Filesystem DAX locking for 4.7

- We use a bit in an exceptional radix tree entry as a lock bit and use it
   similarly to how page lock is used for normal faults.  This fixes races
   between hole instantiation and read faults of the same index.
 
 - Filesystem DAX PMD faults are disabled, and will be re-enabled when PMD
   locking is implemented.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJXRKwLAAoJEJ/BjXdf9fLB+BkP/3HBm05KlAKDklvnBIPFDMUK
 hA7g2K6vuvaEDZXZQ1ioc1Ajf1sCpVip7shXJsojZqwWmRz0/4nneF7ytluW9AjS
 dBX+0qCgKGH1fnwyGFF+MN7fuj7kGrSDz34lG0OObRN6/oKiVNb2svXiYKkT6J6C
 AgsWlWRUpMy9jrn1u/FduMjDhk92Z3ojarexuicr0i8NUlBClCIrdCEmUMi4orSB
 DuiIjestLOc7+mERBUwrXkzoh9v8Z0FpIgnDLWwpeEkAvJwWkGe5eXrBJwF+hEbi
 RYfTrOYc7bBQLo22LRb8pdighjrx3OW9EpNCfEmLDOjM3cYBbMK/d2i/ww52H6IK
 Mw6iS5rXdGgJtQIGL8N96HLFk+cDyZ8J8xNUCwbYYBJqgpMzxzVkL3vTm72tyFnl
 InWhih+miCMbBPytQSRd6+1wZG2piJTv6SsFTd5K1OaiRmJhBJZG47t2QTBRBu7Y
 5A4FGPtlraV+iDJvD6VLO1Tp8twxdLluOJ2BwdGeiKXiGh6LP+FGGFF3aFa5N4Ro
 xSslCTX7Q1G66zXQwD4+IMWLwS1FDNymPkUSsF6RQo6qfAnl9SrmYTc4xJ4QXy92
 sUdrWEz2OBTfxKNqbGyc/KrXKZT3RnEkJNft8snB2h6WTCdOPaNYs/yETUwiwkSc
 CXpuQFrxm69QYwNsqVu1
 =Pkd0
 -----END PGP SIGNATURE-----

Merge tag 'dax-locking-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull DAX locking updates from Ross Zwisler:
 "Filesystem DAX locking for 4.7

   - We use a bit in an exceptional radix tree entry as a lock bit and
     use it similarly to how page lock is used for normal faults.  This
     fixes races between hole instantiation and read faults of the same
     index.

   - Filesystem DAX PMD faults are disabled, and will be re-enabled when
     PMD locking is implemented"

* tag 'dax-locking-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  dax: Remove i_mmap_lock protection
  dax: Use radix tree entry lock to protect cow faults
  dax: New fault locking
  dax: Allow DAX code to replace exceptional entries
  dax: Define DAX lock bit for radix tree exceptional entry
  dax: Make huge page handling depend of CONFIG_BROKEN
  dax: Fix condition for filling of PMD holes
This commit is contained in:
Linus Torvalds 2016-05-26 20:00:28 -07:00
commit 478a1469a7
7 changed files with 514 additions and 236 deletions

View file

@ -3,17 +3,25 @@
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/radix-tree.h>
#include <asm/pgtable.h>
/* We use lowest available exceptional entry bit for locking */
#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
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_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
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, 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
@ -22,6 +30,12 @@ static inline struct page *read_dax_sector(struct block_device *bdev,
{
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)
{
@ -29,7 +43,7 @@ static inline int __dax_zero_page_range(struct block_device *bdev,
}
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#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 *,