[PATCH 4.14 43/62] perf/x86: Add check_period PMU callback

[Greg Kroah-Hartman]

4.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Jiri Olsa <jolsa@xxxxxxxxxx>

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@xxxxxxxxx>
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Acked-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Naveen N. Rao <naveen.n.rao@xxxxxxxxxxxxxxxxxx>
Cc: Ravi Bangoria <ravi.bangoria@xxxxxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/20190204123532.GA4794@krava
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 arch/x86/events/core.c       |   14 ++++++++++++++
 arch/x86/events/intel/core.c |    9 +++++++++
 arch/x86/events/perf_event.h |   16 ++++++++++++++--
 include/linux/perf_event.h   |    5 +++++
 kernel/events/core.c         |   16 ++++++++++++++++
 5 files changed, 58 insertions(+), 2 deletions(-)

--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2250,6 +2250,19 @@ void perf_check_microcode(void)
 		x86_pmu.check_microcode();
 }
 
+static int x86_pmu_check_period(struct perf_event *event, u64 value)
+{
+	if (x86_pmu.check_period && x86_pmu.check_period(event, value))
+		return -EINVAL;
+
+	if (value && x86_pmu.limit_period) {
+		if (x86_pmu.limit_period(event, value) > value)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
 	.pmu_disable		= x86_pmu_disable,
@@ -2274,6 +2287,7 @@ static struct pmu pmu = {
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
 	.task_ctx_size          = sizeof(struct x86_perf_task_context),
+	.check_period		= x86_pmu_check_period,
 };
 
 void arch_perf_update_userpage(struct perf_event *event,
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3445,6 +3445,11 @@ static void intel_pmu_sched_task(struct
 	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
+static int intel_pmu_check_period(struct perf_event *event, u64 value)
+{
+	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -3525,6 +3530,8 @@ static __initconst const struct x86_pmu
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.cpu_dead		= intel_pmu_cpu_dead,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static struct attribute *intel_pmu_attrs[];
@@ -3568,6 +3575,8 @@ static __initconst const struct x86_pmu
 
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static __init void intel_clovertown_quirk(void)
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -639,6 +639,11 @@ struct x86_pmu {
 	 * Intel host/guest support (KVM)
 	 */
 	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
+
+	/*
+	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
+	 */
+	int (*check_period) (struct perf_event *event, u64 period);
 };
 
 struct x86_perf_task_context {
@@ -848,7 +853,7 @@ static inline int amd_pmu_init(void)
 
 #ifdef CONFIG_CPU_SUP_INTEL
 
-static inline bool intel_pmu_has_bts(struct perf_event *event)
+static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned int hw_event, bts_event;
@@ -859,7 +864,14 @@ static inline bool intel_pmu_has_bts(str
 	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
 	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
-	return hw_event == bts_event && hwc->sample_period == 1;
+	return hw_event == bts_event && period == 1;
+}
+
+static inline bool intel_pmu_has_bts(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	return intel_pmu_has_bts_period(event, hwc->sample_period);
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -446,6 +446,11 @@ struct pmu {
 	 * Filter events for PMU-specific reasons.
 	 */
 	int (*filter_match)		(struct perf_event *event); /* optional */
+
+	/*
+	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
+	 */
+	int (*check_period)		(struct perf_event *event, u64 value); /* optional */
 };
 
 /**
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4738,6 +4738,11 @@ static void __perf_event_period(struct p
 	}
 }
 
+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;
@@ -4754,6 +4759,9 @@ static int perf_event_period(struct perf
 	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;
@@ -8951,6 +8959,11 @@ static int perf_pmu_nop_int(struct 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)
@@ -9251,6 +9264,9 @@ 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;