Merge branch 'support-bpf-traversal-of-wakeup-sources'

Samuel Wu says:

====================
Support BPF traversal of wakeup sources

This patchset adds requisite kfuncs for BPF programs to safely traverse
wakeup_sources, and puts a config flag around the sysfs interface.

Currently, a traversal of wakeup sources require going through
/sys/class/wakeup/* or /d/wakeup_sources/*. The repeated syscalls to query
sysfs is inefficient, as there can be hundreds of wakeup_sources, with each
wakeup source also having multiple attributes. debugfs is unstable and
insecure.

Adding kfuncs to lock/unlock wakeup sources allows BPF program to safely
traverse the wakeup sources list, and a kfunc to get head of wakeup
sources list is needed to start traversing the list.

On a quiescent Pixel 6 traversing 150 wakeup_sources, I am seeing ~34x
speedup (sampled 75 times in table below). For a device under load, the
speedup is greater.
+-------+----+----------+----------+
|       | n  | AVG (ms) | STD (ms) |
+-------+----+----------+----------+
| sysfs | 75 | 44.9     | 12.6     |
+-------+----+----------+----------+
| BPF   | 75 | 1.3      | 0.7      |
+-------+----+----------+----------+

The initial attempts for BPF traversal of wakeup_sources was with BPF
iterators [1]. However, BPF already allows for traversing of a simple list
with bpf_for(), and this current patchset has the added benefit of being
~2-3x more performant than BPF iterators.

[1]: https://lore.kernel.org/all/20260225210820.177674-1-wusamuel@google.com/

Changes in v4:
- Removed `.owner = THIS_MODULE` for btf_kfunc_id_set per Greg
- Add a graceful exit in selftest if bpf_wakeup_sources_get_head() is not
  present due to kernel configs without CONFIG_PM_SLEEP (e.g. s390)
- Relaxed substr match in wakeup_source_unlock_null() selftest
- v3 link: https://lore.kernel.org/all/20260331153413.2469218-1-wusamuel@google.com/

Changes in v3:
- Changed return type of bpf_wakeup_sources_get_head() to `void *` per Alexei
- Added failure test for direct dereference of wakeup source head
- Use bpf_core_cast() instead of macros in BPF program per Kumar
- v2 link: https://lore.kernel.org/all/20260326112521.2827500-1-wusamuel@google.com/

Changes in v2:
- Dropped CONFIG_PM_WAKEUP_STATS_SYSFS patch for future patchset
- Added declarations for kfuncs to .h to fix sparse and checkpatch warnings
- Added kfunc to get address of wakeup_source's head
- Added example bpf prog selftest for traversal of wakeup sources per Kumar
- Added *_fail.c selftest per Kumar
- More concise commit message in patch 1/2
- v1 link: https://lore.kernel.org/all/20260320160055.4114055-1-wusamuel@google.com/
====================

Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20260511174559.659782-1-wusamuel@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This commit is contained in:
Alexei Starovoitov 2026-05-14 16:02:06 -07:00
commit 9c3f95bc56
7 changed files with 386 additions and 3 deletions

View File

@ -168,3 +168,10 @@ static inline void device_pm_init(struct device *dev)
device_pm_sleep_init(dev);
pm_runtime_init(dev);
}
#ifdef CONFIG_BPF_SYSCALL
struct bpf_ws_lock { };
struct bpf_ws_lock *bpf_wakeup_sources_read_lock(void);
void bpf_wakeup_sources_read_unlock(struct bpf_ws_lock *lock);
void *bpf_wakeup_sources_get_head(void);
#endif

View File

@ -1168,11 +1168,78 @@ static const struct file_operations wakeup_sources_stats_fops = {
.release = seq_release_private,
};
static int __init wakeup_sources_debugfs_init(void)
#ifdef CONFIG_BPF_SYSCALL
#include <linux/btf.h>
__bpf_kfunc_start_defs();
/**
* bpf_wakeup_sources_read_lock - Acquire the SRCU lock for wakeup sources
*
* The underlying SRCU lock returns an integer index. However, the BPF verifier
* requires a pointer (PTR_TO_BTF_ID) to strictly track the state of acquired
* resources using KF_ACQUIRE and KF_RELEASE semantics. We use an opaque
* structure pointer (struct bpf_ws_lock *) to satisfy the verifier while
* safely encoding the integer index within the pointer address itself.
*
* Return: An opaque pointer encoding the SRCU lock index + 1 (to avoid NULL).
*/
__bpf_kfunc struct bpf_ws_lock *bpf_wakeup_sources_read_lock(void)
{
return (struct bpf_ws_lock *)(long)(wakeup_sources_read_lock() + 1);
}
/**
* bpf_wakeup_sources_read_unlock - Release the SRCU lock for wakeup sources
* @lock: The opaque pointer returned by bpf_wakeup_sources_read_lock()
*
* The BPF verifier guarantees that @lock is a valid, unreleased pointer from
* the acquire function. We decode the pointer back into the integer SRCU index
* by subtracting 1 and release the lock.
*/
__bpf_kfunc void bpf_wakeup_sources_read_unlock(struct bpf_ws_lock *lock)
{
wakeup_sources_read_unlock((int)(long)lock - 1);
}
/**
* bpf_wakeup_sources_get_head - Get the head of the wakeup sources list
*
* Return: The head of the wakeup sources list.
*/
__bpf_kfunc void *bpf_wakeup_sources_get_head(void)
{
return &wakeup_sources;
}
__bpf_kfunc_end_defs();
BTF_KFUNCS_START(wakeup_source_kfunc_ids)
BTF_ID_FLAGS(func, bpf_wakeup_sources_read_lock, KF_ACQUIRE)
BTF_ID_FLAGS(func, bpf_wakeup_sources_read_unlock, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_wakeup_sources_get_head)
BTF_KFUNCS_END(wakeup_source_kfunc_ids)
static const struct btf_kfunc_id_set wakeup_source_kfunc_set = {
.set = &wakeup_source_kfunc_ids,
};
static void __init wakeup_sources_bpf_init(void)
{
if (register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &wakeup_source_kfunc_set))
pm_pr_dbg("Wakeup: failed to register BTF kfuncs\n");
}
#else
static inline void wakeup_sources_bpf_init(void) {}
#endif /* CONFIG_BPF_SYSCALL */
static int __init wakeup_sources_init(void)
{
debugfs_create_file("wakeup_sources", 0444, NULL, NULL,
&wakeup_sources_stats_fops);
wakeup_sources_bpf_init();
return 0;
}
postcore_initcall(wakeup_sources_debugfs_init);
postcore_initcall(wakeup_sources_init);

View File

@ -130,4 +130,5 @@ CONFIG_INFINIBAND=y
CONFIG_SMC=y
CONFIG_SMC_HS_CTRL_BPF=y
CONFIG_DIBS=y
CONFIG_DIBS_LO=y
CONFIG_DIBS_LO=y
CONFIG_PM_WAKELOCKS=y

View File

@ -0,0 +1,118 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright 2026 Google LLC */
#include <test_progs.h>
#include <bpf/btf.h>
#include <fcntl.h>
#include "test_wakeup_source.skel.h"
#include "wakeup_source_fail.skel.h"
#include "progs/wakeup_source.h"
static int lock_ws(const char *name)
{
int fd;
ssize_t bytes;
fd = open("/sys/power/wake_lock", O_WRONLY);
if (!ASSERT_OK_FD(fd, "open /sys/power/wake_lock"))
return -1;
bytes = write(fd, name, strlen(name));
close(fd);
if (!ASSERT_EQ(bytes, strlen(name), "write to wake_lock"))
return -1;
return 0;
}
static void unlock_ws(const char *name)
{
int fd;
fd = open("/sys/power/wake_unlock", O_WRONLY);
if (fd < 0)
return;
write(fd, name, strlen(name));
close(fd);
}
struct rb_ctx {
const char *name;
bool found;
long long active_time_ns;
long long total_time_ns;
};
static int process_sample(void *ctx, void *data, size_t len)
{
struct rb_ctx *rb_ctx = ctx;
struct wakeup_event_t *e = data;
if (strcmp(e->name, rb_ctx->name) == 0) {
rb_ctx->found = true;
rb_ctx->active_time_ns = e->active_time_ns;
rb_ctx->total_time_ns = e->total_time_ns;
}
return 0;
}
void test_wakeup_source(void)
{
struct btf *btf;
int id;
btf = btf__load_vmlinux_btf();
if (!ASSERT_OK_PTR(btf, "btf_vmlinux"))
return;
id = btf__find_by_name_kind(btf, "bpf_wakeup_sources_get_head", BTF_KIND_FUNC);
btf__free(btf);
if (id < 0) {
printf("%s:SKIP:bpf_wakeup_sources_get_head kfunc not found in BTF\n", __func__);
test__skip();
return;
}
if (test__start_subtest("iterate_and_verify_times")) {
struct test_wakeup_source *skel;
struct ring_buffer *rb = NULL;
struct rb_ctx rb_ctx = {
.name = "bpf_selftest_ws_times",
.found = false,
};
int err;
skel = test_wakeup_source__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
return;
rb = ring_buffer__new(bpf_map__fd(skel->maps.rb), process_sample, &rb_ctx, NULL);
if (!ASSERT_OK_PTR(rb, "ring_buffer__new"))
goto destroy;
/* Create a temporary wakeup source */
if (!ASSERT_OK(lock_ws(rb_ctx.name), "lock_ws"))
goto unlock;
err = bpf_prog_test_run_opts(bpf_program__fd(
skel->progs.iterate_wakeupsources), NULL);
ASSERT_OK(err, "bpf_prog_test_run");
ring_buffer__consume(rb);
ASSERT_TRUE(rb_ctx.found, "found_test_ws_in_rb");
ASSERT_GT(rb_ctx.active_time_ns, 0, "active_time_gt_0");
ASSERT_GT(rb_ctx.total_time_ns, 0, "total_time_gt_0");
unlock:
unlock_ws(rb_ctx.name);
destroy:
if (rb)
ring_buffer__free(rb);
test_wakeup_source__destroy(skel);
}
RUN_TESTS(wakeup_source_fail);
}

View File

@ -0,0 +1,92 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright 2026 Google LLC */
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_core_read.h>
#include "bpf_experimental.h"
#include "bpf_misc.h"
#include "wakeup_source.h"
#define MAX_LOOP_ITER 1000
#define RB_SIZE (16384 * 4)
struct {
__uint(type, BPF_MAP_TYPE_RINGBUF);
__uint(max_entries, RB_SIZE);
} rb SEC(".maps");
struct bpf_ws_lock;
struct bpf_ws_lock *bpf_wakeup_sources_read_lock(void) __ksym;
void bpf_wakeup_sources_read_unlock(struct bpf_ws_lock *lock) __ksym;
void *bpf_wakeup_sources_get_head(void) __ksym;
SEC("syscall")
__success __retval(0)
int iterate_wakeupsources(void *ctx)
{
struct list_head *head = bpf_wakeup_sources_get_head();
struct list_head *pos = head;
struct bpf_ws_lock *lock;
int i;
lock = bpf_wakeup_sources_read_lock();
if (!lock)
return 0;
bpf_for(i, 0, MAX_LOOP_ITER) {
if (bpf_core_read(&pos, sizeof(pos), &pos->next) || !pos || pos == head)
break;
struct wakeup_event_t *e = bpf_ringbuf_reserve(&rb, sizeof(*e), 0);
if (!e)
break;
struct wakeup_source *ws = bpf_core_cast(
(void *)pos - bpf_core_field_offset(struct wakeup_source, entry),
struct wakeup_source);
s64 active_time = 0;
bool active = BPF_CORE_READ_BITFIELD(ws, active);
bool autosleep_enable = BPF_CORE_READ_BITFIELD(ws, autosleep_enabled);
s64 last_time = ws->last_time;
s64 max_time = ws->max_time;
s64 prevent_sleep_time = ws->prevent_sleep_time;
s64 total_time = ws->total_time;
if (active) {
s64 curr_time = bpf_ktime_get_ns();
s64 prevent_time = ws->start_prevent_time;
if (curr_time > last_time)
active_time = curr_time - last_time;
total_time += active_time;
if (active_time > max_time)
max_time = active_time;
if (autosleep_enable && curr_time > prevent_time)
prevent_sleep_time += curr_time - prevent_time;
}
e->active_count = ws->active_count;
e->active_time_ns = active_time;
e->event_count = ws->event_count;
e->expire_count = ws->expire_count;
e->last_time_ns = last_time;
e->max_time_ns = max_time;
e->prevent_sleep_time_ns = prevent_sleep_time;
e->total_time_ns = total_time;
e->wakeup_count = ws->wakeup_count;
if (bpf_probe_read_kernel_str(
e->name, WAKEUP_NAME_LEN, ws->name) < 0)
e->name[0] = '\0';
bpf_ringbuf_submit(e, 0);
}
bpf_wakeup_sources_read_unlock(lock);
return 0;
}
char _license[] SEC("license") = "GPL";

View File

@ -0,0 +1,22 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright 2026 Google LLC */
#ifndef __WAKEUP_SOURCE_H__
#define __WAKEUP_SOURCE_H__
#define WAKEUP_NAME_LEN 128
struct wakeup_event_t {
unsigned long active_count;
long long active_time_ns;
unsigned long event_count;
unsigned long expire_count;
long long last_time_ns;
long long max_time_ns;
long long prevent_sleep_time_ns;
long long total_time_ns;
unsigned long wakeup_count;
char name[WAKEUP_NAME_LEN];
};
#endif /* __WAKEUP_SOURCE_H__ */

View File

@ -0,0 +1,76 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright 2026 Google LLC */
#include <vmlinux.h>
#include <bpf/bpf_helpers.h>
#include "bpf_misc.h"
struct bpf_ws_lock;
struct bpf_ws_lock *bpf_wakeup_sources_read_lock(void) __ksym;
void bpf_wakeup_sources_read_unlock(struct bpf_ws_lock *lock) __ksym;
void *bpf_wakeup_sources_get_head(void) __ksym;
SEC("syscall")
__failure __msg("BPF_EXIT instruction in main prog would lead to reference leak")
int wakeup_source_lock_no_unlock(void *ctx)
{
struct bpf_ws_lock *lock;
lock = bpf_wakeup_sources_read_lock();
if (!lock)
return 0;
return 0;
}
SEC("syscall")
__failure __msg("access beyond struct")
int wakeup_source_access_lock_fields(void *ctx)
{
struct bpf_ws_lock *lock;
int val;
lock = bpf_wakeup_sources_read_lock();
if (!lock)
return 0;
val = *(int *)lock;
bpf_wakeup_sources_read_unlock(lock);
return val;
}
SEC("syscall")
__failure __msg("type=scalar expected=fp")
int wakeup_source_unlock_no_lock(void *ctx)
{
struct bpf_ws_lock *lock = (void *)0x1;
bpf_wakeup_sources_read_unlock(lock);
return 0;
}
SEC("syscall")
__failure __msg("Possibly NULL pointer passed to trusted")
int wakeup_source_unlock_null(void *ctx)
{
bpf_wakeup_sources_read_unlock(NULL);
return 0;
}
SEC("syscall")
__failure __msg("R0 invalid mem access 'scalar'")
int wakeup_source_unsafe_dereference(void *ctx)
{
struct list_head *head = bpf_wakeup_sources_get_head();
if (head->next)
return 1;
return 0;
}
char _license[] SEC("license") = "GPL";