perf symbol: Add command line support for addr2line path

Allow addr2line to be set either on the command line or via the
perfconfig file. This doesn't currently work with llvm-addr2line as
the addr2line code emits two things:
1) the address to decode,
2) a bogus ',' value.
The expectation is the bogus value will generate:
??
??:0
that terminates the addr2line reading. However, the output from
llvm-addr2line is a single line with just the input ',' locking up the
addr2line reading that is expecting a second line.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andres Freund <andres@anarazel.de>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Tom Rix <trix@redhat.com>
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230328235543.1082207-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-annotate.txt

@@ -116,6 +116,9 @@ include::itrace.txt[]
 -M::
 --disassembler-style=:: Set disassembler style for objdump.
 
+--addr2line=<path>::
+        Path to addr2line binary.
+
 --objdump=<path>::
         Path to objdump binary.
 

tools/perf/Documentation/perf-config.txt

@@ -250,6 +250,9 @@ annotate.*::
 	These are in control of addresses, jump function, source code
 	in lines of assembly code from a specific program.
 
+	annotate.addr2line::
+		addr2line binary to use for file names and line numbers.
+
 	annotate.objdump::
 		objdump binary to use for disassembly and annotations.
 

tools/perf/Documentation/perf-report.txt

@@ -381,6 +381,9 @@ OPTIONS
 	This allows to examine the path the program took to each sample.
 	The data collection must have used -b (or -j) and -g.
 
+--addr2line=<path>::
+        Path to addr2line binary.
+
 --objdump=<path>::
         Path to objdump binary.
 

tools/perf/Documentation/perf-top.txt

@@ -161,6 +161,12 @@ Default is to monitor all CPUS.
 -M::
 --disassembler-style=:: Set disassembler style for objdump.
 
+--addr2line=<path>::
+        Path to addr2line binary.
+
+--objdump=<path>::
+        Path to objdump binary.
+
 --prefix=PREFIX::
 --prefix-strip=N::
         Remove first N entries from source file path names in executables

tools/perf/builtin-annotate.c

@@ -517,7 +517,7 @@ int cmd_annotate(int argc, const char **argv)
 	struct itrace_synth_opts itrace_synth_opts = {
 		.set = 0,
 	};
-	const char *disassembler_style = NULL, *objdump_path = NULL;
+	const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL;
 	struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
@@ -570,6 +570,8 @@ int cmd_annotate(int argc, const char **argv)
 		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
+	OPT_STRING(0, "addr2line", &addr2line_path, "path",
+		   "addr2line binary to use for line numbers"),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
 		    "Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
@@ -629,6 +631,11 @@ int cmd_annotate(int argc, const char **argv)
 		if (!annotate.opts.objdump_path)
 			return -ENOMEM;
 	}
+	if (addr2line_path) {
+		symbol_conf.addr2line_path = strdup(addr2line_path);
+		if (!symbol_conf.addr2line_path)
+			return -ENOMEM;
+	}
 
 	if (annotate_check_args(&annotate.opts) < 0)
 		return -EINVAL;

tools/perf/builtin-report.c

@@ -1226,7 +1226,7 @@ int cmd_report(int argc, const char **argv)
 	};
 	char *sort_order_help = sort_help("sort by key(s):");
 	char *field_order_help = sort_help("output field(s): overhead period sample ");
-	const char *disassembler_style = NULL, *objdump_path = NULL;
+	const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL;
 	const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
@@ -1344,6 +1344,8 @@ int cmd_report(int argc, const char **argv)
 		    "add last branch records to call history"),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
+	OPT_STRING(0, "addr2line", &addr2line_path, "path",
+		   "addr2line binary to use for line numbers"),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
 		    "Disable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
@@ -1430,6 +1432,11 @@ int cmd_report(int argc, const char **argv)
 		if (!report.annotation_opts.objdump_path)
 			return -ENOMEM;
 	}
+	if (addr2line_path) {
+		symbol_conf.addr2line_path = strdup(addr2line_path);
+		if (!symbol_conf.addr2line_path)
+			return -ENOMEM;
+	}
 
 	if (annotate_check_args(&report.annotation_opts) < 0) {
 		ret = -EINVAL;

tools/perf/builtin-top.c

@@ -1439,7 +1439,7 @@ int cmd_top(int argc, const char **argv)
 	};
 	struct record_opts *opts = &top.record_opts;
 	struct target *target = &opts->target;
-	const char *disassembler_style = NULL, *objdump_path = NULL;
+	const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL;
 	const struct option options[] = {
 	OPT_CALLBACK('e', "event", &top.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
@@ -1527,6 +1527,8 @@ int cmd_top(int argc, const char **argv)
 	OPT_BOOLEAN(0, "no-bpf-event", &top.record_opts.no_bpf_event, "do not record bpf events"),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		    "objdump binary to use for disassembly and annotations"),
+	OPT_STRING(0, "addr2line", &addr2line_path, "path",
+		   "addr2line binary to use for line numbers"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix",
@@ -1629,7 +1631,11 @@ int cmd_top(int argc, const char **argv)
 		if (!top.annotation_opts.objdump_path)
 			return -ENOMEM;
 	}
-
+	if (addr2line_path) {
+		symbol_conf.addr2line_path = strdup(addr2line_path);
+		if (!symbol_conf.addr2line_path)
+			return -ENOMEM;
+	}
 
 	status = symbol__validate_sym_arguments();
 	if (status)

tools/perf/util/annotate.c

@@ -3217,6 +3217,12 @@ static int annotation__config(const char *var, const char *value, void *data)
 			pr_err("Not enough memory for annotate.objdump\n");
 			return -1;
 		}
+	} else if (!strcmp(var, "annotate.addr2line")) {
+		symbol_conf.addr2line_path = strdup(value);
+		if (!symbol_conf.addr2line_path) {
+			pr_err("Not enough memory for annotate.addr2line\n");
+			return -1;
+		}
 	} else if (!strcmp(var, "annotate.demangle")) {
 		symbol_conf.demangle = perf_config_bool("demangle", value);
 	} else if (!strcmp(var, "annotate.demangle_kernel")) {

tools/perf/util/srcline.c

@@ -414,9 +414,14 @@ static void addr2line_subprocess_cleanup(struct a2l_subprocess *a2l)
 	free(a2l);
 }
 
-static struct a2l_subprocess *addr2line_subprocess_init(const char *path)
+static struct a2l_subprocess *addr2line_subprocess_init(const char *addr2line_path,
+							const char *binary_path)
 {
-	const char *argv[] = { "addr2line", "-e", path, "-i", "-f", NULL };
+	const char *argv[] = {
+		addr2line_path ?: "addr2line",
+		"-e", binary_path,
+		"-i", "-f", NULL
+	};
 	struct a2l_subprocess *a2l = zalloc(sizeof(*a2l));
 	int start_command_status = 0;
 
@@ -436,21 +441,22 @@ static struct a2l_subprocess *addr2line_subprocess_init(const char *path)
 	a2l->addr2line.argv = NULL; /* it's not used after start_command; avoid dangling pointers */
 
 	if (start_command_status != 0) {
-		pr_warning("could not start addr2line for %s: start_command return code %d\n",
-			   path,
-			   start_command_status);
+		pr_warning("could not start addr2line (%s) for %s: start_command return code %d\n",
+			addr2line_path, binary_path, start_command_status);
 		goto out;
 	}
 
 	a2l->to_child = fdopen(a2l->addr2line.in, "w");
 	if (a2l->to_child == NULL) {
-		pr_warning("could not open write-stream to addr2line of %s\n", path);
+		pr_warning("could not open write-stream to addr2line (%s) of %s\n",
+			addr2line_path, binary_path);
 		goto out;
 	}
 
 	a2l->from_child = fdopen(a2l->addr2line.out, "r");
 	if (a2l->from_child == NULL) {
-		pr_warning("could not open read-stream from addr2line of %s\n", path);
+		pr_warning("could not open read-stream from addr2line (%s) of %s\n",
+			addr2line_path, binary_path);
 		goto out;
 	}
 
@@ -490,7 +496,6 @@ static int read_addr2line_record(struct a2l_subprocess *a2l,
 
 	if (getline(&line, &line_len, a2l->from_child) < 0 || !line_len)
 		goto error;
-
 	if (function != NULL)
 		*function = strdup(strim(line));
 
@@ -553,7 +558,8 @@ static int addr2line(const char *dso_name, u64 addr,
 		if (!filename__has_section(dso_name, ".debug_line"))
 			goto out;
 
-		dso->a2l = addr2line_subprocess_init(dso_name);
+		dso->a2l = addr2line_subprocess_init(symbol_conf.addr2line_path,
+						     dso_name);
 		a2l = dso->a2l;
 	}
 

tools/perf/util/symbol_conf.h

@@ -61,6 +61,7 @@ struct symbol_conf {
 			*sym_list_str,
 			*col_width_list_str,
 			*bt_stop_list_str;
+	char		*addr2line_path;
 	unsigned long	time_quantum;
        struct strlist	*dso_list,
 			*comm_list,