Re: [PATCH v11 2/7] nfs/localio: avoid issuing misaligned IO using O_DIRECT

Add nfsd_file_dio_alignment and use it to avoid issuing misaligned IO
using O_DIRECT. Any misaligned DIO falls back to using buffered IO.

Because misaligned DIO is now handled safely, remove the nfs modparam
'localio_O_DIRECT_semantics' that was added to require users opt-in to
the requirement that all O_DIRECT be properly DIO-aligned.

Also, introduce nfs_iov_iter_aligned_bvec() which is a variant of
iov_iter_aligned_bvec() that also verifies the offset associated with
an iov_iter is DIO-aligned.  NOTE: in a parallel effort,
iov_iter_aligned_bvec() is being removed along with
iov_iter_is_aligned().

Lastly, add pr_info_ratelimited if underlying filesystem returns
-EINVAL because it was made to try O_DIRECT for IO that is not
DIO-aligned (shouldn't happen, so its best to be louder if it does).

Fixes: 3feec68563d ("nfs/localio: add direct IO enablement with sync and async IO support")
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
 fs/nfs/localio.c           | 65 ++++++++++++++++++++++++++++++++------
 fs/nfsd/localio.c          | 11 +++++++
 include/linux/nfslocalio.h |  2 ++
 3 files changed, 68 insertions(+), 10 deletions(-)

diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 42ea50d42c995..b165922e5cb65 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c

@@ -49,11 +49,6 @@ struct nfs_local_fsync_ctx {
 static bool localio_enabled __read_mostly = true;
 module_param(localio_enabled, bool, 0644);
 
-static bool localio_O_DIRECT_semantics __read_mostly = false;
-module_param(localio_O_DIRECT_semantics, bool, 0644);
-MODULE_PARM_DESC(localio_O_DIRECT_semantics,
-		 "LOCALIO will use O_DIRECT semantics to filesystem.");
-

 static inline bool nfs_client_is_local(const struct nfs_client *clp)
 {
 	return !!rcu_access_pointer(clp->cl_uuid.net);

@@ -322,12 +317,9 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
 		return NULL;
 	}
 
-	if (localio_O_DIRECT_semantics &&
-	    test_bit(NFS_IOHDR_ODIRECT, &hdr->flags)) {
-		iocb->kiocb.ki_filp = file;
+	init_sync_kiocb(&iocb->kiocb, file);
+	if (test_bit(NFS_IOHDR_ODIRECT, &hdr->flags))
 		iocb->kiocb.ki_flags = IOCB_DIRECT;
-	} else
-		init_sync_kiocb(&iocb->kiocb, file);
 
 	iocb->kiocb.ki_pos = hdr->args.offset;
 	iocb->hdr = hdr;

@@ -337,6 +329,30 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
 	return iocb;
 }
 
+static bool nfs_iov_iter_aligned_bvec(const struct iov_iter *i,
+		loff_t offset, unsigned int addr_mask, unsigned int len_mask)
+{
+	const struct bio_vec *bvec = i->bvec;
+	size_t skip = i->iov_offset;
+	size_t size = i->count;
+
+	if ((offset | size) & len_mask)
+		return false;
+	do {
+		size_t len = bvec->bv_len;
+
+		if (len > size)
+			len = size;
+		if ((unsigned long)(bvec->bv_offset + skip) & addr_mask)
+			return false;
+		bvec++;
+		size -= len;
+		skip = 0;
+	} while (size);
+
+	return true;
+}
+
 static void
 nfs_local_iter_init(struct iov_iter *i, struct nfs_local_kiocb *iocb, int dir)
 {

@@ -346,6 +362,25 @@ nfs_local_iter_init(struct iov_iter *i, struct nfs_local_kiocb *iocb, int dir)
 		      hdr->args.count + hdr->args.pgbase);
 	if (hdr->args.pgbase != 0)
 		iov_iter_advance(i, hdr->args.pgbase);
+
+	if (iocb->kiocb.ki_flags & IOCB_DIRECT) {
+		u32 nf_dio_mem_align, nf_dio_offset_align, nf_dio_read_offset_align;
+		/* Verify the IO is DIO-aligned as required */
+		nfs_to->nfsd_file_dio_alignment(iocb->localio, &nf_dio_mem_align,
+						&nf_dio_offset_align,
+						&nf_dio_read_offset_align);
+		if (dir == READ)
+			nf_dio_offset_align = nf_dio_read_offset_align;
+
+		if (nf_dio_mem_align && nf_dio_offset_align &&
+		    nfs_iov_iter_aligned_bvec(i, hdr->args.offset,
+					      nf_dio_mem_align - 1,
+					      nf_dio_offset_align - 1))
+			return; /* is DIO-aligned */
+
+		/* Fallback to using buffered for this misaligned IO */
+		iocb->kiocb.ki_flags &= ~IOCB_DIRECT;
+	}
 }
 
 static void

@@ -406,6 +441,11 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
 	struct nfs_pgio_header *hdr = iocb->hdr;
 	struct file *filp = iocb->kiocb.ki_filp;
 
+	if ((iocb->kiocb.ki_flags & IOCB_DIRECT) && status == -EINVAL) {
+		/* Underlying FS will return -EINVAL if misaligned DIO is attempted. */
+		pr_info_ratelimited("nfs: Unexpected direct I/O read alignment failure\n");

+	}
+
 	nfs_local_pgio_done(hdr, status);
 
 	/*

@@ -598,6 +638,11 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
 
 	dprintk("%s: wrote %ld bytes.\n", __func__, status > 0 ? status : 0);
 
+	if ((iocb->kiocb.ki_flags & IOCB_DIRECT) && status == -EINVAL) {
+		/* Underlying FS will return -EINVAL if misaligned DIO is attempted. */
+		pr_info_ratelimited("nfs: Unexpected direct I/O write alignment failure\n");
+	}
+
 	/* Handle short writes as if they are ENOSPC */
 	if (status > 0 && status < hdr->args.count) {
 		hdr->mds_offset += status;

diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
index 269fa9391dc46..be710d809a3ba 100644
--- a/fs/nfsd/localio.c
+++ b/fs/nfsd/localio.c

@@ -117,12 +117,23 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
 	return localio;
 }
 
+static void nfsd_file_dio_alignment(struct nfsd_file *nf,
+				    u32 *nf_dio_mem_align,
+				    u32 *nf_dio_offset_align,
+				    u32 *nf_dio_read_offset_align)
+{
+	*nf_dio_mem_align = nf->nf_dio_mem_align;
+	*nf_dio_offset_align = nf->nf_dio_offset_align;
+	*nf_dio_read_offset_align = nf->nf_dio_read_offset_align;
+}
+
 static const struct nfsd_localio_operations nfsd_localio_ops = {
 	.nfsd_net_try_get  = nfsd_net_try_get,
 	.nfsd_net_put  = nfsd_net_put,
 	.nfsd_open_local_fh = nfsd_open_local_fh,
 	.nfsd_file_put_local = nfsd_file_put_local,
 	.nfsd_file_file = nfsd_file_file,
+	.nfsd_file_dio_alignment = nfsd_file_dio_alignment,
 };
 
 void nfsd_localio_ops_init(void)

diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
index 59ea90bd136b6..3d91043254e64 100644
--- a/include/linux/nfslocalio.h
+++ b/include/linux/nfslocalio.h

@@ -64,6 +64,8 @@ struct nfsd_localio_operations {
 						const fmode_t);
 	struct net *(*nfsd_file_put_local)(struct nfsd_file __rcu **);
 	struct file *(*nfsd_file_file)(struct nfsd_file *);
+	void (*nfsd_file_dio_alignment)(struct nfsd_file *,
+					u32 *, u32 *, u32 *);
 } ____cacheline_aligned;
 
 extern void nfsd_localio_ops_init(void);