perf record: Introduce a symtab cache

Now a cache will be created in a ~/.debug debuginfo like
hierarchy, so that at the end of a 'perf record' session all the
binaries (with build-ids) involved get collected and indexed by
their build-ids, so that perf report can find them.

This is interesting when developing software where you want to
do a 'perf diff' with the previous build and opens avenues for
lots more interesting tools, like a 'perf diff --graph' that
takes more than two binaries into account.

Tunables for collecting just the symtabs can be added if one
doesn't want to have the full binary, but having the full binary
allows things like 'perf rerecord' or other tools that can
re-run the tests by having access to the exact binary in some
perf.data file, so it may well be interesting to keep the full
binary there.

Space consumption is minimised by trying to use hard links, a
'perf cache' tool to manage the space used, a la ccache is
required to purge older entries.

With this in place it will be possible also to introduce new
commands, 'perf archive' and 'perf restore' (or some more
suitable and future proof names) to create a cpio/tar file with
the perf data and the files in the cache that _had_ perf hits of
interest.

There are more aspects to polish, like finding the right vmlinux
file to cache, etc, but this is enough for a first step.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1261957026-15580-10-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

6 files changed, 165 insertions, 9 deletions

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index fafea0b..7c84642 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -425,6 +425,7 @@ LIB_OBJS += util/svghelper.o
 LIB_OBJS += util/sort.o
 LIB_OBJS += util/hist.o
 LIB_OBJS += util/probe-event.o
+LIB_OBJS += util/util.o
 
 BUILTIN_OBJS += builtin-annotate.o
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 8a0bca5..df237c3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -169,20 +169,23 @@ static int do_write(int fd, const void *buf, size_t size)
 	return 0;
 }
 
+#define dsos__for_each_with_build_id(pos, head)	\
+	list_for_each_entry(pos, head, node)	\
+		if (!pos->has_build_id)		\
+			continue;		\
+		else
+
 static int __dsos__write_buildid_table(struct list_head *head, int fd)
 {
 #define NAME_ALIGN	64
 	struct dso *pos;
 	static const char zero_buf[NAME_ALIGN];
 
-	list_for_each_entry(pos, head, node) {
+	dsos__for_each_with_build_id(pos, head) {
 		int err;
 		struct build_id_event b;
-		size_t len;
+		size_t len = pos->long_name_len + 1;
 
-		if (!pos->has_build_id)
-			continue;
-		len = pos->long_name_len + 1;
 		len = ALIGN(len, NAME_ALIGN);
 		memset(&b, 0, sizeof(b));
 		memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id));
@@ -209,6 +212,74 @@ static int dsos__write_buildid_table(int fd)
 	return err;
 }
 
+static int dso__cache_build_id(struct dso *self, const char *debugdir)
+{
+	const size_t size = PATH_MAX;
+	char *filename = malloc(size),
+	     *linkname = malloc(size), *targetname, *sbuild_id;
+	int len, err = -1;
+
+	if (filename == NULL || linkname == NULL)
+		goto out_free;
+
+	len = snprintf(filename, size, "%s%s", debugdir, self->long_name);
+	if (mkdir_p(filename, 0755))
+		goto out_free;
+
+	len += snprintf(filename + len, sizeof(filename) - len, "/");
+	sbuild_id = filename + len;
+	build_id__sprintf(self->build_id, sizeof(self->build_id), sbuild_id);
+
+	if (access(filename, F_OK) && link(self->long_name, filename) &&
+	    copyfile(self->long_name, filename))
+		goto out_free;
+
+	len = snprintf(linkname, size, "%s/.build-id/%.2s",
+		       debugdir, sbuild_id);
+
+	if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
+		goto out_free;
+
+	snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
+	targetname = filename + strlen(debugdir) - 5;
+	memcpy(targetname, "../..", 5);
+
+	if (symlink(targetname, linkname) == 0)
+		err = 0;
+out_free:
+	free(filename);
+	free(linkname);
+	return err;
+}
+
+static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
+{
+	struct dso *pos;
+	int err = 0;
+
+	dsos__for_each_with_build_id(pos, head)
+		if (dso__cache_build_id(pos, debugdir))
+			err = -1;
+
+	return err;
+}
+
+static int dsos__cache_build_ids(void)
+{
+	int err_kernel, err_user;
+	char debugdir[PATH_MAX];
+
+	snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
+		 DEBUG_CACHE_DIR);
+
+	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
+		return -1;
+
+	err_kernel = __dsos__cache_build_ids(&dsos__kernel, debugdir);
+	err_user   = __dsos__cache_build_ids(&dsos__user, debugdir);
+	return err_kernel || err_user ? -1 : 0;
+}
+
 static int perf_header__adds_write(struct perf_header *self, int fd)
 {
 	int nr_sections;
@@ -258,6 +329,7 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
 			goto out_free;
 		}
 		buildid_sec->size = lseek(fd, 0, SEEK_CUR) - buildid_sec->offset;
+		dsos__cache_build_ids();
 	}
 
 	lseek(fd, sec_start, SEEK_SET);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ab92763..79ca6a0 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -22,6 +22,7 @@
 enum dso_origin {
 	DSO__ORIG_KERNEL = 0,
 	DSO__ORIG_JAVA_JIT,
+	DSO__ORIG_BUILD_ID_CACHE,
 	DSO__ORIG_FEDORA,
 	DSO__ORIG_UBUNTU,
 	DSO__ORIG_BUILDID,
@@ -1191,6 +1192,7 @@ char dso__symtab_origin(const struct dso *self)
 	static const char origin[] = {
 		[DSO__ORIG_KERNEL] =   'k',
 		[DSO__ORIG_JAVA_JIT] = 'j',
+		[DSO__ORIG_BUILD_ID_CACHE] = 'B',
 		[DSO__ORIG_FEDORA] =   'f',
 		[DSO__ORIG_UBUNTU] =   'u',
 		[DSO__ORIG_BUILDID] =  'b',
@@ -1209,6 +1211,7 @@ int dso__load(struct dso *self, struct map *map, struct perf_session *session,
 	int size = PATH_MAX;
 	char *name;
 	u8 build_id[BUILD_ID_SIZE];
+	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 	int ret = -1;
 	int fd;
 
@@ -1230,8 +1233,16 @@ int dso__load(struct dso *self, struct map *map, struct perf_session *session,
 		return ret;
 	}
 
-	self->origin = DSO__ORIG_FEDORA - 1;
+	self->origin = DSO__ORIG_BUILD_ID_CACHE;
 
+	if (self->has_build_id) {
+		build_id__sprintf(self->build_id, sizeof(self->build_id),
+				  build_id_hex);
+		snprintf(name, size, "%s/%s/.build-id/%.2s/%s",
+			 getenv("HOME"), DEBUG_CACHE_DIR,
+			 build_id_hex, build_id_hex + 2);
+		goto open_file;
+	}
 more:
 	do {
 		self->origin++;
@@ -1247,8 +1258,6 @@ more:
 		case DSO__ORIG_BUILDID:
 			if (filename__read_build_id(self->long_name, build_id,
 						    sizeof(build_id))) {
-				char build_id_hex[BUILD_ID_SIZE * 2 + 1];
-
 				build_id__sprintf(build_id, sizeof(build_id),
 						  build_id_hex);
 				snprintf(name, size,
@@ -1276,7 +1285,7 @@ compare_build_id:
 			if (!dso__build_id_equal(self, build_id))
 				goto more;
 		}
-
+open_file:
 		fd = open(name, O_RDONLY);
 	} while (fd < 0);
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 9eabd60..f27e158 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -8,6 +8,8 @@
 #include <linux/rbtree.h>
 #include "event.h"
 
+#define DEBUG_CACHE_DIR ".debug"
+
 #ifdef HAVE_CPLUS_DEMANGLE
 extern char *cplus_demangle(const char *, int);
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
new file mode 100644
index 0000000..f3c0798
--- /dev/null
+++ b/tools/perf/util/util.c
@@ -0,0 +1,69 @@
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include "util.h"
+
+int mkdir_p(char *path, mode_t mode)
+{
+	struct stat st;
+	int err;
+	char *d = path;
+
+	if (*d != '/')
+		return -1;
+
+	if (stat(path, &st) == 0)
+		return 0;
+
+	while (*++d == '/');
+
+	while ((d = strchr(d, '/'))) {
+		*d = '\0';
+		err = stat(path, &st) && mkdir(path, mode);
+		*d++ = '/';
+		if (err)
+			return -1;
+		while (*d == '/')
+			++d;
+	}
+	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
+}
+
+int copyfile(const char *from, const char *to)
+{
+	int fromfd, tofd;
+	struct stat st;
+	void *addr;
+	int err = -1;
+
+	if (stat(from, &st))
+		goto out;
+
+	fromfd = open(from, O_RDONLY);
+	if (fromfd < 0)
+		goto out;
+
+	tofd = creat(to, 0755);
+	if (tofd < 0)
+		goto out_close_from;
+
+	addr = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fromfd, 0);
+	if (addr == MAP_FAILED)
+		goto out_close_to;
+
+	if (write(tofd, addr, st.st_size) == st.st_size)
+		err = 0;
+
+	munmap(addr, st.st_size);
+out_close_to:
+	close(tofd);
+	if (err)
+		unlink(to);
+out_close_from:
+	close(fromfd);
+out:
+	return err;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c673d88..0f5b2a6 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -403,4 +403,7 @@ void git_qsort(void *base, size_t nmemb, size_t size,
 #endif
 #endif
 
+int mkdir_p(char *path, mode_t mode);
+int copyfile(const char *from, const char *to);
+
 #endif