Date:   Fri, 19 May 2017 10:06:21 -0700
From:   kan.liang@...el.com
To:     peterz@...radead.org, mingo@...hat.com, eranian@...gle.com,
        linux-kernel@...r.kernel.org
Cc:     alexander.shishkin@...ux.intel.com, acme@...hat.com,
        jolsa@...hat.com, torvalds@...ux-foundation.org,
        tglx@...utronix.de, vincent.weaver@...ne.edu, ak@...ux.intel.com,
        Kan Liang <Kan.liang@...el.com>
Subject: [PATCH 1/2] perf/x86/intel: enable CPU ref_cycles for GP counter

From: Kan Liang <Kan.liang@...el.com>

The CPU ref_cycles can only be used by one user at the same time,
otherwise a "not counted" error will be displaced.
    [kan]$ sudo perf stat -x, -e ref-cycles,ref-cycles -- sleep 1
    1203264,,ref-cycles,513112,100.00,,,,
    <not counted>,,ref-cycles,0,0.00,,,,

CPU ref_cycles can only be counted by fixed counter 2. It uses
pseudo-encoding. The GP counter doesn't recognize.

BUS_CYCLES (0x013c) is another event which is not affected by core
frequency changes. It has a constant ratio with the CPU ref_cycles.
BUS_CYCLES could be used as an alternative event for ref_cycles on GP
counter.
A hook is implemented in x86_schedule_events. If the fixed counter 2 is
occupied and a GP counter is assigned, BUS_CYCLES is used to replace
ref_cycles. A new flag PERF_X86_EVENT_REF_CYCLES_REP in
hw_perf_event is introduced to indicate the replacement.
To make the switch transparent, counting and sampling are also specially
handled.
 - For counting, it multiplies the result with the constant ratio after
   reading it.
 - For sampling with fixed period, the BUS_CYCLES period = ref_cycles
   period / the constant ratio.
 - For sampling with fixed frequency, the adaptive frequency algorithm
   will figure it out on its own. Do nothing.

The constant ratio is model specific.
For the model after NEHALEM but before Skylake, the ratio is defined in
MSR_PLATFORM_INFO.
For the model after Skylake, it can be get from CPUID.15H.
For Knights Landing, Goldmont and later, the ratio is always 1.

The old Silvermont/Airmont, Core2 and Atom machines are not covered by
the patch. The behavior on those machines will not change.

Signed-off-by: Kan Liang <Kan.liang@...el.com>
---
 arch/x86/events/core.c       | 19 +++++++++
 arch/x86/events/intel/core.c | 93 ++++++++++++++++++++++++++++++++++++++++----
 arch/x86/events/perf_event.h |  3 ++
 3 files changed, 107 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 580b60f..e8b2326 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -101,6 +101,10 @@ u64 x86_perf_event_update(struct perf_event *event)
 	delta = (new_raw_count << shift) - (prev_raw_count << shift);
 	delta >>= shift;
 
+	/* Correct the count number if applying ref_cycles replacement */
+	if (!is_sampling_event(event) &&
+	    (hwc->flags & PERF_X86_EVENT_REF_CYCLES_REP))
+		delta *= x86_pmu.ref_cycles_factor;
 	local64_add(delta, &event->count);
 	local64_sub(delta, &hwc->period_left);
 
@@ -934,6 +938,21 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		for (i = 0; i < n; i++) {
 			e = cpuc->event_list[i];
 			e->hw.flags |= PERF_X86_EVENT_COMMITTED;
+
+			/*
+			 * 0x0300 is pseudo-encoding for REF_CPU_CYCLES.
+			 * It indicates that fixed counter 2 should be used.
+			 *
+			 * If fixed counter 2 is occupied and a GP counter
+			 * is assigned, an alternative event which can be
+			 * counted in GP counter will be used to replace
+			 * the pseudo-encoding REF_CPU_CYCLES event.
+			 */
+			if (((e->hw.config & X86_RAW_EVENT_MASK) == 0x0300) &&
+			    (assign[i] < INTEL_PMC_IDX_FIXED) &&
+			    x86_pmu.ref_cycles_rep)
+				x86_pmu.ref_cycles_rep(e);
+
 			if (x86_pmu.commit_scheduling)
 				x86_pmu.commit_scheduling(cpuc, i, assign[i]);
 		}
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a6d91d4..af5a464 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3063,6 +3063,55 @@ static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
 	return left;
 }
 
+static __init unsigned int glm_get_ref_cycles_factor(void)
+{
+	return 1;
+}
+
+static __init unsigned int nhm_get_ref_cycles_factor(void)
+{
+	u64 platform_info;
+
+	rdmsrl(MSR_PLATFORM_INFO, platform_info);
+	return (platform_info >> 8) & 0xff;
+}
+
+static __init unsigned int skl_get_ref_cycles_factor(void)
+{
+	unsigned int cpuid21_eax, cpuid21_ebx, cpuid21_ecx, unused;
+
+	cpuid(21, &cpuid21_eax, &cpuid21_ebx, &cpuid21_ecx, &unused);
+	if (!cpuid21_eax || !cpuid21_ebx)
+		return 0;
+
+	return cpuid21_ebx / cpuid21_eax;
+}
+
+/*
+ * BUS_CYCLES (0x013c) is another event which is not affected by core
+ * frequency changes. It has a constant ratio with the CPU ref_cycles.
+ * BUS_CYCLES could be used as an alternative event for ref_cycles on
+ * GP counter.
+ */
+void nhm_ref_cycles_rep(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	hwc->config = (hwc->config & ~X86_RAW_EVENT_MASK) |
+		      intel_perfmon_event_map[PERF_COUNT_HW_BUS_CYCLES];
+	hwc->flags |= PERF_X86_EVENT_REF_CYCLES_REP;
+
+	/* adjust the sample period for ref_cycles replacement event */
+	if (is_sampling_event(event) && hwc->sample_period != 1) {
+
+		hwc->sample_period /= x86_pmu.ref_cycles_factor;
+		if (hwc->sample_period < 2)
+			hwc->sample_period = 2;
+		hwc->last_period = hwc->sample_period;
+		local64_set(&hwc->period_left, hwc->sample_period);
+	}
+}
+
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -3712,7 +3761,9 @@ __init int intel_pmu_init(void)
 
 		intel_pmu_pebs_data_source_nhm();
 		x86_add_quirk(intel_nehalem_quirk);
-
+		x86_pmu.ref_cycles_factor = nhm_get_ref_cycles_factor();
+		if (x86_pmu.ref_cycles_factor)
+			x86_pmu.ref_cycles_rep = nhm_ref_cycles_rep;
 		pr_cont("Nehalem events, ");
 		break;
 
@@ -3772,6 +3823,9 @@ __init int intel_pmu_init(void)
 		x86_pmu.lbr_pt_coexist = true;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.cpu_events = glm_events_attrs;
+		x86_pmu.ref_cycles_factor = glm_get_ref_cycles_factor();
+		if (x86_pmu.ref_cycles_factor)
+			x86_pmu.ref_cycles_rep = nhm_ref_cycles_rep;
 		pr_cont("Goldmont events, ");
 		break;
 
@@ -3801,6 +3855,9 @@ __init int intel_pmu_init(void)
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
 		intel_pmu_pebs_data_source_nhm();
+		x86_pmu.ref_cycles_factor = nhm_get_ref_cycles_factor();
+		if (x86_pmu.ref_cycles_factor)
+			x86_pmu.ref_cycles_rep = nhm_ref_cycles_rep;
 		pr_cont("Westmere events, ");
 		break;
 
@@ -3836,6 +3893,9 @@ __init int intel_pmu_init(void)
 		/* UOPS_DISPATCHED.THREAD,c=1,i=1 to count stall cycles*/
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x01, .inv=1, .cmask=1);
+		x86_pmu.ref_cycles_factor = nhm_get_ref_cycles_factor();
+		if (x86_pmu.ref_cycles_factor)
+			x86_pmu.ref_cycles_rep = nhm_ref_cycles_rep;
 
 		pr_cont("SandyBridge events, ");
 		break;
@@ -3870,6 +3930,9 @@ __init int intel_pmu_init(void)
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
 			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
+		x86_pmu.ref_cycles_factor = nhm_get_ref_cycles_factor();
+		if (x86_pmu.ref_cycles_factor)
+			x86_pmu.ref_cycles_rep = nhm_ref_cycles_rep;
 
 		pr_cont("IvyBridge events, ");
 		break;
@@ -3899,6 +3962,9 @@ __init int intel_pmu_init(void)
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
 		x86_pmu.cpu_events = hsw_events_attrs;
 		x86_pmu.lbr_double_abort = true;
+		x86_pmu.ref_cycles_factor = nhm_get_ref_cycles_factor();
+		if (x86_pmu.ref_cycles_factor)
+			x86_pmu.ref_cycles_rep = nhm_ref_cycles_rep;
 		pr_cont("Haswell events, ");
 		break;
 
@@ -3935,6 +4001,9 @@ __init int intel_pmu_init(void)
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
 		x86_pmu.cpu_events = hsw_events_attrs;
 		x86_pmu.limit_period = bdw_limit_period;
+		x86_pmu.ref_cycles_factor = nhm_get_ref_cycles_factor();
+		if (x86_pmu.ref_cycles_factor)
+			x86_pmu.ref_cycles_rep = nhm_ref_cycles_rep;
 		pr_cont("Broadwell events, ");
 		break;
 
@@ -3953,6 +4022,9 @@ __init int intel_pmu_init(void)
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+		x86_pmu.ref_cycles_factor = glm_get_ref_cycles_factor();
+		if (x86_pmu.ref_cycles_factor)
+			x86_pmu.ref_cycles_rep = nhm_ref_cycles_rep;
 
 		pr_cont("Knights Landing/Mill events, ");
 		break;
@@ -3988,6 +4060,9 @@ __init int intel_pmu_init(void)
 						  skl_format_attr);
 		WARN_ON(!x86_pmu.format_attrs);
 		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.ref_cycles_factor = skl_get_ref_cycles_factor();
+		if (x86_pmu.ref_cycles_factor)
+			x86_pmu.ref_cycles_rep = nhm_ref_cycles_rep;
 		pr_cont("Skylake events, ");
 		break;
 
@@ -4024,15 +4099,17 @@ __init int intel_pmu_init(void)
 		((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
 
 	if (x86_pmu.event_constraints) {
-		/*
-		 * event on fixed counter2 (REF_CYCLES) only works on this
-		 * counter, so do not extend mask to generic counters
-		 */
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if (c->cmask == FIXED_EVENT_FLAGS
-			    && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+			if (c->cmask == FIXED_EVENT_FLAGS)
 				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
-			}
+			/*
+			 * event on fixed counter2 (REF_CYCLES) only works on
+			 * this counter on some old platforms, e.g. core2, Atom.
+			 * So do not extend mask to generic counters
+			 */
+			if ((c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) &&
+			    !x86_pmu.ref_cycles_rep)
+				c->idxmsk64 &= ~((1ULL << x86_pmu.num_counters) - 1);
 			c->idxmsk64 &=
 				~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
 			c->weight = hweight64(c->idxmsk64);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index be3d362..6497d0a 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -68,6 +68,7 @@ struct event_constraint {
 #define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
 #define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
 #define PERF_X86_EVENT_FREERUNNING	0x0800 /* use freerunning PEBS */
+#define PERF_X86_EVENT_REF_CYCLES_REP	0x1000 /* use ref_cycles replacement */
 
 
 struct amd_nb {
@@ -550,6 +551,8 @@ struct x86_pmu {
 	int		perfctr_second_write;
 	bool		late_ack;
 	unsigned	(*limit_period)(struct perf_event *event, unsigned l);
+	unsigned int	ref_cycles_factor;
+	void		(*ref_cycles_rep)(struct perf_event *event);
 
 	/*
 	 * sysfs attrs
-- 
2.7.4

Powered by blists - more mailing lists