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

Merge in late fixes to prepare for the 6.17 net-next PR.

Conflicts:

net/core/neighbour.c
  1bbb76a89948 ("neighbour: Fix null-ptr-deref in neigh_flush_dev().")
  13a936bb99fb ("neighbour: Protect tbl->phash_buckets[] with a dedicated mutex.")
  03dc03fa0432 ("neighbor: Add NTF_EXT_VALIDATED flag for externally validated entries")

Adjacent changes:

drivers/net/usb/usbnet.c
  0d9cfc9b8cb1 ("net: usbnet: Avoid potential RCU stall on LINK_CHANGE event")
  2c04d279e857 ("net: usb: Convert tasklet API to new bottom half workqueue mechanism")

net/ipv6/route.c
  31d7d67ba127 ("ipv6: annotate data-races around rt->fib6_nsiblings")
  1caf27297215 ("ipv6: adopt dst_dev() helper")
  3b3ccf9ed05e ("net: Remove unnecessary NULL check for lwtunnel_fill_encap()")

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

18 files changed, 247 insertions, 121 deletions

diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index 4d85b29a17b78..ebefc274b50a5 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -49,7 +49,7 @@ struct __packed pcan_ufd_fw_info {
 	__le32	ser_no;		/* S/N */
 	__le32	flags;		/* special functions */
 
-	/* extended data when type == PCAN_USBFD_TYPE_EXT */
+	/* extended data when type >= PCAN_USBFD_TYPE_EXT */
 	u8	cmd_out_ep;	/* ep for cmd */
 	u8	cmd_in_ep;	/* ep for replies */
 	u8	data_out_ep[2];	/* ep for CANx TX */
@@ -982,10 +982,11 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev)
 			dev->can.ctrlmode |= CAN_CTRLMODE_FD_NON_ISO;
 		}
 
-		/* if vendor rsp is of type 2, then it contains EP numbers to
-		 * use for cmds pipes. If not, then default EP should be used.
+		/* if vendor rsp type is greater than or equal to 2, then it
+		 * contains EP numbers to use for cmds pipes. If not, then
+		 * default EP should be used.
 		 */
-		if (fw_info->type != cpu_to_le16(PCAN_USBFD_TYPE_EXT)) {
+		if (le16_to_cpu(fw_info->type) < PCAN_USBFD_TYPE_EXT) {
 			fw_info->cmd_out_ep = PCAN_USBPRO_EP_CMDOUT;
 			fw_info->cmd_in_ep = PCAN_USBPRO_EP_CMDIN;
 		}
@@ -1018,11 +1019,11 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev)
 	dev->can_channel_id =
 		le32_to_cpu(pdev->usb_if->fw_info.dev_id[dev->ctrl_idx]);
 
-	/* if vendor rsp is of type 2, then it contains EP numbers to
-	 * use for data pipes. If not, then statically defined EP are used
-	 * (see peak_usb_create_dev()).
+	/* if vendor rsp type is greater than or equal to 2, then it contains EP
+	 * numbers to use for data pipes. If not, then statically defined EP are
+	 * used (see peak_usb_create_dev()).
 	 */
-	if (fw_info->type == cpu_to_le16(PCAN_USBFD_TYPE_EXT)) {
+	if (le16_to_cpu(fw_info->type) >= PCAN_USBFD_TYPE_EXT) {
 		dev->ep_msg_in = fw_info->data_in_ep;
 		dev->ep_msg_out = fw_info->data_out_ep[dev->ctrl_idx];
 	}
diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c
index c400e1c0369e3..76e490070e9c2 100644
--- a/drivers/net/dsa/microchip/ksz8.c
+++ b/drivers/net/dsa/microchip/ksz8.c
@@ -384,6 +384,9 @@ static void ksz8863_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
 	addr -= dev->info->reg_mib_cnt;
 	ctrl_addr = addr ? KSZ8863_MIB_PACKET_DROPPED_TX_0 :
 			   KSZ8863_MIB_PACKET_DROPPED_RX_0;
+	if (ksz_is_8895_family(dev) &&
+	    ctrl_addr == KSZ8863_MIB_PACKET_DROPPED_RX_0)
+		ctrl_addr = KSZ8895_MIB_PACKET_DROPPED_RX_0;
 	ctrl_addr += port;
 	ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
 
diff --git a/drivers/net/dsa/microchip/ksz8_reg.h b/drivers/net/dsa/microchip/ksz8_reg.h
index 491aa1e50175b..332408567b473 100644
--- a/drivers/net/dsa/microchip/ksz8_reg.h
+++ b/drivers/net/dsa/microchip/ksz8_reg.h
@@ -833,7 +833,9 @@
 #define KSZ8795_MIB_TOTAL_TX_1		0x105
 
 #define KSZ8863_MIB_PACKET_DROPPED_TX_0 0x100
-#define KSZ8863_MIB_PACKET_DROPPED_RX_0 0x105
+#define KSZ8863_MIB_PACKET_DROPPED_RX_0 0x103
+
+#define KSZ8895_MIB_PACKET_DROPPED_RX_0 0x105
 
 #define MIB_PACKET_DROPPED		0x0000FFFF
 
diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c
index 5cf67ba292694..30ce5fbb5b776 100644
--- a/drivers/net/ethernet/intel/igb/igb_xsk.c
+++ b/drivers/net/ethernet/intel/igb/igb_xsk.c
@@ -482,7 +482,7 @@ bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool)
 	if (!nb_pkts)
 		return true;
 
-	while (nb_pkts-- > 0) {
+	for (; i < nb_pkts; i++) {
 		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
 		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len);
 
@@ -512,7 +512,6 @@ bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool)
 
 		total_bytes += descs[i].len;
 
-		i++;
 		tx_ring->next_to_use++;
 		tx_buffer_info->next_to_watch = tx_desc;
 		if (tx_ring->next_to_use == tx_ring->count)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 60d24d8a22425..0dd3bc0f4caae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -726,6 +726,7 @@ struct mlx5e_rq {
 	struct xsk_buff_pool  *xsk_pool;
 
 	struct work_struct     recover_work;
+	struct work_struct     rx_timeout_work;
 
 	/* control */
 	struct mlx5_wq_ctrl    wq_ctrl;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index 8e25f4ef5ccce..5ae787656a7ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -331,6 +331,9 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
+	/* RO bits should be set to 0 on write */
+	MLX5_SET(pbmc_reg, in, port_buffer_size, 0);
+
 	err = mlx5e_port_set_pbmc(mdev, in);
 out:
 	kfree(in);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index e75759533ae0c..16c44d628eda6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -170,16 +170,23 @@ static int mlx5e_rx_reporter_err_rq_cqe_recover(void *ctx)
 static int mlx5e_rx_reporter_timeout_recover(void *ctx)
 {
 	struct mlx5_eq_comp *eq;
+	struct mlx5e_priv *priv;
 	struct mlx5e_rq *rq;
 	int err;
 
 	rq = ctx;
+	priv = rq->priv;
+
+	mutex_lock(&priv->state_lock);
+
 	eq = rq->cq.mcq.eq;
 
 	err = mlx5e_health_channel_eq_recover(rq->netdev, eq, rq->cq.ch_stats);
 	if (err && rq->icosq)
 		clear_bit(MLX5E_SQ_STATE_ENABLED, &rq->icosq->state);
 
+	mutex_unlock(&priv->state_lock);
+
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 727fa7c185238..6056106edcc64 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -327,6 +327,10 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 	if (unlikely(!sa_entry)) {
 		rcu_read_unlock();
 		atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_sadb_miss);
+		/* Clear secpath to prevent invalid dereference
+		 * in downstream XFRM policy checks.
+		 */
+		secpath_reset(skb);
 		return;
 	}
 	xfrm_state_hold(sa_entry->x);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 33bdb7f1e03fd..21bb88c5d3dce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -676,6 +676,27 @@ static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work)
 	mlx5e_reporter_rq_cqe_err(rq);
 }
 
+static void mlx5e_rq_timeout_work(struct work_struct *timeout_work)
+{
+	struct mlx5e_rq *rq = container_of(timeout_work,
+					   struct mlx5e_rq,
+					   rx_timeout_work);
+
+	/* Acquire netdev instance lock to synchronize with channel close and
+	 * reopen flows. Either successfully obtain the lock, or detect that
+	 * channels are closing for another reason, making this work no longer
+	 * necessary.
+	 */
+	while (!netdev_trylock(rq->netdev)) {
+		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &rq->priv->state))
+			return;
+		msleep(20);
+	}
+
+	mlx5e_reporter_rx_timeout(rq);
+	netdev_unlock(rq->netdev);
+}
+
 static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq)
 {
 	rq->wqe_overflow.page = alloc_page(GFP_KERNEL);
@@ -876,6 +897,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 
 	rqp->wq.db_numa_node = node;
 	INIT_WORK(&rq->recover_work, mlx5e_rq_err_cqe_work);
+	INIT_WORK(&rq->rx_timeout_work, mlx5e_rq_timeout_work);
 
 	if (params->xdp_prog)
 		bpf_prog_inc(params->xdp_prog);
@@ -1261,7 +1283,8 @@ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
 	netdev_warn(rq->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
 		    rq->ix, rq->rqn, mlx5e_rqwq_get_cur_sz(rq), min_wqes);
 
-	mlx5e_reporter_rx_timeout(rq);
+	queue_work(rq->priv->wq, &rq->rx_timeout_work);
+
 	return -ETIMEDOUT;
 }
 
@@ -1432,6 +1455,7 @@ void mlx5e_close_rq(struct mlx5e_rq *rq)
 	if (rq->dim)
 		cancel_work_sync(&rq->dim->work);
 	cancel_work_sync(&rq->recover_work);
+	cancel_work_sync(&rq->rx_timeout_work);
 	mlx5e_destroy_rq(rq);
 	mlx5e_free_rx_descs(rq);
 	mlx5e_free_rq(rq);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index f350a6662880a..f1abf4242cd2f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2596,7 +2596,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 
 	budget = min(budget, stmmac_tx_avail(priv, queue));
 
-	while (budget-- > 0) {
+	for (; budget > 0; budget--) {
 		struct stmmac_metadata_request meta_req;
 		struct xsk_tx_metadata *meta = NULL;
 		dma_addr_t dma_addr;
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index f678c1bdacdf0..605b0315b4cb0 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -477,6 +477,8 @@ static const struct kszphy_type ksz8051_type = {
 
 static const struct kszphy_type ksz8081_type = {
 	.led_mode_reg		= MII_KSZPHY_CTRL_2,
+	.cable_diag_reg		= KSZ8081_LMD,
+	.pair_mask		= KSZPHY_WIRE_PAIR_MASK,
 	.has_broadcast_disable	= true,
 	.has_nand_tree_disable	= true,
 	.has_rmii_ref_clk_sel	= true,
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index a8d50dd93d12c..a38ffbf4b3f03 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1129,6 +1129,9 @@ static void __handle_link_change(struct usbnet *dev)
 		 * tx queue is stopped by netcore after link becomes off
 		 */
 	} else {
+		if (test_and_clear_bit(EVENT_LINK_CARRIER_ON, &dev->flags))
+			netif_carrier_on(dev->net);
+
 		/* submitting URBs for reading packets */
 		queue_work(system_bh_wq, &dev->bh_work);
 	}
@@ -2015,10 +2018,12 @@ EXPORT_SYMBOL(usbnet_manage_power);
 void usbnet_link_change(struct usbnet *dev, bool link, bool need_reset)
 {
 	/* update link after link is reseted */
-	if (link && !need_reset)
-		netif_carrier_on(dev->net);
-	else
+	if (link && !need_reset) {
+		set_bit(EVENT_LINK_CARRIER_ON, &dev->flags);
+	} else {
+		clear_bit(EVENT_LINK_CARRIER_ON, &dev->flags);
 		netif_carrier_off(dev->net);
+	}
 
 	if (need_reset && link)
 		usbnet_defer_kevent(dev, EVENT_LINK_RESET);
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 9a4beea6ee0c2..3ccd649913b50 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1302,6 +1302,8 @@ static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
 	struct net *net = dev_net(vrf_dev);
 	struct rt6_info *rt6;
 
+	skb_dst_drop(skb);
+
 	rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb,
 				   RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE);
 	if (unlikely(!rt6))
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 208682f771793..a2d54122823da 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -76,6 +76,7 @@ struct usbnet {
 #		define EVENT_LINK_CHANGE	11
 #		define EVENT_SET_RX_MODE	12
 #		define EVENT_NO_IP_ALIGN	13
+#		define EVENT_LINK_CARRIER_ON	14
 /* This one is special, as it indicates that the device is going away
  * there are cyclic dependencies between tasklet, timer and bh
  * that must be broken
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 4316ca3d98729..bddfa389effa7 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -379,6 +379,43 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net,
 	}
 }
 
+static void neigh_flush_one(struct neighbour *n)
+{
+	hlist_del_rcu(&n->hash);
+	hlist_del_rcu(&n->dev_list);
+
+	write_lock(&n->lock);
+
+	neigh_del_timer(n);
+	neigh_mark_dead(n);
+
+	if (refcount_read(&n->refcnt) != 1) {
+		/* The most unpleasant situation.
+		 * We must destroy neighbour entry,
+		 * but someone still uses it.
+		 *
+		 * The destroy will be delayed until
+		 * the last user releases us, but
+		 * we must kill timers etc. and move
+		 * it to safe state.
+		 */
+		__skb_queue_purge(&n->arp_queue);
+		n->arp_queue_len_bytes = 0;
+		WRITE_ONCE(n->output, neigh_blackhole);
+
+		if (n->nud_state & NUD_VALID)
+			n->nud_state = NUD_NOARP;
+		else
+			n->nud_state = NUD_NONE;
+
+		neigh_dbg(2, "neigh %p is stray\n", n);
+	}
+
+	write_unlock(&n->lock);
+
+	neigh_cleanup_and_release(n);
+}
+
 static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev,
 			    bool skip_perm)
 {
@@ -394,32 +431,24 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev,
 		     n->flags & NTF_EXT_VALIDATED))
 			continue;
 
-		hlist_del_rcu(&n->hash);
-		hlist_del_rcu(&n->dev_list);
-		write_lock(&n->lock);
-		neigh_del_timer(n);
-		neigh_mark_dead(n);
-		if (refcount_read(&n->refcnt) != 1) {
-			/* The most unpleasant situation.
-			 * We must destroy neighbour entry,
-			 * but someone still uses it.
-			 *
-			 * The destroy will be delayed until
-			 * the last user releases us, but
-			 * we must kill timers etc. and move
-			 * it to safe state.
-			 */
-			__skb_queue_purge(&n->arp_queue);
-			n->arp_queue_len_bytes = 0;
-			WRITE_ONCE(n->output, neigh_blackhole);
-			if (n->nud_state & NUD_VALID)
-				n->nud_state = NUD_NOARP;
-			else
-				n->nud_state = NUD_NONE;
-			neigh_dbg(2, "neigh %p is stray\n", n);
-		}
-		write_unlock(&n->lock);
-		neigh_cleanup_and_release(n);
+		neigh_flush_one(n);
+	}
+}
+
+static void neigh_flush_table(struct neigh_table *tbl)
+{
+	struct neigh_hash_table *nht;
+	int i;
+
+	nht = rcu_dereference_protected(tbl->nht,
+					lockdep_is_held(&tbl->lock));
+
+	for (i = 0; i < (1 << nht->hash_shift); i++) {
+		struct hlist_node *tmp;
+		struct neighbour *n;
+
+		neigh_for_each_in_bucket_safe(n, tmp, &nht->hash_heads[i])
+			neigh_flush_one(n);
 	}
 }
 
@@ -435,7 +464,12 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev,
 			  bool skip_perm)
 {
 	write_lock_bh(&tbl->lock);
-	neigh_flush_dev(tbl, dev, skip_perm);
+	if (likely(dev)) {
+		neigh_flush_dev(tbl, dev, skip_perm);
+	} else {
+		DEBUG_NET_WARN_ON_ONCE(skip_perm);
+		neigh_flush_table(tbl);
+	}
 	write_unlock_bh(&tbl->lock);
 
 	pneigh_ifdown(tbl, dev, skip_perm);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7272d7e0fc36b..02c16909f6182 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -445,15 +445,17 @@ struct fib6_dump_arg {
 static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg)
 {
 	enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE;
+	unsigned int nsiblings;
 	int err;
 
 	if (!rt || rt == arg->net->ipv6.fib6_null_entry)
 		return 0;
 
-	if (rt->fib6_nsiblings)
+	nsiblings = READ_ONCE(rt->fib6_nsiblings);
+	if (nsiblings)
 		err = call_fib6_multipath_entry_notifier(arg->nb, fib_event,
 							 rt,
-							 rt->fib6_nsiblings,
+							 nsiblings,
 							 arg->extack);
 	else
 		err = call_fib6_entry_notifier(arg->nb, fib_event, rt,
@@ -1126,7 +1128,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 
 			if (rt6_duplicate_nexthop(iter, rt)) {
 				if (rt->fib6_nsiblings)
-					rt->fib6_nsiblings = 0;
+					WRITE_ONCE(rt->fib6_nsiblings, 0);
 				if (!(iter->fib6_flags & RTF_EXPIRES))
 					return -EEXIST;
 				if (!(rt->fib6_flags & RTF_EXPIRES)) {
@@ -1155,7 +1157,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 			 */
 			if (rt_can_ecmp &&
 			    rt6_qualify_for_ecmp(iter))
-				rt->fib6_nsiblings++;
+				WRITE_ONCE(rt->fib6_nsiblings,
+					   rt->fib6_nsiblings + 1);
 		}
 
 		if (iter->fib6_metric > rt->fib6_metric)
@@ -1205,7 +1208,8 @@ next_iter:
 		fib6_nsiblings = 0;
 		list_for_each_entry_safe(sibling, temp_sibling,
 					 &rt->fib6_siblings, fib6_siblings) {
-			sibling->fib6_nsiblings++;
+			WRITE_ONCE(sibling->fib6_nsiblings,
+				   sibling->fib6_nsiblings + 1);
 			BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings);
 			fib6_nsiblings++;
 		}
@@ -1252,8 +1256,9 @@ add:
 				list_for_each_entry_safe(sibling, next_sibling,
 							 &rt->fib6_siblings,
 							 fib6_siblings)
-					sibling->fib6_nsiblings--;
-				rt->fib6_nsiblings = 0;
+					WRITE_ONCE(sibling->fib6_nsiblings,
+						   sibling->fib6_nsiblings - 1);
+				WRITE_ONCE(rt->fib6_nsiblings, 0);
 				list_del_rcu(&rt->fib6_siblings);
 				rcu_read_lock();
 				rt6_multipath_rebalance(next_sibling);
@@ -2002,8 +2007,9 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 			notify_del = true;
 		list_for_each_entry_safe(sibling, next_sibling,
 					 &rt->fib6_siblings, fib6_siblings)
-			sibling->fib6_nsiblings--;
-		rt->fib6_nsiblings = 0;
+			WRITE_ONCE(sibling->fib6_nsiblings,
+				   sibling->fib6_nsiblings - 1);
+		WRITE_ONCE(rt->fib6_nsiblings, 0);
 		list_del_rcu(&rt->fib6_siblings);
 		rt6_multipath_rebalance(next_sibling);
 	}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3fbe0885c21c6..17c5b54ecad84 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5347,7 +5347,8 @@ static void ip6_route_mpath_notify(struct fib6_info *rt,
 	 */
 	rcu_read_lock();
 
-	if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) {
+	if ((nlflags & NLM_F_APPEND) && rt_last &&
+	    READ_ONCE(rt_last->fib6_nsiblings)) {
 		rt = list_first_or_null_rcu(&rt_last->fib6_siblings,
 					    struct fib6_info,
 					    fib6_siblings);
@@ -5671,32 +5672,34 @@ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg)
 
 static size_t rt6_nlmsg_size(struct fib6_info *f6i)
 {
+	struct fib6_info *sibling;
+	struct fib6_nh *nh;
 	int nexthop_len;
 
 	if (f6i->nh) {
 		nexthop_len = nla_total_size(4); /* RTA_NH_ID */
 		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
 					 &nexthop_len);
-	} else {
-		struct fib6_nh *nh = f6i->fib6_nh;
-		struct fib6_info *sibling;
-
-		nexthop_len = 0;
-		if (f6i->fib6_nsiblings) {
-			rt6_nh_nlmsg_size(nh, &nexthop_len);
-
-			rcu_read_lock();
+		goto common;
+	}
 
-			list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
-						fib6_siblings) {
-				rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
-			}
+	rcu_read_lock();
+retry:
+	nh = f6i->fib6_nh;
+	nexthop_len = 0;
+	if (READ_ONCE(f6i->fib6_nsiblings)) {
+		rt6_nh_nlmsg_size(nh, &nexthop_len);
 
-			rcu_read_unlock();
+		list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+					fib6_siblings) {
+			rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
+			if (!READ_ONCE(f6i->fib6_nsiblings))
+				goto retry;
 		}
-		nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
 	}
-
+	rcu_read_unlock();
+	nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
+common:
 	return NLMSG_ALIGN(sizeof(struct rtmsg))
 	       + nla_total_size(16) /* RTA_SRC */
 	       + nla_total_size(16) /* RTA_DST */
@@ -5857,7 +5860,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 
 		if (lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
 			goto nla_put_failure;
-	} else if (rt->fib6_nsiblings) {
+	} else if (READ_ONCE(rt->fib6_nsiblings)) {
 		struct fib6_info *sibling;
 		struct nlattr *mp;
 
@@ -5959,16 +5962,21 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i,
 	if (f6i->fib6_nh->fib_nh_dev == dev)
 		return true;
 
-	if (f6i->fib6_nsiblings) {
-		struct fib6_info *sibling, *next_sibling;
+	if (READ_ONCE(f6i->fib6_nsiblings)) {
+		const struct fib6_info *sibling;
 
-		list_for_each_entry_safe(sibling, next_sibling,
-					 &f6i->fib6_siblings, fib6_siblings) {
-			if (sibling->fib6_nh->fib_nh_dev == dev)
+		rcu_read_lock();
+		list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+					fib6_siblings) {
+			if (sibling->fib6_nh->fib_nh_dev == dev) {
+				rcu_read_unlock();
 				return true;
+			}
+			if (!READ_ONCE(f6i->fib6_nsiblings))
+				break;
 		}
+		rcu_read_unlock();
 	}
-
 	return false;
 }
 
@@ -6324,8 +6332,9 @@ errout:
 void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		     unsigned int nlm_flags)
 {
-	struct sk_buff *skb;
 	struct net *net = info->nl_net;
+	struct sk_buff *skb;
+	size_t sz;
 	u32 seq;
 	int err;
 
@@ -6333,17 +6342,21 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 	seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 
 	rcu_read_lock();
-
-	skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC);
+	sz = rt6_nlmsg_size(rt);
+retry:
+	skb = nlmsg_new(sz, GFP_ATOMIC);
 	if (!skb)
 		goto errout;
 
 	err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0,
 			    event, info->portid, seq, nlm_flags);
 	if (err < 0) {
-		/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
-		WARN_ON(err == -EMSGSIZE);
 		kfree_skb(skb);
+		/* -EMSGSIZE implies needed space grew under us. */
+		if (err == -EMSGSIZE) {
+			sz = max(rt6_nlmsg_size(rt), sz << 1);
+			goto retry;
+		}
 		goto errout;
 	}
 
diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py
index 3500d8f1bac45..c13dd5efa27a1 100755
--- a/tools/testing/selftests/drivers/net/hw/tso.py
+++ b/tools/testing/selftests/drivers/net/hw/tso.py
@@ -102,7 +102,7 @@ def build_tunnel(cfg, outer_ipver, tun_info):
     remote_addr = cfg.remote_addr_v[outer_ipver]
 
     tun_type = tun_info[0]
-    tun_arg  = tun_info[2]
+    tun_arg  = tun_info[1]
     ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {local_addr} remote {remote_addr} dev {cfg.ifname}")
     defer(ip, f"link del {tun_type}-ksft")
     ip(f"link set dev {tun_type}-ksft up")
@@ -119,15 +119,30 @@ def build_tunnel(cfg, outer_ipver, tun_info):
     return remote_v4, remote_v6
 
 
+def restore_wanted_features(cfg):
+    features_cmd = ""
+    for feature in cfg.hw_features:
+        setting = "on" if feature in cfg.wanted_features else "off"
+        features_cmd += f" {feature} {setting}"
+    try:
+        ethtool(f"-K {cfg.ifname} {features_cmd}")
+    except Exception as e:
+        ksft_pr(f"WARNING: failure restoring wanted features: {e}")
+
+
 def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None):
     """Construct specific tests from the common template."""
     def f(cfg):
         cfg.require_ipver(outer_ipver)
+        defer(restore_wanted_features, cfg)
 
         if not cfg.have_stat_super_count and \
            not cfg.have_stat_wire_count:
             raise KsftSkipEx(f"Device does not support LSO queue stats")
 
+        if feature not in cfg.hw_features:
+            raise KsftSkipEx(f"Device does not support {feature}")
+
         ipver = outer_ipver
         if tun:
             remote_v4, remote_v6 = build_tunnel(cfg, ipver, tun)
@@ -136,36 +151,21 @@ def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None):
             remote_v4 = cfg.remote_addr_v["4"]
             remote_v6 = cfg.remote_addr_v["6"]
 
-        tun_partial = tun and tun[1]
-        # Tunnel which can silently fall back to gso-partial
-        has_gso_partial = tun and 'tx-gso-partial' in cfg.features
-
-        # For TSO4 via partial we need mangleid
-        if ipver == "4" and feature in cfg.partial_features:
-            ksft_pr("Testing with mangleid enabled")
-            if 'tx-tcp-mangleid-segmentation' not in cfg.features:
-                ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation on")
-                defer(ethtool, f"-K {cfg.ifname} tx-tcp-mangleid-segmentation off")
-
         # First test without the feature enabled.
         ethtool(f"-K {cfg.ifname} {feature} off")
-        if has_gso_partial:
-            ethtool(f"-K {cfg.ifname} tx-gso-partial off")
         run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=False)
 
-        # Now test with the feature enabled.
-        # For compatible tunnels only - just GSO partial, not specific feature.
-        if has_gso_partial:
+        ethtool(f"-K {cfg.ifname} tx-gso-partial off")
+        ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation off")
+        if feature in cfg.partial_features:
             ethtool(f"-K {cfg.ifname} tx-gso-partial on")
-            run_one_stream(cfg, ipver, remote_v4, remote_v6,
-                           should_lso=tun_partial)
+            if ipver == "4":
+                ksft_pr("Testing with mangleid enabled")
+                ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation on")
 
         # Full feature enabled.
-        if feature in cfg.features:
-            ethtool(f"-K {cfg.ifname} {feature} on")
-            run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=True)
-        else:
-            raise KsftXfailEx(f"Device does not support {feature}")
+        ethtool(f"-K {cfg.ifname} {feature} on")
+        run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=True)
 
     f.__name__ = name + ((outer_ipver + "_") if tun else "") + "ipv" + inner_ipver
     return f
@@ -176,23 +176,39 @@ def query_nic_features(cfg) -> None:
     cfg.have_stat_super_count = False
     cfg.have_stat_wire_count = False
 
-    cfg.features = set()
     features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}})
-    for f in features["active"]["bits"]["bit"]:
-        cfg.features.add(f["name"])
+
+    cfg.wanted_features = set()
+    for f in features["wanted"]["bits"]["bit"]:
+        cfg.wanted_features.add(f["name"])
+
+    cfg.hw_features = set()
+    hw_all_features_cmd = ""
+    for f in features["hw"]["bits"]["bit"]:
+        if f.get("value", False):
+            feature = f["name"]
+            cfg.hw_features.add(feature)
+            hw_all_features_cmd += f" {feature} on"
+    try:
+        ethtool(f"-K {cfg.ifname} {hw_all_features_cmd}")
+    except Exception as e:
+        ksft_pr(f"WARNING: failure enabling all hw features: {e}")
+        ksft_pr("partial gso feature detection may be impacted")
 
     # Check which features are supported via GSO partial
     cfg.partial_features = set()
-    if 'tx-gso-partial' in cfg.features:
+    if 'tx-gso-partial' in cfg.hw_features:
         ethtool(f"-K {cfg.ifname} tx-gso-partial off")
 
         no_partial = set()
         features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}})
         for f in features["active"]["bits"]["bit"]:
             no_partial.add(f["name"])
-        cfg.partial_features = cfg.features - no_partial
+        cfg.partial_features = cfg.hw_features - no_partial
         ethtool(f"-K {cfg.ifname} tx-gso-partial on")
 
+    restore_wanted_features(cfg)
+
     stats = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)
     if stats:
         if 'tx-hw-gso-packets' in stats[0]:
@@ -211,13 +227,14 @@ def main() -> None:
         query_nic_features(cfg)
 
         test_info = (
-            # name,       v4/v6  ethtool_feature              tun:(type,    partial, args)
-            ("",            "4", "tx-tcp-segmentation",           None),
-            ("",            "6", "tx-tcp6-segmentation",          None),
-            ("vxlan",        "", "tx-udp_tnl-segmentation",       ("vxlan",  True,  "id 100 dstport 4789 noudpcsum")),
-            ("vxlan_csum",   "", "tx-udp_tnl-csum-segmentation",  ("vxlan",  False, "id 100 dstport 4789 udpcsum")),
-            ("gre",         "4", "tx-gre-segmentation",           ("gre",    False,  "")),
-            ("gre",         "6", "tx-gre-segmentation",           ("ip6gre", False,  "")),
+            # name,       v4/v6  ethtool_feature               tun:(type, args, inner ip versions)
+            ("",           "4", "tx-tcp-segmentation",         None),
+            ("",           "6", "tx-tcp6-segmentation",        None),
+            ("vxlan",      "4", "tx-udp_tnl-segmentation",     ("vxlan", "id 100 dstport 4789 noudpcsum", ("4", "6"))),
+            ("vxlan",      "6", "tx-udp_tnl-segmentation",     ("vxlan", "id 100 dstport 4789 udp6zerocsumtx udp6zerocsumrx", ("4", "6"))),
+            ("vxlan_csum", "", "tx-udp_tnl-csum-segmentation", ("vxlan", "id 100 dstport 4789 udpcsum", ("4", "6"))),
+            ("gre",        "4", "tx-gre-segmentation",         ("gre",   "", ("4", "6"))),
+            ("gre",        "6", "tx-gre-segmentation",         ("ip6gre","", ("4", "6"))),
         )
 
         cases = []
@@ -227,11 +244,13 @@ def main() -> None:
                 if info[1] and outer_ipver != info[1]:
                     continue
 
-                cases.append(test_builder(info[0], cfg, outer_ipver, info[2],
-                                          tun=info[3], inner_ipver="4"))
                 if info[3]:
-                    cases.append(test_builder(info[0], cfg, outer_ipver, info[2],
-                                              tun=info[3], inner_ipver="6"))
+                    cases += [
+                        test_builder(info[0], cfg, outer_ipver, info[2], info[3], inner_ipver)
+                        for inner_ipver in info[3][2]
+                    ]
+                else:
+                    cases.append(test_builder(info[0], cfg, outer_ipver, info[2], None, outer_ipver))
 
         ksft_run(cases=cases, args=(cfg, ))
     ksft_exit()