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

[Sarah Emery]

From: Pu Lehui <pulehui at huawei.com>

BugLink: https://bugs.launchpad.net/bugs/2142235

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>
Signed-off-by: Daniel Borkmann <daniel at iogearbox.net>
Tested-by: Björn Töpel <bjorn at rivosinc.com>
Acked-by: Björn Töpel <bjorn at kernel.org>
Link: https://lore.kernel.org/bpf/20240115131235.2914289-7-pulehui@huaweicloud.com
(cherry picked from commit 06a33d024838414432b6c0f51f994e7f1695b74f)
Signed-off-by: Sarah Emery <sarah.emery at canonical.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 c74302112fb9..68bc7fa0204f 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1224,8 +1224,7 @@ 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)
@@ -1236,54 +1235,9 @@ 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 */
-- 
2.51.0