[Patch v5 08/18] perf/x86/intel: Avoid re-enabling PMU and LBR for BPF when disabled

[Dapeng Mi]

__intel_pmu_snapshot_branch_stack() currently re-enables the PMU and LBR
unconditionally even when they were already disabled in PMI context.
This can cause events such as cycles and instructions to be counted
while the PMI handler is running, which is not intended.

Only restore the PMU and LBR on the BPF path if they were originally
enabled.

Reported-by: Sashiko <sashiko-bot@xxxxxxxxxx>
Closes: https://lore.kernel.org/all/sashiko-outbox-179823@xxxxxxxxxx/
Fixes: c22ac2a3d4bd ("perf: Enable branch record for software events")
Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
---
 arch/x86/events/intel/core.c | 38 ++++++++++++++++++++++++++++++++----
 1 file changed, 34 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 5b44a4224d2c..15dcf8b78de9 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2821,7 +2821,8 @@ static void intel_pmu_enable_all(int added)
 
 static noinline int
 __intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries,
-				  unsigned int cnt, unsigned long flags)
+				  unsigned int cnt, unsigned long flags,
+				  int pmu_enabled, int lbr_enabled)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
@@ -2829,7 +2830,22 @@ __intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries,
 	cnt = min_t(unsigned int, cnt, cpuc->lbr_stack.nr);
 
 	memcpy(entries, cpuc->lbr_entries, sizeof(struct perf_branch_entry) * cnt);
-	intel_pmu_enable_all(0);
+
+	/*
+	 * Do not blindly call intel_pmu_enable_all() to re-enable LBR.
+	 * This path may be entered from the PMI handler through
+	 * bpf_overflow_handler().
+	 *
+	 * If PMU version < 4, LBR is disabled by the LBR freeze mechanism,
+	 * LBR can't be re-enabled here.
+	 * If PMU version >= 4, LBR is only frozen instead of disabled,
+	 * LBR should be re-enabled here.
+	 */
+	if (lbr_enabled)
+		intel_pmu_lbr_enable_all(false);
+	if (pmu_enabled)
+		___intel_pmu_enable_all();
+
 	local_irq_restore(flags);
 	return cnt;
 }
@@ -2837,27 +2853,41 @@ __intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries,
 static int
 intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
 {
+	struct cpu_hw_events *cpuc;
 	unsigned long flags;
+	int pmu_enabled;
+	int lbr_enabled;
 
 	/* must not have branches... */
 	local_irq_save(flags);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
+	pmu_enabled = cpuc->enabled;
+	lbr_enabled = cpuc->lbr_enabled;
 	__intel_pmu_disable_all(false); /* we don't care about BTS */
 	__intel_pmu_lbr_disable();
 	/*            ... until here */
-	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags);
+	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags,
+						 pmu_enabled, lbr_enabled);
 }
 
 static int
 intel_pmu_snapshot_arch_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
 {
+	struct cpu_hw_events *cpuc;
 	unsigned long flags;
+	int pmu_enabled;
+	int lbr_enabled;
 
 	/* must not have branches... */
 	local_irq_save(flags);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
+	pmu_enabled = cpuc->enabled;
+	lbr_enabled = cpuc->lbr_enabled;
 	__intel_pmu_disable_all(false); /* we don't care about BTS */
 	__intel_pmu_arch_lbr_disable();
 	/*            ... until here */
-	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags);
+	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags,
+						 pmu_enabled, lbr_enabled);
 }
 
 /*
-- 
2.34.1