@@ -198,24 +198,46 @@ static inline bool map_value_has_spin_lock(const struct bpf_map *map)
return map->spin_lock_off >= 0;
}
-static inline void check_and_init_map_lock(struct bpf_map *map, void *dst)
+static inline bool map_value_has_timer(const struct bpf_map *map)
{
- if (likely(!map_value_has_spin_lock(map)))
- return;
- *(struct bpf_spin_lock *)(dst + map->spin_lock_off) =
- (struct bpf_spin_lock){};
+ return map->timer_off >= 0;
}
-/* copy everything but bpf_spin_lock */
+static inline void check_and_init_map_value(struct bpf_map *map, void *dst)
+{
+ if (unlikely(map_value_has_spin_lock(map)))
+ *(struct bpf_spin_lock *)(dst + map->spin_lock_off) =
+ (struct bpf_spin_lock){};
+ if (unlikely(map_value_has_timer(map)))
+ *(struct bpf_timer *)(dst + map->timer_off) =
+ (struct bpf_timer){};
+}
+
+/* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */
static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
{
+ u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0;
+
if (unlikely(map_value_has_spin_lock(map))) {
- u32 off = map->spin_lock_off;
+ s_off = map->spin_lock_off;
+ s_sz = sizeof(struct bpf_spin_lock);
+ } else if (unlikely(map_value_has_timer(map))) {
+ t_off = map->timer_off;
+ t_sz = sizeof(struct bpf_timer);
+ }
- memcpy(dst, src, off);
- memcpy(dst + off + sizeof(struct bpf_spin_lock),
- src + off + sizeof(struct bpf_spin_lock),
- map->value_size - off - sizeof(struct bpf_spin_lock));
+ if (unlikely(s_sz || t_sz)) {
+ if (s_off < t_off || !s_sz) {
+ swap(s_off, t_off);
+ swap(s_sz, t_sz);
+ }
+ memcpy(dst, src, t_off);
+ memcpy(dst + t_off + t_sz,
+ src + t_off + t_sz,
+ s_off - t_off - t_sz);
+ memcpy(dst + s_off + s_sz,
+ src + s_off + s_sz,
+ map->value_size - s_off - s_sz);
} else {
memcpy(dst, src, map->value_size);
}
@@ -99,6 +99,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
const struct btf_member *m,
u32 expected_offset, u32 expected_size);
int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
+int btf_find_timer(const struct btf *btf, const struct btf_type *t);
bool btf_type_is_void(const struct btf_type *t);
s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind);
const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
@@ -287,6 +287,12 @@ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key
return 0;
}
+static void check_and_free_timer_in_array(struct bpf_array *arr, void *val)
+{
+ if (unlikely(map_value_has_timer(&arr->map)))
+ bpf_timer_cancel_and_free(val + arr->map.timer_off);
+}
+
/* Called from syscall or from eBPF program */
static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
@@ -321,6 +327,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
copy_map_value_locked(map, val, value, false);
else
copy_map_value(map, val, value);
+ check_and_free_timer_in_array(array, val);
}
return 0;
}
@@ -374,6 +381,19 @@ static void *array_map_vmalloc_addr(struct bpf_array *array)
return (void *)round_down((unsigned long)array, PAGE_SIZE);
}
+static void array_map_free_timers(struct bpf_map *map)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ int i;
+
+ if (likely(!map_value_has_timer(map)))
+ return;
+
+ for (i = 0; i < array->map.max_entries; i++)
+ bpf_timer_cancel_and_free(array->value + array->elem_size * i +
+ map->timer_off);
+}
+
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void array_map_free(struct bpf_map *map)
{
@@ -382,6 +402,7 @@ static void array_map_free(struct bpf_map *map)
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
bpf_array_free_percpu(array);
+ array_map_free_timers(map);
if (array->map.map_flags & BPF_F_MMAPABLE)
bpf_map_area_free(array_map_vmalloc_addr(array));
else
@@ -668,6 +689,7 @@ const struct bpf_map_ops array_map_ops = {
.map_alloc = array_map_alloc,
.map_free = array_map_free,
.map_get_next_key = array_map_get_next_key,
+ .map_release_uref = array_map_free_timers,
.map_lookup_elem = array_map_lookup_elem,
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
@@ -3046,43 +3046,92 @@ static void btf_struct_log(struct btf_verifier_env *env,
btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
}
-/* find 'struct bpf_spin_lock' in map value.
- * return >= 0 offset if found
- * and < 0 in case of error
- */
-int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
+static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t,
+ const char *name, int sz, int align)
{
const struct btf_member *member;
u32 i, off = -ENOENT;
- if (!__btf_type_is_struct(t))
- return -EINVAL;
-
for_each_member(i, t, member) {
const struct btf_type *member_type = btf_type_by_id(btf,
member->type);
if (!__btf_type_is_struct(member_type))
continue;
- if (member_type->size != sizeof(struct bpf_spin_lock))
+ if (member_type->size != sz)
continue;
- if (strcmp(__btf_name_by_offset(btf, member_type->name_off),
- "bpf_spin_lock"))
+ if (strcmp(__btf_name_by_offset(btf, member_type->name_off), name))
continue;
if (off != -ENOENT)
- /* only one 'struct bpf_spin_lock' is allowed */
+ /* only one such field is allowed */
return -E2BIG;
off = btf_member_bit_offset(t, member);
if (off % 8)
/* valid C code cannot generate such BTF */
return -EINVAL;
off /= 8;
- if (off % __alignof__(struct bpf_spin_lock))
- /* valid struct bpf_spin_lock will be 4 byte aligned */
+ if (off % align)
+ return -EINVAL;
+ }
+ return off;
+}
+
+static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
+ const char *name, int sz, int align)
+{
+ const struct btf_var_secinfo *vsi;
+ u32 i, off = -ENOENT;
+
+ for_each_vsi(i, t, vsi) {
+ const struct btf_type *var = btf_type_by_id(btf, vsi->type);
+ const struct btf_type *var_type = btf_type_by_id(btf, var->type);
+
+ if (!__btf_type_is_struct(var_type))
+ continue;
+ if (var_type->size != sz)
+ continue;
+ if (vsi->size != sz)
+ continue;
+ if (strcmp(__btf_name_by_offset(btf, var_type->name_off), name))
+ continue;
+ if (off != -ENOENT)
+ /* only one such field is allowed */
+ return -E2BIG;
+ off = vsi->offset;
+ if (off % align)
return -EINVAL;
}
return off;
}
+static int btf_find_field(const struct btf *btf, const struct btf_type *t,
+ const char *name, int sz, int align)
+{
+
+ if (__btf_type_is_struct(t))
+ return btf_find_struct_field(btf, t, name, sz, align);
+ else if (btf_type_is_datasec(t))
+ return btf_find_datasec_var(btf, t, name, sz, align);
+ return -EINVAL;
+}
+
+/* find 'struct bpf_spin_lock' in map value.
+ * return >= 0 offset if found
+ * and < 0 in case of error
+ */
+int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
+{
+ return btf_find_field(btf, t, "bpf_spin_lock",
+ sizeof(struct bpf_spin_lock),
+ __alignof__(struct bpf_spin_lock));
+}
+
+int btf_find_timer(const struct btf *btf, const struct btf_type *t)
+{
+ return btf_find_field(btf, t, "bpf_timer",
+ sizeof(struct bpf_timer),
+ __alignof__(struct bpf_timer));
+}
+
static void __btf_struct_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct btf_show *show)
@@ -228,6 +228,32 @@ static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
return (struct htab_elem *) (htab->elems + i * (u64)htab->elem_size);
}
+static bool htab_has_extra_elems(struct bpf_htab *htab)
+{
+ return !htab_is_percpu(htab) && !htab_is_lru(htab);
+}
+
+static void htab_free_prealloced_timers(struct bpf_htab *htab)
+{
+ u32 num_entries = htab->map.max_entries;
+ int i;
+
+ if (likely(!map_value_has_timer(&htab->map)))
+ return;
+ if (htab_has_extra_elems(htab))
+ num_entries += num_possible_cpus();
+
+ for (i = 0; i < num_entries; i++) {
+ struct htab_elem *elem;
+
+ elem = get_htab_elem(htab, i);
+ bpf_timer_cancel_and_free(elem->key +
+ round_up(htab->map.key_size, 8) +
+ htab->map.timer_off);
+ cond_resched();
+ }
+}
+
static void htab_free_elems(struct bpf_htab *htab)
{
int i;
@@ -244,6 +270,7 @@ static void htab_free_elems(struct bpf_htab *htab)
cond_resched();
}
free_elems:
+ htab_free_prealloced_timers(htab);
bpf_map_area_free(htab->elems);
}
@@ -265,8 +292,11 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
struct htab_elem *l;
if (node) {
+ u32 key_size = htab->map.key_size;
l = container_of(node, struct htab_elem, lru_node);
- memcpy(l->key, key, htab->map.key_size);
+ memcpy(l->key, key, key_size);
+ check_and_init_map_value(&htab->map,
+ l->key + round_up(key_size, 8));
return l;
}
@@ -278,7 +308,7 @@ static int prealloc_init(struct bpf_htab *htab)
u32 num_entries = htab->map.max_entries;
int err = -ENOMEM, i;
- if (!htab_is_percpu(htab) && !htab_is_lru(htab))
+ if (htab_has_extra_elems(htab))
num_entries += num_possible_cpus();
htab->elems = bpf_map_area_alloc((u64)htab->elem_size * num_entries,
@@ -695,6 +725,14 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map,
return insn - insn_buf;
}
+static void check_and_free_timer(struct bpf_htab *htab, struct htab_elem *elem)
+{
+ if (unlikely(map_value_has_timer(&htab->map)))
+ bpf_timer_cancel_and_free(elem->key +
+ round_up(htab->map.key_size, 8) +
+ htab->map.timer_off);
+}
+
/* It is called from the bpf_lru_list when the LRU needs to delete
* older elements from the htab.
*/
@@ -719,6 +757,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
if (l == tgt_l) {
hlist_nulls_del_rcu(&l->hash_node);
+ check_and_free_timer(htab, l);
break;
}
@@ -790,6 +829,7 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
{
if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
+ check_and_free_timer(htab, l);
kfree(l);
}
@@ -817,6 +857,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
htab_put_fd_value(htab, l);
if (htab_is_prealloc(htab)) {
+ check_and_free_timer(htab, l);
__pcpu_freelist_push(&htab->freelist, &l->fnode);
} else {
atomic_dec(&htab->count);
@@ -920,8 +961,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
l_new = ERR_PTR(-ENOMEM);
goto dec_count;
}
- check_and_init_map_lock(&htab->map,
- l_new->key + round_up(key_size, 8));
+ check_and_init_map_value(&htab->map,
+ l_new->key + round_up(key_size, 8));
}
memcpy(l_new->key, key, key_size);
@@ -1062,6 +1103,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
hlist_nulls_del_rcu(&l_old->hash_node);
if (!htab_is_prealloc(htab))
free_htab_elem(htab, l_old);
+ else
+ check_and_free_timer(htab, l_old);
}
ret = 0;
err:
@@ -1069,6 +1112,12 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
return ret;
}
+static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem)
+{
+ check_and_free_timer(htab, elem);
+ bpf_lru_push_free(&htab->lru, &elem->lru_node);
+}
+
static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
@@ -1102,7 +1151,8 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
l_new = prealloc_lru_pop(htab, key, hash);
if (!l_new)
return -ENOMEM;
- memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size);
+ copy_map_value(&htab->map,
+ l_new->key + round_up(map->key_size, 8), value);
ret = htab_lock_bucket(htab, b, hash, &flags);
if (ret)
@@ -1128,9 +1178,9 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
htab_unlock_bucket(htab, b, hash, flags);
if (ret)
- bpf_lru_push_free(&htab->lru, &l_new->lru_node);
+ htab_lru_push_free(htab, l_new);
else if (l_old)
- bpf_lru_push_free(&htab->lru, &l_old->lru_node);
+ htab_lru_push_free(htab, l_old);
return ret;
}
@@ -1339,7 +1389,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
htab_unlock_bucket(htab, b, hash, flags);
if (l)
- bpf_lru_push_free(&htab->lru, &l->lru_node);
+ htab_lru_push_free(htab, l);
return ret;
}
@@ -1359,6 +1409,32 @@ static void delete_all_elements(struct bpf_htab *htab)
}
}
+static void htab_free_malloced_timers(struct bpf_htab *htab)
+{
+ int i;
+
+ for (i = 0; i < htab->n_buckets; i++) {
+ struct hlist_nulls_head *head = select_bucket(htab, i);
+ struct hlist_nulls_node *n;
+ struct htab_elem *l;
+
+ hlist_nulls_for_each_entry(l, n, head, hash_node)
+ check_and_free_timer(htab, l);
+ }
+}
+
+static void htab_map_free_timers(struct bpf_map *map)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+ if (likely(!map_value_has_timer(&htab->map)))
+ return;
+ if (!htab_is_prealloc(htab))
+ htab_free_malloced_timers(htab);
+ else
+ htab_free_prealloced_timers(htab);
+}
+
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void htab_map_free(struct bpf_map *map)
{
@@ -1456,7 +1532,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
else
copy_map_value(map, value, l->key +
roundup_key_size);
- check_and_init_map_lock(map, value);
+ check_and_init_map_value(map, value);
}
hlist_nulls_del_rcu(&l->hash_node);
@@ -1467,7 +1543,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
htab_unlock_bucket(htab, b, hash, bflags);
if (is_lru_map && l)
- bpf_lru_push_free(&htab->lru, &l->lru_node);
+ htab_lru_push_free(htab, l);
return ret;
}
@@ -1645,7 +1721,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
true);
else
copy_map_value(map, dst_val, value);
- check_and_init_map_lock(map, dst_val);
+ check_and_init_map_value(map, dst_val);
}
if (do_delete) {
hlist_nulls_del_rcu(&l->hash_node);
@@ -1672,7 +1748,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
while (node_to_free) {
l = node_to_free;
node_to_free = node_to_free->batch_flink;
- bpf_lru_push_free(&htab->lru, &l->lru_node);
+ htab_lru_push_free(htab, l);
}
next_batch:
@@ -2034,6 +2110,7 @@ const struct bpf_map_ops htab_map_ops = {
.map_alloc = htab_map_alloc,
.map_free = htab_map_free,
.map_get_next_key = htab_map_get_next_key,
+ .map_release_uref = htab_map_free_timers,
.map_lookup_elem = htab_map_lookup_elem,
.map_lookup_and_delete_elem = htab_map_lookup_and_delete_elem,
.map_update_elem = htab_map_update_elem,
@@ -2055,6 +2132,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
.map_alloc = htab_map_alloc,
.map_free = htab_map_free,
.map_get_next_key = htab_map_get_next_key,
+ .map_release_uref = htab_map_free_timers,
.map_lookup_elem = htab_lru_map_lookup_elem,
.map_lookup_and_delete_elem = htab_lru_map_lookup_and_delete_elem,
.map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys,
@@ -173,7 +173,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key,
return -ENOMEM;
memcpy(&new->data[0], value, map->value_size);
- check_and_init_map_lock(map, new->data);
+ check_and_init_map_value(map, new->data);
new = xchg(&storage->buf, new);
kfree_rcu(new, rcu);
@@ -509,7 +509,7 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
map->numa_node);
if (!storage->buf)
goto enomem;
- check_and_init_map_lock(map, storage->buf->data);
+ check_and_init_map_value(map, storage->buf->data);
} else {
storage->percpu_buf = bpf_map_alloc_percpu(map, size, 8, gfp);
if (!storage->percpu_buf)
@@ -50,6 +50,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
inner_map_meta->map_flags = inner_map->map_flags;
inner_map_meta->max_entries = inner_map->max_entries;
inner_map_meta->spin_lock_off = inner_map->spin_lock_off;
+ inner_map_meta->timer_off = inner_map->timer_off;
/* Misc members not needed in bpf_map_meta_equal() check. */
inner_map_meta->ops = inner_map->ops;
@@ -75,6 +76,7 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0,
return meta0->map_type == meta1->map_type &&
meta0->key_size == meta1->key_size &&
meta0->value_size == meta1->value_size &&
+ meta0->timer_off == meta1->timer_off &&
meta0->map_flags == meta1->map_flags;
}
@@ -260,8 +260,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
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);
+ /* mask lock and timer, since value wasn't zero inited */
+ check_and_init_map_value(map, value);
}
rcu_read_unlock();
}
@@ -623,7 +623,8 @@ 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))
+ if (!map->ops->map_mmap || map_value_has_spin_lock(map) ||
+ map_value_has_timer(map))
return -ENOTSUPP;
if (!(vma->vm_flags & VM_SHARED))
@@ -793,6 +794,16 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
}
}
+ map->timer_off = btf_find_timer(btf, value_type);
+ if (map_value_has_timer(map)) {
+ if (map->map_flags & BPF_F_RDONLY_PROG)
+ return -EACCES;
+ if (map->map_type != BPF_MAP_TYPE_HASH &&
+ map->map_type != BPF_MAP_TYPE_LRU_HASH &&
+ map->map_type != BPF_MAP_TYPE_ARRAY)
+ return -EOPNOTSUPP;
+ }
+
if (map->ops->map_check_btf)
ret = map->ops->map_check_btf(map, btf, key_type, value_type);
@@ -844,6 +855,7 @@ static int map_create(union bpf_attr *attr)
mutex_init(&map->freeze_mutex);
map->spin_lock_off = -EINVAL;
+ map->timer_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
@@ -1591,7 +1603,8 @@ static int map_freeze(const union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
- if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
+ if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS ||
+ map_value_has_timer(map)) {
fdput(f);
return -ENOTSUPP;
}
@@ -3241,6 +3241,15 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
return -EACCES;
}
}
+ if (map_value_has_timer(map)) {
+ u32 t = map->timer_off;
+
+ if (reg->smin_value + off < t + sizeof(struct bpf_timer) &&
+ t < reg->umax_value + off + size) {
+ verbose(env, "bpf_timer cannot be accessed directly by load/store\n");
+ return -EACCES;
+ }
+ }
return err;
}
@@ -4675,9 +4684,24 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
map->name);
return -EINVAL;
}
- if (val) {
- /* This restriction will be removed in the next patch */
- verbose(env, "bpf_timer field can only be first in the map value element\n");
+ if (!map_value_has_timer(map)) {
+ if (map->timer_off == -E2BIG)
+ verbose(env,
+ "map '%s' has more than one 'struct bpf_timer'\n",
+ map->name);
+ else if (map->timer_off == -ENOENT)
+ verbose(env,
+ "map '%s' doesn't have 'struct bpf_timer'\n",
+ map->name);
+ else
+ verbose(env,
+ "map '%s' is not a struct type or bpf_timer is mangled\n",
+ map->name);
+ return -EINVAL;
+ }
+ if (map->timer_off != val + reg->off) {
+ verbose(env, "off %lld doesn't point to 'struct bpf_timer' that is at %d\n",
+ val + reg->off, map->timer_off);
return -EINVAL;
}
if (meta->map_ptr) {