--- zzzz-none-000/linux-3.10.107/fs/nfsd/vfs.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/fs/nfsd/vfs.c	2021-02-04 17:41:59.000000000 +0000
@@ -16,6 +16,7 @@
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/splice.h>
+#include <linux/falloc.h>
 #include <linux/fcntl.h>
 #include <linux/namei.h>
 #include <linux/delay.h>
@@ -28,6 +29,7 @@
 #include <asm/uaccess.h>
 #include <linux/exportfs.h>
 #include <linux/writeback.h>
+#include <linux/security.h>
 
 #ifdef CONFIG_NFSD_V3
 #include "xdr3.h"
@@ -172,7 +174,7 @@
 		return 1;
 	if (!(exp->ex_flags & NFSEXP_V4ROOT))
 		return 0;
-	return dentry->d_inode != NULL;
+	return d_inode(dentry) != NULL;
 }
 
 __be32
@@ -188,8 +190,7 @@
 	dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
 
 	dparent = fhp->fh_dentry;
-	exp  = fhp->fh_export;
-	exp_get(exp);
+	exp = exp_get(fhp->fh_export);
 
 	/* Lookup the name, but don't follow links */
 	if (isdotent(name, len)) {
@@ -206,7 +207,12 @@
 				goto out_nfserr;
 		}
 	} else {
-		fh_lock(fhp);
+		/*
+		 * In the nfsd4_open() case, this may be held across
+		 * subsequent open and delegation acquisition which may
+		 * need to take the child's i_mutex:
+		 */
+		fh_lock_nested(fhp, I_MUTEX_PARENT);
 		dentry = lookup_one_len(name, dparent, len);
 		host_err = PTR_ERR(dentry);
 		if (IS_ERR(dentry))
@@ -264,7 +270,7 @@
 	 * dentry may be negative, it may need to be updated.
 	 */
 	err = fh_compose(resfh, exp, dentry, fhp);
-	if (!err && !dentry->d_inode)
+	if (!err && d_really_is_negative(dentry))
 		err = nfserr_noent;
 out:
 	dput(dentry);
@@ -272,20 +278,13 @@
 	return err;
 }
 
-static int nfsd_break_lease(struct inode *inode)
-{
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	return break_lease(inode, O_WRONLY | O_NONBLOCK);
-}
-
 /*
  * Commit metadata changes to stable storage.
  */
 static int
 commit_metadata(struct svc_fh *fhp)
 {
-	struct inode *inode = fhp->fh_dentry->d_inode;
+	struct inode *inode = d_inode(fhp->fh_dentry);
 	const struct export_operations *export_ops = inode->i_sb->s_export_op;
 
 	if (!EX_ISSYNC(fhp->fh_export))
@@ -303,42 +302,6 @@
 static void
 nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
 {
-	/*
-	 * NFSv2 does not differentiate between "set-[ac]time-to-now"
-	 * which only requires access, and "set-[ac]time-to-X" which
-	 * requires ownership.
-	 * So if it looks like it might be "set both to the same time which
-	 * is close to now", and if inode_change_ok fails, then we
-	 * convert to "set to now" instead of "set to explicit time"
-	 *
-	 * We only call inode_change_ok as the last test as technically
-	 * it is not an interface that we should be using.
-	 */
-#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
-#define	MAX_TOUCH_TIME_ERROR (30*60)
-	if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET &&
-	    iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) {
-		/*
-		 * Looks probable.
-		 *
-		 * Now just make sure time is in the right ballpark.
-		 * Solaris, at least, doesn't seem to care what the time
-		 * request is.  We require it be within 30 minutes of now.
-		 */
-		time_t delta = iap->ia_atime.tv_sec - get_seconds();
-		if (delta < 0)
-			delta = -delta;
-		if (delta < MAX_TOUCH_TIME_ERROR &&
-		    inode_change_ok(inode, iap) != 0) {
-			/*
-			 * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME.
-			 * This will cause notify_change to set these times
-			 * to "now"
-			 */
-			iap->ia_valid &= ~BOTH_TIME_SET;
-		}
-	}
-
 	/* sanitize the mode change */
 	if (iap->ia_valid & ATTR_MODE) {
 		iap->ia_mode &= S_IALLUGO;
@@ -347,8 +310,7 @@
 
 	/* Revoke setuid/setgid on chown */
 	if (!S_ISDIR(inode->i_mode) &&
-	    (((iap->ia_valid & ATTR_UID) && !uid_eq(iap->ia_uid, inode->i_uid)) ||
-	     ((iap->ia_valid & ATTR_GID) && !gid_eq(iap->ia_gid, inode->i_gid)))) {
+	    ((iap->ia_valid & ATTR_UID) || (iap->ia_valid & ATTR_GID))) {
 		iap->ia_valid |= ATTR_KILL_PRIV;
 		if (iap->ia_valid & ATTR_MODE) {
 			/* we're setting mode too, just clear the s*id bits */
@@ -366,7 +328,7 @@
 nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		struct iattr *iap)
 {
-	struct inode *inode = fhp->fh_dentry->d_inode;
+	struct inode *inode = d_inode(fhp->fh_dentry);
 	int host_err;
 
 	if (iap->ia_size < inode->i_size) {
@@ -407,7 +369,7 @@
 	__be32		err;
 	int		host_err;
 	bool		get_write_count;
-	int		size_change = 0;
+	bool		size_change = (iap->ia_valid & ATTR_SIZE);
 
 	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
 		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
@@ -420,217 +382,83 @@
 	/* Get inode */
 	err = fh_verify(rqstp, fhp, ftype, accmode);
 	if (err)
-		goto out;
+		return err;
 	if (get_write_count) {
 		host_err = fh_want_write(fhp);
 		if (host_err)
-			return nfserrno(host_err);
+			goto out;
 	}
 
 	dentry = fhp->fh_dentry;
-	inode = dentry->d_inode;
+	inode = d_inode(dentry);
 
 	/* Ignore any mode updates on symlinks */
 	if (S_ISLNK(inode->i_mode))
 		iap->ia_valid &= ~ATTR_MODE;
 
 	if (!iap->ia_valid)
-		goto out;
+		return 0;
 
 	nfsd_sanitize_attrs(inode, iap);
 
+	if (check_guard && guardtime != inode->i_ctime.tv_sec)
+		return nfserr_notsync;
+
 	/*
 	 * The size case is special, it changes the file in addition to the
-	 * attributes.
+	 * attributes, and file systems don't expect it to be mixed with
+	 * "random" attribute changes.  We thus split out the size change
+	 * into a separate call to ->setattr, and do the rest as a separate
+	 * setattr call.
 	 */
-	if (iap->ia_valid & ATTR_SIZE) {
+	if (size_change) {
 		err = nfsd_get_write_access(rqstp, fhp, iap);
 		if (err)
-			goto out;
-		size_change = 1;
+			return err;
 	}
 
-	iap->ia_valid |= ATTR_CTIME;
+	fh_lock(fhp);
+	if (size_change) {
+		/*
+		 * RFC5661, Section 18.30.4:
+		 *   Changing the size of a file with SETATTR indirectly
+		 *   changes the time_modify and change attributes.
+		 *
+		 * (and similar for the older RFCs)
+		 */
+		struct iattr size_attr = {
+			.ia_valid	= ATTR_SIZE | ATTR_CTIME | ATTR_MTIME,
+			.ia_size	= iap->ia_size,
+		};
 
-	if (check_guard && guardtime != inode->i_ctime.tv_sec) {
-		err = nfserr_notsync;
-		goto out_put_write_access;
+		host_err = notify_change(dentry, &size_attr, NULL);
+		if (host_err)
+			goto out_unlock;
+		iap->ia_valid &= ~ATTR_SIZE;
+
+		/*
+		 * Avoid the additional setattr call below if the only other
+		 * attribute that the client sends is the mtime, as we update
+		 * it as part of the size change above.
+		 */
+		if ((iap->ia_valid & ~ATTR_MTIME) == 0)
+			goto out_unlock;
 	}
 
-	host_err = nfsd_break_lease(inode);
-	if (host_err)
-		goto out_put_write_access_nfserror;
+	iap->ia_valid |= ATTR_CTIME;
+	host_err = notify_change(dentry, iap, NULL);
 
-	fh_lock(fhp);
-	host_err = notify_change(dentry, iap);
+out_unlock:
 	fh_unlock(fhp);
-
-out_put_write_access_nfserror:
-	err = nfserrno(host_err);
-out_put_write_access:
 	if (size_change)
 		put_write_access(inode);
-	if (!err)
-		commit_metadata(fhp);
 out:
-	return err;
-}
-
-#if defined(CONFIG_NFSD_V2_ACL) || \
-    defined(CONFIG_NFSD_V3_ACL) || \
-    defined(CONFIG_NFSD_V4)
-static ssize_t nfsd_getxattr(struct dentry *dentry, char *key, void **buf)
-{
-	ssize_t buflen;
-	ssize_t ret;
-
-	buflen = vfs_getxattr(dentry, key, NULL, 0);
-	if (buflen <= 0)
-		return buflen;
-
-	*buf = kmalloc(buflen, GFP_KERNEL);
-	if (!*buf)
-		return -ENOMEM;
-
-	ret = vfs_getxattr(dentry, key, *buf, buflen);
-	if (ret < 0)
-		kfree(*buf);
-	return ret;
+	if (!host_err)
+		host_err = commit_metadata(fhp);
+	return nfserrno(host_err);
 }
-#endif
 
 #if defined(CONFIG_NFSD_V4)
-static int
-set_nfsv4_acl_one(struct dentry *dentry, struct posix_acl *pacl, char *key)
-{
-	int len;
-	size_t buflen;
-	char *buf = NULL;
-	int error = 0;
-
-	if (!pacl)
-		return vfs_setxattr(dentry, key, NULL, 0, 0);
-
-	buflen = posix_acl_xattr_size(pacl->a_count);
-	buf = kmalloc(buflen, GFP_KERNEL);
-	error = -ENOMEM;
-	if (buf == NULL)
-		goto out;
-
-	len = posix_acl_to_xattr(&init_user_ns, pacl, buf, buflen);
-	if (len < 0) {
-		error = len;
-		goto out;
-	}
-
-	error = vfs_setxattr(dentry, key, buf, len, 0);
-out:
-	kfree(buf);
-	return error;
-}
-
-__be32
-nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
-    struct nfs4_acl *acl)
-{
-	__be32 error;
-	int host_error;
-	struct dentry *dentry;
-	struct inode *inode;
-	struct posix_acl *pacl = NULL, *dpacl = NULL;
-	unsigned int flags = 0;
-
-	/* Get inode */
-	error = fh_verify(rqstp, fhp, 0, NFSD_MAY_SATTR);
-	if (error)
-		return error;
-
-	dentry = fhp->fh_dentry;
-	inode = dentry->d_inode;
-	if (S_ISDIR(inode->i_mode))
-		flags = NFS4_ACL_DIR;
-
-	host_error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags);
-	if (host_error == -EINVAL) {
-		return nfserr_attrnotsupp;
-	} else if (host_error < 0)
-		goto out_nfserr;
-
-	host_error = set_nfsv4_acl_one(dentry, pacl, POSIX_ACL_XATTR_ACCESS);
-	if (host_error < 0)
-		goto out_release;
-
-	if (S_ISDIR(inode->i_mode))
-		host_error = set_nfsv4_acl_one(dentry, dpacl, POSIX_ACL_XATTR_DEFAULT);
-
-out_release:
-	posix_acl_release(pacl);
-	posix_acl_release(dpacl);
-out_nfserr:
-	if (host_error == -EOPNOTSUPP)
-		return nfserr_attrnotsupp;
-	else
-		return nfserrno(host_error);
-}
-
-static struct posix_acl *
-_get_posix_acl(struct dentry *dentry, char *key)
-{
-	void *buf = NULL;
-	struct posix_acl *pacl = NULL;
-	int buflen;
-
-	buflen = nfsd_getxattr(dentry, key, &buf);
-	if (!buflen)
-		buflen = -ENODATA;
-	if (buflen <= 0)
-		return ERR_PTR(buflen);
-
-	pacl = posix_acl_from_xattr(&init_user_ns, buf, buflen);
-	kfree(buf);
-	return pacl;
-}
-
-int
-nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_acl **acl)
-{
-	struct inode *inode = dentry->d_inode;
-	int error = 0;
-	struct posix_acl *pacl = NULL, *dpacl = NULL;
-	unsigned int flags = 0;
-
-	pacl = _get_posix_acl(dentry, POSIX_ACL_XATTR_ACCESS);
-	if (IS_ERR(pacl) && PTR_ERR(pacl) == -ENODATA)
-		pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
-	if (IS_ERR(pacl)) {
-		error = PTR_ERR(pacl);
-		pacl = NULL;
-		goto out;
-	}
-
-	if (S_ISDIR(inode->i_mode)) {
-		dpacl = _get_posix_acl(dentry, POSIX_ACL_XATTR_DEFAULT);
-		if (IS_ERR(dpacl) && PTR_ERR(dpacl) == -ENODATA)
-			dpacl = NULL;
-		else if (IS_ERR(dpacl)) {
-			error = PTR_ERR(dpacl);
-			dpacl = NULL;
-			goto out;
-		}
-		flags = NFS4_ACL_DIR;
-	}
-
-	*acl = nfs4_acl_posix_to_nfsv4(pacl, dpacl, flags);
-	if (IS_ERR(*acl)) {
-		error = PTR_ERR(*acl);
-		*acl = NULL;
-	}
- out:
-	posix_acl_release(pacl);
-	posix_acl_release(dpacl);
-	return error;
-}
-
 /*
  * NFS junction information is stored in an extended attribute.
  */
@@ -646,7 +474,7 @@
  */
 int nfsd4_is_junction(struct dentry *dentry)
 {
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = d_inode(dentry);
 
 	if (inode == NULL)
 		return 0;
@@ -658,6 +486,48 @@
 		return 0;
 	return 1;
 }
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		struct xdr_netobj *label)
+{
+	__be32 error;
+	int host_error;
+	struct dentry *dentry;
+
+	error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR);
+	if (error)
+		return error;
+
+	dentry = fhp->fh_dentry;
+
+	mutex_lock(&d_inode(dentry)->i_mutex);
+	host_error = security_inode_setsecctx(dentry, label->data, label->len);
+	mutex_unlock(&d_inode(dentry)->i_mutex);
+	return nfserrno(host_error);
+}
+#else
+__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		struct xdr_netobj *label)
+{
+	return nfserr_notsupp;
+}
+#endif
+
+__be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp,
+			   struct file *file, loff_t offset, loff_t len,
+			   int flags)
+{
+	int error;
+
+	if (!S_ISREG(file_inode(file)->i_mode))
+		return nfserr_inval;
+
+	error = vfs_fallocate(file, flags, offset, len);
+	if (!error)
+		error = commit_metadata(fhp);
+
+	return nfserrno(error);
+}
 #endif /* defined(CONFIG_NFSD_V4) */
 
 #ifdef CONFIG_NFSD_V3
@@ -719,9 +589,9 @@
 	export = fhp->fh_export;
 	dentry = fhp->fh_dentry;
 
-	if (S_ISREG(dentry->d_inode->i_mode))
+	if (d_is_reg(dentry))
 		map = nfs3_regaccess;
-	else if (S_ISDIR(dentry->d_inode->i_mode))
+	else if (d_is_dir(dentry))
 		map = nfs3_diraccess;
 	else
 		map = nfs3_anyaccess;
@@ -784,6 +654,7 @@
 {
 	struct path	path;
 	struct inode	*inode;
+	struct file	*file;
 	int		flags = O_RDONLY|O_LARGEFILE;
 	__be32		err;
 	int		host_err = 0;
@@ -809,7 +680,7 @@
 
 	path.mnt = fhp->fh_export->ex_path.mnt;
 	path.dentry = fhp->fh_dentry;
-	inode = path.dentry->d_inode;
+	inode = d_inode(path.dentry);
 
 	/* Disallow write access to files with the append-only bit set
 	 * or any access when mandatory locking enabled
@@ -838,19 +709,25 @@
 		else
 			flags = O_WRONLY|O_LARGEFILE;
 	}
-	*filp = dentry_open(&path, flags, current_cred());
-	if (IS_ERR(*filp)) {
-		host_err = PTR_ERR(*filp);
-		*filp = NULL;
-	} else {
-		host_err = ima_file_check(*filp, may_flags);
 
-		if (may_flags & NFSD_MAY_64BIT_COOKIE)
-			(*filp)->f_mode |= FMODE_64BITHASH;
-		else
-			(*filp)->f_mode |= FMODE_32BITHASH;
+	file = dentry_open(&path, flags, current_cred());
+	if (IS_ERR(file)) {
+		host_err = PTR_ERR(file);
+		goto out_nfserr;
+	}
+
+	host_err = ima_file_check(file, may_flags, 0);
+	if (host_err) {
+		fput(file);
+		goto out_nfserr;
 	}
 
+	if (may_flags & NFSD_MAY_64BIT_COOKIE)
+		file->f_mode |= FMODE_64BITHASH;
+	else
+		file->f_mode |= FMODE_32BITHASH;
+
+	*filp = file;
 out_nfserr:
 	err = nfserrno(host_err);
 out:
@@ -858,23 +735,12 @@
 	return err;
 }
 
-/*
- * Close a file.
- */
-void
-nfsd_close(struct file *filp)
-{
-	fput(filp);
-}
-
-/*
- * Obtain the readahead parameters for the file
- * specified by (dev, ino).
- */
-
-static inline struct raparms *
-nfsd_get_raparms(dev_t dev, ino_t ino)
+struct raparms *
+nfsd_init_raparms(struct file *file)
 {
+	struct inode *inode = file_inode(file);
+	dev_t dev = inode->i_sb->s_dev;
+	ino_t ino = inode->i_ino;
 	struct raparms	*ra, **rap, **frap = NULL;
 	int depth = 0;
 	unsigned int hash;
@@ -911,9 +777,23 @@
 	ra->p_count++;
 	nfsdstats.ra_depth[depth*10/nfsdstats.ra_size]++;
 	spin_unlock(&rab->pb_lock);
+
+	if (ra->p_set)
+		file->f_ra = ra->p_ra;
 	return ra;
 }
 
+void nfsd_put_raparams(struct file *file, struct raparms *ra)
+{
+	struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex];
+
+	spin_lock(&rab->pb_lock);
+	ra->p_ra = file->f_ra;
+	ra->p_set = 1;
+	ra->p_count--;
+	spin_unlock(&rab->pb_lock);
+}
+
 /*
  * Grab and keep cached pages associated with a file in the svc_rqst
  * so that they can be passed to the network sendmsg/sendpage routines
@@ -955,50 +835,54 @@
 }
 
 static __be32
-nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
-              loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+nfsd_finish_read(struct file *file, unsigned long *count, int host_err)
 {
-	mm_segment_t	oldfs;
-	__be32		err;
-	int		host_err;
-
-	err = nfserr_perm;
-
-	if (file->f_op->splice_read && rqstp->rq_splice_ok) {
-		struct splice_desc sd = {
-			.len		= 0,
-			.total_len	= *count,
-			.pos		= offset,
-			.u.data		= rqstp,
-		};
-
-		rqstp->rq_next_page = rqstp->rq_respages + 1;
-		host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
-	} else {
-		oldfs = get_fs();
-		set_fs(KERNEL_DS);
-		host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
-		set_fs(oldfs);
-	}
-
 	if (host_err >= 0) {
 		nfsdstats.io_read += host_err;
 		*count = host_err;
-		err = 0;
 		fsnotify_access(file);
+		return 0;
 	} else 
-		err = nfserrno(host_err);
-	return err;
+		return nfserrno(host_err);
+}
+
+__be32 nfsd_splice_read(struct svc_rqst *rqstp,
+		     struct file *file, loff_t offset, unsigned long *count)
+{
+	struct splice_desc sd = {
+		.len		= 0,
+		.total_len	= *count,
+		.pos		= offset,
+		.u.data		= rqstp,
+	};
+	int host_err;
+
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
+	host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
+	return nfsd_finish_read(file, count, host_err);
 }
 
-static void kill_suid(struct dentry *dentry)
+__be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen,
+		unsigned long *count)
 {
-	struct iattr	ia;
-	ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
+	mm_segment_t oldfs;
+	int host_err;
+
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
+	set_fs(oldfs);
+	return nfsd_finish_read(file, count, host_err);
+}
 
-	mutex_lock(&dentry->d_inode->i_mutex);
-	notify_change(dentry, &ia);
-	mutex_unlock(&dentry->d_inode->i_mutex);
+static __be32
+nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file,
+	      loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+{
+	if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags))
+		return nfsd_splice_read(rqstp, file, offset, count);
+	else
+		return nfsd_readv(file, offset, vec, vlen, count);
 }
 
 /*
@@ -1038,13 +922,12 @@
 	return err;
 }
 
-static __be32
+__be32
 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 				loff_t offset, struct kvec *vec, int vlen,
 				unsigned long *cnt, int *stablep)
 {
 	struct svc_export	*exp;
-	struct dentry		*dentry;
 	struct inode		*inode;
 	mm_segment_t		oldfs;
 	__be32			err = 0;
@@ -1052,9 +935,19 @@
 	int			stable = *stablep;
 	int			use_wgather;
 	loff_t			pos = offset;
+	loff_t			end = LLONG_MAX;
+	unsigned int		pflags = current->flags;
+
+	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
+		/*
+		 * We want less throttling in balance_dirty_pages()
+		 * and shrink_inactive_list() so that nfs to
+		 * localhost doesn't cause nfsd to lock up due to all
+		 * the client's dirty pages or its congested queue.
+		 */
+		current->flags |= PF_LESS_THROTTLE;
 
-	dentry = file->f_path.dentry;
-	inode = dentry->d_inode;
+	inode = file_inode(file);
 	exp   = fhp->fh_export;
 
 	use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
@@ -1072,15 +965,14 @@
 	nfsdstats.io_write += host_err;
 	fsnotify_modify(file);
 
-	/* clear setuid/setgid flag after write */
-	if (inode->i_mode & (S_ISUID | S_ISGID))
-		kill_suid(dentry);
-
 	if (stable) {
-		if (use_wgather)
+		if (use_wgather) {
 			host_err = wait_for_concurrent_writes(file);
-		else
-			host_err = vfs_fsync_range(file, offset, offset+*cnt, 0);
+		} else {
+			if (*cnt)
+				end = offset + *cnt - 1;
+			host_err = vfs_fsync_range(file, offset, end, 0);
+		}
 	}
 
 out_nfserr:
@@ -1089,6 +981,8 @@
 		err = 0;
 	else
 		err = nfserrno(host_err);
+	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
+		tsk_restore_flags(current, pflags, PF_LESS_THROTTLE);
 	return err;
 }
 
@@ -1101,7 +995,6 @@
 	loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
 {
 	struct file *file;
-	struct inode *inode;
 	struct raparms	*ra;
 	__be32 err;
 
@@ -1109,47 +1002,12 @@
 	if (err)
 		return err;
 
-	inode = file_inode(file);
-
-	/* Get readahead parameters */
-	ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
-
-	if (ra && ra->p_set)
-		file->f_ra = ra->p_ra;
-
-	err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
+	ra = nfsd_init_raparms(file);
+	err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count);
+	if (ra)
+		nfsd_put_raparams(file, ra);
+	fput(file);
 
-	/* Write back readahead params */
-	if (ra) {
-		struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex];
-		spin_lock(&rab->pb_lock);
-		ra->p_ra = file->f_ra;
-		ra->p_set = 1;
-		ra->p_count--;
-		spin_unlock(&rab->pb_lock);
-	}
-
-	nfsd_close(file);
-	return err;
-}
-
-/* As above, but use the provided file descriptor. */
-__be32
-nfsd_read_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
-		loff_t offset, struct kvec *vec, int vlen,
-		unsigned long *count)
-{
-	__be32		err;
-
-	if (file) {
-		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
-				NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE);
-		if (err)
-			goto out;
-		err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
-	} else /* Note file may still be NULL in NFSv4 special stateid case: */
-		err = nfsd_read(rqstp, fhp, offset, vec, vlen, count);
-out:
 	return err;
 }
 
@@ -1180,7 +1038,7 @@
 		if (cnt)
 			err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen,
 					     cnt, stablep);
-		nfsd_close(file);
+		fput(file);
 	}
 out:
 	return err;
@@ -1225,7 +1083,7 @@
 			err = nfserr_notsupp;
 	}
 
-	nfsd_close(file);
+	fput(file);
 out:
 	return err;
 }
@@ -1248,7 +1106,8 @@
 		iap->ia_valid &= ~(ATTR_UID|ATTR_GID);
 	if (iap->ia_valid)
 		return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
-	return 0;
+	/* Callers expect file metadata to be committed here */
+	return nfserrno(commit_metadata(resfhp));
 }
 
 /* HPUX client sometimes creates a file in mode 000, and sets size to 0.
@@ -1297,7 +1156,7 @@
 		goto out;
 
 	dentry = fhp->fh_dentry;
-	dirp = dentry->d_inode;
+	dirp = d_inode(dentry);
 
 	err = nfserr_notdir;
 	if (!dirp->i_op->lookup)
@@ -1326,9 +1185,8 @@
 		if (!fhp->fh_locked) {
 			/* not actually possible */
 			printk(KERN_ERR
-				"nfsd_create: parent %s/%s not locked!\n",
-				dentry->d_parent->d_name.name,
-				dentry->d_name.name);
+				"nfsd_create: parent %pd2 not locked!\n",
+				dentry);
 			err = nfserr_io;
 			goto out;
 		}
@@ -1337,9 +1195,9 @@
 	 * Make sure the child dentry is still negative ...
 	 */
 	err = nfserr_exist;
-	if (dchild->d_inode) {
-		dprintk("nfsd_create: dentry %s/%s not negative!\n",
-			dentry->d_name.name, dchild->d_name.name);
+	if (d_really_is_positive(dchild)) {
+		dprintk("nfsd_create: dentry %pd/%pd not negative!\n",
+			dentry, dchild);
 		goto out; 
 	}
 
@@ -1381,9 +1239,10 @@
 	err = nfsd_create_setattr(rqstp, resfhp, iap);
 
 	/*
-	 * nfsd_setattr already committed the child.  Transactional filesystems
-	 * had a chance to commit changes for both parent and child
-	 * simultaneously making the following commit_metadata a noop.
+	 * nfsd_create_setattr already committed the child.  Transactional
+	 * filesystems had a chance to commit changes for both parent and
+	 * child * simultaneously making the following commit_metadata a
+	 * noop.
 	 */
 	err2 = nfserrno(commit_metadata(fhp));
 	if (err2)
@@ -1405,12 +1264,6 @@
 
 #ifdef CONFIG_NFSD_V3
 
-static inline int nfsd_create_is_exclusive(int createmode)
-{
-	return createmode == NFS3_CREATE_EXCLUSIVE
-	       || createmode == NFS4_CREATE_EXCLUSIVE4_1;
-}
-
 /*
  * NFSv3 and NFSv4 version of nfsd_create
  */
@@ -1439,7 +1292,7 @@
 		goto out;
 
 	dentry = fhp->fh_dentry;
-	dirp = dentry->d_inode;
+	dirp = d_inode(dentry);
 
 	/* Get all the sanity checks out of the way before
 	 * we lock the parent. */
@@ -1462,7 +1315,7 @@
 		goto out_nfserr;
 
 	/* If file doesn't exist, check for permissions to create one */
-	if (!dchild->d_inode) {
+	if (d_really_is_negative(dchild)) {
 		err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
 		if (err)
 			goto out;
@@ -1483,12 +1336,12 @@
 		v_atime = verifier[1]&0x7fffffff;
 	}
 	
-	if (dchild->d_inode) {
+	if (d_really_is_positive(dchild)) {
 		err = 0;
 
 		switch (createmode) {
 		case NFS3_CREATE_UNCHECKED:
-			if (! S_ISREG(dchild->d_inode->i_mode))
+			if (! d_is_reg(dchild))
 				goto out;
 			else if (truncp) {
 				/* in nfsv4, we need to treat this case a little
@@ -1506,17 +1359,17 @@
 			}
 			break;
 		case NFS3_CREATE_EXCLUSIVE:
-			if (   dchild->d_inode->i_mtime.tv_sec == v_mtime
-			    && dchild->d_inode->i_atime.tv_sec == v_atime
-			    && dchild->d_inode->i_size  == 0 ) {
+			if (   d_inode(dchild)->i_mtime.tv_sec == v_mtime
+			    && d_inode(dchild)->i_atime.tv_sec == v_atime
+			    && d_inode(dchild)->i_size  == 0 ) {
 				if (created)
 					*created = 1;
 				break;
 			}
 		case NFS4_CREATE_EXCLUSIVE4_1:
-			if (   dchild->d_inode->i_mtime.tv_sec == v_mtime
-			    && dchild->d_inode->i_atime.tv_sec == v_atime
-			    && dchild->d_inode->i_size  == 0 ) {
+			if (   d_inode(dchild)->i_mtime.tv_sec == v_mtime
+			    && d_inode(dchild)->i_atime.tv_sec == v_atime
+			    && d_inode(dchild)->i_size  == 0 ) {
 				if (created)
 					*created = 1;
 				goto set_attr;
@@ -1554,7 +1407,8 @@
 	err = nfsd_create_setattr(rqstp, resfhp, iap);
 
 	/*
-	 * nfsd_setattr already committed the child (and possibly also the parent).
+	 * nfsd_create_setattr already committed the child
+	 * (and possibly also the parent).
 	 */
 	if (!err)
 		err = nfserrno(commit_metadata(fhp));
@@ -1598,7 +1452,7 @@
 
 	path.mnt = fhp->fh_export->ex_path.mnt;
 	path.dentry = fhp->fh_dentry;
-	inode = path.dentry->d_inode;
+	inode = d_inode(path.dentry);
 
 	err = nfserr_inval;
 	if (!inode->i_op->readlink)
@@ -1632,16 +1486,15 @@
 __be32
 nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				char *fname, int flen,
-				char *path,  int plen,
-				struct svc_fh *resfhp,
-				struct iattr *iap)
+				char *path,
+				struct svc_fh *resfhp)
 {
 	struct dentry	*dentry, *dnew;
 	__be32		err, cerr;
 	int		host_err;
 
 	err = nfserr_noent;
-	if (!flen || !plen)
+	if (!flen || path[0] == '\0')
 		goto out;
 	err = nfserr_exist;
 	if (isdotent(fname, flen))
@@ -1662,18 +1515,7 @@
 	if (IS_ERR(dnew))
 		goto out_nfserr;
 
-	if (unlikely(path[plen] != 0)) {
-		char *path_alloced = kmalloc(plen+1, GFP_KERNEL);
-		if (path_alloced == NULL)
-			host_err = -ENOMEM;
-		else {
-			strncpy(path_alloced, path, plen);
-			path_alloced[plen] = 0;
-			host_err = vfs_symlink(dentry->d_inode, dnew, path_alloced);
-			kfree(path_alloced);
-		}
-	} else
-		host_err = vfs_symlink(dentry->d_inode, dnew, path);
+	host_err = vfs_symlink(d_inode(dentry), dnew, path);
 	err = nfserrno(host_err);
 	if (!err)
 		err = nfserrno(commit_metadata(fhp));
@@ -1712,7 +1554,7 @@
 	if (err)
 		goto out;
 	err = nfserr_isdir;
-	if (S_ISDIR(tfhp->fh_dentry->d_inode->i_mode))
+	if (d_is_dir(tfhp->fh_dentry))
 		goto out;
 	err = nfserr_perm;
 	if (!len)
@@ -1729,7 +1571,7 @@
 
 	fh_lock_nested(ffhp, I_MUTEX_PARENT);
 	ddir = ffhp->fh_dentry;
-	dirp = ddir->d_inode;
+	dirp = d_inode(ddir);
 
 	dnew = lookup_one_len(name, ddir, len);
 	host_err = PTR_ERR(dnew);
@@ -1739,14 +1581,9 @@
 	dold = tfhp->fh_dentry;
 
 	err = nfserr_noent;
-	if (!dold->d_inode)
-		goto out_dput;
-	host_err = nfsd_break_lease(dold->d_inode);
-	if (host_err) {
-		err = nfserrno(host_err);
+	if (d_really_is_negative(dold))
 		goto out_dput;
-	}
-	host_err = vfs_link(dold, dirp, dnew);
+	host_err = vfs_link(dold, dirp, dnew, NULL);
 	if (!host_err) {
 		err = nfserrno(commit_metadata(ffhp));
 		if (!err)
@@ -1791,10 +1628,10 @@
 		goto out;
 
 	fdentry = ffhp->fh_dentry;
-	fdir = fdentry->d_inode;
+	fdir = d_inode(fdentry);
 
 	tdentry = tfhp->fh_dentry;
-	tdir = tdentry->d_inode;
+	tdir = d_inode(tdentry);
 
 	err = nfserr_perm;
 	if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen))
@@ -1809,7 +1646,7 @@
 	/* cannot use fh_lock as we need deadlock protective ordering
 	 * so do it by hand */
 	trap = lock_rename(tdentry, fdentry);
-	ffhp->fh_locked = tfhp->fh_locked = 1;
+	ffhp->fh_locked = tfhp->fh_locked = true;
 	fill_pre_wcc(ffhp);
 	fill_pre_wcc(tfhp);
 
@@ -1819,7 +1656,7 @@
 		goto out_nfserr;
 
 	host_err = -ENOENT;
-	if (!odentry->d_inode)
+	if (d_really_is_negative(odentry))
 		goto out_dput_old;
 	host_err = -EINVAL;
 	if (odentry == trap)
@@ -1839,15 +1676,7 @@
 	if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
 		goto out_dput_new;
 
-	host_err = nfsd_break_lease(odentry->d_inode);
-	if (host_err)
-		goto out_dput_new;
-	if (ndentry->d_inode) {
-		host_err = nfsd_break_lease(ndentry->d_inode);
-		if (host_err)
-			goto out_dput_new;
-	}
-	host_err = vfs_rename(fdir, odentry, tdir, ndentry);
+	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
 	if (!host_err) {
 		host_err = commit_metadata(tfhp);
 		if (!host_err)
@@ -1859,15 +1688,15 @@
 	dput(odentry);
  out_nfserr:
 	err = nfserrno(host_err);
-
-	/* we cannot reply on fh_unlock on the two filehandles,
+	/*
+	 * We cannot rely on fh_unlock on the two filehandles,
 	 * as that would do the wrong thing if the two directories
-	 * were the same, so again we do it by hand
+	 * were the same, so again we do it by hand.
 	 */
 	fill_post_wcc(ffhp);
 	fill_post_wcc(tfhp);
 	unlock_rename(tdentry, fdentry);
-	ffhp->fh_locked = tfhp->fh_locked = 0;
+	ffhp->fh_locked = tfhp->fh_locked = false;
 	fh_drop_write(ffhp);
 
 out:
@@ -1900,32 +1729,28 @@
 
 	fh_lock_nested(fhp, I_MUTEX_PARENT);
 	dentry = fhp->fh_dentry;
-	dirp = dentry->d_inode;
+	dirp = d_inode(dentry);
 
 	rdentry = lookup_one_len(fname, dentry, flen);
 	host_err = PTR_ERR(rdentry);
 	if (IS_ERR(rdentry))
 		goto out_nfserr;
 
-	if (!rdentry->d_inode) {
+	if (d_really_is_negative(rdentry)) {
 		dput(rdentry);
 		err = nfserr_noent;
 		goto out;
 	}
 
 	if (!type)
-		type = rdentry->d_inode->i_mode & S_IFMT;
+		type = d_inode(rdentry)->i_mode & S_IFMT;
 
-	host_err = nfsd_break_lease(rdentry->d_inode);
-	if (host_err)
-		goto out_put;
 	if (type != S_IFDIR)
-		host_err = vfs_unlink(dirp, rdentry);
+		host_err = vfs_unlink(dirp, rdentry, NULL);
 	else
 		host_err = vfs_rmdir(dirp, rdentry);
 	if (!host_err)
 		host_err = commit_metadata(fhp);
-out_put:
 	dput(rdentry);
 
 out_nfserr:
@@ -1950,15 +1775,18 @@
 };
 
 struct readdir_data {
+	struct dir_context ctx;
 	char		*dirent;
 	size_t		used;
 	int		full;
 };
 
-static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen,
-				 loff_t offset, u64 ino, unsigned int d_type)
+static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name,
+				 int namlen, loff_t offset, u64 ino,
+				 unsigned int d_type)
 {
-	struct readdir_data *buf = __buf;
+	struct readdir_data *buf =
+		container_of(ctx, struct readdir_data, ctx);
 	struct buffered_dirent *de = (void *)(buf->dirent + buf->used);
 	unsigned int reclen;
 
@@ -1978,16 +1806,18 @@
 	return 0;
 }
 
-static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func,
+static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
 				    struct readdir_cd *cdp, loff_t *offsetp)
 {
-	struct readdir_data buf;
 	struct buffered_dirent *de;
 	int host_err;
 	int size;
 	loff_t offset;
+	struct readdir_data buf = {
+		.ctx.actor = nfsd_buffered_filldir,
+		.dirent = (void *)__get_free_page(GFP_KERNEL)
+	};
 
-	buf.dirent = (void *)__get_free_page(GFP_KERNEL);
 	if (!buf.dirent)
 		return nfserrno(-ENOMEM);
 
@@ -2001,7 +1831,7 @@
 		buf.used = 0;
 		buf.full = 0;
 
-		host_err = vfs_readdir(file, nfsd_buffered_filldir, &buf);
+		host_err = iterate_dir(file, &buf.ctx);
 		if (buf.full)
 			host_err = 0;
 
@@ -2060,7 +1890,7 @@
  */
 __be32
 nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, 
-	     struct readdir_cd *cdp, filldir_t func)
+	     struct readdir_cd *cdp, nfsd_filldir_t func)
 {
 	__be32		err;
 	struct file	*file;
@@ -2086,7 +1916,7 @@
 	if (err == nfserr_eof || err == nfserr_toosmall)
 		err = nfs_ok; /* can still be found in ->err */
 out_close:
-	nfsd_close(file);
+	fput(file);
 out:
 	return err;
 }
@@ -2124,7 +1954,7 @@
 nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 					struct dentry *dentry, int acc)
 {
-	struct inode	*inode = dentry->d_inode;
+	struct inode	*inode = d_inode(dentry);
 	int		err;
 
 	if ((acc & NFSD_MAY_MASK) == NFSD_MAY_NOP)
@@ -2235,8 +2065,7 @@
 	if (raparm_hash[0].pb_head)
 		return 0;
 	nperbucket = DIV_ROUND_UP(cache_size, RAPARM_HASH_SIZE);
-	if (nperbucket < 2)
-		nperbucket = 2;
+	nperbucket = max(2, nperbucket);
 	cache_size = nperbucket * RAPARM_HASH_SIZE;
 
 	dprintk("nfsd: allocating %d readahead buffers.\n", cache_size);
@@ -2262,93 +2091,3 @@
 	nfsd_racache_shutdown();
 	return -ENOMEM;
 }
-
-#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
-struct posix_acl *
-nfsd_get_posix_acl(struct svc_fh *fhp, int type)
-{
-	struct inode *inode = fhp->fh_dentry->d_inode;
-	char *name;
-	void *value = NULL;
-	ssize_t size;
-	struct posix_acl *acl;
-
-	if (!IS_POSIXACL(inode))
-		return ERR_PTR(-EOPNOTSUPP);
-
-	switch (type) {
-	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
-		break;
-	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
-		break;
-	default:
-		return ERR_PTR(-EOPNOTSUPP);
-	}
-
-	size = nfsd_getxattr(fhp->fh_dentry, name, &value);
-	if (size < 0)
-		return ERR_PTR(size);
-
-	acl = posix_acl_from_xattr(&init_user_ns, value, size);
-	kfree(value);
-	return acl;
-}
-
-int
-nfsd_set_posix_acl(struct svc_fh *fhp, int type, struct posix_acl *acl)
-{
-	struct inode *inode = fhp->fh_dentry->d_inode;
-	char *name;
-	void *value = NULL;
-	size_t size;
-	int error;
-
-	if (!IS_POSIXACL(inode) ||
-	    !inode->i_op->setxattr || !inode->i_op->removexattr)
-		return -EOPNOTSUPP;
-	switch(type) {
-		case ACL_TYPE_ACCESS:
-			name = POSIX_ACL_XATTR_ACCESS;
-			break;
-		case ACL_TYPE_DEFAULT:
-			name = POSIX_ACL_XATTR_DEFAULT;
-			break;
-		default:
-			return -EOPNOTSUPP;
-	}
-
-	if (acl && acl->a_count) {
-		size = posix_acl_xattr_size(acl->a_count);
-		value = kmalloc(size, GFP_KERNEL);
-		if (!value)
-			return -ENOMEM;
-		error = posix_acl_to_xattr(&init_user_ns, acl, value, size);
-		if (error < 0)
-			goto getout;
-		size = error;
-	} else
-		size = 0;
-
-	error = fh_want_write(fhp);
-	if (error)
-		goto getout;
-	if (size)
-		error = vfs_setxattr(fhp->fh_dentry, name, value, size, 0);
-	else {
-		if (!S_ISDIR(inode->i_mode) && type == ACL_TYPE_DEFAULT)
-			error = 0;
-		else {
-			error = vfs_removexattr(fhp->fh_dentry, name);
-			if (error == -ENODATA)
-				error = 0;
-		}
-	}
-	fh_drop_write(fhp);
-
-getout:
-	kfree(value);
-	return error;
-}
-#endif  /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */