perf dso: Move read_symbol() from llvm/capstone to dso

Move the read_symbol function to dso.h, make the return type const and
add a mutable out_buf out parameter.

In future changes this will allow a code pointer to be returned without
necessary allocating memory.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Charlie Jenkins <charlie@rivosinc.com>
Cc: Collin Funk <collin.funk1@gmail.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Haibo Xu <haibo1.xu@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Li Huafei <lihuafei1@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Author: captain5050

tools/perf/util/capstone.c

@@ -215,69 +215,24 @@ static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg)
 }
 #endif
 
-#ifdef HAVE_LIBCAPSTONE_SUPPORT
-static u8 *
-read_symbol(const char *filename, struct map *map, struct symbol *sym,
-	    u64 *len, bool *is_64bit)
-{
-	struct dso *dso = map__dso(map);
-	struct nscookie nsc;
-	u64 start = map__rip_2objdump(map, sym->start);
-	u64 end = map__rip_2objdump(map, sym->end);
-	int fd, count;
-	u8 *buf = NULL;
-	struct find_file_offset_data data = {
-		.ip = start,
-	};
-
-	*is_64bit = false;
-
-	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
-	fd = open(filename, O_RDONLY);
-	nsinfo__mountns_exit(&nsc);
-	if (fd < 0)
-		return NULL;
-
-	if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data,
-			    is_64bit) == 0)
-		goto err;
-
-	*len = end - start;
-	buf = malloc(*len);
-	if (buf == NULL)
-		goto err;
-
-	count = pread(fd, buf, *len, data.offset);
-	close(fd);
-	fd = -1;
-
-	if ((u64)count != *len)
-		goto err;
-
-	return buf;
-
-err:
-	if (fd >= 0)
-		close(fd);
-	free(buf);
-	return NULL;
-}
-#endif
-
 int symbol__disassemble_capstone(const char *filename __maybe_unused,
 				 struct symbol *sym __maybe_unused,
 				 struct annotate_args *args __maybe_unused)
 {
 #ifdef HAVE_LIBCAPSTONE_SUPPORT
 	struct annotation *notes = symbol__annotation(sym);
 	struct map *map = args->ms.map;
+	struct dso *dso = map__dso(map);
 	u64 start = map__rip_2objdump(map, sym->start);
-	u64 len;
 	u64 offset;
 	int i, count, free_count;
 	bool is_64bit = false;
 	bool needs_cs_close = false;
-	u8 *buf = NULL;
+	/* Malloc-ed buffer containing instructions read from disk. */
+	u8 *code_buf = NULL;
+	/* Pointer to code to be disassembled. */
+	const u8 *buf;
+	u64 buf_len;
 	csh handle;
 	cs_insn *insn = NULL;
 	char disasm_buf[512];
@@ -287,7 +242,8 @@ int symbol__disassemble_capstone(const char *filename __maybe_unused,
 	if (args->options->objdump_path)
 		return -1;
 
-	buf = read_symbol(filename, map, sym, &len, &is_64bit);
+	buf = dso__read_symbol(dso, filename, map, sym,
+			       &code_buf, &buf_len, &is_64bit);
 	if (buf == NULL)
 		return -1;
 
@@ -316,7 +272,7 @@ int symbol__disassemble_capstone(const char *filename __maybe_unused,
 
 	needs_cs_close = true;
 
-	free_count = count = cs_disasm(handle, buf, len, start, len, &insn);
+	free_count = count = cs_disasm(handle, buf, buf_len, start, buf_len, &insn);
 	for (i = 0, offset = 0; i < count; i++) {
 		int printed;
 
@@ -340,7 +296,7 @@ int symbol__disassemble_capstone(const char *filename __maybe_unused,
 	}
 
 	/* It failed in the middle: probably due to unknown instructions */
-	if (offset != len) {
+	if (offset != buf_len) {
 		struct list_head *list = &notes->src->source;
 
 		/* Discard all lines and fallback to objdump */
@@ -359,7 +315,7 @@ int symbol__disassemble_capstone(const char *filename __maybe_unused,
 		if (free_count > 0)
 			cs_free(insn, free_count);
 	}
-	free(buf);
+	free(code_buf);
 	return count < 0 ? count : 0;
 
 err:

tools/perf/util/dso.c

@@ -1798,3 +1798,70 @@ bool is_perf_pid_map_name(const char *dso_name)
 
 	return perf_pid_map_tid(dso_name, &tid);
 }
+
+struct find_file_offset_data {
+	u64 ip;
+	u64 offset;
+};
+
+/* This will be called for each PHDR in an ELF binary */
+static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg)
+{
+	struct find_file_offset_data *data = arg;
+
+	if (start <= data->ip && data->ip < start + len) {
+		data->offset = pgoff + data->ip - start;
+		return 1;
+	}
+	return 0;
+}
+
+const u8 *dso__read_symbol(struct dso *dso, const char *symfs_filename,
+			   const struct map *map, const struct symbol *sym,
+			   u8 **out_buf, u64 *out_buf_len, bool *is_64bit)
+{
+	struct nscookie nsc;
+	u64 start = map__rip_2objdump(map, sym->start);
+	u64 end = map__rip_2objdump(map, sym->end);
+	int fd, count;
+	u8 *buf = NULL;
+	size_t len;
+	struct find_file_offset_data data = {
+		.ip = start,
+	};
+
+	*out_buf = NULL;
+	*out_buf_len = 0;
+	*is_64bit = false;
+
+	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
+	fd = open(symfs_filename, O_RDONLY);
+	nsinfo__mountns_exit(&nsc);
+	if (fd < 0)
+		return NULL;
+
+	if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data, is_64bit) == 0)
+		goto err;
+
+	len = end - start;
+	buf = malloc(len);
+	if (buf == NULL)
+		goto err;
+
+	count = pread(fd, buf, len, data.offset);
+	close(fd);
+	fd = -1;
+
+	if ((u64)count != len)
+		goto err;
+
+	*out_buf = buf;
+	*out_buf_len = len;
+	return buf;
+
+err:
+	if (fd >= 0)
+		close(fd);
+	free(buf);
+	return NULL;
+}

tools/perf/util/dso.h

@@ -924,4 +924,8 @@ static inline struct debuginfo *dso__debuginfo(struct dso *dso)
 	return debuginfo__new(dso__long_name(dso));
 }
 
+const u8 *dso__read_symbol(struct dso *dso, const char *symfs_filename,
+			   const struct map *map, const struct symbol *sym,
+			   u8 **out_buf, u64 *out_buf_len, bool *is_64bit);
+
 #endif /* __PERF_DSO */

tools/perf/util/llvm.c

@@ -87,71 +87,6 @@ static void init_llvm(void)
 	}
 }
 
-struct find_file_offset_data {
-	u64 ip;
-	u64 offset;
-};
-
-/* This will be called for each PHDR in an ELF binary */
-static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg)
-{
-	struct find_file_offset_data *data = arg;
-
-	if (start <= data->ip && data->ip < start + len) {
-		data->offset = pgoff + data->ip - start;
-		return 1;
-	}
-	return 0;
-}
-
-static u8 *
-read_symbol(const char *filename, struct map *map, struct symbol *sym,
-	    u64 *len, bool *is_64bit)
-{
-	struct dso *dso = map__dso(map);
-	struct nscookie nsc;
-	u64 start = map__rip_2objdump(map, sym->start);
-	u64 end = map__rip_2objdump(map, sym->end);
-	int fd, count;
-	u8 *buf = NULL;
-	struct find_file_offset_data data = {
-		.ip = start,
-	};
-
-	*is_64bit = false;
-
-	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
-	fd = open(filename, O_RDONLY);
-	nsinfo__mountns_exit(&nsc);
-	if (fd < 0)
-		return NULL;
-
-	if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data,
-			    is_64bit) == 0)
-		goto err;
-
-	*len = end - start;
-	buf = malloc(*len);
-	if (buf == NULL)
-		goto err;
-
-	count = pread(fd, buf, *len, data.offset);
-	close(fd);
-	fd = -1;
-
-	if ((u64)count != *len)
-		goto err;
-
-	return buf;
-
-err:
-	if (fd >= 0)
-		close(fd);
-	free(buf);
-	return NULL;
-}
-#endif
-
 /*
  * Whenever LLVM wants to resolve an address into a symbol, it calls this
  * callback. We don't ever actually _return_ anything (in particular, because
@@ -160,7 +95,6 @@ read_symbol(const char *filename, struct map *map, struct symbol *sym,
  * should add some textual annotation for after the instruction. The caller
  * will use this information to add the actual annotation.
  */
-#ifdef HAVE_LIBLLVM_SUPPORT
 struct symbol_lookup_storage {
 	u64 branch_addr;
 	u64 pcrel_load_addr;
@@ -191,8 +125,11 @@ int symbol__disassemble_llvm(const char *filename, struct symbol *sym,
 	struct map *map = args->ms.map;
 	struct dso *dso = map__dso(map);
 	u64 start = map__rip_2objdump(map, sym->start);
-	u8 *buf;
-	u64 len;
+	/* Malloc-ed buffer containing instructions read from disk. */
+	u8 *code_buf = NULL;
+	/* Pointer to code to be disassembled. */
+	const u8 *buf;
+	u64 buf_len;
 	u64 pc;
 	bool is_64bit;
 	char disasm_buf[2048];
@@ -207,7 +144,8 @@ int symbol__disassemble_llvm(const char *filename, struct symbol *sym,
 	if (args->options->objdump_path)
 		return -1;
 
-	buf = read_symbol(filename, map, sym, &len, &is_64bit);
+	buf = dso__read_symbol(dso, filename, map, sym,
+			       &code_buf, &buf_len, &is_64bit);
 	if (buf == NULL)
 		return -1;
 
@@ -259,14 +197,18 @@ int symbol__disassemble_llvm(const char *filename, struct symbol *sym,
 	annotation_line__add(&dl->al, &notes->src->source);
 
 	pc = start;
-	for (u64 offset = 0; offset < len; ) {
+	for (u64 offset = 0; offset < buf_len; ) {
 		unsigned int ins_len;
 
 		storage.branch_addr = 0;
 		storage.pcrel_load_addr = 0;
 
-		ins_len = LLVMDisasmInstruction(disasm, buf + offset,
-						len - offset, pc,
+		/*
+		 * LLVM's API has the code be disassembled as non-const, cast
+		 * here as we may be disassembling from mapped read-only memory.
+		 */
+		ins_len = LLVMDisasmInstruction(disasm, (u8 *)(buf + offset),
+						buf_len - offset, pc,
 						disasm_buf, sizeof(disasm_buf));
 		if (ins_len == 0)
 			goto err;
@@ -324,7 +266,7 @@ int symbol__disassemble_llvm(const char *filename, struct symbol *sym,
 
 err:
 	LLVMDisasmDispose(disasm);
-	free(buf);
+	free(code_buf);
 	free(line_storage);
 	return ret;
 #else // HAVE_LIBLLVM_SUPPORT