summaryrefslogtreecommitdiffstats
path: root/fs/libfs.c
diff options
context:
space:
mode:
authornpiggin@suse.de <npiggin@suse.de>2010-05-27 01:05:33 +1000
committerAl Viro <viro@zeniv.linux.org.uk>2010-05-27 22:15:33 -0400
commit7bb46a6734a7e1ad4beaecc11cae7ed3ff81d30f (patch)
treee575d9c55e2a6ccc645dcb3ae2564de458b428f2 /fs/libfs.c
parent7000d3c424e5bb350e502a477fb0e1ed42f8b10e (diff)
downloadlinux-7bb46a6734a7e1ad4beaecc11cae7ed3ff81d30f.tar.gz
linux-7bb46a6734a7e1ad4beaecc11cae7ed3ff81d30f.tar.bz2
linux-7bb46a6734a7e1ad4beaecc11cae7ed3ff81d30f.zip
fs: introduce new truncate sequence
Introduce a new truncate calling sequence into fs/mm subsystems. Rather than setattr > vmtruncate > truncate, have filesystems call their truncate sequence from ->setattr if filesystem specific operations are required. vmtruncate is deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced previously should be used. simple_setattr is introduced for simple in-ram filesystems to implement the new truncate sequence. Eventually all filesystems should be converted to implement a setattr, and the default code in notify_change should go away. simple_setsize is also introduced to perform just the ATTR_SIZE portion of simple_setattr (ie. changing i_size and trimming pagecache). To implement the new truncate sequence: - filesystem specific manipulations (eg freeing blocks) must be done in the setattr method rather than ->truncate. - vmtruncate can not be used by core code to trim blocks past i_size in the event of write failure after allocation, so this must be performed in the fs code. - convert usage of helpers block_write_begin, nobh_write_begin, cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed variants. These avoid calling vmtruncate to trim blocks (see previous). - inode_setattr should not be used. generic_setattr is a new function to be used to copy simple attributes into the generic inode. - make use of the better opportunity to handle errors with the new sequence. Big problem with the previous calling sequence: the filesystem is not called until i_size has already changed. This means it is not allowed to fail the call, and also it does not know what the previous i_size was. Also, generic code calling vmtruncate to truncate allocated blocks in case of error had no good way to return a meaningful error (or, for example, atomically handle block deallocation). Cc: Christoph Hellwig <hch@lst.de> Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Diffstat (limited to 'fs/libfs.c')
-rw-r--r--fs/libfs.c76
1 files changed, 76 insertions, 0 deletions
diff --git a/fs/libfs.c b/fs/libfs.c
index b84d0a7a2204..09e1016eb774 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -8,6 +8,7 @@
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/vfs.h>
+#include <linux/quotaops.h>
#include <linux/mutex.h>
#include <linux/exportfs.h>
#include <linux/writeback.h>
@@ -325,6 +326,81 @@ int simple_rename(struct inode *old_dir, struct dentry *old_dentry,
return 0;
}
+/**
+ * simple_setsize - handle core mm and vfs requirements for file size change
+ * @inode: inode
+ * @newsize: new file size
+ *
+ * Returns 0 on success, -error on failure.
+ *
+ * simple_setsize must be called with inode_mutex held.
+ *
+ * simple_setsize will check that the requested new size is OK (see
+ * inode_newsize_ok), and then will perform the necessary i_size update
+ * and pagecache truncation (if necessary). It will be typically be called
+ * from the filesystem's setattr function when ATTR_SIZE is passed in.
+ *
+ * The inode itself must have correct permissions and attributes to allow
+ * i_size to be changed, this function then just checks that the new size
+ * requested is valid.
+ *
+ * In the case of simple in-memory filesystems with inodes stored solely
+ * in the inode cache, and file data in the pagecache, nothing more needs
+ * to be done to satisfy a truncate request. Filesystems with on-disk
+ * blocks for example will need to free them in the case of truncate, in
+ * that case it may be easier not to use simple_setsize (but each of its
+ * components will likely be required at some point to update pagecache
+ * and inode etc).
+ */
+int simple_setsize(struct inode *inode, loff_t newsize)
+{
+ loff_t oldsize;
+ int error;
+
+ error = inode_newsize_ok(inode, newsize);
+ if (error)
+ return error;
+
+ oldsize = inode->i_size;
+ i_size_write(inode, newsize);
+ truncate_pagecache(inode, oldsize, newsize);
+
+ return error;
+}
+EXPORT_SYMBOL(simple_setsize);
+
+/**
+ * simple_setattr - setattr for simple in-memory filesystem
+ * @dentry: dentry
+ * @iattr: iattr structure
+ *
+ * Returns 0 on success, -error on failure.
+ *
+ * simple_setattr implements setattr for an in-memory filesystem which
+ * does not store its own file data or metadata (eg. uses the page cache
+ * and inode cache as its data store).
+ */
+int simple_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+ struct inode *inode = dentry->d_inode;
+ int error;
+
+ error = inode_change_ok(inode, iattr);
+ if (error)
+ return error;
+
+ if (iattr->ia_valid & ATTR_SIZE) {
+ error = simple_setsize(inode, iattr->ia_size);
+ if (error)
+ return error;
+ }
+
+ generic_setattr(inode, iattr);
+
+ return error;
+}
+EXPORT_SYMBOL(simple_setattr);
+
int simple_readpage(struct file *file, struct page *page)
{
clear_highpage(page);