diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 5aa2b5525f79..a47406042a22 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -80,9 +80,6 @@ struct bucket {
 	raw_spinlock_t raw_lock;
 };
 
-#define HASHTAB_MAP_LOCK_COUNT 8
-#define HASHTAB_MAP_LOCK_MASK (HASHTAB_MAP_LOCK_COUNT - 1)
-
 struct bpf_htab {
 	struct bpf_map map;
 	struct bpf_mem_alloc ma;
@@ -104,7 +101,6 @@ struct bpf_htab {
 	u32 elem_size;	/* size of each element in bytes */
 	u32 hashrnd;
 	struct lock_class_key lockdep_key;
-	int __percpu *map_locked[HASHTAB_MAP_LOCK_COUNT];
 };
 
 /* each htab element is struct htab_elem + key + value */
@@ -146,35 +142,26 @@ static void htab_init_buckets(struct bpf_htab *htab)
 	}
 }
 
-static inline int htab_lock_bucket(const struct bpf_htab *htab,
-				   struct bucket *b, u32 hash,
+static inline int htab_lock_bucket(struct bucket *b,
 				   unsigned long *pflags)
 {
 	unsigned long flags;
 
-	hash = hash & HASHTAB_MAP_LOCK_MASK;
-
-	preempt_disable();
-	if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
-		__this_cpu_dec(*(htab->map_locked[hash]));
-		preempt_enable();
-		return -EBUSY;
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&b->raw_lock, flags))
+			return -EBUSY;
+	} else {
+		raw_spin_lock_irqsave(&b->raw_lock, flags);
 	}
 
-	raw_spin_lock_irqsave(&b->raw_lock, flags);
 	*pflags = flags;
-
 	return 0;
 }
 
-static inline void htab_unlock_bucket(const struct bpf_htab *htab,
-				      struct bucket *b, u32 hash,
+static inline void htab_unlock_bucket(struct bucket *b,
 				      unsigned long flags)
 {
-	hash = hash & HASHTAB_MAP_LOCK_MASK;
 	raw_spin_unlock_irqrestore(&b->raw_lock, flags);
-	__this_cpu_dec(*(htab->map_locked[hash]));
-	preempt_enable();
 }
 
 static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
@@ -467,7 +454,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
 	bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
 	struct bpf_htab *htab;
-	int err, i;
+	int err;
 
 	htab = bpf_map_area_alloc(sizeof(*htab), NUMA_NO_NODE);
 	if (!htab)
@@ -512,15 +499,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	if (!htab->buckets)
 		goto free_htab;
 
-	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) {
-		htab->map_locked[i] = bpf_map_alloc_percpu(&htab->map,
-							   sizeof(int),
-							   sizeof(int),
-							   GFP_USER);
-		if (!htab->map_locked[i])
-			goto free_map_locked;
-	}
-
 	if (htab->map.map_flags & BPF_F_ZERO_SEED)
 		htab->hashrnd = 0;
 	else
@@ -548,13 +526,13 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	if (htab->use_percpu_counter) {
 		err = percpu_counter_init(&htab->pcount, 0, GFP_KERNEL);
 		if (err)
-			goto free_map_locked;
+			goto free_buckets;
 	}
 
 	if (prealloc) {
 		err = prealloc_init(htab);
 		if (err)
-			goto free_map_locked;
+			goto free_buckets;
 
 		if (!percpu && !lru) {
 			/* lru itself can remove the least used element, so
@@ -567,12 +545,12 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	} else {
 		err = bpf_mem_alloc_init(&htab->ma, htab->elem_size, false);
 		if (err)
-			goto free_map_locked;
+			goto free_buckets;
 		if (percpu) {
 			err = bpf_mem_alloc_init(&htab->pcpu_ma,
 						 round_up(htab->map.value_size, 8), true);
 			if (err)
-				goto free_map_locked;
+				goto free_buckets;
 		}
 	}
 
@@ -580,11 +558,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 
 free_prealloc:
 	prealloc_destroy(htab);
-free_map_locked:
+free_buckets:
 	if (htab->use_percpu_counter)
 		percpu_counter_destroy(&htab->pcount);
-	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
-		free_percpu(htab->map_locked[i]);
+
 	bpf_map_area_free(htab->buckets);
 	bpf_mem_alloc_destroy(&htab->pcpu_ma);
 	bpf_mem_alloc_destroy(&htab->ma);
@@ -781,7 +758,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 	b = __select_bucket(htab, tgt_l->hash);
 	head = &b->head;
 
-	ret = htab_lock_bucket(htab, b, tgt_l->hash, &flags);
+	ret = htab_lock_bucket(b, &flags);
 	if (ret)
 		return false;
 
@@ -792,7 +769,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 			break;
 		}
 
-	htab_unlock_bucket(htab, b, tgt_l->hash, flags);
+	htab_unlock_bucket(b, flags);
 
 	return l == tgt_l;
 }
@@ -1106,7 +1083,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		 */
 	}
 
-	ret = htab_lock_bucket(htab, b, hash, &flags);
+	ret = htab_lock_bucket(b, &flags);
 	if (ret)
 		return ret;
 
@@ -1151,7 +1128,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 	}
 	ret = 0;
 err:
-	htab_unlock_bucket(htab, b, hash, flags);
+	htab_unlock_bucket(b, flags);
 	return ret;
 }
 
@@ -1197,7 +1174,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 	copy_map_value(&htab->map,
 		       l_new->key + round_up(map->key_size, 8), value);
 
-	ret = htab_lock_bucket(htab, b, hash, &flags);
+	ret = htab_lock_bucket(b, &flags);
 	if (ret)
 		return ret;
 
@@ -1218,7 +1195,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 	ret = 0;
 
 err:
-	htab_unlock_bucket(htab, b, hash, flags);
+	htab_unlock_bucket(b, flags);
 
 	if (ret)
 		htab_lru_push_free(htab, l_new);
@@ -1254,7 +1231,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	ret = htab_lock_bucket(htab, b, hash, &flags);
+	ret = htab_lock_bucket(b, &flags);
 	if (ret)
 		return ret;
 
@@ -1279,7 +1256,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 	}
 	ret = 0;
 err:
-	htab_unlock_bucket(htab, b, hash, flags);
+	htab_unlock_bucket(b, flags);
 	return ret;
 }
 
@@ -1320,7 +1297,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 			return -ENOMEM;
 	}
 
-	ret = htab_lock_bucket(htab, b, hash, &flags);
+	ret = htab_lock_bucket(b, &flags);
 	if (ret)
 		return ret;
 
@@ -1344,7 +1321,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 	}
 	ret = 0;
 err:
-	htab_unlock_bucket(htab, b, hash, flags);
+	htab_unlock_bucket(b, flags);
 	if (l_new)
 		bpf_lru_push_free(&htab->lru, &l_new->lru_node);
 	return ret;
@@ -1383,7 +1360,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	ret = htab_lock_bucket(htab, b, hash, &flags);
+	ret = htab_lock_bucket(b, &flags);
 	if (ret)
 		return ret;
 
@@ -1396,7 +1373,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 		ret = -ENOENT;
 	}
 
-	htab_unlock_bucket(htab, b, hash, flags);
+	htab_unlock_bucket(b, flags);
 	return ret;
 }
 
@@ -1419,7 +1396,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	ret = htab_lock_bucket(htab, b, hash, &flags);
+	ret = htab_lock_bucket(b, &flags);
 	if (ret)
 		return ret;
 
@@ -1430,7 +1407,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 	else
 		ret = -ENOENT;
 
-	htab_unlock_bucket(htab, b, hash, flags);
+	htab_unlock_bucket(b, flags);
 	if (l)
 		htab_lru_push_free(htab, l);
 	return ret;
@@ -1493,7 +1470,6 @@ static void htab_map_free_timers(struct bpf_map *map)
 static void htab_map_free(struct bpf_map *map)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	int i;
 
 	/* bpf_free_used_maps() or close(map_fd) will trigger this map_free callback.
 	 * bpf_free_used_maps() is called after bpf prog is no longer executing.
@@ -1515,10 +1491,10 @@ static void htab_map_free(struct bpf_map *map)
 	bpf_map_area_free(htab->buckets);
 	bpf_mem_alloc_destroy(&htab->pcpu_ma);
 	bpf_mem_alloc_destroy(&htab->ma);
+
 	if (htab->use_percpu_counter)
 		percpu_counter_destroy(&htab->pcount);
-	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
-		free_percpu(htab->map_locked[i]);
+
 	lockdep_unregister_key(&htab->lockdep_key);
 	bpf_map_area_free(htab);
 }
@@ -1562,7 +1538,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	ret = htab_lock_bucket(htab, b, hash, &bflags);
+	ret = htab_lock_bucket(b, &bflags);
 	if (ret)
 		return ret;
 
@@ -1600,7 +1576,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
 			free_htab_elem(htab, l);
 	}
 
-	htab_unlock_bucket(htab, b, hash, bflags);
+	htab_unlock_bucket(b, bflags);
 
 	if (is_lru_map && l)
 		htab_lru_push_free(htab, l);
@@ -1718,7 +1694,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 	head = &b->head;
 	/* do not grab the lock unless need it (bucket_cnt > 0). */
 	if (locked) {
-		ret = htab_lock_bucket(htab, b, batch, &flags);
+		ret = htab_lock_bucket(b, &flags);
 		if (ret) {
 			rcu_read_unlock();
 			bpf_enable_instrumentation();
@@ -1741,7 +1717,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 		/* Note that since bucket_cnt > 0 here, it is implicit
 		 * that the locked was grabbed, so release it.
 		 */
-		htab_unlock_bucket(htab, b, batch, flags);
+		htab_unlock_bucket(b, flags);
 		rcu_read_unlock();
 		bpf_enable_instrumentation();
 		goto after_loop;
@@ -1752,7 +1728,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 		/* Note that since bucket_cnt > 0 here, it is implicit
 		 * that the locked was grabbed, so release it.
 		 */
-		htab_unlock_bucket(htab, b, batch, flags);
+		htab_unlock_bucket(b, flags);
 		rcu_read_unlock();
 		bpf_enable_instrumentation();
 		kvfree(keys);
@@ -1813,7 +1789,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 		dst_val += value_size;
 	}
 
-	htab_unlock_bucket(htab, b, batch, flags);
+	htab_unlock_bucket(b, flags);
 	locked = false;
 
 	while (node_to_free) {