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 /include/linux/bpf.h | |
| parent | 263ae152e96253f40c2c276faad8629e096b3bad (diff) | |
| download | linux-bc34dee65a65e9c920c420005b8a43f2a721a458.tar.gz | |
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 'include/linux/bpf.h')
| -rw-r--r-- | include/linux/bpf.h | 15 |
1 files changed, 14 insertions, 1 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b26c8176b9e0..c72321b6f306 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -395,11 +395,14 @@ 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_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; -#define DYNPTR_TYPE_FLAG_MASK DYNPTR_TYPE_LOCAL +#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -2231,6 +2234,9 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; +extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto; +extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto; +extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; @@ -2402,6 +2408,13 @@ 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 */ + BPF_DYNPTR_TYPE_RINGBUF, }; +void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, + enum bpf_dynptr_type type, u32 offset, u32 size); +void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); +int bpf_dynptr_check_size(u32 size); + #endif /* _LINUX_BPF_H */ |