linux-stable/include/linux/dax.h
Linus Torvalds 37187df45a New code for 5.10:
- Don't WARN_ON weird states that unprivileged users can create.
 - Don't invalidate page cache when direct writes want to fall back to
   buffered.
 - Fix some problems when readahead ios fail.
 - Fix a problem where inline data pages weren't getting flushed during
   an unshare operation.
 - Rework iomap to support arbitrarily many blocks per page in
   preparation to support THP for the page cache.
 - Fix a bug in the blocksize < pagesize buffered io path where we could
   fail to initialize the many-blocks-per-page uptodate bitmap correctly
   when the backing page is actually up to date.  This could cause us to
   forget to write out dirty pages.
 - Split out the generic_write_sync at the end of the directio write path
   so that btrfs can drop the inode lock before sync'ing the file.
 - Call inode_dio_end before trying to sync the file after a O_DSYNC
   direct write (instead of afterwards) to match the behavior of the
   old directio code.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEUzaAxoMeQq6m2jMV+H93GTRKtOsFAl9yB04ACgkQ+H93GTRK
 tOuZxw/+IrBV3HV45PtqQX+HC2F4ebax26cIJrmCQD0neiu16I7H3COjIGN/YOGw
 bN04VirC3bG4BtzVHO/eRHQOCwCevIpP3LkhT6yOfOgkO4Z9Xn/O7E+7uYtgT5Qi
 dBqOFe/aoB6+uHEHaioWUTxF1MlsVqEK/yPWjbSIdQGKFVE03Azj4V5QHtBouF2+
 pNEk7lbBnF0ua3biambeyDO3JTR9dsziIPH8QzQ4M/fMuNLfR2v0s6d4Ol/ndVrC
 Lp3RtThLcioAXh8xSPMO6RVUFfK97SLgNCRngApFbIJn85z9yq7eI7llnhO+XcHF
 FBJ+XottlwJFDt+0xNUaHmjkfUH9GoK8VeFOd3zHvp6xgZZpDkjG2JJk9ZC8Qnn5
 xg4grGngWshNdxFBf8S/O73bAJ1SyRcD5ePYGyMfiij3beGJ0aulKGoYOdDfC/4c
 hHcUc8XpjHSobg5gklQijBif0WIQos1Z4OyDK9d2LqrJOO0NUypO/t2YIdgPFzkj
 rXLmWlKsUYSZyefI5Z8q0AVy7TQGxstS9poC3lkXlsszQ1E5BNup0/bhCGTgCW+5
 az9m41KXxPEDLxieOvIAUhHSSP02IAGQ9Lvvat1GnGfEqShAEWS/IvmIxHDbvyNW
 lZ0NLqNKsItKBH0oIPsrP7fHz2ES1hUIMIaLbApUwKpUcAxrCLY=
 =ocIt
 -----END PGP SIGNATURE-----

Merge tag 'iomap-5.10-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull iomap updates from Darrick Wong:
 "There's not a lot of new stuff going on here -- a little bit of code
  refactoring to make iomap workable with btrfs' fsync locking model,
  cleanups in preparation for adding THP support for filesystems, and
  fixing a data corruption issue for blocksize < pagesize filesystems.

  Summary:

   - Don't WARN_ON weird states that unprivileged users can create.

   - Don't invalidate page cache when direct writes want to fall back to
     buffered.

   - Fix some problems when readahead ios fail.

   - Fix a problem where inline data pages weren't getting flushed
     during an unshare operation.

   - Rework iomap to support arbitrarily many blocks per page in
     preparation to support THP for the page cache.

   - Fix a bug in the blocksize < pagesize buffered io path where we
     could fail to initialize the many-blocks-per-page uptodate bitmap
     correctly when the backing page is actually up to date. This could
     cause us to forget to write out dirty pages.

   - Split out the generic_write_sync at the end of the directio write
     path so that btrfs can drop the inode lock before sync'ing the
     file.

   - Call inode_dio_end before trying to sync the file after a O_DSYNC
     direct write (instead of afterwards) to match the behavior of the
     old directio code"

* tag 'iomap-5.10-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  iomap: Call inode_dio_end() before generic_write_sync()
  iomap: Allow filesystem to call iomap_dio_complete without i_rwsem
  iomap: Set all uptodate bits for an Uptodate page
  iomap: Change calling convention for zeroing
  iomap: Convert iomap_write_end types
  iomap: Convert write_count to write_bytes_pending
  iomap: Convert read_count to read_bytes_pending
  iomap: Support arbitrarily many blocks per page
  iomap: Use bitmap ops to set uptodate bits
  iomap: Use kzalloc to allocate iomap_page
  fs: Introduce i_blocks_per_page
  iomap: Fix misplaced page flushing
  iomap: Use round_down/round_up macros in __iomap_write_begin
  iomap: Mark read blocks uptodate in write_begin
  iomap: Clear page error before beginning a write
  iomap: Fix direct I/O write consistency check
  iomap: fix WARN_ON_ONCE() from unprivileged users
2020-10-14 12:23:00 -07:00

248 lines
7.1 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>
/* Flag for synchronous flush */
#define DAXDEV_F_SYNC (1UL << 0)
typedef unsigned long dax_entry_t;
struct iomap_ops;
struct iomap;
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 *);
/*
* Validate whether this device is usable as an fsdax backing
* device.
*/
bool (*dax_supported)(struct dax_device *, struct block_device *, int,
sector_t, sector_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 *);
/* zero_page_range: required operation. Zero page range */
int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
};
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, unsigned long flags);
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);
bool __dax_synchronous(struct dax_device *dax_dev);
static inline bool dax_synchronous(struct dax_device *dax_dev)
{
return __dax_synchronous(dax_dev);
}
void __set_dax_synchronous(struct dax_device *dax_dev);
static inline void set_dax_synchronous(struct dax_device *dax_dev)
{
__set_dax_synchronous(dax_dev);
}
bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
int blocksize, sector_t start, sector_t len);
/*
* Check if given mapping is supported by the file / underlying device.
*/
static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
struct dax_device *dax_dev)
{
if (!(vma->vm_flags & VM_SYNC))
return true;
if (!IS_DAX(file_inode(vma->vm_file)))
return false;
return dax_synchronous(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, unsigned long flags)
{
/*
* 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;
}
static inline bool dax_synchronous(struct dax_device *dax_dev)
{
return true;
}
static inline void set_dax_synchronous(struct dax_device *dax_dev)
{
}
static inline bool dax_supported(struct dax_device *dax_dev,
struct block_device *bdev, int blocksize, sector_t start,
sector_t len)
{
return false;
}
static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
struct dax_device *dax_dev)
{
return !(vma->vm_flags & VM_SYNC);
}
#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);
}
bool __generic_fsdax_supported(struct dax_device *dax_dev,
struct block_device *bdev, int blocksize, sector_t start,
sector_t sectors);
static inline bool generic_fsdax_supported(struct dax_device *dax_dev,
struct block_device *bdev, int blocksize, sector_t start,
sector_t sectors)
{
return __generic_fsdax_supported(dax_dev, bdev, blocksize, start,
sectors);
}
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 dax_device *dax_dev, 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 bool generic_fsdax_supported(struct dax_device *dax_dev,
struct block_device *bdev, int blocksize, sector_t start,
sector_t sectors)
{
return false;
}
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 dax_device *dax_dev, 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
#if IS_ENABLED(CONFIG_DAX)
int dax_read_lock(void);
void dax_read_unlock(int id);
#else
static inline int dax_read_lock(void)
{
return 0;
}
static inline void dax_read_unlock(int id)
{
}
#endif /* CONFIG_DAX */
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);
int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
size_t nr_pages);
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);
s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
static inline bool dax_mapping(struct address_space *mapping)
{
return mapping->host && IS_DAX(mapping->host);
}
#ifdef CONFIG_DEV_DAX_HMEM_DEVICES
void hmem_register_device(int target_nid, struct resource *r);
#else
static inline void hmem_register_device(int target_nid, struct resource *r)
{
}
#endif
#endif