[PATCH bpf-next v2 6/6] riscv, bpf: Optimize bswap insns with Zbb support

[Björn Töpel]

Pu Lehui <pulehui at huaweicloud.com> writes:

> From: Pu Lehui <pulehui at huawei.com>
>
> 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 at huawei.com>
> ---
>  arch/riscv/net/bpf_jit.h        | 67 +++++++++++++++++++++++++++++++++
>  arch/riscv/net/bpf_jit_comp64.c | 50 +-----------------------
>  2 files changed, 69 insertions(+), 48 deletions(-)
>
> diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
> index 944bdd6e4..a04eed672 100644
> --- a/arch/riscv/net/bpf_jit.h
> +++ b/arch/riscv/net/bpf_jit.h
> @@ -1135,12 +1135,79 @@ static inline void emit_sextw(u8 rd, u8 rs, struct rv_jit_context *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);
> +	} else {
> +		emit_slli(rd, rs, 48, ctx);
> +		emit_srli(rd, rd, 48, ctx);
> +	}
> +}
> +

Prefer early-exit.

>  static inline void emit_zextw(u8 rd, u8 rs, struct rv_jit_context *ctx)
>  {
>  	emit_slli(rd, rs, 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);
> +	} else {
> +		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);
> +	}
> +}

Definitely early-exit for this one!

This function really show-cases why ZBB is nice! ;-)

I'll take the next rev of series for a test!


Björn