Merge tag 'net-7.1-rc6-2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull more networking fixes from Jakub Kicinski:
 "Quick follow up, nothing super urgent here. Main reason I'm sending
  this out is because the IPsec and Bluetooth PRs did not make it
  yesterday. I don't want to have to send you all of this + whatever
  comes next week, for rc7. The fixes under "Previous releases -
  regressions" are for real user-reported regressions from v7.0.

  Previous releases - regressions:

   - Revert "ipv6: preserve insertion order for same-scope addresses"

   - xfrm: move policy_bydst RCU sync, a fix which added a sync RCU on
     netns exit got backported to stable and was causing serious
     accumulation of dying netns's for real workloads

   - pcs-mtk-lynxi: fix bpi-r3 serdes configuration

  Previous releases - always broken:

   - usual grab bag of race, locking and leak fixes for Bluetooth

   - handful of page handling fixes for IPsec"

* tag 'net-7.1-rc6-2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (36 commits)
  wireguard: send: append trailer after expanding head
  Revert "ipv6: preserve insertion order for same-scope addresses"
  net: skbuff: fix pskb_carve leaking zcopy pages
  ipv6: fix possible infinite loop in fib6_select_path()
  ipv6: fix possible infinite loop in rt6_fill_node()
  bpf: sockmap: fix tail fragment offset in bpf_msg_push_data
  vsock/virtio: bind uarg before filling zerocopy skb
  Revert "esp: fix page frag reference leak on skb_to_sgvec failure"
  net: pcs: pcs-mtk-lynxi: fix bpi-r3 serdes configuration
  sctp: fix race between sctp_wait_for_connect and peeloff
  net: mana: Skip redundant detach on already-detached port
  net: mana: Add NULL guards in teardown path to prevent panic on attach failure
  Bluetooth: hci_sync: Reset device counters in hci_dev_close_sync()
  Bluetooth: hci_sync: Set HCI_CMD_DRAIN_WORKQUEUE during device close
  Bluetooth: hci_core: Rework hci_dev_do_reset() to use hci_sync functions
  Bluetooth: ISO: serialize iso_sock_clear_timer with socket lock
  Bluetooth: ISO: fix UAF in iso_recv_frame
  Bluetooth: L2CAP: Fix possible crash on l2cap_ecred_conn_rsp
  Bluetooth: l2cap: clear chan->ident on ECRED reconfiguration success
  Bluetooth: hci_qca: Use 100 ms SSR delay for rampatch and NVM loading
  ...

25 files changed, 200 insertions, 109 deletions

diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 2f03b780b40d..960a19b3e26d 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -486,6 +486,8 @@ static int send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev)
 			int ret;
 
 			local_skb = skb_clone(skb, GFP_ATOMIC);
+			if (!local_skb)
+				continue;
 
 			BT_DBG("xmit %s to %pMR type %u IP %pI6c chan %p",
 			       netdev->name,
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 17b46ad6a349..54eabaa46960 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -870,8 +870,10 @@ static int hci_le_big_terminate(struct hci_dev *hdev, struct hci_conn *conn)
 			d->big_sync_term = true;
 	}
 
-	if (!d->pa_sync_term && !d->big_sync_term)
+	if (!d->pa_sync_term && !d->big_sync_term) {
+		kfree(d);
 		return 0;
+	}
 
 	ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d,
 				 terminate_big_destroy);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index c46c1236ebfa..28d7929dc593 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -539,46 +539,9 @@ static int hci_dev_do_reset(struct hci_dev *hdev)
 
 	hci_req_sync_lock(hdev);
 
-	/* Drop queues */
-	skb_queue_purge(&hdev->rx_q);
-	skb_queue_purge(&hdev->cmd_q);
-
-	/* Cancel these to avoid queueing non-chained pending work */
-	hci_dev_set_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE);
-	/* Wait for
-	 *
-	 *    if (!hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE))
-	 *        queue_delayed_work(&hdev->{cmd,ncmd}_timer)
-	 *
-	 * inside RCU section to see the flag or complete scheduling.
-	 */
-	synchronize_rcu();
-	/* Explicitly cancel works in case scheduled after setting the flag. */
-	cancel_delayed_work(&hdev->cmd_timer);
-	cancel_delayed_work(&hdev->ncmd_timer);
-
-	/* Avoid potential lockdep warnings from the *_flush() calls by
-	 * ensuring the workqueue is empty up front.
-	 */
-	drain_workqueue(hdev->workqueue);
-
-	hci_dev_lock(hdev);
-	hci_inquiry_cache_flush(hdev);
-	hci_conn_hash_flush(hdev);
-	hci_dev_unlock(hdev);
-
-	if (hdev->flush)
-		hdev->flush(hdev);
-
-	hci_dev_clear_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE);
-
-	atomic_set(&hdev->cmd_cnt, 1);
-	hdev->acl_cnt = 0;
-	hdev->sco_cnt = 0;
-	hdev->le_cnt = 0;
-	hdev->iso_cnt = 0;
-
-	ret = hci_reset_sync(hdev);
+	ret = hci_dev_close_sync(hdev);
+	if (!ret)
+		ret = hci_dev_open_sync(hdev);
 
 	hci_req_sync_unlock(hdev);
 	return ret;
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index aff8562a8690..aeccd8084cba 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5301,6 +5301,12 @@ int hci_dev_close_sync(struct hci_dev *hdev)
 
 	bt_dev_dbg(hdev, "");
 
+	/* Set HCI_DRAIN_WORKQUEUE flag to prevent queuing work during
+	 * reset/close. See hci_cmd_work() and handle_cmd_cnt_and_timer().
+	 */
+	hci_dev_set_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE);
+	synchronize_rcu();
+
 	if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) {
 		disable_delayed_work(&hdev->power_off);
 		disable_delayed_work(&hdev->ncmd_timer);
@@ -5324,6 +5330,7 @@ int hci_dev_close_sync(struct hci_dev *hdev)
 
 	if (!test_and_clear_bit(HCI_UP, &hdev->flags)) {
 		cancel_delayed_work_sync(&hdev->cmd_timer);
+		hci_dev_clear_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE);
 		return err;
 	}
 
@@ -5386,6 +5393,10 @@ int hci_dev_close_sync(struct hci_dev *hdev)
 	/* Reset device */
 	skb_queue_purge(&hdev->cmd_q);
 	atomic_set(&hdev->cmd_cnt, 1);
+	hdev->acl_cnt = 0;
+	hdev->sco_cnt = 0;
+	hdev->le_cnt = 0;
+	hdev->iso_cnt = 0;
 	if (hci_test_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE) &&
 	    !auto_off && !hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
 		set_bit(HCI_INIT, &hdev->flags);
@@ -5423,6 +5434,7 @@ int hci_dev_close_sync(struct hci_dev *hdev)
 	/* Clear flags */
 	hdev->flags &= BIT(HCI_RAW);
 	hci_dev_clear_volatile_flags(hdev);
+	hci_dev_clear_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE);
 
 	memset(hdev->eir, 0, sizeof(hdev->eir));
 	memset(hdev->dev_class, 0, sizeof(hdev->dev_class));
@@ -6699,6 +6711,7 @@ int hci_le_create_cis_sync(struct hci_dev *hdev)
 	DEFINE_FLEX(struct hci_cp_le_create_cis, cmd, cis, num_cis, 0x1f);
 	size_t aux_num_cis = 0;
 	struct hci_conn *conn;
+	u16 timeout = 0;
 	u8 cig = BT_ISO_QOS_CIG_UNSET;
 
 	/* The spec allows only one pending LE Create CIS command at a time. If
@@ -6769,6 +6782,7 @@ int hci_le_create_cis_sync(struct hci_dev *hdev)
 		set_bit(HCI_CONN_CREATE_CIS, &conn->flags);
 		cis->acl_handle = cpu_to_le16(conn->parent->handle);
 		cis->cis_handle = cpu_to_le16(conn->handle);
+		timeout = conn->conn_timeout;
 		aux_num_cis++;
 
 		if (aux_num_cis >= cmd->num_cis)
@@ -6788,7 +6802,7 @@ done:
 	return __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_CREATE_CIS,
 					struct_size(cmd, cis, cmd->num_cis),
 					cmd, HCI_EVT_LE_CIS_ESTABLISHED,
-					conn->conn_timeout, NULL);
+					timeout, NULL);
 }
 
 int hci_le_remove_cig_sync(struct hci_dev *hdev, u8 handle)
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 976f91eeb745..70344bd3248a 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -179,12 +179,21 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb)
 {
 	struct input_dev *dev = session->input;
 	unsigned char *keys = session->keys;
-	unsigned char *udata = skb->data + 1;
-	signed char *sdata = skb->data + 1;
-	int i, size = skb->len - 1;
+	unsigned char *udata;
+	signed char *sdata;
+	u8 *hdr;
+	int i;
+
+	hdr = skb_pull_data(skb, 1);
+	if (!hdr)
+		return;
 
-	switch (skb->data[0]) {
+	switch (*hdr) {
 	case 0x01:	/* Keyboard report */
+		udata = skb_pull_data(skb, 8);
+		if (!udata)
+			break;
+
 		for (i = 0; i < 8; i++)
 			input_report_key(dev, hidp_keycode[i + 224], (udata[0] >> i) & 1);
 
@@ -213,6 +222,10 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb)
 		break;
 
 	case 0x02:	/* Mouse report */
+		sdata = skb_pull_data(skb, 3);
+		if (!sdata)
+			break;
+
 		input_report_key(dev, BTN_LEFT,   sdata[0] & 0x01);
 		input_report_key(dev, BTN_RIGHT,  sdata[0] & 0x02);
 		input_report_key(dev, BTN_MIDDLE, sdata[0] & 0x04);
@@ -222,7 +235,7 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb)
 		input_report_rel(dev, REL_X, sdata[1]);
 		input_report_rel(dev, REL_Y, sdata[2]);
 
-		if (size > 3)
+		if (skb->len > 0)
 			input_report_rel(dev, REL_WHEEL, sdata[3]);
 		break;
 	}
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index d7af617cda45..876649556d3c 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -564,7 +564,7 @@ static void iso_recv_frame(struct iso_conn *conn, struct sk_buff *skb)
 	struct sock *sk;
 
 	iso_conn_lock(conn);
-	sk = conn->sk;
+	sk = iso_sock_hold(conn);
 	iso_conn_unlock(conn);
 
 	if (!sk)
@@ -573,11 +573,15 @@ static void iso_recv_frame(struct iso_conn *conn, struct sk_buff *skb)
 	BT_DBG("sk %p len %d", sk, skb->len);
 
 	if (sk->sk_state != BT_CONNECTED)
-		goto drop;
+		goto drop_put;
 
-	if (!sock_queue_rcv_skb(sk, skb))
+	if (!sock_queue_rcv_skb(sk, skb)) {
+		sock_put(sk);
 		return;
+	}
 
+drop_put:
+	sock_put(sk);
 drop:
 	kfree_skb(skb);
 }
@@ -860,8 +864,8 @@ static void __iso_sock_close(struct sock *sk)
 /* Must be called on unlocked socket. */
 static void iso_sock_close(struct sock *sk)
 {
-	iso_sock_clear_timer(sk);
 	lock_sock(sk);
+	iso_sock_clear_timer(sk);
 	__iso_sock_close(sk);
 	release_sock(sk);
 	iso_sock_kill(sk);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index fdccd62ccca8..45b175399e8d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -411,8 +411,10 @@ static void l2cap_chan_timeout(struct work_struct *work)
 
 	BT_DBG("chan %p state %s", chan, state_to_string(chan->state));
 
-	if (!conn)
+	if (!conn) {
+		l2cap_chan_put(chan);
 		return;
+	}
 
 	mutex_lock(&conn->lock);
 	/* __set_chan_timer() calls l2cap_chan_hold(chan) while scheduling
@@ -5260,6 +5262,7 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn,
 	cmd_len -= sizeof(*rsp);
 
 	list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) {
+		struct l2cap_chan *orig;
 		u16 dcid;
 
 		if (chan->ident != cmd->ident ||
@@ -5281,8 +5284,10 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn,
 
 		BT_DBG("dcid[%d] 0x%4.4x", i, dcid);
 
+		orig = __l2cap_get_chan_by_dcid(conn, dcid);
+
 		/* Check if dcid is already in use */
-		if (dcid && __l2cap_get_chan_by_dcid(conn, dcid)) {
+		if (dcid && orig) {
 			/* If a device receives a
 			 * L2CAP_CREDIT_BASED_CONNECTION_RSP packet with an
 			 * already-assigned Destination CID, then both the
@@ -5291,10 +5296,24 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn,
 			 */
 			l2cap_chan_del(chan, ECONNREFUSED);
 			l2cap_chan_unlock(chan);
-			chan = __l2cap_get_chan_by_dcid(conn, dcid);
-			l2cap_chan_lock(chan);
-			l2cap_chan_del(chan, ECONNRESET);
-			l2cap_chan_unlock(chan);
+
+			/* Check that the dcid channel mode is
+			 * L2CAP_MODE_EXT_FLOWCTL since this procedure is only
+			 * valid for that mode and shouldn't disconnect a dcid
+			 * in other modes.
+			 */
+			if (orig->mode == L2CAP_MODE_EXT_FLOWCTL) {
+				l2cap_chan_lock(orig);
+				/* Disconnect the original channel as it may be
+				 * considered connected since dcid has already
+				 * been assigned; don't call l2cap_chan_close
+				 * directly since that could lead to
+				 * l2cap_chan_del and then removing the channel
+				 * from the list while we're iterating over it.
+				 */
+				__set_chan_timer(orig, 0);
+				l2cap_chan_unlock(orig);
+			}
 			continue;
 		}
 
@@ -5458,14 +5477,20 @@ static inline int l2cap_ecred_reconf_rsp(struct l2cap_conn *conn,
 
 	BT_DBG("result 0x%4.4x", result);
 
-	if (!result)
+	if (!result) {
+		list_for_each_entry(chan, &conn->chan_l, list) {
+			if (chan->ident == cmd->ident)
+				chan->ident = 0;
+		}
 		return 0;
+	}
 
 	list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) {
 		if (chan->ident != cmd->ident)
 			continue;
 
-		l2cap_chan_hold(chan);
+		if (!l2cap_chan_hold_unless_zero(chan))
+			continue;
 		l2cap_chan_lock(chan);
 
 		l2cap_chan_del(chan, ECONNRESET);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index b34e7da8d906..c138aa4ae266 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1499,6 +1499,10 @@ static void l2cap_sock_cleanup_listen(struct sock *parent)
 	 * pin it (hold_unless_zero() additionally skips a chan already past
 	 * its last reference).  We then drop the sk lock before taking
 	 * chan->lock, so sk and chan locks are never held together.
+	 *
+	 * Since we cannot call l2cap_chan_close() without conn->lock,
+	 * schedule l2cap_chan_timeout to close the channel; it already
+	 * acquires conn->lock -> chan->lock in the correct order.
 	 */
 	while ((sk = bt_accept_dequeue(parent, NULL))) {
 		struct l2cap_chan *chan;
@@ -1516,14 +1520,12 @@ static void l2cap_sock_cleanup_listen(struct sock *parent)
 		       state_to_string(chan->state));
 
 		l2cap_chan_lock(chan);
-		__clear_chan_timer(chan);
-		l2cap_chan_close(chan, ECONNRESET);
-		/* l2cap_conn_del() may already have killed this socket
-		 * (it sets SOCK_DEAD); skip the duplicate to avoid a
-		 * double sock_put()/l2cap_chan_put().
+		/* Since we cannot call l2cap_chan_close() without
+		 * conn->lock, schedule its timer to trigger the close
+		 * and cleanup of this channel.
 		 */
-		if (!sock_flag(sk, SOCK_DEAD))
-			l2cap_sock_kill(sk);
+		if (chan->conn)
+			__set_chan_timer(chan, 0);
 		l2cap_chan_unlock(chan);
 
 		l2cap_chan_put(chan);
diff --git a/net/core/filter.c b/net/core/filter.c
index 9590877b0714..80439767e0ee 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2869,7 +2869,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 
 		psge->length = start - offset;
 		rsge.length -= psge->length;
-		rsge.offset += start;
+		rsge.offset += start - offset;
 
 		sk_msg_iter_var_next(i);
 		sg_unmark_end(psge);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0d3cc115f2e7..c02f0a507ba8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6823,6 +6823,11 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off,
 	skb_copy_from_linear_data_offset(skb, off, data, new_hlen);
 	skb->len -= off;
 
+	/* Remove SKBFL_MANAGED_FRAG_REFS instead of trying to honour it
+	 * while refcounting frags below.
+	 */
+	skb_zcopy_downgrade_managed(skb);
+
 	memcpy((struct skb_shared_info *)(data + size),
 	       skb_shinfo(skb),
 	       offsetof(struct skb_shared_info,
@@ -6936,6 +6941,11 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off,
 		return -ENOMEM;
 	size = SKB_WITH_OVERHEAD(size);
 
+	/* Remove SKBFL_MANAGED_FRAG_REFS instead of trying to honour it
+	 * while refcounting frags below.
+	 */
+	skb_zcopy_downgrade_managed(skb);
+
 	memcpy((struct skb_shared_info *)(data + size),
 	       skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0]));
 	if (skb_orphan_frags(skb, gfp_mask)) {
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 4366cbac3f06..6fd642d2278d 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -143,7 +143,7 @@ static void ah_output_done(void *data, int err)
 	}
 
 	kfree(AH_SKB_CB(skb)->tmp);
-	xfrm_output_resume(skb->sk, skb, err);
+	xfrm_output_resume(skb_to_full_sk(skb), skb, err);
 }
 
 static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 6a5febbdbee4..513c8215c947 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -419,8 +419,8 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			return err;
 	}
 
-	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
-	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
+	if (ALIGN(skb->data_len + tailen, L1_CACHE_BYTES) >
+	    PAGE_SIZE)
 		goto cow;
 
 	if (!skb_cloned(skb)) {
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 5476b6536eb7..bb84a78b80f6 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1013,7 +1013,7 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp)
 	list_for_each(p, &idev->addr_list) {
 		struct inet6_ifaddr *ifa
 			= list_entry(p, struct inet6_ifaddr, if_list);
-		if (ifp_scope > ipv6_addr_src_scope(&ifa->addr))
+		if (ifp_scope >= ipv6_addr_src_scope(&ifa->addr))
 			break;
 	}
 
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index de1e68199a01..76f7a2de9108 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -337,7 +337,7 @@ static void ah6_output_done(void *data, int err)
 	ah6_restore_hdrs(top_iph, iph_ext, extlen);
 
 	kfree(AH_SKB_CB(skb)->tmp);
-	xfrm_output_resume(skb->sk, skb, err);
+	xfrm_output_resume(skb_to_full_sk(skb), skb, err);
 }
 
 static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 9c06c5a1419d..57481e423e59 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -448,8 +448,8 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 			return err;
 	}
 
-	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
-	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
+	if (ALIGN(skb->data_len + tailen, L1_CACHE_BYTES) >
+	    PAGE_SIZE)
 		goto cow;
 
 	if (!skb_cloned(skb)) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b106e5fef9cb..636f0120d7e3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -481,6 +481,9 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 		const struct fib6_nh *nh = sibling->fib6_nh;
 		int nh_upper_bound;
 
+		if (!READ_ONCE(first->fib6_nsiblings))
+			break;
+
 		nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound);
 		if (hash > nh_upper_bound)
 			continue;
@@ -5902,6 +5905,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 
 				goto nla_put_failure;
 			}
+			if (!READ_ONCE(rt->fib6_nsiblings))
+				break;
 		}
 
 		rcu_read_unlock();
diff --git a/net/key/af_key.c b/net/key/af_key.c
index a166a88d8788..9cffeef18cd9 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3564,7 +3564,7 @@ static int set_ipsecrequest(struct sk_buff *skb,
 #ifdef CONFIG_NET_KEY_MIGRATE
 static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			      const struct xfrm_migrate *m, int num_bundles,
-			      const struct xfrm_kmaddress *k,
+			      const struct xfrm_kmaddress *k, struct net *net,
 			      const struct xfrm_encap_tmpl *encap)
 {
 	int i;
@@ -3669,7 +3669,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	}
 
 	/* broadcast migrate message to sockets */
-	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, net);
 
 	return 0;
 
@@ -3680,7 +3680,7 @@ err:
 #else
 static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			      const struct xfrm_migrate *m, int num_bundles,
-			      const struct xfrm_kmaddress *k,
+			      const struct xfrm_kmaddress *k, struct net *net,
 			      const struct xfrm_encap_tmpl *encap)
 {
 	return -ENOPROTOOPT;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 1d2568bb6bc2..66e12fb0c646 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -9403,6 +9403,8 @@ static int sctp_wait_for_connect(struct sctp_association *asoc, long *timeo_p)
 		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
 		lock_sock(sk);
+		if (sk != asoc->base.sk)
+			goto do_error;
 
 		*timeo_p = current_timeo;
 	}
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index b143290a311d..b10666937c49 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -205,6 +205,7 @@ static u16 virtio_transport_get_type(struct sock *sk)
 static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info,
 						  size_t payload_len,
 						  bool zcopy,
+						  struct ubuf_info *uarg,
 						  u32 src_cid,
 						  u32 src_port,
 						  u32 dst_cid,
@@ -245,6 +246,12 @@ static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *
 	if (info->msg && payload_len > 0) {
 		int err;
 
+		/* Bind the zerocopy lifetime before filling frags so error
+		 * rollback frees managed fixed-buffer pages through
+		 * the uarg-aware path.
+		 */
+		skb_zcopy_set(skb, uarg, NULL);
+
 		err = virtio_transport_fill_skb(skb, info, payload_len, zcopy);
 		if (err)
 			goto out;
@@ -364,6 +371,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 		skb_len = min(max_skb_len, rest_len);
 
 		skb = virtio_transport_alloc_skb(info, skb_len, can_zcopy,
+						 uarg,
 						 src_cid, src_port,
 						 dst_cid, dst_port);
 		if (!skb) {
@@ -371,8 +379,6 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 			break;
 		}
 
-		skb_zcopy_set(skb, uarg, NULL);
-
 		virtio_transport_inc_tx_pkt(vvs, skb);
 
 		ret = t_ops->send_pkt(skb, info->net);
@@ -1183,7 +1189,7 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t,
 	if (!t)
 		return -ENOTCONN;
 
-	reply = virtio_transport_alloc_skb(&info, 0, false,
+	reply = virtio_transport_alloc_skb(&info, 0, false, NULL,
 					   le64_to_cpu(hdr->dst_cid),
 					   le32_to_cpu(hdr->dst_port),
 					   le64_to_cpu(hdr->src_cid),
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index f65291eba1f6..e4c2cd24936d 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -797,9 +797,12 @@ static void xfrm_trans_reinject(struct work_struct *work)
 	spin_unlock_bh(&trans->queue_lock);
 
 	local_bh_disable();
-	while ((skb = __skb_dequeue(&queue)))
-		XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net,
-					       NULL, skb);
+	while ((skb = __skb_dequeue(&queue))) {
+		struct net *net = XFRM_TRANS_SKB_CB(skb)->net;
+
+		XFRM_TRANS_SKB_CB(skb)->finish(net, NULL, skb);
+		put_net(net);
+	}
 	local_bh_enable();
 }
 
@@ -808,6 +811,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 				       struct sk_buff *))
 {
 	struct xfrm_trans_tasklet *trans;
+	struct net *hold_net;
 
 	trans = this_cpu_ptr(&xfrm_trans_tasklet);
 
@@ -816,8 +820,12 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 
 	BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));
 
+	hold_net = maybe_get_net(net);
+	if (!hold_net)
+		return -ENODEV;
+
 	XFRM_TRANS_SKB_CB(skb)->finish = finish;
-	XFRM_TRANS_SKB_CB(skb)->net = net;
+	XFRM_TRANS_SKB_CB(skb)->net = hold_net;
 	spin_lock_bh(&trans->queue_lock);
 	__skb_queue_tail(&trans->queue, skb);
 	spin_unlock_bh(&trans->queue_lock);
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index 5f38dff16177..671d48f8c937 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -51,11 +51,15 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
 	struct scatterlist *dsg;
 	int len, dlen;
 
-	if (unlikely(err))
-		goto out_free_req;
+	if (unlikely(!req))
+		return err;
 
 	extra = acomp_request_extra(req);
 	dsg = extra->sg;
+
+	if (unlikely(err))
+		goto out_free_req;
+
 	dlen = req->dlen;
 
 	pskb_trim_unique(skb, 0);
@@ -84,10 +88,10 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
 		skb_shinfo(skb)->nr_frags++;
 	} while ((dlen -= len));
 
-	for (; dsg; dsg = sg_next(dsg))
+out_free_req:
+	for (; dsg && sg_page(dsg); dsg = sg_next(dsg))
 		__free_page(sg_page(dsg));
 
-out_free_req:
 	acomp_request_free(req);
 	return err;
 }
diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
index 97bc979e55ba..6c6bbc040517 100644
--- a/net/xfrm/xfrm_iptfs.c
+++ b/net/xfrm/xfrm_iptfs.c
@@ -2650,7 +2650,8 @@ static void __iptfs_init_state(struct xfrm_state *x,
 	x->props.enc_hdr_len = sizeof(struct ip_iptfs_hdr);
 
 	/* Always keep a module reference when x->mode_data is set */
-	__module_get(x->mode_cbs->owner);
+	if (x->mode_data != xtfs)
+		__module_get(x->mode_cbs->owner);
 
 	x->mode_data = xtfs;
 	xtfs->x = x;
@@ -2658,22 +2659,39 @@ static void __iptfs_init_state(struct xfrm_state *x,
 
 static int iptfs_clone_state(struct xfrm_state *x, struct xfrm_state *orig)
 {
+	struct skb_wseq *w_saved = NULL;
 	struct xfrm_iptfs_data *xtfs;
 
 	xtfs = kmemdup(orig->mode_data, sizeof(*xtfs), GFP_KERNEL);
 	if (!xtfs)
 		return -ENOMEM;
 
-	xtfs->ra_newskb = NULL;
 	if (xtfs->cfg.reorder_win_size) {
-		xtfs->w_saved = kzalloc_objs(*xtfs->w_saved,
-					     xtfs->cfg.reorder_win_size);
-		if (!xtfs->w_saved) {
+		w_saved = kzalloc_objs(*w_saved, xtfs->cfg.reorder_win_size);
+		if (!w_saved) {
 			kfree_sensitive(xtfs);
 			return -ENOMEM;
 		}
 	}
+	xtfs->w_saved = w_saved;
+
+	__skb_queue_head_init(&xtfs->queue);
+	xtfs->queue_size = 0;
+	hrtimer_setup(&xtfs->iptfs_timer, iptfs_delay_timer, CLOCK_MONOTONIC,
+		      IPTFS_HRTIMER_MODE);
+
+	spin_lock_init(&xtfs->drop_lock);
+	hrtimer_setup(&xtfs->drop_timer, iptfs_drop_timer, CLOCK_MONOTONIC,
+		      IPTFS_HRTIMER_MODE);
 
+	xtfs->w_seq_set = false;
+	xtfs->w_wantseq = 0;
+	xtfs->w_savedlen = 0;
+	xtfs->ra_newskb = NULL;
+	xtfs->ra_wantseq = 0;
+	xtfs->ra_runtlen = 0;
+
+	__module_get(x->mode_cbs->owner);
 	x->mode_data = xtfs;
 	xtfs->x = x;
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c944327ce66c..dd09d2063da2 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4276,21 +4276,21 @@ out_byidx:
 	return -ENOMEM;
 }
 
-static void xfrm_policy_fini(struct net *net)
+static void __net_exit xfrm_net_pre_exit(struct net *net)
 {
-	struct xfrm_pol_inexact_bin *b, *t;
-	unsigned int sz;
-	int dir;
-
 	disable_work_sync(&net->xfrm.policy_hthresh.work);
-
 	flush_work(&net->xfrm.policy_hash_work);
 #ifdef CONFIG_XFRM_SUB_POLICY
 	xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false);
 #endif
 	xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false);
+}
 
-	synchronize_rcu();
+static void xfrm_policy_fini(struct net *net)
+{
+	struct xfrm_pol_inexact_bin *b, *t;
+	unsigned int sz;
+	int dir;
 
 	WARN_ON(!list_empty(&net->xfrm.policy_all));
 
@@ -4368,6 +4368,7 @@ static void __net_exit xfrm_net_exit(struct net *net)
 
 static struct pernet_operations __net_initdata xfrm_net_ops = {
 	.init = xfrm_net_init,
+	.pre_exit = xfrm_net_pre_exit,
 	.exit = xfrm_net_exit,
 };
 
@@ -4703,7 +4704,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	}
 
 	/* Stage 5 - announce */
-	km_migrate(sel, dir, type, m, num_migrate, k, encap);
+	km_migrate(sel, dir, type, m, num_migrate, k, net, encap);
 
 	xfrm_pol_put(pol);
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 686014d39429..589c3b6e4679 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2837,7 +2837,7 @@ EXPORT_SYMBOL(km_policy_expired);
 #ifdef CONFIG_XFRM_MIGRATE
 int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	       const struct xfrm_migrate *m, int num_migrate,
-	       const struct xfrm_kmaddress *k,
+	       const struct xfrm_kmaddress *k, struct net *net,
 	       const struct xfrm_encap_tmpl *encap)
 {
 	int err = -EINVAL;
@@ -2848,7 +2848,7 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
 		if (km->migrate) {
 			ret = km->migrate(sel, dir, type, m, num_migrate, k,
-					  encap);
+					  net, encap);
 			if (!ret)
 				err = ret;
 		}
@@ -3114,10 +3114,14 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
 	const struct xfrm_type *type = READ_ONCE(x->type);
 	struct crypto_aead *aead;
 	u32 blksize, net_adj = 0;
+	u32 overhead, payload_mtu;
 
 	if (x->km.state != XFRM_STATE_VALID ||
-	    !type || type->proto != IPPROTO_ESP)
+	    !type || type->proto != IPPROTO_ESP) {
+		if (mtu <= x->props.header_len)
+			return 1;
 		return mtu - x->props.header_len;
+	}
 
 	aead = x->data;
 	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
@@ -3140,8 +3144,17 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
 		break;
 	}
 
-	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
-		 net_adj) & ~(blksize - 1)) + net_adj - 2;
+	overhead = x->props.header_len + crypto_aead_authsize(aead) + net_adj;
+	if (mtu <= overhead)
+		return 1;
+
+	payload_mtu = mtu - overhead;
+	payload_mtu &= ~(blksize - 1);
+	if (payload_mtu <= 2)
+		return 1;
+
+	return payload_mtu + net_adj - 2;
+
 }
 EXPORT_SYMBOL_GPL(xfrm_state_mtu);
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 38a90e5ee3d9..71a4b7278eba 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -3271,10 +3271,9 @@ out_cancel:
 
 static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			     const struct xfrm_migrate *m, int num_migrate,
-			     const struct xfrm_kmaddress *k,
+			     const struct xfrm_kmaddress *k, struct net *net,
 			     const struct xfrm_encap_tmpl *encap)
 {
-	struct net *net = &init_net;
 	struct sk_buff *skb;
 	int err;
 
@@ -3292,7 +3291,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 #else
 static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			     const struct xfrm_migrate *m, int num_migrate,
-			     const struct xfrm_kmaddress *k,
+			     const struct xfrm_kmaddress *k, struct net *net,
 			     const struct xfrm_encap_tmpl *encap)
 {
 	return -ENOPROTOOPT;