From 7317d7b87edb41a9135e30be1ec3f7ef817c53dd Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 30 Sep 2008 20:50:27 +1000 Subject: sched: improve preempt debugging This patch helped me out with a problem I recently had.... Basically, when the kernel lock is held, then preempt_count underflow does not get detected until it is released which may be a long time (and arbitrarily, eg at different points it may be rescheduled). If the bkl is released at schedule, the resulting output is actually fairly cryptic... With any other lock that elevates preempt_count, it is illegal to schedule under it (which would get found pretty quickly). bkl allows scheduling with preempt_count elevated, which makes underflows hard to debug. Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 9889080..ec3bd1f 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4305,7 +4305,7 @@ void __kprobes sub_preempt_count(int val) /* * Underflow? */ - if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) + if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked()))) return; /* * Is the spinlock portion underflowing? -- cgit v1.1 From 74fcd524e808975dd546dac847119f1995a7c622 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 17 Nov 2008 15:39:52 +0100 Subject: account_steal_time: kill the unneeded account_group_system_time() Impact: remove unnecessary accounting call I don't actually understand account_steal_time() and I failed to find the commit which added account_group_system_time(), but this looks bogus. In any case rq->idle must be single-threaded, so it can't have ->totals. Signed-off-by: Oleg Nesterov 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 c94baf2..b388c9b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4202,7 +4202,6 @@ void account_steal_time(struct task_struct *p, cputime_t steal) if (p == rq->idle) { p->stime = cputime_add(p->stime, steal); - account_group_system_time(p, steal); if (atomic_read(&rq->nr_iowait) > 0) cpustat->iowait = cputime64_add(cpustat->iowait, tmp); else -- cgit v1.1 From ca109491f612aab5c8152207631c0444f63da97f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Nov 2008 12:43:51 +0100 Subject: hrtimer: removing all ur callback modes Impact: cleanup, move all hrtimer processing into hardirq context This is an attempt at removing some of the hrtimer complexity by reducing the number of callback modes to 1. This means that all hrtimer callback functions will be ran from HARD-irq context. I went through all the 30 odd hrtimer callback functions in the kernel and saw only one that I'm not quite sure of, which is the one in net/can/bcm.c - hence I'm CC-ing the folks responsible for that code. Furthermore, the hrtimer core now calls callbacks directly with IRQs disabled in case you try to enqueue an expired timer. If this timer is a periodic timer (which should use hrtimer_forward() to advance its time) then it might be possible to end up in an inf. recursive loop due to the fact that hrtimer_forward() doesn't round up to the next timer granularity, and therefore keeps on calling the callback - obviously this needs a fix. Aside from that, this seems to compile and actually boot on my dual core test box - although I'm sure there are some bugs in, me not hitting any makes me certain :-) Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 9b1e793..5ac5e95 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -203,7 +203,6 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); rt_b->rt_period_timer.function = sched_rt_period_timer; - rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED; } static inline int rt_bandwidth_enabled(void) @@ -1139,7 +1138,6 @@ static void init_rq_hrtick(struct rq *rq) hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); rq->hrtick_timer.function = hrtick; - rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; } #else /* CONFIG_SCHED_HRTICK */ static inline void hrtick_clear(struct rq *rq) -- cgit v1.1