perf symbols: Add symfs option for off-box analysis using specified tree

The symfs argument allows analysis of perf.data file using a locally accessible
filesystem tree with debug symbols - e.g., tree created during image builds,
sshfs mount, loop mounted KVM disk images, USB keys, initrds, etc. Anything
with an OS tree can be analyzed from anywhere without the need to populate a
local data store with build-ids.

Commiter notes:

o Fixed up symfs="/" variants handling.

o prefixed DSO__ORIG_GUEST_KMODULE case with symfs too, avoiding use of files
  outside the symfs directory.

LKML-Reference: <1291926427-28846-1-git-send-email-daahern@cisco.com>
Signed-off-by: David Ahern <daahern@cisco.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 6a9ec2b..74d7481 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -66,6 +66,8 @@
 --force::
        Don't complain, do it.
 
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index fefea77..8ba03d6 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -116,6 +116,9 @@
 --force::
         Don't complain, do it.
 
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1]
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 4b17883..d7b79e2 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -38,6 +38,8 @@
 --process::
         Select the processes to display, by name or PID
 
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
 
 SEE ALSO
 --------
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 97846dc..3153e49 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -194,6 +194,8 @@
 	OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
 		   "separator for columns, no spaces will be added between "
 		   "columns '.' is reserved."),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		    "Look for files with symbols relative to this directory"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 4af7ce6..75183a4 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -483,6 +483,8 @@
 		   "columns '.' is reserved."),
 	OPT_BOOLEAN('U', "hide-unresolved", &hide_unresolved,
 		    "Only display entries resolved to a symbol"),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		    "Look for files with symbols relative to this directory"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 459b5e3..d75084b 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1022,6 +1022,8 @@
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		    "Look for files with symbols relative to this directory"),
 	OPT_END()
 };
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index a3b8416..d503670 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1092,6 +1092,12 @@
 	FILE *file;
 	int err = 0;
 	u64 len;
+	char symfs_filename[PATH_MAX];
+
+	if (filename) {
+		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+			 symbol_conf.symfs, filename);
+	}
 
 	if (filename == NULL) {
 		if (dso->has_build_id) {
@@ -1100,9 +1106,9 @@
 			return -ENOMEM;
 		}
 		goto fallback;
-	} else if (readlink(filename, command, sizeof(command)) < 0 ||
+	} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
 		   strstr(command, "[kernel.kallsyms]") ||
-		   access(filename, R_OK)) {
+		   access(symfs_filename, R_OK)) {
 		free(filename);
 fallback:
 		/*
@@ -1111,6 +1117,8 @@
 		 * DSO is the same as when 'perf record' ran.
 		 */
 		filename = dso->long_name;
+		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+			 symbol_conf.symfs, filename);
 		free_filename = false;
 	}
 
@@ -1137,7 +1145,7 @@
 		 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS -C %s|grep -v %s|expand",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
-		 filename, filename);
+		 symfs_filename, filename);
 
 	pr_debug("Executing: %s\n", command);
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ceefa65..561db63 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -41,6 +41,7 @@
 	.exclude_other	  = true,
 	.use_modules	  = true,
 	.try_vmlinux_path = true,
+	.symfs            = "",
 };
 
 int dso__name_len(const struct dso *self)
@@ -839,8 +840,11 @@
 	char sympltname[1024];
 	Elf *elf;
 	int nr = 0, symidx, fd, err = 0;
+	char name[PATH_MAX];
 
-	fd = open(self->long_name, O_RDONLY);
+	snprintf(name, sizeof(name), "%s%s",
+		 symbol_conf.symfs, self->long_name);
+	fd = open(name, O_RDONLY);
 	if (fd < 0)
 		goto out;
 
@@ -1452,16 +1456,19 @@
 	     self->origin++) {
 		switch (self->origin) {
 		case DSO__ORIG_BUILD_ID_CACHE:
-			if (dso__build_id_filename(self, name, size) == NULL)
+			/* skip the locally configured cache if a symfs is given */
+			if (symbol_conf.symfs[0] ||
+			    (dso__build_id_filename(self, name, size) == NULL)) {
 				continue;
+			}
 			break;
 		case DSO__ORIG_FEDORA:
-			snprintf(name, size, "/usr/lib/debug%s.debug",
-				 self->long_name);
+			snprintf(name, size, "%s/usr/lib/debug%s.debug",
+				 symbol_conf.symfs, self->long_name);
 			break;
 		case DSO__ORIG_UBUNTU:
-			snprintf(name, size, "/usr/lib/debug%s",
-				 self->long_name);
+			snprintf(name, size, "%s/usr/lib/debug%s",
+				 symbol_conf.symfs, self->long_name);
 			break;
 		case DSO__ORIG_BUILDID: {
 			char build_id_hex[BUILD_ID_SIZE * 2 + 1];
@@ -1473,19 +1480,26 @@
 					  sizeof(self->build_id),
 					  build_id_hex);
 			snprintf(name, size,
-				 "/usr/lib/debug/.build-id/%.2s/%s.debug",
-				 build_id_hex, build_id_hex + 2);
+				 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
+				 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
 			}
 			break;
 		case DSO__ORIG_DSO:
-			snprintf(name, size, "%s", self->long_name);
+			snprintf(name, size, "%s%s",
+			     symbol_conf.symfs, self->long_name);
 			break;
 		case DSO__ORIG_GUEST_KMODULE:
 			if (map->groups && map->groups->machine)
 				root_dir = map->groups->machine->root_dir;
 			else
 				root_dir = "";
-			snprintf(name, size, "%s%s", root_dir, self->long_name);
+			snprintf(name, size, "%s%s%s", symbol_conf.symfs,
+				 root_dir, self->long_name);
+			break;
+
+		case DSO__ORIG_KMODULE:
+			snprintf(name, size, "%s%s", symbol_conf.symfs,
+				 self->long_name);
 			break;
 
 		default:
@@ -1784,17 +1798,20 @@
 			     const char *vmlinux, symbol_filter_t filter)
 {
 	int err = -1, fd;
+	char symfs_vmlinux[PATH_MAX];
 
-	fd = open(vmlinux, O_RDONLY);
+	snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s/%s",
+		 symbol_conf.symfs, vmlinux);
+	fd = open(symfs_vmlinux, O_RDONLY);
 	if (fd < 0)
 		return -1;
 
 	dso__set_loaded(self, map->type);
-	err = dso__load_sym(self, map, vmlinux, fd, filter, 0, 0);
+	err = dso__load_sym(self, map, symfs_vmlinux, fd, filter, 0, 0);
 	close(fd);
 
 	if (err > 0)
-		pr_debug("Using %s for symbols\n", vmlinux);
+		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 
 	return err;
 }
@@ -1872,6 +1889,10 @@
 			goto out_fixup;
 	}
 
+	/* do not try local files if a symfs was given */
+	if (symbol_conf.symfs[0] != 0)
+		return -1;
+
 	/*
 	 * Say the kernel DSO was created when processing the build-id header table,
 	 * we have a build-id, so check if it is the same as the running kernel,
@@ -2262,9 +2283,6 @@
 	struct utsname uts;
 	char bf[PATH_MAX];
 
-	if (uname(&uts) < 0)
-		return -1;
-
 	vmlinux_path = malloc(sizeof(char *) * 5);
 	if (vmlinux_path == NULL)
 		return -1;
@@ -2277,6 +2295,14 @@
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
 		goto out_fail;
 	++vmlinux_path__nr_entries;
+
+	/* only try running kernel version if no symfs was given */
+	if (symbol_conf.symfs[0] != 0)
+		return 0;
+
+	if (uname(&uts) < 0)
+		return -1;
+
 	snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release);
 	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
@@ -2336,6 +2362,8 @@
 
 int symbol__init(void)
 {
+	const char *symfs;
+
 	if (symbol_conf.initialized)
 		return 0;
 
@@ -2364,6 +2392,18 @@
 		       symbol_conf.sym_list_str, "symbol") < 0)
 		goto out_free_comm_list;
 
+	/*
+	 * A path to symbols of "/" is identical to ""
+	 * reset here for simplicity.
+	 */
+	symfs = realpath(symbol_conf.symfs, NULL);
+	if (symfs == NULL)
+		symfs = symbol_conf.symfs;
+	if (strcmp(symfs, "/") == 0)
+		symbol_conf.symfs = "";
+	if (symfs != symbol_conf.symfs)
+		free((void *)symfs);
+
 	symbol_conf.initialized = true;
 	return 0;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 12defbe..bcd2f98 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -86,6 +86,7 @@
        struct strlist	*dso_list,
 			*comm_list,
 			*sym_list;
+	const char	*symfs;
 };
 
 extern struct symbol_conf symbol_conf;