perf jit: Add unwinding support

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 <ssanfilippo@chromium.org>
Signed-off-by: Ross McIlroy <rmcilroy@chromium.org>
Reviewed-by: Stephane Eranian <eranian@google.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1476356383-30100-7-git-send-email-eranian@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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;
 	pid_t pid, tid;
@@ -483,6 +504,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 
 	pid = jr->move.pid;
 	tid =  jr->move.tid;
+	usize = jd->unwinding_mapped_size;
 	idr_size = jd->machine->id_hdr_size;
 
 	/*
@@ -511,7 +533,8 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 			(sizeof(event->mmap2.filename) - size) + idr_size);
 	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
 	event->mmap2.start = jr->move.new_code_addr;
-	event->mmap2.len   = jr->move.code_size;
+	event->mmap2.len   = usize ? ALIGN_8(jr->move.code_size) + usize
+				   : jr->move.code_size;
 	event->mmap2.pid   = pid;
 	event->mmap2.tid   = tid;
 	event->mmap2.ino   = st.st_ino;
@@ -577,6 +600,31 @@ static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr)
 	return 0;
 }
 
+static int
+jit_repipe_unwinding_info(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	void *unwinding_data;
+	uint32_t unwinding_data_size;
+
+	if (!(jd && jr))
+		return -1;
+
+	unwinding_data_size  = jr->prefix.total_size - sizeof(jr->unwinding);
+	unwinding_data = malloc(unwinding_data_size);
+	if (!unwinding_data)
+		return -1;
+
+	memcpy(unwinding_data, &jr->unwinding.unwinding_data,
+	       unwinding_data_size);
+
+	jd->eh_frame_hdr_size = jr->unwinding.eh_frame_hdr_size;
+	jd->unwinding_size = jr->unwinding.unwinding_size;
+	jd->unwinding_mapped_size = jr->unwinding.mapped_size;
+	jd->unwinding_data = unwinding_data;
+
+	return 0;
+}
+
 static int
 jit_process_dump(struct jit_buf_desc *jd)
 {
@@ -594,6 +642,9 @@ jit_process_dump(struct jit_buf_desc *jd)
 		case JIT_CODE_DEBUG_INFO:
 			ret = jit_repipe_debug_info(jd, jr);
 			break;
+		case JIT_CODE_UNWINDING_INFO:
+			ret = jit_repipe_unwinding_info(jd, jr);
+			break;
 		default:
 			ret = 0;
 			continue;

tools/perf/util/jitdump.h

@@ -19,6 +19,7 @@
 #define JITHEADER_MAGIC_SW	0x4454694A
 
 #define PADDING_8ALIGNED(x) ((((x) + 7) & 7) ^ 7)
+#define ALIGN_8(x) (((x) + 7) & (~7))
 
 #define JITHEADER_VERSION 1
 
@@ -48,6 +49,7 @@ enum jit_record_type {
         JIT_CODE_MOVE           = 1,
 	JIT_CODE_DEBUG_INFO	= 2,
 	JIT_CODE_CLOSE		= 3,
+	JIT_CODE_UNWINDING_INFO	= 4,
 
 	JIT_CODE_MAX,
 };
@@ -101,12 +103,22 @@ struct jr_code_debug_info {
 	struct debug_entry entries[0];
 };
 
+struct jr_code_unwinding_info {
+	struct jr_prefix p;
+
+	uint64_t unwinding_size;
+	uint64_t eh_frame_hdr_size;
+	uint64_t mapped_size;
+	const char unwinding_data[0];
+};
+
 union jr_entry {
         struct jr_code_debug_info info;
         struct jr_code_close close;
         struct jr_code_load load;
         struct jr_code_move move;
         struct jr_prefix prefix;
+        struct jr_code_unwinding_info unwinding;
 };
 
 static inline struct debug_entry *