diff options
Diffstat (limited to 'arch/riscv/net')
| -rw-r--r-- | arch/riscv/net/bpf_jit.h | 72 | ||||
| -rw-r--r-- | arch/riscv/net/bpf_jit_comp32.c | 3 | ||||
| -rw-r--r-- | arch/riscv/net/bpf_jit_comp64.c | 778 | ||||
| -rw-r--r-- | arch/riscv/net/bpf_jit_core.c | 25 |
4 files changed, 686 insertions, 192 deletions
diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index f4b6b3b9edda..e7b032dfd17f 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 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); @@ -81,6 +86,8 @@ struct rv_jit_context { int nexentries; unsigned long flags; int stack_size; + u64 arena_vm_start; + u64 user_vm_start; }; /* Convert from ninsns to bytes. */ @@ -601,12 +608,27 @@ static inline u32 rv_fence(u8 pred, u8 succ) return rv_i_insn(imm11_0, 0, 0, 0, 0xf); } +static inline void emit_fence_r_rw(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x2, 0x3), ctx); +} + +static inline void emit_fence_rw_w(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x3, 0x1), ctx); +} + +static inline void emit_fence_rw_rw(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x3, 0x3), ctx); +} + static inline u32 rv_nop(void) { return rv_i_insn(0, 0, 0, 0, 0x13); } -/* RVC instrutions. */ +/* RVC instructions. */ static inline u16 rvc_addi4spn(u8 rd, u32 imm10) { @@ -735,7 +757,18 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2) return rv_css_insn(0x6, imm, rs2, 0x2); } -/* RVZBB instrutions. */ +/* 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 instructions. */ static inline u32 rvzbb_sextb(u8 rd, u8 rs1) { return rv_i_insn(0x604, rs1, 1, rd, 0x13); @@ -937,6 +970,14 @@ 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. */ @@ -1080,6 +1121,28 @@ 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 @@ -1159,6 +1222,11 @@ static inline void emit_zexth(u8 rd, u8 rs, struct rv_jit_context *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); } diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index f5ba73bb153d..592dd86fbf81 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 aac190085472..10e01ff06312 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -10,14 +10,21 @@ #include <linux/filter.h> #include <linux/memory.h> #include <linux/stop_machine.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/cfi.h> +#include <asm/percpu.h> #include "bpf_jit.h" +#define RV_MAX_REG_ARGS 8 #define RV_FENTRY_NINSNS 2 +#define RV_FENTRY_NBYTES (RV_FENTRY_NINSNS * 4) +#define RV_KCFI_NINSNS (IS_ENABLED(CONFIG_CFI_CLANG) ? 1 : 0) +/* imm that allows emit_imm to emit max count insns */ +#define RV_MAX_COUNT_IMM 0x7FFF7FF7FF7FF7FF #define RV_REG_TCC RV_REG_A6 #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */ +#define RV_REG_ARENA RV_REG_S7 /* For storing arena_vm_start */ static const int regmap[] = { [BPF_REG_0] = RV_REG_A5, @@ -255,13 +262,18 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) emit_ld(RV_REG_S6, store_offset, RV_REG_SP, ctx); store_offset -= 8; } + if (ctx->arena_vm_start) { + emit_ld(RV_REG_ARENA, store_offset, RV_REG_SP, ctx); + store_offset -= 8; + } emit_addi(RV_REG_SP, RV_REG_SP, stack_adjust, ctx); /* Set return value. */ if (!is_tail_call) 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 ? (RV_FENTRY_NINSNS + 1) * 4 : 0, /* skip reserved nops and TCC init */ + /* kcfi, fentry and TCC init insns will be skipped on tailcall */ + is_tail_call ? (RV_KCFI_NINSNS + RV_FENTRY_NINSNS + 1) * 4 : 0, ctx); } @@ -374,8 +386,7 @@ 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; @@ -462,11 +473,212 @@ static inline void emit_kcfi(u32 hash, struct rv_jit_context *ctx) emit(hash, ctx); } -static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, - struct rv_jit_context *ctx) +static int emit_load_8(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lb(rd, off, rs), ctx); + else + emit(rv_lbu(rd, off, rs), ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lb(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lbu(rd, 0, RV_REG_T1), ctx); + return ctx->ninsns - insns_start; +} + +static int emit_load_16(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lh(rd, off, rs), ctx); + else + emit(rv_lhu(rd, off, rs), ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lh(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lhu(rd, 0, RV_REG_T1), ctx); + return ctx->ninsns - insns_start; +} + +static int emit_load_32(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lw(rd, off, rs), ctx); + else + emit(rv_lwu(rd, off, rs), ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lw(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lwu(rd, 0, RV_REG_T1), ctx); + return ctx->ninsns - insns_start; +} + +static int emit_load_64(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit_ld(rd, off, rs, ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + emit_ld(rd, 0, RV_REG_T1, ctx); + return ctx->ninsns - insns_start; +} + +static void emit_store_8(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit(rv_sb(rd, off, rs), ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit(rv_sb(RV_REG_T1, 0, rs), ctx); +} + +static void emit_store_16(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit(rv_sh(rd, off, rs), ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit(rv_sh(RV_REG_T1, 0, rs), ctx); +} + +static void emit_store_32(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit_sw(rd, off, rs, ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit_sw(RV_REG_T1, 0, rs, ctx); +} + +static void emit_store_64(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit_sd(rd, off, rs, ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit_sd(RV_REG_T1, 0, rs, ctx); +} + +static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn, + struct rv_jit_context *ctx) +{ + u8 code = insn->code; + s32 imm = insn->imm; + s16 off = insn->off; + + switch (imm) { + /* dst_reg = load_acquire(src_reg + off16) */ + case BPF_LOAD_ACQ: + switch (BPF_SIZE(code)) { + case BPF_B: + emit_load_8(false, rd, off, rs, ctx); + break; + case BPF_H: + emit_load_16(false, rd, off, rs, ctx); + break; + case BPF_W: + emit_load_32(false, rd, off, rs, ctx); + break; + case BPF_DW: + emit_load_64(false, rd, off, rs, ctx); + break; + } + emit_fence_r_rw(ctx); + + /* If our next insn is a redundant zext, return 1 to tell + * build_body() to skip it. + */ + if (BPF_SIZE(code) != BPF_DW && insn_is_zext(&insn[1])) + return 1; + break; + /* store_release(dst_reg + off16, src_reg) */ + case BPF_STORE_REL: + emit_fence_rw_w(ctx); + switch (BPF_SIZE(code)) { + case BPF_B: + emit_store_8(rd, off, rs, ctx); + break; + case BPF_H: + emit_store_16(rd, off, rs, ctx); + break; + case BPF_W: + emit_store_32(rd, off, rs, ctx); + break; + case BPF_DW: + emit_store_64(rd, off, rs, ctx); + break; + } + break; + default: + pr_err_once("bpf-jit: invalid atomic load/store opcode %02x\n", imm); + return -EINVAL; + } + + return 0; +} + +static int emit_atomic_rmw(u8 rd, u8 rs, const struct bpf_insn *insn, + struct rv_jit_context *ctx) { - u8 r0; + u8 r0, code = insn->code; + s16 off = insn->off; + s32 imm = insn->imm; int jmp_offset; + bool is64; + + if (BPF_SIZE(code) != BPF_W && BPF_SIZE(code) != BPF_DW) { + pr_err_once("bpf-jit: 1- and 2-byte RMW atomics are not supported\n"); + return -EINVAL; + } + is64 = BPF_SIZE(code) == BPF_DW; if (off) { if (is_12b_int(off)) { @@ -498,56 +710,64 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, break; /* src_reg = atomic_fetch_<op>(dst_reg + off16, src_reg) */ case BPF_ADD | BPF_FETCH: - emit(is64 ? rv_amoadd_d(rs, rs, rd, 0, 0) : - rv_amoadd_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoadd_d(rs, rs, rd, 1, 1) : + rv_amoadd_w(rs, rs, rd, 1, 1), ctx); if (!is64) 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); + emit(is64 ? rv_amoand_d(rs, rs, rd, 1, 1) : + rv_amoand_w(rs, rs, rd, 1, 1), ctx); if (!is64) 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); + emit(is64 ? rv_amoor_d(rs, rs, rd, 1, 1) : + rv_amoor_w(rs, rs, rd, 1, 1), ctx); if (!is64) 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); + emit(is64 ? rv_amoxor_d(rs, rs, rd, 1, 1) : + rv_amoxor_w(rs, rs, rd, 1, 1), ctx); if (!is64) 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); + emit(is64 ? rv_amoswap_d(rs, rs, rd, 1, 1) : + rv_amoswap_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zextw(rs, rs, ctx); break; /* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */ case BPF_CMPXCHG: r0 = bpf_to_rv_reg(BPF_REG_0, ctx); - emit(is64 ? rv_addi(RV_REG_T2, r0, 0) : - rv_addiw(RV_REG_T2, r0, 0), ctx); + if (is64) + emit_mv(RV_REG_T2, r0, ctx); + else + emit_addiw(RV_REG_T2, r0, 0, ctx); emit(is64 ? rv_lr_d(r0, 0, rd, 0, 0) : rv_lr_w(r0, 0, rd, 0, 0), ctx); jmp_offset = ninsns_rvoff(8); emit(rv_bne(RV_REG_T2, r0, jmp_offset >> 1), ctx); - emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 0) : - rv_sc_w(RV_REG_T3, rs, rd, 0, 0), ctx); + emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 1) : + rv_sc_w(RV_REG_T3, rs, rd, 0, 1), ctx); jmp_offset = ninsns_rvoff(-6); emit(rv_bne(RV_REG_T3, 0, jmp_offset >> 1), ctx); - emit(rv_fence(0x3, 0x3), ctx); + emit_fence_rw_rw(ctx); break; + default: + pr_err_once("bpf-jit: invalid atomic RMW opcode %02x\n", imm); + return -EINVAL; } + + return 0; } #define BPF_FIXUP_OFFSET_MASK GENMASK(26, 0) #define BPF_FIXUP_REG_MASK GENMASK(31, 27) +#define REG_DONT_CLEAR_MARKER 0 /* RV_REG_ZERO unused in pt_regmap */ bool ex_handler_bpf(const struct exception_table_entry *ex, struct pt_regs *regs) @@ -555,7 +775,8 @@ bool ex_handler_bpf(const struct exception_table_entry *ex, off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup); int regs_offset = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup); - *(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0; + if (regs_offset != REG_DONT_CLEAR_MARKER) + *(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0; regs->epc = (unsigned long)&ex->fixup - offset; return true; @@ -572,7 +793,8 @@ static int add_exception_handler(const struct bpf_insn *insn, off_t fixup_offset; if (!ctx->insns || !ctx->ro_insns || !ctx->prog->aux->extable || - (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX)) + (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX && + BPF_MODE(insn->code) != BPF_PROBE_MEM32)) return 0; if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries)) @@ -663,7 +885,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, if (ret) return ret; - if (memcmp(ip, old_insns, RV_FENTRY_NINSNS * 4)) + if (memcmp(ip, old_insns, RV_FENTRY_NBYTES)) return -EFAULT; ret = gen_jump_or_nops(new_addr, ip, new_insns, is_call); @@ -672,34 +894,53 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, 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); + if (memcmp(ip, new_insns, RV_FENTRY_NBYTES)) + ret = patch_text(ip, new_insns, RV_FENTRY_NBYTES); mutex_unlock(&text_mutex); cpus_read_unlock(); return ret; } -static void store_args(int nregs, int args_off, struct rv_jit_context *ctx) +static void store_args(int nr_arg_slots, 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); + for (i = 0; i < nr_arg_slots; i++) { + if (i < RV_MAX_REG_ARGS) { + emit_sd(RV_REG_FP, -args_off, RV_REG_A0 + i, ctx); + } else { + /* skip slots for T0 and FP of traced function */ + emit_ld(RV_REG_T1, 16 + (i - RV_MAX_REG_ARGS) * 8, RV_REG_FP, ctx); + emit_sd(RV_REG_FP, -args_off, RV_REG_T1, ctx); + } args_off -= 8; } } -static void restore_args(int nregs, int args_off, struct rv_jit_context *ctx) +static void restore_args(int nr_reg_args, int args_off, struct rv_jit_context *ctx) { int i; - for (i = 0; i < nregs; i++) { + for (i = 0; i < nr_reg_args; i++) { emit_ld(RV_REG_A0 + i, -args_off, RV_REG_FP, ctx); args_off -= 8; } } +static void restore_stack_args(int nr_stack_args, int args_off, int stk_arg_off, + struct rv_jit_context *ctx) +{ + int i; + + for (i = 0; i < nr_stack_args; i++) { + emit_ld(RV_REG_T1, -(args_off - RV_MAX_REG_ARGS * 8), RV_REG_FP, ctx); + emit_sd(RV_REG_FP, -stk_arg_off, RV_REG_T1, ctx); + args_off -= 8; + stk_arg_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) { @@ -722,6 +963,9 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of if (ret) return ret; + /* store prog start time */ + emit_mv(RV_REG_S1, RV_REG_A0, ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ @@ -729,9 +973,6 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of /* 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) @@ -772,8 +1013,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, { 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; + int stack_size = 0, nr_arg_slots = 0; + int retval_off, args_off, nregs_off, ip_off, run_ctx_off, sreg_off, stk_arg_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]; @@ -819,20 +1060,21 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, * FP - sreg_off [ callee saved reg ] * * [ pads ] pads for 16 bytes alignment + * + * [ stack_argN ] + * [ ... ] + * FP - stk_arg_off [ stack_arg1 ] BPF_TRAMP_F_CALL_ORIG */ 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) + if (m->nr_args > MAX_BPF_FUNC_ARGS) return -ENOTSUPP; + for (i = 0; i < m->nr_args; i++) + nr_arg_slots += round_up(m->arg_size[i], 8) / 8; + /* room of trampoline frame to store return address and frame pointer */ stack_size += 16; @@ -842,7 +1084,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, retval_off = stack_size; } - stack_size += nregs * 8; + stack_size += nr_arg_slots * 8; args_off = stack_size; stack_size += 8; @@ -859,7 +1101,13 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, stack_size += 8; sreg_off = stack_size; - stack_size = round_up(stack_size, 16); + if ((flags & BPF_TRAMP_F_CALL_ORIG) && (nr_arg_slots - RV_MAX_REG_ARGS > 0)) + stack_size += (nr_arg_slots - RV_MAX_REG_ARGS) * 8; + + stack_size = round_up(stack_size, STACK_ALIGN); + + /* room for args on stack must be at the top of stack */ + stk_arg_off = stack_size; if (!is_struct_ops) { /* For the trampoline called from function entry, @@ -896,17 +1144,17 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, emit_sd(RV_REG_FP, -ip_off, RV_REG_T1, ctx); } - emit_li(RV_REG_T1, nregs, ctx); + emit_li(RV_REG_T1, nr_arg_slots, ctx); emit_sd(RV_REG_FP, -nregs_off, RV_REG_T1, ctx); - store_args(nregs, args_off, ctx); + store_args(nr_arg_slots, 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); + emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx); ret = emit_call((const u64)__bpf_tramp_enter, true, ctx); if (ret) return ret; @@ -939,13 +1187,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_CALL_ORIG) { - restore_args(nregs, args_off, ctx); + restore_args(min_t(int, nr_arg_slots, RV_MAX_REG_ARGS), args_off, ctx); + restore_stack_args(nr_arg_slots - RV_MAX_REG_ARGS, args_off, stk_arg_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; + im->ip_after_call = ctx->ro_insns + ctx->ninsns; /* 2 nops reserved for auipc+jalr pair */ emit(rv_nop(), ctx); emit(rv_nop(), ctx); @@ -966,15 +1215,15 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_CALL_ORIG) { - im->ip_epilogue = ctx->insns + ctx->ninsns; - emit_imm(RV_REG_A0, (const s64)im, ctx); + im->ip_epilogue = ctx->ro_insns + ctx->ninsns; + emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, 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); + restore_args(min_t(int, nr_arg_slots, RV_MAX_REG_ARGS), args_off, ctx); if (save_ret) { emit_ld(RV_REG_A0, -retval_off, RV_REG_FP, ctx); @@ -1029,31 +1278,52 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, 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, +void *arch_alloc_bpf_trampoline(unsigned int size) +{ + return bpf_prog_pack_alloc(size, bpf_fill_ill_insns); +} + +void arch_free_bpf_trampoline(void *image, unsigned int size) +{ + bpf_prog_pack_free(image, size); +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, + void *ro_image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr) { int ret; + void *image, *res; struct rv_jit_context ctx; + u32 size = ro_image_end - ro_image; + + image = kvmalloc(size, GFP_KERNEL); + if (!image) + return -ENOMEM; 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; + ctx.ro_insns = ro_image; ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx); if (ret < 0) - return ret; + goto out; - bpf_flush_icache(ctx.insns, ctx.insns + ctx.ninsns); + if (WARN_ON(size < ninsns_rvoff(ctx.ninsns))) { + ret = -E2BIG; + goto out; + } - return ninsns_rvoff(ret); + res = bpf_arch_text_copy(ro_image, image, size); + if (IS_ERR(res)) { + ret = PTR_ERR(res); + goto out; + } + + bpf_flush_icache(ro_image, ro_image_end); +out: + kvfree(image); + return ret < 0 ? ret : size; } int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, @@ -1073,6 +1343,31 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, /* dst = src */ case BPF_ALU | BPF_MOV | BPF_X: case BPF_ALU64 | BPF_MOV | BPF_X: + if (insn_is_cast_user(insn)) { + emit_mv(RV_REG_T1, rs, ctx); + emit_zextw(RV_REG_T1, RV_REG_T1, ctx); + emit_imm(rd, (ctx->user_vm_start >> 32) << 32, ctx); + emit(rv_beq(RV_REG_T1, RV_REG_ZERO, 4), ctx); + emit_or(RV_REG_T1, rd, RV_REG_T1, ctx); + emit_mv(rd, RV_REG_T1, ctx); + break; + } else if (insn_is_mov_percpu_addr(insn)) { + if (rd != rs) + emit_mv(rd, rs, ctx); +#ifdef CONFIG_SMP + /* Load current CPU number in T1 */ + emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu), + RV_REG_TP, ctx); + /* Load address of __per_cpu_offset array in T2 */ + emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx); + /* Get address of __per_cpu_offset[cpu] in T1 */ + emit_sh3add(RV_REG_T1, RV_REG_T1, RV_REG_T2, ctx); + /* Load __per_cpu_offset[cpu] in T1 */ + emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx); + /* Add the offset to Rd */ + emit_add(rd, rd, RV_REG_T1, ctx); +#endif + } if (imm == 1) { /* Special mov32 for zext */ emit_zextw(rd, rd, ctx); @@ -1457,12 +1752,44 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, bool fixed_addr; u64 addr; + /* Inline calls to bpf_get_smp_processor_id() + * + * RV_REG_TP holds the address of the current CPU's task_struct and thread_info is + * at offset 0 in task_struct. + * Load cpu from thread_info: + * Set R0 to ((struct thread_info *)(RV_REG_TP))->cpu + * + * This replicates the implementation of raw_smp_processor_id() on RISCV + */ + if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) { + /* Load current CPU number in R0 */ + emit_ld(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu), + RV_REG_TP, ctx); + break; + } + mark_call(ctx); ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &addr, &fixed_addr); if (ret < 0) return ret; + if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { + const struct btf_func_model *fm; + int idx; + + fm = bpf_jit_find_kfunc_model(ctx->prog, insn); + if (!fm) + return -EINVAL; + + for (idx = 0; idx < fm->nr_args; idx++) { + u8 reg = bpf_to_rv_reg(BPF_REG_1 + idx, ctx); + + if (fm->arg_size[idx] == sizeof(int)) + emit_sextw(reg, reg, ctx); + } + } + ret = emit_call(addr, fixed_addr, ctx); if (ret) return ret; @@ -1523,87 +1850,35 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case BPF_LDX | BPF_PROBE_MEMSX | BPF_B: case BPF_LDX | BPF_PROBE_MEMSX | BPF_H: case BPF_LDX | BPF_PROBE_MEMSX | BPF_W: + /* LDX | PROBE_MEM32: dst = *(unsigned size *)(src + RV_REG_ARENA + off) */ + case BPF_LDX | BPF_PROBE_MEM32 | BPF_B: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_H: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_W: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW: { - int insn_len, insns_start; bool sign_ext; + int insn_len; sign_ext = BPF_MODE(insn->code) == BPF_MEMSX || BPF_MODE(insn->code) == BPF_PROBE_MEMSX; + if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) { + emit_add(RV_REG_T2, rs, RV_REG_ARENA, ctx); + rs = RV_REG_T2; + } + switch (BPF_SIZE(code)) { case BPF_B: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - 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; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - 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; + insn_len = emit_load_8(sign_ext, rd, off, rs, ctx); break; case BPF_H: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - 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; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - 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; + insn_len = emit_load_16(sign_ext, rd, off, rs, ctx); break; case BPF_W: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - 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; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - 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; + insn_len = emit_load_32(sign_ext, rd, off, rs, ctx); break; case BPF_DW: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - emit_ld(rd, off, rs, ctx); - insn_len = ctx->ninsns - insns_start; - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - emit_ld(rd, 0, RV_REG_T1, ctx); - insn_len = ctx->ninsns - insns_start; + insn_len = emit_load_64(sign_ext, rd, off, rs, ctx); break; } @@ -1666,52 +1941,188 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_sd(RV_REG_T2, 0, RV_REG_T1, ctx); break; - /* STX: *(size *)(dst + off) = src */ - case BPF_STX | BPF_MEM | BPF_B: - if (is_12b_int(off)) { - emit(rv_sb(rd, off, rs), ctx); + case BPF_ST | BPF_PROBE_MEM32 | BPF_B: + case BPF_ST | BPF_PROBE_MEM32 | BPF_H: + case BPF_ST | BPF_PROBE_MEM32 | BPF_W: + case BPF_ST | BPF_PROBE_MEM32 | BPF_DW: + { + int insn_len, insns_start; + + emit_add(RV_REG_T3, rd, RV_REG_ARENA, ctx); + rd = RV_REG_T3; + + /* Load imm to a register then store it */ + emit_imm(RV_REG_T1, imm, ctx); + + switch (BPF_SIZE(code)) { + case BPF_B: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit(rv_sb(rd, off, RV_REG_T1), ctx); + insn_len = ctx->ninsns - insns_start; + break; + } + + emit_imm(RV_REG_T2, off, ctx); + emit_add(RV_REG_T2, RV_REG_T2, rd, ctx); + insns_start = ctx->ninsns; + emit(rv_sb(RV_REG_T2, 0, RV_REG_T1), ctx); + insn_len = ctx->ninsns - insns_start; break; - } + case BPF_H: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit(rv_sh(rd, off, RV_REG_T1), ctx); + insn_len = ctx->ninsns - insns_start; + break; + } - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit(rv_sb(RV_REG_T1, 0, rs), ctx); - break; - case BPF_STX | BPF_MEM | BPF_H: - if (is_12b_int(off)) { - emit(rv_sh(rd, off, rs), ctx); + emit_imm(RV_REG_T2, off, ctx); + emit_add(RV_REG_T2, RV_REG_T2, rd, ctx); + insns_start = ctx->ninsns; + emit(rv_sh(RV_REG_T2, 0, RV_REG_T1), ctx); + insn_len = ctx->ninsns - insns_start; break; - } + case BPF_W: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit_sw(rd, off, RV_REG_T1, ctx); + insn_len = ctx->ninsns - insns_start; + break; + } - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit(rv_sh(RV_REG_T1, 0, rs), ctx); - break; - case BPF_STX | BPF_MEM | BPF_W: - if (is_12b_int(off)) { - emit_sw(rd, off, rs, ctx); + emit_imm(RV_REG_T2, off, ctx); + emit_add(RV_REG_T2, RV_REG_T2, rd, ctx); + insns_start = ctx->ninsns; + emit_sw(RV_REG_T2, 0, RV_REG_T1, ctx); + insn_len = ctx->ninsns - insns_start; break; - } + case BPF_DW: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit_sd(rd, off, RV_REG_T1, ctx); + insn_len = ctx->ninsns - insns_start; + break; + } - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit_sw(RV_REG_T1, 0, rs, ctx); - break; - case BPF_STX | BPF_MEM | BPF_DW: - if (is_12b_int(off)) { - emit_sd(rd, off, rs, ctx); + emit_imm(RV_REG_T2, off, ctx); + emit_add(RV_REG_T2, RV_REG_T2, rd, ctx); + insns_start = ctx->ninsns; + emit_sd(RV_REG_T2, 0, RV_REG_T1, ctx); + insn_len = ctx->ninsns - insns_start; break; } - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit_sd(RV_REG_T1, 0, rs, ctx); + ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER, + insn_len); + if (ret) + return ret; + + break; + } + + /* STX: *(size *)(dst + off) = src */ + case BPF_STX | BPF_MEM | BPF_B: + emit_store_8(rd, off, rs, ctx); + break; + case BPF_STX | BPF_MEM | BPF_H: + emit_store_16(rd, off, rs, ctx); + break; + case BPF_STX | BPF_MEM | BPF_W: + emit_store_32(rd, off, rs, ctx); + break; + case BPF_STX | BPF_MEM | BPF_DW: + emit_store_64(rd, off, rs, ctx); break; + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_H: case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: - emit_atomic(rd, rs, off, imm, - BPF_SIZE(code) == BPF_DW, ctx); + if (bpf_atomic_is_load_store(insn)) + ret = emit_atomic_ld_st(rd, rs, insn, ctx); + else + ret = emit_atomic_rmw(rd, rs, insn, ctx); + if (ret) + return ret; + break; + + case BPF_STX | BPF_PROBE_MEM32 | BPF_B: + case BPF_STX | BPF_PROBE_MEM32 | BPF_H: + case BPF_STX | BPF_PROBE_MEM32 | BPF_W: + case BPF_STX | BPF_PROBE_MEM32 | BPF_DW: + { + int insn_len, insns_start; + + emit_add(RV_REG_T2, rd, RV_REG_ARENA, ctx); + rd = RV_REG_T2; + + switch (BPF_SIZE(code)) { + case BPF_B: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit(rv_sb(rd, off, rs), ctx); + insn_len = ctx->ninsns - insns_start; + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + insns_start = ctx->ninsns; + emit(rv_sb(RV_REG_T1, 0, rs), ctx); + insn_len = ctx->ninsns - insns_start; + break; + case BPF_H: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit(rv_sh(rd, off, rs), ctx); + insn_len = ctx->ninsns - insns_start; + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + insns_start = ctx->ninsns; + emit(rv_sh(RV_REG_T1, 0, rs), ctx); + insn_len = ctx->ninsns - insns_start; + break; + case BPF_W: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit_sw(rd, off, rs, ctx); + insn_len = ctx->ninsns - insns_start; + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + insns_start = ctx->ninsns; + emit_sw(RV_REG_T1, 0, rs, ctx); + insn_len = ctx->ninsns - insns_start; + break; + case BPF_DW: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit_sd(rd, off, rs, ctx); + insn_len = ctx->ninsns - insns_start; + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + insns_start = ctx->ninsns; + emit_sd(RV_REG_T1, 0, rs, ctx); + insn_len = ctx->ninsns - insns_start; + break; + } + + ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER, + insn_len); + if (ret) + return ret; + break; + } + default: pr_err("bpf-jit: unknown opcode %02x\n", code); return -EINVAL; @@ -1724,7 +2135,7 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog) { int i, stack_adjust = 0, store_offset, bpf_stack_adjust; - bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16); + bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, STACK_ALIGN); if (bpf_stack_adjust) mark_fp(ctx); @@ -1743,8 +2154,10 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog) stack_adjust += 8; if (seen_reg(RV_REG_S6, ctx)) stack_adjust += 8; + if (ctx->arena_vm_start) + stack_adjust += 8; - stack_adjust = round_up(stack_adjust, 16); + stack_adjust = round_up(stack_adjust, STACK_ALIGN); stack_adjust += bpf_stack_adjust; store_offset = stack_adjust - 8; @@ -1794,6 +2207,10 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog) emit_sd(RV_REG_SP, store_offset, RV_REG_S6, ctx); store_offset -= 8; } + if (ctx->arena_vm_start) { + emit_sd(RV_REG_SP, store_offset, RV_REG_ARENA, ctx); + store_offset -= 8; + } emit_addi(RV_REG_FP, RV_REG_SP, stack_adjust, ctx); @@ -1807,6 +2224,9 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog) emit_mv(RV_REG_TCC_SAVED, RV_REG_TCC, ctx); ctx->stack_size = stack_adjust; + + if (ctx->arena_vm_start) + emit_imm(RV_REG_ARENA, ctx->arena_vm_start, ctx); } void bpf_jit_build_epilogue(struct rv_jit_context *ctx) @@ -1823,3 +2243,23 @@ bool bpf_jit_supports_ptr_xchg(void) { return true; } + +bool bpf_jit_supports_arena(void) +{ + return true; +} + +bool bpf_jit_supports_percpu_insn(void) +{ + return true; +} + +bool bpf_jit_inlines_helper_call(s32 imm) +{ + switch (imm) { + case BPF_FUNC_get_smp_processor_id: + return true; + default: + return false; + } +} diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index 6b3acac30c06..f6ca5cfa6b2f 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -9,7 +9,7 @@ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/memory.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/cfi.h> #include "bpf_jit.h" @@ -26,9 +26,8 @@ static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset) int ret; ret = bpf_jit_emit_insn(insn, ctx, extra_pass); - /* BPF_LD | BPF_IMM | BPF_DW: skip the next instruction. */ if (ret > 0) - i++; + i++; /* skip the next instruction */ if (offset) offset[i] = ctx->ninsns; if (ret < 0) @@ -80,6 +79,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) goto skip_init_ctx; } + ctx->arena_vm_start = bpf_arena_get_kern_vm_start(prog->aux->arena); + ctx->user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena); ctx->prog = prog; ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL); if (!ctx->offset) { @@ -176,8 +177,7 @@ skip_init_ctx: prog->jited_len = prog_size - cfi_get_offset(); if (!prog->is_func || extra_pass) { - if (WARN_ON(bpf_jit_binary_pack_finalize(prog, jit_data->ro_header, - jit_data->header))) { + if (WARN_ON(bpf_jit_binary_pack_finalize(jit_data->ro_header, jit_data->header))) { /* ro_header has been freed */ jit_data->ro_header = NULL; prog = orig_prog; @@ -219,19 +219,6 @@ u64 bpf_jit_alloc_exec_limit(void) return BPF_JIT_REGION_SIZE; } -void *bpf_jit_alloc_exec(unsigned long size) -{ - return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, - BPF_JIT_REGION_END, GFP_KERNEL, - PAGE_KERNEL, 0, NUMA_NO_NODE, - __builtin_return_address(0)); -} - -void bpf_jit_free_exec(void *addr) -{ - return vfree(addr); -} - void *bpf_arch_text_copy(void *dst, void *src, size_t len) { int ret; @@ -269,7 +256,7 @@ void bpf_jit_free(struct bpf_prog *prog) * before freeing it. */ if (jit_data) { - bpf_jit_binary_pack_finalize(prog, jit_data->ro_header, jit_data->header); + bpf_jit_binary_pack_finalize(jit_data->ro_header, jit_data->header); kfree(jit_data); } hdr = bpf_jit_binary_pack_hdr(prog); |