[PATCH] perf/x86/amd: Warn only on new bits set

[Breno Leitao]

Warning at every leaking bits can cause a flood of message, triggering
vairous stall-warning mechanisms to fire, including CSD locks, which
makes the machine to be unusable.

Track the bits that are being leaked, and only warn when a new bit is
set.

Suggested-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Signed-off-by: Breno Leitao <leitao@xxxxxxxxxx>
---
 arch/x86/events/amd/core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 1fc4ce44e743..df0ba2382d13 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -941,11 +941,12 @@ static int amd_pmu_v2_snapshot_branch_stack(struct perf_branch_entry *entries, u
 static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	static atomic64_t status_warned = ATOMIC64_INIT(0);
+	u64 reserved, status, mask, new_bits;
 	struct perf_sample_data data;
 	struct hw_perf_event *hwc;
 	struct perf_event *event;
 	int handled = 0, idx;
-	u64 reserved, status, mask;
 	bool pmu_enabled;
 
 	/*
@@ -1010,7 +1011,11 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 	 * the corresponding PMCs are expected to be inactive according to the
 	 * active_mask
 	 */
-	WARN_ON(status > 0);
+	if (status > 0) {
+		new_bits = atomic64_fetch_or(status, &status_warned) ^ atomic64_read(&status_warned);
+		// A new bit was set for the very first time.
+		WARN(new_bits, "New overflows for inactive PMCs: %llx\n", new_bits);
+	}
 
 	/* Clear overflow and freeze bits */
 	amd_pmu_ack_global_status(~status);
-- 
2.43.0