linux/fs, branch v3.12.4

aio: clean up aio ring in the fail path

2013-12-08T15:29:17Z

commit d1b9432712a25eeb06114fb4b587133525a47de5 upstream. Clean up the aio ring file in the fail path of aio_setup_ring and ioctx_alloc. And maybe it can fix the GPF issue reported by Dave Jones: https://lkml.org/lkml/2013/11/25/898 Signed-off-by: Gu Zheng Signed-off-by: Benjamin LaHaise Signed-off-by: Greg Kroah-Hartman

aio: nullify aio->ring_pages after freeing it

2013-12-08T15:29:17Z

commit ddb8c45ba15149ebd41d7586261c05f7ca37f9a1 upstream. After freeing ring_pages we leave it as is causing a dangling pointer. This has already caused an issue so to help catching any issues in the future NULL it out. Signed-off-by: Sasha Levin Signed-off-by: Benjamin LaHaise Signed-off-by: Greg Kroah-Hartman

aio: prevent double free in ioctx_alloc

2013-12-08T15:29:16Z

commit d558023207e008a4476a3b7bb8706b2a2bf5d84f upstream. ioctx_alloc() calls aio_setup_ring() to allocate a ring. If aio_setup_ring() fails to do so it would call aio_free_ring() before returning, but ioctx_alloc() would call aio_free_ring() again causing a double free of the ring. This is easily reproducible from userspace. Signed-off-by: Sasha Levin Signed-off-by: Benjamin LaHaise Signed-off-by: Greg Kroah-Hartman

aio: checking for NULL instead of IS_ERR

2013-12-08T15:29:16Z

commit 7f62656be8a8ef14c168db2d98021fb9c8cc1076 upstream. alloc_anon_inode() returns an ERR_PTR(), it doesn't return NULL. Fixes: 71ad7490c1f3 ('rework aio migrate pages to use aio fs') Signed-off-by: Dan Carpenter Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman

rework aio migrate pages to use aio fs

2013-12-08T15:29:16Z

commit 71ad7490c1f32bd7829df76360f9fa17829868f3 upstream. Don't abuse anon_inodes.c to host private files needed by aio; we can bloody well declare a mini-fs of our own instead of patching up what anon_inodes can create for us. Tested-by: Benjamin LaHaise Acked-by: Benjamin LaHaise Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman

take anon inode allocation to libfs.c

2013-12-08T15:29:16Z

commit 6987843ff7e836ea65b554905aec34d2fad05c94 upstream. Signed-off-by: Al Viro Cc: Benjamin LaHaise Signed-off-by: Greg Kroah-Hartman

aio: Fix a trinity splat

2013-12-08T15:29:16Z

commit e34ecee2ae791df674dfb466ce40692ca6218e43 upstream. aio kiocb refcounting was broken - it was relying on keeping track of the number of available ring buffer entries, which it needs to do anyways; then at shutdown time it'd wait for completions to be delivered until the # of available ring buffer entries equalled what it was initialized to. Problem with that is that the ring buffer is mapped writable into userspace, so userspace could futz with the head and tail pointers to cause the kernel to see extra completions, and cause free_ioctx() to return while there were still outstanding kiocbs. Which would be bad. Fix is just to directly refcount the kiocbs - which is more straightforward, and with the new percpu refcounting code doesn't cost us any cacheline bouncing which was the whole point of the original scheme. Also clean up ioctx_alloc()'s error path and fix a bug where it wasn't subtracting from aio_nr if ioctx_add_table() failed. Signed-off-by: Kent Overstreet Cc: Benjamin LaHaise Signed-off-by: Greg Kroah-Hartman

xfs: add capability check to free eofblocks ioctl

2013-12-08T15:29:15Z

commit 8c567a7fab6e086a0284eee2db82348521e7120c upstream. Check for CAP_SYS_ADMIN since the caller can truncate preallocated blocks from files they do not own nor have write access to. A more fine grained access check was considered: require the caller to specify their own uid/gid and to use inode_permission to check for write, but this would not catch the case of an inode not reachable via path traversal from the callers mount namespace. Add check for read-only filesystem to free eofblocks ioctl. Reviewed-by: Brian Foster Reviewed-by: Dave Chinner Reviewed-by: Gao feng Signed-off-by: Dwight Engen Signed-off-by: Ben Myers Cc: Kees Cook Signed-off-by: Greg Kroah-Hartman

GFS2: Fix ref count bug relating to atomic_open

2013-12-04T19:06:16Z

commit ea0341e071527d5cec350917b01ab901af09d758 upstream. In the case that atomic_open calls finish_no_open() with the dentry that was supplied to gfs2_atomic_open() an extra reference count is required. This patch fixes that issue preventing a bug trap triggering at umount time. Signed-off-by: Steven Whitehouse Signed-off-by: Greg Kroah-Hartman

setfacl removes part of ACL when setting POSIX ACLs to Samba

2013-12-04T19:05:53Z

commit b1d93356427be6f050dc55c86eb019d173700af6 upstream. setfacl over cifs mounts can remove the default ACL when setting the (non-default part of) the ACL and vice versa (we were leaving at 0 rather than setting to -1 the count field for the unaffected half of the ACL. For example notice the setfacl removed the default ACL in this sequence: steven@steven-GA-970A-DS3:~/cifs-2.6$ getfacl /mnt/test-dir ; setfacl -m default:user:test:rwx,user:test:rwx /mnt/test-dir getfacl: Removing leading '/' from absolute path names user::rwx group::r-x other::r-x default:user::rwx default:user:test:rwx default:group::r-x default:mask::rwx default:other::r-x steven@steven-GA-970A-DS3:~/cifs-2.6$ getfacl /mnt/test-dir getfacl: Removing leading '/' from absolute path names user::rwx user:test:rwx group::r-x mask::rwx other::r-x Signed-off-by: Steve French Acked-by: Jeremy Allison Signed-off-by: Greg Kroah-Hartman