4 files changed, 121 insertions, 9 deletions

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 94c7f77ecb6b..da5639a5bd3b 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -12,6 +12,9 @@
 
 static atomic_t cache_idx;
 
+#define SK_STORAGE_CREATE_FLAG_MASK					\
+	(BPF_F_NO_PREALLOC | BPF_F_CLONE)
+
 struct bucket {
 	struct hlist_head list;
 	raw_spinlock_t lock;
@@ -209,7 +212,6 @@ static void selem_unlink_sk(struct bpf_sk_storage_elem *selem)
 		kfree_rcu(sk_storage, rcu);
 }
 
-/* sk_storage->lock must be held and sk_storage->list cannot be empty */
 static void __selem_link_sk(struct bpf_sk_storage *sk_storage,
 			    struct bpf_sk_storage_elem *selem)
 {
@@ -509,7 +511,7 @@ static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
 	return 0;
 }
 
-/* Called by __sk_destruct() */
+/* Called by __sk_destruct() & bpf_sk_storage_clone() */
 void bpf_sk_storage_free(struct sock *sk)
 {
 	struct bpf_sk_storage_elem *selem;
@@ -557,6 +559,11 @@ static void bpf_sk_storage_map_free(struct bpf_map *map)
 
 	smap = (struct bpf_sk_storage_map *)map;
 
+	/* Note that this map might be concurrently cloned from
+	 * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
+	 * RCU read section to finish before proceeding. New RCU
+	 * read sections should be prevented via bpf_map_inc_not_zero.
+	 */
 	synchronize_rcu();
 
 	/* bpf prog and the userspace can no longer access this map
@@ -601,7 +608,9 @@ static void bpf_sk_storage_map_free(struct bpf_map *map)
 
 static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
 {
-	if (attr->map_flags != BPF_F_NO_PREALLOC || attr->max_entries ||
+	if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK ||
+	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
+	    attr->max_entries ||
 	    attr->key_size != sizeof(int) || !attr->value_size ||
 	    /* Enforce BTF for userspace sk dumping */
 	    !attr->btf_key_type_id || !attr->btf_value_type_id)
@@ -739,6 +748,95 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
 	return err;
 }
 
+static struct bpf_sk_storage_elem *
+bpf_sk_storage_clone_elem(struct sock *newsk,
+			  struct bpf_sk_storage_map *smap,
+			  struct bpf_sk_storage_elem *selem)
+{
+	struct bpf_sk_storage_elem *copy_selem;
+
+	copy_selem = selem_alloc(smap, newsk, NULL, true);
+	if (!copy_selem)
+		return NULL;
+
+	if (map_value_has_spin_lock(&smap->map))
+		copy_map_value_locked(&smap->map, SDATA(copy_selem)->data,
+				      SDATA(selem)->data, true);
+	else
+		copy_map_value(&smap->map, SDATA(copy_selem)->data,
+			       SDATA(selem)->data);
+
+	return copy_selem;
+}
+
+int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
+{
+	struct bpf_sk_storage *new_sk_storage = NULL;
+	struct bpf_sk_storage *sk_storage;
+	struct bpf_sk_storage_elem *selem;
+	int ret = 0;
+
+	RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL);
+
+	rcu_read_lock();
+	sk_storage = rcu_dereference(sk->sk_bpf_storage);
+
+	if (!sk_storage || hlist_empty(&sk_storage->list))
+		goto out;
+
+	hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) {
+		struct bpf_sk_storage_elem *copy_selem;
+		struct bpf_sk_storage_map *smap;
+		struct bpf_map *map;
+
+		smap = rcu_dereference(SDATA(selem)->smap);
+		if (!(smap->map.map_flags & BPF_F_CLONE))
+			continue;
+
+		/* Note that for lockless listeners adding new element
+		 * here can race with cleanup in bpf_sk_storage_map_free.
+		 * Try to grab map refcnt to make sure that it's still
+		 * alive and prevent concurrent removal.
+		 */
+		map = bpf_map_inc_not_zero(&smap->map, false);
+		if (IS_ERR(map))
+			continue;
+
+		copy_selem = bpf_sk_storage_clone_elem(newsk, smap, selem);
+		if (!copy_selem) {
+			ret = -ENOMEM;
+			bpf_map_put(map);
+			goto out;
+		}
+
+		if (new_sk_storage) {
+			selem_link_map(smap, copy_selem);
+			__selem_link_sk(new_sk_storage, copy_selem);
+		} else {
+			ret = sk_storage_alloc(newsk, smap, copy_selem);
+			if (ret) {
+				kfree(copy_selem);
+				atomic_sub(smap->elem_size,
+					   &newsk->sk_omem_alloc);
+				bpf_map_put(map);
+				goto out;
+			}
+
+			new_sk_storage = rcu_dereference(copy_selem->sk_storage);
+		}
+		bpf_map_put(map);
+	}
+
+out:
+	rcu_read_unlock();
+
+	/* In case of an error, don't free anything explicitly here, the
+	 * caller is responsible to call bpf_sk_storage_free.
+	 */
+
+	return ret;
+}
+
 BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 	   void *, value, u64, flags)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index 49589ed2018d..b1afafee3e2a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8126,12 +8126,15 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		bpf_chk = generic_xdp_install;
 
 	if (fd >= 0) {
+		u32 prog_id;
+
 		if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) {
 			NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time");
 			return -EEXIST;
 		}
-		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
-		    __dev_xdp_query(dev, bpf_op, query)) {
+
+		prog_id = __dev_xdp_query(dev, bpf_op, query);
+		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && prog_id) {
 			NL_SET_ERR_MSG(extack, "XDP program already attached");
 			return -EBUSY;
 		}
@@ -8146,6 +8149,14 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			bpf_prog_put(prog);
 			return -EINVAL;
 		}
+
+		if (prog->aux->id == prog_id) {
+			bpf_prog_put(prog);
+			return 0;
+		}
+	} else {
+		if (!__dev_xdp_query(dev, bpf_op, query))
+			return 0;
 	}
 
 	err = dev_xdp_install(dev, bpf_op, extack, flags, prog);
diff --git a/net/core/filter.c b/net/core/filter.c
index b91988f8b94e..ed6563622ce3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5903,7 +5903,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
 	default:
 		return -EPROTONOSUPPORT;
 	}
-	if (mss <= 0)
+	if (mss == 0)
 		return -ENOENT;
 
 	return cookie | ((u64)mss << 32);
diff --git a/net/core/sock.c b/net/core/sock.c
index 545fac19a711..07863edbe6fc 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1851,9 +1851,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 			goto out;
 		}
 		RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL);
-#ifdef CONFIG_BPF_SYSCALL
-		RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL);
-#endif
+
+		if (bpf_sk_storage_clone(sk, newsk)) {
+			sk_free_unlock_clone(newsk);
+			newsk = NULL;
+			goto out;
+		}
 
 		newsk->sk_err	   = 0;
 		newsk->sk_err_soft = 0;