bpf, x64: save several bytes when mul dest is r0/r3 anyway

Instead of unconditionally performing push/pop on rax/rdx
in case of multiplication, we can save a few bytes in case
of dest register being either BPF r0 (rax) or r3 (rdx)
since the result is written in there anyway.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/x86/net/bpf_jit_comp.c

@@ -615,7 +615,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU | BPF_MUL | BPF_X:
 		case BPF_ALU64 | BPF_MUL | BPF_K:
 		case BPF_ALU64 | BPF_MUL | BPF_X:
+			if (dst_reg != BPF_REG_0)
 				EMIT1(0x50); /* push rax */
+			if (dst_reg != BPF_REG_3)
 				EMIT1(0x52); /* push rdx */
 
 			/* mov r11, dst_reg */
@@ -636,14 +638,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			/* mul(q) r11 */
 			EMIT2(0xF7, add_1reg(0xE0, AUX_REG));
 
-			/* mov r11, rax */
-			EMIT_mov(AUX_REG, BPF_REG_0);
-
+			if (dst_reg != BPF_REG_3)
 				EMIT1(0x5A); /* pop rdx */
+			if (dst_reg != BPF_REG_0) {
+				/* mov dst_reg, rax */
+				EMIT_mov(dst_reg, BPF_REG_0);
 				EMIT1(0x58); /* pop rax */
-
-			/* mov dst_reg, r11 */
-			EMIT_mov(dst_reg, AUX_REG);
+			}
 			break;
 
 			/* shifts */