ipc: use private shmem or hugetlbfs inodes for shm segments.

The shm implementation internally uses shmem or hugetlbfs inodes for shm
segments.  As these inodes are never directly exposed to userspace and
only accessed through the shm operations which are already hooked by
security modules, mark the inodes with the S_PRIVATE flag so that inode
security initialization and permission checking is skipped.

This was motivated by the following lockdep warning:

  ======================================================
   [ INFO: possible circular locking dependency detected ]
   4.2.0-0.rc3.git0.1.fc24.x86_64+debug #1 Tainted: G        W
  -------------------------------------------------------
   httpd/1597 is trying to acquire lock:
   (&ids->rwsem){+++++.}, at: shm_close+0x34/0x130
   but task is already holding lock:
   (&mm->mmap_sem){++++++}, at: SyS_shmdt+0x4b/0x180
   which lock already depends on the new lock.
   the existing dependency chain (in reverse order) is:
   -> #3 (&mm->mmap_sem){++++++}:
        lock_acquire+0xc7/0x270
        __might_fault+0x7a/0xa0
        filldir+0x9e/0x130
        xfs_dir2_block_getdents.isra.12+0x198/0x1c0 [xfs]
        xfs_readdir+0x1b4/0x330 [xfs]
        xfs_file_readdir+0x2b/0x30 [xfs]
        iterate_dir+0x97/0x130
        SyS_getdents+0x91/0x120
        entry_SYSCALL_64_fastpath+0x12/0x76
   -> #2 (&xfs_dir_ilock_class){++++.+}:
        lock_acquire+0xc7/0x270
        down_read_nested+0x57/0xa0
        xfs_ilock+0x167/0x350 [xfs]
        xfs_ilock_attr_map_shared+0x38/0x50 [xfs]
        xfs_attr_get+0xbd/0x190 [xfs]
        xfs_xattr_get+0x3d/0x70 [xfs]
        generic_getxattr+0x4f/0x70
        inode_doinit_with_dentry+0x162/0x670
        sb_finish_set_opts+0xd9/0x230
        selinux_set_mnt_opts+0x35c/0x660
        superblock_doinit+0x77/0xf0
        delayed_superblock_init+0x10/0x20
        iterate_supers+0xb3/0x110
        selinux_complete_init+0x2f/0x40
        security_load_policy+0x103/0x600
        sel_write_load+0xc1/0x750
        __vfs_write+0x37/0x100
        vfs_write+0xa9/0x1a0
        SyS_write+0x58/0xd0
        entry_SYSCALL_64_fastpath+0x12/0x76
  ...

Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Reported-by: Morten Stevens <mstevens@fedoraproject.org>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Eric Paris <eparis@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 5 insertions, 3 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 0cf74df..973c24c 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1010,6 +1010,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out_dentry;
+	if (creat_flags == HUGETLB_SHMFS_INODE)
+		inode->i_flags |= S_PRIVATE;
 
 	file = ERR_PTR(-ENOMEM);
 	if (hugetlb_reserve_pages(inode, 0,
diff --git a/ipc/shm.c b/ipc/shm.c
index 06e5cf2..4aef24d 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -545,7 +545,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 		if  ((shmflg & SHM_NORESERVE) &&
 				sysctl_overcommit_memory != OVERCOMMIT_NEVER)
 			acctflag = VM_NORESERVE;
-		file = shmem_file_setup(name, size, acctflag);
+		file = shmem_kernel_file_setup(name, size, acctflag);
 	}
 	error = PTR_ERR(file);
 	if (IS_ERR(file))
diff --git a/mm/shmem.c b/mm/shmem.c
index 4caf8ed..dbe0c1e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3363,8 +3363,8 @@ put_path:
  * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be
  * 	kernel internal.  There will be NO LSM permission checks against the
  * 	underlying inode.  So users of this interface must do LSM checks at a
- * 	higher layer.  The one user is the big_key implementation.  LSM checks
- * 	are provided at the key level rather than the inode level.
+ *	higher layer.  The users are the big_key and shm implementations.  LSM
+ *	checks are provided at the key or shm level rather than the inode.
  * @name: name for dentry (to be seen in /proc/<pid>/maps
  * @size: size to be set for the file
  * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size