diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/core.c | 54 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 2 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 336 | ||||
-rw-r--r-- | kernel/compat.c | 18 | ||||
-rw-r--r-- | kernel/events/core.c | 2 | ||||
-rw-r--r-- | kernel/exit.c | 6 | ||||
-rw-r--r-- | kernel/futex.c | 35 | ||||
-rw-r--r-- | kernel/printk/printk.c | 4 | ||||
-rw-r--r-- | kernel/ptrace.c | 4 | ||||
-rw-r--r-- | kernel/rseq.c | 6 | ||||
-rw-r--r-- | kernel/sched/core.c | 4 | ||||
-rw-r--r-- | kernel/signal.c | 8 | ||||
-rw-r--r-- | kernel/sys.c | 2 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 2 |
14 files changed, 359 insertions, 124 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 38de580abcc2..f908b9356025 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -54,6 +54,7 @@ #define DST regs[insn->dst_reg] #define SRC regs[insn->src_reg] #define FP regs[BPF_REG_FP] +#define AX regs[BPF_REG_AX] #define ARG1 regs[BPF_REG_ARG1] #define CTX regs[BPF_REG_CTX] #define IMM insn->imm @@ -857,6 +858,26 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG); + /* Constraints on AX register: + * + * AX register is inaccessible from user space. It is mapped in + * all JITs, and used here for constant blinding rewrites. It is + * typically "stateless" meaning its contents are only valid within + * the executed instruction, but not across several instructions. + * There are a few exceptions however which are further detailed + * below. + * + * Constant blinding is only used by JITs, not in the interpreter. + * The interpreter uses AX in some occasions as a local temporary + * register e.g. in DIV or MOD instructions. + * + * In restricted circumstances, the verifier can also use the AX + * register for rewrites as long as they do not interfere with + * the above cases! + */ + if (from->dst_reg == BPF_REG_AX || from->src_reg == BPF_REG_AX) + goto out; + if (from->imm == 0 && (from->code == (BPF_ALU | BPF_MOV | BPF_K) || from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) { @@ -1188,7 +1209,6 @@ bool bpf_opcode_in_insntable(u8 code) */ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) { - u64 tmp; #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z static const void *jumptable[256] = { @@ -1268,36 +1288,36 @@ select_insn: (*(s64 *) &DST) >>= IMM; CONT; ALU64_MOD_X: - div64_u64_rem(DST, SRC, &tmp); - DST = tmp; + div64_u64_rem(DST, SRC, &AX); + DST = AX; CONT; ALU_MOD_X: - tmp = (u32) DST; - DST = do_div(tmp, (u32) SRC); + AX = (u32) DST; + DST = do_div(AX, (u32) SRC); CONT; ALU64_MOD_K: - div64_u64_rem(DST, IMM, &tmp); - DST = tmp; + div64_u64_rem(DST, IMM, &AX); + DST = AX; CONT; ALU_MOD_K: - tmp = (u32) DST; - DST = do_div(tmp, (u32) IMM); + AX = (u32) DST; + DST = do_div(AX, (u32) IMM); CONT; ALU64_DIV_X: DST = div64_u64(DST, SRC); CONT; ALU_DIV_X: - tmp = (u32) DST; - do_div(tmp, (u32) SRC); - DST = (u32) tmp; + AX = (u32) DST; + do_div(AX, (u32) SRC); + DST = (u32) AX; CONT; ALU64_DIV_K: DST = div64_u64(DST, IMM); CONT; ALU_DIV_K: - tmp = (u32) DST; - do_div(tmp, (u32) IMM); - DST = (u32) tmp; + AX = (u32) DST; + do_div(AX, (u32) IMM); + DST = (u32) AX; CONT; ALU_END_TO_BE: switch (IMM) { @@ -1553,7 +1573,7 @@ STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ - u64 regs[MAX_BPF_REG]; \ + u64 regs[MAX_BPF_EXT_REG]; \ \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ ARG1 = (u64) (unsigned long) ctx; \ @@ -1566,7 +1586,7 @@ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \ const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ - u64 regs[MAX_BPF_REG]; \ + u64 regs[MAX_BPF_EXT_REG]; \ \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ BPF_R1 = r1; \ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0607db304def..b155cd17c1bd 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -79,7 +79,7 @@ int bpf_check_uarg_tail_zero(void __user *uaddr, if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; - if (unlikely(!access_ok(VERIFY_READ, uaddr, actual_size))) + if (unlikely(!access_ok(uaddr, actual_size))) return -EFAULT; if (actual_size <= expected_size) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 71d86e3024ae..f6bc62a9ee8e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -710,6 +710,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, free_func_state(dst_state->frame[i]); dst_state->frame[i] = NULL; } + dst_state->speculative = src->speculative; dst_state->curframe = src->curframe; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; @@ -754,7 +755,8 @@ static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, } static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, - int insn_idx, int prev_insn_idx) + int insn_idx, int prev_insn_idx, + bool speculative) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem; @@ -772,6 +774,7 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, err = copy_verifier_state(&elem->st, cur); if (err) goto err; + elem->st.speculative |= speculative; if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) { verbose(env, "BPF program is too complex\n"); goto err; @@ -1387,6 +1390,31 @@ static int check_stack_read(struct bpf_verifier_env *env, } } +static int check_stack_access(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + int off, int size) +{ + /* Stack accesses must be at a fixed offset, so that we + * can determine what type of data were returned. See + * check_stack_read(). + */ + if (!tnum_is_const(reg->var_off)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, "variable stack access var_off=%s off=%d size=%d", + tn_buf, off, size); + return -EACCES; + } + + if (off >= 0 || off < -MAX_BPF_STACK) { + verbose(env, "invalid stack off=%d size=%d\n", off, size); + return -EACCES; + } + + return 0; +} + /* check read/write into map element returned by bpf_map_lookup_elem() */ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) @@ -1418,13 +1446,17 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, */ if (env->log.level) print_verifier_state(env, state); + /* The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our * index'es we need to make sure that whatever we use * will have a set floor within our range. */ - if (reg->smin_value < 0) { + if (reg->smin_value < 0 && + (reg->smin_value == S64_MIN || + (off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) || + reg->smin_value + off < 0)) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; @@ -1954,24 +1986,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } } else if (reg->type == PTR_TO_STACK) { - /* stack accesses must be at a fixed offset, so that we can - * determine what type of data were returned. - * See check_stack_read(). - */ - if (!tnum_is_const(reg->var_off)) { - char tn_buf[48]; - - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "variable stack access var_off=%s off=%d size=%d", - tn_buf, off, size); - return -EACCES; - } off += reg->var_off.value; - if (off >= 0 || off < -MAX_BPF_STACK) { - verbose(env, "invalid stack off=%d size=%d\n", off, - size); - return -EACCES; - } + err = check_stack_access(env, reg, off, size); + if (err) + return err; state = func(env, reg); err = update_stack_depth(env, state, off); @@ -3052,6 +3070,102 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env, return true; } +static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env) +{ + return &env->insn_aux_data[env->insn_idx]; +} + +static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, + u32 *ptr_limit, u8 opcode, bool off_is_neg) +{ + bool mask_to_left = (opcode == BPF_ADD && off_is_neg) || + (opcode == BPF_SUB && !off_is_neg); + u32 off; + + switch (ptr_reg->type) { + case PTR_TO_STACK: + off = ptr_reg->off + ptr_reg->var_off.value; + if (mask_to_left) + *ptr_limit = MAX_BPF_STACK + off; + else + *ptr_limit = -off; + return 0; + case PTR_TO_MAP_VALUE: + if (mask_to_left) { + *ptr_limit = ptr_reg->umax_value + ptr_reg->off; + } else { + off = ptr_reg->smin_value + ptr_reg->off; + *ptr_limit = ptr_reg->map_ptr->value_size - off; + } + return 0; + default: + return -EINVAL; + } +} + +static int sanitize_ptr_alu(struct bpf_verifier_env *env, + struct bpf_insn *insn, + const struct bpf_reg_state *ptr_reg, + struct bpf_reg_state *dst_reg, + bool off_is_neg) +{ + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_insn_aux_data *aux = cur_aux(env); + bool ptr_is_dst_reg = ptr_reg == dst_reg; + u8 opcode = BPF_OP(insn->code); + u32 alu_state, alu_limit; + struct bpf_reg_state tmp; + bool ret; + + if (env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K) + return 0; + + /* We already marked aux for masking from non-speculative + * paths, thus we got here in the first place. We only care + * to explore bad access from here. + */ + if (vstate->speculative) + goto do_sim; + + alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; + alu_state |= ptr_is_dst_reg ? + BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + + if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg)) + return 0; + + /* If we arrived here from different branches with different + * limits to sanitize, then this won't work. + */ + if (aux->alu_state && + (aux->alu_state != alu_state || + aux->alu_limit != alu_limit)) + return -EACCES; + + /* Corresponding fixup done in fixup_bpf_calls(). */ + aux->alu_state = alu_state; + aux->alu_limit = alu_limit; + +do_sim: + /* Simulate and find potential out-of-bounds access under + * speculative execution from truncation as a result of + * masking when off was not within expected range. If off + * sits in dst, then we temporarily need to move ptr there + * to simulate dst (== 0) +/-= ptr. Needed, for example, + * for cases where we use K-based arithmetic in one direction + * and truncated reg-based in the other in order to explore + * bad access. + */ + if (!ptr_is_dst_reg) { + tmp = *dst_reg; + *dst_reg = *ptr_reg; + } + ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); + if (!ptr_is_dst_reg) + *dst_reg = tmp; + return !ret ? -EFAULT : 0; +} + /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off. * Caller should also handle BPF_MOV case separately. * If we return -EACCES, caller may want to try again treating pointer as a @@ -3070,8 +3184,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; + u32 dst = insn->dst_reg, src = insn->src_reg; u8 opcode = BPF_OP(insn->code); - u32 dst = insn->dst_reg; + int ret; dst_reg = ®s[dst]; @@ -3104,6 +3219,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str[ptr_reg->type]); return -EACCES; + case PTR_TO_MAP_VALUE: + if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) { + verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n", + off_reg == dst_reg ? dst : src); + return -EACCES; + } + /* fall-through */ default: break; } @@ -3120,6 +3242,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, switch (opcode) { case BPF_ADD: + ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); + if (ret < 0) { + verbose(env, "R%d tried to add from different maps or paths\n", dst); + return ret; + } /* We can take a fixed offset as long as it doesn't overflow * the s32 'off' field */ @@ -3170,6 +3297,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } break; case BPF_SUB: + ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); + if (ret < 0) { + verbose(env, "R%d tried to sub from different maps or paths\n", dst); + return ret; + } if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ verbose(env, "R%d tried to subtract pointer from scalar\n", @@ -3249,6 +3381,25 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, __update_reg_bounds(dst_reg); __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); + + /* For unprivileged we require that resulting offset must be in bounds + * in order to be able to sanitize access later on. + */ + if (!env->allow_ptr_leaks) { + if (dst_reg->type == PTR_TO_MAP_VALUE && + check_map_access(env, dst, dst_reg->off, 1, false)) { + verbose(env, "R%d pointer arithmetic of map value goes out of range, " + "prohibited for !root\n", dst); + return -EACCES; + } else if (dst_reg->type == PTR_TO_STACK && + check_stack_access(env, dst_reg, dst_reg->off + + dst_reg->var_off.value, 1)) { + verbose(env, "R%d stack pointer arithmetic goes out of range, " + "prohibited for !root\n", dst); + return -EACCES; + } + } + return 0; } @@ -4348,7 +4499,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } } - other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx); + other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, + false); if (!other_branch) return -EFAULT; other_branch_regs = other_branch->frame[other_branch->curframe]->regs; @@ -5458,6 +5610,12 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->curframe != cur->curframe) return false; + /* Verification state from speculative execution simulation + * must never prune a non-speculative execution one. + */ + if (old->speculative && !cur->speculative) + return false; + /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ @@ -5650,7 +5808,6 @@ static int do_check(struct bpf_verifier_env *env) struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; int insn_cnt = env->prog->len, i; - int insn_idx, prev_insn_idx = 0; int insn_processed = 0; bool do_print_state = false; @@ -5660,6 +5817,7 @@ static int do_check(struct bpf_verifier_env *env) if (!state) return -ENOMEM; state->curframe = 0; + state->speculative = false; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); if (!state->frame[0]) { kfree(state); @@ -5670,19 +5828,19 @@ static int do_check(struct bpf_verifier_env *env) BPF_MAIN_FUNC /* callsite */, 0 /* frameno */, 0 /* subprogno, zero == main subprog */); - insn_idx = 0; + for (;;) { struct bpf_insn *insn; u8 class; int err; - if (insn_idx >= insn_cnt) { + if (env->insn_idx >= insn_cnt) { verbose(env, "invalid insn idx %d insn_cnt %d\n", - insn_idx, insn_cnt); + env->insn_idx, insn_cnt); return -EFAULT; } - insn = &insns[insn_idx]; + insn = &insns[env->insn_idx]; class = BPF_CLASS(insn->code); if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { @@ -5692,17 +5850,19 @@ static int do_check(struct bpf_verifier_env *env) return -E2BIG; } - err = is_state_visited(env, insn_idx); + err = is_state_visited(env, env->insn_idx); if (err < 0) return err; if (err == 1) { /* found equivalent state, can prune the search */ if (env->log.level) { if (do_print_state) - verbose(env, "\nfrom %d to %d: safe\n", - prev_insn_idx, insn_idx); + verbose(env, "\nfrom %d to %d%s: safe\n", + env->prev_insn_idx, env->insn_idx, + env->cur_state->speculative ? + " (speculative execution)" : ""); else - verbose(env, "%d: safe\n", insn_idx); + verbose(env, "%d: safe\n", env->insn_idx); } goto process_bpf_exit; } @@ -5715,10 +5875,12 @@ static int do_check(struct bpf_verifier_env *env) if (env->log.level > 1 || (env->log.level && do_print_state)) { if (env->log.level > 1) - verbose(env, "%d:", insn_idx); + verbose(env, "%d:", env->insn_idx); else - verbose(env, "\nfrom %d to %d:", - prev_insn_idx, insn_idx); + verbose(env, "\nfrom %d to %d%s:", + env->prev_insn_idx, env->insn_idx, + env->cur_state->speculative ? + " (speculative execution)" : ""); print_verifier_state(env, state->frame[state->curframe]); do_print_state = false; } @@ -5729,20 +5891,20 @@ static int do_check(struct bpf_verifier_env *env) .private_data = env, }; - verbose_linfo(env, insn_idx, "; "); - verbose(env, "%d: ", insn_idx); + verbose_linfo(env, env->insn_idx, "; "); + verbose(env, "%d: ", env->insn_idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } if (bpf_prog_is_dev_bound(env->prog->aux)) { - err = bpf_prog_offload_verify_insn(env, insn_idx, - prev_insn_idx); + err = bpf_prog_offload_verify_insn(env, env->insn_idx, + env->prev_insn_idx); if (err) return err; } regs = cur_regs(env); - env->insn_aux_data[insn_idx].seen = true; + env->insn_aux_data[env->insn_idx].seen = true; if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); @@ -5768,13 +5930,13 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (src_reg + off) is readable, * the state of dst_reg will be updated by this func */ - err = check_mem_access(env, insn_idx, insn->src_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, - insn->dst_reg, false); + err = check_mem_access(env, env->insn_idx, insn->src_reg, + insn->off, BPF_SIZE(insn->code), + BPF_READ, insn->dst_reg, false); if (err) return err; - prev_src_type = &env->insn_aux_data[insn_idx].ptr_type; + prev_src_type = &env->insn_aux_data[env->insn_idx].ptr_type; if (*prev_src_type == NOT_INIT) { /* saw a valid insn @@ -5799,10 +5961,10 @@ static int do_check(struct bpf_verifier_env *env) enum bpf_reg_type *prev_dst_type, dst_reg_type; if (BPF_MODE(insn->code) == BPF_XADD) { - err = check_xadd(env, insn_idx, insn); + err = check_xadd(env, env->insn_idx, insn); if (err) return err; - insn_idx++; + env->insn_idx++; continue; } @@ -5818,13 +5980,13 @@ static int do_check(struct bpf_verifier_env *env) dst_reg_type = regs[insn->dst_reg].type; /* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_WRITE, - insn->src_reg, false); + err = check_mem_access(env, env->insn_idx, insn->dst_reg, + insn->off, BPF_SIZE(insn->code), + BPF_WRITE, insn->src_reg, false); if (err) return err; - prev_dst_type = &env->insn_aux_data[insn_idx].ptr_type; + prev_dst_type = &env->insn_aux_data[env->insn_idx].ptr_type; if (*prev_dst_type == NOT_INIT) { *prev_dst_type = dst_reg_type; @@ -5852,9 +6014,9 @@ static int do_check(struct bpf_verifier_env *env) } /* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_WRITE, - -1, false); + err = check_mem_access(env, env->insn_idx, insn->dst_reg, + insn->off, BPF_SIZE(insn->code), + BPF_WRITE, -1, false); if (err) return err; @@ -5872,9 +6034,9 @@ static int do_check(struct bpf_verifier_env *env) } if (insn->src_reg == BPF_PSEUDO_CALL) - err = check_func_call(env, insn, &insn_idx); + err = check_func_call(env, insn, &env->insn_idx); else - err = check_helper_call(env, insn->imm, insn_idx); + err = check_helper_call(env, insn->imm, env->insn_idx); if (err) return err; @@ -5887,7 +6049,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - insn_idx += insn->off + 1; + env->insn_idx += insn->off + 1; continue; } else if (opcode == BPF_EXIT) { @@ -5901,8 +6063,8 @@ static int do_check(struct bpf_verifier_env *env) if (state->curframe) { /* exit from nested function */ - prev_insn_idx = insn_idx; - err = prepare_func_exit(env, &insn_idx); + env->prev_insn_idx = env->insn_idx; + err = prepare_func_exit(env, &env->insn_idx); if (err) return err; do_print_state = true; @@ -5932,7 +6094,8 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; process_bpf_exit: - err = pop_stack(env, &prev_insn_idx, &insn_idx); + err = pop_stack(env, &env->prev_insn_idx, + &env->insn_idx); if (err < 0) { if (err != -ENOENT) return err; @@ -5942,7 +6105,7 @@ process_bpf_exit: continue; } } else { - err = check_cond_jmp_op(env, insn, &insn_idx); + err = check_cond_jmp_op(env, insn, &env->insn_idx); if (err) return err; } @@ -5959,8 +6122,8 @@ process_bpf_exit: if (err) return err; - insn_idx++; - env->insn_aux_data[insn_idx].seen = true; + env->insn_idx++; + env->insn_aux_data[env->insn_idx].seen = true; } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; @@ -5970,7 +6133,7 @@ process_bpf_exit: return -EINVAL; } - insn_idx++; + env->insn_idx++; } verbose(env, "processed %d insns (limit %d), stack depth ", @@ -6709,6 +6872,57 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) continue; } + if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) || + insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) { + const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X; + const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X; + struct bpf_insn insn_buf[16]; + struct bpf_insn *patch = &insn_buf[0]; + bool issrc, isneg; + u32 off_reg; + + aux = &env->insn_aux_data[i + delta]; + if (!aux->alu_state) + continue; + + isneg = aux->alu_state & BPF_ALU_NEG_VALUE; + issrc = (aux->alu_state & BPF_ALU_SANITIZE) == + BPF_ALU_SANITIZE_SRC; + + off_reg = issrc ? insn->src_reg : insn->dst_reg; + if (isneg) + *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); + *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1); + *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); + *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); + *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); + *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63); + if (issrc) { + *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, + off_reg); + insn->src_reg = BPF_REG_AX; + } else { + *patch++ = BPF_ALU64_REG(BPF_AND, off_reg, + BPF_REG_AX); + } + if (isneg) + insn->code = insn->code == code_add ? + code_sub : code_add; + *patch++ = *insn; + if (issrc && isneg) + *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); + cnt = patch - insn_buf; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (insn->code != (BPF_JMP | BPF_CALL)) continue; if (insn->src_reg == BPF_PSEUDO_CALL) diff --git a/kernel/compat.c b/kernel/compat.c index 089d00d0da9c..f01affa17e22 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -95,28 +95,28 @@ int compat_put_timex(struct compat_timex __user *utp, const struct timex *txc) static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv) { - return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) || + return (!access_ok(ctv, sizeof(*ctv)) || __get_user(tv->tv_sec, &ctv->tv_sec) || __get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; } static int __compat_put_timeval(const struct timeval *tv, struct old_timeval32 __user *ctv) { - return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) || + return (!access_ok(ctv, sizeof(*ctv)) || __put_user(tv->tv_sec, &ctv->tv_sec) || __put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; } static int __compat_get_timespec(struct timespec *ts, const struct old_timespec32 __user *cts) { - return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) || + return (!access_ok(cts, sizeof(*cts)) || __get_user(ts->tv_sec, &cts->tv_sec) || __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; } static int __compat_put_timespec(const struct timespec *ts, struct old_timespec32 __user *cts) { - return (!access_ok(VERIFY_WRITE, cts, sizeof(*cts)) || + return (!access_ok(cts, sizeof(*cts)) || __put_user(ts->tv_sec, &cts->tv_sec) || __put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; } @@ -335,7 +335,7 @@ int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event) { memset(event, 0, sizeof(*event)); - return (!access_ok(VERIFY_READ, u_event, sizeof(*u_event)) || + return (!access_ok(u_event, sizeof(*u_event)) || __get_user(event->sigev_value.sival_int, &u_event->sigev_value.sival_int) || __get_user(event->sigev_signo, &u_event->sigev_signo) || @@ -354,10 +354,9 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG); nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size); - if (!access_ok(VERIFY_READ, umask, bitmap_size / 8)) + if (!user_access_begin(umask, bitmap_size / 8)) return -EFAULT; - user_access_begin(); while (nr_compat_longs > 1) { compat_ulong_t l1, l2; unsafe_get_user(l1, umask++, Efault); @@ -384,10 +383,9 @@ long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG); nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size); - if (!access_ok(VERIFY_WRITE, umask, bitmap_size / 8)) + if (!user_access_begin(umask, bitmap_size / 8)) return -EFAULT; - user_access_begin(); while (nr_compat_longs > 1) { unsigned long m = *mask++; unsafe_put_user((compat_ulong_t)m, umask++, Efault); @@ -438,7 +436,7 @@ void __user *compat_alloc_user_space(unsigned long len) ptr = arch_compat_alloc_user_space(len); - if (unlikely(!access_ok(VERIFY_WRITE, ptr, len))) + if (unlikely(!access_ok(ptr, len))) return NULL; return ptr; diff --git a/kernel/events/core.c b/kernel/events/core.c index 67ecac337374..3cd13a30f732 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10135,7 +10135,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, u32 size; int ret; - if (!access_ok(VERIFY_WRITE, uattr, PERF_ATTR_SIZE_VER0)) + if (!access_ok(uattr, PERF_ATTR_SIZE_VER0)) return -EFAULT; /* diff --git a/kernel/exit.c b/kernel/exit.c index 0e21e6d21f35..2d14979577ee 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1604,10 +1604,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, if (!infop) return err; - if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + if (!user_access_begin(infop, sizeof(*infop))) return -EFAULT; - user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); @@ -1732,10 +1731,9 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (!infop) return err; - if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + if (!user_access_begin(infop, sizeof(*infop))) return -EFAULT; - user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); diff --git a/kernel/futex.c b/kernel/futex.c index 054105854e0e..be3bff2315ff 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -481,13 +481,18 @@ static void drop_futex_key_refs(union futex_key *key) } } +enum futex_access { + FUTEX_READ, + FUTEX_WRITE +}; + /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED * @key: address where result is stored. - * @rw: mapping needs to be read/write (values: VERIFY_READ, - * VERIFY_WRITE) + * @rw: mapping needs to be read/write (values: FUTEX_READ, + * FUTEX_WRITE) * * Return: a negative error code or 0 * @@ -500,7 +505,7 @@ static void drop_futex_key_refs(union futex_key *key) * lock_page() might sleep, the caller should not hold a spinlock. */ static int -get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) +get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_access rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; @@ -516,7 +521,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) return -EINVAL; address -= key->both.offset; - if (unlikely(!access_ok(rw, uaddr, sizeof(u32)))) + if (unlikely(!access_ok(uaddr, sizeof(u32)))) return -EFAULT; if (unlikely(should_fail_futex(fshared))) @@ -546,7 +551,7 @@ again: * If write access is not required (eg. FUTEX_WAIT), try * and get read-only access. */ - if (err == -EFAULT && rw == VERIFY_READ) { + if (err == -EFAULT && rw == FUTEX_READ) { err = get_user_pages_fast(address, 1, 0, &page); ro = 1; } @@ -1583,7 +1588,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) if (!bitset) return -EINVAL; - ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_READ); + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, FUTEX_READ); if (unlikely(ret != 0)) goto out; @@ -1642,7 +1647,7 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) oparg = 1 << oparg; } - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + if (!access_ok(uaddr, sizeof(u32))) return -EFAULT; ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr); @@ -1682,10 +1687,10 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, DEFINE_WAKE_Q(wake_q); retry: - ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ); + ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) goto out_put_key1; @@ -1961,11 +1966,11 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, } retry: - ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ); + ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ); if (unlikely(ret != 0)) goto out; ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, - requeue_pi ? VERIFY_WRITE : VERIFY_READ); + requeue_pi ? FUTEX_WRITE : FUTEX_READ); if (unlikely(ret != 0)) goto out_put_key1; @@ -2634,7 +2639,7 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, * while the syscall executes. */ retry: - ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key, VERIFY_READ); + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key, FUTEX_READ); if (unlikely(ret != 0)) return ret; @@ -2793,7 +2798,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, } retry: - ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, VERIFY_WRITE); + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, FUTEX_WRITE); if (unlikely(ret != 0)) goto out; @@ -2972,7 +2977,7 @@ retry: if ((uval & FUTEX_TID_MASK) != vpid) return -EPERM; - ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE); + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, FUTEX_WRITE); if (ret) return ret; @@ -3199,7 +3204,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, */ rt_mutex_init_waiter(&rt_waiter); - ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) goto out; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 1306fe0c1dc6..d3d170374ceb 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1466,7 +1466,7 @@ int do_syslog(int type, char __user *buf, int len, int source) return -EINVAL; if (!len) return 0; - if (!access_ok(VERIFY_WRITE, buf, len)) + if (!access_ok(buf, len)) return -EFAULT; error = wait_event_interruptible(log_wait, syslog_seq != log_next_seq); @@ -1484,7 +1484,7 @@ int do_syslog(int type, char __user *buf, int len, int source) return -EINVAL; if (!len) return 0; - if (!access_ok(VERIFY_WRITE, buf, len)) + if (!access_ok(buf, len)) return -EFAULT; error = syslog_print_all(buf, len, clear); break; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index c2cee9db5204..771e93f9c43f 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -1073,7 +1073,7 @@ int ptrace_request(struct task_struct *child, long request, struct iovec kiov; struct iovec __user *uiov = datavp; - if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov))) + if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(kiov.iov_base, &uiov->iov_base) || @@ -1229,7 +1229,7 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_uptr_t ptr; compat_size_t len; - if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov))) + if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(ptr, &uiov->iov_base) || diff --git a/kernel/rseq.c b/kernel/rseq.c index c6242d8594dc..25e9a7b60eba 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -267,7 +267,7 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) if (unlikely(t->flags & PF_EXITING)) return; - if (unlikely(!access_ok(VERIFY_WRITE, t->rseq, sizeof(*t->rseq)))) + if (unlikely(!access_ok(t->rseq, sizeof(*t->rseq)))) goto error; ret = rseq_ip_fixup(regs); if (unlikely(ret < 0)) @@ -295,7 +295,7 @@ void rseq_syscall(struct pt_regs *regs) if (!t->rseq) return; - if (!access_ok(VERIFY_READ, t->rseq, sizeof(*t->rseq)) || + if (!access_ok(t->rseq, sizeof(*t->rseq)) || rseq_get_rseq_cs(t, &rseq_cs) || in_rseq_cs(ip, &rseq_cs)) force_sig(SIGSEGV, t); } @@ -351,7 +351,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, if (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) || rseq_len != sizeof(*rseq)) return -EINVAL; - if (!access_ok(VERIFY_WRITE, rseq, rseq_len)) + if (!access_ok(rseq, rseq_len)) return -EFAULT; current->rseq = rseq; current->rseq_len = rseq_len; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 17a954c9e153..223f78d5c111 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4450,7 +4450,7 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a u32 size; int ret; - if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0)) + if (!access_ok(uattr, SCHED_ATTR_SIZE_VER0)) return -EFAULT; /* Zero the full structure, so that a short copy will be nice: */ @@ -4650,7 +4650,7 @@ static int sched_read_attr(struct sched_attr __user *uattr, { int ret; - if (!access_ok(VERIFY_WRITE, uattr, usize)) + if (!access_ok(uattr, usize)) return -EFAULT; /* diff --git a/kernel/signal.c b/kernel/signal.c index 53e07d97ffe0..e1d7ad8e6ab1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3997,7 +3997,7 @@ SYSCALL_DEFINE3(sigaction, int, sig, if (act) { old_sigset_t mask; - if (!access_ok(VERIFY_READ, act, sizeof(*act)) || + if (!access_ok(act, sizeof(*act)) || __get_user(new_ka.sa.sa_handler, &act->sa_handler) || __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) || __get_user(new_ka.sa.sa_flags, &act->sa_flags) || @@ -4012,7 +4012,7 @@ SYSCALL_DEFINE3(sigaction, int, sig, ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { - if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || + if (!access_ok(oact, sizeof(*oact)) || __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) || __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || @@ -4034,7 +4034,7 @@ COMPAT_SYSCALL_DEFINE3(sigaction, int, sig, compat_uptr_t handler, restorer; if (act) { - if (!access_ok(VERIFY_READ, act, sizeof(*act)) || + if (!access_ok(act, sizeof(*act)) || __get_user(handler, &act->sa_handler) || __get_user(restorer, &act->sa_restorer) || __get_user(new_ka.sa.sa_flags, &act->sa_flags) || @@ -4052,7 +4052,7 @@ COMPAT_SYSCALL_DEFINE3(sigaction, int, sig, ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { - if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || + if (!access_ok(oact, sizeof(*oact)) || __put_user(ptr_to_compat(old_ka.sa.sa_handler), &oact->sa_handler) || __put_user(ptr_to_compat(old_ka.sa.sa_restorer), diff --git a/kernel/sys.c b/kernel/sys.c index 64b5a230f38d..a48cbf1414b8 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2627,7 +2627,7 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info) s.freehigh >>= bitcount; } - if (!access_ok(VERIFY_WRITE, info, sizeof(struct compat_sysinfo)) || + if (!access_ok(info, sizeof(struct compat_sysinfo)) || __put_user(s.uptime, &info->uptime) || __put_user(s.loads[0], &info->loads[0]) || __put_user(s.loads[1], &info->loads[1]) || diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 9ddb6fddb4e0..8b068adb9da1 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -170,7 +170,7 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, return -EPERM; if (unlikely(uaccess_kernel())) return -EPERM; - if (!access_ok(VERIFY_WRITE, unsafe_ptr, size)) + if (!access_ok(unsafe_ptr, size)) return -EPERM; return probe_kernel_write(unsafe_ptr, src, size); |