bpf: Convert BPF_DISPATCHER to use static_call() (not ftrace)

The dispatcher function is currently abusing the ftrace __fentry__
call location for its own purposes -- this obviously gives trouble
when the dispatcher and ftrace are both in use.

A previous solution tried using __attribute__((patchable_function_entry()))
which works, except it is GCC-8+ only, breaking the build on the
earlier still supported compilers. Instead use static_call() -- which
has its own annotations and does not conflict with ftrace -- to
rewrite the dispatch function.

By using: return static_call()(ctx, insni, bpf_func) you get a perfect
forwarding tail call as function body (iow a single jmp instruction).
By having the default static_call() target be bpf_dispatcher_nop_func()
it retains the default behaviour (an indirect call to the argument
function). Only once a dispatcher program is attached is the target
rewritten to directly call the JIT'ed image.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Björn Töpel <bjorn@kernel.org>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Björn Töpel <bjorn@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lkml.kernel.org/r/Y1/oBlK0yFk5c/Im@hirez.programming.kicks-ass.net
Link: https://lore.kernel.org/bpf/20221103120647.796772565@infradead.org

include/linux/bpf.h

@@ -27,6 +27,7 @@
 #include <linux/bpfptr.h>
 #include <linux/btf.h>
 #include <linux/rcupdate_trace.h>
+#include <linux/static_call.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -953,6 +954,10 @@ struct bpf_dispatcher {
 	void *rw_image;
 	u32 image_off;
 	struct bpf_ksym ksym;
+#ifdef CONFIG_HAVE_STATIC_CALL
+	struct static_call_key *sc_key;
+	void *sc_tramp;
+#endif
 };
 
 static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
@@ -970,6 +975,34 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
 int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs);
+
+/*
+ * When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn
+ * indirection with a direct call to the bpf program. If the architecture does
+ * not have STATIC_CALL, avoid a double-indirection.
+ */
+#ifdef CONFIG_HAVE_STATIC_CALL
+
+#define __BPF_DISPATCHER_SC_INIT(_name)				\
+	.sc_key = &STATIC_CALL_KEY(_name),			\
+	.sc_tramp = STATIC_CALL_TRAMP_ADDR(_name),
+
+#define __BPF_DISPATCHER_SC(name)				\
+	DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func)
+
+#define __BPF_DISPATCHER_CALL(name)				\
+	static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func)
+
+#define __BPF_DISPATCHER_UPDATE(_d, _new)			\
+	__static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new))
+
+#else
+#define __BPF_DISPATCHER_SC_INIT(name)
+#define __BPF_DISPATCHER_SC(name)
+#define __BPF_DISPATCHER_CALL(name)		bpf_func(ctx, insnsi)
+#define __BPF_DISPATCHER_UPDATE(_d, _new)
+#endif
+
 #define BPF_DISPATCHER_INIT(_name) {				\
 	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
 	.func = &_name##_func,					\
@@ -981,25 +1014,29 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 		.name  = #_name,				\
 		.lnode = LIST_HEAD_INIT(_name.ksym.lnode),	\
 	},							\
+	__BPF_DISPATCHER_SC_INIT(_name##_call)			\
 }
 
 #define DEFINE_BPF_DISPATCHER(name)					\
+	__BPF_DISPATCHER_SC(name);					\
 	noinline __nocfi unsigned int bpf_dispatcher_##name##_func(	\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func)					\
 	{								\
-		return bpf_func(ctx, insnsi);				\
+		return __BPF_DISPATCHER_CALL(name);			\
 	}								\
 	EXPORT_SYMBOL(bpf_dispatcher_##name##_func);			\
 	struct bpf_dispatcher bpf_dispatcher_##name =			\
 		BPF_DISPATCHER_INIT(bpf_dispatcher_##name);
+
 #define DECLARE_BPF_DISPATCHER(name)					\
 	unsigned int bpf_dispatcher_##name##_func(			\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func);					\
 	extern struct bpf_dispatcher bpf_dispatcher_##name;
+
 #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func
 #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name)
 void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,

kernel/bpf/dispatcher.c

@@ -4,6 +4,7 @@
 #include <linux/hash.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/static_call.h>
 
 /* The BPF dispatcher is a multiway branch code generator. The
  * dispatcher is a mechanism to avoid the performance penalty of an
@@ -104,17 +105,11 @@ static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *b
 
 static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs)
 {
-	void *old, *new, *tmp;
-	u32 noff;
-	int err;
+	void *new, *tmp;
+	u32 noff = 0;
 
-	if (!prev_num_progs) {
-		old = NULL;
-		noff = 0;
-	} else {
-		old = d->image + d->image_off;
+	if (prev_num_progs)
 		noff = d->image_off ^ (PAGE_SIZE / 2);
-	}
 
 	new = d->num_progs ? d->image + noff : NULL;
 	tmp = d->num_progs ? d->rw_image + noff : NULL;
@@ -128,11 +123,10 @@ static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs)
 			return;
 	}
 
-	err = bpf_arch_text_poke(d->func, BPF_MOD_JUMP, old, new);
-	if (err || !new)
-		return;
+	__BPF_DISPATCHER_UPDATE(d, new ?: &bpf_dispatcher_nop_func);
 
-	d->image_off = noff;
+	if (new)
+		d->image_off = noff;
 }
 
 void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,