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, 946 insertions, 0 deletions

diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
new file mode 100644
index 000000000..44b29289a
--- /dev/null
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -0,0 +1,946 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel IFC VF NIC driver for virtio dataplane offloading
+ *
+ * Copyright (C) 2020 Intel Corporation.
+ *
+ * Author: Zhu Lingshan <lingshan.zhu@intel.com>
+ *
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/sysfs.h>
+#include "ifcvf_base.h"
+
+#define DRIVER_AUTHOR   "Intel Corporation"
+#define IFCVF_DRIVER_NAME       "ifcvf"
+
+static irqreturn_t ifcvf_config_changed(int irq, void *arg)
+{
+	struct ifcvf_hw *vf = arg;
+
+	if (vf->config_cb.callback)
+		return vf->config_cb.callback(vf->config_cb.private);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ifcvf_vq_intr_handler(int irq, void *arg)
+{
+	struct vring_info *vring = arg;
+
+	if (vring->cb.callback)
+		return vring->cb.callback(vring->cb.private);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ifcvf_vqs_reused_intr_handler(int irq, void *arg)
+{
+	struct ifcvf_hw *vf = arg;
+	struct vring_info *vring;
+	int i;
+
+	for (i = 0; i < vf->nr_vring; i++) {
+		vring = &vf->vring[i];
+		if (vring->cb.callback)
+			vring->cb.callback(vring->cb.private);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ifcvf_dev_intr_handler(int irq, void *arg)
+{
+	struct ifcvf_hw *vf = arg;
+	u8 isr;
+
+	isr = vp_ioread8(vf->isr);
+	if (isr & VIRTIO_PCI_ISR_CONFIG)
+		ifcvf_config_changed(irq, arg);
+
+	return ifcvf_vqs_reused_intr_handler(irq, arg);
+}
+
+static void ifcvf_free_irq_vectors(void *data)
+{
+	pci_free_irq_vectors(data);
+}
+
+static void ifcvf_free_per_vq_irq(struct ifcvf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ifcvf_hw *vf = &adapter->vf;
+	int i;
+
+	for (i = 0; i < vf->nr_vring; i++) {
+		if (vf->vring[i].irq != -EINVAL) {
+			devm_free_irq(&pdev->dev, vf->vring[i].irq, &vf->vring[i]);
+			vf->vring[i].irq = -EINVAL;
+		}
+	}
+}
+
+static void ifcvf_free_vqs_reused_irq(struct ifcvf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ifcvf_hw *vf = &adapter->vf;
+
+	if (vf->vqs_reused_irq != -EINVAL) {
+		devm_free_irq(&pdev->dev, vf->vqs_reused_irq, vf);
+		vf->vqs_reused_irq = -EINVAL;
+	}
+
+}
+
+static void ifcvf_free_vq_irq(struct ifcvf_adapter *adapter)
+{
+	struct ifcvf_hw *vf = &adapter->vf;
+
+	if (vf->msix_vector_status == MSIX_VECTOR_PER_VQ_AND_CONFIG)
+		ifcvf_free_per_vq_irq(adapter);
+	else
+		ifcvf_free_vqs_reused_irq(adapter);
+}
+
+static void ifcvf_free_config_irq(struct ifcvf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ifcvf_hw *vf = &adapter->vf;
+
+	if (vf->config_irq == -EINVAL)
+		return;
+
+	/* If the irq is shared by all vqs and the config interrupt,
+	 * it is already freed in ifcvf_free_vq_irq, so here only
+	 * need to free config irq when msix_vector_status != MSIX_VECTOR_DEV_SHARED
+	 */
+	if (vf->msix_vector_status != MSIX_VECTOR_DEV_SHARED) {
+		devm_free_irq(&pdev->dev, vf->config_irq, vf);
+		vf->config_irq = -EINVAL;
+	}
+}
+
+static void ifcvf_free_irq(struct ifcvf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+
+	ifcvf_free_vq_irq(adapter);
+	ifcvf_free_config_irq(adapter);
+	ifcvf_free_irq_vectors(pdev);
+}
+
+/* ifcvf MSIX vectors allocator, this helper tries to allocate
+ * vectors for all virtqueues and the config interrupt.
+ * It returns the number of allocated vectors, negative
+ * return value when fails.
+ */
+static int ifcvf_alloc_vectors(struct ifcvf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ifcvf_hw *vf = &adapter->vf;
+	int max_intr, ret;
+
+	/* all queues and config interrupt  */
+	max_intr = vf->nr_vring + 1;
+	ret = pci_alloc_irq_vectors(pdev, 1, max_intr, PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
+
+	if (ret < 0) {
+		IFCVF_ERR(pdev, "Failed to alloc IRQ vectors\n");
+		return ret;
+	}
+
+	if (ret < max_intr)
+		IFCVF_INFO(pdev,
+			   "Requested %u vectors, however only %u allocated, lower performance\n",
+			   max_intr, ret);
+
+	return ret;
+}
+
+static int ifcvf_request_per_vq_irq(struct ifcvf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ifcvf_hw *vf = &adapter->vf;
+	int i, vector, ret, irq;
+
+	vf->vqs_reused_irq = -EINVAL;
+	for (i = 0; i < vf->nr_vring; i++) {
+		snprintf(vf->vring[i].msix_name, 256, "ifcvf[%s]-%d\n", pci_name(pdev), i);
+		vector = i;
+		irq = pci_irq_vector(pdev, vector);
+		ret = devm_request_irq(&pdev->dev, irq,
+				       ifcvf_vq_intr_handler, 0,
+				       vf->vring[i].msix_name,
+				       &vf->vring[i]);
+		if (ret) {
+			IFCVF_ERR(pdev, "Failed to request irq for vq %d\n", i);
+			goto err;
+		}
+
+		vf->vring[i].irq = irq;
+		ret = ifcvf_set_vq_vector(vf, i, vector);
+		if (ret == VIRTIO_MSI_NO_VECTOR) {
+			IFCVF_ERR(pdev, "No msix vector for vq %u\n", i);
+			goto err;
+		}
+	}
+
+	return 0;
+err:
+	ifcvf_free_irq(adapter);
+
+	return -EFAULT;
+}
+
+static int ifcvf_request_vqs_reused_irq(struct ifcvf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ifcvf_hw *vf = &adapter->vf;
+	int i, vector, ret, irq;
+
+	vector = 0;
+	snprintf(vf->vring[0].msix_name, 256, "ifcvf[%s]-vqs-reused-irq\n", pci_name(pdev));
+	irq = pci_irq_vector(pdev, vector);
+	ret = devm_request_irq(&pdev->dev, irq,
+			       ifcvf_vqs_reused_intr_handler, 0,
+			       vf->vring[0].msix_name, vf);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to request reused irq for the device\n");
+		goto err;
+	}
+
+	vf->vqs_reused_irq = irq;
+	for (i = 0; i < vf->nr_vring; i++) {
+		vf->vring[i].irq = -EINVAL;
+		ret = ifcvf_set_vq_vector(vf, i, vector);
+		if (ret == VIRTIO_MSI_NO_VECTOR) {
+			IFCVF_ERR(pdev, "No msix vector for vq %u\n", i);
+			goto err;
+		}
+	}
+
+	return 0;
+err:
+	ifcvf_free_irq(adapter);
+
+	return -EFAULT;
+}
+
+static int ifcvf_request_dev_irq(struct ifcvf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ifcvf_hw *vf = &adapter->vf;
+	int i, vector, ret, irq;
+
+	vector = 0;
+	snprintf(vf->vring[0].msix_name, 256, "ifcvf[%s]-dev-irq\n", pci_name(pdev));
+	irq = pci_irq_vector(pdev, vector);
+	ret = devm_request_irq(&pdev->dev, irq,
+			       ifcvf_dev_intr_handler, 0,
+			       vf->vring[0].msix_name, vf);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to request irq for the device\n");
+		goto err;
+	}
+
+	vf->vqs_reused_irq = irq;
+	for (i = 0; i < vf->nr_vring; i++) {
+		vf->vring[i].irq = -EINVAL;
+		ret = ifcvf_set_vq_vector(vf, i, vector);
+		if (ret == VIRTIO_MSI_NO_VECTOR) {
+			IFCVF_ERR(pdev, "No msix vector for vq %u\n", i);
+			goto err;
+		}
+	}
+
+	vf->config_irq = irq;
+	ret = ifcvf_set_config_vector(vf, vector);
+	if (ret == VIRTIO_MSI_NO_VECTOR) {
+		IFCVF_ERR(pdev, "No msix vector for device config\n");
+		goto err;
+	}
+
+	return 0;
+err:
+	ifcvf_free_irq(adapter);
+
+	return -EFAULT;
+
+}
+
+static int ifcvf_request_vq_irq(struct ifcvf_adapter *adapter)
+{
+	struct ifcvf_hw *vf = &adapter->vf;
+	int ret;
+
+	if (vf->msix_vector_status == MSIX_VECTOR_PER_VQ_AND_CONFIG)
+		ret = ifcvf_request_per_vq_irq(adapter);
+	else
+		ret = ifcvf_request_vqs_reused_irq(adapter);
+
+	return ret;
+}
+
+static int ifcvf_request_config_irq(struct ifcvf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ifcvf_hw *vf = &adapter->vf;
+	int config_vector, ret;
+
+	if (vf->msix_vector_status == MSIX_VECTOR_PER_VQ_AND_CONFIG)
+		config_vector = vf->nr_vring;
+	else if (vf->msix_vector_status ==  MSIX_VECTOR_SHARED_VQ_AND_CONFIG)
+		/* vector 0 for vqs and 1 for config interrupt */
+		config_vector = 1;
+	else if (vf->msix_vector_status == MSIX_VECTOR_DEV_SHARED)
+		/* re-use the vqs vector */
+		return 0;
+	else
+		return -EINVAL;
+
+	snprintf(vf->config_msix_name, 256, "ifcvf[%s]-config\n",
+		 pci_name(pdev));
+	vf->config_irq = pci_irq_vector(pdev, config_vector);
+	ret = devm_request_irq(&pdev->dev, vf->config_irq,
+			       ifcvf_config_changed, 0,
+			       vf->config_msix_name, vf);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to request config irq\n");
+		goto err;
+	}
+
+	ret = ifcvf_set_config_vector(vf, config_vector);
+	if (ret == VIRTIO_MSI_NO_VECTOR) {
+		IFCVF_ERR(pdev, "No msix vector for device config\n");
+		goto err;
+	}
+
+	return 0;
+err:
+	ifcvf_free_irq(adapter);
+
+	return -EFAULT;
+}
+
+static int ifcvf_request_irq(struct ifcvf_adapter *adapter)
+{
+	struct ifcvf_hw *vf = &adapter->vf;
+	int nvectors, ret, max_intr;
+
+	nvectors = ifcvf_alloc_vectors(adapter);
+	if (nvectors <= 0)
+		return -EFAULT;
+
+	vf->msix_vector_status = MSIX_VECTOR_PER_VQ_AND_CONFIG;
+	max_intr = vf->nr_vring + 1;
+	if (nvectors < max_intr)
+		vf->msix_vector_status = MSIX_VECTOR_SHARED_VQ_AND_CONFIG;
+
+	if (nvectors == 1) {
+		vf->msix_vector_status = MSIX_VECTOR_DEV_SHARED;
+		ret = ifcvf_request_dev_irq(adapter);
+
+		return ret;
+	}
+
+	ret = ifcvf_request_vq_irq(adapter);
+	if (ret)
+		return ret;
+
+	ret = ifcvf_request_config_irq(adapter);
+
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int ifcvf_start_datapath(void *private)
+{
+	struct ifcvf_hw *vf = ifcvf_private_to_vf(private);
+	u8 status;
+	int ret;
+
+	ret = ifcvf_start_hw(vf);
+	if (ret < 0) {
+		status = ifcvf_get_status(vf);
+		status |= VIRTIO_CONFIG_S_FAILED;
+		ifcvf_set_status(vf, status);
+	}
+
+	return ret;
+}
+
+static int ifcvf_stop_datapath(void *private)
+{
+	struct ifcvf_hw *vf = ifcvf_private_to_vf(private);
+	int i;
+
+	for (i = 0; i < vf->nr_vring; i++)
+		vf->vring[i].cb.callback = NULL;
+
+	ifcvf_stop_hw(vf);
+
+	return 0;
+}
+
+static void ifcvf_reset_vring(struct ifcvf_adapter *adapter)
+{
+	struct ifcvf_hw *vf = ifcvf_private_to_vf(adapter);
+	int i;
+
+	for (i = 0; i < vf->nr_vring; i++) {
+		vf->vring[i].last_avail_idx = 0;
+		vf->vring[i].desc = 0;
+		vf->vring[i].avail = 0;
+		vf->vring[i].used = 0;
+		vf->vring[i].ready = 0;
+		vf->vring[i].cb.callback = NULL;
+		vf->vring[i].cb.private = NULL;
+	}
+
+	ifcvf_reset(vf);
+}
+
+static struct ifcvf_adapter *vdpa_to_adapter(struct vdpa_device *vdpa_dev)
+{
+	return container_of(vdpa_dev, struct ifcvf_adapter, vdpa);
+}
+
+static struct ifcvf_hw *vdpa_to_vf(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev);
+
+	return &adapter->vf;
+}
+
+static u64 ifcvf_vdpa_get_device_features(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev);
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+	struct pci_dev *pdev = adapter->pdev;
+	u32 type = vf->dev_type;
+	u64 features;
+
+	if (type == VIRTIO_ID_NET || type == VIRTIO_ID_BLOCK)
+		features = ifcvf_get_features(vf);
+	else {
+		features = 0;
+		IFCVF_ERR(pdev, "VIRTIO ID %u not supported\n", vf->dev_type);
+	}
+
+	return features;
+}
+
+static int ifcvf_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 features)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+	int ret;
+
+	ret = ifcvf_verify_min_features(vf, features);
+	if (ret)
+		return ret;
+
+	vf->req_features = features;
+
+	return 0;
+}
+
+static u64 ifcvf_vdpa_get_driver_features(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return vf->req_features;
+}
+
+static u8 ifcvf_vdpa_get_status(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return ifcvf_get_status(vf);
+}
+
+static void ifcvf_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
+{
+	struct ifcvf_adapter *adapter;
+	struct ifcvf_hw *vf;
+	u8 status_old;
+	int ret;
+
+	vf  = vdpa_to_vf(vdpa_dev);
+	adapter = vdpa_to_adapter(vdpa_dev);
+	status_old = ifcvf_get_status(vf);
+
+	if (status_old == status)
+		return;
+
+	if ((status & VIRTIO_CONFIG_S_DRIVER_OK) &&
+	    !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) {
+		ret = ifcvf_request_irq(adapter);
+		if (ret) {
+			status = ifcvf_get_status(vf);
+			status |= VIRTIO_CONFIG_S_FAILED;
+			ifcvf_set_status(vf, status);
+			return;
+		}
+
+		if (ifcvf_start_datapath(adapter) < 0)
+			IFCVF_ERR(adapter->pdev,
+				  "Failed to set ifcvf vdpa  status %u\n",
+				  status);
+	}
+
+	ifcvf_set_status(vf, status);
+}
+
+static int ifcvf_vdpa_reset(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_adapter *adapter;
+	struct ifcvf_hw *vf;
+	u8 status_old;
+
+	vf  = vdpa_to_vf(vdpa_dev);
+	adapter = vdpa_to_adapter(vdpa_dev);
+	status_old = ifcvf_get_status(vf);
+
+	if (status_old == 0)
+		return 0;
+
+	if (status_old & VIRTIO_CONFIG_S_DRIVER_OK) {
+		ifcvf_stop_datapath(adapter);
+		ifcvf_free_irq(adapter);
+	}
+
+	ifcvf_reset_vring(adapter);
+
+	return 0;
+}
+
+static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev)
+{
+	return IFCVF_QUEUE_MAX;
+}
+
+static int ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
+				   struct vdpa_vq_state *state)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	state->split.avail_index = ifcvf_get_vq_state(vf, qid);
+	return 0;
+}
+
+static int ifcvf_vdpa_set_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
+				   const struct vdpa_vq_state *state)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return ifcvf_set_vq_state(vf, qid, state->split.avail_index);
+}
+
+static void ifcvf_vdpa_set_vq_cb(struct vdpa_device *vdpa_dev, u16 qid,
+				 struct vdpa_callback *cb)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	vf->vring[qid].cb = *cb;
+}
+
+static void ifcvf_vdpa_set_vq_ready(struct vdpa_device *vdpa_dev,
+				    u16 qid, bool ready)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	vf->vring[qid].ready = ready;
+}
+
+static bool ifcvf_vdpa_get_vq_ready(struct vdpa_device *vdpa_dev, u16 qid)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return vf->vring[qid].ready;
+}
+
+static void ifcvf_vdpa_set_vq_num(struct vdpa_device *vdpa_dev, u16 qid,
+				  u32 num)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	vf->vring[qid].size = num;
+}
+
+static int ifcvf_vdpa_set_vq_address(struct vdpa_device *vdpa_dev, u16 qid,
+				     u64 desc_area, u64 driver_area,
+				     u64 device_area)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	vf->vring[qid].desc = desc_area;
+	vf->vring[qid].avail = driver_area;
+	vf->vring[qid].used = device_area;
+
+	return 0;
+}
+
+static void ifcvf_vdpa_kick_vq(struct vdpa_device *vdpa_dev, u16 qid)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	ifcvf_notify_queue(vf, qid);
+}
+
+static u32 ifcvf_vdpa_get_generation(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return vp_ioread8(&vf->common_cfg->config_generation);
+}
+
+static u32 ifcvf_vdpa_get_device_id(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return vf->dev_type;
+}
+
+static u32 ifcvf_vdpa_get_vendor_id(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev);
+	struct pci_dev *pdev = adapter->pdev;
+
+	return pdev->subsystem_vendor;
+}
+
+static u32 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev)
+{
+	return IFCVF_QUEUE_ALIGNMENT;
+}
+
+static size_t ifcvf_vdpa_get_config_size(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return  vf->config_size;
+}
+
+static u32 ifcvf_vdpa_get_vq_group(struct vdpa_device *vdpa, u16 idx)
+{
+	return 0;
+}
+
+static void ifcvf_vdpa_get_config(struct vdpa_device *vdpa_dev,
+				  unsigned int offset,
+				  void *buf, unsigned int len)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	ifcvf_read_dev_config(vf, offset, buf, len);
+}
+
+static void ifcvf_vdpa_set_config(struct vdpa_device *vdpa_dev,
+				  unsigned int offset, const void *buf,
+				  unsigned int len)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	ifcvf_write_dev_config(vf, offset, buf, len);
+}
+
+static void ifcvf_vdpa_set_config_cb(struct vdpa_device *vdpa_dev,
+				     struct vdpa_callback *cb)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	vf->config_cb.callback = cb->callback;
+	vf->config_cb.private = cb->private;
+}
+
+static int ifcvf_vdpa_get_vq_irq(struct vdpa_device *vdpa_dev,
+				 u16 qid)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	if (vf->vqs_reused_irq < 0)
+		return vf->vring[qid].irq;
+	else
+		return -EINVAL;
+}
+
+static struct vdpa_notification_area ifcvf_get_vq_notification(struct vdpa_device *vdpa_dev,
+							       u16 idx)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+	struct vdpa_notification_area area;
+
+	area.addr = vf->vring[idx].notify_pa;
+	if (!vf->notify_off_multiplier)
+		area.size = PAGE_SIZE;
+	else
+		area.size = vf->notify_off_multiplier;
+
+	return area;
+}
+
+/*
+ * IFCVF currently doesn't have on-chip IOMMU, so not
+ * implemented set_map()/dma_map()/dma_unmap()
+ */
+static const struct vdpa_config_ops ifc_vdpa_ops = {
+	.get_device_features = ifcvf_vdpa_get_device_features,
+	.set_driver_features = ifcvf_vdpa_set_driver_features,
+	.get_driver_features = ifcvf_vdpa_get_driver_features,
+	.get_status	= ifcvf_vdpa_get_status,
+	.set_status	= ifcvf_vdpa_set_status,
+	.reset		= ifcvf_vdpa_reset,
+	.get_vq_num_max	= ifcvf_vdpa_get_vq_num_max,
+	.get_vq_state	= ifcvf_vdpa_get_vq_state,
+	.set_vq_state	= ifcvf_vdpa_set_vq_state,
+	.set_vq_cb	= ifcvf_vdpa_set_vq_cb,
+	.set_vq_ready	= ifcvf_vdpa_set_vq_ready,
+	.get_vq_ready	= ifcvf_vdpa_get_vq_ready,
+	.set_vq_num	= ifcvf_vdpa_set_vq_num,
+	.set_vq_address	= ifcvf_vdpa_set_vq_address,
+	.get_vq_irq	= ifcvf_vdpa_get_vq_irq,
+	.kick_vq	= ifcvf_vdpa_kick_vq,
+	.get_generation	= ifcvf_vdpa_get_generation,
+	.get_device_id	= ifcvf_vdpa_get_device_id,
+	.get_vendor_id	= ifcvf_vdpa_get_vendor_id,
+	.get_vq_align	= ifcvf_vdpa_get_vq_align,
+	.get_vq_group	= ifcvf_vdpa_get_vq_group,
+	.get_config_size	= ifcvf_vdpa_get_config_size,
+	.get_config	= ifcvf_vdpa_get_config,
+	.set_config	= ifcvf_vdpa_set_config,
+	.set_config_cb  = ifcvf_vdpa_set_config_cb,
+	.get_vq_notification = ifcvf_get_vq_notification,
+};
+
+static struct virtio_device_id id_table_net[] = {
+	{VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID},
+	{0},
+};
+
+static struct virtio_device_id id_table_blk[] = {
+	{VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID},
+	{0},
+};
+
+static u32 get_dev_type(struct pci_dev *pdev)
+{
+	u32 dev_type;
+
+	/* This drirver drives both modern virtio devices and transitional
+	 * devices in modern mode.
+	 * vDPA requires feature bit VIRTIO_F_ACCESS_PLATFORM,
+	 * so legacy devices and transitional devices in legacy
+	 * mode will not work for vDPA, this driver will not
+	 * drive devices with legacy interface.
+	 */
+
+	if (pdev->device < 0x1040)
+		dev_type =  pdev->subsystem_device;
+	else
+		dev_type =  pdev->device - 0x1040;
+
+	return dev_type;
+}
+
+static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
+			      const struct vdpa_dev_set_config *config)
+{
+	struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev;
+	struct ifcvf_adapter *adapter;
+	struct vdpa_device *vdpa_dev;
+	struct pci_dev *pdev;
+	struct ifcvf_hw *vf;
+	int ret;
+
+	ifcvf_mgmt_dev = container_of(mdev, struct ifcvf_vdpa_mgmt_dev, mdev);
+	if (!ifcvf_mgmt_dev->adapter)
+		return -EOPNOTSUPP;
+
+	adapter = ifcvf_mgmt_dev->adapter;
+	vf = &adapter->vf;
+	pdev = adapter->pdev;
+	vdpa_dev = &adapter->vdpa;
+
+	if (name)
+		ret = dev_set_name(&vdpa_dev->dev, "%s", name);
+	else
+		ret = dev_set_name(&vdpa_dev->dev, "vdpa%u", vdpa_dev->index);
+
+	ret = _vdpa_register_device(&adapter->vdpa, vf->nr_vring);
+	if (ret) {
+		put_device(&adapter->vdpa.dev);
+		IFCVF_ERR(pdev, "Failed to register to vDPA bus");
+		return ret;
+	}
+
+	return 0;
+}
+
+
+static void ifcvf_vdpa_dev_del(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev)
+{
+	struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev;
+
+	ifcvf_mgmt_dev = container_of(mdev, struct ifcvf_vdpa_mgmt_dev, mdev);
+	_vdpa_unregister_device(dev);
+	ifcvf_mgmt_dev->adapter = NULL;
+}
+
+static const struct vdpa_mgmtdev_ops ifcvf_vdpa_mgmt_dev_ops = {
+	.dev_add = ifcvf_vdpa_dev_add,
+	.dev_del = ifcvf_vdpa_dev_del
+};
+
+static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev;
+	struct device *dev = &pdev->dev;
+	struct ifcvf_adapter *adapter;
+	struct ifcvf_hw *vf;
+	u32 dev_type;
+	int ret, i;
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to enable device\n");
+		return ret;
+	}
+	ret = pcim_iomap_regions(pdev, BIT(0) | BIT(2) | BIT(4),
+				 IFCVF_DRIVER_NAME);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to request MMIO region\n");
+		return ret;
+	}
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	if (ret) {
+		IFCVF_ERR(pdev, "No usable DMA configuration\n");
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(dev, ifcvf_free_irq_vectors, pdev);
+	if (ret) {
+		IFCVF_ERR(pdev,
+			  "Failed for adding devres for freeing irq vectors\n");
+		return ret;
+	}
+
+	pci_set_master(pdev);
+
+	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
+				    dev, &ifc_vdpa_ops, 1, 1, NULL, false);
+	if (IS_ERR(adapter)) {
+		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
+		return PTR_ERR(adapter);
+	}
+
+	vf = &adapter->vf;
+	vf->dev_type = get_dev_type(pdev);
+	vf->base = pcim_iomap_table(pdev);
+
+	adapter->pdev = pdev;
+	adapter->vdpa.dma_dev = &pdev->dev;
+
+	ret = ifcvf_init_hw(vf, pdev);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to init IFCVF hw\n");
+		goto err;
+	}
+
+	for (i = 0; i < vf->nr_vring; i++)
+		vf->vring[i].irq = -EINVAL;
+
+	vf->hw_features = ifcvf_get_hw_features(vf);
+	vf->config_size = ifcvf_get_config_size(vf);
+
+	ifcvf_mgmt_dev = kzalloc(sizeof(struct ifcvf_vdpa_mgmt_dev), GFP_KERNEL);
+	if (!ifcvf_mgmt_dev) {
+		IFCVF_ERR(pdev, "Failed to alloc memory for the vDPA management device\n");
+		return -ENOMEM;
+	}
+
+	ifcvf_mgmt_dev->mdev.ops = &ifcvf_vdpa_mgmt_dev_ops;
+	ifcvf_mgmt_dev->mdev.device = dev;
+	ifcvf_mgmt_dev->adapter = adapter;
+
+	dev_type = get_dev_type(pdev);
+	switch (dev_type) {
+	case VIRTIO_ID_NET:
+		ifcvf_mgmt_dev->mdev.id_table = id_table_net;
+		break;
+	case VIRTIO_ID_BLOCK:
+		ifcvf_mgmt_dev->mdev.id_table = id_table_blk;
+		break;
+	default:
+		IFCVF_ERR(pdev, "VIRTIO ID %u not supported\n", dev_type);
+		ret = -EOPNOTSUPP;
+		goto err;
+	}
+
+	ifcvf_mgmt_dev->mdev.max_supported_vqs = vf->nr_vring;
+	ifcvf_mgmt_dev->mdev.supported_features = vf->hw_features;
+
+	adapter->vdpa.mdev = &ifcvf_mgmt_dev->mdev;
+
+
+	ret = vdpa_mgmtdev_register(&ifcvf_mgmt_dev->mdev);
+	if (ret) {
+		IFCVF_ERR(pdev,
+			  "Failed to initialize the management interfaces\n");
+		goto err;
+	}
+
+	pci_set_drvdata(pdev, ifcvf_mgmt_dev);
+
+	return 0;
+
+err:
+	kfree(ifcvf_mgmt_dev);
+	return ret;
+}
+
+static void ifcvf_remove(struct pci_dev *pdev)
+{
+	struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev;
+
+	ifcvf_mgmt_dev = pci_get_drvdata(pdev);
+	vdpa_mgmtdev_unregister(&ifcvf_mgmt_dev->mdev);
+	kfree(ifcvf_mgmt_dev);
+}
+
+static struct pci_device_id ifcvf_pci_ids[] = {
+	/* N3000 network device */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_REDHAT_QUMRANET,
+			 N3000_DEVICE_ID,
+			 PCI_VENDOR_ID_INTEL,
+			 N3000_SUBSYS_DEVICE_ID) },
+	/* C5000X-PL network device */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_REDHAT_QUMRANET,
+			 VIRTIO_TRANS_ID_NET,
+			 PCI_VENDOR_ID_INTEL,
+			 VIRTIO_ID_NET) },
+	/* C5000X-PL block device */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_REDHAT_QUMRANET,
+			 VIRTIO_TRANS_ID_BLOCK,
+			 PCI_VENDOR_ID_INTEL,
+			 VIRTIO_ID_BLOCK) },
+
+	{ 0 },
+};
+MODULE_DEVICE_TABLE(pci, ifcvf_pci_ids);
+
+static struct pci_driver ifcvf_driver = {
+	.name     = IFCVF_DRIVER_NAME,
+	.id_table = ifcvf_pci_ids,
+	.probe    = ifcvf_probe,
+	.remove   = ifcvf_remove,
+};
+
+module_pci_driver(ifcvf_driver);
+
+MODULE_LICENSE("GPL v2");