diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5300954833bd56e6fce5f8449bfb3ea6f16ee4b9..622c88236169e34f7ea25e789acc0a50154d5416 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -64,6 +64,8 @@ struct bpf_map_ops {
 	void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key);
 	int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr,
 				union bpf_attr __user *uattr);
+	int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key,
+					  void *value, u64 flags);
 	int (*map_lookup_and_delete_batch)(struct bpf_map *map,
 					   const union bpf_attr *attr,
 					   union bpf_attr __user *uattr);
@@ -159,6 +161,7 @@ struct bpf_map {
 	u32 value_size;
 	u32 max_entries;
 	u32 map_flags;
+	u64 map_extra; /* any per-map-type extra fields */
 	int spin_lock_off; /* >=0 valid offset, <0 error */
 	u32 id;
 	int numa_node;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index e256d6ef4765bdc34cf8216475d504a1898df8be..4cfa1fc39f30103cdea19ba92f8282cf8abb09d7 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -125,6 +125,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops)
 
 BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint)
 BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f5bf3d62b960f1867b54a2589b7fb3bd739e2e6c..df47f25c5ce9cc7511ea37f6a355800036a6bad3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -158,6 +158,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_RINGBUF,
 	BPF_MAP_TYPE_INODE_STORAGE,
 	BPF_MAP_TYPE_TASK_STORAGE,
+	BPF_MAP_TYPE_BLOOM_FILTER,
 };
 
 /* Note that tracing related programs such as
@@ -503,6 +504,13 @@ union bpf_attr {
 						   * struct stored as the
 						   * map value
 						   */
+		/* Any per-map-type extra fields
+		 *
+		 * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
+		 * number of hash functions (if 0, the bloom filter will default
+		 * to using 5 hash functions).
+		 */
+		__u64	map_extra;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -4499,6 +4507,7 @@ struct bpf_map_info {
 	__u32 btf_id;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
+	__u64 map_extra;
 } __attribute__((aligned(8)));
 
 struct bpf_btf_info {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index d1249340fd6baed87ebfa77e2198aab0265790fb..05593c2b0411703d7b0fd815007f4c800b34f863 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -7,7 +7,7 @@ endif
 CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
-obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
+obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
 obj-${CONFIG_BPF_LSM}	  += bpf_inode_storage.o
 obj-${CONFIG_BPF_LSM}	  += bpf_task_storage.o
diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c
new file mode 100644
index 0000000000000000000000000000000000000000..b141a1346f72dd6d1535fed97f76da97a4a475b3
--- /dev/null
+++ b/kernel/bpf/bloom_filter.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bitmap.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+#include <linux/jhash.h>
+#include <linux/random.h>
+
+#define BLOOM_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK)
+
+struct bpf_bloom_filter {
+	struct bpf_map map;
+	u32 bitset_mask;
+	u32 hash_seed;
+	/* If the size of the values in the bloom filter is u32 aligned,
+	 * then it is more performant to use jhash2 as the underlying hash
+	 * function, else we use jhash. This tracks the number of u32s
+	 * in an u32-aligned value size. If the value size is not u32 aligned,
+	 * this will be 0.
+	 */
+	u32 aligned_u32_count;
+	u32 nr_hash_funcs;
+	unsigned long bitset[];
+};
+
+static u32 hash(struct bpf_bloom_filter *bloom, void *value,
+		u32 value_size, u32 index)
+{
+	u32 h;
+
+	if (bloom->aligned_u32_count)
+		h = jhash2(value, bloom->aligned_u32_count,
+			   bloom->hash_seed + index);
+	else
+		h = jhash(value, value_size, bloom->hash_seed + index);
+
+	return h & bloom->bitset_mask;
+}
+
+static int bloom_map_peek_elem(struct bpf_map *map, void *value)
+{
+	struct bpf_bloom_filter *bloom =
+		container_of(map, struct bpf_bloom_filter, map);
+	u32 i, h;
+
+	for (i = 0; i < bloom->nr_hash_funcs; i++) {
+		h = hash(bloom, value, map->value_size, i);
+		if (!test_bit(h, bloom->bitset))
+			return -ENOENT;
+	}
+
+	return 0;
+}
+
+static int bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags)
+{
+	struct bpf_bloom_filter *bloom =
+		container_of(map, struct bpf_bloom_filter, map);
+	u32 i, h;
+
+	if (flags != BPF_ANY)
+		return -EINVAL;
+
+	for (i = 0; i < bloom->nr_hash_funcs; i++) {
+		h = hash(bloom, value, map->value_size, i);
+		set_bit(h, bloom->bitset);
+	}
+
+	return 0;
+}
+
+static int bloom_map_pop_elem(struct bpf_map *map, void *value)
+{
+	return -EOPNOTSUPP;
+}
+
+static int bloom_map_delete_elem(struct bpf_map *map, void *value)
+{
+	return -EOPNOTSUPP;
+}
+
+static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct bpf_map *bloom_map_alloc(union bpf_attr *attr)
+{
+	u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits;
+	int numa_node = bpf_map_attr_numa_node(attr);
+	struct bpf_bloom_filter *bloom;
+
+	if (!bpf_capable())
+		return ERR_PTR(-EPERM);
+
+	if (attr->key_size != 0 || attr->value_size == 0 ||
+	    attr->max_entries == 0 ||
+	    attr->map_flags & ~BLOOM_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags) ||
+	    /* The lower 4 bits of map_extra (0xF) specify the number
+	     * of hash functions
+	     */
+	    (attr->map_extra & ~0xF))
+		return ERR_PTR(-EINVAL);
+
+	nr_hash_funcs = attr->map_extra;
+	if (nr_hash_funcs == 0)
+		/* Default to using 5 hash functions if unspecified */
+		nr_hash_funcs = 5;
+
+	/* For the bloom filter, the optimal bit array size that minimizes the
+	 * false positive probability is n * k / ln(2) where n is the number of
+	 * expected entries in the bloom filter and k is the number of hash
+	 * functions. We use 7 / 5 to approximate 1 / ln(2).
+	 *
+	 * We round this up to the nearest power of two to enable more efficient
+	 * hashing using bitmasks. The bitmask will be the bit array size - 1.
+	 *
+	 * If this overflows a u32, the bit array size will have 2^32 (4
+	 * GB) bits.
+	 */
+	if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) ||
+	    check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) ||
+	    nr_bits > (1UL << 31)) {
+		/* The bit array size is 2^32 bits but to avoid overflowing the
+		 * u32, we use U32_MAX, which will round up to the equivalent
+		 * number of bytes
+		 */
+		bitset_bytes = BITS_TO_BYTES(U32_MAX);
+		bitset_mask = U32_MAX;
+	} else {
+		if (nr_bits <= BITS_PER_LONG)
+			nr_bits = BITS_PER_LONG;
+		else
+			nr_bits = roundup_pow_of_two(nr_bits);
+		bitset_bytes = BITS_TO_BYTES(nr_bits);
+		bitset_mask = nr_bits - 1;
+	}
+
+	bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long));
+	bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node);
+
+	if (!bloom)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&bloom->map, attr);
+
+	bloom->nr_hash_funcs = nr_hash_funcs;
+	bloom->bitset_mask = bitset_mask;
+
+	/* Check whether the value size is u32-aligned */
+	if ((attr->value_size & (sizeof(u32) - 1)) == 0)
+		bloom->aligned_u32_count =
+			attr->value_size / sizeof(u32);
+
+	if (!(attr->map_flags & BPF_F_ZERO_SEED))
+		bloom->hash_seed = get_random_int();
+
+	return &bloom->map;
+}
+
+static void bloom_map_free(struct bpf_map *map)
+{
+	struct bpf_bloom_filter *bloom =
+		container_of(map, struct bpf_bloom_filter, map);
+
+	bpf_map_area_free(bloom);
+}
+
+static void *bloom_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	/* The eBPF program should use map_peek_elem instead */
+	return ERR_PTR(-EINVAL);
+}
+
+static int bloom_map_update_elem(struct bpf_map *map, void *key,
+				 void *value, u64 flags)
+{
+	/* The eBPF program should use map_push_elem instead */
+	return -EINVAL;
+}
+
+static int bloom_map_check_btf(const struct bpf_map *map,
+			       const struct btf *btf,
+			       const struct btf_type *key_type,
+			       const struct btf_type *value_type)
+{
+	/* Bloom filter maps are keyless */
+	return btf_type_is_void(key_type) ? 0 : -EINVAL;
+}
+
+static int bpf_bloom_map_btf_id;
+const struct bpf_map_ops bloom_filter_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
+	.map_alloc = bloom_map_alloc,
+	.map_free = bloom_map_free,
+	.map_get_next_key = bloom_map_get_next_key,
+	.map_push_elem = bloom_map_push_elem,
+	.map_peek_elem = bloom_map_peek_elem,
+	.map_pop_elem = bloom_map_pop_elem,
+	.map_lookup_elem = bloom_map_lookup_elem,
+	.map_update_elem = bloom_map_update_elem,
+	.map_delete_elem = bloom_map_delete_elem,
+	.map_check_btf = bloom_map_check_btf,
+	.map_btf_name = "bpf_bloom_filter",
+	.map_btf_id = &bpf_bloom_map_btf_id,
+};
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 6c444e815406bd36c70d231c5459634f0fed62ac..cccabeb0f0f1b92706cbc5f925707bdc508173f2 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -86,6 +86,9 @@ struct bucket {
 	};
 };
 
+#define HASHTAB_MAP_LOCK_COUNT 8
+#define HASHTAB_MAP_LOCK_MASK (HASHTAB_MAP_LOCK_COUNT - 1)
+
 struct bpf_htab {
 	struct bpf_map map;
 	struct bucket *buckets;
@@ -99,6 +102,8 @@ 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 */
@@ -136,35 +141,56 @@ static void htab_init_buckets(struct bpf_htab *htab)
 {
 	unsigned i;
 
+	lockdep_register_key(&htab->lockdep_key);
 	for (i = 0; i < htab->n_buckets; i++) {
 		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
-		if (htab_use_raw_lock(htab))
+		if (htab_use_raw_lock(htab)) {
 			raw_spin_lock_init(&htab->buckets[i].raw_lock);
-		else
+			lockdep_set_class(&htab->buckets[i].raw_lock,
+					  &htab->lockdep_key);
+		} else {
 			spin_lock_init(&htab->buckets[i].lock);
+			lockdep_set_class(&htab->buckets[i].lock,
+					  &htab->lockdep_key);
+		}
 	}
 }
 
-static inline unsigned long htab_lock_bucket(const struct bpf_htab *htab,
-					     struct bucket *b)
+static inline int htab_lock_bucket(const struct bpf_htab *htab,
+				   struct bucket *b, u32 hash,
+				   unsigned long *pflags)
 {
 	unsigned long flags;
 
+	hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
+
+	migrate_disable();
+	if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
+		__this_cpu_dec(*(htab->map_locked[hash]));
+		migrate_enable();
+		return -EBUSY;
+	}
+
 	if (htab_use_raw_lock(htab))
 		raw_spin_lock_irqsave(&b->raw_lock, flags);
 	else
 		spin_lock_irqsave(&b->lock, flags);
-	return flags;
+	*pflags = flags;
+
+	return 0;
 }
 
 static inline void htab_unlock_bucket(const struct bpf_htab *htab,
-				      struct bucket *b,
+				      struct bucket *b, u32 hash,
 				      unsigned long flags)
 {
+	hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
 	if (htab_use_raw_lock(htab))
 		raw_spin_unlock_irqrestore(&b->raw_lock, flags);
 	else
 		spin_unlock_irqrestore(&b->lock, flags);
+	__this_cpu_dec(*(htab->map_locked[hash]));
+	migrate_enable();
 }
 
 static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
@@ -422,8 +448,8 @@ 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;
 	u64 cost;
-	int err;
 
 	htab = kzalloc(sizeof(*htab), GFP_USER);
 	if (!htab)
@@ -480,6 +506,13 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	if (!htab->buckets)
 		goto free_charge;
 
+	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) {
+		htab->map_locked[i] = __alloc_percpu_gfp(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
@@ -490,7 +523,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	if (prealloc) {
 		err = prealloc_init(htab);
 		if (err)
-			goto free_buckets;
+			goto free_map_locked;
 
 		if (!percpu && !lru) {
 			/* lru itself can remove the least used element, so
@@ -506,7 +539,9 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 
 free_prealloc:
 	prealloc_destroy(htab);
-free_buckets:
+free_map_locked:
+	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
+		free_percpu(htab->map_locked[i]);
 	bpf_map_area_free(htab->buckets);
 free_charge:
 	bpf_map_charge_finish(&htab->map.memory);
@@ -687,12 +722,15 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 	struct hlist_nulls_node *n;
 	unsigned long flags;
 	struct bucket *b;
+	int ret;
 
 	tgt_l = container_of(node, struct htab_elem, lru_node);
 	b = __select_bucket(htab, tgt_l->hash);
 	head = &b->head;
 
-	flags = htab_lock_bucket(htab, b);
+	ret = htab_lock_bucket(htab, b, tgt_l->hash, &flags);
+	if (ret)
+		return false;
 
 	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		if (l == tgt_l) {
@@ -700,7 +738,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 			break;
 		}
 
-	htab_unlock_bucket(htab, b, flags);
+	htab_unlock_bucket(htab, b, tgt_l->hash, flags);
 
 	return l == tgt_l;
 }
@@ -998,7 +1036,9 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		 */
 	}
 
-	flags = htab_lock_bucket(htab, b);
+	ret = htab_lock_bucket(htab, b, hash, &flags);
+	if (ret)
+		return ret;
 
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 
@@ -1039,7 +1079,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 	}
 	ret = 0;
 err:
-	htab_unlock_bucket(htab, b, flags);
+	htab_unlock_bucket(htab, b, hash, flags);
 	return ret;
 }
 
@@ -1077,7 +1117,9 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -ENOMEM;
 	memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size);
 
-	flags = htab_lock_bucket(htab, b);
+	ret = htab_lock_bucket(htab, b, hash, &flags);
+	if (ret)
+		return ret;
 
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 
@@ -1096,7 +1138,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 	ret = 0;
 
 err:
-	htab_unlock_bucket(htab, b, flags);
+	htab_unlock_bucket(htab, b, hash, flags);
 
 	if (ret)
 		bpf_lru_push_free(&htab->lru, &l_new->lru_node);
@@ -1131,7 +1173,9 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	flags = htab_lock_bucket(htab, b);
+	ret = htab_lock_bucket(htab, b, hash, &flags);
+	if (ret)
+		return ret;
 
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 
@@ -1154,7 +1198,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 	}
 	ret = 0;
 err:
-	htab_unlock_bucket(htab, b, flags);
+	htab_unlock_bucket(htab, b, hash, flags);
 	return ret;
 }
 
@@ -1194,7 +1238,9 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 			return -ENOMEM;
 	}
 
-	flags = htab_lock_bucket(htab, b);
+	ret = htab_lock_bucket(htab, b, hash, &flags);
+	if (ret)
+		return ret;
 
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 
@@ -1216,7 +1262,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 	}
 	ret = 0;
 err:
-	htab_unlock_bucket(htab, b, flags);
+	htab_unlock_bucket(htab, b, hash, flags);
 	if (l_new)
 		bpf_lru_push_free(&htab->lru, &l_new->lru_node);
 	return ret;
@@ -1244,7 +1290,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 	struct htab_elem *l;
 	unsigned long flags;
 	u32 hash, key_size;
-	int ret = -ENOENT;
+	int ret;
 
 	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
@@ -1254,17 +1300,20 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	flags = htab_lock_bucket(htab, b);
+	ret = htab_lock_bucket(htab, b, hash, &flags);
+	if (ret)
+		return ret;
 
 	l = lookup_elem_raw(head, hash, key, key_size);
 
 	if (l) {
 		hlist_nulls_del_rcu(&l->hash_node);
 		free_htab_elem(htab, l);
-		ret = 0;
+	} else {
+		ret = -ENOENT;
 	}
 
-	htab_unlock_bucket(htab, b, flags);
+	htab_unlock_bucket(htab, b, hash, flags);
 	return ret;
 }
 
@@ -1276,7 +1325,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 	struct htab_elem *l;
 	unsigned long flags;
 	u32 hash, key_size;
-	int ret = -ENOENT;
+	int ret;
 
 	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
@@ -1286,16 +1335,18 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	flags = htab_lock_bucket(htab, b);
+	ret = htab_lock_bucket(htab, b, hash, &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);
-		ret = 0;
-	}
+	else
+		ret = -ENOENT;
 
-	htab_unlock_bucket(htab, b, flags);
+	htab_unlock_bucket(htab, b, hash, flags);
 	if (l)
 		bpf_lru_push_free(&htab->lru, &l->lru_node);
 	return ret;
@@ -1321,6 +1372,7 @@ static void delete_all_elements(struct bpf_htab *htab)
 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.
@@ -1338,6 +1390,9 @@ static void htab_map_free(struct bpf_map *map)
 
 	free_percpu(htab->extra_elems);
 	bpf_map_area_free(htab->buckets);
+	lockdep_unregister_key(&htab->lockdep_key);
+	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
+		free_percpu(htab->map_locked[i]);
 	kfree(htab);
 }
 
@@ -1362,6 +1417,100 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
+static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+					     void *value, bool is_lru_map,
+					     bool is_percpu, u64 flags)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_nulls_head *head;
+	unsigned long bflags;
+	struct htab_elem *l;
+	u32 hash, key_size;
+	struct bucket *b;
+	int ret;
+
+	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, &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;
+
+			pptr = htab_elem_get_ptr(l, key_size);
+			for_each_possible_cpu(cpu) {
+				bpf_long_memcpy(value + off,
+						per_cpu_ptr(pptr, cpu),
+						roundup_value_size);
+				off += roundup_value_size;
+			}
+		} else {
+			u32 roundup_key_size = round_up(map->key_size, 8);
+
+			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);
+			check_and_init_map_lock(map, value);
+		}
+
+		hlist_nulls_del_rcu(&l->hash_node);
+		if (!is_lru_map)
+			free_htab_elem(htab, l);
+	}
+
+	htab_unlock_bucket(htab, b, hash, bflags);
+
+	if (is_lru_map && l)
+		bpf_lru_push_free(&htab->lru, &l->lru_node);
+
+	return ret;
+}
+
+static int htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+					   void *value, u64 flags)
+{
+	return __htab_map_lookup_and_delete_elem(map, key, value, false, false,
+						 flags);
+}
+
+static int htab_percpu_map_lookup_and_delete_elem(struct bpf_map *map,
+						  void *key, void *value,
+						  u64 flags)
+{
+	return __htab_map_lookup_and_delete_elem(map, key, value, false, true,
+						 flags);
+}
+
+static int htab_lru_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+					       void *value, u64 flags)
+{
+	return __htab_map_lookup_and_delete_elem(map, key, value, true, false,
+						 flags);
+}
+
+static int htab_lru_percpu_map_lookup_and_delete_elem(struct bpf_map *map,
+						      void *key, void *value,
+						      u64 flags)
+{
+	return __htab_map_lookup_and_delete_elem(map, key, value, true, true,
+						 flags);
+}
+
 static int
 __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 				   const union bpf_attr *attr,
@@ -1441,8 +1590,14 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 	b = &htab->buckets[batch];
 	head = &b->head;
 	/* do not grab the lock unless need it (bucket_cnt > 0). */
-	if (locked)
-		flags = htab_lock_bucket(htab, b);
+	if (locked) {
+		ret = htab_lock_bucket(htab, b, batch, &flags);
+		if (ret) {
+			rcu_read_unlock();
+			bpf_enable_instrumentation();
+			goto after_loop;
+		}
+	}
 
 	bucket_cnt = 0;
 	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
@@ -1459,7 +1614,7 @@ __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, flags);
+		htab_unlock_bucket(htab, b, batch, flags);
 		rcu_read_unlock();
 		bpf_enable_instrumentation();
 		goto after_loop;
@@ -1470,7 +1625,7 @@ __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, flags);
+		htab_unlock_bucket(htab, b, batch, flags);
 		rcu_read_unlock();
 		bpf_enable_instrumentation();
 		kvfree(keys);
@@ -1523,7 +1678,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 		dst_val += value_size;
 	}
 
-	htab_unlock_bucket(htab, b, flags);
+	htab_unlock_bucket(htab, b, batch, flags);
 	locked = false;
 
 	while (node_to_free) {
@@ -1835,6 +1990,7 @@ 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,
@@ -1853,6 +2009,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.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,
 	.map_update_elem = htab_lru_map_update_elem,
 	.map_delete_elem = htab_lru_map_delete_elem,
@@ -1974,6 +2131,7 @@ 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_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,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
@@ -1991,6 +2149,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.map_lookup_elem = htab_lru_percpu_map_lookup_elem,
+	.map_lookup_and_delete_elem = htab_lru_percpu_map_lookup_and_delete_elem,
 	.map_update_elem = htab_lru_percpu_map_update_elem,
 	.map_delete_elem = htab_lru_map_delete_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 20160386c7fb2fc0f1ae1b057686526c373d94cf..da57b0322c1ef66015434cff0dbb13d7bd4f6b31 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -210,7 +210,8 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key,
 		err = bpf_fd_reuseport_array_update_elem(map, key, value,
 							 flags);
 	} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
-		   map->map_type == BPF_MAP_TYPE_STACK) {
+		   map->map_type == BPF_MAP_TYPE_STACK ||
+		   map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
 		err = map->ops->map_push_elem(map, value, flags);
 	} else {
 		rcu_read_lock();
@@ -249,7 +250,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
 	} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
 		err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
-		   map->map_type == BPF_MAP_TYPE_STACK) {
+		   map->map_type == BPF_MAP_TYPE_STACK ||
+		   map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
 		err = map->ops->map_peek_elem(map, value);
 	} else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
 		/* struct_ops map requires directly updating "value" */
@@ -355,6 +357,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
 	map->max_entries = attr->max_entries;
 	map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags);
 	map->numa_node = bpf_map_attr_numa_node(attr);
+	map->map_extra = attr->map_extra;
 }
 
 static int bpf_charge_memlock(struct user_struct *user, u32 pages)
@@ -563,6 +566,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   "value_size:\t%u\n"
 		   "max_entries:\t%u\n"
 		   "map_flags:\t%#x\n"
+		   "map_extra:\t%#llx\n"
 		   "memlock:\t%llu\n"
 		   "map_id:\t%u\n"
 		   "frozen:\t%u\n",
@@ -571,6 +575,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   map->value_size,
 		   map->max_entries,
 		   map->map_flags,
+		   (unsigned long long)map->map_extra,
 		   map->memory.pages * 1ULL << PAGE_SHIFT,
 		   map->id,
 		   READ_ONCE(map->frozen));
@@ -803,7 +808,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	return ret;
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id
+#define BPF_MAP_CREATE_LAST_FIELD map_extra
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
@@ -825,6 +830,10 @@ static int map_create(union bpf_attr *attr)
 		return -EINVAL;
 	}
 
+	if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER &&
+	    attr->map_extra != 0)
+		return -EINVAL;
+
 	f_flags = bpf_get_file_flag(attr->map_flags);
 	if (f_flags < 0)
 		return f_flags;
@@ -1057,6 +1066,14 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (!value)
 		goto free_key;
 
+	if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
+		if (copy_from_user(value, uvalue, value_size))
+			err = -EFAULT;
+		else
+			err = bpf_map_copy_value(map, key, value, attr->flags);
+		goto free_value;
+	}
+
 	err = bpf_map_copy_value(map, key, value, attr->flags);
 	if (err)
 		goto free_value;
@@ -1481,7 +1498,7 @@ int generic_map_lookup_batch(struct bpf_map *map,
 	return err;
 }
 
-#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value
+#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags
 
 static int map_lookup_and_delete_elem(union bpf_attr *attr)
 {
@@ -1497,6 +1514,9 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM))
 		return -EINVAL;
 
+	if (attr->flags & ~BPF_F_LOCK)
+		return -EINVAL;
+
 	f = fdget(ufd);
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
@@ -1508,24 +1528,47 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
+	if (attr->flags &&
+	    (map->map_type == BPF_MAP_TYPE_QUEUE ||
+	     map->map_type == BPF_MAP_TYPE_STACK)) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
+	if ((attr->flags & BPF_F_LOCK) &&
+	    !map_value_has_spin_lock(map)) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
 	key = __bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
 		goto err_put;
 	}
 
-	value_size = map->value_size;
+	value_size = bpf_map_value_size(map);
 
 	err = -ENOMEM;
 	value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
 	if (!value)
 		goto free_key;
 
+	err = -ENOTSUPP;
 	if (map->map_type == BPF_MAP_TYPE_QUEUE ||
 	    map->map_type == BPF_MAP_TYPE_STACK) {
 		err = map->ops->map_pop_elem(map, value);
-	} else {
-		err = -ENOTSUPP;
+	} else if (map->map_type == BPF_MAP_TYPE_HASH ||
+		   map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+		   map->map_type == BPF_MAP_TYPE_LRU_HASH ||
+		   map->map_type == BPF_MAP_TYPE_LRU_PERCPU_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, attr->flags);
+			rcu_read_unlock();
+			bpf_enable_instrumentation();
+		}
 	}
 
 	if (err)
@@ -3712,6 +3755,7 @@ static int bpf_map_get_info_by_fd(struct file *file,
 	info.value_size = map->value_size;
 	info.max_entries = map->max_entries;
 	info.map_flags = map->map_flags;
+	info.map_extra = map->map_extra;
 	memcpy(info.name, map->name, sizeof(map->name));
 
 	if (map->btf) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d8ec405ce4bfe15db930f9a19d536eeec66d448f..707b9e8c208486444f5a87530f433005e1ee8dca 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4313,7 +4313,10 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 			return -EINVAL;
 		}
 		break;
-
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		if (meta->func_id == BPF_FUNC_map_peek_elem)
+			*arg_type = ARG_PTR_TO_MAP_VALUE;
+		break;
 	default:
 		break;
 	}
@@ -4828,6 +4831,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_task_storage_delete)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		if (func_id != BPF_FUNC_map_peek_elem &&
+		    func_id != BPF_FUNC_map_push_elem)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -4895,13 +4903,18 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    map->map_type != BPF_MAP_TYPE_SOCKHASH)
 			goto error;
 		break;
-	case BPF_FUNC_map_peek_elem:
 	case BPF_FUNC_map_pop_elem:
-	case BPF_FUNC_map_push_elem:
 		if (map->map_type != BPF_MAP_TYPE_QUEUE &&
 		    map->map_type != BPF_MAP_TYPE_STACK)
 			goto error;
 		break;
+	case BPF_FUNC_map_peek_elem:
+	case BPF_FUNC_map_push_elem:
+		if (map->map_type != BPF_MAP_TYPE_QUEUE &&
+		    map->map_type != BPF_MAP_TYPE_STACK &&
+		    map->map_type != BPF_MAP_TYPE_BLOOM_FILTER)
+			goto error;
+		break;
 	case BPF_FUNC_sk_storage_get:
 	case BPF_FUNC_sk_storage_delete:
 		if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b481addbd92adc4b3f1510866f5812ab213e4f1a..81a23646a8e0ed1b0c12650ed9aea839c224e4a8 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -158,6 +158,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_RINGBUF,
 	BPF_MAP_TYPE_INODE_STORAGE,
 	BPF_MAP_TYPE_TASK_STORAGE,
+	BPF_MAP_TYPE_BLOOM_FILTER,
 };
 
 /* Note that tracing related programs such as
@@ -503,6 +504,13 @@ union bpf_attr {
 						   * struct stored as the
 						   * map value
 						   */
+		/* Any per-map-type extra fields
+		 *
+		 * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
+		 * number of hash functions (if 0, the bloom filter will default
+		 * to using 5 hash functions).
+		 */
+		__u64	map_extra;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -4499,6 +4507,7 @@ struct bpf_map_info {
 	__u32 btf_id;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
+	__u64 map_extra;
 } __attribute__((aligned(8)));
 
 struct bpf_btf_info {
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index d27e34133973b52e1152c955fbaac831feeeecc0..a3009cd60878f314f89fef0c7b5759eb64031803 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -76,7 +76,7 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
 	return fd;
 }
 
-int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
+int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr)
 {
 	union bpf_attr attr;
 
@@ -100,10 +100,35 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 			create_attr->btf_vmlinux_value_type_id;
 	else
 		attr.inner_map_fd = create_attr->inner_map_fd;
+	attr.map_extra = create_attr->map_extra;
 
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
+int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
+{
+	struct bpf_create_map_params p = {};
+
+	p.map_type = create_attr->map_type;
+	p.key_size = create_attr->key_size;
+	p.value_size = create_attr->value_size;
+	p.max_entries = create_attr->max_entries;
+	p.map_flags = create_attr->map_flags;
+	p.name = create_attr->name;
+	p.numa_node = create_attr->numa_node;
+	p.btf_fd = create_attr->btf_fd;
+	p.btf_key_type_id = create_attr->btf_key_type_id;
+	p.btf_value_type_id = create_attr->btf_value_type_id;
+	p.map_ifindex = create_attr->map_ifindex;
+	if (p.map_type == BPF_MAP_TYPE_STRUCT_OPS)
+		p.btf_vmlinux_value_type_id =
+			create_attr->btf_vmlinux_value_type_id;
+	else
+		p.inner_map_fd = create_attr->inner_map_fd;
+
+	return libbpf__bpf_create_map_xattr(&p);
+}
+
 int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
 			int key_size, int value_size, int max_entries,
 			__u32 map_flags, int node)
@@ -418,6 +443,19 @@ int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
 	return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
 }
 
+int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags)
+{
+	union bpf_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+	attr.flags = flags;
+
+	return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+}
+
 int bpf_map_delete_elem(int fd, const void *key)
 {
 	union bpf_attr attr;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 875dde20d56e325c4b173fdbb0e5f0b91aa8b39c..4f758f8f50cd730bd21f78bf30c33d73af6b994c 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -124,6 +124,8 @@ LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value,
 					 __u64 flags);
 LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
 					      void *value);
+LIBBPF_API int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key,
+						    void *value, __u64 flags);
 LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_map_freeze(int fd);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 3e52e5a3f4c7ad1841553909f01603f01fd7afeb..2552dae4519747e5702c0379f77b3c54f5c80fc2 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -355,6 +355,7 @@ struct bpf_map {
 	char *pin_path;
 	bool pinned;
 	bool reused;
+	__u64 map_extra;
 };
 
 enum extern_type {
@@ -2193,6 +2194,14 @@ static int parse_btf_map_def(struct bpf_object *obj,
 					return err;
 				}
 			}
+		} else if (strcmp(name, "map_extra") == 0) {
+			__u32 map_extra;
+
+			if (!get_map_field_int(map->name, obj->btf, m, &map_extra))
+				return -EINVAL;
+			pr_debug("map '%s': found map_extra = 0x%llx.\n", map->name,
+				(unsigned long long)map_extra);
+			map->map_extra = map_extra;
 		} else {
 			if (strict) {
 				pr_warn("map '%s': unknown field '%s'.\n",
@@ -3698,6 +3707,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 	map->btf_key_type_id = info.btf_key_type_id;
 	map->btf_value_type_id = info.btf_value_type_id;
 	map->reused = true;
+	map->map_extra = info.map_extra;
 
 	return 0;
 
@@ -4090,7 +4100,8 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
 		map_info.key_size == map->def.key_size &&
 		map_info.value_size == map->def.value_size &&
 		map_info.max_entries == map->def.max_entries &&
-		map_info.map_flags == map->def.map_flags);
+		map_info.map_flags == map->def.map_flags &&
+		map_info.map_extra == map->map_extra);
 }
 
 static int
@@ -4166,7 +4177,7 @@ static void bpf_map__destroy(struct bpf_map *map);
 
 static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 {
-	struct bpf_create_map_attr create_attr;
+	struct bpf_create_map_params create_attr;
 	struct bpf_map_def *def = &map->def;
 	int err = 0;
 
@@ -4180,6 +4191,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 	create_attr.key_size = def->key_size;
 	create_attr.value_size = def->value_size;
 	create_attr.numa_node = map->numa_node;
+	create_attr.map_extra = map->map_extra;
 
 	if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) {
 		int nr_cpus;
@@ -4223,7 +4235,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 			create_attr.inner_map_fd = map->inner_map_fd;
 	}
 
-	map->fd = bpf_create_map_xattr(&create_attr);
+	map->fd = libbpf__bpf_create_map_xattr(&create_attr);
 	if (map->fd < 0 && (create_attr.btf_key_type_id ||
 			    create_attr.btf_value_type_id)) {
 		char *cp, errmsg[STRERR_BUFSIZE];
@@ -4237,7 +4249,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 		create_attr.btf_value_type_id = 0;
 		map->btf_key_type_id = 0;
 		map->btf_value_type_id = 0;
-		map->fd = bpf_create_map_xattr(&create_attr);
+		map->fd = libbpf__bpf_create_map_xattr(&create_attr);
 	}
 
 	err = map->fd < 0 ? -errno : 0;
@@ -8855,6 +8867,19 @@ int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags)
 	return 0;
 }
 
+__u64 bpf_map__map_extra(const struct bpf_map *map)
+{
+	return map->map_extra;
+}
+
+int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra)
+{
+	if (map->fd >= 0)
+		return -EBUSY;
+	map->map_extra = map_extra;
+	return 0;
+}
+
 __u32 bpf_map__numa_node(const struct bpf_map *map)
 {
 	return map->numa_node;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 57d10b779dea019e05a218a8f0e965b84988088c..0208f1e5c5d4c7c7e0a56050021a68ffa5e0eca0 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -463,6 +463,9 @@ LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
 /* get/set map if_index */
 LIBBPF_API __u32 bpf_map__ifindex(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
+/* get/set map map_extra flags */
+LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map);
+LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra);
 
 typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 4ebfadf45b47d27a3e66bb23aac6d90767df67ed..06b6eb2c113c2f4791cdf265e2503aafc3351bbe 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -337,3 +337,20 @@ LIBBPF_0.2.0 {
 		perf_buffer__consume_buffer;
 		xsk_socket__create_shared;
 } LIBBPF_0.1.0;
+
+LIBBPF_0.3.0 {
+} LIBBPF_0.2.0;
+
+LIBBPF_0.4.0 {
+} LIBBPF_0.3.0;
+
+LIBBPF_0.5.0 {
+	global:
+		bpf_map_lookup_and_delete_elem_flags;
+} LIBBPF_0.4.0;
+
+LIBBPF_0.6.0 {
+	global:
+		bpf_map__map_extra;
+		bpf_map__set_map_extra;
+} LIBBPF_0.5.0;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index d99bc847bf84577eda8e21209a5946da04dc2b1a..8bf152688ddc5ea6c66a2defa044dcf0408a428e 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -156,6 +156,27 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name,
 int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
 				__u32 *off);
 
+struct bpf_create_map_params {
+	const char *name;
+	enum bpf_map_type map_type;
+	__u32 map_flags;
+	__u32 key_size;
+	__u32 value_size;
+	__u32 max_entries;
+	__u32 numa_node;
+	__u32 btf_fd;
+	__u32 btf_key_type_id;
+	__u32 btf_value_type_id;
+	__u32 map_ifindex;
+	union {
+		__u32 inner_map_fd;
+		__u32 btf_vmlinux_value_type_id;
+	};
+	__u64 map_extra;
+};
+
+int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr);
+
 struct btf_ext_info {
 	/*
 	 * info points to the individual info section (e.g. func_info and
diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
new file mode 100644
index 0000000000000000000000000000000000000000..6a946e3043dfb7c5916b977bb6ca4505c4e694ef
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include "bloom_filter_map.skel.h"
+
+static void test_fail_cases(void)
+{
+	__u32 value;
+	int fd, err;
+
+	/* Invalid key size */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 4, sizeof(value), 100, 0);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid key size"))
+		close(fd);
+
+	/* Invalid value size */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, 0, 100, 0);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid value size 0"))
+		close(fd);
+
+	/* Invalid max entries size */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 0, 0);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid max entries size"))
+		close(fd);
+
+	/* Bloom filter maps do not support BPF_F_NO_PREALLOC */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100,
+			    BPF_F_NO_PREALLOC);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid flags"))
+		close(fd);
+
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100, 0);
+	if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter"))
+		return;
+
+	/* Test invalid flags */
+	err = bpf_map_update_elem(fd, NULL, &value, -1);
+	err = err < 0 ? -errno : err;
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, BPF_EXIST);
+	err = err < 0 ? -errno : err;
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, BPF_F_LOCK);
+	err = err < 0 ? -errno : err;
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, BPF_NOEXIST);
+	err = err < 0 ? -errno : err;
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, 10000);
+	err = err < 0 ? -errno : err;
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	close(fd);
+}
+
+static void test_success_cases(void)
+{
+	char value[11];
+	int fd, err;
+
+	/* Create a map */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100,
+			    BPF_F_ZERO_SEED | BPF_F_NUMA_NODE);
+	if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter success case"))
+		return;
+
+	/* Add a value to the bloom filter */
+	err = bpf_map_update_elem(fd, NULL, &value, 0);
+	if (!ASSERT_OK(err, "bpf_map_update_elem bloom filter success case"))
+		goto done;
+
+	 /* Lookup a value in the bloom filter */
+	err = bpf_map_lookup_elem(fd, NULL, &value);
+	ASSERT_OK(err, "bpf_map_update_elem bloom filter success case");
+
+done:
+	close(fd);
+}
+
+static void check_bloom(struct bloom_filter_map *skel)
+{
+	struct bpf_link *link;
+
+	link = bpf_program__attach(skel->progs.check_bloom);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->error, 0, "error");
+
+	bpf_link__destroy(link);
+}
+
+static void test_inner_map(struct bloom_filter_map *skel, const __u32 *rand_vals,
+			   __u32 nr_rand_vals)
+{
+	int outer_map_fd, inner_map_fd, err, i, key = 0;
+	struct bpf_link *link;
+
+	/* Create a bloom filter map that will be used as the inner map */
+	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(*rand_vals),
+				      nr_rand_vals, 0);
+	if (!ASSERT_GE(inner_map_fd, 0, "bpf_create_map bloom filter inner map"))
+		return;
+
+	for (i = 0; i < nr_rand_vals; i++) {
+		err = bpf_map_update_elem(inner_map_fd, NULL, rand_vals + i, BPF_ANY);
+		if (!ASSERT_OK(err, "Add random value to inner_map_fd"))
+			goto done;
+	}
+
+	/* Add the bloom filter map to the outer map */
+	outer_map_fd = bpf_map__fd(skel->maps.outer_map);
+	err = bpf_map_update_elem(outer_map_fd, &key, &inner_map_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "Add bloom filter map to outer map"))
+		goto done;
+
+	/* Attach the bloom_filter_inner_map prog */
+	link = bpf_program__attach(skel->progs.inner_map);
+	if (!ASSERT_OK_PTR(link, "link"))
+		goto delete_inner_map;
+
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->error, 0, "error");
+
+	bpf_link__destroy(link);
+
+delete_inner_map:
+	/* Ensure the inner bloom filter map can be deleted */
+	err = bpf_map_delete_elem(outer_map_fd, &key);
+	ASSERT_OK(err, "Delete inner bloom filter map");
+
+done:
+	close(inner_map_fd);
+}
+
+static int setup_progs(struct bloom_filter_map **out_skel, __u32 **out_rand_vals,
+		       __u32 *out_nr_rand_vals)
+{
+	struct bloom_filter_map *skel;
+	int random_data_fd, bloom_fd;
+	__u32 *rand_vals = NULL;
+	__u32 map_size, val;
+	int err, i;
+
+	/* Set up a bloom filter map skeleton */
+	skel = bloom_filter_map__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bloom_filter_map__open_and_load"))
+		return -EINVAL;
+
+	/* Set up rand_vals */
+	map_size = bpf_map__max_entries(skel->maps.map_random_data);
+	rand_vals = malloc(sizeof(*rand_vals) * map_size);
+	if (!rand_vals) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	/* Generate random values and populate both skeletons */
+	random_data_fd = bpf_map__fd(skel->maps.map_random_data);
+	bloom_fd = bpf_map__fd(skel->maps.map_bloom);
+	for (i = 0; i < map_size; i++) {
+		val = rand();
+
+		err = bpf_map_update_elem(random_data_fd, &i, &val, BPF_ANY);
+		if (!ASSERT_OK(err, "Add random value to map_random_data"))
+			goto error;
+
+		err = bpf_map_update_elem(bloom_fd, NULL, &val, BPF_ANY);
+		if (!ASSERT_OK(err, "Add random value to map_bloom"))
+			goto error;
+
+		rand_vals[i] = val;
+	}
+
+	*out_skel = skel;
+	*out_rand_vals = rand_vals;
+	*out_nr_rand_vals = map_size;
+
+	return 0;
+
+error:
+	bloom_filter_map__destroy(skel);
+	if (rand_vals)
+		free(rand_vals);
+	return err;
+}
+
+void test_bloom_filter_map(void)
+{
+	__u32 *rand_vals, nr_rand_vals;
+	struct bloom_filter_map *skel;
+	int err;
+
+	test_fail_cases();
+	test_success_cases();
+
+	err = setup_progs(&skel, &rand_vals, &nr_rand_vals);
+	if (err)
+		return;
+
+	test_inner_map(skel, rand_vals, nr_rand_vals);
+	free(rand_vals);
+
+	check_bloom(skel);
+
+	bloom_filter_map__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/lookup_and_delete.c b/tools/testing/selftests/bpf/prog_tests/lookup_and_delete.c
new file mode 100644
index 0000000000000000000000000000000000000000..beebfa9730e1c09a282836d404aa87a0e8c507fc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lookup_and_delete.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <test_progs.h>
+#include "test_lookup_and_delete.skel.h"
+
+#define START_VALUE 1234
+#define NEW_VALUE 4321
+#define MAX_ENTRIES 2
+
+static int duration;
+static int nr_cpus;
+
+static int fill_values(int map_fd)
+{
+	__u64 key, value = START_VALUE;
+	int err;
+
+	for (key = 1; key < MAX_ENTRIES + 1; key++) {
+		err = bpf_map_update_elem(map_fd, &key, &value, BPF_NOEXIST);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			return -1;
+	}
+
+	return 0;
+}
+
+static int fill_values_percpu(int map_fd)
+{
+	__u64 key, value[nr_cpus];
+	int i, err;
+
+	for (i = 0; i < nr_cpus; i++)
+		value[i] = START_VALUE;
+
+	for (key = 1; key < MAX_ENTRIES + 1; key++) {
+		err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			return -1;
+	}
+
+	return 0;
+}
+
+static struct test_lookup_and_delete *setup_prog(enum bpf_map_type map_type,
+						 int *map_fd)
+{
+	struct test_lookup_and_delete *skel;
+	int err;
+
+	skel = test_lookup_and_delete__open();
+	if (!ASSERT_OK_PTR(skel, "test_lookup_and_delete__open"))
+		return NULL;
+
+	err = bpf_map__set_type(skel->maps.hash_map, map_type);
+	if (!ASSERT_OK(err, "bpf_map__set_type"))
+		goto cleanup;
+
+	err = bpf_map__set_max_entries(skel->maps.hash_map, MAX_ENTRIES);
+	if (!ASSERT_OK(err, "bpf_map__set_max_entries"))
+		goto cleanup;
+
+	err = test_lookup_and_delete__load(skel);
+	if (!ASSERT_OK(err, "test_lookup_and_delete__load"))
+		goto cleanup;
+
+	*map_fd = bpf_map__fd(skel->maps.hash_map);
+	if (!ASSERT_GE(*map_fd, 0, "bpf_map__fd"))
+		goto cleanup;
+
+	return skel;
+
+cleanup:
+	test_lookup_and_delete__destroy(skel);
+	return NULL;
+}
+
+/* Triggers BPF program that updates map with given key and value */
+static int trigger_tp(struct test_lookup_and_delete *skel, __u64 key,
+		      __u64 value)
+{
+	int err;
+
+	skel->bss->set_pid = getpid();
+	skel->bss->set_key = key;
+	skel->bss->set_value = value;
+
+	err = test_lookup_and_delete__attach(skel);
+	if (!ASSERT_OK(err, "test_lookup_and_delete__attach"))
+		return -1;
+
+	syscall(__NR_getpgid);
+
+	test_lookup_and_delete__detach(skel);
+
+	return 0;
+}
+
+static void test_lookup_and_delete_hash(void)
+{
+	struct test_lookup_and_delete *skel;
+	__u64 key, value;
+	int map_fd, err;
+
+	/* Setup program and fill the map. */
+	skel = setup_prog(BPF_MAP_TYPE_HASH, &map_fd);
+	if (!ASSERT_OK_PTR(skel, "setup_prog"))
+		return;
+
+	err = fill_values(map_fd);
+	if (!ASSERT_OK(err, "fill_values"))
+		goto cleanup;
+
+	/* Lookup and delete element. */
+	key = 1;
+	err = bpf_map_lookup_and_delete_elem(map_fd, &key, &value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem"))
+		goto cleanup;
+
+	/* Fetched value should match the initially set value. */
+	if (CHECK(value != START_VALUE, "bpf_map_lookup_and_delete_elem",
+		  "unexpected value=%lld\n", value))
+		goto cleanup;
+
+	/* Check that the entry is non existent. */
+	err = bpf_map_lookup_elem(map_fd, &key, &value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+cleanup:
+	test_lookup_and_delete__destroy(skel);
+}
+
+static void test_lookup_and_delete_percpu_hash(void)
+{
+	struct test_lookup_and_delete *skel;
+	__u64 key, val, value[nr_cpus];
+	int map_fd, err, i;
+
+	/* Setup program and fill the map. */
+	skel = setup_prog(BPF_MAP_TYPE_PERCPU_HASH, &map_fd);
+	if (!ASSERT_OK_PTR(skel, "setup_prog"))
+		return;
+
+	err = fill_values_percpu(map_fd);
+	if (!ASSERT_OK(err, "fill_values_percpu"))
+		goto cleanup;
+
+	/* Lookup and delete element. */
+	key = 1;
+	err = bpf_map_lookup_and_delete_elem(map_fd, &key, value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem"))
+		goto cleanup;
+
+	for (i = 0; i < nr_cpus; i++) {
+		val = value[i];
+
+		/* Fetched value should match the initially set value. */
+		if (CHECK(val != START_VALUE, "map value",
+			  "unexpected for cpu %d: %lld\n", i, val))
+			goto cleanup;
+	}
+
+	/* Check that the entry is non existent. */
+	err = bpf_map_lookup_elem(map_fd, &key, value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+cleanup:
+	test_lookup_and_delete__destroy(skel);
+}
+
+static void test_lookup_and_delete_lru_hash(void)
+{
+	struct test_lookup_and_delete *skel;
+	__u64 key, value;
+	int map_fd, err;
+
+	/* Setup program and fill the LRU map. */
+	skel = setup_prog(BPF_MAP_TYPE_LRU_HASH, &map_fd);
+	if (!ASSERT_OK_PTR(skel, "setup_prog"))
+		return;
+
+	err = fill_values(map_fd);
+	if (!ASSERT_OK(err, "fill_values"))
+		goto cleanup;
+
+	/* Insert new element at key=3, should reuse LRU element. */
+	key = 3;
+	err = trigger_tp(skel, key, NEW_VALUE);
+	if (!ASSERT_OK(err, "trigger_tp"))
+		goto cleanup;
+
+	/* Lookup and delete element 3. */
+	err = bpf_map_lookup_and_delete_elem(map_fd, &key, &value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem"))
+		goto cleanup;
+
+	/* Value should match the new value. */
+	if (CHECK(value != NEW_VALUE, "bpf_map_lookup_and_delete_elem",
+		  "unexpected value=%lld\n", value))
+		goto cleanup;
+
+	/* Check that entries 3 and 1 are non existent. */
+	err = bpf_map_lookup_elem(map_fd, &key, &value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+	key = 1;
+	err = bpf_map_lookup_elem(map_fd, &key, &value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+cleanup:
+	test_lookup_and_delete__destroy(skel);
+}
+
+static void test_lookup_and_delete_lru_percpu_hash(void)
+{
+	struct test_lookup_and_delete *skel;
+	__u64 key, val, value[nr_cpus];
+	int map_fd, err, i, cpucnt = 0;
+
+	/* Setup program and fill the LRU map. */
+	skel = setup_prog(BPF_MAP_TYPE_LRU_PERCPU_HASH, &map_fd);
+	if (!ASSERT_OK_PTR(skel, "setup_prog"))
+		return;
+
+	err = fill_values_percpu(map_fd);
+	if (!ASSERT_OK(err, "fill_values_percpu"))
+		goto cleanup;
+
+	/* Insert new element at key=3, should reuse LRU element 1. */
+	key = 3;
+	err = trigger_tp(skel, key, NEW_VALUE);
+	if (!ASSERT_OK(err, "trigger_tp"))
+		goto cleanup;
+
+	/* Clean value. */
+	for (i = 0; i < nr_cpus; i++)
+		value[i] = 0;
+
+	/* Lookup and delete element 3. */
+	err = bpf_map_lookup_and_delete_elem(map_fd, &key, value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem")) {
+		goto cleanup;
+	}
+
+	/* Check if only one CPU has set the value. */
+	for (i = 0; i < nr_cpus; i++) {
+		val = value[i];
+		if (val) {
+			if (CHECK(val != NEW_VALUE, "map value",
+				  "unexpected for cpu %d: %lld\n", i, val))
+				goto cleanup;
+			cpucnt++;
+		}
+	}
+	if (CHECK(cpucnt != 1, "map value", "set for %d CPUs instead of 1!\n",
+		  cpucnt))
+		goto cleanup;
+
+	/* Check that entries 3 and 1 are non existent. */
+	err = bpf_map_lookup_elem(map_fd, &key, &value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+	key = 1;
+	err = bpf_map_lookup_elem(map_fd, &key, &value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+cleanup:
+	test_lookup_and_delete__destroy(skel);
+}
+
+void test_lookup_and_delete(void)
+{
+	nr_cpus = bpf_num_possible_cpus();
+
+	if (test__start_subtest("lookup_and_delete"))
+		test_lookup_and_delete_hash();
+	if (test__start_subtest("lookup_and_delete_percpu"))
+		test_lookup_and_delete_percpu_hash();
+	if (test__start_subtest("lookup_and_delete_lru"))
+		test_lookup_and_delete_lru_hash();
+	if (test__start_subtest("lookup_and_delete_lru_percpu"))
+		test_lookup_and_delete_lru_percpu_hash();
+}
diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_map.c b/tools/testing/selftests/bpf/progs/bloom_filter_map.c
new file mode 100644
index 0000000000000000000000000000000000000000..5286af5f8aa12480203d5ce16b16798d7b7961ce
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bloom_filter_map.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_map;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 1000);
+} map_random_data SEC(".maps");
+
+struct map_bloom_type {
+	__uint(type, BPF_MAP_TYPE_BLOOM_FILTER);
+	__type(value, __u32);
+	__uint(max_entries, 10000);
+	__uint(map_extra, 5);
+} map_bloom SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct map_bloom_type);
+} outer_map SEC(".maps");
+
+int error = 0;
+
+static void check_elem(struct bpf_map *map)
+{
+	int err, i, key, *map_random_val;
+
+	for (i = 0; i < 1000; i++) {
+		key = i;
+		map_random_val = bpf_map_lookup_elem(&map_random_data, &key);
+		if (!map_random_val) {
+			error |= 2;
+			return;
+		}
+		err = bpf_map_peek_elem(map, map_random_val);
+		if (err) {
+			error |= 1;
+			return;
+		}
+	}
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int inner_map(void *ctx)
+{
+	struct bpf_map *inner_map;
+	int key = 0;
+
+	inner_map = bpf_map_lookup_elem(&outer_map, &key);
+	if (!inner_map) {
+		error |= 2;
+		return 0;
+	}
+
+	check_elem(inner_map);
+
+	return 0;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int check_bloom(void *ctx)
+{
+	check_elem(&map_bloom);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c b/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c
new file mode 100644
index 0000000000000000000000000000000000000000..3a193f42c7e75c3dfd22df8c35bbe6969a443228
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+__u32 set_pid = 0;
+__u64 set_key = 0;
+__u64 set_value = 0;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 2);
+	__type(key, __u64);
+	__type(value, __u64);
+} hash_map SEC(".maps");
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int bpf_lookup_and_delete_test(const void *ctx)
+{
+	if (set_pid == bpf_get_current_pid_tgid() >> 32)
+		bpf_map_update_elem(&hash_map, &set_key, &set_value, BPF_NOEXIST);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index 6a5349f9eb148eebea296425ec7a000c8f5b8a7d..7e9049fa3edfe18bb9a5906b9e288f54c39739da 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -231,6 +231,14 @@ static void test_lru_sanity0(int map_type, int map_flags)
 	assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 &&
 	       errno == ENOENT);
 
+	/* lookup elem key=1 and delete it, then check it doesn't exist */
+	key = 1;
+	assert(!bpf_map_lookup_and_delete_elem(lru_map_fd, &key, &value));
+	assert(value[0] == 1234);
+
+	/* remove the same element from the expected map */
+	assert(!bpf_map_delete_elem(expected_map_fd, &key));
+
 	assert(map_equal(lru_map_fd, expected_map_fd));
 
 	close(expected_map_fd);
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 179e680e8d134a7ab6086d8a695ac626e51f56e4..c9f395f109886b9e47e257614db7ccc4ac8caa4b 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/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);
 
@@ -166,6 +173,16 @@ static void test_hashmap_percpu(unsigned int task, void *data)
 	/* Insert key=1 element. */
 	assert(!(expected_key_mask & key));
 	assert(bpf_map_update_elem(fd, &key, value, BPF_ANY) == 0);
+
+	/* Lookup and delete elem key=1 and check value. */
+	assert(bpf_map_lookup_and_delete_elem(fd, &key, value) == 0 &&
+	       bpf_percpu(value,0) == 100);
+
+	for (i = 0; i < nr_cpus; i++)
+		bpf_percpu(value,i) = i + 100;
+
+	/* Insert key=1 element which should not exist. */
+	assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == 0);
 	expected_key_mask |= key;
 
 	/* BPF_NOEXIST means add new element if it doesn't exist. */
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 238f5f61189eed07ce76d5c3b41134fa60972620..91ca714ef1d50c84dc44497aa773f5ec716462d3 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -141,6 +141,50 @@ extern int test__join_cgroup(const char *path);
 	___ok;								\
 })
 
+#define ASSERT_LT(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act < ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld >= expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
+#define ASSERT_LE(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act <= ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld > expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
+#define ASSERT_GT(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act > ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld <= expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
+#define ASSERT_GE(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act >= ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld < expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
 #define ASSERT_STREQ(actual, expected, name) ({				\
 	static int duration = 0;					\
 	const char *___act = actual;					\