From 38f51c07054ff4796e473dba3bff2e648378002c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 3 Oct 2019 01:45:11 +0200 Subject: [PATCH] bpf, x86: Small optimization in comparing against imm0 Replace 'cmp reg, 0' with 'test reg, reg' for comparisons against zero. Saves 1 byte of instruction encoding per occurrence. The flag results of test 'reg, reg' are identical to 'cmp reg, 0' in all cases except for AF which we don't use/care about. In terms of macro-fusibility in combination with a subsequent conditional jump instruction, both have the same properties for the jumps used in the JIT translation. For example, same JITed Cilium program can shrink a bit from e.g. 12,455 to 12,317 bytes as tests with 0 are used quite frequently. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Acked-by: John Fastabend --- arch/x86/net/bpf_jit_comp.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 991549a1c5f3..3ad2ba1ad855 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -909,6 +909,16 @@ xadd: if (is_imm8(insn->off)) case BPF_JMP32 | BPF_JSLT | BPF_K: case BPF_JMP32 | BPF_JSGE | BPF_K: case BPF_JMP32 | BPF_JSLE | BPF_K: + /* test dst_reg, dst_reg to save one extra byte */ + if (imm32 == 0) { + if (BPF_CLASS(insn->code) == BPF_JMP) + EMIT1(add_2mod(0x48, dst_reg, dst_reg)); + else if (is_ereg(dst_reg)) + EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg)); + goto emit_cond_jmp; + } + /* cmp dst_reg, imm8/32 */ if (BPF_CLASS(insn->code) == BPF_JMP) EMIT1(add_1mod(0x48, dst_reg)); -- 2.30.2