[PATCH] nbd: fix TX/RX race condition

Janos Haar of First NetCenter Bt.  reported numerous crashes involving the
NBD driver.  With his help, this was tracked down to bogus bio vectors
which in turn was the result of a race condition between the
receive/transmit routines in the NBD driver.

The bug manifests itself like this:

CPU0				CPU1
do_nbd_request
	add req to queuelist
	nbd_send_request
		send req head
		for each bio
			kmap
			send
				nbd_read_stat
					nbd_find_request
					nbd_end_request
			kunmap

When CPU1 finishes nbd_end_request, the request and all its associated
bio's are freed.  So when CPU0 calls kunmap whose argument is derived from
the last bio, it may crash.

Under normal circumstances, the race occurs only on the last bio.  However,
if an error is encountered on the remote NBD server (such as an incorrect
magic number in the request), or if there were a bug in the server, it is
possible for the nbd_end_request to occur any time after the request's
addition to the queuelist.

The following patch fixes this problem by making sure that requests are not
added to the queuelist until after they have been completed transmission.

In order for the receiving side to be ready for responses involving
requests still being transmitted, the patch introduces the concept of the
active request.

When a response matches the current active request, its processing is
delayed until after the tranmission has come to a stop.

This has been tested by Janos and it has been successful in curing this
race condition.

From: Herbert Xu <herbert@gondor.apana.org.au>

  Here is an updated patch which removes the active_req wait in
  nbd_clear_queue and the associated memory barrier.

  I've also clarified this in the comment.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Cc: <djani22@dynamicweb.hu>
Cc: Paul Clements <Paul.Clements@SteelEye.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 68 insertions, 62 deletions

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 9e268ddedfbd..d5c8ee7d9815 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -54,11 +54,15 @@
 #include <linux/errno.h>
 #include <linux/file.h>
 #include <linux/ioctl.h>
+#include <linux/compiler.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
 #include <net/sock.h>
 
 #include <linux/devfs_fs_kernel.h>
 
 #include <asm/uaccess.h>
+#include <asm/system.h>
 #include <asm/types.h>
 
 #include <linux/nbd.h>
@@ -230,14 +234,6 @@ static int nbd_send_req(struct nbd_device *lo, struct request *req)
         request.len = htonl(size);
         memcpy(request.handle, &req, sizeof(req));
 
-        down(&lo->tx_lock);
-
-        if (!sock || !lo->sock) {
-                printk(KERN_ERR "%s: Attempted send on closed socket\n",
-                                lo->disk->disk_name);
-                goto error_out;
-        }
-
         dprintk(DBG_TX, "%s: request %p: sending control (%s@%llu,%luB)\n",
                         lo->disk->disk_name, req,
                         nbdcmd_to_ascii(nbd_cmd(req)),
@@ -276,11 +272,9 @@ static int nbd_send_req(struct nbd_device *lo, struct request *req)
                         }
                 }
         }
-        up(&lo->tx_lock);
         return 0;
 
 error_out:
-        up(&lo->tx_lock);
         return 1;
 }
 
@@ -289,9 +283,14 @@ static struct request *nbd_find_request(struct nbd_device *lo, char *handle)
         struct request *req;
         struct list_head *tmp;
         struct request *xreq;
+        int err;
 
         memcpy(&xreq, handle, sizeof(xreq));
 
+        err = wait_event_interruptible(lo->active_wq, lo->active_req != xreq);
+        if (unlikely(err))
+                goto out;
+
         spin_lock(&lo->queue_lock);
         list_for_each(tmp, &lo->queue_head) {
                 req = list_entry(tmp, struct request, queuelist);
@@ -302,7 +301,11 @@ static struct request *nbd_find_request(struct nbd_device *lo, char *handle)
                 return req;
         }
         spin_unlock(&lo->queue_lock);
-        return NULL;
+
+        err = -ENOENT;
+
+out:
+        return ERR_PTR(err);
 }
 
 static inline int sock_recv_bvec(struct socket *sock, struct bio_vec *bvec)
@@ -331,7 +334,11 @@ static struct request *nbd_read_stat(struct nbd_device *lo)
                 goto harderror;
         }
         req = nbd_find_request(lo, reply.handle);
-        if (req == NULL) {
+        if (unlikely(IS_ERR(req))) {
+                result = PTR_ERR(req);
+                if (result != -ENOENT)
+                        goto harderror;
+
                 printk(KERN_ERR "%s: Unexpected reply (%p)\n",
                                 lo->disk->disk_name, reply.handle);
                 result = -EBADR;
@@ -395,19 +402,24 @@ static void nbd_clear_que(struct nbd_device *lo)
 
         BUG_ON(lo->magic != LO_MAGIC);
 
-        do {
-                req = NULL;
-                spin_lock(&lo->queue_lock);
-                if (!list_empty(&lo->queue_head)) {
-                        req = list_entry(lo->queue_head.next, struct request, queuelist);
-                        list_del_init(&req->queuelist);
-                }
-                spin_unlock(&lo->queue_lock);
-                if (req) {
-                        req->errors++;
-                        nbd_end_request(req);
-                }
-        } while (req);
+        /*
+         * Because we have set lo->sock to NULL under the tx_lock, all
+         * modifications to the list must have completed by now.  For
+         * the same reason, the active_req must be NULL.
+         *
+         * As a consequence, we don't need to take the spin lock while
+         * purging the list here.
+         */
+        BUG_ON(lo->sock);
+        BUG_ON(lo->active_req);
+
+        while (!list_empty(&lo->queue_head)) {
+                req = list_entry(lo->queue_head.next, struct request,
+                                 queuelist);
+                list_del_init(&req->queuelist);
+                req->errors++;
+                nbd_end_request(req);
+        }
 }
 
 /*
@@ -435,11 +447,6 @@ static void do_nbd_request(request_queue_t * q)
 
                 BUG_ON(lo->magic != LO_MAGIC);
 
-                if (!lo->file) {
-                        printk(KERN_ERR "%s: Request when not-ready\n",
-                                        lo->disk->disk_name);
-                        goto error_out;
-                }
                 nbd_cmd(req) = NBD_CMD_READ;
                 if (rq_data_dir(req) == WRITE) {
                         nbd_cmd(req) = NBD_CMD_WRITE;
@@ -453,32 +460,34 @@ static void do_nbd_request(request_queue_t * q)
                 req->errors = 0;
                 spin_unlock_irq(q->queue_lock);
 
-                spin_lock(&lo->queue_lock);
-
-                if (!lo->file) {
-                        spin_unlock(&lo->queue_lock);
-                        printk(KERN_ERR "%s: failed between accept and semaphore, file lost\n",
-                                        lo->disk->disk_name);
+                down(&lo->tx_lock);
+                if (unlikely(!lo->sock)) {
+                        up(&lo->tx_lock);
+                        printk(KERN_ERR "%s: Attempted send on closed socket\n",
+                               lo->disk->disk_name);
                         req->errors++;
                         nbd_end_request(req);
                         spin_lock_irq(q->queue_lock);
                         continue;
                 }
 
-                list_add(&req->queuelist, &lo->queue_head);
-                spin_unlock(&lo->queue_lock);
+                lo->active_req = req;
 
                 if (nbd_send_req(lo, req) != 0) {
                         printk(KERN_ERR "%s: Request send failed\n",
                                         lo->disk->disk_name);
-                        if (nbd_find_request(lo, (char *)&req) != NULL) {
-                                /* we still own req */
+                        req->errors++;
+                        nbd_end_request(req);