Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs:
  [net/9p]: Introduce basic flow-control for VirtIO transport.
  9p: use the updated offset given by generic_write_checks
  [net/9p] Don't re-pin pages on retrying virtqueue_add_buf().
  [net/9p] Set the condition just before waking up.
  [net/9p] unconditional wake_up to proc waiting for space on VirtIO ring
  fs/9p: Add v9fs_dentry2v9ses
  fs/9p: Attach writeback_fid on first open with WR flag
  fs/9p: Open writeback fid in O_SYNC mode
  fs/9p: Use truncate_setsize instead of vmtruncate
  net/9p: Fix compile warning
  net/9p: Convert the in the 9p rpc call path to GFP_NOFS
  fs/9p: Fix race in initializing writeback fid

7 files changed, 64 insertions, 44 deletions

diff --git a/net/9p/client.c b/net/9p/client.c
index 347ec0cd2718..2ccbf04d37df 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -223,7 +223,7 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 
 	req = &c->reqs[row][col];
 	if (!req->tc) {
-		req->wq = kmalloc(sizeof(wait_queue_head_t), GFP_KERNEL);
+		req->wq = kmalloc(sizeof(wait_queue_head_t), GFP_NOFS);
 		if (!req->wq) {
 			printk(KERN_ERR "Couldn't grow tag array\n");
 			return ERR_PTR(-ENOMEM);
@@ -233,17 +233,17 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 				P9_TRANS_PREF_PAYLOAD_SEP) {
 			int alloc_msize = min(c->msize, 4096);
 			req->tc = kmalloc(sizeof(struct p9_fcall)+alloc_msize,
-					GFP_KERNEL);
+					  GFP_NOFS);
 			req->tc->capacity = alloc_msize;
 			req->rc = kmalloc(sizeof(struct p9_fcall)+alloc_msize,
-					GFP_KERNEL);
+					  GFP_NOFS);
 			req->rc->capacity = alloc_msize;
 		} else {
 			req->tc = kmalloc(sizeof(struct p9_fcall)+c->msize,
-					GFP_KERNEL);
+					  GFP_NOFS);
 			req->tc->capacity = c->msize;
 			req->rc = kmalloc(sizeof(struct p9_fcall)+c->msize,
-					GFP_KERNEL);
+					  GFP_NOFS);
 			req->rc->capacity = c->msize;
 		}
 		if ((!req->tc) || (!req->rc)) {
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 2ce515b859b3..8a4084fa8b5a 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -205,7 +205,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 				if (errcode)
 					break;
 
-				*sptr = kmalloc(len + 1, GFP_KERNEL);
+				*sptr = kmalloc(len + 1, GFP_NOFS);
 				if (*sptr == NULL) {
 					errcode = -EFAULT;
 					break;
@@ -273,7 +273,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 				if (!errcode) {
 					*wnames =
 					    kmalloc(sizeof(char *) * *nwname,
-						    GFP_KERNEL);
+						    GFP_NOFS);
 					if (!*wnames)
 						errcode = -ENOMEM;
 				}
@@ -317,7 +317,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 					*wqids =
 					    kmalloc(*nwqid *
 						    sizeof(struct p9_qid),
-						    GFP_KERNEL);
+						    GFP_NOFS);
 					if (*wqids == NULL)
 						errcode = -ENOMEM;
 				}
diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c
index d62b9aa58df8..9172ab78fcb0 100644
--- a/net/9p/trans_common.c
+++ b/net/9p/trans_common.c
@@ -41,9 +41,9 @@ EXPORT_SYMBOL(p9_release_req_pages);
 int
 p9_nr_pages(struct p9_req_t *req)
 {
-	int start_page, end_page;
-	start_page =  (unsigned long long)req->tc->pubuf >> PAGE_SHIFT;
-	end_page = ((unsigned long long)req->tc->pubuf + req->tc->pbuf_size +
+	unsigned long start_page, end_page;
+	start_page =  (unsigned long)req->tc->pubuf >> PAGE_SHIFT;
+	end_page = ((unsigned long)req->tc->pubuf + req->tc->pbuf_size +
 			PAGE_SIZE - 1) >> PAGE_SHIFT;
 	return end_page - start_page;
 }
@@ -69,8 +69,8 @@ p9_payload_gup(struct p9_req_t *req, size_t *pdata_off, int *pdata_len,
 	*pdata_off = (size_t)req->tc->pubuf & (PAGE_SIZE-1);
 
 	if (*pdata_off)
-		first_page_bytes = min((PAGE_SIZE - *pdata_off),
-				req->tc->pbuf_size);
+		first_page_bytes = min(((size_t)PAGE_SIZE - *pdata_off),
+				       req->tc->pbuf_size);
 
 	rpinfo = req->tc->private;
 	pdata_mapped_pages = get_user_pages_fast((unsigned long)req->tc->pubuf,
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index a30471e51740..aa5672b15eae 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -350,7 +350,7 @@ static void p9_read_work(struct work_struct *work)
 
 		if (m->req->rc == NULL) {
 			m->req->rc = kmalloc(sizeof(struct p9_fcall) +
-						m->client->msize, GFP_KERNEL);
+						m->client->msize, GFP_NOFS);
 			if (!m->req->rc) {
 				m->req = NULL;
 				err = -ENOMEM;
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 29a54ccd213d..150e0c4bbf40 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -424,7 +424,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 	struct p9_rdma_context *rpl_context = NULL;
 
 	/* Allocate an fcall for the reply */
-	rpl_context = kmalloc(sizeof *rpl_context, GFP_KERNEL);
+	rpl_context = kmalloc(sizeof *rpl_context, GFP_NOFS);
 	if (!rpl_context) {
 		err = -ENOMEM;
 		goto err_close;
@@ -437,7 +437,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 	 */
 	if (!req->rc) {
 		req->rc = kmalloc(sizeof(struct p9_fcall)+client->msize,
-								GFP_KERNEL);
+				  GFP_NOFS);
 		if (req->rc) {
 			req->rc->sdata = (char *) req->rc +
 						sizeof(struct p9_fcall);
@@ -468,7 +468,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 	req->rc = NULL;
 
 	/* Post the request */
-	c = kmalloc(sizeof *c, GFP_KERNEL);
+	c = kmalloc(sizeof *c, GFP_NOFS);
 	if (!c) {
 		err = -ENOMEM;
 		goto err_free1;
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 9b550ed9c711..e8f046b07182 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -43,6 +43,7 @@
 #include <net/9p/client.h>
 #include <net/9p/transport.h>
 #include <linux/scatterlist.h>
+#include <linux/swap.h>
 #include <linux/virtio.h>
 #include <linux/virtio_9p.h>
 #include "trans_common.h"
@@ -51,6 +52,8 @@
 
 /* a single mutex to manage channel initialization and attachment */
 static DEFINE_MUTEX(virtio_9p_lock);
+static DECLARE_WAIT_QUEUE_HEAD(vp_wq);
+static atomic_t vp_pinned = ATOMIC_INIT(0);
 
 /**
  * struct virtio_chan - per-instance transport information
@@ -78,7 +81,10 @@ struct virtio_chan {
 	struct virtqueue *vq;
 	int ring_bufs_avail;
 	wait_queue_head_t *vc_wq;
-
+	/* This is global limit. Since we don't have a global structure,
+	 * will be placing it in each channel.
+	 */
+	int p9_max_pages;
 	/* Scatterlist: can be too big for stack. */
 	struct scatterlist sg[VIRTQUEUE_NUM];
 
@@ -141,34 +147,36 @@ static void req_done(struct virtqueue *vq)
 
 	P9_DPRINTK(P9_DEBUG_TRANS, ": request done\n");
 
-	do {
+	while (1) {
 		spin_lock_irqsave(&chan->lock, flags);
 		rc = virtqueue_get_buf(chan->vq, &len);
 
-		if (rc != NULL) {
-			if (!chan->ring_bufs_avail) {
-				chan->ring_bufs_avail = 1;
-				wake_up(chan->vc_wq);
-			}
-			spin_unlock_irqrestore(&chan->lock, flags);
-			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;
-			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 {
+		if (rc == NULL) {
 			spin_unlock_irqrestore(&chan->lock, flags);
+			break;
+		}
+
+		chan->ring_bufs_avail = 1;
+		spin_unlock_irqrestore(&chan->lock, flags);
+		/* Wakeup if anyone waiting for VirtIO ring space. */
+		wake_up(chan->vc_wq);
+		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);
+		if (req->tc->private) {
+			struct trans_rpage_info *rp = req->tc->private;
+			int p = rp->rp_nr_pages;
+			/*Release pages */
+			p9_release_req_pages(rp);
+			atomic_sub(p, &vp_pinned);
+			wake_up(&vp_wq);
+			if (rp->rp_alloc)
+				kfree(rp);
+			req->tc->private = NULL;
 		}
-	} while (rc != NULL);
+		req->status = REQ_STATUS_RCVD;
+		p9_client_cb(chan->client, req);
+	}
 }
 
 /**
@@ -263,7 +271,6 @@ p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
 
 	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)) {
@@ -271,6 +278,14 @@ req_retry:
 		int rpinfo_size = sizeof(struct trans_rpage_info) +
 			sizeof(struct page *) * nr_pages;
 
+		if (atomic_read(&vp_pinned) >= chan->p9_max_pages) {
+			err = wait_event_interruptible(vp_wq,
+				atomic_read(&vp_pinned) < chan->p9_max_pages);
+			if (err  == -ERESTARTSYS)
+				return err;
+			P9_DPRINTK(P9_DEBUG_TRANS, "9p: May gup pages now.\n");
+		}
+
 		if (rpinfo_size <= (req->tc->capacity - req->tc->size)) {
 			/* We can use sdata */
 			req->tc->private = req->tc->sdata + req->tc->size;
@@ -293,9 +308,12 @@ req_retry:
 			if (rpinfo->rp_alloc)
 				kfree(rpinfo);
 			return err;
+		} else {
+			atomic_add(rpinfo->rp_nr_pages, &vp_pinned);
 		}
 	}
 
+req_retry_pinned:
 	spin_lock_irqsave(&chan->lock, flags);
 
 	/* Handle out VirtIO ring buffers */
@@ -356,7 +374,7 @@ req_retry:
 				return err;
 
 			P9_DPRINTK(P9_DEBUG_TRANS, "9p:Retry virtio request\n");
-			goto req_retry;
+			goto req_retry_pinned;
 		} else {
 			spin_unlock_irqrestore(&chan->lock, flags);
 			P9_DPRINTK(P9_DEBUG_TRANS,
@@ -453,6 +471,8 @@ static int p9_virtio_probe(struct virtio_device *vdev)
 	}
 	init_waitqueue_head(chan->vc_wq);
 	chan->ring_bufs_avail = 1;
+	/* Ceiling limit to avoid denial of service attacks */
+	chan->p9_max_pages = nr_free_buffer_pages()/4;
 
 	mutex_lock(&virtio_9p_lock);
 	list_add_tail(&chan->chan_list, &virtio_chan_list);
diff --git a/net/9p/util.c b/net/9p/util.c
index e048701a72d2..b84619b5ba22 100644
--- a/net/9p/util.c
+++ b/net/9p/util.c
@@ -92,7 +92,7 @@ int p9_idpool_get(struct p9_idpool *p)
 	unsigned long flags;
 
 retry:
-	if (idr_pre_get(&p->pool, GFP_KERNEL) == 0)
+	if (idr_pre_get(&p->pool, GFP_NOFS) == 0)
 		return 0;
 
 	spin_lock_irqsave(&p->lock, flags);