Revision 9a291a7c9428155e8e623e4a3989f8be47134df5 authored by James Morse on 02 June 2017, 21:46:46 UTC, committed by Linus Torvalds on 02 June 2017, 22:07:38 UTC
KVM uses get_user_pages() to resolve its stage2 faults. KVM sets the FOLL_HWPOISON flag causing faultin_page() to return -EHWPOISON when it finds a VM_FAULT_HWPOISON. KVM handles these hwpoison pages as a special case. (check_user_page_hwpoison()) When huge pages are involved, this doesn't work so well. get_user_pages() calls follow_hugetlb_page(), which stops early if it receives VM_FAULT_HWPOISON from hugetlb_fault(), eventually returning -EFAULT to the caller. The step to map this to -EHWPOISON based on the FOLL_ flags is missing. The hwpoison special case is skipped, and -EFAULT is returned to user-space, causing Qemu or kvmtool to exit. Instead, move this VM_FAULT_ to errno mapping code into a header file and use it from faultin_page() and follow_hugetlb_page(). With this, KVM works as expected. This isn't a problem for arm64 today as we haven't enabled MEMORY_FAILURE, but I can't see any reason this doesn't happen on x86 too, so I think this should be a fix. This doesn't apply earlier than stable's v4.11.1 due to all sorts of cleanup. [james.morse@arm.com: add vm_fault_to_errno() call to faultin_page()] suggested. Link: http://lkml.kernel.org/r/20170525171035.16359-1-james.morse@arm.com [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20170524160900.28786-1-james.morse@arm.com Signed-off-by: James Morse <james.morse@arm.com> Acked-by: Punit Agrawal <punit.agrawal@arm.com> Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: <stable@vger.kernel.org> [4.11.1+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 70feee0
export.c
/*
* Squashfs - a compressed read only filesystem for Linux
*
* Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
* Phillip Lougher <phillip@squashfs.org.uk>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version 2,
* or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* export.c
*/
/*
* This file implements code to make Squashfs filesystems exportable (NFS etc.)
*
* The export code uses an inode lookup table to map inode numbers passed in
* filehandles to an inode location on disk. This table is stored compressed
* into metadata blocks. A second index table is used to locate these. This
* second index table for speed of access (and because it is small) is read at
* mount time and cached in memory.
*
* The inode lookup table is used only by the export code, inode disk
* locations are directly encoded in directories, enabling direct access
* without an intermediate lookup for all operations except the export ops.
*/
#include <linux/fs.h>
#include <linux/vfs.h>
#include <linux/dcache.h>
#include <linux/exportfs.h>
#include <linux/slab.h>
#include "squashfs_fs.h"
#include "squashfs_fs_sb.h"
#include "squashfs_fs_i.h"
#include "squashfs.h"
/*
* Look-up inode number (ino) in table, returning the inode location.
*/
static long long squashfs_inode_lookup(struct super_block *sb, int ino_num)
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
int blk = SQUASHFS_LOOKUP_BLOCK(ino_num - 1);
int offset = SQUASHFS_LOOKUP_BLOCK_OFFSET(ino_num - 1);
u64 start = le64_to_cpu(msblk->inode_lookup_table[blk]);
__le64 ino;
int err;
TRACE("Entered squashfs_inode_lookup, inode_number = %d\n", ino_num);
err = squashfs_read_metadata(sb, &ino, &start, &offset, sizeof(ino));
if (err < 0)
return err;
TRACE("squashfs_inode_lookup, inode = 0x%llx\n",
(u64) le64_to_cpu(ino));
return le64_to_cpu(ino);
}
static struct dentry *squashfs_export_iget(struct super_block *sb,
unsigned int ino_num)
{
long long ino;
struct dentry *dentry = ERR_PTR(-ENOENT);
TRACE("Entered squashfs_export_iget\n");
ino = squashfs_inode_lookup(sb, ino_num);
if (ino >= 0)
dentry = d_obtain_alias(squashfs_iget(sb, ino, ino_num));
return dentry;
}
static struct dentry *squashfs_fh_to_dentry(struct super_block *sb,
struct fid *fid, int fh_len, int fh_type)
{
if ((fh_type != FILEID_INO32_GEN && fh_type != FILEID_INO32_GEN_PARENT)
|| fh_len < 2)
return NULL;
return squashfs_export_iget(sb, fid->i32.ino);
}
static struct dentry *squashfs_fh_to_parent(struct super_block *sb,
struct fid *fid, int fh_len, int fh_type)
{
if (fh_type != FILEID_INO32_GEN_PARENT || fh_len < 4)
return NULL;
return squashfs_export_iget(sb, fid->i32.parent_ino);
}
static struct dentry *squashfs_get_parent(struct dentry *child)
{
struct inode *inode = d_inode(child);
unsigned int parent_ino = squashfs_i(inode)->parent;
return squashfs_export_iget(inode->i_sb, parent_ino);
}
/*
* Read uncompressed inode lookup table indexes off disk into memory
*/
__le64 *squashfs_read_inode_lookup_table(struct super_block *sb,
u64 lookup_table_start, u64 next_table, unsigned int inodes)
{
unsigned int length = SQUASHFS_LOOKUP_BLOCK_BYTES(inodes);
__le64 *table;
TRACE("In read_inode_lookup_table, length %d\n", length);
/* Sanity check values */
/* there should always be at least one inode */
if (inodes == 0)
return ERR_PTR(-EINVAL);
/* length bytes should not extend into the next table - this check
* also traps instances where lookup_table_start is incorrectly larger
* than the next table start
*/
if (lookup_table_start + length > next_table)
return ERR_PTR(-EINVAL);
table = squashfs_read_table(sb, lookup_table_start, length);
/*
* table[0] points to the first inode lookup table metadata block,
* this should be less than lookup_table_start
*/
if (!IS_ERR(table) && le64_to_cpu(table[0]) >= lookup_table_start) {
kfree(table);
return ERR_PTR(-EINVAL);
}
return table;
}
const struct export_operations squashfs_export_ops = {
.fh_to_dentry = squashfs_fh_to_dentry,
.fh_to_parent = squashfs_fh_to_parent,
.get_parent = squashfs_get_parent
};
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...