linux-kernel - Re: New warning in nvme_setup

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]

Message-ID: <YPFSUfG+fMITAH01@T590>
Date:   Fri, 16 Jul 2021 17:33:05 +0800
From:   Ming Lei <ming.lei@...hat.com>
To:     Oleksandr Natalenko <oleksandr@...alenko.name>
Cc:     linux-kernel@...r.kernel.org, Jens Axboe <axboe@...com>,
        Christoph Hellwig <hch@....de>,
        Sagi Grimberg <sagi@...mberg.me>,
        linux-nvme@...ts.infradead.org,
        David Jeffery <djeffery@...hat.com>,
        Laurence Oberman <loberman@...hat.com>,
        Paolo Valente <paolo.valente@...aro.org>,
        Jan Kara <jack@...e.cz>, Sasha Levin <sashal@...nel.org>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        Keith Busch <kbusch@...nel.org>
Subject: Re: New warning in nvme_setup_discard

On Fri, Jul 16, 2021 at 07:53:28AM +0200, Oleksandr Natalenko wrote:
> Hello.
> 
> On pátek 16. července 2021 4:16:18 CEST Ming Lei wrote:
> > >  850     if (WARN_ON_ONCE(n != segments)) {
> > 
> > What is 'n' and 'segments'?
> 
> So, I used this change to check that:
> 
> ```
> diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
> index 66973bb56305..0a64f2f77daf 100644
> --- a/drivers/nvme/host/core.c
> +++ b/drivers/nvme/host/core.c
> @@ -847,7 +847,8 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, 
> struct request *req,
>  		n++;
>  	}
>  
> -	if (WARN_ON_ONCE(n != segments)) {
> +	if (unlikely(n != segments)) {
> +		pr_warn("nvme_setup_discard: n != segments (%u != %u)\n", n, 
> segments);
>  		if (virt_to_page(range) == ns->ctrl->discard_page)
>  			clear_bit_unlock(0, &ns->ctrl->discard_page_busy);
>  		else
> 
> ```
> 
> and the result is:
> 
> ```
> nvme_setup_discard: n != segments (3 != 2)
> nvme_setup_discard: n != segments (12 != 11)
> ```

Can you test the following patch?

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 727955918563..673a634eadd9 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -2361,6 +2361,9 @@ static int bfq_request_merge(struct request_queue *q, struct request **req,
 	__rq = bfq_find_rq_fmerge(bfqd, bio, q);
 	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
+
+		if (blk_discard_mergable(__rq))
+			return ELEVATOR_DISCARD_MERGE;
 		return ELEVATOR_FRONT_MERGE;
 	}
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index a11b3b53717e..f8707ff7e2fc 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -705,22 +705,6 @@ static void blk_account_io_merge_request(struct request *req)
 	}
 }
 
-/*
- * Two cases of handling DISCARD merge:
- * If max_discard_segments > 1, the driver takes every bio
- * as a range and send them to controller together. The ranges
- * needn't to be contiguous.
- * Otherwise, the bios/requests will be handled as same as
- * others which should be contiguous.
- */
-static inline bool blk_discard_mergable(struct request *req)
-{
-	if (req_op(req) == REQ_OP_DISCARD &&
-	    queue_max_discard_segments(req->q) > 1)
-		return true;
-	return false;
-}
-
 static enum elv_merge blk_try_req_merge(struct request *req,
 					struct request *next)
 {
diff --git a/block/elevator.c b/block/elevator.c
index 52ada14cfe45..a5fe2615ec0f 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -336,6 +336,9 @@ enum elv_merge elv_merge(struct request_queue *q, struct request **req,
 	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
 	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
+
+		if (blk_discard_mergable(__rq))
+			return ELEVATOR_DISCARD_MERGE;
 		return ELEVATOR_BACK_MERGE;
 	}
 
diff --git a/block/mq-deadline-main.c b/block/mq-deadline-main.c
index 6f612e6dc82b..294be0c0db65 100644
--- a/block/mq-deadline-main.c
+++ b/block/mq-deadline-main.c
@@ -677,6 +677,8 @@ static int dd_request_merge(struct request_queue *q, struct request **rq,
 
 		if (elv_bio_merge_ok(__rq, bio)) {
 			*rq = __rq;
+			if (blk_discard_mergable(__rq))
+				return ELEVATOR_DISCARD_MERGE;
 			return ELEVATOR_FRONT_MERGE;
 		}
 	}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3177181c4326..87f00292fd7a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1521,6 +1521,22 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 	return offset << SECTOR_SHIFT;
 }
 
+/*
+ * Two cases of handling DISCARD merge:
+ * If max_discard_segments > 1, the driver takes every bio
+ * as a range and send them to controller together. The ranges
+ * needn't to be contiguous.
+ * Otherwise, the bios/requests will be handled as same as
+ * others which should be contiguous.
+ */
+static inline bool blk_discard_mergable(struct request *req)
+{
+	if (req_op(req) == REQ_OP_DISCARD &&
+	    queue_max_discard_segments(req->q) > 1)
+		return true;
+	return false;
+}
+
 static inline int bdev_discard_alignment(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);

Thanks,
Ming