From dbe08d82ce3967ccdf459f7951d02589cf967300 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 19 Jan 2011 19:22:07 +0100 Subject: perf: Fix find_get_context() vs perf_event_exit_task() race find_get_context() must not install the new perf_event_context if the task has already passed perf_event_exit_task(). If nothing else, this means the memory leak. Initially ctx->refcount == 2, it is supposed that perf_event_exit_task_context() should participate and do the necessary put_ctx(). find_lively_task_by_vpid() checks PF_EXITING but this buys nothing, by the time we call find_get_context() this task can be already dead. To the point, cmpxchg() can succeed when the task has already done the last schedule(). Change find_get_context() to populate task->perf_event_ctxp[] under task->perf_event_mutex, this way we can trust PF_EXITING because perf_event_exit_task() takes the same mutex. Also, change perf_event_exit_task_context() to use rcu_dereference(). Probably this is not strictly needed, but with or without this change find_get_context() can race with setup_new_exec()->perf_event_exit_task(), rcu_dereference() looks better. Signed-off-by: Oleg Nesterov Acked-by: Peter Zijlstra Cc: Alan Stern Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Prasad Cc: Roland McGrath LKML-Reference: <20110119182207.GB12183@redhat.com> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 34 ++++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 84522c79698..4ec55ef5810 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2201,13 +2201,6 @@ find_lively_task_by_vpid(pid_t vpid) if (!task) return ERR_PTR(-ESRCH); - /* - * Can't attach events to a dying task. - */ - err = -ESRCH; - if (task->flags & PF_EXITING) - goto errout; - /* Reuse ptrace permission checks for now. */ err = -EACCES; if (!ptrace_may_access(task, PTRACE_MODE_READ)) @@ -2268,14 +2261,27 @@ retry: get_ctx(ctx); - if (cmpxchg(&task->perf_event_ctxp[ctxn], NULL, ctx)) { - /* - * We raced with some other task; use - * the context they set. - */ + err = 0; + mutex_lock(&task->perf_event_mutex); + /* + * If it has already passed perf_event_exit_task(). + * we must see PF_EXITING, it takes this mutex too. + */ + if (task->flags & PF_EXITING) + err = -ESRCH; + else if (task->perf_event_ctxp[ctxn]) + err = -EAGAIN; + else + rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx); + mutex_unlock(&task->perf_event_mutex); + + if (unlikely(err)) { put_task_struct(task); kfree(ctx); - goto retry; + + if (err == -EAGAIN) + goto retry; + goto errout; } } @@ -6127,7 +6133,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) * scheduled, so we are now safe from rescheduling changing * our context. */ - child_ctx = child->perf_event_ctxp[ctxn]; + child_ctx = rcu_dereference(child->perf_event_ctxp[ctxn]); task_ctx_sched_out(child_ctx, EVENT_ALL); /* -- cgit v1.2.3-70-g09d2 From 8550d7cb6ed6c89add49c3b6ad4c753ab8a3d7f9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 19 Jan 2011 19:22:28 +0100 Subject: perf: Fix perf_event_init_task()/perf_event_free_task() interaction perf_event_init_task() should clear child->perf_event_ctxp[] before anything else. Otherwise, if perf_event_init_context(perf_hw_context) fails, perf_event_free_task() can free perf_event_ctxp[perf_sw_context] copied from parent->perf_event_ctxp[] by dup_task_struct(). Also move the initialization of perf_event_mutex and perf_event_list from perf_event_init_context() to perf_event_init_context(). Signed-off-by: Oleg Nesterov Acked-by: Peter Zijlstra Cc: Alan Stern Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Prasad Cc: Roland McGrath LKML-Reference: <20110119182228.GC12183@redhat.com> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 4ec55ef5810..244ca3acb0e 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -6446,11 +6446,6 @@ int perf_event_init_context(struct task_struct *child, int ctxn) unsigned long flags; int ret = 0; - child->perf_event_ctxp[ctxn] = NULL; - - mutex_init(&child->perf_event_mutex); - INIT_LIST_HEAD(&child->perf_event_list); - if (likely(!parent->perf_event_ctxp[ctxn])) return 0; @@ -6539,6 +6534,10 @@ int perf_event_init_task(struct task_struct *child) { int ctxn, ret; + memset(child->perf_event_ctxp, 0, sizeof(child->perf_event_ctxp)); + mutex_init(&child->perf_event_mutex); + INIT_LIST_HEAD(&child->perf_event_list); + for_each_task_context_nr(ctxn) { ret = perf_event_init_context(child, ctxn); if (ret) -- cgit v1.2.3-70-g09d2 From 547e9fd7d328af261f184bf66effc5033c886498 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 Jan 2011 12:51:39 +0100 Subject: perf: Annotate cpuctx->ctx.mutex to avoid a lockdep splat Lockdep spotted: loop_1b_instruc/1899 is trying to acquire lock: (event_mutex){+.+.+.}, at: [] perf_trace_init+0x3b/0x2f7 but task is already holding lock: (&ctx->mutex){+.+.+.}, at: [] perf_event_init_context+0xc0/0x218 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&ctx->mutex){+.+.+.}: -> #2 (cpu_hotplug.lock){+.+.+.}: -> #1 (module_mutex){+.+...}: -> #0 (event_mutex){+.+.+.}: But because the deadlock would be cpuhotplug (cpu-event) vs fork (task-event) it cannot, in fact, happen. We can annotate this by giving the perf_event_context used for the cpuctx a different lock class from those used by tasks. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 244ca3acb0e..c5fa717cf09 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -5380,6 +5380,8 @@ free_dev: goto out; } +static struct lock_class_key cpuctx_mutex; + int perf_pmu_register(struct pmu *pmu, char *name, int type) { int cpu, ret; @@ -5428,6 +5430,7 @@ skip_type: cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); __perf_event_init_context(&cpuctx->ctx); + lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex); cpuctx->ctx.type = cpu_context; cpuctx->ctx.pmu = pmu; cpuctx->jiffies_interval = 1; -- cgit v1.2.3-70-g09d2 From 806839b22cbda90176d7f8d421889bddd7826e93 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 21 Jan 2011 18:45:47 +0100 Subject: perf: perf_event_exit_task_context: s/rcu_dereference/rcu_dereference_raw/ In theory, almost every user of task->child->perf_event_ctxp[] is wrong. find_get_context() can install the new context at any moment, we need read_barrier_depends(). dbe08d82ce3967ccdf459f7951d02589cf967300 "perf: Fix find_get_context() vs perf_event_exit_task() race" added rcu_dereference() into perf_event_exit_task_context() to make the precedent, but this makes __rcu_dereference_check() unhappy. Use rcu_dereference_raw() to shut up the warning. Reported-by: Ingo Molnar Signed-off-by: Oleg Nesterov Cc: acme@redhat.com Cc: paulus@samba.org Cc: stern@rowland.harvard.edu Cc: a.p.zijlstra@chello.nl Cc: fweisbec@gmail.com Cc: roland@redhat.com Cc: prasad@linux.vnet.ibm.com Cc: Paul E. McKenney LKML-Reference: <20110121174547.GA8796@redhat.com> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index c5fa717cf09..126a302c481 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -6136,7 +6136,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) * scheduled, so we are now safe from rescheduling changing * our context. */ - child_ctx = rcu_dereference(child->perf_event_ctxp[ctxn]); + child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]); task_ctx_sched_out(child_ctx, EVENT_ALL); /* -- cgit v1.2.3-70-g09d2