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
io.c
/*
* Copyright (c) 2016 Trond Myklebust
*
* I/O and data path helper functionality.
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/rwsem.h>
#include <linux/fs.h>
#include <linux/nfs_fs.h>
#include "internal.h"
/* Call with exclusively locked inode->i_rwsem */
static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode)
{
if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
inode_dio_wait(inode);
}
}
/**
* nfs_start_io_read - declare the file is being used for buffered reads
* @inode - file inode
*
* Declare that a buffered read operation is about to start, and ensure
* that we block all direct I/O.
* On exit, the function ensures that the NFS_INO_ODIRECT flag is unset,
* and holds a shared lock on inode->i_rwsem to ensure that the flag
* cannot be changed.
* In practice, this means that buffered read operations are allowed to
* execute in parallel, thanks to the shared lock, whereas direct I/O
* operations need to wait to grab an exclusive lock in order to set
* NFS_INO_ODIRECT.
* Note that buffered writes and truncates both take a write lock on
* inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
*/
void
nfs_start_io_read(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
/* Be an optimist! */
down_read(&inode->i_rwsem);
if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0)
return;
up_read(&inode->i_rwsem);
/* Slow path.... */
down_write(&inode->i_rwsem);
nfs_block_o_direct(nfsi, inode);
downgrade_write(&inode->i_rwsem);
}
/**
* nfs_end_io_read - declare that the buffered read operation is done
* @inode - file inode
*
* Declare that a buffered read operation is done, and release the shared
* lock on inode->i_rwsem.
*/
void
nfs_end_io_read(struct inode *inode)
{
up_read(&inode->i_rwsem);
}
/**
* nfs_start_io_write - declare the file is being used for buffered writes
* @inode - file inode
*
* Declare that a buffered read operation is about to start, and ensure
* that we block all direct I/O.
*/
void
nfs_start_io_write(struct inode *inode)
{
down_write(&inode->i_rwsem);
nfs_block_o_direct(NFS_I(inode), inode);
}
/**
* nfs_end_io_write - declare that the buffered write operation is done
* @inode - file inode
*
* Declare that a buffered write operation is done, and release the
* lock on inode->i_rwsem.
*/
void
nfs_end_io_write(struct inode *inode)
{
up_write(&inode->i_rwsem);
}
/* Call with exclusively locked inode->i_rwsem */
static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode)
{
if (!test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
set_bit(NFS_INO_ODIRECT, &nfsi->flags);
nfs_wb_all(inode);
}
}
/**
* nfs_end_io_direct - declare the file is being used for direct i/o
* @inode - file inode
*
* Declare that a direct I/O operation is about to start, and ensure
* that we block all buffered I/O.
* On exit, the function ensures that the NFS_INO_ODIRECT flag is set,
* and holds a shared lock on inode->i_rwsem to ensure that the flag
* cannot be changed.
* In practice, this means that direct I/O operations are allowed to
* execute in parallel, thanks to the shared lock, whereas buffered I/O
* operations need to wait to grab an exclusive lock in order to clear
* NFS_INO_ODIRECT.
* Note that buffered writes and truncates both take a write lock on
* inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
*/
void
nfs_start_io_direct(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
/* Be an optimist! */
down_read(&inode->i_rwsem);
if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) != 0)
return;
up_read(&inode->i_rwsem);
/* Slow path.... */
down_write(&inode->i_rwsem);
nfs_block_buffered(nfsi, inode);
downgrade_write(&inode->i_rwsem);
}
/**
* nfs_end_io_direct - declare that the direct i/o operation is done
* @inode - file inode
*
* Declare that a direct I/O operation is done, and release the shared
* lock on inode->i_rwsem.
*/
void
nfs_end_io_direct(struct inode *inode)
{
up_read(&inode->i_rwsem);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...