Messages in this thread Patch in this message | | | Subject | [PATCH] mce: fix RCU lockdep from mce_log() | From | Davidlohr Bueso <> | Date | Fri, 05 Nov 2010 18:44:59 -0300 |
| |
Hi,
Please review this patch, I am not very familiar with MCE/RCU so I'm not sure that this is the correct fix (otherwise consider it a bug report :)). This does "fix" the message though and I can use MCE normally.
Thanks, Davidlohr
From: Davidlohr Bueso <dave@gnu.org>
Based on the following message:
=================================================== [ INFO: suspicious rcu_dereference_check() usage. ] --------------------------------------------------- arch/x86/kernel/cpu/mcheck/mce.c:1628 invoked rcu_dereference_check() without protection!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks = 1 no locks held by mcelog/2350.
stack backtrace: Pid: 2350, comm: mcelog Tainted: G W 2.6.37-rc1+ #7 Call Trace: [<ffffffff8108e6d4>] lockdep_rcu_dereference+0xa4/0xc0 [<ffffffff810189e9>] mce_poll+0xa9/0xd0 [<ffffffff81160585>] do_sys_poll+0x275/0x550 [<ffffffff8115f0e0>] ? __pollwait+0x0/0xf0 [<ffffffff8115f1d0>] ? pollwake+0x0/0x60 [<ffffffff8115f1d0>] ? pollwake+0x0/0x60 [<ffffffff8130431c>] ? rcu_read_lock_held+0x2c/0x30 [<ffffffff8130549a>] ? radix_tree_lookup_element+0xda/0x100 [<ffffffff81121f08>] ? __do_fault+0x128/0x470 [<ffffffff81100bdb>] ? filemap_fault+0xdb/0x4e0 [<ffffffff810ffe75>] ? unlock_page+0x25/0x30 [<ffffffff81069ddf>] ? sigprocmask+0x3f/0x100 [<ffffffff8183672b>] ? _raw_spin_unlock_irq+0x2b/0x60 [<ffffffff8108fefd>] ? trace_hardirqs_on_caller+0x13d/0x180 [<ffffffff8108ff4d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8183672b>] ? _raw_spin_unlock_irq+0x2b/0x60 [<ffffffff811608a7>] sys_ppoll+0x47/0x190 [<ffffffff8108fefd>] ? trace_hardirqs_on_caller+0x13d/0x180 [<ffffffff81835d39>] ? trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff810030eb>] system_call_fastpath+0x16/0x1b
At this point the arch/x86/kernel/cpu/mcheck/mce.c:1628 invoked rcu_dereference_check() without protection!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks = 1 no locks held by mcelog/2350.
stack backtrace: Pid: 2350, comm: mcelog Tainted: G W 2.6.37-rc1+ #7 Call Trace: [<ffffffff8108e6d4>] lockdep_rcu_dereference+0xa4/0xc0 [<ffffffff810189e9>] mce_poll+0xa9/0xd0 [<ffffffff81160585>] do_sys_poll+0x275/0x550 [<ffffffff8115f0e0>] ? __pollwait+0x0/0xf0 [<ffffffff8115f1d0>] ? pollwake+0x0/0x60 [<ffffffff8115f1d0>] ? pollwake+0x0/0x60 [<ffffffff8130431c>] ? rcu_read_lock_held+0x2c/0x30 [<ffffffff8130549a>] ? radix_tree_lookup_element+0xda/0x100 [<ffffffff81121f08>] ? __do_fault+0x128/0x470 [<ffffffff81100bdb>] ? filemap_fault+0xdb/0x4e0 [<ffffffff810ffe75>] ? unlock_page+0x25/0x30 [<ffffffff81069ddf>] ? sigprocmask+0x3f/0x100 [<ffffffff8183672b>] ? _raw_spin_unlock_irq+0x2b/0x60 [<ffffffff8108fefd>] ? trace_hardirqs_on_caller+0x13d/0x180 [<ffffffff8108ff4d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8183672b>] ? _raw_spin_unlock_irq+0x2b/0x60 [<ffffffff811608a7>] sys_ppoll+0x47/0x190 [<ffffffff8108fefd>] ? trace_hardirqs_on_caller+0x13d/0x180 [<ffffffff81835d39>] ? trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff810030eb>] system_call_fastpath+0x16/0x1b
At this point the lockdep_is_held(&mce_read_mutex) call is failing. So check if the mce_read_mutex is held before derefencing instead of using rcu_dereference_check_mce()
Signed-off-by: Davidlohr Bueso <dave@gnu.org> --- arch/x86/kernel/cpu/mcheck/mce.c | 8 ++++++-- 1 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 7a35b72..6f95b2c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1625,8 +1625,12 @@ out: static unsigned int mce_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_wait, wait); - if (rcu_dereference_check_mce(mcelog.next)) - return POLLIN | POLLRDNORM; + + if (mutex_is_locked(&mce_read_mutex)) { + if (rcu_dereference_index_check(mcelog.next, + rcu_read_lock_sched_held())) + return POLLIN | POLLRDNORM; + } if (!mce_apei_read_done && apei_check_mce()) return POLLIN | POLLRDNORM; return 0; -- 1.7.1
| |