summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-06-12 13:14:19 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2014-06-12 13:14:19 -0700
commit19c1940feab777bb037c665a09f495d08a6c4e6c (patch)
tree68d4de31f30c9d69a1f1ea080b8a69ce61e1ead5
parent7c574cf6aeb75920ba4d3af937bb1b3c42785ac4 (diff)
parentd715a226b0b3dae48865d05e8c36175a8f75a809 (diff)
Merge tag 'pm+acpi-3.16-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull more ACPI and power management updates from Rafael Wysocki: "These are fixups on top of the previous PM+ACPI pull request, regression fixes (ACPI hotplug, cpufreq ppc-corenet), other bug fixes (ACPI reset, cpufreq), new PM trace points for system suspend profiling and a copyright notice update. Specifics: - I didn't remember correctly that the Hans de Goede's ACPI video patches actually didn't flip the video.use_native_backlight default, although we had discussed that and decided to do that. Since I said we would do that in the previous PM+ACPI pull request, make that change for real now. - ACPI bus check notifications for PCI host bridges don't cause the bus below the host bridge to be checked for changes as they should because of a mistake in the ACPI-based PCI hotplug (ACPIPHP) subsystem that forgets to add hotplug contexts to PCI host bridge ACPI device objects. Create hotplug contexts for PCI host bridges too as appropriate. - Revert recent cpufreq commit related to the big.LITTLE cpufreq driver that breaks arm64 builds. - Fix for a regression in the ppc-corenet cpufreq driver introduced during the 3.15 cycle and causing the driver to use the remainder from do_div instead of the quotient. From Ed Swarthout. - Resets triggered by panic activate a BUG_ON() in vmalloc.c on systems where the ACPI reset register is located in memory address space. Fix from Randy Wright. - Fix for a problem with cpufreq governors that decisions made by them may be suboptimal due to the fact that deferrable timers are used by them for CPU load sampling. From Srivatsa S Bhat. - Fix for a problem with the Tegra cpufreq driver where the CPU frequency is temporarily switched to a "stable" level that is different from both the initial and target frequencies during transitions which causes udelay() to expire earlier than it should sometimes. From Viresh Kumar. - New trace points and rework of some existing trace points for system suspend/resume profiling from Todd Brandt. - Assorted cpufreq fixes and cleanups from Stratos Karafotis and Viresh Kumar. - Copyright notice update for suspend-and-cpuhotplug.txt from Srivatsa S Bhat" * tag 'pm+acpi-3.16-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: ACPI / hotplug / PCI: Add hotplug contexts to PCI host bridges PM / sleep: trace events for device PM callbacks cpufreq: cpufreq-cpu0: remove dependency on THERMAL and REGULATOR cpufreq: tegra: update comment for clarity cpufreq: intel_pstate: Remove duplicate CPU ID check cpufreq: Mark CPU0 driver with CPUFREQ_NEED_INITIAL_FREQ_CHECK flag PM / Documentation: Update copyright in suspend-and-cpuhotplug.txt cpufreq: governor: remove copy_prev_load from 'struct cpu_dbs_common_info' cpufreq: governor: Be friendly towards latency-sensitive bursty workloads PM / sleep: trace events for suspend/resume cpufreq: ppc-corenet-cpu-freq: do_div use quotient Revert "cpufreq: Enable big.LITTLE cpufreq driver on arm64" cpufreq: Tegra: implement intermediate frequency callbacks cpufreq: add support for intermediate (stable) frequencies ACPI / video: Change the default for video.use_native_backlight to 1 ACPI: Fix bug when ACPI reset register is implemented in system memory
-rw-r--r--Documentation/cpu-freq/cpu-drivers.txt29
-rw-r--r--Documentation/power/suspend-and-cpuhotplug.txt2
-rw-r--r--drivers/acpi/osl.c12
-rw-r--r--drivers/acpi/sleep.c3
-rw-r--r--drivers/acpi/video.c2
-rw-r--r--drivers/base/power/main.c30
-rw-r--r--drivers/base/syscore.c5
-rw-r--r--drivers/cpufreq/Kconfig2
-rw-r--r--drivers/cpufreq/Kconfig.arm3
-rw-r--r--drivers/cpufreq/cpufreq-cpu0.c2
-rw-r--r--drivers/cpufreq/cpufreq.c67
-rw-r--r--drivers/cpufreq/cpufreq_governor.c67
-rw-r--r--drivers/cpufreq/cpufreq_governor.h7
-rw-r--r--drivers/cpufreq/intel_pstate.c6
-rw-r--r--drivers/cpufreq/ppc-corenet-cpufreq.c9
-rw-r--r--drivers/cpufreq/tegra-cpufreq.c100
-rw-r--r--drivers/pci/hotplug/acpiphp.h10
-rw-r--r--drivers/pci/hotplug/acpiphp_glue.c60
-rw-r--r--include/linux/cpufreq.h25
-rw-r--r--include/trace/events/power.h84
-rw-r--r--kernel/cpu.c5
-rw-r--r--kernel/power/hibernate.c3
-rw-r--r--kernel/power/process.c3
-rw-r--r--kernel/power/suspend.c14
24 files changed, 437 insertions, 113 deletions
diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt
index b045fe54986..14f4e6336d8 100644
--- a/Documentation/cpu-freq/cpu-drivers.txt
+++ b/Documentation/cpu-freq/cpu-drivers.txt
@@ -26,6 +26,7 @@ Contents:
1.4 target/target_index or setpolicy?
1.5 target/target_index
1.6 setpolicy
+1.7 get_intermediate and target_intermediate
2. Frequency Table Helpers
@@ -79,6 +80,10 @@ cpufreq_driver.attr - A pointer to a NULL-terminated list of
"struct freq_attr" which allow to
export values to sysfs.
+cpufreq_driver.get_intermediate
+and target_intermediate Used to switch to stable frequency while
+ changing CPU frequency.
+
1.2 Per-CPU Initialization
--------------------------
@@ -151,7 +156,7 @@ Some cpufreq-capable processors switch the frequency between certain
limits on their own. These shall use the ->setpolicy call
-1.4. target/target_index
+1.5. target/target_index
-------------
The target_index call has two arguments: struct cpufreq_policy *policy,
@@ -160,6 +165,9 @@ and unsigned int index (into the exposed frequency table).
The CPUfreq driver must set the new frequency when called here. The
actual frequency must be determined by freq_table[index].frequency.
+It should always restore to earlier frequency (i.e. policy->restore_freq) in
+case of errors, even if we switched to intermediate frequency earlier.
+
Deprecated:
----------
The target call has three arguments: struct cpufreq_policy *policy,
@@ -179,7 +187,7 @@ Here again the frequency table helper might assist you - see section 2
for details.
-1.5 setpolicy
+1.6 setpolicy
---------------
The setpolicy call only takes a struct cpufreq_policy *policy as
@@ -190,6 +198,23 @@ setting when policy->policy is CPUFREQ_POLICY_PERFORMANCE, and a
powersaving-oriented setting when CPUFREQ_POLICY_POWERSAVE. Also check
the reference implementation in drivers/cpufreq/longrun.c
+1.7 get_intermediate and target_intermediate
+--------------------------------------------
+
+Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION unset.
+
+get_intermediate should return a stable intermediate frequency platform wants to
+switch to, and target_intermediate() should set CPU to to that frequency, before
+jumping to the frequency corresponding to 'index'. Core will take care of
+sending notifications and driver doesn't have to handle them in
+target_intermediate() or target_index().
+
+Drivers can return '0' from get_intermediate() in case they don't wish to switch
+to intermediate frequency for some target frequency. In that case core will
+directly call ->target_index().
+
+NOTE: ->target_index() should restore to policy->restore_freq in case of
+failures as core would send notifications for that.
2. Frequency Table Helpers
diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt
index e13dafc8e8f..2850df3bf95 100644
--- a/Documentation/power/suspend-and-cpuhotplug.txt
+++ b/Documentation/power/suspend-and-cpuhotplug.txt
@@ -1,6 +1,6 @@
Interaction of Suspend code (S3) with the CPU hotplug infrastructure
- (C) 2011 Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
+ (C) 2011 - 2014 Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
I. How does the regular CPU hotplug code differ from how the Suspend-to-RAM
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 147bc1b91b4..3f2bdc812d2 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -1810,6 +1810,16 @@ acpi_status __init acpi_os_initialize(void)
acpi_os_map_generic_address(&acpi_gbl_FADT.xpm1b_event_block);
acpi_os_map_generic_address(&acpi_gbl_FADT.xgpe0_block);
acpi_os_map_generic_address(&acpi_gbl_FADT.xgpe1_block);
+ if (acpi_gbl_FADT.flags & ACPI_FADT_RESET_REGISTER) {
+ /*
+ * Use acpi_os_map_generic_address to pre-map the reset
+ * register if it's in system memory.
+ */
+ int rv;
+
+ rv = acpi_os_map_generic_address(&acpi_gbl_FADT.reset_register);
+ pr_debug(PREFIX "%s: map reset_reg status %d\n", __func__, rv);
+ }
return AE_OK;
}
@@ -1838,6 +1848,8 @@ acpi_status acpi_os_terminate(void)
acpi_os_unmap_generic_address(&acpi_gbl_FADT.xgpe0_block);
acpi_os_unmap_generic_address(&acpi_gbl_FADT.xpm1b_event_block);
acpi_os_unmap_generic_address(&acpi_gbl_FADT.xpm1a_event_block);
+ if (acpi_gbl_FADT.flags & ACPI_FADT_RESET_REGISTER)
+ acpi_os_unmap_generic_address(&acpi_gbl_FADT.reset_register);
destroy_workqueue(kacpid_wq);
destroy_workqueue(kacpi_notify_wq);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index c11e3795431..b3e3cc73ba7 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -19,6 +19,7 @@
#include <linux/acpi.h>
#include <linux/module.h>
#include <asm/io.h>
+#include <trace/events/power.h>
#include "internal.h"
#include "sleep.h"
@@ -501,6 +502,7 @@ static int acpi_suspend_enter(suspend_state_t pm_state)
ACPI_FLUSH_CPU_CACHE();
+ trace_suspend_resume(TPS("acpi_suspend"), acpi_state, true);
switch (acpi_state) {
case ACPI_STATE_S1:
barrier();
@@ -516,6 +518,7 @@ static int acpi_suspend_enter(suspend_state_t pm_state)
pr_info(PREFIX "Low-level resume complete\n");
break;
}
+ trace_suspend_resume(TPS("acpi_suspend"), acpi_state, false);
/* This violates the spec but is required for bug compatibility. */
acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1);
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 101fb090dcb..fb9ffe9adc6 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -82,7 +82,7 @@ module_param(allow_duplicates, bool, 0644);
* For Windows 8 systems: used to decide if video module
* should skip registering backlight interface of its own.
*/
-static int use_native_backlight_param = -1;
+static int use_native_backlight_param = 1;
module_param_named(use_native_backlight, use_native_backlight_param, int, 0444);
static bool use_native_backlight_dmi = false;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 343ffad5937..bf412961a93 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -214,9 +214,6 @@ static void initcall_debug_report(struct device *dev, ktime_t calltime,
pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev),
error, (unsigned long long)nsecs >> 10);
}
-
- trace_device_pm_report_time(dev, info, nsecs, pm_verb(state.event),
- error);
}
/**
@@ -387,7 +384,9 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev,
calltime = initcall_debug_start(dev);
pm_dev_dbg(dev, state, info);
+ trace_device_pm_callback_start(dev, info, state.event);
error = cb(dev);
+ trace_device_pm_callback_end(dev, error);
suspend_report_result(cb, error);
initcall_debug_report(dev, calltime, error, state, info);
@@ -545,6 +544,7 @@ static void dpm_resume_noirq(pm_message_t state)
struct device *dev;
ktime_t starttime = ktime_get();
+ trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, true);
mutex_lock(&dpm_list_mtx);
pm_transition = state;
@@ -587,6 +587,7 @@ static void dpm_resume_noirq(pm_message_t state)
dpm_show_time(starttime, state, "noirq");
resume_device_irqs();
cpuidle_resume();
+ trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false);
}
/**
@@ -664,6 +665,7 @@ static void dpm_resume_early(pm_message_t state)
struct device *dev;
ktime_t starttime = ktime_get();
+ trace_suspend_resume(TPS("dpm_resume_early"), state.event, true);
mutex_lock(&dpm_list_mtx);
pm_transition = state;
@@ -703,6 +705,7 @@ static void dpm_resume_early(pm_message_t state)
mutex_unlock(&dpm_list_mtx);
async_synchronize_full();
dpm_show_time(starttime, state, "early");
+ trace_suspend_resume(TPS("dpm_resume_early"), state.event, false);
}
/**
@@ -834,6 +837,7 @@ void dpm_resume(pm_message_t state)
struct device *dev;
ktime_t starttime = ktime_get();
+ trace_suspend_resume(TPS("dpm_resume"), state.event, true);
might_sleep();
mutex_lock(&dpm_list_mtx);
@@ -875,6 +879,7 @@ void dpm_resume(pm_message_t state)
dpm_show_time(starttime, state, NULL);
cpufreq_resume();
+ trace_suspend_resume(TPS("dpm_resume"), state.event, false);
}
/**
@@ -913,7 +918,9 @@ static void device_complete(struct device *dev, pm_message_t state)
if (callback) {
pm_dev_dbg(dev, state, info);
+ trace_device_pm_callback_start(dev, info, state.event);
callback(dev);
+ trace_device_pm_callback_end(dev, 0);
}
device_unlock(dev);
@@ -932,6 +939,7 @@ void dpm_complete(pm_message_t state)
{
struct list_head list;
+ trace_suspend_resume(TPS("dpm_complete"), state.event, true);
might_sleep();
INIT_LIST_HEAD(&list);
@@ -951,6 +959,7 @@ void dpm_complete(pm_message_t state)
}
list_splice(&list, &dpm_list);
mutex_unlock(&dpm_list_mtx);
+ trace_suspend_resume(TPS("dpm_complete"), state.event, false);
}
/**
@@ -1086,6 +1095,7 @@ static int dpm_suspend_noirq(pm_message_t state)
ktime_t starttime = ktime_get();
int error = 0;
+ trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true);
cpuidle_pause();
suspend_device_irqs();
mutex_lock(&dpm_list_mtx);
@@ -1126,6 +1136,7 @@ static int dpm_suspend_noirq(pm_message_t state)
} else {
dpm_show_time(starttime, state, "noirq");
}
+ trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, false);
return error;
}
@@ -1222,6 +1233,7 @@ static int dpm_suspend_late(pm_message_t state)
ktime_t starttime = ktime_get();
int error = 0;
+ trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true);
mutex_lock(&dpm_list_mtx);
pm_transition = state;
async_error = 0;
@@ -1257,6 +1269,7 @@ static int dpm_suspend_late(pm_message_t state)
} else {
dpm_show_time(starttime, state, "late");
}
+ trace_suspend_resume(TPS("dpm_suspend_late"), state.event, false);
return error;
}
@@ -1295,7 +1308,9 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
calltime = initcall_debug_start(dev);
+ trace_device_pm_callback_start(dev, info, state.event);
error = cb(dev, state);
+ trace_device_pm_callback_end(dev, error);
suspend_report_result(cb, error);
initcall_debug_report(dev, calltime, error, state, info);
@@ -1461,6 +1476,7 @@ int dpm_suspend(pm_message_t state)
ktime_t starttime = ktime_get();
int error = 0;
+ trace_suspend_resume(TPS("dpm_suspend"), state.event, true);
might_sleep();
cpufreq_suspend();
@@ -1498,6 +1514,7 @@ int dpm_suspend(pm_message_t state)
dpm_save_failed_step(SUSPEND_SUSPEND);
} else
dpm_show_time(starttime, state, NULL);
+ trace_suspend_resume(TPS("dpm_suspend"), state.event, false);
return error;
}
@@ -1549,8 +1566,11 @@ static int device_prepare(struct device *dev, pm_message_t state)
callback = dev->driver->pm->prepare;
}
- if (callback)
+ if (callback) {
+ trace_device_pm_callback_start(dev, info, state.event);
ret = callback(dev);
+ trace_device_pm_callback_end(dev, ret);
+ }
device_unlock(dev);
@@ -1582,6 +1602,7 @@ int dpm_prepare(pm_message_t state)
{
int error = 0;
+ trace_suspend_resume(TPS("dpm_prepare"), state.event, true);
might_sleep();
mutex_lock(&dpm_list_mtx);
@@ -1612,6 +1633,7 @@ int dpm_prepare(pm_message_t state)
put_device(dev);
}
mutex_unlock(&dpm_list_mtx);
+ trace_suspend_resume(TPS("dpm_prepare"), state.event, false);
return error;
}
diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c
index e8d11b6630e..dbb8350ea8d 100644
--- a/drivers/base/syscore.c
+++ b/drivers/base/syscore.c
@@ -10,6 +10,7 @@
#include <linux/mutex.h>
#include <linux/module.h>
#include <linux/interrupt.h>
+#include <trace/events/power.h>
static LIST_HEAD(syscore_ops_list);
static DEFINE_MUTEX(syscore_ops_lock);
@@ -49,6 +50,7 @@ int syscore_suspend(void)
struct syscore_ops *ops;
int ret = 0;
+ trace_suspend_resume(TPS("syscore_suspend"), 0, true);
pr_debug("Checking wakeup interrupts\n");
/* Return error code if there are any wakeup interrupts pending. */
@@ -70,6 +72,7 @@ int syscore_suspend(void)
"Interrupts enabled after %pF\n", ops->suspend);
}
+ trace_suspend_resume(TPS("syscore_suspend"), 0, false);
return 0;
err_out:
@@ -92,6 +95,7 @@ void syscore_resume(void)
{
struct syscore_ops *ops;
+ trace_suspend_resume(TPS("syscore_resume"), 0, true);
WARN_ONCE(!irqs_disabled(),
"Interrupts enabled before system core resume.\n");
@@ -103,6 +107,7 @@ void syscore_resume(void)
WARN_ONCE(!irqs_disabled(),
"Interrupts enabled after %pF\n", ops->resume);
}
+ trace_suspend_resume(TPS("syscore_resume"), 0, false);
}
EXPORT_SYMBOL_GPL(syscore_resume);
#endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 1fbe11f2a14..e473d6555f9 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -185,7 +185,7 @@ config CPU_FREQ_GOV_CONSERVATIVE
config GENERIC_CPUFREQ_CPU0
tristate "Generic CPU0 cpufreq driver"
- depends on HAVE_CLK && REGULATOR && OF && THERMAL && CPU_THERMAL
+ depends on HAVE_CLK && OF
select PM_OPP
help
This adds a generic cpufreq driver for CPU0 frequency management.
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 36d20d0fce2..ebac6711500 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -5,8 +5,7 @@
# big LITTLE core layer and glue drivers
config ARM_BIG_LITTLE_CPUFREQ
tristate "Generic ARM big LITTLE CPUfreq driver"
- depends on (BIG_LITTLE && ARM_CPU_TOPOLOGY) || (ARM64 && SMP)
- depends on HAVE_CLK
+ depends on ARM && BIG_LITTLE && ARM_CPU_TOPOLOGY && HAVE_CLK
select PM_OPP
help
This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index 09b9129c7bd..ee1ae303a07 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -104,7 +104,7 @@ static int cpu0_cpufreq_init(struct cpufreq_policy *policy)
}
static struct cpufreq_driver cpu0_cpufreq_driver = {
- .flags = CPUFREQ_STICKY,
+ .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
.verify = cpufreq_generic_frequency_table_verify,
.target_index = cpu0_set_target,
.get = cpufreq_generic_get,
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index ae11dd51f81..aed2b0cb83d 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1816,20 +1816,55 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier);
* GOVERNORS *
*********************************************************************/
+/* Must set freqs->new to intermediate frequency */
+static int __target_intermediate(struct cpufreq_policy *policy,
+ struct cpufreq_freqs *freqs, int index)
+{
+ int ret;
+
+ freqs->new = cpufreq_driver->get_intermediate(policy, index);
+
+ /* We don't need to switch to intermediate freq */
+ if (!freqs->new)
+ return 0;
+
+ pr_debug("%s: cpu: %d, switching to intermediate freq: oldfreq: %u, intermediate freq: %u\n",
+ __func__, policy->cpu, freqs->old, freqs->new);
+
+ cpufreq_freq_transition_begin(policy, freqs);
+ ret = cpufreq_driver->target_intermediate(policy, index);
+ cpufreq_freq_transition_end(policy, freqs, ret);
+
+ if (ret)
+ pr_err("%s: Failed to change to intermediate frequency: %d\n",
+ __func__, ret);
+
+ return ret;
+}
+
static int __target_index(struct cpufreq_policy *policy,
struct cpufreq_frequency_table *freq_table, int index)
{
- struct cpufreq_freqs freqs;
+ struct cpufreq_freqs freqs = {.old = policy->cur, .flags = 0};
+ unsigned int intermediate_freq = 0;
int retval = -EINVAL;
bool notify;
notify = !(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION);
-
if (notify) {
- freqs.old = policy->cur;
- freqs.new = freq_table[index].frequency;
- freqs.flags = 0;
+ /* Handle switching to intermediate frequency */
+ if (cpufreq_driver->get_intermediate) {
+ retval = __target_intermediate(policy, &freqs, index);
+ if (retval)
+ return retval;
+
+ intermediate_freq = freqs.new;
+ /* Set old freq to intermediate */
+ if (intermediate_freq)
+ freqs.old = freqs.new;
+ }
+ freqs.new = freq_table[index].frequency;
pr_debug("%s: cpu: %d, oldfreq: %u, new freq: %u\n",
__func__, policy->cpu, freqs.old, freqs.new);
@@ -1841,9 +1876,23 @@ static int __target_index(struct cpufreq_policy *policy,
pr_err("%s: Failed to change cpu frequency: %d\n", __func__,
retval);
- if (notify)
+ if (notify) {
cpufreq_freq_transition_end(policy, &freqs, retval);
+ /*
+ * Failed after setting to intermediate freq? Driver should have
+ * reverted back to initial frequency and so should we. Check
+ * here for intermediate_freq instead of get_intermediate, in
+ * case we have't switched to intermediate freq at all.
+ */
+ if (unlikely(retval && intermediate_freq)) {
+ freqs.old = intermediate_freq;
+ freqs.new = policy->restore_freq;
+ cpufreq_freq_transition_begin(policy, &freqs);
+ cpufreq_freq_transition_end(policy, &freqs, 0);
+ }
+ }
+
return retval;
}
@@ -1875,6 +1924,9 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
if (target_freq == policy->cur)
return 0;
+ /* Save last value to restore later on errors */
+ policy->restore_freq = policy->cur;
+
if (cpufreq_driver->target)
retval = cpufreq_driver->target(policy, target_freq, relation);
else if (cpufreq_driver->target_index) {
@@ -2361,7 +2413,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
!(driver_data->setpolicy || driver_data->target_index ||
driver_data->target) ||
(driver_data->setpolicy && (driver_data->target_index ||
- driver_data->target)))
+ driver_data->target)) ||
+ (!!driver_data->get_intermediate != !!driver_data->target_intermediate))
return -EINVAL;
pr_debug("trying to register driver %s\n", driver_data->name);
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index e1c6433b16e..1b44496b2d2 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -36,14 +36,29 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
struct od_dbs_tuners *od_tuners = dbs_data->tuners;
struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
struct cpufreq_policy *policy;
+ unsigned int sampling_rate;
unsigned int max_load = 0;
unsigned int ignore_nice;
unsigned int j;
- if (dbs_data->cdata->governor == GOV_ONDEMAND)
+ if (dbs_data->cdata->governor == GOV_ONDEMAND) {
+ struct od_cpu_dbs_info_s *od_dbs_info =
+ dbs_data->cdata->get_cpu_dbs_info_s(cpu);
+
+ /*
+ * Sometimes, the ondemand governor uses an additional
+ * multiplier to give long delays. So apply this multiplier to
+ * the 'sampling_rate', so as to keep the wake-up-from-idle
+ * detection logic a bit conservative.
+ */
+ sampling_rate = od_tuners->sampling_rate;
+ sampling_rate *= od_dbs_info->rate_mult;
+
ignore_nice = od_tuners->ignore_nice_load;
- else
+ } else {
+ sampling_rate = cs_tuners->sampling_rate;
ignore_nice = cs_tuners->ignore_nice_load;
+ }
policy = cdbs->cur_policy;
@@ -96,7 +111,46 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
if (unlikely(!wall_time || wall_time < idle_time))
continue;
- load = 100 * (wall_time - idle_time) / wall_time;
+ /*
+ * If the CPU had gone completely idle, and a task just woke up
+ * on this CPU now, it would be unfair to calculate 'load' the
+ * usual way for this elapsed time-window, because it will show
+ * near-zero load, irrespective of how CPU intensive that task
+ * actually is. This is undesirable for latency-sensitive bursty
+ * workloads.
+ *
+ * To avoid this, we reuse the 'load' from the previous
+ * time-window and give this task a chance to start with a
+ * reasonably high CPU frequency. (However, we shouldn't over-do
+ * this copy, lest we get stuck at a high load (high frequency)
+ * for too long, even when the current system load has actually
+ * dropped down. So we perform the copy only once, upon the
+ * first wake-up from idle.)
+ *
+ * Detecting this situation is easy: the governor's deferrable
+ * timer would not have fired during CPU-idle periods. Hence
+ * an unusually large 'wall_time' (as compared to the sampling
+ * rate) indicates this scenario.
+ *
+ * prev_load can be zero in two cases and we must recalculate it
+ * for both cases:
+ * - during long idle intervals
+ * - explicitly set to zero
+ */
+ if (unlikely(wall_time > (2 * sampling_rate) &&
+ j_cdbs->prev_load)) {
+ load = j_cdbs->prev_load;
+
+ /*
+ * Perform a destructive copy, to ensure that we copy
+ * the previous load only once, upon the first wake-up
+ * from idle.
+ */
+ j_cdbs->prev_load = 0;
+ } else {
+ load = 100 * (wall_time - idle_time) / wall_time;
+ j_cdbs->prev_load = load;
+ }
if (load > max_load)
max_load = load;
@@ -318,11 +372,18 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
for_each_cpu(j, policy->cpus) {
struct cpu_dbs_common_info *j_cdbs =
dbs_data->cdata->get_cpu_cdbs(j);
+ unsigned int prev_load;
j_cdbs->cpu = j;
j_cdbs->cur_policy = policy;
j_cdbs->prev_cpu_idle = get_cpu_idle_time(j,
&j_cdbs->prev_cpu_wall, io_busy);
+
+ prev_load = (unsigned int)
+ (j_cdbs->prev_cpu_wall - j_cdbs->prev_cpu_idle);
+ j_cdbs->prev_load = 100 * prev_load /
+ (unsigned int) j_cdbs->prev_cpu_wall;
+
if (ignore_nice)
j_cdbs->prev_cpu_nice =
kcpustat_cpu(j).cpustat[CPUTIME_NICE];
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index bfb9ae14142..cc401d147e7 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -134,6 +134,13 @@ struct cpu_dbs_common_info {
u64 prev_cpu_idle;
u64 prev_cpu_wall;
u64 prev_cpu_nice;
+ /*
+ * Used to keep track of load in the previous interval. However, when
+ * explicitly set to zero, it is used as a flag to ensure that we copy
+ * the previous load to the current interval only once, upon the first
+ * wake-up from idle.
+ */
+ unsigned int prev_load;
struct cpufreq_policy *cur_policy;
struct delayed_work work;
/*
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index aebd4572eb6..4e7f492ad58 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -691,14 +691,8 @@ MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
static int intel_pstate_init_cpu(unsigned int cpunum)
{
-
- const struct x86_cpu_id *id;
struct cpudata *cpu;
- id = x86_match_cpu(intel_pstate_cpu_ids);
- if (!id)
- return -ENODEV;
-
all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), GFP_KERNEL);
if (!all_cpu_data[cpunum])
return -ENOMEM;
diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c
index 0af618abeba..3607070797a 100644
--- a/drivers/cpufreq/ppc-corenet-cpufreq.c
+++ b/drivers/cpufreq/ppc-corenet-cpufreq.c
@@ -138,7 +138,7 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy)
struct cpufreq_frequency_table *table;
struct cpu_data *data;
unsigned int cpu = policy->cpu;
- u64 transition_latency_hz;
+ u64 u64temp;
np = of_get_cpu_node(cpu, NULL);
if (!np)
@@ -206,9 +206,10 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy)
for_each_cpu(i, per_cpu(cpu_mask, cpu))
per_cpu(cpu_data, i) = data;
- transition_latency_hz = 12ULL * NSEC_PER_SEC;
- policy->cpuinfo.transition_latency =
- do_div(transition_latency_hz, fsl_get_sys_freq());
+ /* Minimum transition latency is 12 platform clocks */
+ u64temp = 12ULL * NSEC_PER_SEC;
+ do_div(u64temp, fsl_get_sys_freq());
+ policy->cpuinfo.transition_latency = u64temp + 1;
of_node_put(np);
diff --git a/drivers/cpufreq/tegra-cpufreq.c b/drivers/cpufreq/tegra-cpufreq.c
index 6e774c6ac20..8084c7f7e20 100644
--- a/drivers/cpufreq/tegra-cpufreq.c
+++ b/drivers/cpufreq/tegra-cpufreq.c
@@ -45,46 +45,54 @@ static struct clk *cpu_clk;
static struct clk *pll_x_clk;
static struct clk *pll_p_clk;
static struct clk *emc_clk;
+static bool pll_x_prepared;
-static int tegra_cpu_clk_set_rate(unsigned long rate)
+static unsigned int tegra_get_intermediate(struct cpufreq_policy *policy,
+ unsigned int index)
+{
+ unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000;
+
+ /*
+ * Don't switch to intermediate freq if:
+ * - we are already at it, i.e. policy->cur == ifreq
+ * - index corresponds to ifreq
+ */
+ if ((freq_table[index].frequency == ifreq) || (policy->cur == ifreq))
+ return 0;
+
+ return ifreq;
+}
+
+static int tegra_target_intermediate(struct cpufreq_policy *policy,
+ unsigned int index)
{
int ret;
/*
* Take an extra reference to the main pll so it doesn't turn
- * off when we move the cpu off of it
+ * off when we move the cpu off of it as enabling it again while we
+ * switch to it from tegra_target() would take additional time.
+ *
+ * When target-freq is equal to intermediate freq we don't need to
+ * switch to an intermediate freq and so this routine isn't called.
+ * Also, we wouldn't be using pll_x anymore and must not take extra
+ * reference to it, as it can be disabled now to save some power.
*/
clk_prepare_enable(pll_x_clk);
ret = clk_set_parent(cpu_clk, pll_p_clk);
- if (ret) {
- pr_err("Failed to switch cpu to clock pll_p\n");
- goto out;
- }
-
- if (rate == clk_get_rate(pll_p_clk))
- goto out;
-
- ret = clk_set_rate(pll_x_clk, rate);
- if (ret) {
- pr_err("Failed to change pll_x to %lu\n", rate);
- goto out;
- }
-
- ret = clk_set_parent(cpu_clk, pll_x_clk);
- if (ret) {
- pr_err("Failed to switch cpu to clock pll_x\n");
- goto out;
- }
+ if (ret)
+ clk_disable_unprepare(pll_x_clk);
+ else
+ pll_x_prepared = true;
-out:
- clk_disable_unprepare(pll_x_clk);
return ret;
}
static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
{
unsigned long rate = freq_table[index].frequency;
+ unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000;
int ret = 0;
/*
@@ -98,10 +106,30 @@ static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
else
clk_set_rate(emc_clk, 100000000); /* emc 50Mhz */
- ret = tegra_cpu_clk_set_rate(rate * 1000);
+ /*
+ * target freq == pll_p, don't need to take extra reference to pll_x_clk
+ * as it isn't used anymore.
+ */
+ if (rate == ifreq)
+ return clk_set_parent(cpu_clk, pll_p_clk);
+
+ ret = clk_set_rate(pll_x_clk, rate * 1000);
+ /* Restore to earlier frequency on error, i.e. pll_x */
if (ret)
- pr_err("cpu-tegra: Failed to set cpu frequency to %lu kHz\n",
- rate);
+ pr_err("Failed to change pll_x to %lu\n", rate);
+
+ ret = clk_set_parent(cpu_clk, pll_x_clk);
+ /* This shouldn't fail while changing or restoring */
+ WARN_ON(ret);
+
+ /*
+ * Drop count to pll_x clock only if we switched to intermediate freq
+ * earlier while transitioning to a target frequency.
+ */
+ if (pll_x_prepared) {
+ clk_disable_unprepare(pll_x_clk);
+ pll_x_prepared = false;
+ }
return ret;
}
@@ -137,16 +165,18 @@ static int tegra_cpu_exit(struct cpufreq_policy *policy)
}
static struct cpufreq_driver tegra_cpufreq_driver = {
- .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK,
- .verify = cpufreq_generic_frequency_table_verify,
- .target_index = tegra_target,
- .get = cpufreq_generic_get,
- .init = tegra_cpu_init,
- .exit = tegra_cpu_exit,
- .name = "tegra",
- .attr = cpufreq_generic_attr,
+ .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+ .verify = cpufreq_generic_frequency_table_verify,
+ .get_intermediate = tegra_get_intermediate,
+ .target_intermediate = tegra_target_intermediate,
+ .target_index = tegra_target,
+ .get = cpufreq_generic_get,
+ .init = tegra_cpu_init,
+ .exit = tegra_cpu_exit,
+ .name = "tegra",
+ .attr = cpufreq_generic_attr,
#ifdef CONFIG_PM
- .suspend = cpufreq_generic_suspend,
+ .suspend = cpufreq_generic_suspend,
#endif
};
diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h
index 2b859249303..b0e61bf261a 100644
--- a/drivers/pci/hotplug/acpiphp.h
+++ b/drivers/pci/hotplug/acpiphp.h
@@ -142,6 +142,16 @@ static inline acpi_handle func_to_handle(struct acpiphp_func *func)
return func_to_acpi_device(func)->handle;
}
+struct acpiphp_root_context {
+ struct acpi_hotplug_context hp;
+ struct acpiphp_bridge *root_bridge;
+};
+
+static inline struct acpiphp_root_context *to_acpiphp_root_context(struct acpi_hotplug_context *hp)
+{
+ return container_of(hp, struct acpiphp_root_context, hp);
+}
+
/*
* struct acpiphp_attention_info - device specific attention registration
*
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 75e17833021..91aa3d78013 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -373,17 +373,13 @@ static acpi_status acpiphp_add_context(acpi_handle handle, u32 lvl, void *data,
static struct acpiphp_bridge *acpiphp_dev_to_bridge(struct acpi_device *adev)
{
- struct acpiphp_context *context;
struct acpiphp_bridge *bridge = NULL;
acpi_lock_hp_context();
- context = acpiphp_get_context(adev);
- if (context) {
- bridge = context->bridge;
+ if (adev->hp) {
+ bridge = to_acpiphp_root_context(adev->hp)->root_bridge;
if (bridge)
get_bridge(bridge);
-
- acpiphp_put_context(context);
}
acpi_unlock_hp_context();
return bridge;
@@ -881,7 +877,17 @@ void acpiphp_enumerate_slots(struct pci_bus *bus)
*/
get_device(&bus->dev);
- if (!pci_is_root_bus(bridge->pci_bus)) {
+ acpi_lock_hp_context();
+ if (pci_is_root_bus(bridge->pci_bus)) {
+ struct acpiphp_root_context *root_context;
+
+ root_context = kzalloc(sizeof(*root_context), GFP_KERNEL);
+ if (!root_context)
+ goto err;
+
+ root_context->root_bridge = bridge;
+ acpi_set_hp_context(adev, &root_context->hp, NULL, NULL, NULL);
+ } else {
struct acpiphp_context *context;
/*
@@ -890,21 +896,16 @@ void acpiphp_enumerate_slots(struct pci_bus *bus)
* parent is going to be handled by pciehp, in which case this
* bridge is not interesting to us either.
*/
- acpi_lock_hp_context();
context = acpiphp_get_context(adev);
- if (!context) {
- acpi_unlock_hp_context();
- put_device(&bus->dev);
- pci_dev_put(bridge->pci_dev);
- kfree(bridge);
- return;
- }
+ if (!context)
+ goto err;
+
bridge->context = context;
context->bridge = bridge;
/* Get a reference to the parent bridge. */
get_bridge(context->func.parent);
- acpi_unlock_hp_context();
}
+ acpi_unlock_hp_context();
/* Must be added to the list prior to calling acpiphp_add_context(). */
mutex_lock(&bridge_mutex);
@@ -919,6 +920,30 @@ void acpiphp_enumerate_slots(struct pci_bus *bus)
cleanup_bridge(bridge);
put_bridge(bridge);
}
+ return;
+
+ err:
+ acpi_unlock_hp_context();
+ put_device(&bus->dev);
+ pci_dev_put(bridge->pci_dev);
+ kfree(bridge);
+}
+
+void acpiphp_drop_bridge(struct acpiphp_bridge *bridge)
+{
+ if (pci_is_root_bus(bridge->pci_bus)) {
+ struct acpiphp_root_context *root_context;
+ struct acpi_device *adev;
+
+ acpi_lock_hp_context();
+ adev = ACPI_COMPANION(bridge->pci_bus->bridge);
+ root_context = to_acpiphp_root_context(adev->hp);
+ adev->hp = NULL;
+ acpi_unlock_hp_context();
+ kfree(root_context);
+ }
+ cleanup_bridge(bridge);
+ put_bridge(bridge);
}
/**
@@ -936,8 +961,7 @@ void acpiphp_remove_slots(struct pci_bus *bus)
list_for_each_entry(bridge, &bridge_list, list)
if (bridge->pci_bus == bus) {
mutex_unlock(&bridge_mutex);
- cleanup_bridge(bridge);
- put_bridge(bridge);
+ acpiphp_drop_bridge(bridge);
return;
}
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 3f458896d45..ec4112d257b 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -75,6 +75,7 @@ struct cpufreq_policy {
unsigned int max; /* in kHz */
unsigned int cur; /* in kHz, only needed if cpufreq
* governors are used */
+ unsigned int restore_freq; /* = policy->cur before transition */
unsigned int suspend_freq; /* freq to set during suspend */
unsigned int policy; /* see above */
@@ -221,11 +222,35 @@ struct cpufreq_driver {
/* define one out of two */
int (*setpolicy) (struct cpufreq_policy *policy);
+
+ /*
+ * On failure, should always restore frequency to policy->restore_freq
+ * (i.e. old freq).
+ */
int (*target) (struct cpufreq_policy *policy, /* Deprecated */
unsigned int target_freq,
unsigned int relation);
int (*target_index) (struct cpufreq_policy *policy,
unsigned int index);
+ /*
+ * Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION
+ * unset.
+ *
+ * get_intermediate should return a stable intermediate frequency
+ * platform wants to switch to and target_intermediate() should set CPU
+ * to to that frequency, before jumping to the frequency corresponding
+ * to 'index'. Core will take care of sending notifications and driver
+ * doesn't have to handle them in target_intermediate() or
+ * target_index().
+ *
+ * Drivers can return '0' from get_intermediate() in case they don't
+ * wish to switch to intermediate frequency for some target frequency.
+ * In that case core will directly call ->target_index().
+ */
+ unsigned int (*get_intermediate)(struct cpufreq_policy *policy,
+ unsigned int index);
+ int (*target_intermediate)(struct cpufreq_policy *policy,
+ unsigned int index);
/* should be defined, if possible */
unsigned int (*get) (unsigned int cpu);
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 9a7e08d6125..d19840b0cac 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -7,6 +7,9 @@
#include <linux/ktime.h>
#include <linux/pm_qos.h>
#include <linux/tracepoint.h>
+#include <linux/ftrace_event.h>
+
+#define TPS(x) tracepoint_string(x)
DECLARE_EVENT_CLASS(cpu,
@@ -90,6 +93,17 @@ TRACE_EVENT(pstate_sample,
#define PWR_EVENT_EXIT -1
#endif
+#define pm_verb_symbolic(event) \
+ __print_symbolic(event, \
+ { PM_EVENT_SUSPEND, "suspend" }, \
+ { PM_EVENT_RESUME, "resume" }, \
+ { PM_EVENT_FREEZE, "freeze" }, \
+ { PM_EVENT_QUIESCE, "quiesce" }, \
+ { PM_EVENT_HIBERNATE, "hibernate" }, \
+ { PM_EVENT_THAW, "thaw" }, \
+ { PM_EVENT_RESTORE, "restore" }, \
+ { PM_EVENT_RECOVER, "recover" })
+
DEFINE_EVENT(cpu, cpu_frequency,
TP_PROTO(unsigned int frequency, unsigned int cpu_id),
@@ -97,58 +111,76 @@ DEFINE_EVENT(cpu, cpu_frequency,
TP_ARGS(frequency, cpu_id)
);
-TRACE_EVENT(machine_suspend,
+TRACE_EVENT(device_pm_callback_start,
- TP_PROTO(unsigned int state),
+ TP_PROTO(struct device *dev, const char *pm_ops, int event),
- TP_ARGS(state),
+ TP_ARGS(dev, pm_ops, event),
TP_STRUCT__entry(
- __field( u32, state )
+ __string(device, dev_name(dev))
+ __string(driver, dev_driver_string(dev))
+ __string(parent, dev->parent ? dev_name(dev->parent) : "none")
+ __string(pm_ops, pm_ops ? pm_ops : "none ")
+ __field(int, event)
),
TP_fast_assign(
- __entry->state = state;
+ __assign_str(device, dev_name(dev));
+ __assign_str(driver, dev_driver_string(dev));
+ __assign_str(parent,
+ dev->parent ? dev_name(dev->parent) : "none");
+ __assign_str(pm_ops, pm_ops ? pm_ops : "none ");
+ __entry->event = event;
),
- TP_printk("state=%lu", (unsigned long)__entry->state)
+ TP_printk("%s %s, parent: %s, %s[%s]", __get_str(driver),
+ __get_str(device), __get_str(parent), __get_str(pm_ops),
+ pm_verb_symbolic(__entry->event))
);
-TRACE_EVENT(device_pm_report_time,
+TRACE_EVENT(device_pm_callback_end,
- TP_PROTO(struct device *dev, const char *pm_ops, s64 ops_time,
- char *pm_event_str, int error),
+ TP_PROTO(struct device *dev, int error),
- TP_ARGS(dev, pm_ops, ops_time, pm_event_str, error),
+ TP_ARGS(dev, error),
TP_STRUCT__entry(
__string(device, dev_name(dev))
__string(driver, dev_driver_string(dev))
- __string(parent, dev->parent ? dev_name(dev->parent) : "none")
- __string(pm_ops, pm_ops ? pm_ops : "none ")
- __string(pm_event_str, pm_event_str)
- __field(s64, ops_time)
__field(int, error)
),
TP_fast_assign(
- const char *tmp = dev->parent ? dev_name(dev->parent) : "none";
- const char *tmp_i = pm_ops ? pm_ops : "none ";
-
__assign_str(device, dev_name(dev));
__assign_str(driver, dev_driver_string(dev));
- __assign_str(parent, tmp);
- __assign_str(pm_ops, tmp_i);
- __assign_str(pm_event_str, pm_event_str);
- __entry->ops_time = ops_time;
__entry->error = error;
),
- /* ops_str has an extra space at the end */
- TP_printk("%s %s parent=%s state=%s ops=%snsecs=%lld err=%d",
- __get_str(driver), __get_str(device), __get_str(parent),
- __get_str(pm_event_str), __get_str(pm_ops),
- __entry->ops_time, __entry->error)
+ TP_printk("%s %s, err=%d",
+ __get_str(driver), __get_str(device), __entry->error)
+);
+
+TRACE_EVENT(suspend_resume,
+
+ TP_PROTO(const char *action, int val, bool start),
+
+ TP_ARGS(action, val, start),
+
+ TP_STRUCT__entry(
+ __field(const char *, action)
+ __field(int, val)
+ __field(bool, start)
+ ),
+
+ TP_fast_assign(
+ __entry->action = action;
+ __entry->val = val;
+ __entry->start = start;
+ ),
+
+ TP_printk("%s[%u] %s", __entry->action, (unsigned int)__entry->val,
+ (__entry->start)?"begin":"end")
);
DECLARE_EVENT_CLASS(wakeup_source,
diff --git a/kernel/cpu.c b/kernel/cpu.c
index acf791c55b7..a343bde710b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -20,6 +20,7 @@
#include <linux/gfp.h>
#include <linux/suspend.h>
#include <linux/lockdep.h>
+#include <trace/events/power.h>
#include "smpboot.h"
@@ -520,7 +521,9 @@ int disable_nonboot_cpus(void)
for_each_online_cpu(cpu) {
if (cpu == first_cpu)
continue;
+ trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
error = _cpu_down(cpu, 1);
+ trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
if (!error)
cpumask_set_cpu(cpu, frozen_cpus);
else {
@@ -563,7 +566,9 @@ void __ref enable_nonboot_cpus(void)
arch_enable_nonboot_cpus_begin();
for_each_cpu(cpu, frozen_cpus) {
+ trace_suspend_resume(TPS("CPU_ON"), cpu, true);
error = _cpu_up(cpu, 1);
+ trace_suspend_resume(TPS("CPU_ON"), cpu, false);
if (!error) {
pr_info("CPU%d is up\n", cpu);
continue;
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index df88d55dc43..49e0a20fd01 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -28,6 +28,7 @@
#include <linux/syscore_ops.h>
#include <linux/ctype.h>
#include <linux/genhd.h>
+#include <trace/events/power.h>
#include "power.h"
@@ -292,7 +293,9 @@ static int create_image(int platform_mode)
in_suspend = 1;
save_processor_state();
+ trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true);
error = swsusp_arch_suspend();
+ trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false);
if (error)
printk(KERN_ERR "PM: Error %d creating hibernation image\n",
error);
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 06ec8869dbf..0ca8d83e236 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -17,6 +17,7 @@
#include <linux/delay.h>
#include <linux/workqueue.h>
#include <linux/kmod.h>
+#include <trace/events/power.h>
/*
* Timeout for stopping processes
@@ -175,6 +176,7 @@ void thaw_processes(void)
struct task_struct *g, *p;
struct task_struct *curr = current;
+ trace_suspend_resume(TPS("thaw_processes"), 0, true);
if (pm_freezing)
atomic_dec(&system_freezing_cnt);
pm_freezing = false;
@@ -201,6 +203,7 @@ void thaw_processes(void)
schedule();
printk("done.\n");
+ trace_suspend_resume(TPS("thaw_processes"), 0, false);
}
void thaw_kernel_threads(void)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 963e6d0f050..4dd8822f732 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -177,7 +177,9 @@ static int suspend_prepare(suspend_state_t state)
if (error)
goto Finish;
+ trace_suspend_resume(TPS("freeze_processes"), 0, true);
error = suspend_freeze_processes();
+ trace_suspend_resume(TPS("freeze_processes"), 0, false);
if (!error)
return 0;
@@ -240,7 +242,9 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
* all the devices are suspended.
*/
if (state == PM_SUSPEND_FREEZE) {
+ trace_suspend_resume(TPS("machine_suspend"), state, true);
freeze_enter();
+ trace_suspend_resume(TPS("machine_suspend"), state, false);
goto Platform_wake;
}
@@ -256,7 +260,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
if (!error) {
*wakeup = pm_wakeup_pending();
if (!(suspend_test(TEST_CORE) || *wakeup)) {
+ trace_suspend_resume(TPS("machine_suspend"),
+ state, true);
error = suspend_ops->enter(state);
+ trace_suspend_resume(TPS("machine_suspend"),
+ state, false);
events_check_enabled = false;
}
syscore_resume();
@@ -294,7 +302,6 @@ int suspend_devices_and_enter(suspend_state_t state)
if (need_suspend_ops(state) && !suspend_ops)
return -ENOSYS;
- trace_machine_suspend(state);
if (need_suspend_ops(state) && suspend_ops->begin) {
error = suspend_ops->begin(state);
if (error)
@@ -331,7 +338,6 @@ int suspend_devices_and_enter(suspend_state_t state)
else if (state == PM_SUSPEND_FREEZE && freeze_ops->end)
freeze_ops->end();
- trace_machine_suspend(PWR_EVENT_EXIT);
return error;
Recover_platform:
@@ -365,6 +371,7 @@ static int enter_state(suspend_state_t state)
{
int error;
+ trace_suspend_resume(TPS("suspend_enter"), state, true);
if (state == PM_SUSPEND_FREEZE) {
#ifdef CONFIG_PM_DEBUG
if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) {
@@ -382,9 +389,11 @@ static int enter_state(suspend_state_t state)
if (state == PM_SUSPEND_FREEZE)
freeze_begin();
+ trace_suspend_resume(TPS("sync_filesystems"), 0, true);
printk(KERN_INFO "PM: Syncing filesystems ... ");
sys_sync();
printk("done.\n");
+ trace_suspend_resume(TPS("sync_filesystems"), 0, false);
pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label);
error = suspend_prepare(state);
@@ -394,6 +403,7 @@ static int enter_state(suspend_state_t state)
if (suspend_test(TEST_FREEZER))
goto Finish;
+ trace_suspend_resume(TPS("suspend_enter"), state, false);
pr_debug("PM: Entering %s sleep\n", pm_states[state].label);
pm_restrict_gfp_mask();
error = suspend_devices_and_enter(state);