8 files changed, 71 insertions, 116 deletions

diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index e913ad1..a721907 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -247,7 +247,7 @@ static int ocfs2_set_acl(handle_t *handle,
 	case ACL_TYPE_ACCESS:
 		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS;
 		if (acl) {
-			mode_t mode = inode->i_mode;
+			umode_t mode = inode->i_mode;
 			ret = posix_acl_equiv_mode(acl, &mode);
 			if (ret < 0)
 				return ret;
@@ -290,47 +290,32 @@ static int ocfs2_set_acl(handle_t *handle,
 	return ret;
 }
 
-int ocfs2_check_acl(struct inode *inode, int mask, unsigned int flags)
+struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
 {
 	struct ocfs2_super *osb;
 	struct buffer_head *di_bh = NULL;
 	struct posix_acl *acl;
 	int ret = -EAGAIN;
 
-	if (flags & IPERM_FLAG_RCU)
-		return -ECHILD;
-
 	osb = OCFS2_SB(inode->i_sb);
 	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
-		return ret;
+		return NULL;
 
 	ret = ocfs2_read_inode_block(inode, &di_bh);
-	if (ret < 0) {
-		mlog_errno(ret);
-		return ret;
-	}
+	if (ret < 0)
+		return ERR_PTR(ret);
 
-	acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, di_bh);
+	acl = ocfs2_get_acl_nolock(inode, type, di_bh);
 
 	brelse(di_bh);
 
-	if (IS_ERR(acl)) {
-		mlog_errno(PTR_ERR(acl));
-		return PTR_ERR(acl);
-	}
-	if (acl) {
-		ret = posix_acl_permission(inode, acl, mask);
-		posix_acl_release(acl);
-		return ret;
-	}
-
-	return -EAGAIN;
+	return acl;
 }
 
 int ocfs2_acl_chmod(struct inode *inode)
 {
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	struct posix_acl *acl, *clone;
+	struct posix_acl *acl;
 	int ret;
 
 	if (S_ISLNK(inode->i_mode))
@@ -342,15 +327,12 @@ int ocfs2_acl_chmod(struct inode *inode)
 	acl = ocfs2_get_acl(inode, ACL_TYPE_ACCESS);
 	if (IS_ERR(acl) || !acl)
 		return PTR_ERR(acl);
-	clone = posix_acl_clone(acl, GFP_KERNEL);
+	ret = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+	if (ret)
+		return ret;
+	ret = ocfs2_set_acl(NULL, inode, NULL, ACL_TYPE_ACCESS,
+			    acl, NULL, NULL);
 	posix_acl_release(acl);
-	if (!clone)
-		return -ENOMEM;
-	ret = posix_acl_chmod_masq(clone, inode->i_mode);
-	if (!ret)
-		ret = ocfs2_set_acl(NULL, inode, NULL, ACL_TYPE_ACCESS,
-				    clone, NULL, NULL);
-	posix_acl_release(clone);
 	return ret;
 }
 
@@ -369,7 +351,7 @@ int ocfs2_init_acl(handle_t *handle,
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct posix_acl *acl = NULL;
 	int ret = 0, ret2;
-	mode_t mode;
+	umode_t mode;
 
 	if (!S_ISLNK(inode->i_mode)) {
 		if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
@@ -388,8 +370,6 @@ int ocfs2_init_acl(handle_t *handle,
 		}
 	}
 	if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) {
-		struct posix_acl *clone;
-
 		if (S_ISDIR(inode->i_mode)) {
 			ret = ocfs2_set_acl(handle, inode, di_bh,
 					    ACL_TYPE_DEFAULT, acl,
@@ -397,27 +377,22 @@ int ocfs2_init_acl(handle_t *handle,
 			if (ret)
 				goto cleanup;
 		}
-		clone = posix_acl_clone(acl, GFP_NOFS);
-		ret = -ENOMEM;
-		if (!clone)
-			goto cleanup;
-
 		mode = inode->i_mode;
-		ret = posix_acl_create_masq(clone, &mode);
-		if (ret >= 0) {
-			ret2 = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
-			if (ret2) {
-				mlog_errno(ret2);
-				ret = ret2;
-				goto cleanup;
-			}
-			if (ret > 0) {
-				ret = ocfs2_set_acl(handle, inode,
-						    di_bh, ACL_TYPE_ACCESS,
-						    clone, meta_ac, data_ac);
-			}
+		ret = posix_acl_create(&acl, GFP_NOFS, &mode);
+		if (ret < 0)
+			return ret;
+
+		ret2 = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
+		if (ret2) {
+			mlog_errno(ret2);
+			ret = ret2;
+			goto cleanup;
+		}
+		if (ret > 0) {
+			ret = ocfs2_set_acl(handle, inode,
+					    di_bh, ACL_TYPE_ACCESS,
+					    acl, meta_ac, data_ac);
 		}
-		posix_acl_release(clone);
 	}
 cleanup:
 	posix_acl_release(acl);
diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h
index 4fe7c9c..071fbd38 100644
--- a/fs/ocfs2/acl.h
+++ b/fs/ocfs2/acl.h
@@ -26,7 +26,7 @@ struct ocfs2_acl_entry {
 	__le32 e_id;
 };
 
-extern int ocfs2_check_acl(struct inode *, int, unsigned int);
+struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type);
 extern int ocfs2_acl_chmod(struct inode *);
 extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *,
 			  struct buffer_head *, struct buffer_head *,
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index ac97bca..c1efe93 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -551,9 +551,8 @@ bail:
 
 /*
  * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
- * particularly interested in the aio/dio case.  Like the core uses
- * i_alloc_sem, we use the rw_lock DLM lock to protect io on one node from
- * truncation on another.
+ * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
+ * to protect io on one node from truncation on another.
  */
 static void ocfs2_dio_end_io(struct kiocb *iocb,
 			     loff_t offset,
@@ -568,10 +567,8 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 	/* this io's submitter should not have unlocked this before we could */
 	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
 
-	if (ocfs2_iocb_is_sem_locked(iocb)) {
-		up_read(&inode->i_alloc_sem);
+	if (ocfs2_iocb_is_sem_locked(iocb))
 		ocfs2_iocb_clear_sem_locked(iocb);
-	}
 
 	ocfs2_iocb_clear_rw_locked(iocb);
 
@@ -580,6 +577,7 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 
 	if (is_async)
 		aio_complete(iocb, ret, 0);
+	inode_dio_done(inode);
 }
 
 /*
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index b1e35a3..de4ea1a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -171,7 +171,8 @@ static int ocfs2_dir_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int ocfs2_sync_file(struct file *file, int datasync)
+static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
+			   int datasync)
 {
 	int err = 0;
 	journal_t *journal;
@@ -184,6 +185,16 @@ static int ocfs2_sync_file(struct file *file, int datasync)
 			      file->f_path.dentry->d_name.name,
 			      (unsigned long long)datasync);
 
+	err = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (err)
+		return err;
+
+	/*
+	 * Probably don't need the i_mutex at all in here, just putting it here
+	 * to be consistent with how fsync used to be called, someone more
+	 * familiar with the fs could possibly remove it.
+	 */
+	mutex_lock(&inode->i_mutex);
 	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) {
 		/*
 		 * We still have to flush drive's caches to get data to the
@@ -200,6 +211,7 @@ static int ocfs2_sync_file(struct file *file, int datasync)
 bail:
 	if (err)
 		mlog_errno(err);
+	mutex_unlock(&inode->i_mutex);
 
 	return (err < 0) ? -EIO : 0;
 }
@@ -1142,6 +1154,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		if (status)
 			goto bail_unlock;
 
+		inode_dio_wait(inode);
+
 		if (i_size_read(inode) > attr->ia_size) {
 			if (ocfs2_should_order_data(inode)) {
 				status = ocfs2_begin_ordered_truncate(inode,
@@ -1279,11 +1293,11 @@ bail:
 	return err;
 }
 
-int ocfs2_permission(struct inode *inode, int mask, unsigned int flags)
+int ocfs2_permission(struct inode *inode, int mask)
 {
 	int ret;
 
-	if (flags & IPERM_FLAG_RCU)
+	if (mask & MAY_NOT_BLOCK)
 		return -ECHILD;
 
 	ret = ocfs2_inode_lock(inode, NULL, 0);
@@ -1293,7 +1307,7 @@ int ocfs2_permission(struct inode *inode, int mask, unsigned int flags)
 		goto out;
 	}
 
-	ret = generic_permission(inode, mask, flags, ocfs2_check_acl);
+	ret = generic_permission(inode, mask);
 
 	ocfs2_inode_unlock(inode, 0);
 out:
@@ -2236,9 +2250,8 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 	ocfs2_iocb_clear_sem_locked(iocb);
 
 relock:
-	/* to match setattr's i_mutex -> i_alloc_sem -> rw_lock ordering */
+	/* to match setattr's i_mutex -> rw_lock ordering */
 	if (direct_io) {
-		down_read(&inode->i_alloc_sem);
 		have_alloc_sem = 1;
 		/* communicate with ocfs2_dio_end_io */
 		ocfs2_iocb_set_sem_locked(iocb);
@@ -2290,7 +2303,6 @@ relock:
 	 */
 	if (direct_io && !can_do_direct) {
 		ocfs2_rw_unlock(inode, rw_level);
-		up_read(&inode->i_alloc_sem);
 
 		have_alloc_sem = 0;
 		rw_level = -1;
@@ -2361,8 +2373,7 @@ out_dio:
 	/*
 	 * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
 	 * function pointer which is called when o_direct io completes so that
-	 * it can unlock our rw lock.  (it's the clustered equivalent of
-	 * i_alloc_sem; protects truncate from racing with pending ios).
+	 * it can unlock our rw lock.
 	 * Unfortunately there are error cases which call end_io and others
 	 * that don't.  so we don't have to unlock the rw_lock if either an
 	 * async dio is going to do it in the future or an end_io after an
@@ -2378,10 +2389,8 @@ out:
 		ocfs2_rw_unlock(inode, rw_level);
 
 out_sems:
-	if (have_alloc_sem) {
-		up_read(&inode->i_alloc_sem);
+	if (have_alloc_sem)
 		ocfs2_iocb_clear_sem_locked(iocb);
-	}
 
 	mutex_unlock(&inode->i_mutex);
 
@@ -2531,7 +2540,6 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 	 * need locks to protect pending reads from racing with truncate.
 	 */
 	if (filp->f_flags & O_DIRECT) {
-		down_read(&inode->i_alloc_sem);
 		have_alloc_sem = 1;
 		ocfs2_iocb_set_sem_locked(iocb);
 
@@ -2574,10 +2582,9 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 	}
 
 bail:
-	if (have_alloc_sem) {
-		up_read(&inode->i_alloc_sem);
+	if (have_alloc_sem)
 		ocfs2_iocb_clear_sem_locked(iocb);
-	}
+
 	if (rw_level != -1)
 		ocfs2_rw_unlock(inode, rw_level);
 
@@ -2593,12 +2600,14 @@ const struct inode_operations ocfs2_file_iops = {
 	.listxattr	= ocfs2_listxattr,
 	.removexattr	= generic_removexattr,
 	.fiemap		= ocfs2_fiemap,
+	.get_acl	= ocfs2_iop_get_acl,
 };
 
 const struct inode_operations ocfs2_special_file_iops = {
 	.setattr	= ocfs2_setattr,
 	.getattr	= ocfs2_getattr,
 	.permission	= ocfs2_permission,
+	.get_acl	= ocfs2_iop_get_acl,
 };
 
 /*
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index f5afbbe..97bf761 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -61,7 +61,7 @@ int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat);
-int ocfs2_permission(struct inode *inode, int mask, unsigned int flags);
+int ocfs2_permission(struct inode *inode, int mask);
 
 int ocfs2_should_update_atime(struct inode *inode,
 			      struct vfsmount *vfsmnt);
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index cd94270..d53cb70 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -36,7 +36,6 @@
 #include "dir.h"
 #include "buffer_head_io.h"
 #include "sysfile.h"
-#include "suballoc.h"
 #include "refcounttree.h"
 #include "move_extents.h"
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index e5d738c..53aa41e 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -2498,4 +2498,5 @@ const struct inode_operations ocfs2_dir_iops = {
 	.listxattr	= ocfs2_listxattr,
 	.removexattr	= generic_removexattr,
 	.fiemap         = ocfs2_fiemap,
+	.get_acl	= ocfs2_iop_get_acl,
 };
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index ebfd382..cf78233 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4368,25 +4368,6 @@ static inline int ocfs2_may_create(struct inode *dir, struct dentry *child)
 	return inode_permission(dir, MAY_WRITE | MAY_EXEC);
 }
 
-/* copied from user_path_parent. */
-static int ocfs2_user_path_parent(const char __user *path,
-				  struct nameidata *nd, char **name)
-{
-	char *s = getname(path);
-	int error;
-
-	if (IS_ERR(s))
-		return PTR_ERR(s);
-
-	error = kern_path_parent(s, nd);
-	if (error)
-		putname(s);
-	else
-		*name = s;
-
-	return error;
-}
-
 /**
  * ocfs2_vfs_reflink - Create a reference-counted link
  *
@@ -4460,10 +4441,8 @@ int ocfs2_reflink_ioctl(struct inode *inode,
 			bool preserve)
 {
 	struct dentry *new_dentry;
-	struct nameidata nd;
-	struct path old_path;
+	struct path old_path, new_path;
 	int error;
-	char *to = NULL;
 
 	if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb)))
 		return -EOPNOTSUPP;
@@ -4474,39 +4453,33 @@ int ocfs2_reflink_ioctl(struct inode *inode,
 		return error;
 	}
 
-	error = ocfs2_user_path_parent(newname, &nd, &to);
-	if (error) {
+	new_dentry = user_path_create(AT_FDCWD, newname, &new_path, 0);
+	error = PTR_ERR(new_dentry);
+	if (IS_ERR(new_dentry)) {
 		mlog_errno(error);
 		goto out;
 	}
 
 	error = -EXDEV;
-	if (old_path.mnt != nd.path.mnt)
-		goto out_release;
-	new_dentry = lookup_create(&nd, 0);
-	error = PTR_ERR(new_dentry);
-	if (IS_ERR(new_dentry)) {
+	if (old_path.mnt != new_path.mnt) {
 		mlog_errno(error);
-		goto out_unlock;
+		goto out_dput;
 	}
 
-	error = mnt_want_write(nd.path.mnt);
+	error = mnt_want_write(new_path.mnt);
 	if (error) {
 		mlog_errno(error);
 		goto out_dput;
 	}
 
 	error = ocfs2_vfs_reflink(old_path.dentry,
-				  nd.path.dentry->d_inode,
+				  new_path.dentry->d_inode,
 				  new_dentry, preserve);
-	mnt_drop_write(nd.path.mnt);
+	mnt_drop_write(new_path.mnt);
 out_dput:
 	dput(new_dentry);
-out_unlock:
-	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
-out_release:
-	path_put(&nd.path);
-	putname(to);
+	mutex_unlock(&new_path.dentry->d_inode->i_mutex);
+	path_put(&new_path);
 out:
 	path_put(&old_path);