From f685ceacab07d3f6c236f04803e2f2f0dbcc5afb Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Fri, 23 Oct 2009 23:09:22 +0200 Subject: sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith Cc: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- kernel/sched_fair.c | 73 ++++++++++++++++++++++++++++++++++------------------- 2 files changed, 48 insertions(+), 27 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 789001d..cae6700 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2008,7 +2008,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) /* * Buddy candidates are cache hot: */ - if (sched_feat(CACHE_HOT_BUDDY) && + if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running && (&p->se == cfs_rq_of(&p->se)->next || &p->se == cfs_rq_of(&p->se)->last)) return 1; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index c32c3e6..37087a7 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -822,6 +822,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) * re-elected due to buddy favours. */ clear_buddies(cfs_rq, curr); + return; + } + + /* + * Ensure that a task that missed wakeup preemption by a + * narrow margin doesn't have to wait for a full slice. + * This also mitigates buddy induced latencies under load. + */ + if (!sched_feat(WAKEUP_PREEMPT)) + return; + + if (delta_exec < sysctl_sched_min_granularity) + return; + + if (cfs_rq->nr_running > 1) { + struct sched_entity *se = __pick_next_entity(cfs_rq); + s64 delta = curr->vruntime - se->vruntime; + + if (delta > ideal_runtime) + resched_task(rq_of(cfs_rq)->curr); } } @@ -861,21 +881,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) { struct sched_entity *se = __pick_next_entity(cfs_rq); - struct sched_entity *buddy; + struct sched_entity *left = se; - if (cfs_rq->next) { - buddy = cfs_rq->next; - cfs_rq->next = NULL; - if (wakeup_preempt_entity(buddy, se) < 1) - return buddy; - } + if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) + se = cfs_rq->next; - if (cfs_rq->last) { - buddy = cfs_rq->last; - cfs_rq->last = NULL; - if (wakeup_preempt_entity(buddy, se) < 1) - return buddy; - } + /* + * Prefer last buddy, try to return the CPU to a preempted task. + */ + if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) + se = cfs_rq->last; + + clear_buddies(cfs_rq, se); return se; } @@ -1577,6 +1594,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ struct sched_entity *se = &curr->se, *pse = &p->se; struct cfs_rq *cfs_rq = task_cfs_rq(curr); int sync = wake_flags & WF_SYNC; + int scale = cfs_rq->nr_running >= sched_nr_latency; update_curr(cfs_rq); @@ -1591,18 +1609,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ if (unlikely(se == pse)) return; - /* - * Only set the backward buddy when the current task is still on the - * rq. This can happen when a wakeup gets interleaved with schedule on - * the ->pre_schedule() or idle_balance() point, either of which can - * drop the rq lock. - * - * Also, during early boot the idle thread is in the fair class, for - * obvious reasons its a bad idea to schedule back to the idle thread. - */ - if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle)) - set_last_buddy(se); - if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) + if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) set_next_buddy(pse); /* @@ -1648,8 +1655,22 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ BUG_ON(!pse); - if (wakeup_preempt_entity(se, pse) == 1) + if (wakeup_preempt_entity(se, pse) == 1) { resched_task(curr); + /* + * Only set the backward buddy when the current task is still + * on the rq. This can happen when a wakeup gets interleaved + * with schedule on the ->pre_schedule() or idle_balance() + * point, either of which can * drop the rq lock. + * + * Also, during early boot the idle thread is in the fair class, + * for obvious reasons its a bad idea to schedule back to it. + */ + if (unlikely(!se->on_rq || curr == rq->idle)) + return; + if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se)) + set_last_buddy(se); + } } static struct task_struct *pick_next_task_fair(struct rq *rq) -- cgit v1.1 From 49557e620339cb134127b5bfbcfecc06b77d0232 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 2 Nov 2009 20:37:20 +1030 Subject: sched: Fix boot crash by zalloc()ing most of the cpu masks I got a boot crash when forcing cpumasks offstack on 32 bit, because find_new_ilb() returned 3 on my UP system (nohz.cpu_mask wasn't zeroed). AFAICT the others need to be zeroed too: only nohz.ilb_grp_nohz_mask is initialized before use. Signed-off-by: Rusty Russell Cc: Peter Zijlstra LKML-Reference: <200911022037.21282.rusty@rustcorp.com.au> Signed-off-by: Ingo Molnar --- kernel/sched.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index cae6700..bf21adb 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -9535,13 +9535,13 @@ void __init sched_init(void) current->sched_class = &fair_sched_class; /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ - alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); + zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); #ifdef CONFIG_SMP #ifdef CONFIG_NO_HZ - alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); + zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT); #endif - alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); #endif /* SMP */ perf_event_init(); -- cgit v1.1 From b00bc0b237055b4c45816325ee14f0bd83e6f590 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 2 Nov 2009 13:01:56 +0100 Subject: uids: Prevent tear down race Ingo triggered the following warning: WARNING: at lib/debugobjects.c:255 debug_print_object+0x42/0x50() Hardware name: System Product Name ODEBUG: init active object type: timer_list Modules linked in: Pid: 2619, comm: dmesg Tainted: G W 2.6.32-rc5-tip+ #5298 Call Trace: [<81035443>] warn_slowpath_common+0x6a/0x81 [<8120e483>] ? debug_print_object+0x42/0x50 [<81035498>] warn_slowpath_fmt+0x29/0x2c [<8120e483>] debug_print_object+0x42/0x50 [<8120ec2a>] __debug_object_init+0x279/0x2d7 [<8120ecb3>] debug_object_init+0x13/0x18 [<810409d2>] init_timer_key+0x17/0x6f [<81041526>] free_uid+0x50/0x6c [<8104ed2d>] put_cred_rcu+0x61/0x72 [<81067fac>] rcu_do_batch+0x70/0x121 debugobjects warns about an enqueued timer being initialized. If CONFIG_USER_SCHED=y the user management code uses delayed work to remove the user from the hash table and tear down the sysfs objects. free_uid is called from RCU and initializes/schedules delayed work if the usage count of the user_struct is 0. The init/schedule happens outside of the uidhash_lock protected region which allows a concurrent caller of find_user() to reference the about to be destroyed user_struct w/o preventing the work from being scheduled. If the next free_uid call happens before the work timer expired then the active timer is initialized and the work scheduled again. The race was introduced in commit 5cb350ba (sched: group scheduling, sysfs tunables) and made more prominent by commit 3959214f (sched: delayed cleanup of user_struct) Move the init/schedule_delayed_work inside of the uidhash_lock protected region to prevent the race. Signed-off-by: Thomas Gleixner Acked-by: Dhaval Giani Cc: Paul E. McKenney Cc: Kay Sievers Cc: stable@kernel.org --- kernel/user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/user.c b/kernel/user.c index 2c000e7..46d0165 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -330,9 +330,9 @@ done: */ static void free_user(struct user_struct *up, unsigned long flags) { - spin_unlock_irqrestore(&uidhash_lock, flags); INIT_DELAYED_WORK(&up->work, cleanup_user_struct); schedule_delayed_work(&up->work, msecs_to_jiffies(1000)); + spin_unlock_irqrestore(&uidhash_lock, flags); } #else /* CONFIG_USER_SCHED && CONFIG_SYSFS */ -- cgit v1.1 From 83f5b01ffbbaea6f97c9a79d21e240dbfb69f2f1 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 28 Oct 2009 08:14:49 -0700 Subject: rcu: Fix long-grace-period race between forcing and initialization Very long RCU read-side critical sections (50 milliseconds or so) can cause a race between force_quiescent_state() and rcu_start_gp() as follows on kernel builds with multi-level rcu_node hierarchies: 1. CPU 0 calls force_quiescent_state(), sees that there is a grace period in progress, and acquires ->fsqlock. 2. CPU 1 detects the end of the grace period, and so cpu_quiet_msk_finish() sets rsp->completed to rsp->gpnum. This operation is carried out under the root rnp->lock, but CPU 0 has not yet acquired that lock. Note that rsp->signaled is still RCU_SAVE_DYNTICK from the last grace period. 3. CPU 1 calls rcu_start_gp(), but no one wants a new grace period, so it drops the root rnp->lock and returns. 4. CPU 0 acquires the root rnp->lock and picks up rsp->completed and rsp->signaled, then drops rnp->lock. It then enters the RCU_SAVE_DYNTICK leg of the switch statement. 5. CPU 2 invokes call_rcu(), and now needs a new grace period. It calls rcu_start_gp(), which acquires the root rnp->lock, sets rsp->signaled to RCU_GP_INIT (too bad that CPU 0 is already in the RCU_SAVE_DYNTICK leg of the switch statement!) and starts initializing the rcu_node hierarchy. If there are multiple levels to the hierarchy, it will drop the root rnp->lock and initialize the lower levels of the hierarchy. 6. CPU 0 notes that rsp->completed has not changed, which permits both CPU 2 and CPU 0 to try updating it concurrently. If CPU 0's update prevails, later calls to force_quiescent_state() can count old quiescent states against the new grace period, which can in turn result in premature ending of grace periods. Not good. This patch adds an RCU_GP_IDLE state for rsp->signaled that is set initially at boot time and any time a grace period ends. This prevents CPU 0 from getting into the workings of force_quiescent_state() in step 4. Additional locking and checks prevent the concurrent update of rsp->signaled in step 6. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1256742889199-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutree.c | 16 +++++++++++----- kernel/rcutree.h | 7 ++++--- 2 files changed, 15 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 0536125..f3077c0 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -59,7 +59,7 @@ NUM_RCU_LVL_2, \ NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \ }, \ - .signaled = RCU_SIGNAL_INIT, \ + .signaled = RCU_GP_IDLE, \ .gpnum = -300, \ .completed = -300, \ .onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \ @@ -657,14 +657,17 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) * irqs disabled. */ rcu_for_each_node_breadth_first(rsp, rnp) { - spin_lock(&rnp->lock); /* irqs already disabled. */ + spin_lock(&rnp->lock); /* irqs already disabled. */ rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; rnp->gpnum = rsp->gpnum; - spin_unlock(&rnp->lock); /* irqs already disabled. */ + spin_unlock(&rnp->lock); /* irqs remain disabled. */ } + rnp = rcu_get_root(rsp); + spin_lock(&rnp->lock); /* irqs already disabled. */ rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */ + spin_unlock(&rnp->lock); /* irqs remain disabled. */ spin_unlock_irqrestore(&rsp->onofflock, flags); } @@ -706,6 +709,7 @@ static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); rsp->completed = rsp->gpnum; + rsp->signaled = RCU_GP_IDLE; rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]); rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */ } @@ -1162,9 +1166,10 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) } spin_unlock(&rnp->lock); switch (signaled) { + case RCU_GP_IDLE: case RCU_GP_INIT: - break; /* grace period still initializing, ignore. */ + break; /* grace period idle or initializing, ignore. */ case RCU_SAVE_DYNTICK: @@ -1178,7 +1183,8 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) /* Update state, record completion counter. */ spin_lock(&rnp->lock); - if (lastcomp == rsp->completed) { + if (lastcomp == rsp->completed && + rsp->signaled == RCU_SAVE_DYNTICK) { rsp->signaled = RCU_FORCE_QS; dyntick_record_completed(rsp, lastcomp); } diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 1823c6e..1899023 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -201,9 +201,10 @@ struct rcu_data { }; /* Values for signaled field in struct rcu_state. */ -#define RCU_GP_INIT 0 /* Grace period being initialized. */ -#define RCU_SAVE_DYNTICK 1 /* Need to scan dyntick state. */ -#define RCU_FORCE_QS 2 /* Need to force quiescent state. */ +#define RCU_GP_IDLE 0 /* No grace period in progress. */ +#define RCU_GP_INIT 1 /* Grace period being initialized. */ +#define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */ +#define RCU_FORCE_QS 3 /* Need to force quiescent state. */ #ifdef CONFIG_NO_HZ #define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK #else /* #ifdef CONFIG_NO_HZ */ -- cgit v1.1 From b84ff7d6f1b7f8a43414e74d972ec4c8f3361db4 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 29 Oct 2009 11:48:30 +0100 Subject: sched: Fix kthread_bind() by moving the body of kthread_bind() to sched.c Eric Paris reported that commit f685ceacab07d3f6c236f04803e2f2f0dbcc5afb causes boot time PREEMPT_DEBUG complaints. [ 4.590699] BUG: using smp_processor_id() in preemptible [00000000] code: rmmod/1314 [ 4.593043] caller is task_hot+0x86/0xd0 Since kthread_bind() messes with scheduler internals, move the body to sched.c, and lock the runqueue. Reported-by: Eric Paris Signed-off-by: Mike Galbraith Tested-by: Eric Paris Cc: Peter Zijlstra LKML-Reference: <1256813310.7574.3.camel@marge.simson.net> [ v2: fix !SMP build and clean up ] Signed-off-by: Ingo Molnar --- kernel/kthread.c | 23 ----------------------- kernel/sched.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/kthread.c b/kernel/kthread.c index 5fe7099..ab7ae57 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -150,29 +150,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data), EXPORT_SYMBOL(kthread_create); /** - * kthread_bind - bind a just-created kthread to a cpu. - * @k: thread created by kthread_create(). - * @cpu: cpu (might not be online, must be possible) for @k to run on. - * - * Description: This function is equivalent to set_cpus_allowed(), - * except that @cpu doesn't need to be online, and the thread must be - * stopped (i.e., just returned from kthread_create()). - */ -void kthread_bind(struct task_struct *k, unsigned int cpu) -{ - /* Must have done schedule() in kthread() before we set_task_cpu */ - if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) { - WARN_ON(1); - return; - } - set_task_cpu(k, cpu); - k->cpus_allowed = cpumask_of_cpu(cpu); - k->rt.nr_cpus_allowed = 1; - k->flags |= PF_THREAD_BOUND; -} -EXPORT_SYMBOL(kthread_bind); - -/** * kthread_stop - stop a thread created by kthread_create(). * @k: thread created by kthread_create(). * diff --git a/kernel/sched.c b/kernel/sched.c index bf21adb..5cb7d63 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1996,6 +1996,38 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, p->sched_class->prio_changed(rq, p, oldprio, running); } +/** + * kthread_bind - bind a just-created kthread to a cpu. + * @k: thread created by kthread_create(). + * @cpu: cpu (might not be online, must be possible) for @k to run on. + * + * Description: This function is equivalent to set_cpus_allowed(), + * except that @cpu doesn't need to be online, and the thread must be + * stopped (i.e., just returned from kthread_create()). + * + * Function lives here instead of kthread.c because it messes with + * scheduler internals which require locking. + */ +void kthread_bind(struct task_struct *p, unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + /* Must have done schedule() in kthread() before we set_task_cpu */ + if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) { + WARN_ON(1); + return; + } + + spin_lock_irqsave(&rq->lock, flags); + set_task_cpu(p, cpu); + p->cpus_allowed = cpumask_of_cpu(cpu); + p->rt.nr_cpus_allowed = 1; + p->flags |= PF_THREAD_BOUND; + spin_unlock_irqrestore(&rq->lock, flags); +} +EXPORT_SYMBOL(kthread_bind); + #ifdef CONFIG_SMP /* * Is this task likely cache-hot: -- cgit v1.1 From f7112949f6a4cd6883d66c882d568c2197321de6 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 3 Nov 2009 19:42:45 +0800 Subject: ring-buffer: Synchronize resizing buffer with reader lock We got a sudden panic when we reduced the size of the ringbuffer. We can reproduce the panic by the following steps: echo 1 > events/sched/enable cat trace_pipe > /dev/null & while ((1)) do echo 12000 > buffer_size_kb echo 512 > buffer_size_kb done (not more than 5 seconds, panic ...) Reported-by: KOSAKI Motohiro Signed-off-by: Lai Jiangshan LKML-Reference: <4AF01735.9060409@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 3ffa502..5dd017f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1193,6 +1193,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) atomic_inc(&cpu_buffer->record_disabled); synchronize_sched(); + spin_lock_irq(&cpu_buffer->reader_lock); rb_head_page_deactivate(cpu_buffer); for (i = 0; i < nr_pages; i++) { @@ -1207,6 +1208,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) return; rb_reset_cpu(cpu_buffer); + spin_unlock_irq(&cpu_buffer->reader_lock); rb_check_pages(cpu_buffer); -- cgit v1.1 From ed146b25942b428f8e8056587b7638ce76573c2f Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 3 Nov 2009 08:55:38 +0800 Subject: ftrace: Fix unmatched locking in ftrace_regex_write() When a command is passed to the set_ftrace_filter, then the ftrace_regex_lock is still held going back to user space. # echo 'do_open : foo' > set_ftrace_filter (still holding ftrace_regex_lock when returning to user space!) Signed-off-by: Li Zefan LKML-Reference: <4AEF7F8A.3080300@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9c451a1..6dc4e5e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2222,15 +2222,15 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, ret = ftrace_process_regex(parser->buffer, parser->idx, enable); if (ret) - goto out; + goto out_unlock; trace_parser_clear(parser); } ret = read; - +out_unlock: mutex_unlock(&ftrace_regex_lock); -out: + return ret; } -- cgit v1.1 From e7e7e0c084ef862d5754701108d4a038514d6314 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Sat, 7 Nov 2009 11:16:13 +0800 Subject: genirq: try_one_irq() must be called with irq disabled Prarit reported: ================================= [ INFO: inconsistent lock state ] 2.6.32-rc5 #1 --------------------------------- inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. swapper/0 [HC0[0]:SC1[1]:HE1:SE0] takes: (&irq_desc_lock_class){?.-...}, at: [] try_one_irq+0x32/0x138 {IN-HARDIRQ-W} state was registered at: [] __lock_acquire+0x2fc/0xd5d [] lock_acquire+0xf3/0x12d [] _spin_lock+0x40/0x89 [] handle_level_irq+0x30/0x105 [] handle_irq+0x95/0xb7 [] do_IRQ+0x6a/0xe0 [] ret_from_intr+0x0/0x16 irq event stamp: 195096 hardirqs last enabled at (195096): [] _spin_unlock_irq+0x3a/0x5c hardirqs last disabled at (195095): [] _spin_lock_irq+0x29/0x95 softirqs last enabled at (195088): [] __do_softirq+0x1c1/0x1ef softirqs last disabled at (195093): [] call_softirq+0x1c/0x30 other info that might help us debug this: 1 lock held by swapper/0: #0: (kernel/irq/spurious.c:21){+.-...}, at: [] run_timer_softirq+0x1a9/0x315 stack backtrace: Pid: 0, comm: swapper Not tainted 2.6.32-rc5 #1 Call Trace: [] valid_state+0x187/0x1ae [] mark_lock+0x129/0x253 [] __lock_acquire+0x370/0xd5d [] lock_acquire+0xf3/0x12d [] _spin_lock+0x40/0x89 [] try_one_irq+0x32/0x138 [] poll_all_shared_irqs+0x41/0x6d [] poll_spurious_irqs+0x1c/0x49 [] run_timer_softirq+0x239/0x315 [] __do_softirq+0x102/0x1ef [] call_softirq+0x1c/0x30 [] do_softirq+0x59/0xca [] irq_exit+0x58/0xae [] smp_apic_timer_interrupt+0x94/0xba [] apic_timer_interrupt+0x13/0x20 The reason is that try_one_irq() is called from hardirq context with interrupts disabled and from softirq context (poll_all_shared_irqs()) with interrupts enabled. Disable interrupts before calling it from poll_all_shared_irqs(). Reported-and-tested-by: Prarit Bhargava Signed-off-by: Yong Zhang LKML-Reference: <1257563773-4620-1-git-send-email-yong.zhang0@gmail.com> Signed-off-by: Thomas Gleixner --- kernel/irq/spurious.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 114e704..bd7273e 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -121,7 +121,9 @@ static void poll_all_shared_irqs(void) if (!(status & IRQ_SPURIOUS_DISABLED)) continue; + local_irq_disable(); try_one_irq(i, desc); + local_irq_enable(); } } -- cgit v1.1 From 968c86458a5975efa7a95f832a4ec9fb21471137 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 6 Nov 2009 15:31:08 -0800 Subject: sched: Fix kernel-doc function parameter name Fix variable name in sched.c kernel-doc notation. Fixes this DocBook warning: Warning(kernel/sched.c:2008): No description found for parameter 'p' Warning(kernel/sched.c:2008): Excess function parameter 'k' description in 'kthread_bind' Signed-off-by: Randy Dunlap LKML-Reference: <4AF4B1BC.8020604@oracle.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 28dd4f4..7d7d5fc 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1994,7 +1994,7 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, /** * kthread_bind - bind a just-created kthread to a cpu. - * @k: thread created by kthread_create(). + * @p: thread created by kthread_create(). * @cpu: cpu (might not be online, must be possible) for @k to run on. * * Description: This function is equivalent to set_cpus_allowed(), -- cgit v1.1 From e9036b36eed4d3cdb33fa9cbcdd9888ae516889f Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Mon, 26 Oct 2009 22:24:14 +0300 Subject: sched: Use root_task_group_empty only with FAIR_GROUP_SCHED root_task_group_empty is used only with FAIR_GROUP_SCHED so if we use other scheduler options we get: kernel/sched.c:314: warning: 'root_task_group_empty' defined but not used So move CONFIG_FAIR_GROUP_SCHED up that it covers root_task_group_empty(). Signed-off-by: Cyrill Gorcunov Cc: Peter Zijlstra LKML-Reference: <20091026192414.GB5321@lenovo> Signed-off-by: Ingo Molnar --- kernel/sched.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 7d7d5fc..3c11ae0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -309,6 +309,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq); */ static DEFINE_SPINLOCK(task_group_lock); +#ifdef CONFIG_FAIR_GROUP_SCHED + #ifdef CONFIG_SMP static int root_task_group_empty(void) { @@ -316,7 +318,6 @@ static int root_task_group_empty(void) } #endif -#ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_USER_SCHED # define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD) #else /* !CONFIG_USER_SCHED */ -- cgit v1.1