[tip:perf/core] perf/x86: Add an MSR PMU driver

[tip-bot for Andy Lutomirski]

Commit-ID:  b7b7c7821d932ba18ef6c8eafc8536066b4c2ef4
Gitweb:     http://git.kernel.org/tip/b7b7c7821d932ba18ef6c8eafc8536066b4c2ef4
Author:     Andy Lutomirski <luto@xxxxxxxxxx>
AuthorDate: Mon, 20 Jul 2015 11:49:06 -0400
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Tue, 4 Aug 2015 10:17:00 +0200

perf/x86: Add an MSR PMU driver

This patch adds an MSR PMU to support free running MSR counters. Such
as time and freq related counters includes TSC, IA32_APERF, IA32_MPERF
and IA32_PPERF, but also SMI_COUNT.

The events are exposed in sysfs for use by perf stat and other tools.
The files are under /sys/devices/msr/events/

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxx>
[ s/freq/msr/, added SMI_COUNT, fixed bugs. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: acme@xxxxxxxxxx
Cc: adrian.hunter@xxxxxxxxx
Cc: dsahern@xxxxxxxxx
Cc: eranian@xxxxxxxxxx
Cc: jolsa@xxxxxxxxxx
Cc: mark.rutland@xxxxxxx
Cc: namhyung@xxxxxxxxxx
Link: http://lkml.kernel.org/r/1437407346-31186-1-git-send-email-kan.liang@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/kernel/cpu/Makefile         |   2 +
 arch/x86/kernel/cpu/perf_event_msr.c | 242 +++++++++++++++++++++++++++++++++++
 2 files changed, 244 insertions(+)

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 9bff687..4eb065c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -46,6 +46,8 @@ obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= perf_event_intel_uncore.o \
 					   perf_event_intel_uncore_snb.o \
 					   perf_event_intel_uncore_snbep.o \
 					   perf_event_intel_uncore_nhmex.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_msr.o
+obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_msr.o
 endif
 
 
diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/kernel/cpu/perf_event_msr.c
new file mode 100644
index 0000000..af216e9
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_msr.c
@@ -0,0 +1,242 @@
+#include <linux/perf_event.h>
+
+enum perf_msr_id {
+	PERF_MSR_TSC			= 0,
+	PERF_MSR_APERF			= 1,
+	PERF_MSR_MPERF			= 2,
+	PERF_MSR_PPERF			= 3,
+	PERF_MSR_SMI			= 4,
+
+	PERF_MSR_EVENT_MAX,
+};
+
+struct perf_msr {
+	int	id;
+	u64	msr;
+};
+
+static struct perf_msr msr[] = {
+	{ PERF_MSR_TSC, 0 },
+	{ PERF_MSR_APERF, MSR_IA32_APERF },
+	{ PERF_MSR_MPERF, MSR_IA32_MPERF },
+	{ PERF_MSR_PPERF, MSR_PPERF },
+	{ PERF_MSR_SMI, MSR_SMI_COUNT },
+};
+
+PMU_EVENT_ATTR_STRING(tsc,   evattr_tsc,   "event=0x00");
+PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01");
+PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02");
+PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03");
+PMU_EVENT_ATTR_STRING(smi,   evattr_smi,   "event=0x04");
+
+static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = {
+	&evattr_tsc.attr.attr,
+};
+
+static struct attribute_group events_attr_group = {
+	.name = "events",
+	.attrs = events_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-63");
+static struct attribute *format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+static struct attribute_group format_attr_group = {
+	.name = "format",
+	.attrs = format_attrs,
+};
+
+static const struct attribute_group *attr_groups[] = {
+	&events_attr_group,
+	&format_attr_group,
+	NULL,
+};
+
+static int msr_event_init(struct perf_event *event)
+{
+	u64 cfg = event->attr.config;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (cfg >= PERF_MSR_EVENT_MAX)
+		return -EINVAL;
+
+	/* unsupported modes and filters */
+	if (event->attr.exclude_user   ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv     ||
+	    event->attr.exclude_idle   ||
+	    event->attr.exclude_host   ||
+	    event->attr.exclude_guest  ||
+	    event->attr.sample_period) /* no sampling */
+		return -EINVAL;
+
+	event->hw.idx = -1;
+	event->hw.event_base = msr[cfg].msr;
+	event->hw.config = cfg;
+
+	return 0;
+}
+
+static inline u64 msr_read_counter(struct perf_event *event)
+{
+	u64 now;
+
+	if (event->hw.event_base)
+		rdmsrl(event->hw.event_base, now);
+	else
+		now = rdtsc();
+
+	return now;
+}
+static void msr_event_update(struct perf_event *event)
+{
+	u64 prev, now;
+	s64 delta;
+
+	/* Careful, an NMI might modify the previous event value. */
+again:
+	prev = local64_read(&event->hw.prev_count);
+	now = msr_read_counter(event);
+
+	if (local64_cmpxchg(&event->hw.prev_count, prev, now) != prev)
+		goto again;
+
+	delta = now - prev;
+	if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) {
+		delta <<= 32;
+		delta >>= 32; /* sign extend */
+	}
+	local64_add(now - prev, &event->count);
+}
+
+static void msr_event_start(struct perf_event *event, int flags)
+{
+	u64 now;
+
+	now = msr_read_counter(event);
+	local64_set(&event->hw.prev_count, now);
+}
+
+static void msr_event_stop(struct perf_event *event, int flags)
+{
+	msr_event_update(event);
+}
+
+static void msr_event_del(struct perf_event *event, int flags)
+{
+	msr_event_stop(event, PERF_EF_UPDATE);
+}
+
+static int msr_event_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		msr_event_start(event, flags);
+
+	return 0;
+}
+
+static struct pmu pmu_msr = {
+	.task_ctx_nr	= perf_sw_context,
+	.attr_groups	= attr_groups,
+	.event_init	= msr_event_init,
+	.add		= msr_event_add,
+	.del		= msr_event_del,
+	.start		= msr_event_start,
+	.stop		= msr_event_stop,
+	.read		= msr_event_update,
+	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+};
+
+static int __init intel_msr_init(int idx)
+{
+	if (boot_cpu_data.x86 != 6)
+		return 0;
+
+	switch (boot_cpu_data.x86_model) {
+	case 30: /* 45nm Nehalem    */
+	case 26: /* 45nm Nehalem-EP */
+	case 46: /* 45nm Nehalem-EX */
+
+	case 37: /* 32nm Westmere    */
+	case 44: /* 32nm Westmere-EP */
+	case 47: /* 32nm Westmere-EX */
+
+	case 42: /* 32nm SandyBridge         */
+	case 45: /* 32nm SandyBridge-E/EN/EP */
+
+	case 58: /* 22nm IvyBridge       */
+	case 62: /* 22nm IvyBridge-EP/EX */
+
+	case 60: /* 22nm Haswell Core */
+	case 63: /* 22nm Haswell Server */
+	case 69: /* 22nm Haswell ULT */
+	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
+
+	case 61: /* 14nm Broadwell Core-M */
+	case 86: /* 14nm Broadwell Xeon D */
+	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
+	case 79: /* 14nm Broadwell Server */
+		events_attrs[idx++] = &evattr_smi.attr.attr;
+		break;
+
+	case 78: /* 14nm Skylake Mobile */
+	case 94: /* 14nm Skylake Desktop */
+		events_attrs[idx++] = &evattr_pperf.attr.attr;
+		events_attrs[idx++] = &evattr_smi.attr.attr;
+		break;
+
+	case 55: /* 22nm Atom "Silvermont"                */
+	case 76: /* 14nm Atom "Airmont"                   */
+	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
+		events_attrs[idx++] = &evattr_smi.attr.attr;
+		break;
+	}
+
+	events_attrs[idx] = NULL;
+
+	return 0;
+}
+
+static int __init amd_msr_init(int idx)
+{
+	return 0;
+}
+
+static int __init msr_init(void)
+{
+	int err;
+	int idx = 1;
+
+	if (boot_cpu_has(X86_FEATURE_APERFMPERF)) {
+		events_attrs[idx++] = &evattr_aperf.attr.attr;
+		events_attrs[idx++] = &evattr_mperf.attr.attr;
+		events_attrs[idx] = NULL;
+	}
+
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_INTEL:
+		err = intel_msr_init(idx);
+		break;
+
+	case X86_VENDOR_AMD:
+		err = amd_msr_init(idx);
+		break;
+
+	default:
+		err = -ENOTSUPP;
+	}
+
+	if (err != 0) {
+		pr_cont("no msr PMU driver.\n");
+		return 0;
+	}
+
+	perf_pmu_register(&pmu_msr, "msr", -1);
+
+	return 0;
+}
+device_initcall(msr_init);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/