Merge tag 'nfsd-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "We introduce 'courteous server' in this release. Previously NFSD would
  purge open and lock state for an unresponsive client after one lease
  period (typically 90 seconds). Now, after one lease period, another
  client can open and lock those files and the unresponsive client's
  lease is purged; otherwise if the unresponsive client's open and lock
  state is uncontended, the server retains that open and lock state for
  up to 24 hours, allowing the client's workload to resume after a
  lengthy network partition.

  A longstanding issue with NFSv4 file creation is also addressed.
  Previously a file creation can fail internally, returning an error to
  the client, but leave the newly created file in place as an artifact.
  The file creation code path has been reorganized so that internal
  failures and race conditions are less likely to result in an unwanted
  file creation.

  A fault injector has been added to help exercise paths that are run
  during kernel metadata cache invalidation. These caches contain
  information maintained by user space about exported filesystems. Many
  of our test workloads do not trigger cache invalidation.

  There is one patch that is needed to support PREEMPT_RT and a fix for
  an ancient 'sleep while spin-locked' splat that seems to have become
  easier to hit since v5.18-rc3"

* tag 'nfsd-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (36 commits)
  NFSD: nfsd_file_put() can sleep
  NFSD: Add documenting comment for nfsd4_release_lockowner()
  NFSD: Modernize nfsd4_release_lockowner()
  NFSD: Fix possible sleep during nfsd4_release_lockowner()
  nfsd: destroy percpu stats counters after reply cache shutdown
  nfsd: Fix null-ptr-deref in nfsd_fill_super()
  nfsd: Unregister the cld notifier when laundry_wq create failed
  SUNRPC: Use RMW bitops in single-threaded hot paths
  NFSD: Clean up the show_nf_flags() macro
  NFSD: Trace filecache opens
  NFSD: Move documenting comment for nfsd4_process_open2()
  NFSD: Fix whitespace
  NFSD: Remove dprintk call sites from tail of nfsd4_open()
  NFSD: Instantiate a struct file when creating a regular NFSv4 file
  NFSD: Clean up nfsd_open_verified()
  NFSD: Remove do_nfsd_create()
  NFSD: Refactor NFSv4 OPEN(CREATE)
  NFSD: Refactor NFSv3 CREATE
  NFSD: Refactor nfsd_create_setattr()
  NFSD: Avoid calling fh_drop_write() twice in do_nfsd_create()
  ...

16 files changed, 910 insertions, 371 deletions

diff --git a/fs/locks.c b/fs/locks.c
index 8c6df10cd9ed..ca28e0e50e56 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -300,6 +300,34 @@ void locks_release_private(struct file_lock *fl)
 }
 EXPORT_SYMBOL_GPL(locks_release_private);
 
+/**
+ * locks_owner_has_blockers - Check for blocking lock requests
+ * @flctx: file lock context
+ * @owner: lock owner
+ *
+ * Return values:
+ *   %true: @owner has at least one blocker
+ *   %false: @owner has no blockers
+ */
+bool locks_owner_has_blockers(struct file_lock_context *flctx,
+		fl_owner_t owner)
+{
+	struct file_lock *fl;
+
+	spin_lock(&flctx->flc_lock);
+	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+		if (fl->fl_owner != owner)
+			continue;
+		if (!list_empty(&fl->fl_blocked_requests)) {
+			spin_unlock(&flctx->flc_lock);
+			return true;
+		}
+	}
+	spin_unlock(&flctx->flc_lock);
+	return false;
+}
+EXPORT_SYMBOL_GPL(locks_owner_has_blockers);
+
 /* Free a lock which is not in use. */
 void locks_free_lock(struct file_lock *fl)
 {
@@ -874,6 +902,8 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 	struct file_lock *cfl;
 	struct file_lock_context *ctx;
 	struct inode *inode = locks_inode(filp);
+	void *owner;
+	void (*func)(void);
 
 	ctx = smp_load_acquire(&inode->i_flctx);
 	if (!ctx || list_empty_careful(&ctx->flc_posix)) {
@@ -881,12 +911,23 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 		return;
 	}
 
+retry:
 	spin_lock(&ctx->flc_lock);
 	list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
-		if (posix_locks_conflict(fl, cfl)) {
-			locks_copy_conflock(fl, cfl);
-			goto out;
+		if (!posix_locks_conflict(fl, cfl))
+			continue;
+		if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable
+			&& (*cfl->fl_lmops->lm_lock_expirable)(cfl)) {
+			owner = cfl->fl_lmops->lm_mod_owner;
+			func = cfl->fl_lmops->lm_expire_lock;
+			__module_get(owner);
+			spin_unlock(&ctx->flc_lock);
+			(*func)();
+			module_put(owner);
+			goto retry;
 		}
+		locks_copy_conflock(fl, cfl);
+		goto out;
 	}
 	fl->fl_type = F_UNLCK;
 out:
@@ -1060,6 +1101,8 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 	int error;
 	bool added = false;
 	LIST_HEAD(dispose);
+	void *owner;
+	void (*func)(void);
 
 	ctx = locks_get_lock_context(inode, request->fl_type);
 	if (!ctx)
@@ -1078,6 +1121,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 		new_fl2 = locks_alloc_lock();
 	}
 
+retry:
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	/*
@@ -1089,6 +1133,17 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 		list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
 			if (!posix_locks_conflict(request, fl))
 				continue;
+			if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable
+				&& (*fl->fl_lmops->lm_lock_expirable)(fl)) {
+				owner = fl->fl_lmops->lm_mod_owner;
+				func = fl->fl_lmops->lm_expire_lock;
+				__module_get(owner);
+				spin_unlock(&ctx->flc_lock);
+				percpu_up_read(&file_rwsem);
+				(*func)();
+				module_put(owner);
+				goto retry;
+			}
 			if (conflock)
 				locks_copy_conflock(conflock, fl);
 			error = -EAGAIN;
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 489c9c1d8f31..f172412447f5 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -303,6 +303,8 @@ nfsd_file_put_noref(struct nfsd_file *nf)
 void
 nfsd_file_put(struct nfsd_file *nf)
 {
+	might_sleep();
+
 	set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
 	if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) {
 		nfsd_file_flush(nf);
@@ -899,9 +901,9 @@ nfsd_file_is_cached(struct inode *inode)
 	return ret;
 }
 
-__be32
-nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
-		  unsigned int may_flags, struct nfsd_file **pnf)
+static __be32
+nfsd_do_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		     unsigned int may_flags, struct nfsd_file **pnf, bool open)
 {
 	__be32	status;
 	struct net *net = SVC_NET(rqstp);
@@ -996,10 +998,14 @@ open_file:
 		nfsd_file_gc();
 
 	nf->nf_mark = nfsd_file_mark_find_or_create(nf);
-	if (nf->nf_mark)
-		status = nfsd_open_verified(rqstp, fhp, S_IFREG,
-				may_flags, &nf->nf_file);
-	else
+	if (nf->nf_mark) {
+		if (open) {
+			status = nfsd_open_verified(rqstp, fhp, may_flags,
+						    &nf->nf_file);
+			trace_nfsd_file_open(nf, status);
+		} else
+			status = nfs_ok;
+	} else
 		status = nfserr_jukebox;
 	/*
 	 * If construction failed, or we raced with a call to unlink()
@@ -1019,6 +1025,40 @@ open_file:
 	goto out;
 }
 
+/**
+ * nfsd_file_acquire - Get a struct nfsd_file with an open file
+ * @rqstp: the RPC transaction being executed
+ * @fhp: the NFS filehandle of the file to be opened
+ * @may_flags: NFSD_MAY_ settings for the file
+ * @pnf: OUT: new or found "struct nfsd_file" object
+ *
+ * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
+ * network byte order is returned.
+ */
+__be32
+nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  unsigned int may_flags, struct nfsd_file **pnf)
+{
+	return nfsd_do_file_acquire(rqstp, fhp, may_flags, pnf, true);
+}
+
+/**
+ * nfsd_file_create - Get a struct nfsd_file, do not open
+ * @rqstp: the RPC transaction being executed
+ * @fhp: the NFS filehandle of the file just created
+ * @may_flags: NFSD_MAY_ settings for the file
+ * @pnf: OUT: new or found "struct nfsd_file" object
+ *
+ * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
+ * network byte order is returned.
+ */
+__be32
+nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		 unsigned int may_flags, struct nfsd_file **pnf)
+{
+	return nfsd_do_file_acquire(rqstp, fhp, may_flags, pnf, false);
+}
+
 /*
  * Note that fields may be added, removed or reordered in the future. Programs
  * scraping this file for info should test the labels to ensure they're
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 435ceab27897..1da0c79a5580 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -59,5 +59,7 @@ void nfsd_file_close_inode_sync(struct inode *inode);
 bool nfsd_file_is_cached(struct inode *inode);
 __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct nfsd_file **nfp);
+__be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  unsigned int may_flags, struct nfsd_file **nfp);
 int	nfsd_file_cache_stats_open(struct inode *, struct file *);
 #endif /* _FS_NFSD_FILECACHE_H */
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 936eebd4c56d..981a3a7a6e16 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -8,6 +8,7 @@
 #include <linux/fs.h>
 #include <linux/ext2_fs.h>
 #include <linux/magic.h>
+#include <linux/namei.h>
 
 #include "cache.h"
 #include "xdr3.h"
@@ -220,17 +221,132 @@ nfsd3_proc_write(struct svc_rqst *rqstp)
 }
 
 /*
- * With NFSv3, CREATE processing is a lot easier than with NFSv2.
- * At least in theory; we'll see how it fares in practice when the
- * first reports about SunOS compatibility problems start to pour in...
+ * Implement NFSv3's unchecked, guarded, and exclusive CREATE
+ * semantics for regular files. Except for the created file,
+ * this operation is stateless on the server.
+ *
+ * Upon return, caller must release @fhp and @resfhp.
  */
 static __be32
+nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  struct svc_fh *resfhp, struct nfsd3_createargs *argp)
+{
+	struct iattr *iap = &argp->attrs;
+	struct dentry *parent, *child;
+	__u32 v_mtime, v_atime;
+	struct inode *inode;
+	__be32 status;
+	int host_err;
+
+	if (isdotent(argp->name, argp->len))
+		return nfserr_exist;
+	if (!(iap->ia_valid & ATTR_MODE))
+		iap->ia_mode = 0;
+
+	status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
+	if (status != nfs_ok)
+		return status;
+
+	parent = fhp->fh_dentry;
+	inode = d_inode(parent);
+
+	host_err = fh_want_write(fhp);
+	if (host_err)
+		return nfserrno(host_err);
+
+	fh_lock_nested(fhp, I_MUTEX_PARENT);
+
+	child = lookup_one_len(argp->name, parent, argp->len);
+	if (IS_ERR(child)) {
+		status = nfserrno(PTR_ERR(child));
+		goto out;
+	}
+
+	if (d_really_is_negative(child)) {
+		status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
+		if (status != nfs_ok)
+			goto out;
+	}
+
+	status = fh_compose(resfhp, fhp->fh_export, child, fhp);
+	if (status != nfs_ok)
+		goto out;
+
+	v_mtime = 0;
+	v_atime = 0;
+	if (argp->createmode == NFS3_CREATE_EXCLUSIVE) {
+		u32 *verifier = (u32 *)argp->verf;
+
+		/*
+		 * Solaris 7 gets confused (bugid 4218508) if these have
+		 * the high bit set, as do xfs filesystems without the
+		 * "bigtime" feature. So just clear the high bits.
+		 */
+		v_mtime = verifier[0] & 0x7fffffff;
+		v_atime = verifier[1] & 0x7fffffff;
+	}
+
+	if (d_really_is_positive(child)) {
+		status = nfs_ok;
+
+		switch (argp->createmode) {
+		case NFS3_CREATE_UNCHECKED:
+			if (!d_is_reg(child))
+				break;
+			iap->ia_valid &= ATTR_SIZE;
+			goto set_attr;
+		case NFS3_CREATE_GUARDED:
+			status = nfserr_exist;
+			break;
+		case NFS3_CREATE_EXCLUSIVE:
+			if (d_inode(child)->i_mtime.tv_sec == v_mtime &&
+			    d_inode(child)->i_atime.tv_sec == v_atime &&
+			    d_inode(child)->i_size == 0) {
+				break;
+			}
+			status = nfserr_exist;
+		}
+		goto out;
+	}
+
+	if (!IS_POSIXACL(inode))
+		iap->ia_mode &= ~current_umask();
+
+	host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true);
+	if (host_err < 0) {
+		status = nfserrno(host_err);
+		goto out;
+	}
+
+	/* A newly created file already has a file size of zero. */
+	if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0))
+		iap->ia_valid &= ~ATTR_SIZE;
+	if (argp->createmode == NFS3_CREATE_EXCLUSIVE) {
+		iap->ia_valid = ATTR_MTIME | ATTR_ATIME |
+				ATTR_MTIME_SET | ATTR_ATIME_SET;
+		iap->ia_mtime.tv_sec = v_mtime;
+		iap->ia_atime.tv_sec = v_atime;
+		iap->ia_mtime.tv_nsec = 0;
+		iap->ia_atime.tv_nsec = 0;
+	}
+
+set_attr:
+	status = nfsd_create_setattr(rqstp, fhp, resfhp, iap);
+
+out:
+	fh_unlock(fhp);
+	if (child && !IS_ERR(child))
+		dput(child);
+	fh_drop_write(fhp);
+	return status;
+}
+
+static __be32
 nfsd3_proc_create(struct svc_rqst *rqstp)
 {
 	struct nfsd3_createargs *argp = rqstp->rq_argp;
 	struct nfsd3_diropres *resp = rqstp->rq_resp;
-	svc_fh		*dirfhp, *newfhp = NULL;
-	struct iattr	*attr;
+	svc_fh *dirfhp, *newfhp;
 
 	dprintk("nfsd: CREATE(3)   %s %.*s\n",
 				SVCFH_fmt(&argp->fh),
@@ -239,21 +355,8 @@ nfsd3_proc_create(struct svc_rqst *rqstp)
 
 	dirfhp = fh_copy(&resp->dirfh, &argp->fh);
 	newfhp = fh_init(&resp->fh, NFS3_FHSIZE);
-	attr   = &argp->attrs;
-
-	/* Unfudge the mode bits */
-	attr->ia_mode &= ~S_IFMT;
-	if (!(attr->ia_valid & ATTR_MODE)) { 
-		attr->ia_valid |= ATTR_MODE;
-		attr->ia_mode = S_IFREG;
-	} else {
-		attr->ia_mode = (attr->ia_mode & ~S_IFMT) | S_IFREG;
-	}
 
-	/* Now create the file and set attributes */
-	resp->status = do_nfsd_create(rqstp, dirfhp, argp->name, argp->len,
-				      attr, newfhp, argp->createmode,
-				      (u32 *)argp->verf, NULL, NULL);
+	resp->status = nfsd3_create_file(rqstp, dirfhp, newfhp, argp);
 	return rpc_success;
 }
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index b207c76a873f..3895eb52d2b1 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -37,6 +37,8 @@
 #include <linux/falloc.h>
 #include <linux/slab.h>
 #include <linux/kthread.h>
+#include <linux/namei.h>
+
 #include <linux/sunrpc/addr.h>
 #include <linux/nfs_ssc.h>
 
@@ -235,6 +237,183 @@ static void nfsd4_set_open_owner_reply_cache(struct nfsd4_compound_state *cstate
 			&resfh->fh_handle);
 }
 
+static inline bool nfsd4_create_is_exclusive(int createmode)
+{
+	return createmode == NFS4_CREATE_EXCLUSIVE ||
+		createmode == NFS4_CREATE_EXCLUSIVE4_1;
+}
+
+static __be32
+nfsd4_vfs_create(struct svc_fh *fhp, struct dentry *child,
+		 struct nfsd4_open *open)
+{
+	struct file *filp;
+	struct path path;
+	int oflags;
+
+	oflags = O_CREAT | O_LARGEFILE;
+	switch (open->op_share_access & NFS4_SHARE_ACCESS_BOTH) {
+	case NFS4_SHARE_ACCESS_WRITE:
+		oflags |= O_WRONLY;
+		break;
+	case NFS4_SHARE_ACCESS_BOTH:
+		oflags |= O_RDWR;
+		break;
+	default:
+		oflags |= O_RDONLY;
+	}
+
+	path.mnt = fhp->fh_export->ex_path.mnt;
+	path.dentry = child;
+	filp = dentry_create(&path, oflags, open->op_iattr.ia_mode,
+			     current_cred());
+	if (IS_ERR(filp))
+		return nfserrno(PTR_ERR(filp));
+
+	open->op_filp = filp;
+	return nfs_ok;
+}
+
+/*
+ * Implement NFSv4's unchecked, guarded, and exclusive create
+ * semantics for regular files. Open state for this new file is
+ * subsequently fabricated in nfsd4_process_open2().
+ *
+ * Upon return, caller must release @fhp and @resfhp.
+ */
+static __be32
+nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  struct svc_fh *resfhp, struct nfsd4_open *open)
+{
+	struct iattr *iap = &open->op_iattr;
+	struct dentry *parent, *child;
+	__u32 v_mtime, v_atime;
+	struct inode *inode;
+	__be32 status;
+	int host_err;
+
+	if (isdotent(open->op_fname, open->op_fnamelen))
+		return nfserr_exist;
+	if (!(iap->ia_valid & ATTR_MODE))
+		iap->ia_mode = 0;
+
+	status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
+	if (status != nfs_ok)
+		return status;
+	parent = fhp->fh_dentry;
+	inode = d_inode(parent);
+
+	host_err = fh_want_write(fhp);
+	if (host_err)
+		return nfserrno(host_err);
+
+	fh_lock_nested(fhp, I_MUTEX_PARENT);
+
+	child = lookup_one_len(open->op_fname, parent, open->op_fnamelen);
+	if (IS_ERR(child)) {
+		status = nfserrno(PTR_ERR(child));
+		goto out;
+	}
+
+	if (d_really_is_negative(child)) {
+		status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
+		if (status != nfs_ok)
+			goto out;
+	}
+
+	status = fh_compose(resfhp, fhp->fh_export, child, fhp);
+	if (status != nfs_ok)
+		goto out;
+
+	v_mtime = 0;
+	v_atime = 0;
+	if (nfsd4_create_is_exclusive(open->op_createmode)) {
+		u32 *verifier = (u32 *)open->op_verf.data;
+
+		/*
+		 * Solaris 7 gets confused (bugid 4218508) if these have
+		 * the high bit set, as do xfs filesystems without the
+		 * "bigtime" feature. So just clear the high bits. If this
+		 * is ever changed to use different attrs for storing the
+		 * verifier, then do_open_lookup() will also need to be
+		 * fixed accordingly.
+		 */
+		v_mtime = verifier[0] & 0x7fffffff;
+		v_atime = verifier[1] & 0x7fffffff;
+	}
+
+	if (d_really_is_positive(child)) {
+		status = nfs_ok;
+
+		switch (open->op_createmode) {
+		case NFS4_CREATE_UNCHECKED:
+			if (!d_is_reg(child))
+				break;
+
+			/*
+			 * In NFSv4, we don't want to truncate the file
+			 * now. This would be wrong if the OPEN fails for
+			 * some other reason. Furthermore, if the size is
+			 * nonzero, we should ignore it according to spec!
+			 */
+			open->op_truncate = (iap->ia_valid & ATTR_SIZE) &&
+						!iap->ia_size;
+			break;
+		case NFS4_CREATE_GUARDED:
+			status = nfserr_exist;
+			break;
+		case NFS4_CREATE_EXCLUSIVE:
+			if (d_inode(child)->i_mtime.tv_sec == v_mtime &&
+			    d_inode(child)->i_atime.tv_sec == v_atime &&
+			    d_inode(child)->i_size == 0) {
+				open->op_created = true;
+				break;		/* subtle */
+			}
+			status = nfserr_exist;
+			break;
+		case NFS4_CREATE_EXCLUSIVE4_1:
+			if (d_inode(child)->i_mtime.tv_sec == v_mtime &&
+			    d_inode(child)->i_atime.tv_sec == v_atime &&
+			    d_inode(child)->i_size == 0) {
+				open->op_created = true;
+				goto set_attr;	/* subtle */
+			}
+			status = nfserr_exist;
+		}
+		goto out;
+	}
+
+	if (!IS_POSIXACL(inode))
+		iap->ia_mode &= ~current_umask();
+
+	status = nfsd4_vfs_create(fhp, child, open);
+	if (status != nfs_ok)
+		goto out;
+	open->op_created = true;
+
+	/* A newly created file already has a file size of zero. */
+	if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0))
+		iap->ia_valid &= ~ATTR_SIZE;
+	if (nfsd4_create_is_exclusive(open->op_createmode)) {
+		iap->ia_valid = ATTR_MTIME | ATTR_ATIME |
+				ATTR_MTIME_SET|ATTR_ATIME_SET;
+		iap->ia_mtime.tv_sec = v_mtime;
+		iap->ia_atime.tv_sec = v_atime;
+		iap->ia_mtime.tv_nsec = 0;
+		iap->ia_atime.tv_nsec = 0;
+	}
+
+set_attr:
+	status = nfsd_create_setattr(rqstp, fhp, resfhp, iap);
+
+out:
+	fh_unlock(fhp);
+	if (child && !IS_ERR(child))
+		dput(child);
+	fh_drop_write(fhp);
+	return status;
+}
+
 static __be32
 do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh **resfh)
 {
@@ -264,16 +443,8 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
 		 * yes          | yes    | GUARDED4        | GUARDED4
 		 */
 
-		/*
-		 * Note: create modes (UNCHECKED,GUARDED...) are the same
-		 * in NFSv4 as in v3 except EXCLUSIVE4_1.
-		 */
 		current->fs->umask = open->op_umask;
-		status = do_nfsd_create(rqstp, current_fh, open->op_fname,
-					open->op_fnamelen, &open->op_iattr,
-					*resfh, open->op_createmode,
-					(u32 *)open->op_verf.data,
-					&open->op_truncate, &open->op_created);
+		status = nfsd4_create_file(rqstp, current_fh, *resfh, open);
 		current->fs->umask = 0;
 
 		if (!status && open->op_label.len)
@@ -284,7 +455,7 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
 		 * use the returned bitmask to indicate which attributes
 		 * we used to store the verifier:
 		 */
-		if (nfsd_create_is_exclusive(open->op_createmode) && status == 0)
+		if (nfsd4_create_is_exclusive(open->op_createmode) && status == 0)
 			open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS |
 						FATTR4_WORD1_TIME_MODIFY);
 	} else
@@ -375,6 +546,8 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		(int)open->op_fnamelen, open->op_fname,
 		open->op_openowner);
 
+	open->op_filp = NULL;
+
 	/* This check required by spec. */
 	if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
 		return nfserr_inval;
@@ -427,43 +600,35 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 
 	switch (open->op_claim_type) {
-		case NFS4_OPEN_CLAIM_DELEGATE_CUR:
-		case NFS4_OPEN_CLAIM_NULL:
-			status = do_open_lookup(rqstp, cstate, open, &resfh);
-			if (status)
-				goto out;
-			break;
-		case NFS4_OPEN_CLAIM_PREVIOUS:
-			status = nfs4_check_open_reclaim(cstate->clp);
-			if (status)
-				goto out;
-			open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
-			reclaim = true;
-			fallthrough;
-		case NFS4_OPEN_CLAIM_FH:
-		case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
-			status = do_open_fhandle(rqstp, cstate, open);
-			if (status)
-				goto out;
-			resfh = &cstate->current_fh;
-			break;
-		case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
-             	case NFS4_OPEN_CLAIM_DELEGATE_PREV:
-			dprintk("NFSD: unsupported OPEN claim type %d\n",
-				open->op_claim_type);
-			status = nfserr_notsupp;
+	case NFS4_OPEN_CLAIM_DELEGATE_CUR:
+	case NFS4_OPEN_CLAIM_NULL:
+		status = do_open_lookup(rqstp, cstate, open, &resfh);
+		if (status)
 			goto out;
-		default:
-			dprintk("NFSD: Invalid OPEN claim type %d\n",
-				open->op_claim_type);
-			status = nfserr_inval;
+		break;
+	case NFS4_OPEN_CLAIM_PREVIOUS:
+		status = nfs4_check_open_reclaim(cstate->clp);
+		if (status)
+			goto out;
+		open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
+		reclaim = true;
+		fallthrough;
+	case NFS4_OPEN_CLAIM_FH:
+	case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
+		status = do_open_fhandle(rqstp, cstate, open);
+		if (status)
 			goto out;
+		resfh = &cstate->current_fh;
+		break;
+	case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
+	case NFS4_OPEN_CLAIM_DELEGATE_PREV:
+		status = nfserr_notsupp;
+		goto out;
+	default:
+		status = nfserr_inval;
+		goto out;
 	}
-	/*
-	 * nfsd4_process_open2() does the actual opening of the file.  If
-	 * successful, it (1) truncates the file if open->op_truncate was
-	 * set, (2) sets open->op_stateid, (3) sets open->op_delegation.
-	 */
+
 	status = nfsd4_process_open2(rqstp, resfh, open);
 	WARN(status && open->op_created,
 	     "nfsd4_process_open2 failed to open newly-created file! status=%u\n",
@@ -471,6 +636,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (reclaim && !status)
 		nn->somebody_reclaimed = true;
 out:
+	if (open->op_filp) {
+		fput(open->op_filp);
+		open->op_filp = NULL;
+	}
 	if (resfh && resfh != &cstate->current_fh) {
 		fh_dup2(&cstate->current_fh, resfh);
 		fh_put(resfh);
@@ -801,7 +970,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * the client wants us to do more in this compound:
 	 */
 	if (!nfsd4_last_compound_op(rqstp))
-		clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+		__clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
 	/* check stateid */
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
@@ -2481,11 +2650,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
 	cstate->minorversion = args->minorversion;
 	fh_init(current_fh, NFS4_FHSIZE);
 	fh_init(save_fh, NFS4_FHSIZE);
+
 	/*
 	 * Don't use the deferral mechanism for NFSv4; compounds make it
 	 * too hard to avoid non-idempotency problems.
 	 */
-	clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+	__clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
 
 	/*
 	 * According to RFC3010, this takes precedence over all other errors.
@@ -2600,7 +2770,7 @@ encode_op:
 out:
 	cstate->status = status;
 	/* Reset deferral mechanism for RPC deferrals */
-	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+	__set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
 	return rpc_success;
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 234e852fcdfa..9409a0dc1b76 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -125,6 +125,23 @@ static void free_session(struct nfsd4_session *);
 static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
 static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops;
 
+static struct workqueue_struct *laundry_wq;
+
+int nfsd4_create_laundry_wq(void)
+{
+	int rc = 0;
+
+	laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4");
+	if (laundry_wq == NULL)
+		rc = -ENOMEM;
+	return rc;
+}
+
+void nfsd4_destroy_laundry_wq(void)
+{
+	destroy_workqueue(laundry_wq);
+}
+
 static bool is_session_dead(struct nfsd4_session *ses)
 {
 	return ses->se_flags & NFS4_SESSION_DEAD;
@@ -152,6 +169,7 @@ static __be32 get_client_locked(struct nfs4_client *clp)
 	if (is_client_expired(clp))
 		return nfserr_expired;
 	atomic_inc(&clp->cl_rpc_users);
+	clp->cl_state = NFSD4_ACTIVE;
 	return nfs_ok;
 }
 
@@ -172,6 +190,7 @@ renew_client_locked(struct nfs4_client *clp)
 
 	list_move_tail(&clp->cl_lru, &nn->client_lru);
 	clp->cl_time = ktime_get_boottime_seconds();
+	clp->cl_state = NFSD4_ACTIVE;
 }
 
 static void put_client_renew_locked(struct nfs4_client *clp)
@@ -690,6 +709,57 @@ static unsigned int file_hashval(struct svc_fh *fh)
 
 static struct hlist_head file_hashtbl[FILE_HASH_SIZE];
 
+/*
+ * Check if courtesy clients have conflicting access and resolve it if possible
+ *
+ * access:  is op_share_access if share_access is true.
+ *	    Check if access mode, op_share_access, would conflict with
+ *	    the current deny mode of the file 'fp'.
+ * access:  is op_share_deny if share_access is false.
+ *	    Check if the deny mode, op_share_deny, would conflict with
+ *	    current access of the file 'fp'.
+ * stp:     skip checking this entry.
+ * new_stp: normal open, not open upgrade.
+ *
+ * Function returns:
+ *	false - access/deny mode conflict with normal client.
+ *	true  - no conflict or conflict with courtesy client(s) is resolved.
+ */
+static bool
+nfs4_resolve_deny_conflicts_locked(struct nfs4_file *fp, bool new_stp,
+		struct nfs4_ol_stateid *stp, u32 access, bool share_access)
+{
+	struct nfs4_ol_stateid *st;
+	bool resolvable = true;
+	unsigned char bmap;
+	struct nfsd_net *nn;
+	struct nfs4_client *clp;
+
+	lockdep_assert_held(&fp->fi_lock);
+	list_for_each_entry(st, &fp->fi_stateids, st_perfile) {
+		/* ignore lock stateid */
+		if (st->st_openstp)
+			continue;
+		if (st == stp && new_stp)
+			continue;
+		/* check file access against deny mode or vice versa */
+		bmap = share_access ? st->st_deny_bmap : st->st_access_bmap;
+		if (!(access & bmap_to_share_mode(bmap)))
+			continue;
+		clp = st->st_stid.sc_client;
+		if (try_to_expire_client(clp))
+			continue;
+		resolvable = false;
+		break;
+	}
+	if (resolvable) {
+		clp = stp->st_stid.sc_client;
+		nn = net_generic(clp->net, nfsd_net_id);
+		mod_delayed_work(laundry_wq, &nn->laundromat_work, 0);
+	}
+	return resolvable;
+}
+
 static void
 __nfs4_file_get_access(struct nfs4_file *fp, u32 access)
 {
@@ -1090,6 +1160,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
 	get_clnt_odstate(odstate);
 	dp->dl_type = NFS4_OPEN_DELEGATE_READ;
 	dp->dl_retries = 1;
+	dp->dl_recalled = false;
 	nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
 		      &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
 	get_nfs4_file(fp);
@@ -2004,6 +2075,8 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 	idr_init(&clp->cl_stateids);
 	atomic_set(&clp->cl_rpc_users, 0);
 	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
+	clp->cl_state = NFSD4_ACTIVE;
+	atomic_set(&clp->cl_delegs_in_recall, 0);
 	INIT_LIST_HEAD(&clp->cl_idhash);
 	INIT_LIST_HEAD(&clp->cl_openowners);
 	INIT_LIST_HEAD(&clp->cl_delegations);
@@ -2408,10 +2481,17 @@ static int client_info_show(struct seq_file *m, void *v)
 	memcpy(&clid, &clp->cl_clientid, sizeof(clid));
 	seq_printf(m, "clientid: 0x%llx\n", clid);
 	seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr);
-	if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
+
+	if (clp->cl_state == NFSD4_COURTESY)
+		seq_puts(m, "status: courtesy\n");
+	else if (clp->cl_state == NFSD4_EXPIRABLE)
+		seq_puts(m, "status: expirable\n");
+	else if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
 		seq_puts(m, "status: confirmed\n");
 	else
 		seq_puts(m, "status: unconfirmed\n");
+	seq_printf(m, "seconds from last renew: %lld\n",
+		ktime_get_boottime_seconds() - clp->cl_time);
 	seq_printf(m, "name: ");
 	seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len);
 	seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion);
@@ -4694,9 +4774,18 @@ nfsd_break_deleg_cb(struct file_lock *fl)
 	bool ret = false;
 	struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
+	struct nfs4_client *clp = dp->dl_stid.sc_client;
+	struct nfsd_net *nn;
 
 	trace_nfsd_cb_recall(&dp->dl_stid);
 
+	dp->dl_recalled = true;
+	atomic_inc(&clp->cl_delegs_in_recall);
+	if (try_to_expire_client(clp)) {
+		nn = net_generic(clp->net, nfsd_net_id);
+		mod_delayed_work(laundry_wq, &nn->laundromat_work, 0);
+	}
+
 	/*
 	 * We don't want the locks code to timeout the lease for us;
 	 * we'll remove it ourself if a delegation isn't returned
@@ -4739,9 +4828,14 @@ static int
 nfsd_change_deleg_cb(struct file_lock *onlist, int arg,
 		     struct list_head *dispose)
 {
-	if (arg & F_UNLCK)
+	struct nfs4_delegation *dp = (struct nfs4_delegation *)onlist->fl_owner;
+	struct nfs4_client *clp = dp->dl_stid.sc_client;
+
+	if (arg & F_UNLCK) {
+		if (dp->dl_recalled)
+			atomic_dec(&clp->cl_delegs_in_recall);
 		return lease_modify(onlist, arg, dispose);
-	else
+	} else
 		return -EAGAIN;
 }