[PATCH bpf v2 0/8] bpf: Fix ring buffer handling

[PATCH bpf v2 0/8] bpf: Fix ring buffer handling

[Tamir Duberstein]

Fix correctness issues in BPF ring buffer handling.

A zero record bound currently consumes one record. A NULL callback is
accepted during manager construction but crashes when callback-based
consumption reaches the ring.

Native-width position counters are also compared by magnitude in
libbpf consumption and pending reservation tracking. The kernel
user-ring drain widens them before arithmetic. On native 32-bit systems
these paths fail after counter wrap.

The libbpf consumer can also miss a readiness notification after
publishing its position and checking for new data without a full
StoreLoad barrier. Use compiler atomics and add the missing barrier
between publishing a consumer position and the next producer-position
load, including across busy retries and early returns.

Callback traversal does not follow the overwrite position maintained by
BPF_F_RB_OVERWRITE maps. Reject callback consumption of those maps, as
discussed here:
https://lore.kernel.org/bpf/CAEf4Bzaq5drHWChXoRBnrmkb6reAsSVj8r=uByFSup31FMA7hw@mail.gmail.com/

Andrew Werner found the position-wrap and missed-wakeup failures while
implementing Aya ring buffer support. The original implementation
contains the equality reasoning and edge-triggered regression test:
https://github.com/aya-rs/aya/commit/e2cf734490bc188bcedb1eac92d23d81123e42cd

Aya later corrected the consumer ordering with the same explicit fence:
https://github.com/aya-rs/aya/commit/7277a57ea8cdb74918d3096a4b22b6d814481973

Assisted-by: Codex:gpt-5.5
Signed-off-by: Tamir Duberstein <tamird@kernel.org>
---
Changes in v2:
- Fix additional native 32-bit wrap paths found by Sashiko review.
- Explain modular position comparisons and leave mixed-bitness ABI work
  separate.
- Preserve the wakeup handshake across bounded and callback returns.
- Follow BPF comment style and simplify wakeup test cleanup.
- Link to v1: https://patch.msgid.link/20260613-bpf-ringbuf-fixes-v1-0-e623481cb724@kernel.org

---
Tamir Duberstein (8):
      libbpf: ringbuf: Honor zero consume bounds
      libbpf: ringbuf: Prevent NULL callback crash
      libbpf: ringbuf: Reject overwrite callback use
      libbpf: ringbuf: Handle position counter wrap
      bpf: ringbuf: Handle pending position wrap
      bpf: user_ringbuf: Handle position wrap
      libbpf: ringbuf: Use compiler atomics
      libbpf: ringbuf: Prevent missed wakeups

 kernel/bpf/ringbuf.c                             |  12 +-
 tools/lib/bpf/libbpf.h                           |  35 +++-
 tools/lib/bpf/ringbuf.c                          |  97 +++++++---
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 228 +++++++++++++++++++++++
 4 files changed, 340 insertions(+), 32 deletions(-)
---
base-commit: e7ae89a0c97ce2b68b0983cd01eda67cf373517d
change-id: 20260613-bpf-ringbuf-fixes-e9a8b3c6125b

Best regards,
--  
Tamir Duberstein <tamird@kernel.org>

[PATCH bpf v2 1/8] libbpf: ringbuf: Honor zero consume bounds

[Tamir Duberstein]

ringbuf_process_ring() checks the record bound only after advancing the
consumer position and invoking the callback. A zero bound therefore
consumes the first available record.

Return before reading the ring positions when the bound is zero so
ring_buffer__consume_n() and ring__consume_n() leave all records queued.

Fixes: 4d22ea94ea33 ("libbpf: Add ring__consume_n / ring_buffer__consume_n")
Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Assisted-by: Codex:gpt-5.5
Signed-off-by: Tamir Duberstein <tamird@kernel.org>
---
 tools/lib/bpf/ringbuf.c                          |  3 +++
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 13 +++++++++++++
 2 files changed, 16 insertions(+)

diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 00ec4837a06d..f2bb619d5a75 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -240,6 +240,9 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 	bool got_new_data;
 	void *sample;
 
+	if (n == 0)
+		return 0;
+
 	cons_pos = smp_load_acquire(r->consumer_pos);
 	do {
 		got_new_data = false;
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index 64520684d2cb..4f0558f14847 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -404,6 +404,7 @@ static int process_n_sample(void *ctx, void *data, size_t len)
 static void ringbuf_n_subtest(void)
 {
 	struct test_ringbuf_n_lskel *skel_n;
+	struct ring *ring;
 	int err, i;
 
 	skel_n = test_ringbuf_n_lskel__open();
@@ -431,6 +432,18 @@ static void ringbuf_n_subtest(void)
 	for (i = 0; i < N_TOT_SAMPLES; i++)
 		syscall(__NR_getpgid);
 
+	ring = ring_buffer__ring(ringbuf, 0);
+	if (!ASSERT_OK_PTR(ring, "ring_buffer__ring"))
+		goto cleanup_ringbuf;
+
+	err = ring_buffer__consume_n(ringbuf, 0);
+	if (!ASSERT_EQ(err, 0, "ringbuf_consume_zero"))
+		goto cleanup_ringbuf;
+
+	err = ring__consume_n(ring, 0);
+	if (!ASSERT_EQ(err, 0, "ring_consume_zero"))
+		goto cleanup_ringbuf;
+
 	/* Consume all samples from the ring buffer in batches of N_SAMPLES */
 	for (i = 0; i < N_TOT_SAMPLES; i += err) {
 		err = ring_buffer__consume_n(ringbuf, N_SAMPLES);

-- 
2.55.0.rc0.159.gbe5d7338c2

[PATCH bpf v2 2/8] libbpf: ringbuf: Prevent NULL callback crash

[Tamir Duberstein]

ring_buffer__new() and ring_buffer__add() allow a NULL sample
callback. When callback-based consumption reaches such a ring, it calls
through the NULL function pointer and crashes.

Check every ring before manager polling or consumption so a missing
callback returns -EINVAL before the manager waits or consumes another
ring. Check the selected ring before direct per-ring consumption. Perform
both checks before honoring a zero record bound so invalid callback use
always reports the error.

Fixes: bf99c936f947 ("libbpf: Add BPF ring buffer support")
Assisted-by: Codex:gpt-5.5
Signed-off-by: Tamir Duberstein <tamird@kernel.org>
---
 tools/lib/bpf/libbpf.h                           | 11 ++-
 tools/lib/bpf/ringbuf.c                          | 43 +++++++++--
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 93 ++++++++++++++++++++++++
 3 files changed, 136 insertions(+), 11 deletions(-)

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index bba4e8464396..9ba6b9ad3498 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1526,18 +1526,17 @@ LIBBPF_API int ring__map_fd(const struct ring *r);
  *
  * @param r A ringbuffer object.
  * @return The number of records consumed (or INT_MAX, whichever is less), or
- * a negative number if any of the callbacks return an error.
+ * a negative error code on failure.
  */
 LIBBPF_API int ring__consume(struct ring *r);
 
 /**
- * @brief **ring__consume_n()** consumes up to a requested amount of items from
- * a ringbuffer without event polling.
+ * @brief **ring__consume_n()** consumes up to a requested number of records
+ * from a ringbuffer without event polling.
  *
  * @param r A ringbuffer object.
- * @param n Maximum amount of items to consume.
- * @return The number of items consumed, or a negative number if any of the
- * callbacks return an error.
+ * @param n Maximum number of records to consume.
+ * @return The number of records consumed, or a negative error code on failure.
  */
 LIBBPF_API int ring__consume_n(struct ring *r, size_t n);
 
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index f2bb619d5a75..0dae4d95d309 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -231,6 +231,26 @@ static inline int roundup_len(__u32 len)
 	return (len + 7) / 8 * 8;
 }
 
+static int ringbuf_validate(const struct ring *r)
+{
+	if (unlikely(!r->sample_cb))
+		return -EINVAL;
+	return 0;
+}
+
+static int ringbuf_validate_callbacks(const struct ring_buffer *rb)
+{
+	int i, err;
+
+	for (i = 0; i < rb->ring_cnt; i++) {
+		err = ringbuf_validate(rb->rings[i]);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 {
 	int *len_ptr, len, err;
@@ -240,6 +260,9 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 	bool got_new_data;
 	void *sample;
 
+	err = ringbuf_validate(r);
+	if (err)
+		return err;
 	if (n == 0)
 		return 0;
 
@@ -284,14 +307,17 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
  * records.
  *
  * Returns number of records consumed across all registered ring buffers (or
- * n, whichever is less), or negative number if any of the callbacks return
- * error.
+ * n, whichever is less), or a negative error code on failure.
  */
 int ring_buffer__consume_n(struct ring_buffer *rb, size_t n)
 {
 	int64_t err, res = 0;
 	int i;
 
+	err = ringbuf_validate_callbacks(rb);
+	if (err)
+		return libbpf_err(err);
+
 	for (i = 0; i < rb->ring_cnt; i++) {
 		struct ring *ring = rb->rings[i];
 
@@ -309,14 +335,17 @@ int ring_buffer__consume_n(struct ring_buffer *rb, size_t n)
 
 /* Consume available ring buffer(s) data without event polling.
  * Returns number of records consumed across all registered ring buffers (or
- * INT_MAX, whichever is less), or negative number if any of the callbacks
- * return error.
+ * INT_MAX, whichever is less), or a negative error code on failure.
  */
 int ring_buffer__consume(struct ring_buffer *rb)
 {
 	int64_t err, res = 0;
 	int i;
 
+	err = ringbuf_validate_callbacks(rb);
+	if (err)
+		return libbpf_err(err);
+
 	for (i = 0; i < rb->ring_cnt; i++) {
 		struct ring *ring = rb->rings[i];
 
@@ -334,13 +363,17 @@ int ring_buffer__consume(struct ring_buffer *rb)
 
 /* Poll for available data and consume records, if any are available.
  * Returns number of records consumed (or INT_MAX, whichever is less), or
- * negative number, if any of the registered callbacks returned error.
+ * a negative error code on failure.
  */
 int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 {
 	int i, cnt;
 	int64_t err, res = 0;
 
+	err = ringbuf_validate_callbacks(rb);
+	if (err)
+		return libbpf_err(err);
+
 	cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms);
 	if (cnt < 0)
 		return libbpf_err(-errno);
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index 4f0558f14847..9ce996bcea8c 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -401,6 +401,97 @@ static int process_n_sample(void *ctx, void *data, size_t len)
 	return 0;
 }
 
+static int process_noop_sample(void *ctx, void *data, size_t len)
+{
+	return 0;
+}
+
+static void ringbuf_null_cb_subtest(void)
+{
+	struct test_ringbuf_n_lskel *skel_n;
+	struct ring_buffer *ringbuf = NULL;
+	struct ring *ring;
+	unsigned long consumer_pos;
+	int no_cb_map_fd = -1;
+	int err;
+
+	skel_n = test_ringbuf_n_lskel__open();
+	if (!ASSERT_OK_PTR(skel_n, "test_ringbuf_n_lskel__open"))
+		return;
+
+	skel_n->maps.ringbuf.max_entries = getpagesize();
+	skel_n->bss->pid = getpid();
+	skel_n->bss->value = SAMPLE_VALUE;
+
+	err = test_ringbuf_n_lskel__load(skel_n);
+	if (!ASSERT_OK(err, "test_ringbuf_n_lskel__load"))
+		goto cleanup;
+
+	err = test_ringbuf_n_lskel__attach(skel_n);
+	if (!ASSERT_OK(err, "test_ringbuf_n_lskel__attach"))
+		goto cleanup;
+
+	syscall(__NR_getpgid);
+
+	no_cb_map_fd = bpf_map_create(BPF_MAP_TYPE_RINGBUF, NULL, 0, 0,
+				      getpagesize(), NULL);
+	if (!ASSERT_OK_FD(no_cb_map_fd, "bpf_map_create"))
+		goto cleanup;
+
+	/* Manager APIs must validate all rings before consuming any of them. */
+	ringbuf = ring_buffer__new(skel_n->maps.ringbuf.map_fd,
+				   process_noop_sample, NULL, NULL);
+	if (!ASSERT_OK_PTR(ringbuf, "ring_buffer__new"))
+		goto cleanup_fd;
+
+	ring = ring_buffer__ring(ringbuf, 0);
+	if (!ASSERT_OK_PTR(ring, "ring_buffer__ring"))
+		goto cleanup_ringbuf;
+
+	err = ring_buffer__add(ringbuf, no_cb_map_fd, NULL, NULL);
+	if (!ASSERT_OK(err, "ring_buffer__add_no_cb"))
+		goto cleanup_ringbuf;
+
+	consumer_pos = ring__consumer_pos(ring);
+	ASSERT_GT(ring__producer_pos(ring), consumer_pos,
+		  "producer_pos_mixed_cb");
+
+	err = ring_buffer__consume_n(ringbuf, 0);
+	ASSERT_EQ(err, -EINVAL, "ringbuf_consume_zero_mixed_cb");
+	err = ring_buffer__consume(ringbuf);
+	ASSERT_EQ(err, -EINVAL, "ringbuf_consume_mixed_cb");
+	err = ring_buffer__poll(ringbuf, 0);
+	ASSERT_EQ(err, -EINVAL, "ringbuf_poll_mixed_cb");
+	ASSERT_EQ(ring__consumer_pos(ring), consumer_pos,
+		  "consumer_pos_mixed_cb");
+
+	ring_buffer__free(ringbuf);
+	ringbuf =
+		ring_buffer__new(skel_n->maps.ringbuf.map_fd, NULL, NULL, NULL);
+	if (!ASSERT_OK_PTR(ringbuf, "ring_buffer__new_no_cb"))
+		goto cleanup_fd;
+
+	ring = ring_buffer__ring(ringbuf, 0);
+	if (!ASSERT_OK_PTR(ring, "ring_buffer__ring_no_cb"))
+		goto cleanup_ringbuf;
+	consumer_pos = ring__consumer_pos(ring);
+
+	err = ring_buffer__consume_n(ringbuf, 0);
+	ASSERT_EQ(err, -EINVAL, "ringbuf_consume_zero_no_cb");
+	err = ring__consume_n(ring, 0);
+	ASSERT_EQ(err, -EINVAL, "ring_consume_zero_no_cb");
+	err = ring__consume(ring);
+	ASSERT_EQ(err, -EINVAL, "ring_consume_no_cb");
+	ASSERT_EQ(ring__consumer_pos(ring), consumer_pos, "consumer_pos_no_cb");
+
+cleanup_ringbuf:
+	ring_buffer__free(ringbuf);
+cleanup_fd:
+	close(no_cb_map_fd);
+cleanup:
+	test_ringbuf_n_lskel__destroy(skel_n);
+}
+
 static void ringbuf_n_subtest(void)
 {
 	struct test_ringbuf_n_lskel *skel_n;
@@ -579,6 +670,8 @@ void test_ringbuf(void)
 		ringbuf_subtest();
 	if (test__start_subtest("ringbuf_n"))
 		ringbuf_n_subtest();
+	if (test__start_subtest("ringbuf_null_cb"))
+		ringbuf_null_cb_subtest();
 	if (test__start_subtest("ringbuf_map_key"))
 		ringbuf_map_key_subtest();
 	if (test__start_subtest("ringbuf_write"))

-- 
2.55.0.rc0.159.gbe5d7338c2

[PATCH bpf v2 3/8] libbpf: ringbuf: Reject overwrite callback use

[Tamir Duberstein]

BPF_F_RB_OVERWRITE can advance overwrite_pos past consumer_pos.
Callback traversal does not read overwrite_pos, so after the producer
laps the consumer it can treat overwritten data as a record header.

An earlier proposal[0] copied the readable window before invoking
callbacks. Review concluded that callbacks are a poor fit because
copying penalizes zero-copy users and the API cannot report skipped
records.

Record the map flag and reject callback consumption with -EOPNOTSUPP.

Link: https://lore.kernel.org/bpf/CAEf4Bzaq5drHWChXoRBnrmkb6reAsSVj8r=uByFSup31FMA7hw@mail.gmail.com/ [0]
Fixes: feeaf1346f80 ("bpf: Add overwrite mode for BPF ring buffer")
Assisted-by: Codex:gpt-5.5
Signed-off-by: Tamir Duberstein <tamird@kernel.org>
---
 tools/lib/bpf/libbpf.h                           |  1 +
 tools/lib/bpf/ringbuf.c                          |  4 +++
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 39 ++++++++++++++++++++++++
 3 files changed, 44 insertions(+)

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 9ba6b9ad3498..ae46b17feaa6 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1439,6 +1439,7 @@ struct ring_buffer;
 struct ring;
 struct user_ring_buffer;
 
+/* Callback-based consumption is unsupported for BPF_F_RB_OVERWRITE maps. */
 typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size);
 
 struct ring_buffer_opts {
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 0dae4d95d309..5737e02c1670 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -30,6 +30,7 @@ struct ring {
 	unsigned long *producer_pos;
 	unsigned long mask;
 	int map_fd;
+	bool overwrite;
 };
 
 struct ring_buffer {
@@ -118,6 +119,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	r->sample_cb = sample_cb;
 	r->ctx = ctx;
 	r->mask = info.max_entries - 1;
+	r->overwrite = info.map_flags & BPF_F_RB_OVERWRITE;
 
 	/* Map writable consumer page */
 	tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0);
@@ -233,6 +235,8 @@ static inline int roundup_len(__u32 len)
 
 static int ringbuf_validate(const struct ring *r)
 {
+	if (unlikely(r->overwrite))
+		return -EOPNOTSUPP;
 	if (unlikely(!r->sample_cb))
 		return -EINVAL;
 	return 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index 9ce996bcea8c..29be2476c478 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -602,6 +602,43 @@ static void ringbuf_map_key_subtest(void)
 	test_ringbuf_map_key_lskel__destroy(skel_map_key);
 }
 
+static void ringbuf_overwrite_callback_subtest(void)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_RB_OVERWRITE);
+	struct ring_buffer *ringbuf;
+	struct ring *ring;
+	int map_fd, err;
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_RINGBUF, NULL, 0, 0, getpagesize(),
+				&opts);
+	if (!ASSERT_OK_FD(map_fd, "bpf_map_create"))
+		return;
+
+	ringbuf = ring_buffer__new(map_fd, process_noop_sample, NULL, NULL);
+	if (!ASSERT_OK_PTR(ringbuf, "ring_buffer__new"))
+		goto cleanup_fd;
+
+	ring = ring_buffer__ring(ringbuf, 0);
+	if (!ASSERT_OK_PTR(ring, "ring_buffer__ring"))
+		goto cleanup_ringbuf;
+
+	err = ring_buffer__consume_n(ringbuf, 0);
+	ASSERT_EQ(err, -EOPNOTSUPP, "ringbuf_consume_zero");
+	err = ring_buffer__consume(ringbuf);
+	ASSERT_EQ(err, -EOPNOTSUPP, "ringbuf_consume");
+	err = ring_buffer__poll(ringbuf, 0);
+	ASSERT_EQ(err, -EOPNOTSUPP, "ringbuf_poll");
+	err = ring__consume_n(ring, 0);
+	ASSERT_EQ(err, -EOPNOTSUPP, "ring_consume_zero");
+	err = ring__consume(ring);
+	ASSERT_EQ(err, -EOPNOTSUPP, "ring_consume");
+
+cleanup_ringbuf:
+	ring_buffer__free(ringbuf);
+cleanup_fd:
+	close(map_fd);
+}
+
 static void ringbuf_overwrite_mode_subtest(void)
 {
 	unsigned long size, len1, len2, len3, len4, len5;
@@ -676,6 +713,8 @@ void test_ringbuf(void)
 		ringbuf_map_key_subtest();
 	if (test__start_subtest("ringbuf_write"))
 		ringbuf_write_subtest();
+	if (test__start_subtest("ringbuf_overwrite_callback"))
+		ringbuf_overwrite_callback_subtest();
 	if (test__start_subtest("ringbuf_overwrite_mode"))
 		ringbuf_overwrite_mode_subtest();
 }

-- 
2.55.0.rc0.159.gbe5d7338c2

[PATCH bpf v2 4/8] libbpf: ringbuf: Handle position counter wrap

[Tamir Duberstein]

Ring buffer positions are unsigned long counters and can wrap on 32-bit
systems. ringbuf_process_ring() stops consuming when producer_pos wraps
below consumer_pos because it compares the counters by magnitude.

Compare the positions for equality instead. The producer cannot move
logically behind the consumer in a non-overwrite ring.

Fixes: bf99c936f947 ("libbpf: Add BPF ring buffer support")
Reported-by: Andrew Werner <awerner32@gmail.com>
Assisted-by: Codex:gpt-5.5
Signed-off-by: Tamir Duberstein <tamird@kernel.org>
---
 tools/lib/bpf/ringbuf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 5737e02c1670..1c5bce2b5e12 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -274,7 +274,8 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 	do {
 		got_new_data = false;
 		prod_pos = smp_load_acquire(r->producer_pos);
-		while (cons_pos < prod_pos) {
+		/* Positions wrap; the consumer cannot logically pass the producer. */
+		while (cons_pos != prod_pos) {
 			len_ptr = r->data + (cons_pos & r->mask);
 			len = smp_load_acquire(len_ptr);
 

-- 
2.55.0.rc0.159.gbe5d7338c2

[PATCH bpf v2 5/8] bpf: ringbuf: Handle pending position wrap

[Tamir Duberstein]

Ring buffer positions are unsigned long counters and can wrap on 32-bit
systems. __bpf_ringbuf_reserve() stops advancing pending_pos after
producer_pos wraps because it compares the counters by magnitude.

Compare the positions for equality instead. The pending position cannot
logically move ahead of the producer position.

Fixes: cfa1a2329a69 ("bpf: Fix overrunning reservations in ringbuf")
Reported-by: Sashiko <sashiko-bot@kernel.org>
Closes: https://lore.kernel.org/bpf/20260614020552.022A11F000E9@smtp.kernel.org/
Assisted-by: Codex:gpt-5.5
Signed-off-by: Tamir Duberstein <tamird@kernel.org>
---
 kernel/bpf/ringbuf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 35ae64ade36b..909880031fd3 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -482,7 +482,8 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 	prod_pos = rb->producer_pos;
 	new_prod_pos = prod_pos + len;
 
-	while (pend_pos < prod_pos) {
+	/* Positions wrap; pending_pos cannot logically pass producer_pos. */
+	while (pend_pos != prod_pos) {
 		hdr = (void *)rb->data + (pend_pos & rb->mask);
 		hdr_len = READ_ONCE(hdr->len);
 		if (hdr_len & BPF_RINGBUF_BUSY_BIT)

-- 
2.55.0.rc0.159.gbe5d7338c2

[PATCH bpf v2 6/8] bpf: user_ringbuf: Handle position wrap

[Tamir Duberstein]

User ring buffer positions are unsigned long counters, but
__bpf_user_ringbuf_peek() widens them to u64 before comparing and
subtracting them. On 32-bit systems, producer_pos wrapping below
consumer_pos therefore appears to move backwards and permanently stalls
the ring. The widened subtraction can also bypass the advertised-window
check.

Keep the positions word-sized and derive the available data with
word-sized subtraction so the arithmetic wraps with the counters. Treat
a zero span as empty and reject spans larger than the ring before
reading a record header.

Fixes: 205715673844 ("bpf: Add bpf_user_ringbuf_drain() helper")
Reported-by: Sashiko <sashiko-bot@kernel.org>
Closes: https://lore.kernel.org/bpf/20260614020552.022A11F000E9@smtp.kernel.org/
Assisted-by: Codex:gpt-5.5
Signed-off-by: Tamir Duberstein <tamird@kernel.org>
---
 kernel/bpf/ringbuf.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 909880031fd3..19cbb9b74ee7 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -748,9 +748,9 @@ const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto = {
 
 static int __bpf_user_ringbuf_peek(struct bpf_ringbuf *rb, void **sample, u32 *size)
 {
+	unsigned long avail, cons_pos, prod_pos;
 	int err;
 	u32 hdr_len, sample_len, total_len, flags, *hdr;
-	u64 cons_pos, prod_pos;
 
 	/* Synchronizes with smp_store_release() in user-space producer. */
 	prod_pos = smp_load_acquire(&rb->producer_pos);
@@ -759,8 +759,11 @@ static int __bpf_user_ringbuf_peek(struct bpf_ringbuf *rb, void **sample, u32 *s
 
 	/* Synchronizes with smp_store_release() in __bpf_user_ringbuf_sample_release() */
 	cons_pos = smp_load_acquire(&rb->consumer_pos);
-	if (cons_pos >= prod_pos)
+	avail = prod_pos - cons_pos;
+	if (!avail)
 		return -ENODATA;
+	if (avail > ringbuf_total_data_sz(rb))
+		return -EINVAL;
 
 	hdr = (u32 *)((uintptr_t)rb->data + (uintptr_t)(cons_pos & rb->mask));
 	/* Synchronizes with smp_store_release() in user-space producer. */
@@ -770,7 +773,7 @@ static int __bpf_user_ringbuf_peek(struct bpf_ringbuf *rb, void **sample, u32 *s
 	total_len = round_up(sample_len + BPF_RINGBUF_HDR_SZ, 8);
 
 	/* The sample must fit within the region advertised by the producer position. */
-	if (total_len > prod_pos - cons_pos)
+	if (total_len > avail)
 		return -EINVAL;
 
 	/* The sample must fit within the data region of the ring buffer. */

-- 
2.55.0.rc0.159.gbe5d7338c2

[PATCH bpf v2 7/8] libbpf: ringbuf: Use compiler atomics

[Tamir Duberstein]

Consumer-side ring buffer code uses architecture-specific smp_* helpers
for shared memory accesses.

Use compiler atomics instead. They provide equivalent acquire and
release ordering through a portable userspace interface and allow the
next commit to use compiler fences in the wakeup protocol without mixing
atomic interfaces.

Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Assisted-by: Codex:gpt-5.5
Signed-off-by: Tamir Duberstein <tamird@kernel.org>
---
 tools/lib/bpf/ringbuf.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 1c5bce2b5e12..141f2cbe56eb 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -270,14 +270,14 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 	if (n == 0)
 		return 0;
 
-	cons_pos = smp_load_acquire(r->consumer_pos);
+	cons_pos = __atomic_load_n(r->consumer_pos, __ATOMIC_ACQUIRE);
 	do {
 		got_new_data = false;
-		prod_pos = smp_load_acquire(r->producer_pos);
+		prod_pos = __atomic_load_n(r->producer_pos, __ATOMIC_ACQUIRE);
 		/* Positions wrap; the consumer cannot logically pass the producer. */
 		while (cons_pos != prod_pos) {
 			len_ptr = r->data + (cons_pos & r->mask);
-			len = smp_load_acquire(len_ptr);
+			len = __atomic_load_n(len_ptr, __ATOMIC_ACQUIRE);
 
 			/* sample not committed yet, bail out for now */
 			if (len & BPF_RINGBUF_BUSY_BIT)
@@ -291,14 +291,16 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 				err = r->sample_cb(r->ctx, sample, len);
 				if (err < 0) {
 					/* update consumer pos and bail out */
-					smp_store_release(r->consumer_pos,
-							  cons_pos);
+					__atomic_store_n(r->consumer_pos,
+							 cons_pos,
+							 __ATOMIC_RELEASE);
 					return err;
 				}
 				cnt++;
 			}
 
-			smp_store_release(r->consumer_pos, cons_pos);
+			__atomic_store_n(r->consumer_pos, cons_pos,
+					 __ATOMIC_RELEASE);
 
 			if (cnt >= n)
 				goto done;
@@ -413,8 +415,8 @@ struct ring *ring_buffer__ring(struct ring_buffer *rb, unsigned int idx)
 
 unsigned long ring__consumer_pos(const struct ring *r)
 {
-	/* Synchronizes with smp_store_release() in ringbuf_process_ring(). */
-	return smp_load_acquire(r->consumer_pos);
+	/* Synchronizes with the release store in ringbuf_process_ring(). */
+	return __atomic_load_n(r->consumer_pos, __ATOMIC_ACQUIRE);
 }
 
 unsigned long ring__producer_pos(const struct ring *r)
@@ -422,7 +424,7 @@ unsigned long ring__producer_pos(const struct ring *r)
 	/* Synchronizes with smp_store_release() in __bpf_ringbuf_reserve() in
 	 * the kernel.
 	 */
-	return smp_load_acquire(r->producer_pos);
+	return __atomic_load_n(r->producer_pos, __ATOMIC_ACQUIRE);
 }
 
 size_t ring__avail_data_size(const struct ring *r)

-- 
2.55.0.rc0.159.gbe5d7338c2

[PATCH bpf v2 8/8] libbpf: ringbuf: Prevent missed wakeups

[Tamir Duberstein]

After consuming the last visible record, ringbuf_process_ring()
publishes the consumer position and checks the producer position. These
operations lack a full StoreLoad barrier. A producer can therefore
commit a new record but read the old consumer position while the
consumer reads the old producer position. The producer sends no
notification and the consumer waits despite a queued record.

Insert a full barrier between publishing a consumer position and the
next producer position load. When a record bound or callback ends the
current invocation first, execute the barrier before returning so the
load in a later invocation completes the same handshake.

Add an edge-triggered epoll test that drains one record per call while a
concurrent producer fills the ring. Without the barrier, a missed
notification leaves the producer dropping records from a full ring while
the consumer times out. Document that bounded consumers and callbacks
that terminate consumption must drain before waiting again.

Fixes: bf99c936f947 ("libbpf: Add BPF ring buffer support")
Reported-by: Andrew Werner <awerner32@gmail.com>
Reported-by: Sashiko <sashiko-bot@kernel.org>
Closes: https://lore.kernel.org/bpf/20260614015716.945AF1F000E9@smtp.kernel.org/
Assisted-by: Codex:gpt-5.5
Signed-off-by: Tamir Duberstein <tamird@kernel.org>
---
 tools/lib/bpf/libbpf.h                           | 23 +++++++
 tools/lib/bpf/ringbuf.c                          | 24 +++++--
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 83 ++++++++++++++++++++++++
 3 files changed, 123 insertions(+), 7 deletions(-)

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index ae46b17feaa6..3a649ed87034 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1440,6 +1440,11 @@ struct ring;
 struct user_ring_buffer;
 
 /* Callback-based consumption is unsupported for BPF_F_RB_OVERWRITE maps. */
+/*
+ * A negative return stops consumption; non-negative values continue. Stopping
+ * can leave records queued without a new readiness notification. Before
+ * waiting for readiness again, consume until no records remain.
+ */
 typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size);
 
 struct ring_buffer_opts {
@@ -1456,6 +1461,20 @@ LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 				ring_buffer_sample_fn sample_cb, void *ctx);
 LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms);
 LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb);
+
+/**
+ * @brief **ring_buffer__consume_n()** consumes up to a requested number of
+ * records from a ring buffer manager without event polling.
+ *
+ * @param rb A ring buffer manager object.
+ * @param n Maximum number of records to consume.
+ * @return The number of records consumed, or a negative error code on failure.
+ *
+ * Reaching the requested bound does not establish that every ring is empty.
+ * Records can remain queued without a new readiness notification. Before
+ * calling ring_buffer__poll() or waiting on ring_buffer__epoll_fd(), call
+ * ring_buffer__consume() until it returns 0.
+ */
 LIBBPF_API int ring_buffer__consume_n(struct ring_buffer *rb, size_t n);
 LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
 
@@ -1538,6 +1557,10 @@ LIBBPF_API int ring__consume(struct ring *r);
  * @param r A ringbuffer object.
  * @param n Maximum number of records to consume.
  * @return The number of records consumed, or a negative error code on failure.
+ *
+ * Reaching the requested bound does not establish that the ring is empty.
+ * Records can remain queued without a new readiness notification. Before
+ * waiting on ring__map_fd(), call ring__consume() until it returns 0.
  */
 LIBBPF_API int ring__consume_n(struct ring *r, size_t n);
 
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 141f2cbe56eb..0598f6c2f7da 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -271,7 +271,7 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 		return 0;
 
 	cons_pos = __atomic_load_n(r->consumer_pos, __ATOMIC_ACQUIRE);
-	do {
+	for (;;) {
 		got_new_data = false;
 		prod_pos = __atomic_load_n(r->producer_pos, __ATOMIC_ACQUIRE);
 		/* Positions wrap; the consumer cannot logically pass the producer. */
@@ -279,9 +279,9 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 			len_ptr = r->data + (cons_pos & r->mask);
 			len = __atomic_load_n(len_ptr, __ATOMIC_ACQUIRE);
 
-			/* sample not committed yet, bail out for now */
+			/* Retry a busy record once after publishing prior records. */
 			if (len & BPF_RINGBUF_BUSY_BIT)
-				goto done;
+				break;
 
 			got_new_data = true;
 			cons_pos += roundup_len(len);
@@ -294,7 +294,8 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 					__atomic_store_n(r->consumer_pos,
 							 cons_pos,
 							 __ATOMIC_RELEASE);
-					return err;
+					cnt = err;
+					break;
 				}
 				cnt++;
 			}
@@ -303,10 +304,19 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 					 __ATOMIC_RELEASE);
 
 			if (cnt >= n)
-				goto done;
+				break;
 		}
-	} while (got_new_data);
-done:
+		if (!got_new_data)
+			break;
+
+		/*
+		 * Order the published consumer position before the next
+		 * producer-position load, whether below or in a later invocation.
+		 */
+		__atomic_thread_fence(__ATOMIC_SEQ_CST);
+		if (cnt < 0 || cnt >= n)
+			break;
+	}
 	return cnt;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index 29be2476c478..0d45a766a580 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -492,6 +492,87 @@ static void ringbuf_null_cb_subtest(void)
 	test_ringbuf_n_lskel__destroy(skel_n);
 }
 
+#define N_WAKEUP_SAMPLES 20000
+
+struct wakeup_ctx {
+	bool stop;
+};
+
+static void *wakeup_producer(void *arg)
+{
+	struct wakeup_ctx *ctx = arg;
+
+	while (!__atomic_load_n(&ctx->stop, __ATOMIC_RELAXED))
+		syscall(__NR_getpgid);
+	return NULL;
+}
+
+static void ringbuf_wakeup_subtest(void)
+{
+	struct test_ringbuf_n_lskel *skel_n;
+	struct ring_buffer *ringbuf = NULL;
+	struct epoll_event event = {
+		.events = EPOLLIN | EPOLLET,
+	};
+	struct wakeup_ctx ctx = {};
+	pthread_t producer;
+	int epoll_fd = -1;
+	int err, total = 0;
+
+	skel_n = test_ringbuf_n_lskel__open();
+	if (!ASSERT_OK_PTR(skel_n, "test_ringbuf_n_lskel__open"))
+		return;
+
+	skel_n->maps.ringbuf.max_entries = getpagesize();
+	skel_n->bss->pid = getpid();
+	skel_n->bss->value = SAMPLE_VALUE;
+
+	err = test_ringbuf_n_lskel__load(skel_n);
+	if (!ASSERT_OK(err, "test_ringbuf_n_lskel__load"))
+		goto cleanup;
+
+	err = test_ringbuf_n_lskel__attach(skel_n);
+	if (!ASSERT_OK(err, "test_ringbuf_n_lskel__attach"))
+		goto cleanup;
+
+	ringbuf = ring_buffer__new(skel_n->maps.ringbuf.map_fd,
+				   process_noop_sample, NULL, NULL);
+	if (!ASSERT_OK_PTR(ringbuf, "ring_buffer__new"))
+		goto cleanup;
+
+	epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (!ASSERT_OK_FD(epoll_fd, "epoll_create1"))
+		goto cleanup_ringbuf;
+
+	err = epoll_ctl(epoll_fd, EPOLL_CTL_ADD, skel_n->maps.ringbuf.map_fd,
+			&event);
+	if (!ASSERT_OK(err, "epoll_ctl"))
+		goto cleanup_epoll;
+
+	err = pthread_create(&producer, NULL, wakeup_producer, &ctx);
+	if (!ASSERT_OK(err, "pthread_create"))
+		goto cleanup_epoll;
+
+	while (total < N_WAKEUP_SAMPLES) {
+		err = epoll_wait(epoll_fd, &event, 1, 1000);
+		if (!ASSERT_EQ(err, 1, "epoll_wait"))
+			break;
+		while ((err = ring_buffer__consume_n(ringbuf, 1)) > 0)
+			total += err;
+		if (!ASSERT_OK(err, "ring_buffer__consume_n"))
+			break;
+	}
+
+	__atomic_store_n(&ctx.stop, true, __ATOMIC_RELAXED);
+	pthread_join(producer, NULL);
+cleanup_epoll:
+	close(epoll_fd);
+cleanup_ringbuf:
+	ring_buffer__free(ringbuf);
+cleanup:
+	test_ringbuf_n_lskel__destroy(skel_n);
+}
+
 static void ringbuf_n_subtest(void)
 {
 	struct test_ringbuf_n_lskel *skel_n;
@@ -709,6 +790,8 @@ void test_ringbuf(void)
 		ringbuf_n_subtest();
 	if (test__start_subtest("ringbuf_null_cb"))
 		ringbuf_null_cb_subtest();
+	if (test__start_subtest("ringbuf_wakeup"))
+		ringbuf_wakeup_subtest();
 	if (test__start_subtest("ringbuf_map_key"))
 		ringbuf_map_key_subtest();
 	if (test__start_subtest("ringbuf_write"))

-- 
2.55.0.rc0.159.gbe5d7338c2