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
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
ulist.h
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Copyright (C) 2011 STRATO AG
 * written by Arne Jansen <sensille@gmx.net>
 */

#ifndef BTRFS_ULIST_H
#define BTRFS_ULIST_H

#include <linux/list.h>
#include <linux/rbtree.h>

/*
 * ulist is a generic data structure to hold a collection of unique u64
 * values. The only operations it supports is adding to the list and
 * enumerating it.
 * It is possible to store an auxiliary value along with the key.
 *
 */
struct ulist_iterator {
	struct list_head *cur_list;  /* hint to start search */
};

/*
 * element of the list
 */
struct ulist_node {
	u64 val;		/* value to store */
	u64 aux;		/* auxiliary value saved along with the val */

	struct list_head list;  /* used to link node */
	struct rb_node rb_node;	/* used to speed up search */
};

struct ulist {
	/*
	 * number of elements stored in list
	 */
	unsigned long nnodes;

	struct list_head nodes;
	struct rb_root root;
};

void ulist_init(struct ulist *ulist);
void ulist_release(struct ulist *ulist);
void ulist_reinit(struct ulist *ulist);
struct ulist *ulist_alloc(gfp_t gfp_mask);
void ulist_free(struct ulist *ulist);
int ulist_add(struct ulist *ulist, u64 val, u64 aux, gfp_t gfp_mask);
int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux,
		    u64 *old_aux, gfp_t gfp_mask);
int ulist_del(struct ulist *ulist, u64 val, u64 aux);

/* just like ulist_add_merge() but take a pointer for the aux data */
static inline int ulist_add_merge_ptr(struct ulist *ulist, u64 val, void *aux,
				      void **old_aux, gfp_t gfp_mask)
{
#if BITS_PER_LONG == 32
	u64 old64 = (uintptr_t)*old_aux;
	int ret = ulist_add_merge(ulist, val, (uintptr_t)aux, &old64, gfp_mask);
	*old_aux = (void *)((uintptr_t)old64);
	return ret;
#else
	return ulist_add_merge(ulist, val, (u64)aux, (u64 *)old_aux, gfp_mask);
#endif
}

struct ulist_node *ulist_next(struct ulist *ulist,
			      struct ulist_iterator *uiter);

#define ULIST_ITER_INIT(uiter) ((uiter)->cur_list = NULL)

#endif
back to top