1 files changed, 252 insertions, 63 deletions

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 7aa4eea930f1..c14c42b95ab8 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -37,6 +37,11 @@ enum {
 	VHOST_MEMORY_F_LOG = 0x1,
 };
 
+static unsigned vhost_zcopy_mask __read_mostly;
+
+#define vhost_used_event(vq) ((u16 __user *)&vq->avail->ring[vq->num])
+#define vhost_avail_event(vq) ((u16 __user *)&vq->used->ring[vq->num])
+
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
@@ -161,6 +166,8 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->last_avail_idx = 0;
 	vq->avail_idx = 0;
 	vq->last_used_idx = 0;
+	vq->signalled_used = 0;
+	vq->signalled_used_valid = false;
 	vq->used_flags = 0;
 	vq->log_used = false;
 	vq->log_addr = -1ull;
@@ -174,6 +181,9 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->call_ctx = NULL;
 	vq->call = NULL;
 	vq->log_ctx = NULL;
+	vq->upend_idx = 0;
+	vq->done_idx = 0;
+	vq->ubufs = NULL;
 }
 
 static int vhost_worker(void *data)
@@ -220,10 +230,28 @@ static int vhost_worker(void *data)
 	return 0;
 }
 
+static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq)
+{
+	kfree(vq->indirect);
+	vq->indirect = NULL;
+	kfree(vq->log);
+	vq->log = NULL;
+	kfree(vq->heads);
+	vq->heads = NULL;
+	kfree(vq->ubuf_info);
+	vq->ubuf_info = NULL;
+}
+
+void vhost_enable_zcopy(int vq)
+{
+	vhost_zcopy_mask |= 0x1 << vq;
+}
+
 /* Helper to allocate iovec buffers for all vqs. */
 static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
 {
 	int i;
+	bool zcopy;
 
 	for (i = 0; i < dev->nvqs; ++i) {
 		dev->vqs[i].indirect = kmalloc(sizeof *dev->vqs[i].indirect *
@@ -232,19 +260,21 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
 					  GFP_KERNEL);
 		dev->vqs[i].heads = kmalloc(sizeof *dev->vqs[i].heads *
 					    UIO_MAXIOV, GFP_KERNEL);
-
+		zcopy = vhost_zcopy_mask & (0x1 << i);
+		if (zcopy)
+			dev->vqs[i].ubuf_info =
+				kmalloc(sizeof *dev->vqs[i].ubuf_info *
+					UIO_MAXIOV, GFP_KERNEL);
 		if (!dev->vqs[i].indirect || !dev->vqs[i].log ||
-			!dev->vqs[i].heads)
+			!dev->vqs[i].heads ||
+			(zcopy && !dev->vqs[i].ubuf_info))
 			goto err_nomem;
 	}
 	return 0;
 
 err_nomem:
-	for (; i >= 0; --i) {
-		kfree(dev->vqs[i].indirect);
-		kfree(dev->vqs[i].log);
-		kfree(dev->vqs[i].heads);
-	}
+	for (; i >= 0; --i)
+		vhost_vq_free_iovecs(&dev->vqs[i]);
 	return -ENOMEM;
 }
 
@@ -252,14 +282,8 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev)
 {
 	int i;
 
-	for (i = 0; i < dev->nvqs; ++i) {
-		kfree(dev->vqs[i].indirect);
-		dev->vqs[i].indirect = NULL;
-		kfree(dev->vqs[i].log);
-		dev->vqs[i].log = NULL;
-		kfree(dev->vqs[i].heads);
-		dev->vqs[i].heads = NULL;
-	}
+	for (i = 0; i < dev->nvqs; ++i)
+		vhost_vq_free_iovecs(&dev->vqs[i]);
 }
 
 long vhost_dev_init(struct vhost_dev *dev,
@@ -282,6 +306,7 @@ long vhost_dev_init(struct vhost_dev *dev,
 		dev->vqs[i].log = NULL;
 		dev->vqs[i].indirect = NULL;
 		dev->vqs[i].heads = NULL;
+		dev->vqs[i].ubuf_info = NULL;
 		dev->vqs[i].dev = dev;
 		mutex_init(&dev->vqs[i].mutex);
 		vhost_vq_reset(dev, dev->vqs + i);
@@ -385,6 +410,30 @@ long vhost_dev_reset_owner(struct vhost_dev *dev)
 	return 0;
 }
 
+/* In case of DMA done not in order in lower device driver for some reason.
+ * upend_idx is used to track end of used idx, done_idx is used to track head
+ * of used idx. Once lower device DMA done contiguously, we will signal KVM
+ * guest used idx.
+ */
+int vhost_zerocopy_signal_used(struct vhost_virtqueue *vq)
+{
+	int i;
+	int j = 0;
+
+	for (i = vq->done_idx; i != vq->upend_idx; i = (i + 1) % UIO_MAXIOV) {
+		if ((vq->heads[i].len == VHOST_DMA_DONE_LEN)) {
+			vq->heads[i].len = VHOST_DMA_CLEAR_LEN;
+			vhost_add_used_and_signal(vq->dev, vq,
+						  vq->heads[i].id, 0);
+			++j;
+		} else
+			break;
+	}
+	if (j)
+		vq->done_idx = i;
+	return j;
+}
+
 /* Caller should have device mutex */
 void vhost_dev_cleanup(struct vhost_dev *dev)
 {
@@ -395,6 +444,13 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
 			vhost_poll_stop(&dev->vqs[i].poll);
 			vhost_poll_flush(&dev->vqs[i].poll);
 		}
+		/* Wait for all lower device DMAs done. */
+		if (dev->vqs[i].ubufs)
+			vhost_ubuf_put_and_wait(dev->vqs[i].ubufs);
+
+		/* Signal guest as appropriate. */
+		vhost_zerocopy_signal_used(&dev->vqs[i]);
+
 		if (dev->vqs[i].error_ctx)
 			eventfd_ctx_put(dev->vqs[i].error_ctx);
 		if (dev->vqs[i].error)
@@ -489,16 +545,17 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
 	return 1;
 }
 
-static int vq_access_ok(unsigned int num,
+static int vq_access_ok(struct vhost_dev *d, unsigned int num,
 			struct vring_desc __user *desc,
 			struct vring_avail __user *avail,
 			struct vring_used __user *used)
 {
+	size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 	return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
 	       access_ok(VERIFY_READ, avail,
-			 sizeof *avail + num * sizeof *avail->ring) &&
+			 sizeof *avail + num * sizeof *avail->ring + s) &&
 	       access_ok(VERIFY_WRITE, used,
-			sizeof *used + num * sizeof *used->ring);
+			sizeof *used + num * sizeof *used->ring + s);
 }
 
 /* Can we log writes? */
@@ -514,9 +571,11 @@ int vhost_log_access_ok(struct vhost_dev *dev)
 
 /* Verify access for write logging. */
 /* Caller should have vq mutex and device mutex */
-static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
+static int vq_log_access_ok(struct vhost_dev *d, struct vhost_virtqueue *vq,
+			    void __user *log_base)
 {
 	struct vhost_memory *mp;
+	size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 
 	mp = rcu_dereference_protected(vq->dev->memory,
 				       lockdep_is_held(&vq->mutex));
@@ -524,15 +583,15 @@ static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
 			    vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
 		(!vq->log_used || log_access_ok(log_base, vq->log_addr,
 					sizeof *vq->used +
-					vq->num * sizeof *vq->used->ring));
+					vq->num * sizeof *vq->used->ring + s));
 }
 
 /* Can we start vq? */
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	return vq_access_ok(vq->num, vq->desc, vq->avail, vq->used) &&
-		vq_log_access_ok(vq, vq->log_base);
+	return vq_access_ok(vq->dev, vq->num, vq->desc, vq->avail, vq->used) &&
+		vq_log_access_ok(vq->dev, vq, vq->log_base);
 }
 
 static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
@@ -570,16 +629,6 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 	return 0;
 }
 
-static int init_used(struct vhost_virtqueue *vq,
-		     struct vring_used __user *used)
-{
-	int r = put_user(vq->used_flags, &used->flags);
-
-	if (r)
-		return r;
-	return get_user(vq->last_used_idx, &used->idx);
-}
-
 static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 {
 	struct file *eventfp, *filep = NULL,
@@ -674,7 +723,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 		 * If it is not, we don't as size might not have been setup.
 		 * We will verify when backend is configured. */
 		if (vq->private_data) {
-			if (!vq_access_ok(vq->num,
+			if (!vq_access_ok(d, vq->num,
 				(void __user *)(unsigned long)a.desc_user_addr,
 				(void __user *)(unsigned long)a.avail_user_addr,
 				(void __user *)(unsigned long)a.used_user_addr)) {
@@ -692,10 +741,6 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 			}
 		}
 
-		r = init_used(vq, (struct vring_used __user *)(unsigned long)
-			      a.used_user_addr);
-		if (r)
-			break;
 		vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
 		vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
 		vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
@@ -818,7 +863,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
 			vq = d->vqs + i;
 			mutex_lock(&vq->mutex);
 			/* If ring is inactive, will check when it's enabled. */
-			if (vq->private_data && !vq_log_access_ok(vq, base))
+			if (vq->private_data && !vq_log_access_ok(d, vq, base))
 				r = -EFAULT;
 			else
 				vq->log_base = base;
@@ -950,6 +995,57 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 	return 0;
 }
 
+static int vhost_update_used_flags(struct vhost_virtqueue *vq)
+{
+	void __user *used;
+	if (__put_user(vq->used_flags, &vq->used->flags) < 0)
+		return -EFAULT;
+	if (unlikely(vq->log_used)) {
+		/* Make sure the flag is seen before log. */
+		smp_wmb();
+		/* Log used flag write. */
+		used = &vq->used->flags;
+		log_write(vq->log_base, vq->log_addr +
+			  (used - (void __user *)vq->used),
+			  sizeof vq->used->flags);
+		if (vq->log_ctx)
+			eventfd_signal(vq->log_ctx, 1);
+	}
+	return 0;
+}
+
+static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
+{
+	if (__put_user(vq->avail_idx, vhost_avail_event(vq)))
+		return -EFAULT;
+	if (unlikely(vq->log_used)) {
+		void __user *used;
+		/* Make sure the event is seen before log. */
+		smp_wmb();
+		/* Log avail event write */
+		used = vhost_avail_event(vq);
+		log_write(vq->log_base, vq->log_addr +
+			  (used - (void __user *)vq->used),
+			  sizeof *vhost_avail_event(vq));
+		if (vq->log_ctx)
+			eventfd_signal(vq->log_ctx, 1);
+	}
+	return 0;
+}
+
+int vhost_init_used(struct vhost_virtqueue *vq)
+{
+	int r;
+	if (!vq->private_data)
+		return 0;
+
+	r = vhost_update_used_flags(vq);
+	if (r)
+		return r;
+	vq->signalled_used_valid = false;
+	return get_user(vq->last_used_idx, &vq->used->idx);
+}
+
 static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
 			  struct iovec iov[], int iov_size)
 {
@@ -1219,6 +1315,10 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 
 	/* On success, increment avail index. */
 	vq->last_avail_idx++;
+
+	/* Assume notifications from guest are disabled at this point,
+	 * if they aren't we would need to update avail_event index. */
+	BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY));
 	return head;
 }
 
@@ -1267,6 +1367,12 @@ int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
 			eventfd_signal(vq->log_ctx, 1);
 	}
 	vq->last_used_idx++;
+	/* If the driver never bothers to signal in a very long while,
+	 * used index might wrap around. If that happens, invalidate
+	 * signalled_used index we stored. TODO: make sure driver
+	 * signals at least once in 2^16 and remove this. */
+	if (unlikely(vq->last_used_idx == vq->signalled_used))
+		vq->signalled_used_valid = false;
 	return 0;
 }
 
@@ -1275,6 +1381,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 			    unsigned count)
 {
 	struct vring_used_elem __user *used;
+	u16 old, new;
 	int start;
 
 	start = vq->last_used_idx % vq->num;
@@ -1292,7 +1399,14 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 			   ((void __user *)used - (void __user *)vq->used),
 			  count * sizeof *used);
 	}
-	vq->last_used_idx += count;
+	old = vq->last_used_idx;
+	new = (vq->last_used_idx += count);
+	/* If the driver never bothers to signal in a very long while,
+	 * used index might wrap around. If that happens, invalidate
+	 * signalled_used index we stored. TODO: make sure driver
+	 * signals at least once in 2^16 and remove this. */
+	if (unlikely((u16)(new - vq->signalled_used) < (u16)(new - old)))
+		vq->signalled_used_valid = false;
 	return 0;
 }
 
@@ -1331,29 +1445,47 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 	return r;
 }
 
-/* This actually signals the guest, using eventfd. */
-void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
-	__u16 flags;
-
+	__u16 old, new, event;
+	bool v;
 	/* Flush out used index updates. This is paired
 	 * with the barrier that the Guest executes when enabling
 	 * interrupts. */
 	smp_mb();
 
-	if (__get_user(flags, &vq->avail->flags)) {
-		vq_err(vq, "Failed to get flags");
-		return;
+	if (vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
+	    unlikely(vq->avail_idx == vq->last_avail_idx))
+		return true;
+
+	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+		__u16 flags;
+		if (__get_user(flags, &vq->avail->flags)) {
+			vq_err(vq, "Failed to get flags");
+			return true;
+		}
+		return !(flags & VRING_AVAIL_F_NO_INTERRUPT);
 	}
+	old = vq->signalled_used;
+	v = vq->signalled_used_valid;
+	new = vq->signalled_used = vq->last_used_idx;
+	vq->signalled_used_valid = true;
 
-	/* If they don't want an interrupt, don't signal, unless empty. */
-	if ((flags & VRING_AVAIL_F_NO_INTERRUPT) &&
-	    (vq->avail_idx != vq->last_avail_idx ||
-	     !vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY)))
-		return;
+	if (unlikely(!v))
+		return true;
+
+	if (get_user(event, vhost_used_event(vq))) {
+		vq_err(vq, "Failed to get used event idx");
+		return true;
+	}
+	return vring_need_event(event, new, old);
+}
 
+/* This actually signals the guest, using eventfd. */
+void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
 	/* Signal the Guest tell them we used something up. */
-	if (vq->call_ctx)
+	if (vq->call_ctx && vhost_notify(dev, vq))
 		eventfd_signal(vq->call_ctx, 1);
 }
 
@@ -1376,7 +1508,7 @@ void vhost_add_used_and_signal_n(struct vhost_dev *dev,
 }
 
 /* OK, now we need to know about added descriptors. */
-bool vhost_enable_notify(struct vhost_virtqueue *vq)
+bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	u16 avail_idx;
 	int r;
@@ -1384,11 +1516,20 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 	if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
 		return false;
 	vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
-	r = put_user(vq->used_flags, &vq->used->flags);
-	if (r) {
-		vq_err(vq, "Failed to enable notification at %p: %d\n",
-		       &vq->used->flags, r);
-		return false;
+	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+		r = vhost_update_used_flags(vq);
+		if (r) {
+			vq_err(vq, "Failed to enable notification at %p: %d\n",
+			       &vq->used->flags, r);
+			return false;
+		}
+	} else {
+		r = vhost_update_avail_event(vq, vq->avail_idx);
+		if (r) {
+			vq_err(vq, "Failed to update avail event index at %p: %d\n",
+			       vhost_avail_event(vq), r);
+			return false;
+		}
 	}
 	/* They could have slipped one in as we were doing that: make
 	 * sure it's written, then check again. */
@@ -1404,15 +1545,63 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 }
 
 /* We don't need to be notified again. */
-void vhost_disable_notify(struct vhost_virtqueue *vq)
+void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	int r;
 
 	if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
 		return;
 	vq->used_flags |= VRING_USED_F_NO_NOTIFY;
-	r = put_user(vq->used_flags, &vq->used->flags);
-	if (r)
-		vq_err(vq, "Failed to enable notification at %p: %d\n",
-		       &vq->used->flags, r);
+	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+		r = vhost_update_used_flags(vq);
+		if (r)
+			vq_err(vq, "Failed to enable notification at %p: %d\n",
+			       &vq->used->flags, r);
+	}
+}
+
+static void vhost_zerocopy_done_signal(struct kref *kref)
+{
+	struct vhost_ubuf_ref *ubufs = container_of(kref, struct vhost_ubuf_ref,
+						    kref);
+	wake_up(&ubufs->wait);
+}
+
+struct vhost_ubuf_ref *vhost_ubuf_alloc(struct vhost_virtqueue *vq,
+					bool zcopy)
+{
+	struct vhost_ubuf_ref *ubufs;
+	/* No zero copy backend? Nothing to count. */
+	if (!zcopy)
+		return NULL;
+	ubufs = kmalloc(sizeof *ubufs, GFP_KERNEL);
+	if (!ubufs)
+		return ERR_PTR(-ENOMEM);
+	kref_init(&ubufs->kref);
+	init_waitqueue_head(&ubufs->wait);
+	ubufs->vq = vq;
+	return ubufs;
+}
+
+void vhost_ubuf_put(struct vhost_ubuf_ref *ubufs)
+{
+	kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
+}
+
+void vhost_ubuf_put_and_wait(struct vhost_ubuf_ref *ubufs)
+{
+	kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
+	wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount));
+	kfree(ubufs);
+}
+
+void vhost_zerocopy_callback(void *arg)
+{
+	struct ubuf_info *ubuf = arg;
+	struct vhost_ubuf_ref *ubufs = ubuf->arg;
+	struct vhost_virtqueue *vq = ubufs->vq;
+
+	/* set len = 1 to mark this desc buffers done DMA */
+	vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN;
+	kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
 }