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

Pull virtio updates from Michael Tsirkin:

 - A huge patchset supporting vq resize using the new vq reset
   capability

 - Features, fixes, and cleanups all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (88 commits)
  vdpa/mlx5: Fix possible uninitialized return value
  vdpa_sim_blk: add support for discard and write-zeroes
  vdpa_sim_blk: add support for VIRTIO_BLK_T_FLUSH
  vdpa_sim_blk: make vdpasim_blk_check_range usable by other requests
  vdpa_sim_blk: check if sector is 0 for commands other than read or write
  vdpa_sim: Implement suspend vdpa op
  vhost-vdpa: uAPI to suspend the device
  vhost-vdpa: introduce SUSPEND backend feature bit
  vdpa: Add suspend operation
  virtio-blk: Avoid use-after-free on suspend/resume
  virtio_vdpa: support the arg sizes of find_vqs()
  vhost-vdpa: Call ida_simple_remove() when failed
  vDPA: fix 'cast to restricted le16' warnings in vdpa.c
  vDPA: !FEATURES_OK should not block querying device config space
  vDPA/ifcvf: support userspace to query features and MQ of a management device
  vDPA/ifcvf: get_config_size should return a value no greater than dev implementation
  vhost scsi: Allow user to control num virtqueues
  vhost-scsi: Fix max number of virtqueues
  vdpa/mlx5: Support different address spaces for control and data
  vdpa/mlx5: Implement susupend virtqueue callback
  ...

13 files changed, 167 insertions, 19 deletions

diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index 4414ed5b6ed2..9becdc3fa503 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -150,6 +150,14 @@ enum {
 	MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR      = 0x3,
 };
 
+/* This indicates that the object was not created or has already
+ * been desroyed. It is very safe to assume that this object will never
+ * have so many states
+ */
+enum {
+	MLX5_VIRTIO_NET_Q_OBJECT_NONE = 0xffffffff
+};
+
 enum {
 	MLX5_RQTC_LIST_Q_TYPE_RQ            = 0x0,
 	MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q  = 0x1,
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 7c943f0a2fc4..aea79c77db0f 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -597,7 +597,7 @@ struct rproc_subdev {
 /**
  * struct rproc_vring - remoteproc vring state
  * @va:	virtual address
- * @len: length, in bytes
+ * @num: vring size
  * @da: device address
  * @align: vring alignment
  * @notifyid: rproc-specific unique vring index
@@ -606,7 +606,7 @@ struct rproc_subdev {
  */
 struct rproc_vring {
 	void *va;
-	int len;
+	int num;
 	u32 da;
 	u32 align;
 	int notifyid;
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 7b4a13d3bd91..d282f464d2f1 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -218,6 +218,9 @@ struct vdpa_map_file {
  * @reset:			Reset device
  *				@vdev: vdpa device
  *				Returns integer: success (0) or error (< 0)
+ * @suspend:			Suspend or resume the device (optional)
+ *				@vdev: vdpa device
+ *				Returns integer: success (0) or error (< 0)
  * @get_config_size:		Get the size of the configuration space includes
  *				fields that are conditional on feature bits.
  *				@vdev: vdpa device
@@ -319,6 +322,7 @@ struct vdpa_config_ops {
 	u8 (*get_status)(struct vdpa_device *vdev);
 	void (*set_status)(struct vdpa_device *vdev, u8 status);
 	int (*reset)(struct vdpa_device *vdev);
+	int (*suspend)(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);
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index d8fdf170637c..a3f73bb6733e 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -19,6 +19,8 @@
  * @priv: a pointer for the virtqueue implementation to use.
  * @index: the zero-based ordinal number for this queue.
  * @num_free: number of elements we expect to be able to fit.
+ * @num_max: the maximum number of elements supported by the device.
+ * @reset: vq is in reset state or not.
  *
  * A note on @num_free: with indirect buffers, each buffer needs one
  * element in the queue, otherwise a buffer will need one element per
@@ -31,7 +33,9 @@ struct virtqueue {
 	struct virtio_device *vdev;
 	unsigned int index;
 	unsigned int num_free;
+	unsigned int num_max;
 	void *priv;
+	bool reset;
 };
 
 int virtqueue_add_outbuf(struct virtqueue *vq,
@@ -89,6 +93,9 @@ dma_addr_t virtqueue_get_desc_addr(struct virtqueue *vq);
 dma_addr_t virtqueue_get_avail_addr(struct virtqueue *vq);
 dma_addr_t virtqueue_get_used_addr(struct virtqueue *vq);
 
+int virtqueue_resize(struct virtqueue *vq, u32 num,
+		     void (*recycle)(struct virtqueue *vq, void *buf));
+
 /**
  * virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
@@ -133,6 +140,9 @@ bool is_virtio_device(struct device *dev);
 void virtio_break_device(struct virtio_device *dev);
 void __virtio_unbreak_device(struct virtio_device *dev);
 
+void __virtqueue_break(struct virtqueue *_vq);
+void __virtqueue_unbreak(struct virtqueue *_vq);
+
 void virtio_config_changed(struct virtio_device *dev);
 #ifdef CONFIG_PM_SLEEP
 int virtio_device_freeze(struct virtio_device *dev);
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index b47c2e7ed0ee..6adff09f7170 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -55,6 +55,7 @@ struct virtio_shm_region {
  *		include a NULL entry for vqs that do not need a callback
  *	names: array of virtqueue names (mainly for debugging)
  *		include a NULL entry for vqs unused by driver
+ *	sizes: array of virtqueue sizes
  *	Returns 0 on success or error status
  * @del_vqs: free virtqueues found by find_vqs().
  * @synchronize_cbs: synchronize with the virtqueue callbacks (optional)
@@ -78,6 +79,18 @@ struct virtio_shm_region {
  * @set_vq_affinity: set the affinity for a virtqueue (optional).
  * @get_vq_affinity: get the affinity for a virtqueue (optional).
  * @get_shm_region: get a shared memory region based on the index.
+ * @disable_vq_and_reset: reset a queue individually (optional).
+ *	vq: the virtqueue
+ *	Returns 0 on success or error status
+ *	disable_vq_and_reset will guarantee that the callbacks are disabled and
+ *	synchronized.
+ *	Except for the callback, the caller should guarantee that the vring is
+ *	not accessed by any functions of virtqueue.
+ * @enable_vq_after_reset: enable a reset queue
+ *	vq: the virtqueue
+ *	Returns 0 on success or error status
+ *	If disable_vq_and_reset is set, then enable_vq_after_reset must also be
+ *	set.
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {
@@ -91,7 +104,9 @@ struct virtio_config_ops {
 	void (*reset)(struct virtio_device *vdev);
 	int (*find_vqs)(struct virtio_device *, unsigned nvqs,
 			struct virtqueue *vqs[], vq_callback_t *callbacks[],
-			const char * const names[], const bool *ctx,
+			const char * const names[],
+			u32 sizes[],
+			const bool *ctx,
 			struct irq_affinity *desc);
 	void (*del_vqs)(struct virtio_device *);
 	void (*synchronize_cbs)(struct virtio_device *);
@@ -104,6 +119,8 @@ struct virtio_config_ops {
 			int index);
 	bool (*get_shm_region)(struct virtio_device *vdev,
 			       struct virtio_shm_region *region, u8 id);
+	int (*disable_vq_and_reset)(struct virtqueue *vq);
+	int (*enable_vq_after_reset)(struct virtqueue *vq);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
@@ -198,7 +215,7 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev,
 	const char *names[] = { n };
 	struct virtqueue *vq;
 	int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL,
-					 NULL);
+					 NULL, NULL);
 	if (err < 0)
 		return ERR_PTR(err);
 	return vq;
@@ -210,7 +227,8 @@ int virtio_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			const char * const names[],
 			struct irq_affinity *desc)
 {
-	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, desc);
+	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL,
+				      NULL, desc);
 }
 
 static inline
@@ -219,8 +237,20 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs,
 			const char * const names[], const bool *ctx,
 			struct irq_affinity *desc)
 {
-	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, ctx,
-				      desc);
+	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL,
+				      ctx, desc);
+}
+
+static inline
+int virtio_find_vqs_ctx_size(struct virtio_device *vdev, u32 nvqs,
+			     struct virtqueue *vqs[],
+			     vq_callback_t *callbacks[],
+			     const char * const names[],
+			     u32 sizes[],
+			     const bool *ctx, struct irq_affinity *desc)
+{
+	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, sizes,
+				      ctx, desc);
 }
 
 /**
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index eb2bd9b4077d..c4eeb79b0139 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -5,6 +5,13 @@
 #include <linux/pci.h>
 #include <linux/virtio_pci.h>
 
+struct virtio_pci_modern_common_cfg {
+	struct virtio_pci_common_cfg cfg;
+
+	__le16 queue_notify_data;	/* read-write */
+	__le16 queue_reset;		/* read-write */
+};
+
 struct virtio_pci_modern_device {
 	struct pci_dev *pci_dev;
 
@@ -106,4 +113,6 @@ void __iomem * vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev,
 				       u16 index, resource_size_t *pa);
 int vp_modern_probe(struct virtio_pci_modern_device *mdev);
 void vp_modern_remove(struct virtio_pci_modern_device *mdev);
+int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index);
+void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index);
 #endif
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index b485b13fa50b..8b8af1a38991 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -76,16 +76,6 @@ struct virtqueue *vring_create_virtqueue(unsigned int index,
 					 void (*callback)(struct virtqueue *vq),
 					 const char *name);
 
-/* Creates a virtqueue with a custom layout. */
-struct virtqueue *__vring_new_virtqueue(unsigned int index,
-					struct vring vring,
-					struct virtio_device *vdev,
-					bool weak_barriers,
-					bool ctx,
-					bool (*notify)(struct virtqueue *),
-					void (*callback)(struct virtqueue *),
-					const char *name);
-
 /*
  * Creates a virtqueue with a standard layout but a caller-allocated
  * ring.
diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h
index 7cfe1c1280c0..11bd48c72c6c 100644
--- a/include/uapi/linux/vduse.h
+++ b/include/uapi/linux/vduse.h
@@ -210,6 +210,53 @@ struct vduse_vq_eventfd {
  */
 #define VDUSE_VQ_INJECT_IRQ	_IOW(VDUSE_BASE, 0x17, __u32)
 
+/**
+ * struct vduse_iova_umem - userspace memory configuration for one IOVA region
+ * @uaddr: start address of userspace memory, it must be aligned to page size
+ * @iova: start of the IOVA region
+ * @size: size of the IOVA region
+ * @reserved: for future use, needs to be initialized to zero
+ *
+ * Structure used by VDUSE_IOTLB_REG_UMEM and VDUSE_IOTLB_DEREG_UMEM
+ * ioctls to register/de-register userspace memory for IOVA regions
+ */
+struct vduse_iova_umem {
+	__u64 uaddr;
+	__u64 iova;
+	__u64 size;
+	__u64 reserved[3];
+};
+
+/* Register userspace memory for IOVA regions */
+#define VDUSE_IOTLB_REG_UMEM	_IOW(VDUSE_BASE, 0x18, struct vduse_iova_umem)
+
+/* De-register the userspace memory. Caller should set iova and size field. */
+#define VDUSE_IOTLB_DEREG_UMEM	_IOW(VDUSE_BASE, 0x19, struct vduse_iova_umem)
+
+/**
+ * struct vduse_iova_info - information of one IOVA region
+ * @start: start of the IOVA region
+ * @last: last of the IOVA region
+ * @capability: capability of the IOVA regsion
+ * @reserved: for future use, needs to be initialized to zero
+ *
+ * Structure used by VDUSE_IOTLB_GET_INFO ioctl to get information of
+ * one IOVA region.
+ */
+struct vduse_iova_info {
+	__u64 start;
+	__u64 last;
+#define VDUSE_IOVA_CAP_UMEM (1 << 0)
+	__u64 capability;
+	__u64 reserved[3];
+};
+
+/*
+ * Find the first IOVA region that overlaps with the range [start, last]
+ * and return some information on it. Caller should set start and last fields.
+ */
+#define VDUSE_IOTLB_GET_INFO	_IOWR(VDUSE_BASE, 0x1a, struct vduse_iova_info)
+
 /* The control messages definition for read(2)/write(2) on /dev/vduse/$NAME */
 
 /**
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index cab645d4a645..f9f115a7c75b 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -171,4 +171,13 @@
 #define VHOST_VDPA_SET_GROUP_ASID	_IOW(VHOST_VIRTIO, 0x7C, \
 					     struct vhost_vring_state)
 
+/* Suspend a device so it does not process virtqueue requests anymore
+ *
+ * After the return of ioctl the device must preserve all the necessary state
+ * (the virtqueue vring base plus the possible device specific states) that is
+ * required for restoring in the future. The device must not change its
+ * configuration after that point.
+ */
+#define VHOST_VDPA_SUSPEND		_IO(VHOST_VIRTIO, 0x7D)
+
 #endif
diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h
index 391331a10879..53601ce2c20a 100644
--- a/include/uapi/linux/vhost_types.h
+++ b/include/uapi/linux/vhost_types.h
@@ -161,5 +161,7 @@ struct vhost_vdpa_iova_range {
  * message
  */
 #define VHOST_BACKEND_F_IOTLB_ASID  0x3
+/* Device can be suspended */
+#define VHOST_BACKEND_F_SUSPEND  0x4
 
 #endif
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index f0fb0ae021c0..3c05162bc988 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -52,7 +52,7 @@
  * rest are per-device feature bits.
  */
 #define VIRTIO_TRANSPORT_F_START	28
-#define VIRTIO_TRANSPORT_F_END		38
+#define VIRTIO_TRANSPORT_F_END		41
 
 #ifndef VIRTIO_CONFIG_NO_LEGACY
 /* Do we get callbacks when the ring is completely used, even if we've
@@ -98,4 +98,9 @@
  * Does the device support Single Root I/O Virtualization?
  */
 #define VIRTIO_F_SR_IOV			37
+
+/*
+ * This feature indicates that the driver can reset a queue individually.
+ */
+#define VIRTIO_F_RING_RESET		40
 #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 3f55a4215f11..29ced55514d4 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -56,7 +56,7 @@
 #define VIRTIO_NET_F_MQ	22	/* Device supports Receive Flow
 					 * Steering */
 #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
-
+#define VIRTIO_NET_F_NOTF_COAL	53	/* Guest can handle notifications coalescing */
 #define VIRTIO_NET_F_HASH_REPORT  57	/* Supports hash report */
 #define VIRTIO_NET_F_RSS	  60	/* Supports RSS RX steering */
 #define VIRTIO_NET_F_RSC_EXT	  61	/* extended coalescing info */
@@ -355,4 +355,36 @@ struct virtio_net_hash_config {
 #define VIRTIO_NET_CTRL_GUEST_OFFLOADS   5
 #define VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET        0
 
+/*
+ * Control notifications coalescing.
+ *
+ * Request the device to change the notifications coalescing parameters.
+ *
+ * Available with the VIRTIO_NET_F_NOTF_COAL feature bit.
+ */
+#define VIRTIO_NET_CTRL_NOTF_COAL		6
+/*
+ * Set the tx-usecs/tx-max-packets patameters.
+ * tx-usecs - Maximum number of usecs to delay a TX notification.
+ * tx-max-packets - Maximum number of packets to send before a TX notification.
+ */
+struct virtio_net_ctrl_coal_tx {
+	__le32 tx_max_packets;
+	__le32 tx_usecs;
+};
+
+#define VIRTIO_NET_CTRL_NOTF_COAL_TX_SET		0
+
+/*
+ * Set the rx-usecs/rx-max-packets patameters.
+ * rx-usecs - Maximum number of usecs to delay a RX notification.
+ * rx-max-frames - Maximum number of packets to receive before a RX notification.
+ */
+struct virtio_net_ctrl_coal_rx {
+	__le32 rx_max_packets;
+	__le32 rx_usecs;
+};
+
+#define VIRTIO_NET_CTRL_NOTF_COAL_RX_SET		1
+
 #endif /* _UAPI_LINUX_VIRTIO_NET_H */
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 3a86f36d7e3d..f703afc7ad31 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -202,6 +202,8 @@ struct virtio_pci_cfg_cap {
 #define VIRTIO_PCI_COMMON_Q_AVAILHI	44
 #define VIRTIO_PCI_COMMON_Q_USEDLO	48
 #define VIRTIO_PCI_COMMON_Q_USEDHI	52
+#define VIRTIO_PCI_COMMON_Q_NDATA	56
+#define VIRTIO_PCI_COMMON_Q_RESET	58
 
 #endif /* VIRTIO_PCI_NO_MODERN */