2 files changed, 210 insertions, 93 deletions

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 8dab163c5ef..bd3ae324a1a 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -108,7 +108,7 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
 	sg_init_one(&sg, vb->pfns, sizeof(vb->pfns[0]) * vb->num_pfns);
 
 	/* We should always be able to add one buffer to an empty queue. */
-	if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0)
+	if (virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL) < 0)
 		BUG();
 	virtqueue_kick(vq);
 
@@ -256,7 +256,7 @@ static void stats_handle_request(struct virtio_balloon *vb)
 	if (!virtqueue_get_buf(vq, &len))
 		return;
 	sg_init_one(&sg, vb->stats, sizeof(vb->stats));
-	if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0)
+	if (virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL) < 0)
 		BUG();
 	virtqueue_kick(vq);
 }
@@ -341,7 +341,7 @@ static int init_vqs(struct virtio_balloon *vb)
 		 * use it to signal us later.
 		 */
 		sg_init_one(&sg, vb->stats, sizeof vb->stats);
-		if (virtqueue_add_buf(vb->stats_vq, &sg, 1, 0, vb, GFP_KERNEL)
+		if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
 		    < 0)
 			BUG();
 		virtqueue_kick(vb->stats_vq);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index ffd7e7da5d3..5217baf5528 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -24,27 +24,6 @@
 #include <linux/module.h>
 #include <linux/hrtimer.h>
 
-/* virtio guest is communicating with a virtual "device" that actually runs on
- * a host processor.  Memory barriers are used to control SMP effects. */
-#ifdef CONFIG_SMP
-/* Where possible, use SMP barriers which are more lightweight than mandatory
- * barriers, because mandatory barriers control MMIO effects on accesses
- * through relaxed memory I/O windows (which virtio-pci does not use). */
-#define virtio_mb(vq) \
-	do { if ((vq)->weak_barriers) smp_mb(); else mb(); } while(0)
-#define virtio_rmb(vq) \
-	do { if ((vq)->weak_barriers) smp_rmb(); else rmb(); } while(0)
-#define virtio_wmb(vq) \
-	do { if ((vq)->weak_barriers) smp_wmb(); else wmb(); } while(0)
-#else
-/* We must force memory ordering even if guest is UP since host could be
- * running on another CPU, but SMP barriers are defined to barrier() in that
- * configuration. So fall back to mandatory barriers instead. */
-#define virtio_mb(vq) mb()
-#define virtio_rmb(vq) rmb()
-#define virtio_wmb(vq) wmb()
-#endif
-
 #ifdef DEBUG
 /* For development, we want to crash whenever the ring is screwed. */
 #define BAD_RING(_vq, fmt, args...)				\
@@ -119,16 +98,36 @@ struct vring_virtqueue
 
 #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
 
+static inline struct scatterlist *sg_next_chained(struct scatterlist *sg,
+						  unsigned int *count)
+{
+	return sg_next(sg);
+}
+
+static inline struct scatterlist *sg_next_arr(struct scatterlist *sg,
+					      unsigned int *count)
+{
+	if (--(*count) == 0)
+		return NULL;
+	return sg + 1;
+}
+
 /* Set up an indirect table of descriptors and add it to the queue. */
-static int vring_add_indirect(struct vring_virtqueue *vq,
-			      struct scatterlist sg[],
-			      unsigned int out,
-			      unsigned int in,
-			      gfp_t gfp)
+static inline int vring_add_indirect(struct vring_virtqueue *vq,
+				     struct scatterlist *sgs[],
+				     struct scatterlist *(*next)
+				       (struct scatterlist *, unsigned int *),
+				     unsigned int total_sg,
+				     unsigned int total_out,
+				     unsigned int total_in,
+				     unsigned int out_sgs,
+				     unsigned int in_sgs,
+				     gfp_t gfp)
 {
 	struct vring_desc *desc;
 	unsigned head;
-	int i;
+	struct scatterlist *sg;
+	int i, n;
 
 	/*
 	 * We require lowmem mappings for the descriptors because
@@ -137,25 +136,31 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	 */
 	gfp &= ~(__GFP_HIGHMEM | __GFP_HIGH);
 
-	desc = kmalloc((out + in) * sizeof(struct vring_desc), gfp);
+	desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp);
 	if (!desc)
 		return -ENOMEM;
 
-	/* Transfer entries from the sg list into the indirect page */
-	for (i = 0; i < out; i++) {
-		desc[i].flags = VRING_DESC_F_NEXT;
-		desc[i].addr = sg_phys(sg);
-		desc[i].len = sg->length;
-		desc[i].next = i+1;
-		sg++;
+	/* Transfer entries from the sg lists into the indirect page */
+	i = 0;
+	for (n = 0; n < out_sgs; n++) {
+		for (sg = sgs[n]; sg; sg = next(sg, &total_out)) {
+			desc[i].flags = VRING_DESC_F_NEXT;
+			desc[i].addr = sg_phys(sg);
+			desc[i].len = sg->length;
+			desc[i].next = i+1;
+			i++;
+		}
 	}
-	for (; i < (out + in); i++) {
-		desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
-		desc[i].addr = sg_phys(sg);
-		desc[i].len = sg->length;
-		desc[i].next = i+1;
-		sg++;
+	for (; n < (out_sgs + in_sgs); n++) {
+		for (sg = sgs[n]; sg; sg = next(sg, &total_in)) {
+			desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
+			desc[i].addr = sg_phys(sg);
+			desc[i].len = sg->length;
+			desc[i].next = i+1;
+			i++;
+		}
 	}
+	BUG_ON(i != total_sg);
 
 	/* Last one doesn't continue. */
 	desc[i-1].flags &= ~VRING_DESC_F_NEXT;
@@ -176,29 +181,20 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	return head;
 }
 
-/**
- * virtqueue_add_buf - expose buffer to other end
- * @vq: the struct virtqueue we're talking about.
- * @sg: the description of the buffer(s).
- * @out_num: the number of sg readable by other side
- * @in_num: the number of sg which are writable (after readable ones)
- * @data: the token identifying the buffer.
- * @gfp: how to do memory allocations (if necessary).
- *
- * Caller must ensure we don't call this with other virtqueue operations
- * at the same time (except where noted).
- *
- * Returns zero or a negative error (ie. ENOSPC, ENOMEM).
- */
-int virtqueue_add_buf(struct virtqueue *_vq,
-		      struct scatterlist sg[],
-		      unsigned int out,
-		      unsigned int in,
-		      void *data,
-		      gfp_t gfp)
+static inline int virtqueue_add(struct virtqueue *_vq,
+				struct scatterlist *sgs[],
+				struct scatterlist *(*next)
+				  (struct scatterlist *, unsigned int *),
+				unsigned int total_out,
+				unsigned int total_in,
+				unsigned int out_sgs,
+				unsigned int in_sgs,
+				void *data,
+				gfp_t gfp)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-	unsigned int i, avail, uninitialized_var(prev);
+	struct scatterlist *sg;
+	unsigned int i, n, avail, uninitialized_var(prev), total_sg;
 	int head;
 
 	START_USE(vq);
@@ -218,46 +214,54 @@ int virtqueue_add_buf(struct virtqueue *_vq,
 	}
 #endif
 
+	total_sg = total_in + total_out;
+
 	/* If the host supports indirect descriptor tables, and we have multiple
 	 * buffers, then go indirect. FIXME: tune this threshold */
-	if (vq->indirect && (out + in) > 1 && vq->vq.num_free) {
-		head = vring_add_indirect(vq, sg, out, in, gfp);
+	if (vq->indirect && total_sg > 1 && vq->vq.num_free) {
+		head = vring_add_indirect(vq, sgs, next, total_sg, total_out,
+					  total_in,
+					  out_sgs, in_sgs, gfp);
 		if (likely(head >= 0))
 			goto add_head;
 	}
 
-	BUG_ON(out + in > vq->vring.num);
-	BUG_ON(out + in == 0);
+	BUG_ON(total_sg > vq->vring.num);
+	BUG_ON(total_sg == 0);
 
-	if (vq->vq.num_free < out + in) {
+	if (vq->vq.num_free < total_sg) {
 		pr_debug("Can't add buf len %i - avail = %i\n",
-			 out + in, vq->vq.num_free);
+			 total_sg, vq->vq.num_free);
 		/* FIXME: for historical reasons, we force a notify here if
 		 * there are outgoing parts to the buffer.  Presumably the
 		 * host should service the ring ASAP. */
-		if (out)
+		if (out_sgs)
 			vq->notify(&vq->vq);
 		END_USE(vq);
 		return -ENOSPC;
 	}
 
 	/* We're about to use some buffers from the free list. */
-	vq->vq.num_free -= out + in;
-
-	head = vq->free_head;
-	for (i = vq->free_head; out; i = vq->vring.desc[i].next, out--) {
-		vq->vring.desc[i].flags = VRING_DESC_F_NEXT;
-		vq->vring.desc[i].addr = sg_phys(sg);
-		vq->vring.desc[i].len = sg->length;
-		prev = i;
-		sg++;
+	vq->vq.num_free -= total_sg;
+
+	head = i = vq->free_head;
+	for (n = 0; n < out_sgs; n++) {
+		for (sg = sgs[n]; sg; sg = next(sg, &total_out)) {
+			vq->vring.desc[i].flags = VRING_DESC_F_NEXT;
+			vq->vring.desc[i].addr = sg_phys(sg);
+			vq->vring.desc[i].len = sg->length;
+			prev = i;
+			i = vq->vring.desc[i].next;
+		}
 	}
-	for (; in; i = vq->vring.desc[i].next, in--) {
-		vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
-		vq->vring.desc[i].addr = sg_phys(sg);
-		vq->vring.desc[i].len = sg->length;
-		prev = i;
-		sg++;
+	for (; n < (out_sgs + in_sgs); n++) {
+		for (sg = sgs[n]; sg; sg = next(sg, &total_in)) {
+			vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
+			vq->vring.desc[i].addr = sg_phys(sg);
+			vq->vring.desc[i].len = sg->length;
+			prev = i;
+			i = vq->vring.desc[i].next;
+		}
 	}
 	/* Last one doesn't continue. */
 	vq->vring.desc[prev].flags &= ~VRING_DESC_F_NEXT;
@@ -276,7 +280,7 @@ add_head:
 
 	/* Descriptors and available array need to be set before we expose the
 	 * new available array entries. */
-	virtio_wmb(vq);
+	virtio_wmb(vq->weak_barriers);
 	vq->vring.avail->idx++;
 	vq->num_added++;
 
@@ -290,9 +294,122 @@ add_head:
 
 	return 0;
 }
+
+/**
+ * virtqueue_add_buf - expose buffer to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sg: the description of the buffer(s).
+ * @out_num: the number of sg readable by other side
+ * @in_num: the number of sg which are writable (after readable ones)
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM).
+ */
+int virtqueue_add_buf(struct virtqueue *_vq,
+		      struct scatterlist sg[],
+		      unsigned int out,
+		      unsigned int in,
+		      void *data,
+		      gfp_t gfp)
+{
+	struct scatterlist *sgs[2];
+
+	sgs[0] = sg;
+	sgs[1] = sg + out;
+
+	return virtqueue_add(_vq, sgs, sg_next_arr,
+			     out, in, out ? 1 : 0, in ? 1 : 0, data, gfp);
+}
 EXPORT_SYMBOL_GPL(virtqueue_add_buf);
 
 /**
+ * virtqueue_add_sgs - expose buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sgs: array of terminated scatterlists.
+ * @out_num: the number of scatterlists readable by other side
+ * @in_num: the number of scatterlists which are writable (after readable ones)
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM).
+ */
+int virtqueue_add_sgs(struct virtqueue *_vq,
+		      struct scatterlist *sgs[],
+		      unsigned int out_sgs,
+		      unsigned int in_sgs,
+		      void *data,
+		      gfp_t gfp)
+{
+	unsigned int i, total_out, total_in;
+
+	/* Count them first. */
+	for (i = total_out = total_in = 0; i < out_sgs; i++) {
+		struct scatterlist *sg;
+		for (sg = sgs[i]; sg; sg = sg_next(sg))
+			total_out++;
+	}
+	for (; i < out_sgs + in_sgs; i++) {
+		struct scatterlist *sg;
+		for (sg = sgs[i]; sg; sg = sg_next(sg))
+			total_in++;
+	}
+	return virtqueue_add(_vq, sgs, sg_next_chained,
+			     total_out, total_in, out_sgs, in_sgs, data, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
+
+/**
+ * virtqueue_add_outbuf - expose output buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sgs: array of scatterlists (need not be terminated!)
+ * @num: the number of scatterlists readable by other side
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM).
+ */
+int virtqueue_add_outbuf(struct virtqueue *vq,
+			 struct scatterlist sg[], unsigned int num,
+			 void *data,
+			 gfp_t gfp)
+{
+	return virtqueue_add(vq, &sg, sg_next_arr, num, 0, 1, 0, data, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
+
+/**
+ * virtqueue_add_inbuf - expose input buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sgs: array of scatterlists (need not be terminated!)
+ * @num: the number of scatterlists writable by other side
+ * @data: the token identifying the buffer.
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM).
+ */
+int virtqueue_add_inbuf(struct virtqueue *vq,
+			struct scatterlist sg[], unsigned int num,
+			void *data,
+			gfp_t gfp)
+{
+	return virtqueue_add(vq, &sg, sg_next_arr, 0, num, 0, 1, data, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);
+
+/**
  * virtqueue_kick_prepare - first half of split virtqueue_kick call.
  * @vq: the struct virtqueue
  *
@@ -312,7 +429,7 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq)
 	START_USE(vq);
 	/* We need to expose available array entries before checking avail
 	 * event. */
-	virtio_mb(vq);
+	virtio_mb(vq->weak_barriers);
 
 	old = vq->vring.avail->idx - vq->num_added;
 	new = vq->vring.avail->idx;
@@ -436,7 +553,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 	}
 
 	/* Only get used array entries after they have been exposed by host. */
-	virtio_rmb(vq);
+	virtio_rmb(vq->weak_barriers);
 
 	last_used = (vq->last_used_idx & (vq->vring.num - 1));
 	i = vq->vring.used->ring[last_used].id;
@@ -460,7 +577,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 	 * the read in the next get_buf call. */
 	if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) {
 		vring_used_event(&vq->vring) = vq->last_used_idx;
-		virtio_mb(vq);
+		virtio_mb(vq->weak_barriers);
 	}
 
 #ifdef DEBUG
@@ -513,7 +630,7 @@ bool virtqueue_enable_cb(struct virtqueue *_vq)
 	 * entry. Always do both to keep code simple. */
 	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
 	vring_used_event(&vq->vring) = vq->last_used_idx;
-	virtio_mb(vq);
+	virtio_mb(vq->weak_barriers);
 	if (unlikely(more_used(vq))) {
 		END_USE(vq);
 		return false;
@@ -553,7 +670,7 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 	/* TODO: tune this threshold */
 	bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4;
 	vring_used_event(&vq->vring) = vq->last_used_idx + bufs;
-	virtio_mb(vq);
+	virtio_mb(vq->weak_barriers);
 	if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) {
 		END_USE(vq);
 		return false;