Add a BPF iterator for traversing through wakeup_sources.
Setup iterators to traverse through a SRCUs of wakeup_sources. This is a
more elegant and efficient traversal than going through the options
today, such as at /sys/class/wakeup, or through debugfs.
Signed-off-by: Samuel Wu <wusamuel@google.com>
---
kernel/bpf/Makefile | 3 +
kernel/bpf/wakeup_source_iter.c | 103 ++++++++++++++++++++++++++++++++
2 files changed, 106 insertions(+)
create mode 100644 kernel/bpf/wakeup_source_iter.c
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 79cf22860a99..1259373298e1 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -66,6 +66,9 @@ obj-$(CONFIG_BPF_SYSCALL) += kmem_cache_iter.o
ifeq ($(CONFIG_DMA_SHARED_BUFFER),y)
obj-$(CONFIG_BPF_SYSCALL) += dmabuf_iter.o
endif
+ifeq ($(CONFIG_PM_SLEEP),y)
+obj-$(CONFIG_BPF_SYSCALL) += wakeup_source_iter.o
+endif
CFLAGS_REMOVE_percpu_freelist.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/bpf/wakeup_source_iter.c b/kernel/bpf/wakeup_source_iter.c
new file mode 100644
index 000000000000..ab83d212a1f9
--- /dev/null
+++ b/kernel/bpf/wakeup_source_iter.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2026 Google LLC */
+#include <linux/bpf.h>
+#include <linux/btf_ids.h>
+#include <linux/kernel.h>
+#include <linux/pm_wakeup.h>
+#include <linux/seq_file.h>
+
+struct bpf_iter__wakeup_source {
+ __bpf_md_ptr(struct bpf_iter_meta *, meta);
+ __bpf_md_ptr(struct wakeup_source *, wakeup_source);
+};
+
+static void *wakeup_source_iter_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ int *srcuidx = seq->private;
+ struct wakeup_source *ws;
+ loff_t i;
+
+ *srcuidx = wakeup_sources_read_lock();
+
+ ws = wakeup_sources_walk_start();
+ for (i = 0; ws && i < *pos; i++)
+ ws = wakeup_sources_walk_next(ws);
+
+ return ws;
+}
+
+static void *wakeup_source_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ struct wakeup_source *ws = v;
+
+ ++*pos;
+
+ return wakeup_sources_walk_next(ws);
+}
+
+static void wakeup_source_iter_seq_stop(struct seq_file *seq, void *v)
+{
+ int *srcuidx = seq->private;
+
+ if (*srcuidx >= 0)
+ wakeup_sources_read_unlock(*srcuidx);
+ *srcuidx = -1;
+}
+
+static int __wakeup_source_seq_show(struct seq_file *seq, void *v, bool in_stop)
+{
+ struct bpf_iter_meta meta = {
+ .seq = seq,
+ };
+ struct bpf_iter__wakeup_source ctx = {
+ .meta = &meta,
+ .wakeup_source = v,
+ };
+ struct bpf_prog *prog = bpf_iter_get_info(&meta, in_stop);
+
+ if (prog)
+ return bpf_iter_run_prog(prog, &ctx);
+
+ return 0;
+}
+
+static int wakeup_source_iter_seq_show(struct seq_file *seq, void *v)
+{
+ return __wakeup_source_seq_show(seq, v, false);
+}
+
+static const struct seq_operations wakeup_source_iter_seq_ops = {
+ .start = wakeup_source_iter_seq_start,
+ .next = wakeup_source_iter_seq_next,
+ .stop = wakeup_source_iter_seq_stop,
+ .show = wakeup_source_iter_seq_show,
+};
+
+static const struct bpf_iter_seq_info wakeup_source_iter_seq_info = {
+ .seq_ops = &wakeup_source_iter_seq_ops,
+ .seq_priv_size = sizeof(int),
+};
+
+static struct bpf_iter_reg bpf_wakeup_source_reg_info = {
+ .target = "wakeup_source",
+ .ctx_arg_info_size = 1,
+ .ctx_arg_info = {
+ {
+ offsetof(struct bpf_iter__wakeup_source, wakeup_source),
+ PTR_TO_BTF_ID_OR_NULL
+ },
+ },
+ .seq_info = &wakeup_source_iter_seq_info,
+};
+
+DEFINE_BPF_ITER_FUNC(wakeup_source, struct bpf_iter_meta *meta,
+ struct wakeup_source *wakeup_source)
+BTF_ID_LIST_SINGLE(bpf_wakeup_source_btf_id, struct, wakeup_source)
+
+static int __init wakeup_source_iter_init(void)
+{
+ bpf_wakeup_source_reg_info.ctx_arg_info[0].btf_id = bpf_wakeup_source_btf_id[0];
+ return bpf_iter_reg_target(&bpf_wakeup_source_reg_info);
+}
+
+late_initcall(wakeup_source_iter_init);
--
2.52.0.457.g6b5491de43-goog> diff --git a/kernel/bpf/wakeup_source_iter.c b/kernel/bpf/wakeup_source_iter.c
> new file mode 100644
> index 000000000000..ab83d212a1f9
> --- /dev/null
> +++ b/kernel/bpf/wakeup_source_iter.c
[ ... ]
> +static void wakeup_source_iter_seq_stop(struct seq_file *seq, void *v)
> +{
> + int *srcuidx = seq->private;
> +
> + if (*srcuidx >= 0)
> + wakeup_sources_read_unlock(*srcuidx);
> + *srcuidx = -1;
> +}
Should this function call __wakeup_source_seq_show(seq, v, true) when v is
NULL to notify the BPF program that iteration has completed?
Looking at other BPF iterators like map_iter, prog_iter, link_iter,
task_iter, and kmem_cache_iter, they all invoke the BPF program with
in_stop=true when the stop callback receives a NULL pointer. For example,
map_iter does:
static void bpf_map_seq_stop(struct seq_file *seq, void *v)
{
if (!v)
(void)__bpf_map_seq_show(seq, v, true);
...
}
The bpf_seq_read() function in kernel/bpf/bpf_iter.c has this comment at
the stop label: "/* bpf program called if !p */", which suggests this
callback is expected.
The __wakeup_source_seq_show() function already accepts an in_stop
parameter but is never called with true. Without this callback, BPF
programs using this iterator cannot detect when iteration has finished.
---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/21306880863
On Fri, Jan 23, 2026 at 5:50 PM <bot+bpf-ci@kernel.org> wrote:
>
> > diff --git a/kernel/bpf/wakeup_source_iter.c b/kernel/bpf/wakeup_source_iter.c
> > new file mode 100644
> > index 000000000000..ab83d212a1f9
> > --- /dev/null
> > +++ b/kernel/bpf/wakeup_source_iter.c
>
> [ ... ]
>
> > +static void wakeup_source_iter_seq_stop(struct seq_file *seq, void *v)
> > +{
> > + int *srcuidx = seq->private;
> > +
> > + if (*srcuidx >= 0)
> > + wakeup_sources_read_unlock(*srcuidx);
> > + *srcuidx = -1;
> > +}
>
> Should this function call __wakeup_source_seq_show(seq, v, true) when v is
> NULL to notify the BPF program that iteration has completed?
My understanding is that above code is invoked as a N+1 case after
iterating through a list of size N. If desired behavior is to do
additional cleanup not already covered by _seq_stop() (e.g. printing
closing footers), then v == NULL should be handled. However, there is
no such need for wakeup_source_iter at the moment.
>
> Looking at other BPF iterators like map_iter, prog_iter, link_iter,
> task_iter, and kmem_cache_iter, they all invoke the BPF program with
> in_stop=true when the stop callback receives a NULL pointer. For example,
> map_iter does:
>
> static void bpf_map_seq_stop(struct seq_file *seq, void *v)
> {
> if (!v)
> (void)__bpf_map_seq_show(seq, v, true);
> ...
> }
>
> The bpf_seq_read() function in kernel/bpf/bpf_iter.c has this comment at
> the stop label: "/* bpf program called if !p */", which suggests this
> callback is expected.
>
> The __wakeup_source_seq_show() function already accepts an in_stop
> parameter but is never called with true. Without this callback, BPF
> programs using this iterator cannot detect when iteration has finished.
>
If I understand correctly, this is not mandatory. For a
straightforward iterator like this one, I'd like to keep it simple and
not unnecessarily handle this case.
>
> ---
> AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
> See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
>
> CI run summary: https://github.com/kernel-patches/bpf/actions/runs/21306880863
© 2016 - 2026 Red Hat, Inc.