[tip:perf/core] perf/x86/rapl: Use new MSR detection interface
From: tip-bot for Jiri Olsa
Date: Tue Jun 25 2019 - 04:40:39 EST
Commit-ID: 5fb5273a905ca4cba7aae16e61c26127cadbac5c
Gitweb: https://git.kernel.org/tip/5fb5273a905ca4cba7aae16e61c26127cadbac5c
Author: Jiri Olsa <jolsa@xxxxxxxxxx>
AuthorDate: Sun, 16 Jun 2019 16:03:54 +0200
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Mon, 24 Jun 2019 19:28:33 +0200
perf/x86/rapl: Use new MSR detection interface
Using perf_msr_probe function to probe for RAPL MSRs.
Adding new rapl_model_match device table, that
gathers events info for given model, following
the MSR and cstate module design.
It will replace the current rapl_cpu_match device
table and detection code in following patches.
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Kan <kan.liang@xxxxxxxxxxxxxxx>
Cc: Liang
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Vince Weaver <vincent.weaver@xxxxxxxxx>
Link: https://lkml.kernel.org/r/20190616140358.27799-5-jolsa@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
arch/x86/events/intel/rapl.c | 192 ++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 191 insertions(+), 1 deletion(-)
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 798135419a62..fa6d8065db15 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -58,6 +58,7 @@
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
+#include "../probe.h"
MODULE_LICENSE("GPL");
@@ -76,6 +77,17 @@ MODULE_LICENSE("GPL");
#define INTEL_RAPL_PSYS 0x5 /* pseudo-encoding */
#define NR_RAPL_DOMAINS 0x5
+
+enum perf_rapl_events {
+ PERF_RAPL_PP0 = 0, /* all cores */
+ PERF_RAPL_PKG, /* entire package */
+ PERF_RAPL_RAM, /* DRAM */
+ PERF_RAPL_PP1, /* gpu */
+ PERF_RAPL_PSYS, /* psys */
+
+ PERF_RAPL_MAX,
+};
+
static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
"pp0-core",
"package",
@@ -153,6 +165,11 @@ struct rapl_pmus {
struct rapl_pmu *pmus[];
};
+struct rapl_model {
+ unsigned long events;
+ bool apply_quirk;
+};
+
/* 1/2^hw_unit Joule */
static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
static struct rapl_pmus *rapl_pmus;
@@ -538,9 +555,18 @@ static struct attribute *rapl_events_knl_attr[] = {
NULL,
};
+/*
+ * There are no default events, but we need to create
+ * "events" group (with empty attrs) before updating
+ * it with detected events.
+ */
+static struct attribute *attrs_empty[] = {
+ NULL,
+};
+
static struct attribute_group rapl_pmu_events_group = {
.name = "events",
- .attrs = NULL, /* patched at runtime */
+ .attrs = attrs_empty,
};
DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
@@ -561,6 +587,79 @@ static const struct attribute_group *rapl_attr_groups[] = {
NULL,
};
+static struct attribute *rapl_events_cores[] = {
+ EVENT_PTR(rapl_cores),
+ EVENT_PTR(rapl_cores_unit),
+ EVENT_PTR(rapl_cores_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_cores_group = {
+ .name = "events",
+ .attrs = rapl_events_cores,
+};
+
+static struct attribute *rapl_events_pkg[] = {
+ EVENT_PTR(rapl_pkg),
+ EVENT_PTR(rapl_pkg_unit),
+ EVENT_PTR(rapl_pkg_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_pkg_group = {
+ .name = "events",
+ .attrs = rapl_events_pkg,
+};
+
+static struct attribute *rapl_events_ram[] = {
+ EVENT_PTR(rapl_ram),
+ EVENT_PTR(rapl_ram_unit),
+ EVENT_PTR(rapl_ram_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_ram_group = {
+ .name = "events",
+ .attrs = rapl_events_ram,
+};
+
+static struct attribute *rapl_events_gpu[] = {
+ EVENT_PTR(rapl_gpu),
+ EVENT_PTR(rapl_gpu_unit),
+ EVENT_PTR(rapl_gpu_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_gpu_group = {
+ .name = "events",
+ .attrs = rapl_events_gpu,
+};
+
+static struct attribute *rapl_events_psys[] = {
+ EVENT_PTR(rapl_psys),
+ EVENT_PTR(rapl_psys_unit),
+ EVENT_PTR(rapl_psys_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_psys_group = {
+ .name = "events",
+ .attrs = rapl_events_psys,
+};
+
+static bool test_msr(int idx, void *data)
+{
+ return test_bit(idx, (unsigned long *) data);
+}
+
+static struct perf_msr rapl_msrs[] = {
+ [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr },
+ [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr },
+ [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr },
+ [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr },
+ [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr },
+};
+
static int rapl_cpu_offline(unsigned int cpu)
{
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
@@ -674,6 +773,15 @@ static void cleanup_rapl_pmus(void)
kfree(rapl_pmus);
}
+const struct attribute_group *rapl_attr_update[] = {
+ &rapl_events_cores_group,
+ &rapl_events_pkg_group,
+ &rapl_events_ram_group,
+ &rapl_events_gpu_group,
+ &rapl_events_gpu_group,
+ NULL,
+};
+
static int __init init_rapl_pmus(void)
{
int maxdie = topology_max_packages() * topology_max_die_per_package();
@@ -686,6 +794,7 @@ static int __init init_rapl_pmus(void)
rapl_pmus->maxdie = maxdie;
rapl_pmus->pmu.attr_groups = rapl_attr_groups;
+ rapl_pmus->pmu.attr_update = rapl_attr_update;
rapl_pmus->pmu.task_ctx_nr = perf_invalid_context;
rapl_pmus->pmu.event_init = rapl_pmu_event_init;
rapl_pmus->pmu.add = rapl_pmu_event_add;
@@ -784,13 +893,94 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
MODULE_DEVICE_TABLE(x86cpu, rapl_cpu_match);
+static struct rapl_model model_snb = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_PP1),
+ .apply_quirk = false,
+};
+
+static struct rapl_model model_snbep = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = false,
+};
+
+static struct rapl_model model_hsw = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM) |
+ BIT(PERF_RAPL_PP1),
+ .apply_quirk = false,
+};
+
+static struct rapl_model model_hsx = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = true,
+};
+
+static struct rapl_model model_knl = {
+ .events = BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = true,
+};
+
+static struct rapl_model model_skl = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM) |
+ BIT(PERF_RAPL_PP1) |
+ BIT(PERF_RAPL_PSYS),
+ .apply_quirk = false,
+};
+
+static const struct x86_cpu_id rapl_model_match[] __initconst = {
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, model_snb),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, model_snbep),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, model_snb),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, model_snbep),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, model_knl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, model_knl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, model_skl),
+ {},
+};
+
static int __init rapl_pmu_init(void)
{
const struct x86_cpu_id *id;
struct intel_rapl_init_fun *rapl_init;
+ struct rapl_model *rm;
bool apply_quirk;
int ret;
+ id = x86_match_cpu(rapl_model_match);
+ if (!id)
+ return -ENODEV;
+
+ rm = (struct rapl_model *) id->driver_data;
+ perf_msr_probe(rapl_msrs, PERF_RAPL_MAX, false, (void *) &rm->events);
+
id = x86_match_cpu(rapl_cpu_match);
if (!id)
return -ENODEV;