perf/x86: Add check_period PMU callback

commit 81ec3f3c4c4d78f2d3b6689c9816bfbdf7417dbb upstream.

Vince (and later on Ravi) reported crashes in the BTS code during
fuzzing with the following backtrace:

  general protection fault: 0000 [#1] SMP PTI
  ...
  RIP: 0010:perf_prepare_sample+0x8f/0x510
  ...
  Call Trace:
   <IRQ>
   ? intel_pmu_drain_bts_buffer+0x194/0x230
   intel_pmu_drain_bts_buffer+0x160/0x230
   ? tick_nohz_irq_exit+0x31/0x40
   ? smp_call_function_single_interrupt+0x48/0xe0
   ? call_function_single_interrupt+0xf/0x20
   ? call_function_single_interrupt+0xa/0x20
   ? x86_schedule_events+0x1a0/0x2f0
   ? x86_pmu_commit_txn+0xb4/0x100
   ? find_busiest_group+0x47/0x5d0
   ? perf_event_set_state.part.42+0x12/0x50
   ? perf_mux_hrtimer_restart+0x40/0xb0
   intel_pmu_disable_event+0xae/0x100
   ? intel_pmu_disable_event+0xae/0x100
   x86_pmu_stop+0x7a/0xb0
   x86_pmu_del+0x57/0x120
   event_sched_out.isra.101+0x83/0x180
   group_sched_out.part.103+0x57/0xe0
   ctx_sched_out+0x188/0x240
   ctx_resched+0xa8/0xd0
   __perf_event_enable+0x193/0x1e0
   event_function+0x8e/0xc0
   remote_function+0x41/0x50
   flush_smp_call_function_queue+0x68/0x100
   generic_smp_call_function_single_interrupt+0x13/0x30
   smp_call_function_single_interrupt+0x3e/0xe0
   call_function_single_interrupt+0xf/0x20
   </IRQ>

The reason is that while event init code does several checks
for BTS events and prevents several unwanted config bits for
BTS event (like precise_ip), the PERF_EVENT_IOC_PERIOD allows
to create BTS event without those checks being done.

Following sequence will cause the crash:

If we create an 'almost' BTS event with precise_ip and callchains,
and it into a BTS event it will crash the perf_prepare_sample()
function because precise_ip events are expected to come
in with callchain data initialized, but that's not the
case for intel_pmu_drain_bts_buffer() caller.

Adding a check_period callback to be called before the period
is changed via PERF_EVENT_IOC_PERIOD. It will deny the change
if the event would become BTS. Plus adding also the limit_period
check as well.

Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20190204123532.GA4794@krava
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 16 insertions, 0 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1af0bbf20984..17339506f9f8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4600,6 +4600,11 @@ static void __perf_event_period(struct perf_event *event,
 	}
 }
 
+static int perf_event_check_period(struct perf_event *event, u64 value)
+{
+	return event->pmu->check_period(event, value);
+}
+
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	u64 value;
@@ -4616,6 +4621,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
 		return -EINVAL;
 
+	if (perf_event_check_period(event, value))
+		return -EINVAL;
+
 	event_function_call(event, __perf_event_period, &value);
 
 	return 0;
@@ -8622,6 +8630,11 @@ static int perf_pmu_nop_int(struct pmu *pmu)
 	return 0;
 }
 
+static int perf_event_nop_int(struct perf_event *event, u64 value)
+{
+	return 0;
+}
+
 static DEFINE_PER_CPU(unsigned int, nop_txn_flags);
 
 static void perf_pmu_start_txn(struct pmu *pmu, unsigned int flags)
@@ -8944,6 +8957,9 @@ got_cpu_context:
 		pmu->pmu_disable = perf_pmu_nop_void;
 	}
 
+	if (!pmu->check_period)
+		pmu->check_period = perf_event_nop_int;
+
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;