diff options
author | Joanne Koong <joannelkoong@gmail.com> | 2022-05-23 14:07:09 -0700 |
---|---|---|
committer | Andrii Nakryiko <andrii@kernel.org> | 2022-05-23 14:31:28 -0700 |
commit | bc34dee65a65e9c920c420005b8a43f2a721a458 (patch) | |
tree | 41c97f526cb40d4cdd2c08add51d2a2d40f740a9 /kernel/bpf/ringbuf.c | |
parent | 263ae152e96253f40c2c276faad8629e096b3bad (diff) | |
download | linux-bc34dee65a65e9c920c420005b8a43f2a721a458.tar.bz2 |
bpf: Dynptr support for ring buffers
Currently, our only way of writing dynamically-sized data into a ring
buffer is through bpf_ringbuf_output but this incurs an extra memcpy
cost. bpf_ringbuf_reserve + bpf_ringbuf_commit avoids this extra
memcpy, but it can only safely support reservation sizes that are
statically known since the verifier cannot guarantee that the bpf
program won’t access memory outside the reserved space.
The bpf_dynptr abstraction allows for dynamically-sized ring buffer
reservations without the extra memcpy.
There are 3 new APIs:
long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr);
void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags);
void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags);
These closely follow the functionalities of the original ringbuf APIs.
For example, all ringbuffer dynptrs that have been reserved must be
either submitted or discarded before the program exits.
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/bpf/20220523210712.3641569-4-joannelkoong@gmail.com
Diffstat (limited to 'kernel/bpf/ringbuf.c')
-rw-r--r-- | kernel/bpf/ringbuf.c | 78 |
1 files changed, 78 insertions, 0 deletions
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 311264ab80c4..ded4faeca192 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -475,3 +475,81 @@ const struct bpf_func_proto bpf_ringbuf_query_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; + +BPF_CALL_4(bpf_ringbuf_reserve_dynptr, struct bpf_map *, map, u32, size, u64, flags, + struct bpf_dynptr_kern *, ptr) +{ + struct bpf_ringbuf_map *rb_map; + void *sample; + int err; + + if (unlikely(flags)) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + err = bpf_dynptr_check_size(size); + if (err) { + bpf_dynptr_set_null(ptr); + return err; + } + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + + sample = __bpf_ringbuf_reserve(rb_map->rb, size); + if (!sample) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + bpf_dynptr_init(ptr, sample, BPF_DYNPTR_TYPE_RINGBUF, 0, size); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = { + .func = bpf_ringbuf_reserve_dynptr, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT, +}; + +BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) +{ + if (!ptr->data) + return 0; + + bpf_ringbuf_commit(ptr->data, flags, false /* discard */); + + bpf_dynptr_set_null(ptr); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto = { + .func = bpf_ringbuf_submit_dynptr, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_ringbuf_discard_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) +{ + if (!ptr->data) + return 0; + + bpf_ringbuf_commit(ptr->data, flags, true /* discard */); + + bpf_dynptr_set_null(ptr); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto = { + .func = bpf_ringbuf_discard_dynptr, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; |