bpf: Add bpf_user_ringbuf_drain() helper

In a prior change, we added a new BPF_MAP_TYPE_USER_RINGBUF map type which
will allow user-space applications to publish messages to a ring buffer
that is consumed by a BPF program in kernel-space. In order for this
map-type to be useful, it will require a BPF helper function that BPF
programs can invoke to drain samples from the ring buffer, and invoke
callbacks on those samples. This change adds that capability via a new BPF
helper function:

bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx,
                       u64 flags)

BPF programs may invoke this function to run callback_fn() on a series of
samples in the ring buffer. callback_fn() has the following signature:

long callback_fn(struct bpf_dynptr *dynptr, void *context);

Samples are provided to the callback in the form of struct bpf_dynptr *'s,
which the program can read using BPF helper functions for querying
struct bpf_dynptr's.

In order to support bpf_ringbuf_drain(), a new PTR_TO_DYNPTR register
type is added to the verifier to reflect a dynptr that was allocated by
a helper function and passed to a BPF program. Unlike PTR_TO_STACK
dynptrs which are allocated on the stack by a BPF program, PTR_TO_DYNPTR
dynptrs need not use reference tracking, as the BPF helper is trusted to
properly free the dynptr before returning. The verifier currently only
supports PTR_TO_DYNPTR registers that are also DYNPTR_TYPE_LOCAL.

Note that while the corresponding user-space libbpf logic will be added
in a subsequent patch, this patch does contain an implementation of the
.map_poll() callback for BPF_MAP_TYPE_USER_RINGBUF maps. This
.map_poll() callback guarantees that an epoll-waiting user-space
producer will receive at least one event notification whenever at least
one sample is drained in an invocation of bpf_user_ringbuf_drain(),
provided that the function is not invoked with the BPF_RB_NO_WAKEUP
flag. If the BPF_RB_FORCE_WAKEUP flag is provided, a wakeup
notification is sent even if no sample was drained.

Signed-off-by: David Vernet <void@manifault.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220920000100.477320-3-void@manifault.com

2 files changed, 47 insertions, 2 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e0dbe0c0a17e..33e543b86e1a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -451,7 +451,7 @@ enum bpf_type_flag {
 	/* DYNPTR points to memory local to the bpf program. */
 	DYNPTR_TYPE_LOCAL	= BIT(8 + BPF_BASE_TYPE_BITS),
 
-	/* DYNPTR points to a ringbuf record. */
+	/* DYNPTR points to a kernel-produced ringbuf record. */
 	DYNPTR_TYPE_RINGBUF	= BIT(9 + BPF_BASE_TYPE_BITS),
 
 	/* Size is known at compile time. */
@@ -656,6 +656,7 @@ enum bpf_reg_type {
 	PTR_TO_MEM,		 /* reg points to valid memory region */
 	PTR_TO_BUF,		 /* reg points to a read/write buffer */
 	PTR_TO_FUNC,		 /* reg points to a bpf program function */
+	PTR_TO_DYNPTR,		 /* reg points to a dynptr */
 	__BPF_REG_TYPE_MAX,
 
 	/* Extended reg_types. */
@@ -1394,6 +1395,11 @@ struct bpf_array {
 #define BPF_MAP_CAN_READ	BIT(0)
 #define BPF_MAP_CAN_WRITE	BIT(1)
 
+/* Maximum number of user-producer ring buffer samples that can be drained in
+ * a call to bpf_user_ringbuf_drain().
+ */
+#define BPF_MAX_USER_RINGBUF_SAMPLES (128 * 1024)
+
 static inline u32 bpf_map_flags_to_cap(struct bpf_map *map)
 {
 	u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
@@ -2495,6 +2501,7 @@ extern const struct bpf_func_proto bpf_loop_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_task_proto;
 extern const struct bpf_func_proto bpf_set_retval_proto;
 extern const struct bpf_func_proto bpf_get_retval_proto;
+extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto;
 
 const struct bpf_func_proto *tracing_prog_func_proto(
   enum bpf_func_id func_id, const struct bpf_prog *prog);
@@ -2639,7 +2646,7 @@ enum bpf_dynptr_type {
 	BPF_DYNPTR_TYPE_INVALID,
 	/* Points to memory that is local to the bpf program */
 	BPF_DYNPTR_TYPE_LOCAL,
-	/* Underlying data is a ringbuf record */
+	/* Underlying data is a kernel-produced ringbuf record */
 	BPF_DYNPTR_TYPE_RINGBUF,
 };
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e18c85324db6..ead35f39f185 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5388,6 +5388,43 @@ union bpf_attr {
  *	Return
  *		Current *ktime*.
  *
+ * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags)
+ *	Description
+ *		Drain samples from the specified user ring buffer, and invoke
+ *		the provided callback for each such sample:
+ *
+ *		long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ *		If **callback_fn** returns 0, the helper will continue to try
+ *		and drain the next sample, up to a maximum of
+ *		BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ *		the helper will skip the rest of the samples and return. Other
+ *		return values are not used now, and will be rejected by the
+ *		verifier.
+ *	Return
+ *		The number of drained samples if no error was encountered while
+ *		draining samples, or 0 if no samples were present in the ring
+ *		buffer. If a user-space producer was epoll-waiting on this map,
+ *		and at least one sample was drained, they will receive an event
+ *		notification notifying them of available space in the ring
+ *		buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ *		function, no wakeup notification will be sent. If the
+ *		BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ *		be sent even if no sample was drained.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EBUSY** if the ring buffer is contended, and another calling
+ *		context was concurrently draining the ring buffer.
+ *
+ *		**-EINVAL** if user-space is not properly tracking the ring
+ *		buffer due to the producer position not being aligned to 8
+ *		bytes, a sample not being aligned to 8 bytes, or the producer
+ *		position not matching the advertised length of a sample.
+ *
+ *		**-E2BIG** if user-space has tried to publish a sample which is
+ *		larger than the size of the ring buffer, or which cannot fit
+ *		within a struct bpf_dynptr.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5599,6 +5636,7 @@ union bpf_attr {
 	FN(tcp_raw_check_syncookie_ipv4),	\
 	FN(tcp_raw_check_syncookie_ipv6),	\
 	FN(ktime_get_tai_ns),		\
+	FN(user_ringbuf_drain),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper