1 files changed, 449 insertions, 247 deletions

diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 814afaa4458a..ed85dd43da18 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * NFS server file handle treatment.
  *
@@ -13,6 +14,7 @@
 #include "nfsd.h"
 #include "vfs.h"
 #include "auth.h"
+#include "trace.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_FH
 
@@ -38,7 +40,8 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry)
 		/* make sure parents give x permission to user */
 		int err;
 		parent = dget_parent(tdentry);
-		err = inode_permission(parent->d_inode, MAY_EXEC);
+		err = inode_permission(&nop_mnt_idmap,
+				       d_inode(parent), MAY_EXEC);
 		if (err < 0) {
 			dput(parent);
 			break;
@@ -47,7 +50,7 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry)
 		tdentry = parent;
 	}
 	if (tdentry != exp->ex_path.dentry)
-		dprintk("nfsd_acceptable failed at %p %s\n", tdentry, tdentry->d_name.name);
+		dprintk("nfsd_acceptable failed at %p %pd\n", tdentry, tdentry);
 	rv = (tdentry == exp->ex_path.dentry);
 	dput(tdentry);
 	return rv;
@@ -59,64 +62,70 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry)
  * the write call).
  */
 static inline __be32
-nfsd_mode_check(struct svc_rqst *rqstp, umode_t mode, umode_t requested)
+nfsd_mode_check(struct dentry *dentry, umode_t requested)
 {
-	mode &= S_IFMT;
+	umode_t mode = d_inode(dentry)->i_mode & S_IFMT;
 
 	if (requested == 0) /* the caller doesn't care */
 		return nfs_ok;
-	if (mode == requested)
+	if (mode == requested) {
+		if (mode == S_IFDIR && !d_can_lookup(dentry)) {
+			WARN_ON_ONCE(1);
+			return nfserr_notdir;
+		}
 		return nfs_ok;
-	/*
-	 * v4 has an error more specific than err_notdir which we should
-	 * return in preference to err_notdir:
-	 */
-	if (rqstp->rq_vers == 4 && mode == S_IFLNK)
+	}
+	if (mode == S_IFLNK) {
+		if (requested == S_IFDIR)
+			return nfserr_symlink_not_dir;
 		return nfserr_symlink;
+	}
 	if (requested == S_IFDIR)
 		return nfserr_notdir;
 	if (mode == S_IFDIR)
 		return nfserr_isdir;
-	return nfserr_inval;
+	return nfserr_wrong_type;
+}
+
+static bool nfsd_originating_port_ok(struct svc_rqst *rqstp,
+				     struct svc_cred *cred,
+				     struct svc_export *exp)
+{
+	if (nfsexp_flags(cred, exp) & NFSEXP_INSECURE_PORT)
+		return true;
+	/* We don't require gss requests to use low ports: */
+	if (cred->cr_flavor >= RPC_AUTH_GSS)
+		return true;
+	return test_bit(RQ_SECURE, &rqstp->rq_flags);
 }
 
 static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
+					  struct svc_cred *cred,
 					  struct svc_export *exp)
 {
-	int flags = nfsexp_flags(rqstp, exp);
-
 	/* Check if the request originated from a secure port. */
-	if (!rqstp->rq_secure && !(flags & NFSEXP_INSECURE_PORT)) {
+	if (rqstp && !nfsd_originating_port_ok(rqstp, cred, exp)) {
 		RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
-		dprintk(KERN_WARNING
-		       "nfsd: request from insecure port %s!\n",
-		       svc_print_addr(rqstp, buf, sizeof(buf)));
+		dprintk("nfsd: request from insecure port %s!\n",
+		        svc_print_addr(rqstp, buf, sizeof(buf)));
 		return nfserr_perm;
 	}
 
 	/* Set user creds for this exportpoint */
-	return nfserrno(nfsd_setuser(rqstp, exp));
+	return nfserrno(nfsd_setuser(cred, exp));
 }
 
-static inline __be32 check_pseudo_root(struct svc_rqst *rqstp,
-	struct dentry *dentry, struct svc_export *exp)
+static inline __be32 check_pseudo_root(struct dentry *dentry,
+				       struct svc_export *exp)
 {
 	if (!(exp->ex_flags & NFSEXP_V4ROOT))
 		return nfs_ok;
 	/*
-	 * v2/v3 clients have no need for the V4ROOT export--they use
-	 * the mount protocl instead; also, further V4ROOT checks may be
-	 * in v4-specific code, in which case v2/v3 clients could bypass
-	 * them.
-	 */
-	if (!nfsd_v4client(rqstp))
-		return nfserr_stale;
-	/*
 	 * We're exposing only the directories and symlinks that have to be
 	 * traversed on the way to real exports:
 	 */
-	if (unlikely(!S_ISDIR(dentry->d_inode->i_mode) &&
-		     !S_ISLNK(dentry->d_inode->i_mode)))
+	if (unlikely(!d_is_dir(dentry) &&
+		     !d_is_symlink(dentry)))
 		return nfserr_stale;
 	/*
 	 * A pseudoroot export gives permission to access only one
@@ -133,64 +142,68 @@ static inline __be32 check_pseudo_root(struct svc_rqst *rqstp,
  * dentry.  On success, the results are used to set fh_export and
  * fh_dentry.
  */
-static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
+static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net,
+				 struct svc_cred *cred,
+				 struct auth_domain *client,
+				 struct auth_domain *gssclient,
+				 struct svc_fh *fhp)
 {
 	struct knfsd_fh	*fh = &fhp->fh_handle;
-	struct fid *fid = NULL, sfid;
+	struct fid *fid = NULL;
 	struct svc_export *exp;
 	struct dentry *dentry;
 	int fileid_type;
 	int data_left = fh->fh_size/4;
+	int len;
 	__be32 error;
 
-	error = nfserr_stale;
-	if (rqstp->rq_vers > 2)
-		error = nfserr_badhandle;
-	if (rqstp->rq_vers == 4 && fh->fh_size == 0)
+	error = nfserr_badhandle;
+	if (fh->fh_size == 0)
 		return nfserr_nofilehandle;
 
-	if (fh->fh_version == 1) {
-		int len;
+	if (fh->fh_version != 1)
+		return error;
 
-		if (--data_left < 0)
-			return error;
-		if (fh->fh_auth_type != 0)
-			return error;
-		len = key_len(fh->fh_fsid_type) / 4;
-		if (len == 0)
-			return error;
-		if  (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
-			/* deprecated, convert to type 3 */
-			len = key_len(FSID_ENCODE_DEV)/4;
-			fh->fh_fsid_type = FSID_ENCODE_DEV;
-			fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl(fh->fh_fsid[0]), ntohl(fh->fh_fsid[1])));
-			fh->fh_fsid[1] = fh->fh_fsid[2];
-		}
-		data_left -= len;
-		if (data_left < 0)
-			return error;
-		exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_auth);
-		fid = (struct fid *)(fh->fh_auth + len);
-	} else {
-		__u32 tfh[2];
-		dev_t xdev;
-		ino_t xino;
+	if (--data_left < 0)
+		return error;
+	if (fh->fh_auth_type != 0)
+		return error;
+	len = key_len(fh->fh_fsid_type) / 4;
+	if (len == 0)
+		return error;
+	if (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
+		u32 *fsid = fh_fsid(fh);
 
-		if (fh->fh_size != NFS_FHSIZE)
-			return error;
-		/* assume old filehandle format */
-		xdev = old_decode_dev(fh->ofh_xdev);
-		xino = u32_to_ino_t(fh->ofh_xino);
-		mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL);
-		exp = rqst_exp_find(rqstp, FSID_DEV, tfh);
+		/* deprecated, convert to type 3 */
+		len = key_len(FSID_ENCODE_DEV)/4;
+		fh->fh_fsid_type = FSID_ENCODE_DEV;
+		/*
+		 * struct knfsd_fh uses host-endian fields, which are
+		 * sometimes used to hold net-endian values. This
+		 * confuses sparse, so we must use __force here to
+		 * keep it from complaining.
+		 */
+		fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fsid[0]),
+					       ntohl((__force __be32)fsid[1])));
+		fsid[1] = fsid[2];
 	}
+	data_left -= len;
+	if (data_left < 0)
+		return error;
+	exp = rqst_exp_find(rqstp ? &rqstp->rq_chandle : NULL,
+			    net, client, gssclient,
+			    fh->fh_fsid_type, fh_fsid(fh));
+	fid = (struct fid *)(fh_fsid(fh) + len);
 
 	error = nfserr_stale;
-	if (PTR_ERR(exp) == -ENOENT)
-		return error;
+	if (IS_ERR(exp)) {
+		trace_nfsd_set_fh_dentry_badexport(rqstp, fhp, PTR_ERR(exp));
+
+		if (PTR_ERR(exp) == -ENOENT)
+			return error;
 
-	if (IS_ERR(exp))
 		return nfserrno(PTR_ERR(exp));
+	}
 
 	if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) {
 		/* Elevate privileges so that the lack of 'r' or 'x'
@@ -203,15 +216,16 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 		 * fix that case easily.
 		 */
 		struct cred *new = prepare_creds();
-		if (!new)
-			return nfserrno(-ENOMEM);
+		if (!new) {
+			error =  nfserrno(-ENOMEM);
+			goto out;
+		}
 		new->cap_effective =
 			cap_raise_nfsd_set(new->cap_effective,
 					   new->cap_permitted);
 		put_cred(override_creds(new));
-		put_cred(new);
 	} else {
-		error = nfsd_setuser_and_check_port(rqstp, exp);
+		error = nfsd_setuser_and_check_port(rqstp, cred, exp);
 		if (error)
 			goto out;
 	}
@@ -219,29 +233,27 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 	/*
 	 * Look up the dentry using the NFS file handle.
 	 */
-	error = nfserr_stale;
-	if (rqstp->rq_vers > 2)
-		error = nfserr_badhandle;
-
-	if (fh->fh_version != 1) {
-		sfid.i32.ino = fh->ofh_ino;
-		sfid.i32.gen = fh->ofh_generation;
-		sfid.i32.parent_ino = fh->ofh_dirino;
-		fid = &sfid;
-		data_left = 3;
-		if (fh->ofh_dirino == 0)
-			fileid_type = FILEID_INO32_GEN;
-		else
-			fileid_type = FILEID_INO32_GEN_PARENT;
-	} else
-		fileid_type = fh->fh_fileid_type;
+	error = nfserr_badhandle;
+
+	fileid_type = fh->fh_fileid_type;
 
 	if (fileid_type == FILEID_ROOT)
 		dentry = dget(exp->ex_path.dentry);
 	else {
-		dentry = exportfs_decode_fh(exp->ex_path.mnt, fid,
-				data_left, fileid_type,
-				nfsd_acceptable, exp);
+		dentry = exportfs_decode_fh_raw(exp->ex_path.mnt, fid,
+						data_left, fileid_type, 0,
+						nfsd_acceptable, exp);
+		if (IS_ERR_OR_NULL(dentry)) {
+			trace_nfsd_set_fh_dentry_badhandle(rqstp, fhp,
+					dentry ?  PTR_ERR(dentry) : -ESTALE);
+			switch (PTR_ERR(dentry)) {
+			case -ENOMEM:
+			case -ETIMEDOUT:
+				break;
+			default:
+				dentry = ERR_PTR(-ESTALE);
+			}
+		}
 	}
 	if (dentry == NULL)
 		goto out;
@@ -251,14 +263,36 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 		goto out;
 	}
 
-	if (S_ISDIR(dentry->d_inode->i_mode) &&
+	if (d_is_dir(dentry) &&
 			(dentry->d_flags & DCACHE_DISCONNECTED)) {
-		printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %s/%s\n",
-				dentry->d_parent->d_name.name, dentry->d_name.name);
+		printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %pd2\n",
+				dentry);
+	}
+
+	switch (fhp->fh_maxsize) {
+	case NFS4_FHSIZE:
+		if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR)
+			fhp->fh_no_atomic_attr = true;
+		fhp->fh_64bit_cookies = true;
+		break;
+	case NFS3_FHSIZE:
+		if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOWCC)
+			fhp->fh_no_wcc = true;
+		fhp->fh_64bit_cookies = true;
+		if (exp->ex_flags & NFSEXP_V4ROOT)
+			goto out;
+		break;
+	case NFS_FHSIZE:
+		fhp->fh_no_wcc = true;
+		if (EX_WGATHER(exp))
+			fhp->fh_use_wgather = true;
+		if (exp->ex_flags & NFSEXP_V4ROOT)
+			goto out;
 	}
 
 	fhp->fh_dentry = dentry;
 	fhp->fh_export = exp;
+
 	return 0;
 out:
 	exp_put(exp);
@@ -266,48 +300,42 @@ out:
 }
 
 /**
- * fh_verify - filehandle lookup and access checking
- * @rqstp: pointer to current rpc request
+ * __fh_verify - filehandle lookup and access checking
+ * @rqstp: RPC transaction context, or NULL
+ * @net: net namespace in which to perform the export lookup
+ * @cred: RPC user credential
+ * @client: RPC auth domain
+ * @gssclient: RPC GSS auth domain, or NULL
  * @fhp: filehandle to be verified
  * @type: expected type of object pointed to by filehandle
  * @access: type of access needed to object
  *
- * Look up a dentry from the on-the-wire filehandle, check the client's
- * access to the export, and set the current task's credentials.
- *
- * Regardless of success or failure of fh_verify(), fh_put() should be
- * called on @fhp when the caller is finished with the filehandle.
- *
- * fh_verify() may be called multiple times on a given filehandle, for
- * example, when processing an NFSv4 compound.  The first call will look
- * up a dentry using the on-the-wire filehandle.  Subsequent calls will
- * skip the lookup and just perform the other checks and possibly change
- * the current task's credentials.
- *
- * @type specifies the type of object expected using one of the S_IF*
- * constants defined in include/linux/stat.h.  The caller may use zero
- * to indicate that it doesn't care, or a negative integer to indicate
- * that it expects something not of the given type.
- *
- * @access is formed from the NFSD_MAY_* constants defined in
- * include/linux/nfsd/nfsd.h.
+ * See fh_verify() for further descriptions of @fhp, @type, and @access.
  */
-__be32
-fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
+static __be32
+__fh_verify(struct svc_rqst *rqstp,
+	    struct net *net, struct svc_cred *cred,
+	    struct auth_domain *client,
+	    struct auth_domain *gssclient,
+	    struct svc_fh *fhp, umode_t type, int access)
 {
-	struct svc_export *exp;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct svc_export *exp = NULL;
+	bool may_bypass_gss = false;
 	struct dentry	*dentry;
 	__be32		error;
 
-	dprintk("nfsd: fh_verify(%s)\n", SVCFH_fmt(fhp));
-
 	if (!fhp->fh_dentry) {
-		error = nfsd_set_fh_dentry(rqstp, fhp);
+		error = nfsd_set_fh_dentry(rqstp, net, cred, client,
+					   gssclient, fhp);
 		if (error)
 			goto out;
 	}
 	dentry = fhp->fh_dentry;
 	exp = fhp->fh_export;
+
+	trace_nfsd_fh_verify(rqstp, fhp, type, access);
+
 	/*
 	 * We still have to do all these permission checks, even when
 	 * fh_dentry is already set:
@@ -324,25 +352,44 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
 	 *	  (for example, if different id-squashing options are in
 	 *	  effect on the new filesystem).
 	 */
-	error = check_pseudo_root(rqstp, dentry, exp);
+	error = check_pseudo_root(dentry, exp);
 	if (error)
 		goto out;
 
-	error = nfsd_setuser_and_check_port(rqstp, exp);
+	error = nfsd_setuser_and_check_port(rqstp, cred, exp);
 	if (error)
 		goto out;
 
-	error = nfsd_mode_check(rqstp, dentry->d_inode->i_mode, type);
+	error = nfsd_mode_check(dentry, type);
 	if (error)
 		goto out;
 
 	/*
-	 * pseudoflavor restrictions are not enforced on NLM,
-	 * which clients virtually always use auth_sys for,
-	 * even while using RPCSEC_GSS for NFS.
+	 * If rqstp is NULL, this is a LOCALIO request which will only
+	 * ever use a filehandle/credential pair for which access has
+	 * been affirmed (by ACCESS or OPEN NFS requests) over the
+	 * wire.  Skip both the xprtsec policy and the security flavor
+	 * checks.
+	 */
+	if (!rqstp)
+		goto check_permissions;
+
+	if ((access & NFSD_MAY_NLM) && (exp->ex_flags & NFSEXP_NOAUTHNLM))
+		/* NLM is allowed to fully bypass authentication */
+		goto out;
+
+	/*
+	 * NLM is allowed to bypass the xprtsec policy check because lockd
+	 * doesn't support xprtsec.
 	 */
-	if (access & NFSD_MAY_LOCK || access & NFSD_MAY_BYPASS_GSS)
-		goto skip_pseudoflavor_check;
+	if (!(access & NFSD_MAY_NLM)) {
+		error = check_xprtsec_policy(exp, rqstp);
+		if (error)
+			goto out;
+	}
+
+	if (access & NFSD_MAY_BYPASS_GSS)
+		may_bypass_gss = true;
 	/*
 	 * Clients may expect to be able to use auth_sys during mount,
 	 * even if they use gss for everything else; see section 2.3.2
@@ -350,29 +397,81 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
 	 */
 	if (access & NFSD_MAY_BYPASS_GSS_ON_ROOT
 			&& exp->ex_path.dentry == dentry)
-		goto skip_pseudoflavor_check;
+		may_bypass_gss = true;
 
-	error = check_nfsd_access(exp, rqstp);
+	error = check_security_flavor(exp, rqstp, may_bypass_gss);
 	if (error)
 		goto out;
 
-skip_pseudoflavor_check:
+	svc_xprt_set_valid(rqstp->rq_xprt);
+
+check_permissions:
 	/* Finally, check access permissions. */
-	error = nfsd_permission(rqstp, exp, dentry, access);
-
-	if (error) {
-		dprintk("fh_verify: %s/%s permission failure, "
-			"acc=%x, error=%d\n",
-			dentry->d_parent->d_name.name,
-			dentry->d_name.name,
-			access, ntohl(error));
-	}
+	error = nfsd_permission(cred, exp, dentry, access);
 out:
+	trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error);
 	if (error == nfserr_stale)
-		nfsdstats.fh_stale++;
+		nfsd_stats_fh_stale_inc(nn, exp);
 	return error;
 }
 
+/**
+ * fh_verify_local - filehandle lookup and access checking
+ * @net: net namespace in which to perform the export lookup
+ * @cred: RPC user credential
+ * @client: RPC auth domain
+ * @fhp: filehandle to be verified
+ * @type: expected type of object pointed to by filehandle
+ * @access: type of access needed to object
+ *
+ * This API can be used by callers who do not have an RPC
+ * transaction context (ie are not running in an nfsd thread).
+ *
+ * See fh_verify() for further descriptions of @fhp, @type, and @access.
+ */
+__be32
+fh_verify_local(struct net *net, struct svc_cred *cred,
+		struct auth_domain *client, struct svc_fh *fhp,
+		umode_t type, int access)
+{
+	return __fh_verify(NULL, net, cred, client, NULL,
+			   fhp, type, access);
+}
+
+/**
+ * fh_verify - filehandle lookup and access checking
+ * @rqstp: pointer to current rpc request
+ * @fhp: filehandle to be verified
+ * @type: expected type of object pointed to by filehandle
+ * @access: type of access needed to object
+ *
+ * Look up a dentry from the on-the-wire filehandle, check the client's
+ * access to the export, and set the current task's credentials.
+ *
+ * Regardless of success or failure of fh_verify(), fh_put() should be
+ * called on @fhp when the caller is finished with the filehandle.
+ *
+ * fh_verify() may be called multiple times on a given filehandle, for
+ * example, when processing an NFSv4 compound.  The first call will look
+ * up a dentry using the on-the-wire filehandle.  Subsequent calls will
+ * skip the lookup and just perform the other checks and possibly change
+ * the current task's credentials.
+ *
+ * @type specifies the type of object expected using one of the S_IF*
+ * constants defined in include/linux/stat.h.  The caller may use zero
+ * to indicate that it doesn't care, or a negative integer to indicate
+ * that it expects something not of the given type.
+ *
+ * @access is formed from the NFSD_MAY_* constants defined in
+ * fs/nfsd/vfs.h.
+ */
+__be32
+fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
+{
+	return __fh_verify(rqstp, SVC_NET(rqstp), &rqstp->rq_cred,
+			   rqstp->rq_client, rqstp->rq_gssclient,
+			   fhp, type, access);
+}
 
 /*
  * Compose a file handle for an NFS reply.
@@ -386,32 +485,21 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp,
 {
 	if (dentry != exp->ex_path.dentry) {
 		struct fid *fid = (struct fid *)
-			(fhp->fh_handle.fh_auth + fhp->fh_handle.fh_size/4 - 1);
+			(fh_fsid(&fhp->fh_handle) + fhp->fh_handle.fh_size/4 - 1);
 		int maxsize = (fhp->fh_maxsize - fhp->fh_handle.fh_size)/4;
-		int subtreecheck = !(exp->ex_flags & NFSEXP_NOSUBTREECHECK);
+		int fh_flags = (exp->ex_flags & NFSEXP_NOSUBTREECHECK) ? 0 :
+				EXPORT_FH_CONNECTABLE;
+		int fileid_type =
+			exportfs_encode_fh(dentry, fid, &maxsize, fh_flags);
 
 		fhp->fh_handle.fh_fileid_type =
-			exportfs_encode_fh(dentry, fid, &maxsize, subtreecheck);
+			fileid_type > 0 ? fileid_type : FILEID_INVALID;
 		fhp->fh_handle.fh_size += maxsize * 4;
 	} else {
 		fhp->fh_handle.fh_fileid_type = FILEID_ROOT;
 	}
 }
 
-/*
- * for composing old style file handles
- */
-static inline void _fh_update_old(struct dentry *dentry,
-				  struct svc_export *exp,
-				  struct knfsd_fh *fh)
-{
-	fh->ofh_ino = ino_t_to_u32(dentry->d_inode->i_ino);
-	fh->ofh_generation = dentry->d_inode->i_generation;
-	if (S_ISDIR(dentry->d_inode->i_mode) ||
-	    (exp->ex_flags & NFSEXP_NOSUBTREECHECK))
-		fh->ofh_dirino = 0;
-}
-
 static bool is_root_export(struct svc_export *exp)
 {
 	return exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root;
@@ -419,7 +507,7 @@ static bool is_root_export(struct svc_export *exp)
 
 static struct super_block *exp_sb(struct svc_export *exp)
 {
-	return exp->ex_path.dentry->d_inode->i_sb;
+	return exp->ex_path.dentry->d_sb;
 }
 
 static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
@@ -427,8 +515,8 @@ static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
 	switch (fsid_type) {
 	case FSID_DEV:
 		if (!old_valid_dev(exp_sb(exp)->s_dev))
-			return 0;
-		/* FALL THROUGH */
+			return false;
+		fallthrough;
 	case FSID_MAJOR_MINOR:
 	case FSID_ENCODE_DEV:
 		return exp_sb(exp)->s_type->fs_flags & FS_REQUIRES_DEV;
@@ -437,13 +525,13 @@ static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
 	case FSID_UUID8:
 	case FSID_UUID16:
 		if (!is_root_export(exp))
-			return 0;
-		/* fall through */
+			return false;
+		fallthrough;
 	case FSID_UUID4_INUM:
 	case FSID_UUID16_INUM:
 		return exp->ex_uuid != NULL;
 	}
-	return 1;
+	return true;
 }
 
 
@@ -508,74 +596,56 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 	/* ref_fh is a reference file handle.
 	 * if it is non-null and for the same filesystem, then we should compose
 	 * a filehandle which is of the same version, where possible.
-	 * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca
-	 * Then create a 32byte filehandle using nfs_fhbase_old
-	 *
 	 */
 
-	struct inode * inode = dentry->d_inode;
-	struct dentry *parent = dentry->d_parent;
-	__u32 *datap;
+	struct inode * inode = d_inode(dentry);
 	dev_t ex_dev = exp_sb(exp)->s_dev;
 
-	dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %s/%s, ino=%ld)\n",
+	dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %pd2, ino=%ld)\n",
 		MAJOR(ex_dev), MINOR(ex_dev),
-		(long) exp->ex_path.dentry->d_inode->i_ino,
-		parent->d_name.name, dentry->d_name.name,
+		(long) d_inode(exp->ex_path.dentry)->i_ino,
+		dentry,
 		(inode ? inode->i_ino : 0));
 
 	/* Choose filehandle version and fsid type based on
 	 * the reference filehandle (if it is in the same export)
 	 * or the export options.
 	 */
-	 set_version_and_fsid_type(fhp, exp, ref_fh);
+	set_version_and_fsid_type(fhp, exp, ref_fh);
+
+	/* If we have a ref_fh, then copy the fh_no_wcc setting from it. */
+	fhp->fh_no_wcc = ref_fh ? ref_fh->fh_no_wcc : false;
 
 	if (ref_fh == fhp)
 		fh_put(ref_fh);
 
-	if (fhp->fh_locked || fhp->fh_dentry) {
-		printk(KERN_ERR "fh_compose: fh %s/%s not initialized!\n",
-		       parent->d_name.name, dentry->d_name.name);
+	if (fhp->fh_dentry) {
+		printk(KERN_ERR "fh_compose: fh %pd2 not initialized!\n",
+		       dentry);
 	}
 	if (fhp->fh_maxsize < NFS_FHSIZE)
-		printk(KERN_ERR "fh_compose: called with maxsize %d! %s/%s\n",
+		printk(KERN_ERR "fh_compose: called with maxsize %d! %pd2\n",
 		       fhp->fh_maxsize,
-		       parent->d_name.name, dentry->d_name.name);
+		       dentry);
 
 	fhp->fh_dentry = dget(dentry); /* our internal copy */
-	fhp->fh_export = exp;
-	cache_get(&exp->h);
-
-	if (fhp->fh_handle.fh_version == 0xca) {
-		/* old style filehandle please */
-		memset(&fhp->fh_handle.fh_base, 0, NFS_FHSIZE);
-		fhp->fh_handle.fh_size = NFS_FHSIZE;
-		fhp->fh_handle.ofh_dcookie = 0xfeebbaca;
-		fhp->fh_handle.ofh_dev =  old_encode_dev(ex_dev);
-		fhp->fh_handle.ofh_xdev = fhp->fh_handle.ofh_dev;
-		fhp->fh_handle.ofh_xino =
-			ino_t_to_u32(exp->ex_path.dentry->d_inode->i_ino);
-		fhp->fh_handle.ofh_dirino = ino_t_to_u32(parent_ino(dentry));
-		if (inode)
-			_fh_update_old(dentry, exp, &fhp->fh_handle);
-	} else {
-		int len;
-		fhp->fh_handle.fh_auth_type = 0;
-		datap = fhp->fh_handle.fh_auth+0;
-		mk_fsid(fhp->fh_handle.fh_fsid_type, datap, ex_dev,
-			exp->ex_path.dentry->d_inode->i_ino,
-			exp->ex_fsid, exp->ex_uuid);
-
-		len = key_len(fhp->fh_handle.fh_fsid_type);
-		datap += len/4;
-		fhp->fh_handle.fh_size = 4 + len;
-
-		if (inode)
-			_fh_update(fhp, exp, dentry);
-		if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
-			fh_put(fhp);
-			return nfserr_opnotsupp;
-		}
+	fhp->fh_export = exp_get(exp);
+
+	fhp->fh_handle.fh_size =
+		key_len(fhp->fh_handle.fh_fsid_type) + 4;
+	fhp->fh_handle.fh_auth_type = 0;
+
+	mk_fsid(fhp->fh_handle.fh_fsid_type,
+		fh_fsid(&fhp->fh_handle),
+		ex_dev,
+		d_inode(exp->ex_path.dentry)->i_ino,
+		exp->ex_fsid, exp->ex_uuid);
+
+	if (inode)
+		_fh_update(fhp, exp, dentry);
+	if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
+		fh_put(fhp);
+		return nfserr_stale;
 	}
 
 	return 0;
@@ -594,28 +664,127 @@ fh_update(struct svc_fh *fhp)
 		goto out_bad;
 
 	dentry = fhp->fh_dentry;
-	if (!dentry->d_inode)
+	if (d_really_is_negative(dentry))
 		goto out_negative;
-	if (fhp->fh_handle.fh_version != 1) {
-		_fh_update_old(dentry, fhp->fh_export, &fhp->fh_handle);
-	} else {
-		if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT)
-			goto out;
+	if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT)
+		return 0;
 
-		_fh_update(fhp, fhp->fh_export, dentry);
-		if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
-			return nfserr_opnotsupp;
-	}
-out:
+	_fh_update(fhp, fhp->fh_export, dentry);
+	if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
+		return nfserr_stale;
 	return 0;
-
 out_bad:
 	printk(KERN_ERR "fh_update: fh not verified!\n");
-	goto out;
+	return nfserr_serverfault;
 out_negative:
-	printk(KERN_ERR "fh_update: %s/%s still negative!\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name);
-	goto out;
+	printk(KERN_ERR "fh_update: %pd2 still negative!\n",
+		dentry);
+	return nfserr_serverfault;
+}
+
+/**
+ * fh_getattr - Retrieve attributes on a local file
+ * @fhp: File handle of target file
+ * @stat: Caller-supplied kstat buffer to be filled in
+ *
+ * Returns nfs_ok on success, otherwise an NFS status code is
+ * returned.
+ */
+__be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat)
+{
+	struct path p = {
+		.mnt		= fhp->fh_export->ex_path.mnt,
+		.dentry		= fhp->fh_dentry,
+	};
+	struct inode *inode = d_inode(p.dentry);
+	u32 request_mask = STATX_BASIC_STATS;
+
+	if (S_ISREG(inode->i_mode))
+		request_mask |= (STATX_DIOALIGN | STATX_DIO_READ_ALIGN);
+
+	if (fhp->fh_maxsize == NFS4_FHSIZE)
+		request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE);
+
+	return nfserrno(vfs_getattr(&p, stat, request_mask,
+				    AT_STATX_SYNC_AS_STAT));
+}
+
+/**
+ * fh_fill_pre_attrs - Fill in pre-op attributes
+ * @fhp: file handle to be updated
+ *
+ */
+__be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp)
+{
+	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
+	struct kstat stat;
+	__be32 err;
+
+	if (fhp->fh_no_wcc || fhp->fh_pre_saved)
+		return nfs_ok;
+
+	err = fh_getattr(fhp, &stat);
+	if (err)
+		return err;
+
+	if (v4)
+		fhp->fh_pre_change = nfsd4_change_attribute(&stat);
+
+	fhp->fh_pre_mtime = stat.mtime;
+	fhp->fh_pre_ctime = stat.ctime;
+	fhp->fh_pre_size  = stat.size;
+	fhp->fh_pre_saved = true;
+	return nfs_ok;
+}
+
+/**
+ * fh_fill_post_attrs - Fill in post-op attributes
+ * @fhp: file handle to be updated
+ *
+ */
+__be32 fh_fill_post_attrs(struct svc_fh *fhp)
+{
+	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
+	__be32 err;
+
+	if (fhp->fh_no_wcc)
+		return nfs_ok;
+
+	if (fhp->fh_post_saved)
+		printk("nfsd: inode locked twice during operation.\n");
+
+	err = fh_getattr(fhp, &fhp->fh_post_attr);
+	if (err)
+		return err;
+
+	fhp->fh_post_saved = true;
+	if (v4)
+		fhp->fh_post_change =
+			nfsd4_change_attribute(&fhp->fh_post_attr);
+	return nfs_ok;
+}
+
+/**
+ * fh_fill_both_attrs - Fill pre-op and post-op attributes
+ * @fhp: file handle to be updated
+ *
+ * This is used when the directory wasn't changed, but wcc attributes
+ * are needed anyway.
+ */
+__be32 __must_check fh_fill_both_attrs(struct svc_fh *fhp)
+{
+	__be32 err;
+
+	err = fh_fill_post_attrs(fhp);
+	if (err)
+		return err;
+
+	fhp->fh_pre_change = fhp->fh_post_change;
+	fhp->fh_pre_mtime = fhp->fh_post_attr.mtime;
+	fhp->fh_pre_ctime = fhp->fh_post_attr.ctime;
+	fhp->fh_pre_size = fhp->fh_post_attr.size;
+	fhp->fh_pre_saved = true;
+	return nfs_ok;
 }
 
 /*
@@ -627,19 +796,16 @@ fh_put(struct svc_fh *fhp)
 	struct dentry * dentry = fhp->fh_dentry;
 	struct svc_export * exp = fhp->fh_export;
 	if (dentry) {
-		fh_unlock(fhp);
 		fhp->fh_dentry = NULL;
 		dput(dentry);
-#ifdef CONFIG_NFSD_V3
-		fhp->fh_pre_saved = 0;
-		fhp->fh_post_saved = 0;
-#endif
+		fh_clear_pre_post_attrs(fhp);
 	}
 	fh_drop_write(fhp);
 	if (exp) {
 		exp_put(exp);
 		fhp->fh_export = NULL;
 	}
+	fhp->fh_no_wcc = false;
 	return;
 }
 
@@ -649,20 +815,15 @@ fh_put(struct svc_fh *fhp)
 char * SVCFH_fmt(struct svc_fh *fhp)
 {
 	struct knfsd_fh *fh = &fhp->fh_handle;
+	static char buf[2+1+1+64*3+1];
 
-	static char buf[80];
-	sprintf(buf, "%d: %08x %08x %08x %08x %08x %08x",
-		fh->fh_size,
-		fh->fh_base.fh_pad[0],
-		fh->fh_base.fh_pad[1],
-		fh->fh_base.fh_pad[2],
-		fh->fh_base.fh_pad[3],
-		fh->fh_base.fh_pad[4],
-		fh->fh_base.fh_pad[5]);
+	if (fh->fh_size > 64)
+		return "bad-fh";
+	sprintf(buf, "%d: %*ph", fh->fh_size, fh->fh_size, fh->fh_raw);
 	return buf;
 }
 
-enum fsid_source fsid_source(struct svc_fh *fhp)
+enum fsid_source fsid_source(const struct svc_fh *fhp)
 {
 	if (fhp->fh_handle.fh_version != 1)
 		return FSIDSOURCE_DEV;
@@ -689,3 +850,44 @@ enum fsid_source fsid_source(struct svc_fh *fhp)
 		return FSIDSOURCE_UUID;
 	return FSIDSOURCE_DEV;
 }
+
+/**
+ * nfsd4_change_attribute - Generate an NFSv4 change_attribute value
+ * @stat: inode attributes
+ *
+ * Caller must fill in @stat before calling, typically by invoking
+ * vfs_getattr() with STATX_MODE, STATX_CTIME, and STATX_CHANGE_COOKIE.
+ * Returns an unsigned 64-bit changeid4 value (RFC 8881 Section 3.2).
+ *
+ * We could use i_version alone as the change attribute.  However, i_version
+ * can go backwards on a regular file after an unclean shutdown.  On its own
+ * that doesn't necessarily cause a problem, but if i_version goes backwards
+ * and then is incremented again it could reuse a value that was previously
+ * used before boot, and a client who queried the two values might incorrectly
+ * assume nothing changed.
+ *
+ * By using both ctime and the i_version counter we guarantee that as long as
+ * time doesn't go backwards we never reuse an old value. If the filesystem
+ * advertises STATX_ATTR_CHANGE_MONOTONIC, then this mitigation is not
+ * needed.
+ *
+ * We only need to do this for regular files as well. For directories, we
+ * assume that the new change attr is always logged to stable storage in some
+ * fashion before the results can be seen.
+ */
+u64 nfsd4_change_attribute(const struct kstat *stat)
+{
+	u64 chattr;
+
+	if (stat->result_mask & STATX_CHANGE_COOKIE) {
+		chattr = stat->change_cookie;
+		if (S_ISREG(stat->mode) &&
+		    !(stat->attributes & STATX_ATTR_CHANGE_MONOTONIC)) {
+			chattr += (u64)stat->ctime.tv_sec << 30;
+			chattr += stat->ctime.tv_nsec;
+		}
+	} else {
+		chattr = time_to_chattr(&stat->ctime);
+	}
+	return chattr;
+}