From e5c1902e9260a0075ea52cb5ef627a8d9aaede89 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 23 Mar 2011 10:37:00 +0100 Subject: signal: Fix premature completion of group stop when interfered by ptrace task->signal->group_stop_count is used to track the progress of group stop. It's initialized to the number of tasks which need to stop for group stop to finish and each stopping or trapping task decrements. However, each task doesn't keep track of whether it decremented the counter or not and if woken up before the group stop is complete and stops again, it can decrement the counter multiple times. Please consider the following example code. static void *worker(void *arg) { while (1) ; return NULL; } int main(void) { pthread_t thread; pid_t pid; int i; pid = fork(); if (!pid) { for (i = 0; i < 5; i++) pthread_create(&thread, NULL, worker, NULL); while (1) ; return 0; } ptrace(PTRACE_ATTACH, pid, NULL, NULL); while (1) { waitid(P_PID, pid, NULL, WSTOPPED); ptrace(PTRACE_SINGLESTEP, pid, NULL, (void *)(long)SIGSTOP); } return 0; } The child creates five threads and the parent continuously traps the first thread and whenever the child gets a signal, SIGSTOP is delivered. If an external process sends SIGSTOP to the child, all other threads in the process should reliably stop. However, due to the above bug, the first thread will often end up consuming group_stop_count multiple times and SIGSTOP often ends up stopping none or part of the other four threads. This patch adds a new field task->group_stop which is protected by siglock and uses GROUP_STOP_CONSUME flag to track which task is still to consume group_stop_count to fix this bug. task_clear_group_stop_pending() and task_participate_group_stop() are added to help manipulating group stop states. As ptrace_stop() now also uses task_participate_group_stop(), it will set SIGNAL_STOP_STOPPED if it completes a group stop. There still are many issues regarding the interaction between group stop and ptrace. Patches to address them will follow. - Oleg spotted duplicate GROUP_STOP_CONSUME. Dropped. Signed-off-by: Tejun Heo Acked-by: Oleg Nesterov Cc: Roland McGrath --- include/linux/sched.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4b601be3dac..85f51042c2b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1260,6 +1260,7 @@ struct task_struct { int exit_state; int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ + unsigned int group_stop; /* GROUP_STOP_*, siglock protected */ /* ??? */ unsigned int personality; unsigned did_exec:1; @@ -1771,6 +1772,11 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) +/* + * task->group_stop flags + */ +#define GROUP_STOP_CONSUME (1 << 17) /* consume group stop count */ + #ifdef CONFIG_PREEMPT_RCU #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ -- cgit v1.2.3-70-g09d2 From 39efa3ef3a376a4e53de2f82fc91182459d34200 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 23 Mar 2011 10:37:00 +0100 Subject: signal: Use GROUP_STOP_PENDING to stop once for a single group stop Currently task->signal->group_stop_count is used to decide whether to stop for group stop. However, if there is a task in the group which is taking a long time to stop, other tasks which are continued by ptrace would repeatedly stop for the same group stop until the group stop is complete. Conversely, if a ptraced task is in TASK_TRACED state, the debugger won't get notified of group stops which is inconsistent compared to the ptraced task in any other state. This patch introduces GROUP_STOP_PENDING which tracks whether a task is yet to stop for the group stop in progress. The flag is set when a group stop starts and cleared when the task stops the first time for the group stop, and consulted whenever whether the task should participate in a group stop needs to be determined. Note that now tasks in TASK_TRACED also participate in group stop. This results in the following behavior changes. * For a single group stop, a ptracer would see at most one stop reported. * A ptracee in TASK_TRACED now also participates in group stop and the tracer would get the notification. However, as a ptraced task could be in TASK_STOPPED state or any ptrace trap could consume group stop, the notification may still be missing. These will be addressed with further patches. * A ptracee may start a group stop while one is still in progress if the tracer let it continue with stop signal delivery. Group stop code handles this correctly. Oleg: * Spotted that a task might skip signal check even when its GROUP_STOP_PENDING is set. Fixed by updating recalc_sigpending_tsk() to check GROUP_STOP_PENDING instead of group_stop_count. * Pointed out that task->group_stop should be cleared whenever task->signal->group_stop_count is cleared. Fixed accordingly. * Pointed out the behavior inconsistency between TASK_TRACED and RUNNING and the last behavior change. Signed-off-by: Tejun Heo Acked-by: Oleg Nesterov Cc: Roland McGrath --- fs/exec.c | 1 + include/linux/sched.h | 3 +++ kernel/signal.c | 36 +++++++++++++++++++++--------------- 3 files changed, 25 insertions(+), 15 deletions(-) (limited to 'include/linux/sched.h') diff --git a/fs/exec.c b/fs/exec.c index 5e62d26a4fe..8328beb9016 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1659,6 +1659,7 @@ static int zap_process(struct task_struct *start, int exit_code) t = start; do { + task_clear_group_stop_pending(t); if (t != current && t->mm) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); diff --git a/include/linux/sched.h b/include/linux/sched.h index 85f51042c2b..b2a17dfbdba 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1775,8 +1775,11 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * /* * task->group_stop flags */ +#define GROUP_STOP_PENDING (1 << 16) /* task should stop for group stop */ #define GROUP_STOP_CONSUME (1 << 17) /* consume group stop count */ +extern void task_clear_group_stop_pending(struct task_struct *task); + #ifdef CONFIG_PREEMPT_RCU #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ diff --git a/kernel/signal.c b/kernel/signal.c index ecb20089eaf..a2e7a6527d2 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -124,7 +124,7 @@ static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked) static int recalc_sigpending_tsk(struct task_struct *t) { - if (t->signal->group_stop_count > 0 || + if ((t->group_stop & GROUP_STOP_PENDING) || PENDING(&t->pending, &t->blocked) || PENDING(&t->signal->shared_pending, &t->blocked)) { set_tsk_thread_flag(t, TIF_SIGPENDING); @@ -232,19 +232,19 @@ static inline void print_dropped_signal(int sig) * CONTEXT: * Must be called with @task->sighand->siglock held. */ -static void task_clear_group_stop_pending(struct task_struct *task) +void task_clear_group_stop_pending(struct task_struct *task) { - task->group_stop &= ~GROUP_STOP_CONSUME; + task->group_stop &= ~(GROUP_STOP_PENDING | GROUP_STOP_CONSUME); } /** * task_participate_group_stop - participate in a group stop * @task: task participating in a group stop * - * @task is participating in a group stop. Group stop states are cleared - * and the group stop count is consumed if %GROUP_STOP_CONSUME was set. If - * the consumption completes the group stop, the appropriate %SIGNAL_* - * flags are set. + * @task has GROUP_STOP_PENDING set and is participating in a group stop. + * Group stop states are cleared and the group stop count is consumed if + * %GROUP_STOP_CONSUME was set. If the consumption completes the group + * stop, the appropriate %SIGNAL_* flags are set. * * CONTEXT: * Must be called with @task->sighand->siglock held. @@ -254,6 +254,8 @@ static bool task_participate_group_stop(struct task_struct *task) struct signal_struct *sig = task->signal; bool consume = task->group_stop & GROUP_STOP_CONSUME; + WARN_ON_ONCE(!(task->group_stop & GROUP_STOP_PENDING)); + task_clear_group_stop_pending(task); if (!consume) @@ -765,6 +767,9 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns) t = p; do { unsigned int state; + + task_clear_group_stop_pending(t); + rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending); /* * If there is a handler for SIGCONT, we must make @@ -906,6 +911,7 @@ static void complete_signal(int sig, struct task_struct *p, int group) signal->group_stop_count = 0; t = p; do { + task_clear_group_stop_pending(t); sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); } while_each_thread(p, t); @@ -1139,6 +1145,7 @@ int zap_other_threads(struct task_struct *p) p->signal->group_stop_count = 0; while_each_thread(p, t) { + task_clear_group_stop_pending(t); count++; /* Don't bother with already dead threads */ @@ -1690,7 +1697,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) * If there is a group stop in progress, * we must participate in the bookkeeping. */ - if (current->signal->group_stop_count > 0) + if (current->group_stop & GROUP_STOP_PENDING) task_participate_group_stop(current); current->last_siginfo = info; @@ -1775,8 +1782,8 @@ static int do_signal_stop(int signr) struct signal_struct *sig = current->signal; int notify = 0; - if (!sig->group_stop_count) { - unsigned int gstop = GROUP_STOP_CONSUME; + if (!(current->group_stop & GROUP_STOP_PENDING)) { + unsigned int gstop = GROUP_STOP_PENDING | GROUP_STOP_CONSUME; struct task_struct *t; if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) || @@ -1796,8 +1803,7 @@ static int do_signal_stop(int signr) * stop is always done with the siglock held, * so this check has no races. */ - if (!(t->flags & PF_EXITING) && - !task_is_stopped_or_traced(t)) { + if (!(t->flags & PF_EXITING) && !task_is_stopped(t)) { t->group_stop = gstop; sig->group_stop_count++; signal_wake_up(t, 0); @@ -1926,8 +1932,8 @@ relock: if (unlikely(signr != 0)) ka = return_ka; else { - if (unlikely(signal->group_stop_count > 0) && - do_signal_stop(0)) + if (unlikely(current->group_stop & + GROUP_STOP_PENDING) && do_signal_stop(0)) goto relock; signr = dequeue_signal(current, ¤t->blocked, @@ -2073,7 +2079,7 @@ void exit_signals(struct task_struct *tsk) if (!signal_pending(t) && !(t->flags & PF_EXITING)) recalc_sigpending_and_wake(t); - if (unlikely(tsk->signal->group_stop_count) && + if (unlikely(tsk->group_stop & GROUP_STOP_PENDING) && task_participate_group_stop(tsk)) group_stop = CLD_STOPPED; out: -- cgit v1.2.3-70-g09d2 From d79fdd6d96f46fabb779d86332e3677c6f5c2a4f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 23 Mar 2011 10:37:00 +0100 Subject: ptrace: Clean transitions between TASK_STOPPED and TRACED Currently, if the task is STOPPED on ptrace attach, it's left alone and the state is silently changed to TRACED on the next ptrace call. The behavior breaks the assumption that arch_ptrace_stop() is called before any task is poked by ptrace and is ugly in that a task manipulates the state of another task directly. With GROUP_STOP_PENDING, the transitions between TASK_STOPPED and TRACED can be made clean. The tracer can use the flag to tell the tracee to retry stop on attach and detach. On retry, the tracee will enter the desired state in the correct way. The lower 16bits of task->group_stop is used to remember the signal number which caused the last group stop. This is used while retrying for ptrace attach as the original group_exit_code could have been consumed with wait(2) by then. As the real parent may wait(2) and consume the group_exit_code anytime, the group_exit_code needs to be saved separately so that it can be used when switching from regular sleep to ptrace_stop(). This is recorded in the lower 16bits of task->group_stop. If a task is already stopped and there's no intervening SIGCONT, a ptrace request immediately following a successful PTRACE_ATTACH should always succeed even if the tracer doesn't wait(2) for attach completion; however, with this change, the tracee might still be TASK_RUNNING trying to enter TASK_TRACED which would cause the following request to fail with -ESRCH. This intermediate state is hidden from the ptracer by setting GROUP_STOP_TRAPPING on attach and making ptrace_check_attach() wait for it to clear on its signal->wait_chldexit. Completing the transition or getting killed clears TRAPPING and wakes up the tracer. Note that the STOPPED -> RUNNING -> TRACED transition is still visible to other threads which are in the same group as the ptracer and the reverse transition is visible to all. Please read the comments for details. Oleg: * Spotted a race condition where a task may retry group stop without proper bookkeeping. Fixed by redoing bookkeeping on retry. * Spotted that the transition is visible to userland in several different ways. Most are fixed with GROUP_STOP_TRAPPING. Unhandled corner case is documented. * Pointed out not setting GROUP_STOP_SIGMASK on an already stopped task would result in more consistent behavior. * Pointed out that calling ptrace_stop() from do_signal_stop() in TASK_STOPPED can race with group stop start logic and then confuse the TRAPPING wait in ptrace_check_attach(). ptrace_stop() is now called with TASK_RUNNING. * Suggested using signal->wait_chldexit instead of bit wait. * Spotted a race condition between TRACED transition and clearing of TRAPPING. Signed-off-by: Tejun Heo Acked-by: Oleg Nesterov Cc: Roland McGrath Cc: Jan Kratochvil --- include/linux/sched.h | 2 ++ kernel/ptrace.c | 49 ++++++++++++++++++++++++++++---- kernel/signal.c | 79 ++++++++++++++++++++++++++++++++++++++++++--------- 3 files changed, 112 insertions(+), 18 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index b2a17dfbdba..456d80ed3b7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1775,8 +1775,10 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * /* * task->group_stop flags */ +#define GROUP_STOP_SIGMASK 0xffff /* signr of the last group stop */ #define GROUP_STOP_PENDING (1 << 16) /* task should stop for group stop */ #define GROUP_STOP_CONSUME (1 << 17) /* consume group stop count */ +#define GROUP_STOP_TRAPPING (1 << 18) /* switching from STOPPED to TRACED */ extern void task_clear_group_stop_pending(struct task_struct *task); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 6acf8954017..745fc2dd00c 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -49,14 +49,22 @@ static void ptrace_untrace(struct task_struct *child) spin_lock(&child->sighand->siglock); if (task_is_traced(child)) { /* - * If the group stop is completed or in progress, - * this thread was already counted as stopped. + * If group stop is completed or in progress, it should + * participate in the group stop. Set GROUP_STOP_PENDING + * before kicking it. + * + * This involves TRACED -> RUNNING -> STOPPED transition + * which is similar to but in the opposite direction of + * what happens while attaching to a stopped task. + * However, in this direction, the intermediate RUNNING + * state is not hidden even from the current ptracer and if + * it immediately re-attaches and performs a WNOHANG + * wait(2), it may fail. */ if (child->signal->flags & SIGNAL_STOP_STOPPED || child->signal->group_stop_count) - __set_task_state(child, TASK_STOPPED); - else - signal_wake_up(child, 1); + child->group_stop |= GROUP_STOP_PENDING; + signal_wake_up(child, 1); } spin_unlock(&child->sighand->siglock); } @@ -165,6 +173,7 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode) static int ptrace_attach(struct task_struct *task) { + bool wait_trap = false; int retval; audit_ptrace(task); @@ -204,12 +213,42 @@ static int ptrace_attach(struct task_struct *task) __ptrace_link(task, current); send_sig_info(SIGSTOP, SEND_SIG_FORCED, task); + spin_lock(&task->sighand->siglock); + + /* + * If the task is already STOPPED, set GROUP_STOP_PENDING and + * TRAPPING, and kick it so that it transits to TRACED. TRAPPING + * will be cleared if the child completes the transition or any + * event which clears the group stop states happens. We'll wait + * for the transition to complete before returning from this + * function. + * + * This hides STOPPED -> RUNNING -> TRACED transition from the + * attaching thread but a different thread in the same group can + * still observe the transient RUNNING state. IOW, if another + * thread's WNOHANG wait(2) on the stopped tracee races against + * ATTACH, the wait(2) may fail due to the transient RUNNING. + * + * The following task_is_stopped() test is safe as both transitions + * in and out of STOPPED are protected by siglock. + */ + if (task_is_stopped(task)) { + task->group_stop |= GROUP_STOP_PENDING | GROUP_STOP_TRAPPING; + signal_wake_up(task, 1); + wait_trap = true; + } + + spin_unlock(&task->sighand->siglock); + retval = 0; unlock_tasklist: write_unlock_irq(&tasklist_lock); unlock_creds: mutex_unlock(&task->signal->cred_guard_mutex); out: + if (wait_trap) + wait_event(current->signal->wait_chldexit, + !(task->group_stop & GROUP_STOP_TRAPPING)); return retval; } diff --git a/kernel/signal.c b/kernel/signal.c index 418776c41d2..1e199919ae0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -223,6 +223,26 @@ static inline void print_dropped_signal(int sig) current->comm, current->pid, sig); } +/** + * task_clear_group_stop_trapping - clear group stop trapping bit + * @task: target task + * + * If GROUP_STOP_TRAPPING is set, a ptracer is waiting for us. Clear it + * and wake up the ptracer. Note that we don't need any further locking. + * @task->siglock guarantees that @task->parent points to the ptracer. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + */ +static void task_clear_group_stop_trapping(struct task_struct *task) +{ + if (unlikely(task->group_stop & GROUP_STOP_TRAPPING)) { + task->group_stop &= ~GROUP_STOP_TRAPPING; + __wake_up_sync(&task->parent->signal->wait_chldexit, + TASK_UNINTERRUPTIBLE, 1); + } +} + /** * task_clear_group_stop_pending - clear pending group stop * @task: target task @@ -1706,8 +1726,20 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) current->last_siginfo = info; current->exit_code = exit_code; - /* Let the debugger run. */ - __set_current_state(TASK_TRACED); + /* + * TRACED should be visible before TRAPPING is cleared; otherwise, + * the tracer might fail do_wait(). + */ + set_current_state(TASK_TRACED); + + /* + * We're committing to trapping. Clearing GROUP_STOP_TRAPPING and + * transition to TASK_TRACED should be atomic with respect to + * siglock. This hsould be done after the arch hook as siglock is + * released and regrabbed across it. + */ + task_clear_group_stop_trapping(current); + spin_unlock_irq(¤t->sighand->siglock); read_lock(&tasklist_lock); if (may_ptrace_stop()) { @@ -1788,6 +1820,9 @@ static int do_signal_stop(int signr) unsigned int gstop = GROUP_STOP_PENDING | GROUP_STOP_CONSUME; struct task_struct *t; + /* signr will be recorded in task->group_stop for retries */ + WARN_ON_ONCE(signr & ~GROUP_STOP_SIGMASK); + if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) || unlikely(signal_group_exit(sig))) return 0; @@ -1797,25 +1832,27 @@ static int do_signal_stop(int signr) */ sig->group_exit_code = signr; - current->group_stop = gstop; + current->group_stop &= ~GROUP_STOP_SIGMASK; + current->group_stop |= signr | gstop; sig->group_stop_count = 1; - for (t = next_thread(current); t != current; t = next_thread(t)) + for (t = next_thread(current); t != current; + t = next_thread(t)) { + t->group_stop &= ~GROUP_STOP_SIGMASK; /* * Setting state to TASK_STOPPED for a group * stop is always done with the siglock held, * so this check has no races. */ if (!(t->flags & PF_EXITING) && !task_is_stopped(t)) { - t->group_stop = gstop; + t->group_stop |= signr | gstop; sig->group_stop_count++; signal_wake_up(t, 0); - } else + } else { task_clear_group_stop_pending(t); + } + } } - - current->exit_code = sig->group_exit_code; - __set_current_state(TASK_STOPPED); - +retry: if (likely(!task_ptrace(current))) { int notify = 0; @@ -1827,6 +1864,7 @@ static int do_signal_stop(int signr) if (task_participate_group_stop(current)) notify = CLD_STOPPED; + __set_current_state(TASK_STOPPED); spin_unlock_irq(¤t->sighand->siglock); if (notify) { @@ -1839,13 +1877,28 @@ static int do_signal_stop(int signr) schedule(); spin_lock_irq(¤t->sighand->siglock); - } else - ptrace_stop(current->exit_code, CLD_STOPPED, 0, NULL); + } else { + ptrace_stop(current->group_stop & GROUP_STOP_SIGMASK, + CLD_STOPPED, 0, NULL); + current->exit_code = 0; + } + + /* + * GROUP_STOP_PENDING could be set if another group stop has + * started since being woken up or ptrace wants us to transit + * between TASK_STOPPED and TRACED. Retry group stop. + */ + if (current->group_stop & GROUP_STOP_PENDING) { + WARN_ON_ONCE(!(current->group_stop & GROUP_STOP_SIGMASK)); + goto retry; + } + + /* PTRACE_ATTACH might have raced with task killing, clear trapping */ + task_clear_group_stop_trapping(current); spin_unlock_irq(¤t->sighand->siglock); tracehook_finish_jctl(); - current->exit_code = 0; return 1; } -- cgit v1.2.3-70-g09d2 From ee77f075921730b2b465880f9fd4367003bdab39 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 1 Apr 2011 20:12:38 +0200 Subject: signal: Turn SIGNAL_STOP_DEQUEUED into GROUP_STOP_DEQUEUED This patch moves SIGNAL_STOP_DEQUEUED from signal_struct->flags to task_struct->group_stop, and thus makes it per-thread. Like SIGNAL_STOP_DEQUEUED, GROUP_STOP_DEQUEUED can be false-positive after return from get_signal_to_deliver(), this is fine. The only purpose of this bit is: we can drop ->siglock after __dequeue_signal() returns the sig_kernel_stop() signal and before we call do_signal_stop(), in this case we must not miss SIGCONT if it comes in between. But, unlike SIGNAL_STOP_DEQUEUED, GROUP_STOP_DEQUEUED can not be false-positive in do_signal_stop() if multiple threads dequeue the sig_kernel_stop() signal at the same time. Consider two threads T1 and T2, SIGTTIN has a hanlder. - T1 dequeues SIGTSTP and sets SIGNAL_STOP_DEQUEUED, then it drops ->siglock - SIGCONT comes and clears SIGNAL_STOP_DEQUEUED, SIGTSTP should be cancelled. - T2 dequeues SIGTTIN and sets SIGNAL_STOP_DEQUEUED again. Since we have a handler we should not stop, T2 returns to usermode to run the handler. - T1 continues, calls do_signal_stop() and wrongly starts the group stop because SIGNAL_STOP_DEQUEUED was restored in between. With or without this change: - we need to do something with ptrace_signal() which can return SIGSTOP, but this needs another discussion - SIGSTOP can be lost if it races with the mt exec, will be fixed later. Signed-off-by: Oleg Nesterov Signed-off-by: Tejun Heo --- include/linux/sched.h | 6 +++--- kernel/signal.c | 14 ++++---------- 2 files changed, 7 insertions(+), 13 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 456d80ed3b7..8cef82d4cf7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -652,9 +652,8 @@ struct signal_struct { * Bits in flags field of signal_struct. */ #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ -#define SIGNAL_STOP_DEQUEUED 0x00000002 /* stop signal dequeued */ -#define SIGNAL_STOP_CONTINUED 0x00000004 /* SIGCONT since WCONTINUED reap */ -#define SIGNAL_GROUP_EXIT 0x00000008 /* group exit in progress */ +#define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ +#define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ /* * Pending notifications to parent. */ @@ -1779,6 +1778,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define GROUP_STOP_PENDING (1 << 16) /* task should stop for group stop */ #define GROUP_STOP_CONSUME (1 << 17) /* consume group stop count */ #define GROUP_STOP_TRAPPING (1 << 18) /* switching from STOPPED to TRACED */ +#define GROUP_STOP_DEQUEUED (1 << 19) /* stop signal dequeued */ extern void task_clear_group_stop_pending(struct task_struct *task); diff --git a/kernel/signal.c b/kernel/signal.c index e9abc69dc0d..4f7312b49b2 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -254,7 +254,8 @@ static void task_clear_group_stop_trapping(struct task_struct *task) */ void task_clear_group_stop_pending(struct task_struct *task) { - task->group_stop &= ~(GROUP_STOP_PENDING | GROUP_STOP_CONSUME); + task->group_stop &= ~(GROUP_STOP_PENDING | GROUP_STOP_CONSUME | + GROUP_STOP_DEQUEUED); } /** @@ -602,7 +603,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) * is to alert stop-signal processing code when another * processor has come along and cleared the flag. */ - tsk->signal->flags |= SIGNAL_STOP_DEQUEUED; + current->group_stop |= GROUP_STOP_DEQUEUED; } if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) { /* @@ -821,13 +822,6 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns) signal->flags = why | SIGNAL_STOP_CONTINUED; signal->group_stop_count = 0; signal->group_exit_code = 0; - } else { - /* - * We are not stopped, but there could be a stop - * signal in the middle of being processed after - * being removed from the queue. Clear that too. - */ - signal->flags &= ~SIGNAL_STOP_DEQUEUED; } } @@ -1855,7 +1849,7 @@ static int do_signal_stop(int signr) /* signr will be recorded in task->group_stop for retries */ WARN_ON_ONCE(signr & ~GROUP_STOP_SIGMASK); - if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) || + if (!likely(current->group_stop & GROUP_STOP_DEQUEUED) || unlikely(signal_group_exit(sig))) return 0; /* -- cgit v1.2.3-70-g09d2 From dce840a08702bd13a9a186e07e63d1ef82256b5e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Apr 2011 14:09:50 +0200 Subject: sched: Dynamically allocate sched_domain/sched_group data-structures Instead of relying on static allocations for the sched_domain and sched_group trees, dynamically allocate and RCU free them. Allocating this dynamically also allows for some build_sched_groups() simplification since we can now (like with other simplifications) rely on the sched_domain tree instead of hard-coded knowledge. One tricky to note is that detach_destroy_domains() needs to hold rcu_read_lock() over the entire tear-down, per-cpu is not sufficient since that can lead to partial sched_group existance (could possibly be solved by doing the tear-down backwards but this is much more robust). A concequence of the above is that we can no longer print the sched_domain debug stuff from cpu_attach_domain() since that might now run with preemption disabled (due to classic RCU etc.) and sched_domain_debug() does some GFP_KERNEL allocations. Another thing to note is that we now fully rely on normal RCU and not RCU-sched, this is because with the new and exiting RCU flavours we grew over the years BH doesn't necessarily hold off RCU-sched grace periods (-rt is known to break this). This would in fact already cause us grief since we do sched_domain/sched_group iterations from softirq context. This patch is somewhat larger than I would like it to be, but I didn't find any means of shrinking/splitting this. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110407122942.245307941@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 + kernel/sched.c | 479 ++++++++++++++++++++------------------------------ kernel/sched_fair.c | 30 +++- 3 files changed, 218 insertions(+), 296 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ec2c027e92..020b79d6c48 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -868,6 +868,7 @@ static inline int sd_power_saving_flags(void) struct sched_group { struct sched_group *next; /* Must be a circular list */ + atomic_t ref; /* * CPU power of this group, SCHED_LOAD_SCALE being max power for a @@ -973,6 +974,10 @@ struct sched_domain { #ifdef CONFIG_SCHED_DEBUG char *name; #endif + union { + void *private; /* used during construction */ + struct rcu_head rcu; /* used during destruction */ + }; unsigned int span_weight; /* diff --git a/kernel/sched.c b/kernel/sched.c index 1cca59ec4a4..65204845063 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -417,6 +417,7 @@ struct rt_rq { */ struct root_domain { atomic_t refcount; + struct rcu_head rcu; cpumask_var_t span; cpumask_var_t online; @@ -571,7 +572,7 @@ static inline int cpu_of(struct rq *rq) #define rcu_dereference_check_sched_domain(p) \ rcu_dereference_check((p), \ - rcu_read_lock_sched_held() || \ + rcu_read_lock_held() || \ lockdep_is_held(&sched_domains_mutex)) /* @@ -6572,12 +6573,11 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) return 1; } -static void free_rootdomain(struct root_domain *rd) +static void free_rootdomain(struct rcu_head *rcu) { - synchronize_sched(); + struct root_domain *rd = container_of(rcu, struct root_domain, rcu); cpupri_cleanup(&rd->cpupri); - free_cpumask_var(rd->rto_mask); free_cpumask_var(rd->online); free_cpumask_var(rd->span); @@ -6618,7 +6618,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) raw_spin_unlock_irqrestore(&rq->lock, flags); if (old_rd) - free_rootdomain(old_rd); + call_rcu_sched(&old_rd->rcu, free_rootdomain); } static int init_rootdomain(struct root_domain *rd) @@ -6669,6 +6669,25 @@ static struct root_domain *alloc_rootdomain(void) return rd; } +static void free_sched_domain(struct rcu_head *rcu) +{ + struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); + if (atomic_dec_and_test(&sd->groups->ref)) + kfree(sd->groups); + kfree(sd); +} + +static void destroy_sched_domain(struct sched_domain *sd, int cpu) +{ + call_rcu(&sd->rcu, free_sched_domain); +} + +static void destroy_sched_domains(struct sched_domain *sd, int cpu) +{ + for (; sd; sd = sd->parent) + destroy_sched_domain(sd, cpu); +} + /* * Attach the domain 'sd' to 'cpu' as its base domain. Callers must * hold the hotplug lock. @@ -6689,20 +6708,25 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) tmp->parent = parent->parent; if (parent->parent) parent->parent->child = tmp; + destroy_sched_domain(parent, cpu); } else tmp = tmp->parent; } if (sd && sd_degenerate(sd)) { + tmp = sd; sd = sd->parent; + destroy_sched_domain(tmp, cpu); if (sd) sd->child = NULL; } - sched_domain_debug(sd, cpu); + /* sched_domain_debug(sd, cpu); */ rq_attach_root(rq, rd); + tmp = rq->sd; rcu_assign_pointer(rq->sd, sd); + destroy_sched_domains(tmp, cpu); } /* cpus with isolated domains */ @@ -6718,56 +6742,6 @@ static int __init isolated_cpu_setup(char *str) __setup("isolcpus=", isolated_cpu_setup); -/* - * init_sched_build_groups takes the cpumask we wish to span, and a pointer - * to a function which identifies what group(along with sched group) a CPU - * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids - * (due to the fact that we keep track of groups covered with a struct cpumask). - * - * init_sched_build_groups will build a circular linked list of the groups - * covered by the given span, and will set each group's ->cpumask correctly, - * and ->cpu_power to 0. - */ -static void -init_sched_build_groups(const struct cpumask *span, - const struct cpumask *cpu_map, - int (*group_fn)(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, - struct cpumask *tmpmask), - struct cpumask *covered, struct cpumask *tmpmask) -{ - struct sched_group *first = NULL, *last = NULL; - int i; - - cpumask_clear(covered); - - for_each_cpu(i, span) { - struct sched_group *sg; - int group = group_fn(i, cpu_map, &sg, tmpmask); - int j; - - if (cpumask_test_cpu(i, covered)) - continue; - - cpumask_clear(sched_group_cpus(sg)); - sg->cpu_power = 0; - - for_each_cpu(j, span) { - if (group_fn(j, cpu_map, NULL, tmpmask) != group) - continue; - - cpumask_set_cpu(j, covered); - cpumask_set_cpu(j, sched_group_cpus(sg)); - } - if (!first) - first = sg; - if (last) - last->next = sg; - last = sg; - } - last->next = first; -} - #define SD_NODES_PER_DOMAIN 16 #ifdef CONFIG_NUMA @@ -6858,154 +6832,96 @@ struct static_sched_domain { DECLARE_BITMAP(span, CONFIG_NR_CPUS); }; +struct sd_data { + struct sched_domain **__percpu sd; + struct sched_group **__percpu sg; +}; + struct s_data { #ifdef CONFIG_NUMA int sd_allnodes; #endif cpumask_var_t nodemask; cpumask_var_t send_covered; - cpumask_var_t tmpmask; struct sched_domain ** __percpu sd; + struct sd_data sdd[SD_LV_MAX]; struct root_domain *rd; }; enum s_alloc { sa_rootdomain, sa_sd, - sa_tmpmask, + sa_sd_storage, sa_send_covered, sa_nodemask, sa_none, }; /* - * SMT sched-domains: + * Assumes the sched_domain tree is fully constructed */ -#ifdef CONFIG_SCHED_SMT -static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_groups); - -static int -cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *unused) +static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) { - if (sg) - *sg = &per_cpu(sched_groups, cpu).sg; - return cpu; -} -#endif /* CONFIG_SCHED_SMT */ + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); + struct sched_domain *child = sd->child; -/* - * multi-core sched-domains: - */ -#ifdef CONFIG_SCHED_MC -static DEFINE_PER_CPU(struct static_sched_domain, core_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_core); + if (child) + cpu = cpumask_first(sched_domain_span(child)); -static int -cpu_to_core_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) -{ - int group; -#ifdef CONFIG_SCHED_SMT - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); -#else - group = cpu; -#endif if (sg) - *sg = &per_cpu(sched_group_core, group).sg; - return group; + *sg = *per_cpu_ptr(sdd->sg, cpu); + + return cpu; } -#endif /* CONFIG_SCHED_MC */ /* - * book sched-domains: + * build_sched_groups takes the cpumask we wish to span, and a pointer + * to a function which identifies what group(along with sched group) a CPU + * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids + * (due to the fact that we keep track of groups covered with a struct cpumask). + * + * build_sched_groups will build a circular linked list of the groups + * covered by the given span, and will set each group's ->cpumask correctly, + * and ->cpu_power to 0. */ -#ifdef CONFIG_SCHED_BOOK -static DEFINE_PER_CPU(struct static_sched_domain, book_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_book); - -static int -cpu_to_book_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) -{ - int group = cpu; -#ifdef CONFIG_SCHED_MC - cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_SMT) - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); -#endif - if (sg) - *sg = &per_cpu(sched_group_book, group).sg; - return group; -} -#endif /* CONFIG_SCHED_BOOK */ - -static DEFINE_PER_CPU(struct static_sched_domain, phys_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys); - -static int -cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) +static void +build_sched_groups(struct sched_domain *sd, struct cpumask *covered) { - int group; -#ifdef CONFIG_SCHED_BOOK - cpumask_and(mask, cpu_book_mask(cpu), cpu_map); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_MC) - cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_SMT) - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); -#else - group = cpu; -#endif - if (sg) - *sg = &per_cpu(sched_group_phys, group).sg; - return group; -} - -#ifdef CONFIG_NUMA -static DEFINE_PER_CPU(struct static_sched_domain, node_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_node); + struct sched_group *first = NULL, *last = NULL; + struct sd_data *sdd = sd->private; + const struct cpumask *span = sched_domain_span(sd); + int i; -static int cpu_to_node_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, - struct cpumask *nodemask) -{ - int group; + cpumask_clear(covered); - cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); - group = cpumask_first(nodemask); + for_each_cpu(i, span) { + struct sched_group *sg; + int group = get_group(i, sdd, &sg); + int j; - if (sg) - *sg = &per_cpu(sched_group_node, group).sg; - return group; -} + if (cpumask_test_cpu(i, covered)) + continue; -static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes); + cpumask_clear(sched_group_cpus(sg)); + sg->cpu_power = 0; -static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, - struct cpumask *nodemask) -{ - int group; + for_each_cpu(j, span) { + if (get_group(j, sdd, NULL) != group) + continue; - cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); - group = cpumask_first(nodemask); + cpumask_set_cpu(j, covered); + cpumask_set_cpu(j, sched_group_cpus(sg)); + } - if (sg) - *sg = &per_cpu(sched_group_allnodes, group).sg; - return group; + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + } + last->next = first; } -#endif /* CONFIG_NUMA */ - /* * Initialize sched groups cpu_power. * @@ -7039,15 +6955,15 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) # 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); \ +#define SD_INIT_FUNC(type) \ +static noinline struct sched_domain *sd_init_##type(struct s_data *d, int cpu) \ +{ \ + struct sched_domain *sd = *per_cpu_ptr(d->sdd[SD_LV_##type].sd, cpu); \ + *sd = SD_##type##_INIT; \ + sd->level = SD_LV_##type; \ + SD_INIT_NAME(sd, type); \ + sd->private = &d->sdd[SD_LV_##type]; \ + return sd; \ } SD_INIT_FUNC(CPU) @@ -7103,13 +7019,22 @@ static void set_domain_attribute(struct sched_domain *sd, static void __free_domain_allocs(struct s_data *d, enum s_alloc what, const struct cpumask *cpu_map) { + int i, j; + switch (what) { case sa_rootdomain: - free_rootdomain(d->rd); /* fall through */ + free_rootdomain(&d->rd->rcu); /* fall through */ case sa_sd: free_percpu(d->sd); /* fall through */ - case sa_tmpmask: - free_cpumask_var(d->tmpmask); /* fall through */ + case sa_sd_storage: + for (i = 0; i < SD_LV_MAX; i++) { + for_each_cpu(j, cpu_map) { + kfree(*per_cpu_ptr(d->sdd[i].sd, j)); + kfree(*per_cpu_ptr(d->sdd[i].sg, j)); + } + free_percpu(d->sdd[i].sd); + free_percpu(d->sdd[i].sg); + } /* fall through */ case sa_send_covered: free_cpumask_var(d->send_covered); /* fall through */ case sa_nodemask: @@ -7122,25 +7047,70 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what, static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, const struct cpumask *cpu_map) { + int i, j; + + memset(d, 0, sizeof(*d)); + if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL)) return sa_none; if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL)) return sa_nodemask; - if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL)) - return sa_send_covered; - d->sd = alloc_percpu(struct sched_domain *); - if (!d->sd) { - printk(KERN_WARNING "Cannot alloc per-cpu pointers\n"); - return sa_tmpmask; + for (i = 0; i < SD_LV_MAX; i++) { + d->sdd[i].sd = alloc_percpu(struct sched_domain *); + if (!d->sdd[i].sd) + return sa_sd_storage; + + d->sdd[i].sg = alloc_percpu(struct sched_group *); + if (!d->sdd[i].sg) + return sa_sd_storage; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + struct sched_group *sg; + + sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sd) + return sa_sd_storage; + + *per_cpu_ptr(d->sdd[i].sd, j) = sd; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sg) + return sa_sd_storage; + + *per_cpu_ptr(d->sdd[i].sg, j) = sg; + } } + d->sd = alloc_percpu(struct sched_domain *); + if (!d->sd) + return sa_sd_storage; d->rd = alloc_rootdomain(); - if (!d->rd) { - printk(KERN_WARNING "Cannot alloc root domain\n"); + if (!d->rd) return sa_sd; - } return sa_rootdomain; } +/* + * NULL the sd_data elements we've used to build the sched_domain and + * sched_group structure so that the subsequent __free_domain_allocs() + * will not free the data we're using. + */ +static void claim_allocations(int cpu, struct sched_domain *sd) +{ + struct sd_data *sdd = sd->private; + struct sched_group *sg = sd->groups; + + WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); + *per_cpu_ptr(sdd->sd, cpu) = NULL; + + if (cpu == cpumask_first(sched_group_cpus(sg))) { + WARN_ON_ONCE(*per_cpu_ptr(sdd->sg, cpu) != sg); + *per_cpu_ptr(sdd->sg, cpu) = NULL; + } +} + static struct sched_domain *__build_numa_sched_domains(struct s_data *d, const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i) { @@ -7151,24 +7121,20 @@ static struct sched_domain *__build_numa_sched_domains(struct s_data *d, d->sd_allnodes = 0; if (cpumask_weight(cpu_map) > SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) { - sd = &per_cpu(allnodes_domains, i).sd; - SD_INIT(sd, ALLNODES); + sd = sd_init_ALLNODES(d, i); set_domain_attribute(sd, attr); cpumask_copy(sched_domain_span(sd), cpu_map); - cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask); d->sd_allnodes = 1; } parent = sd; - sd = &per_cpu(node_domains, i).sd; - SD_INIT(sd, NODE); + sd = sd_init_NODE(d, i); set_domain_attribute(sd, attr); sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); sd->parent = parent; if (parent) parent->child = sd; cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map); - cpu_to_node_group(i, cpu_map, &sd->groups, d->tmpmask); #endif return sd; } @@ -7178,14 +7144,12 @@ static struct sched_domain *__build_cpu_sched_domain(struct s_data *d, struct sched_domain *parent, int i) { struct sched_domain *sd; - sd = &per_cpu(phys_domains, i).sd; - SD_INIT(sd, CPU); + sd = sd_init_CPU(d, i); set_domain_attribute(sd, attr); cpumask_copy(sched_domain_span(sd), d->nodemask); sd->parent = parent; if (parent) parent->child = sd; - cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask); return sd; } @@ -7195,13 +7159,11 @@ static struct sched_domain *__build_book_sched_domain(struct s_data *d, { struct sched_domain *sd = parent; #ifdef CONFIG_SCHED_BOOK - sd = &per_cpu(book_domains, i).sd; - SD_INIT(sd, BOOK); + sd = sd_init_BOOK(d, i); set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i)); sd->parent = parent; parent->child = sd; - cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask); #endif return sd; } @@ -7212,13 +7174,11 @@ static struct sched_domain *__build_mc_sched_domain(struct s_data *d, { struct sched_domain *sd = parent; #ifdef CONFIG_SCHED_MC - sd = &per_cpu(core_domains, i).sd; - SD_INIT(sd, MC); + sd = sd_init_MC(d, i); set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i)); sd->parent = parent; parent->child = sd; - cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask); #endif return sd; } @@ -7229,92 +7189,32 @@ static struct sched_domain *__build_smt_sched_domain(struct s_data *d, { struct sched_domain *sd = parent; #ifdef CONFIG_SCHED_SMT - sd = &per_cpu(cpu_domains, i).sd; - SD_INIT(sd, SIBLING); + sd = sd_init_SIBLING(d, i); set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i)); sd->parent = parent; parent->child = sd; - cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask); #endif return sd; } -static void build_sched_groups(struct s_data *d, struct sched_domain *sd, - const struct cpumask *cpu_map, int cpu) -{ - switch (sd->level) { -#ifdef CONFIG_SCHED_SMT - case SD_LV_SIBLING: /* set up CPU (sibling) groups */ - if (cpu == cpumask_first(sched_domain_span(sd))) - init_sched_build_groups(sched_domain_span(sd), cpu_map, - &cpu_to_cpu_group, - d->send_covered, d->tmpmask); - break; -#endif -#ifdef CONFIG_SCHED_MC - case SD_LV_MC: /* set up multi-core groups */ - if (cpu == cpumask_first(sched_domain_span(sd))) - init_sched_build_groups(sched_domain_span(sd), cpu_map, - &cpu_to_core_group, - d->send_covered, d->tmpmask); - break; -#endif -#ifdef CONFIG_SCHED_BOOK - case SD_LV_BOOK: /* set up book groups */ - if (cpu == cpumask_first(sched_domain_span(sd))) - init_sched_build_groups(sched_domain_span(sd), cpu_map, - &cpu_to_book_group, - d->send_covered, d->tmpmask); - break; -#endif - case SD_LV_CPU: /* set up physical groups */ - if (cpu == cpumask_first(sched_domain_span(sd))) - init_sched_build_groups(sched_domain_span(sd), cpu_map, - &cpu_to_phys_group, - d->send_covered, d->tmpmask); - break; -#ifdef CONFIG_NUMA - case SD_LV_NODE: - if (cpu == cpumask_first(sched_domain_span(sd))) - init_sched_build_groups(sched_domain_span(sd), cpu_map, - &cpu_to_node_group, - d->send_covered, d->tmpmask); - - case SD_LV_ALLNODES: - if (cpu == cpumask_first(cpu_map)) - init_sched_build_groups(cpu_map, cpu_map, - &cpu_to_allnodes_group, - d->send_covered, d->tmpmask); - break; -#endif - default: - break; - } -} - /* * Build sched domains for a given set of cpus and attach the sched domains * to the individual cpus */ -static int __build_sched_domains(const struct cpumask *cpu_map, - struct sched_domain_attr *attr) +static int build_sched_domains(const struct cpumask *cpu_map, + struct sched_domain_attr *attr) { enum s_alloc alloc_state = sa_none; + struct sched_domain *sd; struct s_data d; - struct sched_domain *sd, *tmp; int i; -#ifdef CONFIG_NUMA - d.sd_allnodes = 0; -#endif alloc_state = __visit_domain_allocation_hell(&d, cpu_map); if (alloc_state != sa_rootdomain) goto error; - /* - * Set up domains for cpus specified by the cpu_map. - */ + /* Set up domains for cpus specified by the cpu_map. */ for_each_cpu(i, cpu_map) { cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map); @@ -7326,10 +7226,19 @@ static int __build_sched_domains(const struct cpumask *cpu_map, sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i); *per_cpu_ptr(d.sd, i) = sd; + } + + /* Build the groups for the domains */ + for_each_cpu(i, cpu_map) { + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + sd->span_weight = cpumask_weight(sched_domain_span(sd)); + get_group(i, sd->private, &sd->groups); + atomic_inc(&sd->groups->ref); - for (tmp = sd; tmp; tmp = tmp->parent) { - tmp->span_weight = cpumask_weight(sched_domain_span(tmp)); - build_sched_groups(&d, tmp, cpu_map, i); + if (i != cpumask_first(sched_domain_span(sd))) + continue; + + build_sched_groups(sd, d.send_covered); } } @@ -7338,18 +7247,21 @@ static int __build_sched_domains(const struct cpumask *cpu_map, if (!cpumask_test_cpu(i, cpu_map)) continue; - sd = *per_cpu_ptr(d.sd, i); - for (; sd; sd = sd->parent) + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + claim_allocations(i, sd); init_sched_groups_power(i, sd); + } } /* Attach the domains */ + rcu_read_lock(); for_each_cpu(i, cpu_map) { sd = *per_cpu_ptr(d.sd, i); cpu_attach_domain(sd, d.rd, i); } + rcu_read_unlock(); - __free_domain_allocs(&d, sa_tmpmask, cpu_map); + __free_domain_allocs(&d, sa_sd, cpu_map); return 0; error: @@ -7357,11 +7269,6 @@ error: return -ENOMEM; } -static int build_sched_domains(const struct cpumask *cpu_map) -{ - return __build_sched_domains(cpu_map, NULL); -} - static cpumask_var_t *doms_cur; /* current sched domains */ static int ndoms_cur; /* number of sched domains in 'doms_cur' */ static struct sched_domain_attr *dattr_cur; @@ -7425,31 +7332,24 @@ static int init_sched_domains(const struct cpumask *cpu_map) doms_cur = &fallback_doms; cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); dattr_cur = NULL; - err = build_sched_domains(doms_cur[0]); + err = build_sched_domains(doms_cur[0], NULL); register_sched_domain_sysctl(); return err; } -static void destroy_sched_domains(const struct cpumask *cpu_map, - struct cpumask *tmpmask) -{ -} - /* * Detach sched domains from a group of cpus specified in cpu_map * These cpus will now be attached to the NULL domain */ static void detach_destroy_domains(const struct cpumask *cpu_map) { - /* Save because hotplug lock held. */ - static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS); int i; + rcu_read_lock(); for_each_cpu(i, cpu_map) cpu_attach_domain(NULL, &def_root_domain, i); - synchronize_sched(); - destroy_sched_domains(cpu_map, to_cpumask(tmpmask)); + rcu_read_unlock(); } /* handle null as "default" */ @@ -7538,8 +7438,7 @@ match1: goto match2; } /* no match - add a new doms_new */ - __build_sched_domains(doms_new[i], - dattr_new ? dattr_new + i : NULL); + build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); match2: ; } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 4ee50f0af8d..4a8ac7c2a18 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1622,6 +1622,7 @@ static int select_idle_sibling(struct task_struct *p, int target) /* * Otherwise, iterate the domains and find an elegible idle cpu. */ + rcu_read_lock(); for_each_domain(target, sd) { if (!(sd->flags & SD_SHARE_PKG_RESOURCES)) break; @@ -1641,6 +1642,7 @@ static int select_idle_sibling(struct task_struct *p, int target) cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) break; } + rcu_read_unlock(); return target; } @@ -1673,6 +1675,7 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ new_cpu = prev_cpu; } + rcu_read_lock(); for_each_domain(cpu, tmp) { if (!(tmp->flags & SD_LOAD_BALANCE)) continue; @@ -1723,9 +1726,10 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ if (affine_sd) { if (cpu == prev_cpu || wake_affine(affine_sd, p, sync)) - return select_idle_sibling(p, cpu); - else - return select_idle_sibling(p, prev_cpu); + prev_cpu = cpu; + + new_cpu = select_idle_sibling(p, prev_cpu); + goto unlock; } while (sd) { @@ -1766,6 +1770,8 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ } /* while loop will break here if sd == NULL */ } +unlock: + rcu_read_unlock(); return new_cpu; } @@ -3462,6 +3468,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq) raw_spin_unlock(&this_rq->lock); update_shares(this_cpu); + rcu_read_lock(); for_each_domain(this_cpu, sd) { unsigned long interval; int balance = 1; @@ -3483,6 +3490,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq) break; } } + rcu_read_unlock(); raw_spin_lock(&this_rq->lock); @@ -3531,6 +3539,7 @@ static int active_load_balance_cpu_stop(void *data) double_lock_balance(busiest_rq, target_rq); /* Search for an sd spanning us and the target CPU. */ + rcu_read_lock(); for_each_domain(target_cpu, sd) { if ((sd->flags & SD_LOAD_BALANCE) && cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) @@ -3546,6 +3555,7 @@ static int active_load_balance_cpu_stop(void *data) else schedstat_inc(sd, alb_failed); } + rcu_read_unlock(); double_unlock_balance(busiest_rq, target_rq); out_unlock: busiest_rq->active_balance = 0; @@ -3672,6 +3682,7 @@ static int find_new_ilb(int cpu) { struct sched_domain *sd; struct sched_group *ilb_group; + int ilb = nr_cpu_ids; /* * Have idle load balancer selection from semi-idle packages only @@ -3687,20 +3698,25 @@ static int find_new_ilb(int cpu) if (cpumask_weight(nohz.idle_cpus_mask) < 2) goto out_done; + rcu_read_lock(); for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) { ilb_group = sd->groups; do { - if (is_semi_idle_group(ilb_group)) - return cpumask_first(nohz.grp_idle_mask); + if (is_semi_idle_group(ilb_group)) { + ilb = cpumask_first(nohz.grp_idle_mask); + goto unlock; + } ilb_group = ilb_group->next; } while (ilb_group != sd->groups); } +unlock: + rcu_read_unlock(); out_done: - return nr_cpu_ids; + return ilb; } #else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ static inline int find_new_ilb(int call_cpu) @@ -3845,6 +3861,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) update_shares(cpu); + rcu_read_lock(); for_each_domain(cpu, sd) { if (!(sd->flags & SD_LOAD_BALANCE)) continue; @@ -3890,6 +3907,7 @@ out: if (!balance) break; } + rcu_read_unlock(); /* * next_balance will be updated only when there is a need. -- cgit v1.2.3-70-g09d2 From 3859173d43658d51a749bc0201b943922577d39c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Apr 2011 14:09:53 +0200 Subject: sched: Reduce some allocation pressure Since we now allocate SD_LV_MAX * nr_cpu_ids sched_domain/sched_group structures when rebuilding the scheduler toplogy it might make sense to shrink that depending on the CONFIG_ options. This is only needed until we get rid of SD_LV_* alltogether and provide a full dynamic topology interface. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110407122942.406226449@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 020b79d6c48..5a9168b01db 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -897,12 +897,20 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg) enum sched_domain_level { SD_LV_NONE = 0, +#ifdef CONFIG_SCHED_SMT SD_LV_SIBLING, +#endif +#ifdef CONFIG_SCHED_MC SD_LV_MC, +#endif +#ifdef CONFIG_SCHED_BOOK SD_LV_BOOK, +#endif SD_LV_CPU, +#ifdef CONFIG_NUMA SD_LV_NODE, SD_LV_ALLNODES, +#endif SD_LV_MAX }; -- cgit v1.2.3-70-g09d2 From 7dd04b730749f957c116f363524fd622b05e5141 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Apr 2011 14:09:56 +0200 Subject: sched: Remove some dead code Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110407122942.553814623@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 ------ kernel/sched.c | 16 ---------------- 2 files changed, 22 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5a9168b01db..09d9e02f2b6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -883,9 +883,6 @@ struct sched_group { * NOTE: this field is variable length. (Allocated dynamically * by attaching extra space to the end of the structure, * depending on how many CPUs the kernel has booted up with) - * - * It is also be embedded into static data structures at build - * time. (See 'struct static_sched_group' in kernel/sched.c) */ unsigned long cpumask[0]; }; @@ -994,9 +991,6 @@ struct sched_domain { * NOTE: this field is variable length. (Allocated dynamically * by attaching extra space to the end of the structure, * depending on how many CPUs the kernel has booted up with) - * - * It is also be embedded into static data structures at build - * time. (See 'struct static_sched_domain' in kernel/sched.c) */ unsigned long span[0]; }; diff --git a/kernel/sched.c b/kernel/sched.c index f4d3a624c50..5ec685ce516 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6816,22 +6816,6 @@ static void sched_domain_node_span(int node, struct cpumask *span) int sched_smt_power_savings = 0, sched_mc_power_savings = 0; -/* - * The cpus mask in sched_group and sched_domain hangs off the end. - * - * ( See the the comments in include/linux/sched.h:struct sched_group - * and struct sched_domain. ) - */ -struct static_sched_group { - struct sched_group sg; - DECLARE_BITMAP(cpus, CONFIG_NR_CPUS); -}; - -struct static_sched_domain { - struct sched_domain sd; - DECLARE_BITMAP(span, CONFIG_NR_CPUS); -}; - struct sd_data { struct sched_domain **__percpu sd; struct sched_group **__percpu sg; -- cgit v1.2.3-70-g09d2 From 60495e7760d8ee364695006af37309b0755e0e17 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Apr 2011 14:10:04 +0200 Subject: sched: Dynamic sched_domain::level Remove the SD_LV_ enum and use dynamic level assignments. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110407122942.969433965@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 23 +++-------------------- kernel/cpuset.c | 2 +- kernel/sched.c | 9 ++++++--- 3 files changed, 10 insertions(+), 24 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 09d9e02f2b6..e43e5b0ab0b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -892,25 +892,6 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg) return to_cpumask(sg->cpumask); } -enum sched_domain_level { - SD_LV_NONE = 0, -#ifdef CONFIG_SCHED_SMT - SD_LV_SIBLING, -#endif -#ifdef CONFIG_SCHED_MC - SD_LV_MC, -#endif -#ifdef CONFIG_SCHED_BOOK - SD_LV_BOOK, -#endif - SD_LV_CPU, -#ifdef CONFIG_NUMA - SD_LV_NODE, - SD_LV_ALLNODES, -#endif - SD_LV_MAX -}; - struct sched_domain_attr { int relax_domain_level; }; @@ -919,6 +900,8 @@ struct sched_domain_attr { .relax_domain_level = -1, \ } +extern int sched_domain_level_max; + struct sched_domain { /* These fields must be setup */ struct sched_domain *parent; /* top domain must be null terminated */ @@ -936,7 +919,7 @@ struct sched_domain { unsigned int forkexec_idx; unsigned int smt_gain; int flags; /* See SD_* */ - enum sched_domain_level level; + int level; /* Runtime fields. */ unsigned long last_balance; /* init to jiffies. units in jiffies */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 33eee16addb..2bb8c2e98ff 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1159,7 +1159,7 @@ int current_cpuset_is_being_rebound(void) static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP - if (val < -1 || val >= SD_LV_MAX) + if (val < -1 || val >= sched_domain_level_max) return -EINVAL; #endif diff --git a/kernel/sched.c b/kernel/sched.c index 3231e199742..506cb8147c7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6966,7 +6966,6 @@ sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \ { \ struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); \ *sd = SD_##type##_INIT; \ - sd->level = SD_LV_##type; \ SD_INIT_NAME(sd, type); \ sd->private = &tl->data; \ return sd; \ @@ -6988,13 +6987,14 @@ SD_INIT_FUNC(CPU) #endif static int default_relax_domain_level = -1; +int sched_domain_level_max; static int __init setup_relax_domain_level(char *str) { unsigned long val; val = simple_strtoul(str, NULL, 0); - if (val < SD_LV_MAX) + if (val < sched_domain_level_max) default_relax_domain_level = val; return 1; @@ -7173,8 +7173,11 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); - if (child) + if (child) { + sd->level = child->level + 1; + sched_domain_level_max = max(sched_domain_level_max, sd->level); child->parent = sd; + } sd->child = child; return sd; -- cgit v1.2.3-70-g09d2 From 184748cc50b2dceb8287f9fb657eda48ff8fcfe7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:39 +0200 Subject: sched: Provide scheduler_ipi() callback in response to smp_send_reschedule() For future rework of try_to_wake_up() we'd like to push part of that function onto the CPU the task is actually going to run on. In order to do so we need a generic callback from the existing scheduler IPI. This patch introduces such a generic callback: scheduler_ipi() and implements it as a NOP. BenH notes: PowerPC might use this IPI on offline CPUs under rare conditions! Acked-by: Russell King Acked-by: Martin Schwidefsky Acked-by: Chris Metcalf Acked-by: Jesper Nilsson Acked-by: Benjamin Herrenschmidt Signed-off-by: Ralf Baechle Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.744338123@chello.nl --- arch/alpha/kernel/smp.c | 3 +-- arch/arm/kernel/smp.c | 5 +---- arch/blackfin/mach-common/smp.c | 3 +++ arch/cris/arch-v32/kernel/smp.c | 13 ++++++++----- arch/ia64/kernel/irq_ia64.c | 2 ++ arch/ia64/xen/irq_xen.c | 10 +++++++++- arch/m32r/kernel/smp.c | 4 +--- arch/mips/cavium-octeon/smp.c | 2 ++ arch/mips/kernel/smtc.c | 2 +- arch/mips/mti-malta/malta-int.c | 2 ++ arch/mips/pmc-sierra/yosemite/smp.c | 4 ++++ arch/mips/sgi-ip27/ip27-irq.c | 2 ++ arch/mips/sibyte/bcm1480/smp.c | 7 +++---- arch/mips/sibyte/sb1250/smp.c | 7 +++---- arch/mn10300/kernel/smp.c | 5 +---- arch/parisc/kernel/smp.c | 5 +---- arch/powerpc/kernel/smp.c | 4 ++-- arch/s390/kernel/smp.c | 6 +++--- arch/sh/kernel/smp.c | 2 ++ arch/sparc/kernel/smp_32.c | 4 +++- arch/sparc/kernel/smp_64.c | 1 + arch/tile/kernel/smp.c | 6 +----- arch/um/kernel/smp.c | 2 +- arch/x86/kernel/smp.c | 5 ++--- arch/x86/xen/smp.c | 5 ++--- include/linux/sched.h | 2 ++ 26 files changed, 63 insertions(+), 50 deletions(-) (limited to 'include/linux/sched.h') diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 42aa078a5e4..5a621c6d22a 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -585,8 +585,7 @@ handle_ipi(struct pt_regs *regs) switch (which) { case IPI_RESCHEDULE: - /* Reschedule callback. Everything to be done - is done by the interrupt return path. */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 8fe05ad932e..7a561eb731e 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -560,10 +560,7 @@ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs) break; case IPI_RESCHEDULE: - /* - * nothing more to do - eveything is - * done on the interrupt return path - */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 6e17a265c4d..326bb86f4d2 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -164,6 +164,9 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance) while (msg_queue->count) { msg = &msg_queue->ipi_message[msg_queue->head]; switch (msg->type) { + case BFIN_IPI_RESCHEDULE: + scheduler_ipi(); + break; case BFIN_IPI_CALL_FUNC: spin_unlock_irqrestore(&msg_queue->lock, flags); ipi_call_function(cpu, msg); diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c index 4c9e3e1ba5d..66cc75657e2 100644 --- a/arch/cris/arch-v32/kernel/smp.c +++ b/arch/cris/arch-v32/kernel/smp.c @@ -342,15 +342,18 @@ irqreturn_t crisv32_ipi_interrupt(int irq, void *dev_id) ipi = REG_RD(intr_vect, irq_regs[smp_processor_id()], rw_ipi); + if (ipi.vector & IPI_SCHEDULE) { + scheduler_ipi(); + } if (ipi.vector & IPI_CALL) { - func(info); + func(info); } if (ipi.vector & IPI_FLUSH_TLB) { - if (flush_mm == FLUSH_ALL) - __flush_tlb_all(); - else if (flush_vma == FLUSH_ALL) + if (flush_mm == FLUSH_ALL) + __flush_tlb_all(); + else if (flush_vma == FLUSH_ALL) __flush_tlb_mm(flush_mm); - else + else __flush_tlb_page(flush_vma, flush_addr); } diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 5b704740f16..782c3a357f2 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -496,6 +497,7 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs) smp_local_flush_tlb(); kstat_incr_irqs_this_cpu(irq, desc); } else if (unlikely(IS_RESCHEDULE(vector))) { + scheduler_ipi(); kstat_incr_irqs_this_cpu(irq, desc); } else { ia64_setreg(_IA64_REG_CR_TPR, vector); diff --git a/arch/ia64/xen/irq_xen.c b/arch/ia64/xen/irq_xen.c index 108bb858acf..b279e142c63 100644 --- a/arch/ia64/xen/irq_xen.c +++ b/arch/ia64/xen/irq_xen.c @@ -92,6 +92,8 @@ static unsigned short saved_irq_cnt; static int xen_slab_ready; #ifdef CONFIG_SMP +#include + /* Dummy stub. Though we may check XEN_RESCHEDULE_VECTOR before __do_IRQ, * it ends up to issue several memory accesses upon percpu data and * thus adds unnecessary traffic to other paths. @@ -99,7 +101,13 @@ static int xen_slab_ready; static irqreturn_t xen_dummy_handler(int irq, void *dev_id) { + return IRQ_HANDLED; +} +static irqreturn_t +xen_resched_handler(int irq, void *dev_id) +{ + scheduler_ipi(); return IRQ_HANDLED; } @@ -110,7 +118,7 @@ static struct irqaction xen_ipi_irqaction = { }; static struct irqaction xen_resched_irqaction = { - .handler = xen_dummy_handler, + .handler = xen_resched_handler, .flags = IRQF_DISABLED, .name = "resched" }; diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c index 31cef20b299..fc10b39893d 100644 --- a/arch/m32r/kernel/smp.c +++ b/arch/m32r/kernel/smp.c @@ -122,8 +122,6 @@ void smp_send_reschedule(int cpu_id) * * Description: This routine executes on CPU which received * 'RESCHEDULE_IPI'. - * Rescheduling is processed at the exit of interrupt - * operation. * * Born on Date: 2002.02.05 * @@ -138,7 +136,7 @@ void smp_send_reschedule(int cpu_id) *==========================================================================*/ void smp_reschedule_interrupt(void) { - /* nothing to do */ + scheduler_ipi(); } /*==========================================================================* diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index ba78b21cc8d..76923eeb58b 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -44,6 +44,8 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id) if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); /* Check if we've been told to flush the icache */ if (action & SMP_ICACHE_FLUSH) diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index 5a88cc4ccd5..cedac463374 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -929,7 +929,7 @@ static void post_direct_ipi(int cpu, struct smtc_ipi *pipi) static void ipi_resched_interrupt(void) { - /* Return from interrupt should be enough to cause scheduler check */ + scheduler_ipi(); } static void ipi_call_interrupt(void) diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index 9027061f0ea..7d93e6fbfa5 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -309,6 +309,8 @@ static void ipi_call_dispatch(void) static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) { + scheduler_ipi(); + return IRQ_HANDLED; } diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c index efc9e889b34..2608752898c 100644 --- a/arch/mips/pmc-sierra/yosemite/smp.c +++ b/arch/mips/pmc-sierra/yosemite/smp.c @@ -55,6 +55,8 @@ void titan_mailbox_irq(void) if (status & 0x2) smp_call_function_interrupt(); + if (status & 0x4) + scheduler_ipi(); break; case 1: @@ -63,6 +65,8 @@ void titan_mailbox_irq(void) if (status & 0x2) smp_call_function_interrupt(); + if (status & 0x4) + scheduler_ipi(); break; } } diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 0a04603d577..b18b04e4857 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -147,8 +147,10 @@ static void ip27_do_irq_mask0(void) #ifdef CONFIG_SMP if (pend0 & (1UL << CPU_RESCHED_A_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_RESCHED_A_IRQ); + scheduler_ipi(); } else if (pend0 & (1UL << CPU_RESCHED_B_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_RESCHED_B_IRQ); + scheduler_ipi(); } else if (pend0 & (1UL << CPU_CALL_A_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ); smp_call_function_interrupt(); diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c index 47b347c992e..d667875be56 100644 --- a/arch/mips/sibyte/bcm1480/smp.c +++ b/arch/mips/sibyte/bcm1480/smp.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -189,10 +190,8 @@ void bcm1480_mailbox_interrupt(void) /* Clear the mailbox to clear the interrupt */ __raw_writeq(((u64)action)<<48, mailbox_0_clear_regs[cpu]); - /* - * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the - * interrupt will do the reschedule for us - */ + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c index c00a5cb1128..38e7f6bd792 100644 --- a/arch/mips/sibyte/sb1250/smp.c +++ b/arch/mips/sibyte/sb1250/smp.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -177,10 +178,8 @@ void sb1250_mailbox_interrupt(void) /* Clear the mailbox to clear the interrupt */ ____raw_writeq(((u64)action) << 48, mailbox_clear_regs[cpu]); - /* - * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the - * interrupt will do the reschedule for us - */ + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c index 226c826a219..83fb2791223 100644 --- a/arch/mn10300/kernel/smp.c +++ b/arch/mn10300/kernel/smp.c @@ -494,14 +494,11 @@ void smp_send_stop(void) * @irq: The interrupt number. * @dev_id: The device ID. * - * We need do nothing here, since the scheduling will be effected on our way - * back through entry.S. - * * Returns IRQ_HANDLED to indicate we handled the interrupt successfully. */ static irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id) { - /* do nothing */ + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 69d63d354ef..828305f19cf 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -155,10 +155,7 @@ ipi_interrupt(int irq, void *dev_id) case IPI_RESCHEDULE: smp_debug(100, KERN_DEBUG "CPU%d IPI_RESCHEDULE\n", this_cpu); - /* - * Reschedule callback. Everything to be - * done is done by the interrupt return path. - */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index cbdbb14be4b..9f9c204bef6 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -116,7 +116,7 @@ void smp_message_recv(int msg) generic_smp_call_function_interrupt(); break; case PPC_MSG_RESCHEDULE: - /* we notice need_resched on exit */ + scheduler_ipi(); break; case PPC_MSG_CALL_FUNC_SINGLE: generic_smp_call_function_single_interrupt(); @@ -146,7 +146,7 @@ static irqreturn_t call_function_action(int irq, void *data) static irqreturn_t reschedule_action(int irq, void *data) { - /* we just need the return path side effect of checking need_resched */ + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 63a97db83f9..63c7d9ff220 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -165,12 +165,12 @@ static void do_ext_call_interrupt(unsigned int ext_int_code, kstat_cpu(smp_processor_id()).irqs[EXTINT_IPI]++; /* * handle bit signal external calls - * - * For the ec_schedule signal we have to do nothing. All the work - * is done automatically when we return from the interrupt. */ bits = xchg(&S390_lowcore.ext_call_fast, 0); + if (test_bit(ec_schedule, &bits)) + scheduler_ipi(); + if (test_bit(ec_call_function, &bits)) generic_smp_call_function_interrupt(); diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index 509b36b4511..6207561ea34 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -323,6 +324,7 @@ void smp_message_recv(unsigned int msg) generic_smp_call_function_interrupt(); break; case SMP_MSG_RESCHEDULE: + scheduler_ipi(); break; case SMP_MSG_FUNCTION_SINGLE: generic_smp_call_function_single_interrupt(); diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index 91c10fb7085..f95690c167b 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -125,7 +125,9 @@ struct linux_prom_registers smp_penguin_ctable __cpuinitdata = { 0 }; void smp_send_reschedule(int cpu) { - /* See sparc64 */ + /* + * XXX missing reschedule IPI, see scheduler_ipi() + */ } void smp_send_stop(void) diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 3e94a8c2323..9478da7fdb3 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1368,6 +1368,7 @@ void smp_send_reschedule(int cpu) void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); + scheduler_ipi(); } /* This is a nop because we capture all other cpus diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c index a4293102ef8..c52224d5ed4 100644 --- a/arch/tile/kernel/smp.c +++ b/arch/tile/kernel/smp.c @@ -189,12 +189,8 @@ void flush_icache_range(unsigned long start, unsigned long end) /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */ static irqreturn_t handle_reschedule_ipi(int irq, void *token) { - /* - * Nothing to do here; when we return from interrupt, the - * rescheduling will occur there. But do bump the interrupt - * profiler count in the meantime. - */ __get_cpu_var(irq_stat).irq_resched_count++; + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c index 106bf27e2a9..eefb107d2d7 100644 --- a/arch/um/kernel/smp.c +++ b/arch/um/kernel/smp.c @@ -173,7 +173,7 @@ void IPI_handler(int cpu) break; case 'R': - set_tsk_need_resched(current); + scheduler_ipi(); break; case 'S': diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 513deac7228..013e7eba83b 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -194,14 +194,13 @@ static void native_stop_other_cpus(int wait) } /* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. + * Reschedule call back. */ void smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); inc_irq_stat(irq_resched_count); + scheduler_ipi(); /* * KVM uses this interrupt to force a cpu out of guest mode */ diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 30612441ed9..762b46ab14d 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -46,13 +46,12 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id); static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id); /* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. + * Reschedule call back. */ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id) { inc_irq_stat(irq_resched_count); + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ec2c027e92..758e27afcda 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2189,8 +2189,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP +static inline void scheduler_ipi(void) { } extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else +static inline void scheduler_ipi(void) { } static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state) { -- cgit v1.2.3-70-g09d2 From 3ca7a440da394808571dad32d33d3bc0389982e6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:40 +0200 Subject: sched: Always provide p->on_cpu Always provide p->on_cpu so that we can determine if its on a cpu without having to lock the rq. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152728.785452014@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 +--- kernel/sched.c | 46 +++++++++++++++++++++++++++++----------------- 2 files changed, 30 insertions(+), 20 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 758e27afcda..3435837e89f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1200,9 +1200,7 @@ struct task_struct { int lock_depth; /* BKL lock depth */ #ifdef CONFIG_SMP -#ifdef __ARCH_WANT_UNLOCKED_CTXSW - int oncpu; -#endif + int on_cpu; #endif int prio, static_prio, normal_prio; diff --git a/kernel/sched.c b/kernel/sched.c index a187c3fe027..cd2593e1a3e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -838,18 +838,39 @@ static inline int task_current(struct rq *rq, struct task_struct *p) return rq->curr == p; } -#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline int task_running(struct rq *rq, struct task_struct *p) { +#ifdef CONFIG_SMP + return p->on_cpu; +#else return task_current(rq, p); +#endif } +#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { +#ifdef CONFIG_SMP + /* + * We can optimise this out completely for !SMP, because the + * SMP rebalancing from interrupt is the only thing that cares + * here. + */ + next->on_cpu = 1; +#endif } static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_SMP + /* + * After ->on_cpu is cleared, the task can be moved to a different CPU. + * We must ensure this doesn't happen until the switch is completely + * finished. + */ + smp_wmb(); + prev->on_cpu = 0; +#endif #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ rq->lock.owner = current; @@ -865,15 +886,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) } #else /* __ARCH_WANT_UNLOCKED_CTXSW */ -static inline int task_running(struct rq *rq, struct task_struct *p) -{ -#ifdef CONFIG_SMP - return p->oncpu; -#else - return task_current(rq, p); -#endif -} - static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { #ifdef CONFIG_SMP @@ -882,7 +894,7 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) * SMP rebalancing from interrupt is the only thing that cares * here. */ - next->oncpu = 1; + next->on_cpu = 1; #endif #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW raw_spin_unlock_irq(&rq->lock); @@ -895,12 +907,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { #ifdef CONFIG_SMP /* - * After ->oncpu is cleared, the task can be moved to a different CPU. + * After ->on_cpu is cleared, the task can be moved to a different CPU. * We must ensure this doesn't happen until the switch is completely * finished. */ smp_wmb(); - prev->oncpu = 0; + prev->on_cpu = 0; #endif #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_enable(); @@ -2686,8 +2698,8 @@ void sched_fork(struct task_struct *p, int clone_flags) if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - p->oncpu = 0; +#if defined(CONFIG_SMP) + p->on_cpu = 0; #endif #ifdef CONFIG_PREEMPT /* Want to start with kernel preemption disabled. */ @@ -5776,8 +5788,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->curr = rq->idle = idle; -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - idle->oncpu = 1; +#if defined(CONFIG_SMP) + idle->on_cpu = 1; #endif raw_spin_unlock_irqrestore(&rq->lock, flags); -- cgit v1.2.3-70-g09d2 From c6eb3dda25892f1f974f5420f63e6721aab02f6f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:41 +0200 Subject: mutex: Use p->on_cpu for the adaptive spin Since we now have p->on_cpu unconditionally available, use it to re-implement mutex_spin_on_owner. Requested-by: Thomas Gleixner Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.826338173@chello.nl --- include/linux/mutex.h | 2 +- include/linux/sched.h | 2 +- kernel/mutex-debug.c | 2 +- kernel/mutex-debug.h | 2 +- kernel/mutex.c | 2 +- kernel/mutex.h | 2 +- kernel/sched.c | 83 ++++++++++++++++++++------------------------------- 7 files changed, 39 insertions(+), 56 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 94b48bd40dd..c75471db576 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -51,7 +51,7 @@ struct mutex { spinlock_t wait_lock; struct list_head wait_list; #if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP) - struct thread_info *owner; + struct task_struct *owner; #endif #ifdef CONFIG_DEBUG_MUTEXES const char *name; diff --git a/include/linux/sched.h b/include/linux/sched.h index 3435837e89f..173850479e2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -360,7 +360,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); -extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner); +extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; struct user_namespace; diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c index ec815a960b5..73da83aff41 100644 --- a/kernel/mutex-debug.c +++ b/kernel/mutex-debug.c @@ -75,7 +75,7 @@ void debug_mutex_unlock(struct mutex *lock) return; DEBUG_LOCKS_WARN_ON(lock->magic != lock); - DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); + DEBUG_LOCKS_WARN_ON(lock->owner != current); DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); mutex_clear_owner(lock); } diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h index 57d527a16f9..0799fd3e4cf 100644 --- a/kernel/mutex-debug.h +++ b/kernel/mutex-debug.h @@ -29,7 +29,7 @@ extern void debug_mutex_init(struct mutex *lock, const char *name, static inline void mutex_set_owner(struct mutex *lock) { - lock->owner = current_thread_info(); + lock->owner = current; } static inline void mutex_clear_owner(struct mutex *lock) diff --git a/kernel/mutex.c b/kernel/mutex.c index c4195fa9890..fe4706cb0c5 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -160,7 +160,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, */ for (;;) { - struct thread_info *owner; + struct task_struct *owner; /* * If we own the BKL, then don't spin. The owner of diff --git a/kernel/mutex.h b/kernel/mutex.h index 67578ca48f9..4115fbf83b1 100644 --- a/kernel/mutex.h +++ b/kernel/mutex.h @@ -19,7 +19,7 @@ #ifdef CONFIG_SMP static inline void mutex_set_owner(struct mutex *lock) { - lock->owner = current_thread_info(); + lock->owner = current; } static inline void mutex_clear_owner(struct mutex *lock) diff --git a/kernel/sched.c b/kernel/sched.c index cd2593e1a3e..55cc50323ce 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4173,70 +4173,53 @@ need_resched: EXPORT_SYMBOL(schedule); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER -/* - * Look out! "owner" is an entirely speculative pointer - * access and not reliable. - */ -int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) -{ - unsigned int cpu; - struct rq *rq; - if (!sched_feat(OWNER_SPIN)) - return 0; +static inline bool owner_running(struct mutex *lock, struct task_struct *owner) +{ + bool ret = false; -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * Need to access the cpu field knowing that - * DEBUG_PAGEALLOC could have unmapped it if - * the mutex owner just released it and exited. - */ - if (probe_kernel_address(&owner->cpu, cpu)) - return 0; -#else - cpu = owner->cpu; -#endif + rcu_read_lock(); + if (lock->owner != owner) + goto fail; /* - * Even if the access succeeded (likely case), - * the cpu field may no longer be valid. + * Ensure we emit the owner->on_cpu, dereference _after_ checking + * lock->owner still matches owner, if that fails, owner might + * point to free()d memory, if it still matches, the rcu_read_lock() + * ensures the memory stays valid. */ - if (cpu >= nr_cpumask_bits) - return 0; + barrier(); - /* - * We need to validate that we can do a - * get_cpu() and that we have the percpu area. - */ - if (!cpu_online(cpu)) - return 0; + ret = owner->on_cpu; +fail: + rcu_read_unlock(); - rq = cpu_rq(cpu); + return ret; +} - for (;;) { - /* - * Owner changed, break to re-assess state. - */ - if (lock->owner != owner) { - /* - * If the lock has switched to a different owner, - * we likely have heavy contention. Return 0 to quit - * optimistic spinning and not contend further: - */ - if (lock->owner) - return 0; - break; - } +/* + * Look out! "owner" is an entirely speculative pointer + * access and not reliable. + */ +int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +{ + if (!sched_feat(OWNER_SPIN)) + return 0; - /* - * Is that owner really running on that cpu? - */ - if (task_thread_info(rq->curr) != owner || need_resched()) + while (owner_running(lock, owner)) { + if (need_resched()) return 0; arch_mutex_cpu_relax(); } + /* + * If the owner changed to another task there is likely + * heavy contention, stop spinning. + */ + if (lock->owner) + return 0; + return 1; } #endif -- cgit v1.2.3-70-g09d2 From fd2f4419b4cbe8fe90796df9617c355762afd6a4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:44 +0200 Subject: sched: Provide p->on_rq Provide a generic p->on_rq because the p->se.on_rq semantics are unfavourable for lockless wakeups but needed for sched_fair. In particular, p->on_rq is only cleared when we actually dequeue the task in schedule() and not on any random dequeue as done by things like __migrate_task() and __sched_setscheduler(). This also allows us to remove p->se usage from !sched_fair code. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.949545047@chello.nl --- include/linux/sched.h | 1 + kernel/sched.c | 38 ++++++++++++++++++++------------------ kernel/sched_debug.c | 2 +- kernel/sched_rt.c | 16 ++++++++-------- kernel/sched_stoptask.c | 2 +- 5 files changed, 31 insertions(+), 28 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 173850479e2..b33a700652d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1202,6 +1202,7 @@ struct task_struct { #ifdef CONFIG_SMP int on_cpu; #endif + int on_rq; int prio, static_prio, normal_prio; unsigned int rt_priority; diff --git a/kernel/sched.c b/kernel/sched.c index 4481638f917..dece28e505c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1785,7 +1785,6 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) update_rq_clock(rq); sched_info_queued(p); p->sched_class->enqueue_task(rq, p, flags); - p->se.on_rq = 1; } static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) @@ -1793,7 +1792,6 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) update_rq_clock(rq); sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, flags); - p->se.on_rq = 0; } /* @@ -2128,7 +2126,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) * A queue event has occurred, and we're going to schedule. In * this case, we can save a useless back to back clock update. */ - if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr)) + if (rq->curr->on_rq && test_tsk_need_resched(rq->curr)) rq->skip_clock_update = 1; } @@ -2203,7 +2201,7 @@ static bool migrate_task(struct task_struct *p, struct rq *rq) * If the task is not on a runqueue (and not running), then * the next wake-up will properly place the task. */ - return p->se.on_rq || task_running(rq, p); + return p->on_rq || task_running(rq, p); } /* @@ -2263,7 +2261,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) rq = task_rq_lock(p, &flags); trace_sched_wait_task(p); running = task_running(rq, p); - on_rq = p->se.on_rq; + on_rq = p->on_rq; ncsw = 0; if (!match_state || p->state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ @@ -2444,6 +2442,7 @@ ttwu_stat(struct rq *rq, struct task_struct *p, int cpu, int wake_flags) static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) { activate_task(rq, p, en_flags); + p->on_rq = 1; /* if a worker is waking up, notify workqueue */ if (p->flags & PF_WQ_WORKER) @@ -2506,7 +2505,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, cpu = task_cpu(p); - if (p->se.on_rq) + if (p->on_rq) goto out_running; orig_cpu = cpu; @@ -2583,7 +2582,7 @@ static void try_to_wake_up_local(struct task_struct *p) if (!(p->state & TASK_NORMAL)) return; - if (!p->se.on_rq) + if (!p->on_rq) ttwu_activate(rq, p, ENQUEUE_WAKEUP); ttwu_post_activation(p, rq, 0); @@ -2620,19 +2619,21 @@ int wake_up_state(struct task_struct *p, unsigned int state) */ static void __sched_fork(struct task_struct *p) { + p->on_rq = 0; + + p->se.on_rq = 0; p->se.exec_start = 0; p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; p->se.vruntime = 0; + INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif INIT_LIST_HEAD(&p->rt.run_list); - p->se.on_rq = 0; - INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); @@ -2750,6 +2751,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) rq = task_rq_lock(p, &flags); activate_task(rq, p, 0); + p->on_rq = 1; trace_sched_wakeup_new(p, true); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP @@ -4051,7 +4053,7 @@ static inline void schedule_debug(struct task_struct *prev) static void put_prev_task(struct rq *rq, struct task_struct *prev) { - if (prev->se.on_rq) + if (prev->on_rq) update_rq_clock(rq); prev->sched_class->put_prev_task(rq, prev); } @@ -4126,7 +4128,9 @@ need_resched: if (to_wakeup) try_to_wake_up_local(to_wakeup); } + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; /* * If we are going to sleep and we have plugged IO queued, make @@ -4695,7 +4699,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) trace_sched_pi_setprio(p, prio); oldprio = p->prio; prev_class = p->sched_class; - on_rq = p->se.on_rq; + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) dequeue_task(rq, p, 0); @@ -4743,7 +4747,7 @@ void set_user_nice(struct task_struct *p, long nice) p->static_prio = NICE_TO_PRIO(nice); goto out_unlock; } - on_rq = p->se.on_rq; + on_rq = p->on_rq; if (on_rq) dequeue_task(rq, p, 0); @@ -4877,8 +4881,6 @@ static struct task_struct *find_process_by_pid(pid_t pid) static void __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) { - BUG_ON(p->se.on_rq); - p->policy = policy; p->rt_priority = prio; p->normal_prio = normal_prio(p); @@ -5044,7 +5046,7 @@ recheck: raw_spin_unlock_irqrestore(&p->pi_lock, flags); goto recheck; } - on_rq = p->se.on_rq; + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) deactivate_task(rq, p, 0); @@ -5965,7 +5967,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) * If we're not on a rq, the next wake-up will ensure we're * placed properly. */ - if (p->se.on_rq) { + if (p->on_rq) { deactivate_task(rq_src, p, 0); set_task_cpu(p, dest_cpu); activate_task(rq_dest, p, 0); @@ -8339,7 +8341,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p) int old_prio = p->prio; int on_rq; - on_rq = p->se.on_rq; + on_rq = p->on_rq; if (on_rq) deactivate_task(rq, p, 0); __setscheduler(rq, p, SCHED_NORMAL, 0); @@ -8682,7 +8684,7 @@ void sched_move_task(struct task_struct *tsk) rq = task_rq_lock(tsk, &flags); running = task_current(rq, tsk); - on_rq = tsk->se.on_rq; + on_rq = tsk->on_rq; if (on_rq) dequeue_task(rq, tsk, 0); diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 7bacd83a415..3669bec6e13 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -152,7 +152,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) read_lock_irqsave(&tasklist_lock, flags); do_each_thread(g, p) { - if (!p->se.on_rq || task_cpu(p) != rq_cpu) + if (!p->on_rq || task_cpu(p) != rq_cpu) continue; print_task(m, rq, p); diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index e7cebdc65f8..9ca4f5f879c 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1136,7 +1136,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) * The previous task needs to be made eligible for pushing * if it is still active */ - if (p->se.on_rq && p->rt.nr_cpus_allowed > 1) + if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); } @@ -1287,7 +1287,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || task_running(rq, task) || - !task->se.on_rq)) { + !task->on_rq)) { raw_spin_unlock(&lowest_rq->lock); lowest_rq = NULL; @@ -1321,7 +1321,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) BUG_ON(task_current(rq, p)); BUG_ON(p->rt.nr_cpus_allowed <= 1); - BUG_ON(!p->se.on_rq); + BUG_ON(!p->on_rq); BUG_ON(!rt_task(p)); return p; @@ -1467,7 +1467,7 @@ static int pull_rt_task(struct rq *this_rq) */ if (p && (p->prio < this_rq->rt.highest_prio.curr)) { WARN_ON(p == src_rq->curr); - WARN_ON(!p->se.on_rq); + WARN_ON(!p->on_rq); /* * There's a chance that p is higher in priority @@ -1538,7 +1538,7 @@ static void set_cpus_allowed_rt(struct task_struct *p, * Update the migration status of the RQ if we have an RT task * which is running AND changing its weight value. */ - if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) { + if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) { struct rq *rq = task_rq(p); if (!task_current(rq, p)) { @@ -1608,7 +1608,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) * we may need to handle the pulling of RT tasks * now. */ - if (p->se.on_rq && !rq->rt.rt_nr_running) + if (p->on_rq && !rq->rt.rt_nr_running) pull_rt_task(rq); } @@ -1638,7 +1638,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) * If that current running task is also an RT task * then see if we can move to another run queue. */ - if (p->se.on_rq && rq->curr != p) { + if (p->on_rq && rq->curr != p) { #ifdef CONFIG_SMP if (rq->rt.overloaded && push_rt_task(rq) && /* Don't resched if we changed runqueues */ @@ -1657,7 +1657,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) static void prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) { - if (!p->se.on_rq) + if (!p->on_rq) return; if (rq->curr == p) { diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c index 1ba2bd40fda..f607de42e6f 100644 --- a/kernel/sched_stoptask.c +++ b/kernel/sched_stoptask.c @@ -26,7 +26,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq) { struct task_struct *stop = rq->stop; - if (stop && stop->se.on_rq) + if (stop && stop->on_rq) return stop; return NULL; -- cgit v1.2.3-70-g09d2 From 7608dec2ce2004c234339bef8c8074e5e601d0e9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:46 +0200 Subject: sched: Drop the rq argument to sched_class::select_task_rq() In preparation of calling select_task_rq() without rq->lock held, drop the dependency on the rq argument. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.031077745@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +-- kernel/sched.c | 20 +++++++++++--------- kernel/sched_fair.c | 2 +- kernel/sched_idletask.c | 2 +- kernel/sched_rt.c | 38 ++++++++++++++++++++++++++------------ kernel/sched_stoptask.c | 3 +-- 6 files changed, 41 insertions(+), 27 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index b33a700652d..ff4e2f9c24a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1067,8 +1067,7 @@ struct sched_class { void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct rq *rq, struct task_struct *p, - int sd_flag, int flags); + int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); diff --git a/kernel/sched.c b/kernel/sched.c index d398f2f0a3c..d4b815d345b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2195,13 +2195,15 @@ static int migration_cpu_stop(void *data); * The task's runqueue lock must be held. * Returns true if you have to wait for migration thread. */ -static bool migrate_task(struct task_struct *p, struct rq *rq) +static bool need_migrate_task(struct task_struct *p) { /* * If the task is not on a runqueue (and not running), then * the next wake-up will properly place the task. */ - return p->on_rq || task_running(rq, p); + bool running = p->on_rq || p->on_cpu; + smp_rmb(); /* finish_lock_switch() */ + return running; } /* @@ -2376,9 +2378,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. */ static inline -int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags) +int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) { - int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags); + int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags); /* * In order not to call set_task_cpu() on a blocking task we need @@ -2533,7 +2535,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, en_flags |= ENQUEUE_WAKING; } - cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags); + cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); if (cpu != orig_cpu) set_task_cpu(p, cpu); __task_rq_unlock(rq); @@ -2744,7 +2746,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) * We set TASK_WAKING so that select_task_rq() can drop rq->lock * without people poking at ->cpus_allowed. */ - cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0); + cpu = select_task_rq(p, SD_BALANCE_FORK, 0); set_task_cpu(p, cpu); p->state = TASK_RUNNING; @@ -3474,7 +3476,7 @@ void sched_exec(void) int dest_cpu; rq = task_rq_lock(p, &flags); - dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0); + dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); if (dest_cpu == smp_processor_id()) goto unlock; @@ -3482,7 +3484,7 @@ void sched_exec(void) * select_task_rq() can race against ->cpus_allowed */ if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) && - likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) { + likely(cpu_active(dest_cpu)) && need_migrate_task(p)) { struct migration_arg arg = { p, dest_cpu }; task_rq_unlock(rq, &flags); @@ -5911,7 +5913,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) goto out; dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); - if (migrate_task(p, rq)) { + if (need_migrate_task(p)) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ __task_rq_unlock(rq); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 4ee50f0af8d..96b2c95ac35 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1657,7 +1657,7 @@ static int select_idle_sibling(struct task_struct *p, int target) * preempt must be disabled. */ static int -select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags) +select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) { struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; int cpu = smp_processor_id(); diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index a776a639642..0a51882534e 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -7,7 +7,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags) +select_task_rq_idle(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 9ca4f5f879c..19ecb312737 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -977,13 +977,23 @@ static void yield_task_rt(struct rq *rq) static int find_lowest_rq(struct task_struct *task); static int -select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) +select_task_rq_rt(struct task_struct *p, int sd_flag, int flags) { + struct task_struct *curr; + struct rq *rq; + int cpu; + if (sd_flag != SD_BALANCE_WAKE) return smp_processor_id(); + cpu = task_cpu(p); + rq = cpu_rq(cpu); + + rcu_read_lock(); + curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + /* - * If the current task is an RT task, then + * If the current task on @p's runqueue is an RT task, then * try to see if we can wake this RT task up on another * runqueue. Otherwise simply start this RT task * on its current runqueue. @@ -997,21 +1007,25 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) * lock? * * For equal prio tasks, we just let the scheduler sort it out. + * + * Otherwise, just let it ride on the affined RQ and the + * post-schedule router will push the preempted task away + * + * This test is optimistic, if we get it wrong the load-balancer + * will have to sort it out. */ - if (unlikely(rt_task(rq->curr)) && - (rq->curr->rt.nr_cpus_allowed < 2 || - rq->curr->prio < p->prio) && + if (curr && unlikely(rt_task(curr)) && + (curr->rt.nr_cpus_allowed < 2 || + curr->prio < p->prio) && (p->rt.nr_cpus_allowed > 1)) { - int cpu = find_lowest_rq(p); + int target = find_lowest_rq(p); - return (cpu == -1) ? task_cpu(p) : cpu; + if (target != -1) + cpu = target; } + rcu_read_unlock(); - /* - * Otherwise, just let it ride on the affined RQ and the - * post-schedule router will push the preempted task away - */ - return task_cpu(p); + return cpu; } static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c index f607de42e6f..6f437632afa 100644 --- a/kernel/sched_stoptask.c +++ b/kernel/sched_stoptask.c @@ -9,8 +9,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_stop(struct rq *rq, struct task_struct *p, - int sd_flag, int flags) +select_task_rq_stop(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* stop tasks as never migrate */ } -- cgit v1.2.3-70-g09d2 From 74f8e4b2335de45485b8d5b31a504747f13c8070 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:47 +0200 Subject: sched: Remove rq argument to sched_class::task_waking() In preparation of calling this without rq->lock held, remove the dependency on the rq argument. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.071474242@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 10 +++++++--- kernel/sched.c | 2 +- kernel/sched_fair.c | 4 +++- 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index ff4e2f9c24a..7f5732f8c61 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1048,8 +1048,12 @@ struct sched_domain; #define WF_FORK 0x02 /* child wakeup after fork */ #define ENQUEUE_WAKEUP 1 -#define ENQUEUE_WAKING 2 -#define ENQUEUE_HEAD 4 +#define ENQUEUE_HEAD 2 +#ifdef CONFIG_SMP +#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ +#else +#define ENQUEUE_WAKING 0 +#endif #define DEQUEUE_SLEEP 1 @@ -1071,7 +1075,7 @@ struct sched_class { void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); - void (*task_waking) (struct rq *this_rq, struct task_struct *task); + void (*task_waking) (struct task_struct *task); void (*task_woken) (struct rq *this_rq, struct task_struct *task); void (*set_cpus_allowed)(struct task_struct *p, diff --git a/kernel/sched.c b/kernel/sched.c index d4b815d345b..46f42cac4eb 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2531,7 +2531,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, p->state = TASK_WAKING; if (p->sched_class->task_waking) { - p->sched_class->task_waking(rq, p); + p->sched_class->task_waking(p); en_flags |= ENQUEUE_WAKING; } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 96b2c95ac35..ad4c414f456 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1372,11 +1372,13 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) #ifdef CONFIG_SMP -static void task_waking_fair(struct rq *rq, struct task_struct *p) +static void task_waking_fair(struct task_struct *p) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); + lockdep_assert_held(&task_rq(p)->lock); + se->vruntime -= cfs_rq->min_vruntime; } -- cgit v1.2.3-70-g09d2 From a8e4f2eaecc9bfa4954adf79a04f4f22fddd829c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:49 +0200 Subject: sched: Delay task_contributes_to_load() In prepratation of having to call task_contributes_to_load() without holding rq->lock, we need to store the result until we do and can update the rq accounting accordingly. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.151523907@chello.nl --- include/linux/sched.h | 1 + kernel/sched.c | 16 ++++------------ 2 files changed, 5 insertions(+), 12 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 7f5732f8c61..25c50317ddc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1273,6 +1273,7 @@ struct task_struct { /* Revert to default priority/policy when forking */ unsigned sched_reset_on_fork:1; + unsigned sched_contributes_to_load:1; pid_t pid; pid_t tgid; diff --git a/kernel/sched.c b/kernel/sched.c index 7a5eb262078..fd32b78c123 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2519,18 +2519,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, if (unlikely(task_running(rq, p))) goto out_activate; - /* - * In order to handle concurrent wakeups and release the rq->lock - * we put the task in TASK_WAKING state. - * - * First fix up the nr_uninterruptible count: - */ - if (task_contributes_to_load(p)) { - if (likely(cpu_online(orig_cpu))) - rq->nr_uninterruptible--; - else - this_rq()->nr_uninterruptible--; - } + p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; if (p->sched_class->task_waking) { @@ -2555,6 +2544,9 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, WARN_ON(task_cpu(p) != cpu); WARN_ON(p->state != TASK_WAKING); + if (p->sched_contributes_to_load) + rq->nr_uninterruptible--; + out_activate: #endif /* CONFIG_SMP */ ttwu_activate(rq, p, en_flags); -- cgit v1.2.3-70-g09d2 From 317f394160e9beb97d19a84c39b7e5eb3d7815a8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:58 +0200 Subject: sched: Move the second half of ttwu() to the remote cpu Now that we've removed the rq->lock requirement from the first part of ttwu() and can compute placement without holding any rq->lock, ensure we execute the second half of ttwu() on the actual cpu we want the task to run on. This avoids having to take rq->lock and doing the task enqueue remotely, saving lots on cacheline transfers. As measured using: http://oss.oracle.com/~mason/sembench.c $ for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i; done $ echo 4096 32000 64 128 > /proc/sys/kernel/sem $ ./sembench -t 2048 -w 1900 -o 0 unpatched: run time 30 seconds 647278 worker burns per second patched: run time 30 seconds 816715 worker burns per second Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.515897185@chello.nl --- include/linux/sched.h | 3 ++- init/Kconfig | 5 +++++ kernel/sched.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++++ kernel/sched_features.h | 6 ++++++ 4 files changed, 69 insertions(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 25c50317ddc..e09dafa6e14 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1203,6 +1203,7 @@ struct task_struct { int lock_depth; /* BKL lock depth */ #ifdef CONFIG_SMP + struct task_struct *wake_entry; int on_cpu; #endif int on_rq; @@ -2192,7 +2193,7 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP -static inline void scheduler_ipi(void) { } +void scheduler_ipi(void); extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else static inline void scheduler_ipi(void) { } diff --git a/init/Kconfig b/init/Kconfig index 56240e724d9..32745bfe059 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -827,6 +827,11 @@ config SCHED_AUTOGROUP desktop applications. Task group autogeneration is currently based upon task session. +config SCHED_TTWU_QUEUE + bool + depends on !SPARC32 + default y + config MM_OWNER bool diff --git a/kernel/sched.c b/kernel/sched.c index 7d8b85fcdf0..9e3ede120e8 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -556,6 +556,10 @@ struct rq { unsigned int ttwu_count; unsigned int ttwu_local; #endif + +#ifdef CONFIG_SMP + struct task_struct *wake_list; +#endif }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); @@ -2516,10 +2520,61 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) return ret; } +#ifdef CONFIG_SMP +static void sched_ttwu_pending(void) +{ + struct rq *rq = this_rq(); + struct task_struct *list = xchg(&rq->wake_list, NULL); + + if (!list) + return; + + raw_spin_lock(&rq->lock); + + while (list) { + struct task_struct *p = list; + list = list->wake_entry; + ttwu_do_activate(rq, p, 0); + } + + raw_spin_unlock(&rq->lock); +} + +void scheduler_ipi(void) +{ + sched_ttwu_pending(); +} + +static void ttwu_queue_remote(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct task_struct *next = rq->wake_list; + + for (;;) { + struct task_struct *old = next; + + p->wake_entry = next; + next = cmpxchg(&rq->wake_list, old, p); + if (next == old) + break; + } + + if (!next) + smp_send_reschedule(cpu); +} +#endif + static void ttwu_queue(struct task_struct *p, int cpu) { struct rq *rq = cpu_rq(cpu); +#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_TTWU_QUEUE) + if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) { + ttwu_queue_remote(p, cpu); + return; + } +#endif + raw_spin_lock(&rq->lock); ttwu_do_activate(rq, p, 0); raw_spin_unlock(&rq->lock); @@ -6331,6 +6386,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) #ifdef CONFIG_HOTPLUG_CPU case CPU_DYING: + sched_ttwu_pending(); /* Update our root-domain */ raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 68e69acc29b..be40f7371ee 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -64,3 +64,9 @@ SCHED_FEAT(OWNER_SPIN, 1) * Decrement CPU power based on irq activity */ SCHED_FEAT(NONIRQ_POWER, 1) + +/* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ +SCHED_FEAT(TTWU_QUEUE, 1) -- cgit v1.2.3-70-g09d2 From 625f2a378e5a10f45fdc37932fc9f8a21676de9e Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Fri, 22 Apr 2011 11:19:10 -0600 Subject: sched: Get rid of lock_depth Neil Brown pointed out that lock_depth somehow escaped the BKL removal work. Let's get rid of it now. Note that the perf scripting utilities still have a bunch of code for dealing with common_lock_depth in tracepoints; I have left that in place in case anybody wants to use that code with older kernels. Suggested-by: Neil Brown Signed-off-by: Jonathan Corbet Cc: Arnd Bergmann Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110422111910.456c0e84@bike.lwn.net Signed-off-by: Ingo Molnar --- Documentation/trace/kprobetrace.txt | 1 - include/linux/init_task.h | 1 - include/linux/sched.h | 6 ------ kernel/fork.c | 1 - kernel/mutex.c | 7 ------- kernel/sched.c | 11 +---------- kernel/sched_debug.c | 4 ---- kernel/trace/trace_kprobe.c | 1 - tools/perf/Documentation/perf-script-perl.txt | 1 - tools/perf/Documentation/perf-script-python.txt | 1 - 10 files changed, 1 insertion(+), 33 deletions(-) (limited to 'include/linux/sched.h') diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt index 6d27ab8d6e9..c83bd6b4e6e 100644 --- a/Documentation/trace/kprobetrace.txt +++ b/Documentation/trace/kprobetrace.txt @@ -120,7 +120,6 @@ format: field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1;signed:0; field:int common_pid; offset:4; size:4; signed:1; - field:int common_lock_depth; offset:8; size:4; signed:1; field:unsigned long __probe_ip; offset:12; size:4; signed:0; field:int __probe_nargs; offset:16; size:4; signed:1; diff --git a/include/linux/init_task.h b/include/linux/init_task.h index caa151fbebb..689496bb665 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -134,7 +134,6 @@ extern struct cred init_cred; .stack = &init_thread_info, \ .usage = ATOMIC_INIT(2), \ .flags = PF_KTHREAD, \ - .lock_depth = -1, \ .prio = MAX_PRIO-20, \ .static_prio = MAX_PRIO-20, \ .normal_prio = MAX_PRIO-20, \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 171ba24b08a..013314a5610 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -731,10 +731,6 @@ struct sched_info { /* timestamps */ unsigned long long last_arrival,/* when we last ran on a cpu */ last_queued; /* when we were last queued to run */ -#ifdef CONFIG_SCHEDSTATS - /* BKL stats */ - unsigned int bkl_count; -#endif }; #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */ @@ -1190,8 +1186,6 @@ struct task_struct { unsigned int flags; /* per process flags, defined below */ unsigned int ptrace; - int lock_depth; /* BKL lock depth */ - #ifdef CONFIG_SMP struct task_struct *wake_entry; int on_cpu; diff --git a/kernel/fork.c b/kernel/fork.c index e7548dee636..aca62871a4f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1103,7 +1103,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, posix_cpu_timers_init(p); - p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); p->real_start_time = p->start_time; monotonic_to_bootbased(&p->real_start_time); diff --git a/kernel/mutex.c b/kernel/mutex.c index fe4706cb0c5..2c938e2337c 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -162,13 +162,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, for (;;) { struct task_struct *owner; - /* - * If we own the BKL, then don't spin. The owner of - * the mutex might be waiting on us to release the BKL. - */ - if (unlikely(current->lock_depth >= 0)) - break; - /* * If there's an owner, wait for it to either * release the lock or go to sleep. diff --git a/kernel/sched.c b/kernel/sched.c index 8cb0a5769a1..9cde2dd229c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4121,12 +4121,6 @@ static inline void schedule_debug(struct task_struct *prev) profile_hit(SCHED_PROFILING, __builtin_return_address(0)); schedstat_inc(this_rq(), sched_count); -#ifdef CONFIG_SCHEDSTATS - if (unlikely(prev->lock_depth >= 0)) { - schedstat_inc(this_rq(), rq_sched_info.bkl_count); - schedstat_inc(prev, sched_info.bkl_count); - } -#endif } static void put_prev_task(struct rq *rq, struct task_struct *prev) @@ -5852,11 +5846,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) raw_spin_unlock_irqrestore(&rq->lock, flags); /* Set the preempt count _outside_ the spinlocks! */ -#if defined(CONFIG_PREEMPT) - task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0); -#else task_thread_info(idle)->preempt_count = 0; -#endif + /* * The idle tasks have their own, simple scheduling class: */ diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 3669bec6e13..a6710a112b4 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -296,9 +296,6 @@ static void print_cpu(struct seq_file *m, int cpu) P(ttwu_count); P(ttwu_local); - SEQ_printf(m, " .%-30s: %d\n", "bkl_count", - rq->rq_sched_info.bkl_count); - #undef P #undef P64 #endif @@ -441,7 +438,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) P(se.statistics.wait_count); PN(se.statistics.iowait_sum); P(se.statistics.iowait_count); - P(sched_info.bkl_count); P(se.nr_migrations); P(se.statistics.nr_migrations_cold); P(se.statistics.nr_failed_migrations_affine); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 35d55a38614..f925c45f0af 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -53,7 +53,6 @@ const char *reserved_field_names[] = { "common_preempt_count", "common_pid", "common_tgid", - "common_lock_depth", FIELD_STRING_IP, FIELD_STRING_RETIP, FIELD_STRING_FUNC, diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index 5bb41e55a3a..3152cca1550 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -63,7 +63,6 @@ The format file for the sched_wakep event defines the following fields field:unsigned char common_flags; field:unsigned char common_preempt_count; field:int common_pid; - field:int common_lock_depth; field:char comm[TASK_COMM_LEN]; field:pid_t pid; diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 36b38277422..47102206911 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -463,7 +463,6 @@ The format file for the sched_wakep event defines the following fields field:unsigned char common_flags; field:unsigned char common_preempt_count; field:int common_pid; - field:int common_lock_depth; field:char comm[TASK_COMM_LEN]; field:pid_t pid; -- cgit v1.2.3-70-g09d2 From bf26c018490c2fce7fe9b629083b96ce0e6ad019 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 7 Apr 2011 16:53:20 +0200 Subject: ptrace: Prepare to fix racy accesses on task breakpoints When a task is traced and is in a stopped state, the tracer may execute a ptrace request to examine the tracee state and get its task struct. Right after, the tracee can be killed and thus its breakpoints released. This can happen concurrently when the tracer is in the middle of reading or modifying these breakpoints, leading to dereferencing a freed pointer. Hence, to prepare the fix, create a generic breakpoint reference holding API. When a reference on the breakpoints of a task is held, the breakpoints won't be released until the last reference is dropped. After that, no more ptrace request on the task's breakpoints can be serviced for the tracer. Reported-by: Oleg Nesterov Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Will Deacon Cc: Prasad Cc: Paul Mundt Cc: v2.6.33.. Link: http://lkml.kernel.org/r/1302284067-7860-2-git-send-email-fweisbec@gmail.com --- include/linux/ptrace.h | 13 ++++++++++++- include/linux/sched.h | 3 +++ kernel/exit.c | 2 +- kernel/ptrace.c | 17 +++++++++++++++++ 4 files changed, 33 insertions(+), 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index a1147e5dd24..9178d5cc0b0 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -189,6 +189,10 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) child->ptrace = current->ptrace; __ptrace_link(child, current->parent); } + +#ifdef CONFIG_HAVE_HW_BREAKPOINT + atomic_set(&child->ptrace_bp_refcnt, 1); +#endif } /** @@ -350,6 +354,13 @@ extern int task_current_syscall(struct task_struct *target, long *callno, unsigned long args[6], unsigned int maxargs, unsigned long *sp, unsigned long *pc); -#endif +#ifdef CONFIG_HAVE_HW_BREAKPOINT +extern int ptrace_get_breakpoints(struct task_struct *tsk); +extern void ptrace_put_breakpoints(struct task_struct *tsk); +#else +static inline void ptrace_put_breakpoints(struct task_struct *tsk) { } +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ + +#endif /* __KERNEL */ #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 18d63cea284..781abd13767 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1537,6 +1537,9 @@ struct task_struct { unsigned long memsw_nr_pages; /* uncharged mem+swap usage */ } memcg_batch; #endif +#ifdef CONFIG_HAVE_HW_BREAKPOINT + atomic_t ptrace_bp_refcnt; +#endif }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ diff --git a/kernel/exit.c b/kernel/exit.c index f5d2f63bae0..8dd87418154 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1016,7 +1016,7 @@ NORET_TYPE void do_exit(long code) /* * FIXME: do that only when needed, using sched_exit tracepoint */ - flush_ptrace_hw_breakpoint(tsk); + ptrace_put_breakpoints(tsk); exit_notify(tsk, group_dead); #ifdef CONFIG_NUMA diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 0fc1eed28d2..dc7ab65f3b3 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -22,6 +22,7 @@ #include #include #include +#include /* @@ -879,3 +880,19 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, return ret; } #endif /* CONFIG_COMPAT */ + +#ifdef CONFIG_HAVE_HW_BREAKPOINT +int ptrace_get_breakpoints(struct task_struct *tsk) +{ + if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt)) + return 0; + + return -1; +} + +void ptrace_put_breakpoints(struct task_struct *tsk) +{ + if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt)) + flush_ptrace_hw_breakpoint(tsk); +} +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ -- cgit v1.2.3-70-g09d2 From 3e51e3edfd81bfd9853ad7de91167e4ce33d0fe7 Mon Sep 17 00:00:00 2001 From: Samir Bellabes Date: Wed, 11 May 2011 18:18:05 +0200 Subject: sched: Remove unused parameters from sched_fork() and wake_up_new_task() sched_fork() and wake_up_new_task() are defined with a parameter 'unsigned long clone_flags', which is unused. This patch removes the parameters. Signed-off-by: Samir Bellabes Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1305130685-1047-1-git-send-email-sam@synack.fr Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 ++--- kernel/fork.c | 4 ++-- kernel/sched.c | 4 ++-- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6b4280b23ee..12211e1666e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2051,14 +2051,13 @@ extern void xtime_update(unsigned long ticks); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); -extern void wake_up_new_task(struct task_struct *tsk, - unsigned long clone_flags); +extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP extern void kick_process(struct task_struct *tsk); #else static inline void kick_process(struct task_struct *tsk) { } #endif -extern void sched_fork(struct task_struct *p, int clone_flags); +extern void sched_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); extern void proc_caches_init(void); diff --git a/kernel/fork.c b/kernel/fork.c index aca62871a4f..2b44d82b823 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1152,7 +1152,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #endif /* Perform scheduler related setup. Assign this task to a CPU. */ - sched_fork(p, clone_flags); + sched_fork(p); retval = perf_event_init_task(p); if (retval) @@ -1463,7 +1463,7 @@ long do_fork(unsigned long clone_flags, */ p->flags &= ~PF_STARTING; - wake_up_new_task(p, clone_flags); + wake_up_new_task(p); tracehook_report_clone_complete(trace, regs, clone_flags, nr, p); diff --git a/kernel/sched.c b/kernel/sched.c index da933815048..f9778c0d91e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2741,7 +2741,7 @@ static void __sched_fork(struct task_struct *p) /* * fork()/clone()-time setup: */ -void sched_fork(struct task_struct *p, int clone_flags) +void sched_fork(struct task_struct *p) { unsigned long flags; int cpu = get_cpu(); @@ -2823,7 +2823,7 @@ void sched_fork(struct task_struct *p, int clone_flags) * that must be done for every newly created context, then puts the task * on the runqueue and wakes it. */ -void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) +void wake_up_new_task(struct task_struct *p) { unsigned long flags; struct rq *rq; -- cgit v1.2.3-70-g09d2 From 1399fa7807a1a5998bbf147e80668e9950661dfa Mon Sep 17 00:00:00 2001 From: Nikhil Rao Date: Wed, 18 May 2011 10:09:39 -0700 Subject: sched: Introduce SCHED_POWER_SCALE to scale cpu_power calculations SCHED_LOAD_SCALE is used to increase nice resolution and to scale cpu_power calculations in the scheduler. This patch introduces SCHED_POWER_SCALE and converts all uses of SCHED_LOAD_SCALE for scaling cpu_power to use SCHED_POWER_SCALE instead. This is a preparatory patch for increasing the resolution of SCHED_LOAD_SCALE, and there is no need to increase resolution for cpu_power calculations. Signed-off-by: Nikhil Rao Acked-by: Peter Zijlstra Cc: Nikunj A. Dadhania Cc: Srivatsa Vaddagiri Cc: Stephan Barwolf Cc: Mike Galbraith Link: http://lkml.kernel.org/r/1305738580-9924-3-git-send-email-ncrao@google.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 13 ++++++++----- kernel/sched.c | 4 ++-- kernel/sched_fair.c | 52 ++++++++++++++++++++++++++------------------------- 3 files changed, 37 insertions(+), 32 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 12211e1666e..f2f440221b7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -787,18 +787,21 @@ enum cpu_idle_type { CPU_MAX_IDLE_TYPES }; -/* - * sched-domains (multiprocessor balancing) declarations: - */ - /* * Increase resolution of nice-level calculations: */ #define SCHED_LOAD_SHIFT 10 #define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) -#define SCHED_LOAD_SCALE_FUZZ SCHED_LOAD_SCALE +/* + * Increase resolution of cpu_power calculations + */ +#define SCHED_POWER_SHIFT 10 +#define SCHED_POWER_SCALE (1L << SCHED_POWER_SHIFT) +/* + * sched-domains (multiprocessor balancing) declarations: + */ #ifdef CONFIG_SMP #define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */ #define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */ diff --git a/kernel/sched.c b/kernel/sched.c index d036048b59a..375e9c677d5 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6530,7 +6530,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); printk(KERN_CONT " %s", str); - if (group->cpu_power != SCHED_LOAD_SCALE) { + if (group->cpu_power != SCHED_POWER_SCALE) { printk(KERN_CONT " (cpu_power = %d)", group->cpu_power); } @@ -7905,7 +7905,7 @@ void __init sched_init(void) #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; - rq->cpu_power = SCHED_LOAD_SCALE; + rq->cpu_power = SCHED_POWER_SCALE; rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 37f22626225..e32a9b70ee9 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1584,7 +1584,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, } /* Adjust by relative CPU power of the group */ - avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power; + avg_load = (avg_load * SCHED_POWER_SCALE) / group->cpu_power; if (local_group) { this_load = avg_load; @@ -1722,7 +1722,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) nr_running += cpu_rq(i)->cfs.nr_running; } - capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE); + capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE); if (tmp->flags & SD_POWERSAVINGS_BALANCE) nr_running /= 2; @@ -2570,7 +2570,7 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) { - return SCHED_LOAD_SCALE; + return SCHED_POWER_SCALE; } unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu) @@ -2607,10 +2607,10 @@ unsigned long scale_rt_power(int cpu) available = total - rq->rt_avg; } - if (unlikely((s64)total < SCHED_LOAD_SCALE)) - total = SCHED_LOAD_SCALE; + if (unlikely((s64)total < SCHED_POWER_SCALE)) + total = SCHED_POWER_SCALE; - total >>= SCHED_LOAD_SHIFT; + total >>= SCHED_POWER_SHIFT; return div_u64(available, total); } @@ -2618,7 +2618,7 @@ unsigned long scale_rt_power(int cpu) static void update_cpu_power(struct sched_domain *sd, int cpu) { unsigned long weight = sd->span_weight; - unsigned long power = SCHED_LOAD_SCALE; + unsigned long power = SCHED_POWER_SCALE; struct sched_group *sdg = sd->groups; if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { @@ -2627,7 +2627,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu) else power *= default_scale_smt_power(sd, cpu); - power >>= SCHED_LOAD_SHIFT; + power >>= SCHED_POWER_SHIFT; } sdg->cpu_power_orig = power; @@ -2637,10 +2637,10 @@ static void update_cpu_power(struct sched_domain *sd, int cpu) else power *= default_scale_freq_power(sd, cpu); - power >>= SCHED_LOAD_SHIFT; + power >>= SCHED_POWER_SHIFT; power *= scale_rt_power(cpu); - power >>= SCHED_LOAD_SHIFT; + power >>= SCHED_POWER_SHIFT; if (!power) power = 1; @@ -2682,7 +2682,7 @@ static inline int fix_small_capacity(struct sched_domain *sd, struct sched_group *group) { /* - * Only siblings can have significantly less than SCHED_LOAD_SCALE + * Only siblings can have significantly less than SCHED_POWER_SCALE */ if (!(sd->flags & SD_SHARE_CPUPOWER)) return 0; @@ -2770,7 +2770,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, } /* Adjust by relative CPU power of the group */ - sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power; + sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->cpu_power; /* * Consider the group unbalanced when the imbalance is larger @@ -2787,7 +2787,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1) sgs->group_imb = 1; - sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE); + sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, + SCHED_POWER_SCALE); if (!sgs->group_capacity) sgs->group_capacity = fix_small_capacity(sd, group); sgs->group_weight = group->group_weight; @@ -2961,7 +2962,7 @@ static int check_asym_packing(struct sched_domain *sd, return 0; *imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->cpu_power, - SCHED_LOAD_SCALE); + SCHED_POWER_SCALE); return 1; } @@ -2990,7 +2991,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds, cpu_avg_load_per_task(this_cpu); scaled_busy_load_per_task = sds->busiest_load_per_task - * SCHED_LOAD_SCALE; + * SCHED_POWER_SCALE; scaled_busy_load_per_task /= sds->busiest->cpu_power; if (sds->max_load - sds->this_load + scaled_busy_load_per_task >= @@ -3009,10 +3010,10 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds, min(sds->busiest_load_per_task, sds->max_load); pwr_now += sds->this->cpu_power * min(sds->this_load_per_task, sds->this_load); - pwr_now /= SCHED_LOAD_SCALE; + pwr_now /= SCHED_POWER_SCALE; /* Amount of load we'd subtract */ - tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) / + tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) / sds->busiest->cpu_power; if (sds->max_load > tmp) pwr_move += sds->busiest->cpu_power * @@ -3020,15 +3021,15 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds, /* Amount of load we'd add */ if (sds->max_load * sds->busiest->cpu_power < - sds->busiest_load_per_task * SCHED_LOAD_SCALE) + sds->busiest_load_per_task * SCHED_POWER_SCALE) tmp = (sds->max_load * sds->busiest->cpu_power) / sds->this->cpu_power; else - tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) / + tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) / sds->this->cpu_power; pwr_move += sds->this->cpu_power * min(sds->this_load_per_task, sds->this_load + tmp); - pwr_move /= SCHED_LOAD_SCALE; + pwr_move /= SCHED_POWER_SCALE; /* Move if we gain throughput */ if (pwr_move > pwr_now) @@ -3070,7 +3071,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, load_above_capacity = (sds->busiest_nr_running - sds->busiest_group_capacity); - load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_LOAD_SCALE); + load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE); load_above_capacity /= sds->busiest->cpu_power; } @@ -3090,7 +3091,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, /* How much load to actually move to equalise the imbalance */ *imbalance = min(max_pull * sds->busiest->cpu_power, (sds->avg_load - sds->this_load) * sds->this->cpu_power) - / SCHED_LOAD_SCALE; + / SCHED_POWER_SCALE; /* * if *imbalance is less than the average load per runnable task @@ -3159,7 +3160,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (!sds.busiest || sds.busiest_nr_running == 0) goto out_balanced; - sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; + sds.avg_load = (SCHED_POWER_SCALE * sds.total_load) / sds.total_pwr; /* * If the busiest group is imbalanced the below checks don't @@ -3238,7 +3239,8 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group, for_each_cpu(i, sched_group_cpus(group)) { unsigned long power = power_of(i); - unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE); + unsigned long capacity = DIV_ROUND_CLOSEST(power, + SCHED_POWER_SCALE); unsigned long wl; if (!capacity) @@ -3263,7 +3265,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group, * the load can be moved away from the cpu that is potentially * running at a lower capacity. */ - wl = (wl * SCHED_LOAD_SCALE) / power; + wl = (wl * SCHED_POWER_SCALE) / power; if (wl > max_load) { max_load = wl; -- cgit v1.2.3-70-g09d2 From c8b281161dfa4bb5d5be63fb036ce19347b88c63 Mon Sep 17 00:00:00 2001 From: Nikhil Rao Date: Wed, 18 May 2011 14:37:48 -0700 Subject: sched: Increase SCHED_LOAD_SCALE resolution Introduce SCHED_LOAD_RESOLUTION, which scales is added to SCHED_LOAD_SHIFT and increases the resolution of SCHED_LOAD_SCALE. This patch sets the value of SCHED_LOAD_RESOLUTION to 10, scaling up the weights for all sched entities by a factor of 1024. With this extra resolution, we can handle deeper cgroup hiearchies and the scheduler can do better shares distribution and load load balancing on larger systems (especially for low weight task groups). This does not change the existing user interface, the scaled weights are only used internally. We do not modify prio_to_weight values or inverses, but use the original weights when calculating the inverse which is used to scale execution time delta in calc_delta_mine(). This ensures we do not lose accuracy when accounting time to the sched entities. Thanks to Nikunj Dadhania for fixing an bug in c_d_m() that broken fairness. Below is some analysis of the performance costs/improvements of this patch. 1. Micro-arch performance costs: Experiment was to run Ingo's pipe_test_100k 200 times with the task pinned to one cpu. I measured instruction, cycles and stalled-cycles for the runs. See: http://thread.gmane.org/gmane.linux.kernel/1129232/focus=1129389 for more info. -tip (baseline): Performance counter stats for '/root/load-scale/pipe-test-100k' (200 runs): 964,991,769 instructions # 0.82 insns per cycle # 0.33 stalled cycles per insn # ( +- 0.05% ) 1,171,186,635 cycles # 0.000 GHz ( +- 0.08% ) 306,373,664 stalled-cycles-backend # 26.16% backend cycles idle ( +- 0.28% ) 314,933,621 stalled-cycles-frontend # 26.89% frontend cycles idle ( +- 0.34% ) 1.122405684 seconds time elapsed ( +- 0.05% ) -tip+patches: Performance counter stats for './load-scale/pipe-test-100k' (200 runs): 963,624,821 instructions # 0.82 insns per cycle # 0.33 stalled cycles per insn # ( +- 0.04% ) 1,175,215,649 cycles # 0.000 GHz ( +- 0.08% ) 315,321,126 stalled-cycles-backend # 26.83% backend cycles idle ( +- 0.28% ) 316,835,873 stalled-cycles-frontend # 26.96% frontend cycles idle ( +- 0.29% ) 1.122238659 seconds time elapsed ( +- 0.06% ) With this patch, instructions decrease by ~0.10% and cycles increase by 0.27%. This doesn't look statistically significant. The number of stalled cycles in the backend increased from 26.16% to 26.83%. This can be attributed to the shifts we do in c_d_m() and other places. The fraction of stalled cycles in the frontend remains about the same, at 26.96% compared to 26.89% in -tip. 2. Balancing low-weight task groups Test setup: run 50 tasks with random sleep/busy times (biased around 100ms) in a low weight container (with cpu.shares = 2). Measure %idle as reported by mpstat over a 10s window. -tip (baseline): 06:47:48 PM CPU %usr %nice %sys %iowait %irq %soft %steal %guest %idle intr/s 06:47:49 PM all 94.32 0.00 0.06 0.00 0.00 0.00 0.00 0.00 5.62 15888.00 06:47:50 PM all 94.57 0.00 0.62 0.00 0.00 0.00 0.00 0.00 4.81 16180.00 06:47:51 PM all 94.69 0.00 0.06 0.00 0.00 0.00 0.00 0.00 5.25 15966.00 06:47:52 PM all 95.81 0.00 0.00 0.00 0.00 0.00 0.00 0.00 4.19 16053.00 06:47:53 PM all 94.88 0.06 0.00 0.00 0.00 0.00 0.00 0.00 5.06 15984.00 06:47:54 PM all 93.31 0.00 0.00 0.00 0.00 0.00 0.00 0.00 6.69 15806.00 06:47:55 PM all 94.19 0.00 0.06 0.00 0.00 0.00 0.00 0.00 5.75 15896.00 06:47:56 PM all 92.87 0.00 0.00 0.00 0.00 0.00 0.00 0.00 7.13 15716.00 06:47:57 PM all 94.88 0.00 0.00 0.00 0.00 0.00 0.00 0.00 5.12 15982.00 06:47:58 PM all 95.44 0.00 0.00 0.00 0.00 0.00 0.00 0.00 4.56 16075.00 Average: all 94.49 0.01 0.08 0.00 0.00 0.00 0.00 0.00 5.42 15954.60 -tip+patches: 06:47:03 PM CPU %usr %nice %sys %iowait %irq %soft %steal %guest %idle intr/s 06:47:04 PM all 100.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 16630.00 06:47:05 PM all 99.69 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.31 16580.20 06:47:06 PM all 99.69 0.00 0.06 0.00 0.00 0.00 0.00 0.00 0.25 16596.00 06:47:07 PM all 99.20 0.00 0.74 0.00 0.00 0.06 0.00 0.00 0.00 17838.61 06:47:08 PM all 100.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 16540.00 06:47:09 PM all 100.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 16575.00 06:47:10 PM all 100.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 16614.00 06:47:11 PM all 99.94 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.06 16588.00 06:47:12 PM all 99.94 0.00 0.06 0.00 0.00 0.00 0.00 0.00 0.00 16593.00 06:47:13 PM all 99.94 0.00 0.06 0.00 0.00 0.00 0.00 0.00 0.00 16551.00 Average: all 99.84 0.00 0.09 0.00 0.00 0.01 0.00 0.00 0.06 16711.58 We see an improvement in idle% on the system (drops from 5.42% on -tip to 0.06% with the patches). We see an improvement in idle% on the system (drops from 5.42% on -tip to 0.06% with the patches). Signed-off-by: Nikhil Rao Acked-by: Peter Zijlstra Cc: Nikunj A. Dadhania Cc: Srivatsa Vaddagiri Cc: Stephan Barwolf Cc: Mike Galbraith Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/1305754668-18792-1-git-send-email-ncrao@google.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 23 +++++++++++++++++++++-- kernel/sched.c | 28 ++++++++++++++++++++-------- 2 files changed, 41 insertions(+), 10 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index f2f440221b7..c34a718e20d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -788,9 +788,28 @@ enum cpu_idle_type { }; /* - * Increase resolution of nice-level calculations: + * Increase resolution of nice-level calculations for 64-bit architectures. + * The extra resolution improves shares distribution and load balancing of + * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup + * hierarchies, especially on larger systems. This is not a user-visible change + * and does not change the user-interface for setting shares/weights. + * + * We increase resolution only if we have enough bits to allow this increased + * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution + * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the + * increased costs. */ -#define SCHED_LOAD_SHIFT 10 +#if BITS_PER_LONG > 32 +# define SCHED_LOAD_RESOLUTION 10 +# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) +# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) +#else +# define SCHED_LOAD_RESOLUTION 0 +# define scale_load(w) (w) +# define scale_load_down(w) (w) +#endif + +#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION) #define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) /* diff --git a/kernel/sched.c b/kernel/sched.c index 375e9c677d5..bb504e1839e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -293,7 +293,7 @@ static DEFINE_SPINLOCK(task_group_lock); * limitation from this.) */ #define MIN_SHARES 2 -#define MAX_SHARES (1UL << 18) +#define MAX_SHARES (1UL << (18 + SCHED_LOAD_RESOLUTION)) static int root_task_group_load = ROOT_TASK_GROUP_LOAD; #endif @@ -1330,13 +1330,25 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight, { u64 tmp; - tmp = (u64)delta_exec * weight; + /* + * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched + * entities since MIN_SHARES = 2. Treat weight as 1 if less than + * 2^SCHED_LOAD_RESOLUTION. + */ + if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION))) + tmp = (u64)delta_exec * scale_load_down(weight); + else + tmp = (u64)delta_exec; if (!lw->inv_weight) { - if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST)) + unsigned long w = scale_load_down(lw->weight); + + if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) lw->inv_weight = 1; + else if (unlikely(!w)) + lw->inv_weight = WMULT_CONST; else - lw->inv_weight = WMULT_CONST / lw->weight; + lw->inv_weight = WMULT_CONST / w; } /* @@ -1785,12 +1797,12 @@ static void set_load_weight(struct task_struct *p) * SCHED_IDLE tasks get minimal weight: */ if (p->policy == SCHED_IDLE) { - load->weight = WEIGHT_IDLEPRIO; + load->weight = scale_load(WEIGHT_IDLEPRIO); load->inv_weight = WMULT_IDLEPRIO; return; } - load->weight = prio_to_weight[prio]; + load->weight = scale_load(prio_to_weight[prio]); load->inv_weight = prio_to_wmult[prio]; } @@ -8809,14 +8821,14 @@ cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype, u64 shareval) { - return sched_group_set_shares(cgroup_tg(cgrp), shareval); + return sched_group_set_shares(cgroup_tg(cgrp), scale_load(shareval)); } static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) { struct task_group *tg = cgroup_tg(cgrp); - return (u64) tg->shares; + return (u64) scale_load_down(tg->shares); } #endif /* CONFIG_FAIR_GROUP_SCHED */ -- cgit v1.2.3-70-g09d2 From 586692a5a5fc5740c8a46abc0f2365495c2d7c5f Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Sun, 22 May 2011 22:10:22 -0700 Subject: watchdog: Disable watchdog when thresh is zero This restores the previous behavior of softlock_thresh. Currently, setting watchdog_thresh to zero causes the watchdog kthreads to consume a lot of CPU. In addition, the logic of proc_dowatchdog_thresh and proc_dowatchdog_enabled has been factored into proc_dowatchdog. Signed-off-by: Mandeep Singh Baines Cc: Marcin Slusarz Cc: Don Zickus Cc: Peter Zijlstra Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/1306127423-3347-3-git-send-email-msb@chromium.org Signed-off-by: Ingo Molnar LKML-Reference: <20110517071018.GE22305@elte.hu> --- include/linux/nmi.h | 5 +++-- include/linux/sched.h | 1 - kernel/sysctl.c | 12 ++++++++---- kernel/watchdog.c | 25 +++++++++---------------- 4 files changed, 20 insertions(+), 23 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index c536f8545f7..5317b8b2198 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -47,9 +47,10 @@ static inline bool trigger_all_cpu_backtrace(void) int hw_nmi_is_cpu_stuck(struct pt_regs *); u64 hw_nmi_get_sample_period(void); extern int watchdog_enabled; +extern int watchdog_thresh; struct ctl_table; -extern int proc_dowatchdog_enabled(struct ctl_table *, int , - void __user *, size_t *, loff_t *); +extern int proc_dowatchdog(struct ctl_table *, int , + void __user *, size_t *, loff_t *); #endif #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 12211e1666e..d8b2d0bec0d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -315,7 +315,6 @@ extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; -extern int softlockup_thresh; void lockup_detector_init(void); #else static inline void touch_softlockup_watchdog(void) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c0bb32414b1..3dd0c46fa3b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -730,14 +730,16 @@ static struct ctl_table kern_table[] = { .data = &watchdog_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = proc_dowatchdog_enabled, + .proc_handler = proc_dowatchdog, + .extra1 = &zero, + .extra2 = &one, }, { .procname = "watchdog_thresh", - .data = &softlockup_thresh, + .data = &watchdog_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dowatchdog_thresh, + .proc_handler = proc_dowatchdog, .extra1 = &neg_one, .extra2 = &sixty, }, @@ -755,7 +757,9 @@ static struct ctl_table kern_table[] = { .data = &watchdog_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = proc_dowatchdog_enabled, + .proc_handler = proc_dowatchdog, + .extra1 = &zero, + .extra2 = &one, }, #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index cf0e09f452e..60301916f62 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -28,7 +28,7 @@ #include int watchdog_enabled = 1; -int __read_mostly softlockup_thresh = 60; +int __read_mostly watchdog_thresh = 60; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); @@ -105,12 +105,12 @@ static unsigned long get_timestamp(int this_cpu) static unsigned long get_sample_period(void) { /* - * convert softlockup_thresh from seconds to ns + * convert watchdog_thresh from seconds to ns * the divide by 5 is to give hrtimer 5 chances to * increment before the hardlockup detector generates * a warning */ - return softlockup_thresh * (NSEC_PER_SEC / 5); + return watchdog_thresh * (NSEC_PER_SEC / 5); } /* Commands for resetting the watchdog */ @@ -182,7 +182,7 @@ static int is_softlockup(unsigned long touch_ts) unsigned long now = get_timestamp(smp_processor_id()); /* Warn about unreasonable delays: */ - if (time_after(now, touch_ts + softlockup_thresh)) + if (time_after(now, touch_ts + watchdog_thresh)) return now - touch_ts; return 0; @@ -501,19 +501,19 @@ static void watchdog_disable_all_cpus(void) /* sysctl functions */ #ifdef CONFIG_SYSCTL /* - * proc handler for /proc/sys/kernel/nmi_watchdog + * proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh */ -int proc_dowatchdog_enabled(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) +int proc_dowatchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_dointvec(table, write, buffer, length, ppos); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) goto out; - if (watchdog_enabled) + if (watchdog_enabled && watchdog_thresh) watchdog_enable_all_cpus(); else watchdog_disable_all_cpus(); @@ -521,13 +521,6 @@ int proc_dowatchdog_enabled(struct ctl_table *table, int write, out: return ret; } - -int proc_dowatchdog_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) -{ - return proc_dointvec_minmax(table, write, buffer, lenp, ppos); -} #endif /* CONFIG_SYSCTL */ -- cgit v1.2.3-70-g09d2 From 72788c385604523422592249c19cba0187021e9b Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 24 May 2011 17:11:40 -0700 Subject: oom: replace PF_OOM_ORIGIN with toggling oom_score_adj There's a kernel-wide shortage of per-process flags, so it's always helpful to trim one when possible without incurring a significant penalty. It's even more important when you're planning on adding a per- process flag yourself, which I plan to do shortly for transparent hugepages. PF_OOM_ORIGIN is used by ksm and swapoff to prefer current since it has a tendency to allocate large amounts of memory and should be preferred for killing over other tasks. We'd rather immediately kill the task making the errant syscall rather than penalizing an innocent task. This patch removes PF_OOM_ORIGIN since its behavior is equivalent to setting the process's oom_score_adj to OOM_SCORE_ADJ_MAX. The process's old oom_score_adj is stored and then set to OOM_SCORE_ADJ_MAX during the time it used to have PF_OOM_ORIGIN. The old value is then reinstated when the process should no longer be considered a high priority for oom killing. Signed-off-by: David Rientjes Reviewed-by: KOSAKI Motohiro Reviewed-by: Minchan Kim Cc: Hugh Dickins Cc: Izik Eidus Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 2 ++ include/linux/sched.h | 1 - mm/ksm.c | 7 +++++-- mm/oom_kill.c | 36 +++++++++++++++++++++++++++--------- mm/swapfile.c | 6 ++++-- 5 files changed, 38 insertions(+), 14 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/oom.h b/include/linux/oom.h index 5e3aa8311c5..4952fb874ad 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -40,6 +40,8 @@ enum oom_constraint { CONSTRAINT_MEMCG, }; +extern int test_set_oom_score_adj(int new_val); + extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, const nodemask_t *nodemask, unsigned long totalpages); extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); diff --git a/include/linux/sched.h b/include/linux/sched.h index aaf71e08222..44b8faaac7c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1753,7 +1753,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define PF_FROZEN 0x00010000 /* frozen for system suspend */ #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ #define PF_KSWAPD 0x00040000 /* I am kswapd */ -#define PF_OOM_ORIGIN 0x00080000 /* Allocating much memory to others */ #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ diff --git a/mm/ksm.c b/mm/ksm.c index 942dfc73a2f..d708b3ef226 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include "internal.h" @@ -1894,9 +1895,11 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, if (ksm_run != flags) { ksm_run = flags; if (flags & KSM_RUN_UNMERGE) { - current->flags |= PF_OOM_ORIGIN; + int oom_score_adj; + + oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX); err = unmerge_and_remove_all_rmap_items(); - current->flags &= ~PF_OOM_ORIGIN; + test_set_oom_score_adj(oom_score_adj); if (err) { ksm_run = KSM_RUN_STOP; count = err; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f52e85c80e8..e4b0991ca35 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -38,6 +38,33 @@ int sysctl_oom_kill_allocating_task; int sysctl_oom_dump_tasks = 1; static DEFINE_SPINLOCK(zone_scan_lock); +/** + * test_set_oom_score_adj() - set current's oom_score_adj and return old value + * @new_val: new oom_score_adj value + * + * Sets the oom_score_adj value for current to @new_val with proper + * synchronization and returns the old value. Usually used to temporarily + * set a value, save the old value in the caller, and then reinstate it later. + */ +int test_set_oom_score_adj(int new_val) +{ + struct sighand_struct *sighand = current->sighand; + int old_val; + + spin_lock_irq(&sighand->siglock); + old_val = current->signal->oom_score_adj; + if (new_val != old_val) { + if (new_val == OOM_SCORE_ADJ_MIN) + atomic_inc(¤t->mm->oom_disable_count); + else if (old_val == OOM_SCORE_ADJ_MIN) + atomic_dec(¤t->mm->oom_disable_count); + current->signal->oom_score_adj = new_val; + } + spin_unlock_irq(&sighand->siglock); + + return old_val; +} + #ifdef CONFIG_NUMA /** * has_intersects_mems_allowed() - check task eligiblity for kill @@ -154,15 +181,6 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, return 0; } - /* - * When the PF_OOM_ORIGIN bit is set, it indicates the task should have - * priority for oom killing. - */ - if (p->flags & PF_OOM_ORIGIN) { - task_unlock(p); - return 1000; - } - /* * The memory controller may have a limit of 0 bytes, so avoid a divide * by zero, if necessary. diff --git a/mm/swapfile.c b/mm/swapfile.c index 8c6b3ce38f0..d537d29e9b7 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -1555,6 +1556,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct address_space *mapping; struct inode *inode; char *pathname; + int oom_score_adj; int i, type, prev; int err; @@ -1613,9 +1615,9 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) p->flags &= ~SWP_WRITEOK; spin_unlock(&swap_lock); - current->flags |= PF_OOM_ORIGIN; + oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX); err = try_to_unuse(type); - current->flags &= ~PF_OOM_ORIGIN; + test_set_oom_score_adj(oom_score_adj); if (err) { /* -- cgit v1.2.3-70-g09d2 From de03c72cfce5b263a674d04348b58475ec50163c Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 24 May 2011 17:12:15 -0700 Subject: mm: convert mm->cpu_vm_cpumask into cpumask_var_t cpumask_t is very big struct and cpu_vm_mask is placed wrong position. It might lead to reduce cache hit ratio. This patch has two change. 1) Move the place of cpumask into last of mm_struct. Because usually cpumask is accessed only front bits when the system has cpu-hotplug capability 2) Convert cpu_vm_mask into cpumask_var_t. It may help to reduce memory footprint if cpumask_size() will use nr_cpumask_bits properly in future. In addition, this patch change the name of cpu_vm_mask with cpu_vm_mask_var. It may help to detect out of tree cpu_vm_mask users. This patch has no functional change. [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: KOSAKI Motohiro Cc: David Howells Cc: Koichi Yasutake Cc: Hugh Dickins Cc: Chris Metcalf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cachetlb.txt | 2 +- arch/x86/kernel/tboot.c | 1 - include/linux/mm_types.h | 9 ++++++--- include/linux/sched.h | 1 + init/main.c | 2 ++ kernel/fork.c | 37 ++++++++++++++++++++++++++++++++++--- mm/init-mm.c | 1 - 7 files changed, 44 insertions(+), 9 deletions(-) (limited to 'include/linux/sched.h') diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt index 9164ae3b83b..9b728dc1753 100644 --- a/Documentation/cachetlb.txt +++ b/Documentation/cachetlb.txt @@ -16,7 +16,7 @@ on all processors in the system. Don't let this scare you into thinking SMP cache/tlb flushing must be so inefficient, this is in fact an area where many optimizations are possible. For example, if it can be proven that a user address space has never executed -on a cpu (see vma->cpu_vm_mask), one need not perform a flush +on a cpu (see mm_cpumask()), one need not perform a flush for this address space on that cpu. First, the TLB flushing interfaces, since they are the simplest. The diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 998e972f3b1..30ac65df7d4 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -110,7 +110,6 @@ static struct mm_struct tboot_mm = { .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem), .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), - .cpu_vm_mask = CPU_MASK_ALL, }; static inline void switch_to_tboot_pt(void) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 201998e5b53..c2f9ea7922f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -265,8 +265,6 @@ struct mm_struct { struct linux_binfmt *binfmt; - cpumask_t cpu_vm_mask; - /* Architecture-specific MM context */ mm_context_t context; @@ -316,9 +314,14 @@ struct mm_struct { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif + + cpumask_var_t cpu_vm_mask_var; }; /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ -#define mm_cpumask(mm) (&(mm)->cpu_vm_mask) +static inline cpumask_t *mm_cpumask(struct mm_struct *mm) +{ + return mm->cpu_vm_mask_var; +} #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 44b8faaac7c..f18300eddfc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2176,6 +2176,7 @@ static inline void mmdrop(struct mm_struct * mm) if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } +extern int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm); /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); diff --git a/init/main.c b/init/main.c index 48df882d51d..22da33918ae 100644 --- a/init/main.c +++ b/init/main.c @@ -509,6 +509,8 @@ asmlinkage void __init start_kernel(void) sort_main_extable(); trap_init(); mm_init(); + BUG_ON(mm_init_cpumask(&init_mm, 0)); + /* * Set up the scheduler prior starting any interrupts (such as the * timer interrupt). Full topology setup happens at smp_init() diff --git a/kernel/fork.c b/kernel/fork.c index 927692734bc..8e7e135d081 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -485,6 +485,20 @@ static void mm_init_aio(struct mm_struct *mm) #endif } +int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm) +{ +#ifdef CONFIG_CPUMASK_OFFSTACK + if (!alloc_cpumask_var(&mm->cpu_vm_mask_var, GFP_KERNEL)) + return -ENOMEM; + + if (oldmm) + cpumask_copy(mm_cpumask(mm), mm_cpumask(oldmm)); + else + memset(mm_cpumask(mm), 0, cpumask_size()); +#endif + return 0; +} + static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); @@ -521,10 +535,20 @@ struct mm_struct * mm_alloc(void) struct mm_struct * mm; mm = allocate_mm(); - if (mm) { - memset(mm, 0, sizeof(*mm)); - mm = mm_init(mm, current); + if (!mm) + return NULL; + + memset(mm, 0, sizeof(*mm)); + mm = mm_init(mm, current); + if (!mm) + return NULL; + + if (mm_init_cpumask(mm, NULL)) { + mm_free_pgd(mm); + free_mm(mm); + return NULL; } + return mm; } @@ -536,6 +560,7 @@ struct mm_struct * mm_alloc(void) void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); + free_cpumask_var(mm->cpu_vm_mask_var); mm_free_pgd(mm); destroy_context(mm); mmu_notifier_mm_destroy(mm); @@ -690,6 +715,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk) if (!mm_init(mm, tsk)) goto fail_nomem; + if (mm_init_cpumask(mm, oldmm)) + goto fail_nocpumask; + if (init_new_context(tsk, mm)) goto fail_nocontext; @@ -716,6 +744,9 @@ fail_nomem: return NULL; fail_nocontext: + free_cpumask_var(mm->cpu_vm_mask_var); + +fail_nocpumask: /* * If init_new_context() failed, we cannot use mmput() to free the mm * because it calls destroy_context() diff --git a/mm/init-mm.c b/mm/init-mm.c index 1d29cdfe8eb..4019979b263 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -21,6 +21,5 @@ struct mm_struct init_mm = { .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem), .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), - .cpu_vm_mask = CPU_MASK_ALL, INIT_MM_CONTEXT(init_mm) }; -- cgit v1.2.3-70-g09d2 From b1cff0ad1062621ae63cb6c5dc4165191fe2e9f1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 25 May 2011 14:27:43 -0400 Subject: ftrace: Add internal recursive checks Witold reported a reboot caused by the selftests of the dynamic function tracer. He sent me a config and I used ktest to do a config_bisect on it (as my config did not cause the crash). It pointed out that the problem config was CONFIG_PROVE_RCU. What happened was that if multiple callbacks are attached to the function tracer, we iterate a list of callbacks. Because the list is managed by synchronize_sched() and preempt_disable, the access to the pointers uses rcu_dereference_raw(). When PROVE_RCU is enabled, the rcu_dereference_raw() calls some debugging functions, which happen to be traced. The tracing of the debug function would then call rcu_dereference_raw() which would then call the debug function and then... well you get the idea. I first wrote two different patches to solve this bug. 1) add a __rcu_dereference_raw() that would not do any checks. 2) add notrace to the offending debug functions. Both of these patches worked. Talking with Paul McKenney on IRC, he suggested to add recursion detection instead. This seemed to be a better solution, so I decided to implement it. As the task_struct already has a trace_recursion to detect recursion in the ring buffer, and that has a very small number it allows, I decided to use that same variable to add flags that can detect the recursion inside the infrastructure of the function tracer. I plan to change it so that the task struct bit can be checked in mcount, but as that requires changes to all archs, I will hold that off to the next merge window. Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Frederic Weisbecker Cc: Paul E. McKenney Link: http://lkml.kernel.org/r/1306348063.1465.116.camel@gandalf.stny.rr.com Reported-by: Witold Baryluk Signed-off-by: Steven Rostedt --- include/linux/sched.h | 2 +- kernel/trace/ftrace.c | 13 ++++++++++++- kernel/trace/ring_buffer.c | 10 +++++----- kernel/trace/trace.h | 15 +++++++++++++++ 4 files changed, 33 insertions(+), 7 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index d8b2d0bec0d..7b78d9cad47 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1513,7 +1513,7 @@ struct task_struct { #ifdef CONFIG_TRACING /* state flags for use by tracers */ unsigned long trace; - /* bitmask of trace recursion */ + /* bitmask and counter of trace recursion */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */ diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 25949b33057..1ee417fcbfa 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -109,12 +109,18 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); static void ftrace_global_list_func(unsigned long ip, unsigned long parent_ip) { - struct ftrace_ops *op = rcu_dereference_raw(ftrace_global_list); /*see above*/ + struct ftrace_ops *op; + + if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT))) + return; + trace_recursion_set(TRACE_GLOBAL_BIT); + op = rcu_dereference_raw(ftrace_global_list); /*see above*/ while (op != &ftrace_list_end) { op->func(ip, parent_ip); op = rcu_dereference_raw(op->next); /*see above*/ }; + trace_recursion_clear(TRACE_GLOBAL_BIT); } static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip) @@ -3490,6 +3496,10 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) { struct ftrace_ops *op; + if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT))) + return; + + trace_recursion_set(TRACE_INTERNAL_BIT); /* * Some of the ops may be dynamically allocated, * they must be freed after a synchronize_sched(). @@ -3502,6 +3512,7 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) op = rcu_dereference_raw(op->next); }; preempt_enable_notrace(); + trace_recursion_clear(TRACE_INTERNAL_BIT); } static void clear_ftrace_swapper(void) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 0ef7b4b2a1f..b0c7aa40794 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2216,7 +2216,7 @@ static noinline void trace_recursive_fail(void) printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:" "HC[%lu]:SC[%lu]:NMI[%lu]\n", - current->trace_recursion, + trace_recursion_buffer(), hardirq_count() >> HARDIRQ_SHIFT, softirq_count() >> SOFTIRQ_SHIFT, in_nmi()); @@ -2226,9 +2226,9 @@ static noinline void trace_recursive_fail(void) static inline int trace_recursive_lock(void) { - current->trace_recursion++; + trace_recursion_inc(); - if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH)) + if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH)) return 0; trace_recursive_fail(); @@ -2238,9 +2238,9 @@ static inline int trace_recursive_lock(void) static inline void trace_recursive_unlock(void) { - WARN_ON_ONCE(!current->trace_recursion); + WARN_ON_ONCE(!trace_recursion_buffer()); - current->trace_recursion--; + trace_recursion_dec(); } #else diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6b69c4bd306..229f8591f61 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -784,4 +784,19 @@ extern const char *__stop___trace_bprintk_fmt[]; FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" +/* Only current can touch trace_recursion */ +#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0) +#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0) + +/* Ring buffer has the 10 LSB bits to count */ +#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff) + +/* for function tracing recursion */ +#define TRACE_INTERNAL_BIT (1<<11) +#define TRACE_GLOBAL_BIT (1<<12) + +#define trace_recursion_set(bit) do { (current)->trace_recursion |= (bit); } while (0) +#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(bit); } while (0) +#define trace_recursion_test(bit) ((current)->trace_recursion & (bit)) + #endif /* _LINUX_KERNEL_TRACE_H */ -- cgit v1.2.3-70-g09d2 From 4714d1d32d97239fb5ae3e10521d3f133a899b66 Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Thu, 26 May 2011 16:25:18 -0700 Subject: cgroups: read-write lock CLONE_THREAD forking per threadgroup Adds functionality to read/write lock CLONE_THREAD fork()ing per-threadgroup Add an rwsem that lives in a threadgroup's signal_struct that's taken for reading in the fork path, under CONFIG_CGROUPS. If another part of the kernel later wants to use such a locking mechanism, the CONFIG_CGROUPS ifdefs should be changed to a higher-up flag that CGROUPS and the other system would both depend on. This is a pre-patch for cgroup-procs-write.patch. Signed-off-by: Ben Blum Cc: "Eric W. Biederman" Cc: Li Zefan Cc: Matt Helsley Reviewed-by: Paul Menage Cc: Oleg Nesterov Cc: David Rientjes Cc: Miao Xie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 9 +++++++++ include/linux/sched.h | 36 ++++++++++++++++++++++++++++++++++++ kernel/fork.c | 10 ++++++++++ 3 files changed, 55 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index bafc58c00fc..580f70c0239 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -22,6 +22,14 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; +#ifdef CONFIG_CGROUPS +#define INIT_THREADGROUP_FORK_LOCK(sig) \ + .threadgroup_fork_lock = \ + __RWSEM_INITIALIZER(sig.threadgroup_fork_lock), +#else +#define INIT_THREADGROUP_FORK_LOCK(sig) +#endif + #define INIT_SIGNALS(sig) { \ .nr_threads = 1, \ .wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\ @@ -38,6 +46,7 @@ extern struct fs_struct init_fs; }, \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ + INIT_THREADGROUP_FORK_LOCK(sig) \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/sched.h b/include/linux/sched.h index f18300eddfc..dc8871295a5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -513,6 +513,7 @@ struct thread_group_cputimer { spinlock_t lock; }; +#include struct autogroup; /* @@ -632,6 +633,16 @@ struct signal_struct { unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif +#ifdef CONFIG_CGROUPS + /* + * The threadgroup_fork_lock prevents threads from forking with + * CLONE_THREAD while held for writing. Use this for fork-sensitive + * threadgroup-wide operations. It's taken for reading in fork.c in + * copy_process(). + * Currently only needed write-side by cgroups. + */ + struct rw_semaphore threadgroup_fork_lock; +#endif int oom_adj; /* OOM kill score adjustment (bit shift) */ int oom_score_adj; /* OOM kill score adjustment */ @@ -2323,6 +2334,31 @@ static inline void unlock_task_sighand(struct task_struct *tsk, spin_unlock_irqrestore(&tsk->sighand->siglock, *flags); } +/* See the declaration of threadgroup_fork_lock in signal_struct. */ +#ifdef CONFIG_CGROUPS +static inline void threadgroup_fork_read_lock(struct task_struct *tsk) +{ + down_read(&tsk->signal->threadgroup_fork_lock); +} +static inline void threadgroup_fork_read_unlock(struct task_struct *tsk) +{ + up_read(&tsk->signal->threadgroup_fork_lock); +} +static inline void threadgroup_fork_write_lock(struct task_struct *tsk) +{ + down_write(&tsk->signal->threadgroup_fork_lock); +} +static inline void threadgroup_fork_write_unlock(struct task_struct *tsk) +{ + up_write(&tsk->signal->threadgroup_fork_lock); +} +#else +static inline void threadgroup_fork_read_lock(struct task_struct *tsk) {} +static inline void threadgroup_fork_read_unlock(struct task_struct *tsk) {} +static inline void threadgroup_fork_write_lock(struct task_struct *tsk) {} +static inline void threadgroup_fork_write_unlock(struct task_struct *tsk) {} +#endif + #ifndef __HAVE_THREAD_FUNCTIONS #define task_thread_info(task) ((struct thread_info *)(task)->stack) diff --git a/kernel/fork.c b/kernel/fork.c index 8e7e135d081..1fa9d940e30 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -957,6 +957,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) tty_audit_fork(sig); sched_autogroup_fork(sig); +#ifdef CONFIG_CGROUPS + init_rwsem(&sig->threadgroup_fork_lock); +#endif + sig->oom_adj = current->signal->oom_adj; sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; @@ -1138,6 +1142,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, monotonic_to_bootbased(&p->real_start_time); p->io_context = NULL; p->audit_context = NULL; + if (clone_flags & CLONE_THREAD) + threadgroup_fork_read_lock(current); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); @@ -1342,6 +1348,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, write_unlock_irq(&tasklist_lock); proc_fork_connector(p); cgroup_post_fork(p); + if (clone_flags & CLONE_THREAD) + threadgroup_fork_read_unlock(current); perf_event_fork(p); return p; @@ -1380,6 +1388,8 @@ bad_fork_cleanup_policy: mpol_put(p->mempolicy); bad_fork_cleanup_cgroup: #endif + if (clone_flags & CLONE_THREAD) + threadgroup_fork_read_unlock(current); cgroup_exit(p, cgroup_callbacks_done); delayacct_tsk_free(p); module_put(task_thread_info(p)->exec_domain->module); -- cgit v1.2.3-70-g09d2 From 1e1b6c511d1b23cb7c3b619d82fc7bd9f620565d Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 19 May 2011 15:08:58 +0900 Subject: cpuset: Fix cpuset_cpus_allowed_fallback(), don't update tsk->rt.nr_cpus_allowed The rule is, we have to update tsk->rt.nr_cpus_allowed if we change tsk->cpus_allowed. Otherwise RT scheduler may confuse. Signed-off-by: KOSAKI Motohiro Cc: Oleg Nesterov Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/4DD4B3FA.5060901@jp.fujitsu.com Signed-off-by: Ingo Molnar --- include/linux/cpuset.h | 2 +- include/linux/sched.h | 7 +++++++ kernel/cpuset.c | 4 ++-- kernel/kthread.c | 4 ++-- kernel/sched.c | 19 ++++++++++++------- 5 files changed, 24 insertions(+), 12 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index f20eb8f1602..e9eaec52265 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -146,7 +146,7 @@ static inline void cpuset_cpus_allowed(struct task_struct *p, static inline int cpuset_cpus_allowed_fallback(struct task_struct *p) { - cpumask_copy(&p->cpus_allowed, cpu_possible_mask); + do_set_cpus_allowed(p, cpu_possible_mask); return cpumask_any(cpu_active_mask); } diff --git a/include/linux/sched.h b/include/linux/sched.h index dc8871295a5..8da84b7bc1b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1841,9 +1841,16 @@ static inline void rcu_copy_process(struct task_struct *p) #endif #ifdef CONFIG_SMP +extern void do_set_cpus_allowed(struct task_struct *p, + const struct cpumask *new_mask); + extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); #else +static inline void do_set_cpus_allowed(struct task_struct *p, + const struct cpumask *new_mask) +{ +} static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 1ceeb049c82..9c9b7545c81 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2190,7 +2190,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk) rcu_read_lock(); cs = task_cs(tsk); if (cs) - cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed); + do_set_cpus_allowed(tsk, cs->cpus_allowed); rcu_read_unlock(); /* @@ -2217,7 +2217,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk) * Like above we can temporary set any mask and rely on * set_cpus_allowed_ptr() as synchronization point. */ - cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask); + do_set_cpus_allowed(tsk, cpu_possible_mask); cpu = cpumask_any(cpu_active_mask); } diff --git a/kernel/kthread.c b/kernel/kthread.c index 3b34d2732bc..4ba7cccb499 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -202,8 +202,8 @@ void kthread_bind(struct task_struct *p, unsigned int cpu) return; } - p->cpus_allowed = cpumask_of_cpu(cpu); - p->rt.nr_cpus_allowed = 1; + /* It's safe because the task is inactive. */ + do_set_cpus_allowed(p, cpumask_of(cpu)); p->flags |= PF_THREAD_BOUND; } EXPORT_SYMBOL(kthread_bind); diff --git a/kernel/sched.c b/kernel/sched.c index a80ee911900..cbb3a0eee58 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5860,7 +5860,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); - cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu)); + do_set_cpus_allowed(idle, cpumask_of(cpu)); /* * We're having a chicken and egg problem, even though we are * holding rq->lock, the cpu isn't yet set to this cpu so the @@ -5948,6 +5948,16 @@ static inline void sched_init_granularity(void) } #ifdef CONFIG_SMP +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ + if (p->sched_class && p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, new_mask); + else { + cpumask_copy(&p->cpus_allowed, new_mask); + p->rt.nr_cpus_allowed = cpumask_weight(new_mask); + } +} + /* * This is how migration works: * @@ -5993,12 +6003,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) goto out; } - if (p->sched_class->set_cpus_allowed) - p->sched_class->set_cpus_allowed(p, new_mask); - else { - cpumask_copy(&p->cpus_allowed, new_mask); - p->rt.nr_cpus_allowed = cpumask_weight(new_mask); - } + do_set_cpus_allowed(p, new_mask); /* Can the task run on the task's current CPU? If so, we're done */ if (cpumask_test_cpu(task_cpu(p), new_mask)) -- cgit v1.2.3-70-g09d2 From 6345d24daf0c1fffe6642081d783cdf653ebaa5c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 29 May 2011 11:32:28 -0700 Subject: mm: Fix boot crash in mm_alloc() Thomas Gleixner reports that we now have a boot crash triggered by CONFIG_CPUMASK_OFFSTACK=y: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [] find_next_bit+0x55/0xb0 Call Trace: [] cpumask_any_but+0x2a/0x70 [] flush_tlb_mm+0x2b/0x80 [] pud_populate+0x35/0x50 [] pgd_alloc+0x9a/0xf0 [] mm_init+0xec/0x120 [] mm_alloc+0x53/0xd0 which was introduced by commit de03c72cfce5 ("mm: convert mm->cpu_vm_cpumask into cpumask_var_t"), and is due to wrong ordering of mm_init() vs mm_init_cpumask Thomas wrote a patch to just fix the ordering of initialization, but I hate the new double allocation in the fork path, so I ended up instead doing some more radical surgery to clean it all up. Reported-by: Thomas Gleixner Reported-by: Ingo Molnar Cc: KOSAKI Motohiro Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 14 ++++++++++++-- include/linux/sched.h | 1 - init/main.c | 2 +- kernel/fork.c | 42 ++++++++++-------------------------------- 4 files changed, 23 insertions(+), 36 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 2a78aae78c6..027935c86c6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -264,6 +264,8 @@ struct mm_struct { struct linux_binfmt *binfmt; + cpumask_var_t cpu_vm_mask_var; + /* Architecture-specific MM context */ mm_context_t context; @@ -311,10 +313,18 @@ struct mm_struct { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif - - cpumask_var_t cpu_vm_mask_var; +#ifdef CONFIG_CPUMASK_OFFSTACK + struct cpumask cpumask_allocation; +#endif }; +static inline void mm_init_cpumask(struct mm_struct *mm) +{ +#ifdef CONFIG_CPUMASK_OFFSTACK + mm->cpu_vm_mask_var = &mm->cpumask_allocation; +#endif +} + /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { diff --git a/include/linux/sched.h b/include/linux/sched.h index bcddd013810..2a8621c4be1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2194,7 +2194,6 @@ static inline void mmdrop(struct mm_struct * mm) if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } -extern int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm); /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); diff --git a/init/main.c b/init/main.c index d2f1e086bf3..cafba67c13b 100644 --- a/init/main.c +++ b/init/main.c @@ -487,6 +487,7 @@ asmlinkage void __init start_kernel(void) printk(KERN_NOTICE "%s", linux_banner); setup_arch(&command_line); mm_init_owner(&init_mm, &init_task); + mm_init_cpumask(&init_mm); setup_command_line(command_line); setup_nr_cpu_ids(); setup_per_cpu_areas(); @@ -510,7 +511,6 @@ asmlinkage void __init start_kernel(void) sort_main_extable(); trap_init(); mm_init(); - BUG_ON(mm_init_cpumask(&init_mm, 0)); /* * Set up the scheduler prior starting any interrupts (such as the diff --git a/kernel/fork.c b/kernel/fork.c index ca406d91671..0276c30401a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -484,20 +484,6 @@ static void mm_init_aio(struct mm_struct *mm) #endif } -int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm) -{ -#ifdef CONFIG_CPUMASK_OFFSTACK - if (!alloc_cpumask_var(&mm->cpu_vm_mask_var, GFP_KERNEL)) - return -ENOMEM; - - if (oldmm) - cpumask_copy(mm_cpumask(mm), mm_cpumask(oldmm)); - else - memset(mm_cpumask(mm), 0, cpumask_size()); -#endif - return 0; -} - static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); @@ -538,17 +524,8 @@ struct mm_struct * mm_alloc(void) return NULL; memset(mm, 0, sizeof(*mm)); - mm = mm_init(mm, current); - if (!mm) - return NULL; - - if (mm_init_cpumask(mm, NULL)) { - mm_free_pgd(mm); - free_mm(mm); - return NULL; - } - - return mm; + mm_init_cpumask(mm); + return mm_init(mm, current); } /* @@ -559,7 +536,6 @@ struct mm_struct * mm_alloc(void) void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); - free_cpumask_var(mm->cpu_vm_mask_var); mm_free_pgd(mm); destroy_context(mm); mmu_notifier_mm_destroy(mm); @@ -753,6 +729,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); + mm_init_cpumask(mm); /* Initializing for Swap token stuff */ mm->token_priority = 0; @@ -765,9 +742,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk) if (!mm_init(mm, tsk)) goto fail_nomem; - if (mm_init_cpumask(mm, oldmm)) - goto fail_nocpumask; - if (init_new_context(tsk, mm)) goto fail_nocontext; @@ -794,9 +768,6 @@ fail_nomem: return NULL; fail_nocontext: - free_cpumask_var(mm->cpu_vm_mask_var); - -fail_nocpumask: /* * If init_new_context() failed, we cannot use mmput() to free the mm * because it calls destroy_context() @@ -1591,6 +1562,13 @@ void __init proc_caches_init(void) fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + /* + * FIXME! The "sizeof(struct mm_struct)" currently includes the + * whole struct cpumask for the OFFSTACK case. We could change + * this to *only* allocate as much of it as required by the + * maximum number of CPU's we can ever have. The cpumask_allocation + * is at the end of the structure, exactly for that reason. + */ mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); -- cgit v1.2.3-70-g09d2 From f339b9dc1f03591761d5d930800db24bc0eda1e1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 31 May 2011 10:49:20 +0200 Subject: sched: Fix schedstat.nr_wakeups_migrate While looking over the code I found that with the ttwu rework the nr_wakeups_migrate test broke since we now switch cpus prior to calling ttwu_stat(), hence the test is always true. Cure this by passing the migration state in wake_flags. Also move the whole test under CONFIG_SMP, its hard to migrate tasks on UP :-) Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-pwwxl7gdqs5676f1d4cx6pj7@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + kernel/sched.c | 11 +++++++---- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8da84b7bc1b..483c1ed5bc4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1063,6 +1063,7 @@ struct sched_domain; */ #define WF_SYNC 0x01 /* waker goes to sleep after wakup */ #define WF_FORK 0x02 /* child wakeup after fork */ +#define WF_MIGRATED 0x04 /* internal use, task got migrated */ #define ENQUEUE_WAKEUP 1 #define ENQUEUE_HEAD 2 diff --git a/kernel/sched.c b/kernel/sched.c index 49cc70b152c..2fe98ed474d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2447,6 +2447,10 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) } rcu_read_unlock(); } + + if (wake_flags & WF_MIGRATED) + schedstat_inc(p, se.statistics.nr_wakeups_migrate); + #endif /* CONFIG_SMP */ schedstat_inc(rq, ttwu_count); @@ -2455,9 +2459,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) if (wake_flags & WF_SYNC) schedstat_inc(p, se.statistics.nr_wakeups_sync); - if (cpu != task_cpu(p)) - schedstat_inc(p, se.statistics.nr_wakeups_migrate); - #endif /* CONFIG_SCHEDSTATS */ } @@ -2675,8 +2676,10 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) p->sched_class->task_waking(p); cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); - if (task_cpu(p) != cpu) + if (task_cpu(p) != cpu) { + wake_flags |= WF_MIGRATED; set_task_cpu(p, cpu); + } #endif /* CONFIG_SMP */ ttwu_queue(p, cpu); -- cgit v1.2.3-70-g09d2