/* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <linux/filter.h>#include <linux/skbuff.h>#include <linux/vmalloc.h>#include <linux/random.h>#include <linux/moduleloader.h>#include <linux/bpf.h>#include <linux/frame.h> #include <asm/unaligned.h> /* Registers */#define BPF_R0 regs[BPF_REG_0]#define BPF_R1 regs[BPF_REG_1]#define BPF_R2 regs[BPF_REG_2]#define BPF_R3 regs[BPF_REG_3]#define BPF_R4 regs[BPF_REG_4]#define BPF_R5 regs[BPF_REG_5]#define BPF_R6 regs[BPF_REG_6]#define BPF_R7 regs[BPF_REG_7]#define BPF_R8 regs[BPF_REG_8]#define BPF_R9 regs[BPF_REG_9]#define BPF_R10 regs[BPF_REG_10] /* Named registers */#define DST regs[insn->dst_reg]#define SRC regs[insn->src_reg]#define FP regs[BPF_REG_FP]#define ARG1 regs[BPF_REG_ARG1]#define CTX regs[BPF_REG_CTX]#define IMM insn->imm /* No hurry in this branch * * Exported for the bpf jit load helper. */void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size){ u8 *ptr = NULL; if (k >= SKF_NET_OFF) ptr = skb_network_header(skb) + k - SKF_NET_OFF; else if (k >= SKF_LL_OFF) ptr = skb_mac_header(skb) + k - SKF_LL_OFF; if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; return NULL;} struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags){ gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | gfp_extra_flags; struct bpf_prog_aux *aux; struct bpf_prog *fp; size = round_up(size, PAGE_SIZE); fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); if (fp == NULL) return NULL; kmemcheck_annotate_bitfield(fp, meta); aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags); if (aux == NULL) { vfree(fp); return NULL; } fp->pages = size / PAGE_SIZE; fp->aux = aux; fp->aux->prog = fp; return fp;}EXPORT_SYMBOL_GPL(bpf_prog_alloc); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags){ gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; BUG_ON(fp_old == NULL); size = round_up(size, PAGE_SIZE); if (size <= fp_old->pages * PAGE_SIZE) return fp_old; fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); if (fp != NULL) { kmemcheck_annotate_bitfield(fp, meta); memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); fp->pages = size / PAGE_SIZE; fp->aux->prog = fp; /* We keep fp->aux from fp_old around in the new * reallocated structure. */ fp_old->aux = NULL; __bpf_prog_free(fp_old); } return fp;} void __bpf_prog_free(struct bpf_prog *fp){ kfree(fp->aux); vfree(fp);} static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn){ return BPF_CLASS(insn->code) == BPF_JMP && /* Call and Exit are both special jumps with no * target inside the BPF instruction image. */ BPF_OP(insn->code) != BPF_CALL && BPF_OP(insn->code) != BPF_EXIT;} static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta){ struct bpf_insn *insn = prog->insnsi; u32 i, insn_cnt = prog->len; for (i = 0; i < insn_cnt; i++, insn++) { if (!bpf_is_jmp_and_has_target(insn)) continue; /* Adjust offset of jmps if we cross boundaries. */ if (i < pos && i + insn->off + 1 > pos) insn->off += delta; else if (i > pos + delta && i + insn->off + 1 <= pos + delta) insn->off -= delta; }} struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len){ u32 insn_adj_cnt, insn_rest, insn_delta = len - 1; struct bpf_prog *prog_adj; /* Since our patchlet doesn't expand the image, we're done. */ if (insn_delta == 0) { memcpy(prog->insnsi + off, patch, sizeof(*patch)); return prog; } insn_adj_cnt = prog->len + insn_delta; /* Several new instructions need to be inserted. Make room * for them. Likely, there's no need for a new allocation as * last page could have large enough tailroom. */ prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt), GFP_USER); if (!prog_adj) return NULL; prog_adj->len = insn_adj_cnt; /* Patching happens in 3 steps: * * 1) Move over tail of insnsi from next instruction onwards, * so we can patch the single target insn with one or more * new ones (patching is always from 1 to n insns, n > 0). * 2) Inject new instructions at the target location. * 3) Adjust branch offsets if necessary. */ insn_rest = insn_adj_cnt - off - len; memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1, sizeof(*patch) * insn_rest); memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len); bpf_adj_branches(prog_adj, off, insn_delta); return prog_adj;} #ifdef CONFIG_BPF_JITstruct bpf_binary_header *bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns){ struct bpf_binary_header *hdr; unsigned int size, hole, start; /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); hdr = module_alloc(size); if (hdr == NULL) return NULL; /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); hdr->pages = size / PAGE_SIZE; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); /* Leave a random number of instructions before BPF code. */ *image_ptr = &hdr->image[start]; return hdr;} void bpf_jit_binary_free(struct bpf_binary_header *hdr){ module_memfree(hdr);} int bpf_jit_harden __read_mostly; static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff){ struct bpf_insn *to = to_buff; u32 imm_rnd = get_random_int(); s16 off; BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG); if (from->imm == 0 && (from->code == (BPF_ALU | BPF_MOV | BPF_K) || from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) { *to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg); goto out; } switch (from->code) { case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MOV | BPF_K: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX); break; case BPF_ALU64 | BPF_ADD | BPF_K: case BPF_ALU64 | BPF_SUB | BPF_K: case BPF_ALU64 | BPF_AND | BPF_K: case BPF_ALU64 | BPF_OR | BPF_K: case BPF_ALU64 | BPF_XOR | BPF_K: case BPF_ALU64 | BPF_MUL | BPF_K: case BPF_ALU64 | BPF_MOV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_MOD | BPF_K: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX); break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; if (off < 0) off -= 2; *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; case BPF_LD | BPF_ABS | BPF_W: case BPF_LD | BPF_ABS | BPF_H: case BPF_LD | BPF_ABS | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0); break; case BPF_LD | BPF_IND | BPF_W: case BPF_LD | BPF_IND | BPF_H: case BPF_LD | BPF_IND | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU32_REG(BPF_ADD, BPF_REG_AX, from->src_reg); *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0); break; case BPF_LD | BPF_IMM | BPF_DW: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); *to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX); break; case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX); break; case BPF_ST | BPF_MEM | BPF_DW: case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off); break; }out: return to - to_buff;} static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other, gfp_t gfp_extra_flags){ gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL); if (fp != NULL) { kmemcheck_annotate_bitfield(fp, meta); /* aux->prog still points to the fp_other one, so * when promoting the clone to the real program, * this still needs to be adapted. */ memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE); } return fp;} static void bpf_prog_clone_free(struct bpf_prog *fp){ /* aux was stolen by the other clone, so we cannot free * it from this path! It will be freed eventually by the * other program on release. * * At this point, we don't need a deferred release since * clone is guaranteed to not be locked. */ fp->aux = NULL; __bpf_prog_free(fp);} void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other){ /* We have to repoint aux->prog to self, as we don't * know whether fp here is the clone or the original. */ fp->aux->prog = fp; bpf_prog_clone_free(fp_other);} struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog){ struct bpf_insn insn_buff[16], aux[2]; struct bpf_prog *clone, *tmp; int insn_delta, insn_cnt; struct bpf_insn *insn; int i, rewritten; if (!bpf_jit_blinding_enabled()) return prog; clone = bpf_prog_clone_create(prog, GFP_USER); if (!clone) return ERR_PTR(-ENOMEM); insn_cnt = clone->len; insn = clone->insnsi; for (i = 0; i < insn_cnt; i++, insn++) { /* We temporarily need to hold the original ld64 insn * so that we can still access the first part in the * second blinding run. */ if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) && insn[1].code == 0) memcpy(aux, insn, sizeof(aux)); rewritten = bpf_jit_blind_insn(insn, aux, insn_buff); if (!rewritten) continue; tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten); if (!tmp) { /* Patching may have repointed aux->prog during * realloc from the original one, so we need to * fix it up here on error. */ bpf_jit_prog_release_other(prog, clone); return ERR_PTR(-ENOMEM); } clone = tmp; insn_delta = rewritten - 1; /* Walk new program and skip insns we just inserted. */ insn = clone->insnsi + i + insn_delta; insn_cnt += insn_delta; i += insn_delta; } return clone;}#endif /* CONFIG_BPF_JIT */ /* Base function for offset calculation. Needs to go into .text section, * therefore keeping it non-static as well; will also be used by JITs * anyway later on, so do not let the compiler omit it. */noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5){ return 0;}EXPORT_SYMBOL_GPL(__bpf_call_base); /** * __bpf_prog_run - run eBPF program on a given context * @ctx: is the data we are operating on * @insn: is the array of eBPF instructions * * Decode and execute eBPF instructions. */static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn){ u64 stack[MAX_BPF_STACK / sizeof(u64)]; u64 regs[MAX_BPF_REG], tmp; static const void *jumptable[256] = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ /* 32 bit ALU operations */ [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X, [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K, [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X, [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K, [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X, [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K, [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X, [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K, [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X, [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K, [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X, [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K, [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X, [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K, [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X, [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K, [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X, [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K, [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X, [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K, [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X, [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K, [BPF_ALU | BPF_NEG] = &&ALU_NEG, [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE, [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,Lines 1–500 of 1092. Load more
/* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/random.h> #include <linux/moduleloader.h> #include <linux/bpf.h> #include <linux/frame.h> #include <asm/unaligned.h> /* Registers */ #define BPF_R0 regs[BPF_REG_0] #define BPF_R1 regs[BPF_REG_1] #define BPF_R2 regs[BPF_REG_2] #define BPF_R3 regs[BPF_REG_3] #define BPF_R4 regs[BPF_REG_4] #define BPF_R5 regs[BPF_REG_5] #define BPF_R6 regs[BPF_REG_6] #define BPF_R7 regs[BPF_REG_7] #define BPF_R8 regs[BPF_REG_8] #define BPF_R9 regs[BPF_REG_9] #define BPF_R10 regs[BPF_REG_10] /* Named registers */ #define DST regs[insn->dst_reg] #define SRC regs[insn->src_reg] #define FP regs[BPF_REG_FP] #define ARG1 regs[BPF_REG_ARG1] #define CTX regs[BPF_REG_CTX] #define IMM insn->imm /* No hurry in this branch * * Exported for the bpf jit load helper. */ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; if (k >= SKF_NET_OFF) ptr = skb_network_header(skb) + k - SKF_NET_OFF; else if (k >= SKF_LL_OFF) ptr = skb_mac_header(skb) + k - SKF_LL_OFF; if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; return NULL; } struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | gfp_extra_flags; struct bpf_prog_aux *aux; struct bpf_prog *fp; size = round_up(size, PAGE_SIZE); fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); if (fp == NULL) return NULL; kmemcheck_annotate_bitfield(fp, meta); aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags); if (aux == NULL) { vfree(fp); return NULL; } fp->pages = size / PAGE_SIZE; fp->aux = aux; fp->aux->prog = fp; return fp; } EXPORT_SYMBOL_GPL(bpf_prog_alloc); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; BUG_ON(fp_old == NULL); size = round_up(size, PAGE_SIZE); if (size <= fp_old->pages * PAGE_SIZE) return fp_old; fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); if (fp != NULL) { kmemcheck_annotate_bitfield(fp, meta); memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); fp->pages = size / PAGE_SIZE; fp->aux->prog = fp; /* We keep fp->aux from fp_old around in the new * reallocated structure. */ fp_old->aux = NULL; __bpf_prog_free(fp_old); } return fp; } void __bpf_prog_free(struct bpf_prog *fp) { kfree(fp->aux); vfree(fp); } static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_JMP && /* Call and Exit are both special jumps with no * target inside the BPF instruction image. */ BPF_OP(insn->code) != BPF_CALL && BPF_OP(insn->code) != BPF_EXIT; } static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta) { struct bpf_insn *insn = prog->insnsi; u32 i, insn_cnt = prog->len; for (i = 0; i < insn_cnt; i++, insn++) { if (!bpf_is_jmp_and_has_target(insn)) continue; /* Adjust offset of jmps if we cross boundaries. */ if (i < pos && i + insn->off + 1 > pos) insn->off += delta; else if (i > pos + delta && i + insn->off + 1 <= pos + delta) insn->off -= delta; } } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len) { u32 insn_adj_cnt, insn_rest, insn_delta = len - 1; struct bpf_prog *prog_adj; /* Since our patchlet doesn't expand the image, we're done. */ if (insn_delta == 0) { memcpy(prog->insnsi + off, patch, sizeof(*patch)); return prog; } insn_adj_cnt = prog->len + insn_delta; /* Several new instructions need to be inserted. Make room * for them. Likely, there's no need for a new allocation as * last page could have large enough tailroom. */ prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt), GFP_USER); if (!prog_adj) return NULL; prog_adj->len = insn_adj_cnt; /* Patching happens in 3 steps: * * 1) Move over tail of insnsi from next instruction onwards, * so we can patch the single target insn with one or more * new ones (patching is always from 1 to n insns, n > 0). * 2) Inject new instructions at the target location. * 3) Adjust branch offsets if necessary. */ insn_rest = insn_adj_cnt - off - len; memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1, sizeof(*patch) * insn_rest); memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len); bpf_adj_branches(prog_adj, off, insn_delta); return prog_adj; } #ifdef CONFIG_BPF_JIT struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *hdr; unsigned int size, hole, start; /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); hdr = module_alloc(size); if (hdr == NULL) return NULL; /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); hdr->pages = size / PAGE_SIZE; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); /* Leave a random number of instructions before BPF code. */ *image_ptr = &hdr->image[start]; return hdr; } void bpf_jit_binary_free(struct bpf_binary_header *hdr) { module_memfree(hdr); } int bpf_jit_harden __read_mostly; static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff) { struct bpf_insn *to = to_buff; u32 imm_rnd = get_random_int(); s16 off; BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG); if (from->imm == 0 && (from->code == (BPF_ALU | BPF_MOV | BPF_K) || from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) { *to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg); goto out; } switch (from->code) { case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MOV | BPF_K: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX); break; case BPF_ALU64 | BPF_ADD | BPF_K: case BPF_ALU64 | BPF_SUB | BPF_K: case BPF_ALU64 | BPF_AND | BPF_K: case BPF_ALU64 | BPF_OR | BPF_K: case BPF_ALU64 | BPF_XOR | BPF_K: case BPF_ALU64 | BPF_MUL | BPF_K: case BPF_ALU64 | BPF_MOV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_MOD | BPF_K: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX); break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; if (off < 0) off -= 2; *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; case BPF_LD | BPF_ABS | BPF_W: case BPF_LD | BPF_ABS | BPF_H: case BPF_LD | BPF_ABS | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0); break; case BPF_LD | BPF_IND | BPF_W: case BPF_LD | BPF_IND | BPF_H: case BPF_LD | BPF_IND | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU32_REG(BPF_ADD, BPF_REG_AX, from->src_reg); *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0); break; case BPF_LD | BPF_IMM | BPF_DW: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); *to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX); break; case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX); break; case BPF_ST | BPF_MEM | BPF_DW: case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off); break; } out: return to - to_buff; } static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL); if (fp != NULL) { kmemcheck_annotate_bitfield(fp, meta); /* aux->prog still points to the fp_other one, so * when promoting the clone to the real program, * this still needs to be adapted. */ memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE); } return fp; } static void bpf_prog_clone_free(struct bpf_prog *fp) { /* aux was stolen by the other clone, so we cannot free * it from this path! It will be freed eventually by the * other program on release. * * At this point, we don't need a deferred release since * clone is guaranteed to not be locked. */ fp->aux = NULL; __bpf_prog_free(fp); } void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other) { /* We have to repoint aux->prog to self, as we don't * know whether fp here is the clone or the original. */ fp->aux->prog = fp; bpf_prog_clone_free(fp_other); } struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) { struct bpf_insn insn_buff[16], aux[2]; struct bpf_prog *clone, *tmp; int insn_delta, insn_cnt; struct bpf_insn *insn; int i, rewritten; if (!bpf_jit_blinding_enabled()) return prog; clone = bpf_prog_clone_create(prog, GFP_USER); if (!clone) return ERR_PTR(-ENOMEM); insn_cnt = clone->len; insn = clone->insnsi; for (i = 0; i < insn_cnt; i++, insn++) { /* We temporarily need to hold the original ld64 insn * so that we can still access the first part in the * second blinding run. */ if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) && insn[1].code == 0) memcpy(aux, insn, sizeof(aux)); rewritten = bpf_jit_blind_insn(insn, aux, insn_buff); if (!rewritten) continue; tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten); if (!tmp) { /* Patching may have repointed aux->prog during * realloc from the original one, so we need to * fix it up here on error. */ bpf_jit_prog_release_other(prog, clone); return ERR_PTR(-ENOMEM); } clone = tmp; insn_delta = rewritten - 1; /* Walk new program and skip insns we just inserted. */ insn = clone->insnsi + i + insn_delta; insn_cnt += insn_delta; i += insn_delta; } return clone; } #endif /* CONFIG_BPF_JIT */ /* Base function for offset calculation. Needs to go into .text section, * therefore keeping it non-static as well; will also be used by JITs * anyway later on, so do not let the compiler omit it. */ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return 0; } EXPORT_SYMBOL_GPL(__bpf_call_base); /** * __bpf_prog_run - run eBPF program on a given context * @ctx: is the data we are operating on * @insn: is the array of eBPF instructions * * Decode and execute eBPF instructions. */ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) { u64 stack[MAX_BPF_STACK / sizeof(u64)]; u64 regs[MAX_BPF_REG], tmp; static const void *jumptable[256] = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ /* 32 bit ALU operations */ [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X, [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K, [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X, [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K, [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X, [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K, [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X, [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K, [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X, [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K, [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X, [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K, [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X, [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K, [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X, [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K, [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X, [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K, [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X, [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K, [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X, [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K, [BPF_ALU | BPF_NEG] = &&ALU_NEG, [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE, [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,