From ffe6275f90cc2ea77e6120a510903687be067b16 Mon Sep 17 00:00:00 2001 From: Andrej Gelenberg Date: Fri, 14 May 2010 15:15:58 -0700 Subject: [CPUFREQ] revert "[CPUFREQ] remove rwsem lock from CPUFREQ_GOV_STOP call (second call site)" 395913d0b1db37092ea3d9d69b832183b1dd84c5 ("[CPUFREQ] remove rwsem lock from CPUFREQ_GOV_STOP call (second call site)") is not needed, because there is no rwsem lock in cpufreq_ondemand and cpufreq_conservative anymore. Lock should not be released until the work done. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=1594 Signed-off-by: Andrej Gelenberg Cc: Mathieu Desnoyers Cc: Venkatesh Pallipadi Signed-off-by: Andrew Morton Acked-by: Mathieu Desnoyers Signed-off-by: Dave Jones --- drivers/cpufreq/cpufreq.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'drivers') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 063b2184caf5..8f22ce1ea684 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1762,17 +1762,8 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, dprintk("governor switch\n"); /* end old governor */ - if (data->governor) { - /* - * Need to release the rwsem around governor - * stop due to lock dependency between - * cancel_delayed_work_sync and the read lock - * taken in the delayed work handler. - */ - unlock_policy_rwsem_write(data->cpu); + if (data->governor) __cpufreq_governor(data, CPUFREQ_GOV_STOP); - lock_policy_rwsem_write(data->cpu); - } /* start new governor */ data->governor = policy->governor; -- cgit v1.2.3 From cad70a6ae5aaef4641a3efdfd536c30f13891afe Mon Sep 17 00:00:00 2001 From: Xiaotian Feng Date: Tue, 20 Jul 2010 20:11:02 +0800 Subject: [CPUFREQ] fix memory leak in cpufreq_add_dev We didn't free policy->related_cpus in error path err_unlock_policy. This is catched by following kmemleak report: unreferenced object 0xffff88022a0b96d0 (size 512): comm "modprobe", pid 886, jiffies 4294689177 (age 780.694s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] create_object+0x186/0x281 [] kmemleak_alloc+0x60/0xa7 [] kmem_cache_alloc_node_notrace+0x120/0x142 [] alloc_cpumask_var_node+0x2c/0xd7 [] alloc_cpumask_var+0x11/0x13 [] zalloc_cpumask_var+0xf/0x11 [] cpufreq_add_dev+0x11f/0x547 [] sysdev_driver_register+0xc2/0x11d [] cpufreq_register_driver+0xcb/0x1b8 [] 0xffffffffa032e040 [] do_one_initcall+0x5e/0x15c [] sys_init_module+0xa6/0x1e6 [] system_call_fastpath+0x16/0x1b [] 0xffffffffffffffff Signed-off-by: Xiaotian Feng Cc: Thomas Renninger Cc: Prarit Bhargava Signed-off-by: Dave Jones --- drivers/cpufreq/cpufreq.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 8f22ce1ea684..938b74ea9ffb 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1077,6 +1077,7 @@ err_out_unregister: err_unlock_policy: unlock_policy_rwsem_write(cpu); + free_cpumask_var(policy->related_cpus); err_free_cpumask: free_cpumask_var(policy->cpus); err_free_policy: -- cgit v1.2.3 From 00e299fff3cc2745847b03eebcc9e9362db9366d Mon Sep 17 00:00:00 2001 From: Mike Chan Date: Tue, 26 Jan 2010 17:06:47 -0800 Subject: [CPUFREQ] ondemand: Refactor frequency increase code Make simpler to read and call. *** v3 - Always call when powersave_bias is enabled. Acked-by: Venkatesh Pallipadi Signed-off-by: Mike Chan Signed-off-by: Dave Jones --- drivers/cpufreq/cpufreq_ondemand.c | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) (limited to 'drivers') diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index e1314212d8d4..fecfcdda6ddd 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -459,6 +459,17 @@ static struct attribute_group dbs_attr_group_old = { /************************** sysfs end ************************/ +static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq) +{ + if (dbs_tuners_ins.powersave_bias) + freq = powersave_bias_target(p, freq, CPUFREQ_RELATION_H); + else if (p->cur == p->max) + return; + + __cpufreq_driver_target(p, freq, dbs_tuners_ins.powersave_bias ? + CPUFREQ_RELATION_L : CPUFREQ_RELATION_H); +} + static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info) { unsigned int max_load_freq; @@ -551,19 +562,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info) /* Check for frequency increase */ if (max_load_freq > dbs_tuners_ins.up_threshold * policy->cur) { - /* if we are already at full speed then break out early */ - if (!dbs_tuners_ins.powersave_bias) { - if (policy->cur == policy->max) - return; - - __cpufreq_driver_target(policy, policy->max, - CPUFREQ_RELATION_H); - } else { - int freq = powersave_bias_target(policy, policy->max, - CPUFREQ_RELATION_H); - __cpufreq_driver_target(policy, freq, - CPUFREQ_RELATION_L); - } + dbs_freq_increase(policy, policy->max); return; } -- cgit v1.2.3 From 226528c6100e4191842e61997110c8ace40605f7 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Thu, 4 Mar 2010 03:23:36 -0500 Subject: [CPUFREQ] unexport (un)lock_policy_rwsem* functions lock_policy_rwsem_* and unlock_policy_rwsem_* functions are scheduled to be unexported when 2.6.33. Now there are no other callers of them out of cpufreq.c, unexport them and make them static. Signed-off-by: WANG Cong Cc: Venkatesh Pallipadi Signed-off-by: Dave Jones --- Documentation/feature-removal-schedule.txt | 10 ---------- drivers/cpufreq/cpufreq.c | 10 +++------- include/linux/cpufreq.h | 5 ----- 3 files changed, 3 insertions(+), 22 deletions(-) (limited to 'drivers') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 1571c0c83dba..182bbe49429b 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -377,16 +377,6 @@ Who: Eric Paris ---------------------------- -What: lock_policy_rwsem_* and unlock_policy_rwsem_* will not be - exported interface anymore. -When: 2.6.33 -Why: cpu_policy_rwsem has a new cleaner definition making it local to - cpufreq core and contained inside cpufreq.c. Other dependent - drivers should not use it in order to safely avoid lockdep issues. -Who: Venkatesh Pallipadi - ----------------------------- - What: sound-slot/service-* module aliases and related clutters in sound/sound_core.c When: August 2010 diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 938b74ea9ffb..40877d219081 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -68,7 +68,7 @@ static DEFINE_PER_CPU(int, cpufreq_policy_cpu); static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem); #define lock_policy_rwsem(mode, cpu) \ -int lock_policy_rwsem_##mode \ +static int lock_policy_rwsem_##mode \ (int cpu) \ { \ int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu); \ @@ -83,26 +83,22 @@ int lock_policy_rwsem_##mode \ } lock_policy_rwsem(read, cpu); -EXPORT_SYMBOL_GPL(lock_policy_rwsem_read); lock_policy_rwsem(write, cpu); -EXPORT_SYMBOL_GPL(lock_policy_rwsem_write); -void unlock_policy_rwsem_read(int cpu) +static void unlock_policy_rwsem_read(int cpu) { int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu); BUG_ON(policy_cpu == -1); up_read(&per_cpu(cpu_policy_rwsem, policy_cpu)); } -EXPORT_SYMBOL_GPL(unlock_policy_rwsem_read); -void unlock_policy_rwsem_write(int cpu) +static void unlock_policy_rwsem_write(int cpu) { int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu); BUG_ON(policy_cpu == -1); up_write(&per_cpu(cpu_policy_rwsem, policy_cpu)); } -EXPORT_SYMBOL_GPL(unlock_policy_rwsem_write); /* internal prototypes */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9f15150ce8d6..c3e9de8321c6 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -196,11 +196,6 @@ extern int __cpufreq_driver_getavg(struct cpufreq_policy *policy, int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); -int lock_policy_rwsem_read(int cpu); -int lock_policy_rwsem_write(int cpu); -void unlock_policy_rwsem_read(int cpu); -void unlock_policy_rwsem_write(int cpu); - /********************************************************************* * CPUFREQ DRIVER INTERFACE * -- cgit v1.2.3 From a665df9d510bfd5bac5664f436411f921471264a Mon Sep 17 00:00:00 2001 From: Jocelyn Falempe Date: Thu, 11 Mar 2010 14:01:11 -0800 Subject: [CPUFREQ] ondemand: don't synchronize sample rate unless multiple cpus present For UP systems this is not required, and results in a more consistent sample interval. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jocelyn Falempe Signed-off-by: Mike Chan Signed-off-by: Andrew Morton Signed-off-by: Dave Jones --- drivers/cpufreq/cpufreq_ondemand.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index fecfcdda6ddd..7b5093664e49 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -609,7 +609,9 @@ static void do_dbs_timer(struct work_struct *work) /* We want all CPUs to do sampling nearly on same jiffy */ int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate); - delay -= jiffies % delay; + if (num_online_cpus() > 1) + delay -= jiffies % delay; + mutex_lock(&dbs_info->timer_mutex); /* Common NORMAL_SAMPLE setup */ @@ -634,7 +636,9 @@ static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info) { /* We want all CPUs to do sampling nearly on same jiffy */ int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate); - delay -= jiffies % delay; + + if (num_online_cpus() > 1) + delay -= jiffies % delay; dbs_info->sample_type = DBS_NORMAL_SAMPLE; INIT_DELAYED_WORK_DEFERRABLE(&dbs_info->work, do_dbs_timer); -- cgit v1.2.3 From 6f4f2723d08534fd4e407e1ef8500b0f4d12c30c Mon Sep 17 00:00:00 2001 From: Thomas Renninger Date: Tue, 20 Apr 2010 13:17:36 +0200 Subject: [CPUFREQ] x86 cpufreq: Make trace_power_frequency cpufreq driver independent and fix the broken case if a core's frequency depends on others. trace_power_frequency was only implemented in a rather ungeneric way in acpi-cpufreq driver's target() function only. -> Move the call to trace_power_frequency to cpufreq.c:cpufreq_notify_transition() where CPUFREQ_POSTCHANGE notifier is triggered. This will support power frequency tracing by all cpufreq drivers trace_power_frequency did not trace frequency changes correctly when the userspace governor was used or when CPU cores' frequency depend on each other. -> Moving this into the CPUFREQ_POSTCHANGE notifier and pass the cpu which gets switched automatically fixes this. Robert Schoene provided some important fixes on top of my initial quick shot version which are integrated in this patch: - Forgot some changes in power_end trace (TP_printk/variable names) - Variable dummy in power_end must now be cpu_id - Use static 64 bit variable instead of unsigned int for cpu_id Signed-off-by: Thomas Renninger CC: davej@redhat.com CC: arjan@infradead.org CC: linux-kernel@vger.kernel.org CC: robert.schoene@tu-dresden.de Tested-by: robert.schoene@tu-dresden.de Signed-off-by: Dave Jones --- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 3 --- arch/x86/kernel/process.c | 8 ++++---- drivers/cpufreq/cpufreq.c | 5 +++++ drivers/cpuidle/cpuidle.c | 2 +- include/trace/events/power.h | 27 +++++++++++++++------------ tools/perf/builtin-timechart.c | 11 ++++++----- 6 files changed, 31 insertions(+), 25 deletions(-) (limited to 'drivers') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index cee7aa949c35..246cd3afbb5f 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -34,7 +34,6 @@ #include #include #include -#include #include #include @@ -324,8 +323,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, } } - trace_power_frequency(POWER_PSTATE, data->freq_table[next_state].frequency); - switch (data->cpu_feature) { case SYSTEM_INTEL_MSR_CAPABLE: cmd.type = SYSTEM_INTEL_MSR_CAPABLE; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e7e35219b32f..787572d43d9c 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -371,7 +371,7 @@ static inline int hlt_use_halt(void) void default_idle(void) { if (hlt_use_halt()) { - trace_power_start(POWER_CSTATE, 1); + trace_power_start(POWER_CSTATE, 1, smp_processor_id()); current_thread_info()->status &= ~TS_POLLING; /* * TS_POLLING-cleared state must be visible before we @@ -441,7 +441,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); */ void mwait_idle_with_hints(unsigned long ax, unsigned long cx) { - trace_power_start(POWER_CSTATE, (ax>>4)+1); + trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id()); if (!need_resched()) { if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -457,7 +457,7 @@ void mwait_idle_with_hints(unsigned long ax, unsigned long cx) static void mwait_idle(void) { if (!need_resched()) { - trace_power_start(POWER_CSTATE, 1); + trace_power_start(POWER_CSTATE, 1, smp_processor_id()); if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -478,7 +478,7 @@ static void mwait_idle(void) */ static void poll_idle(void) { - trace_power_start(POWER_CSTATE, 0); + trace_power_start(POWER_CSTATE, 0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 40877d219081..6ce1bb735635 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -29,6 +29,8 @@ #include #include +#include + #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, \ "cpufreq-core", msg) @@ -350,6 +352,9 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) case CPUFREQ_POSTCHANGE: adjust_jiffies(CPUFREQ_POSTCHANGE, freqs); + dprintk("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new, + (unsigned long)freqs->cpu); + trace_power_frequency(POWER_PSTATE, freqs->new, freqs->cpu); srcu_notifier_call_chain(&cpufreq_transition_notifier_list, CPUFREQ_POSTCHANGE, freqs); if (likely(policy) && likely(policy->cpu == freqs->cpu)) diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 199488576a05..dbefe15bd582 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -95,7 +95,7 @@ static void cpuidle_idle_call(void) /* give the governor an opportunity to reflect on the outcome */ if (cpuidle_curr_governor->reflect) cpuidle_curr_governor->reflect(dev); - trace_power_end(0); + trace_power_end(smp_processor_id()); } /** diff --git a/include/trace/events/power.h b/include/trace/events/power.h index c4efe9b8280d..35a2a6e7bf1e 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -18,52 +18,55 @@ enum { DECLARE_EVENT_CLASS(power, - TP_PROTO(unsigned int type, unsigned int state), + TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id), - TP_ARGS(type, state), + TP_ARGS(type, state, cpu_id), TP_STRUCT__entry( __field( u64, type ) __field( u64, state ) + __field( u64, cpu_id ) ), TP_fast_assign( __entry->type = type; __entry->state = state; + __entry->cpu_id = cpu_id; ), - TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long)__entry->state) + TP_printk("type=%lu state=%lu cpu_id=%lu", (unsigned long)__entry->type, + (unsigned long)__entry->state, (unsigned long)__entry->cpu_id) ); DEFINE_EVENT(power, power_start, - TP_PROTO(unsigned int type, unsigned int state), + TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id), - TP_ARGS(type, state) + TP_ARGS(type, state, cpu_id) ); DEFINE_EVENT(power, power_frequency, - TP_PROTO(unsigned int type, unsigned int state), + TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id), - TP_ARGS(type, state) + TP_ARGS(type, state, cpu_id) ); TRACE_EVENT(power_end, - TP_PROTO(int dummy), + TP_PROTO(unsigned int cpu_id), - TP_ARGS(dummy), + TP_ARGS(cpu_id), TP_STRUCT__entry( - __field( u64, dummy ) + __field( u64, cpu_id ) ), TP_fast_assign( - __entry->dummy = 0xffff; + __entry->cpu_id = cpu_id; ), - TP_printk("dummy=%lu", (unsigned long)__entry->dummy) + TP_printk("cpu_id=%lu", (unsigned long)__entry->cpu_id) ); diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 5a52ed9fc10b..5161619d4714 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -300,8 +300,9 @@ struct trace_entry { struct power_entry { struct trace_entry te; - s64 type; - s64 value; + u64 type; + u64 value; + u64 cpu_id; }; #define TASK_COMM_LEN 16 @@ -498,13 +499,13 @@ static int process_sample_event(event_t *event, struct perf_session *session) return 0; if (strcmp(event_str, "power:power_start") == 0) - c_state_start(data.cpu, data.time, pe->value); + c_state_start(pe->cpu_id, data.time, pe->value); if (strcmp(event_str, "power:power_end") == 0) - c_state_end(data.cpu, data.time); + c_state_end(pe->cpu_id, data.time); if (strcmp(event_str, "power:power_frequency") == 0) - p_state_change(data.cpu, data.time, pe->value); + p_state_change(pe->cpu_id, data.time, pe->value); if (strcmp(event_str, "sched:sched_wakeup") == 0) sched_wakeup(data.cpu, data.time, data.pid, te); -- cgit v1.2.3 From 9c36f746d7e191ad6f44f01859af843f0c4d3c5d Mon Sep 17 00:00:00 2001 From: Neal Buckendahl Date: Tue, 22 Jun 2010 22:02:44 -0500 Subject: [CPUFREQ] fix brace coding style issue. This patch fixes up a brace warning found by the checkpatch.pl tool Signed-off-by: Neal Buckendahl Signed-off-by: Dave Jones --- drivers/cpufreq/cpufreq.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 6ce1bb735635..199dcb9f0b83 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1876,8 +1876,7 @@ static int __cpuinit cpufreq_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block __refdata cpufreq_cpu_notifier = -{ +static struct notifier_block __refdata cpufreq_cpu_notifier = { .notifier_call = cpufreq_cpu_callback, }; -- cgit v1.2.3