From ad93f7b3715449704225feb33d5fbe6507472245 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 27 Jul 2021 10:53:48 +0530 Subject: dt-bindings: virtio: Add binding for virtio devices Allow virtio device sub-nodes to be added to the virtio mmio or pci nodes. The compatible property for virtio device must be of the format "virtio,device", where ID is virtio device ID in hexadecimal format. Signed-off-by: Viresh Kumar Link: https://lore.kernel.org/r/d8319fd18df7086b12cdcc23193c313893aa071a.1627362340.git.viresh.kumar@linaro.org Signed-off-by: Michael S. Tsirkin Reviewed-by: Arnd Bergmann Reviewed-by: Rob Herring --- Documentation/devicetree/bindings/virtio/mmio.yaml | 3 +- .../devicetree/bindings/virtio/virtio-device.yaml | 41 ++++++++++++++++++++++ 2 files changed, 43 insertions(+), 1 deletion(-) create mode 100644 Documentation/devicetree/bindings/virtio/virtio-device.yaml (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/virtio/mmio.yaml b/Documentation/devicetree/bindings/virtio/mmio.yaml index d46597028cf1..4b7a0273181c 100644 --- a/Documentation/devicetree/bindings/virtio/mmio.yaml +++ b/Documentation/devicetree/bindings/virtio/mmio.yaml @@ -36,7 +36,8 @@ required: - reg - interrupts -additionalProperties: false +additionalProperties: + type: object examples: - | diff --git a/Documentation/devicetree/bindings/virtio/virtio-device.yaml b/Documentation/devicetree/bindings/virtio/virtio-device.yaml new file mode 100644 index 000000000000..1778ea9b5aa5 --- /dev/null +++ b/Documentation/devicetree/bindings/virtio/virtio-device.yaml @@ -0,0 +1,41 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/virtio/virtio-device.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Virtio device bindings + +maintainers: + - Viresh Kumar + +description: + These bindings are applicable to virtio devices irrespective of the bus they + are bound to, like mmio or pci. + +# We need a select here so we don't match all nodes with 'virtio,mmio' +properties: + compatible: + pattern: "^virtio,device[0-9a-f]{1,8}$" + description: Virtio device nodes. + "virtio,deviceID", where ID is the virtio device id. The textual + representation of ID shall be in lower case hexadecimal with leading + zeroes suppressed. + +required: + - compatible + +additionalProperties: true + +examples: + - | + virtio@3000 { + compatible = "virtio,mmio"; + reg = <0x3000 0x100>; + interrupts = <43>; + + i2c { + compatible = "virtio,device22"; + }; + }; +... -- cgit v1.2.3-58-ga151 From 7f815fce08d563006e43d1b7d2f9a0a4f3b832f3 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 27 Jul 2021 10:53:49 +0530 Subject: dt-bindings: i2c: Add bindings for i2c-virtio This patch adds binding for virtio I2C device, it is based on virtio-device bindings. Acked-by: Wolfram Sang Reviewed-by: Arnd Bergmann Signed-off-by: Viresh Kumar Link: https://lore.kernel.org/r/33c317b95097ce491845c697db1e8285e3ec1d41.1627362340.git.viresh.kumar@linaro.org Signed-off-by: Michael S. Tsirkin Reviewed-by: Rob Herring --- .../devicetree/bindings/i2c/i2c-virtio.yaml | 51 ++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 Documentation/devicetree/bindings/i2c/i2c-virtio.yaml (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/i2c/i2c-virtio.yaml b/Documentation/devicetree/bindings/i2c/i2c-virtio.yaml new file mode 100644 index 000000000000..7d87ed855301 --- /dev/null +++ b/Documentation/devicetree/bindings/i2c/i2c-virtio.yaml @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/i2c/i2c-virtio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Virtio I2C Adapter + +maintainers: + - Viresh Kumar + +allOf: + - $ref: /schemas/i2c/i2c-controller.yaml# + - $ref: /schemas/virtio/virtio-device.yaml# + +description: + Virtio I2C device, see /schemas/virtio/virtio-device.yaml for more details. + +properties: + $nodename: + const: i2c + + compatible: + const: virtio,device22 + +required: + - compatible + +unevaluatedProperties: false + +examples: + - | + virtio@3000 { + compatible = "virtio,mmio"; + reg = <0x3000 0x100>; + interrupts = <41>; + + i2c { + compatible = "virtio,device22"; + + #address-cells = <1>; + #size-cells = <0>; + + light-sensor@20 { + compatible = "dynaimage,al3320a"; + reg = <0x20>; + }; + }; + }; + +... -- cgit v1.2.3-58-ga151 From f3a66dcdf2390f8434622a4e20a1af7413502623 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 27 Jul 2021 10:53:50 +0530 Subject: dt-bindings: gpio: Add bindings for gpio-virtio This patch adds binding for virtio GPIO controller, it is based on virtio-device bindings. Reviewed-by: Arnd Bergmann Signed-off-by: Viresh Kumar Link: https://lore.kernel.org/r/acf7402ef4aabc0ad6295c32846f2bef1cd9b56a.1627362340.git.viresh.kumar@linaro.org Signed-off-by: Michael S. Tsirkin Reviewed-by: Rob Herring --- .../devicetree/bindings/gpio/gpio-virtio.yaml | 59 ++++++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 Documentation/devicetree/bindings/gpio/gpio-virtio.yaml (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/gpio/gpio-virtio.yaml b/Documentation/devicetree/bindings/gpio/gpio-virtio.yaml new file mode 100644 index 000000000000..601d85754577 --- /dev/null +++ b/Documentation/devicetree/bindings/gpio/gpio-virtio.yaml @@ -0,0 +1,59 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/gpio/gpio-virtio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Virtio GPIO controller + +maintainers: + - Viresh Kumar + +allOf: + - $ref: /schemas/virtio/virtio-device.yaml# + +description: + Virtio GPIO controller, see /schemas/virtio/virtio-device.yaml for more + details. + +properties: + $nodename: + const: gpio + + compatible: + const: virtio,device29 + + gpio-controller: true + + "#gpio-cells": + const: 2 + + interrupt-controller: true + + "#interrupt-cells": + const: 2 + +required: + - compatible + - gpio-controller + - "#gpio-cells" + +unevaluatedProperties: false + +examples: + - | + virtio@3000 { + compatible = "virtio,mmio"; + reg = <0x3000 0x100>; + interrupts = <41>; + + gpio { + compatible = "virtio,device29"; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + +... -- cgit v1.2.3-58-ga151 From c8a6153b6c59d95c0e091f053f6f180952ade91e Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Tue, 31 Aug 2021 18:36:33 +0800 Subject: vduse: Introduce VDUSE - vDPA Device in Userspace This VDUSE driver enables implementing software-emulated vDPA devices in userspace. The vDPA device is created by ioctl(VDUSE_CREATE_DEV) on /dev/vduse/control. Then a char device interface (/dev/vduse/$NAME) is exported to userspace for device emulation. In order to make the device emulation more secure, the device's control path is handled in kernel. A message mechnism is introduced to forward some dataplane related control messages to userspace. And in the data path, the DMA buffer will be mapped into userspace address space through different ways depending on the vDPA bus to which the vDPA device is attached. In virtio-vdpa case, the MMU-based software IOTLB is used to achieve that. And in vhost-vdpa case, the DMA buffer is reside in a userspace memory region which can be shared to the VDUSE userspace processs via transferring the shmfd. For more details on VDUSE design and usage, please see the follow-on Documentation commit. NB(mst): when merging this with b542e383d8c0 ("eventfd: Make signal recursion protection a task bit") replace eventfd_signal_count with eventfd_signal_allowed, and drop the previous ("eventfd: Export eventfd_wake_count to modules"). Signed-off-by: Xie Yongji Acked-by: Jason Wang Link: https://lore.kernel.org/r/20210831103634.33-13-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin --- 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 | 1646 ++++++++++++++++++++ include/uapi/linux/vduse.h | 306 ++++ 6 files changed, 1969 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 (limited to 'Documentation') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 1409e40e6345..293ca3aef358 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 e48e2b10ca36..3d91982d8371 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -33,6 +33,16 @@ config VDPA_SIM_BLOCK vDPA block device simulator which terminates IO request in a memory buffer. +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..b9b2659408e6 --- /dev/null +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -0,0 +1,1646 @@ +// 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 + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "iova_domain.h" + +#define DRV_AUTHOR "Yongji Xie " +#define DRV_DESC "vDPA Device in Userspace" +#define DRV_LICENSE "GPL v2" + +#define VDUSE_DEV_MAX (1U << MINORBITS) +#define VDUSE_BOUNCE_SIZE (64 * 1024 * 1024) +#define VDUSE_IOVA_SIZE (128 * 1024 * 1024) +#define VDUSE_MSG_DEFAULT_TIMEOUT 30 + +struct vduse_virtqueue { + u16 index; + u16 num_max; + u32 num; + u64 desc_addr; + u64 driver_addr; + u64 device_addr; + struct vdpa_vq_state state; + bool ready; + bool kicked; + spinlock_t kick_lock; + spinlock_t irq_lock; + struct eventfd_ctx *kickfd; + struct vdpa_callback cb; + struct work_struct inject; + struct work_struct kick; +}; + +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 vduse_virtqueue *vqs; + struct vduse_iova_domain *domain; + char *name; + struct mutex lock; + spinlock_t msg_lock; + u64 msg_unique; + u32 msg_timeout; + wait_queue_head_t waitq; + struct list_head send_list; + struct list_head recv_list; + struct vdpa_callback config_cb; + struct work_struct inject; + spinlock_t irq_lock; + int minor; + bool broken; + bool connected; + u64 api_version; + u64 device_features; + u64 driver_features; + u32 device_id; + u32 vendor_id; + u32 generation; + u32 config_size; + void *config; + u8 status; + u32 vq_num; + u32 vq_align; +}; + +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 { + u64 api_version; +}; + +static DEFINE_MUTEX(vduse_lock); +static DEFINE_IDR(vduse_idr); + +static dev_t vduse_major; +static struct class *vduse_class; +static struct cdev vduse_ctrl_cdev; +static struct cdev vduse_cdev; +static struct workqueue_struct *vduse_irq_wq; + +static u32 allowed_device_id[] = { + VIRTIO_ID_BLOCK, +}; + +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 *msg; + + list_for_each_entry(msg, head, list) { + if (msg->req.request_id == request_id) { + list_del(&msg->list); + return msg; + } + } + + return NULL; +} + +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 void vduse_dev_broken(struct vduse_dev *dev) +{ + struct vduse_dev_msg *msg, *tmp; + + if (unlikely(dev->broken)) + return; + + list_splice_init(&dev->recv_list, &dev->send_list); + list_for_each_entry_safe(msg, tmp, &dev->send_list, list) { + list_del(&msg->list); + msg->completed = 1; + msg->resp.result = VDUSE_REQ_RESULT_FAILED; + wake_up(&msg->waitq); + } + dev->broken = true; + wake_up(&dev->waitq); +} + +static int vduse_dev_msg_sync(struct vduse_dev *dev, + struct vduse_dev_msg *msg) +{ + int ret; + + if (unlikely(dev->broken)) + return -EIO; + + init_waitqueue_head(&msg->waitq); + spin_lock(&dev->msg_lock); + if (unlikely(dev->broken)) { + spin_unlock(&dev->msg_lock); + return -EIO; + } + msg->req.request_id = dev->msg_unique++; + vduse_enqueue_msg(&dev->send_list, msg); + wake_up(&dev->waitq); + spin_unlock(&dev->msg_lock); + if (dev->msg_timeout) + ret = wait_event_killable_timeout(msg->waitq, msg->completed, + (long)dev->msg_timeout * HZ); + else + ret = wait_event_killable(msg->waitq, msg->completed); + + spin_lock(&dev->msg_lock); + if (!msg->completed) { + list_del(&msg->list); + msg->resp.result = VDUSE_REQ_RESULT_FAILED; + /* Mark the device as malfunction when there is a timeout */ + if (!ret) + vduse_dev_broken(dev); + } + ret = (msg->resp.result == VDUSE_REQ_RESULT_OK) ? 0 : -EIO; + spin_unlock(&dev->msg_lock); + + return ret; +} + +static int vduse_dev_get_vq_state_packed(struct vduse_dev *dev, + struct vduse_virtqueue *vq, + struct vdpa_vq_state_packed *packed) +{ + struct vduse_dev_msg msg = { 0 }; + int ret; + + msg.req.type = VDUSE_GET_VQ_STATE; + msg.req.vq_state.index = vq->index; + + ret = vduse_dev_msg_sync(dev, &msg); + if (ret) + return ret; + + packed->last_avail_counter = + msg.resp.vq_state.packed.last_avail_counter & 0x0001; + packed->last_avail_idx = + msg.resp.vq_state.packed.last_avail_idx & 0x7FFF; + packed->last_used_counter = + msg.resp.vq_state.packed.last_used_counter & 0x0001; + packed->last_used_idx = + msg.resp.vq_state.packed.last_used_idx & 0x7FFF; + + return 0; +} + +static int vduse_dev_get_vq_state_split(struct vduse_dev *dev, + struct vduse_virtqueue *vq, + struct vdpa_vq_state_split *split) +{ + struct vduse_dev_msg msg = { 0 }; + int ret; + + msg.req.type = VDUSE_GET_VQ_STATE; + msg.req.vq_state.index = vq->index; + + ret = vduse_dev_msg_sync(dev, &msg); + if (ret) + return ret; + + split->avail_index = msg.resp.vq_state.split.avail_index; + + return 0; +} + +static int vduse_dev_set_status(struct vduse_dev *dev, u8 status) +{ + struct vduse_dev_msg msg = { 0 }; + + msg.req.type = VDUSE_SET_STATUS; + msg.req.s.status = status; + + 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.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; + + if (iov_iter_count(to) < size) + return -EINVAL; + + 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); +unlock: + spin_unlock(&dev->msg_lock); + + return ret; +} + +static bool is_mem_zero(const char *ptr, int size) +{ + int i; + + for (i = 0; i < size; i++) { + if (ptr[i]) + return false; + } + return true; +} + +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; + + if (!is_mem_zero((const char *)resp.reserved, sizeof(resp.reserved))) + return -EINVAL; + + spin_lock(&dev->msg_lock); + msg = vduse_find_msg(&dev->recv_list, resp.request_id); + if (!msg) { + ret = -ENOENT; + 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); + + spin_lock(&dev->msg_lock); + + if (unlikely(dev->broken)) + mask |= EPOLLERR; + if (!list_empty(&dev->send_list)) + mask |= EPOLLIN | EPOLLRDNORM; + if (!list_empty(&dev->recv_list)) + mask |= EPOLLOUT | EPOLLWRNORM; + + spin_unlock(&dev->msg_lock); + + return mask; +} + +static void vduse_dev_reset(struct vduse_dev *dev) +{ + int i; + struct vduse_iova_domain *domain = dev->domain; + + /* The coherent mappings are handled in vduse_dev_free_coherent() */ + if (domain->bounce_map) + vduse_domain_reset_bounce_map(domain); + + dev->status = 0; + dev->driver_features = 0; + dev->generation++; + spin_lock(&dev->irq_lock); + dev->config_cb.callback = NULL; + dev->config_cb.private = NULL; + spin_unlock(&dev->irq_lock); + flush_work(&dev->inject); + + for (i = 0; i < dev->vq_num; i++) { + struct vduse_virtqueue *vq = &dev->vqs[i]; + + vq->ready = false; + vq->desc_addr = 0; + vq->driver_addr = 0; + vq->device_addr = 0; + vq->num = 0; + memset(&vq->state, 0, sizeof(vq->state)); + + spin_lock(&vq->kick_lock); + vq->kicked = false; + if (vq->kickfd) + eventfd_ctx_put(vq->kickfd); + vq->kickfd = NULL; + spin_unlock(&vq->kick_lock); + + spin_lock(&vq->irq_lock); + vq->cb.callback = NULL; + vq->cb.private = NULL; + spin_unlock(&vq->irq_lock); + flush_work(&vq->inject); + flush_work(&vq->kick); + } +} + +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]; + + vq->desc_addr = desc_area; + vq->driver_addr = driver_area; + vq->device_addr = device_area; + + return 0; +} + +static void vduse_vq_kick(struct vduse_virtqueue *vq) +{ + spin_lock(&vq->kick_lock); + if (!vq->ready) + goto unlock; + + if (vq->kickfd) + eventfd_signal(vq->kickfd, 1); + else + vq->kicked = true; +unlock: + spin_unlock(&vq->kick_lock); +} + +static void vduse_vq_kick_work(struct work_struct *work) +{ + struct vduse_virtqueue *vq = container_of(work, + struct vduse_virtqueue, kick); + + vduse_vq_kick(vq); +} + +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]; + + /* + * TODO: after applying b542e383d8c0 ("eventfd: Make signal recursion protection a task bit") + * replace eventfd_signal_count with eventfd_signal_allowed, and + * drop the previous ("eventfd: Export eventfd_wake_count to modules") + * */ + if (eventfd_signal_count()) { + schedule_work(&vq->kick); + return; + } + vduse_vq_kick(vq); +} + +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]; + + vq->num = 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]; + + 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]; + + 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]; + + if (dev->driver_features & BIT_ULL(VIRTIO_F_RING_PACKED)) { + vq->state.packed.last_avail_counter = + state->packed.last_avail_counter; + vq->state.packed.last_avail_idx = state->packed.last_avail_idx; + vq->state.packed.last_used_counter = + state->packed.last_used_counter; + vq->state.packed.last_used_idx = state->packed.last_used_idx; + } else + vq->state.split.avail_index = state->split.avail_index; + + return 0; +} + +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]; + + if (dev->driver_features & BIT_ULL(VIRTIO_F_RING_PACKED)) + return vduse_dev_get_vq_state_packed(dev, vq, &state->packed); + + return vduse_dev_get_vq_state_split(dev, vq, &state->split); +} + +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 dev->device_features; +} + +static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + dev->driver_features = features; + return 0; +} + +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); + u16 num_max = 0; + int i; + + for (i = 0; i < dev->vq_num; i++) + if (num_max < dev->vqs[i].num_max) + num_max = dev->vqs[i].num_max; + + return num_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 dev->status; +} + +static void vduse_vdpa_set_status(struct vdpa_device *vdpa, u8 status) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + if (vduse_dev_set_status(dev, status)) + return; + + dev->status = status; +} + +static size_t vduse_vdpa_get_config_size(struct vdpa_device *vdpa) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + return dev->config_size; +} + +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); + + if (len > dev->config_size - offset) + return; + + memcpy(buf, dev->config + offset, len); +} + +static void vduse_vdpa_set_config(struct vdpa_device *vdpa, unsigned int offset, + const void *buf, unsigned int len) +{ + /* Now we only support read-only configuration space */ +} + +static int vduse_vdpa_reset(struct vdpa_device *vdpa) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + if (vduse_dev_set_status(dev, 0)) + return -EIO; + + vduse_dev_reset(dev); + + return 0; +} + +static u32 vduse_vdpa_get_generation(struct vdpa_device *vdpa) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + return dev->generation; +} + +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); + if (ret) + return ret; + + ret = vduse_dev_update_iotlb(dev, 0ULL, ULLONG_MAX); + if (ret) { + vduse_domain_clear_map(dev->domain, iotlb); + return ret; + } + + return 0; +} + +static void vduse_vdpa_free(struct vdpa_device *vdpa) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + 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_size = vduse_vdpa_get_config_size, + .get_config = vduse_vdpa_get_config, + .set_config = vduse_vdpa_set_config, + .get_generation = vduse_vdpa_get_generation, + .reset = vduse_vdpa_reset, + .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; + + 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; + + vduse_domain_free_coherent(domain, size, vaddr, dma_addr, attrs); +} + +static size_t vduse_dev_max_mapping_size(struct device *dev) +{ + struct vduse_dev *vdev = dev_to_vduse(dev); + struct vduse_iova_domain *domain = vdev->domain; + + return domain->bounce_size; +} + +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, + .max_mapping_size = vduse_dev_max_mapping_size, +}; + +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; + u32 index; + + if (eventfd->index >= dev->vq_num) + return -EINVAL; + + index = array_index_nospec(eventfd->index, dev->vq_num); + vq = &dev->vqs[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; + + spin_lock(&vq->kick_lock); + if (vq->kickfd) + eventfd_ctx_put(vq->kickfd); + vq->kickfd = ctx; + if (vq->ready && vq->kicked && vq->kickfd) { + eventfd_signal(vq->kickfd, 1); + vq->kicked = false; + } + spin_unlock(&vq->kick_lock); + + return 0; +} + +static bool vduse_dev_is_ready(struct vduse_dev *dev) +{ + int i; + + for (i = 0; i < dev->vq_num; i++) + if (!dev->vqs[i].num_max) + return false; + + return true; +} + +static void vduse_dev_irq_inject(struct work_struct *work) +{ + struct vduse_dev *dev = container_of(work, struct vduse_dev, inject); + + spin_lock_irq(&dev->irq_lock); + if (dev->config_cb.callback) + dev->config_cb.callback(dev->config_cb.private); + spin_unlock_irq(&dev->irq_lock); +} + +static void vduse_vq_irq_inject(struct work_struct *work) +{ + struct vduse_virtqueue *vq = container_of(work, + struct vduse_virtqueue, inject); + + spin_lock_irq(&vq->irq_lock); + if (vq->ready && vq->cb.callback) + vq->cb.callback(vq->cb.private); + spin_unlock_irq(&vq->irq_lock); +} + +static long vduse_dev_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct vduse_dev *dev = file->private_data; + void __user *argp = (void __user *)arg; + int ret; + + if (unlikely(dev->broken)) + return -EPERM; + + switch (cmd) { + case VDUSE_IOTLB_GET_FD: { + struct vduse_iotlb_entry entry; + struct vhost_iotlb_map *map; + struct vdpa_map_file *map_file; + struct vduse_iova_domain *domain = dev->domain; + struct file *f = NULL; + + ret = -EFAULT; + if (copy_from_user(&entry, argp, sizeof(entry))) + break; + + ret = -EINVAL; + if (entry.start > entry.last) + break; + + spin_lock(&domain->iotlb_lock); + map = vhost_iotlb_itree_first(domain->iotlb, + entry.start, entry.last); + if (map) { + map_file = (struct vdpa_map_file *)map->opaque; + f = get_file(map_file->file); + entry.offset = map_file->offset; + entry.start = map->start; + entry.last = map->last; + entry.perm = map->perm; + } + spin_unlock(&domain->iotlb_lock); + ret = -EINVAL; + if (!f) + break; + + ret = -EFAULT; + if (copy_to_user(argp, &entry, sizeof(entry))) { + fput(f); + break; + } + ret = receive_fd(f, perm_to_file_flags(entry.perm)); + fput(f); + break; + } + case VDUSE_DEV_GET_FEATURES: + /* + * Just mirror what driver wrote here. + * The driver is expected to check FEATURE_OK later. + */ + ret = put_user(dev->driver_features, (u64 __user *)argp); + break; + case VDUSE_DEV_SET_CONFIG: { + struct vduse_config_data config; + unsigned long size = offsetof(struct vduse_config_data, + buffer); + + ret = -EFAULT; + if (copy_from_user(&config, argp, size)) + break; + + ret = -EINVAL; + if (config.length == 0 || + config.length > dev->config_size - config.offset) + break; + + ret = -EFAULT; + if (copy_from_user(dev->config + config.offset, argp + size, + config.length)) + break; + + ret = 0; + break; + } + case VDUSE_DEV_INJECT_CONFIG_IRQ: + ret = 0; + queue_work(vduse_irq_wq, &dev->inject); + break; + case VDUSE_VQ_SETUP: { + struct vduse_vq_config config; + u32 index; + + ret = -EFAULT; + if (copy_from_user(&config, argp, sizeof(config))) + break; + + ret = -EINVAL; + if (config.index >= dev->vq_num) + break; + + if (!is_mem_zero((const char *)config.reserved, + sizeof(config.reserved))) + break; + + index = array_index_nospec(config.index, dev->vq_num); + dev->vqs[index].num_max = config.max_size; + ret = 0; + break; + } + case VDUSE_VQ_GET_INFO: { + struct vduse_vq_info vq_info; + struct vduse_virtqueue *vq; + u32 index; + + ret = -EFAULT; + if (copy_from_user(&vq_info, argp, sizeof(vq_info))) + break; + + ret = -EINVAL; + if (vq_info.index >= dev->vq_num) + break; + + index = array_index_nospec(vq_info.index, dev->vq_num); + vq = &dev->vqs[index]; + vq_info.desc_addr = vq->desc_addr; + vq_info.driver_addr = vq->driver_addr; + vq_info.device_addr = vq->device_addr; + vq_info.num = vq->num; + + if (dev->driver_features & BIT_ULL(VIRTIO_F_RING_PACKED)) { + vq_info.packed.last_avail_counter = + vq->state.packed.last_avail_counter; + vq_info.packed.last_avail_idx = + vq->state.packed.last_avail_idx; + vq_info.packed.last_used_counter = + vq->state.packed.last_used_counter; + vq_info.packed.last_used_idx = + vq->state.packed.last_used_idx; + } else + vq_info.split.avail_index = + vq->state.split.avail_index; + + vq_info.ready = vq->ready; + + ret = -EFAULT; + if (copy_to_user(argp, &vq_info, sizeof(vq_info))) + break; + + ret = 0; + break; + } + case VDUSE_VQ_SETUP_KICKFD: { + struct vduse_vq_eventfd eventfd; + + ret = -EFAULT; + if (copy_from_user(&eventfd, argp, sizeof(eventfd))) + break; + + ret = vduse_kickfd_setup(dev, &eventfd); + break; + } + case VDUSE_VQ_INJECT_IRQ: { + u32 index; + + ret = -EFAULT; + if (get_user(index, (u32 __user *)argp)) + break; + + ret = -EINVAL; + if (index >= dev->vq_num) + break; + + ret = 0; + index = array_index_nospec(index, dev->vq_num); + queue_work(vduse_irq_wq, &dev->vqs[index].inject); + break; + } + default: + ret = -ENOIOCTLCMD; + break; + } + + return ret; +} + +static int vduse_dev_release(struct inode *inode, struct file *file) +{ + struct vduse_dev *dev = file->private_data; + + spin_lock(&dev->msg_lock); + /* Make sure the inflight messages can processed after reconncection */ + list_splice_init(&dev->recv_list, &dev->send_list); + spin_unlock(&dev->msg_lock); + dev->connected = false; + + return 0; +} + +static struct vduse_dev *vduse_dev_get_from_minor(int minor) +{ + struct vduse_dev *dev; + + mutex_lock(&vduse_lock); + dev = idr_find(&vduse_idr, minor); + mutex_unlock(&vduse_lock); + + return dev; +} + +static int vduse_dev_open(struct inode *inode, struct file *file) +{ + int ret; + struct vduse_dev *dev = vduse_dev_get_from_minor(iminor(inode)); + + if (!dev) + return -ENODEV; + + ret = -EBUSY; + mutex_lock(&dev->lock); + if (dev->connected) + goto unlock; + + ret = 0; + dev->connected = true; + file->private_data = dev; +unlock: + mutex_unlock(&dev->lock); + + return ret; +} + +static const struct file_operations vduse_dev_fops = { + .owner = THIS_MODULE, + .open = vduse_dev_open, + .release = vduse_dev_release, + .read_iter = vduse_dev_read_iter, + .write_iter = vduse_dev_write_iter, + .poll = vduse_dev_poll, + .unlocked_ioctl = vduse_dev_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .llseek = noop_llseek, +}; + +static struct vduse_dev *vduse_dev_create(void) +{ + struct vduse_dev *dev = kzalloc(sizeof(*dev), GFP_KERNEL); + + if (!dev) + return NULL; + + mutex_init(&dev->lock); + spin_lock_init(&dev->msg_lock); + INIT_LIST_HEAD(&dev->send_list); + INIT_LIST_HEAD(&dev->recv_list); + spin_lock_init(&dev->irq_lock); + + INIT_WORK(&dev->inject, vduse_dev_irq_inject); + init_waitqueue_head(&dev->waitq); + + return dev; +} + +static void vduse_dev_destroy(struct vduse_dev *dev) +{ + kfree(dev); +} + +static struct vduse_dev *vduse_find_dev(const char *name) +{ + struct vduse_dev *dev; + int id; + + idr_for_each_entry(&vduse_idr, dev, id) + if (!strcmp(dev->name, name)) + return dev; + + return NULL; +} + +static int vduse_destroy_dev(char *name) +{ + struct vduse_dev *dev = vduse_find_dev(name); + + if (!dev) + return -EINVAL; + + mutex_lock(&dev->lock); + if (dev->vdev || dev->connected) { + mutex_unlock(&dev->lock); + return -EBUSY; + } + dev->connected = true; + mutex_unlock(&dev->lock); + + vduse_dev_reset(dev); + device_destroy(vduse_class, MKDEV(MAJOR(vduse_major), dev->minor)); + idr_remove(&vduse_idr, dev->minor); + kvfree(dev->config); + kfree(dev->vqs); + vduse_domain_destroy(dev->domain); + kfree(dev->name); + vduse_dev_destroy(dev); + module_put(THIS_MODULE); + + return 0; +} + +static bool device_is_allowed(u32 device_id) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(allowed_device_id); i++) + if (allowed_device_id[i] == device_id) + return true; + + return false; +} + +static bool features_is_valid(u64 features) +{ + if (!(features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) + return false; + + /* Now we only support read-only configuration space */ + if (features & (1ULL << VIRTIO_BLK_F_CONFIG_WCE)) + return false; + + return true; +} + +static bool vduse_validate_config(struct vduse_dev_config *config) +{ + if (!is_mem_zero((const char *)config->reserved, + sizeof(config->reserved))) + return false; + + if (config->vq_align > PAGE_SIZE) + return false; + + if (config->config_size > PAGE_SIZE) + return false; + + if (!device_is_allowed(config->device_id)) + return false; + + if (!features_is_valid(config->features)) + return false; + + return true; +} + +static ssize_t msg_timeout_show(struct device *device, + struct device_attribute *attr, char *buf) +{ + struct vduse_dev *dev = dev_get_drvdata(device); + + return sysfs_emit(buf, "%u\n", dev->msg_timeout); +} + +static ssize_t msg_timeout_store(struct device *device, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct vduse_dev *dev = dev_get_drvdata(device); + int ret; + + ret = kstrtouint(buf, 10, &dev->msg_timeout); + if (ret < 0) + return ret; + + return count; +} + +static DEVICE_ATTR_RW(msg_timeout); + +static struct attribute *vduse_dev_attrs[] = { + &dev_attr_msg_timeout.attr, + NULL +}; + +ATTRIBUTE_GROUPS(vduse_dev); + +static int vduse_create_dev(struct vduse_dev_config *config, + void *config_buf, u64 api_version) +{ + int i, ret; + struct vduse_dev *dev; + + ret = -EEXIST; + if (vduse_find_dev(config->name)) + goto err; + + ret = -ENOMEM; + dev = vduse_dev_create(); + if (!dev) + goto err; + + dev->api_version = api_version; + dev->device_features = config->features; + dev->device_id = config->device_id; + dev->vendor_id = config->vendor_id; + dev->name = kstrdup(config->name, GFP_KERNEL); + if (!dev->name) + goto err_str; + + dev->domain = vduse_domain_create(VDUSE_IOVA_SIZE - 1, + VDUSE_BOUNCE_SIZE); + if (!dev->domain) + goto err_domain; + + dev->config = config_buf; + dev->config_size = config->config_size; + dev->vq_align = config->vq_align; + dev->vq_num = config->vq_num; + dev->vqs = kcalloc(dev->vq_num, sizeof(*dev->vqs), GFP_KERNEL); + if (!dev->vqs) + goto err_vqs; + + for (i = 0; i < dev->vq_num; i++) { + dev->vqs[i].index = i; + INIT_WORK(&dev->vqs[i].inject, vduse_vq_irq_inject); + INIT_WORK(&dev->vqs[i].kick, vduse_vq_kick_work); + spin_lock_init(&dev->vqs[i].kick_lock); + spin_lock_init(&dev->vqs[i].irq_lock); + } + + ret = idr_alloc(&vduse_idr, dev, 1, VDUSE_DEV_MAX, GFP_KERNEL); + if (ret < 0) + goto err_idr; + + dev->minor = ret; + dev->msg_timeout = VDUSE_MSG_DEFAULT_TIMEOUT; + dev->dev = device_create(vduse_class, NULL, + MKDEV(MAJOR(vduse_major), dev->minor), + dev, "%s", config->name); + if (IS_ERR(dev->dev)) { + ret = PTR_ERR(dev->dev); + goto err_dev; + } + __module_get(THIS_MODULE); + + return 0; +err_dev: + idr_remove(&vduse_idr, dev->minor); +err_idr: + kfree(dev->vqs); +err_vqs: + vduse_domain_destroy(dev->domain); +err_domain: + kfree(dev->name); +err_str: + vduse_dev_destroy(dev); +err: + kvfree(config_buf); + return ret; +} + +static long vduse_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + int ret; + void __user *argp = (void __user *)arg; + struct vduse_control *control = file->private_data; + + mutex_lock(&vduse_lock); + switch (cmd) { + case VDUSE_GET_API_VERSION: + ret = put_user(control->api_version, (u64 __user *)argp); + break; + case VDUSE_SET_API_VERSION: { + u64 api_version; + + ret = -EFAULT; + if (get_user(api_version, (u64 __user *)argp)) + break; + + ret = -EINVAL; + if (api_version > VDUSE_API_VERSION) + break; + + ret = 0; + control->api_version = api_version; + break; + } + case VDUSE_CREATE_DEV: { + struct vduse_dev_config config; + unsigned long size = offsetof(struct vduse_dev_config, config); + void *buf; + + ret = -EFAULT; + if (copy_from_user(&config, argp, size)) + break; + + ret = -EINVAL; + if (vduse_validate_config(&config) == false) + break; + + buf = vmemdup_user(argp + size, config.config_size); + if (IS_ERR(buf)) { + ret = PTR_ERR(buf); + break; + } + config.name[VDUSE_NAME_MAX - 1] = '\0'; + ret = vduse_create_dev(&config, buf, control->api_version); + break; + } + case VDUSE_DESTROY_DEV: { + char name[VDUSE_NAME_MAX]; + + ret = -EFAULT; + if (copy_from_user(name, argp, VDUSE_NAME_MAX)) + break; + + name[VDUSE_NAME_MAX - 1] = '\0'; + ret = vduse_destroy_dev(name); + break; + } + default: + ret = -EINVAL; + break; + } + mutex_unlock(&vduse_lock); + + return ret; +} + +static int vduse_release(struct inode *inode, struct file *file) +{ + struct vduse_control *control = file->private_data; + + kfree(control); + return 0; +} + +static int vduse_open(struct inode *inode, struct file *file) +{ + struct vduse_control *control; + + control = kmalloc(sizeof(struct vduse_control), GFP_KERNEL); + if (!control) + return -ENOMEM; + + control->api_version = VDUSE_API_VERSION; + file->private_data = control; + + return 0; +} + +static const struct file_operations vduse_ctrl_fops = { + .owner = THIS_MODULE, + .open = vduse_open, + .release = vduse_release, + .unlocked_ioctl = vduse_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .llseek = noop_llseek, +}; + +static char *vduse_devnode(struct device *dev, umode_t *mode) +{ + return kasprintf(GFP_KERNEL, "vduse/%s", dev_name(dev)); +} + +static void vduse_mgmtdev_release(struct device *dev) +{ +} + +static struct device vduse_mgmtdev = { + .init_name = "vduse", + .release = vduse_mgmtdev_release, +}; + +static struct vdpa_mgmt_dev mgmt_dev; + +static int vduse_dev_init_vdpa(struct vduse_dev *dev, const char *name) +{ + struct vduse_vdpa *vdev; + int ret; + + if (dev->vdev) + return -EEXIST; + + vdev = vdpa_alloc_device(struct vduse_vdpa, vdpa, dev->dev, + &vduse_vdpa_config_ops, name, true); + if (IS_ERR(vdev)) + return PTR_ERR(vdev); + + dev->vdev = vdev; + vdev->dev = dev; + vdev->vdpa.dev.dma_mask = &vdev->vdpa.dev.coherent_dma_mask; + ret = dma_set_mask_and_coherent(&vdev->vdpa.dev, DMA_BIT_MASK(64)); + if (ret) { + put_device(&vdev->vdpa.dev); + return ret; + } + set_dma_ops(&vdev->vdpa.dev, &vduse_dev_dma_ops); + vdev->vdpa.dma_dev = &vdev->vdpa.dev; + vdev->vdpa.mdev = &mgmt_dev; + + return 0; +} + +static int vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name) +{ + struct vduse_dev *dev; + int ret; + + mutex_lock(&vduse_lock); + dev = vduse_find_dev(name); + if (!dev || !vduse_dev_is_ready(dev)) { + mutex_unlock(&vduse_lock); + return -EINVAL; + } + ret = vduse_dev_init_vdpa(dev, name); + mutex_unlock(&vduse_lock); + if (ret) + return ret; + + ret = _vdpa_register_device(&dev->vdev->vdpa, dev->vq_num); + if (ret) { + put_device(&dev->vdev->vdpa.dev); + return ret; + } + + return 0; +} + +static void vdpa_dev_del(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev) +{ + _vdpa_unregister_device(dev); +} + +static const struct vdpa_mgmtdev_ops vdpa_dev_mgmtdev_ops = { + .dev_add = vdpa_dev_add, + .dev_del = vdpa_dev_del, +}; + +static struct virtio_device_id id_table[] = { + { VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static struct vdpa_mgmt_dev mgmt_dev = { + .device = &vduse_mgmtdev, + .id_table = id_table, + .ops = &vdpa_dev_mgmtdev_ops, +}; + +static int vduse_mgmtdev_init(void) +{ + int ret; + + ret = device_register(&vduse_mgmtdev); + if (ret) + return ret; + + ret = vdpa_mgmtdev_register(&mgmt_dev); + if (ret) + goto err; + + return 0; +err: + device_unregister(&vduse_mgmtdev); + return ret; +} + +static void vduse_mgmtdev_exit(void) +{ + vdpa_mgmtdev_unregister(&mgmt_dev); + device_unregister(&vduse_mgmtdev); +} + +static int vduse_init(void) +{ + int ret; + struct device *dev; + + vduse_class = class_create(THIS_MODULE, "vduse"); + if (IS_ERR(vduse_class)) + return PTR_ERR(vduse_class); + + vduse_class->devnode = vduse_devnode; + vduse_class->dev_groups = vduse_dev_groups; + + ret = alloc_chrdev_region(&vduse_major, 0, VDUSE_DEV_MAX, "vduse"); + if (ret) + goto err_chardev_region; + + /* /dev/vduse/control */ + cdev_init(&vduse_ctrl_cdev, &vduse_ctrl_fops); + vduse_ctrl_cdev.owner = THIS_MODULE; + ret = cdev_add(&vduse_ctrl_cdev, vduse_major, 1); + if (ret) + goto err_ctrl_cdev; + + dev = device_create(vduse_class, NULL, vduse_major, NULL, "control"); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto err_device; + } + + /* /dev/vduse/$DEVICE */ + cdev_init(&vduse_cdev, &vduse_dev_fops); + vduse_cdev.owner = THIS_MODULE; + ret = cdev_add(&vduse_cdev, MKDEV(MAJOR(vduse_major), 1), + VDUSE_DEV_MAX - 1); + if (ret) + goto err_cdev; + + vduse_irq_wq = alloc_workqueue("vduse-irq", + WQ_HIGHPRI | WQ_SYSFS | WQ_UNBOUND, 0); + if (!vduse_irq_wq) + goto err_wq; + + ret = vduse_domain_init(); + if (ret) + goto err_domain; + + ret = vduse_mgmtdev_init(); + if (ret) + goto err_mgmtdev; + + return 0; +err_mgmtdev: + vduse_domain_exit(); +err_domain: + destroy_workqueue(vduse_irq_wq); +err_wq: + cdev_del(&vduse_cdev); +err_cdev: + device_destroy(vduse_class, vduse_major); +err_device: + cdev_del(&vduse_ctrl_cdev); +err_ctrl_cdev: + unregister_chrdev_region(vduse_major, VDUSE_DEV_MAX); +err_chardev_region: + class_destroy(vduse_class); + return ret; +} +module_init(vduse_init); + +static void vduse_exit(void) +{ + vduse_mgmtdev_exit(); + vduse_domain_exit(); + destroy_workqueue(vduse_irq_wq); + cdev_del(&vduse_cdev); + device_destroy(vduse_class, vduse_major); + cdev_del(&vduse_ctrl_cdev); + unregister_chrdev_region(vduse_major, VDUSE_DEV_MAX); + class_destroy(vduse_class); +} +module_exit(vduse_exit); + +MODULE_LICENSE(DRV_LICENSE); +MODULE_AUTHOR(DRV_AUTHOR); +MODULE_DESCRIPTION(DRV_DESC); diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h new file mode 100644 index 000000000000..7cfe1c1280c0 --- /dev/null +++ b/include/uapi/linux/vduse.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_VDUSE_H_ +#define _UAPI_VDUSE_H_ + +#include + +#define VDUSE_BASE 0x81 + +/* The ioctls for control device (/dev/vduse/control) */ + +#define VDUSE_API_VERSION 0 + +/* + * Get the version of VDUSE API that kernel supported (VDUSE_API_VERSION). + * This is used for future extension. + */ +#define VDUSE_GET_API_VERSION _IOR(VDUSE_BASE, 0x00, __u64) + +/* Set the version of VDUSE API that userspace supported. */ +#define VDUSE_SET_API_VERSION _IOW(VDUSE_BASE, 0x01, __u64) + +/** + * struct vduse_dev_config - basic configuration of a VDUSE device + * @name: VDUSE device name, needs to be NUL terminated + * @vendor_id: virtio vendor id + * @device_id: virtio device id + * @features: virtio features + * @vq_num: the number of virtqueues + * @vq_align: the allocation alignment of virtqueue's metadata + * @reserved: for future use, needs to be initialized to zero + * @config_size: the size of the configuration space + * @config: the buffer of the configuration space + * + * Structure used by VDUSE_CREATE_DEV ioctl to create VDUSE device. + */ +struct vduse_dev_config { +#define VDUSE_NAME_MAX 256 + char name[VDUSE_NAME_MAX]; + __u32 vendor_id; + __u32 device_id; + __u64 features; + __u32 vq_num; + __u32 vq_align; + __u32 reserved[13]; + __u32 config_size; + __u8 config[]; +}; + +/* Create a VDUSE device which is represented by a char device (/dev/vduse/$NAME) */ +#define VDUSE_CREATE_DEV _IOW(VDUSE_BASE, 0x02, struct vduse_dev_config) + +/* + * Destroy a VDUSE device. Make sure there are no more references + * to the char device (/dev/vduse/$NAME). + */ +#define VDUSE_DESTROY_DEV _IOW(VDUSE_BASE, 0x03, char[VDUSE_NAME_MAX]) + +/* The ioctls for VDUSE device (/dev/vduse/$NAME) */ + +/** + * struct vduse_iotlb_entry - entry of IOTLB to describe one IOVA region [start, last] + * @offset: the mmap offset on returned file descriptor + * @start: start of the IOVA region + * @last: last of the IOVA region + * @perm: access permission of the IOVA region + * + * Structure used by VDUSE_IOTLB_GET_FD ioctl to find an overlapped IOVA region. + */ +struct vduse_iotlb_entry { + __u64 offset; + __u64 start; + __u64 last; +#define VDUSE_ACCESS_RO 0x1 +#define VDUSE_ACCESS_WO 0x2 +#define VDUSE_ACCESS_RW 0x3 + __u8 perm; +}; + +/* + * Find the first IOVA region that overlaps with the range [start, last] + * and return the corresponding file descriptor. Return -EINVAL means the + * IOVA region doesn't exist. Caller should set start and last fields. + */ +#define VDUSE_IOTLB_GET_FD _IOWR(VDUSE_BASE, 0x10, struct vduse_iotlb_entry) + +/* + * Get the negotiated virtio features. It's a subset of the features in + * struct vduse_dev_config which can be accepted by virtio driver. It's + * only valid after FEATURES_OK status bit is set. + */ +#define VDUSE_DEV_GET_FEATURES _IOR(VDUSE_BASE, 0x11, __u64) + +/** + * struct vduse_config_data - data used to update configuration space + * @offset: the offset from the beginning of configuration space + * @length: the length to write to configuration space + * @buffer: the buffer used to write from + * + * Structure used by VDUSE_DEV_SET_CONFIG ioctl to update device + * configuration space. + */ +struct vduse_config_data { + __u32 offset; + __u32 length; + __u8 buffer[]; +}; + +/* Set device configuration space */ +#define VDUSE_DEV_SET_CONFIG _IOW(VDUSE_BASE, 0x12, struct vduse_config_data) + +/* + * Inject a config interrupt. It's usually used to notify virtio driver + * that device configuration space has changed. + */ +#define VDUSE_DEV_INJECT_CONFIG_IRQ _IO(VDUSE_BASE, 0x13) + +/** + * struct vduse_vq_config - basic configuration of a virtqueue + * @index: virtqueue index + * @max_size: the max size of virtqueue + * @reserved: for future use, needs to be initialized to zero + * + * Structure used by VDUSE_VQ_SETUP ioctl to setup a virtqueue. + */ +struct vduse_vq_config { + __u32 index; + __u16 max_size; + __u16 reserved[13]; +}; + +/* + * Setup the specified virtqueue. Make sure all virtqueues have been + * configured before the device is attached to vDPA bus. + */ +#define VDUSE_VQ_SETUP _IOW(VDUSE_BASE, 0x14, struct vduse_vq_config) + +/** + * struct vduse_vq_state_split - split virtqueue state + * @avail_index: available index + */ +struct vduse_vq_state_split { + __u16 avail_index; +}; + +/** + * struct vduse_vq_state_packed - packed virtqueue state + * @last_avail_counter: last driver ring wrap counter observed by device + * @last_avail_idx: device available index + * @last_used_counter: device ring wrap counter + * @last_used_idx: used index + */ +struct vduse_vq_state_packed { + __u16 last_avail_counter; + __u16 last_avail_idx; + __u16 last_used_counter; + __u16 last_used_idx; +}; + +/** + * struct vduse_vq_info - information of a virtqueue + * @index: virtqueue index + * @num: the size of virtqueue + * @desc_addr: address of desc area + * @driver_addr: address of driver area + * @device_addr: address of device area + * @split: split virtqueue state + * @packed: packed virtqueue state + * @ready: ready status of virtqueue + * + * Structure used by VDUSE_VQ_GET_INFO ioctl to get virtqueue's information. + */ +struct vduse_vq_info { + __u32 index; + __u32 num; + __u64 desc_addr; + __u64 driver_addr; + __u64 device_addr; + union { + struct vduse_vq_state_split split; + struct vduse_vq_state_packed packed; + }; + __u8 ready; +}; + +/* Get the specified virtqueue's information. Caller should set index field. */ +#define VDUSE_VQ_GET_INFO _IOWR(VDUSE_BASE, 0x15, struct vduse_vq_info) + +/** + * struct vduse_vq_eventfd - eventfd configuration for a virtqueue + * @index: virtqueue index + * @fd: eventfd, -1 means de-assigning the eventfd + * + * Structure used by VDUSE_VQ_SETUP_KICKFD ioctl to setup kick eventfd. + */ +struct vduse_vq_eventfd { + __u32 index; +#define VDUSE_EVENTFD_DEASSIGN -1 + int fd; +}; + +/* + * Setup kick eventfd for specified virtqueue. The kick eventfd is used + * by VDUSE kernel module to notify userspace to consume the avail vring. + */ +#define VDUSE_VQ_SETUP_KICKFD _IOW(VDUSE_BASE, 0x16, struct vduse_vq_eventfd) + +/* + * Inject an interrupt for specific virtqueue. It's used to notify virtio driver + * to consume the used vring. + */ +#define VDUSE_VQ_INJECT_IRQ _IOW(VDUSE_BASE, 0x17, __u32) + +/* The control messages definition for read(2)/write(2) on /dev/vduse/$NAME */ + +/** + * enum vduse_req_type - request type + * @VDUSE_GET_VQ_STATE: get the state for specified virtqueue from userspace + * @VDUSE_SET_STATUS: set the device status + * @VDUSE_UPDATE_IOTLB: Notify userspace to update the memory mapping for + * specified IOVA range via VDUSE_IOTLB_GET_FD ioctl + */ +enum vduse_req_type { + VDUSE_GET_VQ_STATE, + VDUSE_SET_STATUS, + VDUSE_UPDATE_IOTLB, +}; + +/** + * struct vduse_vq_state - virtqueue state + * @index: virtqueue index + * @split: split virtqueue state + * @packed: packed virtqueue state + */ +struct vduse_vq_state { + __u32 index; + union { + struct vduse_vq_state_split split; + struct vduse_vq_state_packed packed; + }; +}; + +/** + * struct vduse_dev_status - device status + * @status: device status + */ +struct vduse_dev_status { + __u8 status; +}; + +/** + * struct vduse_iova_range - IOVA range [start, last] + * @start: start of the IOVA range + * @last: last of the IOVA range + */ +struct vduse_iova_range { + __u64 start; + __u64 last; +}; + +/** + * struct vduse_dev_request - control request + * @type: request type + * @request_id: request id + * @reserved: for future use + * @vq_state: virtqueue state, only index field is available + * @s: device status + * @iova: IOVA range for updating + * @padding: padding + * + * Structure used by read(2) on /dev/vduse/$NAME. + */ +struct vduse_dev_request { + __u32 type; + __u32 request_id; + __u32 reserved[4]; + union { + struct vduse_vq_state vq_state; + struct vduse_dev_status s; + struct vduse_iova_range iova; + __u32 padding[32]; + }; +}; + +/** + * struct vduse_dev_response - response to control request + * @request_id: corresponding request id + * @result: the result of request + * @reserved: for future use, needs to be initialized to zero + * @vq_state: virtqueue state + * @padding: padding + * + * Structure used by write(2) on /dev/vduse/$NAME. + */ +struct vduse_dev_response { + __u32 request_id; +#define VDUSE_REQ_RESULT_OK 0x00 +#define VDUSE_REQ_RESULT_FAILED 0x01 + __u32 result; + __u32 reserved[4]; + union { + struct vduse_vq_state vq_state; + __u32 padding[32]; + }; +}; + +#endif /* _UAPI_VDUSE_H_ */ -- cgit v1.2.3-58-ga151 From 7bc7f61897b66bef78bb5952e3d1e9f3aaf9ccca Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Tue, 31 Aug 2021 18:36:34 +0800 Subject: Documentation: Add documentation for VDUSE VDUSE (vDPA Device in Userspace) is a framework to support implementing software-emulated vDPA devices in userspace. This document is intended to clarify the VDUSE design and usage. Signed-off-by: Xie Yongji Acked-by: Jason Wang Link: https://lore.kernel.org/r/20210831103634.33-14-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin --- Documentation/userspace-api/index.rst | 1 + Documentation/userspace-api/vduse.rst | 233 ++++++++++++++++++++++++++++++++++ drivers/vdpa/vdpa_user/vduse_dev.c | 5 - 3 files changed, 234 insertions(+), 5 deletions(-) create mode 100644 Documentation/userspace-api/vduse.rst (limited to 'Documentation') diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index 0b5eefed027e..c432be070f67 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -27,6 +27,7 @@ place where this information is gathered. iommu media/index sysfs-platform_profile + vduse .. only:: subproject and html diff --git a/Documentation/userspace-api/vduse.rst b/Documentation/userspace-api/vduse.rst new file mode 100644 index 000000000000..42ef59ea5314 --- /dev/null +++ b/Documentation/userspace-api/vduse.rst @@ -0,0 +1,233 @@ +================================== +VDUSE - "vDPA Device in Userspace" +================================== + +vDPA (virtio data path acceleration) device is a device that uses a +datapath which complies with the virtio specifications with vendor +specific control path. vDPA devices can be both physically located on +the hardware or emulated by software. VDUSE is a framework that makes it +possible to implement software-emulated vDPA devices in userspace. And +to make the device emulation more secure, the emulated vDPA device's +control path is handled in the kernel and only the data path is +implemented in the userspace. + +Note that only virtio block device is supported by VDUSE framework now, +which can reduce security risks when the userspace process that implements +the data path is run by an unprivileged user. The support for other device +types can be added after the security issue of corresponding device driver +is clarified or fixed in the future. + +Create/Destroy VDUSE devices +------------------------ + +VDUSE devices are created as follows: + +1. Create a new VDUSE instance with ioctl(VDUSE_CREATE_DEV) on + /dev/vduse/control. + +2. Setup each virtqueue with ioctl(VDUSE_VQ_SETUP) on /dev/vduse/$NAME. + +3. Begin processing VDUSE messages from /dev/vduse/$NAME. The first + messages will arrive while attaching the VDUSE instance to vDPA bus. + +4. Send the VDPA_CMD_DEV_NEW netlink message to attach the VDUSE + instance to vDPA bus. + +VDUSE devices are destroyed as follows: + +1. Send the VDPA_CMD_DEV_DEL netlink message to detach the VDUSE + instance from vDPA bus. + +2. Close the file descriptor referring to /dev/vduse/$NAME. + +3. Destroy the VDUSE instance with ioctl(VDUSE_DESTROY_DEV) on + /dev/vduse/control. + +The netlink messages can be sent via vdpa tool in iproute2 or use the +below sample codes: + +.. code-block:: c + + static int netlink_add_vduse(const char *name, enum vdpa_command cmd) + { + struct nl_sock *nlsock; + struct nl_msg *msg; + int famid; + + nlsock = nl_socket_alloc(); + if (!nlsock) + return -ENOMEM; + + if (genl_connect(nlsock)) + goto free_sock; + + famid = genl_ctrl_resolve(nlsock, VDPA_GENL_NAME); + if (famid < 0) + goto close_sock; + + msg = nlmsg_alloc(); + if (!msg) + goto close_sock; + + if (!genlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, famid, 0, 0, cmd, 0)) + goto nla_put_failure; + + NLA_PUT_STRING(msg, VDPA_ATTR_DEV_NAME, name); + if (cmd == VDPA_CMD_DEV_NEW) + NLA_PUT_STRING(msg, VDPA_ATTR_MGMTDEV_DEV_NAME, "vduse"); + + if (nl_send_sync(nlsock, msg)) + goto close_sock; + + nl_close(nlsock); + nl_socket_free(nlsock); + + return 0; + nla_put_failure: + nlmsg_free(msg); + close_sock: + nl_close(nlsock); + free_sock: + nl_socket_free(nlsock); + return -1; + } + +How VDUSE works +--------------- + +As mentioned above, a VDUSE device is created by ioctl(VDUSE_CREATE_DEV) on +/dev/vduse/control. With this ioctl, userspace can specify some basic configuration +such as device name (uniquely identify a VDUSE device), virtio features, virtio +configuration space, the number of virtqueues and so on for this emulated device. +Then a char device interface (/dev/vduse/$NAME) is exported to userspace for device +emulation. Userspace can use the VDUSE_VQ_SETUP ioctl on /dev/vduse/$NAME to +add per-virtqueue configuration such as the max size of virtqueue to the device. + +After the initialization, the VDUSE device can be attached to vDPA bus via +the VDPA_CMD_DEV_NEW netlink message. Userspace needs to read()/write() on +/dev/vduse/$NAME to receive/reply some control messages from/to VDUSE kernel +module as follows: + +.. code-block:: c + + static int vduse_message_handler(int dev_fd) + { + int len; + struct vduse_dev_request req; + struct vduse_dev_response resp; + + len = read(dev_fd, &req, sizeof(req)); + if (len != sizeof(req)) + return -1; + + resp.request_id = req.request_id; + + switch (req.type) { + + /* handle different types of messages */ + + } + + len = write(dev_fd, &resp, sizeof(resp)); + if (len != sizeof(resp)) + return -1; + + return 0; + } + +There are now three types of messages introduced by VDUSE framework: + +- VDUSE_GET_VQ_STATE: Get the state for virtqueue, userspace should return + avail index for split virtqueue or the device/driver ring wrap counters and + the avail and used index for packed virtqueue. + +- VDUSE_SET_STATUS: Set the device status, userspace should follow + the virtio spec: https://docs.oasis-open.org/virtio/virtio/v1.1/virtio-v1.1.html + to process this message. For example, fail to set the FEATURES_OK device + status bit if the device can not accept the negotiated virtio features + get from the VDUSE_DEV_GET_FEATURES ioctl. + +- VDUSE_UPDATE_IOTLB: Notify userspace to update the memory mapping for specified + IOVA range, userspace should firstly remove the old mapping, then setup the new + mapping via the VDUSE_IOTLB_GET_FD ioctl. + +After DRIVER_OK status bit is set via the VDUSE_SET_STATUS message, userspace is +able to start the dataplane processing as follows: + +1. Get the specified virtqueue's information with the VDUSE_VQ_GET_INFO ioctl, + including the size, the IOVAs of descriptor table, available ring and used ring, + the state and the ready status. + +2. Pass the above IOVAs to the VDUSE_IOTLB_GET_FD ioctl so that those IOVA regions + can be mapped into userspace. Some sample codes is shown below: + +.. code-block:: c + + static int perm_to_prot(uint8_t perm) + { + int prot = 0; + + switch (perm) { + case VDUSE_ACCESS_WO: + prot |= PROT_WRITE; + break; + case VDUSE_ACCESS_RO: + prot |= PROT_READ; + break; + case VDUSE_ACCESS_RW: + prot |= PROT_READ | PROT_WRITE; + break; + } + + return prot; + } + + static void *iova_to_va(int dev_fd, uint64_t iova, uint64_t *len) + { + int fd; + void *addr; + size_t size; + struct vduse_iotlb_entry entry; + + entry.start = iova; + entry.last = iova; + + /* + * Find the first IOVA region that overlaps with the specified + * range [start, last] and return the corresponding file descriptor. + */ + fd = ioctl(dev_fd, VDUSE_IOTLB_GET_FD, &entry); + if (fd < 0) + return NULL; + + size = entry.last - entry.start + 1; + *len = entry.last - iova + 1; + addr = mmap(0, size, perm_to_prot(entry.perm), MAP_SHARED, + fd, entry.offset); + close(fd); + if (addr == MAP_FAILED) + return NULL; + + /* + * Using some data structures such as linked list to store + * the iotlb mapping. The munmap(2) should be called for the + * cached mapping when the corresponding VDUSE_UPDATE_IOTLB + * message is received or the device is reset. + */ + + return addr + iova - entry.start; + } + +3. Setup the kick eventfd for the specified virtqueues with the VDUSE_VQ_SETUP_KICKFD + ioctl. The kick eventfd is used by VDUSE kernel module to notify userspace to + consume the available ring. This is optional since userspace can choose to poll the + available ring instead. + +4. Listen to the kick eventfd (optional) and consume the available ring. The buffer + described by the descriptors in the descriptor table should be also mapped into + userspace via the VDUSE_IOTLB_GET_FD ioctl before accessing. + +5. Inject an interrupt for specific virtqueue with the VDUSE_INJECT_VQ_IRQ ioctl + after the used ring is filled. + +For more details on the uAPI, please see include/uapi/linux/vduse.h. diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index b9b2659408e6..59a93e5b967a 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -486,11 +486,6 @@ 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]; - /* - * TODO: after applying b542e383d8c0 ("eventfd: Make signal recursion protection a task bit") - * replace eventfd_signal_count with eventfd_signal_allowed, and - * drop the previous ("eventfd: Export eventfd_wake_count to modules") - * */ if (eventfd_signal_count()) { schedule_work(&vq->kick); return; -- cgit v1.2.3-58-ga151