https://github.com/torvalds/linux
Revision 9230a0b65b47fe6856c4468ec0175c4987e5bede authored by Dave Chinner on 20 November 2018, 06:50:08 UTC, committed by Darrick J. Wong on 21 November 2018, 18:10:53 UTC
Long saga. There have been days spent following this through dead end after dead end in multi-GB event traces. This morning, after writing a trace-cmd wrapper that enabled me to be more selective about XFS trace points, I discovered that I could get just enough essential tracepoints enabled that there was a 50:50 chance the fsx config would fail at ~115k ops. If it didn't fail at op 115547, I stopped fsx at op 115548 anyway. That gave me two traces - one where the problem manifested, and one where it didn't. After refining the traces to have the necessary information, I found that in the failing case there was a real extent in the COW fork compared to an unwritten extent in the working case. Walking back through the two traces to the point where the CWO fork extents actually diverged, I found that the bad case had an extra unwritten extent in it. This is likely because the bug it led me to had triggered multiple times in those 115k ops, leaving stray COW extents around. What I saw was a COW delalloc conversion to an unwritten extent (as they should always be through xfs_iomap_write_allocate()) resulted in a /written extent/: xfs_writepage: dev 259:0 ino 0x83 pgoff 0x17000 size 0x79a00 offset 0 length 0 xfs_iext_remove: dev 259:0 ino 0x83 state RC|LF|RF|COW cur 0xffff888247b899c0/2 offset 32 block 152 count 20 flag 1 caller xfs_bmap_add_extent_delay_real xfs_bmap_pre_update: dev 259:0 ino 0x83 state RC|LF|RF|COW cur 0xffff888247b899c0/1 offset 1 block 4503599627239429 count 31 flag 0 caller xfs_bmap_add_extent_delay_real xfs_bmap_post_update: dev 259:0 ino 0x83 state RC|LF|RF|COW cur 0xffff888247b899c0/1 offset 1 block 121 count 51 flag 0 caller xfs_bmap_add_ex Basically, Cow fork before: 0 1 32 52 +H+DDDDDDDDDDDD+UUUUUUUUUUU+ PREV RIGHT COW delalloc conversion allocates: 1 32 +uuuuuuuuuuuu+ NEW And the result according to the xfs_bmap_post_update trace was: 0 1 32 52 +H+wwwwwwwwwwwwwwwwwwwwwwww+ PREV Which is clearly wrong - it should be a merged unwritten extent, not an unwritten extent. That lead me to look at the LEFT_FILLING|RIGHT_FILLING|RIGHT_CONTIG case in xfs_bmap_add_extent_delay_real(), and sure enough, there's the bug. It takes the old delalloc extent (PREV) and adds the length of the RIGHT extent to it, takes the start block from NEW, removes the RIGHT extent and then updates PREV with the new extent. What it fails to do is update PREV.br_state. For delalloc, this is always XFS_EXT_NORM, while in this case we are converting the delayed allocation to unwritten, so it needs to be updated to XFS_EXT_UNWRITTEN. This LF|RF|RC case does not do this, and so the resultant extent is always written. And that's the bug I've been chasing for a week - a bmap btree bug, not a reflink/dedupe/copy_file_range bug, but a BMBT bug introduced with the recent in core extent tree scalability enhancements. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
1 parent 2c30717
Tip revision: 9230a0b65b47fe6856c4468ec0175c4987e5bede authored by Dave Chinner on 20 November 2018, 06:50:08 UTC
xfs: delalloc -> unwritten COW fork allocation can go wrong
xfs: delalloc -> unwritten COW fork allocation can go wrong
Tip revision: 9230a0b
siphash.c
/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
*
* This file is provided under a dual BSD/GPLv2 license.
*
* SipHash: a fast short-input PRF
* https://131002.net/siphash/
*
* This implementation is specifically for SipHash2-4 for a secure PRF
* and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for
* hashtables.
*/
#include <linux/siphash.h>
#include <asm/unaligned.h>
#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
#include <linux/dcache.h>
#include <asm/word-at-a-time.h>
#endif
#define SIPROUND \
do { \
v0 += v1; v1 = rol64(v1, 13); v1 ^= v0; v0 = rol64(v0, 32); \
v2 += v3; v3 = rol64(v3, 16); v3 ^= v2; \
v0 += v3; v3 = rol64(v3, 21); v3 ^= v0; \
v2 += v1; v1 = rol64(v1, 17); v1 ^= v2; v2 = rol64(v2, 32); \
} while (0)
#define PREAMBLE(len) \
u64 v0 = 0x736f6d6570736575ULL; \
u64 v1 = 0x646f72616e646f6dULL; \
u64 v2 = 0x6c7967656e657261ULL; \
u64 v3 = 0x7465646279746573ULL; \
u64 b = ((u64)(len)) << 56; \
v3 ^= key->key[1]; \
v2 ^= key->key[0]; \
v1 ^= key->key[1]; \
v0 ^= key->key[0];
#define POSTAMBLE \
v3 ^= b; \
SIPROUND; \
SIPROUND; \
v0 ^= b; \
v2 ^= 0xff; \
SIPROUND; \
SIPROUND; \
SIPROUND; \
SIPROUND; \
return (v0 ^ v1) ^ (v2 ^ v3);
u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
const u8 left = len & (sizeof(u64) - 1);
u64 m;
PREAMBLE(len)
for (; data != end; data += sizeof(u64)) {
m = le64_to_cpup(data);
v3 ^= m;
SIPROUND;
SIPROUND;
v0 ^= m;
}
#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
if (left)
b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
bytemask_from_count(left)));
#else
switch (left) {
case 7: b |= ((u64)end[6]) << 48;
case 6: b |= ((u64)end[5]) << 40;
case 5: b |= ((u64)end[4]) << 32;
case 4: b |= le32_to_cpup(data); break;
case 3: b |= ((u64)end[2]) << 16;
case 2: b |= le16_to_cpup(data); break;
case 1: b |= end[0];
}
#endif
POSTAMBLE
}
EXPORT_SYMBOL(__siphash_aligned);
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
const u8 left = len & (sizeof(u64) - 1);
u64 m;
PREAMBLE(len)
for (; data != end; data += sizeof(u64)) {
m = get_unaligned_le64(data);
v3 ^= m;
SIPROUND;
SIPROUND;
v0 ^= m;
}
#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
if (left)
b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
bytemask_from_count(left)));
#else
switch (left) {
case 7: b |= ((u64)end[6]) << 48;
case 6: b |= ((u64)end[5]) << 40;
case 5: b |= ((u64)end[4]) << 32;
case 4: b |= get_unaligned_le32(end); break;
case 3: b |= ((u64)end[2]) << 16;
case 2: b |= get_unaligned_le16(end); break;
case 1: b |= end[0];
}
#endif
POSTAMBLE
}
EXPORT_SYMBOL(__siphash_unaligned);
#endif
/**
* siphash_1u64 - compute 64-bit siphash PRF value of a u64
* @first: first u64
* @key: the siphash key
*/
u64 siphash_1u64(const u64 first, const siphash_key_t *key)
{
PREAMBLE(8)
v3 ^= first;
SIPROUND;
SIPROUND;
v0 ^= first;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_1u64);
/**
* siphash_2u64 - compute 64-bit siphash PRF value of 2 u64
* @first: first u64
* @second: second u64
* @key: the siphash key
*/
u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t *key)
{
PREAMBLE(16)
v3 ^= first;
SIPROUND;
SIPROUND;
v0 ^= first;
v3 ^= second;
SIPROUND;
SIPROUND;
v0 ^= second;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_2u64);
/**
* siphash_3u64 - compute 64-bit siphash PRF value of 3 u64
* @first: first u64
* @second: second u64
* @third: third u64
* @key: the siphash key
*/
u64 siphash_3u64(const u64 first, const u64 second, const u64 third,
const siphash_key_t *key)
{
PREAMBLE(24)
v3 ^= first;
SIPROUND;
SIPROUND;
v0 ^= first;
v3 ^= second;
SIPROUND;
SIPROUND;
v0 ^= second;
v3 ^= third;
SIPROUND;
SIPROUND;
v0 ^= third;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_3u64);
/**
* siphash_4u64 - compute 64-bit siphash PRF value of 4 u64
* @first: first u64
* @second: second u64
* @third: third u64
* @forth: forth u64
* @key: the siphash key
*/
u64 siphash_4u64(const u64 first, const u64 second, const u64 third,
const u64 forth, const siphash_key_t *key)
{
PREAMBLE(32)
v3 ^= first;
SIPROUND;
SIPROUND;
v0 ^= first;
v3 ^= second;
SIPROUND;
SIPROUND;
v0 ^= second;
v3 ^= third;
SIPROUND;
SIPROUND;
v0 ^= third;
v3 ^= forth;
SIPROUND;
SIPROUND;
v0 ^= forth;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_4u64);
u64 siphash_1u32(const u32 first, const siphash_key_t *key)
{
PREAMBLE(4)
b |= first;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_1u32);
u64 siphash_3u32(const u32 first, const u32 second, const u32 third,
const siphash_key_t *key)
{
u64 combined = (u64)second << 32 | first;
PREAMBLE(12)
v3 ^= combined;
SIPROUND;
SIPROUND;
v0 ^= combined;
b |= third;
POSTAMBLE
}
EXPORT_SYMBOL(siphash_3u32);
#if BITS_PER_LONG == 64
/* Note that on 64-bit, we make HalfSipHash1-3 actually be SipHash1-3, for
* performance reasons. On 32-bit, below, we actually implement HalfSipHash1-3.
*/
#define HSIPROUND SIPROUND
#define HPREAMBLE(len) PREAMBLE(len)
#define HPOSTAMBLE \
v3 ^= b; \
HSIPROUND; \
v0 ^= b; \
v2 ^= 0xff; \
HSIPROUND; \
HSIPROUND; \
HSIPROUND; \
return (v0 ^ v1) ^ (v2 ^ v3);
u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
const u8 left = len & (sizeof(u64) - 1);
u64 m;
HPREAMBLE(len)
for (; data != end; data += sizeof(u64)) {
m = le64_to_cpup(data);
v3 ^= m;
HSIPROUND;
v0 ^= m;
}
#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
if (left)
b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
bytemask_from_count(left)));
#else
switch (left) {
case 7: b |= ((u64)end[6]) << 48;
case 6: b |= ((u64)end[5]) << 40;
case 5: b |= ((u64)end[4]) << 32;
case 4: b |= le32_to_cpup(data); break;
case 3: b |= ((u64)end[2]) << 16;
case 2: b |= le16_to_cpup(data); break;
case 1: b |= end[0];
}
#endif
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_aligned);
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_unaligned(const void *data, size_t len,
const hsiphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
const u8 left = len & (sizeof(u64) - 1);
u64 m;
HPREAMBLE(len)
for (; data != end; data += sizeof(u64)) {
m = get_unaligned_le64(data);
v3 ^= m;
HSIPROUND;
v0 ^= m;
}
#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
if (left)
b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
bytemask_from_count(left)));
#else
switch (left) {
case 7: b |= ((u64)end[6]) << 48;
case 6: b |= ((u64)end[5]) << 40;
case 5: b |= ((u64)end[4]) << 32;
case 4: b |= get_unaligned_le32(end); break;
case 3: b |= ((u64)end[2]) << 16;
case 2: b |= get_unaligned_le16(end); break;
case 1: b |= end[0];
}
#endif
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_unaligned);
#endif
/**
* hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32
* @first: first u32
* @key: the hsiphash key
*/
u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key)
{
HPREAMBLE(4)
b |= first;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_1u32);
/**
* hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32
* @first: first u32
* @second: second u32
* @key: the hsiphash key
*/
u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key)
{
u64 combined = (u64)second << 32 | first;
HPREAMBLE(8)
v3 ^= combined;
HSIPROUND;
v0 ^= combined;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_2u32);
/**
* hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32
* @first: first u32
* @second: second u32
* @third: third u32
* @key: the hsiphash key
*/
u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third,
const hsiphash_key_t *key)
{
u64 combined = (u64)second << 32 | first;
HPREAMBLE(12)
v3 ^= combined;
HSIPROUND;
v0 ^= combined;
b |= third;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_3u32);
/**
* hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32
* @first: first u32
* @second: second u32
* @third: third u32
* @forth: forth u32
* @key: the hsiphash key
*/
u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third,
const u32 forth, const hsiphash_key_t *key)
{
u64 combined = (u64)second << 32 | first;
HPREAMBLE(16)
v3 ^= combined;
HSIPROUND;
v0 ^= combined;
combined = (u64)forth << 32 | third;
v3 ^= combined;
HSIPROUND;
v0 ^= combined;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_4u32);
#else
#define HSIPROUND \
do { \
v0 += v1; v1 = rol32(v1, 5); v1 ^= v0; v0 = rol32(v0, 16); \
v2 += v3; v3 = rol32(v3, 8); v3 ^= v2; \
v0 += v3; v3 = rol32(v3, 7); v3 ^= v0; \
v2 += v1; v1 = rol32(v1, 13); v1 ^= v2; v2 = rol32(v2, 16); \
} while (0)
#define HPREAMBLE(len) \
u32 v0 = 0; \
u32 v1 = 0; \
u32 v2 = 0x6c796765U; \
u32 v3 = 0x74656462U; \
u32 b = ((u32)(len)) << 24; \
v3 ^= key->key[1]; \
v2 ^= key->key[0]; \
v1 ^= key->key[1]; \
v0 ^= key->key[0];
#define HPOSTAMBLE \
v3 ^= b; \
HSIPROUND; \
v0 ^= b; \
v2 ^= 0xff; \
HSIPROUND; \
HSIPROUND; \
HSIPROUND; \
return v1 ^ v3;
u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u32));
const u8 left = len & (sizeof(u32) - 1);
u32 m;
HPREAMBLE(len)
for (; data != end; data += sizeof(u32)) {
m = le32_to_cpup(data);
v3 ^= m;
HSIPROUND;
v0 ^= m;
}
switch (left) {
case 3: b |= ((u32)end[2]) << 16;
case 2: b |= le16_to_cpup(data); break;
case 1: b |= end[0];
}
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_aligned);
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_unaligned(const void *data, size_t len,
const hsiphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u32));
const u8 left = len & (sizeof(u32) - 1);
u32 m;
HPREAMBLE(len)
for (; data != end; data += sizeof(u32)) {
m = get_unaligned_le32(data);
v3 ^= m;
HSIPROUND;
v0 ^= m;
}
switch (left) {
case 3: b |= ((u32)end[2]) << 16;
case 2: b |= get_unaligned_le16(end); break;
case 1: b |= end[0];
}
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_unaligned);
#endif
/**
* hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32
* @first: first u32
* @key: the hsiphash key
*/
u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key)
{
HPREAMBLE(4)
v3 ^= first;
HSIPROUND;
v0 ^= first;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_1u32);
/**
* hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32
* @first: first u32
* @second: second u32
* @key: the hsiphash key
*/
u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key)
{
HPREAMBLE(8)
v3 ^= first;
HSIPROUND;
v0 ^= first;
v3 ^= second;
HSIPROUND;
v0 ^= second;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_2u32);
/**
* hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32
* @first: first u32
* @second: second u32
* @third: third u32
* @key: the hsiphash key
*/
u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third,
const hsiphash_key_t *key)
{
HPREAMBLE(12)
v3 ^= first;
HSIPROUND;
v0 ^= first;
v3 ^= second;
HSIPROUND;
v0 ^= second;
v3 ^= third;
HSIPROUND;
v0 ^= third;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_3u32);
/**
* hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32
* @first: first u32
* @second: second u32
* @third: third u32
* @forth: forth u32
* @key: the hsiphash key
*/
u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third,
const u32 forth, const hsiphash_key_t *key)
{
HPREAMBLE(16)
v3 ^= first;
HSIPROUND;
v0 ^= first;
v3 ^= second;
HSIPROUND;
v0 ^= second;
v3 ^= third;
HSIPROUND;
v0 ^= third;
v3 ^= forth;
HSIPROUND;
v0 ^= forth;
HPOSTAMBLE
}
EXPORT_SYMBOL(hsiphash_4u32);
#endif
Computing file changes ...
