diff options
Diffstat (limited to 'kernel/bpf')
| -rw-r--r-- | kernel/bpf/Makefile | 8 | ||||
| -rw-r--r-- | kernel/bpf/arraymap.c | 33 | ||||
| -rw-r--r-- | kernel/bpf/bpf_lru_list.h | 3 | ||||
| -rw-r--r-- | kernel/bpf/core.c | 61 | ||||
| -rw-r--r-- | kernel/bpf/devmap.c | 409 | ||||
| -rw-r--r-- | kernel/bpf/hashtab.c | 60 | ||||
| -rw-r--r-- | kernel/bpf/lpm_trie.c | 9 | ||||
| -rw-r--r-- | kernel/bpf/sockmap.c | 873 | ||||
| -rw-r--r-- | kernel/bpf/stackmap.c | 8 | ||||
| -rw-r--r-- | kernel/bpf/syscall.c | 129 | ||||
| -rw-r--r-- | kernel/bpf/tnum.c | 180 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 2448 |
12 files changed, 3192 insertions, 1029 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index e1e5e658f2db..897daa005b23 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,7 +1,13 @@ obj-y := core.o -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +ifeq ($(CONFIG_NET),y) +obj-$(CONFIG_BPF_SYSCALL) += devmap.o +ifeq ($(CONFIG_STREAM_PARSER),y) +obj-$(CONFIG_BPF_SYSCALL) += sockmap.o +endif +endif ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o endif diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index d771a3872500..98c0f00c3f5e 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -49,13 +49,15 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_array *array; u64 array_size; u32 elem_size; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size == 0 || attr->map_flags) + attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE || + (percpu && numa_node != NUMA_NO_NODE)) return ERR_PTR(-EINVAL); if (attr->value_size > KMALLOC_MAX_SIZE) @@ -77,7 +79,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); /* allocate all map elements and zero-initialize them */ - array = bpf_map_area_alloc(array_size); + array = bpf_map_area_alloc(array_size, numa_node); if (!array) return ERR_PTR(-ENOMEM); @@ -87,6 +89,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array->map.value_size = attr->value_size; array->map.max_entries = attr->max_entries; array->map.map_flags = attr->map_flags; + array->map.numa_node = numa_node; array->elem_size = elem_size; if (!percpu) @@ -603,6 +606,31 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key) return READ_ONCE(*inner_map); } +static u32 array_of_map_gen_lookup(struct bpf_map *map, + struct bpf_insn *insn_buf) +{ + u32 elem_size = round_up(map->value_size, 8); + struct bpf_insn *insn = insn_buf; + const int ret = BPF_REG_0; + const int map_ptr = BPF_REG_1; + const int index = BPF_REG_2; + + *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); + *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5); + if (is_power_of_2(elem_size)) + *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); + else + *insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size); + *insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr); + *insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0); + *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); + *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *insn++ = BPF_MOV64_IMM(ret, 0); + + return insn - insn_buf; +} + const struct bpf_map_ops array_of_maps_map_ops = { .map_alloc = array_of_map_alloc, .map_free = array_of_map_free, @@ -612,4 +640,5 @@ const struct bpf_map_ops array_of_maps_map_ops = { .map_fd_get_ptr = bpf_map_fd_get_ptr, .map_fd_put_ptr = bpf_map_fd_put_ptr, .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, + .map_gen_lookup = array_of_map_gen_lookup, }; diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 5c35a98d02bf..7d4f89b7cb84 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -69,7 +69,8 @@ static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node) /* ref is an approximation on access frequency. It does not * have to be very accurate. Hence, no protection is used. */ - node->ref = 1; + if (!node->ref) + node->ref = 1; } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ad5f55922a13..917cc04a0a94 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -595,9 +595,13 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; @@ -833,12 +837,20 @@ static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K, [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X, [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K, + [BPF_JMP | BPF_JLT | BPF_X] = &&JMP_JLT_X, + [BPF_JMP | BPF_JLT | BPF_K] = &&JMP_JLT_K, [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X, [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K, + [BPF_JMP | BPF_JLE | BPF_X] = &&JMP_JLE_X, + [BPF_JMP | BPF_JLE | BPF_K] = &&JMP_JLE_K, [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X, [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K, + [BPF_JMP | BPF_JSLT | BPF_X] = &&JMP_JSLT_X, + [BPF_JMP | BPF_JSLT | BPF_K] = &&JMP_JSLT_K, [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X, [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K, + [BPF_JMP | BPF_JSLE | BPF_X] = &&JMP_JSLE_X, + [BPF_JMP | BPF_JSLE | BPF_K] = &&JMP_JSLE_K, [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X, [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K, /* Program return */ @@ -1073,6 +1085,18 @@ out: CONT_JMP; } CONT; + JMP_JLT_X: + if (DST < SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JLT_K: + if (DST < IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JGE_X: if (DST >= SRC) { insn += insn->off; @@ -1085,6 +1109,18 @@ out: CONT_JMP; } CONT; + JMP_JLE_X: + if (DST <= SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JLE_K: + if (DST <= IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JSGT_X: if (((s64) DST) > ((s64) SRC)) { insn += insn->off; @@ -1097,6 +1133,18 @@ out: CONT_JMP; } CONT; + JMP_JSLT_X: + if (((s64) DST) < ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSLT_K: + if (((s64) DST) < ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JSGE_X: if (((s64) DST) >= ((s64) SRC)) { insn += insn->off; @@ -1109,6 +1157,18 @@ out: CONT_JMP; } CONT; + JMP_JSLE_X: + if (((s64) DST) <= ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSLE_K: + if (((s64) DST) <= ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JSET_X: if (DST & SRC) { insn += insn->off; @@ -1378,6 +1438,7 @@ const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; +const struct bpf_func_proto bpf_sock_map_update_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c new file mode 100644 index 000000000000..ecf9f99ecc57 --- /dev/null +++ b/kernel/bpf/devmap.c @@ -0,0 +1,409 @@ +/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +/* Devmaps primary use is as a backend map for XDP BPF helper call + * bpf_redirect_map(). Because XDP is mostly concerned with performance we + * spent some effort to ensure the datapath with redirect maps does not use + * any locking. This is a quick note on the details. + * + * We have three possible paths to get into the devmap control plane bpf + * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall + * will invoke an update, delete, or lookup operation. To ensure updates and + * deletes appear atomic from the datapath side xchg() is used to modify the + * netdev_map array. Then because the datapath does a lookup into the netdev_map + * array (read-only) from an RCU critical section we use call_rcu() to wait for + * an rcu grace period before free'ing the old data structures. This ensures the + * datapath always has a valid copy. However, the datapath does a "flush" + * operation that pushes any pending packets in the driver outside the RCU + * critical section. Each bpf_dtab_netdev tracks these pending operations using + * an atomic per-cpu bitmap. The bpf_dtab_netdev object will not be destroyed + * until all bits are cleared indicating outstanding flush operations have + * completed. + * + * BPF syscalls may race with BPF program calls on any of the update, delete + * or lookup operations. As noted above the xchg() operation also keep the + * netdev_map consistent in this case. From the devmap side BPF programs + * calling into these operations are the same as multiple user space threads + * making system calls. + * + * Finally, any of the above may race with a netdev_unregister notifier. The + * unregister notifier must search for net devices in the map structure that + * contain a reference to the net device and remove them. This is a two step + * process (a) dereference the bpf_dtab_netdev object in netdev_map and (b) + * check to see if the ifindex is the same as the net_device being removed. + * When removing the dev a cmpxchg() is used to ensure the correct dev is + * removed, in the case of a concurrent update or delete operation it is + * possible that the initially referenced dev is no longer in the map. As the + * notifier hook walks the map we know that new dev references can not be + * added by the user because core infrastructure ensures dev_get_by_index() + * calls will fail at this point. + */ +#include <linux/bpf.h> +#include <linux/filter.h> + +struct bpf_dtab_netdev { + struct net_device *dev; + struct bpf_dtab *dtab; + unsigned int bit; + struct rcu_head rcu; +}; + +struct bpf_dtab { + struct bpf_map map; + struct bpf_dtab_netdev **netdev_map; + unsigned long __percpu *flush_needed; + struct list_head list; +}; + +static DEFINE_SPINLOCK(dev_map_lock); +static LIST_HEAD(dev_map_list); + +static u64 dev_map_bitmap_size(const union bpf_attr *attr) +{ + return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); +} + +static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +{ + struct bpf_dtab *dtab; + u64 cost; + int err; + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + return ERR_PTR(-EINVAL); + + dtab = kzalloc(sizeof(*dtab), GFP_USER); + if (!dtab) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + dtab->map.map_type = attr->map_type; + dtab->map.key_size = attr->key_size; + dtab->map.value_size = attr->value_size; + dtab->map.max_entries = attr->max_entries; + dtab->map.map_flags = attr->map_flags; + dtab->map.numa_node = bpf_map_attr_numa_node(attr); + + /* make sure page count doesn't overflow */ + cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); + cost += dev_map_bitmap_size(attr) * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_dtab; + + dtab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* if map size is larger than memlock limit, reject it early */ + err = bpf_map_precharge_memlock(dtab->map.pages); + if (err) + goto free_dtab; + + /* A per cpu bitfield with a bit per possible net device */ + dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr), + __alignof__(unsigned long)); + if (!dtab->flush_needed) + goto free_dtab; + + dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries * + sizeof(struct bpf_dtab_netdev *), + dtab->map.numa_node); + if (!dtab->netdev_map) + goto free_dtab; + + spin_lock(&dev_map_lock); + list_add_tail_rcu(&dtab->list, &dev_map_list); + spin_unlock(&dev_map_lock); + + return &dtab->map; +free_dtab: + free_percpu(dtab->flush_needed); + kfree(dtab); + return ERR_PTR(-ENOMEM); +} + +static void dev_map_free(struct bpf_map *map) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + int i, cpu; + + /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete. The rcu critical section only guarantees + * no further reads against netdev_map. It does __not__ ensure pending + * flush operations (if any) are complete. + */ + + spin_lock(&dev_map_lock); + list_del_rcu(&dtab->list); + spin_unlock(&dev_map_lock); + + synchronize_rcu(); + + /* To ensure all pending flush operations have completed wait for flush + * bitmap to indicate all flush_needed bits to be zero on _all_ cpus. + * Because the above synchronize_rcu() ensures the map is disconnected + * from the program we can assume no new bits will be set. + */ + for_each_online_cpu(cpu) { + unsigned long *bitmap = per_cpu_ptr(dtab->flush_needed, cpu); + + while (!bitmap_empty(bitmap, dtab->map.max_entries)) + cpu_relax(); + } + + for (i = 0; i < dtab->map.max_entries; i++) { + struct bpf_dtab_netdev *dev; + + dev = dtab->netdev_map[i]; + if (!dev) + continue; + + dev_put(dev->dev); + kfree(dev); + } + + free_percpu(dtab->flush_needed); + bpf_map_area_free(dtab->netdev_map); + kfree(dtab); +} + +static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = next_key; + + if (index >= dtab->map.max_entries) { + *next = 0; + return 0; + } + + if (index == dtab->map.max_entries - 1) + return -ENOENT; + *next = index + 1; + return 0; +} + +void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed); + + __set_bit(bit, bitmap); +} + +/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled + * from the driver before returning from its napi->poll() routine. The poll() + * routine is called either from busy_poll context or net_rx_action signaled + * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the + * net device can be torn down. On devmap tear down we ensure the ctx bitmap + * is zeroed before completing to ensure all flush operations have completed. + */ +void __dev_map_flush(struct bpf_map *map) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed); + u32 bit; + + for_each_set_bit(bit, bitmap, map->max_entries) { + struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]); + struct net_device *netdev; + + /* This is possible if the dev entry is removed by user space + * between xdp redirect and flush op. + */ + if (unlikely(!dev)) + continue; + + __clear_bit(bit, bitmap); + netdev = dev->dev; + if (likely(netdev->netdev_ops->ndo_xdp_flush)) + netdev->netdev_ops->ndo_xdp_flush(netdev); + } +} + +/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or + * update happens in parallel here a dev_put wont happen until after reading the + * ifindex. + */ +struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev; + + if (key >= map->max_entries) + return NULL; + + dev = READ_ONCE(dtab->netdev_map[key]); + return dev ? dev->dev : NULL; +} + +static void *dev_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct net_device *dev = __dev_map_lookup_elem(map, *(u32 *)key); + + return dev ? &dev->ifindex : NULL; +} + +static void dev_map_flush_old(struct bpf_dtab_netdev *dev) +{ + if (dev->dev->netdev_ops->ndo_xdp_flush) { + struct net_device *fl = dev->dev; + unsigned long *bitmap; + int cpu; + + for_each_online_cpu(cpu) { + bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu); + __clear_bit(dev->bit, bitmap); + + fl->netdev_ops->ndo_xdp_flush(dev->dev); + } + } +} + +static void __dev_map_entry_free(struct rcu_head *rcu) +{ + struct bpf_dtab_netdev *dev; + + dev = container_of(rcu, struct bpf_dtab_netdev, rcu); + dev_map_flush_old(dev); + dev_put(dev->dev); + kfree(dev); +} + +static int dev_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *old_dev; + int k = *(u32 *)key; + + if (k >= map->max_entries) + return -EINVAL; + + /* Use call_rcu() here to ensure any rcu critical sections have + * completed, but this does not guarantee a flush has happened + * yet. Because driver side rcu_read_lock/unlock only protects the + * running XDP program. However, for pending flush operations the + * dev and ctx are stored in another per cpu map. And additionally, + * the driver tear down ensures all soft irqs are complete before + * removing the net device in the case of dev_put equals zero. + */ + old_dev = xchg(&dtab->netdev_map[k], NULL); + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + return 0; +} + +static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct net *net = current->nsproxy->net_ns; + struct bpf_dtab_netdev *dev, *old_dev; + u32 i = *(u32 *)key; + u32 ifindex = *(u32 *)value; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(i >= dtab->map.max_entries)) + return -E2BIG; + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + + if (!ifindex) { + dev = NULL; + } else { + dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, + map->numa_node); + if (!dev) + return -ENOMEM; + + dev->dev = dev_get_by_index(net, ifindex); + if (!dev->dev) { + kfree(dev); + return -EINVAL; + } + + dev->bit = i; + dev->dtab = dtab; + } + + /* Use call_rcu() here to ensure rcu critical sections have completed + * Remembering the driver side flush operation will happen before the + * net device is removed. + */ + old_dev = xchg(&dtab->netdev_map[i], dev); + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + + return 0; +} + +const struct bpf_map_ops dev_map_ops = { + .map_alloc = dev_map_alloc, + .map_free = dev_map_free, + .map_get_next_key = dev_map_get_next_key, + .map_lookup_elem = dev_map_lookup_elem, + .map_update_elem = dev_map_update_elem, + .map_delete_elem = dev_map_delete_elem, +}; + +static int dev_map_notification(struct notifier_block *notifier, + ulong event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct bpf_dtab *dtab; + int i; + + switch (event) { + case NETDEV_UNREGISTER: + /* This rcu_read_lock/unlock pair is needed because + * dev_map_list is an RCU list AND to ensure a delete + * operation does not free a netdev_map entry while we + * are comparing it against the netdev being unregistered. + */ + rcu_read_lock(); + list_for_each_entry_rcu(dtab, &dev_map_list, list) { + for (i = 0; i < dtab->map.max_entries; i++) { + struct bpf_dtab_netdev *dev, *odev; + + dev = READ_ONCE(dtab->netdev_map[i]); + if (!dev || + dev->dev->ifindex != netdev->ifindex) + continue; + odev = cmpxchg(&dtab->netdev_map[i], dev, NULL); + if (dev == odev) + call_rcu(&dev->rcu, + __dev_map_entry_free); + } + } + rcu_read_unlock(); + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block dev_map_notifier = { + .notifier_call = dev_map_notification, +}; + +static int __init dev_map_init(void) +{ + register_netdevice_notifier(&dev_map_notifier); + return 0; +} + +subsys_initcall(dev_map_init); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index d11c8181f4c5..431126f31ea3 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -18,6 +18,9 @@ #include "bpf_lru_list.h" #include "map_in_map.h" +#define HTAB_CREATE_FLAG_MASK \ + (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE) + struct bucket { struct hlist_nulls_head head; raw_spinlock_t lock; @@ -138,7 +141,8 @@ static int prealloc_init(struct bpf_htab *htab) if (!htab_is_percpu(htab) && !htab_is_lru(htab)) num_entries += num_possible_cpus(); - htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries); + htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries, + htab->map.numa_node); if (!htab->elems) return -ENOMEM; @@ -233,6 +237,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_htab *htab; int err, i; u64 cost; @@ -248,7 +253,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ return ERR_PTR(-EPERM); - if (attr->map_flags & ~(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU)) + if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK) /* reserved bits should not be used */ return ERR_PTR(-EINVAL); @@ -258,6 +263,9 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (lru && !prealloc) return ERR_PTR(-ENOTSUPP); + if (numa_node != NUMA_NO_NODE && (percpu || percpu_lru)) + return ERR_PTR(-EINVAL); + htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) return ERR_PTR(-ENOMEM); @@ -268,6 +276,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->map.value_size = attr->value_size; htab->map.max_entries = attr->max_entries; htab->map.map_flags = attr->map_flags; + htab->map.numa_node = numa_node; /* check sanity of attributes. * value_size == 0 may be allowed in the future to use map as a set @@ -346,7 +355,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) err = -ENOMEM; htab->buckets = bpf_map_area_alloc(htab->n_buckets * - sizeof(struct bucket)); + sizeof(struct bucket), + htab->map.numa_node); if (!htab->buckets) goto free_htab; @@ -504,6 +514,29 @@ static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +static u32 htab_lru_map_gen_lookup(struct bpf_map *map, + struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + const int ret = BPF_REG_0; + const int ref_reg = BPF_REG_1; + + *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4); + *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret, + offsetof(struct htab_elem, lru_node) + + offsetof(struct bpf_lru_node, ref)); + *insn++ = BPF_JMP_IMM(BPF_JNE, ref_reg, 0, 1); + *insn++ = BPF_ST_MEM(BPF_B, ret, + offsetof(struct htab_elem, lru_node) + + offsetof(struct bpf_lru_node, ref), + 1); + *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, + offsetof(struct htab_elem, key) + + round_up(map->key_size, 8)); + return insn - insn_buf; +} + /* It is called from the bpf_lru_list when the LRU needs to delete * older elements from the htab. */ @@ -704,7 +737,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, atomic_dec(&htab->count); return ERR_PTR(-E2BIG); } - l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); + l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, + htab->map.numa_node); if (!l_new) return ERR_PTR(-ENOMEM); } @@ -1126,6 +1160,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_lookup_elem = htab_lru_map_lookup_elem, .map_update_elem = htab_lru_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, + .map_gen_lookup = htab_lru_map_gen_lookup, }; /* Called from eBPF program */ @@ -1315,6 +1350,22 @@ static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key) return READ_ONCE(*inner_map); } +static u32 htab_of_map_gen_lookup(struct bpf_map *map, + struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + const int ret = BPF_REG_0; + + *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2); + *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, + offsetof(struct htab_elem, key) + + round_up(map->key_size, 8)); + *insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0); + + return insn - insn_buf; +} + static void htab_of_map_free(struct bpf_map *map) { bpf_map_meta_free(map->inner_map_meta); @@ -1330,4 +1381,5 @@ const struct bpf_map_ops htab_of_maps_map_ops = { .map_fd_get_ptr = bpf_map_fd_get_ptr, .map_fd_put_ptr = bpf_map_fd_put_ptr, .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, + .map_gen_lookup = htab_of_map_gen_lookup, }; diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index b09185f0f17d..1b767844a76f 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -244,7 +244,8 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, if (value) size += trie->map.value_size; - node = kmalloc(size, GFP_ATOMIC | __GFP_NOWARN); + node = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN, + trie->map.numa_node); if (!node) return NULL; @@ -405,6 +406,8 @@ static int trie_delete_elem(struct bpf_map *map, void *key) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) +#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE) + static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; @@ -416,7 +419,8 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || - attr->map_flags != BPF_F_NO_PREALLOC || + !(attr->map_flags & BPF_F_NO_PREALLOC) || + attr->map_flags & ~LPM_CREATE_FLAG_MASK || attr->key_size < LPM_KEY_SIZE_MIN || attr->key_size > LPM_KEY_SIZE_MAX || attr->value_size < LPM_VAL_SIZE_MIN || @@ -433,6 +437,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) trie->map.value_size = attr->value_size; trie->map.max_entries = attr->max_entries; trie->map.map_flags = attr->map_flags; + trie->map.numa_node = bpf_map_attr_numa_node(attr); trie->data_size = attr->key_size - offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c new file mode 100644 index 000000000000..f6ffde9c6a68 --- /dev/null +++ b/kernel/bpf/sockmap.c @@ -0,0 +1,873 @@ +/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +/* A BPF sock_map is used to store sock objects. This is primarly used + * for doing socket redirect with BPF helper routines. + * + * A sock map may have BPF programs attached to it, currently a program + * used to parse packets and a program to provide a verdict and redirect + * decision on the packet are supported. Any programs attached to a sock + * map are inherited by sock objects when they are added to the map. If + * no BPF programs are attached the sock object may only be used for sock + * redirect. + * + * A sock object may be in multiple maps, but can only inherit a single + * parse or verdict program. If adding a sock object to a map would result + * in having multiple parsing programs the update will return an EBUSY error. + * + * For reference this program is similar to devmap used in XDP context + * reviewing these together may be useful. For an example please review + * ./samples/bpf/sockmap/. + */ +#include <linux/bpf.h> +#include <net/sock.h> +#include <linux/filter.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/kernel.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/workqueue.h> +#include <linux/list.h> +#include <net/strparser.h> + +struct bpf_stab { + struct bpf_map map; + struct sock **sock_map; + struct bpf_prog *bpf_parse; + struct bpf_prog *bpf_verdict; +}; + +enum smap_psock_state { + SMAP_TX_RUNNING, +}; + +struct smap_psock_map_entry { + struct list_head list; + struct sock **entry; +}; + +struct smap_psock { + struct rcu_head rcu; + /* refcnt is used inside sk_callback_lock */ + u32 refcnt; + + /* datapath variables */ + struct sk_buff_head rxqueue; + bool strp_enabled; + + /* datapath error path cache across tx work invocations */ + int save_rem; + int save_off; + struct sk_buff *save_skb; + + struct strparser strp; + struct bpf_prog *bpf_parse; + struct bpf_prog *bpf_verdict; + struct list_head maps; + + /* Back reference used when sock callback trigger sockmap operations */ + struct sock *sock; + unsigned long state; + + struct work_struct tx_work; + struct work_struct gc_work; + + void (*save_data_ready)(struct sock *sk); + void (*save_write_space)(struct sock *sk); + void (*save_state_change)(struct sock *sk); +}; + +static inline struct smap_psock *smap_psock_sk(const struct sock *sk) +{ + return rcu_dereference_sk_user_data(sk); +} + +static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) +{ + struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict); + int rc; + + if (unlikely(!prog)) + return SK_DROP; + + skb_orphan(skb); + skb->sk = psock->sock; + bpf_compute_data_end(skb); + rc = (*prog->bpf_func)(skb, prog->insnsi); + skb->sk = NULL; + + return rc; +} + +static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) +{ + struct sock *sk; + int rc; + + /* Because we use per cpu values to feed input from sock redirect + * in BPF program to do_sk_redirect_map() call we need to ensure we + * are not preempted. RCU read lock is not sufficient in this case + * with CONFIG_PREEMPT_RCU enabled so we must be explicit here. + */ + preempt_disable(); + rc = smap_verdict_func(psock, skb); + switch (rc) { + case SK_REDIRECT: + sk = do_sk_redirect_map(); + preempt_enable(); + if (likely(sk)) { + struct smap_psock *peer = smap_psock_sk(sk); + + if (likely(peer && + test_bit(SMAP_TX_RUNNING, &peer->state) && + !sock_flag(sk, SOCK_DEAD) && + sock_writeable(sk))) { + skb_set_owner_w(skb, sk); + skb_queue_tail(&peer->rxqueue, skb); + schedule_work(&peer->tx_work); + break; + } + } + /* Fall through and free skb otherwise */ + case SK_DROP: + default: + if (rc != SK_REDIRECT) + preempt_enable(); + kfree_skb(skb); + } +} + +static void smap_report_sk_error(struct smap_psock *psock, int err) +{ + struct sock *sk = psock->sock; + + sk->sk_err = err; + sk->sk_error_report(sk); +} + +static void smap_release_sock(struct smap_psock *psock, struct sock *sock); + +/* Called with lock_sock(sk) held */ +static void smap_state_change(struct sock *sk) +{ + struct smap_psock_map_entry *e, *tmp; + struct smap_psock *psock; + struct socket_wq *wq; + struct sock *osk; + + rcu_read_lock(); + + /* Allowing transitions into an established syn_recv states allows + * for early binding sockets to a smap object before the connection + * is established. + */ + switch (sk->sk_state) { + case TCP_SYN_SENT: + case TCP_SYN_RECV: + case TCP_ESTABLISHED: + break; + case TCP_CLOSE_WAIT: + case TCP_CLOSING: + case TCP_LAST_ACK: + case TCP_FIN_WAIT1: + case TCP_FIN_WAIT2: + case TCP_LISTEN: + break; + case TCP_CLOSE: + /* Only release if the map entry is in fact the sock in + * question. There is a case where the operator deletes + * the sock from the map, but the TCP sock is closed before + * the psock is detached. Use cmpxchg to verify correct + * sock is removed. + */ + psock = smap_psock_sk(sk); + if (unlikely(!psock)) + break; + write_lock_bh(&sk->sk_callback_lock); + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + osk = cmpxchg(e->entry, sk, NULL); + if (osk == sk) { + list_del(&e->list); + smap_release_sock(psock, sk); + } + } + write_unlock_bh(&sk->sk_callback_lock); + break; + default: + psock = smap_psock_sk(sk); + if (unlikely(!psock)) + break; + smap_report_sk_error(psock, EPIPE); + break; + } + + wq = rcu_dereference(sk->sk_wq); + if (skwq_has_sleeper(wq)) + wake_up_interruptible_all(&wq->wait); + rcu_read_unlock(); +} + +static void smap_read_sock_strparser(struct strparser *strp, + struct sk_buff *skb) +{ + struct smap_psock *psock; + + rcu_read_lock(); + psock = container_of(strp, struct smap_psock, strp); + smap_do_verdict(psock, skb); + rcu_read_unlock(); +} + +/* Called with lock held on socket */ +static void smap_data_ready(struct sock *sk) +{ + struct smap_psock *psock; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (likely(psock)) { + write_lock_bh(&sk->sk_callback_lock); + strp_data_ready(&psock->strp); + write_unlock_bh(&sk->sk_callback_lock); + } + rcu_read_unlock(); +} + +static void smap_tx_work(struct work_struct *w) +{ + struct smap_psock *psock; + struct sk_buff *skb; + int rem, off, n; + + psock = container_of(w, struct smap_psock, tx_work); + + /* lock sock to avoid losing sk_socket at some point during loop */ + lock_sock(psock->sock); + if (psock->save_skb) { + skb = psock->save_skb; + rem = psock->save_rem; + off = psock->save_off; + psock->save_skb = NULL; + goto start; + } + + while ((skb = skb_dequeue(&psock->rxqueue))) { + rem = skb->len; + off = 0; +start: + do { + if (likely(psock->sock->sk_socket)) + n = skb_send_sock_locked(psock->sock, + skb, off, rem); + else + n = -EINVAL; + if (n <= 0) { + if (n == -EAGAIN) { + /* Retry when space is available */ + psock->save_skb = skb; + psock->save_rem = rem; + psock->save_off = off; + goto out; + } + /* Hard errors break pipe and stop xmit */ + smap_report_sk_error(psock, n ? -n : EPIPE); + clear_bit(SMAP_TX_RUNNING, &psock->state); + kfree_skb(skb); + goto out; + } + rem -= n; + off += n; + } while (rem); + kfree_skb(skb); + } +out: + release_sock(psock->sock); +} + +static void smap_write_space(struct sock *sk) +{ + struct smap_psock *psock; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (likely(psock && test_bit(SMAP_TX_RUNNING, &psock->state))) + schedule_work(&psock->tx_work); + rcu_read_unlock(); +} + +static void smap_stop_sock(struct smap_psock *psock, struct sock *sk) +{ + if (!psock->strp_enabled) + return; + sk->sk_data_ready = psock->save_data_ready; + sk->sk_write_space = psock->save_write_space; + sk->sk_state_change = psock->save_state_change; + psock->save_data_ready = NULL; + psock->save_write_space = NULL; + psock->save_state_change = NULL; + strp_stop(&psock->strp); + psock->strp_enabled = false; +} + +static void smap_destroy_psock(struct rcu_head *rcu) +{ + struct smap_psock *psock = container_of(rcu, + struct smap_psock, rcu); + + /* Now that a grace period has passed there is no longer + * any reference to this sock in the sockmap so we can + * destroy the psock, strparser, and bpf programs. But, + * because we use workqueue sync operations we can not + * do it in rcu context + */ + schedule_work(&psock->gc_work); +} + +static void smap_release_sock(struct smap_psock *psock, struct sock *sock) +{ + psock->refcnt--; + if (psock->refcnt) + return; + + smap_stop_sock(psock, sock); + clear_bit(SMAP_TX_RUNNING, &psock->state); + rcu_assign_sk_user_data(sock, NULL); + call_rcu_sched(&psock->rcu, smap_destroy_psock); +} + +static int smap_parse_func_strparser(struct strparser *strp, + struct sk_buff *skb) +{ + struct smap_psock *psock; + struct bpf_prog *prog; + int rc; + + rcu_read_lock(); + psock = container_of(strp, struct smap_psock, strp); + prog = READ_ONCE(psock->bpf_parse); + + if (unlikely(!prog)) { + rcu_read_unlock(); + return skb->len; + } + + /* Attach socket for bpf program to use if needed we can do this + * because strparser clones the skb before handing it to a upper + * layer, meaning skb_orphan has been called. We NULL sk on the + * way out to ensure we don't trigger a BUG_ON in skb/sk operations + * later and because we are not charging the memory of this skb to + * any socket yet. + */ + skb->sk = psock->sock; + bpf_compute_data_end(skb); + rc = (*prog->bpf_func)(skb, prog->insnsi); + skb->sk = NULL; + rcu_read_unlock(); + return rc; +} + + +static int smap_read_sock_done(struct strparser *strp, int err) +{ + return err; +} + +static int smap_init_sock(struct smap_psock *psock, + struct sock *sk) +{ + static const struct strp_callbacks cb = { + .rcv_msg = smap_read_sock_strparser, + .parse_msg = smap_parse_func_strparser, + .read_sock_done = smap_read_sock_done, + }; + + return strp_init(&psock->strp, sk, &cb); +} + +static void smap_init_progs(struct smap_psock *psock, + struct bpf_stab *stab, + struct bpf_prog *verdict, + struct bpf_prog *parse) +{ + struct bpf_prog *orig_parse, *orig_verdict; + + orig_parse = xchg(&psock->bpf_parse, parse); + orig_verdict = xchg(&psock->bpf_verdict, verdict); + + if (orig_verdict) + bpf_prog_put(orig_verdict); + if (orig_parse) + bpf_prog_put(orig_parse); +} + +static void smap_start_sock(struct smap_psock *psock, struct sock *sk) +{ + if (sk->sk_data_ready == smap_data_ready) + return; + psock->save_data_ready = sk->sk_data_ready; + psock->save_write_space = sk->sk_write_space; + psock->save_state_change = sk->sk_state_change; + sk->sk_data_ready = smap_data_ready; + sk->sk_write_space = smap_write_space; + sk->sk_state_change = smap_state_change; + psock->strp_enabled = true; +} + +static void sock_map_remove_complete(struct bpf_stab *stab) +{ + bpf_map_area_free(stab->sock_map); + kfree(stab); +} + +static void smap_gc_work(struct work_struct *w) +{ + struct smap_psock_map_entry *e, *tmp; + struct smap_psock *psock; + + psock = container_of(w, struct smap_psock, gc_work); + + /* no callback lock needed because we already detached sockmap ops */ + if (psock->strp_enabled) + strp_done(&psock->strp); + + cancel_work_sync(&psock->tx_work); + __skb_queue_purge(&psock->rxqueue); + + /* At this point all strparser and xmit work must be complete */ + if (psock->bpf_parse) + bpf_prog_put(psock->bpf_parse); + if (psock->bpf_verdict) + bpf_prog_put(psock->bpf_verdict); + + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + list_del(&e->list); + kfree(e); + } + + sock_put(psock->sock); + kfree(psock); +} + +static struct smap_psock *smap_init_psock(struct sock *sock, + struct bpf_stab *stab) +{ + struct smap_psock *psock; + + psock = kzalloc_node(sizeof(struct smap_psock), + GFP_ATOMIC | __GFP_NOWARN, + stab->map.numa_node); + if (!psock) + return ERR_PTR(-ENOMEM); + + psock->sock = sock; + skb_queue_head_init(&psock->rxqueue); + INIT_WORK(&psock->tx_work, smap_tx_work); + INIT_WORK(&psock->gc_work, smap_gc_work); + INIT_LIST_HEAD(&psock->maps); + psock->refcnt = 1; + + rcu_assign_sk_user_data(sock, psock); + sock_hold(sock); + return psock; +} + +static struct bpf_map *sock_map_alloc(union bpf_attr *attr) +{ + struct bpf_stab *stab; + int err = -EINVAL; + u64 cost; + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + return ERR_PTR(-EINVAL); + + if (attr->value_size > KMALLOC_MAX_SIZE) + return ERR_PTR(-E2BIG); + + stab = kzalloc(sizeof(*stab), GFP_USER); + if (!stab) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + stab->map.map_type = attr->map_type; + stab->map.key_size = attr->key_size; + stab->map.value_size = attr->value_size; + stab->map.max_entries = attr->max_entries; + stab->map.map_flags = attr->map_flags; + stab->map.numa_node = bpf_map_attr_numa_node(attr); + + /* make sure page count doesn't overflow */ + cost = (u64) stab->map.max_entries * sizeof(struct sock *); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_stab; + + stab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* if map size is larger than memlock limit, reject it early */ + err = bpf_map_precharge_memlock(stab->map.pages); + if (err) + goto free_stab; + + err = -ENOMEM; + stab->sock_map = bpf_map_area_alloc(stab->map.max_entries * + sizeof(struct sock *), + stab->map.numa_node); + if (!stab->sock_map) + goto free_stab; + + return &stab->map; +free_stab: + kfree(stab); + return ERR_PTR(err); +} + +static void smap_list_remove(struct smap_psock *psock, struct sock **entry) +{ + struct smap_psock_map_entry *e, *tmp; + + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + if (e->entry == entry) { + list_del(&e->list); + break; + } + } +} + +static void sock_map_free(struct bpf_map *map) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + int i; + + synchronize_rcu(); + + /* At this point no update, lookup or delete operations can happen. + * However, be aware we can still get a socket state event updates, + * and data ready callabacks that reference the psock from sk_user_data + * Also psock worker threads are still in-flight. So smap_release_sock + * will only free the psock after cancel_sync on the worker threads + * and a grace period expire to ensure psock is really safe to remove. + */ + rcu_read_lock(); + for (i = 0; i < stab->map.max_entries; i++) { + struct smap_psock *psock; + struct sock *sock; + + sock = xchg(&stab->sock_map[i], NULL); + if (!sock) + continue; + + write_lock_bh(&sock->sk_callback_lock); + psock = smap_psock_sk(sock); + smap_list_remove(psock, &stab->sock_map[i]); + smap_release_sock(psock, sock); + write_unlock_bh(&sock->sk_callback_lock); + } + rcu_read_unlock(); + + if (stab->bpf_verdict) + bpf_prog_put(stab->bpf_verdict); + if (stab->bpf_parse) + bpf_prog_put(stab->bpf_parse); + + sock_map_remove_complete(stab); +} + +static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + u32 i = key ? *(u32 *)key : U32_MAX; + u32 *next = (u32 *)next_key; + + if (i >= stab->map.max_entries) { + *next = 0; + return 0; + } + + if (i == stab->map.max_entries - 1) + return -ENOENT; + + *next = i + 1; + return 0; +} + +struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + + if (key >= map->max_entries) + return NULL; + + return READ_ONCE(stab->sock_map[key]); +} + +static int sock_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct smap_psock *psock; + int k = *(u32 *)key; + struct sock *sock; + + if (k >= map->max_entries) + return -EINVAL; + + sock = xchg(&stab->sock_map[k], NULL); + if (!sock) + return -EINVAL; + + write_lock_bh(&sock->sk_callback_lock); + psock = smap_psock_sk(sock); + if (!psock) + goto out; + + if (psock->bpf_parse) + smap_stop_sock(psock, sock); + smap_list_remove(psock, &stab->sock_map[k]); + smap_release_sock(psock, sock); +out: + write_unlock_bh(&sock->sk_callback_lock); + return 0; +} + +/* Locking notes: Concurrent updates, deletes, and lookups are allowed and are + * done inside rcu critical sections. This ensures on updates that the psock + * will not be released via smap_release_sock() until concurrent updates/deletes + * complete. All operations operate on sock_map using cmpxchg and xchg + * operations to ensure we do not get stale references. Any reads into the + * map must be done with READ_ONCE() because of this. + * + * A psock is destroyed via call_rcu and after any worker threads are cancelled + * and syncd so we are certain all references from the update/lookup/delete + * operations as well as references in the data path are no longer in use. + * + * Psocks may exist in multiple maps, but only a single set of parse/verdict + * programs may be inherited from the maps it belongs to. A reference count + * is kept with the total number of references to the psock from all maps. The + * psock will not be released until this reaches zero. The psock and sock + * user data data use the sk_callback_lock to protect critical data structures + * from concurrent access. This allows us to avoid two updates from modifying + * the user data in sock and the lock is required anyways for modifying + * callbacks, we simply increase its scope slightly. + * + * Rules to follow, + * - psock must always be read inside RCU critical section + * - sk_user_data must only be modified inside sk_callback_lock and read + * inside RCU critical section. + * - psock->maps list must only be read & modified inside sk_callback_lock + * - sock_map must use READ_ONCE and (cmp)xchg operations + * - BPF verdict/parse programs must use READ_ONCE and xchg operations + */ +static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, + struct bpf_map *map, + void *key, u64 flags) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct smap_psock_map_entry *e = NULL; + struct bpf_prog *verdict, *parse; + struct sock *osock, *sock; + struct smap_psock *psock; + u32 i = *(u32 *)key; + int err; + + if (unlikely(flags > BPF_EXIST)) + return -EINVAL; + + if (unlikely(i >= stab->map.max_entries)) + return -E2BIG; + + sock = READ_ONCE(stab->sock_map[i]); + if (flags == BPF_EXIST && !sock) + return -ENOENT; + else if (flags == BPF_NOEXIST && sock) + return -EEXIST; + + sock = skops->sk; + + /* 1. If sock map has BPF programs those will be inherited by the + * sock being added. If the sock is already attached to BPF programs + * this results in an error. + */ + verdict = READ_ONCE(stab->bpf_verdict); + parse = READ_ONCE(stab->bpf_parse); + + if (parse && verdict) { + /* bpf prog refcnt may be zero if a concurrent attach operation + * removes the program after the above READ_ONCE() but before + * we increment the refcnt. If this is the case abort with an + * error. + */ + verdict = bpf_prog_inc_not_zero(stab->bpf_verdict); + if (IS_ERR(verdict)) + return PTR_ERR(verdict); + + parse = bpf_prog_inc_not_zero(stab->bpf_parse); + if (IS_ERR(parse)) { + bpf_prog_put(verdict); + return PTR_ERR(parse); + } + } + + write_lock_bh(&sock->sk_callback_lock); + psock = smap_psock_sk(sock); + + /* 2. Do not allow inheriting programs if psock exists and has + * already inherited programs. This would create confusion on + * which parser/verdict program is running. If no psock exists + * create one. Inside sk_callback_lock to ensure concurrent create + * doesn't update user data. + */ + if (psock) { + if (READ_ONCE(psock->bpf_parse) && parse) { + err = -EBUSY; + goto out_progs; + } + psock->refcnt++; + } else { + psock = smap_init_psock(sock, stab); + if (IS_ERR(psock)) { + err = PTR_ERR(psock); + goto out_progs; + } + + set_bit(SMAP_TX_RUNNING, &psock->state); + } + + e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); + if (!e) { + err = -ENOMEM; + goto out_progs; + } + e->entry = &stab->sock_map[i]; + + /* 3. At this point we have a reference to a valid psock that is + * running. Attach any BPF programs needed. + */ + if (parse && verdict && !psock->strp_enabled) { + err = smap_init_sock(psock, sock); + if (err) + goto out_free; + smap_init_progs(psock, stab, verdict, parse); + smap_start_sock(psock, sock); + } + + /* 4. Place psock in sockmap for use and stop any programs on + * the old sock assuming its not the same sock we are replacing + * it with. Because we can only have a single set of programs if + * old_sock has a strp we can stop it. + */ + list_add_tail(&e->list, &psock->maps); + write_unlock_bh(&sock->sk_callback_lock); + + osock = xchg(&stab->sock_map[i], sock); + if (osock) { + struct smap_psock *opsock = smap_psock_sk(osock); + + write_lock_bh(&osock->sk_callback_lock); + if (osock != sock && parse) + smap_stop_sock(opsock, osock); + smap_list_remove(opsock, &stab->sock_map[i]); + smap_release_sock(opsock, osock); + write_unlock_bh(&osock->sk_callback_lock); + } + return 0; +out_free: + smap_release_sock(psock, sock); +out_progs: + if (verdict) + bpf_prog_put(verdict); + if (parse) + bpf_prog_put(parse); + write_unlock_bh(&sock->sk_callback_lock); + kfree(e); + return err; +} + +int sock_map_attach_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct bpf_prog *orig; + + if (unlikely(map->map_type != BPF_MAP_TYPE_SOCKMAP)) + return -EINVAL; + + switch (type) { + case BPF_SK_SKB_STREAM_PARSER: + orig = xchg(&stab->bpf_parse, prog); + break; + case BPF_SK_SKB_STREAM_VERDICT: + orig = xchg(&stab->bpf_verdict, prog); + break; + default: + return -EOPNOTSUPP; + } + + if (orig) + bpf_prog_put(orig); + + return 0; +} + +static void *sock_map_lookup(struct bpf_map *map, void *key) +{ + return NULL; +} + +static int sock_map_update_elem(struct bpf_map *map, + void *key, void *value, u64 flags) +{ + struct bpf_sock_ops_kern skops; + u32 fd = *(u32 *)value; + struct socket *socket; + int err; + + socket = sockfd_lookup(fd, &err); + if (!socket) + return err; + + skops.sk = socket->sk; + if (!skops.sk) { + fput(socket->file); + return -EINVAL; + } + + err = sock_map_ctx_update_elem(&skops, map, key, flags); + fput(socket->file); + return err; +} + +const struct bpf_map_ops sock_map_ops = { + .map_alloc = sock_map_alloc, + .map_free = sock_map_free, + .map_lookup_elem = sock_map_lookup, + .map_get_next_key = sock_map_get_next_key, + .map_update_elem = sock_map_update_elem, + .map_delete_elem = sock_map_delete_elem, +}; + +BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, + struct bpf_map *, map, void *, key, u64, flags) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return sock_map_ctx_update_elem(bpf_sock, map, key, flags); +} + +const struct bpf_func_proto bpf_sock_map_update_proto = { + .func = bpf_sock_map_update, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 31147d730abf..135be433e9a0 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -31,7 +31,8 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; int err; - smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries); + smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries, + smap->map.numa_node); if (!smap->elems) return -ENOMEM; @@ -59,7 +60,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (attr->map_flags) + if (attr->map_flags & ~BPF_F_NUMA_NODE) return ERR_PTR(-EINVAL); /* check sanity of attributes */ @@ -75,7 +76,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); - smap = bpf_map_area_alloc(cost); + smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) return ERR_PTR(-ENOMEM); @@ -91,6 +92,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) smap->map.map_flags = attr->map_flags; smap->n_buckets = n_buckets; smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + smap->map.numa_node = bpf_map_attr_numa_node(attr); err = bpf_map_precharge_memlock(smap->map.pages); if (err) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6c772adabad2..70ad8e220343 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -48,6 +48,47 @@ static const struct bpf_map_ops * const bpf_map_types[] = { #undef BPF_MAP_TYPE }; +/* + * If we're handed a bigger struct than we know of, ensure all the unknown bits + * are 0 - i.e. new user-space does not rely on any kernel feature extensions + * we don't know about yet. + * + * There is a ToCToU between this function call and the following + * copy_from_user() call. However, this is not a concern since this function is + * meant to be a future-proofing of bits. + */ +static int check_uarg_tail_zero(void __user *uaddr, + size_t expected_size, + size_t actual_size) +{ + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + int err; + + if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ + return -E2BIG; + + if (unlikely(!access_ok(VERIFY_READ, uaddr, actual_size))) + return -EFAULT; + + if (actual_size <= expected_size) + return 0; + + addr = uaddr + expected_size; + end = uaddr + actual_size; + + for (; addr < end; addr++) { + err = get_user(val, addr); + if (err) + return err; + if (val) + return -E2BIG; + } + + return 0; +} + static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) { struct bpf_map *map; @@ -64,7 +105,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } -void *bpf_map_area_alloc(size_t size) +void *bpf_map_area_alloc(size_t size, int numa_node) { /* We definitely need __GFP_NORETRY, so OOM killer doesn't * trigger under memory pressure as we really just want to @@ -74,12 +115,13 @@ void *bpf_map_area_alloc(size_t size) void *area; if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - area = kmalloc(size, GFP_USER | flags); + area = kmalloc_node(size, GFP_USER | flags, numa_node); if (area != NULL) return area; } - return __vmalloc(size, GFP_KERNEL | flags, PAGE_KERNEL); + return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags, + __builtin_return_address(0)); } void bpf_map_area_free(void *area) @@ -268,10 +310,11 @@ int bpf_map_new_fd(struct bpf_map *map) offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL -#define BPF_MAP_CREATE_LAST_FIELD inner_map_fd +#define BPF_MAP_CREATE_LAST_FIELD numa_node /* called via syscall */ static int map_create(union bpf_attr *attr) { + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_map *map; int err; @@ -279,6 +322,11 @@ static int map_create(union bpf_attr *attr) if (err) return -EINVAL; + if (numa_node != NUMA_NO_NODE && + ((unsigned int)numa_node >= nr_node_ids || + !node_online(numa_node))) + return -EINVAL; + /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ map = find_and_alloc_map(attr); if (IS_ERR(map)) @@ -870,7 +918,7 @@ struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) EXPORT_SYMBOL_GPL(bpf_prog_inc); /* prog_idr_lock should have been held */ -static struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) +struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; @@ -886,6 +934,7 @@ static struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) return prog; } +EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) { @@ -1047,6 +1096,36 @@ static int bpf_obj_get(const union bpf_attr *attr) #define BPF_PROG_ATTACH_LAST_FIELD attach_flags +static int sockmap_get_from_fd(const union bpf_attr *attr) +{ + int ufd = attr->target_fd; + struct bpf_prog *prog; + struct bpf_map *map; + struct fd f; + int err; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + prog = bpf_prog_get_type(attr->attach_bpf_fd, BPF_PROG_TYPE_SK_SKB); + if (IS_ERR(prog)) { + fdput(f); + return PTR_ERR(prog); + } + + err = sock_map_attach_prog(map, prog, attr->attach_type); + if (err) { + fdput(f); + bpf_prog_put(prog); + return err; + } + + fdput(f); + return 0; +} + static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; @@ -1074,6 +1153,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_SOCK_OPS: ptype = BPF_PROG_TYPE_SOCK_OPS; break; + case BPF_SK_SKB_STREAM_PARSER: + case BPF_SK_SKB_STREAM_VERDICT: + return sockmap_get_from_fd(attr); default: return -EINVAL; } @@ -1246,32 +1328,6 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) return fd; } -static int check_uarg_tail_zero(void __user *uaddr, - size_t expected_size, - size_t actual_size) -{ - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - int err; - - if (actual_size <= expected_size) - return 0; - - addr = uaddr + expected_size; - end = uaddr + actual_size; - - for (; addr < end; addr++) { - err = get_user(val, addr); - if (err) - return err; - if (val) - return -E2BIG; - } - - return 0; -} - static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -1393,17 +1449,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled) return -EPERM; - if (!access_ok(VERIFY_READ, uattr, 1)) - return -EFAULT; - - if (size > PAGE_SIZE) /* silly large */ - return -E2BIG; - - /* If we're handed a bigger struct than we know of, - * ensure all the unknown bits are 0 - i.e. new - * user-space does not rely on any kernel feature - * extensions we dont know about yet. - */ err = check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c new file mode 100644 index 000000000000..1f4bf68c12db --- /dev/null +++ b/kernel/bpf/tnum.c @@ -0,0 +1,180 @@ +/* tnum: tracked (or tristate) numbers + * + * A tnum tracks knowledge about the bits of a value. Each bit can be either + * known (0 or 1), or unknown (x). Arithmetic operations on tnums will + * propagate the unknown bits such that the tnum result represents all the + * possible results for possible values of the operands. + */ +#include <linux/kernel.h> +#include <linux/tnum.h> + +#define TNUM(_v, _m) (struct tnum){.value = _v, .mask = _m} +/* A completely unknown value */ +const struct tnum tnum_unknown = { .value = 0, .mask = -1 }; + +struct tnum tnum_const(u64 value) +{ + return TNUM(value, 0); +} + +struct tnum tnum_range(u64 min, u64 max) +{ + u64 chi = min ^ max, delta; + u8 bits = fls64(chi); + + /* special case, needed because 1ULL << 64 is undefined */ + if (bits > 63) + return tnum_unknown; + /* e.g. if chi = 4, bits = 3, delta = (1<<3) - 1 = 7. + * if chi = 0, bits = 0, delta = (1<<0) - 1 = 0, so we return + * constant min (since min == max). + */ + delta = (1ULL << bits) - 1; + return TNUM(min & ~delta, delta); +} + +struct tnum tnum_lshift(struct tnum a, u8 shift) +{ + return TNUM(a.value << shift, a.mask << shift); +} + +struct tnum tnum_rshift(struct tnum a, u8 shift) +{ + return TNUM(a.value >> shift, a.mask >> shift); +} + +struct tnum tnum_add(struct tnum a, struct tnum b) +{ + u64 sm, sv, sigma, chi, mu; + + sm = a.mask + b.mask; + sv = a.value + b.value; + sigma = sm + sv; + chi = sigma ^ sv; + mu = chi | a.mask | b.mask; + return TNUM(sv & ~mu, mu); +} + +struct tnum tnum_sub(struct tnum a, struct tnum b) +{ + u64 dv, alpha, beta, chi, mu; + + dv = a.value - b.value; + alpha = dv + a.mask; + beta = dv - b.mask; + chi = alpha ^ beta; + mu = chi | a.mask | b.mask; + return TNUM(dv & ~mu, mu); +} + +struct tnum tnum_and(struct tnum a, struct tnum b) +{ + u64 alpha, beta, v; + + alpha = a.value | a.mask; + beta = b.value | b.mask; + v = a.value & b.value; + return TNUM(v, alpha & beta & ~v); +} + +struct tnum tnum_or(struct tnum a, struct tnum b) +{ + u64 v, mu; + + v = a.value | b.value; + mu = a.mask | b.mask; + return TNUM(v, mu & ~v); +} + +struct tnum tnum_xor(struct tnum a, struct tnum b) +{ + u64 v, mu; + + v = a.value ^ b.value; + mu = a.mask | b.mask; + return TNUM(v & ~mu, mu); +} + +/* half-multiply add: acc += (unknown * mask * value). + * An intermediate step in the multiply algorithm. + */ +static struct tnum hma(struct tnum acc, u64 value, u64 mask) +{ + while (mask) { + if (mask & 1) + acc = tnum_add(acc, TNUM(0, value)); + mask >>= 1; + value <<= 1; + } + return acc; +} + +struct tnum tnum_mul(struct tnum a, struct tnum b) +{ + struct tnum acc; + u64 pi; + + pi = a.value * b.value; + acc = hma(TNUM(pi, 0), a.mask, b.mask | b.value); + return hma(acc, b.mask, a.value); +} + +/* Note that if a and b disagree - i.e. one has a 'known 1' where the other has + * a 'known 0' - this will return a 'known 1' for that bit. + */ +struct tnum tnum_intersect(struct tnum a, struct tnum b) +{ + u64 v, mu; + + v = a.value | b.value; + mu = a.mask & b.mask; + return TNUM(v & ~mu, mu); +} + +struct tnum tnum_cast(struct tnum a, u8 size) +{ + a.value &= (1ULL << (size * 8)) - 1; + a.mask &= (1ULL << (size * 8)) - 1; + return a; +} + +bool tnum_is_aligned(struct tnum a, u64 size) +{ + if (!size) + return true; + return !((a.value | a.mask) & (size - 1)); +} + +bool tnum_in(struct tnum a, struct tnum b) +{ + if (b.mask & ~a.mask) + return false; + b.value &= ~a.mask; + return a.value == b.value; +} + +int tnum_strn(char *str, size_t size, struct tnum a) +{ + return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); +} +EXPORT_SYMBOL_GPL(tnum_strn); + +int tnum_sbin(char *str, size_t size, struct tnum a) +{ + size_t n; + + for (n = 64; n; n--) { + if (n < size) { + if (a.mask & 1) + str[n - 1] = 'x'; + else if (a.value & 1) + str[n - 1] = '1'; + else + str[n - 1] = '0'; + } + a.mask >>= 1; + a.value >>= 1; + } + str[min(size - 1, (size_t)64)] = 0; + return 64; +} diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 664d93972373..d690c7dd1f1a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -61,12 +61,12 @@ * (and -20 constant is saved for further stack bounds checking). * Meaning that this reg is a pointer to stack plus known immediate constant. * - * Most of the time the registers have UNKNOWN_VALUE type, which + * Most of the time the registers have SCALAR_VALUE type, which * means the register has some value, but it's not a valid pointer. - * (like pointer plus pointer becomes UNKNOWN_VALUE type) + * (like pointer plus pointer becomes SCALAR_VALUE type) * * When verifier sees load or store instructions the type of base register - * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, FRAME_PTR. These are three pointer + * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK. These are three pointer * types recognized by check_mem_access() function. * * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' @@ -140,7 +140,7 @@ struct bpf_verifier_stack_elem { struct bpf_verifier_stack_elem *next; }; -#define BPF_COMPLEXITY_LIMIT_INSNS 98304 +#define BPF_COMPLEXITY_LIMIT_INSNS 131072 #define BPF_COMPLEXITY_LIMIT_STACK 1024 #define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA) @@ -180,15 +180,12 @@ static __printf(1, 2) void verbose(const char *fmt, ...) /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", - [UNKNOWN_VALUE] = "inv", + [SCALAR_VALUE] = "inv", [PTR_TO_CTX] = "ctx", [CONST_PTR_TO_MAP] = "map_ptr", [PTR_TO_MAP_VALUE] = "map_value", [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", - [PTR_TO_MAP_VALUE_ADJ] = "map_value_adj", - [FRAME_PTR] = "fp", [PTR_TO_STACK] = "fp", - [CONST_IMM] = "imm", [PTR_TO_PACKET] = "pkt", [PTR_TO_PACKET_END] = "pkt_end", }; @@ -221,32 +218,52 @@ static void print_verifier_state(struct bpf_verifier_state *state) if (t == NOT_INIT) continue; verbose(" R%d=%s", i, reg_type_str[t]); - if (t == CONST_IMM || t == PTR_TO_STACK) - verbose("%lld", reg->imm); - else if (t == PTR_TO_PACKET) - verbose("(id=%d,off=%d,r=%d)", - reg->id, reg->off, reg->range); - else if (t == UNKNOWN_VALUE && reg->imm) - verbose("%lld", reg->imm); - else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || - t == PTR_TO_MAP_VALUE_OR_NULL || - t == PTR_TO_MAP_VALUE_ADJ) - verbose("(ks=%d,vs=%d,id=%u)", - reg->map_ptr->key_size, - reg->map_ptr->value_size, - reg->id); - if (reg->min_value != BPF_REGISTER_MIN_RANGE) - verbose(",min_value=%lld", - (long long)reg->min_value); - if (reg->max_value != BPF_REGISTER_MAX_RANGE) - verbose(",max_value=%llu", - (unsigned long long)reg->max_value); - if (reg->min_align) - verbose(",min_align=%u", reg->min_align); - if (reg->aux_off) - verbose(",aux_off=%u", reg->aux_off); - if (reg->aux_off_align) - verbose(",aux_off_align=%u", reg->aux_off_align); + if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && + tnum_is_const(reg->var_off)) { + /* reg->off should be 0 for SCALAR_VALUE */ + verbose("%lld", reg->var_off.value + reg->off); + } else { + verbose("(id=%d", reg->id); + if (t != SCALAR_VALUE) + verbose(",off=%d", reg->off); + if (t == PTR_TO_PACKET) + verbose(",r=%d", reg->range); + else if (t == CONST_PTR_TO_MAP || + t == PTR_TO_MAP_VALUE || + t == PTR_TO_MAP_VALUE_OR_NULL) + verbose(",ks=%d,vs=%d", + reg->map_ptr->key_size, + reg->map_ptr->value_size); + if (tnum_is_const(reg->var_off)) { + /* Typically an immediate SCALAR_VALUE, but + * could be a pointer whose offset is too big + * for reg->off + */ + verbose(",imm=%llx", reg->var_off.value); + } else { + if (reg->smin_value != reg->umin_value && + reg->smin_value != S64_MIN) + verbose(",smin_value=%lld", + (long long)reg->smin_value); + if (reg->smax_value != reg->umax_value && + reg->smax_value != S64_MAX) + verbose(",smax_value=%lld", + (long long)reg->smax_value); + if (reg->umin_value != 0) + verbose(",umin_value=%llu", + (unsigned long long)reg->umin_value); + if (reg->umax_value != U64_MAX) + verbose(",umax_value=%llu", + (unsigned long long)reg->umax_value); + if (!tnum_is_unknown(reg->var_off)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(",var_off=%s", tn_buf); + } + } + verbose(")"); + } } for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] == STACK_SPILL) @@ -295,11 +312,15 @@ static const char *const bpf_jmp_string[16] = { [BPF_JA >> 4] = "jmp", [BPF_JEQ >> 4] = "==", [BPF_JGT >> 4] = ">", + [BPF_JLT >> 4] = "<", [BPF_JGE >> 4] = ">=", + [BPF_JLE >> 4] = "<=", [BPF_JSET >> 4] = "&", [BPF_JNE >> 4] = "!=", [BPF_JSGT >> 4] = "s>", + [BPF_JSLT >> 4] = "s<", [BPF_JSGE >> 4] = "s>=", + [BPF_JSLE >> 4] = "s<=", [BPF_CALL >> 4] = "call", [BPF_EXIT >> 4] = "exit", }; @@ -463,56 +484,163 @@ static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno) +static void __mark_reg_not_init(struct bpf_reg_state *reg); + +/* Mark the unknown part of a register (variable offset or scalar value) as + * known to have the value @imm. + */ +static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) { - BUG_ON(regno >= MAX_BPF_REG); + reg->id = 0; + reg->var_off = tnum_const(imm); + reg->smin_value = (s64)imm; + reg->smax_value = (s64)imm; + reg->umin_value = imm; + reg->umax_value = imm; +} - memset(®s[regno], 0, sizeof(regs[regno])); - regs[regno].type = NOT_INIT; - regs[regno].min_value = BPF_REGISTER_MIN_RANGE; - regs[regno].max_value = BPF_REGISTER_MAX_RANGE; +/* Mark the 'variable offset' part of a register as zero. This should be + * used only on registers holding a pointer type. + */ +static void __mark_reg_known_zero(struct bpf_reg_state *reg) +{ + __mark_reg_known(reg, 0); } -static void init_reg_state(struct bpf_reg_state *regs) +static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno) { - int i; + if (WARN_ON(regno >= MAX_BPF_REG)) { + verbose("mark_reg_known_zero(regs, %u)\n", regno); + /* Something bad happened, let's kill all regs */ + for (regno = 0; regno < MAX_BPF_REG; regno++) + __mark_reg_not_init(regs + regno); + return; + } + __mark_reg_known_zero(regs + regno); +} - for (i = 0; i < MAX_BPF_REG; i++) - mark_reg_not_init(regs, i); +/* Attempts to improve min/max values based on var_off information */ +static void __update_reg_bounds(struct bpf_reg_state *reg) +{ + /* min signed is max(sign bit) | min(other bits) */ + reg->smin_value = max_t(s64, reg->smin_value, + reg->var_off.value | (reg->var_off.mask & S64_MIN)); + /* max signed is min(sign bit) | max(other bits) */ + reg->smax_value = min_t(s64, reg->smax_value, + reg->var_off.value | (reg->var_off.mask & S64_MAX)); + reg->umin_value = max(reg->umin_value, reg->var_off.value); + reg->umax_value = min(reg->umax_value, + reg->var_off.value | reg->var_off.mask); +} - /* frame pointer */ - regs[BPF_REG_FP].type = FRAME_PTR; +/* Uses signed min/max values to inform unsigned, and vice-versa */ +static void __reg_deduce_bounds(struct bpf_reg_state *reg) +{ + /* Learn sign from signed bounds. + * If we cannot cross the sign boundary, then signed and unsigned bounds + * are the same, so combine. This works even in the negative case, e.g. + * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. + */ + if (reg->smin_value >= 0 || reg->smax_value < 0) { + reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, + reg->umin_value); + reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, + reg->umax_value); + return; + } + /* Learn sign from unsigned bounds. Signed bounds cross the sign + * boundary, so we must be careful. + */ + if ((s64)reg->umax_value >= 0) { + /* Positive. We can't learn anything from the smin, but smax + * is positive, hence safe. + */ + reg->smin_value = reg->umin_value; + reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, + reg->umax_value); + } else if ((s64)reg->umin_value < 0) { + /* Negative. We can't learn anything from the smax, but smin + * is negative, hence safe. + */ + reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, + reg->umin_value); + reg->smax_value = reg->umax_value; + } +} - /* 1st arg to a function */ - regs[BPF_REG_1].type = PTR_TO_CTX; +/* Attempts to improve var_off based on unsigned min/max information */ +static void __reg_bound_offset(struct bpf_reg_state *reg) +{ + reg->var_off = tnum_intersect(reg->var_off, + tnum_range(reg->umin_value, + reg->umax_value)); } -static void __mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno) +/* Reset the min/max bounds of a register */ +static void __mark_reg_unbounded(struct bpf_reg_state *reg) { - regs[regno].type = UNKNOWN_VALUE; - regs[regno].id = 0; - regs[regno].imm = 0; + reg->smin_value = S64_MIN; + reg->smax_value = S64_MAX; + reg->umin_value = 0; + reg->umax_value = U64_MAX; } -static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno) +/* Mark a register as having a completely unknown (scalar) value. */ +static void __mark_reg_unknown(struct bpf_reg_state *reg) { - BUG_ON(regno >= MAX_BPF_REG); - __mark_reg_unknown_value(regs, regno); + reg->type = SCALAR_VALUE; + reg->id = 0; + reg->off = 0; + reg->var_off = tnum_unknown; + __mark_reg_unbounded(reg); } -static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno) +static void mark_reg_unknown(struct bpf_reg_state *regs, u32 regno) { - regs[regno].min_value = BPF_REGISTER_MIN_RANGE; - regs[regno].max_value = BPF_REGISTER_MAX_RANGE; - regs[regno].value_from_signed = false; - regs[regno].min_align = 0; + if (WARN_ON(regno >= MAX_BPF_REG)) { + verbose("mark_reg_unknown(regs, %u)\n", regno); + /* Something bad happened, let's kill all regs */ + for (regno = 0; regno < MAX_BPF_REG; regno++) + __mark_reg_not_init(regs + regno); + return; + } + __mark_reg_unknown(regs + regno); } -static void mark_reg_unknown_value_and_range(struct bpf_reg_state *regs, - u32 regno) +static void __mark_reg_not_init(struct bpf_reg_state *reg) +{ + __mark_reg_unknown(reg); + reg->type = NOT_INIT; +} + +static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno) { - mark_reg_unknown_value(regs, regno); - reset_reg_range_values(regs, regno); + if (WARN_ON(regno >= MAX_BPF_REG)) { + verbose("mark_reg_not_init(regs, %u)\n", regno); + /* Something bad happened, let's kill all regs */ + for (regno = 0; regno < MAX_BPF_REG; regno++) + __mark_reg_not_init(regs + regno); + return; + } + __mark_reg_not_init(regs + regno); +} + +static void init_reg_state(struct bpf_reg_state *regs) +{ + int i; + + for (i = 0; i < MAX_BPF_REG; i++) { + mark_reg_not_init(regs, i); + regs[i].live = REG_LIVE_NONE; + } + + /* frame pointer */ + regs[BPF_REG_FP].type = PTR_TO_STACK; + mark_reg_known_zero(regs, BPF_REG_FP); + + /* 1st arg to a function */ + regs[BPF_REG_1].type = PTR_TO_CTX; + mark_reg_known_zero(regs, BPF_REG_1); } enum reg_arg_type { @@ -521,9 +649,26 @@ enum reg_arg_type { DST_OP_NO_MARK /* same as above, check only, don't mark */ }; -static int check_reg_arg(struct bpf_reg_state *regs, u32 regno, +static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno) +{ + struct bpf_verifier_state *parent = state->parent; + + while (parent) { + /* if read wasn't screened by an earlier write ... */ + if (state->regs[regno].live & REG_LIVE_WRITTEN) + break; + /* ... then we depend on parent's value */ + parent->regs[regno].live |= REG_LIVE_READ; + state = parent; + parent = state->parent; + } +} + +static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, enum reg_arg_type t) { + struct bpf_reg_state *regs = env->cur_state.regs; + if (regno >= MAX_BPF_REG) { verbose("R%d is invalid\n", regno); return -EINVAL; @@ -535,14 +680,16 @@ static int check_reg_arg(struct bpf_reg_state *regs, u32 regno, verbose("R%d !read_ok\n", regno); return -EACCES; } + mark_reg_read(&env->cur_state, regno); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { verbose("frame pointer is read only\n"); return -EACCES; } + regs[regno].live |= REG_LIVE_WRITTEN; if (t == DST_OP) - mark_reg_unknown_value(regs, regno); + mark_reg_unknown(regs, regno); } return 0; } @@ -552,12 +699,10 @@ static bool is_spillable_regtype(enum bpf_reg_type type) switch (type) { case PTR_TO_MAP_VALUE: case PTR_TO_MAP_VALUE_OR_NULL: - case PTR_TO_MAP_VALUE_ADJ: case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: case PTR_TO_PACKET_END: - case FRAME_PTR: case CONST_PTR_TO_MAP: return true; default: @@ -571,7 +716,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) static int check_stack_write(struct bpf_verifier_state *state, int off, int size, int value_regno) { - int i; + int i, spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, * so it's aligned access and [off, off + size) are within stack limits */ @@ -586,15 +731,14 @@ static int check_stack_write(struct bpf_verifier_state *state, int off, } /* save register state */ - state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] = - state->regs[value_regno]; + state->spilled_regs[spi] = state->regs[value_regno]; + state->spilled_regs[spi].live |= REG_LIVE_WRITTEN; for (i = 0; i < BPF_REG_SIZE; i++) state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL; } else { /* regular write of data into stack */ - state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] = - (struct bpf_reg_state) {}; + state->spilled_regs[spi] = (struct bpf_reg_state) {}; for (i = 0; i < size; i++) state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC; @@ -602,11 +746,26 @@ static int check_stack_write(struct bpf_verifier_state *state, int off, return 0; } +static void mark_stack_slot_read(const struct bpf_verifier_state *state, int slot) +{ + struct bpf_verifier_state *parent = state->parent; + + while (parent) { + /* if read wasn't screened by an earlier write ... */ + if (state->spilled_regs[slot].live & REG_LIVE_WRITTEN) + break; + /* ... then we depend on parent's value */ + parent->spilled_regs[slot].live |= REG_LIVE_READ; + state = parent; + parent = state->parent; + } +} + static int check_stack_read(struct bpf_verifier_state *state, int off, int size, int value_regno) { u8 *slot_type; - int i; + int i, spi; slot_type = &state->stack_slot_type[MAX_BPF_STACK + off]; @@ -622,10 +781,13 @@ static int check_stack_read(struct bpf_verifier_state *state, int off, int size, } } - if (value_regno >= 0) + spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE; + + if (value_regno >= 0) { /* restore register state from stack */ - state->regs[value_regno] = - state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE]; + state->regs[value_regno] = state->spilled_regs[spi]; + mark_stack_slot_read(state, spi); + } return 0; } else { for (i = 0; i < size; i++) { @@ -637,14 +799,13 @@ static int check_stack_read(struct bpf_verifier_state *state, int off, int size, } if (value_regno >= 0) /* have read misc data from the stack */ - mark_reg_unknown_value_and_range(state->regs, - value_regno); + mark_reg_unknown(state->regs, value_regno); 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, +static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size) { struct bpf_map *map = env->cur_state.regs[regno].map_ptr; @@ -657,49 +818,50 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off, return 0; } -/* check read/write into an adjusted map element */ -static int check_map_access_adj(struct bpf_verifier_env *env, u32 regno, +/* check read/write into a map element with possible variable offset */ +static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size) { struct bpf_verifier_state *state = &env->cur_state; struct bpf_reg_state *reg = &state->regs[regno]; int err; - /* We adjusted the register to this map value, so we - * need to change off and size to min_value and max_value - * respectively to make sure our theoretical access will be - * safe. + /* We may have adjusted the register to this map value, so we + * need to try adding each of min_value and max_value to off + * to make sure our theoretical access will be safe. */ if (log_level) print_verifier_state(state); - env->varlen_map_value_access = true; /* 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->min_value < 0) { + if (reg->smin_value < 0) { verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } - err = check_map_access(env, regno, reg->min_value + off, size); + err = __check_map_access(env, regno, reg->smin_value + off, size); if (err) { - verbose("R%d min value is outside of the array range\n", - regno); + verbose("R%d min value is outside of the array range\n", regno); return err; } - /* If we haven't set a max value then we need to bail - * since we can't be sure we won't do bad things. + /* If we haven't set a max value then we need to bail since we can't be + * sure we won't do bad things. + * If reg->umax_value + off could overflow, treat that as unbounded too. */ - if (reg->max_value == BPF_REGISTER_MAX_RANGE) { + if (reg->umax_value >= BPF_MAX_VAR_OFF) { verbose("R%d unbounded memory access, make sure to bounds check any array access into a map\n", regno); return -EACCES; } - return check_map_access(env, regno, reg->max_value + off, size); + err = __check_map_access(env, regno, reg->umax_value + off, size); + if (err) + verbose("R%d max value is outside of the array range\n", regno); + return err; } #define MAX_PACKET_OFF 0xffff @@ -719,6 +881,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_XMIT: + case BPF_PROG_TYPE_SK_SKB: if (meta) return meta->pkt_access; @@ -729,14 +892,13 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, } } -static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, - int size) +static int __check_packet_access(struct bpf_verifier_env *env, u32 regno, + int off, int size) { struct bpf_reg_state *regs = env->cur_state.regs; struct bpf_reg_state *reg = ®s[regno]; - off += reg->off; - if (off < 0 || size <= 0 || off + size > reg->range) { + if (off < 0 || size <= 0 || (u64)off + size > reg->range) { verbose("invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", off, size, regno, reg->id, reg->off, reg->range); return -EACCES; @@ -744,7 +906,35 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, return 0; } -/* check access to 'struct bpf_context' fields */ +static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, + int size) +{ + struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *reg = ®s[regno]; + int err; + + /* We may have added a variable offset to the packet pointer; but any + * reg->range we have comes after that. We are only checking the fixed + * offset. + */ + + /* We don't allow negative numbers, because we aren't tracking enough + * detail to prove they're safe. + */ + if (reg->smin_value < 0) { + verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + regno); + return -EACCES; + } + err = __check_packet_access(env, regno, off, size); + if (err) { + verbose("R%d offset is outside of the packet\n", regno); + return err; + } + return err; +} + +/* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type) { @@ -784,13 +974,7 @@ static bool __is_pointer_value(bool allow_ptr_leaks, if (allow_ptr_leaks) return false; - switch (reg->type) { - case UNKNOWN_VALUE: - case CONST_IMM: - return false; - default: - return true; - } + return reg->type != SCALAR_VALUE; } static bool is_pointer_value(struct bpf_verifier_env *env, int regno) @@ -801,23 +985,13 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, int off, int size, bool strict) { + struct tnum reg_off; int ip_align; - int reg_off; /* Byte size accesses are always allowed. */ if (!strict || size == 1) return 0; - reg_off = reg->off; - if (reg->id) { - if (reg->aux_off_align % size) { - verbose("Packet access is only %u byte aligned, %d byte access not allowed\n", - reg->aux_off_align, size); - return -EACCES; - } - reg_off += reg->aux_off; - } - /* For platforms that do not have a Kconfig enabling * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of * NET_IP_ALIGN is universally set to '2'. And on platforms @@ -827,20 +1001,37 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, * unconditional IP align value of '2'. */ ip_align = 2; - if ((ip_align + reg_off + off) % size != 0) { - verbose("misaligned packet access off %d+%d+%d size %d\n", - ip_align, reg_off, off, size); + + reg_off = tnum_add(reg->var_off, tnum_const(ip_align + reg->off + off)); + if (!tnum_is_aligned(reg_off, size)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose("misaligned packet access off %d+%s+%d+%d size %d\n", + ip_align, tn_buf, reg->off, off, size); return -EACCES; } return 0; } -static int check_val_ptr_alignment(const struct bpf_reg_state *reg, - int size, bool strict) +static int check_generic_ptr_alignment(const struct bpf_reg_state *reg, + const char *pointer_desc, + int off, int size, bool strict) { - if (strict && size != 1) { - verbose("Unknown alignment. Only byte-sized access allowed in value access.\n"); + struct tnum reg_off; + + /* Byte size accesses are always allowed. */ + if (!strict || size == 1) + return 0; + + reg_off = tnum_add(reg->var_off, tnum_const(reg->off + off)); + if (!tnum_is_aligned(reg_off, size)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose("misaligned %saccess off %s+%d+%d size %d\n", + pointer_desc, tn_buf, reg->off, off, size); return -EACCES; } @@ -852,21 +1043,25 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, int off, int size) { bool strict = env->strict_alignment; + const char *pointer_desc = ""; switch (reg->type) { case PTR_TO_PACKET: + /* special case, because of NET_IP_ALIGN */ return check_pkt_ptr_alignment(reg, off, size, strict); - case PTR_TO_MAP_VALUE_ADJ: - return check_val_ptr_alignment(reg, size, strict); + case PTR_TO_MAP_VALUE: + pointer_desc = "value "; + break; + case PTR_TO_CTX: + pointer_desc = "context "; + break; + case PTR_TO_STACK: + pointer_desc = "stack "; + break; default: - if (off % size != 0) { - verbose("misaligned access off %d size %d\n", - off, size); - return -EACCES; - } - - return 0; + break; } + return check_generic_ptr_alignment(reg, pointer_desc, off, size, strict); } /* check whether memory at (regno + off) is accessible for t = (read | write) @@ -883,52 +1078,79 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn struct bpf_reg_state *reg = &state->regs[regno]; int size, err = 0; - if (reg->type == PTR_TO_STACK) - off += reg->imm; - size = bpf_size_to_bytes(bpf_size); if (size < 0) return size; + /* alignment checks will add in reg->off themselves */ err = check_ptr_alignment(env, reg, off, size); if (err) return err; - if (reg->type == PTR_TO_MAP_VALUE || - reg->type == PTR_TO_MAP_VALUE_ADJ) { + /* for access checks, reg->off is just part of off */ + off += reg->off; + + if (reg->type == PTR_TO_MAP_VALUE) { if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose("R%d leaks addr into map\n", value_regno); return -EACCES; } - if (reg->type == PTR_TO_MAP_VALUE_ADJ) - err = check_map_access_adj(env, regno, off, size); - else - err = check_map_access(env, regno, off, size); + err = check_map_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) - mark_reg_unknown_value_and_range(state->regs, - value_regno); + mark_reg_unknown(state->regs, value_regno); } else if (reg->type == PTR_TO_CTX) { - enum bpf_reg_type reg_type = UNKNOWN_VALUE; + enum bpf_reg_type reg_type = SCALAR_VALUE; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose("R%d leaks addr into ctx\n", value_regno); return -EACCES; } + /* ctx accesses must be at a fixed offset, so that we can + * determine what type of data were returned. + */ + if (!tnum_is_const(reg->var_off)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose("variable ctx access var_off=%s off=%d size=%d", + tn_buf, off, size); + return -EACCES; + } + off += reg->var_off.value; err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { - mark_reg_unknown_value_and_range(state->regs, - value_regno); - /* note that reg.[id|off|range] == 0 */ + /* ctx access returns either a scalar, or a + * PTR_TO_PACKET[_END]. In the latter case, we know + * the offset is zero. + */ + if (reg_type == SCALAR_VALUE) + mark_reg_unknown(state->regs, value_regno); + else + mark_reg_known_zero(state->regs, value_regno); + state->regs[value_regno].id = 0; + state->regs[value_regno].off = 0; + state->regs[value_regno].range = 0; state->regs[value_regno].type = reg_type; - state->regs[value_regno].aux_off = 0; - state->regs[value_regno].aux_off_align = 0; } - } else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) { + } 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("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("invalid stack off=%d size=%d\n", off, size); return -EACCES; @@ -948,7 +1170,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else { err = check_stack_read(state, off, size, value_regno); } - } else if (state->regs[regno].type == PTR_TO_PACKET) { + } else if (reg->type == PTR_TO_PACKET) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose("cannot write into packet\n"); return -EACCES; @@ -960,28 +1182,25 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } err = check_packet_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) - mark_reg_unknown_value_and_range(state->regs, - value_regno); + mark_reg_unknown(state->regs, value_regno); } else { verbose("R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); return -EACCES; } - if (!err && size <= 2 && value_regno >= 0 && env->allow_ptr_leaks && - state->regs[value_regno].type == UNKNOWN_VALUE) { - /* 1 or 2 byte load zero-extends, determine the number of - * zero upper bits. Not doing it fo 4 byte load, since - * such values cannot be added to ptr_to_packet anyway. - */ - state->regs[value_regno].imm = 64 - size * 8; + if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ && + state->regs[value_regno].type == SCALAR_VALUE) { + /* b/h/w load zero-extends, mark upper bits as known 0 */ + state->regs[value_regno].var_off = tnum_cast( + state->regs[value_regno].var_off, size); + __update_reg_bounds(&state->regs[value_regno]); } return err; } static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) { - struct bpf_reg_state *regs = env->cur_state.regs; int err; if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) || @@ -991,12 +1210,12 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins } /* check src1 operand */ - err = check_reg_arg(regs, insn->src_reg, SRC_OP); + err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check src2 operand */ - err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; @@ -1016,9 +1235,17 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins BPF_SIZE(insn->code), BPF_WRITE, -1); } +/* Does this register contain a constant zero? */ +static bool register_is_null(struct bpf_reg_state reg) +{ + return reg.type == SCALAR_VALUE && tnum_equals_const(reg.var_off, 0); +} + /* when register 'regno' is passed into function that will read 'access_size' * bytes from that pointer, make sure that it's within stack boundary - * and all elements of stack are initialized + * and all elements of stack are initialized. + * Unlike most pointer bounds-checking functions, this one doesn't take an + * 'off' argument, so it has to add in reg->off itself. */ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, int access_size, bool zero_size_allowed, @@ -1029,9 +1256,9 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, int off, i; if (regs[regno].type != PTR_TO_STACK) { + /* Allow zero-byte read from NULL, regardless of pointer type */ if (zero_size_allowed && access_size == 0 && - regs[regno].type == CONST_IMM && - regs[regno].imm == 0) + register_is_null(regs[regno])) return 0; verbose("R%d type=%s expected=%s\n", regno, @@ -1040,7 +1267,15 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, return -EACCES; } - off = regs[regno].imm; + /* Only allow fixed-offset stack reads */ + if (!tnum_is_const(regs[regno].var_off)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), regs[regno].var_off); + verbose("invalid variable stack read R%d var_off=%s\n", + regno, tn_buf); + } + off = regs[regno].off + regs[regno].var_off.value; if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || access_size <= 0) { verbose("invalid stack type R%d off=%d access_size=%d\n", @@ -1071,16 +1306,14 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, int access_size, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { - struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = env->cur_state.regs, *reg = ®s[regno]; - switch (regs[regno].type) { + switch (reg->type) { case PTR_TO_PACKET: - return check_packet_access(env, regno, 0, access_size); + return check_packet_access(env, regno, reg->off, access_size); case PTR_TO_MAP_VALUE: - return check_map_access(env, regno, 0, access_size); - case PTR_TO_MAP_VALUE_ADJ: - return check_map_access_adj(env, regno, 0, access_size); - default: /* const_imm|ptr_to_stack or invalid ptr */ + return check_map_access(env, regno, reg->off, access_size); + default: /* scalar_value|ptr_to_stack or invalid ptr */ return check_stack_boundary(env, regno, access_size, zero_size_allowed, meta); } @@ -1097,10 +1330,9 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_DONTCARE) return 0; - if (type == NOT_INIT) { - verbose("R%d !read_ok\n", regno); - return -EACCES; - } + err = check_reg_arg(env, regno, SRC_OP); + if (err) + return err; if (arg_type == ARG_ANYTHING) { if (is_pointer_value(env, regno)) { @@ -1123,11 +1355,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO) { - expected_type = CONST_IMM; - /* One exception. Allow UNKNOWN_VALUE registers when the - * boundaries are known and don't cause unsafe memory accesses - */ - if (type != UNKNOWN_VALUE && type != expected_type) + expected_type = SCALAR_VALUE; + if (type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_MAP_PTR) { expected_type = CONST_PTR_TO_MAP; @@ -1141,13 +1370,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, arg_type == ARG_PTR_TO_UNINIT_MEM) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be - * passed in as argument, it's a CONST_IMM type. Final test + * passed in as argument, it's a SCALAR_VALUE type. Final test * happens during stack boundary checking. */ - if (type == CONST_IMM && reg->imm == 0) + if (register_is_null(*reg)) /* final test in check_stack_boundary() */; else if (type != PTR_TO_PACKET && type != PTR_TO_MAP_VALUE && - type != PTR_TO_MAP_VALUE_ADJ && type != expected_type) + type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; } else { @@ -1173,7 +1402,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return -EACCES; } if (type == PTR_TO_PACKET) - err = check_packet_access(env, regno, 0, + err = check_packet_access(env, regno, reg->off, meta->map_ptr->key_size); else err = check_stack_boundary(env, regno, @@ -1189,7 +1418,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return -EACCES; } if (type == PTR_TO_PACKET) - err = check_packet_access(env, regno, 0, + err = check_packet_access(env, regno, reg->off, meta->map_ptr->value_size); else err = check_stack_boundary(env, regno, @@ -1209,10 +1438,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return -EACCES; } - /* If the register is UNKNOWN_VALUE, the access check happens - * using its boundaries. Otherwise, just use its imm + /* The register is SCALAR_VALUE; the access check + * happens using its boundaries. */ - if (type == UNKNOWN_VALUE) { + + if (!tnum_is_const(reg->var_off)) /* For unprivileged variable accesses, disable raw * mode so that the program is required to * initialize all the memory that the helper could @@ -1220,35 +1450,28 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ meta = NULL; - if (reg->min_value < 0) { - verbose("R%d min value is negative, either use unsigned or 'var &= const'\n", - regno); - return -EACCES; - } - - if (reg->min_value == 0) { - err = check_helper_mem_access(env, regno - 1, 0, - zero_size_allowed, - meta); - if (err) - return err; - } + if (reg->smin_value < 0) { + verbose("R%d min value is negative, either use unsigned or 'var &= const'\n", + regno); + return -EACCES; + } - if (reg->max_value == BPF_REGISTER_MAX_RANGE) { - verbose("R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", - regno); - return -EACCES; - } - err = check_helper_mem_access(env, regno - 1, - reg->max_value, - zero_size_allowed, meta); + if (reg->umin_value == 0) { + err = check_helper_mem_access(env, regno - 1, 0, + zero_size_allowed, + meta); if (err) return err; - } else { - /* register is CONST_IMM */ - err = check_helper_mem_access(env, regno - 1, reg->imm, - zero_size_allowed, meta); } + + if (reg->umax_value >= BPF_MAX_VAR_SIZ) { + verbose("R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", + regno); + return -EACCES; + } + err = check_helper_mem_access(env, regno - 1, + reg->umax_value, + zero_size_allowed, meta); } return err; @@ -1283,10 +1506,25 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) func_id != BPF_FUNC_current_task_under_cgroup) goto error; break; + /* devmap returns a pointer to a live net_device ifindex that we cannot + * allow to be modified from bpf side. So do not allow lookup elements + * for now. + */ + case BPF_MAP_TYPE_DEVMAP: + if (func_id != BPF_FUNC_redirect_map) + goto error; + break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) goto error; + break; + case BPF_MAP_TYPE_SOCKMAP: + if (func_id != BPF_FUNC_sk_redirect_map && + func_id != BPF_FUNC_sock_map_update && + func_id != BPF_FUNC_map_delete_elem) + goto error; + break; default: break; } @@ -1311,6 +1549,18 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) goto error; break; + case BPF_FUNC_redirect_map: + if (map->map_type != BPF_MAP_TYPE_DEVMAP) + goto error; + break; + case BPF_FUNC_sk_redirect_map: + if (map->map_type != BPF_MAP_TYPE_SOCKMAP) + goto error; + break; + case BPF_FUNC_sock_map_update: + if (map->map_type != BPF_MAP_TYPE_SOCKMAP) + goto error; + break; default: break; } @@ -1340,6 +1590,9 @@ static int check_raw_mode(const struct bpf_func_proto *fn) return count > 1 ? -EINVAL : 0; } +/* Packet data might have moved, any old PTR_TO_PACKET[_END] are now invalid, + * so turn them into unknown SCALAR_VALUE. + */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { struct bpf_verifier_state *state = &env->cur_state; @@ -1349,7 +1602,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) for (i = 0; i < MAX_BPF_REG; i++) if (regs[i].type == PTR_TO_PACKET || regs[i].type == PTR_TO_PACKET_END) - mark_reg_unknown_value(regs, i); + mark_reg_unknown(regs, i); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) @@ -1358,8 +1611,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) if (reg->type != PTR_TO_PACKET && reg->type != PTR_TO_PACKET_END) continue; - __mark_reg_unknown_value(state->spilled_regs, - i / BPF_REG_SIZE); + __mark_reg_unknown(reg); } } @@ -1434,19 +1686,24 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) } /* reset caller saved regs */ - for (i = 0; i < CALLER_SAVED_REGS; i++) + for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(regs, caller_saved[i]); + check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); + } - /* update return register */ + /* update return register (already marked as written above) */ if (fn->ret_type == RET_INTEGER) { - regs[BPF_REG_0].type = UNKNOWN_VALUE; + /* sets type to SCALAR_VALUE */ + mark_reg_unknown(regs, BPF_REG_0); } else if (fn->ret_type == RET_VOID) { regs[BPF_REG_0].type = NOT_INIT; } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) { struct bpf_insn_aux_data *insn_aux; regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; - regs[BPF_REG_0].max_value = regs[BPF_REG_0].min_value = 0; + /* There is no offset yet applied, variable or fixed */ + mark_reg_known_zero(regs, BPF_REG_0); + regs[BPF_REG_0].off = 0; /* remember map_ptr, so that check_map_access() * can check 'value_size' boundary of memory access * to map element returned from bpf_map_lookup_elem() @@ -1477,494 +1734,551 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) return 0; } -static int check_packet_ptr_add(struct bpf_verifier_env *env, - struct bpf_insn *insn) +static void coerce_reg_to_32(struct bpf_reg_state *reg) { - struct bpf_reg_state *regs = env->cur_state.regs; - struct bpf_reg_state *dst_reg = ®s[insn->dst_reg]; - struct bpf_reg_state *src_reg = ®s[insn->src_reg]; - struct bpf_reg_state tmp_reg; - s32 imm; - - if (BPF_SRC(insn->code) == BPF_K) { - /* pkt_ptr += imm */ - imm = insn->imm; - -add_imm: - if (imm < 0) { - verbose("addition of negative constant to packet pointer is not allowed\n"); - return -EACCES; - } - if (imm >= MAX_PACKET_OFF || - imm + dst_reg->off >= MAX_PACKET_OFF) { - verbose("constant %d is too large to add to packet pointer\n", - imm); - return -EACCES; - } - /* a constant was added to pkt_ptr. - * Remember it while keeping the same 'id' - */ - dst_reg->off += imm; - } else { - bool had_id; - - if (src_reg->type == PTR_TO_PACKET) { - /* R6=pkt(id=0,off=0,r=62) R7=imm22; r7 += r6 */ - tmp_reg = *dst_reg; /* save r7 state */ - *dst_reg = *src_reg; /* copy pkt_ptr state r6 into r7 */ - src_reg = &tmp_reg; /* pretend it's src_reg state */ - /* if the checks below reject it, the copy won't matter, - * since we're rejecting the whole program. If all ok, - * then imm22 state will be added to r7 - * and r7 will be pkt(id=0,off=22,r=62) while - * r6 will stay as pkt(id=0,off=0,r=62) - */ - } + /* clear high 32 bits */ + reg->var_off = tnum_cast(reg->var_off, 4); + /* Update bounds */ + __update_reg_bounds(reg); +} - if (src_reg->type == CONST_IMM) { - /* pkt_ptr += reg where reg is known constant */ - imm = src_reg->imm; - goto add_imm; - } - /* disallow pkt_ptr += reg - * if reg is not uknown_value with guaranteed zero upper bits - * otherwise pkt_ptr may overflow and addition will become - * subtraction which is not allowed - */ - if (src_reg->type != UNKNOWN_VALUE) { - verbose("cannot add '%s' to ptr_to_packet\n", - reg_type_str[src_reg->type]); - return -EACCES; - } - if (src_reg->imm < 48) { - verbose("cannot add integer value with %lld upper zero bits to ptr_to_packet\n", - src_reg->imm); - return -EACCES; - } +static bool signed_add_overflows(s64 a, s64 b) +{ + /* Do the add in u64, where overflow is well-defined */ + s64 res = (s64)((u64)a + (u64)b); - had_id = (dst_reg->id != 0); + if (b < 0) + return res > a; + return res < a; +} - /* dst_reg stays as pkt_ptr type and since some positive - * integer value was added to the pointer, increment its 'id' - */ - dst_reg->id = ++env->id_gen; - - /* something was added to pkt_ptr, set range to zero */ - dst_reg->aux_off += dst_reg->off; - dst_reg->off = 0; - dst_reg->range = 0; - if (had_id) - dst_reg->aux_off_align = min(dst_reg->aux_off_align, - src_reg->min_align); - else - dst_reg->aux_off_align = src_reg->min_align; - } - return 0; +static bool signed_sub_overflows(s64 a, s64 b) +{ + /* Do the sub in u64, where overflow is well-defined */ + s64 res = (s64)((u64)a - (u64)b); + + if (b < 0) + return res < a; + return res > a; } -static int evaluate_reg_alu(struct bpf_verifier_env *env, struct bpf_insn *insn) +/* 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 + * scalar. So we only emit a diagnostic if !env->allow_ptr_leaks. + */ +static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, + struct bpf_insn *insn, + const struct bpf_reg_state *ptr_reg, + const struct bpf_reg_state *off_reg) { - struct bpf_reg_state *regs = env->cur_state.regs; - struct bpf_reg_state *dst_reg = ®s[insn->dst_reg]; + struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg; + bool known = tnum_is_const(off_reg->var_off); + s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value, + 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; u8 opcode = BPF_OP(insn->code); - s64 imm_log2; + u32 dst = insn->dst_reg; - /* for type == UNKNOWN_VALUE: - * imm > 0 -> number of zero upper bits - * imm == 0 -> don't track which is the same as all bits can be non-zero - */ + dst_reg = ®s[dst]; - if (BPF_SRC(insn->code) == BPF_X) { - struct bpf_reg_state *src_reg = ®s[insn->src_reg]; - - if (src_reg->type == UNKNOWN_VALUE && src_reg->imm > 0 && - dst_reg->imm && opcode == BPF_ADD) { - /* dreg += sreg - * where both have zero upper bits. Adding them - * can only result making one more bit non-zero - * in the larger value. - * Ex. 0xffff (imm=48) + 1 (imm=63) = 0x10000 (imm=47) - * 0xffff (imm=48) + 0xffff = 0x1fffe (imm=47) - */ - dst_reg->imm = min(dst_reg->imm, src_reg->imm); - dst_reg->imm--; - return 0; - } - if (src_reg->type == CONST_IMM && src_reg->imm > 0 && - dst_reg->imm && opcode == BPF_ADD) { - /* dreg += sreg - * where dreg has zero upper bits and sreg is const. - * Adding them can only result making one more bit - * non-zero in the larger value. - */ - imm_log2 = __ilog2_u64((long long)src_reg->imm); - dst_reg->imm = min(dst_reg->imm, 63 - imm_log2); - dst_reg->imm--; - return 0; - } - /* all other cases non supported yet, just mark dst_reg */ - dst_reg->imm = 0; - return 0; + if (WARN_ON_ONCE(known && (smin_val != smax_val))) { + print_verifier_state(&env->cur_state); + verbose("verifier internal error: known but bad sbounds\n"); + return -EINVAL; + } + if (WARN_ON_ONCE(known && (umin_val != umax_val))) { + print_verifier_state(&env->cur_state); + verbose("verifier internal error: known but bad ubounds\n"); + return -EINVAL; } - /* sign extend 32-bit imm into 64-bit to make sure that - * negative values occupy bit 63. Note ilog2() would have - * been incorrect, since sizeof(insn->imm) == 4 - */ - imm_log2 = __ilog2_u64((long long)insn->imm); - - if (dst_reg->imm && opcode == BPF_LSH) { - /* reg <<= imm - * if reg was a result of 2 byte load, then its imm == 48 - * which means that upper 48 bits are zero and shifting this reg - * left by 4 would mean that upper 44 bits are still zero - */ - dst_reg->imm -= insn->imm; - } else if (dst_reg->imm && opcode == BPF_MUL) { - /* reg *= imm - * if multiplying by 14 subtract 4 - * This is conservative calculation of upper zero bits. - * It's not trying to special case insn->imm == 1 or 0 cases - */ - dst_reg->imm -= imm_log2 + 1; - } else if (opcode == BPF_AND) { - /* reg &= imm */ - dst_reg->imm = 63 - imm_log2; - } else if (dst_reg->imm && opcode == BPF_ADD) { - /* reg += imm */ - dst_reg->imm = min(dst_reg->imm, 63 - imm_log2); - dst_reg->imm--; - } else if (opcode == BPF_RSH) { - /* reg >>= imm - * which means that after right shift, upper bits will be zero - * note that verifier already checked that - * 0 <= imm < 64 for shift insn - */ - dst_reg->imm += insn->imm; - if (unlikely(dst_reg->imm > 64)) - /* some dumb code did: - * r2 = *(u32 *)mem; - * r2 >>= 32; - * and all bits are zero now */ - dst_reg->imm = 64; - } else { - /* all other alu ops, means that we don't know what will - * happen to the value, mark it with unknown number of zero bits - */ - dst_reg->imm = 0; + if (BPF_CLASS(insn->code) != BPF_ALU64) { + /* 32-bit ALU ops on pointers produce (meaningless) scalars */ + if (!env->allow_ptr_leaks) + verbose("R%d 32-bit pointer arithmetic prohibited\n", + dst); + return -EACCES; } - if (dst_reg->imm < 0) { - /* all 64 bits of the register can contain non-zero bits - * and such value cannot be added to ptr_to_packet, since it - * may overflow, mark it as unknown to avoid further eval - */ - dst_reg->imm = 0; + if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { + if (!env->allow_ptr_leaks) + verbose("R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", + dst); + return -EACCES; + } + if (ptr_reg->type == CONST_PTR_TO_MAP) { + if (!env->allow_ptr_leaks) + verbose("R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", + dst); + return -EACCES; + } + if (ptr_reg->type == PTR_TO_PACKET_END) { + if (!env->allow_ptr_leaks) + verbose("R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", + dst); + return -EACCES; } - return 0; -} -static int evaluate_reg_imm_alu_unknown(struct bpf_verifier_env *env, - struct bpf_insn *insn) -{ - struct bpf_reg_state *regs = env->cur_state.regs; - struct bpf_reg_state *dst_reg = ®s[insn->dst_reg]; - struct bpf_reg_state *src_reg = ®s[insn->src_reg]; - u8 opcode = BPF_OP(insn->code); - s64 imm_log2 = __ilog2_u64((long long)dst_reg->imm); - - /* BPF_X code with src_reg->type UNKNOWN_VALUE here. */ - if (src_reg->imm > 0 && dst_reg->imm) { - switch (opcode) { - case BPF_ADD: - /* dreg += sreg - * where both have zero upper bits. Adding them - * can only result making one more bit non-zero - * in the larger value. - * Ex. 0xffff (imm=48) + 1 (imm=63) = 0x10000 (imm=47) - * 0xffff (imm=48) + 0xffff = 0x1fffe (imm=47) - */ - dst_reg->imm = min(src_reg->imm, 63 - imm_log2); - dst_reg->imm--; - break; - case BPF_AND: - /* dreg &= sreg - * AND can not extend zero bits only shrink - * Ex. 0x00..00ffffff - * & 0x0f..ffffffff - * ---------------- - * 0x00..00ffffff - */ - dst_reg->imm = max(src_reg->imm, 63 - imm_log2); + /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. + * The id may be overwritten later if we create a new variable offset. + */ + dst_reg->type = ptr_reg->type; + dst_reg->id = ptr_reg->id; + + switch (opcode) { + case BPF_ADD: + /* We can take a fixed offset as long as it doesn't overflow + * the s32 'off' field + */ + if (known && (ptr_reg->off + smin_val == + (s64)(s32)(ptr_reg->off + smin_val))) { + /* pointer += K. Accumulate it into fixed offset */ + dst_reg->smin_value = smin_ptr; + dst_reg->smax_value = smax_ptr; + dst_reg->umin_value = umin_ptr; + 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; break; - case BPF_OR: - /* dreg |= sreg - * OR can only extend zero bits - * Ex. 0x00..00ffffff - * | 0x0f..ffffffff - * ---------------- - * 0x0f..00ffffff - */ - dst_reg->imm = min(src_reg->imm, 63 - imm_log2); + } + /* A new variable offset is created. Note that off_reg->off + * == 0, since it's a scalar. + * dst_reg gets the pointer type and since some positive + * integer value was added to the pointer, give it a new 'id' + * if it's a PTR_TO_PACKET. + * this creates a new 'base' pointer, off_reg (variable) gets + * added into the variable offset, and we copy the fixed offset + * from ptr_reg. + */ + if (signed_add_overflows(smin_ptr, smin_val) || + signed_add_overflows(smax_ptr, smax_val)) { + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value = smin_ptr + smin_val; + dst_reg->smax_value = smax_ptr + smax_val; + } + if (umin_ptr + umin_val < umin_ptr || + umax_ptr + umax_val < umax_ptr) { + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + } else { + dst_reg->umin_value = umin_ptr + umin_val; + dst_reg->umax_value = umax_ptr + umax_val; + } + dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); + dst_reg->off = ptr_reg->off; + if (ptr_reg->type == PTR_TO_PACKET) { + dst_reg->id = ++env->id_gen; + /* something was added to pkt_ptr, set range to zero */ + dst_reg->range = 0; + } + break; + case BPF_SUB: + if (dst_reg == off_reg) { + /* scalar -= pointer. Creates an unknown scalar */ + if (!env->allow_ptr_leaks) + verbose("R%d tried to subtract pointer from scalar\n", + dst); + return -EACCES; + } + /* We don't allow subtraction from FP, because (according to + * test_verifier.c test "invalid fp arithmetic", JITs might not + * be able to deal with it. + */ + if (ptr_reg->type == PTR_TO_STACK) { + if (!env->allow_ptr_leaks) + verbose("R%d subtraction from stack pointer prohibited\n", + dst); + return -EACCES; + } + if (known && (ptr_reg->off - smin_val == + (s64)(s32)(ptr_reg->off - smin_val))) { + /* pointer -= K. Subtract it from fixed offset */ + dst_reg->smin_value = smin_ptr; + dst_reg->smax_value = smax_ptr; + dst_reg->umin_value = umin_ptr; + dst_reg->umax_value = umax_ptr; + 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; break; - case BPF_SUB: - case BPF_MUL: - case BPF_RSH: - case BPF_LSH: - /* These may be flushed out later */ - default: - mark_reg_unknown_value(regs, insn->dst_reg); } - } else { - mark_reg_unknown_value(regs, insn->dst_reg); + /* A new variable offset is created. If the subtrahend is known + * nonnegative, then any reg->range we had before is still good. + */ + if (signed_sub_overflows(smin_ptr, smax_val) || + signed_sub_overflows(smax_ptr, smin_val)) { + /* Overflow possible, we know nothing */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value = smin_ptr - smax_val; + dst_reg->smax_value = smax_ptr - smin_val; + } + if (umin_ptr < umax_val) { + /* Overflow possible, we know nothing */ + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + } else { + /* Cannot overflow (as long as bounds are consistent) */ + dst_reg->umin_value = umin_ptr - umax_val; + dst_reg->umax_value = umax_ptr - umin_val; + } + dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); + dst_reg->off = ptr_reg->off; + if (ptr_reg->type == PTR_TO_PACKET) { + dst_reg->id = ++env->id_gen; + /* something was added to pkt_ptr, set range to zero */ + if (smin_val < 0) + dst_reg->range = 0; + } + break; + case BPF_AND: + case BPF_OR: + case BPF_XOR: + /* bitwise ops on pointers are troublesome, prohibit for now. + * (However, in principle we could allow some cases, e.g. + * ptr &= ~3 which would reduce min_value by 3.) + */ + if (!env->allow_ptr_leaks) + verbose("R%d bitwise operator %s on pointer prohibited\n", + dst, bpf_alu_string[opcode >> 4]); + return -EACCES; + default: + /* other operators (e.g. MUL,LSH) produce non-pointer results */ + if (!env->allow_ptr_leaks) + verbose("R%d pointer arithmetic with %s operator prohibited\n", + dst, bpf_alu_string[opcode >> 4]); + return -EACCES; } - dst_reg->type = UNKNOWN_VALUE; + __update_reg_bounds(dst_reg); + __reg_deduce_bounds(dst_reg); + __reg_bound_offset(dst_reg); return 0; } -static int evaluate_reg_imm_alu(struct bpf_verifier_env *env, - struct bpf_insn *insn) +static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct bpf_reg_state *dst_reg, + struct bpf_reg_state src_reg) { struct bpf_reg_state *regs = env->cur_state.regs; - struct bpf_reg_state *dst_reg = ®s[insn->dst_reg]; - struct bpf_reg_state *src_reg = ®s[insn->src_reg]; u8 opcode = BPF_OP(insn->code); - u64 dst_imm = dst_reg->imm; - - if (BPF_SRC(insn->code) == BPF_X && src_reg->type == UNKNOWN_VALUE) - return evaluate_reg_imm_alu_unknown(env, insn); - - /* dst_reg->type == CONST_IMM here. Simulate execution of insns - * containing ALU ops. Don't care about overflow or negative - * values, just add/sub/... them; registers are in u64. - */ - if (opcode == BPF_ADD && BPF_SRC(insn->code) == BPF_K) { - dst_imm += insn->imm; - } else if (opcode == BPF_ADD && BPF_SRC(insn->code) == BPF_X && - src_reg->type == CONST_IMM) { - dst_imm += src_reg->imm; - } else if (opcode == BPF_SUB && BPF_SRC(insn->code) == BPF_K) { - dst_imm -= insn->imm; - } else if (opcode == BPF_SUB && BPF_SRC(insn->code) == BPF_X && - src_reg->type == CONST_IMM) { - dst_imm -= src_reg->imm; - } else if (opcode == BPF_MUL && BPF_SRC(insn->code) == BPF_K) { - dst_imm *= insn->imm; - } else if (opcode == BPF_MUL && BPF_SRC(insn->code) == BPF_X && - src_reg->type == CONST_IMM) { - dst_imm *= src_reg->imm; - } else if (opcode == BPF_OR && BPF_SRC(insn->code) == BPF_K) { - dst_imm |= insn->imm; - } else if (opcode == BPF_OR && BPF_SRC(insn->code) == BPF_X && - src_reg->type == CONST_IMM) { - dst_imm |= src_reg->imm; - } else if (opcode == BPF_AND && BPF_SRC(insn->code) == BPF_K) { - dst_imm &= insn->imm; - } else if (opcode == BPF_AND && BPF_SRC(insn->code) == BPF_X && - src_reg->type == CONST_IMM) { - dst_imm &= src_reg->imm; - } else if (opcode == BPF_RSH && BPF_SRC(insn->code) == BPF_K) { - dst_imm >>= insn->imm; - } else if (opcode == BPF_RSH && BPF_SRC(insn->code) == BPF_X && - src_reg->type == CONST_IMM) { - dst_imm >>= src_reg->imm; - } else if (opcode == BPF_LSH && BPF_SRC(insn->code) == BPF_K) { - dst_imm <<= insn->imm; - } else if (opcode == BPF_LSH && BPF_SRC(insn->code) == BPF_X && - src_reg->type == CONST_IMM) { - dst_imm <<= src_reg->imm; - } else { - mark_reg_unknown_value(regs, insn->dst_reg); - goto out; - } - - dst_reg->imm = dst_imm; -out: - return 0; -} - -static void check_reg_overflow(struct bpf_reg_state *reg) -{ - if (reg->max_value > BPF_REGISTER_MAX_RANGE) - reg->max_value = BPF_REGISTER_MAX_RANGE; - if (reg->min_value < BPF_REGISTER_MIN_RANGE || - reg->min_value > BPF_REGISTER_MAX_RANGE) - reg->min_value = BPF_REGISTER_MIN_RANGE; -} - -static u32 calc_align(u32 imm) -{ - if (!imm) - return 1U << 31; - return imm - ((imm - 1) & imm); -} - -static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, - struct bpf_insn *insn) -{ - struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg; - s64 min_val = BPF_REGISTER_MIN_RANGE; - u64 max_val = BPF_REGISTER_MAX_RANGE; - u8 opcode = BPF_OP(insn->code); - u32 dst_align, src_align; - - dst_reg = ®s[insn->dst_reg]; - src_align = 0; - if (BPF_SRC(insn->code) == BPF_X) { - check_reg_overflow(®s[insn->src_reg]); - min_val = regs[insn->src_reg].min_value; - max_val = regs[insn->src_reg].max_value; - - /* If the source register is a random pointer then the - * min_value/max_value values represent the range of the known - * accesses into that value, not the actual min/max value of the - * register itself. In this case we have to reset the reg range - * values so we know it is not safe to look at. - */ - if (regs[insn->src_reg].type != CONST_IMM && - regs[insn->src_reg].type != UNKNOWN_VALUE) { - min_val = BPF_REGISTER_MIN_RANGE; - max_val = BPF_REGISTER_MAX_RANGE; - src_align = 0; - } else { - src_align = regs[insn->src_reg].min_align; - } - } else if (insn->imm < BPF_REGISTER_MAX_RANGE && - (s64)insn->imm > BPF_REGISTER_MIN_RANGE) { - min_val = max_val = insn->imm; - src_align = calc_align(insn->imm); - } - - dst_align = dst_reg->min_align; - - /* We don't know anything about what was done to this register, mark it - * as unknown. Also, if both derived bounds came from signed/unsigned - * mixed compares and one side is unbounded, we cannot really do anything - * with them as boundaries cannot be trusted. Thus, arithmetic of two - * regs of such kind will get invalidated bounds on the dst side. - */ - if ((min_val == BPF_REGISTER_MIN_RANGE && - max_val == BPF_REGISTER_MAX_RANGE) || - (BPF_SRC(insn->code) == BPF_X && - ((min_val != BPF_REGISTER_MIN_RANGE && - max_val == BPF_REGISTER_MAX_RANGE) || - (min_val == BPF_REGISTER_MIN_RANGE && - max_val != BPF_REGISTER_MAX_RANGE) || - (dst_reg->min_value != BPF_REGISTER_MIN_RANGE && - dst_reg->max_value == BPF_REGISTER_MAX_RANGE) || - (dst_reg->min_value == BPF_REGISTER_MIN_RANGE && - dst_reg->max_value != BPF_REGISTER_MAX_RANGE)) && - regs[insn->dst_reg].value_from_signed != - regs[insn->src_reg].value_from_signed)) { - reset_reg_range_values(regs, insn->dst_reg); - return; - } - - /* If one of our values was at the end of our ranges then we can't just - * do our normal operations to the register, we need to set the values - * to the min/max since they are undefined. - */ - if (opcode != BPF_SUB) { - if (min_val == BPF_REGISTER_MIN_RANGE) - dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - if (max_val == BPF_REGISTER_MAX_RANGE) - dst_reg->max_value = BPF_REGISTER_MAX_RANGE; + bool src_known, dst_known; + s64 smin_val, smax_val; + u64 umin_val, umax_val; + + if (BPF_CLASS(insn->code) != BPF_ALU64) { + /* 32-bit ALU ops are (32,32)->64 */ + coerce_reg_to_32(dst_reg); + coerce_reg_to_32(&src_reg); } + smin_val = src_reg.smin_value; + smax_val = src_reg.smax_value; + umin_val = src_reg.umin_value; + umax_val = src_reg.umax_value; + src_known = tnum_is_const(src_reg.var_off); + dst_known = tnum_is_const(dst_reg->var_off); switch (opcode) { case BPF_ADD: - if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) - dst_reg->min_value += min_val; - if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) - dst_reg->max_value += max_val; - dst_reg->min_align = min(src_align, dst_align); + 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; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value += smin_val; + dst_reg->smax_value += smax_val; + } + if (dst_reg->umin_value + umin_val < umin_val || + dst_reg->umax_value + umax_val < umax_val) { + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + } else { + dst_reg->umin_value += umin_val; + dst_reg->umax_value += umax_val; + } + dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: - /* If one of our values was at the end of our ranges, then the - * _opposite_ value in the dst_reg goes to the end of our range. - */ - if (min_val == BPF_REGISTER_MIN_RANGE) - dst_reg->max_value = BPF_REGISTER_MAX_RANGE; - if (max_val == BPF_REGISTER_MAX_RANGE) - dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) - dst_reg->min_value -= max_val; - if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) - dst_reg->max_value -= min_val; - dst_reg->min_align = min(src_align, dst_align); + if (signed_sub_overflows(dst_reg->smin_value, smax_val) || + signed_sub_overflows(dst_reg->smax_value, smin_val)) { + /* Overflow possible, we know nothing */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value -= smax_val; + dst_reg->smax_value -= smin_val; + } + if (dst_reg->umin_value < umax_val) { + /* Overflow possible, we know nothing */ + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + } else { + /* Cannot overflow (as long as bounds are consistent) */ + dst_reg->umin_value -= umax_val; + dst_reg->umax_value -= umin_val; + } + dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off); break; case BPF_MUL: - if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) - dst_reg->min_value *= min_val; - if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) - dst_reg->max_value *= max_val; - dst_reg->min_align = max(src_align, dst_align); + dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off); + if (smin_val < 0 || dst_reg->smin_value < 0) { + /* Ain't nobody got time to multiply that sign */ + __mark_reg_unbounded(dst_reg); + __update_reg_bounds(dst_reg); + break; + } + /* Both values are positive, so we can work with unsigned and + * copy the result to signed (unless it exceeds S64_MAX). + */ + if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) { + /* Potential overflow, we know nothing */ + __mark_reg_unbounded(dst_reg); + /* (except what we can learn from the var_off) */ + __update_reg_bounds(dst_reg); + break; + } + dst_reg->umin_value *= umin_val; + dst_reg->umax_value *= umax_val; + if (dst_reg->umax_value > S64_MAX) { + /* Overflow possible, we know nothing */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value = dst_reg->umin_value; + dst_reg->smax_value = dst_reg->umax_value; + } break; case BPF_AND: - /* Disallow AND'ing of negative numbers, ain't nobody got time - * for that. Otherwise the minimum is 0 and the max is the max - * value we could AND against. + if (src_known && dst_known) { + __mark_reg_known(dst_reg, dst_reg->var_off.value & + src_reg.var_off.value); + break; + } + /* We get our minimum from the var_off, since that's inherently + * bitwise. Our maximum is the minimum of the operands' maxima. */ - if (min_val < 0) - dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - else - dst_reg->min_value = 0; - dst_reg->max_value = max_val; - dst_reg->min_align = max(src_align, dst_align); + dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off); + dst_reg->umin_value = dst_reg->var_off.value; + dst_reg->umax_value = min(dst_reg->umax_value, umax_val); + if (dst_reg->smin_value < 0 || smin_val < 0) { + /* Lose signed bounds when ANDing negative numbers, + * ain't nobody got time for that. + */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + /* ANDing two positives gives a positive, so safe to + * cast result into s64. + */ + dst_reg->smin_value = dst_reg->umin_value; + dst_reg->smax_value = dst_reg->umax_value; + } + /* We may learn something more from the var_off */ + __update_reg_bounds(dst_reg); break; - case BPF_LSH: - /* Gotta have special overflow logic here, if we're shifting - * more than MAX_RANGE then just assume we have an invalid - * range. + case BPF_OR: + if (src_known && dst_known) { + __mark_reg_known(dst_reg, dst_reg->var_off.value | + src_reg.var_off.value); + break; + } + /* We get our maximum from the var_off, and our minimum is the + * maximum of the operands' minima */ - if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) { - dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - dst_reg->min_align = 1; + dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off); + dst_reg->umin_value = max(dst_reg->umin_value, umin_val); + dst_reg->umax_value = dst_reg->var_off.value | + dst_reg->var_off.mask; + if (dst_reg->smin_value < 0 || smin_val < 0) { + /* Lose signed bounds when ORing negative numbers, + * ain't nobody got time for that. + */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; } else { - if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) - dst_reg->min_value <<= min_val; - if (!dst_reg->min_align) - dst_reg->min_align = 1; - dst_reg->min_align <<= min_val; - } - if (max_val > ilog2(BPF_REGISTER_MAX_RANGE)) - dst_reg->max_value = BPF_REGISTER_MAX_RANGE; - else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) - dst_reg->max_value <<= max_val; + /* ORing two positives gives a positive, so safe to + * cast result into s64. + */ + dst_reg->smin_value = dst_reg->umin_value; + dst_reg->smax_value = dst_reg->umax_value; + } + /* We may learn something more from the var_off */ + __update_reg_bounds(dst_reg); break; - case BPF_RSH: - /* RSH by a negative number is undefined, and the BPF_RSH is an - * unsigned shift, so make the appropriate casts. + case BPF_LSH: + if (umax_val > 63) { + /* Shifts greater than 63 are undefined. This includes + * shifts by a negative number. + */ + mark_reg_unknown(regs, insn->dst_reg); + break; + } + /* We lose all sign bit information (except what we can pick + * up from var_off) */ - if (min_val < 0 || dst_reg->min_value < 0) { - dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + /* If we might shift our top bit out, then we know nothing */ + if (dst_reg->umax_value > 1ULL << (63 - umax_val)) { + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; } else { - dst_reg->min_value = - (u64)(dst_reg->min_value) >> min_val; + dst_reg->umin_value <<= umin_val; + dst_reg->umax_value <<= umax_val; + } + if (src_known) + dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); + else + dst_reg->var_off = tnum_lshift(tnum_unknown, umin_val); + /* We may learn something more from the var_off */ + __update_reg_bounds(dst_reg); + break; + case BPF_RSH: + if (umax_val > 63) { + /* Shifts greater than 63 are undefined. This includes + * shifts by a negative number. + */ + mark_reg_unknown(regs, insn->dst_reg); + break; } - if (min_val < 0) { - dst_reg->min_align = 1; + /* BPF_RSH is an unsigned shift, so make the appropriate casts */ + if (dst_reg->smin_value < 0) { + if (umin_val) { + /* Sign bit will be cleared */ + dst_reg->smin_value = 0; + } else { + /* Lost sign bit information */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } } else { - dst_reg->min_align >>= (u64) min_val; - if (!dst_reg->min_align) - dst_reg->min_align = 1; + dst_reg->smin_value = + (u64)(dst_reg->smin_value) >> umax_val; } - if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) - dst_reg->max_value >>= max_val; + if (src_known) + dst_reg->var_off = tnum_rshift(dst_reg->var_off, + umin_val); + else + dst_reg->var_off = tnum_rshift(tnum_unknown, umin_val); + dst_reg->umin_value >>= umax_val; + dst_reg->umax_value >>= umin_val; + /* We may learn something more from the var_off */ + __update_reg_bounds(dst_reg); break; default: - reset_reg_range_values(regs, insn->dst_reg); + mark_reg_unknown(regs, insn->dst_reg); break; } - check_reg_overflow(dst_reg); + __reg_deduce_bounds(dst_reg); + __reg_bound_offset(dst_reg); + return 0; +} + +/* Handles ALU ops other than BPF_END, BPF_NEG and BPF_MOV: computes new min/max + * and var_off. + */ +static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg, *src_reg; + struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; + u8 opcode = BPF_OP(insn->code); + int rc; + + dst_reg = ®s[insn->dst_reg]; + src_reg = NULL; + if (dst_reg->type != SCALAR_VALUE) + ptr_reg = dst_reg; + if (BPF_SRC(insn->code) == BPF_X) { + src_reg = ®s[insn->src_reg]; + if (src_reg->type != SCALAR_VALUE) { + if (dst_reg->type != SCALAR_VALUE) { + /* Combining two pointers by any ALU op yields + * an arbitrary scalar. + */ + if (!env->allow_ptr_leaks) { + verbose("R%d pointer %s pointer prohibited\n", + insn->dst_reg, + bpf_alu_string[opcode >> 4]); + return -EACCES; + } + mark_reg_unknown(regs, insn->dst_reg); + return 0; + } else { + /* scalar += pointer + * This is legal, but we have to reverse our + * src/dest handling in computing the range + */ + rc = adjust_ptr_min_max_vals(env, insn, + src_reg, dst_reg); + if (rc == -EACCES && env->allow_ptr_leaks) { + /* scalar += unknown scalar */ + __mark_reg_unknown(&off_reg); + return adjust_scalar_min_max_vals( + env, insn, + dst_reg, off_reg); + } + return rc; + } + } else if (ptr_reg) { + /* pointer += scalar */ + rc = adjust_ptr_min_max_vals(env, insn, + dst_reg, src_reg); + if (rc == -EACCES && env->allow_ptr_leaks) { + /* unknown scalar += scalar */ + __mark_reg_unknown(dst_reg); + return adjust_scalar_min_max_vals( + env, insn, dst_reg, *src_reg); + } + return rc; + } + } else { + /* Pretend the src is a reg with a known value, since we only + * need to be able to read from this state. + */ + off_reg.type = SCALAR_VALUE; + __mark_reg_known(&off_reg, insn->imm); + src_reg = &off_reg; + if (ptr_reg) { /* pointer += K */ + rc = adjust_ptr_min_max_vals(env, insn, + ptr_reg, src_reg); + if (rc == -EACCES && env->allow_ptr_leaks) { + /* unknown scalar += K */ + __mark_reg_unknown(dst_reg); + return adjust_scalar_min_max_vals( + env, insn, dst_reg, off_reg); + } + return rc; + } + } + + /* Got here implies adding two SCALAR_VALUEs */ + if (WARN_ON_ONCE(ptr_reg)) { + print_verifier_state(&env->cur_state); + verbose("verifier internal error: unexpected ptr_reg\n"); + return -EINVAL; + } + if (WARN_ON(!src_reg)) { + print_verifier_state(&env->cur_state); + verbose("verifier internal error: no src_reg\n"); + return -EINVAL; + } + return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); } /* check validity of 32-bit and 64-bit arithmetic operations */ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg; + struct bpf_reg_state *regs = env->cur_state.regs; u8 opcode = BPF_OP(insn->code); int err; @@ -1985,7 +2299,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check src operand */ - err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; @@ -1996,7 +2310,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check dest operand */ - err = check_reg_arg(regs, insn->dst_reg, DST_OP); + err = check_reg_arg(env, insn->dst_reg, DST_OP); if (err) return err; @@ -2009,7 +2323,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check src operand */ - err = check_reg_arg(regs, insn->src_reg, SRC_OP); + err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } else { @@ -2020,15 +2334,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check dest operand */ - err = check_reg_arg(regs, insn->dst_reg, DST_OP); + err = check_reg_arg(env, insn->dst_reg, DST_OP); if (err) return err; - /* we are setting our register to something new, we need to - * reset its range values. - */ - reset_reg_range_values(regs, insn->dst_reg); - if (BPF_SRC(insn->code) == BPF_X) { if (BPF_CLASS(insn->code) == BPF_ALU64) { /* case: R1 = R2 @@ -2036,24 +2345,24 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) */ regs[insn->dst_reg] = regs[insn->src_reg]; } else { + /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { verbose("R%d partial copy of pointer\n", insn->src_reg); return -EACCES; } - mark_reg_unknown_value(regs, insn->dst_reg); + mark_reg_unknown(regs, insn->dst_reg); + /* high 32 bits are known zero. */ + regs[insn->dst_reg].var_off = tnum_cast( + regs[insn->dst_reg].var_off, 4); + __update_reg_bounds(®s[insn->dst_reg]); } } else { /* case: R = imm * remember the value we stored into this reg */ - regs[insn->dst_reg].type = CONST_IMM; - regs[insn->dst_reg].imm = insn->imm; - regs[insn->dst_reg].id = 0; - regs[insn->dst_reg].max_value = insn->imm; - regs[insn->dst_reg].min_value = insn->imm; - regs[insn->dst_reg].min_align = calc_align(insn->imm); - regs[insn->dst_reg].value_from_signed = false; + regs[insn->dst_reg].type = SCALAR_VALUE; + __mark_reg_known(regs + insn->dst_reg, insn->imm); } } else if (opcode > BPF_END) { @@ -2068,7 +2377,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } /* check src1 operand */ - err = check_reg_arg(regs, insn->src_reg, SRC_OP); + err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } else { @@ -2079,7 +2388,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check src2 operand */ - err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; @@ -2100,72 +2409,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check dest operand */ - err = check_reg_arg(regs, insn->dst_reg, DST_OP_NO_MARK); + err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; - dst_reg = ®s[insn->dst_reg]; - - /* first we want to adjust our ranges. */ - adjust_reg_min_max_vals(env, insn); - - /* pattern match 'bpf_add Rx, imm' instruction */ - if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 && - dst_reg->type == FRAME_PTR && BPF_SRC(insn->code) == BPF_K) { - dst_reg->type = PTR_TO_STACK; - dst_reg->imm = insn->imm; - return 0; - } else if (opcode == BPF_ADD && - BPF_CLASS(insn->code) == BPF_ALU64 && - dst_reg->type == PTR_TO_STACK && - ((BPF_SRC(insn->code) == BPF_X && - regs[insn->src_reg].type == CONST_IMM) || - BPF_SRC(insn->code) == BPF_K)) { - if (BPF_SRC(insn->code) == BPF_X) - dst_reg->imm += regs[insn->src_reg].imm; - else - dst_reg->imm += insn->imm; - return 0; - } else if (opcode == BPF_ADD && - BPF_CLASS(insn->code) == BPF_ALU64 && - (dst_reg->type == PTR_TO_PACKET || - (BPF_SRC(insn->code) == BPF_X && - regs[insn->src_reg].type == PTR_TO_PACKET))) { - /* ptr_to_packet += K|X */ - return check_packet_ptr_add(env, insn); - } else if (BPF_CLASS(insn->code) == BPF_ALU64 && - dst_reg->type == UNKNOWN_VALUE && - env->allow_ptr_leaks) { - /* unknown += K|X */ - return evaluate_reg_alu(env, insn); - } else if (BPF_CLASS(insn->code) == BPF_ALU64 && - dst_reg->type == CONST_IMM && - env->allow_ptr_leaks) { - /* reg_imm += K|X */ - return evaluate_reg_imm_alu(env, insn); - } else if (is_pointer_value(env, insn->dst_reg)) { - verbose("R%d pointer arithmetic prohibited\n", - insn->dst_reg); - return -EACCES; - } else if (BPF_SRC(insn->code) == BPF_X && - is_pointer_value(env, insn->src_reg)) { - verbose("R%d pointer arithmetic prohibited\n", - insn->src_reg); - return -EACCES; - } - - /* If we did pointer math on a map value then just set it to our - * PTR_TO_MAP_VALUE_ADJ type so we can deal with any stores or - * loads to this register appropriately, otherwise just mark the - * register as unknown. - */ - if (env->allow_ptr_leaks && - BPF_CLASS(insn->code) == BPF_ALU64 && opcode == BPF_ADD && - (dst_reg->type == PTR_TO_MAP_VALUE || - dst_reg->type == PTR_TO_MAP_VALUE_ADJ)) - dst_reg->type = PTR_TO_MAP_VALUE_ADJ; - else - mark_reg_unknown_value(regs, insn->dst_reg); + return adjust_reg_min_max_vals(env, insn); } return 0; @@ -2177,27 +2425,48 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, struct bpf_reg_state *regs = state->regs, *reg; int i; - /* LLVM can generate two kind of checks: + if (dst_reg->off < 0) + /* This doesn't give us any range */ + return; + + if (dst_reg->umax_value > MAX_PACKET_OFF || + dst_reg->umax_value + dst_reg->off > MAX_PACKET_OFF) + /* Risk of overflow. For instance, ptr + (1<<63) may be less + * than pkt_end, but that's because it's also less than pkt. + */ + return; + + /* LLVM can generate four kind of checks: * - * Type 1: + * Type 1/2: * * r2 = r3; * r2 += 8; * if (r2 > pkt_end) goto <handle exception> * <access okay> * + * r2 = r3; + * r2 += 8; + * if (r2 < pkt_end) goto <access okay> + * <handle exception> + * * Where: * r2 == dst_reg, pkt_end == src_reg * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * - * Type 2: + * Type 3/4: * * r2 = r3; * r2 += 8; * if (pkt_end >= r2) goto <access okay> * <handle exception> * + * r2 = r3; + * r2 += 8; + * if (pkt_end <= r2) goto <handle exception> + * <access okay> + * * Where: * pkt_end == dst_reg, r2 == src_reg * r2=pkt(id=n,off=8,r=0) @@ -2207,193 +2476,247 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * so that range of bytes [r3, r3 + 8) is safe to access. */ + /* If our ids match, then we must have the same max_value. And we + * don't care about the other reg's fixed offset, since if it's too big + * the range won't allow anything. + * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. + */ for (i = 0; i < MAX_BPF_REG; i++) if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) /* keep the maximum range already checked */ - regs[i].range = max(regs[i].range, dst_reg->off); + regs[i].range = max_t(u16, regs[i].range, dst_reg->off); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) - reg->range = max(reg->range, dst_reg->off); + reg->range = max_t(u16, reg->range, dst_reg->off); } } /* 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. + * In JEQ/JNE cases we also adjust the var_off values. */ static void reg_set_min_max(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u8 opcode) { - bool value_from_signed = true; - bool is_range = true; + /* 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. + * Since false_reg and true_reg have the same type by construction, we + * only need to check one of them for pointerness. + */ + if (__is_pointer_value(false, false_reg)) + return; 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. */ - true_reg->max_value = true_reg->min_value = val; - is_range = false; + __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; */ - false_reg->max_value = false_reg->min_value = val; - is_range = false; + __mark_reg_known(false_reg, val); break; case BPF_JGT: - value_from_signed = false; - /* fallthrough */ + 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: - if (true_reg->value_from_signed != value_from_signed) - reset_reg_range_values(true_reg, 0); - if (false_reg->value_from_signed != value_from_signed) - reset_reg_range_values(false_reg, 0); - if (opcode == BPF_JGT) { - /* Unsigned comparison, the minimum value is 0. */ - false_reg->min_value = 0; - } - /* If this is false then we know the maximum val is val, - * otherwise we know the min val is val+1. - */ - false_reg->max_value = val; - false_reg->value_from_signed = value_from_signed; - true_reg->min_value = val + 1; - true_reg->value_from_signed = value_from_signed; + 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); + 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); break; case BPF_JGE: - value_from_signed = false; - /* fallthrough */ + false_reg->umax_value = min(false_reg->umax_value, val - 1); + true_reg->umin_value = max(true_reg->umin_value, val); + break; case BPF_JSGE: - if (true_reg->value_from_signed != value_from_signed) - reset_reg_range_values(true_reg, 0); - if (false_reg->value_from_signed != value_from_signed) - reset_reg_range_values(false_reg, 0); - if (opcode == BPF_JGE) { - /* Unsigned comparison, the minimum value is 0. */ - false_reg->min_value = 0; - } - /* If this is false then we know the maximum value is val - 1, - * otherwise we know the mimimum value is val. - */ - false_reg->max_value = val - 1; - false_reg->value_from_signed = value_from_signed; - true_reg->min_value = val; - true_reg->value_from_signed = value_from_signed; + 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); + 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); + 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); break; default: break; } - check_reg_overflow(false_reg); - check_reg_overflow(true_reg); - if (is_range) { - if (__is_pointer_value(false, false_reg)) - reset_reg_range_values(false_reg, 0); - if (__is_pointer_value(false, true_reg)) - reset_reg_range_values(true_reg, 0); - } + __reg_deduce_bounds(false_reg); + __reg_deduce_bounds(true_reg); + /* We might have learned some bits from the bounds. */ + __reg_bound_offset(false_reg); + __reg_bound_offset(true_reg); + /* Intersecting with the old var_off might have improved our bounds + * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), + * then new var_off is (0; 0x7f...fc) which improves our umax. + */ + __update_reg_bounds(false_reg); + __update_reg_bounds(true_reg); } -/* Same as above, but for the case that dst_reg is a CONST_IMM reg and src_reg - * is the variable reg. +/* Same as above, but for the case that dst_reg holds a constant and src_reg is + * the variable reg. */ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u8 opcode) { - bool value_from_signed = true; - bool is_range = true; + if (__is_pointer_value(false, false_reg)) + return; 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. */ - true_reg->max_value = true_reg->min_value = val; - is_range = false; + __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; */ - false_reg->max_value = false_reg->min_value = val; - is_range = false; + __mark_reg_known(false_reg, val); break; case BPF_JGT: - value_from_signed = false; - /* fallthrough */ + 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: - if (true_reg->value_from_signed != value_from_signed) - reset_reg_range_values(true_reg, 0); - if (false_reg->value_from_signed != value_from_signed) - reset_reg_range_values(false_reg, 0); - if (opcode == BPF_JGT) { - /* Unsigned comparison, the minimum value is 0. */ - true_reg->min_value = 0; - } - /* - * If this is false, then the val is <= the register, if it is - * true the register <= to the val. - */ - false_reg->min_value = val; - false_reg->value_from_signed = value_from_signed; - true_reg->max_value = val - 1; - true_reg->value_from_signed = value_from_signed; + 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); + 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); break; case BPF_JGE: - value_from_signed = false; - /* fallthrough */ + true_reg->umax_value = min(true_reg->umax_value, val); + false_reg->umin_value = max(false_reg->umin_value, val + 1); + break; case BPF_JSGE: - if (true_reg->value_from_signed != value_from_signed) - reset_reg_range_values(true_reg, 0); - if (false_reg->value_from_signed != value_from_signed) - reset_reg_range_values(false_reg, 0); - if (opcode == BPF_JGE) { - /* Unsigned comparison, the minimum value is 0. */ - true_reg->min_value = 0; - } - /* If this is false then constant < register, if it is true then - * the register < constant. - */ - false_reg->min_value = val + 1; - false_reg->value_from_signed = value_from_signed; - true_reg->max_value = val; - true_reg->value_from_signed = value_from_signed; + 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); + 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); + 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); break; default: break; } - check_reg_overflow(false_reg); - check_reg_overflow(true_reg); - if (is_range) { - if (__is_pointer_value(false, false_reg)) - reset_reg_range_values(false_reg, 0); - if (__is_pointer_value(false, true_reg)) - reset_reg_range_values(true_reg, 0); + __reg_deduce_bounds(false_reg); + __reg_deduce_bounds(true_reg); + /* We might have learned some bits from the bounds. */ + __reg_bound_offset(false_reg); + __reg_bound_offset(true_reg); + /* Intersecting with the old var_off might have improved our bounds + * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), + * then new var_off is (0; 0x7f...fc) which improves our umax. + */ + __update_reg_bounds(false_reg); + __update_reg_bounds(true_reg); +} + +/* Regs are known to be equal, so intersect their min/max/var_off */ +static void __reg_combine_min_max(struct bpf_reg_state *src_reg, + struct bpf_reg_state *dst_reg) +{ + src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value, + dst_reg->umin_value); + src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value, + dst_reg->umax_value); + src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value, + dst_reg->smin_value); + src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value, + dst_reg->smax_value); + src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off, + dst_reg->var_off); + /* We might have learned new bounds from the var_off. */ + __update_reg_bounds(src_reg); + __update_reg_bounds(dst_reg); + /* We might have learned something about the sign bit. */ + __reg_deduce_bounds(src_reg); + __reg_deduce_bounds(dst_reg); + /* We might have learned some bits from the bounds. */ + __reg_bound_offset(src_reg); + __reg_bound_offset(dst_reg); + /* Intersecting with the old var_off might have improved our bounds + * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), + * then new var_off is (0; 0x7f...fc) which improves our umax. + */ + __update_reg_bounds(src_reg); + __update_reg_bounds(dst_reg); +} + +static void reg_combine_min_max(struct bpf_reg_state *true_src, + struct bpf_reg_state *true_dst, + struct bpf_reg_state *false_src, + struct bpf_reg_state *false_dst, + u8 opcode) +{ + switch (opcode) { + case BPF_JEQ: + __reg_combine_min_max(true_src, true_dst); + break; + case BPF_JNE: + __reg_combine_min_max(false_src, false_dst); + break; } } static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, - enum bpf_reg_type type) + bool is_null) { struct bpf_reg_state *reg = ®s[regno]; if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) { - if (type == UNKNOWN_VALUE) { - __mark_reg_unknown_value(regs, regno); + /* Old offset (both fixed and variable parts) should + * have been known-zero, because we don't allow pointer + * arithmetic on pointers that might be NULL. + */ + if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || + !tnum_equals_const(reg->var_off, 0) || + reg->off)) { + __mark_reg_known_zero(reg); + reg->off = 0; + } + if (is_null) { + reg->type = SCALAR_VALUE; } else if (reg->map_ptr->inner_map_meta) { reg->type = CONST_PTR_TO_MAP; reg->map_ptr = reg->map_ptr->inner_map_meta; } else { - reg->type = type; + reg->type = PTR_TO_MAP_VALUE; } /* We don't need id from this point onwards anymore, thus we * should better reset it, so that state pruning has chances @@ -2407,19 +2730,19 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, * be folded together at some point. */ static void mark_map_regs(struct bpf_verifier_state *state, u32 regno, - enum bpf_reg_type type) + bool is_null) { struct bpf_reg_state *regs = state->regs; u32 id = regs[regno].id; int i; for (i = 0; i < MAX_BPF_REG; i++) - mark_map_reg(regs, i, id, type); + mark_map_reg(regs, i, id, is_null); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; - mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, type); + mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, is_null); } } @@ -2431,7 +2754,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, u8 opcode = BPF_OP(insn->code); int err; - if (opcode > BPF_EXIT) { + if (opcode > BPF_JSLE) { verbose("invalid BPF_JMP opcode %x\n", opcode); return -EINVAL; } @@ -2443,7 +2766,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } /* check src1 operand */ - err = check_reg_arg(regs, insn->src_reg, SRC_OP); + err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; @@ -2460,7 +2783,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } /* check src2 operand */ - err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; @@ -2469,7 +2792,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, /* 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 == CONST_IMM && dst_reg->imm == insn->imm) { + dst_reg->type == SCALAR_VALUE && + tnum_equals_const(dst_reg->var_off, insn->imm)) { if (opcode == BPF_JEQ) { /* if (imm == imm) goto pc+off; * only follow the goto, ignore fall-through @@ -2491,17 +2815,30 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, /* detect if we are comparing against a constant value so we can adjust * our min/max values for our dst register. + * this is only legit if both are scalars (or pointers to the same + * object, I suppose, but we don't support that right now), because + * otherwise the different base pointers mean the offsets aren't + * comparable. */ if (BPF_SRC(insn->code) == BPF_X) { - if (regs[insn->src_reg].type == CONST_IMM) - reg_set_min_max(&other_branch->regs[insn->dst_reg], - dst_reg, regs[insn->src_reg].imm, - opcode); - else if (dst_reg->type == CONST_IMM) - reg_set_min_max_inv(&other_branch->regs[insn->src_reg], - ®s[insn->src_reg], dst_reg->imm, - opcode); - } else { + if (dst_reg->type == SCALAR_VALUE && + regs[insn->src_reg].type == SCALAR_VALUE) { + if (tnum_is_const(regs[insn->src_reg].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)) + 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) + /* 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); + } + } else if (dst_reg->type == SCALAR_VALUE) { reg_set_min_max(&other_branch->regs[insn->dst_reg], dst_reg, insn->imm, opcode); } @@ -2513,18 +2850,24 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, /* Mark all identical map registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ - mark_map_regs(this_branch, insn->dst_reg, - opcode == BPF_JEQ ? PTR_TO_MAP_VALUE : UNKNOWN_VALUE); - mark_map_regs(other_branch, insn->dst_reg, - opcode == BPF_JEQ ? UNKNOWN_VALUE : PTR_TO_MAP_VALUE); + mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE); + mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { find_good_pkt_pointers(this_branch, dst_reg); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET && + regs[insn->src_reg].type == PTR_TO_PACKET_END) { + find_good_pkt_pointers(other_branch, dst_reg); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { find_good_pkt_pointers(other_branch, ®s[insn->src_reg]); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && + dst_reg->type == PTR_TO_PACKET_END && + regs[insn->src_reg].type == PTR_TO_PACKET) { + find_good_pkt_pointers(this_branch, ®s[insn->src_reg]); } else if (is_pointer_value(env, insn->dst_reg)) { verbose("R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; @@ -2557,16 +2900,15 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - err = check_reg_arg(regs, insn->dst_reg, DST_OP); + err = check_reg_arg(env, insn->dst_reg, DST_OP); if (err) return err; if (insn->src_reg == 0) { u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; - regs[insn->dst_reg].type = CONST_IMM; - regs[insn->dst_reg].imm = imm; - regs[insn->dst_reg].id = 0; + regs[insn->dst_reg].type = SCALAR_VALUE; + __mark_reg_known(®s[insn->dst_reg], imm); return 0; } @@ -2624,7 +2966,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check whether implicit source operand (register R6) is readable */ - err = check_reg_arg(regs, BPF_REG_6, SRC_OP); + err = check_reg_arg(env, BPF_REG_6, SRC_OP); if (err) return err; @@ -2635,19 +2977,22 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) if (mode == BPF_IND) { /* check explicit source operand */ - err = check_reg_arg(regs, insn->src_reg, SRC_OP); + err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } /* reset caller saved regs to unreadable */ - for (i = 0; i < CALLER_SAVED_REGS; i++) + for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(regs, caller_saved[i]); + check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); + } /* mark destination R0 register as readable, since it contains - * the value fetched from the packet + * the value fetched from the packet. + * Already marked as written above. */ - regs[BPF_REG_0].type = UNKNOWN_VALUE; + mark_reg_unknown(regs, BPF_REG_0); return 0; } @@ -2850,57 +3195,144 @@ err_free: return ret; } -/* the following conditions reduce the number of explored insns - * from ~140k to ~80k for ultra large programs that use a lot of ptr_to_packet +/* check %cur's range satisfies %old's */ +static bool range_within(struct bpf_reg_state *old, + struct bpf_reg_state *cur) +{ + return old->umin_value <= cur->umin_value && + old->umax_value >= cur->umax_value && + old->smin_value <= cur->smin_value && + old->smax_value >= cur->smax_value; +} + +/* Maximum number of register states that can exist at once */ +#define ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) +struct idpair { + u32 old; + u32 cur; +}; + +/* If in the old state two registers had the same id, then they need to have + * the same id in the new state as well. But that id could be different from + * the old state, so we need to track the mapping from old to new ids. + * Once we have seen that, say, a reg with old id 5 had new id 9, any subsequent + * regs with old id 5 must also have new id 9 for the new state to be safe. But + * regs with a different old id could still have new id 9, we don't care about + * that. + * So we look through our idmap to see if this old id has been seen before. If + * so, we require the new id to match; otherwise, we add the id pair to the map. */ -static bool compare_ptrs_to_packet(struct bpf_verifier_env *env, - struct bpf_reg_state *old, - struct bpf_reg_state *cur) +static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap) { - if (old->id != cur->id) - return false; + unsigned int i; + + for (i = 0; i < ID_MAP_SIZE; i++) { + if (!idmap[i].old) { + /* Reached an empty slot; haven't seen this id before */ + idmap[i].old = old_id; + idmap[i].cur = cur_id; + return true; + } + if (idmap[i].old == old_id) + return idmap[i].cur == cur_id; + } + /* We ran out of idmap slots, which should be impossible */ + WARN_ON_ONCE(1); + return false; +} - /* old ptr_to_packet is more conservative, since it allows smaller - * range. Ex: - * old(off=0,r=10) is equal to cur(off=0,r=20), because - * old(off=0,r=10) means that with range=10 the verifier proceeded - * further and found no issues with the program. Now we're in the same - * spot with cur(off=0,r=20), so we're safe too, since anything further - * will only be looking at most 10 bytes after this pointer. - */ - if (old->off == cur->off && old->range < cur->range) +/* Returns true if (rold safe implies rcur safe) */ +static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, + struct idpair *idmap) +{ + if (!(rold->live & REG_LIVE_READ)) + /* explored state didn't use this */ return true; - /* old(off=20,r=10) is equal to cur(off=22,re=22 or 5 or 0) - * since both cannot be used for packet access and safe(old) - * pointer has smaller off that could be used for further - * 'if (ptr > data_end)' check - * Ex: - * old(off=20,r=10) and cur(off=22,r=22) and cur(off=22,r=0) mean - * that we cannot access the packet. - * The safe range is: - * [ptr, ptr + range - off) - * so whenever off >=range, it means no safe bytes from this pointer. - * When comparing old->off <= cur->off, it means that older code - * went with smaller offset and that offset was later - * used to figure out the safe range after 'if (ptr > data_end)' check - * Say, 'old' state was explored like: - * ... R3(off=0, r=0) - * R4 = R3 + 20 - * ... now R4(off=20,r=0) <-- here - * if (R4 > data_end) - * ... R4(off=20,r=20), R3(off=0,r=20) and R3 can be used to access. - * ... the code further went all the way to bpf_exit. - * Now the 'cur' state at the mark 'here' has R4(off=30,r=0). - * old_R4(off=20,r=0) equal to cur_R4(off=30,r=0), since if the verifier - * goes further, such cur_R4 will give larger safe packet range after - * 'if (R4 > data_end)' and all further insn were already good with r=20, - * so they will be good with r=30 and we can prune the search. - */ - if (!env->strict_alignment && old->off <= cur->off && - old->off >= old->range && cur->off >= cur->range) + if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, live)) == 0) return true; + if (rold->type == NOT_INIT) + /* explored state can't have used this */ + return true; + if (rcur->type == NOT_INIT) + return false; + switch (rold->type) { + case SCALAR_VALUE: + if (rcur->type == SCALAR_VALUE) { + /* new val must satisfy old val knowledge */ + return range_within(rold, rcur) && + tnum_in(rold->var_off, rcur->var_off); + } else { + /* if we knew anything about the old value, we're not + * equal, because we can't know anything about the + * scalar value of the pointer in the new value. + */ + return rold->umin_value == 0 && + rold->umax_value == U64_MAX && + rold->smin_value == S64_MIN && + rold->smax_value == S64_MAX && + tnum_is_unknown(rold->var_off); + } + 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) + */ + return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && + range_within(rold, rcur) && + tnum_in(rold->var_off, rcur->var_off); + case PTR_TO_MAP_VALUE_OR_NULL: + /* a PTR_TO_MAP_VALUE could be safe to use as a + * PTR_TO_MAP_VALUE_OR_NULL into the same map. + * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- + * checked, doing so could have affected others with the same + * id, and we can't check for that because we lost the id when + * we converted to a PTR_TO_MAP_VALUE. + */ + if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL) + return false; + if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) + return false; + /* Check our ids match any regs they're supposed to */ + return check_ids(rold->id, rcur->id, idmap); + case PTR_TO_PACKET: + if (rcur->type != PTR_TO_PACKET) + return false; + /* We must have at least as much range as the old ptr + * did, so that any accesses which were safe before are + * still safe. This is true even if old range < old off, + * since someone could have accessed through (ptr - k), or + * even done ptr -= k in a register, to get a safe access. + */ + if (rold->range > rcur->range) + return false; + /* If the offsets don't match, we can't trust our alignment; + * nor can we be sure that we won't fall out of range. + */ + if (rold->off != rcur->off) + return false; + /* id relations must be preserved */ + if (rold->id && !check_ids(rold->id, rcur->id, idmap)) + return false; + /* new val must satisfy old val knowledge */ + return range_within(rold, rcur) && + tnum_in(rold->var_off, rcur->var_off); + case PTR_TO_CTX: + case CONST_PTR_TO_MAP: + case PTR_TO_STACK: + case PTR_TO_PACKET_END: + /* Only valid matches are exact, which memcmp() above + * would have accepted + */ + default: + /* Don't know what's going on, just say it's not safe */ + return false; + } + + /* Shouldn't get here; if we do, say it's not safe */ + WARN_ON_ONCE(1); return false; } @@ -2934,44 +3366,18 @@ static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { - bool varlen_map_access = env->varlen_map_value_access; - struct bpf_reg_state *rold, *rcur; + struct idpair *idmap; + bool ret = false; int i; - for (i = 0; i < MAX_BPF_REG; i++) { - rold = &old->regs[i]; - rcur = &cur->regs[i]; - - if (memcmp(rold, rcur, sizeof(*rold)) == 0) - continue; - - /* If the ranges were not the same, but everything else was and - * we didn't do a variable access into a map then we are a-ok. - */ - if (!varlen_map_access && - memcmp(rold, rcur, offsetofend(struct bpf_reg_state, id)) == 0) - continue; - - /* If we didn't map access then again we don't care about the - * mismatched range values and it's ok if our old type was - * UNKNOWN and we didn't go to a NOT_INIT'ed reg. - */ - if (rold->type == NOT_INIT || - (!varlen_map_access && rold->type == UNKNOWN_VALUE && - rcur->type != NOT_INIT)) - continue; - - /* Don't care about the reg->id in this case. */ - if (rold->type == PTR_TO_MAP_VALUE_OR_NULL && - rcur->type == PTR_TO_MAP_VALUE_OR_NULL && - rold->map_ptr == rcur->map_ptr) - continue; - - if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET && - compare_ptrs_to_packet(env, rold, rcur)) - continue; - + idmap = kcalloc(ID_MAP_SIZE, sizeof(struct idpair), GFP_KERNEL); + /* If we failed to allocate the idmap, just say it's not safe */ + if (!idmap) return false; + + for (i = 0; i < MAX_BPF_REG; i++) { + if (!regsafe(&old->regs[i], &cur->regs[i], idmap)) + goto out_free; } for (i = 0; i < MAX_BPF_STACK; i++) { @@ -2983,35 +3389,104 @@ static bool states_equal(struct bpf_verifier_env *env, * this verifier states are not equivalent, * return false to continue verification of this path */ - return false; + goto out_free; if (i % BPF_REG_SIZE) continue; if (old->stack_slot_type[i] != STACK_SPILL) continue; - if (memcmp(&old->spilled_regs[i / BPF_REG_SIZE], - &cur->spilled_regs[i / BPF_REG_SIZE], - sizeof(old->spilled_regs[0]))) - /* when explored and current stack slot types are - * the same, check that stored pointers types + if (!regsafe(&old->spilled_regs[i / BPF_REG_SIZE], + &cur->spilled_regs[i / BPF_REG_SIZE], + idmap)) + /* when explored and current stack slot are both storing + * spilled registers, check that stored pointers types * are the same as well. * Ex: explored safe path could have stored - * (bpf_reg_state) {.type = PTR_TO_STACK, .imm = -8} + * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8} * but current path has stored: - * (bpf_reg_state) {.type = PTR_TO_STACK, .imm = -16} + * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16} * such verifier states are not equivalent. * return false to continue verification of this path */ - return false; + goto out_free; else continue; } - return true; + ret = true; +out_free: + kfree(idmap); + return ret; +} + +/* A write screens off any subsequent reads; but write marks come from the + * straight-line code between a state and its parent. When we arrive at a + * jump target (in the first iteration of the propagate_liveness() loop), + * we didn't arrive by the straight-line code, so read marks in state must + * propagate to parent regardless of state's write marks. + */ +static bool do_propagate_liveness(const struct bpf_verifier_state *state, + struct bpf_verifier_state *parent) +{ + bool writes = parent == state->parent; /* Observe write marks */ + bool touched = false; /* any changes made? */ + int i; + + if (!parent) + return touched; + /* Propagate read liveness of registers... */ + BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); + /* We don't need to worry about FP liveness because it's read-only */ + for (i = 0; i < BPF_REG_FP; i++) { + if (parent->regs[i].live & REG_LIVE_READ) + continue; + if (writes && (state->regs[i].live & REG_LIVE_WRITTEN)) + continue; + if (state->regs[i].live & REG_LIVE_READ) { + parent->regs[i].live |= REG_LIVE_READ; + touched = true; + } + } + /* ... and stack slots */ + for (i = 0; i < MAX_BPF_STACK / BPF_REG_SIZE; i++) { + if (parent->stack_slot_type[i * BPF_REG_SIZE] != STACK_SPILL) + continue; + if (state->stack_slot_type[i * BPF_REG_SIZE] != STACK_SPILL) + continue; + if (parent->spilled_regs[i].live & REG_LIVE_READ) + continue; + if (writes && (state->spilled_regs[i].live & REG_LIVE_WRITTEN)) + continue; + if (state->spilled_regs[i].live & REG_LIVE_READ) { + parent->spilled_regs[i].live |= REG_LIVE_READ; + touched = true; + } + } + return touched; +} + +/* "parent" is "a state from which we reach the current state", but initially + * it is not the state->parent (i.e. "the state whose straight-line code leads + * to the current state"), instead it is the state that happened to arrive at + * a (prunable) equivalent of the current state. See comment above + * do_propagate_liveness() for consequences of this. + * This function is just a more efficient way of calling mark_reg_read() or + * mark_stack_slot_read() on each reg in "parent" that is read in "state", + * though it requires that parent != state->parent in the call arguments. + */ +static void propagate_liveness(const struct bpf_verifier_state *state, + struct bpf_verifier_state *parent) +{ + while (do_propagate_liveness(state, parent)) { + /* Something changed, so we need to feed those changes onward */ + state = parent; + parent = state->parent; + } } 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; + int i; sl = env->explored_states[insn_idx]; if (!sl) @@ -3021,11 +3496,20 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return 0; while (sl != STATE_LIST_MARK) { - if (states_equal(env, &sl->state, &env->cur_state)) + if (states_equal(env, &sl->state, &env->cur_state)) { /* reached equivalent register/stack state, - * prune the search + * prune the search. + * Registers read by the continuation are read by us. + * If we have any write marks in env->cur_state, they + * will prevent corresponding reads in the continuation + * from reaching our parent (an explored_state). Our + * own state will get the read marks recorded, but + * they'll be immediately forgotten as we're pruning + * this state and will pop a new one. */ + propagate_liveness(&sl->state, &env->cur_state); return 1; + } sl = sl->next; } @@ -3043,6 +3527,19 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) memcpy(&new_sl->state, &env->cur_state, sizeof(env->cur_state)); new_sl->next = env->explored_states[insn_idx]; env->explored_states[insn_idx] = new_sl; + /* connect new state to parentage chain */ + env->cur_state.parent = &new_sl->state; + /* 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 + * their parent and current state never has children yet. Only + * explored_states can get read marks.) + */ + for (i = 0; i < BPF_REG_FP; i++) + env->cur_state.regs[i].live = REG_LIVE_NONE; + for (i = 0; i < MAX_BPF_STACK / BPF_REG_SIZE; i++) + if (env->cur_state.stack_slot_type[i * BPF_REG_SIZE] == STACK_SPILL) + env->cur_state.spilled_regs[i].live = REG_LIVE_NONE; return 0; } @@ -3066,8 +3563,8 @@ static int do_check(struct bpf_verifier_env *env) bool do_print_state = false; init_reg_state(regs); + state->parent = NULL; insn_idx = 0; - env->varlen_map_value_access = false; for (;;) { struct bpf_insn *insn; u8 class; @@ -3136,11 +3633,11 @@ static int do_check(struct bpf_verifier_env *env) /* check for reserved fields is already done */ /* check src operand */ - err = check_reg_arg(regs, insn->src_reg, SRC_OP); + err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; - err = check_reg_arg(regs, insn->dst_reg, DST_OP_NO_MARK); + err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; @@ -3190,11 +3687,11 @@ static int do_check(struct bpf_verifier_env *env) } /* check src1 operand */ - err = check_reg_arg(regs, insn->src_reg, SRC_OP); + err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check src2 operand */ - err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; @@ -3225,7 +3722,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } /* check src operand */ - err = check_reg_arg(regs, insn->dst_reg, SRC_OP); + err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; @@ -3279,7 +3776,7 @@ static int do_check(struct bpf_verifier_env *env) * of bpf_exit, which means that program wrote * something into it earlier */ - err = check_reg_arg(regs, BPF_REG_0, SRC_OP); + err = check_reg_arg(env, BPF_REG_0, SRC_OP); if (err) return err; @@ -3319,7 +3816,6 @@ process_bpf_exit: verbose("invalid BPF_LD mode\n"); return -EINVAL; } - reset_reg_range_values(regs, insn->dst_reg); } else { verbose("unknown insn class %d\n", class); return -EINVAL; @@ -3678,7 +4174,11 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) continue; } - if (ebpf_jit_enabled() && insn->imm == BPF_FUNC_map_lookup_elem) { + /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup + * handlers are currently limited to 64 bit only. + */ + if (ebpf_jit_enabled() && BITS_PER_LONG == 64 && + insn->imm == BPF_FUNC_map_lookup_elem) { map_ptr = env->insn_aux_data[i + delta].map_ptr; if (map_ptr == BPF_MAP_PTR_POISON || !map_ptr->ops->map_gen_lookup) |