perf: Avoid RCU vs preemption assumptions

The per-pmu per-cpu context patch converted things from
get_cpu_var() to this_cpu_ptr(), but that only works if
rcu_read_lock() actually disables preemption, and since
there is no such guarantee, we need to fix that.

Use the newly introduced {get,put}_cpu_ptr().

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Tejun Heo <tj@kernel.org>
LKML-Reference: <20100917093009.308453028@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index baae136..c16158c 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -3836,18 +3836,20 @@
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
 		perf_event_task_ctx(&cpuctx->ctx, task_event);
 
 		ctx = task_event->task_ctx;
 		if (!ctx) {
 			ctxn = pmu->task_ctx_nr;
 			if (ctxn < 0)
-				continue;
+				goto next;
 			ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
 		}
 		if (ctx)
 			perf_event_task_ctx(ctx, task_event);
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
 	}
 	rcu_read_unlock();
 }
@@ -3969,16 +3971,18 @@
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
 		perf_event_comm_ctx(&cpuctx->ctx, comm_event);
 
 		ctxn = pmu->task_ctx_nr;
 		if (ctxn < 0)
-			continue;
+			goto next;
 
 		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
 		if (ctx)
 			perf_event_comm_ctx(ctx, comm_event);
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
 	}
 	rcu_read_unlock();
 }
@@ -4152,19 +4156,21 @@
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
 		perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
 					vma->vm_flags & VM_EXEC);
 
 		ctxn = pmu->task_ctx_nr;
 		if (ctxn < 0)
-			continue;
+			goto next;
 
 		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
 		if (ctx) {
 			perf_event_mmap_ctx(ctx, mmap_event,
 					vma->vm_flags & VM_EXEC);
 		}
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
 	}
 	rcu_read_unlock();