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>

1 files changed, 77 insertions, 5 deletions

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 8a0bca55106f..df237c3a041b 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);