From: "Venkateswararao Jujjuri (JV)" <jvrao@linux.vnet.ibm.com>
To: v9fs-developer@lists.sourceforge.net
Cc: linux-fsdevel@vger.kernel.org,
"Venkateswararao Jujjuri (JV)" <jvrao@linux.vnet.ibm.com>
Subject: [PATCH 3/7] [net/9p] Add gup/zero_copy support to VirtIO transport layer.
Date: Sun, 13 Feb 2011 18:21:29 -0800 [thread overview]
Message-ID: <1297650093-10508-4-git-send-email-jvrao@linux.vnet.ibm.com> (raw)
In-Reply-To: <1297650093-10508-1-git-send-email-jvrao@linux.vnet.ibm.com>
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>
---
net/9p/trans_common.h | 3 +
net/9p/trans_virtio.c | 127 +++++++++++++++++++++++++++++++++++++++++++++++--
2 files changed, 125 insertions(+), 5 deletions(-)
diff --git a/net/9p/trans_common.h b/net/9p/trans_common.h
index 04977e0..7630922 100644
--- a/net/9p/trans_common.h
+++ b/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.
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index c8f3f72..f11358f 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 +156,14 @@ 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);
@@ -203,6 +212,38 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
}
/**
+ * 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
* @req: request to be issued
@@ -212,22 +253,96 @@ 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 (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)) {
+ /*
+ * 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 (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, 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 +361,8 @@ req_retry:
P9_DPRINTK(P9_DEBUG_TRANS,
"9p debug: "
"virtio rpc add_buf returned failure");
+ if (rpinfo && rpinfo->rp_alloc)
+ kfree(rpinfo);
return -EIO;
}
}
--
1.6.5.2
next prev parent reply other threads:[~2011-02-14 1:43 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-02-14 2:21 [net/9p] ZeroCopy patch series Venkateswararao Jujjuri (JV)
2011-02-14 2:21 ` [PATCH 1/7] [net/9p] Preparation and helper functions for zero copy Venkateswararao Jujjuri (JV)
2011-02-14 2:21 ` [PATCH 2/7] [net/9p] Assign type of transaction to tc->pdu->id which is otherwise unsed Venkateswararao Jujjuri (JV)
2011-02-14 2:21 ` Venkateswararao Jujjuri (JV) [this message]
2011-02-14 2:21 ` [PATCH 4/7] [net/9p] Add preferences to transport layer Venkateswararao Jujjuri (JV)
2011-02-14 2:21 ` [PATCH 5/7] [net/9p] Read side zerocopy changes for 9P2000.L protocol Venkateswararao Jujjuri (JV)
2011-02-14 2:21 ` [PATCH 6/7] [net/9p] Write " Venkateswararao Jujjuri (JV)
2011-02-14 2:21 ` [PATCH 7/7] [net/9p] Handle TREAD/RERROR case in !dotl case Venkateswararao Jujjuri (JV)
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1297650093-10508-4-git-send-email-jvrao@linux.vnet.ibm.com \
--to=jvrao@linux.vnet.ibm.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=v9fs-developer@lists.sourceforge.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).