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

Pull virtio updates from Michael Tsirkin:

 - vduse driver ("vDPA Device in Userspace") supporting emulated virtio
   block devices

 - virtio-vsock support for end of record with SEQPACKET

 - vdpa: mac and mq support for ifcvf and mlx5

 - vdpa: management netlink for ifcvf

 - virtio-i2c, gpio dt bindings

 - misc fixes and cleanups

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (39 commits)
  Documentation: Add documentation for VDUSE
  vduse: Introduce VDUSE - vDPA Device in Userspace
  vduse: Implement an MMU-based software IOTLB
  vdpa: Support transferring virtual addressing during DMA mapping
  vdpa: factor out vhost_vdpa_pa_map() and vhost_vdpa_pa_unmap()
  vdpa: Add an opaque pointer for vdpa_config_ops.dma_map()
  vhost-iotlb: Add an opaque pointer for vhost IOTLB
  vhost-vdpa: Handle the failure of vdpa_reset()
  vdpa: Add reset callback in vdpa_config_ops
  vdpa: Fix some coding style issues
  file: Export receive_fd() to modules
  eventfd: Export eventfd_wake_count to modules
  iova: Export alloc_iova_fast() and free_iova_fast()
  virtio-blk: remove unneeded "likely" statements
  virtio-balloon: Use virtio_find_vqs() helper
  vdpa: Make use of PFN_PHYS/PFN_UP/PFN_DOWN helper macro
  vsock_test: update message bounds test for MSG_EOR
  af_vsock: rename variables in receive loop
  virtio/vsock: support MSG_EOR bit processing
  vhost/vsock: support MSG_EOR bit processing
  ...

6 files changed, 363 insertions, 27 deletions

diff --git a/include/linux/file.h b/include/linux/file.h
index 2de2e4613d7b..51e830b4fe3a 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -94,6 +94,9 @@ extern void fd_install(unsigned int fd, struct file *file);
 
 extern int __receive_fd(struct file *file, int __user *ufd,
 			unsigned int o_flags);
+
+extern int receive_fd(struct file *file, unsigned int o_flags);
+
 static inline int receive_fd_user(struct file *file, int __user *ufd,
 				  unsigned int o_flags)
 {
@@ -101,10 +104,6 @@ static inline int receive_fd_user(struct file *file, int __user *ufd,
 		return -EFAULT;
 	return __receive_fd(file, ufd, o_flags);
 }
-static inline int receive_fd(struct file *file, unsigned int o_flags)
-{
-	return __receive_fd(file, NULL, o_flags);
-}
 int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags);
 
 extern void flush_delayed_fput(void);
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 8cfe49d201dd..3972ab765de1 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -43,17 +43,17 @@ struct vdpa_vq_state_split {
  * @last_used_idx: used index
  */
 struct vdpa_vq_state_packed {
-        u16	last_avail_counter:1;
-        u16	last_avail_idx:15;
-        u16	last_used_counter:1;
-        u16	last_used_idx:15;
+	u16	last_avail_counter:1;
+	u16	last_avail_idx:15;
+	u16	last_used_counter:1;
+	u16	last_used_idx:15;
 };
 
 struct vdpa_vq_state {
-     union {
-          struct vdpa_vq_state_split split;
-          struct vdpa_vq_state_packed packed;
-     };
+	union {
+		struct vdpa_vq_state_split split;
+		struct vdpa_vq_state_packed packed;
+	};
 };
 
 struct vdpa_mgmt_dev;
@@ -65,6 +65,7 @@ struct vdpa_mgmt_dev;
  * @config: the configuration ops for this device.
  * @index: device index
  * @features_valid: were features initialized? for legacy guests
+ * @use_va: indicate whether virtual address must be used by this device
  * @nvqs: maximum number of supported virtqueues
  * @mdev: management device pointer; caller must setup when registering device as part
  *	  of dev_add() mgmtdev ops callback before invoking _vdpa_register_device().
@@ -75,6 +76,7 @@ struct vdpa_device {
 	const struct vdpa_config_ops *config;
 	unsigned int index;
 	bool features_valid;
+	bool use_va;
 	int nvqs;
 	struct vdpa_mgmt_dev *mdev;
 };
@@ -90,6 +92,16 @@ struct vdpa_iova_range {
 };
 
 /**
+ * Corresponding file area for device memory mapping
+ * @file: vma->vm_file for the mapping
+ * @offset: mapping offset in the vm_file
+ */
+struct vdpa_map_file {
+	struct file *file;
+	u64 offset;
+};
+
+/**
  * struct vdpa_config_ops - operations for configuring a vDPA device.
  * Note: vDPA device drivers are required to implement all of the
  * operations unless it is mentioned to be optional in the following
@@ -131,7 +143,7 @@ struct vdpa_iova_range {
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				@state: pointer to returned state (last_avail_idx)
- * @get_vq_notification: 	Get the notification area for a virtqueue
+ * @get_vq_notification:	Get the notification area for a virtqueue
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				Returns the notifcation area
@@ -171,6 +183,9 @@ struct vdpa_iova_range {
  * @set_status:			Set the device status
  *				@vdev: vdpa device
  *				@status: virtio device status
+ * @reset:			Reset device
+ *				@vdev: vdpa device
+ *				Returns integer: success (0) or error (< 0)
  * @get_config_size:		Get the size of the configuration space
  *				@vdev: vdpa device
  *				Returns size_t: configuration size
@@ -255,6 +270,7 @@ struct vdpa_config_ops {
 	u32 (*get_vendor_id)(struct vdpa_device *vdev);
 	u8 (*get_status)(struct vdpa_device *vdev);
 	void (*set_status)(struct vdpa_device *vdev, u8 status);
+	int (*reset)(struct vdpa_device *vdev);
 	size_t (*get_config_size)(struct vdpa_device *vdev);
 	void (*get_config)(struct vdpa_device *vdev, unsigned int offset,
 			   void *buf, unsigned int len);
@@ -266,7 +282,7 @@ struct vdpa_config_ops {
 	/* DMA ops */
 	int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
 	int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size,
-		       u64 pa, u32 perm);
+		       u64 pa, u32 perm, void *opaque);
 	int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size);
 
 	/* Free device resources */
@@ -275,7 +291,8 @@ struct vdpa_config_ops {
 
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					size_t size, const char *name);
+					size_t size, const char *name,
+					bool use_va);
 
 /**
  * vdpa_alloc_device - allocate and initilaize a vDPA device
@@ -285,15 +302,16 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
  * @name: name of the vdpa device
+ * @use_va: indicate whether virtual address must be used by this device
  *
  * Return allocated data structure or ERR_PTR upon error
  */
-#define vdpa_alloc_device(dev_struct, member, parent, config, name)   \
+#define vdpa_alloc_device(dev_struct, member, parent, config, name, use_va)   \
 			  container_of(__vdpa_alloc_device( \
 				       parent, config, \
 				       sizeof(dev_struct) + \
 				       BUILD_BUG_ON_ZERO(offsetof( \
-				       dev_struct, member)), name), \
+				       dev_struct, member)), name, use_va), \
 				       dev_struct, member)
 
 int vdpa_register_device(struct vdpa_device *vdev, int nvqs);
@@ -348,27 +366,27 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev)
 	return vdev->dma_dev;
 }
 
-static inline void vdpa_reset(struct vdpa_device *vdev)
+static inline int vdpa_reset(struct vdpa_device *vdev)
 {
-        const struct vdpa_config_ops *ops = vdev->config;
+	const struct vdpa_config_ops *ops = vdev->config;
 
 	vdev->features_valid = false;
-        ops->set_status(vdev, 0);
+	return ops->reset(vdev);
 }
 
 static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features)
 {
-        const struct vdpa_config_ops *ops = vdev->config;
+	const struct vdpa_config_ops *ops = vdev->config;
 
 	vdev->features_valid = true;
-        return ops->set_features(vdev, features);
+	return ops->set_features(vdev, features);
 }
 
-
-static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset,
-				   void *buf, unsigned int len)
+static inline void vdpa_get_config(struct vdpa_device *vdev,
+				   unsigned int offset, void *buf,
+				   unsigned int len)
 {
-        const struct vdpa_config_ops *ops = vdev->config;
+	const struct vdpa_config_ops *ops = vdev->config;
 
 	/*
 	 * Config accesses aren't supposed to trigger before features are set.
diff --git a/include/linux/vhost_iotlb.h b/include/linux/vhost_iotlb.h
index 6b09b786a762..2d0e2f52f938 100644
--- a/include/linux/vhost_iotlb.h
+++ b/include/linux/vhost_iotlb.h
@@ -17,6 +17,7 @@ struct vhost_iotlb_map {
 	u32 perm;
 	u32 flags_padding;
 	u64 __subtree_last;
+	void *opaque;
 };
 
 #define VHOST_IOTLB_FLAG_RETIRE 0x1
@@ -29,6 +30,8 @@ struct vhost_iotlb {
 	unsigned int flags;
 };
 
+int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, u64 start, u64 last,
+			      u64 addr, unsigned int perm, void *opaque);
 int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last,
 			  u64 addr, unsigned int perm);
 void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last);
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 <linux/types.h>
+
+#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_ */
diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
index 50d352f5e86f..80d76b75bccd 100644
--- a/include/uapi/linux/virtio_ids.h
+++ b/include/uapi/linux/virtio_ids.h
@@ -54,9 +54,18 @@
 #define VIRTIO_ID_SOUND			25 /* virtio sound */
 #define VIRTIO_ID_FS			26 /* virtio filesystem */
 #define VIRTIO_ID_PMEM			27 /* virtio pmem */
+#define VIRTIO_ID_RPMB			28 /* virtio rpmb */
 #define VIRTIO_ID_MAC80211_HWSIM	29 /* virtio mac80211-hwsim */
+#define VIRTIO_ID_VIDEO_ENCODER		30 /* virtio video encoder */
+#define VIRTIO_ID_VIDEO_DECODER		31 /* virtio video decoder */
 #define VIRTIO_ID_SCMI			32 /* virtio SCMI */
+#define VIRTIO_ID_NITRO_SEC_MOD		33 /* virtio nitro secure module*/
 #define VIRTIO_ID_I2C_ADAPTER		34 /* virtio i2c adapter */
+#define VIRTIO_ID_WATCHDOG		35 /* virtio watchdog */
+#define VIRTIO_ID_CAN			36 /* virtio can */
+#define VIRTIO_ID_DMABUF		37 /* virtio dmabuf */
+#define VIRTIO_ID_PARAM_SERV		38 /* virtio parameter server */
+#define VIRTIO_ID_AUDIO_POLICY		39 /* virtio audio policy */
 #define VIRTIO_ID_BT			40 /* virtio bluetooth */
 #define VIRTIO_ID_GPIO			41 /* virtio gpio */
 
diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h
index 3dd3555b2740..64738838bee5 100644
--- a/include/uapi/linux/virtio_vsock.h
+++ b/include/uapi/linux/virtio_vsock.h
@@ -97,7 +97,8 @@ enum virtio_vsock_shutdown {
 
 /* VIRTIO_VSOCK_OP_RW flags values */
 enum virtio_vsock_rw {
-	VIRTIO_VSOCK_SEQ_EOR = 1,
+	VIRTIO_VSOCK_SEQ_EOM = 1,
+	VIRTIO_VSOCK_SEQ_EOR = 2,
 };
 
 #endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */