dax.h 3.6 KB
Newer Older
1 2 3 4 5
#ifndef _LINUX_DAX_H
#define _LINUX_DAX_H

#include <linux/fs.h>
#include <linux/mm.h>
6
#include <linux/radix-tree.h>
7 8
#include <asm/pgtable.h>

9
struct iomap_ops;
D
Dan Williams 已提交
10 11 12 13 14 15 16 17 18 19
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 *);
};
20

21 22
int dax_read_lock(void);
void dax_read_unlock(int id);
23
struct dax_device *dax_get_by_host(const char *host);
D
Dan Williams 已提交
24 25 26 27 28 29
struct dax_device *alloc_dax(void *private, const char *host,
		const struct dax_operations *ops);
void put_dax(struct dax_device *dax_dev);
bool dax_alive(struct dax_device *dax_dev);
void kill_dax(struct dax_device *dax_dev);
void *dax_get_private(struct dax_device *dax_dev);
30 31
long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
		void **kaddr, pfn_t *pfn);
32

33
/*
34 35 36 37 38 39 40 41
 * We use lowest available bit in exceptional entry for locking, one bit for
 * the entry size (PMD) and two more to tell us if the entry is a huge zero
 * page (HZP) or an empty entry that is just used for locking.  In total four
 * special bits.
 *
 * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and
 * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
 * block allocation.
42
 */
43
#define RADIX_DAX_SHIFT	(RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
44
#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
45 46 47
#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
48

49 50 51 52 53 54 55 56 57 58 59
static inline unsigned long dax_radix_sector(void *entry)
{
	return (unsigned long)entry >> RADIX_DAX_SHIFT;
}

static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
{
	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
			((unsigned long)sector << RADIX_DAX_SHIFT) |
			RADIX_DAX_ENTRY_LOCK);
}
60

61
ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
62
		const struct iomap_ops *ops);
63 64
int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
		    const struct iomap_ops *ops);
J
Jan Kara 已提交
65
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
66 67 68
int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
				      pgoff_t index);
J
Jan Kara 已提交
69
void dax_wake_mapping_entry_waiter(struct address_space *mapping,
70
		pgoff_t index, void *entry, bool wake_all);
71 72

#ifdef CONFIG_FS_DAX
73 74
int __dax_zero_page_range(struct block_device *bdev,
		struct dax_device *dax_dev, sector_t sector,
75
		unsigned int offset, unsigned int length);
76
#else
77
static inline int __dax_zero_page_range(struct block_device *bdev,
78 79
		struct dax_device *dax_dev, sector_t sector,
		unsigned int offset, unsigned int length)
80 81 82
{
	return -ENXIO;
}
83 84
#endif

85 86 87 88 89 90 91 92 93 94 95 96 97
#ifdef CONFIG_FS_DAX_PMD
static inline unsigned int dax_radix_order(void *entry)
{
	if ((unsigned long)entry & RADIX_DAX_PMD)
		return PMD_SHIFT - PAGE_SHIFT;
	return 0;
}
#else
static inline unsigned int dax_radix_order(void *entry)
{
	return 0;
}
#endif
98
int dax_pfn_mkwrite(struct vm_fault *vmf);
99

M
Matthew Wilcox 已提交
100 101 102 103
static inline bool vma_is_dax(struct vm_area_struct *vma)
{
	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
}
104 105 106 107 108

static inline bool dax_mapping(struct address_space *mapping)
{
	return mapping->host && IS_DAX(mapping->host);
}
109 110 111 112

struct writeback_control;
int dax_writeback_mapping_range(struct address_space *mapping,
		struct block_device *bdev, struct writeback_control *wbc);
113
#endif