On 8/5/25 2:44 PM, Mike Snitzer wrote:
> From: Mike Snitzer <snitzer@xxxxxxxxxxxxxxx>
>
> Check the bvec is DIO-aligned while creating it, saves CPU cycles by
> avoiding iterating the bvec elements a second time using
> iov_iter_is_aligned().
>
> This prepares for Keith Busch's near-term removal of the
> iov_iter_is_aligned() interface. This fixes cel/nfsd-testing commit
> 5d78ac1e674b4 ("NFSD: issue READs using O_DIRECT even if IO is
> misaligned") and it should be folded into that commit so that NFSD
> doesn't require iov_iter_is_aligned() while it is being removed
> upstream in parallel.
>
> Fixes: cel/nfsd-testing 5d78ac1e674b4 ("NFSD: issue READs using O_DIRECT even if IO is misaligned")
> Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxxxxxxx>
> ---
> fs/nfsd/vfs.c | 29 +++++++++++++++--------------
> 1 file changed, 15 insertions(+), 14 deletions(-)
>
> diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
> index 46189020172fb..e1751d3715264 100644
> --- a/fs/nfsd/vfs.c
> +++ b/fs/nfsd/vfs.c
> @@ -1226,7 +1226,10 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
> */
> offset = read_dio.start;
> in_count = read_dio.end - offset;
> - kiocb.ki_flags = IOCB_DIRECT;
> + /* Verify ondisk DIO alignment, memory addrs checked below */
> + if (likely(((offset | in_count) &
> + (nf->nf_dio_read_offset_align - 1)) == 0))
> + kiocb.ki_flags = IOCB_DIRECT;
> }
> } else if (nfsd_io_cache_read == NFSD_IO_DONTCACHE)
> kiocb.ki_flags = IOCB_DONTCACHE;
> @@ -1236,16 +1239,24 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
> v = 0;
> total = in_count;
> if (read_dio.start_extra) {
> - bvec_set_page(&rqstp->rq_bvec[v++], read_dio.start_extra_page,
> + bvec_set_page(&rqstp->rq_bvec[v], read_dio.start_extra_page,
> read_dio.start_extra, PAGE_SIZE - read_dio.start_extra);
> + if (unlikely((kiocb.ki_flags & IOCB_DIRECT) &&
> + rqstp->rq_bvec[v].bv_offset & (nf->nf_dio_mem_align - 1)))
> + kiocb.ki_flags &= ~IOCB_DIRECT;
> total -= read_dio.start_extra;
> + v++;
> }
> while (total) {
> len = min_t(size_t, total, PAGE_SIZE - base);
> - bvec_set_page(&rqstp->rq_bvec[v++], *(rqstp->rq_next_page++),
> - len, base);
> + bvec_set_page(&rqstp->rq_bvec[v], *(rqstp->rq_next_page++), len, base);
> + /* No need to verify memory is DIO-aligned since bv_offset is 0 */
> + if (unlikely((kiocb.ki_flags & IOCB_DIRECT) && base &&
> + (base & (nf->nf_dio_mem_align - 1))))
> + kiocb.ki_flags &= ~IOCB_DIRECT;
> total -= len;
> base = 0;
> + v++;
> }
> if (WARN_ONCE(v > rqstp->rq_maxpages,
> "%s: v=%lu exceeds rqstp->rq_maxpages=%lu\n", __func__,
> @@ -1256,16 +1267,6 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
> if (!host_err) {
> trace_nfsd_read_vector(rqstp, fhp, offset, in_count);
> iov_iter_bvec(&iter, ITER_DEST, rqstp->rq_bvec, v, in_count);
> -
> - /* Double check nfsd_analyze_read_dio's DIO-aligned result */
> - if (unlikely((kiocb.ki_flags & IOCB_DIRECT) &&
> - !iov_iter_is_aligned(&iter,
> - nf->nf_dio_mem_align - 1,
> - nf->nf_dio_read_offset_align - 1))) {
> - /* Fallback to buffered IO */
> - kiocb.ki_flags &= ~IOCB_DIRECT;
> - }
> -
> host_err = vfs_iocb_iter_read(file, &kiocb, &iter);
> }
>
Hi Mike,
In cases where the SQUASHME patch is this large, I usually drop the
patch (or series) in nfsd-testing and ask the contributor to rebase and
repost. This gets the new version of the patch properly archived on
lore, for one thing.
Before reposting, please do run checkpatch.pl on the series.
--
Chuck Lever
