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, 43 insertions, 4 deletions

diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index 556bb06798f2..57f54781f5ed 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/limits.h>
 #include <linux/bpf.h>
+#include <linux/compiler.h>
 #include <sys/types.h> /* pid_t */
 
 #define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem))
@@ -153,22 +154,60 @@ enum {
 	PERF_CPU_MAP__MASK = 1,
 };
 
+/*
+ * Array encoding of a perf_cpu_map where nr is the number of entries in cpu[]
+ * and each entry is a value for a CPU in the map.
+ */
 struct cpu_map_entries {
 	__u16			 nr;
 	__u16			 cpu[];
 };
 
-struct perf_record_record_cpu_map {
+/* Bitmap encoding of a perf_cpu_map where bitmap entries are 32-bit. */
+struct perf_record_mask_cpu_map32 {
+	/* Number of mask values. */
 	__u16			 nr;
+	/* Constant 4. */
 	__u16			 long_size;
-	unsigned long		 mask[];
+	/* Bitmap data. */
+	__u32			 mask[];
 };
 
-struct perf_record_cpu_map_data {
+/* Bitmap encoding of a perf_cpu_map where bitmap entries are 64-bit. */
+struct perf_record_mask_cpu_map64 {
+	/* Number of mask values. */
+	__u16			 nr;
+	/* Constant 8. */
+	__u16			 long_size;
+	/* Legacy padding. */
+	char                     __pad[4];
+	/* Bitmap data. */
+	__u64			 mask[];
+};
+
+/*
+ * 'struct perf_record_cpu_map_data' is packed as unfortunately an earlier
+ * version had unaligned data and we wish to retain file format compatibility.
+ * -irogers
+ */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
+
+struct __packed perf_record_cpu_map_data {
 	__u16			 type;
-	char			 data[];
+	union {
+		/* Used when type == PERF_CPU_MAP__CPUS. */
+		struct cpu_map_entries cpus_data;
+		/* Used when type == PERF_CPU_MAP__MASK and long_size == 4. */
+		struct perf_record_mask_cpu_map32 mask32_data;
+		/* Used when type == PERF_CPU_MAP__MASK and long_size == 8. */
+		struct perf_record_mask_cpu_map64 mask64_data;
+	};
 };
 
+#pragma GCC diagnostic pop
+
 struct perf_record_cpu_map {
 	struct perf_event_header	 header;
 	struct perf_record_cpu_map_data	 data;