Message-ID: <1434636076-13502-1-git-send-email-houpengyang@huawei.com>
Date:	Thu, 18 Jun 2015 14:01:16 +0000
From:	Hou Pengyang <houpengyang@...wei.com>
To:	<acme@...nel.org>, <mingo@...hat.com>, <namhyung@...nel.org>,
	<a.p.zijlstra@...llo.nl>
CC:	<wangnan0@...wei.com>, <linux-kernel@...r.kernel.org>
Subject: [RFC] perf report: introduce --map-anon-mem for anon-executable-memory symbols parsing

This patch introduces a --map-anon-mem argument to perf report to deal
with anon-executable-memory symbol parsing.

Sometimes, we mmap() executable memory area, and copy some '.so' or '.o'
files to the area, and then do the relocation and code fixing to make the 
code work well. However, perf could not parse symbol info in those files,
since the memory area is not file-backended.

The problem was first discussed in :
    https://lkml.org/lkml/2015/4/1/203

In this discussion, we finally preferred to something like 'perf inject' 
to inject fake mmap events into perf.data. However, for embeded system 
whose space is limited, it's not so wise to make another big perf.data
by 'perf inject'. So we still adopt the previous solution: introduce 
'--map-anon-mem' argument and let user directly hint perf-report about
the private mapping info.

The content of this patch:
 1) A new field mapping_strlist is introduced to struct report, in order
    to store --map-anon-mem string for afterwards parsing.
 2) A new field maps_anon is introduced to struct map_groups. maps_anon is used
 	to store the maps user defines directly for anon-mapping. when searching maps
	in map_groups, we prefer to the maps stored in maps_anon.
 3) The main part of this patch resides in builtin-report.c and session.c.
    the part in builtin-report.c is charge of storing --map-anon-mem string,
    while the part in session.c parses the string, create maps, and store maps
    in map_groups->maps_anon.

Here is an example:
 $ perf report --map-anon-mem=./libtesta.o@257,0x7f864c0000,0x60,0 \
 				--map-anon-mem=./libtestb.o@257,0x7f864c0060,0x1000,0 

Where 257 is the pid and 0x76864c0000 is private map area got through:

    mmap(NULL, 4096 * 4, PROT_EXEC|PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE, \
          -1, 0);

and libtesta.o is copied to [0x7f864c0000,0x7f864c0060), 
	libtestb.o is copied to [0x7f864c0060,0x7f864c1060).

Signed-off-by: Wang Nan <wangnan0@...wei.com>
Signed-off-by: Hou Pengyang <houpengyang@...wei.com>
---
 tools/perf/Documentation/perf-report.txt |   8 +++
 tools/perf/builtin-report.c              |  39 +++++++++++
 tools/perf/util/map.c                    |   3 +-
 tools/perf/util/map.h                    |  10 ++-
 tools/perf/util/session.c                | 117 +++++++++++++++++++++++++++++++
 tools/perf/util/session.h                |   4 ++
 6 files changed, 178 insertions(+), 3 deletions(-)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index c33b69f..78df4eb 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -353,6 +353,15 @@ OPTIONS
 
 	To disable decoding entirely, use --no-itrace.
 
+--map-anon-mem=objfile@pid,start,length[,pgoff]::
+	Give memory layout hints for specific process. This makes
+	perf regard provided range of memory as mapped from provided
+	file instead of its original attributes found in perf.data.
+	pid is necessary, since mmap address is meaningless for other process.
+	start and length represent the address range. pgoff represent mapping
+	offset of that file, default value is 0 (map from start of the file).
+	pid should be decimal, while for start, length, and pgoff, both
+	decimal and hexadecimal are avaliable.
 
 include::callchain-overhead-calculation.txt[]
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 32626ea..5b6ea06 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -62,6 +62,7 @@ struct report {
 	u64			nr_entries;
 	u64			queue_size;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+	struct strlist		*mapping_strlist;
 };
 
 static int report__config(const char *var, const char *value, void *cb)
@@ -586,6 +587,32 @@ parse_percent_limit(const struct option *opt, const char *str,
 	return 0;
 }
 
+static int
+append_to_strlist(const struct option *opt, const char *str,
+		  int unset __maybe_unused)
+{
+	struct strlist **pslist = (struct strlist **)opt->value;
+	struct strlist *s;
+	int err;
+
+	if (!str)
+		return -1;
+
+	if (!*pslist)
+		*pslist = strlist__new(true, NULL);
+
+	s = *pslist;
+
+	if (!s) {
+		pr_err("No enough memory: can't alloc strlist\n");
+		return -ENOMEM;
+	}
+
+	err = strlist__add(s, str);
+	return err;
+}
+
+
 int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_session *session;
@@ -728,6 +755,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
 			    "Instruction Tracing options",
 			    itrace_parse_synth_opts),
+	OPT_CALLBACK_OPTARG(0, "map-anon-mem", &report.mapping_strlist, NULL,
+			    "objfile@pid,start,length[,offset]",
+			    "Provide map adjustment hinting",
+			    append_to_strlist),
 	OPT_END()
 	};
 	struct perf_data_file file = {
@@ -767,6 +798,14 @@ repeat:
 	if (session == NULL)
 		return -1;
 
+	if (perf_session__map_anon(session,
+				      report.mapping_strlist)) {
+		parse_options_usage(report_usage, options,
+				    "map-anon-mem", 0);
+		goto error;
+	}
+
+
 	if (report.queue_size) {
 		ordered_events__set_alloc_size(&session->ordered_events,
 					       report.queue_size);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 1241ab9..3118ad9 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -448,6 +448,7 @@ void map_groups__init(struct map_groups *mg, struct machine *machine)
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
 		maps__init(&mg->maps[i]);
 	}
+	maps__init(&mg->maps_anon);
 	mg->machine = machine;
 	atomic_set(&mg->refcnt, 1);
 }
@@ -662,7 +663,7 @@ size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 	return printed + map_groups__fprintf_removed_maps(mg, fp);
 }
 
-static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
+int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 {
 	struct rb_root *root;
 	struct rb_node *next;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index b8df09d..d804910 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -67,6 +67,7 @@ struct maps {
 };
 
 struct map_groups {
+	struct maps	 maps_anon;
 	struct maps	 maps[MAP__NR_TYPES];
 	struct machine	 *machine;
 	atomic_t	 refcnt;
@@ -183,6 +184,8 @@ void maps__insert(struct maps *maps, struct map *map);
 void maps__remove(struct maps *maps, struct map *map);
 struct map *maps__find(struct maps *maps, u64 addr);
 struct map *maps__first(struct maps *maps);
+int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp);
+
 struct map *map__next(struct map *map);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
@@ -207,7 +210,11 @@ static inline void map_groups__remove(struct map_groups *mg, struct map *map)
 static inline struct map *map_groups__find(struct map_groups *mg,
 					   enum map_type type, u64 addr)
 {
-	return maps__find(&mg->maps[type], addr);
+	struct map *map = NULL;
+
+	if (type == MAP__FUNCTION)
+		map = maps__find(&mg->maps_anon, addr);
+	return map ? map : maps__find(&mg->maps[type], addr);
 }
 
 static inline struct map *map_groups__first(struct map_groups *mg,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f31e024..3e3a7e5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1999,3 +1999,120 @@ out_err:
 
 	return err;
 }
+
+static int
+parse_map_anon_mem(const char *str, char *path,
+		  int *p_pid, u64 *p_addr, u64 *p_length,
+		  u64 *p_offset)
+{
+	char *sep, *pos;
+	int path_sz;
+
+	path[0] = '\0';
+	*p_pid = -1;
+	*p_addr = *p_length = *p_offset = 0;
+
+	sep = strchr(str, '@');
+	if (!sep)
+		return -1;
+
+	path_sz = sep - str;
+	strncpy(path, str, path_sz >= PATH_MAX ? PATH_MAX : path_sz);
+	path[PATH_MAX - 1] = '\0';
+	if (path_sz < PATH_MAX)
+		path[path_sz] = '\0';
+
+	/* skip '@' */
+	pos = sep + 1;
+	if (*pos == '\0')
+		return -1;
+
+	*p_pid = strtol(pos, &sep, 10);
+	if (*sep != ',')
+		return -1;
+
+	pos = sep + 1;
+	if (!strncmp(pos,"0x",2) || !strncmp(pos,"0X",2))
+		*p_addr = strtoll(pos, &sep, 16);
+	else
+		*p_addr = strtoll(pos, &sep, 10);
+	if (*sep != ',')
+		return -1;
+
+	pos = sep + 1;
+	if (!strncmp(pos,"0x",2) || !strncmp(pos,"0X",2))
+		*p_length = strtoll(pos, &sep, 16);
+	else
+		*p_length = strtoll(pos, &sep, 10);
+	if (*sep == '\0')
+		return 0;
+	if (*sep != ',')
+		return -1;
+
+	pos = sep + 1;
+	if (!strncmp(pos,"0x",2) || !strncmp(pos,"0X",2))
+		*p_offset = strtoll(pos, &sep, 16);
+	else
+		*p_offset = strtoll(pos, &sep, 10);
+	if (*sep != '\0')
+		return -1;
+	return 0;
+}
+
+static int
+__perf_session__map_anon(struct perf_session *session, int pid,
+			    char *path, u64 addr, u64 length,
+			    u64 offset)
+{
+	struct thread *thread;
+	struct map *map;
+	int err = -1;
+
+	thread = perf_session__findnew(session, pid);
+	if (!thread)
+		return -1;
+
+	map = map__new(&session->machines.host, addr, length, offset,
+		       pid, 0, 0, 0, 0, PROT_READ | PROT_EXEC, 0, path,
+		       MAP__FUNCTION, thread);
+	if (!map)
+		goto out;
+
+	maps__fixup_overlappings(&thread->mg->maps_anon, map, stderr);
+	maps__insert(&thread->mg->maps_anon, map);
+	map->groups = thread->mg;
+
+	err = 0;
+out:
+	thread__put(thread);
+	return err;
+}
+
+int perf_session__map_anon(struct perf_session *session,
+			      struct strlist *slist)
+{
+	struct str_node *node;
+	int err;
+
+	if (!slist)
+		return 0;
+
+	strlist__for_each(node, slist) {
+		int pid;
+		u64 addr, length, offset;
+		const char *map_anon_cmd = node->s;
+		char path[PATH_MAX];
+
+		if (parse_map_anon_mem(map_anon_cmd, path,
+				      &pid, &addr, &length, &offset))
+			return -1;
+
+		err = __perf_session__map_anon(session,
+						  pid, path, addr,
+						  length, offset);
+		if (err)
+			return -1;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index b44afc7..8df4632 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -9,6 +9,7 @@
 #include "thread.h"
 #include "data.h"
 #include "ordered-events.h"
+#include "strlist.h"
 #include <linux/rbtree.h>
 #include <linux/perf_event.h>
 
@@ -101,6 +102,9 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
+int perf_session__map_anon(struct perf_session *session,
+			      struct strlist *slist);
+
 void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 			  struct addr_location *al,
 			  unsigned int print_opts, unsigned int stack_depth);
-- 
1.8.5.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists