[PATCH 03/22] virtio_ring: don't count elements twice for add_buf path.

[Rusty Russell <rusty@rustcorp.com.au>]

Extract the post-counting code into virtqueue_add(), make both callers
use it.  As much for neatness as optimization.

for i in `seq 50`; do /usr/bin/time -f 'Wall time:%e' ./vringh_test --indirect --eventidx --parallel --fast-vringh; done 2>&1 | stats --trim-outliers:

Before:
	Using CPUS 0 and 3
	Guest: notified 0, pinged 39019-39063(39061)
	Host: notified 39019-39063(39061), pinged 0
	Wall time:2.090000-2.520000(2.188542)

After:
	Using CPUS 0 and 3
	Guest: notified 0, pinged 39014-39063(39062)
	Host: notified 39014-39063(39062), pinged 0
	Wall time:1.900000-2.350000(1.921875)

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Reviewed-by: Wanlong Gao <gaowanlong@cn.fujitsu.com>
---
 drivers/virtio/virtio_ring.c |  147 +++++++++++++++++++++++-------------------
 1 file changed, 80 insertions(+), 67 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 27e31d3..c537385 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -163,69 +163,17 @@ 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)
-{
-	struct scatterlist *sgs[2];
-	unsigned int i;
-
-	sgs[0] = sg;
-	sgs[1] = sg + out;
-
-	/* Workaround until callers pass well-formed sgs. */
-	for (i = 0; i < out + in; i++)
-		sg_unmark_end(sg + i);
-
-	sg_mark_end(sg + out + in - 1);
-	if (out && in)
-		sg_mark_end(sg + out - 1);
-
-	return virtqueue_add_sgs(_vq, sgs, 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)
+static int virtqueue_add(struct virtqueue *_vq,
+			 struct scatterlist *sgs[],
+			 unsigned int total_sg,
+			 unsigned int out_sgs,
+			 unsigned int in_sgs,
+			 void *data,
+			 gfp_t gfp)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	struct scatterlist *sg;
-	unsigned int i, n, avail, uninitialized_var(prev), total_sg;
+	unsigned int i, n, avail, uninitialized_var(prev);
 	int head;
 
 	START_USE(vq);
@@ -245,13 +193,6 @@ int virtqueue_add_sgs(struct virtqueue *_vq,
 	}
 #endif
 
-	/* Count them first. */
-	for (i = total_sg = 0; i < out_sgs + in_sgs; i++) {
-		struct scatterlist *sg;
-		for (sg = sgs[i]; sg; sg = sg_next(sg))
-			total_sg++;
-	}
-
 	/* If the host supports indirect descriptor tables, and we have multiple
 	 * buffers, then go indirect. FIXME: tune this threshold */
 	if (vq->indirect && total_sg > 1 && vq->vq.num_free) {
@@ -329,6 +270,78 @@ 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];
+	unsigned int i;
+
+	sgs[0] = sg;
+	sgs[1] = sg + out;
+
+	/* Workaround until callers pass well-formed sgs. */
+	for (i = 0; i < out + in; i++)
+		sg_unmark_end(sg + i);
+
+	sg_mark_end(sg + out + in - 1);
+	if (out && in)
+		sg_mark_end(sg + out - 1);
+
+	return virtqueue_add(_vq, sgs, 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_sg;
+
+	/* Count them first. */
+	for (i = total_sg = 0; i < out_sgs + in_sgs; i++) {
+		struct scatterlist *sg;
+		for (sg = sgs[i]; sg; sg = sg_next(sg))
+			total_sg++;
+	}
+	return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs, data, gfp);
+}
 EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
 
 /**
-- 
1.7.10.4