[PATCH] Fix some problems with truncate and mtime semantics.

SUS requires that when truncating a file to the size that it currently
is:
  truncate and ftruncate should NOT modify ctime or mtime
  O_TRUNC SHOULD modify ctime and mtime.

Currently mtime and ctime are always modified on most local
filesystems (side effect of ->truncate) or never modified (on NFS).

With this patch:
  ATTR_CTIME|ATTR_MTIME are sent with ATTR_SIZE precisely when
    an update of these times is required whether size changes or not
    (via a new argument to do_truncate).  This allows NFS to do
    the right thing for O_TRUNC.
  inode_setattr nolonger forces ATTR_MTIME|ATTR_CTIME when the ATTR_SIZE
    sets the size to it's current value.  This allows local filesystems
    to do the right thing for f?truncate.

Also, the logic in inode_setattr is changed a bit so there are two return
points.  One returns the error from vmtruncate if it failed, the other
returns 0 (there can be no other failure).

Finally, if vmtruncate succeeds, and ATTR_SIZE is the only change
requested, we now fall-through and mark_inode_dirty.  If a filesystem did
not have a ->truncate function, then vmtruncate will have changed i_size,
without marking the inode as 'dirty', and I think this is wrong.

Signed-off-by: Neil Brown <neilb@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

5 files changed, 17 insertions, 23 deletions

diff --git a/fs/attr.c b/fs/attr.c
index 67bcd9b14ea580..b34732506f1dcf 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -67,20 +67,12 @@ EXPORT_SYMBOL(inode_change_ok);
 int inode_setattr(struct inode * inode, struct iattr * attr)
 {
 	unsigned int ia_valid = attr->ia_valid;
-	int error = 0;
-
-	if (ia_valid & ATTR_SIZE) {
-		if (attr->ia_size != i_size_read(inode)) {
-			error = vmtruncate(inode, attr->ia_size);
-			if (error || (ia_valid == ATTR_SIZE))
-				goto out;
-		} else {
-			/*
-			 * We skipped the truncate but must still update
-			 * timestamps
-			 */
-			ia_valid |= ATTR_MTIME|ATTR_CTIME;
-		}
+
+	if (ia_valid & ATTR_SIZE &&
+	    attr->ia_size != i_size_read(inode)) {
+		int error = vmtruncate(inode, attr->ia_size);
+		if (error)
+			return error;
 	}
 
 	if (ia_valid & ATTR_UID)
@@ -104,8 +96,8 @@ int inode_setattr(struct inode * inode, struct iattr * attr)
 		inode->i_mode = mode;
 	}
 	mark_inode_dirty(inode);
-out:
-	return error;
+
+	return 0;
 }
 EXPORT_SYMBOL(inode_setattr);
 
diff --git a/fs/exec.c b/fs/exec.c
index e9650cd22a3b9f..2075b674d85e5a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1505,7 +1505,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
 		goto close_fail;
 	if (!file->f_op->write)
 		goto close_fail;
-	if (do_truncate(file->f_dentry, 0, file) != 0)
+	if (do_truncate(file->f_dentry, 0, 0, file) != 0)
 		goto close_fail;
 
 	retval = binfmt->core_dump(signr, regs, file);
diff --git a/fs/namei.c b/fs/namei.c
index 6dbbd42d8b95fb..300eae088d5f8c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1491,7 +1491,7 @@ int may_open(struct nameidata *nd, int acc_mode, int flag)
 		if (!error) {
 			DQUOT_INIT(inode);
 			
-			error = do_truncate(dentry, 0, NULL);
+			error = do_truncate(dentry, 0, ATTR_MTIME|ATTR_CTIME, NULL);
 		}
 		put_write_access(inode);
 		if (error)
diff --git a/fs/open.c b/fs/open.c
index f53a5b9ffb7dce..94968cb3afca02 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -194,7 +194,8 @@ out:
 	return error;
 }
 
-int do_truncate(struct dentry *dentry, loff_t length, struct file *filp)
+int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
+	struct file *filp)
 {
 	int err;
 	struct iattr newattrs;
@@ -204,7 +205,7 @@ int do_truncate(struct dentry *dentry, loff_t length, struct file *filp)
 		return -EINVAL;
 
 	newattrs.ia_size = length;
-	newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
+	newattrs.ia_valid = ATTR_SIZE | time_attrs;
 	if (filp) {
 		newattrs.ia_file = filp;
 		newattrs.ia_valid |= ATTR_FILE;
@@ -266,7 +267,7 @@ static inline long do_sys_truncate(const char __user * path, loff_t length)
 	error = locks_verify_truncate(inode, NULL, length);
 	if (!error) {
 		DQUOT_INIT(inode);
-		error = do_truncate(nd.dentry, length, NULL);
+		error = do_truncate(nd.dentry, length, 0, NULL);
 	}
 	put_write_access(inode);
 
@@ -318,7 +319,7 @@ static inline long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
 
 	error = locks_verify_truncate(inode, file, length);
 	if (!error)
-		error = do_truncate(dentry, length, file);
+		error = do_truncate(dentry, length, 0, file);
 out_putf:
 	fput(file);
 out:
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ef29500b5df896..74c01aabd4ab63 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1344,7 +1344,8 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 
 /* fs/open.c */
 
-extern int do_truncate(struct dentry *, loff_t start, struct file *filp);
+extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
+		       struct file *filp);
 extern long do_sys_open(const char __user *filename, int flags, int mode);
 extern struct file *filp_open(const char *, int, int);
 extern struct file * dentry_open(struct dentry *, struct vfsmount *, int);