Revision 4759d386d55fef452d692bf101167914437e848e authored by Linus Torvalds on 01 January 2017, 20:27:05 UTC, committed by Linus Torvalds on 01 January 2017, 20:27:05 UTC
Pull DAX updates from Dan Williams: "The completion of Jan's DAX work for 4.10. As I mentioned in the libnvdimm-for-4.10 pull request, these are some final fixes for the DAX dirty-cacheline-tracking invalidation work that was merged through the -mm, ext4, and xfs trees in -rc1. These patches were prepared prior to the merge window, but we waited for 4.10-rc1 to have a stable merge base after all the prerequisites were merged. Quoting Jan on the overall changes in these patches: "So I'd like all these 6 patches to go for rc2. The first three patches fix invalidation of exceptional DAX entries (a bug which is there for a long time) - without these patches data loss can occur on power failure even though user called fsync(2). The other three patches change locking of DAX faults so that ->iomap_begin() is called in a more relaxed locking context and we are safe to start a transaction there for ext4" These have received a build success notification from the kbuild robot, and pass the latest libnvdimm unit tests. There have not been any -next releases since -rc1, so they have not appeared there" * 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: ext4: Simplify DAX fault path dax: Call ->iomap_begin without entry lock during dax fault dax: Finish fault completely when loading holes dax: Avoid page invalidation races and unnecessary radix tree traversals mm: Invalidate DAX radix tree entries only if appropriate ext2: Return BH_New buffers for zeroed blocks
word-at-a-time.h
#ifndef _ASM_WORD_AT_A_TIME_H
#define _ASM_WORD_AT_A_TIME_H
#include <linux/kernel.h>
#include <asm/byteorder.h>
#ifdef __BIG_ENDIAN
struct word_at_a_time {
const unsigned long high_bits, low_bits;
};
#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0xfe) + 1, REPEAT_BYTE(0x7f) }
/* Bit set in the bytes that have a zero */
static inline long prep_zero_mask(unsigned long val, unsigned long rhs, const struct word_at_a_time *c)
{
unsigned long mask = (val & c->low_bits) + c->low_bits;
return ~(mask | rhs);
}
#define create_zero_mask(mask) (mask)
static inline long find_zero(unsigned long mask)
{
long byte = 0;
#ifdef CONFIG_64BIT
if (mask >> 32)
mask >>= 32;
else
byte = 4;
#endif
if (mask >> 16)
mask >>= 16;
else
byte += 2;
return (mask >> 8) ? byte : byte + 1;
}
static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c)
{
unsigned long rhs = val | c->low_bits;
*data = rhs;
return (val + c->high_bits) & ~rhs;
}
#ifndef zero_bytemask
#define zero_bytemask(mask) (~1ul << __fls(mask))
#endif
#else
/*
* The optimal byte mask counting is probably going to be something
* that is architecture-specific. If you have a reliably fast
* bit count instruction, that might be better than the multiply
* and shift, for example.
*/
struct word_at_a_time {
const unsigned long one_bits, high_bits;
};
#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
#ifdef CONFIG_64BIT
/*
* Jan Achrenius on G+: microoptimized version of
* the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
* that works for the bytemasks without having to
* mask them first.
*/
static inline long count_masked_bytes(unsigned long mask)
{
return mask*0x0001020304050608ul >> 56;
}
#else /* 32-bit case */
/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
static inline long count_masked_bytes(long mask)
{
/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
long a = (0x0ff0001+mask) >> 23;
/* Fix the 1 for 00 case */
return a & mask;
}
#endif
/* Return nonzero if it has a zero */
static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
{
unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
*bits = mask;
return mask;
}
static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
{
return bits;
}
static inline unsigned long create_zero_mask(unsigned long bits)
{
bits = (bits - 1) & ~bits;
return bits >> 7;
}
/* The mask we created is directly usable as a bytemask */
#define zero_bytemask(mask) (mask)
static inline unsigned long find_zero(unsigned long mask)
{
return count_masked_bytes(mask);
}
#endif /* __BIG_ENDIAN */
#endif /* _ASM_WORD_AT_A_TIME_H */
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...