iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

riscv, bpf: Optimize bswap insns with Zbb support

Browse Source 
Optimize bswap instructions by rev8 Zbb instruction conbined with srli
instruction. And Optimize 16-bit zero-extension with Zbb support.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/bpf/20240115131235.2914289-7-pulehui@huaweicloud.com
This commit is contained in:
Pu Lehui 2024-01-15 13:12:35 +00:00 committed by Daniel Borkmann
parent 519fb722be
commit 06a33d0248
2 changed files with 71 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
arch/riscv/net/bpf_jit.h
View File

@ -1146,12 +1146,81 @@ static inline void emit_sextw(u8 rd, u8 rs, struct rv_jit_context *ctx)
emit_addiw(rd, rs, 0, ctx); emit_addiw(rd, rs, 0, ctx);
} }
static inline void emit_zexth(u8 rd, u8 rs, struct rv_jit_context *ctx)
{
if (rvzbb_enabled()) {
emit(rvzbb_zexth(rd, rs), ctx);
return;
}
emit_slli(rd, rs, 48, ctx);
emit_srli(rd, rd, 48, ctx);
}
static inline void emit_zextw(u8 rd, u8 rs, struct rv_jit_context *ctx) static inline void emit_zextw(u8 rd, u8 rs, struct rv_jit_context *ctx)
{ {
emit_slli(rd, rs, 32, ctx); emit_slli(rd, rs, 32, ctx);
emit_srli(rd, rd, 32, ctx); emit_srli(rd, rd, 32, ctx);
} }
static inline void emit_bswap(u8 rd, s32 imm, struct rv_jit_context *ctx)
{
if (rvzbb_enabled()) {
int bits = 64 - imm;
emit(rvzbb_rev8(rd, rd), ctx);
if (bits)
emit_srli(rd, rd, bits, ctx);
return;
}
emit_li(RV_REG_T2, 0, ctx);
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
if (imm == 16)
goto out_be;
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
if (imm == 32)
goto out_be;
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
out_be:
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_mv(rd, RV_REG_T2, ctx);
}
#endif /* __riscv_xlen == 64 */ #endif /* __riscv_xlen == 64 */
void bpf_jit_build_prologue(struct rv_jit_context *ctx); void bpf_jit_build_prologue(struct rv_jit_context *ctx);

50
arch/riscv/net/bpf_jit_comp64.c
View File

@ -1177,8 +1177,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
case BPF_ALU | BPF_END | BPF_FROM_LE: case BPF_ALU | BPF_END | BPF_FROM_LE:
switch (imm) { switch (imm) {
case 16: case 16:
emit_slli(rd, rd, 48, ctx); emit_zexth(rd, rd, ctx);
emit_srli(rd, rd, 48, ctx);
break; break;
case 32: case 32:
if (!aux->verifier_zext) if (!aux->verifier_zext)
@ -1189,54 +1188,9 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
break; break;
} }
break; break;
case BPF_ALU | BPF_END | BPF_FROM_BE: case BPF_ALU | BPF_END | BPF_FROM_BE:
case BPF_ALU64 | BPF_END | BPF_FROM_LE: case BPF_ALU64 | BPF_END | BPF_FROM_LE:
emit_li(RV_REG_T2, 0, ctx); emit_bswap(rd, imm, ctx);
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
if (imm == 16)
goto out_be;
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
if (imm == 32)
goto out_be;
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx);
emit_srli(rd, rd, 8, ctx);
out_be:
emit_andi(RV_REG_T1, rd, 0xff, ctx);
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx);
emit_mv(rd, RV_REG_T2, ctx);
break; break;
/* dst = imm */ /* dst = imm */