diff options
Diffstat (limited to 'arch/riscv/net')
-rw-r--r-- | arch/riscv/net/bpf_jit.h | 180 | ||||
-rw-r--r-- | arch/riscv/net/bpf_jit_comp32.c | 2 | ||||
-rw-r--r-- | arch/riscv/net/bpf_jit_comp64.c | 876 | ||||
-rw-r--r-- | arch/riscv/net/bpf_jit_core.c | 130 |
4 files changed, 969 insertions, 219 deletions
diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index d926e0f7ef57..f4b6b3b9edda 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -18,6 +18,11 @@ static inline bool rvc_enabled(void) return IS_ENABLED(CONFIG_RISCV_ISA_C); } +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 */ @@ -68,8 +73,9 @@ static inline bool is_creg(u8 reg) struct rv_jit_context { struct bpf_prog *prog; u16 *insns; /* RV insns */ + u16 *ro_insns; int ninsns; - int body_len; + int prologue_len; int epilogue_offset; int *offset; /* BPF to RV */ int nexentries; @@ -85,7 +91,9 @@ static inline int ninsns_rvoff(int ninsns) struct rv_jit_data { struct bpf_binary_header *header; + struct bpf_binary_header *ro_header; u8 *image; + u8 *ro_image; struct rv_jit_context ctx; }; @@ -216,8 +224,8 @@ static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx) int from, to; off++; /* BPF branch is from PC+1, RV is from PC */ - from = (insn > 0) ? ctx->offset[insn - 1] : 0; - to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0; + from = (insn > 0) ? ctx->offset[insn - 1] : ctx->prologue_len; + to = (insn + off > 0) ? ctx->offset[insn + off - 1] : ctx->prologue_len; return ninsns_rvoff(to - from); } @@ -431,11 +439,21 @@ static inline u32 rv_mulhu(u8 rd, u8 rs1, u8 rs2) return rv_r_insn(1, rs2, rs1, 3, rd, 0x33); } +static inline u32 rv_div(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 4, rd, 0x33); +} + static inline u32 rv_divu(u8 rd, u8 rs1, u8 rs2) { return rv_r_insn(1, rs2, rs1, 5, rd, 0x33); } +static inline u32 rv_rem(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 6, rd, 0x33); +} + static inline u32 rv_remu(u8 rd, u8 rs1, u8 rs2) { return rv_r_insn(1, rs2, rs1, 7, rd, 0x33); @@ -501,6 +519,16 @@ static inline u32 rv_ble(u8 rs1, u8 rs2, u16 imm12_1) return rv_bge(rs2, rs1, imm12_1); } +static inline u32 rv_lb(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x03); +} + +static inline u32 rv_lh(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x03); +} + static inline u32 rv_lw(u8 rd, u16 imm11_0, u8 rs1) { return rv_i_insn(imm11_0, rs1, 2, rd, 0x03); @@ -573,6 +601,11 @@ static inline u32 rv_fence(u8 pred, u8 succ) return rv_i_insn(imm11_0, 0, 0, 0, 0xf); } +static inline u32 rv_nop(void) +{ + return rv_i_insn(0, 0, 0, 0, 0x13); +} + /* RVC instrutions. */ static inline u16 rvc_addi4spn(u8 rd, u32 imm10) @@ -702,6 +735,33 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2) return rv_css_insn(0x6, imm, rs2, 0x2); } +/* 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. * @@ -761,11 +821,21 @@ static inline u32 rv_mulw(u8 rd, u8 rs1, u8 rs2) return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b); } +static inline u32 rv_divw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 4, rd, 0x3b); +} + static inline u32 rv_divuw(u8 rd, u8 rs1, u8 rs2) { return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b); } +static inline u32 rv_remw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 6, rd, 0x3b); +} + static inline u32 rv_remuw(u8 rd, u8 rs1, u8 rs2) { return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b); @@ -1049,9 +1119,111 @@ 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) +{ + 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); +void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog); void bpf_jit_build_epilogue(struct rv_jit_context *ctx); int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index 529a83b85c1c..f5ba73bb153d 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -1301,7 +1301,7 @@ notsupported: return 0; } -void bpf_jit_build_prologue(struct rv_jit_context *ctx) +void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog) { const s8 *fp = bpf2rv32[BPF_REG_FP]; const s8 *r1 = bpf2rv32[BPF_REG_1]; diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 00df3a8f92ac..aac190085472 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -8,8 +8,14 @@ #include <linux/bitfield.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/memory.h> +#include <linux/stop_machine.h> +#include <asm/patch.h> +#include <asm/cfi.h> #include "bpf_jit.h" +#define RV_FENTRY_NINSNS 2 + #define RV_REG_TCC RV_REG_A6 #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */ @@ -136,6 +142,42 @@ 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) +{ + /* + * Use the ro_insns(RX) to calculate the offset as the BPF program will + * finally run from this memory region. + */ + u64 ip = (u64)(ctx->ro_insns + ctx->ninsns); + s64 off = addr - ip; + s64 upper = (off + (1 << 11)) >> 12; + s64 lower = off & 0xfff; + + if (extra_pass && !in_auipc_jalr_range(off)) { + pr_err("bpf-jit: target offset 0x%llx is out of range\n", off); + return -ERANGE; + } + + emit(rv_auipc(rd, upper), ctx); + emit(rv_addi(rd, rd, lower), ctx); + return 0; +} + +/* Emit variable-length instructions for 32-bit and 64-bit imm */ static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx) { /* Note that the immediate from the add is sign-extended, @@ -217,9 +259,9 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) emit_addi(RV_REG_SP, RV_REG_SP, stack_adjust, ctx); /* Set return value. */ if (!is_tail_call) - emit_mv(RV_REG_A0, RV_REG_A5, ctx); + emit_addiw(RV_REG_A0, RV_REG_A5, 0, ctx); emit_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA, - is_tail_call ? 4 : 0, /* skip TCC init */ + is_tail_call ? (RV_FENTRY_NINSNS + 1) * 4 : 0, /* skip reserved nops and TCC init */ ctx); } @@ -298,12 +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; @@ -318,7 +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)) @@ -377,44 +413,12 @@ 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 force_jalr, +static int emit_jump_and_link(u8 rd, s64 rvoff, bool fixed_addr, struct rv_jit_context *ctx) { s64 upper, lower; - if (rvoff && is_21b_int(rvoff) && !force_jalr) { + if (rvoff && fixed_addr && is_21b_int(rvoff)) { emit(rv_jal(rd, rvoff >> 1), ctx); return 0; } else if (in_auipc_jalr_range(rvoff)) { @@ -435,24 +439,27 @@ static bool is_signed_bpf_cond(u8 cond) cond == BPF_JSGE || cond == BPF_JSLE; } -static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx) +static int emit_call(u64 addr, bool fixed_addr, struct rv_jit_context *ctx) { s64 off = 0; u64 ip; - u8 rd; - int ret; - if (addr && ctx->insns) { - ip = (u64)(long)(ctx->insns + ctx->ninsns); + if (addr && ctx->insns && ctx->ro_insns) { + /* + * Use the ro_insns(RX) to calculate the offset as the BPF + * program will finally run from this memory region. + */ + ip = (u64)(long)(ctx->ro_insns + ctx->ninsns); off = addr - ip; } - ret = emit_jump_and_link(RV_REG_RA, off, !fixed, ctx); - if (ret) - return ret; - rd = bpf_to_rv_reg(BPF_REG_0, ctx); - emit_mv(rd, RV_REG_A0, ctx); - return 0; + return emit_jump_and_link(RV_REG_RA, off, fixed_addr, ctx); +} + +static inline void emit_kcfi(u32 hash, struct rv_jit_context *ctx) +{ + if (IS_ENABLED(CONFIG_CFI_CLANG)) + emit(hash, ctx); } static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, @@ -494,32 +501,32 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, emit(is64 ? rv_amoadd_d(rs, rs, rd, 0, 0) : rv_amoadd_w(rs, rs, rd, 0, 0), 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, 0, 0) : rv_amoand_w(rs, rs, rd, 0, 0), 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, 0, 0) : rv_amoor_w(rs, rs, rd, 0, 0), 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, 0, 0) : rv_amoxor_w(rs, rs, rd, 0, 0), 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, 0, 0) : rv_amoswap_w(rs, rs, rd, 0, 0), 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: @@ -561,9 +568,11 @@ static int add_exception_handler(const struct bpf_insn *insn, { struct exception_table_entry *ex; unsigned long pc; - off_t offset; + off_t ins_offset; + off_t fixup_offset; - if (!ctx->insns || !ctx->prog->aux->extable || BPF_MODE(insn->code) != BPF_PROBE_MEM) + if (!ctx->insns || !ctx->ro_insns || !ctx->prog->aux->extable || + (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX)) return 0; if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries)) @@ -576,12 +585,17 @@ static int add_exception_handler(const struct bpf_insn *insn, return -EINVAL; ex = &ctx->prog->aux->extable[ctx->nexentries]; - pc = (unsigned long)&ctx->insns[ctx->ninsns - insn_len]; + pc = (unsigned long)&ctx->ro_insns[ctx->ninsns - insn_len]; - offset = pc - (long)&ex->insn; - if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN)) + /* + * This is the relative offset of the instruction that may fault from + * the exception table itself. This will be written to the exception + * table and if this instruction faults, the destination register will + * be set to '0' and the execution will jump to the next instruction. + */ + ins_offset = pc - (long)&ex->insn; + if (WARN_ON_ONCE(ins_offset >= 0 || ins_offset < INT_MIN)) return -ERANGE; - ex->insn = offset; /* * Since the extable follows the program, the fixup offset is always @@ -590,12 +604,25 @@ static int add_exception_handler(const struct bpf_insn *insn, * bits. We don't need to worry about buildtime or runtime sort * modifying the upper bits because the table is already sorted, and * isn't part of the main exception table. + * + * The fixup_offset is set to the next instruction from the instruction + * that may fault. The execution will jump to this after handling the + * fault. */ - offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16)); - if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset)) + fixup_offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16)); + if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, fixup_offset)) return -ERANGE; - ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) | + /* + * The offsets above have been calculated using the RO buffer but we + * need to use the R/W buffer for writes. + * switch ex to rw buffer for writing. + */ + ex = (void *)ctx->insns + ((void *)ex - (void *)ctx->ro_insns); + + ex->insn = ins_offset; + + ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, fixup_offset) | FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg); ex->type = EX_TYPE_BPF; @@ -603,6 +630,432 @@ static int add_exception_handler(const struct bpf_insn *insn, return 0; } +static int gen_jump_or_nops(void *target, void *ip, u32 *insns, bool is_call) +{ + s64 rvoff; + struct rv_jit_context ctx; + + ctx.ninsns = 0; + ctx.insns = (u16 *)insns; + + if (!target) { + emit(rv_nop(), &ctx); + emit(rv_nop(), &ctx); + return 0; + } + + rvoff = (s64)(target - ip); + return emit_jump_and_link(is_call ? RV_REG_T0 : RV_REG_ZERO, rvoff, false, &ctx); +} + +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, + void *old_addr, void *new_addr) +{ + u32 old_insns[RV_FENTRY_NINSNS], new_insns[RV_FENTRY_NINSNS]; + bool is_call = poke_type == BPF_MOD_CALL; + int ret; + + if (!is_kernel_text((unsigned long)ip) && + !is_bpf_text_address((unsigned long)ip)) + return -ENOTSUPP; + + ret = gen_jump_or_nops(old_addr, ip, old_insns, is_call); + if (ret) + return ret; + + if (memcmp(ip, old_insns, RV_FENTRY_NINSNS * 4)) + return -EFAULT; + + ret = gen_jump_or_nops(new_addr, ip, new_insns, is_call); + if (ret) + return ret; + + cpus_read_lock(); + mutex_lock(&text_mutex); + if (memcmp(ip, new_insns, RV_FENTRY_NINSNS * 4)) + ret = patch_text(ip, new_insns, RV_FENTRY_NINSNS); + mutex_unlock(&text_mutex); + cpus_read_unlock(); + + return ret; +} + +static void store_args(int nregs, int args_off, struct rv_jit_context *ctx) +{ + int i; + + for (i = 0; i < nregs; i++) { + emit_sd(RV_REG_FP, -args_off, RV_REG_A0 + i, ctx); + args_off -= 8; + } +} + +static void restore_args(int nregs, int args_off, struct rv_jit_context *ctx) +{ + int i; + + for (i = 0; i < nregs; i++) { + emit_ld(RV_REG_A0 + i, -args_off, RV_REG_FP, ctx); + args_off -= 8; + } +} + +static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_off, + int run_ctx_off, bool save_ret, struct rv_jit_context *ctx) +{ + int ret, branch_off; + struct bpf_prog *p = l->link.prog; + int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie); + + if (l->cookie) { + emit_imm(RV_REG_T1, l->cookie, ctx); + emit_sd(RV_REG_FP, -run_ctx_off + cookie_off, RV_REG_T1, ctx); + } else { + emit_sd(RV_REG_FP, -run_ctx_off + cookie_off, RV_REG_ZERO, ctx); + } + + /* arg1: prog */ + emit_imm(RV_REG_A0, (const s64)p, ctx); + /* arg2: &run_ctx */ + emit_addi(RV_REG_A1, RV_REG_FP, -run_ctx_off, ctx); + ret = emit_call((const u64)bpf_trampoline_enter(p), true, ctx); + if (ret) + return ret; + + /* if (__bpf_prog_enter(prog) == 0) + * goto skip_exec_of_prog; + */ + branch_off = ctx->ninsns; + /* nop reserved for conditional jump */ + emit(rv_nop(), ctx); + + /* store prog start time */ + emit_mv(RV_REG_S1, RV_REG_A0, ctx); + + /* arg1: &args_off */ + emit_addi(RV_REG_A0, RV_REG_FP, -args_off, ctx); + if (!p->jited) + /* arg2: progs[i]->insnsi for interpreter */ + emit_imm(RV_REG_A1, (const s64)p->insnsi, ctx); + ret = emit_call((const u64)p->bpf_func, true, ctx); + if (ret) + return ret; + + if (save_ret) { + emit_sd(RV_REG_FP, -retval_off, RV_REG_A0, ctx); + emit_sd(RV_REG_FP, -(retval_off - 8), regmap[BPF_REG_0], ctx); + } + + /* update branch with beqz */ + if (ctx->insns) { + int offset = ninsns_rvoff(ctx->ninsns - branch_off); + u32 insn = rv_beq(RV_REG_A0, RV_REG_ZERO, offset >> 1); + *(u32 *)(ctx->insns + branch_off) = insn; + } + + /* arg1: prog */ + emit_imm(RV_REG_A0, (const s64)p, ctx); + /* arg2: prog start time */ + emit_mv(RV_REG_A1, RV_REG_S1, ctx); + /* arg3: &run_ctx */ + emit_addi(RV_REG_A2, RV_REG_FP, -run_ctx_off, ctx); + ret = emit_call((const u64)bpf_trampoline_exit(p), true, ctx); + + return ret; +} + +static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, + const struct btf_func_model *m, + struct bpf_tramp_links *tlinks, + void *func_addr, u32 flags, + struct rv_jit_context *ctx) +{ + int i, ret, offset; + int *branches_off = NULL; + int stack_size = 0, nregs = m->nr_args; + int retval_off, args_off, nregs_off, ip_off, run_ctx_off, sreg_off; + struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; + struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; + struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; + bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT; + void *orig_call = func_addr; + bool save_ret; + u32 insn; + + /* Two types of generated trampoline stack layout: + * + * 1. trampoline called from function entry + * -------------------------------------- + * FP + 8 [ RA to parent func ] return address to parent + * function + * FP + 0 [ FP of parent func ] frame pointer of parent + * function + * FP - 8 [ T0 to traced func ] return address of traced + * function + * FP - 16 [ FP of traced func ] frame pointer of traced + * function + * -------------------------------------- + * + * 2. trampoline called directly + * -------------------------------------- + * FP - 8 [ RA to caller func ] return address to caller + * function + * FP - 16 [ FP of caller func ] frame pointer of caller + * function + * -------------------------------------- + * + * FP - retval_off [ return value ] BPF_TRAMP_F_CALL_ORIG or + * BPF_TRAMP_F_RET_FENTRY_RET + * [ argN ] + * [ ... ] + * FP - args_off [ arg1 ] + * + * FP - nregs_off [ regs count ] + * + * FP - ip_off [ traced func ] BPF_TRAMP_F_IP_ARG + * + * FP - run_ctx_off [ bpf_tramp_run_ctx ] + * + * FP - sreg_off [ callee saved reg ] + * + * [ pads ] pads for 16 bytes alignment + */ + + if (flags & (BPF_TRAMP_F_ORIG_STACK | BPF_TRAMP_F_SHARE_IPMODIFY)) + return -ENOTSUPP; + + /* extra regiters for struct arguments */ + for (i = 0; i < m->nr_args; i++) + if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) + nregs += round_up(m->arg_size[i], 8) / 8 - 1; + + /* 8 arguments passed by registers */ + if (nregs > 8) + return -ENOTSUPP; + + /* room of trampoline frame to store return address and frame pointer */ + stack_size += 16; + + save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); + if (save_ret) { + stack_size += 16; /* Save both A5 (BPF R0) and A0 */ + retval_off = stack_size; + } + + stack_size += nregs * 8; + args_off = stack_size; + + stack_size += 8; + nregs_off = stack_size; + + if (flags & BPF_TRAMP_F_IP_ARG) { + stack_size += 8; + ip_off = stack_size; + } + + stack_size += round_up(sizeof(struct bpf_tramp_run_ctx), 8); + run_ctx_off = stack_size; + + stack_size += 8; + sreg_off = stack_size; + + stack_size = round_up(stack_size, 16); + + if (!is_struct_ops) { + /* For the trampoline called from function entry, + * the frame of traced function and the frame of + * trampoline need to be considered. + */ + emit_addi(RV_REG_SP, RV_REG_SP, -16, ctx); + emit_sd(RV_REG_SP, 8, RV_REG_RA, ctx); + emit_sd(RV_REG_SP, 0, RV_REG_FP, ctx); + emit_addi(RV_REG_FP, RV_REG_SP, 16, ctx); + + emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx); + emit_sd(RV_REG_SP, stack_size - 8, RV_REG_T0, ctx); + emit_sd(RV_REG_SP, stack_size - 16, RV_REG_FP, ctx); + emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx); + } else { + /* emit kcfi hash */ + emit_kcfi(cfi_get_func_hash(func_addr), ctx); + /* For the trampoline called directly, just handle + * the frame of trampoline. + */ + emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx); + emit_sd(RV_REG_SP, stack_size - 8, RV_REG_RA, ctx); + emit_sd(RV_REG_SP, stack_size - 16, RV_REG_FP, ctx); + emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx); + } + + /* callee saved register S1 to pass start time */ + emit_sd(RV_REG_FP, -sreg_off, RV_REG_S1, ctx); + + /* store ip address of the traced function */ + if (flags & BPF_TRAMP_F_IP_ARG) { + emit_imm(RV_REG_T1, (const s64)func_addr, ctx); + emit_sd(RV_REG_FP, -ip_off, RV_REG_T1, ctx); + } + + emit_li(RV_REG_T1, nregs, ctx); + emit_sd(RV_REG_FP, -nregs_off, RV_REG_T1, ctx); + + store_args(nregs, args_off, ctx); + + /* skip to actual body of traced function */ + if (flags & BPF_TRAMP_F_SKIP_FRAME) + orig_call += RV_FENTRY_NINSNS * 4; + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + emit_imm(RV_REG_A0, (const s64)im, ctx); + ret = emit_call((const u64)__bpf_tramp_enter, true, ctx); + if (ret) + return ret; + } + + for (i = 0; i < fentry->nr_links; i++) { + ret = invoke_bpf_prog(fentry->links[i], args_off, retval_off, run_ctx_off, + flags & BPF_TRAMP_F_RET_FENTRY_RET, ctx); + if (ret) + return ret; + } + + if (fmod_ret->nr_links) { + branches_off = kcalloc(fmod_ret->nr_links, sizeof(int), GFP_KERNEL); + if (!branches_off) + return -ENOMEM; + + /* cleanup to avoid garbage return value confusion */ + emit_sd(RV_REG_FP, -retval_off, RV_REG_ZERO, ctx); + for (i = 0; i < fmod_ret->nr_links; i++) { + ret = invoke_bpf_prog(fmod_ret->links[i], args_off, retval_off, + run_ctx_off, true, ctx); + if (ret) + goto out; + emit_ld(RV_REG_T1, -retval_off, RV_REG_FP, ctx); + branches_off[i] = ctx->ninsns; + /* nop reserved for conditional jump */ + emit(rv_nop(), ctx); + } + } + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + restore_args(nregs, args_off, ctx); + ret = emit_call((const u64)orig_call, true, ctx); + if (ret) + goto out; + emit_sd(RV_REG_FP, -retval_off, RV_REG_A0, ctx); + emit_sd(RV_REG_FP, -(retval_off - 8), regmap[BPF_REG_0], ctx); + im->ip_after_call = ctx->insns + ctx->ninsns; + /* 2 nops reserved for auipc+jalr pair */ + emit(rv_nop(), ctx); + emit(rv_nop(), ctx); + } + + /* update branches saved in invoke_bpf_mod_ret with bnez */ + for (i = 0; ctx->insns && i < fmod_ret->nr_links; i++) { + offset = ninsns_rvoff(ctx->ninsns - branches_off[i]); + insn = rv_bne(RV_REG_T1, RV_REG_ZERO, offset >> 1); + *(u32 *)(ctx->insns + branches_off[i]) = insn; + } + + for (i = 0; i < fexit->nr_links; i++) { + ret = invoke_bpf_prog(fexit->links[i], args_off, retval_off, + run_ctx_off, false, ctx); + if (ret) + goto out; + } + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + im->ip_epilogue = ctx->insns + ctx->ninsns; + emit_imm(RV_REG_A0, (const s64)im, ctx); + ret = emit_call((const u64)__bpf_tramp_exit, true, ctx); + if (ret) + goto out; + } + + if (flags & BPF_TRAMP_F_RESTORE_REGS) + restore_args(nregs, args_off, ctx); + + if (save_ret) { + emit_ld(RV_REG_A0, -retval_off, RV_REG_FP, ctx); + emit_ld(regmap[BPF_REG_0], -(retval_off - 8), RV_REG_FP, ctx); + } + + emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx); + + if (!is_struct_ops) { + /* trampoline called from function entry */ + emit_ld(RV_REG_T0, stack_size - 8, RV_REG_SP, ctx); + emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx); + emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx); + + emit_ld(RV_REG_RA, 8, RV_REG_SP, ctx); + emit_ld(RV_REG_FP, 0, RV_REG_SP, ctx); + emit_addi(RV_REG_SP, RV_REG_SP, 16, ctx); + + if (flags & BPF_TRAMP_F_SKIP_FRAME) + /* return to parent function */ + emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx); + else + /* return to traced function */ + emit_jalr(RV_REG_ZERO, RV_REG_T0, 0, ctx); + } else { + /* trampoline called directly */ + emit_ld(RV_REG_RA, stack_size - 8, RV_REG_SP, ctx); + emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx); + emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx); + + emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx); + } + + ret = ctx->ninsns; +out: + kfree(branches_off); + return ret; +} + +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) +{ + struct bpf_tramp_image im; + struct rv_jit_context ctx; + int ret; + + ctx.ninsns = 0; + ctx.insns = NULL; + ctx.ro_insns = NULL; + ret = __arch_prepare_bpf_trampoline(&im, m, tlinks, func_addr, flags, &ctx); + + return ret < 0 ? ret : ninsns_rvoff(ctx.ninsns); +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, + void *image_end, const struct btf_func_model *m, + u32 flags, struct bpf_tramp_links *tlinks, + void *func_addr) +{ + int ret; + struct rv_jit_context ctx; + + ctx.ninsns = 0; + /* + * The bpf_int_jit_compile() uses a RW buffer (ctx.insns) to write the + * JITed instructions and later copies it to a RX region (ctx.ro_insns). + * It also uses ctx.ro_insns to calculate offsets for jumps etc. As the + * trampoline image uses the same memory area for writing and execution, + * both ctx.insns and ctx.ro_insns can be set to image. + */ + ctx.insns = image; + ctx.ro_insns = image; + ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx); + if (ret < 0) + return ret; + + bpf_flush_icache(ctx.insns, ctx.insns + ctx.ninsns); + + return ninsns_rvoff(ret); +} + int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, bool extra_pass) { @@ -622,12 +1075,25 @@ 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) { + case 0: + emit_mv(rd, rs, ctx); + break; + case 8: + emit_sextb(rd, rs, ctx); + break; + case 16: + emit_sexth(rd, rs, ctx); + break; + case 32: + emit_sextw(rd, rs, ctx); break; } - emit_mv(rd, rs, ctx); if (!is64 && !aux->verifier_zext) - emit_zext_32(rd, ctx); + emit_zextw(rd, rd, ctx); break; /* dst = dst OP src */ @@ -635,7 +1101,7 @@ 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: @@ -645,61 +1111,67 @@ 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: - emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx); + if (off) + emit(is64 ? rv_div(rd, rd, rs) : rv_divw(rd, rd, rs), 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: - emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx); + if (off) + emit(is64 ? rv_rem(rd, rd, rs) : rv_remw(rd, rd, rs), 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 */ @@ -707,72 +1179,27 @@ 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: - 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); + case BPF_ALU64 | BPF_END | BPF_FROM_LE: + emit_bswap(rd, imm, ctx); break; /* dst = imm */ @@ -780,7 +1207,7 @@ out_be: 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 */ @@ -793,7 +1220,7 @@ out_be: 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: @@ -804,7 +1231,7 @@ out_be: 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: @@ -815,7 +1242,7 @@ out_be: 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: @@ -826,7 +1253,7 @@ out_be: 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: @@ -837,7 +1264,7 @@ out_be: 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: @@ -845,30 +1272,38 @@ out_be: 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: emit_imm(RV_REG_T1, imm, ctx); - emit(is64 ? rv_divu(rd, rd, RV_REG_T1) : - rv_divuw(rd, rd, RV_REG_T1), ctx); + if (off) + emit(is64 ? rv_div(rd, rd, RV_REG_T1) : + rv_divw(rd, rd, RV_REG_T1), ctx); + else + 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: emit_imm(RV_REG_T1, imm, ctx); - emit(is64 ? rv_remu(rd, rd, RV_REG_T1) : - rv_remuw(rd, rd, RV_REG_T1), ctx); + if (off) + emit(is64 ? rv_rem(rd, rd, RV_REG_T1) : + rv_remw(rd, rd, RV_REG_T1), ctx); + else + 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: @@ -878,7 +1313,7 @@ out_be: 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: @@ -888,13 +1323,17 @@ out_be: 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 */ case BPF_JMP | BPF_JA: - rvoff = rv_offset(i, off, ctx); - ret = emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + case BPF_JMP32 | BPF_JA: + if (BPF_CLASS(code) == BPF_JMP) + rvoff = rv_offset(i, off, ctx); + else + rvoff = rv_offset(i, imm, ctx); + ret = emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); if (ret) return ret; break; @@ -925,10 +1364,13 @@ out_be: 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 */ @@ -939,8 +1381,7 @@ out_be: /* 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); } @@ -969,18 +1410,18 @@ out_be: 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; @@ -1004,7 +1445,7 @@ out_be: * 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); @@ -1013,17 +1454,21 @@ out_be: /* function call */ case BPF_JMP | BPF_CALL: { - bool fixed; + bool fixed_addr; u64 addr; mark_call(ctx); - ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &addr, - &fixed); + ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, + &addr, &fixed_addr); if (ret < 0) return ret; - ret = emit_call(fixed, addr, ctx); + + ret = emit_call(addr, fixed_addr, ctx); if (ret) return ret; + + if (insn->src_reg != BPF_PSEUDO_CALL) + emit_mv(bpf_to_rv_reg(BPF_REG_0, ctx), RV_REG_A0, ctx); break; } /* tail call */ @@ -1038,7 +1483,7 @@ out_be: break; rvoff = epilogue_offset(ctx); - ret = emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + ret = emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); if (ret) return ret; break; @@ -1050,11 +1495,19 @@ out_be: u64 imm64; imm64 = (u64)insn1.imm << 32 | (u32)imm; - emit_imm(rd, imm64, ctx); + if (bpf_pseudo_func(insn)) { + /* fixed-length insns for extra jit pass */ + ret = emit_addr(rd, imm64, extra_pass, ctx); + if (ret) + return ret; + } else { + emit_imm(rd, imm64, ctx); + } + return 1; } - /* LDX: dst = *(size *)(src + off) */ + /* LDX: dst = *(unsigned size *)(src + off) */ case BPF_LDX | BPF_MEM | BPF_B: case BPF_LDX | BPF_MEM | BPF_H: case BPF_LDX | BPF_MEM | BPF_W: @@ -1063,14 +1516,28 @@ out_be: case BPF_LDX | BPF_PROBE_MEM | BPF_H: case BPF_LDX | BPF_PROBE_MEM | BPF_W: case BPF_LDX | BPF_PROBE_MEM | BPF_DW: + /* LDSX: dst = *(signed size *)(src + off) */ + case BPF_LDX | BPF_MEMSX | BPF_B: + case BPF_LDX | BPF_MEMSX | BPF_H: + case BPF_LDX | BPF_MEMSX | BPF_W: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_B: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_H: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_W: { int insn_len, insns_start; + bool sign_ext; + + sign_ext = BPF_MODE(insn->code) == BPF_MEMSX || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX; switch (BPF_SIZE(code)) { case BPF_B: if (is_12b_int(off)) { insns_start = ctx->ninsns; - emit(rv_lbu(rd, off, rs), ctx); + if (sign_ext) + emit(rv_lb(rd, off, rs), ctx); + else + emit(rv_lbu(rd, off, rs), ctx); insn_len = ctx->ninsns - insns_start; break; } @@ -1078,15 +1545,19 @@ out_be: emit_imm(RV_REG_T1, off, ctx); emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); insns_start = ctx->ninsns; - emit(rv_lbu(rd, 0, RV_REG_T1), ctx); + if (sign_ext) + emit(rv_lb(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lbu(rd, 0, RV_REG_T1), ctx); insn_len = ctx->ninsns - insns_start; - if (insn_is_zext(&insn[1])) - return 1; break; case BPF_H: if (is_12b_int(off)) { insns_start = ctx->ninsns; - emit(rv_lhu(rd, off, rs), ctx); + if (sign_ext) + emit(rv_lh(rd, off, rs), ctx); + else + emit(rv_lhu(rd, off, rs), ctx); insn_len = ctx->ninsns - insns_start; break; } @@ -1094,15 +1565,19 @@ out_be: emit_imm(RV_REG_T1, off, ctx); emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); insns_start = ctx->ninsns; - emit(rv_lhu(rd, 0, RV_REG_T1), ctx); + if (sign_ext) + emit(rv_lh(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lhu(rd, 0, RV_REG_T1), ctx); insn_len = ctx->ninsns - insns_start; - if (insn_is_zext(&insn[1])) - return 1; break; case BPF_W: if (is_12b_int(off)) { insns_start = ctx->ninsns; - emit(rv_lwu(rd, off, rs), ctx); + if (sign_ext) + emit(rv_lw(rd, off, rs), ctx); + else + emit(rv_lwu(rd, off, rs), ctx); insn_len = ctx->ninsns - insns_start; break; } @@ -1110,10 +1585,11 @@ out_be: emit_imm(RV_REG_T1, off, ctx); emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); insns_start = ctx->ninsns; - emit(rv_lwu(rd, 0, RV_REG_T1), ctx); + if (sign_ext) + emit(rv_lw(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lwu(rd, 0, RV_REG_T1), ctx); insn_len = ctx->ninsns - insns_start; - if (insn_is_zext(&insn[1])) - return 1; break; case BPF_DW: if (is_12b_int(off)) { @@ -1134,6 +1610,9 @@ out_be: ret = add_exception_handler(insn, ctx, rd, insn_len); if (ret) return ret; + + if (BPF_SIZE(code) != BPF_DW && insn_is_zext(&insn[1])) + return 1; break; } /* speculation barrier */ @@ -1241,9 +1720,9 @@ out_be: return 0; } -void bpf_jit_build_prologue(struct rv_jit_context *ctx) +void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog) { - int stack_adjust = 0, store_offset, bpf_stack_adjust; + int i, stack_adjust = 0, store_offset, bpf_stack_adjust; bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16); if (bpf_stack_adjust) @@ -1270,6 +1749,13 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx) store_offset = stack_adjust - 8; + /* emit kcfi type preamble immediately before the first insn */ + emit_kcfi(is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash, ctx); + + /* nops reserved for auipc+jalr pair */ + for (i = 0; i < RV_FENTRY_NINSNS; i++) + emit(rv_nop(), ctx); + /* First instruction is always setting the tail-call-counter * (TCC) register. This instruction is skipped for tail calls. * Force using a 4-byte (non-compressed) instruction. @@ -1327,3 +1813,13 @@ void bpf_jit_build_epilogue(struct rv_jit_context *ctx) { __build_epilogue(false, ctx); } + +bool bpf_jit_supports_kfunc_call(void) +{ + return true; +} + +bool bpf_jit_supports_ptr_xchg(void) +{ + return true; +} diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index 737baf8715da..6b3acac30c06 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -8,6 +8,9 @@ #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/memory.h> +#include <asm/patch.h> +#include <asm/cfi.h> #include "bpf_jit.h" /* Number of iterations to try until offsets converge. */ @@ -44,7 +47,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) unsigned int prog_size = 0, extable_size = 0; bool tmp_blinded = false, extra_pass = false; struct bpf_prog *tmp, *orig_prog = prog; - int pass = 0, prev_ninsns = 0, prologue_len, i; + int pass = 0, prev_ninsns = 0, i; struct rv_jit_data *jit_data; struct rv_jit_context *ctx; @@ -83,6 +86,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = orig_prog; goto out_offset; } + + if (build_body(ctx, extra_pass, NULL)) { + prog = orig_prog; + goto out_offset; + } + for (i = 0; i < prog->len; i++) { prev_ninsns += 32; ctx->offset[i] = prev_ninsns; @@ -91,12 +100,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) for (i = 0; i < NR_JIT_ITERATIONS; i++) { pass++; ctx->ninsns = 0; + + bpf_jit_build_prologue(ctx, bpf_is_subprog(prog)); + ctx->prologue_len = ctx->ninsns; + if (build_body(ctx, extra_pass, ctx->offset)) { prog = orig_prog; goto out_offset; } - ctx->body_len = ctx->ninsns; - bpf_jit_build_prologue(ctx); + ctx->epilogue_offset = ctx->ninsns; bpf_jit_build_epilogue(ctx); @@ -108,16 +120,24 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) sizeof(struct exception_table_entry); prog_size = sizeof(*ctx->insns) * ctx->ninsns; - jit_data->header = - bpf_jit_binary_alloc(prog_size + extable_size, - &jit_data->image, - sizeof(u32), - bpf_fill_ill_insns); - if (!jit_data->header) { + jit_data->ro_header = + bpf_jit_binary_pack_alloc(prog_size + extable_size, + &jit_data->ro_image, sizeof(u32), + &jit_data->header, &jit_data->image, + bpf_fill_ill_insns); + if (!jit_data->ro_header) { prog = orig_prog; goto out_offset; } + /* + * Use the image(RW) for writing the JITed instructions. But also save + * the ro_image(RX) for calculating the offsets in the image. The RW + * image will be later copied to the RX image from where the program + * will run. The bpf_jit_binary_pack_finalize() will do this copy in the + * final step. + */ + ctx->ro_insns = (u16 *)jit_data->ro_image; ctx->insns = (u16 *)jit_data->image; /* * Now, when the image is allocated, the image can @@ -129,43 +149,49 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (i == NR_JIT_ITERATIONS) { pr_err("bpf-jit: image did not converge in <%d passes!\n", i); - if (jit_data->header) - bpf_jit_binary_free(jit_data->header); prog = orig_prog; - goto out_offset; + goto out_free_hdr; } if (extable_size) - prog->aux->extable = (void *)ctx->insns + prog_size; + prog->aux->extable = (void *)ctx->ro_insns + prog_size; skip_init_ctx: pass++; ctx->ninsns = 0; ctx->nexentries = 0; - bpf_jit_build_prologue(ctx); + bpf_jit_build_prologue(ctx, bpf_is_subprog(prog)); if (build_body(ctx, extra_pass, NULL)) { - bpf_jit_binary_free(jit_data->header); prog = orig_prog; - goto out_offset; + goto out_free_hdr; } bpf_jit_build_epilogue(ctx); if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, prog_size, pass, ctx->insns); - prog->bpf_func = (void *)ctx->insns; + prog->bpf_func = (void *)ctx->ro_insns + cfi_get_offset(); prog->jited = 1; - prog->jited_len = prog_size; - - bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); + prog->jited_len = prog_size - cfi_get_offset(); if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(jit_data->header); - prologue_len = ctx->epilogue_offset - ctx->body_len; + if (WARN_ON(bpf_jit_binary_pack_finalize(prog, jit_data->ro_header, + jit_data->header))) { + /* ro_header has been freed */ + jit_data->ro_header = NULL; + prog = orig_prog; + goto out_offset; + } + /* + * The instructions have now been copied to the ROX region from + * where they will execute. + * Write any modified data cache blocks out to memory and + * invalidate the corresponding blocks in the instruction cache. + */ + bpf_flush_icache(jit_data->ro_header, ctx->ro_insns + ctx->ninsns); for (i = 0; i < prog->len; i++) - ctx->offset[i] = ninsns_rvoff(prologue_len + - ctx->offset[i]); + ctx->offset[i] = ninsns_rvoff(ctx->offset[i]); bpf_prog_fill_jited_linfo(prog, ctx->offset); out_offset: kfree(ctx->offset); @@ -178,6 +204,14 @@ out: bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog); return prog; + +out_free_hdr: + if (jit_data->header) { + bpf_arch_text_copy(&jit_data->ro_header->size, &jit_data->header->size, + sizeof(jit_data->header->size)); + bpf_jit_binary_pack_free(jit_data->ro_header, jit_data->header); + } + goto out_offset; } u64 bpf_jit_alloc_exec_limit(void) @@ -197,3 +231,51 @@ void bpf_jit_free_exec(void *addr) { return vfree(addr); } + +void *bpf_arch_text_copy(void *dst, void *src, size_t len) +{ + int ret; + + mutex_lock(&text_mutex); + ret = patch_text_nosync(dst, src, len); + mutex_unlock(&text_mutex); + + if (ret) + return ERR_PTR(-EINVAL); + + return dst; +} + +int bpf_arch_text_invalidate(void *dst, size_t len) +{ + int ret; + + mutex_lock(&text_mutex); + ret = patch_text_set_nosync(dst, 0, len); + mutex_unlock(&text_mutex); + + return ret; +} + +void bpf_jit_free(struct bpf_prog *prog) +{ + if (prog->jited) { + struct rv_jit_data *jit_data = prog->aux->jit_data; + struct bpf_binary_header *hdr; + + /* + * If we fail the final pass of JIT (from jit_subprogs), + * the program may not be finalized yet. Call finalize here + * before freeing it. + */ + if (jit_data) { + bpf_jit_binary_pack_finalize(prog, jit_data->ro_header, jit_data->header); + kfree(jit_data); + } + hdr = bpf_jit_binary_pack_hdr(prog); + bpf_jit_binary_pack_free(hdr, NULL); + WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog)); + } + + bpf_prog_unlock_free(prog); +} |