Merge tag 'net-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core & protocols:

   - Continue Netlink conversions to per-namespace RTNL lock
     (IPv4 routing, routing rules, routing next hops, ARP ioctls)

   - Continue extending the use of netdev instance locks. As a driver
     opt-in protect queue operations and (in due course) ethtool
     operations with the instance lock and not RTNL lock.

   - Support collecting TCP timestamps (data submitted, sent, acked) in
     BPF, allowing for transparent (to the application) and lower
     overhead tracking of TCP RPC performance.

   - Tweak existing networking Rx zero-copy infra to support zero-copy
     Rx via io_uring.

   - Optimize MPTCP performance in single subflow mode by 29%.

   - Enable GRO on packets which went thru XDP CPU redirect (were queued
     for processing on a different CPU). Improving TCP stream
     performance up to 2x.

   - Improve performance of contended connect() by 200% by searching for
     an available 4-tuple under RCU rather than a spin lock. Bring an
     additional 229% improvement by tweaking hash distribution.

   - Avoid unconditionally touching sk_tsflags on RX, improving
     performance under UDP flood by as much as 10%.

   - Avoid skb_clone() dance in ping_rcv() to improve performance under
     ping flood.

   - Avoid FIB lookup in netfilter if socket is available, 20% perf win.

   - Rework network device creation (in-kernel) API to more clearly
     identify network namespaces and their roles. There are up to 4
     namespace roles but we used to have just 2 netns pointer arguments,
     interpreted differently based on context.

   - Use sysfs_break_active_protection() instead of trylock to avoid
     deadlocks between unregistering objects and sysfs access.

   - Add a new sysctl and sockopt for capping max retransmit timeout in
     TCP.

   - Support masking port and DSCP in routing rule matches.

   - Support dumping IPv4 multicast addresses with RTM_GETMULTICAST.

   - Support specifying at what time packet should be sent on AF_XDP
     sockets.

   - Expose TCP ULP diagnostic info (for TLS and MPTCP) to non-admin
     users.

   - Add Netlink YAML spec for WiFi (nl80211) and conntrack.

   - Introduce EXPORT_IPV6_MOD() and EXPORT_IPV6_MOD_GPL() for symbols
     which only need to be exported when IPv6 support is built as a
     module.

   - Age FDB entries based on Rx not Tx traffic in VxLAN, similar to
     normal bridging.

   - Allow users to specify source port range for GENEVE tunnels.

   - netconsole: allow attaching kernel release, CPU ID and task name to
     messages as metadata

  Driver API:

   - Continue rework / fixing of Energy Efficient Ethernet (EEE) across
     the SW layers. Delegate the responsibilities to phylink where
     possible. Improve its handling in phylib.

   - Support symmetric OR-XOR RSS hashing algorithm.

   - Support tracking and preserving IRQ affinity by NAPI itself.

   - Support loopback mode speed selection for interface selftests.

  Device drivers:

   - Remove the IBM LCS driver for s390

   - Remove the sb1000 cable modem driver

   - Add support for SFP module access over SMBus

   - Add MCTP transport driver for MCTP-over-USB

   - Enable XDP metadata support in multiple drivers

   - Ethernet high-speed NICs:
      - Broadcom (bnxt):
         - add PCIe TLP Processing Hints (TPH) support for new AMD
           platforms
         - support dumping RoCE queue state for debug
         - opt into instance locking
      - Intel (100G, ice, idpf):
         - ice: rework MSI-X IRQ management and distribution
         - ice: support for E830 devices
         - iavf: add support for Rx timestamping
         - iavf: opt into instance locking
      - nVidia/Mellanox:
         - mlx4: use page pool memory allocator for Rx
         - mlx5: support for one PTP device per hardware clock
         - mlx5: support for 200Gbps per-lane link modes
         - mlx5: move IPSec policy check after decryption
      - AMD/Solarflare:
         - support FW flashing via devlink
      - Cisco (enic):
         - use page pool memory allocator for Rx
         - enable 32, 64 byte CQEs
         - get max rx/tx ring size from the device
      - Meta (fbnic):
         - support flow steering and RSS configuration
         - report queue stats
         - support TCP segmentation
         - support IRQ coalescing
         - support ring size configuration
      - Marvell/Cavium:
         - support AF_XDP
      - Wangxun:
         - support for PTP clock and timestamping
      - Huawei (hibmcge):
         - checksum offload
         - add more statistics

   - Ethernet virtual:
      - VirtIO net:
         - aggressively suppress Tx completions, improve perf by 96%
           with 1 CPU and 55% with 2 CPUs
         - expose NAPI to IRQ mapping and persist NAPI settings
      - Google (gve):
         - support XDP in DQO RDA Queue Format
         - opt into instance locking
      - Microsoft vNIC:
         - support BIG TCP

   - Ethernet NICs consumer, and embedded:
      - Synopsys (stmmac):
         - cleanup Tx and Tx clock setting and other link-focused
           cleanups
         - enable SGMII and 2500BASEX mode switching for Intel platforms
         - support Sophgo SG2044
      - Broadcom switches (b53):
         - support for BCM53101
      - TI:
         - iep: add perout configuration support
         - icssg: support XDP
      - Cadence (macb):
         - implement BQL
      - Xilinx (axinet):
         - support dynamic IRQ moderation and changing coalescing at
           runtime
         - implement BQL
         - report standard stats
      - MediaTek:
         - support phylink managed EEE
      - Intel:
         - igc: don't restart the interface on every XDP program change
      - RealTek (r8169):
         - support reading registers of internal PHYs directly
         - increase max jumbo packet size on RTL8125/RTL8126
      - Airoha:
         - support for RISC-V NPU packet processing unit
         - enable scatter-gather and support MTU up to 9kB
      - Tehuti (tn40xx):
         - support cards with TN4010 MAC and an Aquantia AQR105 PHY

   - Ethernet PHYs:
      - support for TJA1102S, TJA1121
      - dp83tg720: add randomized polling intervals for link detection
      - dp83822: support changing the transmit amplitude voltage
      - support for LEDs on 88q2xxx

   - CAN:
      - canxl: support Remote Request Substitution bit access
      - flexcan: add S32G2/S32G3 SoC

   - WiFi:
      - remove cooked monitor support
      - strict mode for better AP testing
      - basic EPCS support
      - OMI RX bandwidth reduction support
      - batman-adv: add support for jumbo frames

   - WiFi drivers:
      - RealTek (rtw88):
         - support RTL8814AE and RTL8814AU
      - RealTek (rtw89):
         - switch using wiphy_lock and wiphy_work
         - add BB context to manipulate two PHY as preparation of MLO
         - improve BT-coexistence mechanism to play A2DP smoothly
      - Intel (iwlwifi):
         - add new iwlmld sub-driver for latest HW/FW combinations
      - MediaTek (mt76):
         - preparation for mt7996 Multi-Link Operation (MLO) support
      - Qualcomm/Atheros (ath12k):
         - continued work on MLO
      - Silabs (wfx):
         - Wake-on-WLAN support

   - Bluetooth:
      - add support for skb TX SND/COMPLETION timestamping
      - hci_core: enable buffer flow control for SCO/eSCO
      - coredump: log devcd dumps into the monitor

   - Bluetooth drivers:
      - intel: add support to configure TX power
      - nxp: handle bootloader error during cmd5 and cmd7"

* tag 'net-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1681 commits)
  unix: fix up for "apparmor: add fine grained af_unix mediation"
  mctp: Fix incorrect tx flow invalidation condition in mctp-i2c
  net: usb: asix: ax88772: Increase phy_name size
  net: phy: Introduce PHY_ID_SIZE — minimum size for PHY ID string
  net: libwx: fix Tx L4 checksum
  net: libwx: fix Tx descriptor content for some tunnel packets
  atm: Fix NULL pointer dereference
  net: tn40xx: add pci-id of the aqr105-based Tehuti TN4010 cards
  net: tn40xx: prepare tn40xx driver to find phy of the TN9510 card
  net: tn40xx: create swnode for mdio and aqr105 phy and add to mdiobus
  net: phy: aquantia: add essential functions to aqr105 driver
  net: phy: aquantia: search for firmware-name in fwnode
  net: phy: aquantia: add probe function to aqr105 for firmware loading
  net: phy: Add swnode support to mdiobus_scan
  gve: add XDP DROP and PASS support for DQ
  gve: update XDP allocation path support RX buffer posting
  gve: merge packet buffer size fields
  gve: update GQ RX to use buf_size
  gve: introduce config-based allocation for XDP
  gve: remove xdp_xsk_done and xdp_xsk_wakeup statistics
  ...

1 files changed, 149 insertions, 116 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 9d7c37e968b5..7e4617216a4b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -360,24 +360,7 @@ struct receive_queue {
 	struct xdp_buff **xsk_buffs;
 };
 
-/* This structure can contain rss message with maximum settings for indirection table and keysize
- * Note, that default structure that describes RSS configuration virtio_net_rss_config
- * contains same info but can't handle table values.
- * In any case, structure would be passed to virtio hw through sg_buf split by parts
- * because table sizes may be differ according to the device configuration.
- */
 #define VIRTIO_NET_RSS_MAX_KEY_SIZE     40
-struct virtio_net_ctrl_rss {
-	u32 hash_types;
-	u16 indirection_table_mask;
-	u16 unclassified_queue;
-	u16 hash_cfg_reserved; /* for HASH_CONFIG (see virtio_net_hash_config for details) */
-	u16 max_tx_vq;
-	u8 hash_key_length;
-	u8 key[VIRTIO_NET_RSS_MAX_KEY_SIZE];
-
-	u16 *indirection_table;
-};
 
 /* Control VQ buffers: protected by the rtnl lock */
 struct control_buf {
@@ -421,7 +404,9 @@ struct virtnet_info {
 	u16 rss_indir_table_size;
 	u32 rss_hash_types_supported;
 	u32 rss_hash_types_saved;
-	struct virtio_net_ctrl_rss rss;
+	struct virtio_net_rss_config_hdr *rss_hdr;
+	struct virtio_net_rss_config_trailer rss_trailer;
+	u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE];
 
 	/* Has control virtqueue */
 	bool has_cvq;
@@ -523,23 +508,16 @@ enum virtnet_xmit_type {
 	VIRTNET_XMIT_TYPE_XSK,
 };
 
-static int rss_indirection_table_alloc(struct virtio_net_ctrl_rss *rss, u16 indir_table_size)
+static size_t virtnet_rss_hdr_size(const struct virtnet_info *vi)
 {
-	if (!indir_table_size) {
-		rss->indirection_table = NULL;
-		return 0;
-	}
+	u16 indir_table_size = vi->has_rss ? vi->rss_indir_table_size : 1;
 
-	rss->indirection_table = kmalloc_array(indir_table_size, sizeof(u16), GFP_KERNEL);
-	if (!rss->indirection_table)
-		return -ENOMEM;
-
-	return 0;
+	return struct_size(vi->rss_hdr, indirection_table, indir_table_size);
 }
 
-static void rss_indirection_table_free(struct virtio_net_ctrl_rss *rss)
+static size_t virtnet_rss_trailer_size(const struct virtnet_info *vi)
 {
-	kfree(rss->indirection_table);
+	return struct_size(&vi->rss_trailer, hash_key_data, vi->rss_key_size);
 }
 
 /* We use the last two bits of the pointer to distinguish the xmit type. */
@@ -1088,11 +1066,10 @@ static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
 		return false;
 }
 
-static void check_sq_full_and_disable(struct virtnet_info *vi,
-				      struct net_device *dev,
-				      struct send_queue *sq)
+static bool tx_may_stop(struct virtnet_info *vi,
+			struct net_device *dev,
+			struct send_queue *sq)
 {
-	bool use_napi = sq->napi.weight;
 	int qnum;
 
 	qnum = sq - vi->sq;
@@ -1114,6 +1091,25 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
 		u64_stats_update_begin(&sq->stats.syncp);
 		u64_stats_inc(&sq->stats.stop);
 		u64_stats_update_end(&sq->stats.syncp);
+
+		return true;
+	}
+
+	return false;
+}
+
+static void check_sq_full_and_disable(struct virtnet_info *vi,
+				      struct net_device *dev,
+				      struct send_queue *sq)
+{
+	bool use_napi = sq->napi.weight;
+	int qnum;
+
+	qnum = sq - vi->sq;
+
+	if (tx_may_stop(vi, dev, sq)) {
+		struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
+
 		if (use_napi) {
 			if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
 				virtqueue_napi_schedule(&sq->napi, sq->vq);
@@ -2789,7 +2785,8 @@ static void skb_recv_done(struct virtqueue *rvq)
 	virtqueue_napi_schedule(&rq->napi, rvq);
 }
 
-static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi)
+static void virtnet_napi_do_enable(struct virtqueue *vq,
+				   struct napi_struct *napi)
 {
 	napi_enable(napi);
 
@@ -2802,10 +2799,21 @@ static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi)
 	local_bh_enable();
 }
 
-static void virtnet_napi_tx_enable(struct virtnet_info *vi,
-				   struct virtqueue *vq,
-				   struct napi_struct *napi)
+static void virtnet_napi_enable(struct receive_queue *rq)
+{
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	int qidx = vq2rxq(rq->vq);
+
+	virtnet_napi_do_enable(rq->vq, &rq->napi);
+	netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_RX, &rq->napi);
+}
+
+static void virtnet_napi_tx_enable(struct send_queue *sq)
 {
+	struct virtnet_info *vi = sq->vq->vdev->priv;
+	struct napi_struct *napi = &sq->napi;
+	int qidx = vq2txq(sq->vq);
+
 	if (!napi->weight)
 		return;
 
@@ -2817,13 +2825,30 @@ static void virtnet_napi_tx_enable(struct virtnet_info *vi,
 		return;
 	}
 
-	return virtnet_napi_enable(vq, napi);
+	virtnet_napi_do_enable(sq->vq, napi);
+	netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_TX, napi);
 }
 
-static void virtnet_napi_tx_disable(struct napi_struct *napi)
+static void virtnet_napi_tx_disable(struct send_queue *sq)
 {
-	if (napi->weight)
+	struct virtnet_info *vi = sq->vq->vdev->priv;
+	struct napi_struct *napi = &sq->napi;
+	int qidx = vq2txq(sq->vq);
+
+	if (napi->weight) {
+		netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_TX, NULL);
 		napi_disable(napi);
+	}
+}
+
+static void virtnet_napi_disable(struct receive_queue *rq)
+{
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	struct napi_struct *napi = &rq->napi;
+	int qidx = vq2rxq(rq->vq);
+
+	netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_RX, NULL);
+	napi_disable(napi);
 }
 
 static void refill_work(struct work_struct *work)
@@ -2836,9 +2861,23 @@ static void refill_work(struct work_struct *work)
 	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		struct receive_queue *rq = &vi->rq[i];
 
+		/*
+		 * When queue API support is added in the future and the call
+		 * below becomes napi_disable_locked, this driver will need to
+		 * be refactored.
+		 *
+		 * One possible solution would be to:
+		 *   - cancel refill_work with cancel_delayed_work (note:
+		 *     non-sync)
+		 *   - cancel refill_work with cancel_delayed_work_sync in
+		 *     virtnet_remove after the netdev is unregistered
+		 *   - wrap all of the work in a lock (perhaps the netdev
+		 *     instance lock)
+		 *   - check netif_running() and return early to avoid a race
+		 */
 		napi_disable(&rq->napi);
 		still_empty = !try_fill_recv(vi, rq, GFP_KERNEL);
-		virtnet_napi_enable(rq->vq, &rq->napi);
+		virtnet_napi_do_enable(rq->vq, &rq->napi);
 
 		/* In theory, this can happen: if we don't get any buffers in
 		 * we will *never* try to fill again.
@@ -3035,8 +3074,8 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 
 static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
 {
-	virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
-	napi_disable(&vi->rq[qp_index].napi);
+	virtnet_napi_tx_disable(&vi->sq[qp_index]);
+	virtnet_napi_disable(&vi->rq[qp_index]);
 	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
 }
 
@@ -3055,8 +3094,8 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
 	if (err < 0)
 		goto err_xdp_reg_mem_model;
 
-	virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
-	virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
+	virtnet_napi_enable(&vi->rq[qp_index]);
+	virtnet_napi_tx_enable(&vi->sq[qp_index]);
 
 	return 0;
 
@@ -3253,15 +3292,10 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool use_napi = sq->napi.weight;
 	bool kick;
 
-	/* Free up any pending old buffers before queueing new ones. */
-	do {
-		if (use_napi)
-			virtqueue_disable_cb(sq->vq);
-
+	if (!use_napi)
 		free_old_xmit(sq, txq, false);
-
-	} while (use_napi && !xmit_more &&
-	       unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
+	else
+		virtqueue_disable_cb(sq->vq);
 
 	/* timestamp packet in software */
 	skb_tx_timestamp(skb);
@@ -3287,7 +3321,10 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		nf_reset_ct(skb);
 	}
 
-	check_sq_full_and_disable(vi, dev, sq);
+	if (use_napi)
+		tx_may_stop(vi, dev, sq);
+	else
+		check_sq_full_and_disable(vi, dev,sq);
 
 	kick = use_napi ? __netdev_tx_sent_queue(txq, skb->len, xmit_more) :
 			  !xmit_more || netif_xmit_stopped(txq);
@@ -3299,6 +3336,9 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
+	if (use_napi && kick && unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
+		virtqueue_napi_schedule(&sq->napi, sq->vq);
+
 	return NETDEV_TX_OK;
 }
 
@@ -3307,7 +3347,7 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
 	bool running = netif_running(vi->dev);
 
 	if (running) {
-		napi_disable(&rq->napi);
+		virtnet_napi_disable(rq);
 		virtnet_cancel_dim(vi, &rq->dim);
 	}
 }
@@ -3320,7 +3360,7 @@ static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
 		schedule_delayed_work(&vi->refill, 0);
 
 	if (running)
-		virtnet_napi_enable(rq->vq, &rq->napi);
+		virtnet_napi_enable(rq);
 }
 
 static int virtnet_rx_resize(struct virtnet_info *vi,
@@ -3349,7 +3389,7 @@ static void virtnet_tx_pause(struct virtnet_info *vi, struct send_queue *sq)
 	qindex = sq - vi->sq;
 
 	if (running)
-		virtnet_napi_tx_disable(&sq->napi);
+		virtnet_napi_tx_disable(sq);
 
 	txq = netdev_get_tx_queue(vi->dev, qindex);
 
@@ -3383,7 +3423,7 @@ static void virtnet_tx_resume(struct virtnet_info *vi, struct send_queue *sq)
 	__netif_tx_unlock_bh(txq);
 
 	if (running)
-		virtnet_napi_tx_enable(vi, sq->vq, &sq->napi);
+		virtnet_napi_tx_enable(sq);
 }
 
 static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq,
@@ -3576,15 +3616,16 @@ static void virtnet_rss_update_by_qpairs(struct virtnet_info *vi, u16 queue_pair
 
 	for (; i < vi->rss_indir_table_size; ++i) {
 		indir_val = ethtool_rxfh_indir_default(i, queue_pairs);
-		vi->rss.indirection_table[i] = indir_val;
+		vi->rss_hdr->indirection_table[i] = cpu_to_le16(indir_val);
 	}
-	vi->rss.max_tx_vq = queue_pairs;
+	vi->rss_trailer.max_tx_vq = cpu_to_le16(queue_pairs);
 }
 
 static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 {
 	struct virtio_net_ctrl_mq *mq __free(kfree) = NULL;
-	struct virtio_net_ctrl_rss old_rss;
+	struct virtio_net_rss_config_hdr *old_rss_hdr;
+	struct virtio_net_rss_config_trailer old_rss_trailer;
 	struct net_device *dev = vi->dev;
 	struct scatterlist sg;
 
@@ -3599,24 +3640,28 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	 * update (VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET below) and return directly.
 	 */
 	if (vi->has_rss && !netif_is_rxfh_configured(dev)) {
-		memcpy(&old_rss, &vi->rss, sizeof(old_rss));
-		if (rss_indirection_table_alloc(&vi->rss, vi->rss_indir_table_size)) {
-			vi->rss.indirection_table = old_rss.indirection_table;
+		old_rss_hdr = vi->rss_hdr;
+		old_rss_trailer = vi->rss_trailer;
+		vi->rss_hdr = devm_kzalloc(&dev->dev, virtnet_rss_hdr_size(vi), GFP_KERNEL);
+		if (!vi->rss_hdr) {
+			vi->rss_hdr = old_rss_hdr;
 			return -ENOMEM;
 		}
 
+		*vi->rss_hdr = *old_rss_hdr;
 		virtnet_rss_update_by_qpairs(vi, queue_pairs);
 
 		if (!virtnet_commit_rss_command(vi)) {
 			/* restore ctrl_rss if commit_rss_command failed */
-			rss_indirection_table_free(&vi->rss);
-			memcpy(&vi->rss, &old_rss, sizeof(old_rss));
+			devm_kfree(&dev->dev, vi->rss_hdr);
+			vi->rss_hdr = old_rss_hdr;
+			vi->rss_trailer = old_rss_trailer;
 
 			dev_warn(&dev->dev, "Fail to set num of queue pairs to %d, because committing RSS failed\n",
 				 queue_pairs);
 			return -EINVAL;
 		}
-		rss_indirection_table_free(&old_rss);
+		devm_kfree(&dev->dev, old_rss_hdr);
 		goto succ;
 	}
 
@@ -4061,28 +4106,12 @@ static int virtnet_set_ringparam(struct net_device *dev,
 static bool virtnet_commit_rss_command(struct virtnet_info *vi)
 {
 	struct net_device *dev = vi->dev;
-	struct scatterlist sgs[4];
-	unsigned int sg_buf_size;
+	struct scatterlist sgs[2];
 
 	/* prepare sgs */
-	sg_init_table(sgs, 4);
-
-	sg_buf_size = offsetof(struct virtio_net_ctrl_rss, hash_cfg_reserved);
-	sg_set_buf(&sgs[0], &vi->rss, sg_buf_size);
-
-	if (vi->has_rss) {
-		sg_buf_size = sizeof(uint16_t) * vi->rss_indir_table_size;
-		sg_set_buf(&sgs[1], vi->rss.indirection_table, sg_buf_size);
-	} else {
-		sg_set_buf(&sgs[1], &vi->rss.hash_cfg_reserved, sizeof(uint16_t));
-	}
-
-	sg_buf_size = offsetof(struct virtio_net_ctrl_rss, key)
-			- offsetof(struct virtio_net_ctrl_rss, max_tx_vq);
-	sg_set_buf(&sgs[2], &vi->rss.max_tx_vq, sg_buf_size);
-
-	sg_buf_size = vi->rss_key_size;
-	sg_set_buf(&sgs[3], vi->rss.key, sg_buf_size);
+	sg_init_table(sgs, 2);
+	sg_set_buf(&sgs[0], vi->rss_hdr, virtnet_rss_hdr_size(vi));
+	sg_set_buf(&sgs[1], &vi->rss_trailer, virtnet_rss_trailer_size(vi));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
 				  vi->has_rss ? VIRTIO_NET_CTRL_MQ_RSS_CONFIG
@@ -4099,17 +4128,17 @@ err:
 
 static void virtnet_init_default_rss(struct virtnet_info *vi)
 {
-	vi->rss.hash_types = vi->rss_hash_types_supported;
+	vi->rss_hdr->hash_types = cpu_to_le32(vi->rss_hash_types_supported);
 	vi->rss_hash_types_saved = vi->rss_hash_types_supported;
-	vi->rss.indirection_table_mask = vi->rss_indir_table_size
-						? vi->rss_indir_table_size - 1 : 0;
-	vi->rss.unclassified_queue = 0;
+	vi->rss_hdr->indirection_table_mask = vi->rss_indir_table_size
+						? cpu_to_le16(vi->rss_indir_table_size - 1) : 0;
+	vi->rss_hdr->unclassified_queue = 0;
 
 	virtnet_rss_update_by_qpairs(vi, vi->curr_queue_pairs);
 
-	vi->rss.hash_key_length = vi->rss_key_size;
+	vi->rss_trailer.hash_key_length = vi->rss_key_size;
 
-	netdev_rss_key_fill(vi->rss.key, vi->rss_key_size);
+	netdev_rss_key_fill(vi->rss_hash_key_data, vi->rss_key_size);
 }
 
 static void virtnet_get_hashflow(const struct virtnet_info *vi, struct ethtool_rxnfc *info)
@@ -4220,7 +4249,7 @@ static bool virtnet_set_hashflow(struct virtnet_info *vi, struct ethtool_rxnfc *
 
 	if (new_hashtypes != vi->rss_hash_types_saved) {
 		vi->rss_hash_types_saved = new_hashtypes;
-		vi->rss.hash_types = vi->rss_hash_types_saved;
+		vi->rss_hdr->hash_types = cpu_to_le32(vi->rss_hash_types_saved);
 		if (vi->dev->features & NETIF_F_RXHASH)
 			return virtnet_commit_rss_command(vi);
 	}
@@ -5400,11 +5429,11 @@ static int virtnet_get_rxfh(struct net_device *dev,
 
 	if (rxfh->indir) {
 		for (i = 0; i < vi->rss_indir_table_size; ++i)
-			rxfh->indir[i] = vi->rss.indirection_table[i];
+			rxfh->indir[i] = le16_to_cpu(vi->rss_hdr->indirection_table[i]);
 	}
 
 	if (rxfh->key)
-		memcpy(rxfh->key, vi->rss.key, vi->rss_key_size);
+		memcpy(rxfh->key, vi->rss_hash_key_data, vi->rss_key_size);
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
@@ -5428,7 +5457,7 @@ static int virtnet_set_rxfh(struct net_device *dev,
 			return -EOPNOTSUPP;
 
 		for (i = 0; i < vi->rss_indir_table_size; ++i)
-			vi->rss.indirection_table[i] = rxfh->indir[i];
+			vi->rss_hdr->indirection_table[i] = cpu_to_le16(rxfh->indir[i]);
 		update = true;
 	}
 
@@ -5440,7 +5469,7 @@ static int virtnet_set_rxfh(struct net_device *dev,
 		if (!vi->has_rss && !vi->has_rss_hash_report)
 			return -EOPNOTSUPP;
 
-		memcpy(vi->rss.key, rxfh->key, vi->rss_key_size);
+		memcpy(vi->rss_hash_key_data, rxfh->key, vi->rss_key_size);
 		update = true;
 	}
 
@@ -5617,8 +5646,11 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	netif_tx_lock_bh(vi->dev);
 	netif_device_detach(vi->dev);
 	netif_tx_unlock_bh(vi->dev);
-	if (netif_running(vi->dev))
+	if (netif_running(vi->dev)) {
+		rtnl_lock();
 		virtnet_close(vi->dev);
+		rtnl_unlock();
+	}
 }
 
 static int init_vqs(struct virtnet_info *vi);
@@ -5638,7 +5670,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 	enable_rx_mode_work(vi);
 
 	if (netif_running(vi->dev)) {
+		rtnl_lock();
 		err = virtnet_open(vi->dev);
+		rtnl_unlock();
 		if (err)
 			return err;
 	}
@@ -5928,8 +5962,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
 	if (netif_running(dev)) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
-			napi_disable(&vi->rq[i].napi);
-			virtnet_napi_tx_disable(&vi->sq[i].napi);
+			virtnet_napi_disable(&vi->rq[i]);
+			virtnet_napi_tx_disable(&vi->sq[i]);
 		}
 	}
 
@@ -5966,9 +6000,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		if (old_prog)
 			bpf_prog_put(old_prog);
 		if (netif_running(dev)) {
-			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
-					       &vi->sq[i].napi);
+			virtnet_napi_enable(&vi->rq[i]);
+			virtnet_napi_tx_enable(&vi->sq[i]);
 		}
 	}
 
@@ -5983,9 +6016,8 @@ err:
 
 	if (netif_running(dev)) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
-					       &vi->sq[i].napi);
+			virtnet_napi_enable(&vi->rq[i]);
+			virtnet_napi_tx_enable(&vi->sq[i]);
 		}
 	}
 	if (prog)
@@ -6046,9 +6078,9 @@ static int virtnet_set_features(struct net_device *dev,
 
 	if ((dev->features ^ features) & NETIF_F_RXHASH) {
 		if (features & NETIF_F_RXHASH)
-			vi->rss.hash_types = vi->rss_hash_types_saved;
+			vi->rss_hdr->hash_types = cpu_to_le32(vi->rss_hash_types_saved);
 		else
-			vi->rss.hash_types = VIRTIO_NET_HASH_REPORT_NONE;
+			vi->rss_hdr->hash_types = cpu_to_le32(VIRTIO_NET_HASH_REPORT_NONE);
 
 		if (!virtnet_commit_rss_command(vi))
 			return -EINVAL;
@@ -6392,8 +6424,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 	INIT_DELAYED_WORK(&vi->refill, refill_work);
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		vi->rq[i].pages = NULL;
-		netif_napi_add_weight(vi->dev, &vi->rq[i].napi, virtnet_poll,
-				      napi_weight);
+		netif_napi_add_config(vi->dev, &vi->rq[i].napi, virtnet_poll,
+				      i);
+		vi->rq[i].napi.weight = napi_weight;
 		netif_napi_add_tx_weight(vi->dev, &vi->sq[i].napi,
 					 virtnet_poll_tx,
 					 napi_tx ? napi_weight : 0);
@@ -6737,9 +6770,11 @@ static int virtnet_probe(struct virtio_device *vdev)
 			virtio_cread16(vdev, offsetof(struct virtio_net_config,
 				rss_max_indirection_table_length));
 	}
-	err = rss_indirection_table_alloc(&vi->rss, vi->rss_indir_table_size);
-	if (err)
+	vi->rss_hdr = devm_kzalloc(&vdev->dev, virtnet_rss_hdr_size(vi), GFP_KERNEL);
+	if (!vi->rss_hdr) {
+		err = -ENOMEM;
 		goto free;
+	}
 
 	if (vi->has_rss || vi->has_rss_hash_report) {
 		vi->rss_key_size =
@@ -7018,8 +7053,6 @@ static void virtnet_remove(struct virtio_device *vdev)
 
 	remove_vq_common(vi);
 
-	rss_indirection_table_free(&vi->rss);
-
 	free_netdev(vi->dev);
 }