// SPDX-License-Identifier: GPL-2.0-only/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */#include <linux/bpf.h>#include <linux/bpf_trace.h>#include <linux/bpf_lirc.h>#include <linux/btf.h>#include <linux/syscalls.h>#include <linux/slab.h>#include <linux/sched/signal.h>#include <linux/vmalloc.h>#include <linux/mmzone.h>#include <linux/anon_inodes.h>#include <linux/fdtable.h>#include <linux/file.h>#include <linux/fs.h>#include <linux/license.h>#include <linux/filter.h>#include <linux/version.h>#include <linux/kernel.h>#include <linux/idr.h>#include <linux/cred.h>#include <linux/timekeeping.h>#include <linux/ctype.h>#include <linux/nospec.h>#include <linux/audit.h>#include <uapi/linux/btf.h>#include <linux/pgtable.h>#include <linux/bpf_lsm.h>#include <linux/poll.h>#include <linux/bpf-netns.h> #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_PROG_ARRAY(map) || \ IS_FD_HASH(map)) #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) DEFINE_PER_CPU(int, bpf_prog_active);static DEFINE_IDR(prog_idr);static DEFINE_SPINLOCK(prog_idr_lock);static DEFINE_IDR(map_idr);static DEFINE_SPINLOCK(map_idr_lock);static DEFINE_IDR(link_idr);static DEFINE_SPINLOCK(link_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly; static const struct bpf_map_ops * const bpf_map_types[] = {#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)#define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops,#define BPF_LINK_TYPE(_id, _name)#include <linux/bpf_types.h>#undef BPF_PROG_TYPE#undef BPF_MAP_TYPE#undef BPF_LINK_TYPE}; /* * If we're handed a bigger struct than we know of, ensure all the unknown bits * are 0 - i.e. new user-space does not rely on any kernel feature extensions * we don't know about yet. * * There is a ToCToU between this function call and the following * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size, size_t actual_size){ unsigned char __user *addr = uaddr + expected_size; int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; if (actual_size <= expected_size) return 0; res = check_zeroed_user(addr, actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG;} const struct bpf_map_ops bpf_map_offload_ops = { .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf,}; static struct bpf_map *find_and_alloc_map(union bpf_attr *attr){ const struct bpf_map_ops *ops; u32 type = attr->map_type; struct bpf_map *map; int err; if (type >= ARRAY_SIZE(bpf_map_types)) return ERR_PTR(-EINVAL); type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types)); ops = bpf_map_types[type]; if (!ops) return ERR_PTR(-EINVAL); if (ops->map_alloc_check) { err = ops->map_alloc_check(attr); if (err) return ERR_PTR(err); } if (attr->map_ifindex) ops = &bpf_map_offload_ops; map = ops->map_alloc(attr); if (IS_ERR(map)) return map; map->ops = ops; map->map_type = type; return map;} 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); } bpf_disable_instrumentation(); 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(); } bpf_enable_instrumentation(); 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); bpf_disable_instrumentation(); 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(); } bpf_enable_instrumentation(); 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, * which is used for lower order allocation requests. * * It has been observed that higher order allocation requests done by * vmalloc with __GFP_NORETRY being set might fail due to not trying * to reclaim memory from the page cache, thus we set * __GFP_RETRY_MAYFAIL to avoid such situations. */ const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO; unsigned int flags = 0; unsigned long align = 1; void *area; if (size >= SIZE_MAX) return NULL; /* kmalloc()'ed memory can't be mmap()'ed */ if (mmapable) { BUG_ON(!PAGE_ALIGNED(size)); align = SHMLBA; flags = VM_USERMAP; } else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY, numa_node); if (area != NULL) return area; } return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL, flags, numa_node, __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);} static u32 bpf_map_flags_retain_permanent(u32 flags){ /* Some map creation flags are not tied to the map object but * rather to the map fd instead, so they have no meaning upon * map object inspection since multiple file descriptors with * different (access) properties can exist here. Thus, given * this has zero meaning for the map itself, lets clear these * from here. */ return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY);} void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr){ map->map_type = attr->map_type; map->key_size = attr->key_size; map->value_size = attr->value_size; map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr);} static int bpf_charge_memlock(struct user_struct *user, u32 pages){ unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) { atomic_long_sub(pages, &user->locked_vm); return -EPERM; } return 0;} static void bpf_uncharge_memlock(struct user_struct *user, u32 pages){ if (user) atomic_long_sub(pages, &user->locked_vm);} 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; int ret; if (size >= U32_MAX - PAGE_SIZE) return -E2BIG; user = get_current_user(); ret = bpf_charge_memlock(user, pages); if (ret) { free_uid(user); return ret; } mem->pages = pages; mem->user = user; return 0;} void bpf_map_charge_finish(struct bpf_map_memory *mem){ bpf_uncharge_memlock(mem->user, mem->pages); free_uid(mem->user);} void bpf_map_charge_move(struct bpf_map_memory *dst, struct bpf_map_memory *src){ *dst = *src; /* Make sure src will not be used for the redundant uncharging. */ memset(src, 0, sizeof(struct bpf_map_memory));} int bpf_map_charge_memlock(struct bpf_map *map, u32 pages){ int ret; ret = bpf_charge_memlock(map->memory.user, pages); if (ret) return ret; map->memory.pages += pages; return ret;} void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages){ bpf_uncharge_memlock(map->memory.user, pages); map->memory.pages -= pages;} static int bpf_map_alloc_id(struct bpf_map *map){ int id; idr_preload(GFP_KERNEL); spin_lock_bh(&map_idr_lock); id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); if (id > 0) map->id = id; spin_unlock_bh(&map_idr_lock); idr_preload_end(); if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id;} void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock){ unsigned long flags; /* Offloaded maps are removed from the IDR store when their device * disappears - even if someone holds an fd to them they are unusable, * the memory is gone, all ops will fail; they are simply waiting for * refcnt to drop to be freed. */ if (!map->id) return; if (do_idr_lock) spin_lock_irqsave(&map_idr_lock, flags); else __acquire(&map_idr_lock); idr_remove(&map_idr, map->id); map->id = 0; if (do_idr_lock) spin_unlock_irqrestore(&map_idr_lock, flags); else __release(&map_idr_lock);} /* called from workqueue */static void bpf_map_free_deferred(struct work_struct *work){ struct bpf_map *map = container_of(work, struct bpf_map, work); struct bpf_map_memory mem; bpf_map_charge_move(&mem, &map->memory); security_bpf_map_free(map); /* implementation dependent freeing */ map->ops->map_free(map); bpf_map_charge_finish(&mem);} static void bpf_map_put_uref(struct bpf_map *map){ if (atomic64_dec_and_test(&map->usercnt)) { if (map->ops->map_release_uref) map->ops->map_release_uref(map); }} /* decrement map refcnt and schedule it for freeing via workqueue * (unrelying map implementation ops->map_free() might sleep) */static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock){ 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); INIT_WORK(&map->work, bpf_map_free_deferred); schedule_work(&map->work); }} void bpf_map_put(struct bpf_map *map){ __bpf_map_put(map, true);}EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map){ bpf_map_put_uref(map); bpf_map_put(map);}Lines 1–500 of 4275. Load more
// SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> #include <linux/btf.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/vmalloc.h> #include <linux/mmzone.h> #include <linux/anon_inodes.h> #include <linux/fdtable.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> #include <linux/version.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> #include <linux/nospec.h> #include <linux/audit.h> #include <uapi/linux/btf.h> #include <linux/pgtable.h> #include <linux/bpf_lsm.h> #include <linux/poll.h> #include <linux/bpf-netns.h> #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_PROG_ARRAY(map) || \ IS_FD_HASH(map)) #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) DEFINE_PER_CPU(int, bpf_prog_active); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops, #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; /* * If we're handed a bigger struct than we know of, ensure all the unknown bits * are 0 - i.e. new user-space does not rely on any kernel feature extensions * we don't know about yet. * * There is a ToCToU between this function call and the following * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size, size_t actual_size) { unsigned char __user *addr = uaddr + expected_size; int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; if (actual_size <= expected_size) return 0; res = check_zeroed_user(addr, actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG; } const struct bpf_map_ops bpf_map_offload_ops = { .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, }; static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) { const struct bpf_map_ops *ops; u32 type = attr->map_type; struct bpf_map *map; int err; if (type >= ARRAY_SIZE(bpf_map_types)) return ERR_PTR(-EINVAL); type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types)); ops = bpf_map_types[type]; if (!ops) return ERR_PTR(-EINVAL); if (ops->map_alloc_check) { err = ops->map_alloc_check(attr); if (err) return ERR_PTR(err); } if (attr->map_ifindex) ops = &bpf_map_offload_ops; map = ops->map_alloc(attr); if (IS_ERR(map)) return map; map->ops = ops; map->map_type = type; return map; } 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); } bpf_disable_instrumentation(); 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(); } bpf_enable_instrumentation(); 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); bpf_disable_instrumentation(); 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(); } bpf_enable_instrumentation(); 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, * which is used for lower order allocation requests. * * It has been observed that higher order allocation requests done by * vmalloc with __GFP_NORETRY being set might fail due to not trying * to reclaim memory from the page cache, thus we set * __GFP_RETRY_MAYFAIL to avoid such situations. */ const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO; unsigned int flags = 0; unsigned long align = 1; void *area; if (size >= SIZE_MAX) return NULL; /* kmalloc()'ed memory can't be mmap()'ed */ if (mmapable) { BUG_ON(!PAGE_ALIGNED(size)); align = SHMLBA; flags = VM_USERMAP; } else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY, numa_node); if (area != NULL) return area; } return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL, flags, numa_node, __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); } static u32 bpf_map_flags_retain_permanent(u32 flags) { /* Some map creation flags are not tied to the map object but * rather to the map fd instead, so they have no meaning upon * map object inspection since multiple file descriptors with * different (access) properties can exist here. Thus, given * this has zero meaning for the map itself, lets clear these * from here. */ return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY); } void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) { map->map_type = attr->map_type; map->key_size = attr->key_size; map->value_size = attr->value_size; map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); } static int bpf_charge_memlock(struct user_struct *user, u32 pages) { unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) { atomic_long_sub(pages, &user->locked_vm); return -EPERM; } return 0; } static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) { if (user) atomic_long_sub(pages, &user->locked_vm); } 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; int ret; if (size >= U32_MAX - PAGE_SIZE) return -E2BIG; user = get_current_user(); ret = bpf_charge_memlock(user, pages); if (ret) { free_uid(user); return ret; } mem->pages = pages; mem->user = user; return 0; } void bpf_map_charge_finish(struct bpf_map_memory *mem) { bpf_uncharge_memlock(mem->user, mem->pages); free_uid(mem->user); } void bpf_map_charge_move(struct bpf_map_memory *dst, struct bpf_map_memory *src) { *dst = *src; /* Make sure src will not be used for the redundant uncharging. */ memset(src, 0, sizeof(struct bpf_map_memory)); } int bpf_map_charge_memlock(struct bpf_map *map, u32 pages) { int ret; ret = bpf_charge_memlock(map->memory.user, pages); if (ret) return ret; map->memory.pages += pages; return ret; } void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages) { bpf_uncharge_memlock(map->memory.user, pages); map->memory.pages -= pages; } static int bpf_map_alloc_id(struct bpf_map *map) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&map_idr_lock); id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); if (id > 0) map->id = id; spin_unlock_bh(&map_idr_lock); idr_preload_end(); if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) { unsigned long flags; /* Offloaded maps are removed from the IDR store when their device * disappears - even if someone holds an fd to them they are unusable, * the memory is gone, all ops will fail; they are simply waiting for * refcnt to drop to be freed. */ if (!map->id) return; if (do_idr_lock) spin_lock_irqsave(&map_idr_lock, flags); else __acquire(&map_idr_lock); idr_remove(&map_idr, map->id); map->id = 0; if (do_idr_lock) spin_unlock_irqrestore(&map_idr_lock, flags); else __release(&map_idr_lock); } /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); struct bpf_map_memory mem; bpf_map_charge_move(&mem, &map->memory); security_bpf_map_free(map); /* implementation dependent freeing */ map->ops->map_free(map); bpf_map_charge_finish(&mem); } static void bpf_map_put_uref(struct bpf_map *map) { if (atomic64_dec_and_test(&map->usercnt)) { if (map->ops->map_release_uref) map->ops->map_release_uref(map); } } /* decrement map refcnt and schedule it for freeing via workqueue * (unrelying map implementation ops->map_free() might sleep) */ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) { 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); INIT_WORK(&map->work, bpf_map_free_deferred); schedule_work(&map->work); } } void bpf_map_put(struct bpf_map *map) { __bpf_map_put(map, true); } EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) { bpf_map_put_uref(map); bpf_map_put(map); }