Merge branch 'libbpf-api-to-partially-consume-items-from-ringbuffer'

Andrea Righi says:

====================
libbpf: API to partially consume items from ringbuffer

Introduce ring__consume_n() and ring_buffer__consume_n() API to
partially consume items from one (or more) ringbuffer(s).

This can be useful, for example, to consume just a single item or when
we need to copy multiple items to a limited user-space buffer from the
ringbuffer callback.

Practical example (where this API can be used):
https://github.com/sched-ext/scx/blob/b7c06b9ed9f72cad83c31e39e9c4e2cfd8683a55/rust/scx_rustland_core/src/bpf.rs#L217

See also:
https://lore.kernel.org/lkml/20240310154726.734289-1-andrea.righi@canonical.com/T/#u

v4:
 - open a new 1.5.0 cycle

v3:
 - rename ring__consume_max() -> ring__consume_n() and
   ring_buffer__consume_max() -> ring_buffer__consume_n()
 - add new API to a new 1.5.0 cycle
 - fixed minor nits / comments

v2:
 - introduce a new API instead of changing the callback's retcode
   behavior
====================

Link: https://lore.kernel.org/r/20240406092005.92399-1-andrea.righi@canonical.com
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

4 files changed, 65 insertions, 10 deletions

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index f88ab50c0229..4f775a6dcaa0 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1293,6 +1293,7 @@ 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);
+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);
 
 /**
@@ -1367,6 +1368,17 @@ LIBBPF_API int ring__map_fd(const struct ring *r);
  */
 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.
+ *
+ * @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.
+ */
+LIBBPF_API int ring__consume_n(struct ring *r, size_t n);
+
 struct user_ring_buffer_opts {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 };
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 51732ecb1385..23d82bba021a 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -416,3 +416,9 @@ LIBBPF_1.4.0 {
 		btf__new_split;
 		btf_ext__raw_data;
 } LIBBPF_1.3.0;
+
+LIBBPF_1.5.0 {
+	global:
+		ring__consume_n;
+		ring_buffer__consume_n;
+} LIBBPF_1.4.0;
diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h
index e783a47da815..d6e5eff967cb 100644
--- a/tools/lib/bpf/libbpf_version.h
+++ b/tools/lib/bpf/libbpf_version.h
@@ -4,6 +4,6 @@
 #define __LIBBPF_VERSION_H
 
 #define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 4
+#define LIBBPF_MINOR_VERSION 5
 
 #endif /* __LIBBPF_VERSION_H */
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index aacb64278a01..99e44cf02321 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -231,7 +231,7 @@ static inline int roundup_len(__u32 len)
 	return (len + 7) / 8 * 8;
 }
 
-static int64_t ringbuf_process_ring(struct ring *r)
+static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 {
 	int *len_ptr, len, err;
 	/* 64-bit to avoid overflow in case of extreme application behavior */
@@ -268,12 +268,42 @@ static int64_t ringbuf_process_ring(struct ring *r)
 			}
 
 			smp_store_release(r->consumer_pos, cons_pos);
+
+			if (cnt >= n)
+				goto done;
 		}
 	} while (got_new_data);
 done:
 	return cnt;
 }
 
+/* Consume available ring buffer(s) data without event polling, up to 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.
+ */
+int ring_buffer__consume_n(struct ring_buffer *rb, size_t n)
+{
+	int64_t err, res = 0;
+	int i;
+
+	for (i = 0; i < rb->ring_cnt; i++) {
+		struct ring *ring = rb->rings[i];
+
+		err = ringbuf_process_ring(ring, n);
+		if (err < 0)
+			return libbpf_err(err);
+		res += err;
+		n -= err;
+
+		if (n == 0)
+			break;
+	}
+	return res;
+}
+
 /* 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
@@ -287,13 +317,15 @@ int ring_buffer__consume(struct ring_buffer *rb)
 	for (i = 0; i < rb->ring_cnt; i++) {
 		struct ring *ring = rb->rings[i];
 
-		err = ringbuf_process_ring(ring);
+		err = ringbuf_process_ring(ring, INT_MAX);
 		if (err < 0)
 			return libbpf_err(err);
 		res += err;
+		if (res > INT_MAX) {
+			res = INT_MAX;
+			break;
+		}
 	}
-	if (res > INT_MAX)
-		return INT_MAX;
 	return res;
 }
 
@@ -314,13 +346,13 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 		__u32 ring_id = rb->events[i].data.fd;
 		struct ring *ring = rb->rings[ring_id];
 
-		err = ringbuf_process_ring(ring);
+		err = ringbuf_process_ring(ring, INT_MAX);
 		if (err < 0)
 			return libbpf_err(err);
 		res += err;
 	}
 	if (res > INT_MAX)
-		return INT_MAX;
+		res = INT_MAX;
 	return res;
 }
 
@@ -371,17 +403,22 @@ int ring__map_fd(const struct ring *r)
 	return r->map_fd;
 }
 
-int ring__consume(struct ring *r)
+int ring__consume_n(struct ring *r, size_t n)
 {
-	int64_t res;
+	int res;
 
-	res = ringbuf_process_ring(r);
+	res = ringbuf_process_ring(r, n);
 	if (res < 0)
 		return libbpf_err(res);
 
 	return res > INT_MAX ? INT_MAX : res;
 }
 
+int ring__consume(struct ring *r)
+{
+	return ring__consume_n(r, INT_MAX);
+}
+
 static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
 {
 	if (rb->consumer_pos) {