Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Thomas Gleixner:
 - fix for do_div() abuse on x86
 - locking fix in perf core
 - a pile of (build) fixes and cleanups in perf tools

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
  perf/x86: Fix incorrect use of do_div() in NMI warning
  perf: Fix perf_lock_task_context() vs RCU
  perf: Remove WARN_ON_ONCE() check in __perf_event_enable() for valid scenario
  perf: Clone child context from parent context pmu
  perf script: Fix broken include in Context.xs
  perf tools: Fix -ldw/-lelf link test when static linking
  perf tools: Revert regression in configuration of Python support
  perf tools: Fix perf version generation
  perf stat: Fix per-socket output bug for uncore events
  perf symbols: Fix vdso list searching
  perf evsel: Fix missing increment in sample parsing
  perf tools: Update symbol_conf.nr_events when processing attribute events
  perf tools: Fix new_term() missing free on error path
  perf tools: Fix parse_events_terms() segfault on error path
  perf evsel: Fix count parameter to read call in event_format__new
  perf tools: fix a typo of a Power7 event name
  perf tools: Fix -x/--exclude-other option for report command
  perf evlist: Enhance perf_evlist__start_workload()
  perf record: Remove -f/--force option
  perf record: Remove -A/--append option
  ...

1 files changed, 25 insertions, 3 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1833bc5..eba8fb5 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;
 }
 
@@ -1950,7 +1963,16 @@ static int __perf_event_enable(void *info)
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	int err;
 
-	if (WARN_ON_ONCE(!ctx->is_active))
+	/*
+	 * There's a time window between 'ctx->is_active' check
+	 * in perf_event_enable function and this place having:
+	 *   - IRQs on
+	 *   - ctx->lock unlocked
+	 *
+	 * where the task could be killed and 'ctx' deactivated
+	 * by perf_event_exit_task.
+	 */
+	if (!ctx->is_active)
 		return -EINVAL;
 
 	raw_spin_lock(&ctx->lock);
@@ -7465,7 +7487,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		 * child.
 		 */
 
-		child_ctx = alloc_perf_context(event->pmu, child);
+		child_ctx = alloc_perf_context(parent_ctx->pmu, child);
 		if (!child_ctx)
 			return -ENOMEM;