1 files changed, 216 insertions, 200 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3a088a5349bc..71f9931ac64c 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -16,6 +16,7 @@
 #include "bpf_lru_list.h"
 #include "map_in_map.h"
 #include <linux/bpf_mem_alloc.h>
+#include <asm/rqspinlock.h>
 
 #define HTAB_CREATE_FLAG_MASK						\
 	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE |	\
@@ -78,7 +79,7 @@
  */
 struct bucket {
 	struct hlist_nulls_head head;
-	raw_spinlock_t raw_lock;
+	rqspinlock_t raw_lock;
 };
 
 #define HASHTAB_MAP_LOCK_COUNT 8
@@ -104,8 +105,6 @@ struct bpf_htab {
 	u32 n_buckets;	/* number of hash buckets */
 	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 */
@@ -140,45 +139,26 @@ static void htab_init_buckets(struct bpf_htab *htab)
 
 	for (i = 0; i < htab->n_buckets; i++) {
 		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
-		raw_spin_lock_init(&htab->buckets[i].raw_lock);
-		lockdep_set_class(&htab->buckets[i].raw_lock,
-					  &htab->lockdep_key);
+		raw_res_spin_lock_init(&htab->buckets[i].raw_lock);
 		cond_resched();
 	}
 }
 
-static inline int htab_lock_bucket(const struct bpf_htab *htab,
-				   struct bucket *b, u32 hash,
-				   unsigned long *pflags)
+static inline int htab_lock_bucket(struct bucket *b, unsigned long *pflags)
 {
 	unsigned long flags;
+	int ret;
 
-	hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
-
-	preempt_disable();
-	local_irq_save(flags);
-	if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
-		__this_cpu_dec(*(htab->map_locked[hash]));
-		local_irq_restore(flags);
-		preempt_enable();
-		return -EBUSY;
-	}
-
-	raw_spin_lock(&b->raw_lock);
+	ret = raw_res_spin_lock_irqsave(&b->raw_lock, flags);
+	if (ret)
+		return ret;
 	*pflags = flags;
-
 	return 0;
 }
 
-static inline void htab_unlock_bucket(const struct bpf_htab *htab,
-				      struct bucket *b, u32 hash,
-				      unsigned long flags)
+static inline void htab_unlock_bucket(struct bucket *b, unsigned long flags)
 {
-	hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
-	raw_spin_unlock(&b->raw_lock);
-	__this_cpu_dec(*(htab->map_locked[hash]));
-	local_irq_restore(flags);
-	preempt_enable();
+	raw_res_spin_unlock_irqrestore(&b->raw_lock, flags);
 }
 
 static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
@@ -195,20 +175,30 @@ static bool htab_is_percpu(const struct bpf_htab *htab)
 		htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
 }
 
+static inline bool is_fd_htab(const struct bpf_htab *htab)
+{
+	return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS;
+}
+
+static inline void *htab_elem_value(struct htab_elem *l, u32 key_size)
+{
+	return l->key + round_up(key_size, 8);
+}
+
 static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
 				     void __percpu *pptr)
 {
-	*(void __percpu **)(l->key + key_size) = pptr;
+	*(void __percpu **)htab_elem_value(l, key_size) = pptr;
 }
 
 static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size)
 {
-	return *(void __percpu **)(l->key + key_size);
+	return *(void __percpu **)htab_elem_value(l, key_size);
 }
 
 static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l)
 {
-	return *(void **)(l->key + roundup(map->key_size, 8));
+	return *(void **)htab_elem_value(l, map->key_size);
 }
 
 static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
@@ -216,18 +206,20 @@ static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
 	return (struct htab_elem *) (htab->elems + i * (u64)htab->elem_size);
 }
 
+/* Both percpu and fd htab support in-place update, so no need for
+ * extra elem. LRU itself can remove the least used element, so
+ * there is no need for an extra elem during map_update.
+ */
 static bool htab_has_extra_elems(struct bpf_htab *htab)
 {
-	return !htab_is_percpu(htab) && !htab_is_lru(htab);
+	return !htab_is_percpu(htab) && !htab_is_lru(htab) && !is_fd_htab(htab);
 }
 
-static void htab_free_prealloced_timers(struct bpf_htab *htab)
+static void htab_free_prealloced_timers_and_wq(struct bpf_htab *htab)
 {
 	u32 num_entries = htab->map.max_entries;
 	int i;
 
-	if (!btf_record_has_field(htab->map.record, BPF_TIMER))
-		return;
 	if (htab_has_extra_elems(htab))
 		num_entries += num_possible_cpus();
 
@@ -235,7 +227,12 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab)
 		struct htab_elem *elem;
 
 		elem = get_htab_elem(htab, i);
-		bpf_obj_free_timer(htab->map.record, elem->key + round_up(htab->map.key_size, 8));
+		if (btf_record_has_field(htab->map.record, BPF_TIMER))
+			bpf_obj_free_timer(htab->map.record,
+					   htab_elem_value(elem, htab->map.key_size));
+		if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE))
+			bpf_obj_free_workqueue(htab->map.record,
+					       htab_elem_value(elem, htab->map.key_size));
 		cond_resched();
 	}
 }
@@ -262,7 +259,8 @@ static void htab_free_prealloced_fields(struct bpf_htab *htab)
 				cond_resched();
 			}
 		} else {
-			bpf_obj_free_fields(htab->map.record, elem->key + round_up(htab->map.key_size, 8));
+			bpf_obj_free_fields(htab->map.record,
+					    htab_elem_value(elem, htab->map.key_size));
 			cond_resched();
 		}
 		cond_resched();
@@ -459,6 +457,9 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 		 * kmalloc-able later in htab_map_update_elem()
 		 */
 		return -E2BIG;
+	/* percpu map value size is bound by PCPU_MIN_UNIT_SIZE */
+	if (percpu && round_up(attr->value_size, 8) > PCPU_MIN_UNIT_SIZE)
+		return -E2BIG;
 
 	return 0;
 }
@@ -467,8 +468,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 {
 	bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 		       attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
-	bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH ||
-		    attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
 	/* percpu_lru means each cpu has its own LRU list.
 	 * it is different from BPF_MAP_TYPE_PERCPU_HASH where
 	 * the map's value itself is percpu.  percpu_lru has
@@ -477,14 +476,12 @@ 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)
 		return ERR_PTR(-ENOMEM);
 
-	lockdep_register_key(&htab->lockdep_key);
-
 	bpf_map_init_from_attr(&htab->map, attr);
 
 	if (percpu_lru) {
@@ -530,15 +527,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	if (!htab->buckets)
 		goto free_elem_count;
 
-	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
@@ -574,10 +562,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		if (err)
 			goto free_map_locked;
 
-		if (!percpu && !lru) {
-			/* lru itself can remove the least used element, so
-			 * there is no need for an extra elem during map_update.
-			 */
+		if (htab_has_extra_elems(htab)) {
 			err = alloc_extra_elems(htab);
 			if (err)
 				goto free_prealloc;
@@ -601,15 +586,12 @@ free_prealloc:
 free_map_locked:
 	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);
 free_elem_count:
 	bpf_map_free_elem_count(&htab->map);
 free_htab:
-	lockdep_unregister_key(&htab->lockdep_key);
 	bpf_map_area_free(htab);
 	return ERR_PTR(err);
 }
@@ -698,7 +680,7 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
 	struct htab_elem *l = __htab_map_lookup_elem(map, key);
 
 	if (l)
-		return l->key + round_up(map->key_size, 8);
+		return htab_elem_value(l, map->key_size);
 
 	return NULL;
 }
@@ -737,7 +719,7 @@ static __always_inline void *__htab_lru_map_lookup_elem(struct bpf_map *map,
 	if (l) {
 		if (mark)
 			bpf_lru_node_set_ref(&l->lru_node);
-		return l->key + round_up(map->key_size, 8);
+		return htab_elem_value(l, map->key_size);
 	}
 
 	return NULL;
@@ -781,6 +763,9 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map,
 static void check_and_free_fields(struct bpf_htab *htab,
 				  struct htab_elem *elem)
 {
+	if (IS_ERR_OR_NULL(htab->map.record))
+		return;
+
 	if (htab_is_percpu(htab)) {
 		void __percpu *pptr = htab_elem_get_ptr(elem, htab->map.key_size);
 		int cpu;
@@ -788,7 +773,7 @@ static void check_and_free_fields(struct bpf_htab *htab,
 		for_each_possible_cpu(cpu)
 			bpf_obj_free_fields(htab->map.record, per_cpu_ptr(pptr, cpu));
 	} else {
-		void *map_value = elem->key + round_up(htab->map.key_size, 8);
+		void *map_value = htab_elem_value(elem, htab->map.key_size);
 
 		bpf_obj_free_fields(htab->map.record, map_value);
 	}
@@ -811,20 +796,21 @@ 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;
 
 	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_fields(htab, l);
 			bpf_map_dec_elem_count(&htab->map);
 			break;
 		}
 
-	htab_unlock_bucket(htab, b, tgt_l->hash, flags);
+	htab_unlock_bucket(b, flags);
 
+	if (l == tgt_l)
+		check_and_free_fields(htab, l);
 	return l == tgt_l;
 }
 
@@ -890,6 +876,7 @@ find_first_elem:
 static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
 {
 	check_and_free_fields(htab, l);
+
 	if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
 		bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr);
 	bpf_mem_cache_free(&htab->ma, l);
@@ -942,7 +929,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 	if (htab_is_prealloc(htab)) {
 		bpf_map_dec_elem_count(&htab->map);
 		check_and_free_fields(htab, l);
-		__pcpu_freelist_push(&htab->freelist, &l->fnode);
+		pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
 		dec_elem_count(htab);
 		htab_elem_free(htab, l);
@@ -991,8 +978,7 @@ static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
 
 static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
 {
-	return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS &&
-	       BITS_PER_LONG == 64;
+	return is_fd_htab(htab) && BITS_PER_LONG == 64;
 }
 
 static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
@@ -1012,7 +998,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			 */
 			pl_new = this_cpu_ptr(htab->extra_elems);
 			l_new = *pl_new;
-			htab_put_fd_value(htab, old_elem);
 			*pl_new = old_elem;
 		} else {
 			struct pcpu_freelist_node *l;
@@ -1046,14 +1031,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			pptr = htab_elem_get_ptr(l_new, key_size);
 		} else {
 			/* alloc_percpu zero-fills */
-			pptr = bpf_mem_cache_alloc(&htab->pcpu_ma);
-			if (!pptr) {
+			void *ptr = bpf_mem_cache_alloc(&htab->pcpu_ma);
+
+			if (!ptr) {
 				bpf_mem_cache_free(&htab->ma, l_new);
 				l_new = ERR_PTR(-ENOMEM);
 				goto dec_count;
 			}
-			l_new->ptr_to_pptr = pptr;
-			pptr = *(void **)pptr;
+			l_new->ptr_to_pptr = ptr;
+			pptr = *(void __percpu **)ptr;
 		}
 
 		pcpu_init_value(htab, pptr, value, onallcpus);
@@ -1062,11 +1048,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			htab_elem_set_ptr(l_new, key_size, pptr);
 	} else if (fd_htab_map_needs_adjust(htab)) {
 		size = round_up(size, 8);
-		memcpy(l_new->key + round_up(key_size, 8), value, size);
+		memcpy(htab_elem_value(l_new, key_size), value, size);
 	} else {
-		copy_map_value(&htab->map,
-			       l_new->key + round_up(key_size, 8),
-			       value);
+		copy_map_value(&htab->map, htab_elem_value(l_new, key_size), value);
 	}
 
 	l_new->hash = hash;
@@ -1095,7 +1079,7 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 				 u64 map_flags)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct htab_elem *l_new = NULL, *l_old;
+	struct htab_elem *l_new, *l_old;
 	struct hlist_nulls_head *head;
 	unsigned long flags;
 	struct bucket *b;
@@ -1128,7 +1112,7 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		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),
+					      htab_elem_value(l_old, key_size),
 					      value, false);
 			return 0;
 		}
@@ -1138,7 +1122,7 @@ static long 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;
 
@@ -1156,7 +1140,7 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		 * and update element in place
 		 */
 		copy_map_value_locked(map,
-				      l_old->key + round_up(key_size, 8),
+				      htab_elem_value(l_old, key_size),
 				      value, false);
 		ret = 0;
 		goto err;
@@ -1176,14 +1160,19 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 	hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	if (l_old) {
 		hlist_nulls_del_rcu(&l_old->hash_node);
-		if (!htab_is_prealloc(htab))
-			free_htab_elem(htab, l_old);
-		else
+
+		/* l_old has already been stashed in htab->extra_elems, free
+		 * its special fields before it is available for reuse.
+		 */
+		if (htab_is_prealloc(htab))
 			check_and_free_fields(htab, l_old);
 	}
-	ret = 0;
+	htab_unlock_bucket(b, flags);
+	if (l_old && !htab_is_prealloc(htab))
+		free_htab_elem(htab, l_old);
+	return 0;
 err:
-	htab_unlock_bucket(htab, b, hash, flags);
+	htab_unlock_bucket(b, flags);
 	return ret;
 }
 
@@ -1227,10 +1216,9 @@ static long 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;
-	copy_map_value(&htab->map,
-		       l_new->key + round_up(map->key_size, 8), value);
+	copy_map_value(&htab->map, htab_elem_value(l_new, map->key_size), value);
 
-	ret = htab_lock_bucket(htab, b, hash, &flags);
+	ret = htab_lock_bucket(b, &flags);
 	if (ret)
 		goto err_lock_bucket;
 
@@ -1251,7 +1239,7 @@ static long 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);
 
 err_lock_bucket:
 	if (ret)
@@ -1262,13 +1250,14 @@ err_lock_bucket:
 	return ret;
 }
 
-static long __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
+static long htab_map_update_elem_in_place(struct bpf_map *map, void *key,
 					  void *value, u64 map_flags,
-					  bool onallcpus)
+					  bool percpu, bool onallcpus)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct htab_elem *l_new = NULL, *l_old;
+	struct htab_elem *l_new, *l_old;
 	struct hlist_nulls_head *head;
+	void *old_map_ptr = NULL;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
@@ -1288,7 +1277,7 @@ static long __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;
 
@@ -1299,21 +1288,29 @@ static long __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 		goto err;
 
 	if (l_old) {
-		/* per-cpu hash map can update value in-place */
-		pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
-				value, onallcpus);
+		/* Update value in-place */
+		if (percpu) {
+			pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
+					value, onallcpus);
+		} else {
+			void **inner_map_pptr = htab_elem_value(l_old, key_size);
+
+			old_map_ptr = *inner_map_pptr;
+			WRITE_ONCE(*inner_map_pptr, *(void **)value);
+		}
 	} else {
 		l_new = alloc_htab_elem(htab, key, value, key_size,
-					hash, true, onallcpus, NULL);
+					hash, percpu, onallcpus, NULL);
 		if (IS_ERR(l_new)) {
 			ret = PTR_ERR(l_new);
 			goto err;
 		}
 		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	}
-	ret = 0;
 err:
-	htab_unlock_bucket(htab, b, hash, flags);
+	htab_unlock_bucket(b, flags);
+	if (old_map_ptr)
+		map->ops->map_fd_put_ptr(map, old_map_ptr, true);
 	return ret;
 }
 
@@ -1354,7 +1351,7 @@ static long __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)
 		goto err_lock_bucket;
 
@@ -1378,7 +1375,7 @@ static long __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);
 err_lock_bucket:
 	if (l_new) {
 		bpf_map_dec_elem_count(&htab->map);
@@ -1390,7 +1387,7 @@ err_lock_bucket:
 static long htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 					void *value, u64 map_flags)
 {
-	return __htab_percpu_map_update_elem(map, key, value, map_flags, false);
+	return htab_map_update_elem_in_place(map, key, value, map_flags, true, false);
 }
 
 static long htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
@@ -1420,20 +1417,20 @@ static long 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;
 
 	l = lookup_elem_raw(head, hash, key, key_size);
-
-	if (l) {
+	if (l)
 		hlist_nulls_del_rcu(&l->hash_node);
-		free_htab_elem(htab, l);
-	} else {
+	else
 		ret = -ENOENT;
-	}
 
-	htab_unlock_bucket(htab, b, hash, flags);
+	htab_unlock_bucket(b, flags);
+
+	if (l)
+		free_htab_elem(htab, l);
 	return ret;
 }
 
@@ -1456,7 +1453,7 @@ static long 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;
 
@@ -1467,7 +1464,7 @@ static long 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;
@@ -1477,10 +1474,9 @@ static void delete_all_elements(struct bpf_htab *htab)
 {
 	int i;
 
-	/* It's called from a worker thread, so disable migration here,
-	 * since bpf_mem_cache_free() relies on that.
+	/* It's called from a worker thread and migration has been disabled,
+	 * therefore, it is OK to invoke bpf_mem_cache_free() directly.
 	 */
-	migrate_disable();
 	for (i = 0; i < htab->n_buckets; i++) {
 		struct hlist_nulls_head *head = select_bucket(htab, i);
 		struct hlist_nulls_node *n;
@@ -1490,11 +1486,11 @@ static void delete_all_elements(struct bpf_htab *htab)
 			hlist_nulls_del_rcu(&l->hash_node);
 			htab_elem_free(htab, l);
 		}
+		cond_resched();
 	}
-	migrate_enable();
 }
 
-static void htab_free_malloced_timers(struct bpf_htab *htab)
+static void htab_free_malloced_timers_and_wq(struct bpf_htab *htab)
 {
 	int i;
 
@@ -1506,31 +1502,35 @@ static void htab_free_malloced_timers(struct bpf_htab *htab)
 
 		hlist_nulls_for_each_entry(l, n, head, hash_node) {
 			/* We only free timer on uref dropping to zero */
-			bpf_obj_free_timer(htab->map.record, l->key + round_up(htab->map.key_size, 8));
+			if (btf_record_has_field(htab->map.record, BPF_TIMER))
+				bpf_obj_free_timer(htab->map.record,
+						   htab_elem_value(l, htab->map.key_size));
+			if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE))
+				bpf_obj_free_workqueue(htab->map.record,
+						       htab_elem_value(l, htab->map.key_size));
 		}
 		cond_resched_rcu();
 	}
 	rcu_read_unlock();
 }
 
-static void htab_map_free_timers(struct bpf_map *map)
+static void htab_map_free_timers_and_wq(struct bpf_map *map)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 
-	/* We only free timer on uref dropping to zero */
-	if (!btf_record_has_field(htab->map.record, BPF_TIMER))
-		return;
-	if (!htab_is_prealloc(htab))
-		htab_free_malloced_timers(htab);
-	else
-		htab_free_prealloced_timers(htab);
+	/* We only free timer and workqueue on uref dropping to zero */
+	if (btf_record_has_field(htab->map.record, BPF_TIMER | BPF_WORKQUEUE)) {
+		if (!htab_is_prealloc(htab))
+			htab_free_malloced_timers_and_wq(htab);
+		else
+			htab_free_prealloced_timers_and_wq(htab);
+	}
 }
 
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
 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.
@@ -1538,7 +1538,7 @@ static void htab_map_free(struct bpf_map *map)
 	 */
 
 	/* htab no longer uses call_rcu() directly. bpf_mem_alloc does it
-	 * underneath and is reponsible for waiting for callbacks to finish
+	 * underneath and is responsible for waiting for callbacks to finish
 	 * during bpf_mem_alloc_destroy().
 	 */
 	if (!htab_is_prealloc(htab)) {
@@ -1555,9 +1555,6 @@ static void htab_map_free(struct bpf_map *map)
 	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);
 }
 
@@ -1577,7 +1574,7 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
 	btf_type_seq_show(map->btf, map->btf_key_type_id, key, m);
 	seq_puts(m, ": ");
 	btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
-	seq_puts(m, "\n");
+	seq_putc(m, '\n');
 
 	rcu_read_unlock();
 }
@@ -1600,48 +1597,48 @@ 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;
 
 	l = lookup_elem_raw(head, hash, key, key_size);
 	if (!l) {
 		ret = -ENOENT;
-	} else {
-		if (is_percpu) {
-			u32 roundup_value_size = round_up(map->value_size, 8);
-			void __percpu *pptr;
-			int off = 0, cpu;
+		goto out_unlock;
+	}
 
-			pptr = htab_elem_get_ptr(l, key_size);
-			for_each_possible_cpu(cpu) {
-				copy_map_value_long(&htab->map, value + off, per_cpu_ptr(pptr, cpu));
-				check_and_init_map_value(&htab->map, value + off);
-				off += roundup_value_size;
-			}
-		} else {
-			u32 roundup_key_size = round_up(map->key_size, 8);
+	if (is_percpu) {
+		u32 roundup_value_size = round_up(map->value_size, 8);
+		void __percpu *pptr;
+		int off = 0, cpu;
 
-			if (flags & BPF_F_LOCK)
-				copy_map_value_locked(map, value, l->key +
-						      roundup_key_size,
-						      true);
-			else
-				copy_map_value(map, value, l->key +
-					       roundup_key_size);
-			/* Zeroing special fields in the temp buffer */
-			check_and_init_map_value(map, value);
+		pptr = htab_elem_get_ptr(l, key_size);
+		for_each_possible_cpu(cpu) {
+			copy_map_value_long(&htab->map, value + off, per_cpu_ptr(pptr, cpu));
+			check_and_init_map_value(&htab->map, value + off);
+			off += roundup_value_size;
 		}
+	} else {
+		void *src = htab_elem_value(l, map->key_size);
 
-		hlist_nulls_del_rcu(&l->hash_node);
-		if (!is_lru_map)
-			free_htab_elem(htab, l);
+		if (flags & BPF_F_LOCK)
+			copy_map_value_locked(map, value, src, true);
+		else
+			copy_map_value(map, value, src);
+		/* Zeroing special fields in the temp buffer */
+		check_and_init_map_value(map, value);
 	}
+	hlist_nulls_del_rcu(&l->hash_node);
 
-	htab_unlock_bucket(htab, b, hash, bflags);
+out_unlock:
+	htab_unlock_bucket(b, bflags);
 
-	if (is_lru_map && l)
-		htab_lru_push_free(htab, l);
+	if (l) {
+		if (is_lru_map)
+			htab_lru_push_free(htab, l);
+		else
+			free_htab_elem(htab, l);
+	}
 
 	return ret;
 }
@@ -1684,12 +1681,12 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 				   bool is_percpu)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	u32 bucket_cnt, total, key_size, value_size, roundup_key_size;
 	void *keys = NULL, *values = NULL, *value, *dst_key, *dst_val;
 	void __user *uvalues = u64_to_user_ptr(attr->batch.values);
 	void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
 	void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch);
 	u32 batch, max_count, size, bucket_size, map_id;
+	u32 bucket_cnt, total, key_size, value_size;
 	struct htab_elem *node_to_free = NULL;
 	u64 elem_map_flags, map_flags;
 	struct hlist_nulls_head *head;
@@ -1724,7 +1721,6 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 		return -ENOENT;
 
 	key_size = htab->map.key_size;
-	roundup_key_size = round_up(htab->map.key_size, 8);
 	value_size = htab->map.value_size;
 	size = round_up(value_size, 8);
 	if (is_percpu)
@@ -1756,7 +1752,7 @@ again_nocopy:
 	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();
@@ -1779,7 +1775,7 @@ again_nocopy:
 		/* 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;
@@ -1790,7 +1786,7 @@ again_nocopy:
 		/* 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);
@@ -1816,8 +1812,8 @@ again_nocopy:
 				off += size;
 			}
 		} else {
-			value = l->key + roundup_key_size;
-			if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+			value = htab_elem_value(l, key_size);
+			if (is_fd_htab(htab)) {
 				struct bpf_map **inner_map = value;
 
 				 /* Actual value is the id of the inner map */
@@ -1840,25 +1836,29 @@ again_nocopy:
 			 * may cause deadlock. See comments in function
 			 * prealloc_lru_pop(). Let us do bpf_lru_push_free()
 			 * after releasing the bucket lock.
+			 *
+			 * For htab of maps, htab_put_fd_value() in
+			 * free_htab_elem() may acquire a spinlock with bucket
+			 * lock being held and it violates the lock rule, so
+			 * invoke free_htab_elem() after unlock as well.
 			 */
-			if (is_lru_map) {
-				l->batch_flink = node_to_free;
-				node_to_free = l;
-			} else {
-				free_htab_elem(htab, l);
-			}
+			l->batch_flink = node_to_free;
+			node_to_free = l;
 		}
 		dst_key += key_size;
 		dst_val += value_size;
 	}
 
-	htab_unlock_bucket(htab, b, batch, flags);
+	htab_unlock_bucket(b, flags);
 	locked = false;
 
 	while (node_to_free) {
 		l = node_to_free;
 		node_to_free = node_to_free->batch_flink;
-		htab_lru_push_free(htab, l);
+		if (is_lru_map)
+			htab_lru_push_free(htab, l);
+		else
+			free_htab_elem(htab, l);
 	}
 
 next_batch:
@@ -2063,11 +2063,11 @@ static void *bpf_hash_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 static int __bpf_hash_map_seq_show(struct seq_file *seq, struct htab_elem *elem)
 {
 	struct bpf_iter_seq_hash_map_info *info = seq->private;
-	u32 roundup_key_size, roundup_value_size;
 	struct bpf_iter__bpf_map_elem ctx = {};
 	struct bpf_map *map = info->map;
 	struct bpf_iter_meta meta;
 	int ret = 0, off = 0, cpu;
+	u32 roundup_value_size;
 	struct bpf_prog *prog;
 	void __percpu *pptr;
 
@@ -2077,10 +2077,9 @@ static int __bpf_hash_map_seq_show(struct seq_file *seq, struct htab_elem *elem)
 		ctx.meta = &meta;
 		ctx.map = info->map;
 		if (elem) {
-			roundup_key_size = round_up(map->key_size, 8);
 			ctx.key = elem->key;
 			if (!info->percpu_value_buf) {
-				ctx.value = elem->key + roundup_key_size;
+				ctx.value = htab_elem_value(elem, map->key_size);
 			} else {
 				roundup_value_size = round_up(map->value_size, 8);
 				pptr = htab_elem_get_ptr(elem, map->key_size);
@@ -2165,7 +2164,6 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
 	struct hlist_nulls_head *head;
 	struct hlist_nulls_node *n;
 	struct htab_elem *elem;
-	u32 roundup_key_size;
 	int i, num_elems = 0;
 	void __percpu *pptr;
 	struct bucket *b;
@@ -2173,29 +2171,29 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
 	bool is_percpu;
 	u64 ret = 0;
 
+	cant_migrate();
+
 	if (flags != 0)
 		return -EINVAL;
 
 	is_percpu = htab_is_percpu(htab);
 
-	roundup_key_size = round_up(map->key_size, 8);
-	/* disable migration so percpu value prepared here will be the
-	 * same as the one seen by the bpf program with bpf_map_lookup_elem().
+	/* migration has been disabled, so percpu value prepared here will be
+	 * the same as the one seen by the bpf program with
+	 * bpf_map_lookup_elem().
 	 */
-	if (is_percpu)
-		migrate_disable();
 	for (i = 0; i < htab->n_buckets; i++) {
 		b = &htab->buckets[i];
 		rcu_read_lock();
 		head = &b->head;
-		hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
+		hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) {
 			key = elem->key;
 			if (is_percpu) {
 				/* current cpu value for percpu map */
 				pptr = htab_elem_get_ptr(elem, map->key_size);
 				val = this_cpu_ptr(pptr);
 			} else {
-				val = elem->key + roundup_key_size;
+				val = htab_elem_value(elem, map->key_size);
 			}
 			num_elems++;
 			ret = callback_fn((u64)(long)map, (u64)(long)key,
@@ -2209,8 +2207,6 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
 		rcu_read_unlock();
 	}
 out:
-	if (is_percpu)
-		migrate_enable();
 	return num_elems;
 }
 
@@ -2259,7 +2255,7 @@ 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_release_uref = htab_map_free_timers_and_wq,
 	.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,
@@ -2280,7 +2276,7 @@ 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_release_uref = htab_map_free_timers_and_wq,
 	.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,
@@ -2307,6 +2303,26 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
 		return NULL;
 }
 
+/* inline bpf_map_lookup_elem() call for per-CPU hashmap */
+static int htab_percpu_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	if (!bpf_jit_supports_percpu_insn())
+		return -EOPNOTSUPP;
+
+	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
+		     (void *(*)(struct bpf_map *map, void *key))NULL));
+	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
+	*insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3);
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_0,
+				offsetof(struct htab_elem, key) + roundup(map->key_size, 8));
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0);
+	*insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
+
+	return insn - insn_buf;
+}
+
 static void *htab_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu)
 {
 	struct htab_elem *l;
@@ -2392,8 +2408,8 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
 		ret = __htab_lru_percpu_map_update_elem(map, key, value,
 							map_flags, true);
 	else
-		ret = __htab_percpu_map_update_elem(map, key, value, map_flags,
-						    true);
+		ret = htab_map_update_elem_in_place(map, key, value, map_flags,
+						    true, true);
 	rcu_read_unlock();
 
 	return ret;
@@ -2421,7 +2437,7 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key,
 		seq_printf(m, "\tcpu%d: ", cpu);
 		btf_type_seq_show(map->btf, map->btf_value_type_id,
 				  per_cpu_ptr(pptr, cpu), m);
-		seq_puts(m, "\n");
+		seq_putc(m, '\n');
 	}
 	seq_puts(m, "}\n");
 
@@ -2435,6 +2451,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.map_lookup_elem = htab_percpu_map_lookup_elem,
+	.map_gen_lookup = htab_percpu_map_gen_lookup,
 	.map_lookup_and_delete_elem = htab_percpu_map_lookup_and_delete_elem,
 	.map_update_elem = htab_percpu_map_update_elem,
 	.map_delete_elem = htab_map_delete_elem,
@@ -2516,24 +2533,23 @@ int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value)
 	return ret;
 }
 
-/* only called from syscall */
+/* Only called from syscall */
 int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 				void *key, void *value, u64 map_flags)
 {
 	void *ptr;
 	int ret;
-	u32 ufd = *(u32 *)value;
 
-	ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
+	ptr = map->ops->map_fd_get_ptr(map, map_file, *(int *)value);
 	if (IS_ERR(ptr))
 		return PTR_ERR(ptr);
 
 	/* The htab bucket lock is always held during update operations in fd
 	 * htab map, and the following rcu_read_lock() is only used to avoid
-	 * the WARN_ON_ONCE in htab_map_update_elem().
+	 * the WARN_ON_ONCE in htab_map_update_elem_in_place().
 	 */
 	rcu_read_lock();
-	ret = htab_map_update_elem(map, key, &ptr, map_flags);
+	ret = htab_map_update_elem_in_place(map, key, &ptr, map_flags, false, false);
 	rcu_read_unlock();
 	if (ret)
 		map->ops->map_fd_put_ptr(map, ptr, false);