x86/perf/core: Add pebs_capable to store valid PEBS_COUNTER_MASK value

The value of pebs_counter_mask will be accessed frequently
for repeated use in the intel_guest_get_msrs(). So it can be
optimized instead of endlessly mucking about with branches.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Message-Id: <20220411101946.20262-7-likexu@tencent.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

arch/x86/events/intel/core.c

@@ -2932,10 +2932,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	 * counters from the GLOBAL_STATUS mask and we always process PEBS
 	 * events via drain_pebs().
 	 */
-	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
-		status &= ~cpuc->pebs_enabled;
-	else
-		status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+	status &= ~(cpuc->pebs_enabled & x86_pmu.pebs_capable);
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
@@ -3981,10 +3978,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
 	arr[0].host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
 	arr[0].guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask;
-	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
-		arr[0].guest &= ~cpuc->pebs_enabled;
-	else
-		arr[0].guest &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+	arr[0].guest &= ~(cpuc->pebs_enabled & x86_pmu.pebs_capable);
 	*nr = 1;
 
 	if (x86_pmu.pebs && x86_pmu.pebs_no_isolation) {
@@ -5692,6 +5686,7 @@ __init int intel_pmu_init(void)
 	x86_pmu.events_mask_len		= eax.split.mask_length;
 
 	x86_pmu.max_pebs_events		= min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
+	x86_pmu.pebs_capable		= PEBS_COUNTER_MASK;
 
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
@@ -5876,6 +5871,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_aliases = NULL;
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.pebs_capable = ~0ULL;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.get_event_constraints = glp_get_event_constraints;
@@ -6233,6 +6229,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_aliases = NULL;
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.pebs_block = true;
+		x86_pmu.pebs_capable = ~0ULL;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
 		x86_pmu.flags |= PMU_FL_PEBS_ALL;
@@ -6278,6 +6275,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_aliases = NULL;
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.pebs_block = true;
+		x86_pmu.pebs_capable = ~0ULL;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
 		x86_pmu.flags |= PMU_FL_PEBS_ALL;

arch/x86/events/perf_event.h

@@ -828,6 +828,7 @@ struct x86_pmu {
 	void		(*pebs_aliases)(struct perf_event *event);
 	unsigned long	large_pebs_flags;
 	u64		rtm_abort_event;
+	u64		pebs_capable;
 
 	/*
 	 * Intel LBR