bpf: pass whole link instead of prog when triggering raw tracepoint

Instead of passing prog as an argument to bpf_trace_runX() helpers, that
are called from tracepoint triggering calls, store BPF link itself
(struct bpf_raw_tp_link for raw tracepoints). This will allow to pass
extra information like BPF cookie into raw tracepoint registration.

Instead of replacing `struct bpf_prog *prog = __data;` with
corresponding `struct bpf_raw_tp_link *link = __data;` assignment in
`__bpf_trace_##call` I just passed `__data` through into underlying
bpf_trace_runX() call. This works well because we implicitly cast `void *`,
and it also avoids naming clashes with arguments coming from
tracepoint's "proto" list. We could have run into the same problem with
"prog", we just happened to not have a tracepoint that has "prog" input
argument. We are less lucky with "link", as there are tracepoints using
"link" argument name already. So instead of trying to avoid naming
conflicts, let's just remove intermediate local variable. It doesn't
hurt readibility, it's either way a bit of a maze of calls and macros,
that requires careful reading.
Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Message-ID: <20240319233852.1977493-3-andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -1607,6 +1607,11 @@ struct bpf_tracing_link {
 	struct bpf_prog *tgt_prog;
 };
 
+struct bpf_raw_tp_link {
+	struct bpf_link link;
+	struct bpf_raw_event_map *btp;
+};
+
 struct bpf_link_primer {
 	struct bpf_link *link;
 	struct file *file;

include/linux/trace_events.h

@@ -759,8 +759,11 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx);
 int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie);
 void perf_event_detach_bpf_prog(struct perf_event *event);
 int perf_event_query_prog_array(struct perf_event *event, void __user *info);
-int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
-int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
+
+struct bpf_raw_tp_link;
+int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link);
+int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link);
+
 struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name);
 void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp);
 int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
@@ -788,11 +791,12 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info)
 {
 	return -EOPNOTSUPP;
 }
-static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p)
+struct bpf_raw_tp_link;
+static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link)
 {
 	return -EOPNOTSUPP;
 }
-static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p)
+static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link)
 {
 	return -EOPNOTSUPP;
 }
@@ -903,31 +907,31 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp);
 int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie);
 void perf_event_free_bpf_prog(struct perf_event *event);
 
-void bpf_trace_run1(struct bpf_prog *prog, u64 arg1);
-void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2);
-void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run1(struct bpf_raw_tp_link *link, u64 arg1);
+void bpf_trace_run2(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2);
+void bpf_trace_run3(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3);
-void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run4(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4);
-void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run5(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4, u64 arg5);
-void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run6(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4, u64 arg5, u64 arg6);
-void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run7(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7);
-void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run8(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
 		    u64 arg8);
-void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run9(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		    u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
 		    u64 arg8, u64 arg9);
-void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run10(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		     u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
 		     u64 arg8, u64 arg9, u64 arg10);
-void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run11(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		     u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
 		     u64 arg8, u64 arg9, u64 arg10, u64 arg11);
-void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2,
+void bpf_trace_run12(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2,
 		     u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
 		     u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12);
 void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,

include/trace/bpf_probe.h

@@ -46,8 +46,7 @@
 static notrace void							\
 __bpf_trace_##call(void *__data, proto)					\
 {									\
-	struct bpf_prog *prog = __data;					\
-	CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args));	\
+	CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(__data, CAST_TO_U64(args));	\
 }
 
 #undef DECLARE_EVENT_CLASS

kernel/bpf/syscall.c

@@ -3469,17 +3469,12 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 	return err;
 }
 
-struct bpf_raw_tp_link {
-	struct bpf_link link;
-	struct bpf_raw_event_map *btp;
-};
-
 static void bpf_raw_tp_link_release(struct bpf_link *link)
 {
 	struct bpf_raw_tp_link *raw_tp =
 		container_of(link, struct bpf_raw_tp_link, link);
 
-	bpf_probe_unregister(raw_tp->btp, raw_tp->link.prog);
+	bpf_probe_unregister(raw_tp->btp, raw_tp);
 	bpf_put_raw_tracepoint(raw_tp->btp);
 }
 
@@ -3833,7 +3828,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
 		goto out_put_btp;
 	}
 
-	err = bpf_probe_register(link->btp, prog);
+	err = bpf_probe_register(link->btp, link);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
 		goto out_put_btp;

kernel/trace/bpf_trace.c

@@ -2366,8 +2366,10 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
 }
 
 static __always_inline
-void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
+void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args)
 {
+	struct bpf_prog *prog = link->link.prog;
+
 	cant_sleep();
 	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
 		bpf_prog_inc_misses_counter(prog);
@@ -2404,12 +2406,12 @@ void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
 #define __SEQ_0_11	0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11
 
 #define BPF_TRACE_DEFN_x(x)						\
-	void bpf_trace_run##x(struct bpf_prog *prog,			\
+	void bpf_trace_run##x(struct bpf_raw_tp_link *link,		\
 			      REPEAT(x, SARG, __DL_COM, __SEQ_0_11))	\
 	{								\
 		u64 args[x];						\
 		REPEAT(x, COPY, __DL_SEM, __SEQ_0_11);			\
-		__bpf_trace_run(prog, args);				\
+		__bpf_trace_run(link, args);				\
 	}								\
 	EXPORT_SYMBOL_GPL(bpf_trace_run##x)
 BPF_TRACE_DEFN_x(1);
@@ -2425,9 +2427,10 @@ BPF_TRACE_DEFN_x(10);
 BPF_TRACE_DEFN_x(11);
 BPF_TRACE_DEFN_x(12);
 
-int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link)
 {
 	struct tracepoint *tp = btp->tp;
+	struct bpf_prog *prog = link->link.prog;
 
 	/*
 	 * check that program doesn't access arguments beyond what's
@@ -2439,13 +2442,12 @@ int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
 	if (prog->aux->max_tp_access > btp->writable_size)
 		return -EINVAL;
 
-	return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func,
-						   prog);
+	return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func, link);
 }
 
-int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link)
 {
-	return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
+	return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, link);
 }
 
 int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,