diff options
Diffstat (limited to 'kernel/bpf/verifier.c')
| -rw-r--r-- | kernel/bpf/verifier.c | 2048 |
1 files changed, 1787 insertions, 261 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 98fa0be35370..a7b96bf0e654 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -11,10 +11,12 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. */ +#include <uapi/linux/btf.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <net/netlink.h> @@ -24,6 +26,7 @@ #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/perf_event.h> +#include <linux/ctype.h> #include "disasm.h" @@ -175,6 +178,7 @@ struct bpf_verifier_stack_elem { #define BPF_COMPLEXITY_LIMIT_INSNS 131072 #define BPF_COMPLEXITY_LIMIT_STACK 1024 +#define BPF_COMPLEXITY_LIMIT_STATES 64 #define BPF_MAP_PTR_UNPRIV 1UL #define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \ @@ -209,10 +213,32 @@ struct bpf_call_arg_meta { s64 msize_smax_value; u64 msize_umax_value; int ptr_id; + int func_id; }; static DEFINE_MUTEX(bpf_verifier_lock); +static const struct bpf_line_info * +find_linfo(const struct bpf_verifier_env *env, u32 insn_off) +{ + const struct bpf_line_info *linfo; + const struct bpf_prog *prog; + u32 i, nr_linfo; + + prog = env->prog; + nr_linfo = prog->aux->nr_linfo; + + if (!nr_linfo || insn_off >= prog->len) + return NULL; + + linfo = prog->aux->linfo; + for (i = 1; i < nr_linfo; i++) + if (insn_off < linfo[i].insn_off) + break; + + return &linfo[i - 1]; +} + void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args) { @@ -263,16 +289,61 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) va_end(args); } +static const char *ltrim(const char *s) +{ + while (isspace(*s)) + s++; + + return s; +} + +__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env, + u32 insn_off, + const char *prefix_fmt, ...) +{ + const struct bpf_line_info *linfo; + + if (!bpf_verifier_log_needed(&env->log)) + return; + + linfo = find_linfo(env, insn_off); + if (!linfo || linfo == env->prev_linfo) + return; + + if (prefix_fmt) { + va_list args; + + va_start(args, prefix_fmt); + bpf_verifier_vlog(&env->log, prefix_fmt, args); + va_end(args); + } + + verbose(env, "%s\n", + ltrim(btf_name_by_offset(env->prog->aux->btf, + linfo->line_off))); + + env->prev_linfo = linfo; +} + static bool type_is_pkt_pointer(enum bpf_reg_type type) { return type == PTR_TO_PACKET || type == PTR_TO_PACKET_META; } +static bool type_is_sk_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET || + type == PTR_TO_SOCK_COMMON || + type == PTR_TO_TCP_SOCK; +} + static bool reg_type_may_be_null(enum bpf_reg_type type) { return type == PTR_TO_MAP_VALUE_OR_NULL || - type == PTR_TO_SOCKET_OR_NULL; + type == PTR_TO_SOCKET_OR_NULL || + type == PTR_TO_SOCK_COMMON_OR_NULL || + type == PTR_TO_TCP_SOCK_OR_NULL; } static bool type_is_refcounted(enum bpf_reg_type type) @@ -290,6 +361,12 @@ static bool reg_is_refcounted(const struct bpf_reg_state *reg) return type_is_refcounted(reg->type); } +static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) +{ + return reg->type == PTR_TO_MAP_VALUE && + map_value_has_spin_lock(reg->map_ptr); +} + static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg) { return type_is_refcounted_or_null(reg->type); @@ -309,6 +386,12 @@ static bool is_release_function(enum bpf_func_id func_id) return func_id == BPF_FUNC_sk_release; } +static bool is_acquire_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_sk_lookup_tcp || + func_id == BPF_FUNC_sk_lookup_udp; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -324,6 +407,10 @@ static const char * const reg_type_str[] = { [PTR_TO_FLOW_KEYS] = "flow_keys", [PTR_TO_SOCKET] = "sock", [PTR_TO_SOCKET_OR_NULL] = "sock_or_null", + [PTR_TO_SOCK_COMMON] = "sock_common", + [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null", + [PTR_TO_TCP_SOCK] = "tcp_sock", + [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", }; static char slot_type_char[] = { @@ -336,12 +423,14 @@ static char slot_type_char[] = { static void print_liveness(struct bpf_verifier_env *env, enum bpf_reg_liveness live) { - if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN)) + if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE)) verbose(env, "_"); if (live & REG_LIVE_READ) verbose(env, "r"); if (live & REG_LIVE_WRITTEN) verbose(env, "w"); + if (live & REG_LIVE_DONE) + verbose(env, "D"); } static struct bpf_func_state *func(struct bpf_verifier_env *env, @@ -548,13 +637,10 @@ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) } /* release function corresponding to acquire_reference_state(). Idempotent. */ -static int __release_reference_state(struct bpf_func_state *state, int ptr_id) +static int release_reference_state(struct bpf_func_state *state, int ptr_id) { int i, last_idx; - if (!ptr_id) - return -EFAULT; - last_idx = state->acquired_refs - 1; for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].id == ptr_id) { @@ -566,21 +652,7 @@ static int __release_reference_state(struct bpf_func_state *state, int ptr_id) return 0; } } - return -EFAULT; -} - -/* variation on the above for cases where we expect that there must be an - * outstanding reference for the specified ptr_id. - */ -static int release_reference_state(struct bpf_verifier_env *env, int ptr_id) -{ - struct bpf_func_state *state = cur_func(env); - int err; - - err = __release_reference_state(state, ptr_id); - if (WARN_ON_ONCE(err != 0)) - verbose(env, "verifier internal error: can't release reference\n"); - return err; + return -EINVAL; } static int transfer_reference_state(struct bpf_func_state *dst, @@ -647,7 +719,9 @@ 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; + dst_state->active_spin_lock = src->active_spin_lock; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -691,7 +765,8 @@ 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; @@ -709,6 +784,7 @@ 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; @@ -1029,7 +1105,7 @@ static int check_subprogs(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++) { u8 code = insn[i].code; - if (BPF_CLASS(code) != BPF_JMP) + if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) goto next; if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) goto next; @@ -1071,6 +1147,12 @@ static int mark_reg_read(struct bpf_verifier_env *env, /* if read wasn't screened by an earlier write ... */ if (writes && state->live & REG_LIVE_WRITTEN) break; + if (parent->live & REG_LIVE_DONE) { + verbose(env, "verifier BUG type %s var_off %lld off %d\n", + reg_type_str[parent->type], + parent->var_off.value, parent->off); + return -EFAULT; + } /* ... then we depend on parent's value */ parent->live |= REG_LIVE_READ; state = parent; @@ -1129,6 +1211,10 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case CONST_PTR_TO_MAP: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: + case PTR_TO_SOCK_COMMON: + case PTR_TO_SOCK_COMMON_OR_NULL: + case PTR_TO_TCP_SOCK: + case PTR_TO_TCP_SOCK_OR_NULL: return true; default: return false; @@ -1217,6 +1303,10 @@ static int check_stack_write(struct bpf_verifier_env *env, /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; + /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ + if (state->stack[spi].slot_type[0] == STACK_SPILL) + for (i = 0; i < BPF_REG_SIZE; i++) + state->stack[spi].slot_type[i] = STACK_MISC; /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon @@ -1234,6 +1324,7 @@ static int check_stack_write(struct bpf_verifier_env *env, register_is_null(&cur->regs[value_regno])) type = STACK_ZERO; + /* Mark slots affected by this stack write. */ for (i = 0; i < size; i++) state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type; @@ -1313,6 +1404,31 @@ 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) @@ -1344,13 +1460,17 @@ 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; @@ -1377,6 +1497,21 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, if (err) verbose(env, "R%d max value is outside of the array range\n", regno); + + if (map_value_has_spin_lock(reg->map_ptr)) { + u32 lock = reg->map_ptr->spin_lock_off; + + /* if any part of struct bpf_spin_lock can be touched by + * load/store reject this program. + * To check that [x1, x2) overlaps with [y1, y2) + * it is sufficient to check x1 < y2 && y1 < x2. + */ + if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) && + lock < reg->umax_value + off + size) { + verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n"); + return -EACCES; + } + } return err; } @@ -1387,21 +1522,24 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, enum bpf_access_type t) { switch (env->prog->type) { + /* Program types only with direct read access go here! */ case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_REUSEPORT: - /* dst_input() and dst_output() can't write for now */ + case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_CGROUP_SKB: if (t == BPF_WRITE) return false; /* fallthrough */ + + /* Program types with direct read + write access go here! */ case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: - case BPF_PROG_TYPE_FLOW_DISSECTOR: if (meta) return meta->pkt_access; @@ -1452,6 +1590,17 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, verbose(env, "R%d offset is outside of the packet\n", regno); return err; } + + /* __check_packet_access has made sure "off + size - 1" is within u16. + * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff, + * otherwise find_good_pkt_pointers would have refused to set range info + * that __check_packet_access would have rejected this pkt access. + * Therefore, "off + reg->umax_value + size - 1" won't overflow u32. + */ + env->prog->aux->max_pkt_offset = + max_t(u32, env->prog->aux->max_pkt_offset, + off + reg->umax_value + size - 1); + return err; } @@ -1497,12 +1646,14 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off, return 0; } -static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, - int size, enum bpf_access_type t) +static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, + u32 regno, int off, int size, + enum bpf_access_type t) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; - struct bpf_insn_access_aux info; + struct bpf_insn_access_aux info = {}; + bool valid; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", @@ -1510,13 +1661,31 @@ static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, return -EACCES; } - if (!bpf_sock_is_valid_access(off, size, t, &info)) { - verbose(env, "invalid bpf_sock access off=%d size=%d\n", - off, size); - return -EACCES; + switch (reg->type) { + case PTR_TO_SOCK_COMMON: + valid = bpf_sock_common_is_valid_access(off, size, t, &info); + break; + case PTR_TO_SOCKET: + valid = bpf_sock_is_valid_access(off, size, t, &info); + break; + case PTR_TO_TCP_SOCK: + valid = bpf_tcp_sock_is_valid_access(off, size, t, &info); + break; + default: + valid = false; } - return 0; + + if (valid) { + env->insn_aux_data[insn_idx].ctx_field_size = + info.ctx_field_size; + return 0; + } + + verbose(env, "R%d invalid %s access off=%d size=%d\n", + regno, reg_type_str[reg->type], off, size); + + return -EACCES; } static bool __is_pointer_value(bool allow_ptr_leaks, @@ -1542,8 +1711,14 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); - return reg->type == PTR_TO_CTX || - reg->type == PTR_TO_SOCKET; + return reg->type == PTR_TO_CTX; +} + +static bool is_sk_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = reg_state(env, regno); + + return type_is_sk_pointer(reg->type); } static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) @@ -1654,6 +1829,12 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, case PTR_TO_SOCKET: pointer_desc = "sock "; break; + case PTR_TO_SOCK_COMMON: + pointer_desc = "sock_common "; + break; + case PTR_TO_TCP_SOCK: + pointer_desc = "tcp_sock "; + break; default: break; } @@ -1857,33 +2038,22 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * PTR_TO_PACKET[_META,_END]. In the latter * case, we know the offset is zero. */ - if (reg_type == SCALAR_VALUE) + if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, value_regno); - else + } else { mark_reg_known_zero(env, regs, value_regno); + if (reg_type_may_be_null(reg_type)) + regs[value_regno].id = ++env->id_gen; + } regs[value_regno].type = reg_type; } } 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); @@ -1921,12 +2091,13 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_flow_keys_access(env, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); - } else if (reg->type == PTR_TO_SOCKET) { + } else if (type_is_sk_pointer(reg->type)) { if (t == BPF_WRITE) { - verbose(env, "cannot write into socket\n"); + verbose(env, "R%d cannot write into %s\n", + regno, reg_type_str[reg->type]); return -EACCES; } - err = check_sock_access(env, regno, off, size, t); + err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else { @@ -1970,7 +2141,8 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins if (is_ctx_reg(env, insn->dst_reg) || is_pkt_reg(env, insn->dst_reg) || - is_flow_key_reg(env, insn->dst_reg)) { + is_flow_key_reg(env, insn->dst_reg) || + is_sk_reg(env, insn->dst_reg)) { verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str[reg_state(env, insn->dst_reg)->type]); @@ -2086,6 +2258,91 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, } } +/* Implementation details: + * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL + * Two bpf_map_lookups (even with the same key) will have different reg->id. + * For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after + * value_or_null->value transition, since the verifier only cares about + * the range of access to valid map value pointer and doesn't care about actual + * address of the map element. + * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps + * reg->id > 0 after value_or_null->value transition. By doing so + * two bpf_map_lookups will be considered two different pointers that + * point to different bpf_spin_locks. + * The verifier allows taking only one bpf_spin_lock at a time to avoid + * dead-locks. + * Since only one bpf_spin_lock is allowed the checks are simpler than + * reg_is_refcounted() logic. The verifier needs to remember only + * one spin_lock instead of array of acquired_refs. + * cur_state->active_spin_lock remembers which map value element got locked + * and clears it after bpf_spin_unlock. + */ +static int process_spin_lock(struct bpf_verifier_env *env, int regno, + bool is_lock) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + struct bpf_verifier_state *cur = env->cur_state; + bool is_const = tnum_is_const(reg->var_off); + struct bpf_map *map = reg->map_ptr; + u64 val = reg->var_off.value; + + if (reg->type != PTR_TO_MAP_VALUE) { + verbose(env, "R%d is not a pointer to map_value\n", regno); + return -EINVAL; + } + if (!is_const) { + verbose(env, + "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n", + regno); + return -EINVAL; + } + if (!map->btf) { + verbose(env, + "map '%s' has to have BTF in order to use bpf_spin_lock\n", + map->name); + return -EINVAL; + } + if (!map_value_has_spin_lock(map)) { + if (map->spin_lock_off == -E2BIG) + verbose(env, + "map '%s' has more than one 'struct bpf_spin_lock'\n", + map->name); + else if (map->spin_lock_off == -ENOENT) + verbose(env, + "map '%s' doesn't have 'struct bpf_spin_lock'\n", + map->name); + else + verbose(env, + "map '%s' is not a struct type or bpf_spin_lock is mangled\n", + map->name); + return -EINVAL; + } + if (map->spin_lock_off != val + reg->off) { + verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n", + val + reg->off); + return -EINVAL; + } + if (is_lock) { + if (cur->active_spin_lock) { + verbose(env, + "Locking two bpf_spin_locks are not allowed\n"); + return -EINVAL; + } + cur->active_spin_lock = reg->id; + } else { + if (!cur->active_spin_lock) { + verbose(env, "bpf_spin_unlock without taking a lock\n"); + return -EINVAL; + } + if (cur->active_spin_lock != reg->id) { + verbose(env, "bpf_spin_unlock of different lock\n"); + return -EINVAL; + } + cur->active_spin_lock = 0; + } + return 0; +} + static bool arg_type_is_mem_ptr(enum bpf_arg_type type) { return type == ARG_PTR_TO_MEM || @@ -2152,6 +2409,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_ctx_reg(env, reg, regno); if (err < 0) return err; + } else if (arg_type == ARG_PTR_TO_SOCK_COMMON) { + expected_type = PTR_TO_SOCK_COMMON; + /* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */ + if (!type_is_sk_pointer(type)) + goto err_type; } else if (arg_type == ARG_PTR_TO_SOCKET) { expected_type = PTR_TO_SOCKET; if (type != expected_type) @@ -2162,6 +2424,17 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return -EFAULT; } meta->ptr_id = reg->id; + } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { + if (meta->func_id == BPF_FUNC_spin_lock) { + if (process_spin_lock(env, regno, true)) + return -EACCES; + } else if (meta->func_id == BPF_FUNC_spin_unlock) { + if (process_spin_lock(env, regno, false)) + return -EACCES; + } else { + verbose(env, "verifier internal error\n"); + return -EFAULT; + } } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be @@ -2555,7 +2828,7 @@ static int release_reference(struct bpf_verifier_env *env, for (i = 0; i <= vstate->curframe; i++) release_reg_references(env, vstate->frame[i], meta->ptr_id); - return release_reference_state(env, meta->ptr_id); + return release_reference_state(cur_func(env), meta->ptr_id); } static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, @@ -2781,6 +3054,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } + meta.func_id = func_id; /* check args */ err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta); if (err) @@ -2820,8 +3094,11 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } } else if (is_release_function(func_id)) { err = release_reference(env, &meta); - if (err) + if (err) { + verbose(env, "func %s#%d reference has not been acquired before\n", + func_id_name(func_id), func_id); return err; + } } regs = cur_regs(env); @@ -2849,10 +3126,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn regs[BPF_REG_0].type = NOT_INIT; } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL || fn->ret_type == RET_PTR_TO_MAP_VALUE) { - if (fn->ret_type == RET_PTR_TO_MAP_VALUE) - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; - else - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); /* remember map_ptr, so that check_map_access() @@ -2865,14 +3138,32 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; - regs[BPF_REG_0].id = ++env->id_gen; + if (fn->ret_type == RET_PTR_TO_MAP_VALUE) { + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; + if (map_value_has_spin_lock(meta.map_ptr)) + regs[BPF_REG_0].id = ++env->id_gen; + } else { + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; + regs[BPF_REG_0].id = ++env->id_gen; + } } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { - int id = acquire_reference_state(env, insn_idx); - if (id < 0) - return id; mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; - regs[BPF_REG_0].id = id; + if (is_acquire_function(func_id)) { + int id = acquire_reference_state(env, insn_idx); + + if (id < 0) + return id; + /* For release_reference() */ + regs[BPF_REG_0].id = id; + } else { + /* For mark_ptr_or_null_reg() */ + regs[BPF_REG_0].id = ++env->id_gen; + } + } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; + regs[BPF_REG_0].id = ++env->id_gen; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -2963,6 +3254,125 @@ 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 bool can_skip_alu_sanitation(const struct bpf_verifier_env *env, + const struct bpf_insn *insn) +{ + return env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K; +} + +static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux, + u32 alu_state, u32 alu_limit) +{ + /* If we arrived here from different branches with different + * state or 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; + return 0; +} + +static int sanitize_val_alu(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + struct bpf_insn_aux_data *aux = cur_aux(env); + + if (can_skip_alu_sanitation(env, insn)) + return 0; + + return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0); +} + +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 (can_skip_alu_sanitation(env, insn)) + 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 (update_alu_sanitation_state(aux, alu_state, alu_limit)) + return -EACCES; +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 @@ -2981,8 +3391,9 @@ 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]; @@ -3012,9 +3423,20 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, case PTR_TO_PACKET_END: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: + case PTR_TO_SOCK_COMMON: + case PTR_TO_SOCK_COMMON_OR_NULL: + case PTR_TO_TCP_SOCK: + case PTR_TO_TCP_SOCK_OR_NULL: 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; } @@ -3031,6 +3453,11 @@ 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 */ @@ -3043,7 +3470,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->umax_value = umax_ptr; dst_reg->var_off = ptr_reg->var_off; dst_reg->off = ptr_reg->off + smin_val; - dst_reg->range = ptr_reg->range; + dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. Note that off_reg->off @@ -3073,13 +3500,19 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; + dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ - dst_reg->range = 0; + dst_reg->raw = 0; } 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", @@ -3105,7 +3538,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->var_off = ptr_reg->var_off; dst_reg->id = ptr_reg->id; dst_reg->off = ptr_reg->off - smin_val; - dst_reg->range = ptr_reg->range; + dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. If the subtrahend is known @@ -3131,11 +3564,12 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; + dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) - dst_reg->range = 0; + dst_reg->raw = 0; } break; case BPF_AND: @@ -3158,6 +3592,25 @@ 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; } @@ -3176,6 +3629,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, s64 smin_val, smax_val; u64 umin_val, umax_val; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; + u32 dst = insn->dst_reg; + int ret; if (insn_bitness == 32) { /* Relevant for 32-bit RSH: Information can propagate towards @@ -3210,6 +3665,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, switch (opcode) { case BPF_ADD: + ret = sanitize_val_alu(env, insn); + if (ret < 0) { + verbose(env, "R%d tried to add from different pointers or scalars\n", dst); + return ret; + } if (signed_add_overflows(dst_reg->smin_value, smin_val) || signed_add_overflows(dst_reg->smax_value, smax_val)) { dst_reg->smin_value = S64_MIN; @@ -3229,6 +3689,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: + ret = sanitize_val_alu(env, insn); + if (ret < 0) { + verbose(env, "R%d tried to sub from different pointers or scalars\n", dst); + return ret; + } if (signed_sub_overflows(dst_reg->smin_value, smax_val) || signed_sub_overflows(dst_reg->smax_value, smin_val)) { /* Overflow possible, we know nothing */ @@ -3564,12 +4029,15 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; if (BPF_SRC(insn->code) == BPF_X) { + struct bpf_reg_state *src_reg = regs + insn->src_reg; + struct bpf_reg_state *dst_reg = regs + insn->dst_reg; + if (BPF_CLASS(insn->code) == BPF_ALU64) { /* case: R1 = R2 * copy register state to dest reg */ - regs[insn->dst_reg] = regs[insn->src_reg]; - regs[insn->dst_reg].live |= REG_LIVE_WRITTEN; + *dst_reg = *src_reg; + dst_reg->live |= REG_LIVE_WRITTEN; } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { @@ -3577,9 +4045,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) "R%d partial copy of pointer\n", insn->src_reg); return -EACCES; + } else if (src_reg->type == SCALAR_VALUE) { + *dst_reg = *src_reg; + dst_reg->live |= REG_LIVE_WRITTEN; + } else { + mark_reg_unknown(env, regs, + insn->dst_reg); } - mark_reg_unknown(env, regs, insn->dst_reg); - coerce_reg_to_size(®s[insn->dst_reg], 4); + coerce_reg_to_size(dst_reg, 4); } } else { /* case: R = imm @@ -3630,11 +4103,6 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) { - verbose(env, "BPF_ARSH not supported for 32 bit ALU\n"); - return -EINVAL; - } - if ((opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; @@ -3745,6 +4213,147 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, } } +/* compute branch direction of the expression "if (reg opcode val) goto target;" + * and return: + * 1 - branch will be taken and "goto target" will be executed + * 0 - branch will not be taken and fall-through to next insn + * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10] + */ +static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, + bool is_jmp32) +{ + struct bpf_reg_state reg_lo; + s64 sval; + + if (__is_pointer_value(false, reg)) + return -1; + + if (is_jmp32) { + reg_lo = *reg; + reg = ®_lo; + /* For JMP32, only low 32 bits are compared, coerce_reg_to_size + * could truncate high bits and update umin/umax according to + * information of low bits. + */ + coerce_reg_to_size(reg, 4); + /* smin/smax need special handling. For example, after coerce, + * if smin_value is 0x00000000ffffffffLL, the value is -1 when + * used as operand to JMP32. It is a negative number from s32's + * point of view, while it is a positive number when seen as + * s64. The smin/smax are kept as s64, therefore, when used with + * JMP32, they need to be transformed into s32, then sign + * extended back to s64. + * + * Also, smin/smax were copied from umin/umax. If umin/umax has + * different sign bit, then min/max relationship doesn't + * maintain after casting into s32, for this case, set smin/smax + * to safest range. + */ + if ((reg->umax_value ^ reg->umin_value) & + (1ULL << 31)) { + reg->smin_value = S32_MIN; + reg->smax_value = S32_MAX; + } + reg->smin_value = (s64)(s32)reg->smin_value; + reg->smax_value = (s64)(s32)reg->smax_value; + + val = (u32)val; + sval = (s64)(s32)val; + } else { + sval = (s64)val; + } + + switch (opcode) { + case BPF_JEQ: + if (tnum_is_const(reg->var_off)) + return !!tnum_equals_const(reg->var_off, val); + break; + case BPF_JNE: + if (tnum_is_const(reg->var_off)) + return !tnum_equals_const(reg->var_off, val); + break; + case BPF_JSET: + if ((~reg->var_off.mask & reg->var_off.value) & val) + return 1; + if (!((reg->var_off.mask | reg->var_off.value) & val)) + return 0; + break; + case BPF_JGT: + if (reg->umin_value > val) + return 1; + else if (reg->umax_value <= val) + return 0; + break; + case BPF_JSGT: + if (reg->smin_value > sval) + return 1; + else if (reg->smax_value < sval) + return 0; + break; + case BPF_JLT: + if (reg->umax_value < val) + return 1; + else if (reg->umin_value >= val) + return 0; + break; + case BPF_JSLT: + if (reg->smax_value < sval) + return 1; + else if (reg->smin_value >= sval) + return 0; + break; + case BPF_JGE: + if (reg->umin_value >= val) + return 1; + else if (reg->umax_value < val) + return 0; + break; + case BPF_JSGE: + if (reg->smin_value >= sval) + return 1; + else if (reg->smax_value < sval) + return 0; + break; + case BPF_JLE: + if (reg->umax_value <= val) + return 1; + else if (reg->umin_value > val) + return 0; + break; + case BPF_JSLE: + if (reg->smax_value <= sval) + return 1; + else if (reg->smin_value > sval) + return 0; + break; + } + + return -1; +} + +/* Generate min value of the high 32-bit from TNUM info. */ +static u64 gen_hi_min(struct tnum var) +{ + return var.value & ~0xffffffffULL; +} + +/* Generate max value of the high 32-bit from TNUM info. */ +static u64 gen_hi_max(struct tnum var) +{ + return (var.value | var.mask) & ~0xffffffffULL; +} + +/* Return true if VAL is compared with a s64 sign extended from s32, and they + * are with the same signedness. + */ +static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg) +{ + return ((s32)sval >= 0 && + reg->smin_value >= 0 && reg->smax_value <= S32_MAX) || + ((s32)sval < 0 && + reg->smax_value <= 0 && reg->smin_value >= S32_MIN); +} + /* Adjusts the register min/max values in the case that the dst_reg is the * variable register that we are working on, and src_reg is a constant or we're * simply doing a BPF_K check. @@ -3752,8 +4361,10 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, */ static void reg_set_min_max(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, - u8 opcode) + u8 opcode, bool is_jmp32) { + s64 sval; + /* If the dst_reg is a pointer, we can't learn anything about its * variable offset from the compare (unless src_reg were a pointer into * the same object, but we don't bother with that. @@ -3763,51 +4374,93 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, if (__is_pointer_value(false, false_reg)) return; + val = is_jmp32 ? (u32)val : val; + sval = is_jmp32 ? (s64)(s32)val : (s64)val; + switch (opcode) { case BPF_JEQ: - /* If this is false then we know nothing Jon Snow, but if it is - * true then we know for sure. - */ - __mark_reg_known(true_reg, val); - break; case BPF_JNE: - /* If this is true we know nothing Jon Snow, but if it is false - * we know the value for sure; + { + struct bpf_reg_state *reg = + opcode == BPF_JEQ ? true_reg : false_reg; + + /* For BPF_JEQ, if this is false we know nothing Jon Snow, but + * if it is true we know the value for sure. Likewise for + * BPF_JNE. */ - __mark_reg_known(false_reg, val); - break; - case BPF_JGT: - false_reg->umax_value = min(false_reg->umax_value, val); - true_reg->umin_value = max(true_reg->umin_value, val + 1); - break; - case BPF_JSGT: - false_reg->smax_value = min_t(s64, false_reg->smax_value, val); - true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1); - break; - case BPF_JLT: - false_reg->umin_value = max(false_reg->umin_value, val); - true_reg->umax_value = min(true_reg->umax_value, val - 1); + if (is_jmp32) { + u64 old_v = reg->var_off.value; + u64 hi_mask = ~0xffffffffULL; + + reg->var_off.value = (old_v & hi_mask) | val; + reg->var_off.mask &= hi_mask; + } else { + __mark_reg_known(reg, val); + } break; - case BPF_JSLT: - false_reg->smin_value = max_t(s64, false_reg->smin_value, val); - true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1); + } + case BPF_JSET: + false_reg->var_off = tnum_and(false_reg->var_off, + tnum_const(~val)); + if (is_power_of_2(val)) + true_reg->var_off = tnum_or(true_reg->var_off, + tnum_const(val)); break; case BPF_JGE: - false_reg->umax_value = min(false_reg->umax_value, val - 1); - true_reg->umin_value = max(true_reg->umin_value, val); + case BPF_JGT: + { + u64 false_umax = opcode == BPF_JGT ? val : val - 1; + u64 true_umin = opcode == BPF_JGT ? val + 1 : val; + + if (is_jmp32) { + false_umax += gen_hi_max(false_reg->var_off); + true_umin += gen_hi_min(true_reg->var_off); + } + false_reg->umax_value = min(false_reg->umax_value, false_umax); + true_reg->umin_value = max(true_reg->umin_value, true_umin); break; + } case BPF_JSGE: - false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1); - true_reg->smin_value = max_t(s64, true_reg->smin_value, val); + case BPF_JSGT: + { + s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1; + s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval; + + /* If the full s64 was not sign-extended from s32 then don't + * deduct further info. + */ + if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) + break; + false_reg->smax_value = min(false_reg->smax_value, false_smax); + true_reg->smin_value = max(true_reg->smin_value, true_smin); break; + } case BPF_JLE: - false_reg->umin_value = max(false_reg->umin_value, val + 1); - true_reg->umax_value = min(true_reg->umax_value, val); + case BPF_JLT: + { + u64 false_umin = opcode == BPF_JLT ? val : val + 1; + u64 true_umax = opcode == BPF_JLT ? val - 1 : val; + + if (is_jmp32) { + false_umin += gen_hi_min(false_reg->var_off); + true_umax += gen_hi_max(true_reg->var_off); + } + false_reg->umin_value = max(false_reg->umin_value, false_umin); + true_reg->umax_value = min(true_reg->umax_value, true_umax); break; + } case BPF_JSLE: - false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1); - true_reg->smax_value = min_t(s64, true_reg->smax_value, val); + case BPF_JSLT: + { + s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1; + s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval; + + if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) + break; + false_reg->smin_value = max(false_reg->smin_value, false_smin); + true_reg->smax_value = min(true_reg->smax_value, true_smax); break; + } default: break; } @@ -3830,56 +4483,93 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, */ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, - u8 opcode) + u8 opcode, bool is_jmp32) { + s64 sval; + if (__is_pointer_value(false, false_reg)) return; + val = is_jmp32 ? (u32)val : val; + sval = is_jmp32 ? (s64)(s32)val : (s64)val; + switch (opcode) { case BPF_JEQ: - /* If this is false then we know nothing Jon Snow, but if it is - * true then we know for sure. - */ - __mark_reg_known(true_reg, val); - break; case BPF_JNE: - /* If this is true we know nothing Jon Snow, but if it is false - * we know the value for sure; - */ - __mark_reg_known(false_reg, val); - break; - case BPF_JGT: - true_reg->umax_value = min(true_reg->umax_value, val - 1); - false_reg->umin_value = max(false_reg->umin_value, val); - break; - case BPF_JSGT: - true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1); - false_reg->smin_value = max_t(s64, false_reg->smin_value, val); - break; - case BPF_JLT: - true_reg->umin_value = max(true_reg->umin_value, val + 1); - false_reg->umax_value = min(false_reg->umax_value, val); + { + struct bpf_reg_state *reg = + opcode == BPF_JEQ ? true_reg : false_reg; + + if (is_jmp32) { + u64 old_v = reg->var_off.value; + u64 hi_mask = ~0xffffffffULL; + + reg->var_off.value = (old_v & hi_mask) | val; + reg->var_off.mask &= hi_mask; + } else { + __mark_reg_known(reg, val); + } break; - case BPF_JSLT: - true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1); - false_reg->smax_value = min_t(s64, false_reg->smax_value, val); + } + case BPF_JSET: + false_reg->var_off = tnum_and(false_reg->var_off, + tnum_const(~val)); + if (is_power_of_2(val)) + true_reg->var_off = tnum_or(true_reg->var_off, + tnum_const(val)); break; case BPF_JGE: - true_reg->umax_value = min(true_reg->umax_value, val); - false_reg->umin_value = max(false_reg->umin_value, val + 1); + case BPF_JGT: + { + u64 false_umin = opcode == BPF_JGT ? val : val + 1; + u64 true_umax = opcode == BPF_JGT ? val - 1 : val; + + if (is_jmp32) { + false_umin += gen_hi_min(false_reg->var_off); + true_umax += gen_hi_max(true_reg->var_off); + } + false_reg->umin_value = max(false_reg->umin_value, false_umin); + true_reg->umax_value = min(true_reg->umax_value, true_umax); break; + } case BPF_JSGE: - true_reg->smax_value = min_t(s64, true_reg->smax_value, val); - false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1); + case BPF_JSGT: + { + s64 false_smin = opcode == BPF_JSGT ? sval : sval + 1; + s64 true_smax = opcode == BPF_JSGT ? sval - 1 : sval; + + if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) + break; + false_reg->smin_value = max(false_reg->smin_value, false_smin); + true_reg->smax_value = min(true_reg->smax_value, true_smax); break; + } case BPF_JLE: - true_reg->umin_value = max(true_reg->umin_value, val); - false_reg->umax_value = min(false_reg->umax_value, val - 1); + case BPF_JLT: + { + u64 false_umax = opcode == BPF_JLT ? val : val - 1; + u64 true_umin = opcode == BPF_JLT ? val + 1 : val; + + if (is_jmp32) { + false_umax += gen_hi_max(false_reg->var_off); + true_umin += gen_hi_min(true_reg->var_off); + } + false_reg->umax_value = min(false_reg->umax_value, false_umax); + true_reg->umin_value = max(true_reg->umin_value, true_umin); break; + } case BPF_JSLE: - true_reg->smin_value = max_t(s64, true_reg->smin_value, val); - false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1); + case BPF_JSLT: + { + s64 false_smax = opcode == BPF_JSLT ? sval : sval - 1; + s64 true_smin = opcode == BPF_JSLT ? sval + 1 : sval; + + if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) + break; + false_reg->smax_value = min(false_reg->smax_value, false_smax); + true_reg->smin_value = max(true_reg->smin_value, true_smin); break; + } default: break; } @@ -3970,8 +4660,13 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, } } else if (reg->type == PTR_TO_SOCKET_OR_NULL) { reg->type = PTR_TO_SOCKET; + } else if (reg->type == PTR_TO_SOCK_COMMON_OR_NULL) { + reg->type = PTR_TO_SOCK_COMMON; + } else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) { + reg->type = PTR_TO_TCP_SOCK; } - if (is_null || !reg_is_refcounted(reg)) { + if (is_null || !(reg_is_refcounted(reg) || + reg_may_point_to_spin_lock(reg))) { /* We don't need id from this point onwards anymore, * thus we should better reset it, so that state * pruning has chances to take effect. @@ -3993,7 +4688,7 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, int i, j; if (reg_is_refcounted_or_null(®s[regno]) && is_null) - __release_reference_state(state, id); + release_reference_state(state, id); for (i = 0; i < MAX_BPF_REG; i++) mark_ptr_or_null_reg(state, ®s[i], id, is_null); @@ -4017,6 +4712,10 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, if (BPF_SRC(insn->code) != BPF_X) return false; + /* Pointers are always 64-bit. */ + if (BPF_CLASS(insn->code) == BPF_JMP32) + return false; + switch (BPF_OP(insn->code)) { case BPF_JGT: if ((dst_reg->type == PTR_TO_PACKET && @@ -4109,16 +4808,18 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs; u8 opcode = BPF_OP(insn->code); + bool is_jmp32; int err; - if (opcode > BPF_JSLE) { - verbose(env, "invalid BPF_JMP opcode %x\n", opcode); + /* Only conditional jumps are expected to reach here. */ + if (opcode == BPF_JA || opcode > BPF_JSLE) { + verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode); return -EINVAL; } if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0) { - verbose(env, "BPF_JMP uses reserved fields\n"); + verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } @@ -4134,7 +4835,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } } else { if (insn->src_reg != BPF_REG_0) { - verbose(env, "BPF_JMP uses reserved fields\n"); + verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } } @@ -4145,29 +4846,26 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return err; dst_reg = ®s[insn->dst_reg]; + is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; - /* detect if R == 0 where R was initialized to zero earlier */ - if (BPF_SRC(insn->code) == BPF_K && - (opcode == BPF_JEQ || opcode == BPF_JNE) && - dst_reg->type == SCALAR_VALUE && - tnum_is_const(dst_reg->var_off)) { - if ((opcode == BPF_JEQ && dst_reg->var_off.value == insn->imm) || - (opcode == BPF_JNE && dst_reg->var_off.value != insn->imm)) { - /* if (imm == imm) goto pc+off; - * only follow the goto, ignore fall-through - */ + if (BPF_SRC(insn->code) == BPF_K) { + int pred = is_branch_taken(dst_reg, insn->imm, opcode, + is_jmp32); + + if (pred == 1) { + /* only follow the goto, ignore fall-through */ *insn_idx += insn->off; return 0; - } else { - /* if (imm != imm) goto pc+off; - * only follow fall-through branch, since + } else if (pred == 0) { + /* only follow fall-through branch, since * that's where the program will go */ return 0; } } - 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; @@ -4180,30 +4878,51 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, * comparable. */ if (BPF_SRC(insn->code) == BPF_X) { + struct bpf_reg_state *src_reg = ®s[insn->src_reg]; + struct bpf_reg_state lo_reg0 = *dst_reg; + struct bpf_reg_state lo_reg1 = *src_reg; + struct bpf_reg_state *src_lo, *dst_lo; + + dst_lo = &lo_reg0; + src_lo = &lo_reg1; + coerce_reg_to_size(dst_lo, 4); + coerce_reg_to_size(src_lo, 4); + if (dst_reg->type == SCALAR_VALUE && - regs[insn->src_reg].type == SCALAR_VALUE) { - if (tnum_is_const(regs[insn->src_reg].var_off)) + src_reg->type == SCALAR_VALUE) { + if (tnum_is_const(src_reg->var_off) || + (is_jmp32 && tnum_is_const(src_lo->var_off))) reg_set_min_max(&other_branch_regs[insn->dst_reg], - dst_reg, regs[insn->src_reg].var_off.value, - opcode); - else if (tnum_is_const(dst_reg->var_off)) + dst_reg, + is_jmp32 + ? src_lo->var_off.value + : src_reg->var_off.value, + opcode, is_jmp32); + else if (tnum_is_const(dst_reg->var_off) || + (is_jmp32 && tnum_is_const(dst_lo->var_off))) reg_set_min_max_inv(&other_branch_regs[insn->src_reg], - ®s[insn->src_reg], - dst_reg->var_off.value, opcode); - else if (opcode == BPF_JEQ || opcode == BPF_JNE) + src_reg, + is_jmp32 + ? dst_lo->var_off.value + : dst_reg->var_off.value, + opcode, is_jmp32); + else if (!is_jmp32 && + (opcode == BPF_JEQ || opcode == BPF_JNE)) /* Comparing for equality, we can combine knowledge */ reg_combine_min_max(&other_branch_regs[insn->src_reg], &other_branch_regs[insn->dst_reg], - ®s[insn->src_reg], - ®s[insn->dst_reg], opcode); + src_reg, dst_reg, opcode); } } else if (dst_reg->type == SCALAR_VALUE) { reg_set_min_max(&other_branch_regs[insn->dst_reg], - dst_reg, insn->imm, opcode); + dst_reg, insn->imm, opcode, is_jmp32); } - /* detect if R == 0 where R is returned from bpf_map_lookup_elem() */ - if (BPF_SRC(insn->code) == BPF_K && + /* detect if R == 0 where R is returned from bpf_map_lookup_elem(). + * NOTE: these optimizations below are related with pointer comparison + * which will never be JMP32. + */ + if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && reg_type_may_be_null(dst_reg->type)) { /* Mark all identical registers in each branch as either @@ -4345,6 +5064,11 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } + if (env->cur_state->active_spin_lock) { + verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); + return -EINVAL; + } + if (regs[BPF_REG_6].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); @@ -4471,6 +5195,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) return 0; if (w < 0 || w >= env->prog->len) { + verbose_linfo(env, t, "%d: ", t); verbose(env, "jump out of range from insn %d to %d\n", t, w); return -EINVAL; } @@ -4488,6 +5213,8 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) insn_stack[cur_stack++] = w; return 1; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { + verbose_linfo(env, t, "%d: ", t); + verbose_linfo(env, w, "%d: ", w); verbose(env, "back-edge from insn %d to %d\n", t, w); return -EINVAL; } else if (insn_state[w] == EXPLORED) { @@ -4510,10 +5237,6 @@ static int check_cfg(struct bpf_verifier_env *env) int ret = 0; int i, t; - ret = check_subprogs(env); - if (ret < 0) - return ret; - insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) return -ENOMEM; @@ -4533,7 +5256,8 @@ peek_stack: goto check_state; t = insn_stack[cur_stack - 1]; - if (BPF_CLASS(insns[t].code) == BPF_JMP) { + if (BPF_CLASS(insns[t].code) == BPF_JMP || + BPF_CLASS(insns[t].code) == BPF_JMP32) { u8 opcode = BPF_OP(insns[t].code); if (opcode == BPF_EXIT) { @@ -4622,6 +5346,278 @@ err_free: return ret; } +/* The minimum supported BTF func info size */ +#define MIN_BPF_FUNCINFO_SIZE 8 +#define MAX_FUNCINFO_REC_SIZE 252 + +static int check_btf_func(struct bpf_verifier_env *env, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + u32 i, nfuncs, urec_size, min_size; + u32 krec_size = sizeof(struct bpf_func_info); + struct bpf_func_info *krecord; + const struct btf_type *type; + struct bpf_prog *prog; + const struct btf *btf; + void __user *urecord; + u32 prev_offset = 0; + int ret = 0; + + nfuncs = attr->func_info_cnt; + if (!nfuncs) + return 0; + + if (nfuncs != env->subprog_cnt) { + verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); + return -EINVAL; + } + + urec_size = attr->func_info_rec_size; + if (urec_size < MIN_BPF_FUNCINFO_SIZE || + urec_size > MAX_FUNCINFO_REC_SIZE || + urec_size % sizeof(u32)) { + verbose(env, "invalid func info rec size %u\n", urec_size); + return -EINVAL; + } + + prog = env->prog; + btf = prog->aux->btf; + + urecord = u64_to_user_ptr(attr->func_info); + min_size = min_t(u32, krec_size, urec_size); + + krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); + if (!krecord) + return -ENOMEM; + + for (i = 0; i < nfuncs; i++) { + ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); + if (ret) { + if (ret == -E2BIG) { + verbose(env, "nonzero tailing record in func info"); + /* set the size kernel expects so loader can zero + * out the rest of the record. + */ + if (put_user(min_size, &uattr->func_info_rec_size)) + ret = -EFAULT; + } + goto err_free; + } + + if (copy_from_user(&krecord[i], urecord, min_size)) { + ret = -EFAULT; + goto err_free; + } + + /* check insn_off */ + if (i == 0) { + if (krecord[i].insn_off) { + verbose(env, + "nonzero insn_off %u for the first func info record", + krecord[i].insn_off); + ret = -EINVAL; + goto err_free; + } + } else if (krecord[i].insn_off <= prev_offset) { + verbose(env, + "same or smaller insn offset (%u) than previous func info record (%u)", + krecord[i].insn_off, prev_offset); + ret = -EINVAL; + goto err_free; + } + + if (env->subprog_info[i].start != krecord[i].insn_off) { + verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); + ret = -EINVAL; + goto err_free; + } + + /* check type_id */ + type = btf_type_by_id(btf, krecord[i].type_id); + if (!type || BTF_INFO_KIND(type->info) != BTF_KIND_FUNC) { + verbose(env, "invalid type id %d in func info", + krecord[i].type_id); + ret = -EINVAL; + goto err_free; + } + + prev_offset = krecord[i].insn_off; + urecord += urec_size; + } + + prog->aux->func_info = krecord; + prog->aux->func_info_cnt = nfuncs; + return 0; + +err_free: + kvfree(krecord); + return ret; +} + +static void adjust_btf_func(struct bpf_verifier_env *env) +{ + int i; + + if (!env->prog->aux->func_info) + return; + + for (i = 0; i < env->subprog_cnt; i++) + env->prog->aux->func_info[i].insn_off = env->subprog_info[i].start; +} + +#define MIN_BPF_LINEINFO_SIZE (offsetof(struct bpf_line_info, line_col) + \ + sizeof(((struct bpf_line_info *)(0))->line_col)) +#define MAX_LINEINFO_REC_SIZE MAX_FUNCINFO_REC_SIZE + +static int check_btf_line(struct bpf_verifier_env *env, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0; + struct bpf_subprog_info *sub; + struct bpf_line_info *linfo; + struct bpf_prog *prog; + const struct btf *btf; + void __user *ulinfo; + int err; + + nr_linfo = attr->line_info_cnt; + if (!nr_linfo) + return 0; + + rec_size = attr->line_info_rec_size; + if (rec_size < MIN_BPF_LINEINFO_SIZE || + rec_size > MAX_LINEINFO_REC_SIZE || + rec_size & (sizeof(u32) - 1)) + return -EINVAL; + + /* Need to zero it in case the userspace may + * pass in a smaller bpf_line_info object. + */ + linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info), + GFP_KERNEL | __GFP_NOWARN); + if (!linfo) + return -ENOMEM; + + prog = env->prog; + btf = prog->aux->btf; + + s = 0; + sub = env->subprog_info; + ulinfo = u64_to_user_ptr(attr->line_info); + expected_size = sizeof(struct bpf_line_info); + ncopy = min_t(u32, expected_size, rec_size); + for (i = 0; i < nr_linfo; i++) { + err = bpf_check_uarg_tail_zero(ulinfo, expected_size, rec_size); + if (err) { + if (err == -E2BIG) { + verbose(env, "nonzero tailing record in line_info"); + if (put_user(expected_size, + &uattr->line_info_rec_size)) + err = -EFAULT; + } + goto err_free; + } + + if (copy_from_user(&linfo[i], ulinfo, ncopy)) { + err = -EFAULT; + goto err_free; + } + + /* + * Check insn_off to ensure + * 1) strictly increasing AND + * 2) bounded by prog->len + * + * The linfo[0].insn_off == 0 check logically falls into + * the later "missing bpf_line_info for func..." case + * because the first linfo[0].insn_off must be the + * first sub also and the first sub must have + * subprog_info[0].start == 0. + */ + if ((i && linfo[i].insn_off <= prev_offset) || + linfo[i].insn_off >= prog->len) { + verbose(env, "Invalid line_info[%u].insn_off:%u (prev_offset:%u prog->len:%u)\n", + i, linfo[i].insn_off, prev_offset, + prog->len); + err = -EINVAL; + goto err_free; + } + + if (!prog->insnsi[linfo[i].insn_off].code) { + verbose(env, + "Invalid insn code at line_info[%u].insn_off\n", + i); + err = -EINVAL; + goto err_free; + } + + if (!btf_name_by_offset(btf, linfo[i].line_off) || + !btf_name_by_offset(btf, linfo[i].file_name_off)) { + verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i); + err = -EINVAL; + goto err_free; + } + + if (s != env->subprog_cnt) { + if (linfo[i].insn_off == sub[s].start) { + sub[s].linfo_idx = i; + s++; + } else if (sub[s].start < linfo[i].insn_off) { + verbose(env, "missing bpf_line_info for func#%u\n", s); + err = -EINVAL; + goto err_free; + } + } + + prev_offset = linfo[i].insn_off; + ulinfo += rec_size; + } + + if (s != env->subprog_cnt) { + verbose(env, "missing bpf_line_info for %u funcs starting from func#%u\n", + env->subprog_cnt - s, s); + err = -EINVAL; + goto err_free; + } + + prog->aux->linfo = linfo; + prog->aux->nr_linfo = nr_linfo; + + return 0; + +err_free: + kvfree(linfo); + return err; +} + +static int check_btf_info(struct bpf_verifier_env *env, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct btf *btf; + int err; + + if (!attr->func_info_cnt && !attr->line_info_cnt) + return 0; + + btf = btf_get_by_fd(attr->prog_btf_fd); + if (IS_ERR(btf)) + return PTR_ERR(btf); + env->prog->aux->btf = btf; + + err = check_btf_func(env, attr, uattr); + if (err) + return err; + + err = check_btf_line(env, attr, uattr); + if (err) + return err; + + return 0; +} + /* check %cur's range satisfies %old's */ static bool range_within(struct bpf_reg_state *old, struct bpf_reg_state *cur) @@ -4668,6 +5664,102 @@ static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap) return false; } +static void clean_func_state(struct bpf_verifier_env *env, + struct bpf_func_state *st) +{ + enum bpf_reg_liveness live; + int i, j; + + for (i = 0; i < BPF_REG_FP; i++) { + live = st->regs[i].live; + /* liveness must not touch this register anymore */ + st->regs[i].live |= REG_LIVE_DONE; + if (!(live & REG_LIVE_READ)) + /* since the register is unused, clear its state + * to make further comparison simpler + */ + __mark_reg_not_init(&st->regs[i]); + } + + for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { + live = st->stack[i].spilled_ptr.live; + /* liveness must not touch this stack slot anymore */ + st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; + if (!(live & REG_LIVE_READ)) { + __mark_reg_not_init(&st->stack[i].spilled_ptr); + for (j = 0; j < BPF_REG_SIZE; j++) + st->stack[i].slot_type[j] = STACK_INVALID; + } + } +} + +static void clean_verifier_state(struct bpf_verifier_env *env, + struct bpf_verifier_state *st) +{ + int i; + + if (st->frame[0]->regs[0].live & REG_LIVE_DONE) + /* all regs in this state in all frames were already marked */ + return; + + for (i = 0; i <= st->curframe; i++) + clean_func_state(env, st->frame[i]); +} + +/* the parentage chains form a tree. + * the verifier states are added to state lists at given insn and + * pushed into state stack for future exploration. + * when the verifier reaches bpf_exit insn some of the verifer states + * stored in the state lists have their final liveness state already, + * but a lot of states will get revised from liveness point of view when + * the verifier explores other branches. + * Example: + * 1: r0 = 1 + * 2: if r1 == 100 goto pc+1 + * 3: r0 = 2 + * 4: exit + * when the verifier reaches exit insn the register r0 in the state list of + * insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch + * of insn 2 and goes exploring further. At the insn 4 it will walk the + * parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ. + * + * Since the verifier pushes the branch states as it sees them while exploring + * the program the condition of walking the branch instruction for the second + * time means that all states below this branch were already explored and + * their final liveness markes are already propagated. + * Hence when the verifier completes the search of state list in is_state_visited() + * we can call this clean_live_states() function to mark all liveness states + * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state' + * will not be used. + * This function also clears the registers and stack for states that !READ + * to simplify state merging. + * + * Important note here that walking the same branch instruction in the callee + * doesn't meant that the states are DONE. The verifier has to compare + * the callsites + */ +static void clean_live_states(struct bpf_verifier_env *env, int insn, + struct bpf_verifier_state *cur) +{ + struct bpf_verifier_state_list *sl; + int i; + + sl = env->explored_states[insn]; + if (!sl) + return; + + while (sl != STATE_LIST_MARK) { + if (sl->state.curframe != cur->curframe) + goto next; + for (i = 0; i <= cur->curframe; i++) + if (sl->state.frame[i]->callsite != cur->frame[i]->callsite) + goto next; + clean_verifier_state(env, &sl->state); +next: + sl = sl->next; + } +} + /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, struct idpair *idmap) @@ -4713,8 +5805,11 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case PTR_TO_MAP_VALUE: /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. - * We don't care about the 'id' value, because nothing - * uses it for PTR_TO_MAP_VALUE (only for ..._OR_NULL) + * 'id' is not compared, since it's only used for maps with + * bpf_spin_lock inside map element and in such cases if + * the rest of the prog is valid for one map element then + * it's valid for all map elements regardless of the key + * used in bpf_map_lookup() */ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && range_within(rold, rcur) && @@ -4762,6 +5857,10 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case PTR_TO_FLOW_KEYS: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: + case PTR_TO_SOCK_COMMON: + case PTR_TO_SOCK_COMMON_OR_NULL: + case PTR_TO_TCP_SOCK: + case PTR_TO_TCP_SOCK_OR_NULL: /* Only valid matches are exact, which memcmp() above * would have accepted */ @@ -4781,12 +5880,6 @@ static bool stacksafe(struct bpf_func_state *old, { int i, spi; - /* if explored stack has more populated slots than current stack - * such stacks are not equivalent - */ - if (old->allocated_stack > cur->allocated_stack) - return false; - /* walk slots of the explored stack and ignore any additional * slots in the current stack, since explored(safe) state * didn't use them @@ -4794,12 +5887,21 @@ static bool stacksafe(struct bpf_func_state *old, for (i = 0; i < old->allocated_stack; i++) { spi = i / BPF_REG_SIZE; - if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) + if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) { + i += BPF_REG_SIZE - 1; /* explored state didn't use this */ continue; + } if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID) continue; + + /* explored stack has more populated slots than current stack + * and these slots were used + */ + if (i >= cur->allocated_stack) + return false; + /* if old state was safe with misc data in the stack * it will be safe with zero-initialized stack. * The opposite is not true @@ -4908,6 +6010,15 @@ 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; + + if (old->active_spin_lock != cur->active_spin_lock) + return false; + /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ @@ -4974,7 +6085,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl; struct bpf_verifier_state *cur = env->cur_state, *new; - int i, j, err; + int i, j, err, states_cnt = 0; sl = env->explored_states[insn_idx]; if (!sl) @@ -4983,6 +6094,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) */ return 0; + clean_live_states(env, insn_idx, cur); + while (sl != STATE_LIST_MARK) { if (states_equal(env, &sl->state, cur)) { /* reached equivalent register/stack state, @@ -5001,8 +6114,12 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return 1; } sl = sl->next; + states_cnt++; } + if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) + return 0; + /* there were no equivalent states, remember current one. * technically the current state is not proven to be safe yet, * but it will either reach outer most bpf_exit (which means it's safe) @@ -5024,9 +6141,16 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) } new_sl->next = env->explored_states[insn_idx]; env->explored_states[insn_idx] = new_sl; - /* connect new state to parentage chain */ - for (i = 0; i < BPF_REG_FP; i++) - cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i]; + /* connect new state to parentage chain. Current frame needs all + * registers connected. Only r6 - r9 of the callers are alive (pushed + * to the stack implicitly by JITs) so in callers' frames connect just + * r6 - r9 as an optimization. Callers will have r1 - r5 connected to + * the state of the call instruction (with WRITTEN set), and r0 comes + * from callee with its full parentage chain, anyway. + */ + for (j = 0; j <= cur->curframe; j++) + for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) + cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i]; /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark @@ -5057,6 +6181,10 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type) case PTR_TO_CTX: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: + case PTR_TO_SOCK_COMMON: + case PTR_TO_SOCK_COMMON_OR_NULL: + case PTR_TO_TCP_SOCK: + case PTR_TO_TCP_SOCK_OR_NULL: return false; default: return true; @@ -5087,14 +6215,16 @@ 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; + env->prev_linfo = NULL; + state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); 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); @@ -5105,19 +6235,19 @@ 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) { @@ -5127,30 +6257,37 @@ 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; } + if (signal_pending(current)) + return -EAGAIN; + if (need_resched()) cond_resched(); 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; } @@ -5161,19 +6298,20 @@ static int do_check(struct bpf_verifier_env *env) .private_data = env, }; - 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); @@ -5199,13 +6337,13 @@ 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 @@ -5230,10 +6368,10 @@ 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; } @@ -5249,13 +6387,13 @@ 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; @@ -5283,13 +6421,13 @@ 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; - } else if (class == BPF_JMP) { + } else if (class == BPF_JMP || class == BPF_JMP32) { u8 opcode = BPF_OP(insn->code); if (opcode == BPF_CALL) { @@ -5297,15 +6435,22 @@ static int do_check(struct bpf_verifier_env *env) insn->off != 0 || (insn->src_reg != BPF_REG_0 && insn->src_reg != BPF_PSEUDO_CALL) || - insn->dst_reg != BPF_REG_0) { + insn->dst_reg != BPF_REG_0 || + class == BPF_JMP32) { verbose(env, "BPF_CALL uses reserved fields\n"); return -EINVAL; } + if (env->cur_state->active_spin_lock && + (insn->src_reg == BPF_PSEUDO_CALL || + insn->imm != BPF_FUNC_spin_unlock)) { + verbose(env, "function calls are not allowed while holding a lock\n"); + return -EINVAL; + } 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; @@ -5313,27 +6458,34 @@ static int do_check(struct bpf_verifier_env *env) if (BPF_SRC(insn->code) != BPF_K || insn->imm != 0 || insn->src_reg != BPF_REG_0 || - insn->dst_reg != BPF_REG_0) { + insn->dst_reg != BPF_REG_0 || + class == BPF_JMP32) { verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } - insn_idx += insn->off + 1; + env->insn_idx += insn->off + 1; continue; } else if (opcode == BPF_EXIT) { if (BPF_SRC(insn->code) != BPF_K || insn->imm != 0 || insn->src_reg != BPF_REG_0 || - insn->dst_reg != BPF_REG_0) { + insn->dst_reg != BPF_REG_0 || + class == BPF_JMP32) { verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } + if (env->cur_state->active_spin_lock) { + verbose(env, "bpf_spin_unlock is missing\n"); + return -EINVAL; + } + 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; @@ -5363,7 +6515,8 @@ 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; @@ -5373,7 +6526,7 @@ 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; } @@ -5390,8 +6543,8 @@ 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; @@ -5401,7 +6554,7 @@ process_bpf_exit: return -EINVAL; } - insn_idx++; + env->insn_idx++; } verbose(env, "processed %d insns (limit %d), stack depth ", @@ -5426,6 +6579,19 @@ static int check_map_prealloc(struct bpf_map *map) !(map->map_flags & BPF_F_NO_PREALLOC); } +static bool is_tracing_prog_type(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_RAW_TRACEPOINT: + return true; + default: + return false; + } +} + static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) @@ -5448,6 +6614,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } + if ((is_tracing_prog_type(prog->type) || + prog->type == BPF_PROG_TYPE_SOCKET_FILTER) && + map_value_has_spin_lock(map)) { + verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); + return -EINVAL; + } + if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); @@ -5644,7 +6817,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len return; /* NOTE: fake 'exit' subprog should be updated as well. */ for (i = 0; i <= env->subprog_cnt; i++) { - if (env->subprog_info[i].start < off) + if (env->subprog_info[i].start <= off) continue; env->subprog_info[i].start += len - 1; } @@ -5664,6 +6837,153 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of return new_prog; } +static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env, + u32 off, u32 cnt) +{ + int i, j; + + /* find first prog starting at or after off (first to remove) */ + for (i = 0; i < env->subprog_cnt; i++) + if (env->subprog_info[i].start >= off) + break; + /* find first prog starting at or after off + cnt (first to stay) */ + for (j = i; j < env->subprog_cnt; j++) + if (env->subprog_info[j].start >= off + cnt) + break; + /* if j doesn't start exactly at off + cnt, we are just removing + * the front of previous prog + */ + if (env->subprog_info[j].start != off + cnt) + j--; + + if (j > i) { + struct bpf_prog_aux *aux = env->prog->aux; + int move; + + /* move fake 'exit' subprog as well */ + move = env->subprog_cnt + 1 - j; + + memmove(env->subprog_info + i, + env->subprog_info + j, + sizeof(*env->subprog_info) * move); + env->subprog_cnt -= j - i; + + /* remove func_info */ + if (aux->func_info) { + move = aux->func_info_cnt - j; + + memmove(aux->func_info + i, + aux->func_info + j, + sizeof(*aux->func_info) * move); + aux->func_info_cnt -= j - i; + /* func_info->insn_off is set after all code rewrites, + * in adjust_btf_func() - no need to adjust + */ + } + } else { + /* convert i from "first prog to remove" to "first to adjust" */ + if (env->subprog_info[i].start == off) + i++; + } + + /* update fake 'exit' subprog as well */ + for (; i <= env->subprog_cnt; i++) + env->subprog_info[i].start -= cnt; + + return 0; +} + +static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off, + u32 cnt) +{ + struct bpf_prog *prog = env->prog; + u32 i, l_off, l_cnt, nr_linfo; + struct bpf_line_info *linfo; + + nr_linfo = prog->aux->nr_linfo; + if (!nr_linfo) + return 0; + + linfo = prog->aux->linfo; + + /* find first line info to remove, count lines to be removed */ + for (i = 0; i < nr_linfo; i++) + if (linfo[i].insn_off >= off) + break; + + l_off = i; + l_cnt = 0; + for (; i < nr_linfo; i++) + if (linfo[i].insn_off < off + cnt) + l_cnt++; + else + break; + + /* First live insn doesn't match first live linfo, it needs to "inherit" + * last removed linfo. prog is already modified, so prog->len == off + * means no live instructions after (tail of the program was removed). + */ + if (prog->len != off && l_cnt && + (i == nr_linfo || linfo[i].insn_off != off + cnt)) { + l_cnt--; + linfo[--i].insn_off = off + cnt; + } + + /* remove the line info which refer to the removed instructions */ + if (l_cnt) { + memmove(linfo + l_off, linfo + i, + sizeof(*linfo) * (nr_linfo - i)); + + prog->aux->nr_linfo -= l_cnt; + nr_linfo = prog->aux->nr_linfo; + } + + /* pull all linfo[i].insn_off >= off + cnt in by cnt */ + for (i = l_off; i < nr_linfo; i++) + linfo[i].insn_off -= cnt; + + /* fix up all subprogs (incl. 'exit') which start >= off */ + for (i = 0; i <= env->subprog_cnt; i++) + if (env->subprog_info[i].linfo_idx > l_off) { + /* program may have started in the removed region but + * may not be fully removed + */ + if (env->subprog_info[i].linfo_idx >= l_off + l_cnt) + env->subprog_info[i].linfo_idx -= l_cnt; + else + env->subprog_info[i].linfo_idx = l_off; + } + + return 0; +} + +static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) +{ + struct bpf_insn_aux_data *aux_data = env->insn_aux_data; + unsigned int orig_prog_len = env->prog->len; + int err; + + if (bpf_prog_is_dev_bound(env->prog->aux)) + bpf_prog_offload_remove_insns(env, off, cnt); + + err = bpf_remove_insns(env->prog, off, cnt); + if (err) + return err; + + err = adjust_subprog_starts_after_remove(env, off, cnt); + if (err) + return err; + + err = bpf_adj_linfo_after_remove(env, off, cnt); + if (err) + return err; + + memmove(aux_data + off, aux_data + off + cnt, + sizeof(*aux_data) * (orig_prog_len - off - cnt)); + + return 0; +} + /* The verifier does more data flow analysis than llvm and will not * explore branches that are dead at run time. Malicious programs can * have dead code too. Therefore replace all dead at-run-time code @@ -5690,6 +7010,91 @@ static void sanitize_dead_code(struct bpf_verifier_env *env) } } +static bool insn_is_cond_jump(u8 code) +{ + u8 op; + + if (BPF_CLASS(code) == BPF_JMP32) + return true; + + if (BPF_CLASS(code) != BPF_JMP) + return false; + + op = BPF_OP(code); + return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL; +} + +static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env) +{ + struct bpf_insn_aux_data *aux_data = env->insn_aux_data; + struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); + struct bpf_insn *insn = env->prog->insnsi; + const int insn_cnt = env->prog->len; + int i; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (!insn_is_cond_jump(insn->code)) + continue; + + if (!aux_data[i + 1].seen) + ja.off = insn->off; + else if (!aux_data[i + 1 + insn->off].seen) + ja.off = 0; + else + continue; + + if (bpf_prog_is_dev_bound(env->prog->aux)) + bpf_prog_offload_replace_insn(env, i, &ja); + + memcpy(insn, &ja, sizeof(ja)); + } +} + +static int opt_remove_dead_code(struct bpf_verifier_env *env) +{ + struct bpf_insn_aux_data *aux_data = env->insn_aux_data; + int insn_cnt = env->prog->len; + int i, err; + + for (i = 0; i < insn_cnt; i++) { + int j; + + j = 0; + while (i + j < insn_cnt && !aux_data[i + j].seen) + j++; + if (!j) + continue; + + err = verifier_remove_insns(env, i, j); + if (err) + return err; + insn_cnt = env->prog->len; + } + + return 0; +} + +static int opt_remove_nops(struct bpf_verifier_env *env) +{ + const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + int i, err; + + for (i = 0; i < insn_cnt; i++) { + if (memcmp(&insn[i], &ja, sizeof(ja))) + continue; + + err = verifier_remove_insns(env, i, 1); + if (err) + return err; + insn_cnt--; + i--; + } + + return 0; +} + /* convert load instructions that access fields of a context type into a * sequence of instructions that access fields of the underlying structure: * struct __sk_buff -> struct sk_buff @@ -5701,12 +7106,16 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; + u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; bool is_narrower_load; - u32 target_size; - if (ops->gen_prologue) { + if (ops->gen_prologue || env->seen_direct_write) { + if (!ops->gen_prologue) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); if (cnt >= ARRAY_SIZE(insn_buf)) { @@ -5778,8 +7187,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) convert_ctx_access = ops->convert_ctx_access; break; case PTR_TO_SOCKET: + case PTR_TO_SOCK_COMMON: convert_ctx_access = bpf_sock_convert_ctx_access; break; + case PTR_TO_TCP_SOCK: + convert_ctx_access = bpf_tcp_sock_convert_ctx_access; + break; default: continue; } @@ -5793,9 +7206,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) * we will apply proper mask to the result. */ is_narrower_load = size < ctx_field_size; + size_default = bpf_ctx_off_adjust_machine(ctx_field_size); + off = insn->off; if (is_narrower_load) { - u32 size_default = bpf_ctx_off_adjust_machine(ctx_field_size); - u32 off = insn->off; u8 size_code; if (type == BPF_WRITE) { @@ -5823,12 +7236,23 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } if (is_narrower_load && size < target_size) { - if (ctx_field_size <= 4) + u8 shift = (off & (size_default - 1)) * 8; + + if (ctx_field_size <= 4) { + if (shift) + insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, + insn->dst_reg, + shift); insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1 << size * 8) - 1); - else + } else { + if (shift) + insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, + insn->dst_reg, + shift); insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, (1 << size * 8) - 1); + } } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); @@ -5851,7 +7275,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) int i, j, subprog_start, subprog_end = 0, len, subprog; struct bpf_insn *insn; void *old_bpf_func; - int err = -ENOMEM; + int err; if (env->subprog_cnt <= 1) return 0; @@ -5882,6 +7306,11 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn->imm = 1; } + err = bpf_prog_alloc_jited_linfo(prog); + if (err) + goto out_undo_insn; + + err = -ENOMEM; func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL); if (!func) goto out_undo_insn; @@ -5891,7 +7320,12 @@ static int jit_subprogs(struct bpf_verifier_env *env) subprog_end = env->subprog_info[i + 1].start; len = subprog_end - subprog_start; - func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER); + /* BPF_PROG_RUN doesn't call subprogs directly, + * hence main prog stats include the runtime of subprogs. + * subprogs don't have IDs and not reachable via prog_get_next_id + * func[i]->aux->stats will never be accessed and stays NULL + */ + func[i] = bpf_prog_alloc_no_stats(bpf_prog_size(len), GFP_USER); if (!func[i]) goto out_free; memcpy(func[i]->insnsi, &prog->insnsi[subprog_start], @@ -5901,12 +7335,21 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (bpf_prog_calc_tag(func[i])) goto out_free; func[i]->is_func = 1; + func[i]->aux->func_idx = i; + /* the btf and func_info will be freed only at prog->aux */ + func[i]->aux->btf = prog->aux->btf; + func[i]->aux->func_info = prog->aux->func_info; + /* Use bpf_prog_F_tag to indicate functions in stack traces. * Long term would need debug info to populate names */ func[i]->aux->name[0] = 'F'; func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; + func[i]->aux->linfo = prog->aux->linfo; + func[i]->aux->nr_linfo = prog->aux->nr_linfo; + func[i]->aux->jited_linfo = prog->aux->jited_linfo; + func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { err = -ENOTSUPP; @@ -5980,6 +7423,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) prog->bpf_func = func[0]->bpf_func; prog->aux->func = func; prog->aux->func_cnt = env->subprog_cnt; + bpf_prog_free_unused_jited_linfo(prog); return 0; out_free: for (i = 0; i < env->subprog_cnt; i++) @@ -5996,6 +7440,7 @@ out_undo_insn: insn->off = 0; insn->imm = env->insn_aux_data[i].call_imm; } + bpf_prog_free_jited_linfo(prog); return err; } @@ -6109,6 +7554,58 @@ 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 || + aux->alu_state == BPF_ALU_NON_POINTER) + 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) @@ -6128,6 +7625,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) */ prog->cb_access = 1; env->prog->aux->stack_depth = MAX_BPF_STACK; + env->prog->aux->max_pkt_offset = MAX_PACKET_OFF; /* mark bpf_tail_call as different opcode to avoid * conditional branch in the interpeter for every normal @@ -6292,11 +7790,13 @@ static void free_states(struct bpf_verifier_env *env) kfree(env->explored_states); } -int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) +int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, + union bpf_attr __user *uattr) { struct bpf_verifier_env *env; struct bpf_verifier_log *log; - int ret = -EINVAL; + int i, len, ret = -EINVAL; + bool is_priv; /* no program is valid */ if (ARRAY_SIZE(bpf_verifier_ops) == 0) @@ -6310,12 +7810,14 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) return -ENOMEM; log = &env->log; + len = (*prog)->len; env->insn_aux_data = - vzalloc(array_size(sizeof(struct bpf_insn_aux_data), - (*prog)->len)); + vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len)); ret = -ENOMEM; if (!env->insn_aux_data) goto err_free_env; + for (i = 0; i < len; i++) + env->insn_aux_data[i].orig_idx = i; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; @@ -6340,13 +7842,18 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; + if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) + env->strict_alignment = false; + + is_priv = capable(CAP_SYS_ADMIN); + env->allow_ptr_leaks = is_priv; ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; if (bpf_prog_is_dev_bound(env->prog->aux)) { - ret = bpf_prog_offload_verifier_prep(env); + ret = bpf_prog_offload_verifier_prep(env->prog); if (ret) goto skip_full_check; } @@ -6358,7 +7865,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!env->explored_states) goto skip_full_check; - env->allow_ptr_leaks = capable(CAP_SYS_ADMIN); + ret = check_subprogs(env); + if (ret < 0) + goto skip_full_check; + + ret = check_btf_info(env, attr, uattr); + if (ret < 0) + goto skip_full_check; ret = check_cfg(env); if (ret < 0) @@ -6378,11 +7891,21 @@ skip_full_check: free_states(env); if (ret == 0) - sanitize_dead_code(env); - - if (ret == 0) ret = check_max_stack_depth(env); + /* instruction rewrites happen after this point */ + if (is_priv) { + if (ret == 0) + opt_hard_wire_dead_code_branches(env); + if (ret == 0) + ret = opt_remove_dead_code(env); + if (ret == 0) + ret = opt_remove_nops(env); + } else { + if (ret == 0) + sanitize_dead_code(env); + } + if (ret == 0) /* program is valid, convert *(u32*)(ctx + off) accesses */ ret = convert_ctx_accesses(env); @@ -6421,6 +7944,9 @@ skip_full_check: convert_pseudo_ld_imm64(env); } + if (ret == 0) + adjust_btf_func(env); + err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release |