[PATCH v2 4/5]nbd: make nbd device wait for its users.

From: Pranay Kr. Srivastava
Date: Thu Jun 02 2016 - 11:27:02 EST


When a timeout occurs or a recv fails, then
instead of abruplty killing nbd block device
wait for it's users to finish.

This is more required when filesystem(s) like
ext2 or ext3 don't expect their buffer heads to
disappear while the filesystem is mounted.

Each open of a nbd device is refcounted, while
the userland program [nbd-client] doing the
NBD_DO_IT ioctl would now wait for any other users
of this device before invalidating the nbd device.

Signed-off-by: Pranay Kr. Srivastava <pranjas@xxxxxxxxx>
---
drivers/block/nbd.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 58 insertions(+)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index d1d898d..4da40dc 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -70,10 +70,13 @@ struct nbd_device {
#if IS_ENABLED(CONFIG_DEBUG_FS)
struct dentry *dbg_dir;
#endif
+ atomic_t inuse;
/*
*This is specifically for calling sock_shutdown, for now.
*/
struct work_struct ws_shutdown;
+ struct kref users;
+ struct completion user_completion;
};

#if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -104,6 +107,7 @@ static DEFINE_SPINLOCK(nbd_lock);
* Shutdown function for nbd_dev work struct.
*/
static void nbd_ws_func_shutdown(struct work_struct *);
+static void nbd_kref_release(struct kref *);

static inline struct device *nbd_to_dev(struct nbd_device *nbd)
{
@@ -682,6 +686,8 @@ static void nbd_reset(struct nbd_device *nbd)
nbd->flags = 0;
nbd->xmit_timeout = 0;
INIT_WORK(&nbd->ws_shutdown, nbd_ws_func_shutdown);
+ init_completion(&nbd->user_completion);
+ kref_init(&nbd->users);
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
del_timer_sync(&nbd->timeout_timer);
}
@@ -815,6 +821,14 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
kthread_stop(thread);

sock_shutdown(nbd);
+ /*
+ * kref_init initializes with ref count as 1,
+ * nbd_client, or the user-land program executing
+ * this ioctl will make the refcount to 2[at least]
+ * so subtracting 2 from refcount.
+ */
+ kref_sub(&nbd->users, 2, nbd_kref_release);
+ wait_for_completion(&nbd->user_completion);
mutex_lock(&nbd->tx_lock);
nbd_clear_que(nbd);
kill_bdev(bdev);
@@ -865,13 +879,56 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,

return error;
}
+static void nbd_kref_release(struct kref *kref_users)
+{
+ struct nbd_device *nbd = container_of(kref_users, struct nbd_device,
+ users);
+ pr_debug("Releasing kref [%s]\n", __func__);
+ atomic_set(&nbd->inuse, 0);
+ complete(&nbd->user_completion);
+
+}
+
+static int nbd_open(struct block_device *bdev, fmode_t mode)
+{
+ struct nbd_device *nbd_dev = bdev->bd_disk->private_data;
+
+ if (kref_get_unless_zero(&nbd_dev->users))
+ atomic_set(&nbd_dev->inuse, 1);
+
+ pr_debug("Opening nbd_dev %s. Active users = %u\n",
+ bdev->bd_disk->disk_name,
+ atomic_read(&nbd_dev->users.refcount) - 1);
+ return 0;
+}
+
+static void nbd_release(struct gendisk *disk, fmode_t mode)
+{
+ struct nbd_device *nbd_dev = disk->private_data;
+ /*
+ *kref_init initializes ref count to 1, so we
+ *we check for refcount to be 2 for a final put.
+ *
+ *kref needs to be re-initialized just here as the
+ *other process holding it must see the ref count as 2.
+ */
+ if (atomic_read(&nbd_dev->inuse))
+ kref_put(&nbd_dev->users, nbd_kref_release);
+
+ pr_debug("Closing nbd_dev %s. Active users = %u\n",
+ disk->disk_name,
+ atomic_read(&nbd_dev->users.refcount) - 1);
+}

static const struct block_device_operations nbd_fops = {
.owner = THIS_MODULE,
.ioctl = nbd_ioctl,
.compat_ioctl = nbd_ioctl,
+ .open = nbd_open,
+ .release = nbd_release
};

+
static void nbd_ws_func_shutdown(struct work_struct *ws_nbd)
{
struct nbd_device *nbd_dev = container_of(ws_nbd, struct nbd_device,
@@ -1107,6 +1164,7 @@ static int __init nbd_init(void)
disk->fops = &nbd_fops;
disk->private_data = &nbd_dev[i];
sprintf(disk->disk_name, "nbd%d", i);
+ atomic_set(&nbd_dev[i].inuse, 0);
nbd_reset(&nbd_dev[i]);
add_disk(disk);
}
--
2.6.2