aboutsummaryrefslogtreecommitdiff
path: root/fs/open.c
diff options
context:
space:
mode:
authorMiklos Szeredi2016-09-16 12:44:21 +0200
committerMiklos Szeredi2016-09-16 12:44:21 +0200
commit4d0c5ba2ff79ef9f5188998b29fd28fcb05f3667 (patch)
tree3e33b719b0057f9d1364af0e8629d16a64cf05b7 /fs/open.c
parent7b1742eb06ead6d02a6cf3c44587088e5392d1aa (diff)
vfs: do get_write_access() on upper layer of overlayfs
The problem with writecount is: we want consistent handling of it for underlying filesystems as well as overlayfs. Making sure i_writecount is correct on all layers is difficult. Instead this patch makes sure that when write access is acquired, it's always done on the underlying writable layer (called the upper layer). We must also make sure to look at the writecount on this layer when checking for conflicting leases. Open for write already updates the upper layer's writecount. Leaving only truncate. For truncate copy up must happen before get_write_access() so that the writecount is updated on the upper layer. Problem with this is if something fails after that, then copy-up was done needlessly. E.g. if break_lease() was interrupted. Probably not a big deal in practice. Another interesting case is if there's a denywrite on a lower file that is then opened for write or truncated. With this patch these will succeed, which is somewhat counterintuitive. But I think it's still acceptable, considering that the copy-up does actually create a different file, so the old, denywrite mapping won't be touched. On non-overlayfs d_real() is an identity function and d_real_inode() is equivalent to d_inode() so this patch doesn't change behavior in that case. Signed-off-by: Miklos Szeredi <mszeredi@redhat.com> Acked-by: Jeff Layton <jlayton@poochiereds.net> Cc: "J. Bruce Fields" <bfields@fieldses.org>
Diffstat (limited to 'fs/open.c')
-rw-r--r--fs/open.c15
1 files changed, 13 insertions, 2 deletions
diff --git a/fs/open.c b/fs/open.c
index 648fb9d3e97a..8aeb08bb278b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -68,6 +68,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
long vfs_truncate(const struct path *path, loff_t length)
{
struct inode *inode;
+ struct dentry *upperdentry;
long error;
inode = path->dentry->d_inode;
@@ -90,7 +91,17 @@ long vfs_truncate(const struct path *path, loff_t length)
if (IS_APPEND(inode))
goto mnt_drop_write_and_out;
- error = get_write_access(inode);
+ /*
+ * If this is an overlayfs then do as if opening the file so we get
+ * write access on the upper inode, not on the overlay inode. For
+ * non-overlay filesystems d_real() is an identity function.
+ */
+ upperdentry = d_real(path->dentry, NULL, O_WRONLY);
+ error = PTR_ERR(upperdentry);
+ if (IS_ERR(upperdentry))
+ goto mnt_drop_write_and_out;
+
+ error = get_write_access(upperdentry->d_inode);
if (error)
goto mnt_drop_write_and_out;
@@ -109,7 +120,7 @@ long vfs_truncate(const struct path *path, loff_t length)
error = do_truncate(path->dentry, length, 0, NULL);
put_write_and_out:
- put_write_access(inode);
+ put_write_access(upperdentry->d_inode);
mnt_drop_write_and_out:
mnt_drop_write(path->mnt);
out: