From aae6d3ddd8b90f5b2c8d79a2b914d1706d124193 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Fri, 17 Sep 2010 15:02:32 -0700 Subject: sched: Use group weight, idle cpu metrics to fix imbalances during idle Currently we consider a sched domain to be well balanced when the imbalance is less than the domain's imablance_pct. As the number of cores and threads are increasing, current values of imbalance_pct (for example 25% for a NUMA domain) are not enough to detect imbalances like: a) On a WSM-EP system (two sockets, each having 6 cores and 12 logical threads), 24 cpu-hogging tasks get scheduled as 13 on one socket and 11 on another socket. Leading to an idle HT cpu. b) On a hypothetial 2 socket NHM-EX system (each socket having 8 cores and 16 logical threads), 16 cpu-hogging tasks can get scheduled as 9 on one socket and 7 on another socket. Leaving one core in a socket idle whereas in another socket we have a core having both its HT siblings busy. While this issue can be fixed by decreasing the domain's imbalance_pct (by making it a function of number of logical cpus in the domain), it can potentially cause more task migrations across sched groups in an overloaded case. Fix this by using imbalance_pct only during newly_idle and busy load balancing. And during idle load balancing, check if there is an imbalance in number of idle cpu's across the busiest and this sched_group or if the busiest group has more tasks than its weight that the idle cpu in this_group can pull. Reported-by: Nikhil Rao Signed-off-by: Suresh Siddha Signed-off-by: Peter Zijlstra LKML-Reference: <1284760952.2676.11.camel@sbsiddha-MOBL3.sc.intel.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index aa14a56..36a0880 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6960,6 +6960,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) if (cpu != group_first_cpu(sd->groups)) return; + sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups)); + child = sd->child; sd->groups->cpu_power = 0; -- cgit v1.1 From 1e5a74059f9059d330744eac84873b1b99657008 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 31 Oct 2010 12:37:04 +0100 Subject: sched: Fix cross-sched-class wakeup preemption Instead of dealing with sched classes inside each check_preempt_curr() implementation, pull out this logic into the generic wakeup preemption path. This fixes a hang in KVM (and others) where we are waiting for the stop machine thread to run ... Reported-by: Markus Trippelsdorf Tested-by: Marcelo Tosatti Tested-by: Sergey Senozhatsky Signed-off-by: Peter Zijlstra LKML-Reference: <1288891946.2039.31.camel@laptop> Signed-off-by: Ingo Molnar --- kernel/sched.c | 37 ++++++++++++++++++++++++++----------- 1 file changed, 26 insertions(+), 11 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 36a0880..dc91a4d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -560,18 +560,8 @@ struct rq { static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -static inline -void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) -{ - rq->curr->sched_class->check_preempt_curr(rq, p, flags); - /* - * A queue event has occurred, and we're going to schedule. In - * this case, we can save a useless back to back clock update. - */ - if (test_tsk_need_resched(p)) - rq->skip_clock_update = 1; -} +static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); static inline int cpu_of(struct rq *rq) { @@ -2118,6 +2108,31 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, p->sched_class->prio_changed(rq, p, oldprio, running); } +static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) +{ + const struct sched_class *class; + + if (p->sched_class == rq->curr->sched_class) { + rq->curr->sched_class->check_preempt_curr(rq, p, flags); + } else { + for_each_class(class) { + if (class == rq->curr->sched_class) + break; + if (class == p->sched_class) { + resched_task(rq->curr); + break; + } + } + } + + /* + * A queue event has occurred, and we're going to schedule. In + * this case, we can save a useless back to back clock update. + */ + if (test_tsk_need_resched(rq->curr)) + rq->skip_clock_update = 1; +} + #ifdef CONFIG_SMP /* * Is this task likely cache-hot: -- cgit v1.1 From 0f004f5a696a9434b7214d0d3cbd0525ee77d428 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 30 Nov 2010 19:48:45 +0100 Subject: sched: Cure more NO_HZ load average woes There's a long-running regression that proved difficult to fix and which is hitting certain people and is rather annoying in its effects. Damien reported that after 74f5187ac8 (sched: Cure load average vs NO_HZ woes) his load average is unnaturally high, he also noted that even with that patch reverted the load avgerage numbers are not correct. The problem is that the previous patch only solved half the NO_HZ problem, it addressed the part of going into NO_HZ mode, not of comming out of NO_HZ mode. This patch implements that missing half. When comming out of NO_HZ mode there are two important things to take care of: - Folding the pending idle delta into the global active count. - Correctly aging the averages for the idle-duration. So with this patch the NO_HZ interaction should be complete and behaviour between CONFIG_NO_HZ=[yn] should be equivalent. Furthermore, this patch slightly changes the load average computation by adding a rounding term to the fixed point multiplication. Reported-by: Damien Wyart Reported-by: Tim McGrath Tested-by: Damien Wyart Tested-by: Orion Poplawski Tested-by: Kyle McMartin Signed-off-by: Peter Zijlstra Cc: stable@kernel.org Cc: Chase Douglas LKML-Reference: <1291129145.32004.874.camel@laptop> Signed-off-by: Ingo Molnar --- kernel/sched.c | 150 ++++++++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 139 insertions(+), 11 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index dc91a4d..6b7c26a 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3119,6 +3119,15 @@ static long calc_load_fold_active(struct rq *this_rq) return delta; } +static unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + load *= exp; + load += active * (FIXED_1 - exp); + load += 1UL << (FSHIFT - 1); + return load >> FSHIFT; +} + #ifdef CONFIG_NO_HZ /* * For NO_HZ we delay the active fold to the next LOAD_FREQ update. @@ -3148,6 +3157,128 @@ static long calc_load_fold_idle(void) return delta; } + +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. + */ +static unsigned long +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) +{ + unsigned long result = 1UL << frac_bits; + + if (n) for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + + return result; +} + +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +static unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); +} + +/* + * NO_HZ can leave us missing all per-cpu ticks calling + * calc_load_account_active(), but since an idle CPU folds its delta into + * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold + * in the pending idle delta if our idle period crossed a load cycle boundary. + * + * Once we've updated the global active value, we need to apply the exponential + * weights adjusted to the number of cycles missed. + */ +static void calc_global_nohz(unsigned long ticks) +{ + long delta, active, n; + + if (time_before(jiffies, calc_load_update)) + return; + + /* + * If we crossed a calc_load_update boundary, make sure to fold + * any pending idle changes, the respective CPUs might have + * missed the tick driven calc_load_account_active() update + * due to NO_HZ. + */ + delta = calc_load_fold_idle(); + if (delta) + atomic_long_add(delta, &calc_load_tasks); + + /* + * If we were idle for multiple load cycles, apply them. + */ + if (ticks >= LOAD_FREQ) { + n = ticks / LOAD_FREQ; + + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; + + avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); + avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); + avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); + + calc_load_update += n * LOAD_FREQ; + } + + /* + * Its possible the remainder of the above division also crosses + * a LOAD_FREQ period, the regular check in calc_global_load() + * which comes after this will take care of that. + * + * Consider us being 11 ticks before a cycle completion, and us + * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will + * age us 4 cycles, and the test in calc_global_load() will + * pick up the final one. + */ +} #else static void calc_load_account_idle(struct rq *this_rq) { @@ -3157,6 +3288,10 @@ static inline long calc_load_fold_idle(void) { return 0; } + +static void calc_global_nohz(unsigned long ticks) +{ +} #endif /** @@ -3174,24 +3309,17 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift) loads[2] = (avenrun[2] + offset) << shift; } -static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) -{ - load *= exp; - load += active * (FIXED_1 - exp); - return load >> FSHIFT; -} - /* * calc_load - update the avenrun load estimates 10 ticks after the * CPUs have updated calc_load_tasks. */ -void calc_global_load(void) +void calc_global_load(unsigned long ticks) { - unsigned long upd = calc_load_update + 10; long active; - if (time_before(jiffies, upd)) + calc_global_nohz(ticks); + + if (time_before(jiffies, calc_load_update + 10)) return; active = atomic_long_read(&calc_load_tasks); -- cgit v1.1 From f26f9aff6aaf67e9a430d16c266f91b13a5bff64 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Wed, 8 Dec 2010 11:05:42 +0100 Subject: Sched: fix skip_clock_update optimization idle_balance() drops/retakes rq->lock, leaving the previous task vulnerable to set_tsk_need_resched(). Clear it after we return from balancing instead, and in setup_thread_stack() as well, so no successfully descheduled or never scheduled task has it set. Need resched confused the skip_clock_update logic, which assumes that the next call to update_rq_clock() will come nearly immediately after being set. Make the optimization robust against the waking a sleeper before it sucessfully deschedules case by checking that the current task has not been dequeued before setting the flag, since it is that useless clock update we're trying to save, and clear unconditionally in schedule() proper instead of conditionally in put_prev_task(). Signed-off-by: Mike Galbraith Reported-by: Bjoern B. Brandenburg Tested-by: Yong Zhang Signed-off-by: Peter Zijlstra Cc: stable@kernel.org LKML-Reference: <1291802742.1417.9.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 6b7c26a..da14302 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -641,17 +641,18 @@ static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time); inline void update_rq_clock(struct rq *rq) { - if (!rq->skip_clock_update) { - int cpu = cpu_of(rq); - u64 irq_time; + int cpu = cpu_of(rq); + u64 irq_time; - rq->clock = sched_clock_cpu(cpu); - irq_time = irq_time_cpu(cpu); - if (rq->clock - irq_time > rq->clock_task) - rq->clock_task = rq->clock - irq_time; + if (rq->skip_clock_update) + return; - sched_irq_time_avg_update(rq, irq_time); - } + rq->clock = sched_clock_cpu(cpu); + irq_time = irq_time_cpu(cpu); + if (rq->clock - irq_time > rq->clock_task) + rq->clock_task = rq->clock - irq_time; + + sched_irq_time_avg_update(rq, irq_time); } /* @@ -2129,7 +2130,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) * A queue event has occurred, and we're going to schedule. In * this case, we can save a useless back to back clock update. */ - if (test_tsk_need_resched(rq->curr)) + if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr)) rq->skip_clock_update = 1; } @@ -3973,7 +3974,6 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev) { if (prev->se.on_rq) update_rq_clock(rq); - rq->skip_clock_update = 0; prev->sched_class->put_prev_task(rq, prev); } @@ -4031,7 +4031,6 @@ need_resched_nonpreemptible: hrtick_clear(rq); raw_spin_lock_irq(&rq->lock); - clear_tsk_need_resched(prev); switch_count = &prev->nivcsw; if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { @@ -4063,6 +4062,8 @@ need_resched_nonpreemptible: put_prev_task(rq, prev); next = pick_next_task(rq); + clear_tsk_need_resched(prev); + rq->skip_clock_update = 0; if (likely(prev != next)) { sched_info_switch(prev, next); @@ -4071,6 +4072,7 @@ need_resched_nonpreemptible: rq->nr_switches++; rq->curr = next; ++*switch_count; + WARN_ON_ONCE(test_tsk_need_resched(next)); context_switch(rq, prev, next); /* unlocks the rq */ /* -- cgit v1.1 From fe44d62122829959e960bc699318d58966922a69 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 9 Dec 2010 14:15:34 +0100 Subject: sched: Fix the irqtime code to deal with u64 wraps Some ARM systems have a short sched_clock() [ which needs to be fixed too ], but this exposed a bug in the irq_time code as well, it doesn't deal with wraps at all. Fix the irq_time code to deal with u64 wraps by re-writing the code to only use delta increments, which avoids the whole issue. Reviewed-by: Venkatesh Pallipadi Reported-by: Mikael Pettersson Tested-by: Mikael Pettersson Signed-off-by: Peter Zijlstra LKML-Reference: <1292242433.6803.199.camel@twins> Signed-off-by: Ingo Molnar --- kernel/sched.c | 83 +++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 50 insertions(+), 33 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index da14302..79b557c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -636,23 +636,18 @@ static inline struct task_group *task_group(struct task_struct *p) #endif /* CONFIG_CGROUP_SCHED */ -static u64 irq_time_cpu(int cpu); -static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time); +static void update_rq_clock_task(struct rq *rq, s64 delta); -inline void update_rq_clock(struct rq *rq) +static void update_rq_clock(struct rq *rq) { - int cpu = cpu_of(rq); - u64 irq_time; + s64 delta; if (rq->skip_clock_update) return; - rq->clock = sched_clock_cpu(cpu); - irq_time = irq_time_cpu(cpu); - if (rq->clock - irq_time > rq->clock_task) - rq->clock_task = rq->clock - irq_time; - - sched_irq_time_avg_update(rq, irq_time); + delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + rq->clock += delta; + update_rq_clock_task(rq, delta); } /* @@ -1946,19 +1941,20 @@ void disable_sched_clock_irqtime(void) sched_clock_irqtime = 0; } -static u64 irq_time_cpu(int cpu) +static inline u64 irq_time_cpu(int cpu) { - if (!sched_clock_irqtime) - return 0; - return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); } +/* + * Called before incrementing preempt_count on {soft,}irq_enter + * and before decrementing preempt_count on {soft,}irq_exit. + */ void account_system_vtime(struct task_struct *curr) { unsigned long flags; + s64 delta; int cpu; - u64 now, delta; if (!sched_clock_irqtime) return; @@ -1966,9 +1962,9 @@ void account_system_vtime(struct task_struct *curr) local_irq_save(flags); cpu = smp_processor_id(); - now = sched_clock_cpu(cpu); - delta = now - per_cpu(irq_start_time, cpu); - per_cpu(irq_start_time, cpu) = now; + delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); + __this_cpu_add(irq_start_time, delta); + /* * We do not account for softirq time from ksoftirqd here. * We want to continue accounting softirq time to ksoftirqd thread @@ -1976,33 +1972,54 @@ void account_system_vtime(struct task_struct *curr) * that do not consume any time, but still wants to run. */ if (hardirq_count()) - per_cpu(cpu_hardirq_time, cpu) += delta; + __this_cpu_add(cpu_hardirq_time, delta); else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD)) - per_cpu(cpu_softirq_time, cpu) += delta; + __this_cpu_add(cpu_softirq_time, delta); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(account_system_vtime); -static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) +static void update_rq_clock_task(struct rq *rq, s64 delta) { - if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) { - u64 delta_irq = curr_irq_time - rq->prev_irq_time; - rq->prev_irq_time = curr_irq_time; - sched_rt_avg_update(rq, delta_irq); - } + s64 irq_delta; + + irq_delta = irq_time_cpu(cpu_of(rq)) - rq->prev_irq_time; + + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}irq region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}irq + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; + + rq->prev_irq_time += irq_delta; + delta -= irq_delta; + rq->clock_task += delta; + + if (irq_delta && sched_feat(NONIRQ_POWER)) + sched_rt_avg_update(rq, irq_delta); } -#else +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ -static u64 irq_time_cpu(int cpu) +static void update_rq_clock_task(struct rq *rq, s64 delta) { - return 0; + rq->clock_task += delta; } -static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { } - -#endif +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ #include "sched_idletask.c" #include "sched_fair.c" -- cgit v1.1 From 8e92c20183ed0579d94501311b81c42b65cb2129 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 9 Dec 2010 14:15:34 +0100 Subject: sched: Fix the irqtime code for 32bit Since the irqtime accounting is using non-atomic u64 and can be read from remote cpus (writes are strictly cpu local, reads are not) we have to deal with observing partial updates. When we do observe partial updates the clock movement (in particular, ->clock_task movement) will go funny (in either direction), a subsequent clock update (observing the full update) will make it go funny in the oposite direction. Since we rely on these clocks to be strictly monotonic we cannot suffer backwards motion. One possible solution would be to simply ignore all backwards deltas, but that will lead to accounting artefacts, most notable: clock_task + irq_time != clock, this inaccuracy would end up in user visible stats. Therefore serialize the reads using a seqcount. Reviewed-by: Venkatesh Pallipadi Reported-by: Mikael Pettersson Tested-by: Mikael Pettersson Signed-off-by: Peter Zijlstra LKML-Reference: <1292242434.6803.200.camel@twins> Signed-off-by: Ingo Molnar --- kernel/sched.c | 51 +++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 45 insertions(+), 6 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 79b557c..456c990 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1920,10 +1920,9 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags) * They are read and saved off onto struct rq in update_rq_clock(). * This may result in other CPU reading this CPU's irq time and can * race with irq/account_system_vtime on this CPU. We would either get old - * or new value (or semi updated value on 32 bit) with a side effect of - * accounting a slice of irq time to wrong task when irq is in progress - * while we read rq->clock. That is a worthy compromise in place of having - * locks on each irq in account_system_time. + * or new value with a side effect of accounting a slice of irq time to wrong + * task when irq is in progress while we read rq->clock. That is a worthy + * compromise in place of having locks on each irq in account_system_time. */ static DEFINE_PER_CPU(u64, cpu_hardirq_time); static DEFINE_PER_CPU(u64, cpu_softirq_time); @@ -1941,10 +1940,48 @@ void disable_sched_clock_irqtime(void) sched_clock_irqtime = 0; } -static inline u64 irq_time_cpu(int cpu) +#ifndef CONFIG_64BIT +static DEFINE_PER_CPU(seqcount_t, irq_time_seq); + +static inline void irq_time_write_begin(void) +{ + __this_cpu_inc(irq_time_seq.sequence); + smp_wmb(); +} + +static inline void irq_time_write_end(void) +{ + smp_wmb(); + __this_cpu_inc(irq_time_seq.sequence); +} + +static inline u64 irq_time_read(int cpu) +{ + u64 irq_time; + unsigned seq; + + do { + seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); + irq_time = per_cpu(cpu_softirq_time, cpu) + + per_cpu(cpu_hardirq_time, cpu); + } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); + + return irq_time; +} +#else /* CONFIG_64BIT */ +static inline void irq_time_write_begin(void) +{ +} + +static inline void irq_time_write_end(void) +{ +} + +static inline u64 irq_time_read(int cpu) { return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); } +#endif /* CONFIG_64BIT */ /* * Called before incrementing preempt_count on {soft,}irq_enter @@ -1965,6 +2002,7 @@ void account_system_vtime(struct task_struct *curr) delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); __this_cpu_add(irq_start_time, delta); + irq_time_write_begin(); /* * We do not account for softirq time from ksoftirqd here. * We want to continue accounting softirq time to ksoftirqd thread @@ -1976,6 +2014,7 @@ void account_system_vtime(struct task_struct *curr) else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD)) __this_cpu_add(cpu_softirq_time, delta); + irq_time_write_end(); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(account_system_vtime); @@ -1984,7 +2023,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) { s64 irq_delta; - irq_delta = irq_time_cpu(cpu_of(rq)) - rq->prev_irq_time; + irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; /* * Since irq_time is only updated on {soft,}irq_exit, we might run into -- cgit v1.1 From 050c6c9b896625d9fa498265be17b82c5fc65257 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 19 Dec 2010 23:24:27 +0100 Subject: sched: Remove debugging check Linus reported that the new warning introduced by commit f26f9aff6aaf "Sched: fix skip_clock_update optimization" triggers. The need_resched flag can be set by other CPUs asynchronously so this debug check is bogus - remove it. Reported-by: Linus Torvalds Cc: Peter Zijlstra Cc: Mike Galbraith LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 456c990..297d1a0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4128,7 +4128,6 @@ need_resched_nonpreemptible: rq->nr_switches++; rq->curr = next; ++*switch_count; - WARN_ON_ONCE(test_tsk_need_resched(next)); context_switch(rq, prev, next); /* unlocks the rq */ /* -- cgit v1.1