From 0b148fa04852859972abbf848177b92daeef138a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 19 Aug 2008 12:33:04 +0200 Subject: sched: rt-bandwidth group disable fixes More extensive disable of bandwidth control. It allows sysctl_sched_rt_runtime to disable full group bandwidth control. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 9a1ddb84e26..c1bee5fb815 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -204,11 +204,13 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; } +static inline int rt_bandwidth_enabled(void); + static void start_rt_bandwidth(struct rt_bandwidth *rt_b) { ktime_t now; - if (rt_b->rt_runtime == RUNTIME_INF) + if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF) return; if (hrtimer_active(&rt_b->rt_period_timer)) @@ -839,6 +841,11 @@ static inline u64 global_rt_runtime(void) return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; } +static inline int rt_bandwidth_enabled(void) +{ + return sysctl_sched_rt_runtime >= 0; +} + #ifndef prepare_arch_switch # define prepare_arch_switch(next) do { } while (0) #endif -- cgit v1.2.3-70-g09d2 From eb755805f21bd5ded84026e167b7a90887ac42e5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 19 Aug 2008 12:33:05 +0200 Subject: sched: extract walk_tg_tree() Extract walk_tg_tree() and make it a little more generic so we can use it in the schedulablity test. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 79 ++++++++++++++++++++++++++++++++++------------------------ 1 file changed, 46 insertions(+), 33 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index c1bee5fb815..8c019a19d05 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1387,38 +1387,24 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load) update_load_sub(&rq->load, load); } -#ifdef CONFIG_SMP -static unsigned long source_load(int cpu, int type); -static unsigned long target_load(int cpu, int type); -static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); - -static unsigned long cpu_avg_load_per_task(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - - if (rq->nr_running) - rq->avg_load_per_task = rq->load.weight / rq->nr_running; - - return rq->avg_load_per_task; -} - -#ifdef CONFIG_FAIR_GROUP_SCHED - -typedef void (*tg_visitor)(struct task_group *, int, struct sched_domain *); +#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) +typedef int (*tg_visitor)(struct task_group *, void *); /* * Iterate the full tree, calling @down when first entering a node and @up when * leaving it for the final time. */ -static void -walk_tg_tree(tg_visitor down, tg_visitor up, int cpu, struct sched_domain *sd) +static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) { struct task_group *parent, *child; + int ret; rcu_read_lock(); parent = &root_task_group; down: - (*down)(parent, cpu, sd); + ret = (*down)(parent, data); + if (ret) + goto out_unlock; list_for_each_entry_rcu(child, &parent->children, siblings) { parent = child; goto down; @@ -1426,14 +1412,42 @@ down: up: continue; } - (*up)(parent, cpu, sd); + ret = (*up)(parent, data); + if (ret) + goto out_unlock; child = parent; parent = parent->parent; if (parent) goto up; +out_unlock: rcu_read_unlock(); + + return ret; +} + +static int tg_nop(struct task_group *tg, void *data) +{ + return 0; } +#endif + +#ifdef CONFIG_SMP +static unsigned long source_load(int cpu, int type); +static unsigned long target_load(int cpu, int type); +static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); + +static unsigned long cpu_avg_load_per_task(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->nr_running) + rq->avg_load_per_task = rq->load.weight / rq->nr_running; + + return rq->avg_load_per_task; +} + +#ifdef CONFIG_FAIR_GROUP_SCHED static void __set_se_shares(struct sched_entity *se, unsigned long shares); @@ -1493,11 +1507,11 @@ __update_group_shares_cpu(struct task_group *tg, int cpu, * This needs to be done in a bottom-up fashion because the rq weight of a * parent group depends on the shares of its child groups. */ -static void -tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd) +static int tg_shares_up(struct task_group *tg, void *data) { unsigned long rq_weight = 0; unsigned long shares = 0; + struct sched_domain *sd = data; int i; for_each_cpu_mask(i, sd->span) { @@ -1522,6 +1536,8 @@ tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd) __update_group_shares_cpu(tg, i, shares, rq_weight); spin_unlock_irqrestore(&rq->lock, flags); } + + return 0; } /* @@ -1529,10 +1545,10 @@ tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd) * This needs to be done in a top-down fashion because the load of a child * group is a fraction of its parents load. */ -static void -tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd) +static int tg_load_down(struct task_group *tg, void *data) { unsigned long load; + long cpu = (long)data; if (!tg->parent) { load = cpu_rq(cpu)->load.weight; @@ -1543,11 +1559,8 @@ tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd) } tg->cfs_rq[cpu]->h_load = load; -} -static void -tg_nop(struct task_group *tg, int cpu, struct sched_domain *sd) -{ + return 0; } static void update_shares(struct sched_domain *sd) @@ -1557,7 +1570,7 @@ static void update_shares(struct sched_domain *sd) if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { sd->last_update = now; - walk_tg_tree(tg_nop, tg_shares_up, 0, sd); + walk_tg_tree(tg_nop, tg_shares_up, sd); } } @@ -1568,9 +1581,9 @@ static void update_shares_locked(struct rq *rq, struct sched_domain *sd) spin_lock(&rq->lock); } -static void update_h_load(int cpu) +static void update_h_load(long cpu) { - walk_tg_tree(tg_load_down, tg_nop, cpu, NULL); + walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); } #else -- cgit v1.2.3-70-g09d2 From 9a7e0b180da21885988d47558671cf580279f9d6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 19 Aug 2008 12:33:06 +0200 Subject: sched: rt-bandwidth fixes The last patch allows sysctl_sched_rt_runtime to disable bandwidth accounting for the group scheduler - however it doesn't deal with sched_setscheduler(), which will keep tasks out of groups that have no assigned runtime. If we relax this, we get into the situation where RT tasks can get into a group when we disable bandwidth control, and then starve them by enabling it again. Rework the schedulability code to check for this condition and fail to turn on bandwidth control with -EBUSY when this situation is found. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 125 +++++++++++++++++++++++++++++---------------------------- 1 file changed, 63 insertions(+), 62 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 8c019a19d05..e41bdae2778 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -300,9 +300,9 @@ static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp; static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity); static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp; #endif /* CONFIG_RT_GROUP_SCHED */ -#else /* !CONFIG_FAIR_GROUP_SCHED */ +#else /* !CONFIG_USER_SCHED */ #define root_task_group init_task_group -#endif /* CONFIG_FAIR_GROUP_SCHED */ +#endif /* CONFIG_USER_SCHED */ /* task_group_lock serializes add/remove of task groups and also changes to * a task group's cpu shares. @@ -1387,7 +1387,7 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load) update_load_sub(&rq->load, load); } -#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) +#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(SCHED_RT_GROUP_SCHED) typedef int (*tg_visitor)(struct task_group *, void *); /* @@ -5082,7 +5082,8 @@ recheck: * Do not allow realtime tasks into groups that have no runtime * assigned. */ - if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0) + if (rt_bandwidth_enabled() && rt_policy(policy) && + task_group(p)->rt_bandwidth.rt_runtime == 0) return -EPERM; #endif @@ -8707,73 +8708,77 @@ static DEFINE_MUTEX(rt_constraints_mutex); static unsigned long to_ratio(u64 period, u64 runtime) { if (runtime == RUNTIME_INF) - return 1ULL << 16; + return 1ULL << 20; - return div64_u64(runtime << 16, period); + return div64_u64(runtime << 20, period); } -#ifdef CONFIG_CGROUP_SCHED -static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) +/* Must be called with tasklist_lock held */ +static inline int tg_has_rt_tasks(struct task_group *tg) { - struct task_group *tgi, *parent = tg->parent; - unsigned long total = 0; + struct task_struct *g, *p; - if (!parent) { - if (global_rt_period() < period) - return 0; + do_each_thread(g, p) { + if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg) + return 1; + } while_each_thread(g, p); - return to_ratio(period, runtime) < - to_ratio(global_rt_period(), global_rt_runtime()); - } + return 0; +} - if (ktime_to_ns(parent->rt_bandwidth.rt_period) < period) - return 0; +struct rt_schedulable_data { + struct task_group *tg; + u64 rt_period; + u64 rt_runtime; +}; - rcu_read_lock(); - list_for_each_entry_rcu(tgi, &parent->children, siblings) { - if (tgi == tg) - continue; +static int tg_schedulable(struct task_group *tg, void *data) +{ + struct rt_schedulable_data *d = data; + struct task_group *child; + unsigned long total, sum = 0; + u64 period, runtime; + + period = ktime_to_ns(tg->rt_bandwidth.rt_period); + runtime = tg->rt_bandwidth.rt_runtime; - total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period), - tgi->rt_bandwidth.rt_runtime); + if (tg == d->tg) { + period = d->rt_period; + runtime = d->rt_runtime; } - rcu_read_unlock(); - return total + to_ratio(period, runtime) <= - to_ratio(ktime_to_ns(parent->rt_bandwidth.rt_period), - parent->rt_bandwidth.rt_runtime); -} -#elif defined CONFIG_USER_SCHED -static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) -{ - struct task_group *tgi; - unsigned long total = 0; - unsigned long global_ratio = - to_ratio(global_rt_period(), global_rt_runtime()); + if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) + return -EBUSY; - rcu_read_lock(); - list_for_each_entry_rcu(tgi, &task_groups, list) { - if (tgi == tg) - continue; + total = to_ratio(period, runtime); - total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period), - tgi->rt_bandwidth.rt_runtime); + list_for_each_entry_rcu(child, &tg->children, siblings) { + period = ktime_to_ns(child->rt_bandwidth.rt_period); + runtime = child->rt_bandwidth.rt_runtime; + + if (child == d->tg) { + period = d->rt_period; + runtime = d->rt_runtime; + } + + sum += to_ratio(period, runtime); } - rcu_read_unlock(); - return total + to_ratio(period, runtime) < global_ratio; + if (sum > total) + return -EINVAL; + + return 0; } -#endif -/* Must be called with tasklist_lock held */ -static inline int tg_has_rt_tasks(struct task_group *tg) +static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) { - struct task_struct *g, *p; - do_each_thread(g, p) { - if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg) - return 1; - } while_each_thread(g, p); - return 0; + struct rt_schedulable_data data = { + .tg = tg, + .rt_period = period, + .rt_runtime = runtime, + }; + + return walk_tg_tree(tg_schedulable, tg_nop, &data); } static int tg_set_bandwidth(struct task_group *tg, @@ -8783,14 +8788,9 @@ static int tg_set_bandwidth(struct task_group *tg, mutex_lock(&rt_constraints_mutex); read_lock(&tasklist_lock); - if (rt_runtime == 0 && tg_has_rt_tasks(tg)) { - err = -EBUSY; + err = __rt_schedulable(tg, rt_period, rt_runtime); + if (err) goto unlock; - } - if (!__rt_schedulable(tg, rt_period, rt_runtime)) { - err = -EINVAL; - goto unlock; - } spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); @@ -8867,8 +8867,9 @@ static int sched_rt_global_constraints(void) rt_runtime = tg->rt_bandwidth.rt_runtime; mutex_lock(&rt_constraints_mutex); - if (!__rt_schedulable(tg, rt_period, rt_runtime)) - ret = -EINVAL; + read_lock(&tasklist_lock); + ret = __rt_schedulable(tg, rt_period, rt_runtime); + read_unlock(&tasklist_lock); mutex_unlock(&rt_constraints_mutex); return ret; -- cgit v1.2.3-70-g09d2 From 94d3d8247de22c5b0624aa00616ceca459498e55 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 20 Aug 2008 16:54:41 -0700 Subject: sched: do_wait_for_common: use signal_pending_state() Change do_wait_for_common() to use signal_pending_state() instead of open coding. Signed-off-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- kernel/sched.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index d601fb0406c..da7c5d23cc0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4599,10 +4599,7 @@ do_wait_for_common(struct completion *x, long timeout, int state) wait.flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue_tail(&x->wait, &wait); do { - if ((state == TASK_INTERRUPTIBLE && - signal_pending(current)) || - (state == TASK_KILLABLE && - fatal_signal_pending(current))) { + if (signal_pending_state(state, current)) { timeout = -ERESTARTSYS; break; } -- cgit v1.2.3-70-g09d2 From f31e11d87a5d7601636710195891ba462ad99f11 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 20 Aug 2008 16:54:44 -0700 Subject: wait_task_inactive(): don't consider task->nivcsw If wait_task_inactive() returns success the task was deactivated. In that case schedule() always increments ->nvcsw which alone can be used as a "generation counter". If the next call returns the same number, we can be sure that the task was unscheduled. Otherwise, because we know that .on_rq == 0 again, ->nvcsw should have been changed in between. Q: perhaps it is better to do "ncsw = (p->nvcsw << 1) | 1" ? This decreases the possibility of "was it unscheduled" false positive when ->nvcsw == 0. Signed-off-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- kernel/sched.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index da7c5d23cc0..908670aa215 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1921,11 +1921,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) running = task_running(rq, p); on_rq = p->se.on_rq; ncsw = 0; - if (!match_state || p->state == match_state) { - ncsw = p->nivcsw + p->nvcsw; - if (unlikely(!ncsw)) - ncsw = 1; - } + if (!match_state || p->state == match_state) + ncsw = p->nvcsw ?: 1; task_rq_unlock(rq, &flags); /* -- cgit v1.2.3-70-g09d2 From 93dcf55f828b035fc93fc19eb03c1390e1e6d570 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 20 Aug 2008 16:54:44 -0700 Subject: wait_task_inactive: "improve" the returned value for ->nvcsw == 0 wait_task_inactive() returns 1 when p->nvcsw == 0 || p->nvcsw == 1. This means that two subsequent calls can return the same number while the task was scheduled in between. Change the code to return "nvcsw | LONG_MIN" instead of "nvcsw ?: 1", now the overlap always needs LONG_MAX schedules. Signed-off-by: Oleg Nesterov Signed-off-by: Andrew Morton 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 908670aa215..6a43c8942b0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1922,7 +1922,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) on_rq = p->se.on_rq; ncsw = 0; if (!match_state || p->state == match_state) - ncsw = p->nvcsw ?: 1; + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ task_rq_unlock(rq, &flags); /* -- cgit v1.2.3-70-g09d2 From 65eb3dc609dec17deea48dcd4de2e549d29a9824 Mon Sep 17 00:00:00 2001 From: Kevin Diggs Date: Tue, 26 Aug 2008 10:26:54 +0200 Subject: sched: add kernel doc for the completion, fix kernel-doc-nano-HOWTO.txt This patch adds kernel doc for the completion feature. An error in the split-man.pl PERL snippet in kernel-doc-nano-HOWTO.txt is also fixed. Signed-off-by: Kevin Diggs Signed-off-by: Ingo Molnar --- Documentation/kernel-doc-nano-HOWTO.txt | 4 +-- include/linux/completion.h | 41 ++++++++++++++++++++++++ kernel/sched.c | 56 +++++++++++++++++++++++++++++++++ 3 files changed, 99 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt index 0bd32748a46..c6841eee959 100644 --- a/Documentation/kernel-doc-nano-HOWTO.txt +++ b/Documentation/kernel-doc-nano-HOWTO.txt @@ -168,10 +168,10 @@ if ($#ARGV < 0) { mkdir $ARGV[0],0777; $state = 0; while () { - if (/^\.TH \"[^\"]*\" 4 \"([^\"]*)\"/) { + if (/^\.TH \"[^\"]*\" 9 \"([^\"]*)\"/) { if ($state == 1) { close OUT } $state = 1; - $fn = "$ARGV[0]/$1.4"; + $fn = "$ARGV[0]/$1.9"; print STDERR "Creating $fn\n"; open OUT, ">$fn" or die "can't open $fn: $!\n"; print OUT $_; diff --git a/include/linux/completion.h b/include/linux/completion.h index 02ef8835999..4a6b604ef7e 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -10,6 +10,18 @@ #include +/** + * struct completion - structure used to maintain state for a "completion" + * + * This is the opaque structure used to maintain the state for a "completion". + * Completions currently use a FIFO to queue threads that have to wait for + * the "completion" event. + * + * See also: complete(), wait_for_completion() (and friends _timeout, + * _interruptible, _interruptible_timeout, and _killable), init_completion(), + * and macros DECLARE_COMPLETION(), DECLARE_COMPLETION_ONSTACK(), and + * INIT_COMPLETION(). + */ struct completion { unsigned int done; wait_queue_head_t wait; @@ -21,6 +33,14 @@ struct completion { #define COMPLETION_INITIALIZER_ONSTACK(work) \ ({ init_completion(&work); work; }) +/** + * DECLARE_COMPLETION: - declare and initialize a completion structure + * @work: identifier for the completion structure + * + * This macro declares and initializes a completion structure. Generally used + * for static declarations. You should use the _ONSTACK variant for automatic + * variables. + */ #define DECLARE_COMPLETION(work) \ struct completion work = COMPLETION_INITIALIZER(work) @@ -29,6 +49,13 @@ struct completion { * completions - so we use the _ONSTACK() variant for those that * are on the kernel stack: */ +/** + * DECLARE_COMPLETION_ONSTACK: - declare and initialize a completion structure + * @work: identifier for the completion structure + * + * This macro declares and initializes a completion structure on the kernel + * stack. + */ #ifdef CONFIG_LOCKDEP # define DECLARE_COMPLETION_ONSTACK(work) \ struct completion work = COMPLETION_INITIALIZER_ONSTACK(work) @@ -36,6 +63,13 @@ struct completion { # define DECLARE_COMPLETION_ONSTACK(work) DECLARE_COMPLETION(work) #endif +/** + * init_completion: - Initialize a dynamically allocated completion + * @x: completion structure that is to be initialized + * + * This inline function will initialize a dynamically created completion + * structure. + */ static inline void init_completion(struct completion *x) { x->done = 0; @@ -55,6 +89,13 @@ extern bool completion_done(struct completion *x); extern void complete(struct completion *); extern void complete_all(struct completion *); +/** + * INIT_COMPLETION: - reinitialize a completion structure + * @x: completion structure to be reinitialized + * + * This macro should be used to reinitialize a completion structure so it can + * be reused. This is especially important after complete_all() is used. + */ #define INIT_COMPLETION(x) ((x).done = 0) diff --git a/kernel/sched.c b/kernel/sched.c index 29e2ec0bd83..93f5ea08be9 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4565,6 +4565,15 @@ __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ +/** + * complete: - signals a single thread waiting on this completion + * @x: holds the state of this particular completion + * + * This will wake up a single thread waiting on this completion. Threads will be + * awakened in the same order in which they were queued. + * + * See also complete_all(), wait_for_completion() and related routines. + */ void complete(struct completion *x) { unsigned long flags; @@ -4576,6 +4585,12 @@ void complete(struct completion *x) } EXPORT_SYMBOL(complete); +/** + * complete_all: - signals all threads waiting on this completion + * @x: holds the state of this particular completion + * + * This will wake up all threads waiting on this particular completion event. + */ void complete_all(struct completion *x) { unsigned long flags; @@ -4624,12 +4639,31 @@ wait_for_common(struct completion *x, long timeout, int state) return timeout; } +/** + * wait_for_completion: - waits for completion of a task + * @x: holds the state of this particular completion + * + * This waits to be signaled for completion of a specific task. It is NOT + * interruptible and there is no timeout. + * + * See also similar routines (i.e. wait_for_completion_timeout()) with timeout + * and interrupt capability. Also see complete(). + */ void __sched wait_for_completion(struct completion *x) { wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(wait_for_completion); +/** + * wait_for_completion_timeout: - waits for completion of a task (w/timeout) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be signaled or for a + * specified timeout to expire. The timeout is in jiffies. It is not + * interruptible. + */ unsigned long __sched wait_for_completion_timeout(struct completion *x, unsigned long timeout) { @@ -4637,6 +4671,13 @@ wait_for_completion_timeout(struct completion *x, unsigned long timeout) } EXPORT_SYMBOL(wait_for_completion_timeout); +/** + * wait_for_completion_interruptible: - waits for completion of a task (w/intr) + * @x: holds the state of this particular completion + * + * This waits for completion of a specific task to be signaled. It is + * interruptible. + */ int __sched wait_for_completion_interruptible(struct completion *x) { long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); @@ -4646,6 +4687,14 @@ int __sched wait_for_completion_interruptible(struct completion *x) } EXPORT_SYMBOL(wait_for_completion_interruptible); +/** + * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr)) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be signaled or for a + * specified timeout to expire. It is interruptible. The timeout is in jiffies. + */ unsigned long __sched wait_for_completion_interruptible_timeout(struct completion *x, unsigned long timeout) @@ -4654,6 +4703,13 @@ wait_for_completion_interruptible_timeout(struct completion *x, } EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); +/** + * wait_for_completion_killable: - waits for completion of a task (killable) + * @x: holds the state of this particular completion + * + * This waits to be signaled for completion of a specific task. It can be + * interrupted by a kill signal. + */ int __sched wait_for_completion_killable(struct completion *x) { long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE); -- cgit v1.2.3-70-g09d2 From 29cbef4869bf288256ab76c7dc674cb132b35de2 Mon Sep 17 00:00:00 2001 From: Joe Korty Date: Wed, 27 Aug 2008 11:21:39 -0400 Subject: make might_sleep() display the oopsing process Expand might_sleep's printk to indicate the oopsing process. Signed-off-by: Joe Korty Signed-off-by: Ingo Molnar --- kernel/sched.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 93f5ea08be9..6e283dc7679 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8233,8 +8233,8 @@ void __might_sleep(char *file, int line) prev_jiffy = jiffies; printk(KERN_ERR "BUG: sleeping function called from invalid" " context at %s:%d\n", file, line); - printk("in_atomic():%d, irqs_disabled():%d\n", - in_atomic(), irqs_disabled()); + printk("in_atomic():%d, irqs_disabled():%d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), current->pid, current->comm); debug_show_held_locks(current); if (irqs_disabled()) print_irqtrace_events(current); -- cgit v1.2.3-70-g09d2 From aef745fca016aea45adae5c98e8698904dd8ad51 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 28 Aug 2008 11:34:43 +0200 Subject: sched: clean up __might_sleep() add KERN_ to the printout and clean up the flow a bit. Signed-off-by: Ingo Molnar --- kernel/sched.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 6e283dc7679..b112caaa400 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8226,20 +8226,25 @@ void __might_sleep(char *file, int line) #ifdef in_atomic static unsigned long prev_jiffy; /* ratelimiting */ - if ((in_atomic() || irqs_disabled()) && - system_state == SYSTEM_RUNNING && !oops_in_progress) { - if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) - return; - prev_jiffy = jiffies; - printk(KERN_ERR "BUG: sleeping function called from invalid" - " context at %s:%d\n", file, line); - printk("in_atomic():%d, irqs_disabled():%d, pid: %d, name: %s\n", - in_atomic(), irqs_disabled(), current->pid, current->comm); - debug_show_held_locks(current); - if (irqs_disabled()) - print_irqtrace_events(current); - dump_stack(); - } + if ((!in_atomic() && !irqs_disabled()) || + system_state != SYSTEM_RUNNING || oops_in_progress) + return; + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + + printk(KERN_ERR + "BUG: sleeping function called from invalid context at %s:%d\n", + file, line); + printk(KERN_ERR + "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), + current->pid, current->comm); + + debug_show_held_locks(current); + if (irqs_disabled()) + print_irqtrace_events(current); + dump_stack(); #endif } EXPORT_SYMBOL(__might_sleep); -- cgit v1.2.3-70-g09d2 From 7940ca3605b77f20cc6e9852e4ca6f2d725b5653 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 19 Aug 2008 13:40:47 +0200 Subject: sched: extract walk_tg_tree(), fix fix: kernel/sched.c: In function '__rt_schedulable': kernel/sched.c:8771: error: implicit declaration of function 'walk_tg_tree' kernel/sched.c:8771: error: 'tg_nop' undeclared (first use in this function) kernel/sched.c:8771: error: (Each undeclared identifier is reported only once kernel/sched.c:8771: error: for each function it appears in.) 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 e41bdae2778..703f56d5db5 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1387,7 +1387,7 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load) update_load_sub(&rq->load, load); } -#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(SCHED_RT_GROUP_SCHED) +#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED) typedef int (*tg_visitor)(struct task_group *, void *); /* -- cgit v1.2.3-70-g09d2 From c8bfff6dd4d41834f4952cbc49e28e31906a6188 Mon Sep 17 00:00:00 2001 From: Krzysztof Helt Date: Fri, 5 Sep 2008 23:46:19 +0200 Subject: sched: compilation fix with gcc 3.4.6 I found that 2.6.27-rc5-mm1 does not compile with gcc 3.4.6. The error is: CC kernel/sched.o kernel/sched.c: In function `start_rt_bandwidth': kernel/sched.c:208: sorry, unimplemented: inlining failed in call to 'rt_bandwidth_enabled': function body not available kernel/sched.c:214: sorry, unimplemented: called from here make[1]: *** [kernel/sched.o] Error 1 make: *** [kernel] Error 2 It seems that the gcc 3.4.6 requires full inline definition before first usage. The patch below fixes the compilation problem. Signed-off-by: Krzysztof Helt (if needed> 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 703f56d5db5..4de2bfb28c5 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -204,7 +204,10 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; } -static inline int rt_bandwidth_enabled(void); +static inline int rt_bandwidth_enabled(void) +{ + return sysctl_sched_rt_runtime >= 0; +} static void start_rt_bandwidth(struct rt_bandwidth *rt_b) { @@ -841,11 +844,6 @@ static inline u64 global_rt_runtime(void) return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; } -static inline int rt_bandwidth_enabled(void) -{ - return sysctl_sched_rt_runtime >= 0; -} - #ifndef prepare_arch_switch # define prepare_arch_switch(next) do { } while (0) #endif -- cgit v1.2.3-70-g09d2 From f06febc96ba8e0af80bcc3eaec0a109e88275fac Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang Overview This patch reworks the handling of POSIX CPU timers, including the ITIMER_PROF, ITIMER_VIRT timers and rlimit handling. It was put together with the help of Roland McGrath, the owner and original writer of this code. The problem we ran into, and the reason for this rework, has to do with using a profiling timer in a process with a large number of threads. It appears that the performance of the old implementation of run_posix_cpu_timers() was at least O(n*3) (where "n" is the number of threads in a process) or worse. Everything is fine with an increasing number of threads until the time taken for that routine to run becomes the same as or greater than the tick time, at which point things degrade rather quickly. This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF." Code Changes This rework corrects the implementation of run_posix_cpu_timers() to make it run in constant time for a particular machine. (Performance may vary between one machine and another depending upon whether the kernel is built as single- or multiprocessor and, in the latter case, depending upon the number of running processors.) To do this, at each tick we now update fields in signal_struct as well as task_struct. The run_posix_cpu_timers() function uses those fields to make its decisions. We define a new structure, "task_cputime," to contain user, system and scheduler times and use these in appropriate places: struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; }; This is included in the structure "thread_group_cputime," which is a new substructure of signal_struct and which varies for uniprocessor versus multiprocessor kernels. For uniprocessor kernels, it uses "task_cputime" as a simple substructure, while for multiprocessor kernels it is a pointer: struct thread_group_cputime { struct task_cputime totals; }; struct thread_group_cputime { struct task_cputime *totals; }; We also add a new task_cputime substructure directly to signal_struct, to cache the earliest expiration of process-wide timers, and task_cputime also replaces the it_*_expires fields of task_struct (used for earliest expiration of thread timers). The "thread_group_cputime" structure contains process-wide timers that are updated via account_user_time() and friends. In the non-SMP case the structure is a simple aggregator; unfortunately in the SMP case that simplicity was not achievable due to cache-line contention between CPUs (in one measured case performance was actually _worse_ on a 16-cpu system than the same test on a 4-cpu system, due to this contention). For SMP, the thread_group_cputime counters are maintained as a per-cpu structure allocated using alloc_percpu(). The timer functions update only the timer field in the structure corresponding to the running CPU, obtained using per_cpu_ptr(). We define a set of inline functions in sched.h that we use to maintain the thread_group_cputime structure and hide the differences between UP and SMP implementations from the rest of the kernel. The thread_group_cputime_init() function initializes the thread_group_cputime structure for the given task. The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the out-of-line function thread_group_cputime_alloc_smp() to allocate and fill in the per-cpu structures and fields. The thread_group_cputime_free() function, also a no-op for UP, in SMP frees the per-cpu structures. The thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls thread_group_cputime_alloc() if the per-cpu structures haven't yet been allocated. The thread_group_cputime() function fills the task_cputime structure it is passed with the contents of the thread_group_cputime fields; in UP it's that simple but in SMP it must also safely check that tsk->signal is non-NULL (if it is it just uses the appropriate fields of task_struct) and, if so, sums the per-cpu values for each online CPU. Finally, the three functions account_group_user_time(), account_group_system_time() and account_group_exec_runtime() are used by timer functions to update the respective fields of the thread_group_cputime structure. Non-SMP operation is trivial and will not be mentioned further. The per-cpu structure is always allocated when a task creates its first new thread, via a call to thread_group_cputime_clone_thread() from copy_signal(). It is freed at process exit via a call to thread_group_cputime_free() from cleanup_signal(). All functions that formerly summed utime/stime/sum_sched_runtime values from from all threads in the thread group now use thread_group_cputime() to snapshot the values in the thread_group_cputime structure or the values in the task structure itself if the per-cpu structure hasn't been allocated. Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit. The run_posix_cpu_timers() function has been split into a fast path and a slow path; the former safely checks whether there are any expired thread timers and, if not, just returns, while the slow path does the heavy lifting. With the dedicated thread group fields, timers are no longer "rebalanced" and the process_timer_rebalance() function and related code has gone away. All summing loops are gone and all code that used them now uses the thread_group_cputime() inline. When process-wide timers are set, the new task_cputime structure in signal_struct is used to cache the earliest expiration; this is checked in the fast path. Performance The fix appears not to add significant overhead to existing operations. It generally performs the same as the current code except in two cases, one in which it performs slightly worse (Case 5 below) and one in which it performs very significantly better (Case 2 below). Overall it's a wash except in those two cases. I've since done somewhat more involved testing on a dual-core Opteron system. Case 1: With no itimer running, for a test with 100,000 threads, the fixed kernel took 1428.5 seconds, 513 seconds more than the unfixed system, all of which was spent in the system. There were twice as many voluntary context switches with the fix as without it. Case 2: With an itimer running at .01 second ticks and 4000 threads (the most an unmodified kernel can handle), the fixed kernel ran the test in eight percent of the time (5.8 seconds as opposed to 70 seconds) and had better tick accuracy (.012 seconds per tick as opposed to .023 seconds per tick). Case 3: A 4000-thread test with an initial timer tick of .01 second and an interval of 10,000 seconds (i.e. a timer that ticks only once) had very nearly the same performance in both cases: 6.3 seconds elapsed for the fixed kernel versus 5.5 seconds for the unfixed kernel. With fewer threads (eight in these tests), the Case 1 test ran in essentially the same time on both the modified and unmodified kernels (5.2 seconds versus 5.8 seconds). The Case 2 test ran in about the same time as well, 5.9 seconds versus 5.4 seconds but again with much better tick accuracy, .013 seconds per tick versus .025 seconds per tick for the unmodified kernel. Since the fix affected the rlimit code, I also tested soft and hard CPU limits. Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer running), the modified kernel was very slightly favored in that while it killed the process in 19.997 seconds of CPU time (5.002 seconds of wall time), only .003 seconds of that was system time, the rest was user time. The unmodified kernel killed the process in 20.001 seconds of CPU (5.014 seconds of wall time) of which .016 seconds was system time. Really, though, the results were too close to call. The results were essentially the same with no itimer running. Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds (where the hard limit would never be reached) and an itimer running, the modified kernel exhibited worse tick accuracy than the unmodified kernel: .050 seconds/tick versus .028 seconds/tick. Otherwise, performance was almost indistinguishable. With no itimer running this test exhibited virtually identical behavior and times in both cases. In times past I did some limited performance testing. those results are below. On a four-cpu Opteron system without this fix, a sixteen-thread test executed in 3569.991 seconds, of which user was 3568.435s and system was 1.556s. On the same system with the fix, user and elapsed time were about the same, but system time dropped to 0.007 seconds. Performance with eight, four and one thread were comparable. Interestingly, the timer ticks with the fix seemed more accurate: The sixteen-thread test with the fix received 149543 ticks for 0.024 seconds per tick, while the same test without the fix received 58720 for 0.061 seconds per tick. Both cases were configured for an interval of 0.01 seconds. Again, the other tests were comparable. Each thread in this test computed the primes up to 25,000,000. I also did a test with a large number of threads, 100,000 threads, which is impossible without the fix. In this case each thread computed the primes only up to 10,000 (to make the runtime manageable). System time dominated, at 1546.968 seconds out of a total 2176.906 seconds (giving a user time of 629.938s). It received 147651 ticks for 0.015 seconds per tick, still quite accurate. There is obviously no comparable test without the fix. Signed-off-by: Frank Mayhar Cc: Roland McGrath Cc: Alexey Dobriyan Cc: Andrew Morton Signed-off-by: Ingo Molnar --- fs/binfmt_elf.c | 19 +- fs/proc/array.c | 8 +- include/linux/posix-timers.h | 2 + include/linux/sched.h | 257 +++++++++++++++++++++-- include/linux/time.h | 3 + kernel/compat.c | 53 ++--- kernel/exit.c | 19 +- kernel/fork.c | 88 ++++---- kernel/itimer.c | 33 +-- kernel/posix-cpu-timers.c | 471 +++++++++++++++++++++++-------------------- kernel/sched.c | 53 ++++- kernel/sched_fair.c | 1 + kernel/sched_rt.c | 4 +- kernel/signal.c | 8 +- kernel/sys.c | 75 +++---- security/selinux/hooks.c | 9 +- 16 files changed, 677 insertions(+), 426 deletions(-) (limited to 'kernel/sched.c') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 655ed8d30a8..a8635f63703 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1333,20 +1333,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_pgrp = task_pgrp_vnr(p); prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { + struct task_cputime cputime; + /* - * This is the record for the group leader. Add in the - * cumulative times of previous dead threads. This total - * won't include the time of each live thread whose state - * is included in the core dump. The final total reported - * to our parent process when it calls wait4 will include - * those sums as well as the little bit more time it takes - * this and each other thread to finish dying after the - * core dump synchronization phase. + * This is the record for the group leader. It shows the + * group-wide total, not its individual thread total. */ - cputime_to_timeval(cputime_add(p->utime, p->signal->utime), - &prstatus->pr_utime); - cputime_to_timeval(cputime_add(p->stime, p->signal->stime), - &prstatus->pr_stime); + thread_group_cputime(p, &cputime); + cputime_to_timeval(cputime.utime, &prstatus->pr_utime); + cputime_to_timeval(cputime.stime, &prstatus->pr_stime); } else { cputime_to_timeval(p->utime, &prstatus->pr_utime); cputime_to_timeval(p->stime, &prstatus->pr_stime); diff --git a/fs/proc/array.c b/fs/proc/array.c index 71c9be59c9c..933953c4e40 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -395,20 +395,20 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* add up live thread stats at the group level */ if (whole) { + struct task_cputime cputime; struct task_struct *t = task; do { min_flt += t->min_flt; maj_flt += t->maj_flt; - utime = cputime_add(utime, task_utime(t)); - stime = cputime_add(stime, task_stime(t)); gtime = cputime_add(gtime, task_gtime(t)); t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; - utime = cputime_add(utime, sig->utime); - stime = cputime_add(stime, sig->stime); + thread_group_cputime(task, &cputime); + utime = cputime.utime; + stime = cputime.stime; gtime = cputime_add(gtime, sig->gtime); } diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index a7dd38f30ad..f9d8e9e94e9 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -115,4 +115,6 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, long clock_nanosleep_restart(struct restart_block *restart_block); +void update_rlimit_cpu(unsigned long rlim_new); + #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 3d9120c5ad1..26d7a5f2d0b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -425,6 +425,45 @@ struct pacct_struct { unsigned long ac_minflt, ac_majflt; }; +/** + * struct task_cputime - collected CPU time counts + * @utime: time spent in user mode, in &cputime_t units + * @stime: time spent in kernel mode, in &cputime_t units + * @sum_exec_runtime: total time spent on the CPU, in nanoseconds + * + * This structure groups together three kinds of CPU time that are + * tracked for threads and thread groups. Most things considering + * CPU time want to group these counts together and treat all three + * of them in parallel. + */ +struct task_cputime { + cputime_t utime; + cputime_t stime; + unsigned long long sum_exec_runtime; +}; +/* Alternate field names when used to cache expirations. */ +#define prof_exp stime +#define virt_exp utime +#define sched_exp sum_exec_runtime + +/** + * struct thread_group_cputime - thread group interval timer counts + * @totals: thread group interval timers; substructure for + * uniprocessor kernel, per-cpu for SMP kernel. + * + * This structure contains the version of task_cputime, above, that is + * used for thread group CPU clock calculations. + */ +#ifdef CONFIG_SMP +struct thread_group_cputime { + struct task_cputime *totals; +}; +#else +struct thread_group_cputime { + struct task_cputime totals; +}; +#endif + /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always @@ -470,6 +509,17 @@ struct signal_struct { cputime_t it_prof_expires, it_virt_expires; cputime_t it_prof_incr, it_virt_incr; + /* + * Thread group totals for process CPU clocks. + * See thread_group_cputime(), et al, for details. + */ + struct thread_group_cputime cputime; + + /* Earliest-expiration cache. */ + struct task_cputime cputime_expires; + + struct list_head cpu_timers[3]; + /* job control IDs */ /* @@ -500,7 +550,7 @@ struct signal_struct { * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ - cputime_t utime, stime, cutime, cstime; + cputime_t cutime, cstime; cputime_t gtime; cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -508,14 +558,6 @@ struct signal_struct { unsigned long inblock, oublock, cinblock, coublock; struct task_io_accounting ioac; - /* - * Cumulative ns of scheduled CPU time for dead threads in the - * group, not including a zombie group leader. (This only differs - * from jiffies_to_ns(utime + stime) if sched_clock uses something - * other than jiffies.) - */ - unsigned long long sum_sched_runtime; - /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs @@ -527,8 +569,6 @@ struct signal_struct { */ struct rlimit rlim[RLIM_NLIMITS]; - struct list_head cpu_timers[3]; - /* keep the process-shared keyrings here so that they do the right * thing in threads created with CLONE_THREAD */ #ifdef CONFIG_KEYS @@ -1134,8 +1174,7 @@ struct task_struct { /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; - cputime_t it_prof_expires, it_virt_expires; - unsigned long long it_sched_expires; + struct task_cputime cputime_expires; struct list_head cpu_timers[3]; /* process credentials */ @@ -1585,6 +1624,7 @@ extern unsigned long long cpu_clock(int cpu); extern unsigned long long task_sched_runtime(struct task_struct *task); +extern unsigned long long thread_group_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP @@ -2081,6 +2121,197 @@ static inline int spin_needbreak(spinlock_t *lock) #endif } +/* + * Thread group CPU time accounting. + */ +#ifdef CONFIG_SMP + +extern int thread_group_cputime_alloc_smp(struct task_struct *); +extern void thread_group_cputime_smp(struct task_struct *, struct task_cputime *); + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals = NULL; +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr, + struct task_struct *new) +{ + if (curr->signal->cputime.totals) + return 0; + return thread_group_cputime_alloc_smp(curr); +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ + free_percpu(sig->cputime.totals); +} + +/** + * thread_group_cputime - Sum the thread group time fields across all CPUs. + * + * This is a wrapper for the real routine, thread_group_cputime_smp(). See + * that routine for details. + */ +static inline void thread_group_cputime( + struct task_struct *tsk, + struct task_cputime *times) +{ + thread_group_cputime_smp(tsk, times); +} + +/** + * thread_group_cputime_account_user - Maintain utime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the utime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->utime = cputime_add(times->utime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_system - Maintain stime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the stime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->stime = cputime_add(times->stime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a + * thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of that structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->sum_exec_runtime += ns; + put_cpu_no_resched(); + } +} + +#else /* CONFIG_SMP */ + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals.utime = cputime_zero; + sig->cputime.totals.stime = cputime_zero; + sig->cputime.totals.sum_exec_runtime = 0; +} + +static inline int thread_group_cputime_alloc(struct task_struct *tsk) +{ + return 0; +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr, + struct task_struct *tsk) +{ +} + +static inline void thread_group_cputime(struct task_struct *tsk, + struct task_cputime *cputime) +{ + *cputime = tsk->signal->cputime.totals; +} + +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); +} + +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); +} + +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + tgtimes->totals->sum_exec_runtime += ns; +} + +#endif /* CONFIG_SMP */ + +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_user(&sig->cputime, cputime); +} + +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_system(&sig->cputime, cputime); +} + +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_exec_runtime(&sig->cputime, ns); +} + /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. diff --git a/include/linux/time.h b/include/linux/time.h index e15206a7e82..1b70b3c293e 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -125,6 +125,9 @@ extern int timekeeping_valid_for_hres(void); extern void update_wall_time(void); extern void update_xtime_cache(u64 nsec); +struct tms; +extern void do_sys_times(struct tms *); + /** * timespec_to_ns - Convert timespec to nanoseconds * @ts: pointer to the timespec variable to be converted diff --git a/kernel/compat.c b/kernel/compat.c index 32c254a8ab9..72650e39b3e 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -150,49 +151,23 @@ asmlinkage long compat_sys_setitimer(int which, return 0; } +static compat_clock_t clock_t_to_compat_clock_t(clock_t x) +{ + return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); +} + asmlinkage long compat_sys_times(struct compat_tms __user *tbuf) { - /* - * In the SMP world we might just be unlucky and have one of - * the times increment as we use it. Since the value is an - * atomically safe type this is just fine. Conceptually its - * as if the syscall took an instant longer to occur. - */ if (tbuf) { + struct tms tms; struct compat_tms tmp; - struct task_struct *tsk = current; - struct task_struct *t; - cputime_t utime, stime, cutime, cstime; - - read_lock(&tasklist_lock); - utime = tsk->signal->utime; - stime = tsk->signal->stime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != tsk); - - /* - * While we have tasklist_lock read-locked, no dying thread - * can be updating current->signal->[us]time. Instead, - * we got their counts included in the live thread loop. - * However, another thread can come in right now and - * do a wait call that updates current->signal->c[us]time. - * To make sure we always see that pair updated atomically, - * we take the siglock around fetching them. - */ - spin_lock_irq(&tsk->sighand->siglock); - cutime = tsk->signal->cutime; - cstime = tsk->signal->cstime; - spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); - - tmp.tms_utime = compat_jiffies_to_clock_t(cputime_to_jiffies(utime)); - tmp.tms_stime = compat_jiffies_to_clock_t(cputime_to_jiffies(stime)); - tmp.tms_cutime = compat_jiffies_to_clock_t(cputime_to_jiffies(cutime)); - tmp.tms_cstime = compat_jiffies_to_clock_t(cputime_to_jiffies(cstime)); + + do_sys_times(&tms); + /* Convert our struct tms to the compat version. */ + tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); + tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); + tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); + tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } diff --git a/kernel/exit.c b/kernel/exit.c index 16395644a98..40036ac0427 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -112,8 +112,6 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime = cputime_add(sig->utime, task_utime(tsk)); - sig->stime = cputime_add(sig->stime, task_stime(tsk)); sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; @@ -122,7 +120,6 @@ static void __exit_signal(struct task_struct *tsk) sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); - sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -1294,6 +1291,7 @@ static int wait_task_zombie(struct task_struct *p, int options, if (likely(!traced)) { struct signal_struct *psig; struct signal_struct *sig; + struct task_cputime cputime; /* * The resource counters for the group leader are in its @@ -1309,20 +1307,23 @@ static int wait_task_zombie(struct task_struct *p, int options, * need to protect the access to p->parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. + * + * We use thread_group_cputime() to get times for the thread + * group, which consolidates times for all threads in the + * group including the group leader. */ spin_lock_irq(&p->parent->sighand->siglock); psig = p->parent->signal; sig = p->signal; + thread_group_cputime(p, &cputime); psig->cutime = cputime_add(psig->cutime, - cputime_add(p->utime, - cputime_add(sig->utime, - sig->cutime))); + cputime_add(cputime.utime, + sig->cutime)); psig->cstime = cputime_add(psig->cstime, - cputime_add(p->stime, - cputime_add(sig->stime, - sig->cstime))); + cputime_add(cputime.stime, + sig->cstime)); psig->cgtime = cputime_add(psig->cgtime, cputime_add(p->gtime, diff --git a/kernel/fork.c b/kernel/fork.c index 7ce2ebe8479..a8ac2efb8e3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -759,15 +759,44 @@ void __cleanup_sighand(struct sighand_struct *sighand) kmem_cache_free(sighand_cachep, sighand); } + +/* + * Initialize POSIX timer handling for a thread group. + */ +static void posix_cpu_timers_init_group(struct signal_struct *sig) +{ + /* Thread group counters. */ + thread_group_cputime_init(sig); + + /* Expiration times and increments. */ + sig->it_virt_expires = cputime_zero; + sig->it_virt_incr = cputime_zero; + sig->it_prof_expires = cputime_zero; + sig->it_prof_incr = cputime_zero; + + /* Cached expiration times. */ + sig->cputime_expires.prof_exp = cputime_zero; + sig->cputime_expires.virt_exp = cputime_zero; + sig->cputime_expires.sched_exp = 0; + + /* The timer lists. */ + INIT_LIST_HEAD(&sig->cpu_timers[0]); + INIT_LIST_HEAD(&sig->cpu_timers[1]); + INIT_LIST_HEAD(&sig->cpu_timers[2]); +} + static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; int ret; if (clone_flags & CLONE_THREAD) { - atomic_inc(¤t->signal->count); - atomic_inc(¤t->signal->live); - return 0; + ret = thread_group_cputime_clone_thread(current, tsk); + if (likely(!ret)) { + atomic_inc(¤t->signal->count); + atomic_inc(¤t->signal->live); + } + return ret; } sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; @@ -795,15 +824,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; - sig->it_virt_expires = cputime_zero; - sig->it_virt_incr = cputime_zero; - sig->it_prof_expires = cputime_zero; - sig->it_prof_incr = cputime_zero; - sig->leader = 0; /* session leadership doesn't inherit */ sig->tty_old_pgrp = NULL; - sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; + sig->cutime = sig->cstime = cputime_zero; sig->gtime = cputime_zero; sig->cgtime = cputime_zero; sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; @@ -820,14 +844,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); - if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - /* - * New sole thread in the process gets an expiry time - * of the whole CPU time limit. - */ - tsk->it_prof_expires = - secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); - } + posix_cpu_timers_init_group(sig); + acct_init_pacct(&sig->pacct); tty_audit_fork(sig); @@ -837,6 +855,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) void __cleanup_signal(struct signal_struct *sig) { + thread_group_cputime_free(sig); exit_thread_group_keys(sig); kmem_cache_free(signal_cachep, sig); } @@ -885,6 +904,19 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p) } #endif /* CONFIG_MM_OWNER */ +/* + * Initialize POSIX timer handling for a single task. + */ +static void posix_cpu_timers_init(struct task_struct *tsk) +{ + tsk->cputime_expires.prof_exp = cputime_zero; + tsk->cputime_expires.virt_exp = cputime_zero; + tsk->cputime_expires.sched_exp = 0; + INIT_LIST_HEAD(&tsk->cpu_timers[0]); + INIT_LIST_HEAD(&tsk->cpu_timers[1]); + INIT_LIST_HEAD(&tsk->cpu_timers[2]); +} + /* * This creates a new process as a copy of the old one, * but does not actually start it yet. @@ -995,12 +1027,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, task_io_accounting_init(&p->ioac); acct_clear_integrals(p); - p->it_virt_expires = cputime_zero; - p->it_prof_expires = cputime_zero; - p->it_sched_expires = 0; - INIT_LIST_HEAD(&p->cpu_timers[0]); - INIT_LIST_HEAD(&p->cpu_timers[1]); - INIT_LIST_HEAD(&p->cpu_timers[2]); + posix_cpu_timers_init(p); p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); @@ -1201,21 +1228,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); - - if (!cputime_eq(current->signal->it_virt_expires, - cputime_zero) || - !cputime_eq(current->signal->it_prof_expires, - cputime_zero) || - current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY || - !list_empty(¤t->signal->cpu_timers[0]) || - !list_empty(¤t->signal->cpu_timers[1]) || - !list_empty(¤t->signal->cpu_timers[2])) { - /* - * Have child wake up on its first tick to check - * for process CPU timers. - */ - p->it_prof_expires = jiffies_to_cputime(1); - } } if (likely(p->pid)) { diff --git a/kernel/itimer.c b/kernel/itimer.c index ab982747d9b..db7c358b9a0 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -55,17 +55,15 @@ int do_getitimer(int which, struct itimerval *value) spin_unlock_irq(&tsk->sighand->siglock); break; case ITIMER_VIRTUAL: - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_virt_expires; cinterval = tsk->signal->it_virt_incr; if (!cputime_eq(cval, cputime_zero)) { - struct task_struct *t = tsk; - cputime_t utime = tsk->signal->utime; - do { - utime = cputime_add(utime, t->utime); - t = next_thread(t); - } while (t != tsk); + struct task_cputime cputime; + cputime_t utime; + + thread_group_cputime(tsk, &cputime); + utime = cputime.utime; if (cputime_le(cval, utime)) { /* about to fire */ cval = jiffies_to_cputime(1); } else { @@ -73,25 +71,19 @@ int do_getitimer(int which, struct itimerval *value) } } spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); cputime_to_timeval(cval, &value->it_value); cputime_to_timeval(cinterval, &value->it_interval); break; case ITIMER_PROF: - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_prof_expires; cinterval = tsk->signal->it_prof_incr; if (!cputime_eq(cval, cputime_zero)) { - struct task_struct *t = tsk; - cputime_t ptime = cputime_add(tsk->signal->utime, - tsk->signal->stime); - do { - ptime = cputime_add(ptime, - cputime_add(t->utime, - t->stime)); - t = next_thread(t); - } while (t != tsk); + struct task_cputime times; + cputime_t ptime; + + thread_group_cputime(tsk, ×); + ptime = cputime_add(times.utime, times.stime); if (cputime_le(cval, ptime)) { /* about to fire */ cval = jiffies_to_cputime(1); } else { @@ -99,7 +91,6 @@ int do_getitimer(int which, struct itimerval *value) } } spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); cputime_to_timeval(cval, &value->it_value); cputime_to_timeval(cinterval, &value->it_interval); break; @@ -185,7 +176,6 @@ again: case ITIMER_VIRTUAL: nval = timeval_to_cputime(&value->it_value); ninterval = timeval_to_cputime(&value->it_interval); - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_virt_expires; cinterval = tsk->signal->it_virt_incr; @@ -200,7 +190,6 @@ again: tsk->signal->it_virt_expires = nval; tsk->signal->it_virt_incr = ninterval; spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); if (ovalue) { cputime_to_timeval(cval, &ovalue->it_value); cputime_to_timeval(cinterval, &ovalue->it_interval); @@ -209,7 +198,6 @@ again: case ITIMER_PROF: nval = timeval_to_cputime(&value->it_value); ninterval = timeval_to_cputime(&value->it_interval); - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_prof_expires; cinterval = tsk->signal->it_prof_incr; @@ -224,7 +212,6 @@ again: tsk->signal->it_prof_expires = nval; tsk->signal->it_prof_incr = ninterval; spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); if (ovalue) { cputime_to_timeval(cval, &ovalue->it_value); cputime_to_timeval(cinterval, &ovalue->it_interval); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index c42a03aef36..dba1c334c3e 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -8,6 +8,99 @@ #include #include +#ifdef CONFIG_SMP +/* + * Allocate the thread_group_cputime structure appropriately for SMP kernels + * and fill in the current values of the fields. Called from copy_signal() + * via thread_group_cputime_clone_thread() when adding a second or subsequent + * thread to a thread group. Assumes interrupts are enabled when called. + */ +int thread_group_cputime_alloc_smp(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + struct task_cputime *cputime; + + /* + * If we have multiple threads and we don't already have a + * per-CPU task_cputime struct, allocate one and fill it in with + * the times accumulated so far. + */ + if (sig->cputime.totals) + return 0; + cputime = alloc_percpu(struct task_cputime); + if (cputime == NULL) + return -ENOMEM; + read_lock(&tasklist_lock); + spin_lock_irq(&tsk->sighand->siglock); + if (sig->cputime.totals) { + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + free_percpu(cputime); + return 0; + } + sig->cputime.totals = cputime; + cputime = per_cpu_ptr(sig->cputime.totals, get_cpu()); + cputime->utime = tsk->utime; + cputime->stime = tsk->stime; + cputime->sum_exec_runtime = tsk->se.sum_exec_runtime; + put_cpu_no_resched(); + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + return 0; +} + +/** + * thread_group_cputime_smp - Sum the thread group time fields across all CPUs. + * + * @tsk: The task we use to identify the thread group. + * @times: task_cputime structure in which we return the summed fields. + * + * Walk the list of CPUs to sum the per-CPU time fields in the thread group + * time structure. + */ +void thread_group_cputime_smp( + struct task_struct *tsk, + struct task_cputime *times) +{ + struct signal_struct *sig; + int i; + struct task_cputime *tot; + + sig = tsk->signal; + if (unlikely(!sig) || !sig->cputime.totals) { + times->utime = tsk->utime; + times->stime = tsk->stime; + times->sum_exec_runtime = tsk->se.sum_exec_runtime; + return; + } + times->stime = times->utime = cputime_zero; + times->sum_exec_runtime = 0; + for_each_possible_cpu(i) { + tot = per_cpu_ptr(tsk->signal->cputime.totals, i); + times->utime = cputime_add(times->utime, tot->utime); + times->stime = cputime_add(times->stime, tot->stime); + times->sum_exec_runtime += tot->sum_exec_runtime; + } +} + +#endif /* CONFIG_SMP */ + +/* + * Called after updating RLIMIT_CPU to set timer expiration if necessary. + */ +void update_rlimit_cpu(unsigned long rlim_new) +{ + cputime_t cputime; + + cputime = secs_to_cputime(rlim_new); + if (cputime_eq(current->signal->it_prof_expires, cputime_zero) || + cputime_lt(current->signal->it_prof_expires, cputime)) { + spin_lock_irq(¤t->sighand->siglock); + set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); + spin_unlock_irq(¤t->sighand->siglock); + } +} + static int check_clock(const clockid_t which_clock) { int error = 0; @@ -158,10 +251,6 @@ static inline cputime_t virt_ticks(struct task_struct *p) { return p->utime; } -static inline unsigned long long sched_ns(struct task_struct *p) -{ - return task_sched_runtime(p); -} int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp) { @@ -211,7 +300,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, cpu->cpu = virt_ticks(p); break; case CPUCLOCK_SCHED: - cpu->sched = sched_ns(p); + cpu->sched = task_sched_runtime(p); break; } return 0; @@ -226,31 +315,20 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx, struct task_struct *p, union cpu_time_count *cpu) { - struct task_struct *t = p; - switch (clock_idx) { + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + switch (clock_idx) { default: return -EINVAL; case CPUCLOCK_PROF: - cpu->cpu = cputime_add(p->signal->utime, p->signal->stime); - do { - cpu->cpu = cputime_add(cpu->cpu, prof_ticks(t)); - t = next_thread(t); - } while (t != p); + cpu->cpu = cputime_add(cputime.utime, cputime.stime); break; case CPUCLOCK_VIRT: - cpu->cpu = p->signal->utime; - do { - cpu->cpu = cputime_add(cpu->cpu, virt_ticks(t)); - t = next_thread(t); - } while (t != p); + cpu->cpu = cputime.utime; break; case CPUCLOCK_SCHED: - cpu->sched = p->signal->sum_sched_runtime; - /* Add in each other live thread. */ - while ((t = next_thread(t)) != p) { - cpu->sched += t->se.sum_exec_runtime; - } - cpu->sched += sched_ns(p); + cpu->sched = thread_group_sched_runtime(p); break; } return 0; @@ -471,80 +549,11 @@ void posix_cpu_timers_exit(struct task_struct *tsk) } void posix_cpu_timers_exit_group(struct task_struct *tsk) { - cleanup_timers(tsk->signal->cpu_timers, - cputime_add(tsk->utime, tsk->signal->utime), - cputime_add(tsk->stime, tsk->signal->stime), - tsk->se.sum_exec_runtime + tsk->signal->sum_sched_runtime); -} - - -/* - * Set the expiry times of all the threads in the process so one of them - * will go off before the process cumulative expiry total is reached. - */ -static void process_timer_rebalance(struct task_struct *p, - unsigned int clock_idx, - union cpu_time_count expires, - union cpu_time_count val) -{ - cputime_t ticks, left; - unsigned long long ns, nsleft; - struct task_struct *t = p; - unsigned int nthreads = atomic_read(&p->signal->live); - - if (!nthreads) - return; + struct task_cputime cputime; - switch (clock_idx) { - default: - BUG(); - break; - case CPUCLOCK_PROF: - left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu), - nthreads); - do { - if (likely(!(t->flags & PF_EXITING))) { - ticks = cputime_add(prof_ticks(t), left); - if (cputime_eq(t->it_prof_expires, - cputime_zero) || - cputime_gt(t->it_prof_expires, ticks)) { - t->it_prof_expires = ticks; - } - } - t = next_thread(t); - } while (t != p); - break; - case CPUCLOCK_VIRT: - left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu), - nthreads); - do { - if (likely(!(t->flags & PF_EXITING))) { - ticks = cputime_add(virt_ticks(t), left); - if (cputime_eq(t->it_virt_expires, - cputime_zero) || - cputime_gt(t->it_virt_expires, ticks)) { - t->it_virt_expires = ticks; - } - } - t = next_thread(t); - } while (t != p); - break; - case CPUCLOCK_SCHED: - nsleft = expires.sched - val.sched; - do_div(nsleft, nthreads); - nsleft = max_t(unsigned long long, nsleft, 1); - do { - if (likely(!(t->flags & PF_EXITING))) { - ns = t->se.sum_exec_runtime + nsleft; - if (t->it_sched_expires == 0 || - t->it_sched_expires > ns) { - t->it_sched_expires = ns; - } - } - t = next_thread(t); - } while (t != p); - break; - } + thread_group_cputime(tsk, &cputime); + cleanup_timers(tsk->signal->cpu_timers, + cputime.utime, cputime.stime, cputime.sum_exec_runtime); } static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) @@ -608,29 +617,32 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) default: BUG(); case CPUCLOCK_PROF: - if (cputime_eq(p->it_prof_expires, + if (cputime_eq(p->cputime_expires.prof_exp, cputime_zero) || - cputime_gt(p->it_prof_expires, + cputime_gt(p->cputime_expires.prof_exp, nt->expires.cpu)) - p->it_prof_expires = nt->expires.cpu; + p->cputime_expires.prof_exp = + nt->expires.cpu; break; case CPUCLOCK_VIRT: - if (cputime_eq(p->it_virt_expires, + if (cputime_eq(p->cputime_expires.virt_exp, cputime_zero) || - cputime_gt(p->it_virt_expires, + cputime_gt(p->cputime_expires.virt_exp, nt->expires.cpu)) - p->it_virt_expires = nt->expires.cpu; + p->cputime_expires.virt_exp = + nt->expires.cpu; break; case CPUCLOCK_SCHED: - if (p->it_sched_expires == 0 || - p->it_sched_expires > nt->expires.sched) - p->it_sched_expires = nt->expires.sched; + if (p->cputime_expires.sched_exp == 0 || + p->cputime_expires.sched_exp > + nt->expires.sched) + p->cputime_expires.sched_exp = + nt->expires.sched; break; } } else { /* - * For a process timer, we must balance - * all the live threads' expirations. + * For a process timer, set the cached expiration time. */ switch (CPUCLOCK_WHICH(timer->it_clock)) { default: @@ -641,7 +653,9 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) cputime_lt(p->signal->it_virt_expires, timer->it.cpu.expires.cpu)) break; - goto rebalance; + p->signal->cputime_expires.virt_exp = + timer->it.cpu.expires.cpu; + break; case CPUCLOCK_PROF: if (!cputime_eq(p->signal->it_prof_expires, cputime_zero) && @@ -652,13 +666,12 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) if (i != RLIM_INFINITY && i <= cputime_to_secs(timer->it.cpu.expires.cpu)) break; - goto rebalance; + p->signal->cputime_expires.prof_exp = + timer->it.cpu.expires.cpu; + break; case CPUCLOCK_SCHED: - rebalance: - process_timer_rebalance( - timer->it.cpu.task, - CPUCLOCK_WHICH(timer->it_clock), - timer->it.cpu.expires, now); + p->signal->cputime_expires.sched_exp = + timer->it.cpu.expires.sched; break; } } @@ -969,13 +982,13 @@ static void check_thread_timers(struct task_struct *tsk, struct signal_struct *const sig = tsk->signal; maxfire = 20; - tsk->it_prof_expires = cputime_zero; + tsk->cputime_expires.prof_exp = cputime_zero; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) { - tsk->it_prof_expires = t->expires.cpu; + tsk->cputime_expires.prof_exp = t->expires.cpu; break; } t->firing = 1; @@ -984,13 +997,13 @@ static void check_thread_timers(struct task_struct *tsk, ++timers; maxfire = 20; - tsk->it_virt_expires = cputime_zero; + tsk->cputime_expires.virt_exp = cputime_zero; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) { - tsk->it_virt_expires = t->expires.cpu; + tsk->cputime_expires.virt_exp = t->expires.cpu; break; } t->firing = 1; @@ -999,13 +1012,13 @@ static void check_thread_timers(struct task_struct *tsk, ++timers; maxfire = 20; - tsk->it_sched_expires = 0; + tsk->cputime_expires.sched_exp = 0; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) { - tsk->it_sched_expires = t->expires.sched; + tsk->cputime_expires.sched_exp = t->expires.sched; break; } t->firing = 1; @@ -1055,10 +1068,10 @@ static void check_process_timers(struct task_struct *tsk, { int maxfire; struct signal_struct *const sig = tsk->signal; - cputime_t utime, stime, ptime, virt_expires, prof_expires; + cputime_t utime, ptime, virt_expires, prof_expires; unsigned long long sum_sched_runtime, sched_expires; - struct task_struct *t; struct list_head *timers = sig->cpu_timers; + struct task_cputime cputime; /* * Don't sample the current process CPU clocks if there are no timers. @@ -1074,18 +1087,10 @@ static void check_process_timers(struct task_struct *tsk, /* * Collect the current process totals. */ - utime = sig->utime; - stime = sig->stime; - sum_sched_runtime = sig->sum_sched_runtime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - sum_sched_runtime += t->se.sum_exec_runtime; - t = next_thread(t); - } while (t != tsk); - ptime = cputime_add(utime, stime); - + thread_group_cputime(tsk, &cputime); + utime = cputime.utime; + ptime = cputime_add(utime, cputime.stime); + sum_sched_runtime = cputime.sum_exec_runtime; maxfire = 20; prof_expires = cputime_zero; while (!list_empty(timers)) { @@ -1193,60 +1198,18 @@ static void check_process_timers(struct task_struct *tsk, } } - if (!cputime_eq(prof_expires, cputime_zero) || - !cputime_eq(virt_expires, cputime_zero) || - sched_expires != 0) { - /* - * Rebalance the threads' expiry times for the remaining - * process CPU timers. - */ - - cputime_t prof_left, virt_left, ticks; - unsigned long long sched_left, sched; - const unsigned int nthreads = atomic_read(&sig->live); - - if (!nthreads) - return; - - prof_left = cputime_sub(prof_expires, utime); - prof_left = cputime_sub(prof_left, stime); - prof_left = cputime_div_non_zero(prof_left, nthreads); - virt_left = cputime_sub(virt_expires, utime); - virt_left = cputime_div_non_zero(virt_left, nthreads); - if (sched_expires) { - sched_left = sched_expires - sum_sched_runtime; - do_div(sched_left, nthreads); - sched_left = max_t(unsigned long long, sched_left, 1); - } else { - sched_left = 0; - } - t = tsk; - do { - if (unlikely(t->flags & PF_EXITING)) - continue; - - ticks = cputime_add(cputime_add(t->utime, t->stime), - prof_left); - if (!cputime_eq(prof_expires, cputime_zero) && - (cputime_eq(t->it_prof_expires, cputime_zero) || - cputime_gt(t->it_prof_expires, ticks))) { - t->it_prof_expires = ticks; - } - - ticks = cputime_add(t->utime, virt_left); - if (!cputime_eq(virt_expires, cputime_zero) && - (cputime_eq(t->it_virt_expires, cputime_zero) || - cputime_gt(t->it_virt_expires, ticks))) { - t->it_virt_expires = ticks; - } - - sched = t->se.sum_exec_runtime + sched_left; - if (sched_expires && (t->it_sched_expires == 0 || - t->it_sched_expires > sched)) { - t->it_sched_expires = sched; - } - } while ((t = next_thread(t)) != tsk); - } + if (!cputime_eq(prof_expires, cputime_zero) && + (cputime_eq(sig->cputime_expires.prof_exp, cputime_zero) || + cputime_gt(sig->cputime_expires.prof_exp, prof_expires))) + sig->cputime_expires.prof_exp = prof_expires; + if (!cputime_eq(virt_expires, cputime_zero) && + (cputime_eq(sig->cputime_expires.virt_exp, cputime_zero) || + cputime_gt(sig->cputime_expires.virt_exp, virt_expires))) + sig->cputime_expires.virt_exp = virt_expires; + if (sched_expires != 0 && + (sig->cputime_expires.sched_exp == 0 || + sig->cputime_expires.sched_exp > sched_expires)) + sig->cputime_expires.sched_exp = sched_expires; } /* @@ -1314,6 +1277,78 @@ out: ++timer->it_requeue_pending; } +/** + * task_cputime_zero - Check a task_cputime struct for all zero fields. + * + * @cputime: The struct to compare. + * + * Checks @cputime to see if all fields are zero. Returns true if all fields + * are zero, false if any field is nonzero. + */ +static inline int task_cputime_zero(const struct task_cputime *cputime) +{ + if (cputime_eq(cputime->utime, cputime_zero) && + cputime_eq(cputime->stime, cputime_zero) && + cputime->sum_exec_runtime == 0) + return 1; + return 0; +} + +/** + * task_cputime_expired - Compare two task_cputime entities. + * + * @sample: The task_cputime structure to be checked for expiration. + * @expires: Expiration times, against which @sample will be checked. + * + * Checks @sample against @expires to see if any field of @sample has expired. + * Returns true if any field of the former is greater than the corresponding + * field of the latter if the latter field is set. Otherwise returns false. + */ +static inline int task_cputime_expired(const struct task_cputime *sample, + const struct task_cputime *expires) +{ + if (!cputime_eq(expires->utime, cputime_zero) && + cputime_ge(sample->utime, expires->utime)) + return 1; + if (!cputime_eq(expires->stime, cputime_zero) && + cputime_ge(cputime_add(sample->utime, sample->stime), + expires->stime)) + return 1; + if (expires->sum_exec_runtime != 0 && + sample->sum_exec_runtime >= expires->sum_exec_runtime) + return 1; + return 0; +} + +/** + * fastpath_timer_check - POSIX CPU timers fast path. + * + * @tsk: The task (thread) being checked. + * @sig: The signal pointer for that task. + * + * If there are no timers set return false. Otherwise snapshot the task and + * thread group timers, then compare them with the corresponding expiration + # times. Returns true if a timer has expired, else returns false. + */ +static inline int fastpath_timer_check(struct task_struct *tsk, + struct signal_struct *sig) +{ + struct task_cputime task_sample = { + .utime = tsk->utime, + .stime = tsk->stime, + .sum_exec_runtime = tsk->se.sum_exec_runtime + }; + struct task_cputime group_sample; + + if (task_cputime_zero(&tsk->cputime_expires) && + task_cputime_zero(&sig->cputime_expires)) + return 0; + if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) + return 1; + thread_group_cputime(tsk, &group_sample); + return task_cputime_expired(&group_sample, &sig->cputime_expires); +} + /* * This is called from the timer interrupt handler. The irq handler has * already updated our counts. We need to check if any timers fire now. @@ -1323,30 +1358,29 @@ void run_posix_cpu_timers(struct task_struct *tsk) { LIST_HEAD(firing); struct k_itimer *timer, *next; + struct signal_struct *sig; + struct sighand_struct *sighand; + unsigned long flags; BUG_ON(!irqs_disabled()); -#define UNEXPIRED(clock) \ - (cputime_eq(tsk->it_##clock##_expires, cputime_zero) || \ - cputime_lt(clock##_ticks(tsk), tsk->it_##clock##_expires)) - - if (UNEXPIRED(prof) && UNEXPIRED(virt) && - (tsk->it_sched_expires == 0 || - tsk->se.sum_exec_runtime < tsk->it_sched_expires)) - return; - -#undef UNEXPIRED - + /* Pick up tsk->signal and make sure it's valid. */ + sig = tsk->signal; /* - * Double-check with locks held. + * The fast path checks that there are no expired thread or thread + * group timers. If that's so, just return. Also check that + * tsk->signal is non-NULL; this probably can't happen but cover the + * possibility anyway. */ - read_lock(&tasklist_lock); - if (likely(tsk->signal != NULL)) { - spin_lock(&tsk->sighand->siglock); - + if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) { + return; + } + sighand = lock_task_sighand(tsk, &flags); + if (likely(sighand)) { /* - * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N] - * all the timers that are firing, and put them on the firing list. + * Here we take off tsk->signal->cpu_timers[N] and + * tsk->cpu_timers[N] all the timers that are firing, and + * put them on the firing list. */ check_thread_timers(tsk, &firing); check_process_timers(tsk, &firing); @@ -1359,9 +1393,8 @@ void run_posix_cpu_timers(struct task_struct *tsk) * that gets the timer lock before we do will give it up and * spin until we've taken care of that timer below. */ - spin_unlock(&tsk->sighand->siglock); } - read_unlock(&tasklist_lock); + unlock_task_sighand(tsk, &flags); /* * Now that all the timers on our list have the firing flag, @@ -1389,10 +1422,9 @@ void run_posix_cpu_timers(struct task_struct *tsk) /* * Set one of the process-wide special case CPU timers. - * The tasklist_lock and tsk->sighand->siglock must be held by the caller. - * The oldval argument is null for the RLIMIT_CPU timer, where *newval is - * absolute; non-null for ITIMER_*, where *newval is relative and we update - * it to be absolute, *oldval is absolute and we update it to be relative. + * The tsk->sighand->siglock must be held by the caller. + * The *newval argument is relative and we update it to be absolute, *oldval + * is absolute and we update it to be relative. */ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval) @@ -1435,13 +1467,14 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_ge(list_first_entry(head, struct cpu_timer_list, entry)->expires.cpu, *newval)) { - /* - * Rejigger each thread's expiry time so that one will - * notice before we hit the process-cumulative expiry time. - */ - union cpu_time_count expires = { .sched = 0 }; - expires.cpu = *newval; - process_timer_rebalance(tsk, clock_idx, expires, now); + switch (clock_idx) { + case CPUCLOCK_PROF: + tsk->signal->cputime_expires.prof_exp = *newval; + break; + case CPUCLOCK_VIRT: + tsk->signal->cputime_expires.virt_exp = *newval; + break; + } } } diff --git a/kernel/sched.c b/kernel/sched.c index cc1f81b50b8..c51b5d27666 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4036,6 +4036,25 @@ DEFINE_PER_CPU(struct kernel_stat, kstat); EXPORT_PER_CPU_SYMBOL(kstat); +/* + * Return any ns on the sched_clock that have not yet been banked in + * @p in case that task is currently running. + * + * Called with task_rq_lock() held on @rq. + */ +static unsigned long long task_delta_exec(struct task_struct *p, struct rq *rq) +{ + if (task_current(rq, p)) { + u64 delta_exec; + + update_rq_clock(rq); + delta_exec = rq->clock - p->se.exec_start; + if ((s64)delta_exec > 0) + return delta_exec; + } + return 0; +} + /* * Return p->sum_exec_runtime plus any more ns on the sched_clock * that have not yet been banked in case the task is currently running. @@ -4043,17 +4062,31 @@ EXPORT_PER_CPU_SYMBOL(kstat); unsigned long long task_sched_runtime(struct task_struct *p) { unsigned long flags; - u64 ns, delta_exec; + u64 ns; struct rq *rq; rq = task_rq_lock(p, &flags); - ns = p->se.sum_exec_runtime; - if (task_current(rq, p)) { - update_rq_clock(rq); - delta_exec = rq->clock - p->se.exec_start; - if ((s64)delta_exec > 0) - ns += delta_exec; - } + ns = p->se.sum_exec_runtime + task_delta_exec(p, rq); + task_rq_unlock(rq, &flags); + + return ns; +} + +/* + * Return sum_exec_runtime for the thread group plus any more ns on the + * sched_clock that have not yet been banked in case the task is currently + * running. + */ +unsigned long long thread_group_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + u64 ns; + struct rq *rq; + struct task_cputime totals; + + rq = task_rq_lock(p, &flags); + thread_group_cputime(p, &totals); + ns = totals.sum_exec_runtime + task_delta_exec(p, rq); task_rq_unlock(rq, &flags); return ns; @@ -4070,6 +4103,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime) cputime64_t tmp; p->utime = cputime_add(p->utime, cputime); + account_group_user_time(p, cputime); /* Add user time to cpustat. */ tmp = cputime_to_cputime64(cputime); @@ -4094,6 +4128,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime) tmp = cputime_to_cputime64(cputime); p->utime = cputime_add(p->utime, cputime); + account_group_user_time(p, cputime); p->gtime = cputime_add(p->gtime, cputime); cpustat->user = cputime64_add(cpustat->user, tmp); @@ -4129,6 +4164,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset, } p->stime = cputime_add(p->stime, cputime); + account_group_system_time(p, cputime); /* Add system time to cpustat. */ tmp = cputime_to_cputime64(cputime); @@ -4170,6 +4206,7 @@ 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 diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index fb8994c6d4b..99aa31acc54 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -507,6 +507,7 @@ static void update_curr(struct cfs_rq *cfs_rq) struct task_struct *curtask = task_of(curr); cpuacct_charge(curtask, delta_exec); + account_group_exec_runtime(curtask, delta_exec); } } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 552310798da..8375e69af36 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -483,6 +483,8 @@ static void update_curr_rt(struct rq *rq) schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + curr->se.exec_start = rq->clock; cpuacct_charge(curr, delta_exec); @@ -1412,7 +1414,7 @@ static void watchdog(struct rq *rq, struct task_struct *p) p->rt.timeout++; next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ); if (p->rt.timeout > next) - p->it_sched_expires = p->se.sum_exec_runtime; + p->cputime_expires.sched_exp = p->se.sum_exec_runtime; } } diff --git a/kernel/signal.c b/kernel/signal.c index e661b01d340..6eea5826d61 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1338,6 +1338,7 @@ int do_notify_parent(struct task_struct *tsk, int sig) struct siginfo info; unsigned long flags; struct sighand_struct *psig; + struct task_cputime cputime; int ret = sig; BUG_ON(sig == -1); @@ -1368,10 +1369,9 @@ int do_notify_parent(struct task_struct *tsk, int sig) info.si_uid = tsk->uid; - info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime, - tsk->signal->utime)); - info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime, - tsk->signal->stime)); + thread_group_cputime(tsk, &cputime); + info.si_utime = cputime_to_jiffies(cputime.utime); + info.si_stime = cputime_to_jiffies(cputime.stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) diff --git a/kernel/sys.c b/kernel/sys.c index 038a7bc0901..d046a7a055c 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -853,38 +853,28 @@ asmlinkage long sys_setfsgid(gid_t gid) return old_fsgid; } +void do_sys_times(struct tms *tms) +{ + struct task_cputime cputime; + cputime_t cutime, cstime; + + spin_lock_irq(¤t->sighand->siglock); + thread_group_cputime(current, &cputime); + cutime = current->signal->cutime; + cstime = current->signal->cstime; + spin_unlock_irq(¤t->sighand->siglock); + tms->tms_utime = cputime_to_clock_t(cputime.utime); + tms->tms_stime = cputime_to_clock_t(cputime.stime); + tms->tms_cutime = cputime_to_clock_t(cutime); + tms->tms_cstime = cputime_to_clock_t(cstime); +} + asmlinkage long sys_times(struct tms __user * tbuf) { - /* - * In the SMP world we might just be unlucky and have one of - * the times increment as we use it. Since the value is an - * atomically safe type this is just fine. Conceptually its - * as if the syscall took an instant longer to occur. - */ if (tbuf) { struct tms tmp; - struct task_struct *tsk = current; - struct task_struct *t; - cputime_t utime, stime, cutime, cstime; - - spin_lock_irq(&tsk->sighand->siglock); - utime = tsk->signal->utime; - stime = tsk->signal->stime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != tsk); - - cutime = tsk->signal->cutime; - cstime = tsk->signal->cstime; - spin_unlock_irq(&tsk->sighand->siglock); - - tmp.tms_utime = cputime_to_clock_t(utime); - tmp.tms_stime = cputime_to_clock_t(stime); - tmp.tms_cutime = cputime_to_clock_t(cutime); - tmp.tms_cstime = cputime_to_clock_t(cstime); + + do_sys_times(&tmp); if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } @@ -1445,7 +1435,6 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) { struct rlimit new_rlim, *old_rlim; - unsigned long it_prof_secs; int retval; if (resource >= RLIM_NLIMITS) @@ -1491,18 +1480,7 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) if (new_rlim.rlim_cur == RLIM_INFINITY) goto out; - it_prof_secs = cputime_to_secs(current->signal->it_prof_expires); - if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) { - unsigned long rlim_cur = new_rlim.rlim_cur; - cputime_t cputime; - - cputime = secs_to_cputime(rlim_cur); - read_lock(&tasklist_lock); - spin_lock_irq(¤t->sighand->siglock); - set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); - spin_unlock_irq(¤t->sighand->siglock); - read_unlock(&tasklist_lock); - } + update_rlimit_cpu(new_rlim.rlim_cur); out: return 0; } @@ -1540,11 +1518,8 @@ out: * */ -static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r, - cputime_t *utimep, cputime_t *stimep) +static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) { - *utimep = cputime_add(*utimep, t->utime); - *stimep = cputime_add(*stimep, t->stime); r->ru_nvcsw += t->nvcsw; r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; @@ -1558,12 +1533,13 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) struct task_struct *t; unsigned long flags; cputime_t utime, stime; + struct task_cputime cputime; memset((char *) r, 0, sizeof *r); utime = stime = cputime_zero; if (who == RUSAGE_THREAD) { - accumulate_thread_rusage(p, r, &utime, &stime); + accumulate_thread_rusage(p, r); goto out; } @@ -1586,8 +1562,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) break; case RUSAGE_SELF: - utime = cputime_add(utime, p->signal->utime); - stime = cputime_add(stime, p->signal->stime); + thread_group_cputime(p, &cputime); + utime = cputime_add(utime, cputime.utime); + stime = cputime_add(stime, cputime.stime); r->ru_nvcsw += p->signal->nvcsw; r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; @@ -1596,7 +1573,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) r->ru_oublock += p->signal->oublock; t = p; do { - accumulate_thread_rusage(t, r, &utime, &stime); + accumulate_thread_rusage(t, r); t = next_thread(t); } while (t != p); break; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 03fc6a81ae3..69649783c26 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -75,6 +75,7 @@ #include #include #include +#include #include "avc.h" #include "objsec.h" @@ -2321,13 +2322,7 @@ static void selinux_bprm_post_apply_creds(struct linux_binprm *bprm) initrlim = init_task.signal->rlim+i; rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } - if (current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - /* - * This will cause RLIMIT_CPU calculations - * to be refigured. - */ - current->it_prof_expires = jiffies_to_cputime(1); - } + update_rlimit_cpu(rlim->rlim_cur); } /* Wake up the parent if it is waiting so that it can -- cgit v1.2.3-70-g09d2 From 15afe09bf496ae10c989e1a375a6b5da7bd3e16e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 20 Sep 2008 23:38:02 +0200 Subject: sched: wakeup preempt when small overlap Lin Ming reported a 10% OLTP regression against 2.6.27-rc4. The difference seems to come from different preemption agressiveness, which affects the cache footprint of the workload and its effective cache trashing. Aggresively preempt a task if its avg overlap is very small, this should avoid the task going to sleep and find it still running when we schedule back to it - saving a wakeup. Reported-by: Lin Ming Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- kernel/sched.c | 12 ++++++------ kernel/sched_fair.c | 13 ++++++++++--- kernel/sched_features.h | 1 + kernel/sched_idletask.c | 6 +++--- kernel/sched_rt.c | 2 +- 6 files changed, 22 insertions(+), 14 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index b3b7a8f3247..d8e699b5585 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -897,7 +897,7 @@ struct sched_class { void (*yield_task) (struct rq *rq); int (*select_task_rq)(struct task_struct *p, int sync); - void (*check_preempt_curr) (struct rq *rq, struct task_struct *p); + void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync); struct task_struct * (*pick_next_task) (struct rq *rq); void (*put_prev_task) (struct rq *rq, struct task_struct *p); diff --git a/kernel/sched.c b/kernel/sched.c index 0d8905a1b8c..ad9d39b021f 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -604,9 +604,9 @@ struct rq { static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -static inline void check_preempt_curr(struct rq *rq, struct task_struct *p) +static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync) { - rq->curr->sched_class->check_preempt_curr(rq, p); + rq->curr->sched_class->check_preempt_curr(rq, p, sync); } static inline int cpu_of(struct rq *rq) @@ -2282,7 +2282,7 @@ out_running: trace_mark(kernel_sched_wakeup, "pid %d state %ld ## rq %p task %p rq->curr %p", p->pid, p->state, rq, p, rq->curr); - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, sync); p->state = TASK_RUNNING; #ifdef CONFIG_SMP @@ -2417,7 +2417,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) trace_mark(kernel_sched_wakeup_new, "pid %d state %ld ## rq %p task %p rq->curr %p", p->pid, p->state, rq, p, rq->curr); - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, 0); #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) p->sched_class->task_wake_up(rq, p); @@ -2877,7 +2877,7 @@ static void pull_task(struct rq *src_rq, struct task_struct *p, * Note that idle threads have a prio of MAX_PRIO, for this test * to be always true for them. */ - check_preempt_curr(this_rq, p); + check_preempt_curr(this_rq, p, 0); } /* @@ -6007,7 +6007,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) set_task_cpu(p, dest_cpu); if (on_rq) { activate_task(rq_dest, p, 0); - check_preempt_curr(rq_dest, p); + check_preempt_curr(rq_dest, p, 0); } done: ret = 1; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index a10ac0bcee6..7328383690f 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1331,7 +1331,7 @@ static inline int depth_se(struct sched_entity *se) /* * Preempt the current task with a newly woken task if needed: */ -static void check_preempt_wakeup(struct rq *rq, struct task_struct *p) +static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) { struct task_struct *curr = rq->curr; struct cfs_rq *cfs_rq = task_cfs_rq(curr); @@ -1367,6 +1367,13 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p) if (!sched_feat(WAKEUP_PREEMPT)) return; + if (sched_feat(WAKEUP_OVERLAP) && sync && + se->avg_overlap < sysctl_sched_migration_cost && + pse->avg_overlap < sysctl_sched_migration_cost) { + resched_task(curr); + return; + } + /* * preemption test can be made between sibling entities who are in the * same cfs_rq i.e who have a common parent. Walk up the hierarchy of @@ -1649,7 +1656,7 @@ static void prio_changed_fair(struct rq *rq, struct task_struct *p, if (p->prio > oldprio) resched_task(rq->curr); } else - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, 0); } /* @@ -1666,7 +1673,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p, if (running) resched_task(rq->curr); else - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, 0); } /* Account for a task changing its policy or group. diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 9353ca78154..bf027a7accf 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -11,3 +11,4 @@ SCHED_FEAT(ASYM_GRAN, 1) SCHED_FEAT(LB_BIAS, 1) SCHED_FEAT(LB_WAKEUP_UPDATE, 1) SCHED_FEAT(ASYM_EFF_LOAD, 1) +SCHED_FEAT(WAKEUP_OVERLAP, 1) diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index 3a4f92dbbe6..dec4ccabe2f 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -14,7 +14,7 @@ static int select_task_rq_idle(struct task_struct *p, int sync) /* * Idle tasks are unconditionally rescheduled: */ -static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p) +static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int sync) { resched_task(rq->idle); } @@ -76,7 +76,7 @@ static void switched_to_idle(struct rq *rq, struct task_struct *p, if (running) resched_task(rq->curr); else - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, 0); } static void prio_changed_idle(struct rq *rq, struct task_struct *p, @@ -93,7 +93,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p, if (p->prio > oldprio) resched_task(rq->curr); } else - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, 0); } /* diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 552310798da..6d2d0a5d030 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -783,7 +783,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) /* * Preempt the current task with a newly woken task if needed: */ -static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p) +static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int sync) { if (p->prio < rq->curr->prio) { resched_task(rq->curr); -- cgit v1.2.3-70-g09d2 From 006c75f146e58e080d2b2725a6664f71886e112b Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 22 Sep 2008 14:55:46 -0700 Subject: sched: clarify ifdef tangle - Add some comments to try to make the ifdef puzzle a bit clearer - Explicitly inline one of the three init_hrtick() implementations. Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- kernel/sched.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index ad9d39b021f..927c9307cd0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1102,7 +1102,7 @@ static void hrtick_start(struct rq *rq, u64 delay) hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL); } -static void init_hrtick(void) +static inline void init_hrtick(void) { } #endif /* CONFIG_SMP */ @@ -1121,7 +1121,7 @@ static void init_rq_hrtick(struct rq *rq) rq->hrtick_timer.function = hrtick; rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; } -#else +#else /* CONFIG_SCHED_HRTICK */ static inline void hrtick_clear(struct rq *rq) { } @@ -1133,7 +1133,7 @@ static inline void init_rq_hrtick(struct rq *rq) static inline void init_hrtick(void) { } -#endif +#endif /* CONFIG_SCHED_HRTICK */ /* * resched_task - mark a task 'to be rescheduled now'. -- cgit v1.2.3-70-g09d2 From bb34d92f643086d546b49cef680f6f305ed84414 Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang, v2 This is the second resubmission of the posix timer rework patch, posted a few days ago. This includes the changes from the previous resubmittion, which addressed Oleg Nesterov's comments, removing the RCU stuff from the patch and un-inlining the thread_group_cputime() function for SMP. In addition, per Ingo Molnar it simplifies the UP code, consolidating much of it with the SMP version and depending on lower-level SMP/UP handling to take care of the differences. It also cleans up some UP compile errors, moves the scheduler stats-related macros into kernel/sched_stats.h, cleans up a merge error in kernel/fork.c and has a few other minor fixes and cleanups as suggested by Oleg and Ingo. Thanks for the review, guys. Signed-off-by: Frank Mayhar Cc: Roland McGrath Cc: Alexey Dobriyan Cc: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/kernel_stat.h | 1 + include/linux/sched.h | 183 ++------------------------------------------ kernel/fork.c | 5 +- kernel/posix-cpu-timers.c | 153 ++++++++++++++++-------------------- kernel/sched.c | 47 ++---------- kernel/sched_stats.h | 136 ++++++++++++++++++++++++++++++++ 6 files changed, 214 insertions(+), 311 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index cf9f40a91c9..cac3750cd65 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -52,6 +52,7 @@ static inline int kstat_irqs(int irq) return sum; } +extern unsigned long long task_delta_exec(struct task_struct *); extern void account_user_time(struct task_struct *, cputime_t); extern void account_user_time_scaled(struct task_struct *, cputime_t); extern void account_system_time(struct task_struct *, int, cputime_t); diff --git a/include/linux/sched.h b/include/linux/sched.h index 7ce8d4e5356..b982fb48c8f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -454,15 +454,9 @@ struct task_cputime { * This structure contains the version of task_cputime, above, that is * used for thread group CPU clock calculations. */ -#ifdef CONFIG_SMP struct thread_group_cputime { struct task_cputime *totals; }; -#else -struct thread_group_cputime { - struct task_cputime totals; -}; -#endif /* * NOTE! "signal_struct" does not have it's own @@ -2124,193 +2118,26 @@ static inline int spin_needbreak(spinlock_t *lock) /* * Thread group CPU time accounting. */ -#ifdef CONFIG_SMP -extern int thread_group_cputime_alloc_smp(struct task_struct *); -extern void thread_group_cputime_smp(struct task_struct *, struct task_cputime *); +extern int thread_group_cputime_alloc(struct task_struct *); +extern void thread_group_cputime(struct task_struct *, struct task_cputime *); static inline void thread_group_cputime_init(struct signal_struct *sig) { sig->cputime.totals = NULL; } -static inline int thread_group_cputime_clone_thread(struct task_struct *curr, - struct task_struct *new) +static inline int thread_group_cputime_clone_thread(struct task_struct *curr) { if (curr->signal->cputime.totals) return 0; - return thread_group_cputime_alloc_smp(curr); + return thread_group_cputime_alloc(curr); } -static inline void thread_group_cputime_free(struct signal_struct *sig) -{ - free_percpu(sig->cputime.totals); -} - -/** - * thread_group_cputime - Sum the thread group time fields across all CPUs. - * - * This is a wrapper for the real routine, thread_group_cputime_smp(). See - * that routine for details. - */ -static inline void thread_group_cputime( - struct task_struct *tsk, - struct task_cputime *times) -{ - thread_group_cputime_smp(tsk, times); -} - -/** - * thread_group_cputime_account_user - Maintain utime for a thread group. - * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the utime field of that - * structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the utime field there. - */ -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - if (tgtimes->totals) { - struct task_cputime *times; - - times = per_cpu_ptr(tgtimes->totals, get_cpu()); - times->utime = cputime_add(times->utime, cputime); - put_cpu_no_resched(); - } -} - -/** - * thread_group_cputime_account_system - Maintain stime for a thread group. - * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the stime field of that - * structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the stime field there. - */ -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - if (tgtimes->totals) { - struct task_cputime *times; - - times = per_cpu_ptr(tgtimes->totals, get_cpu()); - times->stime = cputime_add(times->stime, cputime); - put_cpu_no_resched(); - } -} - -/** - * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a - * thread group. - * - * @tgtimes: Pointer to thread_group_cputime structure. - * @ns: Time value by which to increment the sum_exec_runtime field - * of that structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the sum_exec_runtime field there. - */ -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) -{ - if (tgtimes->totals) { - struct task_cputime *times; - - times = per_cpu_ptr(tgtimes->totals, get_cpu()); - times->sum_exec_runtime += ns; - put_cpu_no_resched(); - } -} - -#else /* CONFIG_SMP */ - -static inline void thread_group_cputime_init(struct signal_struct *sig) -{ - sig->cputime.totals.utime = cputime_zero; - sig->cputime.totals.stime = cputime_zero; - sig->cputime.totals.sum_exec_runtime = 0; -} - -static inline int thread_group_cputime_alloc(struct task_struct *tsk) -{ - return 0; -} static inline void thread_group_cputime_free(struct signal_struct *sig) { -} - -static inline int thread_group_cputime_clone_thread(struct task_struct *curr, - struct task_struct *tsk) -{ - return 0; -} - -static inline void thread_group_cputime(struct task_struct *tsk, - struct task_cputime *cputime) -{ - *cputime = tsk->signal->cputime.totals; -} - -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals.utime = cputime_add(tgtimes->totals.utime, cputime); -} - -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals.stime = cputime_add(tgtimes->totals.stime, cputime); -} - -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) -{ - tgtimes->totals.sum_exec_runtime += ns; -} - -#endif /* CONFIG_SMP */ - -static inline void account_group_user_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_user(&sig->cputime, cputime); -} - -static inline void account_group_system_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_system(&sig->cputime, cputime); -} - -static inline void account_group_exec_runtime(struct task_struct *tsk, - unsigned long long ns) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_exec_runtime(&sig->cputime, ns); + free_percpu(sig->cputime.totals); } /* diff --git a/kernel/fork.c b/kernel/fork.c index 1181b9aac48..021ae012cc7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -791,7 +791,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) int ret; if (clone_flags & CLONE_THREAD) { - ret = thread_group_cputime_clone_thread(current, tsk); + ret = thread_group_cputime_clone_thread(current); if (likely(!ret)) { atomic_inc(¤t->signal->count); atomic_inc(¤t->signal->live); @@ -834,9 +834,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; task_io_accounting_init(&sig->ioac); - INIT_LIST_HEAD(&sig->cpu_timers[0]); - INIT_LIST_HEAD(&sig->cpu_timers[1]); - INIT_LIST_HEAD(&sig->cpu_timers[2]); taskstats_tgid_init(sig); task_lock(current->group_leader); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 9a7ea049fcd..153dcb2639c 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -7,50 +7,46 @@ #include #include #include +#include -#ifdef CONFIG_SMP /* - * Allocate the thread_group_cputime structure appropriately for SMP kernels - * and fill in the current values of the fields. Called from copy_signal() - * via thread_group_cputime_clone_thread() when adding a second or subsequent + * Allocate the thread_group_cputime structure appropriately and fill in the + * current values of the fields. Called from copy_signal() via + * thread_group_cputime_clone_thread() when adding a second or subsequent * thread to a thread group. Assumes interrupts are enabled when called. */ -int thread_group_cputime_alloc_smp(struct task_struct *tsk) +int thread_group_cputime_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct task_cputime *cputime; /* * If we have multiple threads and we don't already have a - * per-CPU task_cputime struct, allocate one and fill it in with - * the times accumulated so far. + * per-CPU task_cputime struct (checked in the caller), allocate + * one and fill it in with the times accumulated so far. We may + * race with another thread so recheck after we pick up the sighand + * lock. */ - if (sig->cputime.totals) - return 0; cputime = alloc_percpu(struct task_cputime); if (cputime == NULL) return -ENOMEM; - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); if (sig->cputime.totals) { spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); free_percpu(cputime); return 0; } sig->cputime.totals = cputime; - cputime = per_cpu_ptr(sig->cputime.totals, get_cpu()); + cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id()); cputime->utime = tsk->utime; cputime->stime = tsk->stime; cputime->sum_exec_runtime = tsk->se.sum_exec_runtime; - put_cpu_no_resched(); spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); return 0; } /** - * thread_group_cputime_smp - Sum the thread group time fields across all CPUs. + * thread_group_cputime - Sum the thread group time fields across all CPUs. * * @tsk: The task we use to identify the thread group. * @times: task_cputime structure in which we return the summed fields. @@ -58,7 +54,7 @@ int thread_group_cputime_alloc_smp(struct task_struct *tsk) * Walk the list of CPUs to sum the per-CPU time fields in the thread group * time structure. */ -void thread_group_cputime_smp( +void thread_group_cputime( struct task_struct *tsk, struct task_cputime *times) { @@ -83,8 +79,6 @@ void thread_group_cputime_smp( } } -#endif /* CONFIG_SMP */ - /* * Called after updating RLIMIT_CPU to set timer expiration if necessary. */ @@ -300,7 +294,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, cpu->cpu = virt_ticks(p); break; case CPUCLOCK_SCHED: - cpu->sched = task_sched_runtime(p); + cpu->sched = p->se.sum_exec_runtime + task_delta_exec(p); break; } return 0; @@ -309,16 +303,15 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, /* * Sample a process (thread group) clock for the given group_leader task. * Must be called with tasklist_lock held for reading. - * Must be called with tasklist_lock held for reading, and p->sighand->siglock. */ -static int cpu_clock_sample_group_locked(unsigned int clock_idx, - struct task_struct *p, - union cpu_time_count *cpu) +static int cpu_clock_sample_group(const clockid_t which_clock, + struct task_struct *p, + union cpu_time_count *cpu) { struct task_cputime cputime; thread_group_cputime(p, &cputime); - switch (clock_idx) { + switch (which_clock) { default: return -EINVAL; case CPUCLOCK_PROF: @@ -328,29 +321,12 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx, cpu->cpu = cputime.utime; break; case CPUCLOCK_SCHED: - cpu->sched = thread_group_sched_runtime(p); + cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p); break; } return 0; } -/* - * Sample a process (thread group) clock for the given group_leader task. - * Must be called with tasklist_lock held for reading. - */ -static int cpu_clock_sample_group(const clockid_t which_clock, - struct task_struct *p, - union cpu_time_count *cpu) -{ - int ret; - unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p, - cpu); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - return ret; -} - int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) { @@ -1324,29 +1300,37 @@ static inline int task_cputime_expired(const struct task_cputime *sample, * fastpath_timer_check - POSIX CPU timers fast path. * * @tsk: The task (thread) being checked. - * @sig: The signal pointer for that task. * - * If there are no timers set return false. Otherwise snapshot the task and - * thread group timers, then compare them with the corresponding expiration - # times. Returns true if a timer has expired, else returns false. + * Check the task and thread group timers. If both are zero (there are no + * timers set) return false. Otherwise snapshot the task and thread group + * timers and compare them with the corresponding expiration times. Return + * true if a timer has expired, else return false. */ -static inline int fastpath_timer_check(struct task_struct *tsk, - struct signal_struct *sig) +static inline int fastpath_timer_check(struct task_struct *tsk) { - struct task_cputime task_sample = { - .utime = tsk->utime, - .stime = tsk->stime, - .sum_exec_runtime = tsk->se.sum_exec_runtime - }; - struct task_cputime group_sample; + struct signal_struct *sig = tsk->signal; - if (task_cputime_zero(&tsk->cputime_expires) && - task_cputime_zero(&sig->cputime_expires)) + if (unlikely(!sig)) return 0; - if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) - return 1; - thread_group_cputime(tsk, &group_sample); - return task_cputime_expired(&group_sample, &sig->cputime_expires); + + if (!task_cputime_zero(&tsk->cputime_expires)) { + struct task_cputime task_sample = { + .utime = tsk->utime, + .stime = tsk->stime, + .sum_exec_runtime = tsk->se.sum_exec_runtime + }; + + if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) + return 1; + } + if (!task_cputime_zero(&sig->cputime_expires)) { + struct task_cputime group_sample; + + thread_group_cputime(tsk, &group_sample); + if (task_cputime_expired(&group_sample, &sig->cputime_expires)) + return 1; + } + return 0; } /* @@ -1358,43 +1342,34 @@ void run_posix_cpu_timers(struct task_struct *tsk) { LIST_HEAD(firing); struct k_itimer *timer, *next; - struct signal_struct *sig; - struct sighand_struct *sighand; - unsigned long flags; BUG_ON(!irqs_disabled()); - /* Pick up tsk->signal and make sure it's valid. */ - sig = tsk->signal; /* * The fast path checks that there are no expired thread or thread - * group timers. If that's so, just return. Also check that - * tsk->signal is non-NULL; this probably can't happen but cover the - * possibility anyway. + * group timers. If that's so, just return. */ - if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) + if (!fastpath_timer_check(tsk)) return; - sighand = lock_task_sighand(tsk, &flags); - if (likely(sighand)) { - /* - * Here we take off tsk->signal->cpu_timers[N] and - * tsk->cpu_timers[N] all the timers that are firing, and - * put them on the firing list. - */ - check_thread_timers(tsk, &firing); - check_process_timers(tsk, &firing); + spin_lock(&tsk->sighand->siglock); + /* + * Here we take off tsk->signal->cpu_timers[N] and + * tsk->cpu_timers[N] all the timers that are firing, and + * put them on the firing list. + */ + check_thread_timers(tsk, &firing); + check_process_timers(tsk, &firing); - /* - * We must release these locks before taking any timer's lock. - * There is a potential race with timer deletion here, as the - * siglock now protects our private firing list. We have set - * the firing flag in each timer, so that a deletion attempt - * that gets the timer lock before we do will give it up and - * spin until we've taken care of that timer below. - */ - } - unlock_task_sighand(tsk, &flags); + /* + * We must release these locks before taking any timer's lock. + * There is a potential race with timer deletion here, as the + * siglock now protects our private firing list. We have set + * the firing flag in each timer, so that a deletion attempt + * that gets the timer lock before we do will give it up and + * spin until we've taken care of that timer below. + */ + spin_unlock(&tsk->sighand->siglock); /* * Now that all the timers on our list have the firing flag, @@ -1433,7 +1408,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, struct list_head *head; BUG_ON(clock_idx == CPUCLOCK_SCHED); - cpu_clock_sample_group_locked(clock_idx, tsk, &now); + cpu_clock_sample_group(clock_idx, tsk, &now); if (oldval) { if (!cputime_eq(*oldval, cputime_zero)) { diff --git a/kernel/sched.c b/kernel/sched.c index c51b5d27666..260c22cc530 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4039,55 +4039,22 @@ EXPORT_PER_CPU_SYMBOL(kstat); /* * Return any ns on the sched_clock that have not yet been banked in * @p in case that task is currently running. - * - * Called with task_rq_lock() held on @rq. */ -static unsigned long long task_delta_exec(struct task_struct *p, struct rq *rq) +unsigned long long task_delta_exec(struct task_struct *p) { + struct rq *rq; + unsigned long flags; + u64 ns = 0; + + rq = task_rq_lock(p, &flags); if (task_current(rq, p)) { u64 delta_exec; update_rq_clock(rq); delta_exec = rq->clock - p->se.exec_start; if ((s64)delta_exec > 0) - return delta_exec; + ns = delta_exec; } - return 0; -} - -/* - * Return p->sum_exec_runtime plus any more ns on the sched_clock - * that have not yet been banked in case the task is currently running. - */ -unsigned long long task_sched_runtime(struct task_struct *p) -{ - unsigned long flags; - u64 ns; - struct rq *rq; - - rq = task_rq_lock(p, &flags); - ns = p->se.sum_exec_runtime + task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); - - return ns; -} - -/* - * Return sum_exec_runtime for the thread group plus any more ns on the - * sched_clock that have not yet been banked in case the task is currently - * running. - */ -unsigned long long thread_group_sched_runtime(struct task_struct *p) -{ - unsigned long flags; - u64 ns; - struct rq *rq; - struct task_cputime totals; - - rq = task_rq_lock(p, &flags); - thread_group_cputime(p, &totals); - ns = totals.sum_exec_runtime + task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); return ns; } diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 8385d43987e..d6903bd0c7a 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -270,3 +270,139 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) #define sched_info_switch(t, next) do { } while (0) #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */ +/* + * The following are functions that support scheduler-internal time accounting. + * These functions are generally called at the timer tick. None of this depends + * on CONFIG_SCHEDSTATS. + */ + +#ifdef CONFIG_SMP + +/** + * thread_group_cputime_account_user - Maintain utime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the utime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->utime = cputime_add(times->utime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_system - Maintain stime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the stime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->stime = cputime_add(times->stime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a + * thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of that structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->sum_exec_runtime += ns; + put_cpu_no_resched(); + } +} + +#else /* CONFIG_SMP */ + +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); +} + +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); +} + +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + tgtimes->totals->sum_exec_runtime += ns; +} + +#endif /* CONFIG_SMP */ + +/* + * These are the generic time-accounting routines that use the above + * functions. They are the functions actually called by the scheduler. + */ +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_user(&sig->cputime, cputime); +} + +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_system(&sig->cputime, cputime); +} + +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_exec_runtime(&sig->cputime, ns); +} -- cgit v1.2.3-70-g09d2 From 4653f803e6e0d970ffeac0efd2c01743eb6c5228 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 23 Sep 2008 15:33:44 +0200 Subject: sched: more sanity checks on the bandwidth settings While playing around with it, I noticed we missed some sanity checks. Also add some comments while we're there. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 669c49aa57f..e1299de1765 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8866,11 +8866,29 @@ static int tg_schedulable(struct task_group *tg, void *data) runtime = d->rt_runtime; } + /* + * Cannot have more runtime than the period. + */ + if (runtime > period && runtime != RUNTIME_INF) + return -EINVAL; + + /* + * Ensure we don't starve existing RT tasks. + */ if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) return -EBUSY; total = to_ratio(period, runtime); + /* + * Nobody can have more than the global setting allows. + */ + if (total > to_ratio(global_rt_period(), global_rt_runtime())) + return -EINVAL; + + /* + * The sum of our children's runtime should not exceed our own. + */ list_for_each_entry_rcu(child, &tg->children, siblings) { period = ktime_to_ns(child->rt_bandwidth.rt_period); runtime = child->rt_bandwidth.rt_runtime; @@ -8978,19 +8996,24 @@ long sched_group_rt_period(struct task_group *tg) static int sched_rt_global_constraints(void) { - struct task_group *tg = &root_task_group; - u64 rt_runtime, rt_period; + u64 runtime, period; int ret = 0; if (sysctl_sched_rt_period <= 0) return -EINVAL; - rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); - rt_runtime = tg->rt_bandwidth.rt_runtime; + runtime = global_rt_runtime(); + period = global_rt_period(); + + /* + * Sanity check on the sysctl variables. + */ + if (runtime > period && runtime != RUNTIME_INF) + return -EINVAL; mutex_lock(&rt_constraints_mutex); read_lock(&tasklist_lock); - ret = __rt_schedulable(tg, rt_period, rt_runtime); + ret = __rt_schedulable(NULL, 0, 0); read_unlock(&tasklist_lock); mutex_unlock(&rt_constraints_mutex); -- cgit v1.2.3-70-g09d2 From 7086efe1c1536f6bc160e7d60a9bfd645b91f279 Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang, v3 - fix UP lockup - another set of UP/SMP cleanups and simplifications Signed-off-by: Frank Mayhar Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - kernel/sched.c | 1 - kernel/sched_stats.h | 126 +++++++++++++++----------------------------------- 3 files changed, 38 insertions(+), 90 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index b982fb48c8f..23d9d546454 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2134,7 +2134,6 @@ static inline int thread_group_cputime_clone_thread(struct task_struct *curr) return thread_group_cputime_alloc(curr); } - static inline void thread_group_cputime_free(struct signal_struct *sig) { free_percpu(sig->cputime.totals); diff --git a/kernel/sched.c b/kernel/sched.c index 260c22cc530..29a3152c45d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4046,7 +4046,6 @@ unsigned long long task_delta_exec(struct task_struct *p) unsigned long flags; u64 ns = 0; - rq = task_rq_lock(p, &flags); if (task_current(rq, p)) { u64 delta_exec; diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index d6903bd0c7a..b8c156979cf 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -276,133 +276,83 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) * on CONFIG_SCHEDSTATS. */ -#ifdef CONFIG_SMP - /** - * thread_group_cputime_account_user - Maintain utime for a thread group. + * account_group_user_time - Maintain utime for a thread group. * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the utime field of that - * structure. + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the utime field of the + * thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the utime field there. */ -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) { - if (tgtimes->totals) { + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { struct task_cputime *times; - times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); times->utime = cputime_add(times->utime, cputime); put_cpu_no_resched(); } } /** - * thread_group_cputime_account_system - Maintain stime for a thread group. + * account_group_system_time - Maintain stime for a thread group. * - * @tgtimes: Pointer to thread_group_cputime structure. - * @cputime: Time value by which to increment the stime field of that - * structure. + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the stime field of the + * thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the stime field there. */ -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) { - if (tgtimes->totals) { + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { struct task_cputime *times; - times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); times->stime = cputime_add(times->stime, cputime); put_cpu_no_resched(); } } /** - * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a - * thread group. + * account_group_exec_runtime - Maintain exec runtime for a thread group. * - * @tgtimes: Pointer to thread_group_cputime structure. + * @tsk: Pointer to task structure. * @ns: Time value by which to increment the sum_exec_runtime field - * of that structure. + * of the thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the sum_exec_runtime field there. */ -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) { - if (tgtimes->totals) { + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { struct task_cputime *times; - times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); times->sum_exec_runtime += ns; put_cpu_no_resched(); } } - -#else /* CONFIG_SMP */ - -static inline void thread_group_cputime_account_user( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); -} - -static inline void thread_group_cputime_account_system( - struct thread_group_cputime *tgtimes, - cputime_t cputime) -{ - tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); -} - -static inline void thread_group_cputime_account_exec_runtime( - struct thread_group_cputime *tgtimes, - unsigned long long ns) -{ - tgtimes->totals->sum_exec_runtime += ns; -} - -#endif /* CONFIG_SMP */ - -/* - * These are the generic time-accounting routines that use the above - * functions. They are the functions actually called by the scheduler. - */ -static inline void account_group_user_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_user(&sig->cputime, cputime); -} - -static inline void account_group_system_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_system(&sig->cputime, cputime); -} - -static inline void account_group_exec_runtime(struct task_struct *tsk, - unsigned long long ns) -{ - struct signal_struct *sig; - - sig = tsk->signal; - if (likely(sig)) - thread_group_cputime_account_exec_runtime(&sig->cputime, ns); -} -- cgit v1.2.3-70-g09d2 From 1508487e7f16d992ad23cabd3712563ff912f413 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 30 Sep 2008 08:28:17 +0200 Subject: timers: fix itimer/many thread hang, fix fix bogus rq dereference: v3 removed the locking but also removed the rq initialization. Signed-off-by: Ingo Molnar --- kernel/sched.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 29a3152c45d..ebb03def564 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4042,10 +4042,12 @@ EXPORT_PER_CPU_SYMBOL(kstat); */ unsigned long long task_delta_exec(struct task_struct *p) { - struct rq *rq; unsigned long flags; + struct rq *rq; u64 ns = 0; + rq = task_rq_lock(p, &flags); + if (task_current(rq, p)) { u64 delta_exec; @@ -4055,6 +4057,8 @@ unsigned long long task_delta_exec(struct task_struct *p) ns = delta_exec; } + task_rq_unlock(rq, &flags); + return ns; } -- cgit v1.2.3-70-g09d2 From 34b3ede2353604ec9861c1d900b2a835ff85de47 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 6 Oct 2008 09:27:00 +0800 Subject: sched: remove redundant code in cpu_cgroup_create() css will be initialized by cgroup core. Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 2caedc47e76..9715f4ce6cf 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -9088,7 +9088,6 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) if (!cgrp->parent) { /* This is early initialization for the top cgroup */ - init_task_group.css.cgroup = cgrp; return &init_task_group.css; } @@ -9097,9 +9096,6 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) if (IS_ERR(tg)) return ERR_PTR(-ENOMEM); - /* Bind the cgroup to task_group object we just created */ - tg->css.cgroup = cgrp; - return &tg->css; } -- cgit v1.2.3-70-g09d2 From a5d8c3483a6e19aca95ef6a2c5890e33bfa5b293 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 9 Oct 2008 11:35:51 +0200 Subject: sched debug: add name to sched_domain sysctl entries add /proc/sys/kernel/sched_domain/cpu0/domain0/name, to make it easier to see which specific scheduler domain remained at that entry. Since we process the scheduler domain tree and simplify it, it's not always immediately clear during debugging which domain came from where. depends on CONFIG_SCHED_DEBUG=y. Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +++ kernel/sched.c | 14 ++++++++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index d8e699b5585..5d0819ee442 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -824,6 +824,9 @@ struct sched_domain { unsigned int ttwu_move_affine; unsigned int ttwu_move_balance; #endif +#ifdef CONFIG_SCHED_DEBUG + char *name; +#endif }; extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new, diff --git a/kernel/sched.c b/kernel/sched.c index 9715f4ce6cf..6f230596bd0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6351,7 +6351,7 @@ set_table_entry(struct ctl_table *entry, static struct ctl_table * sd_alloc_ctl_domain_table(struct sched_domain *sd) { - struct ctl_table *table = sd_alloc_ctl_entry(12); + struct ctl_table *table = sd_alloc_ctl_entry(13); if (table == NULL) return NULL; @@ -6379,7 +6379,9 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) sizeof(int), 0644, proc_dointvec_minmax); set_table_entry(&table[10], "flags", &sd->flags, sizeof(int), 0644, proc_dointvec_minmax); - /* &table[11] is terminator */ + set_table_entry(&table[11], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring); + /* &table[12] is terminator */ return table; } @@ -7263,13 +7265,21 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) * Non-inlined to reduce accumulated stack pressure in build_sched_domains() */ +#ifdef CONFIG_SCHED_DEBUG +# define SD_INIT_NAME(sd, type) sd->name = #type +#else +# define SD_INIT_NAME(sd, type) do { } while (0) +#endif + #define SD_INIT(sd, type) sd_init_##type(sd) + #define SD_INIT_FUNC(type) \ static noinline void sd_init_##type(struct sched_domain *sd) \ { \ memset(sd, 0, sizeof(*sd)); \ *sd = SD_##type##_INIT; \ sd->level = SD_LV_##type; \ + SD_INIT_NAME(sd, type); \ } SD_INIT_FUNC(CPU) -- cgit v1.2.3-70-g09d2 From 0a16b6075843325dc402edf80c1662838b929aff Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 18 Jul 2008 12:16:17 -0400 Subject: tracing, sched: LTTng instrumentation - scheduler Instrument the scheduler activity (sched_switch, migration, wakeups, wait for a task, signal delivery) and process/thread creation/destruction (fork, exit, kthread stop). Actually, kthread creation is not instrumented in this patch because it is architecture dependent. It allows to connect tracers such as ftrace which detects scheduling latencies, good/bad scheduler decisions. Tools like LTTng can export this scheduler information along with instrumentation of the rest of the kernel activity to perform post-mortem analysis on the scheduler activity. About the performance impact of tracepoints (which is comparable to markers), even without immediate values optimizations, tests done by Hideo Aoki on ia64 show no regression. His test case was using hackbench on a kernel where scheduler instrumentation (about 5 events in code scheduler code) was added. See the "Tracepoints" patch header for performance result detail. Changelog : - Change instrumentation location and parameter to match ftrace instrumentation, previously done with kernel markers. [ mingo@elte.hu: conflict resolutions ] Signed-off-by: Mathieu Desnoyers Acked-by: 'Peter Zijlstra' Signed-off-by: Ingo Molnar --- include/trace/sched.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ kernel/exit.c | 10 +++++++++- kernel/fork.c | 3 +++ kernel/kthread.c | 5 +++++ kernel/sched.c | 17 ++++++----------- kernel/signal.c | 3 +++ 6 files changed, 71 insertions(+), 12 deletions(-) create mode 100644 include/trace/sched.h (limited to 'kernel/sched.c') diff --git a/include/trace/sched.h b/include/trace/sched.h new file mode 100644 index 00000000000..506ae132365 --- /dev/null +++ b/include/trace/sched.h @@ -0,0 +1,45 @@ +#ifndef _TRACE_SCHED_H +#define _TRACE_SCHED_H + +#include +#include + +DEFINE_TRACE(sched_kthread_stop, + TPPROTO(struct task_struct *t), + TPARGS(t)); +DEFINE_TRACE(sched_kthread_stop_ret, + TPPROTO(int ret), + TPARGS(ret)); +DEFINE_TRACE(sched_wait_task, + TPPROTO(struct rq *rq, struct task_struct *p), + TPARGS(rq, p)); +DEFINE_TRACE(sched_wakeup, + TPPROTO(struct rq *rq, struct task_struct *p), + TPARGS(rq, p)); +DEFINE_TRACE(sched_wakeup_new, + TPPROTO(struct rq *rq, struct task_struct *p), + TPARGS(rq, p)); +DEFINE_TRACE(sched_switch, + TPPROTO(struct rq *rq, struct task_struct *prev, + struct task_struct *next), + TPARGS(rq, prev, next)); +DEFINE_TRACE(sched_migrate_task, + TPPROTO(struct rq *rq, struct task_struct *p, int dest_cpu), + TPARGS(rq, p, dest_cpu)); +DEFINE_TRACE(sched_process_free, + TPPROTO(struct task_struct *p), + TPARGS(p)); +DEFINE_TRACE(sched_process_exit, + TPPROTO(struct task_struct *p), + TPARGS(p)); +DEFINE_TRACE(sched_process_wait, + TPPROTO(struct pid *pid), + TPARGS(pid)); +DEFINE_TRACE(sched_process_fork, + TPPROTO(struct task_struct *parent, struct task_struct *child), + TPARGS(parent, child)); +DEFINE_TRACE(sched_signal_send, + TPPROTO(int sig, struct task_struct *p), + TPARGS(sig, p)); + +#endif diff --git a/kernel/exit.c b/kernel/exit.c index 85a83c83185..7b71f87f120 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -149,7 +150,10 @@ static void __exit_signal(struct task_struct *tsk) static void delayed_put_task_struct(struct rcu_head *rhp) { - put_task_struct(container_of(rhp, struct task_struct, rcu)); + struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); + + trace_sched_process_free(tsk); + put_task_struct(tsk); } @@ -1074,6 +1078,8 @@ NORET_TYPE void do_exit(long code) if (group_dead) acct_process(); + trace_sched_process_exit(tsk); + exit_sem(tsk); exit_files(tsk); exit_fs(tsk); @@ -1675,6 +1681,8 @@ static long do_wait(enum pid_type type, struct pid *pid, int options, struct task_struct *tsk; int retval; + trace_sched_process_wait(pid); + add_wait_queue(¤t->signal->wait_chldexit,&wait); repeat: /* diff --git a/kernel/fork.c b/kernel/fork.c index 30de644a40c..cfaff92f61f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -58,6 +58,7 @@ #include #include #include +#include #include #include @@ -1364,6 +1365,8 @@ long do_fork(unsigned long clone_flags, if (!IS_ERR(p)) { struct completion vfork; + trace_sched_process_fork(current, p); + nr = task_pid_vnr(p); if (clone_flags & CLONE_PARENT_SETTID) diff --git a/kernel/kthread.c b/kernel/kthread.c index 96cff2f8710..50598e29439 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -13,6 +13,7 @@ #include #include #include +#include #define KTHREAD_NICE_LEVEL (-5) @@ -206,6 +207,8 @@ int kthread_stop(struct task_struct *k) /* It could exit after stop_info.k set, but before wake_up_process. */ get_task_struct(k); + trace_sched_kthread_stop(k); + /* Must init completion *before* thread sees kthread_stop_info.k */ init_completion(&kthread_stop_info.done); smp_wmb(); @@ -221,6 +224,8 @@ int kthread_stop(struct task_struct *k) ret = kthread_stop_info.err; mutex_unlock(&kthread_stop_lock); + trace_sched_kthread_stop_ret(ret); + return ret; } EXPORT_SYMBOL(kthread_stop); diff --git a/kernel/sched.c b/kernel/sched.c index 6f230596bd0..3d1ad130c24 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -71,6 +71,7 @@ #include #include #include +#include #include #include @@ -1936,6 +1937,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * just go back and repeat. */ rq = task_rq_lock(p, &flags); + trace_sched_wait_task(rq, p); running = task_running(rq, p); on_rq = p->se.on_rq; ncsw = 0; @@ -2297,9 +2299,7 @@ out_activate: success = 1; out_running: - trace_mark(kernel_sched_wakeup, - "pid %d state %ld ## rq %p task %p rq->curr %p", - p->pid, p->state, rq, p, rq->curr); + trace_sched_wakeup(rq, p); check_preempt_curr(rq, p, sync); p->state = TASK_RUNNING; @@ -2432,9 +2432,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) p->sched_class->task_new(rq, p); inc_nr_running(rq); } - trace_mark(kernel_sched_wakeup_new, - "pid %d state %ld ## rq %p task %p rq->curr %p", - p->pid, p->state, rq, p, rq->curr); + trace_sched_wakeup_new(rq, p); check_preempt_curr(rq, p, 0); #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) @@ -2607,11 +2605,7 @@ context_switch(struct rq *rq, struct task_struct *prev, struct mm_struct *mm, *oldmm; prepare_task_switch(rq, prev, next); - trace_mark(kernel_sched_schedule, - "prev_pid %d next_pid %d prev_state %ld " - "## rq %p prev %p next %p", - prev->pid, next->pid, prev->state, - rq, prev, next); + trace_sched_switch(rq, prev, next); mm = next->mm; oldmm = prev->active_mm; /* @@ -2851,6 +2845,7 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu) || unlikely(!cpu_active(dest_cpu))) goto out; + trace_sched_migrate_task(rq, p, dest_cpu); /* force the process onto the specified CPU */ if (migrate_task(p, dest_cpu, &req)) { /* Need to wait for migration thread (might exit: take ref). */ diff --git a/kernel/signal.c b/kernel/signal.c index e661b01d340..bf40ecc87b2 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -803,6 +804,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, struct sigpending *pending; struct sigqueue *q; + trace_sched_signal_send(sig, t); + assert_spin_locked(&t->sighand->siglock); if (!prepare_signal(sig, t)) return 0; -- cgit v1.2.3-70-g09d2