--- zzzz-none-000/linux-3.10.107/arch/arm/net/bpf_jit_32.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/arm/net/bpf_jit_32.c 2021-02-04 17:41:59.000000000 +0000 @@ -12,13 +12,14 @@ #include #include #include -#include #include #include #include #include + #include #include +#include #include "bpf_jit_32.h" @@ -53,9 +54,10 @@ #define SEEN_DATA (1 << (BPF_MEMWORDS + 3)) #define FLAG_NEED_X_RESET (1 << 0) +#define FLAG_IMM_OVERFLOW (1 << 1) struct jit_ctx { - const struct sk_filter *skf; + const struct bpf_prog *skf; unsigned idx; unsigned prologue_bytes; int ret0_fp_idx; @@ -72,38 +74,58 @@ int bpf_jit_enable __read_mostly; -static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset) +static inline int call_neg_helper(struct sk_buff *skb, int offset, void *ret, + unsigned int size) +{ + void *ptr = bpf_internal_load_pointer_neg_helper(skb, offset, size); + + if (!ptr) + return -EFAULT; + memcpy(ret, ptr, size); + return 0; +} + +static u64 jit_get_skb_b(struct sk_buff *skb, int offset) { u8 ret; int err; - err = skb_copy_bits(skb, offset, &ret, 1); + if (offset < 0) + err = call_neg_helper(skb, offset, &ret, 1); + else + err = skb_copy_bits(skb, offset, &ret, 1); return (u64)err << 32 | ret; } -static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset) +static u64 jit_get_skb_h(struct sk_buff *skb, int offset) { u16 ret; int err; - err = skb_copy_bits(skb, offset, &ret, 2); + if (offset < 0) + err = call_neg_helper(skb, offset, &ret, 2); + else + err = skb_copy_bits(skb, offset, &ret, 2); return (u64)err << 32 | ntohs(ret); } -static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset) +static u64 jit_get_skb_w(struct sk_buff *skb, int offset) { u32 ret; int err; - err = skb_copy_bits(skb, offset, &ret, 4); + if (offset < 0) + err = call_neg_helper(skb, offset, &ret, 4); + else + err = skb_copy_bits(skb, offset, &ret, 4); return (u64)err << 32 | ntohl(ret); } /* - * Wrapper that handles both OABI and EABI and assures Thumb2 interworking + * Wrappers which handle both OABI and EABI and assures Thumb2 interworking * (where the assembly routines like __aeabi_uidiv could cause problems). */ static u32 jit_udiv(u32 dividend, u32 divisor) @@ -111,10 +133,18 @@ return dividend / divisor; } +static u32 jit_mod(u32 dividend, u32 divisor) +{ + return dividend % divisor; +} + static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx) { + inst |= (cond << 28); + inst = __opcode_to_mem_arm(inst); + if (ctx->target != NULL) - ctx->target[ctx->idx] = inst | (cond << 28); + ctx->target[ctx->idx] = inst; ctx->idx++; } @@ -132,7 +162,7 @@ u16 ret = 0; if ((ctx->skf->len > 1) || - (ctx->skf->insns[0].code == BPF_S_RET_A)) + (ctx->skf->insns[0].code == (BPF_RET | BPF_A))) ret |= 1 << r_A; #ifdef CONFIG_FRAME_POINTER @@ -157,31 +187,17 @@ return fls(ctx->seen & SEEN_MEM); } -static inline bool is_load_to_a(u16 inst) +static void jit_fill_hole(void *area, unsigned int size) { - switch (inst) { - case BPF_S_LD_W_LEN: - case BPF_S_LD_W_ABS: - case BPF_S_LD_H_ABS: - case BPF_S_LD_B_ABS: - case BPF_S_ANC_CPU: - case BPF_S_ANC_IFINDEX: - case BPF_S_ANC_MARK: - case BPF_S_ANC_PROTOCOL: - case BPF_S_ANC_RXHASH: - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: - case BPF_S_ANC_QUEUE: - return true; - default: - return false; - } + u32 *ptr; + /* We are guaranteed to have aligned memory. */ + for (ptr = area; size >= sizeof(u32); size -= sizeof(u32)) + *ptr++ = __opcode_to_mem_arm(ARM_INST_UDF); } static void build_prologue(struct jit_ctx *ctx) { u16 reg_set = saved_regs(ctx); - u16 first_inst = ctx->skf->insns[0].code; u16 off; #ifdef CONFIG_FRAME_POINTER @@ -211,7 +227,7 @@ emit(ARM_MOV_I(r_X, 0), ctx); /* do not leak kernel data to userspace */ - if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst))) + if (bpf_needs_clear_a(&ctx->skf->insns[0])) emit(ARM_MOV_I(r_A, 0), ctx); /* stack space for the BPF_MEM words */ @@ -289,6 +305,15 @@ /* PC in ARM mode == address of the instruction + 8 */ imm = offset - (8 + ctx->idx * 4); + if (imm & ~0xfff) { + /* + * literal pool is too far, signal it into flags. we + * can only detect it on the second pass unfortunately. + */ + ctx->flags |= FLAG_IMM_OVERFLOW; + return 0; + } + return imm; } @@ -437,21 +462,39 @@ #endif } -static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx) +static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, + int bpf_op) { #if __LINUX_ARM_ARCH__ == 7 if (elf_hwcap & HWCAP_IDIVA) { - emit(ARM_UDIV(rd, rm, rn), ctx); + if (bpf_op == BPF_DIV) + emit(ARM_UDIV(rd, rm, rn), ctx); + else { + emit(ARM_UDIV(ARM_R3, rm, rn), ctx); + emit(ARM_MLS(rd, rn, ARM_R3, rm), ctx); + } return; } #endif - if (rm != ARM_R0) - emit(ARM_MOV_R(ARM_R0, rm), ctx); + + /* + * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4 + * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into + * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm + * before using it as a source for ARM_R1. + * + * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is + * ARM_R5 (r_X) so there is no particular register overlap + * issues. + */ if (rn != ARM_R1) emit(ARM_MOV_R(ARM_R1, rn), ctx); + if (rm != ARM_R0) + emit(ARM_MOV_R(ARM_R0, rm), ctx); ctx->seen |= SEEN_CALL; - emit_mov_i(ARM_R3, (u32)jit_udiv, ctx); + emit_mov_i(ARM_R3, bpf_op == BPF_DIV ? (u32)jit_udiv : (u32)jit_mod, + ctx); emit_blx_r(ARM_R3, ctx); if (rd != ARM_R0) @@ -469,48 +512,48 @@ static int build_body(struct jit_ctx *ctx) { void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w}; - const struct sk_filter *prog = ctx->skf; + const struct bpf_prog *prog = ctx->skf; const struct sock_filter *inst; unsigned i, load_order, off, condt; int imm12; u32 k; for (i = 0; i < prog->len; i++) { + u16 code; + inst = &(prog->insns[i]); /* K as an immediate value operand */ k = inst->k; + code = bpf_anc_helper(inst); /* compute offsets only in the fake pass */ if (ctx->target == NULL) ctx->offsets[i] = ctx->idx * 4; - switch (inst->code) { - case BPF_S_LD_IMM: + switch (code) { + case BPF_LD | BPF_IMM: emit_mov_i(r_A, k, ctx); break; - case BPF_S_LD_W_LEN: + case BPF_LD | BPF_W | BPF_LEN: ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); emit(ARM_LDR_I(r_A, r_skb, offsetof(struct sk_buff, len)), ctx); break; - case BPF_S_LD_MEM: + case BPF_LD | BPF_MEM: /* A = scratch[k] */ ctx->seen |= SEEN_MEM_WORD(k); emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx); break; - case BPF_S_LD_W_ABS: + case BPF_LD | BPF_W | BPF_ABS: load_order = 2; goto load; - case BPF_S_LD_H_ABS: + case BPF_LD | BPF_H | BPF_ABS: load_order = 1; goto load; - case BPF_S_LD_B_ABS: + case BPF_LD | BPF_B | BPF_ABS: load_order = 0; load: - /* the interpreter will deal with the negative K */ - if ((int)k < 0) - return -ENOTSUPP; emit_mov_i(r_off, k, ctx); load_common: ctx->seen |= SEEN_DATA | SEEN_CALL; @@ -519,12 +562,24 @@ emit(ARM_SUB_I(r_scratch, r_skb_hl, 1 << load_order), ctx); emit(ARM_CMP_R(r_scratch, r_off), ctx); - condt = ARM_COND_HS; + condt = ARM_COND_GE; } else { emit(ARM_CMP_R(r_skb_hl, r_off), ctx); condt = ARM_COND_HI; } + /* + * test for negative offset, only if we are + * currently scheduled to take the fast + * path. this will update the flags so that + * the slowpath instruction are ignored if the + * offset is negative. + * + * for loard_order == 0 the HI condition will + * make loads at offset 0 take the slow path too. + */ + _emit(condt, ARM_CMP_I(r_off, 0), ctx); + _emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data), ctx); @@ -548,31 +603,32 @@ emit_err_ret(ARM_COND_NE, ctx); emit(ARM_MOV_R(r_A, ARM_R0), ctx); break; - case BPF_S_LD_W_IND: + case BPF_LD | BPF_W | BPF_IND: load_order = 2; goto load_ind; - case BPF_S_LD_H_IND: + case BPF_LD | BPF_H | BPF_IND: load_order = 1; goto load_ind; - case BPF_S_LD_B_IND: + case BPF_LD | BPF_B | BPF_IND: load_order = 0; load_ind: + update_on_xread(ctx); OP_IMM3(ARM_ADD, r_off, r_X, k, ctx); goto load_common; - case BPF_S_LDX_IMM: + case BPF_LDX | BPF_IMM: ctx->seen |= SEEN_X; emit_mov_i(r_X, k, ctx); break; - case BPF_S_LDX_W_LEN: + case BPF_LDX | BPF_W | BPF_LEN: ctx->seen |= SEEN_X | SEEN_SKB; emit(ARM_LDR_I(r_X, r_skb, offsetof(struct sk_buff, len)), ctx); break; - case BPF_S_LDX_MEM: + case BPF_LDX | BPF_MEM: ctx->seen |= SEEN_X | SEEN_MEM_WORD(k); emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx); break; - case BPF_S_LDX_B_MSH: + case BPF_LDX | BPF_B | BPF_MSH: /* x = ((*(frame + k)) & 0xf) << 2; */ ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL; /* the interpreter should deal with the negative K */ @@ -602,113 +658,128 @@ emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx); emit(ARM_LSL_I(r_X, r_X, 2), ctx); break; - case BPF_S_ST: + case BPF_ST: ctx->seen |= SEEN_MEM_WORD(k); emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx); break; - case BPF_S_STX: + case BPF_STX: update_on_xread(ctx); ctx->seen |= SEEN_MEM_WORD(k); emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx); break; - case BPF_S_ALU_ADD_K: + case BPF_ALU | BPF_ADD | BPF_K: /* A += K */ OP_IMM3(ARM_ADD, r_A, r_A, k, ctx); break; - case BPF_S_ALU_ADD_X: + case BPF_ALU | BPF_ADD | BPF_X: update_on_xread(ctx); emit(ARM_ADD_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_SUB_K: + case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */ OP_IMM3(ARM_SUB, r_A, r_A, k, ctx); break; - case BPF_S_ALU_SUB_X: + case BPF_ALU | BPF_SUB | BPF_X: update_on_xread(ctx); emit(ARM_SUB_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_MUL_K: + case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */ emit_mov_i(r_scratch, k, ctx); emit(ARM_MUL(r_A, r_A, r_scratch), ctx); break; - case BPF_S_ALU_MUL_X: + case BPF_ALU | BPF_MUL | BPF_X: update_on_xread(ctx); emit(ARM_MUL(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_DIV_K: + case BPF_ALU | BPF_DIV | BPF_K: if (k == 1) break; emit_mov_i(r_scratch, k, ctx); - emit_udiv(r_A, r_A, r_scratch, ctx); + emit_udivmod(r_A, r_A, r_scratch, ctx, BPF_DIV); + break; + case BPF_ALU | BPF_DIV | BPF_X: + update_on_xread(ctx); + emit(ARM_CMP_I(r_X, 0), ctx); + emit_err_ret(ARM_COND_EQ, ctx); + emit_udivmod(r_A, r_A, r_X, ctx, BPF_DIV); + break; + case BPF_ALU | BPF_MOD | BPF_K: + if (k == 1) { + emit_mov_i(r_A, 0, ctx); + break; + } + emit_mov_i(r_scratch, k, ctx); + emit_udivmod(r_A, r_A, r_scratch, ctx, BPF_MOD); break; - case BPF_S_ALU_DIV_X: + case BPF_ALU | BPF_MOD | BPF_X: update_on_xread(ctx); emit(ARM_CMP_I(r_X, 0), ctx); emit_err_ret(ARM_COND_EQ, ctx); - emit_udiv(r_A, r_A, r_X, ctx); + emit_udivmod(r_A, r_A, r_X, ctx, BPF_MOD); break; - case BPF_S_ALU_OR_K: + case BPF_ALU | BPF_OR | BPF_K: /* A |= K */ OP_IMM3(ARM_ORR, r_A, r_A, k, ctx); break; - case BPF_S_ALU_OR_X: + case BPF_ALU | BPF_OR | BPF_X: update_on_xread(ctx); emit(ARM_ORR_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_XOR_K: + case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K; */ OP_IMM3(ARM_EOR, r_A, r_A, k, ctx); break; - case BPF_S_ANC_ALU_XOR_X: - case BPF_S_ALU_XOR_X: + case BPF_ANC | SKF_AD_ALU_XOR_X: + case BPF_ALU | BPF_XOR | BPF_X: /* A ^= X */ update_on_xread(ctx); emit(ARM_EOR_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_AND_K: + case BPF_ALU | BPF_AND | BPF_K: /* A &= K */ OP_IMM3(ARM_AND, r_A, r_A, k, ctx); break; - case BPF_S_ALU_AND_X: + case BPF_ALU | BPF_AND | BPF_X: update_on_xread(ctx); emit(ARM_AND_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_LSH_K: + case BPF_ALU | BPF_LSH | BPF_K: if (unlikely(k > 31)) return -1; emit(ARM_LSL_I(r_A, r_A, k), ctx); break; - case BPF_S_ALU_LSH_X: + case BPF_ALU | BPF_LSH | BPF_X: update_on_xread(ctx); emit(ARM_LSL_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_RSH_K: + case BPF_ALU | BPF_RSH | BPF_K: if (unlikely(k > 31)) return -1; - emit(ARM_LSR_I(r_A, r_A, k), ctx); + if (k) + emit(ARM_LSR_I(r_A, r_A, k), ctx); break; - case BPF_S_ALU_RSH_X: + case BPF_ALU | BPF_RSH | BPF_X: update_on_xread(ctx); emit(ARM_LSR_R(r_A, r_A, r_X), ctx); break; - case BPF_S_ALU_NEG: + case BPF_ALU | BPF_NEG: /* A = -A */ emit(ARM_RSB_I(r_A, r_A, 0), ctx); break; - case BPF_S_JMP_JA: + case BPF_JMP | BPF_JA: /* pc += K */ emit(ARM_B(b_imm(i + k + 1, ctx)), ctx); break; - case BPF_S_JMP_JEQ_K: + case BPF_JMP | BPF_JEQ | BPF_K: /* pc += (A == K) ? pc->jt : pc->jf */ condt = ARM_COND_EQ; goto cmp_imm; - case BPF_S_JMP_JGT_K: + case BPF_JMP | BPF_JGT | BPF_K: /* pc += (A > K) ? pc->jt : pc->jf */ condt = ARM_COND_HI; goto cmp_imm; - case BPF_S_JMP_JGE_K: + case BPF_JMP | BPF_JGE | BPF_K: /* pc += (A >= K) ? pc->jt : pc->jf */ condt = ARM_COND_HS; cmp_imm: @@ -727,22 +798,22 @@ _emit(condt ^ 1, ARM_B(b_imm(i + inst->jf + 1, ctx)), ctx); break; - case BPF_S_JMP_JEQ_X: + case BPF_JMP | BPF_JEQ | BPF_X: /* pc += (A == X) ? pc->jt : pc->jf */ condt = ARM_COND_EQ; goto cmp_x; - case BPF_S_JMP_JGT_X: + case BPF_JMP | BPF_JGT | BPF_X: /* pc += (A > X) ? pc->jt : pc->jf */ condt = ARM_COND_HI; goto cmp_x; - case BPF_S_JMP_JGE_X: + case BPF_JMP | BPF_JGE | BPF_X: /* pc += (A >= X) ? pc->jt : pc->jf */ condt = ARM_COND_CS; cmp_x: update_on_xread(ctx); emit(ARM_CMP_R(r_A, r_X), ctx); goto cond_jump; - case BPF_S_JMP_JSET_K: + case BPF_JMP | BPF_JSET | BPF_K: /* pc += (A & K) ? pc->jt : pc->jf */ condt = ARM_COND_NE; /* not set iff all zeroes iff Z==1 iff EQ */ @@ -755,16 +826,16 @@ emit(ARM_TST_I(r_A, imm12), ctx); } goto cond_jump; - case BPF_S_JMP_JSET_X: + case BPF_JMP | BPF_JSET | BPF_X: /* pc += (A & X) ? pc->jt : pc->jf */ update_on_xread(ctx); condt = ARM_COND_NE; emit(ARM_TST_R(r_A, r_X), ctx); goto cond_jump; - case BPF_S_RET_A: + case BPF_RET | BPF_A: emit(ARM_MOV_R(ARM_R0, r_A), ctx); goto b_epilogue; - case BPF_S_RET_K: + case BPF_RET | BPF_K: if ((k == 0) && (ctx->ret0_fp_idx < 0)) ctx->ret0_fp_idx = i; emit_mov_i(ARM_R0, k, ctx); @@ -772,17 +843,17 @@ if (i != ctx->skf->len - 1) emit(ARM_B(b_imm(prog->len, ctx)), ctx); break; - case BPF_S_MISC_TAX: + case BPF_MISC | BPF_TAX: /* X = A */ ctx->seen |= SEEN_X; emit(ARM_MOV_R(r_X, r_A), ctx); break; - case BPF_S_MISC_TXA: + case BPF_MISC | BPF_TXA: /* A = X */ update_on_xread(ctx); emit(ARM_MOV_R(r_A, r_X), ctx); break; - case BPF_S_ANC_PROTOCOL: + case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol) */ ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, @@ -791,7 +862,7 @@ emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx); emit_swap16(r_A, r_scratch, ctx); break; - case BPF_S_ANC_CPU: + case BPF_ANC | SKF_AD_CPU: /* r_scratch = current_thread_info() */ OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx); /* A = current_thread_info()->cpu */ @@ -799,8 +870,10 @@ off = offsetof(struct thread_info, cpu); emit(ARM_LDR_I(r_A, r_scratch, off), ctx); break; - case BPF_S_ANC_IFINDEX: + case BPF_ANC | SKF_AD_IFINDEX: + case BPF_ANC | SKF_AD_HATYPE: /* A = skb->dev->ifindex */ + /* A = skb->dev->type */ ctx->seen |= SEEN_SKB; off = offsetof(struct sk_buff, dev); emit(ARM_LDR_I(r_scratch, r_skb, off), ctx); @@ -810,33 +883,62 @@ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - off = offsetof(struct net_device, ifindex); - emit(ARM_LDR_I(r_A, r_scratch, off), ctx); + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, + type) != 2); + + if (code == (BPF_ANC | SKF_AD_IFINDEX)) { + off = offsetof(struct net_device, ifindex); + emit(ARM_LDR_I(r_A, r_scratch, off), ctx); + } else { + /* + * offset of field "type" in "struct + * net_device" is above what can be + * used in the ldrh rd, [rn, #imm] + * instruction, so load the offset in + * a register and use ldrh rd, [rn, rm] + */ + off = offsetof(struct net_device, type); + emit_mov_i(ARM_R3, off, ctx); + emit(ARM_LDRH_R(r_A, r_scratch, ARM_R3), ctx); + } break; - case BPF_S_ANC_MARK: + case BPF_ANC | SKF_AD_MARK: ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); off = offsetof(struct sk_buff, mark); emit(ARM_LDR_I(r_A, r_skb, off), ctx); break; - case BPF_S_ANC_RXHASH: + case BPF_ANC | SKF_AD_RXHASH: ctx->seen |= SEEN_SKB; - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4); - off = offsetof(struct sk_buff, rxhash); + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + off = offsetof(struct sk_buff, hash); emit(ARM_LDR_I(r_A, r_skb, off), ctx); break; - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: + case BPF_ANC | SKF_AD_VLAN_TAG: + case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); off = offsetof(struct sk_buff, vlan_tci); emit(ARM_LDRH_I(r_A, r_skb, off), ctx); - if (inst->code == BPF_S_ANC_VLAN_TAG) - OP_IMM3(ARM_AND, r_A, r_A, VLAN_VID_MASK, ctx); - else - OP_IMM3(ARM_AND, r_A, r_A, VLAN_TAG_PRESENT, ctx); + if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) + OP_IMM3(ARM_AND, r_A, r_A, ~VLAN_TAG_PRESENT, ctx); + else { + OP_IMM3(ARM_LSR, r_A, r_A, 12, ctx); + OP_IMM3(ARM_AND, r_A, r_A, 0x1, ctx); + } + break; + case BPF_ANC | SKF_AD_PKTTYPE: + ctx->seen |= SEEN_SKB; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + __pkt_type_offset[0]) != 1); + off = PKT_TYPE_OFFSET(); + emit(ARM_LDRB_I(r_A, r_skb, off), ctx); + emit(ARM_AND_I(r_A, r_A, PKT_TYPE_MAX), ctx); +#ifdef __BIG_ENDIAN_BITFIELD + emit(ARM_LSR_I(r_A, r_A, 5), ctx); +#endif break; - case BPF_S_ANC_QUEUE: + case BPF_ANC | SKF_AD_QUEUE: ctx->seen |= SEEN_SKB; BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); @@ -845,9 +947,35 @@ off = offsetof(struct sk_buff, queue_mapping); emit(ARM_LDRH_I(r_A, r_skb, off), ctx); break; + case BPF_ANC | SKF_AD_PAY_OFFSET: + ctx->seen |= SEEN_SKB | SEEN_CALL; + + emit(ARM_MOV_R(ARM_R0, r_skb), ctx); + emit_mov_i(ARM_R3, (unsigned int)skb_get_poff, ctx); + emit_blx_r(ARM_R3, ctx); + emit(ARM_MOV_R(r_A, ARM_R0), ctx); + break; + case BPF_LDX | BPF_W | BPF_ABS: + /* + * load a 32bit word from struct seccomp_data. + * seccomp_check_filter() will already have checked + * that k is 32bit aligned and lies within the + * struct seccomp_data. + */ + ctx->seen |= SEEN_SKB; + emit(ARM_LDR_I(r_A, r_skb, k), ctx); + break; default: return -1; } + + if (ctx->flags & FLAG_IMM_OVERFLOW) + /* + * this instruction generated an overflow when + * trying to access the literal pool, so + * delegate this filter to the kernel interpreter. + */ + return -1; } /* compute offsets only during the first pass */ @@ -858,11 +986,13 @@ } -void bpf_jit_compile(struct sk_filter *fp) +void bpf_jit_compile(struct bpf_prog *fp) { + struct bpf_binary_header *header; struct jit_ctx ctx; unsigned tmp_idx; unsigned alloc_size; + u8 *target_ptr; if (!bpf_jit_enable) return; @@ -898,19 +1028,27 @@ /* there's nothing after the epilogue on ARMv7 */ build_epilogue(&ctx); #endif - alloc_size = 4 * ctx.idx; - ctx.target = module_alloc(max(sizeof(struct work_struct), - alloc_size)); - if (unlikely(ctx.target == NULL)) + header = bpf_jit_binary_alloc(alloc_size, &target_ptr, + 4, jit_fill_hole); + if (header == NULL) goto out; + ctx.target = (u32 *) target_ptr; ctx.idx = 0; + build_prologue(&ctx); - build_body(&ctx); + if (build_body(&ctx) < 0) { +#if __LINUX_ARM_ARCH__ < 7 + if (ctx.imm_count) + kfree(ctx.imms); +#endif + bpf_jit_binary_free(header); + goto out; + } build_epilogue(&ctx); - flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx)); + flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx)); #if __LINUX_ARM_ARCH__ < 7 if (ctx.imm_count) @@ -921,25 +1059,25 @@ /* there are 2 passes here */ bpf_jit_dump(fp->len, alloc_size, 2, ctx.target); + set_memory_ro((unsigned long)header, header->pages); fp->bpf_func = (void *)ctx.target; + fp->jited = 1; out: kfree(ctx.offsets); return; } -static void bpf_jit_free_worker(struct work_struct *work) +void bpf_jit_free(struct bpf_prog *fp) { - module_free(NULL, work); -} + unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; + struct bpf_binary_header *header = (void *)addr; -void bpf_jit_free(struct sk_filter *fp) -{ - struct work_struct *work; + if (!fp->jited) + goto free_filter; - if (fp->bpf_func != sk_run_filter) { - work = (struct work_struct *)fp->bpf_func; + set_memory_rw(addr, header->pages); + bpf_jit_binary_free(header); - INIT_WORK(work, bpf_jit_free_worker); - schedule_work(work); - } +free_filter: + bpf_prog_unlock_free(fp); }