lkml.org 
[lkml]   [2010]   [Nov]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[tip:perf/core] perf: Fix inherit vs. context rotation bug
Commit-ID:  dddd3379a619a4cb8247bfd3c94ca9ae3797aa2e
Gitweb: http://git.kernel.org/tip/dddd3379a619a4cb8247bfd3c94ca9ae3797aa2e
Author: Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 24 Nov 2010 10:05:55 +0100
Committer: Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 26 Nov 2010 15:00:56 +0100

perf: Fix inherit vs. context rotation bug

It was found that sometimes children of tasks with inherited events had
one extra event. Eventually it turned out to be due to the list rotation
no being exclusive with the list iteration in the inheritance code.

Cure this by temporarily disabling the rotation while we inherit the events.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
include/linux/perf_event.h | 1 +
kernel/perf_event.c | 22 ++++++++++++++++++++--
2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 40150f3..142e3d6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -850,6 +850,7 @@ struct perf_event_context {
int nr_active;
int is_active;
int nr_stat;
+ int rotate_disable;
atomic_t refcount;
struct task_struct *task;

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 671f6c8..f365dd8 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1622,8 +1622,12 @@ static void rotate_ctx(struct perf_event_context *ctx)
{
raw_spin_lock(&ctx->lock);

- /* Rotate the first entry last of non-pinned groups */
- list_rotate_left(&ctx->flexible_groups);
+ /*
+ * Rotate the first entry last of non-pinned groups. Rotation might be
+ * disabled by the inheritance code.
+ */
+ if (!ctx->rotate_disable)
+ list_rotate_left(&ctx->flexible_groups);

raw_spin_unlock(&ctx->lock);
}
@@ -6162,6 +6166,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
struct perf_event *event;
struct task_struct *parent = current;
int inherited_all = 1;
+ unsigned long flags;
int ret = 0;

child->perf_event_ctxp[ctxn] = NULL;
@@ -6202,6 +6207,15 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
break;
}

+ /*
+ * We can't hold ctx->lock when iterating the ->flexible_group list due
+ * to allocations, but we need to prevent rotation because
+ * rotate_ctx() will change the list from interrupt context.
+ */
+ raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+ parent_ctx->rotate_disable = 1;
+ raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
ret = inherit_task_group(event, parent, parent_ctx,
child, ctxn, &inherited_all);
@@ -6209,6 +6223,10 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
break;
}

+ raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+ parent_ctx->rotate_disable = 0;
+ raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
child_ctx = child->perf_event_ctxp[ctxn];

if (child_ctx && inherited_all) {

\
 
 \ /
  Last update: 2010-11-26 16:03    [W:0.032 / U:0.120 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site