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
sha256.c
/*
* SHA-256, as specified in
* http://csrc.nist.gov/groups/STM/cavp/documents/shs/sha256-384-512.pdf
*
* SHA-256 code by Jean-Luc Cooke <jlcooke@certainkey.com>.
*
* Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com>
* Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
* Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
* Copyright (c) 2014 Red Hat Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*/
#include <linux/bitops.h>
#include <linux/sha256.h>
#include <linux/string.h>
#include <asm/byteorder.h>
static inline u32 Ch(u32 x, u32 y, u32 z)
{
return z ^ (x & (y ^ z));
}
static inline u32 Maj(u32 x, u32 y, u32 z)
{
return (x & y) | (z & (x | y));
}
#define e0(x) (ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22))
#define e1(x) (ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25))
#define s0(x) (ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3))
#define s1(x) (ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10))
static inline void LOAD_OP(int I, u32 *W, const u8 *input)
{
W[I] = __be32_to_cpu(((__be32 *)(input))[I]);
}
static inline void BLEND_OP(int I, u32 *W)
{
W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16];
}
static void sha256_transform(u32 *state, const u8 *input)
{
u32 a, b, c, d, e, f, g, h, t1, t2;
u32 W[64];
int i;
/* load the input */
for (i = 0; i < 16; i++)
LOAD_OP(i, W, input);
/* now blend */
for (i = 16; i < 64; i++)
BLEND_OP(i, W);
/* load the state into our registers */
a = state[0]; b = state[1]; c = state[2]; d = state[3];
e = state[4]; f = state[5]; g = state[6]; h = state[7];
/* now iterate */
t1 = h + e1(e) + Ch(e, f, g) + 0x428a2f98 + W[0];
t2 = e0(a) + Maj(a, b, c); d += t1; h = t1 + t2;
t1 = g + e1(d) + Ch(d, e, f) + 0x71374491 + W[1];
t2 = e0(h) + Maj(h, a, b); c += t1; g = t1 + t2;
t1 = f + e1(c) + Ch(c, d, e) + 0xb5c0fbcf + W[2];
t2 = e0(g) + Maj(g, h, a); b += t1; f = t1 + t2;
t1 = e + e1(b) + Ch(b, c, d) + 0xe9b5dba5 + W[3];
t2 = e0(f) + Maj(f, g, h); a += t1; e = t1 + t2;
t1 = d + e1(a) + Ch(a, b, c) + 0x3956c25b + W[4];
t2 = e0(e) + Maj(e, f, g); h += t1; d = t1 + t2;
t1 = c + e1(h) + Ch(h, a, b) + 0x59f111f1 + W[5];
t2 = e0(d) + Maj(d, e, f); g += t1; c = t1 + t2;
t1 = b + e1(g) + Ch(g, h, a) + 0x923f82a4 + W[6];
t2 = e0(c) + Maj(c, d, e); f += t1; b = t1 + t2;
t1 = a + e1(f) + Ch(f, g, h) + 0xab1c5ed5 + W[7];
t2 = e0(b) + Maj(b, c, d); e += t1; a = t1 + t2;
t1 = h + e1(e) + Ch(e, f, g) + 0xd807aa98 + W[8];
t2 = e0(a) + Maj(a, b, c); d += t1; h = t1 + t2;
t1 = g + e1(d) + Ch(d, e, f) + 0x12835b01 + W[9];
t2 = e0(h) + Maj(h, a, b); c += t1; g = t1 + t2;
t1 = f + e1(c) + Ch(c, d, e) + 0x243185be + W[10];
t2 = e0(g) + Maj(g, h, a); b += t1; f = t1 + t2;
t1 = e + e1(b) + Ch(b, c, d) + 0x550c7dc3 + W[11];
t2 = e0(f) + Maj(f, g, h); a += t1; e = t1 + t2;
t1 = d + e1(a) + Ch(a, b, c) + 0x72be5d74 + W[12];
t2 = e0(e) + Maj(e, f, g); h += t1; d = t1 + t2;
t1 = c + e1(h) + Ch(h, a, b) + 0x80deb1fe + W[13];
t2 = e0(d) + Maj(d, e, f); g += t1; c = t1 + t2;
t1 = b + e1(g) + Ch(g, h, a) + 0x9bdc06a7 + W[14];
t2 = e0(c) + Maj(c, d, e); f += t1; b = t1 + t2;
t1 = a + e1(f) + Ch(f, g, h) + 0xc19bf174 + W[15];
t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
t1 = h + e1(e) + Ch(e, f, g) + 0xe49b69c1 + W[16];
t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
t1 = g + e1(d) + Ch(d, e, f) + 0xefbe4786 + W[17];
t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
t1 = f + e1(c) + Ch(c, d, e) + 0x0fc19dc6 + W[18];
t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
t1 = e + e1(b) + Ch(b, c, d) + 0x240ca1cc + W[19];
t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
t1 = d + e1(a) + Ch(a, b, c) + 0x2de92c6f + W[20];
t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
t1 = c + e1(h) + Ch(h, a, b) + 0x4a7484aa + W[21];
t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
t1 = b + e1(g) + Ch(g, h, a) + 0x5cb0a9dc + W[22];
t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
t1 = a + e1(f) + Ch(f, g, h) + 0x76f988da + W[23];
t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
t1 = h + e1(e) + Ch(e, f, g) + 0x983e5152 + W[24];
t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
t1 = g + e1(d) + Ch(d, e, f) + 0xa831c66d + W[25];
t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
t1 = f + e1(c) + Ch(c, d, e) + 0xb00327c8 + W[26];
t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
t1 = e + e1(b) + Ch(b, c, d) + 0xbf597fc7 + W[27];
t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
t1 = d + e1(a) + Ch(a, b, c) + 0xc6e00bf3 + W[28];
t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
t1 = c + e1(h) + Ch(h, a, b) + 0xd5a79147 + W[29];
t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
t1 = b + e1(g) + Ch(g, h, a) + 0x06ca6351 + W[30];
t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
t1 = a + e1(f) + Ch(f, g, h) + 0x14292967 + W[31];
t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
t1 = h + e1(e) + Ch(e, f, g) + 0x27b70a85 + W[32];
t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
t1 = g + e1(d) + Ch(d, e, f) + 0x2e1b2138 + W[33];
t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
t1 = f + e1(c) + Ch(c, d, e) + 0x4d2c6dfc + W[34];
t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
t1 = e + e1(b) + Ch(b, c, d) + 0x53380d13 + W[35];
t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
t1 = d + e1(a) + Ch(a, b, c) + 0x650a7354 + W[36];
t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
t1 = c + e1(h) + Ch(h, a, b) + 0x766a0abb + W[37];
t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
t1 = b + e1(g) + Ch(g, h, a) + 0x81c2c92e + W[38];
t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
t1 = a + e1(f) + Ch(f, g, h) + 0x92722c85 + W[39];
t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
t1 = h + e1(e) + Ch(e, f, g) + 0xa2bfe8a1 + W[40];
t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
t1 = g + e1(d) + Ch(d, e, f) + 0xa81a664b + W[41];
t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
t1 = f + e1(c) + Ch(c, d, e) + 0xc24b8b70 + W[42];
t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
t1 = e + e1(b) + Ch(b, c, d) + 0xc76c51a3 + W[43];
t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
t1 = d + e1(a) + Ch(a, b, c) + 0xd192e819 + W[44];
t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
t1 = c + e1(h) + Ch(h, a, b) + 0xd6990624 + W[45];
t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
t1 = b + e1(g) + Ch(g, h, a) + 0xf40e3585 + W[46];
t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
t1 = a + e1(f) + Ch(f, g, h) + 0x106aa070 + W[47];
t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
t1 = h + e1(e) + Ch(e, f, g) + 0x19a4c116 + W[48];
t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
t1 = g + e1(d) + Ch(d, e, f) + 0x1e376c08 + W[49];
t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
t1 = f + e1(c) + Ch(c, d, e) + 0x2748774c + W[50];
t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
t1 = e + e1(b) + Ch(b, c, d) + 0x34b0bcb5 + W[51];
t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
t1 = d + e1(a) + Ch(a, b, c) + 0x391c0cb3 + W[52];
t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
t1 = c + e1(h) + Ch(h, a, b) + 0x4ed8aa4a + W[53];
t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
t1 = b + e1(g) + Ch(g, h, a) + 0x5b9cca4f + W[54];
t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
t1 = a + e1(f) + Ch(f, g, h) + 0x682e6ff3 + W[55];
t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
t1 = h + e1(e) + Ch(e, f, g) + 0x748f82ee + W[56];
t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2;
t1 = g + e1(d) + Ch(d, e, f) + 0x78a5636f + W[57];
t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2;
t1 = f + e1(c) + Ch(c, d, e) + 0x84c87814 + W[58];
t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2;
t1 = e + e1(b) + Ch(b, c, d) + 0x8cc70208 + W[59];
t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2;
t1 = d + e1(a) + Ch(a, b, c) + 0x90befffa + W[60];
t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2;
t1 = c + e1(h) + Ch(h, a, b) + 0xa4506ceb + W[61];
t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2;
t1 = b + e1(g) + Ch(g, h, a) + 0xbef9a3f7 + W[62];
t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2;
t1 = a + e1(f) + Ch(f, g, h) + 0xc67178f2 + W[63];
t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2;
state[0] += a; state[1] += b; state[2] += c; state[3] += d;
state[4] += e; state[5] += f; state[6] += g; state[7] += h;
/* clear any sensitive info... */
a = b = c = d = e = f = g = h = t1 = t2 = 0;
memset(W, 0, 64 * sizeof(u32));
}
int sha256_init(struct sha256_state *sctx)
{
sctx->state[0] = SHA256_H0;
sctx->state[1] = SHA256_H1;
sctx->state[2] = SHA256_H2;
sctx->state[3] = SHA256_H3;
sctx->state[4] = SHA256_H4;
sctx->state[5] = SHA256_H5;
sctx->state[6] = SHA256_H6;
sctx->state[7] = SHA256_H7;
sctx->count = 0;
return 0;
}
int sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
{
unsigned int partial, done;
const u8 *src;
partial = sctx->count & 0x3f;
sctx->count += len;
done = 0;
src = data;
if ((partial + len) > 63) {
if (partial) {
done = -partial;
memcpy(sctx->buf + partial, data, done + 64);
src = sctx->buf;
}
do {
sha256_transform(sctx->state, src);
done += 64;
src = data + done;
} while (done + 63 < len);
partial = 0;
}
memcpy(sctx->buf + partial, src, len - done);
return 0;
}
int sha256_final(struct sha256_state *sctx, u8 *out)
{
__be32 *dst = (__be32 *)out;
__be64 bits;
unsigned int index, pad_len;
int i;
static const u8 padding[64] = { 0x80, };
/* Save number of bits */
bits = cpu_to_be64(sctx->count << 3);
/* Pad out to 56 mod 64. */
index = sctx->count & 0x3f;
pad_len = (index < 56) ? (56 - index) : ((64+56) - index);
sha256_update(sctx, padding, pad_len);
/* Append length (before padding) */
sha256_update(sctx, (const u8 *)&bits, sizeof(bits));
/* Store state in digest */
for (i = 0; i < 8; i++)
dst[i] = cpu_to_be32(sctx->state[i]);
/* Zeroize sensitive information. */
memset(sctx, 0, sizeof(*sctx));
return 0;
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...