From: Dapeng Mi <dapeng1.mi@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Kan Liang <kan.liang@linux.intel.com>
Cc: linux-kernel@vger.kernel.org, Andi Kleen <ak@linux.intel.com>,
Zhenyu Wang <zhenyuw@linux.intel.com>,
Yongwei Ma <yongwei.ma@intel.com>,
Pawan Gupta <pawan.kumar.gupta@linux.intel.com>,
Dapeng Mi <dapeng1.mi@intel.com>,
Dapeng Mi <dapeng1.mi@linux.intel.com>
Subject: [PATCH 4/4] perf/x86/intel: Add PMU support for ArrowLake-H
Date: Thu, 8 Aug 2024 14:02:10 +0000 [thread overview]
Message-ID: <20240808140210.1666783-5-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20240808140210.1666783-1-dapeng1.mi@linux.intel.com>
ArrowLake-H contains 3 different uarchs, LionCove, Skymont and Crestmont.
It is different with previous hybrid processors which only contains two
kinds of uarchs.
This patch adds PMU support for ArrowLake-H processor, adds ARL-H
specific events which supports the 3 kinds of uarchs, such as
td_retiring_arl_h, and extends some existed format attributes like
offcore_rsp to make them be available to support ARL-H as well. Althrough
these format attributes like offcore_rsp have been extended to support
ARL-H, they can still support the regular hybrid platforms with 2 kinds
of uarchs since the helper hybrid_format_is_visible() would filter PMU
types and only show the format attribute for available PMUs.
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
---
arch/x86/events/intel/core.c | 105 ++++++++++++++++++++++++++++++++++-
arch/x86/events/intel/ds.c | 21 +++++++
arch/x86/events/perf_event.h | 4 ++
3 files changed, 127 insertions(+), 3 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index b6429bc009c0..72836bb05387 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4589,6 +4589,28 @@ static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
return HYBRID_INTEL_CORE;
}
+static struct event_constraint *
+arl_h_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+ if (pmu->pmu_type == hybrid_small2)
+ return cmt_get_event_constraints(cpuc, idx, event);
+
+ return mtl_get_event_constraints(cpuc, idx, event);
+}
+
+static int arl_h_hw_config(struct perf_event *event)
+{
+ struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+ if (pmu->pmu_type == hybrid_small2)
+ return intel_pmu_hw_config(event);
+
+ return adl_hw_config(event);
+}
+
/*
* Broadwell:
*
@@ -5952,6 +5974,37 @@ static struct attribute *lnl_hybrid_events_attrs[] = {
NULL
};
+/* The event string must be in PMU IDX order. */
+EVENT_ATTR_STR_HYBRID(topdown-retiring,
+ td_retiring_arl_h,
+ "event=0xc2,umask=0x02;event=0x00,umask=0x80;event=0xc2,umask=0x0",
+ hybrid_big_small_arl_h);
+EVENT_ATTR_STR_HYBRID(topdown-bad-spec,
+ td_bad_spec_arl_h,
+ "event=0x73,umask=0x0;event=0x00,umask=0x81;event=0x73,umask=0x0",
+ hybrid_big_small_arl_h);
+EVENT_ATTR_STR_HYBRID(topdown-fe-bound,
+ td_fe_bound_arl_h,
+ "event=0x9c,umask=0x01;event=0x00,umask=0x82;event=0x71,umask=0x0",
+ hybrid_big_small_arl_h);
+EVENT_ATTR_STR_HYBRID(topdown-be-bound,
+ td_be_bound_arl_h,
+ "event=0xa4,umask=0x02;event=0x00,umask=0x83;event=0x74,umask=0x0",
+ hybrid_big_small_arl_h);
+
+static struct attribute *arl_h_hybrid_events_attrs[] = {
+ EVENT_PTR(slots_adl),
+ EVENT_PTR(td_retiring_arl_h),
+ EVENT_PTR(td_bad_spec_arl_h),
+ EVENT_PTR(td_fe_bound_arl_h),
+ EVENT_PTR(td_be_bound_arl_h),
+ 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);
@@ -5970,6 +6023,21 @@ static struct attribute *mtl_hybrid_mem_attrs[] = {
NULL
};
+EVENT_ATTR_STR_HYBRID(mem-loads,
+ mem_ld_arl_h,
+ "event=0xd0,umask=0x5,ldlat=3;event=0xcd,umask=0x1,ldlat=3;event=0xd0,umask=0x5,ldlat=3",
+ hybrid_big_small_arl_h);
+EVENT_ATTR_STR_HYBRID(mem-stores,
+ mem_st_arl_h,
+ "event=0xd0,umask=0x6;event=0xcd,umask=0x2;event=0xd0,umask=0x6",
+ hybrid_big_small_arl_h);
+
+static struct attribute *arl_h_hybrid_mem_attrs[] = {
+ EVENT_PTR(mem_ld_arl_h),
+ EVENT_PTR(mem_st_arl_h),
+ NULL,
+};
+
EVENT_ATTR_STR_HYBRID(tx-start, tx_start_adl, "event=0xc9,umask=0x1", hybrid_big);
EVENT_ATTR_STR_HYBRID(tx-commit, tx_commit_adl, "event=0xc9,umask=0x2", hybrid_big);
EVENT_ATTR_STR_HYBRID(tx-abort, tx_abort_adl, "event=0xc9,umask=0x4", hybrid_big);
@@ -5993,8 +6061,8 @@ static struct attribute *adl_hybrid_tsx_attrs[] = {
FORMAT_ATTR_HYBRID(in_tx, hybrid_big);
FORMAT_ATTR_HYBRID(in_tx_cp, hybrid_big);
-FORMAT_ATTR_HYBRID(offcore_rsp, hybrid_big_small);
-FORMAT_ATTR_HYBRID(ldlat, hybrid_big_small);
+FORMAT_ATTR_HYBRID(offcore_rsp, hybrid_big_small_arl_h);
+FORMAT_ATTR_HYBRID(ldlat, hybrid_big_small_arl_h);
FORMAT_ATTR_HYBRID(frontend, hybrid_big);
#define ADL_HYBRID_RTM_FORMAT_ATTR \
@@ -6017,7 +6085,7 @@ static struct attribute *adl_hybrid_extra_attr[] = {
NULL
};
-FORMAT_ATTR_HYBRID(snoop_rsp, hybrid_small);
+FORMAT_ATTR_HYBRID(snoop_rsp, hybrid_small_all);
static struct attribute *mtl_hybrid_extra_attr_rtm[] = {
ADL_HYBRID_RTM_FORMAT_ATTR,
@@ -7098,6 +7166,37 @@ __init int intel_pmu_init(void)
name = "lunarlake_hybrid";
break;
+ case INTEL_ARROWLAKE_H:
+ intel_pmu_init_hybrid(hybrid_big_small_arl_h);
+
+ x86_pmu.pebs_latency_data = arl_h_latency_data;
+ x86_pmu.get_event_constraints = arl_h_get_event_constraints;
+ x86_pmu.hw_config = arl_h_hw_config;
+
+ td_attr = arl_h_hybrid_events_attrs;
+ mem_attr = arl_h_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);
+
+ /* Initialize Atom2 core specific PerfMon capabilities.*/
+ pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM2_IDX];
+ intel_pmu_init_grt(&pmu->pmu);
+ pmu->extra_regs = intel_cmt_extra_regs;
+
+ intel_pmu_pebs_data_source_arl_h();
+ pr_cont("ArrowLake-H Hybrid events, ");
+ name = "arrowlake_h_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 fa5ea65de0d0..64242a8ffaf1 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -177,6 +177,17 @@ void __init intel_pmu_pebs_data_source_mtl(void)
__intel_pmu_pebs_data_source_cmt(data_source);
}
+void __init intel_pmu_pebs_data_source_arl_h(void)
+{
+ u64 *data_source;
+
+ intel_pmu_pebs_data_source_lnl();
+
+ data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM2_IDX].pebs_data_source;
+ memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
+ __intel_pmu_pebs_data_source_cmt(data_source);
+}
+
void __init intel_pmu_pebs_data_source_cmt(void)
{
__intel_pmu_pebs_data_source_cmt(pebs_data_source);
@@ -388,6 +399,16 @@ u64 lnl_latency_data(struct perf_event *event, u64 status)
return lnc_latency_data(event, status);
}
+u64 arl_h_latency_data(struct perf_event *event, u64 status)
+{
+ struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+ if (pmu->pmu_type == hybrid_small2)
+ return cmt_latency_data(event, status);
+
+ return lnl_latency_data(event, status);
+}
+
static u64 load_latency_data(struct perf_event *event, u64 status)
{
union intel_x86_pebs_dse dse;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index f7b55c909eff..32fcbdb464e2 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1591,6 +1591,8 @@ u64 cmt_latency_data(struct perf_event *event, u64 status);
u64 lnl_latency_data(struct perf_event *event, u64 status);
+u64 arl_h_latency_data(struct perf_event *event, u64 status);
+
extern struct event_constraint intel_core2_pebs_event_constraints[];
extern struct event_constraint intel_atom_pebs_event_constraints[];
@@ -1710,6 +1712,8 @@ void intel_pmu_pebs_data_source_grt(void);
void intel_pmu_pebs_data_source_mtl(void);
+void intel_pmu_pebs_data_source_arl_h(void);
+
void intel_pmu_pebs_data_source_cmt(void);
void intel_pmu_pebs_data_source_lnl(void);
--
2.40.1
next prev parent reply other threads:[~2024-08-08 7:48 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-08 14:02 [PATCH 0/4] Enable PMU for ArrowLake-H Dapeng Mi
2024-08-08 14:02 ` [PATCH 1/4] perf/x86: Refine hybrid_pmu_type defination Dapeng Mi
2024-08-10 21:35 ` Peter Zijlstra
2024-08-12 2:44 ` Mi, Dapeng
2024-08-08 14:02 ` [PATCH 2/4] x86/cpu/intel: Define helper to get CPU core native ID Dapeng Mi
2024-08-08 14:02 ` [PATCH 3/4] perf/x86/intel: Support hybrid PMU with multiple atom uarchs Dapeng Mi
2024-08-10 21:55 ` Peter Zijlstra
2024-08-12 3:18 ` Mi, Dapeng
2024-08-12 3:27 ` Zhenyu Wang
2024-08-16 3:54 ` Mi, Dapeng
2024-08-08 14:02 ` Dapeng Mi [this message]
2024-08-08 16:07 ` [PATCH 0/4] Enable PMU for ArrowLake-H Liang, Kan
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=20240808140210.1666783-5-dapeng1.mi@linux.intel.com \
--to=dapeng1.mi@linux.intel.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=dapeng1.mi@intel.com \
--cc=irogers@google.com \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=peterz@infradead.org \
--cc=yongwei.ma@intel.com \
--cc=zhenyuw@linux.intel.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.