summaryrefslogtreecommitdiffstats
path: root/drivers/block/nbd.c
diff options
context:
space:
mode:
authorLaurent Vivier <Laurent.Vivier@bull.net>2008-04-29 01:02:46 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2008-04-29 08:06:23 -0700
commit48cf6061b30205b29b306bf9bc22dd6f0b091461 (patch)
treebba7827177587a17160c29392651aa27aa7f98fd /drivers/block/nbd.c
parent8c4dd6068221cd1d0d90490ace80eb4344914a8c (diff)
downloadlinux-48cf6061b30205b29b306bf9bc22dd6f0b091461.tar.bz2
NBD: allow nbd to be used locally
This patch allows Network Block Device to be mounted locally (nbd-client to nbd-server over 127.0.0.1). It creates a kthread to avoid the deadlock described in NBD tools documentation. So, if nbd-client hangs waiting for pages, the kblockd thread can continue its work and free pages. I have tested the patch to verify that it avoids the hang that always occurs when writing to a localhost nbd connection. I have also tested to verify that no performance degradation results from the additional thread and queue. Patch originally from Laurent Vivier. Signed-off-by: Paul Clements <paul.clements@steeleye.com> Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'drivers/block/nbd.c')
-rw-r--r--drivers/block/nbd.c144
1 files changed, 95 insertions, 49 deletions
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 60cc54368b66..8e33de6bea33 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -29,6 +29,7 @@
#include <linux/kernel.h>
#include <net/sock.h>
#include <linux/net.h>
+#include <linux/kthread.h>
#include <asm/uaccess.h>
#include <asm/system.h>
@@ -441,6 +442,85 @@ static void nbd_clear_que(struct nbd_device *lo)
}
+static void nbd_handle_req(struct nbd_device *lo, struct request *req)
+{
+ if (!blk_fs_request(req))
+ goto error_out;
+
+ nbd_cmd(req) = NBD_CMD_READ;
+ if (rq_data_dir(req) == WRITE) {
+ nbd_cmd(req) = NBD_CMD_WRITE;
+ if (lo->flags & NBD_READ_ONLY) {
+ printk(KERN_ERR "%s: Write on read-only\n",
+ lo->disk->disk_name);
+ goto error_out;
+ }
+ }
+
+ req->errors = 0;
+
+ mutex_lock(&lo->tx_lock);
+ if (unlikely(!lo->sock)) {
+ mutex_unlock(&lo->tx_lock);
+ printk(KERN_ERR "%s: Attempted send on closed socket\n",
+ lo->disk->disk_name);
+ req->errors++;
+ nbd_end_request(req);
+ return;
+ }
+
+ lo->active_req = req;
+
+ if (nbd_send_req(lo, req) != 0) {
+ printk(KERN_ERR "%s: Request send failed\n",
+ lo->disk->disk_name);
+ req->errors++;
+ nbd_end_request(req);
+ } else {
+ spin_lock(&lo->queue_lock);
+ list_add(&req->queuelist, &lo->queue_head);
+ spin_unlock(&lo->queue_lock);
+ }
+
+ lo->active_req = NULL;
+ mutex_unlock(&lo->tx_lock);
+ wake_up_all(&lo->active_wq);
+
+ return;
+
+error_out:
+ req->errors++;
+ nbd_end_request(req);
+}
+
+static int nbd_thread(void *data)
+{
+ struct nbd_device *lo = data;
+ struct request *req;
+
+ set_user_nice(current, -20);
+ while (!kthread_should_stop() || !list_empty(&lo->waiting_queue)) {
+ /* wait for something to do */
+ wait_event_interruptible(lo->waiting_wq,
+ kthread_should_stop() ||
+ !list_empty(&lo->waiting_queue));
+
+ /* extract request */
+ if (list_empty(&lo->waiting_queue))
+ continue;
+
+ spin_lock_irq(&lo->queue_lock);
+ req = list_entry(lo->waiting_queue.next, struct request,
+ queuelist);
+ list_del_init(&req->queuelist);
+ spin_unlock_irq(&lo->queue_lock);
+
+ /* handle request */
+ nbd_handle_req(lo, req);
+ }
+ return 0;
+}
+
/*
* We always wait for result of write, for now. It would be nice to make it optional
* in future
@@ -456,65 +536,23 @@ static void do_nbd_request(struct request_queue * q)
struct nbd_device *lo;
blkdev_dequeue_request(req);
+
+ spin_unlock_irq(q->queue_lock);
+
dprintk(DBG_BLKDEV, "%s: request %p: dequeued (flags=%x)\n",
req->rq_disk->disk_name, req, req->cmd_type);
- if (!blk_fs_request(req))
- goto error_out;
-
lo = req->rq_disk->private_data;
BUG_ON(lo->magic != LO_MAGIC);
- nbd_cmd(req) = NBD_CMD_READ;
- if (rq_data_dir(req) == WRITE) {
- nbd_cmd(req) = NBD_CMD_WRITE;
- if (lo->flags & NBD_READ_ONLY) {
- printk(KERN_ERR "%s: Write on read-only\n",
- lo->disk->disk_name);
- goto error_out;
- }
- }
-
- req->errors = 0;
- spin_unlock_irq(q->queue_lock);
-
- mutex_lock(&lo->tx_lock);
- if (unlikely(!lo->sock)) {
- mutex_unlock(&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;
- }
+ spin_lock_irq(&lo->queue_lock);
+ list_add_tail(&req->queuelist, &lo->waiting_queue);
+ spin_unlock_irq(&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);
- req->errors++;
- nbd_end_request(req);
- } else {
- spin_lock(&lo->queue_lock);
- list_add(&req->queuelist, &lo->queue_head);
- spin_unlock(&lo->queue_lock);
- }
-
- lo->active_req = NULL;
- mutex_unlock(&lo->tx_lock);
- wake_up_all(&lo->active_wq);
+ wake_up(&lo->waiting_wq);
spin_lock_irq(q->queue_lock);
- continue;
-
-error_out:
- req->errors++;
- spin_unlock(q->queue_lock);
- nbd_end_request(req);
- spin_lock(q->queue_lock);
}
}
@@ -524,6 +562,7 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
struct nbd_device *lo = inode->i_bdev->bd_disk->private_data;
int error;
struct request sreq ;
+ struct task_struct *thread;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -606,7 +645,12 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
case NBD_DO_IT:
if (!lo->file)
return -EINVAL;
+ thread = kthread_create(nbd_thread, lo, lo->disk->disk_name);
+ if (IS_ERR(thread))
+ return PTR_ERR(thread);
+ wake_up_process(thread);
error = nbd_do_it(lo);
+ kthread_stop(thread);
if (error)
return error;
sock_shutdown(lo, 1);
@@ -695,10 +739,12 @@ static int __init nbd_init(void)
nbd_dev[i].file = NULL;
nbd_dev[i].magic = LO_MAGIC;
nbd_dev[i].flags = 0;
+ INIT_LIST_HEAD(&nbd_dev[i].waiting_queue);
spin_lock_init(&nbd_dev[i].queue_lock);
INIT_LIST_HEAD(&nbd_dev[i].queue_head);
mutex_init(&nbd_dev[i].tx_lock);
init_waitqueue_head(&nbd_dev[i].active_wq);
+ init_waitqueue_head(&nbd_dev[i].waiting_wq);
nbd_dev[i].blksize = 1024;
nbd_dev[i].bytesize = 0;
disk->major = NBD_MAJOR;