Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 680 insertions, 0 deletions

diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c
new file mode 100644
index 000000000..0ba754ebc
--- /dev/null
+++ b/drivers/net/xen-netback/rx.c
@@ -0,0 +1,680 @@
+/*
+ * Copyright (c) 2016 Citrix Systems Inc.
+ * Copyright (c) 2002-2005, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+#include "common.h"
+
+#include <linux/kthread.h>
+
+#include <xen/xen.h>
+#include <xen/events.h>
+
+/*
+ * Update the needed ring page slots for the first SKB queued.
+ * Note that any call sequence outside the RX thread calling this function
+ * needs to wake up the RX thread via a call of xenvif_kick_thread()
+ * afterwards in order to avoid a race with putting the thread to sleep.
+ */
+static void xenvif_update_needed_slots(struct xenvif_queue *queue,
+				       const struct sk_buff *skb)
+{
+	unsigned int needed = 0;
+
+	if (skb) {
+		needed = DIV_ROUND_UP(skb->len, XEN_PAGE_SIZE);
+		if (skb_is_gso(skb))
+			needed++;
+		if (skb->sw_hash)
+			needed++;
+	}
+
+	WRITE_ONCE(queue->rx_slots_needed, needed);
+}
+
+static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue)
+{
+	RING_IDX prod, cons;
+	unsigned int needed;
+
+	needed = READ_ONCE(queue->rx_slots_needed);
+	if (!needed)
+		return false;
+
+	do {
+		prod = queue->rx.sring->req_prod;
+		cons = queue->rx.req_cons;
+
+		if (prod - cons >= needed)
+			return true;
+
+		queue->rx.sring->req_event = prod + 1;
+
+		/* Make sure event is visible before we check prod
+		 * again.
+		 */
+		mb();
+	} while (queue->rx.sring->req_prod != prod);
+
+	return false;
+}
+
+bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb)
+{
+	unsigned long flags;
+	bool ret = true;
+
+	spin_lock_irqsave(&queue->rx_queue.lock, flags);
+
+	if (queue->rx_queue_len >= queue->rx_queue_max) {
+		struct net_device *dev = queue->vif->dev;
+
+		netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
+		ret = false;
+	} else {
+		if (skb_queue_empty(&queue->rx_queue))
+			xenvif_update_needed_slots(queue, skb);
+
+		__skb_queue_tail(&queue->rx_queue, skb);
+
+		queue->rx_queue_len += skb->len;
+	}
+
+	spin_unlock_irqrestore(&queue->rx_queue.lock, flags);
+
+	return ret;
+}
+
+static struct sk_buff *xenvif_rx_dequeue(struct xenvif_queue *queue)
+{
+	struct sk_buff *skb;
+
+	spin_lock_irq(&queue->rx_queue.lock);
+
+	skb = __skb_dequeue(&queue->rx_queue);
+	if (skb) {
+		xenvif_update_needed_slots(queue, skb_peek(&queue->rx_queue));
+
+		queue->rx_queue_len -= skb->len;
+		if (queue->rx_queue_len < queue->rx_queue_max) {
+			struct netdev_queue *txq;
+
+			txq = netdev_get_tx_queue(queue->vif->dev, queue->id);
+			netif_tx_wake_queue(txq);
+		}
+	}
+
+	spin_unlock_irq(&queue->rx_queue.lock);
+
+	return skb;
+}
+
+static void xenvif_rx_queue_purge(struct xenvif_queue *queue)
+{
+	struct sk_buff *skb;
+
+	while ((skb = xenvif_rx_dequeue(queue)) != NULL)
+		kfree_skb(skb);
+}
+
+static void xenvif_rx_queue_drop_expired(struct xenvif_queue *queue)
+{
+	struct sk_buff *skb;
+
+	for (;;) {
+		skb = skb_peek(&queue->rx_queue);
+		if (!skb)
+			break;
+		if (time_before(jiffies, XENVIF_RX_CB(skb)->expires))
+			break;
+		xenvif_rx_dequeue(queue);
+		kfree_skb(skb);
+		queue->vif->dev->stats.rx_dropped++;
+	}
+}
+
+static void xenvif_rx_copy_flush(struct xenvif_queue *queue)
+{
+	unsigned int i;
+	int notify;
+
+	gnttab_batch_copy(queue->rx_copy.op, queue->rx_copy.num);
+
+	for (i = 0; i < queue->rx_copy.num; i++) {
+		struct gnttab_copy *op;
+
+		op = &queue->rx_copy.op[i];
+
+		/* If the copy failed, overwrite the status field in
+		 * the corresponding response.
+		 */
+		if (unlikely(op->status != GNTST_okay)) {
+			struct xen_netif_rx_response *rsp;
+
+			rsp = RING_GET_RESPONSE(&queue->rx,
+						queue->rx_copy.idx[i]);
+			rsp->status = op->status;
+		}
+	}
+
+	queue->rx_copy.num = 0;
+
+	/* Push responses for all completed packets. */
+	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->rx, notify);
+	if (notify)
+		notify_remote_via_irq(queue->rx_irq);
+
+	__skb_queue_purge(queue->rx_copy.completed);
+}
+
+static void xenvif_rx_copy_add(struct xenvif_queue *queue,
+			       struct xen_netif_rx_request *req,
+			       unsigned int offset, void *data, size_t len)
+{
+	struct gnttab_copy *op;
+	struct page *page;
+	struct xen_page_foreign *foreign;
+
+	if (queue->rx_copy.num == COPY_BATCH_SIZE)
+		xenvif_rx_copy_flush(queue);
+
+	op = &queue->rx_copy.op[queue->rx_copy.num];
+
+	page = virt_to_page(data);
+
+	op->flags = GNTCOPY_dest_gref;
+
+	foreign = xen_page_foreign(page);
+	if (foreign) {
+		op->source.domid = foreign->domid;
+		op->source.u.ref = foreign->gref;
+		op->flags |= GNTCOPY_source_gref;
+	} else {
+		op->source.u.gmfn = virt_to_gfn(data);
+		op->source.domid  = DOMID_SELF;
+	}
+
+	op->source.offset = xen_offset_in_page(data);
+	op->dest.u.ref    = req->gref;
+	op->dest.domid    = queue->vif->domid;
+	op->dest.offset   = offset;
+	op->len           = len;
+
+	queue->rx_copy.idx[queue->rx_copy.num] = queue->rx.req_cons;
+	queue->rx_copy.num++;
+}
+
+static unsigned int xenvif_gso_type(struct sk_buff *skb)
+{
+	if (skb_is_gso(skb)) {
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+			return XEN_NETIF_GSO_TYPE_TCPV4;
+		else
+			return XEN_NETIF_GSO_TYPE_TCPV6;
+	}
+	return XEN_NETIF_GSO_TYPE_NONE;
+}
+
+struct xenvif_pkt_state {
+	struct sk_buff *skb;
+	size_t remaining_len;
+	struct sk_buff *frag_iter;
+	int frag; /* frag == -1 => frag_iter->head */
+	unsigned int frag_offset;
+	struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1];
+	unsigned int extra_count;
+	unsigned int slot;
+};
+
+static void xenvif_rx_next_skb(struct xenvif_queue *queue,
+			       struct xenvif_pkt_state *pkt)
+{
+	struct sk_buff *skb;
+	unsigned int gso_type;
+
+	skb = xenvif_rx_dequeue(queue);
+
+	queue->stats.tx_bytes += skb->len;
+	queue->stats.tx_packets++;
+
+	/* Reset packet state. */
+	memset(pkt, 0, sizeof(struct xenvif_pkt_state));
+
+	pkt->skb = skb;
+	pkt->frag_iter = skb;
+	pkt->remaining_len = skb->len;
+	pkt->frag = -1;
+
+	gso_type = xenvif_gso_type(skb);
+	if ((1 << gso_type) & queue->vif->gso_mask) {
+		struct xen_netif_extra_info *extra;
+
+		extra = &pkt->extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
+
+		extra->u.gso.type = gso_type;
+		extra->u.gso.size = skb_shinfo(skb)->gso_size;
+		extra->u.gso.pad = 0;
+		extra->u.gso.features = 0;
+		extra->type = XEN_NETIF_EXTRA_TYPE_GSO;
+		extra->flags = 0;
+
+		pkt->extra_count++;
+	}
+
+	if (queue->vif->xdp_headroom) {
+		struct xen_netif_extra_info *extra;
+
+		extra = &pkt->extras[XEN_NETIF_EXTRA_TYPE_XDP - 1];
+
+		memset(extra, 0, sizeof(struct xen_netif_extra_info));
+		extra->u.xdp.headroom = queue->vif->xdp_headroom;
+		extra->type = XEN_NETIF_EXTRA_TYPE_XDP;
+		extra->flags = 0;
+
+		pkt->extra_count++;
+	}
+
+	if (skb->sw_hash) {
+		struct xen_netif_extra_info *extra;
+
+		extra = &pkt->extras[XEN_NETIF_EXTRA_TYPE_HASH - 1];
+
+		extra->u.hash.algorithm =
+			XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ;
+
+		if (skb->l4_hash)
+			extra->u.hash.type =
+				skb->protocol == htons(ETH_P_IP) ?
+				_XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP :
+				_XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP;
+		else
+			extra->u.hash.type =
+				skb->protocol == htons(ETH_P_IP) ?
+				_XEN_NETIF_CTRL_HASH_TYPE_IPV4 :
+				_XEN_NETIF_CTRL_HASH_TYPE_IPV6;
+
+		*(uint32_t *)extra->u.hash.value = skb_get_hash_raw(skb);
+
+		extra->type = XEN_NETIF_EXTRA_TYPE_HASH;
+		extra->flags = 0;
+
+		pkt->extra_count++;
+	}
+}
+
+static void xenvif_rx_complete(struct xenvif_queue *queue,
+			       struct xenvif_pkt_state *pkt)
+{
+	/* All responses are ready to be pushed. */
+	queue->rx.rsp_prod_pvt = queue->rx.req_cons;
+
+	__skb_queue_tail(queue->rx_copy.completed, pkt->skb);
+}
+
+static void xenvif_rx_next_frag(struct xenvif_pkt_state *pkt)
+{
+	struct sk_buff *frag_iter = pkt->frag_iter;
+	unsigned int nr_frags = skb_shinfo(frag_iter)->nr_frags;
+
+	pkt->frag++;
+	pkt->frag_offset = 0;
+
+	if (pkt->frag >= nr_frags) {
+		if (frag_iter == pkt->skb)
+			pkt->frag_iter = skb_shinfo(frag_iter)->frag_list;
+		else
+			pkt->frag_iter = frag_iter->next;
+
+		pkt->frag = -1;
+	}
+}
+
+static void xenvif_rx_next_chunk(struct xenvif_queue *queue,
+				 struct xenvif_pkt_state *pkt,
+				 unsigned int offset, void **data,
+				 size_t *len)
+{
+	struct sk_buff *frag_iter = pkt->frag_iter;
+	void *frag_data;
+	size_t frag_len, chunk_len;
+
+	BUG_ON(!frag_iter);
+
+	if (pkt->frag == -1) {
+		frag_data = frag_iter->data;
+		frag_len = skb_headlen(frag_iter);
+	} else {
+		skb_frag_t *frag = &skb_shinfo(frag_iter)->frags[pkt->frag];
+
+		frag_data = skb_frag_address(frag);
+		frag_len = skb_frag_size(frag);
+	}
+
+	frag_data += pkt->frag_offset;
+	frag_len -= pkt->frag_offset;
+
+	chunk_len = min_t(size_t, frag_len, XEN_PAGE_SIZE - offset);
+	chunk_len = min_t(size_t, chunk_len, XEN_PAGE_SIZE -
+					     xen_offset_in_page(frag_data));
+
+	pkt->frag_offset += chunk_len;
+
+	/* Advance to next frag? */
+	if (frag_len == chunk_len)
+		xenvif_rx_next_frag(pkt);
+
+	*data = frag_data;
+	*len = chunk_len;
+}
+
+static void xenvif_rx_data_slot(struct xenvif_queue *queue,
+				struct xenvif_pkt_state *pkt,
+				struct xen_netif_rx_request *req,
+				struct xen_netif_rx_response *rsp)
+{
+	unsigned int offset = queue->vif->xdp_headroom;
+	unsigned int flags;
+
+	do {
+		size_t len;
+		void *data;
+
+		xenvif_rx_next_chunk(queue, pkt, offset, &data, &len);
+		xenvif_rx_copy_add(queue, req, offset, data, len);
+
+		offset += len;
+		pkt->remaining_len -= len;
+
+	} while (offset < XEN_PAGE_SIZE && pkt->remaining_len > 0);
+
+	if (pkt->remaining_len > 0)
+		flags = XEN_NETRXF_more_data;
+	else
+		flags = 0;
+
+	if (pkt->slot == 0) {
+		struct sk_buff *skb = pkt->skb;
+
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			flags |= XEN_NETRXF_csum_blank |
+				 XEN_NETRXF_data_validated;
+		else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
+			flags |= XEN_NETRXF_data_validated;
+
+		if (pkt->extra_count != 0)
+			flags |= XEN_NETRXF_extra_info;
+	}
+
+	rsp->offset = 0;
+	rsp->flags = flags;
+	rsp->id = req->id;
+	rsp->status = (s16)offset;
+}
+
+static void xenvif_rx_extra_slot(struct xenvif_queue *queue,
+				 struct xenvif_pkt_state *pkt,
+				 struct xen_netif_rx_request *req,
+				 struct xen_netif_rx_response *rsp)
+{
+	struct xen_netif_extra_info *extra = (void *)rsp;
+	unsigned int i;
+
+	pkt->extra_count--;
+
+	for (i = 0; i < ARRAY_SIZE(pkt->extras); i++) {
+		if (pkt->extras[i].type) {
+			*extra = pkt->extras[i];
+
+			if (pkt->extra_count != 0)
+				extra->flags |= XEN_NETIF_EXTRA_FLAG_MORE;
+
+			pkt->extras[i].type = 0;
+			return;
+		}
+	}
+	BUG();
+}
+
+static void xenvif_rx_skb(struct xenvif_queue *queue)
+{
+	struct xenvif_pkt_state pkt;
+
+	xenvif_rx_next_skb(queue, &pkt);
+
+	queue->last_rx_time = jiffies;
+
+	do {
+		struct xen_netif_rx_request *req;
+		struct xen_netif_rx_response *rsp;
+
+		req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons);
+		rsp = RING_GET_RESPONSE(&queue->rx, queue->rx.req_cons);
+
+		/* Extras must go after the first data slot */
+		if (pkt.slot != 0 && pkt.extra_count != 0)
+			xenvif_rx_extra_slot(queue, &pkt, req, rsp);
+		else
+			xenvif_rx_data_slot(queue, &pkt, req, rsp);
+
+		queue->rx.req_cons++;
+		pkt.slot++;
+	} while (pkt.remaining_len > 0 || pkt.extra_count != 0);
+
+	xenvif_rx_complete(queue, &pkt);
+}
+
+#define RX_BATCH_SIZE 64
+
+static void xenvif_rx_action(struct xenvif_queue *queue)
+{
+	struct sk_buff_head completed_skbs;
+	unsigned int work_done = 0;
+
+	__skb_queue_head_init(&completed_skbs);
+	queue->rx_copy.completed = &completed_skbs;
+
+	while (xenvif_rx_ring_slots_available(queue) &&
+	       !skb_queue_empty(&queue->rx_queue) &&
+	       work_done < RX_BATCH_SIZE) {
+		xenvif_rx_skb(queue);
+		work_done++;
+	}
+
+	/* Flush any pending copies and complete all skbs. */
+	xenvif_rx_copy_flush(queue);
+}
+
+static RING_IDX xenvif_rx_queue_slots(const struct xenvif_queue *queue)
+{
+	RING_IDX prod, cons;
+
+	prod = queue->rx.sring->req_prod;
+	cons = queue->rx.req_cons;
+
+	return prod - cons;
+}
+
+static bool xenvif_rx_queue_stalled(const struct xenvif_queue *queue)
+{
+	unsigned int needed = READ_ONCE(queue->rx_slots_needed);
+
+	return !queue->stalled &&
+		xenvif_rx_queue_slots(queue) < needed &&
+		time_after(jiffies,
+			   queue->last_rx_time + queue->vif->stall_timeout);
+}
+
+static bool xenvif_rx_queue_ready(struct xenvif_queue *queue)
+{
+	unsigned int needed = READ_ONCE(queue->rx_slots_needed);
+
+	return queue->stalled && xenvif_rx_queue_slots(queue) >= needed;
+}
+
+bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread)
+{
+	return xenvif_rx_ring_slots_available(queue) ||
+		(queue->vif->stall_timeout &&
+		 (xenvif_rx_queue_stalled(queue) ||
+		  xenvif_rx_queue_ready(queue))) ||
+		(test_kthread && kthread_should_stop()) ||
+		queue->vif->disabled;
+}
+
+static long xenvif_rx_queue_timeout(struct xenvif_queue *queue)
+{
+	struct sk_buff *skb;
+	long timeout;
+
+	skb = skb_peek(&queue->rx_queue);
+	if (!skb)
+		return MAX_SCHEDULE_TIMEOUT;
+
+	timeout = XENVIF_RX_CB(skb)->expires - jiffies;
+	return timeout < 0 ? 0 : timeout;
+}
+
+/* Wait until the guest Rx thread has work.
+ *
+ * The timeout needs to be adjusted based on the current head of the
+ * queue (and not just the head at the beginning).  In particular, if
+ * the queue is initially empty an infinite timeout is used and this
+ * needs to be reduced when a skb is queued.
+ *
+ * This cannot be done with wait_event_timeout() because it only
+ * calculates the timeout once.
+ */
+static void xenvif_wait_for_rx_work(struct xenvif_queue *queue)
+{
+	DEFINE_WAIT(wait);
+
+	if (xenvif_have_rx_work(queue, true))
+		return;
+
+	for (;;) {
+		long ret;
+
+		prepare_to_wait(&queue->wq, &wait, TASK_INTERRUPTIBLE);
+		if (xenvif_have_rx_work(queue, true))
+			break;
+		if (atomic_fetch_andnot(NETBK_RX_EOI | NETBK_COMMON_EOI,
+					&queue->eoi_pending) &
+		    (NETBK_RX_EOI | NETBK_COMMON_EOI))
+			xen_irq_lateeoi(queue->rx_irq, 0);
+
+		ret = schedule_timeout(xenvif_rx_queue_timeout(queue));
+		if (!ret)
+			break;
+	}
+	finish_wait(&queue->wq, &wait);
+}
+
+static void xenvif_queue_carrier_off(struct xenvif_queue *queue)
+{
+	struct xenvif *vif = queue->vif;
+
+	queue->stalled = true;
+
+	/* At least one queue has stalled? Disable the carrier. */
+	spin_lock(&vif->lock);
+	if (vif->stalled_queues++ == 0) {
+		netdev_info(vif->dev, "Guest Rx stalled");
+		netif_carrier_off(vif->dev);
+	}
+	spin_unlock(&vif->lock);
+}
+
+static void xenvif_queue_carrier_on(struct xenvif_queue *queue)
+{
+	struct xenvif *vif = queue->vif;
+
+	queue->last_rx_time = jiffies; /* Reset Rx stall detection. */
+	queue->stalled = false;
+
+	/* All queues are ready? Enable the carrier. */
+	spin_lock(&vif->lock);
+	if (--vif->stalled_queues == 0) {
+		netdev_info(vif->dev, "Guest Rx ready");
+		netif_carrier_on(vif->dev);
+	}
+	spin_unlock(&vif->lock);
+}
+
+int xenvif_kthread_guest_rx(void *data)
+{
+	struct xenvif_queue *queue = data;
+	struct xenvif *vif = queue->vif;
+
+	if (!vif->stall_timeout)
+		xenvif_queue_carrier_on(queue);
+
+	for (;;) {
+		xenvif_wait_for_rx_work(queue);
+
+		if (kthread_should_stop())
+			break;
+
+		/* This frontend is found to be rogue, disable it in
+		 * kthread context. Currently this is only set when
+		 * netback finds out frontend sends malformed packet,
+		 * but we cannot disable the interface in softirq
+		 * context so we defer it here, if this thread is
+		 * associated with queue 0.
+		 */
+		if (unlikely(vif->disabled && queue->id == 0)) {
+			xenvif_carrier_off(vif);
+			break;
+		}
+
+		if (!skb_queue_empty(&queue->rx_queue))
+			xenvif_rx_action(queue);
+
+		/* If the guest hasn't provided any Rx slots for a
+		 * while it's probably not responsive, drop the
+		 * carrier so packets are dropped earlier.
+		 */
+		if (vif->stall_timeout) {
+			if (xenvif_rx_queue_stalled(queue))
+				xenvif_queue_carrier_off(queue);
+			else if (xenvif_rx_queue_ready(queue))
+				xenvif_queue_carrier_on(queue);
+		}
+
+		/* Queued packets may have foreign pages from other
+		 * domains.  These cannot be queued indefinitely as
+		 * this would starve guests of grant refs and transmit
+		 * slots.
+		 */
+		xenvif_rx_queue_drop_expired(queue);
+
+		cond_resched();
+	}
+
+	/* Bin any remaining skbs */
+	xenvif_rx_queue_purge(queue);
+
+	return 0;
+}