This VDUSE driver enables implementing vDPA devices in userspace.
Both control path and data path of vDPA devices will be able to
be handled in userspace.
In the control path, the VDUSE driver will make use of message
mechnism to forward the config operation from vdpa bus driver
to userspace. Userspace can use read()/write() to receive/reply
those control messages.
In the data path, VDUSE_IOTLB_GET_FD ioctl will be used to get
the file descriptors referring to vDPA device's iova regions. Then
userspace can use mmap() to access those iova regions. Besides,
userspace can use ioctl() to inject interrupt and use the eventfd
mechanism to receive virtqueue kicks.
Signed-off-by: Xie Yongji <xieyongji@xxxxxxxxxxxxx>
---
Documentation/userspace-api/ioctl/ioctl-number.rst | 1 +
drivers/vdpa/Kconfig | 10 +
drivers/vdpa/Makefile | 1 +
drivers/vdpa/vdpa_user/Makefile | 5 +
drivers/vdpa/vdpa_user/vduse_dev.c | 1362 ++++++++++++++++++++
include/uapi/linux/vduse.h | 175 +++
6 files changed, 1554 insertions(+)
create mode 100644 drivers/vdpa/vdpa_user/Makefile
create mode 100644 drivers/vdpa/vdpa_user/vduse_dev.c
create mode 100644 include/uapi/linux/vduse.h
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index a4c75a28c839..71722e6f8f23 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -300,6 +300,7 @@ Code Seq# Include File Comments
'z' 10-4F drivers/s390/crypto/zcrypt_api.h conflict!
'|' 00-7F linux/media.h
0x80 00-1F linux/fb.h
+0x81 00-1F linux/vduse.h
0x89 00-06 arch/x86/include/asm/sockios.h
0x89 0B-DF linux/sockios.h
0x89 E0-EF linux/sockios.h SIOCPROTOPRIVATE range
diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index a245809c99d0..77a1da522c21 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -25,6 +25,16 @@ config VDPA_SIM_NET
help
vDPA networking device simulator which loops TX traffic back to RX.
+config VDPA_USER
+ tristate "VDUSE (vDPA Device in Userspace) support"
+ depends on EVENTFD && MMU && HAS_DMA
+ select DMA_OPS
+ select VHOST_IOTLB
+ select IOMMU_IOVA
+ help
+ With VDUSE it is possible to emulate a vDPA Device
+ in a userspace program.
+
config IFCVF
tristate "Intel IFC VF vDPA driver"
depends on PCI_MSI
diff --git a/drivers/vdpa/Makefile b/drivers/vdpa/Makefile
index 67fe7f3d6943..f02ebed33f19 100644
--- a/drivers/vdpa/Makefile
+++ b/drivers/vdpa/Makefile
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_VDPA) += vdpa.o
obj-$(CONFIG_VDPA_SIM) += vdpa_sim/
+obj-$(CONFIG_VDPA_USER) += vdpa_user/
obj-$(CONFIG_IFCVF) += ifcvf/
obj-$(CONFIG_MLX5_VDPA) += mlx5/
obj-$(CONFIG_VP_VDPA) += virtio_pci/
diff --git a/drivers/vdpa/vdpa_user/Makefile b/drivers/vdpa/vdpa_user/Makefile
new file mode 100644
index 000000000000..260e0b26af99
--- /dev/null
+++ b/drivers/vdpa/vdpa_user/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+vduse-y := vduse_dev.o iova_domain.o
+
+obj-$(CONFIG_VDPA_USER) += vduse.o
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
new file mode 100644
index 000000000000..51ca73464d0d
--- /dev/null
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -0,0 +1,1362 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VDUSE: vDPA Device in Userspace
+ *
+ * Copyright (C) 2020-2021 Bytedance Inc. and/or its affiliates. All rights reserved.
+ *
+ * Author: Xie Yongji <xieyongji@xxxxxxxxxxxxx>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/miscdevice.h>
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/eventfd.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/dma-map-ops.h>
+#include <linux/poll.h>
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/vdpa.h>
+#include <uapi/linux/vduse.h>
+#include <uapi/linux/vdpa.h>
+#include <uapi/linux/virtio_config.h>
+#include <linux/mod_devicetable.h>
+
+#include "iova_domain.h"
+
+#define DRV_VERSION "1.0"
+#define DRV_AUTHOR "Yongji Xie <xieyongji@xxxxxxxxxxxxx>"
+#define DRV_DESC "vDPA Device in Userspace"
+#define DRV_LICENSE "GPL v2"
+
+#define VDUSE_DEV_MAX (1U << MINORBITS)
+
+struct vduse_virtqueue {
+ u16 index;
+ bool ready;
+ spinlock_t kick_lock;
+ spinlock_t irq_lock;
+ struct eventfd_ctx *kickfd;
+ struct vdpa_callback cb;
+ struct work_struct inject;
+};
+
+struct vduse_dev;
+
+struct vduse_vdpa {
+ struct vdpa_device vdpa;
+ struct vduse_dev *dev;
+};
+
+struct vduse_dev {
+ struct vduse_vdpa *vdev;
+ struct device dev;
+ struct cdev cdev;
+ struct vduse_virtqueue *vqs;
+ struct vduse_iova_domain *domain;
+ struct mutex lock;
+ spinlock_t msg_lock;
+ atomic64_t msg_unique;
+ wait_queue_head_t waitq;
+ struct list_head send_list;
+ struct list_head recv_list;
+ struct list_head list;
+ struct vdpa_callback config_cb;
+ spinlock_t irq_lock;
+ unsigned long api_version;
+ bool connected;
+ int minor;
+ u16 vq_size_max;
+ u16 vq_num;
+ u32 vq_align;
+ u32 device_id;
+ u32 vendor_id;
+};
+
+struct vduse_dev_msg {
+ struct vduse_dev_request req;
+ struct vduse_dev_response resp;
+ struct list_head list;
+ wait_queue_head_t waitq;
+ bool completed;
+};
+
+struct vduse_control {
+ unsigned long api_version;
+};
+
+static unsigned long max_bounce_size = (64 * 1024 * 1024);
+module_param(max_bounce_size, ulong, 0444);
+MODULE_PARM_DESC(max_bounce_size, "Maximum bounce buffer size. (default: 64M)");
+
+static unsigned long max_iova_size = (128 * 1024 * 1024);
+module_param(max_iova_size, ulong, 0444);
+MODULE_PARM_DESC(max_iova_size, "Maximum iova space size (default: 128M)");
+
+static DEFINE_MUTEX(vduse_lock);
+static LIST_HEAD(vduse_devs);
+static DEFINE_IDA(vduse_ida);
+
+static dev_t vduse_major;
+static struct class *vduse_class;
+static struct workqueue_struct *vduse_irq_wq;
+
+static inline struct vduse_dev *vdpa_to_vduse(struct vdpa_device *vdpa)
+{
+ struct vduse_vdpa *vdev = container_of(vdpa, struct vduse_vdpa, vdpa);
+
+ return vdev->dev;
+}
+
+static inline struct vduse_dev *dev_to_vduse(struct device *dev)
+{
+ struct vdpa_device *vdpa = dev_to_vdpa(dev);
+
+ return vdpa_to_vduse(vdpa);
+}
+
+static struct vduse_dev_msg *vduse_find_msg(struct list_head *head,
+ uint32_t request_id)
+{
+ struct vduse_dev_msg *tmp, *msg = NULL;
+
+ list_for_each_entry(tmp, head, list) {
+ if (tmp->req.request_id == request_id) {
+ msg = tmp;
+ list_del(&tmp->list);
+ break;
+ }
+ }
+
+ return msg;
+}
+
+static struct vduse_dev_msg *vduse_dequeue_msg(struct list_head *head)
+{
+ struct vduse_dev_msg *msg = NULL;
+
+ if (!list_empty(head)) {
+ msg = list_first_entry(head, struct vduse_dev_msg, list);
+ list_del(&msg->list);
+ }
+
+ return msg;
+}
+
+static void vduse_enqueue_msg(struct list_head *head,
+ struct vduse_dev_msg *msg)
+{
+ list_add_tail(&msg->list, head);
+}
+
+static int vduse_dev_msg_sync(struct vduse_dev *dev,
+ struct vduse_dev_msg *msg)
+{
+ init_waitqueue_head(&msg->waitq);
+ spin_lock(&dev->msg_lock);
+ vduse_enqueue_msg(&dev->send_list, msg);
+ wake_up(&dev->waitq);
+ spin_unlock(&dev->msg_lock);
+ wait_event_interruptible(msg->waitq, msg->completed);
+ spin_lock(&dev->msg_lock);
+ if (!msg->completed)
+ list_del(&msg->list);
+ spin_unlock(&dev->msg_lock);
+
+ return (msg->resp.result == VDUSE_REQUEST_OK) ? 0 : -1;
+}
+
+static u32 vduse_dev_get_request_id(struct vduse_dev *dev)
+{
+ return atomic64_fetch_inc(&dev->msg_unique);
+}
+
+static u64 vduse_dev_get_features(struct vduse_dev *dev)
+{
+ struct vduse_dev_msg msg = { 0 };
+
+ msg.req.type = VDUSE_GET_FEATURES;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+
+ return vduse_dev_msg_sync(dev, &msg) ? 0 : msg.resp.f.features;
+}
+
+static int vduse_dev_set_features(struct vduse_dev *dev, u64 features)
+{
+ struct vduse_dev_msg msg = { 0 };
+
+ msg.req.type = VDUSE_SET_FEATURES;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.f.features = features;
+
+ return vduse_dev_msg_sync(dev, &msg);
+}
+
+static u8 vduse_dev_get_status(struct vduse_dev *dev)
+{
+ struct vduse_dev_msg msg = { 0 };
+
+ msg.req.type = VDUSE_GET_STATUS;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+
+ return vduse_dev_msg_sync(dev, &msg) ? 0 : msg.resp.s.status;
+}
+
+static void vduse_dev_set_status(struct vduse_dev *dev, u8 status)
+{
+ struct vduse_dev_msg msg = { 0 };
+
+ msg.req.type = VDUSE_SET_STATUS;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.s.status = status;
+
+ vduse_dev_msg_sync(dev, &msg);
+}
+
+static void vduse_dev_get_config(struct vduse_dev *dev, unsigned int offset,
+ void *buf, unsigned int len)
+{
+ struct vduse_dev_msg msg = { 0 };
+ unsigned int sz;
+
+ while (len) {
+ sz = min_t(unsigned int, len, sizeof(msg.req.config.data));
+ msg.req.type = VDUSE_GET_CONFIG;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.config.offset = offset;
+ msg.req.config.len = sz;
+ vduse_dev_msg_sync(dev, &msg);
+ memcpy(buf, msg.resp.config.data, sz);
+ buf += sz;
+ offset += sz;
+ len -= sz;
+ }
+}
+
+static void vduse_dev_set_config(struct vduse_dev *dev, unsigned int offset,
+ const void *buf, unsigned int len)
+{
+ struct vduse_dev_msg msg = { 0 };
+ unsigned int sz;
+
+ while (len) {
+ sz = min_t(unsigned int, len, sizeof(msg.req.config.data));
+ msg.req.type = VDUSE_SET_CONFIG;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.config.offset = offset;
+ msg.req.config.len = sz;
+ memcpy(msg.req.config.data, buf, sz);
+ vduse_dev_msg_sync(dev, &msg);
+ buf += sz;
+ offset += sz;
+ len -= sz;
+ }
+}
+
+static void vduse_dev_set_vq_num(struct vduse_dev *dev,
+ struct vduse_virtqueue *vq, u32 num)
+{
+ struct vduse_dev_msg msg = { 0 };
+
+ msg.req.type = VDUSE_SET_VQ_NUM;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.vq_num.index = vq->index;
+ msg.req.vq_num.num = num;
+
+ vduse_dev_msg_sync(dev, &msg);
+}
+
+static int vduse_dev_set_vq_addr(struct vduse_dev *dev,
+ struct vduse_virtqueue *vq, u64 desc_addr,
+ u64 driver_addr, u64 device_addr)
+{
+ struct vduse_dev_msg msg = { 0 };
+
+ msg.req.type = VDUSE_SET_VQ_ADDR;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.vq_addr.index = vq->index;
+ msg.req.vq_addr.desc_addr = desc_addr;
+ msg.req.vq_addr.driver_addr = driver_addr;
+ msg.req.vq_addr.device_addr = device_addr;
+
+ return vduse_dev_msg_sync(dev, &msg);
+}
+
+static void vduse_dev_set_vq_ready(struct vduse_dev *dev,
+ struct vduse_virtqueue *vq, bool ready)
+{
+ struct vduse_dev_msg msg = { 0 };
+
+ msg.req.type = VDUSE_SET_VQ_READY;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.vq_ready.index = vq->index;
+ msg.req.vq_ready.ready = ready;
+
+ vduse_dev_msg_sync(dev, &msg);
+}
+
+static bool vduse_dev_get_vq_ready(struct vduse_dev *dev,
+ struct vduse_virtqueue *vq)
+{
+ struct vduse_dev_msg msg = { 0 };
+
+ msg.req.type = VDUSE_GET_VQ_READY;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.vq_ready.index = vq->index;
+
+ return vduse_dev_msg_sync(dev, &msg) ? false : msg.resp.vq_ready.ready;
+}
+
+static int vduse_dev_get_vq_state(struct vduse_dev *dev,
+ struct vduse_virtqueue *vq,
+ struct vdpa_vq_state *state)
+{
+ struct vduse_dev_msg msg = { 0 };
+ int ret;
+
+ msg.req.type = VDUSE_GET_VQ_STATE;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.vq_state.index = vq->index;
+
+ ret = vduse_dev_msg_sync(dev, &msg);
+ if (!ret)
+ state->avail_index = msg.resp.vq_state.avail_idx;
+
+ return ret;
+}
+
+static int vduse_dev_set_vq_state(struct vduse_dev *dev,
+ struct vduse_virtqueue *vq,
+ const struct vdpa_vq_state *state)
+{
+ struct vduse_dev_msg msg = { 0 };
+
+ msg.req.type = VDUSE_SET_VQ_STATE;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.vq_state.index = vq->index;
+ msg.req.vq_state.avail_idx = state->avail_index;
+
+ return vduse_dev_msg_sync(dev, &msg);
+}
+
+static int vduse_dev_update_iotlb(struct vduse_dev *dev,
+ u64 start, u64 last)
+{
+ struct vduse_dev_msg msg = { 0 };
+
+ if (last < start)
+ return -EINVAL;
+
+ msg.req.type = VDUSE_UPDATE_IOTLB;
+ msg.req.request_id = vduse_dev_get_request_id(dev);
+ msg.req.iova.start = start;
+ msg.req.iova.last = last;
+
+ return vduse_dev_msg_sync(dev, &msg);
+}
+
+static ssize_t vduse_dev_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+ struct file *file = iocb->ki_filp;
+ struct vduse_dev *dev = file->private_data;
+ struct vduse_dev_msg *msg;
+ int size = sizeof(struct vduse_dev_request);
+ ssize_t ret = 0;
+
+ if (iov_iter_count(to) < size)
+ return 0;
+
+ spin_lock(&dev->msg_lock);
+ while (1) {
+ msg = vduse_dequeue_msg(&dev->send_list);
+ if (msg)
+ break;
+
+ ret = -EAGAIN;
+ if (file->f_flags & O_NONBLOCK)
+ goto unlock;
+
+ spin_unlock(&dev->msg_lock);
+ ret = wait_event_interruptible_exclusive(dev->waitq,
+ !list_empty(&dev->send_list));
+ if (ret)
+ return ret;
+
+ spin_lock(&dev->msg_lock);
+ }
+ spin_unlock(&dev->msg_lock);
+ ret = copy_to_iter(&msg->req, size, to);
+ spin_lock(&dev->msg_lock);
+ if (ret != size) {
+ ret = -EFAULT;
+ vduse_enqueue_msg(&dev->send_list, msg);
+ goto unlock;
+ }
+ vduse_enqueue_msg(&dev->recv_list, msg);
+ wake_up(&dev->waitq);
+unlock:
+ spin_unlock(&dev->msg_lock);
+
+ return ret;
+}
+
+static ssize_t vduse_dev_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct vduse_dev *dev = file->private_data;
+ struct vduse_dev_response resp;
+ struct vduse_dev_msg *msg;
+ size_t ret;
+
+ ret = copy_from_iter(&resp, sizeof(resp), from);
+ if (ret != sizeof(resp))
+ return -EINVAL;
+
+ spin_lock(&dev->msg_lock);
+ msg = vduse_find_msg(&dev->recv_list, resp.request_id);
+ if (!msg) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+
+ memcpy(&msg->resp, &resp, sizeof(resp));
+ msg->completed = 1;
+ wake_up(&msg->waitq);
+unlock:
+ spin_unlock(&dev->msg_lock);
+
+ return ret;
+}
+
+static __poll_t vduse_dev_poll(struct file *file, poll_table *wait)
+{
+ struct vduse_dev *dev = file->private_data;
+ __poll_t mask = 0;
+
+ poll_wait(file, &dev->waitq, wait);
+
+ if (!list_empty(&dev->send_list))
+ mask |= EPOLLIN | EPOLLRDNORM;
+ if (!list_empty(&dev->recv_list))
+ mask |= EPOLLOUT;
+
+ return mask;
+}
+
+static void vduse_dev_reset(struct vduse_dev *dev)
+{
+ int i;
+
+ /* The coherent mappings are handled in vduse_dev_free_coherent() */
+ vduse_domain_reset_bounce_map(dev->domain);
+ vduse_dev_update_iotlb(dev, 0ULL, ULLONG_MAX);
+
+ spin_lock(&dev->irq_lock);
+ dev->config_cb.callback = NULL;
+ dev->config_cb.private = NULL;
+ spin_unlock(&dev->irq_lock);
+
+ for (i = 0; i < dev->vq_num; i++) {
+ struct vduse_virtqueue *vq = &dev->vqs[i];
+
+ spin_lock(&vq->irq_lock);
+ vq->ready = false;
+ vq->cb.callback = NULL;
+ vq->cb.private = NULL;
+ spin_unlock(&vq->irq_lock);
+ }
+}
+
+static int vduse_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 idx,
+ u64 desc_area, u64 driver_area,
+ u64 device_area)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+ struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+ return vduse_dev_set_vq_addr(dev, vq, desc_area,
+ driver_area, device_area);
+}
+
+static void vduse_vdpa_kick_vq(struct vdpa_device *vdpa, u16 idx)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+ struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+ spin_lock(&vq->kick_lock);
+ if (vq->ready && vq->kickfd)
+ eventfd_signal(vq->kickfd, 1);
+ spin_unlock(&vq->kick_lock);
+}
+
+static void vduse_vdpa_set_vq_cb(struct vdpa_device *vdpa, u16 idx,
+ struct vdpa_callback *cb)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+ struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+ spin_lock(&vq->irq_lock);
+ vq->cb.callback = cb->callback;
+ vq->cb.private = cb->private;
+ spin_unlock(&vq->irq_lock);
+}
+
+static void vduse_vdpa_set_vq_num(struct vdpa_device *vdpa, u16 idx, u32 num)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+ struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+ vduse_dev_set_vq_num(dev, vq, num);
+}
+
+static void vduse_vdpa_set_vq_ready(struct vdpa_device *vdpa,
+ u16 idx, bool ready)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+ struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+ vduse_dev_set_vq_ready(dev, vq, ready);
+ vq->ready = ready;
+}
+
+static bool vduse_vdpa_get_vq_ready(struct vdpa_device *vdpa, u16 idx)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+ struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+ vq->ready = vduse_dev_get_vq_ready(dev, vq);
+
+ return vq->ready;
+}
+
+static int vduse_vdpa_set_vq_state(struct vdpa_device *vdpa, u16 idx,
+ const struct vdpa_vq_state *state)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+ struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+ return vduse_dev_set_vq_state(dev, vq, state);
+}
+
+static int vduse_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 idx,
+ struct vdpa_vq_state *state)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+ struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+ return vduse_dev_get_vq_state(dev, vq, state);
+}
+
+static u32 vduse_vdpa_get_vq_align(struct vdpa_device *vdpa)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ return dev->vq_align;
+}
+
+static u64 vduse_vdpa_get_features(struct vdpa_device *vdpa)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ return vduse_dev_get_features(dev);
+}
+
+static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ if (!(features & (1ULL << VIRTIO_F_ACCESS_PLATFORM)))
+ return -EINVAL;
+
+ return vduse_dev_set_features(dev, features);
+}
+
+static void vduse_vdpa_set_config_cb(struct vdpa_device *vdpa,
+ struct vdpa_callback *cb)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ spin_lock(&dev->irq_lock);
+ dev->config_cb.callback = cb->callback;
+ dev->config_cb.private = cb->private;
+ spin_unlock(&dev->irq_lock);
+}
+
+static u16 vduse_vdpa_get_vq_num_max(struct vdpa_device *vdpa)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ return dev->vq_size_max;
+}
+
+static u32 vduse_vdpa_get_device_id(struct vdpa_device *vdpa)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ return dev->device_id;
+}
+
+static u32 vduse_vdpa_get_vendor_id(struct vdpa_device *vdpa)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ return dev->vendor_id;
+}
+
+static u8 vduse_vdpa_get_status(struct vdpa_device *vdpa)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ return vduse_dev_get_status(dev);
+}
+
+static void vduse_vdpa_set_status(struct vdpa_device *vdpa, u8 status)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ vduse_dev_set_status(dev, status);
+
+ if (status == 0)
+ vduse_dev_reset(dev);
+}
+
+static void vduse_vdpa_get_config(struct vdpa_device *vdpa, unsigned int offset,
+ void *buf, unsigned int len)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ vduse_dev_get_config(dev, offset, buf, len);
+}
+
+static void vduse_vdpa_set_config(struct vdpa_device *vdpa, unsigned int offset,
+ const void *buf, unsigned int len)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ vduse_dev_set_config(dev, offset, buf, len);
+}
+
+static int vduse_vdpa_set_map(struct vdpa_device *vdpa,
+ struct vhost_iotlb *iotlb)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+ int ret;
+
+ ret = vduse_domain_set_map(dev->domain, iotlb);
+ vduse_dev_update_iotlb(dev, 0ULL, ULLONG_MAX);
+
+ return ret;
+}
+
+static void vduse_vdpa_free(struct vdpa_device *vdpa)
+{
+ struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+ WARN_ON(!list_empty(&dev->send_list));
+ WARN_ON(!list_empty(&dev->recv_list));
+ dev->vdev = NULL;
+}
+
+static const struct vdpa_config_ops vduse_vdpa_config_ops = {
+ .set_vq_address = vduse_vdpa_set_vq_address,
+ .kick_vq = vduse_vdpa_kick_vq,
+ .set_vq_cb = vduse_vdpa_set_vq_cb,
+ .set_vq_num = vduse_vdpa_set_vq_num,
+ .set_vq_ready = vduse_vdpa_set_vq_ready,
+ .get_vq_ready = vduse_vdpa_get_vq_ready,
+ .set_vq_state = vduse_vdpa_set_vq_state,
+ .get_vq_state = vduse_vdpa_get_vq_state,
+ .get_vq_align = vduse_vdpa_get_vq_align,
+ .get_features = vduse_vdpa_get_features,
+ .set_features = vduse_vdpa_set_features,
+ .set_config_cb = vduse_vdpa_set_config_cb,
+ .get_vq_num_max = vduse_vdpa_get_vq_num_max,
+ .get_device_id = vduse_vdpa_get_device_id,
+ .get_vendor_id = vduse_vdpa_get_vendor_id,
+ .get_status = vduse_vdpa_get_status,
+ .set_status = vduse_vdpa_set_status,
+ .get_config = vduse_vdpa_get_config,
+ .set_config = vduse_vdpa_set_config,
+ .set_map = vduse_vdpa_set_map,
+ .free = vduse_vdpa_free,
+};
+
+static dma_addr_t vduse_dev_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct vduse_dev *vdev = dev_to_vduse(dev);
+ struct vduse_iova_domain *domain = vdev->domain;
+
+ return vduse_domain_map_page(domain, page, offset, size, dir, attrs);
+}
+
+static void vduse_dev_unmap_page(struct device *dev, dma_addr_t dma_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct vduse_dev *vdev = dev_to_vduse(dev);
+ struct vduse_iova_domain *domain = vdev->domain;
+
+ return vduse_domain_unmap_page(domain, dma_addr, size, dir, attrs);
+}
+
+static void *vduse_dev_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_addr, gfp_t flag,
+ unsigned long attrs)
+{
+ struct vduse_dev *vdev = dev_to_vduse(dev);
+ struct vduse_iova_domain *domain = vdev->domain;
+ unsigned long iova;
+ void *addr;
+
+ *dma_addr = DMA_MAPPING_ERROR;
+ addr = vduse_domain_alloc_coherent(domain, size,
+ (dma_addr_t *)&iova, flag, attrs);
+ if (!addr)
+ return NULL;
+
+ *dma_addr = (dma_addr_t)iova;
+ vduse_dev_update_iotlb(vdev, iova, iova + size - 1);
+
+ return addr;
+}
+
+static void vduse_dev_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_addr,
+ unsigned long attrs)
+{
+ struct vduse_dev *vdev = dev_to_vduse(dev);
+ struct vduse_iova_domain *domain = vdev->domain;
+ unsigned long start = (unsigned long)dma_addr;
+ unsigned long last = start + size - 1;
+
+ vduse_domain_free_coherent(domain, size, vaddr, dma_addr, attrs);
+ vduse_dev_update_iotlb(vdev, start, last);
+}
+
+static const struct dma_map_ops vduse_dev_dma_ops = {
+ .map_page = vduse_dev_map_page,
+ .unmap_page = vduse_dev_unmap_page,
+ .alloc = vduse_dev_alloc_coherent,
+ .free = vduse_dev_free_coherent,
+};
+
+static unsigned int perm_to_file_flags(u8 perm)
+{
+ unsigned int flags = 0;
+
+ switch (perm) {
+ case VDUSE_ACCESS_WO:
+ flags |= O_WRONLY;
+ break;
+ case VDUSE_ACCESS_RO:
+ flags |= O_RDONLY;
+ break;
+ case VDUSE_ACCESS_RW:
+ flags |= O_RDWR;
+ break;
+ default:
+ WARN(1, "invalidate vhost IOTLB permission\n");
+ break;
+ }
+
+ return flags;
+}
+
+static int vduse_kickfd_setup(struct vduse_dev *dev,
+ struct vduse_vq_eventfd *eventfd)
+{
+ struct eventfd_ctx *ctx = NULL;
+ struct vduse_virtqueue *vq;
+
+ if (eventfd->index >= dev->vq_num)
+ return -EINVAL;
+
+ vq = &dev->vqs[eventfd->index];
+ if (eventfd->fd > 0) {
+ ctx = eventfd_ctx_fdget(eventfd->fd);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+ } else if (eventfd->fd != VDUSE_EVENTFD_DEASSIGN)
+ return 0;
