Commit c79aa0d9 authored by Paul E. McKenney's avatar Paul E. McKenney Committed by Ingo Molnar

events: Protect access via task_subsys_state_check()

The following RCU splat indicates lack of RCU protection:

[  953.267649] ===============================
[  953.267652] [ INFO: suspicious RCU usage. ]
[  953.267657] 3.9.0-0.rc6.git2.4.fc19.ppc64p7 #1 Not tainted
[  953.267661] -------------------------------
[  953.267664] include/linux/cgroup.h:534 suspicious rcu_dereference_check() usage!
[  953.267669]
[  953.267669] other info that might help us debug this:
[  953.267669]
[  953.267675]
[  953.267675] rcu_scheduler_active = 1, debug_locks = 0
[  953.267680] 1 lock held by glxgears/1289:
[  953.267683]  #0:  (&sig->cred_guard_mutex){+.+.+.}, at: [<c00000000027f884>] .prepare_bprm_creds+0x34/0xa0
[  953.267700]
[  953.267700] stack backtrace:
[  953.267704] Call Trace:
[  953.267709] [c0000001f0d1b6e0] [c000000000016e30] .show_stack+0x130/0x200 (unreliable)
[  953.267717] [c0000001f0d1b7b0] [c0000000001267f8] .lockdep_rcu_suspicious+0x138/0x180
[  953.267724] [c0000001f0d1b840] [c0000000001d43a4] .perf_event_comm+0x4c4/0x690
[  953.267731] [c0000001f0d1b950] [c00000000027f6e4] .set_task_comm+0x84/0x1f0
[  953.267737] [c0000001f0d1b9f0] [c000000000280414] .setup_new_exec+0x94/0x220
[  953.267744] [c0000001f0d1ba70] [c0000000002f665c] .load_elf_binary+0x58c/0x19b0
...

This commit therefore adds the required RCU read-side critical
section to perf_event_comm().
Reported-by: default avatarAdam Jackson <ajax@redhat.com>
Signed-off-by: default avatarPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: a.p.zijlstra@chello.nl
Cc: paulus@samba.org
Cc: acme@ghostprotocols.net
Link: http://lkml.kernel.org/r/20130419190124.GA8638@linux.vnet.ibm.comSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
Tested-by: default avatarGustavo Luiz Duarte <gusld@br.ibm.com>
parent f1923820
...@@ -4596,6 +4596,7 @@ void perf_event_comm(struct task_struct *task) ...@@ -4596,6 +4596,7 @@ void perf_event_comm(struct task_struct *task)
struct perf_event_context *ctx; struct perf_event_context *ctx;
int ctxn; int ctxn;
rcu_read_lock();
for_each_task_context_nr(ctxn) { for_each_task_context_nr(ctxn) {
ctx = task->perf_event_ctxp[ctxn]; ctx = task->perf_event_ctxp[ctxn];
if (!ctx) if (!ctx)
...@@ -4603,6 +4604,7 @@ void perf_event_comm(struct task_struct *task) ...@@ -4603,6 +4604,7 @@ void perf_event_comm(struct task_struct *task)
perf_event_enable_on_exec(ctx); perf_event_enable_on_exec(ctx);
} }
rcu_read_unlock();
if (!atomic_read(&nr_comm_events)) if (!atomic_read(&nr_comm_events))
return; return;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment