Merge branch 'bpf-tracepoints'

Alexei Starovoitov says:

====================
allow bpf attach to tracepoints

Hi Steven, Peter,

v1->v2: addressed Peter's comments:
- fixed wording in patch 1, added ack
- refactored 2nd patch into 3:
2/10 remove unused __perf_addr macro which frees up
an argument in perf_trace_buf_submit
3/10 split perf_trace_buf_prepare into alloc and update parts, so that bpf
programs don't have to pay performance penalty for update of struct trace_entry
which is not going to be accessed by bpf
4/10 actual addition of bpf filter to perf tracepoint handler is now trivial
and bpf prog can be used as proper filter of tracepoints

v1 cover:
last time we discussed bpf+tracepoints it was a year ago [1] and the reason
we didn't proceed with that approach was that bpf would make arguments
arg1, arg2 to trace_xx(arg1, arg2) call to be exposed to bpf program
and that was considered unnecessary extension of abi. Back then I wanted
to avoid the cost of buffer alloc and field assign part in all
of the tracepoints, but looks like when optimized the cost is acceptable.
So this new apporach doesn't expose any new abi to bpf program.
The program is looking at tracepoint fields after they were copied
by perf_trace_xx() and described in /sys/kernel/debug/tracing/events/xxx/format
We made a tool [2] that takes arguments from /sys/.../format and works as:
$ tplist.py -v random:urandom_read
    int got_bits;
    int pool_left;
    int input_left;
Then these fields can be copy-pasted into bpf program like:
struct urandom_read {
    __u64 hidden_pad;
    int got_bits;
    int pool_left;
    int input_left;
};
and the program can use it:
SEC("tracepoint/random/urandom_read")
int bpf_prog(struct urandom_read *ctx)
{
    return ctx->pool_left > 0 ? 1 : 0;
}
This way the program can access tracepoint fields faster than
equivalent bpf+kprobe program, which is the main goal of these patches.

Patch 1-4 are simple changes in perf core side, please review.
I'd like to take the whole set via net-next tree, since the rest of
the patches might conflict with other bpf work going on in net-next
and we want to avoid cross-tree merge conflicts.
Alternatively we can put patches 1-4 into both tip and net-next.

Patch 9 is an example of access to tracepoint fields from bpf prog.
Patch 10 is a micro benchmark for bpf+kprobe vs bpf+tracepoint.

Note that for actual tracing tools the user doesn't need to
run tplist.py and copy-paste fields manually. The tools do it
automatically. Like argdist tool [3] can be used as:
$ argdist -H 't:block:block_rq_complete():u32:nr_sector'
where 'nr_sector' is name of tracepoint field taken from
/sys/kernel/debug/tracing/events/block/block_rq_complete/format
and appropriate bpf program is generated on the fly.

[1] http://thread.gmane.org/gmane.linux.kernel.api/8127/focus=8165
[2] https://github.com/iovisor/bcc/blob/master/tools/tplist.py
[3] https://github.com/iovisor/bcc/blob/master/tools/argdist.py
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 23 insertions, 19 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 21ee41b92e8a..b2365a6eba3d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -131,6 +131,7 @@ struct bpf_prog_type_list {
 struct bpf_prog_aux {
 	atomic_t refcnt;
 	u32 used_map_cnt;
+	u32 max_ctx_offset;
 	const struct bpf_verifier_ops *ops;
 	struct bpf_map **used_maps;
 	struct bpf_prog *prog;
@@ -160,6 +161,7 @@ struct bpf_array {
 #define MAX_TAIL_CALL_CNT 32
 
 u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
+u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 void bpf_fd_array_map_clear(struct bpf_map *map);
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f291275ffd71..eb41b535ef38 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -882,8 +882,6 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo
  */
 static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 {
-	memset(regs, 0, sizeof(*regs));
-
 	perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
 }
 
@@ -1018,7 +1016,7 @@ static inline bool perf_paranoid_kernel(void)
 }
 
 extern void perf_event_init(void);
-extern void perf_tp_event(u64 addr, u64 count, void *record,
+extern void perf_tp_event(u16 event_type, u64 count, void *record,
 			  int entry_size, struct pt_regs *regs,
 			  struct hlist_head *head, int rctx,
 			  struct task_struct *task);
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 0810f81b6db2..fe6441203b59 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -569,6 +569,7 @@ extern int trace_define_field(struct trace_event_call *call, const char *type,
 			      int is_signed, int filter_type);
 extern int trace_add_event_call(struct trace_event_call *call);
 extern int trace_remove_event_call(struct trace_event_call *call);
+extern int trace_event_get_offsets(struct trace_event_call *call);
 
 #define is_signed_type(type)	(((type)(-1)) < (type)1)
 
@@ -605,15 +606,15 @@ extern void perf_trace_del(struct perf_event *event, int flags);
 extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
-extern void *perf_trace_buf_prepare(int size, unsigned short type,
-				    struct pt_regs **regs, int *rctxp);
+void perf_trace_buf_update(void *record, u16 type);
+void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp);
 
 static inline void
-perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
+perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type,
 		       u64 count, struct pt_regs *regs, void *head,
 		       struct task_struct *task)
 {
-	perf_tp_event(addr, count, raw_data, size, regs, head, rctx, task);
+	perf_tp_event(type, count, raw_data, size, regs, head, rctx, task);
 }
 #endif
 
diff --git a/include/trace/perf.h b/include/trace/perf.h
index 26486fcd74ce..a182306eefd7 100644
--- a/include/trace/perf.h
+++ b/include/trace/perf.h
@@ -20,9 +20,6 @@
 #undef __get_bitmask
 #define __get_bitmask(field) (char *)__get_dynamic_array(field)
 
-#undef __perf_addr
-#define __perf_addr(a)	(__addr = (a))
-
 #undef __perf_count
 #define __perf_count(c)	(__count = (c))
 
@@ -37,8 +34,9 @@ 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 __addr = 0, __count = 1;					\
+	u64 __count = 1;						\
 	struct task_struct *__task = NULL;				\
 	struct hlist_head *head;					\
 	int __entry_size;						\
@@ -48,7 +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;							\
 									\
@@ -56,8 +54,7 @@ perf_trace_##call(void *__data, proto)					\
 			     sizeof(u64));				\
 	__entry_size -= sizeof(u32);					\
 									\
-	entry = perf_trace_buf_prepare(__entry_size,			\
-			event_call->event.type, &__regs, &rctx);	\
+	entry = perf_trace_buf_alloc(__entry_size, &__regs, &rctx);	\
 	if (!entry)							\
 		return;							\
 									\
@@ -67,8 +64,16 @@ perf_trace_##call(void *__data, proto)					\
 									\
 	{ assign; }							\
 									\
-	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
-		__count, __regs, head, __task);				\
+	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);				\
 }
 
 /*
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 170c93bbdbb7..80679a9fae65 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -652,9 +652,6 @@ static inline notrace int trace_event_get_offsets_##call(		\
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args
 
-#undef __perf_addr
-#define __perf_addr(a)	(a)
-
 #undef __perf_count
 #define __perf_count(c)	(c)
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 23917bb47bf3..70eda5aeb304 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -92,6 +92,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_KPROBE,
 	BPF_PROG_TYPE_SCHED_CLS,
 	BPF_PROG_TYPE_SCHED_ACT,
+	BPF_PROG_TYPE_TRACEPOINT,
 };
 
 #define BPF_PSEUDO_MAP_FD	1