Re: [PATCH v4 5/6] perf tools: Show memory region in perf-script subcommand
Ian Rogers <[email protected]>
| Newsgroups | org.kernel.vger.linux-perf-users,org.kernel.vger.linux-kernel |
|---|---|
| Message-ID | <CAP-5=fVu02rzde-U2uoXiWa2Sbfp5X5fA8VKL+isA260t8aLew@mail.gmail.com> |
On Tue, Aug 11, 2026 at 10:34 AM Thomas Falcon <[email protected]> wrote: > > From: Dapeng Mi <[email protected]> > > Show the memory region in perf-script subcommand. Memory region is found > in the mem_region field of the memory information data source. This > field was included with the introduction of support for the Off-module > Response facility (OMR) [1] in Intel's Diamond Rapids and Nova Lake > Architectures. > > An example of perf-script output with the new memory region field is shown > below: > > random 10e6a100042 |OP LOAD|LVL L0 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A|Region N/A 7f32ae64a2ec > random 2411a68201042 |OP LOAD|LVL RAM hit|SNP Hit|TLB L1 or L2 hit|LCK No|BLK N/A|Region Mem-1 561de7f8910a > random 10e6a100042 |OP LOAD|LVL L0 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A|Region N/A 7f32ae64a2d0 > random 20e6a100042 |OP LOAD|LVL L0 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK Data|Region N/A 7f32ae64a2d0 > random 20e6a100042 |OP LOAD|LVL L0 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK Data|Region N/A 7f32ae64a2d0 > random 10e6a100042 |OP LOAD|LVL L0 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A|Region N/A 7f32ae64a2ec > random 10e6a100042 |OP LOAD|LVL L0 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A|Region N/A 7f32ae64a2d0 > random 10e6a100042 |OP LOAD|LVL L0 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A|Region N/A 7f32ae64a2d0 > random 2411a68201042 |OP LOAD|LVL RAM hit|SNP Hit|TLB L1 or L2 hit|LCK No|BLK N/A|Region Mem-1 561de7f8910a > random 10e6a100042 |OP LOAD|LVL L0 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A|Region N/A 7f32ae64a2ec > random 10e6a100042 |OP LOAD|LVL L0 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A|Region N/A 7f32ae64a2d0 > > [1]: https://lore.kernel.org/all/[email protected]/ > > Assisted-by: Sashiko:gemini-3.1-pro-preview > Assisted-by: GitHub-Copilot:claude-opus-4-8 > Signed-off-by: Dapeng Mi <[email protected]> > Signed-off-by: Thomas Falcon <[email protected]> > Link: https://lore.kernel.org/all/[email protected]/ Reviewed-by: Ian Rogers <[email protected]> Thanks, Ian > --- > v4: Drop the global show-region flag; pass perf_session to > perf_script__meminfo_scnprintf() and gate the Region field > on the feature bit, with a pipe-mode fallback > > v3: make memory region reporting conditional on feature bit > --- > tools/perf/builtin-script.c | 13 +-- > tools/perf/util/mem-events.c | 86 ++++++++++++++++++- > tools/perf/util/mem-events.h | 4 +- > .../scripting-engines/trace-event-python.c | 5 +- > 4 files changed, 98 insertions(+), 10 deletions(-) > > diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c > index f91d8b1fbd01..410ccad56f99 100644 > --- a/tools/perf/builtin-script.c > +++ b/tools/perf/builtin-script.c > @@ -2078,11 +2078,12 @@ static int evlist__max_name_len(struct evlist *evlist) > return max; > } > > -static int data_src__fprintf(u64 data_src, FILE *fp) > +static int data_src__fprintf(struct perf_session *session, > + u64 data_src, FILE *fp) > { > struct mem_info *mi = mem_info__new(); > - char decode[100]; > - char out[100]; > + char decode[200]; > + char out[200]; > static int maxlen; > int len; > > @@ -2090,10 +2091,10 @@ static int data_src__fprintf(u64 data_src, FILE *fp) > return -ENOMEM; > > mem_info__data_src(mi)->val = data_src; > - perf_script__meminfo_scnprintf(decode, 100, mi); > + perf_script__meminfo_scnprintf(decode, 200, mi, session); > mem_info__put(mi); > > - len = scnprintf(out, 100, "%16" PRIx64 " %s", data_src, decode); > + len = scnprintf(out, 200, "%16" PRIx64 " %s", data_src, decode); > if (maxlen < len) > maxlen = len; > > @@ -2487,7 +2488,7 @@ static void process_event(struct perf_script *script, > perf_sample__fprintf_addr(sample, thread, evsel, fp); > > if (PRINT_FIELD(DATA_SRC)) > - data_src__fprintf(sample->data_src, fp); > + data_src__fprintf(evsel__session(evsel), sample->data_src, fp); > > if (PRINT_FIELD(WEIGHT)) > fprintf(fp, "%16" PRIu64, sample->weight); > diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c > index 4fd48fd20055..8ce4996cad8d 100644 > --- a/tools/perf/util/mem-events.c > +++ b/tools/perf/util/mem-events.c > @@ -604,8 +604,77 @@ int perf_mem__blk_scnprintf(char *out, size_t sz, const struct mem_info *mem_inf > return l; > } > > -int perf_script__meminfo_scnprintf(char *out, size_t sz, const struct mem_info *mem_info) > +static int perf_mem__region_scnprintf(char *out, size_t sz, const struct mem_info *mem_info) > { > + size_t l = 0; > + u64 mem = PERF_MEM_REGION_NA; > + > + sz -= 1; /* -1 for null termination */ > + out[0] = '\0'; > + > + if (mem_info) > + mem = mem_info__const_data_src(mem_info)->mem_region; > + > + switch (mem) { > + case PERF_MEM_REGION_NA: > + case PERF_MEM_REGION_RSVD: > + l += scnprintf(out + l, sz - l, "N/A"); > + break; > + case PERF_MEM_REGION_L_SHARE: > + l += scnprintf(out + l, sz - l, "Local-shared-cache"); > + break; > + case PERF_MEM_REGION_L_NON_SHARE: > + l += scnprintf(out + l, sz - l, "Local-non-shared-cache"); > + break; > + case PERF_MEM_REGION_O_IO: > + l += scnprintf(out + l, sz - l, "Other-IO"); > + break; > + case PERF_MEM_REGION_O_SHARE: > + l += scnprintf(out + l, sz - l, "Other-shared-cache"); > + break; > + case PERF_MEM_REGION_O_NON_SHARE: > + l += scnprintf(out + l, sz - l, "Other-non-shared-cache"); > + break; > + case PERF_MEM_REGION_MMIO: > + l += scnprintf(out + l, sz - l, "MMIO"); > + break; > + case PERF_MEM_REGION_MEM0: > + l += scnprintf(out + l, sz - l, "Mem-0"); > + break; > + case PERF_MEM_REGION_MEM1: > + l += scnprintf(out + l, sz - l, "Mem-1"); > + break; > + case PERF_MEM_REGION_MEM2: > + l += scnprintf(out + l, sz - l, "Mem-2"); > + break; > + case PERF_MEM_REGION_MEM3: > + l += scnprintf(out + l, sz - l, "Mem-3"); > + break; > + case PERF_MEM_REGION_MEM4: > + l += scnprintf(out + l, sz - l, "Mem-4"); > + break; > + case PERF_MEM_REGION_MEM5: > + l += scnprintf(out + l, sz - l, "Mem-5"); > + break; > + case PERF_MEM_REGION_MEM6: > + l += scnprintf(out + l, sz - l, "Mem-6"); > + break; > + case PERF_MEM_REGION_MEM7: > + l += scnprintf(out + l, sz - l, "Mem-7"); > + break; > + default: > + l += scnprintf(out + l, sz - l, "N/A"); > + break; > + } > + > + return l; > +} > + > +int perf_script__meminfo_scnprintf(char *out, size_t sz, > + const struct mem_info *mem_info, > + struct perf_session *session) > +{ > + struct perf_env *env; > int i = 0; > > i += scnprintf(out, sz, "|OP "); > @@ -620,6 +689,21 @@ int perf_script__meminfo_scnprintf(char *out, size_t sz, const struct mem_info * > i += perf_mem__lck_scnprintf(out + i, sz - i, mem_info); > i += scnprintf(out + i, sz - i, "|BLK "); > i += perf_mem__blk_scnprintf(out + i, sz - i, mem_info); > + if (session) { > + /* > + * In case the feature bits are not available, as in > + * pipe mode, fallback to checking for the existence of > + * memory ranges > + */ > + env = perf_session__env(session); > + if ((env && session->data->is_pipe && env->nr_memory_ranges) || > + perf_header__has_feat(&session->header, > + HEADER_MEMORY_RANGES)) { > + i += scnprintf(out + i, sz - i, "|Region "); > + i += perf_mem__region_scnprintf(out + i, sz - i, > + mem_info); > + } > + } > > return i; > } > diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h > index daa22748f9fe..4ebb8109fc3c 100644 > --- a/tools/perf/util/mem-events.h > +++ b/tools/perf/util/mem-events.h > @@ -4,6 +4,7 @@ > > #include <stdbool.h> > #include <linux/types.h> > +#include "session.h" > > struct perf_mem_event { > bool supported; > @@ -47,7 +48,8 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, const struct mem_info *mem_inf > int perf_mem__lck_scnprintf(char *out, size_t sz, const struct mem_info *mem_info); > int perf_mem__blk_scnprintf(char *out, size_t sz, const struct mem_info *mem_info); > > -int perf_script__meminfo_scnprintf(char *bf, size_t size, const struct mem_info *mem_info); > +int perf_script__meminfo_scnprintf(char *bf, size_t size, const struct mem_info *mem_info, > + struct perf_session *session); > > struct c2c_stats { > u32 nr_entries; > diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c > index 8f832ae316ca..e359fe529586 100644 > --- a/tools/perf/util/scripting-engines/trace-event-python.c > +++ b/tools/perf/util/scripting-engines/trace-event-python.c > @@ -694,8 +694,9 @@ static void set_sample_read_in_dict(PyObject *dict_sample, struct perf_sample *s > static void set_sample_datasrc_in_dict(PyObject *dict, > struct perf_sample *sample) > { > + struct perf_session *session = evsel__session(sample->evsel); > struct mem_info *mi = mem_info__new(); > - char decode[100]; > + char decode[200]; > > if (!mi) > Py_FatalError("couldn't create mem-info"); > @@ -704,7 +705,7 @@ static void set_sample_datasrc_in_dict(PyObject *dict, > PyLong_FromUnsignedLongLong(sample->data_src)); > > mem_info__data_src(mi)->val = sample->data_src; > - perf_script__meminfo_scnprintf(decode, 100, mi); > + perf_script__meminfo_scnprintf(decode, 200, mi, session); > mem_info__put(mi); > > pydict_set_item_string_decref(dict, "datasrc_decode", > -- > 2.55.0 >