From: Nilay Shroff <nilay@linux.ibm.com>
To: John Garry <john.g.garry@oracle.com>
Cc: axboe@kernel.dk, brauner@kernel.org, bvanassche@acm.org,
dchinner@redhat.com, djwong@kernel.org, hch@lst.de, jack@suse.cz,
jbongio@google.com, jejb@linux.ibm.com, kbusch@kernel.org,
linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-nvme@lists.infradead.org,
linux-scsi@vger.kernel.org, linux-xfs@vger.kernel.org,
martin.petersen@oracle.com, ming.lei@redhat.com,
ojaswin@linux.ibm.com, sagi@grimberg.me, tytso@mit.edu,
viro@zeniv.linux.org.uk
Subject: Re: [PATCH v3 10/15] block: Add fops atomic write support
Date: Tue, 13 Feb 2024 16:38:31 +0530 [thread overview]
Message-ID: <e99cf4ef-40ec-4e66-956f-c9e2aebb4621@linux.ibm.com> (raw)
In-Reply-To: <9ffc3102-2936-4f83-b69d-bbf64793b9ca@oracle.com>
On 2/13/24 15:28, John Garry wrote:
> On 13/02/2024 09:36, Nilay Shroff wrote:
>>> +static bool blkdev_atomic_write_valid(struct block_device *bdev, loff_t pos,
>>
>>> + struct iov_iter *iter)
>>
>>> +{
>>
>>> + struct request_queue *q = bdev_get_queue(bdev);
>>
>>> + unsigned int min_bytes = queue_atomic_write_unit_min_bytes(q);
>>
>>> + unsigned int max_bytes = queue_atomic_write_unit_max_bytes(q);
>>
>>> +
>>
>>> + if (!iter_is_ubuf(iter))
>>
>>> + return false;
>>
>>> + if (iov_iter_count(iter) & (min_bytes - 1))
>>
>>> + return false;
>>
>>> + if (!is_power_of_2(iov_iter_count(iter)))
>>
>>> + return false;
>>
>>> + if (pos & (iov_iter_count(iter) - 1))
>>
>>> + return false;
>>
>>> + if (iov_iter_count(iter) > max_bytes)
>>
>>> + return false;
>>
>>> + return true;
>>
>>> +}
>>
>>
>>
>> Here do we need to also validate whether the IO doesn't straddle
>>
>> the atmic bondary limit (if it's non-zero)? We do check that IO
>>
>> doesn't straddle the atomic boundary limit but that happens very
>>
>> late in the IO code path either during blk-merge or in NVMe driver
>>
>> code.
>
> It's relied that atomic_write_unit_max is <= atomic_write_boundary and both are a power-of-2. Please see the NVMe patch, which this is checked. Indeed, it would not make sense if atomic_write_unit_max > atomic_write_boundary (when non-zero).
>
> So if the write is naturally aligned and its size is <= atomic_write_unit_max, then it cannot be straddling a boundary.
Ok fine but in case the device doesn't support namespace atomic boundary size (i.e. NABSPF is zero) then still do we need
to restrict IO which crosses the atomic boundary?
I am quoting this from NVMe spec (Command Set Specification, revision 1.0a, Section 2.1.4.3) :
"To ensure backwards compatibility, the values reported for AWUN, AWUPF, and ACWU shall be set such that
they are supported even if a write crosses an atomic boundary. If a controller does not
guarantee atomicity across atomic boundaries, the controller shall set AWUN, AWUPF, and ACWU to 0h (1 LBA)."
Thanks,
--Nilay
next prev parent reply other threads:[~2024-02-13 11:09 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-24 11:38 [PATCH v3 00/15] block atomic writes John Garry
2024-01-24 11:38 ` [PATCH v3 01/15] block: Add atomic write operations to request_queue limits John Garry
2024-02-13 6:22 ` Christoph Hellwig
2024-01-24 11:38 ` [PATCH v3 02/15] block: Limit atomic writes according to bio and queue limits John Garry
2024-02-13 4:33 ` Ritesh Harjani
2024-02-13 8:05 ` John Garry
2024-01-24 11:38 ` [PATCH v3 03/15] fs/bdev: Add atomic write support info to statx John Garry
2024-01-24 11:38 ` [PATCH v3 04/15] fs: Add RWF_ATOMIC and IOCB_ATOMIC flags for atomic write support John Garry
2024-01-24 11:38 ` [PATCH v3 05/15] block: Add REQ_ATOMIC flag John Garry
2024-02-13 6:24 ` Christoph Hellwig
2024-01-24 11:38 ` [PATCH v3 06/15] block: Pass blk_queue_get_max_sectors() a request pointer John Garry
2024-02-13 6:23 ` Christoph Hellwig
2024-02-13 8:15 ` John Garry
2024-01-24 11:38 ` [PATCH v3 07/15] block: Limit atomic write IO size according to atomic_write_max_sectors John Garry
2024-02-13 6:26 ` Christoph Hellwig
2024-02-13 8:15 ` John Garry
2024-02-14 7:26 ` Christoph Hellwig
2024-02-14 9:24 ` John Garry
2024-01-24 11:38 ` [PATCH v3 08/15] block: Error an attempt to split an atomic write bio John Garry
2024-01-24 11:38 ` [PATCH v3 09/15] block: Add checks to merging of atomic writes John Garry
2024-02-12 10:54 ` Nilay Shroff
2024-02-12 11:20 ` [PATCH " John Garry
2024-02-12 12:01 ` Nilay Shroff
2024-02-12 12:09 ` John Garry
2024-02-13 6:52 ` Nilay Shroff
2024-01-24 11:38 ` [PATCH v3 10/15] block: Add fops atomic write support John Garry
2024-02-13 9:36 ` Nilay Shroff
2024-02-13 9:58 ` [PATCH " John Garry
2024-02-13 11:08 ` Nilay Shroff [this message]
2024-02-13 11:52 ` John Garry
2024-02-14 9:38 ` Nilay Shroff
2024-02-14 11:29 ` John Garry
2024-02-14 11:47 ` Nilay Shroff
2024-01-24 11:38 ` [PATCH v3 11/15] scsi: sd: Support reading atomic write properties from block limits VPD John Garry
2024-02-13 6:31 ` Christoph Hellwig
2024-02-13 8:16 ` John Garry
2024-01-24 11:38 ` [PATCH v3 12/15] scsi: sd: Add WRITE_ATOMIC_16 support John Garry
2024-01-24 11:38 ` [PATCH v3 13/15] scsi: scsi_debug: Atomic write support John Garry
2024-01-24 11:38 ` [PATCH v3 14/15] nvme: Support atomic writes John Garry
2024-02-13 6:42 ` Christoph Hellwig
2024-02-13 14:21 ` John Garry
2024-02-14 8:00 ` Christoph Hellwig
2024-02-14 9:21 ` John Garry
2024-02-14 12:27 ` Nilay Shroff
2024-02-14 13:02 ` John Garry
2024-02-14 16:45 ` Nilay Shroff
2024-01-24 11:38 ` [PATCH v3 15/15] nvme: Ensure atomic writes will be executed atomically John Garry
2024-01-25 0:52 ` Keith Busch
2024-01-25 11:28 ` John Garry
2024-01-29 6:20 ` Christoph Hellwig
2024-01-29 9:36 ` John Garry
2024-01-29 14:39 ` Christoph Hellwig
2024-01-26 3:50 ` Chaitanya Kulkarni
2024-02-13 6:42 ` Christoph Hellwig
2024-02-13 14:07 ` John Garry
2024-01-29 6:18 ` [PATCH v3 00/15] block atomic writes Christoph Hellwig
2024-01-29 9:17 ` John Garry
2024-02-06 18:44 ` John Garry
2024-02-10 12:12 ` David Laight
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=e99cf4ef-40ec-4e66-956f-c9e2aebb4621@linux.ibm.com \
--to=nilay@linux.ibm.com \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--cc=bvanassche@acm.org \
--cc=dchinner@redhat.com \
--cc=djwong@kernel.org \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=jbongio@google.com \
--cc=jejb@linux.ibm.com \
--cc=john.g.garry@oracle.com \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-scsi@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=ming.lei@redhat.com \
--cc=ojaswin@linux.ibm.com \
--cc=sagi@grimberg.me \
--cc=tytso@mit.edu \
--cc=viro@zeniv.linux.org.uk \
/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;
as well as URLs for NNTP newsgroup(s).