From: Mike Snitzer <snitzer@kernel.org>
To: Christoph Hellwig <hch@infradead.org>,
Alexander Viro <viro@zeniv.linux.org.uk>,
Andrew Morton <akpm@linux-foundation.org>
Cc: Jeff Layton <jlayton@kernel.org>,
Chuck Lever <chuck.lever@oracle.com>,
linux-nfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
Jens Axboe <axboe@kernel.dk>,
david.flynn@hammerspace.com
Subject: [RFC PATCH] lib/iov_iter: remove piecewise bvec length checking in iov_iter_aligned_bvec [was: Re: need SUNRPC TCP to receive into aligned pages]
Date: Tue, 17 Jun 2025 18:23:05 -0400 [thread overview]
Message-ID: <aFHqyU4qO_W1enUT@kernel.org> (raw)
In-Reply-To: <aFHPgrPM798wXdSG@kernel.org>
[Cc'ing Al and Andrew]
On Tue, Jun 17, 2025 at 04:26:42PM -0400, Mike Snitzer wrote:
> On Mon, Jun 16, 2025 at 09:37:01PM -0700, Christoph Hellwig wrote:
> > On Mon, Jun 16, 2025 at 12:07:42PM -0400, Mike Snitzer wrote:
> > > But that's OK... my test bdev is a bad example (archaic VMware vSphere
> > > provided SCSI device): it doesn't reflect expected modern hardware.
> > >
> > > But I just slapped together a test pmem blockdevice (memory backed,
> > > using memmap=6G!18G) and it too has dma_alignment=511
> >
> > That's the block layer default when not overriden by the driver, I guess
> > pmem folks didn't care enough. I suspect it should not have any
> > alignment requirements at all.
>
> Yeah, I hacked it with this just to quickly simulate NVMe's dma_alignment:
>
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index 210fb77f51ba..0ab2826073f9 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -457,6 +457,7 @@ static int pmem_attach_disk(struct device *dev,
> .max_hw_sectors = UINT_MAX,
> .features = BLK_FEAT_WRITE_CACHE |
> BLK_FEAT_SYNCHRONOUS,
> + .dma_alignment = 3,
> };
> int nid = dev_to_node(dev), fua;
> struct resource *res = &nsio->res;
>
> > > I'd like NFSD to be able to know if its bvec is dma-aligned, before
> > > issuing DIO writes to underlying XFS. AFAIK I can do that simply by
> > > checking the STATX_DIOALIGN provided dio_mem_align...
> >
> > Exactly.
>
> I'm finding that even with dma_alignment=3 the bvec, that
> nfsd_vfs_write()'s call to xdr_buf_to_bvec() produces from NFS's WRITE
> payload, still causes iov_iter_aligned_bvec() to return false.
>
> The reason is that iov_iter_aligned_bvec() inspects each member of the
> bio_vec in isolation (in its while() loop). So even though NFS WRITE
> payload's overall size is aligned on-disk (e.g. offset=0 len=512K) its
> first and last bvec members are _not_ aligned (due to 512K NFS WRITE
> payload being offset 148 bytes into the first page of the pages
> allocated for it by SUNRPC). So iov_iter_aligned_bvec() fails at this
> check:
>
> if (len & len_mask)
> return false;
>
> with tracing I added:
>
> nfsd-14027 [001] ..... 3734.668780: nfsd_vfs_write: iov_iter_aligned_bvec: addr_mask=3 len_mask=511
> nfsd-14027 [001] ..... 3734.668781: nfsd_vfs_write: iov_iter_aligned_bvec: len=3948 & len_mask=511 failed
>
> Is this another case of the checks being too strict? The bvec does
> describe a contiguous 512K extent of on-disk LBA, just not if
> inspected piece-wise.
>
> BTW, XFS's directio code _will_ also check with
> iov_iter_aligned_bvec() via iov_iter_is_aligned().
This works, I just don't know what (if any) breakage it exposes us to:
Author: Mike Snitzer <snitzer@kernel.org>
Date: Tue Jun 17 22:04:44 2025 +0000
Subject: lib/iov_iter: remove piecewise bvec length checking in iov_iter_aligned_bvec
iov_iter_aligned_bvec() is strictly checking alignment of each element
of the bvec to arrive at whether the bvec is aligned relative to
dma_alignment and on-disk alignment. Checking each element
individually results in disallowing a bvec that in aggregate is
perfectly aligned relative to the provided @len_mask.
Relax the on-disk alignment checking such that it is done on the full
extent described by the bvec but still do piecewise checking of the
dma_alignment for each bvec's bv_offset.
This allows for NFS's WRITE payload to be issued using O_DIRECT as
long as the bvec created with xdr_buf_to_bvec() is composed of pages
that respect the underlying device's dma_alignment (@addr_mask) and
the overall contiguous on-disk extent is aligned relative to the
logical_block_size (@len_mask).
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index bdb37d572e97..b2ae482b8a1d 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -819,13 +819,14 @@ static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask,
unsigned skip = i->iov_offset;
size_t size = i->count;
+ if (size & len_mask)
+ return false;
+
do {
size_t len = bvec->bv_len;
if (len > size)
len = size;
- if (len & len_mask)
- return false;
if ((unsigned long)(bvec->bv_offset + skip) & addr_mask)
return false;
next prev parent reply other threads:[~2025-06-17 22:23 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-10 20:57 [PATCH 0/6] NFSD: add enable-dontcache and initially use it to add DIO support Mike Snitzer
2025-06-10 20:57 ` [PATCH 1/6] NFSD: add the ability to enable use of RWF_DONTCACHE for all IO Mike Snitzer
2025-06-11 6:57 ` Christoph Hellwig
2025-06-11 10:44 ` Mike Snitzer
2025-06-11 13:04 ` Jeff Layton
2025-06-11 13:56 ` Chuck Lever
2025-06-11 14:31 ` Chuck Lever
2025-06-11 19:18 ` Mike Snitzer
2025-06-11 20:29 ` Jeff Layton
2025-06-11 21:36 ` need SUNRPC TCP to receive into aligned pages [was: Re: [PATCH 1/6] NFSD: add the ability to enable use of RWF_DONTCACHE for all IO] Mike Snitzer
2025-06-12 10:28 ` Jeff Layton
2025-06-12 11:28 ` Jeff Layton
2025-06-12 13:28 ` Chuck Lever
2025-06-12 14:17 ` Benjamin Coddington
2025-06-12 15:56 ` Mike Snitzer
2025-06-12 15:58 ` Chuck Lever
2025-06-12 16:12 ` Mike Snitzer
2025-06-12 16:32 ` Chuck Lever
2025-06-13 5:39 ` Christoph Hellwig
2025-06-12 16:22 ` Jeff Layton
2025-06-13 5:46 ` Christoph Hellwig
2025-06-13 9:23 ` Mike Snitzer
2025-06-13 13:02 ` Jeff Layton
2025-06-16 12:35 ` Christoph Hellwig
2025-06-16 12:29 ` Christoph Hellwig
2025-06-16 16:07 ` Mike Snitzer
2025-06-17 4:37 ` Christoph Hellwig
2025-06-17 20:26 ` Mike Snitzer
2025-06-17 22:23 ` Mike Snitzer [this message]
2025-07-03 0:12 ` NeilBrown
2025-06-12 7:13 ` [PATCH 1/6] NFSD: add the ability to enable use of RWF_DONTCACHE for all IO Christoph Hellwig
2025-06-12 13:15 ` Chuck Lever
2025-06-12 13:21 ` Chuck Lever
2025-06-12 16:00 ` Mike Snitzer
2025-06-16 13:32 ` Chuck Lever
2025-06-16 16:10 ` Mike Snitzer
2025-06-17 17:22 ` Mike Snitzer
2025-06-17 17:31 ` Chuck Lever
2025-06-19 20:19 ` Mike Snitzer
2025-06-30 14:50 ` Chuck Lever
2025-07-04 19:46 ` Mike Snitzer
2025-07-04 19:49 ` Chuck Lever
2025-06-10 20:57 ` [PATCH 2/6] NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support Mike Snitzer
2025-06-10 20:57 ` [PATCH 3/6] NFSD: pass nfsd_file to nfsd_iter_read() Mike Snitzer
2025-06-10 20:57 ` [PATCH 4/6] fs: introduce RWF_DIRECT to allow using O_DIRECT on a per-IO basis Mike Snitzer
2025-06-11 6:58 ` Christoph Hellwig
2025-06-11 10:51 ` Mike Snitzer
2025-06-11 14:17 ` Chuck Lever
2025-06-12 7:15 ` Christoph Hellwig
2025-06-10 20:57 ` [PATCH 5/6] NFSD: leverage DIO alignment to selectively issue O_DIRECT reads and writes Mike Snitzer
2025-06-11 7:00 ` Christoph Hellwig
2025-06-11 12:23 ` Mike Snitzer
2025-06-11 13:30 ` Jeff Layton
2025-06-12 7:22 ` Christoph Hellwig
2025-06-12 7:23 ` Christoph Hellwig
2025-06-11 14:42 ` Chuck Lever
2025-06-11 15:07 ` Jeff Layton
2025-06-11 15:11 ` Chuck Lever
2025-06-11 15:44 ` Jeff Layton
2025-06-11 20:51 ` Mike Snitzer
2025-06-12 7:32 ` Christoph Hellwig
2025-06-12 7:28 ` Christoph Hellwig
2025-06-12 7:25 ` Christoph Hellwig
2025-06-10 20:57 ` [PATCH 6/6] NFSD: issue READs using O_DIRECT even if IO is misaligned Mike Snitzer
2025-06-11 12:55 ` [PATCH 0/6] NFSD: add enable-dontcache and initially use it to add DIO support Jeff Layton
2025-06-12 7:39 ` Christoph Hellwig
2025-06-12 20:37 ` Mike Snitzer
2025-06-13 5:31 ` Christoph Hellwig
2025-06-11 14:16 ` Chuck Lever
2025-06-11 18:02 ` Mike Snitzer
2025-06-11 19:06 ` Chuck Lever
2025-06-11 19:58 ` Mike Snitzer
2025-06-12 13:46 ` Chuck Lever
2025-06-12 19:08 ` Mike Snitzer
2025-06-12 20:17 ` Chuck Lever
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=aFHqyU4qO_W1enUT@kernel.org \
--to=snitzer@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=axboe@kernel.dk \
--cc=chuck.lever@oracle.com \
--cc=david.flynn@hammerspace.com \
--cc=hch@infradead.org \
--cc=jlayton@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-nfs@vger.kernel.org \
--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).