2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-27 14:43:58 +08:00
linux-next/include/linux/dax.h
Matthew Wilcox 27359fd6e5 dax: Fix unlock mismatch with updated API
Internal to dax_unlock_mapping_entry(), dax_unlock_entry() is used to
store a replacement entry in the Xarray at the given xas-index with the
DAX_LOCKED bit clear. When called, dax_unlock_entry() expects the unlocked
value of the entry relative to the current Xarray state to be specified.

In most contexts dax_unlock_entry() is operating in the same scope as
the matched dax_lock_entry(). However, in the dax_unlock_mapping_entry()
case the implementation needs to recall the original entry. In the case
where the original entry is a 'pmd' entry it is possible that the pfn
performed to do the lookup is misaligned to the value retrieved in the
Xarray.

Change the api to return the unlock cookie from dax_lock_page() and pass
it to dax_unlock_page(). This fixes a bug where dax_unlock_page() was
assuming that the page was PMD-aligned if the entry was a PMD entry with
signatures like:

 WARNING: CPU: 38 PID: 1396 at fs/dax.c:340 dax_insert_entry+0x2b2/0x2d0
 RIP: 0010:dax_insert_entry+0x2b2/0x2d0
 [..]
 Call Trace:
  dax_iomap_pte_fault.isra.41+0x791/0xde0
  ext4_dax_huge_fault+0x16f/0x1f0
  ? up_read+0x1c/0xa0
  __do_fault+0x1f/0x160
  __handle_mm_fault+0x1033/0x1490
  handle_mm_fault+0x18b/0x3d0

Link: https://lkml.kernel.org/r/20181130154902.GL10377@bombadil.infradead.org
Fixes: 9f32d22130 ("dax: Convert dax_lock_mapping_entry to XArray")
Reported-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Matthew Wilcox <willy@infradead.org>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2018-12-04 21:32:00 -08:00

180 lines
5.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_DAX_H
#define _LINUX_DAX_H
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/radix-tree.h>
#include <asm/pgtable.h>
typedef unsigned long dax_entry_t;
struct iomap_ops;
struct dax_device;
struct dax_operations {
/*
* direct_access: translate a device-relative
* logical-page-offset into an absolute physical pfn. Return the
* number of pages available for DAX at that pfn.
*/
long (*direct_access)(struct dax_device *, pgoff_t, long,
void **, pfn_t *);
/* copy_from_iter: required operation for fs-dax direct-i/o */
size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
struct iov_iter *);
/* copy_to_iter: required operation for fs-dax direct-i/o */
size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t,
struct iov_iter *);
};
extern struct attribute_group dax_attribute_group;
#if IS_ENABLED(CONFIG_DAX)
struct dax_device *dax_get_by_host(const char *host);
struct dax_device *alloc_dax(void *private, const char *host,
const struct dax_operations *ops);
void put_dax(struct dax_device *dax_dev);
void kill_dax(struct dax_device *dax_dev);
void dax_write_cache(struct dax_device *dax_dev, bool wc);
bool dax_write_cache_enabled(struct dax_device *dax_dev);
#else
static inline struct dax_device *dax_get_by_host(const char *host)
{
return NULL;
}
static inline struct dax_device *alloc_dax(void *private, const char *host,
const struct dax_operations *ops)
{
/*
* Callers should check IS_ENABLED(CONFIG_DAX) to know if this
* NULL is an error or expected.
*/
return NULL;
}
static inline void put_dax(struct dax_device *dax_dev)
{
}
static inline void kill_dax(struct dax_device *dax_dev)
{
}
static inline void dax_write_cache(struct dax_device *dax_dev, bool wc)
{
}
static inline bool dax_write_cache_enabled(struct dax_device *dax_dev)
{
return false;
}
#endif
struct writeback_control;
int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
#if IS_ENABLED(CONFIG_FS_DAX)
bool __bdev_dax_supported(struct block_device *bdev, int blocksize);
static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize)
{
return __bdev_dax_supported(bdev, blocksize);
}
static inline struct dax_device *fs_dax_get_by_host(const char *host)
{
return dax_get_by_host(host);
}
static inline void fs_put_dax(struct dax_device *dax_dev)
{
put_dax(dax_dev);
}
struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
int dax_writeback_mapping_range(struct address_space *mapping,
struct block_device *bdev, struct writeback_control *wbc);
struct page *dax_layout_busy_page(struct address_space *mapping);
dax_entry_t dax_lock_page(struct page *page);
void dax_unlock_page(struct page *page, dax_entry_t cookie);
#else
static inline bool bdev_dax_supported(struct block_device *bdev,
int blocksize)
{
return false;
}
static inline struct dax_device *fs_dax_get_by_host(const char *host)
{
return NULL;
}
static inline void fs_put_dax(struct dax_device *dax_dev)
{
}
static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
{
return NULL;
}
static inline struct page *dax_layout_busy_page(struct address_space *mapping)
{
return NULL;
}
static inline int dax_writeback_mapping_range(struct address_space *mapping,
struct block_device *bdev, struct writeback_control *wbc)
{
return -EOPNOTSUPP;
}
static inline dax_entry_t dax_lock_page(struct page *page)
{
if (IS_DAX(page->mapping->host))
return ~0UL;
return 0;
}
static inline void dax_unlock_page(struct page *page, dax_entry_t cookie)
{
}
#endif
int dax_read_lock(void);
void dax_read_unlock(int id);
bool dax_alive(struct dax_device *dax_dev);
void *dax_get_private(struct dax_device *dax_dev);
long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
void **kaddr, pfn_t *pfn);
size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
size_t bytes, struct iov_iter *i);
size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
size_t bytes, struct iov_iter *i);
void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops);
vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
pfn_t *pfnp, int *errp, const struct iomap_ops *ops);
vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
enum page_entry_size pe_size, pfn_t pfn);
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
pgoff_t index);
#ifdef CONFIG_FS_DAX
int __dax_zero_page_range(struct block_device *bdev,
struct dax_device *dax_dev, sector_t sector,
unsigned int offset, unsigned int length);
#else
static inline int __dax_zero_page_range(struct block_device *bdev,
struct dax_device *dax_dev, sector_t sector,
unsigned int offset, unsigned int length)
{
return -ENXIO;
}
#endif
static inline bool dax_mapping(struct address_space *mapping)
{
return mapping->host && IS_DAX(mapping->host);
}
#endif