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

Cross-merge networking fixes after downstream PR (net-6.19-rc6).

No conflicts, or adjacent changes.

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

24 files changed, 143 insertions, 103 deletions

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index a9f5b1a68356..cbc3a75d7326 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4420,6 +4420,7 @@ static int hci_le_set_event_mask_sync(struct hci_dev *hdev)
 	if (bis_capable(hdev)) {
 		events[1] |= 0x20;	/* LE PA Report */
 		events[1] |= 0x40;	/* LE PA Sync Established */
+		events[1] |= 0x80;	/* LE PA Sync Lost */
 		events[3] |= 0x04;	/* LE Create BIG Complete */
 		events[3] |= 0x08;	/* LE Terminate BIG Complete */
 		events[3] |= 0x10;	/* LE BIG Sync Established */
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 655efac6f133..26cfcfdc45eb 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -1294,8 +1294,6 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			batch_size = NAPI_POLL_WEIGHT;
 		else if (batch_size > TEST_XDP_MAX_BATCH)
 			return -E2BIG;
-
-		headroom += sizeof(struct xdp_page_head);
 	} else if (batch_size) {
 		return -EINVAL;
 	}
@@ -1308,16 +1306,26 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 		/* There can't be user provided data before the meta data */
 		if (ctx->data_meta || ctx->data_end > kattr->test.data_size_in ||
 		    ctx->data > ctx->data_end ||
-		    unlikely(xdp_metalen_invalid(ctx->data)) ||
 		    (do_live && (kattr->test.data_out || kattr->test.ctx_out)))
 			goto free_ctx;
-		/* Meta data is allocated from the headroom */
-		headroom -= ctx->data;
 
 		meta_sz = ctx->data;
+		if (xdp_metalen_invalid(meta_sz) || meta_sz > headroom - sizeof(struct xdp_frame))
+			goto free_ctx;
+
+		/* Meta data is allocated from the headroom */
+		headroom -= meta_sz;
 		linear_sz = ctx->data_end;
 	}
 
+	/* The xdp_page_head structure takes up space in each page, limiting the
+         * size of the packet data; add the extra size to headroom here to make
+         * sure it's accounted in the length checks below, but not in the
+         * metadata size check above.
+         */
+        if (do_live)
+		headroom += sizeof(struct xdp_page_head);
+
 	max_linear_sz = PAGE_SIZE - headroom - tailroom;
 	linear_sz = min_t(u32, linear_sz, max_linear_sz);
 
@@ -1355,13 +1363,13 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 			if (sinfo->nr_frags == MAX_SKB_FRAGS) {
 				ret = -ENOMEM;
-				goto out;
+				goto out_put_dev;
 			}
 
 			page = alloc_page(GFP_KERNEL);
 			if (!page) {
 				ret = -ENOMEM;
-				goto out;
+				goto out_put_dev;
 			}
 
 			frag = &sinfo->frags[sinfo->nr_frags++];
@@ -1373,7 +1381,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			if (copy_from_user(page_address(page), data_in + size,
 					   data_len)) {
 				ret = -EFAULT;
-				goto out;
+				goto out_put_dev;
 			}
 			sinfo->xdp_frags_size += data_len;
 			size += data_len;
@@ -1388,6 +1396,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 		ret = bpf_test_run_xdp_live(prog, &xdp, repeat, batch_size, &duration);
 	else
 		ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
+out_put_dev:
 	/* We convert the xdp_buff back to an xdp_md before checking the return
 	 * code so the reference count of any held netdevice will be decremented
 	 * even if the test run failed.
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 58d22e2b85fc..0501ffcb8a3d 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -70,7 +70,7 @@ static inline int has_expired(const struct net_bridge *br,
 {
 	return !test_bit(BR_FDB_STATIC, &fdb->flags) &&
 	       !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags) &&
-	       time_before_eq(fdb->updated + hold_time(br), jiffies);
+	       time_before_eq(READ_ONCE(fdb->updated) + hold_time(br), jiffies);
 }
 
 static int fdb_to_nud(const struct net_bridge *br,
@@ -126,9 +126,9 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
 	if (nla_put_u32(skb, NDA_FLAGS_EXT, ext_flags))
 		goto nla_put_failure;
 
-	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
+	ci.ndm_used	 = jiffies_to_clock_t(now - READ_ONCE(fdb->used));
 	ci.ndm_confirmed = 0;
-	ci.ndm_updated	 = jiffies_to_clock_t(now - fdb->updated);
+	ci.ndm_updated	 = jiffies_to_clock_t(now - READ_ONCE(fdb->updated));
 	ci.ndm_refcnt	 = 0;
 	if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
 		goto nla_put_failure;
@@ -551,7 +551,7 @@ void br_fdb_cleanup(struct work_struct *work)
 	 */
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) {
-		unsigned long this_timer = f->updated + delay;
+		unsigned long this_timer = READ_ONCE(f->updated) + delay;
 
 		if (test_bit(BR_FDB_STATIC, &f->flags) ||
 		    test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags)) {
@@ -924,6 +924,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf,
 {
 	struct net_bridge_fdb_entry *f;
 	struct __fdb_entry *fe = buf;
+	unsigned long delta;
 	int num = 0;
 
 	memset(buf, 0, maxnum*sizeof(struct __fdb_entry));
@@ -953,8 +954,11 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf,
 		fe->port_hi = f->dst->port_no >> 8;
 
 		fe->is_local = test_bit(BR_FDB_LOCAL, &f->flags);
-		if (!test_bit(BR_FDB_STATIC, &f->flags))
-			fe->ageing_timer_value = jiffies_delta_to_clock_t(jiffies - f->updated);
+		if (!test_bit(BR_FDB_STATIC, &f->flags)) {
+			delta = jiffies - READ_ONCE(f->updated);
+			fe->ageing_timer_value =
+				jiffies_delta_to_clock_t(delta);
+		}
 		++fe;
 		++num;
 	}
@@ -1002,8 +1006,8 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 			unsigned long now = jiffies;
 			bool fdb_modified = false;
 
-			if (now != fdb->updated) {
-				fdb->updated = now;
+			if (now != READ_ONCE(fdb->updated)) {
+				WRITE_ONCE(fdb->updated, now);
 				fdb_modified = __fdb_mark_active(fdb);
 			}
 
@@ -1242,10 +1246,10 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
 	if (fdb_handle_notify(fdb, notify))
 		modified = true;
 
-	fdb->used = jiffies;
+	WRITE_ONCE(fdb->used, jiffies);
 	if (modified) {
 		if (refresh)
-			fdb->updated = jiffies;
+			WRITE_ONCE(fdb->updated, jiffies);
 		fdb_notify(br, fdb, RTM_NEWNEIGH, true);
 	}
 
@@ -1556,7 +1560,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
 			goto err_unlock;
 		}
 
-		fdb->updated = jiffies;
+		WRITE_ONCE(fdb->updated, jiffies);
 
 		if (READ_ONCE(fdb->dst) != p) {
 			WRITE_ONCE(fdb->dst, p);
@@ -1565,7 +1569,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
 
 		if (test_and_set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) {
 			/* Refresh entry */
-			fdb->used = jiffies;
+			WRITE_ONCE(fdb->used, jiffies);
 		} else {
 			modified = true;
 		}
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 777fa869c1a1..e355a15bf5ab 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -221,8 +221,8 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 		if (test_bit(BR_FDB_LOCAL, &dst->flags))
 			return br_pass_frame_up(skb, false);
 
-		if (now != dst->used)
-			dst->used = now;
+		if (now != READ_ONCE(dst->used))
+			WRITE_ONCE(dst->used, now);
 		br_forward(dst->dst, skb, local_rcv, false);
 	} else {
 		if (!mcast_hit)
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index 613a911dda10..8656ab388c83 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1695,8 +1695,16 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session,
 
 		j1939_session_timers_cancel(session);
 		j1939_session_cancel(session, J1939_XTP_ABORT_BUSY);
-		if (session->transmission)
+		if (session->transmission) {
 			j1939_session_deactivate_activate_next(session);
+		} else if (session->state == J1939_SESSION_WAITING_ABORT) {
+			/* Force deactivation for the receiver.
+			 * If we rely on the timer starting in j1939_session_cancel,
+			 * a second RTS call here will cancel that timer and fail
+			 * to restart it because the state is already WAITING_ABORT.
+			 */
+			j1939_session_deactivate_activate_next(session);
+		}
 
 		return -EBUSY;
 	}
diff --git a/net/can/raw.c b/net/can/raw.c
index be1ef7cf4204..12293363413c 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -49,8 +49,8 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <linux/can.h>
+#include <linux/can/can-ml.h>
 #include <linux/can/core.h>
-#include <linux/can/dev.h> /* for can_is_canxl_dev_mtu() */
 #include <linux/can/skb.h>
 #include <linux/can/raw.h>
 #include <net/sock.h>
@@ -892,58 +892,21 @@ static void raw_put_canxl_vcid(struct raw_sock *ro, struct sk_buff *skb)
 	}
 }
 
-static inline bool raw_dev_cc_enabled(struct net_device *dev,
-				      struct can_priv *priv)
-{
-	/* The CANXL-only mode disables error-signalling on the CAN bus
-	 * which is needed to send CAN CC/FD frames
-	 */
-	if (priv)
-		return !can_dev_in_xl_only_mode(priv);
-
-	/* virtual CAN interfaces always support CAN CC */
-	return true;
-}
-
-static inline bool raw_dev_fd_enabled(struct net_device *dev,
-				      struct can_priv *priv)
-{
-	/* check FD ctrlmode on real CAN interfaces */
-	if (priv)
-		return (priv->ctrlmode & CAN_CTRLMODE_FD);
-
-	/* check MTU for virtual CAN FD interfaces */
-	return (READ_ONCE(dev->mtu) >= CANFD_MTU);
-}
-
-static inline bool raw_dev_xl_enabled(struct net_device *dev,
-				      struct can_priv *priv)
-{
-	/* check XL ctrlmode on real CAN interfaces */
-	if (priv)
-		return (priv->ctrlmode & CAN_CTRLMODE_XL);
-
-	/* check MTU for virtual CAN XL interfaces */
-	return can_is_canxl_dev_mtu(READ_ONCE(dev->mtu));
-}
-
 static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb,
 				      struct net_device *dev)
 {
-	struct can_priv *priv = safe_candev_priv(dev);
-
 	/* Classical CAN */
-	if (can_is_can_skb(skb) && raw_dev_cc_enabled(dev, priv))
+	if (can_is_can_skb(skb) && can_cap_enabled(dev, CAN_CAP_CC))
 		return CAN_MTU;
 
 	/* CAN FD */
 	if (ro->fd_frames && can_is_canfd_skb(skb) &&
-	    raw_dev_fd_enabled(dev, priv))
+	    can_cap_enabled(dev, CAN_CAP_FD))
 		return CANFD_MTU;
 
 	/* CAN XL */
 	if (ro->xl_frames && can_is_canxl_skb(skb) &&
-	    raw_dev_xl_enabled(dev, priv))
+	    can_cap_enabled(dev, CAN_CAP_XL))
 		return CANXL_MTU;
 
 	return 0;
@@ -982,6 +945,12 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	if (!dev)
 		return -ENXIO;
 
+	/* no sending on a CAN device in read-only mode */
+	if (can_cap_enabled(dev, CAN_CAP_RO)) {
+		err = -EACCES;
+		goto put_dev;
+	}
+
 	skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv),
 				  msg->msg_flags & MSG_DONTWAIT, &err);
 	if (!skb)
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 833e57849c1d..c9d50c0dcd33 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -2376,7 +2376,9 @@ static int process_auth_done(struct ceph_connection *con, void *p, void *end)
 
 	ceph_decode_64_safe(&p, end, global_id, bad);
 	ceph_decode_32_safe(&p, end, con->v2.con_mode, bad);
+
 	ceph_decode_32_safe(&p, end, payload_len, bad);
+	ceph_decode_need(&p, end, payload_len, bad);
 
 	dout("%s con %p global_id %llu con_mode %d payload_len %d\n",
 	     __func__, con, global_id, con->v2.con_mode, payload_len);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index c227ececa925..fa8dd2a20f7d 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -1417,7 +1417,7 @@ static int mon_handle_auth_done(struct ceph_connection *con,
 	if (!ret)
 		finish_hunting(monc);
 	mutex_unlock(&monc->mutex);
-	return 0;
+	return ret;
 }
 
 static int mon_handle_auth_bad_method(struct ceph_connection *con,
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 3667319b949d..610e584524d1 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1586,6 +1586,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 	struct ceph_pg_pool_info *pi;
 	struct ceph_pg pgid, last_pgid;
 	struct ceph_osds up, acting;
+	bool should_be_paused;
 	bool is_read = t->flags & CEPH_OSD_FLAG_READ;
 	bool is_write = t->flags & CEPH_OSD_FLAG_WRITE;
 	bool force_resend = false;
@@ -1654,10 +1655,16 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 				 &last_pgid))
 		force_resend = true;
 
-	if (t->paused && !target_should_be_paused(osdc, t, pi)) {
-		t->paused = false;
+	should_be_paused = target_should_be_paused(osdc, t, pi);
+	if (t->paused && !should_be_paused) {
 		unpaused = true;
 	}
+	if (t->paused != should_be_paused) {
+		dout("%s t %p paused %d -> %d\n", __func__, t, t->paused,
+		     should_be_paused);
+		t->paused = should_be_paused;
+	}
+
 	legacy_change = ceph_pg_compare(&t->pgid, &pgid) ||
 			ceph_osds_changed(&t->acting, &acting,
 					  t->used_replica || any_change);
@@ -4281,6 +4288,9 @@ static void osd_fault(struct ceph_connection *con)
 		goto out_unlock;
 	}
 
+	osd->o_sparse_op_idx = -1;
+	ceph_init_sparse_read(&osd->o_sparse_read);
+
 	if (!reopen_osd(osd))
 		kick_osd_requests(osd);
 	maybe_request_map(osdc);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 34b3ab59602f..92a44026de29 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -241,22 +241,26 @@ static struct crush_choose_arg_map *alloc_choose_arg_map(void)
 
 static void free_choose_arg_map(struct crush_choose_arg_map *arg_map)
 {
-	if (arg_map) {
-		int i, j;
+	int i, j;
+
+	if (!arg_map)
+		return;
 
-		WARN_ON(!RB_EMPTY_NODE(&arg_map->node));
+	WARN_ON(!RB_EMPTY_NODE(&arg_map->node));
 
+	if (arg_map->args) {
 		for (i = 0; i < arg_map->size; i++) {
 			struct crush_choose_arg *arg = &arg_map->args[i];
-
-			for (j = 0; j < arg->weight_set_size; j++)
-				kfree(arg->weight_set[j].weights);
-			kfree(arg->weight_set);
+			if (arg->weight_set) {
+				for (j = 0; j < arg->weight_set_size; j++)
+					kfree(arg->weight_set[j].weights);
+				kfree(arg->weight_set);
+			}
 			kfree(arg->ids);
 		}
 		kfree(arg_map->args);
-		kfree(arg_map);
 	}
+	kfree(arg_map);
 }
 
 DEFINE_RB_FUNCS(choose_arg_map, struct crush_choose_arg_map, choose_args_index,
@@ -1979,11 +1983,13 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, bool msgr2,
 			 sizeof(u64) + sizeof(u32), e_inval);
 	ceph_decode_copy(p, &fsid, sizeof(fsid));
 	epoch = ceph_decode_32(p);
-	BUG_ON(epoch != map->epoch+1);
 	ceph_decode_copy(p, &modified, sizeof(modified));
 	new_pool_max = ceph_decode_64(p);
 	new_flags = ceph_decode_32(p);
 
+	if (epoch != map->epoch + 1)
+		goto e_inval;
+
 	/* full map? */
 	ceph_decode_32_safe(p, end, len, e_inval);
 	if (len > 0) {
diff --git a/net/core/dev.c b/net/core/dev.c
index c711da335510..2661b68f5be3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -477,15 +477,21 @@ static const unsigned short netdev_lock_type[] = {
 	 ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
 	 ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
 	 ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
+	 ARPHRD_CAN, ARPHRD_MCTP,
 	 ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
-	 ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
+	 ARPHRD_RAWHDLC, ARPHRD_RAWIP,
+	 ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
 	 ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
 	 ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
 	 ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
 	 ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
 	 ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
-	 ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
-	 ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
+	 ARPHRD_IEEE80211_RADIOTAP,
+	 ARPHRD_IEEE802154, ARPHRD_IEEE802154_MONITOR,
+	 ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
+	 ARPHRD_CAIF, ARPHRD_IP6GRE, ARPHRD_NETLINK, ARPHRD_6LOWPAN,
+	 ARPHRD_VSOCKMON,
+	 ARPHRD_VOID, ARPHRD_NONE};
 
 static const char *const netdev_lock_name[] = {
 	"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
@@ -494,15 +500,21 @@ static const char *const netdev_lock_name[] = {
 	"_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
 	"_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
 	"_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
+	"_xmit_CAN", "_xmit_MCTP",
 	"_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
-	"_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
+	"_xmit_RAWHDLC", "_xmit_RAWIP",
+	"_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
 	"_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
 	"_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
 	"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
 	"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
 	"_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
-	"_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
-	"_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
+	"_xmit_IEEE80211_RADIOTAP",
+	"_xmit_IEEE802154", "_xmit_IEEE802154_MONITOR",
+	"_xmit_PHONET", "_xmit_PHONET_PIPE",
+	"_xmit_CAIF", "_xmit_IP6GRE", "_xmit_NETLINK", "_xmit_6LOWPAN",
+	"_xmit_VSOCKMON",
+	"_xmit_VOID", "_xmit_NONE"};
 
 static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
 static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
@@ -515,6 +527,7 @@ static inline unsigned short netdev_lock_pos(unsigned short dev_type)
 		if (netdev_lock_type[i] == dev_type)
 			return i;
 	/* the last key is used by default */
+	WARN_ONCE(1, "netdev_lock_pos() could not find dev_type=%u\n", dev_type);
 	return ARRAY_SIZE(netdev_lock_type) - 1;
 }
 
@@ -4189,8 +4202,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	do {
 		if (first_n && !defer_count) {
 			defer_count = atomic_long_inc_return(&q->defer_count);
-			if (unlikely(defer_count > READ_ONCE(q->limit))) {
-				kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_DROP);
+			if (unlikely(defer_count > READ_ONCE(net_hotdata.qdisc_max_burst))) {
+				kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_BURST_DROP);
 				return NET_XMIT_DROP;
 			}
 		}
@@ -4208,7 +4221,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	ll_list = llist_del_all(&q->defer_list);
 	/* There is a small race because we clear defer_count not atomically
 	 * with the prior llist_del_all(). This means defer_list could grow
-	 * over q->limit.
+	 * over qdisc_max_burst.
 	 */
 	atomic_long_set(&q->defer_count, 0);
 
diff --git a/net/core/dst.c b/net/core/dst.c
index e9d35f49c9e7..1dae26c51ebe 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -68,6 +68,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
 	dst->lwtstate = NULL;
 	rcuref_init(&dst->__rcuref, 1);
 	INIT_LIST_HEAD(&dst->rt_uncached);
+	dst->rt_uncached_list = NULL;
 	dst->__use = 0;
 	dst->lastuse = jiffies;
 	dst->flags = flags;
diff --git a/net/core/hotdata.c b/net/core/hotdata.c
index dddd5c287cf0..a6db36580817 100644
--- a/net/core/hotdata.c
+++ b/net/core/hotdata.c
@@ -17,6 +17,7 @@ struct net_hotdata net_hotdata __cacheline_aligned = {
 
 	.tstamp_prequeue = 1,
 	.max_backlog = 1000,
+	.qdisc_max_burst = 1000,
 	.dev_tx_weight = 64,
 	.dev_rx_weight = 64,
 	.sysctl_max_skb_frags = MAX_SKB_FRAGS,
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 8d4decb2606f..05dd55cf8b58 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -430,6 +430,13 @@ static struct ctl_table net_core_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
+		.procname	= "qdisc_max_burst",
+		.data		= &net_hotdata.qdisc_max_burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
 		.procname	= "netdev_rss_key",
 		.data		= &netdev_rss_key,
 		.maxlen		= sizeof(int),
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 05828d4cb6cd..abd77162f5e7 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -122,8 +122,8 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x,
 						struct sk_buff *skb,
 						netdev_features_t features)
 {
-	const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x,
-					XFRM_MODE_SKB_CB(skb)->protocol);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, xo->proto);
 	__be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6)
 						     : htons(ETH_P_IP);
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 8178c44a3cdd..e13244729ad8 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -891,10 +891,17 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
 			const void *daddr, const void *saddr, unsigned int len)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
-	struct iphdr *iph;
 	struct gre_base_hdr *greh;
+	struct iphdr *iph;
+	int needed;
+
+	needed = t->hlen + sizeof(*iph);
+	if (skb_headroom(skb) < needed &&
+	    pskb_expand_head(skb, HH_DATA_ALIGN(needed - skb_headroom(skb)),
+			     0, GFP_ATOMIC))
+		return -needed;
 
-	iph = skb_push(skb, t->hlen + sizeof(*iph));
+	iph = skb_push(skb, needed);
 	greh = (struct gre_base_hdr *)(iph+1);
 	greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags);
 	greh->protocol = htons(type);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 158a30ae7c5f..50d0f5fe4e4c 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1281,7 +1281,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_changelink);
 
-int ip_tunnel_init(struct net_device *dev)
+int __ip_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
@@ -1308,10 +1308,9 @@ int ip_tunnel_init(struct net_device *dev)
 
 	if (tunnel->collect_md)
 		netif_keep_dst(dev);
-	netdev_lockdep_set_classes(dev);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ip_tunnel_init);
+EXPORT_SYMBOL_GPL(__ip_tunnel_init);
 
 void ip_tunnel_uninit(struct net_device *dev)
 {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 05f8c550a915..06aa39ae80d6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1537,9 +1537,9 @@ void rt_add_uncached_list(struct rtable *rt)
 
 void rt_del_uncached_list(struct rtable *rt)
 {
-	if (!list_empty(&rt->dst.rt_uncached)) {
-		struct uncached_list *ul = rt->dst.rt_uncached_list;
+	struct uncached_list *ul = rt->dst.rt_uncached_list;
 
+	if (ul) {
 		spin_lock_bh(&ul->lock);
 		list_del_init(&rt->dst.rt_uncached);
 		spin_unlock_bh(&ul->lock);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index fe64988a23ab..7138e0e67991 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3112,12 +3112,12 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
 			in6_ifa_hold(ifp);
 			read_unlock_bh(&idev->lock);
 
-			ipv6_del_addr(ifp);
-
 			if (!(ifp->flags & IFA_F_TEMPORARY) &&
 			    (ifp->flags & IFA_F_MANAGETEMPADDR))
 				delete_tempaddrs(idev, ifp);
 
+			ipv6_del_addr(ifp);
+
 			addrconf_verify_rtnl(net);
 			if (ipv6_addr_is_multicast(pfx)) {
 				ipv6_mc_config(net->ipv6.mc_autojoin_sk,
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 22410243ebe8..22895521a57d 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -158,8 +158,8 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x,
 						struct sk_buff *skb,
 						netdev_features_t features)
 {
-	const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x,
-					XFRM_MODE_SKB_CB(skb)->protocol);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, xo->proto);
 	__be16 type = inner_mode->family == AF_INET ? htons(ETH_P_IP)
 						    : htons(ETH_P_IPV6);
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 6405072050e0..c1f39735a236 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -844,7 +844,7 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 
 	skb_reset_network_header(skb);
 
-	if (!pskb_inet_may_pull(skb)) {
+	if (skb_vlan_inet_prepare(skb, true)) {
 		DEV_STATS_INC(tunnel->dev, rx_length_errors);
 		DEV_STATS_INC(tunnel->dev, rx_errors);
 		goto drop;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 00a8318f33a7..ddeb9cd7f383 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -148,9 +148,9 @@ void rt6_uncached_list_add(struct rt6_info *rt)
 
 void rt6_uncached_list_del(struct rt6_info *rt)
 {
-	if (!list_empty(&rt->dst.rt_uncached)) {
-		struct uncached_list *ul = rt->dst.rt_uncached_list;
+	struct uncached_list *ul = rt->dst.rt_uncached_list;
 
+	if (ul) {
 		spin_lock_bh(&ul->lock);
 		list_del_init(&rt->dst.rt_uncached);
 		spin_unlock_bh(&ul->lock);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index f4013b547438..9d59090bbe93 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -529,8 +529,10 @@ set_change_agg:
 	return 0;
 
 destroy_class:
-	qdisc_put(cl->qdisc);
-	kfree(cl);
+	if (!existing) {
+		qdisc_put(cl->qdisc);
+		kfree(cl);
+	}
 	return err;
 }
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 9e14e453b55c..98b362d51836 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -3151,6 +3151,7 @@ int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack)
 	int err;
 
 	if (family == AF_INET &&
+	    (!x->dir || x->dir == XFRM_SA_DIR_OUT) &&
 	    READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc))
 		x->props.flags |= XFRM_STATE_NOPMTUDISC;