From 95a79fd458b85132c25e351d45037ec9643312b2 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 7 Jan 2013 18:12:14 +0100 Subject: context_tracking: Export context state for generic vtime Export the context state: whether we run in user / kernel from the context tracking subsystem point of view. This is going to be used by the generic virtual cputime accounting subsystem that is needed to implement the full dynticks. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Ingo Molnar Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/context_tracking.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index e0e07fd..54f471e 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -1,24 +1,10 @@ #include #include #include -#include #include -struct context_tracking { - /* - * When active is false, hooks are not set to - * minimize overhead: TIF flags are cleared - * and calls to user_enter/exit are ignored. This - * may be further optimized using static keys. - */ - bool active; - enum { - IN_KERNEL = 0, - IN_USER, - } state; -}; -static DEFINE_PER_CPU(struct context_tracking, context_tracking) = { +DEFINE_PER_CPU(struct context_tracking, context_tracking) = { #ifdef CONFIG_CONTEXT_TRACKING_FORCE .active = true, #endif -- cgit v1.1 From ae8dda5c473bf1a85913942adcaac449e5754bf3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Jan 2013 18:02:04 +0100 Subject: cputime: Move default nsecs_to_cputime() to jiffies based cputime file If the architecture doesn't provide an implementation of nsecs_to_cputime(), the cputime accounting core uses a default one that converts the nanoseconds to jiffies. However this only makes sense if we use the jiffies based cputime. For now it doesn't matter much because this API is only called on code that uses jiffies based cputime accounting. But the code may evolve and this API may be used more broadly in the future. Keeping this default implementation around is very error prone as it may introduce a bug and hide it on architectures that don't override this API. Fix this by moving this definition to the jiffies based cputime headers as it is the only place where it belongs to. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Ingo Molnar Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/cputime.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 293b202..5849448b 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -505,10 +505,6 @@ EXPORT_SYMBOL_GPL(vtime_account); #else -#ifndef nsecs_to_cputime -# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) -#endif - static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total) { u64 temp = (__force u64) rtime; -- cgit v1.1 From abf917cd91cbb73952758f9741e2fa65002a48ee Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 25 Jul 2012 07:56:04 +0200 Subject: cputime: Generic on-demand virtual cputime accounting If we want to stop the tick further idle, we need to be able to account the cputime without using the tick. Virtual based cputime accounting solves that problem by hooking into kernel/user boundaries. However implementing CONFIG_VIRT_CPU_ACCOUNTING require low level hooks and involves more overhead. But we already have a generic context tracking subsystem that is required for RCU needs by archs which plan to shut down the tick outside idle. This patch implements a generic virtual based cputime accounting that relies on these generic kernel/user hooks. There are some upsides of doing this: - This requires no arch code to implement CONFIG_VIRT_CPU_ACCOUNTING if context tracking is already built (already necessary for RCU in full tickless mode). - We can rely on the generic context tracking subsystem to dynamically (de)activate the hooks, so that we can switch anytime between virtual and tick based accounting. This way we don't have the overhead of the virtual accounting when the tick is running periodically. And one downside: - There is probably more overhead than a native virtual based cputime accounting. But this relies on hooks that are already set anyway. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Ingo Molnar Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/context_tracking.c | 6 +++-- kernel/sched/cputime.c | 61 +++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 61 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 54f471e..9002e92e 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -30,8 +30,9 @@ void user_enter(void) local_irq_save(flags); if (__this_cpu_read(context_tracking.active) && __this_cpu_read(context_tracking.state) != IN_USER) { - __this_cpu_write(context_tracking.state, IN_USER); + vtime_user_enter(current); rcu_user_enter(); + __this_cpu_write(context_tracking.state, IN_USER); } local_irq_restore(flags); } @@ -53,8 +54,9 @@ void user_exit(void) local_irq_save(flags); if (__this_cpu_read(context_tracking.state) == IN_USER) { - __this_cpu_write(context_tracking.state, IN_KERNEL); rcu_user_exit(); + vtime_user_exit(current); + __this_cpu_write(context_tracking.state, IN_KERNEL); } local_irq_restore(flags); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5849448b..1c964ec 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -3,6 +3,7 @@ #include #include #include +#include #include "sched.h" @@ -479,7 +480,9 @@ void vtime_task_switch(struct task_struct *prev) else vtime_account_system(prev); +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE vtime_account_user(prev); +#endif arch_vtime_task_switch(prev); } #endif @@ -495,10 +498,24 @@ void vtime_task_switch(struct task_struct *prev) #ifndef __ARCH_HAS_VTIME_ACCOUNT void vtime_account(struct task_struct *tsk) { - if (in_interrupt() || !is_idle_task(tsk)) - vtime_account_system(tsk); - else - vtime_account_idle(tsk); + if (!in_interrupt()) { + /* + * If we interrupted user, context_tracking_in_user() + * is 1 because the context tracking don't hook + * on irq entry/exit. This way we know if + * we need to flush user time on kernel entry. + */ + if (context_tracking_in_user()) { + vtime_account_user(tsk); + return; + } + + if (is_idle_task(tsk)) { + vtime_account_idle(tsk); + return; + } + } + vtime_account_system(tsk); } EXPORT_SYMBOL_GPL(vtime_account); #endif /* __ARCH_HAS_VTIME_ACCOUNT */ @@ -583,3 +600,39 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st); } #endif + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +static DEFINE_PER_CPU(unsigned long long, cputime_snap); + +static cputime_t get_vtime_delta(void) +{ + unsigned long long delta; + + delta = sched_clock() - __this_cpu_read(cputime_snap); + __this_cpu_add(cputime_snap, delta); + + /* CHECKME: always safe to convert nsecs to cputime? */ + return nsecs_to_cputime(delta); +} + +void vtime_account_system(struct task_struct *tsk) +{ + cputime_t delta_cpu = get_vtime_delta(); + + account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu)); +} + +void vtime_account_user(struct task_struct *tsk) +{ + cputime_t delta_cpu = get_vtime_delta(); + + account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); +} + +void vtime_account_idle(struct task_struct *tsk) +{ + cputime_t delta_cpu = get_vtime_delta(); + + account_idle_time(delta_cpu); +} +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -- cgit v1.1 From 3f4724ea85b7d9055a9976fa8f30b471bdfbca93 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 16 Jul 2012 18:00:34 +0200 Subject: cputime: Allow dynamic switch between tick/virtual based cputime accounting Allow to dynamically switch between tick and virtual based cputime accounting. This way we can provide a kind of "on-demand" virtual based cputime accounting. In this mode, the kernel relies on the context tracking subsystem to dynamically probe on kernel boundaries. This is in preparation for being able to stop the timer tick in more places than just the idle state. Doing so will depend on CONFIG_VIRT_CPU_ACCOUNTING_GEN which makes it possible to account the cputime without the tick by hooking on kernel/user boundaries. Depending whether the tick is stopped or not, we can switch between tick and vtime based accounting anytime in order to minimize the overhead associated to user hooks. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Ingo Molnar Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/cputime.c | 41 +++++++++++++++++++++++++++++++---------- kernel/time/tick-sched.c | 5 ++++- 2 files changed, 35 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 1c964ec..e1939d3 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -317,8 +317,6 @@ out: rcu_read_unlock(); } -#ifndef CONFIG_VIRT_CPU_ACCOUNTING - #ifdef CONFIG_IRQ_TIME_ACCOUNTING /* * Account a tick to a process and cpustat @@ -383,11 +381,12 @@ static void irqtime_account_idle_ticks(int ticks) irqtime_account_process_tick(current, 0, rq); } #else /* CONFIG_IRQ_TIME_ACCOUNTING */ -static void irqtime_account_idle_ticks(int ticks) {} -static void irqtime_account_process_tick(struct task_struct *p, int user_tick, +static inline void irqtime_account_idle_ticks(int ticks) {} +static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick, struct rq *rq) {} #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* * Account a single tick of cpu time. * @p: the process that the cpu time gets accounted to @@ -398,6 +397,9 @@ void account_process_tick(struct task_struct *p, int user_tick) cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); struct rq *rq = this_rq(); + if (vtime_accounting_enabled()) + return; + if (sched_clock_irqtime) { irqtime_account_process_tick(p, user_tick, rq); return; @@ -439,8 +441,7 @@ void account_idle_ticks(unsigned long ticks) account_idle_time(jiffies_to_cputime(ticks)); } - -#endif +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ /* * Use precise platform statistics if available: @@ -475,6 +476,9 @@ EXPORT_SYMBOL_GPL(vtime_account_system_irqsafe); #ifndef __ARCH_HAS_VTIME_TASK_SWITCH void vtime_task_switch(struct task_struct *prev) { + if (!vtime_accounting_enabled()) + return; + if (is_idle_task(prev)) vtime_account_idle(prev); else @@ -498,6 +502,9 @@ void vtime_task_switch(struct task_struct *prev) #ifndef __ARCH_HAS_VTIME_ACCOUNT void vtime_account(struct task_struct *tsk) { + if (!vtime_accounting_enabled()) + return; + if (!in_interrupt()) { /* * If we interrupted user, context_tracking_in_user() @@ -520,7 +527,7 @@ void vtime_account(struct task_struct *tsk) EXPORT_SYMBOL_GPL(vtime_account); #endif /* __ARCH_HAS_VTIME_ACCOUNT */ -#else +#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total) { @@ -599,7 +606,7 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime thread_group_cputime(p, &cputime); cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st); } -#endif +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN static DEFINE_PER_CPU(unsigned long long, cputime_snap); @@ -617,14 +624,23 @@ static cputime_t get_vtime_delta(void) void vtime_account_system(struct task_struct *tsk) { - cputime_t delta_cpu = get_vtime_delta(); + cputime_t delta_cpu; + + if (!vtime_accounting_enabled()) + return; + delta_cpu = get_vtime_delta(); account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu)); } void vtime_account_user(struct task_struct *tsk) { - cputime_t delta_cpu = get_vtime_delta(); + cputime_t delta_cpu; + + if (!vtime_accounting_enabled()) + return; + + delta_cpu = get_vtime_delta(); account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); } @@ -635,4 +651,9 @@ void vtime_account_idle(struct task_struct *tsk) account_idle_time(delta_cpu); } + +bool vtime_accounting_enabled(void) +{ + return context_tracking_active(); +} #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index d58e552..46dfb6d 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -631,8 +631,11 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) static void tick_nohz_account_idle_ticks(struct tick_sched *ts) { -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE unsigned long ticks; + + if (vtime_accounting_enabled()) + return; /* * We stopped the tick in idle. Update process times would miss the * time we slept as update_process_times does only a 1 tick -- cgit v1.1 From 6fac4829ce0ef9b7f24369086ce5f0e9f38d37bc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 13 Nov 2012 14:20:55 +0100 Subject: cputime: Use accessors to read task cputime stats This is in preparation for the full dynticks feature. While remotely reading the cputime of a task running in a full dynticks CPU, we'll need to do some extra-computation. This way we can account the time it spent tickless in userspace since its last cputime snapshot. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Ingo Molnar Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/acct.c | 6 ++++-- kernel/cpu.c | 4 +++- kernel/delayacct.c | 7 +++++-- kernel/exit.c | 10 ++++++---- kernel/posix-cpu-timers.c | 28 ++++++++++++++++++++++------ kernel/sched/cputime.c | 13 +++++++------ kernel/signal.c | 12 ++++++++---- kernel/tsacct.c | 44 ++++++++++++++++++++++++++++++++++---------- 8 files changed, 89 insertions(+), 35 deletions(-) (limited to 'kernel') diff --git a/kernel/acct.c b/kernel/acct.c index 051e071..e8b1627 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -566,6 +566,7 @@ out: void acct_collect(long exitcode, int group_dead) { struct pacct_struct *pacct = ¤t->signal->pacct; + cputime_t utime, stime; unsigned long vsize = 0; if (group_dead && current->mm) { @@ -593,8 +594,9 @@ void acct_collect(long exitcode, int group_dead) pacct->ac_flag |= ACORE; if (current->flags & PF_SIGNALED) pacct->ac_flag |= AXSIG; - pacct->ac_utime += current->utime; - pacct->ac_stime += current->stime; + task_cputime(current, &utime, &stime); + pacct->ac_utime += utime; + pacct->ac_stime += stime; pacct->ac_minflt += current->min_flt; pacct->ac_majflt += current->maj_flt; spin_unlock_irq(¤t->sighand->siglock); diff --git a/kernel/cpu.c b/kernel/cpu.c index 3046a50..e5d5e8e 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -224,11 +224,13 @@ void clear_tasks_mm_cpumask(int cpu) static inline void check_for_tasks(int cpu) { struct task_struct *p; + cputime_t utime, stime; write_lock_irq(&tasklist_lock); for_each_process(p) { + task_cputime(p, &utime, &stime); if (task_cpu(p) == cpu && p->state == TASK_RUNNING && - (p->utime || p->stime)) + (utime || stime)) printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d " "(state = %ld, flags = %x)\n", p->comm, task_pid_nr(p), cpu, diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 418b3f7..d473988 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -106,6 +106,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) unsigned long long t2, t3; unsigned long flags; struct timespec ts; + cputime_t utime, stime, stimescaled, utimescaled; /* Though tsk->delays accessed later, early exit avoids * unnecessary returning of other data @@ -114,12 +115,14 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) goto done; tmp = (s64)d->cpu_run_real_total; - cputime_to_timespec(tsk->utime + tsk->stime, &ts); + task_cputime(tsk, &utime, &stime); + cputime_to_timespec(utime + stime, &ts); tmp += timespec_to_ns(&ts); d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp; tmp = (s64)d->cpu_scaled_run_real_total; - cputime_to_timespec(tsk->utimescaled + tsk->stimescaled, &ts); + task_cputime_scaled(tsk, &utimescaled, &stimescaled); + cputime_to_timespec(utimescaled + stimescaled, &ts); tmp += timespec_to_ns(&ts); d->cpu_scaled_run_real_total = (tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp; diff --git a/kernel/exit.c b/kernel/exit.c index b4df219..7dd2040 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -85,6 +85,7 @@ static void __exit_signal(struct task_struct *tsk) bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *uninitialized_var(tty); + cputime_t utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); @@ -123,9 +124,10 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime += tsk->utime; - sig->stime += tsk->stime; - sig->gtime += tsk->gtime; + task_cputime(tsk, &utime, &stime); + sig->utime += utime; + sig->stime += stime; + sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; @@ -1092,7 +1094,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) sig = p->signal; psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; - psig->cgtime += p->gtime + sig->gtime + sig->cgtime; + psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index a278cad..165d476 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -155,11 +155,19 @@ static void bump_cpu_timer(struct k_itimer *timer, static inline cputime_t prof_ticks(struct task_struct *p) { - return p->utime + p->stime; + cputime_t utime, stime; + + task_cputime(p, &utime, &stime); + + return utime + stime; } static inline cputime_t virt_ticks(struct task_struct *p) { - return p->utime; + cputime_t utime; + + task_cputime(p, &utime, NULL); + + return utime; } static int @@ -471,18 +479,23 @@ static void cleanup_timers(struct list_head *head, */ void posix_cpu_timers_exit(struct task_struct *tsk) { + cputime_t utime, stime; + add_device_randomness((const void*) &tsk->se.sum_exec_runtime, sizeof(unsigned long long)); + task_cputime(tsk, &utime, &stime); cleanup_timers(tsk->cpu_timers, - tsk->utime, tsk->stime, tsk->se.sum_exec_runtime); + utime, stime, tsk->se.sum_exec_runtime); } void posix_cpu_timers_exit_group(struct task_struct *tsk) { struct signal_struct *const sig = tsk->signal; + cputime_t utime, stime; + task_cputime(tsk, &utime, &stime); cleanup_timers(tsk->signal->cpu_timers, - tsk->utime + sig->utime, tsk->stime + sig->stime, + utime + sig->utime, stime + sig->stime, tsk->se.sum_exec_runtime + sig->sum_sched_runtime); } @@ -1226,11 +1239,14 @@ static inline int task_cputime_expired(const struct task_cputime *sample, static inline int fastpath_timer_check(struct task_struct *tsk) { struct signal_struct *sig; + cputime_t utime, stime; + + task_cputime(tsk, &utime, &stime); if (!task_cputime_zero(&tsk->cputime_expires)) { struct task_cputime task_sample = { - .utime = tsk->utime, - .stime = tsk->stime, + .utime = utime, + .stime = stime, .sum_exec_runtime = tsk->se.sum_exec_runtime }; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index e1939d3..c533dea 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -164,7 +164,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime, task_group_account_field(p, index, (__force u64) cputime); /* Account for user time used */ - acct_update_integrals(p); + acct_account_cputime(p); } /* @@ -214,7 +214,7 @@ void __account_system_time(struct task_struct *p, cputime_t cputime, task_group_account_field(p, index, (__force u64) cputime); /* Account for system time used */ - acct_update_integrals(p); + acct_account_cputime(p); } /* @@ -296,6 +296,7 @@ static __always_inline bool steal_account_process_tick(void) void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) { struct signal_struct *sig = tsk->signal; + cputime_t utime, stime; struct task_struct *t; times->utime = sig->utime; @@ -309,8 +310,9 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) t = tsk; do { - times->utime += t->utime; - times->stime += t->stime; + task_cputime(tsk, &utime, &stime); + times->utime += utime; + times->stime += stime; times->sum_exec_runtime += task_sched_runtime(t); } while_each_thread(tsk, t); out: @@ -588,11 +590,10 @@ static void cputime_adjust(struct task_cputime *curr, void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) { struct task_cputime cputime = { - .utime = p->utime, - .stime = p->stime, .sum_exec_runtime = p->se.sum_exec_runtime, }; + task_cputime(p, &cputime.utime, &cputime.stime); cputime_adjust(&cputime, &p->prev_cputime, ut, st); } diff --git a/kernel/signal.c b/kernel/signal.c index 372771e..776a45a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1638,6 +1638,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig) unsigned long flags; struct sighand_struct *psig; bool autoreap = false; + cputime_t utime, stime; BUG_ON(sig == -1); @@ -1675,8 +1676,9 @@ bool do_notify_parent(struct task_struct *tsk, int sig) task_uid(tsk)); rcu_read_unlock(); - info.si_utime = cputime_to_clock_t(tsk->utime + tsk->signal->utime); - info.si_stime = cputime_to_clock_t(tsk->stime + tsk->signal->stime); + task_cputime(tsk, &utime, &stime); + info.si_utime = cputime_to_clock_t(utime + tsk->signal->utime); + info.si_stime = cputime_to_clock_t(stime + tsk->signal->stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) @@ -1740,6 +1742,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, unsigned long flags; struct task_struct *parent; struct sighand_struct *sighand; + cputime_t utime, stime; if (for_ptracer) { parent = tsk->parent; @@ -1758,8 +1761,9 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk)); rcu_read_unlock(); - info.si_utime = cputime_to_clock_t(tsk->utime); - info.si_stime = cputime_to_clock_t(tsk->stime); + task_cputime(tsk, &utime, &stime); + info.si_utime = cputime_to_clock_t(utime); + info.si_stime = cputime_to_clock_t(stime); info.si_code = why; switch (why) { diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 625df0b..a1dd9a1 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -32,6 +32,7 @@ void bacct_add_tsk(struct user_namespace *user_ns, { const struct cred *tcred; struct timespec uptime, ts; + cputime_t utime, stime, utimescaled, stimescaled; u64 ac_etime; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); @@ -65,10 +66,15 @@ void bacct_add_tsk(struct user_namespace *user_ns, stats->ac_ppid = pid_alive(tsk) ? task_tgid_nr_ns(rcu_dereference(tsk->real_parent), pid_ns) : 0; rcu_read_unlock(); - stats->ac_utime = cputime_to_usecs(tsk->utime); - stats->ac_stime = cputime_to_usecs(tsk->stime); - stats->ac_utimescaled = cputime_to_usecs(tsk->utimescaled); - stats->ac_stimescaled = cputime_to_usecs(tsk->stimescaled); + + task_cputime(tsk, &utime, &stime); + stats->ac_utime = cputime_to_usecs(utime); + stats->ac_stime = cputime_to_usecs(stime); + + task_cputime_scaled(tsk, &utimescaled, &stimescaled); + stats->ac_utimescaled = cputime_to_usecs(utimescaled); + stats->ac_stimescaled = cputime_to_usecs(stimescaled); + stats->ac_minflt = tsk->min_flt; stats->ac_majflt = tsk->maj_flt; @@ -115,11 +121,8 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) #undef KB #undef MB -/** - * acct_update_integrals - update mm integral fields in task_struct - * @tsk: task_struct for accounting - */ -void acct_update_integrals(struct task_struct *tsk) +static void __acct_update_integrals(struct task_struct *tsk, + cputime_t utime, cputime_t stime) { if (likely(tsk->mm)) { cputime_t time, dtime; @@ -128,7 +131,7 @@ void acct_update_integrals(struct task_struct *tsk) u64 delta; local_irq_save(flags); - time = tsk->stime + tsk->utime; + time = stime + utime; dtime = time - tsk->acct_timexpd; jiffies_to_timeval(cputime_to_jiffies(dtime), &value); delta = value.tv_sec; @@ -145,6 +148,27 @@ void acct_update_integrals(struct task_struct *tsk) } /** + * acct_update_integrals - update mm integral fields in task_struct + * @tsk: task_struct for accounting + */ +void acct_update_integrals(struct task_struct *tsk) +{ + cputime_t utime, stime; + + task_cputime(tsk, &utime, &stime); + __acct_update_integrals(tsk, utime, stime); +} + +/** + * acct_account_cputime - update mm integral after cputime update + * @tsk: task_struct for accounting + */ +void acct_account_cputime(struct task_struct *tsk) +{ + __acct_update_integrals(tsk, tsk->utime, tsk->stime); +} + +/** * acct_clear_integrals - clear the mm integral fields in task_struct * @tsk: task_struct whose accounting fields are cleared */ -- cgit v1.1 From c11f11fcbdb5be790c565aed46411486a7586afc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 21 Jan 2013 00:50:22 +0100 Subject: kvm: Prepare to add generic guest entry/exit callbacks Do some ground preparatory work before adding guest_enter() and guest_exit() context tracking callbacks. Those will be later used to read the guest cputime safely when we run in full dynticks mode. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Gleb Natapov Cc: Ingo Molnar Cc: Li Zhong Cc: Marcelo Tosatti Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/cputime.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index c533dea..a44ecdf 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -465,16 +465,6 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime *st = cputime.stime; } -void vtime_account_system_irqsafe(struct task_struct *tsk) -{ - unsigned long flags; - - local_irq_save(flags); - vtime_account_system(tsk); - local_irq_restore(flags); -} -EXPORT_SYMBOL_GPL(vtime_account_system_irqsafe); - #ifndef __ARCH_HAS_VTIME_TASK_SWITCH void vtime_task_switch(struct task_struct *prev) { -- cgit v1.1 From 6a61671bb2f3a1bd12cd17b8fca811a624782632 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 16 Dec 2012 20:00:34 +0100 Subject: cputime: Safely read cputime of full dynticks CPUs While remotely reading the cputime of a task running in a full dynticks CPU, the values stored in utime/stime fields of struct task_struct may be stale. Its values may be those of the last kernel <-> user transition time snapshot and we need to add the tickless time spent since this snapshot. To fix this, flush the cputime of the dynticks CPUs on kernel <-> user transition and record the time / context where we did this. Then on top of this snapshot and the current time, perform the fixup on the reader side from task_times() accessors. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Ingo Molnar Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner [fixed kvm module related build errors] Signed-off-by: Sedat Dilek --- kernel/context_tracking.c | 21 ++++- kernel/fork.c | 6 ++ kernel/sched/core.c | 1 + kernel/sched/cputime.c | 193 +++++++++++++++++++++++++++++++++++++++++++--- kernel/softirq.c | 6 +- 5 files changed, 211 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 9002e92e..74f68f4 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -1,8 +1,9 @@ #include +#include #include #include #include - +#include DEFINE_PER_CPU(struct context_tracking, context_tracking) = { #ifdef CONFIG_CONTEXT_TRACKING_FORCE @@ -61,6 +62,24 @@ void user_exit(void) local_irq_restore(flags); } +void guest_enter(void) +{ + if (vtime_accounting_enabled()) + vtime_guest_enter(current); + else + __guest_enter(); +} +EXPORT_SYMBOL_GPL(guest_enter); + +void guest_exit(void) +{ + if (vtime_accounting_enabled()) + vtime_guest_exit(current); + else + __guest_exit(); +} +EXPORT_SYMBOL_GPL(guest_exit); + void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next) { diff --git a/kernel/fork.c b/kernel/fork.c index 65ca6d2..e68a95b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1233,6 +1233,12 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifndef CONFIG_VIRT_CPU_ACCOUNTING p->prev_cputime.utime = p->prev_cputime.stime = 0; #endif +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + seqlock_init(&p->vtime_seqlock); + p->vtime_snap = 0; + p->vtime_snap_whence = VTIME_SLEEPING; +#endif + #if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); #endif diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 257002c..261022d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4666,6 +4666,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) */ idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); + vtime_init_idle(idle); #if defined(CONFIG_SMP) sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index a44ecdf..082e05d 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -492,7 +492,7 @@ void vtime_task_switch(struct task_struct *prev) * vtime_account(). */ #ifndef __ARCH_HAS_VTIME_ACCOUNT -void vtime_account(struct task_struct *tsk) +void vtime_account_irq_enter(struct task_struct *tsk) { if (!vtime_accounting_enabled()) return; @@ -516,7 +516,7 @@ void vtime_account(struct task_struct *tsk) } vtime_account_system(tsk); } -EXPORT_SYMBOL_GPL(vtime_account); +EXPORT_SYMBOL_GPL(vtime_account_irq_enter); #endif /* __ARCH_HAS_VTIME_ACCOUNT */ #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ @@ -600,28 +600,55 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -static DEFINE_PER_CPU(unsigned long long, cputime_snap); +static unsigned long long vtime_delta(struct task_struct *tsk) +{ + unsigned long long clock; + + clock = sched_clock(); + if (clock < tsk->vtime_snap) + return 0; -static cputime_t get_vtime_delta(void) + return clock - tsk->vtime_snap; +} + +static cputime_t get_vtime_delta(struct task_struct *tsk) { - unsigned long long delta; + unsigned long long delta = vtime_delta(tsk); - delta = sched_clock() - __this_cpu_read(cputime_snap); - __this_cpu_add(cputime_snap, delta); + WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING); + tsk->vtime_snap += delta; /* CHECKME: always safe to convert nsecs to cputime? */ return nsecs_to_cputime(delta); } +static void __vtime_account_system(struct task_struct *tsk) +{ + cputime_t delta_cpu = get_vtime_delta(tsk); + + account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu)); +} + void vtime_account_system(struct task_struct *tsk) { - cputime_t delta_cpu; + if (!vtime_accounting_enabled()) + return; + + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + write_sequnlock(&tsk->vtime_seqlock); +} +void vtime_account_irq_exit(struct task_struct *tsk) +{ if (!vtime_accounting_enabled()) return; - delta_cpu = get_vtime_delta(); - account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu)); + write_seqlock(&tsk->vtime_seqlock); + if (context_tracking_in_user()) + tsk->vtime_snap_whence = VTIME_USER; + __vtime_account_system(tsk); + write_sequnlock(&tsk->vtime_seqlock); } void vtime_account_user(struct task_struct *tsk) @@ -631,14 +658,44 @@ void vtime_account_user(struct task_struct *tsk) if (!vtime_accounting_enabled()) return; - delta_cpu = get_vtime_delta(); + delta_cpu = get_vtime_delta(tsk); + write_seqlock(&tsk->vtime_seqlock); + tsk->vtime_snap_whence = VTIME_SYS; account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_user_enter(struct task_struct *tsk) +{ + if (!vtime_accounting_enabled()) + return; + + write_seqlock(&tsk->vtime_seqlock); + tsk->vtime_snap_whence = VTIME_USER; + __vtime_account_system(tsk); + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_guest_enter(struct task_struct *tsk) +{ + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + current->flags |= PF_VCPU; + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_guest_exit(struct task_struct *tsk) +{ + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + current->flags &= ~PF_VCPU; + write_sequnlock(&tsk->vtime_seqlock); } void vtime_account_idle(struct task_struct *tsk) { - cputime_t delta_cpu = get_vtime_delta(); + cputime_t delta_cpu = get_vtime_delta(tsk); account_idle_time(delta_cpu); } @@ -647,4 +704,116 @@ bool vtime_accounting_enabled(void) { return context_tracking_active(); } + +void arch_vtime_task_switch(struct task_struct *prev) +{ + write_seqlock(&prev->vtime_seqlock); + prev->vtime_snap_whence = VTIME_SLEEPING; + write_sequnlock(&prev->vtime_seqlock); + + write_seqlock(¤t->vtime_seqlock); + current->vtime_snap_whence = VTIME_SYS; + current->vtime_snap = sched_clock(); + write_sequnlock(¤t->vtime_seqlock); +} + +void vtime_init_idle(struct task_struct *t) +{ + unsigned long flags; + + write_seqlock_irqsave(&t->vtime_seqlock, flags); + t->vtime_snap_whence = VTIME_SYS; + t->vtime_snap = sched_clock(); + write_sequnlock_irqrestore(&t->vtime_seqlock, flags); +} + +cputime_t task_gtime(struct task_struct *t) +{ + unsigned long flags; + unsigned int seq; + cputime_t gtime; + + do { + seq = read_seqbegin_irqsave(&t->vtime_seqlock, flags); + + gtime = t->gtime; + if (t->flags & PF_VCPU) + gtime += vtime_delta(t); + + } while (read_seqretry_irqrestore(&t->vtime_seqlock, seq, flags)); + + return gtime; +} + +/* + * Fetch cputime raw values from fields of task_struct and + * add up the pending nohz execution time since the last + * cputime snapshot. + */ +static void +fetch_task_cputime(struct task_struct *t, + cputime_t *u_dst, cputime_t *s_dst, + cputime_t *u_src, cputime_t *s_src, + cputime_t *udelta, cputime_t *sdelta) +{ + unsigned long flags; + unsigned int seq; + unsigned long long delta; + + do { + *udelta = 0; + *sdelta = 0; + + seq = read_seqbegin_irqsave(&t->vtime_seqlock, flags); + + if (u_dst) + *u_dst = *u_src; + if (s_dst) + *s_dst = *s_src; + + /* Task is sleeping, nothing to add */ + if (t->vtime_snap_whence == VTIME_SLEEPING || + is_idle_task(t)) + continue; + + delta = vtime_delta(t); + + /* + * Task runs either in user or kernel space, add pending nohz time to + * the right place. + */ + if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU) { + *udelta = delta; + } else { + if (t->vtime_snap_whence == VTIME_SYS) + *sdelta = delta; + } + } while (read_seqretry_irqrestore(&t->vtime_seqlock, seq, flags)); +} + + +void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime) +{ + cputime_t udelta, sdelta; + + fetch_task_cputime(t, utime, stime, &t->utime, + &t->stime, &udelta, &sdelta); + if (utime) + *utime += udelta; + if (stime) + *stime += sdelta; +} + +void task_cputime_scaled(struct task_struct *t, + cputime_t *utimescaled, cputime_t *stimescaled) +{ + cputime_t udelta, sdelta; + + fetch_task_cputime(t, utimescaled, stimescaled, + &t->utimescaled, &t->stimescaled, &udelta, &sdelta); + if (utimescaled) + *utimescaled += cputime_to_scaled(udelta); + if (stimescaled) + *stimescaled += cputime_to_scaled(sdelta); +} #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ diff --git a/kernel/softirq.c b/kernel/softirq.c index ed567ba..f5cc25f 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -221,7 +221,7 @@ asmlinkage void __do_softirq(void) current->flags &= ~PF_MEMALLOC; pending = local_softirq_pending(); - vtime_account_irq_enter(current); + account_irq_enter_time(current); __local_bh_disable((unsigned long)__builtin_return_address(0), SOFTIRQ_OFFSET); @@ -272,7 +272,7 @@ restart: lockdep_softirq_exit(); - vtime_account_irq_exit(current); + account_irq_exit_time(current); __local_bh_enable(SOFTIRQ_OFFSET); tsk_restore_flags(current, old_flags, PF_MEMALLOC); } @@ -341,7 +341,7 @@ static inline void invoke_softirq(void) */ void irq_exit(void) { - vtime_account_irq_exit(current); + account_irq_exit_time(current); trace_hardirq_exit(); sub_preempt_count(IRQ_EXIT_OFFSET); if (!in_interrupt() && local_softirq_pending()) -- cgit v1.1