642261ac99
DAX PMDs have been disabled since Jan Kara introduced DAX radix tree based locking. This patch allows DAX PMDs to participate in the DAX radix tree based locking scheme so that they can be re-enabled using the new struct iomap based fault handlers. There are currently three types of DAX 4k entries: 4k zero pages, 4k DAX mappings that have an associated block allocation, and 4k DAX empty entries. The empty entries exist to provide locking for the duration of a given page fault. This patch adds three equivalent 2MiB DAX entries: Huge Zero Page (HZP) entries, PMD DAX entries that have associated block allocations, and 2 MiB DAX empty entries. Unlike the 4k case where we insert a struct page* into the radix tree for 4k zero pages, for HZP we insert a DAX exceptional entry with the new RADIX_DAX_HZP flag set. This is because we use a single 2 MiB zero page in every 2MiB hole mapping, and it doesn't make sense to have that same struct page* with multiple entries in multiple trees. This would cause contention on the single page lock for the one Huge Zero Page, and it would break the page->index and page->mapping associations that are assumed to be valid in many other places in the kernel. One difficult use case is when one thread is trying to use 4k entries in radix tree for a given offset, and another thread is using 2 MiB entries for that same offset. The current code handles this by making the 2 MiB user fall back to 4k entries for most cases. This was done because it is the simplest solution, and because the use of 2MiB pages is already opportunistic. If we were to try to upgrade from 4k pages to 2MiB pages for a given range, we run into the problem of how we lock out 4k page faults for the entire 2MiB range while we clean out the radix tree so we can insert the 2MiB entry. We can solve this problem if we need to, but I think that the cases where both 2MiB entries and 4K entries are being used for the same range will be rare enough and the gain small enough that it probably won't be worth the complexity. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Dave Chinner <david@fromorbit.com>
119 lines
3.8 KiB
C
119 lines
3.8 KiB
C
#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>
|
|
|
|
struct iomap_ops;
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
|
|
#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
|
|
#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))
|
|
|
|
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);
|
|
}
|
|
|
|
ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
|
|
struct iomap_ops *ops);
|
|
ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *,
|
|
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_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
|
|
struct iomap_ops *ops);
|
|
int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
|
|
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
|
|
void dax_wake_mapping_entry_waiter(struct address_space *mapping,
|
|
pgoff_t index, void *entry, bool wake_all);
|
|
|
|
#ifdef CONFIG_FS_DAX
|
|
struct page *read_dax_sector(struct block_device *bdev, sector_t n);
|
|
void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index);
|
|
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);
|
|
}
|
|
/* Shouldn't ever be called when dax is disabled. */
|
|
static inline void dax_unlock_mapping_entry(struct address_space *mapping,
|
|
pgoff_t index)
|
|
{
|
|
BUG();
|
|
}
|
|
static inline int __dax_zero_page_range(struct block_device *bdev,
|
|
sector_t sector, unsigned int offset, unsigned int length)
|
|
{
|
|
return -ENXIO;
|
|
}
|
|
#endif
|
|
|
|
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;
|
|
}
|
|
|
|
#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;
|
|
}
|
|
int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
|
|
pmd_t *pmd, unsigned int flags, struct iomap_ops *ops);
|
|
#else
|
|
static inline unsigned int dax_radix_order(void *entry)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma,
|
|
unsigned long address, pmd_t *pmd, unsigned int flags,
|
|
struct iomap_ops *ops)
|
|
{
|
|
return VM_FAULT_FALLBACK;
|
|
}
|
|
#endif
|
|
int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
|
|
#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
|