Merge branch 'linux-next' of https://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git

2 files changed, 150 insertions, 15 deletions

diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 10dcf016bfb0..eb71b91324ef 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -9,6 +9,7 @@
  */
 
 #include "linux/virtio_net.h"
+#include <linux/bits.h>
 #include <linux/cleanup.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -51,6 +52,10 @@
 
 #define IRQ_UNBOUND -1
 
+/* Supported VDUSE features */
+static const uint64_t vduse_features = BIT_U64(VDUSE_F_QUEUE_READY) |
+				       BIT_U64(VDUSE_F_SUSPEND);
+
 /*
  * VDUSE instance have not asked the vduse API version, so assume 0.
  *
@@ -80,6 +85,7 @@ struct vduse_virtqueue {
 	int irq_effective_cpu;
 	struct cpumask irq_affinity;
 	struct kobject kobj;
+	struct vduse_dev *dev;
 };
 
 struct vduse_dev;
@@ -116,6 +122,7 @@ struct vduse_dev {
 	char *name;
 	struct mutex lock;
 	spinlock_t msg_lock;
+	u64 vduse_features;
 	u64 msg_unique;
 	u32 msg_timeout;
 	wait_queue_head_t waitq;
@@ -128,6 +135,7 @@ struct vduse_dev {
 	int minor;
 	bool broken;
 	bool connected;
+	bool suspended;
 	u64 api_version;
 	u64 device_features;
 	u64 driver_features;
@@ -163,6 +171,7 @@ static DEFINE_IDR(vduse_idr);
 
 static dev_t vduse_major;
 static struct cdev vduse_ctrl_cdev;
+static const struct device *vduse_ctrl_dev;
 static struct cdev vduse_cdev;
 static struct workqueue_struct *vduse_irq_wq;
 static struct workqueue_struct *vduse_irq_bound_wq;
@@ -496,6 +505,7 @@ static void vduse_dev_reset(struct vduse_dev *dev)
 
 	down_write(&dev->rwsem);
 
+	dev->suspended = false;
 	dev->status = 0;
 	dev->driver_features = 0;
 	dev->generation++;
@@ -550,16 +560,18 @@ static int vduse_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 idx,
 
 static void vduse_vq_kick(struct vduse_virtqueue *vq)
 {
-	spin_lock(&vq->kick_lock);
+	guard(rwsem_read)(&vq->dev->rwsem);
+	if (vq->dev->suspended)
+		return;
+
+	guard(spinlock)(&vq->kick_lock);
 	if (!vq->ready)
-		goto unlock;
+		return;
 
 	if (vq->kickfd)
 		eventfd_signal(vq->kickfd);
 	else
 		vq->kicked = true;
-unlock:
-	spin_unlock(&vq->kick_lock);
 }
 
 static void vduse_vq_kick_work(struct work_struct *work)
@@ -619,8 +631,29 @@ static void vduse_vdpa_set_vq_ready(struct vdpa_device *vdpa,
 {
 	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
 	struct vduse_virtqueue *vq = dev->vqs[idx];
+	struct vduse_dev_msg msg = { 0 };
+	int r;
 
 	vq->ready = ready;
+
+	if (!(dev->vduse_features & BIT_U64(VDUSE_F_QUEUE_READY)))
+		return;
+
+	msg.req.type = VDUSE_SET_VQ_READY;
+	msg.req.vq_ready.num = idx;
+	msg.req.vq_ready.ready = !!ready;
+
+	r = vduse_dev_msg_sync(dev, &msg);
+
+	if (r < 0) {
+		dev_dbg(&vdpa->dev, "device refuses to set vq %u ready %u",
+			idx, ready);
+
+		/* We can't do better than break the device in this case */
+		spin_lock(&dev->msg_lock);
+		vduse_dev_broken(dev);
+		spin_unlock(&dev->msg_lock);
+	}
 }
 
 static bool vduse_vdpa_get_vq_ready(struct vdpa_device *vdpa, u16 idx)
@@ -891,6 +924,27 @@ static int vduse_vdpa_set_map(struct vdpa_device *vdpa,
 	return 0;
 }
 
+static int vduse_vdpa_suspend(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	struct vduse_dev_msg msg = { 0 };
+	int ret;
+
+	msg.req.type = VDUSE_SUSPEND;
+
+	ret = vduse_dev_msg_sync(dev, &msg);
+	if (ret == 0) {
+		scoped_guard(rwsem_write, &dev->rwsem)
+			dev->suspended = true;
+
+		cancel_work_sync(&dev->inject);
+		for (u32 i = 0; i < dev->vq_num; i++)
+			cancel_work_sync(&dev->vqs[i]->inject);
+	}
+
+	return ret;
+}
+
 static void vduse_vdpa_free(struct vdpa_device *vdpa)
 {
 	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
@@ -932,6 +986,41 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = {
 	.free			= vduse_vdpa_free,
 };
 
+static const struct vdpa_config_ops vduse_vdpa_config_ops_with_suspend = {
+	.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,
+	.get_vq_size		= vduse_vdpa_get_vq_size,
+	.get_vq_group		= vduse_get_vq_group,
+	.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_device_features	= vduse_vdpa_get_device_features,
+	.set_driver_features	= vduse_vdpa_set_driver_features,
+	.get_driver_features	= vduse_vdpa_get_driver_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,
+	.set_vq_affinity	= vduse_vdpa_set_vq_affinity,
+	.get_vq_affinity	= vduse_vdpa_get_vq_affinity,
+	.reset			= vduse_vdpa_reset,
+	.set_map		= vduse_vdpa_set_map,
+	.set_group_asid		= vduse_set_group_asid,
+	.get_vq_map		= vduse_get_vq_map,
+	.suspend		= vduse_vdpa_suspend,
+	.free			= vduse_vdpa_free,
+};
+
 static void vduse_dev_sync_single_for_device(union virtio_map token,
 					     dma_addr_t dma_addr, size_t size,
 					     enum dma_data_direction dir)
@@ -1143,6 +1232,10 @@ static void vduse_dev_irq_inject(struct work_struct *work)
 {
 	struct vduse_dev *dev = container_of(work, struct vduse_dev, inject);
 
+	guard(rwsem_read)(&dev->rwsem);
+	if (dev->suspended)
+		return;
+
 	spin_lock_bh(&dev->irq_lock);
 	if (dev->config_cb.callback)
 		dev->config_cb.callback(dev->config_cb.private);
@@ -1154,6 +1247,10 @@ static void vduse_vq_irq_inject(struct work_struct *work)
 	struct vduse_virtqueue *vq = container_of(work,
 					struct vduse_virtqueue, inject);
 
+	guard(rwsem_read)(&vq->dev->rwsem);
+	if (vq->dev->suspended)
+		return;
+
 	spin_lock_bh(&vq->irq_lock);
 	if (vq->ready && vq->cb.callback)
 		vq->cb.callback(vq->cb.private);
@@ -1183,9 +1280,9 @@ static int vduse_dev_queue_irq_work(struct vduse_dev *dev,
 {
 	int ret = -EINVAL;
 
-	down_read(&dev->rwsem);
-	if (!(dev->status & VIRTIO_CONFIG_S_DRIVER_OK))
-		goto unlock;
+	guard(rwsem_read)(&dev->rwsem);
+	if (dev->suspended || !(dev->status & VIRTIO_CONFIG_S_DRIVER_OK))
+		return ret;
 
 	ret = 0;
 	if (irq_effective_cpu == IRQ_UNBOUND)
@@ -1193,8 +1290,6 @@ static int vduse_dev_queue_irq_work(struct vduse_dev *dev,
 	else
 		queue_work_on(irq_effective_cpu,
 			      vduse_irq_bound_wq, irq_work);
-unlock:
-	up_read(&dev->rwsem);
 
 	return ret;
 }
@@ -1948,6 +2043,7 @@ static int vduse_dev_init_vqs(struct vduse_dev *dev, u32 vq_align, u32 vq_num)
 		}
 
 		dev->vqs[i]->index = i;
+		dev->vqs[i]->dev = dev;
 		dev->vqs[i]->irq_effective_cpu = IRQ_UNBOUND;
 		INIT_WORK(&dev->vqs[i]->inject, vduse_vq_irq_inject);
 		INIT_WORK(&dev->vqs[i]->kick, vduse_vq_kick_work);
@@ -2210,6 +2306,9 @@ static int vduse_create_dev(struct vduse_dev_config *config,
 	dev->device_features = config->features;
 	dev->device_id = config->device_id;
 	dev->vendor_id = config->vendor_id;
+	dev->vduse_features = config->vduse_features;
+	dev_dbg(vduse_ctrl_dev, "Creating device %s with features 0x%llx",
+		config->name, config->vduse_features);
 
 	dev->nas = (dev->api_version < VDUSE_API_VERSION_1) ? 1 : config->nas;
 	dev->as = kzalloc_objs(dev->as[0], dev->nas);
@@ -2341,6 +2440,10 @@ static long vduse_ioctl(struct file *file, unsigned int cmd,
 		ret = vduse_destroy_dev(name);
 		break;
 	}
+	case VDUSE_GET_FEATURES:
+		ret = put_user(vduse_features, (u64 __user *)argp);
+		break;
+
 	default:
 		ret = -EINVAL;
 		break;
@@ -2391,12 +2494,18 @@ static struct vduse_mgmt_dev *vduse_mgmt;
 static int vduse_dev_init_vdpa(struct vduse_dev *dev, const char *name)
 {
 	struct vduse_vdpa *vdev;
+	const struct vdpa_config_ops *ops;
 
 	if (dev->vdev)
 		return -EEXIST;
 
+	if (dev->vduse_features & BIT_U64(VDUSE_F_SUSPEND))
+		ops = &vduse_vdpa_config_ops_with_suspend;
+	else
+		ops = &vduse_vdpa_config_ops;
+
 	vdev = vdpa_alloc_device(struct vduse_vdpa, vdpa, dev->dev,
-				 &vduse_vdpa_config_ops, &vduse_map_ops,
+				 ops, &vduse_map_ops,
 				 dev->ngroups, dev->nas, name, true);
 	if (IS_ERR(vdev))
 		return PTR_ERR(vdev);
@@ -2531,7 +2640,6 @@ static void vduse_mgmtdev_exit(void)
 static int vduse_init(void)
 {
 	int ret;
-	struct device *dev;
 
 	ret = class_register(&vduse_class);
 	if (ret)
@@ -2548,9 +2656,9 @@ static int vduse_init(void)
 	if (ret)
 		goto err_ctrl_cdev;
 
-	dev = device_create(&vduse_class, NULL, vduse_major, NULL, "control");
-	if (IS_ERR(dev)) {
-		ret = PTR_ERR(dev);
+	vduse_ctrl_dev = device_create(&vduse_class, NULL, vduse_major, NULL, "control");
+	if (IS_ERR(vduse_ctrl_dev)) {
+		ret = PTR_ERR(vduse_ctrl_dev);
 		goto err_device;
 	}
 
diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h
index 361eea511c21..8c616895c511 100644
--- a/include/uapi/linux/vduse.h
+++ b/include/uapi/linux/vduse.h
@@ -14,6 +14,12 @@
 
 #define VDUSE_API_VERSION_1	1
 
+/* The VDUSE instance expects a request for vq ready */
+#define VDUSE_F_QUEUE_READY	0
+
+/* The VDUSE instance expects a request for suspend */
+#define VDUSE_F_SUSPEND		1
+
 /*
  * Get the version of VDUSE API that kernel supported (VDUSE_API_VERSION).
  * This is used for future extension.
@@ -33,6 +39,7 @@
  * @vq_align: the allocation alignment of virtqueue's metadata
  * @ngroups: number of vq groups that VDUSE device declares
  * @nas: number of address spaces that VDUSE device declares
+ * @vduse_features: VDUSE features
  * @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
@@ -49,7 +56,8 @@ struct vduse_dev_config {
 	__u32 vq_align;
 	__u32 ngroups; /* if VDUSE_API_VERSION >= 1 */
 	__u32 nas; /* if VDUSE_API_VERSION >= 1 */
-	__u32 reserved[11];
+	__u64 vduse_features; /* if VDUSE_GET_FEATURES is not EINVAL */
+	__u32 reserved[9];
 	__u32 config_size;
 	__u8 config[];
 };
@@ -63,6 +71,9 @@ struct vduse_dev_config {
  */
 #define VDUSE_DESTROY_DEV	_IOW(VDUSE_BASE, 0x03, char[VDUSE_NAME_MAX])
 
+/* Get the VDUSE supported features */
+#define VDUSE_GET_FEATURES	_IOR(VDUSE_BASE, 0x04, __u64)
+
 /* The ioctls for VDUSE device (/dev/vduse/$NAME) */
 
 /**
@@ -325,6 +336,8 @@ enum vduse_req_type {
 	VDUSE_SET_STATUS,
 	VDUSE_UPDATE_IOTLB,
 	VDUSE_SET_VQ_GROUP_ASID,
+	VDUSE_SET_VQ_READY,
+	VDUSE_SUSPEND,
 };
 
 /**
@@ -373,6 +386,15 @@ struct vduse_iova_range_v2 {
 };
 
 /**
+ * struct vduse_vq_ready - Virtqueue ready request message
+ * @num: Virtqueue number
+ */
+struct vduse_vq_ready {
+	__u32 num;
+	__u32 ready;
+};
+
+/**
  * struct vduse_dev_request - control request
  * @type: request type
  * @request_id: request id
@@ -382,6 +404,7 @@ struct vduse_iova_range_v2 {
  * @iova: IOVA range for updating
  * @iova_v2: IOVA range for updating if API_VERSION >= 1
  * @vq_group_asid: ASID of a virtqueue group
+ * @vq_ready: Virtqueue ready request
  * @padding: padding
  *
  * Structure used by read(2) on /dev/vduse/$NAME.
@@ -399,6 +422,10 @@ struct vduse_dev_request {
 		 */
 		struct vduse_iova_range_v2 iova_v2;
 		struct vduse_vq_group_asid vq_group_asid;
+
+		/* Only if VDUSE_F_QUEUE_READY is negotiated */
+		struct vduse_vq_ready vq_ready;
+
 		__u32 padding[32];
 	};
 };