Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull Ceph fixes from Sage Weil:
 "We have some patches fixing up ACL support issues from Zheng and
  Guangliang and a mount option to enable/disable this support.  (These
  fixes were somewhat delayed by the Chinese holiday.)

  There is also a small fix for cached readdir handling when directories
  are fragmented"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
  ceph: fix __dcache_readdir()
  ceph: add acl, noacl options for cephfs mount
  ceph: make ceph_forget_all_cached_acls() static inline
  ceph: add missing init_acl() for mkdir() and atomic_open()
  ceph: fix ceph_set_acl()
  ceph: fix ceph_removexattr()
  ceph: remove xattr when null value is given to setxattr()
  ceph: properly handle XATTR_CREATE and XATTR_REPLACE

6 files changed, 93 insertions, 35 deletions

diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 4c2d452c4bfc..21887d63dad5 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -54,11 +54,6 @@ static inline struct posix_acl *ceph_get_cached_acl(struct inode *inode,
 	return acl;
 }
 
-void ceph_forget_all_cached_acls(struct inode *inode)
-{
-	forget_all_cached_acls(inode);
-}
-
 struct posix_acl *ceph_get_acl(struct inode *inode, int type)
 {
 	int size;
@@ -160,11 +155,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 			goto out_dput;
 	}
 
-	if (value)
-		ret = __ceph_setxattr(dentry, name, value, size, 0);
-	else
-		ret = __ceph_removexattr(dentry, name);
-
+	ret = __ceph_setxattr(dentry, name, value, size, 0);
 	if (ret) {
 		if (new_mode != old_mode) {
 			newattrs.ia_mode = old_mode;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 6da4df84ba30..45eda6d7a40c 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -100,6 +100,14 @@ static unsigned fpos_off(loff_t p)
 	return p & 0xffffffff;
 }
 
+static int fpos_cmp(loff_t l, loff_t r)
+{
+	int v = ceph_frag_compare(fpos_frag(l), fpos_frag(r));
+	if (v)
+		return v;
+	return (int)(fpos_off(l) - fpos_off(r));
+}
+
 /*
  * When possible, we try to satisfy a readdir by peeking at the
  * dcache.  We make this work by carefully ordering dentries on
@@ -156,7 +164,7 @@ more:
 		if (!d_unhashed(dentry) && dentry->d_inode &&
 		    ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
 		    ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
-		    ctx->pos <= di->offset)
+		    fpos_cmp(ctx->pos, di->offset) <= 0)
 			break;
 		dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry,
 		     dentry->d_name.len, dentry->d_name.name, di->offset,
@@ -695,9 +703,8 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
 	ceph_mdsc_put_request(req);
 
 	if (!err)
-		err = ceph_init_acl(dentry, dentry->d_inode, dir);
-
-	if (err)
+		ceph_init_acl(dentry, dentry->d_inode, dir);
+	else
 		d_drop(dentry);
 	return err;
 }
@@ -735,7 +742,9 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
 	ceph_mdsc_put_request(req);
-	if (err)
+	if (!err)
+		ceph_init_acl(dentry, dentry->d_inode, dir);
+	else
 		d_drop(dentry);
 	return err;
 }
@@ -776,7 +785,9 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		err = ceph_handle_notrace_create(dir, dentry);
 	ceph_mdsc_put_request(req);
 out:
-	if (err < 0)
+	if (!err)
+		ceph_init_acl(dentry, dentry->d_inode, dir);
+	else
 		d_drop(dentry);
 	return err;
 }
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index dfd2ce3419f8..09c7afe32e49 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -286,6 +286,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	} else {
 		dout("atomic_open finish_open on dn %p\n", dn);
 		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
+			ceph_init_acl(dentry, dentry->d_inode, dir);
 			*opened |= FILE_CREATED;
 		}
 		err = finish_open(file, dentry, ceph_open, opened);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 2df963f1cf5a..10a4ccbf38da 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -144,7 +144,11 @@ enum {
 	Opt_ino32,
 	Opt_noino32,
 	Opt_fscache,
-	Opt_nofscache
+	Opt_nofscache,
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	Opt_acl,
+#endif
+	Opt_noacl
 };
 
 static match_table_t fsopt_tokens = {
@@ -172,6 +176,10 @@ static match_table_t fsopt_tokens = {
 	{Opt_noino32, "noino32"},
 	{Opt_fscache, "fsc"},
 	{Opt_nofscache, "nofsc"},
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	{Opt_acl, "acl"},
+#endif
+	{Opt_noacl, "noacl"},
 	{-1, NULL}
 };
 
@@ -271,6 +279,14 @@ static int parse_fsopt_token(char *c, void *private)
 	case Opt_nofscache:
 		fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
 		break;
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	case Opt_acl:
+		fsopt->sb_flags |= MS_POSIXACL;
+		break;
+#endif
+	case Opt_noacl:
+		fsopt->sb_flags &= ~MS_POSIXACL;
+		break;
 	default:
 		BUG_ON(token);
 	}
@@ -438,6 +454,13 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 	else
 		seq_puts(m, ",nofsc");
 
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	if (fsopt->sb_flags & MS_POSIXACL)
+		seq_puts(m, ",acl");
+	else
+		seq_puts(m, ",noacl");
+#endif
+
 	if (fsopt->wsize)
 		seq_printf(m, ",wsize=%d", fsopt->wsize);
 	if (fsopt->rsize != CEPH_RSIZE_DEFAULT)
@@ -819,9 +842,6 @@ static int ceph_set_super(struct super_block *s, void *data)
 
 	s->s_flags = fsc->mount_options->sb_flags;
 	s->s_maxbytes = 1ULL << 40;  /* temp value until we get mdsmap */
-#ifdef CONFIG_CEPH_FS_POSIX_ACL
-	s->s_flags |= MS_POSIXACL;
-#endif
 
 	s->s_xattr = ceph_xattr_handlers;
 	s->s_fs_info = fsc;
@@ -911,6 +931,10 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
 	struct ceph_options *opt = NULL;
 
 	dout("ceph_mount\n");
+
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	flags |= MS_POSIXACL;
+#endif
 	err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path);
 	if (err < 0) {
 		res = ERR_PTR(err);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 19793b56d0a7..d8801a95b685 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -13,6 +13,7 @@
 #include <linux/wait.h>
 #include <linux/writeback.h>
 #include <linux/slab.h>
+#include <linux/posix_acl.h>
 
 #include <linux/ceph/libceph.h>
 
@@ -743,7 +744,11 @@ extern const struct xattr_handler *ceph_xattr_handlers[];
 struct posix_acl *ceph_get_acl(struct inode *, int);
 int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 int ceph_init_acl(struct dentry *, struct inode *, struct inode *);
-void ceph_forget_all_cached_acls(struct inode *inode);
+
+static inline void ceph_forget_all_cached_acls(struct inode *inode)
+{
+       forget_all_cached_acls(inode);
+}
 
 #else
 
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 898b6565ad3e..a55ec37378c6 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -12,6 +12,9 @@
 #define XATTR_CEPH_PREFIX "ceph."
 #define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1)
 
+static int __remove_xattr(struct ceph_inode_info *ci,
+			  struct ceph_inode_xattr *xattr);
+
 /*
  * List of handlers for synthetic system.* attributes. Other
  * attributes are handled directly.
@@ -319,8 +322,7 @@ static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode,
 static int __set_xattr(struct ceph_inode_info *ci,
 			   const char *name, int name_len,
 			   const char *val, int val_len,
-			   int dirty,
-			   int should_free_name, int should_free_val,
+			   int flags, int update_xattr,
 			   struct ceph_inode_xattr **newxattr)
 {
 	struct rb_node **p;
@@ -349,12 +351,31 @@ static int __set_xattr(struct ceph_inode_info *ci,
 		xattr = NULL;
 	}
 
+	if (update_xattr) {
+		int err = 0;
+		if (xattr && (flags & XATTR_CREATE))
+			err = -EEXIST;
+		else if (!xattr && (flags & XATTR_REPLACE))
+			err = -ENODATA;
+		if (err) {
+			kfree(name);
+			kfree(val);
+			return err;
+		}
+		if (update_xattr < 0) {
+			if (xattr)
+				__remove_xattr(ci, xattr);
+			kfree(name);
+			return 0;
+		}
+	}
+
 	if (!xattr) {
 		new = 1;
 		xattr = *newxattr;
 		xattr->name = name;
 		xattr->name_len = name_len;
-		xattr->should_free_name = should_free_name;
+		xattr->should_free_name = update_xattr;
 
 		ci->i_xattrs.count++;
 		dout("__set_xattr count=%d\n", ci->i_xattrs.count);
@@ -364,7 +385,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
 		if (xattr->should_free_val)
 			kfree((void *)xattr->val);
 
-		if (should_free_name) {
+		if (update_xattr) {
 			kfree((void *)name);
 			name = xattr->name;
 		}
@@ -379,8 +400,8 @@ static int __set_xattr(struct ceph_inode_info *ci,
 		xattr->val = "";
 
 	xattr->val_len = val_len;
-	xattr->dirty = dirty;
-	xattr->should_free_val = (val && should_free_val);
+	xattr->dirty = update_xattr;
+	xattr->should_free_val = (val && update_xattr);
 
 	if (new) {
 		rb_link_node(&xattr->node, parent, p);
@@ -442,7 +463,7 @@ static int __remove_xattr(struct ceph_inode_info *ci,
 			  struct ceph_inode_xattr *xattr)
 {
 	if (!xattr)
-		return -EOPNOTSUPP;
+		return -ENODATA;
 
 	rb_erase(&xattr->node, &ci->i_xattrs.index);
 
@@ -588,7 +609,7 @@ start:
 			p += len;
 
 			err = __set_xattr(ci, name, namelen, val, len,
-					  0, 0, 0, &xattrs[numattr]);
+					  0, 0, &xattrs[numattr]);
 
 			if (err < 0)
 				goto bad;
@@ -850,6 +871,9 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 
 	dout("setxattr value=%.*s\n", (int)size, value);
 
+	if (!value)
+		flags |= CEPH_XATTR_REMOVE;
+
 	/* do request */
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR,
 				       USE_AUTH_MDS);
@@ -892,7 +916,7 @@ int __ceph_setxattr(struct dentry *dentry, const char *name,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int issued;
 	int err;
-	int dirty;
+	int dirty = 0;
 	int name_len = strlen(name);
 	int val_len = size;
 	char *newname = NULL;
@@ -953,12 +977,14 @@ retry:
 		goto retry;
 	}
 
-	err = __set_xattr(ci, newname, name_len, newval,
-			  val_len, 1, 1, 1, &xattr);
+	err = __set_xattr(ci, newname, name_len, newval, val_len,
+			  flags, value ? 1 : -1, &xattr);
 
-	dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
-	ci->i_xattrs.dirty = true;
-	inode->i_ctime = CURRENT_TIME;
+	if (!err) {
+		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
+		ci->i_xattrs.dirty = true;
+		inode->i_ctime = CURRENT_TIME;
+	}
 
 	spin_unlock(&ci->i_ceph_lock);
 	if (dirty)