[PATCH 3.10 211/319] perf: Tighten (and fix) the grouping condition

[Willy Tarreau]

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

commit c3c87e770458aa004bd7ed3f29945ff436fd6511 upstream.

The fix from 9fc81d87420d ("perf: Fix events installation during
moving group") was incomplete in that it failed to recognise that
creating a group with events for different CPUs is semantically
broken -- they cannot be co-scheduled.

Furthermore, it leads to real breakage where, when we create an event
for CPU Y and then migrate it to form a group on CPU X, the code gets
confused where the counter is programmed -- triggered in practice
as well by me via the perf fuzzer.

Fix this by tightening the rules for creating groups. Only allow
grouping of counters that can be co-scheduled in the same context.
This means for the same task and/or the same cpu.

Fixes: 9fc81d87420d ("perf: Fix events installation during moving group")
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/20150123125834.090683288@xxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Willy Tarreau <w@xxxxxx>
---
 include/linux/perf_event.h |  6 ------
 kernel/events/core.c       | 15 +++++++++++++--
 2 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 229a757..3204422 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -430,11 +430,6 @@ struct perf_event {
 #endif /* CONFIG_PERF_EVENTS */
 };
 
-enum perf_event_context_type {
-	task_context,
-	cpu_context,
-};
-
 /**
  * struct perf_event_context - event context structure
  *
@@ -442,7 +437,6 @@ enum perf_event_context_type {
  */
 struct perf_event_context {
 	struct pmu			*pmu;
-	enum perf_event_context_type	type;
 	/*
 	 * Protect the states of the events in the list,
 	 * nr_active, and the list:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0f52078..76e26b8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6249,7 +6249,6 @@ skip_type:
 		__perf_event_init_context(&cpuctx->ctx);
 		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
-		cpuctx->ctx.type = cpu_context;
 		cpuctx->ctx.pmu = pmu;
 		cpuctx->jiffies_interval = 1;
 		INIT_LIST_HEAD(&cpuctx->rotation_list);
@@ -6856,7 +6855,19 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * task or CPU context:
 		 */
 		if (move_group) {
-			if (group_leader->ctx->type != ctx->type)
+			/*
+			 * Make sure we're both on the same task, or both
+			 * per-cpu events.
+			 */
+			if (group_leader->ctx->task != ctx->task)
+				goto err_context;
+
+			/*
+			 * Make sure we're both events for the same CPU;
+			 * grouping events for different CPUs is broken; since
+			 * you can never concurrently schedule them anyhow.
+			 */
+			if (group_leader->cpu != event->cpu)
 				goto err_context;
 		} else {
 			if (group_leader->ctx != ctx)
-- 
2.8.0.rc2.1.gbe9624a