From e26873bb10f722f10b1af9de05119a3d7cbc07b2 Mon Sep 17 00:00:00 2001 From: roel kluin Date: Tue, 22 Jul 2008 16:51:15 -0400 Subject: sched: test runtime rather than period in global_rt_runtime() Test runtime rather than period Signed-off-by: Roel Kluin Acked-by: Peter Zijlstra 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 0236958addc..0d1717b0022 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -834,7 +834,7 @@ static inline u64 global_rt_period(void) static inline u64 global_rt_runtime(void) { - if (sysctl_sched_rt_period < 0) + if (sysctl_sched_rt_runtime < 0) return RUNTIME_INF; return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; -- cgit v1.2.3-70-g09d2 From 5e710e37bde120bb069f691bee68e69ef4393173 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Jul 2008 13:26:57 +0200 Subject: lockdep: change scheduler annotation While thinking about David's graph walk lockdep patch it _finally_ dawned on me that there is no reason we have a lock class per cpu ... Sorry for being dense :-/ The below changes the annotation from a lock class per cpu, to a single nested lock, as the scheduler never holds more that 2 rq locks at a time anyway. If there was code requiring holding all rq locks this would not work and the original annotation would be the only option, but that not being the case, this is a much lighter one. Compiles and boots on a 2-way x86_64. Signed-off-by: Peter Zijlstra Cc: David Miller Signed-off-by: Ingo Molnar --- kernel/sched.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 0236958addc..655f1db26b1 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -600,7 +600,6 @@ struct rq { /* BKL stats */ unsigned int bkl_count; #endif - struct lock_class_key rq_lock_key; }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); @@ -2759,10 +2758,10 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2) } else { if (rq1 < rq2) { spin_lock(&rq1->lock); - spin_lock(&rq2->lock); + spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&rq2->lock); - spin_lock(&rq1->lock); + spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); } } update_rq_clock(rq1); @@ -2805,10 +2804,10 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest) if (busiest < this_rq) { spin_unlock(&this_rq->lock); spin_lock(&busiest->lock); - spin_lock(&this_rq->lock); + spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); ret = 1; } else - spin_lock(&busiest->lock); + spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); } return ret; } @@ -7998,7 +7997,6 @@ void __init sched_init(void) rq = cpu_rq(i); spin_lock_init(&rq->lock); - lockdep_set_class(&rq->lock, &rq->rq_lock_key); rq->nr_running = 0; init_cfs_rq(&rq->cfs, rq); init_rt_rq(&rq->rt, rq); -- cgit v1.2.3-70-g09d2 From 1b12bbc747560ea68bcc132c3d05699e52271da0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 11 Aug 2008 09:30:22 +0200 Subject: lockdep: re-annotate scheduler runqueues Instead of using a per-rq lock class, use the regular nesting operations. However, take extra care with double_lock_balance() as it can release the already held rq->lock (and therefore change its nesting class). So what can happen is: spin_lock(rq->lock); // this rq subclass 0 double_lock_balance(rq, other_rq); // release rq // acquire other_rq->lock subclass 0 // acquire rq->lock subclass 1 spin_unlock(other_rq->lock); leaving you with rq->lock in subclass 1 So a subsequent double_lock_balance() call can try to nest a subclass 1 lock while already holding a subclass 1 lock. Fix this by introducing double_unlock_balance() which releases the other rq's lock, but also re-sets the subclass for this rq's lock to 0. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 11 +++++++++-- kernel/sched_rt.c | 8 +++++--- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 655f1db26b1..9b2b6a85577 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2812,6 +2812,13 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest) return ret; } +static void double_unlock_balance(struct rq *this_rq, struct rq *busiest) + __releases(busiest->lock) +{ + spin_unlock(&busiest->lock); + lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); +} + /* * If dest_cpu is allowed for this process, migrate the task to it. * This is accomplished by forcing the cpu_allowed mask to only @@ -3636,7 +3643,7 @@ redo: ld_moved = move_tasks(this_rq, this_cpu, busiest, imbalance, sd, CPU_NEWLY_IDLE, &all_pinned); - spin_unlock(&busiest->lock); + double_unlock_balance(this_rq, busiest); if (unlikely(all_pinned)) { cpu_clear(cpu_of(busiest), *cpus); @@ -3751,7 +3758,7 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) else schedstat_inc(sd, alb_failed); } - spin_unlock(&target_rq->lock); + double_unlock_balance(busiest_rq, target_rq); } #ifdef CONFIG_NO_HZ diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 908c04f9dad..6163e4cf885 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -861,6 +861,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) #define RT_MAX_TRIES 3 static int double_lock_balance(struct rq *this_rq, struct rq *busiest); +static void double_unlock_balance(struct rq *this_rq, struct rq *busiest); + static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep); static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) @@ -1022,7 +1024,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) break; /* try again */ - spin_unlock(&lowest_rq->lock); + double_unlock_balance(rq, lowest_rq); lowest_rq = NULL; } @@ -1091,7 +1093,7 @@ static int push_rt_task(struct rq *rq) resched_task(lowest_rq->curr); - spin_unlock(&lowest_rq->lock); + double_unlock_balance(rq, lowest_rq); ret = 1; out: @@ -1197,7 +1199,7 @@ static int pull_rt_task(struct rq *this_rq) } skip: - spin_unlock(&src_rq->lock); + double_unlock_balance(this_rq, src_rq); } return ret; -- cgit v1.2.3-70-g09d2 From 09f2724a786f76475ef2985cf84f5359c553aade Mon Sep 17 00:00:00 2001 From: "Zhang, Yanmin" Date: Wed, 14 Aug 2030 15:56:40 +0800 Subject: sched: fix the race between walk_tg_tree and sched_create_group With 2.6.27-rc3, I hit a kernel panic when running volanoMark on my new x86_64 machine. I also hit it with other 2.6.27-rc kernels. See below log. Basically, function walk_tg_tree and sched_create_group have a race between accessing and initiating tg->children. Below patch fixes it by moving tg->children initiation to the front of linking tg->siblings to parent->children. {----------------panic log------------} BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 IP: [] walk_tg_tree+0x45/0x7f PGD 1be1c4067 PUD 1bdd8d067 PMD 0 Oops: 0000 [1] SMP CPU 11 Modules linked in: igb Pid: 22979, comm: java Not tainted 2.6.27-rc3 #1 RIP: 0010:[] [] walk_tg_tree+0x45/0x7f RSP: 0018:ffff8801bfbbbd18 EFLAGS: 00010083 RAX: 0000000000000000 RBX: ffff8800be0dce40 RCX: ffffffffffffffc0 RDX: ffff880102c43740 RSI: 0000000000000000 RDI: ffff8800be0dce40 RBP: ffff8801bfbbbd48 R08: ffff8800ba437bc8 R09: 0000000000001f40 R10: ffff8801be812100 R11: ffffffff805fdf44 R12: ffff880102c43740 R13: 0000000000000000 R14: ffffffff8022cf0f R15: ffffffff8022749f FS: 00000000568ac950(0063) GS:ffff8801bfa26d00(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000000 CR3: 00000001bd848000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process java (pid: 22979, threadinfo ffff8801b145a000, task ffff8801bf18e450) Stack: 0000000000000001 ffff8800ba5c8d60 0000000000000001 0000000000000001 ffff8800bad1ccb8 0000000000000000 ffff8801bfbbbd98 ffffffff8022ed37 0000000000000001 0000000000000286 ffff8801bd5ee180 ffff8800ba437bc8 Call Trace: [] try_to_wake_up+0x71/0x24c [] autoremove_wake_function+0x9/0x2e [] ? __wake_up_common+0x46/0x76 [] __wake_up+0x38/0x4f [] tcp_v4_rcv+0x380/0x62e Signed-off-by: Zhang Yanmin Acked-by: Peter Zijlstra 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 d601fb0406c..8bf8a5528bc 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8462,8 +8462,8 @@ struct task_group *sched_create_group(struct task_group *parent) WARN_ON(!parent); /* root should already exist */ tg->parent = parent; - list_add_rcu(&tg->siblings, &parent->children); INIT_LIST_HEAD(&tg->children); + list_add_rcu(&tg->siblings, &parent->children); spin_unlock_irqrestore(&task_group_lock, flags); return tg; -- cgit v1.2.3-70-g09d2 From be4de35263f59ca1f4740edfffbfb02cc3f2189e Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 15 Aug 2008 00:40:44 -0700 Subject: completions: uninline try_wait_for_completion and completion_done m68k fails to build with these functions inlined in completion.h. Move them out of line into sched.c and export them to avoid this problem. Signed-off-by: Dave Chinner Cc: Geert Uytterhoeven Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/completion.h | 46 ++-------------------------------------------- kernel/sched.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+), 44 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/completion.h b/include/linux/completion.h index 57faa60de9b..02ef8835999 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -49,6 +49,8 @@ extern unsigned long wait_for_completion_timeout(struct completion *x, unsigned long timeout); extern unsigned long wait_for_completion_interruptible_timeout( struct completion *x, unsigned long timeout); +extern bool try_wait_for_completion(struct completion *x); +extern bool completion_done(struct completion *x); extern void complete(struct completion *); extern void complete_all(struct completion *); @@ -56,48 +58,4 @@ extern void complete_all(struct completion *); #define INIT_COMPLETION(x) ((x).done = 0) -/** - * try_wait_for_completion - try to decrement a completion without blocking - * @x: completion structure - * - * Returns: 0 if a decrement cannot be done without blocking - * 1 if a decrement succeeded. - * - * If a completion is being used as a counting completion, - * attempt to decrement the counter without blocking. This - * enables us to avoid waiting if the resource the completion - * is protecting is not available. - */ -static inline bool try_wait_for_completion(struct completion *x) -{ - int ret = 1; - - spin_lock_irq(&x->wait.lock); - if (!x->done) - ret = 0; - else - x->done--; - spin_unlock_irq(&x->wait.lock); - return ret; -} - -/** - * completion_done - Test to see if a completion has any waiters - * @x: completion structure - * - * Returns: 0 if there are waiters (wait_for_completion() in progress) - * 1 if there are no waiters. - * - */ -static inline bool completion_done(struct completion *x) -{ - int ret = 1; - - spin_lock_irq(&x->wait.lock); - if (!x->done) - ret = 0; - spin_unlock_irq(&x->wait.lock); - return ret; -} - #endif diff --git a/kernel/sched.c b/kernel/sched.c index d601fb0406c..95e6ad3c231 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4669,6 +4669,52 @@ int __sched wait_for_completion_killable(struct completion *x) } EXPORT_SYMBOL(wait_for_completion_killable); +/** + * try_wait_for_completion - try to decrement a completion without blocking + * @x: completion structure + * + * Returns: 0 if a decrement cannot be done without blocking + * 1 if a decrement succeeded. + * + * If a completion is being used as a counting completion, + * attempt to decrement the counter without blocking. This + * enables us to avoid waiting if the resource the completion + * is protecting is not available. + */ +bool try_wait_for_completion(struct completion *x) +{ + int ret = 1; + + spin_lock_irq(&x->wait.lock); + if (!x->done) + ret = 0; + else + x->done--; + spin_unlock_irq(&x->wait.lock); + return ret; +} +EXPORT_SYMBOL(try_wait_for_completion); + +/** + * completion_done - Test to see if a completion has any waiters + * @x: completion structure + * + * Returns: 0 if there are waiters (wait_for_completion() in progress) + * 1 if there are no waiters. + * + */ +bool completion_done(struct completion *x) +{ + int ret = 1; + + spin_lock_irq(&x->wait.lock); + if (!x->done) + ret = 0; + spin_unlock_irq(&x->wait.lock); + return ret; +} +EXPORT_SYMBOL(completion_done); + static long __sched sleep_on_common(wait_queue_head_t *q, int state, long timeout) { -- cgit v1.2.3-70-g09d2 From 55cd53404c5cc5fd94708232e3b4aa4a9388917b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 4 Aug 2008 08:54:26 +0200 Subject: sched: scale sysctl_sched_shares_ratelimit with nr_cpus David reported that his Niagra spend a little too much time in tg_shares_up(), which considering he has a large cpu count makes sense. So scale the ratelimit value with the number of cpus like we do for other controls as well. Reported-by: David Miller Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 8bf8a5528bc..040807196b3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -808,9 +808,9 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32; /* * ratelimit for updating the group shares. - * default: 0.5ms + * default: 0.25ms */ -const_debug unsigned int sysctl_sched_shares_ratelimit = 500000; +unsigned int sysctl_sched_shares_ratelimit = 250000; /* * period over which we measure -rt task cpu usage in us. @@ -5740,6 +5740,8 @@ static inline void sched_init_granularity(void) sysctl_sched_latency = limit; sysctl_sched_wakeup_granularity *= factor; + + sysctl_sched_shares_ratelimit *= factor; } #ifdef CONFIG_SMP -- cgit v1.2.3-70-g09d2