[PATCH 2/2] rbd: prevent open for image being removed

[PATCH 2/2] rbd: prevent open for image being removed

[Alex Elder]

An open request for a mapped rbd image can arrive while removal of
that mapping is underway.  The control mutex and an open count is
protect a mapped device that's in use from being removed.  But it
is possible for the removal of the mapping to reach the point of no
return *after* a racing open has concluded it is OK to proceed.  The
result of this is not good.

Define and use a flag to indicate a mapping is getting removed to
avoid this problem.

This addresses http://tracker.newdream.net/issues/3427

Signed-off-by: Alex Elder <elder@inktank.com>
---
 drivers/block/rbd.c |   15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 9eb1631..760f7f7 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -264,6 +264,7 @@ struct rbd_device {

 enum rbd_dev_flags {
 	rbd_dev_flag_exists,	/* mapped snapshot has not been deleted */
+	rbd_dev_flag_removing,	/* this mapping is being removed */
 };

 static DEFINE_MUTEX(ctl_mutex);	  /* Serialize open/close/setup/teardown */
@@ -351,17 +352,22 @@ static int rbd_dev_v2_refresh(struct rbd_device
*rbd_dev, u64 *hver);
 static int rbd_open(struct block_device *bdev, fmode_t mode)
 {
 	struct rbd_device *rbd_dev = bdev->bd_disk->private_data;
+	int ret = 0;

 	if ((mode & FMODE_WRITE) && rbd_dev->mapping.read_only)
 		return -EROFS;

 	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-	(void) get_device(&rbd_dev->dev);
-	set_device_ro(bdev, rbd_dev->mapping.read_only);
-	rbd_dev->open_count++;
+	if (!test_bit(rbd_dev_flag_removing, &rbd_dev->flags)) {
+		(void) get_device(&rbd_dev->dev);
+		set_device_ro(bdev, rbd_dev->mapping.read_only);
+		rbd_dev->open_count++;
+	} else {
+		ret = -ENOENT;
+	}
 	mutex_unlock(&ctl_mutex);

-	return 0;
+	return ret;
 }

 static int rbd_release(struct gendisk *disk, fmode_t mode)
@@ -3796,6 +3802,7 @@ static ssize_t rbd_remove(struct bus_type *bus,
 		ret = -EBUSY;
 		goto done;
 	}
+	set_bit(rbd_dev_flag_removing, &rbd_dev->flags);

 	rbd_remove_all_snaps(rbd_dev);
 	rbd_bus_del_dev(rbd_dev);
-- 
1.7.9.5

[PATCH 0/2] rbd: manage racing opens/removes

[Alex Elder]

A recent change to rbd prevented rbd devices from being unmapped
when they were in use.  However that change did not address a
different, but related problem.  It is possible for an open (the
one that would bump the open count from 0 to 1) to begin after
a request to remove the rbd device has decided it can proceed.

To fix this, define a new "removing" flag to prevent opens from
proceeding once ermoval of a device has begun.  The first patch
in this series defines a new flags field, and uses it for this
as well as the "exists" flag for snapshot mappings.

					-Alex

[PATCH 1/2] rbd: define flags field, use it for exists flag
[PATCH 2/2] rbd: prevent open for image being removed

[PATCH 1/2] rbd: define flags field, use it for exists flag

[Alex Elder]

Define a new rbd device flags field, manipulated using bit
operations.  Replace the use of the current "exists" flag with a bit
in this new "flags" field.  Add a little commentary about the
"exists" flag, which does not need to be manipulated atomically.

Signed-off-by: Alex Elder <elder@inktank.com>
---
 drivers/block/rbd.c |   37 ++++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 177ba0c..107df40 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -262,7 +262,7 @@ struct rbd_device {
 	spinlock_t		lock;		/* queue lock */

 	struct rbd_image_header	header;
-	atomic_t		exists;
+	unsigned long		flags;
 	struct rbd_spec		*spec;

 	char			*header_name;
@@ -291,6 +291,12 @@ struct rbd_device {
 	unsigned long		open_count;
 };

+/* Flag bits for rbd_dev->flags */
+
+enum rbd_dev_flags {
+	rbd_dev_flag_exists,	/* mapped snapshot has not been deleted */
+};
+
 static DEFINE_MUTEX(ctl_mutex);	  /* Serialize open/close/setup/teardown */

 static LIST_HEAD(rbd_dev_list);    /* devices */
@@ -790,7 +796,8 @@ static int rbd_dev_set_mapping(struct rbd_device
*rbd_dev)
 			goto done;
 		rbd_dev->mapping.read_only = true;
 	}
-	atomic_set(&rbd_dev->exists, 1);
+	set_bit(rbd_dev_flag_exists, &rbd_dev->flags);
+
 done:
 	return ret;
 }
@@ -1886,9 +1893,14 @@ static void rbd_request_fn(struct request_queue *q)
 			rbd_assert(rbd_dev->spec->snap_id == CEPH_NOSNAP);
 		}

-		/* Quit early if the snapshot has disappeared */
-
-		if (!atomic_read(&rbd_dev->exists)) {
+		/*
+		 * Quit early if the mapped snapshot no longer
+		 * exists.  It's still possible the snapshot will
+		 * have disappeared by the time our request arrives
+		 * at the osd, but there's no sense in sending it if
+		 * we already know.
+		 */
+		if (!test_bit(rbd_dev_flag_exists, &rbd_dev->flags)) {
 			dout("request for non-existent snapshot");
 			rbd_assert(rbd_dev->spec->snap_id != CEPH_NOSNAP);
 			result = -ENXIO;
@@ -2578,7 +2590,7 @@ struct rbd_device *rbd_dev_create(struct
rbd_client *rbdc,
 		return NULL;

 	spin_lock_init(&rbd_dev->lock);
-	atomic_set(&rbd_dev->exists, 0);
+	rbd_dev->flags = 0;
 	INIT_LIST_HEAD(&rbd_dev->node);
 	INIT_LIST_HEAD(&rbd_dev->snaps);
 	init_rwsem(&rbd_dev->header_rwsem);
@@ -3207,10 +3219,17 @@ static int rbd_dev_snaps_update(struct
rbd_device *rbd_dev)
 		if (snap_id == CEPH_NOSNAP || (snap && snap->id > snap_id)) {
 			struct list_head *next = links->next;

-			/* Existing snapshot not in the new snap context */
-
+			/*
+			 * A previously-existing snapshot is not in
+			 * the new snap context.
+			 *
+			 * If the now missing snapshot is the one the
+			 * image is mapped to, clear its exists flag
+			 * so we can avoid sending any more requests
+			 * to it.
+			 */
 			if (rbd_dev->spec->snap_id == snap->id)
-				atomic_set(&rbd_dev->exists, 0);
+				clear_bit(rbd_dev_flag_exists, &rbd_dev->flags);
 			rbd_remove_snap_dev(snap);
 			dout("%ssnap id %llu has been removed\n",
 				rbd_dev->spec->snap_id == snap->id ?
-- 
1.7.9.5

[PATCH 2/2] rbd: prevent open for image being removed

[Alex Elder]

An open request for a mapped rbd image can arrive while removal of
that mapping is underway.  We need to prevent such an open request
from succeeding.  (It appears that Maciej Galkiewicz ran into this
problem.)

Define and use a "removing" flag to indicate a mapping is getting
removed.  Set it in the remove path after verifying nothing holds
the device open.  And check it in the open path before allowing the
open to proceed.  Acquire the rbd device's lock around each of these
spots to avoid any races accessing the flags and open_count fields.

This addresses:
    http://tracker.newdream.net/issues/3427

Reported-by:  Maciej Galkiewicz <maciejgalkiewicz@ragnarson.com>
Signed-off-by: Alex Elder <elder@inktank.com>
---
 drivers/block/rbd.c |   42 +++++++++++++++++++++++++++++++++---------
 1 file changed, 33 insertions(+), 9 deletions(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 107df40..03b15b8 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -259,10 +259,10 @@ struct rbd_device {

 	char			name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */

-	spinlock_t		lock;		/* queue lock */
+	spinlock_t		lock;		/* queue, flags, open_count */

 	struct rbd_image_header	header;
-	unsigned long		flags;
+	unsigned long		flags;		/* possibly lock protected */
 	struct rbd_spec		*spec;

 	char			*header_name;
@@ -288,13 +288,20 @@ struct rbd_device {

 	/* sysfs related */
 	struct device		dev;
-	unsigned long		open_count;
+	unsigned long		open_count;	/* protected by lock */
 };

-/* Flag bits for rbd_dev->flags */
+/*
+ * Flag bits for rbd_dev->flags.  If atomicity is required,
+ * rbd_dev->lock is used to protect access.
+ *
+ * Currently, only the "removing" flag (which is coupled with the
+ * "open_count" field) requires atomic access.
+ */

 enum rbd_dev_flags {
 	rbd_dev_flag_exists,	/* mapped snapshot has not been deleted */
+	rbd_dev_flag_removing,	/* this mapping is being removed */
 };

 static DEFINE_MUTEX(ctl_mutex);	  /* Serialize open/close/setup/teardown */
@@ -383,14 +390,23 @@ static int rbd_dev_v2_refresh(struct rbd_device
*rbd_dev, u64 *hver);
 static int rbd_open(struct block_device *bdev, fmode_t mode)
 {
 	struct rbd_device *rbd_dev = bdev->bd_disk->private_data;
+	bool removing = false;

 	if ((mode & FMODE_WRITE) && rbd_dev->mapping.read_only)
 		return -EROFS;

+	spin_lock(&rbd_dev->lock);
+	if (test_bit(rbd_dev_flag_removing, &rbd_dev->flags))
+		removing = true;
+	else
+		rbd_dev->open_count++;
+	spin_unlock(&rbd_dev->lock);
+	if (removing)
+		return -ENOENT;
+
 	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
 	(void) get_device(&rbd_dev->dev);
 	set_device_ro(bdev, rbd_dev->mapping.read_only);
-	rbd_dev->open_count++;
 	mutex_unlock(&ctl_mutex);

 	return 0;
@@ -399,10 +415,14 @@ static int rbd_open(struct block_device *bdev,
fmode_t mode)
 static int rbd_release(struct gendisk *disk, fmode_t mode)
 {
 	struct rbd_device *rbd_dev = disk->private_data;
+	unsigned long open_count_before;
+
+	spin_lock(&rbd_dev->lock);
+	open_count_before = rbd_dev->open_count--;
+	spin_unlock(&rbd_dev->lock);
+	rbd_assert(open_count_before > 0);

 	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-	rbd_assert(rbd_dev->open_count > 0);
-	rbd_dev->open_count--;
 	put_device(&rbd_dev->dev);
 	mutex_unlock(&ctl_mutex);

@@ -4135,10 +4155,14 @@ static ssize_t rbd_remove(struct bus_type *bus,
 		goto done;
 	}

-	if (rbd_dev->open_count) {
+	spin_lock(&rbd_dev->lock);
+	if (rbd_dev->open_count)
 		ret = -EBUSY;
+	else
+		set_bit(rbd_dev_flag_removing, &rbd_dev->flags);
+	spin_unlock(&rbd_dev->lock);
+	if (ret < 0)
 		goto done;
-	}

 	while (rbd_dev->parent_spec) {
 		struct rbd_device *first = rbd_dev;
-- 
1.7.9.5

Re: [PATCH 1/2] rbd: define flags field, use it for exists flag

[Josh Durgin]

Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

On 01/28/2013 02:09 PM, Alex Elder wrote:
> Define a new rbd device flags field, manipulated using bit
> operations.  Replace the use of the current "exists" flag with a bit
> in this new "flags" field.  Add a little commentary about the
> "exists" flag, which does not need to be manipulated atomically.
>
> Signed-off-by: Alex Elder <elder@inktank.com>
> ---
>   drivers/block/rbd.c |   37 ++++++++++++++++++++++++++++---------
>   1 file changed, 28 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
> index 177ba0c..107df40 100644
> --- a/drivers/block/rbd.c
> +++ b/drivers/block/rbd.c
> @@ -262,7 +262,7 @@ struct rbd_device {
>   	spinlock_t		lock;		/* queue lock */
>
>   	struct rbd_image_header	header;
> -	atomic_t		exists;
> +	unsigned long		flags;
>   	struct rbd_spec		*spec;
>
>   	char			*header_name;
> @@ -291,6 +291,12 @@ struct rbd_device {
>   	unsigned long		open_count;
>   };
>
> +/* Flag bits for rbd_dev->flags */
> +
> +enum rbd_dev_flags {
> +	rbd_dev_flag_exists,	/* mapped snapshot has not been deleted */
> +};
> +
>   static DEFINE_MUTEX(ctl_mutex);	  /* Serialize open/close/setup/teardown */
>
>   static LIST_HEAD(rbd_dev_list);    /* devices */
> @@ -790,7 +796,8 @@ static int rbd_dev_set_mapping(struct rbd_device
> *rbd_dev)
>   			goto done;
>   		rbd_dev->mapping.read_only = true;
>   	}
> -	atomic_set(&rbd_dev->exists, 1);
> +	set_bit(rbd_dev_flag_exists, &rbd_dev->flags);
> +
>   done:
>   	return ret;
>   }
> @@ -1886,9 +1893,14 @@ static void rbd_request_fn(struct request_queue *q)
>   			rbd_assert(rbd_dev->spec->snap_id == CEPH_NOSNAP);
>   		}
>
> -		/* Quit early if the snapshot has disappeared */
> -
> -		if (!atomic_read(&rbd_dev->exists)) {
> +		/*
> +		 * Quit early if the mapped snapshot no longer
> +		 * exists.  It's still possible the snapshot will
> +		 * have disappeared by the time our request arrives
> +		 * at the osd, but there's no sense in sending it if
> +		 * we already know.
> +		 */
> +		if (!test_bit(rbd_dev_flag_exists, &rbd_dev->flags)) {
>   			dout("request for non-existent snapshot");
>   			rbd_assert(rbd_dev->spec->snap_id != CEPH_NOSNAP);
>   			result = -ENXIO;
> @@ -2578,7 +2590,7 @@ struct rbd_device *rbd_dev_create(struct
> rbd_client *rbdc,
>   		return NULL;
>
>   	spin_lock_init(&rbd_dev->lock);
> -	atomic_set(&rbd_dev->exists, 0);
> +	rbd_dev->flags = 0;
>   	INIT_LIST_HEAD(&rbd_dev->node);
>   	INIT_LIST_HEAD(&rbd_dev->snaps);
>   	init_rwsem(&rbd_dev->header_rwsem);
> @@ -3207,10 +3219,17 @@ static int rbd_dev_snaps_update(struct
> rbd_device *rbd_dev)
>   		if (snap_id == CEPH_NOSNAP || (snap && snap->id > snap_id)) {
>   			struct list_head *next = links->next;
>
> -			/* Existing snapshot not in the new snap context */
> -
> +			/*
> +			 * A previously-existing snapshot is not in
> +			 * the new snap context.
> +			 *
> +			 * If the now missing snapshot is the one the
> +			 * image is mapped to, clear its exists flag
> +			 * so we can avoid sending any more requests
> +			 * to it.
> +			 */
>   			if (rbd_dev->spec->snap_id == snap->id)
> -				atomic_set(&rbd_dev->exists, 0);
> +				clear_bit(rbd_dev_flag_exists, &rbd_dev->flags);
>   			rbd_remove_snap_dev(snap);
>   			dout("%ssnap id %llu has been removed\n",
>   				rbd_dev->spec->snap_id == snap->id ?
>

Re: [PATCH 2/2] rbd: prevent open for image being removed

[Josh Durgin]

Enums should be capitalized according to Documentation/CodingStyle.

Other than that, looks good.
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

On 01/28/2013 02:09 PM, Alex Elder wrote:
> An open request for a mapped rbd image can arrive while removal of
> that mapping is underway.  We need to prevent such an open request
> from succeeding.  (It appears that Maciej Galkiewicz ran into this
> problem.)
>
> Define and use a "removing" flag to indicate a mapping is getting
> removed.  Set it in the remove path after verifying nothing holds
> the device open.  And check it in the open path before allowing the
> open to proceed.  Acquire the rbd device's lock around each of these
> spots to avoid any races accessing the flags and open_count fields.
>
> This addresses:
>      http://tracker.newdream.net/issues/3427
>
> Reported-by:  Maciej Galkiewicz <maciejgalkiewicz@ragnarson.com>
> Signed-off-by: Alex Elder <elder@inktank.com>
> ---
>   drivers/block/rbd.c |   42 +++++++++++++++++++++++++++++++++---------
>   1 file changed, 33 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
> index 107df40..03b15b8 100644
> --- a/drivers/block/rbd.c
> +++ b/drivers/block/rbd.c
> @@ -259,10 +259,10 @@ struct rbd_device {
>
>   	char			name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */
>
> -	spinlock_t		lock;		/* queue lock */
> +	spinlock_t		lock;		/* queue, flags, open_count */
>
>   	struct rbd_image_header	header;
> -	unsigned long		flags;
> +	unsigned long		flags;		/* possibly lock protected */
>   	struct rbd_spec		*spec;
>
>   	char			*header_name;
> @@ -288,13 +288,20 @@ struct rbd_device {
>
>   	/* sysfs related */
>   	struct device		dev;
> -	unsigned long		open_count;
> +	unsigned long		open_count;	/* protected by lock */
>   };
>
> -/* Flag bits for rbd_dev->flags */
> +/*
> + * Flag bits for rbd_dev->flags.  If atomicity is required,
> + * rbd_dev->lock is used to protect access.
> + *
> + * Currently, only the "removing" flag (which is coupled with the
> + * "open_count" field) requires atomic access.
> + */
>
>   enum rbd_dev_flags {
>   	rbd_dev_flag_exists,	/* mapped snapshot has not been deleted */
> +	rbd_dev_flag_removing,	/* this mapping is being removed */
>   };
>
>   static DEFINE_MUTEX(ctl_mutex);	  /* Serialize open/close/setup/teardown */
> @@ -383,14 +390,23 @@ static int rbd_dev_v2_refresh(struct rbd_device
> *rbd_dev, u64 *hver);
>   static int rbd_open(struct block_device *bdev, fmode_t mode)
>   {
>   	struct rbd_device *rbd_dev = bdev->bd_disk->private_data;
> +	bool removing = false;
>
>   	if ((mode & FMODE_WRITE) && rbd_dev->mapping.read_only)
>   		return -EROFS;
>
> +	spin_lock(&rbd_dev->lock);
> +	if (test_bit(rbd_dev_flag_removing, &rbd_dev->flags))
> +		removing = true;
> +	else
> +		rbd_dev->open_count++;
> +	spin_unlock(&rbd_dev->lock);
> +	if (removing)
> +		return -ENOENT;
> +
>   	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
>   	(void) get_device(&rbd_dev->dev);
>   	set_device_ro(bdev, rbd_dev->mapping.read_only);
> -	rbd_dev->open_count++;
>   	mutex_unlock(&ctl_mutex);
>
>   	return 0;
> @@ -399,10 +415,14 @@ static int rbd_open(struct block_device *bdev,
> fmode_t mode)
>   static int rbd_release(struct gendisk *disk, fmode_t mode)
>   {
>   	struct rbd_device *rbd_dev = disk->private_data;
> +	unsigned long open_count_before;
> +
> +	spin_lock(&rbd_dev->lock);
> +	open_count_before = rbd_dev->open_count--;
> +	spin_unlock(&rbd_dev->lock);
> +	rbd_assert(open_count_before > 0);
>
>   	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
> -	rbd_assert(rbd_dev->open_count > 0);
> -	rbd_dev->open_count--;
>   	put_device(&rbd_dev->dev);
>   	mutex_unlock(&ctl_mutex);
>
> @@ -4135,10 +4155,14 @@ static ssize_t rbd_remove(struct bus_type *bus,
>   		goto done;
>   	}
>
> -	if (rbd_dev->open_count) {
> +	spin_lock(&rbd_dev->lock);
> +	if (rbd_dev->open_count)
>   		ret = -EBUSY;
> +	else
> +		set_bit(rbd_dev_flag_removing, &rbd_dev->flags);
> +	spin_unlock(&rbd_dev->lock);
> +	if (ret < 0)
>   		goto done;
> -	}
>
>   	while (rbd_dev->parent_spec) {
>   		struct rbd_device *first = rbd_dev;
>

Re: [PATCH 2/2] rbd: prevent open for image being removed

[Alex Elder]

On 01/30/2013 01:52 PM, Josh Durgin wrote:
> Enums should be capitalized according to Documentation/CodingStyle.

I already updated that in my own copy after last time...
Thanks.

					-Alex

> Other than that, looks good.
> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
>