The existing implementation allows races between bsg_unregister and
bsg_open paths. bsg_ungegister and request_queue cleanup and
deletion may start and complete right after bsg_get_device (in bsg_open path)
retrieves bsg_class_device and releases the mutex. Then bsg_open path
touches freed memory of bsg_class_device and request_queue.
One possible fix is to hold the mutex all the way through bsg_get_device
instead of releasing it after bsg_class_device retrieval.
From a8647f9cfb3b2b69dcac493554cb6ea2f9b4c2dd Mon Sep 17 00:00:00 2001
From: Anatoliy Glagolev <[email protected]>
Date: Wed, 13 Jun 2018 15:38:51 -0600
Subject: [PATCH] Fix race of bsg_open and bsg_unregister
Signed-Off-By: Anatoliy Glagolev <[email protected]>
---
block/bsg.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/block/bsg.c b/block/bsg.c
index 132e657..10bc6a4 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -693,6 +693,8 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
struct bsg_device *bd;
unsigned char buf[32];
+ lockdep_assert_held(&bsg_mutex);
+
if (!blk_get_queue(rq))
return ERR_PTR(-ENXIO);
@@ -707,14 +709,12 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
bsg_set_block(bd, file);
atomic_set(&bd->ref_count, 1);
- mutex_lock(&bsg_mutex);
hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1);
bsg_dbg(bd, "bound to <%s>, max queue %d\n",
format_dev_t(buf, inode->i_rdev), bd->max_queue);
- mutex_unlock(&bsg_mutex);
return bd;
}
@@ -722,7 +722,7 @@ static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q)
{
struct bsg_device *bd;
- mutex_lock(&bsg_mutex);
+ lockdep_assert_held(&bsg_mutex);
hlist_for_each_entry(bd, bsg_dev_idx_hash(minor), dev_list) {
if (bd->queue == q) {
@@ -732,7 +732,6 @@ static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q)
}
bd = NULL;
found:
- mutex_unlock(&bsg_mutex);
return bd;
}
@@ -746,16 +745,18 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
*/
mutex_lock(&bsg_mutex);
bcd = idr_find(&bsg_minor_idr, iminor(inode));
- mutex_unlock(&bsg_mutex);
if (!bcd)
return ERR_PTR(-ENODEV);
bd = __bsg_get_device(iminor(inode), bcd->queue);
- if (bd)
+ if (bd) {
+ mutex_unlock(&bsg_mutex);
return bd;
+ }
bd = bsg_add_device(inode, bcd->queue, file);
+ mutex_unlock(&bsg_mutex);
return bd;
}
--
1.9.1
On Wed, Jun 13, 2018 at 04:14:18PM -0600, Anatoliy Glagolev wrote:
> The existing implementation allows races between bsg_unregister and
> bsg_open paths. bsg_ungegister and request_queue cleanup and
> deletion may start and complete right after bsg_get_device (in bsg_open path)
> retrieves bsg_class_device and releases the mutex. Then bsg_open path
> touches freed memory of bsg_class_device and request_queue.
>
> One possible fix is to hold the mutex all the way through bsg_get_device
> instead of releasing it after bsg_class_device retrieval.
This looks generally fine to me. Nitpicks below:
> @@ -746,16 +745,18 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
> */
> mutex_lock(&bsg_mutex);
> bcd = idr_find(&bsg_minor_idr, iminor(inode));
> - mutex_unlock(&bsg_mutex);
>
> if (!bcd)
> return ERR_PTR(-ENODEV);
This needs to unlock the mutex. E.g.
if (!bcd) {
bd = ERR_PTR(-ENODEV);
goto out_unlock;
}
> bd = __bsg_get_device(iminor(inode), bcd->queue);
> + if (bd) {
> + mutex_unlock(&bsg_mutex);
> return bd;
> + }
>
> bd = bsg_add_device(inode, bcd->queue, file);
> + mutex_unlock(&bsg_mutex);
>
> return bd;
I'd simply do:
bd = __bsg_get_device(iminor(inode), bcd->queue);
if (!bd)
bd = bsg_add_device(inode, bcd->queue, file);
out_unlock:
mutex_unlock(&bsg_mutex);
return bd;
Thanks, Christoph. Good catch releasing the mutex on failure path.
V2 patch with your suggestions applied.
From 7a8dc4b10f344d915658549581158f3da2cc1f91 Mon Sep 17 00:00:00 2001
From: Anatoliy Glagolev <[email protected]>
Date: Wed, 13 Jun 2018 15:38:51 -0600
Subject: [PATCHv2] Fix race of bsg_open and bsg_unregister
Signed-Off-By: Anatoliy Glagolev <[email protected]>
---
block/bsg.c | 22 +++++++++++-----------
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/block/bsg.c b/block/bsg.c
index 132e657..66602c4 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -693,6 +693,8 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
struct bsg_device *bd;
unsigned char buf[32];
+ lockdep_assert_held(&bsg_mutex);
+
if (!blk_get_queue(rq))
return ERR_PTR(-ENXIO);
@@ -707,14 +709,12 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
bsg_set_block(bd, file);
atomic_set(&bd->ref_count, 1);
- mutex_lock(&bsg_mutex);
hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1);
bsg_dbg(bd, "bound to <%s>, max queue %d\n",
format_dev_t(buf, inode->i_rdev), bd->max_queue);
- mutex_unlock(&bsg_mutex);
return bd;
}
@@ -722,7 +722,7 @@ static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q)
{
struct bsg_device *bd;
- mutex_lock(&bsg_mutex);
+ lockdep_assert_held(&bsg_mutex);
hlist_for_each_entry(bd, bsg_dev_idx_hash(minor), dev_list) {
if (bd->queue == q) {
@@ -732,7 +732,6 @@ static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q)
}
bd = NULL;
found:
- mutex_unlock(&bsg_mutex);
return bd;
}
@@ -746,17 +745,18 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
*/
mutex_lock(&bsg_mutex);
bcd = idr_find(&bsg_minor_idr, iminor(inode));
- mutex_unlock(&bsg_mutex);
- if (!bcd)
- return ERR_PTR(-ENODEV);
+ if (!bcd) {
+ bd = ERR_PTR(-ENODEV);
+ goto out_unlock;
+ }
bd = __bsg_get_device(iminor(inode), bcd->queue);
- if (bd)
- return bd;
-
- bd = bsg_add_device(inode, bcd->queue, file);
+ if (!bd)
+ bd = bsg_add_device(inode, bcd->queue, file);
+out_unlock:
+ mutex_unlock(&bsg_mutex);
return bd;
}
--
1.9.1
On Thu, Jun 14, 2018 at 05:47:34PM -0600, Anatoliy Glagolev wrote:
> Thanks, Christoph. Good catch releasing the mutex on failure path.
> V2 patch with your suggestions applied.
Looks good:
Reviewed-by: Christoph Hellwig <[email protected]>
Now just re-add the changelog and resend it in a new thread.
On 6/15/18 3:27 AM, Christoph Hellwig wrote:
> On Thu, Jun 14, 2018 at 05:47:34PM -0600, Anatoliy Glagolev wrote:
>> Thanks, Christoph. Good catch releasing the mutex on failure path.
>> V2 patch with your suggestions applied.
>
> Looks good:
>
> Reviewed-by: Christoph Hellwig <[email protected]>
>
> Now just re-add the changelog and resend it in a new thread.
The original one was mixed up, too. Anatoliy, I fixed it up for
you. But for future patches, please follow the usual patch
format where the commit message is actually in the patch.
--
Jens Axboe