[PATCH bpf-next v4] libbpf: Expose API to consume one ring at a time

[PATCH bpf-next v4] libbpf: Expose API to consume one ring at a time

[Adam Sindelar]

We already provide ring_buffer__epoll_fd to enable use of external
polling systems. However, the only API available to consume the ring
buffer is ring_buffer__consume, which always checks all rings. When
polling for many events, this can be wasteful.

Signed-off-by: Adam Sindelar <adam@wowsignal.io>
---
v1->v2: Added entry to libbpf.map
v2->v3: Correctly set errno and handle overflow
v3->v4: Fixed an embarrasing typo from zealous autocomplete

 tools/lib/bpf/libbpf.h   |  1 +
 tools/lib/bpf/libbpf.map |  1 +
 tools/lib/bpf/ringbuf.c  | 22 ++++++++++++++++++++++
 3 files changed, 24 insertions(+)

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 55b97b2087540..20ccc65eb3f9d 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1195,6 +1195,7 @@ 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_ring(struct ring_buffer *rb, uint32_t ring_id);
 LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
 
 struct user_ring_buffer_opts {
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 9c7538dd5835e..42dc418b4672f 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -398,4 +398,5 @@ LIBBPF_1.3.0 {
 		bpf_prog_detach_opts;
 		bpf_program__attach_netfilter;
 		bpf_program__attach_tcx;
+		ring_buffer__consume_ring;
 } LIBBPF_1.2.0;
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 02199364db136..457469fc7d71e 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -290,6 +290,28 @@ int ring_buffer__consume(struct ring_buffer *rb)
 	return res;
 }
 
+/* Consume available data from a single RINGBUF map identified by its ID.
+ * The ring ID is returned in epoll_data by epoll_wait when called with
+ * ring_buffer__epoll_fd.
+ */
+int ring_buffer__consume_ring(struct ring_buffer *rb, uint32_t ring_id)
+{
+	struct ring *ring;
+	int64_t res;
+
+	if (ring_id >= rb->ring_cnt)
+		return libbpf_err(-EINVAL);
+
+	ring = &rb->rings[ring_id];
+	res = ringbuf_process_ring(ring);
+	if (res < 0)
+		return libbpf_err(res);
+
+	if (res > INT_MAX)
+		return INT_MAX;
+	return res;
+}
+
 /* 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.
-- 
2.39.2

RE: [PATCH bpf-next v4] libbpf: Expose API to consume one ring at a time

[John Fastabend]

Adam Sindelar wrote:
> We already provide ring_buffer__epoll_fd to enable use of external
> polling systems. However, the only API available to consume the ring
> buffer is ring_buffer__consume, which always checks all rings. When
> polling for many events, this can be wasteful.
> 
> Signed-off-by: Adam Sindelar <adam@wowsignal.io>
> ---
> v1->v2: Added entry to libbpf.map
> v2->v3: Correctly set errno and handle overflow
> v3->v4: Fixed an embarrasing typo from zealous autocomplete
> 
>  tools/lib/bpf/libbpf.h   |  1 +
>  tools/lib/bpf/libbpf.map |  1 +
>  tools/lib/bpf/ringbuf.c  | 22 ++++++++++++++++++++++
>  3 files changed, 24 insertions(+)
> 
> diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
> index 55b97b2087540..20ccc65eb3f9d 100644
> --- a/tools/lib/bpf/libbpf.h
> +++ b/tools/lib/bpf/libbpf.h
> @@ -1195,6 +1195,7 @@ 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_ring(struct ring_buffer *rb, uint32_t ring_id);
>  LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
>  
>  struct user_ring_buffer_opts {
> diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
> index 9c7538dd5835e..42dc418b4672f 100644
> --- a/tools/lib/bpf/libbpf.map
> +++ b/tools/lib/bpf/libbpf.map
> @@ -398,4 +398,5 @@ LIBBPF_1.3.0 {
>  		bpf_prog_detach_opts;
>  		bpf_program__attach_netfilter;
>  		bpf_program__attach_tcx;
> +		ring_buffer__consume_ring;
>  } LIBBPF_1.2.0;
> diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
> index 02199364db136..457469fc7d71e 100644
> --- a/tools/lib/bpf/ringbuf.c
> +++ b/tools/lib/bpf/ringbuf.c
> @@ -290,6 +290,28 @@ int ring_buffer__consume(struct ring_buffer *rb)
>  	return res;
>  }
>  
> +/* Consume available data from a single RINGBUF map identified by its ID.
> + * The ring ID is returned in epoll_data by epoll_wait when called with
> + * ring_buffer__epoll_fd.
> + */
> +int ring_buffer__consume_ring(struct ring_buffer *rb, uint32_t ring_id)
> +{
> +	struct ring *ring;
> +	int64_t res;
> +
> +	if (ring_id >= rb->ring_cnt)
> +		return libbpf_err(-EINVAL);
> +
> +	ring = &rb->rings[ring_id];
> +	res = ringbuf_process_ring(ring);
> +	if (res < 0)
> +		return libbpf_err(res);
> +
> +	if (res > INT_MAX)
> +		return INT_MAX;
> +	return res;

Why not just return int64_t here? Then skip the INT_MAX check? I would
just assume get the actual value if I was calling this.

> +}
> +
>  /* 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.
> -- 
> 2.39.2
> 
> 

Re: [PATCH bpf-next v4] libbpf: Expose API to consume one ring at a time

[Adam Sindelar]

On Thu, Jul 27, 2023 at 12:00:10PM -0700, John Fastabend wrote:
> Adam Sindelar wrote:
> > We already provide ring_buffer__epoll_fd to enable use of external
> > polling systems. However, the only API available to consume the ring
> > buffer is ring_buffer__consume, which always checks all rings. When
> > polling for many events, this can be wasteful.
> > 
> > Signed-off-by: Adam Sindelar <adam@wowsignal.io>
> > ---
> > v1->v2: Added entry to libbpf.map
> > v2->v3: Correctly set errno and handle overflow
> > v3->v4: Fixed an embarrasing typo from zealous autocomplete
> > 
> >  tools/lib/bpf/libbpf.h   |  1 +
> >  tools/lib/bpf/libbpf.map |  1 +
> >  tools/lib/bpf/ringbuf.c  | 22 ++++++++++++++++++++++
> >  3 files changed, 24 insertions(+)
> > 
> > diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
> > index 55b97b2087540..20ccc65eb3f9d 100644
> > --- a/tools/lib/bpf/libbpf.h
> > +++ b/tools/lib/bpf/libbpf.h
> > @@ -1195,6 +1195,7 @@ 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_ring(struct ring_buffer *rb, uint32_t ring_id);
> >  LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
> >  
> >  struct user_ring_buffer_opts {
> > diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
> > index 9c7538dd5835e..42dc418b4672f 100644
> > --- a/tools/lib/bpf/libbpf.map
> > +++ b/tools/lib/bpf/libbpf.map
> > @@ -398,4 +398,5 @@ LIBBPF_1.3.0 {
> >  		bpf_prog_detach_opts;
> >  		bpf_program__attach_netfilter;
> >  		bpf_program__attach_tcx;
> > +		ring_buffer__consume_ring;
> >  } LIBBPF_1.2.0;
> > diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
> > index 02199364db136..457469fc7d71e 100644
> > --- a/tools/lib/bpf/ringbuf.c
> > +++ b/tools/lib/bpf/ringbuf.c
> > @@ -290,6 +290,28 @@ int ring_buffer__consume(struct ring_buffer *rb)
> >  	return res;
> >  }
> >  
> > +/* Consume available data from a single RINGBUF map identified by its ID.
> > + * The ring ID is returned in epoll_data by epoll_wait when called with
> > + * ring_buffer__epoll_fd.
> > + */
> > +int ring_buffer__consume_ring(struct ring_buffer *rb, uint32_t ring_id)
> > +{
> > +	struct ring *ring;
> > +	int64_t res;
> > +
> > +	if (ring_id >= rb->ring_cnt)
> > +		return libbpf_err(-EINVAL);
> > +
> > +	ring = &rb->rings[ring_id];
> > +	res = ringbuf_process_ring(ring);
> > +	if (res < 0)
> > +		return libbpf_err(res);
> > +
> > +	if (res > INT_MAX)
> > +		return INT_MAX;
> > +	return res;
> 
> Why not just return int64_t here? Then skip the INT_MAX check? I would
> just assume get the actual value if I was calling this.
> 

Mainly for consistency with the existing API. So far, the comparable
LIBBPF_API functions use int. It's hard to imagine that the number of
records would exceed ~2 billion in a single call - I think the
abberation is that ringbuf_process_ring using a 64-bit counter. If you
do exceed INT_MAX records, something is probably wrong and maybe the function
should return error instead. (But that would be outside the scope of
this patch.)

> > +}
> > +
> >  /* 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.
> > -- 
> > 2.39.2
> > 
> > 
> 
> 

Re: [PATCH bpf-next v4] libbpf: Expose API to consume one ring at a time

[Yonghong Song]

On 7/27/23 1:34 AM, Adam Sindelar wrote:
> We already provide ring_buffer__epoll_fd to enable use of external
> polling systems. However, the only API available to consume the ring
> buffer is ring_buffer__consume, which always checks all rings. When
> polling for many events, this can be wasteful.
> 
> Signed-off-by: Adam Sindelar <adam@wowsignal.io>
> ---
> v1->v2: Added entry to libbpf.map
> v2->v3: Correctly set errno and handle overflow
> v3->v4: Fixed an embarrasing typo from zealous autocomplete
> 
>   tools/lib/bpf/libbpf.h   |  1 +
>   tools/lib/bpf/libbpf.map |  1 +
>   tools/lib/bpf/ringbuf.c  | 22 ++++++++++++++++++++++
>   3 files changed, 24 insertions(+)

Could you add a selftest to exercise ring_buffer__consume_ring()?
This way, people can better understand how this API could be used.

> 
> diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
> index 55b97b2087540..20ccc65eb3f9d 100644
> --- a/tools/lib/bpf/libbpf.h
> +++ b/tools/lib/bpf/libbpf.h
> @@ -1195,6 +1195,7 @@ 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_ring(struct ring_buffer *rb, uint32_t ring_id);
>   LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
>   
[...]

Re: [PATCH bpf-next v4] libbpf: Expose API to consume one ring at a time

[Adam Sindelar]

On Thu, Jul 27, 2023 at 03:11:00PM -0700, Yonghong Song wrote:
> 
> 
> On 7/27/23 1:34 AM, Adam Sindelar wrote:
> > We already provide ring_buffer__epoll_fd to enable use of external
> > polling systems. However, the only API available to consume the ring
> > buffer is ring_buffer__consume, which always checks all rings. When
> > polling for many events, this can be wasteful.
> > 
> > Signed-off-by: Adam Sindelar <adam@wowsignal.io>
> > ---
> > v1->v2: Added entry to libbpf.map
> > v2->v3: Correctly set errno and handle overflow
> > v3->v4: Fixed an embarrasing typo from zealous autocomplete
> > 
> >   tools/lib/bpf/libbpf.h   |  1 +
> >   tools/lib/bpf/libbpf.map |  1 +
> >   tools/lib/bpf/ringbuf.c  | 22 ++++++++++++++++++++++
> >   3 files changed, 24 insertions(+)
> 
> Could you add a selftest to exercise ring_buffer__consume_ring()?
> This way, people can better understand how this API could be used.
> 

Yes, will do - I'll try to send out v5 with a test case this afternoon.

As a note, I looked at the perf ring buffer API and it turns out Andrii
Nakryiko saw the same problem and solved in a similar way in 2020. (See
perf_buffer__consume_buffer).

> > 
> > diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
> > index 55b97b2087540..20ccc65eb3f9d 100644
> > --- a/tools/lib/bpf/libbpf.h
> > +++ b/tools/lib/bpf/libbpf.h
> > @@ -1195,6 +1195,7 @@ 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_ring(struct ring_buffer *rb, uint32_t ring_id);
> >   LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
> [...]