perf/core: Fix reentry problem in perf_output_read_group()

commit 6b959ba22d34ca793ffdb15b5715457c78e38b1a upstream.

perf_output_read_group may respond to IPI request of other cores and invoke
__perf_install_in_context function. As a result, hwc configuration is modified.
causing inconsistency and unexpected consequences.

Interrupts are not disabled when perf_output_read_group reads PMU counter.
In this case, IPI request may be received from other cores.
As a result, PMU configuration is modified and an error occurs when
reading PMU counter:

		     CPU0                                         CPU1
						      __se_sys_perf_event_open
							perf_install_in_context
  perf_output_read_group                                  smp_call_function_single
    for_each_sibling_event(sub, leader) {                   generic_exec_single
      if ((sub != event) &&                                   remote_function
	  (sub->state == PERF_EVENT_STATE_ACTIVE))                    |
  <enter IPI handler: __perf_install_in_context>   <----RAISE IPI-----+
  __perf_install_in_context
    ctx_resched
      event_sched_out
	armpmu_del
	  ...
	  hwc->idx = -1; // event->hwc.idx is set to -1
  ...
  <exit IPI>
	      sub->pmu->read(sub);
		armpmu_read
		  armv8pmu_read_counter
		    armv8pmu_read_hw_counter
		      int idx = event->hw.idx; // idx = -1
		      u64 val = armv8pmu_read_evcntr(idx);
			u32 counter = ARMV8_IDX_TO_COUNTER(idx); // invalid counter = 30
			read_pmevcntrn(counter) // undefined instruction

Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220902082918.179248-1-yangjihong1@huawei.com
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4e5a73c7db12c221e16f4e393eaf3374610295b5..e79cd0fd1d2b74d6d7ff92c9e3c2e2efd964ccc1 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7119,9 +7119,16 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 {
        struct perf_event *leader = event->group_leader, *sub;
        u64 read_format = event->attr.read_format;
+       unsigned long flags;
        u64 values[6];
        int n = 0;
 
+       /*
+        * Disabling interrupts avoids all counter scheduling
+        * (context switches, timer based rotation and IPIs).
+        */
+       local_irq_save(flags);
+
        values[n++] = 1 + leader->nr_siblings;
 
        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
@@ -7157,6 +7164,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 
                __output_copy(handle, values, n * sizeof(u64));
        }
+
+       local_irq_restore(flags);
 }
 
 #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\