Skip to contentSkip to conversation

perf unwind-libdw: Fix unwinding of multi-threaded processes

PATCH Superseded Alessio Podda 4 participants 6 messages Jul 22 – Aug 2 perf events

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 perf unwind-libdw: Fix unwinding of multi-threaded processes

The libdw callback API has two levels: dwfl_getthread_frames() first finds the requested thread using the next_thread() or get_thread() callback and then walks its stack.

Since perf only has a snapshot of the stack of a single thread, it provides a stubbed-out API that always returns the pid the Dwfl was attached with (i.e. whatever was passed to dwfl_attach_state()), rather than the actual sampled thread's TID.

Commit 6b2658b3f36a ("perf unwind-libdw: Don't discard loaded ELF/DWARF after every unwind") changed libdw unwinding from recreating the Dwfl object for each sample to caching it in struct maps, which is shared by every thread in the process. It left next_thread() unchanged.

Since the pid passed to dwfl_attach_state() is only set at creation, only the thread of the first sample is ever found. As a result, dwfl_getthread_frames() fails with ESRCH when asked to unwind a sample from another thread.

Make next_thread() return the current sample's TID, provide get_thread() so libdw can find it directly, and pass the process PID expected by dwfl_attach_state(). This allows libdw to unwind samples from every thread in a multi-threaded process.

Fixes 6b2658b3f36a ("perf unwind-libdw: Don't discard loaded ELF/DWARF after every unwind")
Assisted-by Codex:gpt-5.6-sol

---

A standalone reproducer is available at:

https://github.com/kryggird/perf-bug-repro/tree/019c8ae97f9e4370ef2265d7badc3269e2a5044f

Run it with the perf binary being tested:

./reproduce.sh /path/to/perf

Results:

perf 7.1.3-201.fc44.x86_64:
1517 of 1522 samples have no userspace callchain

patched perf 7.2.rc4.g1590cf032971:
15 of 1449 samples have no userspace callchain

 tools/perf/util/unwind-libdw.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)
tools/perf/util/unwind-libdw.c +20 -3
index 7f35042be567..3735ef83c8c4 100644
@@ -173,14 +173,30 @@ static int entry(u64 ip, struct unwind_info *ui)
 	return 0;
 }
 
-static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
+static pid_t next_thread(Dwfl *dwfl __maybe_unused, void *arg, void **thread_argp)
 {
+	struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
 	/* We want only single thread to be processed. */
 	if (*thread_argp != NULL)
 		return 0;
 
+	assert(dwfl_ui_ti->ui != NULL);
 	*thread_argp = arg;
-	return dwfl_pid(dwfl);
+	return thread__tid(dwfl_ui_ti->ui->thread);
+}
+
+static bool get_thread(Dwfl *dwfl __maybe_unused, pid_t tid, void *arg,
+		       void **thread_argp)
+{
+	struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
+	assert(dwfl_ui_ti->ui != NULL);
+	if (tid != thread__tid(dwfl_ui_ti->ui->thread))
+		return false;
+
+	*thread_argp = arg;
+	return true;
 }
 
 static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
@@ -306,6 +322,7 @@ static bool libdw_set_initial_registers(Dwfl_Thread *thread, void *arg)
 
 static const Dwfl_Thread_Callbacks callbacks = {
 	.next_thread           = next_thread,
+	.get_thread            = get_thread,
 	.memory_read           = memory_read,
 	.set_initial_registers = libdw_set_initial_registers,
 };
@@ -400,7 +417,7 @@ int libdw__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (err)
 		goto out;
 
-	dwfl_attach_state(dwfl, /*elf=*/NULL, thread__tid(thread), &callbacks,
+	dwfl_attach_state(dwfl, /*elf=*/NULL, thread__pid(thread), &callbacks,
 			  /* Dwfl thread function argument*/dwfl_ui_ti);
 	// Ignore thread already attached error.
 

base-commit: b95f03f04d475aa6719d15a636ddf32222d55657

Signature · 1 line
2.55.0
#1 lore raw
Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

New issues:
- [Low] Missing explicit POSIX standard header inclusion for <assert.h>, breaking compatibility with musl libc.

Pre-existing issues:
- [High] Missing NULL check on zalloc allocation for dwfl_ui_ti leads to a NULL pointer dereference, and unchecked dwfl_begin() failure leads to a memory leak.
- [High] The local pointer ui is declared as a static variable but is dynamically allocated and freed within the function, creating a severe data race. --

--- Patch [1]: [PATCH] perf unwind-libdw: Fix unwinding of multi-threaded processes --- commit cd2051f3de0d807edd3e4fcc7ed115a6364be27d
Author: Alessio Podda <[email protected]>

perf unwind-libdw: Fix unwinding of multi-threaded processes

This commit fixes unwinding of multi-threaded processes in perf. It updates next_thread() to return the current sample's TID and provides get_thread() so libdw can find the thread directly.

Quoted 8 lines
tools/perf/util/unwind-libdw.c +0 -0
index 7f35042be5677..3735ef83c8c48 100644
@@ -173,14 +173,30 @@ static int entry(u64 ip, struct unwind_info *ui)
 	return 0;
 }
 

tools/perf/util/unwind-libdw.c static int entry(u64 ip, struct unwind_info *ui) · line 184

Quoted 10 lines
tools/perf/util/unwind-libdw.c +4 -1
-static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
+static pid_t next_thread(Dwfl *dwfl __maybe_unused, void *arg, void **thread_argp)
 {
+	struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
 	/* We want only single thread to be processed. */
 	if (*thread_argp != NULL)
 		return 0;
 
+	assert(dwfl_ui_ti->ui != NULL);

[Severity: Low]
Does this file need an explicit include for <assert.h>? The perf subsystem guidelines require direct POSIX header inclusions for compatibility with musl libc, and it appears the assert macro is being introduced here without it.

Quoted 4 lines
tools/perf/util/unwind-libdw.c +2 -1
+	*thread_argp = arg;
-	return dwfl_pid(dwfl);
+	return thread__tid(dwfl_ui_ti->ui->thread);
 }

[ ... ]

tools/perf/util/unwind-libdw.c int libdw__get_entries(unwind_entry_cb_t cb, void *arg, · line 422

Quoted 8 lines
tools/perf/util/unwind-libdw.c +1 -1
@@ -400,7 +417,7 @@ int libdw__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (err)
 		goto out;
 
-	dwfl_attach_state(dwfl, /*elf=*/NULL, thread__tid(thread), &callbacks,
+	dwfl_attach_state(dwfl, /*elf=*/NULL, thread__pid(thread), &callbacks,
 			  /* Dwfl thread function argument*/dwfl_ui_ti);
 	// Ignore thread already attached error.

[Severity: High]
This is a pre-existing issue, but can the allocation for dwfl_ui_ti fail and lead to a NULL pointer dereference?

Looking at earlier code in libdw__get_entries():

	dwfl_ui_ti = zalloc(sizeof(*dwfl_ui_ti));
	dwfl = dwfl_begin(&offline_callbacks);
	if (!dwfl)
		goto out;

	dwfl_ui_ti->dwfl = dwfl;

If zalloc fails, it seems we would dereference the NULL dwfl_ui_ti right away. Also, if dwfl_begin fails, we jump to out:

out:
...

	dwfl_ui_ti->ui = NULL;

which would also dereference NULL, or leak the allocated dwfl_ui_ti if zalloc had succeeded. Does this error path need a NULL check and proper cleanup?

[Severity: High]
This is a pre-existing issue, but does the static declaration of the ui pointer cause data races?

In libdw__get_entries(), ui is declared as static but dynamically allocated:

	static struct unwind_info *ui;
...
	ui = zalloc(sizeof(*ui) + sizeof(ui->entries[0]) * max_stack);

And then freed at the end of the same function:

	free(ui);

If multiple threads process events concurrently, could this static pointer be overwritten, leading to memory leaks, use-after-free, or double-free issues?

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
reviewer
#2 lore raw
In reply to Alessio Podda
Quoted 20 lines · Alessio Podda

The libdw callback API has two levels: dwfl_getthread_frames() first finds the requested thread using the next_thread() or get_thread() callback and then walks its stack.

Since perf only has a snapshot of the stack of a single thread, it provides a stubbed-out API that always returns the pid the Dwfl was attached with (i.e. whatever was passed to dwfl_attach_state()), rather than the actual sampled thread's TID.

Commit 6b2658b3f36a ("perf unwind-libdw: Don't discard loaded ELF/DWARF after every unwind") changed libdw unwinding from recreating the Dwfl object for each sample to caching it in struct maps, which is shared by every thread in the process. It left next_thread() unchanged.

Since the pid passed to dwfl_attach_state() is only set at creation, only the thread of the first sample is ever found. As a result, dwfl_getthread_frames() fails with ESRCH when asked to unwind a sample from another thread.

Quoted 8 lines

Make next_thread() return the current sample's TID, provide get_thread() so libdw can find it directly, and pass the process PID expected by dwfl_attach_state(). This allows libdw to unwind samples from every thread in a multi-threaded process.

Fixes 6b2658b3f36a ("perf unwind-libdw: Don't discard loaded ELF/DWARF after every unwind")
Assisted-by Codex:gpt-5.6-sol

This is great, thank you! Did you have a test that would reproduce this problem? Could we add it to tools/perf/tests ?

Thanks,
Ian

Quoted 79 lines

---

A standalone reproducer is available at:

https://github.com/kryggird/perf-bug-repro/tree/019c8ae97f9e4370ef2265d7badc3269e2a5044f

Run it with the perf binary being tested:

./reproduce.sh /path/to/perf

Results:

perf 7.1.3-201.fc44.x86_64:
1517 of 1522 samples have no userspace callchain

patched perf 7.2.rc4.g1590cf032971:
15 of 1449 samples have no userspace callchain

 tools/perf/util/unwind-libdw.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)
tools/perf/util/unwind-libdw.c +20 -3
index 7f35042be567..3735ef83c8c4 100644
@@ -173,14 +173,30 @@ static int entry(u64 ip, struct unwind_info *ui)
        return 0;
 }
 
-static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
+static pid_t next_thread(Dwfl *dwfl __maybe_unused, void *arg, void **thread_argp)
 {
+       struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
        /* We want only single thread to be processed. */
        if (*thread_argp != NULL)
                return 0;
 
+       assert(dwfl_ui_ti->ui != NULL);
        *thread_argp = arg;
-       return dwfl_pid(dwfl);
+       return thread__tid(dwfl_ui_ti->ui->thread);
+}
+
+static bool get_thread(Dwfl *dwfl __maybe_unused, pid_t tid, void *arg,
+                      void **thread_argp)
+{
+       struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
+       assert(dwfl_ui_ti->ui != NULL);
+       if (tid != thread__tid(dwfl_ui_ti->ui->thread))
+               return false;
+
+       *thread_argp = arg;
+       return true;
 }
 
 static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
@@ -306,6 +322,7 @@ static bool libdw_set_initial_registers(Dwfl_Thread *thread, void *arg)
 
 static const Dwfl_Thread_Callbacks callbacks = {
        .next_thread           = next_thread,
+       .get_thread            = get_thread,
        .memory_read           = memory_read,
        .set_initial_registers = libdw_set_initial_registers,
 };
@@ -400,7 +417,7 @@ int libdw__get_entries(unwind_entry_cb_t cb, void *arg,
        if (err)
                goto out;
 
-       dwfl_attach_state(dwfl, /*elf=*/NULL, thread__tid(thread), &callbacks,
+       dwfl_attach_state(dwfl, /*elf=*/NULL, thread__pid(thread), &callbacks,
                          /* Dwfl thread function argument*/dwfl_ui_ti);
        // Ignore thread already attached error.
 

base-commit: b95f03f04d475aa6719d15a636ddf32222d55657 --
2.55.0

#3 lore raw

PATCH v2 1/1 perf unwind-libdw: Fix unwinding of multi-threaded processes

The libdw callback API has two levels: dwfl_getthread_frames() first finds the requested thread using the next_thread() or get_thread() callback and then walks its stack.

Since perf only has a snapshot of the stack of a single thread, it provides a stubbed-out API that always returns the pid the Dwfl was attached with (i.e. whatever was passed to dwfl_attach_state()), rather than the actual sampled thread's TID.

Commit 6b2658b3f36a ("perf unwind-libdw: Don't discard loaded ELF/DWARF after every unwind") changed libdw unwinding from recreating the Dwfl object for each sample to caching it in struct maps, which is shared by every thread in the process. It left next_thread() unchanged.

Since the pid passed to dwfl_attach_state() is only set at creation, only the thread of the first sample is ever found. As a result, dwfl_getthread_frames() fails with ESRCH when asked to unwind a sample from another thread.

Make next_thread() return the current sample's TID, provide get_thread() so libdw can find it directly, and pass the process PID expected by dwfl_attach_state(). This allows libdw to unwind samples from every thread in a multi-threaded process.

Add a shell regression test that records a four-thread workload and verifies that libdw recovers the worker callchain for every worker TID.

Fixes 6b2658b3f36a ("perf unwind-libdw: Don't discard loaded ELF/DWARF after every unwind")
Assisted-by Codex:gpt-5.6-sol

---
Changes in v2:
- Add a shell regression test for multi-threaded libdw unwinding.
- Include <assert.h> directly instead of relying on a transitive include.

 .../shell/test_dwarf_unwind_multithreaded.sh  | 65 +++++++++++++++++++
 tools/perf/util/unwind-libdw.c                | 24 ++++++-
 2 files changed, 86 insertions(+), 3 deletions(-)
 create mode 100755 tools/perf/tests/shell/test_dwarf_unwind_multithreaded.sh
tools/perf/tests/shell/test_dwarf_unwind_multithreaded.sh new file +65 -0
new file mode 100755
index 000000000000..49e6e3af771f
@@ -0,0 +1,65 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# Test libdw unwinding of multi-threaded processes (exclusive)
+
+set -e
+
+if ! perf check feature -q libdw-dwarf-unwind; then
+	echo "Skip: libdw DWARF unwinding is not available"
+	exit 2
+fi
+
+tmpdir=$(mktemp -d /tmp/perf-test-dwarf-unwind-multithreaded.XXXXXX)
+perf_data="$tmpdir/perf.data"
+perf_script="$tmpdir/perf-script.txt"
+nr_threads=4
+nr_worker_threads=$((nr_threads - 1))
+
+cleanup()
+{
+	trap - EXIT TERM INT
+	rm -rf "$tmpdir"
+}
+
+trap cleanup EXIT TERM INT
+
+if ! perf record -q -e task-clock:u -F 99 --call-graph dwarf,8192 \
+	-o "$perf_data" -- perf test -w thloop 2 "$nr_threads"
+then
+	echo "Skip: failed to record task-clock:u"
+	exit 2
+fi
+
+if ! perf script --unwind-style=libdw \
+	-F comm,pid,tid,event,ip,sym -i "$perf_data" > "$perf_script"
+then
+	echo "Error: failed to process the recording with libdw" >&2
+	exit 1
+fi
+
+nr_unwound_threads=$(
+	awk '
+		BEGIN { RS = "" }
+
+		# thfunc is the worker-only caller of test_loop. Finding it proves
+		# that libdw unwound beyond the sampled leaf for this worker TID.
+		/thfunc/ {
+			split($2, id, "/")
+			seen[id[2]] = 1
+		}
+
+		END {
+			for (tid in seen)
+				nr_tids++
+			print nr_tids + 0
+		}
+	' "$perf_script"
+)
+
+if [ "$nr_unwound_threads" -ne "$nr_worker_threads" ]; then
+	echo "Error: expected callchains for $nr_worker_threads worker TIDs," \
+		"found $nr_unwound_threads" >&2
+	exit 1
+fi
+
+exit 0
tools/perf/util/unwind-libdw.c +21 -3
index 7f35042be567..63a5c2253174 100644
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
 #include <linux/compiler.h>
 #include <elfutils/libdw.h>
 #include <elfutils/libdwfl.h>
@@ -173,14 +174,30 @@ static int entry(u64 ip, struct unwind_info *ui)
 	return 0;
 }
 
-static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
+static pid_t next_thread(Dwfl *dwfl __maybe_unused, void *arg, void **thread_argp)
 {
+	struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
 	/* We want only single thread to be processed. */
 	if (*thread_argp != NULL)
 		return 0;
 
+	assert(dwfl_ui_ti->ui != NULL);
 	*thread_argp = arg;
-	return dwfl_pid(dwfl);
+	return thread__tid(dwfl_ui_ti->ui->thread);
+}
+
+static bool get_thread(Dwfl *dwfl __maybe_unused, pid_t tid, void *arg,
+		       void **thread_argp)
+{
+	struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
+	assert(dwfl_ui_ti->ui != NULL);
+	if (tid != thread__tid(dwfl_ui_ti->ui->thread))
+		return false;
+
+	*thread_argp = arg;
+	return true;
 }
 
 static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
@@ -306,6 +323,7 @@ static bool libdw_set_initial_registers(Dwfl_Thread *thread, void *arg)
 
 static const Dwfl_Thread_Callbacks callbacks = {
 	.next_thread           = next_thread,
+	.get_thread            = get_thread,
 	.memory_read           = memory_read,
 	.set_initial_registers = libdw_set_initial_registers,
 };
@@ -400,7 +418,7 @@ int libdw__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (err)
 		goto out;
 
-	dwfl_attach_state(dwfl, /*elf=*/NULL, thread__tid(thread), &callbacks,
+	dwfl_attach_state(dwfl, /*elf=*/NULL, thread__pid(thread), &callbacks,
 			  /* Dwfl thread function argument*/dwfl_ui_ti);
 	// Ignore thread already attached error.
 

base-commit: b95f03f04d475aa6719d15a636ddf32222d55657

Signature · 1 line
2.55.0
maintainer
#4 lore raw
Quoted 27 lines · Alessio Podda

The libdw callback API has two levels: dwfl_getthread_frames() first finds the requested thread using the next_thread() or get_thread() callback and then walks its stack.

Since perf only has a snapshot of the stack of a single thread, it provides a stubbed-out API that always returns the pid the Dwfl was attached with (i.e. whatever was passed to dwfl_attach_state()), rather than the actual sampled thread's TID.

Commit 6b2658b3f36a ("perf unwind-libdw: Don't discard loaded ELF/DWARF after every unwind") changed libdw unwinding from recreating the Dwfl object for each sample to caching it in struct maps, which is shared by every thread in the process. It left next_thread() unchanged.

Since the pid passed to dwfl_attach_state() is only set at creation, only the thread of the first sample is ever found. As a result, dwfl_getthread_frames() fails with ESRCH when asked to unwind a sample from another thread.

Make next_thread() return the current sample's TID, provide get_thread() so libdw can find it directly, and pass the process PID expected by dwfl_attach_state(). This allows libdw to unwind samples from every thread in a multi-threaded process.

Add a shell regression test that records a four-thread workload and verifies that libdw recovers the worker callchain for every worker TID.

Quoted 7 lines
Fixes 6b2658b3f36a ("perf unwind-libdw: Don't discard loaded ELF/DWARF after every unwind")
Assisted-by Codex:gpt-5.6-sol

---
Changes in v2:
- Add a shell regression test for multi-threaded libdw unwinding.
- Include <assert.h> directly instead of relying on a transitive include.

Ian, are you ok with this now?

Thanks,
Namhyung

Quoted 141 lines
 .../shell/test_dwarf_unwind_multithreaded.sh  | 65 +++++++++++++++++++
 tools/perf/util/unwind-libdw.c                | 24 ++++++-
 2 files changed, 86 insertions(+), 3 deletions(-)
 create mode 100755 tools/perf/tests/shell/test_dwarf_unwind_multithreaded.sh
tools/perf/tests/shell/test_dwarf_unwind_multithreaded.sh new file +65 -0
new file mode 100755
index 000000000000..49e6e3af771f
@@ -0,0 +1,65 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# Test libdw unwinding of multi-threaded processes (exclusive)
+
+set -e
+
+if ! perf check feature -q libdw-dwarf-unwind; then
+	echo "Skip: libdw DWARF unwinding is not available"
+	exit 2
+fi
+
+tmpdir=$(mktemp -d /tmp/perf-test-dwarf-unwind-multithreaded.XXXXXX)
+perf_data="$tmpdir/perf.data"
+perf_script="$tmpdir/perf-script.txt"
+nr_threads=4
+nr_worker_threads=$((nr_threads - 1))
+
+cleanup()
+{
+	trap - EXIT TERM INT
+	rm -rf "$tmpdir"
+}
+
+trap cleanup EXIT TERM INT
+
+if ! perf record -q -e task-clock:u -F 99 --call-graph dwarf,8192 \
+	-o "$perf_data" -- perf test -w thloop 2 "$nr_threads"
+then
+	echo "Skip: failed to record task-clock:u"
+	exit 2
+fi
+
+if ! perf script --unwind-style=libdw \
+	-F comm,pid,tid,event,ip,sym -i "$perf_data" > "$perf_script"
+then
+	echo "Error: failed to process the recording with libdw" >&2
+	exit 1
+fi
+
+nr_unwound_threads=$(
+	awk '
+		BEGIN { RS = "" }
+
+		# thfunc is the worker-only caller of test_loop. Finding it proves
+		# that libdw unwound beyond the sampled leaf for this worker TID.
+		/thfunc/ {
+			split($2, id, "/")
+			seen[id[2]] = 1
+		}
+
+		END {
+			for (tid in seen)
+				nr_tids++
+			print nr_tids + 0
+		}
+	' "$perf_script"
+)
+
+if [ "$nr_unwound_threads" -ne "$nr_worker_threads" ]; then
+	echo "Error: expected callchains for $nr_worker_threads worker TIDs," \
+		"found $nr_unwound_threads" >&2
+	exit 1
+fi
+
+exit 0
tools/perf/util/unwind-libdw.c +21 -3
index 7f35042be567..63a5c2253174 100644
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
 #include <linux/compiler.h>
 #include <elfutils/libdw.h>
 #include <elfutils/libdwfl.h>
@@ -173,14 +174,30 @@ static int entry(u64 ip, struct unwind_info *ui)
 	return 0;
 }
 
-static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
+static pid_t next_thread(Dwfl *dwfl __maybe_unused, void *arg, void **thread_argp)
 {
+	struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
 	/* We want only single thread to be processed. */
 	if (*thread_argp != NULL)
 		return 0;
 
+	assert(dwfl_ui_ti->ui != NULL);
 	*thread_argp = arg;
-	return dwfl_pid(dwfl);
+	return thread__tid(dwfl_ui_ti->ui->thread);
+}
+
+static bool get_thread(Dwfl *dwfl __maybe_unused, pid_t tid, void *arg,
+		       void **thread_argp)
+{
+	struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
+	assert(dwfl_ui_ti->ui != NULL);
+	if (tid != thread__tid(dwfl_ui_ti->ui->thread))
+		return false;
+
+	*thread_argp = arg;
+	return true;
 }
 
 static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
@@ -306,6 +323,7 @@ static bool libdw_set_initial_registers(Dwfl_Thread *thread, void *arg)
 
 static const Dwfl_Thread_Callbacks callbacks = {
 	.next_thread           = next_thread,
+	.get_thread            = get_thread,
 	.memory_read           = memory_read,
 	.set_initial_registers = libdw_set_initial_registers,
 };
@@ -400,7 +418,7 @@ int libdw__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (err)
 		goto out;
 
-	dwfl_attach_state(dwfl, /*elf=*/NULL, thread__tid(thread), &callbacks,
+	dwfl_attach_state(dwfl, /*elf=*/NULL, thread__pid(thread), &callbacks,
 			  /* Dwfl thread function argument*/dwfl_ui_ti);
 	// Ignore thread already attached error.
 

base-commit: b95f03f04d475aa6719d15a636ddf32222d55657

Signature · 1 line
2.55.0
maintainer Applied
#5 lore raw
In reply to Alessio Podda
Quoted 10 lines · Alessio Podda

The libdw callback API has two levels: dwfl_getthread_frames() first finds the requested thread using the next_thread() or get_thread() callback and then walks its stack.

Since perf only has a snapshot of the stack of a single thread, it provides a stubbed-out API that always returns the pid the Dwfl was attached with (i.e. whatever was passed to dwfl_attach_state()), rather than the actual sampled thread's TID.

[...]

Applied to perf-tools-next, thanks!

Best regards,
Namhyung