mirror of
https://github.com/torvalds/linux.git
synced 2025-11-04 10:40:15 +02:00
85b67bcb7e
move trace_call_bpf() into helper function to minimize the size
of perf_trace_*() tracepoint handlers.
text data bss dec hex filename
10541679 5526646 2945024 19013349 1221ee5 vmlinux_before
10509422 5526646 2945024 18981092 121a0e4 vmlinux_after
It may seem that perf_fetch_caller_regs() can also be moved,
but that is incorrect, since ip/sp will be wrong.
bpf+tracepoint performance is not affected, since
perf_swevent_put_recursion_context() is now inlined.
export_symbol_gpl can also be dropped.
No measurable change in normal perf tracepoints.
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
90 lines
2.5 KiB
C
90 lines
2.5 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; } \
|
|
\
|
|
perf_trace_run_bpf_submit(entry, __entry_size, rctx, \
|
|
event_call, __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 */
|