The build-id events written at the end of the record session are broken
due to unexpected data. The write_buildid() writes the fixed length
event first and then variable length filename.
But a recent change made it write more data in the padding area
accidentally. So readers of the event see zero-filled data for the
next entry and treat it incorrectly. This resulted in wrong kernel
symbols because the kernel DSO loaded a random vmlinux image in the
path as it didn't have a valid build-id.
Fixes: ae39ba16554e ("perf inject: Fix build ID injection")
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/Z0aRFFW9xMh3mqKB@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
struct perf_record_header_build_id b;
size_t len;
- len = sizeof(b) + name_len + 1;
+ len = name_len + 1;
len = PERF_ALIGN(len, sizeof(u64));
memset(&b, 0, sizeof(b));
misc |= PERF_RECORD_MISC_BUILD_ID_SIZE;
b.pid = pid;
b.header.misc = misc;
- b.header.size = len;
+ b.header.size = sizeof(b) + len;
err = do_write(fd, &b, sizeof(b));
if (err < 0)