perf cpumap: Fix alignment for masks in event encoding

A mask encoding of a cpu map is laid out as:

  u16 nr
  u16 long_size
  unsigned long mask[];

However, the mask may be 8-byte aligned meaning there is a 4-byte pad
after long_size. This means 32-bit and 64-bit builds see the mask as
being at different offsets. On top of this the structure is in the byte
data[] encoded as:

  u16 type
  char data[]

This means the mask's struct isn't the required 4 or 8 byte aligned, but
is offset by 2. Consequently the long reads and writes are causing
undefined behavior as the alignment is broken.

Fix the mask struct by creating explicit 32 and 64-bit variants, use a
union to avoid data[] and casts; the struct must be packed so the
layout matches the existing perf.data layout. Taking an address of a
member of a packed struct breaks alignment so pass the packed
perf_record_cpu_map_data to functions, so they can access variables with
the right alignment.

As the 64-bit version has 4 bytes of padding, optimizing writing to only
write the 32-bit version.

Committer notes:

Disable warnings about 'packed' that break the build in some arches like
riscv64, but just around that specific struct.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Colin Ian King <colin.king@intel.com>
Cc: Dave Marchevsky <davemarchevsky@fb.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Kees Kook <keescook@chromium.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20220614143353.1559597-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 9 insertions, 10 deletions

diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index f94929ebb54b..7ea150cdc137 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -17,21 +17,23 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused,
 			 struct machine *machine __maybe_unused)
 {
 	struct perf_record_cpu_map *map_event = &event->cpu_map;
-	struct perf_record_record_cpu_map *mask;
 	struct perf_record_cpu_map_data *data;
 	struct perf_cpu_map *map;
 	int i;
+	unsigned int long_size;
 
 	data = &map_event->data;
 
 	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK);
 
-	mask = (struct perf_record_record_cpu_map *)data->data;
+	long_size = data->mask32_data.long_size;
 
-	TEST_ASSERT_VAL("wrong nr",   mask->nr == 1);
+	TEST_ASSERT_VAL("wrong long_size", long_size == 4 || long_size == 8);
+
+	TEST_ASSERT_VAL("wrong nr",   data->mask32_data.nr == 1);
 
 	for (i = 0; i < 20; i++) {
-		TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask));
+		TEST_ASSERT_VAL("wrong cpu", perf_record_cpu_map_data__test_bit(i, data));
 	}
 
 	map = cpu_map__new_data(data);
@@ -51,7 +53,6 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 			 struct machine *machine __maybe_unused)
 {
 	struct perf_record_cpu_map *map_event = &event->cpu_map;
-	struct cpu_map_entries *cpus;
 	struct perf_record_cpu_map_data *data;
 	struct perf_cpu_map *map;
 
@@ -59,11 +60,9 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 
 	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS);
 
-	cpus = (struct cpu_map_entries *)data->data;
-
-	TEST_ASSERT_VAL("wrong nr",   cpus->nr == 2);
-	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[0] == 1);
-	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[1] == 256);
+	TEST_ASSERT_VAL("wrong nr",   data->cpus_data.nr == 2);
+	TEST_ASSERT_VAL("wrong cpu",  data->cpus_data.cpu[0] == 1);
+	TEST_ASSERT_VAL("wrong cpu",  data->cpus_data.cpu[1] == 256);
 
 	map = cpu_map__new_data(data);
 	TEST_ASSERT_VAL("wrong nr",  perf_cpu_map__nr(map) == 2);