perf: Tighten (and fix) the grouping condition

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@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20150123125834.090683288@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 13 insertions, 8 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4f7a61ca4b39..664de5a4ec46 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -450,11 +450,6 @@ struct perf_event {
 #endif /* CONFIG_PERF_EVENTS */
 };
 
-enum perf_event_context_type {
-        task_context,
-        cpu_context,
-};
-
 /**
  * struct perf_event_context - event context structure
  *
@@ -462,7 +457,6 @@ 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 882f835a0d85..19efcf13375a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6776,7 +6776,6 @@ 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;
 
                 __perf_cpu_hrtimer_init(cpuctx, cpu);
@@ -7420,7 +7419,19 @@ 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)