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

Pull virtio updates from Michael Tsirkin:
 "vhost,virtio,vdpa: features, fixes, cleanups.

  vdpa/mlx5:
   - VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK
   - new maintainer

  vdpa:
   - support for vq descriptor mappings
   - decouple reset of iotlb mapping from device reset

  and fixes, cleanups all over the place"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (34 commits)
  vdpa_sim: implement .reset_map support
  vdpa/mlx5: implement .reset_map driver op
  vhost-vdpa: clean iotlb map during reset for older userspace
  vdpa: introduce .compat_reset operation callback
  vhost-vdpa: introduce IOTLB_PERSIST backend feature bit
  vhost-vdpa: reset vendor specific mapping to initial state in .release
  vdpa: introduce .reset_map operation callback
  virtio_pci: add check for common cfg size
  virtio-blk: fix implicit overflow on virtio_max_dma_size
  virtio_pci: add build offset check for the new common cfg items
  virtio: add definition of VIRTIO_F_NOTIF_CONFIG_DATA feature bit
  vduse: make vduse_class constant
  vhost-scsi: Spelling s/preceeding/preceding/g
  virtio: kdoc for struct virtio_pci_modern_device
  vdpa: Update sysfs ABI documentation
  MAINTAINERS: Add myself as mlx5_vdpa driver
  virtio-balloon: correct the comment of virtballoon_migratepage()
  mlx5_vdpa: offer VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK
  vdpa/mlx5: Update cvq iotlb mapping on ASID change
  vdpa/mlx5: Make iotlb helper functions more generic
  ...

7 files changed, 95 insertions, 16 deletions

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 4df6d1c12437..6f3631425f38 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1232,7 +1232,13 @@ struct mlx5_ifc_virtio_emulation_cap_bits {
 	u8         max_emulated_devices[0x8];
 	u8         max_num_virtio_queues[0x18];
 
-	u8         reserved_at_a0[0x60];
+	u8         reserved_at_a0[0x20];
+
+	u8	   reserved_at_c0[0x13];
+	u8         desc_group_mkey_supported[0x1];
+	u8         reserved_at_d4[0xc];
+
+	u8         reserved_at_e0[0x20];
 
 	u8         umem_1_buffer_param_a[0x20];
 
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index 9becdc3fa503..b86d51a855f6 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -74,7 +74,11 @@ struct mlx5_ifc_virtio_q_bits {
 	u8    reserved_at_320[0x8];
 	u8    pd[0x18];
 
-	u8    reserved_at_340[0xc0];
+	u8    reserved_at_340[0x20];
+
+	u8    desc_group_mkey[0x20];
+
+	u8    reserved_at_380[0x80];
 };
 
 struct mlx5_ifc_virtio_net_q_object_bits {
@@ -141,6 +145,7 @@ enum {
 	MLX5_VIRTQ_MODIFY_MASK_STATE                    = (u64)1 << 0,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
+	MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY          = (u64)1 << 14,
 };
 
 enum {
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 0e652026b776..db15ac07f8a6 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -204,6 +204,16 @@ struct vdpa_map_file {
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				Returns u32: group id for this virtqueue
+ * @get_vq_desc_group:		Get the group id for the descriptor table of
+ *				a specific virtqueue (optional)
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				Returns u32: group id for the descriptor table
+ *				portion of this virtqueue. Could be different
+ *				than the one from @get_vq_group, in which case
+ *				the access to the descriptor table can be
+ *				confined to a separate asid, isolating from
+ *				the virtqueue's buffer address access.
  * @get_device_features:	Get virtio features supported by the device
  *				@vdev: vdpa device
  *				Returns the virtio features support by the
@@ -242,6 +252,17 @@ struct vdpa_map_file {
  * @reset:			Reset device
  *				@vdev: vdpa device
  *				Returns integer: success (0) or error (< 0)
+ * @compat_reset:		Reset device with compatibility quirks to
+ *				accommodate older userspace. Only needed by
+ *				parent driver which used to have bogus reset
+ *				behaviour, and has to maintain such behaviour
+ *				for compatibility with older userspace.
+ *				Historically compliant driver only has to
+ *				implement .reset, Historically non-compliant
+ *				driver should implement both.
+ *				@vdev: vdpa device
+ *				@flags: compatibility quirks for reset
+ *				Returns integer: success (0) or error (< 0)
  * @suspend:			Suspend the device (optional)
  *				@vdev: vdpa device
  *				Returns integer: success (0) or error (< 0)
@@ -317,6 +338,15 @@ struct vdpa_map_file {
  *				@iova: iova to be unmapped
  *				@size: size of the area
  *				Returns integer: success (0) or error (< 0)
+ * @reset_map:			Reset device memory mapping to the default
+ *				state (optional)
+ *				Needed for devices that are using device
+ *				specific DMA translation and prefer mapping
+ *				to be decoupled from the virtio life cycle,
+ *				i.e. device .reset op does not reset mapping
+ *				@vdev: vdpa device
+ *				@asid: address space identifier
+ *				Returns integer: success (0) or error (< 0)
  * @get_vq_dma_dev:		Get the dma device for a specific
  *				virtqueue (optional)
  *				@vdev: vdpa device
@@ -360,6 +390,7 @@ struct vdpa_config_ops {
 	/* Device ops */
 	u32 (*get_vq_align)(struct vdpa_device *vdev);
 	u32 (*get_vq_group)(struct vdpa_device *vdev, u16 idx);
+	u32 (*get_vq_desc_group)(struct vdpa_device *vdev, u16 idx);
 	u64 (*get_device_features)(struct vdpa_device *vdev);
 	u64 (*get_backend_features)(const struct vdpa_device *vdev);
 	int (*set_driver_features)(struct vdpa_device *vdev, u64 features);
@@ -373,6 +404,8 @@ 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 (*compat_reset)(struct vdpa_device *vdev, u32 flags);
+#define VDPA_RESET_F_CLEAN_MAP 1
 	int (*suspend)(struct vdpa_device *vdev);
 	int (*resume)(struct vdpa_device *vdev);
 	size_t (*get_config_size)(struct vdpa_device *vdev);
@@ -394,6 +427,7 @@ struct vdpa_config_ops {
 		       u64 iova, u64 size, u64 pa, u32 perm, void *opaque);
 	int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid,
 			 u64 iova, u64 size);
+	int (*reset_map)(struct vdpa_device *vdev, unsigned int asid);
 	int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group,
 			      unsigned int asid);
 	struct device *(*get_vq_dma_dev)(struct vdpa_device *vdev, u16 idx);
@@ -485,14 +519,17 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev)
 	return vdev->dma_dev;
 }
 
-static inline int vdpa_reset(struct vdpa_device *vdev)
+static inline int vdpa_reset(struct vdpa_device *vdev, u32 flags)
 {
 	const struct vdpa_config_ops *ops = vdev->config;
 	int ret;
 
 	down_write(&vdev->cf_lock);
 	vdev->features_valid = false;
-	ret = ops->reset(vdev);
+	if (ops->compat_reset && flags)
+		ret = ops->compat_reset(vdev, flags);
+	else
+		ret = ops->reset(vdev);
 	up_write(&vdev->cf_lock);
 	return ret;
 }
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index 067ac1d789bc..d0f2797420f7 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -12,37 +12,48 @@ struct virtio_pci_modern_common_cfg {
 	__le16 queue_reset;		/* read-write */
 };
 
+/**
+ * struct virtio_pci_modern_device - info for modern PCI virtio
+ * @pci_dev:	    Ptr to the PCI device struct
+ * @common:	    Position of the common capability in the PCI config
+ * @device:	    Device-specific data (non-legacy mode)
+ * @notify_base:    Base of vq notifications (non-legacy mode)
+ * @notify_pa:	    Physical base of vq notifications
+ * @isr:	    Where to read and clear interrupt
+ * @notify_len:	    So we can sanity-check accesses
+ * @device_len:	    So we can sanity-check accesses
+ * @notify_map_cap: Capability for when we need to map notifications per-vq
+ * @notify_offset_multiplier: Multiply queue_notify_off by this value
+ *                            (non-legacy mode).
+ * @modern_bars:    Bitmask of BARs
+ * @id:		    Device and vendor id
+ * @device_id_check: Callback defined before vp_modern_probe() to be used to
+ *		    verify the PCI device is a vendor's expected device rather
+ *		    than the standard virtio PCI device
+ *		    Returns the found device id or ERRNO
+ * @dma_mask:	    Optional mask instead of the traditional DMA_BIT_MASK(64),
+ *		    for vendor devices with DMA space address limitations
+ */
 struct virtio_pci_modern_device {
 	struct pci_dev *pci_dev;
 
 	struct virtio_pci_common_cfg __iomem *common;
-	/* Device-specific data (non-legacy mode)  */
 	void __iomem *device;
-	/* Base of vq notifications (non-legacy mode). */
 	void __iomem *notify_base;
-	/* Physical base of vq notifications */
 	resource_size_t notify_pa;
-	/* Where to read and clear interrupt */
 	u8 __iomem *isr;
 
-	/* So we can sanity-check accesses. */
 	size_t notify_len;
 	size_t device_len;
+	size_t common_len;
 
-	/* Capability for when we need to map notifications per-vq. */
 	int notify_map_cap;
 
-	/* Multiply queue_notify_off by this value. (non-legacy mode). */
 	u32 notify_offset_multiplier;
-
 	int modern_bars;
-
 	struct virtio_device_id id;
 
-	/* optional check for vendor virtio device, returns dev_id or -ERRNO */
 	int (*device_id_check)(struct pci_dev *pdev);
-
-	/* optional mask for devices with limited DMA space */
 	u64 dma_mask;
 };
 
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index f5c48b61ab62..649560c685f1 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -219,4 +219,12 @@
  */
 #define VHOST_VDPA_RESUME		_IO(VHOST_VIRTIO, 0x7E)
 
+/* Get the group for the descriptor table including driver & device areas
+ * of a virtqueue: read index, write group in num.
+ * The virtqueue index is stored in the index field of vhost_vring_state.
+ * The group ID of the descriptor table for this specific virtqueue
+ * is returned via num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_GET_VRING_DESC_GROUP	_IOWR(VHOST_VIRTIO, 0x7F,	\
+					      struct vhost_vring_state)
 #endif
diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h
index 2d827d22cd99..d7656908f730 100644
--- a/include/uapi/linux/vhost_types.h
+++ b/include/uapi/linux/vhost_types.h
@@ -185,5 +185,12 @@ struct vhost_vdpa_iova_range {
  * DRIVER_OK
  */
 #define VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK  0x6
+/* Device may expose the virtqueue's descriptor area, driver area and
+ * device area to a different group for ASID binding than where its
+ * buffers may reside. Requires VHOST_BACKEND_F_IOTLB_ASID.
+ */
+#define VHOST_BACKEND_F_DESC_ASID    0x7
+/* IOTLB don't flush memory mapping across device reset */
+#define VHOST_BACKEND_F_IOTLB_PERSIST  0x8
 
 #endif
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 2c712c654165..8881aea60f6f 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -105,6 +105,11 @@
  */
 #define VIRTIO_F_NOTIFICATION_DATA	38
 
+/* This feature indicates that the driver uses the data provided by the device
+ * as a virtqueue identifier in available buffer notifications.
+ */
+#define VIRTIO_F_NOTIF_CONFIG_DATA	39
+
 /*
  * This feature indicates that the driver can reset a queue individually.
  */