Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
"I'm sending this out, in particular, to get the iwlwifi fix
propagated:
1) Fix build due to missing include in i40e driver, from Lucas
Tanure.
2) Memory leak in openvswitch port allocation, from Chirstoph Jaeger.
3) Check DMA mapping errors in myri10ge, from Stanislaw Gruszka.
4) Fix various deadlock scenerios in sunvnet driver, from Sowmini
Varadhan.
5) Fix cxgb4i build failures with incompatible Kconfig settings of
the driver vs ipv6, from Anish Bhatt.
6) Fix generation of ACK packet timestamps in the presence of TSO
which will be split up, from Willem de Bruijn.
7) Don't enable sched scan in iwlwifi driver, it causes firmware
crashes in some revisions. From Emmanuel Grumbach.
8) Revert a macvlan simplification that causes crashes.
9) Handle RTT calculations properly in the presence of repair'd SKBs,
from Andrey Vagin.
10) SIT tunnel lookup uses wrong device index in compares, from
Shmulik Ladkani.
11) Handle MTU reductions in TCP properly for ipv4 mapped ipv6
sockets, from Neal Cardwell.
12) Add missing annotations in rhashtable code, from Thomas Graf.
13) Fix false interpretation of two RTOs as being from the same TCP
loss event in the FRTO code, from Neal Cardwell"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (42 commits)
netlink: Annotate RCU locking for seq_file walker
rhashtable: fix annotations for rht_for_each_entry_rcu()
rhashtable: unexport and make rht_obj() static
rhashtable: RCU annotations for next pointers
tcp: fix ssthresh and undo for consecutive short FRTO episodes
tcp: don't allow syn packets without timestamps to pass tcp_tw_recycle logic
tcp: fix tcp_release_cb() to dispatch via address family for mtu_reduced()
sit: Fix ipip6_tunnel_lookup device matching criteria
net: ethernet: ibm: ehea: Remove duplicate object from Makefile
net: xgene: Check negative return value of xgene_enet_get_ring_size()
tcp: don't use timestamp from repaired skb-s to calculate RTT (v2)
net: xilinx: Remove .owner field for driver
Revert "macvlan: simplify the structure port"
iwlwifi: mvm: disable scheduled scan to prevent firmware crash
xen-netback: remove loop waiting function
xen-netback: don't stop dealloc kthread too early
xen-netback: move NAPI add/remove calls
xen-netback: fix debugfs entry creation
xen-netback: fix debugfs write length check
net-timestamp: fix missing tcp fragmentation cases
...
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index af7c40a..e1a8f4e 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -581,7 +581,11 @@
struct xgene_enet_desc_ring *ring;
struct xgene_enet_pdata *pdata = netdev_priv(ndev);
struct device *dev = ndev_to_dev(ndev);
- u32 size;
+ int size;
+
+ size = xgene_enet_get_ring_size(dev, cfgsize);
+ if (size < 0)
+ return NULL;
ring = devm_kzalloc(dev, sizeof(struct xgene_enet_desc_ring),
GFP_KERNEL);
@@ -593,7 +597,6 @@
ring->cfgsize = cfgsize;
ring->id = ring_id;
- size = xgene_enet_get_ring_size(dev, cfgsize);
ring->desc_addr = dma_zalloc_coherent(dev, size, &ring->dma,
GFP_KERNEL);
if (!ring->desc_addr) {
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index a3dd5dc..4296b3d26 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14093,8 +14093,9 @@
spin_lock_bh(&tp->lock);
if (!tp->hw_stats) {
+ *stats = tp->net_stats_prev;
spin_unlock_bh(&tp->lock);
- return &tp->net_stats_prev;
+ return stats;
}
tg3_get_nstats(tp, stats);
diff --git a/drivers/net/ethernet/ibm/ehea/Makefile b/drivers/net/ethernet/ibm/ehea/Makefile
index 775d996..cd473e2 100644
--- a/drivers/net/ethernet/ibm/ehea/Makefile
+++ b/drivers/net/ethernet/ibm/ehea/Makefile
@@ -1,6 +1,6 @@
#
# Makefile for the eHEA ethernet device driver for IBM eServer System p
#
-ehea-y = ehea_main.o ehea_phyp.o ehea_qmr.o ehea_ethtool.o ehea_phyp.o
+ehea-y = ehea_main.o ehea_phyp.o ehea_qmr.o ehea_ethtool.o
obj-$(CONFIG_EHEA) += ehea.o
diff --git a/drivers/net/ethernet/intel/e1000e/manage.c b/drivers/net/ethernet/intel/e1000e/manage.c
index 5885603..06edfca 100644
--- a/drivers/net/ethernet/intel/e1000e/manage.c
+++ b/drivers/net/ethernet/intel/e1000e/manage.c
@@ -47,7 +47,7 @@
* e1000_mng_enable_host_if - Checks host interface is enabled
* @hw: pointer to the HW structure
*
- * Returns E1000_success upon success, else E1000_ERR_HOST_INTERFACE_COMMAND
+ * Returns 0 upon success, else -E1000_ERR_HOST_INTERFACE_COMMAND
*
* This function checks whether the HOST IF is enabled for command operation
* and also checks whether the previous command is completed. It busy waits
@@ -78,7 +78,7 @@
}
if (i == E1000_MNG_DHCP_COMMAND_TIMEOUT) {
- e_dbg("Previous command timeout failed .\n");
+ e_dbg("Previous command timeout failed.\n");
return -E1000_ERR_HOST_INTERFACE_COMMAND;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
index 6938fc1a..5d01db1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
@@ -33,6 +33,7 @@
#include <scsi/fc/fc_fcoe.h>
#include <scsi/libfc.h>
#include <scsi/libfcoe.h>
+#include <uapi/linux/dcbnl.h>
#include "i40e.h"
#include "i40e_fcoe.h"
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 51bc030..871474f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4415,13 +4415,13 @@
switch (vsi->back->hw.phy.link_info.link_speed) {
case I40E_LINK_SPEED_40GB:
- strncpy(speed, "40 Gbps", SPEED_SIZE);
+ strlcpy(speed, "40 Gbps", SPEED_SIZE);
break;
case I40E_LINK_SPEED_10GB:
- strncpy(speed, "10 Gbps", SPEED_SIZE);
+ strlcpy(speed, "10 Gbps", SPEED_SIZE);
break;
case I40E_LINK_SPEED_1GB:
- strncpy(speed, "1000 Mbps", SPEED_SIZE);
+ strlcpy(speed, "1000 Mbps", SPEED_SIZE);
break;
default:
break;
@@ -4429,16 +4429,16 @@
switch (vsi->back->hw.fc.current_mode) {
case I40E_FC_FULL:
- strncpy(fc, "RX/TX", FC_SIZE);
+ strlcpy(fc, "RX/TX", FC_SIZE);
break;
case I40E_FC_TX_PAUSE:
- strncpy(fc, "TX", FC_SIZE);
+ strlcpy(fc, "TX", FC_SIZE);
break;
case I40E_FC_RX_PAUSE:
- strncpy(fc, "RX", FC_SIZE);
+ strlcpy(fc, "RX", FC_SIZE);
break;
default:
- strncpy(fc, "None", FC_SIZE);
+ strlcpy(fc, "None", FC_SIZE);
break;
}
@@ -5839,7 +5839,7 @@
dv.minor_version = DRV_VERSION_MINOR;
dv.build_version = DRV_VERSION_BUILD;
dv.subbuild_version = 0;
- strncpy(dv.driver_string, DRV_VERSION, sizeof(dv.driver_string));
+ strlcpy(dv.driver_string, DRV_VERSION, sizeof(dv.driver_string));
i40e_aq_send_driver_version(&pf->hw, &dv, NULL);
}
@@ -6293,7 +6293,7 @@
if (alloc_qvectors) {
/* allocate memory for q_vector pointers */
- size = sizeof(struct i40e_q_vectors *) * vsi->num_q_vectors;
+ size = sizeof(struct i40e_q_vector *) * vsi->num_q_vectors;
vsi->q_vectors = kzalloc(size, GFP_KERNEL);
if (!vsi->q_vectors) {
ret = -ENOMEM;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 97bda3d..25c4f9a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -251,9 +251,9 @@
*
* Writes a 16 bit words buffer to the Shadow RAM using the admin command.
**/
-i40e_status i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer,
- u32 offset, u16 words, void *data,
- bool last_command)
+static i40e_status i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer,
+ u32 offset, u16 words, void *data,
+ bool last_command)
{
i40e_status ret_code = I40E_ERR_NVM;
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 69c26f0..679db02 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -873,6 +873,10 @@
return -ENOMEM;
dmatest_bus = pci_map_page(mgp->pdev, dmatest_page, 0, PAGE_SIZE,
DMA_BIDIRECTIONAL);
+ if (unlikely(pci_dma_mapping_error(mgp->pdev, dmatest_bus))) {
+ __free_page(dmatest_page);
+ return -ENOMEM;
+ }
/* Run a small DMA test.
* The magic multipliers to the length tell the firmware
@@ -1294,6 +1298,7 @@
int bytes, int watchdog)
{
struct page *page;
+ dma_addr_t bus;
int idx;
#if MYRI10GE_ALLOC_SIZE > 4096
int end_offset;
@@ -1318,11 +1323,21 @@
rx->watchdog_needed = 1;
return;
}
+
+ bus = pci_map_page(mgp->pdev, page, 0,
+ MYRI10GE_ALLOC_SIZE,
+ PCI_DMA_FROMDEVICE);
+ if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) {
+ __free_pages(page, MYRI10GE_ALLOC_ORDER);
+ if (rx->fill_cnt - rx->cnt < 16)
+ rx->watchdog_needed = 1;
+ return;
+ }
+
rx->page = page;
rx->page_offset = 0;
- rx->bus = pci_map_page(mgp->pdev, page, 0,
- MYRI10GE_ALLOC_SIZE,
- PCI_DMA_FROMDEVICE);
+ rx->bus = bus;
+
}
rx->info[idx].page = rx->page;
rx->info[idx].page_offset = rx->page_offset;
@@ -2764,6 +2779,35 @@
mb();
}
+static void myri10ge_unmap_tx_dma(struct myri10ge_priv *mgp,
+ struct myri10ge_tx_buf *tx, int idx)
+{
+ unsigned int len;
+ int last_idx;
+
+ /* Free any DMA resources we've alloced and clear out the skb slot */
+ last_idx = (idx + 1) & tx->mask;
+ idx = tx->req & tx->mask;
+ do {
+ len = dma_unmap_len(&tx->info[idx], len);
+ if (len) {
+ if (tx->info[idx].skb != NULL)
+ pci_unmap_single(mgp->pdev,
+ dma_unmap_addr(&tx->info[idx],
+ bus), len,
+ PCI_DMA_TODEVICE);
+ else
+ pci_unmap_page(mgp->pdev,
+ dma_unmap_addr(&tx->info[idx],
+ bus), len,
+ PCI_DMA_TODEVICE);
+ dma_unmap_len_set(&tx->info[idx], len, 0);
+ tx->info[idx].skb = NULL;
+ }
+ idx = (idx + 1) & tx->mask;
+ } while (idx != last_idx);
+}
+
/*
* Transmit a packet. We need to split the packet so that a single
* segment does not cross myri10ge->tx_boundary, so this makes segment
@@ -2787,7 +2831,7 @@
u32 low;
__be32 high_swapped;
unsigned int len;
- int idx, last_idx, avail, frag_cnt, frag_idx, count, mss, max_segments;
+ int idx, avail, frag_cnt, frag_idx, count, mss, max_segments;
u16 pseudo_hdr_offset, cksum_offset, queue;
int cum_len, seglen, boundary, rdma_count;
u8 flags, odd_flag;
@@ -2884,9 +2928,12 @@
/* map the skb for DMA */
len = skb_headlen(skb);
+ bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE);
+ if (unlikely(pci_dma_mapping_error(mgp->pdev, bus)))
+ goto drop;
+
idx = tx->req & tx->mask;
tx->info[idx].skb = skb;
- bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE);
dma_unmap_addr_set(&tx->info[idx], bus, bus);
dma_unmap_len_set(&tx->info[idx], len, len);
@@ -2985,12 +3032,16 @@
break;
/* map next fragment for DMA */
- idx = (count + tx->req) & tx->mask;
frag = &skb_shinfo(skb)->frags[frag_idx];
frag_idx++;
len = skb_frag_size(frag);
bus = skb_frag_dma_map(&mgp->pdev->dev, frag, 0, len,
DMA_TO_DEVICE);
+ if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) {
+ myri10ge_unmap_tx_dma(mgp, tx, idx);
+ goto drop;
+ }
+ idx = (count + tx->req) & tx->mask;
dma_unmap_addr_set(&tx->info[idx], bus, bus);
dma_unmap_len_set(&tx->info[idx], len, len);
}
@@ -3021,31 +3072,8 @@
return NETDEV_TX_OK;
abort_linearize:
- /* Free any DMA resources we've alloced and clear out the skb
- * slot so as to not trip up assertions, and to avoid a
- * double-free if linearizing fails */
+ myri10ge_unmap_tx_dma(mgp, tx, idx);
- last_idx = (idx + 1) & tx->mask;
- idx = tx->req & tx->mask;
- tx->info[idx].skb = NULL;
- do {
- len = dma_unmap_len(&tx->info[idx], len);
- if (len) {
- if (tx->info[idx].skb != NULL)
- pci_unmap_single(mgp->pdev,
- dma_unmap_addr(&tx->info[idx],
- bus), len,
- PCI_DMA_TODEVICE);
- else
- pci_unmap_page(mgp->pdev,
- dma_unmap_addr(&tx->info[idx],
- bus), len,
- PCI_DMA_TODEVICE);
- dma_unmap_len_set(&tx->info[idx], len, 0);
- tx->info[idx].skb = NULL;
- }
- idx = (idx + 1) & tx->mask;
- } while (idx != last_idx);
if (skb_is_gso(skb)) {
netdev_err(mgp->dev, "TSO but wanted to linearize?!?!?\n");
goto drop;
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index d813bfb..23c89ab 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -32,6 +32,11 @@
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_MODULE_VERSION);
+/* Heuristic for the number of times to exponentially backoff and
+ * retry sending an LDC trigger when EAGAIN is encountered
+ */
+#define VNET_MAX_RETRIES 10
+
/* Ordered from largest major to lowest */
static struct vio_version vnet_versions[] = {
{ .major = 1, .minor = 0 },
@@ -260,6 +265,7 @@
.state = vio_dring_state,
};
int err, delay;
+ int retries = 0;
hdr.seq = dr->snd_nxt;
delay = 1;
@@ -272,6 +278,13 @@
udelay(delay);
if ((delay <<= 1) > 128)
delay = 128;
+ if (retries++ > VNET_MAX_RETRIES) {
+ pr_info("ECONNRESET %x:%x:%x:%x:%x:%x\n",
+ port->raddr[0], port->raddr[1],
+ port->raddr[2], port->raddr[3],
+ port->raddr[4], port->raddr[5]);
+ err = -ECONNRESET;
+ }
} while (err == -EAGAIN);
return err;
@@ -475,8 +488,9 @@
return 0;
}
-static void maybe_tx_wakeup(struct vnet *vp)
+static void maybe_tx_wakeup(unsigned long param)
{
+ struct vnet *vp = (struct vnet *)param;
struct net_device *dev = vp->dev;
netif_tx_lock(dev);
@@ -573,8 +587,13 @@
break;
}
spin_unlock(&vio->lock);
+ /* Kick off a tasklet to wake the queue. We cannot call
+ * maybe_tx_wakeup directly here because we could deadlock on
+ * netif_tx_lock() with dev_watchdog()
+ */
if (unlikely(tx_wakeup && err != -ECONNRESET))
- maybe_tx_wakeup(port->vp);
+ tasklet_schedule(&port->vp->vnet_tx_wakeup);
+
local_irq_restore(flags);
}
@@ -593,6 +612,7 @@
.end_idx = (u32) -1,
};
int err, delay;
+ int retries = 0;
hdr.seq = dr->snd_nxt;
delay = 1;
@@ -605,6 +625,8 @@
udelay(delay);
if ((delay <<= 1) > 128)
delay = 128;
+ if (retries++ > VNET_MAX_RETRIES)
+ break;
} while (err == -EAGAIN);
return err;
@@ -691,7 +713,15 @@
memset(tx_buf+VNET_PACKET_SKIP+skb->len, 0, len - skb->len);
}
- d->hdr.ack = VIO_ACK_ENABLE;
+ /* We don't rely on the ACKs to free the skb in vnet_start_xmit(),
+ * thus it is safe to not set VIO_ACK_ENABLE for each transmission:
+ * the protocol itself does not require it as long as the peer
+ * sends a VIO_SUBTYPE_ACK for VIO_DRING_STOPPED.
+ *
+ * An ACK for every packet in the ring is expensive as the
+ * sending of LDC messages is slow and affects performance.
+ */
+ d->hdr.ack = VIO_ACK_DISABLE;
d->size = len;
d->ncookies = port->tx_bufs[dr->prod].ncookies;
for (i = 0; i < d->ncookies; i++)
@@ -1046,6 +1076,7 @@
vp = netdev_priv(dev);
spin_lock_init(&vp->lock);
+ tasklet_init(&vp->vnet_tx_wakeup, maybe_tx_wakeup, (unsigned long)vp);
vp->dev = dev;
INIT_LIST_HEAD(&vp->port_list);
@@ -1105,6 +1136,7 @@
vp = list_first_entry(&vnet_list, struct vnet, list);
list_del(&vp->list);
dev = vp->dev;
+ tasklet_kill(&vp->vnet_tx_wakeup);
/* vio_unregister_driver() should have cleaned up port_list */
BUG_ON(!list_empty(&vp->port_list));
unregister_netdev(dev);
diff --git a/drivers/net/ethernet/sun/sunvnet.h b/drivers/net/ethernet/sun/sunvnet.h
index d347a5b..de5c2c6 100644
--- a/drivers/net/ethernet/sun/sunvnet.h
+++ b/drivers/net/ethernet/sun/sunvnet.h
@@ -1,6 +1,8 @@
#ifndef _SUNVNET_H
#define _SUNVNET_H
+#include <linux/interrupt.h>
+
#define DESC_NCOOKIES(entry_size) \
((entry_size) - sizeof(struct vio_net_desc))
@@ -78,6 +80,8 @@
struct list_head list;
u64 local_mac;
+
+ struct tasklet_struct vnet_tx_wakeup;
};
#endif /* _SUNVNET_H */
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 36f4459..fda5891 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -1170,7 +1170,6 @@
.probe = temac_of_probe,
.remove = temac_of_remove,
.driver = {
- .owner = THIS_MODULE,
.name = "xilinx_temac",
.of_match_table = temac_of_match,
},
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 30e8608..c8fd941 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1645,7 +1645,6 @@
.probe = axienet_of_probe,
.remove = axienet_of_remove,
.driver = {
- .owner = THIS_MODULE,
.name = "xilinx_axienet",
.of_match_table = axienet_of_match,
},
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 782bb93..28dbbdc 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -1245,7 +1245,6 @@
static struct platform_driver xemaclite_of_driver = {
.driver = {
.name = DRIVER_NAME,
- .owner = THIS_MODULE,
.of_match_table = xemaclite_of_match,
},
.probe = xemaclite_of_probe,
diff --git a/drivers/net/irda/donauboe.c b/drivers/net/irda/donauboe.c
index 768dfe9..6d3e209 100644
--- a/drivers/net/irda/donauboe.c
+++ b/drivers/net/irda/donauboe.c
@@ -1755,17 +1755,4 @@
.resume = toshoboe_wakeup
};
-static int __init
-donauboe_init (void)
-{
- return pci_register_driver(&donauboe_pci_driver);
-}
-
-static void __exit
-donauboe_cleanup (void)
-{
- pci_unregister_driver(&donauboe_pci_driver);
-}
-
-module_init(donauboe_init);
-module_exit(donauboe_cleanup);
+module_pci_driver(donauboe_pci_driver);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index ef8a5c2..60e4ca0 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -45,10 +45,9 @@
struct sk_buff_head bc_queue;
struct work_struct bc_work;
bool passthru;
+ int count;
};
-#define MACVLAN_PORT_IS_EMPTY(port) list_empty(&port->vlans)
-
struct macvlan_skb_cb {
const struct macvlan_dev *src;
};
@@ -667,7 +666,8 @@
free_percpu(vlan->pcpu_stats);
- if (MACVLAN_PORT_IS_EMPTY(port))
+ port->count -= 1;
+ if (!port->count)
macvlan_port_destroy(port->dev);
}
@@ -1020,12 +1020,13 @@
vlan->flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]);
if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
- if (!MACVLAN_PORT_IS_EMPTY(port))
+ if (port->count)
return -EINVAL;
port->passthru = true;
eth_hw_addr_inherit(dev, lowerdev);
}
+ port->count += 1;
err = register_netdevice(dev);
if (err < 0)
goto destroy_port;
@@ -1043,7 +1044,8 @@
unregister_netdev:
unregister_netdevice(dev);
destroy_port:
- if (MACVLAN_PORT_IS_EMPTY(port))
+ port->count -= 1;
+ if (!port->count)
macvlan_port_destroy(lowerdev);
return err;
diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h
index 8596aba..237d0cd 100644
--- a/drivers/net/wireless/ath/carl9170/carl9170.h
+++ b/drivers/net/wireless/ath/carl9170/carl9170.h
@@ -256,6 +256,7 @@
atomic_t rx_work_urbs;
atomic_t rx_pool_urbs;
kernel_ulong_t features;
+ bool usb_ep_cmd_is_bulk;
/* firmware settings */
struct completion fw_load_wait;
diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index f35c7f3..c9f9331 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -621,9 +621,16 @@
goto err_free;
}
- usb_fill_int_urb(urb, ar->udev, usb_sndintpipe(ar->udev,
- AR9170_USB_EP_CMD), cmd, cmd->hdr.len + 4,
- carl9170_usb_cmd_complete, ar, 1);
+ if (ar->usb_ep_cmd_is_bulk)
+ usb_fill_bulk_urb(urb, ar->udev,
+ usb_sndbulkpipe(ar->udev, AR9170_USB_EP_CMD),
+ cmd, cmd->hdr.len + 4,
+ carl9170_usb_cmd_complete, ar);
+ else
+ usb_fill_int_urb(urb, ar->udev,
+ usb_sndintpipe(ar->udev, AR9170_USB_EP_CMD),
+ cmd, cmd->hdr.len + 4,
+ carl9170_usb_cmd_complete, ar, 1);
if (free_buf)
urb->transfer_flags |= URB_FREE_BUFFER;
@@ -1032,9 +1039,10 @@
static int carl9170_usb_probe(struct usb_interface *intf,
const struct usb_device_id *id)
{
+ struct usb_endpoint_descriptor *ep;
struct ar9170 *ar;
struct usb_device *udev;
- int err;
+ int i, err;
err = usb_reset_device(interface_to_usbdev(intf));
if (err)
@@ -1050,6 +1058,21 @@
ar->intf = intf;
ar->features = id->driver_info;
+ /* We need to remember the type of endpoint 4 because it differs
+ * between high- and full-speed configuration. The high-speed
+ * configuration specifies it as interrupt and the full-speed
+ * configuration as bulk endpoint. This information is required
+ * later when sending urbs to that endpoint.
+ */
+ for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; ++i) {
+ ep = &intf->cur_altsetting->endpoint[i].desc;
+
+ if (usb_endpoint_num(ep) == AR9170_USB_EP_CMD &&
+ usb_endpoint_dir_out(ep) &&
+ usb_endpoint_type(ep) == USB_ENDPOINT_XFER_BULK)
+ ar->usb_ep_cmd_is_bulk = true;
+ }
+
usb_set_intfdata(intf, ar);
SET_IEEE80211_DEV(ar->hw, &intf->dev);
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c
index 535c7eb..8f8b937 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c
@@ -1318,6 +1318,8 @@
msgbuf->nrof_flowrings = if_msgbuf->nrof_flowrings;
msgbuf->flowring_dma_handle = kzalloc(msgbuf->nrof_flowrings *
sizeof(*msgbuf->flowring_dma_handle), GFP_ATOMIC);
+ if (!msgbuf->flowring_dma_handle)
+ goto fail;
msgbuf->rx_dataoffset = if_msgbuf->rx_dataoffset;
msgbuf->max_rxbufpost = if_msgbuf->max_rxbufpost;
@@ -1362,6 +1364,7 @@
kfree(msgbuf->flow_map);
kfree(msgbuf->txstatus_done_map);
brcmf_msgbuf_release_pktids(msgbuf);
+ kfree(msgbuf->flowring_dma_handle);
if (msgbuf->ioctbuf)
dma_free_coherent(drvr->bus_if->dev,
BRCMF_TX_IOCTL_MAX_MSG_SIZE,
@@ -1391,6 +1394,7 @@
BRCMF_TX_IOCTL_MAX_MSG_SIZE,
msgbuf->ioctbuf, msgbuf->ioctbuf_handle);
brcmf_msgbuf_release_pktids(msgbuf);
+ kfree(msgbuf->flowring_dma_handle);
kfree(msgbuf);
drvr->proto->pd = NULL;
}
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/brcm80211/brcmfmac/pcie.c
index bc972c0..e5101b2 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/pcie.c
@@ -591,12 +591,13 @@
}
if (dtoh_mb_data & BRCMF_D2H_DEV_DS_EXIT_NOTE)
brcmf_dbg(PCIE, "D2H_MB_DATA: DEEP SLEEP EXIT\n");
- if (dtoh_mb_data & BRCMF_D2H_DEV_D3_ACK)
+ if (dtoh_mb_data & BRCMF_D2H_DEV_D3_ACK) {
brcmf_dbg(PCIE, "D2H_MB_DATA: D3 ACK\n");
if (waitqueue_active(&devinfo->mbdata_resp_wait)) {
devinfo->mbdata_completed = true;
wake_up(&devinfo->mbdata_resp_wait);
}
+ }
}
diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c
index c5aa404..389656b 100644
--- a/drivers/net/wireless/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/ipw2x00/ipw2200.c
@@ -9853,6 +9853,7 @@
strncpy(extra, "unknown", MAX_WX_STRING);
break;
}
+ extra[MAX_WX_STRING - 1] = '\0';
IPW_DEBUG_WX("PRIV GET MODE: %s\n", extra);
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index 0d6a8b7..7c87965 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -396,7 +396,8 @@
else
hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
- hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_SCHED_SCAN;
+ /* TODO: enable that only for firmwares that don't crash */
+ /* hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_SCHED_SCAN; */
hw->wiphy->max_sched_scan_ssids = PROBE_OPTION_MAX;
hw->wiphy->max_match_sets = IWL_SCAN_MAX_PROFILES;
/* we create the 802.11 header and zero length SSID IE. */
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index ef3026f..d4eb8d2 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -165,6 +165,7 @@
u16 dealloc_ring[MAX_PENDING_REQS];
struct task_struct *dealloc_task;
wait_queue_head_t dealloc_wq;
+ atomic_t inflight_packets;
/* Use kthread for guest RX */
struct task_struct *task;
@@ -329,4 +330,8 @@
extern struct dentry *xen_netback_dbg_root;
#endif
+void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue,
+ struct sk_buff *skb);
+void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue);
+
#endif /* __XEN_NETBACK__COMMON_H__ */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index bfd10cb..e29e15dc 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -43,6 +43,23 @@
#define XENVIF_QUEUE_LENGTH 32
#define XENVIF_NAPI_WEIGHT 64
+/* This function is used to set SKBTX_DEV_ZEROCOPY as well as
+ * increasing the inflight counter. We need to increase the inflight
+ * counter because core driver calls into xenvif_zerocopy_callback
+ * which calls xenvif_skb_zerocopy_complete.
+ */
+void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue,
+ struct sk_buff *skb)
+{
+ skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ atomic_inc(&queue->inflight_packets);
+}
+
+void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue)
+{
+ atomic_dec(&queue->inflight_packets);
+}
+
static inline void xenvif_stop_queue(struct xenvif_queue *queue)
{
struct net_device *dev = queue->vif->dev;
@@ -524,9 +541,6 @@
init_timer(&queue->rx_stalled);
- netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll,
- XENVIF_NAPI_WEIGHT);
-
return 0;
}
@@ -560,6 +574,7 @@
init_waitqueue_head(&queue->wq);
init_waitqueue_head(&queue->dealloc_wq);
+ atomic_set(&queue->inflight_packets, 0);
if (tx_evtchn == rx_evtchn) {
/* feature-split-event-channels == 0 */
@@ -614,6 +629,9 @@
wake_up_process(queue->task);
wake_up_process(queue->dealloc_task);
+ netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll,
+ XENVIF_NAPI_WEIGHT);
+
return 0;
err_rx_unbind:
@@ -642,25 +660,6 @@
rtnl_unlock();
}
-static void xenvif_wait_unmap_timeout(struct xenvif_queue *queue,
- unsigned int worst_case_skb_lifetime)
-{
- int i, unmap_timeout = 0;
-
- for (i = 0; i < MAX_PENDING_REQS; ++i) {
- if (queue->grant_tx_handle[i] != NETBACK_INVALID_HANDLE) {
- unmap_timeout++;
- schedule_timeout(msecs_to_jiffies(1000));
- if (unmap_timeout > worst_case_skb_lifetime &&
- net_ratelimit())
- netdev_err(queue->vif->dev,
- "Page still granted! Index: %x\n",
- i);
- i = -1;
- }
- }
-}
-
void xenvif_disconnect(struct xenvif *vif)
{
struct xenvif_queue *queue = NULL;
@@ -672,6 +671,8 @@
for (queue_index = 0; queue_index < num_queues; ++queue_index) {
queue = &vif->queues[queue_index];
+ netif_napi_del(&queue->napi);
+
if (queue->task) {
del_timer_sync(&queue->rx_stalled);
kthread_stop(queue->task);
@@ -704,7 +705,6 @@
void xenvif_deinit_queue(struct xenvif_queue *queue)
{
free_xenballooned_pages(MAX_PENDING_REQS, queue->mmap_pages);
- netif_napi_del(&queue->napi);
}
void xenvif_free(struct xenvif *vif)
@@ -712,21 +712,11 @@
struct xenvif_queue *queue = NULL;
unsigned int num_queues = vif->num_queues;
unsigned int queue_index;
- /* Here we want to avoid timeout messages if an skb can be legitimately
- * stuck somewhere else. Realistically this could be an another vif's
- * internal or QDisc queue. That another vif also has this
- * rx_drain_timeout_msecs timeout, so give it time to drain out.
- * Although if that other guest wakes up just before its timeout happens
- * and takes only one skb from QDisc, it can hold onto other skbs for a
- * longer period.
- */
- unsigned int worst_case_skb_lifetime = (rx_drain_timeout_msecs/1000);
unregister_netdev(vif->dev);
for (queue_index = 0; queue_index < num_queues; ++queue_index) {
queue = &vif->queues[queue_index];
- xenvif_wait_unmap_timeout(queue, worst_case_skb_lifetime);
xenvif_deinit_queue(queue);
}
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 4734472..08f659965 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1525,10 +1525,12 @@
/* remove traces of mapped pages and frag_list */
skb_frag_list_init(skb);
uarg = skb_shinfo(skb)->destructor_arg;
+ /* increase inflight counter to offset decrement in callback */
+ atomic_inc(&queue->inflight_packets);
uarg->callback(uarg, true);
skb_shinfo(skb)->destructor_arg = NULL;
- skb_shinfo(nskb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ xenvif_skb_zerocopy_prepare(queue, nskb);
kfree_skb(nskb);
return 0;
@@ -1589,7 +1591,7 @@
if (net_ratelimit())
netdev_err(queue->vif->dev,
"Not enough memory to consolidate frag_list!\n");
- skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ xenvif_skb_zerocopy_prepare(queue, skb);
kfree_skb(skb);
continue;
}
@@ -1609,7 +1611,7 @@
"Can't setup checksum in net_tx_action\n");
/* We have to set this flag to trigger the callback */
if (skb_shinfo(skb)->destructor_arg)
- skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ xenvif_skb_zerocopy_prepare(queue, skb);
kfree_skb(skb);
continue;
}
@@ -1641,7 +1643,7 @@
* skb. E.g. the __pskb_pull_tail earlier can do such thing.
*/
if (skb_shinfo(skb)->destructor_arg) {
- skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ xenvif_skb_zerocopy_prepare(queue, skb);
queue->stats.tx_zerocopy_sent++;
}
@@ -1681,6 +1683,7 @@
queue->stats.tx_zerocopy_success++;
else
queue->stats.tx_zerocopy_fail++;
+ xenvif_skb_zerocopy_complete(queue);
}
static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue)
@@ -2058,15 +2061,24 @@
return 0;
}
+static bool xenvif_dealloc_kthread_should_stop(struct xenvif_queue *queue)
+{
+ /* Dealloc thread must remain running until all inflight
+ * packets complete.
+ */
+ return kthread_should_stop() &&
+ !atomic_read(&queue->inflight_packets);
+}
+
int xenvif_dealloc_kthread(void *data)
{
struct xenvif_queue *queue = data;
- while (!kthread_should_stop()) {
+ for (;;) {
wait_event_interruptible(queue->dealloc_wq,
tx_dealloc_work_todo(queue) ||
- kthread_should_stop());
- if (kthread_should_stop())
+ xenvif_dealloc_kthread_should_stop(queue));
+ if (xenvif_dealloc_kthread_should_stop(queue))
break;
xenvif_tx_dealloc_action(queue);
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 580517d..9c47b89 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -116,6 +116,7 @@
}
#define XENVIF_KICK_STR "kick"
+#define BUFFER_SIZE 32
static ssize_t
xenvif_write_io_ring(struct file *filp, const char __user *buf, size_t count,
@@ -124,22 +125,24 @@
struct xenvif_queue *queue =
((struct seq_file *)filp->private_data)->private;
int len;
- char write[sizeof(XENVIF_KICK_STR)];
+ char write[BUFFER_SIZE];
/* don't allow partial writes and check the length */
if (*ppos != 0)
return 0;
- if (count < sizeof(XENVIF_KICK_STR) - 1)
+ if (count >= sizeof(write))
return -ENOSPC;
len = simple_write_to_buffer(write,
- sizeof(write),
+ sizeof(write) - 1,
ppos,
buf,
count);
if (len < 0)
return len;
+ write[len] = '\0';
+
if (!strncmp(write, XENVIF_KICK_STR, sizeof(XENVIF_KICK_STR) - 1))
xenvif_interrupt(0, (void *)queue);
else {
@@ -171,10 +174,9 @@
.write = xenvif_write_io_ring,
};
-static void xenvif_debugfs_addif(struct xenvif_queue *queue)
+static void xenvif_debugfs_addif(struct xenvif *vif)
{
struct dentry *pfile;
- struct xenvif *vif = queue->vif;
int i;
if (IS_ERR_OR_NULL(xen_netback_dbg_root))
@@ -733,11 +735,12 @@
be->vif->num_queues = queue_index;
goto err;
}
-#ifdef CONFIG_DEBUG_FS
- xenvif_debugfs_addif(queue);
-#endif /* CONFIG_DEBUG_FS */
}
+#ifdef CONFIG_DEBUG_FS
+ xenvif_debugfs_addif(be->vif);
+#endif /* CONFIG_DEBUG_FS */
+
/* Initialisation completed, tell core driver the number of
* active queues.
*/
diff --git a/drivers/scsi/cxgbi/cxgb3i/Kconfig b/drivers/scsi/cxgbi/cxgb3i/Kconfig
index 6bbc36f..e460398 100644
--- a/drivers/scsi/cxgbi/cxgb3i/Kconfig
+++ b/drivers/scsi/cxgbi/cxgb3i/Kconfig
@@ -1,6 +1,6 @@
config SCSI_CXGB3_ISCSI
tristate "Chelsio T3 iSCSI support"
- depends on PCI && INET
+ depends on PCI && INET && (IPV6 || IPV6=n)
select NETDEVICES
select ETHERNET
select NET_VENDOR_CHELSIO
diff --git a/drivers/scsi/cxgbi/cxgb4i/Kconfig b/drivers/scsi/cxgbi/cxgb4i/Kconfig
index 16b2c7d..8c4e423 100644
--- a/drivers/scsi/cxgbi/cxgb4i/Kconfig
+++ b/drivers/scsi/cxgbi/cxgb4i/Kconfig
@@ -1,6 +1,6 @@
config SCSI_CXGB4_ISCSI
tristate "Chelsio T4 iSCSI support"
- depends on PCI && INET
+ depends on PCI && INET && (IPV6 || IPV6=n)
select NETDEVICES
select ETHERNET
select NET_VENDOR_CHELSIO
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 9cda293..36826c0 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -21,7 +21,7 @@
#include <linux/rculist.h>
struct rhash_head {
- struct rhash_head *next;
+ struct rhash_head __rcu *next;
};
#define INIT_HASH_HEAD(ptr) ((ptr)->next = NULL)
@@ -97,7 +97,7 @@
void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node, gfp_t);
bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node, gfp_t);
void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj,
- struct rhash_head **pprev, gfp_t flags);
+ struct rhash_head __rcu **pprev, gfp_t flags);
bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size);
bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size);
@@ -117,18 +117,12 @@
#define rht_dereference_rcu(p, ht) \
rcu_dereference_check(p, lockdep_rht_mutex_is_held(ht))
-/* Internal, use rht_obj() instead */
#define rht_entry(ptr, type, member) container_of(ptr, type, member)
#define rht_entry_safe(ptr, type, member) \
({ \
typeof(ptr) __ptr = (ptr); \
__ptr ? rht_entry(__ptr, type, member) : NULL; \
})
-#define rht_entry_safe_rcu(ptr, type, member) \
-({ \
- typeof(*ptr) __rcu *__ptr = (typeof(*ptr) __rcu __force *)ptr; \
- __ptr ? container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member) : NULL; \
-})
#define rht_next_entry_safe(pos, ht, member) \
({ \
@@ -205,9 +199,10 @@
* traversal is guarded by rcu_read_lock().
*/
#define rht_for_each_entry_rcu(pos, head, member) \
- for (pos = rht_entry_safe_rcu(head, typeof(*(pos)), member); \
+ for (pos = rht_entry_safe(rcu_dereference_raw(head), \
+ typeof(*(pos)), member); \
pos; \
- pos = rht_entry_safe_rcu((pos)->member.next, \
- typeof(*(pos)), member))
+ pos = rht_entry_safe(rcu_dereference_raw((pos)->member.next), \
+ typeof(*(pos)), member))
#endif /* _LINUX_RHASHTABLE_H */
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 7a43138..5fbe656 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -62,6 +62,7 @@
void (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
int (*bind_conflict)(const struct sock *sk,
const struct inet_bind_bucket *tb, bool relax);
+ void (*mtu_reduced)(struct sock *sk);
};
/** inet_connection_sock - INET connection oriented sock
diff --git a/include/net/sock.h b/include/net/sock.h
index 38805fa..7f2ab72 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -987,7 +987,6 @@
struct sk_buff *skb);
void (*release_cb)(struct sock *sk);
- void (*mtu_reduced)(struct sock *sk);
/* Keeping track of sk's, looking them up, and port selection methods. */
void (*hash)(struct sock *sk);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index dafa1cb..590e01a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -417,7 +417,7 @@
void tcp_init_metrics(struct sock *sk);
void tcp_metrics_init(void);
bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
- bool paws_check);
+ bool paws_check, bool timestamps);
bool tcp_remember_stamp(struct sock *sk);
bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw);
void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst);
@@ -448,6 +448,7 @@
*/
void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
+void tcp_v4_mtu_reduced(struct sock *sk);
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
struct sock *tcp_create_openreq_child(struct sock *sk,
struct request_sock *req,
@@ -705,8 +706,10 @@
#define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */
#define TCPCB_LOST 0x04 /* SKB is lost */
#define TCPCB_TAGBITS 0x07 /* All tag bits */
+#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp) */
#define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */
-#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)
+#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
+ TCPCB_REPAIRED)
__u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
/* 1 byte hole */
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index e6940cf..a2c7881 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -38,16 +38,10 @@
EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);
#endif
-/**
- * rht_obj - cast hash head to outer object
- * @ht: hash table
- * @he: hashed node
- */
-void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he)
+static void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he)
{
return (void *) he - ht->p.head_offset;
}
-EXPORT_SYMBOL_GPL(rht_obj);
static u32 __hashfn(const struct rhashtable *ht, const void *key,
u32 len, u32 hsize)
@@ -386,7 +380,7 @@
* deletion when combined with walking or lookup.
*/
void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj,
- struct rhash_head **pprev, gfp_t flags)
+ struct rhash_head __rcu **pprev, gfp_t flags)
{
struct bucket_table *tbl = rht_dereference(ht->tbl, ht);
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 4c5b8ba..e4853b5 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -833,7 +833,6 @@
loff_t *l)
{
struct hlist_node *e = state->node;
- struct lec_arp_table *tmp;
if (!e)
e = tbl->first;
@@ -842,9 +841,7 @@
--*l;
}
- tmp = container_of(e, struct lec_arp_table, next);
-
- hlist_for_each_entry_from(tmp, next) {
+ for (; e; e = e->next) {
if (--*l < 0)
break;
}
diff --git a/net/atm/svc.c b/net/atm/svc.c
index d8e5d0c2..1ba23f5 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -50,12 +50,12 @@
pr_debug("%p\n", vcc);
if (test_bit(ATM_VF_REGIS, &vcc->flags)) {
- prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
sigd_enq(vcc, as_close, NULL, NULL, NULL);
- while (!test_bit(ATM_VF_RELEASED, &vcc->flags) && sigd) {
+ for (;;) {
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
+ if (test_bit(ATM_VF_RELEASED, &vcc->flags) || !sigd)
+ break;
schedule();
- prepare_to_wait(sk_sleep(sk), &wait,
- TASK_UNINTERRUPTIBLE);
}
finish_wait(sk_sleep(sk), &wait);
}
@@ -126,11 +126,12 @@
}
vcc->local = *addr;
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
sigd_enq(vcc, as_bind, NULL, NULL, &vcc->local);
- while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
- schedule();
+ for (;;) {
prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
+ if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd)
+ break;
+ schedule();
}
finish_wait(sk_sleep(sk), &wait);
clear_bit(ATM_VF_REGIS, &vcc->flags); /* doesn't count */
@@ -202,15 +203,14 @@
}
vcc->remote = *addr;
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
sigd_enq(vcc, as_connect, NULL, NULL, &vcc->remote);
if (flags & O_NONBLOCK) {
- finish_wait(sk_sleep(sk), &wait);
sock->state = SS_CONNECTING;
error = -EINPROGRESS;
goto out;
}
error = 0;
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
schedule();
if (!signal_pending(current)) {
@@ -297,11 +297,12 @@
goto out;
}
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
sigd_enq(vcc, as_listen, NULL, NULL, &vcc->local);
- while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
- schedule();
+ for (;;) {
prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
+ if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd)
+ break;
+ schedule();
}
finish_wait(sk_sleep(sk), &wait);
if (!sigd) {
@@ -387,15 +388,15 @@
}
/* wait should be short, so we ignore the non-blocking flag */
set_bit(ATM_VF_WAITING, &new_vcc->flags);
- prepare_to_wait(sk_sleep(sk_atm(new_vcc)), &wait,
- TASK_UNINTERRUPTIBLE);
sigd_enq(new_vcc, as_accept, old_vcc, NULL, NULL);
- while (test_bit(ATM_VF_WAITING, &new_vcc->flags) && sigd) {
+ for (;;) {
+ prepare_to_wait(sk_sleep(sk_atm(new_vcc)), &wait,
+ TASK_UNINTERRUPTIBLE);
+ if (!test_bit(ATM_VF_WAITING, &new_vcc->flags) || !sigd)
+ break;
release_sock(sk);
schedule();
lock_sock(sk);
- prepare_to_wait(sk_sleep(sk_atm(new_vcc)), &wait,
- TASK_UNINTERRUPTIBLE);
}
finish_wait(sk_sleep(sk_atm(new_vcc)), &wait);
if (!sigd) {
@@ -433,12 +434,14 @@
DEFINE_WAIT(wait);
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
sigd_enq2(vcc, as_modify, NULL, NULL, &vcc->local, qos, 0);
- while (test_bit(ATM_VF_WAITING, &vcc->flags) &&
- !test_bit(ATM_VF_RELEASED, &vcc->flags) && sigd) {
- schedule();
+ for (;;) {
prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
+ if (!test_bit(ATM_VF_WAITING, &vcc->flags) ||
+ test_bit(ATM_VF_RELEASED, &vcc->flags) || !sigd) {
+ break;
+ }
+ schedule();
}
finish_wait(sk_sleep(sk), &wait);
if (!sigd)
@@ -529,18 +532,18 @@
lock_sock(sk);
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
sigd_enq(vcc, as_addparty, NULL, NULL,
(struct sockaddr_atmsvc *) sockaddr);
if (flags & O_NONBLOCK) {
- finish_wait(sk_sleep(sk), &wait);
error = -EINPROGRESS;
goto out;
}
pr_debug("added wait queue\n");
- while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
- schedule();
+ for (;;) {
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd)
+ break;
+ schedule();
}
finish_wait(sk_sleep(sk), &wait);
error = xchg(&sk->sk_err_soft, 0);
@@ -558,11 +561,12 @@
lock_sock(sk);
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
sigd_enq2(vcc, as_dropparty, NULL, NULL, NULL, NULL, ep_ref);
- while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
- schedule();
+ for (;;) {
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd)
+ break;
+ schedule();
}
finish_wait(sk_sleep(sk), &wait);
if (!sigd) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 181b70e..541f26a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1188,13 +1188,6 @@
goto wait_for_memory;
/*
- * All packets are restored as if they have
- * already been sent.
- */
- if (tp->repair)
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
-
- /*
* Check whether we can use HW checksum.
*/
if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
@@ -1203,6 +1196,13 @@
skb_entail(sk, skb);
copy = size_goal;
max = size_goal;
+
+ /* All packets are restored as if they have
+ * already been sent. skb_mstamp isn't set to
+ * avoid wrong rtt estimation.
+ */
+ if (tp->repair)
+ TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
}
/* Try to append data to the end of skb. */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a3d47af..a906e02 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2687,7 +2687,6 @@
*/
static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
{
- struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
bool recovered = !before(tp->snd_una, tp->high_seq);
@@ -2713,12 +2712,9 @@
if (recovered) {
/* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */
- icsk->icsk_retransmits = 0;
tcp_try_undo_recovery(sk);
return;
}
- if (flag & FLAG_DATA_ACKED)
- icsk->icsk_retransmits = 0;
if (tcp_is_reno(tp)) {
/* A Reno DUPACK means new data in F-RTO step 2.b above are
* delivered. Lower inflight to clock out (re)tranmissions.
@@ -3050,10 +3046,15 @@
first_ackt.v64 = 0;
while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
+ struct skb_shared_info *shinfo = skb_shinfo(skb);
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
u8 sacked = scb->sacked;
u32 acked_pcount;
+ if (unlikely(shinfo->tx_flags & SKBTX_ACK_TSTAMP) &&
+ between(shinfo->tskey, prior_snd_una, tp->snd_una - 1))
+ __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+
/* Determine how many packets and what bytes were acked, tso and else */
if (after(scb->end_seq, tp->snd_una)) {
if (tcp_skb_pcount(skb) == 1 ||
@@ -3107,11 +3108,6 @@
tp->retrans_stamp = 0;
}
- if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_ACK_TSTAMP) &&
- between(skb_shinfo(skb)->tskey, prior_snd_una,
- tp->snd_una + 1))
- __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
-
if (!fully_acked)
break;
@@ -3405,8 +3401,10 @@
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
tcp_rearm_rto(sk);
- if (after(ack, prior_snd_una))
+ if (after(ack, prior_snd_una)) {
flag |= FLAG_SND_UNA_ADVANCED;
+ icsk->icsk_retransmits = 0;
+ }
prior_fackets = tp->fackets_out;
@@ -5979,12 +5977,14 @@
* timewait bucket, so that all the necessary checks
* are made in the function processing timewait state.
*/
- if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle) {
+ if (tcp_death_row.sysctl_tw_recycle) {
bool strict;
dst = af_ops->route_req(sk, &fl, req, &strict);
+
if (dst && strict &&
- !tcp_peer_is_proven(req, dst, true)) {
+ !tcp_peer_is_proven(req, dst, true,
+ tmp_opt.saw_tstamp)) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
goto drop_and_release;
}
@@ -5993,7 +5993,8 @@
else if (!sysctl_tcp_syncookies &&
(sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
(sysctl_max_syn_backlog >> 2)) &&
- !tcp_peer_is_proven(req, dst, false)) {
+ !tcp_peer_is_proven(req, dst, false,
+ tmp_opt.saw_tstamp)) {
/* Without syncookies last quarter of
* backlog is filled with destinations,
* proven to be alive.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index dceff5f..cd17f00 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -271,7 +271,7 @@
* It can be called through tcp_release_cb() if socket was owned by user
* at the time tcp_v4_err() was called to handle ICMP message.
*/
-static void tcp_v4_mtu_reduced(struct sock *sk)
+void tcp_v4_mtu_reduced(struct sock *sk)
{
struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
@@ -302,6 +302,7 @@
tcp_simple_retransmit(sk);
} /* else let the usual retransmit timer handle it */
}
+EXPORT_SYMBOL(tcp_v4_mtu_reduced);
static void do_redirect(struct sk_buff *skb, struct sock *sk)
{
@@ -1787,6 +1788,7 @@
.compat_setsockopt = compat_ip_setsockopt,
.compat_getsockopt = compat_ip_getsockopt,
#endif
+ .mtu_reduced = tcp_v4_mtu_reduced,
};
EXPORT_SYMBOL(ipv4_specific);
@@ -2406,7 +2408,6 @@
.sendpage = tcp_sendpage,
.backlog_rcv = tcp_v4_do_rcv,
.release_cb = tcp_release_cb,
- .mtu_reduced = tcp_v4_mtu_reduced,
.hash = inet_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 0d54e59..ed9c9a9 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -576,7 +576,8 @@
tp->snd_cwnd_stamp = tcp_time_stamp;
}
-bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, bool paws_check)
+bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
+ bool paws_check, bool timestamps)
{
struct tcp_metrics_block *tm;
bool ret;
@@ -589,7 +590,8 @@
if (paws_check) {
if (tm &&
(u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL &&
- (s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW)
+ ((s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW ||
+ !timestamps))
ret = false;
else
ret = true;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8fcfc919..5a7c41f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -800,7 +800,7 @@
__sock_put(sk);
}
if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) {
- sk->sk_prot->mtu_reduced(sk);
+ inet_csk(sk)->icsk_af_ops->mtu_reduced(sk);
__sock_put(sk);
}
}
@@ -1069,6 +1069,21 @@
tcp_verify_left_out(tp);
}
+static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2)
+{
+ struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+ if (unlikely(shinfo->tx_flags & SKBTX_ANY_TSTAMP) &&
+ !before(shinfo->tskey, TCP_SKB_CB(skb2)->seq)) {
+ struct skb_shared_info *shinfo2 = skb_shinfo(skb2);
+ u8 tsflags = shinfo->tx_flags & SKBTX_ANY_TSTAMP;
+
+ shinfo->tx_flags &= ~tsflags;
+ shinfo2->tx_flags |= tsflags;
+ swap(shinfo->tskey, shinfo2->tskey);
+ }
+}
+
/* Function to create two new TCP segments. Shrinks the given segment
* to the specified size and appends a new segment with the rest of the
* packet to the list. This won't be called frequently, I hope.
@@ -1136,6 +1151,7 @@
*/
TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when;
buff->tstamp = skb->tstamp;
+ tcp_fragment_tstamp(skb, buff);
old_factor = tcp_skb_pcount(skb);
@@ -1652,6 +1668,7 @@
buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL;
skb_split(skb, buff, len);
+ tcp_fragment_tstamp(skb, buff);
/* Fix up tso_factor for both original and new SKB. */
tcp_set_skb_tso_segs(sk, skb, mss_now);
@@ -1917,8 +1934,11 @@
tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
BUG_ON(!tso_segs);
- if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE)
+ if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
+ /* "when" is used as a start point for the retransmit timer */
+ TCP_SKB_CB(skb)->when = tcp_time_stamp;
goto repair; /* Skip network transmission */
+ }
cwnd_quota = tcp_cwnd_test(tp, skb);
if (!cwnd_quota) {
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 2e9ba03..6163f85 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -101,19 +101,19 @@
for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
- (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+ (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) {
if (remote == t->parms.iph.daddr &&
- (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+ (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) {
if (local == t->parms.iph.saddr &&
- (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+ (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f2ce955..29964c3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1595,6 +1595,7 @@
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
+ .mtu_reduced = tcp_v6_mtu_reduced,
};
#ifdef CONFIG_TCP_MD5SIG
@@ -1625,6 +1626,7 @@
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
+ .mtu_reduced = tcp_v4_mtu_reduced,
};
#ifdef CONFIG_TCP_MD5SIG
@@ -1864,7 +1866,6 @@
.sendpage = tcp_sendpage,
.backlog_rcv = tcp_v6_do_rcv,
.release_cb = tcp_release_cb,
- .mtu_reduced = tcp_v6_mtu_reduced,
.hash = tcp_v6_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c
index 9ea0c93..a37998c 100644
--- a/net/irda/irlap_frame.c
+++ b/net/irda/irlap_frame.c
@@ -622,7 +622,7 @@
frame = (struct rd_frame *)skb_put(tx_skb, 2);
frame->caddr = self->caddr;
- frame->caddr = RD_RSP | PF_BIT;
+ frame->control = RD_RSP | PF_BIT;
irlap_queue_xmit(self, tx_skb);
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 2e152e5f..c416725 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2921,6 +2921,7 @@
}
static void *netlink_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(RCU)
{
rcu_read_lock();
return *pos ? netlink_seq_socket_idx(seq, *pos - 1) : SEQ_START_TOKEN;
@@ -2970,6 +2971,7 @@
}
static void netlink_seq_stop(struct seq_file *seq, void *v)
+ __releases(RCU)
{
rcu_read_unlock();
}
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 702fb21..6d8f2ec 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -137,8 +137,10 @@
vport->ops = ops;
INIT_HLIST_NODE(&vport->dp_hash_node);
- if (ovs_vport_set_upcall_portids(vport, parms->upcall_portids))
+ if (ovs_vport_set_upcall_portids(vport, parms->upcall_portids)) {
+ kfree(vport);
return ERR_PTR(-EINVAL);
+ }
vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!vport->percpu_stats) {
