diff options
Diffstat (limited to 'kernel/bpf')
-rw-r--r-- | kernel/bpf/Makefile | 8 | ||||
-rw-r--r-- | kernel/bpf/arraymap.c | 265 | ||||
-rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 633 | ||||
-rw-r--r-- | kernel/bpf/bpf_struct_ops_types.h | 9 | ||||
-rw-r--r-- | kernel/bpf/btf.c | 1239 | ||||
-rw-r--r-- | kernel/bpf/cgroup.c | 145 | ||||
-rw-r--r-- | kernel/bpf/core.c | 151 | ||||
-rw-r--r-- | kernel/bpf/cpumap.c | 76 | ||||
-rw-r--r-- | kernel/bpf/devmap.c | 540 | ||||
-rw-r--r-- | kernel/bpf/dispatcher.c | 158 | ||||
-rw-r--r-- | kernel/bpf/hashtab.c | 264 | ||||
-rw-r--r-- | kernel/bpf/helpers.c | 14 | ||||
-rw-r--r-- | kernel/bpf/inode.c | 140 | ||||
-rw-r--r-- | kernel/bpf/local_storage.c | 30 | ||||
-rw-r--r-- | kernel/bpf/map_in_map.c | 10 | ||||
-rw-r--r-- | kernel/bpf/offload.c | 16 | ||||
-rw-r--r-- | kernel/bpf/stackmap.c | 11 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 1120 | ||||
-rw-r--r-- | kernel/bpf/sysfs_btf.c | 46 | ||||
-rw-r--r-- | kernel/bpf/tnum.c | 9 | ||||
-rw-r--r-- | kernel/bpf/trampoline.c | 426 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 1090 | ||||
-rw-r--r-- | kernel/bpf/xskmap.c | 239 |
23 files changed, 5664 insertions, 975 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 29d781061cd5..046ce5d98033 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,9 @@ 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 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o +obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o +obj-$(CONFIG_BPF_JIT) += dispatcher.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o @@ -22,3 +24,9 @@ obj-$(CONFIG_CGROUP_BPF) += cgroup.o ifeq ($(CONFIG_INET),y) obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o endif +ifeq ($(CONFIG_SYSFS),y) +obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o +endif +ifeq ($(CONFIG_BPF_JIT),y) +obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o +endif diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 1c65ce0098a9..95d77770353c 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -14,7 +14,7 @@ #include "map_in_map.h" #define ARRAY_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) + (BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK) static void bpf_array_free_percpu(struct bpf_array *array) { @@ -59,6 +59,10 @@ int array_map_alloc_check(union bpf_attr *attr) (percpu && numa_node != NUMA_NO_NODE)) return -EINVAL; + if (attr->map_type != BPF_MAP_TYPE_ARRAY && + attr->map_flags & BPF_F_MMAPABLE) + return -EINVAL; + if (attr->value_size > KMALLOC_MAX_SIZE) /* if value_size is bigger, the user space won't be able to * access the elements. @@ -102,10 +106,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) } array_size = sizeof(*array); - if (percpu) + if (percpu) { array_size += (u64) max_entries * sizeof(void *); - else - array_size += (u64) max_entries * elem_size; + } else { + /* rely on vmalloc() to return page-aligned memory and + * ensure array->value is exactly page-aligned + */ + if (attr->map_flags & BPF_F_MMAPABLE) { + array_size = PAGE_ALIGN(array_size); + array_size += PAGE_ALIGN((u64) max_entries * elem_size); + } else { + array_size += (u64) max_entries * elem_size; + } + } /* make sure there is no u32 overflow later in round_up() */ cost = array_size; @@ -117,7 +130,20 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) return ERR_PTR(ret); /* allocate all map elements and zero-initialize them */ - array = bpf_map_area_alloc(array_size, numa_node); + if (attr->map_flags & BPF_F_MMAPABLE) { + void *data; + + /* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */ + data = bpf_map_area_mmapable_alloc(array_size, numa_node); + if (!data) { + bpf_map_charge_finish(&mem); + return ERR_PTR(-ENOMEM); + } + array = data + PAGE_ALIGN(sizeof(struct bpf_array)) + - offsetof(struct bpf_array, value); + } else { + array = bpf_map_area_alloc(array_size, numa_node); + } if (!array) { bpf_map_charge_finish(&mem); return ERR_PTR(-ENOMEM); @@ -350,6 +376,11 @@ static int array_map_delete_elem(struct bpf_map *map, void *key) return -EINVAL; } +static void *array_map_vmalloc_addr(struct bpf_array *array) +{ + return (void *)round_down((unsigned long)array, PAGE_SIZE); +} + /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void array_map_free(struct bpf_map *map) { @@ -365,7 +396,10 @@ static void array_map_free(struct bpf_map *map) if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); - bpf_map_area_free(array); + if (array->map.map_flags & BPF_F_MMAPABLE) + bpf_map_area_free(array_map_vmalloc_addr(array)); + else + bpf_map_area_free(array); } static void array_map_seq_show_elem(struct bpf_map *map, void *key, @@ -444,6 +478,17 @@ static int array_map_check_btf(const struct bpf_map *map, return 0; } +static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + pgoff_t pgoff = PAGE_ALIGN(sizeof(*array)) >> PAGE_SHIFT; + + if (!(map->map_flags & BPF_F_MMAPABLE)) + return -EINVAL; + + return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff); +} + const struct bpf_map_ops array_map_ops = { .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, @@ -455,8 +500,11 @@ const struct bpf_map_ops array_map_ops = { .map_gen_lookup = array_map_gen_lookup, .map_direct_value_addr = array_map_direct_value_addr, .map_direct_value_meta = array_map_direct_value_meta, + .map_mmap = array_map_mmap, .map_seq_show_elem = array_map_seq_show_elem, .map_check_btf = array_map_check_btf, + .map_lookup_batch = generic_map_lookup_batch, + .map_update_batch = generic_map_update_batch, }; const struct bpf_map_ops percpu_array_map_ops = { @@ -540,10 +588,17 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, if (IS_ERR(new_ptr)) return PTR_ERR(new_ptr); - old_ptr = xchg(array->ptrs + index, new_ptr); + if (map->ops->map_poke_run) { + mutex_lock(&array->aux->poke_mutex); + old_ptr = xchg(array->ptrs + index, new_ptr); + map->ops->map_poke_run(map, index, old_ptr, new_ptr); + mutex_unlock(&array->aux->poke_mutex); + } else { + old_ptr = xchg(array->ptrs + index, new_ptr); + } + if (old_ptr) map->ops->map_fd_put_ptr(old_ptr); - return 0; } @@ -556,7 +611,15 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key) if (index >= array->map.max_entries) return -E2BIG; - old_ptr = xchg(array->ptrs + index, NULL); + if (map->ops->map_poke_run) { + mutex_lock(&array->aux->poke_mutex); + old_ptr = xchg(array->ptrs + index, NULL); + map->ops->map_poke_run(map, index, old_ptr, NULL); + mutex_unlock(&array->aux->poke_mutex); + } else { + old_ptr = xchg(array->ptrs + index, NULL); + } + if (old_ptr) { map->ops->map_fd_put_ptr(old_ptr); return 0; @@ -625,17 +688,195 @@ static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +struct prog_poke_elem { + struct list_head list; + struct bpf_prog_aux *aux; +}; + +static int prog_array_map_poke_track(struct bpf_map *map, + struct bpf_prog_aux *prog_aux) +{ + struct prog_poke_elem *elem; + struct bpf_array_aux *aux; + int ret = 0; + + aux = container_of(map, struct bpf_array, map)->aux; + mutex_lock(&aux->poke_mutex); + list_for_each_entry(elem, &aux->poke_progs, list) { + if (elem->aux == prog_aux) + goto out; + } + + elem = kmalloc(sizeof(*elem), GFP_KERNEL); + if (!elem) { + ret = -ENOMEM; + goto out; + } + + INIT_LIST_HEAD(&elem->list); + /* We must track the program's aux info at this point in time + * since the program pointer itself may not be stable yet, see + * also comment in prog_array_map_poke_run(). + */ + elem->aux = prog_aux; + + list_add_tail(&elem->list, &aux->poke_progs); +out: + mutex_unlock(&aux->poke_mutex); + return ret; +} + +static void prog_array_map_poke_untrack(struct bpf_map *map, + struct bpf_prog_aux *prog_aux) +{ + struct prog_poke_elem *elem, *tmp; + struct bpf_array_aux *aux; + + aux = container_of(map, struct bpf_array, map)->aux; + mutex_lock(&aux->poke_mutex); + list_for_each_entry_safe(elem, tmp, &aux->poke_progs, list) { + if (elem->aux == prog_aux) { + list_del_init(&elem->list); + kfree(elem); + break; + } + } + mutex_unlock(&aux->poke_mutex); +} + +static void prog_array_map_poke_run(struct bpf_map *map, u32 key, + struct bpf_prog *old, + struct bpf_prog *new) +{ + struct prog_poke_elem *elem; + struct bpf_array_aux *aux; + + aux = container_of(map, struct bpf_array, map)->aux; + WARN_ON_ONCE(!mutex_is_locked(&aux->poke_mutex)); + + list_for_each_entry(elem, &aux->poke_progs, list) { + struct bpf_jit_poke_descriptor *poke; + int i, ret; + + for (i = 0; i < elem->aux->size_poke_tab; i++) { + poke = &elem->aux->poke_tab[i]; + + /* Few things to be aware of: + * + * 1) We can only ever access aux in this context, but + * not aux->prog since it might not be stable yet and + * there could be danger of use after free otherwise. + * 2) Initially when we start tracking aux, the program + * is not JITed yet and also does not have a kallsyms + * entry. We skip these as poke->ip_stable is not + * active yet. The JIT will do the final fixup before + * setting it stable. The various poke->ip_stable are + * successively activated, so tail call updates can + * arrive from here while JIT is still finishing its + * final fixup for non-activated poke entries. + * 3) On program teardown, the program's kallsym entry gets + * removed out of RCU callback, but we can only untrack + * from sleepable context, therefore bpf_arch_text_poke() + * might not see that this is in BPF text section and + * bails out with -EINVAL. As these are unreachable since + * RCU grace period already passed, we simply skip them. + * 4) Also programs reaching refcount of zero while patching + * is in progress is okay since we're protected under + * poke_mutex and untrack the programs before the JIT + * buffer is freed. When we're still in the middle of + * patching and suddenly kallsyms entry of the program + * gets evicted, we just skip the rest which is fine due + * to point 3). + * 5) Any other error happening below from bpf_arch_text_poke() + * is a unexpected bug. + */ + if (!READ_ONCE(poke->ip_stable)) + continue; + if (poke->reason != BPF_POKE_REASON_TAIL_CALL) + continue; + if (poke->tail_call.map != map || + poke->tail_call.key != key) + continue; + + ret = bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP, + old ? (u8 *)old->bpf_func + + poke->adj_off : NULL, + new ? (u8 *)new->bpf_func + + poke->adj_off : NULL); + BUG_ON(ret < 0 && ret != -EINVAL); + } + } +} + +static void prog_array_map_clear_deferred(struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_array_aux, + work)->map; + bpf_fd_array_map_clear(map); + bpf_map_put(map); +} + +static void prog_array_map_clear(struct bpf_map *map) +{ + struct bpf_array_aux *aux = container_of(map, struct bpf_array, + map)->aux; + bpf_map_inc(map); + schedule_work(&aux->work); +} + +static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) +{ + struct bpf_array_aux *aux; + struct bpf_map *map; + + aux = kzalloc(sizeof(*aux), GFP_KERNEL); + if (!aux) + return ERR_PTR(-ENOMEM); + + INIT_WORK(&aux->work, prog_array_map_clear_deferred); + INIT_LIST_HEAD(&aux->poke_progs); + mutex_init(&aux->poke_mutex); + + map = array_map_alloc(attr); + if (IS_ERR(map)) { + kfree(aux); + return map; + } + + container_of(map, struct bpf_array, map)->aux = aux; + aux->map = map; + + return map; +} + +static void prog_array_map_free(struct bpf_map *map) +{ + struct prog_poke_elem *elem, *tmp; + struct bpf_array_aux *aux; + + aux = container_of(map, struct bpf_array, map)->aux; + list_for_each_entry_safe(elem, tmp, &aux->poke_progs, list) { + list_del_init(&elem->list); + kfree(elem); + } + kfree(aux); + fd_array_map_free(map); +} + const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, - .map_alloc = array_map_alloc, - .map_free = fd_array_map_free, + .map_alloc = prog_array_map_alloc, + .map_free = prog_array_map_free, + .map_poke_track = prog_array_map_poke_track, + .map_poke_untrack = prog_array_map_poke_untrack, + .map_poke_run = prog_array_map_poke_run, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = prog_fd_array_get_ptr, .map_fd_put_ptr = prog_fd_array_put_ptr, .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, - .map_release_uref = bpf_fd_array_map_clear, + .map_release_uref = prog_array_map_clear, .map_seq_show_elem = prog_array_map_seq_show_elem, }; diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c new file mode 100644 index 000000000000..042f95534f86 --- /dev/null +++ b/kernel/bpf/bpf_struct_ops.c @@ -0,0 +1,633 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2019 Facebook */ + +#include <linux/bpf.h> +#include <linux/bpf_verifier.h> +#include <linux/btf.h> +#include <linux/filter.h> +#include <linux/slab.h> +#include <linux/numa.h> +#include <linux/seq_file.h> +#include <linux/refcount.h> +#include <linux/mutex.h> + +enum bpf_struct_ops_state { + BPF_STRUCT_OPS_STATE_INIT, + BPF_STRUCT_OPS_STATE_INUSE, + BPF_STRUCT_OPS_STATE_TOBEFREE, +}; + +#define BPF_STRUCT_OPS_COMMON_VALUE \ + refcount_t refcnt; \ + enum bpf_struct_ops_state state + +struct bpf_struct_ops_value { + BPF_STRUCT_OPS_COMMON_VALUE; + char data[0] ____cacheline_aligned_in_smp; +}; + +struct bpf_struct_ops_map { + struct bpf_map map; + const struct bpf_struct_ops *st_ops; + /* protect map_update */ + struct mutex lock; + /* progs has all the bpf_prog that is populated + * to the func ptr of the kernel's struct + * (in kvalue.data). + */ + struct bpf_prog **progs; + /* image is a page that has all the trampolines + * that stores the func args before calling the bpf_prog. + * A PAGE_SIZE "image" is enough to store all trampoline for + * "progs[]". + */ + void *image; + /* uvalue->data stores the kernel struct + * (e.g. tcp_congestion_ops) that is more useful + * to userspace than the kvalue. For example, + * the bpf_prog's id is stored instead of the kernel + * address of a func ptr. + */ + struct bpf_struct_ops_value *uvalue; + /* kvalue.data stores the actual kernel's struct + * (e.g. tcp_congestion_ops) that will be + * registered to the kernel subsystem. + */ + struct bpf_struct_ops_value kvalue; +}; + +#define VALUE_PREFIX "bpf_struct_ops_" +#define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) + +/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is + * the map's value exposed to the userspace and its btf-type-id is + * stored at the map->btf_vmlinux_value_type_id. + * + */ +#define BPF_STRUCT_OPS_TYPE(_name) \ +extern struct bpf_struct_ops bpf_##_name; \ + \ +struct bpf_struct_ops_##_name { \ + BPF_STRUCT_OPS_COMMON_VALUE; \ + struct _name data ____cacheline_aligned_in_smp; \ +}; +#include "bpf_struct_ops_types.h" +#undef BPF_STRUCT_OPS_TYPE + +enum { +#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name, +#include "bpf_struct_ops_types.h" +#undef BPF_STRUCT_OPS_TYPE + __NR_BPF_STRUCT_OPS_TYPE, +}; + +static struct bpf_struct_ops * const bpf_struct_ops[] = { +#define BPF_STRUCT_OPS_TYPE(_name) \ + [BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name, +#include "bpf_struct_ops_types.h" +#undef BPF_STRUCT_OPS_TYPE +}; + +const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { +}; + +const struct bpf_prog_ops bpf_struct_ops_prog_ops = { +}; + +static const struct btf_type *module_type; + +void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) +{ + s32 type_id, value_id, module_id; + const struct btf_member *member; + struct bpf_struct_ops *st_ops; + const struct btf_type *t; + char value_name[128]; + const char *mname; + u32 i, j; + + /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ +#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); +#include "bpf_struct_ops_types.h" +#undef BPF_STRUCT_OPS_TYPE + + module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT); + if (module_id < 0) { + pr_warn("Cannot find struct module in btf_vmlinux\n"); + return; + } + module_type = btf_type_by_id(btf, module_id); + + for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { + st_ops = bpf_struct_ops[i]; + + if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= + sizeof(value_name)) { + pr_warn("struct_ops name %s is too long\n", + st_ops->name); + continue; + } + sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); + + value_id = btf_find_by_name_kind(btf, value_name, + BTF_KIND_STRUCT); + if (value_id < 0) { + pr_warn("Cannot find struct %s in btf_vmlinux\n", + value_name); + continue; + } + + type_id = btf_find_by_name_kind(btf, st_ops->name, + BTF_KIND_STRUCT); + if (type_id < 0) { + pr_warn("Cannot find struct %s in btf_vmlinux\n", + st_ops->name); + continue; + } + t = btf_type_by_id(btf, type_id); + if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { + pr_warn("Cannot support #%u members in struct %s\n", + btf_type_vlen(t), st_ops->name); + continue; + } + + for_each_member(j, t, member) { + const struct btf_type *func_proto; + + mname = btf_name_by_offset(btf, member->name_off); + if (!*mname) { + pr_warn("anon member in struct %s is not supported\n", + st_ops->name); + break; + } + + if (btf_member_bitfield_size(t, member)) { + pr_warn("bit field member %s in struct %s is not supported\n", + mname, st_ops->name); + break; + } + + func_proto = btf_type_resolve_func_ptr(btf, + member->type, + NULL); + if (func_proto && + btf_distill_func_proto(log, btf, + func_proto, mname, + &st_ops->func_models[j])) { + pr_warn("Error in parsing func ptr %s in struct %s\n", + mname, st_ops->name); + break; + } + } + + if (j == btf_type_vlen(t)) { + if (st_ops->init(btf)) { + pr_warn("Error in init bpf_struct_ops %s\n", + st_ops->name); + } else { + st_ops->type_id = type_id; + st_ops->type = t; + st_ops->value_id = value_id; + st_ops->value_type = btf_type_by_id(btf, + value_id); + } + } + } +} + +extern struct btf *btf_vmlinux; + +static const struct bpf_struct_ops * +bpf_struct_ops_find_value(u32 value_id) +{ + unsigned int i; + + if (!value_id || !btf_vmlinux) + return NULL; + + for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { + if (bpf_struct_ops[i]->value_id == value_id) + return bpf_struct_ops[i]; + } + + return NULL; +} + +const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) +{ + unsigned int i; + + if (!type_id || !btf_vmlinux) + return NULL; + + for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { + if (bpf_struct_ops[i]->type_id == type_id) + return bpf_struct_ops[i]; + } + + return NULL; +} + +static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + if (key && *(u32 *)key == 0) + return -ENOENT; + + *(u32 *)next_key = 0; + return 0; +} + +int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, + void *value) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + struct bpf_struct_ops_value *uvalue, *kvalue; + enum bpf_struct_ops_state state; + + if (unlikely(*(u32 *)key != 0)) + return -ENOENT; + + kvalue = &st_map->kvalue; + /* Pair with smp_store_release() during map_update */ + state = smp_load_acquire(&kvalue->state); + if (state == BPF_STRUCT_OPS_STATE_INIT) { + memset(value, 0, map->value_size); + return 0; + } + + /* No lock is needed. state and refcnt do not need + * to be updated together under atomic context. + */ + uvalue = (struct bpf_struct_ops_value *)value; + memcpy(uvalue, st_map->uvalue, map->value_size); + uvalue->state = state; + refcount_set(&uvalue->refcnt, refcount_read(&kvalue->refcnt)); + + return 0; +} + +static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key) +{ + return ERR_PTR(-EINVAL); +} + +static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) +{ + const struct btf_type *t = st_map->st_ops->type; + u32 i; + + for (i = 0; i < btf_type_vlen(t); i++) { + if (st_map->progs[i]) { + bpf_prog_put(st_map->progs[i]); + st_map->progs[i] = NULL; + } + } +} + +static int check_zero_holes(const struct btf_type *t, void *data) +{ + const struct btf_member *member; + u32 i, moff, msize, prev_mend = 0; + const struct btf_type *mtype; + + for_each_member(i, t, member) { + moff = btf_member_bit_offset(t, member) / 8; + if (moff > prev_mend && + memchr_inv(data + prev_mend, 0, moff - prev_mend)) + return -EINVAL; + + mtype = btf_type_by_id(btf_vmlinux, member->type); + mtype = btf_resolve_size(btf_vmlinux, mtype, &msize, + NULL, NULL); + if (IS_ERR(mtype)) + return PTR_ERR(mtype); + prev_mend = moff + msize; + } + + if (t->size > prev_mend && + memchr_inv(data + prev_mend, 0, t->size - prev_mend)) + return -EINVAL; + + return 0; +} + +static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + const struct bpf_struct_ops *st_ops = st_map->st_ops; + struct bpf_struct_ops_value *uvalue, *kvalue; + const struct btf_member *member; + const struct btf_type *t = st_ops->type; + void *udata, *kdata; + int prog_fd, err = 0; + void *image; + u32 i; + + if (flags) + return -EINVAL; + + if (*(u32 *)key != 0) + return -E2BIG; + + err = check_zero_holes(st_ops->value_type, value); + if (err) + return err; + + uvalue = (struct bpf_struct_ops_value *)value; + err = check_zero_holes(t, uvalue->data); + if (err) + return err; + + if (uvalue->state || refcount_read(&uvalue->refcnt)) + return -EINVAL; + + uvalue = (struct bpf_struct_ops_value *)st_map->uvalue; + kvalue = (struct bpf_struct_ops_value *)&st_map->kvalue; + + mutex_lock(&st_map->lock); + + if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) { + err = -EBUSY; + goto unlock; + } + + memcpy(uvalue, value, map->value_size); + + udata = &uvalue->data; + kdata = &kvalue->data; + image = st_map->image; + + for_each_member(i, t, member) { + const struct btf_type *mtype, *ptype; + struct bpf_prog *prog; + u32 moff; + + moff = btf_member_bit_offset(t, member) / 8; + ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); + if (ptype == module_type) { + if (*(void **)(udata + moff)) + goto reset_unlock; + *(void **)(kdata + moff) = BPF_MODULE_OWNER; + continue; + } + + err = st_ops->init_member(t, member, kdata, udata); + if (err < 0) + goto reset_unlock; + + /* The ->init_member() has handled this member */ + if (err > 0) + continue; + + /* If st_ops->init_member does not handle it, + * we will only handle func ptrs and zero-ed members + * here. Reject everything else. + */ + + /* All non func ptr member must be 0 */ + if (!ptype || !btf_type_is_func_proto(ptype)) { + u32 msize; + + mtype = btf_type_by_id(btf_vmlinux, member->type); + mtype = btf_resolve_size(btf_vmlinux, mtype, &msize, + NULL, NULL); + if (IS_ERR(mtype)) { + err = PTR_ERR(mtype); + goto reset_unlock; + } + + if (memchr_inv(udata + moff, 0, msize)) { + err = -EINVAL; + goto reset_unlock; + } + + continue; + } + + prog_fd = (int)(*(unsigned long *)(udata + moff)); + /* Similar check as the attr->attach_prog_fd */ + if (!prog_fd) + continue; + + prog = bpf_prog_get(prog_fd); + if (IS_ERR(prog)) { + err = PTR_ERR(prog); + goto reset_unlock; + } + st_map->progs[i] = prog; + + if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || + prog->aux->attach_btf_id != st_ops->type_id || + prog->expected_attach_type != i) { + err = -EINVAL; + goto reset_unlock; + } + + err = arch_prepare_bpf_trampoline(image, + st_map->image + PAGE_SIZE, + &st_ops->func_models[i], 0, + &prog, 1, NULL, 0, NULL); + if (err < 0) + goto reset_unlock; + + *(void **)(kdata + moff) = image; + image += err; + + /* put prog_id to udata */ + *(unsigned long *)(udata + moff) = prog->aux->id; + } + + refcount_set(&kvalue->refcnt, 1); + bpf_map_inc(map); + + set_memory_ro((long)st_map->image, 1); + set_memory_x((long)st_map->image, 1); + err = st_ops->reg(kdata); + if (likely(!err)) { + /* Pair with smp_load_acquire() during lookup_elem(). + * It ensures the above udata updates (e.g. prog->aux->id) + * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set. + */ + smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE); + goto unlock; + } + + /* Error during st_ops->reg(). It is very unlikely since + * the above init_member() should have caught it earlier + * before reg(). The only possibility is if there was a race + * in registering the struct_ops (under the same name) to + * a sub-system through different struct_ops's maps. + */ + set_memory_nx((long)st_map->image, 1); + set_memory_rw((long)st_map->image, 1); + bpf_map_put(map); + +reset_unlock: + bpf_struct_ops_map_put_progs(st_map); + memset(uvalue, 0, map->value_size); + memset(kvalue, 0, map->value_size); +unlock: + mutex_unlock(&st_map->lock); + return err; +} + +static int bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) +{ + enum bpf_struct_ops_state prev_state; + struct bpf_struct_ops_map *st_map; + + st_map = (struct bpf_struct_ops_map *)map; + prev_state = cmpxchg(&st_map->kvalue.state, + BPF_STRUCT_OPS_STATE_INUSE, + BPF_STRUCT_OPS_STATE_TOBEFREE); + if (prev_state == BPF_STRUCT_OPS_STATE_INUSE) { + st_map->st_ops->unreg(&st_map->kvalue.data); + if (refcount_dec_and_test(&st_map->kvalue.refcnt)) + bpf_map_put(map); + } + + return 0; +} + +static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + void *value; + int err; + + value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN); + if (!value) + return; + + err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); + if (!err) { + btf_type_seq_show(btf_vmlinux, map->btf_vmlinux_value_type_id, + value, m); + seq_puts(m, "\n"); + } + + kfree(value); +} + +static void bpf_struct_ops_map_free(struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + if (st_map->progs) + bpf_struct_ops_map_put_progs(st_map); + bpf_map_area_free(st_map->progs); + bpf_jit_free_exec(st_map->image); + bpf_map_area_free(st_map->uvalue); + bpf_map_area_free(st_map); +} + +static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) +{ + if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 || + attr->map_flags || !attr->btf_vmlinux_value_type_id) + return -EINVAL; + return 0; +} + +static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) +{ + const struct bpf_struct_ops *st_ops; + size_t map_total_size, st_map_size; + struct bpf_struct_ops_map *st_map; + const struct btf_type *t, *vt; + struct bpf_map_memory mem; + struct bpf_map *map; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); + if (!st_ops) + return ERR_PTR(-ENOTSUPP); + + vt = st_ops->value_type; + if (attr->value_size != vt->size) + return ERR_PTR(-EINVAL); + + t = st_ops->type; + + st_map_size = sizeof(*st_map) + + /* kvalue stores the + * struct bpf_struct_ops_tcp_congestions_ops + */ + (vt->size - sizeof(struct bpf_struct_ops_value)); + map_total_size = st_map_size + + /* uvalue */ + sizeof(vt->size) + + /* struct bpf_progs **progs */ + btf_type_vlen(t) * sizeof(struct bpf_prog *); + err = bpf_map_charge_init(&mem, map_total_size); + if (err < 0) + return ERR_PTR(err); + + st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE); + if (!st_map) { + bpf_map_charge_finish(&mem); + return ERR_PTR(-ENOMEM); + } + st_map->st_ops = st_ops; + map = &st_map->map; + + st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); + st_map->progs = + bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_prog *), + NUMA_NO_NODE); + st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!st_map->uvalue || !st_map->progs || !st_map->image) { + bpf_struct_ops_map_free(map); + bpf_map_charge_finish(&mem); + return ERR_PTR(-ENOMEM); + } + + mutex_init(&st_map->lock); + set_vm_flush_reset_perms(st_map->image); + bpf_map_init_from_attr(map, attr); + bpf_map_charge_move(&map->memory, &mem); + + return map; +} + +const struct bpf_map_ops bpf_struct_ops_map_ops = { + .map_alloc_check = bpf_struct_ops_map_alloc_check, + .map_alloc = bpf_struct_ops_map_alloc, + .map_free = bpf_struct_ops_map_free, + .map_get_next_key = bpf_struct_ops_map_get_next_key, + .map_lookup_elem = bpf_struct_ops_map_lookup_elem, + .map_delete_elem = bpf_struct_ops_map_delete_elem, + .map_update_elem = bpf_struct_ops_map_update_elem, + .map_seq_show_elem = bpf_struct_ops_map_seq_show_elem, +}; + +/* "const void *" because some subsystem is + * passing a const (e.g. const struct tcp_congestion_ops *) + */ +bool bpf_struct_ops_get(const void *kdata) +{ + struct bpf_struct_ops_value *kvalue; + + kvalue = container_of(kdata, struct bpf_struct_ops_value, data); + + return refcount_inc_not_zero(&kvalue->refcnt); +} + +void bpf_struct_ops_put(const void *kdata) +{ + struct bpf_struct_ops_value *kvalue; + + kvalue = container_of(kdata, struct bpf_struct_ops_value, data); + if (refcount_dec_and_test(&kvalue->refcnt)) { + struct bpf_struct_ops_map *st_map; + + st_map = container_of(kvalue, struct bpf_struct_ops_map, + kvalue); + bpf_map_put(&st_map->map); + } +} diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h new file mode 100644 index 000000000000..066d83ea1c99 --- /dev/null +++ b/kernel/bpf/bpf_struct_ops_types.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* internal file - do not include directly */ + +#ifdef CONFIG_BPF_JIT +#ifdef CONFIG_INET +#include <net/tcp.h> +BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) +#endif +#endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 5fcc7a17eb5a..805c43b083e9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2,6 +2,8 @@ /* Copyright (c) 2018 Facebook */ #include <uapi/linux/btf.h> +#include <uapi/linux/bpf.h> +#include <uapi/linux/bpf_perf_event.h> #include <uapi/linux/types.h> #include <linux/seq_file.h> #include <linux/compiler.h> @@ -16,6 +18,9 @@ #include <linux/sort.h> #include <linux/bpf_verifier.h> #include <linux/btf.h> +#include <linux/skmsg.h> +#include <linux/perf_event.h> +#include <net/sock.h> /* BTF (BPF Type Format) is the meta data format which describes * the data types of BPF program/map. Hence, it basically focus @@ -175,11 +180,6 @@ */ #define BTF_MAX_SIZE (16 * 1024 * 1024) -#define for_each_member(i, struct_type, member) \ - for (i = 0, member = btf_type_member(struct_type); \ - i < btf_type_vlen(struct_type); \ - i++, member++) - #define for_each_member_from(i, from, struct_type, member) \ for (i = from, member = btf_type_member(struct_type) + from; \ i < btf_type_vlen(struct_type); \ @@ -195,8 +195,8 @@ i < btf_type_vlen(struct_type); \ i++, member++) -static DEFINE_IDR(btf_idr); -static DEFINE_SPINLOCK(btf_idr_lock); +DEFINE_IDR(btf_idr); +DEFINE_SPINLOCK(btf_idr_lock); struct btf { void *data; @@ -276,6 +276,11 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_DATASEC] = "DATASEC", }; +static const char *btf_type_str(const struct btf_type *t) +{ + return btf_kind_str[BTF_INFO_KIND(t->info)]; +} + struct btf_kind_operations { s32 (*check_meta)(struct btf_verifier_env *env, const struct btf_type *t, @@ -336,16 +341,6 @@ static bool btf_type_is_fwd(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; } -static bool btf_type_is_func(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; -} - -static bool btf_type_is_func_proto(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; -} - static bool btf_type_nosize(const struct btf_type *t) { return btf_type_is_void(t) || btf_type_is_fwd(t) || @@ -377,24 +372,73 @@ static bool btf_type_is_array(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; } -static bool btf_type_is_ptr(const struct btf_type *t) +static bool btf_type_is_var(const struct btf_type *t) { - return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; + return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; } -static bool btf_type_is_int(const struct btf_type *t) +static bool btf_type_is_datasec(const struct btf_type *t) { - return BTF_INFO_KIND(t->info) == BTF_KIND_INT; + return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } -static bool btf_type_is_var(const struct btf_type *t) +s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind) { - return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; + const struct btf_type *t; + const char *tname; + u32 i; + + for (i = 1; i <= btf->nr_types; i++) { + t = btf->types[i]; + if (BTF_INFO_KIND(t->info) != kind) + continue; + + tname = btf_name_by_offset(btf, t->name_off); + if (!strcmp(tname, name)) + return i; + } + + return -ENOENT; } -static bool btf_type_is_datasec(const struct btf_type *t) +const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, + u32 id, u32 *res_id) { - return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; + const struct btf_type *t = btf_type_by_id(btf, id); + + while (btf_type_is_modifier(t)) { + id = t->type; + t = btf_type_by_id(btf, t->type); + } + + if (res_id) + *res_id = id; + + return t; +} + +const struct btf_type *btf_type_resolve_ptr(const struct btf *btf, + u32 id, u32 *res_id) +{ + const struct btf_type *t; + + t = btf_type_skip_modifiers(btf, id, NULL); + if (!btf_type_is_ptr(t)) + return NULL; + + return btf_type_skip_modifiers(btf, t->type, res_id); +} + +const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, + u32 id, u32 *res_id) +{ + const struct btf_type *ptype; + + ptype = btf_type_resolve_ptr(btf, id, res_id); + if (ptype && btf_type_is_func_proto(ptype)) + return ptype; + + return NULL; } /* Types that act only as a source, not sink or intermediate @@ -461,30 +505,6 @@ static const char *btf_int_encoding_str(u8 encoding) return "UNKN"; } -static u16 btf_type_vlen(const struct btf_type *t) -{ - return BTF_INFO_VLEN(t->info); -} - -static bool btf_type_kflag(const struct btf_type *t) -{ - return BTF_INFO_KFLAG(t->info); -} - -static u32 btf_member_bit_offset(const struct btf_type *struct_type, - const struct btf_member *member) -{ - return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) - : member->offset; -} - -static u32 btf_member_bitfield_size(const struct btf_type *struct_type, - const struct btf_member *member) -{ - return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) - : 0; -} - static u32 btf_type_int(const struct btf_type *t) { return *(u32 *)(t + 1); @@ -495,11 +515,6 @@ static const struct btf_array *btf_type_array(const struct btf_type *t) return (const struct btf_array *)(t + 1); } -static const struct btf_member *btf_type_member(const struct btf_type *t) -{ - return (const struct btf_member *)(t + 1); -} - static const struct btf_enum *btf_type_enum(const struct btf_type *t) { return (const struct btf_enum *)(t + 1); @@ -698,6 +713,13 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; + /* btf verifier prints all types it is processing via + * btf_verifier_log_type(..., fmt = NULL). + * Skip those prints for in-kernel BTF verification. + */ + if (log->level == BPF_LOG_KERNEL && !fmt) + return; + __btf_verifier_log(log, "[%u] %s %s%s", env->log_type_id, btf_kind_str[kind], @@ -735,6 +757,8 @@ static void btf_verifier_log_member(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; + if (log->level == BPF_LOG_KERNEL && !fmt) + return; /* The CHECK_META phase already did a btf dump. * * If member is logged again, it must hit an error in @@ -777,6 +801,8 @@ static void btf_verifier_log_vsi(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; + if (log->level == BPF_LOG_KERNEL && !fmt) + return; if (env->phase != CHECK_META) btf_verifier_log_type(env, datasec_type, NULL); @@ -802,6 +828,8 @@ static void btf_verifier_log_hdr(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; + if (log->level == BPF_LOG_KERNEL) + return; hdr = &btf->hdr; __btf_verifier_log(log, "magic: 0x%x\n", hdr->magic); __btf_verifier_log(log, "version: %u\n", hdr->version); @@ -1043,6 +1071,84 @@ static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env) return env->top_stack ? &env->stack[env->top_stack - 1] : NULL; } +/* Resolve the size of a passed-in "type" + * + * type: is an array (e.g. u32 array[x][y]) + * return type: type "u32[x][y]", i.e. BTF_KIND_ARRAY, + * *type_size: (x * y * sizeof(u32)). Hence, *type_size always + * corresponds to the return type. + * *elem_type: u32 + * *total_nelems: (x * y). Hence, individual elem size is + * (*type_size / *total_nelems) + * + * type: is not an array (e.g. const struct X) + * return type: type "struct X" + * *type_size: sizeof(struct X) + * *elem_type: same as return type ("struct X") + * *total_nelems: 1 + */ +const struct btf_type * +btf_resolve_size(const struct btf *btf, const struct btf_type *type, + u32 *type_size, const struct btf_type **elem_type, + u32 *total_nelems) +{ + const struct btf_type *array_type = NULL; + const struct btf_array *array; + u32 i, size, nelems = 1; + + for (i = 0; i < MAX_RESOLVE_DEPTH; i++) { + switch (BTF_INFO_KIND(type->info)) { + /* type->size can be used */ + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + size = type->size; + goto resolved; + + case BTF_KIND_PTR: + size = sizeof(void *); + goto resolved; + + /* Modifiers */ + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + type = btf_type_by_id(btf, type->type); + break; + + case BTF_KIND_ARRAY: + if (!array_type) + array_type = type; + array = btf_type_array(type); + if (nelems && array->nelems > U32_MAX / nelems) + return ERR_PTR(-EINVAL); + nelems *= array->nelems; + type = btf_type_by_id(btf, array->type); + break; + + /* type without size */ + default: + return ERR_PTR(-EINVAL); + } + } + + return ERR_PTR(-EINVAL); + +resolved: + if (nelems && size > U32_MAX / nelems) + return ERR_PTR(-EINVAL); + + *type_size = nelems * size; + if (total_nelems) + *total_nelems = nelems; + if (elem_type) + *elem_type = type; + + return array_type ? : type; +} + /* The input param "type_id" must point to a needs_resolve type */ static const struct btf_type *btf_type_id_resolve(const struct btf *btf, u32 *type_id) @@ -1752,7 +1858,10 @@ static void btf_modifier_seq_show(const struct btf *btf, u32 type_id, void *data, u8 bits_offset, struct seq_file *m) { - t = btf_type_id_resolve(btf, &type_id); + if (btf->resolved_ids) + t = btf_type_id_resolve(btf, &type_id); + else + t = btf_type_skip_modifiers(btf, type_id, NULL); btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m); } @@ -2332,7 +2441,7 @@ static int btf_enum_check_kflag_member(struct btf_verifier_env *env, if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); - return -EINVAL; + return -EINVAL; } nr_bits = int_bitsize; @@ -2377,9 +2486,8 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (t->size != sizeof(int)) { - btf_verifier_log_type(env, t, "Expected size:%zu", - sizeof(int)); + if (t->size > 8 || !is_power_of_2(t->size)) { + btf_verifier_log_type(env, t, "Unexpected size"); return -EINVAL; } @@ -2406,7 +2514,8 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, return -EINVAL; } - + if (env->log.level == BPF_LOG_KERNEL) + continue; btf_verifier_log(env, "\t%s val=%d\n", __btf_name_by_offset(btf, enums[i].name_off), enums[i].val); @@ -2547,8 +2656,8 @@ static s32 btf_func_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (btf_type_vlen(t)) { - btf_verifier_log_type(env, t, "vlen != 0"); + if (btf_type_vlen(t) > BTF_FUNC_GLOBAL) { + btf_verifier_log_type(env, t, "Invalid func linkage"); return -EINVAL; } @@ -3368,6 +3477,1000 @@ errout: return ERR_PTR(err); } +extern char __weak _binary__btf_vmlinux_bin_start[]; +extern char __weak _binary__btf_vmlinux_bin_end[]; +extern struct btf *btf_vmlinux; + +#define BPF_MAP_TYPE(_id, _ops) +static union { + struct bpf_ctx_convert { +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ + prog_ctx_type _id##_prog; \ + kern_ctx_type _id##_kern; +#include <linux/bpf_types.h> +#undef BPF_PROG_TYPE + } *__t; + /* 't' is written once under lock. Read many times. */ + const struct btf_type *t; +} bpf_ctx_convert; +enum { +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ + __ctx_convert##_id, +#include <linux/bpf_types.h> +#undef BPF_PROG_TYPE + __ctx_convert_unused, /* to avoid empty enum in extreme .config */ +}; +static u8 bpf_ctx_convert_map[] = { +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ + [_id] = __ctx_convert##_id, +#include <linux/bpf_types.h> +#undef BPF_PROG_TYPE + 0, /* avoid empty array */ +}; +#undef BPF_MAP_TYPE + +static const struct btf_member * +btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) +{ + const struct btf_type *conv_struct; + const struct btf_type *ctx_struct; + const struct btf_member *ctx_type; + const char *tname, *ctx_tname; + + conv_struct = bpf_ctx_convert.t; + if (!conv_struct) { + bpf_log(log, "btf_vmlinux is malformed\n"); + return NULL; + } + t = btf_type_by_id(btf, t->type); + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (!btf_type_is_struct(t)) { + /* Only pointer to struct is supported for now. + * That means that BPF_PROG_TYPE_TRACEPOINT with BTF + * is not supported yet. + * BPF_PROG_TYPE_RAW_TRACEPOINT is fine. + */ + if (log->level & BPF_LOG_LEVEL) + bpf_log(log, "arg#%d type is not a struct\n", arg); + return NULL; + } + tname = btf_name_by_offset(btf, t->name_off); + if (!tname) { + bpf_log(log, "arg#%d struct doesn't have a name\n", arg); + return NULL; + } + /* prog_type is valid bpf program type. No need for bounds check. */ + ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; + /* ctx_struct is a pointer to prog_ctx_type in vmlinux. + * Like 'struct __sk_buff' + */ + ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type); + if (!ctx_struct) + /* should not happen */ + return NULL; + ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off); + if (!ctx_tname) { + /* should not happen */ + bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); + return NULL; + } + /* only compare that prog's ctx type name is the same as + * kernel expects. No need to compare field by field. + * It's ok for bpf prog to do: + * struct __sk_buff {}; + * int socket_filter_bpf_prog(struct __sk_buff *skb) + * { // no fields of skb are ever used } + */ + if (strcmp(ctx_tname, tname)) + return NULL; + return ctx_type; +} + +static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, + struct btf *btf, + const struct btf_type *t, + enum bpf_prog_type prog_type, + int arg) +{ + const struct btf_member *prog_ctx_type, *kern_ctx_type; + + prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg); + if (!prog_ctx_type) + return -ENOENT; + kern_ctx_type = prog_ctx_type + 1; + return kern_ctx_type->type; +} + +struct btf *btf_parse_vmlinux(void) +{ + struct btf_verifier_env *env = NULL; + struct bpf_verifier_log *log; + struct btf *btf = NULL; + int err, i; + + env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); + if (!env) + return ERR_PTR(-ENOMEM); + + log = &env->log; + log->level = BPF_LOG_KERNEL; + + btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); + if (!btf) { + err = -ENOMEM; + goto errout; + } + env->btf = btf; + + btf->data = _binary__btf_vmlinux_bin_start; + btf->data_size = _binary__btf_vmlinux_bin_end - + _binary__btf_vmlinux_bin_start; + + err = btf_parse_hdr(env); + if (err) + goto errout; + + btf->nohdr_data = btf->data + btf->hdr.hdr_len; + + err = btf_parse_str_sec(env); + if (err) + goto errout; + + err = btf_check_all_metas(env); + if (err) + goto errout; + + /* find struct bpf_ctx_convert for type checking later */ + for (i = 1; i <= btf->nr_types; i++) { + const struct btf_type *t; + const char *tname; + + t = btf_type_by_id(btf, i); + if (!__btf_type_is_struct(t)) + continue; + tname = __btf_name_by_offset(btf, t->name_off); + if (!strcmp(tname, "bpf_ctx_convert")) { + /* btf_parse_vmlinux() runs under bpf_verifier_lock */ + bpf_ctx_convert.t = t; + break; + } + } + if (i > btf->nr_types) { + err = -ENOENT; + goto errout; + } + + bpf_struct_ops_init(btf, log); + + btf_verifier_env_free(env); + refcount_set(&btf->refcnt, 1); + return btf; + +errout: + btf_verifier_env_free(env); + if (btf) { + kvfree(btf->types); + kfree(btf); + } + return ERR_PTR(err); +} + +struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) +{ + struct bpf_prog *tgt_prog = prog->aux->linked_prog; + + if (tgt_prog) { + return tgt_prog->aux->btf; + } else { + return btf_vmlinux; + } +} + +static bool is_string_ptr(struct btf *btf, const struct btf_type *t) +{ + /* t comes in already as a pointer */ + t = btf_type_by_id(btf, t->type); + + /* allow const */ + if (BTF_INFO_KIND(t->info) == BTF_KIND_CONST) + t = btf_type_by_id(btf, t->type); + + /* char, signed char, unsigned char */ + return btf_type_is_int(t) && t->size == 1; +} + +bool btf_ctx_access(int off, int size, enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + const struct btf_type *t = prog->aux->attach_func_proto; + struct bpf_prog *tgt_prog = prog->aux->linked_prog; + struct btf *btf = bpf_prog_get_target_btf(prog); + const char *tname = prog->aux->attach_func_name; + struct bpf_verifier_log *log = info->log; + const struct btf_param *args; + u32 nr_args, arg; + int ret; + + if (off % 8) { + bpf_log(log, "func '%s' offset %d is not multiple of 8\n", + tname, off); + return false; + } + arg = off / 8; + args = (const struct btf_param *)(t + 1); + /* if (t == NULL) Fall back to default BPF prog with 5 u64 arguments */ + nr_args = t ? btf_type_vlen(t) : 5; + if (prog->aux->attach_btf_trace) { + /* skip first 'void *__data' argument in btf_trace_##name typedef */ + args++; + nr_args--; + } + + if (prog->expected_attach_type == BPF_TRACE_FEXIT && + arg == nr_args) { + if (!t) + /* Default prog with 5 args. 6th arg is retval. */ + return true; + /* function return type */ + t = btf_type_by_id(btf, t->type); + } else if (arg >= nr_args) { + bpf_log(log, "func '%s' doesn't have %d-th argument\n", + tname, arg + 1); + return false; + } else { + if (!t) + /* Default prog with 5 args */ + return true; + t = btf_type_by_id(btf, args[arg].type); + } + /* skip modifiers */ + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (btf_type_is_int(t) || btf_type_is_enum(t)) + /* accessing a scalar */ + return true; + if (!btf_type_is_ptr(t)) { + bpf_log(log, + "func '%s' arg%d '%s' has type %s. Only pointer access is allowed\n", + tname, arg, + __btf_name_by_offset(btf, t->name_off), + btf_kind_str[BTF_INFO_KIND(t->info)]); + return false; + } + if (t->type == 0) + /* This is a pointer to void. + * It is the same as scalar from the verifier safety pov. + * No further pointer walking is allowed. + */ + return true; + + if (is_string_ptr(btf, t)) + return true; + + /* this is a pointer to another type */ + info->reg_type = PTR_TO_BTF_ID; + + if (tgt_prog) { + ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type, arg); + if (ret > 0) { + info->btf_id = ret; + return true; + } else { + return false; + } + } + + info->btf_id = t->type; + t = btf_type_by_id(btf, t->type); + /* skip modifiers */ + while (btf_type_is_modifier(t)) { + info->btf_id = t->type; + t = btf_type_by_id(btf, t->type); + } + if (!btf_type_is_struct(t)) { + bpf_log(log, + "func '%s' arg%d type %s is not a struct\n", + tname, arg, btf_kind_str[BTF_INFO_KIND(t->info)]); + return false; + } + bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n", + tname, arg, info->btf_id, btf_kind_str[BTF_INFO_KIND(t->info)], + __btf_name_by_offset(btf, t->name_off)); + return true; +} + +int btf_struct_access(struct bpf_verifier_log *log, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, + u32 *next_btf_id) +{ + u32 i, moff, mtrue_end, msize = 0, total_nelems = 0; + const struct btf_type *mtype, *elem_type = NULL; + const struct btf_member *member; + const char *tname, *mname; + +again: + tname = __btf_name_by_offset(btf_vmlinux, t->name_off); + if (!btf_type_is_struct(t)) { + bpf_log(log, "Type '%s' is not a struct\n", tname); + return -EINVAL; + } + + if (off + size > t->size) { + bpf_log(log, "access beyond struct %s at off %u size %u\n", + tname, off, size); + return -EACCES; + } + + for_each_member(i, t, member) { + /* offset of the field in bytes */ + moff = btf_member_bit_offset(t, member) / 8; + if (off + size <= moff) + /* won't find anything, field is already too far */ + break; + + if (btf_member_bitfield_size(t, member)) { + u32 end_bit = btf_member_bit_offset(t, member) + + btf_member_bitfield_size(t, member); + + /* off <= moff instead of off == moff because clang + * does not generate a BTF member for anonymous + * bitfield like the ":16" here: + * struct { + * int :16; + * int x:8; + * }; + */ + if (off <= moff && + BITS_ROUNDUP_BYTES(end_bit) <= off + size) + return SCALAR_VALUE; + + /* off may be accessing a following member + * + * or + * + * Doing partial access at either end of this + * bitfield. Continue on this case also to + * treat it as not accessing this bitfield + * and eventually error out as field not + * found to keep it simple. + * It could be relaxed if there was a legit + * partial access case later. + */ + continue; + } + + /* In case of "off" is pointing to holes of a struct */ + if (off < moff) + break; + + /* type of the field */ + mtype = btf_type_by_id(btf_vmlinux, member->type); + mname = __btf_name_by_offset(btf_vmlinux, member->name_off); + + mtype = btf_resolve_size(btf_vmlinux, mtype, &msize, + &elem_type, &total_nelems); + if (IS_ERR(mtype)) { + bpf_log(log, "field %s doesn't have size\n", mname); + return -EFAULT; + } + + mtrue_end = moff + msize; + if (off >= mtrue_end) + /* no overlap with member, keep iterating */ + continue; + + if (btf_type_is_array(mtype)) { + u32 elem_idx; + + /* btf_resolve_size() above helps to + * linearize a multi-dimensional array. + * + * The logic here is treating an array + * in a struct as the following way: + * + * struct outer { + * struct inner array[2][2]; + * }; + * + * looks like: + * + * struct outer { + * struct inner array_elem0; + * struct inner array_elem1; + * struct inner array_elem2; + * struct inner array_elem3; + * }; + * + * When accessing outer->array[1][0], it moves + * moff to "array_elem2", set mtype to + * "struct inner", and msize also becomes + * sizeof(struct inner). Then most of the + * remaining logic will fall through without + * caring the current member is an array or + * not. + * + * Unlike mtype/msize/moff, mtrue_end does not + * change. The naming difference ("_true") tells + * that it is not always corresponding to + * the current mtype/msize/moff. + * It is the true end of the current + * member (i.e. array in this case). That + * will allow an int array to be accessed like + * a scratch space, + * i.e. allow access beyond the size of + * the array's element as long as it is + * within the mtrue_end boundary. + */ + + /* skip empty array */ + if (moff == mtrue_end) + continue; + + msize /= total_nelems; + elem_idx = (off - moff) / msize; + moff += elem_idx * msize; + mtype = elem_type; + } + + /* the 'off' we're looking for is either equal to start + * of this field or inside of this struct + */ + if (btf_type_is_struct(mtype)) { + /* our field must be inside that union or struct */ + t = mtype; + + /* adjust offset we're looking for */ + off -= moff; + goto again; + } + + if (btf_type_is_ptr(mtype)) { + const struct btf_type *stype; + u32 id; + + if (msize != size || off != moff) { + bpf_log(log, + "cannot access ptr member %s with moff %u in struct %s with off %u size %u\n", + mname, moff, tname, off, size); + return -EACCES; + } + + stype = btf_type_skip_modifiers(btf_vmlinux, mtype->type, &id); + if (btf_type_is_struct(stype)) { + *next_btf_id = id; + return PTR_TO_BTF_ID; + } + } + + /* Allow more flexible access within an int as long as + * it is within mtrue_end. + * Since mtrue_end could be the end of an array, + * that also allows using an array of int as a scratch + * space. e.g. skb->cb[]. + */ + if (off + size > mtrue_end) { + bpf_log(log, + "access beyond the end of member %s (mend:%u) in struct %s with off %u size %u\n", + mname, mtrue_end, tname, off, size); + return -EACCES; + } + + return SCALAR_VALUE; + } + bpf_log(log, "struct %s doesn't have field at offset %d\n", tname, off); + return -EINVAL; +} + +static int __btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, + int arg) +{ + char fnname[KSYM_SYMBOL_LEN + 4] = "btf_"; + const struct btf_param *args; + const struct btf_type *t; + const char *tname, *sym; + u32 btf_id, i; + + if (IS_ERR(btf_vmlinux)) { + bpf_log(log, "btf_vmlinux is malformed\n"); + return -EINVAL; + } + + sym = kallsyms_lookup((long)fn, NULL, NULL, NULL, fnname + 4); + if (!sym) { + bpf_log(log, "kernel doesn't have kallsyms\n"); + return -EFAULT; + } + + for (i = 1; i <= btf_vmlinux->nr_types; i++) { + t = btf_type_by_id(btf_vmlinux, i); + if (BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) + continue; + tname = __btf_name_by_offset(btf_vmlinux, t->name_off); + if (!strcmp(tname, fnname)) + break; + } + if (i > btf_vmlinux->nr_types) { + bpf_log(log, "helper %s type is not found\n", fnname); + return -ENOENT; + } + + t = btf_type_by_id(btf_vmlinux, t->type); + if (!btf_type_is_ptr(t)) + return -EFAULT; + t = btf_type_by_id(btf_vmlinux, t->type); + if (!btf_type_is_func_proto(t)) + return -EFAULT; + + args = (const struct btf_param *)(t + 1); + if (arg >= btf_type_vlen(t)) { + bpf_log(log, "bpf helper %s doesn't have %d-th argument\n", + fnname, arg); + return -EINVAL; + } + + t = btf_type_by_id(btf_vmlinux, args[arg].type); + if (!btf_type_is_ptr(t) || !t->type) { + /* anything but the pointer to struct is a helper config bug */ + bpf_log(log, "ARG_PTR_TO_BTF is misconfigured\n"); + return -EFAULT; + } + btf_id = t->type; + t = btf_type_by_id(btf_vmlinux, t->type); + /* skip modifiers */ + while (btf_type_is_modifier(t)) { + btf_id = t->type; + t = btf_type_by_id(btf_vmlinux, t->type); + } + if (!btf_type_is_struct(t)) { + bpf_log(log, "ARG_PTR_TO_BTF is not a struct\n"); + return -EFAULT; + } + bpf_log(log, "helper %s arg%d has btf_id %d struct %s\n", fnname + 4, + arg, btf_id, __btf_name_by_offset(btf_vmlinux, t->name_off)); + return btf_id; +} + +int btf_resolve_helper_id(struct bpf_verifier_log *log, + const struct bpf_func_proto *fn, int arg) +{ + int *btf_id = &fn->btf_id[arg]; + int ret; + + if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID) + return -EINVAL; + + ret = READ_ONCE(*btf_id); + if (ret) + return ret; + /* ok to race the search. The result is the same */ + ret = __btf_resolve_helper_id(log, fn->func, arg); + if (!ret) { + /* Function argument cannot be type 'void' */ + bpf_log(log, "BTF resolution bug\n"); + return -EFAULT; + } + WRITE_ONCE(*btf_id, ret); + return ret; +} + +static int __get_type_size(struct btf *btf, u32 btf_id, + const struct btf_type **bad_type) +{ + const struct btf_type *t; + + if (!btf_id) + /* void */ + return 0; + t = btf_type_by_id(btf, btf_id); + while (t && btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (!t) { + *bad_type = btf->types[0]; + return -EINVAL; + } + if (btf_type_is_ptr(t)) + /* kernel size of pointer. Not BPF's size of pointer*/ + return sizeof(void *); + if (btf_type_is_int(t) || btf_type_is_enum(t)) + return t->size; + *bad_type = t; + return -EINVAL; +} + +int btf_distill_func_proto(struct bpf_verifier_log *log, + struct btf *btf, + const struct btf_type *func, + const char *tname, + struct btf_func_model *m) +{ + const struct btf_param *args; + const struct btf_type *t; + u32 i, nargs; + int ret; + + if (!func) { + /* BTF function prototype doesn't match the verifier types. + * Fall back to 5 u64 args. + */ + for (i = 0; i < 5; i++) + m->arg_size[i] = 8; + m->ret_size = 8; + m->nr_args = 5; + return 0; + } + args = (const struct btf_param *)(func + 1); + nargs = btf_type_vlen(func); + if (nargs >= MAX_BPF_FUNC_ARGS) { + bpf_log(log, + "The function %s has %d arguments. Too many.\n", + tname, nargs); + return -EINVAL; + } + ret = __get_type_size(btf, func->type, &t); + if (ret < 0) { + bpf_log(log, + "The function %s return type %s is unsupported.\n", + tname, btf_kind_str[BTF_INFO_KIND(t->info)]); + return -EINVAL; + } + m->ret_size = ret; + + for (i = 0; i < nargs; i++) { + ret = __get_type_size(btf, args[i].type, &t); + if (ret < 0) { + bpf_log(log, + "The function %s arg%d type %s is unsupported.\n", + tname, i, btf_kind_str[BTF_INFO_KIND(t->info)]); + return -EINVAL; + } + m->arg_size[i] = ret; + } + m->nr_args = nargs; + return 0; +} + +/* Compare BTFs of two functions assuming only scalars and pointers to context. + * t1 points to BTF_KIND_FUNC in btf1 + * t2 points to BTF_KIND_FUNC in btf2 + * Returns: + * EINVAL - function prototype mismatch + * EFAULT - verifier bug + * 0 - 99% match. The last 1% is validated by the verifier. + */ +int btf_check_func_type_match(struct bpf_verifier_log *log, + struct btf *btf1, const struct btf_type *t1, + struct btf *btf2, const struct btf_type *t2) +{ + const struct btf_param *args1, *args2; + const char *fn1, *fn2, *s1, *s2; + u32 nargs1, nargs2, i; + + fn1 = btf_name_by_offset(btf1, t1->name_off); + fn2 = btf_name_by_offset(btf2, t2->name_off); + + if (btf_func_linkage(t1) != BTF_FUNC_GLOBAL) { + bpf_log(log, "%s() is not a global function\n", fn1); + return -EINVAL; + } + if (btf_func_linkage(t2) != BTF_FUNC_GLOBAL) { + bpf_log(log, "%s() is not a global function\n", fn2); + return -EINVAL; + } + + t1 = btf_type_by_id(btf1, t1->type); + if (!t1 || !btf_type_is_func_proto(t1)) + return -EFAULT; + t2 = btf_type_by_id(btf2, t2->type); + if (!t2 || !btf_type_is_func_proto(t2)) + return -EFAULT; + + args1 = (const struct btf_param *)(t1 + 1); + nargs1 = btf_type_vlen(t1); + args2 = (const struct btf_param *)(t2 + 1); + nargs2 = btf_type_vlen(t2); + + if (nargs1 != nargs2) { + bpf_log(log, "%s() has %d args while %s() has %d args\n", + fn1, nargs1, fn2, nargs2); + return -EINVAL; + } + + t1 = btf_type_skip_modifiers(btf1, t1->type, NULL); + t2 = btf_type_skip_modifiers(btf2, t2->type, NULL); + if (t1->info != t2->info) { + bpf_log(log, + "Return type %s of %s() doesn't match type %s of %s()\n", + btf_type_str(t1), fn1, + btf_type_str(t2), fn2); + return -EINVAL; + } + + for (i = 0; i < nargs1; i++) { + t1 = btf_type_skip_modifiers(btf1, args1[i].type, NULL); + t2 = btf_type_skip_modifiers(btf2, args2[i].type, NULL); + + if (t1->info != t2->info) { + bpf_log(log, "arg%d in %s() is %s while %s() has %s\n", + i, fn1, btf_type_str(t1), + fn2, btf_type_str(t2)); + return -EINVAL; + } + if (btf_type_has_size(t1) && t1->size != t2->size) { + bpf_log(log, + "arg%d in %s() has size %d while %s() has %d\n", + i, fn1, t1->size, + fn2, t2->size); + return -EINVAL; + } + + /* global functions are validated with scalars and pointers + * to context only. And only global functions can be replaced. + * Hence type check only those types. + */ + if (btf_type_is_int(t1) || btf_type_is_enum(t1)) + continue; + if (!btf_type_is_ptr(t1)) { + bpf_log(log, + "arg%d in %s() has unrecognized type\n", + i, fn1); + return -EINVAL; + } + t1 = btf_type_skip_modifiers(btf1, t1->type, NULL); + t2 = btf_type_skip_modifiers(btf2, t2->type, NULL); + if (!btf_type_is_struct(t1)) { + bpf_log(log, + "arg%d in %s() is not a pointer to context\n", + i, fn1); + return -EINVAL; + } + if (!btf_type_is_struct(t2)) { + bpf_log(log, + "arg%d in %s() is not a pointer to context\n", + i, fn2); + return -EINVAL; + } + /* This is an optional check to make program writing easier. + * Compare names of structs and report an error to the user. + * btf_prepare_func_args() already checked that t2 struct + * is a context type. btf_prepare_func_args() will check + * later that t1 struct is a context type as well. + */ + s1 = btf_name_by_offset(btf1, t1->name_off); + s2 = btf_name_by_offset(btf2, t2->name_off); + if (strcmp(s1, s2)) { + bpf_log(log, + "arg%d %s(struct %s *) doesn't match %s(struct %s *)\n", + i, fn1, s1, fn2, s2); + return -EINVAL; + } + } + return 0; +} + +/* Compare BTFs of given program with BTF of target program */ +int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, + struct btf *btf2, const struct btf_type *t2) +{ + struct btf *btf1 = prog->aux->btf; + const struct btf_type *t1; + u32 btf_id = 0; + + if (!prog->aux->func_info) { + bpf_log(&env->log, "Program extension requires BTF\n"); + return -EINVAL; + } + + btf_id = prog->aux->func_info[0].type_id; + if (!btf_id) + return -EFAULT; + + t1 = btf_type_by_id(btf1, btf_id); + if (!t1 || !btf_type_is_func(t1)) + return -EFAULT; + + return btf_check_func_type_match(&env->log, btf1, t1, btf2, t2); +} + +/* Compare BTF of a function with given bpf_reg_state. + * Returns: + * EFAULT - there is a verifier bug. Abort verification. + * EINVAL - there is a type mismatch or BTF is not available. + * 0 - BTF matches with what bpf_reg_state expects. + * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. + */ +int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *reg) +{ + struct bpf_verifier_log *log = &env->log; + struct bpf_prog *prog = env->prog; + struct btf *btf = prog->aux->btf; + const struct btf_param *args; + const struct btf_type *t; + u32 i, nargs, btf_id; + const char *tname; + + if (!prog->aux->func_info) + return -EINVAL; + + btf_id = prog->aux->func_info[subprog].type_id; + if (!btf_id) + return -EFAULT; + + if (prog->aux->func_info_aux[subprog].unreliable) + return -EINVAL; + + t = btf_type_by_id(btf, btf_id); + if (!t || !btf_type_is_func(t)) { + /* These checks were already done by the verifier while loading + * struct bpf_func_info + */ + bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n", + subprog); + return -EFAULT; + } + tname = btf_name_by_offset(btf, t->name_off); + + t = btf_type_by_id(btf, t->type); + if (!t || !btf_type_is_func_proto(t)) { + bpf_log(log, "Invalid BTF of func %s\n", tname); + return -EFAULT; + } + args = (const struct btf_param *)(t + 1); + nargs = btf_type_vlen(t); + if (nargs > 5) { + bpf_log(log, "Function %s has %d > 5 args\n", tname, nargs); + goto out; + } + /* check that BTF function arguments match actual types that the + * verifier sees. + */ + for (i = 0; i < nargs; i++) { + t = btf_type_by_id(btf, args[i].type); + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (btf_type_is_int(t) || btf_type_is_enum(t)) { + if (reg[i + 1].type == SCALAR_VALUE) + continue; + bpf_log(log, "R%d is not a scalar\n", i + 1); + goto out; + } + if (btf_type_is_ptr(t)) { + if (reg[i + 1].type == SCALAR_VALUE) { + bpf_log(log, "R%d is not a pointer\n", i + 1); + goto out; + } + /* If function expects ctx type in BTF check that caller + * is passing PTR_TO_CTX. + */ + if (btf_get_prog_ctx_type(log, btf, t, prog->type, i)) { + if (reg[i + 1].type != PTR_TO_CTX) { + bpf_log(log, + "arg#%d expected pointer to ctx, but got %s\n", + i, btf_kind_str[BTF_INFO_KIND(t->info)]); + goto out; + } + if (check_ctx_reg(env, ®[i + 1], i + 1)) + goto out; + continue; + } + } + bpf_log(log, "Unrecognized arg#%d type %s\n", + i, btf_kind_str[BTF_INFO_KIND(t->info)]); + goto out; + } + return 0; +out: + /* Compiler optimizations can remove arguments from static functions + * or mismatched type can be passed into a global function. + * In such cases mark the function as unreliable from BTF point of view. + */ + prog->aux->func_info_aux[subprog].unreliable = true; + return -EINVAL; +} + +/* Convert BTF of a function into bpf_reg_state if possible + * Returns: + * EFAULT - there is a verifier bug. Abort verification. + * EINVAL - cannot convert BTF. + * 0 - Successfully converted BTF into bpf_reg_state + * (either PTR_TO_CTX or SCALAR_VALUE). + */ +int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *reg) +{ + struct bpf_verifier_log *log = &env->log; + struct bpf_prog *prog = env->prog; + enum bpf_prog_type prog_type = prog->type; + struct btf *btf = prog->aux->btf; + const struct btf_param *args; + const struct btf_type *t; + u32 i, nargs, btf_id; + const char *tname; + + if (!prog->aux->func_info || + prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) { + bpf_log(log, "Verifier bug\n"); + return -EFAULT; + } + + btf_id = prog->aux->func_info[subprog].type_id; + if (!btf_id) { + bpf_log(log, "Global functions need valid BTF\n"); + return -EFAULT; + } + + t = btf_type_by_id(btf, btf_id); + if (!t || !btf_type_is_func(t)) { + /* These checks were already done by the verifier while loading + * struct bpf_func_info + */ + bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n", + subprog); + return -EFAULT; + } + tname = btf_name_by_offset(btf, t->name_off); + + if (log->level & BPF_LOG_LEVEL) + bpf_log(log, "Validating %s() func#%d...\n", + tname, subprog); + + if (prog->aux->func_info_aux[subprog].unreliable) { + bpf_log(log, "Verifier bug in function %s()\n", tname); + return -EFAULT; + } + if (prog_type == BPF_PROG_TYPE_EXT) + prog_type = prog->aux->linked_prog->type; + + t = btf_type_by_id(btf, t->type); + if (!t || !btf_type_is_func_proto(t)) { + bpf_log(log, "Invalid type of function %s()\n", tname); + return -EFAULT; + } + args = (const struct btf_param *)(t + 1); + nargs = btf_type_vlen(t); + if (nargs > 5) { + bpf_log(log, "Global function %s() with %d > 5 args. Buggy compiler.\n", + tname, nargs); + return -EINVAL; + } + /* check that function returns int */ + t = btf_type_by_id(btf, t->type); + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (!btf_type_is_int(t) && !btf_type_is_enum(t)) { + bpf_log(log, + "Global function %s() doesn't return scalar. Only those are supported.\n", + tname); + return -EINVAL; + } + /* Convert BTF function arguments into verifier types. + * Only PTR_TO_CTX and SCALAR are supported atm. + */ + for (i = 0; i < nargs; i++) { + t = btf_type_by_id(btf, args[i].type); + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (btf_type_is_int(t) || btf_type_is_enum(t)) { + reg[i + 1].type = SCALAR_VALUE; + continue; + } + if (btf_type_is_ptr(t) && + btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { + reg[i + 1].type = PTR_TO_CTX; + continue; + } + bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n", + i, btf_kind_str[BTF_INFO_KIND(t->info)], tname); + return -EINVAL; + } + return 0; +} + void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m) { @@ -3376,6 +4479,15 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m); } +#ifdef CONFIG_PROC_FS +static void bpf_btf_show_fdinfo(struct seq_file *m, struct file *filp) +{ + const struct btf *btf = filp->private_data; + + seq_printf(m, "btf_id:\t%u\n", btf->id); +} +#endif + static int btf_release(struct inode *inode, struct file *filp) { btf_put(filp->private_data); @@ -3383,6 +4495,9 @@ static int btf_release(struct inode *inode, struct file *filp) } const struct file_operations btf_fops = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = bpf_btf_show_fdinfo, +#endif .release = btf_release, }; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 0a00eaca6fae..9a500fadbef5 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -35,8 +35,8 @@ void cgroup_bpf_offline(struct cgroup *cgrp) */ static void cgroup_bpf_release(struct work_struct *work) { - struct cgroup *cgrp = container_of(work, struct cgroup, - bpf.release_work); + struct cgroup *p, *cgrp = container_of(work, struct cgroup, + bpf.release_work); enum bpf_cgroup_storage_type stype; struct bpf_prog_array *old_array; unsigned int type; @@ -65,6 +65,9 @@ static void cgroup_bpf_release(struct work_struct *work) mutex_unlock(&cgroup_mutex); + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_put(p); + percpu_ref_exit(&cgrp->bpf.refcnt); cgroup_put(cgrp); } @@ -103,8 +106,7 @@ static u32 prog_list_length(struct list_head *head) * if parent has overridable or multi-prog, allow attaching */ static bool hierarchy_allows_attach(struct cgroup *cgrp, - enum bpf_attach_type type, - u32 new_flags) + enum bpf_attach_type type) { struct cgroup *p; @@ -180,8 +182,8 @@ static void activate_effective_progs(struct cgroup *cgrp, enum bpf_attach_type type, struct bpf_prog_array *old_array) { - rcu_swap_protected(cgrp->bpf.effective[type], old_array, - lockdep_is_held(&cgroup_mutex)); + old_array = rcu_replace_pointer(cgrp->bpf.effective[type], old_array, + lockdep_is_held(&cgroup_mutex)); /* free prog array after grace period, since __cgroup_bpf_run_*() * might be still walking the array */ @@ -199,6 +201,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) */ #define NR ARRAY_SIZE(cgrp->bpf.effective) struct bpf_prog_array *arrays[NR] = {}; + struct cgroup *p; int ret, i; ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0, @@ -206,6 +209,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) if (ret) return ret; + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_get(p); + for (i = 0; i < NR; i++) INIT_LIST_HEAD(&cgrp->bpf.progs[i]); @@ -283,31 +289,34 @@ cleanup: * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to attach + * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set * @type: Type of attach operation * @flags: Option flags * * Must be called with cgroup_mutex held. */ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + struct bpf_prog *replace_prog, enum bpf_attach_type type, u32 flags) { + u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)); struct list_head *progs = &cgrp->bpf.progs[type]; struct bpf_prog *old_prog = NULL; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE], *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL}; + struct bpf_prog_list *pl, *replace_pl = NULL; enum bpf_cgroup_storage_type stype; - struct bpf_prog_list *pl; - bool pl_was_allocated; int err; - if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) + if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) || + ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI))) /* invalid combination */ return -EINVAL; - if (!hierarchy_allows_attach(cgrp, type, flags)) + if (!hierarchy_allows_attach(cgrp, type)) return -EPERM; - if (!list_empty(progs) && cgrp->bpf.flags[type] != flags) + if (!list_empty(progs) && cgrp->bpf.flags[type] != saved_flags) /* Disallow attaching non-overridable on top * of existing overridable in this cgroup. * Disallow attaching multi-prog if overridable or none @@ -317,6 +326,21 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; + if (flags & BPF_F_ALLOW_MULTI) { + list_for_each_entry(pl, progs, node) { + if (pl->prog == prog) + /* disallow attaching the same prog twice */ + return -EINVAL; + if (pl->prog == replace_prog) + replace_pl = pl; + } + if ((flags & BPF_F_REPLACE) && !replace_pl) + /* prog to replace not found for cgroup */ + return -ENOENT; + } else if (!list_empty(progs)) { + replace_pl = list_first_entry(progs, typeof(*pl), node); + } + for_each_cgroup_storage_type(stype) { storage[stype] = bpf_cgroup_storage_alloc(prog, stype); if (IS_ERR(storage[stype])) { @@ -327,53 +351,28 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, } } - if (flags & BPF_F_ALLOW_MULTI) { - list_for_each_entry(pl, progs, node) { - if (pl->prog == prog) { - /* disallow attaching the same prog twice */ - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); - return -EINVAL; - } + if (replace_pl) { + pl = replace_pl; + old_prog = pl->prog; + for_each_cgroup_storage_type(stype) { + old_storage[stype] = pl->storage[stype]; + bpf_cgroup_storage_unlink(old_storage[stype]); } - + } else { pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storage[stype]); return -ENOMEM; } - - pl_was_allocated = true; - pl->prog = prog; - for_each_cgroup_storage_type(stype) - pl->storage[stype] = storage[stype]; list_add_tail(&pl->node, progs); - } else { - if (list_empty(progs)) { - pl = kmalloc(sizeof(*pl), GFP_KERNEL); - if (!pl) { - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); - return -ENOMEM; - } - pl_was_allocated = true; - list_add_tail(&pl->node, progs); - } else { - pl = list_first_entry(progs, typeof(*pl), node); - old_prog = pl->prog; - for_each_cgroup_storage_type(stype) { - old_storage[stype] = pl->storage[stype]; - bpf_cgroup_storage_unlink(old_storage[stype]); - } - pl_was_allocated = false; - } - pl->prog = prog; - for_each_cgroup_storage_type(stype) - pl->storage[stype] = storage[stype]; } - cgrp->bpf.flags[type] = flags; + pl->prog = prog; + for_each_cgroup_storage_type(stype) + pl->storage[stype] = storage[stype]; + + cgrp->bpf.flags[type] = saved_flags; err = update_effective_progs(cgrp, type); if (err) @@ -401,7 +400,7 @@ cleanup: pl->storage[stype] = old_storage[stype]; bpf_cgroup_storage_link(old_storage[stype], cgrp, type); } - if (pl_was_allocated) { + if (!replace_pl) { list_del(&pl->node); kfree(pl); } @@ -539,6 +538,7 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog) { + struct bpf_prog *replace_prog = NULL; struct cgroup *cgrp; int ret; @@ -546,8 +546,20 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr, if (IS_ERR(cgrp)) return PTR_ERR(cgrp); - ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, + if ((attr->attach_flags & BPF_F_ALLOW_MULTI) && + (attr->attach_flags & BPF_F_REPLACE)) { + replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, ptype); + if (IS_ERR(replace_prog)) { + cgroup_put(cgrp); + return PTR_ERR(replace_prog); + } + } + + ret = cgroup_bpf_attach(cgrp, prog, replace_prog, attr->attach_type, attr->attach_flags); + + if (replace_prog) + bpf_prog_put(replace_prog); cgroup_put(cgrp); return ret; } @@ -964,7 +976,6 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) return -ENOMEM; ctx->optval_end = ctx->optval + max_optlen; - ctx->optlen = max_optlen; return 0; } @@ -984,7 +995,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, .level = *level, .optname = *optname, }; - int ret; + int ret, max_optlen; /* Opportunistic check to see whether we have any BPF program * attached to the hook so we don't waste time allocating @@ -994,10 +1005,18 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT)) return 0; - ret = sockopt_alloc_buf(&ctx, *optlen); + /* Allocate a bit more than the initial user buffer for + * BPF program. The canonical use case is overriding + * TCP_CONGESTION(nv) to TCP_CONGESTION(cubic). + */ + max_optlen = max_t(int, 16, *optlen); + + ret = sockopt_alloc_buf(&ctx, max_optlen); if (ret) return ret; + ctx.optlen = *optlen; + if (copy_from_user(ctx.optval, optval, *optlen) != 0) { ret = -EFAULT; goto out; @@ -1016,7 +1035,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, if (ctx.optlen == -1) { /* optlen set to -1, bypass kernel */ ret = 1; - } else if (ctx.optlen > *optlen || ctx.optlen < -1) { + } else if (ctx.optlen > max_optlen || ctx.optlen < -1) { /* optlen is out of bounds */ ret = -EFAULT; } else { @@ -1063,6 +1082,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, if (ret) return ret; + ctx.optlen = max_optlen; + if (!retval) { /* If kernel getsockopt finished successfully, * copy whatever was returned to the user back @@ -1302,12 +1323,12 @@ static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type, return false; switch (off) { - case offsetof(struct bpf_sysctl, write): + case bpf_ctx_range(struct bpf_sysctl, write): if (type != BPF_READ) return false; bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); - case offsetof(struct bpf_sysctl, file_pos): + case bpf_ctx_range(struct bpf_sysctl, file_pos): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); @@ -1325,13 +1346,14 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; + u32 read_size; switch (si->off) { case offsetof(struct bpf_sysctl, write): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sysctl_kern, write, - FIELD_SIZEOF(struct bpf_sysctl_kern, + sizeof_field(struct bpf_sysctl_kern, write), target_size)); break; @@ -1356,7 +1378,9 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, ppos)); *insn++ = BPF_STX_MEM( - BPF_SIZEOF(u32), treg, si->src_reg, 0); + BPF_SIZEOF(u32), treg, si->src_reg, + bpf_ctx_narrow_access_offset( + 0, sizeof(u32), sizeof(loff_t))); *insn++ = BPF_LDX_MEM( BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, tmp_reg)); @@ -1365,8 +1389,11 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), si->dst_reg, si->src_reg, offsetof(struct bpf_sysctl_kern, ppos)); + read_size = bpf_size_to_bytes(BPF_SIZE(si->code)); *insn++ = BPF_LDX_MEM( - BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0); + BPF_SIZE(si->code), si->dst_reg, si->dst_reg, + bpf_ctx_narrow_access_offset( + 0, read_size, sizeof(loff_t))); } *target_size = sizeof(u32); break; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 8191a7db2777..973a20d49749 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -30,7 +30,8 @@ #include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/perf_event.h> - +#include <linux/extable.h> +#include <linux/log2.h> #include <asm/unaligned.h> /* Registers */ @@ -221,8 +222,6 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, u32 pages, delta; int ret; - BUG_ON(fp_old == NULL); - size = round_up(size, PAGE_SIZE); pages = size / PAGE_SIZE; if (pages <= fp_old->pages) @@ -255,6 +254,7 @@ void __bpf_prog_free(struct bpf_prog *fp) { if (fp->aux) { free_percpu(fp->aux->stats); + kfree(fp->aux->poke_tab); kfree(fp->aux); } vfree(fp); @@ -502,7 +502,7 @@ int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false)); } -void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) +static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) { int i; @@ -518,9 +518,9 @@ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) #ifdef CONFIG_BPF_JIT /* All BPF JIT sysctl knobs here. */ -int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); +int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); +int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; -int bpf_jit_kallsyms __read_mostly; long bpf_jit_limit __read_mostly; static __always_inline void @@ -668,9 +668,6 @@ static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr) { struct latch_tree_node *n; - if (!bpf_jit_kallsyms_enabled()) - return NULL; - n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops); return n ? container_of(n, struct bpf_prog_aux, ksym_tnode)->prog : @@ -712,6 +709,24 @@ bool is_bpf_text_address(unsigned long addr) return ret; } +const struct exception_table_entry *search_bpf_extables(unsigned long addr) +{ + const struct exception_table_entry *e = NULL; + struct bpf_prog *prog; + + rcu_read_lock(); + prog = bpf_prog_kallsyms_find(addr); + if (!prog) + goto out; + if (!prog->aux->num_exentries) + goto out; + + e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr); +out: + rcu_read_unlock(); + return e; +} + int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { @@ -740,6 +755,39 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, return ret; } +int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, + struct bpf_jit_poke_descriptor *poke) +{ + struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; + static const u32 poke_tab_max = 1024; + u32 slot = prog->aux->size_poke_tab; + u32 size = slot + 1; + + if (size > poke_tab_max) + return -ENOSPC; + if (poke->ip || poke->ip_stable || poke->adj_off) + return -EINVAL; + + switch (poke->reason) { + case BPF_POKE_REASON_TAIL_CALL: + if (!poke->tail_call.map) + return -EINVAL; + break; + default: + return -EINVAL; + } + + tab = krealloc(tab, size * sizeof(*poke), GFP_KERNEL); + if (!tab) + return -ENOMEM; + + memcpy(&tab[slot], poke, sizeof(*poke)); + prog->aux->size_poke_tab = size; + prog->aux->poke_tab = tab; + + return slot; +} + static atomic_long_t bpf_jit_current; /* Can be overridden by an arch's JIT compiler if it has a custom, @@ -800,6 +848,9 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, struct bpf_binary_header *hdr; u32 size, hole, start, pages; + WARN_ON_ONCE(!is_power_of_2(alignment) || + alignment > BPF_IMAGE_ALIGNMENT); + /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. @@ -890,7 +941,8 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog, static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, - struct bpf_insn *to_buff) + struct bpf_insn *to_buff, + bool emit_zext) { struct bpf_insn *to = to_buff; u32 imm_rnd = get_random_int(); @@ -1005,6 +1057,8 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); + if (emit_zext) + *to++ = BPF_ZEXT_REG(BPF_REG_AX); *to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX); break; @@ -1088,7 +1142,8 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) insn[1].code == 0) memcpy(aux, insn, sizeof(aux)); - rewritten = bpf_jit_blind_insn(insn, aux, insn_buff); + rewritten = bpf_jit_blind_insn(insn, aux, insn_buff, + clone->aux->verifier_zext); if (!rewritten) continue; @@ -1287,6 +1342,12 @@ bool bpf_opcode_in_insntable(u8 code) } #ifndef CONFIG_BPF_JIT_ALWAYS_ON +u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) +{ + memset(dst, 0, size); + return -EFAULT; +} + /** * __bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers @@ -1306,6 +1367,10 @@ static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u6 /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, + [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, + [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, + [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, + [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW, }; #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL @@ -1538,6 +1603,16 @@ out: LDST(W, u32) LDST(DW, u64) #undef LDST +#define LDX_PROBE(SIZEOP, SIZE) \ + LDX_PROBE_MEM_##SIZEOP: \ + bpf_probe_read_kernel(&DST, SIZE, (const void *)(long) (SRC + insn->off)); \ + CONT; + LDX_PROBE(B, 1) + LDX_PROBE(H, 2) + LDX_PROBE(W, 4) + LDX_PROBE(DW, 8) +#undef LDX_PROBE + STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ atomic_add((u32) SRC, (atomic_t *)(unsigned long) (DST + insn->off)); @@ -1648,18 +1723,17 @@ bool bpf_prog_array_compatible(struct bpf_array *array, if (fp->kprobe_override) return false; - if (!array->owner_prog_type) { + if (!array->aux->type) { /* There's no owner yet where we could check for * compatibility. */ - array->owner_prog_type = fp->type; - array->owner_jited = fp->jited; - + array->aux->type = fp->type; + array->aux->jited = fp->jited; return true; } - return array->owner_prog_type == fp->type && - array->owner_jited == fp->jited; + return array->aux->type == fp->type && + array->aux->jited == fp->jited; } static int bpf_check_tail_call(const struct bpf_prog *fp) @@ -1960,18 +2034,52 @@ int bpf_prog_array_copy_info(struct bpf_prog_array *array, : 0; } +static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) { + if (!aux->cgroup_storage[stype]) + continue; + bpf_cgroup_storage_release(aux, aux->cgroup_storage[stype]); + } +} + +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len) +{ + struct bpf_map *map; + u32 i; + + bpf_free_cgroup_storage(aux); + for (i = 0; i < len; i++) { + map = used_maps[i]; + if (map->ops->map_poke_untrack) + map->ops->map_poke_untrack(map, aux); + bpf_map_put(map); + } +} + +static void bpf_free_used_maps(struct bpf_prog_aux *aux) +{ + __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt); + kfree(aux->used_maps); +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; int i; aux = container_of(work, struct bpf_prog_aux, work); + bpf_free_used_maps(aux); if (bpf_prog_is_dev_bound(aux)) bpf_prog_offload_destroy(aux->prog); #ifdef CONFIG_PERF_EVENTS if (aux->prog->has_callchain_buf) put_callchain_buffers(); #endif + bpf_trampoline_put(aux->trampoline); for (i = 0; i < aux->func_cnt; i++) bpf_jit_free(aux->func[i]); if (aux->func_cnt) { @@ -1987,6 +2095,8 @@ void bpf_prog_free(struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; + if (aux->linked_prog) + bpf_prog_put(aux->linked_prog); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } @@ -2027,6 +2137,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; const struct bpf_func_proto bpf_spin_lock_proto __weak; const struct bpf_func_proto bpf_spin_unlock_proto __weak; +const struct bpf_func_proto bpf_jiffies64_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; @@ -2101,6 +2212,12 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, return -EFAULT; } +int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, + void *addr1, void *addr2) +{ + return -ENOTSUPP; +} + DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index ef49e17ae47c..70f71b154fa5 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -72,17 +72,18 @@ struct bpf_cpu_map { struct bpf_map map; /* Below members specific for map type */ struct bpf_cpu_map_entry **cpu_map; - struct list_head __percpu *flush_list; }; -static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx); +static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list); + +static int bq_flush_to_queue(struct xdp_bulk_queue *bq); static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) { struct bpf_cpu_map *cmap; int err = -ENOMEM; - int ret, cpu; u64 cost; + int ret; if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -106,7 +107,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) /* make sure page count doesn't overflow */ cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); - cost += sizeof(struct list_head) * num_possible_cpus(); /* Notice returns -EPERM on if map size is larger than memlock limit */ ret = bpf_map_charge_init(&cmap->map.memory, cost); @@ -115,23 +115,14 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) goto free_cmap; } - cmap->flush_list = alloc_percpu(struct list_head); - if (!cmap->flush_list) - goto free_charge; - - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(per_cpu_ptr(cmap->flush_list, cpu)); - /* Alloc array for possible remote "destination" CPUs */ cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *), cmap->map.numa_node); if (!cmap->cpu_map) - goto free_percpu; + goto free_charge; return &cmap->map; -free_percpu: - free_percpu(cmap->flush_list); free_charge: bpf_map_charge_finish(&cmap->map.memory); free_cmap: @@ -399,22 +390,14 @@ free_rcu: static void __cpu_map_entry_free(struct rcu_head *rcu) { struct bpf_cpu_map_entry *rcpu; - int cpu; /* This cpu_map_entry have been disconnected from map and one - * RCU graze-period have elapsed. Thus, XDP cannot queue any + * RCU grace-period have elapsed. Thus, XDP cannot queue any * new packets and cannot change/set flush_needed that can * find this entry. */ rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu); - /* Flush remaining packets in percpu bulkq */ - for_each_online_cpu(cpu) { - struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); - - /* No concurrent bq_enqueue can run at this point */ - bq_flush_to_queue(bq, false); - } free_percpu(rcpu->bulkq); /* Cannot kthread_stop() here, last put free rcpu resources */ put_cpu_map_entry(rcpu); @@ -436,7 +419,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu) * percpu bulkq to queue. Due to caller map_delete_elem() disable * preemption, cannot call kthread_stop() to make sure queue is empty. * Instead a work_queue is started for stopping kthread, - * cpu_map_kthread_stop, which waits for an RCU graze period before + * cpu_map_kthread_stop, which waits for an RCU grace period before * stopping kthread, emptying the queue. */ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, @@ -507,7 +490,6 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, static void cpu_map_free(struct bpf_map *map) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); - int cpu; u32 i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, @@ -522,18 +504,6 @@ static void cpu_map_free(struct bpf_map *map) bpf_clear_redirect_map(map); synchronize_rcu(); - /* To ensure all pending flush operations have completed wait for flush - * list be empty on _all_ cpus. Because the above synchronize_rcu() - * ensures the map is disconnected from the program we can assume no new - * items will be added to the list. - */ - for_each_online_cpu(cpu) { - struct list_head *flush_list = per_cpu_ptr(cmap->flush_list, cpu); - - while (!list_empty(flush_list)) - cond_resched(); - } - /* For cpu_map the remote CPUs can still be using the entries * (struct bpf_cpu_map_entry). */ @@ -544,10 +514,9 @@ static void cpu_map_free(struct bpf_map *map) if (!rcpu) continue; - /* bq flush and cleanup happens after RCU graze-period */ + /* bq flush and cleanup happens after RCU grace-period */ __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */ } - free_percpu(cmap->flush_list); bpf_map_area_free(cmap->cpu_map); kfree(cmap); } @@ -599,7 +568,7 @@ const struct bpf_map_ops cpu_map_ops = { .map_check_btf = map_check_no_btf, }; -static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx) +static int bq_flush_to_queue(struct xdp_bulk_queue *bq) { struct bpf_cpu_map_entry *rcpu = bq->obj; unsigned int processed = 0, drops = 0; @@ -620,10 +589,7 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx) err = __ptr_ring_produce(q, xdpf); if (err) { drops++; - if (likely(in_napi_ctx)) - xdp_return_frame_rx_napi(xdpf); - else - xdp_return_frame(xdpf); + xdp_return_frame_rx_napi(xdpf); } processed++; } @@ -642,11 +608,11 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx) */ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { - struct list_head *flush_list = this_cpu_ptr(rcpu->cmap->flush_list); + struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list); struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) - bq_flush_to_queue(bq, true); + bq_flush_to_queue(bq); /* Notice, xdp_buff/page MUST be queued here, long enough for * driver to code invoking us to finished, due to driver @@ -681,16 +647,26 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, return 0; } -void __cpu_map_flush(struct bpf_map *map) +void __cpu_map_flush(void) { - struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); - struct list_head *flush_list = this_cpu_ptr(cmap->flush_list); + struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list); struct xdp_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { - bq_flush_to_queue(bq, true); + bq_flush_to_queue(bq); /* If already running, costs spin_lock_irqsave + smb_mb */ wake_up_process(bq->obj->kthread); } } + +static int __init cpu_map_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + INIT_LIST_HEAD(&per_cpu(cpu_map_flush_list, cpu)); + return 0; +} + +subsys_initcall(cpu_map_init); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index d83cf8ccc872..58bdca5d978a 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -37,6 +37,12 @@ * 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. + * + * The devmap_hash type is a map type which interprets keys as ifindexes and + * indexes these using a hashmap. This allows maps that use ifindex as key to be + * densely packed instead of having holes in the lookup array for unused + * ifindexes. The setup and packet enqueue/send code is shared between the two + * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> @@ -47,109 +53,149 @@ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) #define DEV_MAP_BULK_SIZE 16 -struct bpf_dtab_netdev; - -struct xdp_bulk_queue { +struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; + struct net_device *dev; struct net_device *dev_rx; - struct bpf_dtab_netdev *obj; unsigned int count; }; struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ + struct hlist_node index_hlist; struct bpf_dtab *dtab; - unsigned int bit; - struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; + unsigned int idx; }; struct bpf_dtab { struct bpf_map map; - struct bpf_dtab_netdev **netdev_map; - struct list_head __percpu *flush_list; + struct bpf_dtab_netdev **netdev_map; /* DEVMAP type only */ struct list_head list; + + /* these are only used for DEVMAP_HASH type maps */ + struct hlist_head *dev_index_head; + spinlock_t index_lock; + unsigned int items; + u32 n_buckets; }; +static DEFINE_PER_CPU(struct list_head, dev_flush_list); static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); -static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +static struct hlist_head *dev_map_create_hash(unsigned int entries) { - struct bpf_dtab *dtab; - int err, cpu; - u64 cost; + int i; + struct hlist_head *hash; - if (!capable(CAP_NET_ADMIN)) - return ERR_PTR(-EPERM); + hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL); + if (hash != NULL) + for (i = 0; i < entries; i++) + INIT_HLIST_HEAD(&hash[i]); + + return hash; +} + +static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, + int idx) +{ + return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; +} + +static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) +{ + u64 cost = 0; + int err; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) - return ERR_PTR(-EINVAL); + return -EINVAL; /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; - dtab = kzalloc(sizeof(*dtab), GFP_USER); - if (!dtab) - return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&dtab->map, attr); - /* make sure page count doesn't overflow */ - cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); - cost += sizeof(struct list_head) * num_possible_cpus(); + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); + + if (!dtab->n_buckets) /* Overflow check */ + return -EINVAL; + cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets; + } else { + cost += (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); + } /* if map size is larger than memlock limit, reject it */ err = bpf_map_charge_init(&dtab->map.memory, cost); if (err) - goto free_dtab; + return -EINVAL; - err = -ENOMEM; + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets); + if (!dtab->dev_index_head) + goto free_charge; - dtab->flush_list = alloc_percpu(struct list_head); - if (!dtab->flush_list) - goto free_charge; + spin_lock_init(&dtab->index_lock); + } else { + 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_charge; + } - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(per_cpu_ptr(dtab->flush_list, cpu)); + return 0; - 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_percpu; +free_charge: + bpf_map_charge_finish(&dtab->map.memory); + return -ENOMEM; +} + +static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +{ + struct bpf_dtab *dtab; + int err; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + + dtab = kzalloc(sizeof(*dtab), GFP_USER); + if (!dtab) + return ERR_PTR(-ENOMEM); + + err = dev_map_init_map(dtab, attr); + if (err) { + kfree(dtab); + return ERR_PTR(err); + } spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; - -free_percpu: - free_percpu(dtab->flush_list); -free_charge: - bpf_map_charge_finish(&dtab->map.memory); -free_dtab: - kfree(dtab); - return ERR_PTR(err); } static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - int i, cpu; + int i; /* 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. + * disconnected from events. The following synchronize_rcu() guarantees + * both rcu read critical sections complete and waits for + * preempt-disable regions (NAPI being the relevant context here) so we + * are certain there will be no further reads against the netdev_map and + * all flush operations are complete. Flush operations can only be done + * from NAPI context for this reason. */ spin_lock(&dev_map_lock); @@ -162,32 +208,37 @@ static void dev_map_free(struct bpf_map *map) /* Make sure prior __dev_map_entry_free() have completed. */ rcu_barrier(); - /* To ensure all pending flush operations have completed wait for flush - * list to empty on _all_ cpus. - * Because the above synchronize_rcu() ensures the map is disconnected - * from the program we can assume no new items will be added. - */ - for_each_online_cpu(cpu) { - struct list_head *flush_list = per_cpu_ptr(dtab->flush_list, cpu); + if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + for (i = 0; i < dtab->n_buckets; i++) { + struct bpf_dtab_netdev *dev; + struct hlist_head *head; + struct hlist_node *next; - while (!list_empty(flush_list)) - cond_resched(); - } + head = dev_map_index_hash(dtab, i); - for (i = 0; i < dtab->map.max_entries; i++) { - struct bpf_dtab_netdev *dev; + hlist_for_each_entry_safe(dev, next, head, index_hlist) { + hlist_del_rcu(&dev->index_hlist); + dev_put(dev->dev); + kfree(dev); + } + } + + kfree(dtab->dev_index_head); + } else { + for (i = 0; i < dtab->map.max_entries; i++) { + struct bpf_dtab_netdev *dev; - dev = dtab->netdev_map[i]; - if (!dev) - continue; + dev = dtab->netdev_map[i]; + if (!dev) + continue; - free_percpu(dev->bulkq); - dev_put(dev->dev); - kfree(dev); + dev_put(dev->dev); + kfree(dev); + } + + bpf_map_area_free(dtab->netdev_map); } - free_percpu(dtab->flush_list); - bpf_map_area_free(dtab->netdev_map); kfree(dtab); } @@ -208,11 +259,68 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, - bool in_napi_ctx) +struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct hlist_head *head = dev_map_index_hash(dtab, key); + struct bpf_dtab_netdev *dev; + + hlist_for_each_entry_rcu(dev, head, index_hlist, + lockdep_is_held(&dtab->index_lock)) + if (dev->idx == key) + return dev; + + return NULL; +} + +static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u32 idx, *next = next_key; + struct bpf_dtab_netdev *dev, *next_dev; + struct hlist_head *head; + int i = 0; + + if (!key) + goto find_first; + + idx = *(u32 *)key; + + dev = __dev_map_hash_lookup_elem(map, idx); + if (!dev) + goto find_first; + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), + struct bpf_dtab_netdev, index_hlist); + + if (next_dev) { + *next = next_dev->idx; + return 0; + } + + i = idx & (dtab->n_buckets - 1); + i++; + + find_first: + for (; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + struct bpf_dtab_netdev, + index_hlist); + if (next_dev) { + *next = next_dev->idx; + return 0; + } + } + + return -ENOENT; +} + +static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { - struct bpf_dtab_netdev *obj = bq->obj; - struct net_device *dev = obj->dev; + struct net_device *dev = bq->dev; int sent = 0, drops = 0, err = 0; int i; @@ -235,8 +343,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, out: bq->count = 0; - trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit, - sent, drops, bq->dev_rx, dev, err); + trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err); bq->dev_rx = NULL; __list_del_clearprev(&bq->flush_node); return 0; @@ -247,33 +354,29 @@ error: for (i = 0; i < bq->count; i++) { struct xdp_frame *xdpf = bq->q[i]; - /* RX path under NAPI protection, can return frames faster */ - if (likely(in_napi_ctx)) - xdp_return_frame_rx_napi(xdpf); - else - xdp_return_frame(xdpf); + xdp_return_frame_rx_napi(xdpf); drops++; } goto out; } -/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled +/* __dev_flush is called from xdp_do_flush() 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 flush list * is empty before completing to ensure all flush operations have completed. + * When drivers update the bpf program they may need to ensure any flush ops + * are also complete. Using synchronize_rcu or call_rcu will suffice for this + * because both wait for napi context to exit. */ -void __dev_map_flush(struct bpf_map *map) +void __dev_flush(void) { - struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct list_head *flush_list = this_cpu_ptr(dtab->flush_list); - struct xdp_bulk_queue *bq, *tmp; + struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); + struct xdp_dev_bulk_queue *bq, *tmp; - rcu_read_lock(); list_for_each_entry_safe(bq, tmp, flush_list, flush_node) - bq_xmit_all(bq, XDP_XMIT_FLUSH, true); - rcu_read_unlock(); + bq_xmit_all(bq, XDP_XMIT_FLUSH); } /* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or @@ -295,15 +398,14 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ -static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, +static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) - { - struct list_head *flush_list = this_cpu_ptr(obj->dtab->flush_list); - struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); + struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); + struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) - bq_xmit_all(bq, 0, true); + bq_xmit_all(bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed @@ -320,10 +422,9 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, return 0; } -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, - struct net_device *dev_rx) +static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, + struct net_device *dev_rx) { - struct net_device *dev = dst->dev; struct xdp_frame *xdpf; int err; @@ -338,7 +439,21 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, if (unlikely(!xdpf)) return -EOVERFLOW; - return bq_enqueue(dst, xdpf, dev_rx); + return bq_enqueue(dev, xdpf, dev_rx); +} + +int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + return __xdp_enqueue(dev, xdp, dev_rx); +} + +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + struct net_device *dev = dst->dev; + + return __xdp_enqueue(dev, xdp, dev_rx); } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, @@ -363,19 +478,13 @@ static void *dev_map_lookup_elem(struct bpf_map *map, void *key) return dev ? &dev->ifindex : NULL; } -static void dev_map_flush_old(struct bpf_dtab_netdev *dev) +static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) { - if (dev->dev->netdev_ops->ndo_xdp_xmit) { - struct xdp_bulk_queue *bq; - int cpu; + struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, + *(u32 *)key); + struct net_device *dev = obj ? obj->dev : NULL; - rcu_read_lock(); - for_each_online_cpu(cpu) { - bq = per_cpu_ptr(dev->bulkq, cpu); - bq_xmit_all(bq, XDP_XMIT_FLUSH, false); - } - rcu_read_unlock(); - } + return dev ? &dev->ifindex : NULL; } static void __dev_map_entry_free(struct rcu_head *rcu) @@ -383,8 +492,6 @@ 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); - free_percpu(dev->bulkq); dev_put(dev->dev); kfree(dev); } @@ -399,12 +506,11 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) 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. + * completed as well as any flush operations because call_rcu + * will wait for preempt-disable region to complete, NAPI in this + * context. 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) @@ -412,17 +518,59 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) return 0; } -static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static int dev_map_hash_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; + unsigned long flags; + int ret = -ENOENT; + + spin_lock_irqsave(&dtab->index_lock, flags); + + old_dev = __dev_map_hash_lookup_elem(map, k); + if (old_dev) { + dtab->items--; + hlist_del_init_rcu(&old_dev->index_hlist); + call_rcu(&old_dev->rcu, __dev_map_entry_free); + ret = 0; + } + spin_unlock_irqrestore(&dtab->index_lock, flags); + + return ret; +} + +static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, + struct bpf_dtab *dtab, + u32 ifindex, + unsigned int idx) +{ + struct bpf_dtab_netdev *dev; + + dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, + dtab->map.numa_node); + if (!dev) + return ERR_PTR(-ENOMEM); + + dev->dev = dev_get_by_index(net, ifindex); + if (!dev->dev) { + kfree(dev); + return ERR_PTR(-EINVAL); + } + + dev->idx = idx; + dev->dtab = dtab; + + return dev; +} + +static int __dev_map_update_elem(struct net *net, 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; - gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; struct bpf_dtab_netdev *dev, *old_dev; u32 ifindex = *(u32 *)value; - struct xdp_bulk_queue *bq; u32 i = *(u32 *)key; - int cpu; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; @@ -434,31 +582,9 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, if (!ifindex) { dev = NULL; } else { - dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node); - if (!dev) - return -ENOMEM; - - dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), - sizeof(void *), gfp); - if (!dev->bulkq) { - kfree(dev); - return -ENOMEM; - } - - for_each_possible_cpu(cpu) { - bq = per_cpu_ptr(dev->bulkq, cpu); - bq->obj = dev; - } - - dev->dev = dev_get_by_index(net, ifindex); - if (!dev->dev) { - free_percpu(dev->bulkq); - kfree(dev); - return -EINVAL; - } - - dev->bit = i; - dev->dtab = dtab; + dev = __dev_map_alloc_node(net, dtab, ifindex, i); + if (IS_ERR(dev)) + return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed @@ -472,6 +598,70 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, return 0; } +static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + +static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev, *old_dev; + u32 ifindex = *(u32 *)value; + u32 idx = *(u32 *)key; + unsigned long flags; + int err = -EEXIST; + + if (unlikely(map_flags > BPF_EXIST || !ifindex)) + return -EINVAL; + + spin_lock_irqsave(&dtab->index_lock, flags); + + old_dev = __dev_map_hash_lookup_elem(map, idx); + if (old_dev && (map_flags & BPF_NOEXIST)) + goto out_err; + + dev = __dev_map_alloc_node(net, dtab, ifindex, idx); + if (IS_ERR(dev)) { + err = PTR_ERR(dev); + goto out_err; + } + + if (old_dev) { + hlist_del_rcu(&old_dev->index_hlist); + } else { + if (dtab->items >= dtab->map.max_entries) { + spin_unlock_irqrestore(&dtab->index_lock, flags); + call_rcu(&dev->rcu, __dev_map_entry_free); + return -E2BIG; + } + dtab->items++; + } + + hlist_add_head_rcu(&dev->index_hlist, + dev_map_index_hash(dtab, idx)); + spin_unlock_irqrestore(&dtab->index_lock, flags); + + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + + return 0; + +out_err: + spin_unlock_irqrestore(&dtab->index_lock, flags); + return err; +} + +static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_hash_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + const struct bpf_map_ops dev_map_ops = { .map_alloc = dev_map_alloc, .map_free = dev_map_free, @@ -482,14 +672,64 @@ const struct bpf_map_ops dev_map_ops = { .map_check_btf = map_check_no_btf, }; +const struct bpf_map_ops dev_map_hash_ops = { + .map_alloc = dev_map_alloc, + .map_free = dev_map_free, + .map_get_next_key = dev_map_hash_get_next_key, + .map_lookup_elem = dev_map_hash_lookup_elem, + .map_update_elem = dev_map_hash_update_elem, + .map_delete_elem = dev_map_hash_delete_elem, + .map_check_btf = map_check_no_btf, +}; + +static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, + struct net_device *netdev) +{ + unsigned long flags; + u32 i; + + spin_lock_irqsave(&dtab->index_lock, flags); + for (i = 0; i < dtab->n_buckets; i++) { + struct bpf_dtab_netdev *dev; + struct hlist_head *head; + struct hlist_node *next; + + head = dev_map_index_hash(dtab, i); + + hlist_for_each_entry_safe(dev, next, head, index_hlist) { + if (netdev != dev->dev) + continue; + + dtab->items--; + hlist_del_rcu(&dev->index_hlist); + call_rcu(&dev->rcu, __dev_map_entry_free); + } + } + spin_unlock_irqrestore(&dtab->index_lock, flags); +} + 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; + int i, cpu; switch (event) { + case NETDEV_REGISTER: + if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) + break; + + /* will be freed in free_netdev() */ + netdev->xdp_bulkq = + __alloc_percpu_gfp(sizeof(struct xdp_dev_bulk_queue), + sizeof(void *), GFP_ATOMIC); + if (!netdev->xdp_bulkq) + return NOTIFY_BAD; + + for_each_possible_cpu(cpu) + per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; + break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete @@ -498,6 +738,11 @@ static int dev_map_notification(struct notifier_block *notifier, */ rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) { + if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dev_map_hash_remove_netdev(dtab, netdev); + continue; + } + for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; @@ -524,10 +769,15 @@ static struct notifier_block dev_map_notifier = { static int __init dev_map_init(void) { + int cpu; + /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); + + for_each_possible_cpu(cpu) + INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu)); return 0; } diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c new file mode 100644 index 000000000000..b3e5b214fed8 --- /dev/null +++ b/kernel/bpf/dispatcher.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2019 Intel Corporation. */ + +#include <linux/hash.h> +#include <linux/bpf.h> +#include <linux/filter.h> + +/* The BPF dispatcher is a multiway branch code generator. The + * dispatcher is a mechanism to avoid the performance penalty of an + * indirect call, which is expensive when retpolines are enabled. A + * dispatch client registers a BPF program into the dispatcher, and if + * there is available room in the dispatcher a direct call to the BPF + * program will be generated. All calls to the BPF programs called via + * the dispatcher will then be a direct call, instead of an + * indirect. The dispatcher hijacks a trampoline function it via the + * __fentry__ of the trampoline. The trampoline function has the + * following signature: + * + * unsigned int trampoline(const void *ctx, const struct bpf_insn *insnsi, + * unsigned int (*bpf_func)(const void *, + * const struct bpf_insn *)); + */ + +static struct bpf_dispatcher_prog *bpf_dispatcher_find_prog( + struct bpf_dispatcher *d, struct bpf_prog *prog) +{ + int i; + + for (i = 0; i < BPF_DISPATCHER_MAX; i++) { + if (prog == d->progs[i].prog) + return &d->progs[i]; + } + return NULL; +} + +static struct bpf_dispatcher_prog *bpf_dispatcher_find_free( + struct bpf_dispatcher *d) +{ + return bpf_dispatcher_find_prog(d, NULL); +} + +static bool bpf_dispatcher_add_prog(struct bpf_dispatcher *d, + struct bpf_prog *prog) +{ + struct bpf_dispatcher_prog *entry; + + if (!prog) + return false; + + entry = bpf_dispatcher_find_prog(d, prog); + if (entry) { + refcount_inc(&entry->users); + return false; + } + + entry = bpf_dispatcher_find_free(d); + if (!entry) + return false; + + bpf_prog_inc(prog); + entry->prog = prog; + refcount_set(&entry->users, 1); + d->num_progs++; + return true; +} + +static bool bpf_dispatcher_remove_prog(struct bpf_dispatcher *d, + struct bpf_prog *prog) +{ + struct bpf_dispatcher_prog *entry; + + if (!prog) + return false; + + entry = bpf_dispatcher_find_prog(d, prog); + if (!entry) + return false; + + if (refcount_dec_and_test(&entry->users)) { + entry->prog = NULL; + bpf_prog_put(prog); + d->num_progs--; + return true; + } + return false; +} + +int __weak arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs) +{ + return -ENOTSUPP; +} + +static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image) +{ + s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0]; + int i; + + for (i = 0; i < BPF_DISPATCHER_MAX; i++) { + if (d->progs[i].prog) + *ipsp++ = (s64)(uintptr_t)d->progs[i].prog->bpf_func; + } + return arch_prepare_bpf_dispatcher(image, &ips[0], d->num_progs); +} + +static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs) +{ + void *old, *new; + u32 noff; + int err; + + if (!prev_num_progs) { + old = NULL; + noff = 0; + } else { + old = d->image + d->image_off; + noff = d->image_off ^ (BPF_IMAGE_SIZE / 2); + } + + new = d->num_progs ? d->image + noff : NULL; + if (new) { + if (bpf_dispatcher_prepare(d, new)) + return; + } + + err = bpf_arch_text_poke(d->func, BPF_MOD_JUMP, old, new); + if (err || !new) + return; + + d->image_off = noff; +} + +void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, + struct bpf_prog *to) +{ + bool changed = false; + int prev_num_progs; + + if (from == to) + return; + + mutex_lock(&d->mutex); + if (!d->image) { + d->image = bpf_image_alloc(); + if (!d->image) + goto out; + } + + prev_num_progs = d->num_progs; + changed |= bpf_dispatcher_remove_prog(d, from); + changed |= bpf_dispatcher_add_prog(d, to); + + if (!changed) + goto out; + + bpf_dispatcher_update(d, prev_num_progs); +out: + mutex_unlock(&d->mutex); +} diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 22066a62c8c9..2d182c4ee9d9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -17,6 +17,16 @@ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED) +#define BATCH_OPS(_name) \ + .map_lookup_batch = \ + _name##_map_lookup_batch, \ + .map_lookup_and_delete_batch = \ + _name##_map_lookup_and_delete_batch, \ + .map_update_batch = \ + generic_map_update_batch, \ + .map_delete_batch = \ + generic_map_delete_batch + struct bucket { struct hlist_nulls_head head; raw_spinlock_t lock; @@ -1232,6 +1242,256 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +static int +__htab_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr, + bool do_delete, bool is_lru_map, + bool is_percpu) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + u32 bucket_cnt, total, key_size, value_size, roundup_key_size; + void *keys = NULL, *values = NULL, *value, *dst_key, *dst_val; + void __user *uvalues = u64_to_user_ptr(attr->batch.values); + void __user *ukeys = u64_to_user_ptr(attr->batch.keys); + void *ubatch = u64_to_user_ptr(attr->batch.in_batch); + u32 batch, max_count, size, bucket_size; + u64 elem_map_flags, map_flags; + struct hlist_nulls_head *head; + struct hlist_nulls_node *n; + unsigned long flags; + struct htab_elem *l; + struct bucket *b; + int ret = 0; + + elem_map_flags = attr->batch.elem_flags; + if ((elem_map_flags & ~BPF_F_LOCK) || + ((elem_map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) + return -EINVAL; + + map_flags = attr->batch.flags; + if (map_flags) + return -EINVAL; + + max_count = attr->batch.count; + if (!max_count) + return 0; + + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + + batch = 0; + if (ubatch && copy_from_user(&batch, ubatch, sizeof(batch))) + return -EFAULT; + + if (batch >= htab->n_buckets) + return -ENOENT; + + key_size = htab->map.key_size; + roundup_key_size = round_up(htab->map.key_size, 8); + value_size = htab->map.value_size; + size = round_up(value_size, 8); + if (is_percpu) + value_size = size * num_possible_cpus(); + total = 0; + /* while experimenting with hash tables with sizes ranging from 10 to + * 1000, it was observed that a bucket can have upto 5 entries. + */ + bucket_size = 5; + +alloc: + /* We cannot do copy_from_user or copy_to_user inside + * the rcu_read_lock. Allocate enough space here. + */ + keys = kvmalloc(key_size * bucket_size, GFP_USER | __GFP_NOWARN); + values = kvmalloc(value_size * bucket_size, GFP_USER | __GFP_NOWARN); + if (!keys || !values) { + ret = -ENOMEM; + goto after_loop; + } + +again: + preempt_disable(); + this_cpu_inc(bpf_prog_active); + rcu_read_lock(); +again_nocopy: + dst_key = keys; + dst_val = values; + b = &htab->buckets[batch]; + head = &b->head; + raw_spin_lock_irqsave(&b->lock, flags); + + bucket_cnt = 0; + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) + bucket_cnt++; + + if (bucket_cnt > (max_count - total)) { + if (total == 0) + ret = -ENOSPC; + raw_spin_unlock_irqrestore(&b->lock, flags); + rcu_read_unlock(); + this_cpu_dec(bpf_prog_active); + preempt_enable(); + goto after_loop; + } + + if (bucket_cnt > bucket_size) { + bucket_size = bucket_cnt; + raw_spin_unlock_irqrestore(&b->lock, flags); + rcu_read_unlock(); + this_cpu_dec(bpf_prog_active); + preempt_enable(); + kvfree(keys); + kvfree(values); + goto alloc; + } + + hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { + memcpy(dst_key, l->key, key_size); + + if (is_percpu) { + int off = 0, cpu; + void __percpu *pptr; + + pptr = htab_elem_get_ptr(l, map->key_size); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(dst_val + off, + per_cpu_ptr(pptr, cpu), size); + off += size; + } + } else { + value = l->key + roundup_key_size; + if (elem_map_flags & BPF_F_LOCK) + copy_map_value_locked(map, dst_val, value, + true); + else + copy_map_value(map, dst_val, value); + check_and_init_map_lock(map, dst_val); + } + if (do_delete) { + hlist_nulls_del_rcu(&l->hash_node); + if (is_lru_map) + bpf_lru_push_free(&htab->lru, &l->lru_node); + else + free_htab_elem(htab, l); + } + dst_key += key_size; + dst_val += value_size; + } + + raw_spin_unlock_irqrestore(&b->lock, flags); + /* If we are not copying data, we can go to next bucket and avoid + * unlocking the rcu. + */ + if (!bucket_cnt && (batch + 1 < htab->n_buckets)) { + batch++; + goto again_nocopy; + } + + rcu_read_unlock(); + this_cpu_dec(bpf_prog_active); + preempt_enable(); + if (bucket_cnt && (copy_to_user(ukeys + total * key_size, keys, + key_size * bucket_cnt) || + copy_to_user(uvalues + total * value_size, values, + value_size * bucket_cnt))) { + ret = -EFAULT; + goto after_loop; + } + + total += bucket_cnt; + batch++; + if (batch >= htab->n_buckets) { + ret = -ENOENT; + goto after_loop; + } + goto again; + +after_loop: + if (ret == -EFAULT) + goto out; + + /* copy # of entries and next batch */ + ubatch = u64_to_user_ptr(attr->batch.out_batch); + if (copy_to_user(ubatch, &batch, sizeof(batch)) || + put_user(total, &uattr->batch.count)) + ret = -EFAULT; + +out: + kvfree(keys); + kvfree(values); + return ret; +} + +static int +htab_percpu_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + false, true); +} + +static int +htab_percpu_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + false, true); +} + +static int +htab_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + false, false); +} + +static int +htab_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + false, false); +} + +static int +htab_lru_percpu_map_lookup_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + true, true); +} + +static int +htab_lru_percpu_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + true, true); +} + +static int +htab_lru_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + true, false); +} + +static int +htab_lru_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + true, false); +} + const struct bpf_map_ops htab_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, @@ -1242,6 +1502,7 @@ const struct bpf_map_ops htab_map_ops = { .map_delete_elem = htab_map_delete_elem, .map_gen_lookup = htab_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, + BATCH_OPS(htab), }; const struct bpf_map_ops htab_lru_map_ops = { @@ -1255,6 +1516,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_delete_elem = htab_lru_map_delete_elem, .map_gen_lookup = htab_lru_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, + BATCH_OPS(htab_lru), }; /* Called from eBPF program */ @@ -1368,6 +1630,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, + BATCH_OPS(htab_percpu), }; const struct bpf_map_ops htab_lru_percpu_map_ops = { @@ -1379,6 +1642,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, + BATCH_OPS(htab_lru_percpu), }; static int fd_htab_map_alloc_check(union bpf_attr *attr) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 5e28718928ca..d8b7b110a1c5 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -11,6 +11,7 @@ #include <linux/uidgid.h> #include <linux/filter.h> #include <linux/ctype.h> +#include <linux/jiffies.h> #include "../../lib/kstrtox.h" @@ -312,12 +313,23 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, preempt_enable(); } +BPF_CALL_0(bpf_jiffies64) +{ + return get_jiffies_64(); +} + +const struct bpf_func_proto bpf_jiffies64_proto = { + .func = bpf_jiffies64, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + #ifdef CONFIG_CGROUPS BPF_CALL_0(bpf_get_current_cgroup_id) { struct cgroup *cgrp = task_dfl_cgroup(current); - return cgrp->kn->id.id; + return cgroup_id(cgrp); } const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index cc0d0cf114e3..5e40e7fccc21 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -14,8 +14,9 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/fs.h> +#include <linux/fs_context.h> +#include <linux/fs_parser.h> #include <linux/kdev_t.h> -#include <linux/parser.h> #include <linux/filter.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> @@ -30,10 +31,10 @@ static void *bpf_any_get(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: - raw = bpf_prog_inc(raw); + bpf_prog_inc(raw); break; case BPF_TYPE_MAP: - raw = bpf_map_inc(raw, true); + bpf_map_inc_with_uref(raw); break; default: WARN_ON_ONCE(1); @@ -195,6 +196,7 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) void *key = map_iter(m)->key; void *prev_key; + (*pos)++; if (map_iter(m)->done) return NULL; @@ -207,8 +209,6 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) map_iter(m)->done = true; return NULL; } - - ++(*pos); return key; } @@ -379,7 +379,7 @@ static const struct inode_operations bpf_dir_iops = { .unlink = simple_unlink, }; -static int bpf_obj_do_pin(const struct filename *pathname, void *raw, +static int bpf_obj_do_pin(const char __user *pathname, void *raw, enum bpf_type type) { struct dentry *dentry; @@ -388,7 +388,7 @@ static int bpf_obj_do_pin(const struct filename *pathname, void *raw, umode_t mode; int ret; - dentry = kern_path_create(AT_FDCWD, pathname->name, &path, 0); + dentry = user_path_create(AT_FDCWD, pathname, &path, 0); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -421,30 +421,22 @@ out: int bpf_obj_pin_user(u32 ufd, const char __user *pathname) { - struct filename *pname; enum bpf_type type; void *raw; int ret; - pname = getname(pathname); - if (IS_ERR(pname)) - return PTR_ERR(pname); - raw = bpf_fd_probe_obj(ufd, &type); - if (IS_ERR(raw)) { - ret = PTR_ERR(raw); - goto out; - } + if (IS_ERR(raw)) + return PTR_ERR(raw); - ret = bpf_obj_do_pin(pname, raw, type); + ret = bpf_obj_do_pin(pathname, raw, type); if (ret != 0) bpf_any_put(raw, type); -out: - putname(pname); + return ret; } -static void *bpf_obj_do_get(const struct filename *pathname, +static void *bpf_obj_do_get(const char __user *pathname, enum bpf_type *type, int flags) { struct inode *inode; @@ -452,7 +444,7 @@ static void *bpf_obj_do_get(const struct filename *pathname, void *raw; int ret; - ret = kern_path(pathname->name, LOOKUP_FOLLOW, &path); + ret = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); @@ -479,36 +471,27 @@ out: int bpf_obj_get_user(const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; - struct filename *pname; - int ret = -ENOENT; int f_flags; void *raw; + int ret; f_flags = bpf_get_file_flag(flags); if (f_flags < 0) return f_flags; - pname = getname(pathname); - if (IS_ERR(pname)) - return PTR_ERR(pname); - - raw = bpf_obj_do_get(pname, &type, f_flags); - if (IS_ERR(raw)) { - ret = PTR_ERR(raw); - goto out; - } + raw = bpf_obj_do_get(pathname, &type, f_flags); + if (IS_ERR(raw)) + return PTR_ERR(raw); if (type == BPF_TYPE_PROG) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) ret = bpf_map_new_fd(raw, f_flags); else - goto out; + return -ENOENT; if (ret < 0) bpf_any_put(raw, type); -out: - putname(pname); return ret; } @@ -533,7 +516,8 @@ static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type if (!bpf_prog_get_ok(prog, &type, false)) return ERR_PTR(-EINVAL); - return bpf_prog_inc(prog); + bpf_prog_inc(prog); + return prog; } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) @@ -583,58 +567,47 @@ static const struct super_operations bpf_super_ops = { enum { OPT_MODE, - OPT_ERR, }; -static const match_table_t bpf_mount_tokens = { - { OPT_MODE, "mode=%o" }, - { OPT_ERR, NULL }, +static const struct fs_parameter_spec bpf_fs_parameters[] = { + fsparam_u32oct ("mode", OPT_MODE), + {} }; struct bpf_mount_opts { umode_t mode; }; -static int bpf_parse_options(char *data, struct bpf_mount_opts *opts) +static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { - substring_t args[MAX_OPT_ARGS]; - int option, token; - char *ptr; + struct bpf_mount_opts *opts = fc->fs_private; + struct fs_parse_result result; + int opt; - opts->mode = S_IRWXUGO; - - while ((ptr = strsep(&data, ",")) != NULL) { - if (!*ptr) - continue; - - token = match_token(ptr, bpf_mount_tokens, args); - switch (token) { - case OPT_MODE: - if (match_octal(&args[0], &option)) - return -EINVAL; - opts->mode = option & S_IALLUGO; - break; + opt = fs_parse(fc, bpf_fs_parameters, param, &result); + if (opt < 0) /* We might like to report bad mount options here, but * traditionally we've ignored all mount options, so we'd * better continue to ignore non-existing options for bpf. */ - } + return opt == -ENOPARAM ? 0 : opt; + + switch (opt) { + case OPT_MODE: + opts->mode = result.uint_32 & S_IALLUGO; + break; } return 0; } -static int bpf_fill_super(struct super_block *sb, void *data, int silent) +static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; - struct bpf_mount_opts opts; + struct bpf_mount_opts *opts = fc->fs_private; struct inode *inode; int ret; - ret = bpf_parse_options(data, &opts); - if (ret) - return ret; - ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; @@ -644,21 +617,50 @@ static int bpf_fill_super(struct super_block *sb, void *data, int silent) inode = sb->s_root->d_inode; inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; - inode->i_mode |= S_ISVTX | opts.mode; + inode->i_mode |= S_ISVTX | opts->mode; return 0; } -static struct dentry *bpf_mount(struct file_system_type *type, int flags, - const char *dev_name, void *data) +static int bpf_get_tree(struct fs_context *fc) +{ + return get_tree_nodev(fc, bpf_fill_super); +} + +static void bpf_free_fc(struct fs_context *fc) { - return mount_nodev(type, flags, data, bpf_fill_super); + kfree(fc->fs_private); +} + +static const struct fs_context_operations bpf_context_ops = { + .free = bpf_free_fc, + .parse_param = bpf_parse_param, + .get_tree = bpf_get_tree, +}; + +/* + * Set up the filesystem mount context. + */ +static int bpf_init_fs_context(struct fs_context *fc) +{ + struct bpf_mount_opts *opts; + + opts = kzalloc(sizeof(struct bpf_mount_opts), GFP_KERNEL); + if (!opts) + return -ENOMEM; + + opts->mode = S_IRWXUGO; + + fc->fs_private = opts; + fc->ops = &bpf_context_ops; + return 0; } static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", - .mount = bpf_mount, + .init_fs_context = bpf_init_fs_context, + .parameters = bpf_fs_parameters, .kill_sb = kill_litter_super, }; diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index addd6fdceec8..33d01866bcc2 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -20,7 +20,7 @@ struct bpf_cgroup_storage_map { struct bpf_map map; spinlock_t lock; - struct bpf_prog *prog; + struct bpf_prog_aux *aux; struct rb_root root; struct list_head list; }; @@ -357,7 +357,7 @@ static int cgroup_storage_check_btf(const struct bpf_map *map, * The first field must be a 64 bit integer at 0 offset. */ m = (struct btf_member *)(key_type + 1); - size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id); + size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id); if (!btf_member_is_reg_int(btf, key_type, m, 0, size)) return -EINVAL; @@ -366,7 +366,7 @@ static int cgroup_storage_check_btf(const struct bpf_map *map, */ m++; offset = offsetof(struct bpf_cgroup_storage_key, attach_type); - size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type); + size = sizeof_field(struct bpf_cgroup_storage_key, attach_type); if (!btf_member_is_reg_int(btf, key_type, m, offset, size)) return -EINVAL; @@ -420,7 +420,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { .map_seq_show_elem = cgroup_storage_seq_show_elem, }; -int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) +int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); @@ -428,14 +428,14 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) spin_lock_bh(&map->lock); - if (map->prog && map->prog != prog) + if (map->aux && map->aux != aux) goto unlock; - if (prog->aux->cgroup_storage[stype] && - prog->aux->cgroup_storage[stype] != _map) + if (aux->cgroup_storage[stype] && + aux->cgroup_storage[stype] != _map) goto unlock; - map->prog = prog; - prog->aux->cgroup_storage[stype] = _map; + map->aux = aux; + aux->cgroup_storage[stype] = _map; ret = 0; unlock: spin_unlock_bh(&map->lock); @@ -443,16 +443,16 @@ unlock: return ret; } -void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) +void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); spin_lock_bh(&map->lock); - if (map->prog == prog) { - WARN_ON(prog->aux->cgroup_storage[stype] != _map); - map->prog = NULL; - prog->aux->cgroup_storage[stype] = NULL; + if (map->aux == aux) { + WARN_ON(aux->cgroup_storage[stype] != _map); + map->aux = NULL; + aux->cgroup_storage[stype] = NULL; } spin_unlock_bh(&map->lock); } @@ -569,7 +569,7 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, return; storage->key.attach_type = type; - storage->key.cgroup_inode_id = cgroup->kn->id.id; + storage->key.cgroup_inode_id = cgroup_id(cgroup); map = storage->map; diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index fab4fb134547..b3c48d1533cb 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -17,13 +17,13 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) if (IS_ERR(inner_map)) return inner_map; - /* prog_array->owner_prog_type and owner_jited - * is a runtime binding. Doing static check alone - * in the verifier is not enough. + /* prog_array->aux->{type,jited} is a runtime binding. + * Doing static check alone in the verifier is not enough. */ if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY || inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || - inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE || + inner_map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { fdput(f); return ERR_PTR(-ENOTSUPP); } @@ -98,7 +98,7 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, return inner_map; if (bpf_map_meta_equal(map->inner_map_meta, inner_map)) - inner_map = bpf_map_inc(inner_map, false); + bpf_map_inc(inner_map); else inner_map = ERR_PTR(-EINVAL); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index ba635209ae9a..2c5dc6541ece 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -302,14 +302,14 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct inode *ns_inode; struct path ns_path; char __user *uinsns; - void *res; + int res; u32 ulen; res = ns_get_path_cb(&ns_path, bpf_prog_offload_info_fill_ns, &args); - if (IS_ERR(res)) { + if (res) { if (!info->ifindex) return -ENODEV; - return PTR_ERR(res); + return res; } down_read(&bpf_devs_lock); @@ -526,13 +526,13 @@ int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map) }; struct inode *ns_inode; struct path ns_path; - void *res; + int res; res = ns_get_path_cb(&ns_path, bpf_map_offload_info_fill_ns, &args); - if (IS_ERR(res)) { + if (res) { if (!info->ifindex) return -ENODEV; - return PTR_ERR(res); + return res; } ns_inode = ns_path.dentry->d_inode; @@ -678,8 +678,10 @@ bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv) down_write(&bpf_devs_lock); if (!offdevs_inited) { err = rhashtable_init(&offdevs, &offdevs_params); - if (err) + if (err) { + up_write(&bpf_devs_lock); return ERR_PTR(err); + } offdevs_inited = true; } up_write(&bpf_devs_lock); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 052580c33d26..3f958b90d914 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -287,16 +287,17 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, bool irq_work_busy = false; struct stack_map_irq_work *work = NULL; - if (in_nmi()) { + if (irqs_disabled()) { work = this_cpu_ptr(&up_read_work); - if (work->irq_work.flags & IRQ_WORK_BUSY) + if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) /* cannot queue more up_read, fallback */ irq_work_busy = true; } /* - * We cannot do up_read() in nmi context. To do build_id lookup - * in nmi context, we need to run up_read() in irq_work. We use + * We cannot do up_read() when the irq is disabled, because of + * risk to deadlock with rq_lock. To do build_id lookup when the + * irqs are disabled, we need to run up_read() in irq_work. We use * a percpu variable to do the irq_work. If the irq_work is * already used by another lookup, we fall back to report ips. * @@ -338,7 +339,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, * up_read_non_owner(). The rwsem_release() is called * here to release the lock from lockdep's perspective. */ - rwsem_release(¤t->mm->mmap_sem.dep_map, 1, _RET_IP_); + rwsem_release(¤t->mm->mmap_sem.dep_map, _RET_IP_); } } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5d141f16f6fa..a91ad518c050 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -23,13 +23,16 @@ #include <linux/timekeeping.h> #include <linux/ctype.h> #include <linux/nospec.h> +#include <linux/audit.h> +#include <uapi/linux/btf.h> -#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ - (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ - (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ - (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) +#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ + (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ + (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) +#define IS_FD_PROG_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY) #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) -#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map)) +#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map) || \ + IS_FD_HASH(map)) #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) @@ -42,7 +45,7 @@ static DEFINE_SPINLOCK(map_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly; static const struct bpf_map_ops * const bpf_map_types[] = { -#define BPF_PROG_TYPE(_id, _ops) +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops, #include <linux/bpf_types.h> @@ -126,7 +129,153 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } -void *bpf_map_area_alloc(size_t size, int numa_node) +static u32 bpf_map_value_size(struct bpf_map *map) +{ + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) + return round_up(map->value_size, 8) * num_possible_cpus(); + else if (IS_FD_MAP(map)) + return sizeof(u32); + else + return map->value_size; +} + +static void maybe_wait_bpf_programs(struct bpf_map *map) +{ + /* Wait for any running BPF programs to complete so that + * userspace, when we return to it, knows that all programs + * that could be running use the new map value. + */ + if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || + map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) + synchronize_rcu(); +} + +static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, + void *value, __u64 flags) +{ + int err; + + /* Need to create a kthread, thus must support schedule */ + if (bpf_map_is_dev_bound(map)) { + return bpf_map_offload_update_elem(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_SOCKHASH || + map->map_type == BPF_MAP_TYPE_SOCKMAP || + map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + return map->ops->map_update_elem(map, key, value, flags); + } else if (IS_FD_PROG_ARRAY(map)) { + return bpf_fd_array_map_update_elem(map, f.file, key, value, + flags); + } + + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from + * inside bpf map update or delete otherwise deadlocks are possible + */ + preempt_disable(); + __this_cpu_inc(bpf_prog_active); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + err = bpf_percpu_hash_update(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + err = bpf_percpu_array_update(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_update(map, key, value, + flags); + } else if (IS_FD_ARRAY(map)) { + rcu_read_lock(); + err = bpf_fd_array_map_update_elem(map, f.file, key, value, + flags); + rcu_read_unlock(); + } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { + rcu_read_lock(); + err = bpf_fd_htab_map_update_elem(map, f.file, key, value, + flags); + rcu_read_unlock(); + } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { + /* rcu_read_lock() is not needed */ + err = bpf_fd_reuseport_array_update_elem(map, key, value, + flags); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_push_elem(map, value, flags); + } else { + rcu_read_lock(); + err = map->ops->map_update_elem(map, key, value, flags); + rcu_read_unlock(); + } + __this_cpu_dec(bpf_prog_active); + preempt_enable(); + maybe_wait_bpf_programs(map); + + return err; +} + +static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, + __u64 flags) +{ + void *ptr; + int err; + + if (bpf_map_is_dev_bound(map)) + return bpf_map_offload_lookup_elem(map, key, value); + + preempt_disable(); + this_cpu_inc(bpf_prog_active); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + err = bpf_percpu_hash_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + err = bpf_percpu_array_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { + err = bpf_stackmap_copy(map, key, value); + } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) { + err = bpf_fd_array_map_lookup_elem(map, key, value); + } else if (IS_FD_HASH(map)) { + err = bpf_fd_htab_map_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { + err = bpf_fd_reuseport_array_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_peek_elem(map, value); + } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + /* struct_ops map requires directly updating "value" */ + err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); + } else { + rcu_read_lock(); + if (map->ops->map_lookup_elem_sys_only) + ptr = map->ops->map_lookup_elem_sys_only(map, key); + else + ptr = map->ops->map_lookup_elem(map, key); + if (IS_ERR(ptr)) { + err = PTR_ERR(ptr); + } else if (!ptr) { + err = -ENOENT; + } else { + err = 0; + if (flags & BPF_F_LOCK) + /* lock 'ptr' and copy everything but lock */ + copy_map_value_locked(map, value, ptr, true); + else + copy_map_value(map, value, ptr); + /* mask lock, since value wasn't zero inited */ + check_and_init_map_lock(map, value); + } + rcu_read_unlock(); + } + + this_cpu_dec(bpf_prog_active); + preempt_enable(); + maybe_wait_bpf_programs(map); + + return err; +} + +static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, @@ -141,18 +290,36 @@ void *bpf_map_area_alloc(size_t size, int numa_node) const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; void *area; - if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { + if (size >= SIZE_MAX) + return NULL; + + /* kmalloc()'ed memory can't be mmap()'ed */ + if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags, numa_node); if (area != NULL) return area; } - + if (mmapable) { + BUG_ON(!PAGE_ALIGNED(size)); + return vmalloc_user_node_flags(size, numa_node, GFP_KERNEL | + __GFP_RETRY_MAYFAIL | flags); + } return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | __GFP_RETRY_MAYFAIL | flags, __builtin_return_address(0)); } +void *bpf_map_area_alloc(u64 size, int numa_node) +{ + return __bpf_map_area_alloc(size, numa_node, false); +} + +void *bpf_map_area_mmapable_alloc(u64 size, int numa_node) +{ + return __bpf_map_area_alloc(size, numa_node, true); +} + void bpf_map_area_free(void *area) { kvfree(area); @@ -197,7 +364,7 @@ static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) atomic_long_sub(pages, &user->locked_vm); } -int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size) +int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size) { u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT; struct user_struct *user; @@ -310,7 +477,7 @@ static void bpf_map_free_deferred(struct work_struct *work) static void bpf_map_put_uref(struct bpf_map *map) { - if (atomic_dec_and_test(&map->usercnt)) { + if (atomic64_dec_and_test(&map->usercnt)) { if (map->ops->map_release_uref) map->ops->map_release_uref(map); } @@ -321,7 +488,7 @@ static void bpf_map_put_uref(struct bpf_map *map) */ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) { - if (atomic_dec_and_test(&map->refcnt)) { + if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map, do_idr_lock); btf_put(map->btf); @@ -370,13 +537,12 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_map *map = filp->private_data; const struct bpf_array *array; - u32 owner_prog_type = 0; - u32 owner_jited = 0; + u32 type = 0, jited = 0; if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { array = container_of(map, struct bpf_array, map); - owner_prog_type = array->owner_prog_type; - owner_jited = array->owner_jited; + type = array->aux->type; + jited = array->aux->jited; } seq_printf(m, @@ -396,12 +562,9 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->memory.pages * 1ULL << PAGE_SHIFT, map->id, READ_ONCE(map->frozen)); - - if (owner_prog_type) { - seq_printf(m, "owner_prog_type:\t%u\n", - owner_prog_type); - seq_printf(m, "owner_jited:\t%u\n", - owner_jited); + if (type) { + seq_printf(m, "owner_prog_type:\t%u\n", type); + seq_printf(m, "owner_jited:\t%u\n", jited); } } #endif @@ -424,6 +587,74 @@ static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, return -EINVAL; } +/* called for any extra memory-mapped regions (except initial) */ +static void bpf_map_mmap_open(struct vm_area_struct *vma) +{ + struct bpf_map *map = vma->vm_file->private_data; + + bpf_map_inc_with_uref(map); + + if (vma->vm_flags & VM_WRITE) { + mutex_lock(&map->freeze_mutex); + map->writecnt++; + mutex_unlock(&map->freeze_mutex); + } +} + +/* called for all unmapped memory region (including initial) */ +static void bpf_map_mmap_close(struct vm_area_struct *vma) +{ + struct bpf_map *map = vma->vm_file->private_data; + + if (vma->vm_flags & VM_WRITE) { + mutex_lock(&map->freeze_mutex); + map->writecnt--; + mutex_unlock(&map->freeze_mutex); + } + + bpf_map_put_with_uref(map); +} + +static const struct vm_operations_struct bpf_map_default_vmops = { + .open = bpf_map_mmap_open, + .close = bpf_map_mmap_close, +}; + +static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct bpf_map *map = filp->private_data; + int err; + + if (!map->ops->map_mmap || map_value_has_spin_lock(map)) + return -ENOTSUPP; + + if (!(vma->vm_flags & VM_SHARED)) + return -EINVAL; + + mutex_lock(&map->freeze_mutex); + + if ((vma->vm_flags & VM_WRITE) && map->frozen) { + err = -EPERM; + goto out; + } + + /* set default open/close callbacks */ + vma->vm_ops = &bpf_map_default_vmops; + vma->vm_private_data = map; + + err = map->ops->map_mmap(map, vma); + if (err) + goto out; + + bpf_map_inc_with_uref(map); + + if (vma->vm_flags & VM_WRITE) + map->writecnt++; +out: + mutex_unlock(&map->freeze_mutex); + return err; +} + const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, @@ -431,6 +662,7 @@ const struct file_operations bpf_map_fops = { .release = bpf_map_release, .read = bpf_dummy_read, .write = bpf_dummy_write, + .mmap = bpf_map_mmap, }; int bpf_map_new_fd(struct bpf_map *map, int flags) @@ -542,7 +774,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; } -#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id +#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -556,6 +788,14 @@ static int map_create(union bpf_attr *attr) if (err) return -EINVAL; + if (attr->btf_vmlinux_value_type_id) { + if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || + attr->btf_key_type_id || attr->btf_value_type_id) + return -EINVAL; + } else if (attr->btf_key_type_id && !attr->btf_value_type_id) { + return -EINVAL; + } + f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; @@ -574,35 +814,39 @@ static int map_create(union bpf_attr *attr) if (err) goto free_map; - atomic_set(&map->refcnt, 1); - atomic_set(&map->usercnt, 1); - - if (attr->btf_key_type_id || attr->btf_value_type_id) { + atomic64_set(&map->refcnt, 1); + atomic64_set(&map->usercnt, 1); + mutex_init(&map->freeze_mutex); + + map->spin_lock_off = -EINVAL; + if (attr->btf_key_type_id || attr->btf_value_type_id || + /* Even the map's value is a kernel's struct, + * the bpf_prog.o must have BTF to begin with + * to figure out the corresponding kernel's + * counter part. Thus, attr->btf_fd has + * to be valid also. + */ + attr->btf_vmlinux_value_type_id) { struct btf *btf; - if (!attr->btf_value_type_id) { - err = -EINVAL; - goto free_map; - } - btf = btf_get_by_fd(attr->btf_fd); if (IS_ERR(btf)) { err = PTR_ERR(btf); goto free_map; } + map->btf = btf; - err = map_check_btf(map, btf, attr->btf_key_type_id, - attr->btf_value_type_id); - if (err) { - btf_put(btf); - goto free_map; + if (attr->btf_value_type_id) { + err = map_check_btf(map, btf, attr->btf_key_type_id, + attr->btf_value_type_id); + if (err) + goto free_map; } - map->btf = btf; map->btf_key_type_id = attr->btf_key_type_id; map->btf_value_type_id = attr->btf_value_type_id; - } else { - map->spin_lock_off = -EINVAL; + map->btf_vmlinux_value_type_id = + attr->btf_vmlinux_value_type_id; } err = security_bpf_map_alloc(map); @@ -652,21 +896,19 @@ struct bpf_map *__bpf_map_get(struct fd f) return f.file->private_data; } -/* prog's and map's refcnt limit */ -#define BPF_MAX_REFCNT 32768 - -struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref) +void bpf_map_inc(struct bpf_map *map) { - if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) { - atomic_dec(&map->refcnt); - return ERR_PTR(-EBUSY); - } - if (uref) - atomic_inc(&map->usercnt); - return map; + atomic64_inc(&map->refcnt); } EXPORT_SYMBOL_GPL(bpf_map_inc); +void bpf_map_inc_with_uref(struct bpf_map *map) +{ + atomic64_inc(&map->refcnt); + atomic64_inc(&map->usercnt); +} +EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); + struct bpf_map *bpf_map_get_with_uref(u32 ufd) { struct fd f = fdget(ufd); @@ -676,34 +918,36 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd) if (IS_ERR(map)) return map; - map = bpf_map_inc(map, true); + bpf_map_inc_with_uref(map); fdput(f); return map; } /* map_idr_lock should have been held */ -static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, - bool uref) +static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) { int refold; - refold = atomic_fetch_add_unless(&map->refcnt, 1, 0); - - if (refold >= BPF_MAX_REFCNT) { - __bpf_map_put(map, false); - return ERR_PTR(-EBUSY); - } - + refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); - if (uref) - atomic_inc(&map->usercnt); + atomic64_inc(&map->usercnt); return map; } +struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map) +{ + spin_lock_bh(&map_idr_lock); + map = __bpf_map_inc_not_zero(map, false); + spin_unlock_bh(&map_idr_lock); + + return map; +} +EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); + int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { return -ENOTSUPP; @@ -729,7 +973,7 @@ static int map_lookup_elem(union bpf_attr *attr) void __user *uvalue = u64_to_user_ptr(attr->value); int ufd = attr->map_fd; struct bpf_map *map; - void *key, *value, *ptr; + void *key, *value; u32 value_size; struct fd f; int err; @@ -761,72 +1005,14 @@ static int map_lookup_elem(union bpf_attr *attr) goto err_put; } - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || - map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) - value_size = round_up(map->value_size, 8) * num_possible_cpus(); - else if (IS_FD_MAP(map)) - value_size = sizeof(u32); - else - value_size = map->value_size; + value_size = bpf_map_value_size(map); err = -ENOMEM; value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; - if (bpf_map_is_dev_bound(map)) { - err = bpf_map_offload_lookup_elem(map, key, value); - goto done; - } - - preempt_disable(); - this_cpu_inc(bpf_prog_active); - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { - err = bpf_percpu_hash_copy(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { - err = bpf_percpu_array_copy(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { - err = bpf_percpu_cgroup_storage_copy(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { - err = bpf_stackmap_copy(map, key, value); - } else if (IS_FD_ARRAY(map)) { - err = bpf_fd_array_map_lookup_elem(map, key, value); - } else if (IS_FD_HASH(map)) { - err = bpf_fd_htab_map_lookup_elem(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { - err = bpf_fd_reuseport_array_lookup_elem(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { - err = map->ops->map_peek_elem(map, value); - } else { - rcu_read_lock(); - if (map->ops->map_lookup_elem_sys_only) - ptr = map->ops->map_lookup_elem_sys_only(map, key); - else - ptr = map->ops->map_lookup_elem(map, key); - if (IS_ERR(ptr)) { - err = PTR_ERR(ptr); - } else if (!ptr) { - err = -ENOENT; - } else { - err = 0; - if (attr->flags & BPF_F_LOCK) - /* lock 'ptr' and copy everything but lock */ - copy_map_value_locked(map, value, ptr, true); - else - copy_map_value(map, value, ptr); - /* mask lock, since value wasn't zero inited */ - check_and_init_map_lock(map, value); - } - rcu_read_unlock(); - } - this_cpu_dec(bpf_prog_active); - preempt_enable(); - -done: + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -845,16 +1031,6 @@ err_put: return err; } -static void maybe_wait_bpf_programs(struct bpf_map *map) -{ - /* Wait for any running BPF programs to complete so that - * userspace, when we return to it, knows that all programs - * that could be running use the new map value. - */ - if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || - map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) - synchronize_rcu(); -} #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags @@ -910,56 +1086,8 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; - /* Need to create a kthread, thus must support schedule */ - if (bpf_map_is_dev_bound(map)) { - err = bpf_map_offload_update_elem(map, key, value, attr->flags); - goto out; - } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || - map->map_type == BPF_MAP_TYPE_SOCKHASH || - map->map_type == BPF_MAP_TYPE_SOCKMAP) { - err = map->ops->map_update_elem(map, key, value, attr->flags); - goto out; - } + err = bpf_map_update_value(map, f, key, value, attr->flags); - /* must increment bpf_prog_active to avoid kprobe+bpf triggering from - * inside bpf map update or delete otherwise deadlocks are possible - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { - err = bpf_percpu_hash_update(map, key, value, attr->flags); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { - err = bpf_percpu_array_update(map, key, value, attr->flags); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { - err = bpf_percpu_cgroup_storage_update(map, key, value, - attr->flags); - } else if (IS_FD_ARRAY(map)) { - rcu_read_lock(); - err = bpf_fd_array_map_update_elem(map, f.file, key, value, - attr->flags); - rcu_read_unlock(); - } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { - rcu_read_lock(); - err = bpf_fd_htab_map_update_elem(map, f.file, key, value, - attr->flags); - rcu_read_unlock(); - } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { - /* rcu_read_lock() is not needed */ - err = bpf_fd_reuseport_array_update_elem(map, key, value, - attr->flags); - } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { - err = map->ops->map_push_elem(map, value, attr->flags); - } else { - rcu_read_lock(); - err = map->ops->map_update_elem(map, key, value, attr->flags); - rcu_read_unlock(); - } - __this_cpu_dec(bpf_prog_active); - preempt_enable(); - maybe_wait_bpf_programs(map); -out: free_value: kfree(value); free_key: @@ -1001,6 +1129,11 @@ static int map_delete_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_delete_elem(map, key); goto out; + } else if (IS_FD_PROG_ARRAY(map) || + map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + /* These maps require sleepable context */ + err = map->ops->map_delete_elem(map, key); + goto out; } preempt_disable(); @@ -1085,6 +1218,220 @@ err_put: return err; } +int generic_map_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + void __user *keys = u64_to_user_ptr(attr->batch.keys); + u32 cp, max_count; + int err = 0; + void *key; + + if (attr->batch.elem_flags & ~BPF_F_LOCK) + return -EINVAL; + + if ((attr->batch.elem_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + return -EINVAL; + } + + max_count = attr->batch.count; + if (!max_count) + return 0; + + key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + if (!key) + return -ENOMEM; + + for (cp = 0; cp < max_count; cp++) { + err = -EFAULT; + if (copy_from_user(key, keys + cp * map->key_size, + map->key_size)) + break; + + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_delete_elem(map, key); + break; + } + + preempt_disable(); + __this_cpu_inc(bpf_prog_active); + rcu_read_lock(); + err = map->ops->map_delete_elem(map, key); + rcu_read_unlock(); + __this_cpu_dec(bpf_prog_active); + preempt_enable(); + maybe_wait_bpf_programs(map); + if (err) + break; + } + if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) + err = -EFAULT; + + kfree(key); + return err; +} + +int generic_map_update_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + void __user *values = u64_to_user_ptr(attr->batch.values); + void __user *keys = u64_to_user_ptr(attr->batch.keys); + u32 value_size, cp, max_count; + int ufd = attr->map_fd; + void *key, *value; + struct fd f; + int err = 0; + + f = fdget(ufd); + if (attr->batch.elem_flags & ~BPF_F_LOCK) + return -EINVAL; + + if ((attr->batch.elem_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + return -EINVAL; + } + + value_size = bpf_map_value_size(map); + + max_count = attr->batch.count; + if (!max_count) + return 0; + + key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + if (!key) + return -ENOMEM; + + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + if (!value) { + kfree(key); + return -ENOMEM; + } + + for (cp = 0; cp < max_count; cp++) { + err = -EFAULT; + if (copy_from_user(key, keys + cp * map->key_size, + map->key_size) || + copy_from_user(value, values + cp * value_size, value_size)) + break; + + err = bpf_map_update_value(map, f, key, value, + attr->batch.elem_flags); + + if (err) + break; + } + + if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) + err = -EFAULT; + + kfree(value); + kfree(key); + return err; +} + +#define MAP_LOOKUP_RETRIES 3 + +int generic_map_lookup_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch); + void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); + void __user *values = u64_to_user_ptr(attr->batch.values); + void __user *keys = u64_to_user_ptr(attr->batch.keys); + void *buf, *buf_prevkey, *prev_key, *key, *value; + int err, retry = MAP_LOOKUP_RETRIES; + u32 value_size, cp, max_count; + + if (attr->batch.elem_flags & ~BPF_F_LOCK) + return -EINVAL; + + if ((attr->batch.elem_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) + return -EINVAL; + + value_size = bpf_map_value_size(map); + + max_count = attr->batch.count; + if (!max_count) + return 0; + + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + + buf_prevkey = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + if (!buf_prevkey) + return -ENOMEM; + + buf = kmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); + if (!buf) { + kvfree(buf_prevkey); + return -ENOMEM; + } + + err = -EFAULT; + prev_key = NULL; + if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size)) + goto free_buf; + key = buf; + value = key + map->key_size; + if (ubatch) + prev_key = buf_prevkey; + + for (cp = 0; cp < max_count;) { + rcu_read_lock(); + err = map->ops->map_get_next_key(map, prev_key, key); + rcu_read_unlock(); + if (err) + break; + err = bpf_map_copy_value(map, key, value, + attr->batch.elem_flags); + + if (err == -ENOENT) { + if (retry) { + retry--; + continue; + } + err = -EINTR; + break; + } + + if (err) + goto free_buf; + + if (copy_to_user(keys + cp * map->key_size, key, + map->key_size)) { + err = -EFAULT; + goto free_buf; + } + if (copy_to_user(values + cp * value_size, value, value_size)) { + err = -EFAULT; + goto free_buf; + } + + if (!prev_key) + prev_key = buf_prevkey; + + swap(prev_key, key); + retry = MAP_LOOKUP_RETRIES; + cp++; + } + + if (err == -EFAULT) + goto free_buf; + + if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) || + (cp && copy_to_user(uobatch, prev_key, map->key_size)))) + err = -EFAULT; + +free_buf: + kfree(buf_prevkey); + kfree(buf); + return err; +} + #define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value static int map_lookup_and_delete_elem(union bpf_attr *attr) @@ -1162,6 +1509,13 @@ static int map_freeze(const union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + + mutex_lock(&map->freeze_mutex); + + if (map->writecnt) { + err = -EBUSY; + goto err_put; + } if (READ_ONCE(map->frozen)) { err = -EBUSY; goto err_put; @@ -1173,12 +1527,13 @@ static int map_freeze(const union bpf_attr *attr) WRITE_ONCE(map->frozen, true); err_put: + mutex_unlock(&map->freeze_mutex); fdput(f); return err; } static const struct bpf_prog_ops * const bpf_prog_types[] = { -#define BPF_PROG_TYPE(_id, _name) \ +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) #include <linux/bpf_types.h> @@ -1205,23 +1560,34 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) return 0; } -/* drop refcnt on maps used by eBPF program and free auxilary data */ -static void free_used_maps(struct bpf_prog_aux *aux) -{ - enum bpf_cgroup_storage_type stype; - int i; +enum bpf_audit { + BPF_AUDIT_LOAD, + BPF_AUDIT_UNLOAD, + BPF_AUDIT_MAX, +}; - for_each_cgroup_storage_type(stype) { - if (!aux->cgroup_storage[stype]) - continue; - bpf_cgroup_storage_release(aux->prog, - aux->cgroup_storage[stype]); - } +static const char * const bpf_audit_str[BPF_AUDIT_MAX] = { + [BPF_AUDIT_LOAD] = "LOAD", + [BPF_AUDIT_UNLOAD] = "UNLOAD", +}; - for (i = 0; i < aux->used_map_cnt; i++) - bpf_map_put(aux->used_maps[i]); +static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) +{ + struct audit_context *ctx = NULL; + struct audit_buffer *ab; - kfree(aux->used_maps); + if (WARN_ON_ONCE(op >= BPF_AUDIT_MAX)) + return; + if (audit_enabled == AUDIT_OFF) + return; + if (op == BPF_AUDIT_LOAD) + ctx = audit_context(); + ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); + if (unlikely(!ab)) + return; + audit_log_format(ab, "prog-id=%u op=%s", + prog->aux->id, bpf_audit_str[op]); + audit_log_end(ab); } int __bpf_prog_charge(struct user_struct *user, u32 pages) @@ -1316,24 +1682,33 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); - free_used_maps(aux); + kvfree(aux->func_info); + kfree(aux->func_info_aux); bpf_prog_uncharge_memlock(aux->prog); security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } +static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) +{ + bpf_prog_kallsyms_del_all(prog); + btf_put(prog->aux->btf); + bpf_prog_free_linfo(prog); + + if (deferred) + call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); + else + __bpf_prog_put_rcu(&prog->aux->rcu); +} + static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { - if (atomic_dec_and_test(&prog->aux->refcnt)) { + if (atomic64_dec_and_test(&prog->aux->refcnt)) { perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); + bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); - bpf_prog_kallsyms_del_all(prog); - btf_put(prog->aux->btf); - kvfree(prog->aux->func_info); - bpf_prog_free_linfo(prog); - - call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); + __bpf_prog_put_noref(prog, true); } } @@ -1435,13 +1810,9 @@ static struct bpf_prog *____bpf_prog_get(struct fd f) return f.file->private_data; } -struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) +void bpf_prog_add(struct bpf_prog *prog, int i) { - if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) { - atomic_sub(i, &prog->aux->refcnt); - return ERR_PTR(-EBUSY); - } - return prog; + atomic64_add(i, &prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_add); @@ -1452,13 +1823,13 @@ void bpf_prog_sub(struct bpf_prog *prog, int i) * path holds a reference to the program, thus atomic_sub() can * be safely used in such cases! */ - WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0); + WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0); } EXPORT_SYMBOL_GPL(bpf_prog_sub); -struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +void bpf_prog_inc(struct bpf_prog *prog) { - return bpf_prog_add(prog, 1); + atomic64_inc(&prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_inc); @@ -1467,12 +1838,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; - refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0); - - if (refold >= BPF_MAX_REFCNT) { - __bpf_prog_put(prog, false); - return ERR_PTR(-EBUSY); - } + refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); @@ -1510,7 +1876,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, goto out; } - prog = bpf_prog_inc(prog); + bpf_prog_inc(prog); out: fdput(f); return prog; @@ -1555,9 +1921,28 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) } static int -bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, - enum bpf_attach_type expected_attach_type) +bpf_prog_load_check_attach(enum bpf_prog_type prog_type, + enum bpf_attach_type expected_attach_type, + u32 btf_id, u32 prog_fd) { + if (btf_id) { + if (btf_id > BTF_MAX_TYPE) + return -EINVAL; + + switch (prog_type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_STRUCT_OPS: + case BPF_PROG_TYPE_EXT: + break; + default: + return -EINVAL; + } + } + + if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING && + prog_type != BPF_PROG_TYPE_EXT) + return -EINVAL; + switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: switch (expected_attach_type) { @@ -1598,13 +1983,17 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_EXT: + if (expected_attach_type) + return -EINVAL; + /* fallthrough */ default: return 0; } } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD line_info_cnt +#define BPF_PROG_LOAD_LAST_FIELD attach_prog_fd static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -1619,6 +2008,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | + BPF_F_TEST_STATE_FREQ | BPF_F_TEST_RND_HI32)) return -EINVAL; @@ -1645,7 +2035,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) return -EPERM; bpf_prog_load_fixup_attach_type(attr); - if (bpf_prog_load_check_attach_type(type, attr->expected_attach_type)) + if (bpf_prog_load_check_attach(type, attr->expected_attach_type, + attr->attach_btf_id, + attr->attach_prog_fd)) return -EINVAL; /* plain bpf_prog allocation */ @@ -1654,6 +2046,17 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) return -ENOMEM; prog->expected_attach_type = attr->expected_attach_type; + prog->aux->attach_btf_id = attr->attach_btf_id; + if (attr->attach_prog_fd) { + struct bpf_prog *tgt_prog; + + tgt_prog = bpf_prog_get(attr->attach_prog_fd); + if (IS_ERR(tgt_prog)) { + err = PTR_ERR(tgt_prog); + goto free_prog_nouncharge; + } + prog->aux->linked_prog = tgt_prog; + } prog->aux->offload_requested = !!attr->prog_ifindex; @@ -1675,7 +2078,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) prog->orig_prog = NULL; prog->jited = 0; - atomic_set(&prog->aux->refcnt, 1); + atomic64_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0; if (bpf_prog_is_dev_bound(prog->aux)) { @@ -1707,28 +2110,36 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (err) goto free_used_maps; - err = bpf_prog_new_fd(prog); - if (err < 0) { - /* failed to allocate fd. - * bpf_prog_put() is needed because the above - * bpf_prog_alloc_id() has published the prog - * to the userspace and the userspace may - * have refcnt-ed it through BPF_PROG_GET_FD_BY_ID. - */ - bpf_prog_put(prog); - return err; - } - + /* Upon success of bpf_prog_alloc_id(), the BPF prog is + * effectively publicly exposed. However, retrieving via + * bpf_prog_get_fd_by_id() will take another reference, + * therefore it cannot be gone underneath us. + * + * Only for the time /after/ successful bpf_prog_new_fd() + * and before returning to userspace, we might just hold + * one reference and any parallel close on that fd could + * rip everything out. Hence, below notifications must + * happen before bpf_prog_new_fd(). + * + * Also, any failure handling from this point onwards must + * be using bpf_prog_put() given the program is exposed. + */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); + bpf_audit_prog(prog, BPF_AUDIT_LOAD); + + err = bpf_prog_new_fd(prog); + if (err < 0) + bpf_prog_put(prog); return err; free_used_maps: - bpf_prog_free_linfo(prog); - kvfree(prog->aux->func_info); - btf_put(prog->aux->btf); - bpf_prog_kallsyms_del_subprogs(prog); - free_used_maps(prog->aux); + /* In case we have subprogs, we need to wait for a grace + * period before we can tear down JIT memory since symbols + * are already exposed under kallsyms. + */ + __bpf_prog_put_noref(prog, prog->aux->func_cnt); + return err; free_prog: bpf_prog_uncharge_memlock(prog); free_prog_sec: @@ -1758,6 +2169,50 @@ static int bpf_obj_get(const union bpf_attr *attr) attr->file_flags); } +static int bpf_tracing_prog_release(struct inode *inode, struct file *filp) +{ + struct bpf_prog *prog = filp->private_data; + + WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog)); + bpf_prog_put(prog); + return 0; +} + +static const struct file_operations bpf_tracing_prog_fops = { + .release = bpf_tracing_prog_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, +}; + +static int bpf_tracing_prog_attach(struct bpf_prog *prog) +{ + int tr_fd, err; + + if (prog->expected_attach_type != BPF_TRACE_FENTRY && + prog->expected_attach_type != BPF_TRACE_FEXIT && + prog->type != BPF_PROG_TYPE_EXT) { + err = -EINVAL; + goto out_put_prog; + } + + err = bpf_trampoline_link_prog(prog); + if (err) + goto out_put_prog; + + tr_fd = anon_inode_getfd("bpf-tracing-prog", &bpf_tracing_prog_fops, + prog, O_CLOEXEC); + if (tr_fd < 0) { + WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog)); + err = tr_fd; + goto out_put_prog; + } + return tr_fd; + +out_put_prog: + bpf_prog_put(prog); + return err; +} + struct bpf_raw_tracepoint { struct bpf_raw_event_map *btp; struct bpf_prog *prog; @@ -1789,17 +2244,54 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) struct bpf_raw_tracepoint *raw_tp; struct bpf_raw_event_map *btp; struct bpf_prog *prog; - char tp_name[128]; + const char *tp_name; + char buf[128]; int tp_fd, err; - if (strncpy_from_user(tp_name, u64_to_user_ptr(attr->raw_tracepoint.name), - sizeof(tp_name) - 1) < 0) - return -EFAULT; - tp_name[sizeof(tp_name) - 1] = 0; + if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) + return -EINVAL; + + prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT && + prog->type != BPF_PROG_TYPE_TRACING && + prog->type != BPF_PROG_TYPE_EXT && + prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) { + err = -EINVAL; + goto out_put_prog; + } + + if (prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_EXT) { + if (attr->raw_tracepoint.name) { + /* The attach point for this category of programs + * should be specified via btf_id during program load. + */ + err = -EINVAL; + goto out_put_prog; + } + if (prog->expected_attach_type == BPF_TRACE_RAW_TP) + tp_name = prog->aux->attach_func_name; + else + return bpf_tracing_prog_attach(prog); + } else { + if (strncpy_from_user(buf, + u64_to_user_ptr(attr->raw_tracepoint.name), + sizeof(buf) - 1) < 0) { + err = -EFAULT; + goto out_put_prog; + } + buf[sizeof(buf) - 1] = 0; + tp_name = buf; + } btp = bpf_get_raw_tracepoint(tp_name); - if (!btp) - return -ENOENT; + if (!btp) { + err = -ENOENT; + goto out_put_prog; + } raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER); if (!raw_tp) { @@ -1807,38 +2299,27 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) goto out_put_btp; } raw_tp->btp = btp; - - prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); - if (IS_ERR(prog)) { - err = PTR_ERR(prog); - goto out_free_tp; - } - if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT && - prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) { - err = -EINVAL; - goto out_put_prog; - } + raw_tp->prog = prog; err = bpf_probe_register(raw_tp->btp, prog); if (err) - goto out_put_prog; + goto out_free_tp; - raw_tp->prog = prog; tp_fd = anon_inode_getfd("bpf-raw-tracepoint", &bpf_raw_tp_fops, raw_tp, O_CLOEXEC); if (tp_fd < 0) { bpf_probe_unregister(raw_tp->btp, prog); err = tp_fd; - goto out_put_prog; + goto out_free_tp; } return tp_fd; -out_put_prog: - bpf_prog_put(prog); out_free_tp: kfree(raw_tp); out_put_btp: bpf_put_raw_tracepoint(btp); +out_put_prog: + bpf_prog_put(prog); return err; } @@ -1859,10 +2340,10 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, } } -#define BPF_PROG_ATTACH_LAST_FIELD attach_flags +#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd #define BPF_F_ATTACH_MASK \ - (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI) + (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) static int bpf_prog_attach(const union bpf_attr *attr) { @@ -2124,17 +2605,12 @@ static int bpf_obj_get_next_id(const union bpf_attr *attr, #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id -static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) +struct bpf_prog *bpf_prog_by_id(u32 id) { struct bpf_prog *prog; - u32 id = attr->prog_id; - int fd; - if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + if (!id) + return ERR_PTR(-ENOENT); spin_lock_bh(&prog_idr_lock); prog = idr_find(&prog_idr, id); @@ -2143,7 +2619,22 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) else prog = ERR_PTR(-ENOENT); spin_unlock_bh(&prog_idr_lock); + return prog; +} + +static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_prog *prog; + u32 id = attr->prog_id; + int fd; + if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + prog = bpf_prog_by_id(id); if (IS_ERR(prog)) return PTR_ERR(prog); @@ -2177,7 +2668,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) - map = bpf_map_inc_not_zero(map, true); + map = __bpf_map_inc_not_zero(map, true); else map = ERR_PTR(-ENOENT); spin_unlock_bh(&map_idr_lock); @@ -2593,6 +3084,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, info.btf_key_type_id = map->btf_key_type_id; info.btf_value_type_id = map->btf_value_type_id; } + info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_info_fill(&info, map); @@ -2805,6 +3297,61 @@ out: return err; } +#define BPF_MAP_BATCH_LAST_FIELD batch.flags + +#define BPF_DO_BATCH(fn) \ + do { \ + if (!fn) { \ + err = -ENOTSUPP; \ + goto err_put; \ + } \ + err = fn(map, attr, uattr); \ + } while (0) + +static int bpf_map_do_batch(const union bpf_attr *attr, + union bpf_attr __user *uattr, + int cmd) +{ + struct bpf_map *map; + int err, ufd; + struct fd f; + + if (CHECK_ATTR(BPF_MAP_BATCH)) + return -EINVAL; + + ufd = attr->batch.map_fd; + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + if ((cmd == BPF_MAP_LOOKUP_BATCH || + cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && + !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + + if (cmd != BPF_MAP_LOOKUP_BATCH && + !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + + if (cmd == BPF_MAP_LOOKUP_BATCH) + BPF_DO_BATCH(map->ops->map_lookup_batch); + else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) + BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch); + else if (cmd == BPF_MAP_UPDATE_BATCH) + BPF_DO_BATCH(map->ops->map_update_batch); + else + BPF_DO_BATCH(map->ops->map_delete_batch); + +err_put: + fdput(f); + return err; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -2874,6 +3421,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_obj_get_next_id(&attr, uattr, &map_idr, &map_idr_lock); break; + case BPF_BTF_GET_NEXT_ID: + err = bpf_obj_get_next_id(&attr, uattr, + &btf_idr, &btf_idr_lock); + break; case BPF_PROG_GET_FD_BY_ID: err = bpf_prog_get_fd_by_id(&attr); break; @@ -2898,6 +3449,19 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; + case BPF_MAP_LOOKUP_BATCH: + err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH); + break; + case BPF_MAP_LOOKUP_AND_DELETE_BATCH: + err = bpf_map_do_batch(&attr, uattr, + BPF_MAP_LOOKUP_AND_DELETE_BATCH); + break; + case BPF_MAP_UPDATE_BATCH: + err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH); + break; + case BPF_MAP_DELETE_BATCH: + err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c new file mode 100644 index 000000000000..7ae5dddd1fe6 --- /dev/null +++ b/kernel/bpf/sysfs_btf.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Provide kernel BTF information for introspection and use by eBPF tools. + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/kobject.h> +#include <linux/init.h> +#include <linux/sysfs.h> + +/* See scripts/link-vmlinux.sh, gen_btf() func for details */ +extern char __weak _binary__btf_vmlinux_bin_start[]; +extern char __weak _binary__btf_vmlinux_bin_end[]; + +static ssize_t +btf_vmlinux_read(struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t len) +{ + memcpy(buf, _binary__btf_vmlinux_bin_start + off, len); + return len; +} + +static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = { + .attr = { .name = "vmlinux", .mode = 0444, }, + .read = btf_vmlinux_read, +}; + +static struct kobject *btf_kobj; + +static int __init btf_vmlinux_init(void) +{ + if (!_binary__btf_vmlinux_bin_start) + return 0; + + btf_kobj = kobject_create_and_add("btf", kernel_kobj); + if (!btf_kobj) + return -ENOMEM; + + bin_attr_btf_vmlinux.size = _binary__btf_vmlinux_bin_end - + _binary__btf_vmlinux_bin_start; + + return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux); +} + +subsys_initcall(btf_vmlinux_init); diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index ca52b9642943..d4f335a9a899 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -44,14 +44,19 @@ struct tnum tnum_rshift(struct tnum a, u8 shift) return TNUM(a.value >> shift, a.mask >> shift); } -struct tnum tnum_arshift(struct tnum a, u8 min_shift) +struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness) { /* if a.value is negative, arithmetic shifting by minimum shift * will have larger negative offset compared to more shifting. * If a.value is nonnegative, arithmetic shifting by minimum shift * will have larger positive offset compare to more shifting. */ - return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift); + if (insn_bitness == 32) + return TNUM((u32)(((s32)a.value) >> min_shift), + (u32)(((s32)a.mask) >> min_shift)); + else + return TNUM((s64)a.value >> min_shift, + (s64)a.mask >> min_shift); } struct tnum tnum_add(struct tnum a, struct tnum b) diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c new file mode 100644 index 000000000000..6b264a92064b --- /dev/null +++ b/kernel/bpf/trampoline.c @@ -0,0 +1,426 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2019 Facebook */ +#include <linux/hash.h> +#include <linux/bpf.h> +#include <linux/filter.h> +#include <linux/ftrace.h> +#include <linux/rbtree_latch.h> + +/* dummy _ops. The verifier will operate on target program's ops. */ +const struct bpf_verifier_ops bpf_extension_verifier_ops = { +}; +const struct bpf_prog_ops bpf_extension_prog_ops = { +}; + +/* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */ +#define TRAMPOLINE_HASH_BITS 10 +#define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS) + +static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE]; +static struct latch_tree_root image_tree __cacheline_aligned; + +/* serializes access to trampoline_table and image_tree */ +static DEFINE_MUTEX(trampoline_mutex); + +static void *bpf_jit_alloc_exec_page(void) +{ + void *image; + + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!image) + return NULL; + + set_vm_flush_reset_perms(image); + /* Keep image as writeable. The alternative is to keep flipping ro/rw + * everytime new program is attached or detached. + */ + set_memory_x((long)image, 1); + return image; +} + +static __always_inline bool image_tree_less(struct latch_tree_node *a, + struct latch_tree_node *b) +{ + struct bpf_image *ia = container_of(a, struct bpf_image, tnode); + struct bpf_image *ib = container_of(b, struct bpf_image, tnode); + + return ia < ib; +} + +static __always_inline int image_tree_comp(void *addr, struct latch_tree_node *n) +{ + void *image = container_of(n, struct bpf_image, tnode); + + if (addr < image) + return -1; + if (addr >= image + PAGE_SIZE) + return 1; + + return 0; +} + +static const struct latch_tree_ops image_tree_ops = { + .less = image_tree_less, + .comp = image_tree_comp, +}; + +static void *__bpf_image_alloc(bool lock) +{ + struct bpf_image *image; + + image = bpf_jit_alloc_exec_page(); + if (!image) + return NULL; + + if (lock) + mutex_lock(&trampoline_mutex); + latch_tree_insert(&image->tnode, &image_tree, &image_tree_ops); + if (lock) + mutex_unlock(&trampoline_mutex); + return image->data; +} + +void *bpf_image_alloc(void) +{ + return __bpf_image_alloc(true); +} + +bool is_bpf_image_address(unsigned long addr) +{ + bool ret; + + rcu_read_lock(); + ret = latch_tree_find((void *) addr, &image_tree, &image_tree_ops) != NULL; + rcu_read_unlock(); + + return ret; +} + +struct bpf_trampoline *bpf_trampoline_lookup(u64 key) +{ + struct bpf_trampoline *tr; + struct hlist_head *head; + void *image; + int i; + + mutex_lock(&trampoline_mutex); + head = &trampoline_table[hash_64(key, TRAMPOLINE_HASH_BITS)]; + hlist_for_each_entry(tr, head, hlist) { + if (tr->key == key) { + refcount_inc(&tr->refcnt); + goto out; + } + } + tr = kzalloc(sizeof(*tr), GFP_KERNEL); + if (!tr) + goto out; + + /* is_root was checked earlier. No need for bpf_jit_charge_modmem() */ + image = __bpf_image_alloc(false); + if (!image) { + kfree(tr); + tr = NULL; + goto out; + } + + tr->key = key; + INIT_HLIST_NODE(&tr->hlist); + hlist_add_head(&tr->hlist, head); + refcount_set(&tr->refcnt, 1); + mutex_init(&tr->mutex); + for (i = 0; i < BPF_TRAMP_MAX; i++) + INIT_HLIST_HEAD(&tr->progs_hlist[i]); + tr->image = image; +out: + mutex_unlock(&trampoline_mutex); + return tr; +} + +static int is_ftrace_location(void *ip) +{ + long addr; + + addr = ftrace_location((long)ip); + if (!addr) + return 0; + if (WARN_ON_ONCE(addr != (long)ip)) + return -EFAULT; + return 1; +} + +static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr) +{ + void *ip = tr->func.addr; + int ret; + + if (tr->func.ftrace_managed) + ret = unregister_ftrace_direct((long)ip, (long)old_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL); + return ret; +} + +static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr) +{ + void *ip = tr->func.addr; + int ret; + + if (tr->func.ftrace_managed) + ret = modify_ftrace_direct((long)ip, (long)old_addr, (long)new_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr); + return ret; +} + +/* first time registering */ +static int register_fentry(struct bpf_trampoline *tr, void *new_addr) +{ + void *ip = tr->func.addr; + int ret; + + ret = is_ftrace_location(ip); + if (ret < 0) + return ret; + tr->func.ftrace_managed = ret; + + if (tr->func.ftrace_managed) + ret = register_ftrace_direct((long)ip, (long)new_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr); + return ret; +} + +/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 + * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 + */ +#define BPF_MAX_TRAMP_PROGS 40 + +static int bpf_trampoline_update(struct bpf_trampoline *tr) +{ + void *old_image = tr->image + ((tr->selector + 1) & 1) * BPF_IMAGE_SIZE/2; + void *new_image = tr->image + (tr->selector & 1) * BPF_IMAGE_SIZE/2; + struct bpf_prog *progs_to_run[BPF_MAX_TRAMP_PROGS]; + int fentry_cnt = tr->progs_cnt[BPF_TRAMP_FENTRY]; + int fexit_cnt = tr->progs_cnt[BPF_TRAMP_FEXIT]; + struct bpf_prog **progs, **fentry, **fexit; + u32 flags = BPF_TRAMP_F_RESTORE_REGS; + struct bpf_prog_aux *aux; + int err; + + if (fentry_cnt + fexit_cnt == 0) { + err = unregister_fentry(tr, old_image); + tr->selector = 0; + goto out; + } + + /* populate fentry progs */ + fentry = progs = progs_to_run; + hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FENTRY], tramp_hlist) + *progs++ = aux->prog; + + /* populate fexit progs */ + fexit = progs; + hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FEXIT], tramp_hlist) + *progs++ = aux->prog; + + if (fexit_cnt) + flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; + + /* Though the second half of trampoline page is unused a task could be + * preempted in the middle of the first half of trampoline and two + * updates to trampoline would change the code from underneath the + * preempted task. Hence wait for tasks to voluntarily schedule or go + * to userspace. + */ + synchronize_rcu_tasks(); + + err = arch_prepare_bpf_trampoline(new_image, new_image + BPF_IMAGE_SIZE / 2, + &tr->func.model, flags, + fentry, fentry_cnt, + fexit, fexit_cnt, + tr->func.addr); + if (err < 0) + goto out; + + if (tr->selector) + /* progs already running at this address */ + err = modify_fentry(tr, old_image, new_image); + else + /* first time registering */ + err = register_fentry(tr, new_image); + if (err) + goto out; + tr->selector++; +out: + return err; +} + +static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t) +{ + switch (t) { + case BPF_TRACE_FENTRY: + return BPF_TRAMP_FENTRY; + case BPF_TRACE_FEXIT: + return BPF_TRAMP_FEXIT; + default: + return BPF_TRAMP_REPLACE; + } +} + +int bpf_trampoline_link_prog(struct bpf_prog *prog) +{ + enum bpf_tramp_prog_type kind; + struct bpf_trampoline *tr; + int err = 0; + int cnt; + + tr = prog->aux->trampoline; + kind = bpf_attach_type_to_tramp(prog->expected_attach_type); + mutex_lock(&tr->mutex); + if (tr->extension_prog) { + /* cannot attach fentry/fexit if extension prog is attached. + * cannot overwrite extension prog either. + */ + err = -EBUSY; + goto out; + } + cnt = tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT]; + if (kind == BPF_TRAMP_REPLACE) { + /* Cannot attach extension if fentry/fexit are in use. */ + if (cnt) { + err = -EBUSY; + goto out; + } + tr->extension_prog = prog; + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL, + prog->bpf_func); + goto out; + } + if (cnt >= BPF_MAX_TRAMP_PROGS) { + err = -E2BIG; + goto out; + } + if (!hlist_unhashed(&prog->aux->tramp_hlist)) { + /* prog already linked */ + err = -EBUSY; + goto out; + } + hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]); + tr->progs_cnt[kind]++; + err = bpf_trampoline_update(prog->aux->trampoline); + if (err) { + hlist_del(&prog->aux->tramp_hlist); + tr->progs_cnt[kind]--; + } +out: + mutex_unlock(&tr->mutex); + return err; +} + +/* bpf_trampoline_unlink_prog() should never fail. */ +int bpf_trampoline_unlink_prog(struct bpf_prog *prog) +{ + enum bpf_tramp_prog_type kind; + struct bpf_trampoline *tr; + int err; + + tr = prog->aux->trampoline; + kind = bpf_attach_type_to_tramp(prog->expected_attach_type); + mutex_lock(&tr->mutex); + if (kind == BPF_TRAMP_REPLACE) { + WARN_ON_ONCE(!tr->extension_prog); + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, + tr->extension_prog->bpf_func, NULL); + tr->extension_prog = NULL; + goto out; + } + hlist_del(&prog->aux->tramp_hlist); + tr->progs_cnt[kind]--; + err = bpf_trampoline_update(prog->aux->trampoline); +out: + mutex_unlock(&tr->mutex); + return err; +} + +void bpf_trampoline_put(struct bpf_trampoline *tr) +{ + struct bpf_image *image; + + if (!tr) + return; + mutex_lock(&trampoline_mutex); + if (!refcount_dec_and_test(&tr->refcnt)) + goto out; + WARN_ON_ONCE(mutex_is_locked(&tr->mutex)); + if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FENTRY]))) + goto out; + if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) + goto out; + image = container_of(tr->image, struct bpf_image, data); + latch_tree_erase(&image->tnode, &image_tree, &image_tree_ops); + /* wait for tasks to get out of trampoline before freeing it */ + synchronize_rcu_tasks(); + bpf_jit_free_exec(image); + hlist_del(&tr->hlist); + kfree(tr); +out: + mutex_unlock(&trampoline_mutex); +} + +/* The logic is similar to BPF_PROG_RUN, but with explicit rcu and preempt that + * are needed for trampoline. The macro is split into + * call _bpf_prog_enter + * call prog->bpf_func + * call __bpf_prog_exit + */ +u64 notrace __bpf_prog_enter(void) +{ + u64 start = 0; + + rcu_read_lock(); + preempt_disable(); + if (static_branch_unlikely(&bpf_stats_enabled_key)) + start = sched_clock(); + return start; +} + +void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) +{ + struct bpf_prog_stats *stats; + + if (static_branch_unlikely(&bpf_stats_enabled_key) && + /* static_key could be enabled in __bpf_prog_enter + * and disabled in __bpf_prog_exit. + * And vice versa. + * Hence check that 'start' is not zero. + */ + start) { + stats = this_cpu_ptr(prog->aux->stats); + u64_stats_update_begin(&stats->syncp); + stats->cnt++; + stats->nsecs += sched_clock() - start; + u64_stats_update_end(&stats->syncp); + } + preempt_enable(); + rcu_read_unlock(); +} + +int __weak +arch_prepare_bpf_trampoline(void *image, void *image_end, + const struct btf_func_model *m, u32 flags, + struct bpf_prog **fentry_progs, int fentry_cnt, + struct bpf_prog **fexit_progs, int fexit_cnt, + void *orig_call) +{ + return -ENOTSUPP; +} + +static int __init init_trampolines(void) +{ + int i; + + for (i = 0; i < TRAMPOLINE_TABLE_SIZE; i++) + INIT_HLIST_HEAD(&trampoline_table[i]); + return 0; +} +late_initcall(init_trampolines); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c84d83f86141..1cc945daa9c8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -23,7 +23,7 @@ #include "disasm.h" static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { -#define BPF_PROG_TYPE(_id, _name) \ +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _verifier_ops, #define BPF_MAP_TYPE(_id, _ops) #include <linux/bpf_types.h> @@ -171,6 +171,9 @@ struct bpf_verifier_stack_elem { #define BPF_COMPLEXITY_LIMIT_JMP_SEQ 8192 #define BPF_COMPLEXITY_LIMIT_STATES 64 +#define BPF_MAP_KEY_POISON (1ULL << 63) +#define BPF_MAP_KEY_SEEN (1ULL << 62) + #define BPF_MAP_PTR_UNPRIV 1UL #define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \ POISON_POINTER_DELTA)) @@ -178,12 +181,12 @@ struct bpf_verifier_stack_elem { static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux) { - return BPF_MAP_PTR(aux->map_state) == BPF_MAP_PTR_POISON; + return BPF_MAP_PTR(aux->map_ptr_state) == BPF_MAP_PTR_POISON; } static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux) { - return aux->map_state & BPF_MAP_PTR_UNPRIV; + return aux->map_ptr_state & BPF_MAP_PTR_UNPRIV; } static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux, @@ -191,8 +194,31 @@ static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux, { BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV); unpriv |= bpf_map_ptr_unpriv(aux); - aux->map_state = (unsigned long)map | - (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL); + aux->map_ptr_state = (unsigned long)map | + (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL); +} + +static bool bpf_map_key_poisoned(const struct bpf_insn_aux_data *aux) +{ + return aux->map_key_state & BPF_MAP_KEY_POISON; +} + +static bool bpf_map_key_unseen(const struct bpf_insn_aux_data *aux) +{ + return !(aux->map_key_state & BPF_MAP_KEY_SEEN); +} + +static u64 bpf_map_key_immediate(const struct bpf_insn_aux_data *aux) +{ + return aux->map_key_state & ~(BPF_MAP_KEY_SEEN | BPF_MAP_KEY_POISON); +} + +static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state) +{ + bool poisoned = bpf_map_key_poisoned(aux); + + aux->map_key_state = state | BPF_MAP_KEY_SEEN | + (poisoned ? BPF_MAP_KEY_POISON : 0ULL); } struct bpf_call_arg_meta { @@ -205,8 +231,11 @@ struct bpf_call_arg_meta { u64 msize_umax_value; int ref_obj_id; int func_id; + u32 btf_id; }; +struct btf *btf_vmlinux; + static DEFINE_MUTEX(bpf_verifier_lock); static const struct bpf_line_info * @@ -243,6 +272,10 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, n = min(log->len_total - log->len_used - 1, n); log->kbuf[n] = '\0'; + if (log->level == BPF_LOG_KERNEL) { + pr_err("BPF:%s\n", log->kbuf); + return; + } if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) log->len_used += n; else @@ -280,6 +313,19 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) va_end(args); } +__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, + const char *fmt, ...) +{ + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); +} + static const char *ltrim(const char *s) { while (isspace(*s)) @@ -400,6 +446,7 @@ static const char * const reg_type_str[] = { [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", [PTR_TO_TP_BUFFER] = "tp_buffer", [PTR_TO_XDP_SOCK] = "xdp_sock", + [PTR_TO_BTF_ID] = "ptr_", }; static char slot_type_char[] = { @@ -430,6 +477,12 @@ static struct bpf_func_state *func(struct bpf_verifier_env *env, return cur->frame[reg->frameno]; } +const char *kernel_type_name(u32 id) +{ + return btf_name_by_offset(btf_vmlinux, + btf_type_by_id(btf_vmlinux, id)->name_off); +} + static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { @@ -454,6 +507,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, /* reg->off should be 0 for SCALAR_VALUE */ verbose(env, "%lld", reg->var_off.value + reg->off); } else { + if (t == PTR_TO_BTF_ID) + verbose(env, "%s", kernel_type_name(reg->btf_id)); verbose(env, "(id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t)) verbose(env, ",ref_obj_id=%d", reg->ref_obj_id); @@ -852,7 +907,8 @@ 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 *reg); +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg); /* Mark the unknown part of a register (variable offset or scalar value) as * known to have the value @imm. @@ -890,7 +946,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, verbose(env, "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); + __mark_reg_not_init(env, regs + regno); return; } __mark_reg_known_zero(regs + regno); @@ -978,6 +1034,17 @@ static void __reg_bound_offset(struct bpf_reg_state *reg) reg->umax_value)); } +static void __reg_bound_offset32(struct bpf_reg_state *reg) +{ + u64 mask = 0xffffFFFF; + struct tnum range = tnum_range(reg->umin_value & mask, + reg->umax_value & mask); + struct tnum lo32 = tnum_cast(reg->var_off, 4); + struct tnum hi32 = tnum_lshift(tnum_rshift(reg->var_off, 32), 32); + + reg->var_off = tnum_or(hi32, tnum_intersect(lo32, range)); +} + /* Reset the min/max bounds of a register */ static void __mark_reg_unbounded(struct bpf_reg_state *reg) { @@ -985,13 +1052,11 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; - - /* constant backtracking is enabled for root only for now */ - reg->precise = capable(CAP_SYS_ADMIN) ? false : true; } /* Mark a register as having a completely unknown (scalar) value. */ -static void __mark_reg_unknown(struct bpf_reg_state *reg) +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { /* * Clear type, id, off, and union(map_ptr, range) and @@ -1001,6 +1066,8 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg) reg->type = SCALAR_VALUE; reg->var_off = tnum_unknown; reg->frameno = 0; + reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? + true : false; __mark_reg_unbounded(reg); } @@ -1011,15 +1078,16 @@ static void mark_reg_unknown(struct bpf_verifier_env *env, verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - __mark_reg_unknown(regs + regno); + __mark_reg_unknown(env, regs + regno); } -static void __mark_reg_not_init(struct bpf_reg_state *reg) +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); reg->type = NOT_INIT; } @@ -1030,10 +1098,10 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); } #define DEF_NOT_SUBREG (0) @@ -1054,10 +1122,6 @@ static void init_reg_state(struct bpf_verifier_env *env, regs[BPF_REG_FP].type = PTR_TO_STACK; mark_reg_known_zero(env, regs, BPF_REG_FP); regs[BPF_REG_FP].frameno = state->frameno; - - /* 1st arg to a function */ - regs[BPF_REG_1].type = PTR_TO_CTX; - mark_reg_known_zero(env, regs, BPF_REG_1); } #define BPF_MAIN_FUNC (-1) @@ -1771,16 +1835,21 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, bitmap_from_u64(mask, stack_mask); for_each_set_bit(i, mask, 64) { if (i >= func->allocated_stack / BPF_REG_SIZE) { - /* This can happen if backtracking - * is propagating stack precision where - * caller has larger stack frame - * than callee, but backtrack_insn() should - * have returned -ENOTSUPP. + /* the sequence of instructions: + * 2: (bf) r3 = r10 + * 3: (7b) *(u64 *)(r3 -8) = r0 + * 4: (79) r4 = *(u64 *)(r10 -8) + * doesn't contain jmps. It's backtracked + * as a single block. + * During backtracking insn 3 is not recognized as + * stack access, so at the end of backtracking + * stack slot fp-8 is still marked in stack_mask. + * However the parent state may not have accessed + * fp-8 and it's "unallocated" stack space. + * In such case fallback to conservative. */ - verbose(env, "BUG spi %d stack_size %d\n", - i, func->allocated_stack); - WARN_ONCE(1, "verifier backtracking bug"); - return -EFAULT; + mark_all_scalars_precise(env, st); + return 0; } if (func->stack[i].slot_type[0] != STACK_SPILL) { @@ -1843,6 +1912,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: + case PTR_TO_BTF_ID: return true; default: return false; @@ -2325,10 +2395,12 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, /* 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) + enum bpf_access_type t, enum bpf_reg_type *reg_type, + u32 *btf_id) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, + .log = &env->log, }; if (env->ops->is_valid_access && @@ -2342,7 +2414,10 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, */ *reg_type = info.reg_type; - env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + if (*reg_type == PTR_TO_BTF_ID) + *btf_id = info.btf_id; + else + env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; @@ -2660,8 +2735,8 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, } #endif -static int check_ctx_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno) +int check_ctx_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno) { /* Access to ctx or passing it to a helper is only allowed in * its original, unmodified form. @@ -2733,6 +2808,98 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) reg->smax_value = reg->umax_value; } +static bool bpf_map_is_rdonly(const struct bpf_map *map) +{ + return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen; +} + +static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) +{ + void *ptr; + u64 addr; + int err; + + err = map->ops->map_direct_value_addr(map, &addr, off); + if (err) + return err; + ptr = (void *)(long)addr + off; + + switch (size) { + case sizeof(u8): + *val = (u64)*(u8 *)ptr; + break; + case sizeof(u16): + *val = (u64)*(u16 *)ptr; + break; + case sizeof(u32): + *val = (u64)*(u32 *)ptr; + break; + case sizeof(u64): + *val = *(u64 *)ptr; + break; + default: + return -EINVAL; + } + return 0; +} + +static int check_ptr_to_btf_access(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, + int regno, int off, int size, + enum bpf_access_type atype, + int value_regno) +{ + struct bpf_reg_state *reg = regs + regno; + const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id); + const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off); + u32 btf_id; + int ret; + + if (off < 0) { + verbose(env, + "R%d is ptr_%s invalid negative access: off=%d\n", + regno, tname, off); + return -EACCES; + } + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, + "R%d is ptr_%s invalid variable offset: off=%d, var_off=%s\n", + regno, tname, off, tn_buf); + return -EACCES; + } + + if (env->ops->btf_struct_access) { + ret = env->ops->btf_struct_access(&env->log, t, off, size, + atype, &btf_id); + } else { + if (atype != BPF_READ) { + verbose(env, "only read is supported\n"); + return -EACCES; + } + + ret = btf_struct_access(&env->log, t, off, size, atype, + &btf_id); + } + + if (ret < 0) + return ret; + + if (atype == BPF_READ) { + if (ret == SCALAR_VALUE) { + mark_reg_unknown(env, regs, value_regno); + return 0; + } + mark_reg_known_zero(env, regs, value_regno); + regs[value_regno].type = PTR_TO_BTF_ID; + regs[value_regno].btf_id = btf_id; + } + + return 0; +} + /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory @@ -2770,11 +2937,30 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err) return err; err = check_map_access(env, regno, off, size, false); - if (!err && t == BPF_READ && value_regno >= 0) - mark_reg_unknown(env, regs, value_regno); + if (!err && t == BPF_READ && value_regno >= 0) { + struct bpf_map *map = reg->map_ptr; + + /* if map is read-only, track its contents as scalars */ + if (tnum_is_const(reg->var_off) && + bpf_map_is_rdonly(map) && + map->ops->map_direct_value_addr) { + int map_off = off + reg->var_off.value; + u64 val = 0; + + err = bpf_map_direct_read(map, map_off, size, + &val); + if (err) + return err; + regs[value_regno].type = SCALAR_VALUE; + __mark_reg_known(®s[value_regno], val); + } else { + mark_reg_unknown(env, regs, value_regno); + } + } } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; + u32 btf_id = 0; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { @@ -2786,7 +2972,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err < 0) return err; - err = check_ctx_access(env, insn_idx, off, size, t, ®_type); + err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf_id); + if (err) + verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a * PTR_TO_PACKET[_META,_END]. In the latter @@ -2805,6 +2993,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; + if (reg_type == PTR_TO_BTF_ID) + regs[value_regno].btf_id = btf_id; } regs[value_regno].type = reg_type; } @@ -2864,6 +3054,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_tp_buffer_access(env, reg, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_BTF_ID) { + err = check_ptr_to_btf_access(env, regs, regno, off, size, t, + value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); @@ -3049,7 +3242,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, } if (state->stack[spi].slot_type[0] == STACK_SPILL && state->stack[spi].spilled_ptr.type == SCALAR_VALUE) { - __mark_reg_unknown(&state->stack[spi].spilled_ptr); + __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) state->stack[spi].slot_type[j] = STACK_MISC; goto mark; @@ -3292,6 +3485,22 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, expected_type = PTR_TO_SOCKET; if (type != expected_type) goto err_type; + } else if (arg_type == ARG_PTR_TO_BTF_ID) { + expected_type = PTR_TO_BTF_ID; + if (type != expected_type) + goto err_type; + if (reg->btf_id != meta->btf_id) { + verbose(env, "Helper has type %s got %s in R%d\n", + kernel_type_name(meta->btf_id), + kernel_type_name(reg->btf_id), regno); + + return -EACCES; + } + if (!tnum_is_const(reg->var_off) || reg->var_off.value || reg->off) { + verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n", + regno); + return -EACCES; + } } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) @@ -3439,6 +3648,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_PERF_EVENT_ARRAY: if (func_id != BPF_FUNC_perf_event_read && func_id != BPF_FUNC_perf_event_output && + func_id != BPF_FUNC_skb_output && func_id != BPF_FUNC_perf_event_read_value) goto error; break; @@ -3457,6 +3667,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; @@ -3525,6 +3736,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_FUNC_perf_event_read: case BPF_FUNC_perf_event_output: case BPF_FUNC_perf_event_read_value: + case BPF_FUNC_skb_output: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; @@ -3539,6 +3751,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && + map->map_type != BPF_MAP_TYPE_DEVMAP_HASH && map->map_type != BPF_MAP_TYPE_CPUMAP && map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; @@ -3687,7 +3900,7 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, if (!reg) continue; if (reg_is_pkt_pointer_any(reg)) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -3715,7 +3928,7 @@ static void release_reg_references(struct bpf_verifier_env *env, if (!reg) continue; if (reg->ref_obj_id == ref_obj_id) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -3739,12 +3952,26 @@ static int release_reference(struct bpf_verifier_env *env, return 0; } +static void clear_caller_saved_regs(struct bpf_verifier_env *env, + struct bpf_reg_state *regs) +{ + int i; + + /* after the call registers r0 - r5 were scratched */ + for (i = 0; i < CALLER_SAVED_REGS; i++) { + mark_reg_not_init(env, regs, caller_saved[i]); + check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); + } +} + static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; + struct bpf_func_info_aux *func_info_aux; struct bpf_func_state *caller, *callee; int i, err, subprog, target_insn; + bool is_global = false; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", @@ -3767,6 +3994,32 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EFAULT; } + func_info_aux = env->prog->aux->func_info_aux; + if (func_info_aux) + is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; + err = btf_check_func_arg_match(env, subprog, caller->regs); + if (err == -EFAULT) + return err; + if (is_global) { + if (err) { + verbose(env, "Caller passes invalid args into func#%d\n", + subprog); + return err; + } else { + if (env->log.level & BPF_LOG_LEVEL) + verbose(env, + "Func#%d is global and valid. Skipping.\n", + subprog); + clear_caller_saved_regs(env, caller->regs); + + /* All global functions return SCALAR_VALUE */ + mark_reg_unknown(env, caller->regs, BPF_REG_0); + + /* continue with next insn after call */ + return 0; + } + } + callee = kzalloc(sizeof(*callee), GFP_KERNEL); if (!callee) return -ENOMEM; @@ -3793,11 +4046,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, for (i = BPF_REG_1; i <= BPF_REG_5; i++) callee->regs[i] = caller->regs[i]; - /* after the call registers r0 - r5 were scratched */ - for (i = 0; i < CALLER_SAVED_REGS; i++) { - mark_reg_not_init(env, caller->regs, caller_saved[i]); - check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); - } + clear_caller_saved_regs(env, caller->regs); /* only increment it after check_reg_arg() finished */ state->curframe++; @@ -3908,15 +4157,54 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return -EACCES; } - if (!BPF_MAP_PTR(aux->map_state)) + if (!BPF_MAP_PTR(aux->map_ptr_state)) bpf_map_ptr_store(aux, meta->map_ptr, meta->map_ptr->unpriv_array); - else if (BPF_MAP_PTR(aux->map_state) != meta->map_ptr) + else if (BPF_MAP_PTR(aux->map_ptr_state) != meta->map_ptr) bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON, meta->map_ptr->unpriv_array); return 0; } +static int +record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, + int func_id, int insn_idx) +{ + struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; + struct bpf_reg_state *regs = cur_regs(env), *reg; + struct bpf_map *map = meta->map_ptr; + struct tnum range; + u64 val; + int err; + + if (func_id != BPF_FUNC_tail_call) + return 0; + if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) { + verbose(env, "kernel subsystem misconfigured verifier\n"); + return -EINVAL; + } + + range = tnum_range(0, map->max_entries - 1); + reg = ®s[BPF_REG_3]; + + if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) { + bpf_map_key_store(aux, BPF_MAP_KEY_POISON); + return 0; + } + + err = mark_chain_precision(env, BPF_REG_3); + if (err) + return err; + + val = reg->var_off.value; + if (bpf_map_key_unseen(aux)) + bpf_map_key_store(aux, val); + else if (!bpf_map_key_poisoned(aux) && + bpf_map_key_immediate(aux) != val) + bpf_map_key_store(aux, BPF_MAP_KEY_POISON); + return 0; +} + static int check_reference_leak(struct bpf_verifier_env *env) { struct bpf_func_state *state = cur_func(env); @@ -3978,23 +4266,20 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn meta.func_id = func_id; /* check args */ - err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta); - if (err) - return err; - err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta); - if (err) - return err; - err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta); - if (err) - return err; - err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta); - if (err) - return err; - err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta); + for (i = 0; i < 5; i++) { + err = btf_resolve_helper_id(&env->log, fn, i); + if (err > 0) + meta.btf_id = err; + err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta); + if (err) + return err; + } + + err = record_func_map(env, &meta, func_id, insn_idx); if (err) return err; - err = record_func_map(env, &meta, func_id, insn_idx); + err = record_func_key(env, &meta, func_id, insn_idx); if (err) return err; @@ -4338,7 +4623,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -4590,13 +4875,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } if (!src_known && opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -4804,9 +5089,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Upon reaching here, src_known is true and * umax_val is equal to umin_val. */ - dst_reg->smin_value >>= umin_val; - dst_reg->smax_value >>= umin_val; - dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); + if (insn_bitness == 32) { + dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val); + dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val); + } else { + dst_reg->smin_value >>= umin_val; + dst_reg->smax_value >>= umin_val; + } + + dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, + insn_bitness); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. @@ -5425,6 +5717,10 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, /* We might have learned some bits from the bounds. */ __reg_bound_offset(false_reg); __reg_bound_offset(true_reg); + if (is_jmp32) { + __reg_bound_offset32(false_reg); + __reg_bound_offset32(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. @@ -5534,6 +5830,10 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, /* We might have learned some bits from the bounds. */ __reg_bound_offset(false_reg); __reg_bound_offset(true_reg); + if (is_jmp32) { + __reg_bound_offset32(false_reg); + __reg_bound_offset32(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. @@ -6011,6 +6311,7 @@ static bool may_access_skb(enum bpf_prog_type type) static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); + static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); int i, err; @@ -6044,7 +6345,7 @@ 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(env, BPF_REG_6, SRC_OP); + err = check_reg_arg(env, ctx_reg, SRC_OP); if (err) return err; @@ -6063,7 +6364,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (regs[BPF_REG_6].type != PTR_TO_CTX) { + if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; @@ -6076,6 +6377,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } + err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); + if (err < 0) + return err; + /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); @@ -6095,8 +6400,30 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) static int check_return_code(struct bpf_verifier_env *env) { struct tnum enforce_attach_type_range = tnum_unknown; + const struct bpf_prog *prog = env->prog; struct bpf_reg_state *reg; struct tnum range = tnum_range(0, 1); + int err; + + /* The struct_ops func-ptr's return type could be "void" */ + if (env->prog->type == BPF_PROG_TYPE_STRUCT_OPS && + !prog->aux->attach_func_proto->type) + return 0; + + /* eBPF calling convetion is such that R0 is used + * to return the value from eBPF program. + * Make sure that it's readable at this time + * of bpf_exit, which means that program wrote + * something into it earlier + */ + err = check_reg_arg(env, BPF_REG_0, SRC_OP); + if (err) + return err; + + if (is_pointer_value(env, BPF_REG_0)) { + verbose(env, "R0 leaks addr as return value\n"); + return -EACCES; + } switch (env->prog->type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: @@ -6116,6 +6443,11 @@ static int check_return_code(struct bpf_verifier_env *env) case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: break; + case BPF_PROG_TYPE_RAW_TRACEPOINT: + if (!env->prog->aux->attach_btf_id) + return 0; + range = tnum_const(0); + break; default: return 0; } @@ -6398,6 +6730,7 @@ static int check_btf_func(struct bpf_verifier_env *env, u32 i, nfuncs, urec_size, min_size; u32 krec_size = sizeof(struct bpf_func_info); struct bpf_func_info *krecord; + struct bpf_func_info_aux *info_aux = NULL; const struct btf_type *type; struct bpf_prog *prog; const struct btf *btf; @@ -6431,6 +6764,9 @@ static int check_btf_func(struct bpf_verifier_env *env, krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); if (!krecord) return -ENOMEM; + info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN); + if (!info_aux) + goto err_free; for (i = 0; i < nfuncs; i++) { ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); @@ -6476,35 +6812,38 @@ static int check_btf_func(struct bpf_verifier_env *env, /* check type_id */ type = btf_type_by_id(btf, krecord[i].type_id); - if (!type || BTF_INFO_KIND(type->info) != BTF_KIND_FUNC) { + if (!type || !btf_type_is_func(type)) { verbose(env, "invalid type id %d in func info", krecord[i].type_id); ret = -EINVAL; goto err_free; } - + info_aux[i].linkage = BTF_INFO_VLEN(type->info); prev_offset = krecord[i].insn_off; urecord += urec_size; } prog->aux->func_info = krecord; prog->aux->func_info_cnt = nfuncs; + prog->aux->func_info_aux = info_aux; return 0; err_free: kvfree(krecord); + kfree(info_aux); return ret; } static void adjust_btf_func(struct bpf_verifier_env *env) { + struct bpf_prog_aux *aux = env->prog->aux; int i; - if (!env->prog->aux->func_info) + if (!aux->func_info) return; for (i = 0; i < env->subprog_cnt; i++) - env->prog->aux->func_info[i].insn_off = env->subprog_info[i].start; + aux->func_info[i].insn_off = env->subprog_info[i].start; } #define MIN_BPF_LINEINFO_SIZE (offsetof(struct bpf_line_info, line_col) + \ @@ -6719,7 +7058,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* since the register is unused, clear its state * to make further comparison simpler */ - __mark_reg_not_init(&st->regs[i]); + __mark_reg_not_init(env, &st->regs[i]); } for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { @@ -6727,7 +7066,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* liveness must not touch this stack slot anymore */ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) { - __mark_reg_not_init(&st->stack[i].spilled_ptr); + __mark_reg_not_init(env, &st->stack[i].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) st->stack[i].slot_type[j] = STACK_INVALID; } @@ -7220,7 +7559,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; - bool add_new_state = false; + bool add_new_state = env->test_state_freq ? true : false; cur->last_insn_idx = env->prev_insn_idx; if (!env->insn_aux_data[insn_idx].prune_point) @@ -7432,6 +7771,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type) case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: + case PTR_TO_BTF_ID: return false; default: return true; @@ -7458,32 +7798,13 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) static int do_check(struct bpf_verifier_env *env) { - struct bpf_verifier_state *state; + struct bpf_verifier_state *state = env->cur_state; struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; int insn_cnt = env->prog->len; bool do_print_state = false; int prev_insn_idx = -1; - env->prev_linfo = NULL; - - state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); - if (!state) - return -ENOMEM; - state->curframe = 0; - state->speculative = false; - state->branches = 1; - state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); - if (!state->frame[0]) { - kfree(state); - return -ENOMEM; - } - env->cur_state = state; - init_func_state(env, state->frame[0], - BPF_MAIN_FUNC /* callsite */, - 0 /* frameno */, - 0 /* subprogno, zero == main subprog */); - for (;;) { struct bpf_insn *insn; u8 class; @@ -7561,7 +7882,7 @@ static int do_check(struct bpf_verifier_env *env) } regs = cur_regs(env); - env->insn_aux_data[env->insn_idx].seen = true; + env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; prev_insn_idx = env->insn_idx; if (class == BPF_ALU || class == BPF_ALU64) { @@ -7747,21 +8068,6 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; - /* eBPF calling convetion is such that R0 is used - * to return the value from eBPF program. - * Make sure that it's readable at this time - * of bpf_exit, which means that program wrote - * something into it earlier - */ - err = check_reg_arg(env, BPF_REG_0, SRC_OP); - if (err) - return err; - - if (is_pointer_value(env, BPF_REG_0)) { - verbose(env, "R0 leaks addr as return value\n"); - return -EACCES; - } - err = check_return_code(env); if (err) return err; @@ -7796,7 +8102,7 @@ process_bpf_exit: return err; env->insn_idx++; - env->insn_aux_data[env->insn_idx].seen = true; + env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; @@ -7809,7 +8115,6 @@ process_bpf_exit: env->insn_idx++; } - env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return 0; } @@ -7869,6 +8174,11 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + verbose(env, "bpf_struct_ops map cannot be used in prog\n"); + return -EINVAL; + } + return 0; } @@ -8000,17 +8310,13 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) * will be used by the valid program until it's unloaded * and all maps are released in free_used_maps() */ - map = bpf_map_inc(map, false); - if (IS_ERR(map)) { - fdput(f); - return PTR_ERR(map); - } + bpf_map_inc(map); aux->map_index = env->used_map_cnt; env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && - bpf_cgroup_storage_assign(env->prog, map)) { + bpf_cgroup_storage_assign(env->prog->aux, map)) { verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; @@ -8040,18 +8346,8 @@ next_insn: /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { - enum bpf_cgroup_storage_type stype; - int i; - - for_each_cgroup_storage_type(stype) { - if (!env->prog->aux->cgroup_storage[stype]) - continue; - bpf_cgroup_storage_release(env->prog, - env->prog->aux->cgroup_storage[stype]); - } - - for (i = 0; i < env->used_map_cnt; i++) - bpf_map_put(env->used_maps[i]); + __bpf_free_used_maps(env->prog->aux, env->used_maps, + env->used_map_cnt); } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ @@ -8095,7 +8391,7 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); for (i = off; i < off + cnt - 1; i++) { - new_data[i].seen = true; + new_data[i].seen = env->pass_cnt; new_data[i].zext_dst = insn_has_def32(env, insn + i); } env->insn_aux_data = new_data; @@ -8573,6 +8869,16 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) case PTR_TO_XDP_SOCK: convert_ctx_access = bpf_xdp_sock_convert_ctx_access; break; + case PTR_TO_BTF_ID: + if (type == BPF_READ) { + insn->code = BPF_LDX | BPF_PROBE_MEM | + BPF_SIZE((insn)->code); + env->prog->aux->num_exentries++; + } else if (env->prog->type != BPF_PROG_TYPE_STRUCT_OPS) { + verbose(env, "Writes through BTF pointers are not allowed\n"); + return -EINVAL; + } + continue; default: continue; } @@ -8616,8 +8922,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } if (is_narrower_load && size < target_size) { - u8 shift = bpf_ctx_narrow_load_shift(off, size, - size_default); + u8 shift = bpf_ctx_narrow_access_offset( + off, size, size_default) * 8; if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, @@ -8863,6 +9169,7 @@ static int fixup_call_args(struct bpf_verifier_env *env) static int fixup_bpf_calls(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; + bool expect_blinding = bpf_jit_blinding_enabled(prog); struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; @@ -8871,7 +9178,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; struct bpf_map *map_ptr; - int i, cnt, delta = 0; + int i, ret, cnt, delta = 0; for (i = 0; i < insn_cnt; i++, insn++) { if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || @@ -9015,6 +9322,27 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->code = BPF_JMP | BPF_TAIL_CALL; aux = &env->insn_aux_data[i + delta]; + if (env->allow_ptr_leaks && !expect_blinding && + prog->jit_requested && + !bpf_map_key_poisoned(aux) && + !bpf_map_ptr_poisoned(aux) && + !bpf_map_ptr_unpriv(aux)) { + struct bpf_jit_poke_descriptor desc = { + .reason = BPF_POKE_REASON_TAIL_CALL, + .tail_call.map = BPF_MAP_PTR(aux->map_ptr_state), + .tail_call.key = bpf_map_key_immediate(aux), + }; + + ret = bpf_jit_add_poke_descriptor(prog, &desc); + if (ret < 0) { + verbose(env, "adding tail call poke descriptor failed\n"); + return ret; + } + + insn->imm = ret + 1; + continue; + } + if (!bpf_map_ptr_unpriv(aux)) continue; @@ -9029,7 +9357,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) return -EINVAL; } - map_ptr = BPF_MAP_PTR(aux->map_state); + map_ptr = BPF_MAP_PTR(aux->map_ptr_state); insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, map_ptr->max_entries, 2); insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, @@ -9063,7 +9391,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; - map_ptr = BPF_MAP_PTR(aux->map_state); + map_ptr = BPF_MAP_PTR(aux->map_ptr_state); ops = map_ptr->ops; if (insn->imm == BPF_FUNC_map_lookup_elem && ops->map_gen_lookup) { @@ -9129,6 +9457,30 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) goto patch_call_imm; } + if (prog->jit_requested && BITS_PER_LONG == 64 && + insn->imm == BPF_FUNC_jiffies64) { + struct bpf_insn ld_jiffies_addr[2] = { + BPF_LD_IMM64(BPF_REG_0, + (unsigned long)&jiffies), + }; + + insn_buf[0] = ld_jiffies_addr[0]; + insn_buf[1] = ld_jiffies_addr[1]; + insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, + BPF_REG_0, 0); + cnt = 3; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, + cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); /* all functions that have prototype and verifier allowed @@ -9143,6 +9495,23 @@ patch_call_imm: insn->imm = fn->func - __bpf_call_base; } + /* Since poke tab is now finalized, publish aux to tracker. */ + for (i = 0; i < prog->aux->size_poke_tab; i++) { + map_ptr = prog->aux->poke_tab[i].tail_call.map; + if (!map_ptr->ops->map_poke_track || + !map_ptr->ops->map_poke_untrack || + !map_ptr->ops->map_poke_run) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } + + ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux); + if (ret < 0) { + verbose(env, "tracking tail call prog failed\n"); + return ret; + } + } + return 0; } @@ -9158,6 +9527,7 @@ static void free_states(struct bpf_verifier_env *env) kfree(sl); sl = sln; } + env->free_list = NULL; if (!env->explored_states) return; @@ -9171,11 +9541,164 @@ static void free_states(struct bpf_verifier_env *env) kfree(sl); sl = sln; } + env->explored_states[i] = NULL; } +} - kvfree(env->explored_states); +/* The verifier is using insn_aux_data[] to store temporary data during + * verification and to store information for passes that run after the + * verification like dead code sanitization. do_check_common() for subprogram N + * may analyze many other subprograms. sanitize_insn_aux_data() clears all + * temporary data after do_check_common() finds that subprogram N cannot be + * verified independently. pass_cnt counts the number of times + * do_check_common() was run and insn->aux->seen tells the pass number + * insn_aux_data was touched. These variables are compared to clear temporary + * data from failed pass. For testing and experiments do_check_common() can be + * run multiple times even when prior attempt to verify is unsuccessful. + */ +static void sanitize_insn_aux_data(struct bpf_verifier_env *env) +{ + struct bpf_insn *insn = env->prog->insnsi; + struct bpf_insn_aux_data *aux; + int i, class; + + for (i = 0; i < env->prog->len; i++) { + class = BPF_CLASS(insn[i].code); + if (class != BPF_LDX && class != BPF_STX) + continue; + aux = &env->insn_aux_data[i]; + if (aux->seen != env->pass_cnt) + continue; + memset(aux, 0, offsetof(typeof(*aux), orig_idx)); + } } +static int do_check_common(struct bpf_verifier_env *env, int subprog) +{ + struct bpf_verifier_state *state; + struct bpf_reg_state *regs; + int ret, i; + + env->prev_linfo = NULL; + env->pass_cnt++; + + state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); + if (!state) + return -ENOMEM; + state->curframe = 0; + state->speculative = false; + state->branches = 1; + state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); + if (!state->frame[0]) { + kfree(state); + return -ENOMEM; + } + env->cur_state = state; + init_func_state(env, state->frame[0], + BPF_MAIN_FUNC /* callsite */, + 0 /* frameno */, + subprog); + + regs = state->frame[state->curframe]->regs; + if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { + ret = btf_prepare_func_args(env, subprog, regs); + if (ret) + goto out; + for (i = BPF_REG_1; i <= BPF_REG_5; i++) { + if (regs[i].type == PTR_TO_CTX) + mark_reg_known_zero(env, regs, i); + else if (regs[i].type == SCALAR_VALUE) + mark_reg_unknown(env, regs, i); + } + } else { + /* 1st arg to a function */ + regs[BPF_REG_1].type = PTR_TO_CTX; + mark_reg_known_zero(env, regs, BPF_REG_1); + ret = btf_check_func_arg_match(env, subprog, regs); + if (ret == -EFAULT) + /* unlikely verifier bug. abort. + * ret == 0 and ret < 0 are sadly acceptable for + * main() function due to backward compatibility. + * Like socket filter program may be written as: + * int bpf_prog(struct pt_regs *ctx) + * and never dereference that ctx in the program. + * 'struct pt_regs' is a type mismatch for socket + * filter that should be using 'struct __sk_buff'. + */ + goto out; + } + + ret = do_check(env); +out: + /* check for NULL is necessary, since cur_state can be freed inside + * do_check() under memory pressure. + */ + if (env->cur_state) { + free_verifier_state(env->cur_state, true); + env->cur_state = NULL; + } + while (!pop_stack(env, NULL, NULL)); + free_states(env); + if (ret) + /* clean aux data in case subprog was rejected */ + sanitize_insn_aux_data(env); + return ret; +} + +/* Verify all global functions in a BPF program one by one based on their BTF. + * All global functions must pass verification. Otherwise the whole program is rejected. + * Consider: + * int bar(int); + * int foo(int f) + * { + * return bar(f); + * } + * int bar(int b) + * { + * ... + * } + * foo() will be verified first for R1=any_scalar_value. During verification it + * will be assumed that bar() already verified successfully and call to bar() + * from foo() will be checked for type match only. Later bar() will be verified + * independently to check that it's safe for R1=any_scalar_value. + */ +static int do_check_subprogs(struct bpf_verifier_env *env) +{ + struct bpf_prog_aux *aux = env->prog->aux; + int i, ret; + + if (!aux->func_info) + return 0; + + for (i = 1; i < env->subprog_cnt; i++) { + if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL) + continue; + env->insn_idx = env->subprog_info[i].start; + WARN_ON_ONCE(env->insn_idx == 0); + ret = do_check_common(env, i); + if (ret) { + return ret; + } else if (env->log.level & BPF_LOG_LEVEL) { + verbose(env, + "Func#%d is safe for any args that match its prototype\n", + i); + } + } + return 0; +} + +static int do_check_main(struct bpf_verifier_env *env) +{ + int ret; + + env->insn_idx = 0; + ret = do_check_common(env, 0); + if (!ret) + env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; + return ret; +} + + static void print_verification_stats(struct bpf_verifier_env *env) { int i; @@ -9200,6 +9723,264 @@ static void print_verification_stats(struct bpf_verifier_env *env) env->peak_states, env->longest_mark_read_walk); } +static int check_struct_ops_btf_id(struct bpf_verifier_env *env) +{ + const struct btf_type *t, *func_proto; + const struct bpf_struct_ops *st_ops; + const struct btf_member *member; + struct bpf_prog *prog = env->prog; + u32 btf_id, member_idx; + const char *mname; + + btf_id = prog->aux->attach_btf_id; + st_ops = bpf_struct_ops_find(btf_id); + if (!st_ops) { + verbose(env, "attach_btf_id %u is not a supported struct\n", + btf_id); + return -ENOTSUPP; + } + + t = st_ops->type; + member_idx = prog->expected_attach_type; + if (member_idx >= btf_type_vlen(t)) { + verbose(env, "attach to invalid member idx %u of struct %s\n", + member_idx, st_ops->name); + return -EINVAL; + } + + member = &btf_type_member(t)[member_idx]; + mname = btf_name_by_offset(btf_vmlinux, member->name_off); + func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type, + NULL); + if (!func_proto) { + verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", + mname, member_idx, st_ops->name); + return -EINVAL; + } + + if (st_ops->check_member) { + int err = st_ops->check_member(t, member); + + if (err) { + verbose(env, "attach to unsupported member %s of struct %s\n", + mname, st_ops->name); + return err; + } + } + + prog->aux->attach_func_proto = func_proto; + prog->aux->attach_func_name = mname; + env->ops = st_ops->verifier_ops; + + return 0; +} + +static int check_attach_btf_id(struct bpf_verifier_env *env) +{ + struct bpf_prog *prog = env->prog; + bool prog_extension = prog->type == BPF_PROG_TYPE_EXT; + struct bpf_prog *tgt_prog = prog->aux->linked_prog; + u32 btf_id = prog->aux->attach_btf_id; + const char prefix[] = "btf_trace_"; + int ret = 0, subprog = -1, i; + struct bpf_trampoline *tr; + const struct btf_type *t; + bool conservative = true; + const char *tname; + struct btf *btf; + long addr; + u64 key; + + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) + return check_struct_ops_btf_id(env); + + if (prog->type != BPF_PROG_TYPE_TRACING && !prog_extension) + return 0; + + if (!btf_id) { + verbose(env, "Tracing programs must provide btf_id\n"); + return -EINVAL; + } + btf = bpf_prog_get_target_btf(prog); + if (!btf) { + verbose(env, + "FENTRY/FEXIT program can only be attached to another program annotated with BTF\n"); + return -EINVAL; + } + t = btf_type_by_id(btf, btf_id); + if (!t) { + verbose(env, "attach_btf_id %u is invalid\n", btf_id); + return -EINVAL; + } + tname = btf_name_by_offset(btf, t->name_off); + if (!tname) { + verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id); + return -EINVAL; + } + if (tgt_prog) { + struct bpf_prog_aux *aux = tgt_prog->aux; + + for (i = 0; i < aux->func_info_cnt; i++) + if (aux->func_info[i].type_id == btf_id) { + subprog = i; + break; + } + if (subprog == -1) { + verbose(env, "Subprog %s doesn't exist\n", tname); + return -EINVAL; + } + conservative = aux->func_info_aux[subprog].unreliable; + if (prog_extension) { + if (conservative) { + verbose(env, + "Cannot replace static functions\n"); + return -EINVAL; + } + if (!prog->jit_requested) { + verbose(env, + "Extension programs should be JITed\n"); + return -EINVAL; + } + env->ops = bpf_verifier_ops[tgt_prog->type]; + } + if (!tgt_prog->jited) { + verbose(env, "Can attach to only JITed progs\n"); + return -EINVAL; + } + if (tgt_prog->type == prog->type) { + /* Cannot fentry/fexit another fentry/fexit program. + * Cannot attach program extension to another extension. + * It's ok to attach fentry/fexit to extension program. + */ + verbose(env, "Cannot recursively attach\n"); + return -EINVAL; + } + if (tgt_prog->type == BPF_PROG_TYPE_TRACING && + prog_extension && + (tgt_prog->expected_attach_type == BPF_TRACE_FENTRY || + tgt_prog->expected_attach_type == BPF_TRACE_FEXIT)) { + /* Program extensions can extend all program types + * except fentry/fexit. The reason is the following. + * The fentry/fexit programs are used for performance + * analysis, stats and can be attached to any program + * type except themselves. When extension program is + * replacing XDP function it is necessary to allow + * performance analysis of all functions. Both original + * XDP program and its program extension. Hence + * attaching fentry/fexit to BPF_PROG_TYPE_EXT is + * allowed. If extending of fentry/fexit was allowed it + * would be possible to create long call chain + * fentry->extension->fentry->extension beyond + * reasonable stack size. Hence extending fentry is not + * allowed. + */ + verbose(env, "Cannot extend fentry/fexit\n"); + return -EINVAL; + } + key = ((u64)aux->id) << 32 | btf_id; + } else { + if (prog_extension) { + verbose(env, "Cannot replace kernel functions\n"); + return -EINVAL; + } + key = btf_id; + } + + switch (prog->expected_attach_type) { + case BPF_TRACE_RAW_TP: + if (tgt_prog) { + verbose(env, + "Only FENTRY/FEXIT progs are attachable to another BPF prog\n"); + return -EINVAL; + } + if (!btf_type_is_typedef(t)) { + verbose(env, "attach_btf_id %u is not a typedef\n", + btf_id); + return -EINVAL; + } + if (strncmp(prefix, tname, sizeof(prefix) - 1)) { + verbose(env, "attach_btf_id %u points to wrong type name %s\n", + btf_id, tname); + return -EINVAL; + } + tname += sizeof(prefix) - 1; + t = btf_type_by_id(btf, t->type); + if (!btf_type_is_ptr(t)) + /* should never happen in valid vmlinux build */ + return -EINVAL; + t = btf_type_by_id(btf, t->type); + if (!btf_type_is_func_proto(t)) + /* should never happen in valid vmlinux build */ + return -EINVAL; + + /* remember two read only pointers that are valid for + * the life time of the kernel + */ + prog->aux->attach_func_name = tname; + prog->aux->attach_func_proto = t; + prog->aux->attach_btf_trace = true; + return 0; + default: + if (!prog_extension) + return -EINVAL; + /* fallthrough */ + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + if (!btf_type_is_func(t)) { + verbose(env, "attach_btf_id %u is not a function\n", + btf_id); + return -EINVAL; + } + if (prog_extension && + btf_check_type_match(env, prog, btf, t)) + return -EINVAL; + t = btf_type_by_id(btf, t->type); + if (!btf_type_is_func_proto(t)) + return -EINVAL; + tr = bpf_trampoline_lookup(key); + if (!tr) + return -ENOMEM; + prog->aux->attach_func_name = tname; + /* t is either vmlinux type or another program's type */ + prog->aux->attach_func_proto = t; + mutex_lock(&tr->mutex); + if (tr->func.addr) { + prog->aux->trampoline = tr; + goto out; + } + if (tgt_prog && conservative) { + prog->aux->attach_func_proto = NULL; + t = NULL; + } + ret = btf_distill_func_proto(&env->log, btf, t, + tname, &tr->func.model); + if (ret < 0) + goto out; + if (tgt_prog) { + if (subprog == 0) + addr = (long) tgt_prog->bpf_func; + else + addr = (long) tgt_prog->aux->func[subprog]->bpf_func; + } else { + addr = kallsyms_lookup_name(tname); + if (!addr) { + verbose(env, + "The address of function %s cannot be found\n", + tname); + ret = -ENOENT; + goto out; + } + } + tr->func.addr = (void *)addr; + prog->aux->trampoline = tr; +out: + mutex_unlock(&tr->mutex); + if (ret) + bpf_trampoline_put(tr); + return ret; + } +} + int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -9233,6 +10014,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, env->ops = bpf_verifier_ops[env->prog->type]; is_priv = capable(CAP_SYS_ADMIN); + if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { + mutex_lock(&bpf_verifier_lock); + if (!btf_vmlinux) + btf_vmlinux = btf_parse_vmlinux(); + mutex_unlock(&bpf_verifier_lock); + } + /* grab the mutex to protect few globals used by verifier */ if (!is_priv) mutex_lock(&bpf_verifier_lock); @@ -9252,6 +10040,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, goto err_unlock; } + if (IS_ERR(btf_vmlinux)) { + /* Either gcc or pahole or kernel are broken. */ + verbose(env, "in-kernel BTF is malformed\n"); + ret = PTR_ERR(btf_vmlinux); + goto skip_full_check; + } + env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; @@ -9260,6 +10055,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, env->allow_ptr_leaks = is_priv; + if (is_priv) + env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; + ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; @@ -9285,22 +10083,22 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (ret < 0) goto skip_full_check; + ret = check_attach_btf_id(env); + if (ret) + goto skip_full_check; + ret = check_cfg(env); if (ret < 0) goto skip_full_check; - ret = do_check(env); - if (env->cur_state) { - free_verifier_state(env->cur_state, true); - env->cur_state = NULL; - } + ret = do_check_subprogs(env); + ret = ret ?: do_check_main(env); if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux)) ret = bpf_prog_offload_finalize(env); skip_full_check: - while (!pop_stack(env, NULL, NULL)); - free_states(env); + kvfree(env->explored_states); if (ret == 0) ret = check_max_stack_depth(env); diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index 9bb96ace9fa1..2cc5c8f4c800 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -9,17 +9,72 @@ #include <linux/slab.h> #include <linux/sched.h> -struct xsk_map { - struct bpf_map map; - struct xdp_sock **xsk_map; - struct list_head __percpu *flush_list; -}; +int xsk_map_inc(struct xsk_map *map) +{ + bpf_map_inc(&map->map); + return 0; +} + +void xsk_map_put(struct xsk_map *map) +{ + bpf_map_put(&map->map); +} + +static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map, + struct xdp_sock **map_entry) +{ + struct xsk_map_node *node; + int err; + + node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN); + if (!node) + return ERR_PTR(-ENOMEM); + + err = xsk_map_inc(map); + if (err) { + kfree(node); + return ERR_PTR(err); + } + + node->map = map; + node->map_entry = map_entry; + return node; +} + +static void xsk_map_node_free(struct xsk_map_node *node) +{ + xsk_map_put(node->map); + kfree(node); +} + +static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node) +{ + spin_lock_bh(&xs->map_list_lock); + list_add_tail(&node->node, &xs->map_list); + spin_unlock_bh(&xs->map_list_lock); +} + +static void xsk_map_sock_delete(struct xdp_sock *xs, + struct xdp_sock **map_entry) +{ + struct xsk_map_node *n, *tmp; + + spin_lock_bh(&xs->map_list_lock); + list_for_each_entry_safe(n, tmp, &xs->map_list, node) { + if (map_entry == n->map_entry) { + list_del(&n->node); + xsk_map_node_free(n); + } + } + spin_unlock_bh(&xs->map_list_lock); +} static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) { + struct bpf_map_memory mem; + int err, numa_node; struct xsk_map *m; - int cpu, err; - u64 cost; + u64 size; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); @@ -29,66 +84,33 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)) return ERR_PTR(-EINVAL); - m = kzalloc(sizeof(*m), GFP_USER); - if (!m) - return ERR_PTR(-ENOMEM); + numa_node = bpf_map_attr_numa_node(attr); + size = struct_size(m, xsk_map, attr->max_entries); - bpf_map_init_from_attr(&m->map, attr); - - cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *); - cost += sizeof(struct list_head) * num_possible_cpus(); - - /* Notice returns -EPERM on if map size is larger than memlock limit */ - err = bpf_map_charge_init(&m->map.memory, cost); - if (err) - goto free_m; - - err = -ENOMEM; + err = bpf_map_charge_init(&mem, size); + if (err < 0) + return ERR_PTR(err); - m->flush_list = alloc_percpu(struct list_head); - if (!m->flush_list) - goto free_charge; + m = bpf_map_area_alloc(size, numa_node); + if (!m) { + bpf_map_charge_finish(&mem); + return ERR_PTR(-ENOMEM); + } - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu)); + bpf_map_init_from_attr(&m->map, attr); + bpf_map_charge_move(&m->map.memory, &mem); + spin_lock_init(&m->lock); - m->xsk_map = bpf_map_area_alloc(m->map.max_entries * - sizeof(struct xdp_sock *), - m->map.numa_node); - if (!m->xsk_map) - goto free_percpu; return &m->map; - -free_percpu: - free_percpu(m->flush_list); -free_charge: - bpf_map_charge_finish(&m->map.memory); -free_m: - kfree(m); - return ERR_PTR(err); } static void xsk_map_free(struct bpf_map *map) { struct xsk_map *m = container_of(map, struct xsk_map, map); - int i; bpf_clear_redirect_map(map); synchronize_net(); - - for (i = 0; i < map->max_entries; i++) { - struct xdp_sock *xs; - - xs = m->xsk_map[i]; - if (!xs) - continue; - - sock_put((struct sock *)xs); - } - - free_percpu(m->flush_list); - bpf_map_area_free(m->xsk_map); - kfree(m); + bpf_map_area_free(m); } static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key) @@ -108,45 +130,20 @@ static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) -{ - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *xs; - - if (key >= map->max_entries) - return NULL; - - xs = READ_ONCE(m->xsk_map[key]); - return xs; -} - -int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, - struct xdp_sock *xs) -{ - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct list_head *flush_list = this_cpu_ptr(m->flush_list); - int err; - - err = xsk_rcv(xs, xdp); - if (err) - return err; - - if (!xs->flush_node.prev) - list_add(&xs->flush_node, flush_list); - - return 0; -} - -void __xsk_map_flush(struct bpf_map *map) +static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct list_head *flush_list = this_cpu_ptr(m->flush_list); - struct xdp_sock *xs, *tmp; - - list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { - xsk_flush(xs); - __list_del_clearprev(&xs->flush_node); - } + const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2; + struct bpf_insn *insn = insn_buf; + + *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5); + *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(sizeof(struct xsk_sock *))); + *insn++ = BPF_ALU64_IMM(BPF_ADD, mp, offsetof(struct xsk_map, xsk_map)); + *insn++ = BPF_ALU64_REG(BPF_ADD, ret, mp); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(struct xsk_sock *), ret, ret, 0); + *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *insn++ = BPF_MOV64_IMM(ret, 0); + return insn - insn_buf; } static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) @@ -164,8 +161,9 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct xsk_map *m = container_of(map, struct xsk_map, map); + struct xdp_sock *xs, *old_xs, **map_entry; u32 i = *(u32 *)key, fd = *(u32 *)value; - struct xdp_sock *xs, *old_xs; + struct xsk_map_node *node; struct socket *sock; int err; @@ -173,8 +171,6 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, return -EINVAL; if (unlikely(i >= m->map.max_entries)) return -E2BIG; - if (unlikely(map_flags == BPF_NOEXIST)) - return -EEXIST; sock = sockfd_lookup(fd, &err); if (!sock) @@ -192,37 +188,76 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, return -EOPNOTSUPP; } - sock_hold(sock->sk); + map_entry = &m->xsk_map[i]; + node = xsk_map_node_alloc(m, map_entry); + if (IS_ERR(node)) { + sockfd_put(sock); + return PTR_ERR(node); + } - old_xs = xchg(&m->xsk_map[i], xs); + spin_lock_bh(&m->lock); + old_xs = READ_ONCE(*map_entry); + if (old_xs == xs) { + err = 0; + goto out; + } else if (old_xs && map_flags == BPF_NOEXIST) { + err = -EEXIST; + goto out; + } else if (!old_xs && map_flags == BPF_EXIST) { + err = -ENOENT; + goto out; + } + xsk_map_sock_add(xs, node); + WRITE_ONCE(*map_entry, xs); if (old_xs) - sock_put((struct sock *)old_xs); - + xsk_map_sock_delete(old_xs, map_entry); + spin_unlock_bh(&m->lock); sockfd_put(sock); return 0; + +out: + spin_unlock_bh(&m->lock); + sockfd_put(sock); + xsk_map_node_free(node); + return err; } static int xsk_map_delete_elem(struct bpf_map *map, void *key) { struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *old_xs; + struct xdp_sock *old_xs, **map_entry; int k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; - old_xs = xchg(&m->xsk_map[k], NULL); + spin_lock_bh(&m->lock); + map_entry = &m->xsk_map[k]; + old_xs = xchg(map_entry, NULL); if (old_xs) - sock_put((struct sock *)old_xs); + xsk_map_sock_delete(old_xs, map_entry); + spin_unlock_bh(&m->lock); return 0; } +void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, + struct xdp_sock **map_entry) +{ + spin_lock_bh(&map->lock); + if (READ_ONCE(*map_entry) == xs) { + WRITE_ONCE(*map_entry, NULL); + xsk_map_sock_delete(xs, map_entry); + } + spin_unlock_bh(&map->lock); +} + const struct bpf_map_ops xsk_map_ops = { .map_alloc = xsk_map_alloc, .map_free = xsk_map_free, .map_get_next_key = xsk_map_get_next_key, .map_lookup_elem = xsk_map_lookup_elem, + .map_gen_lookup = xsk_map_gen_lookup, .map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only, .map_update_elem = xsk_map_update_elem, .map_delete_elem = xsk_map_delete_elem, |