linux/include/trace/perf.h
Alexei Starovoitov 98b5c2c65c 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>
2016-04-07 21:04:26 -04:00

98 lines
2.8 KiB
C

#undef TRACE_SYSTEM_VAR
#ifdef CONFIG_PERF_EVENTS
#undef __entry
#define __entry entry
#undef __get_dynamic_array
#define __get_dynamic_array(field) \
((void *)__entry + (__entry->__data_loc_##field & 0xffff))
#undef __get_dynamic_array_len
#define __get_dynamic_array_len(field) \
((__entry->__data_loc_##field >> 16) & 0xffff)
#undef __get_str
#define __get_str(field) (char *)__get_dynamic_array(field)
#undef __get_bitmask
#define __get_bitmask(field) (char *)__get_dynamic_array(field)
#undef __perf_count
#define __perf_count(c) (__count = (c))
#undef __perf_task
#define __perf_task(t) (__task = (t))
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
static notrace void \
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; \
struct hlist_head *head; \
int __entry_size; \
int __data_size; \
int rctx; \
\
__data_size = trace_event_get_offsets_##call(&__data_offsets, args); \
\
head = this_cpu_ptr(event_call->perf_events); \
if (!prog && __builtin_constant_p(!__task) && !__task && \
hlist_empty(head)) \
return; \
\
__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
sizeof(u64)); \
__entry_size -= sizeof(u32); \
\
entry = perf_trace_buf_alloc(__entry_size, &__regs, &rctx); \
if (!entry) \
return; \
\
perf_fetch_caller_regs(__regs); \
\
tstruct \
\
{ 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); \
}
/*
* This part is compiled out, it is only here as a build time check
* to make sure that if the tracepoint handling changes, the
* perf probe will fail to compile unless it too is updated.
*/
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
static inline void perf_test_probe_##call(void) \
{ \
check_trace_callback_type_##call(perf_trace_##template); \
}
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
#endif /* CONFIG_PERF_EVENTS */