From: kan.liang@linux.intel.com
To: peterz@infradead.org, mingo@kernel.org, acme@kernel.org,
namhyung@kernel.org, irogers@google.com, adrian.hunter@intel.com,
alexander.shishkin@linux.intel.com, linux-kernel@vger.kernel.org
Cc: ak@linux.intel.com, eranian@google.com,
Kan Liang <kan.liang@linux.intel.com>
Subject: [PATCH V3 03/13] perf/x86: Add Lunar Lake and Arrow Lake support
Date: Wed, 26 Jun 2024 07:35:35 -0700 [thread overview]
Message-ID: <20240626143545.480761-4-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20240626143545.480761-1-kan.liang@linux.intel.com>
From: Kan Liang <kan.liang@linux.intel.com>
From PMU's perspective, Lunar Lake and Arrow Lake are similar to the
previous generation Meteor Lake. Both are hybrid platforms, with e-core
and p-core.
The key differences include:
- The e-core supports 3 new fixed counters
- The p-core supports an updated PEBS Data Source format
- More GP counters (Updated event constraint table)
- New Architectural performance monitoring V6
(New Perfmon MSRs aliasing, umask2, eq).
- New PEBS format V6 (Counters Snapshotting group)
- New RDPMC metrics clear mode
The legacy features, the 3 new fixed counters and updated event
constraint table are enabled in this patch.
The new PEBS data source format, the architectural performance
monitoring V6, the PEBS format V6, and the new RDPMC metrics clear mode
are supported in the following patches.
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
arch/x86/events/intel/core.c | 117 ++++++++++++++++++++++++++++++
arch/x86/events/intel/ds.c | 24 ++++++
arch/x86/events/perf_event.h | 2 +
arch/x86/include/asm/perf_event.h | 4 +
4 files changed, 147 insertions(+)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index aaf3884073ba..73dbbbdcc421 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -220,6 +220,17 @@ static struct event_constraint intel_grt_event_constraints[] __read_mostly = {
EVENT_CONSTRAINT_END
};
+static struct event_constraint intel_skt_event_constraints[] __read_mostly = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */
+ FIXED_EVENT_CONSTRAINT(0x0073, 4), /* TOPDOWN_BAD_SPECULATION.ALL */
+ FIXED_EVENT_CONSTRAINT(0x019c, 5), /* TOPDOWN_FE_BOUND.ALL */
+ FIXED_EVENT_CONSTRAINT(0x02c2, 6), /* TOPDOWN_RETIRING.ALL */
+ EVENT_CONSTRAINT_END
+};
+
static struct event_constraint intel_skl_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -370,6 +381,55 @@ static struct extra_reg intel_rwc_extra_regs[] __read_mostly = {
EVENT_EXTRA_END
};
+static struct event_constraint intel_lnc_event_constraints[] = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x0100, 0), /* INST_RETIRED.PREC_DIST */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */
+ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FE_BOUND, 2),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BE_BOUND, 3),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_HEAVY_OPS, 4),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BR_MISPREDICT, 5),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
+
+ INTEL_UEVENT_CONSTRAINT(0x0148, 0x4),
+ INTEL_UEVENT_CONSTRAINT(0x0175, 0x4),
+
+ INTEL_EVENT_CONSTRAINT(0x2e, 0x3ff),
+ INTEL_EVENT_CONSTRAINT(0x3c, 0x3ff),
+ /*
+ * Generally event codes < 0x90 are restricted to counters 0-3.
+ * The 0x2E and 0x3C are exception, which has no restriction.
+ */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf),
+
+ INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
+ INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
+ INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
+ INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
+ INTEL_UEVENT_CONSTRAINT(0x10a4, 0x1),
+ INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8),
+ INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3),
+ INTEL_EVENT_CONSTRAINT(0xce, 0x1),
+
+ INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf),
+ /*
+ * Generally event codes >= 0x90 are likely to have no restrictions.
+ * The exception are defined as above.
+ */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0x3ff),
+
+ EVENT_CONSTRAINT_END
+};
+
+
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
@@ -5790,6 +5850,23 @@ static struct attribute *adl_hybrid_events_attrs[] = {
NULL,
};
+EVENT_ATTR_STR_HYBRID(topdown-retiring, td_retiring_lnl, "event=0xc2,umask=0x02;event=0x00,umask=0x80", hybrid_big_small);
+EVENT_ATTR_STR_HYBRID(topdown-fe-bound, td_fe_bound_lnl, "event=0x9c,umask=0x01;event=0x00,umask=0x82", hybrid_big_small);
+EVENT_ATTR_STR_HYBRID(topdown-be-bound, td_be_bound_lnl, "event=0xa4,umask=0x02;event=0x00,umask=0x83", hybrid_big_small);
+
+static struct attribute *lnl_hybrid_events_attrs[] = {
+ EVENT_PTR(slots_adl),
+ EVENT_PTR(td_retiring_lnl),
+ EVENT_PTR(td_bad_spec_adl),
+ EVENT_PTR(td_fe_bound_lnl),
+ EVENT_PTR(td_be_bound_lnl),
+ EVENT_PTR(td_heavy_ops_adl),
+ EVENT_PTR(td_br_mis_adl),
+ EVENT_PTR(td_fetch_lat_adl),
+ EVENT_PTR(td_mem_bound_adl),
+ NULL
+};
+
/* Must be in IDX order */
EVENT_ATTR_STR_HYBRID(mem-loads, mem_ld_adl, "event=0xd0,umask=0x5,ldlat=3;event=0xcd,umask=0x1,ldlat=3", hybrid_big_small);
EVENT_ATTR_STR_HYBRID(mem-stores, mem_st_adl, "event=0xd0,umask=0x6;event=0xcd,umask=0x2", hybrid_big_small);
@@ -6139,6 +6216,21 @@ static __always_inline void intel_pmu_init_grt(struct pmu *pmu)
intel_pmu_ref_cycles_ext();
}
+static __always_inline void intel_pmu_init_lnc(struct pmu *pmu)
+{
+ intel_pmu_init_glc(pmu);
+ hybrid(pmu, event_constraints) = intel_lnc_event_constraints;
+ hybrid(pmu, pebs_constraints) = intel_lnc_pebs_event_constraints;
+ hybrid(pmu, extra_regs) = intel_rwc_extra_regs;
+}
+
+static __always_inline void intel_pmu_init_skt(struct pmu *pmu)
+{
+ intel_pmu_init_grt(pmu);
+ hybrid(pmu, event_constraints) = intel_skt_event_constraints;
+ hybrid(pmu, extra_regs) = intel_cmt_extra_regs;
+}
+
__init int intel_pmu_init(void)
{
struct attribute **extra_skl_attr = &empty_attrs;
@@ -6864,6 +6956,31 @@ __init int intel_pmu_init(void)
name = "meteorlake_hybrid";
break;
+ case INTEL_LUNARLAKE_M:
+ case INTEL_ARROWLAKE:
+ intel_pmu_init_hybrid(hybrid_big_small);
+
+ x86_pmu.get_event_constraints = mtl_get_event_constraints;
+ x86_pmu.hw_config = adl_hw_config;
+
+ td_attr = lnl_hybrid_events_attrs;
+ mem_attr = mtl_hybrid_mem_attrs;
+ tsx_attr = adl_hybrid_tsx_attrs;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;
+
+ /* Initialize big core specific PerfMon capabilities.*/
+ pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
+ intel_pmu_init_lnc(&pmu->pmu);
+
+ /* Initialize Atom core specific PerfMon capabilities.*/
+ pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
+ intel_pmu_init_skt(&pmu->pmu);
+
+ pr_cont("Lunarlake Hybrid events, ");
+ name = "lunarlake_hybrid";
+ break;
+
default:
switch (x86_pmu.version) {
case 1:
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 6f834a7d852a..79e23dec6714 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1086,6 +1086,30 @@ struct event_constraint intel_glc_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_lnc_pebs_event_constraints[] = {
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
+
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf),
+
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf),
+
+ /*
+ * Everything else is handled by PMU_FL_PEBS_ALL, because we
+ * need the full constraints from the main table.
+ */
+
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
struct event_constraint *pebs_constraints = hybrid(event->pmu, pebs_constraints);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index b3214d6e8f4c..3c781dabce76 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1582,6 +1582,8 @@ extern struct event_constraint intel_icl_pebs_event_constraints[];
extern struct event_constraint intel_glc_pebs_event_constraints[];
+extern struct event_constraint intel_lnc_pebs_event_constraints[];
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_add(struct perf_event *event);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 7f1e17250546..400c909b8658 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -307,6 +307,10 @@ struct x86_pmu_capability {
#define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3)
#define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS)
+/* TOPDOWN_BAD_SPECULATION.ALL: fixed counter 4 (Atom only) */
+/* TOPDOWN_FE_BOUND.ALL: fixed counter 5 (Atom only) */
+/* TOPDOWN_RETIRING.ALL: fixed counter 6 (Atom only) */
+
static inline bool use_fixed_pseudo_encoding(u64 code)
{
return !(code & 0xff);
--
2.38.1
next prev parent reply other threads:[~2024-06-26 14:35 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-26 14:35 [PATCH V3 00/13] Support Lunar Lake and Arrow Lake core PMU kan.liang
2024-06-26 14:35 ` [PATCH V3 01/13] perf/x86/intel: Support the PEBS event mask kan.liang
2024-06-28 8:42 ` Peter Zijlstra
2024-07-05 21:06 ` [tip: perf/core] " tip-bot2 for Kan Liang
2024-06-26 14:35 ` [PATCH V3 02/13] perf/x86: Support counter mask kan.liang
2024-07-05 21:06 ` [tip: perf/core] " tip-bot2 for Kan Liang
2024-06-26 14:35 ` kan.liang [this message]
2024-07-05 21:06 ` [tip: perf/core] perf/x86: Add Lunar Lake and Arrow Lake support tip-bot2 for Kan Liang
2024-06-26 14:35 ` [PATCH V3 04/13] perf/x86/intel: Rename model-specific pebs_latency_data functions kan.liang
2024-07-05 21:06 ` [tip: perf/core] " tip-bot2 for Kan Liang
2024-06-26 14:35 ` [PATCH V3 05/13] perf/x86/intel: Support new data source for Lunar Lake kan.liang
2024-07-05 21:06 ` [tip: perf/core] " tip-bot2 for Kan Liang
2024-06-26 14:35 ` [PATCH V3 06/13] perf/x86: Add config_mask to represent EVENTSEL bitmask kan.liang
2024-07-05 21:06 ` [tip: perf/core] " tip-bot2 for Kan Liang
2024-06-26 14:35 ` [PATCH V3 07/13] perf/x86/intel: Support PERFEVTSEL extension kan.liang
2024-07-05 21:06 ` [tip: perf/core] " tip-bot2 for Kan Liang
2024-06-26 14:35 ` [PATCH V3 08/13] perf/x86/intel: Support Perfmon MSRs aliasing kan.liang
2024-07-05 21:06 ` [tip: perf/core] " tip-bot2 for Kan Liang
2024-06-26 14:35 ` [PATCH V3 09/13] perf/x86: Extend event update interface kan.liang
2024-06-26 14:35 ` [PATCH V3 10/13] perf: Extend perf_output_read kan.liang
2024-06-26 14:35 ` [PATCH V3 11/13] perf/x86/intel: Move PEBS event update after the sample output kan.liang
2024-06-26 14:35 ` [PATCH V3 12/13] perf/x86/intel: Support PEBS counters snapshotting kan.liang
2024-06-26 14:35 ` [PATCH V3 13/13] perf/x86/intel: Support RDPMC metrics clear mode kan.liang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240626143545.480761-4-kan.liang@linux.intel.com \
--to=kan.liang@linux.intel.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=eranian@google.com \
--cc=irogers@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox