diff options
| author | Jerin Jacob <jerinj@marvell.com> | 2019-09-02 09:14:48 +0300 |
|---|---|---|
| committer | Daniel Borkmann <daniel@iogearbox.net> | 2019-09-03 16:44:40 +0300 |
| commit | 504792e07a44844f24e9d79913e4a2f8373cd332 (patch) | |
| tree | 2a1df20689ac52cb0fd6b063f1bf8127dcddd503 /arch/arm64/net | |
| parent | 53092f7e074936df43aa4dbf4b6c3df812f3dab9 (diff) | |
| download | linux-504792e07a44844f24e9d79913e4a2f8373cd332.tar.xz | |
arm64: bpf: optimize modulo operation
Optimize modulo operation instruction generation by
using single MSUB instruction vs MUL followed by SUB
instruction scheme.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Diffstat (limited to 'arch/arm64/net')
| -rw-r--r-- | arch/arm64/net/bpf_jit.h | 3 | ||||
| -rw-r--r-- | arch/arm64/net/bpf_jit_comp.c | 6 |
2 files changed, 5 insertions, 4 deletions
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index cb7ab50b7657..eb73f9f72c46 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -171,6 +171,9 @@ /* Rd = Ra + Rn * Rm */ #define A64_MADD(sf, Rd, Ra, Rn, Rm) aarch64_insn_gen_data3(Rd, Ra, Rn, Rm, \ A64_VARIANT(sf), AARCH64_INSN_DATA3_MADD) +/* Rd = Ra - Rn * Rm */ +#define A64_MSUB(sf, Rd, Ra, Rn, Rm) aarch64_insn_gen_data3(Rd, Ra, Rn, Rm, \ + A64_VARIANT(sf), AARCH64_INSN_DATA3_MSUB) /* Rd = Rn * Rm */ #define A64_MUL(sf, Rd, Rn, Rm) A64_MADD(sf, Rd, A64_ZR, Rn, Rm) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index f5b437f8a22b..cdc79de0c794 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -409,8 +409,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, break; case BPF_MOD: emit(A64_UDIV(is64, tmp, dst, src), ctx); - emit(A64_MUL(is64, tmp, tmp, src), ctx); - emit(A64_SUB(is64, dst, dst, tmp), ctx); + emit(A64_MSUB(is64, dst, dst, tmp, src), ctx); break; } break; @@ -516,8 +515,7 @@ emit_bswap_uxt: case BPF_ALU64 | BPF_MOD | BPF_K: emit_a64_mov_i(is64, tmp2, imm, ctx); emit(A64_UDIV(is64, tmp, dst, tmp2), ctx); - emit(A64_MUL(is64, tmp, tmp, tmp2), ctx); - emit(A64_SUB(is64, dst, dst, tmp), ctx); + emit(A64_MSUB(is64, dst, dst, tmp, tmp2), ctx); break; case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU64 | BPF_LSH | BPF_K: |