mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: John Garry <john.garry@huawei.com>
To: <axboe@kernel.dk>, <ming.lei@redhat.com>
Cc: <linux-block@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	<hch@lst.de>, <hare@suse.de>, <ppvk@codeaurora.org>,
	<bvanassche@acm.org>, <kashyap.desai@broadcom.com>,
	<linuxarm@huawei.com>, John Garry <john.garry@huawei.com>
Subject: [RFC PATCH v2 1/2] blk-mq: Clean up references to old requests when freeing rqs
Date: Thu, 17 Dec 2020 19:07:52 +0800	[thread overview]
Message-ID: <1608203273-170555-2-git-send-email-john.garry@huawei.com> (raw)
In-Reply-To: <1608203273-170555-1-git-send-email-john.garry@huawei.com>

It has been reported many times that a use-after-free can be intermittently
found when iterating busy requests:

- https://lore.kernel.org/linux-block/8376443a-ec1b-0cef-8244-ed584b96fa96@huawei.com/
- https://lore.kernel.org/linux-block/5c3ac5af-ed81-11e4-fee3-f92175f14daf@acm.org/T/#m6c1ac11540522716f645d004e2a5a13c9f218908
- https://lore.kernel.org/linux-block/04e2f9e8-79fa-f1cb-ab23-4a15bf3f64cc@kernel.dk/

The issue is that when we switch IO scheduler or change queue depth,
there may be references in the driver tagset to the stale requests; and
since getting a tag and setting the request pointer is not atomic, a
tagset iter may see a stale request for a tag recently allocated.

As a solution, clean up any references to those requests in the driver
tagset. This is done with a cmpxchg to make safe any race with setting the
driver tagset request from another queue.

Signed-off-by: John Garry <john.garry@huawei.com>
---
 block/blk-mq-sched.c |  2 +-
 block/blk-mq-tag.c   |  2 +-
 block/blk-mq.c       | 20 ++++++++++++++++++--
 block/blk-mq.h       |  2 ++
 4 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index deff4e826e23..fa1035e1ac6e 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -621,7 +621,7 @@ void blk_mq_sched_free_requests(struct request_queue *q)
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (hctx->sched_tags)
-			blk_mq_free_rqs(q->tag_set, hctx->sched_tags, i);
+			blk_mq_free_rqs_ext(q->tag_set, hctx->sched_tags, i, hctx->tags);
 	}
 }
 
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 6cfd6bb00ede..a6df2d5df88a 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -580,7 +580,7 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 			return -ENOMEM;
 		}
 
-		blk_mq_free_rqs(set, *tagsptr, hctx->queue_num);
+		blk_mq_free_rqs_ext(set, *tagsptr, hctx->queue_num, hctx->tags);
 		blk_mq_free_rq_map(*tagsptr, flags);
 		*tagsptr = new;
 	} else {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6f207ec9ef83..8465d7c5ebf0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2278,8 +2278,8 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 	return BLK_QC_T_NONE;
 }
 
-void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
-		     unsigned int hctx_idx)
+void __blk_mq_free_rqs_ext(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx, struct blk_mq_tags *ref_tags)
 {
 	struct page *page;
 
@@ -2288,10 +2288,14 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 
 		for (i = 0; i < tags->nr_tags; i++) {
 			struct request *rq = tags->static_rqs[i];
+			int j;
 
 			if (!rq)
 				continue;
 			set->ops->exit_request(set, rq, hctx_idx);
+			/* clean up any references which occur in @ref_tags */
+			for (j = 0; ref_tags && j < ref_tags->nr_tags; j++)
+				cmpxchg(&ref_tags->rqs[j], rq, 0);
 			tags->static_rqs[i] = NULL;
 		}
 	}
@@ -2308,6 +2312,18 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 	}
 }
 
+void blk_mq_free_rqs_ext(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx, struct blk_mq_tags *ref_tags)
+{
+	__blk_mq_free_rqs_ext(set, tags, hctx_idx, ref_tags);
+}
+			 
+void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx)
+{
+	__blk_mq_free_rqs_ext(set, tags, hctx_idx, NULL);
+}
+
 void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags)
 {
 	kfree(tags->rqs);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index c1458d9502f1..487ca30a6509 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -53,6 +53,8 @@ struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
  */
 void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		     unsigned int hctx_idx);
+void blk_mq_free_rqs_ext(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx, struct blk_mq_tags *references);
 void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags);
 struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 					unsigned int hctx_idx,
-- 
2.26.2


  reply	other threads:[~2020-12-17 11:12 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-17 11:07 [RFC PATCH v2 0/2] blk-mq: Avoid use-after-free for accessing old requests John Garry
2020-12-17 11:07 ` John Garry [this message]
2020-12-17 11:07 ` [RFC PATCH v2 2/2] blk-mq: Lockout tagset iter when freeing rqs John Garry
2020-12-18  1:55   ` Bart Van Assche
2020-12-18  9:30     ` John Garry
2020-12-18  3:31   ` Ming Lei
2020-12-18 10:01     ` John Garry
2020-12-18 22:43   ` Bart Van Assche
2020-12-21 12:06     ` John Garry
2020-12-21 18:09       ` Bart Van Assche
2020-12-21 18:47         ` John Garry
2020-12-22  2:13           ` Bart Van Assche
2020-12-22 11:15             ` John Garry
2020-12-22 16:16               ` Bart Van Assche
2020-12-23 11:10                 ` John Garry
2020-12-23 11:40                   ` John Garry
2020-12-23 15:47                     ` Bart Van Assche
2021-01-04 15:33                       ` John Garry
2021-01-04 17:22                         ` Bart Van Assche
2021-01-04 18:43                           ` John Garry
     [not found]                           ` <760304b3-dcbc-5b9d-0c70-627b7ff5b4eb@huawei.com>
2021-02-10 14:39                             ` John Garry
2020-12-22 11:22             ` John Garry
2020-12-22 13:24               ` Ming Lei

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1608203273-170555-2-git-send-email-john.garry@huawei.com \
    --to=john.garry@huawei.com \
    --cc=axboe@kernel.dk \
    --cc=bvanassche@acm.org \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=kashyap.desai@broadcom.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxarm@huawei.com \
    --cc=ming.lei@redhat.com \
    --cc=ppvk@codeaurora.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®