1 files changed, 22 insertions, 20 deletions

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 19a9fd974e3e..54007174c15b 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -932,11 +932,11 @@ unlock:
 	return 1;
 }
 
-static inline void intel_pmu_drain_pebs_buffer(void)
+void intel_pmu_drain_pebs_buffer(void)
 {
 	struct perf_sample_data data;
 
-	x86_pmu.drain_pebs(NULL, &data);
+	static_call(x86_pmu_drain_pebs)(NULL, &data);
 }
 
 /*
@@ -1178,7 +1178,7 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
 
-	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff),
+	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3fc),
 	INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_STORES */
@@ -1317,8 +1317,10 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 	 * + precise_ip < 2 for the non event IP
 	 * + For RTM TSX weight we need GPRs for the abort code.
 	 */
-	gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
-	       (attr->sample_regs_intr & PEBS_GP_REGS);
+	gprs = ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+		(attr->sample_regs_intr & PEBS_GP_REGS)) ||
+	       ((sample_type & PERF_SAMPLE_REGS_USER) &&
+		(attr->sample_regs_user & PEBS_GP_REGS));
 
 	tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) &&
 		     ((attr->config & INTEL_ARCH_EVENT_MASK) ==
@@ -1970,7 +1972,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			regs->flags &= ~PERF_EFLAGS_EXACT;
 		}
 
-		if (sample_type & PERF_SAMPLE_REGS_INTR)
+		if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER))
 			adaptive_pebs_save_regs(regs, gprs);
 	}
 
@@ -2079,15 +2081,6 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
 	return NULL;
 }
 
-void intel_pmu_auto_reload_read(struct perf_event *event)
-{
-	WARN_ON(!(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD));
-
-	perf_pmu_disable(event->pmu);
-	intel_pmu_drain_pebs_buffer();
-	perf_pmu_enable(event->pmu);
-}
-
 /*
  * Special variant of intel_pmu_save_and_restart() for auto-reload.
  */
@@ -2247,8 +2240,9 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_
 			       setup_pebs_fixed_sample_data);
 }
 
-static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, u64 mask)
 {
+	u64 pebs_enabled = cpuc->pebs_enabled & mask;
 	struct perf_event *event;
 	int bit;
 
@@ -2259,7 +2253,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int
 	 * It needs to call intel_pmu_save_and_restart_reload() to
 	 * update the event->count for this case.
 	 */
-	for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+	for_each_set_bit(bit, (unsigned long *)&pebs_enabled, X86_PMC_IDX_MAX) {
 		event = cpuc->events[bit];
 		if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
 			intel_pmu_save_and_restart_reload(event, 0);
@@ -2294,7 +2288,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 	}
 
 	if (unlikely(base >= top)) {
-		intel_pmu_pebs_event_update_no_drain(cpuc, size);
+		intel_pmu_pebs_event_update_no_drain(cpuc, mask);
 		return;
 	}
 
@@ -2404,7 +2398,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 	       (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
 
 	if (unlikely(base >= top)) {
-		intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
+		intel_pmu_pebs_event_update_no_drain(cpuc, mask);
 		return;
 	}
 
@@ -2523,7 +2517,15 @@ void __init intel_ds_init(void)
 			}
 			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
 
-			if (!is_hybrid() && x86_pmu.intel_cap.pebs_output_pt_available) {
+			/*
+			 * The PEBS-via-PT is not supported on hybrid platforms,
+			 * because not all CPUs of a hybrid machine support it.
+			 * The global x86_pmu.intel_cap, which only contains the
+			 * common capabilities, is used to check the availability
+			 * of the feature. The per-PMU pebs_output_pt_available
+			 * in a hybrid machine should be ignored.
+			 */
+			if (x86_pmu.intel_cap.pebs_output_pt_available) {
 				pr_cont("PEBS-via-PT, ");
 				x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
 			}