More NFS Client Bugfixes for Linux 6.18-rc

Bugfixes:
  * Various fixes when using NFS with TLS
  * Localio direct-IO fixes
  * Fix error handling in nfs_atomic_open_v23()
  * Fix sysfs memory leak when nfs_client kobject add fails
  * Fix an incorrect parameter when calling nfs4_call_sync()
  * Fix a failing LTP test when using delegated timestamps
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEnZ5MQTpR7cLU7KEp18tUv7ClQOsFAmkXmqIACgkQ18tUv7Cl
 QOsdlg/8CgomAZvepcW9e5H/bXi0x3Q4gUTcXWV49/oqwfnpVJ1C0Xanx1zdtY6P
 QhchYwHv1r989IEJWaeO4U/ppCei8LoOSq2dkb1TzWohZuUbIg44KnpPtcbkXTgy
 cDcGZu3PNLtvwodljDOtaF4ZVLaWl0MwTYnp0I4xQJc12InHUQ9TPPCSOBb262nN
 BeFPRguhQXZl1jUOv/F0SE/bEcoAnNX8MnbXMaIN3aHy2d9Vq5m4IpJCgyeXQwle
 KvEE6hAmJGm3rG+wpkz7x56KOn7k/K/Py772T7qzEADLcr4Qmusi1++ffnxikVIc
 F9EElTw5pgAvdTuKr+sVw+gktaYWu0LeTFbcIK9dwC5N+uksb7l/TcP9cmhA6lxE
 7KVVmYZGzPV8rwDIztoO8qPSePQTaJB8P3mQmZ8XVd1bz75BQ1zi4SSz578kl84E
 YMHVLHBHiR/chA1z1YSrh8fV8inOiijwrjXU3Oa/blaRhhaH1AvEFboMbn7FyW17
 GjmtL2rfC+hg+kWuvflJiK/zlVJOSNyZBNoD3iQaHq/D4vwXqVETETZnT8002kwL
 sWVFmHdv1Y0fF3K/VsB8QFVhW46K6urJlKU694bWVzo9aK2pX7oj+ElcyXqyFv/p
 Hq1sxe4KPlsVPoG/ClVvtH2a56vNRTOO0LySUN/ZAfUruLQeVv8=
 =7pf4
 -----END PGP SIGNATURE-----

Merge tag 'nfs-for-6.18-3' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client fixes from Anna Schumaker:

 - Various fixes when using NFS with TLS

 - Localio direct-IO fixes

 - Fix error handling in nfs_atomic_open_v23()

 - Fix sysfs memory leak when nfs_client kobject add fails

 - Fix an incorrect parameter when calling nfs4_call_sync()

 - Fix a failing LTP test when using delegated timestamps

* tag 'nfs-for-6.18-3' of git://git.linux-nfs.org/projects/anna/linux-nfs:
  NFS: Fix LTP test failures when timestamps are delegated
  NFSv4: Fix an incorrect parameter when calling nfs4_call_sync()
  NFS: sysfs: fix leak when nfs_client kobject add fails
  NFSv2/v3: Fix error handling in nfs_atomic_open_v23()
  nfs/localio: do not issue misaligned DIO out-of-order
  nfs/localio: Ensure DIO WRITE's IO on stable storage upon completion
  nfs/localio: backfill missing partial read support for misaligned DIO
  nfs/localio: add refcounting for each iocb IO associated with NFS pgio header
  nfs/localio: remove unecessary ENOTBLK handling in DIO WRITE support
  NFS: Check the TLS certificate fields in nfs_match_client()
  pnfs: Set transport security policy to RPC_XPRTSEC_NONE unless using TLS
  pnfs: Fix TLS logic in _nfs4_pnfs_v4_ds_connect()
  pnfs: Fix TLS logic in _nfs4_pnfs_v3_ds_connect()

fs/nfs/client.c

@@ -338,6 +338,14 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 		/* Match the xprt security policy */
 		if (clp->cl_xprtsec.policy != data->xprtsec.policy)
 			continue;
+		if (clp->cl_xprtsec.policy == RPC_XPRTSEC_TLS_X509) {
+			if (clp->cl_xprtsec.cert_serial !=
+			    data->xprtsec.cert_serial)
+				continue;
+			if (clp->cl_xprtsec.privkey_serial !=
+			    data->xprtsec.privkey_serial)
+				continue;
+		}
 
 		refcount_inc(&clp->cl_count);
 		return clp;

fs/nfs/dir.c

@@ -2268,11 +2268,12 @@ int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry,
 		return -ENAMETOOLONG;
 
 	if (open_flags & O_CREAT) {
-		file->f_mode |= FMODE_CREATED;
 		error = nfs_do_create(dir, dentry, mode, open_flags);
-		if (error)
+		if (!error) {
+			file->f_mode |= FMODE_CREATED;
+			return finish_open(file, dentry, NULL);
+		} else if (error != -EEXIST || open_flags & O_EXCL)
 			return error;
-		return finish_open(file, dentry, NULL);
 	}
 	if (d_in_lookup(dentry)) {
 		/* The only flags nfs_lookup considers are

fs/nfs/inode.c

@@ -718,6 +718,8 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	struct nfs_fattr *fattr;
 	loff_t oldsize = i_size_read(inode);
 	int error = 0;
+	kuid_t task_uid = current_fsuid();
+	kuid_t owner_uid = inode->i_uid;
 
 	nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
 
@@ -739,9 +741,11 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) {
 		spin_lock(&inode->i_lock);
 		if (attr->ia_valid & ATTR_MTIME_SET) {
-			nfs_set_timestamps_to_ts(inode, attr);
+			if (uid_eq(task_uid, owner_uid)) {
-			attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET|
+				nfs_set_timestamps_to_ts(inode, attr);
+				attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET|
 						ATTR_ATIME|ATTR_ATIME_SET);
+			}
 		} else {
 			nfs_update_timestamps(inode, attr->ia_valid);
 			attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME);
@@ -751,10 +755,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		   attr->ia_valid & ATTR_ATIME &&
 		   !(attr->ia_valid & ATTR_MTIME)) {
 		if (attr->ia_valid & ATTR_ATIME_SET) {
-			spin_lock(&inode->i_lock);
+			if (uid_eq(task_uid, owner_uid)) {
-			nfs_set_timestamps_to_ts(inode, attr);
+				spin_lock(&inode->i_lock);
-			spin_unlock(&inode->i_lock);
+				nfs_set_timestamps_to_ts(inode, attr);
-			attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET);
+				spin_unlock(&inode->i_lock);
+				attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET);
+			}
 		} else {
 			nfs_update_delegated_atime(inode);
 			attr->ia_valid &= ~ATTR_ATIME;

fs/nfs/localio.c

@@ -42,10 +42,9 @@ struct nfs_local_kiocb {
 	/* Begin mostly DIO-specific members */
 	size_t                  end_len;
 	short int		end_iter_index;
-	short int		n_iters;
+	atomic_t		n_iters;
 	bool			iter_is_dio_aligned[NFSLOCAL_MAX_IOS];
-	loff_t                  offset[NFSLOCAL_MAX_IOS] ____cacheline_aligned;
+	struct iov_iter		iters[NFSLOCAL_MAX_IOS] ____cacheline_aligned;
-	struct iov_iter		iters[NFSLOCAL_MAX_IOS];
 	/* End mostly DIO-specific members */
 };
 
@@ -314,7 +313,9 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
 	init_sync_kiocb(&iocb->kiocb, file);
 
 	iocb->hdr = hdr;
+	iocb->kiocb.ki_pos = hdr->args.offset;
 	iocb->kiocb.ki_flags &= ~IOCB_APPEND;
+	iocb->kiocb.ki_complete = NULL;
 	iocb->aio_complete_work = NULL;
 
 	iocb->end_iter_index = -1;
@@ -388,13 +389,24 @@ static bool nfs_iov_iter_aligned_bvec(const struct iov_iter *i,
 	return true;
 }
 
+static void
+nfs_local_iter_setup(struct iov_iter *iter, int rw, struct bio_vec *bvec,
+		     unsigned int nvecs, unsigned long total,
+		     size_t start, size_t len)
+{
+	iov_iter_bvec(iter, rw, bvec, nvecs, total);
+	if (start)
+		iov_iter_advance(iter, start);
+	iov_iter_truncate(iter, len);
+}
+
 /*
  * Setup as many as 3 iov_iter based on extents described by @local_dio.
  * Returns the number of iov_iter that were setup.
  */
 static int
 nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw,
-			  unsigned int nvecs, size_t len,
+			  unsigned int nvecs, unsigned long total,
 			  struct nfs_local_dio *local_dio)
 {
 	int n_iters = 0;
@@ -402,39 +414,17 @@ nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw,
 
 	/* Setup misaligned start? */
 	if (local_dio->start_len) {
-		iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len);
+		nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec,
-		iters[n_iters].count = local_dio->start_len;
+				     nvecs, total, 0, local_dio->start_len);
-		iocb->offset[n_iters] = iocb->hdr->args.offset;
-		iocb->iter_is_dio_aligned[n_iters] = false;
 		++n_iters;
 	}
 
-	/* Setup misaligned end?
+	/*
-	 * If so, the end is purposely setup to be issued using buffered IO
+	 * Setup DIO-aligned middle, if there is no misaligned end (below)
-	 * before the middle (which will use DIO, if DIO-aligned, with AIO).
+	 * then AIO completion is used, see nfs_local_call_{read,write}
-	 * This creates problems if/when the end results in a partial write.
-	 * So must save index and length of end to handle this corner case.
 	 */
-	if (local_dio->end_len) {
+	nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec, nvecs,
-		iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len);
+			     total, local_dio->start_len, local_dio->middle_len);
-		iocb->offset[n_iters] = local_dio->end_offset;
-		iov_iter_advance(&iters[n_iters],
-			local_dio->start_len + local_dio->middle_len);
-		iocb->iter_is_dio_aligned[n_iters] = false;
-		/* Save index and length of end */
-		iocb->end_iter_index = n_iters;
-		iocb->end_len = local_dio->end_len;
-		++n_iters;
-	}
-
-	/* Setup DIO-aligned middle to be issued last, to allow for
-	 * DIO with AIO completion (see nfs_local_call_{read,write}).
-	 */
-	iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len);
-	if (local_dio->start_len)
-		iov_iter_advance(&iters[n_iters], local_dio->start_len);
-	iters[n_iters].count -= local_dio->end_len;
-	iocb->offset[n_iters] = local_dio->middle_offset;
 
 	iocb->iter_is_dio_aligned[n_iters] =
 		nfs_iov_iter_aligned_bvec(&iters[n_iters],
@@ -442,12 +432,22 @@ nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw,
 
 	if (unlikely(!iocb->iter_is_dio_aligned[n_iters])) {
 		trace_nfs_local_dio_misaligned(iocb->hdr->inode,
-			iocb->hdr->args.offset, len, local_dio);
+			local_dio->start_len, local_dio->middle_len, local_dio);
 		return 0; /* no DIO-aligned IO possible */
 	}
+	iocb->end_iter_index = n_iters;
 	++n_iters;
 
-	iocb->n_iters = n_iters;
+	/* Setup misaligned end? */
+	if (local_dio->end_len) {
+		nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec,
+				     nvecs, total, local_dio->start_len +
+				     local_dio->middle_len, local_dio->end_len);
+		iocb->end_iter_index = n_iters;
+		++n_iters;
+	}
+
+	atomic_set(&iocb->n_iters, n_iters);
 	return n_iters;
 }
 
@@ -473,18 +473,26 @@ nfs_local_iters_init(struct nfs_local_kiocb *iocb, int rw)
 	}
 	len = hdr->args.count - total;
 
+	/*
+	 * For each iocb, iocb->n_iters is always at least 1 and we always
+	 * end io after first nfs_local_pgio_done call unless misaligned DIO.
+	 */
+	atomic_set(&iocb->n_iters, 1);
+
 	if (test_bit(NFS_IOHDR_ODIRECT, &hdr->flags)) {
 		struct nfs_local_dio local_dio;
 
 		if (nfs_is_local_dio_possible(iocb, rw, len, &local_dio) &&
-		    nfs_local_iters_setup_dio(iocb, rw, v, len, &local_dio) != 0)
+		    nfs_local_iters_setup_dio(iocb, rw, v, len, &local_dio) != 0) {
+			/* Ensure DIO WRITE's IO on stable storage upon completion */
+			if (rw == ITER_SOURCE)
+				iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC;
 			return; /* is DIO-aligned */
+		}
 	}
 
 	/* Use buffered IO */
-	iocb->offset[0] = hdr->args.offset;
 	iov_iter_bvec(&iocb->iters[0], rw, iocb->bvec, v, len);
-	iocb->n_iters = 1;
 }
 
 static void
@@ -504,9 +512,11 @@ nfs_local_pgio_init(struct nfs_pgio_header *hdr,
 		hdr->task.tk_start = ktime_get();
 }
 
-static void
+static bool
-nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status)
+nfs_local_pgio_done(struct nfs_local_kiocb *iocb, long status, bool force)
 {
+	struct nfs_pgio_header *hdr = iocb->hdr;
+
 	/* Must handle partial completions */
 	if (status >= 0) {
 		hdr->res.count += status;
@@ -517,6 +527,12 @@ nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status)
 		hdr->res.op_status = nfs_localio_errno_to_nfs4_stat(status);
 		hdr->task.tk_status = status;
 	}
+
+	if (force)
+		return true;
+
+	BUG_ON(atomic_read(&iocb->n_iters) <= 0);
+	return atomic_dec_and_test(&iocb->n_iters);
 }
 
 static void
@@ -547,11 +563,11 @@ static inline void nfs_local_pgio_aio_complete(struct nfs_local_kiocb *iocb)
 	queue_work(nfsiod_workqueue, &iocb->work);
 }
 
-static void
+static void nfs_local_read_done(struct nfs_local_kiocb *iocb)
-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;
+	long status = hdr->task.tk_status;
 
 	if ((iocb->kiocb.ki_flags & IOCB_DIRECT) && status == -EINVAL) {
 		/* Underlying FS will return -EINVAL if misaligned DIO is attempted. */
@@ -564,20 +580,27 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
 	 */
 	hdr->res.replen = 0;
 
-	if (hdr->res.count != hdr->args.count ||
+	/* nfs_readpage_result() handles short read */
-	    hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp)))
+
+	if (hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp)))
 		hdr->res.eof = true;
 
 	dprintk("%s: read %ld bytes eof %d.\n", __func__,
 			status > 0 ? status : 0, hdr->res.eof);
 }
 
+static inline void nfs_local_read_iocb_done(struct nfs_local_kiocb *iocb)
+{
+	nfs_local_read_done(iocb);
+	nfs_local_pgio_release(iocb);
+}
+
 static void nfs_local_read_aio_complete_work(struct work_struct *work)
 {
 	struct nfs_local_kiocb *iocb =
 		container_of(work, struct nfs_local_kiocb, work);
 
-	nfs_local_pgio_release(iocb);
+	nfs_local_read_iocb_done(iocb);
 }
 
 static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret)
@@ -585,8 +608,10 @@ static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret)
 	struct nfs_local_kiocb *iocb =
 		container_of(kiocb, struct nfs_local_kiocb, kiocb);
 
-	nfs_local_pgio_done(iocb->hdr, ret);
+	/* AIO completion of DIO read should always be last to complete */
-	nfs_local_read_done(iocb, ret);
+	if (unlikely(!nfs_local_pgio_done(iocb, ret, false)))
+		return;
+
 	nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_read_aio_complete_work */
 }
 
@@ -596,32 +621,36 @@ static void nfs_local_call_read(struct work_struct *work)
 		container_of(work, struct nfs_local_kiocb, work);
 	struct file *filp = iocb->kiocb.ki_filp;
 	const struct cred *save_cred;
+	bool force_done = false;
 	ssize_t status;
+	int n_iters;
 
 	save_cred = override_creds(filp->f_cred);
 
-	for (int i = 0; i < iocb->n_iters ; i++) {
+	n_iters = atomic_read(&iocb->n_iters);
+	for (int i = 0; i < n_iters ; i++) {
 		if (iocb->iter_is_dio_aligned[i]) {
 			iocb->kiocb.ki_flags |= IOCB_DIRECT;
-			iocb->kiocb.ki_complete = nfs_local_read_aio_complete;
+			/* Only use AIO completion if DIO-aligned segment is last */
-			iocb->aio_complete_work = nfs_local_read_aio_complete_work;
+			if (i == iocb->end_iter_index) {
-		}
+				iocb->kiocb.ki_complete = nfs_local_read_aio_complete;
+				iocb->aio_complete_work = nfs_local_read_aio_complete_work;
+			}
+		} else
+			iocb->kiocb.ki_flags &= ~IOCB_DIRECT;
 
-		iocb->kiocb.ki_pos = iocb->offset[i];
 		status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]);
 		if (status != -EIOCBQUEUED) {
-			nfs_local_pgio_done(iocb->hdr, status);
+			if (unlikely(status >= 0 && status < iocb->iters[i].count))
-			if (iocb->hdr->task.tk_status)
+				force_done = true; /* Partial read */
+			if (nfs_local_pgio_done(iocb, status, force_done)) {
+				nfs_local_read_iocb_done(iocb);
 				break;
+			}
 		}
 	}
 
 	revert_creds(save_cred);
-
-	if (status != -EIOCBQUEUED) {
-		nfs_local_read_done(iocb, status);
-		nfs_local_pgio_release(iocb);
-	}
 }
 
 static int
@@ -736,11 +765,10 @@ static void nfs_local_vfs_getattr(struct nfs_local_kiocb *iocb)
 	fattr->du.nfs3.used = stat.blocks << 9;
 }
 
-static void
+static void nfs_local_write_done(struct nfs_local_kiocb *iocb)
-nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
 {
 	struct nfs_pgio_header *hdr = iocb->hdr;
-	struct inode *inode = hdr->inode;
+	long status = hdr->task.tk_status;
 
 	dprintk("%s: wrote %ld bytes.\n", __func__, status > 0 ? status : 0);
 
@@ -759,10 +787,17 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
 		nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset);
 		status = -ENOSPC;
 		/* record -ENOSPC in terms of nfs_local_pgio_done */
-		nfs_local_pgio_done(hdr, status);
+		(void) nfs_local_pgio_done(iocb, status, true);
 	}
 	if (hdr->task.tk_status < 0)
-		nfs_reset_boot_verifier(inode);
+		nfs_reset_boot_verifier(hdr->inode);
+}
+
+static inline void nfs_local_write_iocb_done(struct nfs_local_kiocb *iocb)
+{
+	nfs_local_write_done(iocb);
+	nfs_local_vfs_getattr(iocb);
+	nfs_local_pgio_release(iocb);
 }
 
 static void nfs_local_write_aio_complete_work(struct work_struct *work)
@@ -770,8 +805,7 @@ static void nfs_local_write_aio_complete_work(struct work_struct *work)
 	struct nfs_local_kiocb *iocb =
 		container_of(work, struct nfs_local_kiocb, work);
 
-	nfs_local_vfs_getattr(iocb);
+	nfs_local_write_iocb_done(iocb);
-	nfs_local_pgio_release(iocb);
 }
 
 static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret)
@@ -779,8 +813,10 @@ static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret)
 	struct nfs_local_kiocb *iocb =
 		container_of(kiocb, struct nfs_local_kiocb, kiocb);
 
-	nfs_local_pgio_done(iocb->hdr, ret);
+	/* AIO completion of DIO write should always be last to complete */
-	nfs_local_write_done(iocb, ret);
+	if (unlikely(!nfs_local_pgio_done(iocb, ret, false)))
+		return;
+
 	nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_write_aio_complete_work */
 }
 
@@ -791,63 +827,40 @@ static void nfs_local_call_write(struct work_struct *work)
 	struct file *filp = iocb->kiocb.ki_filp;
 	unsigned long old_flags = current->flags;
 	const struct cred *save_cred;
+	bool force_done = false;
 	ssize_t status;
+	int n_iters;
 
 	current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO;
 	save_cred = override_creds(filp->f_cred);
 
 	file_start_write(filp);
-	for (int i = 0; i < iocb->n_iters ; i++) {
+	n_iters = atomic_read(&iocb->n_iters);
+	for (int i = 0; i < n_iters ; i++) {
 		if (iocb->iter_is_dio_aligned[i]) {
 			iocb->kiocb.ki_flags |= IOCB_DIRECT;
-			iocb->kiocb.ki_complete = nfs_local_write_aio_complete;
+			/* Only use AIO completion if DIO-aligned segment is last */
-			iocb->aio_complete_work = nfs_local_write_aio_complete_work;
+			if (i == iocb->end_iter_index) {
-		}
+				iocb->kiocb.ki_complete = nfs_local_write_aio_complete;
-retry:
+				iocb->aio_complete_work = nfs_local_write_aio_complete_work;
-		iocb->kiocb.ki_pos = iocb->offset[i];
+			}
+		} else
+			iocb->kiocb.ki_flags &= ~IOCB_DIRECT;
+
 		status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]);
 		if (status != -EIOCBQUEUED) {
-			if (unlikely(status >= 0 && status < iocb->iters[i].count)) {
+			if (unlikely(status >= 0 && status < iocb->iters[i].count))
-				/* partial write */
+				force_done = true; /* Partial write */
-				if (i == iocb->end_iter_index) {
+			if (nfs_local_pgio_done(iocb, status, force_done)) {
-					/* Must not account partial end, otherwise, due
+				nfs_local_write_iocb_done(iocb);
-					 * to end being issued before middle: the partial
-					 * write accounting in nfs_local_write_done()
-					 * would incorrectly advance hdr->args.offset
-					 */
-					status = 0;
-				} else {
-					/* Partial write at start or buffered middle,
-					 * exit early.
-					 */
-					nfs_local_pgio_done(iocb->hdr, status);
-					break;
-				}
-			} else if (unlikely(status == -ENOTBLK &&
-					    (iocb->kiocb.ki_flags & IOCB_DIRECT))) {
-				/* VFS will return -ENOTBLK if DIO WRITE fails to
-				 * invalidate the page cache. Retry using buffered IO.
-				 */
-				iocb->kiocb.ki_flags &= ~IOCB_DIRECT;
-				iocb->kiocb.ki_complete = NULL;
-				iocb->aio_complete_work = NULL;
-				goto retry;
-			}
-			nfs_local_pgio_done(iocb->hdr, status);
-			if (iocb->hdr->task.tk_status)
 				break;
+			}
 		}
 	}
 	file_end_write(filp);
 
 	revert_creds(save_cred);
 	current->flags = old_flags;
-
-	if (status != -EIOCBQUEUED) {
-		nfs_local_write_done(iocb, status);
-		nfs_local_vfs_getattr(iocb);
-		nfs_local_pgio_release(iocb);
-	}
 }
 
 static int

fs/nfs/nfs3client.c

@@ -2,6 +2,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
 #include <linux/sunrpc/addr.h>
+#include <net/handshake.h>
 #include "internal.h"
 #include "nfs3_fs.h"
 #include "netns.h"
@@ -98,7 +99,11 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 		.net = mds_clp->cl_net,
 		.timeparms = &ds_timeout,
 		.cred = mds_srv->cred,
-		.xprtsec = mds_clp->cl_xprtsec,
+		.xprtsec = {
+			.policy = RPC_XPRTSEC_NONE,
+			.cert_serial = TLS_NO_CERT,
+			.privkey_serial = TLS_NO_PRIVKEY,
+		},
 		.connect_timeout = connect_timeout,
 		.reconnect_timeout = connect_timeout,
 	};
@@ -111,9 +116,14 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 	cl_init.hostname = buf;
 
 	switch (ds_proto) {
+	case XPRT_TRANSPORT_TCP_TLS:
+		if (mds_clp->cl_xprtsec.policy != RPC_XPRTSEC_NONE)
+			cl_init.xprtsec = mds_clp->cl_xprtsec;
+		else
+			ds_proto = XPRT_TRANSPORT_TCP;
+		fallthrough;
 	case XPRT_TRANSPORT_RDMA:
 	case XPRT_TRANSPORT_TCP:
-	case XPRT_TRANSPORT_TCP_TLS:
 		if (mds_clp->cl_nconnect > 1)
 			cl_init.nconnect = mds_clp->cl_nconnect;
 	}

fs/nfs/nfs4client.c

@@ -11,6 +11,7 @@
 #include <linux/sunrpc/xprt.h>
 #include <linux/sunrpc/bc_xprt.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
+#include <net/handshake.h>
 #include "internal.h"
 #include "callback.h"
 #include "delegation.h"
@@ -983,7 +984,11 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 		.net = mds_clp->cl_net,
 		.timeparms = &ds_timeout,
 		.cred = mds_srv->cred,
-		.xprtsec = mds_srv->nfs_client->cl_xprtsec,
+		.xprtsec = {
+			.policy = RPC_XPRTSEC_NONE,
+			.cert_serial = TLS_NO_CERT,
+			.privkey_serial = TLS_NO_PRIVKEY,
+		},
 	};
 	char buf[INET6_ADDRSTRLEN + 1];
 
@@ -992,9 +997,14 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 	cl_init.hostname = buf;
 
 	switch (ds_proto) {
+	case XPRT_TRANSPORT_TCP_TLS:
+		if (mds_srv->nfs_client->cl_xprtsec.policy != RPC_XPRTSEC_NONE)
+			cl_init.xprtsec = mds_srv->nfs_client->cl_xprtsec;
+		else
+			ds_proto = XPRT_TRANSPORT_TCP;
+		fallthrough;
 	case XPRT_TRANSPORT_RDMA:
 	case XPRT_TRANSPORT_TCP:
-	case XPRT_TRANSPORT_TCP_TLS:
 		if (mds_clp->cl_nconnect > 1) {
 			cl_init.nconnect = mds_clp->cl_nconnect;
 			cl_init.max_connect = NFS_MAX_TRANSPORTS;

fs/nfs/nfs4proc.c

@@ -4715,16 +4715,19 @@ static int _nfs4_proc_lookupp(struct inode *inode,
 	};
 	unsigned short task_flags = 0;
 
-	if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL)
+	if (server->flags & NFS_MOUNT_SOFTREVAL)
 		task_flags |= RPC_TASK_TIMEOUT;
+	if (server->caps & NFS_CAP_MOVEABLE)
+		task_flags |= RPC_TASK_MOVEABLE;
 
 	args.bitmask = nfs4_bitmask(server, fattr->label);
 
 	nfs_fattr_init(fattr);
+	nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0);
 
 	dprintk("NFS call  lookupp ino=0x%lx\n", inode->i_ino);
-	status = nfs4_call_sync(clnt, server, &msg, &args.seq_args,
+	status = nfs4_do_call_sync(clnt, server, &msg, &args.seq_args,
-				&res.seq_res, task_flags);
+				   &res.seq_res, task_flags);
 	dprintk("NFS reply lookupp: %d\n", status);
 	return status;
 }

fs/nfs/pnfs_nfs.c

@@ -809,8 +809,11 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 				 unsigned int retrans)
 {
 	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs_client *mds_clp = mds_srv->nfs_client;
+	enum xprtsec_policies xprtsec_policy = mds_clp->cl_xprtsec.policy;
 	struct nfs4_pnfs_ds_addr *da;
 	unsigned long connect_timeout = timeo * (retrans + 1) * HZ / 10;
+	int ds_proto;
 	int status = 0;
 
 	dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr);
@@ -834,27 +837,28 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 				.xprtsec = clp->cl_xprtsec,
 			};
 
-			if (da->da_transport != clp->cl_proto &&
+			if (xprt_args.ident == XPRT_TRANSPORT_TCP &&
-			    clp->cl_proto != XPRT_TRANSPORT_TCP_TLS)
+			    clp->cl_proto == XPRT_TRANSPORT_TCP_TLS)
-				continue;
-			if (da->da_transport == XPRT_TRANSPORT_TCP &&
-			    mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS)
 				xprt_args.ident = XPRT_TRANSPORT_TCP_TLS;
 
-			if (da->da_addr.ss_family != clp->cl_addr.ss_family)
+			if (xprt_args.ident != clp->cl_proto)
+				continue;
+			if (xprt_args.dstaddr->sa_family !=
+			    clp->cl_addr.ss_family)
 				continue;
 			/* Add this address as an alias */
 			rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
-					rpc_clnt_test_and_add_xprt, NULL);
+					  rpc_clnt_test_and_add_xprt, NULL);
 			continue;
 		}
-		if (da->da_transport == XPRT_TRANSPORT_TCP &&
+
-		    mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS)
+		ds_proto = da->da_transport;
-			da->da_transport = XPRT_TRANSPORT_TCP_TLS;
+		if (ds_proto == XPRT_TRANSPORT_TCP &&
-		clp = get_v3_ds_connect(mds_srv,
+		    xprtsec_policy != RPC_XPRTSEC_NONE)
-				&da->da_addr,
+			ds_proto = XPRT_TRANSPORT_TCP_TLS;
-				da->da_addrlen, da->da_transport,
+
-				timeo, retrans);
+		clp = get_v3_ds_connect(mds_srv, &da->da_addr, da->da_addrlen,
+					ds_proto, timeo, retrans);
 		if (IS_ERR(clp))
 			continue;
 		clp->cl_rpcclient->cl_softerr = 0;
@@ -880,7 +884,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 				 u32 minor_version)
 {
 	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs_client *mds_clp = mds_srv->nfs_client;
+	enum xprtsec_policies xprtsec_policy = mds_clp->cl_xprtsec.policy;
 	struct nfs4_pnfs_ds_addr *da;
+	int ds_proto;
 	int status = 0;
 
 	dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr);
@@ -908,12 +915,8 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 				.data = &xprtdata,
 			};
 
-			if (da->da_transport != clp->cl_proto &&
+			if (xprt_args.ident == XPRT_TRANSPORT_TCP &&
-					clp->cl_proto != XPRT_TRANSPORT_TCP_TLS)
+			    clp->cl_proto == XPRT_TRANSPORT_TCP_TLS) {
-				continue;
-			if (da->da_transport == XPRT_TRANSPORT_TCP &&
-				mds_srv->nfs_client->cl_proto ==
-					XPRT_TRANSPORT_TCP_TLS) {
 				struct sockaddr *addr =
 					(struct sockaddr *)&da->da_addr;
 				struct sockaddr_in *sin =
@@ -944,7 +947,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 				xprt_args.ident = XPRT_TRANSPORT_TCP_TLS;
 				xprt_args.servername = servername;
 			}
-			if (da->da_addr.ss_family != clp->cl_addr.ss_family)
+			if (xprt_args.ident != clp->cl_proto)
+				continue;
+			if (xprt_args.dstaddr->sa_family !=
+			    clp->cl_addr.ss_family)
 				continue;
 
 			/**
@@ -958,15 +964,14 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 			if (xprtdata.cred)
 				put_cred(xprtdata.cred);
 		} else {
-			if (da->da_transport == XPRT_TRANSPORT_TCP &&
+			ds_proto = da->da_transport;
-				mds_srv->nfs_client->cl_proto ==
+			if (ds_proto == XPRT_TRANSPORT_TCP &&
-					XPRT_TRANSPORT_TCP_TLS)
+			    xprtsec_policy != RPC_XPRTSEC_NONE)
-				da->da_transport = XPRT_TRANSPORT_TCP_TLS;
+				ds_proto = XPRT_TRANSPORT_TCP_TLS;
-			clp = nfs4_set_ds_client(mds_srv,
+
-						&da->da_addr,
+			clp = nfs4_set_ds_client(mds_srv, &da->da_addr,
-						da->da_addrlen,
+						 da->da_addrlen, ds_proto,
-						da->da_transport, timeo,
+						 timeo, retrans, minor_version);
-						retrans, minor_version);
 			if (IS_ERR(clp))
 				continue;
 
@@ -977,7 +982,6 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 				clp = ERR_PTR(-EIO);
 				continue;
 			}
-
 		}
 	}
 

fs/nfs/sysfs.c

@@ -189,6 +189,7 @@ static struct nfs_netns_client *nfs_netns_client_alloc(struct kobject *parent,
 			return p;
 
 		kobject_put(&p->kobject);
+		kobject_put(&p->nfs_net_kobj);
 	}
 	return NULL;
 }