Re: [PATCH v2 4/6] perf tools: Show memory region in perf-script subcommand

[Mi, Dapeng]

On 7/29/2026 1:18 AM, Namhyung Kim wrote:
> On Mon, Jul 13, 2026 at 07:43:57PM -0500, Thomas Falcon wrote:
>> 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:
>>
>> 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/20260114011750.350569-1-dapeng1.mi@xxxxxxxxxxxxxxx/
>>
>> Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
>> Signed-off-by: Thomas Falcon <thomas.falcon@xxxxxxxxx>
>> ---
>> Changes in v2:
>> -- increased buffers passed to perf_script__meminfo_scnprintf() from 150
>>    to 200 bytes to avoid silent truncation
>> ---
>>  tools/perf/builtin-script.c                   |  8 +--
>>  tools/perf/util/mem-events.c                  | 68 +++++++++++++++++++
>>  .../scripting-engines/trace-event-python.c    |  4 +-
>>  3 files changed, 74 insertions(+), 6 deletions(-)
>>
>> diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
>> index f91d8b1fbd01..ba8ec0093f4f 100644
>> --- a/tools/perf/builtin-script.c
>> +++ b/tools/perf/builtin-script.c
>> @@ -2081,8 +2081,8 @@ static int evlist__max_name_len(struct evlist *evlist)
>>  static int data_src__fprintf(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 +2090,10 @@ 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);
>>  	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;
>>  
>> diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
>> index 4fd48fd20055..ff08f1fee0e3 100644
>> --- a/tools/perf/util/mem-events.c
>> +++ b/tools/perf/util/mem-events.c
>> @@ -604,6 +604,72 @@ int perf_mem__blk_scnprintf(char *out, size_t sz, const struct mem_info *mem_inf
>>  	return l;
>>  }
>>  
>> +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)
>>  {
>>  	int i = 0;
>> @@ -620,6 +686,8 @@ 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);
>> +	i += scnprintf(out + i, sz - i, "|Region ");
>> +	i += perf_mem__region_scnprintf(out + i, sz - i, mem_info);
> Same thing.  Would be nice if it can be conditional.

Sure. Thanks.


>
> Thanks,
> Namhyung
>
>>  
>>  	return i;
>>  }
>> diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
>> index 8f832ae316ca..57ec259897e4 100644
>> --- a/tools/perf/util/scripting-engines/trace-event-python.c
>> +++ b/tools/perf/util/scripting-engines/trace-event-python.c
>> @@ -695,7 +695,7 @@ static void set_sample_datasrc_in_dict(PyObject *dict,
>>  				      struct perf_sample *sample)
>>  {
>>  	struct mem_info *mi = mem_info__new();
>> -	char decode[100];
>> +	char decode[200];
>>  
>>  	if (!mi)
>>  		Py_FatalError("couldn't create mem-info");
>> @@ -704,7 +704,7 @@ 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);
>>  	mem_info__put(mi);
>>  
>>  	pydict_set_item_string_decref(dict, "datasrc_decode",
>> -- 
>> 2.43.0
>>