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, 549 insertions, 0 deletions

diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c
new file mode 100644
index 000000000..5a09a09cc
--- /dev/null
+++ b/drivers/vdpa/alibaba/eni_vdpa.c
@@ -0,0 +1,549 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vDPA bridge driver for Alibaba ENI(Elastic Network Interface)
+ *
+ * Copyright (c) 2021, Alibaba Inc. All rights reserved.
+ * Author: Wu Zongyong <wuzongyong@linux.alibaba.com>
+ *
+ */
+
+#include "linux/bits.h"
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/vdpa.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_pci.h>
+#include <linux/virtio_pci_legacy.h>
+#include <uapi/linux/virtio_net.h>
+
+#define ENI_MSIX_NAME_SIZE 256
+
+#define ENI_ERR(pdev, fmt, ...)	\
+	dev_err(&pdev->dev, "%s"fmt, "eni_vdpa: ", ##__VA_ARGS__)
+#define ENI_DBG(pdev, fmt, ...)	\
+	dev_dbg(&pdev->dev, "%s"fmt, "eni_vdpa: ", ##__VA_ARGS__)
+#define ENI_INFO(pdev, fmt, ...) \
+	dev_info(&pdev->dev, "%s"fmt, "eni_vdpa: ", ##__VA_ARGS__)
+
+struct eni_vring {
+	void __iomem *notify;
+	char msix_name[ENI_MSIX_NAME_SIZE];
+	struct vdpa_callback cb;
+	int irq;
+};
+
+struct eni_vdpa {
+	struct vdpa_device vdpa;
+	struct virtio_pci_legacy_device ldev;
+	struct eni_vring *vring;
+	struct vdpa_callback config_cb;
+	char msix_name[ENI_MSIX_NAME_SIZE];
+	int config_irq;
+	int queues;
+	int vectors;
+};
+
+static struct eni_vdpa *vdpa_to_eni(struct vdpa_device *vdpa)
+{
+	return container_of(vdpa, struct eni_vdpa, vdpa);
+}
+
+static struct virtio_pci_legacy_device *vdpa_to_ldev(struct vdpa_device *vdpa)
+{
+	struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+
+	return &eni_vdpa->ldev;
+}
+
+static u64 eni_vdpa_get_device_features(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+	u64 features = vp_legacy_get_features(ldev);
+
+	features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM);
+	features |= BIT_ULL(VIRTIO_F_ORDER_PLATFORM);
+
+	return features;
+}
+
+static int eni_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+	if (!(features & BIT_ULL(VIRTIO_NET_F_MRG_RXBUF)) && features) {
+		ENI_ERR(ldev->pci_dev,
+			"VIRTIO_NET_F_MRG_RXBUF is not negotiated\n");
+		return -EINVAL;
+	}
+
+	vp_legacy_set_features(ldev, (u32)features);
+
+	return 0;
+}
+
+static u64 eni_vdpa_get_driver_features(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+	return vp_legacy_get_driver_features(ldev);
+}
+
+static u8 eni_vdpa_get_status(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+	return vp_legacy_get_status(ldev);
+}
+
+static int eni_vdpa_get_vq_irq(struct vdpa_device *vdpa, u16 idx)
+{
+	struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+	int irq = eni_vdpa->vring[idx].irq;
+
+	if (irq == VIRTIO_MSI_NO_VECTOR)
+		return -EINVAL;
+
+	return irq;
+}
+
+static void eni_vdpa_free_irq(struct eni_vdpa *eni_vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+	struct pci_dev *pdev = ldev->pci_dev;
+	int i;
+
+	for (i = 0; i < eni_vdpa->queues; i++) {
+		if (eni_vdpa->vring[i].irq != VIRTIO_MSI_NO_VECTOR) {
+			vp_legacy_queue_vector(ldev, i, VIRTIO_MSI_NO_VECTOR);
+			devm_free_irq(&pdev->dev, eni_vdpa->vring[i].irq,
+				      &eni_vdpa->vring[i]);
+			eni_vdpa->vring[i].irq = VIRTIO_MSI_NO_VECTOR;
+		}
+	}
+
+	if (eni_vdpa->config_irq != VIRTIO_MSI_NO_VECTOR) {
+		vp_legacy_config_vector(ldev, VIRTIO_MSI_NO_VECTOR);
+		devm_free_irq(&pdev->dev, eni_vdpa->config_irq, eni_vdpa);
+		eni_vdpa->config_irq = VIRTIO_MSI_NO_VECTOR;
+	}
+
+	if (eni_vdpa->vectors) {
+		pci_free_irq_vectors(pdev);
+		eni_vdpa->vectors = 0;
+	}
+}
+
+static irqreturn_t eni_vdpa_vq_handler(int irq, void *arg)
+{
+	struct eni_vring *vring = arg;
+
+	if (vring->cb.callback)
+		return vring->cb.callback(vring->cb.private);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t eni_vdpa_config_handler(int irq, void *arg)
+{
+	struct eni_vdpa *eni_vdpa = arg;
+
+	if (eni_vdpa->config_cb.callback)
+		return eni_vdpa->config_cb.callback(eni_vdpa->config_cb.private);
+
+	return IRQ_HANDLED;
+}
+
+static int eni_vdpa_request_irq(struct eni_vdpa *eni_vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+	struct pci_dev *pdev = ldev->pci_dev;
+	int i, ret, irq;
+	int queues = eni_vdpa->queues;
+	int vectors = queues + 1;
+
+	ret = pci_alloc_irq_vectors(pdev, vectors, vectors, PCI_IRQ_MSIX);
+	if (ret != vectors) {
+		ENI_ERR(pdev,
+			"failed to allocate irq vectors want %d but %d\n",
+			vectors, ret);
+		return ret;
+	}
+
+	eni_vdpa->vectors = vectors;
+
+	for (i = 0; i < queues; i++) {
+		snprintf(eni_vdpa->vring[i].msix_name, ENI_MSIX_NAME_SIZE,
+			 "eni-vdpa[%s]-%d\n", pci_name(pdev), i);
+		irq = pci_irq_vector(pdev, i);
+		ret = devm_request_irq(&pdev->dev, irq,
+				       eni_vdpa_vq_handler,
+				       0, eni_vdpa->vring[i].msix_name,
+				       &eni_vdpa->vring[i]);
+		if (ret) {
+			ENI_ERR(pdev, "failed to request irq for vq %d\n", i);
+			goto err;
+		}
+		vp_legacy_queue_vector(ldev, i, i);
+		eni_vdpa->vring[i].irq = irq;
+	}
+
+	snprintf(eni_vdpa->msix_name, ENI_MSIX_NAME_SIZE, "eni-vdpa[%s]-config\n",
+		 pci_name(pdev));
+	irq = pci_irq_vector(pdev, queues);
+	ret = devm_request_irq(&pdev->dev, irq, eni_vdpa_config_handler, 0,
+			       eni_vdpa->msix_name, eni_vdpa);
+	if (ret) {
+		ENI_ERR(pdev, "failed to request irq for config vq %d\n", i);
+		goto err;
+	}
+	vp_legacy_config_vector(ldev, queues);
+	eni_vdpa->config_irq = irq;
+
+	return 0;
+err:
+	eni_vdpa_free_irq(eni_vdpa);
+	return ret;
+}
+
+static void eni_vdpa_set_status(struct vdpa_device *vdpa, u8 status)
+{
+	struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+	struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+	u8 s = eni_vdpa_get_status(vdpa);
+
+	if (status & VIRTIO_CONFIG_S_DRIVER_OK &&
+	    !(s & VIRTIO_CONFIG_S_DRIVER_OK)) {
+		eni_vdpa_request_irq(eni_vdpa);
+	}
+
+	vp_legacy_set_status(ldev, status);
+
+	if (!(status & VIRTIO_CONFIG_S_DRIVER_OK) &&
+	    (s & VIRTIO_CONFIG_S_DRIVER_OK))
+		eni_vdpa_free_irq(eni_vdpa);
+}
+
+static int eni_vdpa_reset(struct vdpa_device *vdpa)
+{
+	struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+	struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+	u8 s = eni_vdpa_get_status(vdpa);
+
+	vp_legacy_set_status(ldev, 0);
+
+	if (s & VIRTIO_CONFIG_S_DRIVER_OK)
+		eni_vdpa_free_irq(eni_vdpa);
+
+	return 0;
+}
+
+static u16 eni_vdpa_get_vq_num_max(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+	return vp_legacy_get_queue_size(ldev, 0);
+}
+
+static u16 eni_vdpa_get_vq_num_min(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+	return vp_legacy_get_queue_size(ldev, 0);
+}
+
+static int eni_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 qid,
+				struct vdpa_vq_state *state)
+{
+	return -EOPNOTSUPP;
+}
+
+static int eni_vdpa_set_vq_state(struct vdpa_device *vdpa, u16 qid,
+				 const struct vdpa_vq_state *state)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+	const struct vdpa_vq_state_split *split = &state->split;
+
+	/* ENI is build upon virtio-pci specfication which not support
+	 * to set state of virtqueue. But if the state is equal to the
+	 * device initial state by chance, we can let it go.
+	 */
+	if (!vp_legacy_get_queue_enable(ldev, qid)
+	    && split->avail_index == 0)
+		return 0;
+
+	return -EOPNOTSUPP;
+}
+
+
+static void eni_vdpa_set_vq_cb(struct vdpa_device *vdpa, u16 qid,
+			       struct vdpa_callback *cb)
+{
+	struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+
+	eni_vdpa->vring[qid].cb = *cb;
+}
+
+static void eni_vdpa_set_vq_ready(struct vdpa_device *vdpa, u16 qid,
+				  bool ready)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+	/* ENI is a legacy virtio-pci device. This is not supported
+	 * by specification. But we can disable virtqueue by setting
+	 * address to 0.
+	 */
+	if (!ready)
+		vp_legacy_set_queue_address(ldev, qid, 0);
+}
+
+static bool eni_vdpa_get_vq_ready(struct vdpa_device *vdpa, u16 qid)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+	return vp_legacy_get_queue_enable(ldev, qid);
+}
+
+static void eni_vdpa_set_vq_num(struct vdpa_device *vdpa, u16 qid,
+			       u32 num)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+	struct pci_dev *pdev = ldev->pci_dev;
+	u16 n = vp_legacy_get_queue_size(ldev, qid);
+
+	/* ENI is a legacy virtio-pci device which not allow to change
+	 * virtqueue size. Just report a error if someone tries to
+	 * change it.
+	 */
+	if (num != n)
+		ENI_ERR(pdev,
+			"not support to set vq %u fixed num %u to %u\n",
+			qid, n, num);
+}
+
+static int eni_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 qid,
+				   u64 desc_area, u64 driver_area,
+				   u64 device_area)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+	u32 pfn = desc_area >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
+
+	vp_legacy_set_queue_address(ldev, qid, pfn);
+
+	return 0;
+}
+
+static void eni_vdpa_kick_vq(struct vdpa_device *vdpa, u16 qid)
+{
+	struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+
+	iowrite16(qid, eni_vdpa->vring[qid].notify);
+}
+
+static u32 eni_vdpa_get_device_id(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+	return ldev->id.device;
+}
+
+static u32 eni_vdpa_get_vendor_id(struct vdpa_device *vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+	return ldev->id.vendor;
+}
+
+static u32 eni_vdpa_get_vq_align(struct vdpa_device *vdpa)
+{
+	return VIRTIO_PCI_VRING_ALIGN;
+}
+
+static size_t eni_vdpa_get_config_size(struct vdpa_device *vdpa)
+{
+	return sizeof(struct virtio_net_config);
+}
+
+
+static void eni_vdpa_get_config(struct vdpa_device *vdpa,
+				unsigned int offset,
+				void *buf, unsigned int len)
+{
+	struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+	struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+	void __iomem *ioaddr = ldev->ioaddr +
+		VIRTIO_PCI_CONFIG_OFF(eni_vdpa->vectors) +
+		offset;
+	u8 *p = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		*p++ = ioread8(ioaddr + i);
+}
+
+static void eni_vdpa_set_config(struct vdpa_device *vdpa,
+				unsigned int offset, const void *buf,
+				unsigned int len)
+{
+	struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+	struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+	void __iomem *ioaddr = ldev->ioaddr +
+		VIRTIO_PCI_CONFIG_OFF(eni_vdpa->vectors) +
+		offset;
+	const u8 *p = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		iowrite8(*p++, ioaddr + i);
+}
+
+static void eni_vdpa_set_config_cb(struct vdpa_device *vdpa,
+				   struct vdpa_callback *cb)
+{
+	struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+
+	eni_vdpa->config_cb = *cb;
+}
+
+static const struct vdpa_config_ops eni_vdpa_ops = {
+	.get_device_features = eni_vdpa_get_device_features,
+	.set_driver_features = eni_vdpa_set_driver_features,
+	.get_driver_features = eni_vdpa_get_driver_features,
+	.get_status	= eni_vdpa_get_status,
+	.set_status	= eni_vdpa_set_status,
+	.reset		= eni_vdpa_reset,
+	.get_vq_num_max	= eni_vdpa_get_vq_num_max,
+	.get_vq_num_min	= eni_vdpa_get_vq_num_min,
+	.get_vq_state	= eni_vdpa_get_vq_state,
+	.set_vq_state	= eni_vdpa_set_vq_state,
+	.set_vq_cb	= eni_vdpa_set_vq_cb,
+	.set_vq_ready	= eni_vdpa_set_vq_ready,
+	.get_vq_ready	= eni_vdpa_get_vq_ready,
+	.set_vq_num	= eni_vdpa_set_vq_num,
+	.set_vq_address	= eni_vdpa_set_vq_address,
+	.kick_vq	= eni_vdpa_kick_vq,
+	.get_device_id	= eni_vdpa_get_device_id,
+	.get_vendor_id	= eni_vdpa_get_vendor_id,
+	.get_vq_align	= eni_vdpa_get_vq_align,
+	.get_config_size = eni_vdpa_get_config_size,
+	.get_config	= eni_vdpa_get_config,
+	.set_config	= eni_vdpa_set_config,
+	.set_config_cb  = eni_vdpa_set_config_cb,
+	.get_vq_irq	= eni_vdpa_get_vq_irq,
+};
+
+
+static u16 eni_vdpa_get_num_queues(struct eni_vdpa *eni_vdpa)
+{
+	struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+	u32 features = vp_legacy_get_features(ldev);
+	u16 num = 2;
+
+	if (features & BIT_ULL(VIRTIO_NET_F_MQ)) {
+		__virtio16 max_virtqueue_pairs;
+
+		eni_vdpa_get_config(&eni_vdpa->vdpa,
+			offsetof(struct virtio_net_config, max_virtqueue_pairs),
+			&max_virtqueue_pairs,
+			sizeof(max_virtqueue_pairs));
+		num = 2 * __virtio16_to_cpu(virtio_legacy_is_little_endian(),
+				max_virtqueue_pairs);
+	}
+
+	if (features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))
+		num += 1;
+
+	return num;
+}
+
+static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct device *dev = &pdev->dev;
+	struct eni_vdpa *eni_vdpa;
+	struct virtio_pci_legacy_device *ldev;
+	int ret, i;
+
+	ret = pcim_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	eni_vdpa = vdpa_alloc_device(struct eni_vdpa, vdpa,
+				     dev, &eni_vdpa_ops, 1, 1, NULL, false);
+	if (IS_ERR(eni_vdpa)) {
+		ENI_ERR(pdev, "failed to allocate vDPA structure\n");
+		return PTR_ERR(eni_vdpa);
+	}
+
+	ldev = &eni_vdpa->ldev;
+	ldev->pci_dev = pdev;
+
+	ret = vp_legacy_probe(ldev);
+	if (ret) {
+		ENI_ERR(pdev, "failed to probe legacy PCI device\n");
+		goto err;
+	}
+
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, eni_vdpa);
+
+	eni_vdpa->vdpa.dma_dev = &pdev->dev;
+	eni_vdpa->queues = eni_vdpa_get_num_queues(eni_vdpa);
+
+	eni_vdpa->vring = devm_kcalloc(&pdev->dev, eni_vdpa->queues,
+				      sizeof(*eni_vdpa->vring),
+				      GFP_KERNEL);
+	if (!eni_vdpa->vring) {
+		ret = -ENOMEM;
+		ENI_ERR(pdev, "failed to allocate virtqueues\n");
+		goto err;
+	}
+
+	for (i = 0; i < eni_vdpa->queues; i++) {
+		eni_vdpa->vring[i].irq = VIRTIO_MSI_NO_VECTOR;
+		eni_vdpa->vring[i].notify = ldev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
+	}
+	eni_vdpa->config_irq = VIRTIO_MSI_NO_VECTOR;
+
+	ret = vdpa_register_device(&eni_vdpa->vdpa, eni_vdpa->queues);
+	if (ret) {
+		ENI_ERR(pdev, "failed to register to vdpa bus\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	put_device(&eni_vdpa->vdpa.dev);
+	return ret;
+}
+
+static void eni_vdpa_remove(struct pci_dev *pdev)
+{
+	struct eni_vdpa *eni_vdpa = pci_get_drvdata(pdev);
+
+	vdpa_unregister_device(&eni_vdpa->vdpa);
+	vp_legacy_remove(&eni_vdpa->ldev);
+}
+
+static struct pci_device_id eni_pci_ids[] = {
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_REDHAT_QUMRANET,
+			 VIRTIO_TRANS_ID_NET,
+			 PCI_SUBVENDOR_ID_REDHAT_QUMRANET,
+			 VIRTIO_ID_NET) },
+	{ 0 },
+};
+
+static struct pci_driver eni_vdpa_driver = {
+	.name		= "alibaba-eni-vdpa",
+	.id_table	= eni_pci_ids,
+	.probe		= eni_vdpa_probe,
+	.remove		= eni_vdpa_remove,
+};
+
+module_pci_driver(eni_vdpa_driver);
+
+MODULE_AUTHOR("Wu Zongyong <wuzongyong@linux.alibaba.com>");
+MODULE_DESCRIPTION("Alibaba ENI vDPA driver");
+MODULE_LICENSE("GPL v2");