bpf, x86: Use emit_nops to replace memcpy x86_nops

Move emit_nops() before emit_prologue() and replace
memcpy(prog, x86_nops[5], X86_PATCH_SIZE) with emit_nops(&prog, X86_PATCH_SIZE).
Signed-off-by: Leon Hwang <hffilwlqm@gmail.com>
Link: https://lore.kernel.org/r/20240104142226.87869-2-hffilwlqm@gmail.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

arch/x86/net/bpf_jit_comp.c

@@ -307,6 +307,25 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
 	*pprog = prog;
 }
 
+static void emit_nops(u8 **pprog, int len)
+{
+	u8 *prog = *pprog;
+	int i, noplen;
+
+	while (len > 0) {
+		noplen = len;
+
+		if (noplen > ASM_NOP_MAX)
+			noplen = ASM_NOP_MAX;
+
+		for (i = 0; i < noplen; i++)
+			EMIT1(x86_nops[noplen][i]);
+		len -= noplen;
+	}
+
+	*pprog = prog;
+}
+
 /*
  * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT
  * in arch/x86/kernel/alternative.c
@@ -385,8 +404,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
-	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
-	prog += X86_PATCH_SIZE;
+	emit_nops(&prog, X86_PATCH_SIZE);
 	if (!ebpf_from_cbpf) {
 		if (tail_call_reachable && !is_subprog)
 			/* When it's the entry of the whole tailcall context,
@@ -692,8 +710,7 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
-	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
-	prog += X86_PATCH_SIZE;
+	emit_nops(&prog, X86_PATCH_SIZE);
 
 	/* out: */
 	ctx->tail_call_direct_label = prog - start;
@@ -1055,25 +1072,6 @@ static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt,
 	}
 }
 
-static void emit_nops(u8 **pprog, int len)
-{
-	u8 *prog = *pprog;
-	int i, noplen;
-
-	while (len > 0) {
-		noplen = len;
-
-		if (noplen > ASM_NOP_MAX)
-			noplen = ASM_NOP_MAX;
-
-		for (i = 0; i < noplen; i++)
-			EMIT1(x86_nops[noplen][i]);
-		len -= noplen;
-	}
-
-	*pprog = prog;
-}
-
 /* emit the 3-byte VEX prefix
  *
  * r: same as rex.r, extra bit for ModRM reg field
@@ -2700,8 +2698,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		/* remember return value in a stack for bpf prog to access */
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 		im->ip_after_call = image + (prog - (u8 *)rw_image);
-		memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
-		prog += X86_PATCH_SIZE;
+		emit_nops(&prog, X86_PATCH_SIZE);
 	}
 
 	if (fmod_ret->nr_links) {