mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-13 22:25:03 +00:00
348e967ab0
Currently the handling of huge pages for DAX is racy. For example the
following can happen:
CPU0 (THP write fault) CPU1 (normal read fault)
__dax_pmd_fault() __dax_fault()
get_block(inode, block, &bh, 0) -> not mapped
get_block(inode, block, &bh, 0)
-> not mapped
if (!buffer_mapped(&bh) && write)
get_block(inode, block, &bh, 1) -> allocates blocks
truncate_pagecache_range(inode, lstart, lend);
dax_load_hole();
This results in data corruption since process on CPU1 won't see changes
into the file done by CPU0.
The race can happen even if two normal faults race however with THP the
situation is even worse because the two faults don't operate on the same
entries in the radix tree and we want to use these entries for
serialization. So make THP support in DAX code depend on CONFIG_BROKEN
for now.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
62 lines
2 KiB
C
62 lines
2 KiB
C
#ifndef _LINUX_DAX_H
|
|
#define _LINUX_DAX_H
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <asm/pgtable.h>
|
|
|
|
ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
|
|
get_block_t, dio_iodone_t, int flags);
|
|
int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
|
|
int dax_truncate_page(struct inode *, loff_t from, get_block_t);
|
|
int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
|
|
int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
|
|
|
|
#ifdef CONFIG_FS_DAX
|
|
struct page *read_dax_sector(struct block_device *bdev, sector_t n);
|
|
int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
|
|
unsigned int offset, unsigned int length);
|
|
#else
|
|
static inline struct page *read_dax_sector(struct block_device *bdev,
|
|
sector_t n)
|
|
{
|
|
return ERR_PTR(-ENXIO);
|
|
}
|
|
static inline int __dax_zero_page_range(struct block_device *bdev,
|
|
sector_t sector, unsigned int offset, unsigned int length)
|
|
{
|
|
return -ENXIO;
|
|
}
|
|
#endif
|
|
|
|
#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
|
|
int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
|
|
unsigned int flags, get_block_t);
|
|
int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
|
|
unsigned int flags, get_block_t);
|
|
#else
|
|
static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
|
|
pmd_t *pmd, unsigned int flags, get_block_t gb)
|
|
{
|
|
return VM_FAULT_FALLBACK;
|
|
}
|
|
#define __dax_pmd_fault dax_pmd_fault
|
|
#endif
|
|
int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
|
|
#define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb)
|
|
#define __dax_mkwrite(vma, vmf, gb) __dax_fault(vma, vmf, gb)
|
|
|
|
static inline bool vma_is_dax(struct vm_area_struct *vma)
|
|
{
|
|
return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
|
|
}
|
|
|
|
static inline bool dax_mapping(struct address_space *mapping)
|
|
{
|
|
return mapping->host && IS_DAX(mapping->host);
|
|
}
|
|
|
|
struct writeback_control;
|
|
int dax_writeback_mapping_range(struct address_space *mapping,
|
|
struct block_device *bdev, struct writeback_control *wbc);
|
|
#endif
|