perf header: Additional note on AMD IBS for max_precise pmu cap

x86 core PMU exposes supported maximum precision level via max_precise
PMU capability. Although, AMD core PMU does not support precise mode,
certain core PMU events with precise_ip > 0 are allowed and forwarded to
IBS OP PMU.

Display a note about this in the 'perf report' header output and
document the details in the perf-list man page.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ross Zwisler <zwisler@chromium.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231107083331.901-2-ravi.bangoria@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index d5f78e125efed157d1270ff256513fa31673f60f..1b90575ee3c84eb206f9291e8fd05d43c70b2f9c 100644 (file)
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -81,11 +81,13 @@ For Intel systems precise event sampling is implemented with PEBS
 which supports up to precise-level 2, and precise level 3 for
 some special cases
 
-On AMD systems it is implemented using IBS (up to precise-level 2).
-The precise modifier works with event types 0x76 (cpu-cycles, CPU
-clocks not halted) and 0xC1 (micro-ops retired). Both events map to
-IBS execution sampling (IBS op) with the IBS Op Counter Control bit
-(IbsOpCntCtl) set respectively (see the
+On AMD systems it is implemented using IBS OP (up to precise-level 2).
+Unlike Intel PEBS which provides levels of precision, AMD core pmu is
+inherently non-precise and IBS is inherently precise. (i.e. ibs_op//,
+ibs_op//p, ibs_op//pp and ibs_op//ppp are all same). The precise modifier
+works with event types 0x76 (cpu-cycles, CPU clocks not halted) and 0xC1
+(micro-ops retired). Both events map to IBS execution sampling (IBS op)
+with the IBS Op Counter Control bit (IbsOpCntCtl) set respectively (see the
 Core Complex (CCX) -> Processor x86 Core -> Instruction Based Sampling (IBS)
 section of the [AMD Processor Programming Reference (PPR)] relevant to the
 family, model and stepping of the processor being used).

diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 44140b7f596a3f2009fc2f901317a602f14fe6c4..cbc18b22ace5231eb1101ab6dfd95b1b23995057 100644 (file)
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -531,6 +531,24 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu)
        return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1;
 }
 
+bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name)
+{
+       char *pmu_mapping = env->pmu_mappings, *colon;
+
+       for (int i = 0; i < env->nr_pmu_mappings; ++i) {
+               if (strtoul(pmu_mapping, &colon, 0) == ULONG_MAX || *colon != ':')
+                       goto out_error;
+
+               pmu_mapping = colon + 1;
+               if (strcmp(pmu_mapping, pmu_name) == 0)
+                       return true;
+
+               pmu_mapping += strlen(pmu_mapping) + 1;
+       }
+out_error:
+       return false;
+}
+
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
                             const char *cap)
 {

diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 48d7f8759a2a7ac0f580871a5dd1f7e1521a335b..94596ff124d541884a6d1573f00f09d7cf81029e 100644 (file)
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -179,4 +179,6 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
                             const char *cap);
+
+bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name);
 #endif /* __PERF_ENV_H */

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index eeb96a1b63a7cad488fab878d8c1f6d7667bf5a4..1c687b5789c0f34077cfae03daffde923ba85c6d 100644 (file)
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2145,6 +2145,14 @@ static void print_pmu_caps(struct feat_fd *ff, FILE *fp)
                __print_pmu_caps(fp, pmu_caps->nr_caps, pmu_caps->caps,
                                 pmu_caps->pmu_name);
        }
+
+       if (strcmp(perf_env__arch(&ff->ph->env), "x86") == 0 &&
+           perf_env__has_pmu_mapping(&ff->ph->env, "ibs_op")) {
+               char *max_precise = perf_env__find_pmu_cap(&ff->ph->env, "cpu", "max_precise");
+
+               if (max_precise != NULL && atoi(max_precise) == 0)
+                       fprintf(fp, "# AMD systems uses ibs_op// PMU for some precise events, e.g.: cycles:p, see the 'perf list' man page for further details.\n");
+       }
 }
 
 static void print_pmu_mappings(struct feat_fd *ff, FILE *fp)