blk-mq: free hw queue's resource in hctx's release handler

commit c7e2d94b3d1634988a95ac4d77a72dc7487ece06 upstream.

Once blk_cleanup_queue() returns, tags shouldn't be used any more,
because blk_mq_free_tag_set() may be called. Commit 45a9c9d909b2
("blk-mq: Fix a use-after-free") fixes this issue exactly.

However, that commit introduces another issue. Before 45a9c9d909b2,
we are allowed to run queue during cleaning up queue if the queue's
kobj refcount is held. After that commit, queue can't be run during
queue cleaning up, otherwise oops can be triggered easily because
some fields of hctx are freed by blk_mq_free_queue() in blk_cleanup_queue().

We have invented ways for addressing this kind of issue before, such as:

	8dc765d438f1 ("SCSI: fix queue cleanup race before queue initialization is done")
	c2856ae2f315 ("blk-mq: quiesce queue before freeing queue")

But still can't cover all cases, recently James reports another such
kind of issue:

	https://marc.info/?l=linux-scsi&m=155389088124782&w=2

This issue can be quite hard to address by previous way, given
scsi_run_queue() may run requeues for other LUNs.

Fixes the above issue by freeing hctx's resources in its release handler, and this
way is safe becasue tags isn't needed for freeing such hctx resource.

This approach follows typical design pattern wrt. kobject's release handler.

Cc: Dongli Zhang <dongli.zhang@oracle.com>
Cc: James Smart <james.smart@broadcom.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: linux-scsi@vger.kernel.org,
Cc: Martin K . Petersen <martin.petersen@oracle.com>,
Cc: Christoph Hellwig <hch@lst.de>,
Cc: James E . J . Bottomley <jejb@linux.vnet.ibm.com>,
Reported-by: James Smart <james.smart@broadcom.com>
Fixes: 45a9c9d909b2 ("blk-mq: Fix a use-after-free")
Cc: stable@vger.kernel.org
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/block/blk-core.c b/block/blk-core.c
index 5bde73a49399320b2185f80d5dca7941076e903f..6ba6d88056973e7b091df2a48ffa9a840208ba57 100644 (file)
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -375,7 +375,7 @@ void blk_cleanup_queue(struct request_queue *q)
        blk_exit_queue(q);
 
        if (queue_is_mq(q))
-               blk_mq_free_queue(q);
+               blk_mq_exit_queue(q);
 
        percpu_ref_exit(&q->q_usage_counter);
 

diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 3f9c3f4ac44ca4632e0f2c25dce8164a08b5b916..4040e62c3737a2f852ce5a8fb0042ca0c899b1d3 100644 (file)
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -10,6 +10,7 @@
 #include <linux/smp.h>
 
 #include <linux/blk-mq.h>
+#include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 
@@ -33,6 +34,11 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj)
 {
        struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
                                                  kobj);
+
+       if (hctx->flags & BLK_MQ_F_BLOCKING)
+               cleanup_srcu_struct(hctx->srcu);
+       blk_free_flush_queue(hctx->fq);
+       sbitmap_free(&hctx->ctx_map);
        free_cpumask_var(hctx->cpumask);
        kfree(hctx->ctxs);
        kfree(hctx);

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5b920a82bfe6095299665612f30cfe31c7267ed7..9957e0fc17fc4c636fa18b7940e4bf7ceca49111 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2270,12 +2270,7 @@ static void blk_mq_exit_hctx(struct request_queue *q,
        if (set->ops->exit_hctx)
                set->ops->exit_hctx(hctx, hctx_idx);
 
-       if (hctx->flags & BLK_MQ_F_BLOCKING)
-               cleanup_srcu_struct(hctx->srcu);
-
        blk_mq_remove_cpuhp(hctx);
-       blk_free_flush_queue(hctx->fq);
-       sbitmap_free(&hctx->ctx_map);
 }
 
 static void blk_mq_exit_hw_queues(struct request_queue *q,
@@ -2904,7 +2899,8 @@ err_exit:
 }
 EXPORT_SYMBOL(blk_mq_init_allocated_queue);
 
-void blk_mq_free_queue(struct request_queue *q)
+/* tags can _not_ be used after returning from blk_mq_exit_queue */
+void blk_mq_exit_queue(struct request_queue *q)
 {
        struct blk_mq_tag_set   *set = q->tag_set;
 

diff --git a/block/blk-mq.h b/block/blk-mq.h
index a3a684a8c633895472b7108fcddce827f1c30b7b..39bc1d5d463795f6eff87c488fc457be202fa11e 100644 (file)
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -36,7 +36,7 @@ struct blk_mq_ctx {
        struct kobject          kobj;
 } ____cacheline_aligned_in_smp;
 
-void blk_mq_free_queue(struct request_queue *q);
+void blk_mq_exit_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);