[RFC] [PATCH 1/7] [net/9p] Additional elements to p9_fcall to accomodate zero copy.

["Venkateswararao Jujjuri (JV)" <jvrao@linux.vnet.ibm.com>]

Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
---
 net/9p/trans_virtio.c |   85 +++++++++++++++++++++++++++++++++++++++++++++---
 1 files changed, 79 insertions(+), 6 deletions(-)

diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index c8f3f72..607f064 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -45,6 +45,7 @@
 #include <linux/scatterlist.h>
 #include <linux/virtio.h>
 #include <linux/virtio_9p.h>
+#include "trans_common.h"
 
 #define VIRTQUEUE_NUM	128
 
@@ -155,6 +156,12 @@ static void req_done(struct virtqueue *vq)
 					rc->tag);
 			req = p9_tag_lookup(chan->client, rc->tag);
 			req->status = REQ_STATUS_RCVD;
+			if (req->tc->private) {
+				/*Release pages */
+				p9_release_req_pages(req->tc->private);
+				kfree(req->tc->private);
+				req->tc->private = NULL;
+			}
 			p9_client_cb(chan->client, req);
 		} else {
 			spin_unlock_irqrestore(&chan->lock, flags);
@@ -202,6 +209,30 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
 	return 1;
 }
 
+static int
+pack_sg_list_p(struct scatterlist *sg, int start, int limit, size_t pdata_off,
+		struct page **pdata, int count)
+{
+	int s;
+	int i = 0;
+	int index = start;
+
+	if (pdata_off) {
+		s = min((int)(PAGE_SIZE - pdata_off), count);
+		sg_set_page(&sg[index++], pdata[i++], s, pdata_off);
+		count -= s;
+	}
+
+	while (count) {
+		BUG_ON(index > limit);
+		s = min((int)PAGE_SIZE, count);
+		sg_set_page(&sg[index++], pdata[i++], s, 0);
+		count -= s;
+	}
+
+	return index-start;
+}
+
 /**
  * p9_virtio_request - issue a request
  * @client: client instance issuing the request
@@ -212,22 +243,64 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
 static int
 p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
 {
-	int in, out;
+	int in, out, inp, outp;
 	struct virtio_chan *chan = client->trans;
 	char *rdata = (char *)req->rc+sizeof(struct p9_fcall);
 	unsigned long flags;
-	int err;
+	size_t pdata_off=0;
+	virtio_rpage_info_t *rpinfo;
+	int err, pdata_len=0;
 
 	P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request\n");
 
 req_retry:
 	req->status = REQ_STATUS_SENT;
 
+	if (req->tc->pbuf_size &&
+			(req->tc->pbuf && !segment_eq(get_fs(), KERNEL_DS))) {
+		err = payload_gup(req, &pdata_off, &pdata_len,
+				req->tc->id == P9_TREAD ? 1 : 0 );
+		if (err < 0)
+			return err;
+	}
+	rpinfo = (virtio_rpage_info_t *)req->tc->private;
+
 	spin_lock_irqsave(&chan->lock, flags);
-	out = pack_sg_list(chan->sg, 0, VIRTQUEUE_NUM, req->tc->sdata,
-								req->tc->size);
-	in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM-out, rdata,
-								client->msize);
+
+	/* Handle out VirtIO ring buffers */
+	if (req->tc->pbuf_size && (req->tc->id == P9_TWRITE)) {
+		/* We have additional write payload buffer to take care */
+		out = pack_sg_list(chan->sg, 0, VIRTQUEUE_NUM, req->tc->sdata,
+				req->tc->size);
+		outp = pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM,
+				pdata_off, rpinfo->vp_data, pdata_len);
+		out += outp;
+	} else {
+		out = pack_sg_list(chan->sg, 0, VIRTQUEUE_NUM, req->tc->sdata,
+				req->tc->size);
+	}
+
+	/* Handle in VirtIO ring buffers */
+	if (req->tc->pbuf_size && (req->tc->id == P9_TREAD)) {
+		/* We have additional Read payload buffer to take care */
+		inp = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, rdata, 11);
+		/* 
+		 * Running executables in the filesystem may result in
+		 * a read request with kernel buffer as opposed to user buffer.
+		 */
+		if (req->tc->pbuf && !segment_eq(get_fs(), KERNEL_DS)) {
+			in = pack_sg_list_p(chan->sg, out+inp, VIRTQUEUE_NUM,
+					pdata_off, rpinfo->vp_data, pdata_len);
+		} else {
+			in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM,
+					(char *)req->tc->pbuf,
+					req->tc->pbuf_size);
+		}
+		in += inp;
+	} else {
+		in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, rdata,
+				client->msize);
+	}
 
 	err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc);
 	if (err < 0) {
-- 
1.6.5.2