diff options
author | Daniel Borkmann <daniel@iogearbox.net> | 2015-12-18 01:51:56 +0300 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2015-12-19 00:04:51 +0300 |
commit | 606c88a86c77fa27cb4eac899ddced9092825bea (patch) | |
tree | 6912e097e8e74ca15f8567739eb4b215845f6bc7 /arch/x86/net | |
parent | 23bf88078afdb8f9b8071dd9f32754ebab7ba3dc (diff) | |
download | linux-606c88a86c77fa27cb4eac899ddced9092825bea.tar.xz |
bpf, x86: detect/optimize loading 0 immediates
When sometimes structs or variables need to be initialized/'memset' to 0 in
an eBPF C program, the x86 BPF JIT converts this to use immediates. We can
however save a couple of bytes (f.e. even up to 7 bytes on a single emmission
of BPF_LD | BPF_IMM | BPF_DW) in the image by detecting such case and use xor
on the dst register instead.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'arch/x86/net')
-rw-r--r-- | arch/x86/net/bpf_jit_comp.c | 26 |
1 files changed, 26 insertions, 0 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index c080e812ce85..4286f3618bd0 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -459,6 +459,18 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } case BPF_ALU | BPF_MOV | BPF_K: + /* optimization: if imm32 is zero, use 'xor <dst>,<dst>' + * to save 3 bytes. + */ + if (imm32 == 0) { + if (is_ereg(dst_reg)) + EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT2(b2, add_2reg(b3, dst_reg, dst_reg)); + break; + } + /* mov %eax, imm32 */ if (is_ereg(dst_reg)) EMIT1(add_1mod(0x40, dst_reg)); @@ -473,6 +485,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, return -EINVAL; } + /* optimization: if imm64 is zero, use 'xor <dst>,<dst>' + * to save 7 bytes. + */ + if (insn[0].imm == 0 && insn[1].imm == 0) { + b1 = add_2mod(0x48, dst_reg, dst_reg); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg)); + + insn++; + i++; + break; + } + /* movabsq %rax, imm64 */ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); EMIT(insn[0].imm, 4); |