On 7/31/25 7:06 PM, Mike Snitzer wrote:
> Refactor nfsd_vfs_write() to support splitting a WRITE into parts
> (which will be either misaligned or DIO-aligned). Doing so in a
> preliminary commit just allows for indentation and slight
> transformation to be more easily understood and reviewed.
>
> Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
> Reviewed-by: Jeff Layton <jlayton@xxxxxxxxxx>
> ---
> fs/nfsd/vfs.c | 45 +++++++++++++++++++++++++++------------------
> 1 file changed, 27 insertions(+), 18 deletions(-)
>
> diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
> index 35c29b8ade9c3..edac73349da0f 100644
> --- a/fs/nfsd/vfs.c
> +++ b/fs/nfsd/vfs.c
> @@ -1341,7 +1341,6 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
> struct super_block *sb = file_inode(file)->i_sb;
> struct kiocb kiocb;
> struct svc_export *exp;
> - struct iov_iter iter;
> errseq_t since;
> __be32 nfserr;
> int host_err;
> @@ -1349,6 +1348,9 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
> unsigned int pflags = current->flags;
> bool restore_flags = false;
> unsigned int nvecs;
> + struct iov_iter iter_stack[1];
> + struct iov_iter *iter = iter_stack;
> + unsigned int n_iters = 0;
>
> trace_nfsd_write_opened(rqstp, fhp, offset, *cnt);
>
> @@ -1378,14 +1380,15 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
> kiocb.ki_flags |= IOCB_DSYNC;
>
> nvecs = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, payload);
> - iov_iter_bvec(&iter, ITER_SOURCE, rqstp->rq_bvec, nvecs, *cnt);
> + iov_iter_bvec(&iter[0], ITER_SOURCE, rqstp->rq_bvec, nvecs, *cnt);
> + n_iters++;
>
> switch (nfsd_io_cache_write) {
> case NFSD_IO_DIRECT:
> /* direct I/O must be aligned to device logical sector size */
> if (nf->nf_dio_mem_align && nf->nf_dio_offset_align &&
> (((offset | *cnt) & (nf->nf_dio_offset_align-1)) == 0) &&
> - iov_iter_is_aligned(&iter, nf->nf_dio_mem_align - 1,
> + iov_iter_is_aligned(&iter[0], nf->nf_dio_mem_align - 1,
> nf->nf_dio_offset_align - 1))
> kiocb.ki_flags = IOCB_DIRECT;
> break;
> @@ -1399,22 +1402,28 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
> since = READ_ONCE(file->f_wb_err);
> if (verf)
> nfsd_copy_write_verifier(verf, nn);
> - host_err = vfs_iocb_iter_write(file, &kiocb, &iter);
> - if (host_err < 0) {
> - commit_reset_write_verifier(nn, rqstp, host_err);
> - goto out_nfserr;
> - }
> - *cnt = host_err;
> - nfsd_stats_io_write_add(nn, exp, *cnt);
> - fsnotify_modify(file);
> - host_err = filemap_check_wb_err(file->f_mapping, since);
> - if (host_err < 0)
> - goto out_nfserr;
> -
> - if (stable && fhp->fh_use_wgather) {
> - host_err = wait_for_concurrent_writes(file);
> - if (host_err < 0)
> + *cnt = 0;
> + for (int i = 0; i < n_iters; i++) {
> + host_err = vfs_iocb_iter_write(file, &kiocb, &iter[i]);
> + if (host_err < 0) {
> commit_reset_write_verifier(nn, rqstp, host_err);
> + goto out_nfserr;
> + }
Does this loop wait after each iter is written? Would it be better to
wait once after all the iters have been written?
> + *cnt += host_err;
> + nfsd_stats_io_write_add(nn, exp, host_err);
> +
> + fsnotify_modify(file);
> + host_err = filemap_check_wb_err(file->f_mapping, since);
> + if (host_err < 0)
> + goto out_nfserr;
> +
> + if (stable && fhp->fh_use_wgather) {
> + host_err = wait_for_concurrent_writes(file);
> + if (host_err < 0) {
> + commit_reset_write_verifier(nn, rqstp, host_err);
> + goto out_nfserr;
> + }
> + }
> }
>
> out_nfserr:
--
Chuck Lever
