Backport subject : "bpf JIT optimization based on Zba and Zbb extension"

arch/riscv/Kconfig

@@ -671,6 +671,18 @@ config TOOLCHAIN_HAS_ZBB
 	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23900
 	depends on AS_HAS_OPTION_ARCH
 
+config RISCV_ISA_ZBA
+	bool "Zba extension support for bit manipulation instructions"
+	default y
+	help
+	   Add support for enabling optimisations in the kernel when the Zba
+	   extension is detected at boot.
+
+	   The Zba extension provides instructions to accelerate the generation
+	   of addresses that index into arrays of basic data types.
+
+	   If you don't know what to do here, say Y.
+
 config RISCV_ISA_ZBB
 	bool "Zbb extension support for bit manipulation instructions"
 	depends on TOOLCHAIN_HAS_ZBB

arch/riscv/net/bpf_jit.h

@@ -18,6 +18,16 @@ static inline bool rvc_enabled(void)
 	return IS_ENABLED(CONFIG_RISCV_ISA_C);
 }
 
+static inline bool rvzba_enabled(void)
+{
+	return IS_ENABLED(CONFIG_RISCV_ISA_ZBA) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBA);
+}
+
+static inline bool rvzbb_enabled(void)
+{
+	return IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBB);
+}
+
 enum {
 	RV_REG_ZERO =	0,	/* The constant value 0 */
 	RV_REG_RA =	1,	/* Return address */
@@ -730,6 +740,44 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2)
 	return rv_css_insn(0x6, imm, rs2, 0x2);
 }
 
+/* RVZBA instructions. */
+static inline u32 rvzba_sh2add(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0x10, rs2, rs1, 0x4, rd, 0x33);
+}
+
+static inline u32 rvzba_sh3add(u8 rd, u8 rs1, u8 rs2)
+{
+	return rv_r_insn(0x10, rs2, rs1, 0x6, rd, 0x33);
+}
+
+/* RVZBB instrutions. */
+static inline u32 rvzbb_sextb(u8 rd, u8 rs1)
+{
+	return rv_i_insn(0x604, rs1, 1, rd, 0x13);
+}
+
+static inline u32 rvzbb_sexth(u8 rd, u8 rs1)
+{
+	return rv_i_insn(0x605, rs1, 1, rd, 0x13);
+}
+
+static inline u32 rvzbb_zexth(u8 rd, u8 rs)
+{
+	if (IS_ENABLED(CONFIG_64BIT))
+		return rv_i_insn(0x80, rs, 4, rd, 0x3b);
+
+	return rv_i_insn(0x80, rs, 4, rd, 0x33);
+}
+
+static inline u32 rvzbb_rev8(u8 rd, u8 rs)
+{
+	if (IS_ENABLED(CONFIG_64BIT))
+		return rv_i_insn(0x6b8, rs, 5, rd, 0x13);
+
+	return rv_i_insn(0x698, rs, 5, rd, 0x13);
+}
+
 /*
  * RV64-only instructions.
  *
@@ -905,6 +953,14 @@ static inline u16 rvc_sdsp(u32 imm9, u8 rs2)
 	return rv_css_insn(0x7, imm, rs2, 0x2);
 }
 
+/* RV64-only ZBA instructions. */
+
+static inline u32 rvzba_zextw(u8 rd, u8 rs1)
+{
+	/* add.uw rd, rs1, ZERO */
+	return rv_r_insn(0x04, RV_REG_ZERO, rs1, 0, rd, 0x3b);
+}
+
 #endif /* __riscv_xlen == 64 */
 
 /* Helper functions that emit RVC instructions when possible. */
@@ -1048,6 +1104,28 @@ static inline void emit_sw(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx)
 		emit(rv_sw(rs1, off, rs2), ctx);
 }
 
+static inline void emit_sh2add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvzba_enabled()) {
+		emit(rvzba_sh2add(rd, rs1, rs2), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs1, 2, ctx);
+	emit_add(rd, rd, rs2, ctx);
+}
+
+static inline void emit_sh3add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
+{
+	if (rvzba_enabled()) {
+		emit(rvzba_sh3add(rd, rs1, rs2), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs1, 3, ctx);
+	emit_add(rd, rd, rs2, ctx);
+}
+
 /* RV64-only helper functions. */
 #if __riscv_xlen == 64
 
@@ -1087,6 +1165,113 @@ static inline void emit_subw(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
 		emit(rv_subw(rd, rs1, rs2), ctx);
 }
 
+static inline void emit_sextb(u8 rd, u8 rs, struct rv_jit_context *ctx)
+{
+	if (rvzbb_enabled()) {
+		emit(rvzbb_sextb(rd, rs), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs, 56, ctx);
+	emit_srai(rd, rd, 56, ctx);
+}
+
+static inline void emit_sexth(u8 rd, u8 rs, struct rv_jit_context *ctx)
+{
+	if (rvzbb_enabled()) {
+		emit(rvzbb_sexth(rd, rs), ctx);
+		return;
+	}
+
+	emit_slli(rd, rs, 48, ctx);
+	emit_srai(rd, rd, 48, ctx);
+}
+
+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)
+{
+	if (rvzba_enabled()) {
+		emit(rvzba_zextw(rd, rs), ctx);
+		return;
+	}
+
+	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);

arch/riscv/net/bpf_jit_comp32.c

@@ -811,8 +811,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 	 * if (!prog)
 	 *   goto out;
 	 */
-	emit(rv_slli(RV_REG_T0, lo(idx_reg), 2), ctx);
-	emit(rv_add(RV_REG_T0, RV_REG_T0, lo(arr_reg)), ctx);
+	emit_sh2add(RV_REG_T0, lo(idx_reg), lo(arr_reg), ctx);
 	off = offsetof(struct bpf_array, ptrs);
 	if (is_12b_check(off, insn))
 		return -1;