1 files changed, 108 insertions, 9 deletions

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 49c26ce2b115..e8b6af199c73 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -21,6 +21,7 @@
 #define NUM_COUNTERS_NB		4
 #define NUM_COUNTERS_L2		4
 #define NUM_COUNTERS_L3		6
+#define NUM_COUNTERS_MAX	64
 
 #define RDPMC_BASE_NB		6
 #define RDPMC_BASE_LLC		10
@@ -38,7 +39,10 @@ struct amd_uncore_ctx {
 	int refcnt;
 	int cpu;
 	struct perf_event **events;
-	struct hlist_node node;
+	unsigned long active_mask[BITS_TO_LONGS(NUM_COUNTERS_MAX)];
+	int nr_active;
+	struct hrtimer hrtimer;
+	u64 hrtimer_duration;
 };
 
 struct amd_uncore_pmu {
@@ -83,11 +87,51 @@ struct amd_uncore {
 
 static struct amd_uncore uncores[UNCORE_TYPE_MAX];
 
+/* Interval for hrtimer, defaults to 60000 milliseconds */
+static unsigned int update_interval = 60 * MSEC_PER_SEC;
+module_param(update_interval, uint, 0444);
+
 static struct amd_uncore_pmu *event_to_amd_uncore_pmu(struct perf_event *event)
 {
 	return container_of(event->pmu, struct amd_uncore_pmu, pmu);
 }
 
+static enum hrtimer_restart amd_uncore_hrtimer(struct hrtimer *hrtimer)
+{
+	struct amd_uncore_ctx *ctx;
+	struct perf_event *event;
+	int bit;
+
+	ctx = container_of(hrtimer, struct amd_uncore_ctx, hrtimer);
+
+	if (!ctx->nr_active || ctx->cpu != smp_processor_id())
+		return HRTIMER_NORESTART;
+
+	for_each_set_bit(bit, ctx->active_mask, NUM_COUNTERS_MAX) {
+		event = ctx->events[bit];
+		event->pmu->read(event);
+	}
+
+	hrtimer_forward_now(hrtimer, ns_to_ktime(ctx->hrtimer_duration));
+	return HRTIMER_RESTART;
+}
+
+static void amd_uncore_start_hrtimer(struct amd_uncore_ctx *ctx)
+{
+	hrtimer_start(&ctx->hrtimer, ns_to_ktime(ctx->hrtimer_duration),
+		      HRTIMER_MODE_REL_PINNED_HARD);
+}
+
+static void amd_uncore_cancel_hrtimer(struct amd_uncore_ctx *ctx)
+{
+	hrtimer_cancel(&ctx->hrtimer);
+}
+
+static void amd_uncore_init_hrtimer(struct amd_uncore_ctx *ctx)
+{
+	hrtimer_setup(&ctx->hrtimer, amd_uncore_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
+}
+
 static void amd_uncore_read(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -106,9 +150,9 @@ static void amd_uncore_read(struct perf_event *event)
 	 * read counts directly from the corresponding PERF_CTR.
 	 */
 	if (hwc->event_base_rdpmc < 0)
-		rdmsrl(hwc->event_base, new);
+		rdmsrq(hwc->event_base, new);
 	else
-		rdpmcl(hwc->event_base_rdpmc, new);
+		new = rdpmc(hwc->event_base_rdpmc);
 
 	local64_set(&hwc->prev_count, new);
 	delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
@@ -118,27 +162,40 @@ static void amd_uncore_read(struct perf_event *event)
 
 static void amd_uncore_start(struct perf_event *event, int flags)
 {
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!ctx->nr_active++)
+		amd_uncore_start_hrtimer(ctx);
+
 	if (flags & PERF_EF_RELOAD)
-		wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
+		wrmsrq(hwc->event_base, (u64)local64_read(&hwc->prev_count));
 
 	hwc->state = 0;
-	wrmsrl(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE));
+	__set_bit(hwc->idx, ctx->active_mask);
+	wrmsrq(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE));
 	perf_event_update_userpage(event);
 }
 
 static void amd_uncore_stop(struct perf_event *event, int flags)
 {
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base, hwc->config);
+	wrmsrq(hwc->config_base, hwc->config);
 	hwc->state |= PERF_HES_STOPPED;
 
 	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
 		event->pmu->read(event);
 		hwc->state |= PERF_HES_UPTODATE;
 	}
+
+	if (!--ctx->nr_active)
+		amd_uncore_cancel_hrtimer(ctx);
+
+	__clear_bit(hwc->idx, ctx->active_mask);
 }
 
 static int amd_uncore_add(struct perf_event *event, int flags)
@@ -491,6 +548,9 @@ static int amd_uncore_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 				goto fail;
 			}
 
+			amd_uncore_init_hrtimer(curr);
+			curr->hrtimer_duration = (u64)update_interval * NSEC_PER_MSEC;
+
 			cpumask_set_cpu(cpu, &pmu->active_mask);
 		}
 
@@ -880,16 +940,55 @@ static int amd_uncore_umc_event_init(struct perf_event *event)
 
 static void amd_uncore_umc_start(struct perf_event *event, int flags)
 {
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!ctx->nr_active++)
+		amd_uncore_start_hrtimer(ctx);
+
 	if (flags & PERF_EF_RELOAD)
-		wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
+		wrmsrq(hwc->event_base, (u64)local64_read(&hwc->prev_count));
 
 	hwc->state = 0;
-	wrmsrl(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC));
+	__set_bit(hwc->idx, ctx->active_mask);
+	wrmsrq(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC));
 	perf_event_update_userpage(event);
 }
 
+static void amd_uncore_umc_read(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 prev, new, shift;
+	s64 delta;
+
+	shift = COUNTER_SHIFT + 1;
+	prev = local64_read(&hwc->prev_count);
+
+	/*
+	 * UMC counters do not have RDPMC assignments. Read counts directly
+	 * from the corresponding PERF_CTR.
+	 */
+	rdmsrl(hwc->event_base, new);
+
+	/*
+	 * Unlike the other uncore counters, UMC counters saturate and set the
+	 * Overflow bit (bit 48) on overflow. Since they do not roll over,
+	 * proactively reset the corresponding PERF_CTR when bit 47 is set so
+	 * that the counter never gets a chance to saturate.
+	 */
+	if (new & BIT_ULL(63 - COUNTER_SHIFT)) {
+		wrmsrl(hwc->event_base, 0);
+		local64_set(&hwc->prev_count, 0);
+	} else {
+		local64_set(&hwc->prev_count, new);
+	}
+
+	delta = (new << shift) - (prev << shift);
+	delta >>= shift;
+	local64_add(delta, &event->count);
+}
+
 static
 void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 {
@@ -968,7 +1067,7 @@ int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 				.del		= amd_uncore_del,
 				.start		= amd_uncore_umc_start,
 				.stop		= amd_uncore_stop,
-				.read		= amd_uncore_read,
+				.read		= amd_uncore_umc_read,
 				.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
 				.module		= THIS_MODULE,
 			};