Re: [PATCH] blk-mq: Fix recently introduced races in the timeout handling code

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Subject: Re: [PATCH] blk-mq: Fix recently introduced races in the timeout handling code
From: Christoph Hellwig <hch@xxxxxx>
Date: Mon, 9 Apr 2018 11:37:44 +0200
Cc: Jens Axboe <axboe@xxxxxxxxx>, linux-block@xxxxxxxxxxxxxxx, Christoph Hellwig <hch@xxxxxx>, Tejun Heo <tj@xxxxxxxxxx>, Sagi Grimberg <sagi@xxxxxxxxxxx>, Israel Rukshin <israelr@xxxxxxxxxxxx>, Max Gurtovoy <maxg@xxxxxxxxxxxx>, stable@xxxxxxxxxxxxxxx
In-reply-to: <20180409052038.5391-1-bart.vanassche@wdc.com>
User-agent: Mutt/1.5.17 (2007-11-01)

This looks sensible, but I'm worried about taking a whole spinlock
for every request completion, including irq disabling.  However it seems
like your new updated pattern would fit use of cmpxchg() very nicely.

Follow-Ups:
- Re: [PATCH] blk-mq: Fix recently introduced races in the timeout handling code
  - From: Bart Van Assche

References:
- [PATCH] blk-mq: Fix recently introduced races in the timeout handling code
  - From: Bart Van Assche

Prev by Date: Patch "IB/rdmavt: Allocate CQ memory on the correct node" has been added to the 4.15-stable tree
Next by Date: Patch "IB/mlx5: Report inner RSS capability" has been added to the 4.15-stable tree
Previous by thread: Re: [PATCH] blk-mq: Fix recently introduced races in the timeout handling code
Next by thread: Re: [PATCH] blk-mq: Fix recently introduced races in the timeout handling code
Index(es):
- Date
- Thread

[Index of Archives] [Linux Kernel] [Kernel Development Newbies] [Linux USB Devel] [Video for Linux] [Linux Audio Users] [Yosemite Hiking] [Linux Kernel] [Linux SCSI]