@@ -554,7 +554,7 @@ void blk_cleanup_queue(struct request_queue *q)
q->queue_lock = &q->__queue_lock;
spin_unlock_irq(lock);
- bdi_destroy(&q->backing_dev_info);
+ bdi_unregister(&q->backing_dev_info);
/* @q is and will stay empty, shutdown and put */
blk_put_queue(q);
@@ -501,6 +501,7 @@ static void blk_release_queue(struct kobject *kobj)
struct request_queue *q =
container_of(kobj, struct request_queue, kobj);
+ bdi_exit(&q->backing_dev_info);
blkcg_exit_queue(q);
if (q->elevator) {
@@ -110,12 +110,15 @@ struct backing_dev_info {
struct backing_dev_info *inode_to_bdi(struct inode *inode);
int __must_check bdi_init(struct backing_dev_info *bdi);
-void bdi_destroy(struct backing_dev_info *bdi);
+void bdi_exit(struct backing_dev_info *bdi);
__printf(3, 4)
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
+void bdi_unregister(struct backing_dev_info *bdi);
+void bdi_destroy(struct backing_dev_info *bdi);
+
int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
enum wb_reason reason);
@@ -421,10 +421,8 @@ err:
}
EXPORT_SYMBOL(bdi_init);
-void bdi_destroy(struct backing_dev_info *bdi)
+void bdi_unregister(struct backing_dev_info *bdi)
{
- int i;
-
bdi_wb_shutdown(bdi);
bdi_set_min_ratio(bdi, 0);
@@ -436,11 +434,24 @@ void bdi_destroy(struct backing_dev_info *bdi)
device_unregister(bdi->dev);
bdi->dev = NULL;
}
+}
+
+void bdi_exit(struct backing_dev_info *bdi)
+{
+ int i;
+
+ WARN_ON_ONCE(bdi->dev);
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
percpu_counter_destroy(&bdi->bdi_stat[i]);
fprop_local_destroy_percpu(&bdi->completions);
}
+
+void bdi_destroy(struct backing_dev_info *bdi)
+{
+ bdi_unregister(bdi);
+ bdi_exit(bdi);
+}
EXPORT_SYMBOL(bdi_destroy);
/*
Hi, This patch was marked for stable v4.2+, but is needed for v4.1 as well. It fixes a regression introduced by: Fixes: 6cd18e711dd8 ("block: destroy bdi before blockdev is unregistered.") This is a backport to 4.1.33 which has been tested and confirmed to work. Bug report at https://bugzilla.kernel.org/show_bug.cgi?id=173031 Please queue for 4.1.y Thanks, NeilBrown From: Tejun Heo <tj@kernel.org> Date: Tue, 8 Sep 2015 12:20:22 -0400 Subject: [PATCH] block: don't release bdi while request_queue has live references [ Upstream commit: b02176f30cd30acccd3b633ab7d9aed8b5da52ff ] bdi's are initialized in two steps, bdi_init() and bdi_register(), but destroyed in a single step by bdi_destroy() which, for a bdi embedded in a request_queue, is called during blk_cleanup_queue() which makes the queue invisible and starts the draining of remaining usages. A request_queue's user can access the congestion state of the embedded bdi as long as it holds a reference to the queue. As such, it may access the congested state of a queue which finished blk_cleanup_queue() but hasn't reached blk_release_queue() yet. Because the congested state was embedded in backing_dev_info which in turn is embedded in request_queue, accessing the congested state after bdi_destroy() was called was fine. The bdi was destroyed but the memory region for the congested state remained accessible till the queue got released. a13f35e87140 ("writeback: don't embed root bdi_writeback_congested in bdi_writeback") changed the situation. Now, the root congested state which is expected to be pinned while request_queue remains accessible is separately reference counted and the base ref is put during bdi_destroy(). This means that the root congested state may go away prematurely while the queue is between bdi_dstroy() and blk_cleanup_queue(), which was detected by Andrey's KASAN tests. The root cause of this problem is that bdi doesn't distinguish the two steps of destruction, unregistration and release, and now the root congested state actually requires a separate release step. To fix the issue, this patch separates out bdi_unregister() and bdi_exit() from bdi_destroy(). bdi_unregister() is called from blk_cleanup_queue() and bdi_exit() from blk_release_queue(). bdi_destroy() is now just a simple wrapper calling the two steps back-to-back. While at it, the prototype of bdi_destroy() is moved right below bdi_setup_and_register() so that the counterpart operations are located together. Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: a13f35e87140 ("writeback: don't embed root bdi_writeback_congested in bdi_writeback") Fixes: 6cd18e711dd8 ("block: destroy bdi before blockdev is unregistered.") Cc: stable@vger.kernel.org # v4.2+ Reported-and-tested-by: Andrey Konovalov <andreyknvl@google.com> Reported-and-tested-by: Francesco Dolcini <francesco@dolcini.it> (for 4.1 backport) Link: http://lkml.kernel.org/g/CAAeHK+zUJ74Zn17=rOyxacHU18SgCfC6bsYW=6kCY5GXJBwGfQ@mail.gmail.com Reviewed-by: Jan Kara <jack@suse.com> Reviewed-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Jens Axboe <axboe@fb.com> Signed-off-by: NeilBrown <neilb@suse.com> --- block/blk-core.c | 2 +- block/blk-sysfs.c | 1 + include/linux/backing-dev.h | 5 ++++- mm/backing-dev.c | 17 ++++++++++++++--- 4 files changed, 20 insertions(+), 5 deletions(-)