diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 9626d0d487e2f90801f1684762482026f44c94c0..39e53afab8cfe707f284e9739ae13bf06e4cbb2f 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -665,6 +665,18 @@ config TOOLCHAIN_HAS_VECTOR_CRYPTO def_bool $(as-instr, .option arch$(comma) +zvkb) 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 diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index a5ce1ab76ecee0cc2581c8bb78a86ece03776993..06f17ddc02a90e7f6ebacebf10a44534c522a244 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/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); diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index 529a83b85c1c934791ed8d18e79b9527c73b83fc..90b42a9fbc5885dcb15adb09b75bd5e9c3912ed3 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/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; diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 16eb4cd11cbd6717779645f8eb31a00258225db5..1462291807b7938c08905c888aeaa17c41346276 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -142,6 +142,19 @@ static bool in_auipc_jalr_range(s64 val) val < ((1L << 31) - (1L << 11)); } +/* Modify rd pointer to alternate reg to avoid corrupting original reg */ +static void emit_sextw_alt(u8 *rd, u8 ra, struct rv_jit_context *ctx) +{ + emit_sextw(ra, *rd, ctx); + *rd = ra; +} + +static void emit_zextw_alt(u8 *rd, u8 ra, struct rv_jit_context *ctx) +{ + emit_zextw(ra, *rd, ctx); + *rd = ra; +} + /* Emit fixed-length instructions for address */ static int emit_addr(u8 rd, u64 addr, bool extra_pass, struct rv_jit_context *ctx) { @@ -327,12 +340,6 @@ static void emit_branch(u8 cond, u8 rd, u8 rs, int rvoff, emit(rv_jalr(RV_REG_ZERO, RV_REG_T1, lower), ctx); } -static void emit_zext_32(u8 reg, struct rv_jit_context *ctx) -{ - emit_slli(reg, reg, 32, ctx); - emit_srli(reg, reg, 32, ctx); -} - static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) { int tc_ninsn, off, start_insn = ctx->ninsns; @@ -347,7 +354,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) */ tc_ninsn = insn ? ctx->offset[insn] - ctx->offset[insn - 1] : ctx->offset[0]; - emit_zext_32(RV_REG_A2, ctx); + emit_zextw(RV_REG_A2, RV_REG_A2, ctx); off = offsetof(struct bpf_array, map.max_entries); if (is_12b_check(off, insn)) @@ -367,8 +374,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) * if (!prog) * goto out; */ - emit_slli(RV_REG_T2, RV_REG_A2, 3, ctx); - emit_add(RV_REG_T2, RV_REG_T2, RV_REG_A1, ctx); + emit_sh3add(RV_REG_T2, RV_REG_A2, RV_REG_A1, ctx); off = offsetof(struct bpf_array, ptrs); if (is_12b_check(off, insn)) return -1; @@ -406,38 +412,6 @@ static void init_regs(u8 *rd, u8 *rs, const struct bpf_insn *insn, *rs = bpf_to_rv_reg(insn->src_reg, ctx); } -static void emit_zext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx) -{ - emit_mv(RV_REG_T2, *rd, ctx); - emit_zext_32(RV_REG_T2, ctx); - emit_mv(RV_REG_T1, *rs, ctx); - emit_zext_32(RV_REG_T1, ctx); - *rd = RV_REG_T2; - *rs = RV_REG_T1; -} - -static void emit_sext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx) -{ - emit_addiw(RV_REG_T2, *rd, 0, ctx); - emit_addiw(RV_REG_T1, *rs, 0, ctx); - *rd = RV_REG_T2; - *rs = RV_REG_T1; -} - -static void emit_zext_32_rd_t1(u8 *rd, struct rv_jit_context *ctx) -{ - emit_mv(RV_REG_T2, *rd, ctx); - emit_zext_32(RV_REG_T2, ctx); - emit_zext_32(RV_REG_T1, ctx); - *rd = RV_REG_T2; -} - -static void emit_sext_32_rd(u8 *rd, struct rv_jit_context *ctx) -{ - emit_addiw(RV_REG_T2, *rd, 0, ctx); - *rd = RV_REG_T2; -} - static int emit_jump_and_link(u8 rd, s64 rvoff, bool fixed_addr, struct rv_jit_context *ctx) { @@ -520,32 +494,32 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, emit(is64 ? rv_amoadd_d(rs, rs, rd, 1, 1) : rv_amoadd_w(rs, rs, rd, 1, 1), ctx); if (!is64) - emit_zext_32(rs, ctx); + emit_zextw(rs, rs, ctx); break; case BPF_AND | BPF_FETCH: emit(is64 ? rv_amoand_d(rs, rs, rd, 1, 1) : rv_amoand_w(rs, rs, rd, 1, 1), ctx); if (!is64) - emit_zext_32(rs, ctx); + emit_zextw(rs, rs, ctx); break; case BPF_OR | BPF_FETCH: emit(is64 ? rv_amoor_d(rs, rs, rd, 1, 1) : rv_amoor_w(rs, rs, rd, 1, 1), ctx); if (!is64) - emit_zext_32(rs, ctx); + emit_zextw(rs, rs, ctx); break; case BPF_XOR | BPF_FETCH: emit(is64 ? rv_amoxor_d(rs, rs, rd, 1, 1) : rv_amoxor_w(rs, rs, rd, 1, 1), ctx); if (!is64) - emit_zext_32(rs, ctx); + emit_zextw(rs, rs, ctx); break; /* src_reg = atomic_xchg(dst_reg + off16, src_reg); */ case BPF_XCHG: emit(is64 ? rv_amoswap_d(rs, rs, rd, 1, 1) : rv_amoswap_w(rs, rs, rd, 1, 1), ctx); if (!is64) - emit_zext_32(rs, ctx); + emit_zextw(rs, rs, ctx); break; /* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */ case BPF_CMPXCHG: @@ -1086,7 +1060,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case BPF_ALU64 | BPF_MOV | BPF_X: if (imm == 1) { /* Special mov32 for zext */ - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; } switch (insn->off) { @@ -1094,16 +1068,17 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_mv(rd, rs, ctx); break; case 8: + emit_sextb(rd, rs, ctx); + break; case 16: - emit_slli(RV_REG_T1, rs, 64 - insn->off, ctx); - emit_srai(rd, RV_REG_T1, 64 - insn->off, ctx); + emit_sexth(rd, rs, ctx); break; case 32: - emit_addiw(rd, rs, 0, ctx); + emit_sextw(rd, rs, ctx); break; } if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; /* dst = dst OP src */ @@ -1111,7 +1086,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case BPF_ALU64 | BPF_ADD | BPF_X: emit_add(rd, rd, rs, ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU64 | BPF_SUB | BPF_X: @@ -1121,31 +1096,31 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_subw(rd, rd, rs, ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU64 | BPF_AND | BPF_X: emit_and(rd, rd, rs, ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU64 | BPF_OR | BPF_X: emit_or(rd, rd, rs, ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU64 | BPF_XOR | BPF_X: emit_xor(rd, rd, rs, ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU64 | BPF_MUL | BPF_X: emit(is64 ? rv_mul(rd, rd, rs) : rv_mulw(rd, rd, rs), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU64 | BPF_DIV | BPF_X: @@ -1154,7 +1129,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, else emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU64 | BPF_MOD | BPF_X: @@ -1163,25 +1138,25 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, else emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU64 | BPF_LSH | BPF_X: emit(is64 ? rv_sll(rd, rd, rs) : rv_sllw(rd, rd, rs), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU64 | BPF_RSH | BPF_X: emit(is64 ? rv_srl(rd, rd, rs) : rv_srlw(rd, rd, rs), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_ARSH | BPF_X: case BPF_ALU64 | BPF_ARSH | BPF_X: emit(is64 ? rv_sra(rd, rd, rs) : rv_sraw(rd, rd, rs), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; /* dst = -dst */ @@ -1189,73 +1164,27 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case BPF_ALU64 | BPF_NEG: emit_sub(rd, RV_REG_ZERO, rd, ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; /* dst = BSWAP##imm(dst) */ 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) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case 64: /* Do nothing */ 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 */ @@ -1263,7 +1192,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case BPF_ALU64 | BPF_MOV | BPF_K: emit_imm(rd, imm, ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; /* dst = dst OP imm */ @@ -1276,7 +1205,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_add(rd, rd, RV_REG_T1, ctx); } if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU64 | BPF_SUB | BPF_K: @@ -1287,7 +1216,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_sub(rd, rd, RV_REG_T1, ctx); } if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU64 | BPF_AND | BPF_K: @@ -1298,7 +1227,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_and(rd, rd, RV_REG_T1, ctx); } if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU64 | BPF_OR | BPF_K: @@ -1309,7 +1238,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_or(rd, rd, RV_REG_T1, ctx); } if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU64 | BPF_XOR | BPF_K: @@ -1320,7 +1249,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_xor(rd, rd, RV_REG_T1, ctx); } if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU64 | BPF_MUL | BPF_K: @@ -1328,7 +1257,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit(is64 ? rv_mul(rd, rd, RV_REG_T1) : rv_mulw(rd, rd, RV_REG_T1), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_K: @@ -1340,7 +1269,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit(is64 ? rv_divu(rd, rd, RV_REG_T1) : rv_divuw(rd, rd, RV_REG_T1), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_MOD | BPF_K: case BPF_ALU64 | BPF_MOD | BPF_K: @@ -1352,14 +1281,14 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit(is64 ? rv_remu(rd, rd, RV_REG_T1) : rv_remuw(rd, rd, RV_REG_T1), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU64 | BPF_LSH | BPF_K: emit_slli(rd, rd, imm, ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU64 | BPF_RSH | BPF_K: @@ -1369,7 +1298,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit(rv_srliw(rd, rd, imm), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; case BPF_ALU | BPF_ARSH | BPF_K: case BPF_ALU64 | BPF_ARSH | BPF_K: @@ -1379,7 +1308,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit(rv_sraiw(rd, rd, imm), ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; /* JUMP off */ @@ -1420,10 +1349,13 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, rvoff = rv_offset(i, off, ctx); if (!is64) { s = ctx->ninsns; - if (is_signed_bpf_cond(BPF_OP(code))) - emit_sext_32_rd_rs(&rd, &rs, ctx); - else - emit_zext_32_rd_rs(&rd, &rs, ctx); + if (is_signed_bpf_cond(BPF_OP(code))) { + emit_sextw_alt(&rs, RV_REG_T1, ctx); + emit_sextw_alt(&rd, RV_REG_T2, ctx); + } else { + emit_zextw_alt(&rs, RV_REG_T1, ctx); + emit_zextw_alt(&rd, RV_REG_T2, ctx); + } e = ctx->ninsns; /* Adjust for extra insns */ @@ -1434,8 +1366,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, /* Adjust for and */ rvoff -= 4; emit_and(RV_REG_T1, rd, rs, ctx); - emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, - ctx); + emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx); } else { emit_branch(BPF_OP(code), rd, rs, rvoff, ctx); } @@ -1464,18 +1395,18 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case BPF_JMP32 | BPF_JSLE | BPF_K: rvoff = rv_offset(i, off, ctx); s = ctx->ninsns; - if (imm) { + if (imm) emit_imm(RV_REG_T1, imm, ctx); - rs = RV_REG_T1; - } else { - /* If imm is 0, simply use zero register. */ - rs = RV_REG_ZERO; - } + rs = imm ? RV_REG_T1 : RV_REG_ZERO; if (!is64) { - if (is_signed_bpf_cond(BPF_OP(code))) - emit_sext_32_rd(&rd, ctx); - else - emit_zext_32_rd_t1(&rd, ctx); + if (is_signed_bpf_cond(BPF_OP(code))) { + emit_sextw_alt(&rd, RV_REG_T2, ctx); + /* rs has been sign extended */ + } else { + emit_zextw_alt(&rd, RV_REG_T2, ctx); + if (imm) + emit_zextw(rs, rs, ctx); + } } e = ctx->ninsns; @@ -1499,7 +1430,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, * as t1 is used only in comparison against zero. */ if (!is64 && imm < 0) - emit_addiw(RV_REG_T1, RV_REG_T1, 0, ctx); + emit_sextw(RV_REG_T1, RV_REG_T1, ctx); e = ctx->ninsns; rvoff -= ninsns_rvoff(e - s); emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx);