diff mbox series

[v2,5.10.y,1/2] bpf: Convert BPF_DISPATCHER to use static_call() (not ftrace)

Message ID 20240531142231.51068-2-kovalev@altlinux.org (mailing list archive)
State Handled Elsewhere
Delegated to: BPF
Headers show
Series bpf: fix warning in ftrace_verify_code() | expand

Checks

Context Check Description
netdev/tree_selection success Guessing tree name failed - patch did not apply, async
bpf/vmtest-bpf-PR fail merge-conflict

Commit Message

Vasiliy Kovalev May 31, 2024, 2:22 p.m. UTC
From: Peter Zijlstra <peterz@infradead.org>

[ Upstream commit c86df29d11dfba27c0a1f5039cd6fe387fbf4239 ]

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
Signed-off-by: Vasiliy Kovalev <kovalev@altlinux.org>
---
 include/linux/bpf.h     | 39 ++++++++++++++++++++++++++++++++++++++-
 kernel/bpf/dispatcher.c | 22 ++++++++--------------
 2 files changed, 46 insertions(+), 15 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a75faf437e750..2c4a08699de21 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -21,6 +21,7 @@ 
 #include <linux/kallsyms.h>
 #include <linux/capability.h>
 #include <linux/percpu-refcount.h>
+#include <linux/static_call.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -659,6 +660,10 @@  struct bpf_dispatcher {
 	void *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 unsigned int bpf_dispatcher_nop_func(
@@ -676,6 +681,34 @@  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, 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,					\
@@ -687,20 +720,23 @@  int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs);
 		.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 unsigned int bpf_dispatcher_##name##_func(		\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		unsigned int (*bpf_func)(const void *,			\
 					 const struct bpf_insn *))	\
 	{								\
-		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,					\
@@ -708,6 +744,7 @@  int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs);
 		unsigned int (*bpf_func)(const void *,			\
 					 const struct bpf_insn *));	\
 	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,
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index 2444bd15cc2d0..23042cfb5e809 100644
--- a/kernel/bpf/dispatcher.c
+++ b/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)
 
 static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs)
 {
-	void *old, *new;
-	u32 noff;
-	int err;
-
-	if (!prev_num_progs) {
-		old = NULL;
-		noff = 0;
-	} else {
-		old = d->image + d->image_off;
+	void *new;
+	u32 noff = 0;
+
+	if (prev_num_progs)
 		noff = d->image_off ^ (PAGE_SIZE / 2);
-	}
 
 	new = d->num_progs ? d->image + noff : NULL;
 	if (new) {
@@ -122,11 +117,10 @@  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,