summaryrefslogtreecommitdiffstats
path: root/include/uapi/linux/bpf.h
diff options
context:
space:
mode:
authorAlexei Starovoitov2016-09-02 03:37:22 +0200
committerDavid S. Miller2016-09-02 19:46:44 +0200
commit0515e5999a466dfe6e1924f460da599bb6821487 (patch)
treee4ba954bea80d223248c57885019b7620375164a /include/uapi/linux/bpf.h
parentbpf: support 8-byte metafield access (diff)
downloadkernel-qcow2-linux-0515e5999a466dfe6e1924f460da599bb6821487.tar.gz
kernel-qcow2-linux-0515e5999a466dfe6e1924f460da599bb6821487.tar.xz
kernel-qcow2-linux-0515e5999a466dfe6e1924f460da599bb6821487.zip
bpf: introduce BPF_PROG_TYPE_PERF_EVENT program type
Introduce BPF_PROG_TYPE_PERF_EVENT programs that can be attached to HW and SW perf events (PERF_TYPE_HARDWARE and PERF_TYPE_SOFTWARE correspondingly in uapi/linux/perf_event.h) The program visible context meta structure is struct bpf_perf_event_data { struct pt_regs regs; __u64 sample_period; }; which is accessible directly from the program: int bpf_prog(struct bpf_perf_event_data *ctx) { ... ctx->sample_period ... ... ctx->regs.ip ... } The bpf verifier rewrites the accesses into kernel internal struct bpf_perf_event_data_kern which allows changing struct perf_sample_data without affecting bpf programs. New fields can be added to the end of struct bpf_perf_event_data in the future. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/uapi/linux/bpf.h')
-rw-r--r--include/uapi/linux/bpf.h1
1 files changed, 1 insertions, 0 deletions
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e4c5a1baa993..f896dfac4ac0 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -95,6 +95,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SCHED_ACT,
BPF_PROG_TYPE_TRACEPOINT,
BPF_PROG_TYPE_XDP,
+ BPF_PROG_TYPE_PERF_EVENT,
};
#define BPF_PSEUDO_MAP_FD 1