From b2f10cd4e805eb647773df273eb1a6ff9e6ea45d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 14 Jun 2022 07:33:51 -0700 Subject: 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 Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Athira Jajeev Cc: Colin Ian King Cc: Dave Marchevsky Cc: German Gomez Cc: Gustavo A. R. Silva Cc: Ingo Molnar Cc: James Clark Cc: Kees Kook Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Song Liu Cc: Stephane Eranian Link: https://lore.kernel.org/r/20220614143353.1559597-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'tools/perf/util/session.c') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 98e16659a149..61bb9675e044 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -916,30 +916,30 @@ static void perf_event__cpu_map_swap(union perf_event *event, bool sample_id_all __maybe_unused) { struct perf_record_cpu_map_data *data = &event->cpu_map.data; - struct cpu_map_entries *cpus; - struct perf_record_record_cpu_map *mask; - unsigned i; data->type = bswap_16(data->type); switch (data->type) { case PERF_CPU_MAP__CPUS: - cpus = (struct cpu_map_entries *)data->data; - - cpus->nr = bswap_16(cpus->nr); + data->cpus_data.nr = bswap_16(data->cpus_data.nr); - for (i = 0; i < cpus->nr; i++) - cpus->cpu[i] = bswap_16(cpus->cpu[i]); + for (unsigned i = 0; i < data->cpus_data.nr; i++) + data->cpus_data.cpu[i] = bswap_16(data->cpus_data.cpu[i]); break; case PERF_CPU_MAP__MASK: - mask = (struct perf_record_record_cpu_map *)data->data; - - mask->nr = bswap_16(mask->nr); - mask->long_size = bswap_16(mask->long_size); + data->mask32_data.long_size = bswap_16(data->mask32_data.long_size); - switch (mask->long_size) { - case 4: mem_bswap_32(&mask->mask, mask->nr); break; - case 8: mem_bswap_64(&mask->mask, mask->nr); break; + switch (data->mask32_data.long_size) { + case 4: + data->mask32_data.nr = bswap_16(data->mask32_data.nr); + for (unsigned i = 0; i < data->mask32_data.nr; i++) + data->mask32_data.mask[i] = bswap_32(data->mask32_data.mask[i]); + break; + case 8: + data->mask64_data.nr = bswap_16(data->mask64_data.nr); + for (unsigned i = 0; i < data->mask64_data.nr; i++) + data->mask64_data.mask[i] = bswap_64(data->mask64_data.mask[i]); + break; default: pr_err("cpu_map swap: unsupported long size\n"); } -- cgit v1.2.3