Skip to main content

Browse the archive

Revision 9e368259ad988356c4c95150fafd1a06af095d98 authored by Andrea Arcangeli on 30 November 2018, 22:09:25 UTC, committed by Linus Torvalds on 30 November 2018, 22:56:14 UTC 
userfaultfd: use ENOENT instead of EFAULT if the atomic copy user fails
 
Patch series "userfaultfd shmem updates".

Jann found two bugs in the userfaultfd shmem MAP_SHARED backend: the
lack of the VM_MAYWRITE check and the lack of i_size checks.

Then looking into the above we also fixed the MAP_PRIVATE case.

Hugh by source review also found a data loss source if UFFDIO_COPY is
used on shmem MAP_SHARED PROT_READ mappings (the production usages
incidentally run with PROT_READ|PROT_WRITE, so the data loss couldn't
happen in those production usages like with QEMU).

The whole patchset is marked for stable.

We verified QEMU postcopy live migration with guest running on shmem
MAP_PRIVATE run as well as before after the fix of shmem MAP_PRIVATE.
Regardless if it's shmem or hugetlbfs or MAP_PRIVATE or MAP_SHARED, QEMU
unconditionally invokes a punch hole if the guest mapping is filebacked
and a MADV_DONTNEED too (needed to get rid of the MAP_PRIVATE COWs and
for the anon backend).

This patch (of 5):

We internally used EFAULT to communicate with the caller, switch to
ENOENT, so EFAULT can be used as a non internal retval.

Link: http://lkml.kernel.org/r/20181126173452.26955-2-aarcange@redhat.com
Fixes: 4c27fe4c4c84 ("userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support")
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Hugh Dickins <hughd@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jann Horn <jannh@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: <stable@vger.kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5618cf0
Raw File
pnode.h 
/*
 *  linux/fs/pnode.h
 *
 * (C) Copyright IBM Corporation 2005.
 *	Released under GPL v2.
 *
 */
#ifndef _LINUX_PNODE_H
#define _LINUX_PNODE_H

#include <linux/list.h>
#include "mount.h"

#define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
#define IS_MNT_SLAVE(m) ((m)->mnt_master)
#define IS_MNT_NEW(m)  (!(m)->mnt_ns)
#define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
#define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
#define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
#define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED)
#define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED)
#define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED)

#define CL_EXPIRE    		0x01
#define CL_SLAVE     		0x02
#define CL_COPY_UNBINDABLE	0x04
#define CL_MAKE_SHARED 		0x08
#define CL_PRIVATE 		0x10
#define CL_SHARED_TO_SLAVE	0x20
#define CL_UNPRIVILEGED		0x40
#define CL_COPY_MNT_NS_FILE	0x80

#define CL_COPY_ALL		(CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE)

static inline void set_mnt_shared(struct mount *mnt)
{
	mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK;
	mnt->mnt.mnt_flags |= MNT_SHARED;
}

void change_mnt_propagation(struct mount *, int);
int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
		struct hlist_head *);
int propagate_umount(struct list_head *);
int propagate_mount_busy(struct mount *, int);
void propagate_mount_unlock(struct mount *);
void mnt_release_group_id(struct mount *);
int get_dominating_id(struct mount *mnt, const struct path *root);
unsigned int mnt_get_count(struct mount *mnt);
void mnt_set_mountpoint(struct mount *, struct mountpoint *,
			struct mount *);
void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
			   struct mount *mnt);
struct mount *copy_tree(struct mount *, struct dentry *, int);
bool is_path_reachable(struct mount *, struct dentry *,
			 const struct path *root);
int count_mounts(struct mnt_namespace *ns, struct mount *mnt);
#endif /* _LINUX_PNODE_H */
back to top