Re: [PATCH v6 06/16] KVM: x86/pmu: Add IA32_PEBS_ENABLE MSR emulation for extended PEBS

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 2021/5/17 16:33, Peter Zijlstra wrote:
On Tue, May 11, 2021 at 10:42:04AM +0800, Like Xu wrote:
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2f89fd599842..c791765f4761 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3898,31 +3898,49 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
  	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
  	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
  	u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
+	u64 pebs_mask = (x86_pmu.flags & PMU_FL_PEBS_ALL) ?
+		cpuc->pebs_enabled : (cpuc->pebs_enabled & PEBS_COUNTER_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);
-	*nr = 1;
Instead of endlessly mucking about with branches, do we want something
like this instead?

Fine to me. How about the commit message for your below patch:

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: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>


---
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2521d03de5e0..bcfba11196c8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2819,10 +2819,7 @@ 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
@@ -3862,10 +3859,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
  	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) {
@@ -5546,6 +5540,7 @@ __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
@@ -5730,6 +5725,7 @@ __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;
@@ -6080,6 +6076,7 @@ __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;
@@ -6123,6 +6120,7 @@ __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;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 27fa85e7d4fd..6f3cf81ccb1b 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -805,6 +805,7 @@ struct x86_pmu {
  	void		(*pebs_aliases)(struct perf_event *event);
  	unsigned long	large_pebs_flags;
  	u64		rtm_abort_event;
+	u64		pebs_capable;
/*
  	 * Intel LBR




[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]

  Powered by Linux