Merge branch 'pm-cpufreq'
Merge cpufreq changes for 4.19.
These are driver extensions, some driver and core fixes and a new
tracepoint for the tracking of frequency limits changes (coming from
Android).
* pm-cpufreq:
cpufreq: intel_pstate: Ignore turbo active ratio in HWP
cpufreq: Fix a circular lock dependency problem
cpu/hotplug: Add a cpus_read_trylock() function
cpufreq: trace frequency limits change
cpufreq: intel_pstate: Show different max frequency with turbo 3 and HWP
cpufreq: pcc-cpufreq: Disable dynamic scaling on many-CPU systems
cpufreq: qcom-kryo: Silently error out on EPROBE_DEFER
cpufreq / CPPC: Add cpuinfo_cur_freq support for CPPC
cpufreq: armada-37xx: Add AVS support
dt-bindings: marvell: Add documentation for the Armada 3700 AVS binding
cpufreq: imx6q/thermal: imx: register cooling device depending on OF
cpufreq: intel_pstate: use match_string() helper
diff --git a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
index fc2bcbe..0ec6814 100644
--- a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
+++ b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
@@ -1,14 +1,10 @@
-* Rockchip rk3399 DMC(Dynamic Memory Controller) device
+* Rockchip rk3399 DMC (Dynamic Memory Controller) device
Required properties:
- compatible: Must be "rockchip,rk3399-dmc".
- devfreq-events: Node to get DDR loading, Refer to
- Documentation/devicetree/bindings/devfreq/
+ Documentation/devicetree/bindings/devfreq/event/
rockchip-dfi.txt
-- interrupts: The interrupt number to the CPU. The interrupt
- specifier format depends on the interrupt controller.
- It should be DCF interrupts, when DDR dvfs finish,
- it will happen.
- clocks: Phandles for clock specified in "clock-names" property
- clock-names : The name of clock used by the DFI, must be
"pclk_ddr_mon";
@@ -17,139 +13,148 @@
- center-supply: DMC supply node.
- status: Marks the node enabled/disabled.
-Following properties are ddr timing:
+Optional properties:
+- interrupts: The CPU interrupt number. The interrupt specifier
+ format depends on the interrupt controller.
+ It should be a DCF interrupt. When DDR DVFS finishes
+ a DCF interrupt is triggered.
-- rockchip,dram_speed_bin : Value reference include/dt-bindings/clock/ddr.h,
- it select ddr3 cl-trp-trcd type, default value
- "DDR3_DEFAULT".it must selected according to
- "Speed Bin" in ddr3 datasheet, DO NOT use
- smaller "Speed Bin" than ddr3 exactly is.
+Following properties relate to DDR timing:
-- rockchip,pd_idle : Config the PD_IDLE value, defined the power-down
- idle period, memories are places into power-down
- mode if bus is idle for PD_IDLE DFI clocks.
+- rockchip,dram_speed_bin : Value reference include/dt-bindings/clock/rk3399-ddr.h,
+ it selects the DDR3 cl-trp-trcd type. It must be
+ set according to "Speed Bin" in DDR3 datasheet,
+ DO NOT use a smaller "Speed Bin" than specified
+ for the DDR3 being used.
-- rockchip,sr_idle : Configure the SR_IDLE value, defined the
- selfrefresh idle period, memories are places
- into self-refresh mode if bus is idle for
- SR_IDLE*1024 DFI clocks (DFI clocks freq is
- half of dram's clocks), defaule value is "0".
+- rockchip,pd_idle : Configure the PD_IDLE value. Defines the
+ power-down idle period in which memories are
+ placed into power-down mode if bus is idle
+ for PD_IDLE DFI clock cycles.
-- rockchip,sr_mc_gate_idle : Defined the self-refresh with memory and
- controller clock gating idle period, memories
- are places into self-refresh mode and memory
- controller clock arg gating if bus is idle for
- sr_mc_gate_idle*1024 DFI clocks.
+- rockchip,sr_idle : Configure the SR_IDLE value. Defines the
+ self-refresh idle period in which memories are
+ placed into self-refresh mode if bus is idle
+ for SR_IDLE * 1024 DFI clock cycles (DFI
+ clocks freq is half of DRAM clock), default
+ value is "0".
-- rockchip,srpd_lite_idle : Defined the self-refresh power down idle
- period, memories are places into self-refresh
- power down mode if bus is idle for
- srpd_lite_idle*1024 DFI clocks. This parameter
- is for LPDDR4 only.
+- rockchip,sr_mc_gate_idle : Defines the memory self-refresh and controller
+ clock gating idle period. Memories are placed
+ into self-refresh mode and memory controller
+ clock arg gating started if bus is idle for
+ sr_mc_gate_idle*1024 DFI clock cycles.
-- rockchip,standby_idle : Defined the standby idle period, memories are
- places into self-refresh than controller, pi,
- phy and dram clock will gating if bus is idle
- for standby_idle * DFI clocks.
+- rockchip,srpd_lite_idle : Defines the self-refresh power down idle
+ period in which memories are placed into
+ self-refresh power down mode if bus is idle
+ for srpd_lite_idle * 1024 DFI clock cycles.
+ This parameter is for LPDDR4 only.
-- rockchip,dram_dll_disb_freq : It's defined the DDR3 dll bypass frequency in
- MHz, when ddr freq less than DRAM_DLL_DISB_FREQ,
- ddr3 dll will bypssed note: if dll was bypassed,
- the odt also stop working.
+- rockchip,standby_idle : Defines the standby idle period in which
+ memories are placed into self-refresh mode.
+ The controller, pi, PHY and DRAM clock will
+ be gated if bus is idle for standby_idle * DFI
+ clock cycles.
-- rockchip,phy_dll_disb_freq : Defined the PHY dll bypass frequency in
- MHz (Mega Hz), when ddr freq less than
- DRAM_DLL_DISB_FREQ, phy dll will bypssed.
- note: phy dll and phy odt are independent.
+- rockchip,dram_dll_dis_freq : Defines the DDR3 DLL bypass frequency in MHz.
+ When DDR frequency is less than DRAM_DLL_DISB_FREQ,
+ DDR3 DLL will be bypassed. Note: if DLL was bypassed,
+ the odt will also stop working.
-- rockchip,ddr3_odt_disb_freq : When dram type is DDR3, this parameter defined
- the odt disable frequency in MHz (Mega Hz),
- when ddr frequency less then ddr3_odt_disb_freq,
- the odt on dram side and controller side are
+- rockchip,phy_dll_dis_freq : Defines the PHY dll bypass frequency in
+ MHz (Mega Hz). When DDR frequency is less than
+ DRAM_DLL_DISB_FREQ, PHY DLL will be bypassed.
+ Note: PHY DLL and PHY ODT are independent.
+
+- rockchip,ddr3_odt_dis_freq : When the DRAM type is DDR3, this parameter defines
+ the ODT disable frequency in MHz (Mega Hz).
+ when the DDR frequency is less then ddr3_odt_dis_freq,
+ the ODT on the DRAM side and controller side are
both disabled.
-- rockchip,ddr3_drv : When dram type is DDR3, this parameter define
- the dram side driver stength in ohm, default
+- rockchip,ddr3_drv : When the DRAM type is DDR3, this parameter defines
+ the DRAM side driver strength in ohms. Default
value is DDR3_DS_40ohm.
-- rockchip,ddr3_odt : When dram type is DDR3, this parameter define
- the dram side ODT stength in ohm, default value
+- rockchip,ddr3_odt : When the DRAM type is DDR3, this parameter defines
+ the DRAM side ODT strength in ohms. Default value
is DDR3_ODT_120ohm.
-- rockchip,phy_ddr3_ca_drv : When dram type is DDR3, this parameter define
- the phy side CA line(incluing command line,
+- rockchip,phy_ddr3_ca_drv : When the DRAM type is DDR3, this parameter defines
+ the phy side CA line (incluing command line,
address line and clock line) driver strength.
Default value is PHY_DRV_ODT_40.
-- rockchip,phy_ddr3_dq_drv : When dram type is DDR3, this parameter define
- the phy side DQ line(incluing DQS/DQ/DM line)
- driver strength. default value is PHY_DRV_ODT_40.
+- rockchip,phy_ddr3_dq_drv : When the DRAM type is DDR3, this parameter defines
+ the PHY side DQ line (including DQS/DQ/DM line)
+ driver strength. Default value is PHY_DRV_ODT_40.
-- rockchip,phy_ddr3_odt : When dram type is DDR3, this parameter define the
- phy side odt strength, default value is
+- rockchip,phy_ddr3_odt : When the DRAM type is DDR3, this parameter defines
+ the PHY side ODT strength. Default value is
PHY_DRV_ODT_240.
-- rockchip,lpddr3_odt_disb_freq : When dram type is LPDDR3, this parameter defined
- then odt disable frequency in MHz (Mega Hz),
- when ddr frequency less then ddr3_odt_disb_freq,
- the odt on dram side and controller side are
+- rockchip,lpddr3_odt_dis_freq : When the DRAM type is LPDDR3, this parameter defines
+ then ODT disable frequency in MHz (Mega Hz).
+ When DDR frequency is less then ddr3_odt_dis_freq,
+ the ODT on the DRAM side and controller side are
both disabled.
-- rockchip,lpddr3_drv : When dram type is LPDDR3, this parameter define
- the dram side driver stength in ohm, default
+- rockchip,lpddr3_drv : When the DRAM type is LPDDR3, this parameter defines
+ the DRAM side driver strength in ohms. Default
value is LP3_DS_34ohm.
-- rockchip,lpddr3_odt : When dram type is LPDDR3, this parameter define
- the dram side ODT stength in ohm, default value
+- rockchip,lpddr3_odt : When the DRAM type is LPDDR3, this parameter defines
+ the DRAM side ODT strength in ohms. Default value
is LP3_ODT_240ohm.
-- rockchip,phy_lpddr3_ca_drv : When dram type is LPDDR3, this parameter define
- the phy side CA line(incluing command line,
+- rockchip,phy_lpddr3_ca_drv : When the DRAM type is LPDDR3, this parameter defines
+ the PHY side CA line (including command line,
address line and clock line) driver strength.
- default value is PHY_DRV_ODT_40.
+ Default value is PHY_DRV_ODT_40.
-- rockchip,phy_lpddr3_dq_drv : When dram type is LPDDR3, this parameter define
- the phy side DQ line(incluing DQS/DQ/DM line)
- driver strength. default value is
+- rockchip,phy_lpddr3_dq_drv : When the DRAM type is LPDDR3, this parameter defines
+ the PHY side DQ line (including DQS/DQ/DM line)
+ driver strength. Default value is
PHY_DRV_ODT_40.
- rockchip,phy_lpddr3_odt : When dram type is LPDDR3, this parameter define
the phy side odt strength, default value is
PHY_DRV_ODT_240.
-- rockchip,lpddr4_odt_disb_freq : When dram type is LPDDR4, this parameter
- defined the odt disable frequency in
- MHz (Mega Hz), when ddr frequency less then
- ddr3_odt_disb_freq, the odt on dram side and
+- rockchip,lpddr4_odt_dis_freq : When the DRAM type is LPDDR4, this parameter
+ defines the ODT disable frequency in
+ MHz (Mega Hz). When the DDR frequency is less then
+ ddr3_odt_dis_freq, the ODT on the DRAM side and
controller side are both disabled.
-- rockchip,lpddr4_drv : When dram type is LPDDR4, this parameter define
- the dram side driver stength in ohm, default
+- rockchip,lpddr4_drv : When the DRAM type is LPDDR4, this parameter defines
+ the DRAM side driver strength in ohms. Default
value is LP4_PDDS_60ohm.
-- rockchip,lpddr4_dq_odt : When dram type is LPDDR4, this parameter define
- the dram side ODT on dqs/dq line stength in ohm,
- default value is LP4_DQ_ODT_40ohm.
+- rockchip,lpddr4_dq_odt : When the DRAM type is LPDDR4, this parameter defines
+ the DRAM side ODT on DQS/DQ line strength in ohms.
+ Default value is LP4_DQ_ODT_40ohm.
-- rockchip,lpddr4_ca_odt : When dram type is LPDDR4, this parameter define
- the dram side ODT on ca line stength in ohm,
- default value is LP4_CA_ODT_40ohm.
+- rockchip,lpddr4_ca_odt : When the DRAM type is LPDDR4, this parameter defines
+ the DRAM side ODT on CA line strength in ohms.
+ Default value is LP4_CA_ODT_40ohm.
-- rockchip,phy_lpddr4_ca_drv : When dram type is LPDDR4, this parameter define
- the phy side CA line(incluing command address
- line) driver strength. default value is
+- rockchip,phy_lpddr4_ca_drv : When the DRAM type is LPDDR4, this parameter defines
+ the PHY side CA line (including command address
+ line) driver strength. Default value is
PHY_DRV_ODT_40.
-- rockchip,phy_lpddr4_ck_cs_drv : When dram type is LPDDR4, this parameter define
- the phy side clock line and cs line driver
- strength. default value is PHY_DRV_ODT_80.
+- rockchip,phy_lpddr4_ck_cs_drv : When the DRAM type is LPDDR4, this parameter defines
+ the PHY side clock line and CS line driver
+ strength. Default value is PHY_DRV_ODT_80.
-- rockchip,phy_lpddr4_dq_drv : When dram type is LPDDR4, this parameter define
- the phy side DQ line(incluing DQS/DQ/DM line)
- driver strength. default value is PHY_DRV_ODT_80.
+- rockchip,phy_lpddr4_dq_drv : When the DRAM type is LPDDR4, this parameter defines
+ the PHY side DQ line (including DQS/DQ/DM line)
+ driver strength. Default value is PHY_DRV_ODT_80.
-- rockchip,phy_lpddr4_odt : When dram type is LPDDR4, this parameter define
- the phy side odt strength, default value is
+- rockchip,phy_lpddr4_odt : When the DRAM type is LPDDR4, this parameter defines
+ the PHY side ODT strength. Default value is
PHY_DRV_ODT_60.
Example:
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
index 7dec508..8f8b25a 100644
--- a/Documentation/devicetree/bindings/power/power_domain.txt
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -114,18 +114,26 @@
- power-domains : A list of PM domain specifiers, as defined by bindings of
the power controller that is the PM domain provider.
+Optional properties:
+ - power-domain-names : A list of power domain name strings sorted in the same
+ order as the power-domains property. Consumers drivers will use
+ power-domain-names to match power domains with power-domains
+ specifiers.
+
Example:
leaky-device@12350000 {
compatible = "foo,i-leak-current";
reg = <0x12350000 0x1000>;
power-domains = <&power 0>;
+ power-domain-names = "io";
};
leaky-device@12351000 {
compatible = "foo,i-leak-current";
reg = <0x12351000 0x1000>;
power-domains = <&power 0>, <&power 1> ;
+ power-domain-names = "io", "clk";
};
The first example above defines a typical PM domain consumer device, which is
diff --git a/Documentation/driver-api/device_link.rst b/Documentation/driver-api/device_link.rst
index 70e328e..d676327 100644
--- a/Documentation/driver-api/device_link.rst
+++ b/Documentation/driver-api/device_link.rst
@@ -81,10 +81,14 @@
Two other flags are specifically targeted at use cases where the device
link is added from the consumer's ``->probe`` callback: ``DL_FLAG_RPM_ACTIVE``
can be specified to runtime resume the supplier upon addition of the
-device link. ``DL_FLAG_AUTOREMOVE`` causes the device link to be automatically
-purged when the consumer fails to probe or later unbinds. This obviates
-the need to explicitly delete the link in the ``->remove`` callback or in
-the error path of the ``->probe`` callback.
+device link. ``DL_FLAG_AUTOREMOVE_CONSUMER`` causes the device link to be
+automatically purged when the consumer fails to probe or later unbinds.
+This obviates the need to explicitly delete the link in the ``->remove``
+callback or in the error path of the ``->probe`` callback.
+
+Similarly, when the device link is added from supplier's ``->probe`` callback,
+``DL_FLAG_AUTOREMOVE_SUPPLIER`` causes the device link to be automatically
+purged when the supplier fails to probe or later unbinds.
Limitations
===========
diff --git a/Documentation/power/freezing-of-tasks.txt b/Documentation/power/freezing-of-tasks.txt
index af00577..cd28319 100644
--- a/Documentation/power/freezing-of-tasks.txt
+++ b/Documentation/power/freezing-of-tasks.txt
@@ -204,26 +204,26 @@
Yes, there are.
-First of all, grabbing the 'pm_mutex' lock to mutually exclude a piece of code
+First of all, grabbing the 'system_transition_mutex' lock to mutually exclude a piece of code
from system-wide sleep such as suspend/hibernation is not encouraged.
If possible, that piece of code must instead hook onto the suspend/hibernation
notifiers to achieve mutual exclusion. Look at the CPU-Hotplug code
(kernel/cpu.c) for an example.
-However, if that is not feasible, and grabbing 'pm_mutex' is deemed necessary,
-it is strongly discouraged to directly call mutex_[un]lock(&pm_mutex) since
+However, if that is not feasible, and grabbing 'system_transition_mutex' is deemed necessary,
+it is strongly discouraged to directly call mutex_[un]lock(&system_transition_mutex) since
that could lead to freezing failures, because if the suspend/hibernate code
-successfully acquired the 'pm_mutex' lock, and hence that other entity failed
+successfully acquired the 'system_transition_mutex' lock, and hence that other entity failed
to acquire the lock, then that task would get blocked in TASK_UNINTERRUPTIBLE
state. As a consequence, the freezer would not be able to freeze that task,
leading to freezing failure.
However, the [un]lock_system_sleep() APIs are safe to use in this scenario,
since they ask the freezer to skip freezing this task, since it is anyway
-"frozen enough" as it is blocked on 'pm_mutex', which will be released
+"frozen enough" as it is blocked on 'system_transition_mutex', which will be released
only after the entire suspend/hibernation sequence is complete.
So, to summarize, use [un]lock_system_sleep() instead of directly using
-mutex_[un]lock(&pm_mutex). That would prevent freezing failures.
+mutex_[un]lock(&system_transition_mutex). That would prevent freezing failures.
V. Miscellaneous
/sys/power/pm_freeze_timeout controls how long it will cost at most to freeze
diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt
index 6f55eb9..a8751b8 100644
--- a/Documentation/power/suspend-and-cpuhotplug.txt
+++ b/Documentation/power/suspend-and-cpuhotplug.txt
@@ -32,7 +32,7 @@
sysfs file
|
v
- Acquire pm_mutex lock
+ Acquire system_transition_mutex lock
|
v
Send PM_SUSPEND_PREPARE
@@ -96,10 +96,10 @@
* thaw tasks
* send PM_POST_SUSPEND notifications
-* Release pm_mutex lock.
+* Release system_transition_mutex lock.
-It is to be noted here that the pm_mutex lock is acquired at the very
+It is to be noted here that the system_transition_mutex lock is acquired at the very
beginning, when we are just starting out to suspend, and then released only
after the entire cycle is complete (i.e., suspend + resume).
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 67ccf64..f8e3b66 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -233,29 +233,35 @@ struct restore_data_record {
*/
static int get_e820_md5(struct e820_table *table, void *buf)
{
- struct scatterlist sg;
- struct crypto_ahash *tfm;
+ struct crypto_shash *tfm;
+ struct shash_desc *desc;
int size;
int ret = 0;
- tfm = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
+ tfm = crypto_alloc_shash("md5", 0, 0);
if (IS_ERR(tfm))
return -ENOMEM;
- {
- AHASH_REQUEST_ON_STACK(req, tfm);
- size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * table->nr_entries;
- ahash_request_set_tfm(req, tfm);
- sg_init_one(&sg, (u8 *)table, size);
- ahash_request_set_callback(req, 0, NULL, NULL);
- ahash_request_set_crypt(req, &sg, buf, size);
-
- if (crypto_ahash_digest(req))
- ret = -EINVAL;
- ahash_request_zero(req);
+ desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
+ GFP_KERNEL);
+ if (!desc) {
+ ret = -ENOMEM;
+ goto free_tfm;
}
- crypto_free_ahash(tfm);
+ desc->tfm = tfm;
+ desc->flags = 0;
+
+ size = offsetof(struct e820_table, entries) +
+ sizeof(struct e820_entry) * table->nr_entries;
+
+ if (crypto_shash_digest(desc, (u8 *)table, size, buf))
+ ret = -EINVAL;
+
+ kzfree(desc);
+
+free_tfm:
+ crypto_free_shash(tfm);
return ret;
}
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 5d0486f..754d59f 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -338,6 +338,14 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
DMI_MATCH(DMI_PRODUCT_NAME, "K54HR"),
},
},
+ {
+ .callback = init_nvs_save_s3,
+ .ident = "Asus 1025C",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "1025C"),
+ },
+ },
/*
* https://bugzilla.kernel.org/show_bug.cgi?id=189431
* Lenovo G50-45 is a platform later than 2012, but needs nvs memory
@@ -718,9 +726,6 @@ static const struct acpi_device_id lps0_device_ids[] = {
#define ACPI_LPS0_ENTRY 5
#define ACPI_LPS0_EXIT 6
-#define ACPI_LPS0_SCREEN_MASK ((1 << ACPI_LPS0_SCREEN_OFF) | (1 << ACPI_LPS0_SCREEN_ON))
-#define ACPI_LPS0_PLATFORM_MASK ((1 << ACPI_LPS0_ENTRY) | (1 << ACPI_LPS0_EXIT))
-
static acpi_handle lps0_device_handle;
static guid_t lps0_dsm_guid;
static char lps0_dsm_func_mask;
@@ -924,17 +929,14 @@ static int lps0_device_attach(struct acpi_device *adev,
if (out_obj && out_obj->type == ACPI_TYPE_BUFFER) {
char bitmask = *(char *)out_obj->buffer.pointer;
- if ((bitmask & ACPI_LPS0_PLATFORM_MASK) == ACPI_LPS0_PLATFORM_MASK ||
- (bitmask & ACPI_LPS0_SCREEN_MASK) == ACPI_LPS0_SCREEN_MASK) {
- lps0_dsm_func_mask = bitmask;
- lps0_device_handle = adev->handle;
- /*
- * Use suspend-to-idle by default if the default
- * suspend mode was not set from the command line.
- */
- if (mem_sleep_default > PM_SUSPEND_MEM)
- mem_sleep_current = PM_SUSPEND_TO_IDLE;
- }
+ lps0_dsm_func_mask = bitmask;
+ lps0_device_handle = adev->handle;
+ /*
+ * Use suspend-to-idle by default if the default
+ * suspend mode was not set from the command line.
+ */
+ if (mem_sleep_default > PM_SUSPEND_MEM)
+ mem_sleep_current = PM_SUSPEND_TO_IDLE;
acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n",
bitmask);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index df3e1a4..e721218 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -178,10 +178,10 @@ void device_pm_move_to_tail(struct device *dev)
* of the link. If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be
* ignored.
*
- * If the DL_FLAG_AUTOREMOVE is set, the link will be removed automatically
- * when the consumer device driver unbinds from it. The combination of both
- * DL_FLAG_AUTOREMOVE and DL_FLAG_STATELESS set is invalid and will cause NULL
- * to be returned.
+ * If the DL_FLAG_AUTOREMOVE_CONSUMER is set, the link will be removed
+ * automatically when the consumer device driver unbinds from it.
+ * The combination of both DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_STATELESS
+ * set is invalid and will cause NULL to be returned.
*
* A side effect of the link creation is re-ordering of dpm_list and the
* devices_kset list by moving the consumer device and all devices depending
@@ -198,7 +198,8 @@ struct device_link *device_link_add(struct device *consumer,
struct device_link *link;
if (!consumer || !supplier ||
- ((flags & DL_FLAG_STATELESS) && (flags & DL_FLAG_AUTOREMOVE)))
+ ((flags & DL_FLAG_STATELESS) &&
+ (flags & DL_FLAG_AUTOREMOVE_CONSUMER)))
return NULL;
device_links_write_lock();
@@ -479,7 +480,7 @@ static void __device_links_no_driver(struct device *dev)
if (link->flags & DL_FLAG_STATELESS)
continue;
- if (link->flags & DL_FLAG_AUTOREMOVE)
+ if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER)
kref_put(&link->kref, __device_link_del);
else if (link->status != DL_STATE_SUPPLIER_UNBIND)
WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
@@ -515,8 +516,18 @@ void device_links_driver_cleanup(struct device *dev)
if (link->flags & DL_FLAG_STATELESS)
continue;
- WARN_ON(link->flags & DL_FLAG_AUTOREMOVE);
+ WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER);
WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND);
+
+ /*
+ * autoremove the links between this @dev and its consumer
+ * devices that are not active, i.e. where the link state
+ * has moved to DL_STATE_SUPPLIER_UNBIND.
+ */
+ if (link->status == DL_STATE_SUPPLIER_UNBIND &&
+ link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
+ kref_put(&link->kref, __device_link_del);
+
WRITE_ONCE(link->status, DL_STATE_DORMANT);
}
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index df41b47..b413951 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -153,6 +153,23 @@ struct device *dev_pm_domain_attach_by_id(struct device *dev,
EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id);
/**
+ * dev_pm_domain_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * For a detailed function description, see dev_pm_domain_attach_by_id().
+ */
+struct device *dev_pm_domain_attach_by_name(struct device *dev,
+ char *name)
+{
+ if (dev->pm_domain)
+ return ERR_PTR(-EEXIST);
+
+ return genpd_dev_pm_attach_by_name(dev, name);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_name);
+
+/**
* dev_pm_domain_detach - Detach a device from its PM domain.
* @dev: Device to detach.
* @power_off: Used to indicate whether we should power off the device.
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 9e84841..79bdca7 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2374,6 +2374,30 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
}
EXPORT_SYMBOL_GPL(genpd_dev_pm_attach_by_id);
+/**
+ * genpd_dev_pm_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * Parse device's OF node to find a PM domain specifier using the
+ * power-domain-names DT property. For further description see
+ * genpd_dev_pm_attach_by_id().
+ */
+struct device *genpd_dev_pm_attach_by_name(struct device *dev, char *name)
+{
+ int index;
+
+ if (!dev->of_node)
+ return NULL;
+
+ index = of_property_match_string(dev->of_node, "power-domain-names",
+ name);
+ if (index < 0)
+ return NULL;
+
+ return genpd_dev_pm_attach_by_id(dev, index);
+}
+
static const struct of_device_id idle_state_match[] = {
{ .compatible = "domain-idle-state", },
{ }
diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index e07bc7a..073557f 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -105,7 +105,8 @@ static int __init arm_idle_init_cpu(int cpu)
ret = cpuidle_register_driver(drv);
if (ret) {
- pr_err("Failed to register cpuidle driver\n");
+ if (ret != -EBUSY)
+ pr_err("Failed to register cpuidle driver\n");
goto out_kfree_drv;
}
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 0b5b3ab..4c49bb1 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -604,28 +604,29 @@ struct devfreq *devfreq_add_device(struct device *dev,
mutex_lock(&devfreq->lock);
}
- devfreq->min_freq = find_available_min_freq(devfreq);
- if (!devfreq->min_freq) {
+ devfreq->scaling_min_freq = find_available_min_freq(devfreq);
+ if (!devfreq->scaling_min_freq) {
mutex_unlock(&devfreq->lock);
err = -EINVAL;
goto err_dev;
}
- devfreq->scaling_min_freq = devfreq->min_freq;
+ devfreq->min_freq = devfreq->scaling_min_freq;
- devfreq->max_freq = find_available_max_freq(devfreq);
- if (!devfreq->max_freq) {
+ devfreq->scaling_max_freq = find_available_max_freq(devfreq);
+ if (!devfreq->scaling_max_freq) {
mutex_unlock(&devfreq->lock);
err = -EINVAL;
goto err_dev;
}
- devfreq->scaling_max_freq = devfreq->max_freq;
+ devfreq->max_freq = devfreq->scaling_max_freq;
dev_set_name(&devfreq->dev, "devfreq%d",
atomic_inc_return(&devfreq_no));
err = device_register(&devfreq->dev);
if (err) {
mutex_unlock(&devfreq->lock);
- goto err_dev;
+ put_device(&devfreq->dev);
+ goto err_out;
}
devfreq->trans_table =
@@ -672,6 +673,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
mutex_unlock(&devfreq_list_lock);
device_unregister(&devfreq->dev);
+ devfreq = NULL;
err_dev:
if (devfreq)
kfree(devfreq);
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 3cd6a18..a9c64f0 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -627,11 +627,9 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
size = sizeof(struct devfreq_event_dev *) * info->num_events;
info->edev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
- if (!info->edev) {
- dev_err(&pdev->dev,
- "failed to allocate memory devfreq-event devices\n");
+ if (!info->edev)
return -ENOMEM;
- }
+
edev = info->edev;
platform_set_drvdata(pdev, info);
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 5dfbfa3c..e795ad2 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -68,15 +68,6 @@ struct rk3399_dmcfreq {
struct devfreq_event_dev *edev;
struct mutex lock;
struct dram_timing timing;
-
- /*
- * DDR Converser of Frequency (DCF) is used to implement DDR frequency
- * conversion without the participation of CPU, we will implement and
- * control it in arm trust firmware.
- */
- wait_queue_head_t wait_dcf_queue;
- int irq;
- int wait_dcf_flag;
struct regulator *vdd_center;
unsigned long rate, target_rate;
unsigned long volt, target_volt;
@@ -112,31 +103,22 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
target_volt);
if (err) {
- dev_err(dev, "Cannot to set voltage %lu uV\n",
+ dev_err(dev, "Cannot set voltage %lu uV\n",
target_volt);
goto out;
}
}
- dmcfreq->wait_dcf_flag = 1;
err = clk_set_rate(dmcfreq->dmc_clk, target_rate);
if (err) {
- dev_err(dev, "Cannot to set frequency %lu (%d)\n",
- target_rate, err);
+ dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate,
+ err);
regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
dmcfreq->volt);
goto out;
}
/*
- * Wait until bcf irq happen, it means freq scaling finish in
- * arm trust firmware, use 100ms as timeout time.
- */
- if (!wait_event_timeout(dmcfreq->wait_dcf_queue,
- !dmcfreq->wait_dcf_flag, HZ / 10))
- dev_warn(dev, "Timeout waiting for dcf interrupt\n");
-
- /*
* Check the dpll rate,
* There only two result we will get,
* 1. Ddr frequency scaling fail, we still get the old rate.
@@ -146,8 +128,8 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
/* If get the incorrect rate, set voltage to old value. */
if (dmcfreq->rate != target_rate) {
- dev_err(dev, "Get wrong ddr frequency, Request frequency %lu,\
- Current frequency %lu\n", target_rate, dmcfreq->rate);
+ dev_err(dev, "Got wrong frequency, Request %lu, Current %lu\n",
+ target_rate, dmcfreq->rate);
regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
dmcfreq->volt);
goto out;
@@ -155,7 +137,7 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
target_volt);
if (err)
- dev_err(dev, "Cannot to set vol %lu uV\n", target_volt);
+ dev_err(dev, "Cannot set voltage %lu uV\n", target_volt);
dmcfreq->rate = target_rate;
dmcfreq->volt = target_volt;
@@ -241,22 +223,6 @@ static __maybe_unused int rk3399_dmcfreq_resume(struct device *dev)
static SIMPLE_DEV_PM_OPS(rk3399_dmcfreq_pm, rk3399_dmcfreq_suspend,
rk3399_dmcfreq_resume);
-static irqreturn_t rk3399_dmc_irq(int irq, void *dev_id)
-{
- struct rk3399_dmcfreq *dmcfreq = dev_id;
- struct arm_smccc_res res;
-
- dmcfreq->wait_dcf_flag = 0;
- wake_up(&dmcfreq->wait_dcf_queue);
-
- /* Clear the DCF interrupt */
- arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, 0, 0,
- ROCKCHIP_SIP_CONFIG_DRAM_CLR_IRQ,
- 0, 0, 0, 0, &res);
-
- return IRQ_HANDLED;
-}
-
static int of_get_ddr_timings(struct dram_timing *timing,
struct device_node *np)
{
@@ -330,16 +296,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
struct device *dev = &pdev->dev;
struct device_node *np = pdev->dev.of_node;
struct rk3399_dmcfreq *data;
- int ret, irq, index, size;
+ int ret, index, size;
uint32_t *timing;
struct dev_pm_opp *opp;
- irq = platform_get_irq(pdev, 0);
- if (irq < 0) {
- dev_err(&pdev->dev,
- "Cannot get the dmc interrupt resource: %d\n", irq);
- return irq;
- }
data = devm_kzalloc(dev, sizeof(struct rk3399_dmcfreq), GFP_KERNEL);
if (!data)
return -ENOMEM;
@@ -348,27 +308,22 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
data->vdd_center = devm_regulator_get(dev, "center");
if (IS_ERR(data->vdd_center)) {
+ if (PTR_ERR(data->vdd_center) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+
dev_err(dev, "Cannot get the regulator \"center\"\n");
return PTR_ERR(data->vdd_center);
}
data->dmc_clk = devm_clk_get(dev, "dmc_clk");
if (IS_ERR(data->dmc_clk)) {
+ if (PTR_ERR(data->dmc_clk) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+
dev_err(dev, "Cannot get the clk dmc_clk\n");
return PTR_ERR(data->dmc_clk);
};
- data->irq = irq;
- ret = devm_request_irq(dev, irq, rk3399_dmc_irq, 0,
- dev_name(dev), data);
- if (ret) {
- dev_err(dev, "Failed to request dmc irq: %d\n", ret);
- return ret;
- }
-
- init_waitqueue_head(&data->wait_dcf_queue);
- data->wait_dcf_flag = 0;
-
data->edev = devfreq_event_get_edev_by_phandle(dev, 0);
if (IS_ERR(data->edev))
return -EPROBE_DEFER;
@@ -420,8 +375,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
data->rate = clk_get_rate(data->dmc_clk);
opp = devfreq_recommended_opp(dev, &data->rate, 0);
- if (IS_ERR(opp))
- return PTR_ERR(opp);
+ if (IS_ERR(opp)) {
+ ret = PTR_ERR(opp);
+ goto err_free_opp;
+ }
data->rate = dev_pm_opp_get_freq(opp);
data->volt = dev_pm_opp_get_voltage(opp);
@@ -433,14 +390,34 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
&rk3399_devfreq_dmc_profile,
DEVFREQ_GOV_SIMPLE_ONDEMAND,
&data->ondemand_data);
- if (IS_ERR(data->devfreq))
- return PTR_ERR(data->devfreq);
+ if (IS_ERR(data->devfreq)) {
+ ret = PTR_ERR(data->devfreq);
+ goto err_free_opp;
+ }
+
devm_devfreq_register_opp_notifier(dev, data->devfreq);
data->dev = dev;
platform_set_drvdata(pdev, data);
return 0;
+
+err_free_opp:
+ dev_pm_opp_of_remove_table(&pdev->dev);
+ return ret;
+}
+
+static int rk3399_dmcfreq_remove(struct platform_device *pdev)
+{
+ struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(&pdev->dev);
+
+ /*
+ * Before remove the opp table we need to unregister the opp notifier.
+ */
+ devm_devfreq_unregister_opp_notifier(dmcfreq->dev, dmcfreq->devfreq);
+ dev_pm_opp_of_remove_table(dmcfreq->dev);
+
+ return 0;
}
static const struct of_device_id rk3399dmc_devfreq_of_match[] = {
@@ -451,6 +428,7 @@ MODULE_DEVICE_TABLE(of, rk3399dmc_devfreq_of_match);
static struct platform_driver rk3399_dmcfreq_driver = {
.probe = rk3399_dmcfreq_probe,
+ .remove = rk3399_dmcfreq_remove,
.driver = {
.name = "rk3399-dmc-freq",
.pm = &rk3399_dmcfreq_pm,
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index c3afe7b2..965088a 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -2312,7 +2312,7 @@ static int tegra_dc_couple(struct tegra_dc *dc)
* POWER_CONTROL registers during CRTC enabling.
*/
if (dc->soc->coupled_pm && dc->pipe == 1) {
- u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE;
+ u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER;
struct device_link *link;
struct device *partner;
diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c
index 0f70e88..2f8db9d6 100644
--- a/drivers/gpu/ipu-v3/ipu-pre.c
+++ b/drivers/gpu/ipu-v3/ipu-pre.c
@@ -128,7 +128,8 @@ ipu_pre_lookup_by_phandle(struct device *dev, const char *name, int index)
list_for_each_entry(pre, &ipu_pre_list, list) {
if (pre_node == pre->dev->of_node) {
mutex_unlock(&ipu_pre_list_mutex);
- device_link_add(dev, pre->dev, DL_FLAG_AUTOREMOVE);
+ device_link_add(dev, pre->dev,
+ DL_FLAG_AUTOREMOVE_CONSUMER);
of_node_put(pre_node);
return pre;
}
diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c
index 83f9dd9..38a3a97 100644
--- a/drivers/gpu/ipu-v3/ipu-prg.c
+++ b/drivers/gpu/ipu-v3/ipu-prg.c
@@ -100,7 +100,8 @@ ipu_prg_lookup_by_phandle(struct device *dev, const char *name, int ipu_id)
list_for_each_entry(prg, &ipu_prg_list, list) {
if (prg_node == prg->dev->of_node) {
mutex_unlock(&ipu_prg_list_mutex);
- device_link_add(dev, prg->dev, DL_FLAG_AUTOREMOVE);
+ device_link_add(dev, prg->dev,
+ DL_FLAG_AUTOREMOVE_CONSUMER);
prg->id = ipu_id;
of_node_put(prg_node);
return prg;
diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig
index 85727ef..6ac27e5 100644
--- a/drivers/powercap/Kconfig
+++ b/drivers/powercap/Kconfig
@@ -29,4 +29,14 @@
controller, CPU core (Power Plance 0), graphics uncore (Power Plane
1), etc.
+config IDLE_INJECT
+ bool "Idle injection framework"
+ depends on CPU_IDLE
+ default n
+ help
+ This enables support for the idle injection framework. It
+ provides a way to force idle periods on a set of specified
+ CPUs for power capping. Idle period can be injected
+ synchronously on a set of specified CPUs or alternatively
+ on a per CPU basis.
endif
diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile
index 0a21ef3..1b32885 100644
--- a/drivers/powercap/Makefile
+++ b/drivers/powercap/Makefile
@@ -1,2 +1,3 @@
obj-$(CONFIG_POWERCAP) += powercap_sys.o
obj-$(CONFIG_INTEL_RAPL) += intel_rapl.o
+obj-$(CONFIG_IDLE_INJECT) += idle_inject.o
diff --git a/drivers/powercap/idle_inject.c b/drivers/powercap/idle_inject.c
new file mode 100644
index 0000000..24ff2a0
--- /dev/null
+++ b/drivers/powercap/idle_inject.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * The idle injection framework provides a way to force CPUs to enter idle
+ * states for a specified fraction of time over a specified period.
+ *
+ * It relies on the smpboot kthreads feature providing common code for CPU
+ * hotplug and thread [un]parking.
+ *
+ * All of the kthreads used for idle injection are created at init time.
+ *
+ * Next, the users of the the idle injection framework provide a cpumask via
+ * its register function. The kthreads will be synchronized with respect to
+ * this cpumask.
+ *
+ * The idle + run duration is specified via separate helpers and that allows
+ * idle injection to be started.
+ *
+ * The idle injection kthreads will call play_idle() with the idle duration
+ * specified as per the above.
+ *
+ * After all of them have been woken up, a timer is set to start the next idle
+ * injection cycle.
+ *
+ * The timer interrupt handler will wake up the idle injection kthreads for
+ * all of the CPUs in the cpumask provided by the user.
+ *
+ * Idle injection is stopped synchronously and no leftover idle injection
+ * kthread activity after its completion is guaranteed.
+ *
+ * It is up to the user of this framework to provide a lock for higher-level
+ * synchronization to prevent race conditions like starting idle injection
+ * while unregistering from the framework.
+ */
+#define pr_fmt(fmt) "ii_dev: " fmt
+
+#include <linux/cpu.h>
+#include <linux/hrtimer.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smpboot.h>
+
+#include <uapi/linux/sched/types.h>
+
+/**
+ * struct idle_inject_thread - task on/off switch structure
+ * @tsk: task injecting the idle cycles
+ * @should_run: whether or not to run the task (for the smpboot kthread API)
+ */
+struct idle_inject_thread {
+ struct task_struct *tsk;
+ int should_run;
+};
+
+/**
+ * struct idle_inject_device - idle injection data
+ * @timer: idle injection period timer
+ * @idle_duration_ms: duration of CPU idle time to inject
+ * @run_duration_ms: duration of CPU run time to allow
+ * @cpumask: mask of CPUs affected by idle injection
+ */
+struct idle_inject_device {
+ struct hrtimer timer;
+ unsigned int idle_duration_ms;
+ unsigned int run_duration_ms;
+ unsigned long int cpumask[0];
+};
+
+static DEFINE_PER_CPU(struct idle_inject_thread, idle_inject_thread);
+static DEFINE_PER_CPU(struct idle_inject_device *, idle_inject_device);
+
+/**
+ * idle_inject_wakeup - Wake up idle injection threads
+ * @ii_dev: target idle injection device
+ *
+ * Every idle injection task associated with the given idle injection device
+ * and running on an online CPU will be woken up.
+ */
+static void idle_inject_wakeup(struct idle_inject_device *ii_dev)
+{
+ struct idle_inject_thread *iit;
+ unsigned int cpu;
+
+ for_each_cpu_and(cpu, to_cpumask(ii_dev->cpumask), cpu_online_mask) {
+ iit = per_cpu_ptr(&idle_inject_thread, cpu);
+ iit->should_run = 1;
+ wake_up_process(iit->tsk);
+ }
+}
+
+/**
+ * idle_inject_timer_fn - idle injection timer function
+ * @timer: idle injection hrtimer
+ *
+ * This function is called when the idle injection timer expires. It wakes up
+ * idle injection tasks associated with the timer and they, in turn, invoke
+ * play_idle() to inject a specified amount of CPU idle time.
+ *
+ * Return: HRTIMER_RESTART.
+ */
+static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
+{
+ unsigned int duration_ms;
+ struct idle_inject_device *ii_dev =
+ container_of(timer, struct idle_inject_device, timer);
+
+ duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+ duration_ms += READ_ONCE(ii_dev->idle_duration_ms);
+
+ idle_inject_wakeup(ii_dev);
+
+ hrtimer_forward_now(timer, ms_to_ktime(duration_ms));
+
+ return HRTIMER_RESTART;
+}
+
+/**
+ * idle_inject_fn - idle injection work function
+ * @cpu: the CPU owning the task
+ *
+ * This function calls play_idle() to inject a specified amount of CPU idle
+ * time.
+ */
+static void idle_inject_fn(unsigned int cpu)
+{
+ struct idle_inject_device *ii_dev;
+ struct idle_inject_thread *iit;
+
+ ii_dev = per_cpu(idle_inject_device, cpu);
+ iit = per_cpu_ptr(&idle_inject_thread, cpu);
+
+ /*
+ * Let the smpboot main loop know that the task should not run again.
+ */
+ iit->should_run = 0;
+
+ play_idle(READ_ONCE(ii_dev->idle_duration_ms));
+}
+
+/**
+ * idle_inject_set_duration - idle and run duration update helper
+ * @run_duration_ms: CPU run time to allow in milliseconds
+ * @idle_duration_ms: CPU idle time to inject in milliseconds
+ */
+void idle_inject_set_duration(struct idle_inject_device *ii_dev,
+ unsigned int run_duration_ms,
+ unsigned int idle_duration_ms)
+{
+ if (run_duration_ms && idle_duration_ms) {
+ WRITE_ONCE(ii_dev->run_duration_ms, run_duration_ms);
+ WRITE_ONCE(ii_dev->idle_duration_ms, idle_duration_ms);
+ }
+}
+
+/**
+ * idle_inject_get_duration - idle and run duration retrieval helper
+ * @run_duration_ms: memory location to store the current CPU run time
+ * @idle_duration_ms: memory location to store the current CPU idle time
+ */
+void idle_inject_get_duration(struct idle_inject_device *ii_dev,
+ unsigned int *run_duration_ms,
+ unsigned int *idle_duration_ms)
+{
+ *run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+ *idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+}
+
+/**
+ * idle_inject_start - start idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function starts idle injection by first waking up all of the idle
+ * injection kthreads associated with @ii_dev to let them inject CPU idle time
+ * sets up a timer to start the next idle injection period.
+ *
+ * Return: -EINVAL if the CPU idle or CPU run time is not set or 0 on success.
+ */
+int idle_inject_start(struct idle_inject_device *ii_dev)
+{
+ unsigned int idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+ unsigned int run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+
+ if (!idle_duration_ms || !run_duration_ms)
+ return -EINVAL;
+
+ pr_debug("Starting injecting idle cycles on CPUs '%*pbl'\n",
+ cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+ idle_inject_wakeup(ii_dev);
+
+ hrtimer_start(&ii_dev->timer,
+ ms_to_ktime(idle_duration_ms + run_duration_ms),
+ HRTIMER_MODE_REL);
+
+ return 0;
+}
+
+/**
+ * idle_inject_stop - stops idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function stops idle injection and waits for the threads to finish work.
+ * If CPU idle time is being injected when this function runs, then it will
+ * wait until the end of the cycle.
+ *
+ * When it returns, there is no more idle injection kthread activity. The
+ * kthreads are scheduled out and the periodic timer is off.
+ */
+void idle_inject_stop(struct idle_inject_device *ii_dev)
+{
+ struct idle_inject_thread *iit;
+ unsigned int cpu;
+
+ pr_debug("Stopping idle injection on CPUs '%*pbl'\n",
+ cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+ hrtimer_cancel(&ii_dev->timer);
+
+ /*
+ * Stopping idle injection requires all of the idle injection kthreads
+ * associated with the given cpumask to be parked and stay that way, so
+ * prevent CPUs from going online at this point. Any CPUs going online
+ * after the loop below will be covered by clearing the should_run flag
+ * that will cause the smpboot main loop to schedule them out.
+ */
+ cpu_hotplug_disable();
+
+ /*
+ * Iterate over all (online + offline) CPUs here in case one of them
+ * goes offline with the should_run flag set so as to prevent its idle
+ * injection kthread from running when the CPU goes online again after
+ * the ii_dev has been freed.
+ */
+ for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+ iit = per_cpu_ptr(&idle_inject_thread, cpu);
+ iit->should_run = 0;
+
+ wait_task_inactive(iit->tsk, 0);
+ }
+
+ cpu_hotplug_enable();
+}
+
+/**
+ * idle_inject_setup - prepare the current task for idle injection
+ * @cpu: not used
+ *
+ * Called once, this function is in charge of setting the current task's
+ * scheduler parameters to make it an RT task.
+ */
+static void idle_inject_setup(unsigned int cpu)
+{
+ struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
+
+ sched_setscheduler(current, SCHED_FIFO, ¶m);
+}
+
+/**
+ * idle_inject_should_run - function helper for the smpboot API
+ * @cpu: CPU the kthread is running on
+ *
+ * Return: whether or not the thread can run.
+ */
+static int idle_inject_should_run(unsigned int cpu)
+{
+ struct idle_inject_thread *iit =
+ per_cpu_ptr(&idle_inject_thread, cpu);
+
+ return iit->should_run;
+}
+
+/**
+ * idle_inject_register - initialize idle injection on a set of CPUs
+ * @cpumask: CPUs to be affected by idle injection
+ *
+ * This function creates an idle injection control device structure for the
+ * given set of CPUs and initializes the timer associated with it. It does not
+ * start any injection cycles.
+ *
+ * Return: NULL if memory allocation fails, idle injection control device
+ * pointer on success.
+ */
+struct idle_inject_device *idle_inject_register(struct cpumask *cpumask)
+{
+ struct idle_inject_device *ii_dev;
+ int cpu, cpu_rb;
+
+ ii_dev = kzalloc(sizeof(*ii_dev) + cpumask_size(), GFP_KERNEL);
+ if (!ii_dev)
+ return NULL;
+
+ cpumask_copy(to_cpumask(ii_dev->cpumask), cpumask);
+ hrtimer_init(&ii_dev->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ ii_dev->timer.function = idle_inject_timer_fn;
+
+ for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+
+ if (per_cpu(idle_inject_device, cpu)) {
+ pr_err("cpu%d is already registered\n", cpu);
+ goto out_rollback;
+ }
+
+ per_cpu(idle_inject_device, cpu) = ii_dev;
+ }
+
+ return ii_dev;
+
+out_rollback:
+ for_each_cpu(cpu_rb, to_cpumask(ii_dev->cpumask)) {
+ if (cpu == cpu_rb)
+ break;
+ per_cpu(idle_inject_device, cpu_rb) = NULL;
+ }
+
+ kfree(ii_dev);
+
+ return NULL;
+}
+
+/**
+ * idle_inject_unregister - unregister idle injection control device
+ * @ii_dev: idle injection control device to unregister
+ *
+ * The function stops idle injection for the given control device,
+ * unregisters its kthreads and frees memory allocated when that device was
+ * created.
+ */
+void idle_inject_unregister(struct idle_inject_device *ii_dev)
+{
+ unsigned int cpu;
+
+ idle_inject_stop(ii_dev);
+
+ for_each_cpu(cpu, to_cpumask(ii_dev->cpumask))
+ per_cpu(idle_inject_device, cpu) = NULL;
+
+ kfree(ii_dev);
+}
+
+static struct smp_hotplug_thread idle_inject_threads = {
+ .store = &idle_inject_thread.tsk,
+ .setup = idle_inject_setup,
+ .thread_fn = idle_inject_fn,
+ .thread_comm = "idle_inject/%u",
+ .thread_should_run = idle_inject_should_run,
+};
+
+static int __init idle_inject_init(void)
+{
+ return smpboot_register_percpu_thread(&idle_inject_threads);
+}
+early_initcall(idle_inject_init);
diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c
index 0097a93..546960a 100644
--- a/drivers/soc/imx/gpc.c
+++ b/drivers/soc/imx/gpc.c
@@ -209,7 +209,7 @@ static int imx_pgc_power_domain_probe(struct platform_device *pdev)
goto genpd_err;
}
- device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE);
+ device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE_CONSUMER);
return 0;
diff --git a/include/dt-bindings/clock/rk3399-ddr.h b/include/dt-bindings/clock/rk3399-ddr.h
new file mode 100644
index 0000000..ed22808
--- /dev/null
+++ b/include/dt-bindings/clock/rk3399-ddr.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */
+
+#ifndef DT_BINDINGS_DDR_H
+#define DT_BINDINGS_DDR_H
+
+/*
+ * DDR3 SDRAM Standard Speed Bins include tCK, tRCD, tRP, tRAS and tRC for
+ * each corresponding bin.
+ */
+
+/* DDR3-800 (5-5-5) */
+#define DDR3_800D 0
+/* DDR3-800 (6-6-6) */
+#define DDR3_800E 1
+/* DDR3-1066 (6-6-6) */
+#define DDR3_1066E 2
+/* DDR3-1066 (7-7-7) */
+#define DDR3_1066F 3
+/* DDR3-1066 (8-8-8) */
+#define DDR3_1066G 4
+/* DDR3-1333 (7-7-7) */
+#define DDR3_1333F 5
+/* DDR3-1333 (8-8-8) */
+#define DDR3_1333G 6
+/* DDR3-1333 (9-9-9) */
+#define DDR3_1333H 7
+/* DDR3-1333 (10-10-10) */
+#define DDR3_1333J 8
+/* DDR3-1600 (8-8-8) */
+#define DDR3_1600G 9
+/* DDR3-1600 (9-9-9) */
+#define DDR3_1600H 10
+/* DDR3-1600 (10-10-10) */
+#define DDR3_1600J 11
+/* DDR3-1600 (11-11-11) */
+#define DDR3_1600K 12
+/* DDR3-1600 (10-10-10) */
+#define DDR3_1866J 13
+/* DDR3-1866 (11-11-11) */
+#define DDR3_1866K 14
+/* DDR3-1866 (12-12-12) */
+#define DDR3_1866L 15
+/* DDR3-1866 (13-13-13) */
+#define DDR3_1866M 16
+/* DDR3-2133 (11-11-11) */
+#define DDR3_2133K 17
+/* DDR3-2133 (12-12-12) */
+#define DDR3_2133L 18
+/* DDR3-2133 (13-13-13) */
+#define DDR3_2133M 19
+/* DDR3-2133 (14-14-14) */
+#define DDR3_2133N 20
+/* DDR3 ATF default */
+#define DDR3_DEFAULT 21
+
+#endif
diff --git a/include/linux/device.h b/include/linux/device.h
index 055a69d..e809204 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -90,7 +90,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
* @num_vf: Called to find out how many virtual functions a device on this
* bus supports.
* @dma_configure: Called to setup DMA configuration on a device on
- this bus.
+ * this bus.
* @pm: Power management operations of this bus, callback the specific
* device driver's pm-ops.
* @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU
@@ -784,14 +784,16 @@ enum device_link_state {
* Device link flags.
*
* STATELESS: The core won't track the presence of supplier/consumer drivers.
- * AUTOREMOVE: Remove this link automatically on consumer driver unbind.
+ * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind.
* PM_RUNTIME: If set, the runtime PM framework will use this link.
* RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation.
+ * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind.
*/
-#define DL_FLAG_STATELESS BIT(0)
-#define DL_FLAG_AUTOREMOVE BIT(1)
-#define DL_FLAG_PM_RUNTIME BIT(2)
-#define DL_FLAG_RPM_ACTIVE BIT(3)
+#define DL_FLAG_STATELESS BIT(0)
+#define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1)
+#define DL_FLAG_PM_RUNTIME BIT(2)
+#define DL_FLAG_RPM_ACTIVE BIT(3)
+#define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4)
/**
* struct device_link - Device link representation.
diff --git a/include/linux/idle_inject.h b/include/linux/idle_inject.h
new file mode 100644
index 0000000..bdc0293
--- /dev/null
+++ b/include/linux/idle_inject.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Linaro Ltd
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ */
+#ifndef __IDLE_INJECT_H__
+#define __IDLE_INJECT_H__
+
+/* private idle injection device structure */
+struct idle_inject_device;
+
+struct idle_inject_device *idle_inject_register(struct cpumask *cpumask);
+
+void idle_inject_unregister(struct idle_inject_device *ii_dev);
+
+int idle_inject_start(struct idle_inject_device *ii_dev);
+
+void idle_inject_stop(struct idle_inject_device *ii_dev);
+
+void idle_inject_set_duration(struct idle_inject_device *ii_dev,
+ unsigned int run_duration_ms,
+ unsigned int idle_duration_ms);
+
+void idle_inject_get_duration(struct idle_inject_device *ii_dev,
+ unsigned int *run_duration_ms,
+ unsigned int *idle_duration_ms);
+#endif /* __IDLE_INJECT_H__ */
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index cb8d840..776c546 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -239,6 +239,8 @@ unsigned int of_genpd_opp_to_performance_state(struct device *dev,
int genpd_dev_pm_attach(struct device *dev);
struct device *genpd_dev_pm_attach_by_id(struct device *dev,
unsigned int index);
+struct device *genpd_dev_pm_attach_by_name(struct device *dev,
+ char *name);
#else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
static inline int of_genpd_add_provider_simple(struct device_node *np,
struct generic_pm_domain *genpd)
@@ -290,6 +292,12 @@ static inline struct device *genpd_dev_pm_attach_by_id(struct device *dev,
return NULL;
}
+static inline struct device *genpd_dev_pm_attach_by_name(struct device *dev,
+ char *name)
+{
+ return NULL;
+}
+
static inline
struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
{
@@ -301,6 +309,8 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
int dev_pm_domain_attach(struct device *dev, bool power_on);
struct device *dev_pm_domain_attach_by_id(struct device *dev,
unsigned int index);
+struct device *dev_pm_domain_attach_by_name(struct device *dev,
+ char *name);
void dev_pm_domain_detach(struct device *dev, bool power_off);
void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd);
#else
@@ -313,6 +323,11 @@ static inline struct device *dev_pm_domain_attach_by_id(struct device *dev,
{
return NULL;
}
+static inline struct device *dev_pm_domain_attach_by_name(struct device *dev,
+ char *name)
+{
+ return NULL;
+}
static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {}
static inline void dev_pm_domain_set(struct device *dev,
struct dev_pm_domain *pd) {}
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 440b62f..5a28ac9 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -414,7 +414,7 @@ static inline bool hibernation_available(void) { return false; }
#define PM_RESTORE_PREPARE 0x0005 /* Going to restore a saved image */
#define PM_POST_RESTORE 0x0006 /* Restore failed */
-extern struct mutex pm_mutex;
+extern struct mutex system_transition_mutex;
#ifdef CONFIG_PM_SLEEP
void save_processor_state(void);
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 6f56a9e..b162b74 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -15,7 +15,9 @@
atomic_t system_freezing_cnt = ATOMIC_INIT(0);
EXPORT_SYMBOL(system_freezing_cnt);
-/* indicate whether PM freezing is in effect, protected by pm_mutex */
+/* indicate whether PM freezing is in effect, protected by
+ * system_transition_mutex
+ */
bool pm_freezing;
bool pm_nosig_freezing;
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 9c85c78..abef759d 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -338,7 +338,7 @@ static int create_image(int platform_mode)
* hibernation_snapshot - Quiesce devices and create a hibernation image.
* @platform_mode: If set, use platform driver to prepare for the transition.
*
- * This routine must be called with pm_mutex held.
+ * This routine must be called with system_transition_mutex held.
*/
int hibernation_snapshot(int platform_mode)
{
@@ -500,8 +500,9 @@ static int resume_target_kernel(bool platform_mode)
* hibernation_restore - Quiesce devices and restore from a hibernation image.
* @platform_mode: If set, use platform driver to prepare for the transition.
*
- * This routine must be called with pm_mutex held. If it is successful, control
- * reappears in the restored target kernel in hibernation_snapshot().
+ * This routine must be called with system_transition_mutex held. If it is
+ * successful, control reappears in the restored target kernel in
+ * hibernation_snapshot().
*/
int hibernation_restore(int platform_mode)
{
@@ -638,6 +639,7 @@ static void power_down(void)
break;
case HIBERNATION_PLATFORM:
hibernation_platform_enter();
+ /* Fall through */
case HIBERNATION_SHUTDOWN:
if (pm_power_off)
kernel_power_off();
@@ -805,13 +807,13 @@ static int software_resume(void)
* name_to_dev_t() below takes a sysfs buffer mutex when sysfs
* is configured into the kernel. Since the regular hibernate
* trigger path is via sysfs which takes a buffer mutex before
- * calling hibernate functions (which take pm_mutex) this can
- * cause lockdep to complain about a possible ABBA deadlock
+ * calling hibernate functions (which take system_transition_mutex)
+ * this can cause lockdep to complain about a possible ABBA deadlock
* which cannot happen since we're in the boot code here and
* sysfs can't be invoked yet. Therefore, we use a subclass
* here to avoid lockdep complaining.
*/
- mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING);
+ mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING);
if (swsusp_resume_device)
goto Check_image;
@@ -899,7 +901,7 @@ static int software_resume(void)
atomic_inc(&snapshot_device_available);
/* For success case, the suspend path will release the lock */
Unlock:
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
return error;
Close_Finish:
diff --git a/kernel/power/main.c b/kernel/power/main.c
index d9706da..35b5082 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -15,17 +15,16 @@
#include <linux/workqueue.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <linux/suspend.h>
#include "power.h"
-DEFINE_MUTEX(pm_mutex);
-
#ifdef CONFIG_PM_SLEEP
void lock_system_sleep(void)
{
current->flags |= PF_FREEZER_SKIP;
- mutex_lock(&pm_mutex);
+ mutex_lock(&system_transition_mutex);
}
EXPORT_SYMBOL_GPL(lock_system_sleep);
@@ -37,8 +36,9 @@ void unlock_system_sleep(void)
*
* Reason:
* Fundamentally, we just don't need it, because freezing condition
- * doesn't come into effect until we release the pm_mutex lock,
- * since the freezer always works with pm_mutex held.
+ * doesn't come into effect until we release the
+ * system_transition_mutex lock, since the freezer always works with
+ * system_transition_mutex held.
*
* More importantly, in the case of hibernation,
* unlock_system_sleep() gets called in snapshot_read() and
@@ -47,7 +47,7 @@ void unlock_system_sleep(void)
* enter the refrigerator, thus causing hibernation to lockup.
*/
current->flags &= ~PF_FREEZER_SKIP;
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
}
EXPORT_SYMBOL_GPL(unlock_system_sleep);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 8733156..9e13afe 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -556,7 +556,7 @@ static int enter_state(suspend_state_t state)
} else if (!valid_state(state)) {
return -EINVAL;
}
- if (!mutex_trylock(&pm_mutex))
+ if (!mutex_trylock(&system_transition_mutex))
return -EBUSY;
if (state == PM_SUSPEND_TO_IDLE)
@@ -590,7 +590,7 @@ static int enter_state(suspend_state_t state)
pm_pr_dbg("Finishing wakeup.\n");
suspend_finish();
Unlock:
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
return error;
}
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index c2bcf97..d7f6c1a 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -923,7 +923,7 @@ int swsusp_write(unsigned int flags)
}
memset(&snapshot, 0, sizeof(struct snapshot_handle));
error = snapshot_read_next(&snapshot);
- if (error < PAGE_SIZE) {
+ if (error < (int)PAGE_SIZE) {
if (error >= 0)
error = -EFAULT;
@@ -1483,7 +1483,7 @@ int swsusp_read(unsigned int *flags_p)
memset(&snapshot, 0, sizeof(struct snapshot_handle));
error = snapshot_write_next(&snapshot);
- if (error < PAGE_SIZE)
+ if (error < (int)PAGE_SIZE)
return error < 0 ? error : -EFAULT;
header = (struct swsusp_info *)data_of(snapshot);
error = get_swap_reader(&handle, flags_p);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index abd2255..2d8b60a 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -216,7 +216,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!mutex_trylock(&pm_mutex))
+ if (!mutex_trylock(&system_transition_mutex))
return -EBUSY;
lock_device_hotplug();
@@ -394,7 +394,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
}
unlock_device_hotplug();
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
return error;
}
diff --git a/kernel/reboot.c b/kernel/reboot.c
index e4ced88..8fb44de 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -294,7 +294,7 @@ void kernel_power_off(void)
}
EXPORT_SYMBOL_GPL(kernel_power_off);
-static DEFINE_MUTEX(reboot_mutex);
+DEFINE_MUTEX(system_transition_mutex);
/*
* Reboot system call: for obvious reasons only root may call it,
@@ -338,7 +338,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
cmd = LINUX_REBOOT_CMD_HALT;
- mutex_lock(&reboot_mutex);
+ mutex_lock(&system_transition_mutex);
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART:
kernel_restart(NULL);
@@ -389,7 +389,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
ret = -EINVAL;
break;
}
- mutex_unlock(&reboot_mutex);
+ mutex_unlock(&system_transition_mutex);
return ret;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a790ef4..3674e42 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -155,16 +155,17 @@ static inline void set_pcppage_migratetype(struct page *page, int migratetype)
* The following functions are used by the suspend/hibernate code to temporarily
* change gfp_allowed_mask in order to avoid using I/O during memory allocations
* while devices are suspended. To avoid races with the suspend/hibernate code,
- * they should always be called with pm_mutex held (gfp_allowed_mask also should
- * only be modified with pm_mutex held, unless the suspend/hibernate code is
- * guaranteed not to run in parallel with that modification).
+ * they should always be called with system_transition_mutex held
+ * (gfp_allowed_mask also should only be modified with system_transition_mutex
+ * held, unless the suspend/hibernate code is guaranteed not to run in parallel
+ * with that modification).
*/
static gfp_t saved_gfp_mask;
void pm_restore_gfp_mask(void)
{
- WARN_ON(!mutex_is_locked(&pm_mutex));
+ WARN_ON(!mutex_is_locked(&system_transition_mutex));
if (saved_gfp_mask) {
gfp_allowed_mask = saved_gfp_mask;
saved_gfp_mask = 0;
@@ -173,7 +174,7 @@ void pm_restore_gfp_mask(void)
void pm_restrict_gfp_mask(void)
{
- WARN_ON(!mutex_is_locked(&pm_mutex));
+ WARN_ON(!mutex_is_locked(&system_transition_mutex));
WARN_ON(saved_gfp_mask);
saved_gfp_mask = gfp_allowed_mask;
gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index d39e4ff..a6db83a 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -106,7 +106,7 @@
\fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3.... The system summary is the average of all CPUs in the system. Note that these are software, reflecting what was requested. The hardware counters reflect what was actually achieved.
\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. These numbers are from hardware residency counters.
\fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
-\fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
+\fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms.
\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz.
\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters.
@@ -114,7 +114,7 @@
\fBCorWatt\fP Watts consumed by the core part of the package.
\fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors.
\fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors.
-\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.
+\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system. Note that the meaning of this field is model specific. For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits. Comparing PkgWatt and PkgTmp to system limits is necessary.
\fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM.
.fi
.SH TOO MUCH INFORMATION EXAMPLE
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 4d14bbb..980bd9d 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1163,9 +1163,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_
if (!printed || !summary_only)
print_header("\t");
- if (topo.num_cpus > 1)
- format_counters(&average.threads, &average.cores,
- &average.packages);
+ format_counters(&average.threads, &average.cores, &average.packages);
printed = 1;
@@ -1692,7 +1690,7 @@ void get_apic_id(struct thread_data *t)
t->x2apic_id = edx;
if (debug && (t->apic_id != t->x2apic_id))
- fprintf(stderr, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id);
+ fprintf(outf, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id);
}
/*
@@ -2473,55 +2471,43 @@ int get_core_id(int cpu)
void set_node_data(void)
{
- char path[80];
- FILE *filep;
- int pkg, node, cpu;
+ int pkg, node, lnode, cpu, cpux;
+ int cpu_count;
- struct pkg_node_info {
- int count;
- int min;
- } *pni;
+ /* initialize logical_node_id */
+ for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu)
+ cpus[cpu].logical_node_id = -1;
- pni = calloc(topo.num_packages, sizeof(struct pkg_node_info));
- if (!pni)
- err(1, "calloc pkg_node_count");
-
- for (pkg = 0; pkg < topo.num_packages; pkg++)
- pni[pkg].min = topo.num_cpus;
-
- for (node = 0; node <= topo.max_node_num; node++) {
- /* find the "first" cpu in the node */
- sprintf(path, "/sys/bus/node/devices/node%d/cpulist", node);
- filep = fopen(path, "r");
- if (!filep)
- continue;
- fscanf(filep, "%d", &cpu);
- fclose(filep);
-
- pkg = cpus[cpu].physical_package_id;
- pni[pkg].count++;
-
- if (node < pni[pkg].min)
- pni[pkg].min = node;
+ cpu_count = 0;
+ for (pkg = 0; pkg < topo.num_packages; pkg++) {
+ lnode = 0;
+ for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu) {
+ if (cpus[cpu].physical_package_id != pkg)
+ continue;
+ /* find a cpu with an unset logical_node_id */
+ if (cpus[cpu].logical_node_id != -1)
+ continue;
+ cpus[cpu].logical_node_id = lnode;
+ node = cpus[cpu].physical_node_id;
+ cpu_count++;
+ /*
+ * find all matching cpus on this pkg and set
+ * the logical_node_id
+ */
+ for (cpux = cpu; cpux <= topo.max_cpu_num; cpux++) {
+ if ((cpus[cpux].physical_package_id == pkg) &&
+ (cpus[cpux].physical_node_id == node)) {
+ cpus[cpux].logical_node_id = lnode;
+ cpu_count++;
+ }
+ }
+ lnode++;
+ if (lnode > topo.nodes_per_pkg)
+ topo.nodes_per_pkg = lnode;
+ }
+ if (cpu_count >= topo.max_cpu_num)
+ break;
}
-
- for (pkg = 0; pkg < topo.num_packages; pkg++)
- if (pni[pkg].count > topo.nodes_per_pkg)
- topo.nodes_per_pkg = pni[0].count;
-
- /* Fake 1 node per pkg for machines that don't
- * expose nodes and thus avoid -nan results
- */
- if (topo.nodes_per_pkg == 0)
- topo.nodes_per_pkg = 1;
-
- for (cpu = 0; cpu < topo.num_cpus; cpu++) {
- pkg = cpus[cpu].physical_package_id;
- node = cpus[cpu].physical_node_id;
- cpus[cpu].logical_node_id = node - pni[pkg].min;
- }
- free(pni);
-
}
int get_physical_node_id(struct cpu_topology *thiscpu)
@@ -4471,7 +4457,9 @@ void process_cpuid()
family = (fms >> 8) & 0xf;
model = (fms >> 4) & 0xf;
stepping = fms & 0xf;
- if (family == 6 || family == 0xf)
+ if (family == 0xf)
+ family += (fms >> 20) & 0xff;
+ if (family >= 6)
model += ((fms >> 16) & 0xf) << 4;
if (!quiet) {
@@ -4840,16 +4828,8 @@ void topology_probe()
siblings = get_thread_siblings(&cpus[i]);
if (siblings > max_siblings)
max_siblings = siblings;
- if (cpus[i].thread_id != -1)
+ if (cpus[i].thread_id == 0)
topo.num_cores++;
-
- if (debug > 1)
- fprintf(outf,
- "cpu %d pkg %d node %d core %d thread %d\n",
- i, cpus[i].physical_package_id,
- cpus[i].physical_node_id,
- cpus[i].physical_core_id,
- cpus[i].thread_id);
}
topo.cores_per_node = max_core_id + 1;
@@ -4875,6 +4855,20 @@ void topology_probe()
topo.threads_per_core = max_siblings;
if (debug > 1)
fprintf(outf, "max_siblings %d\n", max_siblings);
+
+ if (debug < 1)
+ return;
+
+ for (i = 0; i <= topo.max_cpu_num; ++i) {
+ fprintf(outf,
+ "cpu %d pkg %d node %d lnode %d core %d thread %d\n",
+ i, cpus[i].physical_package_id,
+ cpus[i].physical_node_id,
+ cpus[i].logical_node_id,
+ cpus[i].physical_core_id,
+ cpus[i].thread_id);
+ }
+
}
void
@@ -5102,7 +5096,7 @@ int get_and_dump_counters(void)
}
void print_version() {
- fprintf(outf, "turbostat version 18.06.20"
+ fprintf(outf, "turbostat version 18.07.27"
" - Len Brown <lenb@kernel.org>\n");
}
