lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:	Sun, 01 Nov 2015 23:30:31 -0500
From:	Dan Williams <dan.j.williams@...el.com>
To:	axboe@...com
Cc:	Jens Axboe <axboe@...nel.dk>, jack@...e.cz,
	linux-nvdimm@...ts.01.org, david@...morbit.com,
	linux-kernel@...r.kernel.org, ross.zwisler@...ux.intel.com,
	hch@....de
Subject: [PATCH v3 09/15] block: notify queue death confirmation

The pmem driver arranges for references to be taken against the queue
while pages it allocated via devm_memremap_pages() are in use.  At
shutdown time, before those pages can be deallocated, they need to be
unmapped, and guaranteed to be idle.  The unmap scan can only be done
once we are certain no new page references will be taken.  Once the blk
queue percpu_ref is confirmed dead the dax core will cease allowing new
references and we can free these "device" pages.

Cc: Jens Axboe <axboe@...nel.dk>
Cc: Christoph Hellwig <hch@....de>
Cc: Ross Zwisler <ross.zwisler@...ux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@...el.com>
---
 block/blk-core.c       |   12 +++++++++---
 block/blk-mq.c         |   19 +++++++++++++++----
 include/linux/blkdev.h |    4 +++-
 3 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 6ebe33ed5154..5159946a2b41 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -516,6 +516,12 @@ void blk_set_queue_dying(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
 
+void blk_wait_queue_dead(struct request_queue *q)
+{
+	wait_event(q->q_freeze_wq, q->q_usage_dead);
+}
+EXPORT_SYMBOL(blk_wait_queue_dead);
+
 /**
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
@@ -641,7 +647,7 @@ int blk_queue_enter(struct request_queue *q, gfp_t gfp)
 		if (!(gfp & __GFP_WAIT))
 			return -EBUSY;
 
-		ret = wait_event_interruptible(q->mq_freeze_wq,
+		ret = wait_event_interruptible(q->q_freeze_wq,
 				!atomic_read(&q->mq_freeze_depth) ||
 				blk_queue_dying(q));
 		if (blk_queue_dying(q))
@@ -661,7 +667,7 @@ static void blk_queue_usage_counter_release(struct percpu_ref *ref)
 	struct request_queue *q =
 		container_of(ref, struct request_queue, q_usage_counter);
 
-	wake_up_all(&q->mq_freeze_wq);
+	wake_up_all(&q->q_freeze_wq);
 }
 
 struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
@@ -723,7 +729,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	q->bypass_depth = 1;
 	__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
 
-	init_waitqueue_head(&q->mq_freeze_wq);
+	init_waitqueue_head(&q->q_freeze_wq);
 
 	/*
 	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6c240712553a..e0417febbcd4 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -78,13 +78,23 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 	clear_bit(CTX_TO_BIT(hctx, ctx), &bm->word);
 }
 
+static void blk_confirm_queue_death(struct percpu_ref *ref)
+{
+	struct request_queue *q = container_of(ref, typeof(*q),
+			q_usage_counter);
+
+	q->q_usage_dead = 1;
+	wake_up_all(&q->q_freeze_wq);
+}
+
 void blk_mq_freeze_queue_start(struct request_queue *q)
 {
 	int freeze_depth;
 
 	freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
 	if (freeze_depth == 1) {
-		percpu_ref_kill(&q->q_usage_counter);
+		percpu_ref_kill_and_confirm(&q->q_usage_counter,
+				blk_confirm_queue_death);
 		blk_mq_run_hw_queues(q, false);
 	}
 }
@@ -92,7 +102,7 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
 
 static void blk_mq_freeze_queue_wait(struct request_queue *q)
 {
-	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
+	wait_event(q->q_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
 }
 
 /*
@@ -130,7 +140,8 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
 	WARN_ON_ONCE(freeze_depth < 0);
 	if (!freeze_depth) {
 		percpu_ref_reinit(&q->q_usage_counter);
-		wake_up_all(&q->mq_freeze_wq);
+		q->q_usage_dead = 0;
+		wake_up_all(&q->q_freeze_wq);
 	}
 }
 EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
@@ -149,7 +160,7 @@ void blk_mq_wake_waiters(struct request_queue *q)
 	 * dying, we need to ensure that processes currently waiting on
 	 * the queue are notified as well.
 	 */
-	wake_up_all(&q->mq_freeze_wq);
+	wake_up_all(&q->q_freeze_wq);
 }
 
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b78e01542e9e..e121e5e0c6ac 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -431,6 +431,7 @@ struct request_queue {
 	 */
 	unsigned int		flush_flags;
 	unsigned int		flush_not_queueable:1;
+	unsigned int		q_usage_dead:1;
 	struct blk_flush_queue	*fq;
 
 	struct list_head	requeue_list;
@@ -453,7 +454,7 @@ struct request_queue {
 	struct throtl_data *td;
 #endif
 	struct rcu_head		rcu_head;
-	wait_queue_head_t	mq_freeze_wq;
+	wait_queue_head_t	q_freeze_wq;
 	struct percpu_ref	q_usage_counter;
 	struct list_head	all_q_node;
 
@@ -953,6 +954,7 @@ extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
 extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
 extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
 						      request_fn_proc *, spinlock_t *);
+extern void blk_wait_queue_dead(struct request_queue *q);
 extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists