[PATCH v10 5/6] perf tools: Show memory region in perf-script subcommand
From: Thomas Falcon
Date: Wed Sep 16 2026 - 14:50:32 EST
From: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
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:
thread 5/0 ... |OP LOAD|LVL L3 hit|SNP HitM|TLB L1 or L2 hit|LCK No|BLK N/A|Region Local-shared-cache ffffffff9f002aba
thread 2/0 ... |OP LOAD|LVL L3 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A|Region Local-shared-cache ffffffff9dc54c95
thread 8/0 ... |OP LOAD|LVL L3 hit|SNP HitM|TLB L1 or L2 hit|LCK No|BLK N/A|Region Other-non-shared-cache ffffffff9dc54db3
thread 0/0 ... |OP LOAD|LVL LFB/MAB hit|SNP None|TLB L1 or L2 hit|LCK No|BLK Addr|Region N/A ffffffff9dc54db3
thread 2/0 ... |OP LOAD|LVL L0 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A|Region N/A ffffffff9f002a8c
thread 0/0 ... |OP LOAD|LVL L3 hit|SNP HitM or Fwd|TLB L1 or L2 hit|LCK No|BLK N/A|Region Local-non-shared-cache ffffffff9f002aba
thread 0/0 ... |OP LOAD|LVL L3 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A|Region Local-shared-cache ffffffff9dc54ca7
thread 30/0 ... |OP LOAD|LVL LFB/MAB hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A|Region N/A ffffffff9dcc1ff2
thread 30/0 ... |OP LOAD|LVL RAM hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A|Region Mem-0 ffffffff9dc54c95
thread 19/0 ... |OP LOAD|LVL LFB/MAB hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A|Region N/A ffffffff9f002cbb
thread 19/0 ... |OP LOAD|LVL L3 hit|SNP HitM or Fwd|TLB L1 or L2 hit|LCK No|BLK N/A|Region Local-non-shared-cache ffffffff9f002aba
[1]: https://lore.kernel.org/all/20260114011750.350569-1-dapeng1.mi@xxxxxxxxxxxxxxx/
Assisted-by: Sashiko:gemini-3.1-pro-preview
Assisted-by: GitHub-Copilot:claude-opus-4-8
Reviewed-by: Ian Rogers <irogers@xxxxxxxxxx>
Reviewed-by: Namhyung Kim <namhyung@xxxxxxxxxx>
Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
Co-developed-by: Thomas Falcon <thomas.falcon@xxxxxxxxx>
Signed-off-by: Thomas Falcon <thomas.falcon@xxxxxxxxx>
---
v10: use a forward declaration of struct perf_session in mem-events.h
instead of including session.h; include session.h directly where
needed (Sashiko)
v8: Update developer tags and commit message with real example output
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 | 87 ++++++++++++++++++-
tools/perf/util/mem-events.h | 4 +-
.../scripting-engines/trace-event-python.c | 6 +-
4 files changed, 100 insertions(+), 10 deletions(-)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 0174489d1c0f..565ee8d55f80 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2153,11 +2153,12 @@ 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;
@@ -2165,10 +2166,10 @@ 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;
@@ -2562,7 +2563,7 @@ 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..0cdcb47647bd 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -17,6 +17,7 @@
#include "symbol.h"
#include "pmu.h"
#include "pmus.h"
+#include "session.h"
unsigned int perf_mem_events__loads_ldlat = 30;
@@ -604,8 +605,77 @@ 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 +690,21 @@ 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..38b14c03392c 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -24,6 +24,7 @@ enum {
struct evsel;
struct mem_info;
struct perf_pmu;
+struct perf_session;
extern unsigned int perf_mem_events__loads_ldlat;
extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
@@ -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 239104b0337d..038c4268a429 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -58,6 +58,7 @@
#include "stat.h"
#include "mem-events.h"
#include "util/perf_regs.h"
+#include "util/session.h"
#define _PyUnicode_FromString(arg) \
PyUnicode_FromString(arg)
@@ -694,8 +695,9 @@ 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 +706,7 @@ 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",
--
2.43.0