[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240115131235.2914289-7-pulehui@huaweicloud.com>
Date: Mon, 15 Jan 2024 13:12:35 +0000
From: Pu Lehui <pulehui@...weicloud.com>
To: bpf@...r.kernel.org,
linux-riscv@...ts.infradead.org,
netdev@...r.kernel.org
Cc: Björn Töpel <bjorn@...nel.org>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Andrii Nakryiko <andrii@...nel.org>,
Martin KaFai Lau <martin.lau@...ux.dev>,
Song Liu <song@...nel.org>,
Yonghong Song <yhs@...com>,
John Fastabend <john.fastabend@...il.com>,
KP Singh <kpsingh@...nel.org>,
Stanislav Fomichev <sdf@...gle.com>,
Hao Luo <haoluo@...gle.com>,
Jiri Olsa <jolsa@...nel.org>,
Palmer Dabbelt <palmer@...belt.com>,
Conor Dooley <conor@...nel.org>,
Luke Nelson <luke.r.nels@...il.com>,
Pu Lehui <pulehui@...wei.com>,
Pu Lehui <pulehui@...weicloud.com>
Subject: [PATCH RESEND bpf-next v3 6/6] riscv, bpf: Optimize bswap insns with Zbb support
From: Pu Lehui <pulehui@...wei.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@...wei.com>
---
arch/riscv/net/bpf_jit.h | 69 +++++++++++++++++++++++++++++++++
arch/riscv/net/bpf_jit_comp64.c | 50 +-----------------------
2 files changed, 71 insertions(+), 48 deletions(-)
diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index b00c5c0591d2..8b35f12a4452 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -1146,12 +1146,81 @@ 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);
+ 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)
{
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);
+ 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 */
void bpf_jit_build_prologue(struct rv_jit_context *ctx);
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 18bbf8122eb3..e86e83649820 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1176,8 +1176,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
case BPF_ALU | BPF_END | BPF_FROM_LE:
switch (imm) {
case 16:
- emit_slli(rd, rd, 48, ctx);
- emit_srli(rd, rd, 48, ctx);
+ emit_zexth(rd, rd, ctx);
break;
case 32:
if (!aux->verifier_zext)
@@ -1188,54 +1187,9 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
break;
}
break;
-
case BPF_ALU | BPF_END | BPF_FROM_BE:
case BPF_ALU64 | BPF_END | BPF_FROM_LE:
- 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);
+ emit_bswap(rd, imm, ctx);
break;
/* dst = imm */
--
2.34.1
Powered by blists - more mailing lists