[PATCH 6/9] perf/jit: add unwinding support
From: Stefano SanfilippoThis record is intended to provide unwinding information in the eh_frame format. This is required to unwind JITed code which does not maintain the frame pointer register during function calls. The eh_frame unwinding information can be emitted by V8 / Chromium when the --perf_prof_unwinding_info is passed. A record of type jr_code_unwinding_info comes before the jr_code_load it referred to and contains both the .eh_frame and .eh_frame_hdr. The fields in the header have the following meaning: * unwinding_size: size of the eh_frame and eh_frame_hdr, necessary for distinguishing the content from the padding. * eh_frame_hdr_size: as the name says. * mapped_size: size of the payload that was in memory at runtime. typically unwinding_size if the .eh_frame_hdr and .eh_frame were mapped, or 0 if they weren't. It should always be the former case, since the .eh_frame is guaranteed to be mapped in memory. However, certain JITs might want to inject an .eh_frame_hdr with an empty LUT to trigger fp-based unwinding fallback in libunwind. The only part of the .eh_frame_hdr that libunwind reads from remote memory is the LUT, and since there is none, mapping the unwinding info in memory is not necessary, and 0 in this field signifies that it wasn't. This practical hack allows to save bytes in code memory for those JIT compilers that might or might not maintain a valid frame pointer. The payload that follows is assumed to contain first the .eh_frame and then the .eh_header_hdr, with no padding between the two. Signed-off-by: Stefano Sanfilippo Signed-off-by: Ross McIlroy Reviewed-by: Stephane Eranian --- tools/perf/util/jitdump.c | 57 --- tools/perf/util/jitdump.h | 12 ++ 2 files changed, 66 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 5db2feb90060..fdddeca26545 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -37,6 +37,10 @@ struct jit_buf_desc { bool needs_bswap; /* handles cross-endianess */ bool use_arch_timestamp; void *debug_data; + void *unwinding_data; + uint64_t unwinding_size; + uint64_t unwinding_mapped_size; + uint64_t eh_frame_hdr_size; size_t nr_debug_entries; uint32_t code_load_count; u64 bytes_written; @@ -295,6 +299,13 @@ jit_get_next_entry(struct jit_buf_desc *jd) } } break; + case JIT_CODE_UNWINDING_INFO: + if (jd->needs_bswap) { + jr->unwinding.unwinding_size = bswap_64(jr->unwinding.unwinding_size); + jr->unwinding.eh_frame_hdr_size = bswap_64(jr->unwinding.eh_frame_hdr_size); + jr->unwinding.mapped_size = bswap_64(jr->unwinding.mapped_size); + } + break; case JIT_CODE_CLOSE: break; case JIT_CODE_LOAD: @@ -370,7 +381,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) u16 idr_size; const char *sym; uint32_t count; - int ret, csize; + int ret, csize, usize; pid_t pid, tid; struct { u32 pid, tid; @@ -380,6 +391,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) pid = jr->load.pid; tid = jr->load.tid; csize = jr->load.code_size; + usize = jd->unwinding_mapped_size; addr = jr->load.code_addr; sym = (void *)((unsigned long)jr + sizeof(jr->load)); code = (unsigned long)jr + jr->load.p.total_size - csize; @@ -408,6 +420,14 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) jd->nr_debug_entries = 0; } + if (jd->unwinding_data && jd->eh_frame_hdr_size) { + free(jd->unwinding_data); + jd->unwinding_data = NULL; + jd->eh_frame_hdr_size = 0; + jd->unwinding_mapped_size = 0; + jd->unwinding_size = 0; + } + if (ret) { free(event); return -1; @@ -422,7 +442,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET; event->mmap2.start = addr; - event->mmap2.len = csize; + event->mmap2.len = usize ? ALIGN_8(csize) + usize : csize; event->mmap2.pid = pid; event->mmap2.tid = tid; event->mmap2.ino = st.st_ino; @@ -473,6 +493,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) char *filename; size_t
[PATCH 6/9] perf/jit: add unwinding support
From: Stefano Sanfilippo This record is intended to provide unwinding information in the eh_frame format. This is required to unwind JITed code which does not maintain the frame pointer register during function calls. The eh_frame unwinding information can be emitted by V8 / Chromium when the --perf_prof_unwinding_info is passed. A record of type jr_code_unwinding_info comes before the jr_code_load it referred to and contains both the .eh_frame and .eh_frame_hdr. The fields in the header have the following meaning: * unwinding_size: size of the eh_frame and eh_frame_hdr, necessary for distinguishing the content from the padding. * eh_frame_hdr_size: as the name says. * mapped_size: size of the payload that was in memory at runtime. typically unwinding_size if the .eh_frame_hdr and .eh_frame were mapped, or 0 if they weren't. It should always be the former case, since the .eh_frame is guaranteed to be mapped in memory. However, certain JITs might want to inject an .eh_frame_hdr with an empty LUT to trigger fp-based unwinding fallback in libunwind. The only part of the .eh_frame_hdr that libunwind reads from remote memory is the LUT, and since there is none, mapping the unwinding info in memory is not necessary, and 0 in this field signifies that it wasn't. This practical hack allows to save bytes in code memory for those JIT compilers that might or might not maintain a valid frame pointer. The payload that follows is assumed to contain first the .eh_frame and then the .eh_header_hdr, with no padding between the two. Signed-off-by: Stefano Sanfilippo Signed-off-by: Ross McIlroy Reviewed-by: Stephane Eranian --- tools/perf/util/jitdump.c | 57 --- tools/perf/util/jitdump.h | 12 ++ 2 files changed, 66 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 5db2feb90060..fdddeca26545 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -37,6 +37,10 @@ struct jit_buf_desc { bool needs_bswap; /* handles cross-endianess */ bool use_arch_timestamp; void *debug_data; + void *unwinding_data; + uint64_t unwinding_size; + uint64_t unwinding_mapped_size; + uint64_t eh_frame_hdr_size; size_t nr_debug_entries; uint32_t code_load_count; u64 bytes_written; @@ -295,6 +299,13 @@ jit_get_next_entry(struct jit_buf_desc *jd) } } break; + case JIT_CODE_UNWINDING_INFO: + if (jd->needs_bswap) { + jr->unwinding.unwinding_size = bswap_64(jr->unwinding.unwinding_size); + jr->unwinding.eh_frame_hdr_size = bswap_64(jr->unwinding.eh_frame_hdr_size); + jr->unwinding.mapped_size = bswap_64(jr->unwinding.mapped_size); + } + break; case JIT_CODE_CLOSE: break; case JIT_CODE_LOAD: @@ -370,7 +381,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) u16 idr_size; const char *sym; uint32_t count; - int ret, csize; + int ret, csize, usize; pid_t pid, tid; struct { u32 pid, tid; @@ -380,6 +391,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) pid = jr->load.pid; tid = jr->load.tid; csize = jr->load.code_size; + usize = jd->unwinding_mapped_size; addr = jr->load.code_addr; sym = (void *)((unsigned long)jr + sizeof(jr->load)); code = (unsigned long)jr + jr->load.p.total_size - csize; @@ -408,6 +420,14 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) jd->nr_debug_entries = 0; } + if (jd->unwinding_data && jd->eh_frame_hdr_size) { + free(jd->unwinding_data); + jd->unwinding_data = NULL; + jd->eh_frame_hdr_size = 0; + jd->unwinding_mapped_size = 0; + jd->unwinding_size = 0; + } + if (ret) { free(event); return -1; @@ -422,7 +442,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET; event->mmap2.start = addr; - event->mmap2.len = csize; + event->mmap2.len = usize ? ALIGN_8(csize) + usize : csize; event->mmap2.pid = pid; event->mmap2.tid = tid; event->mmap2.ino = st.st_ino; @@ -473,6 +493,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) char *filename; size_t size; struct stat st; + int usize; u16 idr_size; int ret;