[PATCH v4] perf inject: Add a command line option to specify build ids.

[Raul Silvera]

This commit adds the option --known-build-ids to perf inject.
It allows the user to explicitly specify the build id for a given
path, instead of retrieving it from the current system. This is
useful in cases where a perf.data file is processed on a different
system from where it was collected, or if some of the binaries are
no longer available.

The build ids and paths are specified in pairs in the command line.
Using the file:// specifier, build ids can be loaded from a file
directly generated by perf buildid-list. This is convenient to copy
build ids from one perf.data file to another.

** Example: In this example we use perf record to create two
perf.data files, one with build ids and another without, and use
perf buildid-list and perf inject to copy the build ids from the
first file to the second.

 $ perf record ls /tmp
 $ perf record --no-buildid -o perf.data.no-buildid ls /tmp
 $ perf buildid-list > build-ids.txt
 $ perf inject -b --known-build-ids='file://build-ids.txt' \
        -i perf.data.no-buildid -o perf.data.buildid

Signed-off-by: Raul Silvera <rsilvera@xxxxxxxxxx>
---

  V3 -> V4: Perform upfront validation of build ids
  V2 -> V3: Added documentation and removed unnecessary temps
  V1 -> V2: Cleaned up patch description, deleted the strlist during
            cleanup, and updated validation of the build id strings
	    
 tools/perf/Documentation/perf-inject.txt |  7 +-
 tools/perf/builtin-inject.c              | 85 ++++++++++++++++++++++++
 2 files changed, 91 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index ffc293fdf61d..70e2ac3cc91a 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -27,9 +27,14 @@ OPTIONS
 --build-ids::
         Inject build-ids into the output stream
 
---buildid-all:
+--buildid-all::
 	Inject build-ids of all DSOs into the output stream
 
+--known-build-ids=::
+	Override build-ids to inject using these comma-separated pairs of
+	build-id and path. Understands file://filename to read these pairs
+	from a file, which can be generated with perf buildid-list.
+
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 2a0f992ca0be..8ec955402488 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -21,6 +21,7 @@
 #include "util/data.h"
 #include "util/auxtrace.h"
 #include "util/jit.h"
+#include "util/string2.h"
 #include "util/symbol.h"
 #include "util/synthetic-events.h"
 #include "util/thread.h"
@@ -38,6 +39,7 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 #include <linux/hash.h>
+#include <ctype.h>
 #include <errno.h>
 #include <signal.h>
 #include <inttypes.h>
@@ -123,6 +125,7 @@ struct perf_inject {
 	char			event_copy[PERF_SAMPLE_MAX_SIZE];
 	struct perf_file_section secs[HEADER_FEAT_BITS];
 	struct guest_session	guest_session;
+	struct strlist		*known_build_ids;
 };
 
 struct event_entry {
@@ -634,9 +637,73 @@ static int dso__read_build_id(struct dso *dso)
 	return dso->has_build_id ? 0 : -1;
 }
 
+static struct strlist *perf_inject__parse_known_build_ids(
+	const char *known_build_ids_string)
+{
+	struct str_node *pos, *tmp;
+	struct strlist *known_build_ids;
+	int bid_len;
+
+	known_build_ids = strlist__new(known_build_ids_string, NULL);
+	if (known_build_ids == NULL)
+		return NULL;
+	strlist__for_each_entry_safe(pos, tmp, known_build_ids) {
+		const char *build_id, *dso_name;
+
+		build_id = skip_spaces(pos->s);
+		dso_name = strchr(build_id, ' ');
+		if (dso_name == NULL) {
+			strlist__remove(known_build_ids, pos);
+			continue;
+		}
+		bid_len = dso_name - pos->s;
+		dso_name = skip_spaces(dso_name);
+		if (bid_len % 2 != 0 || bid_len >= SBUILD_ID_SIZE) {
+			strlist__remove(known_build_ids, pos);
+			continue;
+		}
+		for (int ix = 0; 2 * ix + 1 < bid_len; ++ix) {
+			if (!isxdigit(build_id[2 * ix]) ||
+			    !isxdigit(build_id[2 * ix + 1])) {
+				strlist__remove(known_build_ids, pos);
+				break;
+			}
+		}
+	}
+	return known_build_ids;
+}
+
+static bool perf_inject__lookup_known_build_id(struct perf_inject *inject,
+					       struct dso *dso)
+{
+	struct str_node *pos;
+	int bid_len;
+
+	strlist__for_each_entry(pos, inject->known_build_ids) {
+		const char *build_id, *dso_name;
+
+		build_id = skip_spaces(pos->s);
+		dso_name = strchr(build_id, ' ');
+		bid_len = dso_name - pos->s;
+		dso_name = skip_spaces(dso_name);
+		if (strcmp(dso->long_name, dso_name))
+			continue;
+		for (int ix = 0; 2 * ix + 1 < bid_len; ++ix) {
+			dso->bid.data[ix] = (hex(build_id[2 * ix]) << 4 |
+					     hex(build_id[2 * ix + 1]));
+		}
+		dso->bid.size = bid_len / 2;
+		dso->has_build_id = 1;
+		return true;
+	}
+	return false;
+}
+
 static int dso__inject_build_id(struct dso *dso, struct perf_tool *tool,
 				struct machine *machine, u8 cpumode, u32 flags)
 {
+	struct perf_inject *inject = container_of(tool, struct perf_inject,
+						  tool);
 	int err;
 
 	if (is_anon_memory(dso->long_name) || flags & MAP_HUGETLB)
@@ -644,6 +711,10 @@ static int dso__inject_build_id(struct dso *dso, struct perf_tool *tool,
 	if (is_no_dso_memory(dso->long_name))
 		return 0;
 
+	if (inject->known_build_ids != NULL &&
+	    perf_inject__lookup_known_build_id(inject, dso))
+		return 1;
+
 	if (dso__read_build_id(dso) < 0) {
 		pr_debug("no build_id found for %s\n", dso->long_name);
 		return -1;
@@ -2112,12 +2183,16 @@ int cmd_inject(int argc, const char **argv)
 	};
 	int ret;
 	bool repipe = true;
+	const char *known_build_ids = NULL;
 
 	struct option options[] = {
 		OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
 			    "Inject build-ids into the output stream"),
 		OPT_BOOLEAN(0, "buildid-all", &inject.build_id_all,
 			    "Inject build-ids of all DSOs into the output stream"),
+		OPT_STRING(0, "known-build-ids", &known_build_ids,
+			   "buildid path [,buildid path...]",
+			   "build-ids to use for given paths"),
 		OPT_STRING('i', "input", &inject.input_name, "file",
 			   "input file name"),
 		OPT_STRING('o', "output", &inject.output.path, "file",
@@ -2257,6 +2332,15 @@ int cmd_inject(int argc, const char **argv)
 		 */
 		inject.tool.ordered_events = true;
 		inject.tool.ordering_requires_timestamps = true;
+		if (known_build_ids != NULL) {
+			inject.known_build_ids =
+				perf_inject__parse_known_build_ids(known_build_ids);
+
+			if (inject.known_build_ids == NULL) {
+				pr_err("Couldn't parse known build ids.\n");
+				goto out_delete;
+			}
+		}
 	}
 
 	if (inject.sched_stat) {
@@ -2285,6 +2369,7 @@ int cmd_inject(int argc, const char **argv)
 	guest_session__exit(&inject.guest_session);
 
 out_delete:
+	strlist__delete(inject.known_build_ids);
 	zstd_fini(&(inject.session->zstd_data));
 	perf_session__delete(inject.session);
 out_close_output:
-- 
2.37.1.595.g718a3a8f04-goog