diff options
| author | Eelco Chaudron <echaudro@redhat.com> | 2020-03-06 08:59:23 +0000 |
|---|---|---|
| committer | Alexei Starovoitov <ast@kernel.org> | 2020-03-12 17:47:38 -0700 |
| commit | d831ee84bfc9173eecf30dbbc2553ae81b996c60 (patch) | |
| tree | 52c110beaf9330261d28ed885ea246cb66e39ee8 /tools/include/uapi/linux/bpf.h | |
| parent | 4823b7210b90a10b88b0c56198f894b27a767509 (diff) | |
bpf: Add bpf_xdp_output() helper
Introduce new helper that reuses existing xdp perf_event output
implementation, but can be called from raw_tracepoint programs
that receive 'struct xdp_buff *' as a tracepoint argument.
Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/158348514556.2239.11050972434793741444.stgit@xdp-tutorial
Diffstat (limited to 'tools/include/uapi/linux/bpf.h')
| -rw-r--r-- | tools/include/uapi/linux/bpf.h | 26 |
1 files changed, 25 insertions, 1 deletions
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 15b239da775b..5d01c5c7e598 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2927,6 +2927,29 @@ union bpf_attr { * * **-ENOENT** if pidns does not exists for the current task. * + * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct xdp_buff. + * + * This helper is similar to **bpf_perf_eventoutput**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3049,7 +3072,8 @@ union bpf_attr { FN(send_signal_thread), \ FN(jiffies64), \ FN(read_branch_records), \ - FN(get_ns_current_pid_tgid), + FN(get_ns_current_pid_tgid), \ + FN(xdp_output), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call |