events: Protect access via task_subsys_state_check()
PATCH 1/1 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
[ 953.267751] [c0000001f0d1bbc0] [c00000000027e724] .search_binary_handler+0x254/0x680
[ 953.267758] [c0000001f0d1bca0] [c0000000002800dc] .do_execve_common.isra.17+0x76c/0x860
[ 953.267764] [c0000001f0d1bd90] [c000000000280698] .SyS_execve+0x58/0x90
[ 953.267771] [c0000001f0d1be30] [c000000000009e60] syscall_exit+0x0/0x98This commit therefore adds the required RCU read-side critical section to perf_event_comm().
Reported-by Adam Jackson <[email protected]>
Signed-off-by Paul E. McKenney <[email protected]>
Tested-by Gustavo Luiz Duarte <[email protected]>
kernel/events/core.c +2 -0
@@ -4593,6 +4593,7 @@ void perf_event_comm(struct task_struct *task)struct perf_event_context *ctx;int ctxn; +rcu_read_lock ();for_each_task_context_nr (ctxn) { ctx = task->perf_event_ctxp[ctxn];if (!ctx)
@@ -4600,6 +4601,7 @@ void perf_event_comm(struct task_struct *task)perf_event_enable_on_exec (ctx); } +rcu_read_unlock ();if (!atomic_read (&nr_comm_events))return ;
tip-bot for Paul E. McKenney
merge botevents: Protect access via task_subsys_state_check()
Commit-ID: c79aa0d96548aee50570209eb2d45c8f4ac49230 Gitweb: http://git.kernel.org/tip/c79aa0d96548aee50570209eb2d45c8f4ac49230 Author: Paul E. McKenney <[email protected]> AuthorDate: Fri, 19 Apr 2013 12:01:24 -0700 Committer: Ingo Molnar <[email protected]> CommitDate: Sun, 21 Apr 2013 11:21:39 +0200
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 Adam Jackson <[email protected]>
Signed-off-by Paul E. McKenney <[email protected]>
Signed-off-by Ingo Molnar <[email protected]>
Tested-by Gustavo Luiz Duarte <[email protected]>
--- kernel/events/core.c | 2 ++ 1 file changed, 2 insertions(+)
kernel/events/core.c +2 -0
@@ -4596,6 +4596,7 @@ void perf_event_comm(struct task_struct *task)struct perf_event_context *ctx;int ctxn; +rcu_read_lock ();for_each_task_context_nr (ctxn) { ctx = task->perf_event_ctxp[ctxn];if (!ctx)
@@ -4603,6 +4604,7 @@ void perf_event_comm(struct task_struct *task)perf_event_enable_on_exec (ctx); } +rcu_read_unlock ();if (!atomic_read (&nr_comm_events))return ;
Quoted 1 line · Paul E. McKenney
The following RCU splat indicates lack of RCU protection:
...
Quoted 6 lines
This commit therefore adds the required RCU read-side critical section to
perf_event_comm().Reported-by Adam Jackson <[email protected]>Signed-off-by Paul E. McKenney <[email protected]>Tested-by Gustavo Luiz Duarte <[email protected]>
Acked-by Peter Zijlstra <[email protected]>
Quoted 21 lines
kernel/events/core.c +2
-0@@ -4593,6 +4593,7 @@ void perf_event_comm(struct task_struct *task)struct perf_event_context *ctx;int ctxn; +rcu_read_lock ();for_each_task_context_nr (ctxn) { ctx = task->perf_event_ctxp[ctxn];if (!ctx)@@ -4600,6 +4601,7 @@ void perf_event_comm(struct task_struct *task)perf_event_enable_on_exec (ctx); } +rcu_read_unlock ();if (!atomic_read (&nr_comm_events))return ;