptr(tbl->stats, cpu);
}
+ (*pos)++;
return NULL;
}
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 3940284..757cc1d 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -211,16 +211,10 @@ static int net_eq_idr(int id, void *net, void *peer)
return 0;
}
-/* Should be called with nsid_lock held. If a new id is assigned, the bool alloc
- * is set to true, thus the caller knows that the new id must be notified via
- * rtnl.
- */
-static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc)
+/* Must be called from RCU-critical section or with nsid_lock held */
+static int __peernet2id(const struct net *net, struct net *peer)
{
int id = idr_for_each(&net->netns_ids, net_eq_idr, peer);
- bool alloc_it = *alloc;
-
- *alloc = false;
/* Magic value for id 0. */
if (id == NET_ID_ZERO)
@@ -228,23 +222,9 @@ static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc)
if (id > 0)
return id;
- if (alloc_it) {
- id = alloc_netid(net, peer, -1);
- *alloc = true;
- return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
- }
-
return NETNSA_NSID_NOT_ASSIGNED;
}
-/* should be called with nsid_lock held */
-static int __peernet2id(struct net *net, struct net *peer)
-{
- bool no = false;
-
- return __peernet2id_alloc(net, peer, &no);
-}
-
static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
struct nlmsghdr *nlh, gfp_t gfp);
/* This function returns the id of a peer netns. If no id is assigned, one will
@@ -252,38 +232,50 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
*/
int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
{
- bool alloc = false, alive = false;
int id;
if (refcount_read(&net->count) == 0)
return NETNSA_NSID_NOT_ASSIGNED;
- spin_lock_bh(&net->nsid_lock);
- /*
- * When peer is obtained from RCU lists, we may race with
+
+ spin_lock(&net->nsid_lock);
+ id = __peernet2id(net, peer);
+ if (id >= 0) {
+ spin_unlock(&net->nsid_lock);
+ return id;
+ }
+
+ /* When peer is obtained from RCU lists, we may race with
* its cleanup. Check whether it's alive, and this guarantees
* we never hash a peer back to net->netns_ids, after it has
* just been idr_remove()'d from there in cleanup_net().
*/
- if (maybe_get_net(peer))
- alive = alloc = true;
- id = __peernet2id_alloc(net, peer, &alloc);
- spin_unlock_bh(&net->nsid_lock);
- if (alloc && id >= 0)
- rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp);
- if (alive)
- put_net(peer);
+ if (!maybe_get_net(peer)) {
+ spin_unlock(&net->nsid_lock);
+ return NETNSA_NSID_NOT_ASSIGNED;
+ }
+
+ id = alloc_netid(net, peer, -1);
+ spin_unlock(&net->nsid_lock);
+
+ put_net(peer);
+ if (id < 0)
+ return NETNSA_NSID_NOT_ASSIGNED;
+
+ rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp);
+
return id;
}
EXPORT_SYMBOL_GPL(peernet2id_alloc);
/* This function returns, if assigned, the id of a peer netns. */
-int peernet2id(struct net *net, struct net *peer)
+int peernet2id(const struct net *net, struct net *peer)
{
int id;
- spin_lock_bh(&net->nsid_lock);
+ rcu_read_lock();
id = __peernet2id(net, peer);
- spin_unlock_bh(&net->nsid_lock);
+ rcu_read_unlock();
+
return id;
}
EXPORT_SYMBOL(peernet2id);
@@ -291,12 +283,12 @@ EXPORT_SYMBOL(peernet2id);
/* This function returns true is the peer netns has an id assigned into the
* current netns.
*/
-bool peernet_has_id(struct net *net, struct net *peer)
+bool peernet_has_id(const struct net *net, struct net *peer)
{
return peernet2id(net, peer) >= 0;
}
-struct net *get_net_ns_by_id(struct net *net, int id)
+struct net *get_net_ns_by_id(const struct net *net, int id)
{
struct net *peer;
@@ -528,20 +520,20 @@ static void unhash_nsid(struct net *net, struct net *last)
for_each_net(tmp) {
int id;
- spin_lock_bh(&tmp->nsid_lock);
+ spin_lock(&tmp->nsid_lock);
id = __peernet2id(tmp, net);
if (id >= 0)
idr_remove(&tmp->netns_ids, id);
- spin_unlock_bh(&tmp->nsid_lock);
+ spin_unlock(&tmp->nsid_lock);
if (id >= 0)
rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL,
GFP_KERNEL);
if (tmp == last)
break;
}
- spin_lock_bh(&net->nsid_lock);
+ spin_lock(&net->nsid_lock);
idr_destroy(&net->netns_ids);
- spin_unlock_bh(&net->nsid_lock);
+ spin_unlock(&net->nsid_lock);
}
static LLIST_HEAD(cleanup_list);
@@ -754,9 +746,9 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
return PTR_ERR(peer);
}
- spin_lock_bh(&net->nsid_lock);
+ spin_lock(&net->nsid_lock);
if (__peernet2id(net, peer) >= 0) {
- spin_unlock_bh(&net->nsid_lock);
+ spin_unlock(&net->nsid_lock);
err = -EEXIST;
NL_SET_BAD_ATTR(extack, nla);
NL_SET_ERR_MSG(extack,
@@ -765,7 +757,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
}
err = alloc_netid(net, peer, nsid);
- spin_unlock_bh(&net->nsid_lock);
+ spin_unlock(&net->nsid_lock);
if (err >= 0) {
rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid,
nlh, GFP_KERNEL);
@@ -950,6 +942,7 @@ struct rtnl_net_dump_cb {
int s_idx;
};
+/* Runs in RCU-critical section. */
static int rtnl_net_dumpid_one(int id, void *peer, void *data)
{
struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data;
@@ -1034,19 +1027,9 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
goto end;
}
- spin_lock_bh(&net_cb.tgt_net->nsid_lock);
- if (net_cb.fillargs.add_ref &&
- !net_eq(net_cb.ref_net, net_cb.tgt_net) &&
- !spin_trylock_bh(&net_cb.ref_net->nsid_lock)) {
- spin_unlock_bh(&net_cb.tgt_net->nsid_lock);
- err = -EAGAIN;
- goto end;
- }
+ rcu_read_lock();
idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb);
- if (net_cb.fillargs.add_ref &&
- !net_eq(net_cb.ref_net, net_cb.tgt_net))
- spin_unlock_bh(&net_cb.ref_net->nsid_lock);
- spin_unlock_bh(&net_cb.tgt_net->nsid_lock);
+ rcu_read_unlock();
cb->args[0] = net_cb.idx;
end:
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 294bfcf..890be1b 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -323,6 +323,10 @@ struct pktgen_dev {
struct in6_addr max_in6_daddr;
struct in6_addr min_in6_saddr;
struct in6_addr max_in6_saddr;
+ u64 max_in6_h;
+ u64 max_in6_l;
+ u64 min_in6_h;
+ u64 min_in6_l;
/* If we're doing ranges, random or incremental, then this
* defines the min/max for those ranges.
@@ -1355,6 +1359,59 @@ static ssize_t pktgen_if_write(struct file *file,
sprintf(pg_result, "OK: dst6_max=%s", buf);
return count;
}
+ if (!strcmp(name, "src6_min")) {
+ len = strn_len(&user_buffer[i], sizeof(buf) - 1);
+ if (len < 0)
+ return len;
+
+ pkt_dev->flags |= F_IPV6;
+
+ if (copy_from_user(buf, &user_buffer[i], len))
+ return -EFAULT;
+ buf[len] = 0;
+
+ in6_pton(buf, -1, pkt_dev->min_in6_saddr.s6_addr, -1, NULL);
+ snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_saddr);
+
+ memcpy(&pkt_dev->min_in6_h, pkt_dev->min_in6_saddr.s6_addr, 8);
+ memcpy(&pkt_dev->min_in6_l, pkt_dev->min_in6_saddr.s6_addr + 8, 8);
+ pkt_dev->min_in6_h = be64_to_cpu(pkt_dev->min_in6_h);
+ pkt_dev->min_in6_l = be64_to_cpu(pkt_dev->min_in6_l);
+
+ pkt_dev->cur_in6_saddr = pkt_dev->min_in6_saddr;
+ if (debug)
+ pr_debug("src6_min set to: %s\n", buf);
+
+ i += len;
+ sprintf(pg_result, "OK: src6_min=%s", buf);
+ return count;
+ }
+ if (!strcmp(name, "src6_max")) {
+ len = strn_len(&user_buffer[i], sizeof(buf) - 1);
+ if (len < 0)
+ return len;
+
+ pkt_dev->flags |= F_IPV6;
+
+ if (copy_from_user(buf, &user_buffer[i], len))
+ return -EFAULT;
+ buf[len] = 0;
+
+ in6_pton(buf, -1, pkt_dev->max_in6_saddr.s6_addr, -1, NULL);
+ snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->max_in6_saddr);
+
+ memcpy(&pkt_dev->max_in6_h, pkt_dev->max_in6_saddr.s6_addr, 8);
+ memcpy(&pkt_dev->max_in6_l, pkt_dev->max_in6_saddr.s6_addr + 8, 8);
+ pkt_dev->max_in6_h = be64_to_cpu(pkt_dev->max_in6_h);
+ pkt_dev->max_in6_l = be64_to_cpu(pkt_dev->max_in6_l);
+
+ if (debug)
+ pr_debug("src6_max set to: %s\n", buf);
+
+ i += len;
+ sprintf(pg_result, "OK: src6_max=%s", buf);
+ return count;
+ }
if (!strcmp(name, "src6")) {
len = strn_len(&user_buffer[i], sizeof(buf) - 1);
if (len < 0)
@@ -2286,6 +2343,45 @@ static void set_cur_queue_map(struct pktgen_dev *pkt_dev)
pkt_dev->cur_queue_map = pkt_dev->cur_queue_map % pkt_dev->odev->real_num_tx_queues;
}
+/* generate ipv6 source addr */
+static void set_src_in6_addr(struct pktgen_dev *pkt_dev)
+{
+ u64 min6, max6, rand, i;
+ struct in6_addr addr6;
+ __be64 addr_l, *t;
+
+ min6 = pkt_dev->min_in6_l;
+ max6 = pkt_dev->max_in6_l;
+
+ /* only generate source address in least significant 64 bits range
+ * most significant 64 bits must be equal
+ */
+ if (pkt_dev->max_in6_h != pkt_dev->min_in6_h || min6 >= max6)
+ return;
+
+ addr6 = pkt_dev->min_in6_saddr;
+ t = (__be64 *)addr6.s6_addr + 1;
+
+ if (pkt_dev->flags & F_IPSRC_RND) {
+ do {
+ prandom_bytes(&rand, sizeof(rand));
+ rand = rand % (max6 - min6) + min6;
+ addr_l = cpu_to_be64(rand);
+ memcpy(t, &addr_l, 8);
+ } while (ipv6_addr_loopback(&addr6) ||
+ ipv6_addr_v4mapped(&addr6) ||
+ ipv6_addr_is_multicast(&addr6));
+ } else {
+ addr6 = pkt_dev->cur_in6_saddr;
+ i = be64_to_cpu(*t);
+ if (++i > max6)
+ i = min6;
+ addr_l = cpu_to_be64(i);
+ memcpy(t, &addr_l, 8);
+ }
+ pkt_dev->cur_in6_saddr = addr6;
+}
+
/* Increment/randomize headers according to flags and current values
* for IP src/dest, UDP src/dst port, MAC-Addr src/dst
*/
@@ -2454,6 +2550,8 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
}
} else { /* IPV6 * */
+ set_src_in6_addr(pkt_dev);
+
if (!ipv6_addr_any(&pkt_dev->min_in6_daddr)) {
int i;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 20bc406..cdad6ed 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3053,8 +3053,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
dev->rtnl_link_ops = ops;
dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
- if (tb[IFLA_MTU])
- dev->mtu = nla_get_u32(tb[IFLA_MTU]);
+ if (tb[IFLA_MTU]) {
+ u32 mtu = nla_get_u32(tb[IFLA_MTU]);
+ int err;
+
+ err = dev_validate_mtu(dev, mtu, extack);
+ if (err) {
+ free_netdev(dev);
+ return ERR_PTR(err);
+ }
+ dev->mtu = mtu;
+ }
if (tb[IFLA_ADDRESS]) {
memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]),
nla_len(tb[IFLA_ADDRESS]));
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 44b0894..864cb9e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -68,6 +68,7 @@
#include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <net/mpls.h>
+#include <net/mptcp.h>
#include <linux/uaccess.h>
#include <trace/events/skb.h>
@@ -3638,6 +3639,97 @@ static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb)
return head_frag;
}
+struct sk_buff *skb_segment_list(struct sk_buff *skb,
+ netdev_features_t features,
+ unsigned int offset)
+{
+ struct sk_buff *list_skb = skb_shinfo(skb)->frag_list;
+ unsigned int tnl_hlen = skb_tnl_header_len(skb);
+ unsigned int delta_truesize = 0;
+ unsigned int delta_len = 0;
+ struct sk_buff *tail = NULL;
+ struct sk_buff *nskb;
+
+ skb_push(skb, -skb_network_offset(skb) + offset);
+
+ skb_shinfo(skb)->frag_list = NULL;
+
+ do {
+ nskb = list_skb;
+ list_skb = list_skb->next;
+
+ if (!tail)
+ skb->next = nskb;
+ else
+ tail->next = nskb;
+
+ tail = nskb;
+
+ delta_len += nskb->len;
+ delta_truesize += nskb->truesize;
+
+ skb_push(nskb, -skb_network_offset(nskb) + offset);
+
+ __copy_skb_header(nskb, skb);
+
+ skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb));
+ skb_copy_from_linear_data_offset(skb, -tnl_hlen,
+ nskb->data - tnl_hlen,
+ offset + tnl_hlen);
+
+ if (skb_needs_linearize(nskb, features) &&
+ __skb_linearize(nskb))
+ goto err_linearize;
+
+ } while (list_skb);
+
+ skb->truesize = skb->truesize - delta_truesize;
+ skb->data_len = skb->data_len - delta_len;
+ skb->len = skb->len - delta_len;
+
+ skb_gso_reset(skb);
+
+ skb->prev = tail;
+
+ if (skb_needs_linearize(skb, features) &&
+ __skb_linearize(skb))
+ goto err_linearize;
+
+ skb_get(skb);
+
+ return skb;
+
+err_linearize:
+ kfree_skb_list(skb->next);
+ skb->next = NULL;
+ return ERR_PTR(-ENOMEM);
+}
+EXPORT_SYMBOL_GPL(skb_segment_list);
+
+int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
+{
+ if (unlikely(p->len + skb->len >= 65536))
+ return -E2BIG;
+
+ if (NAPI_GRO_CB(p)->last == p)
+ skb_shinfo(p)->frag_list = skb;
+ else
+ NAPI_GRO_CB(p)->last->next = skb;
+
+ skb_pull(skb, skb_gro_offset(skb));
+
+ NAPI_GRO_CB(p)->last = skb;
+ NAPI_GRO_CB(p)->count++;
+ p->data_len += skb->len;
+ p->truesize += skb->truesize;
+ p->len += skb->len;
+
+ NAPI_GRO_CB(skb)->same_flow = 1;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(skb_gro_receive_list);
+
/**
* skb_segment - Perform protocol segmentation on skb.
* @head_skb: buffer to segment
@@ -4109,6 +4201,9 @@ static const u8 skb_ext_type_len[] = {
#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
[TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext),
#endif
+#if IS_ENABLED(CONFIG_MPTCP)
+ [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext),
+#endif
};
static __always_inline unsigned int skb_ext_total_length(void)
@@ -4123,6 +4218,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
skb_ext_type_len[TC_SKB_EXT] +
#endif
+#if IS_ENABLED(CONFIG_MPTCP)
+ skb_ext_type_len[SKB_EXT_MPTCP] +
+#endif
0;
}
@@ -5980,7 +6078,14 @@ static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id)
return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE);
}
-static struct skb_ext *skb_ext_alloc(void)
+/**
+ * __skb_ext_alloc - allocate a new skb extensions storage
+ *
+ * Returns the newly allocated pointer. The pointer can later attached to a
+ * skb via __skb_ext_set().
+ * Note: caller must handle the skb_ext as an opaque data.
+ */
+struct skb_ext *__skb_ext_alloc(void)
{
struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC);
@@ -6021,6 +6126,30 @@ static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old,
}
/**
+ * __skb_ext_set - attach the specified extension storage to this skb
+ * @skb: buffer
+ * @id: extension id
+ * @ext: extension storage previously allocated via __skb_ext_alloc()
+ *
+ * Existing extensions, if any, are cleared.
+ *
+ * Returns the pointer to the extension.
+ */
+void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id,
+ struct skb_ext *ext)
+{
+ unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext);
+
+ skb_ext_put(skb);
+ newlen = newoff + skb_ext_type_len[id];
+ ext->chunks = newlen;
+ ext->offset[id] = newoff;
+ skb->extensions = ext;
+ skb->active_extensions = 1 << id;
+ return skb_ext_get_ptr(ext, id);
+}
+
+/**
* skb_ext_add - allocate space for given extension, COW if needed
* @skb: buffer
* @id: extension to allocate space for
@@ -6053,7 +6182,7 @@ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id)
} else {
newoff = SKB_EXT_CHUNKSIZEOF(*new);
- new = skb_ext_alloc();
+ new = __skb_ext_alloc();
if (!new)
return NULL;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 8459ad5..a4c8fac 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2786,7 +2786,7 @@ static void sock_def_error_report(struct sock *sk)
rcu_read_unlock();
}
-static void sock_def_readable(struct sock *sk)
+void sock_def_readable(struct sock *sk)
{
struct socket_wq *wq;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index eb114ee..8998e35 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -241,8 +241,11 @@ static void sock_map_free(struct bpf_map *map)
struct sock *sk;
sk = xchg(psk, NULL);
- if (sk)
+ if (sk) {
+ lock_sock(sk);
sock_map_unref(sk, psk);
+ release_sock(sk);
+ }
}
raw_spin_unlock_bh(&stab->lock);
rcu_read_unlock();
@@ -862,7 +865,9 @@ static void sock_hash_free(struct bpf_map *map)
raw_spin_lock_bh(&bucket->lock);
hlist_for_each_entry_safe(elem, node, &bucket->head, node) {
hlist_del_rcu(&elem->node);
+ lock_sock(elem->sk);
sock_map_unref(elem->sk, elem);
+ release_sock(elem->sk);
}
raw_spin_unlock_bh(&bucket->lock);
}
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index f19f179..91e9f22 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -107,7 +107,6 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
if (!more_reuse)
return NULL;
- more_reuse->max_socks = more_socks_size;
more_reuse->num_socks = reuse->num_socks;
more_reuse->prog = reuse->prog;
more_reuse->reuseport_id = reuse->reuseport_id;
diff --git a/net/core/utils.c b/net/core/utils.c
index 6b6e51d..1f31a39 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -438,6 +438,23 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
}
EXPORT_SYMBOL(inet_proto_csum_replace4);
+/**
+ * inet_proto_csum_replace16 - update layer 4 header checksum field
+ * @sum: Layer 4 header checksum field
+ * @skb: sk_buff for the packet
+ * @from: old IPv6 address
+ * @to: new IPv6 address
+ * @pseudohdr: True if layer 4 header checksum includes pseudoheader
+ *
+ * Update layer 4 header as per the update in IPv6 src/dst address.
+ *
+ * There is no need to update skb->csum in this function, because update in two
+ * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other
+ * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to
+ * update skb->csum, because update in 3 fields a.) IPv4 src/dst address,
+ * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as
+ * L4 Header checksum for skb->csum calculation.
+ */
void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
const __be32 *from, const __be32 *to,
bool pseudohdr)
@@ -449,9 +466,6 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
if (skb->ip_summed != CHECKSUM_PARTIAL) {
*sum = csum_fold(csum_partial(diff, sizeof(diff),
~csum_unfold(*sum)));
- if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr)
- skb->csum = ~csum_partial(diff, sizeof(diff),
- ~skb->csum);
} else if (pseudohdr)
*sum = ~csum_fold(csum_partial(diff, sizeof(diff),
csum_unfold(*sum)));
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index e19a92a..0a46ea3 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -670,7 +670,7 @@ static int dn_create(struct net *net, struct socket *sock, int protocol,
{
struct sock *sk;
- if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+ if (protocol < 0 || protocol > U8_MAX)
return -EINVAL;
if (!net_eq(net, &init_net))
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index c66abbe..e7c30b4 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -614,6 +614,32 @@ static int dsa_port_parse_dsa(struct dsa_port *dp)
return 0;
}
+static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp,
+ struct net_device *master)
+{
+ enum dsa_tag_protocol tag_protocol = DSA_TAG_PROTO_NONE;
+ struct dsa_switch *mds, *ds = dp->ds;
+ unsigned int mdp_upstream;
+ struct dsa_port *mdp;
+
+ /* It is possible to stack DSA switches onto one another when that
+ * happens the switch driver may want to know if its tagging protocol
+ * is going to work in such a configuration.
+ */
+ if (dsa_slave_dev_check(master)) {
+ mdp = dsa_slave_to_port(master);
+ mds = mdp->ds;
+ mdp_upstream = dsa_upstream_port(mds, mdp->index);
+ tag_protocol = mds->ops->get_tag_protocol(mds, mdp_upstream,
+ DSA_TAG_PROTO_NONE);
+ }
+
+ /* If the master device is not itself a DSA slave in a disjoint DSA
+ * tree, then return immediately.
+ */
+ return ds->ops->get_tag_protocol(ds, dp->index, tag_protocol);
+}
+
static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master)
{
struct dsa_switch *ds = dp->ds;
@@ -621,20 +647,21 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master)
const struct dsa_device_ops *tag_ops;
enum dsa_tag_protocol tag_protocol;
- tag_protocol = ds->ops->get_tag_protocol(ds, dp->index);
+ tag_protocol = dsa_get_tag_protocol(dp, master);
tag_ops = dsa_tag_driver_get(tag_protocol);
if (IS_ERR(tag_ops)) {
if (PTR_ERR(tag_ops) == -ENOPROTOOPT)
return -EPROBE_DEFER;
dev_warn(ds->dev, "No tagger for this switch\n");
+ dp->master = NULL;
return PTR_ERR(tag_ops);
}
+ dp->master = master;
dp->type = DSA_PORT_TYPE_CPU;
dp->filter = tag_ops->filter;
dp->rcv = tag_ops->rcv;
dp->tag_ops = tag_ops;
- dp->master = master;
dp->dst = dst;
return 0;
@@ -822,6 +849,19 @@ static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd)
return dsa_switch_parse_ports(ds, cd);
}
+static void dsa_switch_release_ports(struct dsa_switch *ds)
+{
+ struct dsa_switch_tree *dst = ds->dst;
+ struct dsa_port *dp, *next;
+
+ list_for_each_entry_safe(dp, next, &dst->ports, list) {
+ if (dp->ds != ds)
+ continue;
+ list_del(&dp->list);
+ kfree(dp);
+ }
+}
+
static int dsa_switch_probe(struct dsa_switch *ds)
{
struct dsa_switch_tree *dst;
@@ -838,12 +878,17 @@ static int dsa_switch_probe(struct dsa_switch *ds)
if (!ds->num_ports)
return -EINVAL;
- if (np)
+ if (np) {
err = dsa_switch_parse_of(ds, np);
- else if (pdata)
+ if (err)
+ dsa_switch_release_ports(ds);
+ } else if (pdata) {
err = dsa_switch_parse(ds, pdata);
- else
+ if (err)
+ dsa_switch_release_ports(ds);
+ } else {
err = -ENODEV;
+ }
if (err)
return err;
@@ -851,8 +896,10 @@ static int dsa_switch_probe(struct dsa_switch *ds)
dst = ds->dst;
dsa_tree_get(dst);
err = dsa_tree_setup(dst);
- if (err)
+ if (err) {
+ dsa_switch_release_ports(ds);
dsa_tree_put(dst);
+ }
return err;
}
@@ -873,15 +920,9 @@ EXPORT_SYMBOL_GPL(dsa_register_switch);
static void dsa_switch_remove(struct dsa_switch *ds)
{
struct dsa_switch_tree *dst = ds->dst;
- struct dsa_port *dp, *next;
dsa_tree_teardown(dst);
-
- list_for_each_entry_safe(dp, next, &dst->ports, list) {
- list_del(&dp->list);
- kfree(dp);
- }
-
+ dsa_switch_release_ports(ds);
dsa_tree_put(dst);
}
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 09ea2fd..a7662e7 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -157,13 +157,12 @@ extern const struct dsa_device_ops notag_netdev_ops;
void dsa_slave_mii_bus_init(struct dsa_switch *ds);
int dsa_slave_create(struct dsa_port *dp);
void dsa_slave_destroy(struct net_device *slave_dev);
+bool dsa_slave_dev_check(const struct net_device *dev);
int dsa_slave_suspend(struct net_device *slave_dev);
int dsa_slave_resume(struct net_device *slave_dev);
int dsa_slave_register_notifier(void);
void dsa_slave_unregister_notifier(void);
-void *dsa_defer_xmit(struct sk_buff *skb, struct net_device *dev);
-
static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
diff --git a/net/dsa/port.c b/net/dsa/port.c
index ffb5601..774facb 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -599,6 +599,7 @@ static int dsa_port_phylink_register(struct dsa_port *dp)
dp->pl_config.dev = ds->dev;
dp->pl_config.type = PHYLINK_DEV;
+ dp->pl_config.pcs_poll = ds->pcs_poll;
dp->pl = phylink_create(&dp->pl_config, of_fwnode_handle(port_dn),
mode, &dsa_port_phylink_mac_ops);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 78ffc87..088c886 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -22,8 +22,6 @@
#include "dsa_priv.h"
-static bool dsa_slave_dev_check(const struct net_device *dev);
-
/* slave mii_bus handling ***************************************************/
static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg)
{
@@ -116,9 +114,6 @@ static int dsa_slave_close(struct net_device *dev)
struct net_device *master = dsa_slave_to_master(dev);
struct dsa_port *dp = dsa_slave_to_port(dev);
- cancel_work_sync(&dp->xmit_work);
- skb_queue_purge(&dp->xmit_queue);
-
phylink_stop(dp->pl);
dsa_port_disable(dp);
@@ -518,7 +513,6 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
s->tx_bytes += skb->len;
u64_stats_update_end(&s->syncp);
- DSA_SKB_CB(skb)->deferred_xmit = false;
DSA_SKB_CB(skb)->clone = NULL;
/* Identify PTP protocol packets, clone them, and pass them to the
@@ -531,39 +525,13 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
*/
nskb = p->xmit(skb, dev);
if (!nskb) {
- if (!DSA_SKB_CB(skb)->deferred_xmit)
- kfree_skb(skb);
+ kfree_skb(skb);
return NETDEV_TX_OK;
}
return dsa_enqueue_skb(nskb, dev);
}
-void *dsa_defer_xmit(struct sk_buff *skb, struct net_device *dev)
-{
- struct dsa_port *dp = dsa_slave_to_port(dev);
-
- DSA_SKB_CB(skb)->deferred_xmit = true;
-
- skb_queue_tail(&dp->xmit_queue, skb);
- schedule_work(&dp->xmit_work);
- return NULL;
-}
-EXPORT_SYMBOL_GPL(dsa_defer_xmit);
-
-static void dsa_port_xmit_work(struct work_struct *work)
-{
- struct dsa_port *dp = container_of(work, struct dsa_port, xmit_work);
- struct dsa_switch *ds = dp->ds;
- struct sk_buff *skb;
-
- if (unlikely(!ds->ops->port_deferred_xmit))
- return;
-
- while ((skb = skb_dequeue(&dp->xmit_queue)) != NULL)
- ds->ops->port_deferred_xmit(ds, dp->index, skb);
-}
-
/* ethtool operations *******************************************************/
static void dsa_slave_get_drvinfo(struct net_device *dev,
@@ -1367,9 +1335,6 @@ int dsa_slave_suspend(struct net_device *slave_dev)
if (!netif_running(slave_dev))
return 0;
- cancel_work_sync(&dp->xmit_work);
- skb_queue_purge(&dp->xmit_queue);
-
netif_device_detach(slave_dev);
rtnl_lock();
@@ -1455,8 +1420,6 @@ int dsa_slave_create(struct dsa_port *port)
}
p->dp = port;
INIT_LIST_HEAD(&p->mall_tc_list);
- INIT_WORK(&port->xmit_work, dsa_port_xmit_work);
- skb_queue_head_init(&port->xmit_queue);
p->xmit = cpu_dp->tag_ops->xmit;
port->slave = slave_dev;
@@ -1508,7 +1471,7 @@ void dsa_slave_destroy(struct net_device *slave_dev)
free_netdev(slave_dev);
}
-static bool dsa_slave_dev_check(const struct net_device *dev)
+bool dsa_slave_dev_check(const struct net_device *dev)
{
return dev->netdev_ops == &dsa_slave_netdev_ops;
}
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index b678160..408d4af 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -104,7 +104,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb,
}
static const struct dsa_device_ops gswip_netdev_ops = {
- .name = "gwsip",
+ .name = "gswip",
.proto = DSA_TAG_PROTO_GSWIP,
.xmit = gswip_tag_xmit,
.rcv = gswip_tag_rcv,
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index c958852..c8a128c 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -33,9 +33,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
struct dsa_port *dp = dsa_slave_to_port(dev);
u16 *phdr, hdr;
- dev->stats.tx_packets++;
- dev->stats.tx_bytes += skb->len;
-
if (skb_cow_head(skb, 0) < 0)
return NULL;
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 63ef2a1..5366ea4 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -83,12 +83,24 @@ static bool sja1105_filter(const struct sk_buff *skb, struct net_device *dev)
return false;
}
+/* Calls sja1105_port_deferred_xmit in sja1105_main.c */
+static struct sk_buff *sja1105_defer_xmit(struct sja1105_port *sp,
+ struct sk_buff *skb)
+{
+ /* Increase refcount so the kfree_skb in dsa_slave_xmit
+ * won't really free the packet.
+ */
+ skb_queue_tail(&sp->xmit_queue, skb_get(skb));
+ kthread_queue_work(sp->xmit_worker, &sp->xmit_work);
+
+ return NULL;
+}
+
static struct sk_buff *sja1105_xmit(struct sk_buff *skb,
struct net_device *netdev)
{
struct dsa_port *dp = dsa_slave_to_port(netdev);
- struct dsa_switch *ds = dp->ds;
- u16 tx_vid = dsa_8021q_tx_vid(ds, dp->index);
+ u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index);
u16 queue_mapping = skb_get_queue_mapping(skb);
u8 pcp = netdev_txq_to_tc(netdev, queue_mapping);
@@ -97,7 +109,7 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb,
* is the .port_deferred_xmit driver callback.
*/
if (unlikely(sja1105_is_link_local(skb)))
- return dsa_defer_xmit(skb, netdev);
+ return sja1105_defer_xmit(dp->priv, skb);
/* If we are under a vlan_filtering bridge, IP termination on
* switch ports based on 802.1Q tags is simply too brittle to
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 9040fe5..c8b9033 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -335,22 +335,6 @@ int eth_mac_addr(struct net_device *dev, void *p)
}
EXPORT_SYMBOL(eth_mac_addr);
-/**
- * eth_change_mtu - set new MTU size
- * @dev: network device
- * @new_mtu: new Maximum Transfer Unit
- *
- * Allow changing MTU size. Needs to be overridden for devices
- * supporting jumbo frames.
- */
-int eth_change_mtu(struct net_device *dev, int new_mtu)
-{
- netdev_warn(dev, "%s is deprecated\n", __func__);
- dev->mtu = new_mtu;
- return 0;
-}
-EXPORT_SYMBOL(eth_change_mtu);
-
int eth_validate_addr(struct net_device *dev)
{
if (!is_valid_ether_addr(dev->dev_addr))
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index e621b16..c7b8956 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -59,6 +59,7 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
[NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record",
[NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload",
[NETIF_F_HW_TLS_RX_BIT] = "tls-hw-rx-offload",
+ [NETIF_F_GRO_FRAGLIST_BIT] = "rx-gro-list",
};
const char
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 4ca96c7..86b79f9 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -319,9 +319,10 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
rtnl_unlock();
if (ret < 0)
goto err_cleanup;
- reply_len = ops->reply_size(req_info, reply_data);
+ ret = ops->reply_size(req_info, reply_data);
if (ret < 0)
goto err_cleanup;
+ reply_len = ret;
ret = -ENOMEM;
rskb = ethnl_reply_init(reply_len, req_info->dev, ops->reply_cmd,
ops->hdr_attr, info, &reply_payload);
@@ -472,8 +473,8 @@ static int ethnl_default_start(struct netlink_callback *cb)
return -ENOMEM;
reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL);
if (!reply_data) {
- kfree(req_info);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto free_req_info;
}
ret = ethnl_default_parse(req_info, cb->nlh, sock_net(cb->skb->sk), ops,
@@ -487,7 +488,7 @@ static int ethnl_default_start(struct netlink_callback *cb)
req_info->dev = NULL;
}
if (ret < 0)
- return ret;
+ goto free_reply_data;
ctx->ops = ops;
ctx->req_info = req_info;
@@ -496,6 +497,13 @@ static int ethnl_default_start(struct netlink_callback *cb)
ctx->pos_idx = 0;
return 0;
+
+free_reply_data:
+ kfree(reply_data);
+free_req_info:
+ kfree(req_info);
+
+ return ret;
}
/* default ->done() handler for GET requests */
@@ -548,9 +556,10 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd,
ret = ops->prepare_data(req_info, reply_data, NULL);
if (ret < 0)
goto err_cleanup;
- reply_len = ops->reply_size(req_info, reply_data);
+ ret = ops->reply_size(req_info, reply_data);
if (ret < 0)
goto err_cleanup;
+ reply_len = ret;
ret = -ENOMEM;
skb = genlmsg_new(reply_len, GFP_KERNEL);
if (!skb)
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 9f22433..82a059c 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -239,6 +239,7 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base,
return -EINVAL;
}
}
+ return 0;
}
ret = ethnl_ops_begin(dev);
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 27dc65d..364ea2c 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -35,7 +35,6 @@ static bool seq_nr_after(u16 a, u16 b)
}
#define seq_nr_before(a, b) seq_nr_after((b), (a))
-#define seq_nr_after_or_eq(a, b) (!seq_nr_before((a), (b)))
#define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b)))
bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr)
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index d40de84..754d84b 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -191,7 +191,7 @@ void hsr_debugfs_term(struct hsr_priv *priv);
void hsr_debugfs_create_root(void);
void hsr_debugfs_remove_root(void);
#else
-static inline void void hsr_debugfs_rename(struct net_device *dev)
+static inline void hsr_debugfs_rename(struct net_device *dev)
{
}
static inline void hsr_debugfs_init(struct hsr_priv *priv,
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index fc816b1..f96bd48 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -378,6 +378,17 @@
If unsure, say N.
+config INET_ESPINTCP
+ bool "IP: ESP in TCP encapsulation (RFC 8229)"
+ depends on XFRM && INET_ESP
+ select STREAM_PARSER
+ select NET_SOCK_MSG
+ help
+ Support for RFC 8229 encapsulation of ESP and IKE over
+ TCP/IPv4 sockets.
+
+ If unsure, say N.
+
config INET_IPCOMP
tristate "IP: IPComp transformation"
select INET_XFRM_TUNNEL
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index d57ecfa..9d97bac 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -65,3 +65,7 @@
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
xfrm4_output.o xfrm4_protocol.o
+
+ifeq ($(CONFIG_BPF_JIT),y)
+obj-$(CONFIG_BPF_SYSCALL) += bpf_tcp_ca.o
+endif
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
new file mode 100644
index 0000000..574972b
--- /dev/null
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -0,0 +1,252 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <linux/types.h>
+#include <linux/bpf_verifier.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/filter.h>
+#include <net/tcp.h>
+
+static u32 optional_ops[] = {
+ offsetof(struct tcp_congestion_ops, init),
+ offsetof(struct tcp_congestion_ops, release),
+ offsetof(struct tcp_congestion_ops, set_state),
+ offsetof(struct tcp_congestion_ops, cwnd_event),
+ offsetof(struct tcp_congestion_ops, in_ack_event),
+ offsetof(struct tcp_congestion_ops, pkts_acked),
+ offsetof(struct tcp_congestion_ops, min_tso_segs),
+ offsetof(struct tcp_congestion_ops, sndbuf_expand),
+ offsetof(struct tcp_congestion_ops, cong_control),
+};
+
+static u32 unsupported_ops[] = {
+ offsetof(struct tcp_congestion_ops, get_info),
+};
+
+static const struct btf_type *tcp_sock_type;
+static u32 tcp_sock_id, sock_id;
+
+static int bpf_tcp_ca_init(struct btf *btf)
+{
+ s32 type_id;
+
+ type_id = btf_find_by_name_kind(btf, "sock", BTF_KIND_STRUCT);
+ if (type_id < 0)
+ return -EINVAL;
+ sock_id = type_id;
+
+ type_id = btf_find_by_name_kind(btf, "tcp_sock", BTF_KIND_STRUCT);
+ if (type_id < 0)
+ return -EINVAL;
+ tcp_sock_id = type_id;
+ tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
+
+ return 0;
+}
+
+static bool is_optional(u32 member_offset)
+{
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(optional_ops); i++) {
+ if (member_offset == optional_ops[i])
+ return true;
+ }
+
+ return false;
+}
+
+static bool is_unsupported(u32 member_offset)
+{
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(unsupported_ops); i++) {
+ if (member_offset == unsupported_ops[i])
+ return true;
+ }
+
+ return false;
+}
+
+extern struct btf *btf_vmlinux;
+
+static bool bpf_tcp_ca_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ const struct bpf_prog *prog,
+ struct bpf_insn_access_aux *info)
+{
+ if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
+ return false;
+ if (type != BPF_READ)
+ return false;
+ if (off % size != 0)
+ return false;
+
+ if (!btf_ctx_access(off, size, type, prog, info))
+ return false;
+
+ if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id)
+ /* promote it to tcp_sock */
+ info->btf_id = tcp_sock_id;
+
+ return true;
+}
+
+static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
+ const struct btf_type *t, int off,
+ int size, enum bpf_access_type atype,
+ u32 *next_btf_id)
+{
+ size_t end;
+
+ if (atype == BPF_READ)
+ return btf_struct_access(log, t, off, size, atype, next_btf_id);
+
+ if (t != tcp_sock_type) {
+ bpf_log(log, "only read is supported\n");
+ return -EACCES;
+ }
+
+ switch (off) {
+ case bpf_ctx_range(struct inet_connection_sock, icsk_ca_priv):
+ end = offsetofend(struct inet_connection_sock, icsk_ca_priv);
+ break;
+ case offsetof(struct inet_connection_sock, icsk_ack.pending):
+ end = offsetofend(struct inet_connection_sock,
+ icsk_ack.pending);
+ break;
+ case offsetof(struct tcp_sock, snd_cwnd):
+ end = offsetofend(struct tcp_sock, snd_cwnd);
+ break;
+ case offsetof(struct tcp_sock, snd_cwnd_cnt):
+ end = offsetofend(struct tcp_sock, snd_cwnd_cnt);
+ break;
+ case offsetof(struct tcp_sock, snd_ssthresh):
+ end = offsetofend(struct tcp_sock, snd_ssthresh);
+ break;
+ case offsetof(struct tcp_sock, ecn_flags):
+ end = offsetofend(struct tcp_sock, ecn_flags);
+ break;
+ default:
+ bpf_log(log, "no write support to tcp_sock at off %d\n", off);
+ return -EACCES;
+ }
+
+ if (off + size > end) {
+ bpf_log(log,
+ "write access at off %d with size %d beyond the member of tcp_sock ended at %zu\n",
+ off, size, end);
+ return -EACCES;
+ }
+
+ return NOT_INIT;
+}
+
+BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt)
+{
+ /* bpf_tcp_ca prog cannot have NULL tp */
+ __tcp_send_ack((struct sock *)tp, rcv_nxt);
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_tcp_send_ack_proto = {
+ .func = bpf_tcp_send_ack,
+ .gpl_only = false,
+ /* In case we want to report error later */
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_BTF_ID,
+ .arg2_type = ARG_ANYTHING,
+ .btf_id = &tcp_sock_id,
+};
+
+static const struct bpf_func_proto *
+bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
+ const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ case BPF_FUNC_tcp_send_ack:
+ return &bpf_tcp_send_ack_proto;
+ default:
+ return bpf_base_func_proto(func_id);
+ }
+}
+
+static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = {
+ .get_func_proto = bpf_tcp_ca_get_func_proto,
+ .is_valid_access = bpf_tcp_ca_is_valid_access,
+ .btf_struct_access = bpf_tcp_ca_btf_struct_access,
+};
+
+static int bpf_tcp_ca_init_member(const struct btf_type *t,
+ const struct btf_member *member,
+ void *kdata, const void *udata)
+{
+ const struct tcp_congestion_ops *utcp_ca;
+ struct tcp_congestion_ops *tcp_ca;
+ size_t tcp_ca_name_len;
+ int prog_fd;
+ u32 moff;
+
+ utcp_ca = (const struct tcp_congestion_ops *)udata;
+ tcp_ca = (struct tcp_congestion_ops *)kdata;
+
+ moff = btf_member_bit_offset(t, member) / 8;
+ switch (moff) {
+ case offsetof(struct tcp_congestion_ops, flags):
+ if (utcp_ca->flags & ~TCP_CONG_MASK)
+ return -EINVAL;
+ tcp_ca->flags = utcp_ca->flags;
+ return 1;
+ case offsetof(struct tcp_congestion_ops, name):
+ tcp_ca_name_len = strnlen(utcp_ca->name, sizeof(utcp_ca->name));
+ if (!tcp_ca_name_len ||
+ tcp_ca_name_len == sizeof(utcp_ca->name))
+ return -EINVAL;
+ if (tcp_ca_find(utcp_ca->name))
+ return -EEXIST;
+ memcpy(tcp_ca->name, utcp_ca->name, sizeof(tcp_ca->name));
+ return 1;
+ }
+
+ if (!btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL))
+ return 0;
+
+ /* Ensure bpf_prog is provided for compulsory func ptr */
+ prog_fd = (int)(*(unsigned long *)(udata + moff));
+ if (!prog_fd && !is_optional(moff) && !is_unsupported(moff))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int bpf_tcp_ca_check_member(const struct btf_type *t,
+ const struct btf_member *member)
+{
+ if (is_unsupported(btf_member_bit_offset(t, member) / 8))
+ return -ENOTSUPP;
+ return 0;
+}
+
+static int bpf_tcp_ca_reg(void *kdata)
+{
+ return tcp_register_congestion_control(kdata);
+}
+
+static void bpf_tcp_ca_unreg(void *kdata)
+{
+ tcp_unregister_congestion_control(kdata);
+}
+
+/* Avoid sparse warning. It is only used in bpf_struct_ops.c. */
+extern struct bpf_struct_ops bpf_tcp_congestion_ops;
+
+struct bpf_struct_ops bpf_tcp_congestion_ops = {
+ .verifier_ops = &bpf_tcp_ca_verifier_ops,
+ .reg = bpf_tcp_ca_reg,
+ .unreg = bpf_tcp_ca_unreg,
+ .check_member = bpf_tcp_ca_check_member,
+ .init_member = bpf_tcp_ca_init_member,
+ .init = bpf_tcp_ca_init,
+ .name = "tcp_congestion_ops",
+};
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 5c96776..103c7d5 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -18,6 +18,8 @@
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/udp.h>
+#include <net/tcp.h>
+#include <net/espintcp.h>
#include <linux/highmem.h>
@@ -117,6 +119,132 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
put_page(sg_page(sg));
}
+#ifdef CONFIG_INET_ESPINTCP
+struct esp_tcp_sk {
+ struct sock *sk;
+ struct rcu_head rcu;
+};
+
+static void esp_free_tcp_sk(struct rcu_head *head)
+{
+ struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
+
+ sock_put(esk->sk);
+ kfree(esk);
+}
+
+static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
+{
+ struct xfrm_encap_tmpl *encap = x->encap;
+ struct esp_tcp_sk *esk;
+ __be16 sport, dport;
+ struct sock *nsk;
+ struct sock *sk;
+
+ sk = rcu_dereference(x->encap_sk);
+ if (sk && sk->sk_state == TCP_ESTABLISHED)
+ return sk;
+
+ spin_lock_bh(&x->lock);
+ sport = encap->encap_sport;
+ dport = encap->encap_dport;
+ nsk = rcu_dereference_protected(x->encap_sk,
+ lockdep_is_held(&x->lock));
+ if (sk && sk == nsk) {
+ esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
+ if (!esk) {
+ spin_unlock_bh(&x->lock);
+ return ERR_PTR(-ENOMEM);
+ }
+ RCU_INIT_POINTER(x->encap_sk, NULL);
+ esk->sk = sk;
+ call_rcu(&esk->rcu, esp_free_tcp_sk);
+ }
+ spin_unlock_bh(&x->lock);
+
+ sk = inet_lookup_established(xs_net(x), &tcp_hashinfo, x->id.daddr.a4,
+ dport, x->props.saddr.a4, sport, 0);
+ if (!sk)
+ return ERR_PTR(-ENOENT);
+
+ if (!tcp_is_ulp_esp(sk)) {
+ sock_put(sk);
+ return ERR_PTR(-EINVAL);
+ }
+
+ spin_lock_bh(&x->lock);
+ nsk = rcu_dereference_protected(x->encap_sk,
+ lockdep_is_held(&x->lock));
+ if (encap->encap_sport != sport ||
+ encap->encap_dport != dport) {
+ sock_put(sk);
+ sk = nsk ?: ERR_PTR(-EREMCHG);
+ } else if (sk == nsk) {
+ sock_put(sk);
+ } else {
+ rcu_assign_pointer(x->encap_sk, sk);
+ }
+ spin_unlock_bh(&x->lock);
+
+ return sk;
+}
+
+static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct sock *sk;
+ int err;
+
+ rcu_read_lock();
+
+ sk = esp_find_tcp_sk(x);
+ err = PTR_ERR_OR_ZERO(sk);
+ if (err)
+ goto out;
+
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk))
+ err = espintcp_queue_out(sk, skb);
+ else
+ err = espintcp_push_skb(sk, skb);
+ bh_unlock_sock(sk);
+
+out:
+ rcu_read_unlock();
+ return err;
+}
+
+static int esp_output_tcp_encap_cb(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ struct xfrm_state *x = dst->xfrm;
+
+ return esp_output_tcp_finish(x, skb);
+}
+
+static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
+{
+ int err;
+
+ local_bh_disable();
+ err = xfrm_trans_queue_net(xs_net(x), skb, esp_output_tcp_encap_cb);
+ local_bh_enable();
+
+ /* EINPROGRESS just happens to do the right thing. It
+ * actually means that the skb has been consumed and
+ * isn't coming back.
+ */
+ return err ?: -EINPROGRESS;
+}
+#else
+static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
+{
+ kfree_skb(skb);
+
+ return -EOPNOTSUPP;
+}
+#endif
+
static void esp_output_done(struct crypto_async_request *base, int err)
{
struct sk_buff *skb = base->data;
@@ -147,7 +275,11 @@ static void esp_output_done(struct crypto_async_request *base, int err)
secpath_reset(skb);
xfrm_dev_resume(skb);
} else {
- xfrm_output_resume(skb, err);
+ if (!err &&
+ x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
+ esp_output_tail_tcp(x, skb);
+ else
+ xfrm_output_resume(skb, err);
}
}
@@ -225,45 +357,100 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
tail[plen - 1] = proto;
}
-static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
+static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb,
+ int encap_type,
+ struct esp_info *esp,
+ __be16 sport,
+ __be16 dport)
{
- int encap_type;
struct udphdr *uh;
__be32 *udpdata32;
- __be16 sport, dport;
- struct xfrm_encap_tmpl *encap = x->encap;
- struct ip_esp_hdr *esph = esp->esph;
unsigned int len;
+ len = skb->len + esp->tailen - skb_transport_offset(skb);
+ if (len + sizeof(struct iphdr) > IP_MAX_MTU)
+ return ERR_PTR(-EMSGSIZE);
+
+ uh = (struct udphdr *)esp->esph;
+ uh->source = sport;
+ uh->dest = dport;
+ uh->len = htons(len);
+ uh->check = 0;
+
+ *skb_mac_header(skb) = IPPROTO_UDP;
+
+ if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) {
+ udpdata32 = (__be32 *)(uh + 1);
+ udpdata32[0] = udpdata32[1] = 0;
+ return (struct ip_esp_hdr *)(udpdata32 + 2);
+ }
+
+ return (struct ip_esp_hdr *)(uh + 1);
+}
+
+#ifdef CONFIG_INET_ESPINTCP
+static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
+ struct sk_buff *skb,
+ struct esp_info *esp)
+{
+ __be16 *lenp = (void *)esp->esph;
+ struct ip_esp_hdr *esph;
+ unsigned int len;
+ struct sock *sk;
+
+ len = skb->len + esp->tailen - skb_transport_offset(skb);
+ if (len > IP_MAX_MTU)
+ return ERR_PTR(-EMSGSIZE);
+
+ rcu_read_lock();
+ sk = esp_find_tcp_sk(x);
+ rcu_read_unlock();
+
+ if (IS_ERR(sk))
+ return ERR_CAST(sk);
+
+ *lenp = htons(len);
+ esph = (struct ip_esp_hdr *)(lenp + 1);
+
+ return esph;
+}
+#else
+static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
+ struct sk_buff *skb,
+ struct esp_info *esp)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+#endif
+
+static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb,
+ struct esp_info *esp)
+{
+ struct xfrm_encap_tmpl *encap = x->encap;
+ struct ip_esp_hdr *esph;
+ __be16 sport, dport;
+ int encap_type;
+
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
dport = encap->encap_dport;
encap_type = encap->encap_type;
spin_unlock_bh(&x->lock);
- len = skb->len + esp->tailen - skb_transport_offset(skb);
- if (len + sizeof(struct iphdr) >= IP_MAX_MTU)
- return -EMSGSIZE;
-
- uh = (struct udphdr *)esph;
- uh->source = sport;
- uh->dest = dport;
- uh->len = htons(len);
- uh->check = 0;
-
switch (encap_type) {
default:
case UDP_ENCAP_ESPINUDP:
- esph = (struct ip_esp_hdr *)(uh + 1);
- break;
case UDP_ENCAP_ESPINUDP_NON_IKE:
- udpdata32 = (__be32 *)(uh + 1);
- udpdata32[0] = udpdata32[1] = 0;
- esph = (struct ip_esp_hdr *)(udpdata32 + 2);
+ esph = esp_output_udp_encap(skb, encap_type, esp, sport, dport);
+ break;
+ case TCP_ENCAP_ESPINTCP:
+ esph = esp_output_tcp_encap(x, skb, esp);
break;
}
- *skb_mac_header(skb) = IPPROTO_UDP;
+ if (IS_ERR(esph))
+ return PTR_ERR(esph);
+
esp->esph = esph;
return 0;
@@ -279,9 +466,9 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
struct sk_buff *trailer;
int tailen = esp->tailen;
- /* this is non-NULL only with UDP Encapsulation */
+ /* this is non-NULL only with TCP/UDP Encapsulation */
if (x->encap) {
- int err = esp_output_udp_encap(x, skb, esp);
+ int err = esp_output_encap(x, skb, esp);
if (err < 0)
return err;
@@ -474,6 +661,9 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
if (sg != dsg)
esp_ssg_unref(x, tmp);
+ if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
+ err = esp_output_tail_tcp(x, skb);
+
error_free:
kfree(tmp);
error:
@@ -600,7 +790,23 @@ int esp_input_done2(struct sk_buff *skb, int err)
if (x->encap) {
struct xfrm_encap_tmpl *encap = x->encap;
+ struct tcphdr *th = (void *)(skb_network_header(skb) + ihl);
struct udphdr *uh = (void *)(skb_network_header(skb) + ihl);
+ __be16 source;
+
+ switch (x->encap->encap_type) {
+ case TCP_ENCAP_ESPINTCP:
+ source = th->source;
+ break;
+ case UDP_ENCAP_ESPINUDP:
+ case UDP_ENCAP_ESPINUDP_NON_IKE:
+ source = uh->source;
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ err = -EINVAL;
+ goto out;
+ }
/*
* 1) if the NAT-T peer's IP or port changed then
@@ -609,11 +815,11 @@ int esp_input_done2(struct sk_buff *skb, int err)
* SRC ports.
*/
if (iph->saddr != x->props.saddr.a4 ||
- uh->source != encap->encap_sport) {
+ source != encap->encap_sport) {
xfrm_address_t ipaddr;
ipaddr.a4 = iph->saddr;
- km_new_mapping(x, &ipaddr, uh->source);
+ km_new_mapping(x, &ipaddr, source);
/* XXX: perhaps add an extra
* policy check here, to see
@@ -988,6 +1194,14 @@ static int esp_init_state(struct xfrm_state *x)
case UDP_ENCAP_ESPINUDP_NON_IKE:
x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32);
break;
+#ifdef CONFIG_INET_ESPINTCP
+ case TCP_ENCAP_ESPINTCP:
+ /* only the length field, TCP encap is done by
+ * the socket
+ */
+ x->props.header_len += 2;
+ break;
+#endif
}
}
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 0e4a7cf..e2e219c 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -57,6 +57,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
if (!x)
goto out_reset;
+ skb->mark = xfrm_smark_get(skb->mark, x);
+
sp->xvec[sp->len++] = x;
sp->olen++;
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index a68b5e2..c092e9a 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -16,6 +16,9 @@ struct fib_alias {
u8 fa_slen;
u32 tb_id;
s16 fa_default;
+ u8 offload:1,
+ trap:1,
+ unused:6;
struct rcu_head rcu;
};
@@ -35,9 +38,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
struct netlink_ext_ack *extack);
bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi);
-int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id,
- u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi,
- unsigned int);
+int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
+ struct fib_rt_info *fri, unsigned int flags);
void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len,
u32 tb_id, const struct nl_info *info, unsigned int nlm_flags);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f1888c6..a803cdd 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -504,6 +504,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
int dst_len, u32 tb_id, const struct nl_info *info,
unsigned int nlm_flags)
{
+ struct fib_rt_info fri;
struct sk_buff *skb;
u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
int err = -ENOBUFS;
@@ -512,9 +513,15 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
if (!skb)
goto errout;
- err = fib_dump_info(skb, info->portid, seq, event, tb_id,
- fa->fa_type, key, dst_len,
- fa->fa_tos, fa->fa_info, nlm_flags);
+ fri.fi = fa->fa_info;
+ fri.tb_id = tb_id;
+ fri.dst = key;
+ fri.dst_len = dst_len;
+ fri.tos = fa->fa_tos;
+ fri.type = fa->fa_type;
+ fri.offload = fa->offload;
+ fri.trap = fa->trap;
+ err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -1725,10 +1732,11 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi)
#endif
int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
- u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
- struct fib_info *fi, unsigned int flags)
+ struct fib_rt_info *fri, unsigned int flags)
{
- unsigned int nhs = fib_info_num_path(fi);
+ unsigned int nhs = fib_info_num_path(fri->fi);
+ struct fib_info *fi = fri->fi;
+ u32 tb_id = fri->tb_id;
struct nlmsghdr *nlh;
struct rtmsg *rtm;
@@ -1738,22 +1746,22 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
rtm = nlmsg_data(nlh);
rtm->rtm_family = AF_INET;
- rtm->rtm_dst_len = dst_len;
+ rtm->rtm_dst_len = fri->dst_len;
rtm->rtm_src_len = 0;
- rtm->rtm_tos = tos;
+ rtm->rtm_tos = fri->tos;
if (tb_id < 256)
rtm->rtm_table = tb_id;
else
rtm->rtm_table = RT_TABLE_COMPAT;
if (nla_put_u32(skb, RTA_TABLE, tb_id))
goto nla_put_failure;
- rtm->rtm_type = type;
+ rtm->rtm_type = fri->type;
rtm->rtm_flags = fi->fib_flags;
rtm->rtm_scope = fi->fib_scope;
rtm->rtm_protocol = fi->fib_protocol;
if (rtm->rtm_dst_len &&
- nla_put_in_addr(skb, RTA_DST, dst))
+ nla_put_in_addr(skb, RTA_DST, fri->dst))
goto nla_put_failure;
if (fi->fib_priority &&
nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
@@ -1795,6 +1803,11 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
goto nla_put_failure;
}
+ if (fri->offload)
+ rtm->rtm_flags |= RTM_F_OFFLOAD;
+ if (fri->trap)
+ rtm->rtm_flags |= RTM_F_TRAP;
+
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index b92a424..ff0c243 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1012,6 +1012,52 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen,
return NULL;
}
+static struct fib_alias *
+fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)
+{
+ u8 slen = KEYLENGTH - fri->dst_len;
+ struct key_vector *l, *tp;
+ struct fib_table *tb;
+ struct fib_alias *fa;
+ struct trie *t;
+
+ tb = fib_get_table(net, fri->tb_id);
+ if (!tb)
+ return NULL;
+
+ t = (struct trie *)tb->tb_data;
+ l = fib_find_node(t, &tp, be32_to_cpu(fri->dst));
+ if (!l)
+ return NULL;
+
+ hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+ if (fa->fa_slen == slen && fa->tb_id == fri->tb_id &&
+ fa->fa_tos == fri->tos && fa->fa_info == fri->fi &&
+ fa->fa_type == fri->type)
+ return fa;
+ }
+
+ return NULL;
+}
+
+void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
+{
+ struct fib_alias *fa_match;
+
+ rcu_read_lock();
+
+ fa_match = fib_find_matching_alias(net, fri);
+ if (!fa_match)
+ goto out;
+
+ fa_match->offload = fri->offload;
+ fa_match->trap = fri->trap;
+
+out:
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set);
+
static void trie_rebalance(struct trie *t, struct key_vector *tn)
{
while (!IS_TRIE(tn))
@@ -1220,24 +1266,29 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
new_fa->fa_slen = fa->fa_slen;
new_fa->tb_id = tb->tb_id;
new_fa->fa_default = -1;
+ new_fa->offload = 0;
+ new_fa->trap = 0;
+
+ hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list);
if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0,
- tb->tb_id, true) == fa) {
+ tb->tb_id, true) == new_fa) {
enum fib_event_type fib_event;
fib_event = FIB_EVENT_ENTRY_REPLACE;
err = call_fib_entry_notifiers(net, fib_event,
key, plen,
new_fa, extack);
- if (err)
+ if (err) {
+ hlist_replace_rcu(&new_fa->fa_list,
+ &fa->fa_list);
goto out_free_new_fa;
+ }
}
rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
tb->tb_id, &cfg->fc_nlinfo, nlflags);
- hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list);
-
alias_free_mem_rcu(fa);
fib_release_info(fi_drop);
@@ -1275,6 +1326,8 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
new_fa->fa_slen = slen;
new_fa->tb_id = tb->tb_id;
new_fa->fa_default = -1;
+ new_fa->offload = 0;
+ new_fa->trap = 0;
/* Insert new entry to the list. */
err = fib_insert_alias(t, tp, l, new_fa, fa, key);
@@ -2191,14 +2244,20 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
if (filter->dump_routes) {
if (!s_fa) {
+ struct fib_rt_info fri;
+
+ fri.fi = fi;
+ fri.tb_id = tb->tb_id;
+ fri.dst = xkey;
+ fri.dst_len = KEYLENGTH - fa->fa_slen;
+ fri.tos = fa->fa_tos;
+ fri.type = fa->fa_type;
+ fri.offload = fa->offload;
+ fri.trap = fa->trap;
err = fib_dump_info(skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- RTM_NEWROUTE,
- tb->tb_id, fa->fa_type,
- xkey,
- KEYLENGTH - fa->fa_slen,
- fa->fa_tos, fi, flags);
+ RTM_NEWROUTE, &fri, flags);
if (err < 0)
goto stop;
}
@@ -2238,6 +2297,12 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
int count = cb->args[2];
t_key key = cb->args[3];
+ /* First time here, count and key are both always 0. Count > 0
+ * and key == 0 means the dump has wrapped around and we are done.
+ */
+ if (count && !key)
+ return skb->len;
+
while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
int err;
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 30fa771d..dcc79ff 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -662,8 +662,8 @@ static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
[FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, },
[FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, },
[FOU_ATTR_PEER_V4] = { .type = NLA_U32, },
- [FOU_ATTR_LOCAL_V6] = { .type = sizeof(struct in6_addr), },
- [FOU_ATTR_PEER_V6] = { .type = sizeof(struct in6_addr), },
+ [FOU_ATTR_LOCAL_V6] = { .len = sizeof(struct in6_addr), },
+ [FOU_ATTR_PEER_V6] = { .len = sizeof(struct in6_addr), },
[FOU_ATTR_PEER_PORT] = { .type = NLA_U16, },
[FOU_ATTR_IFINDEX] = { .type = NLA_S32, },
};
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 18c0d5b..a4db79b 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -610,12 +610,6 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
}
EXPORT_SYMBOL_GPL(inet_csk_route_child_sock);
-#if IS_ENABLED(CONFIG_IPV6)
-#define AF_INET_FAMILY(fam) ((fam) == AF_INET)
-#else
-#define AF_INET_FAMILY(fam) true
-#endif
-
/* Decide when to expire the request and when to resend SYN-ACK */
static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
const int max_retries,
@@ -770,6 +764,18 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
}
EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
+static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk,
+ const gfp_t priority)
+{
+ struct inet_connection_sock *icsk = inet_csk(newsk);
+
+ if (!icsk->icsk_ulp_ops)
+ return;
+
+ if (icsk->icsk_ulp_ops->clone)
+ icsk->icsk_ulp_ops->clone(req, newsk, priority);
+}
+
/**
* inet_csk_clone_lock - clone an inet socket, and lock its clone
* @sk: the socket to clone
@@ -810,6 +816,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
/* Deinitialize accept_queue to trap illegal accesses. */
memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
+ inet_clone_ulp(req, newsk, priority);
+
security_inet_csk_clone(newsk, req);
}
return newsk;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 14db1e0..d848198 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -240,8 +240,8 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
static int ip_finish_output_gso(struct net *net, struct sock *sk,
struct sk_buff *skb, unsigned int mtu)
{
+ struct sk_buff *segs, *nskb;
netdev_features_t features;
- struct sk_buff *segs;
int ret = 0;
/* common case: seglen is <= mtu
@@ -272,8 +272,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
consume_skb(skb);
- do {
- struct sk_buff *nskb = segs->next;
+ skb_list_walk_safe(segs, segs, nskb) {
int err;
skb_mark_not_on_list(segs);
@@ -281,8 +280,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
if (err && ret == 0)
ret = err;
- segs = nskb;
- } while (segs);
+ }
return ret;
}
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0fe2a5d..74e1d96 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1236,10 +1236,8 @@ int ip_tunnel_init(struct net_device *dev)
iph->version = 4;
iph->ihl = 5;
- if (tunnel->collect_md) {
- dev->features |= NETIF_F_NETNS_LOCAL;
+ if (tunnel->collect_md)
netif_keep_dst(dev);
- }
return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_init);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index e90b600..37cddd1 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -187,8 +187,17 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
int mtu;
if (!dst) {
- dev->stats.tx_carrier_errors++;
- goto tx_error_icmp;
+ struct rtable *rt;
+
+ fl->u.ip4.flowi4_oif = dev->ifindex;
+ fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+ rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4);
+ if (IS_ERR(rt)) {
+ dev->stats.tx_carrier_errors++;
+ goto tx_error_icmp;
+ }
+ dst = &rt->dst;
+ skb_dst_set(skb, dst);
}
dst_hold(dst);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 214154b..f1f78a7 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -384,10 +384,11 @@ next: ;
return 1;
}
-static inline int check_target(struct arpt_entry *e, const char *name)
+static int check_target(struct arpt_entry *e, struct net *net, const char *name)
{
struct xt_entry_target *t = arpt_get_target(e);
struct xt_tgchk_param par = {
+ .net = net,
.table = name,
.entryinfo = e,
.target = t->u.kernel.target,
@@ -399,8 +400,9 @@ static inline int check_target(struct arpt_entry *e, const char *name)
return xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false);
}
-static inline int
-find_check_entry(struct arpt_entry *e, const char *name, unsigned int size,
+static int
+find_check_entry(struct arpt_entry *e, struct net *net, const char *name,
+ unsigned int size,
struct xt_percpu_counter_alloc_state *alloc_state)
{
struct xt_entry_target *t;
@@ -419,7 +421,7 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size,
}
t->u.kernel.target = target;
- ret = check_target(e, name);
+ ret = check_target(e, net, name);
if (ret)
goto err;
return 0;
@@ -494,12 +496,13 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
return 0;
}
-static inline void cleanup_entry(struct arpt_entry *e)
+static void cleanup_entry(struct arpt_entry *e, struct net *net)
{
struct xt_tgdtor_param par;
struct xt_entry_target *t;
t = arpt_get_target(e);
+ par.net = net;
par.target = t->u.kernel.target;
par.targinfo = t->data;
par.family = NFPROTO_ARP;
@@ -512,7 +515,9 @@ static inline void cleanup_entry(struct arpt_entry *e)
/* Checks and translates the user-supplied table segment (held in
* newinfo).
*/
-static int translate_table(struct xt_table_info *newinfo, void *entry0,
+static int translate_table(struct net *net,
+ struct xt_table_info *newinfo,
+ void *entry0,
const struct arpt_replace *repl)
{
struct xt_percpu_counter_alloc_state alloc_state = { 0 };
@@ -569,7 +574,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
/* Finally, each sanity check must pass */
i = 0;
xt_entry_foreach(iter, entry0, newinfo->size) {
- ret = find_check_entry(iter, repl->name, repl->size,
+ ret = find_check_entry(iter, net, repl->name, repl->size,
&alloc_state);
if (ret != 0)
break;
@@ -580,7 +585,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
xt_entry_foreach(iter, entry0, newinfo->size) {
if (i-- == 0)
break;
- cleanup_entry(iter);
+ cleanup_entry(iter, net);
}
return ret;
}
@@ -923,7 +928,7 @@ static int __do_replace(struct net *net, const char *name,
/* Decrease module usage counts and free resource */
loc_cpu_old_entry = oldinfo->entries;
xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size)
- cleanup_entry(iter);
+ cleanup_entry(iter, net);
xt_free_table_info(oldinfo);
if (copy_to_user(counters_ptr, counters,
@@ -974,7 +979,7 @@ static int do_replace(struct net *net, const void __user *user,
goto free_newinfo;
}
- ret = translate_table(newinfo, loc_cpu_entry, &tmp);
+ ret = translate_table(net, newinfo, loc_cpu_entry, &tmp);
if (ret != 0)
goto free_newinfo;
@@ -986,7 +991,7 @@ static int do_replace(struct net *net, const void __user *user,
free_newinfo_untrans:
xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
- cleanup_entry(iter);
+ cleanup_entry(iter, net);
free_newinfo:
xt_free_table_info(newinfo);
return ret;
@@ -1149,7 +1154,8 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
}
}
-static int translate_compat_table(struct xt_table_info **pinfo,
+static int translate_compat_table(struct net *net,
+ struct xt_table_info **pinfo,
void **pentry0,
const struct compat_arpt_replace *compatr)
{
@@ -1217,7 +1223,7 @@ static int translate_compat_table(struct xt_table_info **pinfo,
repl.num_counters = 0;
repl.counters = NULL;
repl.size = newinfo->size;
- ret = translate_table(newinfo, entry1, &repl);
+ ret = translate_table(net, newinfo, entry1, &repl);
if (ret)
goto free_newinfo;
@@ -1270,7 +1276,7 @@ static int compat_do_replace(struct net *net, void __user *user,
goto free_newinfo;
}
- ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp);
+ ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp);
if (ret != 0)
goto free_newinfo;
@@ -1282,7 +1288,7 @@ static int compat_do_replace(struct net *net, void __user *user,
free_newinfo_untrans:
xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
- cleanup_entry(iter);
+ cleanup_entry(iter, net);
free_newinfo:
xt_free_table_info(newinfo);
return ret;
@@ -1509,7 +1515,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
return ret;
}
-static void __arpt_unregister_table(struct xt_table *table)
+static void __arpt_unregister_table(struct net *net, struct xt_table *table)
{
struct xt_table_info *private;
void *loc_cpu_entry;
@@ -1521,7 +1527,7 @@ static void __arpt_unregister_table(struct xt_table *table)
/* Decrease module usage counts and free resources */
loc_cpu_entry = private->entries;
xt_entry_foreach(iter, loc_cpu_entry, private->size)
- cleanup_entry(iter);
+ cleanup_entry(iter, net);
if (private->number > private->initial_entries)
module_put(table_owner);
xt_free_table_info(private);
@@ -1546,7 +1552,7 @@ int arpt_register_table(struct net *net,
loc_cpu_entry = newinfo->entries;
memcpy(loc_cpu_entry, repl->entries, repl->size);
- ret = translate_table(newinfo, loc_cpu_entry, repl);
+ ret = translate_table(net, newinfo, loc_cpu_entry, repl);
if (ret != 0)
goto out_free;
@@ -1561,7 +1567,7 @@ int arpt_register_table(struct net *net,
ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
if (ret != 0) {
- __arpt_unregister_table(new_table);
+ __arpt_unregister_table(net, new_table);
*res = NULL;
}
@@ -1576,7 +1582,7 @@ void arpt_unregister_table(struct net *net, struct xt_table *table,
const struct nf_hook_ops *ops)
{
nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
- __arpt_unregister_table(table);
+ __arpt_unregister_table(net, table);
}
/* The built-in targets: standard (NULL) and error. */
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 511eaa9..d072c32 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -321,7 +321,9 @@ static size_t nh_nlmsg_size_single(struct nexthop *nh)
static size_t nh_nlmsg_size(struct nexthop *nh)
{
- size_t sz = nla_total_size(4); /* NHA_ID */
+ size_t sz = NLMSG_ALIGN(sizeof(struct nhmsg));
+
+ sz += nla_total_size(4); /* NHA_ID */
if (nh->is_group)
sz += nh_nlmsg_size_grp(nh);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index cc90243..2580303 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -289,6 +289,8 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP),
SNMP_MIB_ITEM("TCPWqueueTooBig", LINUX_MIB_TCPWQUEUETOOBIG),
SNMP_MIB_ITEM("TCPFastOpenPassiveAltKey", LINUX_MIB_TCPFASTOPENPASSIVEALTKEY),
+ SNMP_MIB_ITEM("TcpTimeoutRehash", LINUX_MIB_TCPTIMEOUTREHASH),
+ SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 87e979f..d5c57b3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -271,6 +271,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
*pos = cpu+1;
return &per_cpu(rt_cache_stat, cpu);
}
+ (*pos)++;
return NULL;
}
@@ -3223,16 +3224,41 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
skb_reset_mac_header(skb);
if (rtm->rtm_flags & RTM_F_FIB_MATCH) {
+ struct fib_rt_info fri;
+
if (!res.fi) {
err = fib_props[res.type].error;
if (!err)
err = -EHOSTUNREACH;
goto errout_rcu;
}
+ fri.fi = res.fi;
+ fri.tb_id = table_id;
+ fri.dst = res.prefix;
+ fri.dst_len = res.prefixlen;
+ fri.tos = fl4.flowi4_tos;
+ fri.type = rt->rt_type;
+ fri.offload = 0;
+ fri.trap = 0;
+ if (res.fa_head) {
+ struct fib_alias *fa;
+
+ hlist_for_each_entry_rcu(fa, res.fa_head, fa_list) {
+ u8 slen = 32 - fri.dst_len;
+
+ if (fa->fa_slen == slen &&
+ fa->tb_id == fri.tb_id &&
+ fa->fa_tos == fri.tos &&
+ fa->fa_info == res.fi &&
+ fa->fa_type == fri.type) {
+ fri.offload = fa->offload;
+ fri.trap = fa->trap;
+ break;
+ }
+ }
+ }
err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
- rt->rt_type, res.prefix, res.prefixlen,
- fl4.flowi4_tos, res.fi, 0);
+ nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0);
} else {
err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb,
NETLINK_CB(in_skb).portid,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f09fbc8..484485a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -271,6 +271,7 @@
#include <net/icmp.h>
#include <net/inet_common.h>
#include <net/tcp.h>
+#include <net/mptcp.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/sock.h>
@@ -690,8 +691,8 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
}
-static void tcp_push(struct sock *sk, int flags, int mss_now,
- int nonagle, int size_goal)
+void tcp_push(struct sock *sk, int flags, int mss_now,
+ int nonagle, int size_goal)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
@@ -925,7 +926,7 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
return max(size_goal, mss_now);
}
-static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
+int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
{
int mss_now;
@@ -2524,6 +2525,7 @@ static void tcp_rtx_queue_purge(struct sock *sk)
{
struct rb_node *p = rb_first(&sk->tcp_rtx_queue);
+ tcp_sk(sk)->highest_sack = NULL;
while (p) {
struct sk_buff *skb = rb_to_skb(p);
@@ -2614,7 +2616,6 @@ int tcp_disconnect(struct sock *sk, int flags)
WRITE_ONCE(tp->write_seq, seq);
icsk->icsk_backoff = 0;
- tp->snd_cwnd = 2;
icsk->icsk_probes_out = 0;
icsk->icsk_rto = TCP_TIMEOUT_INIT;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
@@ -3336,6 +3337,7 @@ static size_t tcp_opt_stats_get_size(void)
nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */
nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */
nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */
+ nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */
0;
}
@@ -3390,6 +3392,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups);
nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen);
nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3);
+ nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash);
return stats;
}
@@ -4021,4 +4024,5 @@ void __init tcp_init(void)
tcp_metrics_init();
BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
tcp_tasklet_init();
+ mptcp_init();
}
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index a6545ef..6c4d79b 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -779,8 +779,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs)
* bandwidth sample. Delivered is in packets and interval_us in uS and
* ratio will be <<1 for most connections. So delivered is first scaled.
*/
- bw = (u64)rs->delivered * BW_UNIT;
- do_div(bw, rs->interval_us);
+ bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us);
/* If this sample is application-limited, it is likely to have a very
* low delivered count that represents application behavior rather than
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index e387051..8a01428 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -121,14 +121,14 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
struct sk_psock *psock;
int copied, ret;
- if (unlikely(flags & MSG_ERRQUEUE))
- return inet_recv_error(sk, msg, len, addr_len);
- if (!skb_queue_empty(&sk->sk_receive_queue))
- return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
-
psock = sk_psock_get(sk);
if (unlikely(!psock))
return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+ if (unlikely(flags & MSG_ERRQUEUE))
+ return inet_recv_error(sk, msg, len, addr_len);
+ if (!skb_queue_empty(&sk->sk_receive_queue) &&
+ sk_psock_queue_empty(psock))
+ return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
lock_sock(sk);
msg_bytes_ready:
copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -139,7 +139,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
timeo = sock_rcvtimeo(sk, nonblock);
data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
if (data) {
- if (skb_queue_empty(&sk->sk_receive_queue))
+ if (!sk_psock_queue_empty(psock))
goto msg_bytes_ready;
release_sock(sk);
sk_psock_put(sk, psock);
@@ -315,10 +315,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
*/
delta = msg->sg.size;
psock->eval = sk_psock_msg_verdict(sk, psock, msg);
- if (msg->sg.size < delta)
- delta -= msg->sg.size;
- else
- delta = 0;
+ delta -= msg->sg.size;
}
if (msg->cork_bytes &&
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 3737ec0..3172e31 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -21,7 +21,7 @@ static DEFINE_SPINLOCK(tcp_cong_list_lock);
static LIST_HEAD(tcp_cong_list);
/* Simple linear search, don't expect many entries! */
-static struct tcp_congestion_ops *tcp_ca_find(const char *name)
+struct tcp_congestion_ops *tcp_ca_find(const char *name)
{
struct tcp_congestion_ops *e;
@@ -162,7 +162,7 @@ void tcp_assign_congestion_control(struct sock *sk)
rcu_read_lock();
ca = rcu_dereference(net->ipv4.tcp_congestion_control);
- if (unlikely(!try_module_get(ca->owner)))
+ if (unlikely(!bpf_try_module_get(ca, ca->owner)))
ca = &tcp_reno;
icsk->icsk_ca_ops = ca;
rcu_read_unlock();
@@ -208,7 +208,7 @@ void tcp_cleanup_congestion_control(struct sock *sk)
if (icsk->icsk_ca_ops->release)
icsk->icsk_ca_ops->release(sk);
- module_put(icsk->icsk_ca_ops->owner);
+ bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner);
}
/* Used by sysctl to change default congestion control */
@@ -222,12 +222,12 @@ int tcp_set_default_congestion_control(struct net *net, const char *name)
ca = tcp_ca_find_autoload(net, name);
if (!ca) {
ret = -ENOENT;
- } else if (!try_module_get(ca->owner)) {
+ } else if (!bpf_try_module_get(ca, ca->owner)) {
ret = -EBUSY;
} else {
prev = xchg(&net->ipv4.tcp_congestion_control, ca);
if (prev)
- module_put(prev->owner);
+ bpf_module_put(prev, prev->owner);
ca->flags |= TCP_CONG_NON_RESTRICTED;
ret = 0;
@@ -366,19 +366,19 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
} else if (!load) {
const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops;
- if (try_module_get(ca->owner)) {
+ if (bpf_try_module_get(ca, ca->owner)) {
if (reinit) {
tcp_reinit_congestion_control(sk, ca);
} else {
icsk->icsk_ca_ops = ca;
- module_put(old_ca->owner);
+ bpf_module_put(old_ca, old_ca->owner);
}
} else {
err = -EBUSY;
}
} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
err = -EPERM;
- } else if (!try_module_get(ca->owner)) {
+ } else if (!bpf_try_module_get(ca, ca->owner)) {
err = -EBUSY;
} else {
tcp_reinit_congestion_control(sk, ca);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1d1e349..e8b840a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -79,6 +79,7 @@
#include <trace/events/tcp.h>
#include <linux/jump_label_ratelimit.h>
#include <net/busy_poll.h>
+#include <net/mptcp.h>
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
@@ -915,9 +916,10 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
/* This must be called before lost_out is incremented */
static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
{
- if (!tp->retransmit_skb_hint ||
- before(TCP_SKB_CB(skb)->seq,
- TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
+ if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) ||
+ (tp->retransmit_skb_hint &&
+ before(TCP_SKB_CB(skb)->seq,
+ TCP_SKB_CB(tp->retransmit_skb_hint)->seq)))
tp->retransmit_skb_hint = skb;
}
@@ -1422,7 +1424,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
goto fallback;
- if (!tcp_skb_can_collapse_to(prev))
+ if (!tcp_skb_can_collapse(prev, skb))
goto fallback;
in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
@@ -1727,8 +1729,11 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
}
/* Ignore very old stuff early */
- if (!after(sp[used_sacks].end_seq, prior_snd_una))
+ if (!after(sp[used_sacks].end_seq, prior_snd_una)) {
+ if (i == 0)
+ first_sack_index = -1;
continue;
+ }
used_sacks++;
}
@@ -3160,6 +3165,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
tp->retransmit_skb_hint = NULL;
if (unlikely(skb == tp->lost_skb_hint))
tp->lost_skb_hint = NULL;
+ tcp_highest_sack_replace(sk, skb, next);
tcp_rtx_queue_unlink_and_free(skb, sk);
}
@@ -3920,6 +3926,10 @@ void tcp_parse_options(const struct net *net,
*/
break;
#endif
+ case TCPOPT_MPTCP:
+ mptcp_parse_option(skb, ptr, opsize, opt_rx);
+ break;
+
case TCPOPT_FASTOPEN:
tcp_parse_fastopen_option(
opsize - TCPOLEN_FASTOPEN_BASE,
@@ -4261,8 +4271,10 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb)
* The receiver remembers and reflects via DSACKs. Leverage the
* DSACK state and change the txhash to re-route speculatively.
*/
- if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq)
+ if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) {
sk_rethink_txhash(sk);
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH);
+ }
}
static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
@@ -4420,6 +4432,9 @@ static bool tcp_try_coalesce(struct sock *sk,
if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
return false;
+ if (!mptcp_skb_can_collapse(to, from))
+ return false;
+
#ifdef CONFIG_TLS_DEVICE
if (from->decrypted != to->decrypted)
return false;
@@ -4758,6 +4773,9 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
bool fragstolen;
int eaten;
+ if (sk_is_mptcp(sk))
+ mptcp_incoming_options(sk, skb, &tp->rx_opt);
+
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
__kfree_skb(skb);
return;
@@ -4929,7 +4947,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
/* The first skb to collapse is:
* - not SYN/FIN and
* - bloated or contains data before "start" or
- * overlaps to the next one.
+ * overlaps to the next one and mptcp allow collapsing.
*/
if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
(tcp_win_from_space(sk, skb->truesize) > skb->len ||
@@ -4938,7 +4956,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
break;
}
- if (n && n != tail &&
+ if (n && n != tail && mptcp_skb_can_collapse(skb, n) &&
TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) {
end_of_skbs = false;
break;
@@ -4971,6 +4989,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
else
__skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */
skb_set_owner_r(nskb, sk);
+ mptcp_skb_ext_move(nskb, skb);
/* Copy data, releasing collapsed skbs. */
while (copy > 0) {
@@ -4990,6 +5009,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
skb = tcp_collapse_one(sk, skb, list, root);
if (!skb ||
skb == tail ||
+ !mptcp_skb_can_collapse(nskb, skb) ||
(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
goto end;
#ifdef CONFIG_TLS_DEVICE
@@ -5964,6 +5984,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
tcp_initialize_rcv_mss(sk);
+ if (sk_is_mptcp(sk))
+ mptcp_rcv_synsent(sk);
+
/* Remember, tcp_poll() does not lock socket!
* Change state from SYN-SENT only after copied_seq
* is initialized. */
@@ -6329,8 +6352,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
case TCP_CLOSE_WAIT:
case TCP_CLOSING:
case TCP_LAST_ACK:
- if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
+ if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
+ if (sk_is_mptcp(sk))
+ mptcp_incoming_options(sk, skb, &tp->rx_opt);
break;
+ }
/* fall through */
case TCP_FIN_WAIT1:
case TCP_FIN_WAIT2:
@@ -6586,6 +6612,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
tcp_rsk(req)->af_specific = af_ops;
tcp_rsk(req)->ts_off = 0;
+#if IS_ENABLED(CONFIG_MPTCP)
+ tcp_rsk(req)->is_mptcp = 0;
+#endif
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = af_ops->mss_clamp;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4adac9c..df1166b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1426,7 +1426,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = {
.syn_ack_timeout = tcp_syn_ack_timeout,
};
-static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
+const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
.mss_clamp = TCP_MSS_DEFAULT,
#ifdef CONFIG_TCP_MD5SIG
.req_md5_lookup = tcp_v4_md5_lookup,
@@ -2678,7 +2678,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
int cpu;
if (net->ipv4.tcp_congestion_control)
- module_put(net->ipv4.tcp_congestion_control->owner);
+ bpf_module_put(net->ipv4.tcp_congestion_control,
+ net->ipv4.tcp_congestion_control->owner);
for_each_possible_cpu(cpu)
inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
@@ -2785,7 +2786,8 @@ static int __net_init tcp_sk_init(struct net *net)
/* Reno is always built in */
if (!net_eq(net, &init_net) &&
- try_module_get(init_net.ipv4.tcp_congestion_control->owner))
+ bpf_try_module_get(init_net.ipv4.tcp_congestion_control,
+ init_net.ipv4.tcp_congestion_control->owner))
net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control;
else
net->ipv4.tcp_congestion_control = &tcp_reno;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index c802bc8..ad3b56d 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -414,7 +414,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
rcu_read_lock();
ca = tcp_ca_find_key(ca_key);
- if (likely(ca && try_module_get(ca->owner))) {
+ if (likely(ca && bpf_try_module_get(ca, ca->owner))) {
icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
icsk->icsk_ca_ops = ca;
ca_got_dst = true;
@@ -425,7 +425,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
/* If no valid choice made yet, assign current system default ca. */
if (!ca_got_dst &&
(!icsk->icsk_ca_setsockopt ||
- !try_module_get(icsk->icsk_ca_ops->owner)))
+ !bpf_try_module_get(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner)))
tcp_assign_congestion_control(sk);
tcp_set_ca_state(sk, TCP_CA_Open);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 58c92a7..306e25d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -38,6 +38,7 @@
#define pr_fmt(fmt) "TCP: " fmt
#include <net/tcp.h>
+#include <net/mptcp.h>
#include <linux/compiler.h>
#include <linux/gfp.h>
@@ -414,6 +415,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
#define OPTION_WSCALE (1 << 3)
#define OPTION_FAST_OPEN_COOKIE (1 << 8)
#define OPTION_SMC (1 << 9)
+#define OPTION_MPTCP (1 << 10)
static void smc_options_write(__be32 *ptr, u16 *options)
{
@@ -439,8 +441,17 @@ struct tcp_out_options {
__u8 *hash_location; /* temporary pointer, overloaded */
__u32 tsval, tsecr; /* need to include OPTION_TS */
struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */
+ struct mptcp_out_options mptcp;
};
+static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
+{
+#if IS_ENABLED(CONFIG_MPTCP)
+ if (unlikely(OPTION_MPTCP & opts->options))
+ mptcp_write_options(ptr, &opts->mptcp);
+#endif
+}
+
/* Write previously computed TCP options to the packet.
*
* Beware: Something in the Internet is very sensitive to the ordering of
@@ -549,6 +560,8 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
}
smc_options_write(ptr, &options);
+
+ mptcp_options_write(ptr, opts);
}
static void smc_set_option(const struct tcp_sock *tp,
@@ -584,6 +597,22 @@ static void smc_set_option_cond(const struct tcp_sock *tp,
#endif
}
+static void mptcp_set_option_cond(const struct request_sock *req,
+ struct tcp_out_options *opts,
+ unsigned int *remaining)
+{
+ if (rsk_is_mptcp(req)) {
+ unsigned int size;
+
+ if (mptcp_synack_options(req, &size, &opts->mptcp)) {
+ if (*remaining >= size) {
+ opts->options |= OPTION_MPTCP;
+ *remaining -= size;
+ }
+ }
+ }
+}
+
/* Compute TCP options for SYN packets. This is not the final
* network wire format yet.
*/
@@ -653,6 +682,15 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
smc_set_option(tp, opts, &remaining);
+ if (sk_is_mptcp(sk)) {
+ unsigned int size;
+
+ if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) {
+ opts->options |= OPTION_MPTCP;
+ remaining -= size;
+ }
+ }
+
return MAX_TCP_OPTION_SPACE - remaining;
}
@@ -714,6 +752,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
}
}
+ mptcp_set_option_cond(req, opts, &remaining);
+
smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
return MAX_TCP_OPTION_SPACE - remaining;
@@ -751,16 +791,37 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
size += TCPOLEN_TSTAMP_ALIGNED;
}
+ /* MPTCP options have precedence over SACK for the limited TCP
+ * option space because a MPTCP connection would be forced to
+ * fall back to regular TCP if a required multipath option is
+ * missing. SACK still gets a chance to use whatever space is
+ * left.
+ */
+ if (sk_is_mptcp(sk)) {
+ unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
+ unsigned int opt_size = 0;
+
+ if (mptcp_established_options(sk, skb, &opt_size, remaining,
+ &opts->mptcp)) {
+ opts->options |= OPTION_MPTCP;
+ size += opt_size;
+ }
+ }
+
eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
if (unlikely(eff_sacks)) {
const unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
+ if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED +
+ TCPOLEN_SACK_PERBLOCK))
+ return size;
+
opts->num_sack_blocks =
min_t(unsigned int, eff_sacks,
(remaining - TCPOLEN_SACK_BASE_ALIGNED) /
TCPOLEN_SACK_PERBLOCK);
- if (likely(opts->num_sack_blocks))
- size += TCPOLEN_SACK_BASE_ALIGNED +
- opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
+
+ size += TCPOLEN_SACK_BASE_ALIGNED +
+ opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
}
return size;
@@ -2865,7 +2926,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
if (!tcp_can_collapse(sk, skb))
break;
- if (!tcp_skb_can_collapse_to(to))
+ if (!tcp_skb_can_collapse(to, skb))
break;
space -= skb->len;
@@ -3232,6 +3293,7 @@ int tcp_send_synack(struct sock *sk)
if (!nskb)
return -ENOMEM;
INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor);
+ tcp_highest_sack_replace(sk, skb, nskb);
tcp_rtx_queue_unlink_and_free(skb, sk);
__skb_header_release(nskb);
tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb);
@@ -3368,8 +3430,8 @@ static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst)
rcu_read_lock();
ca = tcp_ca_find_key(ca_key);
- if (likely(ca && try_module_get(ca->owner))) {
- module_put(icsk->icsk_ca_ops->owner);
+ if (likely(ca && bpf_try_module_get(ca, ca->owner))) {
+ bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner);
icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
icsk->icsk_ca_ops = ca;
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 1097b43..c3f26dc 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -223,6 +223,9 @@ static int tcp_write_timeout(struct sock *sk)
dst_negative_advice(sk);
} else {
sk_rethink_txhash(sk);
+ tp->timeout_rehash++;
+ __NET_INC_STATS(sock_net(sk),
+ LINUX_MIB_TCPTIMEOUTREHASH);
}
retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
expired = icsk->icsk_retransmits >= retry_until;
@@ -234,6 +237,9 @@ static int tcp_write_timeout(struct sock *sk)
dst_negative_advice(sk);
} else {
sk_rethink_txhash(sk);
+ tp->timeout_rehash++;
+ __NET_INC_STATS(sock_net(sk),
+ LINUX_MIB_TCPTIMEOUTREHASH);
}
retry_until = net->ipv4.sysctl_tcp_retries2;
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 12ab5db..38d3ad1 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -99,17 +99,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen)
rcu_read_unlock();
}
-void tcp_update_ulp(struct sock *sk, struct proto *proto)
+void tcp_update_ulp(struct sock *sk, struct proto *proto,
+ void (*write_space)(struct sock *sk))
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (!icsk->icsk_ulp_ops) {
+ sk->sk_write_space = write_space;
sk->sk_prot = proto;
return;
}
if (icsk->icsk_ulp_ops->update)
- icsk->icsk_ulp_ops->update(sk, proto);
+ icsk->icsk_ulp_ops->update(sk, proto, write_space);
}
void tcp_cleanup_ulp(struct sock *sk)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 93a355b6..db76b96 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1368,7 +1368,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
if (likely(partial)) {
up->forward_deficit += size;
size = up->forward_deficit;
- if (size < (sk->sk_rcvbuf >> 2))
+ if (size < (sk->sk_rcvbuf >> 2) &&
+ !skb_queue_empty(&up->reader_queue))
return;
} else {
size += up->forward_deficit;
@@ -1708,7 +1709,8 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
/* sk_queue is empty, reader_queue may contain peeked packets */
} while (timeo &&
- !__skb_wait_for_more_packets(sk, &error, &timeo,
+ !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue,
+ &error, &timeo,
(struct sk_buff *)sk_queue));
*err = error;
@@ -2104,8 +2106,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_SGO_CB_OFFSET);
__skb_push(skb, -skb_mac_offset(skb));
segs = udp_rcv_segment(sk, skb, true);
- for (skb = segs; skb; skb = next) {
- next = skb->next;
+ skb_list_walk_safe(segs, skb, next) {
__skb_pull(skb, skb_transport_offset(skb));
ret = udp_queue_rcv_one_skb(sk, skb);
if (ret > 0)
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b25e421..1a98583 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -184,6 +184,20 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
}
EXPORT_SYMBOL(skb_udp_tunnel_segment);
+static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ unsigned int mss = skb_shinfo(skb)->gso_size;
+
+ skb = skb_segment_list(skb, features, skb_mac_header_len(skb));
+ if (IS_ERR(skb))
+ return skb;
+
+ udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss);
+
+ return skb;
+}
+
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
netdev_features_t features)
{
@@ -196,6 +210,9 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
__sum16 check;
__be16 newlen;
+ if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)
+ return __udp_gso_segment_list(gso_skb, features);
+
mss = skb_shinfo(gso_skb)->gso_size;
if (gso_skb->len <= sizeof(*uh) + mss)
return ERR_PTR(-EINVAL);
@@ -354,6 +371,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
struct udphdr *uh2;
struct sk_buff *p;
unsigned int ulen;
+ int ret = 0;
/* requires non zero csum, for symmetry with GSO */
if (!uh->check) {
@@ -369,7 +387,6 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
}
/* pull encapsulating udp header */
skb_gro_pull(skb, sizeof(struct udphdr));
- skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
@@ -383,14 +400,40 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
continue;
}
+ if (NAPI_GRO_CB(skb)->is_flist != NAPI_GRO_CB(p)->is_flist) {
+ NAPI_GRO_CB(skb)->flush = 1;
+ return p;
+ }
+
/* Terminate the flow on len mismatch or if it grow "too much".
* Under small packet flood GRO count could elsewhere grow a lot
* leading to excessive truesize values.
* On len mismatch merge the first packet shorter than gso_size,
* otherwise complete the GRO packet.
*/
- if (ulen > ntohs(uh2->len) || skb_gro_receive(p, skb) ||
- ulen != ntohs(uh2->len) ||
+ if (ulen > ntohs(uh2->len)) {
+ pp = p;
+ } else {
+ if (NAPI_GRO_CB(skb)->is_flist) {
+ if (!pskb_may_pull(skb, skb_gro_offset(skb))) {
+ NAPI_GRO_CB(skb)->flush = 1;
+ return NULL;
+ }
+ if ((skb->ip_summed != p->ip_summed) ||
+ (skb->csum_level != p->csum_level)) {
+ NAPI_GRO_CB(skb)->flush = 1;
+ return NULL;
+ }
+ ret = skb_gro_receive_list(p, skb);
+ } else {
+ skb_gro_postpull_rcsum(skb, uh,
+ sizeof(struct udphdr));
+
+ ret = skb_gro_receive(p, skb);
+ }
+ }
+
+ if (ret || ulen != ntohs(uh2->len) ||
NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
pp = p;
@@ -401,36 +444,29 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
return NULL;
}
-INDIRECT_CALLABLE_DECLARE(struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
- __be16 sport, __be16 dport));
struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
- struct udphdr *uh, udp_lookup_t lookup)
+ struct udphdr *uh, struct sock *sk)
{
struct sk_buff *pp = NULL;
struct sk_buff *p;
struct udphdr *uh2;
unsigned int off = skb_gro_offset(skb);
int flush = 1;
- struct sock *sk;
- rcu_read_lock();
- sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb,
- udp4_lib_lookup_skb, skb, uh->source, uh->dest);
- if (!sk)
- goto out_unlock;
+ if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
+ NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1;
- if (udp_sk(sk)->gro_enabled) {
+ if ((sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) {
pp = call_gro_receive(udp_gro_receive_segment, head, skb);
- rcu_read_unlock();
return pp;
}
- if (NAPI_GRO_CB(skb)->encap_mark ||
+ if (!sk || NAPI_GRO_CB(skb)->encap_mark ||
(skb->ip_summed != CHECKSUM_PARTIAL &&
NAPI_GRO_CB(skb)->csum_cnt == 0 &&
!NAPI_GRO_CB(skb)->csum_valid) ||
!udp_sk(sk)->gro_receive)
- goto out_unlock;
+ goto out;
/* mark that this skb passed once through the tunnel gro layer */
NAPI_GRO_CB(skb)->encap_mark = 1;
@@ -457,8 +493,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
-out_unlock:
- rcu_read_unlock();
+out:
skb_gro_flush_final(skb, pp, flush);
return pp;
}
@@ -468,8 +503,10 @@ INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ struct sk_buff *pp;
+ struct sock *sk;
- if (unlikely(!uh) || !static_branch_unlikely(&udp_encap_needed_key))
+ if (unlikely(!uh))
goto flush;
/* Don't bother verifying checksum if we're going to flush anyway. */
@@ -484,7 +521,11 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
inet_gro_compute_pseudo);
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 0;
- return udp_gro_receive(head, skb, uh, udp4_lib_lookup_skb);
+ rcu_read_lock();
+ sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+ pp = udp_gro_receive(head, skb, uh, sk);
+ rcu_read_unlock();
+ return pp;
flush:
NAPI_GRO_CB(skb)->flush = 1;
@@ -517,9 +558,7 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
rcu_read_lock();
sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb,
udp4_lib_lookup_skb, skb, uh->source, uh->dest);
- if (sk && udp_sk(sk)->gro_enabled) {
- err = udp_gro_complete_segment(skb);
- } else if (sk && udp_sk(sk)->gro_complete) {
+ if (sk && udp_sk(sk)->gro_complete) {
skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM
: SKB_GSO_UDP_TUNNEL;
@@ -529,6 +568,8 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
skb->encapsulation = 1;
err = udp_sk(sk)->gro_complete(sk, skb,
nhoff + sizeof(struct udphdr));
+ } else {
+ err = udp_gro_complete_segment(skb);
}
rcu_read_unlock();
@@ -544,6 +585,23 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
const struct iphdr *iph = ip_hdr(skb);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
+ if (NAPI_GRO_CB(skb)->is_flist) {
+ uh->len = htons(skb->len - nhoff);
+
+ skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);
+ skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+ if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+ if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
+ skb->csum_level++;
+ } else {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->csum_level = 0;
+ }
+
+ return 0;
+ }
+
if (uh->check)
uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
iph->daddr, 0);
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index 8a42857..ea595c8 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/net/ipv4/xfrm4_protocol.c
@@ -72,6 +72,14 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
if (!head)
goto out;
+ if (!skb_dst(skb)) {
+ const struct iphdr *iph = ip_hdr(skb);
+
+ if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev))
+ goto drop;
+ }
+
for_each_protocol_rcu(*head, handler)
if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
return ret;
@@ -79,6 +87,7 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
out:
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+drop:
kfree_skb(skb);
return 0;
}
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index e31626f..fd53505 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -79,6 +79,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
if (!x)
goto out_reset;
+ skb->mark = xfrm_smark_get(skb->mark, x);
+
sp->xvec[sp->len++] = x;
sp->olen++;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index b1e9a10..58fbde2 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2571,14 +2571,13 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
struct net *net = seq_file_net(seq);
struct ipv6_route_iter *iter = seq->private;
+ ++(*pos);
if (!v)
goto iter_table;
n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next);
- if (n) {
- ++*pos;
+ if (n)
return n;
- }
iter_table:
ipv6_route_check_sernum(iter);
@@ -2586,8 +2585,6 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
r = fib6_walk_continue(&iter->w);
spin_unlock_bh(&iter->tbl->tb6_lock);
if (r > 0) {
- if (v)
- ++*pos;
return iter->w.leaf;
} else if (r < 0) {
fib6_walker_unlink(net, &iter->w);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index ee968d9..55bfc51 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1466,7 +1466,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
dev->mtu -= 8;
if (tunnel->parms.collect_md) {
- dev->features |= NETIF_F_NETNS_LOCAL;
netif_keep_dst(dev);
}
ip6gre_tnl_init_features(dev);
@@ -1894,7 +1893,6 @@ static void ip6gre_tap_setup(struct net_device *dev)
dev->needs_free_netdev = true;
dev->priv_destructor = ip6gre_dev_free;
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
netif_keep_dst(dev);
@@ -2197,7 +2195,6 @@ static void ip6erspan_tap_setup(struct net_device *dev)
dev->needs_free_netdev = true;
dev->priv_destructor = ip6gre_dev_free;
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
netif_keep_dst(dev);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 2f376db..b5dd20c 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1877,10 +1877,8 @@ static int ip6_tnl_dev_init(struct net_device *dev)
if (err)
return err;
ip6_tnl_link_config(t);
- if (t->parms.collect_md) {
- dev->features |= NETIF_F_NETNS_LOCAL;
+ if (t->parms.collect_md)
netif_keep_dst(dev);
- }
return 0;
}
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 6f08b76..524006a 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -449,8 +449,17 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
int err = -1;
int mtu;
- if (!dst)
- goto tx_err_link_failure;
+ if (!dst) {
+ fl->u.ip6.flowi6_oif = dev->ifindex;
+ fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
+ dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6);
+ if (dst->error) {
+ dst_release(dst);
+ dst = NULL;
+ goto tx_err_link_failure;
+ }
+ skb_dst_set(skb, dst);
+ }
dst_hold(dst);
dst = xfrm_lookup(t->net, dst, fl, NULL, 0);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0253b70..4fbdc60 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5576,6 +5576,13 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
expires -= jiffies;
}
+ if (!dst) {
+ if (rt->offload)
+ rtm->rtm_flags |= RTM_F_OFFLOAD;
+ if (rt->trap)
+ rtm->rtm_flags |= RTM_F_TRAP;
+ }
+
if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0)
goto nla_put_failure;
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 85a5447..7cbc1973 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -23,6 +23,7 @@
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/dst_cache.h>
+#include <net/ip_tunnels.h>
#ifdef CONFIG_IPV6_SEG6_HMAC
#include <net/seg6_hmac.h>
#endif
@@ -135,7 +136,8 @@ static bool decap_and_validate(struct sk_buff *skb, int proto)
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
- skb->encapsulation = 0;
+ if (iptunnel_pull_offloads(skb))
+ return false;
return true;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 95e4e1e..33a578a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -75,7 +75,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
static const struct inet_connection_sock_af_ops ipv6_mapped;
-static const struct inet_connection_sock_af_ops ipv6_specific;
+const struct inet_connection_sock_af_ops ipv6_specific;
#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_sock_af_ops tcp_sock_ipv6_specific;
static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
@@ -238,6 +238,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &ipv6_mapped;
+ if (sk_is_mptcp(sk))
+ mptcp_handle_ipv6_mapped(sk, true);
sk->sk_backlog_rcv = tcp_v4_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_mapped_specific;
@@ -248,6 +250,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &ipv6_specific;
+ if (sk_is_mptcp(sk))
+ mptcp_handle_ipv6_mapped(sk, false);
sk->sk_backlog_rcv = tcp_v6_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_specific;
@@ -819,7 +823,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
.syn_ack_timeout = tcp_syn_ack_timeout,
};
-static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
+const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) -
sizeof(struct ipv6hdr),
#ifdef CONFIG_TCP_MD5SIG
@@ -1203,6 +1207,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
newnp->saddr = newsk->sk_v6_rcv_saddr;
inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
+ if (sk_is_mptcp(newsk))
+ mptcp_handle_ipv6_mapped(newsk, true);
newsk->sk_backlog_rcv = tcp_v4_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
@@ -1794,7 +1800,7 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = {
.twsk_destructor = tcp_twsk_destructor,
};
-static const struct inet_connection_sock_af_ops ipv6_specific = {
+const struct inet_connection_sock_af_ops ipv6_specific = {
.queue_xmit = inet6_csk_xmit,
.send_check = tcp_v6_send_check,
.rebuild_header = inet6_sk_rebuild_header,
@@ -2163,9 +2169,16 @@ int __init tcpv6_init(void)
ret = register_pernet_subsys(&tcpv6_net_ops);
if (ret)
goto out_tcpv6_protosw;
+
+ ret = mptcpv6_init();
+ if (ret)
+ goto out_tcpv6_pernet_subsys;
+
out:
return ret;
+out_tcpv6_pernet_subsys:
+ unregister_pernet_subsys(&tcpv6_net_ops);
out_tcpv6_protosw:
inet6_unregister_protosw(&tcpv6_protosw);
out_tcpv6_protocol:
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9fec580..5dc439a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -690,8 +690,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
__skb_push(skb, -skb_mac_offset(skb));
segs = udp_rcv_segment(sk, skb, false);
- for (skb = segs; skb; skb = next) {
- next = skb->next;
+ skb_list_walk_safe(segs, skb, next) {
__skb_pull(skb, skb_transport_offset(skb));
ret = udpv6_queue_rcv_one_skb(sk, skb);
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index f0d5fc2..584157a 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -115,8 +115,10 @@ INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ struct sk_buff *pp;
+ struct sock *sk;
- if (unlikely(!uh) || !static_branch_unlikely(&udpv6_encap_needed_key))
+ if (unlikely(!uh))
goto flush;
/* Don't bother verifying checksum if we're going to flush anyway. */
@@ -132,7 +134,11 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 1;
- return udp_gro_receive(head, skb, uh, udp6_lib_lookup_skb);
+ rcu_read_lock();
+ sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+ pp = udp_gro_receive(head, skb, uh, sk);
+ rcu_read_unlock();
+ return pp;
flush:
NAPI_GRO_CB(skb)->flush = 1;
@@ -144,6 +150,23 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff)
const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
+ if (NAPI_GRO_CB(skb)->is_flist) {
+ uh->len = htons(skb->len - nhoff);
+
+ skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);
+ skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+ if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+ if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
+ skb->csum_level++;
+ } else {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->csum_level = 0;
+ }
+
+ return 0;
+ }
+
if (uh->check)
uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr,
&ipv6h->daddr, 0);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 4fb7f1f..000c742 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2954,6 +2954,28 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy,
return err;
}
+static void ieee80211_end_cac(struct wiphy *wiphy,
+ struct net_device *dev)
+{
+ struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+ struct ieee80211_local *local = sdata->local;
+
+ mutex_lock(&local->mtx);
+ list_for_each_entry(sdata, &local->interfaces, list) {
+ /* it might be waiting for the local->mtx, but then
+ * by the time it gets it, sdata->wdev.cac_started
+ * will no longer be true
+ */
+ cancel_delayed_work(&sdata->dfs_cac_timer_work);
+
+ if (sdata->wdev.cac_started) {
+ ieee80211_vif_release_channel(sdata);
+ sdata->wdev.cac_started = false;
+ }
+ }
+ mutex_unlock(&local->mtx);
+}
+
static struct cfg80211_beacon_data *
cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon)
{
@@ -4023,6 +4045,7 @@ const struct cfg80211_ops mac80211_config_ops = {
#endif
.get_channel = ieee80211_cfg_get_channel,
.start_radar_detection = ieee80211_start_radar_detection,
+ .end_cac = ieee80211_end_cac,
.channel_switch = ieee80211_channel_switch,
.set_qos_map = ieee80211_set_qos_map,
.set_ap_chanwidth = ieee80211_set_ap_chanwidth,
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 68af623..d699833 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -328,6 +328,9 @@ u32 airtime_link_metric_get(struct ieee80211_local *local,
unsigned long fail_avg =
ewma_mesh_fail_avg_read(&sta->mesh->fail_avg);
+ if (sta->mesh->plink_state != NL80211_PLINK_ESTAB)
+ return MAX_METRIC;
+
/* Try to get rate based on HW/SW RC algorithm.
* Rate is returned in units of Kbps, correct this
* to comply with airtime calculation units
diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c
index 727dc9f..e7f57bb 100644
--- a/net/mac80211/tkip.c
+++ b/net/mac80211/tkip.c
@@ -263,9 +263,21 @@ int ieee80211_tkip_decrypt_data(struct arc4_ctx *ctx,
if ((keyid >> 6) != key->conf.keyidx)
return TKIP_DECRYPT_INVALID_KEYIDX;
- if (rx_ctx->ctx.state != TKIP_STATE_NOT_INIT &&
- (iv32 < rx_ctx->iv32 ||
- (iv32 == rx_ctx->iv32 && iv16 <= rx_ctx->iv16)))
+ /* Reject replays if the received TSC is smaller than or equal to the
+ * last received value in a valid message, but with an exception for
+ * the case where a new key has been set and no valid frame using that
+ * key has yet received and the local RSC was initialized to 0. This
+ * exception allows the very first frame sent by the transmitter to be
+ * accepted even if that transmitter were to use TSC 0 (IEEE 802.11
+ * described TSC to be initialized to 1 whenever a new key is taken into
+ * use).
+ */
+ if (iv32 < rx_ctx->iv32 ||
+ (iv32 == rx_ctx->iv32 &&
+ (iv16 < rx_ctx->iv16 ||
+ (iv16 == rx_ctx->iv16 &&
+ (rx_ctx->iv32 || rx_ctx->iv16 ||
+ rx_ctx->ctx.state != TKIP_STATE_NOT_INIT)))))
return TKIP_DECRYPT_REPLAY;
if (only_iv) {
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index a8a7306a..4bd1faf 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3949,18 +3949,15 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
}
}
- next = skb;
- while (next) {
- skb = next;
- next = skb->next;
-
- skb->prev = NULL;
- skb->next = NULL;
+ skb_list_walk_safe(skb, skb, next) {
+ skb_mark_not_on_list(skb);
skb = ieee80211_build_hdr(sdata, skb, info_flags,
sta, ctrl_flags);
- if (IS_ERR(skb))
+ if (IS_ERR(skb)) {
+ kfree_skb_list(next);
goto out;
+ }
ieee80211_tx_stats(dev, skb->len);
diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig
new file mode 100644
index 0000000..5db56d2
--- /dev/null
+++ b/net/mptcp/Kconfig
@@ -0,0 +1,26 @@
+
+config MPTCP
+ bool "MPTCP: Multipath TCP"
+ depends on INET
+ select SKB_EXTENSIONS
+ select CRYPTO_LIB_SHA256
+ help
+ Multipath TCP (MPTCP) connections send and receive data over multiple
+ subflows in order to utilize multiple network paths. Each subflow
+ uses the TCP protocol, and TCP options carry header information for
+ MPTCP.
+
+config MPTCP_IPV6
+ bool "MPTCP: IPv6 support for Multipath TCP"
+ depends on MPTCP
+ select IPV6
+ default y
+
+config MPTCP_HMAC_TEST
+ bool "Tests for MPTCP HMAC implementation"
+ default n
+ help
+ This option enable boot time self-test for the HMAC implementation
+ used by the MPTCP code
+
+ Say N if you are unsure.
diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile
new file mode 100644
index 0000000..4e98d9e
--- /dev/null
+++ b/net/mptcp/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_MPTCP) += mptcp.o
+
+mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o
diff --git a/net/mptcp/crypto.c b/net/mptcp/crypto.c
new file mode 100644
index 0000000..40d1bb1
--- /dev/null
+++ b/net/mptcp/crypto.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP cryptographic functions
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ *
+ * Note: This code is based on mptcp_ctrl.c, mptcp_ipv4.c, and
+ * mptcp_ipv6 from multipath-tcp.org, authored by:
+ *
+ * Sébastien Barré <sebastien.barre@uclouvain.be>
+ * Christoph Paasch <christoph.paasch@uclouvain.be>
+ * Jaakko Korkeaniemi <jaakko.korkeaniemi@aalto.fi>
+ * Gregory Detal <gregory.detal@uclouvain.be>
+ * Fabien Duchêne <fabien.duchene@uclouvain.be>
+ * Andreas Seelinger <Andreas.Seelinger@rwth-aachen.de>
+ * Lavkesh Lahngir <lavkesh51@gmail.com>
+ * Andreas Ripke <ripke@neclab.eu>
+ * Vlad Dogaru <vlad.dogaru@intel.com>
+ * Octavian Purdila <octavian.purdila@intel.com>
+ * John Ronan <jronan@tssg.org>
+ * Catalin Nicutar <catalin.nicutar@gmail.com>
+ * Brandon Heller <brandonh@stanford.edu>
+ */
+
+#include <linux/kernel.h>
+#include <crypto/sha.h>
+#include <asm/unaligned.h>
+
+#include "protocol.h"
+
+#define SHA256_DIGEST_WORDS (SHA256_DIGEST_SIZE / 4)
+
+void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn)
+{
+ __be32 mptcp_hashed_key[SHA256_DIGEST_WORDS];
+ __be64 input = cpu_to_be64(key);
+ struct sha256_state state;
+
+ sha256_init(&state);
+ sha256_update(&state, (__force u8 *)&input, sizeof(input));
+ sha256_final(&state, (u8 *)mptcp_hashed_key);
+
+ if (token)
+ *token = be32_to_cpu(mptcp_hashed_key[0]);
+ if (idsn)
+ *idsn = be64_to_cpu(*((__be64 *)&mptcp_hashed_key[6]));
+}
+
+void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u32 nonce1, u32 nonce2,
+ void *hmac)
+{
+ u8 input[SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE];
+ __be32 mptcp_hashed_key[SHA256_DIGEST_WORDS];
+ __be32 *hash_out = (__force __be32 *)hmac;
+ struct sha256_state state;
+ u8 key1be[8];
+ u8 key2be[8];
+ int i;
+
+ put_unaligned_be64(key1, key1be);
+ put_unaligned_be64(key2, key2be);
+
+ /* Generate key xored with ipad */
+ memset(input, 0x36, SHA_MESSAGE_BYTES);
+ for (i = 0; i < 8; i++)
+ input[i] ^= key1be[i];
+ for (i = 0; i < 8; i++)
+ input[i + 8] ^= key2be[i];
+
+ put_unaligned_be32(nonce1, &input[SHA256_BLOCK_SIZE]);
+ put_unaligned_be32(nonce2, &input[SHA256_BLOCK_SIZE + 4]);
+
+ sha256_init(&state);
+ sha256_update(&state, input, SHA256_BLOCK_SIZE + 8);
+
+ /* emit sha256(K1 || msg) on the second input block, so we can
+ * reuse 'input' for the last hashing
+ */
+ sha256_final(&state, &input[SHA256_BLOCK_SIZE]);
+
+ /* Prepare second part of hmac */
+ memset(input, 0x5C, SHA_MESSAGE_BYTES);
+ for (i = 0; i < 8; i++)
+ input[i] ^= key1be[i];
+ for (i = 0; i < 8; i++)
+ input[i + 8] ^= key2be[i];
+
+ sha256_init(&state);
+ sha256_update(&state, input, SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE);
+ sha256_final(&state, (u8 *)mptcp_hashed_key);
+
+ /* takes only first 160 bits */
+ for (i = 0; i < 5; i++)
+ hash_out[i] = mptcp_hashed_key[i];
+}
+
+#ifdef CONFIG_MPTCP_HMAC_TEST
+struct test_cast {
+ char *key;
+ char *msg;
+ char *result;
+};
+
+/* we can't reuse RFC 4231 test vectors, as we have constraint on the
+ * input and key size, and we truncate the output.
+ */
+static struct test_cast tests[] = {
+ {
+ .key = "0b0b0b0b0b0b0b0b",
+ .msg = "48692054",
+ .result = "8385e24fb4235ac37556b6b886db106284a1da67",
+ },
+ {
+ .key = "aaaaaaaaaaaaaaaa",
+ .msg = "dddddddd",
+ .result = "2c5e219164ff1dca1c4a92318d847bb6b9d44492",
+ },
+ {
+ .key = "0102030405060708",
+ .msg = "cdcdcdcd",
+ .result = "e73b9ba9969969cefb04aa0d6df18ec2fcc075b6",
+ },
+};
+
+static int __init test_mptcp_crypto(void)
+{
+ char hmac[20], hmac_hex[41];
+ u32 nonce1, nonce2;
+ u64 key1, key2;
+ int i, j;
+
+ for (i = 0; i < ARRAY_SIZE(tests); ++i) {
+ /* mptcp hmap will convert to be before computing the hmac */
+ key1 = be64_to_cpu(*((__be64 *)&tests[i].key[0]));
+ key2 = be64_to_cpu(*((__be64 *)&tests[i].key[8]));
+ nonce1 = be32_to_cpu(*((__be32 *)&tests[i].msg[0]));
+ nonce2 = be32_to_cpu(*((__be32 *)&tests[i].msg[4]));
+
+ mptcp_crypto_hmac_sha(key1, key2, nonce1, nonce2, hmac);
+ for (j = 0; j < 20; ++j)
+ sprintf(&hmac_hex[j << 1], "%02x", hmac[j] & 0xff);
+ hmac_hex[40] = 0;
+
+ if (memcmp(hmac_hex, tests[i].result, 40))
+ pr_err("test %d failed, got %s expected %s", i,
+ hmac_hex, tests[i].result);
+ else
+ pr_info("test %d [ ok ]", i);
+ }
+ return 0;
+}
+
+late_initcall(test_mptcp_crypto);
+#endif
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
new file mode 100644
index 0000000..8e39585
--- /dev/null
+++ b/net/mptcp/ctrl.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2019, Tessares SA.
+ */
+
+#include <linux/sysctl.h>
+
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+#include "protocol.h"
+
+#define MPTCP_SYSCTL_PATH "net/mptcp"
+
+static int mptcp_pernet_id;
+struct mptcp_pernet {
+ struct ctl_table_header *ctl_table_hdr;
+
+ int mptcp_enabled;
+};
+
+static struct mptcp_pernet *mptcp_get_pernet(struct net *net)
+{
+ return net_generic(net, mptcp_pernet_id);
+}
+
+int mptcp_is_enabled(struct net *net)
+{
+ return mptcp_get_pernet(net)->mptcp_enabled;
+}
+
+static struct ctl_table mptcp_sysctl_table[] = {
+ {
+ .procname = "enabled",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ /* users with CAP_NET_ADMIN or root (not and) can change this
+ * value, same as other sysctl or the 'net' tree.
+ */
+ .proc_handler = proc_dointvec,
+ },
+ {}
+};
+
+static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
+{
+ pernet->mptcp_enabled = 1;
+}
+
+static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
+{
+ struct ctl_table_header *hdr;
+ struct ctl_table *table;
+
+ table = mptcp_sysctl_table;
+ if (!net_eq(net, &init_net)) {
+ table = kmemdup(table, sizeof(mptcp_sysctl_table), GFP_KERNEL);
+ if (!table)
+ goto err_alloc;
+ }
+
+ table[0].data = &pernet->mptcp_enabled;
+
+ hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
+ if (!hdr)
+ goto err_reg;
+
+ pernet->ctl_table_hdr = hdr;
+
+ return 0;
+
+err_reg:
+ if (!net_eq(net, &init_net))
+ kfree(table);
+err_alloc:
+ return -ENOMEM;
+}
+
+static void mptcp_pernet_del_table(struct mptcp_pernet *pernet)
+{
+ struct ctl_table *table = pernet->ctl_table_hdr->ctl_table_arg;
+
+ unregister_net_sysctl_table(pernet->ctl_table_hdr);
+
+ kfree(table);
+}
+
+static int __net_init mptcp_net_init(struct net *net)
+{
+ struct mptcp_pernet *pernet = mptcp_get_pernet(net);
+
+ mptcp_pernet_set_defaults(pernet);
+
+ return mptcp_pernet_new_table(net, pernet);
+}
+
+/* Note: the callback will only be called per extra netns */
+static void __net_exit mptcp_net_exit(struct net *net)
+{
+ struct mptcp_pernet *pernet = mptcp_get_pernet(net);
+
+ mptcp_pernet_del_table(pernet);
+}
+
+static struct pernet_operations mptcp_pernet_ops = {
+ .init = mptcp_net_init,
+ .exit = mptcp_net_exit,
+ .id = &mptcp_pernet_id,
+ .size = sizeof(struct mptcp_pernet),
+};
+
+void __init mptcp_init(void)
+{
+ mptcp_proto_init();
+
+ if (register_pernet_subsys(&mptcp_pernet_ops) < 0)
+ panic("Failed to register MPTCP pernet subsystem.\n");
+}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+int __init mptcpv6_init(void)
+{
+ int err;
+
+ err = mptcp_proto_v6_init();
+
+ return err;
+}
+#endif
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
new file mode 100644
index 0000000..45acd87
--- /dev/null
+++ b/net/mptcp/options.c
@@ -0,0 +1,586 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#include <linux/kernel.h>
+#include <net/tcp.h>
+#include <net/mptcp.h>
+#include "protocol.h"
+
+static bool mptcp_cap_flag_sha256(u8 flags)
+{
+ return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256;
+}
+
+void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
+ int opsize, struct tcp_options_received *opt_rx)
+{
+ struct mptcp_options_received *mp_opt = &opt_rx->mptcp;
+ u8 subtype = *ptr >> 4;
+ int expected_opsize;
+ u8 version;
+ u8 flags;
+
+ switch (subtype) {
+ case MPTCPOPT_MP_CAPABLE:
+ /* strict size checking */
+ if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+ if (skb->len > tcp_hdr(skb)->doff << 2)
+ expected_opsize = TCPOLEN_MPTCP_MPC_ACK_DATA;
+ else
+ expected_opsize = TCPOLEN_MPTCP_MPC_ACK;
+ } else {
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)
+ expected_opsize = TCPOLEN_MPTCP_MPC_SYNACK;
+ else
+ expected_opsize = TCPOLEN_MPTCP_MPC_SYN;
+ }
+ if (opsize != expected_opsize)
+ break;
+
+ /* try to be gentle vs future versions on the initial syn */
+ version = *ptr++ & MPTCP_VERSION_MASK;
+ if (opsize != TCPOLEN_MPTCP_MPC_SYN) {
+ if (version != MPTCP_SUPPORTED_VERSION)
+ break;
+ } else if (version < MPTCP_SUPPORTED_VERSION) {
+ break;
+ }
+
+ flags = *ptr++;
+ if (!mptcp_cap_flag_sha256(flags) ||
+ (flags & MPTCP_CAP_EXTENSIBILITY))
+ break;
+
+ /* RFC 6824, Section 3.1:
+ * "For the Checksum Required bit (labeled "A"), if either
+ * host requires the use of checksums, checksums MUST be used.
+ * In other words, the only way for checksums not to be used
+ * is if both hosts in their SYNs set A=0."
+ *
+ * Section 3.3.0:
+ * "If a checksum is not present when its use has been
+ * negotiated, the receiver MUST close the subflow with a RST as
+ * it is considered broken."
+ *
+ * We don't implement DSS checksum - fall back to TCP.
+ */
+ if (flags & MPTCP_CAP_CHECKSUM_REQD)
+ break;
+
+ mp_opt->mp_capable = 1;
+ if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) {
+ mp_opt->sndr_key = get_unaligned_be64(ptr);
+ ptr += 8;
+ }
+ if (opsize >= TCPOLEN_MPTCP_MPC_ACK) {
+ mp_opt->rcvr_key = get_unaligned_be64(ptr);
+ ptr += 8;
+ }
+ if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA) {
+ /* Section 3.1.:
+ * "the data parameters in a MP_CAPABLE are semantically
+ * equivalent to those in a DSS option and can be used
+ * interchangeably."
+ */
+ mp_opt->dss = 1;
+ mp_opt->use_map = 1;
+ mp_opt->mpc_map = 1;
+ mp_opt->data_len = get_unaligned_be16(ptr);
+ ptr += 2;
+ }
+ pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d",
+ version, flags, opsize, mp_opt->sndr_key,
+ mp_opt->rcvr_key, mp_opt->data_len);
+ break;
+
+ case MPTCPOPT_DSS:
+ pr_debug("DSS");
+ ptr++;
+
+ /* we must clear 'mpc_map' be able to detect MP_CAPABLE
+ * map vs DSS map in mptcp_incoming_options(), and reconstruct
+ * map info accordingly
+ */
+ mp_opt->mpc_map = 0;
+ flags = (*ptr++) & MPTCP_DSS_FLAG_MASK;
+ mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0;
+ mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0;
+ mp_opt->use_map = (flags & MPTCP_DSS_HAS_MAP) != 0;
+ mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0;
+ mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK);
+
+ pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d",
+ mp_opt->data_fin, mp_opt->dsn64,
+ mp_opt->use_map, mp_opt->ack64,
+ mp_opt->use_ack);
+
+ expected_opsize = TCPOLEN_MPTCP_DSS_BASE;
+
+ if (mp_opt->use_ack) {
+ if (mp_opt->ack64)
+ expected_opsize += TCPOLEN_MPTCP_DSS_ACK64;
+ else
+ expected_opsize += TCPOLEN_MPTCP_DSS_ACK32;
+ }
+
+ if (mp_opt->use_map) {
+ if (mp_opt->dsn64)
+ expected_opsize += TCPOLEN_MPTCP_DSS_MAP64;
+ else
+ expected_opsize += TCPOLEN_MPTCP_DSS_MAP32;
+ }
+
+ /* RFC 6824, Section 3.3:
+ * If a checksum is present, but its use had
+ * not been negotiated in the MP_CAPABLE handshake,
+ * the checksum field MUST be ignored.
+ */
+ if (opsize != expected_opsize &&
+ opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM)
+ break;
+
+ mp_opt->dss = 1;
+
+ if (mp_opt->use_ack) {
+ if (mp_opt->ack64) {
+ mp_opt->data_ack = get_unaligned_be64(ptr);
+ ptr += 8;
+ } else {
+ mp_opt->data_ack = get_unaligned_be32(ptr);
+ ptr += 4;
+ }
+
+ pr_debug("data_ack=%llu", mp_opt->data_ack);
+ }
+
+ if (mp_opt->use_map) {
+ if (mp_opt->dsn64) {
+ mp_opt->data_seq = get_unaligned_be64(ptr);
+ ptr += 8;
+ } else {
+ mp_opt->data_seq = get_unaligned_be32(ptr);
+ ptr += 4;
+ }
+
+ mp_opt->subflow_seq = get_unaligned_be32(ptr);
+ ptr += 4;
+
+ mp_opt->data_len = get_unaligned_be16(ptr);
+ ptr += 2;
+
+ pr_debug("data_seq=%llu subflow_seq=%u data_len=%u",
+ mp_opt->data_seq, mp_opt->subflow_seq,
+ mp_opt->data_len);
+ }
+
+ break;
+
+ default:
+ break;
+ }
+}
+
+void mptcp_get_options(const struct sk_buff *skb,
+ struct tcp_options_received *opt_rx)
+{
+ const unsigned char *ptr;
+ const struct tcphdr *th = tcp_hdr(skb);
+ int length = (th->doff * 4) - sizeof(struct tcphdr);
+
+ ptr = (const unsigned char *)(th + 1);
+
+ while (length > 0) {
+ int opcode = *ptr++;
+ int opsize;
+
+ switch (opcode) {
+ case TCPOPT_EOL:
+ return;
+ case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */
+ length--;
+ continue;
+ default:
+ opsize = *ptr++;
+ if (opsize < 2) /* "silly options" */
+ return;
+ if (opsize > length)
+ return; /* don't parse partial options */
+ if (opcode == TCPOPT_MPTCP)
+ mptcp_parse_option(skb, ptr, opsize, opt_rx);
+ ptr += opsize - 2;
+ length -= opsize;
+ }
+ }
+}
+
+bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
+ unsigned int *size, struct mptcp_out_options *opts)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+
+ /* we will use snd_isn to detect first pkt [re]transmission
+ * in mptcp_established_options_mp()
+ */
+ subflow->snd_isn = TCP_SKB_CB(skb)->end_seq;
+ if (subflow->request_mptcp) {
+ pr_debug("local_key=%llu", subflow->local_key);
+ opts->suboptions = OPTION_MPTCP_MPC_SYN;
+ opts->sndr_key = subflow->local_key;
+ *size = TCPOLEN_MPTCP_MPC_SYN;
+ return true;
+ }
+ return false;
+}
+
+void mptcp_rcv_synsent(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ pr_debug("subflow=%p", subflow);
+ if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) {
+ subflow->mp_capable = 1;
+ subflow->can_ack = 1;
+ subflow->remote_key = tp->rx_opt.mptcp.sndr_key;
+ } else {
+ tcp_sk(sk)->is_mptcp = 0;
+ }
+}
+
+static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
+ unsigned int *size,
+ unsigned int remaining,
+ struct mptcp_out_options *opts)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct mptcp_ext *mpext;
+ unsigned int data_len;
+
+ pr_debug("subflow=%p fourth_ack=%d seq=%x:%x remaining=%d", subflow,
+ subflow->fourth_ack, subflow->snd_isn,
+ skb ? TCP_SKB_CB(skb)->seq : 0, remaining);
+
+ if (subflow->mp_capable && !subflow->fourth_ack && skb &&
+ subflow->snd_isn == TCP_SKB_CB(skb)->seq) {
+ /* When skb is not available, we better over-estimate the
+ * emitted options len. A full DSS option is longer than
+ * TCPOLEN_MPTCP_MPC_ACK_DATA, so let's the caller try to fit
+ * that.
+ */
+ mpext = mptcp_get_ext(skb);
+ data_len = mpext ? mpext->data_len : 0;
+
+ /* we will check ext_copy.data_len in mptcp_write_options() to
+ * discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and
+ * TCPOLEN_MPTCP_MPC_ACK
+ */
+ opts->ext_copy.data_len = data_len;
+ opts->suboptions = OPTION_MPTCP_MPC_ACK;
+ opts->sndr_key = subflow->local_key;
+ opts->rcvr_key = subflow->remote_key;
+
+ /* Section 3.1.
+ * The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK
+ * packets that start the first subflow of an MPTCP connection,
+ * as well as the first packet that carries data
+ */
+ if (data_len > 0)
+ *size = ALIGN(TCPOLEN_MPTCP_MPC_ACK_DATA, 4);
+ else
+ *size = TCPOLEN_MPTCP_MPC_ACK;
+
+ pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d",
+ subflow, subflow->local_key, subflow->remote_key,
+ data_len);
+
+ return true;
+ }
+ return false;
+}
+
+static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
+ struct mptcp_ext *ext)
+{
+ ext->data_fin = 1;
+
+ if (!ext->use_map) {
+ /* RFC6824 requires a DSS mapping with specific values
+ * if DATA_FIN is set but no data payload is mapped
+ */
+ ext->use_map = 1;
+ ext->dsn64 = 1;
+ ext->data_seq = mptcp_sk(subflow->conn)->write_seq;
+ ext->subflow_seq = 0;
+ ext->data_len = 1;
+ } else {
+ /* If there's an existing DSS mapping, DATA_FIN consumes
+ * 1 additional byte of mapping space.
+ */
+ ext->data_len++;
+ }
+}
+
+static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
+ unsigned int *size,
+ unsigned int remaining,
+ struct mptcp_out_options *opts)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ unsigned int dss_size = 0;
+ struct mptcp_ext *mpext;
+ struct mptcp_sock *msk;
+ unsigned int ack_size;
+ bool ret = false;
+ u8 tcp_fin;
+
+ if (skb) {
+ mpext = mptcp_get_ext(skb);
+ tcp_fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
+ } else {
+ mpext = NULL;
+ tcp_fin = 0;
+ }
+
+ if (!skb || (mpext && mpext->use_map) || tcp_fin) {
+ unsigned int map_size;
+
+ map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
+
+ remaining -= map_size;
+ dss_size = map_size;
+ if (mpext)
+ opts->ext_copy = *mpext;
+
+ if (skb && tcp_fin &&
+ subflow->conn->sk_state != TCP_ESTABLISHED)
+ mptcp_write_data_fin(subflow, &opts->ext_copy);
+ ret = true;
+ }
+
+ opts->ext_copy.use_ack = 0;
+ msk = mptcp_sk(subflow->conn);
+ if (!msk || !READ_ONCE(msk->can_ack)) {
+ *size = ALIGN(dss_size, 4);
+ return ret;
+ }
+
+ ack_size = TCPOLEN_MPTCP_DSS_ACK64;
+
+ /* Add kind/length/subtype/flag overhead if mapping is not populated */
+ if (dss_size == 0)
+ ack_size += TCPOLEN_MPTCP_DSS_BASE;
+
+ dss_size += ack_size;
+
+ opts->ext_copy.data_ack = msk->ack_seq;
+ opts->ext_copy.ack64 = 1;
+ opts->ext_copy.use_ack = 1;
+
+ *size = ALIGN(dss_size, 4);
+ return true;
+}
+
+bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
+ unsigned int *size, unsigned int remaining,
+ struct mptcp_out_options *opts)
+{
+ unsigned int opt_size = 0;
+ bool ret = false;
+
+ if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts))
+ ret = true;
+ else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining,
+ opts))
+ ret = true;
+
+ /* we reserved enough space for the above options, and exceeding the
+ * TCP option space would be fatal
+ */
+ if (WARN_ON_ONCE(opt_size > remaining))
+ return false;
+
+ *size += opt_size;
+ remaining -= opt_size;
+
+ return ret;
+}
+
+bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
+ struct mptcp_out_options *opts)
+{
+ struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
+
+ if (subflow_req->mp_capable) {
+ opts->suboptions = OPTION_MPTCP_MPC_SYNACK;
+ opts->sndr_key = subflow_req->local_key;
+ *size = TCPOLEN_MPTCP_MPC_SYNACK;
+ pr_debug("subflow_req=%p, local_key=%llu",
+ subflow_req, subflow_req->local_key);
+ return true;
+ }
+ return false;
+}
+
+static bool check_fourth_ack(struct mptcp_subflow_context *subflow,
+ struct sk_buff *skb,
+ struct mptcp_options_received *mp_opt)
+{
+ /* here we can process OoO, in-window pkts, only in-sequence 4th ack
+ * are relevant
+ */
+ if (likely(subflow->fourth_ack ||
+ TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1))
+ return true;
+
+ if (mp_opt->use_ack)
+ subflow->fourth_ack = 1;
+
+ if (subflow->can_ack)
+ return true;
+
+ /* If the first established packet does not contain MP_CAPABLE + data
+ * then fallback to TCP
+ */
+ if (!mp_opt->mp_capable) {
+ subflow->mp_capable = 0;
+ tcp_sk(mptcp_subflow_tcp_sock(subflow))->is_mptcp = 0;
+ return false;
+ }
+ subflow->remote_key = mp_opt->sndr_key;
+ subflow->can_ack = 1;
+ return true;
+}
+
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
+ struct tcp_options_received *opt_rx)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct mptcp_options_received *mp_opt;
+ struct mptcp_ext *mpext;
+
+ mp_opt = &opt_rx->mptcp;
+ if (!check_fourth_ack(subflow, skb, mp_opt))
+ return;
+
+ if (!mp_opt->dss)
+ return;
+
+ mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
+ if (!mpext)
+ return;
+
+ memset(mpext, 0, sizeof(*mpext));
+
+ if (mp_opt->use_map) {
+ if (mp_opt->mpc_map) {
+ /* this is an MP_CAPABLE carrying MPTCP data
+ * we know this map the first chunk of data
+ */
+ mptcp_crypto_key_sha(subflow->remote_key, NULL,
+ &mpext->data_seq);
+ mpext->data_seq++;
+ mpext->subflow_seq = 1;
+ mpext->dsn64 = 1;
+ mpext->mpc_map = 1;
+ } else {
+ mpext->data_seq = mp_opt->data_seq;
+ mpext->subflow_seq = mp_opt->subflow_seq;
+ mpext->dsn64 = mp_opt->dsn64;
+ }
+ mpext->data_len = mp_opt->data_len;
+ mpext->use_map = 1;
+ }
+
+ if (mp_opt->use_ack) {
+ mpext->data_ack = mp_opt->data_ack;
+ mpext->use_ack = 1;
+ mpext->ack64 = mp_opt->ack64;
+ }
+
+ mpext->data_fin = mp_opt->data_fin;
+}
+
+void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
+{
+ if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
+ OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
+ u8 len;
+
+ if (OPTION_MPTCP_MPC_SYN & opts->suboptions)
+ len = TCPOLEN_MPTCP_MPC_SYN;
+ else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions)
+ len = TCPOLEN_MPTCP_MPC_SYNACK;
+ else if (opts->ext_copy.data_len)
+ len = TCPOLEN_MPTCP_MPC_ACK_DATA;
+ else
+ len = TCPOLEN_MPTCP_MPC_ACK;
+
+ *ptr++ = htonl((TCPOPT_MPTCP << 24) | (len << 16) |
+ (MPTCPOPT_MP_CAPABLE << 12) |
+ (MPTCP_SUPPORTED_VERSION << 8) |
+ MPTCP_CAP_HMAC_SHA256);
+
+ if (!((OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) &
+ opts->suboptions))
+ goto mp_capable_done;
+
+ put_unaligned_be64(opts->sndr_key, ptr);
+ ptr += 2;
+ if (!((OPTION_MPTCP_MPC_ACK) & opts->suboptions))
+ goto mp_capable_done;
+
+ put_unaligned_be64(opts->rcvr_key, ptr);
+ ptr += 2;
+ if (!opts->ext_copy.data_len)
+ goto mp_capable_done;
+
+ put_unaligned_be32(opts->ext_copy.data_len << 16 |
+ TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+ ptr += 1;
+ }
+
+mp_capable_done:
+ if (opts->ext_copy.use_ack || opts->ext_copy.use_map) {
+ struct mptcp_ext *mpext = &opts->ext_copy;
+ u8 len = TCPOLEN_MPTCP_DSS_BASE;
+ u8 flags = 0;
+
+ if (mpext->use_ack) {
+ len += TCPOLEN_MPTCP_DSS_ACK64;
+ flags = MPTCP_DSS_HAS_ACK | MPTCP_DSS_ACK64;
+ }
+
+ if (mpext->use_map) {
+ len += TCPOLEN_MPTCP_DSS_MAP64;
+
+ /* Use only 64-bit mapping flags for now, add
+ * support for optional 32-bit mappings later.
+ */
+ flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64;
+ if (mpext->data_fin)
+ flags |= MPTCP_DSS_DATA_FIN;
+ }
+
+ *ptr++ = htonl((TCPOPT_MPTCP << 24) |
+ (len << 16) |
+ (MPTCPOPT_DSS << 12) |
+ (flags));
+
+ if (mpext->use_ack) {
+ put_unaligned_be64(mpext->data_ack, ptr);
+ ptr += 2;
+ }
+
+ if (mpext->use_map) {
+ put_unaligned_be64(mpext->data_seq, ptr);
+ ptr += 2;
+ put_unaligned_be32(mpext->subflow_seq, ptr);
+ ptr += 1;
+ put_unaligned_be32(mpext->data_len << 16 |
+ TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+ }
+ }
+}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
new file mode 100644
index 0000000..39fdca7
--- /dev/null
+++ b/net/mptcp/protocol.c
@@ -0,0 +1,1276 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/sched/signal.h>
+#include <linux/atomic.h>
+#include <net/sock.h>
+#include <net/inet_common.h>
+#include <net/inet_hashtables.h>
+#include <net/protocol.h>
+#include <net/tcp.h>
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+#include <net/transp_v6.h>
+#endif
+#include <net/mptcp.h>
+#include "protocol.h"
+
+#define MPTCP_SAME_STATE TCP_MAX_STATES
+
+static void __mptcp_close(struct sock *sk, long timeout);
+
+static const struct proto_ops *tcp_proto_ops(struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6)
+ return &inet6_stream_ops;
+#endif
+ return &inet_stream_ops;
+}
+
+/* MP_CAPABLE handshake failed, convert msk to plain tcp, replacing
+ * socket->sk and stream ops and destroying msk
+ * return the msk socket, as we can't access msk anymore after this function
+ * completes
+ * Called with msk lock held, releases such lock before returning
+ */
+static struct socket *__mptcp_fallback_to_tcp(struct mptcp_sock *msk,
+ struct sock *ssk)
+{
+ struct mptcp_subflow_context *subflow;
+ struct socket *sock;
+ struct sock *sk;
+
+ sk = (struct sock *)msk;
+ sock = sk->sk_socket;
+ subflow = mptcp_subflow_ctx(ssk);
+
+ /* detach the msk socket */
+ list_del_init(&subflow->node);
+ sock_orphan(sk);
+ sock->sk = NULL;
+
+ /* socket is now TCP */
+ lock_sock(ssk);
+ sock_graft(ssk, sock);
+ if (subflow->conn) {
+ /* We can't release the ULP data on a live socket,
+ * restore the tcp callback
+ */
+ mptcp_subflow_tcp_fallback(ssk, subflow);
+ sock_put(subflow->conn);
+ subflow->conn = NULL;
+ }
+ release_sock(ssk);
+ sock->ops = tcp_proto_ops(ssk);
+
+ /* destroy the left-over msk sock */
+ __mptcp_close(sk, 0);
+ return sock;
+}
+
+/* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not
+ * completed yet or has failed, return the subflow socket.
+ * Otherwise return NULL.
+ */
+static struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk)
+{
+ if (!msk->subflow || READ_ONCE(msk->can_ack))
+ return NULL;
+
+ return msk->subflow;
+}
+
+static bool __mptcp_needs_tcp_fallback(const struct mptcp_sock *msk)
+{
+ return msk->first && !sk_is_mptcp(msk->first);
+}
+
+/* if the mp_capable handshake has failed, it fallbacks msk to plain TCP,
+ * releases the socket lock and returns a reference to the now TCP socket.
+ * Otherwise returns NULL
+ */
+static struct socket *__mptcp_tcp_fallback(struct mptcp_sock *msk)
+{
+ sock_owned_by_me((const struct sock *)msk);
+
+ if (likely(!__mptcp_needs_tcp_fallback(msk)))
+ return NULL;
+
+ if (msk->subflow) {
+ /* the first subflow is an active connection, discart the
+ * paired socket
+ */
+ msk->subflow->sk = NULL;
+ sock_release(msk->subflow);
+ msk->subflow = NULL;
+ }
+
+ return __mptcp_fallback_to_tcp(msk, msk->first);
+}
+
+static bool __mptcp_can_create_subflow(const struct mptcp_sock *msk)
+{
+ return !msk->first;
+}
+
+static struct socket *__mptcp_socket_create(struct mptcp_sock *msk, int state)
+{
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = (struct sock *)msk;
+ struct socket *ssock;
+ int err;
+
+ ssock = __mptcp_nmpc_socket(msk);
+ if (ssock)
+ goto set_state;
+
+ if (!__mptcp_can_create_subflow(msk))
+ return ERR_PTR(-EINVAL);
+
+ err = mptcp_subflow_create_socket(sk, &ssock);
+ if (err)
+ return ERR_PTR(err);
+
+ msk->first = ssock->sk;
+ msk->subflow = ssock;
+ subflow = mptcp_subflow_ctx(ssock->sk);
+ list_add(&subflow->node, &msk->conn_list);
+ subflow->request_mptcp = 1;
+
+set_state:
+ if (state != MPTCP_SAME_STATE)
+ inet_sk_state_store(sk, state);
+ return ssock;
+}
+
+static struct sock *mptcp_subflow_get(const struct mptcp_sock *msk)
+{
+ struct mptcp_subflow_context *subflow;
+
+ sock_owned_by_me((const struct sock *)msk);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ return mptcp_subflow_tcp_sock(subflow);
+ }
+
+ return NULL;
+}
+
+static bool mptcp_ext_cache_refill(struct mptcp_sock *msk)
+{
+ if (!msk->cached_ext)
+ msk->cached_ext = __skb_ext_alloc();
+
+ return !!msk->cached_ext;
+}
+
+static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
+{
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = (struct sock *)msk;
+
+ sock_owned_by_me(sk);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ if (subflow->data_avail)
+ return mptcp_subflow_tcp_sock(subflow);
+ }
+
+ return NULL;
+}
+
+static inline bool mptcp_skb_can_collapse_to(const struct mptcp_sock *msk,
+ const struct sk_buff *skb,
+ const struct mptcp_ext *mpext)
+{
+ if (!tcp_skb_can_collapse_to(skb))
+ return false;
+
+ /* can collapse only if MPTCP level sequence is in order */
+ return mpext && mpext->data_seq + mpext->data_len == msk->write_seq;
+}
+
+static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
+ struct msghdr *msg, long *timeo, int *pmss_now,
+ int *ps_goal)
+{
+ int mss_now, avail_size, size_goal, ret;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct mptcp_ext *mpext = NULL;
+ struct sk_buff *skb, *tail;
+ bool can_collapse = false;
+ struct page_frag *pfrag;
+ size_t psize;
+
+ /* use the mptcp page cache so that we can easily move the data
+ * from one substream to another, but do per subflow memory accounting
+ */
+ pfrag = sk_page_frag(sk);
+ while (!sk_page_frag_refill(ssk, pfrag) ||
+ !mptcp_ext_cache_refill(msk)) {
+ ret = sk_stream_wait_memory(ssk, timeo);
+ if (ret)
+ return ret;
+ if (unlikely(__mptcp_needs_tcp_fallback(msk)))
+ return 0;
+ }
+
+ /* compute copy limit */
+ mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
+ *pmss_now = mss_now;
+ *ps_goal = size_goal;
+ avail_size = size_goal;
+ skb = tcp_write_queue_tail(ssk);
+ if (skb) {
+ mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
+
+ /* Limit the write to the size available in the
+ * current skb, if any, so that we create at most a new skb.
+ * Explicitly tells TCP internals to avoid collapsing on later
+ * queue management operation, to avoid breaking the ext <->
+ * SSN association set here
+ */
+ can_collapse = (size_goal - skb->len > 0) &&
+ mptcp_skb_can_collapse_to(msk, skb, mpext);
+ if (!can_collapse)
+ TCP_SKB_CB(skb)->eor = 1;
+ else
+ avail_size = size_goal - skb->len;
+ }
+ psize = min_t(size_t, pfrag->size - pfrag->offset, avail_size);
+
+ /* Copy to page */
+ pr_debug("left=%zu", msg_data_left(msg));
+ psize = copy_page_from_iter(pfrag->page, pfrag->offset,
+ min_t(size_t, msg_data_left(msg), psize),
+ &msg->msg_iter);
+ pr_debug("left=%zu", msg_data_left(msg));
+ if (!psize)
+ return -EINVAL;
+
+ /* tell the TCP stack to delay the push so that we can safely
+ * access the skb after the sendpages call
+ */
+ ret = do_tcp_sendpages(ssk, pfrag->page, pfrag->offset, psize,
+ msg->msg_flags | MSG_SENDPAGE_NOTLAST);
+ if (ret <= 0)
+ return ret;
+ if (unlikely(ret < psize))
+ iov_iter_revert(&msg->msg_iter, psize - ret);
+
+ /* if the tail skb extension is still the cached one, collapsing
+ * really happened. Note: we can't check for 'same skb' as the sk_buff
+ * hdr on tail can be transmitted, freed and re-allocated by the
+ * do_tcp_sendpages() call
+ */
+ tail = tcp_write_queue_tail(ssk);
+ if (mpext && tail && mpext == skb_ext_find(tail, SKB_EXT_MPTCP)) {
+ WARN_ON_ONCE(!can_collapse);
+ mpext->data_len += ret;
+ goto out;
+ }
+
+ skb = tcp_write_queue_tail(ssk);
+ mpext = __skb_ext_set(skb, SKB_EXT_MPTCP, msk->cached_ext);
+ msk->cached_ext = NULL;
+
+ memset(mpext, 0, sizeof(*mpext));
+ mpext->data_seq = msk->write_seq;
+ mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq;
+ mpext->data_len = ret;
+ mpext->use_map = 1;
+ mpext->dsn64 = 1;
+
+ pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d",
+ mpext->data_seq, mpext->subflow_seq, mpext->data_len,
+ mpext->dsn64);
+
+out:
+ pfrag->offset += ret;
+ msk->write_seq += ret;
+ mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
+
+ return ret;
+}
+
+static void ssk_check_wmem(struct mptcp_sock *msk, struct sock *ssk)
+{
+ struct socket *sock;
+
+ if (likely(sk_stream_is_writeable(ssk)))
+ return;
+
+ sock = READ_ONCE(ssk->sk_socket);
+
+ if (sock) {
+ clear_bit(MPTCP_SEND_SPACE, &msk->flags);
+ smp_mb__after_atomic();
+ /* set NOSPACE only after clearing SEND_SPACE flag */
+ set_bit(SOCK_NOSPACE, &sock->flags);
+ }
+}
+
+static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
+{
+ int mss_now = 0, size_goal = 0, ret = 0;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct socket *ssock;
+ size_t copied = 0;
+ struct sock *ssk;
+ long timeo;
+
+ if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
+ return -EOPNOTSUPP;
+
+ lock_sock(sk);
+ ssock = __mptcp_tcp_fallback(msk);
+ if (unlikely(ssock)) {
+fallback:
+ pr_debug("fallback passthrough");
+ ret = sock_sendmsg(ssock, msg);
+ return ret >= 0 ? ret + copied : (copied ? copied : ret);
+ }
+
+ timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+
+ ssk = mptcp_subflow_get(msk);
+ if (!ssk) {
+ release_sock(sk);
+ return -ENOTCONN;
+ }
+
+ pr_debug("conn_list->subflow=%p", ssk);
+
+ lock_sock(ssk);
+ while (msg_data_left(msg)) {
+ ret = mptcp_sendmsg_frag(sk, ssk, msg, &timeo, &mss_now,
+ &size_goal);
+ if (ret < 0)
+ break;
+ if (ret == 0 && unlikely(__mptcp_needs_tcp_fallback(msk))) {
+ release_sock(ssk);
+ ssock = __mptcp_tcp_fallback(msk);
+ goto fallback;
+ }
+
+ copied += ret;
+ }
+
+ if (copied) {
+ ret = copied;
+ tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle,
+ size_goal);
+ }
+
+ ssk_check_wmem(msk, ssk);
+ release_sock(ssk);
+ release_sock(sk);
+ return ret;
+}
+
+int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb,
+ unsigned int offset, size_t len)
+{
+ struct mptcp_read_arg *arg = desc->arg.data;
+ size_t copy_len;
+
+ copy_len = min(desc->count, len);
+
+ if (likely(arg->msg)) {
+ int err;
+
+ err = skb_copy_datagram_msg(skb, offset, arg->msg, copy_len);
+ if (err) {
+ pr_debug("error path");
+ desc->error = err;
+ return err;
+ }
+ } else {
+ pr_debug("Flushing skb payload");
+ }
+
+ desc->count -= copy_len;
+
+ pr_debug("consumed %zu bytes, %zu left", copy_len, desc->count);
+ return copy_len;
+}
+
+static void mptcp_wait_data(struct sock *sk, long *timeo)
+{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+
+ sk_wait_event(sk, timeo,
+ test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait);
+
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
+}
+
+static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+ int nonblock, int flags, int *addr_len)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct mptcp_subflow_context *subflow;
+ bool more_data_avail = false;
+ struct mptcp_read_arg arg;
+ read_descriptor_t desc;
+ bool wait_data = false;
+ struct socket *ssock;
+ struct tcp_sock *tp;
+ bool done = false;
+ struct sock *ssk;
+ int copied = 0;
+ int target;
+ long timeo;
+
+ if (msg->msg_flags & ~(MSG_WAITALL | MSG_DONTWAIT))
+ return -EOPNOTSUPP;
+
+ lock_sock(sk);
+ ssock = __mptcp_tcp_fallback(msk);
+ if (unlikely(ssock)) {
+fallback:
+ pr_debug("fallback-read subflow=%p",
+ mptcp_subflow_ctx(ssock->sk));
+ copied = sock_recvmsg(ssock, msg, flags);
+ return copied;
+ }
+
+ arg.msg = msg;
+ desc.arg.data = &arg;
+ desc.error = 0;
+
+ timeo = sock_rcvtimeo(sk, nonblock);
+
+ len = min_t(size_t, len, INT_MAX);
+ target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
+
+ while (!done) {
+ u32 map_remaining;
+ int bytes_read;
+
+ ssk = mptcp_subflow_recv_lookup(msk);
+ pr_debug("msk=%p ssk=%p", msk, ssk);
+ if (!ssk)
+ goto wait_for_data;
+
+ subflow = mptcp_subflow_ctx(ssk);
+ tp = tcp_sk(ssk);
+
+ lock_sock(ssk);
+ do {
+ /* try to read as much data as available */
+ map_remaining = subflow->map_data_len -
+ mptcp_subflow_get_map_offset(subflow);
+ desc.count = min_t(size_t, len - copied, map_remaining);
+ pr_debug("reading %zu bytes, copied %d", desc.count,
+ copied);
+ bytes_read = tcp_read_sock(ssk, &desc,
+ mptcp_read_actor);
+ if (bytes_read < 0) {
+ if (!copied)
+ copied = bytes_read;
+ done = true;
+ goto next;
+ }
+
+ pr_debug("msk ack_seq=%llx -> %llx", msk->ack_seq,
+ msk->ack_seq + bytes_read);
+ msk->ack_seq += bytes_read;
+ copied += bytes_read;
+ if (copied >= len) {
+ done = true;
+ goto next;
+ }
+ if (tp->urg_data && tp->urg_seq == tp->copied_seq) {
+ pr_err("Urgent data present, cannot proceed");
+ done = true;
+ goto next;
+ }
+next:
+ more_data_avail = mptcp_subflow_data_available(ssk);
+ } while (more_data_avail && !done);
+ release_sock(ssk);
+ continue;
+
+wait_for_data:
+ more_data_avail = false;
+
+ /* only the master socket status is relevant here. The exit
+ * conditions mirror closely tcp_recvmsg()
+ */
+ if (copied >= target)
+ break;
+
+ if (copied) {
+ if (sk->sk_err ||
+ sk->sk_state == TCP_CLOSE ||
+ (sk->sk_shutdown & RCV_SHUTDOWN) ||
+ !timeo ||
+ signal_pending(current))
+ break;
+ } else {
+ if (sk->sk_err) {
+ copied = sock_error(sk);
+ break;
+ }
+
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ break;
+
+ if (sk->sk_state == TCP_CLOSE) {
+ copied = -ENOTCONN;
+ break;
+ }
+
+ if (!timeo) {
+ copied = -EAGAIN;
+ break;
+ }
+
+ if (signal_pending(current)) {
+ copied = sock_intr_errno(timeo);
+ break;
+ }
+ }
+
+ pr_debug("block timeout %ld", timeo);
+ wait_data = true;
+ mptcp_wait_data(sk, &timeo);
+ if (unlikely(__mptcp_tcp_fallback(msk)))
+ goto fallback;
+ }
+
+ if (more_data_avail) {
+ if (!test_bit(MPTCP_DATA_READY, &msk->flags))
+ set_bit(MPTCP_DATA_READY, &msk->flags);
+ } else if (!wait_data) {
+ clear_bit(MPTCP_DATA_READY, &msk->flags);
+
+ /* .. race-breaker: ssk might get new data after last
+ * data_available() returns false.
+ */
+ ssk = mptcp_subflow_recv_lookup(msk);
+ if (unlikely(ssk))
+ set_bit(MPTCP_DATA_READY, &msk->flags);
+ }
+
+ release_sock(sk);
+ return copied;
+}
+
+/* subflow sockets can be either outgoing (connect) or incoming
+ * (accept).
+ *
+ * Outgoing subflows use in-kernel sockets.
+ * Incoming subflows do not have their own 'struct socket' allocated,
+ * so we need to use tcp_close() after detaching them from the mptcp
+ * parent socket.
+ */
+static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
+ struct mptcp_subflow_context *subflow,
+ long timeout)
+{
+ struct socket *sock = READ_ONCE(ssk->sk_socket);
+
+ list_del(&subflow->node);
+
+ if (sock && sock != sk->sk_socket) {
+ /* outgoing subflow */
+ sock_release(sock);
+ } else {
+ /* incoming subflow */
+ tcp_close(ssk, timeout);
+ }
+}
+
+static int __mptcp_init_sock(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ INIT_LIST_HEAD(&msk->conn_list);
+ __set_bit(MPTCP_SEND_SPACE, &msk->flags);
+
+ msk->first = NULL;
+
+ return 0;
+}
+
+static int mptcp_init_sock(struct sock *sk)
+{
+ if (!mptcp_is_enabled(sock_net(sk)))
+ return -ENOPROTOOPT;
+
+ return __mptcp_init_sock(sk);
+}
+
+static void mptcp_subflow_shutdown(struct sock *ssk, int how)
+{
+ lock_sock(ssk);
+
+ switch (ssk->sk_state) {
+ case TCP_LISTEN:
+ if (!(how & RCV_SHUTDOWN))
+ break;
+ /* fall through */
+ case TCP_SYN_SENT:
+ tcp_disconnect(ssk, O_NONBLOCK);
+ break;
+ default:
+ ssk->sk_shutdown |= how;
+ tcp_shutdown(ssk, how);
+ break;
+ }
+
+ /* Wake up anyone sleeping in poll. */
+ ssk->sk_state_change(ssk);
+ release_sock(ssk);
+}
+
+/* Called with msk lock held, releases such lock before returning */
+static void __mptcp_close(struct sock *sk, long timeout)
+{
+ struct mptcp_subflow_context *subflow, *tmp;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ mptcp_token_destroy(msk->token);
+ inet_sk_state_store(sk, TCP_CLOSE);
+
+ list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ __mptcp_close_ssk(sk, ssk, subflow, timeout);
+ }
+
+ if (msk->cached_ext)
+ __skb_ext_put(msk->cached_ext);
+ release_sock(sk);
+ sk_common_release(sk);
+}
+
+static void mptcp_close(struct sock *sk, long timeout)
+{
+ lock_sock(sk);
+ __mptcp_close(sk, timeout);
+}
+
+static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
+{
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ const struct ipv6_pinfo *ssk6 = inet6_sk(ssk);
+ struct ipv6_pinfo *msk6 = inet6_sk(msk);
+
+ msk->sk_v6_daddr = ssk->sk_v6_daddr;
+ msk->sk_v6_rcv_saddr = ssk->sk_v6_rcv_saddr;
+
+ if (msk6 && ssk6) {
+ msk6->saddr = ssk6->saddr;
+ msk6->flow_label = ssk6->flow_label;
+ }
+#endif
+
+ inet_sk(msk)->inet_num = inet_sk(ssk)->inet_num;
+ inet_sk(msk)->inet_dport = inet_sk(ssk)->inet_dport;
+ inet_sk(msk)->inet_sport = inet_sk(ssk)->inet_sport;
+ inet_sk(msk)->inet_daddr = inet_sk(ssk)->inet_daddr;
+ inet_sk(msk)->inet_saddr = inet_sk(ssk)->inet_saddr;
+ inet_sk(msk)->inet_rcv_saddr = inet_sk(ssk)->inet_rcv_saddr;
+}
+
+static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
+ bool kern)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct socket *listener;
+ struct sock *newsk;
+
+ listener = __mptcp_nmpc_socket(msk);
+ if (WARN_ON_ONCE(!listener)) {
+ *err = -EINVAL;
+ return NULL;
+ }
+
+ pr_debug("msk=%p, listener=%p", msk, mptcp_subflow_ctx(listener->sk));
+ newsk = inet_csk_accept(listener->sk, flags, err, kern);
+ if (!newsk)
+ return NULL;
+
+ pr_debug("msk=%p, subflow is mptcp=%d", msk, sk_is_mptcp(newsk));
+
+ if (sk_is_mptcp(newsk)) {
+ struct mptcp_subflow_context *subflow;
+ struct sock *new_mptcp_sock;
+ struct sock *ssk = newsk;
+ u64 ack_seq;
+
+ subflow = mptcp_subflow_ctx(newsk);
+ lock_sock(sk);
+
+ local_bh_disable();
+ new_mptcp_sock = sk_clone_lock(sk, GFP_ATOMIC);
+ if (!new_mptcp_sock) {
+ *err = -ENOBUFS;
+ local_bh_enable();
+ release_sock(sk);
+ mptcp_subflow_shutdown(newsk, SHUT_RDWR + 1);
+ tcp_close(newsk, 0);
+ return NULL;
+ }
+
+ __mptcp_init_sock(new_mptcp_sock);
+
+ msk = mptcp_sk(new_mptcp_sock);
+ msk->local_key = subflow->local_key;
+ msk->token = subflow->token;
+ msk->subflow = NULL;
+ msk->first = newsk;
+
+ mptcp_token_update_accept(newsk, new_mptcp_sock);
+
+ msk->write_seq = subflow->idsn + 1;
+ if (subflow->can_ack) {
+ msk->can_ack = true;
+ msk->remote_key = subflow->remote_key;
+ mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
+ ack_seq++;
+ msk->ack_seq = ack_seq;
+ }
+ newsk = new_mptcp_sock;
+ mptcp_copy_inaddrs(newsk, ssk);
+ list_add(&subflow->node, &msk->conn_list);
+
+ /* will be fully established at mptcp_stream_accept()
+ * completion.
+ */
+ inet_sk_state_store(new_mptcp_sock, TCP_SYN_RECV);
+ bh_unlock_sock(new_mptcp_sock);
+ local_bh_enable();
+ release_sock(sk);
+
+ /* the subflow can already receive packet, avoid racing with
+ * the receive path and process the pending ones
+ */
+ lock_sock(ssk);
+ subflow->rel_write_seq = 1;
+ subflow->tcp_sock = ssk;
+ subflow->conn = new_mptcp_sock;
+ if (unlikely(!skb_queue_empty(&ssk->sk_receive_queue)))
+ mptcp_subflow_data_available(ssk);
+ release_sock(ssk);
+ }
+
+ return newsk;
+}
+
+static void mptcp_destroy(struct sock *sk)
+{
+}
+
+static int mptcp_setsockopt(struct sock *sk, int level, int optname,
+ char __user *uoptval, unsigned int optlen)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ char __kernel *optval;
+ int ret = -EOPNOTSUPP;
+ struct socket *ssock;
+
+ /* will be treated as __user in tcp_setsockopt */
+ optval = (char __kernel __force *)uoptval;
+
+ pr_debug("msk=%p", msk);
+
+ /* @@ the meaning of setsockopt() when the socket is connected and
+ * there are multiple subflows is not defined.
+ */
+ lock_sock(sk);
+ ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
+ if (!IS_ERR(ssock)) {
+ pr_debug("subflow=%p", ssock->sk);
+ ret = kernel_setsockopt(ssock, level, optname, optval, optlen);
+ }
+ release_sock(sk);
+
+ return ret;
+}
+
+static int mptcp_getsockopt(struct sock *sk, int level, int optname,
+ char __user *uoptval, int __user *uoption)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ char __kernel *optval;
+ int ret = -EOPNOTSUPP;
+ int __kernel *option;
+ struct socket *ssock;
+
+ /* will be treated as __user in tcp_getsockopt */
+ optval = (char __kernel __force *)uoptval;
+ option = (int __kernel __force *)uoption;
+
+ pr_debug("msk=%p", msk);
+
+ /* @@ the meaning of getsockopt() when the socket is connected and
+ * there are multiple subflows is not defined.
+ */
+ lock_sock(sk);
+ ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
+ if (!IS_ERR(ssock)) {
+ pr_debug("subflow=%p", ssock->sk);
+ ret = kernel_getsockopt(ssock, level, optname, optval, option);
+ }
+ release_sock(sk);
+
+ return ret;
+}
+
+static int mptcp_get_port(struct sock *sk, unsigned short snum)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct socket *ssock;
+
+ ssock = __mptcp_nmpc_socket(msk);
+ pr_debug("msk=%p, subflow=%p", msk, ssock);
+ if (WARN_ON_ONCE(!ssock))
+ return -EINVAL;
+
+ return inet_csk_get_port(ssock->sk, snum);
+}
+
+void mptcp_finish_connect(struct sock *ssk)
+{
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk;
+ struct sock *sk;
+ u64 ack_seq;
+
+ subflow = mptcp_subflow_ctx(ssk);
+
+ if (!subflow->mp_capable)
+ return;
+
+ sk = subflow->conn;
+ msk = mptcp_sk(sk);
+
+ pr_debug("msk=%p, token=%u", sk, subflow->token);
+
+ mptcp_crypto_key_sha(subflow->remote_key, NULL, &ack_seq);
+ ack_seq++;
+ subflow->map_seq = ack_seq;
+ subflow->map_subflow_seq = 1;
+ subflow->rel_write_seq = 1;
+
+ /* the socket is not connected yet, no msk/subflow ops can access/race
+ * accessing the field below
+ */
+ WRITE_ONCE(msk->remote_key, subflow->remote_key);
+ WRITE_ONCE(msk->local_key, subflow->local_key);
+ WRITE_ONCE(msk->token, subflow->token);
+ WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
+ WRITE_ONCE(msk->ack_seq, ack_seq);
+ WRITE_ONCE(msk->can_ack, 1);
+}
+
+static void mptcp_sock_graft(struct sock *sk, struct socket *parent)
+{
+ write_lock_bh(&sk->sk_callback_lock);
+ rcu_assign_pointer(sk->sk_wq, &parent->wq);
+ sk_set_socket(sk, parent);
+ sk->sk_uid = SOCK_INODE(parent)->i_uid;
+ write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static bool mptcp_memory_free(const struct sock *sk, int wake)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ return wake ? test_bit(MPTCP_SEND_SPACE, &msk->flags) : true;
+}
+
+static struct proto mptcp_prot = {
+ .name = "MPTCP",
+ .owner = THIS_MODULE,
+ .init = mptcp_init_sock,
+ .close = mptcp_close,
+ .accept = mptcp_accept,
+ .setsockopt = mptcp_setsockopt,
+ .getsockopt = mptcp_getsockopt,
+ .shutdown = tcp_shutdown,
+ .destroy = mptcp_destroy,
+ .sendmsg = mptcp_sendmsg,
+ .recvmsg = mptcp_recvmsg,
+ .hash = inet_hash,
+ .unhash = inet_unhash,
+ .get_port = mptcp_get_port,
+ .stream_memory_free = mptcp_memory_free,
+ .obj_size = sizeof(struct mptcp_sock),
+ .no_autobind = true,
+};
+
+static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+{
+ struct mptcp_sock *msk = mptcp_sk(sock->sk);
+ struct socket *ssock;
+ int err;
+
+ lock_sock(sock->sk);
+ ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
+ if (IS_ERR(ssock)) {
+ err = PTR_ERR(ssock);
+ goto unlock;
+ }
+
+ err = ssock->ops->bind(ssock, uaddr, addr_len);
+ if (!err)
+ mptcp_copy_inaddrs(sock->sk, ssock->sk);
+
+unlock:
+ release_sock(sock->sk);
+ return err;
+}
+
+static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len, int flags)
+{
+ struct mptcp_sock *msk = mptcp_sk(sock->sk);
+ struct socket *ssock;
+ int err;
+
+ lock_sock(sock->sk);
+ ssock = __mptcp_socket_create(msk, TCP_SYN_SENT);
+ if (IS_ERR(ssock)) {
+ err = PTR_ERR(ssock);
+ goto unlock;
+ }
+
+#ifdef CONFIG_TCP_MD5SIG
+ /* no MPTCP if MD5SIG is enabled on this socket or we may run out of
+ * TCP option space.
+ */
+ if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info))
+ mptcp_subflow_ctx(ssock->sk)->request_mptcp = 0;
+#endif
+
+ err = ssock->ops->connect(ssock, uaddr, addr_len, flags);
+ inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk));
+ mptcp_copy_inaddrs(sock->sk, ssock->sk);
+
+unlock:
+ release_sock(sock->sk);
+ return err;
+}
+
+static int mptcp_v4_getname(struct socket *sock, struct sockaddr *uaddr,
+ int peer)
+{
+ if (sock->sk->sk_prot == &tcp_prot) {
+ /* we are being invoked from __sys_accept4, after
+ * mptcp_accept() has just accepted a non-mp-capable
+ * flow: sk is a tcp_sk, not an mptcp one.
+ *
+ * Hand the socket over to tcp so all further socket ops
+ * bypass mptcp.
+ */
+ sock->ops = &inet_stream_ops;
+ }
+
+ return inet_getname(sock, uaddr, peer);
+}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+static int mptcp_v6_getname(struct socket *sock, struct sockaddr *uaddr,
+ int peer)
+{
+ if (sock->sk->sk_prot == &tcpv6_prot) {
+ /* we are being invoked from __sys_accept4 after
+ * mptcp_accept() has accepted a non-mp-capable
+ * subflow: sk is a tcp_sk, not mptcp.
+ *
+ * Hand the socket over to tcp so all further
+ * socket ops bypass mptcp.
+ */
+ sock->ops = &inet6_stream_ops;
+ }
+
+ return inet6_getname(sock, uaddr, peer);
+}
+#endif
+
+static int mptcp_listen(struct socket *sock, int backlog)
+{
+ struct mptcp_sock *msk = mptcp_sk(sock->sk);
+ struct socket *ssock;
+ int err;
+
+ pr_debug("msk=%p", msk);
+
+ lock_sock(sock->sk);
+ ssock = __mptcp_socket_create(msk, TCP_LISTEN);
+ if (IS_ERR(ssock)) {
+ err = PTR_ERR(ssock);
+ goto unlock;
+ }
+
+ err = ssock->ops->listen(ssock, backlog);
+ inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk));
+ if (!err)
+ mptcp_copy_inaddrs(sock->sk, ssock->sk);
+
+unlock:
+ release_sock(sock->sk);
+ return err;
+}
+
+static bool is_tcp_proto(const struct proto *p)
+{
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ return p == &tcp_prot || p == &tcpv6_prot;
+#else
+ return p == &tcp_prot;
+#endif
+}
+
+static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
+ int flags, bool kern)
+{
+ struct mptcp_sock *msk = mptcp_sk(sock->sk);
+ struct socket *ssock;
+ int err;
+
+ pr_debug("msk=%p", msk);
+
+ lock_sock(sock->sk);
+ if (sock->sk->sk_state != TCP_LISTEN)
+ goto unlock_fail;
+
+ ssock = __mptcp_nmpc_socket(msk);
+ if (!ssock)
+ goto unlock_fail;
+
+ sock_hold(ssock->sk);
+ release_sock(sock->sk);
+
+ err = ssock->ops->accept(sock, newsock, flags, kern);
+ if (err == 0 && !is_tcp_proto(newsock->sk->sk_prot)) {
+ struct mptcp_sock *msk = mptcp_sk(newsock->sk);
+ struct mptcp_subflow_context *subflow;
+
+ /* set ssk->sk_socket of accept()ed flows to mptcp socket.
+ * This is needed so NOSPACE flag can be set from tcp stack.
+ */
+ list_for_each_entry(subflow, &msk->conn_list, node) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ if (!ssk->sk_socket)
+ mptcp_sock_graft(ssk, newsock);
+ }
+
+ inet_sk_state_store(newsock->sk, TCP_ESTABLISHED);
+ }
+
+ sock_put(ssock->sk);
+ return err;
+
+unlock_fail:
+ release_sock(sock->sk);
+ return -EINVAL;
+}
+
+static __poll_t mptcp_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait)
+{
+ struct sock *sk = sock->sk;
+ struct mptcp_sock *msk;
+ struct socket *ssock;
+ __poll_t mask = 0;
+
+ msk = mptcp_sk(sk);
+ lock_sock(sk);
+ ssock = __mptcp_nmpc_socket(msk);
+ if (ssock) {
+ mask = ssock->ops->poll(file, ssock, wait);
+ release_sock(sk);
+ return mask;
+ }
+
+ release_sock(sk);
+ sock_poll_wait(file, sock, wait);
+ lock_sock(sk);
+ ssock = __mptcp_tcp_fallback(msk);
+ if (unlikely(ssock))
+ return ssock->ops->poll(file, ssock, NULL);
+
+ if (test_bit(MPTCP_DATA_READY, &msk->flags))
+ mask = EPOLLIN | EPOLLRDNORM;
+ if (sk_stream_is_writeable(sk) &&
+ test_bit(MPTCP_SEND_SPACE, &msk->flags))
+ mask |= EPOLLOUT | EPOLLWRNORM;
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
+
+ release_sock(sk);
+
+ return mask;
+}
+
+static int mptcp_shutdown(struct socket *sock, int how)
+{
+ struct mptcp_sock *msk = mptcp_sk(sock->sk);
+ struct mptcp_subflow_context *subflow;
+ int ret = 0;
+
+ pr_debug("sk=%p, how=%d", msk, how);
+
+ lock_sock(sock->sk);
+
+ if (how == SHUT_WR || how == SHUT_RDWR)
+ inet_sk_state_store(sock->sk, TCP_FIN_WAIT1);
+
+ how++;
+
+ if ((how & ~SHUTDOWN_MASK) || !how) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
+ if (sock->state == SS_CONNECTING) {
+ if ((1 << sock->sk->sk_state) &
+ (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
+ sock->state = SS_DISCONNECTING;
+ else
+ sock->state = SS_CONNECTED;
+ }
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
+
+ mptcp_subflow_shutdown(tcp_sk, how);
+ }
+
+out_unlock:
+ release_sock(sock->sk);
+
+ return ret;
+}
+
+static const struct proto_ops mptcp_stream_ops = {
+ .family = PF_INET,
+ .owner = THIS_MODULE,
+ .release = inet_release,
+ .bind = mptcp_bind,
+ .connect = mptcp_stream_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = mptcp_stream_accept,
+ .getname = mptcp_v4_getname,
+ .poll = mptcp_poll,
+ .ioctl = inet_ioctl,
+ .gettstamp = sock_gettstamp,
+ .listen = mptcp_listen,
+ .shutdown = mptcp_shutdown,
+ .setsockopt = sock_common_setsockopt,
+ .getsockopt = sock_common_getsockopt,
+ .sendmsg = inet_sendmsg,
+ .recvmsg = inet_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = inet_sendpage,
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_sock_common_setsockopt,
+ .compat_getsockopt = compat_sock_common_getsockopt,
+#endif
+};
+
+static struct inet_protosw mptcp_protosw = {
+ .type = SOCK_STREAM,
+ .protocol = IPPROTO_MPTCP,
+ .prot = &mptcp_prot,
+ .ops = &mptcp_stream_ops,
+ .flags = INET_PROTOSW_ICSK,
+};
+
+void mptcp_proto_init(void)
+{
+ mptcp_prot.h.hashinfo = tcp_prot.h.hashinfo;
+
+ mptcp_subflow_init();
+
+ if (proto_register(&mptcp_prot, 1) != 0)
+ panic("Failed to register MPTCP proto.\n");
+
+ inet_register_protosw(&mptcp_protosw);
+}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+static const struct proto_ops mptcp_v6_stream_ops = {
+ .family = PF_INET6,
+ .owner = THIS_MODULE,
+ .release = inet6_release,
+ .bind = mptcp_bind,
+ .connect = mptcp_stream_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = mptcp_stream_accept,
+ .getname = mptcp_v6_getname,
+ .poll = mptcp_poll,
+ .ioctl = inet6_ioctl,
+ .gettstamp = sock_gettstamp,
+ .listen = mptcp_listen,
+ .shutdown = mptcp_shutdown,
+ .setsockopt = sock_common_setsockopt,
+ .getsockopt = sock_common_getsockopt,
+ .sendmsg = inet6_sendmsg,
+ .recvmsg = inet6_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = inet_sendpage,
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_sock_common_setsockopt,
+ .compat_getsockopt = compat_sock_common_getsockopt,
+#endif
+};
+
+static struct proto mptcp_v6_prot;
+
+static void mptcp_v6_destroy(struct sock *sk)
+{
+ mptcp_destroy(sk);
+ inet6_destroy_sock(sk);
+}
+
+static struct inet_protosw mptcp_v6_protosw = {
+ .type = SOCK_STREAM,
+ .protocol = IPPROTO_MPTCP,
+ .prot = &mptcp_v6_prot,
+ .ops = &mptcp_v6_stream_ops,
+ .flags = INET_PROTOSW_ICSK,
+};
+
+int mptcp_proto_v6_init(void)
+{
+ int err;
+
+ mptcp_v6_prot = mptcp_prot;
+ strcpy(mptcp_v6_prot.name, "MPTCPv6");
+ mptcp_v6_prot.slab = NULL;
+ mptcp_v6_prot.destroy = mptcp_v6_destroy;
+ mptcp_v6_prot.obj_size = sizeof(struct mptcp_sock) +
+ sizeof(struct ipv6_pinfo);
+
+ err = proto_register(&mptcp_v6_prot, 1);
+ if (err)
+ return err;
+
+ err = inet6_register_protosw(&mptcp_v6_protosw);
+ if (err)
+ proto_unregister(&mptcp_v6_prot);
+
+ return err;
+}
+#endif
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
new file mode 100644
index 0000000..8a99a29
--- /dev/null
+++ b/net/mptcp/protocol.h
@@ -0,0 +1,240 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#ifndef __MPTCP_PROTOCOL_H
+#define __MPTCP_PROTOCOL_H
+
+#include <linux/random.h>
+#include <net/tcp.h>
+#include <net/inet_connection_sock.h>
+
+#define MPTCP_SUPPORTED_VERSION 1
+
+/* MPTCP option bits */
+#define OPTION_MPTCP_MPC_SYN BIT(0)
+#define OPTION_MPTCP_MPC_SYNACK BIT(1)
+#define OPTION_MPTCP_MPC_ACK BIT(2)
+
+/* MPTCP option subtypes */
+#define MPTCPOPT_MP_CAPABLE 0
+#define MPTCPOPT_MP_JOIN 1
+#define MPTCPOPT_DSS 2
+#define MPTCPOPT_ADD_ADDR 3
+#define MPTCPOPT_RM_ADDR 4
+#define MPTCPOPT_MP_PRIO 5
+#define MPTCPOPT_MP_FAIL 6
+#define MPTCPOPT_MP_FASTCLOSE 7
+
+/* MPTCP suboption lengths */
+#define TCPOLEN_MPTCP_MPC_SYN 4
+#define TCPOLEN_MPTCP_MPC_SYNACK 12
+#define TCPOLEN_MPTCP_MPC_ACK 20
+#define TCPOLEN_MPTCP_MPC_ACK_DATA 22
+#define TCPOLEN_MPTCP_DSS_BASE 4
+#define TCPOLEN_MPTCP_DSS_ACK32 4
+#define TCPOLEN_MPTCP_DSS_ACK64 8
+#define TCPOLEN_MPTCP_DSS_MAP32 10
+#define TCPOLEN_MPTCP_DSS_MAP64 14
+#define TCPOLEN_MPTCP_DSS_CHECKSUM 2
+
+/* MPTCP MP_CAPABLE flags */
+#define MPTCP_VERSION_MASK (0x0F)
+#define MPTCP_CAP_CHECKSUM_REQD BIT(7)
+#define MPTCP_CAP_EXTENSIBILITY BIT(6)
+#define MPTCP_CAP_HMAC_SHA256 BIT(0)
+#define MPTCP_CAP_FLAG_MASK (0x3F)
+
+/* MPTCP DSS flags */
+#define MPTCP_DSS_DATA_FIN BIT(4)
+#define MPTCP_DSS_DSN64 BIT(3)
+#define MPTCP_DSS_HAS_MAP BIT(2)
+#define MPTCP_DSS_ACK64 BIT(1)
+#define MPTCP_DSS_HAS_ACK BIT(0)
+#define MPTCP_DSS_FLAG_MASK (0x1F)
+
+/* MPTCP socket flags */
+#define MPTCP_DATA_READY BIT(0)
+#define MPTCP_SEND_SPACE BIT(1)
+
+/* MPTCP connection sock */
+struct mptcp_sock {
+ /* inet_connection_sock must be the first member */
+ struct inet_connection_sock sk;
+ u64 local_key;
+ u64 remote_key;
+ u64 write_seq;
+ u64 ack_seq;
+ u32 token;
+ unsigned long flags;
+ bool can_ack;
+ struct list_head conn_list;
+ struct skb_ext *cached_ext; /* for the next sendmsg */
+ struct socket *subflow; /* outgoing connect/listener/!mp_capable */
+ struct sock *first;
+};
+
+#define mptcp_for_each_subflow(__msk, __subflow) \
+ list_for_each_entry(__subflow, &((__msk)->conn_list), node)
+
+static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
+{
+ return (struct mptcp_sock *)sk;
+}
+
+struct mptcp_subflow_request_sock {
+ struct tcp_request_sock sk;
+ u16 mp_capable : 1,
+ mp_join : 1,
+ backup : 1,
+ remote_key_valid : 1;
+ u64 local_key;
+ u64 remote_key;
+ u64 idsn;
+ u32 token;
+ u32 ssn_offset;
+};
+
+static inline struct mptcp_subflow_request_sock *
+mptcp_subflow_rsk(const struct request_sock *rsk)
+{
+ return (struct mptcp_subflow_request_sock *)rsk;
+}
+
+/* MPTCP subflow context */
+struct mptcp_subflow_context {
+ struct list_head node;/* conn_list of subflows */
+ u64 local_key;
+ u64 remote_key;
+ u64 idsn;
+ u64 map_seq;
+ u32 snd_isn;
+ u32 token;
+ u32 rel_write_seq;
+ u32 map_subflow_seq;
+ u32 ssn_offset;
+ u32 map_data_len;
+ u32 request_mptcp : 1, /* send MP_CAPABLE */
+ mp_capable : 1, /* remote is MPTCP capable */
+ fourth_ack : 1, /* send initial DSS */
+ conn_finished : 1,
+ map_valid : 1,
+ mpc_map : 1,
+ data_avail : 1,
+ rx_eof : 1,
+ can_ack : 1; /* only after processing the remote a key */
+
+ struct sock *tcp_sock; /* tcp sk backpointer */
+ struct sock *conn; /* parent mptcp_sock */
+ const struct inet_connection_sock_af_ops *icsk_af_ops;
+ void (*tcp_data_ready)(struct sock *sk);
+ void (*tcp_state_change)(struct sock *sk);
+ void (*tcp_write_space)(struct sock *sk);
+
+ struct rcu_head rcu;
+};
+
+static inline struct mptcp_subflow_context *
+mptcp_subflow_ctx(const struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ /* Use RCU on icsk_ulp_data only for sock diag code */
+ return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
+}
+
+static inline struct sock *
+mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
+{
+ return subflow->tcp_sock;
+}
+
+static inline u64
+mptcp_subflow_get_map_offset(const struct mptcp_subflow_context *subflow)
+{
+ return tcp_sk(mptcp_subflow_tcp_sock(subflow))->copied_seq -
+ subflow->ssn_offset -
+ subflow->map_subflow_seq;
+}
+
+static inline u64
+mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
+{
+ return subflow->map_seq + mptcp_subflow_get_map_offset(subflow);
+}
+
+int mptcp_is_enabled(struct net *net);
+bool mptcp_subflow_data_available(struct sock *sk);
+void mptcp_subflow_init(void);
+int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
+
+static inline void mptcp_subflow_tcp_fallback(struct sock *sk,
+ struct mptcp_subflow_context *ctx)
+{
+ sk->sk_data_ready = ctx->tcp_data_ready;
+ sk->sk_state_change = ctx->tcp_state_change;
+ sk->sk_write_space = ctx->tcp_write_space;
+
+ inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops;
+}
+
+extern const struct inet_connection_sock_af_ops ipv4_specific;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+extern const struct inet_connection_sock_af_ops ipv6_specific;
+#endif
+
+void mptcp_proto_init(void);
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+int mptcp_proto_v6_init(void);
+#endif
+
+struct mptcp_read_arg {
+ struct msghdr *msg;
+};
+
+int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb,
+ unsigned int offset, size_t len);
+
+void mptcp_get_options(const struct sk_buff *skb,
+ struct tcp_options_received *opt_rx);
+
+void mptcp_finish_connect(struct sock *sk);
+
+int mptcp_token_new_request(struct request_sock *req);
+void mptcp_token_destroy_request(u32 token);
+int mptcp_token_new_connect(struct sock *sk);
+int mptcp_token_new_accept(u32 token);
+void mptcp_token_update_accept(struct sock *sk, struct sock *conn);
+void mptcp_token_destroy(u32 token);
+
+void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn);
+static inline void mptcp_crypto_key_gen_sha(u64 *key, u32 *token, u64 *idsn)
+{
+ /* we might consider a faster version that computes the key as a
+ * hash of some information available in the MPTCP socket. Use
+ * random data at the moment, as it's probably the safest option
+ * in case multiple sockets are opened in different namespaces at
+ * the same time.
+ */
+ get_random_bytes(key, sizeof(u64));
+ mptcp_crypto_key_sha(*key, token, idsn);
+}
+
+void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u32 nonce1, u32 nonce2,
+ void *hash_out);
+
+static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
+{
+ return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);
+}
+
+static inline bool before64(__u64 seq1, __u64 seq2)
+{
+ return (__s64)(seq1 - seq2) < 0;
+}
+
+#define after64(seq2, seq1) before64(seq1, seq2)
+
+#endif /* __MPTCP_PROTOCOL_H */
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
new file mode 100644
index 0000000..1662e11
--- /dev/null
+++ b/net/mptcp/subflow.c
@@ -0,0 +1,860 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <net/sock.h>
+#include <net/inet_common.h>
+#include <net/inet_hashtables.h>
+#include <net/protocol.h>
+#include <net/tcp.h>
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+#include <net/ip6_route.h>
+#endif
+#include <net/mptcp.h>
+#include "protocol.h"
+
+static int subflow_rebuild_header(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ int err = 0;
+
+ if (subflow->request_mptcp && !subflow->token) {
+ pr_debug("subflow=%p", sk);
+ err = mptcp_token_new_connect(sk);
+ }
+
+ if (err)
+ return err;
+
+ return subflow->icsk_af_ops->rebuild_header(sk);
+}
+
+static void subflow_req_destructor(struct request_sock *req)
+{
+ struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
+
+ pr_debug("subflow_req=%p", subflow_req);
+
+ if (subflow_req->mp_capable)
+ mptcp_token_destroy_request(subflow_req->token);
+ tcp_request_sock_ops.destructor(req);
+}
+
+static void subflow_init_req(struct request_sock *req,
+ const struct sock *sk_listener,
+ struct sk_buff *skb)
+{
+ struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
+ struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
+ struct tcp_options_received rx_opt;
+
+ pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);
+
+ memset(&rx_opt.mptcp, 0, sizeof(rx_opt.mptcp));
+ mptcp_get_options(skb, &rx_opt);
+
+ subflow_req->mp_capable = 0;
+ subflow_req->remote_key_valid = 0;
+
+#ifdef CONFIG_TCP_MD5SIG
+ /* no MPTCP if MD5SIG is enabled on this socket or we may run out of
+ * TCP option space.
+ */
+ if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info))
+ return;
+#endif
+
+ if (rx_opt.mptcp.mp_capable && listener->request_mptcp) {
+ int err;
+
+ err = mptcp_token_new_request(req);
+ if (err == 0)
+ subflow_req->mp_capable = 1;
+
+ subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
+ }
+}
+
+static void subflow_v4_init_req(struct request_sock *req,
+ const struct sock *sk_listener,
+ struct sk_buff *skb)
+{
+ tcp_rsk(req)->is_mptcp = 1;
+
+ tcp_request_sock_ipv4_ops.init_req(req, sk_listener, skb);
+
+ subflow_init_req(req, sk_listener, skb);
+}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+static void subflow_v6_init_req(struct request_sock *req,
+ const struct sock *sk_listener,
+ struct sk_buff *skb)
+{
+ tcp_rsk(req)->is_mptcp = 1;
+
+ tcp_request_sock_ipv6_ops.init_req(req, sk_listener, skb);
+
+ subflow_init_req(req, sk_listener, skb);
+}
+#endif
+
+static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+
+ subflow->icsk_af_ops->sk_rx_dst_set(sk, skb);
+
+ if (subflow->conn && !subflow->conn_finished) {
+ pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk),
+ subflow->remote_key);
+ mptcp_finish_connect(sk);
+ subflow->conn_finished = 1;
+
+ if (skb) {
+ pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq);
+ subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
+ }
+ }
+}
+
+static struct request_sock_ops subflow_request_sock_ops;
+static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops;
+
+static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+
+ pr_debug("subflow=%p", subflow);
+
+ /* Never answer to SYNs sent to broadcast or multicast */
+ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
+ goto drop;
+
+ return tcp_conn_request(&subflow_request_sock_ops,
+ &subflow_request_sock_ipv4_ops,
+ sk, skb);
+drop:
+ tcp_listendrop(sk);
+ return 0;
+}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops;
+static struct inet_connection_sock_af_ops subflow_v6_specific;
+static struct inet_connection_sock_af_ops subflow_v6m_specific;
+
+static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+
+ pr_debug("subflow=%p", subflow);
+
+ if (skb->protocol == htons(ETH_P_IP))
+ return subflow_v4_conn_request(sk, skb);
+
+ if (!ipv6_unicast_destination(skb))
+ goto drop;
+
+ return tcp_conn_request(&subflow_request_sock_ops,
+ &subflow_request_sock_ipv6_ops, sk, skb);
+
+drop:
+ tcp_listendrop(sk);
+ return 0; /* don't send reset */
+}
+#endif
+
+static struct sock *subflow_syn_recv_sock(const struct sock *sk,
+ struct sk_buff *skb,
+ struct request_sock *req,
+ struct dst_entry *dst,
+ struct request_sock *req_unhash,
+ bool *own_req)
+{
+ struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
+ struct mptcp_subflow_request_sock *subflow_req;
+ struct tcp_options_received opt_rx;
+ struct sock *child;
+
+ pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
+
+ /* if the sk is MP_CAPABLE, we try to fetch the client key */
+ subflow_req = mptcp_subflow_rsk(req);
+ if (subflow_req->mp_capable) {
+ if (TCP_SKB_CB(skb)->seq != subflow_req->ssn_offset + 1) {
+ /* here we can receive and accept an in-window,
+ * out-of-order pkt, which will not carry the MP_CAPABLE
+ * opt even on mptcp enabled paths
+ */
+ goto create_child;
+ }
+
+ opt_rx.mptcp.mp_capable = 0;
+ mptcp_get_options(skb, &opt_rx);
+ if (opt_rx.mptcp.mp_capable) {
+ subflow_req->remote_key = opt_rx.mptcp.sndr_key;
+ subflow_req->remote_key_valid = 1;
+ } else {
+ subflow_req->mp_capable = 0;
+ }
+ }
+
+create_child:
+ child = listener->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
+ req_unhash, own_req);
+
+ if (child && *own_req) {
+ struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child);
+
+ /* we have null ctx on TCP fallback, not fatal on MPC
+ * handshake
+ */
+ if (!ctx)
+ return child;
+
+ if (ctx->mp_capable) {
+ if (mptcp_token_new_accept(ctx->token))
+ goto close_child;
+ }
+ }
+
+ return child;
+
+close_child:
+ pr_debug("closing child socket");
+ tcp_send_active_reset(child, GFP_ATOMIC);
+ inet_csk_prepare_forced_close(child);
+ tcp_done(child);
+ return NULL;
+}
+
+static struct inet_connection_sock_af_ops subflow_specific;
+
+enum mapping_status {
+ MAPPING_OK,
+ MAPPING_INVALID,
+ MAPPING_EMPTY,
+ MAPPING_DATA_FIN
+};
+
+static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq)
+{
+ if ((u32)seq == (u32)old_seq)
+ return old_seq;
+
+ /* Assume map covers data not mapped yet. */
+ return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32));
+}
+
+static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
+{
+ WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
+ ssn, subflow->map_subflow_seq, subflow->map_data_len);
+}
+
+static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ unsigned int skb_consumed;
+
+ skb_consumed = tcp_sk(ssk)->copied_seq - TCP_SKB_CB(skb)->seq;
+ if (WARN_ON_ONCE(skb_consumed >= skb->len))
+ return true;
+
+ return skb->len - skb_consumed <= subflow->map_data_len -
+ mptcp_subflow_get_map_offset(subflow);
+}
+
+static bool validate_mapping(struct sock *ssk, struct sk_buff *skb)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ u32 ssn = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
+
+ if (unlikely(before(ssn, subflow->map_subflow_seq))) {
+ /* Mapping covers data later in the subflow stream,
+ * currently unsupported.
+ */
+ warn_bad_map(subflow, ssn);
+ return false;
+ }
+ if (unlikely(!before(ssn, subflow->map_subflow_seq +
+ subflow->map_data_len))) {
+ /* Mapping does covers past subflow data, invalid */
+ warn_bad_map(subflow, ssn + skb->len);
+ return false;
+ }
+ return true;
+}
+
+static enum mapping_status get_mapping_status(struct sock *ssk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ struct mptcp_ext *mpext;
+ struct sk_buff *skb;
+ u16 data_len;
+ u64 map_seq;
+
+ skb = skb_peek(&ssk->sk_receive_queue);
+ if (!skb)
+ return MAPPING_EMPTY;
+
+ mpext = mptcp_get_ext(skb);
+ if (!mpext || !mpext->use_map) {
+ if (!subflow->map_valid && !skb->len) {
+ /* the TCP stack deliver 0 len FIN pkt to the receive
+ * queue, that is the only 0len pkts ever expected here,
+ * and we can admit no mapping only for 0 len pkts
+ */
+ if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
+ WARN_ONCE(1, "0len seq %d:%d flags %x",
+ TCP_SKB_CB(skb)->seq,
+ TCP_SKB_CB(skb)->end_seq,
+ TCP_SKB_CB(skb)->tcp_flags);
+ sk_eat_skb(ssk, skb);
+ return MAPPING_EMPTY;
+ }
+
+ if (!subflow->map_valid)
+ return MAPPING_INVALID;
+
+ goto validate_seq;
+ }
+
+ pr_debug("seq=%llu is64=%d ssn=%u data_len=%u data_fin=%d",
+ mpext->data_seq, mpext->dsn64, mpext->subflow_seq,
+ mpext->data_len, mpext->data_fin);
+
+ data_len = mpext->data_len;
+ if (data_len == 0) {
+ pr_err("Infinite mapping not handled");
+ return MAPPING_INVALID;
+ }
+
+ if (mpext->data_fin == 1) {
+ if (data_len == 1) {
+ pr_debug("DATA_FIN with no payload");
+ if (subflow->map_valid) {
+ /* A DATA_FIN might arrive in a DSS
+ * option before the previous mapping
+ * has been fully consumed. Continue
+ * handling the existing mapping.
+ */
+ skb_ext_del(skb, SKB_EXT_MPTCP);
+ return MAPPING_OK;
+ } else {
+ return MAPPING_DATA_FIN;
+ }
+ }
+
+ /* Adjust for DATA_FIN using 1 byte of sequence space */
+ data_len--;
+ }
+
+ if (!mpext->dsn64) {
+ map_seq = expand_seq(subflow->map_seq, subflow->map_data_len,
+ mpext->data_seq);
+ pr_debug("expanded seq=%llu", subflow->map_seq);
+ } else {
+ map_seq = mpext->data_seq;
+ }
+
+ if (subflow->map_valid) {
+ /* Allow replacing only with an identical map */
+ if (subflow->map_seq == map_seq &&
+ subflow->map_subflow_seq == mpext->subflow_seq &&
+ subflow->map_data_len == data_len) {
+ skb_ext_del(skb, SKB_EXT_MPTCP);
+ return MAPPING_OK;
+ }
+
+ /* If this skb data are fully covered by the current mapping,
+ * the new map would need caching, which is not supported
+ */
+ if (skb_is_fully_mapped(ssk, skb))
+ return MAPPING_INVALID;
+
+ /* will validate the next map after consuming the current one */
+ return MAPPING_OK;
+ }
+
+ subflow->map_seq = map_seq;
+ subflow->map_subflow_seq = mpext->subflow_seq;
+ subflow->map_data_len = data_len;
+ subflow->map_valid = 1;
+ subflow->mpc_map = mpext->mpc_map;
+ pr_debug("new map seq=%llu subflow_seq=%u data_len=%u",
+ subflow->map_seq, subflow->map_subflow_seq,
+ subflow->map_data_len);
+
+validate_seq:
+ /* we revalidate valid mapping on new skb, because we must ensure
+ * the current skb is completely covered by the available mapping
+ */
+ if (!validate_mapping(ssk, skb))
+ return MAPPING_INVALID;
+
+ skb_ext_del(skb, SKB_EXT_MPTCP);
+ return MAPPING_OK;
+}
+
+static bool subflow_check_data_avail(struct sock *ssk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ enum mapping_status status;
+ struct mptcp_sock *msk;
+ struct sk_buff *skb;
+
+ pr_debug("msk=%p ssk=%p data_avail=%d skb=%p", subflow->conn, ssk,
+ subflow->data_avail, skb_peek(&ssk->sk_receive_queue));
+ if (subflow->data_avail)
+ return true;
+
+ if (!subflow->conn)
+ return false;
+
+ msk = mptcp_sk(subflow->conn);
+ for (;;) {
+ u32 map_remaining;
+ size_t delta;
+ u64 ack_seq;
+ u64 old_ack;
+
+ status = get_mapping_status(ssk);
+ pr_debug("msk=%p ssk=%p status=%d", msk, ssk, status);
+ if (status == MAPPING_INVALID) {
+ ssk->sk_err = EBADMSG;
+ goto fatal;
+ }
+
+ if (status != MAPPING_OK)
+ return false;
+
+ skb = skb_peek(&ssk->sk_receive_queue);
+ if (WARN_ON_ONCE(!skb))
+ return false;
+
+ /* if msk lacks the remote key, this subflow must provide an
+ * MP_CAPABLE-based mapping
+ */
+ if (unlikely(!READ_ONCE(msk->can_ack))) {
+ if (!subflow->mpc_map) {
+ ssk->sk_err = EBADMSG;
+ goto fatal;
+ }
+ WRITE_ONCE(msk->remote_key, subflow->remote_key);
+ WRITE_ONCE(msk->ack_seq, subflow->map_seq);
+ WRITE_ONCE(msk->can_ack, true);
+ }
+
+ old_ack = READ_ONCE(msk->ack_seq);
+ ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
+ pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
+ ack_seq);
+ if (ack_seq == old_ack)
+ break;
+
+ /* only accept in-sequence mapping. Old values are spurious
+ * retransmission; we can hit "future" values on active backup
+ * subflow switch, we relay on retransmissions to get
+ * in-sequence data.
+ * Cuncurrent subflows support will require subflow data
+ * reordering
+ */
+ map_remaining = subflow->map_data_len -
+ mptcp_subflow_get_map_offset(subflow);
+ if (before64(ack_seq, old_ack))
+ delta = min_t(size_t, old_ack - ack_seq, map_remaining);
+ else
+ delta = min_t(size_t, ack_seq - old_ack, map_remaining);
+
+ /* discard mapped data */
+ pr_debug("discarding %zu bytes, current map len=%d", delta,
+ map_remaining);
+ if (delta) {
+ struct mptcp_read_arg arg = {
+ .msg = NULL,
+ };
+ read_descriptor_t desc = {
+ .count = delta,
+ .arg.data = &arg,
+ };
+ int ret;
+
+ ret = tcp_read_sock(ssk, &desc, mptcp_read_actor);
+ if (ret < 0) {
+ ssk->sk_err = -ret;
+ goto fatal;
+ }
+ if (ret < delta)
+ return false;
+ if (delta == map_remaining)
+ subflow->map_valid = 0;
+ }
+ }
+ return true;
+
+fatal:
+ /* fatal protocol error, close the socket */
+ /* This barrier is coupled with smp_rmb() in tcp_poll() */
+ smp_wmb();
+ ssk->sk_error_report(ssk);
+ tcp_set_state(ssk, TCP_CLOSE);
+ tcp_send_active_reset(ssk, GFP_ATOMIC);
+ return false;
+}
+
+bool mptcp_subflow_data_available(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct sk_buff *skb;
+
+ /* check if current mapping is still valid */
+ if (subflow->map_valid &&
+ mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) {
+ subflow->map_valid = 0;
+ subflow->data_avail = 0;
+
+ pr_debug("Done with mapping: seq=%u data_len=%u",
+ subflow->map_subflow_seq,
+ subflow->map_data_len);
+ }
+
+ if (!subflow_check_data_avail(sk)) {
+ subflow->data_avail = 0;
+ return false;
+ }
+
+ skb = skb_peek(&sk->sk_receive_queue);
+ subflow->data_avail = skb &&
+ before(tcp_sk(sk)->copied_seq, TCP_SKB_CB(skb)->end_seq);
+ return subflow->data_avail;
+}
+
+static void subflow_data_ready(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct sock *parent = subflow->conn;
+
+ if (!parent || !subflow->mp_capable) {
+ subflow->tcp_data_ready(sk);
+
+ if (parent)
+ parent->sk_data_ready(parent);
+ return;
+ }
+
+ if (mptcp_subflow_data_available(sk)) {
+ set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags);
+
+ parent->sk_data_ready(parent);
+ }
+}
+
+static void subflow_write_space(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct sock *parent = subflow->conn;
+
+ sk_stream_write_space(sk);
+ if (parent && sk_stream_is_writeable(sk)) {
+ set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags);
+ smp_mb__after_atomic();
+ /* set SEND_SPACE before sk_stream_write_space clears NOSPACE */
+ sk_stream_write_space(parent);
+ }
+}
+
+static struct inet_connection_sock_af_ops *
+subflow_default_af_ops(struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ if (sk->sk_family == AF_INET6)
+ return &subflow_v6_specific;
+#endif
+ return &subflow_specific;
+}
+
+void mptcp_handle_ipv6_mapped(struct sock *sk, bool mapped)
+{
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ struct inet_connection_sock_af_ops *target;
+
+ target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk);
+
+ pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d",
+ subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped);
+
+ if (likely(icsk->icsk_af_ops == target))
+ return;
+
+ subflow->icsk_af_ops = icsk->icsk_af_ops;
+ icsk->icsk_af_ops = target;
+#endif
+}
+
+int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
+{
+ struct mptcp_subflow_context *subflow;
+ struct net *net = sock_net(sk);
+ struct socket *sf;
+ int err;
+
+ err = sock_create_kern(net, sk->sk_family, SOCK_STREAM, IPPROTO_TCP,
+ &sf);
+ if (err)
+ return err;
+
+ lock_sock(sf->sk);
+
+ /* kernel sockets do not by default acquire net ref, but TCP timer
+ * needs it.
+ */
+ sf->sk->sk_net_refcnt = 1;
+ get_net(net);
+ this_cpu_add(*net->core.sock_inuse, 1);
+ err = tcp_set_ulp(sf->sk, "mptcp");
+ release_sock(sf->sk);
+
+ if (err)
+ return err;
+
+ subflow = mptcp_subflow_ctx(sf->sk);
+ pr_debug("subflow=%p", subflow);
+
+ *new_sock = sf;
+ sock_hold(sk);
+ subflow->conn = sk;
+
+ return 0;
+}
+
+static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
+ gfp_t priority)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ struct mptcp_subflow_context *ctx;
+
+ ctx = kzalloc(sizeof(*ctx), priority);
+ if (!ctx)
+ return NULL;
+
+ rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
+ INIT_LIST_HEAD(&ctx->node);
+
+ pr_debug("subflow=%p", ctx);
+
+ ctx->tcp_sock = sk;
+
+ return ctx;
+}
+
+static void __subflow_state_change(struct sock *sk)
+{
+ struct socket_wq *wq;
+
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ if (skwq_has_sleeper(wq))
+ wake_up_interruptible_all(&wq->wait);
+ rcu_read_unlock();
+}
+
+static bool subflow_is_done(const struct sock *sk)
+{
+ return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE;
+}
+
+static void subflow_state_change(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct sock *parent = READ_ONCE(subflow->conn);
+
+ __subflow_state_change(sk);
+
+ /* as recvmsg() does not acquire the subflow socket for ssk selection
+ * a fin packet carrying a DSS can be unnoticed if we don't trigger
+ * the data available machinery here.
+ */
+ if (parent && subflow->mp_capable && mptcp_subflow_data_available(sk)) {
+ set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags);
+
+ parent->sk_data_ready(parent);
+ }
+
+ if (parent && !(parent->sk_shutdown & RCV_SHUTDOWN) &&
+ !subflow->rx_eof && subflow_is_done(sk)) {
+ subflow->rx_eof = 1;
+ parent->sk_shutdown |= RCV_SHUTDOWN;
+ __subflow_state_change(parent);
+ }
+}
+
+static int subflow_ulp_init(struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ struct mptcp_subflow_context *ctx;
+ struct tcp_sock *tp = tcp_sk(sk);
+ int err = 0;
+
+ /* disallow attaching ULP to a socket unless it has been
+ * created with sock_create_kern()
+ */
+ if (!sk->sk_kern_sock) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ ctx = subflow_create_ctx(sk, GFP_KERNEL);
+ if (!ctx) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ pr_debug("subflow=%p, family=%d", ctx, sk->sk_family);
+
+ tp->is_mptcp = 1;
+ ctx->icsk_af_ops = icsk->icsk_af_ops;
+ icsk->icsk_af_ops = subflow_default_af_ops(sk);
+ ctx->tcp_data_ready = sk->sk_data_ready;
+ ctx->tcp_state_change = sk->sk_state_change;
+ ctx->tcp_write_space = sk->sk_write_space;
+ sk->sk_data_ready = subflow_data_ready;
+ sk->sk_write_space = subflow_write_space;
+ sk->sk_state_change = subflow_state_change;
+out:
+ return err;
+}
+
+static void subflow_ulp_release(struct sock *sk)
+{
+ struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(sk);
+
+ if (!ctx)
+ return;
+
+ if (ctx->conn)
+ sock_put(ctx->conn);
+
+ kfree_rcu(ctx, rcu);
+}
+
+static void subflow_ulp_fallback(struct sock *sk,
+ struct mptcp_subflow_context *old_ctx)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ mptcp_subflow_tcp_fallback(sk, old_ctx);
+ icsk->icsk_ulp_ops = NULL;
+ rcu_assign_pointer(icsk->icsk_ulp_data, NULL);
+ tcp_sk(sk)->is_mptcp = 0;
+}
+
+static void subflow_ulp_clone(const struct request_sock *req,
+ struct sock *newsk,
+ const gfp_t priority)
+{
+ struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
+ struct mptcp_subflow_context *old_ctx = mptcp_subflow_ctx(newsk);
+ struct mptcp_subflow_context *new_ctx;
+
+ if (!subflow_req->mp_capable) {
+ subflow_ulp_fallback(newsk, old_ctx);
+ return;
+ }
+
+ new_ctx = subflow_create_ctx(newsk, priority);
+ if (!new_ctx) {
+ subflow_ulp_fallback(newsk, old_ctx);
+ return;
+ }
+
+ /* see comments in subflow_syn_recv_sock(), MPTCP connection is fully
+ * established only after we receive the remote key
+ */
+ new_ctx->conn_finished = 1;
+ new_ctx->icsk_af_ops = old_ctx->icsk_af_ops;
+ new_ctx->tcp_data_ready = old_ctx->tcp_data_ready;
+ new_ctx->tcp_state_change = old_ctx->tcp_state_change;
+ new_ctx->tcp_write_space = old_ctx->tcp_write_space;
+ new_ctx->mp_capable = 1;
+ new_ctx->fourth_ack = subflow_req->remote_key_valid;
+ new_ctx->can_ack = subflow_req->remote_key_valid;
+ new_ctx->remote_key = subflow_req->remote_key;
+ new_ctx->local_key = subflow_req->local_key;
+ new_ctx->token = subflow_req->token;
+ new_ctx->ssn_offset = subflow_req->ssn_offset;
+ new_ctx->idsn = subflow_req->idsn;
+}
+
+static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = {
+ .name = "mptcp",
+ .owner = THIS_MODULE,
+ .init = subflow_ulp_init,
+ .release = subflow_ulp_release,
+ .clone = subflow_ulp_clone,
+};
+
+static int subflow_ops_init(struct request_sock_ops *subflow_ops)
+{
+ subflow_ops->obj_size = sizeof(struct mptcp_subflow_request_sock);
+ subflow_ops->slab_name = "request_sock_subflow";
+
+ subflow_ops->slab = kmem_cache_create(subflow_ops->slab_name,
+ subflow_ops->obj_size, 0,
+ SLAB_ACCOUNT |
+ SLAB_TYPESAFE_BY_RCU,
+ NULL);
+ if (!subflow_ops->slab)
+ return -ENOMEM;
+
+ subflow_ops->destructor = subflow_req_destructor;
+
+ return 0;
+}
+
+void mptcp_subflow_init(void)
+{
+ subflow_request_sock_ops = tcp_request_sock_ops;
+ if (subflow_ops_init(&subflow_request_sock_ops) != 0)
+ panic("MPTCP: failed to init subflow request sock ops\n");
+
+ subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops;
+ subflow_request_sock_ipv4_ops.init_req = subflow_v4_init_req;
+
+ subflow_specific = ipv4_specific;
+ subflow_specific.conn_request = subflow_v4_conn_request;
+ subflow_specific.syn_recv_sock = subflow_syn_recv_sock;
+ subflow_specific.sk_rx_dst_set = subflow_finish_connect;
+ subflow_specific.rebuild_header = subflow_rebuild_header;
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops;
+ subflow_request_sock_ipv6_ops.init_req = subflow_v6_init_req;
+
+ subflow_v6_specific = ipv6_specific;
+ subflow_v6_specific.conn_request = subflow_v6_conn_request;
+ subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock;
+ subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect;
+ subflow_v6_specific.rebuild_header = subflow_rebuild_header;
+
+ subflow_v6m_specific = subflow_v6_specific;
+ subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit;
+ subflow_v6m_specific.send_check = ipv4_specific.send_check;
+ subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len;
+ subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced;
+ subflow_v6m_specific.net_frag_header_len = 0;
+#endif
+
+ if (tcp_register_ulp(&subflow_ulp_ops) != 0)
+ panic("MPTCP: failed to register subflows to ULP\n");
+}
diff --git a/net/mptcp/token.c b/net/mptcp/token.c
new file mode 100644
index 0000000..84d8878
--- /dev/null
+++ b/net/mptcp/token.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP token management
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ *
+ * Note: This code is based on mptcp_ctrl.c from multipath-tcp.org,
+ * authored by:
+ *
+ * Sébastien Barré <sebastien.barre@uclouvain.be>
+ * Christoph Paasch <christoph.paasch@uclouvain.be>
+ * Jaakko Korkeaniemi <jaakko.korkeaniemi@aalto.fi>
+ * Gregory Detal <gregory.detal@uclouvain.be>
+ * Fabien Duchêne <fabien.duchene@uclouvain.be>
+ * Andreas Seelinger <Andreas.Seelinger@rwth-aachen.de>
+ * Lavkesh Lahngir <lavkesh51@gmail.com>
+ * Andreas Ripke <ripke@neclab.eu>
+ * Vlad Dogaru <vlad.dogaru@intel.com>
+ * Octavian Purdila <octavian.purdila@intel.com>
+ * John Ronan <jronan@tssg.org>
+ * Catalin Nicutar <catalin.nicutar@gmail.com>
+ * Brandon Heller <brandonh@stanford.edu>
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/radix-tree.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <net/sock.h>
+#include <net/inet_common.h>
+#include <net/protocol.h>
+#include <net/mptcp.h>
+#include "protocol.h"
+
+static RADIX_TREE(token_tree, GFP_ATOMIC);
+static RADIX_TREE(token_req_tree, GFP_ATOMIC);
+static DEFINE_SPINLOCK(token_tree_lock);
+static int token_used __read_mostly;
+
+/**
+ * mptcp_token_new_request - create new key/idsn/token for subflow_request
+ * @req - the request socket
+ *
+ * This function is called when a new mptcp connection is coming in.
+ *
+ * It creates a unique token to identify the new mptcp connection,
+ * a secret local key and the initial data sequence number (idsn).
+ *
+ * Returns 0 on success.
+ */
+int mptcp_token_new_request(struct request_sock *req)
+{
+ struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
+ int err;
+
+ while (1) {
+ u32 token;
+
+ mptcp_crypto_key_gen_sha(&subflow_req->local_key,
+ &subflow_req->token,
+ &subflow_req->idsn);
+ pr_debug("req=%p local_key=%llu, token=%u, idsn=%llu\n",
+ req, subflow_req->local_key, subflow_req->token,
+ subflow_req->idsn);
+
+ token = subflow_req->token;
+ spin_lock_bh(&token_tree_lock);
+ if (!radix_tree_lookup(&token_req_tree, token) &&
+ !radix_tree_lookup(&token_tree, token))
+ break;
+ spin_unlock_bh(&token_tree_lock);
+ }
+
+ err = radix_tree_insert(&token_req_tree,
+ subflow_req->token, &token_used);
+ spin_unlock_bh(&token_tree_lock);
+ return err;
+}
+
+/**
+ * mptcp_token_new_connect - create new key/idsn/token for subflow
+ * @sk - the socket that will initiate a connection
+ *
+ * This function is called when a new outgoing mptcp connection is
+ * initiated.
+ *
+ * It creates a unique token to identify the new mptcp connection,
+ * a secret local key and the initial data sequence number (idsn).
+ *
+ * On success, the mptcp connection can be found again using
+ * the computed token at a later time, this is needed to process
+ * join requests.
+ *
+ * returns 0 on success.
+ */
+int mptcp_token_new_connect(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct sock *mptcp_sock = subflow->conn;
+ int err;
+
+ while (1) {
+ u32 token;
+
+ mptcp_crypto_key_gen_sha(&subflow->local_key, &subflow->token,
+ &subflow->idsn);
+
+ pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n",
+ sk, subflow->local_key, subflow->token, subflow->idsn);
+
+ token = subflow->token;
+ spin_lock_bh(&token_tree_lock);
+ if (!radix_tree_lookup(&token_req_tree, token) &&
+ !radix_tree_lookup(&token_tree, token))
+ break;
+ spin_unlock_bh(&token_tree_lock);
+ }
+ err = radix_tree_insert(&token_tree, subflow->token, mptcp_sock);
+ spin_unlock_bh(&token_tree_lock);
+
+ return err;
+}
+
+/**
+ * mptcp_token_new_accept - insert token for later processing
+ * @token: the token to insert to the tree
+ *
+ * Called when a SYN packet creates a new logical connection, i.e.
+ * is not a join request.
+ *
+ * We don't have an mptcp socket yet at that point.
+ * This is paired with mptcp_token_update_accept, called on accept().
+ */
+int mptcp_token_new_accept(u32 token)
+{
+ int err;
+
+ spin_lock_bh(&token_tree_lock);
+ err = radix_tree_insert(&token_tree, token, &token_used);
+ spin_unlock_bh(&token_tree_lock);
+
+ return err;
+}
+
+/**
+ * mptcp_token_update_accept - update token to map to mptcp socket
+ * @conn: the new struct mptcp_sock
+ * @sk: the initial subflow for this mptcp socket
+ *
+ * Called when the first mptcp socket is created on accept to
+ * refresh the dummy mapping (done to reserve the token) with
+ * the mptcp_socket structure that wasn't allocated before.
+ */
+void mptcp_token_update_accept(struct sock *sk, struct sock *conn)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ void __rcu **slot;
+
+ spin_lock_bh(&token_tree_lock);
+ slot = radix_tree_lookup_slot(&token_tree, subflow->token);
+ WARN_ON_ONCE(!slot);
+ if (slot) {
+ WARN_ON_ONCE(rcu_access_pointer(*slot) != &token_used);
+ radix_tree_replace_slot(&token_tree, slot, conn);
+ }
+ spin_unlock_bh(&token_tree_lock);
+}
+
+/**
+ * mptcp_token_destroy_request - remove mptcp connection/token
+ * @token - token of mptcp connection to remove
+ *
+ * Remove not-yet-fully-established incoming connection identified
+ * by @token.
+ */
+void mptcp_token_destroy_request(u32 token)
+{
+ spin_lock_bh(&token_tree_lock);
+ radix_tree_delete(&token_req_tree, token);
+ spin_unlock_bh(&token_tree_lock);
+}
+
+/**
+ * mptcp_token_destroy - remove mptcp connection/token
+ * @token - token of mptcp connection to remove
+ *
+ * Remove the connection identified by @token.
+ */
+void mptcp_token_destroy(u32 token)
+{
+ spin_lock_bh(&token_tree_lock);
+ radix_tree_delete(&token_tree, token);
+ spin_unlock_bh(&token_tree_lock);
+}
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index ad3fd7f..e371025 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -64,6 +64,17 @@ enum {
NCSI_MODE_MAX
};
+/* Supported media status bits for Mellanox Mac affinity command.
+ * Bit (0-2) for different protocol support; Bit 1 for RBT support,
+ * bit 1 for SMBUS support and bit 2 for PCIE support. Bit (3-5)
+ * for different protocol availability. Bit 4 for RBT, bit 4 for
+ * SMBUS and bit 5 for PCIE.
+ */
+enum {
+ MLX_MC_RBT_SUPPORT = 0x01, /* MC supports RBT */
+ MLX_MC_RBT_AVL = 0x08, /* RBT medium is available */
+};
+
/* OEM Vendor Manufacture ID */
#define NCSI_OEM_MFR_MLX_ID 0x8119
#define NCSI_OEM_MFR_BCM_ID 0x113d
@@ -72,9 +83,15 @@ enum {
/* Mellanox specific OEM Command */
#define NCSI_OEM_MLX_CMD_GMA 0x00 /* CMD ID for Get MAC */
#define NCSI_OEM_MLX_CMD_GMA_PARAM 0x1b /* Parameter for GMA */
+#define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */
+#define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */
/* OEM Command payload lengths*/
#define NCSI_OEM_BCM_CMD_GMA_LEN 12
#define NCSI_OEM_MLX_CMD_GMA_LEN 8
+#define NCSI_OEM_MLX_CMD_SMAF_LEN 60
+/* Offset in OEM request */
+#define MLX_SMAF_MAC_ADDR_OFFSET 8 /* Offset for MAC in SMAF */
+#define MLX_SMAF_MED_SUPPORT_OFFSET 14 /* Offset for medium in SMAF */
/* Mac address offset in OEM response */
#define BCM_MAC_ADDR_OFFSET 28
#define MLX_MAC_ADDR_OFFSET 8
@@ -251,6 +268,8 @@ enum {
ncsi_dev_state_probe_deselect = 0x0201,
ncsi_dev_state_probe_package,
ncsi_dev_state_probe_channel,
+ ncsi_dev_state_probe_mlx_gma,
+ ncsi_dev_state_probe_mlx_smaf,
ncsi_dev_state_probe_cis,
ncsi_dev_state_probe_gvi,
ncsi_dev_state_probe_gc,
@@ -311,6 +330,7 @@ struct ncsi_dev_priv {
struct list_head vlan_vids; /* List of active VLAN IDs */
bool multi_package; /* Enable multiple packages */
+ bool mlx_multi_host; /* Enable multi host Mellanox */
u32 package_whitelist; /* Packages to configure */
};
diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c
index 0187e65..ba9ae48 100644
--- a/net/ncsi/ncsi-cmd.c
+++ b/net/ncsi/ncsi-cmd.c
@@ -369,7 +369,15 @@ int ncsi_xmit_cmd(struct ncsi_cmd_arg *nca)
eh = skb_push(nr->cmd, sizeof(*eh));
eh->h_proto = htons(ETH_P_NCSI);
eth_broadcast_addr(eh->h_dest);
- eth_broadcast_addr(eh->h_source);
+
+ /* If mac address received from device then use it for
+ * source address as unicast address else use broadcast
+ * address as source address
+ */
+ if (nca->ndp->gma_flag == 1)
+ memcpy(eh->h_source, nca->ndp->ndev.dev->dev_addr, ETH_ALEN);
+ else
+ eth_broadcast_addr(eh->h_source);
/* Start the timer for the request that might not have
* corresponding response. Given NCSI is an internal
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index e20b815..1f387be 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -8,6 +8,8 @@
#include <linux/init.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
#include <net/ncsi.h>
#include <net/net_namespace.h>
@@ -730,6 +732,34 @@ static int ncsi_oem_gma_handler_mlx(struct ncsi_cmd_arg *nca)
return ret;
}
+static int ncsi_oem_smaf_mlx(struct ncsi_cmd_arg *nca)
+{
+ union {
+ u8 data_u8[NCSI_OEM_MLX_CMD_SMAF_LEN];
+ u32 data_u32[NCSI_OEM_MLX_CMD_SMAF_LEN / sizeof(u32)];
+ } u;
+ int ret = 0;
+
+ memset(&u, 0, sizeof(u));
+ u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID);
+ u.data_u8[5] = NCSI_OEM_MLX_CMD_SMAF;
+ u.data_u8[6] = NCSI_OEM_MLX_CMD_SMAF_PARAM;
+ memcpy(&u.data_u8[MLX_SMAF_MAC_ADDR_OFFSET],
+ nca->ndp->ndev.dev->dev_addr, ETH_ALEN);
+ u.data_u8[MLX_SMAF_MED_SUPPORT_OFFSET] =
+ (MLX_MC_RBT_AVL | MLX_MC_RBT_SUPPORT);
+
+ nca->payload = NCSI_OEM_MLX_CMD_SMAF_LEN;
+ nca->data = u.data_u8;
+
+ ret = ncsi_xmit_cmd(nca);
+ if (ret)
+ netdev_err(nca->ndp->ndev.dev,
+ "NCSI: Failed to transmit cmd 0x%x during probe\n",
+ nca->type);
+ return ret;
+}
+
/* OEM Command handlers initialization */
static struct ncsi_oem_gma_handler {
unsigned int mfr_id;
@@ -1310,8 +1340,38 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
break;
}
nd->state = ncsi_dev_state_probe_cis;
+ if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) &&
+ ndp->mlx_multi_host)
+ nd->state = ncsi_dev_state_probe_mlx_gma;
+
schedule_work(&ndp->work);
break;
+#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC)
+ case ncsi_dev_state_probe_mlx_gma:
+ ndp->pending_req_num = 1;
+
+ nca.type = NCSI_PKT_CMD_OEM;
+ nca.package = ndp->active_package->id;
+ nca.channel = 0;
+ ret = ncsi_oem_gma_handler_mlx(&nca);
+ if (ret)
+ goto error;
+
+ nd->state = ncsi_dev_state_probe_mlx_smaf;
+ break;
+ case ncsi_dev_state_probe_mlx_smaf:
+ ndp->pending_req_num = 1;
+
+ nca.type = NCSI_PKT_CMD_OEM;
+ nca.package = ndp->active_package->id;
+ nca.channel = 0;
+ ret = ncsi_oem_smaf_mlx(&nca);
+ if (ret)
+ goto error;
+
+ nd->state = ncsi_dev_state_probe_cis;
+ break;
+#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */
case ncsi_dev_state_probe_cis:
ndp->pending_req_num = NCSI_RESERVED_CHANNEL;
@@ -1621,6 +1681,8 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev,
{
struct ncsi_dev_priv *ndp;
struct ncsi_dev *nd;
+ struct platform_device *pdev;
+ struct device_node *np;
unsigned long flags;
int i;
@@ -1667,6 +1729,13 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev,
/* Set up generic netlink interface */
ncsi_init_netlink(dev);
+ pdev = to_platform_device(dev->dev.parent);
+ if (pdev) {
+ np = pdev->dev.of_node;
+ if (np && of_get_property(np, "mlx,multi-host", NULL))
+ ndp->mlx_multi_host = true;
+ }
+
return nd;
}
EXPORT_SYMBOL_GPL(ncsi_register_dev);
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 5e9b2eb..3f572e5 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -81,7 +81,8 @@
nft_chain_route.o nf_tables_offload.o
nf_tables_set-objs := nf_tables_set_core.o \
- nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o
+ nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o \
+ nft_set_pipapo.o
obj-$(CONFIG_NF_TABLES) += nf_tables.o
obj-$(CONFIG_NF_TABLES_SET) += nf_tables_set.o
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 1abd6f0..26ab0e9 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -60,9 +60,9 @@ mtype_destroy(struct ip_set *set)
if (SET_WITH_TIMEOUT(set))
del_timer_sync(&map->gc);
- ip_set_free(map->members);
if (set->dsize && set->extensions & IPSET_EXT_DESTROY)
mtype_ext_cleanup(set);
+ ip_set_free(map->members);
ip_set_free(map);
set->data = NULL;
@@ -75,7 +75,7 @@ mtype_flush(struct ip_set *set)
if (set->extensions & IPSET_EXT_DESTROY)
mtype_ext_cleanup(set);
- memset(map->members, 0, map->memsize);
+ bitmap_zero(map->members, map->elements);
set->elements = 0;
set->ext_size = 0;
}
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index abe8f77..0a2196f 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -37,7 +37,7 @@ MODULE_ALIAS("ip_set_bitmap:ip");
/* Type structure */
struct bitmap_ip {
- void *members; /* the set members */
+ unsigned long *members; /* the set members */
u32 first_ip; /* host byte order, included in range */
u32 last_ip; /* host byte order, included in range */
u32 elements; /* number of max elements in the set */
@@ -220,7 +220,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
u32 first_ip, u32 last_ip,
u32 elements, u32 hosts, u8 netmask)
{
- map->members = ip_set_alloc(map->memsize);
+ map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN);
if (!map->members)
return false;
map->first_ip = first_ip;
@@ -322,7 +322,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
if (!map)
return -ENOMEM;
- map->memsize = bitmap_bytes(0, elements - 1);
+ map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
set->variant = &bitmap_ip;
if (!init_map_ip(set, map, first_ip, last_ip,
elements, hosts, netmask)) {
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index b618713..739e343 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -42,7 +42,7 @@ enum {
/* Type structure */
struct bitmap_ipmac {
- void *members; /* the set members */
+ unsigned long *members; /* the set members */
u32 first_ip; /* host byte order, included in range */
u32 last_ip; /* host byte order, included in range */
u32 elements; /* number of max elements in the set */
@@ -299,7 +299,7 @@ static bool
init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
u32 first_ip, u32 last_ip, u32 elements)
{
- map->members = ip_set_alloc(map->memsize);
+ map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN);
if (!map->members)
return false;
map->first_ip = first_ip;
@@ -360,7 +360,7 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
if (!map)
return -ENOMEM;
- map->memsize = bitmap_bytes(0, elements - 1);
+ map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
set->variant = &bitmap_ipmac;
if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
kfree(map);
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 23d6095..b49978d 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -30,7 +30,7 @@ MODULE_ALIAS("ip_set_bitmap:port");
/* Type structure */
struct bitmap_port {
- void *members; /* the set members */
+ unsigned long *members; /* the set members */
u16 first_port; /* host byte order, included in range */
u16 last_port; /* host byte order, included in range */
u32 elements; /* number of max elements in the set */
@@ -231,7 +231,7 @@ static bool
init_map_port(struct ip_set *set, struct bitmap_port *map,
u16 first_port, u16 last_port)
{
- map->members = ip_set_alloc(map->memsize);
+ map->members = bitmap_zalloc(map->elements, GFP_KERNEL | __GFP_NOWARN);
if (!map->members)
return false;
map->first_port = first_port;
@@ -271,7 +271,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
return -ENOMEM;
map->elements = elements;
- map->memsize = bitmap_bytes(0, map->elements);
+ map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
set->variant = &bitmap_port;
if (!init_map_port(set, map, first_port, last_port)) {
kfree(map);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 169e0a04..cf895bc 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1848,6 +1848,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb,
struct ip_set *set;
struct nlattr *tb[IPSET_ATTR_ADT_MAX + 1] = {};
int ret = 0;
+ u32 lineno;
if (unlikely(protocol_min_failed(attr) ||
!attr[IPSET_ATTR_SETNAME] ||
@@ -1864,7 +1865,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb,
return -IPSET_ERR_PROTOCOL;
rcu_read_lock_bh();
- ret = set->variant->uadt(set, tb, IPSET_TEST, NULL, 0, 0);
+ ret = set->variant->uadt(set, tb, IPSET_TEST, &lineno, 0, 0);
rcu_read_unlock_bh();
/* Userspace can't trigger element to be re-added */
if (ret == -EAGAIN)
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 8dc892a..605e0f6 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1239,7 +1239,7 @@ static void ip_vs_process_message(struct netns_ipvs *ipvs, __u8 *buffer,
p = msg_end;
if (p + sizeof(s->v4) > buffer+buflen) {
- IP_VS_ERR_RL("BACKUP, Dropping buffer, to small\n");
+ IP_VS_ERR_RL("BACKUP, Dropping buffer, too small\n");
return;
}
s = (union ip_vs_sync_conn *)p;
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index b6b14db..b3f4a33 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -677,6 +677,9 @@ static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[],
unsigned int *timeouts = data;
int i;
+ if (!timeouts)
+ timeouts = dn->dccp_timeout;
+
/* set default DCCP timeouts. */
for (i=0; i<CT_DCCP_MAX; i++)
timeouts[i] = dn->dccp_timeout[i];
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index fce3d93..4f897b1 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -114,7 +114,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
{
/* ORIGINAL */
/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
-/* init */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA},
+/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA},
/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},
/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS},
@@ -130,7 +130,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
/* REPLY */
/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */
-/* init_ack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},
+/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},
/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL},
/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR},
/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA},
@@ -316,7 +316,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = sh->vtag;
}
- ct->proto.sctp.state = new_state;
+ ct->proto.sctp.state = SCTP_CONNTRACK_NONE;
}
return true;
@@ -594,6 +594,9 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[],
struct nf_sctp_net *sn = nf_sctp_pernet(net);
int i;
+ if (!timeouts)
+ timeouts = sn->timeouts;
+
/* set default SCTP timeouts. */
for (i=0; i<SCTP_CONNTRACK_MAX; i++)
timeouts[i] = sn->timeouts[i];
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 9889d52..7e91989 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -61,9 +61,9 @@ struct flow_offload *flow_offload_alloc(struct nf_conn *ct)
flow_offload_fill_dir(flow, FLOW_OFFLOAD_DIR_REPLY);
if (ct->status & IPS_SRC_NAT)
- flow->flags |= FLOW_OFFLOAD_SNAT;
+ __set_bit(NF_FLOW_SNAT, &flow->flags);
if (ct->status & IPS_DST_NAT)
- flow->flags |= FLOW_OFFLOAD_DNAT;
+ __set_bit(NF_FLOW_DNAT, &flow->flags);
return flow;
@@ -134,11 +134,6 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
#define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT (120 * HZ)
#define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT (30 * HZ)
-static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
-{
- return (__s32)(timeout - (u32)jiffies);
-}
-
static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
{
const struct nf_conntrack_l4proto *l4proto;
@@ -187,8 +182,6 @@ void flow_offload_free(struct flow_offload *flow)
default:
break;
}
- if (flow->flags & FLOW_OFFLOAD_DYING)
- nf_ct_delete(flow->ct, 0, 0);
nf_ct_put(flow->ct);
kfree_rcu(flow, rcu_head);
}
@@ -232,7 +225,7 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
{
int err;
- flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+ flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
err = rhashtable_insert_fast(&flow_table->rhashtable,
&flow->tuplehash[0].node,
@@ -250,8 +243,10 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
return err;
}
- if (flow_table->flags & NF_FLOWTABLE_HW_OFFLOAD)
+ if (nf_flowtable_hw_offload(flow_table)) {
+ __set_bit(NF_FLOW_HW, &flow->flags);
nf_flow_offload_add(flow_table, flow);
+ }
return 0;
}
@@ -276,7 +271,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
if (nf_flow_has_expired(flow))
flow_offload_fixup_ct(flow->ct);
- else if (flow->flags & FLOW_OFFLOAD_TEARDOWN)
+ else if (test_bit(NF_FLOW_TEARDOWN, &flow->flags))
flow_offload_fixup_ct_timeout(flow->ct);
flow_offload_free(flow);
@@ -284,7 +279,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
void flow_offload_teardown(struct flow_offload *flow)
{
- flow->flags |= FLOW_OFFLOAD_TEARDOWN;
+ set_bit(NF_FLOW_TEARDOWN, &flow->flags);
flow_offload_fixup_ct_state(flow->ct);
}
@@ -305,7 +300,7 @@ flow_offload_lookup(struct nf_flowtable *flow_table,
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
- if (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))
+ if (test_bit(NF_FLOW_TEARDOWN, &flow->flags))
return NULL;
if (unlikely(nf_ct_is_dying(flow->ct)))
@@ -353,19 +348,18 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
{
struct nf_flowtable *flow_table = data;
- if (flow->flags & FLOW_OFFLOAD_HW)
- nf_flow_offload_stats(flow_table, flow);
-
if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) ||
- (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))) {
- if (flow->flags & FLOW_OFFLOAD_HW) {
- if (!(flow->flags & FLOW_OFFLOAD_HW_DYING))
+ test_bit(NF_FLOW_TEARDOWN, &flow->flags)) {
+ if (test_bit(NF_FLOW_HW, &flow->flags)) {
+ if (!test_bit(NF_FLOW_HW_DYING, &flow->flags))
nf_flow_offload_del(flow_table, flow);
- else if (flow->flags & FLOW_OFFLOAD_HW_DEAD)
+ else if (test_bit(NF_FLOW_HW_DEAD, &flow->flags))
flow_offload_del(flow_table, flow);
} else {
flow_offload_del(flow_table, flow);
}
+ } else if (test_bit(NF_FLOW_HW, &flow->flags)) {
+ nf_flow_offload_stats(flow_table, flow);
}
}
@@ -529,7 +523,7 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
if (net_eq(nf_ct_net(flow->ct), dev_net(dev)) &&
(flow->tuplehash[0].tuple.iifidx == dev->ifindex ||
flow->tuplehash[1].tuple.iifidx == dev->ifindex))
- flow_offload_dead(flow);
+ flow_offload_teardown(flow);
}
static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index b9e7dd6..9e563fd 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -144,11 +144,11 @@ static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
{
struct iphdr *iph = ip_hdr(skb);
- if (flow->flags & FLOW_OFFLOAD_SNAT &&
+ if (test_bit(NF_FLOW_SNAT, &flow->flags) &&
(nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0))
return -1;
- if (flow->flags & FLOW_OFFLOAD_DNAT &&
+ if (test_bit(NF_FLOW_DNAT, &flow->flags) &&
(nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0))
return -1;
@@ -232,6 +232,13 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
return NF_STOLEN;
}
+static bool nf_flow_offload_refresh(struct nf_flowtable *flow_table,
+ struct flow_offload *flow)
+{
+ return nf_flowtable_hw_offload(flow_table) &&
+ test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags);
+}
+
unsigned int
nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
@@ -272,6 +279,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff))
return NF_ACCEPT;
+ if (unlikely(nf_flow_offload_refresh(flow_table, flow)))
+ nf_flow_offload_add(flow_table, flow);
+
if (nf_flow_offload_dst_check(&rt->dst)) {
flow_offload_teardown(flow);
return NF_ACCEPT;
@@ -280,7 +290,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0)
return NF_DROP;
- flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+ flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
iph = ip_hdr(skb);
ip_decrease_ttl(iph);
skb->tstamp = 0;
@@ -414,11 +424,11 @@ static int nf_flow_nat_ipv6(const struct flow_offload *flow,
struct ipv6hdr *ip6h = ipv6_hdr(skb);
unsigned int thoff = sizeof(*ip6h);
- if (flow->flags & FLOW_OFFLOAD_SNAT &&
+ if (test_bit(NF_FLOW_SNAT, &flow->flags) &&
(nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
return -1;
- if (flow->flags & FLOW_OFFLOAD_DNAT &&
+ if (test_bit(NF_FLOW_DNAT, &flow->flags) &&
(nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
return -1;
@@ -498,6 +508,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
sizeof(*ip6h)))
return NF_ACCEPT;
+ if (unlikely(nf_flow_offload_refresh(flow_table, flow)))
+ nf_flow_offload_add(flow_table, flow);
+
if (nf_flow_offload_dst_check(&rt->dst)) {
flow_offload_teardown(flow);
return NF_ACCEPT;
@@ -509,7 +522,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
if (nf_flow_nat_ipv6(flow, skb, dir) < 0)
return NF_DROP;
- flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+ flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
ip6h = ipv6_hdr(skb);
ip6h->hop_limit--;
skb->tstamp = 0;
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 0d72e5c..c8b70ff 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -24,6 +24,7 @@ struct flow_offload_work {
};
struct nf_flow_key {
+ struct flow_dissector_key_meta meta;
struct flow_dissector_key_control control;
struct flow_dissector_key_basic basic;
union {
@@ -55,6 +56,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match,
struct nf_flow_key *mask = &match->mask;
struct nf_flow_key *key = &match->key;
+ NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_META, meta);
NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control);
NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_BASIC, basic);
NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
@@ -62,6 +64,9 @@ static int nf_flow_rule_match(struct nf_flow_match *match,
NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp);
NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp);
+ key->meta.ingress_ifindex = tuple->iifidx;
+ mask->meta.ingress_ifindex = 0xffffffff;
+
switch (tuple->l3proto) {
case AF_INET:
key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
@@ -105,7 +110,8 @@ static int nf_flow_rule_match(struct nf_flow_match *match,
key->tp.dst = tuple->dst_port;
mask->tp.dst = 0xffff;
- match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+ match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_META) |
+ BIT(FLOW_DISSECTOR_KEY_CONTROL) |
BIT(FLOW_DISSECTOR_KEY_BASIC) |
BIT(FLOW_DISSECTOR_KEY_PORTS);
return 0;
@@ -166,24 +172,38 @@ static int flow_offload_eth_dst(struct net *net,
enum flow_offload_tuple_dir dir,
struct nf_flow_rule *flow_rule)
{
- const struct flow_offload_tuple *tuple = &flow->tuplehash[dir].tuple;
struct flow_action_entry *entry0 = flow_action_entry_next(flow_rule);
struct flow_action_entry *entry1 = flow_action_entry_next(flow_rule);
+ const void *daddr = &flow->tuplehash[!dir].tuple.src_v4;
+ const struct dst_entry *dst_cache;
+ unsigned char ha[ETH_ALEN];
struct neighbour *n;
u32 mask, val;
+ u8 nud_state;
u16 val16;
- n = dst_neigh_lookup(tuple->dst_cache, &tuple->dst_v4);
+ dst_cache = flow->tuplehash[dir].tuple.dst_cache;
+ n = dst_neigh_lookup(dst_cache, daddr);
if (!n)
return -ENOENT;
+ read_lock_bh(&n->lock);
+ nud_state = n->nud_state;
+ ether_addr_copy(ha, n->ha);
+ read_unlock_bh(&n->lock);
+
+ if (!(nud_state & NUD_VALID)) {
+ neigh_release(n);
+ return -ENOENT;
+ }
+
mask = ~0xffffffff;
- memcpy(&val, n->ha, 4);
+ memcpy(&val, ha, 4);
flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 0,
&val, &mask);
mask = ~0x0000ffff;
- memcpy(&val16, n->ha + 4, 2);
+ memcpy(&val16, ha + 4, 2);
val = val16;
flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4,
&val, &mask);
@@ -335,22 +355,26 @@ static void flow_offload_port_snat(struct net *net,
struct nf_flow_rule *flow_rule)
{
struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
- u32 mask = ~htonl(0xffff0000), port;
+ u32 mask, port;
u32 offset;
switch (dir) {
case FLOW_OFFLOAD_DIR_ORIGINAL:
port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port);
offset = 0; /* offsetof(struct tcphdr, source); */
+ port = htonl(port << 16);
+ mask = ~htonl(0xffff0000);
break;
case FLOW_OFFLOAD_DIR_REPLY:
port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port);
offset = 0; /* offsetof(struct tcphdr, dest); */
+ port = htonl(port);
+ mask = ~htonl(0xffff);
break;
default:
return;
}
- port = htonl(port << 16);
+
flow_offload_mangle(entry, flow_offload_l4proto(flow), offset,
&port, &mask);
}
@@ -361,22 +385,26 @@ static void flow_offload_port_dnat(struct net *net,
struct nf_flow_rule *flow_rule)
{
struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
- u32 mask = ~htonl(0xffff), port;
+ u32 mask, port;
u32 offset;
switch (dir) {
case FLOW_OFFLOAD_DIR_ORIGINAL:
- port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port);
- offset = 0; /* offsetof(struct tcphdr, source); */
+ port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port);
+ offset = 0; /* offsetof(struct tcphdr, dest); */
+ port = htonl(port);
+ mask = ~htonl(0xffff);
break;
case FLOW_OFFLOAD_DIR_REPLY:
- port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port);
- offset = 0; /* offsetof(struct tcphdr, dest); */
+ port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port);
+ offset = 0; /* offsetof(struct tcphdr, source); */
+ port = htonl(port << 16);
+ mask = ~htonl(0xffff0000);
break;
default:
return;
}
- port = htonl(port);
+
flow_offload_mangle(entry, flow_offload_l4proto(flow), offset,
&port, &mask);
}
@@ -422,16 +450,16 @@ int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow,
flow_offload_eth_dst(net, flow, dir, flow_rule) < 0)
return -1;
- if (flow->flags & FLOW_OFFLOAD_SNAT) {
+ if (test_bit(NF_FLOW_SNAT, &flow->flags)) {
flow_offload_ipv4_snat(net, flow, dir, flow_rule);
flow_offload_port_snat(net, flow, dir, flow_rule);
}
- if (flow->flags & FLOW_OFFLOAD_DNAT) {
+ if (test_bit(NF_FLOW_DNAT, &flow->flags)) {
flow_offload_ipv4_dnat(net, flow, dir, flow_rule);
flow_offload_port_dnat(net, flow, dir, flow_rule);
}
- if (flow->flags & FLOW_OFFLOAD_SNAT ||
- flow->flags & FLOW_OFFLOAD_DNAT)
+ if (test_bit(NF_FLOW_SNAT, &flow->flags) ||
+ test_bit(NF_FLOW_DNAT, &flow->flags))
flow_offload_ipv4_checksum(net, flow, flow_rule);
flow_offload_redirect(flow, dir, flow_rule);
@@ -448,11 +476,11 @@ int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow,
flow_offload_eth_dst(net, flow, dir, flow_rule) < 0)
return -1;
- if (flow->flags & FLOW_OFFLOAD_SNAT) {
+ if (test_bit(NF_FLOW_SNAT, &flow->flags)) {
flow_offload_ipv6_snat(net, flow, dir, flow_rule);
flow_offload_port_snat(net, flow, dir, flow_rule);
}
- if (flow->flags & FLOW_OFFLOAD_DNAT) {
+ if (test_bit(NF_FLOW_DNAT, &flow->flags)) {
flow_offload_ipv6_dnat(net, flow, dir, flow_rule);
flow_offload_port_dnat(net, flow, dir, flow_rule);
}
@@ -564,23 +592,25 @@ static void nf_flow_offload_init(struct flow_cls_offload *cls_flow,
cls_flow->cookie = (unsigned long)tuple;
}
-static int flow_offload_tuple_add(struct flow_offload_work *offload,
- struct nf_flow_rule *flow_rule,
- enum flow_offload_tuple_dir dir)
+static int nf_flow_offload_tuple(struct nf_flowtable *flowtable,
+ struct flow_offload *flow,
+ struct nf_flow_rule *flow_rule,
+ enum flow_offload_tuple_dir dir,
+ int priority, int cmd,
+ struct list_head *block_cb_list)
{
- struct nf_flowtable *flowtable = offload->flowtable;
struct flow_cls_offload cls_flow = {};
struct flow_block_cb *block_cb;
struct netlink_ext_ack extack;
__be16 proto = ETH_P_ALL;
int err, i = 0;
- nf_flow_offload_init(&cls_flow, proto, offload->priority,
- FLOW_CLS_REPLACE,
- &offload->flow->tuplehash[dir].tuple, &extack);
- cls_flow.rule = flow_rule->rule;
+ nf_flow_offload_init(&cls_flow, proto, priority, cmd,
+ &flow->tuplehash[dir].tuple, &extack);
+ if (cmd == FLOW_CLS_REPLACE)
+ cls_flow.rule = flow_rule->rule;
- list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) {
+ list_for_each_entry(block_cb, block_cb_list, list) {
err = block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow,
block_cb->cb_priv);
if (err < 0)
@@ -592,23 +622,22 @@ static int flow_offload_tuple_add(struct flow_offload_work *offload,
return i;
}
+static int flow_offload_tuple_add(struct flow_offload_work *offload,
+ struct nf_flow_rule *flow_rule,
+ enum flow_offload_tuple_dir dir)
+{
+ return nf_flow_offload_tuple(offload->flowtable, offload->flow,
+ flow_rule, dir, offload->priority,
+ FLOW_CLS_REPLACE,
+ &offload->flowtable->flow_block.cb_list);
+}
+
static void flow_offload_tuple_del(struct flow_offload_work *offload,
enum flow_offload_tuple_dir dir)
{
- struct nf_flowtable *flowtable = offload->flowtable;
- struct flow_cls_offload cls_flow = {};
- struct flow_block_cb *block_cb;
- struct netlink_ext_ack extack;
- __be16 proto = ETH_P_ALL;
-
- nf_flow_offload_init(&cls_flow, proto, offload->priority,
- FLOW_CLS_DESTROY,
- &offload->flow->tuplehash[dir].tuple, &extack);
-
- list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list)
- block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv);
-
- offload->flow->flags |= FLOW_OFFLOAD_HW_DEAD;
+ nf_flow_offload_tuple(offload->flowtable, offload->flow, NULL, dir,
+ offload->priority, FLOW_CLS_DESTROY,
+ &offload->flowtable->flow_block.cb_list);
}
static int flow_offload_rule_add(struct flow_offload_work *offload,
@@ -626,20 +655,20 @@ static int flow_offload_rule_add(struct flow_offload_work *offload,
return 0;
}
-static int flow_offload_work_add(struct flow_offload_work *offload)
+static void flow_offload_work_add(struct flow_offload_work *offload)
{
struct nf_flow_rule *flow_rule[FLOW_OFFLOAD_DIR_MAX];
int err;
err = nf_flow_offload_alloc(offload, flow_rule);
if (err < 0)
- return -ENOMEM;
+ return;
err = flow_offload_rule_add(offload, flow_rule);
+ if (err < 0)
+ set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags);
nf_flow_offload_destroy(flow_rule);
-
- return err;
}
static void flow_offload_work_del(struct flow_offload_work *offload)
@@ -684,7 +713,6 @@ static void flow_offload_work_handler(struct work_struct *work)
{
struct flow_offload_work *offload, *next;
LIST_HEAD(offload_pending_list);
- int ret;
spin_lock_bh(&flow_offload_pending_list_lock);
list_replace_init(&flow_offload_pending_list, &offload_pending_list);
@@ -693,9 +721,7 @@ static void flow_offload_work_handler(struct work_struct *work)
list_for_each_entry_safe(offload, next, &offload_pending_list, list) {
switch (offload->cmd) {
case FLOW_CLS_REPLACE:
- ret = flow_offload_work_add(offload);
- if (ret < 0)
- offload->flow->flags &= ~FLOW_OFFLOAD_HW;
+ flow_offload_work_add(offload);
break;
case FLOW_CLS_DESTROY:
flow_offload_work_del(offload);
@@ -720,20 +746,33 @@ static void flow_offload_queue_work(struct flow_offload_work *offload)
schedule_work(&nf_flow_offload_work);
}
-void nf_flow_offload_add(struct nf_flowtable *flowtable,
- struct flow_offload *flow)
+static struct flow_offload_work *
+nf_flow_offload_work_alloc(struct nf_flowtable *flowtable,
+ struct flow_offload *flow, unsigned int cmd)
{
struct flow_offload_work *offload;
offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC);
if (!offload)
- return;
+ return NULL;
- offload->cmd = FLOW_CLS_REPLACE;
+ offload->cmd = cmd;
offload->flow = flow;
offload->priority = flowtable->priority;
offload->flowtable = flowtable;
- flow->flags |= FLOW_OFFLOAD_HW;
+
+ return offload;
+}
+
+
+void nf_flow_offload_add(struct nf_flowtable *flowtable,
+ struct flow_offload *flow)
+{
+ struct flow_offload_work *offload;
+
+ offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_REPLACE);
+ if (!offload)
+ return;
flow_offload_queue_work(offload);
}
@@ -743,15 +782,11 @@ void nf_flow_offload_del(struct nf_flowtable *flowtable,
{
struct flow_offload_work *offload;
- offload = kzalloc(sizeof(struct flow_offload_work), GFP_ATOMIC);
+ offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_DESTROY);
if (!offload)
return;
- offload->cmd = FLOW_CLS_DESTROY;
- offload->flow = flow;
- offload->flow->flags |= FLOW_OFFLOAD_HW_DYING;
- offload->flowtable = flowtable;
-
+ set_bit(NF_FLOW_HW_DYING, &flow->flags);
flow_offload_queue_work(offload);
}
@@ -759,27 +794,22 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
struct flow_offload *flow)
{
struct flow_offload_work *offload;
- s64 delta;
+ __s32 delta;
- delta = flow->timeout - jiffies;
- if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10) ||
- flow->flags & FLOW_OFFLOAD_HW_DYING)
+ delta = nf_flow_timeout_delta(flow->timeout);
+ if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10))
return;
- offload = kzalloc(sizeof(struct flow_offload_work), GFP_ATOMIC);
+ offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_STATS);
if (!offload)
return;
- offload->cmd = FLOW_CLS_STATS;
- offload->flow = flow;
- offload->flowtable = flowtable;
-
flow_offload_queue_work(offload);
}
void nf_flow_table_offload_flush(struct nf_flowtable *flowtable)
{
- if (flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD)
+ if (nf_flowtable_hw_offload(flowtable))
flush_work(&nf_flow_offload_work);
}
@@ -808,28 +838,44 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable,
return err;
}
-int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
- struct net_device *dev,
- enum flow_block_command cmd)
+static int nf_flow_table_offload_cmd(struct flow_block_offload *bo,
+ struct nf_flowtable *flowtable,
+ struct net_device *dev,
+ enum flow_block_command cmd,
+ struct netlink_ext_ack *extack)
{
- struct netlink_ext_ack extack = {};
- struct flow_block_offload bo = {};
int err;
- if (!(flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD))
+ if (!nf_flowtable_hw_offload(flowtable))
return 0;
if (!dev->netdev_ops->ndo_setup_tc)
return -EOPNOTSUPP;
- bo.net = dev_net(dev);
- bo.block = &flowtable->flow_block;
- bo.command = cmd;
- bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
- bo.extack = &extack;
- INIT_LIST_HEAD(&bo.cb_list);
+ memset(bo, 0, sizeof(*bo));
+ bo->net = dev_net(dev);
+ bo->block = &flowtable->flow_block;
+ bo->command = cmd;
+ bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+ bo->extack = extack;
+ INIT_LIST_HEAD(&bo->cb_list);
- err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, &bo);
+ err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo);
+ if (err < 0)
+ return err;
+
+ return 0;
+}
+
+int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
+ struct net_device *dev,
+ enum flow_block_command cmd)
+{
+ struct netlink_ext_ack extack = {};
+ struct flow_block_offload bo;
+ int err;
+
+ err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack);
if (err < 0)
return err;
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 0a59c14..64eedc1 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -233,6 +233,19 @@ icmp_manip_pkt(struct sk_buff *skb,
return false;
hdr = (struct icmphdr *)(skb->data + hdroff);
+ switch (hdr->type) {
+ case ICMP_ECHO:
+ case ICMP_ECHOREPLY:
+ case ICMP_TIMESTAMP:
+ case ICMP_TIMESTAMPREPLY:
+ case ICMP_INFO_REQUEST:
+ case ICMP_INFO_REPLY:
+ case ICMP_ADDRESS:
+ case ICMP_ADDRESSREPLY:
+ break;
+ default:
+ return true;
+ }
inet_proto_csum_replace2(&hdr->checksum, skb,
hdr->un.echo.id, tuple->src.u.icmp.id, false);
hdr->un.echo.id = tuple->src.u.icmp.id;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 273f383..d1318bd 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -22,6 +22,8 @@
#include <net/net_namespace.h>
#include <net/sock.h>
+#define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-"))
+
static LIST_HEAD(nf_tables_expressions);
static LIST_HEAD(nf_tables_objects);
static LIST_HEAD(nf_tables_flowtables);
@@ -551,46 +553,70 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table)
static const struct nft_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX];
static const struct nft_chain_type *
+__nft_chain_type_get(u8 family, enum nft_chain_types type)
+{
+ if (family >= NFPROTO_NUMPROTO ||
+ type >= NFT_CHAIN_T_MAX)
+ return NULL;
+
+ return chain_type[family][type];
+}
+
+static const struct nft_chain_type *
__nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family)
{
+ const struct nft_chain_type *type;
int i;
for (i = 0; i < NFT_CHAIN_T_MAX; i++) {
- if (chain_type[family][i] != NULL &&
- !nla_strcmp(nla, chain_type[family][i]->name))
- return chain_type[family][i];
+ type = __nft_chain_type_get(family, i);
+ if (!type)
+ continue;
+ if (!nla_strcmp(nla, type->name))
+ return type;
}
return NULL;
}
-/*
- * Loading a module requires dropping mutex that guards the
- * transaction.
- * We first need to abort any pending transactions as once
- * mutex is unlocked a different client could start a new
- * transaction. It must not see any 'future generation'
- * changes * as these changes will never happen.
- */
-#ifdef CONFIG_MODULES
-static int __nf_tables_abort(struct net *net);
+struct nft_module_request {
+ struct list_head list;
+ char module[MODULE_NAME_LEN];
+ bool done;
+};
-static void nft_request_module(struct net *net, const char *fmt, ...)
+#ifdef CONFIG_MODULES
+static int nft_request_module(struct net *net, const char *fmt, ...)
{
char module_name[MODULE_NAME_LEN];
+ struct nft_module_request *req;
va_list args;
int ret;
- __nf_tables_abort(net);
-
va_start(args, fmt);
ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
va_end(args);
- if (WARN(ret >= MODULE_NAME_LEN, "truncated: '%s' (len %d)", module_name, ret))
- return;
+ if (ret >= MODULE_NAME_LEN)
+ return 0;
- mutex_unlock(&net->nft.commit_mutex);
- request_module("%s", module_name);
- mutex_lock(&net->nft.commit_mutex);
+ list_for_each_entry(req, &net->nft.module_list, list) {
+ if (!strcmp(req->module, module_name)) {
+ if (req->done)
+ return 0;
+
+ /* A request to load this module already exists. */
+ return -EAGAIN;
+ }
+ }
+
+ req = kmalloc(sizeof(*req), GFP_KERNEL);
+ if (!req)
+ return -ENOMEM;
+
+ req->done = false;
+ strlcpy(req->module, module_name, MODULE_NAME_LEN);
+ list_add_tail(&req->list, &net->nft.module_list);
+
+ return -EAGAIN;
}
#endif
@@ -614,10 +640,9 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla,
lockdep_nfnl_nft_mutex_not_held();
#ifdef CONFIG_MODULES
if (autoload) {
- nft_request_module(net, "nft-chain-%u-%.*s", family,
- nla_len(nla), (const char *)nla_data(nla));
- type = __nf_tables_chain_type_lookup(nla, family);
- if (type != NULL)
+ if (nft_request_module(net, "nft-chain-%u-%.*s", family,
+ nla_len(nla),
+ (const char *)nla_data(nla)) == -EAGAIN)
return ERR_PTR(-EAGAIN);
}
#endif
@@ -1045,12 +1070,18 @@ static int nft_flush_table(struct nft_ctx *ctx)
}
list_for_each_entry_safe(flowtable, nft, &ctx->table->flowtables, list) {
+ if (!nft_is_active_next(ctx->net, flowtable))
+ continue;
+
err = nft_delflowtable(ctx, flowtable);
if (err < 0)
goto out;
}
list_for_each_entry_safe(obj, ne, &ctx->table->objects, list) {
+ if (!nft_is_active_next(ctx->net, obj))
+ continue;
+
err = nft_delobj(ctx, obj);
if (err < 0)
goto out;
@@ -1153,11 +1184,8 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx)
void nft_register_chain_type(const struct nft_chain_type *ctype)
{
- if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO))
- return;
-
nfnl_lock(NFNL_SUBSYS_NFTABLES);
- if (WARN_ON(chain_type[ctype->family][ctype->type] != NULL)) {
+ if (WARN_ON(__nft_chain_type_get(ctype->family, ctype->type))) {
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
return;
}
@@ -1241,7 +1269,8 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
.len = NFT_CHAIN_MAXNAMELEN - 1 },
[NFTA_CHAIN_HOOK] = { .type = NLA_NESTED },
[NFTA_CHAIN_POLICY] = { .type = NLA_U32 },
- [NFTA_CHAIN_TYPE] = { .type = NLA_STRING },
+ [NFTA_CHAIN_TYPE] = { .type = NLA_STRING,
+ .len = NFT_MODULE_AUTOLOAD_LIMIT },
[NFTA_CHAIN_COUNTERS] = { .type = NLA_NESTED },
[NFTA_CHAIN_FLAGS] = { .type = NLA_U32 },
};
@@ -1676,6 +1705,7 @@ static int nf_tables_parse_netdev_hooks(struct net *net,
goto err_hook;
}
if (nft_hook_list_find(hook_list, hook)) {
+ kfree(hook);
err = -EEXIST;
goto err_hook;
}
@@ -1757,7 +1787,10 @@ static int nft_chain_parse_hook(struct net *net,
hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY]));
- type = chain_type[family][NFT_CHAIN_T_DEFAULT];
+ type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT);
+ if (!type)
+ return -EOPNOTSUPP;
+
if (nla[NFTA_CHAIN_TYPE]) {
type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE],
family, autoload);
@@ -2317,9 +2350,8 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family,
static int nft_expr_type_request_module(struct net *net, u8 family,
struct nlattr *nla)
{
- nft_request_module(net, "nft-expr-%u-%.*s", family,
- nla_len(nla), (char *)nla_data(nla));
- if (__nft_expr_type_get(family, nla))
+ if (nft_request_module(net, "nft-expr-%u-%.*s", family,
+ nla_len(nla), (char *)nla_data(nla)) == -EAGAIN)
return -EAGAIN;
return 0;
@@ -2345,9 +2377,9 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net,
if (nft_expr_type_request_module(net, family, nla) == -EAGAIN)
return ERR_PTR(-EAGAIN);
- nft_request_module(net, "nft-expr-%.*s",
- nla_len(nla), (char *)nla_data(nla));
- if (__nft_expr_type_get(family, nla))
+ if (nft_request_module(net, "nft-expr-%.*s",
+ nla_len(nla),
+ (char *)nla_data(nla)) == -EAGAIN)
return ERR_PTR(-EAGAIN);
}
#endif
@@ -2355,7 +2387,8 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net,
}
static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = {
- [NFTA_EXPR_NAME] = { .type = NLA_STRING },
+ [NFTA_EXPR_NAME] = { .type = NLA_STRING,
+ .len = NFT_MODULE_AUTOLOAD_LIMIT },
[NFTA_EXPR_DATA] = { .type = NLA_NESTED },
};
@@ -2437,9 +2470,10 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
err = PTR_ERR(ops);
#ifdef CONFIG_MODULES
if (err == -EAGAIN)
- nft_expr_type_request_module(ctx->net,
- ctx->family,
- tb[NFTA_EXPR_NAME]);
+ if (nft_expr_type_request_module(ctx->net,
+ ctx->family,
+ tb[NFTA_EXPR_NAME]) != -EAGAIN)
+ err = -ENOENT;
#endif
goto err1;
}
@@ -3276,8 +3310,7 @@ nft_select_set_ops(const struct nft_ctx *ctx,
lockdep_nfnl_nft_mutex_not_held();
#ifdef CONFIG_MODULES
if (list_empty(&nf_tables_set_types)) {
- nft_request_module(ctx->net, "nft-set");
- if (!list_empty(&nf_tables_set_types))
+ if (nft_request_module(ctx->net, "nft-set") == -EAGAIN)
return ERR_PTR(-EAGAIN);
}
#endif
@@ -3358,6 +3391,7 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = {
[NFTA_SET_DESC_SIZE] = { .type = NLA_U32 },
+ [NFTA_SET_DESC_CONCAT] = { .type = NLA_NESTED },
};
static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
@@ -3524,6 +3558,33 @@ static __be64 nf_jiffies64_to_msecs(u64 input)
return cpu_to_be64(jiffies64_to_msecs(input));
}
+static int nf_tables_fill_set_concat(struct sk_buff *skb,
+ const struct nft_set *set)
+{
+ struct nlattr *concat, *field;
+ int i;
+
+ concat = nla_nest_start_noflag(skb, NFTA_SET_DESC_CONCAT);
+ if (!concat)
+ return -ENOMEM;
+
+ for (i = 0; i < set->field_count; i++) {
+ field = nla_nest_start_noflag(skb, NFTA_LIST_ELEM);
+ if (!field)
+ return -ENOMEM;
+
+ if (nla_put_be32(skb, NFTA_SET_FIELD_LEN,
+ htonl(set->field_len[i])))
+ return -ENOMEM;
+
+ nla_nest_end(skb, field);
+ }
+
+ nla_nest_end(skb, concat);
+
+ return 0;
+}
+
static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
const struct nft_set *set, u16 event, u16 flags)
{
@@ -3587,11 +3648,17 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
goto nla_put_failure;
desc = nla_nest_start_noflag(skb, NFTA_SET_DESC);
+
if (desc == NULL)
goto nla_put_failure;
if (set->size &&
nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(set->size)))
goto nla_put_failure;
+
+ if (set->field_count > 1 &&
+ nf_tables_fill_set_concat(skb, set))
+ goto nla_put_failure;
+
nla_nest_end(skb, desc);
nlmsg_end(skb, nlh);
@@ -3764,6 +3831,53 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk,
return err;
}
+static const struct nla_policy nft_concat_policy[NFTA_SET_FIELD_MAX + 1] = {
+ [NFTA_SET_FIELD_LEN] = { .type = NLA_U32 },
+};
+
+static int nft_set_desc_concat_parse(const struct nlattr *attr,
+ struct nft_set_desc *desc)
+{
+ struct nlattr *tb[NFTA_SET_FIELD_MAX + 1];
+ u32 len;
+ int err;
+
+ err = nla_parse_nested_deprecated(tb, NFTA_SET_FIELD_MAX, attr,
+ nft_concat_policy, NULL);
+ if (err < 0)
+ return err;
+
+ if (!tb[NFTA_SET_FIELD_LEN])
+ return -EINVAL;
+
+ len = ntohl(nla_get_be32(tb[NFTA_SET_FIELD_LEN]));
+
+ if (len * BITS_PER_BYTE / 32 > NFT_REG32_COUNT)
+ return -E2BIG;
+
+ desc->field_len[desc->field_count++] = len;
+
+ return 0;
+}
+
+static int nft_set_desc_concat(struct nft_set_desc *desc,
+ const struct nlattr *nla)
+{
+ struct nlattr *attr;
+ int rem, err;
+
+ nla_for_each_nested(attr, nla, rem) {
+ if (nla_type(attr) != NFTA_LIST_ELEM)
+ return -EINVAL;
+
+ err = nft_set_desc_concat_parse(attr, desc);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
+}
+
static int nf_tables_set_desc_parse(struct nft_set_desc *desc,
const struct nlattr *nla)
{
@@ -3777,8 +3891,10 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc,
if (da[NFTA_SET_DESC_SIZE] != NULL)
desc->size = ntohl(nla_get_be32(da[NFTA_SET_DESC_SIZE]));
+ if (da[NFTA_SET_DESC_CONCAT])
+ err = nft_set_desc_concat(desc, da[NFTA_SET_DESC_CONCAT]);
- return 0;
+ return err;
}
static int nf_tables_newset(struct net *net, struct sock *nlsk,
@@ -3801,6 +3917,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
unsigned char *udata;
u16 udlen;
int err;
+ int i;
if (nla[NFTA_SET_TABLE] == NULL ||
nla[NFTA_SET_NAME] == NULL ||
@@ -3979,6 +4096,10 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
set->gc_int = gc_int;
set->handle = nf_tables_alloc_handle(table);
+ set->field_count = desc.field_count;
+ for (i = 0; i < desc.field_count; i++)
+ set->field_len[i] = desc.field_len[i];
+
err = ops->init(set, &desc, nla);
if (err < 0)
goto err3;
@@ -4182,6 +4303,9 @@ const struct nft_set_ext_type nft_set_ext_types[] = {
.len = sizeof(struct nft_userdata),
.align = __alignof__(struct nft_userdata),
},
+ [NFT_SET_EXT_KEY_END] = {
+ .align = __alignof__(u32),
+ },
};
EXPORT_SYMBOL_GPL(nft_set_ext_types);
@@ -4198,7 +4322,9 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = {
[NFTA_SET_ELEM_USERDATA] = { .type = NLA_BINARY,
.len = NFT_USERDATA_MAXLEN },
[NFTA_SET_ELEM_EXPR] = { .type = NLA_NESTED },
- [NFTA_SET_ELEM_OBJREF] = { .type = NLA_STRING },
+ [NFTA_SET_ELEM_OBJREF] = { .type = NLA_STRING,
+ .len = NFT_OBJ_MAXNAMELEN - 1 },
+ [NFTA_SET_ELEM_KEY_END] = { .type = NLA_NESTED },
};
static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = {
@@ -4248,6 +4374,11 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
NFT_DATA_VALUE, set->klen) < 0)
goto nla_put_failure;
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END) &&
+ nft_data_dump(skb, NFTA_SET_ELEM_KEY_END, nft_set_ext_key_end(ext),
+ NFT_DATA_VALUE, set->klen) < 0)
+ goto nla_put_failure;
+
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext),
set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE,
@@ -4490,11 +4621,28 @@ static int nft_setelem_parse_flags(const struct nft_set *set,
return 0;
}
+static int nft_setelem_parse_key(struct nft_ctx *ctx, struct nft_set *set,
+ struct nft_data *key, struct nlattr *attr)
+{
+ struct nft_data_desc desc;
+ int err;
+
+ err = nft_data_init(ctx, key, NFT_DATA_VALUE_MAXLEN, &desc, attr);
+ if (err < 0)
+ return err;
+
+ if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) {
+ nft_data_release(key, desc.type);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
const struct nlattr *attr)
{
struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
- struct nft_data_desc desc;
struct nft_set_elem elem;
struct sk_buff *skb;
uint32_t flags = 0;
@@ -4513,15 +4661,16 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
if (err < 0)
return err;
- err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &desc,
- nla[NFTA_SET_ELEM_KEY]);
+ err = nft_setelem_parse_key(ctx, set, &elem.key.val,
+ nla[NFTA_SET_ELEM_KEY]);
if (err < 0)
return err;
- err = -EINVAL;
- if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) {
- nft_data_release(&elem.key.val, desc.type);
- return err;
+ if (nla[NFTA_SET_ELEM_KEY_END]) {
+ err = nft_setelem_parse_key(ctx, set, &elem.key_end.val,
+ nla[NFTA_SET_ELEM_KEY_END]);
+ if (err < 0)
+ return err;
}
priv = set->ops->get(ctx->net, set, &elem, flags);
@@ -4649,8 +4798,8 @@ static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx,
void *nft_set_elem_init(const struct nft_set *set,
const struct nft_set_ext_tmpl *tmpl,
- const u32 *key, const u32 *data,
- u64 timeout, u64 expiration, gfp_t gfp)
+ const u32 *key, const u32 *key_end,
+ const u32 *data, u64 timeout, u64 expiration, gfp_t gfp)
{
struct nft_set_ext *ext;
void *elem;
@@ -4663,6 +4812,8 @@ void *nft_set_elem_init(const struct nft_set *set,
nft_set_ext_init(ext, tmpl);
memcpy(nft_set_ext_key(ext), key, set->klen);
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END))
+ memcpy(nft_set_ext_key_end(ext), key_end, set->klen);
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
memcpy(nft_set_ext_data(ext), data, set->dlen);
if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
@@ -4722,13 +4873,13 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
{
struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
u8 genmask = nft_genmask_next(ctx->net);
- struct nft_data_desc d1, d2;
struct nft_set_ext_tmpl tmpl;
struct nft_set_ext *ext, *ext2;
struct nft_set_elem elem;
struct nft_set_binding *binding;
struct nft_object *obj = NULL;
struct nft_userdata *udata;
+ struct nft_data_desc desc;
struct nft_data data;
enum nft_registers dreg;
struct nft_trans *trans;
@@ -4794,15 +4945,22 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
return err;
}
- err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &d1,
- nla[NFTA_SET_ELEM_KEY]);
+ err = nft_setelem_parse_key(ctx, set, &elem.key.val,
+ nla[NFTA_SET_ELEM_KEY]);
if (err < 0)
- goto err1;
- err = -EINVAL;
- if (d1.type != NFT_DATA_VALUE || d1.len != set->klen)
- goto err2;
+ return err;
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, d1.len);
+ nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+
+ if (nla[NFTA_SET_ELEM_KEY_END]) {
+ err = nft_setelem_parse_key(ctx, set, &elem.key_end.val,
+ nla[NFTA_SET_ELEM_KEY_END]);
+ if (err < 0)
+ goto err_parse_key;
+
+ nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+ }
+
if (timeout > 0) {
nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION);
if (timeout != set->timeout)
@@ -4812,27 +4970,27 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
if (nla[NFTA_SET_ELEM_OBJREF] != NULL) {
if (!(set->flags & NFT_SET_OBJECT)) {
err = -EINVAL;
- goto err2;
+ goto err_parse_key_end;
}
obj = nft_obj_lookup(ctx->net, ctx->table,
nla[NFTA_SET_ELEM_OBJREF],
set->objtype, genmask);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
- goto err2;
+ goto err_parse_key_end;
}
nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF);
}
if (nla[NFTA_SET_ELEM_DATA] != NULL) {
- err = nft_data_init(ctx, &data, sizeof(data), &d2,
+ err = nft_data_init(ctx, &data, sizeof(data), &desc,
nla[NFTA_SET_ELEM_DATA]);
if (err < 0)
- goto err2;
+ goto err_parse_key_end;
err = -EINVAL;
- if (set->dtype != NFT_DATA_VERDICT && d2.len != set->dlen)
- goto err3;
+ if (set->dtype != NFT_DATA_VERDICT && desc.len != set->dlen)
+ goto err_parse_data;
dreg = nft_type_to_reg(set->dtype);
list_for_each_entry(binding, &set->bindings, list) {
@@ -4848,18 +5006,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
err = nft_validate_register_store(&bind_ctx, dreg,
&data,
- d2.type, d2.len);
+ desc.type, desc.len);
if (err < 0)
- goto err3;
+ goto err_parse_data;
- if (d2.type == NFT_DATA_VERDICT &&
+ if (desc.type == NFT_DATA_VERDICT &&
(data.verdict.code == NFT_GOTO ||
data.verdict.code == NFT_JUMP))
nft_validate_state_update(ctx->net,
NFT_VALIDATE_NEED);
}
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, d2.len);
+ nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len);
}
/* The full maximum length of userdata can exceed the maximum
@@ -4875,10 +5033,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
}
err = -ENOMEM;
- elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, data.data,
+ elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data,
+ elem.key_end.val.data, data.data,
timeout, expiration, GFP_KERNEL);
if (elem.priv == NULL)
- goto err3;
+ goto err_parse_data;
ext = nft_set_elem_ext(set, elem.priv);
if (flags)
@@ -4895,7 +5054,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
if (trans == NULL)
- goto err4;
+ goto err_trans;
ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK;
err = set->ops->insert(ctx->net, set, &elem, &ext2);
@@ -4906,7 +5065,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^
nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) {
err = -EBUSY;
- goto err5;
+ goto err_element_clash;
}
if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) &&
@@ -4919,33 +5078,35 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
else if (!(nlmsg_flags & NLM_F_EXCL))
err = 0;
}
- goto err5;
+ goto err_element_clash;
}
if (set->size &&
!atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) {
err = -ENFILE;
- goto err6;
+ goto err_set_full;
}
nft_trans_elem(trans) = elem;
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
-err6:
+err_set_full:
set->ops->remove(ctx->net, set, &elem);
-err5:
+err_element_clash:
kfree(trans);
-err4:
+err_trans:
if (obj)
obj->use--;
kfree(elem.priv);
-err3:
+err_parse_data:
if (nla[NFTA_SET_ELEM_DATA] != NULL)
- nft_data_release(&data, d2.type);
-err2:
- nft_data_release(&elem.key.val, d1.type);
-err1:
+ nft_data_release(&data, desc.type);
+err_parse_key_end:
+ nft_data_release(&elem.key_end.val, NFT_DATA_VALUE);
+err_parse_key:
+ nft_data_release(&elem.key.val, NFT_DATA_VALUE);
+
return err;
}
@@ -5040,7 +5201,6 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
{
struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
struct nft_set_ext_tmpl tmpl;
- struct nft_data_desc desc;
struct nft_set_elem elem;
struct nft_set_ext *ext;
struct nft_trans *trans;
@@ -5051,11 +5211,10 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr,
nft_set_elem_policy, NULL);
if (err < 0)
- goto err1;
+ return err;
- err = -EINVAL;
if (nla[NFTA_SET_ELEM_KEY] == NULL)
- goto err1;
+ return -EINVAL;
nft_set_ext_prepare(&tmpl);
@@ -5065,37 +5224,41 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
if (flags != 0)
nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
- err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &desc,
- nla[NFTA_SET_ELEM_KEY]);
+ err = nft_setelem_parse_key(ctx, set, &elem.key.val,
+ nla[NFTA_SET_ELEM_KEY]);
if (err < 0)
- goto err1;
+ return err;
- err = -EINVAL;
- if (desc.type != NFT_DATA_VALUE || desc.len != set->klen)
- goto err2;
+ nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, desc.len);
+ if (nla[NFTA_SET_ELEM_KEY_END]) {
+ err = nft_setelem_parse_key(ctx, set, &elem.key_end.val,
+ nla[NFTA_SET_ELEM_KEY_END]);
+ if (err < 0)
+ return err;
+
+ nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+ }
err = -ENOMEM;
- elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, NULL, 0,
- 0, GFP_KERNEL);
+ elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data,
+ elem.key_end.val.data, NULL, 0, 0,
+ GFP_KERNEL);
if (elem.priv == NULL)
- goto err2;
+ goto fail_elem;
ext = nft_set_elem_ext(set, elem.priv);
if (flags)
*nft_set_ext_flags(ext) = flags;
trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set);
- if (trans == NULL) {
- err = -ENOMEM;
- goto err3;
- }
+ if (trans == NULL)
+ goto fail_trans;
priv = set->ops->deactivate(ctx->net, set, &elem);
if (priv == NULL) {
err = -ENOENT;
- goto err4;
+ goto fail_ops;
}
kfree(elem.priv);
elem.priv = priv;
@@ -5106,13 +5269,12 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
-err4:
+fail_ops:
kfree(trans);
-err3:
+fail_trans:
kfree(elem.priv);
-err2:
- nft_data_release(&elem.key.val, desc.type);
-err1:
+fail_elem:
+ nft_data_release(&elem.key.val, NFT_DATA_VALUE);
return err;
}
@@ -5402,8 +5564,7 @@ nft_obj_type_get(struct net *net, u32 objtype)
lockdep_nfnl_nft_mutex_not_held();
#ifdef CONFIG_MODULES
if (type == NULL) {
- nft_request_module(net, "nft-obj-%u", objtype);
- if (__nft_obj_type_get(objtype))
+ if (nft_request_module(net, "nft-obj-%u", objtype) == -EAGAIN)
return ERR_PTR(-EAGAIN);
}
#endif
@@ -5976,14 +6137,14 @@ nft_flowtable_type_get(struct net *net, u8 family)
lockdep_nfnl_nft_mutex_not_held();
#ifdef CONFIG_MODULES
if (type == NULL) {
- nft_request_module(net, "nf-flowtable-%u", family);
- if (__nft_flowtable_type_get(family))
+ if (nft_request_module(net, "nf-flowtable-%u", family) == -EAGAIN)
return ERR_PTR(-EAGAIN);
}
#endif
return ERR_PTR(-ENOENT);
}
+/* Only called from error and netdev event paths. */
static void nft_unregister_flowtable_hook(struct net *net,
struct nft_flowtable *flowtable,
struct nft_hook *hook)
@@ -5999,7 +6160,7 @@ static void nft_unregister_flowtable_net_hooks(struct net *net,
struct nft_hook *hook;
list_for_each_entry(hook, &flowtable->hook_list, list)
- nft_unregister_flowtable_hook(net, flowtable, hook);
+ nf_unregister_net_hook(net, &hook->ops);
}
static int nft_register_flowtable_net_hooks(struct net *net,
@@ -6448,12 +6609,14 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
{
struct nft_hook *hook, *next;
+ flowtable->data.type->free(&flowtable->data);
list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) {
+ flowtable->data.type->setup(&flowtable->data, hook->ops.dev,
+ FLOW_BLOCK_UNBIND);
list_del_rcu(&hook->list);
kfree(hook);
}
kfree(flowtable->name);
- flowtable->data.type->free(&flowtable->data);
module_put(flowtable->data.type->owner);
kfree(flowtable);
}
@@ -6497,6 +6660,7 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev,
if (hook->ops.dev != dev)
continue;
+ /* flow_offload_netdev_event() cleans up entries for us. */
nft_unregister_flowtable_hook(dev_net(dev), flowtable, hook);
list_del_rcu(&hook->list);
kfree_rcu(hook, rcu);
@@ -6975,6 +7139,18 @@ static void nft_chain_del(struct nft_chain *chain)
list_del_rcu(&chain->list);
}
+static void nf_tables_module_autoload_cleanup(struct net *net)
+{
+ struct nft_module_request *req, *next;
+
+ WARN_ON_ONCE(!list_empty(&net->nft.commit_list));
+ list_for_each_entry_safe(req, next, &net->nft.module_list, list) {
+ WARN_ON_ONCE(!req->done);
+ list_del(&req->list);
+ kfree(req);
+ }
+}
+
static void nf_tables_commit_release(struct net *net)
{
struct nft_trans *trans;
@@ -6987,6 +7163,7 @@ static void nf_tables_commit_release(struct net *net)
* to prevent expensive synchronize_rcu() in commit phase.
*/
if (list_empty(&net->nft.commit_list)) {
+ nf_tables_module_autoload_cleanup(net);
mutex_unlock(&net->nft.commit_mutex);
return;
}
@@ -7001,6 +7178,7 @@ static void nf_tables_commit_release(struct net *net)
list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list);
spin_unlock(&nf_tables_destroy_list_lock);
+ nf_tables_module_autoload_cleanup(net);
mutex_unlock(&net->nft.commit_mutex);
schedule_work(&trans_destroy_work);
@@ -7192,6 +7370,26 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
return 0;
}
+static void nf_tables_module_autoload(struct net *net)
+{
+ struct nft_module_request *req, *next;
+ LIST_HEAD(module_list);
+
+ list_splice_init(&net->nft.module_list, &module_list);
+ mutex_unlock(&net->nft.commit_mutex);
+ list_for_each_entry_safe(req, next, &module_list, list) {
+ if (req->done) {
+ list_del(&req->list);
+ kfree(req);
+ } else {
+ request_module("%s", req->module);
+ req->done = true;
+ }
+ }
+ mutex_lock(&net->nft.commit_mutex);
+ list_splice(&module_list, &net->nft.module_list);
+}
+
static void nf_tables_abort_release(struct nft_trans *trans)
{
switch (trans->msg_type) {
@@ -7221,7 +7419,7 @@ static void nf_tables_abort_release(struct nft_trans *trans)
kfree(trans);
}
-static int __nf_tables_abort(struct net *net)
+static int __nf_tables_abort(struct net *net, bool autoload)
{
struct nft_trans *trans, *next;
struct nft_trans_elem *te;
@@ -7343,6 +7541,11 @@ static int __nf_tables_abort(struct net *net)
nf_tables_abort_release(trans);
}
+ if (autoload)
+ nf_tables_module_autoload(net);
+ else
+ nf_tables_module_autoload_cleanup(net);
+
return 0;
}
@@ -7351,9 +7554,9 @@ static void nf_tables_cleanup(struct net *net)
nft_validate_state_update(net, NFT_VALIDATE_SKIP);
}
-static int nf_tables_abort(struct net *net, struct sk_buff *skb)
+static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload)
{
- int ret = __nf_tables_abort(net);
+ int ret = __nf_tables_abort(net, autoload);
mutex_unlock(&net->nft.commit_mutex);
@@ -7948,6 +8151,7 @@ static int __net_init nf_tables_init_net(struct net *net)
{
INIT_LIST_HEAD(&net->nft.tables);
INIT_LIST_HEAD(&net->nft.commit_list);
+ INIT_LIST_HEAD(&net->nft.module_list);
mutex_init(&net->nft.commit_mutex);
net->nft.base_seq = 1;
net->nft.validate_state = NFT_VALIDATE_SKIP;
@@ -7959,7 +8163,7 @@ static void __net_exit nf_tables_exit_net(struct net *net)
{
mutex_lock(&net->nft.commit_mutex);
if (!list_empty(&net->nft.commit_list))
- __nf_tables_abort(net);
+ __nf_tables_abort(net, false);
__nft_release_tables(net);
mutex_unlock(&net->nft.commit_mutex);
WARN_ON_ONCE(!list_empty(&net->nft.tables));
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index a9ea29a..2bb2848 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -564,7 +564,7 @@ static void nft_indr_block_cb(struct net_device *dev,
mutex_lock(&net->nft.commit_mutex);
chain = __nft_offload_get_chain(dev);
- if (chain) {
+ if (chain && chain->flags & NFT_CHAIN_HW_OFFLOAD) {
struct nft_base_chain *basechain;
basechain = nft_base_chain(chain);
diff --git a/net/netfilter/nf_tables_set_core.c b/net/netfilter/nf_tables_set_core.c
index a9fce8d..586b621 100644
--- a/net/netfilter/nf_tables_set_core.c
+++ b/net/netfilter/nf_tables_set_core.c
@@ -9,12 +9,14 @@ static int __init nf_tables_set_module_init(void)
nft_register_set(&nft_set_rhash_type);
nft_register_set(&nft_set_bitmap_type);
nft_register_set(&nft_set_rbtree_type);
+ nft_register_set(&nft_set_pipapo_type);
return 0;
}
static void __exit nf_tables_set_module_exit(void)
{
+ nft_unregister_set(&nft_set_pipapo_type);
nft_unregister_set(&nft_set_rbtree_type);
nft_unregister_set(&nft_set_bitmap_type);
nft_unregister_set(&nft_set_rhash_type);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 4abbb45..99127e2 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -476,7 +476,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
}
done:
if (status & NFNL_BATCH_REPLAY) {
- ss->abort(net, oskb);
+ ss->abort(net, oskb, true);
nfnl_err_reset(&err_list);
kfree_skb(skb);
module_put(ss->owner);
@@ -487,11 +487,11 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
status |= NFNL_BATCH_REPLAY;
goto done;
} else if (err) {
- ss->abort(net, oskb);
+ ss->abort(net, oskb, false);
netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
}
} else {
- ss->abort(net, oskb);
+ ss->abort(net, oskb, false);
}
if (ss->cleanup)
ss->cleanup(net);
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index feabdfb..76535fd 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -778,7 +778,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
{
unsigned int queued;
struct nfqnl_instance *queue;
- struct sk_buff *skb, *segs;
+ struct sk_buff *skb, *segs, *nskb;
int err = -ENOBUFS;
struct net *net = entry->state.net;
struct nfnl_queue_net *q = nfnl_queue_pernet(net);
@@ -815,8 +815,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
goto out_err;
queued = 0;
err = 0;
- do {
- struct sk_buff *nskb = segs->next;
+ skb_list_walk_safe(segs, segs, nskb) {
if (err == 0)
err = __nfqnl_enqueue_packet_gso(net, queue,
segs, entry);
@@ -824,8 +823,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
queued++;
else
kfree_skb(segs);
- segs = nskb;
- } while (segs);
+ }
if (queued) {
if (err) /* some segments are already queued */
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index 10e9d50..0ed2281 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -18,21 +18,66 @@
struct nft_bitwise {
enum nft_registers sreg:8;
enum nft_registers dreg:8;
+ enum nft_bitwise_ops op:8;
u8 len;
struct nft_data mask;
struct nft_data xor;
+ struct nft_data data;
};
+static void nft_bitwise_eval_bool(u32 *dst, const u32 *src,
+ const struct nft_bitwise *priv)
+{
+ unsigned int i;
+
+ for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++)
+ dst[i] = (src[i] & priv->mask.data[i]) ^ priv->xor.data[i];
+}
+
+static void nft_bitwise_eval_lshift(u32 *dst, const u32 *src,
+ const struct nft_bitwise *priv)
+{
+ u32 shift = priv->data.data[0];
+ unsigned int i;
+ u32 carry = 0;
+
+ for (i = DIV_ROUND_UP(priv->len, sizeof(u32)); i > 0; i--) {
+ dst[i - 1] = (src[i - 1] << shift) | carry;
+ carry = src[i - 1] >> (BITS_PER_TYPE(u32) - shift);
+ }
+}
+
+static void nft_bitwise_eval_rshift(u32 *dst, const u32 *src,
+ const struct nft_bitwise *priv)
+{
+ u32 shift = priv->data.data[0];
+ unsigned int i;
+ u32 carry = 0;
+
+ for (i = 0; i < DIV_ROUND_UP(priv->len, sizeof(u32)); i++) {
+ dst[i] = carry | (src[i] >> shift);
+ carry = src[i] << (BITS_PER_TYPE(u32) - shift);
+ }
+}
+
void nft_bitwise_eval(const struct nft_expr *expr,
struct nft_regs *regs, const struct nft_pktinfo *pkt)
{
const struct nft_bitwise *priv = nft_expr_priv(expr);
const u32 *src = ®s->data[priv->sreg];
u32 *dst = ®s->data[priv->dreg];
- unsigned int i;
- for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++)
- dst[i] = (src[i] & priv->mask.data[i]) ^ priv->xor.data[i];
+ switch (priv->op) {
+ case NFT_BITWISE_BOOL:
+ nft_bitwise_eval_bool(dst, src, priv);
+ break;
+ case NFT_BITWISE_LSHIFT:
+ nft_bitwise_eval_lshift(dst, src, priv);
+ break;
+ case NFT_BITWISE_RSHIFT:
+ nft_bitwise_eval_rshift(dst, src, priv);
+ break;
+ }
}
static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = {
@@ -41,40 +86,22 @@ static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = {
[NFTA_BITWISE_LEN] = { .type = NLA_U32 },
[NFTA_BITWISE_MASK] = { .type = NLA_NESTED },
[NFTA_BITWISE_XOR] = { .type = NLA_NESTED },
+ [NFTA_BITWISE_OP] = { .type = NLA_U32 },
+ [NFTA_BITWISE_DATA] = { .type = NLA_NESTED },
};
-static int nft_bitwise_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[])
+static int nft_bitwise_init_bool(struct nft_bitwise *priv,
+ const struct nlattr *const tb[])
{
- struct nft_bitwise *priv = nft_expr_priv(expr);
struct nft_data_desc d1, d2;
- u32 len;
int err;
- if (tb[NFTA_BITWISE_SREG] == NULL ||
- tb[NFTA_BITWISE_DREG] == NULL ||
- tb[NFTA_BITWISE_LEN] == NULL ||
- tb[NFTA_BITWISE_MASK] == NULL ||
- tb[NFTA_BITWISE_XOR] == NULL)
+ if (tb[NFTA_BITWISE_DATA])
return -EINVAL;
- err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len);
- if (err < 0)
- return err;
-
- priv->len = len;
-
- priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]);
- err = nft_validate_register_load(priv->sreg, priv->len);
- if (err < 0)
- return err;
-
- priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]);
- err = nft_validate_register_store(ctx, priv->dreg, NULL,
- NFT_DATA_VALUE, priv->len);
- if (err < 0)
- return err;
+ if (!tb[NFTA_BITWISE_MASK] ||
+ !tb[NFTA_BITWISE_XOR])
+ return -EINVAL;
err = nft_data_init(NULL, &priv->mask, sizeof(priv->mask), &d1,
tb[NFTA_BITWISE_MASK]);
@@ -102,40 +129,151 @@ static int nft_bitwise_init(const struct nft_ctx *ctx,
return err;
}
-static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static int nft_bitwise_init_shift(struct nft_bitwise *priv,
+ const struct nlattr *const tb[])
{
- const struct nft_bitwise *priv = nft_expr_priv(expr);
+ struct nft_data_desc d;
+ int err;
- if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg))
- goto nla_put_failure;
- if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg))
- goto nla_put_failure;
- if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(priv->len)))
- goto nla_put_failure;
+ if (tb[NFTA_BITWISE_MASK] ||
+ tb[NFTA_BITWISE_XOR])
+ return -EINVAL;
+ if (!tb[NFTA_BITWISE_DATA])
+ return -EINVAL;
+
+ err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &d,
+ tb[NFTA_BITWISE_DATA]);
+ if (err < 0)
+ return err;
+ if (d.type != NFT_DATA_VALUE || d.len != sizeof(u32) ||
+ priv->data.data[0] >= BITS_PER_TYPE(u32)) {
+ nft_data_release(&priv->data, d.type);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int nft_bitwise_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_bitwise *priv = nft_expr_priv(expr);
+ u32 len;
+ int err;
+
+ if (!tb[NFTA_BITWISE_SREG] ||
+ !tb[NFTA_BITWISE_DREG] ||
+ !tb[NFTA_BITWISE_LEN])
+ return -EINVAL;
+
+ err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len);
+ if (err < 0)
+ return err;
+
+ priv->len = len;
+
+ priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]);
+ err = nft_validate_register_load(priv->sreg, priv->len);
+ if (err < 0)
+ return err;
+
+ priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]);
+ err = nft_validate_register_store(ctx, priv->dreg, NULL,
+ NFT_DATA_VALUE, priv->len);
+ if (err < 0)
+ return err;
+
+ if (tb[NFTA_BITWISE_OP]) {
+ priv->op = ntohl(nla_get_be32(tb[NFTA_BITWISE_OP]));
+ switch (priv->op) {
+ case NFT_BITWISE_BOOL:
+ case NFT_BITWISE_LSHIFT:
+ case NFT_BITWISE_RSHIFT:
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+ } else {
+ priv->op = NFT_BITWISE_BOOL;
+ }
+
+ switch(priv->op) {
+ case NFT_BITWISE_BOOL:
+ err = nft_bitwise_init_bool(priv, tb);
+ break;
+ case NFT_BITWISE_LSHIFT:
+ case NFT_BITWISE_RSHIFT:
+ err = nft_bitwise_init_shift(priv, tb);
+ break;
+ }
+
+ return err;
+}
+
+static int nft_bitwise_dump_bool(struct sk_buff *skb,
+ const struct nft_bitwise *priv)
+{
if (nft_data_dump(skb, NFTA_BITWISE_MASK, &priv->mask,
NFT_DATA_VALUE, priv->len) < 0)
- goto nla_put_failure;
+ return -1;
if (nft_data_dump(skb, NFTA_BITWISE_XOR, &priv->xor,
NFT_DATA_VALUE, priv->len) < 0)
- goto nla_put_failure;
+ return -1;
return 0;
+}
-nla_put_failure:
- return -1;
+static int nft_bitwise_dump_shift(struct sk_buff *skb,
+ const struct nft_bitwise *priv)
+{
+ if (nft_data_dump(skb, NFTA_BITWISE_DATA, &priv->data,
+ NFT_DATA_VALUE, sizeof(u32)) < 0)
+ return -1;
+ return 0;
+}
+
+static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_bitwise *priv = nft_expr_priv(expr);
+ int err = 0;
+
+ if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg))
+ return -1;
+ if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg))
+ return -1;
+ if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(priv->len)))
+ return -1;
+ if (nla_put_be32(skb, NFTA_BITWISE_OP, htonl(priv->op)))
+ return -1;
+
+ switch (priv->op) {
+ case NFT_BITWISE_BOOL:
+ err = nft_bitwise_dump_bool(skb, priv);
+ break;
+ case NFT_BITWISE_LSHIFT:
+ case NFT_BITWISE_RSHIFT:
+ err = nft_bitwise_dump_shift(skb, priv);
+ break;
+ }
+
+ return err;
}
static struct nft_data zero;
static int nft_bitwise_offload(struct nft_offload_ctx *ctx,
- struct nft_flow_rule *flow,
- const struct nft_expr *expr)
+ struct nft_flow_rule *flow,
+ const struct nft_expr *expr)
{
const struct nft_bitwise *priv = nft_expr_priv(expr);
struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
+ if (priv->op != NFT_BITWISE_BOOL)
+ return -EOPNOTSUPP;
+
if (memcmp(&priv->xor, &zero, sizeof(priv->xor)) ||
priv->sreg != priv->dreg || priv->len != reg->len)
return -EOPNOTSUPP;
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 8887295..6837852 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -54,7 +54,7 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr,
timeout = priv->timeout ? : set->timeout;
elem = nft_set_elem_init(set, &priv->tmpl,
- ®s->data[priv->sreg_key],
+ ®s->data[priv->sreg_key], NULL,
®s->data[priv->sreg_data],
timeout, 0, GFP_ATOMIC);
if (elem == NULL)
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index dd82ff2e..b70b489 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -200,9 +200,6 @@ static void nft_flow_offload_activate(const struct nft_ctx *ctx,
static void nft_flow_offload_destroy(const struct nft_ctx *ctx,
const struct nft_expr *expr)
{
- struct nft_flow_offload *priv = nft_expr_priv(expr);
-
- priv->flowtable->use--;
nf_ct_netns_put(ctx->net, ctx->family);
}
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index f54d6ae..b42247a 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -61,6 +61,9 @@ static int nft_osf_init(const struct nft_ctx *ctx,
int err;
u8 ttl;
+ if (!tb[NFTA_OSF_DREG])
+ return -EINVAL;
+
if (tb[NFTA_OSF_TTL]) {
ttl = nla_get_u8(tb[NFTA_OSF_TTL]);
if (ttl > 2)
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 087a056..87e8d9b 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -259,8 +259,8 @@ static u64 nft_bitmap_privsize(const struct nlattr * const nla[],
}
static int nft_bitmap_init(const struct nft_set *set,
- const struct nft_set_desc *desc,
- const struct nlattr * const nla[])
+ const struct nft_set_desc *desc,
+ const struct nlattr * const nla[])
{
struct nft_bitmap *priv = nft_set_priv(set);
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index b331a3c..d350a7cd 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -645,7 +645,7 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
}
static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features,
- struct nft_set_estimate *est)
+ struct nft_set_estimate *est)
{
if (!desc->size)
return false;
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
new file mode 100644
index 0000000..f0cb1e1
--- /dev/null
+++ b/net/netfilter/nft_set_pipapo.c
@@ -0,0 +1,2102 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* PIPAPO: PIle PAcket POlicies: set for arbitrary concatenations of ranges
+ *
+ * Copyright (c) 2019-2020 Red Hat GmbH
+ *
+ * Author: Stefano Brivio <sbrivio@redhat.com>
+ */
+
+/**
+ * DOC: Theory of Operation
+ *
+ *
+ * Problem
+ * -------
+ *
+ * Match packet bytes against entries composed of ranged or non-ranged packet
+ * field specifiers, mapping them to arbitrary references. For example:
+ *
+ * ::
+ *
+ * --- fields --->
+ * | [net],[port],[net]... => [reference]
+ * entries [net],[port],[net]... => [reference]
+ * | [net],[port],[net]... => [reference]
+ * V ...
+ *
+ * where [net] fields can be IP ranges or netmasks, and [port] fields are port
+ * ranges. Arbitrary packet fields can be matched.
+ *
+ *
+ * Algorithm Overview
+ * ------------------
+ *
+ * This algorithm is loosely inspired by [Ligatti 2010], and fundamentally
+ * relies on the consideration that every contiguous range in a space of b bits
+ * can be converted into b * 2 netmasks, from Theorem 3 in [Rottenstreich 2010],
+ * as also illustrated in Section 9 of [Kogan 2014].
+ *
+ * Classification against a number of entries, that require matching given bits
+ * of a packet field, is performed by grouping those bits in sets of arbitrary
+ * size, and classifying packet bits one group at a time.
+ *
+ * Example:
+ * to match the source port (16 bits) of a packet, we can divide those 16 bits
+ * in 4 groups of 4 bits each. Given the entry:
+ * 0000 0001 0101 1001
+ * and a packet with source port:
+ * 0000 0001 1010 1001
+ * first and second groups match, but the third doesn't. We conclude that the
+ * packet doesn't match the given entry.
+ *
+ * Translate the set to a sequence of lookup tables, one per field. Each table
+ * has two dimensions: bit groups to be matched for a single packet field, and
+ * all the possible values of said groups (buckets). Input entries are
+ * represented as one or more rules, depending on the number of composing
+ * netmasks for the given field specifier, and a group match is indicated as a
+ * set bit, with number corresponding to the rule index, in all the buckets
+ * whose value matches the entry for a given group.
+ *
+ * Rules are mapped between fields through an array of x, n pairs, with each
+ * item mapping a matched rule to one or more rules. The position of the pair in
+ * the array indicates the matched rule to be mapped to the next field, x
+ * indicates the first rule index in the next field, and n the amount of
+ * next-field rules the current rule maps to.
+ *
+ * The mapping array for the last field maps to the desired references.
+ *
+ * To match, we perform table lookups using the values of grouped packet bits,
+ * and use a sequence of bitwise operations to progressively evaluate rule
+ * matching.
+ *
+ * A stand-alone, reference implementation, also including notes about possible
+ * future optimisations, is available at:
+ * https://pipapo.lameexcu.se/
+ *
+ * Insertion
+ * ---------
+ *
+ * - For each packet field:
+ *
+ * - divide the b packet bits we want to classify into groups of size t,
+ * obtaining ceil(b / t) groups
+ *
+ * Example: match on destination IP address, with t = 4: 32 bits, 8 groups
+ * of 4 bits each
+ *
+ * - allocate a lookup table with one column ("bucket") for each possible
+ * value of a group, and with one row for each group
+ *
+ * Example: 8 groups, 2^4 buckets:
+ *
+ * ::
+ *
+ * bucket
+ * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
+ * 0
+ * 1
+ * 2
+ * 3
+ * 4
+ * 5
+ * 6
+ * 7
+ *
+ * - map the bits we want to classify for the current field, for a given
+ * entry, to a single rule for non-ranged and netmask set items, and to one
+ * or multiple rules for ranges. Ranges are expanded to composing netmasks
+ * by pipapo_expand().
+ *
+ * Example: 2 entries, 10.0.0.5:1024 and 192.168.1.0-192.168.2.1:2048
+ * - rule #0: 10.0.0.5
+ * - rule #1: 192.168.1.0/24
+ * - rule #2: 192.168.2.0/31
+ *
+ * - insert references to the rules in the lookup table, selecting buckets
+ * according to bit values of a rule in the given group. This is done by
+ * pipapo_insert().
+ *
+ * Example: given:
+ * - rule #0: 10.0.0.5 mapping to buckets
+ * < 0 10 0 0 0 0 0 5 >
+ * - rule #1: 192.168.1.0/24 mapping to buckets
+ * < 12 0 10 8 0 1 < 0..15 > < 0..15 > >
+ * - rule #2: 192.168.2.0/31 mapping to buckets
+ * < 12 0 10 8 0 2 0 < 0..1 > >
+ *
+ * these bits are set in the lookup table:
+ *
+ * ::
+ *
+ * bucket
+ * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
+ * 0 0 1,2
+ * 1 1,2 0
+ * 2 0 1,2
+ * 3 0 1,2
+ * 4 0,1,2
+ * 5 0 1 2
+ * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
+ * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1
+ *
+ * - if this is not the last field in the set, fill a mapping array that maps
+ * rules from the lookup table to rules belonging to the same entry in
+ * the next lookup table, done by pipapo_map().
+ *
+ * Note that as rules map to contiguous ranges of rules, given how netmask
+ * expansion and insertion is performed, &union nft_pipapo_map_bucket stores
+ * this information as pairs of first rule index, rule count.
+ *
+ * Example: 2 entries, 10.0.0.5:1024 and 192.168.1.0-192.168.2.1:2048,
+ * given lookup table #0 for field 0 (see example above):
+ *
+ * ::
+ *
+ * bucket
+ * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
+ * 0 0 1,2
+ * 1 1,2 0
+ * 2 0 1,2
+ * 3 0 1,2
+ * 4 0,1,2
+ * 5 0 1 2
+ * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
+ * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1
+ *
+ * and lookup table #1 for field 1 with:
+ * - rule #0: 1024 mapping to buckets
+ * < 0 0 4 0 >
+ * - rule #1: 2048 mapping to buckets
+ * < 0 0 5 0 >
+ *
+ * ::
+ *
+ * bucket
+ * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
+ * 0 0,1
+ * 1 0,1
+ * 2 0 1
+ * 3 0,1
+ *
+ * we need to map rules for 10.0.0.5 in lookup table #0 (rule #0) to 1024
+ * in lookup table #1 (rule #0) and rules for 192.168.1.0-192.168.2.1
+ * (rules #1, #2) to 2048 in lookup table #2 (rule #1):
+ *
+ * ::
+ *
+ * rule indices in current field: 0 1 2
+ * map to rules in next field: 0 1 1
+ *
+ * - if this is the last field in the set, fill a mapping array that maps
+ * rules from the last lookup table to element pointers, also done by
+ * pipapo_map().
+ *
+ * Note that, in this implementation, we have two elements (start, end) for
+ * each entry. The pointer to the end element is stored in this array, and
+ * the pointer to the start element is linked from it.
+ *
+ * Example: entry 10.0.0.5:1024 has a corresponding &struct nft_pipapo_elem
+ * pointer, 0x66, and element for 192.168.1.0-192.168.2.1:2048 is at 0x42.
+ * From the rules of lookup table #1 as mapped above:
+ *
+ * ::
+ *
+ * rule indices in last field: 0 1
+ * map to elements: 0x42 0x66
+ *
+ *
+ * Matching
+ * --------
+ *
+ * We use a result bitmap, with the size of a single lookup table bucket, to
+ * represent the matching state that applies at every algorithm step. This is
+ * done by pipapo_lookup().
+ *
+ * - For each packet field:
+ *
+ * - start with an all-ones result bitmap (res_map in pipapo_lookup())
+ *
+ * - perform a lookup into the table corresponding to the current field,
+ * for each group, and at every group, AND the current result bitmap with
+ * the value from the lookup table bucket
+ *
+ * ::
+ *
+ * Example: 192.168.1.5 < 12 0 10 8 0 1 0 5 >, with lookup table from
+ * insertion examples.
+ * Lookup table buckets are at least 3 bits wide, we'll assume 8 bits for
+ * convenience in this example. Initial result bitmap is 0xff, the steps
+ * below show the value of the result bitmap after each group is processed:
+ *
+ * bucket
+ * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
+ * 0 0 1,2
+ * result bitmap is now: 0xff & 0x6 [bucket 12] = 0x6
+ *
+ * 1 1,2 0
+ * result bitmap is now: 0x6 & 0x6 [bucket 0] = 0x6
+ *
+ * 2 0 1,2
+ * result bitmap is now: 0x6 & 0x6 [bucket 10] = 0x6
+ *
+ * 3 0 1,2
+ * result bitmap is now: 0x6 & 0x6 [bucket 8] = 0x6
+ *
+ * 4 0,1,2
+ * result bitmap is now: 0x6 & 0x7 [bucket 0] = 0x6
+ *
+ * 5 0 1 2
+ * result bitmap is now: 0x6 & 0x2 [bucket 1] = 0x2
+ *
+ * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
+ * result bitmap is now: 0x2 & 0x7 [bucket 0] = 0x2
+ *
+ * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1
+ * final result bitmap for this field is: 0x2 & 0x3 [bucket 5] = 0x2
+ *
+ * - at the next field, start with a new, all-zeroes result bitmap. For each
+ * bit set in the previous result bitmap, fill the new result bitmap
+ * (fill_map in pipapo_lookup()) with the rule indices from the
+ * corresponding buckets of the mapping field for this field, done by
+ * pipapo_refill()
+ *
+ * Example: with mapping table from insertion examples, with the current
+ * result bitmap from the previous example, 0x02:
+ *
+ * ::
+ *
+ * rule indices in current field: 0 1 2
+ * map to rules in next field: 0 1 1
+ *
+ * the new result bitmap will be 0x02: rule 1 was set, and rule 1 will be
+ * set.
+ *
+ * We can now extend this example to cover the second iteration of the step
+ * above (lookup and AND bitmap): assuming the port field is
+ * 2048 < 0 0 5 0 >, with starting result bitmap 0x2, and lookup table
+ * for "port" field from pre-computation example:
+ *
+ * ::
+ *
+ * bucket
+ * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
+ * 0 0,1
+ * 1 0,1
+ * 2 0 1
+ * 3 0,1
+ *
+ * operations are: 0x2 & 0x3 [bucket 0] & 0x3 [bucket 0] & 0x2 [bucket 5]
+ * & 0x3 [bucket 0], resulting bitmap is 0x2.
+ *
+ * - if this is the last field in the set, look up the value from the mapping
+ * array corresponding to the final result bitmap
+ *
+ * Example: 0x2 resulting bitmap from 192.168.1.5:2048, mapping array for
+ * last field from insertion example:
+ *
+ * ::
+ *
+ * rule indices in last field: 0 1
+ * map to elements: 0x42 0x66
+ *
+ * the matching element is at 0x42.
+ *
+ *
+ * References
+ * ----------
+ *
+ * [Ligatti 2010]
+ * A Packet-classification Algorithm for Arbitrary Bitmask Rules, with
+ * Automatic Time-space Tradeoffs
+ * Jay Ligatti, Josh Kuhn, and Chris Gage.
+ * Proceedings of the IEEE International Conference on Computer
+ * Communication Networks (ICCCN), August 2010.
+ * http://www.cse.usf.edu/~ligatti/papers/grouper-conf.pdf
+ *
+ * [Rottenstreich 2010]
+ * Worst-Case TCAM Rule Expansion
+ * Ori Rottenstreich and Isaac Keslassy.
+ * 2010 Proceedings IEEE INFOCOM, San Diego, CA, 2010.
+ * http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.212.4592&rep=rep1&type=pdf
+ *
+ * [Kogan 2014]
+ * SAX-PAC (Scalable And eXpressive PAcket Classification)
+ * Kirill Kogan, Sergey Nikolenko, Ori Rottenstreich, William Culhane,
+ * and Patrick Eugster.
+ * Proceedings of the 2014 ACM conference on SIGCOMM, August 2014.
+ * http://www.sigcomm.org/sites/default/files/ccr/papers/2014/August/2619239-2626294.pdf
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/log2.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <uapi/linux/netfilter/nf_tables.h>
+#include <net/ipv6.h> /* For the maximum length of a field */
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+/* Count of concatenated fields depends on count of 32-bit nftables registers */
+#define NFT_PIPAPO_MAX_FIELDS NFT_REG32_COUNT
+
+/* Largest supported field size */
+#define NFT_PIPAPO_MAX_BYTES (sizeof(struct in6_addr))
+#define NFT_PIPAPO_MAX_BITS (NFT_PIPAPO_MAX_BYTES * BITS_PER_BYTE)
+
+/* Number of bits to be grouped together in lookup table buckets, arbitrary */
+#define NFT_PIPAPO_GROUP_BITS 4
+#define NFT_PIPAPO_GROUPS_PER_BYTE (BITS_PER_BYTE / NFT_PIPAPO_GROUP_BITS)
+
+/* Fields are padded to 32 bits in input registers */
+#define NFT_PIPAPO_GROUPS_PADDED_SIZE(x) \
+ (round_up((x) / NFT_PIPAPO_GROUPS_PER_BYTE, sizeof(u32)))
+#define NFT_PIPAPO_GROUPS_PADDING(x) \
+ (NFT_PIPAPO_GROUPS_PADDED_SIZE((x)) - (x) / NFT_PIPAPO_GROUPS_PER_BYTE)
+
+/* Number of buckets, given by 2 ^ n, with n grouped bits */
+#define NFT_PIPAPO_BUCKETS (1 << NFT_PIPAPO_GROUP_BITS)
+
+/* Each n-bit range maps to up to n * 2 rules */
+#define NFT_PIPAPO_MAP_NBITS (const_ilog2(NFT_PIPAPO_MAX_BITS * 2))
+
+/* Use the rest of mapping table buckets for rule indices, but it makes no sense
+ * to exceed 32 bits
+ */
+#if BITS_PER_LONG == 64
+#define NFT_PIPAPO_MAP_TOBITS 32
+#else
+#define NFT_PIPAPO_MAP_TOBITS (BITS_PER_LONG - NFT_PIPAPO_MAP_NBITS)
+#endif
+
+/* ...which gives us the highest allowed index for a rule */
+#define NFT_PIPAPO_RULE0_MAX ((1UL << (NFT_PIPAPO_MAP_TOBITS - 1)) \
+ - (1UL << NFT_PIPAPO_MAP_NBITS))
+
+#define nft_pipapo_for_each_field(field, index, match) \
+ for ((field) = (match)->f, (index) = 0; \
+ (index) < (match)->field_count; \
+ (index)++, (field)++)
+
+/**
+ * union nft_pipapo_map_bucket - Bucket of mapping table
+ * @to: First rule number (in next field) this rule maps to
+ * @n: Number of rules (in next field) this rule maps to
+ * @e: If there's no next field, pointer to element this rule maps to
+ */
+union nft_pipapo_map_bucket {
+ struct {
+#if BITS_PER_LONG == 64
+ static_assert(NFT_PIPAPO_MAP_TOBITS <= 32);
+ u32 to;
+
+ static_assert(NFT_PIPAPO_MAP_NBITS <= 32);
+ u32 n;
+#else
+ unsigned long to:NFT_PIPAPO_MAP_TOBITS;
+ unsigned long n:NFT_PIPAPO_MAP_NBITS;
+#endif
+ };
+ struct nft_pipapo_elem *e;
+};
+
+/**
+ * struct nft_pipapo_field - Lookup, mapping tables and related data for a field
+ * @groups: Amount of 4-bit groups
+ * @rules: Number of inserted rules
+ * @bsize: Size of each bucket in lookup table, in longs
+ * @lt: Lookup table: 'groups' rows of NFT_PIPAPO_BUCKETS buckets
+ * @mt: Mapping table: one bucket per rule
+ */
+struct nft_pipapo_field {
+ int groups;
+ unsigned long rules;
+ size_t bsize;
+ unsigned long *lt;
+ union nft_pipapo_map_bucket *mt;
+};
+
+/**
+ * struct nft_pipapo_match - Data used for lookup and matching
+ * @field_count Amount of fields in set
+ * @scratch: Preallocated per-CPU maps for partial matching results
+ * @bsize_max: Maximum lookup table bucket size of all fields, in longs
+ * @rcu Matching data is swapped on commits
+ * @f: Fields, with lookup and mapping tables
+ */
+struct nft_pipapo_match {
+ int field_count;
+ unsigned long * __percpu *scratch;
+ size_t bsize_max;
+ struct rcu_head rcu;
+ struct nft_pipapo_field f[0];
+};
+
+/* Current working bitmap index, toggled between field matches */
+static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index);
+
+/**
+ * struct nft_pipapo - Representation of a set
+ * @match: Currently in-use matching data
+ * @clone: Copy where pending insertions and deletions are kept
+ * @groups: Total amount of 4-bit groups for fields in this set
+ * @width: Total bytes to be matched for one packet, including padding
+ * @dirty: Working copy has pending insertions or deletions
+ * @last_gc: Timestamp of last garbage collection run, jiffies
+ */
+struct nft_pipapo {
+ struct nft_pipapo_match __rcu *match;
+ struct nft_pipapo_match *clone;
+ int groups;
+ int width;
+ bool dirty;
+ unsigned long last_gc;
+};
+
+struct nft_pipapo_elem;
+
+/**
+ * struct nft_pipapo_elem - API-facing representation of single set element
+ * @ext: nftables API extensions
+ */
+struct nft_pipapo_elem {
+ struct nft_set_ext ext;
+};
+
+/**
+ * pipapo_refill() - For each set bit, set bits from selected mapping table item
+ * @map: Bitmap to be scanned for set bits
+ * @len: Length of bitmap in longs
+ * @rules: Number of rules in field
+ * @dst: Destination bitmap
+ * @mt: Mapping table containing bit set specifiers
+ * @match_only: Find a single bit and return, don't fill
+ *
+ * Iteration over set bits with __builtin_ctzl(): Daniel Lemire, public domain.
+ *
+ * For each bit set in map, select the bucket from mapping table with index
+ * corresponding to the position of the bit set. Use start bit and amount of
+ * bits specified in bucket to fill region in dst.
+ *
+ * Return: -1 on no match, bit position on 'match_only', 0 otherwise.
+ */
+static int pipapo_refill(unsigned long *map, int len, int rules,
+ unsigned long *dst, union nft_pipapo_map_bucket *mt,
+ bool match_only)
+{
+ unsigned long bitset;
+ int k, ret = -1;
+
+ for (k = 0; k < len; k++) {
+ bitset = map[k];
+ while (bitset) {
+ unsigned long t = bitset & -bitset;
+ int r = __builtin_ctzl(bitset);
+ int i = k * BITS_PER_LONG + r;
+
+ if (unlikely(i >= rules)) {
+ map[k] = 0;
+ return -1;
+ }
+
+ if (unlikely(match_only)) {
+ bitmap_clear(map, i, 1);
+ return i;
+ }
+
+ ret = 0;
+
+ bitmap_set(dst, mt[i].to, mt[i].n);
+
+ bitset ^= t;
+ }
+ map[k] = 0;
+ }
+
+ return ret;
+}
+
+/**
+ * nft_pipapo_lookup() - Lookup function
+ * @net: Network namespace
+ * @set: nftables API set representation
+ * @elem: nftables API element representation containing key data
+ * @ext: nftables API extension pointer, filled with matching reference
+ *
+ * For more details, see DOC: Theory of Operation.
+ *
+ * Return: true on match, false otherwise.
+ */
+static bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
+ const u32 *key, const struct nft_set_ext **ext)
+{
+ struct nft_pipapo *priv = nft_set_priv(set);
+ unsigned long *res_map, *fill_map;
+ u8 genmask = nft_genmask_cur(net);
+ const u8 *rp = (const u8 *)key;
+ struct nft_pipapo_match *m;
+ struct nft_pipapo_field *f;
+ bool map_index;
+ int i;
+
+ local_bh_disable();
+
+ map_index = raw_cpu_read(nft_pipapo_scratch_index);
+
+ m = rcu_dereference(priv->match);
+
+ if (unlikely(!m || !*raw_cpu_ptr(m->scratch)))
+ goto out;
+
+ res_map = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0);
+ fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max);
+
+ memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));
+
+ nft_pipapo_for_each_field(f, i, m) {
+ bool last = i == m->field_count - 1;
+ unsigned long *lt = f->lt;
+ int b, group;
+
+ /* For each 4-bit group: select lookup table bucket depending on
+ * packet bytes value, then AND bucket value
+ */
+ for (group = 0; group < f->groups; group += 2) {
+ u8 v;
+
+ v = *rp >> 4;
+ __bitmap_and(res_map, res_map, lt + v * f->bsize,
+ f->bsize * BITS_PER_LONG);
+ lt += f->bsize * NFT_PIPAPO_BUCKETS;
+
+ v = *rp & 0x0f;
+ rp++;
+ __bitmap_and(res_map, res_map, lt + v * f->bsize,
+ f->bsize * BITS_PER_LONG);
+ lt += f->bsize * NFT_PIPAPO_BUCKETS;
+ }
+
+ /* Now populate the bitmap for the next field, unless this is
+ * the last field, in which case return the matched 'ext'
+ * pointer if any.
+ *
+ * Now res_map contains the matching bitmap, and fill_map is the
+ * bitmap for the next field.
+ */
+next_match:
+ b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt,
+ last);
+ if (b < 0) {
+ raw_cpu_write(nft_pipapo_scratch_index, map_index);
+ local_bh_enable();
+
+ return false;
+ }
+
+ if (last) {
+ *ext = &f->mt[b].e->ext;
+ if (unlikely(nft_set_elem_expired(*ext) ||
+ !nft_set_elem_active(*ext, genmask)))
+ goto next_match;
+
+ /* Last field: we're just returning the key without
+ * filling the initial bitmap for the next field, so the
+ * current inactive bitmap is clean and can be reused as
+ * *next* bitmap (not initial) for the next packet.
+ */
+ raw_cpu_write(nft_pipapo_scratch_index, map_index);
+ local_bh_enable();
+
+ return true;
+ }
+
+ /* Swap bitmap indices: res_map is the initial bitmap for the
+ * next field, and fill_map is guaranteed to be all-zeroes at
+ * this point.
+ */
+ map_index = !map_index;
+ swap(res_map, fill_map);
+
+ rp += NFT_PIPAPO_GROUPS_PADDING(f->groups);
+ }
+
+out:
+ local_bh_enable();
+ return false;
+}
+
+/**
+ * pipapo_get() - Get matching element reference given key data
+ * @net: Network namespace
+ * @set: nftables API set representation
+ * @data: Key data to be matched against existing elements
+ * @genmask: If set, check that element is active in given genmask
+ *
+ * This is essentially the same as the lookup function, except that it matches
+ * key data against the uncommitted copy and doesn't use preallocated maps for
+ * bitmap results.
+ *
+ * Return: pointer to &struct nft_pipapo_elem on match, error pointer otherwise.
+ */
+static struct nft_pipapo_elem *pipapo_get(const struct net *net,
+ const struct nft_set *set,
+ const u8 *data, u8 genmask)
+{
+ struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT);
+ struct nft_pipapo *priv = nft_set_priv(set);
+ struct nft_pipapo_match *m = priv->clone;
+ unsigned long *res_map, *fill_map = NULL;
+ struct nft_pipapo_field *f;
+ int i;
+
+ res_map = kmalloc_array(m->bsize_max, sizeof(*res_map), GFP_ATOMIC);
+ if (!res_map) {
+ ret = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ fill_map = kcalloc(m->bsize_max, sizeof(*res_map), GFP_ATOMIC);
+ if (!fill_map) {
+ ret = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));
+
+ nft_pipapo_for_each_field(f, i, m) {
+ bool last = i == m->field_count - 1;
+ unsigned long *lt = f->lt;
+ int b, group;
+
+ /* For each 4-bit group: select lookup table bucket depending on
+ * packet bytes value, then AND bucket value
+ */
+ for (group = 0; group < f->groups; group++) {
+ u8 v;
+
+ if (group % 2) {
+ v = *data & 0x0f;
+ data++;
+ } else {
+ v = *data >> 4;
+ }
+ __bitmap_and(res_map, res_map, lt + v * f->bsize,
+ f->bsize * BITS_PER_LONG);
+
+ lt += f->bsize * NFT_PIPAPO_BUCKETS;
+ }
+
+ /* Now populate the bitmap for the next field, unless this is
+ * the last field, in which case return the matched 'ext'
+ * pointer if any.
+ *
+ * Now res_map contains the matching bitmap, and fill_map is the
+ * bitmap for the next field.
+ */
+next_match:
+ b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt,
+ last);
+ if (b < 0)
+ goto out;
+
+ if (last) {
+ if (nft_set_elem_expired(&f->mt[b].e->ext) ||
+ (genmask &&
+ !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
+ goto next_match;
+
+ ret = f->mt[b].e;
+ goto out;
+ }
+
+ data += NFT_PIPAPO_GROUPS_PADDING(f->groups);
+
+ /* Swap bitmap indices: fill_map will be the initial bitmap for
+ * the next field (i.e. the new res_map), and res_map is
+ * guaranteed to be all-zeroes at this point, ready to be filled
+ * according to the next mapping table.
+ */
+ swap(res_map, fill_map);
+ }
+
+out:
+ kfree(fill_map);
+ kfree(res_map);
+ return ret;
+}
+
+/**
+ * nft_pipapo_get() - Get matching element reference given key data
+ * @net: Network namespace
+ * @set: nftables API set representation
+ * @elem: nftables API element representation containing key data
+ * @flags: Unused
+ */
+void *nft_pipapo_get(const struct net *net, const struct nft_set *set,
+ const struct nft_set_elem *elem, unsigned int flags)
+{
+ return pipapo_get(net, set, (const u8 *)elem->key.val.data,
+ nft_genmask_cur(net));
+}
+
+/**
+ * pipapo_resize() - Resize lookup or mapping table, or both
+ * @f: Field containing lookup and mapping tables
+ * @old_rules: Previous amount of rules in field
+ * @rules: New amount of rules
+ *
+ * Increase, decrease or maintain tables size depending on new amount of rules,
+ * and copy data over. In case the new size is smaller, throw away data for
+ * highest-numbered rules.
+ *
+ * Return: 0 on success, -ENOMEM on allocation failure.
+ */
+static int pipapo_resize(struct nft_pipapo_field *f, int old_rules, int rules)
+{
+ long *new_lt = NULL, *new_p, *old_lt = f->lt, *old_p;
+ union nft_pipapo_map_bucket *new_mt, *old_mt = f->mt;
+ size_t new_bucket_size, copy;
+ int group, bucket;
+
+ new_bucket_size = DIV_ROUND_UP(rules, BITS_PER_LONG);
+
+ if (new_bucket_size == f->bsize)
+ goto mt;
+
+ if (new_bucket_size > f->bsize)
+ copy = f->bsize;
+ else
+ copy = new_bucket_size;
+
+ new_lt = kvzalloc(f->groups * NFT_PIPAPO_BUCKETS * new_bucket_size *
+ sizeof(*new_lt), GFP_KERNEL);
+ if (!new_lt)
+ return -ENOMEM;
+
+ new_p = new_lt;
+ old_p = old_lt;
+ for (group = 0; group < f->groups; group++) {
+ for (bucket = 0; bucket < NFT_PIPAPO_BUCKETS; bucket++) {
+ memcpy(new_p, old_p, copy * sizeof(*new_p));
+ new_p += copy;
+ old_p += copy;
+
+ if (new_bucket_size > f->bsize)
+ new_p += new_bucket_size - f->bsize;
+ else
+ old_p += f->bsize - new_bucket_size;
+ }
+ }
+
+mt:
+ new_mt = kvmalloc(rules * sizeof(*new_mt), GFP_KERNEL);
+ if (!new_mt) {
+ kvfree(new_lt);
+ return -ENOMEM;
+ }
+
+ memcpy(new_mt, f->mt, min(old_rules, rules) * sizeof(*new_mt));
+ if (rules > old_rules) {
+ memset(new_mt + old_rules, 0,
+ (rules - old_rules) * sizeof(*new_mt));
+ }
+
+ if (new_lt) {
+ f->bsize = new_bucket_size;
+ f->lt = new_lt;
+ kvfree(old_lt);
+ }
+
+ f->mt = new_mt;
+ kvfree(old_mt);
+
+ return 0;
+}
+
+/**
+ * pipapo_bucket_set() - Set rule bit in bucket given group and group value
+ * @f: Field containing lookup table
+ * @rule: Rule index
+ * @group: Group index
+ * @v: Value of bit group
+ */
+static void pipapo_bucket_set(struct nft_pipapo_field *f, int rule, int group,
+ int v)
+{
+ unsigned long *pos;
+
+ pos = f->lt + f->bsize * NFT_PIPAPO_BUCKETS * group;
+ pos += f->bsize * v;
+
+ __set_bit(rule, pos);
+}
+
+/**
+ * pipapo_insert() - Insert new rule in field given input key and mask length
+ * @f: Field containing lookup table
+ * @k: Input key for classification, without nftables padding
+ * @mask_bits: Length of mask; matches field length for non-ranged entry
+ *
+ * Insert a new rule reference in lookup buckets corresponding to k and
+ * mask_bits.
+ *
+ * Return: 1 on success (one rule inserted), negative error code on failure.
+ */
+static int pipapo_insert(struct nft_pipapo_field *f, const uint8_t *k,
+ int mask_bits)
+{
+ int rule = f->rules++, group, ret;
+
+ ret = pipapo_resize(f, f->rules - 1, f->rules);
+ if (ret)
+ return ret;
+
+ for (group = 0; group < f->groups; group++) {
+ int i, v;
+ u8 mask;
+
+ if (group % 2)
+ v = k[group / 2] & 0x0f;
+ else
+ v = k[group / 2] >> 4;
+
+ if (mask_bits >= (group + 1) * 4) {
+ /* Not masked */
+ pipapo_bucket_set(f, rule, group, v);
+ } else if (mask_bits <= group * 4) {
+ /* Completely masked */
+ for (i = 0; i < NFT_PIPAPO_BUCKETS; i++)
+ pipapo_bucket_set(f, rule, group, i);
+ } else {
+ /* The mask limit falls on this group */
+ mask = 0x0f >> (mask_bits - group * 4);
+ for (i = 0; i < NFT_PIPAPO_BUCKETS; i++) {
+ if ((i & ~mask) == (v & ~mask))
+ pipapo_bucket_set(f, rule, group, i);
+ }
+ }
+ }
+
+ return 1;
+}
+
+/**
+ * pipapo_step_diff() - Check if setting @step bit in netmask would change it
+ * @base: Mask we are expanding
+ * @step: Step bit for given expansion step
+ * @len: Total length of mask space (set and unset bits), bytes
+ *
+ * Convenience function for mask expansion.
+ *
+ * Return: true if step bit changes mask (i.e. isn't set), false otherwise.
+ */
+static bool pipapo_step_diff(u8 *base, int step, int len)
+{
+ /* Network order, byte-addressed */
+#ifdef __BIG_ENDIAN__
+ return !(BIT(step % BITS_PER_BYTE) & base[step / BITS_PER_BYTE]);
+#else
+ return !(BIT(step % BITS_PER_BYTE) &
+ base[len - 1 - step / BITS_PER_BYTE]);
+#endif
+}
+
+/**
+ * pipapo_step_after_end() - Check if mask exceeds range end with given step
+ * @base: Mask we are expanding
+ * @end: End of range
+ * @step: Step bit for given expansion step, highest bit to be set
+ * @len: Total length of mask space (set and unset bits), bytes
+ *
+ * Convenience function for mask expansion.
+ *
+ * Return: true if mask exceeds range setting step bits, false otherwise.
+ */
+static bool pipapo_step_after_end(const u8 *base, const u8 *end, int step,
+ int len)
+{
+ u8 tmp[NFT_PIPAPO_MAX_BYTES];
+ int i;
+
+ memcpy(tmp, base, len);
+
+ /* Network order, byte-addressed */
+ for (i = 0; i <= step; i++)
+#ifdef __BIG_ENDIAN__
+ tmp[i / BITS_PER_BYTE] |= BIT(i % BITS_PER_BYTE);
+#else
+ tmp[len - 1 - i / BITS_PER_BYTE] |= BIT(i % BITS_PER_BYTE);
+#endif
+
+ return memcmp(tmp, end, len) > 0;
+}
+
+/**
+ * pipapo_base_sum() - Sum step bit to given len-sized netmask base with carry
+ * @base: Netmask base
+ * @step: Step bit to sum
+ * @len: Netmask length, bytes
+ */
+static void pipapo_base_sum(u8 *base, int step, int len)
+{
+ bool carry = false;
+ int i;
+
+ /* Network order, byte-addressed */
+#ifdef __BIG_ENDIAN__
+ for (i = step / BITS_PER_BYTE; i < len; i++) {
+#else
+ for (i = len - 1 - step / BITS_PER_BYTE; i >= 0; i--) {
+#endif
+ if (carry)
+ base[i]++;
+ else
+ base[i] += 1 << (step % BITS_PER_BYTE);
+
+ if (base[i])
+ break;
+
+ carry = true;
+ }
+}
+
+/**
+ * pipapo_expand() - Expand to composing netmasks, insert into lookup table
+ * @f: Field containing lookup table
+ * @start: Start of range
+ * @end: End of range
+ * @len: Length of value in bits
+ *
+ * Expand range to composing netmasks and insert corresponding rule references
+ * in lookup buckets.
+ *
+ * Return: number of inserted rules on success, negative error code on failure.
+ */
+static int pipapo_expand(struct nft_pipapo_field *f,
+ const u8 *start, const u8 *end, int len)
+{
+ int step, masks = 0, bytes = DIV_ROUND_UP(len, BITS_PER_BYTE);
+ u8 base[NFT_PIPAPO_MAX_BYTES];
+
+ memcpy(base, start, bytes);
+ while (memcmp(base, end, bytes) <= 0) {
+ int err;
+
+ step = 0;
+ while (pipapo_step_diff(base, step, bytes)) {
+ if (pipapo_step_after_end(base, end, step, bytes))
+ break;
+
+ step++;
+ if (step >= len) {
+ if (!masks) {
+ pipapo_insert(f, base, 0);
+ masks = 1;
+ }
+ goto out;
+ }
+ }
+
+ err = pipapo_insert(f, base, len - step);
+
+ if (err < 0)
+ return err;
+
+ masks++;
+ pipapo_base_sum(base, step, bytes);
+ }
+out:
+ return masks;
+}
+
+/**
+ * pipapo_map() - Insert rules in mapping tables, mapping them between fields
+ * @m: Matching data, including mapping table
+ * @map: Table of rule maps: array of first rule and amount of rules
+ * in next field a given rule maps to, for each field
+ * @ext: For last field, nft_set_ext pointer matching rules map to
+ */
+static void pipapo_map(struct nft_pipapo_match *m,
+ union nft_pipapo_map_bucket map[NFT_PIPAPO_MAX_FIELDS],
+ struct nft_pipapo_elem *e)
+{
+ struct nft_pipapo_field *f;
+ int i, j;
+
+ for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) {
+ for (j = 0; j < map[i].n; j++) {
+ f->mt[map[i].to + j].to = map[i + 1].to;
+ f->mt[map[i].to + j].n = map[i + 1].n;
+ }
+ }
+
+ /* Last field: map to ext instead of mapping to next field */
+ for (j = 0; j < map[i].n; j++)
+ f->mt[map[i].to + j].e = e;
+}
+
+/**
+ * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results
+ * @clone: Copy of matching data with pending insertions and deletions
+ * @bsize_max Maximum bucket size, scratch maps cover two buckets
+ *
+ * Return: 0 on success, -ENOMEM on failure.
+ */
+static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
+ unsigned long bsize_max)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ unsigned long *scratch;
+
+ scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2,
+ GFP_KERNEL, cpu_to_node(i));
+ if (!scratch) {
+ /* On failure, there's no need to undo previous
+ * allocations: this means that some scratch maps have
+ * a bigger allocated size now (this is only called on
+ * insertion), but the extra space won't be used by any
+ * CPU as new elements are not inserted and m->bsize_max
+ * is not updated.
+ */
+ return -ENOMEM;
+ }
+
+ kfree(*per_cpu_ptr(clone->scratch, i));
+
+ *per_cpu_ptr(clone->scratch, i) = scratch;
+ }
+
+ return 0;
+}
+
+/**
+ * nft_pipapo_insert() - Validate and insert ranged elements
+ * @net: Network namespace
+ * @set: nftables API set representation
+ * @elem: nftables API element representation containing key data
+ * @ext2: Filled with pointer to &struct nft_set_ext in inserted element
+ *
+ * Return: 0 on success, error pointer on failure.
+ */
+static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
+ const struct nft_set_elem *elem,
+ struct nft_set_ext **ext2)
+{
+ const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+ union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS];
+ const u8 *start = (const u8 *)elem->key.val.data, *end;
+ struct nft_pipapo_elem *e = elem->priv, *dup;
+ struct nft_pipapo *priv = nft_set_priv(set);
+ struct nft_pipapo_match *m = priv->clone;
+ u8 genmask = nft_genmask_next(net);
+ struct nft_pipapo_field *f;
+ int i, bsize_max, err = 0;
+
+ dup = pipapo_get(net, set, start, genmask);
+ if (PTR_ERR(dup) == -ENOENT) {
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) {
+ end = (const u8 *)nft_set_ext_key_end(ext)->data;
+ dup = pipapo_get(net, set, end, nft_genmask_next(net));
+ } else {
+ end = start;
+ }
+ }
+
+ if (PTR_ERR(dup) != -ENOENT) {
+ if (IS_ERR(dup))
+ return PTR_ERR(dup);
+ *ext2 = &dup->ext;
+ return -EEXIST;
+ }
+
+ /* Validate */
+ nft_pipapo_for_each_field(f, i, m) {
+ const u8 *start_p = start, *end_p = end;
+
+ if (f->rules >= (unsigned long)NFT_PIPAPO_RULE0_MAX)
+ return -ENOSPC;
+
+ if (memcmp(start_p, end_p,
+ f->groups / NFT_PIPAPO_GROUPS_PER_BYTE) > 0)
+ return -EINVAL;
+
+ start_p += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups);
+ end_p += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups);
+ }
+
+ /* Insert */
+ priv->dirty = true;
+
+ bsize_max = m->bsize_max;
+
+ nft_pipapo_for_each_field(f, i, m) {
+ int ret;
+
+ rulemap[i].to = f->rules;
+
+ ret = memcmp(start, end,
+ f->groups / NFT_PIPAPO_GROUPS_PER_BYTE);
+ if (!ret) {
+ ret = pipapo_insert(f, start,
+ f->groups * NFT_PIPAPO_GROUP_BITS);
+ } else {
+ ret = pipapo_expand(f, start, end,
+ f->groups * NFT_PIPAPO_GROUP_BITS);
+ }
+
+ if (f->bsize > bsize_max)
+ bsize_max = f->bsize;
+
+ rulemap[i].n = ret;
+
+ start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups);
+ end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups);
+ }
+
+ if (!*this_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) {
+ err = pipapo_realloc_scratch(m, bsize_max);
+ if (err)
+ return err;
+
+ this_cpu_write(nft_pipapo_scratch_index, false);
+
+ m->bsize_max = bsize_max;
+ }
+
+ *ext2 = &e->ext;
+
+ pipapo_map(m, rulemap, e);
+
+ return 0;
+}
+
+/**
+ * pipapo_clone() - Clone matching data to create new working copy
+ * @old: Existing matching data
+ *
+ * Return: copy of matching data passed as 'old', error pointer on failure
+ */
+static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
+{
+ struct nft_pipapo_field *dst, *src;
+ struct nft_pipapo_match *new;
+ int i;
+
+ new = kmalloc(sizeof(*new) + sizeof(*dst) * old->field_count,
+ GFP_KERNEL);
+ if (!new)
+ return ERR_PTR(-ENOMEM);
+
+ new->field_count = old->field_count;
+ new->bsize_max = old->bsize_max;
+
+ new->scratch = alloc_percpu(*new->scratch);
+ if (!new->scratch)
+ goto out_scratch;
+
+ rcu_head_init(&new->rcu);
+
+ src = old->f;
+ dst = new->f;
+
+ for (i = 0; i < old->field_count; i++) {
+ memcpy(dst, src, offsetof(struct nft_pipapo_field, lt));
+
+ dst->lt = kvzalloc(src->groups * NFT_PIPAPO_BUCKETS *
+ src->bsize * sizeof(*dst->lt),
+ GFP_KERNEL);
+ if (!dst->lt)
+ goto out_lt;
+
+ memcpy(dst->lt, src->lt,
+ src->bsize * sizeof(*dst->lt) *
+ src->groups * NFT_PIPAPO_BUCKETS);
+
+ dst->mt = kvmalloc(src->rules * sizeof(*src->mt), GFP_KERNEL);
+ if (!dst->mt)
+ goto out_mt;
+
+ memcpy(dst->mt, src->mt, src->rules * sizeof(*src->mt));
+ src++;
+ dst++;
+ }
+
+ return new;
+
+out_mt:
+ kvfree(dst->lt);
+out_lt:
+ for (dst--; i > 0; i--) {
+ kvfree(dst->mt);
+ kvfree(dst->lt);
+ dst--;
+ }
+ free_percpu(new->scratch);
+out_scratch:
+ kfree(new);
+
+ return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * pipapo_rules_same_key() - Get number of rules originated from the same entry
+ * @f: Field containing mapping table
+ * @first: Index of first rule in set of rules mapping to same entry
+ *
+ * Using the fact that all rules in a field that originated from the same entry
+ * will map to the same set of rules in the next field, or to the same element
+ * reference, return the cardinality of the set of rules that originated from
+ * the same entry as the rule with index @first, @first rule included.
+ *
+ * In pictures:
+ * rules
+ * field #0 0 1 2 3 4
+ * map to: 0 1 2-4 2-4 5-9
+ * . . ....... . ...
+ * | | | | \ \
+ * | | | | \ \
+ * | | | | \ \
+ * ' ' ' ' ' \
+ * in field #1 0 1 2 3 4 5 ...
+ *
+ * if this is called for rule 2 on field #0, it will return 3, as also rules 2
+ * and 3 in field 0 map to the same set of rules (2, 3, 4) in the next field.
+ *
+ * For the last field in a set, we can rely on associated entries to map to the
+ * same element references.
+ *
+ * Return: Number of rules that originated from the same entry as @first.
+ */
+static int pipapo_rules_same_key(struct nft_pipapo_field *f, int first)
+{
+ struct nft_pipapo_elem *e = NULL; /* Keep gcc happy */
+ int r;
+
+ for (r = first; r < f->rules; r++) {
+ if (r != first && e != f->mt[r].e)
+ return r - first;
+
+ e = f->mt[r].e;
+ }
+
+ if (r != first)
+ return r - first;
+
+ return 0;
+}
+
+/**
+ * pipapo_unmap() - Remove rules from mapping tables, renumber remaining ones
+ * @mt: Mapping array
+ * @rules: Original amount of rules in mapping table
+ * @start: First rule index to be removed
+ * @n: Amount of rules to be removed
+ * @to_offset: First rule index, in next field, this group of rules maps to
+ * @is_last: If this is the last field, delete reference from mapping array
+ *
+ * This is used to unmap rules from the mapping table for a single field,
+ * maintaining consistency and compactness for the existing ones.
+ *
+ * In pictures: let's assume that we want to delete rules 2 and 3 from the
+ * following mapping array:
+ *
+ * rules
+ * 0 1 2 3 4
+ * map to: 4-10 4-10 11-15 11-15 16-18
+ *
+ * the result will be:
+ *
+ * rules
+ * 0 1 2
+ * map to: 4-10 4-10 11-13
+ *
+ * for fields before the last one. In case this is the mapping table for the
+ * last field in a set, and rules map to pointers to &struct nft_pipapo_elem:
+ *
+ * rules
+ * 0 1 2 3 4
+ * element pointers: 0x42 0x42 0x33 0x33 0x44
+ *
+ * the result will be:
+ *
+ * rules
+ * 0 1 2
+ * element pointers: 0x42 0x42 0x44
+ */
+static void pipapo_unmap(union nft_pipapo_map_bucket *mt, int rules,
+ int start, int n, int to_offset, bool is_last)
+{
+ int i;
+
+ memmove(mt + start, mt + start + n, (rules - start - n) * sizeof(*mt));
+ memset(mt + rules - n, 0, n * sizeof(*mt));
+
+ if (is_last)
+ return;
+
+ for (i = start; i < rules - n; i++)
+ mt[i].to -= to_offset;
+}
+
+/**
+ * pipapo_drop() - Delete entry from lookup and mapping tables, given rule map
+ * @m: Matching data
+ * @rulemap Table of rule maps, arrays of first rule and amount of rules
+ * in next field a given entry maps to, for each field
+ *
+ * For each rule in lookup table buckets mapping to this set of rules, drop
+ * all bits set in lookup table mapping. In pictures, assuming we want to drop
+ * rules 0 and 1 from this lookup table:
+ *
+ * bucket
+ * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
+ * 0 0 1,2
+ * 1 1,2 0
+ * 2 0 1,2
+ * 3 0 1,2
+ * 4 0,1,2
+ * 5 0 1 2
+ * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
+ * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1
+ *
+ * rule 2 becomes rule 0, and the result will be:
+ *
+ * bucket
+ * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
+ * 0 0
+ * 1 0
+ * 2 0
+ * 3 0
+ * 4 0
+ * 5 0
+ * 6 0
+ * 7 0 0
+ *
+ * once this is done, call unmap() to drop all the corresponding rule references
+ * from mapping tables.
+ */
+static void pipapo_drop(struct nft_pipapo_match *m,
+ union nft_pipapo_map_bucket rulemap[])
+{
+ struct nft_pipapo_field *f;
+ int i;
+
+ nft_pipapo_for_each_field(f, i, m) {
+ int g;
+
+ for (g = 0; g < f->groups; g++) {
+ unsigned long *pos;
+ int b;
+
+ pos = f->lt + g * NFT_PIPAPO_BUCKETS * f->bsize;
+
+ for (b = 0; b < NFT_PIPAPO_BUCKETS; b++) {
+ bitmap_cut(pos, pos, rulemap[i].to,
+ rulemap[i].n,
+ f->bsize * BITS_PER_LONG);
+
+ pos += f->bsize;
+ }
+ }
+
+ pipapo_unmap(f->mt, f->rules, rulemap[i].to, rulemap[i].n,
+ rulemap[i + 1].n, i == m->field_count - 1);
+ if (pipapo_resize(f, f->rules, f->rules - rulemap[i].n)) {
+ /* We can ignore this, a failure to shrink tables down
+ * doesn't make tables invalid.
+ */
+ ;
+ }
+ f->rules -= rulemap[i].n;
+ }
+}
+
+/**
+ * pipapo_gc() - Drop expired entries from set, destroy start and end elements
+ * @set: nftables API set representation
+ * @m: Matching data
+ */
+static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m)
+{
+ struct nft_pipapo *priv = nft_set_priv(set);
+ int rules_f0, first_rule = 0;
+
+ while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) {
+ union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS];
+ struct nft_pipapo_field *f;
+ struct nft_pipapo_elem *e;
+ int i, start, rules_fx;
+
+ start = first_rule;
+ rules_fx = rules_f0;
+
+ nft_pipapo_for_each_field(f, i, m) {
+ rulemap[i].to = start;
+ rulemap[i].n = rules_fx;
+
+ if (i < m->field_count - 1) {
+ rules_fx = f->mt[start].n;
+ start = f->mt[start].to;
+ }
+ }
+
+ /* Pick the last field, and its last index */
+ f--;
+ i--;
+ e = f->mt[rulemap[i].to].e;
+ if (nft_set_elem_expired(&e->ext) &&
+ !nft_set_elem_mark_busy(&e->ext)) {
+ priv->dirty = true;
+ pipapo_drop(m, rulemap);
+
+ rcu_barrier();
+ nft_set_elem_destroy(set, e, true);
+
+ /* And check again current first rule, which is now the
+ * first we haven't checked.
+ */
+ } else {
+ first_rule += rules_f0;
+ }
+ }
+
+ priv->last_gc = jiffies;
+}
+
+/**
+ * pipapo_free_fields() - Free per-field tables contained in matching data
+ * @m: Matching data
+ */
+static void pipapo_free_fields(struct nft_pipapo_match *m)
+{
+ struct nft_pipapo_field *f;
+ int i;
+
+ nft_pipapo_for_each_field(f, i, m) {
+ kvfree(f->lt);
+ kvfree(f->mt);
+ }
+}
+
+/**
+ * pipapo_reclaim_match - RCU callback to free fields from old matching data
+ * @rcu: RCU head
+ */
+static void pipapo_reclaim_match(struct rcu_head *rcu)
+{
+ struct nft_pipapo_match *m;
+ int i;
+
+ m = container_of(rcu, struct nft_pipapo_match, rcu);
+
+ for_each_possible_cpu(i)
+ kfree(*per_cpu_ptr(m->scratch, i));
+
+ free_percpu(m->scratch);
+
+ pipapo_free_fields(m);
+
+ kfree(m);
+}
+
+/**
+ * pipapo_commit() - Replace lookup data with current working copy
+ * @set: nftables API set representation
+ *
+ * While at it, check if we should perform garbage collection on the working
+ * copy before committing it for lookup, and don't replace the table if the
+ * working copy doesn't have pending changes.
+ *
+ * We also need to create a new working copy for subsequent insertions and
+ * deletions.
+ */
+static void pipapo_commit(const struct nft_set *set)
+{
+ struct nft_pipapo *priv = nft_set_priv(set);
+ struct nft_pipapo_match *new_clone, *old;
+
+ if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set)))
+ pipapo_gc(set, priv->clone);
+
+ if (!priv->dirty)
+ return;
+
+ new_clone = pipapo_clone(priv->clone);
+ if (IS_ERR(new_clone))
+ return;
+
+ priv->dirty = false;
+
+ old = rcu_access_pointer(priv->match);
+ rcu_assign_pointer(priv->match, priv->clone);
+ if (old)
+ call_rcu(&old->rcu, pipapo_reclaim_match);
+
+ priv->clone = new_clone;
+}
+
+/**
+ * nft_pipapo_activate() - Mark element reference as active given key, commit
+ * @net: Network namespace
+ * @set: nftables API set representation
+ * @elem: nftables API element representation containing key data
+ *
+ * On insertion, elements are added to a copy of the matching data currently
+ * in use for lookups, and not directly inserted into current lookup data, so
+ * we'll take care of that by calling pipapo_commit() here. Both
+ * nft_pipapo_insert() and nft_pipapo_activate() are called once for each
+ * element, hence we can't purpose either one as a real commit operation.
+ */
+static void nft_pipapo_activate(const struct net *net,
+ const struct nft_set *set,
+ const struct nft_set_elem *elem)
+{
+ struct nft_pipapo_elem *e;
+
+ e = pipapo_get(net, set, (const u8 *)elem->key.val.data, 0);
+ if (IS_ERR(e))
+ return;
+
+ nft_set_elem_change_active(net, set, &e->ext);
+ nft_set_elem_clear_busy(&e->ext);
+
+ pipapo_commit(set);
+}
+
+/**
+ * pipapo_deactivate() - Check that element is in set, mark as inactive
+ * @net: Network namespace
+ * @set: nftables API set representation
+ * @data: Input key data
+ * @ext: nftables API extension pointer, used to check for end element
+ *
+ * This is a convenience function that can be called from both
+ * nft_pipapo_deactivate() and nft_pipapo_flush(), as they are in fact the same
+ * operation.
+ *
+ * Return: deactivated element if found, NULL otherwise.
+ */
+static void *pipapo_deactivate(const struct net *net, const struct nft_set *set,
+ const u8 *data, const struct nft_set_ext *ext)
+{
+ struct nft_pipapo_elem *e;
+
+ e = pipapo_get(net, set, data, nft_genmask_next(net));
+ if (IS_ERR(e))
+ return NULL;
+
+ nft_set_elem_change_active(net, set, &e->ext);
+
+ return e;
+}
+
+/**
+ * nft_pipapo_deactivate() - Call pipapo_deactivate() to make element inactive
+ * @net: Network namespace
+ * @set: nftables API set representation
+ * @elem: nftables API element representation containing key data
+ *
+ * Return: deactivated element if found, NULL otherwise.
+ */
+static void *nft_pipapo_deactivate(const struct net *net,
+ const struct nft_set *set,
+ const struct nft_set_elem *elem)
+{
+ const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+
+ return pipapo_deactivate(net, set, (const u8 *)elem->key.val.data, ext);
+}
+
+/**
+ * nft_pipapo_flush() - Call pipapo_deactivate() to make element inactive
+ * @net: Network namespace
+ * @set: nftables API set representation
+ * @elem: nftables API element representation containing key data
+ *
+ * This is functionally the same as nft_pipapo_deactivate(), with a slightly
+ * different interface, and it's also called once for each element in a set
+ * being flushed, so we can't implement, strictly speaking, a flush operation,
+ * which would otherwise be as simple as allocating an empty copy of the
+ * matching data.
+ *
+ * Note that we could in theory do that, mark the set as flushed, and ignore
+ * subsequent calls, but we would leak all the elements after the first one,
+ * because they wouldn't then be freed as result of API calls.
+ *
+ * Return: true if element was found and deactivated.
+ */
+static bool nft_pipapo_flush(const struct net *net, const struct nft_set *set,
+ void *elem)
+{
+ struct nft_pipapo_elem *e = elem;
+
+ return pipapo_deactivate(net, set, (const u8 *)nft_set_ext_key(&e->ext),
+ &e->ext);
+}
+
+/**
+ * pipapo_get_boundaries() - Get byte interval for associated rules
+ * @f: Field including lookup table
+ * @first_rule: First rule (lowest index)
+ * @rule_count: Number of associated rules
+ * @left: Byte expression for left boundary (start of range)
+ * @right: Byte expression for right boundary (end of range)
+ *
+ * Given the first rule and amount of rules that originated from the same entry,
+ * build the original range associated with the entry, and calculate the length
+ * of the originating netmask.
+ *
+ * In pictures:
+ *
+ * bucket
+ * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
+ * 0 1,2
+ * 1 1,2
+ * 2 1,2
+ * 3 1,2
+ * 4 1,2
+ * 5 1 2
+ * 6 1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
+ * 7 1,2 1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1
+ *
+ * this is the lookup table corresponding to the IPv4 range
+ * 192.168.1.0-192.168.2.1, which was expanded to the two composing netmasks,
+ * rule #1: 192.168.1.0/24, and rule #2: 192.168.2.0/31.
+ *
+ * This function fills @left and @right with the byte values of the leftmost
+ * and rightmost bucket indices for the lowest and highest rule indices,
+ * respectively. If @first_rule is 1 and @rule_count is 2, we obtain, in
+ * nibbles:
+ * left: < 12, 0, 10, 8, 0, 1, 0, 0 >
+ * right: < 12, 0, 10, 8, 0, 2, 2, 1 >
+ * corresponding to bytes:
+ * left: < 192, 168, 1, 0 >
+ * right: < 192, 168, 2, 1 >
+ * with mask length irrelevant here, unused on return, as the range is already
+ * defined by its start and end points. The mask length is relevant for a single
+ * ranged entry instead: if @first_rule is 1 and @rule_count is 1, we ignore
+ * rule 2 above: @left becomes < 192, 168, 1, 0 >, @right becomes
+ * < 192, 168, 1, 255 >, and the mask length, calculated from the distances
+ * between leftmost and rightmost bucket indices for each group, would be 24.
+ *
+ * Return: mask length, in bits.
+ */
+static int pipapo_get_boundaries(struct nft_pipapo_field *f, int first_rule,
+ int rule_count, u8 *left, u8 *right)
+{
+ u8 *l = left, *r = right;
+ int g, mask_len = 0;
+
+ for (g = 0; g < f->groups; g++) {
+ int b, x0, x1;
+
+ x0 = -1;
+ x1 = -1;
+ for (b = 0; b < NFT_PIPAPO_BUCKETS; b++) {
+ unsigned long *pos;
+
+ pos = f->lt + (g * NFT_PIPAPO_BUCKETS + b) * f->bsize;
+ if (test_bit(first_rule, pos) && x0 == -1)
+ x0 = b;
+ if (test_bit(first_rule + rule_count - 1, pos))
+ x1 = b;
+ }
+
+ if (g % 2) {
+ *(l++) |= x0 & 0x0f;
+ *(r++) |= x1 & 0x0f;
+ } else {
+ *l |= x0 << 4;
+ *r |= x1 << 4;
+ }
+
+ if (x1 - x0 == 0)
+ mask_len += 4;
+ else if (x1 - x0 == 1)
+ mask_len += 3;
+ else if (x1 - x0 == 3)
+ mask_len += 2;
+ else if (x1 - x0 == 7)
+ mask_len += 1;
+ }
+
+ return mask_len;
+}
+
+/**
+ * pipapo_match_field() - Match rules against byte ranges
+ * @f: Field including the lookup table
+ * @first_rule: First of associated rules originating from same entry
+ * @rule_count: Amount of associated rules
+ * @start: Start of range to be matched
+ * @end: End of range to be matched
+ *
+ * Return: true on match, false otherwise.
+ */
+static bool pipapo_match_field(struct nft_pipapo_field *f,
+ int first_rule, int rule_count,
+ const u8 *start, const u8 *end)
+{
+ u8 right[NFT_PIPAPO_MAX_BYTES] = { 0 };
+ u8 left[NFT_PIPAPO_MAX_BYTES] = { 0 };
+
+ pipapo_get_boundaries(f, first_rule, rule_count, left, right);
+
+ return !memcmp(start, left, f->groups / NFT_PIPAPO_GROUPS_PER_BYTE) &&
+ !memcmp(end, right, f->groups / NFT_PIPAPO_GROUPS_PER_BYTE);
+}
+
+/**
+ * nft_pipapo_remove() - Remove element given key, commit
+ * @net: Network namespace
+ * @set: nftables API set representation
+ * @elem: nftables API element representation containing key data
+ *
+ * Similarly to nft_pipapo_activate(), this is used as commit operation by the
+ * API, but it's called once per element in the pending transaction, so we can't
+ * implement this as a single commit operation. Closest we can get is to remove
+ * the matched element here, if any, and commit the updated matching data.
+ */
+static void nft_pipapo_remove(const struct net *net, const struct nft_set *set,
+ const struct nft_set_elem *elem)
+{
+ const u8 *data = (const u8 *)elem->key.val.data;
+ struct nft_pipapo *priv = nft_set_priv(set);
+ struct nft_pipapo_match *m = priv->clone;
+ int rules_f0, first_rule = 0;
+ struct nft_pipapo_elem *e;
+
+ e = pipapo_get(net, set, data, 0);
+ if (IS_ERR(e))
+ return;
+
+ while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) {
+ union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS];
+ const u8 *match_start, *match_end;
+ struct nft_pipapo_field *f;
+ int i, start, rules_fx;
+
+ match_start = data;
+ match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data;
+
+ start = first_rule;
+ rules_fx = rules_f0;
+
+ nft_pipapo_for_each_field(f, i, m) {
+ if (!pipapo_match_field(f, start, rules_fx,
+ match_start, match_end))
+ break;
+
+ rulemap[i].to = start;
+ rulemap[i].n = rules_fx;
+
+ rules_fx = f->mt[start].n;
+ start = f->mt[start].to;
+
+ match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups);
+ match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups);
+ }
+
+ if (i == m->field_count) {
+ priv->dirty = true;
+ pipapo_drop(m, rulemap);
+ pipapo_commit(set);
+ return;
+ }
+
+ first_rule += rules_f0;
+ }
+}
+
+/**
+ * nft_pipapo_walk() - Walk over elements
+ * @ctx: nftables API context
+ * @set: nftables API set representation
+ * @iter: Iterator
+ *
+ * As elements are referenced in the mapping array for the last field, directly
+ * scan that array: there's no need to follow rule mappings from the first
+ * field.
+ */
+static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set,
+ struct nft_set_iter *iter)
+{
+ struct nft_pipapo *priv = nft_set_priv(set);
+ struct nft_pipapo_match *m;
+ struct nft_pipapo_field *f;
+ int i, r;
+
+ rcu_read_lock();
+ m = rcu_dereference(priv->match);
+
+ if (unlikely(!m))
+ goto out;
+
+ for (i = 0, f = m->f; i < m->field_count - 1; i++, f++)
+ ;
+
+ for (r = 0; r < f->rules; r++) {
+ struct nft_pipapo_elem *e;
+ struct nft_set_elem elem;
+
+ if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e)
+ continue;
+
+ if (iter->count < iter->skip)
+ goto cont;
+
+ e = f->mt[r].e;
+ if (nft_set_elem_expired(&e->ext))
+ goto cont;
+
+ elem.priv = e;
+
+ iter->err = iter->fn(ctx, set, iter, &elem);
+ if (iter->err < 0)
+ goto out;
+
+cont:
+ iter->count++;
+ }
+
+out:
+ rcu_read_unlock();
+}
+
+/**
+ * nft_pipapo_privsize() - Return the size of private data for the set
+ * @nla: netlink attributes, ignored as size doesn't depend on them
+ * @desc: Set description, ignored as size doesn't depend on it
+ *
+ * Return: size of private data for this set implementation, in bytes
+ */
+static u64 nft_pipapo_privsize(const struct nlattr * const nla[],
+ const struct nft_set_desc *desc)
+{
+ return sizeof(struct nft_pipapo);
+}
+
+/**
+ * nft_pipapo_estimate() - Estimate set size, space and lookup complexity
+ * @desc: Set description, element count and field description used here
+ * @features: Flags: NFT_SET_INTERVAL needs to be there
+ * @est: Storage for estimation data
+ *
+ * The size for this set type can vary dramatically, as it depends on the number
+ * of rules (composing netmasks) the entries expand to. We compute the worst
+ * case here.
+ *
+ * In general, for a non-ranged entry or a single composing netmask, we need
+ * one bit in each of the sixteen NFT_PIPAPO_BUCKETS, for each 4-bit group (that
+ * is, each input bit needs four bits of matching data), plus a bucket in the
+ * mapping table for each field.
+ *
+ * Return: true only for compatible range concatenations
+ */
+static bool nft_pipapo_estimate(const struct nft_set_desc *desc, u32 features,
+ struct nft_set_estimate *est)
+{
+ unsigned long entry_size;
+ int i;
+
+ if (!(features & NFT_SET_INTERVAL) || desc->field_count <= 1)
+ return false;
+
+ for (i = 0, entry_size = 0; i < desc->field_count; i++) {
+ unsigned long rules;
+
+ if (desc->field_len[i] > NFT_PIPAPO_MAX_BYTES)
+ return false;
+
+ /* Worst-case ranges for each concatenated field: each n-bit
+ * field can expand to up to n * 2 rules in each bucket, and
+ * each rule also needs a mapping bucket.
+ */
+ rules = ilog2(desc->field_len[i] * BITS_PER_BYTE) * 2;
+ entry_size += rules * NFT_PIPAPO_BUCKETS / BITS_PER_BYTE;
+ entry_size += rules * sizeof(union nft_pipapo_map_bucket);
+ }
+
+ /* Rules in lookup and mapping tables are needed for each entry */
+ est->size = desc->size * entry_size;
+ if (est->size && div_u64(est->size, desc->size) != entry_size)
+ return false;
+
+ est->size += sizeof(struct nft_pipapo) +
+ sizeof(struct nft_pipapo_match) * 2;
+
+ est->size += sizeof(struct nft_pipapo_field) * desc->field_count;
+
+ est->lookup = NFT_SET_CLASS_O_LOG_N;
+
+ est->space = NFT_SET_CLASS_O_N;
+
+ return true;
+}
+
+/**
+ * nft_pipapo_init() - Initialise data for a set instance
+ * @set: nftables API set representation
+ * @desc: Set description
+ * @nla: netlink attributes
+ *
+ * Validate number and size of fields passed as NFTA_SET_DESC_CONCAT netlink
+ * attributes, initialise internal set parameters, current instance of matching
+ * data and a copy for subsequent insertions.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+static int nft_pipapo_init(const struct nft_set *set,
+ const struct nft_set_desc *desc,
+ const struct nlattr * const nla[])
+{
+ struct nft_pipapo *priv = nft_set_priv(set);
+ struct nft_pipapo_match *m;
+ struct nft_pipapo_field *f;
+ int err, i;
+
+ if (desc->field_count > NFT_PIPAPO_MAX_FIELDS)
+ return -EINVAL;
+
+ m = kmalloc(sizeof(*priv->match) + sizeof(*f) * desc->field_count,
+ GFP_KERNEL);
+ if (!m)
+ return -ENOMEM;
+
+ m->field_count = desc->field_count;
+ m->bsize_max = 0;
+
+ m->scratch = alloc_percpu(unsigned long *);
+ if (!m->scratch) {
+ err = -ENOMEM;
+ goto out_free;
+ }
+ for_each_possible_cpu(i)
+ *per_cpu_ptr(m->scratch, i) = NULL;
+
+ rcu_head_init(&m->rcu);
+
+ nft_pipapo_for_each_field(f, i, m) {
+ f->groups = desc->field_len[i] * NFT_PIPAPO_GROUPS_PER_BYTE;
+ priv->groups += f->groups;
+
+ priv->width += round_up(desc->field_len[i], sizeof(u32));
+
+ f->bsize = 0;
+ f->rules = 0;
+ f->lt = NULL;
+ f->mt = NULL;
+ }
+
+ /* Create an initial clone of matching data for next insertion */
+ priv->clone = pipapo_clone(m);
+ if (IS_ERR(priv->clone)) {
+ err = PTR_ERR(priv->clone);
+ goto out_free;
+ }
+
+ priv->dirty = false;
+
+ rcu_assign_pointer(priv->match, m);
+
+ return 0;
+
+out_free:
+ free_percpu(m->scratch);
+ kfree(m);
+
+ return err;
+}
+
+/**
+ * nft_pipapo_destroy() - Free private data for set and all committed elements
+ * @set: nftables API set representation
+ */
+static void nft_pipapo_destroy(const struct nft_set *set)
+{
+ struct nft_pipapo *priv = nft_set_priv(set);
+ struct nft_pipapo_match *m;
+ struct nft_pipapo_field *f;
+ int i, r, cpu;
+
+ m = rcu_dereference_protected(priv->match, true);
+ if (m) {
+ rcu_barrier();
+
+ for (i = 0, f = m->f; i < m->field_count - 1; i++, f++)
+ ;
+
+ for (r = 0; r < f->rules; r++) {
+ struct nft_pipapo_elem *e;
+
+ if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e)
+ continue;
+
+ e = f->mt[r].e;
+
+ nft_set_elem_destroy(set, e, true);
+ }
+
+ for_each_possible_cpu(cpu)
+ kfree(*per_cpu_ptr(m->scratch, cpu));
+ free_percpu(m->scratch);
+
+ pipapo_free_fields(m);
+ kfree(m);
+ priv->match = NULL;
+ }
+
+ if (priv->clone) {
+ for_each_possible_cpu(cpu)
+ kfree(*per_cpu_ptr(priv->clone->scratch, cpu));
+ free_percpu(priv->clone->scratch);
+
+ pipapo_free_fields(priv->clone);
+ kfree(priv->clone);
+ priv->clone = NULL;
+ }
+}
+
+/**
+ * nft_pipapo_gc_init() - Initialise garbage collection
+ * @set: nftables API set representation
+ *
+ * Instead of actually setting up a periodic work for garbage collection, as
+ * this operation requires a swap of matching data with the working copy, we'll
+ * do that opportunistically with other commit operations if the interval is
+ * elapsed, so we just need to set the current jiffies timestamp here.
+ */
+static void nft_pipapo_gc_init(const struct nft_set *set)
+{
+ struct nft_pipapo *priv = nft_set_priv(set);
+
+ priv->last_gc = jiffies;
+}
+
+struct nft_set_type nft_set_pipapo_type __read_mostly = {
+ .owner = THIS_MODULE,
+ .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT |
+ NFT_SET_TIMEOUT,
+ .ops = {
+ .lookup = nft_pipapo_lookup,
+ .insert = nft_pipapo_insert,
+ .activate = nft_pipapo_activate,
+ .deactivate = nft_pipapo_deactivate,
+ .flush = nft_pipapo_flush,
+ .remove = nft_pipapo_remove,
+ .walk = nft_pipapo_walk,
+ .get = nft_pipapo_get,
+ .privsize = nft_pipapo_privsize,
+ .estimate = nft_pipapo_estimate,
+ .init = nft_pipapo_init,
+ .destroy = nft_pipapo_destroy,
+ .gc_init = nft_pipapo_gc_init,
+ .elemsize = offsetof(struct nft_pipapo_elem, ext),
+ },
+};
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index a9f804f..5000b93 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -466,6 +466,9 @@ static void nft_rbtree_destroy(const struct nft_set *set)
static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
struct nft_set_estimate *est)
{
+ if (desc->field_count > 1)
+ return false;
+
if (desc->size)
est->size = sizeof(struct nft_rbtree) +
desc->size * sizeof(struct nft_rbtree_elem);
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 23cd163..4c3f2e24 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -76,7 +76,7 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx,
struct nft_tunnel *priv = nft_expr_priv(expr);
u32 len;
- if (!tb[NFTA_TUNNEL_KEY] &&
+ if (!tb[NFTA_TUNNEL_KEY] ||
!tb[NFTA_TUNNEL_DREG])
return -EINVAL;
@@ -267,6 +267,9 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr,
if (err < 0)
return err;
+ if (!tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION])
+ return -EINVAL;
+
version = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION]));
switch (version) {
case ERSPAN_VERSION:
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index ced3fc8..bccd47c 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -357,21 +357,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
return 0;
}
-static bool select_all(const struct xt_hashlimit_htable *ht,
- const struct dsthash_ent *he)
-{
- return true;
-}
-
-static bool select_gc(const struct xt_hashlimit_htable *ht,
- const struct dsthash_ent *he)
-{
- return time_after_eq(jiffies, he->expires);
-}
-
-static void htable_selective_cleanup(struct xt_hashlimit_htable *ht,
- bool (*select)(const struct xt_hashlimit_htable *ht,
- const struct dsthash_ent *he))
+static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, bool select_all)
{
unsigned int i;
@@ -381,7 +367,7 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht,
spin_lock_bh(&ht->lock);
hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) {
- if ((*select)(ht, dh))
+ if (time_after_eq(jiffies, dh->expires) || select_all)
dsthash_free(ht, dh);
}
spin_unlock_bh(&ht->lock);
@@ -395,7 +381,7 @@ static void htable_gc(struct work_struct *work)
ht = container_of(work, struct xt_hashlimit_htable, gc_work.work);
- htable_selective_cleanup(ht, select_gc);
+ htable_selective_cleanup(ht, false);
queue_delayed_work(system_power_efficient_wq,
&ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval));
@@ -419,7 +405,7 @@ static void htable_destroy(struct xt_hashlimit_htable *hinfo)
{
cancel_delayed_work_sync(&hinfo->gc_work);
htable_remove_proc_entry(hinfo);
- htable_selective_cleanup(hinfo, select_all);
+ htable_selective_cleanup(hinfo, true);
kfree(hinfo->name);
vfree(hinfo);
}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index e3a37d2..659c2a7 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -321,8 +321,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
}
/* Queue all of the segments. */
- skb = segs;
- do {
+ skb_list_walk_safe(segs, skb, nskb) {
if (gso_type & SKB_GSO_UDP && skb != segs)
key = &later_key;
@@ -330,17 +329,15 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
if (err)
break;
- } while ((skb = skb->next));
+ }
/* Free all of the segments. */
- skb = segs;
- do {
- nskb = skb->next;
+ skb_list_walk_safe(segs, skb, nskb) {
if (err)
kfree_skb(skb);
else
consume_skb(skb);
- } while ((skb = nskb));
+ }
return err;
}
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 88f98f27a..5a8e42a 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -8,6 +8,8 @@
#include <linux/qrtr.h>
#include <linux/termios.h> /* For TIOCINQ/OUTQ */
#include <linux/numa.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
#include <net/sock.h>
@@ -97,10 +99,11 @@ static inline struct qrtr_sock *qrtr_sk(struct sock *sk)
static unsigned int qrtr_local_nid = NUMA_NO_NODE;
/* for node ids */
-static RADIX_TREE(qrtr_nodes, GFP_KERNEL);
+static RADIX_TREE(qrtr_nodes, GFP_ATOMIC);
+static DEFINE_SPINLOCK(qrtr_nodes_lock);
/* broadcast list */
static LIST_HEAD(qrtr_all_nodes);
-/* lock for qrtr_nodes, qrtr_all_nodes and node reference */
+/* lock for qrtr_all_nodes and node reference */
static DEFINE_MUTEX(qrtr_node_lock);
/* local port allocation management */
@@ -113,8 +116,9 @@ static DEFINE_MUTEX(qrtr_port_lock);
* @ep: endpoint
* @ref: reference count for node
* @nid: node id
+ * @qrtr_tx_flow: tree of qrtr_tx_flow, keyed by node << 32 | port
+ * @qrtr_tx_lock: lock for qrtr_tx_flow inserts
* @rx_queue: receive queue
- * @work: scheduled work struct for recv work
* @item: list item for broadcast list
*/
struct qrtr_node {
@@ -123,17 +127,36 @@ struct qrtr_node {
struct kref ref;
unsigned int nid;
+ struct radix_tree_root qrtr_tx_flow;
+ struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */
+
struct sk_buff_head rx_queue;
- struct work_struct work;
struct list_head item;
};
+/**
+ * struct qrtr_tx_flow - tx flow control
+ * @resume_tx: waiters for a resume tx from the remote
+ * @pending: number of waiting senders
+ * @tx_failed: indicates that a message with confirm_rx flag was lost
+ */
+struct qrtr_tx_flow {
+ struct wait_queue_head resume_tx;
+ int pending;
+ int tx_failed;
+};
+
+#define QRTR_TX_FLOW_HIGH 10
+#define QRTR_TX_FLOW_LOW 5
+
static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb,
int type, struct sockaddr_qrtr *from,
struct sockaddr_qrtr *to);
static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
int type, struct sockaddr_qrtr *from,
struct sockaddr_qrtr *to);
+static struct qrtr_sock *qrtr_port_lookup(int port);
+static void qrtr_port_put(struct qrtr_sock *ipc);
/* Release node resources and free the node.
*
@@ -143,15 +166,25 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
static void __qrtr_node_release(struct kref *kref)
{
struct qrtr_node *node = container_of(kref, struct qrtr_node, ref);
+ struct radix_tree_iter iter;
+ unsigned long flags;
+ void __rcu **slot;
+ spin_lock_irqsave(&qrtr_nodes_lock, flags);
if (node->nid != QRTR_EP_NID_AUTO)
radix_tree_delete(&qrtr_nodes, node->nid);
+ spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
list_del(&node->item);
mutex_unlock(&qrtr_node_lock);
- cancel_work_sync(&node->work);
skb_queue_purge(&node->rx_queue);
+
+ /* Free tx flow counters */
+ radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) {
+ radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot);
+ kfree(*slot);
+ }
kfree(node);
}
@@ -171,6 +204,126 @@ static void qrtr_node_release(struct qrtr_node *node)
kref_put_mutex(&node->ref, __qrtr_node_release, &qrtr_node_lock);
}
+/**
+ * qrtr_tx_resume() - reset flow control counter
+ * @node: qrtr_node that the QRTR_TYPE_RESUME_TX packet arrived on
+ * @skb: resume_tx packet
+ */
+static void qrtr_tx_resume(struct qrtr_node *node, struct sk_buff *skb)
+{
+ struct qrtr_ctrl_pkt *pkt = (struct qrtr_ctrl_pkt *)skb->data;
+ u64 remote_node = le32_to_cpu(pkt->client.node);
+ u32 remote_port = le32_to_cpu(pkt->client.port);
+ struct qrtr_tx_flow *flow;
+ unsigned long key;
+
+ key = remote_node << 32 | remote_port;
+
+ rcu_read_lock();
+ flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
+ rcu_read_unlock();
+ if (flow) {
+ spin_lock(&flow->resume_tx.lock);
+ flow->pending = 0;
+ spin_unlock(&flow->resume_tx.lock);
+ wake_up_interruptible_all(&flow->resume_tx);
+ }
+
+ consume_skb(skb);
+}
+
+/**
+ * qrtr_tx_wait() - flow control for outgoing packets
+ * @node: qrtr_node that the packet is to be send to
+ * @dest_node: node id of the destination
+ * @dest_port: port number of the destination
+ * @type: type of message
+ *
+ * The flow control scheme is based around the low and high "watermarks". When
+ * the low watermark is passed the confirm_rx flag is set on the outgoing
+ * message, which will trigger the remote to send a control message of the type
+ * QRTR_TYPE_RESUME_TX to reset the counter. If the high watermark is hit
+ * further transmision should be paused.
+ *
+ * Return: 1 if confirm_rx should be set, 0 otherwise or errno failure
+ */
+static int qrtr_tx_wait(struct qrtr_node *node, int dest_node, int dest_port,
+ int type)
+{
+ unsigned long key = (u64)dest_node << 32 | dest_port;
+ struct qrtr_tx_flow *flow;
+ int confirm_rx = 0;
+ int ret;
+
+ /* Never set confirm_rx on non-data packets */
+ if (type != QRTR_TYPE_DATA)
+ return 0;
+
+ mutex_lock(&node->qrtr_tx_lock);
+ flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
+ if (!flow) {
+ flow = kzalloc(sizeof(*flow), GFP_KERNEL);
+ if (flow) {
+ init_waitqueue_head(&flow->resume_tx);
+ radix_tree_insert(&node->qrtr_tx_flow, key, flow);
+ }
+ }
+ mutex_unlock(&node->qrtr_tx_lock);
+
+ /* Set confirm_rx if we where unable to find and allocate a flow */
+ if (!flow)
+ return 1;
+
+ spin_lock_irq(&flow->resume_tx.lock);
+ ret = wait_event_interruptible_locked_irq(flow->resume_tx,
+ flow->pending < QRTR_TX_FLOW_HIGH ||
+ flow->tx_failed ||
+ !node->ep);
+ if (ret < 0) {
+ confirm_rx = ret;
+ } else if (!node->ep) {
+ confirm_rx = -EPIPE;
+ } else if (flow->tx_failed) {
+ flow->tx_failed = 0;
+ confirm_rx = 1;
+ } else {
+ flow->pending++;
+ confirm_rx = flow->pending == QRTR_TX_FLOW_LOW;
+ }
+ spin_unlock_irq(&flow->resume_tx.lock);
+
+ return confirm_rx;
+}
+
+/**
+ * qrtr_tx_flow_failed() - flag that tx of confirm_rx flagged messages failed
+ * @node: qrtr_node that the packet is to be send to
+ * @dest_node: node id of the destination
+ * @dest_port: port number of the destination
+ *
+ * Signal that the transmission of a message with confirm_rx flag failed. The
+ * flow's "pending" counter will keep incrementing towards QRTR_TX_FLOW_HIGH,
+ * at which point transmission would stall forever waiting for the resume TX
+ * message associated with the dropped confirm_rx message.
+ * Work around this by marking the flow as having a failed transmission and
+ * cause the next transmission attempt to be sent with the confirm_rx.
+ */
+static void qrtr_tx_flow_failed(struct qrtr_node *node, int dest_node,
+ int dest_port)
+{
+ unsigned long key = (u64)dest_node << 32 | dest_port;
+ struct qrtr_tx_flow *flow;
+
+ rcu_read_lock();
+ flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
+ rcu_read_unlock();
+ if (flow) {
+ spin_lock_irq(&flow->resume_tx.lock);
+ flow->tx_failed = 1;
+ spin_unlock_irq(&flow->resume_tx.lock);
+ }
+}
+
/* Pass an outgoing packet socket buffer to the endpoint driver. */
static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
int type, struct sockaddr_qrtr *from,
@@ -179,6 +332,13 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
struct qrtr_hdr_v1 *hdr;
size_t len = skb->len;
int rc = -ENODEV;
+ int confirm_rx;
+
+ confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type);
+ if (confirm_rx < 0) {
+ kfree_skb(skb);
+ return confirm_rx;
+ }
hdr = skb_push(skb, sizeof(*hdr));
hdr->version = cpu_to_le32(QRTR_PROTO_VER_1);
@@ -194,9 +354,9 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
}
hdr->size = cpu_to_le32(len);
- hdr->confirm_rx = 0;
+ hdr->confirm_rx = !!confirm_rx;
- skb_put_padto(skb, ALIGN(len, 4));
+ skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
mutex_lock(&node->ep_lock);
if (node->ep)
@@ -205,6 +365,11 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
kfree_skb(skb);
mutex_unlock(&node->ep_lock);
+ /* Need to ensure that a subsequent message carries the otherwise lost
+ * confirm_rx flag if we dropped this one */
+ if (rc && confirm_rx)
+ qrtr_tx_flow_failed(node, to->sq_node, to->sq_port);
+
return rc;
}
@@ -215,11 +380,12 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
static struct qrtr_node *qrtr_node_lookup(unsigned int nid)
{
struct qrtr_node *node;
+ unsigned long flags;
- mutex_lock(&qrtr_node_lock);
+ spin_lock_irqsave(&qrtr_nodes_lock, flags);
node = radix_tree_lookup(&qrtr_nodes, nid);
node = qrtr_node_acquire(node);
- mutex_unlock(&qrtr_node_lock);
+ spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
return node;
}
@@ -231,13 +397,15 @@ static struct qrtr_node *qrtr_node_lookup(unsigned int nid)
*/
static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid)
{
+ unsigned long flags;
+
if (node->nid != QRTR_EP_NID_AUTO || nid == QRTR_EP_NID_AUTO)
return;
- mutex_lock(&qrtr_node_lock);
+ spin_lock_irqsave(&qrtr_nodes_lock, flags);
radix_tree_insert(&qrtr_nodes, nid, node);
node->nid = nid;
- mutex_unlock(&qrtr_node_lock);
+ spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
}
/**
@@ -253,6 +421,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
struct qrtr_node *node = ep->node;
const struct qrtr_hdr_v1 *v1;
const struct qrtr_hdr_v2 *v2;
+ struct qrtr_sock *ipc;
struct sk_buff *skb;
struct qrtr_cb *cb;
unsigned int size;
@@ -311,13 +480,26 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
if (len != ALIGN(size, 4) + hdrlen)
goto err;
- if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA)
+ if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA &&
+ cb->type != QRTR_TYPE_RESUME_TX)
goto err;
skb_put_data(skb, data + hdrlen, size);
- skb_queue_tail(&node->rx_queue, skb);
- schedule_work(&node->work);
+ qrtr_node_assign(node, cb->src_node);
+
+ if (cb->type == QRTR_TYPE_RESUME_TX) {
+ qrtr_tx_resume(node, skb);
+ } else {
+ ipc = qrtr_port_lookup(cb->dst_port);
+ if (!ipc)
+ goto err;
+
+ if (sock_queue_rcv_skb(&ipc->sk, skb))
+ goto err;
+
+ qrtr_port_put(ipc);
+ }
return 0;
@@ -352,61 +534,6 @@ static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt)
return skb;
}
-static struct qrtr_sock *qrtr_port_lookup(int port);
-static void qrtr_port_put(struct qrtr_sock *ipc);
-
-/* Handle and route a received packet.
- *
- * This will auto-reply with resume-tx packet as necessary.
- */
-static void qrtr_node_rx_work(struct work_struct *work)
-{
- struct qrtr_node *node = container_of(work, struct qrtr_node, work);
- struct qrtr_ctrl_pkt *pkt;
- struct sockaddr_qrtr dst;
- struct sockaddr_qrtr src;
- struct sk_buff *skb;
-
- while ((skb = skb_dequeue(&node->rx_queue)) != NULL) {
- struct qrtr_sock *ipc;
- struct qrtr_cb *cb;
- int confirm;
-
- cb = (struct qrtr_cb *)skb->cb;
- src.sq_node = cb->src_node;
- src.sq_port = cb->src_port;
- dst.sq_node = cb->dst_node;
- dst.sq_port = cb->dst_port;
- confirm = !!cb->confirm_rx;
-
- qrtr_node_assign(node, cb->src_node);
-
- ipc = qrtr_port_lookup(cb->dst_port);
- if (!ipc) {
- kfree_skb(skb);
- } else {
- if (sock_queue_rcv_skb(&ipc->sk, skb))
- kfree_skb(skb);
-
- qrtr_port_put(ipc);
- }
-
- if (confirm) {
- skb = qrtr_alloc_ctrl_packet(&pkt);
- if (!skb)
- break;
-
- pkt->cmd = cpu_to_le32(QRTR_TYPE_RESUME_TX);
- pkt->client.node = cpu_to_le32(dst.sq_node);
- pkt->client.port = cpu_to_le32(dst.sq_port);
-
- if (qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX,
- &dst, &src))
- break;
- }
- }
-}
-
/**
* qrtr_endpoint_register() - register a new endpoint
* @ep: endpoint to register
@@ -426,13 +553,15 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid)
if (!node)
return -ENOMEM;
- INIT_WORK(&node->work, qrtr_node_rx_work);
kref_init(&node->ref);
mutex_init(&node->ep_lock);
skb_queue_head_init(&node->rx_queue);
node->nid = QRTR_EP_NID_AUTO;
node->ep = ep;
+ INIT_RADIX_TREE(&node->qrtr_tx_flow, GFP_KERNEL);
+ mutex_init(&node->qrtr_tx_lock);
+
qrtr_node_assign(node, nid);
mutex_lock(&qrtr_node_lock);
@@ -453,8 +582,11 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
struct qrtr_node *node = ep->node;
struct sockaddr_qrtr src = {AF_QIPCRTR, node->nid, QRTR_PORT_CTRL};
struct sockaddr_qrtr dst = {AF_QIPCRTR, qrtr_local_nid, QRTR_PORT_CTRL};
+ struct radix_tree_iter iter;
struct qrtr_ctrl_pkt *pkt;
+ struct qrtr_tx_flow *flow;
struct sk_buff *skb;
+ void __rcu **slot;
mutex_lock(&node->ep_lock);
node->ep = NULL;
@@ -467,6 +599,14 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst);
}
+ /* Wake up any transmitters waiting for resume-tx from the node */
+ mutex_lock(&node->qrtr_tx_lock);
+ radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) {
+ flow = *slot;
+ wake_up_interruptible_all(&flow->resume_tx);
+ }
+ mutex_unlock(&node->qrtr_tx_lock);
+
qrtr_node_release(node);
ep->node = NULL;
}
@@ -483,11 +623,11 @@ static struct qrtr_sock *qrtr_port_lookup(int port)
if (port == QRTR_PORT_CTRL)
port = 0;
- mutex_lock(&qrtr_port_lock);
+ rcu_read_lock();
ipc = idr_find(&qrtr_ports, port);
if (ipc)
sock_hold(&ipc->sk);
- mutex_unlock(&qrtr_port_lock);
+ rcu_read_unlock();
return ipc;
}
@@ -529,6 +669,10 @@ static void qrtr_port_remove(struct qrtr_sock *ipc)
mutex_lock(&qrtr_port_lock);
idr_remove(&qrtr_ports, port);
mutex_unlock(&qrtr_port_lock);
+
+ /* Ensure that if qrtr_port_lookup() did enter the RCU read section we
+ * wait for it to up increment the refcount */
+ synchronize_rcu();
}
/* Assign port number to socket.
@@ -816,6 +960,34 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
return rc;
}
+static int qrtr_send_resume_tx(struct qrtr_cb *cb)
+{
+ struct sockaddr_qrtr remote = { AF_QIPCRTR, cb->src_node, cb->src_port };
+ struct sockaddr_qrtr local = { AF_QIPCRTR, cb->dst_node, cb->dst_port };
+ struct qrtr_ctrl_pkt *pkt;
+ struct qrtr_node *node;
+ struct sk_buff *skb;
+ int ret;
+
+ node = qrtr_node_lookup(remote.sq_node);
+ if (!node)
+ return -EINVAL;
+
+ skb = qrtr_alloc_ctrl_packet(&pkt);
+ if (!skb)
+ return -ENOMEM;
+
+ pkt->cmd = cpu_to_le32(QRTR_TYPE_RESUME_TX);
+ pkt->client.node = cpu_to_le32(cb->dst_node);
+ pkt->client.port = cpu_to_le32(cb->dst_port);
+
+ ret = qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX, &local, &remote);
+
+ qrtr_node_release(node);
+
+ return ret;
+}
+
static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg,
size_t size, int flags)
{
@@ -838,6 +1010,7 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg,
release_sock(sk);
return rc;
}
+ cb = (struct qrtr_cb *)skb->cb;
copied = skb->len;
if (copied > size) {
@@ -851,7 +1024,6 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg,
rc = copied;
if (addr) {
- cb = (struct qrtr_cb *)skb->cb;
addr->sq_family = AF_QIPCRTR;
addr->sq_node = cb->src_node;
addr->sq_port = cb->src_port;
@@ -859,6 +1031,9 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg,
}
out:
+ if (cb->confirm_rx)
+ qrtr_send_resume_tx(cb);
+
skb_free_datagram(sk, skb);
release_sock(sk);
diff --git a/net/rds/ib.c b/net/rds/ib.c
index 3fd5f40..a792d8a 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -156,6 +156,13 @@ static void rds_ib_add_one(struct ib_device *device)
has_fmr = (device->ops.alloc_fmr && device->ops.dealloc_fmr &&
device->ops.map_phys_fmr && device->ops.unmap_fmr);
rds_ibdev->use_fastreg = (has_fr && !has_fmr);
+ rds_ibdev->odp_capable =
+ !!(device->attrs.device_cap_flags &
+ IB_DEVICE_ON_DEMAND_PAGING) &&
+ !!(device->attrs.odp_caps.per_transport_caps.rc_odp_caps &
+ IB_ODP_SUPPORT_WRITE) &&
+ !!(device->attrs.odp_caps.per_transport_caps.rc_odp_caps &
+ IB_ODP_SUPPORT_READ);
rds_ibdev->fmr_max_remaps = device->attrs.max_map_per_fmr?: 32;
rds_ibdev->max_1m_mrs = device->attrs.max_mr ?
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 6e6f247..0296f1f 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -247,7 +247,8 @@ struct rds_ib_device {
struct ib_device *dev;
struct ib_pd *pd;
struct dma_pool *rid_hdrs_pool; /* RDS headers DMA pool */
- bool use_fastreg;
+ u8 use_fastreg:1;
+ u8 odp_capable:1;
unsigned int max_mrs;
struct rds_ib_mr_pool *mr_1m_pool;
diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h
index 9045a8c..0c8252d7 100644
--- a/net/rds/ib_mr.h
+++ b/net/rds/ib_mr.h
@@ -67,6 +67,7 @@ struct rds_ib_frmr {
/* This is stored as mr->r_trans_private. */
struct rds_ib_mr {
+ struct delayed_work work;
struct rds_ib_device *device;
struct rds_ib_mr_pool *pool;
struct rds_ib_connection *ic;
@@ -81,9 +82,11 @@ struct rds_ib_mr {
unsigned int sg_len;
int sg_dma_len;
+ u8 odp:1;
union {
struct rds_ib_fmr fmr;
struct rds_ib_frmr frmr;
+ struct ib_mr *mr;
} u;
};
@@ -122,12 +125,14 @@ void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *);
void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
struct rds_sock *rs, u32 *key_ret,
- struct rds_connection *conn);
+ struct rds_connection *conn, u64 start, u64 length,
+ int need_odp);
void rds_ib_sync_mr(void *trans_private, int dir);
void rds_ib_free_mr(void *trans_private, int invalidate);
void rds_ib_flush_mrs(void);
int rds_ib_mr_init(void);
void rds_ib_mr_exit(void);
+u32 rds_ib_get_lkey(void *trans_private);
void __rds_ib_teardown_mr(struct rds_ib_mr *);
void rds_ib_teardown_mr(struct rds_ib_mr *);
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index c8c1e3a..b34b24e 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -37,8 +37,15 @@
#include "rds_single_path.h"
#include "ib_mr.h"
+#include "rds.h"
struct workqueue_struct *rds_ib_mr_wq;
+struct rds_ib_dereg_odp_mr {
+ struct work_struct work;
+ struct ib_mr *mr;
+};
+
+static void rds_ib_odp_mr_worker(struct work_struct *work);
static struct rds_ib_device *rds_ib_get_device(__be32 ipaddr)
{
@@ -213,6 +220,9 @@ void rds_ib_sync_mr(void *trans_private, int direction)
struct rds_ib_mr *ibmr = trans_private;
struct rds_ib_device *rds_ibdev = ibmr->device;
+ if (ibmr->odp)
+ return;
+
switch (direction) {
case DMA_FROM_DEVICE:
ib_dma_sync_sg_for_cpu(rds_ibdev->dev, ibmr->sg,
@@ -482,6 +492,16 @@ void rds_ib_free_mr(void *trans_private, int invalidate)
rdsdebug("RDS/IB: free_mr nents %u\n", ibmr->sg_len);
+ if (ibmr->odp) {
+ /* A MR created and marked as use_once. We use delayed work,
+ * because there is a change that we are in interrupt and can't
+ * call to ib_dereg_mr() directly.
+ */
+ INIT_DELAYED_WORK(&ibmr->work, rds_ib_odp_mr_worker);
+ queue_delayed_work(rds_ib_mr_wq, &ibmr->work, 0);
+ return;
+ }
+
/* Return it to the pool's free list */
if (rds_ibdev->use_fastreg)
rds_ib_free_frmr_list(ibmr);
@@ -526,9 +546,17 @@ void rds_ib_flush_mrs(void)
up_read(&rds_ib_devices_lock);
}
+u32 rds_ib_get_lkey(void *trans_private)
+{
+ struct rds_ib_mr *ibmr = trans_private;
+
+ return ibmr->u.mr->lkey;
+}
+
void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
struct rds_sock *rs, u32 *key_ret,
- struct rds_connection *conn)
+ struct rds_connection *conn,
+ u64 start, u64 length, int need_odp)
{
struct rds_ib_device *rds_ibdev;
struct rds_ib_mr *ibmr = NULL;
@@ -541,6 +569,51 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
goto out;
}
+ if (need_odp == ODP_ZEROBASED || need_odp == ODP_VIRTUAL) {
+ u64 virt_addr = need_odp == ODP_ZEROBASED ? 0 : start;
+ int access_flags =
+ (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ |
+ IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC |
+ IB_ACCESS_ON_DEMAND);
+ struct ib_sge sge = {};
+ struct ib_mr *ib_mr;
+
+ if (!rds_ibdev->odp_capable) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
+ ib_mr = ib_reg_user_mr(rds_ibdev->pd, start, length, virt_addr,
+ access_flags);
+
+ if (IS_ERR(ib_mr)) {
+ rdsdebug("rds_ib_get_user_mr returned %d\n",
+ IS_ERR(ib_mr));
+ ret = PTR_ERR(ib_mr);
+ goto out;
+ }
+ if (key_ret)
+ *key_ret = ib_mr->rkey;
+
+ ibmr = kzalloc(sizeof(*ibmr), GFP_KERNEL);
+ if (!ibmr) {
+ ib_dereg_mr(ib_mr);
+ ret = -ENOMEM;
+ goto out;
+ }
+ ibmr->u.mr = ib_mr;
+ ibmr->odp = 1;
+
+ sge.addr = virt_addr;
+ sge.length = length;
+ sge.lkey = ib_mr->lkey;
+
+ ib_advise_mr(rds_ibdev->pd,
+ IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE,
+ IB_UVERBS_ADVISE_MR_FLAG_FLUSH, &sge, 1);
+ return ibmr;
+ }
+
if (conn)
ic = conn->c_transport_data;
@@ -629,3 +702,12 @@ void rds_ib_mr_exit(void)
{
destroy_workqueue(rds_ib_mr_wq);
}
+
+static void rds_ib_odp_mr_worker(struct work_struct *work)
+{
+ struct rds_ib_mr *ibmr;
+
+ ibmr = container_of(work, struct rds_ib_mr, work.work);
+ ib_dereg_mr(ibmr->u.mr);
+ kfree(ibmr);
+}
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index d1cc1d7..dfe7782 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -39,6 +39,7 @@
#include "rds_single_path.h"
#include "rds.h"
#include "ib.h"
+#include "ib_mr.h"
/*
* Convert IB-specific error message to RDS error message and call core
@@ -635,6 +636,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
send->s_sge[0].addr = ic->i_send_hdrs_dma[pos];
send->s_sge[0].length = sizeof(struct rds_header);
+ send->s_sge[0].lkey = ic->i_pd->local_dma_lkey;
memcpy(ic->i_send_hdrs[pos], &rm->m_inc.i_hdr,
sizeof(struct rds_header));
@@ -650,6 +652,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
send->s_sge[1].addr = sg_dma_address(scat);
send->s_sge[1].addr += rm->data.op_dmaoff;
send->s_sge[1].length = len;
+ send->s_sge[1].lkey = ic->i_pd->local_dma_lkey;
bytes_sent += len;
rm->data.op_dmaoff += len;
@@ -858,20 +861,29 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
int ret;
int num_sge;
int nr_sig = 0;
+ u64 odp_addr = op->op_odp_addr;
+ u32 odp_lkey = 0;
/* map the op the first time we see it */
- if (!op->op_mapped) {
- op->op_count = ib_dma_map_sg(ic->i_cm_id->device,
- op->op_sg, op->op_nents, (op->op_write) ?
- DMA_TO_DEVICE : DMA_FROM_DEVICE);
- rdsdebug("ic %p mapping op %p: %d\n", ic, op, op->op_count);
- if (op->op_count == 0) {
- rds_ib_stats_inc(s_ib_tx_sg_mapping_failure);
- ret = -ENOMEM; /* XXX ? */
- goto out;
+ if (!op->op_odp_mr) {
+ if (!op->op_mapped) {
+ op->op_count =
+ ib_dma_map_sg(ic->i_cm_id->device, op->op_sg,
+ op->op_nents,
+ (op->op_write) ? DMA_TO_DEVICE :
+ DMA_FROM_DEVICE);
+ rdsdebug("ic %p mapping op %p: %d\n", ic, op,
+ op->op_count);
+ if (op->op_count == 0) {
+ rds_ib_stats_inc(s_ib_tx_sg_mapping_failure);
+ ret = -ENOMEM; /* XXX ? */
+ goto out;
+ }
+ op->op_mapped = 1;
}
-
- op->op_mapped = 1;
+ } else {
+ op->op_count = op->op_nents;
+ odp_lkey = rds_ib_get_lkey(op->op_odp_mr->r_trans_private);
}
/*
@@ -923,14 +935,20 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
for (j = 0; j < send->s_rdma_wr.wr.num_sge &&
scat != &op->op_sg[op->op_count]; j++) {
len = sg_dma_len(scat);
- send->s_sge[j].addr = sg_dma_address(scat);
+ if (!op->op_odp_mr) {
+ send->s_sge[j].addr = sg_dma_address(scat);
+ send->s_sge[j].lkey = ic->i_pd->local_dma_lkey;
+ } else {
+ send->s_sge[j].addr = odp_addr;
+ send->s_sge[j].lkey = odp_lkey;
+ }
send->s_sge[j].length = len;
- send->s_sge[j].lkey = ic->i_pd->local_dma_lkey;
sent += len;
rdsdebug("ic %p sent %d remote_addr %llu\n", ic, sent, remote_addr);
remote_addr += len;
+ odp_addr += len;
scat++;
}
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 916f5ec..3341eee 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -156,11 +156,13 @@ void rds_rdma_drop_keys(struct rds_sock *rs)
static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages,
struct page **pages, int write)
{
+ unsigned int gup_flags = FOLL_LONGTERM;
int ret;
- ret = get_user_pages_fast(user_addr, nr_pages, write ? FOLL_WRITE : 0,
- pages);
+ if (write)
+ gup_flags |= FOLL_WRITE;
+ ret = get_user_pages_fast(user_addr, nr_pages, gup_flags, pages);
if (ret >= 0 && ret < nr_pages) {
while (ret--)
put_page(pages[ret]);
@@ -175,13 +177,14 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
struct rds_conn_path *cp)
{
struct rds_mr *mr = NULL, *found;
+ struct scatterlist *sg = NULL;
unsigned int nr_pages;
struct page **pages = NULL;
- struct scatterlist *sg;
void *trans_private;
unsigned long flags;
rds_rdma_cookie_t cookie;
- unsigned int nents;
+ unsigned int nents = 0;
+ int need_odp = 0;
long i;
int ret;
@@ -195,6 +198,21 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
goto out;
}
+ /* If the combination of the addr and size requested for this memory
+ * region causes an integer overflow, return error.
+ */
+ if (((args->vec.addr + args->vec.bytes) < args->vec.addr) ||
+ PAGE_ALIGN(args->vec.addr + args->vec.bytes) <
+ (args->vec.addr + args->vec.bytes)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (!can_do_mlock()) {
+ ret = -EPERM;
+ goto out;
+ }
+
nr_pages = rds_pages_in_vec(&args->vec);
if (nr_pages == 0) {
ret = -EINVAL;
@@ -248,36 +266,44 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
* the zero page.
*/
ret = rds_pin_pages(args->vec.addr, nr_pages, pages, 1);
- if (ret < 0)
+ if (ret == -EOPNOTSUPP) {
+ need_odp = 1;
+ } else if (ret <= 0) {
goto out;
+ } else {
+ nents = ret;
+ sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL);
+ if (!sg) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ WARN_ON(!nents);
+ sg_init_table(sg, nents);
- nents = ret;
- sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL);
- if (!sg) {
- ret = -ENOMEM;
- goto out;
+ /* Stick all pages into the scatterlist */
+ for (i = 0 ; i < nents; i++)
+ sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0);
+
+ rdsdebug("RDS: trans_private nents is %u\n", nents);
}
- WARN_ON(!nents);
- sg_init_table(sg, nents);
-
- /* Stick all pages into the scatterlist */
- for (i = 0 ; i < nents; i++)
- sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0);
-
- rdsdebug("RDS: trans_private nents is %u\n", nents);
-
/* Obtain a transport specific MR. If this succeeds, the
* s/g list is now owned by the MR.
* Note that dma_map() implies that pending writes are
* flushed to RAM, so no dma_sync is needed here. */
- trans_private = rs->rs_transport->get_mr(sg, nents, rs,
- &mr->r_key,
- cp ? cp->cp_conn : NULL);
+ trans_private = rs->rs_transport->get_mr(
+ sg, nents, rs, &mr->r_key, cp ? cp->cp_conn : NULL,
+ args->vec.addr, args->vec.bytes,
+ need_odp ? ODP_ZEROBASED : ODP_NOT_NEEDED);
if (IS_ERR(trans_private)) {
- for (i = 0 ; i < nents; i++)
- put_page(sg_page(&sg[i]));
- kfree(sg);
+ /* In ODP case, we don't GUP pages, so don't need
+ * to release anything.
+ */
+ if (!need_odp) {
+ for (i = 0 ; i < nents; i++)
+ put_page(sg_page(&sg[i]));
+ kfree(sg);
+ }
ret = PTR_ERR(trans_private);
goto out;
}
@@ -291,7 +317,11 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
* map page aligned regions. So we keep the offset, and build
* a 64bit cookie containing <R_Key, offset> and pass that
* around. */
- cookie = rds_rdma_make_cookie(mr->r_key, args->vec.addr & ~PAGE_MASK);
+ if (need_odp)
+ cookie = rds_rdma_make_cookie(mr->r_key, 0);
+ else
+ cookie = rds_rdma_make_cookie(mr->r_key,
+ args->vec.addr & ~PAGE_MASK);
if (cookie_ret)
*cookie_ret = cookie;
@@ -456,22 +486,26 @@ void rds_rdma_free_op(struct rm_rdma_op *ro)
{
unsigned int i;
- for (i = 0; i < ro->op_nents; i++) {
- struct page *page = sg_page(&ro->op_sg[i]);
+ if (ro->op_odp_mr) {
+ rds_mr_put(ro->op_odp_mr);
+ } else {
+ for (i = 0; i < ro->op_nents; i++) {
+ struct page *page = sg_page(&ro->op_sg[i]);
- /* Mark page dirty if it was possibly modified, which
- * is the case for a RDMA_READ which copies from remote
- * to local memory */
- if (!ro->op_write) {
- WARN_ON(!page->mapping && irqs_disabled());
- set_page_dirty(page);
+ /* Mark page dirty if it was possibly modified, which
+ * is the case for a RDMA_READ which copies from remote
+ * to local memory
+ */
+ if (!ro->op_write)
+ set_page_dirty(page);
+ put_page(page);
}
- put_page(page);
}
kfree(ro->op_notifier);
ro->op_notifier = NULL;
ro->op_active = 0;
+ ro->op_odp_mr = NULL;
}
void rds_atomic_free_op(struct rm_atomic_op *ao)
@@ -581,6 +615,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
struct rds_iovec *iovs;
unsigned int i, j;
int ret = 0;
+ bool odp_supported = true;
if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args))
|| rm->rdma.op_active)
@@ -602,6 +637,9 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
ret = -EINVAL;
goto out_ret;
}
+ /* odp-mr is not supported for multiple requests within one message */
+ if (args->nr_local != 1)
+ odp_supported = false;
iovs = vec->iov;
@@ -623,6 +661,8 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
op->op_silent = !!(args->flags & RDS_RDMA_SILENT);
op->op_active = 1;
op->op_recverr = rs->rs_recverr;
+ op->op_odp_mr = NULL;
+
WARN_ON(!nr_pages);
op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret);
if (!op->op_sg)
@@ -672,10 +712,44 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
* If it's a READ operation, we need to pin the pages for writing.
*/
ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write);
- if (ret < 0)
+ if ((!odp_supported && ret <= 0) ||
+ (odp_supported && ret <= 0 && ret != -EOPNOTSUPP))
goto out_pages;
- else
- ret = 0;
+
+ if (ret == -EOPNOTSUPP) {
+ struct rds_mr *local_odp_mr;
+
+ if (!rs->rs_transport->get_mr) {
+ ret = -EOPNOTSUPP;
+ goto out_pages;
+ }
+ local_odp_mr =
+ kzalloc(sizeof(*local_odp_mr), GFP_KERNEL);
+ if (!local_odp_mr) {
+ ret = -ENOMEM;
+ goto out_pages;
+ }
+ RB_CLEAR_NODE(&local_odp_mr->r_rb_node);
+ refcount_set(&local_odp_mr->r_refcount, 1);
+ local_odp_mr->r_trans = rs->rs_transport;
+ local_odp_mr->r_sock = rs;
+ local_odp_mr->r_trans_private =
+ rs->rs_transport->get_mr(
+ NULL, 0, rs, &local_odp_mr->r_key, NULL,
+ iov->addr, iov->bytes, ODP_VIRTUAL);
+ if (IS_ERR(local_odp_mr->r_trans_private)) {
+ ret = IS_ERR(local_odp_mr->r_trans_private);
+ rdsdebug("get_mr ret %d %p\"", ret,
+ local_odp_mr->r_trans_private);
+ kfree(local_odp_mr);
+ ret = -EOPNOTSUPP;
+ goto out_pages;
+ }
+ rdsdebug("Need odp; local_odp_mr %p trans_private %p\n",
+ local_odp_mr, local_odp_mr->r_trans_private);
+ op->op_odp_mr = local_odp_mr;
+ op->op_odp_addr = iov->addr;
+ }
rdsdebug("RDS: nr_bytes %u nr %u iov->bytes %llu iov->addr %llx\n",
nr_bytes, nr, iov->bytes, iov->addr);
@@ -691,6 +765,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
min_t(unsigned int, iov->bytes, PAGE_SIZE - offset),
offset);
+ sg_dma_len(sg) = sg->length;
rdsdebug("RDS: sg->offset %x sg->len %x iov->addr %llx iov->bytes %llu\n",
sg->offset, sg->length, iov->addr, iov->bytes);
@@ -709,6 +784,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
goto out_pages;
}
op->op_bytes = nr_bytes;
+ ret = 0;
out_pages:
kfree(pages);
@@ -755,7 +831,8 @@ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm,
spin_unlock_irqrestore(&rs->rs_rdma_lock, flags);
if (mr) {
- mr->r_trans->sync_mr(mr->r_trans_private, DMA_TO_DEVICE);
+ mr->r_trans->sync_mr(mr->r_trans_private,
+ DMA_TO_DEVICE);
rm->rdma.op_rdma_mr = mr;
}
return err;
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 53e8691..e4a6035 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -40,7 +40,6 @@
#ifdef ATOMIC64_INIT
#define KERNEL_HAS_ATOMIC64
#endif
-
#ifdef RDS_DEBUG
#define rdsdebug(fmt, args...) pr_debug("%s(): " fmt, __func__ , ##args)
#else
@@ -478,6 +477,9 @@ struct rds_message {
struct rds_notifier *op_notifier;
struct rds_mr *op_rdma_mr;
+
+ u64 op_odp_addr;
+ struct rds_mr *op_odp_mr;
} rdma;
struct rm_data_op {
unsigned int op_active:1;
@@ -573,7 +575,8 @@ struct rds_transport {
void (*exit)(void);
void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg,
struct rds_sock *rs, u32 *key_ret,
- struct rds_connection *conn);
+ struct rds_connection *conn,
+ u64 start, u64 length, int need_odp);
void (*sync_mr)(void *trans_private, int direction);
void (*free_mr)(void *trans_private, int invalidate);
void (*flush_mrs)(void);
@@ -956,6 +959,12 @@ static inline bool rds_destroy_pending(struct rds_connection *conn)
(conn->c_trans->t_unloading && conn->c_trans->t_unloading(conn));
}
+enum {
+ ODP_NOT_NEEDED,
+ ODP_ZEROBASED,
+ ODP_VIRTUAL
+};
+
/* stats.c */
DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats);
#define rds_stats_inc_which(which, member) do { \
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 46b8ff2..1e8eeb0 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1475,7 +1475,7 @@ static int __init rose_proto_init(void)
int rc;
if (rose_ndevs > 0x7FFFFFFF/sizeof(struct net_device *)) {
- printk(KERN_ERR "ROSE: rose_proto_init - rose_ndevs parameter to large\n");
+ printk(KERN_ERR "ROSE: rose_proto_init - rose_ndevs parameter too large\n");
rc = -EINVAL;
goto out;
}
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index c533076..5277631 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -696,7 +696,6 @@ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause,
for (i = 0; i < node->count; i++) {
if (!rose_ftimer_running(node->neighbour[i])) {
res = node->neighbour[i];
- failed = 0;
goto out;
}
failed = 1;
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 86bd133..96d54e5 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -413,7 +413,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
enum rxrpc_call_state state;
- unsigned int j;
+ unsigned int j, nr_subpackets;
rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0;
rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack;
bool immediate_ack = false, jumbo_bad = false;
@@ -457,7 +457,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
call->ackr_prev_seq = seq0;
hard_ack = READ_ONCE(call->rx_hard_ack);
- if (sp->nr_subpackets > 1) {
+ nr_subpackets = sp->nr_subpackets;
+ if (nr_subpackets > 1) {
if (call->nr_jumbo_bad > 3) {
ack = RXRPC_ACK_NOSPACE;
ack_serial = serial;
@@ -465,11 +466,11 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
}
}
- for (j = 0; j < sp->nr_subpackets; j++) {
+ for (j = 0; j < nr_subpackets; j++) {
rxrpc_serial_t serial = sp->hdr.serial + j;
rxrpc_seq_t seq = seq0 + j;
unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK;
- bool terminal = (j == sp->nr_subpackets - 1);
+ bool terminal = (j == nr_subpackets - 1);
bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST);
u8 flags, annotation = j;
@@ -506,7 +507,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
}
if (call->rxtx_buffer[ix]) {
- rxrpc_input_dup_data(call, seq, sp->nr_subpackets > 1,
+ rxrpc_input_dup_data(call, seq, nr_subpackets > 1,
&jumbo_bad);
if (ack != RXRPC_ACK_DUPLICATE) {
ack = RXRPC_ACK_DUPLICATE;
@@ -564,6 +565,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
* ring.
*/
skb = NULL;
+ sp = NULL;
}
if (last) {
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index b1e7ec7..edde0e5 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -366,6 +366,19 @@
If unsure, say N.
+config NET_SCH_FQ_PIE
+ depends on NET_SCH_PIE
+ tristate "Flow Queue Proportional Integral controller Enhanced (FQ-PIE)"
+ help
+ Say Y here if you want to use the Flow Queue Proportional Integral
+ controller Enhanced (FQ-PIE) packet scheduling algorithm.
+ For more information, please see https://tools.ietf.org/html/rfc8033
+
+ To compile this driver as a module, choose M here: the module
+ will be called sch_fq_pie.
+
+ If unsure, say N.
+
config NET_SCH_INGRESS
tristate "Ingress/classifier-action Qdisc"
depends on NET_CLS_ACT
diff --git a/net/sched/Makefile b/net/sched/Makefile
index bc8856b..31c367a 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -59,6 +59,7 @@
obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o
obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o
obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o
+obj-$(CONFIG_NET_SCH_FQ_PIE) += sch_fq_pie.o
obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o
obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o
obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index 40038c3..1964962 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -360,6 +360,16 @@ static int tcf_ctinfo_search(struct net *net, struct tc_action **a, u32 index)
return tcf_idr_search(tn, a, index);
}
+static void tcf_ctinfo_cleanup(struct tc_action *a)
+{
+ struct tcf_ctinfo *ci = to_ctinfo(a);
+ struct tcf_ctinfo_params *cp;
+
+ cp = rcu_dereference_protected(ci->params, 1);
+ if (cp)
+ kfree_rcu(cp, rcu);
+}
+
static struct tc_action_ops act_ctinfo_ops = {
.kind = "ctinfo",
.id = TCA_ID_CTINFO,
@@ -367,6 +377,7 @@ static struct tc_action_ops act_ctinfo_ops = {
.act = tcf_ctinfo_act,
.dump = tcf_ctinfo_dump,
.init = tcf_ctinfo_init,
+ .cleanup= tcf_ctinfo_cleanup,
.walk = tcf_ctinfo_walker,
.lookup = tcf_ctinfo_search,
.size = sizeof(struct tcf_ctinfo),
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 5e63790..c1fcd85 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -537,6 +537,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
}
ife = to_ife(*a);
+ if (ret == ACT_P_CREATED)
+ INIT_LIST_HEAD(&ife->metalist);
+
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0)
goto release_idr;
@@ -566,10 +569,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
p->eth_type = ife_type;
}
-
- if (ret == ACT_P_CREATED)
- INIT_LIST_HEAD(&ife->metalist);
-
if (tb[TCA_IFE_METALST]) {
err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
tb[TCA_IFE_METALST], NULL,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 76e0d12..c2cdd0f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2055,9 +2055,8 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
&chain_info));
mutex_unlock(&chain->filter_chain_lock);
- tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]),
- protocol, prio, chain, rtnl_held,
- extack);
+ tp_new = tcf_proto_create(name, protocol, prio, chain,
+ rtnl_held, extack);
if (IS_ERR(tp_new)) {
err = PTR_ERR(tp_new);
goto errout_tp;
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 4aafbe3..f256a7c 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -263,12 +263,17 @@ static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg,
}
}
-static void basic_bind_class(void *fh, u32 classid, unsigned long cl)
+static void basic_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+ unsigned long base)
{
struct basic_filter *f = fh;
- if (f && f->res.classid == classid)
- f->res.class = cl;
+ if (f && f->res.classid == classid) {
+ if (cl)
+ __tcf_bind_filter(q, &f->res, base);
+ else
+ __tcf_unbind_filter(q, &f->res);
+ }
}
static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh,
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 8229ed4..6e3e63d 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -631,12 +631,17 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh,
return -1;
}
-static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl)
+static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl,
+ void *q, unsigned long base)
{
struct cls_bpf_prog *prog = fh;
- if (prog && prog->res.classid == classid)
- prog->res.class = cl;
+ if (prog && prog->res.classid == classid) {
+ if (cl)
+ __tcf_bind_filter(q, &prog->res, base);
+ else
+ __tcf_unbind_filter(q, &prog->res);
+ }
}
static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg,
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index b0f42e6..f9c0d1e 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -2765,12 +2765,17 @@ static int fl_tmplt_dump(struct sk_buff *skb, struct net *net, void *tmplt_priv)
return -EMSGSIZE;
}
-static void fl_bind_class(void *fh, u32 classid, unsigned long cl)
+static void fl_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+ unsigned long base)
{
struct cls_fl_filter *f = fh;
- if (f && f->res.classid == classid)
- f->res.class = cl;
+ if (f && f->res.classid == classid) {
+ if (cl)
+ __tcf_bind_filter(q, &f->res, base);
+ else
+ __tcf_unbind_filter(q, &f->res);
+ }
}
static bool fl_delete_empty(struct tcf_proto *tp)
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index c9496c9..ec94529 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -419,12 +419,17 @@ static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh,
return -1;
}
-static void fw_bind_class(void *fh, u32 classid, unsigned long cl)
+static void fw_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+ unsigned long base)
{
struct fw_filter *f = fh;
- if (f && f->res.classid == classid)
- f->res.class = cl;
+ if (f && f->res.classid == classid) {
+ if (cl)
+ __tcf_bind_filter(q, &f->res, base);
+ else
+ __tcf_unbind_filter(q, &f->res);
+ }
}
static struct tcf_proto_ops cls_fw_ops __read_mostly = {
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 7fc2eb6..039cc86 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -393,12 +393,17 @@ static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,
return -1;
}
-static void mall_bind_class(void *fh, u32 classid, unsigned long cl)
+static void mall_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+ unsigned long base)
{
struct cls_mall_head *head = fh;
- if (head && head->res.classid == classid)
- head->res.class = cl;
+ if (head && head->res.classid == classid) {
+ if (cl)
+ __tcf_bind_filter(q, &head->res, base);
+ else
+ __tcf_unbind_filter(q, &head->res);
+ }
}
static struct tcf_proto_ops cls_mall_ops __read_mostly = {
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 2d9e0b4..6f8786b 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -641,12 +641,17 @@ static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh,
return -1;
}
-static void route4_bind_class(void *fh, u32 classid, unsigned long cl)
+static void route4_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+ unsigned long base)
{
struct route4_filter *f = fh;
- if (f && f->res.classid == classid)
- f->res.class = cl;
+ if (f && f->res.classid == classid) {
+ if (cl)
+ __tcf_bind_filter(q, &f->res, base);
+ else
+ __tcf_unbind_filter(q, &f->res);
+ }
}
static struct tcf_proto_ops cls_route4_ops __read_mostly = {
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 2f3c03b..c226241 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -738,12 +738,17 @@ static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh,
return -1;
}
-static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl)
+static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+ unsigned long base)
{
struct rsvp_filter *f = fh;
- if (f && f->res.classid == classid)
- f->res.class = cl;
+ if (f && f->res.classid == classid) {
+ if (cl)
+ __tcf_bind_filter(q, &f->res, base);
+ else
+ __tcf_unbind_filter(q, &f->res);
+ }
}
static struct tcf_proto_ops RSVP_OPS __read_mostly = {
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index e573e5a..3d4a128 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -654,12 +654,17 @@ static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh,
return -1;
}
-static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl)
+static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl,
+ void *q, unsigned long base)
{
struct tcindex_filter_result *r = fh;
- if (r && r->res.classid == classid)
- r->res.class = cl;
+ if (r && r->res.classid == classid) {
+ if (cl)
+ __tcf_bind_filter(q, &r->res, base);
+ else
+ __tcf_unbind_filter(q, &r->res);
+ }
}
static struct tcf_proto_ops cls_tcindex_ops __read_mostly = {
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index a0e6fac..e15ff33 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -1255,12 +1255,17 @@ static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
return 0;
}
-static void u32_bind_class(void *fh, u32 classid, unsigned long cl)
+static void u32_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+ unsigned long base)
{
struct tc_u_knode *n = fh;
- if (n && n->res.classid == classid)
- n->res.class = cl;
+ if (n && n->res.classid == classid) {
+ if (cl)
+ __tcf_bind_filter(q, &n->res, base);
+ else
+ __tcf_unbind_filter(q, &n->res);
+ }
}
static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh,
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 8f2ad70..dd3b8c1 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -238,6 +238,9 @@ static int tcf_em_validate(struct tcf_proto *tp,
goto errout;
if (em->ops->change) {
+ err = -EINVAL;
+ if (em_hdr->flags & TCF_EM_SIMPLE)
+ goto errout;
err = em->ops->change(net, data, data_len, em);
if (err < 0)
goto errout;
@@ -263,12 +266,12 @@ static int tcf_em_validate(struct tcf_proto *tp,
}
em->data = (unsigned long) v;
}
+ em->datalen = data_len;
}
}
em->matchid = em_hdr->matchid;
em->flags = em_hdr->flags;
- em->datalen = data_len;
em->net = net;
err = 0;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 1047825..5079412 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1891,8 +1891,9 @@ static int tclass_del_notify(struct net *net,
struct tcf_bind_args {
struct tcf_walker w;
- u32 classid;
+ unsigned long base;
unsigned long cl;
+ u32 classid;
};
static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
@@ -1903,28 +1904,30 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
struct Qdisc *q = tcf_block_q(tp->chain->block);
sch_tree_lock(q);
- tp->ops->bind_class(n, a->classid, a->cl);
+ tp->ops->bind_class(n, a->classid, a->cl, q, a->base);
sch_tree_unlock(q);
}
return 0;
}
-static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
- unsigned long new_cl)
+struct tc_bind_class_args {
+ struct qdisc_walker w;
+ unsigned long new_cl;
+ u32 portid;
+ u32 clid;
+};
+
+static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl,
+ struct qdisc_walker *w)
{
+ struct tc_bind_class_args *a = (struct tc_bind_class_args *)w;
const struct Qdisc_class_ops *cops = q->ops->cl_ops;
struct tcf_block *block;
struct tcf_chain *chain;
- unsigned long cl;
- cl = cops->find(q, portid);
- if (!cl)
- return;
- if (!cops->tcf_block)
- return;
block = cops->tcf_block(q, cl, NULL);
if (!block)
- return;
+ return 0;
for (chain = tcf_get_next_chain(block, NULL);
chain;
chain = tcf_get_next_chain(block, chain)) {
@@ -1935,11 +1938,29 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
struct tcf_bind_args arg = {};
arg.w.fn = tcf_node_bind;
- arg.classid = clid;
- arg.cl = new_cl;
+ arg.classid = a->clid;
+ arg.base = cl;
+ arg.cl = a->new_cl;
tp->ops->walk(tp, &arg.w, true);
}
}
+
+ return 0;
+}
+
+static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
+ unsigned long new_cl)
+{
+ const struct Qdisc_class_ops *cops = q->ops->cl_ops;
+ struct tc_bind_class_args args = {};
+
+ if (!cops->tcf_block)
+ return;
+ args.portid = portid;
+ args.clid = clid;
+ args.new_cl = new_cl;
+ args.w.fn = tc_bind_class_walker;
+ q->ops->cl_ops->walk(q, &args.w);
}
#else
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 6cc3ab1..1496e87 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1682,8 +1682,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
if (IS_ERR_OR_NULL(segs))
return qdisc_drop(skb, sch, to_free);
- while (segs) {
- nskb = segs->next;
+ skb_list_walk_safe(segs, segs, nskb) {
skb_mark_not_on_list(segs);
qdisc_skb_cb(segs)->pkt_len = segs->len;
cobalt_set_enqueue_time(segs, now);
@@ -1696,7 +1695,6 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
slen += segs->len;
q->buffer_used += segs->truesize;
b->packets++;
- segs = nskb;
}
/* stats */
@@ -1768,7 +1766,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
q->avg_window_begin));
u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC;
- do_div(b, window_interval);
+ b = div64_u64(b, window_interval);
q->avg_peak_bandwidth =
cake_ewma(q->avg_peak_bandwidth, b,
b > q->avg_peak_bandwidth ? 2 : 8);
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index ff4c5e9..a5a2954 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -786,10 +786,12 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
if (tb[TCA_FQ_QUANTUM]) {
u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
- if (quantum > 0)
+ if (quantum > 0 && quantum <= (1 << 20)) {
q->quantum = quantum;
- else
+ } else {
+ NL_SET_ERR_MSG_MOD(extack, "invalid quantum");
err = -EINVAL;
+ }
}
if (tb[TCA_FQ_INITIAL_QUANTUM])
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
new file mode 100644
index 0000000..bbd0dea
--- /dev/null
+++ b/net/sched/sch_fq_pie.c
@@ -0,0 +1,562 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Flow Queue PIE discipline
+ *
+ * Copyright (C) 2019 Mohit P. Tahiliani <tahiliani@nitk.edu.in>
+ * Copyright (C) 2019 Sachin D. Patil <sdp.sachin@gmail.com>
+ * Copyright (C) 2019 V. Saicharan <vsaicharan1998@gmail.com>
+ * Copyright (C) 2019 Mohit Bhasi <mohitbhasi1998@gmail.com>
+ * Copyright (C) 2019 Leslie Monis <lesliemonis@gmail.com>
+ * Copyright (C) 2019 Gautam Ramakrishnan <gautamramk@gmail.com>
+ */
+
+#include <linux/jhash.h>
+#include <linux/sizes.h>
+#include <linux/vmalloc.h>
+#include <net/pkt_cls.h>
+#include <net/pie.h>
+
+/* Flow Queue PIE
+ *
+ * Principles:
+ * - Packets are classified on flows.
+ * - This is a Stochastic model (as we use a hash, several flows might
+ * be hashed to the same slot)
+ * - Each flow has a PIE managed queue.
+ * - Flows are linked onto two (Round Robin) lists,
+ * so that new flows have priority on old ones.
+ * - For a given flow, packets are not reordered.
+ * - Drops during enqueue only.
+ * - ECN capability is off by default.
+ * - ECN threshold (if ECN is enabled) is at 10% by default.
+ * - Uses timestamps to calculate queue delay by default.
+ */
+
+/**
+ * struct fq_pie_flow - contains data for each flow
+ * @vars: pie vars associated with the flow
+ * @deficit: number of remaining byte credits
+ * @backlog: size of data in the flow
+ * @qlen: number of packets in the flow
+ * @flowchain: flowchain for the flow
+ * @head: first packet in the flow
+ * @tail: last packet in the flow
+ */
+struct fq_pie_flow {
+ struct pie_vars vars;
+ s32 deficit;
+ u32 backlog;
+ u32 qlen;
+ struct list_head flowchain;
+ struct sk_buff *head;
+ struct sk_buff *tail;
+};
+
+struct fq_pie_sched_data {
+ struct tcf_proto __rcu *filter_list; /* optional external classifier */
+ struct tcf_block *block;
+ struct fq_pie_flow *flows;
+ struct Qdisc *sch;
+ struct list_head old_flows;
+ struct list_head new_flows;
+ struct pie_params p_params;
+ u32 ecn_prob;
+ u32 flows_cnt;
+ u32 quantum;
+ u32 memory_limit;
+ u32 new_flow_count;
+ u32 memory_usage;
+ u32 overmemory;
+ struct pie_stats stats;
+ struct timer_list adapt_timer;
+};
+
+static unsigned int fq_pie_hash(const struct fq_pie_sched_data *q,
+ struct sk_buff *skb)
+{
+ return reciprocal_scale(skb_get_hash(skb), q->flows_cnt);
+}
+
+static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch,
+ int *qerr)
+{
+ struct fq_pie_sched_data *q = qdisc_priv(sch);
+ struct tcf_proto *filter;
+ struct tcf_result res;
+ int result;
+
+ if (TC_H_MAJ(skb->priority) == sch->handle &&
+ TC_H_MIN(skb->priority) > 0 &&
+ TC_H_MIN(skb->priority) <= q->flows_cnt)
+ return TC_H_MIN(skb->priority);
+
+ filter = rcu_dereference_bh(q->filter_list);
+ if (!filter)
+ return fq_pie_hash(q, skb) + 1;
+
+ *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+ result = tcf_classify(skb, filter, &res, false);
+ if (result >= 0) {
+#ifdef CONFIG_NET_CLS_ACT
+ switch (result) {
+ case TC_ACT_STOLEN:
+ case TC_ACT_QUEUED:
+ case TC_ACT_TRAP:
+ *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+ /* fall through */
+ case TC_ACT_SHOT:
+ return 0;
+ }
+#endif
+ if (TC_H_MIN(res.classid) <= q->flows_cnt)
+ return TC_H_MIN(res.classid);
+ }
+ return 0;
+}
+
+/* add skb to flow queue (tail add) */
+static inline void flow_queue_add(struct fq_pie_flow *flow,
+ struct sk_buff *skb)
+{
+ if (!flow->head)
+ flow->head = skb;
+ else
+ flow->tail->next = skb;
+ flow->tail = skb;
+ skb->next = NULL;
+}
+
+static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+ struct sk_buff **to_free)
+{
+ struct fq_pie_sched_data *q = qdisc_priv(sch);
+ struct fq_pie_flow *sel_flow;
+ int uninitialized_var(ret);
+ u8 memory_limited = false;
+ u8 enqueue = false;
+ u32 pkt_len;
+ u32 idx;
+
+ /* Classifies packet into corresponding flow */
+ idx = fq_pie_classify(skb, sch, &ret);
+ sel_flow = &q->flows[idx];
+
+ /* Checks whether adding a new packet would exceed memory limit */
+ get_pie_cb(skb)->mem_usage = skb->truesize;
+ memory_limited = q->memory_usage > q->memory_limit + skb->truesize;
+
+ /* Checks if the qdisc is full */
+ if (unlikely(qdisc_qlen(sch) >= sch->limit)) {
+ q->stats.overlimit++;
+ goto out;
+ } else if (unlikely(memory_limited)) {
+ q->overmemory++;
+ }
+
+ if (!pie_drop_early(sch, &q->p_params, &sel_flow->vars,
+ sel_flow->backlog, skb->len)) {
+ enqueue = true;
+ } else if (q->p_params.ecn &&
+ sel_flow->vars.prob <= (MAX_PROB / 100) * q->ecn_prob &&
+ INET_ECN_set_ce(skb)) {
+ /* If packet is ecn capable, mark it if drop probability
+ * is lower than the parameter ecn_prob, else drop it.
+ */
+ q->stats.ecn_mark++;
+ enqueue = true;
+ }
+ if (enqueue) {
+ /* Set enqueue time only when dq_rate_estimator is disabled. */
+ if (!q->p_params.dq_rate_estimator)
+ pie_set_enqueue_time(skb);
+
+ pkt_len = qdisc_pkt_len(skb);
+ q->stats.packets_in++;
+ q->memory_usage += skb->truesize;
+ sch->qstats.backlog += pkt_len;
+ sch->q.qlen++;
+ flow_queue_add(sel_flow, skb);
+ if (list_empty(&sel_flow->flowchain)) {
+ list_add_tail(&sel_flow->flowchain, &q->new_flows);
+ q->new_flow_count++;
+ sel_flow->deficit = q->quantum;
+ sel_flow->qlen = 0;
+ sel_flow->backlog = 0;
+ }
+ sel_flow->qlen++;
+ sel_flow->backlog += pkt_len;
+ return NET_XMIT_SUCCESS;
+ }
+out:
+ q->stats.dropped++;
+ sel_flow->vars.accu_prob = 0;
+ sel_flow->vars.accu_prob_overflows = 0;
+ __qdisc_drop(skb, to_free);
+ qdisc_qstats_drop(sch);
+ return NET_XMIT_CN;
+}
+
+static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = {
+ [TCA_FQ_PIE_LIMIT] = {.type = NLA_U32},
+ [TCA_FQ_PIE_FLOWS] = {.type = NLA_U32},
+ [TCA_FQ_PIE_TARGET] = {.type = NLA_U32},
+ [TCA_FQ_PIE_TUPDATE] = {.type = NLA_U32},
+ [TCA_FQ_PIE_ALPHA] = {.type = NLA_U32},
+ [TCA_FQ_PIE_BETA] = {.type = NLA_U32},
+ [TCA_FQ_PIE_QUANTUM] = {.type = NLA_U32},
+ [TCA_FQ_PIE_MEMORY_LIMIT] = {.type = NLA_U32},
+ [TCA_FQ_PIE_ECN_PROB] = {.type = NLA_U32},
+ [TCA_FQ_PIE_ECN] = {.type = NLA_U32},
+ [TCA_FQ_PIE_BYTEMODE] = {.type = NLA_U32},
+ [TCA_FQ_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32},
+};
+
+static inline struct sk_buff *dequeue_head(struct fq_pie_flow *flow)
+{
+ struct sk_buff *skb = flow->head;
+
+ flow->head = skb->next;
+ skb->next = NULL;
+ return skb;
+}
+
+static struct sk_buff *fq_pie_qdisc_dequeue(struct Qdisc *sch)
+{
+ struct fq_pie_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *skb = NULL;
+ struct fq_pie_flow *flow;
+ struct list_head *head;
+ u32 pkt_len;
+
+begin:
+ head = &q->new_flows;
+ if (list_empty(head)) {
+ head = &q->old_flows;
+ if (list_empty(head))
+ return NULL;
+ }
+
+ flow = list_first_entry(head, struct fq_pie_flow, flowchain);
+ /* Flow has exhausted all its credits */
+ if (flow->deficit <= 0) {
+ flow->deficit += q->quantum;
+ list_move_tail(&flow->flowchain, &q->old_flows);
+ goto begin;
+ }
+
+ if (flow->head) {
+ skb = dequeue_head(flow);
+ pkt_len = qdisc_pkt_len(skb);
+ sch->qstats.backlog -= pkt_len;
+ sch->q.qlen--;
+ qdisc_bstats_update(sch, skb);
+ }
+
+ if (!skb) {
+ /* force a pass through old_flows to prevent starvation */
+ if (head == &q->new_flows && !list_empty(&q->old_flows))
+ list_move_tail(&flow->flowchain, &q->old_flows);
+ else
+ list_del_init(&flow->flowchain);
+ goto begin;
+ }
+
+ flow->qlen--;
+ flow->deficit -= pkt_len;
+ flow->backlog -= pkt_len;
+ q->memory_usage -= get_pie_cb(skb)->mem_usage;
+ pie_process_dequeue(skb, &q->p_params, &flow->vars, flow->backlog);
+ return skb;
+}
+
+static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ struct fq_pie_sched_data *q = qdisc_priv(sch);
+ struct nlattr *tb[TCA_FQ_PIE_MAX + 1];
+ unsigned int len_dropped = 0;
+ unsigned int num_dropped = 0;
+ int err;
+
+ if (!opt)
+ return -EINVAL;
+
+ err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack);
+ if (err < 0)
+ return err;
+
+ sch_tree_lock(sch);
+ if (tb[TCA_FQ_PIE_LIMIT]) {
+ u32 limit = nla_get_u32(tb[TCA_FQ_PIE_LIMIT]);
+
+ q->p_params.limit = limit;
+ sch->limit = limit;
+ }
+ if (tb[TCA_FQ_PIE_FLOWS]) {
+ if (q->flows) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Number of flows cannot be changed");
+ goto flow_error;
+ }
+ q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]);
+ if (!q->flows_cnt || q->flows_cnt > 65536) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Number of flows must be < 65536");
+ goto flow_error;
+ }
+ }
+
+ /* convert from microseconds to pschedtime */
+ if (tb[TCA_FQ_PIE_TARGET]) {
+ /* target is in us */
+ u32 target = nla_get_u32(tb[TCA_FQ_PIE_TARGET]);
+
+ /* convert to pschedtime */
+ q->p_params.target =
+ PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC);
+ }
+
+ /* tupdate is in jiffies */
+ if (tb[TCA_FQ_PIE_TUPDATE])
+ q->p_params.tupdate =
+ usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE]));
+
+ if (tb[TCA_FQ_PIE_ALPHA])
+ q->p_params.alpha = nla_get_u32(tb[TCA_FQ_PIE_ALPHA]);
+
+ if (tb[TCA_FQ_PIE_BETA])
+ q->p_params.beta = nla_get_u32(tb[TCA_FQ_PIE_BETA]);
+
+ if (tb[TCA_FQ_PIE_QUANTUM])
+ q->quantum = nla_get_u32(tb[TCA_FQ_PIE_QUANTUM]);
+
+ if (tb[TCA_FQ_PIE_MEMORY_LIMIT])
+ q->memory_limit = nla_get_u32(tb[TCA_FQ_PIE_MEMORY_LIMIT]);
+
+ if (tb[TCA_FQ_PIE_ECN_PROB])
+ q->ecn_prob = nla_get_u32(tb[TCA_FQ_PIE_ECN_PROB]);
+
+ if (tb[TCA_FQ_PIE_ECN])
+ q->p_params.ecn = nla_get_u32(tb[TCA_FQ_PIE_ECN]);
+
+ if (tb[TCA_FQ_PIE_BYTEMODE])
+ q->p_params.bytemode = nla_get_u32(tb[TCA_FQ_PIE_BYTEMODE]);
+
+ if (tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR])
+ q->p_params.dq_rate_estimator =
+ nla_get_u32(tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]);
+
+ /* Drop excess packets if new limit is lower */
+ while (sch->q.qlen > sch->limit) {
+ struct sk_buff *skb = fq_pie_qdisc_dequeue(sch);
+
+ kfree_skb(skb);
+ len_dropped += qdisc_pkt_len(skb);
+ num_dropped += 1;
+ }
+ qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped);
+
+ sch_tree_unlock(sch);
+ return 0;
+
+flow_error:
+ sch_tree_unlock(sch);
+ return -EINVAL;
+}
+
+static void fq_pie_timer(struct timer_list *t)
+{
+ struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer);
+ struct Qdisc *sch = q->sch;
+ spinlock_t *root_lock; /* to lock qdisc for probability calculations */
+ u16 idx;
+
+ root_lock = qdisc_lock(qdisc_root_sleeping(sch));
+ spin_lock(root_lock);
+
+ for (idx = 0; idx < q->flows_cnt; idx++)
+ pie_calculate_probability(&q->p_params, &q->flows[idx].vars,
+ q->flows[idx].backlog);
+
+ /* reset the timer to fire after 'tupdate' jiffies. */
+ if (q->p_params.tupdate)
+ mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate);
+
+ spin_unlock(root_lock);
+}
+
+static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ struct fq_pie_sched_data *q = qdisc_priv(sch);
+ int err;
+ u16 idx;
+
+ pie_params_init(&q->p_params);
+ sch->limit = 10 * 1024;
+ q->p_params.limit = sch->limit;
+ q->quantum = psched_mtu(qdisc_dev(sch));
+ q->sch = sch;
+ q->ecn_prob = 10;
+ q->flows_cnt = 1024;
+ q->memory_limit = SZ_32M;
+
+ INIT_LIST_HEAD(&q->new_flows);
+ INIT_LIST_HEAD(&q->old_flows);
+
+ if (opt) {
+ err = fq_pie_change(sch, opt, extack);
+
+ if (err)
+ return err;
+ }
+
+ err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
+ if (err)
+ goto init_failure;
+
+ q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_pie_flow),
+ GFP_KERNEL);
+ if (!q->flows) {
+ err = -ENOMEM;
+ goto init_failure;
+ }
+ for (idx = 0; idx < q->flows_cnt; idx++) {
+ struct fq_pie_flow *flow = q->flows + idx;
+
+ INIT_LIST_HEAD(&flow->flowchain);
+ pie_vars_init(&flow->vars);
+ }
+
+ timer_setup(&q->adapt_timer, fq_pie_timer, 0);
+ mod_timer(&q->adapt_timer, jiffies + HZ / 2);
+
+ return 0;
+
+init_failure:
+ q->flows_cnt = 0;
+
+ return err;
+}
+
+static int fq_pie_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+ struct fq_pie_sched_data *q = qdisc_priv(sch);
+ struct nlattr *opts;
+
+ opts = nla_nest_start(skb, TCA_OPTIONS);
+ if (!opts)
+ return -EMSGSIZE;
+
+ /* convert target from pschedtime to us */
+ if (nla_put_u32(skb, TCA_FQ_PIE_LIMIT, sch->limit) ||
+ nla_put_u32(skb, TCA_FQ_PIE_FLOWS, q->flows_cnt) ||
+ nla_put_u32(skb, TCA_FQ_PIE_TARGET,
+ ((u32)PSCHED_TICKS2NS(q->p_params.target)) /
+ NSEC_PER_USEC) ||
+ nla_put_u32(skb, TCA_FQ_PIE_TUPDATE,
+ jiffies_to_usecs(q->p_params.tupdate)) ||
+ nla_put_u32(skb, TCA_FQ_PIE_ALPHA, q->p_params.alpha) ||
+ nla_put_u32(skb, TCA_FQ_PIE_BETA, q->p_params.beta) ||
+ nla_put_u32(skb, TCA_FQ_PIE_QUANTUM, q->quantum) ||
+ nla_put_u32(skb, TCA_FQ_PIE_MEMORY_LIMIT, q->memory_limit) ||
+ nla_put_u32(skb, TCA_FQ_PIE_ECN_PROB, q->ecn_prob) ||
+ nla_put_u32(skb, TCA_FQ_PIE_ECN, q->p_params.ecn) ||
+ nla_put_u32(skb, TCA_FQ_PIE_BYTEMODE, q->p_params.bytemode) ||
+ nla_put_u32(skb, TCA_FQ_PIE_DQ_RATE_ESTIMATOR,
+ q->p_params.dq_rate_estimator))
+ goto nla_put_failure;
+
+ return nla_nest_end(skb, opts);
+
+nla_put_failure:
+ nla_nest_cancel(skb, opts);
+ return -EMSGSIZE;
+}
+
+static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+ struct fq_pie_sched_data *q = qdisc_priv(sch);
+ struct tc_fq_pie_xstats st = {
+ .packets_in = q->stats.packets_in,
+ .overlimit = q->stats.overlimit,
+ .overmemory = q->overmemory,
+ .dropped = q->stats.dropped,
+ .ecn_mark = q->stats.ecn_mark,
+ .new_flow_count = q->new_flow_count,
+ .memory_usage = q->memory_usage,
+ };
+ struct list_head *pos;
+
+ sch_tree_lock(sch);
+ list_for_each(pos, &q->new_flows)
+ st.new_flows_len++;
+
+ list_for_each(pos, &q->old_flows)
+ st.old_flows_len++;
+ sch_tree_unlock(sch);
+
+ return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+static void fq_pie_reset(struct Qdisc *sch)
+{
+ struct fq_pie_sched_data *q = qdisc_priv(sch);
+ u16 idx;
+
+ INIT_LIST_HEAD(&q->new_flows);
+ INIT_LIST_HEAD(&q->old_flows);
+ for (idx = 0; idx < q->flows_cnt; idx++) {
+ struct fq_pie_flow *flow = q->flows + idx;
+
+ /* Removes all packets from flow */
+ rtnl_kfree_skbs(flow->head, flow->tail);
+ flow->head = NULL;
+
+ INIT_LIST_HEAD(&flow->flowchain);
+ pie_vars_init(&flow->vars);
+ }
+
+ sch->q.qlen = 0;
+ sch->qstats.backlog = 0;
+}
+
+static void fq_pie_destroy(struct Qdisc *sch)
+{
+ struct fq_pie_sched_data *q = qdisc_priv(sch);
+
+ tcf_block_put(q->block);
+ del_timer_sync(&q->adapt_timer);
+ kvfree(q->flows);
+}
+
+static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = {
+ .id = "fq_pie",
+ .priv_size = sizeof(struct fq_pie_sched_data),
+ .enqueue = fq_pie_qdisc_enqueue,
+ .dequeue = fq_pie_qdisc_dequeue,
+ .peek = qdisc_peek_dequeued,
+ .init = fq_pie_init,
+ .destroy = fq_pie_destroy,
+ .reset = fq_pie_reset,
+ .change = fq_pie_change,
+ .dump = fq_pie_dump,
+ .dump_stats = fq_pie_dump_stats,
+ .owner = THIS_MODULE,
+};
+
+static int __init fq_pie_module_init(void)
+{
+ return register_qdisc(&fq_pie_qdisc_ops);
+}
+
+static void __exit fq_pie_module_exit(void)
+{
+ unregister_qdisc(&fq_pie_qdisc_ops);
+}
+
+module_init(fq_pie_module_init);
+module_exit(fq_pie_module_exit);
+
+MODULE_DESCRIPTION("Flow Queue Proportional Integral controller Enhanced (FQ-PIE)");
+MODULE_AUTHOR("Mohit P. Tahiliani");
+MODULE_LICENSE("GPL");
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index b0b0dc4..915bcdb 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -19,159 +19,76 @@
#include <linux/skbuff.h>
#include <net/pkt_sched.h>
#include <net/inet_ecn.h>
-
-#define QUEUE_THRESHOLD 16384
-#define DQCOUNT_INVALID -1
-#define DTIME_INVALID 0xffffffffffffffff
-#define MAX_PROB 0xffffffffffffffff
-#define PIE_SCALE 8
-
-/* parameters used */
-struct pie_params {
- psched_time_t target; /* user specified target delay in pschedtime */
- u32 tupdate; /* timer frequency (in jiffies) */
- u32 limit; /* number of packets that can be enqueued */
- u32 alpha; /* alpha and beta are between 0 and 32 */
- u32 beta; /* and are used for shift relative to 1 */
- bool ecn; /* true if ecn is enabled */
- bool bytemode; /* to scale drop early prob based on pkt size */
- u8 dq_rate_estimator; /* to calculate delay using Little's law */
-};
-
-/* variables used */
-struct pie_vars {
- u64 prob; /* probability but scaled by u64 limit. */
- psched_time_t burst_time;
- psched_time_t qdelay;
- psched_time_t qdelay_old;
- u64 dq_count; /* measured in bytes */
- psched_time_t dq_tstamp; /* drain rate */
- u64 accu_prob; /* accumulated drop probability */
- u32 avg_dq_rate; /* bytes per pschedtime tick,scaled */
- u32 qlen_old; /* in bytes */
- u8 accu_prob_overflows; /* overflows of accu_prob */
-};
-
-/* statistics gathering */
-struct pie_stats {
- u32 packets_in; /* total number of packets enqueued */
- u32 dropped; /* packets dropped due to pie_action */
- u32 overlimit; /* dropped due to lack of space in queue */
- u32 maxq; /* maximum queue size */
- u32 ecn_mark; /* packets marked with ECN */
-};
+#include <net/pie.h>
/* private data for the Qdisc */
struct pie_sched_data {
- struct pie_params params;
struct pie_vars vars;
+ struct pie_params params;
struct pie_stats stats;
struct timer_list adapt_timer;
struct Qdisc *sch;
};
-static void pie_params_init(struct pie_params *params)
+bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
+ struct pie_vars *vars, u32 qlen, u32 packet_size)
{
- params->alpha = 2;
- params->beta = 20;
- params->tupdate = usecs_to_jiffies(15 * USEC_PER_MSEC); /* 15 ms */
- params->limit = 1000; /* default of 1000 packets */
- params->target = PSCHED_NS2TICKS(15 * NSEC_PER_MSEC); /* 15 ms */
- params->ecn = false;
- params->bytemode = false;
- params->dq_rate_estimator = false;
-}
-
-/* private skb vars */
-struct pie_skb_cb {
- psched_time_t enqueue_time;
-};
-
-static struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb)
-{
- qdisc_cb_private_validate(skb, sizeof(struct pie_skb_cb));
- return (struct pie_skb_cb *)qdisc_skb_cb(skb)->data;
-}
-
-static psched_time_t pie_get_enqueue_time(const struct sk_buff *skb)
-{
- return get_pie_cb(skb)->enqueue_time;
-}
-
-static void pie_set_enqueue_time(struct sk_buff *skb)
-{
- get_pie_cb(skb)->enqueue_time = psched_get_time();
-}
-
-static void pie_vars_init(struct pie_vars *vars)
-{
- vars->dq_count = DQCOUNT_INVALID;
- vars->dq_tstamp = DTIME_INVALID;
- vars->accu_prob = 0;
- vars->avg_dq_rate = 0;
- /* default of 150 ms in pschedtime */
- vars->burst_time = PSCHED_NS2TICKS(150 * NSEC_PER_MSEC);
- vars->accu_prob_overflows = 0;
-}
-
-static bool drop_early(struct Qdisc *sch, u32 packet_size)
-{
- struct pie_sched_data *q = qdisc_priv(sch);
u64 rnd;
- u64 local_prob = q->vars.prob;
+ u64 local_prob = vars->prob;
u32 mtu = psched_mtu(qdisc_dev(sch));
/* If there is still burst allowance left skip random early drop */
- if (q->vars.burst_time > 0)
+ if (vars->burst_time > 0)
return false;
/* If current delay is less than half of target, and
* if drop prob is low already, disable early_drop
*/
- if ((q->vars.qdelay < q->params.target / 2) &&
- (q->vars.prob < MAX_PROB / 5))
+ if ((vars->qdelay < params->target / 2) &&
+ (vars->prob < MAX_PROB / 5))
return false;
- /* If we have fewer than 2 mtu-sized packets, disable drop_early,
+ /* If we have fewer than 2 mtu-sized packets, disable pie_drop_early,
* similar to min_th in RED
*/
- if (sch->qstats.backlog < 2 * mtu)
+ if (qlen < 2 * mtu)
return false;
/* If bytemode is turned on, use packet size to compute new
* probablity. Smaller packets will have lower drop prob in this case
*/
- if (q->params.bytemode && packet_size <= mtu)
+ if (params->bytemode && packet_size <= mtu)
local_prob = (u64)packet_size * div_u64(local_prob, mtu);
else
- local_prob = q->vars.prob;
+ local_prob = vars->prob;
if (local_prob == 0) {
- q->vars.accu_prob = 0;
- q->vars.accu_prob_overflows = 0;
+ vars->accu_prob = 0;
+ vars->accu_prob_overflows = 0;
}
- if (local_prob > MAX_PROB - q->vars.accu_prob)
- q->vars.accu_prob_overflows++;
+ if (local_prob > MAX_PROB - vars->accu_prob)
+ vars->accu_prob_overflows++;
- q->vars.accu_prob += local_prob;
+ vars->accu_prob += local_prob;
- if (q->vars.accu_prob_overflows == 0 &&
- q->vars.accu_prob < (MAX_PROB / 100) * 85)
+ if (vars->accu_prob_overflows == 0 &&
+ vars->accu_prob < (MAX_PROB / 100) * 85)
return false;
- if (q->vars.accu_prob_overflows == 8 &&
- q->vars.accu_prob >= MAX_PROB / 2)
+ if (vars->accu_prob_overflows == 8 &&
+ vars->accu_prob >= MAX_PROB / 2)
return true;
prandom_bytes(&rnd, 8);
if (rnd < local_prob) {
- q->vars.accu_prob = 0;
- q->vars.accu_prob_overflows = 0;
+ vars->accu_prob = 0;
+ vars->accu_prob_overflows = 0;
return true;
}
return false;
}
+EXPORT_SYMBOL_GPL(pie_drop_early);
static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
@@ -184,7 +101,8 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
goto out;
}
- if (!drop_early(sch, skb->len)) {
+ if (!pie_drop_early(sch, &q->params, &q->vars, sch->qstats.backlog,
+ skb->len)) {
enqueue = true;
} else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) &&
INET_ECN_set_ce(skb)) {
@@ -216,14 +134,14 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
}
static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = {
- [TCA_PIE_TARGET] = {.type = NLA_U32},
- [TCA_PIE_LIMIT] = {.type = NLA_U32},
- [TCA_PIE_TUPDATE] = {.type = NLA_U32},
- [TCA_PIE_ALPHA] = {.type = NLA_U32},
- [TCA_PIE_BETA] = {.type = NLA_U32},
- [TCA_PIE_ECN] = {.type = NLA_U32},
- [TCA_PIE_BYTEMODE] = {.type = NLA_U32},
- [TCA_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32},
+ [TCA_PIE_TARGET] = {.type = NLA_U32},
+ [TCA_PIE_LIMIT] = {.type = NLA_U32},
+ [TCA_PIE_TUPDATE] = {.type = NLA_U32},
+ [TCA_PIE_ALPHA] = {.type = NLA_U32},
+ [TCA_PIE_BETA] = {.type = NLA_U32},
+ [TCA_PIE_ECN] = {.type = NLA_U32},
+ [TCA_PIE_BYTEMODE] = {.type = NLA_U32},
+ [TCA_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32},
};
static int pie_change(struct Qdisc *sch, struct nlattr *opt,
@@ -296,26 +214,25 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt,
return 0;
}
-static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
+void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params,
+ struct pie_vars *vars, u32 qlen)
{
- struct pie_sched_data *q = qdisc_priv(sch);
- int qlen = sch->qstats.backlog; /* current queue size in bytes */
psched_time_t now = psched_get_time();
u32 dtime = 0;
/* If dq_rate_estimator is disabled, calculate qdelay using the
* packet timestamp.
*/
- if (!q->params.dq_rate_estimator) {
- q->vars.qdelay = now - pie_get_enqueue_time(skb);
+ if (!params->dq_rate_estimator) {
+ vars->qdelay = now - pie_get_enqueue_time(skb);
- if (q->vars.dq_tstamp != DTIME_INVALID)
- dtime = now - q->vars.dq_tstamp;
+ if (vars->dq_tstamp != DTIME_INVALID)
+ dtime = now - vars->dq_tstamp;
- q->vars.dq_tstamp = now;
+ vars->dq_tstamp = now;
if (qlen == 0)
- q->vars.qdelay = 0;
+ vars->qdelay = 0;
if (dtime == 0)
return;
@@ -327,39 +244,39 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
* we have enough packets to calculate the drain rate. Save
* current time as dq_tstamp and start measurement cycle.
*/
- if (qlen >= QUEUE_THRESHOLD && q->vars.dq_count == DQCOUNT_INVALID) {
- q->vars.dq_tstamp = psched_get_time();
- q->vars.dq_count = 0;
+ if (qlen >= QUEUE_THRESHOLD && vars->dq_count == DQCOUNT_INVALID) {
+ vars->dq_tstamp = psched_get_time();
+ vars->dq_count = 0;
}
- /* Calculate the average drain rate from this value. If queue length
- * has receded to a small value viz., <= QUEUE_THRESHOLD bytes,reset
+ /* Calculate the average drain rate from this value. If queue length
+ * has receded to a small value viz., <= QUEUE_THRESHOLD bytes, reset
* the dq_count to -1 as we don't have enough packets to calculate the
- * drain rate anymore The following if block is entered only when we
+ * drain rate anymore. The following if block is entered only when we
* have a substantial queue built up (QUEUE_THRESHOLD bytes or more)
* and we calculate the drain rate for the threshold here. dq_count is
* in bytes, time difference in psched_time, hence rate is in
* bytes/psched_time.
*/
- if (q->vars.dq_count != DQCOUNT_INVALID) {
- q->vars.dq_count += skb->len;
+ if (vars->dq_count != DQCOUNT_INVALID) {
+ vars->dq_count += skb->len;
- if (q->vars.dq_count >= QUEUE_THRESHOLD) {
- u32 count = q->vars.dq_count << PIE_SCALE;
+ if (vars->dq_count >= QUEUE_THRESHOLD) {
+ u32 count = vars->dq_count << PIE_SCALE;
- dtime = now - q->vars.dq_tstamp;
+ dtime = now - vars->dq_tstamp;
if (dtime == 0)
return;
count = count / dtime;
- if (q->vars.avg_dq_rate == 0)
- q->vars.avg_dq_rate = count;
+ if (vars->avg_dq_rate == 0)
+ vars->avg_dq_rate = count;
else
- q->vars.avg_dq_rate =
- (q->vars.avg_dq_rate -
- (q->vars.avg_dq_rate >> 3)) + (count >> 3);
+ vars->avg_dq_rate =
+ (vars->avg_dq_rate -
+ (vars->avg_dq_rate >> 3)) + (count >> 3);
/* If the queue has receded below the threshold, we hold
* on to the last drain rate calculated, else we reset
@@ -367,10 +284,10 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
* packet is dequeued
*/
if (qlen < QUEUE_THRESHOLD) {
- q->vars.dq_count = DQCOUNT_INVALID;
+ vars->dq_count = DQCOUNT_INVALID;
} else {
- q->vars.dq_count = 0;
- q->vars.dq_tstamp = psched_get_time();
+ vars->dq_count = 0;
+ vars->dq_tstamp = psched_get_time();
}
goto burst_allowance_reduction;
@@ -380,18 +297,18 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
return;
burst_allowance_reduction:
- if (q->vars.burst_time > 0) {
- if (q->vars.burst_time > dtime)
- q->vars.burst_time -= dtime;
+ if (vars->burst_time > 0) {
+ if (vars->burst_time > dtime)
+ vars->burst_time -= dtime;
else
- q->vars.burst_time = 0;
+ vars->burst_time = 0;
}
}
+EXPORT_SYMBOL_GPL(pie_process_dequeue);
-static void calculate_probability(struct Qdisc *sch)
+void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
+ u32 qlen)
{
- struct pie_sched_data *q = qdisc_priv(sch);
- u32 qlen = sch->qstats.backlog; /* queue size in bytes */
psched_time_t qdelay = 0; /* in pschedtime */
psched_time_t qdelay_old = 0; /* in pschedtime */
s64 delta = 0; /* determines the change in probability */
@@ -400,21 +317,21 @@ static void calculate_probability(struct Qdisc *sch)
u32 power;
bool update_prob = true;
- if (q->params.dq_rate_estimator) {
- qdelay_old = q->vars.qdelay;
- q->vars.qdelay_old = q->vars.qdelay;
+ if (params->dq_rate_estimator) {
+ qdelay_old = vars->qdelay;
+ vars->qdelay_old = vars->qdelay;
- if (q->vars.avg_dq_rate > 0)
- qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate;
+ if (vars->avg_dq_rate > 0)
+ qdelay = (qlen << PIE_SCALE) / vars->avg_dq_rate;
else
qdelay = 0;
} else {
- qdelay = q->vars.qdelay;
- qdelay_old = q->vars.qdelay_old;
+ qdelay = vars->qdelay;
+ qdelay_old = vars->qdelay_old;
}
- /* If qdelay is zero and qlen is not, it means qlen is very small, less
- * than dequeue_rate, so we do not update probabilty in this round
+ /* If qdelay is zero and qlen is not, it means qlen is very small,
+ * so we do not update probabilty in this round.
*/
if (qdelay == 0 && qlen != 0)
update_prob = false;
@@ -426,18 +343,18 @@ static void calculate_probability(struct Qdisc *sch)
* probability. alpha/beta are updated locally below by scaling down
* by 16 to come to 0-2 range.
*/
- alpha = ((u64)q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
- beta = ((u64)q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
+ alpha = ((u64)params->alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
+ beta = ((u64)params->beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
/* We scale alpha and beta differently depending on how heavy the
* congestion is. Please see RFC 8033 for details.
*/
- if (q->vars.prob < MAX_PROB / 10) {
+ if (vars->prob < MAX_PROB / 10) {
alpha >>= 1;
beta >>= 1;
power = 100;
- while (q->vars.prob < div_u64(MAX_PROB, power) &&
+ while (vars->prob < div_u64(MAX_PROB, power) &&
power <= 1000000) {
alpha >>= 2;
beta >>= 2;
@@ -446,14 +363,14 @@ static void calculate_probability(struct Qdisc *sch)
}
/* alpha and beta should be between 0 and 32, in multiples of 1/16 */
- delta += alpha * (u64)(qdelay - q->params.target);
+ delta += alpha * (u64)(qdelay - params->target);
delta += beta * (u64)(qdelay - qdelay_old);
- oldprob = q->vars.prob;
+ oldprob = vars->prob;
/* to ensure we increase probability in steps of no more than 2% */
if (delta > (s64)(MAX_PROB / (100 / 2)) &&
- q->vars.prob >= MAX_PROB / 10)
+ vars->prob >= MAX_PROB / 10)
delta = (MAX_PROB / 100) * 2;
/* Non-linear drop:
@@ -464,12 +381,12 @@ static void calculate_probability(struct Qdisc *sch)
if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC)))
delta += MAX_PROB / (100 / 2);
- q->vars.prob += delta;
+ vars->prob += delta;
if (delta > 0) {
/* prevent overflow */
- if (q->vars.prob < oldprob) {
- q->vars.prob = MAX_PROB;
+ if (vars->prob < oldprob) {
+ vars->prob = MAX_PROB;
/* Prevent normalization error. If probability is at
* maximum value already, we normalize it here, and
* skip the check to do a non-linear drop in the next
@@ -479,8 +396,8 @@ static void calculate_probability(struct Qdisc *sch)
}
} else {
/* prevent underflow */
- if (q->vars.prob > oldprob)
- q->vars.prob = 0;
+ if (vars->prob > oldprob)
+ vars->prob = 0;
}
/* Non-linear drop in probability: Reduce drop probability quickly if
@@ -489,10 +406,10 @@ static void calculate_probability(struct Qdisc *sch)
if (qdelay == 0 && qdelay_old == 0 && update_prob)
/* Reduce drop probability to 98.4% */
- q->vars.prob -= q->vars.prob / 64u;
+ vars->prob -= vars->prob / 64;
- q->vars.qdelay = qdelay;
- q->vars.qlen_old = qlen;
+ vars->qdelay = qdelay;
+ vars->qlen_old = qlen;
/* We restart the measurement cycle if the following conditions are met
* 1. If the delay has been low for 2 consecutive Tupdate periods
@@ -500,16 +417,17 @@ static void calculate_probability(struct Qdisc *sch)
* 3. If average dq_rate_estimator is enabled, we have atleast one
* estimate for the avg_dq_rate ie., is a non-zero value
*/
- if ((q->vars.qdelay < q->params.target / 2) &&
- (q->vars.qdelay_old < q->params.target / 2) &&
- q->vars.prob == 0 &&
- (!q->params.dq_rate_estimator || q->vars.avg_dq_rate > 0)) {
- pie_vars_init(&q->vars);
+ if ((vars->qdelay < params->target / 2) &&
+ (vars->qdelay_old < params->target / 2) &&
+ vars->prob == 0 &&
+ (!params->dq_rate_estimator || vars->avg_dq_rate > 0)) {
+ pie_vars_init(vars);
}
- if (!q->params.dq_rate_estimator)
- q->vars.qdelay_old = qdelay;
+ if (!params->dq_rate_estimator)
+ vars->qdelay_old = qdelay;
}
+EXPORT_SYMBOL_GPL(pie_calculate_probability);
static void pie_timer(struct timer_list *t)
{
@@ -518,7 +436,7 @@ static void pie_timer(struct timer_list *t)
spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
spin_lock(root_lock);
- calculate_probability(sch);
+ pie_calculate_probability(&q->params, &q->vars, sch->qstats.backlog);
/* reset the timer to fire after 'tupdate'. tupdate is in jiffies. */
if (q->params.tupdate)
@@ -607,12 +525,13 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch)
{
+ struct pie_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb = qdisc_dequeue_head(sch);
if (!skb)
return NULL;
- pie_process_dequeue(sch, skb);
+ pie_process_dequeue(skb, &q->params, &q->vars, sch->qstats.backlog);
return skb;
}
@@ -633,7 +552,7 @@ static void pie_destroy(struct Qdisc *sch)
}
static struct Qdisc_ops pie_qdisc_ops __read_mostly = {
- .id = "pie",
+ .id = "pie",
.priv_size = sizeof(struct pie_sched_data),
.enqueue = pie_qdisc_enqueue,
.dequeue = pie_qdisc_dequeue,
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 18b884c..6479417 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -292,8 +292,14 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
struct tc_prio_qopt_offload graft_offload;
unsigned long band = arg - 1;
- if (new == NULL)
- new = &noop_qdisc;
+ if (!new) {
+ new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+ TC_H_MAKE(sch->handle, arg), extack);
+ if (!new)
+ new = &noop_qdisc;
+ else
+ qdisc_hash_add(new, true);
+ }
*old = qdisc_replace(sch, new, &q->queues[band]);
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 5f72f3f..78e7902 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -15,6 +15,7 @@
#include <linux/skbuff.h>
#include <net/netlink.h>
#include <net/sch_generic.h>
+#include <net/pkt_cls.h>
#include <net/pkt_sched.h>
@@ -137,6 +138,52 @@ static u64 psched_ns_t2l(const struct psched_ratecfg *r,
return len;
}
+static void tbf_offload_change(struct Qdisc *sch)
+{
+ struct tbf_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+ struct tc_tbf_qopt_offload qopt;
+
+ if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+ return;
+
+ qopt.command = TC_TBF_REPLACE;
+ qopt.handle = sch->handle;
+ qopt.parent = sch->parent;
+ qopt.replace_params.rate = q->rate;
+ qopt.replace_params.max_size = q->max_size;
+ qopt.replace_params.qstats = &sch->qstats;
+
+ dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TBF, &qopt);
+}
+
+static void tbf_offload_destroy(struct Qdisc *sch)
+{
+ struct net_device *dev = qdisc_dev(sch);
+ struct tc_tbf_qopt_offload qopt;
+
+ if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+ return;
+
+ qopt.command = TC_TBF_DESTROY;
+ qopt.handle = sch->handle;
+ qopt.parent = sch->parent;
+ dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TBF, &qopt);
+}
+
+static int tbf_offload_dump(struct Qdisc *sch)
+{
+ struct tc_tbf_qopt_offload qopt;
+
+ qopt.command = TC_TBF_STATS;
+ qopt.handle = sch->handle;
+ qopt.parent = sch->parent;
+ qopt.stats.bstats = &sch->bstats;
+ qopt.stats.qstats = &sch->qstats;
+
+ return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_TBF, &qopt);
+}
+
/* GSO packet is too big, segment it so that tbf can transmit
* each segment in time
*/
@@ -155,8 +202,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
return qdisc_drop(skb, sch, to_free);
nb = 0;
- while (segs) {
- nskb = segs->next;
+ skb_list_walk_safe(segs, segs, nskb) {
skb_mark_not_on_list(segs);
qdisc_skb_cb(segs)->pkt_len = segs->len;
len += segs->len;
@@ -167,7 +213,6 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
} else {
nb++;
}
- segs = nskb;
}
sch->q.qlen += nb;
if (nb > 1)
@@ -409,6 +454,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
sch_tree_unlock(sch);
err = 0;
+
+ tbf_offload_change(sch);
done:
return err;
}
@@ -434,6 +481,7 @@ static void tbf_destroy(struct Qdisc *sch)
struct tbf_sched_data *q = qdisc_priv(sch);
qdisc_watchdog_cancel(&q->watchdog);
+ tbf_offload_destroy(sch);
qdisc_put(q->qdisc);
}
@@ -442,8 +490,12 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
struct tbf_sched_data *q = qdisc_priv(sch);
struct nlattr *nest;
struct tc_tbf_qopt opt;
+ int err;
- sch->qstats.backlog = q->qdisc->qstats.backlog;
+ err = tbf_offload_dump(sch);
+ if (err)
+ return err;
+
nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index ce82699..2bc2946 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1359,8 +1359,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
/* Generate an INIT ACK chunk. */
new_obj = sctp_make_init_ack(asoc, chunk, GFP_ATOMIC,
0);
- if (!new_obj)
- goto nomem;
+ if (!new_obj) {
+ error = -ENOMEM;
+ break;
+ }
sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
SCTP_CHUNK(new_obj));
@@ -1382,7 +1384,8 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
if (!new_obj) {
if (cmd->obj.chunk)
sctp_chunk_free(cmd->obj.chunk);
- goto nomem;
+ error = -ENOMEM;
+ break;
}
sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
SCTP_CHUNK(new_obj));
@@ -1429,8 +1432,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
/* Generate a SHUTDOWN chunk. */
new_obj = sctp_make_shutdown(asoc, chunk);
- if (!new_obj)
- goto nomem;
+ if (!new_obj) {
+ error = -ENOMEM;
+ break;
+ }
sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
SCTP_CHUNK(new_obj));
break;
@@ -1766,11 +1771,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
break;
}
- if (error)
+ if (error) {
+ cmd = sctp_next_cmd(commands);
+ while (cmd) {
+ if (cmd->verb == SCTP_CMD_REPLY)
+ sctp_chunk_free(cmd->obj.chunk);
+ cmd = sctp_next_cmd(commands);
+ }
break;
+ }
}
-out:
/* If this is in response to a received chunk, wait until
* we are done with the packet to open the queue so that we don't
* send multiple packets in response to a single request.
@@ -1785,7 +1796,4 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
sp->data_ready_signalled = 0;
return error;
-nomem:
- error = -ENOMEM;
- goto out;
}
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 82dedf0..2a5ed47 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -611,7 +611,7 @@ static const struct genl_ops smc_pnet_ops[] = {
{
.cmd = SMC_PNETID_GET,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM,
+ /* can be retrieved by unprivileged users */
.doit = smc_pnet_get,
.dumpit = smc_pnet_dump,
.start = smc_pnet_dump_start
diff --git a/net/socket.c b/net/socket.c
index 51bf349..b79a05d 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -128,7 +128,18 @@ static ssize_t sock_sendpage(struct file *file, struct page *page,
static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags);
-static void sock_show_fdinfo(struct seq_file *m, struct file *f);
+
+#ifdef CONFIG_PROC_FS
+static void sock_show_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct socket *sock = f->private_data;
+
+ if (sock->ops->show_fdinfo)
+ sock->ops->show_fdinfo(m, sock);
+}
+#else
+#define sock_show_fdinfo NULL
+#endif
/*
* Socket files have a set of 'special' operations as well as the generic file ones. These don't appear
@@ -151,9 +162,7 @@ static const struct file_operations socket_file_ops = {
.sendpage = sock_sendpage,
.splice_write = generic_splice_sendpage,
.splice_read = sock_splice_read,
-#ifdef CONFIG_PROC_FS
.show_fdinfo = sock_show_fdinfo,
-#endif
};
/*
@@ -997,14 +1006,6 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
return res;
}
-static void sock_show_fdinfo(struct seq_file *m, struct file *f)
-{
- struct socket *sock = f->private_data;
-
- if (sock->ops->show_fdinfo)
- sock->ops->show_fdinfo(m, sock);
-}
-
/*
* Atomic setting of ioctl hooks to avoid race
* with module unload.
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 77c7dd7..fda3889 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -77,7 +77,7 @@
static void rpcrdma_sendctx_put_locked(struct rpcrdma_xprt *r_xprt,
struct rpcrdma_sendctx *sc);
static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt);
-static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf);
+static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt);
static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt);
static void rpcrdma_mrs_destroy(struct rpcrdma_xprt *r_xprt);
static struct rpcrdma_regbuf *
@@ -244,6 +244,7 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
ia->ri_id->device->name,
rpcrdma_addrstr(r_xprt), rpcrdma_portstr(r_xprt));
#endif
+ init_completion(&ia->ri_remove_done);
set_bit(RPCRDMA_IAF_REMOVING, &ia->ri_flags);
ep->rep_connected = -ENODEV;
xprt_force_disconnect(xprt);
@@ -297,7 +298,6 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia)
int rc;
init_completion(&ia->ri_done);
- init_completion(&ia->ri_remove_done);
id = rdma_create_id(xprt->rx_xprt.xprt_net, rpcrdma_cm_event_handler,
xprt, RDMA_PS_TCP, IB_QPT_RC);
@@ -421,7 +421,7 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia)
/* The ULP is responsible for ensuring all DMA
* mappings and MRs are gone.
*/
- rpcrdma_reps_destroy(buf);
+ rpcrdma_reps_unmap(r_xprt);
list_for_each_entry(req, &buf->rb_allreqs, rl_all) {
rpcrdma_regbuf_dma_unmap(req->rl_rdmabuf);
rpcrdma_regbuf_dma_unmap(req->rl_sendbuf);
@@ -599,6 +599,7 @@ static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt,
struct ib_qp_init_attr *qp_init_attr)
{
struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+ struct rpcrdma_ep *ep = &r_xprt->rx_ep;
int rc, err;
trace_xprtrdma_reinsert(r_xprt);
@@ -613,6 +614,7 @@ static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt,
pr_err("rpcrdma: rpcrdma_ep_create returned %d\n", err);
goto out2;
}
+ memcpy(qp_init_attr, &ep->rep_attr, sizeof(*qp_init_attr));
rc = -ENETUNREACH;
err = rdma_create_qp(ia->ri_id, ia->ri_pd, qp_init_attr);
@@ -1090,6 +1092,7 @@ static struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt,
rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov;
rep->rr_recv_wr.num_sge = 1;
rep->rr_temp = temp;
+ list_add(&rep->rr_all, &r_xprt->rx_buf.rb_all_reps);
return rep;
out_free:
@@ -1100,6 +1103,7 @@ static struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt,
static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep)
{
+ list_del(&rep->rr_all);
rpcrdma_regbuf_free(rep->rr_rdmabuf);
kfree(rep);
}
@@ -1118,10 +1122,16 @@ static struct rpcrdma_rep *rpcrdma_rep_get_locked(struct rpcrdma_buffer *buf)
static void rpcrdma_rep_put(struct rpcrdma_buffer *buf,
struct rpcrdma_rep *rep)
{
- if (!rep->rr_temp)
- llist_add(&rep->rr_node, &buf->rb_free_reps);
- else
- rpcrdma_rep_destroy(rep);
+ llist_add(&rep->rr_node, &buf->rb_free_reps);
+}
+
+static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt)
+{
+ struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+ struct rpcrdma_rep *rep;
+
+ list_for_each_entry(rep, &buf->rb_all_reps, rr_all)
+ rpcrdma_regbuf_dma_unmap(rep->rr_rdmabuf);
}
static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf)
@@ -1152,6 +1162,7 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
INIT_LIST_HEAD(&buf->rb_send_bufs);
INIT_LIST_HEAD(&buf->rb_allreqs);
+ INIT_LIST_HEAD(&buf->rb_all_reps);
rc = -ENOMEM;
for (i = 0; i < buf->rb_max_requests; i++) {
@@ -1504,6 +1515,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
wr = NULL;
while (needed) {
rep = rpcrdma_rep_get_locked(buf);
+ if (rep && rep->rr_temp) {
+ rpcrdma_rep_destroy(rep);
+ continue;
+ }
if (!rep)
rep = rpcrdma_rep_create(r_xprt, temp);
if (!rep)
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 5d15140..d796d68 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -203,6 +203,7 @@ struct rpcrdma_rep {
struct xdr_stream rr_stream;
struct llist_node rr_node;
struct ib_recv_wr rr_recv_wr;
+ struct list_head rr_all;
};
/* To reduce the rate at which a transport invokes ib_post_recv
@@ -368,6 +369,7 @@ struct rpcrdma_buffer {
struct list_head rb_allreqs;
struct list_head rb_all_mrs;
+ struct list_head rb_all_reps;
struct llist_head rb_free_reps;
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index 11255e9..ee49a9f 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -9,7 +9,7 @@
core.o link.o discover.o msg.o \
name_distr.o subscr.o monitor.o name_table.o net.o \
netlink.o netlink_compat.o node.o socket.o eth_media.o \
- topsrv.o socket.o group.o trace.o
+ topsrv.o group.o trace.o
CFLAGS_trace.o += -I$(src)
@@ -20,5 +20,3 @@
obj-$(CONFIG_TIPC_DIAG) += diag.o
-
-tipc_diag-y := diag.o
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 0254bb7..2175163 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -204,8 +204,8 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
return -ENOMEM;
}
- attrbuf = kmalloc_array(tipc_genl_family.maxattr + 1,
- sizeof(struct nlattr *), GFP_KERNEL);
+ attrbuf = kcalloc(tipc_genl_family.maxattr + 1,
+ sizeof(struct nlattr *), GFP_KERNEL);
if (!attrbuf) {
err = -ENOMEM;
goto err_out;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 6552f98..f9b4fb9 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -287,12 +287,12 @@ static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err)
*
* Caller must hold socket lock
*/
-static void tsk_rej_rx_queue(struct sock *sk)
+static void tsk_rej_rx_queue(struct sock *sk, int error)
{
struct sk_buff *skb;
while ((skb = __skb_dequeue(&sk->sk_receive_queue)))
- tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
+ tipc_sk_respond(sk, skb, error);
}
static bool tipc_sk_connected(struct sock *sk)
@@ -545,34 +545,45 @@ static void __tipc_shutdown(struct socket *sock, int error)
/* Remove pending SYN */
__skb_queue_purge(&sk->sk_write_queue);
- /* Reject all unreceived messages, except on an active connection
- * (which disconnects locally & sends a 'FIN+' to peer).
- */
- while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
- if (TIPC_SKB_CB(skb)->bytes_read) {
- kfree_skb(skb);
- continue;
- }
- if (!tipc_sk_type_connectionless(sk) &&
- sk->sk_state != TIPC_DISCONNECTING) {
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- tipc_node_remove_conn(net, dnode, tsk->portid);
- }
- tipc_sk_respond(sk, skb, error);
+ /* Remove partially received buffer if any */
+ skb = skb_peek(&sk->sk_receive_queue);
+ if (skb && TIPC_SKB_CB(skb)->bytes_read) {
+ __skb_unlink(skb, &sk->sk_receive_queue);
+ kfree_skb(skb);
}
- if (tipc_sk_type_connectionless(sk))
+ /* Reject all unreceived messages if connectionless */
+ if (tipc_sk_type_connectionless(sk)) {
+ tsk_rej_rx_queue(sk, error);
return;
+ }
- if (sk->sk_state != TIPC_DISCONNECTING) {
+ switch (sk->sk_state) {
+ case TIPC_CONNECTING:
+ case TIPC_ESTABLISHED:
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ tipc_node_remove_conn(net, dnode, tsk->portid);
+ /* Send a FIN+/- to its peer */
+ skb = __skb_dequeue(&sk->sk_receive_queue);
+ if (skb) {
+ __skb_queue_purge(&sk->sk_receive_queue);
+ tipc_sk_respond(sk, skb, error);
+ break;
+ }
skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
tsk_own_node(tsk), tsk_peer_port(tsk),
tsk->portid, error);
if (skb)
tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
- tipc_node_remove_conn(net, dnode, tsk->portid);
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ break;
+ case TIPC_LISTEN:
+ /* Reject all SYN messages */
+ tsk_rej_rx_queue(sk, error);
+ break;
+ default:
+ __skb_queue_purge(&sk->sk_receive_queue);
+ break;
}
}
@@ -2432,8 +2443,8 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
return sock_intr_errno(*timeo_p);
add_wait_queue(sk_sleep(sk), &wait);
- done = sk_wait_event(sk, timeo_p,
- sk->sk_state != TIPC_CONNECTING, &wait);
+ done = sk_wait_event(sk, timeo_p, tipc_sk_connected(sk),
+ &wait);
remove_wait_queue(sk_sleep(sk), &wait);
} while (!done);
return 0;
@@ -2643,7 +2654,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
* Reject any stray messages received by new socket
* before the socket lock was taken (very, very unlikely)
*/
- tsk_rej_rx_queue(new_sk);
+ tsk_rej_rx_queue(new_sk, TIPC_ERR_NO_PORT);
/* Connect new socket to it's peer */
tipc_sk_finish_conn(new_tsock, msg_origport(msg), msg_orignode(msg));
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index dac24c7..94774c0 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -732,15 +732,19 @@ static int tls_init(struct sock *sk)
return rc;
}
-static void tls_update(struct sock *sk, struct proto *p)
+static void tls_update(struct sock *sk, struct proto *p,
+ void (*write_space)(struct sock *sk))
{
struct tls_context *ctx;
ctx = tls_get_ctx(sk);
- if (likely(ctx))
+ if (likely(ctx)) {
+ ctx->sk_write_space = write_space;
ctx->sk_proto = p;
- else
+ } else {
sk->sk_prot = p;
+ sk->sk_write_space = write_space;
+ }
}
static int tls_get_info(const struct sock *sk, struct sk_buff *skb)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index c6803a8..c98e602 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -256,8 +256,6 @@ static int tls_do_decryption(struct sock *sk,
return ret;
ret = crypto_wait_req(ret, &ctx->async_wait);
- } else if (ret == -EBADMSG) {
- TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTERROR);
}
if (async)
@@ -682,12 +680,32 @@ static int tls_push_record(struct sock *sk, int flags,
split_point = msg_pl->apply_bytes;
split = split_point && split_point < msg_pl->sg.size;
+ if (unlikely((!split &&
+ msg_pl->sg.size +
+ prot->overhead_size > msg_en->sg.size) ||
+ (split &&
+ split_point +
+ prot->overhead_size > msg_en->sg.size))) {
+ split = true;
+ split_point = msg_en->sg.size;
+ }
if (split) {
rc = tls_split_open_record(sk, rec, &tmp, msg_pl, msg_en,
split_point, prot->overhead_size,
&orig_end);
if (rc < 0)
return rc;
+ /* This can happen if above tls_split_open_record allocates
+ * a single large encryption buffer instead of two smaller
+ * ones. In this case adjust pointers and continue without
+ * split.
+ */
+ if (!msg_pl->sg.size) {
+ tls_merge_open_record(sk, rec, tmp, orig_end);
+ msg_pl = &rec->msg_plaintext;
+ msg_en = &rec->msg_encrypted;
+ split = false;
+ }
sk_msg_trim(sk, msg_en, msg_pl->sg.size +
prot->overhead_size);
}
@@ -709,6 +727,12 @@ static int tls_push_record(struct sock *sk, int flags,
sg_mark_end(sk_msg_elem(msg_pl, i));
}
+ if (msg_pl->sg.end < msg_pl->sg.start) {
+ sg_chain(&msg_pl->sg.data[msg_pl->sg.start],
+ MAX_SKB_FRAGS - msg_pl->sg.start + 1,
+ msg_pl->sg.data);
+ }
+
i = msg_pl->sg.start;
sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]);
@@ -772,7 +796,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
psock = sk_psock_get(sk);
if (!psock || !policy) {
err = tls_push_record(sk, flags, record_type);
- if (err) {
+ if (err && err != -EINPROGRESS) {
*copied -= sk_msg_free(sk, msg);
tls_free_open_rec(sk);
}
@@ -783,10 +807,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
if (psock->eval == __SK_NONE) {
delta = msg->sg.size;
psock->eval = sk_psock_msg_verdict(sk, psock, msg);
- if (delta < msg->sg.size)
- delta -= msg->sg.size;
- else
- delta = 0;
+ delta -= msg->sg.size;
}
if (msg->cork_bytes && msg->cork_bytes > msg->sg.size &&
!enospc && !full_record) {
@@ -801,7 +822,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
switch (psock->eval) {
case __SK_PASS:
err = tls_push_record(sk, flags, record_type);
- if (err < 0) {
+ if (err && err != -EINPROGRESS) {
*copied -= sk_msg_free(sk, msg);
tls_free_open_rec(sk);
goto out_err;
@@ -1515,7 +1536,9 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb,
if (err == -EINPROGRESS)
tls_advance_record_sn(sk, prot,
&tls_ctx->rx);
-
+ else if (err == -EBADMSG)
+ TLS_INC_STATS(sock_net(sk),
+ LINUX_MIB_TLSDECRYPTERROR);
return err;
}
} else {
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 6756a3c..321af97 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2100,8 +2100,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
mutex_lock(&u->iolock);
skip = sk_peek_offset(sk, flags);
- skb = __skb_try_recv_datagram(sk, flags, scm_stat_del,
- &skip, &err, &last);
+ skb = __skb_try_recv_datagram(sk, &sk->sk_receive_queue, flags,
+ scm_stat_del, &skip, &err, &last);
if (skb)
break;
@@ -2110,7 +2110,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
if (err != -EAGAIN)
break;
} while (timeo &&
- !__skb_wait_for_more_packets(sk, &err, &timeo, last));
+ !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue,
+ &err, &timeo, last));
if (!skb) { /* implies iolock unlocked */
unix_state_lock(sk);
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index b3bdae7..3492c02 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -138,28 +138,15 @@ struct hvsock {
****************************************************************************
* The only valid Service GUIDs, from the perspectives of both the host and *
* Linux VM, that can be connected by the other end, must conform to this *
- * format: <port>-facb-11e6-bd58-64006a7986d3, and the "port" must be in *
- * this range [0, 0x7FFFFFFF]. *
+ * format: <port>-facb-11e6-bd58-64006a7986d3. *
****************************************************************************
*
* When we write apps on the host to connect(), the GUID ServiceID is used.
* When we write apps in Linux VM to connect(), we only need to specify the
* port and the driver will form the GUID and use that to request the host.
*
- * From the perspective of Linux VM:
- * 1. the local ephemeral port (i.e. the local auto-bound port when we call
- * connect() without explicit bind()) is generated by __vsock_bind_stream(),
- * and the range is [1024, 0xFFFFFFFF).
- * 2. the remote ephemeral port (i.e. the auto-generated remote port for
- * a connect request initiated by the host's connect()) is generated by
- * hvs_remote_addr_init() and the range is [0x80000000, 0xFFFFFFFF).
*/
-#define MAX_LISTEN_PORT ((u32)0x7FFFFFFF)
-#define MAX_VM_LISTEN_PORT MAX_LISTEN_PORT
-#define MAX_HOST_LISTEN_PORT MAX_LISTEN_PORT
-#define MIN_HOST_EPHEMERAL_PORT (MAX_HOST_LISTEN_PORT + 1)
-
/* 00000000-facb-11e6-bd58-64006a7986d3 */
static const guid_t srv_id_template =
GUID_INIT(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58,
@@ -184,34 +171,6 @@ static void hvs_addr_init(struct sockaddr_vm *addr, const guid_t *svr_id)
vsock_addr_init(addr, VMADDR_CID_ANY, port);
}
-static void hvs_remote_addr_init(struct sockaddr_vm *remote,
- struct sockaddr_vm *local)
-{
- static u32 host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT;
- struct sock *sk;
-
- /* Remote peer is always the host */
- vsock_addr_init(remote, VMADDR_CID_HOST, VMADDR_PORT_ANY);
-
- while (1) {
- /* Wrap around ? */
- if (host_ephemeral_port < MIN_HOST_EPHEMERAL_PORT ||
- host_ephemeral_port == VMADDR_PORT_ANY)
- host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT;
-
- remote->svm_port = host_ephemeral_port++;
-
- sk = vsock_find_connected_socket(remote, local);
- if (!sk) {
- /* Found an available ephemeral port */
- return;
- }
-
- /* Release refcnt got in vsock_find_connected_socket */
- sock_put(sk);
- }
-}
-
static void hvs_set_channel_pending_send_size(struct vmbus_channel *chan)
{
set_channel_pending_send_size(chan,
@@ -341,12 +300,7 @@ static void hvs_open_connection(struct vmbus_channel *chan)
if_type = &chan->offermsg.offer.if_type;
if_instance = &chan->offermsg.offer.if_instance;
conn_from_host = chan->offermsg.offer.u.pipe.user_def[0];
-
- /* The host or the VM should only listen on a port in
- * [0, MAX_LISTEN_PORT]
- */
- if (!is_valid_srv_id(if_type) ||
- get_port_by_srv_id(if_type) > MAX_LISTEN_PORT)
+ if (!is_valid_srv_id(if_type))
return;
hvs_addr_init(&addr, conn_from_host ? if_type : if_instance);
@@ -371,8 +325,11 @@ static void hvs_open_connection(struct vmbus_channel *chan)
vnew = vsock_sk(new);
hvs_addr_init(&vnew->local_addr, if_type);
- hvs_remote_addr_init(&vnew->remote_addr, &vnew->local_addr);
+ /* Remote peer is always the host */
+ vsock_addr_init(&vnew->remote_addr,
+ VMADDR_CID_HOST, VMADDR_PORT_ANY);
+ vnew->remote_addr.svm_port = get_port_by_srv_id(if_instance);
ret = vsock_assign_transport(vnew, vsock_sk(sk));
/* Transport assigned (looking at remote_addr) must be the
* same where we received the request.
@@ -766,16 +723,6 @@ static bool hvs_stream_is_active(struct vsock_sock *vsk)
static bool hvs_stream_allow(u32 cid, u32 port)
{
- /* The host's port range [MIN_HOST_EPHEMERAL_PORT, 0xFFFFFFFF) is
- * reserved as ephemeral ports, which are used as the host's ports
- * when the host initiates connections.
- *
- * Perform this check in the guest so an immediate error is produced
- * instead of a timeout.
- */
- if (port > MAX_HOST_LISTEN_PORT)
- return false;
-
if (cid == VMADDR_CID_HOST)
return true;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index fa35265..123b8d72 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -10843,6 +10843,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev,
if (err)
return err;
+ cfg80211_sinfo_release_content(&sinfo);
if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG))
wdev->cqm_config->last_rssi_event_value =
(s8) sinfo.rx_beacon_signal_avg;
@@ -13795,6 +13796,8 @@ static int nl80211_probe_mesh_link(struct sk_buff *skb, struct genl_info *info)
if (err)
return err;
+ cfg80211_sinfo_release_content(&sinfo);
+
return rdev_probe_mesh_link(rdev, dev, dest, buf, len);
}
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index e853a4f..e0d34f7 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -538,6 +538,10 @@ static inline int
rdev_set_wiphy_params(struct cfg80211_registered_device *rdev, u32 changed)
{
int ret;
+
+ if (!rdev->ops->set_wiphy_params)
+ return -EOPNOTSUPP;
+
trace_rdev_set_wiphy_params(&rdev->wiphy, changed);
ret = rdev->ops->set_wiphy_params(&rdev->wiphy, changed);
trace_rdev_return_int(&rdev->wiphy, ret);
@@ -1167,6 +1171,16 @@ rdev_start_radar_detection(struct cfg80211_registered_device *rdev,
return ret;
}
+static inline void
+rdev_end_cac(struct cfg80211_registered_device *rdev,
+ struct net_device *dev)
+{
+ trace_rdev_end_cac(&rdev->wiphy, dev);
+ if (rdev->ops->end_cac)
+ rdev->ops->end_cac(&rdev->wiphy, dev);
+ trace_rdev_return_void(&rdev->wiphy);
+}
+
static inline int
rdev_set_mcast_rate(struct cfg80211_registered_device *rdev,
struct net_device *dev,
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 446c76d..fff9a74 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2261,14 +2261,15 @@ static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator)
static void handle_channel_custom(struct wiphy *wiphy,
struct ieee80211_channel *chan,
- const struct ieee80211_regdomain *regd)
+ const struct ieee80211_regdomain *regd,
+ u32 min_bw)
{
u32 bw_flags = 0;
const struct ieee80211_reg_rule *reg_rule = NULL;
const struct ieee80211_power_rule *power_rule = NULL;
u32 bw;
- for (bw = MHZ_TO_KHZ(20); bw >= MHZ_TO_KHZ(5); bw = bw / 2) {
+ for (bw = MHZ_TO_KHZ(20); bw >= min_bw; bw = bw / 2) {
reg_rule = freq_reg_info_regd(MHZ_TO_KHZ(chan->center_freq),
regd, bw);
if (!IS_ERR(reg_rule))
@@ -2324,8 +2325,14 @@ static void handle_band_custom(struct wiphy *wiphy,
if (!sband)
return;
+ /*
+ * We currently assume that you always want at least 20 MHz,
+ * otherwise channel 12 might get enabled if this rule is
+ * compatible to US, which permits 2402 - 2472 MHz.
+ */
for (i = 0; i < sband->n_channels; i++)
- handle_channel_custom(wiphy, &sband->channels[i], regd);
+ handle_channel_custom(wiphy, &sband->channels[i], regd,
+ MHZ_TO_KHZ(20));
}
/* Used by drivers prior to wiphy registration */
@@ -3885,6 +3892,25 @@ bool regulatory_pre_cac_allowed(struct wiphy *wiphy)
}
EXPORT_SYMBOL(regulatory_pre_cac_allowed);
+static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev)
+{
+ struct wireless_dev *wdev;
+ /* If we finished CAC or received radar, we should end any
+ * CAC running on the same channels.
+ * the check !cfg80211_chandef_dfs_usable contain 2 options:
+ * either all channels are available - those the CAC_FINISHED
+ * event has effected another wdev state, or there is a channel
+ * in unavailable state in wdev chandef - those the RADAR_DETECTED
+ * event has effected another wdev state.
+ * In both cases we should end the CAC on the wdev.
+ */
+ list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
+ if (wdev->cac_started &&
+ !cfg80211_chandef_dfs_usable(&rdev->wiphy, &wdev->chandef))
+ rdev_end_cac(rdev, wdev->netdev);
+ }
+}
+
void regulatory_propagate_dfs_state(struct wiphy *wiphy,
struct cfg80211_chan_def *chandef,
enum nl80211_dfs_state dfs_state,
@@ -3911,8 +3937,10 @@ void regulatory_propagate_dfs_state(struct wiphy *wiphy,
cfg80211_set_dfs_state(&rdev->wiphy, chandef, dfs_state);
if (event == NL80211_RADAR_DETECTED ||
- event == NL80211_RADAR_CAC_FINISHED)
+ event == NL80211_RADAR_CAC_FINISHED) {
cfg80211_sched_dfs_chan_update(rdev);
+ cfg80211_check_and_end_cac(rdev);
+ }
nl80211_radar_notify(rdev, chandef, event, NULL, GFP_KERNEL);
}
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 7a6c38d..d32a2ec 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -1307,14 +1307,14 @@ void cfg80211_autodisconnect_wk(struct work_struct *work)
if (wdev->conn_owner_nlportid) {
switch (wdev->iftype) {
case NL80211_IFTYPE_ADHOC:
- cfg80211_leave_ibss(rdev, wdev->netdev, false);
+ __cfg80211_leave_ibss(rdev, wdev->netdev, false);
break;
case NL80211_IFTYPE_AP:
case NL80211_IFTYPE_P2P_GO:
- cfg80211_stop_ap(rdev, wdev->netdev, false);
+ __cfg80211_stop_ap(rdev, wdev->netdev, false);
break;
case NL80211_IFTYPE_MESH_POINT:
- cfg80211_leave_mesh(rdev, wdev->netdev);
+ __cfg80211_leave_mesh(rdev, wdev->netdev);
break;
case NL80211_IFTYPE_STATION:
case NL80211_IFTYPE_P2P_CLIENT:
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index d98ad2b..8677d7a 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -646,6 +646,11 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_flush_pmksa,
TP_ARGS(wiphy, netdev)
);
+DEFINE_EVENT(wiphy_netdev_evt, rdev_end_cac,
+ TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
+ TP_ARGS(wiphy, netdev)
+);
+
DECLARE_EVENT_CLASS(station_add_change,
TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *mac,
struct station_parameters *params),
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 5b4ed5b..8481e9a 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -564,7 +564,7 @@ __frame_add_frag(struct sk_buff *skb, struct page *page,
struct skb_shared_info *sh = skb_shinfo(skb);
int page_offset;
- page_ref_inc(page);
+ get_page(page);
page_offset = ptr - page_address(page);
skb_add_rx_frag(skb, sh->nr_frags, page, page_offset, len, size);
}
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index 5e677da..69102fd 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -657,7 +657,8 @@ struct iw_statistics *get_wireless_stats(struct net_device *dev)
return NULL;
}
-static int iw_handler_get_iwstats(struct net_device * dev,
+/* noinline to avoid a bogus warning with -O3 */
+static noinline int iw_handler_get_iwstats(struct net_device * dev,
struct iw_request_info * info,
union iwreq_data * wrqu,
char * extra)
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 2efe44a..d5b09bb 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -766,6 +766,10 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr,
if (sk->sk_state == TCP_ESTABLISHED)
goto out;
+ rc = -EALREADY; /* Do nothing if call is already in progress */
+ if (sk->sk_state == TCP_SYN_SENT)
+ goto out;
+
sk->sk_state = TCP_CLOSE;
sock->state = SS_UNCONNECTED;
@@ -812,7 +816,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr,
/* Now the loop */
rc = -EINPROGRESS;
if (sk->sk_state != TCP_ESTABLISHED && (flags & O_NONBLOCK))
- goto out_put_neigh;
+ goto out;
rc = x25_wait_for_connection_establishment(sk);
if (rc)
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 3049af2..f93e917 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -249,7 +249,7 @@ static void xdp_umem_release(struct xdp_umem *umem)
xdp_umem_unmap_pages(umem);
xdp_umem_unpin_pages(umem);
- kfree(umem->pages);
+ kvfree(umem->pages);
umem->pages = NULL;
xdp_umem_unaccount_pages(umem);
@@ -409,7 +409,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
if (err)
goto out_account;
- umem->pages = kcalloc(umem->npgs, sizeof(*umem->pages), GFP_KERNEL);
+ umem->pages = kvcalloc(umem->npgs, sizeof(*umem->pages),
+ GFP_KERNEL_ACCOUNT);
if (!umem->pages) {
err = -ENOMEM;
goto out_pin;
@@ -419,7 +420,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
if (!err)
return 0;
- kfree(umem->pages);
+ kvfree(umem->pages);
out_pin:
xdp_umem_unpin_pages(umem);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 02ada7a..df60048 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -217,7 +217,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
static void xsk_flush(struct xdp_sock *xs)
{
xskq_prod_submit(xs->rx);
- xs->sk.sk_data_ready(&xs->sk);
+ sock_def_readable(&xs->sk);
}
int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index fbc4552d..212a4fc 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -11,3 +11,4 @@
obj-$(CONFIG_XFRM_USER) += xfrm_user.o
obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
+obj-$(CONFIG_INET_ESPINTCP) += espintcp.o
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
new file mode 100644
index 0000000..f15d6a5
--- /dev/null
+++ b/net/xfrm/espintcp.c
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <net/tcp.h>
+#include <net/strparser.h>
+#include <net/xfrm.h>
+#include <net/esp.h>
+#include <net/espintcp.h>
+#include <linux/skmsg.h>
+#include <net/inet_common.h>
+
+static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb,
+ struct sock *sk)
+{
+ if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf ||
+ !sk_rmem_schedule(sk, skb, skb->truesize)) {
+ kfree_skb(skb);
+ return;
+ }
+
+ skb_set_owner_r(skb, sk);
+
+ memset(skb->cb, 0, sizeof(skb->cb));
+ skb_queue_tail(&ctx->ike_queue, skb);
+ ctx->saved_data_ready(sk);
+}
+
+static void handle_esp(struct sk_buff *skb, struct sock *sk)
+{
+ skb_reset_transport_header(skb);
+ memset(skb->cb, 0, sizeof(skb->cb));
+
+ rcu_read_lock();
+ skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
+ local_bh_disable();
+ xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, TCP_ENCAP_ESPINTCP);
+ local_bh_enable();
+ rcu_read_unlock();
+}
+
+static void espintcp_rcv(struct strparser *strp, struct sk_buff *skb)
+{
+ struct espintcp_ctx *ctx = container_of(strp, struct espintcp_ctx,
+ strp);
+ struct strp_msg *rxm = strp_msg(skb);
+ u32 nonesp_marker;
+ int err;
+
+ err = skb_copy_bits(skb, rxm->offset + 2, &nonesp_marker,
+ sizeof(nonesp_marker));
+ if (err < 0) {
+ kfree_skb(skb);
+ return;
+ }
+
+ /* remove header, leave non-ESP marker/SPI */
+ if (!__pskb_pull(skb, rxm->offset + 2)) {
+ kfree_skb(skb);
+ return;
+ }
+
+ if (pskb_trim(skb, rxm->full_len - 2) != 0) {
+ kfree_skb(skb);
+ return;
+ }
+
+ if (nonesp_marker == 0)
+ handle_nonesp(ctx, skb, strp->sk);
+ else
+ handle_esp(skb, strp->sk);
+}
+
+static int espintcp_parse(struct strparser *strp, struct sk_buff *skb)
+{
+ struct strp_msg *rxm = strp_msg(skb);
+ __be16 blen;
+ u16 len;
+ int err;
+
+ if (skb->len < rxm->offset + 2)
+ return 0;
+
+ err = skb_copy_bits(skb, rxm->offset, &blen, sizeof(blen));
+ if (err < 0)
+ return err;
+
+ len = be16_to_cpu(blen);
+ if (len < 6)
+ return -EINVAL;
+
+ return len;
+}
+
+static int espintcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+ int nonblock, int flags, int *addr_len)
+{
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+ struct sk_buff *skb;
+ int err = 0;
+ int copied;
+ int off = 0;
+
+ flags |= nonblock ? MSG_DONTWAIT : 0;
+
+ skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, NULL, &off, &err);
+ if (!skb)
+ return err;
+
+ copied = len;
+ if (copied > skb->len)
+ copied = skb->len;
+ else if (copied < skb->len)
+ msg->msg_flags |= MSG_TRUNC;
+
+ err = skb_copy_datagram_msg(skb, 0, msg, copied);
+ if (unlikely(err)) {
+ kfree_skb(skb);
+ return err;
+ }
+
+ if (flags & MSG_TRUNC)
+ copied = skb->len;
+ kfree_skb(skb);
+ return copied;
+}
+
+int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
+{
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+ if (skb_queue_len(&ctx->out_queue) >= netdev_max_backlog)
+ return -ENOBUFS;
+
+ __skb_queue_tail(&ctx->out_queue, skb);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(espintcp_queue_out);
+
+/* espintcp length field is 2B and length includes the length field's size */
+#define MAX_ESPINTCP_MSG (((1 << 16) - 1) - 2)
+
+static int espintcp_sendskb_locked(struct sock *sk, struct espintcp_msg *emsg,
+ int flags)
+{
+ do {
+ int ret;
+
+ ret = skb_send_sock_locked(sk, emsg->skb,
+ emsg->offset, emsg->len);
+ if (ret < 0)
+ return ret;
+
+ emsg->len -= ret;
+ emsg->offset += ret;
+ } while (emsg->len > 0);
+
+ kfree_skb(emsg->skb);
+ memset(emsg, 0, sizeof(*emsg));
+
+ return 0;
+}
+
+static int espintcp_sendskmsg_locked(struct sock *sk,
+ struct espintcp_msg *emsg, int flags)
+{
+ struct sk_msg *skmsg = &emsg->skmsg;
+ struct scatterlist *sg;
+ int done = 0;
+ int ret;
+
+ flags |= MSG_SENDPAGE_NOTLAST;
+ sg = &skmsg->sg.data[skmsg->sg.start];
+ do {
+ size_t size = sg->length - emsg->offset;
+ int offset = sg->offset + emsg->offset;
+ struct page *p;
+
+ emsg->offset = 0;
+
+ if (sg_is_last(sg))
+ flags &= ~MSG_SENDPAGE_NOTLAST;
+
+ p = sg_page(sg);
+retry:
+ ret = do_tcp_sendpages(sk, p, offset, size, flags);
+ if (ret < 0) {
+ emsg->offset = offset - sg->offset;
+ skmsg->sg.start += done;
+ return ret;
+ }
+
+ if (ret != size) {
+ offset += ret;
+ size -= ret;
+ goto retry;
+ }
+
+ done++;
+ put_page(p);
+ sk_mem_uncharge(sk, sg->length);
+ sg = sg_next(sg);
+ } while (sg);
+
+ memset(emsg, 0, sizeof(*emsg));
+
+ return 0;
+}
+
+static int espintcp_push_msgs(struct sock *sk)
+{
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+ struct espintcp_msg *emsg = &ctx->partial;
+ int err;
+
+ if (!emsg->len)
+ return 0;
+
+ if (ctx->tx_running)
+ return -EAGAIN;
+ ctx->tx_running = 1;
+
+ if (emsg->skb)
+ err = espintcp_sendskb_locked(sk, emsg, 0);
+ else
+ err = espintcp_sendskmsg_locked(sk, emsg, 0);
+ if (err == -EAGAIN) {
+ ctx->tx_running = 0;
+ return 0;
+ }
+ if (!err)
+ memset(emsg, 0, sizeof(*emsg));
+
+ ctx->tx_running = 0;
+
+ return err;
+}
+
+int espintcp_push_skb(struct sock *sk, struct sk_buff *skb)
+{
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+ struct espintcp_msg *emsg = &ctx->partial;
+ unsigned int len;
+ int offset;
+
+ if (sk->sk_state != TCP_ESTABLISHED) {
+ kfree_skb(skb);
+ return -ECONNRESET;
+ }
+
+ offset = skb_transport_offset(skb);
+ len = skb->len - offset;
+
+ espintcp_push_msgs(sk);
+
+ if (emsg->len) {
+ kfree_skb(skb);
+ return -ENOBUFS;
+ }
+
+ skb_set_owner_w(skb, sk);
+
+ emsg->offset = offset;
+ emsg->len = len;
+ emsg->skb = skb;
+
+ espintcp_push_msgs(sk);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(espintcp_push_skb);
+
+static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+ long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+ struct espintcp_msg *emsg = &ctx->partial;
+ struct iov_iter pfx_iter;
+ struct kvec pfx_iov = {};
+ size_t msglen = size + 2;
+ char buf[2] = {0};
+ int err, end;
+
+ if (msg->msg_flags)
+ return -EOPNOTSUPP;
+
+ if (size > MAX_ESPINTCP_MSG)
+ return -EMSGSIZE;
+
+ if (msg->msg_controllen)
+ return -EOPNOTSUPP;
+
+ lock_sock(sk);
+
+ err = espintcp_push_msgs(sk);
+ if (err < 0) {
+ err = -ENOBUFS;
+ goto unlock;
+ }
+
+ sk_msg_init(&emsg->skmsg);
+ while (1) {
+ /* only -ENOMEM is possible since we don't coalesce */
+ err = sk_msg_alloc(sk, &emsg->skmsg, msglen, 0);
+ if (!err)
+ break;
+
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err)
+ goto fail;
+ }
+
+ *((__be16 *)buf) = cpu_to_be16(msglen);
+ pfx_iov.iov_base = buf;
+ pfx_iov.iov_len = sizeof(buf);
+ iov_iter_kvec(&pfx_iter, WRITE, &pfx_iov, 1, pfx_iov.iov_len);
+
+ err = sk_msg_memcopy_from_iter(sk, &pfx_iter, &emsg->skmsg,
+ pfx_iov.iov_len);
+ if (err < 0)
+ goto fail;
+
+ err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, &emsg->skmsg, size);
+ if (err < 0)
+ goto fail;
+
+ end = emsg->skmsg.sg.end;
+ emsg->len = size;
+ sk_msg_iter_var_prev(end);
+ sg_mark_end(sk_msg_elem(&emsg->skmsg, end));
+
+ tcp_rate_check_app_limited(sk);
+
+ err = espintcp_push_msgs(sk);
+ /* this message could be partially sent, keep it */
+ if (err < 0)
+ goto unlock;
+ release_sock(sk);
+
+ return size;
+
+fail:
+ sk_msg_free(sk, &emsg->skmsg);
+ memset(emsg, 0, sizeof(*emsg));
+unlock:
+ release_sock(sk);
+ return err;
+}
+
+static struct proto espintcp_prot __ro_after_init;
+static struct proto_ops espintcp_ops __ro_after_init;
+
+static void espintcp_data_ready(struct sock *sk)
+{
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+ strp_data_ready(&ctx->strp);
+}
+
+static void espintcp_tx_work(struct work_struct *work)
+{
+ struct espintcp_ctx *ctx = container_of(work,
+ struct espintcp_ctx, work);
+ struct sock *sk = ctx->strp.sk;
+
+ lock_sock(sk);
+ if (!ctx->tx_running)
+ espintcp_push_msgs(sk);
+ release_sock(sk);
+}
+
+static void espintcp_write_space(struct sock *sk)
+{
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+ schedule_work(&ctx->work);
+ ctx->saved_write_space(sk);
+}
+
+static void espintcp_destruct(struct sock *sk)
+{
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+ kfree(ctx);
+}
+
+bool tcp_is_ulp_esp(struct sock *sk)
+{
+ return sk->sk_prot == &espintcp_prot;
+}
+EXPORT_SYMBOL_GPL(tcp_is_ulp_esp);
+
+static int espintcp_init_sk(struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ struct strp_callbacks cb = {
+ .rcv_msg = espintcp_rcv,
+ .parse_msg = espintcp_parse,
+ };
+ struct espintcp_ctx *ctx;
+ int err;
+
+ /* sockmap is not compatible with espintcp */
+ if (sk->sk_user_data)
+ return -EBUSY;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ err = strp_init(&ctx->strp, sk, &cb);
+ if (err)
+ goto free;
+
+ __sk_dst_reset(sk);
+
+ strp_check_rcv(&ctx->strp);
+ skb_queue_head_init(&ctx->ike_queue);
+ skb_queue_head_init(&ctx->out_queue);
+ sk->sk_prot = &espintcp_prot;
+ sk->sk_socket->ops = &espintcp_ops;
+ ctx->saved_data_ready = sk->sk_data_ready;
+ ctx->saved_write_space = sk->sk_write_space;
+ sk->sk_data_ready = espintcp_data_ready;
+ sk->sk_write_space = espintcp_write_space;
+ sk->sk_destruct = espintcp_destruct;
+ rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
+ INIT_WORK(&ctx->work, espintcp_tx_work);
+
+ /* avoid using task_frag */
+ sk->sk_allocation = GFP_ATOMIC;
+
+ return 0;
+
+free:
+ kfree(ctx);
+ return err;
+}
+
+static void espintcp_release(struct sock *sk)
+{
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+ struct sk_buff_head queue;
+ struct sk_buff *skb;
+
+ __skb_queue_head_init(&queue);
+ skb_queue_splice_init(&ctx->out_queue, &queue);
+
+ while ((skb = __skb_dequeue(&queue)))
+ espintcp_push_skb(sk, skb);
+
+ tcp_release_cb(sk);
+}
+
+static void espintcp_close(struct sock *sk, long timeout)
+{
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+ struct espintcp_msg *emsg = &ctx->partial;
+
+ strp_stop(&ctx->strp);
+
+ sk->sk_prot = &tcp_prot;
+ barrier();
+
+ cancel_work_sync(&ctx->work);
+ strp_done(&ctx->strp);
+
+ skb_queue_purge(&ctx->out_queue);
+ skb_queue_purge(&ctx->ike_queue);
+
+ if (emsg->len) {
+ if (emsg->skb)
+ kfree_skb(emsg->skb);
+ else
+ sk_msg_free(sk, &emsg->skmsg);
+ }
+
+ tcp_close(sk, timeout);
+}
+
+static __poll_t espintcp_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
+{
+ __poll_t mask = datagram_poll(file, sock, wait);
+ struct sock *sk = sock->sk;
+ struct espintcp_ctx *ctx = espintcp_getctx(sk);
+
+ if (!skb_queue_empty(&ctx->ike_queue))
+ mask |= EPOLLIN | EPOLLRDNORM;
+
+ return mask;
+}
+
+static struct tcp_ulp_ops espintcp_ulp __read_mostly = {
+ .name = "espintcp",
+ .owner = THIS_MODULE,
+ .init = espintcp_init_sk,
+};
+
+void __init espintcp_init(void)
+{
+ memcpy(&espintcp_prot, &tcp_prot, sizeof(tcp_prot));
+ memcpy(&espintcp_ops, &inet_stream_ops, sizeof(inet_stream_ops));
+ espintcp_prot.sendmsg = espintcp_sendmsg;
+ espintcp_prot.recvmsg = espintcp_recvmsg;
+ espintcp_prot.close = espintcp_close;
+ espintcp_prot.release_cb = espintcp_release;
+ espintcp_ops.poll = espintcp_poll;
+
+ tcp_register_ulp(&espintcp_ulp);
+}
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 189ef15..50f567a 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -78,7 +78,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
int err;
unsigned long flags;
struct xfrm_state *x;
- struct sk_buff *skb2;
+ struct sk_buff *skb2, *nskb;
struct softnet_data *sd;
netdev_features_t esp_features = features;
struct xfrm_offload *xo = xfrm_offload(skb);
@@ -148,11 +148,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
return skb;
}
- skb2 = skb;
-
- do {
- struct sk_buff *nskb = skb2->next;
-
+ skb_list_walk_safe(skb, skb2, nskb) {
esp_features |= skb->dev->gso_partial_features;
skb_mark_not_on_list(skb2);
@@ -176,14 +172,11 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
if (!skb)
return NULL;
- goto skip_push;
+ continue;
}
skb_push(skb2, skb2->data - skb_mac_header(skb2));
-
-skip_push:
- skb2 = nskb;
- } while (skb2);
+ }
return skb;
}
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 2c86a2f..aa35f23 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -36,6 +36,7 @@ struct xfrm_trans_cb {
#endif
} header;
int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb);
+ struct net *net;
};
#define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0]))
@@ -766,12 +767,13 @@ static void xfrm_trans_reinject(unsigned long data)
skb_queue_splice_init(&trans->queue, &queue);
while ((skb = __skb_dequeue(&queue)))
- XFRM_TRANS_SKB_CB(skb)->finish(dev_net(skb->dev), NULL, skb);
+ XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net,
+ NULL, skb);
}
-int xfrm_trans_queue(struct sk_buff *skb,
- int (*finish)(struct net *, struct sock *,
- struct sk_buff *))
+int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
+ int (*finish)(struct net *, struct sock *,
+ struct sk_buff *))
{
struct xfrm_trans_tasklet *trans;
@@ -780,11 +782,22 @@ int xfrm_trans_queue(struct sk_buff *skb,
if (skb_queue_len(&trans->queue) >= netdev_max_backlog)
return -ENOBUFS;
+ BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));
+
XFRM_TRANS_SKB_CB(skb)->finish = finish;
+ XFRM_TRANS_SKB_CB(skb)->net = net;
__skb_queue_tail(&trans->queue, skb);
tasklet_schedule(&trans->tasklet);
return 0;
}
+EXPORT_SYMBOL(xfrm_trans_queue_net);
+
+int xfrm_trans_queue(struct sk_buff *skb,
+ int (*finish)(struct net *, struct sock *,
+ struct sk_buff *))
+{
+ return xfrm_trans_queue_net(dev_net(skb->dev), skb, finish);
+}
EXPORT_SYMBOL(xfrm_trans_queue);
void __init xfrm_input_init(void)
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 7ac1542..dc651a6 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -268,9 +268,6 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
int err = -1;
int mtu;
- if (!dst)
- goto tx_err_link_failure;
-
dst_hold(dst);
dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id);
if (IS_ERR(dst)) {
@@ -297,7 +294,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
mtu = dst_mtu(dst);
if (!skb->ignore_df && skb->len > mtu) {
- skb_dst_update_pmtu(skb, mtu);
+ skb_dst_update_pmtu_no_confirm(skb, mtu);
if (skb->protocol == htons(ETH_P_IPV6)) {
if (mtu < IPV6_MIN_MTU)
@@ -343,6 +340,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct xfrm_if *xi = netdev_priv(dev);
struct net_device_stats *stats = &xi->dev->stats;
+ struct dst_entry *dst = skb_dst(skb);
struct flowi fl;
int ret;
@@ -352,10 +350,33 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
case htons(ETH_P_IPV6):
xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ if (!dst) {
+ fl.u.ip6.flowi6_oif = dev->ifindex;
+ fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
+ dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6);
+ if (dst->error) {
+ dst_release(dst);
+ stats->tx_carrier_errors++;
+ goto tx_err;
+ }
+ skb_dst_set(skb, dst);
+ }
break;
case htons(ETH_P_IP):
xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ if (!dst) {
+ struct rtable *rt;
+
+ fl.u.ip4.flowi4_oif = dev->ifindex;
+ fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+ rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4);
+ if (IS_ERR(rt)) {
+ stats->tx_carrier_errors++;
+ goto tx_err;
+ }
+ skb_dst_set(skb, &rt->dst);
+ }
break;
default:
goto tx_err;
@@ -563,12 +584,9 @@ static void xfrmi_dev_setup(struct net_device *dev)
{
dev->netdev_ops = &xfrmi_netdev_ops;
dev->type = ARPHRD_NONE;
- dev->hard_header_len = ETH_HLEN;
- dev->min_header_len = ETH_HLEN;
dev->mtu = ETH_DATA_LEN;
dev->min_mtu = ETH_MIN_MTU;
- dev->max_mtu = ETH_DATA_LEN;
- dev->addr_len = ETH_ALEN;
+ dev->max_mtu = IP_MAX_MTU;
dev->flags = IFF_NOARP;
dev->needs_free_netdev = true;
dev->priv_destructor = xfrmi_dev_free;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index b1db55b..fafc7ab 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -533,7 +533,7 @@ static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct sk_buff *segs;
+ struct sk_buff *segs, *nskb;
BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET);
@@ -544,8 +544,7 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb
if (segs == NULL)
return -EINVAL;
- do {
- struct sk_buff *nskb = segs->next;
+ skb_list_walk_safe(segs, segs, nskb) {
int err;
skb_mark_not_on_list(segs);
@@ -555,9 +554,7 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb
kfree_skb_list(nskb);
return err;
}
-
- segs = nskb;
- } while (segs);
+ }
return 0;
}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f2d1e57..297d1eb 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -39,6 +39,9 @@
#ifdef CONFIG_XFRM_STATISTICS
#include <net/snmp.h>
#endif
+#ifdef CONFIG_INET_ESPINTCP
+#include <net/espintcp.h>
+#endif
#include "xfrm_hash.h"
@@ -4157,6 +4160,10 @@ void __init xfrm_init(void)
seqcount_init(&xfrm_policy_hash_generation);
xfrm_input_init();
+#ifdef CONFIG_INET_ESPINTCP
+ espintcp_init();
+#endif
+
RCU_INIT_POINTER(xfrm_if_cb, NULL);
synchronize_rcu();
}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index f342356..170d6e7 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -670,6 +670,9 @@ int __xfrm_state_delete(struct xfrm_state *x)
net->xfrm.state_num--;
spin_unlock(&net->xfrm.xfrm_state_lock);
+ if (x->encap_sk)
+ sock_put(rcu_dereference_raw(x->encap_sk));
+
xfrm_dev_state_delete(x);
/* All xfrm_state objects are created by xfrm_state_alloc.
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 5b89c03..b0e8adf7 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -184,7 +184,6 @@
TPROGS_CFLAGS += -Wstrict-prototypes
TPROGS_CFLAGS += -I$(objtree)/usr/include
-TPROGS_CFLAGS += -I$(srctree)/tools/lib/bpf/
TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
TPROGS_CFLAGS += -I$(srctree)/tools/lib/
TPROGS_CFLAGS += -I$(srctree)/tools/include
@@ -254,7 +253,7 @@
clean:
$(MAKE) -C ../../ M=$(CURDIR) clean
- @rm -f *~
+ @find $(CURDIR) -type f -name '*~' -delete
$(LIBBPF): FORCE
# Fix up variables inherited from Kbuild that tools/ build system won't like
@@ -305,7 +304,7 @@
@echo " CLANG-bpf " $@
$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \
-I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \
- -I$(srctree)/tools/lib/bpf/ \
+ -I$(srctree)/tools/lib/ \
-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
-D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c
index 68c84da..a86a19d 100644
--- a/samples/bpf/cpustat_kern.c
+++ b/samples/bpf/cpustat_kern.c
@@ -3,7 +3,7 @@
#include <linux/version.h>
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/*
* The CPU number, cstate number and pstate number are based
diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c
index 2d4b717..d5992f7 100644
--- a/samples/bpf/fds_example.c
+++ b/samples/bpf/fds_example.c
@@ -14,7 +14,7 @@
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "bpf_insn.h"
#include "sock_example.h"
diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c
index 829b68d..7d71537 100644
--- a/samples/bpf/hbm.c
+++ b/samples/bpf/hbm.c
@@ -50,8 +50,8 @@
#include "cgroup_helpers.h"
#include "hbm.h"
#include "bpf_util.h"
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
bool outFlag = true;
int minRate = 1000; /* cgroup rate limit in Mbps */
diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h
index 4edaf47..e00f26f 100644
--- a/samples/bpf/hbm_kern.h
+++ b/samples/bpf/hbm_kern.h
@@ -22,8 +22,8 @@
#include <uapi/linux/pkt_cls.h>
#include <net/ipv6.h>
#include <net/inet_ecn.h>
-#include "bpf_endian.h"
-#include "bpf_helpers.h"
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
#include "hbm.h"
#define DROP_PKT 0
diff --git a/samples/bpf/ibumad_kern.c b/samples/bpf/ibumad_kern.c
index f281df7..3a91b4c 100644
--- a/samples/bpf/ibumad_kern.c
+++ b/samples/bpf/ibumad_kern.c
@@ -13,7 +13,7 @@
#define KBUILD_MODNAME "ibumad_count_pkts_by_class"
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") read_count = {
diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c
index cb5a8f9..fa06eef 100644
--- a/samples/bpf/ibumad_user.c
+++ b/samples/bpf/ibumad_user.c
@@ -25,7 +25,7 @@
#include "bpf_load.h"
#include "bpf_util.h"
-#include "libbpf.h"
+#include <bpf/libbpf.h>
static void dump_counts(int fd)
{
diff --git a/samples/bpf/lathist_kern.c b/samples/bpf/lathist_kern.c
index 18fa088..ca9c2e4 100644
--- a/samples/bpf/lathist_kern.c
+++ b/samples/bpf/lathist_kern.c
@@ -8,7 +8,7 @@
#include <linux/version.h>
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define MAX_ENTRIES 20
#define MAX_CPU 4
diff --git a/samples/bpf/lwt_len_hist_kern.c b/samples/bpf/lwt_len_hist_kern.c
index df75383..9ed63e1 100644
--- a/samples/bpf/lwt_len_hist_kern.c
+++ b/samples/bpf/lwt_len_hist_kern.c
@@ -14,7 +14,7 @@
#include <uapi/linux/if_ether.h>
#include <uapi/linux/ip.h>
#include <uapi/linux/in.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
# define printk(fmt, ...) \
({ \
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 281bcda..12e91ae 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -8,9 +8,9 @@
#include <linux/netdevice.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_tracing.h>
#define MAX_ENTRIES 1000
#define MAX_NR_CPUS 1024
diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c
index 9cb5207..c4ec10d 100644
--- a/samples/bpf/offwaketime_kern.c
+++ b/samples/bpf/offwaketime_kern.c
@@ -5,8 +5,8 @@
* License as published by the Free Software Foundation.
*/
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
#include <uapi/linux/ptrace.h>
#include <uapi/linux/perf_event.h>
#include <linux/version.h>
diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c
index fc8767d..51c7da5 100644
--- a/samples/bpf/offwaketime_user.c
+++ b/samples/bpf/offwaketime_user.c
@@ -12,7 +12,7 @@
#include <assert.h>
#include <stdbool.h>
#include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "trace_helpers.h"
diff --git a/samples/bpf/parse_ldabs.c b/samples/bpf/parse_ldabs.c
index ef58923..c6f65f9 100644
--- a/samples/bpf/parse_ldabs.c
+++ b/samples/bpf/parse_ldabs.c
@@ -11,7 +11,7 @@
#include <linux/tcp.h>
#include <linux/udp.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
#define DEFAULT_PKTGEN_UDP_PORT 9
diff --git a/samples/bpf/parse_simple.c b/samples/bpf/parse_simple.c
index 10af53d..4a486cb 100644
--- a/samples/bpf/parse_simple.c
+++ b/samples/bpf/parse_simple.c
@@ -12,7 +12,7 @@
#include <linux/udp.h>
#include <uapi/linux/bpf.h>
#include <net/ip.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define DEFAULT_PKTGEN_UDP_PORT 9
diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c
index 0b6f22f..d862384 100644
--- a/samples/bpf/parse_varlen.c
+++ b/samples/bpf/parse_varlen.c
@@ -14,7 +14,7 @@
#include <linux/udp.h>
#include <uapi/linux/bpf.h>
#include <net/ip.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define DEFAULT_PKTGEN_UDP_PORT 9
#define DEBUG 0
diff --git a/samples/bpf/sampleip_kern.c b/samples/bpf/sampleip_kern.c
index 4a19089..e504dc3 100644
--- a/samples/bpf/sampleip_kern.c
+++ b/samples/bpf/sampleip_kern.c
@@ -8,8 +8,8 @@
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/bpf_perf_event.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
#define MAX_IPS 8192
diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c
index 6b5dc26..b0f115f 100644
--- a/samples/bpf/sampleip_user.c
+++ b/samples/bpf/sampleip_user.c
@@ -15,7 +15,7 @@
#include <linux/ptrace.h>
#include <linux/bpf.h>
#include <sys/ioctl.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "perf-sys.h"
#include "trace_helpers.h"
diff --git a/samples/bpf/sock_flags_kern.c b/samples/bpf/sock_flags_kern.c
index 05dcdf8..6d0ac75 100644
--- a/samples/bpf/sock_flags_kern.c
+++ b/samples/bpf/sock_flags_kern.c
@@ -3,7 +3,7 @@
#include <linux/net.h>
#include <uapi/linux/in.h>
#include <uapi/linux/in6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("cgroup/sock1")
int bpf_prog1(struct bpf_sock *sk)
diff --git a/samples/bpf/sockex1_kern.c b/samples/bpf/sockex1_kern.c
index 2408dbf..431c956 100644
--- a/samples/bpf/sockex1_kern.c
+++ b/samples/bpf/sockex1_kern.c
@@ -2,7 +2,7 @@
#include <uapi/linux/if_ether.h>
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
struct {
diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c
index a219442..3c83722 100644
--- a/samples/bpf/sockex1_user.c
+++ b/samples/bpf/sockex1_user.c
@@ -3,7 +3,7 @@
#include <assert.h>
#include <linux/bpf.h>
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "sock_example.h"
#include <unistd.h>
#include <arpa/inet.h>
diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c
index a7bcd03..a41dd52 100644
--- a/samples/bpf/sockex2_kern.c
+++ b/samples/bpf/sockex2_kern.c
@@ -1,5 +1,5 @@
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
#include <uapi/linux/in.h>
#include <uapi/linux/if.h>
diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c
index 6de383d..af925a5 100644
--- a/samples/bpf/sockex2_user.c
+++ b/samples/bpf/sockex2_user.c
@@ -3,7 +3,7 @@
#include <assert.h>
#include <linux/bpf.h>
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "sock_example.h"
#include <unistd.h>
#include <arpa/inet.h>
diff --git a/samples/bpf/sockex3_kern.c b/samples/bpf/sockex3_kern.c
index 151dd84..36d4dac 100644
--- a/samples/bpf/sockex3_kern.c
+++ b/samples/bpf/sockex3_kern.c
@@ -5,7 +5,7 @@
* License as published by the Free Software Foundation.
*/
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
#include <uapi/linux/in.h>
#include <uapi/linux/if.h>
diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c
index 6e9478a..f508af3 100644
--- a/samples/bpf/spintest_kern.c
+++ b/samples/bpf/spintest_kern.c
@@ -9,8 +9,8 @@
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/perf_event.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c
index 2556af2..fb430ea 100644
--- a/samples/bpf/spintest_user.c
+++ b/samples/bpf/spintest_user.c
@@ -5,7 +5,7 @@
#include <string.h>
#include <assert.h>
#include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "trace_helpers.h"
diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c
index 630ce8c..5a62b03 100644
--- a/samples/bpf/syscall_tp_kern.c
+++ b/samples/bpf/syscall_tp_kern.c
@@ -2,7 +2,7 @@
/* Copyright (c) 2017 Facebook
*/
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct syscalls_enter_open_args {
unsigned long long unused;
diff --git a/samples/bpf/task_fd_query_kern.c b/samples/bpf/task_fd_query_kern.c
index fb56fc2..278ade5 100644
--- a/samples/bpf/task_fd_query_kern.c
+++ b/samples/bpf/task_fd_query_kern.c
@@ -2,7 +2,7 @@
#include <linux/version.h>
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("kprobe/blk_mq_start_request")
int bpf_prog1(struct pt_regs *ctx)
diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c
index 4c31b30..ff2e9c1 100644
--- a/samples/bpf/task_fd_query_user.c
+++ b/samples/bpf/task_fd_query_user.c
@@ -15,7 +15,7 @@
#include <sys/stat.h>
#include <linux/perf_event.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "bpf_util.h"
#include "perf-sys.h"
diff --git a/samples/bpf/tc_l2_redirect_kern.c b/samples/bpf/tc_l2_redirect_kern.c
index 7ef2a12..fd2fa00 100644
--- a/samples/bpf/tc_l2_redirect_kern.c
+++ b/samples/bpf/tc_l2_redirect_kern.c
@@ -15,7 +15,7 @@
#include <uapi/linux/filter.h>
#include <uapi/linux/pkt_cls.h>
#include <net/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define _htonl __builtin_bswap32
diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c
index ff43341..e935613 100644
--- a/samples/bpf/tcbpf1_kern.c
+++ b/samples/bpf/tcbpf1_kern.c
@@ -7,7 +7,7 @@
#include <uapi/linux/tcp.h>
#include <uapi/linux/filter.h>
#include <uapi/linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
/* compiler workaround */
diff --git a/samples/bpf/tcp_basertt_kern.c b/samples/bpf/tcp_basertt_kern.c
index 9dba48c..8dfe09a 100644
--- a/samples/bpf/tcp_basertt_kern.c
+++ b/samples/bpf/tcp_basertt_kern.c
@@ -16,8 +16,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define DEBUG 1
diff --git a/samples/bpf/tcp_bufs_kern.c b/samples/bpf/tcp_bufs_kern.c
index af8486f..6a80d08 100644
--- a/samples/bpf/tcp_bufs_kern.c
+++ b/samples/bpf/tcp_bufs_kern.c
@@ -17,8 +17,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define DEBUG 1
diff --git a/samples/bpf/tcp_clamp_kern.c b/samples/bpf/tcp_clamp_kern.c
index 26c0fd0..e88bd9a 100644
--- a/samples/bpf/tcp_clamp_kern.c
+++ b/samples/bpf/tcp_clamp_kern.c
@@ -17,8 +17,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define DEBUG 1
diff --git a/samples/bpf/tcp_cong_kern.c b/samples/bpf/tcp_cong_kern.c
index 6d4dc4c..2311fc9 100644
--- a/samples/bpf/tcp_cong_kern.c
+++ b/samples/bpf/tcp_cong_kern.c
@@ -16,8 +16,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define DEBUG 1
diff --git a/samples/bpf/tcp_dumpstats_kern.c b/samples/bpf/tcp_dumpstats_kern.c
index 8557913..e80d3af 100644
--- a/samples/bpf/tcp_dumpstats_kern.c
+++ b/samples/bpf/tcp_dumpstats_kern.c
@@ -4,8 +4,8 @@
*/
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define INTERVAL 1000000000ULL
diff --git a/samples/bpf/tcp_iw_kern.c b/samples/bpf/tcp_iw_kern.c
index da61d53..d144455 100644
--- a/samples/bpf/tcp_iw_kern.c
+++ b/samples/bpf/tcp_iw_kern.c
@@ -17,8 +17,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define DEBUG 1
diff --git a/samples/bpf/tcp_rwnd_kern.c b/samples/bpf/tcp_rwnd_kern.c
index d011e38..223d9c2 100644
--- a/samples/bpf/tcp_rwnd_kern.c
+++ b/samples/bpf/tcp_rwnd_kern.c
@@ -16,8 +16,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define DEBUG 1
diff --git a/samples/bpf/tcp_synrto_kern.c b/samples/bpf/tcp_synrto_kern.c
index 720d195..d58004e 100644
--- a/samples/bpf/tcp_synrto_kern.c
+++ b/samples/bpf/tcp_synrto_kern.c
@@ -16,8 +16,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define DEBUG 1
diff --git a/samples/bpf/tcp_tos_reflect_kern.c b/samples/bpf/tcp_tos_reflect_kern.c
index 369faca..953fedc 100644
--- a/samples/bpf/tcp_tos_reflect_kern.c
+++ b/samples/bpf/tcp_tos_reflect_kern.c
@@ -15,8 +15,8 @@
#include <uapi/linux/ipv6.h>
#include <uapi/linux/in.h>
#include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define DEBUG 1
diff --git a/samples/bpf/test_cgrp2_tc_kern.c b/samples/bpf/test_cgrp2_tc_kern.c
index 1547b36..4dd532a 100644
--- a/samples/bpf/test_cgrp2_tc_kern.c
+++ b/samples/bpf/test_cgrp2_tc_kern.c
@@ -10,7 +10,7 @@
#include <uapi/linux/ipv6.h>
#include <uapi/linux/pkt_cls.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* copy of 'struct ethhdr' without __packed */
struct eth_hdr {
diff --git a/samples/bpf/test_current_task_under_cgroup_kern.c b/samples/bpf/test_current_task_under_cgroup_kern.c
index 86b28d7..6dc4f41 100644
--- a/samples/bpf/test_current_task_under_cgroup_kern.c
+++ b/samples/bpf/test_current_task_under_cgroup_kern.c
@@ -8,7 +8,7 @@
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include <uapi/linux/utsname.h>
struct bpf_map_def SEC("maps") cgroup_map = {
diff --git a/samples/bpf/test_lwt_bpf.c b/samples/bpf/test_lwt_bpf.c
index bacc801..1b56857 100644
--- a/samples/bpf/test_lwt_bpf.c
+++ b/samples/bpf/test_lwt_bpf.c
@@ -20,7 +20,7 @@
#include <linux/udp.h>
#include <linux/icmpv6.h>
#include <linux/if_ether.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include <string.h>
# define printk(fmt, ...) \
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
index 32ee752..6cee61e 100644
--- a/samples/bpf/test_map_in_map_kern.c
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -10,9 +10,9 @@
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/in6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_tracing.h>
#define MAX_NR_PORTS 65536
diff --git a/samples/bpf/test_overhead_kprobe_kern.c b/samples/bpf/test_overhead_kprobe_kern.c
index 8d2518e..8b811c2 100644
--- a/samples/bpf/test_overhead_kprobe_kern.c
+++ b/samples/bpf/test_overhead_kprobe_kern.c
@@ -7,8 +7,8 @@
#include <linux/version.h>
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})
diff --git a/samples/bpf/test_overhead_raw_tp_kern.c b/samples/bpf/test_overhead_raw_tp_kern.c
index d2af8bc..8763181 100644
--- a/samples/bpf/test_overhead_raw_tp_kern.c
+++ b/samples/bpf/test_overhead_raw_tp_kern.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2018 Facebook */
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("raw_tracepoint/task_rename")
int prog(struct bpf_raw_tracepoint_args *ctx)
diff --git a/samples/bpf/test_overhead_tp_kern.c b/samples/bpf/test_overhead_tp_kern.c
index 38f5c0b..eaa3269 100644
--- a/samples/bpf/test_overhead_tp_kern.c
+++ b/samples/bpf/test_overhead_tp_kern.c
@@ -5,7 +5,7 @@
* License as published by the Free Software Foundation.
*/
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* from /sys/kernel/debug/tracing/events/task/task_rename/format */
struct task_rename {
diff --git a/samples/bpf/test_probe_write_user_kern.c b/samples/bpf/test_probe_write_user_kern.c
index b7c48f3..f033f36 100644
--- a/samples/bpf/test_probe_write_user_kern.c
+++ b/samples/bpf/test_probe_write_user_kern.c
@@ -8,8 +8,8 @@
#include <linux/netdevice.h>
#include <uapi/linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
struct bpf_map_def SEC("maps") dnat_map = {
.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c
index 8dc18d23..da1d69e 100644
--- a/samples/bpf/trace_event_kern.c
+++ b/samples/bpf/trace_event_kern.c
@@ -9,8 +9,8 @@
#include <uapi/linux/bpf.h>
#include <uapi/linux/bpf_perf_event.h>
#include <uapi/linux/perf_event.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
struct key_t {
char comm[TASK_COMM_LEN];
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index 749a50f..356171b 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -15,7 +15,7 @@
#include <assert.h>
#include <errno.h>
#include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "perf-sys.h"
#include "trace_helpers.h"
diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c
index 9b96f4f..1d7d422 100644
--- a/samples/bpf/trace_output_kern.c
+++ b/samples/bpf/trace_output_kern.c
@@ -1,7 +1,7 @@
#include <linux/ptrace.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c
index 8ee4769..60a17dd 100644
--- a/samples/bpf/trace_output_user.c
+++ b/samples/bpf/trace_output_user.c
@@ -15,7 +15,7 @@
#include <sys/mman.h>
#include <time.h>
#include <signal.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "perf-sys.h"
diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c
index 1a15f66..8e2610e 100644
--- a/samples/bpf/tracex1_kern.c
+++ b/samples/bpf/tracex1_kern.c
@@ -8,8 +8,8 @@
#include <linux/netdevice.h>
#include <uapi/linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})
diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c
index d70b3ea..d865bb3 100644
--- a/samples/bpf/tracex2_kern.c
+++ b/samples/bpf/tracex2_kern.c
@@ -8,8 +8,8 @@
#include <linux/netdevice.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c
index 9af546b..fe21c14f 100644
--- a/samples/bpf/tracex3_kern.c
+++ b/samples/bpf/tracex3_kern.c
@@ -8,8 +8,8 @@
#include <linux/netdevice.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4_kern.c
index 2a02cbe..b1bb9df 100644
--- a/samples/bpf/tracex4_kern.c
+++ b/samples/bpf/tracex4_kern.c
@@ -7,8 +7,8 @@
#include <linux/ptrace.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
struct pair {
u64 val;
diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c
index b3557b2..481790f 100644
--- a/samples/bpf/tracex5_kern.c
+++ b/samples/bpf/tracex5_kern.c
@@ -10,8 +10,8 @@
#include <uapi/linux/seccomp.h>
#include <uapi/linux/unistd.h>
#include "syscall_nrs.h"
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
#define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F
diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c
index 46c557a..96c234e 100644
--- a/samples/bpf/tracex6_kern.c
+++ b/samples/bpf/tracex6_kern.c
@@ -1,7 +1,7 @@
#include <linux/ptrace.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") counters = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7_kern.c
index 1ab308a..c5a92df 100644
--- a/samples/bpf/tracex7_kern.c
+++ b/samples/bpf/tracex7_kern.c
@@ -1,7 +1,7 @@
#include <uapi/linux/ptrace.h>
#include <uapi/linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("kprobe/open_ctree")
int bpf_prog1(struct pt_regs *ctx)
diff --git a/samples/bpf/xdp1_kern.c b/samples/bpf/xdp1_kern.c
index db6870a..34b6439 100644
--- a/samples/bpf/xdp1_kern.c
+++ b/samples/bpf/xdp1_kern.c
@@ -12,7 +12,7 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index 38a8852..c447ad9 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -15,8 +15,8 @@
#include <net/if.h>
#include "bpf_util.h"
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
static int ifindex;
static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c
index c74b52c..c787f4b 100644
--- a/samples/bpf/xdp2_kern.c
+++ b/samples/bpf/xdp2_kern.c
@@ -12,7 +12,7 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
diff --git a/samples/bpf/xdp2skb_meta_kern.c b/samples/bpf/xdp2skb_meta_kern.c
index 0c12048..9b78331 100644
--- a/samples/bpf/xdp2skb_meta_kern.c
+++ b/samples/bpf/xdp2skb_meta_kern.c
@@ -12,7 +12,7 @@
#include <uapi/linux/bpf.h>
#include <uapi/linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/*
* This struct is stored in the XDP 'data_meta' area, which is located
diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c
index 0f707e0..ffdd548 100644
--- a/samples/bpf/xdp_adjust_tail_kern.c
+++ b/samples/bpf/xdp_adjust_tail_kern.c
@@ -18,7 +18,7 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/icmp.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define DEFAULT_TTL 64
#define MAX_PCKT_SIZE 600
diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c
index 008789e..ba482dc 100644
--- a/samples/bpf/xdp_adjust_tail_user.c
+++ b/samples/bpf/xdp_adjust_tail_user.c
@@ -19,8 +19,8 @@
#include <netinet/ether.h>
#include <unistd.h>
#include <time.h>
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#define STATS_INTERVAL_S 2U
#define MAX_PCKT_SIZE 600
diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c
index d013029..54c099c 100644
--- a/samples/bpf/xdp_fwd_kern.c
+++ b/samples/bpf/xdp_fwd_kern.c
@@ -19,7 +19,7 @@
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF)
diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c
index c30f9ac..74a4583 100644
--- a/samples/bpf/xdp_fwd_user.c
+++ b/samples/bpf/xdp_fwd_user.c
@@ -24,7 +24,7 @@
#include <fcntl.h>
#include <libgen.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include <bpf/bpf.h>
static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c
index ad10fe7..3d33cca 100644
--- a/samples/bpf/xdp_monitor_kern.c
+++ b/samples/bpf/xdp_monitor_kern.c
@@ -4,7 +4,7 @@
* XDP monitor tool, based on tracepoints
*/
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") redirect_err_cnt = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
@@ -222,14 +222,12 @@ struct bpf_map_def SEC("maps") devmap_xmit_cnt = {
*/
struct devmap_xmit_ctx {
u64 __pad; // First 8 bytes are not accessible by bpf code
- int map_id; // offset:8; size:4; signed:1;
+ int from_ifindex; // offset:8; size:4; signed:1;
u32 act; // offset:12; size:4; signed:0;
- u32 map_index; // offset:16; size:4; signed:0;
+ int to_ifindex; // offset:16; size:4; signed:1;
int drops; // offset:20; size:4; signed:1;
int sent; // offset:24; size:4; signed:1;
- int from_ifindex; // offset:28; size:4; signed:1;
- int to_ifindex; // offset:32; size:4; signed:1;
- int err; // offset:36; size:4; signed:1;
+ int err; // offset:28; size:4; signed:1;
};
SEC("tracepoint/xdp/xdp_devmap_xmit")
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
index cfcc31e..313a8fe 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -12,7 +12,7 @@
#include <uapi/linux/udp.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "hash_func01.h"
#define MAX_CPUS 64 /* WARNING - sync with _user.c */
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 79a2fb7..15bdf04 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -30,7 +30,7 @@ static const char *__doc__ =
#define MAX_PROG 6
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "bpf_util.h"
diff --git a/samples/bpf/xdp_redirect_kern.c b/samples/bpf/xdp_redirect_kern.c
index 1f0b7d0..d26ec3a 100644
--- a/samples/bpf/xdp_redirect_kern.c
+++ b/samples/bpf/xdp_redirect_kern.c
@@ -17,7 +17,7 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
diff --git a/samples/bpf/xdp_redirect_map_kern.c b/samples/bpf/xdp_redirect_map_kern.c
index 4631b48..6489352 100644
--- a/samples/bpf/xdp_redirect_map_kern.c
+++ b/samples/bpf/xdp_redirect_map_kern.c
@@ -17,7 +17,7 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_DEVMAP);
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
index cc84066..35e16de 100644
--- a/samples/bpf/xdp_redirect_map_user.c
+++ b/samples/bpf/xdp_redirect_map_user.c
@@ -17,7 +17,7 @@
#include "bpf_util.h"
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
static int ifindex_in;
static int ifindex_out;
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index 71dff8e..9ca2bf4 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/samples/bpf/xdp_redirect_user.c
@@ -17,7 +17,7 @@
#include "bpf_util.h"
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
static int ifindex_in;
static int ifindex_out;
diff --git a/samples/bpf/xdp_router_ipv4_kern.c b/samples/bpf/xdp_router_ipv4_kern.c
index bf11efc..b37ca2b 100644
--- a/samples/bpf/xdp_router_ipv4_kern.c
+++ b/samples/bpf/xdp_router_ipv4_kern.c
@@ -12,7 +12,7 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include <linux/slab.h>
#include <net/ip_fib.h>
diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c
index fef286c..c2da1b5 100644
--- a/samples/bpf/xdp_router_ipv4_user.c
+++ b/samples/bpf/xdp_router_ipv4_user.c
@@ -21,7 +21,7 @@
#include <sys/ioctl.h>
#include <sys/syscall.h>
#include "bpf_util.h"
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include <sys/resource.h>
#include <libgen.h>
diff --git a/samples/bpf/xdp_rxq_info_kern.c b/samples/bpf/xdp_rxq_info_kern.c
index 272d0f8..5e7459f 100644
--- a/samples/bpf/xdp_rxq_info_kern.c
+++ b/samples/bpf/xdp_rxq_info_kern.c
@@ -6,7 +6,7 @@
#include <uapi/linux/bpf.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/in.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* Config setup from with userspace
*
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index fc4983f..4fe4750 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -22,8 +22,8 @@ static const char *__doc__ = " XDP RX-queue info extract example\n\n"
#include <arpa/inet.h>
#include <linux/if_link.h>
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#include "bpf_util.h"
static int ifindex = -1;
diff --git a/samples/bpf/xdp_sample_pkts_kern.c b/samples/bpf/xdp_sample_pkts_kern.c
index 6c7c7e0..3337728 100644
--- a/samples/bpf/xdp_sample_pkts_kern.c
+++ b/samples/bpf/xdp_sample_pkts_kern.c
@@ -2,7 +2,7 @@
#include <linux/ptrace.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define SAMPLE_SIZE 64ul
#define MAX_CPUS 128
diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c
index 8c1af1b..991ef6f 100644
--- a/samples/bpf/xdp_sample_pkts_user.c
+++ b/samples/bpf/xdp_sample_pkts_user.c
@@ -10,7 +10,7 @@
#include <sys/sysinfo.h>
#include <sys/ioctl.h>
#include <signal.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include <sys/resource.h>
#include <libgen.h>
diff --git a/samples/bpf/xdp_tx_iptunnel_kern.c b/samples/bpf/xdp_tx_iptunnel_kern.c
index 6db450a..575d57e 100644
--- a/samples/bpf/xdp_tx_iptunnel_kern.c
+++ b/samples/bpf/xdp_tx_iptunnel_kern.c
@@ -16,7 +16,7 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "xdp_tx_iptunnel_common.h"
struct {
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 5f33b55..a419bee 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -15,7 +15,7 @@
#include <netinet/ether.h>
#include <unistd.h>
#include <time.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include "bpf_util.h"
#include "xdp_tx_iptunnel_common.h"
diff --git a/samples/bpf/xdpsock_kern.c b/samples/bpf/xdpsock_kern.c
index a06177c..0543048 100644
--- a/samples/bpf/xdpsock_kern.c
+++ b/samples/bpf/xdpsock_kern.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "xdpsock.h"
/* This XDP program is only needed for the XDP_SHARED_UMEM mode.
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index d74c4c8..0b5acd7 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -30,10 +30,10 @@
#include <time.h>
#include <unistd.h>
-#include "libbpf.h"
-#include "xsk.h"
-#include "xdpsock.h"
+#include <bpf/libbpf.h>
+#include <bpf/xsk.h>
#include <bpf/bpf.h>
+#include "xdpsock.h"
#ifndef SOL_XDP
#define SOL_XDP 283
diff --git a/samples/seccomp/user-trap.c b/samples/seccomp/user-trap.c
index 6d0125c..20291ec6 100644
--- a/samples/seccomp/user-trap.c
+++ b/samples/seccomp/user-trap.c
@@ -298,14 +298,14 @@ int main(void)
req = malloc(sizes.seccomp_notif);
if (!req)
goto out_close;
- memset(req, 0, sizeof(*req));
resp = malloc(sizes.seccomp_notif_resp);
if (!resp)
goto out_req;
- memset(resp, 0, sizeof(*resp));
+ memset(resp, 0, sizes.seccomp_notif_resp);
while (1) {
+ memset(req, 0, sizes.seccomp_notif);
if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, req)) {
perror("ioctl recv");
goto out_resp;
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 7548569..90baf7d 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -158,8 +158,6 @@
break
self.reader.close()
- print('Parsed description of %d helper function(s)' % len(self.helpers),
- file=sys.stderr)
###############################################################################
diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig
index d33de0b..e356954 100644
--- a/scripts/gcc-plugins/Kconfig
+++ b/scripts/gcc-plugins/Kconfig
@@ -14,8 +14,8 @@
An arch should select this symbol if it supports building with
GCC plugins.
-config GCC_PLUGINS
- bool
+menuconfig GCC_PLUGINS
+ bool "GCC plugins"
depends on HAVE_GCC_PLUGINS
depends on PLUGIN_HOSTCC != ""
default y
@@ -25,8 +25,7 @@
See Documentation/core-api/gcc-plugins.rst for details.
-menu "GCC plugins"
- depends on GCC_PLUGINS
+if GCC_PLUGINS
config GCC_PLUGIN_CYC_COMPLEXITY
bool "Compute the cyclomatic complexity of a function" if EXPERT
@@ -113,4 +112,4 @@
bool
depends on GCC_PLUGINS && ARM
-endmenu
+endif
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 4363799..408b5c0 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -108,13 +108,13 @@
local bin_arch
if ! [ -x "$(command -v ${PAHOLE})" ]; then
- info "BTF" "${1}: pahole (${PAHOLE}) is not available"
+ echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available"
return 1
fi
pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/')
if [ "${pahole_ver}" -lt "113" ]; then
- info "BTF" "${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13"
+ echo >&2 "BTF: ${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13"
return 1
fi
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 7c23001..357dc56 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -136,7 +136,7 @@
echo "1.0" > debian/source/format
echo $debarch > debian/arch
-extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev)"
+extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev:native)"
extra_build_depends="$extra_build_depends, $(if_enabled_echo CONFIG_SYSTEM_TRUSTED_KEYRING libssl-dev:native)"
# Generate a simple changelog template
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 612268e..7225107a 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -38,6 +38,10 @@
#define R_AARCH64_ABS64 257
#endif
+#define R_ARM_PC24 1
+#define R_ARM_THM_CALL 10
+#define R_ARM_CALL 28
+
static int fd_map; /* File descriptor for file being modified. */
static int mmap_failed; /* Boolean flag. */
static char gpfx; /* prefix for global symbol name (sometimes '_') */
@@ -418,6 +422,18 @@ static char const *already_has_rel_mcount = "success"; /* our work here is done!
#define RECORD_MCOUNT_64
#include "recordmcount.h"
+static int arm_is_fake_mcount(Elf32_Rel const *rp)
+{
+ switch (ELF32_R_TYPE(w(rp->r_info))) {
+ case R_ARM_THM_CALL:
+ case R_ARM_CALL:
+ case R_ARM_PC24:
+ return 0;
+ }
+
+ return 1;
+}
+
/* 64-bit EM_MIPS has weird ELF64_Rela.r_info.
* http://techpubs.sgi.com/library/manuals/4000/007-4658-001/pdf/007-4658-001.pdf
* We interpret Table 29 Relocation Operation (Elf64_Rel, Elf64_Rela) [p.40]
@@ -523,6 +539,7 @@ static int do_file(char const *const fname)
altmcount = "__gnu_mcount_nc";
make_nop = make_nop_arm;
rel_type_nop = R_ARM_NONE;
+ is_fake_mcount32 = arm_is_fake_mcount;
gpfx = 0;
break;
case EM_AARCH64:
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 09996f2..47aff87 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -623,7 +623,7 @@ static __poll_t ns_revision_poll(struct file *file, poll_table *pt)
void __aa_bump_ns_revision(struct aa_ns *ns)
{
- ns->revision++;
+ WRITE_ONCE(ns->revision, ns->revision + 1);
wake_up_interruptible(&ns->wait);
}
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 9be7ccb..6ceb74e 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -317,6 +317,7 @@ static int aa_xattrs_match(const struct linux_binprm *bprm,
if (!bprm || !profile->xattr_count)
return 0;
+ might_sleep();
/* transition from exec match to xattr set */
state = aa_dfa_null_transition(profile->xmatch, state);
@@ -361,10 +362,11 @@ static int aa_xattrs_match(const struct linux_binprm *bprm,
}
/**
- * __attach_match_ - find an attachment match
+ * find_attach - do attachment search for unconfined processes
* @bprm - binprm structure of transitioning task
- * @name - to match against (NOT NULL)
+ * @ns: the current namespace (NOT NULL)
* @head - profile list to walk (NOT NULL)
+ * @name - to match against (NOT NULL)
* @info - info message if there was an error (NOT NULL)
*
* Do a linear search on the profiles in the list. There is a matching
@@ -374,12 +376,11 @@ static int aa_xattrs_match(const struct linux_binprm *bprm,
*
* Requires: @head not be shared or have appropriate locks held
*
- * Returns: profile or NULL if no match found
+ * Returns: label or NULL if no match found
*/
-static struct aa_profile *__attach_match(const struct linux_binprm *bprm,
- const char *name,
- struct list_head *head,
- const char **info)
+static struct aa_label *find_attach(const struct linux_binprm *bprm,
+ struct aa_ns *ns, struct list_head *head,
+ const char *name, const char **info)
{
int candidate_len = 0, candidate_xattrs = 0;
bool conflict = false;
@@ -388,6 +389,8 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm,
AA_BUG(!name);
AA_BUG(!head);
+ rcu_read_lock();
+restart:
list_for_each_entry_rcu(profile, head, base.list) {
if (profile->label.flags & FLAG_NULL &&
&profile->label == ns_unconfined(profile->ns))
@@ -413,16 +416,32 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm,
perm = dfa_user_allow(profile->xmatch, state);
/* any accepting state means a valid match. */
if (perm & MAY_EXEC) {
- int ret;
+ int ret = 0;
if (count < candidate_len)
continue;
- ret = aa_xattrs_match(bprm, profile, state);
- /* Fail matching if the xattrs don't match */
- if (ret < 0)
- continue;
+ if (bprm && profile->xattr_count) {
+ long rev = READ_ONCE(ns->revision);
+ if (!aa_get_profile_not0(profile))
+ goto restart;
+ rcu_read_unlock();
+ ret = aa_xattrs_match(bprm, profile,
+ state);
+ rcu_read_lock();
+ aa_put_profile(profile);
+ if (rev !=
+ READ_ONCE(ns->revision))
+ /* policy changed */
+ goto restart;
+ /*
+ * Fail matching if the xattrs don't
+ * match
+ */
+ if (ret < 0)
+ continue;
+ }
/*
* TODO: allow for more flexible best match
*
@@ -445,43 +464,28 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm,
candidate_xattrs = ret;
conflict = false;
}
- } else if (!strcmp(profile->base.name, name))
+ } else if (!strcmp(profile->base.name, name)) {
/*
* old exact non-re match, without conditionals such
* as xattrs. no more searching required
*/
- return profile;
+ candidate = profile;
+ goto out;
+ }
}
- if (conflict) {
- *info = "conflicting profile attachments";
+ if (!candidate || conflict) {
+ if (conflict)
+ *info = "conflicting profile attachments";
+ rcu_read_unlock();
return NULL;
}
- return candidate;
-}
-
-/**
- * find_attach - do attachment search for unconfined processes
- * @bprm - binprm structure of transitioning task
- * @ns: the current namespace (NOT NULL)
- * @list: list to search (NOT NULL)
- * @name: the executable name to match against (NOT NULL)
- * @info: info message if there was an error
- *
- * Returns: label or NULL if no match found
- */
-static struct aa_label *find_attach(const struct linux_binprm *bprm,
- struct aa_ns *ns, struct list_head *list,
- const char *name, const char **info)
-{
- struct aa_profile *profile;
-
- rcu_read_lock();
- profile = aa_get_profile(__attach_match(bprm, name, list, info));
+out:
+ candidate = aa_get_newest_profile(candidate);
rcu_read_unlock();
- return profile ? &profile->label : NULL;
+ return &candidate->label;
}
static const char *next_name(int xtype, const char *name)
diff --git a/security/apparmor/file.c b/security/apparmor/file.c
index fe2ebe5..f1caf36 100644
--- a/security/apparmor/file.c
+++ b/security/apparmor/file.c
@@ -618,8 +618,7 @@ int aa_file_perm(const char *op, struct aa_label *label, struct file *file,
fctx = file_ctx(file);
rcu_read_lock();
- flabel = aa_get_newest_label(rcu_dereference(fctx->label));
- rcu_read_unlock();
+ flabel = rcu_dereference(fctx->label);
AA_BUG(!flabel);
/* revalidate access, if task is unconfined, or the cached cred
@@ -631,9 +630,13 @@ int aa_file_perm(const char *op, struct aa_label *label, struct file *file,
*/
denied = request & ~fctx->allow;
if (unconfined(label) || unconfined(flabel) ||
- (!denied && aa_label_is_subset(flabel, label)))
+ (!denied && aa_label_is_subset(flabel, label))) {
+ rcu_read_unlock();
goto done;
+ }
+ flabel = aa_get_newest_label(flabel);
+ rcu_read_unlock();
/* TODO: label cross check */
if (file->f_path.mnt && path_mediated_fs(file->f_path.dentry))
@@ -643,8 +646,9 @@ int aa_file_perm(const char *op, struct aa_label *label, struct file *file,
else if (S_ISSOCK(file_inode(file)->i_mode))
error = __file_sock_perm(op, label, flabel, file, request,
denied);
-done:
aa_put_label(flabel);
+
+done:
return error;
}
diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c
index 4ed6688..e0828ee 100644
--- a/security/apparmor/mount.c
+++ b/security/apparmor/mount.c
@@ -442,7 +442,7 @@ int aa_bind_mount(struct aa_label *label, const struct path *path,
buffer = aa_get_buffer(false);
old_buffer = aa_get_buffer(false);
error = -ENOMEM;
- if (!buffer || old_buffer)
+ if (!buffer || !old_buffer)
goto out;
error = fn_for_each_confined(label, profile,
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 0310483..269f2f5 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -1125,8 +1125,8 @@ ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj,
if (!name) {
/* remove namespace - can only happen if fqname[0] == ':' */
mutex_lock_nested(&ns->parent->lock, ns->level);
- __aa_remove_ns(ns);
__aa_bump_ns_revision(ns);
+ __aa_remove_ns(ns);
mutex_unlock(&ns->parent->lock);
} else {
/* remove profile */
@@ -1138,9 +1138,9 @@ ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj,
goto fail_ns_lock;
}
name = profile->base.hname;
+ __aa_bump_ns_revision(ns);
__remove_profile(profile);
__aa_labelset_update_subtree(ns);
- __aa_bump_ns_revision(ns);
mutex_unlock(&ns->lock);
}
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index c97fdae..b692319 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -85,6 +85,9 @@ static const struct nlmsg_perm nlmsg_route_perms[] =
{ RTM_GETNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_READ },
{ RTM_NEWLINKPROP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
{ RTM_DELLINKPROP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+ { RTM_NEWVLAN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+ { RTM_DELVLAN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+ { RTM_GETVLAN, NETLINK_ROUTE_SOCKET__NLMSG_READ },
};
static const struct nlmsg_perm nlmsg_tcpdiag_perms[] =
@@ -168,7 +171,7 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm)
* structures at the top of this file with the new mappings
* before updating the BUILD_BUG_ON() macro!
*/
- BUILD_BUG_ON(RTM_MAX != (RTM_NEWLINKPROP + 3));
+ BUILD_BUG_ON(RTM_MAX != (RTM_NEWVLAN + 3));
err = nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms,
sizeof(nlmsg_route_perms));
break;
diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c
index 63dc7bd..be59b59 100644
--- a/sound/core/seq/seq_timer.c
+++ b/sound/core/seq/seq_timer.c
@@ -471,15 +471,19 @@ void snd_seq_info_timer_read(struct snd_info_entry *entry,
q = queueptr(idx);
if (q == NULL)
continue;
- if ((tmr = q->timer) == NULL ||
- (ti = tmr->timeri) == NULL) {
- queuefree(q);
- continue;
- }
+ mutex_lock(&q->timer_mutex);
+ tmr = q->timer;
+ if (!tmr)
+ goto unlock;
+ ti = tmr->timeri;
+ if (!ti)
+ goto unlock;
snd_iprintf(buffer, "Timer for queue %i : %s\n", q->queue, ti->timer->name);
resolution = snd_timer_resolution(ti) * tmr->ticks;
snd_iprintf(buffer, " Period time : %lu.%09lu\n", resolution / 1000000000, resolution % 1000000000);
snd_iprintf(buffer, " Skew : %u / %u\n", tmr->skew, tmr->skew_base);
+unlock:
+ mutex_unlock(&q->timer_mutex);
queuefree(q);
}
}
diff --git a/sound/firewire/dice/dice-extension.c b/sound/firewire/dice/dice-extension.c
index a63fcbc..02f4a83 100644
--- a/sound/firewire/dice/dice-extension.c
+++ b/sound/firewire/dice/dice-extension.c
@@ -159,8 +159,11 @@ int snd_dice_detect_extension_formats(struct snd_dice *dice)
int j;
for (j = i + 1; j < 9; ++j) {
- if (pointers[i * 2] == pointers[j * 2])
+ if (pointers[i * 2] == pointers[j * 2]) {
+ // Fallback to limited functionality.
+ err = -ENXIO;
goto end;
+ }
}
}
diff --git a/sound/firewire/tascam/amdtp-tascam.c b/sound/firewire/tascam/amdtp-tascam.c
index e80bb84..f823a2ab 100644
--- a/sound/firewire/tascam/amdtp-tascam.c
+++ b/sound/firewire/tascam/amdtp-tascam.c
@@ -157,14 +157,15 @@ static void read_status_messages(struct amdtp_stream *s,
if ((before ^ after) & mask) {
struct snd_firewire_tascam_change *entry =
&tscm->queue[tscm->push_pos];
+ unsigned long flag;
- spin_lock_irq(&tscm->lock);
+ spin_lock_irqsave(&tscm->lock, flag);
entry->index = index;
entry->before = before;
entry->after = after;
if (++tscm->push_pos >= SND_TSCM_QUEUE_COUNT)
tscm->push_pos = 0;
- spin_unlock_irq(&tscm->lock);
+ spin_unlock_irqrestore(&tscm->lock, flag);
wake_up(&tscm->hwdep_wait);
}
diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c
index 906b1e2..286361e 100644
--- a/sound/hda/hdac_regmap.c
+++ b/sound/hda/hdac_regmap.c
@@ -363,7 +363,6 @@ static const struct regmap_config hda_regmap_cfg = {
.reg_write = hda_reg_write,
.use_single_read = true,
.use_single_write = true,
- .disable_locking = true,
};
/**
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index b856b89..8ef223a 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -125,7 +125,7 @@ static char *patch[SNDRV_CARDS];
static bool beep_mode[SNDRV_CARDS] = {[0 ... (SNDRV_CARDS-1)] =
CONFIG_SND_HDA_INPUT_BEEP_MODE};
#endif
-static bool dsp_driver = 1;
+static bool dmic_detect = 1;
module_param_array(index, int, NULL, 0444);
MODULE_PARM_DESC(index, "Index value for Intel HD audio interface.");
@@ -160,9 +160,10 @@ module_param_array(beep_mode, bool, NULL, 0444);
MODULE_PARM_DESC(beep_mode, "Select HDA Beep registration mode "
"(0=off, 1=on) (default=1).");
#endif
-module_param(dsp_driver, bool, 0444);
-MODULE_PARM_DESC(dsp_driver, "Allow DSP driver selection (bypass this driver) "
- "(0=off, 1=on) (default=1)");
+module_param(dmic_detect, bool, 0444);
+MODULE_PARM_DESC(dmic_detect, "Allow DSP driver selection (bypass this driver) "
+ "(0=off, 1=on) (default=1); "
+ "deprecated, use snd-intel-dspcfg.dsp_driver option instead");
#ifdef CONFIG_PM
static int param_set_xint(const char *val, const struct kernel_param *kp);
@@ -282,12 +283,13 @@ enum {
/* quirks for old Intel chipsets */
#define AZX_DCAPS_INTEL_ICH \
- (AZX_DCAPS_OLD_SSYNC | AZX_DCAPS_NO_ALIGN_BUFSIZE)
+ (AZX_DCAPS_OLD_SSYNC | AZX_DCAPS_NO_ALIGN_BUFSIZE |\
+ AZX_DCAPS_SYNC_WRITE)
/* quirks for Intel PCH */
#define AZX_DCAPS_INTEL_PCH_BASE \
(AZX_DCAPS_NO_ALIGN_BUFSIZE | AZX_DCAPS_COUNT_LPIB_DELAY |\
- AZX_DCAPS_SNOOP_TYPE(SCH))
+ AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE)
/* PCH up to IVB; no runtime PM; bind with i915 gfx */
#define AZX_DCAPS_INTEL_PCH_NOPM \
@@ -302,13 +304,13 @@ enum {
#define AZX_DCAPS_INTEL_HASWELL \
(/*AZX_DCAPS_ALIGN_BUFSIZE |*/ AZX_DCAPS_COUNT_LPIB_DELAY |\
AZX_DCAPS_PM_RUNTIME | AZX_DCAPS_I915_COMPONENT |\
- AZX_DCAPS_SNOOP_TYPE(SCH))
+ AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE)
/* Broadwell HDMI can't use position buffer reliably, force to use LPIB */
#define AZX_DCAPS_INTEL_BROADWELL \
(/*AZX_DCAPS_ALIGN_BUFSIZE |*/ AZX_DCAPS_POSFIX_LPIB |\
AZX_DCAPS_PM_RUNTIME | AZX_DCAPS_I915_COMPONENT |\
- AZX_DCAPS_SNOOP_TYPE(SCH))
+ AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE)
#define AZX_DCAPS_INTEL_BAYTRAIL \
(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_I915_COMPONENT)
@@ -1410,7 +1412,17 @@ static bool atpx_present(void)
acpi_handle dhandle, atpx_handle;
acpi_status status;
- while ((pdev = pci_get_class(PCI_BASE_CLASS_DISPLAY << 16, pdev)) != NULL) {
+ while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
+ dhandle = ACPI_HANDLE(&pdev->dev);
+ if (dhandle) {
+ status = acpi_get_handle(dhandle, "ATPX", &atpx_handle);
+ if (!ACPI_FAILURE(status)) {
+ pci_dev_put(pdev);
+ return true;
+ }
+ }
+ }
+ while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
dhandle = ACPI_HANDLE(&pdev->dev);
if (dhandle) {
status = acpi_get_handle(dhandle, "ATPX", &atpx_handle);
@@ -2088,11 +2100,13 @@ static int azx_probe(struct pci_dev *pci,
/*
* stop probe if another Intel's DSP driver should be activated
*/
- if (dsp_driver) {
+ if (dmic_detect) {
err = snd_intel_dsp_driver_probe(pci);
if (err != SND_INTEL_DSP_DRIVER_ANY &&
err != SND_INTEL_DSP_DRIVER_LEGACY)
return -ENODEV;
+ } else {
+ dev_warn(&pci->dev, "dmic_detect option is deprecated, pass snd-intel-dspcfg.dsp_driver=1 option instead\n");
}
err = snd_card_new(&pci->dev, index[dev], id[dev], THIS_MODULE,
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index dbfafee..f2ea352 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -412,6 +412,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
case 0x10ec0672:
alc_update_coef_idx(codec, 0xd, 0, 1<<14); /* EAPD Ctrl */
break;
+ case 0x10ec0222:
case 0x10ec0623:
alc_update_coef_idx(codec, 0x19, 1<<13, 0);
break;
@@ -430,6 +431,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
break;
case 0x10ec0899:
case 0x10ec0900:
+ case 0x10ec0b00:
case 0x10ec1168:
case 0x10ec1220:
alc_update_coef_idx(codec, 0x7, 1<<1, 0);
@@ -501,6 +503,7 @@ static void alc_shutup_pins(struct hda_codec *codec)
struct alc_spec *spec = codec->spec;
switch (codec->core.vendor_id) {
+ case 0x10ec0283:
case 0x10ec0286:
case 0x10ec0288:
case 0x10ec0298:
@@ -2525,6 +2528,7 @@ static int patch_alc882(struct hda_codec *codec)
case 0x10ec0882:
case 0x10ec0885:
case 0x10ec0900:
+ case 0x10ec0b00:
case 0x10ec1220:
break;
default:
@@ -5904,9 +5908,12 @@ enum {
ALC256_FIXUP_ASUS_HEADSET_MIC,
ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
ALC299_FIXUP_PREDATOR_SPK,
- ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC,
ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE,
- ALC294_FIXUP_ASUS_INTSPK_GPIO,
+ ALC289_FIXUP_DELL_SPK2,
+ ALC289_FIXUP_DUAL_SPK,
+ ALC294_FIXUP_SPK2_TO_DAC1,
+ ALC294_FIXUP_ASUS_DUAL_SPK,
+
};
static const struct hda_fixup alc269_fixups[] = {
@@ -6981,16 +6988,6 @@ static const struct hda_fixup alc269_fixups[] = {
{ }
}
},
- [ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC] = {
- .type = HDA_FIXUP_PINS,
- .v.pins = (const struct hda_pintbl[]) {
- { 0x14, 0x411111f0 }, /* disable confusing internal speaker */
- { 0x19, 0x04a11150 }, /* use as headset mic, without its own jack detect */
- { }
- },
- .chained = true,
- .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
- },
[ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
@@ -7001,13 +6998,35 @@ static const struct hda_fixup alc269_fixups[] = {
.chained = true,
.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
},
- [ALC294_FIXUP_ASUS_INTSPK_GPIO] = {
+ [ALC289_FIXUP_DELL_SPK2] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x17, 0x90170130 }, /* bass spk */
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE
+ },
+ [ALC289_FIXUP_DUAL_SPK] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_speaker2_to_dac1,
+ .chained = true,
+ .chain_id = ALC289_FIXUP_DELL_SPK2
+ },
+ [ALC294_FIXUP_SPK2_TO_DAC1] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_speaker2_to_dac1,
+ .chained = true,
+ .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC
+ },
+ [ALC294_FIXUP_ASUS_DUAL_SPK] = {
.type = HDA_FIXUP_FUNC,
/* The GPIO must be pulled to initialize the AMP */
.v.func = alc_fixup_gpio4,
.chained = true,
- .chain_id = ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC
+ .chain_id = ALC294_FIXUP_SPK2_TO_DAC1
},
+
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -7080,6 +7099,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),
+ SND_PCI_QUIRK(0x1028, 0x097e, "Dell Precision", ALC289_FIXUP_DUAL_SPK),
+ SND_PCI_QUIRK(0x1028, 0x097d, "Dell Precision", ALC289_FIXUP_DUAL_SPK),
SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -7167,7 +7188,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
- SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_INTSPK_GPIO),
+ SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK),
SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
@@ -7239,6 +7260,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+ SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Yoga 7th", ALC285_FIXUP_SPEAKER2_TO_DAC1),
SND_PCI_QUIRK(0x17aa, 0x2293, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_SPEAKER2_TO_DAC1),
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
@@ -9237,6 +9259,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
HDA_CODEC_ENTRY(0x10ec0892, "ALC892", patch_alc662),
HDA_CODEC_ENTRY(0x10ec0899, "ALC898", patch_alc882),
HDA_CODEC_ENTRY(0x10ec0900, "ALC1150", patch_alc882),
+ HDA_CODEC_ENTRY(0x10ec0b00, "ALCS1200A", patch_alc882),
HDA_CODEC_ENTRY(0x10ec1168, "ALC1220", patch_alc882),
HDA_CODEC_ENTRY(0x10ec1220, "ALC1220", patch_alc882),
{} /* terminator */
diff --git a/sound/pci/ice1712/ice1724.c b/sound/pci/ice1712/ice1724.c
index c80a16e..242542e 100644
--- a/sound/pci/ice1712/ice1724.c
+++ b/sound/pci/ice1712/ice1724.c
@@ -647,6 +647,7 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate,
unsigned long flags;
unsigned char mclk_change;
unsigned int i, old_rate;
+ bool call_set_rate = false;
if (rate > ice->hw_rates->list[ice->hw_rates->count - 1])
return -EINVAL;
@@ -670,7 +671,7 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate,
* setting clock rate for internal clock mode */
old_rate = ice->get_rate(ice);
if (force || (old_rate != rate))
- ice->set_rate(ice, rate);
+ call_set_rate = true;
else if (rate == ice->cur_rate) {
spin_unlock_irqrestore(&ice->reg_lock, flags);
return 0;
@@ -678,12 +679,14 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate,
}
ice->cur_rate = rate;
+ spin_unlock_irqrestore(&ice->reg_lock, flags);
+
+ if (call_set_rate)
+ ice->set_rate(ice, rate);
/* setting master clock */
mclk_change = ice->set_mclk(ice, rate);
- spin_unlock_irqrestore(&ice->reg_lock, flags);
-
if (mclk_change && ice->gpio.i2s_mclk_changed)
ice->gpio.i2s_mclk_changed(ice);
if (ice->gpio.set_pro_rate)
diff --git a/sound/soc/codecs/cros_ec_codec.c b/sound/soc/codecs/cros_ec_codec.c
index 7b17f39..ce3ed05 100644
--- a/sound/soc/codecs/cros_ec_codec.c
+++ b/sound/soc/codecs/cros_ec_codec.c
@@ -10,6 +10,7 @@
#include <crypto/hash.h>
#include <crypto/sha.h>
+#include <linux/acpi.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/io.h>
@@ -1047,10 +1048,17 @@ static const struct of_device_id cros_ec_codec_of_match[] = {
MODULE_DEVICE_TABLE(of, cros_ec_codec_of_match);
#endif
+static const struct acpi_device_id cros_ec_codec_acpi_id[] = {
+ { "GOOG0013", 0 },
+ { }
+};
+MODULE_DEVICE_TABLE(acpi, cros_ec_codec_acpi_id);
+
static struct platform_driver cros_ec_codec_platform_driver = {
.driver = {
.name = "cros-ec-codec",
.of_match_table = of_match_ptr(cros_ec_codec_of_match),
+ .acpi_match_table = ACPI_PTR(cros_ec_codec_acpi_id),
},
.probe = cros_ec_codec_platform_probe,
};
diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c
index 6803d39..4311015 100644
--- a/sound/soc/codecs/hdac_hda.c
+++ b/sound/soc/codecs/hdac_hda.c
@@ -588,7 +588,9 @@ static int hdac_hda_dev_remove(struct hdac_device *hdev)
struct hdac_hda_priv *hda_pvt;
hda_pvt = dev_get_drvdata(&hdev->dev);
- cancel_delayed_work_sync(&hda_pvt->codec.jackpoll_work);
+ if (hda_pvt && hda_pvt->codec.registered)
+ cancel_delayed_work_sync(&hda_pvt->codec.jackpoll_work);
+
return 0;
}
diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index f53235b..1f7964b 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -396,9 +396,6 @@ static int pm8916_wcd_analog_enable_micbias_int(struct snd_soc_component
switch (event) {
case SND_SOC_DAPM_PRE_PMU:
- snd_soc_component_update_bits(component, CDC_A_MICB_1_INT_RBIAS,
- MICB_1_INT_TX2_INT_RBIAS_EN_MASK,
- MICB_1_INT_TX2_INT_RBIAS_EN_ENABLE);
snd_soc_component_update_bits(component, reg, MICB_1_EN_PULL_DOWN_EN_MASK, 0);
snd_soc_component_update_bits(component, CDC_A_MICB_1_EN,
MICB_1_EN_OPA_STG2_TAIL_CURR_MASK,
@@ -448,6 +445,14 @@ static int pm8916_wcd_analog_enable_micbias_int1(struct
struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
struct pm8916_wcd_analog_priv *wcd = snd_soc_component_get_drvdata(component);
+ switch (event) {
+ case SND_SOC_DAPM_PRE_PMU:
+ snd_soc_component_update_bits(component, CDC_A_MICB_1_INT_RBIAS,
+ MICB_1_INT_TX1_INT_RBIAS_EN_MASK,
+ MICB_1_INT_TX1_INT_RBIAS_EN_ENABLE);
+ break;
+ }
+
return pm8916_wcd_analog_enable_micbias_int(component, event, w->reg,
wcd->micbias1_cap_mode);
}
@@ -558,6 +563,11 @@ static int pm8916_wcd_analog_enable_micbias_int2(struct
struct pm8916_wcd_analog_priv *wcd = snd_soc_component_get_drvdata(component);
switch (event) {
+ case SND_SOC_DAPM_PRE_PMU:
+ snd_soc_component_update_bits(component, CDC_A_MICB_1_INT_RBIAS,
+ MICB_1_INT_TX2_INT_RBIAS_EN_MASK,
+ MICB_1_INT_TX2_INT_RBIAS_EN_ENABLE);
+ break;
case SND_SOC_DAPM_POST_PMU:
pm8916_mbhc_configure_bias(wcd, true);
break;
@@ -938,10 +948,10 @@ static const struct snd_soc_dapm_widget pm8916_wcd_analog_dapm_widgets[] = {
SND_SOC_DAPM_SUPPLY("MIC BIAS External1", CDC_A_MICB_1_EN, 7, 0,
pm8916_wcd_analog_enable_micbias_ext1,
- SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+ SND_SOC_DAPM_POST_PMU),
SND_SOC_DAPM_SUPPLY("MIC BIAS External2", CDC_A_MICB_2_EN, 7, 0,
pm8916_wcd_analog_enable_micbias_ext2,
- SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD),
+ SND_SOC_DAPM_POST_PMU),
SND_SOC_DAPM_ADC_E("ADC1", NULL, CDC_A_TX_1_EN, 7, 0,
pm8916_wcd_analog_enable_adc,
diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c
index 58b2468..09fccac 100644
--- a/sound/soc/codecs/msm8916-wcd-digital.c
+++ b/sound/soc/codecs/msm8916-wcd-digital.c
@@ -586,6 +586,12 @@ static int msm8916_wcd_digital_enable_interpolator(
snd_soc_component_write(component, rx_gain_reg[w->shift],
snd_soc_component_read32(component, rx_gain_reg[w->shift]));
break;
+ case SND_SOC_DAPM_POST_PMD:
+ snd_soc_component_update_bits(component, LPASS_CDC_CLK_RX_RESET_CTL,
+ 1 << w->shift, 1 << w->shift);
+ snd_soc_component_update_bits(component, LPASS_CDC_CLK_RX_RESET_CTL,
+ 1 << w->shift, 0x0);
+ break;
}
return 0;
}
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index adbae1f..747ca24 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -2432,6 +2432,13 @@ static void rt5640_disable_jack_detect(struct snd_soc_component *component)
{
struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
+ /*
+ * soc_remove_component() force-disables jack and thus rt5640->jack
+ * could be NULL at the time of driver's module unloading.
+ */
+ if (!rt5640->jack)
+ return;
+
disable_irq(rt5640->irq);
rt5640_cancel_work(rt5640);
diff --git a/sound/soc/fsl/fsl_audmix.c b/sound/soc/fsl/fsl_audmix.c
index a1db1bc..5faecbe 100644
--- a/sound/soc/fsl/fsl_audmix.c
+++ b/sound/soc/fsl/fsl_audmix.c
@@ -505,15 +505,20 @@ static int fsl_audmix_probe(struct platform_device *pdev)
ARRAY_SIZE(fsl_audmix_dai));
if (ret) {
dev_err(dev, "failed to register ASoC DAI\n");
- return ret;
+ goto err_disable_pm;
}
priv->pdev = platform_device_register_data(dev, mdrv, 0, NULL, 0);
if (IS_ERR(priv->pdev)) {
ret = PTR_ERR(priv->pdev);
dev_err(dev, "failed to register platform %s: %d\n", mdrv, ret);
+ goto err_disable_pm;
}
+ return 0;
+
+err_disable_pm:
+ pm_runtime_disable(dev);
return ret;
}
@@ -521,6 +526,8 @@ static int fsl_audmix_remove(struct platform_device *pdev)
{
struct fsl_audmix *priv = dev_get_drvdata(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
+
if (priv->pdev)
platform_device_unregister(priv->pdev);
diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
index 4661233..54e9745 100644
--- a/sound/soc/intel/boards/bytcht_es8316.c
+++ b/sound/soc/intel/boards/bytcht_es8316.c
@@ -442,7 +442,8 @@ static const struct dmi_system_id byt_cht_es8316_quirk_table[] = {
DMI_MATCH(DMI_SYS_VENDOR, "IRBIS"),
DMI_MATCH(DMI_PRODUCT_NAME, "NB41"),
},
- .driver_data = (void *)(BYT_CHT_ES8316_INTMIC_IN2_MAP
+ .driver_data = (void *)(BYT_CHT_ES8316_SSP0
+ | BYT_CHT_ES8316_INTMIC_IN2_MAP
| BYT_CHT_ES8316_JD_INVERTED),
},
{ /* Teclast X98 Plus II */
diff --git a/sound/soc/intel/boards/cml_rt1011_rt5682.c b/sound/soc/intel/boards/cml_rt1011_rt5682.c
index a22f972..5f1bf6d 100644
--- a/sound/soc/intel/boards/cml_rt1011_rt5682.c
+++ b/sound/soc/intel/boards/cml_rt1011_rt5682.c
@@ -11,7 +11,6 @@
#include <linux/clk.h>
#include <linux/dmi.h>
#include <linux/slab.h>
-#include <asm/cpu_device_id.h>
#include <linux/acpi.h>
#include <sound/core.h>
#include <sound/jack.h>
diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c
index 9054558..b94680f 100644
--- a/sound/soc/soc-component.c
+++ b/sound/soc/soc-component.c
@@ -539,6 +539,9 @@ void snd_soc_pcm_component_free(struct snd_soc_pcm_runtime *rtd)
struct snd_soc_rtdcom_list *rtdcom;
struct snd_soc_component *component;
+ if (!rtd->pcm)
+ return;
+
for_each_rtd_components(rtd, rtdcom, component)
if (component->driver->pcm_destruct)
component->driver->pcm_destruct(component, rtd->pcm);
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 1c84ff1..8ef0efe 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -479,6 +479,12 @@ static struct snd_soc_pcm_runtime *soc_new_pcm_runtime(
goto free_rtd;
rtd->dev = dev;
+ INIT_LIST_HEAD(&rtd->list);
+ INIT_LIST_HEAD(&rtd->component_list);
+ INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_PLAYBACK].be_clients);
+ INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_CAPTURE].be_clients);
+ INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_PLAYBACK].fe_clients);
+ INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_CAPTURE].fe_clients);
dev_set_drvdata(dev, rtd);
INIT_DELAYED_WORK(&rtd->delayed_work, close_delayed_work);
@@ -494,12 +500,6 @@ static struct snd_soc_pcm_runtime *soc_new_pcm_runtime(
/*
* rtd remaining settings
*/
- INIT_LIST_HEAD(&rtd->component_list);
- INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_PLAYBACK].be_clients);
- INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_CAPTURE].be_clients);
- INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_PLAYBACK].fe_clients);
- INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_CAPTURE].fe_clients);
-
rtd->card = card;
rtd->dai_link = dai_link;
if (!rtd->dai_link->ops)
@@ -1871,6 +1871,8 @@ static void soc_check_tplg_fes(struct snd_soc_card *card)
/* convert non BE into BE */
dai_link->no_pcm = 1;
+ dai_link->dpcm_playback = 1;
+ dai_link->dpcm_capture = 1;
/* override any BE fixups */
dai_link->be_hw_params_fixup =
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index b286131..92e4f4d 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -548,12 +548,12 @@ static void remove_link(struct snd_soc_component *comp,
if (dobj->ops && dobj->ops->link_unload)
dobj->ops->link_unload(comp, dobj);
+ list_del(&dobj->list);
+ snd_soc_remove_dai_link(comp->card, link);
+
kfree(link->name);
kfree(link->stream_name);
kfree(link->cpus->dai_name);
-
- list_del(&dobj->list);
- snd_soc_remove_dai_link(comp->card, link);
kfree(link);
}
diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c
index cfefcfd..aef6ca1 100644
--- a/sound/soc/sof/imx/imx8.c
+++ b/sound/soc/sof/imx/imx8.c
@@ -209,7 +209,7 @@ static int imx8_probe(struct snd_sof_dev *sdev)
priv->pd_dev = devm_kmalloc_array(&pdev->dev, priv->num_domains,
sizeof(*priv->pd_dev), GFP_KERNEL);
- if (!priv)
+ if (!priv->pd_dev)
return -ENOMEM;
priv->link = devm_kmalloc_array(&pdev->dev, priv->num_domains,
@@ -304,6 +304,9 @@ static int imx8_probe(struct snd_sof_dev *sdev)
}
sdev->mailbox_bar = SOF_FW_BLK_TYPE_SRAM;
+ /* set default mailbox offset for FW ready message */
+ sdev->dsp_box.offset = MBOX_OFFSET;
+
return 0;
exit_pdev_unregister:
diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c
index 827f84a..fbfa225 100644
--- a/sound/soc/sof/intel/hda-codec.c
+++ b/sound/soc/sof/intel/hda-codec.c
@@ -24,19 +24,18 @@
#define IDISP_VID_INTEL 0x80860000
/* load the legacy HDA codec driver */
-#ifdef MODULE
-static void hda_codec_load_module(struct hda_codec *codec)
+static int hda_codec_load_module(struct hda_codec *codec)
{
+#ifdef MODULE
char alias[MODULE_NAME_LEN];
const char *module = alias;
snd_hdac_codec_modalias(&codec->core, alias, sizeof(alias));
dev_dbg(&codec->core.dev, "loading codec module: %s\n", module);
request_module(module);
-}
-#else
-static void hda_codec_load_module(struct hda_codec *codec) {}
#endif
+ return device_attach(hda_codec_dev(codec));
+}
/* enable controller wake up event for all codecs with jack connectors */
void hda_codec_jack_wake_enable(struct snd_sof_dev *sdev)
@@ -129,10 +128,16 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address)
if ((mach_params && mach_params->common_hdmi_codec_drv) ||
(resp & 0xFFFF0000) != IDISP_VID_INTEL) {
hdev->type = HDA_DEV_LEGACY;
- hda_codec_load_module(&hda_priv->codec);
+ ret = hda_codec_load_module(&hda_priv->codec);
+ /*
+ * handle ret==0 (no driver bound) as an error, but pass
+ * other return codes without modification
+ */
+ if (ret == 0)
+ ret = -ENOENT;
}
- return 0;
+ return ret;
#else
hdev = devm_kzalloc(sdev->dev, sizeof(*hdev), GFP_KERNEL);
if (!hdev)
diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c
index 8796f38..896d219 100644
--- a/sound/soc/sof/intel/hda-dai.c
+++ b/sound/soc/sof/intel/hda-dai.c
@@ -216,6 +216,8 @@ static int hda_link_hw_params(struct snd_pcm_substream *substream,
link_dev = hda_link_stream_assign(bus, substream);
if (!link_dev)
return -EBUSY;
+
+ snd_soc_dai_set_dma_data(dai, substream, (void *)link_dev);
}
stream_tag = hdac_stream(link_dev)->stream_tag;
@@ -228,8 +230,6 @@ static int hda_link_hw_params(struct snd_pcm_substream *substream,
if (ret < 0)
return ret;
- snd_soc_dai_set_dma_data(dai, substream, (void *)link_dev);
-
link = snd_hdac_ext_bus_get_link(bus, codec_dai->component->name);
if (!link)
return -EINVAL;
@@ -361,6 +361,13 @@ static int hda_link_hw_free(struct snd_pcm_substream *substream,
bus = hstream->bus;
rtd = snd_pcm_substream_chip(substream);
link_dev = snd_soc_dai_get_dma_data(dai, substream);
+
+ if (!link_dev) {
+ dev_dbg(dai->dev,
+ "%s: link_dev is not assigned\n", __func__);
+ return -EINVAL;
+ }
+
hda_stream = hstream_to_sof_hda_stream(link_dev);
/* free the link DMA channel in the FW */
diff --git a/sound/soc/sof/intel/hda-loader.c b/sound/soc/sof/intel/hda-loader.c
index b178336..bae7ac3 100644
--- a/sound/soc/sof/intel/hda-loader.c
+++ b/sound/soc/sof/intel/hda-loader.c
@@ -329,13 +329,13 @@ int hda_dsp_cl_boot_firmware(struct snd_sof_dev *sdev)
if (!ret)
break;
- dev_err(sdev->dev, "error: Error code=0x%x: FW status=0x%x\n",
+ dev_dbg(sdev->dev, "iteration %d of Core En/ROM load failed: %d\n",
+ i, ret);
+ dev_dbg(sdev->dev, "Error code=0x%x: FW status=0x%x\n",
snd_sof_dsp_read(sdev, HDA_DSP_BAR,
HDA_DSP_SRAM_REG_ROM_ERROR),
snd_sof_dsp_read(sdev, HDA_DSP_BAR,
HDA_DSP_SRAM_REG_ROM_STATUS));
- dev_err(sdev->dev, "error: iteration %d of Core En/ROM load failed: %d\n",
- i, ret);
}
if (i == HDA_FW_BOOT_ATTEMPTS) {
diff --git a/sound/soc/sof/ipc.c b/sound/soc/sof/ipc.c
index 5994e10..5fdfbaa 100644
--- a/sound/soc/sof/ipc.c
+++ b/sound/soc/sof/ipc.c
@@ -826,6 +826,9 @@ void snd_sof_ipc_free(struct snd_sof_dev *sdev)
{
struct snd_sof_ipc *ipc = sdev->ipc;
+ if (!ipc)
+ return;
+
/* disable sending of ipc's */
mutex_lock(&ipc->tx_mutex);
ipc->disable_ipc_tx = true;
diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index 48ea915..2ed92c9 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -226,7 +226,6 @@ static void uni_player_set_channel_status(struct uniperif *player,
* sampling frequency. If no sample rate is already specified, then
* set one.
*/
- mutex_lock(&player->ctrl_lock);
if (runtime) {
switch (runtime->rate) {
case 22050:
@@ -303,7 +302,6 @@ static void uni_player_set_channel_status(struct uniperif *player,
player->stream_settings.iec958.status[3 + (n * 4)] << 24;
SET_UNIPERIF_CHANNEL_STA_REGN(player, n, status);
}
- mutex_unlock(&player->ctrl_lock);
/* Update the channel status */
if (player->ver < SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0)
@@ -365,8 +363,10 @@ static int uni_player_prepare_iec958(struct uniperif *player,
SET_UNIPERIF_CTRL_ZERO_STUFF_HW(player);
+ mutex_lock(&player->ctrl_lock);
/* Update the channel status */
uni_player_set_channel_status(player, runtime);
+ mutex_unlock(&player->ctrl_lock);
/* Clear the user validity user bits */
SET_UNIPERIF_USER_VALIDITY_VALIDITY_LR(player, 0);
@@ -598,7 +598,6 @@ static int uni_player_ctl_iec958_put(struct snd_kcontrol *kcontrol,
iec958->status[1] = ucontrol->value.iec958.status[1];
iec958->status[2] = ucontrol->value.iec958.status[2];
iec958->status[3] = ucontrol->value.iec958.status[3];
- mutex_unlock(&player->ctrl_lock);
spin_lock_irqsave(&player->irq_lock, flags);
if (player->substream && player->substream->runtime)
@@ -608,6 +607,8 @@ static int uni_player_ctl_iec958_put(struct snd_kcontrol *kcontrol,
uni_player_set_channel_status(player, NULL);
spin_unlock_irqrestore(&player->irq_lock, flags);
+ mutex_unlock(&player->ctrl_lock);
+
return 0;
}
diff --git a/sound/soc/stm/stm32_adfsdm.c b/sound/soc/stm/stm32_adfsdm.c
index 81c407d..08696a4 100644
--- a/sound/soc/stm/stm32_adfsdm.c
+++ b/sound/soc/stm/stm32_adfsdm.c
@@ -153,13 +153,13 @@ static const struct snd_soc_component_driver stm32_adfsdm_dai_component = {
.name = "stm32_dfsdm_audio",
};
-static void memcpy_32to16(void *dest, const void *src, size_t n)
+static void stm32_memcpy_32to16(void *dest, const void *src, size_t n)
{
unsigned int i = 0;
u16 *d = (u16 *)dest, *s = (u16 *)src;
s++;
- for (i = n; i > 0; i--) {
+ for (i = n >> 1; i > 0; i--) {
*d++ = *s++;
s++;
}
@@ -186,8 +186,8 @@ static int stm32_afsdm_pcm_cb(const void *data, size_t size, void *private)
if ((priv->pos + src_size) > buff_size) {
if (format == SNDRV_PCM_FORMAT_S16_LE)
- memcpy_32to16(&pcm_buff[priv->pos], src_buff,
- buff_size - priv->pos);
+ stm32_memcpy_32to16(&pcm_buff[priv->pos], src_buff,
+ buff_size - priv->pos);
else
memcpy(&pcm_buff[priv->pos], src_buff,
buff_size - priv->pos);
@@ -196,8 +196,8 @@ static int stm32_afsdm_pcm_cb(const void *data, size_t size, void *private)
}
if (format == SNDRV_PCM_FORMAT_S16_LE)
- memcpy_32to16(&pcm_buff[priv->pos],
- &src_buff[src_size - cur_size], cur_size);
+ stm32_memcpy_32to16(&pcm_buff[priv->pos],
+ &src_buff[src_size - cur_size], cur_size);
else
memcpy(&pcm_buff[priv->pos], &src_buff[src_size - cur_size],
cur_size);
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index 48e629a..30bcd5d 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -184,6 +184,56 @@ static bool stm32_sai_sub_writeable_reg(struct device *dev, unsigned int reg)
}
}
+static int stm32_sai_sub_reg_up(struct stm32_sai_sub_data *sai,
+ unsigned int reg, unsigned int mask,
+ unsigned int val)
+{
+ int ret;
+
+ ret = clk_enable(sai->pdata->pclk);
+ if (ret < 0)
+ return ret;
+
+ ret = regmap_update_bits(sai->regmap, reg, mask, val);
+
+ clk_disable(sai->pdata->pclk);
+
+ return ret;
+}
+
+static int stm32_sai_sub_reg_wr(struct stm32_sai_sub_data *sai,
+ unsigned int reg, unsigned int mask,
+ unsigned int val)
+{
+ int ret;
+
+ ret = clk_enable(sai->pdata->pclk);
+ if (ret < 0)
+ return ret;
+
+ ret = regmap_write_bits(sai->regmap, reg, mask, val);
+
+ clk_disable(sai->pdata->pclk);
+
+ return ret;
+}
+
+static int stm32_sai_sub_reg_rd(struct stm32_sai_sub_data *sai,
+ unsigned int reg, unsigned int *val)
+{
+ int ret;
+
+ ret = clk_enable(sai->pdata->pclk);
+ if (ret < 0)
+ return ret;
+
+ ret = regmap_read(sai->regmap, reg, val);
+
+ clk_disable(sai->pdata->pclk);
+
+ return ret;
+}
+
static const struct regmap_config stm32_sai_sub_regmap_config_f4 = {
.reg_bits = 32,
.reg_stride = 4,
@@ -295,7 +345,7 @@ static int stm32_sai_set_clk_div(struct stm32_sai_sub_data *sai,
mask = SAI_XCR1_MCKDIV_MASK(SAI_XCR1_MCKDIV_WIDTH(version));
cr1 = SAI_XCR1_MCKDIV_SET(div);
- ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, mask, cr1);
+ ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX, mask, cr1);
if (ret < 0)
dev_err(&sai->pdev->dev, "Failed to update CR1 register\n");
@@ -372,8 +422,8 @@ static int stm32_sai_mclk_enable(struct clk_hw *hw)
dev_dbg(&sai->pdev->dev, "Enable master clock\n");
- return regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
- SAI_XCR1_MCKEN, SAI_XCR1_MCKEN);
+ return stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+ SAI_XCR1_MCKEN, SAI_XCR1_MCKEN);
}
static void stm32_sai_mclk_disable(struct clk_hw *hw)
@@ -383,7 +433,7 @@ static void stm32_sai_mclk_disable(struct clk_hw *hw)
dev_dbg(&sai->pdev->dev, "Disable master clock\n");
- regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, SAI_XCR1_MCKEN, 0);
+ stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX, SAI_XCR1_MCKEN, 0);
}
static const struct clk_ops mclk_ops = {
@@ -446,15 +496,15 @@ static irqreturn_t stm32_sai_isr(int irq, void *devid)
unsigned int sr, imr, flags;
snd_pcm_state_t status = SNDRV_PCM_STATE_RUNNING;
- regmap_read(sai->regmap, STM_SAI_IMR_REGX, &imr);
- regmap_read(sai->regmap, STM_SAI_SR_REGX, &sr);
+ stm32_sai_sub_reg_rd(sai, STM_SAI_IMR_REGX, &imr);
+ stm32_sai_sub_reg_rd(sai, STM_SAI_SR_REGX, &sr);
flags = sr & imr;
if (!flags)
return IRQ_NONE;
- regmap_write_bits(sai->regmap, STM_SAI_CLRFR_REGX, SAI_XCLRFR_MASK,
- SAI_XCLRFR_MASK);
+ stm32_sai_sub_reg_wr(sai, STM_SAI_CLRFR_REGX, SAI_XCLRFR_MASK,
+ SAI_XCLRFR_MASK);
if (!sai->substream) {
dev_err(&pdev->dev, "Device stopped. Spurious IRQ 0x%x\n", sr);
@@ -503,8 +553,8 @@ static int stm32_sai_set_sysclk(struct snd_soc_dai *cpu_dai,
int ret;
if (dir == SND_SOC_CLOCK_OUT && sai->sai_mclk) {
- ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
- SAI_XCR1_NODIV,
+ ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+ SAI_XCR1_NODIV,
freq ? 0 : SAI_XCR1_NODIV);
if (ret < 0)
return ret;
@@ -583,7 +633,7 @@ static int stm32_sai_set_dai_tdm_slot(struct snd_soc_dai *cpu_dai, u32 tx_mask,
slotr_mask |= SAI_XSLOTR_SLOTEN_MASK;
- regmap_update_bits(sai->regmap, STM_SAI_SLOTR_REGX, slotr_mask, slotr);
+ stm32_sai_sub_reg_up(sai, STM_SAI_SLOTR_REGX, slotr_mask, slotr);
sai->slot_width = slot_width;
sai->slots = slots;
@@ -665,7 +715,7 @@ static int stm32_sai_set_dai_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt)
cr1_mask |= SAI_XCR1_CKSTR;
frcr_mask |= SAI_XFRCR_FSPOL;
- regmap_update_bits(sai->regmap, STM_SAI_FRCR_REGX, frcr_mask, frcr);
+ stm32_sai_sub_reg_up(sai, STM_SAI_FRCR_REGX, frcr_mask, frcr);
/* DAI clock master masks */
switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
@@ -693,7 +743,7 @@ static int stm32_sai_set_dai_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt)
cr1_mask |= SAI_XCR1_SLAVE;
conf_update:
- ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, cr1_mask, cr1);
+ ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX, cr1_mask, cr1);
if (ret < 0) {
dev_err(cpu_dai->dev, "Failed to update CR1 register\n");
return ret;
@@ -730,12 +780,12 @@ static int stm32_sai_startup(struct snd_pcm_substream *substream,
}
/* Enable ITs */
- regmap_write_bits(sai->regmap, STM_SAI_CLRFR_REGX,
- SAI_XCLRFR_MASK, SAI_XCLRFR_MASK);
+ stm32_sai_sub_reg_wr(sai, STM_SAI_CLRFR_REGX,
+ SAI_XCLRFR_MASK, SAI_XCLRFR_MASK);
imr = SAI_XIMR_OVRUDRIE;
if (STM_SAI_IS_CAPTURE(sai)) {
- regmap_read(sai->regmap, STM_SAI_CR2_REGX, &cr2);
+ stm32_sai_sub_reg_rd(sai, STM_SAI_CR2_REGX, &cr2);
if (cr2 & SAI_XCR2_MUTECNT_MASK)
imr |= SAI_XIMR_MUTEDETIE;
}
@@ -745,8 +795,8 @@ static int stm32_sai_startup(struct snd_pcm_substream *substream,
else
imr |= SAI_XIMR_AFSDETIE | SAI_XIMR_LFSDETIE;
- regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX,
- SAI_XIMR_MASK, imr);
+ stm32_sai_sub_reg_up(sai, STM_SAI_IMR_REGX,
+ SAI_XIMR_MASK, imr);
return 0;
}
@@ -763,10 +813,10 @@ static int stm32_sai_set_config(struct snd_soc_dai *cpu_dai,
* SAI fifo threshold is set to half fifo, to keep enough space
* for DMA incoming bursts.
*/
- regmap_write_bits(sai->regmap, STM_SAI_CR2_REGX,
- SAI_XCR2_FFLUSH | SAI_XCR2_FTH_MASK,
- SAI_XCR2_FFLUSH |
- SAI_XCR2_FTH_SET(STM_SAI_FIFO_TH_HALF));
+ stm32_sai_sub_reg_wr(sai, STM_SAI_CR2_REGX,
+ SAI_XCR2_FFLUSH | SAI_XCR2_FTH_MASK,
+ SAI_XCR2_FFLUSH |
+ SAI_XCR2_FTH_SET(STM_SAI_FIFO_TH_HALF));
/* DS bits in CR1 not set for SPDIF (size forced to 24 bits).*/
if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
@@ -795,7 +845,7 @@ static int stm32_sai_set_config(struct snd_soc_dai *cpu_dai,
if ((sai->slots == 2) && (params_channels(params) == 1))
cr1 |= SAI_XCR1_MONO;
- ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, cr1_mask, cr1);
+ ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX, cr1_mask, cr1);
if (ret < 0) {
dev_err(cpu_dai->dev, "Failed to update CR1 register\n");
return ret;
@@ -809,7 +859,7 @@ static int stm32_sai_set_slots(struct snd_soc_dai *cpu_dai)
struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
int slotr, slot_sz;
- regmap_read(sai->regmap, STM_SAI_SLOTR_REGX, &slotr);
+ stm32_sai_sub_reg_rd(sai, STM_SAI_SLOTR_REGX, &slotr);
/*
* If SLOTSZ is set to auto in SLOTR, align slot width on data size
@@ -831,16 +881,16 @@ static int stm32_sai_set_slots(struct snd_soc_dai *cpu_dai)
sai->slots = 2;
/* The number of slots in the audio frame is equal to NBSLOT[3:0] + 1*/
- regmap_update_bits(sai->regmap, STM_SAI_SLOTR_REGX,
- SAI_XSLOTR_NBSLOT_MASK,
- SAI_XSLOTR_NBSLOT_SET((sai->slots - 1)));
+ stm32_sai_sub_reg_up(sai, STM_SAI_SLOTR_REGX,
+ SAI_XSLOTR_NBSLOT_MASK,
+ SAI_XSLOTR_NBSLOT_SET((sai->slots - 1)));
/* Set default slots mask if not already set from DT */
if (!(slotr & SAI_XSLOTR_SLOTEN_MASK)) {
sai->slot_mask = (1 << sai->slots) - 1;
- regmap_update_bits(sai->regmap,
- STM_SAI_SLOTR_REGX, SAI_XSLOTR_SLOTEN_MASK,
- SAI_XSLOTR_SLOTEN_SET(sai->slot_mask));
+ stm32_sai_sub_reg_up(sai,
+ STM_SAI_SLOTR_REGX, SAI_XSLOTR_SLOTEN_MASK,
+ SAI_XSLOTR_SLOTEN_SET(sai->slot_mask));
}
dev_dbg(cpu_dai->dev, "Slots %d, slot width %d\n",
@@ -870,14 +920,14 @@ static void stm32_sai_set_frame(struct snd_soc_dai *cpu_dai)
dev_dbg(cpu_dai->dev, "Frame length %d, frame active %d\n",
sai->fs_length, fs_active);
- regmap_update_bits(sai->regmap, STM_SAI_FRCR_REGX, frcr_mask, frcr);
+ stm32_sai_sub_reg_up(sai, STM_SAI_FRCR_REGX, frcr_mask, frcr);
if ((sai->fmt & SND_SOC_DAIFMT_FORMAT_MASK) == SND_SOC_DAIFMT_LSB) {
offset = sai->slot_width - sai->data_size;
- regmap_update_bits(sai->regmap, STM_SAI_SLOTR_REGX,
- SAI_XSLOTR_FBOFF_MASK,
- SAI_XSLOTR_FBOFF_SET(offset));
+ stm32_sai_sub_reg_up(sai, STM_SAI_SLOTR_REGX,
+ SAI_XSLOTR_FBOFF_MASK,
+ SAI_XSLOTR_FBOFF_SET(offset));
}
}
@@ -994,9 +1044,9 @@ static int stm32_sai_configure_clock(struct snd_soc_dai *cpu_dai,
return -EINVAL;
}
- regmap_update_bits(sai->regmap,
- STM_SAI_CR1_REGX,
- SAI_XCR1_OSR, cr1);
+ stm32_sai_sub_reg_up(sai,
+ STM_SAI_CR1_REGX,
+ SAI_XCR1_OSR, cr1);
div = stm32_sai_get_clk_div(sai, sai_clk_rate,
sai->mclk_rate);
@@ -1058,12 +1108,12 @@ static int stm32_sai_trigger(struct snd_pcm_substream *substream, int cmd,
case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
dev_dbg(cpu_dai->dev, "Enable DMA and SAI\n");
- regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
- SAI_XCR1_DMAEN, SAI_XCR1_DMAEN);
+ stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+ SAI_XCR1_DMAEN, SAI_XCR1_DMAEN);
/* Enable SAI */
- ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
- SAI_XCR1_SAIEN, SAI_XCR1_SAIEN);
+ ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+ SAI_XCR1_SAIEN, SAI_XCR1_SAIEN);
if (ret < 0)
dev_err(cpu_dai->dev, "Failed to update CR1 register\n");
break;
@@ -1072,16 +1122,16 @@ static int stm32_sai_trigger(struct snd_pcm_substream *substream, int cmd,
case SNDRV_PCM_TRIGGER_STOP:
dev_dbg(cpu_dai->dev, "Disable DMA and SAI\n");
- regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX,
- SAI_XIMR_MASK, 0);
+ stm32_sai_sub_reg_up(sai, STM_SAI_IMR_REGX,
+ SAI_XIMR_MASK, 0);
- regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
- SAI_XCR1_SAIEN,
- (unsigned int)~SAI_XCR1_SAIEN);
+ stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+ SAI_XCR1_SAIEN,
+ (unsigned int)~SAI_XCR1_SAIEN);
- ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
- SAI_XCR1_DMAEN,
- (unsigned int)~SAI_XCR1_DMAEN);
+ ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+ SAI_XCR1_DMAEN,
+ (unsigned int)~SAI_XCR1_DMAEN);
if (ret < 0)
dev_err(cpu_dai->dev, "Failed to update CR1 register\n");
@@ -1101,7 +1151,7 @@ static void stm32_sai_shutdown(struct snd_pcm_substream *substream,
struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
unsigned long flags;
- regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX, SAI_XIMR_MASK, 0);
+ stm32_sai_sub_reg_up(sai, STM_SAI_IMR_REGX, SAI_XIMR_MASK, 0);
clk_disable_unprepare(sai->sai_ck);
@@ -1169,7 +1219,7 @@ static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
cr1_mask |= SAI_XCR1_SYNCEN_MASK;
cr1 |= SAI_XCR1_SYNCEN_SET(sai->sync);
- return regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, cr1_mask, cr1);
+ return stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX, cr1_mask, cr1);
}
static const struct snd_soc_dai_ops stm32_sai_pcm_dai_ops = {
@@ -1322,8 +1372,13 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev,
if (STM_SAI_HAS_PDM(sai) && STM_SAI_IS_SUB_A(sai))
sai->regmap_config = &stm32_sai_sub_regmap_config_h7;
- sai->regmap = devm_regmap_init_mmio_clk(&pdev->dev, "sai_ck",
- base, sai->regmap_config);
+ /*
+ * Do not manage peripheral clock through regmap framework as this
+ * can lead to circular locking issue with sai master clock provider.
+ * Manage peripheral clock directly in driver instead.
+ */
+ sai->regmap = devm_regmap_init_mmio(&pdev->dev, base,
+ sai->regmap_config);
if (IS_ERR(sai->regmap)) {
dev_err(&pdev->dev, "Failed to initialize MMIO\n");
return PTR_ERR(sai->regmap);
@@ -1420,6 +1475,10 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev,
return PTR_ERR(sai->sai_ck);
}
+ ret = clk_prepare(sai->pdata->pclk);
+ if (ret < 0)
+ return ret;
+
if (STM_SAI_IS_F4(sai->pdata))
return 0;
@@ -1501,22 +1560,48 @@ static int stm32_sai_sub_probe(struct platform_device *pdev)
return 0;
}
+static int stm32_sai_sub_remove(struct platform_device *pdev)
+{
+ struct stm32_sai_sub_data *sai = dev_get_drvdata(&pdev->dev);
+
+ clk_unprepare(sai->pdata->pclk);
+
+ return 0;
+}
+
#ifdef CONFIG_PM_SLEEP
static int stm32_sai_sub_suspend(struct device *dev)
{
struct stm32_sai_sub_data *sai = dev_get_drvdata(dev);
+ int ret;
+
+ ret = clk_enable(sai->pdata->pclk);
+ if (ret < 0)
+ return ret;
regcache_cache_only(sai->regmap, true);
regcache_mark_dirty(sai->regmap);
+
+ clk_disable(sai->pdata->pclk);
+
return 0;
}
static int stm32_sai_sub_resume(struct device *dev)
{
struct stm32_sai_sub_data *sai = dev_get_drvdata(dev);
+ int ret;
+
+ ret = clk_enable(sai->pdata->pclk);
+ if (ret < 0)
+ return ret;
regcache_cache_only(sai->regmap, false);
- return regcache_sync(sai->regmap);
+ ret = regcache_sync(sai->regmap);
+
+ clk_disable(sai->pdata->pclk);
+
+ return ret;
}
#endif /* CONFIG_PM_SLEEP */
@@ -1531,6 +1616,7 @@ static struct platform_driver stm32_sai_sub_driver = {
.pm = &stm32_sai_sub_pm_ops,
},
.probe = stm32_sai_sub_probe,
+ .remove = stm32_sai_sub_remove,
};
module_platform_driver(stm32_sai_sub_driver);
diff --git a/sound/soc/stm/stm32_spdifrx.c b/sound/soc/stm/stm32_spdifrx.c
index 3fd28ee..3769d9c 100644
--- a/sound/soc/stm/stm32_spdifrx.c
+++ b/sound/soc/stm/stm32_spdifrx.c
@@ -12,7 +12,6 @@
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/of_platform.h>
-#include <linux/pinctrl/consumer.h>
#include <linux/regmap.h>
#include <linux/reset.h>
@@ -220,6 +219,7 @@
* @slave_config: dma slave channel runtime config pointer
* @phys_addr: SPDIFRX registers physical base address
* @lock: synchronization enabling lock
+ * @irq_lock: prevent race condition with IRQ on stream state
* @cs: channel status buffer
* @ub: user data buffer
* @irq: SPDIFRX interrupt line
@@ -240,6 +240,7 @@ struct stm32_spdifrx_data {
struct dma_slave_config slave_config;
dma_addr_t phys_addr;
spinlock_t lock; /* Sync enabling lock */
+ spinlock_t irq_lock; /* Prevent race condition on stream state */
unsigned char cs[SPDIFRX_CS_BYTES_NB];
unsigned char ub[SPDIFRX_UB_BYTES_NB];
int irq;
@@ -320,6 +321,7 @@ static void stm32_spdifrx_dma_ctrl_stop(struct stm32_spdifrx_data *spdifrx)
static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx)
{
int cr, cr_mask, imr, ret;
+ unsigned long flags;
/* Enable IRQs */
imr = SPDIFRX_IMR_IFEIE | SPDIFRX_IMR_SYNCDIE | SPDIFRX_IMR_PERRIE;
@@ -327,7 +329,7 @@ static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx)
if (ret)
return ret;
- spin_lock(&spdifrx->lock);
+ spin_lock_irqsave(&spdifrx->lock, flags);
spdifrx->refcount++;
@@ -362,7 +364,7 @@ static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx)
"Failed to start synchronization\n");
}
- spin_unlock(&spdifrx->lock);
+ spin_unlock_irqrestore(&spdifrx->lock, flags);
return ret;
}
@@ -370,11 +372,12 @@ static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx)
static void stm32_spdifrx_stop(struct stm32_spdifrx_data *spdifrx)
{
int cr, cr_mask, reg;
+ unsigned long flags;
- spin_lock(&spdifrx->lock);
+ spin_lock_irqsave(&spdifrx->lock, flags);
if (--spdifrx->refcount) {
- spin_unlock(&spdifrx->lock);
+ spin_unlock_irqrestore(&spdifrx->lock, flags);
return;
}
@@ -393,7 +396,7 @@ static void stm32_spdifrx_stop(struct stm32_spdifrx_data *spdifrx)
regmap_read(spdifrx->regmap, STM32_SPDIFRX_DR, ®);
regmap_read(spdifrx->regmap, STM32_SPDIFRX_CSR, ®);
- spin_unlock(&spdifrx->lock);
+ spin_unlock_irqrestore(&spdifrx->lock, flags);
}
static int stm32_spdifrx_dma_ctrl_register(struct device *dev,
@@ -480,8 +483,6 @@ static int stm32_spdifrx_get_ctrl_data(struct stm32_spdifrx_data *spdifrx)
memset(spdifrx->cs, 0, SPDIFRX_CS_BYTES_NB);
memset(spdifrx->ub, 0, SPDIFRX_UB_BYTES_NB);
- pinctrl_pm_select_default_state(&spdifrx->pdev->dev);
-
ret = stm32_spdifrx_dma_ctrl_start(spdifrx);
if (ret < 0)
return ret;
@@ -513,7 +514,6 @@ static int stm32_spdifrx_get_ctrl_data(struct stm32_spdifrx_data *spdifrx)
end:
clk_disable_unprepare(spdifrx->kclk);
- pinctrl_pm_select_sleep_state(&spdifrx->pdev->dev);
return ret;
}
@@ -665,7 +665,6 @@ static const struct regmap_config stm32_h7_spdifrx_regmap_conf = {
static irqreturn_t stm32_spdifrx_isr(int irq, void *devid)
{
struct stm32_spdifrx_data *spdifrx = (struct stm32_spdifrx_data *)devid;
- struct snd_pcm_substream *substream = spdifrx->substream;
struct platform_device *pdev = spdifrx->pdev;
unsigned int cr, mask, sr, imr;
unsigned int flags, sync_state;
@@ -745,14 +744,19 @@ static irqreturn_t stm32_spdifrx_isr(int irq, void *devid)
return IRQ_HANDLED;
}
- if (substream)
- snd_pcm_stop(substream, SNDRV_PCM_STATE_DISCONNECTED);
+ spin_lock(&spdifrx->irq_lock);
+ if (spdifrx->substream)
+ snd_pcm_stop(spdifrx->substream,
+ SNDRV_PCM_STATE_DISCONNECTED);
+ spin_unlock(&spdifrx->irq_lock);
return IRQ_HANDLED;
}
- if (err_xrun && substream)
- snd_pcm_stop_xrun(substream);
+ spin_lock(&spdifrx->irq_lock);
+ if (err_xrun && spdifrx->substream)
+ snd_pcm_stop_xrun(spdifrx->substream);
+ spin_unlock(&spdifrx->irq_lock);
return IRQ_HANDLED;
}
@@ -761,9 +765,12 @@ static int stm32_spdifrx_startup(struct snd_pcm_substream *substream,
struct snd_soc_dai *cpu_dai)
{
struct stm32_spdifrx_data *spdifrx = snd_soc_dai_get_drvdata(cpu_dai);
+ unsigned long flags;
int ret;
+ spin_lock_irqsave(&spdifrx->irq_lock, flags);
spdifrx->substream = substream;
+ spin_unlock_irqrestore(&spdifrx->irq_lock, flags);
ret = clk_prepare_enable(spdifrx->kclk);
if (ret)
@@ -839,8 +846,12 @@ static void stm32_spdifrx_shutdown(struct snd_pcm_substream *substream,
struct snd_soc_dai *cpu_dai)
{
struct stm32_spdifrx_data *spdifrx = snd_soc_dai_get_drvdata(cpu_dai);
+ unsigned long flags;
+ spin_lock_irqsave(&spdifrx->irq_lock, flags);
spdifrx->substream = NULL;
+ spin_unlock_irqrestore(&spdifrx->irq_lock, flags);
+
clk_disable_unprepare(spdifrx->kclk);
}
@@ -944,6 +955,7 @@ static int stm32_spdifrx_probe(struct platform_device *pdev)
spdifrx->pdev = pdev;
init_completion(&spdifrx->cs_completion);
spin_lock_init(&spdifrx->lock);
+ spin_lock_init(&spdifrx->irq_lock);
platform_set_drvdata(pdev, spdifrx);
diff --git a/sound/usb/card.h b/sound/usb/card.h
index 2991b99..395403a 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -145,6 +145,7 @@ struct snd_usb_substream {
struct snd_usb_endpoint *sync_endpoint;
unsigned long flags;
bool need_setup_ep; /* (re)configure EP at prepare? */
+ bool need_setup_fmt; /* (re)configure fmt after resume? */
unsigned int speed; /* USB_SPEED_XXX */
u64 formats; /* format bitmasks (all or'ed) */
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 9c8930b..0e4eab9 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -370,7 +370,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
add_sync_ep_from_ifnum:
iface = usb_ifnum_to_if(dev, ifnum);
- if (!iface || iface->num_altsetting == 0)
+ if (!iface || iface->num_altsetting < 2)
return -EINVAL;
alts = &iface->altsetting[1];
@@ -506,15 +506,15 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt)
if (WARN_ON(!iface))
return -EINVAL;
alts = usb_altnum_to_altsetting(iface, fmt->altsetting);
- altsd = get_iface_desc(alts);
- if (WARN_ON(altsd->bAlternateSetting != fmt->altsetting))
+ if (WARN_ON(!alts))
return -EINVAL;
+ altsd = get_iface_desc(alts);
- if (fmt == subs->cur_audiofmt)
+ if (fmt == subs->cur_audiofmt && !subs->need_setup_fmt)
return 0;
/* close the old interface */
- if (subs->interface >= 0 && subs->interface != fmt->iface) {
+ if (subs->interface >= 0 && (subs->interface != fmt->iface || subs->need_setup_fmt)) {
if (!subs->stream->chip->keep_iface) {
err = usb_set_interface(subs->dev, subs->interface, 0);
if (err < 0) {
@@ -528,6 +528,9 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt)
subs->altset_idx = 0;
}
+ if (subs->need_setup_fmt)
+ subs->need_setup_fmt = false;
+
/* set interface */
if (iface->cur_altsetting != alts) {
err = snd_usb_select_mode_quirk(subs, fmt);
@@ -1728,6 +1731,13 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea
subs->data_endpoint->retire_data_urb = retire_playback_urb;
subs->running = 0;
return 0;
+ case SNDRV_PCM_TRIGGER_SUSPEND:
+ if (subs->stream->chip->setup_fmt_after_resume_quirk) {
+ stop_endpoints(subs, true);
+ subs->need_setup_fmt = true;
+ return 0;
+ }
+ break;
}
return -EINVAL;
@@ -1760,6 +1770,13 @@ static int snd_usb_substream_capture_trigger(struct snd_pcm_substream *substream
subs->data_endpoint->retire_data_urb = retire_capture_urb;
subs->running = 1;
return 0;
+ case SNDRV_PCM_TRIGGER_SUSPEND:
+ if (subs->stream->chip->setup_fmt_after_resume_quirk) {
+ stop_endpoints(subs, true);
+ subs->need_setup_fmt = true;
+ return 0;
+ }
+ break;
}
return -EINVAL;
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 70c338f..d187aa6 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -3466,7 +3466,8 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
.vendor_name = "Dell",
.product_name = "WD19 Dock",
.profile_name = "Dell-WD15-Dock",
- .ifnum = QUIRK_NO_INTERFACE
+ .ifnum = QUIRK_ANY_INTERFACE,
+ .type = QUIRK_SETUP_FMT_AFTER_RESUME
}
},
/* MOTU Microbook II */
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 349e1e5..8218403 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -508,6 +508,16 @@ static int create_standard_mixer_quirk(struct snd_usb_audio *chip,
return snd_usb_create_mixer(chip, quirk->ifnum, 0);
}
+
+static int setup_fmt_after_resume_quirk(struct snd_usb_audio *chip,
+ struct usb_interface *iface,
+ struct usb_driver *driver,
+ const struct snd_usb_audio_quirk *quirk)
+{
+ chip->setup_fmt_after_resume_quirk = 1;
+ return 1; /* Continue with creating streams and mixer */
+}
+
/*
* audio-interface quirks
*
@@ -546,6 +556,7 @@ int snd_usb_create_quirk(struct snd_usb_audio *chip,
[QUIRK_AUDIO_EDIROL_UAXX] = create_uaxx_quirk,
[QUIRK_AUDIO_ALIGN_TRANSFER] = create_align_transfer_quirk,
[QUIRK_AUDIO_STANDARD_MIXER] = create_standard_mixer_quirk,
+ [QUIRK_SETUP_FMT_AFTER_RESUME] = setup_fmt_after_resume_quirk,
};
if (quirk->type < QUIRK_TYPE_COUNT) {
@@ -1386,6 +1397,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */
case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */
+ case USB_ID(0x05a7, 0x1020): /* Bose Companion 5 */
case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */
case USB_ID(0x1395, 0x740a): /* Sennheiser DECT */
case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index ff3cbf6..6fe3ab58 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -33,7 +33,7 @@ struct snd_usb_audio {
wait_queue_head_t shutdown_wait;
unsigned int txfr_quirk:1; /* Subframe boundaries on transfers */
unsigned int tx_length_quirk:1; /* Put length specifier in transfers */
-
+ unsigned int setup_fmt_after_resume_quirk:1; /* setup the format to interface after resume */
int num_interfaces;
int num_suspended_intf;
int sample_rate_read_error;
@@ -98,6 +98,7 @@ enum quirk_type {
QUIRK_AUDIO_EDIROL_UAXX,
QUIRK_AUDIO_ALIGN_TRANSFER,
QUIRK_AUDIO_STANDARD_MIXER,
+ QUIRK_SETUP_FMT_AFTER_RESUME,
QUIRK_TYPE_COUNT
};
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 5535650..f897eee 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -38,7 +38,7 @@
FEATURE_DISPLAY = libbfd disassembler-four-args
check_feat := 1
-NON_CHECK_FEAT_TARGETS := clean bpftool_clean
+NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean
ifdef MAKECMDGOALS
ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
check_feat := 0
@@ -73,7 +73,7 @@
PROGS = $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg $(OUTPUT)bpf_asm
-all: $(PROGS) bpftool
+all: $(PROGS) bpftool runqslower
$(OUTPUT)bpf_jit_disasm: CFLAGS += -DPACKAGE='bpf_jit_disasm'
$(OUTPUT)bpf_jit_disasm: $(OUTPUT)bpf_jit_disasm.o
@@ -89,7 +89,7 @@
$(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
$(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
-clean: bpftool_clean
+clean: bpftool_clean runqslower_clean
$(call QUIET_CLEAN, bpf-progs)
$(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \
$(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.*
@@ -97,7 +97,7 @@
$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf
$(Q)$(RM) -r -- $(OUTPUT)feature
-install: $(PROGS) bpftool_install
+install: $(PROGS) bpftool_install runqslower_install
$(call QUIET_INSTALL, bpf_jit_disasm)
$(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin
$(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm
@@ -115,4 +115,14 @@
bpftool_clean:
$(call descend,bpftool,clean)
-.PHONY: all install clean bpftool bpftool_install bpftool_clean
+runqslower:
+ $(call descend,runqslower)
+
+runqslower_install:
+ $(call descend,runqslower,install)
+
+runqslower_clean:
+ $(call descend,runqslower,clean)
+
+.PHONY: all install clean bpftool bpftool_install bpftool_clean \
+ runqslower runqslower_install runqslower_clean
diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
index 86a87da..94d9132 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
@@ -196,7 +196,7 @@
#define __EXAMPLE_SKEL_H__
#include <stdlib.h>
- #include <libbpf.h>
+ #include <bpf/libbpf.h>
struct example {
struct bpf_object_skeleton *skeleton;
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 39bc6f0..c4e8103 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -45,7 +45,7 @@
-I$(srctree)/kernel/bpf/ \
-I$(srctree)/tools/include \
-I$(srctree)/tools/include/uapi \
- -I$(srctree)/tools/lib/bpf \
+ -I$(srctree)/tools/lib \
-I$(srctree)/tools/perf
CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
ifneq ($(EXTRA_CFLAGS),)
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index e5bc97b..4ba90d8 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -8,15 +8,15 @@
#include <stdio.h>
#include <string.h>
#include <unistd.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
#include <linux/btf.h>
#include <linux/hashtable.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
-#include "btf.h"
#include "json_writer.h"
#include "main.h"
@@ -370,6 +370,10 @@ static int dump_btf_c(const struct btf *btf,
if (IS_ERR(d))
return PTR_ERR(d);
+ printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
+ printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n");
+ printf("#endif\n\n");
+
if (root_type_cnt) {
for (i = 0; i < root_type_cnt; i++) {
err = btf_dump__dump_type(d, root_type_ids[i]);
@@ -386,6 +390,10 @@ static int dump_btf_c(const struct btf *btf,
}
}
+ printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
+ printf("#pragma clang attribute pop\n");
+ printf("#endif\n");
+
done:
btf_dump__free(d);
return err;
@@ -524,7 +532,7 @@ static int do_dump(int argc, char **argv)
if (IS_ERR(btf)) {
err = PTR_ERR(btf);
btf = NULL;
- p_err("failed to load BTF from %s: %s",
+ p_err("failed to load BTF from %s: %s",
*argv, strerror(err));
goto done;
}
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index d66131f..01cc52b 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -8,8 +8,8 @@
#include <linux/bitops.h>
#include <linux/btf.h>
#include <linux/err.h>
+#include <bpf/btf.h>
-#include "btf.h"
#include "json_writer.h"
#include "main.h"
@@ -26,7 +26,7 @@ static void btf_dumper_ptr(const void *data, json_writer_t *jw,
bool is_plain_text)
{
if (is_plain_text)
- jsonw_printf(jw, "%p", data);
+ jsonw_printf(jw, "%p", *(void **)data);
else
jsonw_printf(jw, "%lu", *(unsigned long *)data);
}
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 2f017ca..62c6a1d 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -14,7 +14,7 @@
#include <sys/types.h>
#include <unistd.h>
-#include <bpf.h>
+#include <bpf/bpf.h>
#include "main.h"
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 88264aba..b75b8ec5 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -20,8 +20,8 @@
#include <sys/stat.h>
#include <sys/vfs.h>
-#include <bpf.h>
-#include <libbpf.h> /* libbpf_num_possible_cpus */
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
#include "main.h"
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index 03bdc5b..446ba89 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -12,8 +12,8 @@
#include <linux/filter.h>
#include <linux/limits.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#include <zlib.h>
#include "main.h"
@@ -572,6 +572,18 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
printf("\n");
}
+static void
+probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
+{
+ bool res;
+
+ res = bpf_probe_large_insn_limit(ifindex);
+ print_bool_feature("have_large_insn_limit",
+ "Large program size limit",
+ "HAVE_LARGE_INSN_LIMIT",
+ res, define_prefix);
+}
+
static int do_probe(int argc, char **argv)
{
enum probe_component target = COMPONENT_UNSPEC;
@@ -724,6 +736,12 @@ static int do_probe(int argc, char **argv)
probe_helpers_for_progtype(i, supported_types[i],
define_prefix, ifindex);
+ print_end_then_start_section("misc",
+ "Scanning miscellaneous eBPF features...",
+ "/*** eBPF misc features ***/",
+ define_prefix);
+ probe_large_insn_limit(define_prefix, ifindex);
+
exit_close_json:
if (json_output) {
/* End current "section" of probes */
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 7ce09a9..f8113b3 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -12,15 +12,15 @@
#include <stdio.h>
#include <string.h>
#include <unistd.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/mman.h>
#include <unistd.h>
+#include <bpf/btf.h>
-#include "btf.h"
-#include "libbpf_internal.h"
+#include "bpf/libbpf_internal.h"
#include "json_writer.h"
#include "main.h"
@@ -333,7 +333,7 @@ static int do_skeleton(int argc, char **argv)
#define %2$s \n\
\n\
#include <stdlib.h> \n\
- #include <libbpf.h> \n\
+ #include <bpf/libbpf.h> \n\
\n\
struct %1$s { \n\
struct bpf_object_skeleton *skeleton; \n\
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index bfed711..f7f5885 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -24,7 +24,7 @@
#include <dis-asm.h>
#include <sys/stat.h>
#include <limits.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include "json_writer.h"
#include "main.h"
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 1fe91c5..6d41bbfc 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -9,8 +9,8 @@
#include <stdlib.h>
#include <string.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#include "main.h"
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index c01f76f..e6c8568 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -15,9 +15,9 @@
#include <sys/types.h>
#include <sys/stat.h>
-#include <bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
-#include "btf.h"
#include "json_writer.h"
#include "main.h"
@@ -48,6 +48,7 @@ const char * const map_type_name[] = {
[BPF_MAP_TYPE_QUEUE] = "queue",
[BPF_MAP_TYPE_STACK] = "stack",
[BPF_MAP_TYPE_SK_STORAGE] = "sk_storage",
+ [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops",
};
const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
@@ -251,6 +252,7 @@ static int do_dump_btf(const struct btf_dumper *d,
struct bpf_map_info *map_info, void *key,
void *value)
{
+ __u32 value_id;
int ret;
/* start of key-value pair */
@@ -264,9 +266,12 @@ static int do_dump_btf(const struct btf_dumper *d,
goto err_end_obj;
}
+ value_id = map_info->btf_vmlinux_value_type_id ?
+ : map_info->btf_value_type_id;
+
if (!map_is_per_cpu(map_info->type)) {
jsonw_name(d->jw, "value");
- ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+ ret = btf_dumper_type(d, value_id, value);
} else {
unsigned int i, n, step;
@@ -278,8 +283,7 @@ static int do_dump_btf(const struct btf_dumper *d,
jsonw_start_object(d->jw);
jsonw_int_field(d->jw, "cpu", i);
jsonw_name(d->jw, "value");
- ret = btf_dumper_type(d, map_info->btf_value_type_id,
- value + i * step);
+ ret = btf_dumper_type(d, value_id, value + i * step);
jsonw_end_object(d->jw);
if (ret)
break;
@@ -915,37 +919,63 @@ static int maps_have_btf(int *fds, int nb_fds)
{
struct bpf_map_info info = {};
__u32 len = sizeof(info);
- struct btf *btf = NULL;
int err, i;
for (i = 0; i < nb_fds; i++) {
err = bpf_obj_get_info_by_fd(fds[i], &info, &len);
if (err) {
p_err("can't get map info: %s", strerror(errno));
- goto err_close;
+ return -1;
}
- err = btf__get_from_id(info.btf_id, &btf);
- if (err) {
- p_err("failed to get btf");
- goto err_close;
- }
-
- if (!btf)
+ if (!info.btf_id)
return 0;
}
return 1;
+}
-err_close:
- for (; i < nb_fds; i++)
- close(fds[i]);
- return -1;
+static struct btf *btf_vmlinux;
+
+static struct btf *get_map_kv_btf(const struct bpf_map_info *info)
+{
+ struct btf *btf = NULL;
+
+ if (info->btf_vmlinux_value_type_id) {
+ if (!btf_vmlinux) {
+ btf_vmlinux = libbpf_find_kernel_btf();
+ if (IS_ERR(btf_vmlinux))
+ p_err("failed to get kernel btf");
+ }
+ return btf_vmlinux;
+ } else if (info->btf_value_type_id) {
+ int err;
+
+ err = btf__get_from_id(info->btf_id, &btf);
+ if (err || !btf) {
+ p_err("failed to get btf");
+ btf = err ? ERR_PTR(err) : ERR_PTR(-ESRCH);
+ }
+ }
+
+ return btf;
+}
+
+static void free_map_kv_btf(struct btf *btf)
+{
+ if (!IS_ERR(btf) && btf != btf_vmlinux)
+ btf__free(btf);
+}
+
+static void free_btf_vmlinux(void)
+{
+ if (!IS_ERR(btf_vmlinux))
+ btf__free(btf_vmlinux);
}
static int
map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
- bool enable_btf, bool show_header)
+ bool show_header)
{
void *key, *value, *prev_key;
unsigned int num_elems = 0;
@@ -962,18 +992,13 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
prev_key = NULL;
- if (enable_btf) {
- err = btf__get_from_id(info->btf_id, &btf);
- if (err || !btf) {
- /* enable_btf is true only if we've already checked
- * that all maps have BTF information.
- */
- p_err("failed to get btf");
+ if (wtr) {
+ btf = get_map_kv_btf(info);
+ if (IS_ERR(btf)) {
+ err = PTR_ERR(btf);
goto exit_free;
}
- }
- if (wtr) {
if (show_header) {
jsonw_start_object(wtr); /* map object */
show_map_header_json(info, wtr);
@@ -1012,7 +1037,7 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
free(key);
free(value);
close(fd);
- btf__free(btf);
+ free_map_kv_btf(btf);
return err;
}
@@ -1021,7 +1046,7 @@ static int do_dump(int argc, char **argv)
{
json_writer_t *wtr = NULL, *btf_wtr = NULL;
struct bpf_map_info info = {};
- int nb_fds, i = 0, btf = 0;
+ int nb_fds, i = 0;
__u32 len = sizeof(info);
int *fds = NULL;
int err = -1;
@@ -1041,17 +1066,17 @@ static int do_dump(int argc, char **argv)
if (json_output) {
wtr = json_wtr;
} else {
- btf = maps_have_btf(fds, nb_fds);
- if (btf < 0)
+ int do_plain_btf;
+
+ do_plain_btf = maps_have_btf(fds, nb_fds);
+ if (do_plain_btf < 0)
goto exit_close;
- if (btf) {
+
+ if (do_plain_btf) {
btf_wtr = get_btf_writer();
- if (btf_wtr) {
- wtr = btf_wtr;
- } else {
+ wtr = btf_wtr;
+ if (!btf_wtr)
p_info("failed to create json writer for btf. falling back to plain output");
- btf = 0;
- }
}
}
@@ -1062,7 +1087,7 @@ static int do_dump(int argc, char **argv)
p_err("can't get map info: %s", strerror(errno));
break;
}
- err = map_dump(fds[i], &info, wtr, btf, nb_fds > 1);
+ err = map_dump(fds[i], &info, wtr, nb_fds > 1);
if (!wtr && i != nb_fds - 1)
printf("\n");
@@ -1073,13 +1098,14 @@ static int do_dump(int argc, char **argv)
if (wtr && nb_fds > 1)
jsonw_end_array(wtr); /* root array */
- if (btf)
+ if (btf_wtr)
jsonw_destroy(&btf_wtr);
exit_close:
for (; i < nb_fds; i++)
close(fds[i]);
exit_free:
free(fds);
+ free_btf_vmlinux();
return err;
}
diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c
index 4c5531d1..d9b29c1 100644
--- a/tools/bpf/bpftool/map_perf_ring.c
+++ b/tools/bpf/bpftool/map_perf_ring.c
@@ -6,7 +6,7 @@
*/
#include <errno.h>
#include <fcntl.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include <poll.h>
#include <signal.h>
#include <stdbool.h>
@@ -21,7 +21,7 @@
#include <sys/mman.h>
#include <sys/syscall.h>
-#include <bpf.h>
+#include <bpf/bpf.h>
#include <perf-sys.h>
#include "main.h"
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index d93bee2..c5e3895 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -7,7 +7,8 @@
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#include <net/if.h>
#include <linux/if.h>
#include <linux/rtnetlink.h>
@@ -16,9 +17,8 @@
#include <sys/stat.h>
#include <sys/types.h>
-#include <bpf.h>
-#include <nlattr.h>
-#include "libbpf_internal.h"
+#include "bpf/nlattr.h"
+#include "bpf/libbpf_internal.h"
#include "main.h"
#include "netlink_dumper.h"
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
index 550a0f5..5f65140 100644
--- a/tools/bpf/bpftool/netlink_dumper.c
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -3,11 +3,11 @@
#include <stdlib.h>
#include <string.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include <linux/rtnetlink.h>
#include <linux/tc_act/tc_bpf.h>
-#include <nlattr.h>
+#include "bpf/nlattr.h"
#include "main.h"
#include "netlink_dumper.h"
diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c
index b2046f3..3341aa1 100644
--- a/tools/bpf/bpftool/perf.c
+++ b/tools/bpf/bpftool/perf.c
@@ -13,7 +13,7 @@
#include <unistd.h>
#include <ftw.h>
-#include <bpf.h>
+#include <bpf/bpf.h>
#include "main.h"
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 47a61ac..a3521de 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -17,9 +17,9 @@
#include <linux/err.h>
#include <linux/sizes.h>
-#include <bpf.h>
-#include <btf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
#include "cfg.h"
#include "main.h"
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 5b91ee6..8608cd6 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -7,7 +7,7 @@
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include "disasm.h"
#include "json_writer.h"
diff --git a/tools/bpf/runqslower/.gitignore b/tools/bpf/runqslower/.gitignore
new file mode 100644
index 0000000..90a456a
--- /dev/null
+++ b/tools/bpf/runqslower/.gitignore
@@ -0,0 +1 @@
+/.output
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
new file mode 100644
index 0000000..faf54186
--- /dev/null
+++ b/tools/bpf/runqslower/Makefile
@@ -0,0 +1,84 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+OUTPUT := .output
+CLANG := clang
+LLC := llc
+LLVM_STRIP := llvm-strip
+DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+LIBBPF_SRC := $(abspath ../../lib/bpf)
+BPFOBJ := $(OUTPUT)/libbpf.a
+BPF_INCLUDE := $(OUTPUT)
+INCLUDES := -I$(BPF_INCLUDE) -I$(OUTPUT) -I$(abspath ../../lib)
+CFLAGS := -g -Wall
+
+# Try to detect best kernel BTF source
+KERNEL_REL := $(shell uname -r)
+VMLINUX_BTF_PATHS := /sys/kernel/btf/vmlinux /boot/vmlinux-$(KERNEL_REL)
+VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword \
+ $(wildcard $(VMLINUX_BTF_PATHS))))
+
+abs_out := $(abspath $(OUTPUT))
+ifeq ($(V),1)
+Q =
+msg =
+else
+Q = @
+msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
+MAKEFLAGS += --no-print-directory
+submake_extras := feature_display=0
+endif
+
+.DELETE_ON_ERROR:
+
+.PHONY: all clean runqslower
+all: runqslower
+
+runqslower: $(OUTPUT)/runqslower
+
+clean:
+ $(call msg,CLEAN)
+ $(Q)rm -rf $(OUTPUT) runqslower
+
+$(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ)
+ $(call msg,BINARY,$@)
+ $(Q)$(CC) $(CFLAGS) -lelf -lz $^ -o $@
+
+$(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \
+ $(OUTPUT)/runqslower.bpf.o
+
+$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h
+
+$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL)
+ $(call msg,GEN-SKEL,$@)
+ $(Q)$(BPFTOOL) gen skeleton $< > $@
+
+$(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT)
+ $(call msg,BPF,$@)
+ $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \
+ -c $(filter %.c,$^) -o $@ && \
+ $(LLVM_STRIP) -g $@
+
+$(OUTPUT)/%.o: %.c | $(OUTPUT)
+ $(call msg,CC,$@)
+ $(Q)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@
+
+$(OUTPUT):
+ $(call msg,MKDIR,$@)
+ $(Q)mkdir -p $(OUTPUT)
+
+$(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL)
+ $(call msg,GEN,$@)
+ $(Q)if [ ! -e "$(VMLINUX_BTF_PATH)" ] ; then \
+ echo "Couldn't find kernel BTF; set VMLINUX_BTF to" \
+ "specify its location." >&2; \
+ exit 1;\
+ fi
+ $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@
+
+$(BPFOBJ): | $(OUTPUT)
+ $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \
+ OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
+
+$(DEFAULT_BPFTOOL):
+ $(Q)$(MAKE) $(submake_extras) -C ../bpftool \
+ prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install
diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c
new file mode 100644
index 0000000..48a39f7
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.bpf.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "runqslower.h"
+
+#define TASK_RUNNING 0
+
+#define BPF_F_INDEX_MASK 0xffffffffULL
+#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
+
+const volatile __u64 min_us = 0;
+const volatile pid_t targ_pid = 0;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 10240);
+ __type(key, u32);
+ __type(value, u64);
+} start SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+ __uint(key_size, sizeof(u32));
+ __uint(value_size, sizeof(u32));
+} events SEC(".maps");
+
+/* record enqueue timestamp */
+__always_inline
+static int trace_enqueue(u32 tgid, u32 pid)
+{
+ u64 ts;
+
+ if (!pid || (targ_pid && targ_pid != pid))
+ return 0;
+
+ ts = bpf_ktime_get_ns();
+ bpf_map_update_elem(&start, &pid, &ts, 0);
+ return 0;
+}
+
+SEC("tp_btf/sched_wakeup")
+int handle__sched_wakeup(u64 *ctx)
+{
+ /* TP_PROTO(struct task_struct *p) */
+ struct task_struct *p = (void *)ctx[0];
+
+ return trace_enqueue(p->tgid, p->pid);
+}
+
+SEC("tp_btf/sched_wakeup_new")
+int handle__sched_wakeup_new(u64 *ctx)
+{
+ /* TP_PROTO(struct task_struct *p) */
+ struct task_struct *p = (void *)ctx[0];
+
+ return trace_enqueue(p->tgid, p->pid);
+}
+
+SEC("tp_btf/sched_switch")
+int handle__sched_switch(u64 *ctx)
+{
+ /* TP_PROTO(bool preempt, struct task_struct *prev,
+ * struct task_struct *next)
+ */
+ struct task_struct *prev = (struct task_struct *)ctx[1];
+ struct task_struct *next = (struct task_struct *)ctx[2];
+ struct event event = {};
+ u64 *tsp, delta_us;
+ long state;
+ u32 pid;
+
+ /* ivcsw: treat like an enqueue event and store timestamp */
+ if (prev->state == TASK_RUNNING)
+ trace_enqueue(prev->tgid, prev->pid);
+
+ pid = next->pid;
+
+ /* fetch timestamp and calculate delta */
+ tsp = bpf_map_lookup_elem(&start, &pid);
+ if (!tsp)
+ return 0; /* missed enqueue */
+
+ delta_us = (bpf_ktime_get_ns() - *tsp) / 1000;
+ if (min_us && delta_us <= min_us)
+ return 0;
+
+ event.pid = pid;
+ event.delta_us = delta_us;
+ bpf_get_current_comm(&event.task, sizeof(event.task));
+
+ /* output */
+ bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU,
+ &event, sizeof(event));
+
+ bpf_map_delete_elem(&start, &pid);
+ return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c
new file mode 100644
index 0000000..d897158
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+// Copyright (c) 2019 Facebook
+#include <argp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <time.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include "runqslower.h"
+#include "runqslower.skel.h"
+
+struct env {
+ pid_t pid;
+ __u64 min_us;
+ bool verbose;
+} env = {
+ .min_us = 10000,
+};
+
+const char *argp_program_version = "runqslower 0.1";
+const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
+const char argp_program_doc[] =
+"runqslower Trace long process scheduling delays.\n"
+" For Linux, uses eBPF, BPF CO-RE, libbpf, BTF.\n"
+"\n"
+"This script traces high scheduling delays between tasks being\n"
+"ready to run and them running on CPU after that.\n"
+"\n"
+"USAGE: runqslower [-p PID] [min_us]\n"
+"\n"
+"EXAMPLES:\n"
+" runqslower # trace run queue latency higher than 10000 us (default)\n"
+" runqslower 1000 # trace run queue latency higher than 1000 us\n"
+" runqslower -p 123 # trace pid 123 only\n";
+
+static const struct argp_option opts[] = {
+ { "pid", 'p', "PID", 0, "Process PID to trace"},
+ { "verbose", 'v', NULL, 0, "Verbose debug output" },
+ {},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+ static int pos_args;
+ int pid;
+ long long min_us;
+
+ switch (key) {
+ case 'v':
+ env.verbose = true;
+ break;
+ case 'p':
+ errno = 0;
+ pid = strtol(arg, NULL, 10);
+ if (errno || pid <= 0) {
+ fprintf(stderr, "Invalid PID: %s\n", arg);
+ argp_usage(state);
+ }
+ env.pid = pid;
+ break;
+ case ARGP_KEY_ARG:
+ if (pos_args++) {
+ fprintf(stderr,
+ "Unrecognized positional argument: %s\n", arg);
+ argp_usage(state);
+ }
+ errno = 0;
+ min_us = strtoll(arg, NULL, 10);
+ if (errno || min_us <= 0) {
+ fprintf(stderr, "Invalid delay (in us): %s\n", arg);
+ argp_usage(state);
+ }
+ env.min_us = min_us;
+ break;
+ default:
+ return ARGP_ERR_UNKNOWN;
+ }
+ return 0;
+}
+
+int libbpf_print_fn(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ if (level == LIBBPF_DEBUG && !env.verbose)
+ return 0;
+ return vfprintf(stderr, format, args);
+}
+
+static int bump_memlock_rlimit(void)
+{
+ struct rlimit rlim_new = {
+ .rlim_cur = RLIM_INFINITY,
+ .rlim_max = RLIM_INFINITY,
+ };
+
+ return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+}
+
+void handle_event(void *ctx, int cpu, void *data, __u32 data_sz)
+{
+ const struct event *e = data;
+ struct tm *tm;
+ char ts[32];
+ time_t t;
+
+ time(&t);
+ tm = localtime(&t);
+ strftime(ts, sizeof(ts), "%H:%M:%S", tm);
+ printf("%-8s %-16s %-6d %14llu\n", ts, e->task, e->pid, e->delta_us);
+}
+
+void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt)
+{
+ printf("Lost %llu events on CPU #%d!\n", lost_cnt, cpu);
+}
+
+int main(int argc, char **argv)
+{
+ static const struct argp argp = {
+ .options = opts,
+ .parser = parse_arg,
+ .doc = argp_program_doc,
+ };
+ struct perf_buffer_opts pb_opts;
+ struct perf_buffer *pb = NULL;
+ struct runqslower_bpf *obj;
+ int err;
+
+ err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
+ if (err)
+ return err;
+
+ libbpf_set_print(libbpf_print_fn);
+
+ err = bump_memlock_rlimit();
+ if (err) {
+ fprintf(stderr, "failed to increase rlimit: %d", err);
+ return 1;
+ }
+
+ obj = runqslower_bpf__open();
+ if (!obj) {
+ fprintf(stderr, "failed to open and/or load BPF object\n");
+ return 1;
+ }
+
+ /* initialize global data (filtering options) */
+ obj->rodata->targ_pid = env.pid;
+ obj->rodata->min_us = env.min_us;
+
+ err = runqslower_bpf__load(obj);
+ if (err) {
+ fprintf(stderr, "failed to load BPF object: %d\n", err);
+ goto cleanup;
+ }
+
+ err = runqslower_bpf__attach(obj);
+ if (err) {
+ fprintf(stderr, "failed to attach BPF programs\n");
+ goto cleanup;
+ }
+
+ printf("Tracing run queue latency higher than %llu us\n", env.min_us);
+ printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)");
+
+ pb_opts.sample_cb = handle_event;
+ pb_opts.lost_cb = handle_lost_events;
+ pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts);
+ err = libbpf_get_error(pb);
+ if (err) {
+ pb = NULL;
+ fprintf(stderr, "failed to open perf buffer: %d\n", err);
+ goto cleanup;
+ }
+
+ while ((err = perf_buffer__poll(pb, 100)) >= 0)
+ ;
+ printf("Error polling perf buffer: %d\n", err);
+
+cleanup:
+ perf_buffer__free(pb);
+ runqslower_bpf__destroy(obj);
+
+ return err != 0;
+}
diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h
new file mode 100644
index 0000000..9db2254
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __RUNQSLOWER_H
+#define __RUNQSLOWER_H
+
+#define TASK_COMM_LEN 16
+
+struct event {
+ char task[TASK_COMM_LEN];
+ __u64 delta_us;
+ pid_t pid;
+};
+
+#endif /* __RUNQSLOWER_H */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7df436d..f1d74a2 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -107,6 +107,10 @@ enum bpf_cmd {
BPF_MAP_LOOKUP_AND_DELETE_ELEM,
BPF_MAP_FREEZE,
BPF_BTF_GET_NEXT_ID,
+ BPF_MAP_LOOKUP_BATCH,
+ BPF_MAP_LOOKUP_AND_DELETE_BATCH,
+ BPF_MAP_UPDATE_BATCH,
+ BPF_MAP_DELETE_BATCH,
};
enum bpf_map_type {
@@ -136,6 +140,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_STACK,
BPF_MAP_TYPE_SK_STORAGE,
BPF_MAP_TYPE_DEVMAP_HASH,
+ BPF_MAP_TYPE_STRUCT_OPS,
};
/* Note that tracing related programs such as
@@ -174,6 +179,8 @@ enum bpf_prog_type {
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
BPF_PROG_TYPE_CGROUP_SOCKOPT,
BPF_PROG_TYPE_TRACING,
+ BPF_PROG_TYPE_STRUCT_OPS,
+ BPF_PROG_TYPE_EXT,
};
enum bpf_attach_type {
@@ -357,7 +364,12 @@ enum bpf_attach_type {
/* Enable memory-mapping BPF map */
#define BPF_F_MMAPABLE (1U << 10)
-/* flags for BPF_PROG_QUERY */
+/* Flags for BPF_PROG_QUERY. */
+
+/* Query effective (directly attached + inherited from ancestor cgroups)
+ * programs that will be executed for events within a cgroup.
+ * attach_flags with this flag are returned only for directly attached programs.
+ */
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
enum bpf_stack_build_id_status {
@@ -397,6 +409,10 @@ union bpf_attr {
__u32 btf_fd; /* fd pointing to a BTF type data */
__u32 btf_key_type_id; /* BTF type_id of the key */
__u32 btf_value_type_id; /* BTF type_id of the value */
+ __u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel-
+ * struct stored as the
+ * map value
+ */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -409,6 +425,23 @@ union bpf_attr {
__u64 flags;
};
+ struct { /* struct used by BPF_MAP_*_BATCH commands */
+ __aligned_u64 in_batch; /* start batch,
+ * NULL to start from beginning
+ */
+ __aligned_u64 out_batch; /* output: next start batch */
+ __aligned_u64 keys;
+ __aligned_u64 values;
+ __u32 count; /* input/output:
+ * input: # of key/value
+ * elements
+ * output: # of filled elements
+ */
+ __u32 map_fd;
+ __u64 elem_flags;
+ __u64 flags;
+ } batch;
+
struct { /* anonymous struct used by BPF_PROG_LOAD command */
__u32 prog_type; /* one of enum bpf_prog_type */
__u32 insn_cnt;
@@ -2703,7 +2736,8 @@ union bpf_attr {
*
* int bpf_send_signal(u32 sig)
* Description
- * Send signal *sig* to the current task.
+ * Send signal *sig* to the process of the current task.
+ * The signal may be delivered to any of this process's threads.
* Return
* 0 on success or successfully queued.
*
@@ -2831,6 +2865,33 @@ union bpf_attr {
* Return
* On success, the strictly positive length of the string, including
* the trailing NUL character. On error, a negative value.
+ *
+ * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
+ * Description
+ * Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
+ * *rcv_nxt* is the ack_seq to be sent out.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_send_signal_thread(u32 sig)
+ * Description
+ * Send signal *sig* to the thread corresponding to the current task.
+ * Return
+ * 0 on success or successfully queued.
+ *
+ * **-EBUSY** if work queue under nmi is full.
+ *
+ * **-EINVAL** if *sig* is invalid.
+ *
+ * **-EPERM** if no permission to send the *sig*.
+ *
+ * **-EAGAIN** if bpf program can try again.
+ *
+ * u64 bpf_jiffies64(void)
+ * Description
+ * Obtain the 64bit jiffies
+ * Return
+ * The 64 bit jiffies
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2948,7 +3009,10 @@ union bpf_attr {
FN(probe_read_user), \
FN(probe_read_kernel), \
FN(probe_read_user_str), \
- FN(probe_read_kernel_str),
+ FN(probe_read_kernel_str), \
+ FN(tcp_send_ack), \
+ FN(send_signal_thread), \
+ FN(jiffies64),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -3349,7 +3413,7 @@ struct bpf_map_info {
__u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
- __u32 :32;
+ __u32 btf_vmlinux_value_type_id;
__u64 netns_dev;
__u64 netns_ino;
__u32 btf_id;
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 1a2898c..5a66710 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -146,6 +146,12 @@ enum {
BTF_VAR_GLOBAL_EXTERN = 2,
};
+enum btf_func_linkage {
+ BTF_FUNC_STATIC = 0,
+ BTF_FUNC_GLOBAL = 1,
+ BTF_FUNC_EXTERN = 2,
+};
+
/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
* additional information related to the variable such as its linkage.
*/
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 8aec876..024af2d1 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -169,6 +169,7 @@ enum {
IFLA_MAX_MTU,
IFLA_PROP_LIST,
IFLA_ALT_IFNAME, /* Alternative ifname */
+ IFLA_PERM_ADDRESS,
__IFLA_MAX
};
@@ -485,6 +486,13 @@ enum macsec_validation_type {
MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1,
};
+enum macsec_offload {
+ MACSEC_OFFLOAD_OFF = 0,
+ MACSEC_OFFLOAD_PHY = 1,
+ __MACSEC_OFFLOAD_END,
+ MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_END - 1,
+};
+
/* IPVLAN section */
enum {
IFLA_IPVLAN_UNSPEC,
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index e7ad9d3..1521073 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -76,6 +76,8 @@ enum {
#define IPPROTO_MPLS IPPROTO_MPLS
IPPROTO_RAW = 255, /* Raw IP packets */
#define IPPROTO_RAW IPPROTO_RAW
+ IPPROTO_MPTCP = 262, /* Multipath TCP connection */
+#define IPPROTO_MPTCP IPPROTO_MPTCP
IPPROTO_MAX
};
#endif
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index d87830e..aee7f1a 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -183,7 +183,7 @@
$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
$(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
- $(Q)$(srctree)/scripts/bpf_helpers_doc.py --header \
+ $(QUIET_GEN)$(srctree)/scripts/bpf_helpers_doc.py --header \
--file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS)
$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
@@ -273,10 +273,11 @@
$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
clean:
- $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \
- *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \
- *.pc LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \
- $(SHARED_OBJDIR) $(STATIC_OBJDIR)
+ $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \
+ *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \
+ $(SHARED_OBJDIR) $(STATIC_OBJDIR) \
+ $(addprefix $(OUTPUT), \
+ *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc)
$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index a787d53..c6dafe5 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -32,6 +32,9 @@
#include "libbpf.h"
#include "libbpf_internal.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
/*
* When building perf, unistd.h is overridden. __NR_bpf is
* required to be defined explicitly.
@@ -95,7 +98,11 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
attr.btf_key_type_id = create_attr->btf_key_type_id;
attr.btf_value_type_id = create_attr->btf_value_type_id;
attr.map_ifindex = create_attr->map_ifindex;
- attr.inner_map_fd = create_attr->inner_map_fd;
+ if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS)
+ attr.btf_vmlinux_value_type_id =
+ create_attr->btf_vmlinux_value_type_id;
+ else
+ attr.inner_map_fd = create_attr->inner_map_fd;
return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}
@@ -228,7 +235,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
memset(&attr, 0, sizeof(attr));
attr.prog_type = load_attr->prog_type;
attr.expected_attach_type = load_attr->expected_attach_type;
- if (attr.prog_type == BPF_PROG_TYPE_TRACING) {
+ if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS) {
+ attr.attach_btf_id = load_attr->attach_btf_id;
+ } else if (attr.prog_type == BPF_PROG_TYPE_TRACING ||
+ attr.prog_type == BPF_PROG_TYPE_EXT) {
attr.attach_btf_id = load_attr->attach_btf_id;
attr.attach_prog_fd = load_attr->attach_prog_fd;
} else {
@@ -443,6 +453,64 @@ int bpf_map_freeze(int fd)
return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
}
+static int bpf_map_batch_common(int cmd, int fd, void *in_batch,
+ void *out_batch, void *keys, void *values,
+ __u32 *count,
+ const struct bpf_map_batch_opts *opts)
+{
+ union bpf_attr attr;
+ int ret;
+
+ if (!OPTS_VALID(opts, bpf_map_batch_opts))
+ return -EINVAL;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.batch.map_fd = fd;
+ attr.batch.in_batch = ptr_to_u64(in_batch);
+ attr.batch.out_batch = ptr_to_u64(out_batch);
+ attr.batch.keys = ptr_to_u64(keys);
+ attr.batch.values = ptr_to_u64(values);
+ attr.batch.count = *count;
+ attr.batch.elem_flags = OPTS_GET(opts, elem_flags, 0);
+ attr.batch.flags = OPTS_GET(opts, flags, 0);
+
+ ret = sys_bpf(cmd, &attr, sizeof(attr));
+ *count = attr.batch.count;
+
+ return ret;
+}
+
+int bpf_map_delete_batch(int fd, void *keys, __u32 *count,
+ const struct bpf_map_batch_opts *opts)
+{
+ return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL,
+ NULL, keys, NULL, count, opts);
+}
+
+int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys,
+ void *values, __u32 *count,
+ const struct bpf_map_batch_opts *opts)
+{
+ return bpf_map_batch_common(BPF_MAP_LOOKUP_BATCH, fd, in_batch,
+ out_batch, keys, values, count, opts);
+}
+
+int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch,
+ void *keys, void *values, __u32 *count,
+ const struct bpf_map_batch_opts *opts)
+{
+ return bpf_map_batch_common(BPF_MAP_LOOKUP_AND_DELETE_BATCH,
+ fd, in_batch, out_batch, keys, values,
+ count, opts);
+}
+
+int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count,
+ const struct bpf_map_batch_opts *opts)
+{
+ return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL,
+ keys, values, count, opts);
+}
+
int bpf_obj_pin(int fd, const char *pathname)
{
union bpf_attr attr;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index f0ab851..b976e77 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -46,7 +46,10 @@ struct bpf_create_map_attr {
__u32 btf_key_type_id;
__u32 btf_value_type_id;
__u32 map_ifindex;
- __u32 inner_map_fd;
+ union {
+ __u32 inner_map_fd;
+ __u32 btf_vmlinux_value_type_id;
+ };
};
LIBBPF_API int
@@ -124,6 +127,28 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
LIBBPF_API int bpf_map_freeze(int fd);
+
+struct bpf_map_batch_opts {
+ size_t sz; /* size of this struct for forward/backward compatibility */
+ __u64 elem_flags;
+ __u64 flags;
+};
+#define bpf_map_batch_opts__last_field flags
+
+LIBBPF_API int bpf_map_delete_batch(int fd, void *keys,
+ __u32 *count,
+ const struct bpf_map_batch_opts *opts);
+LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch,
+ void *keys, void *values, __u32 *count,
+ const struct bpf_map_batch_opts *opts);
+LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch,
+ void *out_batch, void *keys,
+ void *values, __u32 *count,
+ const struct bpf_map_batch_opts *opts);
+LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values,
+ __u32 *count,
+ const struct bpf_map_batch_opts *opts);
+
LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
LIBBPF_API int bpf_obj_get(const char *pathname);
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 3ed1a27..bafca49 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -8,6 +8,9 @@
#include "libbpf.h"
#include "libbpf_internal.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
struct bpf_prog_linfo {
void *raw_linfo;
void *raw_jited_linfo;
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 5f04f56..3d1c25f 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -8,6 +8,10 @@
#include <fcntl.h>
#include <unistd.h>
#include <errno.h>
+#include <sys/utsname.h>
+#include <sys/param.h>
+#include <sys/stat.h>
+#include <linux/kernel.h>
#include <linux/err.h>
#include <linux/btf.h>
#include <gelf.h>
@@ -17,8 +21,11 @@
#include "libbpf_internal.h"
#include "hashmap.h"
-#define BTF_MAX_NR_TYPES 0x7fffffff
-#define BTF_MAX_STR_OFFSET 0x7fffffff
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+#define BTF_MAX_NR_TYPES 0x7fffffffU
+#define BTF_MAX_STR_OFFSET 0x7fffffffU
static struct btf_type btf_void;
@@ -50,7 +57,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t)
if (btf->types_size == BTF_MAX_NR_TYPES)
return -E2BIG;
- expand_by = max(btf->types_size >> 2, 16);
+ expand_by = max(btf->types_size >> 2, 16U);
new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by);
new_types = realloc(btf->types, sizeof(*new_types) * new_size);
@@ -286,7 +293,7 @@ int btf__align_of(const struct btf *btf, __u32 id)
switch (kind) {
case BTF_KIND_INT:
case BTF_KIND_ENUM:
- return min(sizeof(void *), t->size);
+ return min(sizeof(void *), (size_t)t->size);
case BTF_KIND_PTR:
return sizeof(void *);
case BTF_KIND_TYPEDEF:
@@ -1398,7 +1405,7 @@ static int btf_dedup_hypot_map_add(struct btf_dedup *d,
if (d->hypot_cnt == d->hypot_cap) {
__u32 *new_list;
- d->hypot_cap += max(16, d->hypot_cap / 2);
+ d->hypot_cap += max((size_t)16, d->hypot_cap / 2);
new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap);
if (!new_list)
return -ENOMEM;
@@ -1694,7 +1701,7 @@ static int btf_dedup_strings(struct btf_dedup *d)
if (strs.cnt + 1 > strs.cap) {
struct btf_str_ptr *new_ptrs;
- strs.cap += max(strs.cnt / 2, 16);
+ strs.cap += max(strs.cnt / 2, 16U);
new_ptrs = realloc(strs.ptrs,
sizeof(strs.ptrs[0]) * strs.cap);
if (!new_ptrs) {
@@ -2928,3 +2935,89 @@ static int btf_dedup_remap_types(struct btf_dedup *d)
}
return 0;
}
+
+static struct btf *btf_load_raw(const char *path)
+{
+ struct btf *btf;
+ size_t read_cnt;
+ struct stat st;
+ void *data;
+ FILE *f;
+
+ if (stat(path, &st))
+ return ERR_PTR(-errno);
+
+ data = malloc(st.st_size);
+ if (!data)
+ return ERR_PTR(-ENOMEM);
+
+ f = fopen(path, "rb");
+ if (!f) {
+ btf = ERR_PTR(-errno);
+ goto cleanup;
+ }
+
+ read_cnt = fread(data, 1, st.st_size, f);
+ fclose(f);
+ if (read_cnt < st.st_size) {
+ btf = ERR_PTR(-EBADF);
+ goto cleanup;
+ }
+
+ btf = btf__new(data, read_cnt);
+
+cleanup:
+ free(data);
+ return btf;
+}
+
+/*
+ * Probe few well-known locations for vmlinux kernel image and try to load BTF
+ * data out of it to use for target BTF.
+ */
+struct btf *libbpf_find_kernel_btf(void)
+{
+ struct {
+ const char *path_fmt;
+ bool raw_btf;
+ } locations[] = {
+ /* try canonical vmlinux BTF through sysfs first */
+ { "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
+ /* fall back to trying to find vmlinux ELF on disk otherwise */
+ { "/boot/vmlinux-%1$s" },
+ { "/lib/modules/%1$s/vmlinux-%1$s" },
+ { "/lib/modules/%1$s/build/vmlinux" },
+ { "/usr/lib/modules/%1$s/kernel/vmlinux" },
+ { "/usr/lib/debug/boot/vmlinux-%1$s" },
+ { "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
+ { "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
+ };
+ char path[PATH_MAX + 1];
+ struct utsname buf;
+ struct btf *btf;
+ int i;
+
+ uname(&buf);
+
+ for (i = 0; i < ARRAY_SIZE(locations); i++) {
+ snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
+
+ if (access(path, R_OK))
+ continue;
+
+ if (locations[i].raw_btf)
+ btf = btf_load_raw(path);
+ else
+ btf = btf__parse_elf(path, NULL);
+
+ pr_debug("loading kernel BTF '%s': %ld\n",
+ path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
+ if (IS_ERR(btf))
+ continue;
+
+ return btf;
+ }
+
+ pr_warn("failed to find valid kernel BTF\n");
+ return ERR_PTR(-ESRCH);
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 8d73f7f5..70c1b7e 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -102,6 +102,8 @@ LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf,
LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
+LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
+
struct btf_dedup_opts {
unsigned int dedup_table_size;
bool dont_resolve_fwds;
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index e95f771..bd09ed1 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -18,6 +18,9 @@
#include "libbpf.h"
#include "libbpf_internal.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
@@ -139,6 +142,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf,
if (IS_ERR(d->type_names)) {
err = PTR_ERR(d->type_names);
d->type_names = NULL;
+ goto err;
}
d->ident_names = hashmap__new(str_hash_fn, str_equal_fn, NULL);
if (IS_ERR(d->ident_names)) {
diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c
index 6122272..54c30c8 100644
--- a/tools/lib/bpf/hashmap.c
+++ b/tools/lib/bpf/hashmap.c
@@ -12,6 +12,9 @@
#include <linux/err.h>
#include "hashmap.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
/* start with 4 buckets */
#define HASHMAP_MIN_CAP_BITS 2
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7513165..ae34b68 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -55,6 +55,9 @@
#include "libbpf_internal.h"
#include "hashmap.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
#ifndef EM_BPF
#define EM_BPF 247
#endif
@@ -70,6 +73,12 @@
#define __printf(a, b) __attribute__((format(printf, a, b)))
+static struct bpf_map *bpf_object__add_map(struct bpf_object *obj);
+static struct bpf_program *bpf_object__find_prog_by_idx(struct bpf_object *obj,
+ int idx);
+static const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
+
static int __base_pr(enum libbpf_print_level level, const char *format,
va_list args)
{
@@ -166,6 +175,8 @@ struct bpf_capabilities {
__u32 btf_datasec:1;
/* BPF_F_MMAPABLE is supported for arrays */
__u32 array_mmap:1;
+ /* BTF_FUNC_GLOBAL is supported */
+ __u32 btf_func_global:1;
};
enum reloc_type {
@@ -229,10 +240,32 @@ struct bpf_program {
__u32 prog_flags;
};
+struct bpf_struct_ops {
+ const char *tname;
+ const struct btf_type *type;
+ struct bpf_program **progs;
+ __u32 *kern_func_off;
+ /* e.g. struct tcp_congestion_ops in bpf_prog's btf format */
+ void *data;
+ /* e.g. struct bpf_struct_ops_tcp_congestion_ops in
+ * btf_vmlinux's format.
+ * struct bpf_struct_ops_tcp_congestion_ops {
+ * [... some other kernel fields ...]
+ * struct tcp_congestion_ops data;
+ * }
+ * kern_vdata-size == sizeof(struct bpf_struct_ops_tcp_congestion_ops)
+ * bpf_map__init_kern_struct_ops() will populate the "kern_vdata"
+ * from "data".
+ */
+ void *kern_vdata;
+ __u32 type_id;
+};
+
#define DATA_SEC ".data"
#define BSS_SEC ".bss"
#define RODATA_SEC ".rodata"
#define KCONFIG_SEC ".kconfig"
+#define STRUCT_OPS_SEC ".struct_ops"
enum libbpf_map_type {
LIBBPF_MAP_UNSPEC,
@@ -259,10 +292,12 @@ struct bpf_map {
struct bpf_map_def def;
__u32 btf_key_type_id;
__u32 btf_value_type_id;
+ __u32 btf_vmlinux_value_type_id;
void *priv;
bpf_map_clear_priv_t clear_priv;
enum libbpf_map_type libbpf_type;
void *mmaped;
+ struct bpf_struct_ops *st_ops;
char *pin_path;
bool pinned;
bool reused;
@@ -326,6 +361,7 @@ struct bpf_object {
Elf_Data *data;
Elf_Data *rodata;
Elf_Data *bss;
+ Elf_Data *st_ops_data;
size_t strtabidx;
struct {
GElf_Shdr shdr;
@@ -339,6 +375,7 @@ struct bpf_object {
int data_shndx;
int rodata_shndx;
int bss_shndx;
+ int st_ops_shndx;
} efile;
/*
* All loaded bpf_object is linked in a list, which is
@@ -348,6 +385,10 @@ struct bpf_object {
struct list_head list;
struct btf *btf;
+ /* Parse and load BTF vmlinux if any of the programs in the object need
+ * it at load time.
+ */
+ struct btf *btf_vmlinux;
struct btf_ext *btf_ext;
void *priv;
@@ -566,6 +607,348 @@ static __u32 get_kernel_version(void)
return KERNEL_VERSION(major, minor, patch);
}
+static const struct btf_member *
+find_member_by_offset(const struct btf_type *t, __u32 bit_offset)
+{
+ struct btf_member *m;
+ int i;
+
+ for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+ if (btf_member_bit_offset(t, i) == bit_offset)
+ return m;
+ }
+
+ return NULL;
+}
+
+static const struct btf_member *
+find_member_by_name(const struct btf *btf, const struct btf_type *t,
+ const char *name)
+{
+ struct btf_member *m;
+ int i;
+
+ for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+ if (!strcmp(btf__name_by_offset(btf, m->name_off), name))
+ return m;
+ }
+
+ return NULL;
+}
+
+#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_"
+static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
+ const char *name, __u32 kind);
+
+static int
+find_struct_ops_kern_types(const struct btf *btf, const char *tname,
+ const struct btf_type **type, __u32 *type_id,
+ const struct btf_type **vtype, __u32 *vtype_id,
+ const struct btf_member **data_member)
+{
+ const struct btf_type *kern_type, *kern_vtype;
+ const struct btf_member *kern_data_member;
+ __s32 kern_vtype_id, kern_type_id;
+ __u32 i;
+
+ kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+ if (kern_type_id < 0) {
+ pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n",
+ tname);
+ return kern_type_id;
+ }
+ kern_type = btf__type_by_id(btf, kern_type_id);
+
+ /* Find the corresponding "map_value" type that will be used
+ * in map_update(BPF_MAP_TYPE_STRUCT_OPS). For example,
+ * find "struct bpf_struct_ops_tcp_congestion_ops" from the
+ * btf_vmlinux.
+ */
+ kern_vtype_id = find_btf_by_prefix_kind(btf, STRUCT_OPS_VALUE_PREFIX,
+ tname, BTF_KIND_STRUCT);
+ if (kern_vtype_id < 0) {
+ pr_warn("struct_ops init_kern: struct %s%s is not found in kernel BTF\n",
+ STRUCT_OPS_VALUE_PREFIX, tname);
+ return kern_vtype_id;
+ }
+ kern_vtype = btf__type_by_id(btf, kern_vtype_id);
+
+ /* Find "struct tcp_congestion_ops" from
+ * struct bpf_struct_ops_tcp_congestion_ops {
+ * [ ... ]
+ * struct tcp_congestion_ops data;
+ * }
+ */
+ kern_data_member = btf_members(kern_vtype);
+ for (i = 0; i < btf_vlen(kern_vtype); i++, kern_data_member++) {
+ if (kern_data_member->type == kern_type_id)
+ break;
+ }
+ if (i == btf_vlen(kern_vtype)) {
+ pr_warn("struct_ops init_kern: struct %s data is not found in struct %s%s\n",
+ tname, STRUCT_OPS_VALUE_PREFIX, tname);
+ return -EINVAL;
+ }
+
+ *type = kern_type;
+ *type_id = kern_type_id;
+ *vtype = kern_vtype;
+ *vtype_id = kern_vtype_id;
+ *data_member = kern_data_member;
+
+ return 0;
+}
+
+static bool bpf_map__is_struct_ops(const struct bpf_map *map)
+{
+ return map->def.type == BPF_MAP_TYPE_STRUCT_OPS;
+}
+
+/* Init the map's fields that depend on kern_btf */
+static int bpf_map__init_kern_struct_ops(struct bpf_map *map,
+ const struct btf *btf,
+ const struct btf *kern_btf)
+{
+ const struct btf_member *member, *kern_member, *kern_data_member;
+ const struct btf_type *type, *kern_type, *kern_vtype;
+ __u32 i, kern_type_id, kern_vtype_id, kern_data_off;
+ struct bpf_struct_ops *st_ops;
+ void *data, *kern_data;
+ const char *tname;
+ int err;
+
+ st_ops = map->st_ops;
+ type = st_ops->type;
+ tname = st_ops->tname;
+ err = find_struct_ops_kern_types(kern_btf, tname,
+ &kern_type, &kern_type_id,
+ &kern_vtype, &kern_vtype_id,
+ &kern_data_member);
+ if (err)
+ return err;
+
+ pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n",
+ map->name, st_ops->type_id, kern_type_id, kern_vtype_id);
+
+ map->def.value_size = kern_vtype->size;
+ map->btf_vmlinux_value_type_id = kern_vtype_id;
+
+ st_ops->kern_vdata = calloc(1, kern_vtype->size);
+ if (!st_ops->kern_vdata)
+ return -ENOMEM;
+
+ data = st_ops->data;
+ kern_data_off = kern_data_member->offset / 8;
+ kern_data = st_ops->kern_vdata + kern_data_off;
+
+ member = btf_members(type);
+ for (i = 0; i < btf_vlen(type); i++, member++) {
+ const struct btf_type *mtype, *kern_mtype;
+ __u32 mtype_id, kern_mtype_id;
+ void *mdata, *kern_mdata;
+ __s64 msize, kern_msize;
+ __u32 moff, kern_moff;
+ __u32 kern_member_idx;
+ const char *mname;
+
+ mname = btf__name_by_offset(btf, member->name_off);
+ kern_member = find_member_by_name(kern_btf, kern_type, mname);
+ if (!kern_member) {
+ pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n",
+ map->name, mname);
+ return -ENOTSUP;
+ }
+
+ kern_member_idx = kern_member - btf_members(kern_type);
+ if (btf_member_bitfield_size(type, i) ||
+ btf_member_bitfield_size(kern_type, kern_member_idx)) {
+ pr_warn("struct_ops init_kern %s: bitfield %s is not supported\n",
+ map->name, mname);
+ return -ENOTSUP;
+ }
+
+ moff = member->offset / 8;
+ kern_moff = kern_member->offset / 8;
+
+ mdata = data + moff;
+ kern_mdata = kern_data + kern_moff;
+
+ mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id);
+ kern_mtype = skip_mods_and_typedefs(kern_btf, kern_member->type,
+ &kern_mtype_id);
+ if (BTF_INFO_KIND(mtype->info) !=
+ BTF_INFO_KIND(kern_mtype->info)) {
+ pr_warn("struct_ops init_kern %s: Unmatched member type %s %u != %u(kernel)\n",
+ map->name, mname, BTF_INFO_KIND(mtype->info),
+ BTF_INFO_KIND(kern_mtype->info));
+ return -ENOTSUP;
+ }
+
+ if (btf_is_ptr(mtype)) {
+ struct bpf_program *prog;
+
+ mtype = skip_mods_and_typedefs(btf, mtype->type, &mtype_id);
+ kern_mtype = skip_mods_and_typedefs(kern_btf,
+ kern_mtype->type,
+ &kern_mtype_id);
+ if (!btf_is_func_proto(mtype) ||
+ !btf_is_func_proto(kern_mtype)) {
+ pr_warn("struct_ops init_kern %s: non func ptr %s is not supported\n",
+ map->name, mname);
+ return -ENOTSUP;
+ }
+
+ prog = st_ops->progs[i];
+ if (!prog) {
+ pr_debug("struct_ops init_kern %s: func ptr %s is not set\n",
+ map->name, mname);
+ continue;
+ }
+
+ prog->attach_btf_id = kern_type_id;
+ prog->expected_attach_type = kern_member_idx;
+
+ st_ops->kern_func_off[i] = kern_data_off + kern_moff;
+
+ pr_debug("struct_ops init_kern %s: func ptr %s is set to prog %s from data(+%u) to kern_data(+%u)\n",
+ map->name, mname, prog->name, moff,
+ kern_moff);
+
+ continue;
+ }
+
+ msize = btf__resolve_size(btf, mtype_id);
+ kern_msize = btf__resolve_size(kern_btf, kern_mtype_id);
+ if (msize < 0 || kern_msize < 0 || msize != kern_msize) {
+ pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n",
+ map->name, mname, (ssize_t)msize,
+ (ssize_t)kern_msize);
+ return -ENOTSUP;
+ }
+
+ pr_debug("struct_ops init_kern %s: copy %s %u bytes from data(+%u) to kern_data(+%u)\n",
+ map->name, mname, (unsigned int)msize,
+ moff, kern_moff);
+ memcpy(kern_mdata, mdata, msize);
+ }
+
+ return 0;
+}
+
+static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj)
+{
+ struct bpf_map *map;
+ size_t i;
+ int err;
+
+ for (i = 0; i < obj->nr_maps; i++) {
+ map = &obj->maps[i];
+
+ if (!bpf_map__is_struct_ops(map))
+ continue;
+
+ err = bpf_map__init_kern_struct_ops(map, obj->btf,
+ obj->btf_vmlinux);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
+{
+ const struct btf_type *type, *datasec;
+ const struct btf_var_secinfo *vsi;
+ struct bpf_struct_ops *st_ops;
+ const char *tname, *var_name;
+ __s32 type_id, datasec_id;
+ const struct btf *btf;
+ struct bpf_map *map;
+ __u32 i;
+
+ if (obj->efile.st_ops_shndx == -1)
+ return 0;
+
+ btf = obj->btf;
+ datasec_id = btf__find_by_name_kind(btf, STRUCT_OPS_SEC,
+ BTF_KIND_DATASEC);
+ if (datasec_id < 0) {
+ pr_warn("struct_ops init: DATASEC %s not found\n",
+ STRUCT_OPS_SEC);
+ return -EINVAL;
+ }
+
+ datasec = btf__type_by_id(btf, datasec_id);
+ vsi = btf_var_secinfos(datasec);
+ for (i = 0; i < btf_vlen(datasec); i++, vsi++) {
+ type = btf__type_by_id(obj->btf, vsi->type);
+ var_name = btf__name_by_offset(obj->btf, type->name_off);
+
+ type_id = btf__resolve_type(obj->btf, vsi->type);
+ if (type_id < 0) {
+ pr_warn("struct_ops init: Cannot resolve var type_id %u in DATASEC %s\n",
+ vsi->type, STRUCT_OPS_SEC);
+ return -EINVAL;
+ }
+
+ type = btf__type_by_id(obj->btf, type_id);
+ tname = btf__name_by_offset(obj->btf, type->name_off);
+ if (!tname[0]) {
+ pr_warn("struct_ops init: anonymous type is not supported\n");
+ return -ENOTSUP;
+ }
+ if (!btf_is_struct(type)) {
+ pr_warn("struct_ops init: %s is not a struct\n", tname);
+ return -EINVAL;
+ }
+
+ map = bpf_object__add_map(obj);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ map->sec_idx = obj->efile.st_ops_shndx;
+ map->sec_offset = vsi->offset;
+ map->name = strdup(var_name);
+ if (!map->name)
+ return -ENOMEM;
+
+ map->def.type = BPF_MAP_TYPE_STRUCT_OPS;
+ map->def.key_size = sizeof(int);
+ map->def.value_size = type->size;
+ map->def.max_entries = 1;
+
+ map->st_ops = calloc(1, sizeof(*map->st_ops));
+ if (!map->st_ops)
+ return -ENOMEM;
+ st_ops = map->st_ops;
+ st_ops->data = malloc(type->size);
+ st_ops->progs = calloc(btf_vlen(type), sizeof(*st_ops->progs));
+ st_ops->kern_func_off = malloc(btf_vlen(type) *
+ sizeof(*st_ops->kern_func_off));
+ if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off)
+ return -ENOMEM;
+
+ if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) {
+ pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n",
+ var_name, STRUCT_OPS_SEC);
+ return -EINVAL;
+ }
+
+ memcpy(st_ops->data,
+ obj->efile.st_ops_data->d_buf + vsi->offset,
+ type->size);
+ st_ops->tname = tname;
+ st_ops->type = type;
+ st_ops->type_id = type_id;
+
+ pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n",
+ tname, type_id, var_name, vsi->offset);
+ }
+
+ return 0;
+}
+
static struct bpf_object *bpf_object__new(const char *path,
const void *obj_buf,
size_t obj_buf_sz,
@@ -607,6 +990,7 @@ static struct bpf_object *bpf_object__new(const char *path,
obj->efile.data_shndx = -1;
obj->efile.rodata_shndx = -1;
obj->efile.bss_shndx = -1;
+ obj->efile.st_ops_shndx = -1;
obj->kconfig_map_idx = -1;
obj->kern_version = get_kernel_version();
@@ -630,6 +1014,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
obj->efile.data = NULL;
obj->efile.rodata = NULL;
obj->efile.bss = NULL;
+ obj->efile.st_ops_data = NULL;
zfree(&obj->efile.reloc_sects);
obj->efile.nr_reloc_sects = 0;
@@ -735,16 +1120,6 @@ bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size)
return 0;
}
-static int compare_bpf_map(const void *_a, const void *_b)
-{
- const struct bpf_map *a = _a;
- const struct bpf_map *b = _b;
-
- if (a->sec_idx != b->sec_idx)
- return a->sec_idx - b->sec_idx;
- return a->sec_offset - b->sec_offset;
-}
-
static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
{
if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
@@ -815,6 +1190,9 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name,
} else if (!strcmp(name, RODATA_SEC)) {
if (obj->efile.rodata)
*size = obj->efile.rodata->d_size;
+ } else if (!strcmp(name, STRUCT_OPS_SEC)) {
+ if (obj->efile.st_ops_data)
+ *size = obj->efile.st_ops_data->d_size;
} else {
ret = bpf_object_search_section_size(obj, name, &d_size);
if (!ret)
@@ -898,7 +1276,7 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map)
long page_sz = sysconf(_SC_PAGE_SIZE);
size_t map_sz;
- map_sz = roundup(map->def.value_size, 8) * map->def.max_entries;
+ map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries;
map_sz = roundup(map_sz, page_sz);
return map_sz;
}
@@ -1440,6 +1818,20 @@ skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id)
return t;
}
+static const struct btf_type *
+resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id)
+{
+ const struct btf_type *t;
+
+ t = skip_mods_and_typedefs(btf, id, NULL);
+ if (!btf_is_ptr(t))
+ return NULL;
+
+ t = skip_mods_and_typedefs(btf, t->type, res_id);
+
+ return btf_is_func_proto(t) ? t : NULL;
+}
+
/*
* Fetch integer attribute of BTF map definition. Such attributes are
* represented using a pointer to an array, in which dimensionality of array
@@ -1787,13 +2179,10 @@ static int bpf_object__init_maps(struct bpf_object *obj,
err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path);
err = err ?: bpf_object__init_global_data_maps(obj);
err = err ?: bpf_object__init_kconfig_map(obj);
+ err = err ?: bpf_object__init_struct_ops_maps(obj);
if (err)
return err;
- if (obj->nr_maps) {
- qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
- compare_bpf_map);
- }
return 0;
}
@@ -1817,13 +2206,14 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx)
static void bpf_object__sanitize_btf(struct bpf_object *obj)
{
+ bool has_func_global = obj->caps.btf_func_global;
bool has_datasec = obj->caps.btf_datasec;
bool has_func = obj->caps.btf_func;
struct btf *btf = obj->btf;
struct btf_type *t;
int i, j, vlen;
- if (!obj->btf || (has_func && has_datasec))
+ if (!obj->btf || (has_func && has_datasec && has_func_global))
return;
for (i = 1; i <= btf__get_nr_types(btf); i++) {
@@ -1871,6 +2261,9 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj)
} else if (!has_func && btf_is_func(t)) {
/* replace FUNC with TYPEDEF */
t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0);
+ } else if (!has_func_global && btf_is_func(t)) {
+ /* replace BTF_FUNC_GLOBAL with BTF_FUNC_STATIC */
+ t->info = BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0);
}
}
}
@@ -1889,23 +2282,26 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
{
return obj->efile.btf_maps_shndx >= 0 ||
- obj->nr_extern > 0;
+ obj->efile.st_ops_shndx >= 0 ||
+ obj->nr_extern > 0;
}
static int bpf_object__init_btf(struct bpf_object *obj,
Elf_Data *btf_data,
Elf_Data *btf_ext_data)
{
- bool btf_required = bpf_object__is_btf_mandatory(obj);
- int err = 0;
+ int err = -ENOENT;
if (btf_data) {
obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
if (IS_ERR(obj->btf)) {
+ err = PTR_ERR(obj->btf);
+ obj->btf = NULL;
pr_warn("Error loading ELF section %s: %d.\n",
BTF_ELF_SEC, err);
goto out;
}
+ err = 0;
}
if (btf_ext_data) {
if (!obj->btf) {
@@ -1923,18 +2319,9 @@ static int bpf_object__init_btf(struct bpf_object *obj,
}
}
out:
- if (err || IS_ERR(obj->btf)) {
- if (btf_required)
- err = err ? : PTR_ERR(obj->btf);
- else
- err = 0;
- if (!IS_ERR_OR_NULL(obj->btf))
- btf__free(obj->btf);
- obj->btf = NULL;
- }
- if (btf_required && !obj->btf) {
+ if (err && bpf_object__is_btf_mandatory(obj)) {
pr_warn("BTF is required, but is missing or corrupted.\n");
- return err == 0 ? -ENOENT : err;
+ return err;
}
return 0;
}
@@ -1963,6 +2350,41 @@ static int bpf_object__finalize_btf(struct bpf_object *obj)
return 0;
}
+static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog)
+{
+ if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
+ return true;
+
+ /* BPF_PROG_TYPE_TRACING programs which do not attach to other programs
+ * also need vmlinux BTF
+ */
+ if (prog->type == BPF_PROG_TYPE_TRACING && !prog->attach_prog_fd)
+ return true;
+
+ return false;
+}
+
+static int bpf_object__load_vmlinux_btf(struct bpf_object *obj)
+{
+ struct bpf_program *prog;
+ int err;
+
+ bpf_object__for_each_program(prog, obj) {
+ if (libbpf_prog_needs_vmlinux_btf(prog)) {
+ obj->btf_vmlinux = libbpf_find_kernel_btf();
+ if (IS_ERR(obj->btf_vmlinux)) {
+ err = PTR_ERR(obj->btf_vmlinux);
+ pr_warn("Error loading vmlinux BTF: %d\n", err);
+ obj->btf_vmlinux = NULL;
+ return err;
+ }
+ return 0;
+ }
+ }
+
+ return 0;
+}
+
static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
{
int err = 0;
@@ -2088,6 +2510,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
} else if (strcmp(name, RODATA_SEC) == 0) {
obj->efile.rodata = data;
obj->efile.rodata_shndx = idx;
+ } else if (strcmp(name, STRUCT_OPS_SEC) == 0) {
+ obj->efile.st_ops_data = data;
+ obj->efile.st_ops_shndx = idx;
} else {
pr_debug("skip section(%d) %s\n", idx, name);
}
@@ -2097,7 +2522,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
int sec = sh.sh_info; /* points to other section */
/* Only do relo for section with exec instructions */
- if (!section_have_execinstr(obj, sec)) {
+ if (!section_have_execinstr(obj, sec) &&
+ strcmp(name, ".rel" STRUCT_OPS_SEC)) {
pr_debug("skip relo %s(%d) for section(%d)\n",
name, idx, sec);
continue;
@@ -2599,8 +3025,12 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
__u32 key_type_id = 0, value_type_id = 0;
int ret;
- /* if it's BTF-defined map, we don't need to search for type IDs */
- if (map->sec_idx == obj->efile.btf_maps_shndx)
+ /* if it's BTF-defined map, we don't need to search for type IDs.
+ * For struct_ops map, it does not need btf_key_type_id and
+ * btf_value_type_id.
+ */
+ if (map->sec_idx == obj->efile.btf_maps_shndx ||
+ bpf_map__is_struct_ops(map))
return 0;
if (!bpf_map__is_internal(map)) {
@@ -2804,6 +3234,32 @@ static int bpf_object__probe_btf_func(struct bpf_object *obj)
return 0;
}
+static int bpf_object__probe_btf_func_global(struct bpf_object *obj)
+{
+ static const char strs[] = "\0int\0x\0a";
+ /* static void x(int a) {} */
+ __u32 types[] = {
+ /* int */
+ BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* FUNC_PROTO */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
+ BTF_PARAM_ENC(7, 1),
+ /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */
+ BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
+ };
+ int btf_fd;
+
+ btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types),
+ strs, sizeof(strs));
+ if (btf_fd >= 0) {
+ obj->caps.btf_func_global = 1;
+ close(btf_fd);
+ return 1;
+ }
+
+ return 0;
+}
+
static int bpf_object__probe_btf_datasec(struct bpf_object *obj)
{
static const char strs[] = "\0x\0.data";
@@ -2859,6 +3315,7 @@ bpf_object__probe_caps(struct bpf_object *obj)
bpf_object__probe_name,
bpf_object__probe_global_data,
bpf_object__probe_btf_func,
+ bpf_object__probe_btf_func_global,
bpf_object__probe_btf_datasec,
bpf_object__probe_array_mmap,
};
@@ -3025,6 +3482,9 @@ bpf_object__create_maps(struct bpf_object *obj)
if (bpf_map_type__is_map_in_map(def->type) &&
map->inner_map_fd >= 0)
create_attr.inner_map_fd = map->inner_map_fd;
+ if (bpf_map__is_struct_ops(map))
+ create_attr.btf_vmlinux_value_type_id =
+ map->btf_vmlinux_value_type_id;
if (obj->btf && !bpf_map_find_btf_info(obj, map)) {
create_attr.btf_fd = btf__fd(obj->btf);
@@ -3860,92 +4320,6 @@ static int bpf_core_reloc_insn(struct bpf_program *prog,
return 0;
}
-static struct btf *btf_load_raw(const char *path)
-{
- struct btf *btf;
- size_t read_cnt;
- struct stat st;
- void *data;
- FILE *f;
-
- if (stat(path, &st))
- return ERR_PTR(-errno);
-
- data = malloc(st.st_size);
- if (!data)
- return ERR_PTR(-ENOMEM);
-
- f = fopen(path, "rb");
- if (!f) {
- btf = ERR_PTR(-errno);
- goto cleanup;
- }
-
- read_cnt = fread(data, 1, st.st_size, f);
- fclose(f);
- if (read_cnt < st.st_size) {
- btf = ERR_PTR(-EBADF);
- goto cleanup;
- }
-
- btf = btf__new(data, read_cnt);
-
-cleanup:
- free(data);
- return btf;
-}
-
-/*
- * Probe few well-known locations for vmlinux kernel image and try to load BTF
- * data out of it to use for target BTF.
- */
-static struct btf *bpf_core_find_kernel_btf(void)
-{
- struct {
- const char *path_fmt;
- bool raw_btf;
- } locations[] = {
- /* try canonical vmlinux BTF through sysfs first */
- { "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
- /* fall back to trying to find vmlinux ELF on disk otherwise */
- { "/boot/vmlinux-%1$s" },
- { "/lib/modules/%1$s/vmlinux-%1$s" },
- { "/lib/modules/%1$s/build/vmlinux" },
- { "/usr/lib/modules/%1$s/kernel/vmlinux" },
- { "/usr/lib/debug/boot/vmlinux-%1$s" },
- { "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
- { "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
- };
- char path[PATH_MAX + 1];
- struct utsname buf;
- struct btf *btf;
- int i;
-
- uname(&buf);
-
- for (i = 0; i < ARRAY_SIZE(locations); i++) {
- snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
-
- if (access(path, R_OK))
- continue;
-
- if (locations[i].raw_btf)
- btf = btf_load_raw(path);
- else
- btf = btf__parse_elf(path, NULL);
-
- pr_debug("loading kernel BTF '%s': %ld\n",
- path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
- if (IS_ERR(btf))
- continue;
-
- return btf;
- }
-
- pr_warn("failed to find valid kernel BTF\n");
- return ERR_PTR(-ESRCH);
-}
-
/* Output spec definition in the format:
* [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
* where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
@@ -4180,7 +4554,7 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path)
if (targ_btf_path)
targ_btf = btf__parse_elf(targ_btf_path, NULL);
else
- targ_btf = bpf_core_find_kernel_btf();
+ targ_btf = libbpf_find_kernel_btf();
if (IS_ERR(targ_btf)) {
pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf));
return PTR_ERR(targ_btf);
@@ -4252,13 +4626,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
size_t new_cnt;
int err;
- if (prog->idx == obj->efile.text_shndx) {
- pr_warn("relo in .text insn %d into off %d (insn #%d)\n",
- relo->insn_idx, relo->sym_off, relo->sym_off / 8);
- return -LIBBPF_ERRNO__RELOC;
- }
-
- if (prog->main_prog_cnt == 0) {
+ if (prog->idx != obj->efile.text_shndx && prog->main_prog_cnt == 0) {
text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx);
if (!text) {
pr_warn("no .text section found yet relo into text exist\n");
@@ -4288,6 +4656,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
text->insns_cnt, text->section_name,
prog->section_name);
}
+
insn = &prog->insns[relo->insn_idx];
insn->imm += relo->sym_off / 8 + prog->main_prog_cnt - relo->insn_idx;
return 0;
@@ -4367,8 +4736,28 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
return err;
}
}
+ /* ensure .text is relocated first, as it's going to be copied as-is
+ * later for sub-program calls
+ */
for (i = 0; i < obj->nr_programs; i++) {
prog = &obj->programs[i];
+ if (prog->idx != obj->efile.text_shndx)
+ continue;
+
+ err = bpf_program__relocate(prog, obj);
+ if (err) {
+ pr_warn("failed to relocate '%s'\n", prog->section_name);
+ return err;
+ }
+ break;
+ }
+ /* now relocate everything but .text, which by now is relocated
+ * properly, so we can copy raw sub-program instructions as is safely
+ */
+ for (i = 0; i < obj->nr_programs; i++) {
+ prog = &obj->programs[i];
+ if (prog->idx == obj->efile.text_shndx)
+ continue;
err = bpf_program__relocate(prog, obj);
if (err) {
@@ -4379,6 +4768,10 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
return 0;
}
+static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj,
+ GElf_Shdr *shdr,
+ Elf_Data *data);
+
static int bpf_object__collect_reloc(struct bpf_object *obj)
{
int i, err;
@@ -4399,6 +4792,15 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
return -LIBBPF_ERRNO__INTERNAL;
}
+ if (idx == obj->efile.st_ops_shndx) {
+ err = bpf_object__collect_struct_ops_map_reloc(obj,
+ shdr,
+ data);
+ if (err)
+ return err;
+ continue;
+ }
+
prog = bpf_object__find_prog_by_idx(obj, idx);
if (!prog) {
pr_warn("relocation failed: no section(%d)\n", idx);
@@ -4433,7 +4835,10 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
load_attr.insns = insns;
load_attr.insns_cnt = insns_cnt;
load_attr.license = license;
- if (prog->type == BPF_PROG_TYPE_TRACING) {
+ if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) {
+ load_attr.attach_btf_id = prog->attach_btf_id;
+ } else if (prog->type == BPF_PROG_TYPE_TRACING ||
+ prog->type == BPF_PROG_TYPE_EXT) {
load_attr.attach_prog_fd = prog->attach_prog_fd;
load_attr.attach_btf_id = prog->attach_btf_id;
} else {
@@ -4508,18 +4913,15 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
return ret;
}
-static int libbpf_find_attach_btf_id(const char *name,
- enum bpf_attach_type attach_type,
- __u32 attach_prog_fd);
+static int libbpf_find_attach_btf_id(struct bpf_program *prog);
int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
{
int err = 0, fd, i, btf_id;
- if (prog->type == BPF_PROG_TYPE_TRACING) {
- btf_id = libbpf_find_attach_btf_id(prog->section_name,
- prog->expected_attach_type,
- prog->attach_prog_fd);
+ if (prog->type == BPF_PROG_TYPE_TRACING ||
+ prog->type == BPF_PROG_TYPE_EXT) {
+ btf_id = libbpf_find_attach_btf_id(prog);
if (btf_id <= 0)
return btf_id;
prog->attach_btf_id = btf_id;
@@ -4679,6 +5081,9 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
enum bpf_prog_type prog_type;
enum bpf_attach_type attach_type;
+ if (prog->type != BPF_PROG_TYPE_UNSPEC)
+ continue;
+
err = libbpf_prog_type_by_name(prog->section_name, &prog_type,
&attach_type);
if (err == -ESRCH)
@@ -4689,7 +5094,8 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
bpf_program__set_type(prog, prog_type);
bpf_program__set_expected_attach_type(prog, attach_type);
- if (prog_type == BPF_PROG_TYPE_TRACING)
+ if (prog_type == BPF_PROG_TYPE_TRACING ||
+ prog_type == BPF_PROG_TYPE_EXT)
prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
}
@@ -4774,8 +5180,11 @@ int bpf_object__unload(struct bpf_object *obj)
if (!obj)
return -EINVAL;
- for (i = 0; i < obj->nr_maps; i++)
+ for (i = 0; i < obj->nr_maps; i++) {
zclose(obj->maps[i].fd);
+ if (obj->maps[i].st_ops)
+ zfree(&obj->maps[i].st_ops->kern_vdata);
+ }
for (i = 0; i < obj->nr_programs; i++)
bpf_program__unload(&obj->programs[i]);
@@ -4891,9 +5300,15 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
err = err ? : bpf_object__sanitize_and_load_btf(obj);
err = err ? : bpf_object__sanitize_maps(obj);
+ err = err ? : bpf_object__load_vmlinux_btf(obj);
+ err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
err = err ? : bpf_object__create_maps(obj);
err = err ? : bpf_object__relocate(obj, attr->target_btf_path);
err = err ? : bpf_object__load_progs(obj, attr->log_level);
+
+ btf__free(obj->btf_vmlinux);
+ obj->btf_vmlinux = NULL;
+
if (err)
goto out;
@@ -5478,6 +5893,13 @@ void bpf_object__close(struct bpf_object *obj)
map->mmaped = NULL;
}
+ if (map->st_ops) {
+ zfree(&map->st_ops->data);
+ zfree(&map->st_ops->progs);
+ zfree(&map->st_ops->kern_func_off);
+ zfree(&map->st_ops);
+ }
+
zfree(&map->name);
zfree(&map->pin_path);
}
@@ -5746,6 +6168,8 @@ BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING);
+BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS);
+BPF_PROG_TYPE_FNS(extension, BPF_PROG_TYPE_EXT);
enum bpf_attach_type
bpf_program__get_expected_attach_type(struct bpf_program *prog)
@@ -5845,6 +6269,9 @@ static const struct bpf_sec_def section_defs[] = {
.expected_attach_type = BPF_TRACE_FEXIT,
.is_attach_btf = true,
.attach_fn = attach_trace),
+ SEC_DEF("freplace/", EXT,
+ .is_attach_btf = true,
+ .attach_fn = attach_trace),
BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP),
BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
@@ -5899,6 +6326,7 @@ static const struct bpf_sec_def section_defs[] = {
BPF_CGROUP_GETSOCKOPT),
BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
BPF_CGROUP_SETSOCKOPT),
+ BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS),
};
#undef BPF_PROG_SEC_IMPL
@@ -5975,34 +6403,182 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
return -ESRCH;
}
-#define BTF_PREFIX "btf_trace_"
+static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
+ size_t offset)
+{
+ struct bpf_map *map;
+ size_t i;
+
+ for (i = 0; i < obj->nr_maps; i++) {
+ map = &obj->maps[i];
+ if (!bpf_map__is_struct_ops(map))
+ continue;
+ if (map->sec_offset <= offset &&
+ offset - map->sec_offset < map->def.value_size)
+ return map;
+ }
+
+ return NULL;
+}
+
+/* Collect the reloc from ELF and populate the st_ops->progs[] */
+static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj,
+ GElf_Shdr *shdr,
+ Elf_Data *data)
+{
+ const struct btf_member *member;
+ struct bpf_struct_ops *st_ops;
+ struct bpf_program *prog;
+ unsigned int shdr_idx;
+ const struct btf *btf;
+ struct bpf_map *map;
+ Elf_Data *symbols;
+ unsigned int moff;
+ const char *name;
+ __u32 member_idx;
+ GElf_Sym sym;
+ GElf_Rel rel;
+ int i, nrels;
+
+ symbols = obj->efile.symbols;
+ btf = obj->btf;
+ nrels = shdr->sh_size / shdr->sh_entsize;
+ for (i = 0; i < nrels; i++) {
+ if (!gelf_getrel(data, i, &rel)) {
+ pr_warn("struct_ops reloc: failed to get %d reloc\n", i);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+ pr_warn("struct_ops reloc: symbol %zx not found\n",
+ (size_t)GELF_R_SYM(rel.r_info));
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+ sym.st_name) ? : "<?>";
+ map = find_struct_ops_map_by_offset(obj, rel.r_offset);
+ if (!map) {
+ pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n",
+ (size_t)rel.r_offset);
+ return -EINVAL;
+ }
+
+ moff = rel.r_offset - map->sec_offset;
+ shdr_idx = sym.st_shndx;
+ st_ops = map->st_ops;
+ pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel.r_offset %zu map->sec_offset %zu name %d (\'%s\')\n",
+ map->name,
+ (long long)(rel.r_info >> 32),
+ (long long)sym.st_value,
+ shdr_idx, (size_t)rel.r_offset,
+ map->sec_offset, sym.st_name, name);
+
+ if (shdr_idx >= SHN_LORESERVE) {
+ pr_warn("struct_ops reloc %s: rel.r_offset %zu shdr_idx %u unsupported non-static function\n",
+ map->name, (size_t)rel.r_offset, shdr_idx);
+ return -LIBBPF_ERRNO__RELOC;
+ }
+
+ member = find_member_by_offset(st_ops->type, moff * 8);
+ if (!member) {
+ pr_warn("struct_ops reloc %s: cannot find member at moff %u\n",
+ map->name, moff);
+ return -EINVAL;
+ }
+ member_idx = member - btf_members(st_ops->type);
+ name = btf__name_by_offset(btf, member->name_off);
+
+ if (!resolve_func_ptr(btf, member->type, NULL)) {
+ pr_warn("struct_ops reloc %s: cannot relocate non func ptr %s\n",
+ map->name, name);
+ return -EINVAL;
+ }
+
+ prog = bpf_object__find_prog_by_idx(obj, shdr_idx);
+ if (!prog) {
+ pr_warn("struct_ops reloc %s: cannot find prog at shdr_idx %u to relocate func ptr %s\n",
+ map->name, shdr_idx, name);
+ return -EINVAL;
+ }
+
+ if (prog->type == BPF_PROG_TYPE_UNSPEC) {
+ const struct bpf_sec_def *sec_def;
+
+ sec_def = find_sec_def(prog->section_name);
+ if (sec_def &&
+ sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) {
+ /* for pr_warn */
+ prog->type = sec_def->prog_type;
+ goto invalid_prog;
+ }
+
+ prog->type = BPF_PROG_TYPE_STRUCT_OPS;
+ prog->attach_btf_id = st_ops->type_id;
+ prog->expected_attach_type = member_idx;
+ } else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
+ prog->attach_btf_id != st_ops->type_id ||
+ prog->expected_attach_type != member_idx) {
+ goto invalid_prog;
+ }
+ st_ops->progs[member_idx] = prog;
+ }
+
+ return 0;
+
+invalid_prog:
+ pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n",
+ map->name, prog->name, prog->section_name, prog->type,
+ prog->attach_btf_id, prog->expected_attach_type, name);
+ return -EINVAL;
+}
+
+#define BTF_TRACE_PREFIX "btf_trace_"
+#define BTF_MAX_NAME_SIZE 128
+
+static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
+ const char *name, __u32 kind)
+{
+ char btf_type_name[BTF_MAX_NAME_SIZE];
+ int ret;
+
+ ret = snprintf(btf_type_name, sizeof(btf_type_name),
+ "%s%s", prefix, name);
+ /* snprintf returns the number of characters written excluding the
+ * the terminating null. So, if >= BTF_MAX_NAME_SIZE are written, it
+ * indicates truncation.
+ */
+ if (ret < 0 || ret >= sizeof(btf_type_name))
+ return -ENAMETOOLONG;
+ return btf__find_by_name_kind(btf, btf_type_name, kind);
+}
+
+static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name,
+ enum bpf_attach_type attach_type)
+{
+ int err;
+
+ if (attach_type == BPF_TRACE_RAW_TP)
+ err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name,
+ BTF_KIND_TYPEDEF);
+ else
+ err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+
+ return err;
+}
+
int libbpf_find_vmlinux_btf_id(const char *name,
enum bpf_attach_type attach_type)
{
- struct btf *btf = bpf_core_find_kernel_btf();
- char raw_tp_btf[128] = BTF_PREFIX;
- char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1;
- const char *btf_name;
- int err = -EINVAL;
- __u32 kind;
+ struct btf *btf;
+ btf = libbpf_find_kernel_btf();
if (IS_ERR(btf)) {
pr_warn("vmlinux BTF is not found\n");
return -EINVAL;
}
- if (attach_type == BPF_TRACE_RAW_TP) {
- /* prepend "btf_trace_" prefix per kernel convention */
- strncat(dst, name, sizeof(raw_tp_btf) - sizeof(BTF_PREFIX));
- btf_name = raw_tp_btf;
- kind = BTF_KIND_TYPEDEF;
- } else {
- btf_name = name;
- kind = BTF_KIND_FUNC;
- }
- err = btf__find_by_name_kind(btf, btf_name, kind);
- btf__free(btf);
- return err;
+ return __find_vmlinux_btf_id(btf, name, attach_type);
}
static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
@@ -6038,10 +6614,11 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
return err;
}
-static int libbpf_find_attach_btf_id(const char *name,
- enum bpf_attach_type attach_type,
- __u32 attach_prog_fd)
+static int libbpf_find_attach_btf_id(struct bpf_program *prog)
{
+ enum bpf_attach_type attach_type = prog->expected_attach_type;
+ __u32 attach_prog_fd = prog->attach_prog_fd;
+ const char *name = prog->section_name;
int i, err;
if (!name)
@@ -6056,8 +6633,9 @@ static int libbpf_find_attach_btf_id(const char *name,
err = libbpf_find_prog_btf_id(name + section_defs[i].len,
attach_prog_fd);
else
- err = libbpf_find_vmlinux_btf_id(name + section_defs[i].len,
- attach_type);
+ err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux,
+ name + section_defs[i].len,
+ attach_type);
if (err <= 0)
pr_warn("%s is not found in vmlinux BTF\n", name);
return err;
@@ -6805,6 +7383,58 @@ struct bpf_link *bpf_program__attach(struct bpf_program *prog)
return sec_def->attach_fn(sec_def, prog);
}
+static int bpf_link__detach_struct_ops(struct bpf_link *link)
+{
+ struct bpf_link_fd *l = (void *)link;
+ __u32 zero = 0;
+
+ if (bpf_map_delete_elem(l->fd, &zero))
+ return -errno;
+
+ return 0;
+}
+
+struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
+{
+ struct bpf_struct_ops *st_ops;
+ struct bpf_link_fd *link;
+ __u32 i, zero = 0;
+ int err;
+
+ if (!bpf_map__is_struct_ops(map) || map->fd == -1)
+ return ERR_PTR(-EINVAL);
+
+ link = calloc(1, sizeof(*link));
+ if (!link)
+ return ERR_PTR(-EINVAL);
+
+ st_ops = map->st_ops;
+ for (i = 0; i < btf_vlen(st_ops->type); i++) {
+ struct bpf_program *prog = st_ops->progs[i];
+ void *kern_data;
+ int prog_fd;
+
+ if (!prog)
+ continue;
+
+ prog_fd = bpf_program__fd(prog);
+ kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i];
+ *(unsigned long *)kern_data = prog_fd;
+ }
+
+ err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0);
+ if (err) {
+ err = -errno;
+ free(link);
+ return ERR_PTR(err);
+ }
+
+ link->link.detach = bpf_link__detach_struct_ops;
+ link->fd = map->fd;
+
+ return (struct bpf_link *)link;
+}
+
enum bpf_perf_event_ret
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
void **copy_mem, size_t *copy_size,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index fe592ef..2a5e3b0 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -239,6 +239,8 @@ bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
LIBBPF_API struct bpf_link *
bpf_program__attach_trace(struct bpf_program *prog);
+struct bpf_map;
+LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
struct bpf_insn;
/*
@@ -315,6 +317,8 @@ LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog);
LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog);
LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
@@ -335,6 +339,8 @@ LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog);
/*
* No need for __attribute__((packed)), all members of 'bpf_map_def'
@@ -354,7 +360,6 @@ struct bpf_map_def {
* The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel,
* so no need to worry about a name clash.
*/
-struct bpf_map;
LIBBPF_API struct bpf_map *
bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
@@ -521,6 +526,7 @@ LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type,
LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex);
/*
* Get bpf_prog_info in continuous memory
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index e9713a5..b035122 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -213,14 +213,25 @@
global:
btf_dump__emit_type_decl;
bpf_link__disconnect;
+ bpf_map__attach_struct_ops;
+ bpf_map_delete_batch;
+ bpf_map_lookup_and_delete_batch;
+ bpf_map_lookup_batch;
+ bpf_map_update_batch;
bpf_object__find_program_by_name;
bpf_object__attach_skeleton;
bpf_object__destroy_skeleton;
bpf_object__detach_skeleton;
bpf_object__load_skeleton;
bpf_object__open_skeleton;
+ bpf_probe_large_insn_limit;
bpf_prog_attach_xattr;
bpf_program__attach;
bpf_program__name;
+ bpf_program__is_extension;
+ bpf_program__is_struct_ops;
+ bpf_program__set_extension;
+ bpf_program__set_struct_ops;
btf__align_of;
+ libbpf_find_kernel_btf;
} LIBBPF_0.0.6;
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index 4343e40..0afb51f 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -13,6 +13,9 @@
#include "libbpf.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START)
#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c)
#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index a9eb8b3..b782ebe 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -17,6 +17,9 @@
#include "libbpf.h"
#include "libbpf_internal.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
static bool grep(const char *buffer, const char *pattern)
{
return !!strstr(buffer, pattern);
@@ -103,6 +106,8 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
case BPF_PROG_TYPE_CGROUP_SYSCTL:
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
case BPF_PROG_TYPE_TRACING:
+ case BPF_PROG_TYPE_STRUCT_OPS:
+ case BPF_PROG_TYPE_EXT:
default:
break;
}
@@ -251,6 +256,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
case BPF_MAP_TYPE_XSKMAP:
case BPF_MAP_TYPE_SOCKHASH:
case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+ case BPF_MAP_TYPE_STRUCT_OPS:
default:
break;
}
@@ -321,3 +327,24 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
return res;
}
+
+/*
+ * Probe for availability of kernel commit (5.3):
+ *
+ * c04c0d2b968a ("bpf: increase complexity limit and maximum program size")
+ */
+bool bpf_probe_large_insn_limit(__u32 ifindex)
+{
+ struct bpf_insn insns[BPF_MAXINSNS + 1];
+ int i;
+
+ for (i = 0; i < BPF_MAXINSNS; i++)
+ insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1);
+ insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
+
+ errno = 0;
+ probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
+ ifindex);
+
+ return errno != E2BIG && errno != EINVAL;
+}
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 5065c1a..431bd25 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -15,6 +15,9 @@
#include "libbpf_internal.h"
#include "nlattr.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
#ifndef SOL_NETLINK
#define SOL_NETLINK 270
#endif
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 8db44bb..0ad41df 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -13,6 +13,9 @@
#include <string.h>
#include <stdio.h>
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = {
[LIBBPF_NLA_U8] = sizeof(uint8_t),
[LIBBPF_NLA_U16] = sizeof(uint16_t),
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index b8064ee..146da01 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -4,6 +4,9 @@
#include <stdio.h>
#include "str_error.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
/*
* Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl
* libc, while checking strerror_r() return to avoid having to check this in
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 8e0ffa8..9807903 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -32,6 +32,9 @@
#include "libbpf_internal.h"
#include "xsk.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
#ifndef SOL_XDP
#define SOL_XDP 283
#endif
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index f3cbf86..20eed71 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1228,8 +1228,10 @@ filter_event(struct tep_event_filter *filter, struct tep_event *event,
}
filter_type = add_filter_type(filter, event->id);
- if (filter_type == NULL)
+ if (filter_type == NULL) {
+ free_arg(arg);
return TEP_ERRNO__MEM_ALLOC_FAILED;
+ }
if (filter_type->filter)
free_arg(filter_type->filter);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 387311c..de98858 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1076,6 +1076,7 @@ int cmd_report(int argc, const char **argv)
struct stat st;
bool has_br_stack = false;
int branch_mode = -1;
+ int last_key = 0;
bool branch_call_mode = false;
#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent"
static const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
@@ -1450,7 +1451,8 @@ int cmd_report(int argc, const char **argv)
sort_order = sort_tmp;
}
- if (setup_sorting(session->evlist) < 0) {
+ if ((last_key != K_SWITCH_INPUT_DATA) &&
+ (setup_sorting(session->evlist) < 0)) {
if (sort_order)
parse_options_usage(report_usage, options, "s", 1);
if (field_order)
@@ -1530,6 +1532,7 @@ int cmd_report(int argc, const char **argv)
ret = __cmd_report(&report);
if (ret == K_SWITCH_INPUT_DATA) {
perf_session__delete(session);
+ last_key = K_SWITCH_INPUT_DATA;
goto repeat;
} else
ret = 0;
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
index b9c20321..49f4f84 100644
--- a/tools/perf/examples/bpf/5sec.c
+++ b/tools/perf/examples/bpf/5sec.c
@@ -39,7 +39,7 @@
Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
*/
-#include <bpf.h>
+#include <bpf/bpf.h>
int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
{
diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c
index 3776d26..7d7fb0c 100644
--- a/tools/perf/examples/bpf/empty.c
+++ b/tools/perf/examples/bpf/empty.c
@@ -1,3 +1,3 @@
-#include <bpf.h>
+#include <bpf/bpf.h>
license(GPL);
diff --git a/tools/perf/examples/bpf/sys_enter_openat.c b/tools/perf/examples/bpf/sys_enter_openat.c
index 9cd124b..c4481c3 100644
--- a/tools/perf/examples/bpf/sys_enter_openat.c
+++ b/tools/perf/examples/bpf/sys_enter_openat.c
@@ -14,7 +14,7 @@
* the return value.
*/
-#include <bpf.h>
+#include <bpf/bpf.h>
struct syscall_enter_openat_args {
unsigned long long unused;
diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h
index 6e61c4b..607189a 100644
--- a/tools/perf/include/bpf/pid_filter.h
+++ b/tools/perf/include/bpf/pid_filter.h
@@ -3,7 +3,7 @@
#ifndef _PERF_BPF_PID_FILTER_
#define _PERF_BPF_PID_FILTER_
-#include <bpf.h>
+#include <bpf/bpf.h>
#define pid_filter(name) pid_map(name, bool)
diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h
index 316af5b..7ca6fa5 100644
--- a/tools/perf/include/bpf/stdio.h
+++ b/tools/perf/include/bpf/stdio.h
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
-#include <bpf.h>
+#include <bpf/bpf.h>
struct bpf_map SEC("maps") __bpf_stdout__ = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h
index ca7877f..d1a35b6 100644
--- a/tools/perf/include/bpf/unistd.h
+++ b/tools/perf/include/bpf/unistd.h
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: LGPL-2.1
-#include <bpf.h>
+#include <bpf/bpf.h>
static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 4528690..0aa63ae 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -339,10 +339,10 @@ static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list)
#define hists__for_each_format(hists, format) \
- perf_hpp_list__for_each_format((hists)->hpp_list, fmt)
+ perf_hpp_list__for_each_format((hists)->hpp_list, format)
#define hists__for_each_sort_list(hists, format) \
- perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt)
+ perf_hpp_list__for_each_sort_list((hists)->hpp_list, format)
extern struct perf_hpp_fmt perf_hpp__format[];
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6658fbf1..1965aef 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -920,6 +920,9 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
if (curr_map == NULL)
return -1;
+ if (curr_dso->kernel)
+ map__kmap(curr_map)->kmaps = kmaps;
+
if (adjust_kernel_syms) {
curr_map->start = shdr->sh_addr + ref_reloc(kmap);
curr_map->end = curr_map->start + shdr->sh_size;
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index b001c60..b45a8f77 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -32,6 +32,7 @@
TARGETS += mount
TARGETS += mqueue
TARGETS += net
+TARGETS += net/mptcp
TARGETS += netfilter
TARGETS += networking/timestamping
TARGETS += nsfs
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 301ac12..ec46485 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -22,17 +22,13 @@
test_skb_cgroup_id_user
test_socket_cookie
test_cgroup_storage
-test_select_reuseport
test_flow_dissector
flow_dissector_load
test_netcnt
-test_section_names
test_tcpnotify_user
test_libbpf
test_tcp_check_syncookie_user
test_sysctl
-libbpf.pc
-libbpf.so.*
test_hashmap
test_btf_dump
xdping
@@ -41,4 +37,4 @@
/no_alu32
/bpf_gcc
/tools
-bpf_helper_defs.h
+
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f1f949c..5f41f5b 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -20,8 +20,8 @@
LLC ?= llc
LLVM_OBJCOPY ?= llvm-objcopy
BPF_GCC ?= $(shell command -v bpf-gcc;)
-CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) \
- -I$(GENDIR) -I$(TOOLSINCDIR) -I$(CURDIR) \
+CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(CURDIR) -I$(APIDIR) \
+ -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR) \
-Dbpf_prog_load=bpf_prog_test_load \
-Dbpf_load_program=bpf_test_load_program
LDLIBS += -lcap -lelf -lz -lrt -lpthread
@@ -73,7 +73,7 @@
# Compile but not part of 'make run_tests'
TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
- test_lirc_mode2_user xdping test_cpp
+ test_lirc_mode2_user xdping test_cpp runqslower
TEST_CUSTOM_PROGS = urandom_read
@@ -83,20 +83,29 @@
# $3 - target (assumed to be file); only file name will be emitted;
# $4 - optional extra arg, emitted as-is, if provided.
ifeq ($(V),1)
+Q =
msg =
else
-msg = @$(info $(1)$(if $(2), [$(2)]) $(notdir $(3)))$(if $(4), $(4))
+Q = @
+msg = @printf ' %-8s%s %s%s\n' "$(1)" "$(if $(2), [$(2)])" "$(notdir $(3))" "$(if $(4), $(4))";
+MAKEFLAGS += --no-print-directory
+submake_extras := feature_display=0
endif
# override lib.mk's default rules
OVERRIDE_TARGETS := 1
override define CLEAN
- $(call msg, CLEAN)
+ $(call msg,CLEAN)
$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
endef
include ../lib.mk
+SCRATCH_DIR := $(OUTPUT)/tools
+BUILD_DIR := $(SCRATCH_DIR)/build
+INCLUDE_DIR := $(SCRATCH_DIR)/include
+BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a
+
# Define simple and short `make test_progs`, `make test_sysctl`, etc targets
# to build individual tests.
# NOTE: Semicolon at the end is critical to override lib.mk's default static
@@ -108,18 +117,25 @@
$(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ;
$(OUTPUT)/%:%.c
- $(call msg, BINARY,,$@)
+ $(call msg,BINARY,,$@)
$(LINK.c) $^ $(LDLIBS) -o $@
$(OUTPUT)/urandom_read: urandom_read.c
- $(call msg, BINARY,,$@)
- $(CC) -o $@ $< -Wl,--build-id
+ $(call msg,BINARY,,$@)
+ $(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id
-$(OUTPUT)/test_stub.o: test_stub.c
- $(call msg, CC,,$@)
+$(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ)
+ $(call msg,CC,,$@)
$(CC) -c $(CFLAGS) -o $@ $<
-BPFOBJ := $(OUTPUT)/libbpf.a
+VMLINUX_BTF_PATHS := $(abspath ../../../../vmlinux) \
+ /sys/kernel/btf/vmlinux \
+ /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF:= $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))
+$(OUTPUT)/runqslower: $(BPFOBJ)
+ $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \
+ OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF) \
+ BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR)
$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ)
@@ -137,23 +153,22 @@
$(OUTPUT)/test_sock_fields: cgroup_helpers.c
$(OUTPUT)/test_sysctl: cgroup_helpers.c
-.PHONY: force
-
-# force a rebuild of BPFOBJ when its dependencies are updated
-force:
-
-DEFAULT_BPFTOOL := $(OUTPUT)/tools/usr/local/sbin/bpftool
+DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool
BPFTOOL ?= $(DEFAULT_BPFTOOL)
+$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BUILD_DIR)/bpftool
+ $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \
+ OUTPUT=$(BUILD_DIR)/bpftool/ \
+ prefix= DESTDIR=$(SCRATCH_DIR)/ install
-$(DEFAULT_BPFTOOL): force
- $(MAKE) -C $(BPFTOOLDIR) DESTDIR=$(OUTPUT)/tools install
+$(BPFOBJ): $(wildcard $(BPFDIR)/*.c $(BPFDIR)/*.h $(BPFDIR)/Makefile) \
+ ../../../include/uapi/linux/bpf.h \
+ | $(INCLUDE_DIR) $(BUILD_DIR)/libbpf
+ $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
+ DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
-$(BPFOBJ): force
- $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
-
-BPF_HELPERS := $(OUTPUT)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h)
-$(OUTPUT)/bpf_helper_defs.h:
- $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ $(OUTPUT)/bpf_helper_defs.h
+$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR):
+ $(call msg,MKDIR,,$@)
+ mkdir -p $@
# Get Clang's default includes on this system, as opposed to those seen by
# '-target bpf'. This fixes "missing" files on some architectures/distros,
@@ -173,8 +188,8 @@
CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \
- -I. -I./include/uapi -I$(APIDIR) \
- -I$(BPFDIR) -I$(abspath $(OUTPUT)/../usr/include)
+ -I$(INCLUDE_DIR) -I$(CURDIR) -I$(CURDIR)/include/uapi \
+ -I$(APIDIR) -I$(abspath $(OUTPUT)/../usr/include)
CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
-Wno-compare-distinct-pointer-types
@@ -190,28 +205,28 @@
# $3 - CFLAGS
# $4 - LDFLAGS
define CLANG_BPF_BUILD_RULE
- $(call msg, CLANG-LLC,$(TRUNNER_BINARY),$2)
+ $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
($(CLANG) $3 -O2 -target bpf -emit-llvm \
-c $1 -o - || echo "BPF obj compilation failed") | \
$(LLC) -mattr=dwarfris -march=bpf -mcpu=probe $4 -filetype=obj -o $2
endef
# Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
define CLANG_NOALU32_BPF_BUILD_RULE
- $(call msg, CLANG-LLC,$(TRUNNER_BINARY),$2)
+ $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
($(CLANG) $3 -O2 -target bpf -emit-llvm \
-c $1 -o - || echo "BPF obj compilation failed") | \
$(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2
endef
# Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC
define CLANG_NATIVE_BPF_BUILD_RULE
- $(call msg, CLANG-BPF,$(TRUNNER_BINARY),$2)
+ $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
($(CLANG) $3 -O2 -emit-llvm \
-c $1 -o - || echo "BPF obj compilation failed") | \
$(LLC) -march=bpf -mcpu=probe $4 -filetype=obj -o $2
endef
# Build BPF object using GCC
define GCC_BPF_BUILD_RULE
- $(call msg, GCC-BPF,$(TRUNNER_BINARY),$2)
+ $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
$(BPF_GCC) $3 $4 -O2 -c $1 -o $2
endef
@@ -252,6 +267,7 @@
ifeq ($($(TRUNNER_OUTPUT)-dir),)
$(TRUNNER_OUTPUT)-dir := y
$(TRUNNER_OUTPUT):
+ $$(call msg,MKDIR,,$$@)
mkdir -p $$@
endif
@@ -262,7 +278,7 @@
$(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \
$(TRUNNER_BPF_PROGS_DIR)/%.c \
$(TRUNNER_BPF_PROGS_DIR)/*.h \
- $$(BPF_HELPERS) | $(TRUNNER_OUTPUT)
+ $$(BPFOBJ) | $(TRUNNER_OUTPUT)
$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \
$(TRUNNER_BPF_CFLAGS), \
$(TRUNNER_BPF_LDFLAGS))
@@ -270,7 +286,7 @@
$(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h: \
$(TRUNNER_OUTPUT)/%.o \
| $(BPFTOOL) $(TRUNNER_OUTPUT)
- $$(call msg, GEN-SKEL,$(TRUNNER_BINARY),$$@)
+ $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
$$(BPFTOOL) gen skeleton $$< > $$@
endif
@@ -278,7 +294,7 @@
ifeq ($($(TRUNNER_TESTS_DIR)-tests-hdr),)
$(TRUNNER_TESTS_DIR)-tests-hdr := y
$(TRUNNER_TESTS_HDR): $(TRUNNER_TESTS_DIR)/*.c
- $$(call msg, TEST-HDR,$(TRUNNER_BINARY),$$@)
+ $$(call msg,TEST-HDR,$(TRUNNER_BINARY),$$@)
$$(shell ( cd $(TRUNNER_TESTS_DIR); \
echo '/* Generated header, do not edit */'; \
ls *.c 2> /dev/null | \
@@ -294,7 +310,7 @@
$(TRUNNER_BPF_OBJS) \
$(TRUNNER_BPF_SKELS) \
$$(BPFOBJ) | $(TRUNNER_OUTPUT)
- $$(call msg, TEST-OBJ,$(TRUNNER_BINARY),$$@)
+ $$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
$(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \
@@ -302,20 +318,20 @@
$(TRUNNER_EXTRA_HDRS) \
$(TRUNNER_TESTS_HDR) \
$$(BPFOBJ) | $(TRUNNER_OUTPUT)
- $$(call msg, EXTRA-OBJ,$(TRUNNER_BINARY),$$@)
+ $$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@)
$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@
# only copy extra resources if in flavored build
$(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT)
ifneq ($2,)
- $$(call msg, EXTRAS-CP,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES))
+ $$(call msg,EXT-COPY,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES))
cp -a $$^ $(TRUNNER_OUTPUT)/
endif
$(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \
$(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \
| $(TRUNNER_BINARY)-extras
- $$(call msg, BINARY,,$$@)
+ $$(call msg,BINARY,,$$@)
$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
endef
@@ -328,7 +344,7 @@
TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \
$(wildcard progs/btf_dump_test_case_*.c)
TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
-TRUNNER_BPF_CFLAGS := -I. -I$(OUTPUT) $(BPF_CFLAGS) $(CLANG_CFLAGS)
+TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
TRUNNER_BPF_LDFLAGS := -mattr=+alu32
$(eval $(call DEFINE_TEST_RUNNER,test_progs))
@@ -367,15 +383,15 @@
echo '#endif' \
) > verifier/tests.h)
$(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT)
- $(call msg, BINARY,,$@)
+ $(call msg,BINARY,,$@)
$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
# Make sure we are able to include and link libbpf against c++.
$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
- $(call msg, CXX,,$@)
+ $(call msg,CXX,,$@)
$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@
-EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) \
+EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) \
prog_tests/tests.h map_tests/tests.h verifier/tests.h \
- feature $(OUTPUT)/*.o $(OUTPUT)/no_alu32 $(OUTPUT)/bpf_gcc \
- tools *.skel.h
+ feature \
+ $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc)
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
new file mode 100644
index 0000000..8f21965
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -0,0 +1,235 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_TCP_HELPERS_H
+#define __BPF_TCP_HELPERS_H
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_trace_helpers.h"
+
+#define BPF_STRUCT_OPS(name, args...) \
+SEC("struct_ops/"#name) \
+BPF_PROG(name, args)
+
+#define tcp_jiffies32 ((__u32)bpf_jiffies64())
+
+struct sock_common {
+ unsigned char skc_state;
+} __attribute__((preserve_access_index));
+
+enum sk_pacing {
+ SK_PACING_NONE = 0,
+ SK_PACING_NEEDED = 1,
+ SK_PACING_FQ = 2,
+};
+
+struct sock {
+ struct sock_common __sk_common;
+ unsigned long sk_pacing_rate;
+ __u32 sk_pacing_status; /* see enum sk_pacing */
+} __attribute__((preserve_access_index));
+
+struct inet_sock {
+ struct sock sk;
+} __attribute__((preserve_access_index));
+
+struct inet_connection_sock {
+ struct inet_sock icsk_inet;
+ __u8 icsk_ca_state:6,
+ icsk_ca_setsockopt:1,
+ icsk_ca_dst_locked:1;
+ struct {
+ __u8 pending;
+ } icsk_ack;
+ __u64 icsk_ca_priv[104 / sizeof(__u64)];
+} __attribute__((preserve_access_index));
+
+struct tcp_sock {
+ struct inet_connection_sock inet_conn;
+
+ __u32 rcv_nxt;
+ __u32 snd_nxt;
+ __u32 snd_una;
+ __u8 ecn_flags;
+ __u32 delivered;
+ __u32 delivered_ce;
+ __u32 snd_cwnd;
+ __u32 snd_cwnd_cnt;
+ __u32 snd_cwnd_clamp;
+ __u32 snd_ssthresh;
+ __u8 syn_data:1, /* SYN includes data */
+ syn_fastopen:1, /* SYN includes Fast Open option */
+ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
+ syn_fastopen_ch:1, /* Active TFO re-enabling probe */
+ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
+ save_syn:1, /* Save headers of SYN packet */
+ is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
+ syn_smc:1; /* SYN includes SMC */
+ __u32 max_packets_out;
+ __u32 lsndtime;
+ __u32 prior_cwnd;
+ __u64 tcp_mstamp; /* most recent packet received/sent */
+} __attribute__((preserve_access_index));
+
+static __always_inline struct inet_connection_sock *inet_csk(const struct sock *sk)
+{
+ return (struct inet_connection_sock *)sk;
+}
+
+static __always_inline void *inet_csk_ca(const struct sock *sk)
+{
+ return (void *)inet_csk(sk)->icsk_ca_priv;
+}
+
+static __always_inline struct tcp_sock *tcp_sk(const struct sock *sk)
+{
+ return (struct tcp_sock *)sk;
+}
+
+static __always_inline bool before(__u32 seq1, __u32 seq2)
+{
+ return (__s32)(seq1-seq2) < 0;
+}
+#define after(seq2, seq1) before(seq1, seq2)
+
+#define TCP_ECN_OK 1
+#define TCP_ECN_QUEUE_CWR 2
+#define TCP_ECN_DEMAND_CWR 4
+#define TCP_ECN_SEEN 8
+
+enum inet_csk_ack_state_t {
+ ICSK_ACK_SCHED = 1,
+ ICSK_ACK_TIMER = 2,
+ ICSK_ACK_PUSHED = 4,
+ ICSK_ACK_PUSHED2 = 8,
+ ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */
+};
+
+enum tcp_ca_event {
+ CA_EVENT_TX_START = 0,
+ CA_EVENT_CWND_RESTART = 1,
+ CA_EVENT_COMPLETE_CWR = 2,
+ CA_EVENT_LOSS = 3,
+ CA_EVENT_ECN_NO_CE = 4,
+ CA_EVENT_ECN_IS_CE = 5,
+};
+
+enum tcp_ca_state {
+ TCP_CA_Open = 0,
+ TCP_CA_Disorder = 1,
+ TCP_CA_CWR = 2,
+ TCP_CA_Recovery = 3,
+ TCP_CA_Loss = 4
+};
+
+struct ack_sample {
+ __u32 pkts_acked;
+ __s32 rtt_us;
+ __u32 in_flight;
+} __attribute__((preserve_access_index));
+
+struct rate_sample {
+ __u64 prior_mstamp; /* starting timestamp for interval */
+ __u32 prior_delivered; /* tp->delivered at "prior_mstamp" */
+ __s32 delivered; /* number of packets delivered over interval */
+ long interval_us; /* time for tp->delivered to incr "delivered" */
+ __u32 snd_interval_us; /* snd interval for delivered packets */
+ __u32 rcv_interval_us; /* rcv interval for delivered packets */
+ long rtt_us; /* RTT of last (S)ACKed packet (or -1) */
+ int losses; /* number of packets marked lost upon ACK */
+ __u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */
+ __u32 prior_in_flight; /* in flight before this ACK */
+ bool is_app_limited; /* is sample from packet with bubble in pipe? */
+ bool is_retrans; /* is sample from retransmission? */
+ bool is_ack_delayed; /* is this (likely) a delayed ACK? */
+} __attribute__((preserve_access_index));
+
+#define TCP_CA_NAME_MAX 16
+#define TCP_CONG_NEEDS_ECN 0x2
+
+struct tcp_congestion_ops {
+ char name[TCP_CA_NAME_MAX];
+ __u32 flags;
+
+ /* initialize private data (optional) */
+ void (*init)(struct sock *sk);
+ /* cleanup private data (optional) */
+ void (*release)(struct sock *sk);
+
+ /* return slow start threshold (required) */
+ __u32 (*ssthresh)(struct sock *sk);
+ /* do new cwnd calculation (required) */
+ void (*cong_avoid)(struct sock *sk, __u32 ack, __u32 acked);
+ /* call before changing ca_state (optional) */
+ void (*set_state)(struct sock *sk, __u8 new_state);
+ /* call when cwnd event occurs (optional) */
+ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
+ /* call when ack arrives (optional) */
+ void (*in_ack_event)(struct sock *sk, __u32 flags);
+ /* new value of cwnd after loss (required) */
+ __u32 (*undo_cwnd)(struct sock *sk);
+ /* hook for packet ack accounting (optional) */
+ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
+ /* override sysctl_tcp_min_tso_segs */
+ __u32 (*min_tso_segs)(struct sock *sk);
+ /* returns the multiplier used in tcp_sndbuf_expand (optional) */
+ __u32 (*sndbuf_expand)(struct sock *sk);
+ /* call when packets are delivered to update cwnd and pacing rate,
+ * after all the ca_state processing. (optional)
+ */
+ void (*cong_control)(struct sock *sk, const struct rate_sample *rs);
+};
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#define max(a, b) ((a) > (b) ? (a) : (b))
+#define min_not_zero(x, y) ({ \
+ typeof(x) __x = (x); \
+ typeof(y) __y = (y); \
+ __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
+
+static __always_inline __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked)
+{
+ __u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh);
+
+ acked -= cwnd - tp->snd_cwnd;
+ tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+
+ return acked;
+}
+
+static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp)
+{
+ return tp->snd_cwnd < tp->snd_ssthresh;
+}
+
+static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+
+ /* If in slow start, ensure cwnd grows to twice what was ACKed. */
+ if (tcp_in_slow_start(tp))
+ return tp->snd_cwnd < 2 * tp->max_packets_out;
+
+ return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited);
+}
+
+static __always_inline void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked)
+{
+ /* If credits accumulated at a higher w, apply them gently now. */
+ if (tp->snd_cwnd_cnt >= w) {
+ tp->snd_cwnd_cnt = 0;
+ tp->snd_cwnd++;
+ }
+
+ tp->snd_cwnd_cnt += acked;
+ if (tp->snd_cwnd_cnt >= w) {
+ __u32 delta = tp->snd_cwnd_cnt / w;
+
+ tp->snd_cwnd_cnt -= delta * w;
+ tp->snd_cwnd += delta;
+ }
+ tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/bpf_trace_helpers.h b/tools/testing/selftests/bpf/bpf_trace_helpers.h
index c76a214..c6f1354d 100644
--- a/tools/testing/selftests/bpf/bpf_trace_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_trace_helpers.h
@@ -1,58 +1,120 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
#ifndef __BPF_TRACE_HELPERS_H
#define __BPF_TRACE_HELPERS_H
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
-#define __BPF_MAP_0(i, m, v, ...) v
-#define __BPF_MAP_1(i, m, v, t, a, ...) m(t, a, ctx[i])
-#define __BPF_MAP_2(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_1(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_3(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_2(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_4(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_3(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_5(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_4(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_6(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_5(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_7(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_6(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_8(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_7(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_9(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_8(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_10(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_9(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_11(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_10(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_12(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_11(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP(n, ...) __BPF_MAP_##n(0, __VA_ARGS__)
+#define ___bpf_concat(a, b) a ## b
+#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#define ___bpf_narg(...) \
+ ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#define ___bpf_empty(...) \
+ ___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
-/* BPF sizeof(void *) is always 8, so no need to cast to long first
- * for ptr to avoid compiler warning.
+#define ___bpf_ctx_cast0() ctx
+#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
+#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
+#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
+#define ___bpf_ctx_cast(args...) \
+ ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
+
+/*
+ * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
+ * similar kinds of BPF programs, that accept input arguments as a single
+ * pointer to untyped u64 array, where each u64 can actually be a typed
+ * pointer or integer of different size. Instead of requring user to write
+ * manual casts and work with array elements by index, BPF_PROG macro
+ * allows user to declare a list of named and typed input arguments in the
+ * same syntax as for normal C function. All the casting is hidden and
+ * performed transparently, while user code can just assume working with
+ * function arguments of specified type and name.
+ *
+ * Original raw context argument is preserved as well as 'ctx' argument.
+ * This is useful when using BPF helpers that expect original context
+ * as one of the parameters (e.g., for bpf_perf_event_output()).
*/
-#define __BPF_CAST(t, a, ctx) (t) ctx
-#define __BPF_V void
-#define __BPF_N
+#define BPF_PROG(name, args...) \
+name(unsigned long long *ctx); \
+static __always_inline typeof(name(0)) \
+____##name(unsigned long long *ctx, ##args); \
+typeof(name(0)) name(unsigned long long *ctx) \
+{ \
+ _Pragma("GCC diagnostic push") \
+ _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
+ return ____##name(___bpf_ctx_cast(args)); \
+ _Pragma("GCC diagnostic pop") \
+} \
+static __always_inline typeof(name(0)) \
+____##name(unsigned long long *ctx, ##args)
-#define __BPF_DECL_ARGS(t, a, ctx) t a
+struct pt_regs;
-#define BPF_TRACE_x(x, sec_name, fname, ret_type, ...) \
-static __always_inline ret_type \
-____##fname(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \
- \
-SEC(sec_name) \
-ret_type fname(__u64 *ctx) \
-{ \
- return ____##fname(__BPF_MAP(x, __BPF_CAST, __BPF_N, __VA_ARGS__));\
-} \
- \
-static __always_inline \
-ret_type ____##fname(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__))
+#define ___bpf_kprobe_args0() ctx
+#define ___bpf_kprobe_args1(x) \
+ ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) \
+ ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) \
+ ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) \
+ ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) \
+ ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args(args...) \
+ ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
-#define BPF_TRACE_0(sec, fname, ...) BPF_TRACE_x(0, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_1(sec, fname, ...) BPF_TRACE_x(1, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_2(sec, fname, ...) BPF_TRACE_x(2, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_3(sec, fname, ...) BPF_TRACE_x(3, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_4(sec, fname, ...) BPF_TRACE_x(4, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_5(sec, fname, ...) BPF_TRACE_x(5, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_6(sec, fname, ...) BPF_TRACE_x(6, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_7(sec, fname, ...) BPF_TRACE_x(7, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_8(sec, fname, ...) BPF_TRACE_x(8, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_9(sec, fname, ...) BPF_TRACE_x(9, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_10(sec, fname, ...) BPF_TRACE_x(10, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_11(sec, fname, ...) BPF_TRACE_x(11, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_12(sec, fname, ...) BPF_TRACE_x(12, sec, fname, int, __VA_ARGS__)
+/*
+ * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
+ * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
+ * low-level way of getting kprobe input arguments from struct pt_regs, and
+ * provides a familiar typed and named function arguments syntax and
+ * semantics of accessing kprobe input paremeters.
+ *
+ * Original struct pt_regs* context is preserved as 'ctx' argument. This might
+ * be necessary when using BPF helpers like bpf_perf_event_output().
+ */
+#define BPF_KPROBE(name, args...) \
+name(struct pt_regs *ctx); \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\
+typeof(name(0)) name(struct pt_regs *ctx) \
+{ \
+ _Pragma("GCC diagnostic push") \
+ _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
+ return ____##name(___bpf_kprobe_args(args)); \
+ _Pragma("GCC diagnostic pop") \
+} \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
+#define ___bpf_kretprobe_args0() ctx
+#define ___bpf_kretprobe_argsN(x, args...) \
+ ___bpf_kprobe_args(args), (void *)PT_REGS_RET(ctx)
+#define ___bpf_kretprobe_args(args...) \
+ ___bpf_apply(___bpf_kretprobe_args, ___bpf_empty(args))(args)
+
+/*
+ * BPF_KRETPROBE is similar to BPF_KPROBE, except, in addition to listing all
+ * input kprobe arguments, one last extra argument has to be specified, which
+ * captures kprobe return value.
+ */
+#define BPF_KRETPROBE(name, args...) \
+name(struct pt_regs *ctx); \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\
+typeof(name(0)) name(struct pt_regs *ctx) \
+{ \
+ _Pragma("GCC diagnostic push") \
+ _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
+ return ____##name(___bpf_kretprobe_args(args)); \
+ _Pragma("GCC diagnostic pop") \
+} \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
#endif
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index ec219f8..a3352a6 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -6,7 +6,7 @@
#include <stdlib.h>
#include <string.h>
#include <errno.h>
-#include <libbpf.h> /* libbpf_num_possible_cpus */
+#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
static inline unsigned int bpf_num_possible_cpus(void)
{
diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
new file mode 100644
index 0000000..f0a64d8
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <test_maps.h>
+
+static void map_batch_update(int map_fd, __u32 max_entries, int *keys,
+ int *values)
+{
+ int i, err;
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ for (i = 0; i < max_entries; i++) {
+ keys[i] = i;
+ values[i] = i + 1;
+ }
+
+ err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts);
+ CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno));
+}
+
+static void map_batch_verify(int *visited, __u32 max_entries,
+ int *keys, int *values)
+{
+ int i;
+
+ memset(visited, 0, max_entries * sizeof(*visited));
+ for (i = 0; i < max_entries; i++) {
+ CHECK(keys[i] + 1 != values[i], "key/value checking",
+ "error: i %d key %d value %d\n", i, keys[i], values[i]);
+ visited[i] = 1;
+ }
+ for (i = 0; i < max_entries; i++) {
+ CHECK(visited[i] != 1, "visited checking",
+ "error: keys array at index %d missing\n", i);
+ }
+}
+
+void test_array_map_batch_ops(void)
+{
+ struct bpf_create_map_attr xattr = {
+ .name = "array_map",
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ };
+ int map_fd, *keys, *values, *visited;
+ __u32 count, total, total_success;
+ const __u32 max_entries = 10;
+ bool nospace_err;
+ __u64 batch = 0;
+ int err, step;
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ xattr.max_entries = max_entries;
+ map_fd = bpf_create_map_xattr(&xattr);
+ CHECK(map_fd == -1,
+ "bpf_create_map_xattr()", "error:%s\n", strerror(errno));
+
+ keys = malloc(max_entries * sizeof(int));
+ values = malloc(max_entries * sizeof(int));
+ visited = malloc(max_entries * sizeof(int));
+ CHECK(!keys || !values || !visited, "malloc()", "error:%s\n",
+ strerror(errno));
+
+ /* populate elements to the map */
+ map_batch_update(map_fd, max_entries, keys, values);
+
+ /* test 1: lookup in a loop with various steps. */
+ total_success = 0;
+ for (step = 1; step < max_entries; step++) {
+ map_batch_update(map_fd, max_entries, keys, values);
+ map_batch_verify(visited, max_entries, keys, values);
+ memset(keys, 0, max_entries * sizeof(*keys));
+ memset(values, 0, max_entries * sizeof(*values));
+ batch = 0;
+ total = 0;
+ /* iteratively lookup/delete elements with 'step'
+ * elements each.
+ */
+ count = step;
+ nospace_err = false;
+ while (true) {
+ err = bpf_map_lookup_batch(map_fd,
+ total ? &batch : NULL, &batch,
+ keys + total,
+ values + total,
+ &count, &opts);
+
+ CHECK((err && errno != ENOENT), "lookup with steps",
+ "error: %s\n", strerror(errno));
+
+ total += count;
+ if (err)
+ break;
+
+ }
+
+ if (nospace_err == true)
+ continue;
+
+ CHECK(total != max_entries, "lookup with steps",
+ "total = %u, max_entries = %u\n", total, max_entries);
+
+ map_batch_verify(visited, max_entries, keys, values);
+
+ total_success++;
+ }
+
+ CHECK(total_success == 0, "check total_success",
+ "unexpected failure\n");
+
+ printf("%s:PASS\n", __func__);
+
+ free(keys);
+ free(values);
+ free(visited);
+}
diff --git a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
new file mode 100644
index 0000000..976bf41
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <bpf_util.h>
+#include <test_maps.h>
+
+static void map_batch_update(int map_fd, __u32 max_entries, int *keys,
+ void *values, bool is_pcpu)
+{
+ typedef BPF_DECLARE_PERCPU(int, value);
+ value *v = NULL;
+ int i, j, err;
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ if (is_pcpu)
+ v = (value *)values;
+
+ for (i = 0; i < max_entries; i++) {
+ keys[i] = i + 1;
+ if (is_pcpu)
+ for (j = 0; j < bpf_num_possible_cpus(); j++)
+ bpf_percpu(v[i], j) = i + 2 + j;
+ else
+ ((int *)values)[i] = i + 2;
+ }
+
+ err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts);
+ CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno));
+}
+
+static void map_batch_verify(int *visited, __u32 max_entries,
+ int *keys, void *values, bool is_pcpu)
+{
+ typedef BPF_DECLARE_PERCPU(int, value);
+ value *v = NULL;
+ int i, j;
+
+ if (is_pcpu)
+ v = (value *)values;
+
+ memset(visited, 0, max_entries * sizeof(*visited));
+ for (i = 0; i < max_entries; i++) {
+
+ if (is_pcpu) {
+ for (j = 0; j < bpf_num_possible_cpus(); j++) {
+ CHECK(keys[i] + 1 + j != bpf_percpu(v[i], j),
+ "key/value checking",
+ "error: i %d j %d key %d value %d\n",
+ i, j, keys[i], bpf_percpu(v[i], j));
+ }
+ } else {
+ CHECK(keys[i] + 1 != ((int *)values)[i],
+ "key/value checking",
+ "error: i %d key %d value %d\n", i, keys[i],
+ ((int *)values)[i]);
+ }
+
+ visited[i] = 1;
+
+ }
+ for (i = 0; i < max_entries; i++) {
+ CHECK(visited[i] != 1, "visited checking",
+ "error: keys array at index %d missing\n", i);
+ }
+}
+
+void __test_map_lookup_and_delete_batch(bool is_pcpu)
+{
+ __u32 batch, count, total, total_success;
+ typedef BPF_DECLARE_PERCPU(int, value);
+ int map_fd, *keys, *visited, key;
+ const __u32 max_entries = 10;
+ value pcpu_values[max_entries];
+ int err, step, value_size;
+ bool nospace_err;
+ void *values;
+ struct bpf_create_map_attr xattr = {
+ .name = "hash_map",
+ .map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH :
+ BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ };
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ xattr.max_entries = max_entries;
+ map_fd = bpf_create_map_xattr(&xattr);
+ CHECK(map_fd == -1,
+ "bpf_create_map_xattr()", "error:%s\n", strerror(errno));
+
+ value_size = is_pcpu ? sizeof(value) : sizeof(int);
+ keys = malloc(max_entries * sizeof(int));
+ if (is_pcpu)
+ values = pcpu_values;
+ else
+ values = malloc(max_entries * sizeof(int));
+ visited = malloc(max_entries * sizeof(int));
+ CHECK(!keys || !values || !visited, "malloc()",
+ "error:%s\n", strerror(errno));
+
+ /* test 1: lookup/delete an empty hash table, -ENOENT */
+ count = max_entries;
+ err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys,
+ values, &count, &opts);
+ CHECK((err && errno != ENOENT), "empty map",
+ "error: %s\n", strerror(errno));
+
+ /* populate elements to the map */
+ map_batch_update(map_fd, max_entries, keys, values, is_pcpu);
+
+ /* test 2: lookup/delete with count = 0, success */
+ count = 0;
+ err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys,
+ values, &count, &opts);
+ CHECK(err, "count = 0", "error: %s\n", strerror(errno));
+
+ /* test 3: lookup/delete with count = max_entries, success */
+ memset(keys, 0, max_entries * sizeof(*keys));
+ memset(values, 0, max_entries * value_size);
+ count = max_entries;
+ err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys,
+ values, &count, &opts);
+ CHECK((err && errno != ENOENT), "count = max_entries",
+ "error: %s\n", strerror(errno));
+ CHECK(count != max_entries, "count = max_entries",
+ "count = %u, max_entries = %u\n", count, max_entries);
+ map_batch_verify(visited, max_entries, keys, values, is_pcpu);
+
+ /* bpf_map_get_next_key() should return -ENOENT for an empty map. */
+ err = bpf_map_get_next_key(map_fd, NULL, &key);
+ CHECK(!err, "bpf_map_get_next_key()", "error: %s\n", strerror(errno));
+
+ /* test 4: lookup/delete in a loop with various steps. */
+ total_success = 0;
+ for (step = 1; step < max_entries; step++) {
+ map_batch_update(map_fd, max_entries, keys, values, is_pcpu);
+ memset(keys, 0, max_entries * sizeof(*keys));
+ memset(values, 0, max_entries * value_size);
+ total = 0;
+ /* iteratively lookup/delete elements with 'step'
+ * elements each
+ */
+ count = step;
+ nospace_err = false;
+ while (true) {
+ err = bpf_map_lookup_batch(map_fd,
+ total ? &batch : NULL,
+ &batch, keys + total,
+ values +
+ total * value_size,
+ &count, &opts);
+ /* It is possible that we are failing due to buffer size
+ * not big enough. In such cases, let us just exit and
+ * go with large steps. Not that a buffer size with
+ * max_entries should always work.
+ */
+ if (err && errno == ENOSPC) {
+ nospace_err = true;
+ break;
+ }
+
+ CHECK((err && errno != ENOENT), "lookup with steps",
+ "error: %s\n", strerror(errno));
+
+ total += count;
+ if (err)
+ break;
+
+ }
+ if (nospace_err == true)
+ continue;
+
+ CHECK(total != max_entries, "lookup with steps",
+ "total = %u, max_entries = %u\n", total, max_entries);
+ map_batch_verify(visited, max_entries, keys, values, is_pcpu);
+
+ total = 0;
+ count = step;
+ while (total < max_entries) {
+ if (max_entries - total < step)
+ count = max_entries - total;
+ err = bpf_map_delete_batch(map_fd,
+ keys + total,
+ &count, &opts);
+ CHECK((err && errno != ENOENT), "delete batch",
+ "error: %s\n", strerror(errno));
+ total += count;
+ if (err)
+ break;
+ }
+ CHECK(total != max_entries, "delete with steps",
+ "total = %u, max_entries = %u\n", total, max_entries);
+
+ /* check map is empty, errono == ENOENT */
+ err = bpf_map_get_next_key(map_fd, NULL, &key);
+ CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()",
+ "error: %s\n", strerror(errno));
+
+ /* iteratively lookup/delete elements with 'step'
+ * elements each
+ */
+ map_batch_update(map_fd, max_entries, keys, values, is_pcpu);
+ memset(keys, 0, max_entries * sizeof(*keys));
+ memset(values, 0, max_entries * value_size);
+ total = 0;
+ count = step;
+ nospace_err = false;
+ while (true) {
+ err = bpf_map_lookup_and_delete_batch(map_fd,
+ total ? &batch : NULL,
+ &batch, keys + total,
+ values +
+ total * value_size,
+ &count, &opts);
+ /* It is possible that we are failing due to buffer size
+ * not big enough. In such cases, let us just exit and
+ * go with large steps. Not that a buffer size with
+ * max_entries should always work.
+ */
+ if (err && errno == ENOSPC) {
+ nospace_err = true;
+ break;
+ }
+
+ CHECK((err && errno != ENOENT), "lookup with steps",
+ "error: %s\n", strerror(errno));
+
+ total += count;
+ if (err)
+ break;
+ }
+
+ if (nospace_err == true)
+ continue;
+
+ CHECK(total != max_entries, "lookup/delete with steps",
+ "total = %u, max_entries = %u\n", total, max_entries);
+
+ map_batch_verify(visited, max_entries, keys, values, is_pcpu);
+ err = bpf_map_get_next_key(map_fd, NULL, &key);
+ CHECK(!err, "bpf_map_get_next_key()", "error: %s\n",
+ strerror(errno));
+
+ total_success++;
+ }
+
+ CHECK(total_success == 0, "check total_success",
+ "unexpected failure\n");
+ free(keys);
+ free(visited);
+ if (!is_pcpu)
+ free(values);
+}
+
+void htab_map_batch_ops(void)
+{
+ __test_map_lookup_and_delete_batch(false);
+ printf("test_%s:PASS\n", __func__);
+}
+
+void htab_percpu_map_batch_ops(void)
+{
+ __test_map_lookup_and_delete_batch(true);
+ printf("test_%s:PASS\n", __func__);
+}
+
+void test_htab_map_batch_ops(void)
+{
+ htab_map_batch_ops();
+ htab_percpu_map_batch_ops();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
new file mode 100644
index 0000000..8482bbc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <linux/err.h>
+#include <test_progs.h>
+#include "bpf_dctcp.skel.h"
+#include "bpf_cubic.skel.h"
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+static const struct timeval timeo_sec = { .tv_sec = 10 };
+static const size_t timeo_optlen = sizeof(timeo_sec);
+static int stop, duration;
+
+static int settimeo(int fd)
+{
+ int err;
+
+ err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
+ timeo_optlen);
+ if (CHECK(err == -1, "setsockopt(fd, SO_RCVTIMEO)", "errno:%d\n",
+ errno))
+ return -1;
+
+ err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec,
+ timeo_optlen);
+ if (CHECK(err == -1, "setsockopt(fd, SO_SNDTIMEO)", "errno:%d\n",
+ errno))
+ return -1;
+
+ return 0;
+}
+
+static int settcpca(int fd, const char *tcp_ca)
+{
+ int err;
+
+ err = setsockopt(fd, IPPROTO_TCP, TCP_CONGESTION, tcp_ca, strlen(tcp_ca));
+ if (CHECK(err == -1, "setsockopt(fd, TCP_CONGESTION)", "errno:%d\n",
+ errno))
+ return -1;
+
+ return 0;
+}
+
+static void *server(void *arg)
+{
+ int lfd = (int)(long)arg, err = 0, fd;
+ ssize_t nr_sent = 0, bytes = 0;
+ char batch[1500];
+
+ fd = accept(lfd, NULL, NULL);
+ while (fd == -1) {
+ if (errno == EINTR)
+ continue;
+ err = -errno;
+ goto done;
+ }
+
+ if (settimeo(fd)) {
+ err = -errno;
+ goto done;
+ }
+
+ while (bytes < total_bytes && !READ_ONCE(stop)) {
+ nr_sent = send(fd, &batch,
+ min(total_bytes - bytes, sizeof(batch)), 0);
+ if (nr_sent == -1 && errno == EINTR)
+ continue;
+ if (nr_sent == -1) {
+ err = -errno;
+ break;
+ }
+ bytes += nr_sent;
+ }
+
+ CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n",
+ bytes, total_bytes, nr_sent, errno);
+
+done:
+ if (fd != -1)
+ close(fd);
+ if (err) {
+ WRITE_ONCE(stop, 1);
+ return ERR_PTR(err);
+ }
+ return NULL;
+}
+
+static void do_test(const char *tcp_ca)
+{
+ struct sockaddr_in6 sa6 = {};
+ ssize_t nr_recv = 0, bytes = 0;
+ int lfd = -1, fd = -1;
+ pthread_t srv_thread;
+ socklen_t addrlen = sizeof(sa6);
+ void *thread_ret;
+ char batch[1500];
+ int err;
+
+ WRITE_ONCE(stop, 0);
+
+ lfd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (CHECK(lfd == -1, "socket", "errno:%d\n", errno))
+ return;
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) {
+ close(lfd);
+ return;
+ }
+
+ if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) ||
+ settimeo(lfd) || settimeo(fd))
+ goto done;
+
+ /* bind, listen and start server thread to accept */
+ sa6.sin6_family = AF_INET6;
+ sa6.sin6_addr = in6addr_loopback;
+ err = bind(lfd, (struct sockaddr *)&sa6, addrlen);
+ if (CHECK(err == -1, "bind", "errno:%d\n", errno))
+ goto done;
+ err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen);
+ if (CHECK(err == -1, "getsockname", "errno:%d\n", errno))
+ goto done;
+ err = listen(lfd, 1);
+ if (CHECK(err == -1, "listen", "errno:%d\n", errno))
+ goto done;
+ err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
+ if (CHECK(err != 0, "pthread_create", "err:%d\n", err))
+ goto done;
+
+ /* connect to server */
+ err = connect(fd, (struct sockaddr *)&sa6, addrlen);
+ if (CHECK(err == -1, "connect", "errno:%d\n", errno))
+ goto wait_thread;
+
+ /* recv total_bytes */
+ while (bytes < total_bytes && !READ_ONCE(stop)) {
+ nr_recv = recv(fd, &batch,
+ min(total_bytes - bytes, sizeof(batch)), 0);
+ if (nr_recv == -1 && errno == EINTR)
+ continue;
+ if (nr_recv == -1)
+ break;
+ bytes += nr_recv;
+ }
+
+ CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n",
+ bytes, total_bytes, nr_recv, errno);
+
+wait_thread:
+ WRITE_ONCE(stop, 1);
+ pthread_join(srv_thread, &thread_ret);
+ CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld",
+ PTR_ERR(thread_ret));
+done:
+ close(lfd);
+ close(fd);
+}
+
+static void test_cubic(void)
+{
+ struct bpf_cubic *cubic_skel;
+ struct bpf_link *link;
+
+ cubic_skel = bpf_cubic__open_and_load();
+ if (CHECK(!cubic_skel, "bpf_cubic__open_and_load", "failed\n"))
+ return;
+
+ link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic);
+ if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
+ PTR_ERR(link))) {
+ bpf_cubic__destroy(cubic_skel);
+ return;
+ }
+
+ do_test("bpf_cubic");
+
+ bpf_link__destroy(link);
+ bpf_cubic__destroy(cubic_skel);
+}
+
+static void test_dctcp(void)
+{
+ struct bpf_dctcp *dctcp_skel;
+ struct bpf_link *link;
+
+ dctcp_skel = bpf_dctcp__open_and_load();
+ if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n"))
+ return;
+
+ link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
+ if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
+ PTR_ERR(link))) {
+ bpf_dctcp__destroy(dctcp_skel);
+ return;
+ }
+
+ do_test("bpf_dctcp");
+
+ bpf_link__destroy(link);
+ bpf_dctcp__destroy(dctcp_skel);
+}
+
+void test_bpf_tcp_ca(void)
+{
+ if (test__start_subtest("dctcp"))
+ test_dctcp();
+ if (test__start_subtest("cubic"))
+ test_cubic();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 9486c13..e9f2f12 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -48,6 +48,8 @@ void test_bpf_verif_scale(void)
{ "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS },
{ "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS },
+ { "pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
+
/* full unroll by llvm */
{ "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
{ "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
diff --git a/tools/testing/selftests/bpf/prog_tests/cpu_mask.c b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c
index 1fa1bdb..f7c7e25 100644
--- a/tools/testing/selftests/bpf/prog_tests/cpu_mask.c
+++ b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
#include <bpf/btf.h>
-#include "libbpf_internal.h"
+#include "bpf/libbpf_internal.h"
static int duration = 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index b426bf2..db5c74d 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -26,7 +26,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
link = calloc(sizeof(struct bpf_link *), prog_cnt);
prog = calloc(sizeof(struct bpf_program *), prog_cnt);
- result = malloc(prog_cnt * sizeof(u64));
+ result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64));
if (CHECK(!link || !prog || !result, "alloc_memory",
"failed to alloc memory"))
goto close_prog;
@@ -98,6 +98,24 @@ static void test_target_yes_callees(void)
"fexit/test_pkt_access",
"fexit/test_pkt_access_subprog1",
"fexit/test_pkt_access_subprog2",
+ "fexit/test_pkt_access_subprog3",
+ };
+ test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
+ "./test_pkt_access.o",
+ ARRAY_SIZE(prog_name),
+ prog_name);
+}
+
+static void test_func_replace(void)
+{
+ const char *prog_name[] = {
+ "fexit/test_pkt_access",
+ "fexit/test_pkt_access_subprog1",
+ "fexit/test_pkt_access_subprog2",
+ "fexit/test_pkt_access_subprog3",
+ "freplace/get_skb_len",
+ "freplace/get_skb_ifindex",
+ "freplace/get_constant",
};
test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
"./test_pkt_access.o",
@@ -109,4 +127,5 @@ void test_fexit_bpf2bpf(void)
{
test_target_no_callees();
test_target_yes_callees();
+ test_func_replace();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index cf6c879..1450ea2 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -4,7 +4,7 @@
#include <sched.h>
#include <sys/socket.h>
#include <test_progs.h>
-#include "libbpf_internal.h"
+#include "bpf/libbpf_internal.h"
static void on_sample(void *ctx, int cpu, void *data, __u32 size)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index b607112..504abb7 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include "test_send_signal_kern.skel.h"
static volatile int sigusr1_received = 0;
@@ -9,17 +10,15 @@ static void sigusr1_handler(int signum)
}
static void test_send_signal_common(struct perf_event_attr *attr,
- int prog_type,
+ bool signal_thread,
const char *test_name)
{
- int err = -1, pmu_fd, prog_fd, info_map_fd, status_map_fd;
- const char *file = "./test_send_signal_kern.o";
- struct bpf_object *obj = NULL;
+ struct test_send_signal_kern *skel;
int pipe_c2p[2], pipe_p2c[2];
- __u32 key = 0, duration = 0;
+ int err = -1, pmu_fd = -1;
+ __u32 duration = 0;
char buf[256];
pid_t pid;
- __u64 val;
if (CHECK(pipe(pipe_c2p), test_name,
"pipe pipe_c2p error: %s\n", strerror(errno)))
@@ -73,45 +72,39 @@ static void test_send_signal_common(struct perf_event_attr *attr,
close(pipe_c2p[1]); /* close write */
close(pipe_p2c[0]); /* close read */
- err = bpf_prog_load(file, prog_type, &obj, &prog_fd);
- if (CHECK(err < 0, test_name, "bpf_prog_load error: %s\n",
- strerror(errno)))
- goto prog_load_failure;
+ skel = test_send_signal_kern__open_and_load();
+ if (CHECK(!skel, "skel_open_and_load", "skeleton open_and_load failed\n"))
+ goto skel_open_load_failure;
- pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1,
- -1 /* group id */, 0 /* flags */);
- if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n",
- strerror(errno))) {
- err = -1;
- goto close_prog;
+ if (!attr) {
+ err = test_send_signal_kern__attach(skel);
+ if (CHECK(err, "skel_attach", "skeleton attach failed\n")) {
+ err = -1;
+ goto destroy_skel;
+ }
+ } else {
+ pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1,
+ -1 /* group id */, 0 /* flags */);
+ if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n",
+ strerror(errno))) {
+ err = -1;
+ goto destroy_skel;
+ }
+
+ skel->links.send_signal_perf =
+ bpf_program__attach_perf_event(skel->progs.send_signal_perf, pmu_fd);
+ if (CHECK(IS_ERR(skel->links.send_signal_perf), "attach_perf_event",
+ "err %ld\n", PTR_ERR(skel->links.send_signal_perf)))
+ goto disable_pmu;
}
- err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
- if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_enable error: %s\n",
- strerror(errno)))
- goto disable_pmu;
-
- err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
- if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_set_bpf error: %s\n",
- strerror(errno)))
- goto disable_pmu;
-
- err = -1;
- info_map_fd = bpf_object__find_map_fd_by_name(obj, "info_map");
- if (CHECK(info_map_fd < 0, test_name, "find map %s error\n", "info_map"))
- goto disable_pmu;
-
- status_map_fd = bpf_object__find_map_fd_by_name(obj, "status_map");
- if (CHECK(status_map_fd < 0, test_name, "find map %s error\n", "status_map"))
- goto disable_pmu;
-
/* wait until child signal handler installed */
read(pipe_c2p[0], buf, 1);
/* trigger the bpf send_signal */
- key = 0;
- val = (((__u64)(SIGUSR1)) << 32) | pid;
- bpf_map_update_elem(info_map_fd, &key, &val, 0);
+ skel->bss->pid = pid;
+ skel->bss->sig = SIGUSR1;
+ skel->bss->signal_thread = signal_thread;
/* notify child that bpf program can send_signal now */
write(pipe_p2c[1], buf, 1);
@@ -132,46 +125,20 @@ static void test_send_signal_common(struct perf_event_attr *attr,
disable_pmu:
close(pmu_fd);
-close_prog:
- bpf_object__close(obj);
-prog_load_failure:
+destroy_skel:
+ test_send_signal_kern__destroy(skel);
+skel_open_load_failure:
close(pipe_c2p[0]);
close(pipe_p2c[1]);
wait(NULL);
}
-static void test_send_signal_tracepoint(void)
+static void test_send_signal_tracepoint(bool signal_thread)
{
- const char *id_path = "/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id";
- struct perf_event_attr attr = {
- .type = PERF_TYPE_TRACEPOINT,
- .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN,
- .sample_period = 1,
- .wakeup_events = 1,
- };
- __u32 duration = 0;
- int bytes, efd;
- char buf[256];
-
- efd = open(id_path, O_RDONLY, 0);
- if (CHECK(efd < 0, "tracepoint",
- "open syscalls/sys_enter_nanosleep/id failure: %s\n",
- strerror(errno)))
- return;
-
- bytes = read(efd, buf, sizeof(buf));
- close(efd);
- if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "tracepoint",
- "read syscalls/sys_enter_nanosleep/id failure: %s\n",
- strerror(errno)))
- return;
-
- attr.config = strtol(buf, NULL, 0);
-
- test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint");
+ test_send_signal_common(NULL, signal_thread, "tracepoint");
}
-static void test_send_signal_perf(void)
+static void test_send_signal_perf(bool signal_thread)
{
struct perf_event_attr attr = {
.sample_period = 1,
@@ -179,15 +146,13 @@ static void test_send_signal_perf(void)
.config = PERF_COUNT_SW_CPU_CLOCK,
};
- test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
- "perf_sw_event");
+ test_send_signal_common(&attr, signal_thread, "perf_sw_event");
}
-static void test_send_signal_nmi(void)
+static void test_send_signal_nmi(bool signal_thread)
{
struct perf_event_attr attr = {
- .sample_freq = 50,
- .freq = 1,
+ .sample_period = 1,
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES,
};
@@ -210,16 +175,21 @@ static void test_send_signal_nmi(void)
close(pmu_fd);
}
- test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
- "perf_hw_event");
+ test_send_signal_common(&attr, signal_thread, "perf_hw_event");
}
void test_send_signal(void)
{
if (test__start_subtest("send_signal_tracepoint"))
- test_send_signal_tracepoint();
+ test_send_signal_tracepoint(false);
if (test__start_subtest("send_signal_perf"))
- test_send_signal_perf();
+ test_send_signal_perf(false);
if (test__start_subtest("send_signal_nmi"))
- test_send_signal_nmi();
+ test_send_signal_nmi(false);
+ if (test__start_subtest("send_signal_tracepoint_thread"))
+ test_send_signal_tracepoint(true);
+ if (test__start_subtest("send_signal_perf_thread"))
+ test_send_signal_perf(true);
+ if (test__start_subtest("send_signal_nmi_thread"))
+ test_send_signal_nmi(true);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
index 8974450..f002e30 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@@ -49,8 +49,12 @@ void test_stacktrace_build_id_nmi(void)
pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
0 /* cpu 0 */, -1 /* group id */,
0 /* flags */);
- if (CHECK(pmu_fd < 0, "perf_event_open",
- "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n",
+ if (pmu_fd < 0 && errno == ENOENT) {
+ printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__);
+ test__skip();
+ goto cleanup;
+ }
+ if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
pmu_fd, errno))
goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
new file mode 100644
index 0000000..25b0685
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+
+const char *err_str;
+bool found;
+
+static int libbpf_debug_print(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ char *log_buf;
+
+ if (level != LIBBPF_WARN ||
+ strcmp(format, "libbpf: \n%s\n")) {
+ vprintf(format, args);
+ return 0;
+ }
+
+ log_buf = va_arg(args, char *);
+ if (!log_buf)
+ goto out;
+ if (strstr(log_buf, err_str) == 0)
+ found = true;
+out:
+ printf(format, log_buf);
+ return 0;
+}
+
+extern int extra_prog_load_log_flags;
+
+static int check_load(const char *file)
+{
+ struct bpf_prog_load_attr attr;
+ struct bpf_object *obj = NULL;
+ int err, prog_fd;
+
+ memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
+ attr.file = file;
+ attr.prog_type = BPF_PROG_TYPE_UNSPEC;
+ attr.log_level = extra_prog_load_log_flags;
+ attr.prog_flags = BPF_F_TEST_RND_HI32;
+ found = false;
+ err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+ bpf_object__close(obj);
+ return err;
+}
+
+struct test_def {
+ const char *file;
+ const char *err_str;
+};
+
+void test_test_global_funcs(void)
+{
+ struct test_def tests[] = {
+ { "test_global_func1.o", "combined stack size of 4 calls is 544" },
+ { "test_global_func2.o" },
+ { "test_global_func3.o" , "the call stack of 8 frames" },
+ { "test_global_func4.o" },
+ { "test_global_func5.o" , "expected pointer to ctx, but got PTR" },
+ { "test_global_func6.o" , "modified ctx ptr R2" },
+ { "test_global_func7.o" , "foo() doesn't return scalar" },
+ };
+ libbpf_print_fn_t old_print_fn = NULL;
+ int err, i, duration = 0;
+
+ old_print_fn = libbpf_set_print(libbpf_debug_print);
+
+ for (i = 0; i < ARRAY_SIZE(tests); i++) {
+ const struct test_def *test = &tests[i];
+
+ if (!test__start_subtest(test->file))
+ continue;
+
+ err_str = test->err_str;
+ err = check_load(test->file);
+ CHECK_FAIL(!!err ^ !!err_str);
+ if (err_str)
+ CHECK(found, "", "expected string '%s'", err_str);
+ }
+ libbpf_set_print(old_print_fn);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
index c32aa28..465b371 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2019 Facebook */
#define _GNU_SOURCE
#include <sched.h>
+#include <sys/prctl.h>
#include <test_progs.h>
#define MAX_CNT 100000
@@ -17,7 +18,7 @@ static __u64 time_get_ns(void)
static int test_task_rename(const char *prog)
{
int i, fd, duration = 0, err;
- char buf[] = "test\n";
+ char buf[] = "test_overhead";
__u64 start_time;
fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
@@ -66,6 +67,10 @@ void test_test_overhead(void)
struct bpf_object *obj;
struct bpf_link *link;
int err, duration = 0;
+ char comm[16] = {};
+
+ if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L)))
+ return;
obj = bpf_object__open_file("./test_overhead.o", NULL);
if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
@@ -138,5 +143,6 @@ void test_test_overhead(void)
test_run("fexit");
bpf_link__destroy(link);
cleanup:
+ prctl(PR_SET_NAME, comm, 0L, 0L, 0L);
bpf_object__close(obj);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
new file mode 100644
index 0000000..6b56bdc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <net/if.h>
+#include "test_xdp.skel.h"
+#include "test_xdp_bpf2bpf.skel.h"
+
+void test_xdp_bpf2bpf(void)
+{
+ __u32 duration = 0, retval, size;
+ char buf[128];
+ int err, pkt_fd, map_fd;
+ struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+ struct iptnl_info value4 = {.family = AF_INET};
+ struct test_xdp *pkt_skel = NULL;
+ struct test_xdp_bpf2bpf *ftrace_skel = NULL;
+ struct vip key4 = {.protocol = 6, .family = AF_INET};
+ DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+
+ /* Load XDP program to introspect */
+ pkt_skel = test_xdp__open_and_load();
+ if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n"))
+ return;
+
+ pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel);
+
+ map_fd = bpf_map__fd(pkt_skel->maps.vip2tnl);
+ bpf_map_update_elem(map_fd, &key4, &value4, 0);
+
+ /* Load trace program */
+ opts.attach_prog_fd = pkt_fd,
+ ftrace_skel = test_xdp_bpf2bpf__open_opts(&opts);
+ if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n"))
+ goto out;
+
+ err = test_xdp_bpf2bpf__load(ftrace_skel);
+ if (CHECK(err, "__load", "ftrace skeleton failed\n"))
+ goto out;
+
+ err = test_xdp_bpf2bpf__attach(ftrace_skel);
+ if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err))
+ goto out;
+
+ /* Run test program */
+ err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ buf, &size, &retval, &duration);
+
+ if (CHECK(err || retval != XDP_TX || size != 74 ||
+ iph->protocol != IPPROTO_IPIP, "ipv4",
+ "err %d errno %d retval %d size %d\n",
+ err, errno, retval, size))
+ goto out;
+
+ /* Verify test results */
+ if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"),
+ "result", "fentry failed err %llu\n",
+ ftrace_skel->bss->test_result_fentry))
+ goto out;
+
+ CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result",
+ "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit);
+
+out:
+ test_xdp__destroy(pkt_skel);
+ test_xdp_bpf2bpf__destroy(ftrace_skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
new file mode 100644
index 0000000..7897c8f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -0,0 +1,544 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* WARNING: This implemenation is not necessarily the same
+ * as the tcp_cubic.c. The purpose is mainly for testing
+ * the kernel BPF logic.
+ *
+ * Highlights:
+ * 1. CONFIG_HZ .kconfig map is used.
+ * 2. In bictcp_update(), calculation is changed to use usec
+ * resolution (i.e. USEC_PER_JIFFY) instead of using jiffies.
+ * Thus, usecs_to_jiffies() is not used in the bpf_cubic.c.
+ * 3. In bitctcp_update() [under tcp_friendliness], the original
+ * "while (ca->ack_cnt > delta)" loop is changed to the equivalent
+ * "ca->ack_cnt / delta" operation.
+ */
+
+#include <linux/bpf.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
+
+#define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation
+ * max_cwnd = snd_cwnd * beta
+ */
+#define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */
+
+/* Two methods of hybrid slow start */
+#define HYSTART_ACK_TRAIN 0x1
+#define HYSTART_DELAY 0x2
+
+/* Number of delay samples for detecting the increase of delay */
+#define HYSTART_MIN_SAMPLES 8
+#define HYSTART_DELAY_MIN (4000U) /* 4ms */
+#define HYSTART_DELAY_MAX (16000U) /* 16 ms */
+#define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX)
+
+static int fast_convergence = 1;
+static const int beta = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */
+static int initial_ssthresh;
+static const int bic_scale = 41;
+static int tcp_friendliness = 1;
+
+static int hystart = 1;
+static int hystart_detect = HYSTART_ACK_TRAIN | HYSTART_DELAY;
+static int hystart_low_window = 16;
+static int hystart_ack_delta_us = 2000;
+
+static const __u32 cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */
+static const __u32 beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3
+ / (BICTCP_BETA_SCALE - beta);
+/* calculate the "K" for (wmax-cwnd) = c/rtt * K^3
+ * so K = cubic_root( (wmax-cwnd)*rtt/c )
+ * the unit of K is bictcp_HZ=2^10, not HZ
+ *
+ * c = bic_scale >> 10
+ * rtt = 100ms
+ *
+ * the following code has been designed and tested for
+ * cwnd < 1 million packets
+ * RTT < 100 seconds
+ * HZ < 1,000,00 (corresponding to 10 nano-second)
+ */
+
+/* 1/c * 2^2*bictcp_HZ * srtt, 2^40 */
+static const __u64 cube_factor = (__u64)(1ull << (10+3*BICTCP_HZ))
+ / (bic_scale * 10);
+
+/* BIC TCP Parameters */
+struct bictcp {
+ __u32 cnt; /* increase cwnd by 1 after ACKs */
+ __u32 last_max_cwnd; /* last maximum snd_cwnd */
+ __u32 last_cwnd; /* the last snd_cwnd */
+ __u32 last_time; /* time when updated last_cwnd */
+ __u32 bic_origin_point;/* origin point of bic function */
+ __u32 bic_K; /* time to origin point
+ from the beginning of the current epoch */
+ __u32 delay_min; /* min delay (usec) */
+ __u32 epoch_start; /* beginning of an epoch */
+ __u32 ack_cnt; /* number of acks */
+ __u32 tcp_cwnd; /* estimated tcp cwnd */
+ __u16 unused;
+ __u8 sample_cnt; /* number of samples to decide curr_rtt */
+ __u8 found; /* the exit point is found? */
+ __u32 round_start; /* beginning of each round */
+ __u32 end_seq; /* end_seq of the round */
+ __u32 last_ack; /* last time when the ACK spacing is close */
+ __u32 curr_rtt; /* the minimum rtt of current round */
+};
+
+static inline void bictcp_reset(struct bictcp *ca)
+{
+ ca->cnt = 0;
+ ca->last_max_cwnd = 0;
+ ca->last_cwnd = 0;
+ ca->last_time = 0;
+ ca->bic_origin_point = 0;
+ ca->bic_K = 0;
+ ca->delay_min = 0;
+ ca->epoch_start = 0;
+ ca->ack_cnt = 0;
+ ca->tcp_cwnd = 0;
+ ca->found = 0;
+}
+
+extern unsigned long CONFIG_HZ __kconfig;
+#define HZ CONFIG_HZ
+#define USEC_PER_MSEC 1000UL
+#define USEC_PER_SEC 1000000UL
+#define USEC_PER_JIFFY (USEC_PER_SEC / HZ)
+
+static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor)
+{
+ return dividend / divisor;
+}
+
+#define div64_ul div64_u64
+
+#define BITS_PER_U64 (sizeof(__u64) * 8)
+static __always_inline int fls64(__u64 x)
+{
+ int num = BITS_PER_U64 - 1;
+
+ if (x == 0)
+ return 0;
+
+ if (!(x & (~0ull << (BITS_PER_U64-32)))) {
+ num -= 32;
+ x <<= 32;
+ }
+ if (!(x & (~0ull << (BITS_PER_U64-16)))) {
+ num -= 16;
+ x <<= 16;
+ }
+ if (!(x & (~0ull << (BITS_PER_U64-8)))) {
+ num -= 8;
+ x <<= 8;
+ }
+ if (!(x & (~0ull << (BITS_PER_U64-4)))) {
+ num -= 4;
+ x <<= 4;
+ }
+ if (!(x & (~0ull << (BITS_PER_U64-2)))) {
+ num -= 2;
+ x <<= 2;
+ }
+ if (!(x & (~0ull << (BITS_PER_U64-1))))
+ num -= 1;
+
+ return num + 1;
+}
+
+static __always_inline __u32 bictcp_clock_us(const struct sock *sk)
+{
+ return tcp_sk(sk)->tcp_mstamp;
+}
+
+static __always_inline void bictcp_hystart_reset(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ ca->round_start = ca->last_ack = bictcp_clock_us(sk);
+ ca->end_seq = tp->snd_nxt;
+ ca->curr_rtt = ~0U;
+ ca->sample_cnt = 0;
+}
+
+/* "struct_ops/" prefix is not a requirement
+ * It will be recognized as BPF_PROG_TYPE_STRUCT_OPS
+ * as long as it is used in one of the func ptr
+ * under SEC(".struct_ops").
+ */
+SEC("struct_ops/bictcp_init")
+void BPF_PROG(bictcp_init, struct sock *sk)
+{
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ bictcp_reset(ca);
+
+ if (hystart)
+ bictcp_hystart_reset(sk);
+
+ if (!hystart && initial_ssthresh)
+ tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
+}
+
+/* No prefix in SEC will also work.
+ * The remaining tcp-cubic functions have an easier way.
+ */
+SEC("no-sec-prefix-bictcp_cwnd_event")
+void BPF_PROG(bictcp_cwnd_event, struct sock *sk, enum tcp_ca_event event)
+{
+ if (event == CA_EVENT_TX_START) {
+ struct bictcp *ca = inet_csk_ca(sk);
+ __u32 now = tcp_jiffies32;
+ __s32 delta;
+
+ delta = now - tcp_sk(sk)->lsndtime;
+
+ /* We were application limited (idle) for a while.
+ * Shift epoch_start to keep cwnd growth to cubic curve.
+ */
+ if (ca->epoch_start && delta > 0) {
+ ca->epoch_start += delta;
+ if (after(ca->epoch_start, now))
+ ca->epoch_start = now;
+ }
+ return;
+ }
+}
+
+/*
+ * cbrt(x) MSB values for x MSB values in [0..63].
+ * Precomputed then refined by hand - Willy Tarreau
+ *
+ * For x in [0..63],
+ * v = cbrt(x << 18) - 1
+ * cbrt(x) = (v[x] + 10) >> 6
+ */
+static const __u8 v[] = {
+ /* 0x00 */ 0, 54, 54, 54, 118, 118, 118, 118,
+ /* 0x08 */ 123, 129, 134, 138, 143, 147, 151, 156,
+ /* 0x10 */ 157, 161, 164, 168, 170, 173, 176, 179,
+ /* 0x18 */ 181, 185, 187, 190, 192, 194, 197, 199,
+ /* 0x20 */ 200, 202, 204, 206, 209, 211, 213, 215,
+ /* 0x28 */ 217, 219, 221, 222, 224, 225, 227, 229,
+ /* 0x30 */ 231, 232, 234, 236, 237, 239, 240, 242,
+ /* 0x38 */ 244, 245, 246, 248, 250, 251, 252, 254,
+};
+
+/* calculate the cubic root of x using a table lookup followed by one
+ * Newton-Raphson iteration.
+ * Avg err ~= 0.195%
+ */
+static __always_inline __u32 cubic_root(__u64 a)
+{
+ __u32 x, b, shift;
+
+ if (a < 64) {
+ /* a in [0..63] */
+ return ((__u32)v[(__u32)a] + 35) >> 6;
+ }
+
+ b = fls64(a);
+ b = ((b * 84) >> 8) - 1;
+ shift = (a >> (b * 3));
+
+ /* it is needed for verifier's bound check on v */
+ if (shift >= 64)
+ return 0;
+
+ x = ((__u32)(((__u32)v[shift] + 10) << b)) >> 6;
+
+ /*
+ * Newton-Raphson iteration
+ * 2
+ * x = ( 2 * x + a / x ) / 3
+ * k+1 k k
+ */
+ x = (2 * x + (__u32)div64_u64(a, (__u64)x * (__u64)(x - 1)));
+ x = ((x * 341) >> 10);
+ return x;
+}
+
+/*
+ * Compute congestion window to use.
+ */
+static __always_inline void bictcp_update(struct bictcp *ca, __u32 cwnd,
+ __u32 acked)
+{
+ __u32 delta, bic_target, max_cnt;
+ __u64 offs, t;
+
+ ca->ack_cnt += acked; /* count the number of ACKed packets */
+
+ if (ca->last_cwnd == cwnd &&
+ (__s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32)
+ return;
+
+ /* The CUBIC function can update ca->cnt at most once per jiffy.
+ * On all cwnd reduction events, ca->epoch_start is set to 0,
+ * which will force a recalculation of ca->cnt.
+ */
+ if (ca->epoch_start && tcp_jiffies32 == ca->last_time)
+ goto tcp_friendliness;
+
+ ca->last_cwnd = cwnd;
+ ca->last_time = tcp_jiffies32;
+
+ if (ca->epoch_start == 0) {
+ ca->epoch_start = tcp_jiffies32; /* record beginning */
+ ca->ack_cnt = acked; /* start counting */
+ ca->tcp_cwnd = cwnd; /* syn with cubic */
+
+ if (ca->last_max_cwnd <= cwnd) {
+ ca->bic_K = 0;
+ ca->bic_origin_point = cwnd;
+ } else {
+ /* Compute new K based on
+ * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ)
+ */
+ ca->bic_K = cubic_root(cube_factor
+ * (ca->last_max_cwnd - cwnd));
+ ca->bic_origin_point = ca->last_max_cwnd;
+ }
+ }
+
+ /* cubic function - calc*/
+ /* calculate c * time^3 / rtt,
+ * while considering overflow in calculation of time^3
+ * (so time^3 is done by using 64 bit)
+ * and without the support of division of 64bit numbers
+ * (so all divisions are done by using 32 bit)
+ * also NOTE the unit of those veriables
+ * time = (t - K) / 2^bictcp_HZ
+ * c = bic_scale >> 10
+ * rtt = (srtt >> 3) / HZ
+ * !!! The following code does not have overflow problems,
+ * if the cwnd < 1 million packets !!!
+ */
+
+ t = (__s32)(tcp_jiffies32 - ca->epoch_start) * USEC_PER_JIFFY;
+ t += ca->delay_min;
+ /* change the unit from usec to bictcp_HZ */
+ t <<= BICTCP_HZ;
+ t /= USEC_PER_SEC;
+
+ if (t < ca->bic_K) /* t - K */
+ offs = ca->bic_K - t;
+ else
+ offs = t - ca->bic_K;
+
+ /* c/rtt * (t-K)^3 */
+ delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ);
+ if (t < ca->bic_K) /* below origin*/
+ bic_target = ca->bic_origin_point - delta;
+ else /* above origin*/
+ bic_target = ca->bic_origin_point + delta;
+
+ /* cubic function - calc bictcp_cnt*/
+ if (bic_target > cwnd) {
+ ca->cnt = cwnd / (bic_target - cwnd);
+ } else {
+ ca->cnt = 100 * cwnd; /* very small increment*/
+ }
+
+ /*
+ * The initial growth of cubic function may be too conservative
+ * when the available bandwidth is still unknown.
+ */
+ if (ca->last_max_cwnd == 0 && ca->cnt > 20)
+ ca->cnt = 20; /* increase cwnd 5% per RTT */
+
+tcp_friendliness:
+ /* TCP Friendly */
+ if (tcp_friendliness) {
+ __u32 scale = beta_scale;
+ __u32 n;
+
+ /* update tcp cwnd */
+ delta = (cwnd * scale) >> 3;
+ if (ca->ack_cnt > delta && delta) {
+ n = ca->ack_cnt / delta;
+ ca->ack_cnt -= n * delta;
+ ca->tcp_cwnd += n;
+ }
+
+ if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */
+ delta = ca->tcp_cwnd - cwnd;
+ max_cnt = cwnd / delta;
+ if (ca->cnt > max_cnt)
+ ca->cnt = max_cnt;
+ }
+ }
+
+ /* The maximum rate of cwnd increase CUBIC allows is 1 packet per
+ * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT.
+ */
+ ca->cnt = max(ca->cnt, 2U);
+}
+
+/* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */
+void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ if (!tcp_is_cwnd_limited(sk))
+ return;
+
+ if (tcp_in_slow_start(tp)) {
+ if (hystart && after(ack, ca->end_seq))
+ bictcp_hystart_reset(sk);
+ acked = tcp_slow_start(tp, acked);
+ if (!acked)
+ return;
+ }
+ bictcp_update(ca, tp->snd_cwnd, acked);
+ tcp_cong_avoid_ai(tp, ca->cnt, acked);
+}
+
+__u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ ca->epoch_start = 0; /* end of epoch */
+
+ /* Wmax and fast convergence */
+ if (tp->snd_cwnd < ca->last_max_cwnd && fast_convergence)
+ ca->last_max_cwnd = (tp->snd_cwnd * (BICTCP_BETA_SCALE + beta))
+ / (2 * BICTCP_BETA_SCALE);
+ else
+ ca->last_max_cwnd = tp->snd_cwnd;
+
+ return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
+}
+
+void BPF_STRUCT_OPS(bictcp_state, struct sock *sk, __u8 new_state)
+{
+ if (new_state == TCP_CA_Loss) {
+ bictcp_reset(inet_csk_ca(sk));
+ bictcp_hystart_reset(sk);
+ }
+}
+
+#define GSO_MAX_SIZE 65536
+
+/* Account for TSO/GRO delays.
+ * Otherwise short RTT flows could get too small ssthresh, since during
+ * slow start we begin with small TSO packets and ca->delay_min would
+ * not account for long aggregation delay when TSO packets get bigger.
+ * Ideally even with a very small RTT we would like to have at least one
+ * TSO packet being sent and received by GRO, and another one in qdisc layer.
+ * We apply another 100% factor because @rate is doubled at this point.
+ * We cap the cushion to 1ms.
+ */
+static __always_inline __u32 hystart_ack_delay(struct sock *sk)
+{
+ unsigned long rate;
+
+ rate = sk->sk_pacing_rate;
+ if (!rate)
+ return 0;
+ return min((__u64)USEC_PER_MSEC,
+ div64_ul((__u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate));
+}
+
+static __always_inline void hystart_update(struct sock *sk, __u32 delay)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+ __u32 threshold;
+
+ if (hystart_detect & HYSTART_ACK_TRAIN) {
+ __u32 now = bictcp_clock_us(sk);
+
+ /* first detection parameter - ack-train detection */
+ if ((__s32)(now - ca->last_ack) <= hystart_ack_delta_us) {
+ ca->last_ack = now;
+
+ threshold = ca->delay_min + hystart_ack_delay(sk);
+
+ /* Hystart ack train triggers if we get ack past
+ * ca->delay_min/2.
+ * Pacing might have delayed packets up to RTT/2
+ * during slow start.
+ */
+ if (sk->sk_pacing_status == SK_PACING_NONE)
+ threshold >>= 1;
+
+ if ((__s32)(now - ca->round_start) > threshold) {
+ ca->found = 1;
+ tp->snd_ssthresh = tp->snd_cwnd;
+ }
+ }
+ }
+
+ if (hystart_detect & HYSTART_DELAY) {
+ /* obtain the minimum delay of more than sampling packets */
+ if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
+ if (ca->curr_rtt > delay)
+ ca->curr_rtt = delay;
+
+ ca->sample_cnt++;
+ } else {
+ if (ca->curr_rtt > ca->delay_min +
+ HYSTART_DELAY_THRESH(ca->delay_min >> 3)) {
+ ca->found = 1;
+ tp->snd_ssthresh = tp->snd_cwnd;
+ }
+ }
+ }
+}
+
+void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk,
+ const struct ack_sample *sample)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+ __u32 delay;
+
+ /* Some calls are for duplicates without timetamps */
+ if (sample->rtt_us < 0)
+ return;
+
+ /* Discard delay samples right after fast recovery */
+ if (ca->epoch_start && (__s32)(tcp_jiffies32 - ca->epoch_start) < HZ)
+ return;
+
+ delay = sample->rtt_us;
+ if (delay == 0)
+ delay = 1;
+
+ /* first time call or link delay decreases */
+ if (ca->delay_min == 0 || ca->delay_min > delay)
+ ca->delay_min = delay;
+
+ /* hystart triggers when cwnd is larger than some threshold */
+ if (!ca->found && tcp_in_slow_start(tp) && hystart &&
+ tp->snd_cwnd >= hystart_low_window)
+ hystart_update(sk, delay);
+}
+
+__u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+
+ return max(tp->snd_cwnd, tp->prior_cwnd);
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops cubic = {
+ .init = (void *)bictcp_init,
+ .ssthresh = (void *)bictcp_recalc_ssthresh,
+ .cong_avoid = (void *)bictcp_cong_avoid,
+ .set_state = (void *)bictcp_state,
+ .undo_cwnd = (void *)tcp_reno_undo_cwnd,
+ .cwnd_event = (void *)bictcp_cwnd_event,
+ .pkts_acked = (void *)bictcp_acked,
+ .name = "bpf_cubic",
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
new file mode 100644
index 0000000..b631fb5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+/* WARNING: This implemenation is not necessarily the same
+ * as the tcp_dctcp.c. The purpose is mainly for testing
+ * the kernel BPF logic.
+ */
+
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_trace_helpers.h"
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define DCTCP_MAX_ALPHA 1024U
+
+struct dctcp {
+ __u32 old_delivered;
+ __u32 old_delivered_ce;
+ __u32 prior_rcv_nxt;
+ __u32 dctcp_alpha;
+ __u32 next_seq;
+ __u32 ce_state;
+ __u32 loss_cwnd;
+};
+
+static unsigned int dctcp_shift_g = 4; /* g = 1/2^4 */
+static unsigned int dctcp_alpha_on_init = DCTCP_MAX_ALPHA;
+
+static __always_inline void dctcp_reset(const struct tcp_sock *tp,
+ struct dctcp *ca)
+{
+ ca->next_seq = tp->snd_nxt;
+
+ ca->old_delivered = tp->delivered;
+ ca->old_delivered_ce = tp->delivered_ce;
+}
+
+SEC("struct_ops/dctcp_init")
+void BPF_PROG(dctcp_init, struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ ca->prior_rcv_nxt = tp->rcv_nxt;
+ ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
+ ca->loss_cwnd = 0;
+ ca->ce_state = 0;
+
+ dctcp_reset(tp, ca);
+}
+
+SEC("struct_ops/dctcp_ssthresh")
+__u32 BPF_PROG(dctcp_ssthresh, struct sock *sk)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ ca->loss_cwnd = tp->snd_cwnd;
+ return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
+}
+
+SEC("struct_ops/dctcp_update_alpha")
+void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ /* Expired RTT */
+ if (!before(tp->snd_una, ca->next_seq)) {
+ __u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce;
+ __u32 alpha = ca->dctcp_alpha;
+
+ /* alpha = (1 - g) * alpha + g * F */
+
+ alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
+ if (delivered_ce) {
+ __u32 delivered = tp->delivered - ca->old_delivered;
+
+ /* If dctcp_shift_g == 1, a 32bit value would overflow
+ * after 8 M packets.
+ */
+ delivered_ce <<= (10 - dctcp_shift_g);
+ delivered_ce /= max(1U, delivered);
+
+ alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA);
+ }
+ ca->dctcp_alpha = alpha;
+ dctcp_reset(tp, ca);
+ }
+}
+
+static __always_inline void dctcp_react_to_loss(struct sock *sk)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ ca->loss_cwnd = tp->snd_cwnd;
+ tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+SEC("struct_ops/dctcp_state")
+void BPF_PROG(dctcp_state, struct sock *sk, __u8 new_state)
+{
+ if (new_state == TCP_CA_Recovery &&
+ new_state != BPF_CORE_READ_BITFIELD(inet_csk(sk), icsk_ca_state))
+ dctcp_react_to_loss(sk);
+ /* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+ * one loss-adjustment per RTT.
+ */
+}
+
+static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (ce_state == 1)
+ tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+ else
+ tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+/* Minimal DCTP CE state machine:
+ *
+ * S: 0 <- last pkt was non-CE
+ * 1 <- last pkt was CE
+ */
+static __always_inline
+void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
+ __u32 *prior_rcv_nxt, __u32 *ce_state)
+{
+ __u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0;
+
+ if (*ce_state != new_ce_state) {
+ /* CE state has changed, force an immediate ACK to
+ * reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
+ dctcp_ece_ack_cwr(sk, *ce_state);
+ bpf_tcp_send_ack(sk, *prior_rcv_nxt);
+ }
+ inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+ }
+ *prior_rcv_nxt = tcp_sk(sk)->rcv_nxt;
+ *ce_state = new_ce_state;
+ dctcp_ece_ack_cwr(sk, new_ce_state);
+}
+
+SEC("struct_ops/dctcp_cwnd_event")
+void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ switch (ev) {
+ case CA_EVENT_ECN_IS_CE:
+ case CA_EVENT_ECN_NO_CE:
+ dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
+ break;
+ case CA_EVENT_LOSS:
+ dctcp_react_to_loss(sk);
+ break;
+ default:
+ /* Don't care for the rest. */
+ break;
+ }
+}
+
+SEC("struct_ops/dctcp_cwnd_undo")
+__u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk)
+{
+ const struct dctcp *ca = inet_csk_ca(sk);
+
+ return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
+SEC("struct_ops/tcp_reno_cong_avoid")
+void BPF_PROG(tcp_reno_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (!tcp_is_cwnd_limited(sk))
+ return;
+
+ /* In "safe" area, increase. */
+ if (tcp_in_slow_start(tp)) {
+ acked = tcp_slow_start(tp, acked);
+ if (!acked)
+ return;
+ }
+ /* In dangerous area, increase slowly. */
+ tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops dctcp_nouse = {
+ .init = (void *)dctcp_init,
+ .set_state = (void *)dctcp_state,
+ .flags = TCP_CONG_NEEDS_ECN,
+ .name = "bpf_dctcp_nouse",
+};
+
+SEC(".struct_ops")
+struct tcp_congestion_ops dctcp = {
+ .init = (void *)dctcp_init,
+ .in_ack_event = (void *)dctcp_update_alpha,
+ .cwnd_event = (void *)dctcp_cwnd_event,
+ .ssthresh = (void *)dctcp_ssthresh,
+ .cong_avoid = (void *)tcp_reno_cong_avoid,
+ .undo_cwnd = (void *)dctcp_cwnd_undo,
+ .set_state = (void *)dctcp_state,
+ .flags = TCP_CONG_NEEDS_ECN,
+ .name = "bpf_dctcp",
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 040a442..9941f0b 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -16,8 +16,8 @@
#include <sys/socket.h>
#include <linux/if_tunnel.h>
#include <linux/mpls.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
#define PROG(F) SEC(#F) int bpf_func_##F
diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index 1fd244d..7508511 100644
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -9,8 +9,8 @@
#include <linux/in6.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define SRC_REWRITE_IP4 0x7f000004U
#define DST_REWRITE_IP4 0x7f000001U
diff --git a/tools/testing/selftests/bpf/progs/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c
index 26397ab..506d0f8 100644
--- a/tools/testing/selftests/bpf/progs/connect6_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect6_prog.c
@@ -9,8 +9,8 @@
#include <linux/in6.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define SRC_REWRITE_IP6_0 0
#define SRC_REWRITE_IP6_1 0
diff --git a/tools/testing/selftests/bpf/progs/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c
index ce41a34..8924e06 100644
--- a/tools/testing/selftests/bpf/progs/dev_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c
@@ -7,7 +7,7 @@
#include <linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("cgroup/dev")
int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx)
diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c
index 615f7c6..38d3a82 100644
--- a/tools/testing/selftests/bpf/progs/fentry_test.c
+++ b/tools/testing/selftests/bpf/progs/fentry_test.c
@@ -1,43 +1,46 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_trace_helpers.h"
char _license[] SEC("license") = "GPL";
__u64 test1_result = 0;
-BPF_TRACE_1("fentry/bpf_fentry_test1", test1, int, a)
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test1, int a)
{
test1_result = a == 1;
return 0;
}
__u64 test2_result = 0;
-BPF_TRACE_2("fentry/bpf_fentry_test2", test2, int, a, __u64, b)
+SEC("fentry/bpf_fentry_test2")
+int BPF_PROG(test2, int a, __u64 b)
{
test2_result = a == 2 && b == 3;
return 0;
}
__u64 test3_result = 0;
-BPF_TRACE_3("fentry/bpf_fentry_test3", test3, char, a, int, b, __u64, c)
+SEC("fentry/bpf_fentry_test3")
+int BPF_PROG(test3, char a, int b, __u64 c)
{
test3_result = a == 4 && b == 5 && c == 6;
return 0;
}
__u64 test4_result = 0;
-BPF_TRACE_4("fentry/bpf_fentry_test4", test4,
- void *, a, char, b, int, c, __u64, d)
+SEC("fentry/bpf_fentry_test4")
+int BPF_PROG(test4, void *a, char b, int c, __u64 d)
{
test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10;
return 0;
}
__u64 test5_result = 0;
-BPF_TRACE_5("fentry/bpf_fentry_test5", test5,
- __u64, a, void *, b, short, c, int, d, __u64, e)
+SEC("fentry/bpf_fentry_test5")
+int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e)
{
test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 &&
e == 15;
@@ -45,8 +48,8 @@ BPF_TRACE_5("fentry/bpf_fentry_test5", test5,
}
__u64 test6_result = 0;
-BPF_TRACE_6("fentry/bpf_fentry_test6", test6,
- __u64, a, void *, b, short, c, int, d, void *, e, __u64, f)
+SEC("fentry/bpf_fentry_test6")
+int BPF_PROG(test6, __u64 a, void *b, short c, int d, void * e, __u64 f)
{
test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
e == (void *)20 && f == 21;
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
index 2d211ee..c329fcc 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
@@ -1,7 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
+#include <linux/stddef.h>
+#include <linux/ipv6.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "bpf_trace_helpers.h"
struct sk_buff {
@@ -9,8 +12,8 @@ struct sk_buff {
};
__u64 test_result = 0;
-BPF_TRACE_2("fexit/test_pkt_access", test_main,
- struct sk_buff *, skb, int, ret)
+SEC("fexit/test_pkt_access")
+int BPF_PROG(test_main, struct sk_buff *skb, int ret)
{
int len;
@@ -24,8 +27,8 @@ BPF_TRACE_2("fexit/test_pkt_access", test_main,
}
__u64 test_result_subprog1 = 0;
-BPF_TRACE_2("fexit/test_pkt_access_subprog1", test_subprog1,
- struct sk_buff *, skb, int, ret)
+SEC("fexit/test_pkt_access_subprog1")
+int BPF_PROG(test_subprog1, struct sk_buff *skb, int ret)
{
int len;
@@ -79,4 +82,73 @@ int test_subprog2(struct args_subprog2 *ctx)
test_result_subprog2 = 1;
return 0;
}
+
+__u64 test_result_subprog3 = 0;
+SEC("fexit/test_pkt_access_subprog3")
+int BPF_PROG(test_subprog3, int val, struct sk_buff *skb, int ret)
+{
+ int len;
+
+ __builtin_preserve_access_index(({
+ len = skb->len;
+ }));
+ if (len != 74 || ret != 74 * val || val != 3)
+ return 0;
+ test_result_subprog3 = 1;
+ return 0;
+}
+
+__u64 test_get_skb_len = 0;
+SEC("freplace/get_skb_len")
+int new_get_skb_len(struct __sk_buff *skb)
+{
+ int len = skb->len;
+
+ if (len != 74)
+ return 0;
+ test_get_skb_len = 1;
+ return 74; /* original get_skb_len() returns skb->len */
+}
+
+__u64 test_get_skb_ifindex = 0;
+SEC("freplace/get_skb_ifindex")
+int new_get_skb_ifindex(int val, struct __sk_buff *skb, int var)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ void *data = (void *)(long)skb->data;
+ struct ipv6hdr ip6, *ip6p;
+ int ifindex = skb->ifindex;
+ __u32 eth_proto;
+ __u32 nh_off;
+
+ /* check that BPF extension can read packet via direct packet access */
+ if (data + 14 + sizeof(ip6) > data_end)
+ return 0;
+ ip6p = data + 14;
+
+ if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123))
+ return 0;
+
+ /* check that legacy packet access helper works too */
+ if (bpf_skb_load_bytes(skb, 14, &ip6, sizeof(ip6)) < 0)
+ return 0;
+ ip6p = &ip6;
+ if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123))
+ return 0;
+
+ if (ifindex != 1 || val != 3 || var != 1)
+ return 0;
+ test_get_skb_ifindex = 1;
+ return 3; /* original get_skb_ifindex() returns val * ifindex * var */
+}
+
+volatile __u64 test_get_constant = 0;
+SEC("freplace/get_constant")
+int new_get_constant(long val)
+{
+ if (val != 123)
+ return 0;
+ test_get_constant = 1;
+ return test_get_constant; /* original get_constant() returns val - 122 */
+}
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
index ebc0ab7..92f3fa4 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_trace_helpers.h"
struct sk_buff {
@@ -9,8 +9,9 @@ struct sk_buff {
};
__u64 test_result = 0;
-BPF_TRACE_2("fexit/test_pkt_md_access", test_main2,
- struct sk_buff *, skb, int, ret)
+
+SEC("fexit/test_pkt_md_access")
+int BPF_PROG(test_main2, struct sk_buff *skb, int ret)
{
int len;
diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c
index 86db0d6..348109b 100644
--- a/tools/testing/selftests/bpf/progs/fexit_test.c
+++ b/tools/testing/selftests/bpf/progs/fexit_test.c
@@ -1,45 +1,47 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_trace_helpers.h"
char _license[] SEC("license") = "GPL";
__u64 test1_result = 0;
-BPF_TRACE_2("fexit/bpf_fentry_test1", test1, int, a, int, ret)
+SEC("fexit/bpf_fentry_test1")
+int BPF_PROG(test1, int a, int ret)
{
test1_result = a == 1 && ret == 2;
return 0;
}
__u64 test2_result = 0;
-BPF_TRACE_3("fexit/bpf_fentry_test2", test2, int, a, __u64, b, int, ret)
+SEC("fexit/bpf_fentry_test2")
+int BPF_PROG(test2, int a, __u64 b, int ret)
{
test2_result = a == 2 && b == 3 && ret == 5;
return 0;
}
__u64 test3_result = 0;
-BPF_TRACE_4("fexit/bpf_fentry_test3", test3, char, a, int, b, __u64, c, int, ret)
+SEC("fexit/bpf_fentry_test3")
+int BPF_PROG(test3, char a, int b, __u64 c, int ret)
{
test3_result = a == 4 && b == 5 && c == 6 && ret == 15;
return 0;
}
__u64 test4_result = 0;
-BPF_TRACE_5("fexit/bpf_fentry_test4", test4,
- void *, a, char, b, int, c, __u64, d, int, ret)
+SEC("fexit/bpf_fentry_test4")
+int BPF_PROG(test4, void *a, char b, int c, __u64 d, int ret)
{
-
test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10 &&
ret == 34;
return 0;
}
__u64 test5_result = 0;
-BPF_TRACE_6("fexit/bpf_fentry_test5", test5,
- __u64, a, void *, b, short, c, int, d, __u64, e, int, ret)
+SEC("fexit/bpf_fentry_test5")
+int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e, int ret)
{
test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 &&
e == 15 && ret == 65;
@@ -47,9 +49,8 @@ BPF_TRACE_6("fexit/bpf_fentry_test5", test5,
}
__u64 test6_result = 0;
-BPF_TRACE_7("fexit/bpf_fentry_test6", test6,
- __u64, a, void *, b, short, c, int, d, void *, e, __u64, f,
- int, ret)
+SEC("fexit/bpf_fentry_test6")
+int BPF_PROG(test6, __u64 a, void *b, short c, int d, void *e, __u64 f, int ret)
{
test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
e == (void *)20 && f == 21 && ret == 111;
diff --git a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
index 16c54ad..6b42db2 100644
--- a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
@@ -2,7 +2,7 @@
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
index 974d6f3..8f48a90 100644
--- a/tools/testing/selftests/bpf/progs/kfree_skb.c
+++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
@@ -2,8 +2,8 @@
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
#include <stdbool.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "bpf_trace_helpers.h"
char _license[] SEC("license") = "GPL";
@@ -57,8 +57,8 @@ struct meta {
/* TRACE_EVENT(kfree_skb,
* TP_PROTO(struct sk_buff *skb, void *location),
*/
-BPF_TRACE_2("tp_btf/kfree_skb", trace_kfree_skb,
- struct sk_buff *, skb, void *, location)
+SEC("tp_btf/kfree_skb")
+int BPF_PROG(trace_kfree_skb, struct sk_buff *skb, void *location)
{
struct net_device *dev;
struct callback_head *ptr;
@@ -114,9 +114,9 @@ static volatile struct {
bool fexit_test_ok;
} result;
-BPF_TRACE_3("fentry/eth_type_trans", fentry_eth_type_trans,
- struct sk_buff *, skb, struct net_device *, dev,
- unsigned short, protocol)
+SEC("fentry/eth_type_trans")
+int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, struct net_device *dev,
+ unsigned short protocol)
{
int len, ifindex;
@@ -132,9 +132,9 @@ BPF_TRACE_3("fentry/eth_type_trans", fentry_eth_type_trans,
return 0;
}
-BPF_TRACE_3("fexit/eth_type_trans", fexit_eth_type_trans,
- struct sk_buff *, skb, struct net_device *, dev,
- unsigned short, protocol)
+SEC("fexit/eth_type_trans")
+int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb, struct net_device *dev,
+ unsigned short protocol)
{
int len, ifindex;
diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c
index 40ac722..50e6677 100644
--- a/tools/testing/selftests/bpf/progs/loop1.c
+++ b/tools/testing/selftests/bpf/progs/loop1.c
@@ -6,8 +6,8 @@
#include <stddef.h>
#include <stdbool.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c
index bb80f29..947bb7e 100644
--- a/tools/testing/selftests/bpf/progs/loop2.c
+++ b/tools/testing/selftests/bpf/progs/loop2.c
@@ -6,8 +6,8 @@
#include <stddef.h>
#include <stdbool.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c
index 2b9165a..76e93b3 100644
--- a/tools/testing/selftests/bpf/progs/loop3.c
+++ b/tools/testing/selftests/bpf/progs/loop3.c
@@ -6,8 +6,8 @@
#include <stddef.h>
#include <stdbool.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/loop4.c b/tools/testing/selftests/bpf/progs/loop4.c
index 6508590..b353379 100644
--- a/tools/testing/selftests/bpf/progs/loop4.c
+++ b/tools/testing/selftests/bpf/progs/loop4.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/loop5.c b/tools/testing/selftests/bpf/progs/loop5.c
index 28d1d66..9137919 100644
--- a/tools/testing/selftests/bpf/progs/loop5.c
+++ b/tools/testing/selftests/bpf/progs/loop5.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define barrier() __asm__ __volatile__("": : :"memory")
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c
index 38a9978..d071adf 100644
--- a/tools/testing/selftests/bpf/progs/netcnt_prog.c
+++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c
@@ -2,7 +2,7 @@
#include <linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "netcnt_common.h"
#define MAX_BPS (3 * 1024 * 1024)
diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h
index 71d383c..cc615b8 100644
--- a/tools/testing/selftests/bpf/progs/pyperf.h
+++ b/tools/testing/selftests/bpf/progs/pyperf.h
@@ -6,7 +6,7 @@
#include <stddef.h>
#include <stdbool.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define FUNCTION_NAME_LEN 64
#define FILE_NAME_LEN 128
@@ -154,7 +154,12 @@ struct {
__uint(value_size, sizeof(long long) * 127);
} stackmap SEC(".maps");
-static __always_inline int __on_event(struct pt_regs *ctx)
+#ifdef GLOBAL_FUNC
+__attribute__((noinline))
+#else
+static __always_inline
+#endif
+int __on_event(struct bpf_raw_tracepoint_args *ctx)
{
uint64_t pid_tgid = bpf_get_current_pid_tgid();
pid_t pid = (pid_t)(pid_tgid >> 32);
@@ -254,7 +259,7 @@ static __always_inline int __on_event(struct pt_regs *ctx)
}
SEC("raw_tracepoint/kfree_skb")
-int on_event(struct pt_regs* ctx)
+int on_event(struct bpf_raw_tracepoint_args* ctx)
{
int i, ret = 0;
ret |= __on_event(ctx);
diff --git a/tools/testing/selftests/bpf/progs/pyperf_global.c b/tools/testing/selftests/bpf/progs/pyperf_global.c
new file mode 100644
index 0000000..079e78a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pyperf_global.c
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define STACK_MAX_LEN 50
+#define GLOBAL_FUNC
+#include "pyperf.h"
diff --git a/tools/testing/selftests/bpf/progs/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c
index 0756303..1612a320 100644
--- a/tools/testing/selftests/bpf/progs/sample_map_ret0.c
+++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") htab = {
.type = BPF_MAP_TYPE_HASH,
diff --git a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
index a91536b..092d9da 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
@@ -5,8 +5,8 @@
#include <linux/bpf.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define SRC1_IP4 0xAC100001U /* 172.16.0.1 */
#define SRC2_IP4 0x00000000U
diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
index a680628..255a432b 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
@@ -5,8 +5,8 @@
#include <linux/bpf.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define SRC_REWRITE_IP6_0 0
#define SRC_REWRITE_IP6_1 0
diff --git a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
index e4440fd..0cb5656 100644
--- a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
+++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
@@ -4,8 +4,8 @@
#include <linux/bpf.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
struct socket_cookie {
__u64 cookie_key;
diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
index 9390e02..a5c6d59 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
@@ -1,6 +1,6 @@
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
index e80484d..fdb4bf4 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
@@ -1,7 +1,7 @@
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
index 433e239..4797dc9 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
@@ -1,6 +1,6 @@
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
index dede0fc..c6d428a 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c
index 4afd259..9d8c212 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <netinet/in.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c
index 1bafbb9..d5a5eeb 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c
@@ -3,7 +3,7 @@
#include <netinet/in.h>
#include <netinet/tcp.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 4bf16e0..ad61b722 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -8,7 +8,7 @@
#include <linux/ptrace.h>
#include <linux/sched.h>
#include <linux/types.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
typedef uint32_t pid_t;
struct task_struct {};
diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c
index 63531e1..1f407e6 100644
--- a/tools/testing/selftests/bpf/progs/tailcall1.c
+++ b/tools/testing/selftests/bpf/progs/tailcall1.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c
index 21c85c4..a093e73 100644
--- a/tools/testing/selftests/bpf/progs/tailcall2.c
+++ b/tools/testing/selftests/bpf/progs/tailcall2.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c
index 1ecae19..cabda87 100644
--- a/tools/testing/selftests/bpf/progs/tailcall3.c
+++ b/tools/testing/selftests/bpf/progs/tailcall3.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c
index 4993887..f82075b 100644
--- a/tools/testing/selftests/bpf/progs/tailcall4.c
+++ b/tools/testing/selftests/bpf/progs/tailcall4.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c
index 49c64eb..ce54507 100644
--- a/tools/testing/selftests/bpf/progs/tailcall5.c
+++ b/tools/testing/selftests/bpf/progs/tailcall5.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c
index 2cf813a..0cb3204 100644
--- a/tools/testing/selftests/bpf/progs/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_adjust_tail.c b/tools/testing/selftests/bpf/progs/test_adjust_tail.c
index 4cd5e86..b7fc857 100644
--- a/tools/testing/selftests/bpf/progs/test_adjust_tail.c
+++ b/tools/testing/selftests/bpf/progs/test_adjust_tail.c
@@ -7,7 +7,7 @@
*/
#include <linux/bpf.h>
#include <linux/if_ether.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
index 221b697..dd8fae6 100644
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -3,7 +3,7 @@
#include <linux/ptrace.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int kprobe_res = 0;
int kretprobe_res = 0;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
index 62ad7e2..88b0566 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
index fb8d91a..a924e53 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
index 3f44220..983aedd 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_core_extern.c b/tools/testing/selftests/bpf/progs/test_core_extern.c
index 9bfc91d..3ac3603 100644
--- a/tools/testing/selftests/bpf/progs/test_core_extern.c
+++ b/tools/testing/selftests/bpf/progs/test_core_extern.c
@@ -5,7 +5,7 @@
#include <stdbool.h>
#include <linux/ptrace.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* non-existing BPF helper, to test dead code elimination */
static int (*bpf_missing_helper)(const void *arg1, int arg2) = (void *) 999;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
index 053b86f..51b3f79 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c
index edc0f7c..56aec20 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
index 6c20e43..ab1e647 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c b/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c
index 1b7f0ae..7e45e2b 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c
index b5dbeef..525acc2 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c
index c78ab6d..6b52907 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
index 270de44..aba928f 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c
index 292a5c4e..d5756db 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
index 0b28bfa..8b533db 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c
index 39279bf..2b4b6d49 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c
index ea57973..2a897567 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c
index d1eb59d..ca61a51 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
index 9e09112..d7fb6cf 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
@@ -3,8 +3,8 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
index 6a4a8f5..29817a7 100644
--- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* Permit pretty deep stack traces */
#define MAX_STACK_RAWTP 100
diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c
index 32a6073..dd7a4d3 100644
--- a/tools/testing/selftests/bpf/progs/test_global_data.c
+++ b/tools/testing/selftests/bpf/progs/test_global_data.c
@@ -5,7 +5,7 @@
#include <linux/pkt_cls.h>
#include <string.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c
new file mode 100644
index 0000000..880260f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func1.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#ifndef MAX_STACK
+#define MAX_STACK (512 - 3 * 32 + 8)
+#endif
+
+static __attribute__ ((noinline))
+int f0(int var, struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+ volatile char buf[MAX_STACK] = {};
+
+ return f0(0, skb) + skb->len;
+}
+
+int f3(int, struct __sk_buff *skb, int);
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+ return f1(skb) + f3(val, skb, 1);
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb, int var)
+{
+ volatile char buf[MAX_STACK] = {};
+
+ return skb->ifindex * val * var;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+ return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func2.c b/tools/testing/selftests/bpf/progs/test_global_func2.c
new file mode 100644
index 0000000..2c18d82
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func2.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#define MAX_STACK (512 - 3 * 32)
+#include "test_global_func1.c"
diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c
new file mode 100644
index 0000000..86f0ecb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func3.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+ return f1(skb) + val;
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb, int var)
+{
+ return f2(var, skb) + val;
+}
+
+__attribute__ ((noinline))
+int f4(struct __sk_buff *skb)
+{
+ return f3(1, skb, 2);
+}
+
+__attribute__ ((noinline))
+int f5(struct __sk_buff *skb)
+{
+ return f4(skb);
+}
+
+__attribute__ ((noinline))
+int f6(struct __sk_buff *skb)
+{
+ return f5(skb);
+}
+
+__attribute__ ((noinline))
+int f7(struct __sk_buff *skb)
+{
+ return f6(skb);
+}
+
+#ifndef NO_FN8
+__attribute__ ((noinline))
+int f8(struct __sk_buff *skb)
+{
+ return f7(skb);
+}
+#endif
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+#ifndef NO_FN8
+ return f8(skb);
+#else
+ return f7(skb);
+#endif
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func4.c b/tools/testing/selftests/bpf/progs/test_global_func4.c
new file mode 100644
index 0000000..610f75ed
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func4.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#define NO_FN8
+#include "test_global_func3.c"
diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c
new file mode 100644
index 0000000..260c25b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func5.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+int f3(int, struct __sk_buff *skb);
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+ return f1(skb) + f3(val, (void *)&val); /* type mismatch */
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb)
+{
+ return skb->ifindex * val;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+ return f1(skb) + f2(2, skb) + f3(3, skb);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c
new file mode 100644
index 0000000..69e19c6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func6.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+int f3(int, struct __sk_buff *skb);
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+ return f1(skb) + f3(val, skb + 1); /* type mismatch */
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb)
+{
+ return skb->ifindex * val;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+ return f1(skb) + f2(2, skb) + f3(3, skb);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c
new file mode 100644
index 0000000..309b3f6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func7.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+void foo(struct __sk_buff *skb)
+{
+ skb->tc_index = 0;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+ foo(skb);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c
index 1d652ee..3349391 100644
--- a/tools/testing/selftests/bpf/progs/test_l4lb.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb.c
@@ -17,9 +17,9 @@
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "test_iptunnel_common.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
index 2e4efe7..2835193 100644
--- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
@@ -13,9 +13,9 @@
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "test_iptunnel_common.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
index 4147130..7a66206 100644
--- a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
@@ -5,7 +5,7 @@
#include <linux/bpf.h>
#include <linux/lirc.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("lirc_mode2")
int bpf_decoder(unsigned int *sample)
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
index c957d6d..d6cb986 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
@@ -4,8 +4,8 @@
#include <linux/bpf.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
struct grehdr {
__be16 flags;
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
index 41a3ebc..48ff2b2 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
@@ -3,8 +3,8 @@
#include <errno.h>
#include <linux/seg6_local.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
/* Packet parsing state machine helpers. */
#define cursor_advance(_cursor, _len) \
diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c
index 1132261..1cfeb94 100644
--- a/tools/testing/selftests/bpf/progs/test_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c
@@ -3,7 +3,7 @@
#include <stddef.h>
#include <linux/bpf.h>
#include <linux/types.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c
index bb7ce35..b5c07ae 100644
--- a/tools/testing/selftests/bpf/progs/test_map_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_map_lock.c
@@ -2,7 +2,7 @@
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define VAR_NUM 16
diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c
index e808791..6239596 100644
--- a/tools/testing/selftests/bpf/progs/test_mmap.c
+++ b/tools/testing/selftests/bpf/progs/test_mmap.c
@@ -3,7 +3,7 @@
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c
index 3d30c02..98b9de2f 100644
--- a/tools/testing/selftests/bpf/progs/test_obj_id.c
+++ b/tools/testing/selftests/bpf/progs/test_obj_id.c
@@ -4,7 +4,7 @@
#include <stddef.h>
#include <linux/bpf.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* It is a dumb bpf program such that it must have no
* issue to be loaded since testing the verifier is
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index 96c0124..bfe9fbc 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -1,39 +1,45 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
+#include <stdbool.h>
+#include <stddef.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <linux/ptrace.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
#include "bpf_trace_helpers.h"
+struct task_struct;
+
SEC("kprobe/__set_task_comm")
-int prog1(struct pt_regs *ctx)
+int BPF_KPROBE(prog1, struct task_struct *tsk, const char *buf, bool exec)
{
- return 0;
+ return !tsk;
}
SEC("kretprobe/__set_task_comm")
-int prog2(struct pt_regs *ctx)
+int BPF_KRETPROBE(prog2,
+ struct task_struct *tsk, const char *buf, bool exec,
+ int ret)
{
- return 0;
+ return !PT_REGS_PARM1(ctx) && ret;
}
SEC("raw_tp/task_rename")
int prog3(struct bpf_raw_tracepoint_args *ctx)
{
- return 0;
+ return !ctx->args[0];
}
-struct task_struct;
-BPF_TRACE_3("fentry/__set_task_comm", prog4,
- struct task_struct *, tsk, const char *, buf, __u8, exec)
+SEC("fentry/__set_task_comm")
+int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec)
{
- return 0;
+ return !tsk;
}
-BPF_TRACE_3("fexit/__set_task_comm", prog5,
- struct task_struct *, tsk, const char *, buf, __u8, exec)
+SEC("fexit/__set_task_comm")
+int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec)
{
- return 0;
+ return !tsk;
}
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
index 07c09ca..ebfcc9f 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -3,7 +3,8 @@
#include <linux/ptrace.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_trace_helpers.h"
struct {
__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
@@ -12,7 +13,7 @@ struct {
} perf_buf_map SEC(".maps");
SEC("kprobe/sys_nanosleep")
-int handle_sys_nanosleep_entry(struct pt_regs *ctx)
+int BPF_KPROBE(handle_sys_nanosleep_entry)
{
int cpu = bpf_get_smp_processor_id();
diff --git a/tools/testing/selftests/bpf/progs/test_pinning.c b/tools/testing/selftests/bpf/progs/test_pinning.c
index f20e7e0..4ef2630 100644
--- a/tools/testing/selftests/bpf/progs/test_pinning.c
+++ b/tools/testing/selftests/bpf/progs/test_pinning.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
index 51b38abe..5412e0c 100644
--- a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
+++ b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c
index 3a7b4b6..e72eba4 100644
--- a/tools/testing/selftests/bpf/progs/test_pkt_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c
@@ -11,8 +11,8 @@
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define barrier() __asm__ __volatile__("": : :"memory")
int _version SEC("version") = 1;
@@ -47,6 +47,38 @@ int test_pkt_access_subprog2(int val, volatile struct __sk_buff *skb)
return skb->len * val;
}
+#define MAX_STACK (512 - 2 * 32)
+
+__attribute__ ((noinline))
+int get_skb_len(struct __sk_buff *skb)
+{
+ volatile char buf[MAX_STACK] = {};
+
+ return skb->len;
+}
+
+__attribute__ ((noinline))
+int get_constant(long val)
+{
+ return val - 122;
+}
+
+int get_skb_ifindex(int, struct __sk_buff *skb, int);
+
+__attribute__ ((noinline))
+int test_pkt_access_subprog3(int val, struct __sk_buff *skb)
+{
+ return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123));
+}
+
+__attribute__ ((noinline))
+int get_skb_ifindex(int val, struct __sk_buff *skb, int var)
+{
+ volatile char buf[MAX_STACK] = {};
+
+ return skb->ifindex * val * var;
+}
+
SEC("classifier/test_pkt_access")
int test_pkt_access(struct __sk_buff *skb)
{
@@ -82,6 +114,8 @@ int test_pkt_access(struct __sk_buff *skb)
return TC_ACT_SHOT;
if (test_pkt_access_subprog2(2, skb) != skb->len * 2)
return TC_ACT_SHOT;
+ if (test_pkt_access_subprog3(3, skb) != skb->len * 3 * skb->ifindex)
+ return TC_ACT_SHOT;
if (tcp) {
if (((void *)(tcp) + 20) > data_end || proto != 6)
return TC_ACT_SHOT;
diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
index 1db2623..610c74e 100644
--- a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
@@ -5,7 +5,7 @@
#include <string.h>
#include <linux/bpf.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c
index 1871e2e..d556b15 100644
--- a/tools/testing/selftests/bpf/progs/test_probe_user.c
+++ b/tools/testing/selftests/bpf/progs/test_probe_user.c
@@ -5,13 +5,14 @@
#include <netinet/in.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_trace_helpers.h"
static struct sockaddr_in old;
SEC("kprobe/__sys_connect")
-int handle_sys_connect(struct pt_regs *ctx)
+int BPF_KPROBE(handle_sys_connect)
{
void *ptr = (void *)PT_REGS_PARM2(ctx);
struct sockaddr_in new;
diff --git a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h
index 0e014d3..4dd9806 100644
--- a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h
+++ b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h
@@ -6,7 +6,7 @@
#include <linux/if_ether.h>
#include <linux/ip.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
index 52d94e8b..ecbeea2 100644
--- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
+++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
@@ -3,7 +3,7 @@
#include <linux/ptrace.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
static volatile const struct {
unsigned a[4];
diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c
index 69880c1..a7278f06 100644
--- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c
@@ -3,8 +3,8 @@
#include <errno.h>
#include <linux/seg6_local.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
/* Packet parsing state machine helpers. */
#define cursor_advance(_cursor, _len) \
diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
index b1f09f5..d69a1f2 100644
--- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
@@ -11,8 +11,8 @@
#include <linux/types.h>
#include <linux/if_ether.h>
-#include "bpf_endian.h"
-#include "bpf_helpers.h"
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
#include "test_select_reuseport_common.h"
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
index 0e6be01..1acc91e 100644
--- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
@@ -2,46 +2,39 @@
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
-struct {
- __uint(type, BPF_MAP_TYPE_ARRAY);
- __uint(max_entries, 1);
- __type(key, __u32);
- __type(value, __u64);
-} info_map SEC(".maps");
+__u32 sig = 0, pid = 0, status = 0, signal_thread = 0;
-struct {
- __uint(type, BPF_MAP_TYPE_ARRAY);
- __uint(max_entries, 1);
- __type(key, __u32);
- __type(value, __u64);
-} status_map SEC(".maps");
-
-SEC("send_signal_demo")
-int bpf_send_signal_test(void *ctx)
+static __always_inline int bpf_send_signal_test(void *ctx)
{
- __u64 *info_val, *status_val;
- __u32 key = 0, pid, sig;
int ret;
- status_val = bpf_map_lookup_elem(&status_map, &key);
- if (!status_val || *status_val != 0)
+ if (status != 0 || sig == 0 || pid == 0)
return 0;
- info_val = bpf_map_lookup_elem(&info_map, &key);
- if (!info_val || *info_val == 0)
- return 0;
-
- sig = *info_val >> 32;
- pid = *info_val & 0xffffFFFF;
-
if ((bpf_get_current_pid_tgid() >> 32) == pid) {
- ret = bpf_send_signal(sig);
+ if (signal_thread)
+ ret = bpf_send_signal_thread(sig);
+ else
+ ret = bpf_send_signal(sig);
if (ret == 0)
- *status_val = 1;
+ status = 1;
}
return 0;
}
+
+SEC("tracepoint/syscalls/sys_enter_nanosleep")
+int send_signal_tp(void *ctx)
+{
+ return bpf_send_signal_test(ctx);
+}
+
+SEC("perf_event")
+int send_signal_perf(void *ctx)
+{
+ return bpf_send_signal_test(ctx);
+}
+
char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
index cb49ccb..d2b38fa 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
@@ -12,8 +12,8 @@
#include <linux/pkt_cls.h>
#include <linux/tcp.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
index 68cf982..552f209 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
@@ -6,7 +6,7 @@
#include <string.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define NUM_CGROUP_LEVELS 4
diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
index e18da87..202de39 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c
index 4f69aac..de03a90 100644
--- a/tools/testing/selftests/bpf/progs/test_skeleton.c
+++ b/tools/testing/selftests/bpf/progs/test_skeleton.c
@@ -3,7 +3,7 @@
#include <stdbool.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct s {
int a;
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
index a47b003..9bcaa37 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
@@ -5,8 +5,8 @@
#include <netinet/in.h>
#include <stdbool.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
enum bpf_addr_array_idx {
ADDR_SRV_IDX,
diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c
index a43b999c..0d31a3b 100644
--- a/tools/testing/selftests/bpf/progs/test_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c
@@ -2,7 +2,7 @@
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct hmap_elem {
volatile int cnt;
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
index f5638e2..0cf0134 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
@@ -2,7 +2,7 @@
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#ifndef PERF_MAX_STACK_DEPTH
#define PERF_MAX_STACK_DEPTH 127
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index 3b7e1dc..00ed486 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -2,7 +2,7 @@
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#ifndef PERF_MAX_STACK_DEPTH
#define PERF_MAX_STACK_DEPTH 127
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
index d22e438..458b0d69 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
@@ -7,7 +7,7 @@
#include <linux/stddef.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#ifndef ARRAY_SIZE
#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
index cb201cb..b2e6f9b 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
@@ -7,7 +7,7 @@
#include <linux/stddef.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#ifndef ARRAY_SIZE
#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
index 5cbbff4..2d0b0b8 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
@@ -7,7 +7,7 @@
#include <linux/stddef.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */
#define MAX_ULONG_STR_LEN 0xF
diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c
index 0961415..bf28814 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_edt.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c
@@ -7,8 +7,8 @@
#include <linux/ip.h>
#include <linux/pkt_cls.h>
#include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
/* the maximum delay we are willing to add (drop packets beyond that) */
#define TIME_HORIZON_NS (2000 * 1000 * 1000)
diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index 74370e7..37bce7a 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -17,8 +17,8 @@
#include <linux/pkt_cls.h>
#include <linux/types.h>
-#include "bpf_endian.h"
-#include "bpf_helpers.h"
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
static const int cfg_port = 8000;
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
index d8803df..47cbe2e 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
@@ -13,8 +13,8 @@
#include <sys/socket.h>
#include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
struct bpf_map_def SEC("maps") results = {
.type = BPF_MAP_TYPE_ARRAY,
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
index 87b7d93..adc83a5 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
@@ -36,7 +36,7 @@
#include <linux/ipv6.h>
#include <linux/version.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define _(P) ({typeof(P) val = 0; bpf_probe_read_kernel(&val, sizeof(val), &P); val;})
#define TCP_ESTATS_MAGIC 0xBAADBEEF
diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index 7fa4595..1f1966e 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@@ -10,8 +10,8 @@
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "test_tcpbpf.h"
struct {
diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
index 08346e7..ac63410 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
@@ -10,8 +10,8 @@
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "test_tcpnotify.h"
struct {
diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c
index 04bf084..4b825ee 100644
--- a/tools/testing/selftests/bpf/progs/test_tracepoint.c
+++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c
@@ -2,7 +2,7 @@
// Copyright (c) 2017 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 504df69..f48dbfe 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -19,8 +19,8 @@
#include <linux/socket.h>
#include <linux/pkt_cls.h>
#include <linux/erspan.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define ERROR(ret) do {\
char fmt[] = "ERROR line:%d ret:%d\n";\
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale1.c b/tools/testing/selftests/bpf/progs/test_verif_scale1.c
index f3236ce3..d38153d 100644
--- a/tools/testing/selftests/bpf/progs/test_verif_scale1.c
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale1.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define ATTR __attribute__((noinline))
#include "test_jhash.h"
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
index 9897150..f024154 100644
--- a/tools/testing/selftests/bpf/progs/test_verif_scale2.c
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define ATTR __always_inline
#include "test_jhash.h"
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale3.c b/tools/testing/selftests/bpf/progs/test_verif_scale3.c
index 1848da0..9beb5bf 100644
--- a/tools/testing/selftests/bpf/progs/test_verif_scale3.c
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale3.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define ATTR __attribute__((noinline))
#include "test_jhash.h"
diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c
index 0941c65..31f9bce 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp.c
@@ -16,8 +16,8 @@
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "test_iptunnel_common.h"
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
new file mode 100644
index 0000000..cb8a04a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_trace_helpers.h"
+
+struct net_device {
+ /* Structure does not need to contain all entries,
+ * as "preserve_access_index" will use BTF to fix this...
+ */
+ int ifindex;
+} __attribute__((preserve_access_index));
+
+struct xdp_rxq_info {
+ /* Structure does not need to contain all entries,
+ * as "preserve_access_index" will use BTF to fix this...
+ */
+ struct net_device *dev;
+ __u32 queue_index;
+} __attribute__((preserve_access_index));
+
+struct xdp_buff {
+ void *data;
+ void *data_end;
+ void *data_meta;
+ void *data_hard_start;
+ unsigned long handle;
+ struct xdp_rxq_info *rxq;
+} __attribute__((preserve_access_index));
+
+__u64 test_result_fentry = 0;
+SEC("fentry/_xdp_tx_iptunnel")
+int BPF_PROG(trace_on_entry, struct xdp_buff *xdp)
+{
+ test_result_fentry = xdp->rxq->dev->ifindex;
+ return 0;
+}
+
+__u64 test_result_fexit = 0;
+SEC("fexit/_xdp_tx_iptunnel")
+int BPF_PROG(trace_on_exit, struct xdp_buff *xdp, int ret)
+{
+ test_result_fexit = ret;
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
index 97175f7..fcabcda3 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
@@ -12,8 +12,8 @@
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "test_iptunnel_common.h"
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
index 8d01826..a7c4a7d 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
@@ -2,7 +2,7 @@
#include <linux/if_ether.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define __round_mask(x, y) ((__typeof__(x))((y) - 1))
#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index e88d7b9..8beecec 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -13,8 +13,8 @@
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
static __u32 rol32(__u32 word, unsigned int shift)
{
@@ -86,7 +86,7 @@ u32 jhash(const void *key, u32 length, u32 initval)
return c;
}
-static __attribute__ ((noinline))
+__attribute__ ((noinline))
u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
{
a += initval;
@@ -96,7 +96,7 @@ u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
return c;
}
-static __attribute__ ((noinline))
+__attribute__ ((noinline))
u32 jhash_2words(u32 a, u32 b, u32 initval)
{
return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
index ef9e704..a5337cd 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
@@ -10,7 +10,7 @@
* General Public License for more details.
*/
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
index 365a7d2..134768f 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
@@ -22,8 +22,8 @@
#include <linux/in.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
/* linux/if_vlan.h have not exposed this as UAPI, thus mirror some here
*
diff --git a/tools/testing/selftests/bpf/progs/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c
index 43b0ef1..ea25e88 100644
--- a/tools/testing/selftests/bpf/progs/xdp_dummy.c
+++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c
@@ -2,7 +2,7 @@
#define KBUILD_MODNAME "xdp_dummy"
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("xdp_dummy")
int xdp_dummy_prog(struct xdp_md *ctx)
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
index 1c5f298..d037262 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_DEVMAP);
diff --git a/tools/testing/selftests/bpf/progs/xdp_tx.c b/tools/testing/selftests/bpf/progs/xdp_tx.c
index 57912e7..94e6c2b 100644
--- a/tools/testing/selftests/bpf/progs/xdp_tx.c
+++ b/tools/testing/selftests/bpf/progs/xdp_tx.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("tx")
int xdp_tx(struct xdp_md *xdp)
diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c
index 112a285..6b9ca40 100644
--- a/tools/testing/selftests/bpf/progs/xdping_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdping_kern.c
@@ -12,8 +12,8 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "xdping.h"
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 3d617e80..93040ca 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -4148,10 +4148,6 @@ static int do_test_file(unsigned int test_num)
if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj)))
return PTR_ERR(obj);
- err = bpf_object__btf_fd(obj);
- if (CHECK(err == -1, "bpf_object__btf_fd: -1"))
- goto done;
-
prog = bpf_program__next(NULL, obj);
if (CHECK(!prog, "Cannot find bpf_prog")) {
err = -1;
diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp
index 6fe23a1..a8d2e9a 100644
--- a/tools/testing/selftests/bpf/test_cpp.cpp
+++ b/tools/testing/selftests/bpf/test_cpp.cpp
@@ -1,8 +1,8 @@
/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
#include <iostream>
-#include "libbpf.h"
-#include "bpf.h"
-#include "btf.h"
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
#include "test_core_extern.skel.h"
/* do nothing, just make sure we can link successfully */
diff --git a/tools/testing/selftests/bpf/test_hashmap.c b/tools/testing/selftests/bpf/test_hashmap.c
index b64094c..c490e01 100644
--- a/tools/testing/selftests/bpf/test_hashmap.c
+++ b/tools/testing/selftests/bpf/test_hashmap.c
@@ -8,7 +8,7 @@
#include <stdio.h>
#include <errno.h>
#include <linux/err.h>
-#include "hashmap.h"
+#include "bpf/hashmap.h"
#define CHECK(condition, format...) ({ \
int __ret = !!(condition); \
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 7fa7d08..bab1e6f 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -8,7 +8,7 @@
#include <string.h>
/* defined in test_progs.h */
-struct test_env env;
+struct test_env env = {};
struct prog_test_def {
const char *test_name;
@@ -29,10 +29,19 @@ struct prog_test_def {
static bool should_run(struct test_selector *sel, int num, const char *name)
{
- if (sel->name && sel->name[0] && !strstr(name, sel->name))
- return false;
+ int i;
- if (!sel->num_set)
+ for (i = 0; i < sel->blacklist.cnt; i++) {
+ if (strstr(name, sel->blacklist.strs[i]))
+ return false;
+ }
+
+ for (i = 0; i < sel->whitelist.cnt; i++) {
+ if (strstr(name, sel->whitelist.strs[i]))
+ return true;
+ }
+
+ if (!sel->whitelist.cnt && !sel->num_set)
return true;
return num < sel->num_set_len && sel->num_set[num];
@@ -334,6 +343,7 @@ const char argp_program_doc[] = "BPF selftests test runner";
enum ARG_KEYS {
ARG_TEST_NUM = 'n',
ARG_TEST_NAME = 't',
+ ARG_TEST_NAME_BLACKLIST = 'b',
ARG_VERIFIER_STATS = 's',
ARG_VERBOSE = 'v',
};
@@ -341,8 +351,10 @@ enum ARG_KEYS {
static const struct argp_option opts[] = {
{ "num", ARG_TEST_NUM, "NUM", 0,
"Run test number NUM only " },
- { "name", ARG_TEST_NAME, "NAME", 0,
- "Run tests with names containing NAME" },
+ { "name", ARG_TEST_NAME, "NAMES", 0,
+ "Run tests with names containing any string from NAMES list" },
+ { "name-blacklist", ARG_TEST_NAME_BLACKLIST, "NAMES", 0,
+ "Don't run tests with names containing any string from NAMES list" },
{ "verifier-stats", ARG_VERIFIER_STATS, NULL, 0,
"Output verifier statistics", },
{ "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL,
@@ -359,6 +371,41 @@ static int libbpf_print_fn(enum libbpf_print_level level,
return 0;
}
+static int parse_str_list(const char *s, struct str_set *set)
+{
+ char *input, *state = NULL, *next, **tmp, **strs = NULL;
+ int cnt = 0;
+
+ input = strdup(s);
+ if (!input)
+ return -ENOMEM;
+
+ set->cnt = 0;
+ set->strs = NULL;
+
+ while ((next = strtok_r(state ? NULL : input, ",", &state))) {
+ tmp = realloc(strs, sizeof(*strs) * (cnt + 1));
+ if (!tmp)
+ goto err;
+ strs = tmp;
+
+ strs[cnt] = strdup(next);
+ if (!strs[cnt])
+ goto err;
+
+ cnt++;
+ }
+
+ set->cnt = cnt;
+ set->strs = (const char **)strs;
+ free(input);
+ return 0;
+err:
+ free(strs);
+ free(input);
+ return -ENOMEM;
+}
+
int parse_num_list(const char *s, struct test_selector *sel)
{
int i, set_len = 0, num, start = 0, end = -1;
@@ -449,12 +496,24 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
if (subtest_str) {
*subtest_str = '\0';
- env->subtest_selector.name = strdup(subtest_str + 1);
- if (!env->subtest_selector.name)
+ if (parse_str_list(subtest_str + 1,
+ &env->subtest_selector.whitelist))
return -ENOMEM;
}
- env->test_selector.name = strdup(arg);
- if (!env->test_selector.name)
+ if (parse_str_list(arg, &env->test_selector.whitelist))
+ return -ENOMEM;
+ break;
+ }
+ case ARG_TEST_NAME_BLACKLIST: {
+ char *subtest_str = strchr(arg, '/');
+
+ if (subtest_str) {
+ *subtest_str = '\0';
+ if (parse_str_list(subtest_str + 1,
+ &env->subtest_selector.blacklist))
+ return -ENOMEM;
+ }
+ if (parse_str_list(arg, &env->test_selector.blacklist))
return -ENOMEM;
break;
}
@@ -617,7 +676,11 @@ int main(int argc, char **argv)
printf("Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
+ free(env.test_selector.blacklist.strs);
+ free(env.test_selector.whitelist.strs);
free(env.test_selector.num_set);
+ free(env.subtest_selector.blacklist.strs);
+ free(env.subtest_selector.whitelist.strs);
free(env.subtest_selector.num_set);
return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index de1fdaa..bcfa9ef 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -35,7 +35,7 @@ typedef __u16 __sum16;
#include "test_iptunnel_common.h"
#include "bpf_util.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
#include "trace_helpers.h"
#include "flow_dissector_load.h"
@@ -46,8 +46,14 @@ enum verbosity {
VERBOSE_SUPER,
};
+struct str_set {
+ const char **strs;
+ int cnt;
+};
+
struct test_selector {
- const char *name;
+ struct str_set whitelist;
+ struct str_set blacklist;
bool *num_set;
int num_set_len;
};
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
index 0e66527..52bf149 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -13,7 +13,7 @@
#include <bpf/bpf.h>
#include "cgroup_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
#include "bpf_rlimit.h"
#include "bpf_util.h"
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h
index d008b41..9b4d3a6 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/test_sockmap_kern.h
@@ -12,8 +12,8 @@
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
/* Sockmap sample program connects a client and a backend together
* using cgroups.
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c
index 40bd93a..d196e2a 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/test_sysctl.c
@@ -13,7 +13,7 @@
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
#include "bpf_rlimit.h"
#include "bpf_util.h"
#include "cgroup_helpers.h"
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index aa4dcfe..0383c9b 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -2,7 +2,7 @@
#ifndef __TRACE_HELPER_H
#define __TRACE_HELPER_H
-#include <libbpf.h>
+#include <bpf/libbpf.h>
struct ksym {
long addr;
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
index b4efb02..d88d8e4 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
@@ -50,6 +50,8 @@
ipv6_mc_dip_reserved_scope_test
ipv6_mc_dip_interface_local_scope_test
blackhole_route_test
+ irif_disabled_test
+ erif_disabled_test
"
NUM_NETIFS=4
@@ -553,6 +555,116 @@
__blackhole_route_test "6" "2001:db8:2::/120" "ipv6" $h2_ipv6 "icmpv6"
}
+irif_disabled_test()
+{
+ local trap_name="irif_disabled"
+ local group_name="l3_drops"
+ local t0_packets t0_bytes
+ local t1_packets t1_bytes
+ local mz_pid
+
+ RET=0
+
+ ping_check $trap_name
+
+ devlink_trap_action_set $trap_name "trap"
+
+ # When RIF of a physical port ("Sub-port RIF") is destroyed, we first
+ # block the STP of the {Port, VLAN} so packets cannot get into the RIF.
+ # Using bridge enables us to see this trap because when bridge is
+ # destroyed, there is a small time window that packets can go into the
+ # RIF, while it is disabled.
+ ip link add dev br0 type bridge
+ ip link set dev $rp1 master br0
+ ip address flush dev $rp1
+ __addr_add_del br0 add 192.0.2.2/24
+ ip li set dev br0 up
+
+ t0_packets=$(devlink_trap_rx_packets_get $trap_name)
+ t0_bytes=$(devlink_trap_rx_bytes_get $trap_name)
+
+ # Generate packets to h2 through br0 RIF that will be removed later
+ $MZ $h1 -t udp "sp=54321,dp=12345" -c 0 -p 100 -a own -b $rp1mac \
+ -B $h2_ipv4 -q &
+ mz_pid=$!
+
+ # Wait before removing br0 RIF to allow packets to go into the bridge.
+ sleep 1
+
+ # Flushing address will dismantle the RIF
+ ip address flush dev br0
+
+ t1_packets=$(devlink_trap_rx_packets_get $trap_name)
+ t1_bytes=$(devlink_trap_rx_bytes_get $trap_name)
+
+ if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then
+ check_err 1 "Trap stats idle when packets should be trapped"
+ fi
+
+ log_test "Ingress RIF disabled"
+
+ kill $mz_pid && wait $mz_pid &> /dev/null
+ ip link set dev $rp1 nomaster
+ __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64
+ ip link del dev br0 type bridge
+ devlink_trap_action_set $trap_name "drop"
+}
+
+erif_disabled_test()
+{
+ local trap_name="erif_disabled"
+ local group_name="l3_drops"
+ local t0_packets t0_bytes
+ local t1_packets t1_bytes
+ local mz_pid
+
+ RET=0
+
+ ping_check $trap_name
+
+ devlink_trap_action_set $trap_name "trap"
+ ip link add dev br0 type bridge
+ ip add flush dev $rp1
+ ip link set dev $rp1 master br0
+ __addr_add_del br0 add 192.0.2.2/24
+ ip link set dev br0 up
+
+ t0_packets=$(devlink_trap_rx_packets_get $trap_name)
+ t0_bytes=$(devlink_trap_rx_bytes_get $trap_name)
+
+ rp2mac=$(mac_get $rp2)
+
+ # Generate packets that should go out through br0 RIF that will be
+ # removed later
+ $MZ $h2 -t udp "sp=54321,dp=12345" -c 0 -p 100 -a own -b $rp2mac \
+ -B 192.0.2.1 -q &
+ mz_pid=$!
+
+ sleep 5
+ # In order to see this trap we need a route that points to disabled RIF.
+ # When ipv6 address is flushed, there is a delay and the routes are
+ # deleted before the RIF and we cannot get state that we have route
+ # to disabled RIF.
+ # Delete IPv6 address first and then check this trap with flushing IPv4.
+ ip -6 add flush dev br0
+ ip -4 add flush dev br0
+
+ t1_packets=$(devlink_trap_rx_packets_get $trap_name)
+ t1_bytes=$(devlink_trap_rx_bytes_get $trap_name)
+
+ if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then
+ check_err 1 "Trap stats idle when packets should be trapped"
+ fi
+
+ log_test "Egress RIF disabled"
+
+ kill $mz_pid && wait $mz_pid &> /dev/null
+ ip link set dev $rp1 nomaster
+ __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64
+ ip link del dev br0 type bridge
+ devlink_trap_action_set $trap_name "drop"
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
new file mode 100755
index 0000000..039629b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
@@ -0,0 +1,265 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test devlink-trap tunnel exceptions functionality over mlxsw.
+# Check all exception traps to make sure they are triggered under the right
+# conditions.
+
+# +-------------------------+
+# | H1 |
+# | $h1 + |
+# | 192.0.2.1/28 | |
+# +-------------------|-----+
+# |
+# +-------------------|-----+
+# | SW1 | |
+# | $swp1 + |
+# | 192.0.2.2/28 |
+# | |
+# | + g1a (gre) |
+# | loc=192.0.2.65 |
+# | rem=192.0.2.66 |
+# | tos=inherit |
+# | |
+# | + $rp1 |
+# | | 198.51.100.1/28 |
+# +--|----------------------+
+# |
+# +--|----------------------+
+# | | VRF2 |
+# | + $rp2 |
+# | 198.51.100.2/28 |
+# +-------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ decap_error_test
+"
+
+NUM_NETIFS=4
+source $lib_dir/lib.sh
+source $lib_dir/tc_common.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+vrf2_create()
+{
+ simple_if_init $rp2 198.51.100.2/28
+}
+
+vrf2_destroy()
+{
+ simple_if_fini $rp2 198.51.100.2/28
+}
+
+switch_create()
+{
+ __addr_add_del $swp1 add 192.0.2.2/28
+ tc qdisc add dev $swp1 clsact
+ ip link set dev $swp1 up
+
+ tunnel_create g1 gre 192.0.2.65 192.0.2.66 tos inherit
+ __addr_add_del g1 add 192.0.2.65/32
+ ip link set dev g1 up
+
+ __addr_add_del $rp1 add 198.51.100.1/28
+ ip link set dev $rp1 up
+}
+
+switch_destroy()
+{
+ ip link set dev $rp1 down
+ __addr_add_del $rp1 del 198.51.100.1/28
+
+ ip link set dev g1 down
+ __addr_add_del g1 del 192.0.2.65/32
+ tunnel_destroy g1
+
+ ip link set dev $swp1 down
+ tc qdisc del dev $swp1 clsact
+ __addr_add_del $swp1 del 192.0.2.2/28
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ rp1=${NETIFS[p3]}
+ rp2=${NETIFS[p4]}
+
+ forwarding_enable
+ vrf_prepare
+ h1_create
+ switch_create
+ vrf2_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ vrf2_destroy
+ switch_destroy
+ h1_destroy
+ vrf_cleanup
+ forwarding_restore
+}
+
+ecn_payload_get()
+{
+ p=$(:
+ )"0"$( : GRE flags
+ )"0:00:"$( : Reserved + version
+ )"08:00:"$( : ETH protocol type
+ )"4"$( : IP version
+ )"5:"$( : IHL
+ )"00:"$( : IP TOS
+ )"00:14:"$( : IP total length
+ )"00:00:"$( : IP identification
+ )"20:00:"$( : IP flags + frag off
+ )"30:"$( : IP TTL
+ )"01:"$( : IP proto
+ )"E7:E6:"$( : IP header csum
+ )"C0:00:01:01:"$( : IP saddr : 192.0.1.1
+ )"C0:00:02:01:"$( : IP daddr : 192.0.2.1
+ )
+ echo $p
+}
+
+ecn_decap_test()
+{
+ local trap_name="decap_error"
+ local group_name="tunnel_drops"
+ local desc=$1; shift
+ local ecn_desc=$1; shift
+ local outer_tos=$1; shift
+ local mz_pid
+
+ RET=0
+
+ tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \
+ flower src_ip 192.0.1.1 dst_ip 192.0.2.1 action pass
+
+ rp1_mac=$(mac_get $rp1)
+ rp2_mac=$(mac_get $rp2)
+ payload=$(ecn_payload_get)
+
+ ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \
+ -A 192.0.2.66 -B 192.0.2.65 -t ip \
+ len=48,tos=$outer_tos,proto=47,p=$payload -q &
+
+ mz_pid=$!
+
+ devlink_trap_exception_test $trap_name $group_name
+
+ tc_check_packets "dev $swp1 egress" 101 0
+ check_err $? "Packets were not dropped"
+
+ log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
+
+ kill $mz_pid && wait $mz_pid &> /dev/null
+ tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
+}
+
+ipip_payload_get()
+{
+ local flags=$1; shift
+ local key=$1; shift
+
+ p=$(:
+ )"$flags"$( : GRE flags
+ )"0:00:"$( : Reserved + version
+ )"08:00:"$( : ETH protocol type
+ )"$key"$( : Key
+ )"4"$( : IP version
+ )"5:"$( : IHL
+ )"00:"$( : IP TOS
+ )"00:14:"$( : IP total length
+ )"00:00:"$( : IP identification
+ )"20:00:"$( : IP flags + frag off
+ )"30:"$( : IP TTL
+ )"01:"$( : IP proto
+ )"E7:E6:"$( : IP header csum
+ )"C0:00:01:01:"$( : IP saddr : 192.0.1.1
+ )"C0:00:02:01:"$( : IP daddr : 192.0.2.1
+ )
+ echo $p
+}
+
+no_matching_tunnel_test()
+{
+ local trap_name="decap_error"
+ local group_name="tunnel_drops"
+ local desc=$1; shift
+ local sip=$1; shift
+ local mz_pid
+
+ RET=0
+
+ tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \
+ flower src_ip 192.0.1.1 dst_ip 192.0.2.1 action pass
+
+ rp1_mac=$(mac_get $rp1)
+ rp2_mac=$(mac_get $rp2)
+ payload=$(ipip_payload_get "$@")
+
+ ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \
+ -A $sip -B 192.0.2.65 -t ip len=48,proto=47,p=$payload -q &
+ mz_pid=$!
+
+ devlink_trap_exception_test $trap_name $group_name
+
+ tc_check_packets "dev $swp1 egress" 101 0
+ check_err $? "Packets were not dropped"
+
+ log_test "$desc"
+
+ kill $mz_pid && wait $mz_pid &> /dev/null
+ tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
+}
+
+decap_error_test()
+{
+ # Correct source IP - the remote address
+ local sip=192.0.2.66
+
+ ecn_decap_test "Decap error" "ECT(1)" 01
+ ecn_decap_test "Decap error" "ECT(0)" 02
+ ecn_decap_test "Decap error" "CE" 03
+
+ no_matching_tunnel_test "Decap error: Source IP check failed" \
+ 192.0.2.68 "0"
+ no_matching_tunnel_test \
+ "Decap error: Key exists but was not expected" $sip "2" ":E9:"
+
+ # Destroy the tunnel and create new one with key
+ __addr_add_del g1 del 192.0.2.65/32
+ tunnel_destroy g1
+
+ tunnel_create g1 gre 192.0.2.65 192.0.2.66 tos inherit key 233
+ __addr_add_del g1 add 192.0.2.65/32
+
+ no_matching_tunnel_test \
+ "Decap error: Key does not exist but was expected" $sip "0"
+ no_matching_tunnel_test \
+ "Decap error: Packet has a wrong key field" $sip "2" "E8:"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
new file mode 100755
index 0000000..fd19161
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
@@ -0,0 +1,330 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test devlink-trap tunnel drops and exceptions functionality over mlxsw.
+# Check all traps to make sure they are triggered under the right
+# conditions.
+
+# +--------------------+
+# | H1 (vrf) |
+# | + $h1 |
+# | | 192.0.2.1/28 |
+# +----|---------------+
+# |
+# +----|----------------------------------------------------------------------+
+# | SW | |
+# | +--|--------------------------------------------------------------------+ |
+# | | + $swp1 BR1 (802.1d) | |
+# | | | |
+# | | + vx1 (vxlan) | |
+# | | local 192.0.2.17 | |
+# | | id 1000 dstport $VXPORT | |
+# | +-----------------------------------------------------------------------+ |
+# | |
+# | + $rp1 |
+# | | 192.0.2.17/28 |
+# +----|----------------------------------------------------------------------+
+# |
+# +----|--------------------------------------------------------+
+# | | VRF2 |
+# | + $rp2 |
+# | 192.0.2.18/28 |
+# | |
+# +-------------------------------------------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ decap_error_test
+ overlay_smac_is_mc_test
+"
+
+NUM_NETIFS=4
+source $lib_dir/lib.sh
+source $lib_dir/tc_common.sh
+source $lib_dir/devlink_lib.sh
+
+: ${VXPORT:=4789}
+export VXPORT
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+switch_create()
+{
+ ip link add name br1 type bridge vlan_filtering 0 mcast_snooping 0
+ # Make sure the bridge uses the MAC address of the local port and not
+ # that of the VxLAN's device.
+ ip link set dev br1 address $(mac_get $swp1)
+ ip link set dev br1 up
+
+ tc qdisc add dev $swp1 clsact
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+
+ ip link add name vx1 type vxlan id 1000 local 192.0.2.17 \
+ dstport "$VXPORT" nolearning noudpcsum tos inherit ttl 100
+ ip link set dev vx1 master br1
+ ip link set dev vx1 up
+
+ ip address add dev $rp1 192.0.2.17/28
+ ip link set dev $rp1 up
+}
+
+switch_destroy()
+{
+ ip link set dev $rp1 down
+ ip address del dev $rp1 192.0.2.17/28
+
+ ip link set dev vx1 down
+ ip link set dev vx1 nomaster
+ ip link del dev vx1
+
+ ip link set dev $swp1 down
+ ip link set dev $swp1 nomaster
+ tc qdisc del dev $swp1 clsact
+
+ ip link set dev br1 down
+ ip link del dev br1
+}
+
+vrf2_create()
+{
+ simple_if_init $rp2 192.0.2.18/28
+}
+
+vrf2_destroy()
+{
+ simple_if_fini $rp2 192.0.2.18/28
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ rp1=${NETIFS[p3]}
+ rp2=${NETIFS[p4]}
+
+ vrf_prepare
+ forwarding_enable
+ h1_create
+ switch_create
+ vrf2_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ vrf2_destroy
+ switch_destroy
+ h1_destroy
+ forwarding_restore
+ vrf_cleanup
+}
+
+ecn_payload_get()
+{
+ dest_mac=$(mac_get $h1)
+ p=$(:
+ )"08:"$( : VXLAN flags
+ )"00:00:00:"$( : VXLAN reserved
+ )"00:03:e8:"$( : VXLAN VNI : 1000
+ )"00:"$( : VXLAN reserved
+ )"$dest_mac:"$( : ETH daddr
+ )"00:00:00:00:00:00:"$( : ETH saddr
+ )"08:00:"$( : ETH type
+ )"45:"$( : IP version + IHL
+ )"00:"$( : IP TOS
+ )"00:14:"$( : IP total length
+ )"00:00:"$( : IP identification
+ )"20:00:"$( : IP flags + frag off
+ )"40:"$( : IP TTL
+ )"00:"$( : IP proto
+ )"D6:E5:"$( : IP header csum
+ )"c0:00:02:03:"$( : IP saddr: 192.0.2.3
+ )"c0:00:02:01:"$( : IP daddr: 192.0.2.1
+ )
+ echo $p
+}
+
+ecn_decap_test()
+{
+ local trap_name="decap_error"
+ local group_name="tunnel_drops"
+ local desc=$1; shift
+ local ecn_desc=$1; shift
+ local outer_tos=$1; shift
+ local mz_pid
+
+ RET=0
+
+ tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \
+ flower src_ip 192.0.2.3 dst_ip 192.0.2.1 action pass
+
+ rp1_mac=$(mac_get $rp1)
+ payload=$(ecn_payload_get)
+
+ ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac -B 192.0.2.17 \
+ -t udp sp=12345,dp=$VXPORT,tos=$outer_tos,p=$payload -q &
+ mz_pid=$!
+
+ devlink_trap_exception_test $trap_name $group_name
+
+ tc_check_packets "dev $swp1 egress" 101 0
+ check_err $? "Packets were not dropped"
+
+ log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
+
+ kill $mz_pid && wait $mz_pid &> /dev/null
+ tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
+}
+
+reserved_bits_payload_get()
+{
+ dest_mac=$(mac_get $h1)
+ p=$(:
+ )"08:"$( : VXLAN flags
+ )"01:00:00:"$( : VXLAN reserved
+ )"00:03:e8:"$( : VXLAN VNI : 1000
+ )"00:"$( : VXLAN reserved
+ )"$dest_mac:"$( : ETH daddr
+ )"00:00:00:00:00:00:"$( : ETH saddr
+ )"08:00:"$( : ETH type
+ )"45:"$( : IP version + IHL
+ )"00:"$( : IP TOS
+ )"00:14:"$( : IP total length
+ )"00:00:"$( : IP identification
+ )"20:00:"$( : IP flags + frag off
+ )"40:"$( : IP TTL
+ )"00:"$( : IP proto
+ )"00:00:"$( : IP header csum
+ )"c0:00:02:03:"$( : IP saddr: 192.0.2.3
+ )"c0:00:02:01:"$( : IP daddr: 192.0.2.1
+ )
+ echo $p
+}
+
+short_payload_get()
+{
+ dest_mac=$(mac_get $h1)
+ p=$(:
+ )"08:"$( : VXLAN flags
+ )"01:00:00:"$( : VXLAN reserved
+ )"00:03:e8:"$( : VXLAN VNI : 1000
+ )"00:"$( : VXLAN reserved
+ )
+ echo $p
+}
+
+corrupted_packet_test()
+{
+ local trap_name="decap_error"
+ local group_name="tunnel_drops"
+ local desc=$1; shift
+ local payload_get=$1; shift
+ local mz_pid
+
+ RET=0
+
+ # In case of too short packet, there is no any inner packet,
+ # so the matching will always succeed
+ tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \
+ flower skip_hw src_ip 192.0.2.3 dst_ip 192.0.2.1 action pass
+
+ rp1_mac=$(mac_get $rp1)
+ payload=$($payload_get)
+ ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac \
+ -B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q &
+ mz_pid=$!
+
+ devlink_trap_exception_test $trap_name $group_name
+
+ tc_check_packets "dev $swp1 egress" 101 0
+ check_err $? "Packets were not dropped"
+
+ log_test "$desc"
+
+ kill $mz_pid && wait $mz_pid &> /dev/null
+ tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
+}
+
+decap_error_test()
+{
+ ecn_decap_test "Decap error" "ECT(1)" 01
+ ecn_decap_test "Decap error" "ECT(0)" 02
+ ecn_decap_test "Decap error" "CE" 03
+
+ corrupted_packet_test "Decap error: Reserved bits in use" \
+ "reserved_bits_payload_get"
+ corrupted_packet_test "Decap error: No L2 header" "short_payload_get"
+}
+
+mc_smac_payload_get()
+{
+ dest_mac=$(mac_get $h1)
+ source_mac=01:02:03:04:05:06
+ p=$(:
+ )"08:"$( : VXLAN flags
+ )"00:00:00:"$( : VXLAN reserved
+ )"00:03:e8:"$( : VXLAN VNI : 1000
+ )"00:"$( : VXLAN reserved
+ )"$dest_mac:"$( : ETH daddr
+ )"$source_mac:"$( : ETH saddr
+ )"08:00:"$( : ETH type
+ )"45:"$( : IP version + IHL
+ )"00:"$( : IP TOS
+ )"00:14:"$( : IP total length
+ )"00:00:"$( : IP identification
+ )"20:00:"$( : IP flags + frag off
+ )"40:"$( : IP TTL
+ )"00:"$( : IP proto
+ )"00:00:"$( : IP header csum
+ )"c0:00:02:03:"$( : IP saddr: 192.0.2.3
+ )"c0:00:02:01:"$( : IP daddr: 192.0.2.1
+ )
+ echo $p
+}
+
+overlay_smac_is_mc_test()
+{
+ local trap_name="overlay_smac_is_mc"
+ local group_name="tunnel_drops"
+ local mz_pid
+
+ RET=0
+
+ # The matching will be checked on devlink_trap_drop_test()
+ # and the filter will be removed on devlink_trap_drop_cleanup()
+ tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \
+ flower src_mac 01:02:03:04:05:06 action pass
+
+ rp1_mac=$(mac_get $rp1)
+ payload=$(mc_smac_payload_get)
+
+ ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac \
+ -B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q &
+ mz_pid=$!
+
+ devlink_trap_drop_test $trap_name $group_name $swp1
+
+ log_test "Overlay source MAC is multicast"
+
+ devlink_trap_drop_cleanup $mz_pid $swp1 "ip"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/fib.sh b/tools/testing/selftests/drivers/net/mlxsw/fib.sh
new file mode 100755
index 0000000..45115f8
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/fib.sh
@@ -0,0 +1,180 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking the FIB offload API on top of mlxsw.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ ipv4_identical_routes
+ ipv4_tos
+ ipv4_metric
+ ipv4_replace
+ ipv4_delete
+ ipv4_plen
+ ipv4_replay
+ ipv4_flush
+ ipv6_add
+ ipv6_metric
+ ipv6_append_single
+ ipv6_replace_single
+ ipv6_metric_multipath
+ ipv6_append_multipath
+ ipv6_replace_multipath
+ ipv6_append_multipath_to_single
+ ipv6_delete_single
+ ipv6_delete_multipath
+ ipv6_replay_single
+ ipv6_replay_multipath
+"
+NUM_NETIFS=0
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+source $lib_dir/fib_offload_lib.sh
+
+ipv4_identical_routes()
+{
+ fib_ipv4_identical_routes_test "testns1"
+}
+
+ipv4_tos()
+{
+ fib_ipv4_tos_test "testns1"
+}
+
+ipv4_metric()
+{
+ fib_ipv4_metric_test "testns1"
+}
+
+ipv4_replace()
+{
+ fib_ipv4_replace_test "testns1"
+}
+
+ipv4_delete()
+{
+ fib_ipv4_delete_test "testns1"
+}
+
+ipv4_plen()
+{
+ fib_ipv4_plen_test "testns1"
+}
+
+ipv4_replay_metric()
+{
+ fib_ipv4_replay_metric_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay_tos()
+{
+ fib_ipv4_replay_tos_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay_plen()
+{
+ fib_ipv4_replay_plen_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay()
+{
+ ipv4_replay_metric
+ ipv4_replay_tos
+ ipv4_replay_plen
+}
+
+ipv4_flush()
+{
+ fib_ipv4_flush_test "testns1"
+}
+
+ipv6_add()
+{
+ fib_ipv6_add_test "testns1"
+}
+
+ipv6_metric()
+{
+ fib_ipv6_metric_test "testns1"
+}
+
+ipv6_append_single()
+{
+ fib_ipv6_append_single_test "testns1"
+}
+
+ipv6_replace_single()
+{
+ fib_ipv6_replace_single_test "testns1"
+}
+
+ipv6_metric_multipath()
+{
+ fib_ipv6_metric_multipath_test "testns1"
+}
+
+ipv6_append_multipath()
+{
+ fib_ipv6_append_multipath_test "testns1"
+}
+
+ipv6_replace_multipath()
+{
+ fib_ipv6_replace_multipath_test "testns1"
+}
+
+ipv6_append_multipath_to_single()
+{
+ fib_ipv6_append_multipath_to_single_test "testns1"
+}
+
+ipv6_delete_single()
+{
+ fib_ipv6_delete_single_test "testns1"
+}
+
+ipv6_delete_multipath()
+{
+ fib_ipv6_delete_multipath_test "testns1"
+}
+
+ipv6_replay_single()
+{
+ fib_ipv6_replay_single_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv6_replay_multipath()
+{
+ fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV"
+}
+
+setup_prepare()
+{
+ ip netns add testns1
+ if [ $? -ne 0 ]; then
+ echo "Failed to add netns \"testns1\""
+ exit 1
+ fi
+
+ devlink dev reload $DEVLINK_DEV netns testns1
+ if [ $? -ne 0 ]; then
+ echo "Failed to reload into netns \"testns1\""
+ exit 1
+ fi
+}
+
+cleanup()
+{
+ pre_cleanup
+ devlink -N testns1 dev reload $DEVLINK_DEV netns $$
+ ip netns del testns1
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
index a593706..faa5101 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
@@ -1,29 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-humanize()
-{
- local speed=$1; shift
-
- for unit in bps Kbps Mbps Gbps; do
- if (($(echo "$speed < 1024" | bc))); then
- break
- fi
-
- speed=$(echo "scale=1; $speed / 1024" | bc)
- done
-
- echo "$speed${unit}"
-}
-
-rate()
-{
- local t0=$1; shift
- local t1=$1; shift
- local interval=$1; shift
-
- echo $((8 * (t1 - t0) / interval))
-}
-
check_rate()
{
local rate=$1; shift
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index 47315fe..24dd8ed4 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -232,7 +232,7 @@
stop_traffic
local ucth1=${uc_rate[1]}
- start_traffic $h1 own bc bc
+ start_traffic $h1 192.0.2.65 bc bc
local d0=$(date +%s)
local t0=$(ethtool_stats_get $h3 rx_octets_prio_0)
@@ -254,7 +254,11 @@
ret = 100 * ($ucth1 - $ucth2) / $ucth1
if (ret > 0) { ret } else { 0 }
")
- check_err $(bc <<< "$deg > 25")
+
+ # Minimum shaper of 200Mbps on MC TCs should cause about 20% of
+ # degradation on 1Gbps link.
+ check_err $(bc <<< "$deg < 15") "Minimum shaper not in effect"
+ check_err $(bc <<< "$deg > 25") "MC traffic degrades UC performance too much"
local interval=$((d1 - d0))
local mc_ir=$(rate $u0 $u1 $interval)
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh
new file mode 100755
index 0000000..c6ce0b4
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source qos_lib.sh
+bail_on_lldpad
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+TCFLAGS=skip_sw
+source $lib_dir/sch_tbf_ets.sh
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh
new file mode 100755
index 0000000..8d245f3
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source qos_lib.sh
+bail_on_lldpad
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+TCFLAGS=skip_sw
+source $lib_dir/sch_tbf_prio.sh
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh
new file mode 100755
index 0000000..0138860
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source qos_lib.sh
+bail_on_lldpad
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+TCFLAGS=skip_sw
+source $lib_dir/sch_tbf_root.sh
diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib.sh b/tools/testing/selftests/drivers/net/netdevsim/fib.sh
new file mode 100755
index 0000000..2f87c3b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/fib.sh
@@ -0,0 +1,341 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking the FIB offload API. It makes use of netdevsim
+# which registers a listener to the FIB notification chain.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ ipv4_identical_routes
+ ipv4_tos
+ ipv4_metric
+ ipv4_replace
+ ipv4_delete
+ ipv4_plen
+ ipv4_replay
+ ipv4_flush
+ ipv4_error_path
+ ipv6_add
+ ipv6_metric
+ ipv6_append_single
+ ipv6_replace_single
+ ipv6_metric_multipath
+ ipv6_append_multipath
+ ipv6_replace_multipath
+ ipv6_append_multipath_to_single
+ ipv6_delete_single
+ ipv6_delete_multipath
+ ipv6_replay_single
+ ipv6_replay_multipath
+ ipv6_error_path
+"
+NETDEVSIM_PATH=/sys/bus/netdevsim/
+DEV_ADDR=1337
+DEV=netdevsim${DEV_ADDR}
+DEVLINK_DEV=netdevsim/${DEV}
+SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/
+NUM_NETIFS=0
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+source $lib_dir/fib_offload_lib.sh
+
+ipv4_identical_routes()
+{
+ fib_ipv4_identical_routes_test "testns1"
+}
+
+ipv4_tos()
+{
+ fib_ipv4_tos_test "testns1"
+}
+
+ipv4_metric()
+{
+ fib_ipv4_metric_test "testns1"
+}
+
+ipv4_replace()
+{
+ fib_ipv4_replace_test "testns1"
+}
+
+ipv4_delete()
+{
+ fib_ipv4_delete_test "testns1"
+}
+
+ipv4_plen()
+{
+ fib_ipv4_plen_test "testns1"
+}
+
+ipv4_replay_metric()
+{
+ fib_ipv4_replay_metric_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay_tos()
+{
+ fib_ipv4_replay_tos_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay_plen()
+{
+ fib_ipv4_replay_plen_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay()
+{
+ ipv4_replay_metric
+ ipv4_replay_tos
+ ipv4_replay_plen
+}
+
+ipv4_flush()
+{
+ fib_ipv4_flush_test "testns1"
+}
+
+ipv4_error_path_add()
+{
+ local lsb
+
+ RET=0
+
+ ip -n testns1 link add name dummy1 type dummy
+ ip -n testns1 link set dev dummy1 up
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 10
+ devlink -N testns1 dev reload $DEVLINK_DEV
+
+ for lsb in $(seq 1 20); do
+ ip -n testns1 route add 192.0.2.${lsb}/32 dev dummy1 \
+ &> /dev/null
+ done
+
+ log_test "IPv4 error path - add"
+
+ ip -n testns1 link del dev dummy1
+}
+
+ipv4_error_path_replay()
+{
+ local lsb
+
+ RET=0
+
+ ip -n testns1 link add name dummy1 type dummy
+ ip -n testns1 link set dev dummy1 up
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 100
+ devlink -N testns1 dev reload $DEVLINK_DEV
+
+ for lsb in $(seq 1 20); do
+ ip -n testns1 route add 192.0.2.${lsb}/32 dev dummy1
+ done
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 10
+ devlink -N testns1 dev reload $DEVLINK_DEV &> /dev/null
+
+ log_test "IPv4 error path - replay"
+
+ ip -n testns1 link del dev dummy1
+
+ # Successfully reload after deleting all the routes.
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 100
+ devlink -N testns1 dev reload $DEVLINK_DEV
+}
+
+ipv4_error_path()
+{
+ # Test the different error paths of the notifiers by limiting the size
+ # of the "IPv4/fib" resource.
+ ipv4_error_path_add
+ ipv4_error_path_replay
+}
+
+ipv6_add()
+{
+ fib_ipv6_add_test "testns1"
+}
+
+ipv6_metric()
+{
+ fib_ipv6_metric_test "testns1"
+}
+
+ipv6_append_single()
+{
+ fib_ipv6_append_single_test "testns1"
+}
+
+ipv6_replace_single()
+{
+ fib_ipv6_replace_single_test "testns1"
+}
+
+ipv6_metric_multipath()
+{
+ fib_ipv6_metric_multipath_test "testns1"
+}
+
+ipv6_append_multipath()
+{
+ fib_ipv6_append_multipath_test "testns1"
+}
+
+ipv6_replace_multipath()
+{
+ fib_ipv6_replace_multipath_test "testns1"
+}
+
+ipv6_append_multipath_to_single()
+{
+ fib_ipv6_append_multipath_to_single_test "testns1"
+}
+
+ipv6_delete_single()
+{
+ fib_ipv6_delete_single_test "testns1"
+}
+
+ipv6_delete_multipath()
+{
+ fib_ipv6_delete_multipath_test "testns1"
+}
+
+ipv6_replay_single()
+{
+ fib_ipv6_replay_single_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv6_replay_multipath()
+{
+ fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv6_error_path_add_single()
+{
+ local lsb
+
+ RET=0
+
+ ip -n testns1 link add name dummy1 type dummy
+ ip -n testns1 link set dev dummy1 up
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10
+ devlink -N testns1 dev reload $DEVLINK_DEV
+
+ for lsb in $(seq 1 20); do
+ ip -n testns1 route add 2001:db8:1::${lsb}/128 dev dummy1 \
+ &> /dev/null
+ done
+
+ log_test "IPv6 error path - add single"
+
+ ip -n testns1 link del dev dummy1
+}
+
+ipv6_error_path_add_multipath()
+{
+ local lsb
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n testns1 link add name dummy$i type dummy
+ ip -n testns1 link set dev dummy$i up
+ ip -n testns1 address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10
+ devlink -N testns1 dev reload $DEVLINK_DEV
+
+ for lsb in $(seq 1 20); do
+ ip -n testns1 route add 2001:db8:10::${lsb}/128 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2 &> /dev/null
+ done
+
+ log_test "IPv6 error path - add multipath"
+
+ for i in $(seq 1 2); do
+ ip -n testns1 link del dev dummy$i
+ done
+}
+
+ipv6_error_path_replay()
+{
+ local lsb
+
+ RET=0
+
+ ip -n testns1 link add name dummy1 type dummy
+ ip -n testns1 link set dev dummy1 up
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 100
+ devlink -N testns1 dev reload $DEVLINK_DEV
+
+ for lsb in $(seq 1 20); do
+ ip -n testns1 route add 2001:db8:1::${lsb}/128 dev dummy1
+ done
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10
+ devlink -N testns1 dev reload $DEVLINK_DEV &> /dev/null
+
+ log_test "IPv6 error path - replay"
+
+ ip -n testns1 link del dev dummy1
+
+ # Successfully reload after deleting all the routes.
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 100
+ devlink -N testns1 dev reload $DEVLINK_DEV
+}
+
+ipv6_error_path()
+{
+ # Test the different error paths of the notifiers by limiting the size
+ # of the "IPv6/fib" resource.
+ ipv6_error_path_add_single
+ ipv6_error_path_add_multipath
+ ipv6_error_path_replay
+}
+
+setup_prepare()
+{
+ local netdev
+
+ modprobe netdevsim &> /dev/null
+
+ echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device
+ while [ ! -d $SYSFS_NET_DIR ] ; do :; done
+
+ ip netns add testns1
+ if [ $? -ne 0 ]; then
+ echo "Failed to add netns \"testns1\""
+ exit 1
+ fi
+
+ devlink dev reload $DEVLINK_DEV netns testns1
+ if [ $? -ne 0 ]; then
+ echo "Failed to reload into netns \"testns1\""
+ exit 1
+ fi
+}
+
+cleanup()
+{
+ pre_cleanup
+ ip netns del testns1
+ echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device
+ modprobe -r netdevsim &> /dev/null
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 15cb8ab6..fb5c55d 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -1165,8 +1165,8 @@
for a in ${NSA_IP} ${VRF_IP}
do
log_start
- show_hint "Should fail 'No route to host' since client is not bound to VRF"
- run_cmd nettest -s -2 ${VRF} &
+ show_hint "Should fail 'Connection refused' since client is not bound to VRF"
+ run_cmd nettest -s -d ${VRF} &
sleep 1
run_cmd nettest -r ${a}
log_test_addr ${a} $? 1 "Global server, local connection"
@@ -2663,8 +2663,8 @@
for a in ${NSA_IP6} ${VRF_IP6}
do
log_start
- show_hint "Fails 'No route to host' since client is not in VRF"
- run_cmd nettest -6 -s -2 ${VRF} &
+ show_hint "Fails 'Connection refused' since client is not in VRF"
+ run_cmd nettest -6 -s -d ${VRF} &
sleep 1
run_cmd nettest -6 -r ${a}
log_test_addr ${a} $? 1 "Global server, local connection"
diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh
new file mode 100644
index 0000000..6649665
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh
@@ -0,0 +1,873 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Various helpers and tests to verify FIB offload.
+
+__fib_trap_check()
+{
+ local ns=$1; shift
+ local family=$1; shift
+ local route=$1; shift
+ local should_fail=$1; shift
+ local ret
+
+ ip -n $ns -j -p -$family route show $route \
+ | jq -e '.[]["flags"] | contains(["trap"])' &> /dev/null
+ ret=$?
+ if [[ $should_fail == "true" ]]; then
+ if [[ $ret -ne 0 ]]; then
+ return 0
+ else
+ return 1
+ fi
+ fi
+
+ return $ret
+}
+
+fib_trap_check()
+{
+ local ns=$1; shift
+ local family=$1; shift
+ local route=$1; shift
+ local should_fail=$1; shift
+
+ busywait 5000 __fib_trap_check $ns $family "$route" $should_fail
+}
+
+fib4_trap_check()
+{
+ local ns=$1; shift
+ local route=$1; shift
+ local should_fail=$1; shift
+
+ fib_trap_check $ns 4 "$route" $should_fail
+}
+
+fib6_trap_check()
+{
+ local ns=$1; shift
+ local route=$1; shift
+ local should_fail=$1; shift
+
+ fib_trap_check $ns 6 "$route" $should_fail
+}
+
+fib_ipv4_identical_routes_test()
+{
+ local ns=$1; shift
+ local i
+
+ RET=0
+
+ for i in $(seq 1 3); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ done
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route append 192.0.2.0/24 dev dummy2 tos 0 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy2 tos 0 metric 1024" true
+ check_err $? "Appended route in hardware when should not"
+
+ ip -n $ns route prepend 192.0.2.0/24 dev dummy3 tos 0 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy3 tos 0 metric 1024" false
+ check_err $? "Prepended route not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true
+ check_err $? "Route was not replaced in hardware by prepended one"
+
+ log_test "IPv4 identical routes"
+
+ for i in $(seq 1 3); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv4_tos_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 2 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 2 metric 1024" false
+ check_err $? "Highest TOS route not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true
+ check_err $? "Lowest TOS route still in hardware when should not"
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1 metric 1024" true
+ check_err $? "Middle TOS route in hardware when should not"
+
+ log_test "IPv4 routes with TOS"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_metric_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1022
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1022" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" true
+ check_err $? "Highest metric route still in hardware when should not"
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1023
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1023" true
+ check_err $? "Middle metric route in hardware when should not"
+
+ log_test "IPv4 routes with metric"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_replace_test()
+{
+ local ns=$1; shift
+ local i
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ done
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route replace 192.0.2.0/24 dev dummy2 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1024" false
+ check_err $? "Replacement route not in hardware when should"
+
+ # Add a route with an higher metric and make sure that replacing it
+ # does not affect the lower metric one.
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1025
+ ip -n $ns route replace 192.0.2.0/24 dev dummy2 metric 1025
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1025" true
+ check_err $? "Highest metric route in hardware when should not"
+
+ log_test "IPv4 route replace"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv4_delete_test()
+{
+ local ns=$1; shift
+ local metric
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ # Insert multiple routes with the same prefix and length and varying
+ # metrics. Make sure that throughout delete operations the lowest
+ # metric route is the one in hardware.
+ for metric in $(seq 1024 1026); do
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric $metric
+ done
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route del 192.0.2.0/24 dev dummy1 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ ip -n $ns route del 192.0.2.0/24 dev dummy1 metric 1026
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" false
+ check_err $? "Sole route not in hardware when should"
+
+ log_test "IPv4 route delete"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_plen_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ # Add two routes with the same key and different prefix length and
+ # make sure both are in hardware. It can be verfied that both are
+ # sharing the same leaf by checking the /proc/net/fib_trie
+ ip -n $ns route add 192.0.2.0/24 dev dummy1
+ ip -n $ns route add 192.0.2.0/25 dev dummy1
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1" false
+ check_err $? "/24 not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/25 dev dummy1" false
+ check_err $? "/25 not in hardware when should"
+
+ log_test "IPv4 routes with different prefix length"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_replay_metric_test()
+{
+ local ns=$1; shift
+ local devlink_dev=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1025
+
+ devlink -N $ns dev reload $devlink_dev
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" true
+ check_err $? "Highest metric route in hardware when should not"
+
+ log_test "IPv4 routes replay - metric"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_replay_tos_test()
+{
+ local ns=$1; shift
+ local devlink_dev=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1
+
+ devlink -N $ns dev reload $devlink_dev
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1" false
+ check_err $? "Highest TOS route not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0" true
+ check_err $? "Lowest TOS route in hardware when should not"
+
+ log_test "IPv4 routes replay - TOS"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_replay_plen_test()
+{
+ local ns=$1; shift
+ local devlink_dev=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1
+ ip -n $ns route add 192.0.2.0/25 dev dummy1
+
+ devlink -N $ns dev reload $devlink_dev
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1" false
+ check_err $? "/24 not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/25 dev dummy1" false
+ check_err $? "/25 not in hardware when should"
+
+ log_test "IPv4 routes replay - prefix length"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_flush_test()
+{
+ local ns=$1; shift
+ local metric
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ # Exercise the routes flushing code paths by inserting various
+ # prefix routes on a netdev and then deleting it.
+ for metric in $(seq 1 20); do
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric $metric
+ done
+
+ ip -n $ns link del dev dummy1
+
+ log_test "IPv4 routes flushing"
+}
+
+fib_ipv6_add_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ done
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route append 2001:db8:1::/64 dev dummy2 metric 1024
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" true
+ check_err $? "Route in hardware when should not"
+
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware after appending route"
+
+ log_test "IPv6 single route add"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_metric_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1022
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1022" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" true
+ check_err $? "Highest metric route still in hardware when should not"
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1023
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1023" true
+ check_err $? "Middle metric route in hardware when should not"
+
+ log_test "IPv6 routes with metric"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv6_append_single_test()
+{
+ local ns=$1; shift
+
+ # When an IPv6 multipath route is added without the 'nexthop' keyword,
+ # different code paths are taken compared to when the keyword is used.
+ # This test tries to verify the former.
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 via 2001:db8:1::2 metric 1024
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route append 2001:db8:10::/64 via 2001:db8:2::2 metric 1024
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware after appending"
+
+ ip -n $ns route add 2001:db8:10::/64 via 2001:db8:1::2 metric 1025
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Route in hardware when should not"
+
+ ip -n $ns route append 2001:db8:10::/64 via 2001:db8:2::2 metric 1025
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Route in hardware when should not after appending"
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ log_test "IPv6 append single route without 'nexthop' keyword"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_replace_single_test()
+{
+ local ns=$1; shift
+ local i
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ done
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route replace 2001:db8:1::/64 dev dummy2 metric 1024
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" false
+ check_err $? "Replacement route not in hardware when should"
+
+ # Add a route with an higher metric and make sure that replacing it
+ # does not affect the lower metric one.
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1025
+ ip -n $ns route replace 2001:db8:1::/64 dev dummy2 metric 1025
+
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1025" true
+ check_err $? "Highest metric route in hardware when should not"
+
+ log_test "IPv6 single route replace"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_metric_multipath_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1022 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1022" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1023 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" true
+ check_err $? "Highest metric route still in hardware when should not"
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1023" true
+ check_err $? "Middle metric route in hardware when should not"
+
+ log_test "IPv6 multipath routes with metric"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_append_multipath_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ for i in $(seq 1 3); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route append 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:2::2 dev dummy2 \
+ nexthop via 2001:db8:3::2 dev dummy3
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware after appending"
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Route in hardware when should not"
+
+ ip -n $ns route append 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:2::2 dev dummy2 \
+ nexthop via 2001:db8:3::2 dev dummy3
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Route in hardware when should not after appending"
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ log_test "IPv6 append multipath route with 'nexthop' keyword"
+
+ for i in $(seq 1 3); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_replace_multipath_test()
+{
+ local ns=$1; shift
+ local i
+
+ RET=0
+
+ for i in $(seq 1 3); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route replace 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:3::2 dev dummy3
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Replacement route not in hardware when should"
+
+ # Add a route with an higher metric and make sure that replacing it
+ # does not affect the lower metric one.
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route replace 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:3::2 dev dummy3
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Highest metric route in hardware when should not"
+
+ log_test "IPv6 multipath route replace"
+
+ for i in $(seq 1 3); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_append_multipath_to_single_test()
+{
+ local ns=$1; shift
+
+ # Test that when the first route in the leaf is not a multipath route
+ # and we try to append a multipath route with the same metric to it, it
+ # is not notified.
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route append 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy2 metric 1024" true
+ check_err $? "Route in hardware when should not"
+
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware after append"
+
+ log_test "IPv6 append multipath route to non-multipath route"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_delete_single_test()
+{
+ local ns=$1; shift
+
+ # Test various deletion scenarios, where only a single route is
+ # deleted from the FIB node.
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ # Test deletion of a single route when it is the only route in the FIB
+ # node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024
+
+ log_test "IPv6 delete sole single route"
+
+ # Test that deletion of last route does not affect the first one.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025
+
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware after deleting higher metric route"
+
+ log_test "IPv6 delete single route not in hardware"
+
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024
+
+ # Test that first route is replaced by next single route in the FIB
+ # node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024
+
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1025" false
+ check_err $? "Route not in hardware after deleting lowest metric route"
+
+ log_test "IPv6 delete single route - replaced by single"
+
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025
+
+ # Test that first route is replaced by next multipath route in the FIB
+ # node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" false
+ check_err $? "Route not in hardware after deleting lowest metric route"
+
+ log_test "IPv6 delete single route - replaced by multipath"
+
+ ip -n $ns route del 2001:db8:10::/64 metric 1025
+
+ # Test deletion of a single nexthop from a multipath route.
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route del 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware after deleting a single nexthop"
+
+ log_test "IPv6 delete single nexthop"
+
+ ip -n $ns route del 2001:db8:10::/64 metric 1024
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_delete_multipath_test()
+{
+ local ns=$1; shift
+
+ # Test various deletion scenarios, where an entire multipath route is
+ # deleted from the FIB node.
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ # Test deletion of a multipath route when it is the only route in the
+ # FIB node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route del 2001:db8:10::/64 metric 1024
+
+ log_test "IPv6 delete sole multipath route"
+
+ # Test that deletion of last route does not affect the first one.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route del 2001:db8:10::/64 metric 1025
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware after deleting higher metric route"
+
+ log_test "IPv6 delete multipath route not in hardware"
+
+ ip -n $ns route del 2001:db8:10::/64 metric 1024
+
+ # Test that first route is replaced by next single route in the FIB
+ # node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025
+ ip -n $ns route del 2001:db8:10::/64 metric 1024
+
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1025" false
+ check_err $? "Route not in hardware after deleting lowest metric route"
+
+ log_test "IPv6 delete multipath route - replaced by single"
+
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025
+
+ # Test that first route is replaced by next multipath route in the FIB
+ # node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route del 2001:db8:10::/64 metric 1024
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" false
+ check_err $? "Route not in hardware after deleting lowest metric route"
+
+ log_test "IPv6 delete multipath route - replaced by multipath"
+
+ ip -n $ns route del 2001:db8:10::/64 metric 1025
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_replay_single_test()
+{
+ local ns=$1; shift
+ local devlink_dev=$1; shift
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ done
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1
+ ip -n $ns route append 2001:db8:1::/64 dev dummy2
+
+ devlink -N $ns dev reload $devlink_dev
+
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1" false
+ check_err $? "First route not in hardware when should"
+
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy2" true
+ check_err $? "Second route in hardware when should not"
+
+ log_test "IPv6 routes replay - single route"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_replay_multipath_test()
+{
+ local ns=$1; shift
+ local devlink_dev=$1; shift
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+
+ devlink -N $ns dev reload $devlink_dev
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "First route not in hardware when should"
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Second route in hardware when should not"
+
+ log_test "IPv6 routes replay - multipath route"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 8dc5fac..2f5da41 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -248,6 +248,24 @@
done
}
+until_counter_is()
+{
+ local value=$1; shift
+ local current=$("$@")
+
+ echo $((current))
+ ((current >= value))
+}
+
+busywait_for_counter()
+{
+ local timeout=$1; shift
+ local delta=$1; shift
+
+ local base=$("$@")
+ busywait "$timeout" until_counter_is $((base + delta)) "$@"
+}
+
setup_wait_dev()
{
local dev=$1; shift
@@ -575,9 +593,10 @@
local dev=$1; shift
local pref=$1; shift
local dir=$1; shift
+ local selector=${1:-.packets}; shift
tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \
- | jq '.[1].options.actions[].stats.packets'
+ | jq ".[1].options.actions[].stats$selector"
}
ethtool_stats_get()
@@ -588,6 +607,30 @@
ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2
}
+humanize()
+{
+ local speed=$1; shift
+
+ for unit in bps Kbps Mbps Gbps; do
+ if (($(echo "$speed < 1024" | bc))); then
+ break
+ fi
+
+ speed=$(echo "scale=1; $speed / 1024" | bc)
+ done
+
+ echo "$speed${unit}"
+}
+
+rate()
+{
+ local t0=$1; shift
+ local t1=$1; shift
+ local interval=$1; shift
+
+ echo $((8 * (t1 - t0) / interval))
+}
+
mac_get()
{
local if_name=$1
diff --git a/tools/testing/selftests/net/forwarding/loopback.sh b/tools/testing/selftests/net/forwarding/loopback.sh
index 6e4626a..8f40573 100755
--- a/tools/testing/selftests/net/forwarding/loopback.sh
+++ b/tools/testing/selftests/net/forwarding/loopback.sh
@@ -1,6 +1,9 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
ALL_TESTS="loopback_test"
NUM_NETIFS=2
source tc_common.sh
@@ -72,6 +75,11 @@
h1_create
h2_create
+
+ if ethtool -k $h1 | grep loopback | grep -q fixed; then
+ log_test "SKIP: dev $h1 does not support loopback feature"
+ exit $ksft_skip
+ fi
}
cleanup()
diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh
index a75cb51..057f91b 100755
--- a/tools/testing/selftests/net/forwarding/router.sh
+++ b/tools/testing/selftests/net/forwarding/router.sh
@@ -1,9 +1,23 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="ping_ipv4 ping_ipv6"
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+ sip_in_class_e
+ mc_mac_mismatch
+ ipv4_sip_equal_dip
+ ipv6_sip_equal_dip
+ ipv4_dip_link_local
+"
+
NUM_NETIFS=4
source lib.sh
+source tc_common.sh
+
+require_command $MCD
+require_command $MC_CLI
+table_name=selftests
h1_create()
{
@@ -64,6 +78,8 @@
ip link set dev $rp1 up
ip link set dev $rp2 up
+ tc qdisc add dev $rp2 clsact
+
ip address add 192.0.2.1/24 dev $rp1
ip address add 2001:db8:1::1/64 dev $rp1
@@ -79,10 +95,31 @@
ip address del 2001:db8:1::1/64 dev $rp1
ip address del 192.0.2.1/24 dev $rp1
+ tc qdisc del dev $rp2 clsact
+
ip link set dev $rp2 down
ip link set dev $rp1 down
}
+start_mcd()
+{
+ SMCROUTEDIR="$(mktemp -d)"
+
+ for ((i = 1; i <= $NUM_NETIFS; ++i)); do
+ echo "phyint ${NETIFS[p$i]} enable" >> \
+ $SMCROUTEDIR/$table_name.conf
+ done
+
+ $MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \
+ -P $SMCROUTEDIR/$table_name.pid
+}
+
+kill_mcd()
+{
+ pkill $MCD
+ rm -rf $SMCROUTEDIR
+}
+
setup_prepare()
{
h1=${NETIFS[p1]}
@@ -91,6 +128,10 @@
rp2=${NETIFS[p3]}
h2=${NETIFS[p4]}
+ rp1mac=$(mac_get $rp1)
+
+ start_mcd
+
vrf_prepare
h1_create
@@ -113,6 +154,8 @@
h1_destroy
vrf_cleanup
+
+ kill_mcd
}
ping_ipv4()
@@ -125,6 +168,150 @@
ping6_test $h1 2001:db8:2::2
}
+sip_in_class_e()
+{
+ RET=0
+
+ # Disable rpfilter to prevent packets to be dropped because of it.
+ sysctl_set net.ipv4.conf.all.rp_filter 0
+ sysctl_set net.ipv4.conf.$rp1.rp_filter 0
+
+ tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \
+ flower src_ip 240.0.0.1 ip_proto udp action pass
+
+ $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \
+ -A 240.0.0.1 -b $rp1mac -B 198.51.100.2 -q
+
+ tc_check_packets "dev $rp2 egress" 101 5
+ check_err $? "Packets were dropped"
+
+ log_test "Source IP in class E"
+
+ tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+ sysctl_restore net.ipv4.conf.$rp1.rp_filter
+ sysctl_restore net.ipv4.conf.all.rp_filter
+}
+
+create_mcast_sg()
+{
+ local if_name=$1; shift
+ local s_addr=$1; shift
+ local mcast=$1; shift
+ local dest_ifs=${@}
+
+ $MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs
+}
+
+delete_mcast_sg()
+{
+ local if_name=$1; shift
+ local s_addr=$1; shift
+ local mcast=$1; shift
+ local dest_ifs=${@}
+
+ $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs
+}
+
+__mc_mac_mismatch()
+{
+ local desc=$1; shift
+ local proto=$1; shift
+ local sip=$1; shift
+ local dip=$1; shift
+ local flags=${1:-""}; shift
+ local dmac=01:02:03:04:05:06
+
+ RET=0
+
+ tc filter add dev $rp2 egress protocol $proto pref 1 handle 101 \
+ flower dst_ip $dip action pass
+
+ create_mcast_sg $rp1 $sip $dip $rp2
+
+ $MZ $flags $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b $dmac \
+ -B $dip -q
+
+ tc_check_packets "dev $rp2 egress" 101 5
+ check_err $? "Packets were dropped"
+
+ log_test "Multicast MAC mismatch: $desc"
+
+ delete_mcast_sg $rp1 $sip $dip $rp2
+ tc filter del dev $rp2 egress protocol $proto pref 1 handle 101 flower
+}
+
+mc_mac_mismatch()
+{
+ __mc_mac_mismatch "IPv4" "ip" 192.0.2.2 225.1.2.3
+ __mc_mac_mismatch "IPv6" "ipv6" 2001:db8:1::2 ff0e::3 "-6"
+}
+
+ipv4_sip_equal_dip()
+{
+ RET=0
+
+ # Disable rpfilter to prevent packets to be dropped because of it.
+ sysctl_set net.ipv4.conf.all.rp_filter 0
+ sysctl_set net.ipv4.conf.$rp1.rp_filter 0
+
+ tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \
+ flower src_ip 198.51.100.2 action pass
+
+ $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \
+ -A 198.51.100.2 -b $rp1mac -B 198.51.100.2 -q
+
+ tc_check_packets "dev $rp2 egress" 101 5
+ check_err $? "Packets were dropped"
+
+ log_test "Source IP is equal to destination IP: IPv4"
+
+ tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+ sysctl_restore net.ipv4.conf.$rp1.rp_filter
+ sysctl_restore net.ipv4.conf.all.rp_filter
+}
+
+ipv6_sip_equal_dip()
+{
+ RET=0
+
+ tc filter add dev $rp2 egress protocol ipv6 pref 1 handle 101 \
+ flower src_ip 2001:db8:2::2 action pass
+
+ $MZ -6 $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \
+ -A 2001:db8:2::2 -b $rp1mac -B 2001:db8:2::2 -q
+
+ tc_check_packets "dev $rp2 egress" 101 5
+ check_err $? "Packets were dropped"
+
+ log_test "Source IP is equal to destination IP: IPv6"
+
+ tc filter del dev $rp2 egress protocol ipv6 pref 1 handle 101 flower
+}
+
+ipv4_dip_link_local()
+{
+ local dip=169.254.1.1
+
+ RET=0
+
+ tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \
+ flower dst_ip $dip action pass
+
+ ip neigh add 169.254.1.1 lladdr 00:11:22:33:44:55 dev $rp2
+ ip route add 169.254.1.0/24 dev $rp2
+
+ $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b $rp1mac -B $dip -q
+
+ tc_check_packets "dev $rp2 egress" 101 5
+ check_err $? "Packets were dropped"
+
+ log_test "IPv4 destination IP is link-local"
+
+ ip route del 169.254.1.0/24 dev $rp2
+ ip neigh del 169.254.1.1 lladdr 00:11:22:33:44:55 dev $rp2
+ tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_core.sh b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh
new file mode 100644
index 0000000..d1f26cb
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh
@@ -0,0 +1,233 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# This test sends a stream of traffic from H1 through a switch, to H2. On the
+# egress port from the switch ($swp2), a shaper is installed. The test verifies
+# that the rates on the port match the configured shaper.
+#
+# In order to test per-class shaping, $swp2 actually contains TBF under PRIO or
+# ETS, with two different configurations. Traffic is prioritized using 802.1p.
+#
+# +-------------------------------------------+
+# | H1 |
+# | + $h1.10 $h1.11 + |
+# | | 192.0.2.1/28 192.0.2.17/28 | |
+# | | | |
+# | \______________ _____________/ |
+# | \ / |
+# | + $h1 |
+# +---------------------|---------------------+
+# |
+# +---------------------|---------------------+
+# | SW + $swp1 |
+# | _______________/ \_______________ |
+# | / \ |
+# | +-|--------------+ +--------------|-+ |
+# | | + $swp1.10 | | $swp1.11 + | |
+# | | | | | |
+# | | BR10 | | BR11 | |
+# | | | | | |
+# | | + $swp2.10 | | $swp2.11 + | |
+# | +-|--------------+ +--------------|-+ |
+# | \_______________ ______________/ |
+# | \ / |
+# | + $swp2 |
+# +---------------------|---------------------+
+# |
+# +---------------------|---------------------+
+# | H2 + $h2 |
+# | ______________/ \______________ |
+# | / \ |
+# | | | |
+# | + $h2.10 $h2.11 + |
+# | 192.0.2.2/28 192.0.2.18/28 |
+# +-------------------------------------------+
+
+NUM_NETIFS=4
+CHECK_TC="yes"
+source $lib_dir/lib.sh
+
+ipaddr()
+{
+ local host=$1; shift
+ local vlan=$1; shift
+
+ echo 192.0.2.$((16 * (vlan - 10) + host))
+}
+
+host_create()
+{
+ local dev=$1; shift
+ local host=$1; shift
+
+ simple_if_init $dev
+ mtu_set $dev 10000
+
+ vlan_create $dev 10 v$dev $(ipaddr $host 10)/28
+ ip link set dev $dev.10 type vlan egress 0:0
+
+ vlan_create $dev 11 v$dev $(ipaddr $host 11)/28
+ ip link set dev $dev.11 type vlan egress 0:1
+}
+
+host_destroy()
+{
+ local dev=$1; shift
+
+ vlan_destroy $dev 11
+ vlan_destroy $dev 10
+ mtu_restore $dev
+ simple_if_fini $dev
+}
+
+h1_create()
+{
+ host_create $h1 1
+}
+
+h1_destroy()
+{
+ host_destroy $h1
+}
+
+h2_create()
+{
+ host_create $h2 2
+
+ tc qdisc add dev $h2 clsact
+ tc filter add dev $h2 ingress pref 1010 prot 802.1q \
+ flower $TCFLAGS vlan_id 10 action pass
+ tc filter add dev $h2 ingress pref 1011 prot 802.1q \
+ flower $TCFLAGS vlan_id 11 action pass
+}
+
+h2_destroy()
+{
+ tc qdisc del dev $h2 clsact
+ host_destroy $h2
+}
+
+switch_create()
+{
+ local intf
+ local vlan
+
+ ip link add dev br10 type bridge
+ ip link add dev br11 type bridge
+
+ for intf in $swp1 $swp2; do
+ ip link set dev $intf up
+ mtu_set $intf 10000
+
+ for vlan in 10 11; do
+ vlan_create $intf $vlan
+ ip link set dev $intf.$vlan master br$vlan
+ ip link set dev $intf.$vlan up
+ done
+ done
+
+ for vlan in 10 11; do
+ ip link set dev $swp1.$vlan type vlan ingress 0:0 1:1
+ done
+
+ ip link set dev br10 up
+ ip link set dev br11 up
+}
+
+switch_destroy()
+{
+ local intf
+ local vlan
+
+ # A test may have been interrupted mid-run, with Qdisc installed. Delete
+ # it here.
+ tc qdisc del dev $swp2 root 2>/dev/null
+
+ ip link set dev br11 down
+ ip link set dev br10 down
+
+ for intf in $swp2 $swp1; do
+ for vlan in 11 10; do
+ ip link set dev $intf.$vlan down
+ ip link set dev $intf.$vlan nomaster
+ vlan_destroy $intf $vlan
+ done
+
+ mtu_restore $intf
+ ip link set dev $intf down
+ done
+
+ ip link del dev br11
+ ip link del dev br10
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ swp4=${NETIFS[p7]}
+ swp5=${NETIFS[p8]}
+
+ h2_mac=$(mac_get $h2)
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h1.10 $(ipaddr 2 10) " vlan 10"
+ ping_test $h1.11 $(ipaddr 2 11) " vlan 11"
+}
+
+tbf_get_counter()
+{
+ local vlan=$1; shift
+
+ tc_rule_stats_get $h2 10$vlan ingress .bytes
+}
+
+do_tbf_test()
+{
+ local vlan=$1; shift
+ local mbit=$1; shift
+
+ start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 2 $vlan) $h2_mac
+ sleep 5 # Wait for the burst to dwindle
+
+ local t2=$(busywait_for_counter 1000 +1 tbf_get_counter $vlan)
+ sleep 10
+ local t3=$(tbf_get_counter $vlan)
+ stop_traffic
+
+ RET=0
+
+ # Note: TBF uses 10^6 Mbits, not 2^20 ones.
+ local er=$((mbit * 1000 * 1000))
+ local nr=$(rate $t2 $t3 10)
+ local nr_pct=$((100 * (nr - er) / er))
+ ((-5 <= nr_pct && nr_pct <= 5))
+ check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-5%."
+
+ log_test "TC $((vlan - 10)): TBF rate ${mbit}Mbit"
+}
diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh b/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh
new file mode 100755
index 0000000..84fb6ca
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh
@@ -0,0 +1,6 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+QDISC="ets strict"
+: ${lib_dir:=.}
+source $lib_dir/sch_tbf_etsprio.sh
diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh
new file mode 100644
index 0000000..8bd85da
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh
@@ -0,0 +1,39 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+ ping_ipv4
+ tbf_test
+"
+source $lib_dir/sch_tbf_core.sh
+
+tbf_test_one()
+{
+ local bs=$1; shift
+
+ tc qdisc replace dev $swp2 parent 10:3 handle 103: tbf \
+ rate 400Mbit burst $bs limit 1M
+ tc qdisc replace dev $swp2 parent 10:2 handle 102: tbf \
+ rate 800Mbit burst $bs limit 1M
+
+ do_tbf_test 10 400 $bs
+ do_tbf_test 11 800 $bs
+}
+
+tbf_test()
+{
+ # This test is used for both ETS and PRIO. Even though we only need two
+ # bands, PRIO demands a minimum of three.
+ tc qdisc add dev $swp2 root handle 10: $QDISC 3 priomap 2 1 0
+ tbf_test_one 128K
+ tc qdisc del dev $swp2 root
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh
new file mode 100755
index 0000000..9c8cb1c
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh
@@ -0,0 +1,6 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+QDISC="prio bands"
+: ${lib_dir:=.}
+source $lib_dir/sch_tbf_etsprio.sh
diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_root.sh b/tools/testing/selftests/net/forwarding/sch_tbf_root.sh
new file mode 100755
index 0000000..72aa21b
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/sch_tbf_root.sh
@@ -0,0 +1,33 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+ ping_ipv4
+ tbf_test
+"
+: ${lib_dir:=.}
+source $lib_dir/sch_tbf_core.sh
+
+tbf_test_one()
+{
+ local bs=$1; shift
+
+ tc qdisc replace dev $swp2 root handle 108: tbf \
+ rate 400Mbit burst $bs limit 1M
+ do_tbf_test 10 400 $bs
+}
+
+tbf_test()
+{
+ tbf_test_one 128K
+ tc qdisc del dev $swp2 root
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
new file mode 100644
index 0000000..d72f076
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -0,0 +1,2 @@
+mptcp_connect
+*.pcap
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
new file mode 100644
index 0000000..93de520
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+
+top_srcdir = ../../../../..
+
+CFLAGS = -Wall -Wl,--no-as-needed -O2 -g
+
+TEST_PROGS := mptcp_connect.sh
+
+TEST_GEN_FILES = mptcp_connect
+
+EXTRA_CLEAN := *.pcap
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
new file mode 100644
index 0000000..2499824
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/config
@@ -0,0 +1,4 @@
+CONFIG_MPTCP=y
+CONFIG_MPTCP_IPV6=y
+CONFIG_VETH=y
+CONFIG_NET_SCH_NETEM=m
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
new file mode 100644
index 0000000..a3dccd8
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -0,0 +1,832 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <string.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <strings.h>
+#include <unistd.h>
+
+#include <sys/poll.h>
+#include <sys/sendfile.h>
+#include <sys/stat.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+
+#include <netdb.h>
+#include <netinet/in.h>
+
+#include <linux/tcp.h>
+
+extern int optind;
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+#ifndef TCP_ULP
+#define TCP_ULP 31
+#endif
+
+static bool listen_mode;
+static int poll_timeout;
+
+enum cfg_mode {
+ CFG_MODE_POLL,
+ CFG_MODE_MMAP,
+ CFG_MODE_SENDFILE,
+};
+
+static enum cfg_mode cfg_mode = CFG_MODE_POLL;
+static const char *cfg_host;
+static const char *cfg_port = "12000";
+static int cfg_sock_proto = IPPROTO_MPTCP;
+static bool tcpulp_audit;
+static int pf = AF_INET;
+static int cfg_sndbuf;
+
+static void die_usage(void)
+{
+ fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] -m mode]"
+ "[ -l ] [ -t timeout ] connect_address\n");
+ exit(1);
+}
+
+static const char *getxinfo_strerr(int err)
+{
+ if (err == EAI_SYSTEM)
+ return strerror(errno);
+
+ return gai_strerror(err);
+}
+
+static void xgetnameinfo(const struct sockaddr *addr, socklen_t addrlen,
+ char *host, socklen_t hostlen,
+ char *serv, socklen_t servlen)
+{
+ int flags = NI_NUMERICHOST | NI_NUMERICSERV;
+ int err = getnameinfo(addr, addrlen, host, hostlen, serv, servlen,
+ flags);
+
+ if (err) {
+ const char *errstr = getxinfo_strerr(err);
+
+ fprintf(stderr, "Fatal: getnameinfo: %s\n", errstr);
+ exit(1);
+ }
+}
+
+static void xgetaddrinfo(const char *node, const char *service,
+ const struct addrinfo *hints,
+ struct addrinfo **res)
+{
+ int err = getaddrinfo(node, service, hints, res);
+
+ if (err) {
+ const char *errstr = getxinfo_strerr(err);
+
+ fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
+ node ? node : "", service ? service : "", errstr);
+ exit(1);
+ }
+}
+
+static void set_sndbuf(int fd, unsigned int size)
+{
+ int err;
+
+ err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &size, sizeof(size));
+ if (err) {
+ perror("set SO_SNDBUF");
+ exit(1);
+ }
+}
+
+static int sock_listen_mptcp(const char * const listenaddr,
+ const char * const port)
+{
+ int sock;
+ struct addrinfo hints = {
+ .ai_protocol = IPPROTO_TCP,
+ .ai_socktype = SOCK_STREAM,
+ .ai_flags = AI_PASSIVE | AI_NUMERICHOST
+ };
+
+ hints.ai_family = pf;
+
+ struct addrinfo *a, *addr;
+ int one = 1;
+
+ xgetaddrinfo(listenaddr, port, &hints, &addr);
+ hints.ai_family = pf;
+
+ for (a = addr; a; a = a->ai_next) {
+ sock = socket(a->ai_family, a->ai_socktype, cfg_sock_proto);
+ if (sock < 0)
+ continue;
+
+ if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one,
+ sizeof(one)))
+ perror("setsockopt");
+
+ if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
+ break; /* success */
+
+ perror("bind");
+ close(sock);
+ sock = -1;
+ }
+
+ freeaddrinfo(addr);
+
+ if (sock < 0) {
+ fprintf(stderr, "Could not create listen socket\n");
+ return sock;
+ }
+
+ if (listen(sock, 20)) {
+ perror("listen");
+ close(sock);
+ return -1;
+ }
+
+ return sock;
+}
+
+static bool sock_test_tcpulp(const char * const remoteaddr,
+ const char * const port)
+{
+ struct addrinfo hints = {
+ .ai_protocol = IPPROTO_TCP,
+ .ai_socktype = SOCK_STREAM,
+ };
+ struct addrinfo *a, *addr;
+ int sock = -1, ret = 0;
+ bool test_pass = false;
+
+ hints.ai_family = AF_INET;
+
+ xgetaddrinfo(remoteaddr, port, &hints, &addr);
+ for (a = addr; a; a = a->ai_next) {
+ sock = socket(a->ai_family, a->ai_socktype, IPPROTO_TCP);
+ if (sock < 0) {
+ perror("socket");
+ continue;
+ }
+ ret = setsockopt(sock, IPPROTO_TCP, TCP_ULP, "mptcp",
+ sizeof("mptcp"));
+ if (ret == -1 && errno == EOPNOTSUPP)
+ test_pass = true;
+ close(sock);
+
+ if (test_pass)
+ break;
+ if (!ret)
+ fprintf(stderr,
+ "setsockopt(TCP_ULP) returned 0\n");
+ else
+ perror("setsockopt(TCP_ULP)");
+ }
+ return test_pass;
+}
+
+static int sock_connect_mptcp(const char * const remoteaddr,
+ const char * const port, int proto)
+{
+ struct addrinfo hints = {
+ .ai_protocol = IPPROTO_TCP,
+ .ai_socktype = SOCK_STREAM,
+ };
+ struct addrinfo *a, *addr;
+ int sock = -1;
+
+ hints.ai_family = pf;
+
+ xgetaddrinfo(remoteaddr, port, &hints, &addr);
+ for (a = addr; a; a = a->ai_next) {
+ sock = socket(a->ai_family, a->ai_socktype, proto);
+ if (sock < 0) {
+ perror("socket");
+ continue;
+ }
+
+ if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
+ break; /* success */
+
+ perror("connect()");
+ close(sock);
+ sock = -1;
+ }
+
+ freeaddrinfo(addr);
+ return sock;
+}
+
+static size_t do_rnd_write(const int fd, char *buf, const size_t len)
+{
+ unsigned int do_w;
+ ssize_t bw;
+
+ do_w = rand() & 0xffff;
+ if (do_w == 0 || do_w > len)
+ do_w = len;
+
+ bw = write(fd, buf, do_w);
+ if (bw < 0)
+ perror("write");
+
+ return bw;
+}
+
+static size_t do_write(const int fd, char *buf, const size_t len)
+{
+ size_t offset = 0;
+
+ while (offset < len) {
+ size_t written;
+ ssize_t bw;
+
+ bw = write(fd, buf + offset, len - offset);
+ if (bw < 0) {
+ perror("write");
+ return 0;
+ }
+
+ written = (size_t)bw;
+ offset += written;
+ }
+
+ return offset;
+}
+
+static ssize_t do_rnd_read(const int fd, char *buf, const size_t len)
+{
+ size_t cap = rand();
+
+ cap &= 0xffff;
+
+ if (cap == 0)
+ cap = 1;
+ else if (cap > len)
+ cap = len;
+
+ return read(fd, buf, cap);
+}
+
+static void set_nonblock(int fd)
+{
+ int flags = fcntl(fd, F_GETFL);
+
+ if (flags == -1)
+ return;
+
+ fcntl(fd, F_SETFL, flags | O_NONBLOCK);
+}
+
+static int copyfd_io_poll(int infd, int peerfd, int outfd)
+{
+ struct pollfd fds = {
+ .fd = peerfd,
+ .events = POLLIN | POLLOUT,
+ };
+ unsigned int woff = 0, wlen = 0;
+ char wbuf[8192];
+
+ set_nonblock(peerfd);
+
+ for (;;) {
+ char rbuf[8192];
+ ssize_t len;
+
+ if (fds.events == 0)
+ break;
+
+ switch (poll(&fds, 1, poll_timeout)) {
+ case -1:
+ if (errno == EINTR)
+ continue;
+ perror("poll");
+ return 1;
+ case 0:
+ fprintf(stderr, "%s: poll timed out (events: "
+ "POLLIN %u, POLLOUT %u)\n", __func__,
+ fds.events & POLLIN, fds.events & POLLOUT);
+ return 2;
+ }
+
+ if (fds.revents & POLLIN) {
+ len = do_rnd_read(peerfd, rbuf, sizeof(rbuf));
+ if (len == 0) {
+ /* no more data to receive:
+ * peer has closed its write side
+ */
+ fds.events &= ~POLLIN;
+
+ if ((fds.events & POLLOUT) == 0)
+ /* and nothing more to send */
+ break;
+
+ /* Else, still have data to transmit */
+ } else if (len < 0) {
+ perror("read");
+ return 3;
+ }
+
+ do_write(outfd, rbuf, len);
+ }
+
+ if (fds.revents & POLLOUT) {
+ if (wlen == 0) {
+ woff = 0;
+ wlen = read(infd, wbuf, sizeof(wbuf));
+ }
+
+ if (wlen > 0) {
+ ssize_t bw;
+
+ bw = do_rnd_write(peerfd, wbuf + woff, wlen);
+ if (bw < 0)
+ return 111;
+
+ woff += bw;
+ wlen -= bw;
+ } else if (wlen == 0) {
+ /* We have no more data to send. */
+ fds.events &= ~POLLOUT;
+
+ if ((fds.events & POLLIN) == 0)
+ /* ... and peer also closed already */
+ break;
+
+ /* ... but we still receive.
+ * Close our write side.
+ */
+ shutdown(peerfd, SHUT_WR);
+ } else {
+ if (errno == EINTR)
+ continue;
+ perror("read");
+ return 4;
+ }
+ }
+
+ if (fds.revents & (POLLERR | POLLNVAL)) {
+ fprintf(stderr, "Unexpected revents: "
+ "POLLERR/POLLNVAL(%x)\n", fds.revents);
+ return 5;
+ }
+ }
+
+ close(peerfd);
+ return 0;
+}
+
+static int do_recvfile(int infd, int outfd)
+{
+ ssize_t r;
+
+ do {
+ char buf[16384];
+
+ r = do_rnd_read(infd, buf, sizeof(buf));
+ if (r > 0) {
+ if (write(outfd, buf, r) != r)
+ break;
+ } else if (r < 0) {
+ perror("read");
+ }
+ } while (r > 0);
+
+ return (int)r;
+}
+
+static int do_mmap(int infd, int outfd, unsigned int size)
+{
+ char *inbuf = mmap(NULL, size, PROT_READ, MAP_SHARED, infd, 0);
+ ssize_t ret = 0, off = 0;
+ size_t rem;
+
+ if (inbuf == MAP_FAILED) {
+ perror("mmap");
+ return 1;
+ }
+
+ rem = size;
+
+ while (rem > 0) {
+ ret = write(outfd, inbuf + off, rem);
+
+ if (ret < 0) {
+ perror("write");
+ break;
+ }
+
+ off += ret;
+ rem -= ret;
+ }
+
+ munmap(inbuf, size);
+ return rem;
+}
+
+static int get_infd_size(int fd)
+{
+ struct stat sb;
+ ssize_t count;
+ int err;
+
+ err = fstat(fd, &sb);
+ if (err < 0) {
+ perror("fstat");
+ return -1;
+ }
+
+ if ((sb.st_mode & S_IFMT) != S_IFREG) {
+ fprintf(stderr, "%s: stdin is not a regular file\n", __func__);
+ return -2;
+ }
+
+ count = sb.st_size;
+ if (count > INT_MAX) {
+ fprintf(stderr, "File too large: %zu\n", count);
+ return -3;
+ }
+
+ return (int)count;
+}
+
+static int do_sendfile(int infd, int outfd, unsigned int count)
+{
+ while (count > 0) {
+ ssize_t r;
+
+ r = sendfile(outfd, infd, NULL, count);
+ if (r < 0) {
+ perror("sendfile");
+ return 3;
+ }
+
+ count -= r;
+ }
+
+ return 0;
+}
+
+static int copyfd_io_mmap(int infd, int peerfd, int outfd,
+ unsigned int size)
+{
+ int err;
+
+ if (listen_mode) {
+ err = do_recvfile(peerfd, outfd);
+ if (err)
+ return err;
+
+ err = do_mmap(infd, peerfd, size);
+ } else {
+ err = do_mmap(infd, peerfd, size);
+ if (err)
+ return err;
+
+ shutdown(peerfd, SHUT_WR);
+
+ err = do_recvfile(peerfd, outfd);
+ }
+
+ return err;
+}
+
+static int copyfd_io_sendfile(int infd, int peerfd, int outfd,
+ unsigned int size)
+{
+ int err;
+
+ if (listen_mode) {
+ err = do_recvfile(peerfd, outfd);
+ if (err)
+ return err;
+
+ err = do_sendfile(infd, peerfd, size);
+ } else {
+ err = do_sendfile(infd, peerfd, size);
+ if (err)
+ return err;
+ err = do_recvfile(peerfd, outfd);
+ }
+
+ return err;
+}
+
+static int copyfd_io(int infd, int peerfd, int outfd)
+{
+ int file_size;
+
+ switch (cfg_mode) {
+ case CFG_MODE_POLL:
+ return copyfd_io_poll(infd, peerfd, outfd);
+ case CFG_MODE_MMAP:
+ file_size = get_infd_size(infd);
+ if (file_size < 0)
+ return file_size;
+ return copyfd_io_mmap(infd, peerfd, outfd, file_size);
+ case CFG_MODE_SENDFILE:
+ file_size = get_infd_size(infd);
+ if (file_size < 0)
+ return file_size;
+ return copyfd_io_sendfile(infd, peerfd, outfd, file_size);
+ }
+
+ fprintf(stderr, "Invalid mode %d\n", cfg_mode);
+
+ die_usage();
+ return 1;
+}
+
+static void check_sockaddr(int pf, struct sockaddr_storage *ss,
+ socklen_t salen)
+{
+ struct sockaddr_in6 *sin6;
+ struct sockaddr_in *sin;
+ socklen_t wanted_size = 0;
+
+ switch (pf) {
+ case AF_INET:
+ wanted_size = sizeof(*sin);
+ sin = (void *)ss;
+ if (!sin->sin_port)
+ fprintf(stderr, "accept: something wrong: ip connection from port 0");
+ break;
+ case AF_INET6:
+ wanted_size = sizeof(*sin6);
+ sin6 = (void *)ss;
+ if (!sin6->sin6_port)
+ fprintf(stderr, "accept: something wrong: ipv6 connection from port 0");
+ break;
+ default:
+ fprintf(stderr, "accept: Unknown pf %d, salen %u\n", pf, salen);
+ return;
+ }
+
+ if (salen != wanted_size)
+ fprintf(stderr, "accept: size mismatch, got %d expected %d\n",
+ (int)salen, wanted_size);
+
+ if (ss->ss_family != pf)
+ fprintf(stderr, "accept: pf mismatch, expect %d, ss_family is %d\n",
+ (int)ss->ss_family, pf);
+}
+
+static void check_getpeername(int fd, struct sockaddr_storage *ss, socklen_t salen)
+{
+ struct sockaddr_storage peerss;
+ socklen_t peersalen = sizeof(peerss);
+
+ if (getpeername(fd, (struct sockaddr *)&peerss, &peersalen) < 0) {
+ perror("getpeername");
+ return;
+ }
+
+ if (peersalen != salen) {
+ fprintf(stderr, "%s: %d vs %d\n", __func__, peersalen, salen);
+ return;
+ }
+
+ if (memcmp(ss, &peerss, peersalen)) {
+ char a[INET6_ADDRSTRLEN];
+ char b[INET6_ADDRSTRLEN];
+ char c[INET6_ADDRSTRLEN];
+ char d[INET6_ADDRSTRLEN];
+
+ xgetnameinfo((struct sockaddr *)ss, salen,
+ a, sizeof(a), b, sizeof(b));
+
+ xgetnameinfo((struct sockaddr *)&peerss, peersalen,
+ c, sizeof(c), d, sizeof(d));
+
+ fprintf(stderr, "%s: memcmp failure: accept %s vs peername %s, %s vs %s salen %d vs %d\n",
+ __func__, a, c, b, d, peersalen, salen);
+ }
+}
+
+static void check_getpeername_connect(int fd)
+{
+ struct sockaddr_storage ss;
+ socklen_t salen = sizeof(ss);
+ char a[INET6_ADDRSTRLEN];
+ char b[INET6_ADDRSTRLEN];
+
+ if (getpeername(fd, (struct sockaddr *)&ss, &salen) < 0) {
+ perror("getpeername");
+ return;
+ }
+
+ xgetnameinfo((struct sockaddr *)&ss, salen,
+ a, sizeof(a), b, sizeof(b));
+
+ if (strcmp(cfg_host, a) || strcmp(cfg_port, b))
+ fprintf(stderr, "%s: %s vs %s, %s vs %s\n", __func__,
+ cfg_host, a, cfg_port, b);
+}
+
+int main_loop_s(int listensock)
+{
+ struct sockaddr_storage ss;
+ struct pollfd polls;
+ socklen_t salen;
+ int remotesock;
+
+ polls.fd = listensock;
+ polls.events = POLLIN;
+
+ switch (poll(&polls, 1, poll_timeout)) {
+ case -1:
+ perror("poll");
+ return 1;
+ case 0:
+ fprintf(stderr, "%s: timed out\n", __func__);
+ close(listensock);
+ return 2;
+ }
+
+ salen = sizeof(ss);
+ remotesock = accept(listensock, (struct sockaddr *)&ss, &salen);
+ if (remotesock >= 0) {
+ check_sockaddr(pf, &ss, salen);
+ check_getpeername(remotesock, &ss, salen);
+
+ return copyfd_io(0, remotesock, 1);
+ }
+
+ perror("accept");
+
+ return 1;
+}
+
+static void init_rng(void)
+{
+ int fd = open("/dev/urandom", O_RDONLY);
+ unsigned int foo;
+
+ if (fd > 0) {
+ int ret = read(fd, &foo, sizeof(foo));
+
+ if (ret < 0)
+ srand(fd + foo);
+ close(fd);
+ }
+
+ srand(foo);
+}
+
+int main_loop(void)
+{
+ int fd;
+
+ /* listener is ready. */
+ fd = sock_connect_mptcp(cfg_host, cfg_port, cfg_sock_proto);
+ if (fd < 0)
+ return 2;
+
+ check_getpeername_connect(fd);
+
+ if (cfg_sndbuf)
+ set_sndbuf(fd, cfg_sndbuf);
+
+ return copyfd_io(0, fd, 1);
+}
+
+int parse_proto(const char *proto)
+{
+ if (!strcasecmp(proto, "MPTCP"))
+ return IPPROTO_MPTCP;
+ if (!strcasecmp(proto, "TCP"))
+ return IPPROTO_TCP;
+
+ fprintf(stderr, "Unknown protocol: %s\n.", proto);
+ die_usage();
+
+ /* silence compiler warning */
+ return 0;
+}
+
+int parse_mode(const char *mode)
+{
+ if (!strcasecmp(mode, "poll"))
+ return CFG_MODE_POLL;
+ if (!strcasecmp(mode, "mmap"))
+ return CFG_MODE_MMAP;
+ if (!strcasecmp(mode, "sendfile"))
+ return CFG_MODE_SENDFILE;
+
+ fprintf(stderr, "Unknown test mode: %s\n", mode);
+ fprintf(stderr, "Supported modes are:\n");
+ fprintf(stderr, "\t\t\"poll\" - interleaved read/write using poll()\n");
+ fprintf(stderr, "\t\t\"mmap\" - send entire input file (mmap+write), then read response (-l will read input first)\n");
+ fprintf(stderr, "\t\t\"sendfile\" - send entire input file (sendfile), then read response (-l will read input first)\n");
+
+ die_usage();
+
+ /* silence compiler warning */
+ return 0;
+}
+
+int parse_sndbuf(const char *size)
+{
+ unsigned long s;
+
+ errno = 0;
+
+ s = strtoul(size, NULL, 0);
+
+ if (errno) {
+ fprintf(stderr, "Invalid sndbuf size %s (%s)\n",
+ size, strerror(errno));
+ die_usage();
+ }
+
+ if (s > INT_MAX) {
+ fprintf(stderr, "Invalid sndbuf size %s (%s)\n",
+ size, strerror(ERANGE));
+ die_usage();
+ }
+
+ cfg_sndbuf = s;
+
+ return 0;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "6lp:s:hut:m:b:")) != -1) {
+ switch (c) {
+ case 'l':
+ listen_mode = true;
+ break;
+ case 'p':
+ cfg_port = optarg;
+ break;
+ case 's':
+ cfg_sock_proto = parse_proto(optarg);
+ break;
+ case 'h':
+ die_usage();
+ break;
+ case 'u':
+ tcpulp_audit = true;
+ break;
+ case '6':
+ pf = AF_INET6;
+ break;
+ case 't':
+ poll_timeout = atoi(optarg) * 1000;
+ if (poll_timeout <= 0)
+ poll_timeout = -1;
+ break;
+ case 'm':
+ cfg_mode = parse_mode(optarg);
+ break;
+ case 'b':
+ cfg_sndbuf = parse_sndbuf(optarg);
+ break;
+ }
+ }
+
+ if (optind + 1 != argc)
+ die_usage();
+ cfg_host = argv[optind];
+
+ if (strchr(cfg_host, ':'))
+ pf = AF_INET6;
+}
+
+int main(int argc, char *argv[])
+{
+ init_rng();
+
+ parse_opts(argc, argv);
+
+ if (tcpulp_audit)
+ return sock_test_tcpulp(cfg_host, cfg_port) ? 0 : 1;
+
+ if (listen_mode) {
+ int fd = sock_listen_mptcp(cfg_host, cfg_port);
+
+ if (fd < 0)
+ return 1;
+
+ if (cfg_sndbuf)
+ set_sndbuf(fd, cfg_sndbuf);
+
+ return main_loop_s(fd);
+ }
+
+ return main_loop();
+}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
new file mode 100755
index 0000000..d573a0f
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -0,0 +1,595 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+time_start=$(date +%s)
+
+optstring="b:d:e:l:r:h4cm:"
+ret=0
+sin=""
+sout=""
+cin=""
+cout=""
+ksft_skip=4
+capture=false
+timeout=30
+ipv6=true
+ethtool_random_on=true
+tc_delay="$((RANDOM%400))"
+tc_loss=$((RANDOM%101))
+tc_reorder=""
+testmode=""
+sndbuf=0
+options_log=true
+
+if [ $tc_loss -eq 100 ];then
+ tc_loss=1%
+elif [ $tc_loss -ge 10 ]; then
+ tc_loss=0.$tc_loss%
+elif [ $tc_loss -ge 1 ]; then
+ tc_loss=0.0$tc_loss%
+else
+ tc_loss=""
+fi
+
+usage() {
+ echo "Usage: $0 [ -a ]"
+ echo -e "\t-d: tc/netem delay in milliseconds, e.g. \"-d 10\" (default random)"
+ echo -e "\t-l: tc/netem loss percentage, e.g. \"-l 0.02\" (default random)"
+ echo -e "\t-r: tc/netem reorder mode, e.g. \"-r 25% 50% gap 5\", use "-r 0" to disable reordering (default random)"
+ echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)"
+ echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)"
+ echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
+ echo -e "\t-b: set sndbuf value (default: use kernel default)"
+ echo -e "\t-m: test mode (poll, sendfile; default: poll)"
+}
+
+while getopts "$optstring" option;do
+ case "$option" in
+ "h")
+ usage $0
+ exit 0
+ ;;
+ "d")
+ if [ $OPTARG -ge 0 ];then
+ tc_delay="$OPTARG"
+ else
+ echo "-d requires numeric argument, got \"$OPTARG\"" 1>&2
+ exit 1
+ fi
+ ;;
+ "e")
+ ethtool_args="$ethtool_args $OPTARG off"
+ ethtool_random_on=false
+ ;;
+ "l")
+ tc_loss="$OPTARG"
+ ;;
+ "r")
+ tc_reorder="$OPTARG"
+ ;;
+ "4")
+ ipv6=false
+ ;;
+ "c")
+ capture=true
+ ;;
+ "b")
+ if [ $OPTARG -ge 0 ];then
+ sndbuf="$OPTARG"
+ else
+ echo "-s requires numeric argument, got \"$OPTARG\"" 1>&2
+ exit 1
+ fi
+ ;;
+ "m")
+ testmode="$OPTARG"
+ ;;
+ "?")
+ usage $0
+ exit 1
+ ;;
+ esac
+done
+
+sec=$(date +%s)
+rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+ns1="ns1-$rndh"
+ns2="ns2-$rndh"
+ns3="ns3-$rndh"
+ns4="ns4-$rndh"
+
+TEST_COUNT=0
+
+cleanup()
+{
+ rm -f "$cin" "$cout"
+ rm -f "$sin" "$sout"
+ rm -f "$capout"
+
+ local netns
+ for netns in "$ns1" "$ns2" "$ns3" "$ns4";do
+ ip netns del $netns
+ done
+}
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+sin=$(mktemp)
+sout=$(mktemp)
+cin=$(mktemp)
+cout=$(mktemp)
+capout=$(mktemp)
+trap cleanup EXIT
+
+for i in "$ns1" "$ns2" "$ns3" "$ns4";do
+ ip netns add $i || exit $ksft_skip
+ ip -net $i link set lo up
+done
+
+# "$ns1" ns2 ns3 ns4
+# ns1eth2 ns2eth1 ns2eth3 ns3eth2 ns3eth4 ns4eth3
+# - drop 1% -> reorder 25%
+# <- TSO off -
+
+ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth1 netns "$ns2"
+ip link add ns2eth3 netns "$ns2" type veth peer name ns3eth2 netns "$ns3"
+ip link add ns3eth4 netns "$ns3" type veth peer name ns4eth3 netns "$ns4"
+
+ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth2
+ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth2 nodad
+
+ip -net "$ns1" link set ns1eth2 up
+ip -net "$ns1" route add default via 10.0.1.2
+ip -net "$ns1" route add default via dead:beef:1::2
+
+ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1
+ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad
+ip -net "$ns2" link set ns2eth1 up
+
+ip -net "$ns2" addr add 10.0.2.1/24 dev ns2eth3
+ip -net "$ns2" addr add dead:beef:2::1/64 dev ns2eth3 nodad
+ip -net "$ns2" link set ns2eth3 up
+ip -net "$ns2" route add default via 10.0.2.2
+ip -net "$ns2" route add default via dead:beef:2::2
+ip netns exec "$ns2" sysctl -q net.ipv4.ip_forward=1
+ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.forwarding=1
+
+ip -net "$ns3" addr add 10.0.2.2/24 dev ns3eth2
+ip -net "$ns3" addr add dead:beef:2::2/64 dev ns3eth2 nodad
+ip -net "$ns3" link set ns3eth2 up
+
+ip -net "$ns3" addr add 10.0.3.2/24 dev ns3eth4
+ip -net "$ns3" addr add dead:beef:3::2/64 dev ns3eth4 nodad
+ip -net "$ns3" link set ns3eth4 up
+ip -net "$ns3" route add default via 10.0.2.1
+ip -net "$ns3" route add default via dead:beef:2::1
+ip netns exec "$ns3" sysctl -q net.ipv4.ip_forward=1
+ip netns exec "$ns3" sysctl -q net.ipv6.conf.all.forwarding=1
+
+ip -net "$ns4" addr add 10.0.3.1/24 dev ns4eth3
+ip -net "$ns4" addr add dead:beef:3::1/64 dev ns4eth3 nodad
+ip -net "$ns4" link set ns4eth3 up
+ip -net "$ns4" route add default via 10.0.3.2
+ip -net "$ns4" route add default via dead:beef:3::2
+
+set_ethtool_flags() {
+ local ns="$1"
+ local dev="$2"
+ local flags="$3"
+
+ ip netns exec $ns ethtool -K $dev $flags 2>/dev/null
+ [ $? -eq 0 ] && echo "INFO: set $ns dev $dev: ethtool -K $flags"
+}
+
+set_random_ethtool_flags() {
+ local flags=""
+ local r=$RANDOM
+
+ local pick1=$((r & 1))
+ local pick2=$((r & 2))
+ local pick3=$((r & 4))
+
+ [ $pick1 -ne 0 ] && flags="tso off"
+ [ $pick2 -ne 0 ] && flags="$flags gso off"
+ [ $pick3 -ne 0 ] && flags="$flags gro off"
+
+ [ -z "$flags" ] && return
+
+ set_ethtool_flags "$1" "$2" "$flags"
+}
+
+if $ethtool_random_on;then
+ set_random_ethtool_flags "$ns3" ns3eth2
+ set_random_ethtool_flags "$ns4" ns4eth3
+else
+ set_ethtool_flags "$ns3" ns3eth2 "$ethtool_args"
+ set_ethtool_flags "$ns4" ns4eth3 "$ethtool_args"
+fi
+
+print_file_err()
+{
+ ls -l "$1" 1>&2
+ echo "Trailing bytes are: "
+ tail -c 27 "$1"
+}
+
+check_transfer()
+{
+ local in=$1
+ local out=$2
+ local what=$3
+
+ cmp "$in" "$out" > /dev/null 2>&1
+ if [ $? -ne 0 ] ;then
+ echo "[ FAIL ] $what does not match (in, out):"
+ print_file_err "$in"
+ print_file_err "$out"
+
+ return 1
+ fi
+
+ return 0
+}
+
+check_mptcp_disabled()
+{
+ local disabled_ns
+ disabled_ns="ns_disabled-$sech-$(mktemp -u XXXXXX)"
+ ip netns add ${disabled_ns} || exit $ksft_skip
+
+ # net.mptcp.enabled should be enabled by default
+ if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then
+ echo -e "net.mptcp.enabled sysctl is not 1 by default\t\t[ FAIL ]"
+ ret=1
+ return 1
+ fi
+ ip netns exec ${disabled_ns} sysctl -q net.mptcp.enabled=0
+
+ local err=0
+ LANG=C ip netns exec ${disabled_ns} ./mptcp_connect -t $timeout -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \
+ grep -q "^socket: Protocol not available$" && err=1
+ ip netns delete ${disabled_ns}
+
+ if [ ${err} -eq 0 ]; then
+ echo -e "New MPTCP socket cannot be blocked via sysctl\t\t[ FAIL ]"
+ ret=1
+ return 1
+ fi
+
+ echo -e "New MPTCP socket can be blocked via sysctl\t\t[ OK ]"
+ return 0
+}
+
+check_mptcp_ulp_setsockopt()
+{
+ local t retval
+ t="ns_ulp-$sech-$(mktemp -u XXXXXX)"
+
+ ip netns add ${t} || exit $ksft_skip
+ if ! ip netns exec ${t} ./mptcp_connect -u -p 10000 -s TCP 127.0.0.1 2>&1; then
+ printf "setsockopt(..., TCP_ULP, \"mptcp\", ...) allowed\t[ FAIL ]\n"
+ retval=1
+ ret=$retval
+ else
+ printf "setsockopt(..., TCP_ULP, \"mptcp\", ...) blocked\t[ OK ]\n"
+ retval=0
+ fi
+ ip netns del ${t}
+ return $retval
+}
+
+# $1: IP address
+is_v6()
+{
+ [ -z "${1##*:*}" ]
+}
+
+do_ping()
+{
+ local listener_ns="$1"
+ local connector_ns="$2"
+ local connect_addr="$3"
+ local ping_args="-q -c 1"
+
+ if is_v6 "${connect_addr}"; then
+ $ipv6 || return 0
+ ping_args="${ping_args} -6"
+ fi
+
+ ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null
+ if [ $? -ne 0 ] ; then
+ echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2
+ ret=1
+
+ return 1
+ fi
+
+ return 0
+}
+
+# $1: ns, $2: port
+wait_local_port_listen()
+{
+ local listener_ns="${1}"
+ local port="${2}"
+
+ local port_hex i
+
+ port_hex="$(printf "%04X" "${port}")"
+ for i in $(seq 10); do
+ ip netns exec "${listener_ns}" cat /proc/net/tcp* | \
+ awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
+ break
+ sleep 0.1
+ done
+}
+
+do_transfer()
+{
+ local listener_ns="$1"
+ local connector_ns="$2"
+ local cl_proto="$3"
+ local srv_proto="$4"
+ local connect_addr="$5"
+ local local_addr="$6"
+ local extra_args=""
+
+ local port
+ port=$((10000+$TEST_COUNT))
+ TEST_COUNT=$((TEST_COUNT+1))
+
+ if [ "$sndbuf" -gt 0 ]; then
+ extra_args="$extra_args -b $sndbuf"
+ fi
+
+ if [ -n "$testmode" ]; then
+ extra_args="$extra_args -m $testmode"
+ fi
+
+ if [ -n "$extra_args" ] && $options_log; then
+ options_log=false
+ echo "INFO: extra options: $extra_args"
+ fi
+
+ :> "$cout"
+ :> "$sout"
+ :> "$capout"
+
+ local addr_port
+ addr_port=$(printf "%s:%d" ${connect_addr} ${port})
+ printf "%.3s %-5s -> %.3s (%-20s) %-5s\t" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto}
+
+ if $capture; then
+ local capuser
+ if [ -z $SUDO_USER ] ; then
+ capuser=""
+ else
+ capuser="-Z $SUDO_USER"
+ fi
+
+ local capfile="${listener_ns}-${connector_ns}-${cl_proto}-${srv_proto}-${connect_addr}.pcap"
+
+ ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 &
+ local cappid=$!
+
+ sleep 1
+ fi
+
+ ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" &
+ local spid=$!
+
+ wait_local_port_listen "${listener_ns}" "${port}"
+
+ local start
+ start=$(date +%s%3N)
+ ip netns exec ${connector_ns} ./mptcp_connect -t $timeout -p $port -s ${cl_proto} $extra_args $connect_addr < "$cin" > "$cout" &
+ local cpid=$!
+
+ wait $cpid
+ local retc=$?
+ wait $spid
+ local rets=$?
+
+ local stop
+ stop=$(date +%s%3N)
+
+ if $capture; then
+ sleep 1
+ kill $cappid
+ fi
+
+ local duration
+ duration=$((stop-start))
+ duration=$(printf "(duration %05sms)" $duration)
+ if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+ echo "$duration [ FAIL ] client exit code $retc, server $rets" 1>&2
+ echo "\nnetns ${listener_ns} socket stat for $port:" 1>&2
+ ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port"
+ echo "\nnetns ${connector_ns} socket stat for $port:" 1>&2
+ ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port"
+
+ cat "$capout"
+ return 1
+ fi
+
+ check_transfer $sin $cout "file received by client"
+ retc=$?
+ check_transfer $cin $sout "file received by server"
+ rets=$?
+
+ if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
+ echo "$duration [ OK ]"
+ cat "$capout"
+ return 0
+ fi
+
+ cat "$capout"
+ return 1
+}
+
+make_file()
+{
+ local name=$1
+ local who=$2
+
+ local SIZE TSIZE
+ SIZE=$((RANDOM % (1024 * 8)))
+ TSIZE=$((SIZE * 1024))
+
+ dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null
+
+ SIZE=$((RANDOM % 1024))
+ SIZE=$((SIZE + 128))
+ TSIZE=$((TSIZE + SIZE))
+ dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null
+ echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
+
+ echo "Created $name (size $TSIZE) containing data sent by $who"
+}
+
+run_tests_lo()
+{
+ local listener_ns="$1"
+ local connector_ns="$2"
+ local connect_addr="$3"
+ local loopback="$4"
+ local lret=0
+
+ # skip if test programs are running inside same netns for subsequent runs.
+ if [ $loopback -eq 0 ] && [ ${listener_ns} = ${connector_ns} ]; then
+ return 0
+ fi
+
+ # skip if we don't want v6
+ if ! $ipv6 && is_v6 "${connect_addr}"; then
+ return 0
+ fi
+
+ local local_addr
+ if is_v6 "${connect_addr}"; then
+ local_addr="::"
+ else
+ local_addr="0.0.0.0"
+ fi
+
+ do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${local_addr}
+ lret=$?
+ if [ $lret -ne 0 ]; then
+ ret=$lret
+ return 1
+ fi
+
+ # don't bother testing fallback tcp except for loopback case.
+ if [ ${listener_ns} != ${connector_ns} ]; then
+ return 0
+ fi
+
+ do_transfer ${listener_ns} ${connector_ns} MPTCP TCP ${connect_addr} ${local_addr}
+ lret=$?
+ if [ $lret -ne 0 ]; then
+ ret=$lret
+ return 1
+ fi
+
+ do_transfer ${listener_ns} ${connector_ns} TCP MPTCP ${connect_addr} ${local_addr}
+ lret=$?
+ if [ $lret -ne 0 ]; then
+ ret=$lret
+ return 1
+ fi
+
+ return 0
+}
+
+run_tests()
+{
+ run_tests_lo $1 $2 $3 0
+}
+
+make_file "$cin" "client"
+make_file "$sin" "server"
+
+check_mptcp_disabled
+
+check_mptcp_ulp_setsockopt
+
+echo "INFO: validating network environment with pings"
+for sender in "$ns1" "$ns2" "$ns3" "$ns4";do
+ do_ping "$ns1" $sender 10.0.1.1
+ do_ping "$ns1" $sender dead:beef:1::1
+
+ do_ping "$ns2" $sender 10.0.1.2
+ do_ping "$ns2" $sender dead:beef:1::2
+ do_ping "$ns2" $sender 10.0.2.1
+ do_ping "$ns2" $sender dead:beef:2::1
+
+ do_ping "$ns3" $sender 10.0.2.2
+ do_ping "$ns3" $sender dead:beef:2::2
+ do_ping "$ns3" $sender 10.0.3.2
+ do_ping "$ns3" $sender dead:beef:3::2
+
+ do_ping "$ns4" $sender 10.0.3.1
+ do_ping "$ns4" $sender dead:beef:3::1
+done
+
+[ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss
+echo -n "INFO: Using loss of $tc_loss "
+test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms "
+
+if [ -z "${tc_reorder}" ]; then
+ reorder1=$((RANDOM%10))
+ reorder1=$((100 - reorder1))
+ reorder2=$((RANDOM%100))
+
+ if [ $tc_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then
+ tc_reorder="reorder ${reorder1}% ${reorder2}%"
+ echo -n "$tc_reorder "
+ fi
+elif [ "$tc_reorder" = "0" ];then
+ tc_reorder=""
+elif [ "$tc_delay" -gt 0 ];then
+ # reordering requires some delay
+ tc_reorder="reorder $tc_reorder"
+ echo -n "$tc_reorder "
+fi
+
+echo "on ns3eth4"
+
+tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${tc_delay}ms $tc_reorder
+
+for sender in $ns1 $ns2 $ns3 $ns4;do
+ run_tests_lo "$ns1" "$sender" 10.0.1.1 1
+ if [ $ret -ne 0 ] ;then
+ echo "FAIL: Could not even run loopback test" 1>&2
+ exit $ret
+ fi
+ run_tests_lo "$ns1" $sender dead:beef:1::1 1
+ if [ $ret -ne 0 ] ;then
+ echo "FAIL: Could not even run loopback v6 test" 2>&1
+ exit $ret
+ fi
+
+ run_tests "$ns2" $sender 10.0.1.2
+ run_tests "$ns2" $sender dead:beef:1::2
+ run_tests "$ns2" $sender 10.0.2.1
+ run_tests "$ns2" $sender dead:beef:2::1
+
+ run_tests "$ns3" $sender 10.0.2.2
+ run_tests "$ns3" $sender dead:beef:2::2
+ run_tests "$ns3" $sender 10.0.3.2
+ run_tests "$ns3" $sender dead:beef:3::2
+
+ run_tests "$ns4" $sender 10.0.3.1
+ run_tests "$ns4" $sender dead:beef:3::1
+done
+
+time_end=$(date +%s)
+time_run=$((time_end-time_start))
+
+echo "Time: ${time_run} seconds"
+
+exit $ret
diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings
new file mode 100644
index 0000000..026384c
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/settings
@@ -0,0 +1 @@
+timeout=450
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index de1032b..08194aa 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -2,6 +2,7 @@
# Makefile for netfilter selftests
TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
- conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh
+ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
+ nft_concat_range.sh
include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
new file mode 100755
index 0000000..aca21dd
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -0,0 +1,1481 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# nft_concat_range.sh - Tests for sets with concatenation of ranged fields
+#
+# Copyright (c) 2019 Red Hat GmbH
+#
+# Author: Stefano Brivio <sbrivio@redhat.com>
+#
+# shellcheck disable=SC2154,SC2034,SC2016,SC2030,SC2031
+# ^ Configuration and templates sourced with eval, counters reused in subshells
+
+KSELFTEST_SKIP=4
+
+# Available test groups:
+# - correctness: check that packets match given entries, and only those
+# - concurrency: attempt races between insertion, deletion and lookup
+# - timeout: check that packets match entries until they expire
+# - performance: estimate matching rate, compare with rbtree and hash baselines
+TESTS="correctness concurrency timeout"
+[ "${quicktest}" != "1" ] && TESTS="${TESTS} performance"
+
+# Set types, defined by TYPE_ variables below
+TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
+ net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port
+ net_port_mac_proto_net"
+
+# List of possible paths to pktgen script from kernel tree for performance tests
+PKTGEN_SCRIPT_PATHS="
+ ../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
+ pktgen/pktgen_bench_xmit_mode_netif_receive.sh"
+
+# Definition of set types:
+# display display text for test report
+# type_spec nftables set type specifier
+# chain_spec nftables type specifier for rules mapping to set
+# dst call sequence of format_*() functions for destination fields
+# src call sequence of format_*() functions for source fields
+# start initial integer used to generate addresses and ports
+# count count of entries to generate and match
+# src_delta number summed to destination generator for source fields
+# tools list of tools for correctness and timeout tests, any can be used
+# proto L4 protocol of test packets
+#
+# race_repeat race attempts per thread, 0 disables concurrency test for type
+# flood_tools list of tools for concurrency tests, any can be used
+# flood_proto L4 protocol of test packets for concurrency tests
+# flood_spec nftables type specifier for concurrency tests
+#
+# perf_duration duration of single pktgen injection test
+# perf_spec nftables type specifier for performance tests
+# perf_dst format_*() functions for destination fields in performance test
+# perf_src format_*() functions for source fields in performance test
+# perf_entries number of set entries for performance test
+# perf_proto L3 protocol of test packets
+TYPE_net_port="
+display net,port
+type_spec ipv4_addr . inet_service
+chain_spec ip daddr . udp dport
+dst addr4 port
+src
+start 1
+count 5
+src_delta 2000
+tools sendip nc bash
+proto udp
+
+race_repeat 3
+flood_tools iperf3 iperf netperf
+flood_proto udp
+flood_spec ip daddr . udp dport
+
+perf_duration 5
+perf_spec ip daddr . udp dport
+perf_dst addr4 port
+perf_src
+perf_entries 1000
+perf_proto ipv4
+"
+
+TYPE_port_net="
+display port,net
+type_spec inet_service . ipv4_addr
+chain_spec udp dport . ip daddr
+dst port addr4
+src
+start 1
+count 5
+src_delta 2000
+tools sendip nc bash
+proto udp
+
+race_repeat 3
+flood_tools iperf3 iperf netperf
+flood_proto udp
+flood_spec udp dport . ip daddr
+
+perf_duration 5
+perf_spec udp dport . ip daddr
+perf_dst port addr4
+perf_src
+perf_entries 100
+perf_proto ipv4
+"
+
+TYPE_net6_port="
+display net6,port
+type_spec ipv6_addr . inet_service
+chain_spec ip6 daddr . udp dport
+dst addr6 port
+src
+start 10
+count 5
+src_delta 2000
+tools sendip nc bash
+proto udp6
+
+race_repeat 3
+flood_tools iperf3 iperf netperf
+flood_proto tcp6
+flood_spec ip6 daddr . udp dport
+
+perf_duration 5
+perf_spec ip6 daddr . udp dport
+perf_dst addr6 port
+perf_src
+perf_entries 1000
+perf_proto ipv6
+"
+
+TYPE_port_proto="
+display port,proto
+type_spec inet_service . inet_proto
+chain_spec udp dport . meta l4proto
+dst port proto
+src
+start 1
+count 5
+src_delta 2000
+tools sendip nc bash
+proto udp
+
+race_repeat 0
+
+perf_duration 5
+perf_spec udp dport . meta l4proto
+perf_dst port proto
+perf_src
+perf_entries 30000
+perf_proto ipv4
+"
+
+TYPE_net6_port_mac="
+display net6,port,mac
+type_spec ipv6_addr . inet_service . ether_addr
+chain_spec ip6 daddr . udp dport . ether saddr
+dst addr6 port
+src mac
+start 10
+count 5
+src_delta 2000
+tools sendip nc bash
+proto udp6
+
+race_repeat 0
+
+perf_duration 5
+perf_spec ip6 daddr . udp dport . ether daddr
+perf_dst addr6 port mac
+perf_src
+perf_entries 10
+perf_proto ipv6
+"
+
+TYPE_net6_port_mac_proto="
+display net6,port,mac,proto
+type_spec ipv6_addr . inet_service . ether_addr . inet_proto
+chain_spec ip6 daddr . udp dport . ether saddr . meta l4proto
+dst addr6 port
+src mac proto
+start 10
+count 5
+src_delta 2000
+tools sendip nc bash
+proto udp6
+
+race_repeat 0
+
+perf_duration 5
+perf_spec ip6 daddr . udp dport . ether daddr . meta l4proto
+perf_dst addr6 port mac proto
+perf_src
+perf_entries 1000
+perf_proto ipv6
+"
+
+TYPE_net_port_net="
+display net,port,net
+type_spec ipv4_addr . inet_service . ipv4_addr
+chain_spec ip daddr . udp dport . ip saddr
+dst addr4 port
+src addr4
+start 1
+count 5
+src_delta 2000
+tools sendip nc bash
+proto udp
+
+race_repeat 3
+flood_tools iperf3 iperf netperf
+flood_proto tcp
+flood_spec ip daddr . udp dport . ip saddr
+
+perf_duration 0
+"
+
+TYPE_net6_port_net6_port="
+display net6,port,net6,port
+type_spec ipv6_addr . inet_service . ipv6_addr . inet_service
+chain_spec ip6 daddr . udp dport . ip6 saddr . udp sport
+dst addr6 port
+src addr6 port
+start 10
+count 5
+src_delta 2000
+tools sendip nc
+proto udp6
+
+race_repeat 3
+flood_tools iperf3 iperf netperf
+flood_proto tcp6
+flood_spec ip6 daddr . tcp dport . ip6 saddr . tcp sport
+
+perf_duration 0
+"
+
+TYPE_net_port_mac_proto_net="
+display net,port,mac,proto,net
+type_spec ipv4_addr . inet_service . ether_addr . inet_proto . ipv4_addr
+chain_spec ip daddr . udp dport . ether saddr . meta l4proto . ip saddr
+dst addr4 port
+src mac proto addr4
+start 1
+count 5
+src_delta 2000
+tools sendip nc bash
+proto udp
+
+race_repeat 0
+
+perf_duration 0
+"
+
+TYPE_net_mac="
+display net,mac
+type_spec ipv4_addr . ether_addr
+chain_spec ip daddr . ether saddr
+dst addr4
+src mac
+start 1
+count 5
+src_delta 2000
+tools sendip nc bash
+proto udp
+
+race_repeat 0
+
+perf_duration 5
+perf_spec ip daddr . ether daddr
+perf_dst addr4 mac
+perf_src
+perf_entries 1000
+perf_proto ipv4
+"
+
+TYPE_net_mac_icmp="
+display net,mac - ICMP
+type_spec ipv4_addr . ether_addr
+chain_spec ip daddr . ether saddr
+dst addr4
+src mac
+start 1
+count 5
+src_delta 2000
+tools ping
+proto icmp
+
+race_repeat 0
+
+perf_duration 0
+"
+
+TYPE_net6_mac_icmp="
+display net6,mac - ICMPv6
+type_spec ipv6_addr . ether_addr
+chain_spec ip6 daddr . ether saddr
+dst addr6
+src mac
+start 10
+count 50
+src_delta 2000
+tools ping
+proto icmp6
+
+race_repeat 0
+
+perf_duration 0
+"
+
+TYPE_net_port_proto_net="
+display net,port,proto,net
+type_spec ipv4_addr . inet_service . inet_proto . ipv4_addr
+chain_spec ip daddr . udp dport . meta l4proto . ip saddr
+dst addr4 port proto
+src addr4
+start 1
+count 5
+src_delta 2000
+tools sendip nc
+proto udp
+
+race_repeat 3
+flood_tools iperf3 iperf netperf
+flood_proto tcp
+flood_spec ip daddr . tcp dport . meta l4proto . ip saddr
+
+perf_duration 0
+"
+
+# Set template for all tests, types and rules are filled in depending on test
+set_template='
+flush ruleset
+
+table inet filter {
+ counter test {
+ packets 0 bytes 0
+ }
+
+ set test {
+ type ${type_spec}
+ flags interval,timeout
+ }
+
+ chain input {
+ type filter hook prerouting priority 0; policy accept;
+ ${chain_spec} @test counter name \"test\"
+ }
+}
+
+table netdev perf {
+ counter test {
+ packets 0 bytes 0
+ }
+
+ counter match {
+ packets 0 bytes 0
+ }
+
+ set test {
+ type ${type_spec}
+ flags interval
+ }
+
+ set norange {
+ type ${type_spec}
+ }
+
+ set noconcat {
+ type ${type_spec%% *}
+ flags interval
+ }
+
+ chain test {
+ type filter hook ingress device veth_a priority 0;
+ }
+}
+'
+
+err_buf=
+info_buf=
+
+# Append string to error buffer
+err() {
+ err_buf="${err_buf}${1}
+"
+}
+
+# Append string to information buffer
+info() {
+ info_buf="${info_buf}${1}
+"
+}
+
+# Flush error buffer to stdout
+err_flush() {
+ printf "%s" "${err_buf}"
+ err_buf=
+}
+
+# Flush information buffer to stdout
+info_flush() {
+ printf "%s" "${info_buf}"
+ info_buf=
+}
+
+# Setup veth pair: this namespace receives traffic, B generates it
+setup_veth() {
+ ip netns add B
+ ip link add veth_a type veth peer name veth_b || return 1
+
+ ip link set veth_a up
+ ip link set veth_b netns B
+
+ ip -n B link set veth_b up
+
+ ip addr add dev veth_a 10.0.0.1
+ ip route add default dev veth_a
+
+ ip -6 addr add fe80::1/64 dev veth_a nodad
+ ip -6 addr add 2001:db8::1/64 dev veth_a nodad
+ ip -6 route add default dev veth_a
+
+ ip -n B route add default dev veth_b
+
+ ip -6 -n B addr add fe80::2/64 dev veth_b nodad
+ ip -6 -n B addr add 2001:db8::2/64 dev veth_b nodad
+ ip -6 -n B route add default dev veth_b
+
+ B() {
+ ip netns exec B "$@" >/dev/null 2>&1
+ }
+
+ sleep 2
+}
+
+# Fill in set template and initialise set
+setup_set() {
+ eval "echo \"${set_template}\"" | nft -f -
+}
+
+# Check that at least one of the needed tools is available
+check_tools() {
+ __tools=
+ for tool in ${tools}; do
+ if [ "${tool}" = "nc" ] && [ "${proto}" = "udp6" ] && \
+ ! nc -u -w0 1.1.1.1 1 2>/dev/null; then
+ # Some GNU netcat builds might not support IPv6
+ __tools="${__tools} netcat-openbsd"
+ continue
+ fi
+ __tools="${__tools} ${tool}"
+
+ command -v "${tool}" >/dev/null && return 0
+ done
+ err "need one of:${__tools}, skipping" && return 1
+}
+
+# Set up function to send ICMP packets
+setup_send_icmp() {
+ send_icmp() {
+ B ping -c1 -W1 "${dst_addr4}" >/dev/null 2>&1
+ }
+}
+
+# Set up function to send ICMPv6 packets
+setup_send_icmp6() {
+ if command -v ping6 >/dev/null; then
+ send_icmp6() {
+ ip -6 addr add "${dst_addr6}" dev veth_a nodad \
+ 2>/dev/null
+ B ping6 -q -c1 -W1 "${dst_addr6}"
+ }
+ else
+ send_icmp6() {
+ ip -6 addr add "${dst_addr6}" dev veth_a nodad \
+ 2>/dev/null
+ B ping -q -6 -c1 -W1 "${dst_addr6}"
+ }
+ fi
+}
+
+# Set up function to send single UDP packets on IPv4
+setup_send_udp() {
+ if command -v sendip >/dev/null; then
+ send_udp() {
+ [ -n "${src_port}" ] && src_port="-us ${src_port}"
+ [ -n "${dst_port}" ] && dst_port="-ud ${dst_port}"
+ [ -n "${src_addr4}" ] && src_addr4="-is ${src_addr4}"
+
+ # shellcheck disable=SC2086 # sendip needs split options
+ B sendip -p ipv4 -p udp ${src_addr4} ${src_port} \
+ ${dst_port} "${dst_addr4}"
+
+ src_port=
+ dst_port=
+ src_addr4=
+ }
+ elif command -v nc >/dev/null; then
+ if nc -u -w0 1.1.1.1 1 2>/dev/null; then
+ # OpenBSD netcat
+ nc_opt="-w0"
+ else
+ # GNU netcat
+ nc_opt="-q0"
+ fi
+
+ send_udp() {
+ if [ -n "${src_addr4}" ]; then
+ B ip addr add "${src_addr4}" dev veth_b
+ __src_addr4="-s ${src_addr4}"
+ fi
+ ip addr add "${dst_addr4}" dev veth_a 2>/dev/null
+ [ -n "${src_port}" ] && src_port="-p ${src_port}"
+
+ echo "" | B nc -u "${nc_opt}" "${__src_addr4}" \
+ "${src_port}" "${dst_addr4}" "${dst_port}"
+
+ src_addr4=
+ src_port=
+ }
+ elif [ -z "$(bash -c 'type -p')" ]; then
+ send_udp() {
+ ip addr add "${dst_addr4}" dev veth_a 2>/dev/null
+ if [ -n "${src_addr4}" ]; then
+ B ip addr add "${src_addr4}/16" dev veth_b
+ B ip route add default dev veth_b
+ fi
+
+ B bash -c "echo > /dev/udp/${dst_addr4}/${dst_port}"
+
+ if [ -n "${src_addr4}" ]; then
+ B ip addr del "${src_addr4}/16" dev veth_b
+ fi
+ src_addr4=
+ }
+ else
+ return 1
+ fi
+}
+
+# Set up function to send single UDP packets on IPv6
+setup_send_udp6() {
+ if command -v sendip >/dev/null; then
+ send_udp6() {
+ [ -n "${src_port}" ] && src_port="-us ${src_port}"
+ [ -n "${dst_port}" ] && dst_port="-ud ${dst_port}"
+ if [ -n "${src_addr6}" ]; then
+ src_addr6="-6s ${src_addr6}"
+ else
+ src_addr6="-6s 2001:db8::2"
+ fi
+ ip -6 addr add "${dst_addr6}" dev veth_a nodad \
+ 2>/dev/null
+
+ # shellcheck disable=SC2086 # this needs split options
+ B sendip -p ipv6 -p udp ${src_addr6} ${src_port} \
+ ${dst_port} "${dst_addr6}"
+
+ src_port=
+ dst_port=
+ src_addr6=
+ }
+ elif command -v nc >/dev/null && nc -u -w0 1.1.1.1 1 2>/dev/null; then
+ # GNU netcat might not work with IPv6, try next tool
+ send_udp6() {
+ ip -6 addr add "${dst_addr6}" dev veth_a nodad \
+ 2>/dev/null
+ if [ -n "${src_addr6}" ]; then
+ B ip addr add "${src_addr6}" dev veth_b nodad
+ else
+ src_addr6="2001:db8::2"
+ fi
+ [ -n "${src_port}" ] && src_port="-p ${src_port}"
+
+ # shellcheck disable=SC2086 # this needs split options
+ echo "" | B nc -u w0 "-s${src_addr6}" ${src_port} \
+ ${dst_addr6} ${dst_port}
+
+ src_addr6=
+ src_port=
+ }
+ elif [ -z "$(bash -c 'type -p')" ]; then
+ send_udp6() {
+ ip -6 addr add "${dst_addr6}" dev veth_a nodad \
+ 2>/dev/null
+ B ip addr add "${src_addr6}" dev veth_b nodad
+ B bash -c "echo > /dev/udp/${dst_addr6}/${dst_port}"
+ ip -6 addr del "${dst_addr6}" dev veth_a 2>/dev/null
+ }
+ else
+ return 1
+ fi
+}
+
+# Set up function to send TCP traffic on IPv4
+setup_flood_tcp() {
+ if command -v iperf3 >/dev/null; then
+ flood_tcp() {
+ [ -n "${dst_port}" ] && dst_port="-p ${dst_port}"
+ if [ -n "${src_addr4}" ]; then
+ B ip addr add "${src_addr4}/16" dev veth_b
+ src_addr4="-B ${src_addr4}"
+ else
+ B ip addr add dev veth_b 10.0.0.2
+ src_addr4="-B 10.0.0.2"
+ fi
+ if [ -n "${src_port}" ]; then
+ src_port="--cport ${src_port}"
+ fi
+ B ip route add default dev veth_b 2>/dev/null
+ ip addr add "${dst_addr4}" dev veth_a 2>/dev/null
+
+ # shellcheck disable=SC2086 # this needs split options
+ iperf3 -s -DB "${dst_addr4}" ${dst_port} >/dev/null 2>&1
+ sleep 2
+
+ # shellcheck disable=SC2086 # this needs split options
+ B iperf3 -c "${dst_addr4}" ${dst_port} ${src_port} \
+ ${src_addr4} -l16 -t 1000
+
+ src_addr4=
+ src_port=
+ dst_port=
+ }
+ elif command -v iperf >/dev/null; then
+ flood_tcp() {
+ [ -n "${dst_port}" ] && dst_port="-p ${dst_port}"
+ if [ -n "${src_addr4}" ]; then
+ B ip addr add "${src_addr4}/16" dev veth_b
+ src_addr4="-B ${src_addr4}"
+ else
+ B ip addr add dev veth_b 10.0.0.2 2>/dev/null
+ src_addr4="-B 10.0.0.2"
+ fi
+ if [ -n "${src_port}" ]; then
+ src_addr4="${src_addr4}:${src_port}"
+ fi
+ B ip route add default dev veth_b
+ ip addr add "${dst_addr4}" dev veth_a 2>/dev/null
+
+ # shellcheck disable=SC2086 # this needs split options
+ iperf -s -DB "${dst_addr4}" ${dst_port} >/dev/null 2>&1
+ sleep 2
+
+ # shellcheck disable=SC2086 # this needs split options
+ B iperf -c "${dst_addr4}" ${dst_port} ${src_addr4} \
+ -l20 -t 1000
+
+ src_addr4=
+ src_port=
+ dst_port=
+ }
+ elif command -v netperf >/dev/null; then
+ flood_tcp() {
+ [ -n "${dst_port}" ] && dst_port="-p ${dst_port}"
+ if [ -n "${src_addr4}" ]; then
+ B ip addr add "${src_addr4}/16" dev veth_b
+ else
+ B ip addr add dev veth_b 10.0.0.2
+ src_addr4="10.0.0.2"
+ fi
+ if [ -n "${src_port}" ]; then
+ dst_port="${dst_port},${src_port}"
+ fi
+ B ip route add default dev veth_b
+ ip addr add "${dst_addr4}" dev veth_a 2>/dev/null
+
+ # shellcheck disable=SC2086 # this needs split options
+ netserver -4 ${dst_port} -L "${dst_addr4}" \
+ >/dev/null 2>&1
+ sleep 2
+
+ # shellcheck disable=SC2086 # this needs split options
+ B netperf -4 -H "${dst_addr4}" ${dst_port} \
+ -L "${src_addr4}" -l 1000 -t TCP_STREAM
+
+ src_addr4=
+ src_port=
+ dst_port=
+ }
+ else
+ return 1
+ fi
+}
+
+# Set up function to send TCP traffic on IPv6
+setup_flood_tcp6() {
+ if command -v iperf3 >/dev/null; then
+ flood_tcp6() {
+ [ -n "${dst_port}" ] && dst_port="-p ${dst_port}"
+ if [ -n "${src_addr6}" ]; then
+ B ip addr add "${src_addr6}" dev veth_b nodad
+ src_addr6="-B ${src_addr6}"
+ else
+ src_addr6="-B 2001:db8::2"
+ fi
+ if [ -n "${src_port}" ]; then
+ src_port="--cport ${src_port}"
+ fi
+ B ip route add default dev veth_b
+ ip -6 addr add "${dst_addr6}" dev veth_a nodad \
+ 2>/dev/null
+
+ # shellcheck disable=SC2086 # this needs split options
+ iperf3 -s -DB "${dst_addr6}" ${dst_port} >/dev/null 2>&1
+ sleep 2
+
+ # shellcheck disable=SC2086 # this needs split options
+ B iperf3 -c "${dst_addr6}" ${dst_port} \
+ ${src_port} ${src_addr6} -l16 -t 1000
+
+ src_addr6=
+ src_port=
+ dst_port=
+ }
+ elif command -v iperf >/dev/null; then
+ flood_tcp6() {
+ [ -n "${dst_port}" ] && dst_port="-p ${dst_port}"
+ if [ -n "${src_addr6}" ]; then
+ B ip addr add "${src_addr6}" dev veth_b nodad
+ src_addr6="-B ${src_addr6}"
+ else
+ src_addr6="-B 2001:db8::2"
+ fi
+ if [ -n "${src_port}" ]; then
+ src_addr6="${src_addr6}:${src_port}"
+ fi
+ B ip route add default dev veth_b
+ ip -6 addr add "${dst_addr6}" dev veth_a nodad \
+ 2>/dev/null
+
+ # shellcheck disable=SC2086 # this needs split options
+ iperf -s -VDB "${dst_addr6}" ${dst_port} >/dev/null 2>&1
+ sleep 2
+
+ # shellcheck disable=SC2086 # this needs split options
+ B iperf -c "${dst_addr6}" -V ${dst_port} \
+ ${src_addr6} -l1 -t 1000
+
+ src_addr6=
+ src_port=
+ dst_port=
+ }
+ elif command -v netperf >/dev/null; then
+ flood_tcp6() {
+ [ -n "${dst_port}" ] && dst_port="-p ${dst_port}"
+ if [ -n "${src_addr6}" ]; then
+ B ip addr add "${src_addr6}" dev veth_b nodad
+ else
+ src_addr6="2001:db8::2"
+ fi
+ if [ -n "${src_port}" ]; then
+ dst_port="${dst_port},${src_port}"
+ fi
+ B ip route add default dev veth_b
+ ip -6 addr add "${dst_addr6}" dev veth_a nodad \
+ 2>/dev/null
+
+ # shellcheck disable=SC2086 # this needs split options
+ netserver -6 ${dst_port} -L "${dst_addr6}" \
+ >/dev/null 2>&1
+ sleep 2
+
+ # shellcheck disable=SC2086 # this needs split options
+ B netperf -6 -H "${dst_addr6}" ${dst_port} \
+ -L "${src_addr6}" -l 1000 -t TCP_STREAM
+
+ src_addr6=
+ src_port=
+ dst_port=
+ }
+ else
+ return 1
+ fi
+}
+
+# Set up function to send UDP traffic on IPv4
+setup_flood_udp() {
+ if command -v iperf3 >/dev/null; then
+ flood_udp() {
+ [ -n "${dst_port}" ] && dst_port="-p ${dst_port}"
+ if [ -n "${src_addr4}" ]; then
+ B ip addr add "${src_addr4}/16" dev veth_b
+ src_addr4="-B ${src_addr4}"
+ else
+ B ip addr add dev veth_b 10.0.0.2 2>/dev/null
+ src_addr4="-B 10.0.0.2"
+ fi
+ if [ -n "${src_port}" ]; then
+ src_port="--cport ${src_port}"
+ fi
+ B ip route add default dev veth_b
+ ip addr add "${dst_addr4}" dev veth_a 2>/dev/null
+
+ # shellcheck disable=SC2086 # this needs split options
+ iperf3 -s -DB "${dst_addr4}" ${dst_port}
+ sleep 2
+
+ # shellcheck disable=SC2086 # this needs split options
+ B iperf3 -u -c "${dst_addr4}" -Z -b 100M -l16 -t1000 \
+ ${dst_port} ${src_port} ${src_addr4}
+
+ src_addr4=
+ src_port=
+ dst_port=
+ }
+ elif command -v iperf >/dev/null; then
+ flood_udp() {
+ [ -n "${dst_port}" ] && dst_port="-p ${dst_port}"
+ if [ -n "${src_addr4}" ]; then
+ B ip addr add "${src_addr4}/16" dev veth_b
+ src_addr4="-B ${src_addr4}"
+ else
+ B ip addr add dev veth_b 10.0.0.2
+ src_addr4="-B 10.0.0.2"
+ fi
+ if [ -n "${src_port}" ]; then
+ src_addr4="${src_addr4}:${src_port}"
+ fi
+ B ip route add default dev veth_b
+ ip addr add "${dst_addr4}" dev veth_a 2>/dev/null
+
+ # shellcheck disable=SC2086 # this needs split options
+ iperf -u -sDB "${dst_addr4}" ${dst_port} >/dev/null 2>&1
+ sleep 2
+
+ # shellcheck disable=SC2086 # this needs split options
+ B iperf -u -c "${dst_addr4}" -b 100M -l1 -t1000 \
+ ${dst_port} ${src_addr4}
+
+ src_addr4=
+ src_port=
+ dst_port=
+ }
+ elif command -v netperf >/dev/null; then
+ flood_udp() {
+ [ -n "${dst_port}" ] && dst_port="-p ${dst_port}"
+ if [ -n "${src_addr4}" ]; then
+ B ip addr add "${src_addr4}/16" dev veth_b
+ else
+ B ip addr add dev veth_b 10.0.0.2
+ src_addr4="10.0.0.2"
+ fi
+ if [ -n "${src_port}" ]; then
+ dst_port="${dst_port},${src_port}"
+ fi
+ B ip route add default dev veth_b
+ ip addr add "${dst_addr4}" dev veth_a 2>/dev/null
+
+ # shellcheck disable=SC2086 # this needs split options
+ netserver -4 ${dst_port} -L "${dst_addr4}" \
+ >/dev/null 2>&1
+ sleep 2
+
+ # shellcheck disable=SC2086 # this needs split options
+ B netperf -4 -H "${dst_addr4}" ${dst_port} \
+ -L "${src_addr4}" -l 1000 -t UDP_STREAM
+
+ src_addr4=
+ src_port=
+ dst_port=
+ }
+ else
+ return 1
+ fi
+}
+
+# Find pktgen script and set up function to start pktgen injection
+setup_perf() {
+ for pktgen_script_path in ${PKTGEN_SCRIPT_PATHS} __notfound; do
+ command -v "${pktgen_script_path}" >/dev/null && break
+ done
+ [ "${pktgen_script_path}" = "__notfound" ] && return 1
+
+ perf_ipv4() {
+ ${pktgen_script_path} -s80 \
+ -i veth_a -d "${dst_addr4}" -p "${dst_port}" \
+ -m "${dst_mac}" \
+ -t $(($(nproc) / 5 + 1)) -b10000 -n0 2>/dev/null &
+ perf_pid=$!
+ }
+ perf_ipv6() {
+ IP6=6 ${pktgen_script_path} -s100 \
+ -i veth_a -d "${dst_addr6}" -p "${dst_port}" \
+ -m "${dst_mac}" \
+ -t $(($(nproc) / 5 + 1)) -b10000 -n0 2>/dev/null &
+ perf_pid=$!
+ }
+}
+
+# Clean up before each test
+cleanup() {
+ nft reset counter inet filter test >/dev/null 2>&1
+ nft flush ruleset >/dev/null 2>&1
+ ip link del dummy0 2>/dev/null
+ ip route del default 2>/dev/null
+ ip -6 route del default 2>/dev/null
+ ip netns del B 2>/dev/null
+ ip link del veth_a 2>/dev/null
+ timeout=
+ killall iperf3 2>/dev/null
+ killall iperf 2>/dev/null
+ killall netperf 2>/dev/null
+ killall netserver 2>/dev/null
+ rm -f ${tmp}
+ sleep 2
+}
+
+# Entry point for setup functions
+setup() {
+ if [ "$(id -u)" -ne 0 ]; then
+ echo " need to run as root"
+ exit ${KSELFTEST_SKIP}
+ fi
+
+ cleanup
+ check_tools || return 1
+ for arg do
+ if ! eval setup_"${arg}"; then
+ err " ${arg} not supported"
+ return 1
+ fi
+ done
+}
+
+# Format integer into IPv4 address, summing 10.0.0.5 (arbitrary) to it
+format_addr4() {
+ a=$((${1} + 16777216 * 10 + 5))
+ printf "%i.%i.%i.%i" \
+ "$((a / 16777216))" "$((a % 16777216 / 65536))" \
+ "$((a % 65536 / 256))" "$((a % 256))"
+}
+
+# Format integer into IPv6 address, summing 2001:db8:: to it
+format_addr6() {
+ printf "2001:db8::%04x:%04x" "$((${1} / 65536))" "$((${1} % 65536))"
+}
+
+# Format integer into EUI-48 address, summing 00:01:00:00:00:00 to it
+format_mac() {
+ printf "00:01:%02x:%02x:%02x:%02x" \
+ "$((${1} / 16777216))" "$((${1} % 16777216 / 65536))" \
+ "$((${1} % 65536 / 256))" "$((${1} % 256))"
+}
+
+# Format integer into port, avoid 0 port
+format_port() {
+ printf "%i" "$((${1} % 65534 + 1))"
+}
+
+# Drop suffixed '6' from L4 protocol, if any
+format_proto() {
+ printf "%s" "${proto}" | tr -d 6
+}
+
+# Format destination and source fields into nft concatenated type
+format() {
+ __start=
+ __end=
+ __expr="{ "
+
+ for f in ${dst}; do
+ [ "${__expr}" != "{ " ] && __expr="${__expr} . "
+
+ __start="$(eval format_"${f}" "${start}")"
+ __end="$(eval format_"${f}" "${end}")"
+
+ if [ "${f}" = "proto" ]; then
+ __expr="${__expr}${__start}"
+ else
+ __expr="${__expr}${__start}-${__end}"
+ fi
+ done
+ for f in ${src}; do
+ __expr="${__expr} . "
+ __start="$(eval format_"${f}" "${srcstart}")"
+ __end="$(eval format_"${f}" "${srcend}")"
+
+ if [ "${f}" = "proto" ]; then
+ __expr="${__expr}${__start}"
+ else
+ __expr="${__expr}${__start}-${__end}"
+ fi
+ done
+
+ if [ -n "${timeout}" ]; then
+ echo "${__expr} timeout ${timeout}s }"
+ else
+ echo "${__expr} }"
+ fi
+}
+
+# Format destination and source fields into nft type, start element only
+format_norange() {
+ __expr="{ "
+
+ for f in ${dst}; do
+ [ "${__expr}" != "{ " ] && __expr="${__expr} . "
+
+ __expr="${__expr}$(eval format_"${f}" "${start}")"
+ done
+ for f in ${src}; do
+ __expr="${__expr} . $(eval format_"${f}" "${start}")"
+ done
+
+ echo "${__expr} }"
+}
+
+# Format first destination field into nft type
+format_noconcat() {
+ for f in ${dst}; do
+ __start="$(eval format_"${f}" "${start}")"
+ __end="$(eval format_"${f}" "${end}")"
+
+ if [ "${f}" = "proto" ]; then
+ echo "{ ${__start} }"
+ else
+ echo "{ ${__start}-${__end} }"
+ fi
+ return
+ done
+}
+
+# Add single entry to 'test' set in 'inet filter' table
+add() {
+ if ! nft add element inet filter test "${1}"; then
+ err "Failed to add ${1} given ruleset:"
+ err "$(nft list ruleset -a)"
+ return 1
+ fi
+}
+
+# Format and output entries for sets in 'netdev perf' table
+add_perf() {
+ if [ "${1}" = "test" ]; then
+ echo "add element netdev perf test $(format)"
+ elif [ "${1}" = "norange" ]; then
+ echo "add element netdev perf norange $(format_norange)"
+ elif [ "${1}" = "noconcat" ]; then
+ echo "add element netdev perf noconcat $(format_noconcat)"
+ fi
+}
+
+# Add single entry to 'norange' set in 'netdev perf' table
+add_perf_norange() {
+ if ! nft add element netdev perf norange "${1}"; then
+ err "Failed to add ${1} given ruleset:"
+ err "$(nft list ruleset -a)"
+ return 1
+ fi
+}
+
+# Add single entry to 'noconcat' set in 'netdev perf' table
+add_perf_noconcat() {
+ if ! nft add element netdev perf noconcat "${1}"; then
+ err "Failed to add ${1} given ruleset:"
+ err "$(nft list ruleset -a)"
+ return 1
+ fi
+}
+
+# Delete single entry from set
+del() {
+ if ! nft delete element inet filter test "${1}"; then
+ err "Failed to delete ${1} given ruleset:"
+ err "$(nft list ruleset -a)"
+ return 1
+ fi
+}
+
+# Return packet count from 'test' counter in 'inet filter' table
+count_packets() {
+ found=0
+ for token in $(nft list counter inet filter test); do
+ [ ${found} -eq 1 ] && echo "${token}" && return
+ [ "${token}" = "packets" ] && found=1
+ done
+}
+
+# Return packet count from 'test' counter in 'netdev perf' table
+count_perf_packets() {
+ found=0
+ for token in $(nft list counter netdev perf test); do
+ [ ${found} -eq 1 ] && echo "${token}" && return
+ [ "${token}" = "packets" ] && found=1
+ done
+}
+
+# Set MAC addresses, send traffic according to specifier
+flood() {
+ ip link set veth_a address "$(format_mac "${1}")"
+ ip -n B link set veth_b address "$(format_mac "${2}")"
+
+ for f in ${dst}; do
+ eval dst_"$f"=\$\(format_\$f "${1}"\)
+ done
+ for f in ${src}; do
+ eval src_"$f"=\$\(format_\$f "${2}"\)
+ done
+ eval flood_\$proto
+}
+
+# Set MAC addresses, start pktgen injection
+perf() {
+ dst_mac="$(format_mac "${1}")"
+ ip link set veth_a address "${dst_mac}"
+
+ for f in ${dst}; do
+ eval dst_"$f"=\$\(format_\$f "${1}"\)
+ done
+ for f in ${src}; do
+ eval src_"$f"=\$\(format_\$f "${2}"\)
+ done
+ eval perf_\$perf_proto
+}
+
+# Set MAC addresses, send single packet, check that it matches, reset counter
+send_match() {
+ ip link set veth_a address "$(format_mac "${1}")"
+ ip -n B link set veth_b address "$(format_mac "${2}")"
+
+ for f in ${dst}; do
+ eval dst_"$f"=\$\(format_\$f "${1}"\)
+ done
+ for f in ${src}; do
+ eval src_"$f"=\$\(format_\$f "${2}"\)
+ done
+ eval send_\$proto
+ if [ "$(count_packets)" != "1" ]; then
+ err "${proto} packet to:"
+ err " $(for f in ${dst}; do
+ eval format_\$f "${1}"; printf ' '; done)"
+ err "from:"
+ err " $(for f in ${src}; do
+ eval format_\$f "${2}"; printf ' '; done)"
+ err "should have matched ruleset:"
+ err "$(nft list ruleset -a)"
+ return 1
+ fi
+ nft reset counter inet filter test >/dev/null
+}
+
+# Set MAC addresses, send single packet, check that it doesn't match
+send_nomatch() {
+ ip link set veth_a address "$(format_mac "${1}")"
+ ip -n B link set veth_b address "$(format_mac "${2}")"
+
+ for f in ${dst}; do
+ eval dst_"$f"=\$\(format_\$f "${1}"\)
+ done
+ for f in ${src}; do
+ eval src_"$f"=\$\(format_\$f "${2}"\)
+ done
+ eval send_\$proto
+ if [ "$(count_packets)" != "0" ]; then
+ err "${proto} packet to:"
+ err " $(for f in ${dst}; do
+ eval format_\$f "${1}"; printf ' '; done)"
+ err "from:"
+ err " $(for f in ${src}; do
+ eval format_\$f "${2}"; printf ' '; done)"
+ err "should not have matched ruleset:"
+ err "$(nft list ruleset -a)"
+ return 1
+ fi
+}
+
+# Correctness test template:
+# - add ranged element, check that packets match it
+# - check that packets outside range don't match it
+# - remove some elements, check that packets don't match anymore
+test_correctness() {
+ setup veth send_"${proto}" set || return ${KSELFTEST_SKIP}
+
+ range_size=1
+ for i in $(seq "${start}" $((start + count))); do
+ end=$((start + range_size))
+
+ # Avoid negative or zero-sized port ranges
+ if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+ start=${end}
+ end=$((end + 1))
+ fi
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ add "$(format)" || return 1
+ for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do
+ send_match "${j}" $((j + src_delta)) || return 1
+ done
+ send_nomatch $((end + 1)) $((end + 1 + src_delta)) || return 1
+
+ # Delete elements now and then
+ if [ $((i % 3)) -eq 0 ]; then
+ del "$(format)" || return 1
+ for j in $(seq ${start} \
+ $((range_size / 2 + 1)) ${end}); do
+ send_nomatch "${j}" $((j + src_delta)) \
+ || return 1
+ done
+ fi
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+}
+
+# Concurrency test template:
+# - add all the elements
+# - start a thread for each physical thread that:
+# - adds all the elements
+# - flushes the set
+# - adds all the elements
+# - flushes the entire ruleset
+# - adds the set back
+# - adds all the elements
+# - delete all the elements
+test_concurrency() {
+ proto=${flood_proto}
+ tools=${flood_tools}
+ chain_spec=${flood_spec}
+ setup veth flood_"${proto}" set || return ${KSELFTEST_SKIP}
+
+ range_size=1
+ cstart=${start}
+ flood_pids=
+ for i in $(seq ${start} $((start + count))); do
+ end=$((start + range_size))
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ add "$(format)" || return 1
+
+ flood "${i}" $((i + src_delta)) & flood_pids="${flood_pids} $!"
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+
+ sleep 10
+
+ pids=
+ for c in $(seq 1 "$(nproc)"); do (
+ for r in $(seq 1 "${race_repeat}"); do
+ range_size=1
+
+ # $start needs to be local to this subshell
+ # shellcheck disable=SC2030
+ start=${cstart}
+ for i in $(seq ${start} $((start + count))); do
+ end=$((start + range_size))
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ add "$(format)" 2>/dev/null
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+
+ nft flush inet filter test 2>/dev/null
+
+ range_size=1
+ start=${cstart}
+ for i in $(seq ${start} $((start + count))); do
+ end=$((start + range_size))
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ add "$(format)" 2>/dev/null
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+
+ nft flush ruleset
+ setup set 2>/dev/null
+
+ range_size=1
+ start=${cstart}
+ for i in $(seq ${start} $((start + count))); do
+ end=$((start + range_size))
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ add "$(format)" 2>/dev/null
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+
+ range_size=1
+ start=${cstart}
+ for i in $(seq ${start} $((start + count))); do
+ end=$((start + range_size))
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ del "$(format)" 2>/dev/null
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+ done
+ ) & pids="${pids} $!"
+ done
+
+ # shellcheck disable=SC2046,SC2086 # word splitting wanted here
+ wait $(for pid in ${pids}; do echo ${pid}; done)
+ # shellcheck disable=SC2046,SC2086
+ kill $(for pid in ${flood_pids}; do echo ${pid}; done) 2>/dev/null
+ # shellcheck disable=SC2046,SC2086
+ wait $(for pid in ${flood_pids}; do echo ${pid}; done) 2>/dev/null
+
+ return 0
+}
+
+# Timeout test template:
+# - add all the elements with 3s timeout while checking that packets match
+# - wait 3s after the last insertion, check that packets don't match any entry
+test_timeout() {
+ setup veth send_"${proto}" set || return ${KSELFTEST_SKIP}
+
+ timeout=3
+ range_size=1
+ for i in $(seq "${start}" $((start + count))); do
+ end=$((start + range_size))
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ add "$(format)" || return 1
+
+ for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do
+ send_match "${j}" $((j + src_delta)) || return 1
+ done
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+ sleep 3
+ for i in $(seq ${start} $((start + count))); do
+ end=$((start + range_size))
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do
+ send_nomatch "${j}" $((j + src_delta)) || return 1
+ done
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+}
+
+# Performance test template:
+# - add concatenated ranged entries
+# - add non-ranged concatenated entries (for hash set matching rate baseline)
+# - add ranged entries with first field only (for rbhash baseline)
+# - start pktgen injection directly on device rx path of this namespace
+# - measure drop only rate, hash and rbtree baselines, then matching rate
+test_performance() {
+ chain_spec=${perf_spec}
+ dst="${perf_dst}"
+ src="${perf_src}"
+ setup veth perf set || return ${KSELFTEST_SKIP}
+
+ first=${start}
+ range_size=1
+ for set in test norange noconcat; do
+ start=${first}
+ for i in $(seq ${start} $((start + perf_entries))); do
+ end=$((start + range_size))
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+ start=${end}
+ end=$((end + 1))
+ elif [ ${start} -eq ${end} ]; then
+ end=$((start + 1))
+ fi
+
+ add_perf ${set}
+
+ start=$((end + range_size))
+ done > "${tmp}"
+ nft -f "${tmp}"
+ done
+
+ perf $((end - 1)) ${srcstart}
+
+ sleep 2
+
+ nft add rule netdev perf test counter name \"test\" drop
+ nft reset counter netdev perf test >/dev/null 2>&1
+ sleep "${perf_duration}"
+ pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))"
+ info " baseline (drop from netdev hook): ${pps}pps"
+ handle="$(nft -a list chain netdev perf test | grep counter)"
+ handle="${handle##* }"
+ nft delete rule netdev perf test handle "${handle}"
+
+ nft add rule "netdev perf test ${chain_spec} @norange \
+ counter name \"test\" drop"
+ nft reset counter netdev perf test >/dev/null 2>&1
+ sleep "${perf_duration}"
+ pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))"
+ info " baseline hash (non-ranged entries): ${pps}pps"
+ handle="$(nft -a list chain netdev perf test | grep counter)"
+ handle="${handle##* }"
+ nft delete rule netdev perf test handle "${handle}"
+
+ nft add rule "netdev perf test ${chain_spec%%. *} @noconcat \
+ counter name \"test\" drop"
+ nft reset counter netdev perf test >/dev/null 2>&1
+ sleep "${perf_duration}"
+ pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))"
+ info " baseline rbtree (match on first field only): ${pps}pps"
+ handle="$(nft -a list chain netdev perf test | grep counter)"
+ handle="${handle##* }"
+ nft delete rule netdev perf test handle "${handle}"
+
+ nft add rule "netdev perf test ${chain_spec} @test \
+ counter name \"test\" drop"
+ nft reset counter netdev perf test >/dev/null 2>&1
+ sleep "${perf_duration}"
+ pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))"
+ p5="$(printf %5s "${perf_entries}")"
+ info " set with ${p5} full, ranged entries: ${pps}pps"
+ kill "${perf_pid}"
+}
+
+# Run everything in a separate network namespace
+[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; }
+tmp="$(mktemp)"
+trap cleanup EXIT
+
+# Entry point for test runs
+passed=0
+for name in ${TESTS}; do
+ printf "TEST: %s\n" "${name}"
+ for type in ${TYPES}; do
+ eval desc=\$TYPE_"${type}"
+ IFS='
+'
+ for __line in ${desc}; do
+ # shellcheck disable=SC2086
+ eval ${__line%% *}=\"${__line##* }\";
+ done
+ IFS='
+'
+
+ if [ "${name}" = "concurrency" ] && \
+ [ "${race_repeat}" = "0" ]; then
+ continue
+ fi
+ if [ "${name}" = "performance" ] && \
+ [ "${perf_duration}" = "0" ]; then
+ continue
+ fi
+
+ printf " %-60s " "${display}"
+ eval test_"${name}"
+ ret=$?
+
+ if [ $ret -eq 0 ]; then
+ printf "[ OK ]\n"
+ info_flush
+ passed=$((passed + 1))
+ elif [ $ret -eq 1 ]; then
+ printf "[FAIL]\n"
+ err_flush
+ exit 1
+ elif [ $ret -eq ${KSELFTEST_SKIP} ]; then
+ printf "[SKIP]\n"
+ err_flush
+ fi
+ done
+done
+
+[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP}
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 6944b89..ee1b727 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -3158,7 +3158,18 @@ TEST(user_notification_basic)
EXPECT_GT(poll(&pollfd, 1, -1), 0);
EXPECT_EQ(pollfd.revents, POLLIN);
- EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+ /* Test that we can't pass garbage to the kernel. */
+ memset(&req, 0, sizeof(req));
+ req.pid = -1;
+ errno = 0;
+ ret = ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EINVAL, errno);
+
+ if (ret) {
+ req.pid = 0;
+ EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+ }
pollfd.fd = listener;
pollfd.events = POLLIN | POLLOUT;
@@ -3278,6 +3289,7 @@ TEST(user_notification_signal)
close(sk_pair[1]);
+ memset(&req, 0, sizeof(req));
EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
EXPECT_EQ(kill(pid, SIGUSR1), 0);
@@ -3296,6 +3308,7 @@ TEST(user_notification_signal)
EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1);
EXPECT_EQ(errno, ENOENT);
+ memset(&req, 0, sizeof(req));
EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
resp.id = req.id;
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index e7310d9..d5c85c7 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -37,7 +37,7 @@
ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; }
ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; }
ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; }
-sleep() { read -t "$1" -N 0 || true; }
+sleep() { read -t "$1" -N 1 || true; }
waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; }
waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
@@ -294,12 +294,9 @@
ip1 -4 route add default dev wg0 table 51820
ip1 -4 rule add not fwmark 51820 table 51820
ip1 -4 rule add table main suppress_prefixlength 0
-# suppress_prefixlength only got added in 3.12, and we want to support 3.10+.
-if [[ $(ip1 -4 rule show all) == *suppress_prefixlength* ]]; then
- # Flood the pings instead of sending just one, to trigger routing table reference counting bugs.
- n1 ping -W 1 -c 100 -f 192.168.99.7
- n1 ping -W 1 -c 100 -f abab::1111
-fi
+# Flood the pings instead of sending just one, to trigger routing table reference counting bugs.
+n1 ping -W 1 -c 100 -f 192.168.99.7
+n1 ping -W 1 -c 100 -f abab::1111
n0 iptables -t nat -F
ip0 link del vethrc
diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile
index 6d51bf7..f10aa35 100644
--- a/tools/testing/selftests/wireguard/qemu/Makefile
+++ b/tools/testing/selftests/wireguard/qemu/Makefile
@@ -5,6 +5,7 @@
PWD := $(shell pwd)
CHOST := $(shell gcc -dumpmachine)
+HOST_ARCH := $(firstword $(subst -, ,$(CHOST)))
ifneq (,$(ARCH))
CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc))))))
ifeq (,$(CBUILD))
@@ -37,19 +38,19 @@
define file_download =
$(DISTFILES_PATH)/$(1):
mkdir -p $(DISTFILES_PATH)
- flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -t inf --retry-on-http-error=404 -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
+ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
endef
-$(eval $(call tar_download,MUSL,musl,1.1.20,.tar.gz,https://www.musl-libc.org/releases/,44be8771d0e6c6b5f82dd15662eb2957c9a3173a19a8b49966ac0542bbd40d61))
+$(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
-$(eval $(call tar_download,IPERF,iperf,3.1.7,.tar.gz,http://downloads.es.net/pub/iperf/,a4ef73406fe92250602b8da2ae89ec53211f805df97a1d1d629db5a14043734f))
+$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
-$(eval $(call tar_download,IPROUTE2,iproute2,5.1.0,.tar.gz,https://www.kernel.org/pub/linux/utils/net/iproute2/,9b43707d6075ecdca14803ca8ce0c8553848c49fa1586d12fd508d66577243f2))
-$(eval $(call tar_download,IPTABLES,iptables,1.6.1,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,0fc2d7bd5d7be11311726466789d4c65fb4c8e096c9182b56ce97440864f0cf5))
-$(eval $(call tar_download,NMAP,nmap,7.60,.tar.bz2,https://nmap.org/dist/,a8796ecc4fa6c38aad6139d9515dc8113023a82e9d787e5a5fb5fa1b05516f21))
-$(eval $(call tar_download,IPUTILS,iputils,s20161105,.tar.gz,https://github.com/iputils/iputils/archive/s20161105.tar.gz/#,f813092f03d17294fd23544b129b95cdb87fe19f7970a51908a6b88509acad8a))
-$(eval $(call tar_download,WIREGUARD_TOOLS,WireGuard,0.0.20191212,.tar.xz,https://git.zx2c4.com/WireGuard/snapshot/,b0d718380f7a8822b2f12d75e462fa4eafa3a77871002981f367cd4fe2a1b071))
+$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
+$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
+$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
+$(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
+$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f))
KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
@@ -59,23 +60,21 @@
export LDFLAGS ?=
export CPPFLAGS := -I$(BUILD_PATH)/include
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
CROSS_COMPILE_FLAG := --host=$(CHOST)
-NOPIE_GCC := gcc -fno-PIE
CFLAGS += -march=native
STRIP := strip
else
$(info Cross compilation: building for $(CBUILD) using $(CHOST))
CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST)
export CROSS_COMPILE=$(CBUILD)-
-NOPIE_GCC := $(CBUILD)-gcc -fno-PIE
STRIP := $(CBUILD)-strip
endif
ifeq ($(ARCH),aarch64)
QEMU_ARCH := aarch64
KERNEL_ARCH := arm64
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
QEMU_MACHINE := -cpu cortex-a53 -machine virt
@@ -85,7 +84,7 @@
QEMU_ARCH := aarch64
KERNEL_ARCH := arm64
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
QEMU_MACHINE := -cpu cortex-a53 -machine virt
@@ -95,7 +94,7 @@
QEMU_ARCH := arm
KERNEL_ARCH := arm
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
QEMU_MACHINE := -cpu cortex-a15 -machine virt
@@ -105,7 +104,7 @@
QEMU_ARCH := arm
KERNEL_ARCH := arm
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
QEMU_MACHINE := -cpu cortex-a15 -machine virt
@@ -116,7 +115,7 @@
QEMU_ARCH := x86_64
KERNEL_ARCH := x86_64
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine q35,accel=kvm
else
QEMU_MACHINE := -cpu Skylake-Server -machine q35
@@ -126,7 +125,7 @@
QEMU_ARCH := i386
KERNEL_ARCH := x86
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
-ifeq ($(subst i686,x86_64,$(CBUILD)),$(CHOST))
+ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH))
QEMU_MACHINE := -cpu host -machine q35,accel=kvm
else
QEMU_MACHINE := -cpu coreduo -machine q35
@@ -136,7 +135,7 @@
QEMU_ARCH := mips64
KERNEL_ARCH := mips
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine malta,accel=kvm
CFLAGS += -EB
else
@@ -147,7 +146,7 @@
QEMU_ARCH := mips64el
KERNEL_ARCH := mips
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine malta,accel=kvm
CFLAGS += -EL
else
@@ -158,7 +157,7 @@
QEMU_ARCH := mips
KERNEL_ARCH := mips
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine malta,accel=kvm
CFLAGS += -EB
else
@@ -169,7 +168,7 @@
QEMU_ARCH := mipsel
KERNEL_ARCH := mips
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine malta,accel=kvm
CFLAGS += -EL
else
@@ -180,7 +179,7 @@
QEMU_ARCH := ppc64
KERNEL_ARCH := powerpc
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host,accel=kvm -machine pseries
else
QEMU_MACHINE := -machine pseries
@@ -190,7 +189,7 @@
QEMU_ARCH := ppc
KERNEL_ARCH := powerpc
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage
-ifeq ($(CHOST),$(CBUILD))
+ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500
else
QEMU_MACHINE := -machine ppce500
@@ -200,10 +199,11 @@
QEMU_ARCH := m68k
KERNEL_ARCH := m68k
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-ifeq ($(CHOST),$(CBUILD))
-QEMU_MACHINE := -cpu host,accel=kvm -machine q800
+KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/m68k.config)
+ifeq ($(HOST_ARCH),$(ARCH))
+QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -smp 1 -append $(KERNEL_CMDLINE)
else
-QEMU_MACHINE := -machine q800
+QEMU_MACHINE := -machine q800 -smp 1 -append $(KERNEL_CMDLINE)
endif
else
$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k)
@@ -238,14 +238,14 @@
echo "nod /dev/console 644 0 0 c 5 1" >> $@
echo "dir /bin 755 0 0" >> $@
echo "file /bin/iperf3 $(IPERF_PATH)/src/iperf3 755 0 0" >> $@
- echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/tools/wg 755 0 0" >> $@
+ echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/wg 755 0 0" >> $@
echo "file /bin/bash $(BASH_PATH)/bash 755 0 0" >> $@
echo "file /bin/ip $(IPROUTE2_PATH)/ip/ip 755 0 0" >> $@
echo "file /bin/ss $(IPROUTE2_PATH)/misc/ss 755 0 0" >> $@
echo "file /bin/ping $(IPUTILS_PATH)/ping 755 0 0" >> $@
echo "file /bin/ncat $(NMAP_PATH)/ncat/ncat 755 0 0" >> $@
- echo "file /bin/xtables-multi $(IPTABLES_PATH)/iptables/xtables-multi 755 0 0" >> $@
- echo "slink /bin/iptables xtables-multi 777 0 0" >> $@
+ echo "file /bin/xtables-legacy-multi $(IPTABLES_PATH)/iptables/xtables-legacy-multi 755 0 0" >> $@
+ echo "slink /bin/iptables xtables-legacy-multi 777 0 0" >> $@
echo "slink /bin/ping6 ping 777 0 0" >> $@
echo "dir /lib 755 0 0" >> $@
echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@
@@ -260,8 +260,8 @@
cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config
$(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,)
-$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/tools/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES)
- $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)"
+$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES)
+ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE)
$(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config
$(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install
@@ -280,7 +280,7 @@
$(MUSL_CC): $(MUSL_PATH)/lib/libc.so
sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs
- printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" -fno-stack-protector -no-pie "$$@"\n' > $(BUILD_PATH)/musl-gcc
+ printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" "$$@"\n' > $(BUILD_PATH)/musl-gcc
chmod +x $(BUILD_PATH)/musl-gcc
$(IPERF_PATH)/.installed: $(IPERF_TAR)
@@ -291,7 +291,7 @@
touch $@
$(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS)
- cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
+ cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --with-openssl=no
$(MAKE) -C $(IPERF_PATH)
$(STRIP) -s $@
@@ -308,8 +308,8 @@
flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
touch $@
-$(WIREGUARD_TOOLS_PATH)/src/tools/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src/tools LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
+$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
+ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
$(STRIP) -s $@
$(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
@@ -323,7 +323,8 @@
touch $@
$(IPUTILS_PATH)/ping: | $(IPUTILS_PATH)/.installed $(USERSPACE_DEPS)
- $(MAKE) -C $(IPUTILS_PATH) USE_CAP=no USE_IDN=no USE_NETTLE=no USE_CRYPTO=no ping
+ sed -i /atexit/d $(IPUTILS_PATH)/ping.c
+ cd $(IPUTILS_PATH) && $(CC) $(CFLAGS) -std=c99 -o $@ ping.c ping_common.c ping6_common.c iputils_common.c -D_GNU_SOURCE -D'IPUTILS_VERSION(f)=f' -lresolv $(LDFLAGS)
$(STRIP) -s $@
$(BASH_PATH)/.installed: $(BASH_TAR)
@@ -357,7 +358,7 @@
sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
touch $@
-$(IPTABLES_PATH)/iptables/xtables-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
+$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
$(MAKE) -C $(IPTABLES_PATH)
$(STRIP) -s $@
@@ -368,8 +369,9 @@
touch $@
$(NMAP_PATH)/ncat/ncat: | $(NMAP_PATH)/.installed $(USERSPACE_DEPS)
- cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux
- $(MAKE) -C $(NMAP_PATH) build-ncat
+ cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux --without-libssh
+ $(MAKE) -C $(NMAP_PATH)/libpcap
+ $(MAKE) -C $(NMAP_PATH)/ncat
$(STRIP) -s $@
clean:
@@ -379,7 +381,7 @@
rm -rf $(DISTFILES_PATH)
menuconfig: $(KERNEL_BUILD_PATH)/.config
- $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)" menuconfig
+ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) menuconfig
.PHONY: qemu build clean distclean menuconfig
.DELETE_ON_ERROR:
diff --git a/tools/testing/selftests/wireguard/qemu/arch/m68k.config b/tools/testing/selftests/wireguard/qemu/arch/m68k.config
index 5381ea1..62a15bd 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/m68k.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config
@@ -1,9 +1,9 @@
CONFIG_MMU=y
+CONFIG_M68KCLASSIC=y
CONFIG_M68040=y
CONFIG_MAC=y
CONFIG_SERIAL_PMACZILOG=y
CONFIG_SERIAL_PMACZILOG_TTYS=y
CONFIG_SERIAL_PMACZILOG_CONSOLE=y
-CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
CONFIG_FRAME_WARN=1024
diff --git a/tools/testing/selftests/wireguard/qemu/init.c b/tools/testing/selftests/wireguard/qemu/init.c
index 51e5dde..90bc981 100644
--- a/tools/testing/selftests/wireguard/qemu/init.c
+++ b/tools/testing/selftests/wireguard/qemu/init.c
@@ -21,6 +21,7 @@
#include <sys/reboot.h>
#include <sys/utsname.h>
#include <sys/sendfile.h>
+#include <sys/sysmacros.h>
#include <linux/random.h>
#include <linux/version.h>
diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index 9cca302..af9323a 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -39,6 +39,7 @@
CONFIG_KALLSYMS=y
CONFIG_BUG=y
CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y
+CONFIG_JUMP_LABEL=y
CONFIG_EMBEDDED=n
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
@@ -55,6 +56,7 @@
CONFIG_NO_HZ_FULL=n
CONFIG_HZ_PERIODIC=n
CONFIG_HIGH_RES_TIMERS=y
+CONFIG_COMPAT_32BIT_TIME=y
CONFIG_ARCH_RANDOM=y
CONFIG_FILE_LOCKING=y
CONFIG_POSIX_TIMERS=y
diff --git a/usr/gen_initramfs_list.sh b/usr/gen_initramfs_list.sh
index 0aad760..2bbac73 100755
--- a/usr/gen_initramfs_list.sh
+++ b/usr/gen_initramfs_list.sh
@@ -128,7 +128,7 @@
str="${ftype} ${name} ${location} ${str}"
;;
"nod")
- local dev=`LC_ALL=C ls -l "${location}"`
+ local dev="`LC_ALL=C ls -l "${location}"`"
local maj=`field 5 ${dev}`
local min=`field 6 ${dev}`
maj=${maj%,}
