aboutsummaryrefslogtreecommitdiff
path: root/kernel/bpf/hashtab.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf/hashtab.c')
-rw-r--r--kernel/bpf/hashtab.c80
1 files changed, 62 insertions, 18 deletions
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 2c1790288138..fed15cf94dca 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -23,7 +23,7 @@
#define HTAB_CREATE_FLAG_MASK \
(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \
- BPF_F_RDONLY | BPF_F_WRONLY)
+ BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED)
struct bucket {
struct hlist_nulls_head head;
@@ -244,6 +244,7 @@ static int htab_map_alloc_check(union bpf_attr *attr)
*/
bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
+ bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED);
int numa_node = bpf_map_attr_numa_node(attr);
BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
@@ -257,6 +258,10 @@ static int htab_map_alloc_check(union bpf_attr *attr)
*/
return -EPERM;
+ if (zero_seed && !capable(CAP_SYS_ADMIN))
+ /* Guard against local DoS, and discourage production use. */
+ return -EPERM;
+
if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
/* reserved bits should not be used */
return -EINVAL;
@@ -373,7 +378,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
if (!htab->buckets)
goto free_htab;
- htab->hashrnd = get_random_int();
+ if (htab->map.map_flags & BPF_F_ZERO_SEED)
+ htab->hashrnd = 0;
+ else
+ htab->hashrnd = get_random_int();
+
for (i = 0; i < htab->n_buckets; i++) {
INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
raw_spin_lock_init(&htab->buckets[i].lock);
@@ -677,7 +686,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
}
if (htab_is_prealloc(htab)) {
- pcpu_freelist_push(&htab->freelist, &l->fnode);
+ __pcpu_freelist_push(&htab->freelist, &l->fnode);
} else {
atomic_dec(&htab->count);
l->htab = htab;
@@ -709,21 +718,12 @@ static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
BITS_PER_LONG == 64;
}
-static u32 htab_size_value(const struct bpf_htab *htab, bool percpu)
-{
- u32 size = htab->map.value_size;
-
- if (percpu || fd_htab_map_needs_adjust(htab))
- size = round_up(size, 8);
- return size;
-}
-
static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
void *value, u32 key_size, u32 hash,
bool percpu, bool onallcpus,
struct htab_elem *old_elem)
{
- u32 size = htab_size_value(htab, percpu);
+ u32 size = htab->map.value_size;
bool prealloc = htab_is_prealloc(htab);
struct htab_elem *l_new, **pl_new;
void __percpu *pptr;
@@ -739,7 +739,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
} else {
struct pcpu_freelist_node *l;
- l = pcpu_freelist_pop(&htab->freelist);
+ l = __pcpu_freelist_pop(&htab->freelist);
if (!l)
return ERR_PTR(-E2BIG);
l_new = container_of(l, struct htab_elem, fnode);
@@ -761,10 +761,13 @@ 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));
}
memcpy(l_new->key, key, key_size);
if (percpu) {
+ size = round_up(size, 8);
if (prealloc) {
pptr = htab_elem_get_ptr(l_new, key_size);
} else {
@@ -782,8 +785,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
if (!prealloc)
htab_elem_set_ptr(l_new, key_size, pptr);
- } else {
+ } else if (fd_htab_map_needs_adjust(htab)) {
+ size = round_up(size, 8);
memcpy(l_new->key + round_up(key_size, 8), value, size);
+ } else {
+ copy_map_value(&htab->map,
+ l_new->key + round_up(key_size, 8),
+ value);
}
l_new->hash = hash;
@@ -796,11 +804,11 @@ dec_count:
static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
u64 map_flags)
{
- if (l_old && map_flags == BPF_NOEXIST)
+ if (l_old && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
/* elem already exists */
return -EEXIST;
- if (!l_old && map_flags == BPF_EXIST)
+ if (!l_old && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
/* elem doesn't exist, cannot update it */
return -ENOENT;
@@ -819,7 +827,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
u32 key_size, hash;
int ret;
- if (unlikely(map_flags > BPF_EXIST))
+ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST))
/* unknown flags */
return -EINVAL;
@@ -832,6 +840,28 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
b = __select_bucket(htab, hash);
head = &b->head;
+ if (unlikely(map_flags & BPF_F_LOCK)) {
+ if (unlikely(!map_value_has_spin_lock(map)))
+ return -EINVAL;
+ /* find an element without taking the bucket lock */
+ l_old = lookup_nulls_elem_raw(head, hash, key, key_size,
+ htab->n_buckets);
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ return ret;
+ if (l_old) {
+ /* grab the element lock and update value in place */
+ copy_map_value_locked(map,
+ l_old->key + round_up(key_size, 8),
+ value, false);
+ return 0;
+ }
+ /* fall through, grab the bucket lock and lookup again.
+ * 99.9% chance that the element won't be found,
+ * but second lookup under lock has to be done.
+ */
+ }
+
/* bpf_map_update_elem() can be called in_irq() */
raw_spin_lock_irqsave(&b->lock, flags);
@@ -841,6 +871,20 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
if (ret)
goto err;
+ if (unlikely(l_old && (map_flags & BPF_F_LOCK))) {
+ /* first lookup without the bucket lock didn't find the element,
+ * but second lookup with the bucket lock found it.
+ * This case is highly unlikely, but has to be dealt with:
+ * grab the element lock in addition to the bucket lock
+ * and update element in place
+ */
+ copy_map_value_locked(map,
+ l_old->key + round_up(key_size, 8),
+ value, false);
+ ret = 0;
+ goto err;
+ }
+
l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
l_old);
if (IS_ERR(l_new)) {
generated by cgit (git 2.34.1) at 2025-05-29 16:25:55 +0000