[net/9p] Add gup/zero_copy support to VirtIO transport layer.

Modify p9_virtio_request() and req_done() functions to support
additional payload sent down to the transport layer through
tc->pubuf and tc->pkbuf.

Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>

net/9p/trans_common.h

@@ -12,6 +12,9 @@
  *
  */
 
+/* TRUE if it is user context */
+#define P9_IS_USER_CONTEXT (!segment_eq(get_fs(), KERNEL_DS))
+
 /**
  * struct trans_rpage_info - To store mapped page information in PDU.
  * @rp_alloc:Set if this structure is allocd, not a reuse unused space in pdu.

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 +156,14 @@ 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) {
+				struct trans_rpage_info *rp = req->tc->private;
+				/*Release pages */
+				p9_release_req_pages(rp);
+				if (rp->rp_alloc)
+					kfree(rp);
+				req->tc->private = NULL;
+			}
 			p9_client_cb(chan->client, req);
 		} else {
 			spin_unlock_irqrestore(&chan->lock, flags);
@@ -202,6 +211,38 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
 	return 1;
 }
 
+/**
+ * pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer,
+ * this takes a list of pages.
+ * @sg: scatter/gather list to pack into
+ * @start: which segment of the sg_list to start at
+ * @pdata_off: Offset into the first page
+ * @**pdata: a list of pages to add into sg.
+ * @count: amount of data to pack into the scatter/gather list
+ */
+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 +253,97 @@ 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;
+	struct trans_rpage_info *rpinfo = NULL;
+	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->pubuf && P9_IS_USER_CONTEXT)) {
+		int nr_pages = p9_nr_pages(req);
+		int rpinfo_size = sizeof(struct trans_rpage_info) +
+			sizeof(struct page *) * nr_pages;
+
+		if (rpinfo_size <= (req->tc->capacity - req->tc->size)) {
+			/* We can use sdata */
+			req->tc->private = req->tc->sdata + req->tc->size;
+			rpinfo = (struct trans_rpage_info *)req->tc->private;
+			rpinfo->rp_alloc = 0;
+		} else {
+			req->tc->private = kmalloc(rpinfo_size, GFP_NOFS);
+			if (!req->tc->private) {
+				P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: "
+					"private kmalloc returned NULL");
+				return -ENOMEM;
+			}
+			rpinfo = (struct trans_rpage_info *)req->tc->private;
+			rpinfo->rp_alloc = 1;
+		}
+
+		err = p9_payload_gup(req, &pdata_off, &pdata_len, nr_pages,
+				req->tc->id == P9_TREAD ? 1 : 0);
+		if (err < 0) {
+			if (rpinfo->rp_alloc)
+				kfree(rpinfo);
+			return err;
+		}
+	}
+
 	spin_lock_irqsave(&chan->lock, flags);
+
+	/* Handle out VirtIO ring buffers */
 	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);
+			req->tc->size);
+
+	if (req->tc->pbuf_size && (req->tc->id == P9_TWRITE)) {
+		/* We have additional write payload buffer to take care */
+		if (req->tc->pubuf && P9_IS_USER_CONTEXT) {
+			outp = pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM,
+					pdata_off, rpinfo->rp_data, pdata_len);
+		} else {
+			char *pbuf = req->tc->pubuf ? req->tc->pubuf :
+								req->tc->pkbuf;
+			outp = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, pbuf,
+					req->tc->pbuf_size);
+		}
+		out += outp;
+	}
+
+	/* Handle in VirtIO ring buffers */
+	if (req->tc->pbuf_size &&
+		((req->tc->id == P9_TREAD) || (req->tc->id == P9_TREADDIR))) {
+		/*
+		 * Take care of additional Read payload.
+		 * 11 is the read/write header = PDU Header(7) + IO Size (4).
+		 * Arrange in such a way that server places header in the
+		 * alloced memory and payload onto the user buffer.
+		 */
+		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->pubuf && P9_IS_USER_CONTEXT) {
+			in = pack_sg_list_p(chan->sg, out+inp, VIRTQUEUE_NUM,
+					pdata_off, rpinfo->rp_data, pdata_len);
+		} else {
+			char *pbuf = req->tc->pubuf ? req->tc->pubuf :
+								req->tc->pkbuf;
+			in = pack_sg_list(chan->sg, out+inp, VIRTQUEUE_NUM,
+					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) {
@@ -246,6 +362,8 @@ req_retry:
 			P9_DPRINTK(P9_DEBUG_TRANS,
 					"9p debug: "
 					"virtio rpc add_buf returned failure");
+			if (rpinfo && rpinfo->rp_alloc)
+				kfree(rpinfo);
 			return -EIO;
 		}
 	}