From f86977620ee4635f26befcf436700493a38ce002 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 1 Aug 2014 14:33:01 +0200 Subject: perf: Set owner pointer for kernel events Adding fake EVENT_OWNER_KERNEL owner pointer value for kernel perf events, so we could distinguish it from user events, which needs special care in following patch. Signed-off-by: Jiri Olsa Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Mark Rutland Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Mark Rutland Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1406896382-18404-3-git-send-email-jolsa@kernel.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 1cf24b3e42ec..bbb3ca22f07c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -119,6 +119,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info) return data.ret; } +#define EVENT_OWNER_KERNEL ((void *) -1) + +static bool is_kernel_event(struct perf_event *event) +{ + return event->owner == EVENT_OWNER_KERNEL; +} + #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ PERF_FLAG_FD_OUTPUT |\ PERF_FLAG_PID_CGROUP |\ @@ -3312,16 +3319,12 @@ static void free_event(struct perf_event *event) } /* - * Called when the last reference to the file is gone. + * Remove user event from the owner task. */ -static void put_event(struct perf_event *event) +static void perf_remove_from_owner(struct perf_event *event) { - struct perf_event_context *ctx = event->ctx; struct task_struct *owner; - if (!atomic_long_dec_and_test(&event->refcount)) - return; - rcu_read_lock(); owner = ACCESS_ONCE(event->owner); /* @@ -3354,6 +3357,20 @@ static void put_event(struct perf_event *event) mutex_unlock(&owner->perf_event_mutex); put_task_struct(owner); } +} + +/* + * Called when the last reference to the file is gone. + */ +static void put_event(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + + if (!atomic_long_dec_and_test(&event->refcount)) + return; + + if (!is_kernel_event(event)) + perf_remove_from_owner(event); WARN_ON_ONCE(ctx->parent_ctx); /* @@ -7366,6 +7383,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, goto err; } + /* Mark owner so we could distinguish it from user events. */ + event->owner = EVENT_OWNER_KERNEL; + account_event(event); ctx = find_get_context(event->pmu, task, cpu); -- cgit v1.2.3 From fadfe7be6e50de7f03913833b33c56cd8fb66bac Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 1 Aug 2014 14:33:02 +0200 Subject: perf: Add queued work to remove orphaned child events In cases when the owner task exits before the workload and the workload made some forks, all the events stay in until the last workload process exits. Thats' because each child event holds parent reference. We want to release all children events once the parent is gone, because at that time there's no process to read them anyway, so they're just eating resources. This removal races with process exit, which removes all events and fork, which clone events. To be clear of those two, adding work queue to remove orphaned child for context in case such event is detected. Using delayed work queue (with delay == 1), because we queue this work under perf scheduler callbacks. Normal work queue tries to wake up the queue process, which deadlocks on rq->lock in this place. Also preventing clones from abandoned parent event. Signed-off-by: Jiri Olsa Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Mark Rutland Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: Frederic Weisbecker Cc: Mark Rutland Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1406896382-18404-4-git-send-email-jolsa@kernel.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 4 +++ kernel/events/core.c | 87 +++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 90 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 707617a8c0f6..ef5b62bdb103 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -52,6 +52,7 @@ struct perf_guest_info_callbacks { #include #include #include +#include #include struct perf_callchain_entry { @@ -507,6 +508,9 @@ struct perf_event_context { int nr_cgroups; /* cgroup evts */ int nr_branch_stack; /* branch_stack evt */ struct rcu_head rcu_head; + + struct delayed_work orphans_remove; + bool orphans_remove_sched; }; /* diff --git a/kernel/events/core.c b/kernel/events/core.c index bbb3ca22f07c..a25460559b4f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -46,6 +46,8 @@ #include +static struct workqueue_struct *perf_wq; + struct remote_function_call { struct task_struct *p; int (*func)(void *info); @@ -1381,6 +1383,45 @@ out: perf_event__header_size(tmp); } +/* + * User event without the task. + */ +static bool is_orphaned_event(struct perf_event *event) +{ + return event && !is_kernel_event(event) && !event->owner; +} + +/* + * Event has a parent but parent's task finished and it's + * alive only because of children holding refference. + */ +static bool is_orphaned_child(struct perf_event *event) +{ + return is_orphaned_event(event->parent); +} + +static void orphans_remove_work(struct work_struct *work); + +static void schedule_orphans_remove(struct perf_event_context *ctx) +{ + if (!ctx->task || ctx->orphans_remove_sched || !perf_wq) + return; + + if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) { + get_ctx(ctx); + ctx->orphans_remove_sched = true; + } +} + +static int __init perf_workqueue_init(void) +{ + perf_wq = create_singlethread_workqueue("perf"); + WARN(!perf_wq, "failed to create perf workqueue\n"); + return perf_wq ? 0 : -1; +} + +core_initcall(perf_workqueue_init); + static inline int event_filter_match(struct perf_event *event) { @@ -1430,6 +1471,9 @@ event_sched_out(struct perf_event *event, if (event->attr.exclusive || !cpuctx->active_oncpu) cpuctx->exclusive = 0; + if (is_orphaned_child(event)) + schedule_orphans_remove(ctx); + perf_pmu_enable(event->pmu); } @@ -1732,6 +1776,9 @@ event_sched_in(struct perf_event *event, if (event->attr.exclusive) cpuctx->exclusive = 1; + if (is_orphaned_child(event)) + schedule_orphans_remove(ctx); + out: perf_pmu_enable(event->pmu); @@ -3074,6 +3121,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx) INIT_LIST_HEAD(&ctx->flexible_groups); INIT_LIST_HEAD(&ctx->event_list); atomic_set(&ctx->refcount, 1); + INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work); } static struct perf_event_context * @@ -3405,6 +3453,42 @@ static int perf_release(struct inode *inode, struct file *file) return 0; } +/* + * Remove all orphanes events from the context. + */ +static void orphans_remove_work(struct work_struct *work) +{ + struct perf_event_context *ctx; + struct perf_event *event, *tmp; + + ctx = container_of(work, struct perf_event_context, + orphans_remove.work); + + mutex_lock(&ctx->mutex); + list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) { + struct perf_event *parent_event = event->parent; + + if (!is_orphaned_child(event)) + continue; + + perf_remove_from_context(event, true); + + mutex_lock(&parent_event->child_mutex); + list_del_init(&event->child_list); + mutex_unlock(&parent_event->child_mutex); + + free_event(event); + put_event(parent_event); + } + + raw_spin_lock_irq(&ctx->lock); + ctx->orphans_remove_sched = false; + raw_spin_unlock_irq(&ctx->lock); + mutex_unlock(&ctx->mutex); + + put_ctx(ctx); +} + u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) { struct perf_event *child; @@ -7709,7 +7793,8 @@ inherit_event(struct perf_event *parent_event, if (IS_ERR(child_event)) return child_event; - if (!atomic_long_inc_not_zero(&parent_event->refcount)) { + if (is_orphaned_event(parent_event) || + !atomic_long_inc_not_zero(&parent_event->refcount)) { free_event(child_event); return NULL; } -- cgit v1.2.3 From e708d7ad80737496870fd0b6794704d063fb0cdc Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 4 Aug 2014 15:31:08 +0200 Subject: perf: Do poll_wait() before checking condition in perf_poll() One should first enqueue to the waitqueue and then check for the condition. If the condition gets true after mutex_unlock() but before poll_wait() then we lose it and would have wait for another wakeup. This has been like this since v2.6.31-rc1 commit c7138f37f9 ("perf_counter: fix perf_poll()"). Before that it was slightly worse. I guess we get enough wakeups so if we miss here one it doesn't really matter. It is still a bad example. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1407159068-1478-1-git-send-email-bigeasy@linutronix.de Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Signed-off-by: Ingo Molnar --- kernel/events/core.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index a25460559b4f..2d7363adf678 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3629,6 +3629,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) struct ring_buffer *rb; unsigned int events = POLL_HUP; + poll_wait(file, &event->waitq, wait); /* * Pin the event->rb by taking event->mmap_mutex; otherwise * perf_event_set_output() can swizzle our rb and make us miss wakeups. @@ -3638,9 +3639,6 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) if (rb) events = atomic_xchg(&rb->poll, 0); mutex_unlock(&event->mmap_mutex); - - poll_wait(file, &event->waitq, wait); - return events; } -- cgit v1.2.3 From 61b67684c4a4d04b30d9ed67aa2eadfa0089c590 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 13 Aug 2014 19:39:56 +0200 Subject: perf: Fix perf_poll to return proper POLLHUP value Currently perf_poll returns POLL_HUP in case of error, which is wrong, because poll syscall expects POLLHUP. The POLL_HUP is meant to be used for SIGIO state. Signed-off-by: Jiri Olsa Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140811120102.GY9918@twins.programming.kicks-ass.net Cc: Adrian Hunter Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jean Pihet Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-0ywfthh4lh65swe15f6w2x2q@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 2d7363adf678..4575dd6e59ea 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3627,7 +3627,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) { struct perf_event *event = file->private_data; struct ring_buffer *rb; - unsigned int events = POLL_HUP; + unsigned int events = POLLHUP; poll_wait(file, &event->waitq, wait); /* -- cgit v1.2.3 From 179033b3e064d2cd3f5f9945e76b0a0f0fbf4883 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Aug 2014 11:48:26 -0400 Subject: perf: Add PERF_EVENT_STATE_EXIT state for events with exited task Adding new perf event state to indicate that the monitored task has exited. In this case the event stays alive until the owner task exits or close the event fd while providing the last data through the read syscall and ring buffer. Instead it needs to propagate the error info (monitored task has died) via poll and read syscalls by returning POLLHUP and 0 respectively. Signed-off-by: Jiri Olsa Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140811120102.GY9918@twins.programming.kicks-ass.net Cc: Adrian Hunter Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jean Pihet Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-t5y3w8jjx6tfo5w8y6oajsjq@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 1 + kernel/events/core.c | 10 +++++++++- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f0a1036b1911..893a0d07986f 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -269,6 +269,7 @@ struct pmu { * enum perf_event_active_state - the states of a event */ enum perf_event_active_state { + PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, diff --git a/kernel/events/core.c b/kernel/events/core.c index 4575dd6e59ea..d8cb4d21a346 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3600,7 +3600,8 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count) * error state (i.e. because it was pinned but it couldn't be * scheduled on to the CPU at some point). */ - if (event->state == PERF_EVENT_STATE_ERROR) + if ((event->state == PERF_EVENT_STATE_ERROR) || + (event->state == PERF_EVENT_STATE_EXIT)) return 0; if (count < event->read_size) @@ -3630,6 +3631,10 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) unsigned int events = POLLHUP; poll_wait(file, &event->waitq, wait); + + if (event->state == PERF_EVENT_STATE_EXIT) + return events; + /* * Pin the event->rb by taking event->mmap_mutex; otherwise * perf_event_set_output() can swizzle our rb and make us miss wakeups. @@ -7588,6 +7593,9 @@ __perf_event_exit_task(struct perf_event *child_event, if (child_event->parent) { sync_child_event(child_event, child); free_event(child_event); + } else { + child_event->state = PERF_EVENT_STATE_EXIT; + perf_event_wakeup(child_event); } } -- cgit v1.2.3 From e0455e194a5e0cf49bc7596a20d4f7e47995b9c6 Mon Sep 17 00:00:00 2001 From: Andreea-Cristina Bernat Date: Fri, 22 Aug 2014 17:15:36 +0300 Subject: perf/callchain: Replace rcu_assign_pointer() with RCU_INIT_POINTER() The use of "rcu_assign_pointer()" is NULLing out the pointer. According to RCU_INIT_POINTER()'s block comment: "1. This use of RCU_INIT_POINTER() is NULLing out the pointer" it is better to use it instead of rcu_assign_pointer() because it has a smaller overhead. The following Coccinelle semantic patch was used: @@ @@ - rcu_assign_pointer + RCU_INIT_POINTER (..., NULL) Signed-off-by: Andreea-Cristina Bernat Signed-off-by: Peter Zijlstra (Intel) Cc: paulmck@linux.vnet.ibm.com Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/20140822141536.GA32051@ada Signed-off-by: Ingo Molnar --- kernel/events/callchain.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 97b67df8fbfe..f2a88de87a49 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -52,7 +52,7 @@ static void release_callchain_buffers(void) struct callchain_cpus_entries *entries; entries = callchain_cpus_entries; - rcu_assign_pointer(callchain_cpus_entries, NULL); + RCU_INIT_POINTER(callchain_cpus_entries, NULL); call_rcu(&entries->rcu_head, release_callchain_buffers_rcu); } -- cgit v1.2.3 From 70691d4a0bf7c871559d4ef1b0056edefbca123b Mon Sep 17 00:00:00 2001 From: Andreea-Cristina Bernat Date: Fri, 22 Aug 2014 16:26:05 +0300 Subject: perf/core: Replace rcu_assign_pointer() with RCU_INIT_POINTER() The use of "rcu_assign_pointer()" is NULLing out the pointer. According to RCU_INIT_POINTER()'s block comment: "1. This use of RCU_INIT_POINTER() is NULLing out the pointer" it is better to use it instead of rcu_assign_pointer() because it has a smaller overhead. The following Coccinelle semantic patch was used: @@ @@ - rcu_assign_pointer + RCU_INIT_POINTER (..., NULL) Signed-off-by: Andreea-Cristina Bernat Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/20140822132605.GA20130@ada Signed-off-by: Ingo Molnar --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 01bd42ed516c..f917dec6f897 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5908,7 +5908,7 @@ static void swevent_hlist_release(struct swevent_htable *swhash) if (!hlist) return; - rcu_assign_pointer(swhash->swevent_hlist, NULL); + RCU_INIT_POINTER(swhash->swevent_hlist, NULL); kfree_rcu(hlist, rcu_head); } -- cgit v1.2.3 From c88f2096136416b261bd3647cc260935f6e95805 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 8 Sep 2014 16:31:07 +0200 Subject: perf: Do not check PERF_EVENT_STATE_EXIT on syscall read path Revert PERF_EVENT_STATE_EXIT check on read syscall path. It breaks standard way to read counter, which is to open the counter, wait for the monitored process to die and read the counter. Reported-by: Stephane Eranian Signed-off-by: Jiri Olsa Acked-by: Stephane Eranian Acked-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: Paul Mackerras Cc: Stephane Eranian Cc: David Ahern Link: http://lkml.kernel.org/r/20140908143107.GG17728@krava.brq.redhat.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index f917dec6f897..733c61636f0d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3601,8 +3601,7 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count) * error state (i.e. because it was pinned but it couldn't be * scheduled on to the CPU at some point). */ - if ((event->state == PERF_EVENT_STATE_ERROR) || - (event->state == PERF_EVENT_STATE_EXIT)) + if (event->state == PERF_EVENT_STATE_ERROR) return 0; if (count < event->read_size) -- cgit v1.2.3 From dc633982ff3f4fd74cdc11b5a6ae53d39a0b2451 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 12 Sep 2014 13:18:26 +0200 Subject: perf: Do not POLLHUP event if it has children Currently we return POLLHUP in event polling if the monitored process is done, but we didn't consider possible children, that might be still running and producing data. Before returning POLLHUP making sure that: 1) the monitored task has exited and that 2) we don't have any children to monitor Also adding parent wakeup when the child event is gone. Suggested-by: Peter Zijlstra Signed-off-by: Jiri Olsa Signed-off-by: Peter Zijlstra (Intel) Link: http://lkml.kernel.org/r/1410520708-19275-1-git-send-email-jolsa@kernel.org Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Stephane Eranian Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Stephane Eranian Cc: Linus Torvalds Signed-off-by: Ingo Molnar --- kernel/events/core.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 733c61636f0d..15e58d4ea035 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3587,6 +3587,19 @@ static int perf_event_read_one(struct perf_event *event, return n * sizeof(u64); } +static bool is_event_hup(struct perf_event *event) +{ + bool no_children; + + if (event->state != PERF_EVENT_STATE_EXIT) + return false; + + mutex_lock(&event->child_mutex); + no_children = list_empty(&event->child_list); + mutex_unlock(&event->child_mutex); + return no_children; +} + /* * Read the performance event - simple non blocking version for now */ @@ -3632,7 +3645,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) poll_wait(file, &event->waitq, wait); - if (event->state == PERF_EVENT_STATE_EXIT) + if (is_event_hup(event)) return events; /* @@ -7579,6 +7592,12 @@ static void sync_child_event(struct perf_event *child_event, list_del_init(&child_event->child_list); mutex_unlock(&parent_event->child_mutex); + /* + * Make sure user/parent get notified, that we just + * lost one event. + */ + perf_event_wakeup(parent_event); + /* * Release the parent event, if this was the last * reference to it. -- cgit v1.2.3 From 1929def9e609d1a8cdb1626d85eda3da66921a7d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 12 Sep 2014 13:18:27 +0200 Subject: perf: Fix child event initial state setup Currently we initialize the child event based on the original parent state. This is wrong, because the original parent event (and its state) is not related to current fork and also could be already gone. We need to initialize the child state based on the immediate parent event state. Signed-off-by: Jiri Olsa Signed-off-by: Peter Zijlstra (Intel) Cc: Frederic Weisbecker Cc: Stephane Eranian Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1410520708-19275-2-git-send-email-jolsa@kernel.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 15e58d4ea035..132524c8b340 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7818,6 +7818,7 @@ inherit_event(struct perf_event *parent_event, struct perf_event *group_leader, struct perf_event_context *child_ctx) { + enum perf_event_active_state parent_state = parent_event->state; struct perf_event *child_event; unsigned long flags; @@ -7851,7 +7852,7 @@ inherit_event(struct perf_event *parent_event, * not its attr.disabled bit. We hold the parent's mutex, * so we won't race with perf_event_{en, dis}able_family. */ - if (parent_event->state >= PERF_EVENT_STATE_INACTIVE) + if (parent_state >= PERF_EVENT_STATE_INACTIVE) child_event->state = PERF_EVENT_STATE_INACTIVE; else child_event->state = PERF_EVENT_STATE_OFF; -- cgit v1.2.3 From 802c8a61d4c9c794db863dcabb0006ab001a651b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 12 Sep 2014 13:18:28 +0200 Subject: Revert "perf: Do not allow optimized switch for non-cloned events" This reverts commit 1f9a7268c67f0290837aada443d28fd953ddca90. With the fix of the initial state for the cloned event we now correctly handle the error described in: 1f9a7268c67f perf: Do not allow optimized switch for non-cloned events so we can revert it. I made an automated test for this, but its not suitable for automated perf tests framework. It needs to be customized for each machine (the more cpu the higher numbers for GROUPS/WORKERS/BYTES) and it could take longer time to hit the issue. Signed-off-by: Jiri Olsa Signed-off-by: Peter Zijlstra (Intel) Cc: Frederic Weisbecker Cc: Stephane Eranian Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20140910143535.GD2409@krava.brq.redhat.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 132524c8b340..b164cb07b30d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2375,7 +2375,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, next_parent = rcu_dereference(next_ctx->parent_ctx); /* If neither context have a parent context; they cannot be clones. */ - if (!parent || !next_parent) + if (!parent && !next_parent) goto unlock; if (next_parent == ctx || next_ctx == parent || next_parent == parent) { -- cgit v1.2.3