bpf: Fix dispatcher patchable function entry to 5 bytes nop

The patchable_function_entry(5) might output 5 single nop
instructions (depends on toolchain), which will clash with
bpf_arch_text_poke check for 5 bytes nop instruction.

Adding early init call for dispatcher that checks and change
the patchable entry into expected 5 nop instruction if needed.

There's no need to take text_mutex, because we are using it
in early init call which is called at pre-smp time.

Fixes: ceea991a01 ("bpf: Move bpf_dispatcher function out of ftrace locations")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20221018075934.574415-1-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/x86/net/bpf_jit_comp.c

@@ -11,6 +11,7 @@
 #include <linux/bpf.h>
 #include <linux/memory.h>
 #include <linux/sort.h>
+#include <linux/init.h>
 #include <asm/extable.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
@@ -388,6 +389,18 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	return ret;
 }
 
+int __init bpf_arch_init_dispatcher_early(void *ip)
+{
+	const u8 *nop_insn = x86_nops[5];
+
+	if (is_endbr(*(u32 *)ip))
+		ip += ENDBR_INSN_SIZE;
+
+	if (memcmp(ip, nop_insn, X86_PATCH_SIZE))
+		text_poke_early(ip, nop_insn, X86_PATCH_SIZE);
+	return 0;
+}
+
 int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *old_addr, void *new_addr)
 {

include/linux/bpf.h

@@ -27,6 +27,7 @@
 #include <linux/bpfptr.h>
 #include <linux/btf.h>
 #include <linux/rcupdate_trace.h>
+#include <linux/init.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -970,6 +971,8 @@ 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);
+int __init bpf_arch_init_dispatcher_early(void *ip);
+
 #define BPF_DISPATCHER_INIT(_name) {				\
 	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
 	.func = &_name##_func,					\
@@ -983,6 +986,13 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 	},							\
 }
 
+#define BPF_DISPATCHER_INIT_CALL(_name)					\
+	static int __init _name##_init(void)				\
+	{								\
+		return bpf_arch_init_dispatcher_early(_name##_func);	\
+	}								\
+	early_initcall(_name##_init)
+
 #ifdef CONFIG_X86_64
 #define BPF_DISPATCHER_ATTRIBUTES __attribute__((patchable_function_entry(5)))
 #else
@@ -1000,7 +1010,9 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 	}								\
 	EXPORT_SYMBOL(bpf_dispatcher_##name##_func);			\
 	struct bpf_dispatcher bpf_dispatcher_##name =			\
-		BPF_DISPATCHER_INIT(bpf_dispatcher_##name);
+		BPF_DISPATCHER_INIT(bpf_dispatcher_##name);		\
+	BPF_DISPATCHER_INIT_CALL(bpf_dispatcher_##name);
+
 #define DECLARE_BPF_DISPATCHER(name)					\
 	unsigned int bpf_dispatcher_##name##_func(			\
 		const void *ctx,					\

kernel/bpf/dispatcher.c

@@ -4,6 +4,7 @@
 #include <linux/hash.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/init.h>
 
 /* The BPF dispatcher is a multiway branch code generator. The
  * dispatcher is a mechanism to avoid the performance penalty of an
@@ -90,6 +91,11 @@ int __weak arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int n
 	return -ENOTSUPP;
 }
 
+int __weak __init bpf_arch_init_dispatcher_early(void *ip)
+{
+	return -ENOTSUPP;
+}
+
 static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *buf)
 {
 	s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0];