From: Alireza Haghdoost via B4 Relay <devnull+haghdoost.uber.com@kernel.org>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>, Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
James Clark <james.clark@linaro.org>,
Alexei Starovoitov <ast@kernel.org>,
Andrii Nakryiko <andriin@fb.com>
Cc: linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
Alireza Haghdoost <haghdoost@uber.com>
Subject: [PATCH v3 2/6] perf dso: Allow reading DSO data from an explicit file
Date: Fri, 25 Sep 2026 12:09:39 -0700 [thread overview]
Message-ID: <20260925-perf-symbol-memory-send-v3-2-3e4e234c363b@uber.com> (raw)
In-Reply-To: <20260925-perf-symbol-memory-send-v3-0-3e4e234c363b@uber.com>
From: Alireza Haghdoost <haghdoost@uber.com>
The DSO data cache derives the file to open from the DSO's binary type,
which can resolve to the runtime image rather than the file a symbol
table was read from. With split debuginfo, offsets taken from the
debuginfo file (for example string-table offsets) are then applied to an
unrelated file.
Add dso__data_set_path() so a DSO can be configured to read from one
exact file while keeping the data cache's descriptor eviction and
reopening. Such DSOs may be owned privately rather than being part of a
dsos collection, so drop the assertion that every opened data DSO is in
one.
Add a DSO data test that reads through an explicit path, closes the
descriptor, and reads an uncached offset to exercise reopening.
Signed-off-by: Alireza Haghdoost <haghdoost@uber.com>
---
tools/perf/tests/dso-data.c | 42 ++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/dso.c | 43 ++++++++++++++++++++++++++++++++++---------
tools/perf/util/dso.h | 2 ++
3 files changed, 78 insertions(+), 9 deletions(-)
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 46bc3f597260..fbfb2f08d3ba 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -393,11 +393,53 @@ static int test__dso_data_reopen(struct test_suite *test __maybe_unused, int sub
return 0;
}
+static int test__dso_data_path(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+ u8 expect[10] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 };
+ char *file = test_file(TEST_FILE_SIZE);
+ struct dso *dso;
+ long nr, nr_end;
+ u8 buf[10];
+
+ TEST_ASSERT_VAL("No test file", file);
+ nr = open_files_cnt();
+
+ /*
+ * The DSO name does not exist and the DSO is not in a dsos
+ * collection; reads must come from the configured path.
+ */
+ dso = dso__new("/nonexistent/perf-test-dso-data-path");
+ TEST_ASSERT_VAL("Failed to create dso", dso);
+ dso__set_binary_type(dso, DSO_BINARY_TYPE__SYSTEM_PATH_DSO);
+ TEST_ASSERT_VAL("Failed to set path", !dso__data_set_path(dso, file));
+
+ TEST_ASSERT_VAL("Wrong size",
+ dso__data_read_offset(dso, NULL, 10, buf, 10) == 10);
+ TEST_ASSERT_VAL("Wrong data", !memcmp(buf, expect, 10));
+
+ /* An uncached offset after close must reopen the configured path. */
+ dso__data_close(dso);
+ memset(buf, 0, sizeof(buf));
+ TEST_ASSERT_VAL("Wrong size after reopen",
+ dso__data_read_offset(dso, NULL, DSO__DATA_CACHE_SIZE * 2 + 10,
+ buf, 10) == 10);
+ TEST_ASSERT_VAL("Wrong data after reopen",
+ buf[0] == (DSO__DATA_CACHE_SIZE * 2 + 10) % 10);
+
+ dso__data_close(dso);
+ dso__put(dso);
+ unlink(file);
+
+ nr_end = open_files_cnt();
+ TEST_ASSERT_VAL("failed leaking files", nr == nr_end);
+ return 0;
+}
static struct test_case tests__dso_data[] = {
TEST_CASE("read", dso_data),
TEST_CASE("cache", dso_data_cache),
TEST_CASE("reopen", dso_data_reopen),
+ TEST_CASE("explicit path", dso_data_path),
{ .name = NULL, }
};
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 9e90de92fcfa..c88b2a771832 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -532,8 +532,6 @@ static void dso__list_add(struct dso *dso) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_o
#ifdef REFCNT_CHECKING
dso__data(dso)->dso = dso__get(dso);
#endif
- /* Assume the dso is part of dsos, hence the optional reference count above. */
- assert(dso__dsos(dso));
dso__data_open_cnt++;
}
@@ -578,16 +576,22 @@ char *dso__filename_with_chroot(const struct dso *dso, const char *filename)
static char *dso__get_filename(struct dso *dso, const char *root_dir,
bool *decomp)
{
- char *name = malloc(PATH_MAX);
+ char *name;
*decomp = false;
- if (name == NULL)
- return NULL;
-
- if (dso__read_binary_type_filename(dso, dso__binary_type(dso),
- root_dir, name, PATH_MAX))
- goto out;
+ if (dso__data(dso)->path) {
+ name = strdup(dso__data(dso)->path);
+ if (!name)
+ return NULL;
+ } else {
+ name = malloc(PATH_MAX);
+ if (!name)
+ return NULL;
+ if (dso__read_binary_type_filename(dso, dso__binary_type(dso),
+ root_dir, name, PATH_MAX))
+ goto out;
+ }
if (!is_regular_file(name)) {
struct stat st;
@@ -813,6 +817,26 @@ void dso__data_close(struct dso *dso)
mutex_unlock(dso__data_open_lock());
}
+/**
+ * dso__data_set_path - Read @dso's data from an explicit file
+ * @dso: dso object
+ * @path: file to open instead of the path derived from the binary type
+ *
+ * Used when the data must come from one specific file, such as the separate
+ * debuginfo file that a symbol table was read from. Must be called before any
+ * data is read, as already cached data is not invalidated.
+ */
+int dso__data_set_path(struct dso *dso, const char *path)
+{
+ char *new_path = strdup(path);
+
+ if (!new_path)
+ return -ENOMEM;
+ free(dso__data(dso)->path);
+ dso__data(dso)->path = new_path;
+ return 0;
+}
+
static void try_to_open_dso(struct dso *dso, struct machine *machine)
EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock)
{
@@ -1762,6 +1786,7 @@ void dso__delete(struct dso *dso)
dso__data_close(dso);
auxtrace_cache__free(RC_CHK_ACCESS(dso)->auxtrace_cache);
dso_cache__free(dso);
+ zfree(&RC_CHK_ACCESS(dso)->data.path);
dso__free_a2l(dso);
dso__free_a2l_libbfd(dso);
dso__free_libdw(dso);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index e7d5f4bbf894..ff2c91e9a2b9 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -264,6 +264,7 @@ struct dso_data {
#ifdef REFCNT_CHECKING
struct dso *dso;
#endif
+ char *path;
int fd;
int status;
u32 status_seen;
@@ -910,6 +911,7 @@ bool dso__data_get_fd(struct dso *dso, struct machine *machine, int *fd)
EXCLUSIVE_TRYLOCK_FUNCTION(true, _dso__data_open_lock);
void dso__data_put_fd(struct dso *dso) UNLOCK_FUNCTION(_dso__data_open_lock);
void dso__data_close(struct dso *dso) LOCKS_EXCLUDED(_dso__data_open_lock);
+int dso__data_set_path(struct dso *dso, const char *path);
int dso__data_file_size(struct dso *dso, struct machine *machine);
off_t dso__data_size(struct dso *dso, struct machine *machine);
--
Git-157)
next prev parent reply other threads:[~2026-09-25 19:15 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-25 19:09 [PATCH v3 0/6] perf script: Bounded and lazy symbol loading Alireza Haghdoost via B4 Relay
2026-09-25 19:09 ` [PATCH v3 1/6] perf symbols: Fix broken ELF_C_READ_MMAP fallback guard Alireza Haghdoost via B4 Relay
2026-09-25 19:09 ` Alireza Haghdoost via B4 Relay [this message]
2026-09-25 19:09 ` [PATCH v3 3/6] perf symbols: Factor out duplicate symbol selection Alireza Haghdoost via B4 Relay
2026-09-25 19:40 ` Ian Rogers
2026-09-25 19:55 ` Alireza Haghdoost
2026-09-25 20:21 ` Ian Rogers
2026-09-25 19:09 ` [PATCH v3 4/6] perf script: Add --max-symbol-bytes to bound ELF symbol memory Alireza Haghdoost via B4 Relay
2026-09-25 19:09 ` [PATCH v3 5/6] perf script: Add --lazy-load-symbols for lazy symbol loading Alireza Haghdoost via B4 Relay
2026-09-25 19:09 ` [PATCH v3 6/6] perf test: Test lazy symbol loading and symbol memory limits Alireza Haghdoost via B4 Relay
2026-09-25 20:20 ` [PATCH v3 0/6] perf script: Bounded and lazy symbol loading Ian Rogers
2026-09-25 21:28 ` Alireza Haghdoost
2026-09-25 21:55 ` Ian Rogers
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260925-perf-symbol-memory-send-v3-2-3e4e234c363b@uber.com \
--to=devnull+haghdoost.uber.com@kernel.org \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=andriin@fb.com \
--cc=ast@kernel.org \
--cc=haghdoost@uber.com \
--cc=irogers@google.com \
--cc=james.clark@linaro.org \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®