bpf: add lookup_and_delete_elem support to hashtab

Extend the existing bpf_map_lookup_and_delete_elem() functionality to
hashtab maps, in addition to stacks and queues.
Create a new hashtab bpf_map_ops function that does lookup and deletion
of the element under the same bucket lock and add the created map_ops to
bpf.h.
Add the appropriate test case to 'maps' selftests.

Signed-off-by: Denis Salopek <denis.salopek@sartura.hr>
Cc: Juraj Vijtiuk <juraj.vijtiuk@sartura.hr>
Cc: Luka Oreskovic <luka.oreskovic@sartura.hr>
Cc: Luka Perkov <luka.perkov@sartura.hr>

Author: Denis Salopek

include/linux/bpf.h

@@ -77,6 +77,7 @@ struct bpf_map_ops {
 
 	/* funcs callable from userspace and from eBPF programs */
 	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
+	int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key, void *value);
 	int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
 	int (*map_delete_elem)(struct bpf_map *map, void *key);
 	int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags);

kernel/bpf/hashtab.c

@@ -973,6 +973,43 @@ static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
 	return 0;
 }
 
+/* Called from syscall or from eBPF program */
+static int htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, void *value)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_nulls_head *head;
+	struct bucket *b;
+	struct htab_elem *l;
+	unsigned long flags;
+	u32 hash, key_size;
+	int ret;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+
+	key_size = map->key_size;
+
+	hash = htab_map_hash(key, key_size, htab->hashrnd);
+	b = __select_bucket(htab, hash);
+	head = &b->head;
+
+	ret = htab_lock_bucket(htab, b, hash, &flags);
+	if (ret)
+		return ret;
+
+	l = lookup_elem_raw(head, hash, key, key_size);
+
+	if (l) {
+		copy_map_value(map, value, l->key + round_up(key_size, 8));
+		hlist_nulls_del_rcu(&l->hash_node);
+		free_htab_elem(htab, l);
+	} else {
+		ret = -ENOENT;
+	}
+
+	htab_unlock_bucket(htab, b, hash, flags);
+	return ret;
+}
+
 /* Called from syscall or from eBPF program */
 static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 				u64 map_flags)
@@ -1877,6 +1914,7 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.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,
 	.map_delete_elem = htab_map_delete_elem,
 	.map_gen_lookup = htab_map_gen_lookup,

kernel/bpf/syscall.c

@@ -1505,6 +1505,15 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	if (map->map_type == BPF_MAP_TYPE_QUEUE ||
 	    map->map_type == BPF_MAP_TYPE_STACK) {
 		err = map->ops->map_pop_elem(map, value);
+	} else if (map->map_type == BPF_MAP_TYPE_HASH) {
+		if (!bpf_map_is_dev_bound(map)) {
+			bpf_disable_instrumentation();
+			rcu_read_lock();
+			err = map->ops->map_lookup_and_delete_elem(map, key, value);
+			rcu_read_unlock();
+			bpf_enable_instrumentation();
+			maybe_wait_bpf_programs(map);
+		}
 	} else {
 		err = -ENOTSUPP;
 	}

tools/testing/selftests/bpf/test_maps.c

@@ -65,6 +65,13 @@ static void test_hashmap(unsigned int task, void *data)
 	assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 1234);
 
 	key = 2;
+	value = 1234;
+	/* Insert key=2 element. */
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
+
+	/* Check that key=2 matches the value and delete it */
+	assert(bpf_map_lookup_and_delete_elem(fd, &key, &value) == 0 && value == 1234);
+
 	/* Check that key=2 is not found. */
 	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);