From b53202e6308939d33ba0c78712e850f891b4e76f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 3 Dec 2015 10:24:08 -0500 Subject: cgroup: kill cgrp_ss_priv[CGROUP_CANFORK_COUNT] and friends Now that nobody use the "priv" arg passed to can_fork/cancel_fork/fork we can kill CGROUP_CANFORK_COUNT/SUBSYS_TAG/etc and cgrp_ss_priv[] in copy_process(). Signed-off-by: Oleg Nesterov Signed-off-by: Tejun Heo --- kernel/fork.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index fce002ee3ddf..ba7d1c037490 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1249,7 +1249,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, { int retval; struct task_struct *p; - void *cgrp_ss_priv[CGROUP_CANFORK_COUNT] = {}; if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); @@ -1526,7 +1525,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, * between here and cgroup_post_fork() if an organisation operation is in * progress. */ - retval = cgroup_can_fork(p, cgrp_ss_priv); + retval = cgroup_can_fork(p); if (retval) goto bad_fork_free_pid; @@ -1608,7 +1607,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, write_unlock_irq(&tasklist_lock); proc_fork_connector(p); - cgroup_post_fork(p, cgrp_ss_priv); + cgroup_post_fork(p); threadgroup_change_end(current); perf_event_fork(p); @@ -1618,7 +1617,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, return p; bad_fork_cancel_cgroup: - cgroup_cancel_fork(p, cgrp_ss_priv); + cgroup_cancel_fork(p); bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); -- cgit v1.2.3 From 7098c1eac75dc03fdbb7249171a6e68ce6044a5a Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 19 Nov 2015 16:47:30 +0100 Subject: sched/cputime: Clarify vtime symbols and document them VTIME_SLEEPING state happens either when: 1) The task is sleeping and no tickless delta is to be added on the task cputime stats. 2) The CPU isn't running vtime at all, so the same properties of 1) applies. Lets rename the vtime symbol to reflect both states. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Chris Metcalf Cc: Christoph Lameter Cc: Hiroshi Shimamoto Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E . McKenney Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1447948054-28668-4-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 ++++- kernel/fork.c | 2 +- kernel/sched/cputime.c | 6 +++--- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index f425aac63317..3533168fe7d1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1522,8 +1522,11 @@ struct task_struct { seqlock_t vtime_seqlock; unsigned long long vtime_snap; enum { - VTIME_SLEEPING = 0, + /* Task is sleeping or running in a CPU with VTIME inactive */ + VTIME_INACTIVE = 0, + /* Task runs in userspace in a CPU with VTIME active */ VTIME_USER, + /* Task runs in kernelspace in a CPU with VTIME active */ VTIME_SYS, } vtime_snap_whence; #endif diff --git a/kernel/fork.c b/kernel/fork.c index f97f2c449f5c..c0a13706b1a7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1350,7 +1350,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqlock_init(&p->vtime_seqlock); p->vtime_snap = 0; - p->vtime_snap_whence = VTIME_SLEEPING; + p->vtime_snap_whence = VTIME_INACTIVE; #endif #if defined(SPLIT_RSS_COUNTING) diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 1128d4ba6c55..4a18a6ed7723 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -680,7 +680,7 @@ static cputime_t get_vtime_delta(struct task_struct *tsk) { unsigned long long delta = vtime_delta(tsk); - WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING); + WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); tsk->vtime_snap += delta; /* CHECKME: always safe to convert nsecs to cputime? */ @@ -764,7 +764,7 @@ void vtime_account_idle(struct task_struct *tsk) void arch_vtime_task_switch(struct task_struct *prev) { write_seqlock(&prev->vtime_seqlock); - prev->vtime_snap_whence = VTIME_SLEEPING; + prev->vtime_snap_whence = VTIME_INACTIVE; write_sequnlock(&prev->vtime_seqlock); write_seqlock(¤t->vtime_seqlock); @@ -829,7 +829,7 @@ fetch_task_cputime(struct task_struct *t, *s_dst = *s_src; /* Task is sleeping, nothing to add */ - if (t->vtime_snap_whence == VTIME_SLEEPING || + if (t->vtime_snap_whence == VTIME_INACTIVE || is_idle_task(t)) continue; -- cgit v1.2.3 From b7ce2277f087fd052e7e1bbf432f7fecbee82bb6 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 19 Nov 2015 16:47:34 +0100 Subject: sched/cputime: Convert vtime_seqlock to seqcount The cputime can only be updated by the current task itself, even in vtime case. So we can safely use seqcount instead of seqlock as there is no writer concurrency involved. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Chris Metcalf Cc: Christoph Lameter Cc: Hiroshi Shimamoto Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E . McKenney Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1447948054-28668-8-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 2 +- include/linux/sched.h | 2 +- kernel/fork.c | 2 +- kernel/sched/cputime.c | 46 ++++++++++++++++++++++++---------------------- 4 files changed, 27 insertions(+), 25 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 1c1ff7e4faa4..f2cb8d45513d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -150,7 +150,7 @@ extern struct task_group root_task_group; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN # define INIT_VTIME(tsk) \ - .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \ + .vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount), \ .vtime_snap = 0, \ .vtime_snap_whence = VTIME_SYS, #else diff --git a/include/linux/sched.h b/include/linux/sched.h index 3533168fe7d1..3b0de68bce41 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1519,7 +1519,7 @@ struct task_struct { cputime_t gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqlock_t vtime_seqlock; + seqcount_t vtime_seqcount; unsigned long long vtime_snap; enum { /* Task is sleeping or running in a CPU with VTIME inactive */ diff --git a/kernel/fork.c b/kernel/fork.c index c0a13706b1a7..eea32b55432a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1348,7 +1348,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqlock_init(&p->vtime_seqlock); + seqcount_init(&p->vtime_seqcount); p->vtime_snap = 0; p->vtime_snap_whence = VTIME_INACTIVE; #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 9989c3f61723..d5ff5c6bf829 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -696,37 +696,37 @@ static void __vtime_account_system(struct task_struct *tsk) void vtime_account_system(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } void vtime_gen_account_irq_exit(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); if (context_tracking_in_user()) tsk->vtime_snap_whence = VTIME_USER; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } void vtime_account_user(struct task_struct *tsk) { cputime_t delta_cpu; - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); delta_cpu = get_vtime_delta(tsk); tsk->vtime_snap_whence = VTIME_SYS; account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } void vtime_user_enter(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); tsk->vtime_snap_whence = VTIME_USER; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } void vtime_guest_enter(struct task_struct *tsk) @@ -738,19 +738,19 @@ void vtime_guest_enter(struct task_struct *tsk) * synchronization against the reader (task_gtime()) * that can thus safely catch up with a tickless delta. */ - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); current->flags |= PF_VCPU; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } EXPORT_SYMBOL_GPL(vtime_guest_enter); void vtime_guest_exit(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); current->flags &= ~PF_VCPU; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } EXPORT_SYMBOL_GPL(vtime_guest_exit); @@ -763,24 +763,26 @@ void vtime_account_idle(struct task_struct *tsk) void arch_vtime_task_switch(struct task_struct *prev) { - write_seqlock(&prev->vtime_seqlock); + write_seqcount_begin(&prev->vtime_seqcount); prev->vtime_snap_whence = VTIME_INACTIVE; - write_sequnlock(&prev->vtime_seqlock); + write_seqcount_end(&prev->vtime_seqcount); - write_seqlock(¤t->vtime_seqlock); + write_seqcount_begin(¤t->vtime_seqcount); current->vtime_snap_whence = VTIME_SYS; current->vtime_snap = sched_clock_cpu(smp_processor_id()); - write_sequnlock(¤t->vtime_seqlock); + write_seqcount_end(¤t->vtime_seqcount); } void vtime_init_idle(struct task_struct *t, int cpu) { unsigned long flags; - write_seqlock_irqsave(&t->vtime_seqlock, flags); + local_irq_save(flags); + write_seqcount_begin(&t->vtime_seqcount); t->vtime_snap_whence = VTIME_SYS; t->vtime_snap = sched_clock_cpu(cpu); - write_sequnlock_irqrestore(&t->vtime_seqlock, flags); + write_seqcount_end(&t->vtime_seqcount); + local_irq_restore(flags); } cputime_t task_gtime(struct task_struct *t) @@ -792,13 +794,13 @@ cputime_t task_gtime(struct task_struct *t) return t->gtime; do { - seq = read_seqbegin(&t->vtime_seqlock); + seq = read_seqcount_begin(&t->vtime_seqcount); gtime = t->gtime; if (t->vtime_snap_whence == VTIME_SYS && t->flags & PF_VCPU) gtime += vtime_delta(t); - } while (read_seqretry(&t->vtime_seqlock, seq)); + } while (read_seqcount_retry(&t->vtime_seqcount, seq)); return gtime; } @@ -821,7 +823,7 @@ fetch_task_cputime(struct task_struct *t, *udelta = 0; *sdelta = 0; - seq = read_seqbegin(&t->vtime_seqlock); + seq = read_seqcount_begin(&t->vtime_seqcount); if (u_dst) *u_dst = *u_src; @@ -845,7 +847,7 @@ fetch_task_cputime(struct task_struct *t, if (t->vtime_snap_whence == VTIME_SYS) *sdelta = delta; } - } while (read_seqretry(&t->vtime_seqlock, seq)); + } while (read_seqcount_retry(&t->vtime_seqcount, seq)); } -- cgit v1.2.3 From 093e5840ae76f1082633503964d035f40ed0216d Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 21 Dec 2015 18:17:10 +0100 Subject: sched/core: Reset task's lockless wake-queues on fork() In the following commit: 7675104990ed ("sched: Implement lockless wake-queues") we gained lockless wake-queues. The -RT kernel managed to lockup itself with those. There could be multiple attempts for task X to enqueue it for a wakeup _even_ if task X is already running. The reason is that task X could be runnable but not yet on CPU. The the task performing the wakeup did not leave the CPU it could performe multiple wakeups. With the proper timming task X could be running and enqueued for a wakeup. If this happens while X is performing a fork() then its its child will have a !NULL `wake_q` member copied. This is not a problem as long as the child task does not participate in lockless wakeups :) Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Cc: Davidlohr Bueso Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Fixes: 7675104990ed ("sched: Implement lockless wake-queues") Link: http://lkml.kernel.org/r/20151221171710.GA5499@linutronix.de Signed-off-by: Ingo Molnar --- kernel/fork.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index fce002ee3ddf..1155eac61687 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -380,6 +380,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; + tsk->wake_q.next = NULL; account_kernel_stack(ti, 1); -- cgit v1.2.3