From 54fdc5816631b43ba55fc3206d7add2d85850bc6 Mon Sep 17 00:00:00 2001 From: Fabio Checconi Date: Thu, 16 Jul 2009 12:32:27 +0200 Subject: [PATCH 1/3] sched: Account for vruntime wrapping I spotted two sites that didn't take vruntime wrap-around into account. Fix these by creating a comparison helper that does do so. Signed-off-by: Fabio Checconi Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 7c248dc30f41..9ffb2b2ceba4 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -266,6 +266,12 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) return min_vruntime; } +static inline int entity_before(struct sched_entity *a, + struct sched_entity *b) +{ + return (s64)(a->vruntime - b->vruntime) < 0; +} + static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) { return se->vruntime - cfs_rq->min_vruntime; @@ -1017,7 +1023,7 @@ static void yield_task_fair(struct rq *rq) /* * Already in the rightmost position? */ - if (unlikely(!rightmost || rightmost->vruntime < se->vruntime)) + if (unlikely(!rightmost || entity_before(rightmost, se))) return; /* @@ -1713,7 +1719,7 @@ static void task_new_fair(struct rq *rq, struct task_struct *p) /* 'curr' will be NULL if the child belongs to a different group */ if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) && - curr && curr->vruntime < se->vruntime) { + curr && entity_before(curr, se)) { /* * Upon rescheduling, sched_class::put_prev_task() will place * 'current' within the tree based on its new key value. From a468d389349a7560249b355cdb6d2097ea1616c9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 17 Jul 2009 14:15:46 +0200 Subject: [PATCH 2/3] sched: fix load average accounting vs. cpu hotplug The new load average code clears rq->calc_load_active on CPU_ONLINE. That's wrong as the new onlined CPU might have got a scheduler tick already and accounted the delta to the stale value of the time we offlined the CPU. Clear the value when we cleanup the dead CPU instead. Also move the update of the calc_load_update time for the newly online CPU to CPU_UP_PREPARE to avoid that the CPU plays catch up with the stale update time value. Signed-off-by: Thomas Gleixner --- kernel/sched.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 98972d366fdc..1b59e265273b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7289,6 +7289,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu) static void calc_global_load_remove(struct rq *rq) { atomic_long_sub(rq->calc_load_active, &calc_load_tasks); + rq->calc_load_active = 0; } #endif /* CONFIG_HOTPLUG_CPU */ @@ -7515,6 +7516,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) task_rq_unlock(rq, &flags); get_task_struct(p); cpu_rq(cpu)->migration_thread = p; + rq->calc_load_update = calc_load_update; break; case CPU_ONLINE: @@ -7525,8 +7527,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) /* Update our root-domain */ rq = cpu_rq(cpu); spin_lock_irqsave(&rq->lock, flags); - rq->calc_load_update = calc_load_update; - rq->calc_load_active = 0; if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); From 6301cb95c119ebf324bb96ee226fa9ddffad80a7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 17 Jul 2009 14:15:47 +0200 Subject: [PATCH 3/3] sched: fix nr_uninterruptible accounting of frozen tasks really commit e3c8ca8336 (sched: do not count frozen tasks toward load) broke the nr_uninterruptible accounting on freeze/thaw. On freeze the task is excluded from accounting with a check for (task->flags & PF_FROZEN), but that flag is cleared before the task is thawed. So while we prevent that the task with state TASK_UNINTERRUPTIBLE is accounted to nr_uninterruptible on freeze we decrement nr_uninterruptible on thaw. Use a separate flag which is handled by the freezing task itself. Set it before calling the scheduler with TASK_UNINTERRUPTIBLE state and clear it after we return from frozen state. Cc: Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 3 ++- kernel/freezer.c | 7 +++++++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 16a982e389fb..3ab08e4bb6b8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -209,7 +209,7 @@ extern unsigned long long time_sync_thresh; ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) #define task_contributes_to_load(task) \ ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ - (task->flags & PF_FROZEN) == 0) + (task->flags & PF_FREEZING) == 0) #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) @@ -1680,6 +1680,7 @@ extern cputime_t task_gtime(struct task_struct *p); #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_FLUSHER 0x00001000 /* responsible for disk writeback */ #define PF_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */ +#define PF_FREEZING 0x00004000 /* freeze in progress. do not account to load */ #define PF_NOFREEZE 0x00008000 /* this thread should not be frozen */ #define PF_FROZEN 0x00010000 /* frozen for system suspend */ #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ diff --git a/kernel/freezer.c b/kernel/freezer.c index 2f4936cf7083..bd1d42b17cb2 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -44,12 +44,19 @@ void refrigerator(void) recalc_sigpending(); /* We sent fake signal, clean it up */ spin_unlock_irq(¤t->sighand->siglock); + /* prevent accounting of that task to load */ + current->flags |= PF_FREEZING; + for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!frozen(current)) break; schedule(); } + + /* Remove the accounting blocker */ + current->flags &= ~PF_FREEZING; + pr_debug("%s left refrigerator\n", current->comm); __set_current_state(save); }