Commit 3a5b64f0 authored by Mao Han's avatar Mao Han Committed by Arnaldo Carvalho de Melo
Browse files

perf evsel: Use hweight64() instead of hweight_long(attr.sample_regs_user) 



On 32-bits platform with more than 32 registers, the 64 bits mask is
truncate to the lower 32 bits and the return value of hweight_long will
always smaller than 32. When kernel outputs more than 32 registers, but
the user perf program only counts 32, there will be a data mismatch
result to overflow check fail.

Signed-off-by: default avatarMao Han <han_mao@c-sky.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Fixes: 6a21c0b5 ("perf tools: Add core support for sampling intr machine state regs")
Fixes: d03f2170 ("perf tools: Expand perf_event__synthesize_sample()")
Fixes: 0f6a3015 ("perf tools: Support user regs and stack in sample parsing")
Link: http://lkml.kernel.org/r/29ad7947dc8fd1ff0abd2093a72cc27a2446be9f.1554883878.git.han_mao@c-sky.com


Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent f32c2877

tools/perf/util/evsel.c

+6 −6
Original line number Diff line number Diff line
@@ -2368,7 +2368,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, 
		if (data->user_regs.abi) {

			u64 mask = evsel->attr.sample_regs_user;



			sz = hweight_long(mask) * sizeof(u64);

			sz = hweight64(mask) * sizeof(u64);

			OVERFLOW_CHECK(array, sz, max_size);

			data->user_regs.mask = mask;

			data->user_regs.regs = (u64 *)array;
@@ -2424,7 +2424,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, 
		if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {

			u64 mask = evsel->attr.sample_regs_intr;



			sz = hweight_long(mask) * sizeof(u64);

			sz = hweight64(mask) * sizeof(u64);

			OVERFLOW_CHECK(array, sz, max_size);

			data->intr_regs.mask = mask;

			data->intr_regs.regs = (u64 *)array;
@@ -2552,7 +2552,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, 
	if (type & PERF_SAMPLE_REGS_USER) {

		if (sample->user_regs.abi) {

			result += sizeof(u64);

			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);

			sz = hweight64(sample->user_regs.mask) * sizeof(u64);

			result += sz;

		} else {

			result += sizeof(u64);
@@ -2580,7 +2580,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, 
	if (type & PERF_SAMPLE_REGS_INTR) {

		if (sample->intr_regs.abi) {

			result += sizeof(u64);

			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);

			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);

			result += sz;

		} else {

			result += sizeof(u64);
@@ -2710,7 +2710,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, 
	if (type & PERF_SAMPLE_REGS_USER) {

		if (sample->user_regs.abi) {

			*array++ = sample->user_regs.abi;

			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);

			sz = hweight64(sample->user_regs.mask) * sizeof(u64);

			memcpy(array, sample->user_regs.regs, sz);

			array = (void *)array + sz;

		} else {
@@ -2746,7 +2746,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, 
	if (type & PERF_SAMPLE_REGS_INTR) {

		if (sample->intr_regs.abi) {

			*array++ = sample->intr_regs.abi;

			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);

			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);

			memcpy(array, sample->intr_regs.regs, sz);

			array = (void *)array + sz;

		} else {

CRA Git | Maintained and supported by SUSTech CRA and CCSE