1 files changed, 170 insertions, 59 deletions

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 71e16b53e9c1..89bfe46a8a7f 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -74,14 +74,14 @@ struct vring_desc_state_packed {
 	void *data;			/* Data for callback. */
 	struct vring_packed_desc *indir_desc; /* Indirect descriptor, if any. */
 	u16 num;			/* Descriptor list length. */
-	u16 next;			/* The next desc state in a list. */
 	u16 last;			/* The last desc state in a list. */
 };
 
-struct vring_desc_extra_packed {
+struct vring_desc_extra {
 	dma_addr_t addr;		/* Buffer DMA addr. */
 	u32 len;			/* Buffer length. */
 	u16 flags;			/* Descriptor flags. */
+	u16 next;			/* The next desc state in a list. */
 };
 
 struct vring_virtqueue {
@@ -113,6 +113,9 @@ struct vring_virtqueue {
 	/* Last used index we've seen. */
 	u16 last_used_idx;
 
+	/* Hint for event idx: already triggered no need to disable. */
+	bool event_triggered;
+
 	union {
 		/* Available for split ring */
 		struct {
@@ -130,6 +133,7 @@ struct vring_virtqueue {
 
 			/* Per-descriptor state. */
 			struct vring_desc_state_split *desc_state;
+			struct vring_desc_extra *desc_extra;
 
 			/* DMA address and size information */
 			dma_addr_t queue_dma_addr;
@@ -166,7 +170,7 @@ struct vring_virtqueue {
 
 			/* Per-descriptor state. */
 			struct vring_desc_state_packed *desc_state;
-			struct vring_desc_extra_packed *desc_extra;
+			struct vring_desc_extra *desc_extra;
 
 			/* DMA address and size information */
 			dma_addr_t ring_dma_addr;
@@ -364,8 +368,8 @@ static int vring_mapping_error(const struct vring_virtqueue *vq,
  * Split ring specific functions - *_split().
  */
 
-static void vring_unmap_one_split(const struct vring_virtqueue *vq,
-				  struct vring_desc *desc)
+static void vring_unmap_one_split_indirect(const struct vring_virtqueue *vq,
+					   struct vring_desc *desc)
 {
 	u16 flags;
 
@@ -389,6 +393,35 @@ static void vring_unmap_one_split(const struct vring_virtqueue *vq,
 	}
 }
 
+static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq,
+					  unsigned int i)
+{
+	struct vring_desc_extra *extra = vq->split.desc_extra;
+	u16 flags;
+
+	if (!vq->use_dma_api)
+		goto out;
+
+	flags = extra[i].flags;
+
+	if (flags & VRING_DESC_F_INDIRECT) {
+		dma_unmap_single(vring_dma_dev(vq),
+				 extra[i].addr,
+				 extra[i].len,
+				 (flags & VRING_DESC_F_WRITE) ?
+				 DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	} else {
+		dma_unmap_page(vring_dma_dev(vq),
+			       extra[i].addr,
+			       extra[i].len,
+			       (flags & VRING_DESC_F_WRITE) ?
+			       DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+
+out:
+	return extra[i].next;
+}
+
 static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq,
 					       unsigned int total_sg,
 					       gfp_t gfp)
@@ -412,6 +445,35 @@ static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq,
 	return desc;
 }
 
+static inline unsigned int virtqueue_add_desc_split(struct virtqueue *vq,
+						    struct vring_desc *desc,
+						    unsigned int i,
+						    dma_addr_t addr,
+						    unsigned int len,
+						    u16 flags,
+						    bool indirect)
+{
+	struct vring_virtqueue *vring = to_vvq(vq);
+	struct vring_desc_extra *extra = vring->split.desc_extra;
+	u16 next;
+
+	desc[i].flags = cpu_to_virtio16(vq->vdev, flags);
+	desc[i].addr = cpu_to_virtio64(vq->vdev, addr);
+	desc[i].len = cpu_to_virtio32(vq->vdev, len);
+
+	if (!indirect) {
+		next = extra[i].next;
+		desc[i].next = cpu_to_virtio16(vq->vdev, next);
+
+		extra[i].addr = addr;
+		extra[i].len = len;
+		extra[i].flags = flags;
+	} else
+		next = virtio16_to_cpu(vq->vdev, desc[i].next);
+
+	return next;
+}
+
 static inline int virtqueue_add_split(struct virtqueue *_vq,
 				      struct scatterlist *sgs[],
 				      unsigned int total_sg,
@@ -484,11 +546,13 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 			if (vring_mapping_error(vq, addr))
 				goto unmap_release;
 
-			desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT);
-			desc[i].addr = cpu_to_virtio64(_vq->vdev, addr);
-			desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length);
 			prev = i;
-			i = virtio16_to_cpu(_vq->vdev, desc[i].next);
+			/* Note that we trust indirect descriptor
+			 * table since it use stream DMA mapping.
+			 */
+			i = virtqueue_add_desc_split(_vq, desc, i, addr, sg->length,
+						     VRING_DESC_F_NEXT,
+						     indirect);
 		}
 	}
 	for (; n < (out_sgs + in_sgs); n++) {
@@ -497,15 +561,22 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 			if (vring_mapping_error(vq, addr))
 				goto unmap_release;
 
-			desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT | VRING_DESC_F_WRITE);
-			desc[i].addr = cpu_to_virtio64(_vq->vdev, addr);
-			desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length);
 			prev = i;
-			i = virtio16_to_cpu(_vq->vdev, desc[i].next);
+			/* Note that we trust indirect descriptor
+			 * table since it use stream DMA mapping.
+			 */
+			i = virtqueue_add_desc_split(_vq, desc, i, addr,
+						     sg->length,
+						     VRING_DESC_F_NEXT |
+						     VRING_DESC_F_WRITE,
+						     indirect);
 		}
 	}
 	/* Last one doesn't continue. */
 	desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT);
+	if (!indirect && vq->use_dma_api)
+		vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags =
+			~VRING_DESC_F_NEXT;
 
 	if (indirect) {
 		/* Now that the indirect table is filled in, map it. */
@@ -515,13 +586,11 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 		if (vring_mapping_error(vq, addr))
 			goto unmap_release;
 
-		vq->split.vring.desc[head].flags = cpu_to_virtio16(_vq->vdev,
-				VRING_DESC_F_INDIRECT);
-		vq->split.vring.desc[head].addr = cpu_to_virtio64(_vq->vdev,
-				addr);
-
-		vq->split.vring.desc[head].len = cpu_to_virtio32(_vq->vdev,
-				total_sg * sizeof(struct vring_desc));
+		virtqueue_add_desc_split(_vq, vq->split.vring.desc,
+					 head, addr,
+					 total_sg * sizeof(struct vring_desc),
+					 VRING_DESC_F_INDIRECT,
+					 false);
 	}
 
 	/* We're using some buffers from the free list. */
@@ -529,8 +598,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 
 	/* Update free pointer */
 	if (indirect)
-		vq->free_head = virtio16_to_cpu(_vq->vdev,
-					vq->split.vring.desc[head].next);
+		vq->free_head = vq->split.desc_extra[head].next;
 	else
 		vq->free_head = i;
 
@@ -575,8 +643,11 @@ unmap_release:
 	for (n = 0; n < total_sg; n++) {
 		if (i == err_idx)
 			break;
-		vring_unmap_one_split(vq, &desc[i]);
-		i = virtio16_to_cpu(_vq->vdev, desc[i].next);
+		if (indirect) {
+			vring_unmap_one_split_indirect(vq, &desc[i]);
+			i = virtio16_to_cpu(_vq->vdev, desc[i].next);
+		} else
+			i = vring_unmap_one_split(vq, i);
 	}
 
 	if (indirect)
@@ -630,14 +701,13 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 	i = head;
 
 	while (vq->split.vring.desc[i].flags & nextflag) {
-		vring_unmap_one_split(vq, &vq->split.vring.desc[i]);
-		i = virtio16_to_cpu(vq->vq.vdev, vq->split.vring.desc[i].next);
+		vring_unmap_one_split(vq, i);
+		i = vq->split.desc_extra[i].next;
 		vq->vq.num_free++;
 	}
 
-	vring_unmap_one_split(vq, &vq->split.vring.desc[i]);
-	vq->split.vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev,
-						vq->free_head);
+	vring_unmap_one_split(vq, i);
+	vq->split.desc_extra[i].next = vq->free_head;
 	vq->free_head = head;
 
 	/* Plus final descriptor */
@@ -652,15 +722,14 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
 		if (!indir_desc)
 			return;
 
-		len = virtio32_to_cpu(vq->vq.vdev,
-				vq->split.vring.desc[head].len);
+		len = vq->split.desc_extra[head].len;
 
-		BUG_ON(!(vq->split.vring.desc[head].flags &
-			 cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
+		BUG_ON(!(vq->split.desc_extra[head].flags &
+				VRING_DESC_F_INDIRECT));
 		BUG_ON(len == 0 || len % sizeof(struct vring_desc));
 
 		for (j = 0; j < len / sizeof(struct vring_desc); j++)
-			vring_unmap_one_split(vq, &indir_desc[j]);
+			vring_unmap_one_split_indirect(vq, &indir_desc[j]);
 
 		kfree(indir_desc);
 		vq->split.desc_state[head].indir_desc = NULL;
@@ -739,7 +808,10 @@ static void virtqueue_disable_cb_split(struct virtqueue *_vq)
 
 	if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
 		vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
-		if (!vq->event)
+		if (vq->event)
+			/* TODO: this is a hack. Figure out a cleaner value to write. */
+			vring_used_event(&vq->split.vring) = 0x0;
+		else
 			vq->split.vring.avail->flags =
 				cpu_to_virtio16(_vq->vdev,
 						vq->split.avail_flags_shadow);
@@ -912,7 +984,7 @@ static struct virtqueue *vring_create_virtqueue_split(
  */
 
 static void vring_unmap_state_packed(const struct vring_virtqueue *vq,
-				     struct vring_desc_extra_packed *state)
+				     struct vring_desc_extra *state)
 {
 	u16 flags;
 
@@ -1061,7 +1133,7 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 				1 << VRING_PACKED_DESC_F_USED;
 	}
 	vq->packed.next_avail_idx = n;
-	vq->free_head = vq->packed.desc_state[id].next;
+	vq->free_head = vq->packed.desc_extra[id].next;
 
 	/* Store token and indirect buffer state. */
 	vq->packed.desc_state[id].num = 1;
@@ -1169,7 +1241,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 					le16_to_cpu(flags);
 			}
 			prev = curr;
-			curr = vq->packed.desc_state[curr].next;
+			curr = vq->packed.desc_extra[curr].next;
 
 			if ((unlikely(++i >= vq->packed.vring.num))) {
 				i = 0;
@@ -1213,13 +1285,16 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 unmap_release:
 	err_idx = i;
 	i = head;
+	curr = vq->free_head;
 
 	vq->packed.avail_used_flags = avail_used_flags;
 
 	for (n = 0; n < total_sg; n++) {
 		if (i == err_idx)
 			break;
-		vring_unmap_desc_packed(vq, &desc[i]);
+		vring_unmap_state_packed(vq,
+					 &vq->packed.desc_extra[curr]);
+		curr = vq->packed.desc_extra[curr].next;
 		i++;
 		if (i >= vq->packed.vring.num)
 			i = 0;
@@ -1290,7 +1365,7 @@ static void detach_buf_packed(struct vring_virtqueue *vq,
 	/* Clear data ptr. */
 	state->data = NULL;
 
-	vq->packed.desc_state[state->last].next = vq->free_head;
+	vq->packed.desc_extra[state->last].next = vq->free_head;
 	vq->free_head = id;
 	vq->vq.num_free += state->num;
 
@@ -1299,7 +1374,7 @@ static void detach_buf_packed(struct vring_virtqueue *vq,
 		for (i = 0; i < state->num; i++) {
 			vring_unmap_state_packed(vq,
 				&vq->packed.desc_extra[curr]);
-			curr = vq->packed.desc_state[curr].next;
+			curr = vq->packed.desc_extra[curr].next;
 		}
 	}
 
@@ -1550,6 +1625,25 @@ static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq)
 	return NULL;
 }
 
+static struct vring_desc_extra *vring_alloc_desc_extra(struct vring_virtqueue *vq,
+						       unsigned int num)
+{
+	struct vring_desc_extra *desc_extra;
+	unsigned int i;
+
+	desc_extra = kmalloc_array(num, sizeof(struct vring_desc_extra),
+				   GFP_KERNEL);
+	if (!desc_extra)
+		return NULL;
+
+	memset(desc_extra, 0, num * sizeof(struct vring_desc_extra));
+
+	for (i = 0; i < num - 1; i++)
+		desc_extra[i].next = i + 1;
+
+	return desc_extra;
+}
+
 static struct virtqueue *vring_create_virtqueue_packed(
 	unsigned int index,
 	unsigned int num,
@@ -1567,7 +1661,6 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	struct vring_packed_desc_event *driver, *device;
 	dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr;
 	size_t ring_size_in_bytes, event_size_in_bytes;
-	unsigned int i;
 
 	ring_size_in_bytes = num * sizeof(struct vring_packed_desc);
 
@@ -1605,6 +1698,7 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	vq->weak_barriers = weak_barriers;
 	vq->broken = false;
 	vq->last_used_idx = 0;
+	vq->event_triggered = false;
 	vq->num_added = 0;
 	vq->packed_ring = true;
 	vq->use_dma_api = vring_use_dma_api(vdev);
@@ -1649,18 +1743,11 @@ static struct virtqueue *vring_create_virtqueue_packed(
 
 	/* Put everything in free lists. */
 	vq->free_head = 0;
-	for (i = 0; i < num-1; i++)
-		vq->packed.desc_state[i].next = i + 1;
 
-	vq->packed.desc_extra = kmalloc_array(num,
-			sizeof(struct vring_desc_extra_packed),
-			GFP_KERNEL);
+	vq->packed.desc_extra = vring_alloc_desc_extra(vq, num);
 	if (!vq->packed.desc_extra)
 		goto err_desc_extra;
 
-	memset(vq->packed.desc_extra, 0,
-		num * sizeof(struct vring_desc_extra_packed));
-
 	/* No callback?  Tell other side not to bother us. */
 	if (!callback) {
 		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE;
@@ -1875,7 +1962,7 @@ bool virtqueue_kick(struct virtqueue *vq)
 EXPORT_SYMBOL_GPL(virtqueue_kick);
 
 /**
- * virtqueue_get_buf - get the next used buffer
+ * virtqueue_get_buf_ctx - get the next used buffer
  * @_vq: the struct virtqueue we're talking about.
  * @len: the length written into the buffer
  * @ctx: extra context for the token
@@ -1919,6 +2006,12 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
+	/* If device triggered an event already it won't trigger one again:
+	 * no need to disable.
+	 */
+	if (vq->event_triggered)
+		return;
+
 	if (vq->packed_ring)
 		virtqueue_disable_cb_packed(_vq);
 	else
@@ -1942,6 +2035,9 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
+	if (vq->event_triggered)
+		vq->event_triggered = false;
+
 	return vq->packed_ring ? virtqueue_enable_cb_prepare_packed(_vq) :
 				 virtqueue_enable_cb_prepare_split(_vq);
 }
@@ -2005,6 +2101,9 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
+	if (vq->event_triggered)
+		vq->event_triggered = false;
+
 	return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) :
 				 virtqueue_enable_cb_delayed_split(_vq);
 }
@@ -2044,6 +2143,10 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
 	if (unlikely(vq->broken))
 		return IRQ_HANDLED;
 
+	/* Just a hint for performance: so it's ok that this can be racy! */
+	if (vq->event)
+		vq->event_triggered = true;
+
 	pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback);
 	if (vq->vq.callback)
 		vq->vq.callback(&vq->vq);
@@ -2062,7 +2165,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 					void (*callback)(struct virtqueue *),
 					const char *name)
 {
-	unsigned int i;
 	struct vring_virtqueue *vq;
 
 	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
@@ -2083,6 +2185,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	vq->weak_barriers = weak_barriers;
 	vq->broken = false;
 	vq->last_used_idx = 0;
+	vq->event_triggered = false;
 	vq->num_added = 0;
 	vq->use_dma_api = vring_use_dma_api(vdev);
 #ifdef DEBUG
@@ -2114,20 +2217,26 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 
 	vq->split.desc_state = kmalloc_array(vring.num,
 			sizeof(struct vring_desc_state_split), GFP_KERNEL);
-	if (!vq->split.desc_state) {
-		kfree(vq);
-		return NULL;
-	}
+	if (!vq->split.desc_state)
+		goto err_state;
+
+	vq->split.desc_extra = vring_alloc_desc_extra(vq, vring.num);
+	if (!vq->split.desc_extra)
+		goto err_extra;
 
 	/* Put everything in free lists. */
 	vq->free_head = 0;
-	for (i = 0; i < vring.num-1; i++)
-		vq->split.vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
 	memset(vq->split.desc_state, 0, vring.num *
 			sizeof(struct vring_desc_state_split));
 
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 	return &vq->vq;
+
+err_extra:
+	kfree(vq->split.desc_state);
+err_state:
+	kfree(vq);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(__vring_new_virtqueue);
 
@@ -2208,8 +2317,10 @@ void vring_del_virtqueue(struct virtqueue *_vq)
 					 vq->split.queue_dma_addr);
 		}
 	}
-	if (!vq->packed_ring)
+	if (!vq->packed_ring) {
 		kfree(vq->split.desc_state);
+		kfree(vq->split.desc_extra);
+	}
 	list_del(&_vq->list);
 	kfree(vq);
 }