From e66c176837462928a05a135bbe16cdce70536d6e Mon Sep 17 00:00:00 2001 From: Dirk Brandewie Date: Tue, 25 Feb 2014 10:35:37 -0800 Subject: intel_pstate: Change busy calculation to use fixed point math. Commit fcb6a15c2e (intel_pstate: Take core C0 time into account for core busy calculation) introduced a regression on some processor SKUs supported by intel_pstate. This was due to the truncation caused by using integer math to calculate core busy and C0 percentages. On a i7-4770K processor operating at 800Mhz going to 100% utilization the percent busy of the CPU using integer math is 22%, but it actually is 22.85%. This value scaled to the current frequency returned 97 which the PID interpreted as no error and did not adjust the P state. Tested on i7-4770K, i7-2600, i5-3230M. Fixes: fcb6a15c2e7e (intel_pstate: Take core C0 time into account for core busy calculation) References: https://lkml.org/lkml/2014/2/19/626 References: https://bugzilla.kernel.org/show_bug.cgi?id=70941 Signed-off-by: Dirk Brandewie Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index e90816105921..2cd36b9297f3 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -39,9 +39,10 @@ #define BYT_TURBO_RATIOS 0x66c -#define FRAC_BITS 8 +#define FRAC_BITS 6 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS) #define fp_toint(X) ((X) >> FRAC_BITS) +#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS) static inline int32_t mul_fp(int32_t x, int32_t y) { @@ -556,18 +557,20 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) static inline void intel_pstate_calc_busy(struct cpudata *cpu, struct sample *sample) { - u64 core_pct; - u64 c0_pct; + int32_t core_pct; + int32_t c0_pct; - core_pct = div64_u64(sample->aperf * 100, sample->mperf); + core_pct = div_fp(int_tofp((sample->aperf)), + int_tofp((sample->mperf))); + core_pct = mul_fp(core_pct, int_tofp(100)); + FP_ROUNDUP(core_pct); + + c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc)); - c0_pct = div64_u64(sample->mperf * 100, sample->tsc); sample->freq = fp_toint( - mul_fp(int_tofp(cpu->pstate.max_pstate), - int_tofp(core_pct * 1000))); + mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct)); - sample->core_pct_busy = mul_fp(int_tofp(core_pct), - div_fp(int_tofp(c0_pct + 1), int_tofp(100))); + sample->core_pct_busy = mul_fp(core_pct, c0_pct); } static inline void intel_pstate_sample(struct cpudata *cpu) @@ -579,6 +582,10 @@ static inline void intel_pstate_sample(struct cpudata *cpu) rdmsrl(MSR_IA32_MPERF, mperf); tsc = native_read_tsc(); + aperf = aperf >> FRAC_BITS; + mperf = mperf >> FRAC_BITS; + tsc = tsc >> FRAC_BITS; + cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT; cpu->samples[cpu->sample_ptr].aperf = aperf; cpu->samples[cpu->sample_ptr].mperf = mperf; @@ -610,7 +617,8 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu) core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy; max_pstate = int_tofp(cpu->pstate.max_pstate); current_pstate = int_tofp(cpu->pstate.current_pstate); - return mul_fp(core_busy, div_fp(max_pstate, current_pstate)); + core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate)); + return FP_ROUNDUP(core_busy); } static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) -- cgit v1.2.3 From f8d5b9e9e5372f0deb7bc1ab1088a9b60b0a793d Mon Sep 17 00:00:00 2001 From: Sebastian Capella Date: Tue, 18 Feb 2014 17:52:08 -0800 Subject: PM / hibernate: Fix restore hang in freeze_processes() During restore, pm_notifier chain are called with PM_RESTORE_PREPARE. The firmware_class driver handler fw_pm_notify does not have a handler for this. As a result, it keeps a reader on the kmod.c umhelper_sem. During freeze_processes, the call to __usermodehelper_disable tries to take a write lock on this semaphore and hangs waiting. Signed-off-by: Sebastian Capella Acked-by: Ming Lei Cc: All applicable Signed-off-by: Rafael J. Wysocki --- drivers/base/firmware_class.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index 8a97ddfa6122..c30df50e4440 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -1580,6 +1580,7 @@ static int fw_pm_notify(struct notifier_block *notify_block, switch (mode) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: + case PM_RESTORE_PREPARE: kill_requests_without_uevent(); device_cache_fw_images(); break; -- cgit v1.2.3 From f3ca4164529b875374c410193bbbac0ee960895f Mon Sep 17 00:00:00 2001 From: Lan Tianyu Date: Wed, 26 Feb 2014 21:03:05 +0800 Subject: ACPI / processor: Rework processor throttling with work_on_cpu() acpi_processor_set_throttling() uses set_cpus_allowed_ptr() to make sure that the (struct acpi_processor)->acpi_processor_set_throttling() callback will run on the right CPU. However, the function may be called from a worker thread already bound to a different CPU in which case that won't work. Make acpi_processor_set_throttling() use work_on_cpu() as appropriate instead of abusing set_cpus_allowed_ptr(). Reported-and-tested-by: Jiri Olsa Signed-off-by: Lan Tianyu Cc: All applicable [rjw: Changelog] Signed-off-by: Rafael J. Wysocki --- drivers/acpi/processor_throttling.c | 69 +++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 37 deletions(-) diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c index 28baa05b8018..84243c32e29c 100644 --- a/drivers/acpi/processor_throttling.c +++ b/drivers/acpi/processor_throttling.c @@ -56,6 +56,12 @@ struct throttling_tstate { int target_state; /* target T-state */ }; +struct acpi_processor_throttling_arg { + struct acpi_processor *pr; + int target_state; + bool force; +}; + #define THROTTLING_PRECHANGE (1) #define THROTTLING_POSTCHANGE (2) @@ -1060,16 +1066,24 @@ static int acpi_processor_set_throttling_ptc(struct acpi_processor *pr, return 0; } +static long acpi_processor_throttling_fn(void *data) +{ + struct acpi_processor_throttling_arg *arg = data; + struct acpi_processor *pr = arg->pr; + + return pr->throttling.acpi_processor_set_throttling(pr, + arg->target_state, arg->force); +} + int acpi_processor_set_throttling(struct acpi_processor *pr, int state, bool force) { - cpumask_var_t saved_mask; int ret = 0; unsigned int i; struct acpi_processor *match_pr; struct acpi_processor_throttling *p_throttling; + struct acpi_processor_throttling_arg arg; struct throttling_tstate t_state; - cpumask_var_t online_throttling_cpus; if (!pr) return -EINVAL; @@ -1080,14 +1094,6 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, if ((state < 0) || (state > (pr->throttling.state_count - 1))) return -EINVAL; - if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL)) - return -ENOMEM; - - if (!alloc_cpumask_var(&online_throttling_cpus, GFP_KERNEL)) { - free_cpumask_var(saved_mask); - return -ENOMEM; - } - if (cpu_is_offline(pr->id)) { /* * the cpu pointed by pr->id is offline. Unnecessary to change @@ -1096,17 +1102,15 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, return -ENODEV; } - cpumask_copy(saved_mask, ¤t->cpus_allowed); t_state.target_state = state; p_throttling = &(pr->throttling); - cpumask_and(online_throttling_cpus, cpu_online_mask, - p_throttling->shared_cpu_map); + /* * The throttling notifier will be called for every * affected cpu in order to get one proper T-state. * The notifier event is THROTTLING_PRECHANGE. */ - for_each_cpu(i, online_throttling_cpus) { + for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) { t_state.cpu = i; acpi_processor_throttling_notifier(THROTTLING_PRECHANGE, &t_state); @@ -1118,21 +1122,18 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, * it can be called only for the cpu pointed by pr. */ if (p_throttling->shared_type == DOMAIN_COORD_TYPE_SW_ANY) { - /* FIXME: use work_on_cpu() */ - if (set_cpus_allowed_ptr(current, cpumask_of(pr->id))) { - /* Can't migrate to the pr->id CPU. Exit */ - ret = -ENODEV; - goto exit; - } - ret = p_throttling->acpi_processor_set_throttling(pr, - t_state.target_state, force); + arg.pr = pr; + arg.target_state = state; + arg.force = force; + ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, &arg); } else { /* * When the T-state coordination is SW_ALL or HW_ALL, * it is necessary to set T-state for every affected * cpus. */ - for_each_cpu(i, online_throttling_cpus) { + for_each_cpu_and(i, cpu_online_mask, + p_throttling->shared_cpu_map) { match_pr = per_cpu(processors, i); /* * If the pointer is invalid, we will report the @@ -1153,13 +1154,12 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, "on CPU %d\n", i)); continue; } - t_state.cpu = i; - /* FIXME: use work_on_cpu() */ - if (set_cpus_allowed_ptr(current, cpumask_of(i))) - continue; - ret = match_pr->throttling. - acpi_processor_set_throttling( - match_pr, t_state.target_state, force); + + arg.pr = match_pr; + arg.target_state = state; + arg.force = force; + ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, + &arg); } } /* @@ -1168,17 +1168,12 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, * affected cpu to update the T-states. * The notifier event is THROTTLING_POSTCHANGE */ - for_each_cpu(i, online_throttling_cpus) { + for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) { t_state.cpu = i; acpi_processor_throttling_notifier(THROTTLING_POSTCHANGE, &t_state); } - /* restore the previous state */ - /* FIXME: use work_on_cpu() */ - set_cpus_allowed_ptr(current, saved_mask); -exit: - free_cpumask_var(online_throttling_cpus); - free_cpumask_var(saved_mask); + return ret; } -- cgit v1.2.3