perf, bpf: allow bpf programs attach to tracepoints
introduce BPF_PROG_TYPE_TRACEPOINT program type and allow it to be attached to the perf tracepoint handler, which will copy the arguments into the per-cpu buffer and pass it to the bpf program as its first argument. The layout of the fields can be discovered by doing 'cat /sys/kernel/debug/tracing/events/sched/sched_switch/format' prior to the compilation of the program with exception that first 8 bytes are reserved and not accessible to the program. This area is used to store the pointer to 'struct pt_regs' which some of the bpf helpers will use: +---------+ | 8 bytes | hidden 'struct pt_regs *' (inaccessible to bpf program) +---------+ | N bytes | static tracepoint fields defined in tracepoint/format (bpf readonly) +---------+ | dynamic | __dynamic_array bytes of tracepoint (inaccessible to bpf yet) +---------+ Not that all of the fields are already dumped to user space via perf ring buffer and broken application access it directly without consulting tracepoint/format. Same rule applies here: static tracepoint fields should only be accessed in a format defined in tracepoint/format. The order of fields and field sizes are not an ABI. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:

committed by
David S. Miller

parent
1e1dcd93b4
commit
98b5c2c65c
@@ -34,6 +34,7 @@ perf_trace_##call(void *__data, proto) \
|
||||
struct trace_event_call *event_call = __data; \
|
||||
struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
|
||||
struct trace_event_raw_##call *entry; \
|
||||
struct bpf_prog *prog = event_call->prog; \
|
||||
struct pt_regs *__regs; \
|
||||
u64 __count = 1; \
|
||||
struct task_struct *__task = NULL; \
|
||||
@@ -45,7 +46,7 @@ perf_trace_##call(void *__data, proto) \
|
||||
__data_size = trace_event_get_offsets_##call(&__data_offsets, args); \
|
||||
\
|
||||
head = this_cpu_ptr(event_call->perf_events); \
|
||||
if (__builtin_constant_p(!__task) && !__task && \
|
||||
if (!prog && __builtin_constant_p(!__task) && !__task && \
|
||||
hlist_empty(head)) \
|
||||
return; \
|
||||
\
|
||||
@@ -63,6 +64,13 @@ perf_trace_##call(void *__data, proto) \
|
||||
\
|
||||
{ assign; } \
|
||||
\
|
||||
if (prog) { \
|
||||
*(struct pt_regs **)entry = __regs; \
|
||||
if (!trace_call_bpf(prog, entry) || hlist_empty(head)) { \
|
||||
perf_swevent_put_recursion_context(rctx); \
|
||||
return; \
|
||||
} \
|
||||
} \
|
||||
perf_trace_buf_submit(entry, __entry_size, rctx, \
|
||||
event_call->event.type, __count, __regs, \
|
||||
head, __task); \
|
||||
|
Reference in New Issue
Block a user