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, 468 insertions, 0 deletions

diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c
new file mode 100644
index 000000000..ff96f2264
--- /dev/null
+++ b/drivers/net/xen-netback/hash.c
@@ -0,0 +1,468 @@
+/*
+ * Copyright (c) 2016 Citrix Systems Inc.
+ *
+ * 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 Softare 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.
+ */
+
+#define XEN_NETIF_DEFINE_TOEPLITZ
+
+#include "common.h"
+#include <linux/vmalloc.h>
+#include <linux/rculist.h>
+
+static void xenvif_add_hash(struct xenvif *vif, const u8 *tag,
+			    unsigned int len, u32 val)
+{
+	struct xenvif_hash_cache_entry *new, *entry, *oldest;
+	unsigned long flags;
+	bool found;
+
+	new = kmalloc(sizeof(*entry), GFP_ATOMIC);
+	if (!new)
+		return;
+
+	memcpy(new->tag, tag, len);
+	new->len = len;
+	new->val = val;
+
+	spin_lock_irqsave(&vif->hash.cache.lock, flags);
+
+	found = false;
+	oldest = NULL;
+	list_for_each_entry_rcu(entry, &vif->hash.cache.list, link,
+				lockdep_is_held(&vif->hash.cache.lock)) {
+		/* Make sure we don't add duplicate entries */
+		if (entry->len == len &&
+		    memcmp(entry->tag, tag, len) == 0)
+			found = true;
+		if (!oldest || entry->seq < oldest->seq)
+			oldest = entry;
+	}
+
+	if (!found) {
+		new->seq = atomic_inc_return(&vif->hash.cache.seq);
+		list_add_rcu(&new->link, &vif->hash.cache.list);
+
+		if (++vif->hash.cache.count > xenvif_hash_cache_size) {
+			list_del_rcu(&oldest->link);
+			vif->hash.cache.count--;
+			kfree_rcu(oldest, rcu);
+		}
+	}
+
+	spin_unlock_irqrestore(&vif->hash.cache.lock, flags);
+
+	if (found)
+		kfree(new);
+}
+
+static u32 xenvif_new_hash(struct xenvif *vif, const u8 *data,
+			   unsigned int len)
+{
+	u32 val;
+
+	val = xen_netif_toeplitz_hash(vif->hash.key,
+				      sizeof(vif->hash.key),
+				      data, len);
+
+	if (xenvif_hash_cache_size != 0)
+		xenvif_add_hash(vif, data, len, val);
+
+	return val;
+}
+
+static void xenvif_flush_hash(struct xenvif *vif)
+{
+	struct xenvif_hash_cache_entry *entry;
+	unsigned long flags;
+
+	if (xenvif_hash_cache_size == 0)
+		return;
+
+	spin_lock_irqsave(&vif->hash.cache.lock, flags);
+
+	list_for_each_entry_rcu(entry, &vif->hash.cache.list, link,
+				lockdep_is_held(&vif->hash.cache.lock)) {
+		list_del_rcu(&entry->link);
+		vif->hash.cache.count--;
+		kfree_rcu(entry, rcu);
+	}
+
+	spin_unlock_irqrestore(&vif->hash.cache.lock, flags);
+}
+
+static u32 xenvif_find_hash(struct xenvif *vif, const u8 *data,
+			    unsigned int len)
+{
+	struct xenvif_hash_cache_entry *entry;
+	u32 val;
+	bool found;
+
+	if (len >= XEN_NETBK_HASH_TAG_SIZE)
+		return 0;
+
+	if (xenvif_hash_cache_size == 0)
+		return xenvif_new_hash(vif, data, len);
+
+	rcu_read_lock();
+
+	found = false;
+
+	list_for_each_entry_rcu(entry, &vif->hash.cache.list, link) {
+		if (entry->len == len &&
+		    memcmp(entry->tag, data, len) == 0) {
+			val = entry->val;
+			entry->seq = atomic_inc_return(&vif->hash.cache.seq);
+			found = true;
+			break;
+		}
+	}
+
+	rcu_read_unlock();
+
+	if (!found)
+		val = xenvif_new_hash(vif, data, len);
+
+	return val;
+}
+
+void xenvif_set_skb_hash(struct xenvif *vif, struct sk_buff *skb)
+{
+	struct flow_keys flow;
+	u32 hash = 0;
+	enum pkt_hash_types type = PKT_HASH_TYPE_NONE;
+	u32 flags = vif->hash.flags;
+	bool has_tcp_hdr;
+
+	/* Quick rejection test: If the network protocol doesn't
+	 * correspond to any enabled hash type then there's no point
+	 * in parsing the packet header.
+	 */
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		if (flags & (XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP |
+			     XEN_NETIF_CTRL_HASH_TYPE_IPV4))
+			break;
+
+		goto done;
+
+	case htons(ETH_P_IPV6):
+		if (flags & (XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP |
+			     XEN_NETIF_CTRL_HASH_TYPE_IPV6))
+			break;
+
+		goto done;
+
+	default:
+		goto done;
+	}
+
+	memset(&flow, 0, sizeof(flow));
+	if (!skb_flow_dissect_flow_keys(skb, &flow, 0))
+		goto done;
+
+	has_tcp_hdr = (flow.basic.ip_proto == IPPROTO_TCP) &&
+		      !(flow.control.flags & FLOW_DIS_IS_FRAGMENT);
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		if (has_tcp_hdr &&
+		    (flags & XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP)) {
+			u8 data[12];
+
+			memcpy(&data[0], &flow.addrs.v4addrs.src, 4);
+			memcpy(&data[4], &flow.addrs.v4addrs.dst, 4);
+			memcpy(&data[8], &flow.ports.src, 2);
+			memcpy(&data[10], &flow.ports.dst, 2);
+
+			hash = xenvif_find_hash(vif, data, sizeof(data));
+			type = PKT_HASH_TYPE_L4;
+		} else if (flags & XEN_NETIF_CTRL_HASH_TYPE_IPV4) {
+			u8 data[8];
+
+			memcpy(&data[0], &flow.addrs.v4addrs.src, 4);
+			memcpy(&data[4], &flow.addrs.v4addrs.dst, 4);
+
+			hash = xenvif_find_hash(vif, data, sizeof(data));
+			type = PKT_HASH_TYPE_L3;
+		}
+
+		break;
+
+	case htons(ETH_P_IPV6):
+		if (has_tcp_hdr &&
+		    (flags & XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP)) {
+			u8 data[36];
+
+			memcpy(&data[0], &flow.addrs.v6addrs.src, 16);
+			memcpy(&data[16], &flow.addrs.v6addrs.dst, 16);
+			memcpy(&data[32], &flow.ports.src, 2);
+			memcpy(&data[34], &flow.ports.dst, 2);
+
+			hash = xenvif_find_hash(vif, data, sizeof(data));
+			type = PKT_HASH_TYPE_L4;
+		} else if (flags & XEN_NETIF_CTRL_HASH_TYPE_IPV6) {
+			u8 data[32];
+
+			memcpy(&data[0], &flow.addrs.v6addrs.src, 16);
+			memcpy(&data[16], &flow.addrs.v6addrs.dst, 16);
+
+			hash = xenvif_find_hash(vif, data, sizeof(data));
+			type = PKT_HASH_TYPE_L3;
+		}
+
+		break;
+	}
+
+done:
+	if (type == PKT_HASH_TYPE_NONE)
+		skb_clear_hash(skb);
+	else
+		__skb_set_sw_hash(skb, hash, type == PKT_HASH_TYPE_L4);
+}
+
+u32 xenvif_set_hash_alg(struct xenvif *vif, u32 alg)
+{
+	switch (alg) {
+	case XEN_NETIF_CTRL_HASH_ALGORITHM_NONE:
+	case XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ:
+		break;
+
+	default:
+		return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+	}
+
+	vif->hash.alg = alg;
+
+	return XEN_NETIF_CTRL_STATUS_SUCCESS;
+}
+
+u32 xenvif_get_hash_flags(struct xenvif *vif, u32 *flags)
+{
+	if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
+		return XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED;
+
+	*flags = XEN_NETIF_CTRL_HASH_TYPE_IPV4 |
+		 XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP |
+		 XEN_NETIF_CTRL_HASH_TYPE_IPV6 |
+		 XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP;
+
+	return XEN_NETIF_CTRL_STATUS_SUCCESS;
+}
+
+u32 xenvif_set_hash_flags(struct xenvif *vif, u32 flags)
+{
+	if (flags & ~(XEN_NETIF_CTRL_HASH_TYPE_IPV4 |
+		      XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP |
+		      XEN_NETIF_CTRL_HASH_TYPE_IPV6 |
+		      XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP))
+		return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+
+	if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
+		return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+
+	vif->hash.flags = flags;
+
+	return XEN_NETIF_CTRL_STATUS_SUCCESS;
+}
+
+u32 xenvif_set_hash_key(struct xenvif *vif, u32 gref, u32 len)
+{
+	u8 *key = vif->hash.key;
+	struct gnttab_copy copy_op = {
+		.source.u.ref = gref,
+		.source.domid = vif->domid,
+		.dest.u.gmfn = virt_to_gfn(key),
+		.dest.domid = DOMID_SELF,
+		.dest.offset = xen_offset_in_page(key),
+		.len = len,
+		.flags = GNTCOPY_source_gref
+	};
+
+	if (len > XEN_NETBK_MAX_HASH_KEY_SIZE)
+		return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+
+	if (copy_op.len != 0) {
+		gnttab_batch_copy(&copy_op, 1);
+
+		if (copy_op.status != GNTST_okay)
+			return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+	}
+
+	/* Clear any remaining key octets */
+	if (len < XEN_NETBK_MAX_HASH_KEY_SIZE)
+		memset(key + len, 0, XEN_NETBK_MAX_HASH_KEY_SIZE - len);
+
+	xenvif_flush_hash(vif);
+
+	return XEN_NETIF_CTRL_STATUS_SUCCESS;
+}
+
+u32 xenvif_set_hash_mapping_size(struct xenvif *vif, u32 size)
+{
+	if (size > XEN_NETBK_MAX_HASH_MAPPING_SIZE)
+		return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+
+	vif->hash.size = size;
+	memset(vif->hash.mapping[vif->hash.mapping_sel], 0,
+	       sizeof(u32) * size);
+
+	return XEN_NETIF_CTRL_STATUS_SUCCESS;
+}
+
+u32 xenvif_set_hash_mapping(struct xenvif *vif, u32 gref, u32 len,
+			    u32 off)
+{
+	u32 *mapping = vif->hash.mapping[!vif->hash.mapping_sel];
+	unsigned int nr = 1;
+	struct gnttab_copy copy_op[2] = {{
+		.source.u.ref = gref,
+		.source.domid = vif->domid,
+		.dest.domid = DOMID_SELF,
+		.len = len * sizeof(*mapping),
+		.flags = GNTCOPY_source_gref
+	}};
+
+	if ((off + len < off) || (off + len > vif->hash.size) ||
+	    len > XEN_PAGE_SIZE / sizeof(*mapping))
+		return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+
+	copy_op[0].dest.u.gmfn = virt_to_gfn(mapping + off);
+	copy_op[0].dest.offset = xen_offset_in_page(mapping + off);
+	if (copy_op[0].dest.offset + copy_op[0].len > XEN_PAGE_SIZE) {
+		copy_op[1] = copy_op[0];
+		copy_op[1].source.offset = XEN_PAGE_SIZE - copy_op[0].dest.offset;
+		copy_op[1].dest.u.gmfn = virt_to_gfn(mapping + off + len);
+		copy_op[1].dest.offset = 0;
+		copy_op[1].len = copy_op[0].len - copy_op[1].source.offset;
+		copy_op[0].len = copy_op[1].source.offset;
+		nr = 2;
+	}
+
+	memcpy(mapping, vif->hash.mapping[vif->hash.mapping_sel],
+	       vif->hash.size * sizeof(*mapping));
+
+	if (copy_op[0].len != 0) {
+		gnttab_batch_copy(copy_op, nr);
+
+		if (copy_op[0].status != GNTST_okay ||
+		    copy_op[nr - 1].status != GNTST_okay)
+			return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+	}
+
+	while (len-- != 0)
+		if (mapping[off++] >= vif->num_queues)
+			return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+
+	vif->hash.mapping_sel = !vif->hash.mapping_sel;
+
+	return XEN_NETIF_CTRL_STATUS_SUCCESS;
+}
+
+#ifdef CONFIG_DEBUG_FS
+void xenvif_dump_hash_info(struct xenvif *vif, struct seq_file *m)
+{
+	unsigned int i;
+
+	switch (vif->hash.alg) {
+	case XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ:
+		seq_puts(m, "Hash Algorithm: TOEPLITZ\n");
+		break;
+
+	case XEN_NETIF_CTRL_HASH_ALGORITHM_NONE:
+		seq_puts(m, "Hash Algorithm: NONE\n");
+		fallthrough;
+	default:
+		return;
+	}
+
+	if (vif->hash.flags) {
+		seq_puts(m, "\nHash Flags:\n");
+
+		if (vif->hash.flags & XEN_NETIF_CTRL_HASH_TYPE_IPV4)
+			seq_puts(m, "- IPv4\n");
+		if (vif->hash.flags & XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP)
+			seq_puts(m, "- IPv4 + TCP\n");
+		if (vif->hash.flags & XEN_NETIF_CTRL_HASH_TYPE_IPV6)
+			seq_puts(m, "- IPv6\n");
+		if (vif->hash.flags & XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP)
+			seq_puts(m, "- IPv6 + TCP\n");
+	}
+
+	seq_puts(m, "\nHash Key:\n");
+
+	for (i = 0; i < XEN_NETBK_MAX_HASH_KEY_SIZE; ) {
+		unsigned int j, n;
+
+		n = 8;
+		if (i + n >= XEN_NETBK_MAX_HASH_KEY_SIZE)
+			n = XEN_NETBK_MAX_HASH_KEY_SIZE - i;
+
+		seq_printf(m, "[%2u - %2u]: ", i, i + n - 1);
+
+		for (j = 0; j < n; j++, i++)
+			seq_printf(m, "%02x ", vif->hash.key[i]);
+
+		seq_puts(m, "\n");
+	}
+
+	if (vif->hash.size != 0) {
+		const u32 *mapping = vif->hash.mapping[vif->hash.mapping_sel];
+
+		seq_puts(m, "\nHash Mapping:\n");
+
+		for (i = 0; i < vif->hash.size; ) {
+			unsigned int j, n;
+
+			n = 8;
+			if (i + n >= vif->hash.size)
+				n = vif->hash.size - i;
+
+			seq_printf(m, "[%4u - %4u]: ", i, i + n - 1);
+
+			for (j = 0; j < n; j++, i++)
+				seq_printf(m, "%4u ", mapping[i]);
+
+			seq_puts(m, "\n");
+		}
+	}
+}
+#endif /* CONFIG_DEBUG_FS */
+
+void xenvif_init_hash(struct xenvif *vif)
+{
+	if (xenvif_hash_cache_size == 0)
+		return;
+
+	BUG_ON(vif->hash.cache.count);
+
+	spin_lock_init(&vif->hash.cache.lock);
+	INIT_LIST_HEAD(&vif->hash.cache.list);
+}
+
+void xenvif_deinit_hash(struct xenvif *vif)
+{
+	xenvif_flush_hash(vif);
+}