From 058ebd0eba3aff16b144eabf4510ed9510e1416e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 12 Jul 2013 11:08:33 +0200 Subject: [PATCH] perf: Fix perf_lock_task_context() vs RCU Jiri managed to trigger this warning: [] ====================================================== [] [ INFO: possible circular locking dependency detected ] [] 3.10.0+ #228 Tainted: G W [] ------------------------------------------------------- [] p/6613 is trying to acquire lock: [] (rcu_node_0){..-...}, at: [] rcu_read_unlock_special+0xa7/0x250 [] [] but task is already holding lock: [] (&ctx->lock){-.-...}, at: [] perf_lock_task_context+0xd9/0x2c0 [] [] which lock already depends on the new lock. [] [] the existing dependency chain (in reverse order) is: [] [] -> #4 (&ctx->lock){-.-...}: [] -> #3 (&rq->lock){-.-.-.}: [] -> #2 (&p->pi_lock){-.-.-.}: [] -> #1 (&rnp->nocb_gp_wq[1]){......}: [] -> #0 (rcu_node_0){..-...}: Paul was quick to explain that due to preemptible RCU we cannot call rcu_read_unlock() while holding scheduler (or nested) locks when part of the read side critical section was preemptible. Therefore solve it by making the entire RCU read side non-preemptible. Also pull out the retry from under the non-preempt to play nice with RT. Reported-by: Jiri Olsa Helped-out-by: Paul E. McKenney Cc: Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/events/core.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index ef5e7cc686e3..eba8fb5834ae 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -947,8 +947,18 @@ perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags) { struct perf_event_context *ctx; - rcu_read_lock(); retry: + /* + * One of the few rules of preemptible RCU is that one cannot do + * rcu_read_unlock() while holding a scheduler (or nested) lock when + * part of the read side critical section was preemptible -- see + * rcu_read_unlock_special(). + * + * Since ctx->lock nests under rq->lock we must ensure the entire read + * side critical section is non-preemptible. + */ + preempt_disable(); + rcu_read_lock(); ctx = rcu_dereference(task->perf_event_ctxp[ctxn]); if (ctx) { /* @@ -964,6 +974,8 @@ retry: raw_spin_lock_irqsave(&ctx->lock, *flags); if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) { raw_spin_unlock_irqrestore(&ctx->lock, *flags); + rcu_read_unlock(); + preempt_enable(); goto retry; } @@ -973,6 +985,7 @@ retry: } } rcu_read_unlock(); + preempt_enable(); return ctx; }