bpf, x86: small optimization in alu ops with imm

For the BPF_REG_0 (BPF_REG_A in cBPF, respectively), we can use
the short form of the opcode as dst mapping is on eax/rax and
thus save a byte per such operation. Added to add/sub/and/or/xor
for 32/64 bit when K immediate is used. There may be more such
low-hanging fruit to add in future as well.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 30 insertions, 5 deletions

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b881a979efe1..5acee5139e28 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -152,6 +152,11 @@ static bool is_ereg(u32 reg)
 			     BIT(BPF_REG_AX));
 }
 
+static bool is_axreg(u32 reg)
+{
+	return reg == BPF_REG_0;
+}
+
 /* add modifiers if 'reg' maps to x64 registers r8..r15 */
 static u8 add_1mod(u8 byte, u32 reg)
 {
@@ -445,16 +450,36 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			else if (is_ereg(dst_reg))
 				EMIT1(add_1mod(0x40, dst_reg));
 
+			/* b3 holds 'normal' opcode, b2 short form only valid
+			 * in case dst is eax/rax.
+			 */
 			switch (BPF_OP(insn->code)) {
-			case BPF_ADD: b3 = 0xC0; break;
-			case BPF_SUB: b3 = 0xE8; break;
-			case BPF_AND: b3 = 0xE0; break;
-			case BPF_OR: b3 = 0xC8; break;
-			case BPF_XOR: b3 = 0xF0; break;
+			case BPF_ADD:
+				b3 = 0xC0;
+				b2 = 0x05;
+				break;
+			case BPF_SUB:
+				b3 = 0xE8;
+				b2 = 0x2D;
+				break;
+			case BPF_AND:
+				b3 = 0xE0;
+				b2 = 0x25;
+				break;
+			case BPF_OR:
+				b3 = 0xC8;
+				b2 = 0x0D;
+				break;
+			case BPF_XOR:
+				b3 = 0xF0;
+				b2 = 0x35;
+				break;
 			}
 
 			if (is_imm8(imm32))
 				EMIT3(0x83, add_1reg(b3, dst_reg), imm32);
+			else if (is_axreg(dst_reg))
+				EMIT1_off32(b2, imm32);
 			else
 				EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32);
 			break;