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

Pull virtio updates from Michael Tsirkin:
 "A bunch of new drivers including vdpa support for block and
  virtio-vdpa.

  Beginning of vq kick (aka doorbell) mapping support.

  Misc fixes"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (40 commits)
  virtio_pci_modern: correct sparse tags for notify
  virtio_pci_modern: __force cast the notify mapping
  vDPA/ifcvf: get_config_size should return dev specific config size
  vDPA/ifcvf: enable Intel C5000X-PL virtio-block for vDPA
  vDPA/ifcvf: deduce VIRTIO device ID when probe
  vdpa_sim_blk: add support for vdpa management tool
  vdpa_sim_blk: handle VIRTIO_BLK_T_GET_ID
  vdpa_sim_blk: implement ramdisk behaviour
  vdpa: add vdpa simulator for block device
  vhost/vdpa: Remove the restriction that only supports virtio-net devices
  vhost/vdpa: use get_config_size callback in vhost_vdpa_config_validate()
  vdpa: add get_config_size callback in vdpa_config_ops
  vdpa_sim: cleanup kiovs in vdpasim_free()
  vringh: add vringh_kiov_length() helper
  vringh: implement vringh_kiov_advance()
  vringh: explain more about cleaning riov and wiov
  vringh: reset kiov 'consumed' field in __vringh_iov()
  vringh: add 'iotlb_lock' to synchronize iotlb accesses
  vdpa_sim: use iova module to allocate IOVA addresses
  vDPA/ifcvf: deduce VIRTIO device ID from pdev ids
  ...

2 files changed, 55 insertions, 30 deletions

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index f5ebe008a28b..fb41db3da611 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -16,12 +16,12 @@
 #include <linux/cdev.h>
 #include <linux/device.h>
 #include <linux/mm.h>
+#include <linux/slab.h>
 #include <linux/iommu.h>
 #include <linux/uuid.h>
 #include <linux/vdpa.h>
 #include <linux/nospec.h>
 #include <linux/vhost.h>
-#include <linux/virtio_net.h>
 
 #include "vhost.h"
 
@@ -188,13 +188,8 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
 static int vhost_vdpa_config_validate(struct vhost_vdpa *v,
 				      struct vhost_vdpa_config *c)
 {
-	long size = 0;
-
-	switch (v->virtio_id) {
-	case VIRTIO_ID_NET:
-		size = sizeof(struct virtio_net_config);
-		break;
-	}
+	struct vdpa_device *vdpa = v->vdpa;
+	long size = vdpa->config->get_config_size(vdpa);
 
 	if (c->len == 0)
 		return -EINVAL;
@@ -989,6 +984,7 @@ static int vhost_vdpa_mmap(struct file *file, struct vm_area_struct *vma)
 	if (vma->vm_end - vma->vm_start != notify.size)
 		return -ENOTSUPP;
 
+	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_ops = &vhost_vdpa_vm_ops;
 	return 0;
 }
@@ -1023,10 +1019,6 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
 	int minor;
 	int r;
 
-	/* Currently, we only accept the network devices. */
-	if (ops->get_device_id(vdpa) != VIRTIO_ID_NET)
-		return -ENOTSUPP;
-
 	v = kzalloc(sizeof(*v), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!v)
 		return -ENOMEM;
diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index 85d85faba058..4af8fa259d65 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -75,6 +75,34 @@ static inline int __vringh_get_head(const struct vringh *vrh,
 	return head;
 }
 
+/**
+ * vringh_kiov_advance - skip bytes from vring_kiov
+ * @iov: an iov passed to vringh_getdesc_*() (updated as we consume)
+ * @len: the maximum length to advance
+ */
+void vringh_kiov_advance(struct vringh_kiov *iov, size_t len)
+{
+	while (len && iov->i < iov->used) {
+		size_t partlen = min(iov->iov[iov->i].iov_len, len);
+
+		iov->consumed += partlen;
+		iov->iov[iov->i].iov_len -= partlen;
+		iov->iov[iov->i].iov_base += partlen;
+
+		if (!iov->iov[iov->i].iov_len) {
+			/* Fix up old iov element then increment. */
+			iov->iov[iov->i].iov_len = iov->consumed;
+			iov->iov[iov->i].iov_base -= iov->consumed;
+
+			iov->consumed = 0;
+			iov->i++;
+		}
+
+		len -= partlen;
+	}
+}
+EXPORT_SYMBOL(vringh_kiov_advance);
+
 /* Copy some bytes to/from the iovec.  Returns num copied. */
 static inline ssize_t vringh_iov_xfer(struct vringh *vrh,
 				      struct vringh_kiov *iov,
@@ -95,19 +123,8 @@ static inline ssize_t vringh_iov_xfer(struct vringh *vrh,
 		done += partlen;
 		len -= partlen;
 		ptr += partlen;
-		iov->consumed += partlen;
-		iov->iov[iov->i].iov_len -= partlen;
-		iov->iov[iov->i].iov_base += partlen;
 
-		if (!iov->iov[iov->i].iov_len) {
-			/* Fix up old iov element then increment. */
-			iov->iov[iov->i].iov_len = iov->consumed;
-			iov->iov[iov->i].iov_base -= iov->consumed;
-
-			
-			iov->consumed = 0;
-			iov->i++;
-		}
+		vringh_kiov_advance(iov, partlen);
 	}
 	return done;
 }
@@ -290,9 +307,9 @@ __vringh_iov(struct vringh *vrh, u16 i,
 		return -EINVAL;
 
 	if (riov)
-		riov->i = riov->used = 0;
+		riov->i = riov->used = riov->consumed = 0;
 	if (wiov)
-		wiov->i = wiov->used = 0;
+		wiov->i = wiov->used = wiov->consumed = 0;
 
 	for (;;) {
 		void *addr;
@@ -662,7 +679,10 @@ EXPORT_SYMBOL(vringh_init_user);
  * *head will be vrh->vring.num.  You may be able to ignore an invalid
  * descriptor, but there's not much you can do with an invalid ring.
  *
- * Note that you may need to clean up riov and wiov, even on error!
+ * Note that you can reuse riov and wiov with subsequent calls. Content is
+ * overwritten and memory reallocated if more space is needed.
+ * When you don't have to use riov and wiov anymore, you should clean up them
+ * calling vringh_iov_cleanup() to release the memory, even on error!
  */
 int vringh_getdesc_user(struct vringh *vrh,
 			struct vringh_iov *riov,
@@ -932,7 +952,10 @@ EXPORT_SYMBOL(vringh_init_kern);
  * *head will be vrh->vring.num.  You may be able to ignore an invalid
  * descriptor, but there's not much you can do with an invalid ring.
  *
- * Note that you may need to clean up riov and wiov, even on error!
+ * Note that you can reuse riov and wiov with subsequent calls. Content is
+ * overwritten and memory reallocated if more space is needed.
+ * When you don't have to use riov and wiov anymore, you should clean up them
+ * calling vringh_kiov_cleanup() to release the memory, even on error!
  */
 int vringh_getdesc_kern(struct vringh *vrh,
 			struct vringh_kiov *riov,
@@ -1074,6 +1097,8 @@ static int iotlb_translate(const struct vringh *vrh,
 	int ret = 0;
 	u64 s = 0;
 
+	spin_lock(vrh->iotlb_lock);
+
 	while (len > s) {
 		u64 size, pa, pfn;
 
@@ -1103,6 +1128,8 @@ static int iotlb_translate(const struct vringh *vrh,
 		++ret;
 	}
 
+	spin_unlock(vrh->iotlb_lock);
+
 	return ret;
 }
 
@@ -1262,10 +1289,13 @@ EXPORT_SYMBOL(vringh_init_iotlb);
  * vringh_set_iotlb - initialize a vringh for a ring with IOTLB.
  * @vrh: the vring
  * @iotlb: iotlb associated with this vring
+ * @iotlb_lock: spinlock to synchronize the iotlb accesses
  */
-void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb)
+void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb,
+		      spinlock_t *iotlb_lock)
 {
 	vrh->iotlb = iotlb;
+	vrh->iotlb_lock = iotlb_lock;
 }
 EXPORT_SYMBOL(vringh_set_iotlb);
 
@@ -1285,7 +1315,10 @@ EXPORT_SYMBOL(vringh_set_iotlb);
  * *head will be vrh->vring.num.  You may be able to ignore an invalid
  * descriptor, but there's not much you can do with an invalid ring.
  *
- * Note that you may need to clean up riov and wiov, even on error!
+ * Note that you can reuse riov and wiov with subsequent calls. Content is
+ * overwritten and memory reallocated if more space is needed.
+ * When you don't have to use riov and wiov anymore, you should clean up them
+ * calling vringh_kiov_cleanup() to release the memory, even on error!
  */
 int vringh_getdesc_iotlb(struct vringh *vrh,
 			 struct vringh_kiov *riov,