Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts.

Adjacent changes:

drivers/net/ethernet/intel/igc/igc_main.c
  06b412589eef ("igc: Add lock to safeguard global Qbv variables")
  d3750076d464 ("igc: Add TransmissionOverrun counter")

drivers/net/ethernet/microsoft/mana/mana_en.c
  a7dfeda6fdec ("net: mana: Fix MANA VF unload when hardware is unresponsive")
  a9ca9f9ceff3 ("page_pool: split types and declarations from page_pool.h")
  92272ec4107e ("eth: add missing xdp.h includes in drivers")

net/mptcp/protocol.h
  511b90e39250 ("mptcp: fix disconnect vs accept race")
  b8dc6d6ce931 ("mptcp: fix rcv buffer auto-tuning")

tools/testing/selftests/net/mptcp/mptcp_join.sh
  c8c101ae390a ("selftests: mptcp: join: fix 'implicit EP' test")
  03668c65d153 ("selftests: mptcp: join: rework detailed report")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

28 files changed, 634 insertions, 336 deletions

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index e40aa3e3641c..b3662119ddbc 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -384,8 +384,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			dev->name);
 		vlan_vid_add(dev, htons(ETH_P_8021Q), 0);
 	}
-	if (event == NETDEV_DOWN &&
-	    (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+	if (event == NETDEV_DOWN)
 		vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
 
 	vlan_info = rtnl_dereference(dev->vlan_info);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 11c04e7d928e..658a6f2320cf 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -3334,17 +3334,24 @@ static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq)
 	int ret;
 
 	dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
-	ret = wait_for_completion_interruptible(&lreq->reg_commit_wait);
+	ret = wait_for_completion_killable(&lreq->reg_commit_wait);
 	return ret ?: lreq->reg_commit_error;
 }
 
-static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq)
+static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq,
+				     unsigned long timeout)
 {
-	int ret;
+	long left;
 
 	dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
-	ret = wait_for_completion_interruptible(&lreq->notify_finish_wait);
-	return ret ?: lreq->notify_finish_error;
+	left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait,
+						ceph_timeout_jiffies(timeout));
+	if (left <= 0)
+		left = left ?: -ETIMEDOUT;
+	else
+		left = lreq->notify_finish_error; /* completed */
+
+	return left;
 }
 
 /*
@@ -4896,7 +4903,8 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc,
 	linger_submit(lreq);
 	ret = linger_reg_commit_wait(lreq);
 	if (!ret)
-		ret = linger_notify_finish_wait(lreq);
+		ret = linger_notify_finish_wait(lreq,
+				 msecs_to_jiffies(2 * timeout * MSEC_PER_SEC));
 	else
 		dout("lreq %p failed to initiate notify %d\n", lreq, ret);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 7c37f4646c20..a094694899c9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4116,12 +4116,6 @@ BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset)
 	if (unlikely(data_end > data_hard_end))
 		return -EINVAL;
 
-	/* ALL drivers MUST init xdp->frame_sz, chicken check below */
-	if (unlikely(xdp->frame_sz > PAGE_SIZE)) {
-		WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz);
-		return -EINVAL;
-	}
-
 	if (unlikely(data_end < xdp->data + ETH_HLEN))
 		return -EINVAL;
 
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index e6dfc846018f..a0659fc29bcc 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1120,13 +1120,19 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 
 int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
 {
+	int ret;
+
 	static const struct strp_callbacks cb = {
 		.rcv_msg	= sk_psock_strp_read,
 		.read_sock_done	= sk_psock_strp_read_done,
 		.parse_msg	= sk_psock_strp_parse,
 	};
 
-	return strp_init(&psock->strp, sk, &cb);
+	ret = strp_init(&psock->strp, sk, &cb);
+	if (!ret)
+		sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED);
+
+	return ret;
 }
 
 void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
@@ -1154,7 +1160,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 static void sk_psock_done_strp(struct sk_psock *psock)
 {
 	/* Parser has been stopped */
-	if (psock->progs.stream_parser)
+	if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED))
 		strp_done(&psock->strp);
 }
 #else
diff --git a/net/core/sock.c b/net/core/sock.c
index 51f7d94eccf7..525619776c6f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1779,7 +1779,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		spin_unlock(&sk->sk_peer_lock);
 
 		if (!peer_pid)
-			return -ESRCH;
+			return -ENODATA;
 
 		pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file);
 		put_pid(peer_pid);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 08ab108206bf..8f07fea39d9e 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -146,13 +146,13 @@ static void sock_map_del_link(struct sock *sk,
 	list_for_each_entry_safe(link, tmp, &psock->link, list) {
 		if (link->link_raw == link_raw) {
 			struct bpf_map *map = link->map;
-			struct bpf_stab *stab = container_of(map, struct bpf_stab,
-							     map);
-			if (psock->saved_data_ready && stab->progs.stream_parser)
+			struct sk_psock_progs *progs = sock_map_progs(map);
+
+			if (psock->saved_data_ready && progs->stream_parser)
 				strp_stop = true;
-			if (psock->saved_data_ready && stab->progs.stream_verdict)
+			if (psock->saved_data_ready && progs->stream_verdict)
 				verdict_stop = true;
-			if (psock->saved_data_ready && stab->progs.skb_verdict)
+			if (psock->saved_data_ready && progs->skb_verdict)
 				verdict_stop = true;
 			list_del(&link->list);
 			sk_psock_free_link(link);
diff --git a/net/dccp/output.c b/net/dccp/output.c
index b8a24734385e..fd2eb148d24d 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -187,7 +187,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu)
 
 	/* And store cached results */
 	icsk->icsk_pmtu_cookie = pmtu;
-	dp->dccps_mss_cache = cur_mps;
+	WRITE_ONCE(dp->dccps_mss_cache, cur_mps);
 
 	return cur_mps;
 }
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index f331e5977a84..4e3266e4d7c3 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -630,7 +630,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
 		return dccp_getsockopt_service(sk, len,
 					       (__be32 __user *)optval, optlen);
 	case DCCP_SOCKOPT_GET_CUR_MPS:
-		val = dp->dccps_mss_cache;
+		val = READ_ONCE(dp->dccps_mss_cache);
 		break;
 	case DCCP_SOCKOPT_AVAILABLE_CCIDS:
 		return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen);
@@ -739,7 +739,7 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	trace_dccp_probe(sk, len);
 
-	if (len > dp->dccps_mss_cache)
+	if (len > READ_ONCE(dp->dccps_mss_cache))
 		return -EMSGSIZE;
 
 	lock_sock(sk);
@@ -772,6 +772,12 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		goto out_discard;
 	}
 
+	/* We need to check dccps_mss_cache after socket is locked. */
+	if (len > dp->dccps_mss_cache) {
+		rc = -EMSGSIZE;
+		goto out_discard;
+	}
+
 	skb_reserve(skb, sk->sk_prot->max_header);
 	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc != 0)
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 92c02c886fe7..586b1b3e35b8 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -224,7 +224,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu)
 		.un.frag.__unused	= 0,
 		.un.frag.mtu		= htons(mtu),
 	};
-	icmph->checksum = ip_compute_csum(icmph, len);
+	icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0));
 	skb_reset_transport_header(skb);
 
 	niph = skb_push(skb, sizeof(*niph));
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 93f14d39fef6..09d36bcbd7d4 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -3244,13 +3244,9 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb)
 				     &rtm_dump_nexthop_cb, &filter);
 	if (err < 0) {
 		if (likely(skb->len))
-			goto out;
-		goto out_err;
+			err = skb->len;
 	}
 
-out:
-	err = skb->len;
-out_err:
 	cb->seq = net->nexthop.seq;
 	nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 	return err;
@@ -3390,25 +3386,19 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb,
 		    dd->filter.res_bucket_nh_id != nhge->nh->id)
 			continue;
 
+		dd->ctx->bucket_index = bucket_index;
 		err = nh_fill_res_bucket(skb, nh, bucket, bucket_index,
 					 RTM_NEWNEXTHOPBUCKET, portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					 cb->extack);
-		if (err < 0) {
-			if (likely(skb->len))
-				goto out;
-			goto out_err;
-		}
+		if (err)
+			return err;
 	}
 
 	dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1;
-	bucket_index = 0;
+	dd->ctx->bucket_index = 0;
 
-out:
-	err = skb->len;
-out_err:
-	dd->ctx->bucket_index = bucket_index;
-	return err;
+	return 0;
 }
 
 static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb,
@@ -3457,13 +3447,9 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb,
 
 	if (err < 0) {
 		if (likely(skb->len))
-			goto out;
-		goto out_err;
+			err = skb->len;
 	}
 
-out:
-	err = skb->len;
-out_err:
 	cb->seq = net->nexthop.seq;
 	nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 	return err;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index c394799be38f..553c8664e0a7 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -197,7 +197,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
 static inline int ndisc_is_useropt(const struct net_device *dev,
 				   struct nd_opt_hdr *opt)
 {
-	return opt->nd_opt_type == ND_OPT_RDNSS ||
+	return opt->nd_opt_type == ND_OPT_PREFIX_INFO ||
+		opt->nd_opt_type == ND_OPT_RDNSS ||
 		opt->nd_opt_type == ND_OPT_DNSSL ||
 		opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL ||
 		opt->nd_opt_type == ND_OPT_PREF64 ||
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 1c079e83481e..48e649fe2360 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2334,7 +2334,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 
 	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
 
-	if (flags & MPTCP_CF_FASTCLOSE) {
+	if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) {
 		/* be sure to force the tcp_disconnect() path,
 		 * to generate the egress reset
 		 */
@@ -3327,7 +3327,7 @@ static void mptcp_release_cb(struct sock *sk)
 
 	if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags))
 		__mptcp_clean_una_wakeup(sk);
-	if (unlikely(&msk->cb_flags)) {
+	if (unlikely(msk->cb_flags)) {
 		/* be sure to set the current sk state before tacking actions
 		 * depending on sk_state, that is processing MPTCP_ERROR_REPORT
 		 */
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 795f422e8597..79fc5cdb67bc 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -326,7 +326,6 @@ struct mptcp_sock {
 	u32		subflow_id;
 	u32		setsockopt_seq;
 	char		ca_name[TCP_CA_NAME_MAX];
-	struct mptcp_sock	*dl_next;
 };
 
 #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index ad7080fabb2f..9bf3c7bc1762 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1793,16 +1793,31 @@ static void subflow_state_change(struct sock *sk)
 void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
 {
 	struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
-	struct mptcp_sock *msk, *next, *head = NULL;
-	struct request_sock *req;
-	struct sock *sk;
+	struct request_sock *req, *head, *tail;
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk, *ssk;
 
-	/* build a list of all unaccepted mptcp sockets */
+	/* Due to lock dependencies no relevant lock can be acquired under rskq_lock.
+	 * Splice the req list, so that accept() can not reach the pending ssk after
+	 * the listener socket is released below.
+	 */
 	spin_lock_bh(&queue->rskq_lock);
-	for (req = queue->rskq_accept_head; req; req = req->dl_next) {
-		struct mptcp_subflow_context *subflow;
-		struct sock *ssk = req->sk;
+	head = queue->rskq_accept_head;
+	tail = queue->rskq_accept_tail;
+	queue->rskq_accept_head = NULL;
+	queue->rskq_accept_tail = NULL;
+	spin_unlock_bh(&queue->rskq_lock);
+
+	if (!head)
+		return;
 
+	/* can't acquire the msk socket lock under the subflow one,
+	 * or will cause ABBA deadlock
+	 */
+	release_sock(listener_ssk);
+
+	for (req = head; req; req = req->dl_next) {
+		ssk = req->sk;
 		if (!sk_is_mptcp(ssk))
 			continue;
 
@@ -1810,32 +1825,10 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s
 		if (!subflow || !subflow->conn)
 			continue;
 
-		/* skip if already in list */
 		sk = subflow->conn;
-		msk = mptcp_sk(sk);
-		if (msk->dl_next || msk == head)
-			continue;
-
 		sock_hold(sk);
-		msk->dl_next = head;
-		head = msk;
-	}
-	spin_unlock_bh(&queue->rskq_lock);
-	if (!head)
-		return;
-
-	/* can't acquire the msk socket lock under the subflow one,
-	 * or will cause ABBA deadlock
-	 */
-	release_sock(listener_ssk);
-
-	for (msk = head; msk; msk = next) {
-		sk = (struct sock *)msk;
 
 		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
-		next = msk->dl_next;
-		msk->dl_next = NULL;
-
 		__mptcp_unaccepted_force_close(sk);
 		release_sock(sk);
 
@@ -1859,6 +1852,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s
 
 	/* we are still under the listener msk socket lock */
 	lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING);
+
+	/* restore the listener queue, to let the TCP code clean it up */
+	spin_lock_bh(&queue->rskq_lock);
+	WARN_ON_ONCE(queue->rskq_accept_head);
+	queue->rskq_accept_head = head;
+	queue->rskq_accept_tail = tail;
+	spin_unlock_bh(&queue->rskq_lock);
 }
 
 static int subflow_ulp_init(struct sock *sk)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index d3c6ecd1f5a6..c62227ae7746 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -31,7 +31,9 @@ static LIST_HEAD(nf_tables_expressions);
 static LIST_HEAD(nf_tables_objects);
 static LIST_HEAD(nf_tables_flowtables);
 static LIST_HEAD(nf_tables_destroy_list);
+static LIST_HEAD(nf_tables_gc_list);
 static DEFINE_SPINLOCK(nf_tables_destroy_list_lock);
+static DEFINE_SPINLOCK(nf_tables_gc_list_lock);
 
 enum {
 	NFT_VALIDATE_SKIP	= 0,
@@ -120,6 +122,9 @@ static void nft_validate_state_update(struct nft_table *table, u8 new_validate_s
 static void nf_tables_trans_destroy_work(struct work_struct *w);
 static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work);
 
+static void nft_trans_gc_work(struct work_struct *work);
+static DECLARE_WORK(trans_gc_work, nft_trans_gc_work);
+
 static void nft_ctx_init(struct nft_ctx *ctx,
 			 struct net *net,
 			 const struct sk_buff *skb,
@@ -582,10 +587,6 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
 	return __nft_trans_set_add(ctx, msg_type, set, NULL);
 }
 
-static void nft_setelem_data_deactivate(const struct net *net,
-					const struct nft_set *set,
-					struct nft_set_elem *elem);
-
 static int nft_mapelem_deactivate(const struct nft_ctx *ctx,
 				  struct nft_set *set,
 				  const struct nft_set_iter *iter,
@@ -5055,6 +5056,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 
 	INIT_LIST_HEAD(&set->bindings);
 	INIT_LIST_HEAD(&set->catchall_list);
+	refcount_set(&set->refs, 1);
 	set->table = table;
 	write_pnet(&set->net, net);
 	set->ops = ops;
@@ -5122,6 +5124,14 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx,
 	}
 }
 
+static void nft_set_put(struct nft_set *set)
+{
+	if (refcount_dec_and_test(&set->refs)) {
+		kfree(set->name);
+		kvfree(set);
+	}
+}
+
 static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
 {
 	int i;
@@ -5134,8 +5144,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
 
 	set->ops->destroy(ctx, set);
 	nft_set_catchall_destroy(ctx, set);
-	kfree(set->name);
-	kvfree(set);
+	nft_set_put(set);
 }
 
 static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info,
@@ -5602,8 +5611,12 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
 				  const struct nft_set_iter *iter,
 				  struct nft_set_elem *elem)
 {
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	struct nft_set_dump_args *args;
 
+	if (nft_set_elem_expired(ext))
+		return 0;
+
 	args = container_of(iter, struct nft_set_dump_args, iter);
 	return nf_tables_fill_setelem(args->skb, set, elem, args->reset);
 }
@@ -6274,7 +6287,8 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net,
 	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
 		if (nft_set_elem_active(ext, genmask) &&
-		    !nft_set_elem_expired(ext))
+		    !nft_set_elem_expired(ext) &&
+		    !nft_set_elem_is_dead(ext))
 			return ext;
 	}
 
@@ -6282,29 +6296,6 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net,
 }
 EXPORT_SYMBOL_GPL(nft_set_catchall_lookup);
 
-void *nft_set_catchall_gc(const struct nft_set *set)
-{
-	struct nft_set_elem_catchall *catchall, *next;
-	struct nft_set_ext *ext;
-	void *elem = NULL;
-
-	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
-		ext = nft_set_elem_ext(set, catchall->elem);
-
-		if (!nft_set_elem_expired(ext) ||
-		    nft_set_elem_mark_busy(ext))
-			continue;
-
-		elem = catchall->elem;
-		list_del_rcu(&catchall->list);
-		kfree_rcu(catchall, rcu);
-		break;
-	}
-
-	return elem;
-}
-EXPORT_SYMBOL_GPL(nft_set_catchall_gc);
-
 static int nft_setelem_catchall_insert(const struct net *net,
 				       struct nft_set *set,
 				       const struct nft_set_elem *elem,
@@ -6366,7 +6357,6 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set,
 
 	if (nft_setelem_is_catchall(set, elem)) {
 		nft_set_elem_change_active(net, set, ext);
-		nft_set_elem_clear_busy(ext);
 	} else {
 		set->ops->activate(net, set, elem);
 	}
@@ -6381,8 +6371,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net,
 
 	list_for_each_entry(catchall, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
-		if (!nft_is_active(net, ext) ||
-		    nft_set_elem_mark_busy(ext))
+		if (!nft_is_active(net, ext))
 			continue;
 
 		kfree(elem->priv);
@@ -6777,7 +6766,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		goto err_elem_free;
 	}
 
-	ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK;
+	ext->genmask = nft_genmask_cur(ctx->net);
 
 	err = nft_setelem_insert(ctx->net, set, &elem, &ext2, flags);
 	if (err) {
@@ -6929,9 +6918,9 @@ static void nft_setelem_data_activate(const struct net *net,
 		nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use);
 }
 
-static void nft_setelem_data_deactivate(const struct net *net,
-					const struct nft_set *set,
-					struct nft_set_elem *elem)
+void nft_setelem_data_deactivate(const struct net *net,
+				 const struct nft_set *set,
+				 struct nft_set_elem *elem)
 {
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 
@@ -7095,8 +7084,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx,
 
 	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
-		if (!nft_set_elem_active(ext, genmask) ||
-		    nft_set_elem_mark_busy(ext))
+		if (!nft_set_elem_active(ext, genmask))
 			continue;
 
 		elem.priv = catchall->elem;
@@ -7170,29 +7158,6 @@ static int nf_tables_delsetelem(struct sk_buff *skb,
 	return err;
 }
 
-void nft_set_gc_batch_release(struct rcu_head *rcu)
-{
-	struct nft_set_gc_batch *gcb;
-	unsigned int i;
-
-	gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu);
-	for (i = 0; i < gcb->head.cnt; i++)
-		nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true);
-	kfree(gcb);
-}
-
-struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set,
-						gfp_t gfp)
-{
-	struct nft_set_gc_batch *gcb;
-
-	gcb = kzalloc(sizeof(*gcb), gfp);
-	if (gcb == NULL)
-		return gcb;
-	gcb->head.set = set;
-	return gcb;
-}
-
 /*
  * Stateful objects
  */
@@ -9414,6 +9379,207 @@ void nft_chain_del(struct nft_chain *chain)
 	list_del_rcu(&chain->list);
 }
 
+static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx,
+					struct nft_trans_gc *trans)
+{
+	void **priv = trans->priv;
+	unsigned int i;
+
+	for (i = 0; i < trans->count; i++) {
+		struct nft_set_elem elem = {
+			.priv = priv[i],
+		};
+
+		nft_setelem_data_deactivate(ctx->net, trans->set, &elem);
+		nft_setelem_remove(ctx->net, trans->set, &elem);
+	}
+}
+
+void nft_trans_gc_destroy(struct nft_trans_gc *trans)
+{
+	nft_set_put(trans->set);
+	put_net(trans->net);
+	kfree(trans);
+}
+
+static void nft_trans_gc_trans_free(struct rcu_head *rcu)
+{
+	struct nft_set_elem elem = {};
+	struct nft_trans_gc *trans;
+	struct nft_ctx ctx = {};
+	unsigned int i;
+
+	trans = container_of(rcu, struct nft_trans_gc, rcu);
+	ctx.net	= read_pnet(&trans->set->net);
+
+	for (i = 0; i < trans->count; i++) {
+		elem.priv = trans->priv[i];
+		if (!nft_setelem_is_catchall(trans->set, &elem))
+			atomic_dec(&trans->set->nelems);
+
+		nf_tables_set_elem_destroy(&ctx, trans->set, elem.priv);
+	}
+
+	nft_trans_gc_destroy(trans);
+}
+
+static bool nft_trans_gc_work_done(struct nft_trans_gc *trans)
+{
+	struct nftables_pernet *nft_net;
+	struct nft_ctx ctx = {};
+
+	nft_net = nft_pernet(trans->net);
+
+	mutex_lock(&nft_net->commit_mutex);
+
+	/* Check for race with transaction, otherwise this batch refers to
+	 * stale objects that might not be there anymore. Skip transaction if
+	 * set has been destroyed from control plane transaction in case gc
+	 * worker loses race.
+	 */
+	if (READ_ONCE(nft_net->gc_seq) != trans->seq || trans->set->dead) {
+		mutex_unlock(&nft_net->commit_mutex);
+		return false;
+	}
+
+	ctx.net = trans->net;
+	ctx.table = trans->set->table;
+
+	nft_trans_gc_setelem_remove(&ctx, trans);
+	mutex_unlock(&nft_net->commit_mutex);
+
+	return true;
+}
+
+static void nft_trans_gc_work(struct work_struct *work)
+{
+	struct nft_trans_gc *trans, *next;
+	LIST_HEAD(trans_gc_list);
+
+	spin_lock(&nf_tables_destroy_list_lock);
+	list_splice_init(&nf_tables_gc_list, &trans_gc_list);
+	spin_unlock(&nf_tables_destroy_list_lock);
+
+	list_for_each_entry_safe(trans, next, &trans_gc_list, list) {
+		list_del(&trans->list);
+		if (!nft_trans_gc_work_done(trans)) {
+			nft_trans_gc_destroy(trans);
+			continue;
+		}
+		call_rcu(&trans->rcu, nft_trans_gc_trans_free);
+	}
+}
+
+struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set,
+					unsigned int gc_seq, gfp_t gfp)
+{
+	struct net *net = read_pnet(&set->net);
+	struct nft_trans_gc *trans;
+
+	trans = kzalloc(sizeof(*trans), gfp);
+	if (!trans)
+		return NULL;
+
+	refcount_inc(&set->refs);
+	trans->set = set;
+	trans->net = get_net(net);
+	trans->seq = gc_seq;
+
+	return trans;
+}
+
+void nft_trans_gc_elem_add(struct nft_trans_gc *trans, void *priv)
+{
+	trans->priv[trans->count++] = priv;
+}
+
+static void nft_trans_gc_queue_work(struct nft_trans_gc *trans)
+{
+	spin_lock(&nf_tables_gc_list_lock);
+	list_add_tail(&trans->list, &nf_tables_gc_list);
+	spin_unlock(&nf_tables_gc_list_lock);
+
+	schedule_work(&trans_gc_work);
+}
+
+static int nft_trans_gc_space(struct nft_trans_gc *trans)
+{
+	return NFT_TRANS_GC_BATCHCOUNT - trans->count;
+}
+
+struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc,
+					      unsigned int gc_seq, gfp_t gfp)
+{
+	if (nft_trans_gc_space(gc))
+		return gc;
+
+	nft_trans_gc_queue_work(gc);
+
+	return nft_trans_gc_alloc(gc->set, gc_seq, gfp);
+}
+
+void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans)
+{
+	if (trans->count == 0) {
+		nft_trans_gc_destroy(trans);
+		return;
+	}
+
+	nft_trans_gc_queue_work(trans);
+}
+
+struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp)
+{
+	if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net)))
+		return NULL;
+
+	if (nft_trans_gc_space(gc))
+		return gc;
+
+	call_rcu(&gc->rcu, nft_trans_gc_trans_free);
+
+	return nft_trans_gc_alloc(gc->set, 0, gfp);
+}
+
+void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans)
+{
+	WARN_ON_ONCE(!lockdep_commit_lock_is_held(trans->net));
+
+	if (trans->count == 0) {
+		nft_trans_gc_destroy(trans);
+		return;
+	}
+
+	call_rcu(&trans->rcu, nft_trans_gc_trans_free);
+}
+
+struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc,
+					   unsigned int gc_seq)
+{
+	struct nft_set_elem_catchall *catchall;
+	const struct nft_set *set = gc->set;
+	struct nft_set_ext *ext;
+
+	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
+		ext = nft_set_elem_ext(set, catchall->elem);
+
+		if (!nft_set_elem_expired(ext))
+			continue;
+		if (nft_set_elem_is_dead(ext))
+			goto dead_elem;
+
+		nft_set_elem_dead(ext);
+dead_elem:
+		gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
+		if (!gc)
+			return NULL;
+
+		nft_trans_gc_elem_add(gc, catchall->elem);
+	}
+
+	return gc;
+}
+
 static void nf_tables_module_autoload_cleanup(struct net *net)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
@@ -9576,11 +9742,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
 	struct nft_trans *trans, *next;
+	unsigned int base_seq, gc_seq;
 	LIST_HEAD(set_update_list);
 	struct nft_trans_elem *te;
 	struct nft_chain *chain;
 	struct nft_table *table;
-	unsigned int base_seq;
 	LIST_HEAD(adl);
 	int err;
 
@@ -9657,6 +9823,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 
 	WRITE_ONCE(nft_net->base_seq, base_seq);
 
+	/* Bump gc counter, it becomes odd, this is the busy mark. */
+	gc_seq = READ_ONCE(nft_net->gc_seq);
+	WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+
 	/* step 3. Start new generation, rules_gen_X now in use. */
 	net->nft.gencursor = nft_gencursor_next(net);
 
@@ -9764,6 +9934,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 			break;
 		case NFT_MSG_DELSET:
 		case NFT_MSG_DESTROYSET:
+			nft_trans_set(trans)->dead = 1;
 			list_del_rcu(&nft_trans_set(trans)->list);
 			nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
 					     trans->msg_type, GFP_KERNEL);
@@ -9866,6 +10037,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	nft_commit_notify(net, NETLINK_CB(skb).portid);
 	nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
 	nf_tables_commit_audit_log(&adl, nft_net->base_seq);
+
+	WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
 	nf_tables_commit_release(net);
 
 	return 0;
@@ -10915,6 +11088,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 	INIT_LIST_HEAD(&nft_net->notify_list);
 	mutex_init(&nft_net->commit_mutex);
 	nft_net->base_seq = 1;
+	nft_net->gc_seq = 0;
 
 	return 0;
 }
@@ -10943,10 +11117,16 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 	WARN_ON_ONCE(!list_empty(&nft_net->notify_list));
 }
 
+static void nf_tables_exit_batch(struct list_head *net_exit_list)
+{
+	flush_work(&trans_gc_work);
+}
+
 static struct pernet_operations nf_tables_net_ops = {
 	.init		= nf_tables_init_net,
 	.pre_exit	= nf_tables_pre_exit_net,
 	.exit		= nf_tables_exit_net,
+	.exit_batch	= nf_tables_exit_batch,
 	.id		= &nf_tables_net_id,
 	.size		= sizeof(struct nftables_pernet),
 };
@@ -11018,6 +11198,7 @@ static void __exit nf_tables_module_exit(void)
 	nft_chain_filter_fini();
 	nft_chain_route_fini();
 	unregister_pernet_subsys(&nf_tables_net_ops);
+	cancel_work_sync(&trans_gc_work);
 	cancel_work_sync(&trans_destroy_work);
 	rcu_barrier();
 	rhltable_destroy(&nft_objname_ht);
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 0b73cb0e752f..cef5df846000 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -59,6 +59,8 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg,
 
 	if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen))
 		return 1;
+	if (nft_set_elem_is_dead(&he->ext))
+		return 1;
 	if (nft_set_elem_expired(&he->ext))
 		return 1;
 	if (!nft_set_elem_active(&he->ext, x->genmask))
@@ -188,7 +190,6 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set,
 	struct nft_rhash_elem *he = elem->priv;
 
 	nft_set_elem_change_active(net, set, &he->ext);
-	nft_set_elem_clear_busy(&he->ext);
 }
 
 static bool nft_rhash_flush(const struct net *net,
@@ -196,12 +197,9 @@ static bool nft_rhash_flush(const struct net *net,
 {
 	struct nft_rhash_elem *he = priv;
 
-	if (!nft_set_elem_mark_busy(&he->ext) ||
-	    !nft_is_active(net, &he->ext)) {
-		nft_set_elem_change_active(net, set, &he->ext);
-		return true;
-	}
-	return false;
+	nft_set_elem_change_active(net, set, &he->ext);
+
+	return true;
 }
 
 static void *nft_rhash_deactivate(const struct net *net,
@@ -218,9 +216,8 @@ static void *nft_rhash_deactivate(const struct net *net,
 
 	rcu_read_lock();
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
-	if (he != NULL &&
-	    !nft_rhash_flush(net, set, he))
-		he = NULL;
+	if (he)
+		nft_set_elem_change_active(net, set, &he->ext);
 
 	rcu_read_unlock();
 
@@ -252,7 +249,9 @@ static bool nft_rhash_delete(const struct nft_set *set,
 	if (he == NULL)
 		return false;
 
-	return rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params) == 0;
+	nft_set_elem_dead(&he->ext);
+
+	return true;
 }
 
 static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
@@ -278,8 +277,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
 
 		if (iter->count < iter->skip)
 			goto cont;
-		if (nft_set_elem_expired(&he->ext))
-			goto cont;
 		if (!nft_set_elem_active(&he->ext, iter->genmask))
 			goto cont;
 
@@ -314,25 +311,48 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set,
 
 static void nft_rhash_gc(struct work_struct *work)
 {
+	struct nftables_pernet *nft_net;
 	struct nft_set *set;
 	struct nft_rhash_elem *he;
 	struct nft_rhash *priv;
-	struct nft_set_gc_batch *gcb = NULL;
 	struct rhashtable_iter hti;
+	struct nft_trans_gc *gc;
+	struct net *net;
+	u32 gc_seq;
 
 	priv = container_of(work, struct nft_rhash, gc_work.work);
 	set  = nft_set_container_of(priv);
+	net  = read_pnet(&set->net);
+	nft_net = nft_pernet(net);
+	gc_seq = READ_ONCE(nft_net->gc_seq);
+
+	gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL);
+	if (!gc)
+		goto done;
 
 	rhashtable_walk_enter(&priv->ht, &hti);
 	rhashtable_walk_start(&hti);
 
 	while ((he = rhashtable_walk_next(&hti))) {
 		if (IS_ERR(he)) {
-			if (PTR_ERR(he) != -EAGAIN)
-				break;
+			if (PTR_ERR(he) != -EAGAIN) {
+				nft_trans_gc_destroy(gc);
+				gc = NULL;
+				goto try_later;
+			}
 			continue;
 		}
 
+		/* Ruleset has been updated, try later. */
+		if (READ_ONCE(nft_net->gc_seq) != gc_seq) {
+			nft_trans_gc_destroy(gc);
+			gc = NULL;
+			goto try_later;
+		}
+
+		if (nft_set_elem_is_dead(&he->ext))
+			goto dead_elem;
+
 		if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPRESSIONS) &&
 		    nft_rhash_expr_needs_gc_run(set, &he->ext))
 			goto needs_gc_run;
@@ -340,26 +360,26 @@ static void nft_rhash_gc(struct work_struct *work)
 		if (!nft_set_elem_expired(&he->ext))
 			continue;
 needs_gc_run:
-		if (nft_set_elem_mark_busy(&he->ext))
-			continue;
+		nft_set_elem_dead(&he->ext);
+dead_elem:
+		gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
+		if (!gc)
+			goto try_later;
 
-		gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
-		if (gcb == NULL)
-			break;
-		rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params);
-		atomic_dec(&set->nelems);
-		nft_set_gc_batch_add(gcb, he);
+		nft_trans_gc_elem_add(gc, he);
 	}
+
+	gc = nft_trans_gc_catchall(gc, gc_seq);
+
+try_later:
+	/* catchall list iteration requires rcu read side lock. */
 	rhashtable_walk_stop(&hti);
 	rhashtable_walk_exit(&hti);
 
-	he = nft_set_catchall_gc(set);
-	if (he) {
-		gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
-		if (gcb)
-			nft_set_gc_batch_add(gcb, he);
-	}
-	nft_set_gc_batch_complete(gcb);
+	if (gc)
+		nft_trans_gc_queue_async_done(gc);
+
+done:
 	queue_delayed_work(system_power_efficient_wq, &priv->gc_work,
 			   nft_set_gc_interval(set));
 }
@@ -394,7 +414,7 @@ static int nft_rhash_init(const struct nft_set *set,
 		return err;
 
 	INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc);
-	if (set->flags & NFT_SET_TIMEOUT)
+	if (set->flags & (NFT_SET_TIMEOUT | NFT_SET_EVAL))
 		nft_rhash_gc_init(set);
 
 	return 0;
@@ -422,7 +442,6 @@ static void nft_rhash_destroy(const struct nft_ctx *ctx,
 	};
 
 	cancel_delayed_work_sync(&priv->gc_work);
-	rcu_barrier();
 	rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy,
 				    (void *)&rhash_ctx);
 }
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 49915a2a58eb..a5b8301afe4a 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -566,8 +566,7 @@ next_match:
 			goto out;
 
 		if (last) {
-			if (nft_set_elem_expired(&f->mt[b].e->ext) ||
-			    (genmask &&
+			if ((genmask &&
 			     !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
 				goto next_match;
 
@@ -601,8 +600,17 @@ out:
 static void *nft_pipapo_get(const struct net *net, const struct nft_set *set,
 			    const struct nft_set_elem *elem, unsigned int flags)
 {
-	return pipapo_get(net, set, (const u8 *)elem->key.val.data,
-			  nft_genmask_cur(net));
+	struct nft_pipapo_elem *ret;
+
+	ret = pipapo_get(net, set, (const u8 *)elem->key.val.data,
+			 nft_genmask_cur(net));
+	if (IS_ERR(ret))
+		return ret;
+
+	if (nft_set_elem_expired(&ret->ext))
+		return ERR_PTR(-ENOENT);
+
+	return ret;
 }
 
 /**
@@ -1528,16 +1536,34 @@ static void pipapo_drop(struct nft_pipapo_match *m,
 	}
 }
 
+static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set,
+				     struct nft_pipapo_elem *e)
+
+{
+	struct nft_set_elem elem = {
+		.priv	= e,
+	};
+
+	nft_setelem_data_deactivate(net, set, &elem);
+}
+
 /**
  * pipapo_gc() - Drop expired entries from set, destroy start and end elements
  * @set:	nftables API set representation
  * @m:		Matching data
  */
-static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m)
+static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m)
 {
+	struct nft_set *set = (struct nft_set *) _set;
 	struct nft_pipapo *priv = nft_set_priv(set);
+	struct net *net = read_pnet(&set->net);
 	int rules_f0, first_rule = 0;
 	struct nft_pipapo_elem *e;
+	struct nft_trans_gc *gc;
+
+	gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL);
+	if (!gc)
+		return;
 
 	while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) {
 		union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS];
@@ -1561,13 +1587,20 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m)
 		f--;
 		i--;
 		e = f->mt[rulemap[i].to].e;
-		if (nft_set_elem_expired(&e->ext) &&
-		    !nft_set_elem_mark_busy(&e->ext)) {
+
+		/* synchronous gc never fails, there is no need to set on
+		 * NFT_SET_ELEM_DEAD_BIT.
+		 */
+		if (nft_set_elem_expired(&e->ext)) {
 			priv->dirty = true;
-			pipapo_drop(m, rulemap);
 
-			rcu_barrier();
-			nft_set_elem_destroy(set, e, true);
+			gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
+			if (!gc)
+				break;
+
+			nft_pipapo_gc_deactivate(net, set, e);
+			pipapo_drop(m, rulemap);
+			nft_trans_gc_elem_add(gc, e);
 
 			/* And check again current first rule, which is now the
 			 * first we haven't checked.
@@ -1577,11 +1610,11 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m)
 		}
 	}
 
-	e = nft_set_catchall_gc(set);
-	if (e)
-		nft_set_elem_destroy(set, e, true);
-
-	priv->last_gc = jiffies;
+	gc = nft_trans_gc_catchall(gc, 0);
+	if (gc) {
+		nft_trans_gc_queue_sync_done(gc);
+		priv->last_gc = jiffies;
+	}
 }
 
 /**
@@ -1706,7 +1739,6 @@ static void nft_pipapo_activate(const struct net *net,
 		return;
 
 	nft_set_elem_change_active(net, set, &e->ext);
-	nft_set_elem_clear_busy(&e->ext);
 }
 
 /**
@@ -2005,8 +2037,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set,
 			goto cont;
 
 		e = f->mt[r].e;
-		if (nft_set_elem_expired(&e->ext))
-			goto cont;
 
 		elem.priv = e;
 
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 8d73fffd2d09..f9d4c8fcbbf8 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -46,6 +46,12 @@ static int nft_rbtree_cmp(const struct nft_set *set,
 		      set->klen);
 }
 
+static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe)
+{
+	return nft_set_elem_expired(&rbe->ext) ||
+	       nft_set_elem_is_dead(&rbe->ext);
+}
+
 static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 				const u32 *key, const struct nft_set_ext **ext,
 				unsigned int seq)
@@ -80,7 +86,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 				continue;
 			}
 
-			if (nft_set_elem_expired(&rbe->ext))
+			if (nft_rbtree_elem_expired(rbe))
 				return false;
 
 			if (nft_rbtree_interval_end(rbe)) {
@@ -98,7 +104,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
-	    !nft_set_elem_expired(&interval->ext) &&
+	    !nft_rbtree_elem_expired(interval) &&
 	    nft_rbtree_interval_start(interval)) {
 		*ext = &interval->ext;
 		return true;
@@ -215,6 +221,18 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set,
 	return rbe;
 }
 
+static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set,
+				 struct nft_rbtree *priv,
+				 struct nft_rbtree_elem *rbe)
+{
+	struct nft_set_elem elem = {
+		.priv	= rbe,
+	};
+
+	nft_setelem_data_deactivate(net, set, &elem);
+	rb_erase(&rbe->node, &priv->root);
+}
+
 static int nft_rbtree_gc_elem(const struct nft_set *__set,
 			      struct nft_rbtree *priv,
 			      struct nft_rbtree_elem *rbe,
@@ -222,11 +240,12 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set,
 {
 	struct nft_set *set = (struct nft_set *)__set;
 	struct rb_node *prev = rb_prev(&rbe->node);
+	struct net *net = read_pnet(&set->net);
 	struct nft_rbtree_elem *rbe_prev;
-	struct nft_set_gc_batch *gcb;
+	struct nft_trans_gc *gc;
 
-	gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC);
-	if (!gcb)
+	gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC);
+	if (!gc)
 		return -ENOMEM;
 
 	/* search for end interval coming before this element.
@@ -244,17 +263,28 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set,
 
 	if (prev) {
 		rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
+		nft_rbtree_gc_remove(net, set, priv, rbe_prev);
 
-		rb_erase(&rbe_prev->node, &priv->root);
-		atomic_dec(&set->nelems);
-		nft_set_gc_batch_add(gcb, rbe_prev);
+		/* There is always room in this trans gc for this element,
+		 * memory allocation never actually happens, hence, the warning
+		 * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT,
+		 * this is synchronous gc which never fails.
+		 */
+		gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
+		if (WARN_ON_ONCE(!gc))
+			return -ENOMEM;
+
+		nft_trans_gc_elem_add(gc, rbe_prev);
 	}
 
-	rb_erase(&rbe->node, &priv->root);
-	atomic_dec(&set->nelems);
+	nft_rbtree_gc_remove(net, set, priv, rbe);
+	gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
+	if (WARN_ON_ONCE(!gc))
+		return -ENOMEM;
+
+	nft_trans_gc_elem_add(gc, rbe);
 
-	nft_set_gc_batch_add(gcb, rbe);
-	nft_set_gc_batch_complete(gcb);
+	nft_trans_gc_queue_sync_done(gc);
 
 	return 0;
 }
@@ -482,7 +512,6 @@ static void nft_rbtree_activate(const struct net *net,
 	struct nft_rbtree_elem *rbe = elem->priv;
 
 	nft_set_elem_change_active(net, set, &rbe->ext);
-	nft_set_elem_clear_busy(&rbe->ext);
 }
 
 static bool nft_rbtree_flush(const struct net *net,
@@ -490,12 +519,9 @@ static bool nft_rbtree_flush(const struct net *net,
 {
 	struct nft_rbtree_elem *rbe = priv;
 
-	if (!nft_set_elem_mark_busy(&rbe->ext) ||
-	    !nft_is_active(net, &rbe->ext)) {
-		nft_set_elem_change_active(net, set, &rbe->ext);
-		return true;
-	}
-	return false;
+	nft_set_elem_change_active(net, set, &rbe->ext);
+
+	return true;
 }
 
 static void *nft_rbtree_deactivate(const struct net *net,
@@ -552,8 +578,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		if (iter->count < iter->skip)
 			goto cont;
-		if (nft_set_elem_expired(&rbe->ext))
-			goto cont;
 		if (!nft_set_elem_active(&rbe->ext, iter->genmask))
 			goto cont;
 
@@ -572,26 +596,40 @@ cont:
 
 static void nft_rbtree_gc(struct work_struct *work)
 {
-	struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL;
-	struct nft_set_gc_batch *gcb = NULL;
+	struct nft_rbtree_elem *rbe, *rbe_end = NULL;
+	struct nftables_pernet *nft_net;
 	struct nft_rbtree *priv;
+	struct nft_trans_gc *gc;
 	struct rb_node *node;
 	struct nft_set *set;
+	unsigned int gc_seq;
 	struct net *net;
-	u8 genmask;
 
 	priv = container_of(work, struct nft_rbtree, gc_work.work);
 	set  = nft_set_container_of(priv);
 	net  = read_pnet(&set->net);
-	genmask = nft_genmask_cur(net);
+	nft_net = nft_pernet(net);
+	gc_seq  = READ_ONCE(nft_net->gc_seq);
+
+	gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL);
+	if (!gc)
+		goto done;
 
 	write_lock_bh(&priv->lock);
 	write_seqcount_begin(&priv->count);
 	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
+
+		/* Ruleset has been updated, try later. */
+		if (READ_ONCE(nft_net->gc_seq) != gc_seq) {
+			nft_trans_gc_destroy(gc);
+			gc = NULL;
+			goto try_later;
+		}
+
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 
-		if (!nft_set_elem_active(&rbe->ext, genmask))
-			continue;
+		if (nft_set_elem_is_dead(&rbe->ext))
+			goto dead_elem;
 
 		/* elements are reversed in the rbtree for historical reasons,
 		 * from highest to lowest value, that is why end element is
@@ -604,46 +642,36 @@ static void nft_rbtree_gc(struct work_struct *work)
 		if (!nft_set_elem_expired(&rbe->ext))
 			continue;
 
-		if (nft_set_elem_mark_busy(&rbe->ext)) {
-			rbe_end = NULL;
+		nft_set_elem_dead(&rbe->ext);
+
+		if (!rbe_end)
 			continue;
-		}
 
-		if (rbe_prev) {
-			rb_erase(&rbe_prev->node, &priv->root);
-			rbe_prev = NULL;
-		}
-		gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
-		if (!gcb)
-			break;
+		nft_set_elem_dead(&rbe_end->ext);
 
-		atomic_dec(&set->nelems);
-		nft_set_gc_batch_add(gcb, rbe);
-		rbe_prev = rbe;
+		gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
+		if (!gc)
+			goto try_later;
 
-		if (rbe_end) {
-			atomic_dec(&set->nelems);
-			nft_set_gc_batch_add(gcb, rbe_end);
-			rb_erase(&rbe_end->node, &priv->root);
-			rbe_end = NULL;
-		}
-		node = rb_next(node);
-		if (!node)
-			break;
+		nft_trans_gc_elem_add(gc, rbe_end);
+		rbe_end = NULL;
+dead_elem:
+		gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
+		if (!gc)
+			goto try_later;
+
+		nft_trans_gc_elem_add(gc, rbe);
 	}
-	if (rbe_prev)
-		rb_erase(&rbe_prev->node, &priv->root);
+
+	gc = nft_trans_gc_catchall(gc, gc_seq);
+
+try_later:
 	write_seqcount_end(&priv->count);
 	write_unlock_bh(&priv->lock);
 
-	rbe = nft_set_catchall_gc(set);
-	if (rbe) {
-		gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
-		if (gcb)
-			nft_set_gc_batch_add(gcb, rbe);
-	}
-	nft_set_gc_batch_complete(gcb);
-
+	if (gc)
+		nft_trans_gc_queue_async_done(gc);
+done:
 	queue_delayed_work(system_power_efficient_wq, &priv->gc_work,
 			   nft_set_gc_interval(set));
 }
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 0a65e696a4c6..8f97648d652f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -401,18 +401,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status)
 {
 	union tpacket_uhdr h;
 
+	/* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */
+
 	h.raw = frame;
 	switch (po->tp_version) {
 	case TPACKET_V1:
-		h.h1->tp_status = status;
+		WRITE_ONCE(h.h1->tp_status, status);
 		flush_dcache_page(pgv_to_page(&h.h1->tp_status));
 		break;
 	case TPACKET_V2:
-		h.h2->tp_status = status;
+		WRITE_ONCE(h.h2->tp_status, status);
 		flush_dcache_page(pgv_to_page(&h.h2->tp_status));
 		break;
 	case TPACKET_V3:
-		h.h3->tp_status = status;
+		WRITE_ONCE(h.h3->tp_status, status);
 		flush_dcache_page(pgv_to_page(&h.h3->tp_status));
 		break;
 	default:
@@ -429,17 +431,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame)
 
 	smp_rmb();
 
+	/* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */
+
 	h.raw = frame;
 	switch (po->tp_version) {
 	case TPACKET_V1:
 		flush_dcache_page(pgv_to_page(&h.h1->tp_status));
-		return h.h1->tp_status;
+		return READ_ONCE(h.h1->tp_status);
 	case TPACKET_V2:
 		flush_dcache_page(pgv_to_page(&h.h2->tp_status));
-		return h.h2->tp_status;
+		return READ_ONCE(h.h2->tp_status);
 	case TPACKET_V3:
 		flush_dcache_page(pgv_to_page(&h.h3->tp_status));
-		return h.h3->tp_status;
+		return READ_ONCE(h.h3->tp_status);
 	default:
 		WARN(1, "TPACKET version not supported.\n");
 		BUG();
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 0c013d2b5d8f..f5834af5fad5 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -378,8 +378,8 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
 	sk->sk_state = SMC_INIT;
 	sk->sk_destruct = smc_destruct;
 	sk->sk_protocol = protocol;
-	WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(net->smc.sysctl_wmem));
-	WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(net->smc.sysctl_rmem));
+	WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem));
+	WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem));
 	smc = smc_sk(sk);
 	INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
 	INIT_WORK(&smc->connect_work, smc_connect_work);
@@ -436,13 +436,60 @@ out:
 	return rc;
 }
 
+/* copy only relevant settings and flags of SOL_SOCKET level from smc to
+ * clc socket (since smc is not called for these options from net/core)
+ */
+
+#define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \
+			     (1UL << SOCK_KEEPOPEN) | \
+			     (1UL << SOCK_LINGER) | \
+			     (1UL << SOCK_BROADCAST) | \
+			     (1UL << SOCK_TIMESTAMP) | \
+			     (1UL << SOCK_DBG) | \
+			     (1UL << SOCK_RCVTSTAMP) | \
+			     (1UL << SOCK_RCVTSTAMPNS) | \
+			     (1UL << SOCK_LOCALROUTE) | \
+			     (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \
+			     (1UL << SOCK_RXQ_OVFL) | \
+			     (1UL << SOCK_WIFI_STATUS) | \
+			     (1UL << SOCK_NOFCS) | \
+			     (1UL << SOCK_FILTER_LOCKED) | \
+			     (1UL << SOCK_TSTAMP_NEW))
+
+/* if set, use value set by setsockopt() - else use IPv4 or SMC sysctl value */
+static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk,
+				     unsigned long mask)
+{
+	struct net *nnet = sock_net(nsk);
+
+	nsk->sk_userlocks = osk->sk_userlocks;
+	if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) {
+		nsk->sk_sndbuf = osk->sk_sndbuf;
+	} else {
+		if (mask == SK_FLAGS_SMC_TO_CLC)
+			WRITE_ONCE(nsk->sk_sndbuf,
+				   READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1]));
+		else
+			WRITE_ONCE(nsk->sk_sndbuf,
+				   2 * READ_ONCE(nnet->smc.sysctl_wmem));
+	}
+	if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) {
+		nsk->sk_rcvbuf = osk->sk_rcvbuf;
+	} else {
+		if (mask == SK_FLAGS_SMC_TO_CLC)
+			WRITE_ONCE(nsk->sk_rcvbuf,
+				   READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1]));
+		else
+			WRITE_ONCE(nsk->sk_rcvbuf,
+				   2 * READ_ONCE(nnet->smc.sysctl_rmem));
+	}
+}
+
 static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
 				   unsigned long mask)
 {
 	/* options we don't get control via setsockopt for */
 	nsk->sk_type = osk->sk_type;
-	nsk->sk_sndbuf = osk->sk_sndbuf;
-	nsk->sk_rcvbuf = osk->sk_rcvbuf;
 	nsk->sk_sndtimeo = osk->sk_sndtimeo;
 	nsk->sk_rcvtimeo = osk->sk_rcvtimeo;
 	nsk->sk_mark = READ_ONCE(osk->sk_mark);
@@ -453,26 +500,10 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
 
 	nsk->sk_flags &= ~mask;
 	nsk->sk_flags |= osk->sk_flags & mask;
+
+	smc_adjust_sock_bufsizes(nsk, osk, mask);
 }
 
-#define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \
-			     (1UL << SOCK_KEEPOPEN) | \
-			     (1UL << SOCK_LINGER) | \
-			     (1UL << SOCK_BROADCAST) | \
-			     (1UL << SOCK_TIMESTAMP) | \
-			     (1UL << SOCK_DBG) | \
-			     (1UL << SOCK_RCVTSTAMP) | \
-			     (1UL << SOCK_RCVTSTAMPNS) | \
-			     (1UL << SOCK_LOCALROUTE) | \
-			     (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \
-			     (1UL << SOCK_RXQ_OVFL) | \
-			     (1UL << SOCK_WIFI_STATUS) | \
-			     (1UL << SOCK_NOFCS) | \
-			     (1UL << SOCK_FILTER_LOCKED) | \
-			     (1UL << SOCK_TSTAMP_NEW))
-/* copy only relevant settings and flags of SOL_SOCKET level from smc to
- * clc socket (since smc is not called for these options from net/core)
- */
 static void smc_copy_sock_settings_to_clc(struct smc_sock *smc)
 {
 	smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC);
@@ -2479,8 +2510,6 @@ static void smc_tcp_listen_work(struct work_struct *work)
 		sock_hold(lsk); /* sock_put in smc_listen_work */
 		INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
 		smc_copy_sock_settings_to_smc(new_smc);
-		new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf;
-		new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf;
 		sock_hold(&new_smc->sk); /* sock_put in passive closing */
 		if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work))
 			sock_put(&new_smc->sk);
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 2eeea4cdc718..1f2b912c43d1 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -161,7 +161,7 @@ struct smc_connection {
 
 	struct smc_buf_desc	*sndbuf_desc;	/* send buffer descriptor */
 	struct smc_buf_desc	*rmb_desc;	/* RMBE descriptor */
-	int			rmbe_size_short;/* compressed notation */
+	int                     rmbe_size_comp; /* compressed notation */
 	int			rmbe_update_limit;
 						/* lower limit for consumer
 						 * cursor update
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index b9b8b07aa702..c90d9e5dda54 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -1007,7 +1007,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 		clc->d0.gid =
 			conn->lgr->smcd->ops->get_local_gid(conn->lgr->smcd);
 		clc->d0.token = conn->rmb_desc->token;
-		clc->d0.dmbe_size = conn->rmbe_size_short;
+		clc->d0.dmbe_size = conn->rmbe_size_comp;
 		clc->d0.dmbe_idx = 0;
 		memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
 		if (version == SMC_V1) {
@@ -1050,7 +1050,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 			clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu);
 			break;
 		}
-		clc->r0.rmbe_size = conn->rmbe_size_short;
+		clc->r0.rmbe_size = conn->rmbe_size_comp;
 		clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ?
 			cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) :
 			cpu_to_be64((u64)sg_dma_address
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 3f465faf2b68..6b78075404d7 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -2309,31 +2309,30 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 	struct smc_connection *conn = &smc->conn;
 	struct smc_link_group *lgr = conn->lgr;
 	struct list_head *buf_list;
-	int bufsize, bufsize_short;
+	int bufsize, bufsize_comp;
 	struct rw_semaphore *lock;	/* lock buffer list */
 	bool is_dgraded = false;
-	int sk_buf_size;
 
 	if (is_rmb)
 		/* use socket recv buffer size (w/o overhead) as start value */
-		sk_buf_size = smc->sk.sk_rcvbuf;
+		bufsize = smc->sk.sk_rcvbuf / 2;
 	else
 		/* use socket send buffer size (w/o overhead) as start value */
-		sk_buf_size = smc->sk.sk_sndbuf;
+		bufsize = smc->sk.sk_sndbuf / 2;
 
-	for (bufsize_short = smc_compress_bufsize(sk_buf_size, is_smcd, is_rmb);
-	     bufsize_short >= 0; bufsize_short--) {
+	for (bufsize_comp = smc_compress_bufsize(bufsize, is_smcd, is_rmb);
+	     bufsize_comp >= 0; bufsize_comp--) {
 		if (is_rmb) {
 			lock = &lgr->rmbs_lock;
-			buf_list = &lgr->rmbs[bufsize_short];
+			buf_list = &lgr->rmbs[bufsize_comp];
 		} else {
 			lock = &lgr->sndbufs_lock;
-			buf_list = &lgr->sndbufs[bufsize_short];
+			buf_list = &lgr->sndbufs[bufsize_comp];
 		}
-		bufsize = smc_uncompress_bufsize(bufsize_short);
+		bufsize = smc_uncompress_bufsize(bufsize_comp);
 
 		/* check for reusable slot in the link group */
-		buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list);
+		buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list);
 		if (buf_desc) {
 			buf_desc->is_dma_need_sync = 0;
 			SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize);
@@ -2377,8 +2376,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 
 	if (is_rmb) {
 		conn->rmb_desc = buf_desc;
-		conn->rmbe_size_short = bufsize_short;
-		smc->sk.sk_rcvbuf = bufsize;
+		conn->rmbe_size_comp = bufsize_comp;
+		smc->sk.sk_rcvbuf = bufsize * 2;
 		atomic_set(&conn->bytes_to_rcv, 0);
 		conn->rmbe_update_limit =
 			smc_rmb_wnd_update_limit(buf_desc->len);
@@ -2386,7 +2385,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 			smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */
 	} else {
 		conn->sndbuf_desc = buf_desc;
-		smc->sk.sk_sndbuf = bufsize;
+		smc->sk.sk_sndbuf = bufsize * 2;
 		atomic_set(&conn->sndbuf_space, bufsize);
 	}
 	return 0;
diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c
index b6f79fabb9d3..0b2a957ca5f5 100644
--- a/net/smc/smc_sysctl.c
+++ b/net/smc/smc_sysctl.c
@@ -21,6 +21,10 @@
 
 static int min_sndbuf = SMC_BUF_MIN_SIZE;
 static int min_rcvbuf = SMC_BUF_MIN_SIZE;
+static int max_sndbuf = INT_MAX / 2;
+static int max_rcvbuf = INT_MAX / 2;
+static const int net_smc_wmem_init = (64 * 1024);
+static const int net_smc_rmem_init = (64 * 1024);
 
 static struct ctl_table smc_table[] = {
 	{
@@ -53,6 +57,7 @@ static struct ctl_table smc_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &min_sndbuf,
+		.extra2		= &max_sndbuf,
 	},
 	{
 		.procname	= "rmem",
@@ -61,6 +66,7 @@ static struct ctl_table smc_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &min_rcvbuf,
+		.extra2		= &max_rcvbuf,
 	},
 	{  }
 };
@@ -88,8 +94,8 @@ int __net_init smc_sysctl_net_init(struct net *net)
 	net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE;
 	net->smc.sysctl_smcr_buf_type = SMCR_PHYS_CONT_BUFS;
 	net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME;
-	WRITE_ONCE(net->smc.sysctl_wmem, READ_ONCE(net->ipv4.sysctl_tcp_wmem[1]));
-	WRITE_ONCE(net->smc.sysctl_rmem, READ_ONCE(net->ipv4.sysctl_tcp_rmem[1]));
+	WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init);
+	WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init);
 
 	return 0;
 
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 5df18f696d7f..2392d06845aa 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -52,6 +52,8 @@ static LIST_HEAD(tls_device_list);
 static LIST_HEAD(tls_device_down_list);
 static DEFINE_SPINLOCK(tls_device_lock);
 
+static struct page *dummy_page;
+
 static void tls_device_free_ctx(struct tls_context *ctx)
 {
 	if (ctx->tx_conf == TLS_HW) {
@@ -312,36 +314,33 @@ static int tls_push_record(struct sock *sk,
 	return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags);
 }
 
-static int tls_device_record_close(struct sock *sk,
-				   struct tls_context *ctx,
-				   struct tls_record_info *record,
-				   struct page_frag *pfrag,
-				   unsigned char record_type)
+static void tls_device_record_close(struct sock *sk,
+				    struct tls_context *ctx,
+				    struct tls_record_info *record,
+				    struct page_frag *pfrag,
+				    unsigned char record_type)
 {
 	struct tls_prot_info *prot = &ctx->prot_info;
-	int ret;
+	struct page_frag dummy_tag_frag;
 
 	/* append tag
 	 * device will fill in the tag, we just need to append a placeholder
 	 * use socket memory to improve coalescing (re-using a single buffer
 	 * increases frag count)
-	 * if we can't allocate memory now, steal some back from data
+	 * if we can't allocate memory now use the dummy page
 	 */
-	if (likely(skb_page_frag_refill(prot->tag_size, pfrag,
-					sk->sk_allocation))) {
-		ret = 0;
-		tls_append_frag(record, pfrag, prot->tag_size);
-	} else {
-		ret = prot->tag_size;
-		if (record->len <= prot->overhead_size)
-			return -ENOMEM;
+	if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) &&
+	    !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) {
+		dummy_tag_frag.page = dummy_page;
+		dummy_tag_frag.offset = 0;
+		pfrag = &dummy_tag_frag;
 	}
+	tls_append_frag(record, pfrag, prot->tag_size);
 
 	/* fill prepend */
 	tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]),
 			 record->len - prot->overhead_size,
 			 record_type);
-	return ret;
 }
 
 static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx,
@@ -545,18 +544,8 @@ last_record:
 
 		if (done || record->len >= max_open_record_len ||
 		    (record->num_frags >= MAX_SKB_FRAGS - 1)) {
-			rc = tls_device_record_close(sk, tls_ctx, record,
-						     pfrag, record_type);
-			if (rc) {
-				if (rc > 0) {
-					size += rc;
-				} else {
-					size = orig_size;
-					destroy_record(record);
-					ctx->open_record = NULL;
-					break;
-				}
-			}
+			tls_device_record_close(sk, tls_ctx, record,
+						pfrag, record_type);
 
 			rc = tls_push_record(sk,
 					     tls_ctx,
@@ -1454,14 +1443,26 @@ int __init tls_device_init(void)
 {
 	int err;
 
-	destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0);
-	if (!destruct_wq)
+	dummy_page = alloc_page(GFP_KERNEL);
+	if (!dummy_page)
 		return -ENOMEM;
 
+	destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0);
+	if (!destruct_wq) {
+		err = -ENOMEM;
+		goto err_free_dummy;
+	}
+
 	err = register_netdevice_notifier(&tls_dev_notifier);
 	if (err)
-		destroy_workqueue(destruct_wq);
+		goto err_destroy_wq;
 
+	return 0;
+
+err_destroy_wq:
+	destroy_workqueue(destruct_wq);
+err_free_dummy:
+	put_page(dummy_page);
 	return err;
 }
 
@@ -1470,4 +1471,5 @@ void __exit tls_device_cleanup(void)
 	unregister_netdevice_notifier(&tls_dev_notifier);
 	destroy_workqueue(destruct_wq);
 	clean_acked_data_flush();
+	put_page(dummy_page);
 }
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 7dbb8cd8f809..f550c84f3408 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -139,9 +139,6 @@ int tls_push_sg(struct sock *sk,
 
 	ctx->splicing_pages = true;
 	while (1) {
-		if (sg_is_last(sg))
-			msg.msg_flags = flags;
-
 		/* is sending application-limited? */
 		tcp_rate_check_app_limited(sk);
 		p = sg_page(sg);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0da2e6a2a7ea..8bcf8e293308 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5430,8 +5430,11 @@ nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs)
 	if (!wiphy->mbssid_max_interfaces)
 		return ERR_PTR(-EINVAL);
 
-	nla_for_each_nested(nl_elems, attrs, rem_elems)
+	nla_for_each_nested(nl_elems, attrs, rem_elems) {
+		if (num_elems >= 255)
+			return ERR_PTR(-EINVAL);
 		num_elems++;
+	}
 
 	elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL);
 	if (!elems)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 47796a5a79b3..fcfc8472f73d 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1189,6 +1189,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 				err = xp_alloc_tx_descs(xs->pool, xs);
 				if (err) {
 					xp_put_pool(xs->pool);
+					xs->pool = NULL;
 					sockfd_put(sock);
 					goto out_unlock;
 				}