[Patch v2 7/7] perf/x86: Optimize ACR handling in match_prev_assignment()

[Dapeng Mi]

match_prev_assignment() currently forces a mismatch for ACR events, so
ACR counter indices are reprogrammed on every scheduling pass. That
causes avoidable overhead because disable and enable paths must touch
multiple MSRs.

The previous ACR assignment is already cached in acr_cfg_b[]. Use that
state to compare the newly computed ACR counter indices in hwc->config1
against the cached value in acr_cfg_b[hwc->idx]. If they match, skip
unnecessary disable and enable work.

Also tighten is_acr_self_reload_event() so it first verifies the event
is an ACR event before testing for the self-reload case.

Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
---
 arch/x86/events/core.c       | 13 ++++++++++++-
 arch/x86/events/perf_event.h |  2 +-
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 143a6e735d9e..8b3ea0adb965 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1297,6 +1297,17 @@ int x86_perf_rdpmc_index(struct perf_event *event)
 	return event->hw.event_base_rdpmc;
 }
 
+static inline bool acr_match_prev_indices(struct perf_event *event,
+					  struct cpu_hw_events *cpuc)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!is_acr_event_group(event))
+		return true;
+	/* ACR counter indices don't change. */
+	return hwc->config1 == cpuc->acr_cfg_b[hwc->idx];
+}
+
 static inline int match_prev_assignment(struct perf_event *event,
 					struct cpu_hw_events *cpuc,
 					int i)
@@ -1306,7 +1317,7 @@ static inline int match_prev_assignment(struct perf_event *event,
 	return hwc->idx == cpuc->assign[i] &&
 	       hwc->last_cpu == smp_processor_id() &&
 	       hwc->last_tag == cpuc->tags[i] &&
-	       !is_acr_event_group(event);
+	       acr_match_prev_indices(event, cpuc);
 }
 
 static void x86_pmu_start(struct perf_event *event, int flags);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index cc9cfaae4f01..fa381110f7a7 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -141,7 +141,7 @@ static inline bool is_acr_self_reload_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (hwc->idx < 0)
+	if (hwc->idx < 0 || !is_acr_event_group(event))
 		return false;
 
 	return test_bit(hwc->idx, (unsigned long *)&hwc->config1);
-- 
2.34.1