From: Alexander Shishkin <[email protected]>
commit 8a58ddae23796c733c5dfbd717538d89d036c5bd upstream.
So far, we tried to disallow grouping exclusive events for the fear of
complications they would cause with moving between contexts. Specifically,
moving a software group to a hardware context would violate the exclusivity
rules if both groups contain matching exclusive events.
This attempt was, however, unsuccessful: the check that we have in the
perf_event_open() syscall is both wrong (looks at wrong PMU) and
insufficient (group leader may still be exclusive), as can be illustrated
by running:
$ perf record -e '{intel_pt//,cycles}' uname
$ perf record -e '{cycles,intel_pt//}' uname
ultimately successfully.
Furthermore, we are completely free to trigger the exclusivity violation
by:
perf -e '{cycles,intel_pt//}' -e '{intel_pt//,instructions}'
even though the helpful perf record will not allow that, the ABI will.
The warning later in the perf_event_open() path will also not trigger, because
it's also wrong.
Fix all this by validating the original group before moving, getting rid
of broken safeguards and placing a useful one to perf_install_in_context().
Signed-off-by: Alexander Shishkin <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vince Weaver <[email protected]>
Cc: [email protected]
Cc: [email protected]
Fixes: bed5b25ad9c8a ("perf: Add a pmu capability for "exclusive" events")
Link:
https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
---
include/linux/perf_event.h | 5 +++++
kernel/events/core.c | 34 ++++++++++++++++++++++------------
2 files changed, 27 insertions(+), 12 deletions(-)
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1049,6 +1049,11 @@ static inline int in_software_context(st
return event->ctx->pmu->task_ctx_nr == perf_sw_context;
}
+static inline int is_exclusive_pmu(struct pmu *pmu)
+{
+ return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE;
+}
+
extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2553,6 +2553,9 @@ unlock:
return ret;
}
+static bool exclusive_event_installable(struct perf_event *event,
+ struct perf_event_context *ctx);
+
/*
* Attach a performance event to a context.
*
@@ -2567,6 +2570,8 @@ perf_install_in_context(struct perf_even
lockdep_assert_held(&ctx->mutex);
+ WARN_ON_ONCE(!exclusive_event_installable(event, ctx));
+
if (event->cpu != -1)
event->cpu = cpu;
@@ -4358,7 +4363,7 @@ static int exclusive_event_init(struct p
{
struct pmu *pmu = event->pmu;
- if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
+ if (!is_exclusive_pmu(pmu))
return 0;
/*
@@ -4389,7 +4394,7 @@ static void exclusive_event_destroy(stru
{
struct pmu *pmu = event->pmu;
- if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
+ if (!is_exclusive_pmu(pmu))
return;
/* see comment in exclusive_event_init() */
@@ -4409,14 +4414,15 @@ static bool exclusive_event_match(struct
return false;
}
-/* Called under the same ctx::mutex as perf_install_in_context() */
static bool exclusive_event_installable(struct perf_event *event,
struct perf_event_context *ctx)
{
struct perf_event *iter_event;
struct pmu *pmu = event->pmu;
- if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
+ lockdep_assert_held(&ctx->mutex);
+
+ if (!is_exclusive_pmu(pmu))
return true;
list_for_each_entry(iter_event, &ctx->event_list, event_entry) {
@@ -10922,11 +10928,6 @@ SYSCALL_DEFINE5(perf_event_open,
goto err_alloc;
}
- if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) {
- err = -EBUSY;
- goto err_context;
- }
-
/*
* Look up the group leader (we will attach this event to it):
*/
@@ -11014,6 +11015,18 @@ SYSCALL_DEFINE5(perf_event_open,
move_group = 0;
}
}
+
+ /*
+ * Failure to create exclusive events returns -EBUSY.
+ */
+ err = -EBUSY;
+ if (!exclusive_event_installable(group_leader, ctx))
+ goto err_locked;
+
+ for_each_sibling_event(sibling, group_leader) {
+ if (!exclusive_event_installable(sibling, ctx))
+ goto err_locked;
+ }
} else {
mutex_lock(&ctx->mutex);
}
@@ -11050,9 +11063,6 @@ SYSCALL_DEFINE5(perf_event_open,
* because we need to serialize with concurrent event creation.
*/
if (!exclusive_event_installable(event, ctx)) {
- /* exclusive and group stuff are assumed mutually exclusive */
- WARN_ON_ONCE(move_group);
-
err = -EBUSY;
goto err_locked;
}
