[PATCH 5/6] NFSD: leverage DIO alignment to selectively issue O_DIRECT reads and writes

[Mike Snitzer <snitzer@xxxxxxxxxx>]

IO must be aligned, otherwise it falls back to using buffered IO.

RWF_DONTCACHE is _not_ currently used for misaligned IO (even when
nfsd/enable-dontcache=1) because it works against us (due to RMW
needing to read without benefit of cache), whereas buffered IO enables
misaligned IO to be more performant.

Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
---
 fs/nfsd/vfs.c | 40 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 36 insertions(+), 4 deletions(-)

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index e7cc8c6dfbad..a942609e3ab9 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1064,6 +1064,22 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err);
 }
 
+static bool is_dio_aligned(const struct iov_iter *iter, loff_t offset,
+			   const u32 blocksize)
+{
+	u32 blocksize_mask;
+
+	if (!blocksize)
+		return false;
+
+	blocksize_mask = blocksize - 1;
+	if ((offset & blocksize_mask) ||
+	    (iov_iter_alignment(iter) & blocksize_mask))
+		return false;
+
+	return true;
+}
+
 /**
  * nfsd_iter_read - Perform a VFS read using an iterator
  * @rqstp: RPC transaction context
@@ -1107,8 +1123,16 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	trace_nfsd_read_vector(rqstp, fhp, offset, *count);
 	iov_iter_bvec(&iter, ITER_DEST, rqstp->rq_bvec, v, *count);
 
-	if (nfsd_enable_dontcache)
-		flags |= RWF_DONTCACHE;
+	if (nfsd_enable_dontcache) {
+		if (is_dio_aligned(&iter, offset, nf->nf_dio_read_offset_align))
+			flags |= RWF_DIRECT;
+		/* FIXME: not using RWF_DONTCACHE for misaligned IO because it works
+		 * against us (due to RMW needing to read without benefit of cache),
+		 * whereas buffered IO enables misaligned IO to be more performant.
+		 */
+		//else
+		//	flags |= RWF_DONTCACHE;
+	}
 
 	host_err = vfs_iter_read(file, &iter, &ppos, flags);
 	return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err);
@@ -1217,8 +1241,16 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	nvecs = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, payload);
 	iov_iter_bvec(&iter, ITER_SOURCE, rqstp->rq_bvec, nvecs, *cnt);
 
-	if (nfsd_enable_dontcache)
-		flags |= RWF_DONTCACHE;
+	if (nfsd_enable_dontcache) {
+		if (is_dio_aligned(&iter, offset, nf->nf_dio_offset_align))
+			flags |= RWF_DIRECT;
+		/* FIXME: not using RWF_DONTCACHE for misaligned IO because it works
+		 * against us (due to RMW needing to read without benefit of cache),
+		 * whereas buffered IO enables misaligned IO to be more performant.
+		 */
+		//else
+		//	flags |= RWF_DONTCACHE;
+	}
 
 	since = READ_ONCE(file->f_wb_err);
 	if (verf)
-- 
2.44.0