Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:

 - vdpa sim refactoring

 - virtio mem: Big Block Mode support

 - misc cleanus, fixes

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (61 commits)
  vdpa: Use simpler version of ida allocation
  vdpa: Add missing comment for virtqueue count
  uapi: virtio_ids: add missing device type IDs from OASIS spec
  uapi: virtio_ids.h: consistent indentions
  vhost scsi: fix error return code in vhost_scsi_set_endpoint()
  virtio_ring: Fix two use after free bugs
  virtio_net: Fix error code in probe()
  virtio_ring: Cut and paste bugs in vring_create_virtqueue_packed()
  tools/virtio: add barrier for aarch64
  tools/virtio: add krealloc_array
  tools/virtio: include asm/bug.h
  vdpa/mlx5: Use write memory barrier after updating CQ index
  vdpa: split vdpasim to core and net modules
  vdpa_sim: split vdpasim_virtqueue's iov field in out_iov and in_iov
  vdpa_sim: make vdpasim->buffer size configurable
  vdpa_sim: use kvmalloc to allocate vdpasim->buffer
  vdpa_sim: set vringh notify callback
  vdpa_sim: add set_config callback in vdpasim_dev_attr
  vdpa_sim: add get_config callback in vdpasim_dev_attr
  vdpa_sim: make 'config' generic and usable for any device type
  ...

8 files changed, 382 insertions, 233 deletions

diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index 6caf539091e5..92a6396f8a73 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -9,21 +9,24 @@ menuconfig VDPA
 if VDPA
 
 config VDPA_SIM
-	tristate "vDPA device simulator"
+	tristate "vDPA device simulator core"
 	depends on RUNTIME_TESTING_MENU && HAS_DMA
 	select DMA_OPS
 	select VHOST_RING
+	help
+	  Enable this module to support vDPA device simulators. These devices
+	  are used for testing, prototyping and development of vDPA.
+
+config VDPA_SIM_NET
+	tristate "vDPA simulator for networking device"
+	depends on VDPA_SIM
 	select GENERIC_NET_UTILS
-	default n
 	help
-	  vDPA networking device simulator which loop TX traffic back
-	  to RX. This device is used for testing, prototyping and
-	  development of vDPA.
+	  vDPA networking device simulator which loops TX traffic back to RX.
 
 config IFCVF
 	tristate "Intel IFC VF vDPA driver"
 	depends on PCI_MSI
-	default n
 	help
 	  This kernel module can drive Intel IFC VF NIC to offload
 	  virtio dataplane traffic to hardware.
@@ -42,7 +45,6 @@ config MLX5_VDPA_NET
 	tristate "vDPA driver for ConnectX devices"
 	select MLX5_VDPA
 	depends on MLX5_CORE
-	default n
 	help
 	  VDPA network driver for ConnectX6 and newer. Provides offloading
 	  of virtio net datapath such that descriptors put on the ring will
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 8b4028556cb6..fa1af301cf55 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -417,16 +417,9 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ret;
 	}
 
-	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (ret) {
-		IFCVF_ERR(pdev, "No usable DMA confiugration\n");
-		return ret;
-	}
-
-	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (ret) {
-		IFCVF_ERR(pdev,
-			  "No usable coherent DMA confiugration\n");
+		IFCVF_ERR(pdev, "No usable DMA configuration\n");
 		return ret;
 	}
 
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index f1d54814db97..88dde3455bfd 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -479,6 +479,11 @@ static int mlx5_vdpa_poll_one(struct mlx5_vdpa_cq *vcq)
 static void mlx5_vdpa_handle_completions(struct mlx5_vdpa_virtqueue *mvq, int num)
 {
 	mlx5_cq_set_ci(&mvq->cq.mcq);
+
+	/* make sure CQ cosumer update is visible to the hardware before updating
+	 * RX doorbell record.
+	 */
+	dma_wmb();
 	rx_post(&mvq->vqqp, num);
 	if (mvq->event_cb.callback)
 		mvq->event_cb.callback(mvq->event_cb.private);
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index a69ffc991e13..c0825650c055 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -89,7 +89,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	if (!vdev)
 		goto err;
 
-	err = ida_simple_get(&vdpa_index_ida, 0, 0, GFP_KERNEL);
+	err = ida_alloc(&vdpa_index_ida, GFP_KERNEL);
 	if (err < 0)
 		goto err_ida;
 
diff --git a/drivers/vdpa/vdpa_sim/Makefile b/drivers/vdpa/vdpa_sim/Makefile
index b40278f65e04..79d4536d347e 100644
--- a/drivers/vdpa/vdpa_sim/Makefile
+++ b/drivers/vdpa/vdpa_sim/Makefile
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_VDPA_SIM) += vdpa_sim.o
+obj-$(CONFIG_VDPA_SIM_NET) += vdpa_sim_net.o
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 6a90fdb9cbfc..b3fcc67bfdf0 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * VDPA networking device simulator.
+ * VDPA device simulator core.
  *
  * Copyright (c) 2020, Red Hat Inc. All rights reserved.
  *     Author: Jason Wang <jasowang@redhat.com>
@@ -11,97 +11,32 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
-#include <linux/fs.h>
-#include <linux/poll.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
-#include <linux/wait.h>
-#include <linux/uuid.h>
-#include <linux/iommu.h>
 #include <linux/dma-map-ops.h>
-#include <linux/sysfs.h>
-#include <linux/file.h>
-#include <linux/etherdevice.h>
 #include <linux/vringh.h>
 #include <linux/vdpa.h>
-#include <linux/virtio_byteorder.h>
 #include <linux/vhost_iotlb.h>
-#include <uapi/linux/virtio_config.h>
-#include <uapi/linux/virtio_net.h>
+
+#include "vdpa_sim.h"
 
 #define DRV_VERSION  "0.1"
 #define DRV_AUTHOR   "Jason Wang <jasowang@redhat.com>"
-#define DRV_DESC     "vDPA Device Simulator"
+#define DRV_DESC     "vDPA Device Simulator core"
 #define DRV_LICENSE  "GPL v2"
 
 static int batch_mapping = 1;
 module_param(batch_mapping, int, 0444);
 MODULE_PARM_DESC(batch_mapping, "Batched mapping 1 -Enable; 0 - Disable");
 
-static char *macaddr;
-module_param(macaddr, charp, 0);
-MODULE_PARM_DESC(macaddr, "Ethernet MAC address");
-
-struct vdpasim_virtqueue {
-	struct vringh vring;
-	struct vringh_kiov iov;
-	unsigned short head;
-	bool ready;
-	u64 desc_addr;
-	u64 device_addr;
-	u64 driver_addr;
-	u32 num;
-	void *private;
-	irqreturn_t (*cb)(void *data);
-};
+static int max_iotlb_entries = 2048;
+module_param(max_iotlb_entries, int, 0444);
+MODULE_PARM_DESC(max_iotlb_entries,
+		 "Maximum number of iotlb entries. 0 means unlimited. (default: 2048)");
 
 #define VDPASIM_QUEUE_ALIGN PAGE_SIZE
 #define VDPASIM_QUEUE_MAX 256
-#define VDPASIM_DEVICE_ID 0x1
 #define VDPASIM_VENDOR_ID 0
-#define VDPASIM_VQ_NUM 0x2
-#define VDPASIM_NAME "vdpasim-netdev"
-
-static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) |
-			      (1ULL << VIRTIO_F_VERSION_1)  |
-			      (1ULL << VIRTIO_F_ACCESS_PLATFORM) |
-			      (1ULL << VIRTIO_NET_F_MAC);
-
-/* State of each vdpasim device */
-struct vdpasim {
-	struct vdpa_device vdpa;
-	struct vdpasim_virtqueue vqs[VDPASIM_VQ_NUM];
-	struct work_struct work;
-	/* spinlock to synchronize virtqueue state */
-	spinlock_t lock;
-	struct virtio_net_config config;
-	struct vhost_iotlb *iommu;
-	void *buffer;
-	u32 status;
-	u32 generation;
-	u64 features;
-	/* spinlock to synchronize iommu table */
-	spinlock_t iommu_lock;
-};
-
-/* TODO: cross-endian support */
-static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim)
-{
-	return virtio_legacy_is_little_endian() ||
-		(vdpasim->features & (1ULL << VIRTIO_F_VERSION_1));
-}
-
-static inline u16 vdpasim16_to_cpu(struct vdpasim *vdpasim, __virtio16 val)
-{
-	return __virtio16_to_cpu(vdpasim_is_little_endian(vdpasim), val);
-}
-
-static inline __virtio16 cpu_to_vdpasim16(struct vdpasim *vdpasim, u16 val)
-{
-	return __cpu_to_virtio16(vdpasim_is_little_endian(vdpasim), val);
-}
-
-static struct vdpasim *vdpasim_dev;
 
 static struct vdpasim *vdpa_to_sim(struct vdpa_device *vdpa)
 {
@@ -115,20 +50,34 @@ static struct vdpasim *dev_to_sim(struct device *dev)
 	return vdpa_to_sim(vdpa);
 }
 
+static void vdpasim_vq_notify(struct vringh *vring)
+{
+	struct vdpasim_virtqueue *vq =
+		container_of(vring, struct vdpasim_virtqueue, vring);
+
+	if (!vq->cb)
+		return;
+
+	vq->cb(vq->private);
+}
+
 static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx)
 {
 	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
 
-	vringh_init_iotlb(&vq->vring, vdpasim_features,
+	vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features,
 			  VDPASIM_QUEUE_MAX, false,
 			  (struct vring_desc *)(uintptr_t)vq->desc_addr,
 			  (struct vring_avail *)
 			  (uintptr_t)vq->driver_addr,
 			  (struct vring_used *)
 			  (uintptr_t)vq->device_addr);
+
+	vq->vring.notify = vdpasim_vq_notify;
 }
 
-static void vdpasim_vq_reset(struct vdpasim_virtqueue *vq)
+static void vdpasim_vq_reset(struct vdpasim *vdpasim,
+			     struct vdpasim_virtqueue *vq)
 {
 	vq->ready = false;
 	vq->desc_addr = 0;
@@ -136,16 +85,18 @@ static void vdpasim_vq_reset(struct vdpasim_virtqueue *vq)
 	vq->device_addr = 0;
 	vq->cb = NULL;
 	vq->private = NULL;
-	vringh_init_iotlb(&vq->vring, vdpasim_features, VDPASIM_QUEUE_MAX,
-			  false, NULL, NULL, NULL);
+	vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features,
+			  VDPASIM_QUEUE_MAX, false, NULL, NULL, NULL);
+
+	vq->vring.notify = NULL;
 }
 
 static void vdpasim_reset(struct vdpasim *vdpasim)
 {
 	int i;
 
-	for (i = 0; i < VDPASIM_VQ_NUM; i++)
-		vdpasim_vq_reset(&vdpasim->vqs[i]);
+	for (i = 0; i < vdpasim->dev_attr.nvqs; i++)
+		vdpasim_vq_reset(vdpasim, &vdpasim->vqs[i]);
 
 	spin_lock(&vdpasim->iommu_lock);
 	vhost_iotlb_reset(vdpasim->iommu);
@@ -156,80 +107,6 @@ static void vdpasim_reset(struct vdpasim *vdpasim)
 	++vdpasim->generation;
 }
 
-static void vdpasim_work(struct work_struct *work)
-{
-	struct vdpasim *vdpasim = container_of(work, struct
-						 vdpasim, work);
-	struct vdpasim_virtqueue *txq = &vdpasim->vqs[1];
-	struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0];
-	ssize_t read, write;
-	size_t total_write;
-	int pkts = 0;
-	int err;
-
-	spin_lock(&vdpasim->lock);
-
-	if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK))
-		goto out;
-
-	if (!txq->ready || !rxq->ready)
-		goto out;
-
-	while (true) {
-		total_write = 0;
-		err = vringh_getdesc_iotlb(&txq->vring, &txq->iov, NULL,
-					   &txq->head, GFP_ATOMIC);
-		if (err <= 0)
-			break;
-
-		err = vringh_getdesc_iotlb(&rxq->vring, NULL, &rxq->iov,
-					   &rxq->head, GFP_ATOMIC);
-		if (err <= 0) {
-			vringh_complete_iotlb(&txq->vring, txq->head, 0);
-			break;
-		}
-
-		while (true) {
-			read = vringh_iov_pull_iotlb(&txq->vring, &txq->iov,
-						     vdpasim->buffer,
-						     PAGE_SIZE);
-			if (read <= 0)
-				break;
-
-			write = vringh_iov_push_iotlb(&rxq->vring, &rxq->iov,
-						      vdpasim->buffer, read);
-			if (write <= 0)
-				break;
-
-			total_write += write;
-		}
-
-		/* Make sure data is wrote before advancing index */
-		smp_wmb();
-
-		vringh_complete_iotlb(&txq->vring, txq->head, 0);
-		vringh_complete_iotlb(&rxq->vring, rxq->head, total_write);
-
-		/* Make sure used is visible before rasing the interrupt. */
-		smp_wmb();
-
-		local_bh_disable();
-		if (txq->cb)
-			txq->cb(txq->private);
-		if (rxq->cb)
-			rxq->cb(rxq->private);
-		local_bh_enable();
-
-		if (++pkts > 4) {
-			schedule_work(&vdpasim->work);
-			goto out;
-		}
-	}
-
-out:
-	spin_unlock(&vdpasim->lock);
-}
-
 static int dir_to_perm(enum dma_data_direction dir)
 {
 	int perm = -EFAULT;
@@ -342,26 +219,28 @@ static const struct dma_map_ops vdpasim_dma_ops = {
 	.free = vdpasim_free_coherent,
 };
 
-static const struct vdpa_config_ops vdpasim_net_config_ops;
-static const struct vdpa_config_ops vdpasim_net_batch_config_ops;
+static const struct vdpa_config_ops vdpasim_config_ops;
+static const struct vdpa_config_ops vdpasim_batch_config_ops;
 
-static struct vdpasim *vdpasim_create(void)
+struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
 {
 	const struct vdpa_config_ops *ops;
 	struct vdpasim *vdpasim;
 	struct device *dev;
-	int ret = -ENOMEM;
+	int i, ret = -ENOMEM;
 
 	if (batch_mapping)
-		ops = &vdpasim_net_batch_config_ops;
+		ops = &vdpasim_batch_config_ops;
 	else
-		ops = &vdpasim_net_config_ops;
+		ops = &vdpasim_config_ops;
 
-	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, VDPASIM_VQ_NUM);
+	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops,
+				    dev_attr->nvqs);
 	if (!vdpasim)
 		goto err_alloc;
 
-	INIT_WORK(&vdpasim->work, vdpasim_work);
+	vdpasim->dev_attr = *dev_attr;
+	INIT_WORK(&vdpasim->work, dev_attr->work_fn);
 	spin_lock_init(&vdpasim->lock);
 	spin_lock_init(&vdpasim->iommu_lock);
 
@@ -371,31 +250,27 @@ static struct vdpasim *vdpasim_create(void)
 		goto err_iommu;
 	set_dma_ops(dev, &vdpasim_dma_ops);
 
-	vdpasim->iommu = vhost_iotlb_alloc(2048, 0);
+	vdpasim->config = kzalloc(dev_attr->config_size, GFP_KERNEL);
+	if (!vdpasim->config)
+		goto err_iommu;
+
+	vdpasim->vqs = kcalloc(dev_attr->nvqs, sizeof(struct vdpasim_virtqueue),
+			       GFP_KERNEL);
+	if (!vdpasim->vqs)
+		goto err_iommu;
+
+	vdpasim->iommu = vhost_iotlb_alloc(max_iotlb_entries, 0);
 	if (!vdpasim->iommu)
 		goto err_iommu;
 
-	vdpasim->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	vdpasim->buffer = kvmalloc(dev_attr->buffer_size, GFP_KERNEL);
 	if (!vdpasim->buffer)
 		goto err_iommu;
 
-	if (macaddr) {
-		mac_pton(macaddr, vdpasim->config.mac);
-		if (!is_valid_ether_addr(vdpasim->config.mac)) {
-			ret = -EADDRNOTAVAIL;
-			goto err_iommu;
-		}
-	} else {
-		eth_random_addr(vdpasim->config.mac);
-	}
-
-	vringh_set_iotlb(&vdpasim->vqs[0].vring, vdpasim->iommu);
-	vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu);
+	for (i = 0; i < dev_attr->nvqs; i++)
+		vringh_set_iotlb(&vdpasim->vqs[i].vring, vdpasim->iommu);
 
 	vdpasim->vdpa.dma_dev = dev;
-	ret = vdpa_register_device(&vdpasim->vdpa);
-	if (ret)
-		goto err_iommu;
 
 	return vdpasim;
 
@@ -404,6 +279,7 @@ err_iommu:
 err_alloc:
 	return ERR_PTR(ret);
 }
+EXPORT_SYMBOL_GPL(vdpasim_create);
 
 static int vdpasim_set_vq_address(struct vdpa_device *vdpa, u16 idx,
 				  u64 desc_area, u64 driver_area,
@@ -498,28 +374,21 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
 
 static u64 vdpasim_get_features(struct vdpa_device *vdpa)
 {
-	return vdpasim_features;
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	return vdpasim->dev_attr.supported_features;
 }
 
 static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
-	struct virtio_net_config *config = &vdpasim->config;
 
 	/* DMA mapping must be done by driver */
 	if (!(features & (1ULL << VIRTIO_F_ACCESS_PLATFORM)))
 		return -EINVAL;
 
-	vdpasim->features = features & vdpasim_features;
-
-	/* We generally only know whether guest is using the legacy interface
-	 * here, so generally that's the earliest we can set config fields.
-	 * Note: We actually require VIRTIO_F_ACCESS_PLATFORM above which
-	 * implies VIRTIO_F_VERSION_1, but let's not try to be clever here.
-	 */
+	vdpasim->features = features & vdpasim->dev_attr.supported_features;
 
-	config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
-	config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);
 	return 0;
 }
 
@@ -536,7 +405,9 @@ static u16 vdpasim_get_vq_num_max(struct vdpa_device *vdpa)
 
 static u32 vdpasim_get_device_id(struct vdpa_device *vdpa)
 {
-	return VDPASIM_DEVICE_ID;
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	return vdpasim->dev_attr.id;
 }
 
 static u32 vdpasim_get_vendor_id(struct vdpa_device *vdpa)
@@ -572,14 +443,27 @@ static void vdpasim_get_config(struct vdpa_device *vdpa, unsigned int offset,
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
-	if (offset + len < sizeof(struct virtio_net_config))
-		memcpy(buf, (u8 *)&vdpasim->config + offset, len);
+	if (offset + len > vdpasim->dev_attr.config_size)
+		return;
+
+	if (vdpasim->dev_attr.get_config)
+		vdpasim->dev_attr.get_config(vdpasim, vdpasim->config);
+
+	memcpy(buf, vdpasim->config + offset, len);
 }
 
 static void vdpasim_set_config(struct vdpa_device *vdpa, unsigned int offset,
 			     const void *buf, unsigned int len)
 {
-	/* No writable config supportted by vdpasim */
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	if (offset + len > vdpasim->dev_attr.config_size)
+		return;
+
+	memcpy(vdpasim->config + offset, buf, len);
+
+	if (vdpasim->dev_attr.set_config)
+		vdpasim->dev_attr.set_config(vdpasim, vdpasim->config);
 }
 
 static u32 vdpasim_get_generation(struct vdpa_device *vdpa)
@@ -656,12 +540,14 @@ static void vdpasim_free(struct vdpa_device *vdpa)
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
 	cancel_work_sync(&vdpasim->work);
-	kfree(vdpasim->buffer);
+	kvfree(vdpasim->buffer);
 	if (vdpasim->iommu)
 		vhost_iotlb_free(vdpasim->iommu);
+	kfree(vdpasim->vqs);
+	kfree(vdpasim->config);
 }
 
-static const struct vdpa_config_ops vdpasim_net_config_ops = {
+static const struct vdpa_config_ops vdpasim_config_ops = {
 	.set_vq_address         = vdpasim_set_vq_address,
 	.set_vq_num             = vdpasim_set_vq_num,
 	.kick_vq                = vdpasim_kick_vq,
@@ -688,7 +574,7 @@ static const struct vdpa_config_ops vdpasim_net_config_ops = {
 	.free                   = vdpasim_free,
 };
 
-static const struct vdpa_config_ops vdpasim_net_batch_config_ops = {
+static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.set_vq_address         = vdpasim_set_vq_address,
 	.set_vq_num             = vdpasim_set_vq_num,
 	.kick_vq                = vdpasim_kick_vq,
@@ -714,26 +600,6 @@ static const struct vdpa_config_ops vdpasim_net_batch_config_ops = {
 	.free                   = vdpasim_free,
 };
 
-static int __init vdpasim_dev_init(void)
-{
-	vdpasim_dev = vdpasim_create();
-
-	if (!IS_ERR(vdpasim_dev))
-		return 0;
-
-	return PTR_ERR(vdpasim_dev);
-}
-
-static void __exit vdpasim_dev_exit(void)
-{
-	struct vdpa_device *vdpa = &vdpasim_dev->vdpa;
-
-	vdpa_unregister_device(vdpa);
-}
-
-module_init(vdpasim_dev_init)
-module_exit(vdpasim_dev_exit)
-
 MODULE_VERSION(DRV_VERSION);
 MODULE_LICENSE(DRV_LICENSE);
 MODULE_AUTHOR(DRV_AUTHOR);
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h
new file mode 100644
index 000000000000..b02142293d5b
--- /dev/null
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020, Red Hat Inc. All rights reserved.
+ */
+
+#ifndef _VDPA_SIM_H
+#define _VDPA_SIM_H
+
+#include <linux/vringh.h>
+#include <linux/vdpa.h>
+#include <linux/virtio_byteorder.h>
+#include <linux/vhost_iotlb.h>
+#include <uapi/linux/virtio_config.h>
+
+#define VDPASIM_FEATURES	((1ULL << VIRTIO_F_ANY_LAYOUT) | \
+				 (1ULL << VIRTIO_F_VERSION_1)  | \
+				 (1ULL << VIRTIO_F_ACCESS_PLATFORM))
+
+struct vdpasim;
+
+struct vdpasim_virtqueue {
+	struct vringh vring;
+	struct vringh_kiov in_iov;
+	struct vringh_kiov out_iov;
+	unsigned short head;
+	bool ready;
+	u64 desc_addr;
+	u64 device_addr;
+	u64 driver_addr;
+	u32 num;
+	void *private;
+	irqreturn_t (*cb)(void *data);
+};
+
+struct vdpasim_dev_attr {
+	u64 supported_features;
+	size_t config_size;
+	size_t buffer_size;
+	int nvqs;
+	u32 id;
+
+	work_func_t work_fn;
+	void (*get_config)(struct vdpasim *vdpasim, void *config);
+	void (*set_config)(struct vdpasim *vdpasim, const void *config);
+};
+
+/* State of each vdpasim device */
+struct vdpasim {
+	struct vdpa_device vdpa;
+	struct vdpasim_virtqueue *vqs;
+	struct work_struct work;
+	struct vdpasim_dev_attr dev_attr;
+	/* spinlock to synchronize virtqueue state */
+	spinlock_t lock;
+	/* virtio config according to device type */
+	void *config;
+	struct vhost_iotlb *iommu;
+	void *buffer;
+	u32 status;
+	u32 generation;
+	u64 features;
+	/* spinlock to synchronize iommu table */
+	spinlock_t iommu_lock;
+};
+
+struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *attr);
+
+/* TODO: cross-endian support */
+static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim)
+{
+	return virtio_legacy_is_little_endian() ||
+		(vdpasim->features & (1ULL << VIRTIO_F_VERSION_1));
+}
+
+static inline u16 vdpasim16_to_cpu(struct vdpasim *vdpasim, __virtio16 val)
+{
+	return __virtio16_to_cpu(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline __virtio16 cpu_to_vdpasim16(struct vdpasim *vdpasim, u16 val)
+{
+	return __cpu_to_virtio16(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline u32 vdpasim32_to_cpu(struct vdpasim *vdpasim, __virtio32 val)
+{
+	return __virtio32_to_cpu(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline __virtio32 cpu_to_vdpasim32(struct vdpasim *vdpasim, u32 val)
+{
+	return __cpu_to_virtio32(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline u64 vdpasim64_to_cpu(struct vdpasim *vdpasim, __virtio64 val)
+{
+	return __virtio64_to_cpu(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline __virtio64 cpu_to_vdpasim64(struct vdpasim *vdpasim, u64 val)
+{
+	return __cpu_to_virtio64(vdpasim_is_little_endian(vdpasim), val);
+}
+
+#endif
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
new file mode 100644
index 000000000000..c10b6981fdab
--- /dev/null
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VDPA simulator for networking device.
+ *
+ * Copyright (c) 2020, Red Hat Inc. All rights reserved.
+ *     Author: Jason Wang <jasowang@redhat.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/etherdevice.h>
+#include <linux/vringh.h>
+#include <linux/vdpa.h>
+#include <uapi/linux/virtio_net.h>
+
+#include "vdpa_sim.h"
+
+#define DRV_VERSION  "0.1"
+#define DRV_AUTHOR   "Jason Wang <jasowang@redhat.com>"
+#define DRV_DESC     "vDPA Device Simulator for networking device"
+#define DRV_LICENSE  "GPL v2"
+
+#define VDPASIM_NET_FEATURES	(VDPASIM_FEATURES | \
+				 (1ULL << VIRTIO_NET_F_MAC))
+
+#define VDPASIM_NET_VQ_NUM	2
+
+static char *macaddr;
+module_param(macaddr, charp, 0);
+MODULE_PARM_DESC(macaddr, "Ethernet MAC address");
+
+u8 macaddr_buf[ETH_ALEN];
+
+static struct vdpasim *vdpasim_net_dev;
+
+static void vdpasim_net_work(struct work_struct *work)
+{
+	struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);
+	struct vdpasim_virtqueue *txq = &vdpasim->vqs[1];
+	struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0];
+	ssize_t read, write;
+	size_t total_write;
+	int pkts = 0;
+	int err;
+
+	spin_lock(&vdpasim->lock);
+
+	if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK))
+		goto out;
+
+	if (!txq->ready || !rxq->ready)
+		goto out;
+
+	while (true) {
+		total_write = 0;
+		err = vringh_getdesc_iotlb(&txq->vring, &txq->out_iov, NULL,
+					   &txq->head, GFP_ATOMIC);
+		if (err <= 0)
+			break;
+
+		err = vringh_getdesc_iotlb(&rxq->vring, NULL, &rxq->in_iov,
+					   &rxq->head, GFP_ATOMIC);
+		if (err <= 0) {
+			vringh_complete_iotlb(&txq->vring, txq->head, 0);
+			break;
+		}
+
+		while (true) {
+			read = vringh_iov_pull_iotlb(&txq->vring, &txq->out_iov,
+						     vdpasim->buffer,
+						     PAGE_SIZE);
+			if (read <= 0)
+				break;
+
+			write = vringh_iov_push_iotlb(&rxq->vring, &rxq->in_iov,
+						      vdpasim->buffer, read);
+			if (write <= 0)
+				break;
+
+			total_write += write;
+		}
+
+		/* Make sure data is wrote before advancing index */
+		smp_wmb();
+
+		vringh_complete_iotlb(&txq->vring, txq->head, 0);
+		vringh_complete_iotlb(&rxq->vring, rxq->head, total_write);
+
+		/* Make sure used is visible before rasing the interrupt. */
+		smp_wmb();
+
+		local_bh_disable();
+		if (vringh_need_notify_iotlb(&txq->vring) > 0)
+			vringh_notify(&txq->vring);
+		if (vringh_need_notify_iotlb(&rxq->vring) > 0)
+			vringh_notify(&rxq->vring);
+		local_bh_enable();
+
+		if (++pkts > 4) {
+			schedule_work(&vdpasim->work);
+			goto out;
+		}
+	}
+
+out:
+	spin_unlock(&vdpasim->lock);
+}
+
+static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config)
+{
+	struct virtio_net_config *net_config =
+		(struct virtio_net_config *)config;
+
+	net_config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
+	net_config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);
+	memcpy(net_config->mac, macaddr_buf, ETH_ALEN);
+}
+
+static int __init vdpasim_net_init(void)
+{
+	struct vdpasim_dev_attr dev_attr = {};
+	int ret;
+
+	if (macaddr) {
+		mac_pton(macaddr, macaddr_buf);
+		if (!is_valid_ether_addr(macaddr_buf)) {
+			ret = -EADDRNOTAVAIL;
+			goto out;
+		}
+	} else {
+		eth_random_addr(macaddr_buf);
+	}
+
+	dev_attr.id = VIRTIO_ID_NET;
+	dev_attr.supported_features = VDPASIM_NET_FEATURES;
+	dev_attr.nvqs = VDPASIM_NET_VQ_NUM;
+	dev_attr.config_size = sizeof(struct virtio_net_config);
+	dev_attr.get_config = vdpasim_net_get_config;
+	dev_attr.work_fn = vdpasim_net_work;
+	dev_attr.buffer_size = PAGE_SIZE;
+
+	vdpasim_net_dev = vdpasim_create(&dev_attr);
+	if (IS_ERR(vdpasim_net_dev)) {
+		ret = PTR_ERR(vdpasim_net_dev);
+		goto out;
+	}
+
+	ret = vdpa_register_device(&vdpasim_net_dev->vdpa);
+	if (ret)
+		goto put_dev;
+
+	return 0;
+
+put_dev:
+	put_device(&vdpasim_net_dev->vdpa.dev);
+out:
+	return ret;
+}
+
+static void __exit vdpasim_net_exit(void)
+{
+	struct vdpa_device *vdpa = &vdpasim_net_dev->vdpa;
+
+	vdpa_unregister_device(vdpa);
+}
+
+module_init(vdpasim_net_init);
+module_exit(vdpasim_net_exit);
+
+MODULE_VERSION(DRV_VERSION);
+MODULE_LICENSE(DRV_LICENSE);
+MODULE_AUTHOR(DRV_AUTHOR);
+MODULE_DESCRIPTION(DRV_DESC);