// SPDX-License-Identifier: GPL-2.0-only/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */#include <linux/bpf.h>#include <linux/bpf-cgroup.h>#include <linux/bpf_trace.h>#include <linux/bpf_lirc.h>#include <linux/bpf_verifier.h>#include <linux/bsearch.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/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/sort.h>#include <linux/bpf-netns.h>#include <linux/rcupdate_trace.h>#include <linux/memcontrol.h>#include <linux/trace_events.h> #include <net/netfilter/nf_bpf_link.h>#include <net/netkit.h>#include <net/tcx.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 = IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; 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(bpfptr_t uaddr, size_t expected_size, size_t actual_size){ int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; if (actual_size <= expected_size) return 0; if (uaddr.is_kernel) res = memchr_inv(uaddr.kernel + expected_size, 0, actual_size - expected_size) == NULL; else res = check_zeroed_user(uaddr.user + expected_size, actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG;} const struct bpf_map_ops bpf_map_offload_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, .map_mem_usage = bpf_map_offload_map_mem_usage,}; static void bpf_map_write_active_inc(struct bpf_map *map){ atomic64_inc(&map->writecnt);} static void bpf_map_write_active_dec(struct bpf_map *map){ atomic64_dec(&map->writecnt);} bool bpf_map_write_active(const struct bpf_map *map){ return atomic64_read(&map->writecnt) != 0;} static u32 bpf_map_value_size(const 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 non-sleepable BPF programs to complete so that * userspace, when we return to it, knows that all non-sleepable * programs that could be running use the new map value. For sleepable * BPF programs, synchronize_rcu_tasks_trace() should be used to wait * for the completions of these programs, but considering the waiting * time can be very long and userspace may think it will hang forever, * so don't handle sleepable BPF programs now. */ 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 file *map_file, void *key, void *value, __u64 flags){ int err; /* Need to create a kthread, thus must support schedule */ if (bpf_map_is_offloaded(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_ARENA || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || map->map_type == BPF_MAP_TYPE_SOCKMAP) { return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { return bpf_fd_array_map_update_elem(map, map_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)) { err = bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { err = bpf_fd_htab_map_update_elem(map, map_file, key, value, flags); } 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 || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { 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(); 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_offloaded(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 || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { 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 and timer, since value wasn't zero inited */ check_and_init_map_value(map, value); } rcu_read_unlock(); } bpf_enable_instrumentation(); return err;} /* Please, do not use this function outside from the map creation path * (e.g. in map update path) without taking care of setting the active * memory cgroup (see at bpf_map_kmalloc_node() for example). */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. */ gfp_t gfp = bpf_memcg_flags(__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); map->map_extra = attr->map_extra;} 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){ 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; spin_lock_irqsave(&map_idr_lock, flags); idr_remove(&map_idr, map->id); map->id = 0; spin_unlock_irqrestore(&map_idr_lock, flags);} #ifdef CONFIG_MEMCGstatic void bpf_map_save_memcg(struct bpf_map *map){ /* Currently if a map is created by a process belonging to the root * memory cgroup, get_obj_cgroup_from_current() will return NULL. * So we have to check map->objcg for being NULL each time it's * being used. */ if (memcg_bpf_enabled()) map->objcg = get_obj_cgroup_from_current();} static void bpf_map_release_memcg(struct bpf_map *map){ if (map->objcg) obj_cgroup_put(map->objcg);} static struct mem_cgroup *bpf_map_get_memcg(const struct bpf_map *map){ if (map->objcg) return get_mem_cgroup_from_objcg(map->objcg); return root_mem_cgroup;} void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node){ struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr;} void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags){ struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kzalloc(size, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr;} void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags){ struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kvcalloc(n, size, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr;} void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags){ struct mem_cgroup *memcg, *old_memcg; void __percpu *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr;} #elsestatic void bpf_map_save_memcg(struct bpf_map *map){} static void bpf_map_release_memcg(struct bpf_map *map){}#endif int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, unsigned long nr_pages, struct page **pages){ unsigned long i, j; struct page *pg; int ret = 0;#ifdef CONFIG_MEMCG struct mem_cgroup *memcg, *old_memcg; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg);#endif for (i = 0; i < nr_pages; i++) { pg = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0); if (pg) { pages[i] = pg; continue;Lines 1–500 of 6069. Load more
// SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> #include <linux/bpf-cgroup.h> #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> #include <linux/bpf_verifier.h> #include <linux/bsearch.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/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/sort.h> #include <linux/bpf-netns.h> #include <linux/rcupdate_trace.h> #include <linux/memcontrol.h> #include <linux/trace_events.h> #include <net/netfilter/nf_bpf_link.h> #include <net/netkit.h> #include <net/tcx.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 = IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; 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(bpfptr_t uaddr, size_t expected_size, size_t actual_size) { int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; if (actual_size <= expected_size) return 0; if (uaddr.is_kernel) res = memchr_inv(uaddr.kernel + expected_size, 0, actual_size - expected_size) == NULL; else res = check_zeroed_user(uaddr.user + expected_size, actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG; } const struct bpf_map_ops bpf_map_offload_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, .map_mem_usage = bpf_map_offload_map_mem_usage, }; static void bpf_map_write_active_inc(struct bpf_map *map) { atomic64_inc(&map->writecnt); } static void bpf_map_write_active_dec(struct bpf_map *map) { atomic64_dec(&map->writecnt); } bool bpf_map_write_active(const struct bpf_map *map) { return atomic64_read(&map->writecnt) != 0; } static u32 bpf_map_value_size(const 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 non-sleepable BPF programs to complete so that * userspace, when we return to it, knows that all non-sleepable * programs that could be running use the new map value. For sleepable * BPF programs, synchronize_rcu_tasks_trace() should be used to wait * for the completions of these programs, but considering the waiting * time can be very long and userspace may think it will hang forever, * so don't handle sleepable BPF programs now. */ 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 file *map_file, void *key, void *value, __u64 flags) { int err; /* Need to create a kthread, thus must support schedule */ if (bpf_map_is_offloaded(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_ARENA || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || map->map_type == BPF_MAP_TYPE_SOCKMAP) { return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { return bpf_fd_array_map_update_elem(map, map_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)) { err = bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { err = bpf_fd_htab_map_update_elem(map, map_file, key, value, flags); } 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 || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { 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(); 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_offloaded(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 || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { 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 and timer, since value wasn't zero inited */ check_and_init_map_value(map, value); } rcu_read_unlock(); } bpf_enable_instrumentation(); return err; } /* Please, do not use this function outside from the map creation path * (e.g. in map update path) without taking care of setting the active * memory cgroup (see at bpf_map_kmalloc_node() for example). */ 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. */ gfp_t gfp = bpf_memcg_flags(__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); map->map_extra = attr->map_extra; } 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) { 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; spin_lock_irqsave(&map_idr_lock, flags); idr_remove(&map_idr, map->id); map->id = 0; spin_unlock_irqrestore(&map_idr_lock, flags); } #ifdef CONFIG_MEMCG static void bpf_map_save_memcg(struct bpf_map *map) { /* Currently if a map is created by a process belonging to the root * memory cgroup, get_obj_cgroup_from_current() will return NULL. * So we have to check map->objcg for being NULL each time it's * being used. */ if (memcg_bpf_enabled()) map->objcg = get_obj_cgroup_from_current(); } static void bpf_map_release_memcg(struct bpf_map *map) { if (map->objcg) obj_cgroup_put(map->objcg); } static struct mem_cgroup *bpf_map_get_memcg(const struct bpf_map *map) { if (map->objcg) return get_mem_cgroup_from_objcg(map->objcg); return root_mem_cgroup; } void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node) { struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kzalloc(size, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kvcalloc(n, size, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void __percpu *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } #else static void bpf_map_save_memcg(struct bpf_map *map) { } static void bpf_map_release_memcg(struct bpf_map *map) { } #endif int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, unsigned long nr_pages, struct page **pages) { unsigned long i, j; struct page *pg; int ret = 0; #ifdef CONFIG_MEMCG struct mem_cgroup *memcg, *old_memcg; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); #endif for (i = 0; i < nr_pages; i++) { pg = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0); if (pg) { pages[i] = pg; continue;