struct bpf_local_storage {
struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE];
struct hlist_head list; /* List of bpf_local_storage_elem */
- struct sock *owner; /* The object that owns the above "list" of
+ void *owner; /* The object that owns the above "list" of
* bpf_local_storage_elem.
*/
struct rcu_head rcu;
return -ENOMEM;
}
+static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size)
+{
+ struct bpf_map *map = &smap->map;
+
+ if (!map->ops->map_local_storage_charge)
+ return 0;
+
+ return map->ops->map_local_storage_charge(smap, owner, size);
+}
+
+static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner,
+ u32 size)
+{
+ struct bpf_map *map = &smap->map;
+
+ if (map->ops->map_local_storage_uncharge)
+ map->ops->map_local_storage_uncharge(smap, owner, size);
+}
+
+static struct bpf_local_storage __rcu **
+owner_storage(struct bpf_local_storage_map *smap, void *owner)
+{
+ struct bpf_map *map = &smap->map;
+
+ return map->ops->map_owner_storage_ptr(owner);
+}
+
static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem)
{
return !hlist_unhashed(&selem->snode);
return !hlist_unhashed(&selem->map_node);
}
-static struct bpf_local_storage_elem *
-bpf_selem_alloc(struct bpf_local_storage_map *smap, struct sock *sk,
- void *value, bool charge_omem)
+struct bpf_local_storage_elem *
+bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
+ void *value, bool charge_mem)
{
struct bpf_local_storage_elem *selem;
- if (charge_omem && omem_charge(sk, smap->elem_size))
+ if (charge_mem && mem_charge(smap, owner, smap->elem_size))
return NULL;
selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
return selem;
}
- if (charge_omem)
- atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
+ if (charge_mem)
+ mem_uncharge(smap, owner, smap->elem_size);
return NULL;
}
* The caller must ensure selem->smap is still valid to be
* dereferenced for its smap->elem_size and smap->cache_idx.
*/
-static bool
-bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
- struct bpf_local_storage_elem *selem,
- bool uncharge_omem)
+bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_elem *selem,
+ bool uncharge_mem)
{
struct bpf_local_storage_map *smap;
bool free_local_storage;
- struct sock *sk;
+ void *owner;
smap = rcu_dereference(SDATA(selem)->smap);
- sk = local_storage->owner;
+ owner = local_storage->owner;
/* All uncharging on the owner must be done first.
* The owner may be freed once the last selem is unlinked
* from local_storage.
*/
- if (uncharge_omem)
- atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
+ if (uncharge_mem)
+ mem_uncharge(smap, owner, smap->elem_size);
free_local_storage = hlist_is_singular_node(&selem->snode,
&local_storage->list);
if (free_local_storage) {
- atomic_sub(sizeof(struct bpf_local_storage), &sk->sk_omem_alloc);
+ mem_uncharge(smap, owner, sizeof(struct bpf_local_storage));
local_storage->owner = NULL;
- /* After this RCU_INIT, sk may be freed and cannot be used */
- RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);
+
+ /* After this RCU_INIT, owner may be freed and cannot be used */
+ RCU_INIT_POINTER(*owner_storage(smap, owner), NULL);
/* local_storage is not freed now. local_storage->lock is
* still held and raw_spin_unlock_bh(&local_storage->lock)
local_storage = rcu_dereference(selem->local_storage);
raw_spin_lock_bh(&local_storage->lock);
if (likely(selem_linked_to_storage(selem)))
- free_local_storage =
- bpf_selem_unlink_storage_nolock(local_storage, selem, true);
+ free_local_storage = bpf_selem_unlink_storage_nolock(
+ local_storage, selem, true);
raw_spin_unlock_bh(&local_storage->lock);
if (free_local_storage)
kfree_rcu(local_storage, rcu);
}
-static void
-bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
- struct bpf_local_storage_elem *selem)
+void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_elem *selem)
{
RCU_INIT_POINTER(selem->local_storage, local_storage);
hlist_add_head(&selem->snode, &local_storage->list);
}
-static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
+void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
{
struct bpf_local_storage_map *smap;
struct bpf_local_storage_map_bucket *b;
raw_spin_unlock_bh(&b->lock);
}
-static void bpf_selem_link_map(struct bpf_local_storage_map *smap,
- struct bpf_local_storage_elem *selem)
+void bpf_selem_link_map(struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *selem)
{
struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem);
raw_spin_unlock_bh(&b->lock);
}
-static void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
+void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
{
/* Always unlink from map before unlinking from local_storage
* because selem will be freed after successfully unlinked from
__bpf_selem_unlink_storage(selem);
}
-static struct bpf_local_storage_data *
+struct bpf_local_storage_data *
bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
struct bpf_local_storage_map *smap,
bool cacheit_lockit)
return 0;
}
-static int sk_storage_alloc(struct sock *sk,
+int bpf_local_storage_alloc(void *owner,
struct bpf_local_storage_map *smap,
struct bpf_local_storage_elem *first_selem)
{
- struct bpf_local_storage *prev_sk_storage, *sk_storage;
+ struct bpf_local_storage *prev_storage, *storage;
+ struct bpf_local_storage **owner_storage_ptr;
int err;
- err = omem_charge(sk, sizeof(*sk_storage));
+ err = mem_charge(smap, owner, sizeof(*storage));
if (err)
return err;
- sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN);
- if (!sk_storage) {
+ storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN);
+ if (!storage) {
err = -ENOMEM;
goto uncharge;
}
- INIT_HLIST_HEAD(&sk_storage->list);
- raw_spin_lock_init(&sk_storage->lock);
- sk_storage->owner = sk;
- bpf_selem_link_storage_nolock(sk_storage, first_selem);
+ INIT_HLIST_HEAD(&storage->list);
+ raw_spin_lock_init(&storage->lock);
+ storage->owner = owner;
+
+ bpf_selem_link_storage_nolock(storage, first_selem);
bpf_selem_link_map(smap, first_selem);
- /* Publish sk_storage to sk. sk->sk_lock cannot be acquired.
- * Hence, atomic ops is used to set sk->sk_bpf_storage
- * from NULL to the newly allocated sk_storage ptr.
+
+ owner_storage_ptr =
+ (struct bpf_local_storage **)owner_storage(smap, owner);
+ /* Publish storage to the owner.
+ * Instead of using any lock of the kernel object (i.e. owner),
+ * cmpxchg will work with any kernel object regardless what
+ * the running context is, bh, irq...etc.
*
- * From now on, the sk->sk_bpf_storage pointer is protected
- * by the sk_storage->lock. Hence, when freeing
- * the sk->sk_bpf_storage, the sk_storage->lock must
- * be held before setting sk->sk_bpf_storage to NULL.
+ * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage)
+ * is protected by the storage->lock. Hence, when freeing
+ * the owner->storage, the storage->lock must be held before
+ * setting owner->storage ptr to NULL.
*/
- prev_sk_storage = cmpxchg((struct bpf_local_storage **)&sk->sk_bpf_storage,
- NULL, sk_storage);
- if (unlikely(prev_sk_storage)) {
+ prev_storage = cmpxchg(owner_storage_ptr, NULL, storage);
+ if (unlikely(prev_storage)) {
bpf_selem_unlink_map(first_selem);
err = -EAGAIN;
goto uncharge;
return 0;
uncharge:
- kfree(sk_storage);
- atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc);
+ kfree(storage);
+ mem_uncharge(smap, owner, sizeof(*storage));
return err;
}
* Otherwise, it will become a leak (and other memory issues
* during map destruction).
*/
-static struct bpf_local_storage_data *
-bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value,
- u64 map_flags)
+struct bpf_local_storage_data *
+bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
+ void *value, u64 map_flags)
{
struct bpf_local_storage_data *old_sdata = NULL;
struct bpf_local_storage_elem *selem;
struct bpf_local_storage *local_storage;
- struct bpf_local_storage_map *smap;
int err;
/* BPF_EXIST and BPF_NOEXIST cannot be both set */
if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
/* BPF_F_LOCK can only be used in a value with spin_lock */
- unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
+ unlikely((map_flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(&smap->map)))
return ERR_PTR(-EINVAL);
- smap = (struct bpf_local_storage_map *)map;
- local_storage = rcu_dereference(sk->sk_bpf_storage);
+ local_storage = rcu_dereference(*owner_storage(smap, owner));
if (!local_storage || hlist_empty(&local_storage->list)) {
/* Very first elem for the owner */
err = check_flags(NULL, map_flags);
if (err)
return ERR_PTR(err);
- selem = bpf_selem_alloc(smap, sk, value, true);
+ selem = bpf_selem_alloc(smap, owner, value, true);
if (!selem)
return ERR_PTR(-ENOMEM);
- err = sk_storage_alloc(sk, smap, selem);
+ err = bpf_local_storage_alloc(owner, smap, selem);
if (err) {
kfree(selem);
- atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
+ mem_uncharge(smap, owner, smap->elem_size);
return ERR_PTR(err);
}
if (err)
return ERR_PTR(err);
if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) {
- copy_map_value_locked(map, old_sdata->data,
+ copy_map_value_locked(&smap->map, old_sdata->data,
value, false);
return old_sdata;
}
goto unlock_err;
if (old_sdata && (map_flags & BPF_F_LOCK)) {
- copy_map_value_locked(map, old_sdata->data, value, false);
+ copy_map_value_locked(&smap->map, old_sdata->data, value,
+ false);
selem = SELEM(old_sdata);
goto unlock;
}
* old_sdata will not be uncharged later during
* bpf_selem_unlink_storage_nolock().
*/
- selem = bpf_selem_alloc(smap, sk, value, !old_sdata);
+ selem = bpf_selem_alloc(smap, owner, value, !old_sdata);
if (!selem) {
err = -ENOMEM;
goto unlock_err;
kfree_rcu(sk_storage, rcu);
}
-static void bpf_local_storage_map_free(struct bpf_map *map)
+void bpf_local_storage_map_free(struct bpf_local_storage_map *smap)
{
struct bpf_local_storage_elem *selem;
- struct bpf_local_storage_map *smap;
struct bpf_local_storage_map_bucket *b;
unsigned int i;
- smap = (struct bpf_local_storage_map *)map;
-
- bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx);
-
/* Note that this map might be concurrently cloned from
* bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
* RCU read section to finish before proceeding. New RCU
synchronize_rcu();
kvfree(smap->buckets);
- kfree(map);
+ kfree(smap);
+}
+
+static void sk_storage_map_free(struct bpf_map *map)
+{
+ struct bpf_local_storage_map *smap;
+
+ smap = (struct bpf_local_storage_map *)map;
+ bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx);
+ bpf_local_storage_map_free(smap);
}
/* U16_MAX is much more than enough for sk local storage
sizeof(struct bpf_local_storage_elem)), \
(U16_MAX - sizeof(struct bpf_local_storage_elem)))
-static int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
+int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
{
if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK ||
!(attr->map_flags & BPF_F_NO_PREALLOC) ||
return 0;
}
-static struct bpf_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
+struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
{
struct bpf_local_storage_map *smap;
unsigned int i;
smap->elem_size =
sizeof(struct bpf_local_storage_elem) + attr->value_size;
- smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache);
+ return smap;
+}
+
+static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_local_storage_map *smap;
+
+ smap = bpf_local_storage_map_alloc(attr);
+ if (IS_ERR(smap))
+ return ERR_CAST(smap);
+
+ smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache);
return &smap->map;
}
return -ENOTSUPP;
}
-static int bpf_local_storage_map_check_btf(const struct bpf_map *map,
- const struct btf *btf,
- const struct btf_type *key_type,
- const struct btf_type *value_type)
+int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+ const struct btf *btf,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
{
u32 int_data;
fd = *(int *)key;
sock = sockfd_lookup(fd, &err);
if (sock) {
- sdata = bpf_local_storage_update(sock->sk, map, value,
- map_flags);
+ sdata = bpf_local_storage_update(
+ sock->sk, (struct bpf_local_storage_map *)map, value,
+ map_flags);
sockfd_put(sock);
return PTR_ERR_OR_ZERO(sdata);
}
bpf_selem_link_map(smap, copy_selem);
bpf_selem_link_storage_nolock(new_sk_storage, copy_selem);
} else {
- ret = sk_storage_alloc(newsk, smap, copy_selem);
+ ret = bpf_local_storage_alloc(newsk, smap, copy_selem);
if (ret) {
kfree(copy_selem);
atomic_sub(smap->elem_size,
* destruction).
*/
refcount_inc_not_zero(&sk->sk_refcnt)) {
- sdata = bpf_local_storage_update(sk, map, value, BPF_NOEXIST);
+ sdata = bpf_local_storage_update(
+ sk, (struct bpf_local_storage_map *)map, value,
+ BPF_NOEXIST);
/* sk must be a fullsock (guaranteed by verifier),
* so sock_gen_put() is unnecessary.
*/
return -ENOENT;
}
+static int sk_storage_charge(struct bpf_local_storage_map *smap,
+ void *owner, u32 size)
+{
+ return omem_charge(owner, size);
+}
+
+static void sk_storage_uncharge(struct bpf_local_storage_map *smap,
+ void *owner, u32 size)
+{
+ struct sock *sk = owner;
+
+ atomic_sub(size, &sk->sk_omem_alloc);
+}
+
+static struct bpf_local_storage __rcu **
+sk_storage_ptr(void *owner)
+{
+ struct sock *sk = owner;
+
+ return &sk->sk_bpf_storage;
+}
+
static int sk_storage_map_btf_id;
const struct bpf_map_ops sk_storage_map_ops = {
.map_alloc_check = bpf_local_storage_map_alloc_check,
- .map_alloc = bpf_local_storage_map_alloc,
- .map_free = bpf_local_storage_map_free,
+ .map_alloc = sk_storage_map_alloc,
+ .map_free = sk_storage_map_free,
.map_get_next_key = notsupp_get_next_key,
.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
.map_update_elem = bpf_fd_sk_storage_update_elem,
.map_check_btf = bpf_local_storage_map_check_btf,
.map_btf_name = "bpf_local_storage_map",
.map_btf_id = &sk_storage_map_btf_id,
+ .map_local_storage_charge = sk_storage_charge,
+ .map_local_storage_uncharge = sk_storage_uncharge,
+ .map_owner_storage_ptr = sk_storage_ptr,
};
const struct bpf_func_proto bpf_sk_storage_get_proto = {