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 1/2] [net/9p]Serialize virtqueue operations to make VirtIO transport SMP safe.
Date: Fri, 1 Oct 2010 16:56:16 -0700 [thread overview]
Message-ID: <1285977377-28736-1-git-send-email-jvrao@linux.vnet.ibm.com> (raw)
Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
---
net/9p/trans_virtio.c | 34 ++++++++++++++++++++++++----------
1 files changed, 24 insertions(+), 10 deletions(-)
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index dcfbe99..0df84bf 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -134,16 +134,24 @@ static void req_done(struct virtqueue *vq)
struct p9_fcall *rc;
unsigned int len;
struct p9_req_t *req;
+ unsigned long flags;
P9_DPRINTK(P9_DEBUG_TRANS, ": request done\n");
- while ((rc = virtqueue_get_buf(chan->vq, &len)) != NULL) {
- P9_DPRINTK(P9_DEBUG_TRANS, ": rc %p\n", rc);
- P9_DPRINTK(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag);
- req = p9_tag_lookup(chan->client, rc->tag);
- req->status = REQ_STATUS_RCVD;
- p9_client_cb(chan->client, req);
- }
+ do {
+ spin_lock_irqsave(&chan->lock, flags);
+ rc = virtqueue_get_buf(chan->vq, &len);
+ spin_unlock_irqrestore(&chan->lock, flags);
+
+ if (rc != NULL) {
+ P9_DPRINTK(P9_DEBUG_TRANS, ": rc %p\n", rc);
+ P9_DPRINTK(P9_DEBUG_TRANS, ": lookup tag %d\n",
+ rc->tag);
+ req = p9_tag_lookup(chan->client, rc->tag);
+ req->status = REQ_STATUS_RCVD;
+ p9_client_cb(chan->client, req);
+ }
+ } while (rc != NULL);
}
/**
@@ -199,23 +207,29 @@ p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
int in, out;
struct virtio_chan *chan = client->trans;
char *rdata = (char *)req->rc+sizeof(struct p9_fcall);
+ unsigned long flags;
+ int err;
P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request\n");
+ req->status = REQ_STATUS_SENT;
+
+ 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);
- req->status = REQ_STATUS_SENT;
-
- if (virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc) < 0) {
+ err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc);
+ if (err < 0) {
+ spin_unlock_irqrestore(&chan->lock, flags);
P9_DPRINTK(P9_DEBUG_TRANS,
"9p debug: virtio rpc add_buf returned failure");
return -EIO;
}
virtqueue_kick(chan->vq);
+ spin_unlock_irqrestore(&chan->lock, flags);
P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request kicked\n");
return 0;
--
1.6.5.2
next reply other threads:[~2010-10-01 23:40 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-01 23:56 Venkateswararao Jujjuri (JV) [this message]
2010-10-01 23:56 ` [PATCH 2/2] [net/9p] Add waitq to VirtIO transport Venkateswararao Jujjuri (JV)
2010-10-05 14:45 ` Aneesh Kumar K. V
2010-10-05 23:26 ` Venkateswararao Jujjuri (JV)
2010-10-06 6:21 ` Aneesh Kumar K. V
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=1285977377-28736-1-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).