Merge branch 'master' into for-next

Sync with Linus' branch in order to be able to apply fixups
of more recent patches.

1 files changed, 252 insertions, 6 deletions

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 0aa02eb18bd3..aba5af9df328 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -612,6 +612,12 @@ static struct accessmap	nfs3_regaccess[] = {
     {	NFS3_ACCESS_MODIFY,	NFSD_MAY_WRITE|NFSD_MAY_TRUNC	},
     {	NFS3_ACCESS_EXTEND,	NFSD_MAY_WRITE			},
 
+#ifdef CONFIG_NFSD_V4
+    {	NFS4_ACCESS_XAREAD,	NFSD_MAY_READ			},
+    {	NFS4_ACCESS_XAWRITE,	NFSD_MAY_WRITE			},
+    {	NFS4_ACCESS_XALIST,	NFSD_MAY_READ			},
+#endif
+
     {	0,			0				}
 };
 
@@ -622,6 +628,12 @@ static struct accessmap	nfs3_diraccess[] = {
     {	NFS3_ACCESS_EXTEND,	NFSD_MAY_EXEC|NFSD_MAY_WRITE	},
     {	NFS3_ACCESS_DELETE,	NFSD_MAY_REMOVE			},
 
+#ifdef CONFIG_NFSD_V4
+    {	NFS4_ACCESS_XAREAD,	NFSD_MAY_READ			},
+    {	NFS4_ACCESS_XAWRITE,	NFSD_MAY_WRITE			},
+    {	NFS4_ACCESS_XALIST,	NFSD_MAY_READ			},
+#endif
+
     {	0,			0				}
 };
 
@@ -979,12 +991,13 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 
 	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
 		/*
-		 * We want less throttling in balance_dirty_pages()
-		 * and shrink_inactive_list() so that nfs to
+		 * We want throttling in balance_dirty_pages()
+		 * and shrink_inactive_list() to only consider
+		 * the backingdev we are writing to, 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;
+		current->flags |= PF_LOCAL_THROTTLE;
 
 	exp = fhp->fh_export;
 	use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
@@ -1037,7 +1050,7 @@ out_nfserr:
 		nfserr = nfserrno(host_err);
 	}
 	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
-		current_restore_flags(pflags, PF_LESS_THROTTLE);
+		current_restore_flags(pflags, PF_LOCAL_THROTTLE);
 	return nfserr;
 }
 
@@ -1225,6 +1238,9 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		iap->ia_mode = 0;
 	iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;
 
+	if (!IS_POSIXACL(dirp))
+		iap->ia_mode &= ~current_umask();
+
 	err = 0;
 	host_err = 0;
 	switch (type) {
@@ -1440,7 +1456,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 					*created = true;
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		case NFS4_CREATE_EXCLUSIVE4_1:
 			if (   d_inode(dchild)->i_mtime.tv_sec == v_mtime
 			    && d_inode(dchild)->i_atime.tv_sec == v_atime
@@ -1449,7 +1465,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 					*created = true;
 				goto set_attr;
 			}
-			/* fall through */
+			fallthrough;
 		case NFS3_CREATE_GUARDED:
 			err = nfserr_exist;
 		}
@@ -1457,6 +1473,9 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out;
 	}
 
+	if (!IS_POSIXACL(dirp))
+		iap->ia_mode &= ~current_umask();
+
 	host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
 	if (host_err < 0) {
 		fh_drop_write(fhp);
@@ -2058,6 +2077,233 @@ static int exp_rdonly(struct svc_rqst *rqstp, struct svc_export *exp)
 	return nfsexp_flags(rqstp, exp) & NFSEXP_READONLY;
 }
 
+#ifdef CONFIG_NFSD_V4
+/*
+ * Helper function to translate error numbers. In the case of xattr operations,
+ * some error codes need to be translated outside of the standard translations.
+ *
+ * ENODATA needs to be translated to nfserr_noxattr.
+ * E2BIG to nfserr_xattr2big.
+ *
+ * Additionally, vfs_listxattr can return -ERANGE. This means that the
+ * file has too many extended attributes to retrieve inside an
+ * XATTR_LIST_MAX sized buffer. This is a bug in the xattr implementation:
+ * filesystems will allow the adding of extended attributes until they hit
+ * their own internal limit. This limit may be larger than XATTR_LIST_MAX.
+ * So, at that point, the attributes are present and valid, but can't
+ * be retrieved using listxattr, since the upper level xattr code enforces
+ * the XATTR_LIST_MAX limit.
+ *
+ * This bug means that we need to deal with listxattr returning -ERANGE. The
+ * best mapping is to return TOOSMALL.
+ */
+static __be32
+nfsd_xattr_errno(int err)
+{
+	switch (err) {
+	case -ENODATA:
+		return nfserr_noxattr;
+	case -E2BIG:
+		return nfserr_xattr2big;
+	case -ERANGE:
+		return nfserr_toosmall;
+	}
+	return nfserrno(err);
+}
+
+/*
+ * Retrieve the specified user extended attribute. To avoid always
+ * having to allocate the maximum size (since we are not getting
+ * a maximum size from the RPC), do a probe + alloc. Hold a reader
+ * lock on i_rwsem to prevent the extended attribute from changing
+ * size while we're doing this.
+ */
+__be32
+nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name,
+	      void **bufp, int *lenp)
+{
+	ssize_t len;
+	__be32 err;
+	char *buf;
+	struct inode *inode;
+	struct dentry *dentry;
+
+	err = fh_verify(rqstp, fhp, 0, NFSD_MAY_READ);
+	if (err)
+		return err;
+
+	err = nfs_ok;
+	dentry = fhp->fh_dentry;
+	inode = d_inode(dentry);
+
+	inode_lock_shared(inode);
+
+	len = vfs_getxattr(dentry, name, NULL, 0);
+
+	/*
+	 * Zero-length attribute, just return.
+	 */
+	if (len == 0) {
+		*bufp = NULL;
+		*lenp = 0;
+		goto out;
+	}
+
+	if (len < 0) {
+		err = nfsd_xattr_errno(len);
+		goto out;
+	}
+
+	if (len > *lenp) {
+		err = nfserr_toosmall;
+		goto out;
+	}
+
+	buf = kvmalloc(len, GFP_KERNEL | GFP_NOFS);
+	if (buf == NULL) {
+		err = nfserr_jukebox;
+		goto out;
+	}
+
+	len = vfs_getxattr(dentry, name, buf, len);
+	if (len <= 0) {
+		kvfree(buf);
+		buf = NULL;
+		err = nfsd_xattr_errno(len);
+	}
+
+	*lenp = len;
+	*bufp = buf;
+
+out:
+	inode_unlock_shared(inode);
+
+	return err;
+}
+
+/*
+ * Retrieve the xattr names. Since we can't know how many are
+ * user extended attributes, we must get all attributes here,
+ * and have the XDR encode filter out the "user." ones.
+ *
+ * While this could always just allocate an XATTR_LIST_MAX
+ * buffer, that's a waste, so do a probe + allocate. To
+ * avoid any changes between the probe and allocate, wrap
+ * this in inode_lock.
+ */
+__be32
+nfsd_listxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char **bufp,
+	       int *lenp)
+{
+	ssize_t len;
+	__be32 err;
+	char *buf;
+	struct inode *inode;
+	struct dentry *dentry;
+
+	err = fh_verify(rqstp, fhp, 0, NFSD_MAY_READ);
+	if (err)
+		return err;
+
+	dentry = fhp->fh_dentry;
+	inode = d_inode(dentry);
+	*lenp = 0;
+
+	inode_lock_shared(inode);
+
+	len = vfs_listxattr(dentry, NULL, 0);
+	if (len <= 0) {
+		err = nfsd_xattr_errno(len);
+		goto out;
+	}
+
+	if (len > XATTR_LIST_MAX) {
+		err = nfserr_xattr2big;
+		goto out;
+	}
+
+	/*
+	 * We're holding i_rwsem - use GFP_NOFS.
+	 */
+	buf = kvmalloc(len, GFP_KERNEL | GFP_NOFS);
+	if (buf == NULL) {
+		err = nfserr_jukebox;
+		goto out;
+	}
+
+	len = vfs_listxattr(dentry, buf, len);
+	if (len <= 0) {
+		kvfree(buf);
+		err = nfsd_xattr_errno(len);
+		goto out;
+	}
+
+	*lenp = len;
+	*bufp = buf;
+
+	err = nfs_ok;
+out:
+	inode_unlock_shared(inode);
+
+	return err;
+}
+
+/*
+ * Removexattr and setxattr need to call fh_lock to both lock the inode
+ * and set the change attribute. Since the top-level vfs_removexattr
+ * and vfs_setxattr calls already do their own inode_lock calls, call
+ * the _locked variant. Pass in a NULL pointer for delegated_inode,
+ * and let the client deal with NFS4ERR_DELAY (same as with e.g.
+ * setattr and remove).
+ */
+__be32
+nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name)
+{
+	int err, ret;
+
+	err = fh_verify(rqstp, fhp, 0, NFSD_MAY_WRITE);
+	if (err)
+		return err;
+
+	ret = fh_want_write(fhp);
+	if (ret)
+		return nfserrno(ret);
+
+	fh_lock(fhp);
+
+	ret = __vfs_removexattr_locked(fhp->fh_dentry, name, NULL);
+
+	fh_unlock(fhp);
+	fh_drop_write(fhp);
+
+	return nfsd_xattr_errno(ret);
+}
+
+__be32
+nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name,
+	      void *buf, u32 len, u32 flags)
+{
+	int err, ret;
+
+	err = fh_verify(rqstp, fhp, 0, NFSD_MAY_WRITE);
+	if (err)
+		return err;
+
+	ret = fh_want_write(fhp);
+	if (ret)
+		return nfserrno(ret);
+	fh_lock(fhp);
+
+	ret = __vfs_setxattr_locked(fhp->fh_dentry, name, buf, len, flags,
+				    NULL);
+
+	fh_unlock(fhp);
+	fh_drop_write(fhp);
+
+	return nfsd_xattr_errno(ret);
+}
+#endif
+
 /*
  * Check for a user's access permissions to this inode.
  */