linux_dsm_epyc7002/fs/xfs/xfs_bmap_btree.c

971 lines
25 KiB
C
Raw Normal View History

/*
* Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
* All Rights Reserved.
*
* 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.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_alloc.h"
#include "xfs_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
#include "xfs_dinode.h"
/*
* Determine the extent state.
*/
/* ARGSUSED */
STATIC xfs_exntst_t
xfs_extent_state(
xfs_filblks_t blks,
int extent_flag)
{
if (extent_flag) {
ASSERT(blks != 0); /* saved for DMIG */
return XFS_EXT_UNWRITTEN;
}
return XFS_EXT_NORM;
}
/*
* Convert on-disk form of btree root to in-memory form.
*/
void
xfs_bmdr_to_bmbt(
struct xfs_inode *ip,
xfs_bmdr_block_t *dblock,
int dblocklen,
struct xfs_btree_block *rblock,
int rblocklen)
{
struct xfs_mount *mp = ip->i_mount;
int dmxr;
xfs_bmbt_key_t *fkp;
__be64 *fpp;
xfs_bmbt_key_t *tkp;
__be64 *tpp;
if (xfs_sb_version_hascrc(&mp->m_sb))
xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
XFS_BMAP_CRC_MAGIC, 0, 0, ip->i_ino,
XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS);
else
xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
XFS_BMAP_MAGIC, 0, 0, ip->i_ino,
XFS_BTREE_LONG_PTRS);
rblock->bb_level = dblock->bb_level;
ASSERT(be16_to_cpu(rblock->bb_level) > 0);
rblock->bb_numrecs = dblock->bb_numrecs;
dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0);
fkp = XFS_BMDR_KEY_ADDR(dblock, 1);
tkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
fpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
tpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
dmxr = be16_to_cpu(dblock->bb_numrecs);
memcpy(tkp, fkp, sizeof(*fkp) * dmxr);
memcpy(tpp, fpp, sizeof(*fpp) * dmxr);
}
/*
* Convert a compressed bmap extent record to an uncompressed form.
* This code must be in sync with the routines xfs_bmbt_get_startoff,
* xfs_bmbt_get_startblock, xfs_bmbt_get_blockcount and xfs_bmbt_get_state.
*/
STATIC void
__xfs_bmbt_get_all(
__uint64_t l0,
__uint64_t l1,
xfs_bmbt_irec_t *s)
{
int ext_flag;
xfs_exntst_t st;
ext_flag = (int)(l0 >> (64 - BMBT_EXNTFLAG_BITLEN));
s->br_startoff = ((xfs_fileoff_t)l0 &
xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN)) >> 9;
#if XFS_BIG_BLKNOS
s->br_startblock = (((xfs_fsblock_t)l0 & xfs_mask64lo(9)) << 43) |
(((xfs_fsblock_t)l1) >> 21);
#else
#ifdef DEBUG
{
xfs_dfsbno_t b;
b = (((xfs_dfsbno_t)l0 & xfs_mask64lo(9)) << 43) |
(((xfs_dfsbno_t)l1) >> 21);
ASSERT((b >> 32) == 0 || isnulldstartblock(b));
s->br_startblock = (xfs_fsblock_t)b;
}
#else /* !DEBUG */
s->br_startblock = (xfs_fsblock_t)(((xfs_dfsbno_t)l1) >> 21);
#endif /* DEBUG */
#endif /* XFS_BIG_BLKNOS */
s->br_blockcount = (xfs_filblks_t)(l1 & xfs_mask64lo(21));
/* This is xfs_extent_state() in-line */
if (ext_flag) {
ASSERT(s->br_blockcount != 0); /* saved for DMIG */
st = XFS_EXT_UNWRITTEN;
} else
st = XFS_EXT_NORM;
s->br_state = st;
}
void
xfs_bmbt_get_all(
xfs_bmbt_rec_host_t *r,
xfs_bmbt_irec_t *s)
{
__xfs_bmbt_get_all(r->l0, r->l1, s);
}
/*
* Extract the blockcount field from an in memory bmap extent record.
*/
xfs_filblks_t
xfs_bmbt_get_blockcount(
xfs_bmbt_rec_host_t *r)
{
return (xfs_filblks_t)(r->l1 & xfs_mask64lo(21));
}
/*
* Extract the startblock field from an in memory bmap extent record.
*/
xfs_fsblock_t
xfs_bmbt_get_startblock(
xfs_bmbt_rec_host_t *r)
{
#if XFS_BIG_BLKNOS
return (((xfs_fsblock_t)r->l0 & xfs_mask64lo(9)) << 43) |
(((xfs_fsblock_t)r->l1) >> 21);
#else
#ifdef DEBUG
xfs_dfsbno_t b;
b = (((xfs_dfsbno_t)r->l0 & xfs_mask64lo(9)) << 43) |
(((xfs_dfsbno_t)r->l1) >> 21);
ASSERT((b >> 32) == 0 || isnulldstartblock(b));
return (xfs_fsblock_t)b;
#else /* !DEBUG */
return (xfs_fsblock_t)(((xfs_dfsbno_t)r->l1) >> 21);
#endif /* DEBUG */
#endif /* XFS_BIG_BLKNOS */
}
/*
* Extract the startoff field from an in memory bmap extent record.
*/
xfs_fileoff_t
xfs_bmbt_get_startoff(
xfs_bmbt_rec_host_t *r)
{
return ((xfs_fileoff_t)r->l0 &
xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN)) >> 9;
}
xfs_exntst_t
xfs_bmbt_get_state(
xfs_bmbt_rec_host_t *r)
{
int ext_flag;
ext_flag = (int)((r->l0) >> (64 - BMBT_EXNTFLAG_BITLEN));
return xfs_extent_state(xfs_bmbt_get_blockcount(r),
ext_flag);
}
/*
* Extract the blockcount field from an on disk bmap extent record.
*/
xfs_filblks_t
xfs_bmbt_disk_get_blockcount(
xfs_bmbt_rec_t *r)
{
return (xfs_filblks_t)(be64_to_cpu(r->l1) & xfs_mask64lo(21));
}
/*
* Extract the startoff field from a disk format bmap extent record.
*/
xfs_fileoff_t
xfs_bmbt_disk_get_startoff(
xfs_bmbt_rec_t *r)
{
return ((xfs_fileoff_t)be64_to_cpu(r->l0) &
xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN)) >> 9;
}
/*
* Set all the fields in a bmap extent record from the arguments.
*/
void
xfs_bmbt_set_allf(
xfs_bmbt_rec_host_t *r,
xfs_fileoff_t startoff,
xfs_fsblock_t startblock,
xfs_filblks_t blockcount,
xfs_exntst_t state)
{
int extent_flag = (state == XFS_EXT_NORM) ? 0 : 1;
ASSERT(state == XFS_EXT_NORM || state == XFS_EXT_UNWRITTEN);
ASSERT((startoff & xfs_mask64hi(64-BMBT_STARTOFF_BITLEN)) == 0);
ASSERT((blockcount & xfs_mask64hi(64-BMBT_BLOCKCOUNT_BITLEN)) == 0);
#if XFS_BIG_BLKNOS
ASSERT((startblock & xfs_mask64hi(64-BMBT_STARTBLOCK_BITLEN)) == 0);
r->l0 = ((xfs_bmbt_rec_base_t)extent_flag << 63) |
((xfs_bmbt_rec_base_t)startoff << 9) |
((xfs_bmbt_rec_base_t)startblock >> 43);
r->l1 = ((xfs_bmbt_rec_base_t)startblock << 21) |
((xfs_bmbt_rec_base_t)blockcount &
(xfs_bmbt_rec_base_t)xfs_mask64lo(21));
#else /* !XFS_BIG_BLKNOS */
if (isnullstartblock(startblock)) {
r->l0 = ((xfs_bmbt_rec_base_t)extent_flag << 63) |
((xfs_bmbt_rec_base_t)startoff << 9) |
(xfs_bmbt_rec_base_t)xfs_mask64lo(9);
r->l1 = xfs_mask64hi(11) |
((xfs_bmbt_rec_base_t)startblock << 21) |
((xfs_bmbt_rec_base_t)blockcount &
(xfs_bmbt_rec_base_t)xfs_mask64lo(21));
} else {
r->l0 = ((xfs_bmbt_rec_base_t)extent_flag << 63) |
((xfs_bmbt_rec_base_t)startoff << 9);
r->l1 = ((xfs_bmbt_rec_base_t)startblock << 21) |
((xfs_bmbt_rec_base_t)blockcount &
(xfs_bmbt_rec_base_t)xfs_mask64lo(21));
}
#endif /* XFS_BIG_BLKNOS */
}
/*
* Set all the fields in a bmap extent record from the uncompressed form.
*/
void
xfs_bmbt_set_all(
xfs_bmbt_rec_host_t *r,
xfs_bmbt_irec_t *s)
{
xfs_bmbt_set_allf(r, s->br_startoff, s->br_startblock,
s->br_blockcount, s->br_state);
}
/*
* Set all the fields in a disk format bmap extent record from the arguments.
*/
void
xfs_bmbt_disk_set_allf(
xfs_bmbt_rec_t *r,
xfs_fileoff_t startoff,
xfs_fsblock_t startblock,
xfs_filblks_t blockcount,
xfs_exntst_t state)
{
int extent_flag = (state == XFS_EXT_NORM) ? 0 : 1;
ASSERT(state == XFS_EXT_NORM || state == XFS_EXT_UNWRITTEN);
ASSERT((startoff & xfs_mask64hi(64-BMBT_STARTOFF_BITLEN)) == 0);
ASSERT((blockcount & xfs_mask64hi(64-BMBT_BLOCKCOUNT_BITLEN)) == 0);
#if XFS_BIG_BLKNOS
ASSERT((startblock & xfs_mask64hi(64-BMBT_STARTBLOCK_BITLEN)) == 0);
r->l0 = cpu_to_be64(
((xfs_bmbt_rec_base_t)extent_flag << 63) |
((xfs_bmbt_rec_base_t)startoff << 9) |
((xfs_bmbt_rec_base_t)startblock >> 43));
r->l1 = cpu_to_be64(
((xfs_bmbt_rec_base_t)startblock << 21) |
((xfs_bmbt_rec_base_t)blockcount &
(xfs_bmbt_rec_base_t)xfs_mask64lo(21)));
#else /* !XFS_BIG_BLKNOS */
if (isnullstartblock(startblock)) {
r->l0 = cpu_to_be64(
((xfs_bmbt_rec_base_t)extent_flag << 63) |
((xfs_bmbt_rec_base_t)startoff << 9) |
(xfs_bmbt_rec_base_t)xfs_mask64lo(9));
r->l1 = cpu_to_be64(xfs_mask64hi(11) |
((xfs_bmbt_rec_base_t)startblock << 21) |
((xfs_bmbt_rec_base_t)blockcount &
(xfs_bmbt_rec_base_t)xfs_mask64lo(21)));
} else {
r->l0 = cpu_to_be64(
((xfs_bmbt_rec_base_t)extent_flag << 63) |
((xfs_bmbt_rec_base_t)startoff << 9));
r->l1 = cpu_to_be64(
((xfs_bmbt_rec_base_t)startblock << 21) |
((xfs_bmbt_rec_base_t)blockcount &
(xfs_bmbt_rec_base_t)xfs_mask64lo(21)));
}
#endif /* XFS_BIG_BLKNOS */
}
/*
* Set all the fields in a bmap extent record from the uncompressed form.
*/
STATIC void
xfs_bmbt_disk_set_all(
xfs_bmbt_rec_t *r,
xfs_bmbt_irec_t *s)
{
xfs_bmbt_disk_set_allf(r, s->br_startoff, s->br_startblock,
s->br_blockcount, s->br_state);
}
/*
* Set the blockcount field in a bmap extent record.
*/
void
xfs_bmbt_set_blockcount(
xfs_bmbt_rec_host_t *r,
xfs_filblks_t v)
{
ASSERT((v & xfs_mask64hi(43)) == 0);
r->l1 = (r->l1 & (xfs_bmbt_rec_base_t)xfs_mask64hi(43)) |
(xfs_bmbt_rec_base_t)(v & xfs_mask64lo(21));
}
/*
* Set the startblock field in a bmap extent record.
*/
void
xfs_bmbt_set_startblock(
xfs_bmbt_rec_host_t *r,
xfs_fsblock_t v)
{
#if XFS_BIG_BLKNOS
ASSERT((v & xfs_mask64hi(12)) == 0);
r->l0 = (r->l0 & (xfs_bmbt_rec_base_t)xfs_mask64hi(55)) |
(xfs_bmbt_rec_base_t)(v >> 43);
r->l1 = (r->l1 & (xfs_bmbt_rec_base_t)xfs_mask64lo(21)) |
(xfs_bmbt_rec_base_t)(v << 21);
#else /* !XFS_BIG_BLKNOS */
if (isnullstartblock(v)) {
r->l0 |= (xfs_bmbt_rec_base_t)xfs_mask64lo(9);
r->l1 = (xfs_bmbt_rec_base_t)xfs_mask64hi(11) |
((xfs_bmbt_rec_base_t)v << 21) |
(r->l1 & (xfs_bmbt_rec_base_t)xfs_mask64lo(21));
} else {
r->l0 &= ~(xfs_bmbt_rec_base_t)xfs_mask64lo(9);
r->l1 = ((xfs_bmbt_rec_base_t)v << 21) |
(r->l1 & (xfs_bmbt_rec_base_t)xfs_mask64lo(21));
}
#endif /* XFS_BIG_BLKNOS */
}
/*
* Set the startoff field in a bmap extent record.
*/
void
xfs_bmbt_set_startoff(
xfs_bmbt_rec_host_t *r,
xfs_fileoff_t v)
{
ASSERT((v & xfs_mask64hi(9)) == 0);
r->l0 = (r->l0 & (xfs_bmbt_rec_base_t) xfs_mask64hi(1)) |
((xfs_bmbt_rec_base_t)v << 9) |
(r->l0 & (xfs_bmbt_rec_base_t)xfs_mask64lo(9));
}
/*
* Set the extent state field in a bmap extent record.
*/
void
xfs_bmbt_set_state(
xfs_bmbt_rec_host_t *r,
xfs_exntst_t v)
{
ASSERT(v == XFS_EXT_NORM || v == XFS_EXT_UNWRITTEN);
if (v == XFS_EXT_NORM)
r->l0 &= xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN);
else
r->l0 |= xfs_mask64hi(BMBT_EXNTFLAG_BITLEN);
}
/*
* Convert in-memory form of btree root to on-disk form.
*/
void
xfs_bmbt_to_bmdr(
struct xfs_mount *mp,
struct xfs_btree_block *rblock,
int rblocklen,
xfs_bmdr_block_t *dblock,
int dblocklen)
{
int dmxr;
xfs_bmbt_key_t *fkp;
__be64 *fpp;
xfs_bmbt_key_t *tkp;
__be64 *tpp;
if (xfs_sb_version_hascrc(&mp->m_sb)) {
ASSERT(rblock->bb_magic == cpu_to_be32(XFS_BMAP_CRC_MAGIC));
ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_uuid));
ASSERT(rblock->bb_u.l.bb_blkno ==
cpu_to_be64(XFS_BUF_DADDR_NULL));
} else
ASSERT(rblock->bb_magic == cpu_to_be32(XFS_BMAP_MAGIC));
ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLDFSBNO));
ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLDFSBNO));
ASSERT(rblock->bb_level != 0);
dblock->bb_level = rblock->bb_level;
dblock->bb_numrecs = rblock->bb_numrecs;
dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0);
fkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
tkp = XFS_BMDR_KEY_ADDR(dblock, 1);
fpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
tpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
dmxr = be16_to_cpu(dblock->bb_numrecs);
memcpy(tkp, fkp, sizeof(*fkp) * dmxr);
memcpy(tpp, fpp, sizeof(*fpp) * dmxr);
}
/*
* Check extent records, which have just been read, for
* any bit in the extent flag field. ASSERT on debug
* kernels, as this condition should not occur.
* Return an error condition (1) if any flags found,
* otherwise return 0.
*/
int
xfs_check_nostate_extents(
xfs_ifork_t *ifp,
xfs_extnum_t idx,
xfs_extnum_t num)
{
for (; num > 0; num--, idx++) {
xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, idx);
if ((ep->l0 >>
(64 - BMBT_EXNTFLAG_BITLEN)) != 0) {
ASSERT(0);
return 1;
}
}
return 0;
}
STATIC struct xfs_btree_cur *
xfs_bmbt_dup_cursor(
struct xfs_btree_cur *cur)
{
struct xfs_btree_cur *new;
new = xfs_bmbt_init_cursor(cur->bc_mp, cur->bc_tp,
cur->bc_private.b.ip, cur->bc_private.b.whichfork);
/*
* Copy the firstblock, flist, and flags values,
* since init cursor doesn't get them.
*/
new->bc_private.b.firstblock = cur->bc_private.b.firstblock;
new->bc_private.b.flist = cur->bc_private.b.flist;
new->bc_private.b.flags = cur->bc_private.b.flags;
return new;
}
STATIC void
xfs_bmbt_update_cursor(
struct xfs_btree_cur *src,
struct xfs_btree_cur *dst)
{
ASSERT((dst->bc_private.b.firstblock != NULLFSBLOCK) ||
(dst->bc_private.b.ip->i_d.di_flags & XFS_DIFLAG_REALTIME));
ASSERT(dst->bc_private.b.flist == src->bc_private.b.flist);
dst->bc_private.b.allocated += src->bc_private.b.allocated;
dst->bc_private.b.firstblock = src->bc_private.b.firstblock;
src->bc_private.b.allocated = 0;
}
STATIC int
xfs_bmbt_alloc_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *start,
union xfs_btree_ptr *new,
int length,
int *stat)
{
xfs_alloc_arg_t args; /* block allocation args */
int error; /* error return value */
memset(&args, 0, sizeof(args));
args.tp = cur->bc_tp;
args.mp = cur->bc_mp;
args.fsbno = cur->bc_private.b.firstblock;
args.firstblock = args.fsbno;
if (args.fsbno == NULLFSBLOCK) {
args.fsbno = be64_to_cpu(start->l);
args.type = XFS_ALLOCTYPE_START_BNO;
/*
* Make sure there is sufficient room left in the AG to
* complete a full tree split for an extent insert. If
* we are converting the middle part of an extent then
* we may need space for two tree splits.
*
* We are relying on the caller to make the correct block
* reservation for this operation to succeed. If the
* reservation amount is insufficient then we may fail a
* block allocation here and corrupt the filesystem.
*/
args.minleft = xfs_trans_get_block_res(args.tp);
} else if (cur->bc_private.b.flist->xbf_low) {
args.type = XFS_ALLOCTYPE_START_BNO;
} else {
args.type = XFS_ALLOCTYPE_NEAR_BNO;
}
args.minlen = args.maxlen = args.prod = 1;
args.wasdel = cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL;
if (!args.wasdel && xfs_trans_get_block_res(args.tp) == 0) {
error = XFS_ERROR(ENOSPC);
goto error0;
}
error = xfs_alloc_vextent(&args);
if (error)
goto error0;
if (args.fsbno == NULLFSBLOCK && args.minleft) {
/*
* Could not find an AG with enough free space to satisfy
* a full btree split. Try again without minleft and if
* successful activate the lowspace algorithm.
*/
args.fsbno = 0;
args.type = XFS_ALLOCTYPE_FIRST_AG;
args.minleft = 0;
error = xfs_alloc_vextent(&args);
if (error)
goto error0;
cur->bc_private.b.flist->xbf_low = 1;
}
if (args.fsbno == NULLFSBLOCK) {
XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
*stat = 0;
return 0;
}
ASSERT(args.len == 1);
cur->bc_private.b.firstblock = args.fsbno;
cur->bc_private.b.allocated++;
cur->bc_private.b.ip->i_d.di_nblocks++;
xfs_trans_log_inode(args.tp, cur->bc_private.b.ip, XFS_ILOG_CORE);
xfs_trans_mod_dquot_byino(args.tp, cur->bc_private.b.ip,
XFS_TRANS_DQ_BCOUNT, 1L);
new->l = cpu_to_be64(args.fsbno);
XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
*stat = 1;
return 0;
error0:
XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
return error;
}
STATIC int
xfs_bmbt_free_block(
struct xfs_btree_cur *cur,
struct xfs_buf *bp)
{
struct xfs_mount *mp = cur->bc_mp;
struct xfs_inode *ip = cur->bc_private.b.ip;
struct xfs_trans *tp = cur->bc_tp;
xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(bp));
xfs_bmap_add_free(fsbno, 1, cur->bc_private.b.flist, mp);
ip->i_d.di_nblocks--;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
xfs_trans_binval(tp, bp);
return 0;
}
STATIC int
xfs_bmbt_get_minrecs(
struct xfs_btree_cur *cur,
int level)
{
if (level == cur->bc_nlevels - 1) {
struct xfs_ifork *ifp;
ifp = XFS_IFORK_PTR(cur->bc_private.b.ip,
cur->bc_private.b.whichfork);
return xfs_bmbt_maxrecs(cur->bc_mp,
ifp->if_broot_bytes, level == 0) / 2;
}
return cur->bc_mp->m_bmap_dmnr[level != 0];
}
int
xfs_bmbt_get_maxrecs(
struct xfs_btree_cur *cur,
int level)
{
if (level == cur->bc_nlevels - 1) {
struct xfs_ifork *ifp;
ifp = XFS_IFORK_PTR(cur->bc_private.b.ip,
cur->bc_private.b.whichfork);
return xfs_bmbt_maxrecs(cur->bc_mp,
ifp->if_broot_bytes, level == 0);
}
return cur->bc_mp->m_bmap_dmxr[level != 0];
}
/*
* Get the maximum records we could store in the on-disk format.
*
* For non-root nodes this is equivalent to xfs_bmbt_get_maxrecs, but
* for the root node this checks the available space in the dinode fork
* so that we can resize the in-memory buffer to match it. After a
* resize to the maximum size this function returns the same value
* as xfs_bmbt_get_maxrecs for the root node, too.
*/
STATIC int
xfs_bmbt_get_dmaxrecs(
struct xfs_btree_cur *cur,
int level)
{
if (level != cur->bc_nlevels - 1)
return cur->bc_mp->m_bmap_dmxr[level != 0];
return xfs_bmdr_maxrecs(cur->bc_mp, cur->bc_private.b.forksize,
level == 0);
}
STATIC void
xfs_bmbt_init_key_from_rec(
union xfs_btree_key *key,
union xfs_btree_rec *rec)
{
key->bmbt.br_startoff =
cpu_to_be64(xfs_bmbt_disk_get_startoff(&rec->bmbt));
}
STATIC void
xfs_bmbt_init_rec_from_key(
union xfs_btree_key *key,
union xfs_btree_rec *rec)
{
ASSERT(key->bmbt.br_startoff != 0);
xfs_bmbt_disk_set_allf(&rec->bmbt, be64_to_cpu(key->bmbt.br_startoff),
0, 0, XFS_EXT_NORM);
}
STATIC void
xfs_bmbt_init_rec_from_cur(
struct xfs_btree_cur *cur,
union xfs_btree_rec *rec)
{
xfs_bmbt_disk_set_all(&rec->bmbt, &cur->bc_rec.b);
}
STATIC void
xfs_bmbt_init_ptr_from_cur(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *ptr)
{
ptr->l = 0;
}
STATIC __int64_t
xfs_bmbt_key_diff(
struct xfs_btree_cur *cur,
union xfs_btree_key *key)
{
return (__int64_t)be64_to_cpu(key->bmbt.br_startoff) -
cur->bc_rec.b.br_startoff;
}
static bool
xfs_bmbt_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
unsigned int level;
switch (block->bb_magic) {
case cpu_to_be32(XFS_BMAP_CRC_MAGIC):
if (!xfs_sb_version_hascrc(&mp->m_sb))
return false;
if (!uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_uuid))
return false;
if (be64_to_cpu(block->bb_u.l.bb_blkno) != bp->b_bn)
return false;
/*
* XXX: need a better way of verifying the owner here. Right now
* just make sure there has been one set.
*/
if (be64_to_cpu(block->bb_u.l.bb_owner) == 0)
return false;
/* fall through */
case cpu_to_be32(XFS_BMAP_MAGIC):
break;
default:
return false;
}
/*
* numrecs and level verification.
*
* We don't know what fork we belong to, so just verify that the level
* is less than the maximum of the two. Later checks will be more
* precise.
*/
level = be16_to_cpu(block->bb_level);
if (level > max(mp->m_bm_maxlevels[0], mp->m_bm_maxlevels[1]))
return false;
if (be16_to_cpu(block->bb_numrecs) > mp->m_bmap_dmxr[level != 0])
return false;
/* sibling pointer verification */
if (!block->bb_u.l.bb_leftsib ||
(block->bb_u.l.bb_leftsib != cpu_to_be64(NULLDFSBNO) &&
!XFS_FSB_SANITY_CHECK(mp, be64_to_cpu(block->bb_u.l.bb_leftsib))))
return false;
if (!block->bb_u.l.bb_rightsib ||
(block->bb_u.l.bb_rightsib != cpu_to_be64(NULLDFSBNO) &&
!XFS_FSB_SANITY_CHECK(mp, be64_to_cpu(block->bb_u.l.bb_rightsib))))
return false;
return true;
}
static void
xfs_bmbt_read_verify(
struct xfs_buf *bp)
{
if (!xfs_btree_lblock_verify_crc(bp))
xfs_buf_ioerror(bp, EFSBADCRC);
else if (!xfs_bmbt_verify(bp))
xfs_buf_ioerror(bp, EFSCORRUPTED);
if (bp->b_error) {
trace_xfs_btree_corrupt(bp, _RET_IP_);
xfs_verifier_error(bp);
}
}
static void
xfs_bmbt_write_verify(
struct xfs_buf *bp)
{
if (!xfs_bmbt_verify(bp)) {
trace_xfs_btree_corrupt(bp, _RET_IP_);
xfs_buf_ioerror(bp, EFSCORRUPTED);
xfs_verifier_error(bp);
return;
}
xfs_btree_lblock_calc_crc(bp);
}
const struct xfs_buf_ops xfs_bmbt_buf_ops = {
.verify_read = xfs_bmbt_read_verify,
.verify_write = xfs_bmbt_write_verify,
};
#if defined(DEBUG) || defined(XFS_WARN)
STATIC int
xfs_bmbt_keys_inorder(
struct xfs_btree_cur *cur,
union xfs_btree_key *k1,
union xfs_btree_key *k2)
{
return be64_to_cpu(k1->bmbt.br_startoff) <
be64_to_cpu(k2->bmbt.br_startoff);
}
STATIC int
xfs_bmbt_recs_inorder(
struct xfs_btree_cur *cur,
union xfs_btree_rec *r1,
union xfs_btree_rec *r2)
{
return xfs_bmbt_disk_get_startoff(&r1->bmbt) +
xfs_bmbt_disk_get_blockcount(&r1->bmbt) <=
xfs_bmbt_disk_get_startoff(&r2->bmbt);
}
#endif /* DEBUG */
static const struct xfs_btree_ops xfs_bmbt_ops = {
.rec_len = sizeof(xfs_bmbt_rec_t),
.key_len = sizeof(xfs_bmbt_key_t),
.dup_cursor = xfs_bmbt_dup_cursor,
.update_cursor = xfs_bmbt_update_cursor,
.alloc_block = xfs_bmbt_alloc_block,
.free_block = xfs_bmbt_free_block,
.get_maxrecs = xfs_bmbt_get_maxrecs,
.get_minrecs = xfs_bmbt_get_minrecs,
.get_dmaxrecs = xfs_bmbt_get_dmaxrecs,
.init_key_from_rec = xfs_bmbt_init_key_from_rec,
.init_rec_from_key = xfs_bmbt_init_rec_from_key,
.init_rec_from_cur = xfs_bmbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_bmbt_init_ptr_from_cur,
.key_diff = xfs_bmbt_key_diff,
.buf_ops = &xfs_bmbt_buf_ops,
#if defined(DEBUG) || defined(XFS_WARN)
.keys_inorder = xfs_bmbt_keys_inorder,
.recs_inorder = xfs_bmbt_recs_inorder,
#endif
};
/*
* Allocate a new bmap btree cursor.
*/
struct xfs_btree_cur * /* new bmap btree cursor */
xfs_bmbt_init_cursor(
struct xfs_mount *mp, /* file system mount point */
struct xfs_trans *tp, /* transaction pointer */
struct xfs_inode *ip, /* inode owning the btree */
int whichfork) /* data or attr fork */
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
struct xfs_btree_cur *cur;
cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_SLEEP);
cur->bc_tp = tp;
cur->bc_mp = mp;
cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
cur->bc_btnum = XFS_BTNUM_BMAP;
cur->bc_blocklog = mp->m_sb.sb_blocklog;
cur->bc_ops = &xfs_bmbt_ops;
cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
if (xfs_sb_version_hascrc(&mp->m_sb))
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
cur->bc_private.b.ip = ip;
cur->bc_private.b.firstblock = NULLFSBLOCK;
cur->bc_private.b.flist = NULL;
cur->bc_private.b.allocated = 0;
cur->bc_private.b.flags = 0;
cur->bc_private.b.whichfork = whichfork;
return cur;
}
/*
* Calculate number of records in a bmap btree block.
*/
int
xfs_bmbt_maxrecs(
struct xfs_mount *mp,
int blocklen,
int leaf)
{
blocklen -= XFS_BMBT_BLOCK_LEN(mp);
if (leaf)
return blocklen / sizeof(xfs_bmbt_rec_t);
return blocklen / (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t));
}
/*
* Calculate number of records in a bmap btree inode root.
*/
int
xfs_bmdr_maxrecs(
struct xfs_mount *mp,
int blocklen,
int leaf)
{
blocklen -= sizeof(xfs_bmdr_block_t);
if (leaf)
return blocklen / sizeof(xfs_bmdr_rec_t);
return blocklen / (sizeof(xfs_bmdr_key_t) + sizeof(xfs_bmdr_ptr_t));
}
xfs: swap extents operations for CRC filesystems For CRC enabled filesystems, we can't just swap inode forks from one inode to another when defragmenting a file - the blocks in the inode fork bmap btree contain pointers back to the owner inode. Hence if we are to swap the inode forks we have to atomically modify every block in the btree during the transaction. We are doing an entire fork swap here, so we could create a new transaction item type that indicates we are changing the owner of a certain structure from one value to another. If we combine this with ordered buffer logging to modify all the buffers in the tree, then we can change the buffers in the tree without needing log space for the operation. However, this then requires log recovery to perform the modification of the owner information of the objects/structures in question. This does introduce some interesting ordering details into recovery: we have to make sure that the owner change replay occurs after the change that moves the objects is made, not before. Hence we can't use a separate log item for this as we have no guarantee of strict ordering between multiple items in the log due to the relogging action of asynchronous transaction commits. Hence there is no "generic" method we can use for changing the ownership of arbitrary metadata structures. For inode forks, however, there is a simple method of communicating that the fork contents need the owner rewritten - we can pass a inode log format flag for the fork for the transaction that does a fork swap. This flag will then follow the inode fork through relogging actions so when the swap actually gets replayed the ownership can be changed immediately by log recovery. So that gives us a simple method of "whole fork" exchange between two inodes. This is relatively simple to implement, so it makes sense to do this as an initial implementation to support xfs_fsr on CRC enabled filesytems in the same manner as we do on existing filesystems. This commit introduces the swapext driven functionality, the recovery functionality will be in a separate patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:44 +07:00
/*
* Change the owner of a btree format fork fo the inode passed in. Change it to
* the owner of that is passed in so that we can change owners before or after
* we switch forks between inodes. The operation that the caller is doing will
* determine whether is needs to change owner before or after the switch.
*
xfs: recovery of swap extents operations for CRC filesystems This is the recovery side of the btree block owner change operation performed by swapext on CRC enabled filesystems. We detect that an owner change is needed by the flag that has been placed on the inode log format flag field. Because the inode recovery is being replayed after the buffers that make up the BMBT in the given checkpoint, we can walk all the buffers and directly modify them when we see the flag set on an inode. Because the inode can be relogged and hence present in multiple chekpoints with the "change owner" flag set, we could do multiple passes across the inode to do this change. While this isn't optimal, we can't directly ignore the flag as there may be multiple independent swap extent operations being replayed on the same inode in different checkpoints so we can't ignore them. Further, because the owner change operation uses ordered buffers, we might have buffers that are newer on disk than the current checkpoint and so already have the owner changed in them. Hence we cannot just peek at a buffer in the tree and check that it has the correct owner and assume that the change was completed. So, for the moment just brute force the owner change every time we see an inode with the flag set. Note that we have to be careful here because the owner of the buffers may point to either the old owner or the new owner. Currently the verifier can't verify the owner directly, so there is no failure case here right now. If we verify the owner exactly in future, then we'll have to take this into account. This was tested in terms of normal operation via xfstests - all of the fsr tests now pass without failure. however, we really need to modify xfs/227 to stress v3 inodes correctly to ensure we fully cover this case for v5 filesystems. In terms of recovery testing, I used a hacked version of xfs_fsr that held the temp inode open for a few seconds before exiting so that the filesystem could be shut down with an open owner change recovery flags set on at least the temp inode. fsr leaves the temp inode unlinked and in btree format, so this was necessary for the owner change to be reliably replayed. logprint confirmed the tmp inode in the log had the correct flag set: INO: cnt:3 total:3 a:0x69e9e0 len:56 a:0x69ea20 len:176 a:0x69eae0 len:88 INODE: #regs:3 ino:0x44 flags:0x209 dsize:88 ^^^^^ 0x200 is set, indicating a data fork owner change needed to be replayed on inode 0x44. A printk in the revoery code confirmed that the inode change was recovered: XFS (vdc): Mounting Filesystem XFS (vdc): Starting recovery (logdev: internal) recovering owner change ino 0x44 XFS (vdc): Version 5 superblock detected. This kernel L support enabled! Use of these features in this kernel is at your own risk! XFS (vdc): Ending recovery (logdev: internal) The script used to test this was: $ cat ./recovery-fsr.sh #!/bin/bash dev=/dev/vdc mntpt=/mnt/scratch testfile=$mntpt/testfile umount $mntpt mkfs.xfs -f -m crc=1 $dev mount $dev $mntpt chmod 777 $mntpt for i in `seq 10000 -1 0`; do xfs_io -f -d -c "pwrite $(($i * 4096)) 4096" $testfile > /dev/null 2>&1 done xfs_bmap -vp $testfile |head -20 xfs_fsr -d -v $testfile & sleep 10 /home/dave/src/xfstests-dev/src/godown -f $mntpt wait umount $mntpt xfs_logprint -t $dev |tail -20 time mount $dev $mntpt xfs_bmap -vp $testfile umount $mntpt $ Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:45 +07:00
* For demand paged transactional modification, the fork switch should be done
* after reading in all the blocks, modifying them and pinning them in the
* transaction. For modification when the buffers are already pinned in memory,
* the fork switch can be done before changing the owner as we won't need to
* validate the owner until the btree buffers are unpinned and writes can occur
* again.
*
* For recovery based ownership change, there is no transactional context and
* so a buffer list must be supplied so that we can record the buffers that we
* modified for the caller to issue IO on.
xfs: swap extents operations for CRC filesystems For CRC enabled filesystems, we can't just swap inode forks from one inode to another when defragmenting a file - the blocks in the inode fork bmap btree contain pointers back to the owner inode. Hence if we are to swap the inode forks we have to atomically modify every block in the btree during the transaction. We are doing an entire fork swap here, so we could create a new transaction item type that indicates we are changing the owner of a certain structure from one value to another. If we combine this with ordered buffer logging to modify all the buffers in the tree, then we can change the buffers in the tree without needing log space for the operation. However, this then requires log recovery to perform the modification of the owner information of the objects/structures in question. This does introduce some interesting ordering details into recovery: we have to make sure that the owner change replay occurs after the change that moves the objects is made, not before. Hence we can't use a separate log item for this as we have no guarantee of strict ordering between multiple items in the log due to the relogging action of asynchronous transaction commits. Hence there is no "generic" method we can use for changing the ownership of arbitrary metadata structures. For inode forks, however, there is a simple method of communicating that the fork contents need the owner rewritten - we can pass a inode log format flag for the fork for the transaction that does a fork swap. This flag will then follow the inode fork through relogging actions so when the swap actually gets replayed the ownership can be changed immediately by log recovery. So that gives us a simple method of "whole fork" exchange between two inodes. This is relatively simple to implement, so it makes sense to do this as an initial implementation to support xfs_fsr on CRC enabled filesytems in the same manner as we do on existing filesystems. This commit introduces the swapext driven functionality, the recovery functionality will be in a separate patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:44 +07:00
*/
int
xfs_bmbt_change_owner(
struct xfs_trans *tp,
struct xfs_inode *ip,
int whichfork,
xfs: recovery of swap extents operations for CRC filesystems This is the recovery side of the btree block owner change operation performed by swapext on CRC enabled filesystems. We detect that an owner change is needed by the flag that has been placed on the inode log format flag field. Because the inode recovery is being replayed after the buffers that make up the BMBT in the given checkpoint, we can walk all the buffers and directly modify them when we see the flag set on an inode. Because the inode can be relogged and hence present in multiple chekpoints with the "change owner" flag set, we could do multiple passes across the inode to do this change. While this isn't optimal, we can't directly ignore the flag as there may be multiple independent swap extent operations being replayed on the same inode in different checkpoints so we can't ignore them. Further, because the owner change operation uses ordered buffers, we might have buffers that are newer on disk than the current checkpoint and so already have the owner changed in them. Hence we cannot just peek at a buffer in the tree and check that it has the correct owner and assume that the change was completed. So, for the moment just brute force the owner change every time we see an inode with the flag set. Note that we have to be careful here because the owner of the buffers may point to either the old owner or the new owner. Currently the verifier can't verify the owner directly, so there is no failure case here right now. If we verify the owner exactly in future, then we'll have to take this into account. This was tested in terms of normal operation via xfstests - all of the fsr tests now pass without failure. however, we really need to modify xfs/227 to stress v3 inodes correctly to ensure we fully cover this case for v5 filesystems. In terms of recovery testing, I used a hacked version of xfs_fsr that held the temp inode open for a few seconds before exiting so that the filesystem could be shut down with an open owner change recovery flags set on at least the temp inode. fsr leaves the temp inode unlinked and in btree format, so this was necessary for the owner change to be reliably replayed. logprint confirmed the tmp inode in the log had the correct flag set: INO: cnt:3 total:3 a:0x69e9e0 len:56 a:0x69ea20 len:176 a:0x69eae0 len:88 INODE: #regs:3 ino:0x44 flags:0x209 dsize:88 ^^^^^ 0x200 is set, indicating a data fork owner change needed to be replayed on inode 0x44. A printk in the revoery code confirmed that the inode change was recovered: XFS (vdc): Mounting Filesystem XFS (vdc): Starting recovery (logdev: internal) recovering owner change ino 0x44 XFS (vdc): Version 5 superblock detected. This kernel L support enabled! Use of these features in this kernel is at your own risk! XFS (vdc): Ending recovery (logdev: internal) The script used to test this was: $ cat ./recovery-fsr.sh #!/bin/bash dev=/dev/vdc mntpt=/mnt/scratch testfile=$mntpt/testfile umount $mntpt mkfs.xfs -f -m crc=1 $dev mount $dev $mntpt chmod 777 $mntpt for i in `seq 10000 -1 0`; do xfs_io -f -d -c "pwrite $(($i * 4096)) 4096" $testfile > /dev/null 2>&1 done xfs_bmap -vp $testfile |head -20 xfs_fsr -d -v $testfile & sleep 10 /home/dave/src/xfstests-dev/src/godown -f $mntpt wait umount $mntpt xfs_logprint -t $dev |tail -20 time mount $dev $mntpt xfs_bmap -vp $testfile umount $mntpt $ Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:45 +07:00
xfs_ino_t new_owner,
struct list_head *buffer_list)
xfs: swap extents operations for CRC filesystems For CRC enabled filesystems, we can't just swap inode forks from one inode to another when defragmenting a file - the blocks in the inode fork bmap btree contain pointers back to the owner inode. Hence if we are to swap the inode forks we have to atomically modify every block in the btree during the transaction. We are doing an entire fork swap here, so we could create a new transaction item type that indicates we are changing the owner of a certain structure from one value to another. If we combine this with ordered buffer logging to modify all the buffers in the tree, then we can change the buffers in the tree without needing log space for the operation. However, this then requires log recovery to perform the modification of the owner information of the objects/structures in question. This does introduce some interesting ordering details into recovery: we have to make sure that the owner change replay occurs after the change that moves the objects is made, not before. Hence we can't use a separate log item for this as we have no guarantee of strict ordering between multiple items in the log due to the relogging action of asynchronous transaction commits. Hence there is no "generic" method we can use for changing the ownership of arbitrary metadata structures. For inode forks, however, there is a simple method of communicating that the fork contents need the owner rewritten - we can pass a inode log format flag for the fork for the transaction that does a fork swap. This flag will then follow the inode fork through relogging actions so when the swap actually gets replayed the ownership can be changed immediately by log recovery. So that gives us a simple method of "whole fork" exchange between two inodes. This is relatively simple to implement, so it makes sense to do this as an initial implementation to support xfs_fsr on CRC enabled filesytems in the same manner as we do on existing filesystems. This commit introduces the swapext driven functionality, the recovery functionality will be in a separate patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:44 +07:00
{
struct xfs_btree_cur *cur;
int error;
xfs: recovery of swap extents operations for CRC filesystems This is the recovery side of the btree block owner change operation performed by swapext on CRC enabled filesystems. We detect that an owner change is needed by the flag that has been placed on the inode log format flag field. Because the inode recovery is being replayed after the buffers that make up the BMBT in the given checkpoint, we can walk all the buffers and directly modify them when we see the flag set on an inode. Because the inode can be relogged and hence present in multiple chekpoints with the "change owner" flag set, we could do multiple passes across the inode to do this change. While this isn't optimal, we can't directly ignore the flag as there may be multiple independent swap extent operations being replayed on the same inode in different checkpoints so we can't ignore them. Further, because the owner change operation uses ordered buffers, we might have buffers that are newer on disk than the current checkpoint and so already have the owner changed in them. Hence we cannot just peek at a buffer in the tree and check that it has the correct owner and assume that the change was completed. So, for the moment just brute force the owner change every time we see an inode with the flag set. Note that we have to be careful here because the owner of the buffers may point to either the old owner or the new owner. Currently the verifier can't verify the owner directly, so there is no failure case here right now. If we verify the owner exactly in future, then we'll have to take this into account. This was tested in terms of normal operation via xfstests - all of the fsr tests now pass without failure. however, we really need to modify xfs/227 to stress v3 inodes correctly to ensure we fully cover this case for v5 filesystems. In terms of recovery testing, I used a hacked version of xfs_fsr that held the temp inode open for a few seconds before exiting so that the filesystem could be shut down with an open owner change recovery flags set on at least the temp inode. fsr leaves the temp inode unlinked and in btree format, so this was necessary for the owner change to be reliably replayed. logprint confirmed the tmp inode in the log had the correct flag set: INO: cnt:3 total:3 a:0x69e9e0 len:56 a:0x69ea20 len:176 a:0x69eae0 len:88 INODE: #regs:3 ino:0x44 flags:0x209 dsize:88 ^^^^^ 0x200 is set, indicating a data fork owner change needed to be replayed on inode 0x44. A printk in the revoery code confirmed that the inode change was recovered: XFS (vdc): Mounting Filesystem XFS (vdc): Starting recovery (logdev: internal) recovering owner change ino 0x44 XFS (vdc): Version 5 superblock detected. This kernel L support enabled! Use of these features in this kernel is at your own risk! XFS (vdc): Ending recovery (logdev: internal) The script used to test this was: $ cat ./recovery-fsr.sh #!/bin/bash dev=/dev/vdc mntpt=/mnt/scratch testfile=$mntpt/testfile umount $mntpt mkfs.xfs -f -m crc=1 $dev mount $dev $mntpt chmod 777 $mntpt for i in `seq 10000 -1 0`; do xfs_io -f -d -c "pwrite $(($i * 4096)) 4096" $testfile > /dev/null 2>&1 done xfs_bmap -vp $testfile |head -20 xfs_fsr -d -v $testfile & sleep 10 /home/dave/src/xfstests-dev/src/godown -f $mntpt wait umount $mntpt xfs_logprint -t $dev |tail -20 time mount $dev $mntpt xfs_bmap -vp $testfile umount $mntpt $ Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:45 +07:00
ASSERT(tp || buffer_list);
ASSERT(!(tp && buffer_list));
xfs: swap extents operations for CRC filesystems For CRC enabled filesystems, we can't just swap inode forks from one inode to another when defragmenting a file - the blocks in the inode fork bmap btree contain pointers back to the owner inode. Hence if we are to swap the inode forks we have to atomically modify every block in the btree during the transaction. We are doing an entire fork swap here, so we could create a new transaction item type that indicates we are changing the owner of a certain structure from one value to another. If we combine this with ordered buffer logging to modify all the buffers in the tree, then we can change the buffers in the tree without needing log space for the operation. However, this then requires log recovery to perform the modification of the owner information of the objects/structures in question. This does introduce some interesting ordering details into recovery: we have to make sure that the owner change replay occurs after the change that moves the objects is made, not before. Hence we can't use a separate log item for this as we have no guarantee of strict ordering between multiple items in the log due to the relogging action of asynchronous transaction commits. Hence there is no "generic" method we can use for changing the ownership of arbitrary metadata structures. For inode forks, however, there is a simple method of communicating that the fork contents need the owner rewritten - we can pass a inode log format flag for the fork for the transaction that does a fork swap. This flag will then follow the inode fork through relogging actions so when the swap actually gets replayed the ownership can be changed immediately by log recovery. So that gives us a simple method of "whole fork" exchange between two inodes. This is relatively simple to implement, so it makes sense to do this as an initial implementation to support xfs_fsr on CRC enabled filesytems in the same manner as we do on existing filesystems. This commit introduces the swapext driven functionality, the recovery functionality will be in a separate patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:44 +07:00
if (whichfork == XFS_DATA_FORK)
ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_BTREE);
xfs: swap extents operations for CRC filesystems For CRC enabled filesystems, we can't just swap inode forks from one inode to another when defragmenting a file - the blocks in the inode fork bmap btree contain pointers back to the owner inode. Hence if we are to swap the inode forks we have to atomically modify every block in the btree during the transaction. We are doing an entire fork swap here, so we could create a new transaction item type that indicates we are changing the owner of a certain structure from one value to another. If we combine this with ordered buffer logging to modify all the buffers in the tree, then we can change the buffers in the tree without needing log space for the operation. However, this then requires log recovery to perform the modification of the owner information of the objects/structures in question. This does introduce some interesting ordering details into recovery: we have to make sure that the owner change replay occurs after the change that moves the objects is made, not before. Hence we can't use a separate log item for this as we have no guarantee of strict ordering between multiple items in the log due to the relogging action of asynchronous transaction commits. Hence there is no "generic" method we can use for changing the ownership of arbitrary metadata structures. For inode forks, however, there is a simple method of communicating that the fork contents need the owner rewritten - we can pass a inode log format flag for the fork for the transaction that does a fork swap. This flag will then follow the inode fork through relogging actions so when the swap actually gets replayed the ownership can be changed immediately by log recovery. So that gives us a simple method of "whole fork" exchange between two inodes. This is relatively simple to implement, so it makes sense to do this as an initial implementation to support xfs_fsr on CRC enabled filesytems in the same manner as we do on existing filesystems. This commit introduces the swapext driven functionality, the recovery functionality will be in a separate patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:44 +07:00
else
ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_BTREE);
xfs: swap extents operations for CRC filesystems For CRC enabled filesystems, we can't just swap inode forks from one inode to another when defragmenting a file - the blocks in the inode fork bmap btree contain pointers back to the owner inode. Hence if we are to swap the inode forks we have to atomically modify every block in the btree during the transaction. We are doing an entire fork swap here, so we could create a new transaction item type that indicates we are changing the owner of a certain structure from one value to another. If we combine this with ordered buffer logging to modify all the buffers in the tree, then we can change the buffers in the tree without needing log space for the operation. However, this then requires log recovery to perform the modification of the owner information of the objects/structures in question. This does introduce some interesting ordering details into recovery: we have to make sure that the owner change replay occurs after the change that moves the objects is made, not before. Hence we can't use a separate log item for this as we have no guarantee of strict ordering between multiple items in the log due to the relogging action of asynchronous transaction commits. Hence there is no "generic" method we can use for changing the ownership of arbitrary metadata structures. For inode forks, however, there is a simple method of communicating that the fork contents need the owner rewritten - we can pass a inode log format flag for the fork for the transaction that does a fork swap. This flag will then follow the inode fork through relogging actions so when the swap actually gets replayed the ownership can be changed immediately by log recovery. So that gives us a simple method of "whole fork" exchange between two inodes. This is relatively simple to implement, so it makes sense to do this as an initial implementation to support xfs_fsr on CRC enabled filesytems in the same manner as we do on existing filesystems. This commit introduces the swapext driven functionality, the recovery functionality will be in a separate patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:44 +07:00
cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork);
xfs: recovery of swap extents operations for CRC filesystems This is the recovery side of the btree block owner change operation performed by swapext on CRC enabled filesystems. We detect that an owner change is needed by the flag that has been placed on the inode log format flag field. Because the inode recovery is being replayed after the buffers that make up the BMBT in the given checkpoint, we can walk all the buffers and directly modify them when we see the flag set on an inode. Because the inode can be relogged and hence present in multiple chekpoints with the "change owner" flag set, we could do multiple passes across the inode to do this change. While this isn't optimal, we can't directly ignore the flag as there may be multiple independent swap extent operations being replayed on the same inode in different checkpoints so we can't ignore them. Further, because the owner change operation uses ordered buffers, we might have buffers that are newer on disk than the current checkpoint and so already have the owner changed in them. Hence we cannot just peek at a buffer in the tree and check that it has the correct owner and assume that the change was completed. So, for the moment just brute force the owner change every time we see an inode with the flag set. Note that we have to be careful here because the owner of the buffers may point to either the old owner or the new owner. Currently the verifier can't verify the owner directly, so there is no failure case here right now. If we verify the owner exactly in future, then we'll have to take this into account. This was tested in terms of normal operation via xfstests - all of the fsr tests now pass without failure. however, we really need to modify xfs/227 to stress v3 inodes correctly to ensure we fully cover this case for v5 filesystems. In terms of recovery testing, I used a hacked version of xfs_fsr that held the temp inode open for a few seconds before exiting so that the filesystem could be shut down with an open owner change recovery flags set on at least the temp inode. fsr leaves the temp inode unlinked and in btree format, so this was necessary for the owner change to be reliably replayed. logprint confirmed the tmp inode in the log had the correct flag set: INO: cnt:3 total:3 a:0x69e9e0 len:56 a:0x69ea20 len:176 a:0x69eae0 len:88 INODE: #regs:3 ino:0x44 flags:0x209 dsize:88 ^^^^^ 0x200 is set, indicating a data fork owner change needed to be replayed on inode 0x44. A printk in the revoery code confirmed that the inode change was recovered: XFS (vdc): Mounting Filesystem XFS (vdc): Starting recovery (logdev: internal) recovering owner change ino 0x44 XFS (vdc): Version 5 superblock detected. This kernel L support enabled! Use of these features in this kernel is at your own risk! XFS (vdc): Ending recovery (logdev: internal) The script used to test this was: $ cat ./recovery-fsr.sh #!/bin/bash dev=/dev/vdc mntpt=/mnt/scratch testfile=$mntpt/testfile umount $mntpt mkfs.xfs -f -m crc=1 $dev mount $dev $mntpt chmod 777 $mntpt for i in `seq 10000 -1 0`; do xfs_io -f -d -c "pwrite $(($i * 4096)) 4096" $testfile > /dev/null 2>&1 done xfs_bmap -vp $testfile |head -20 xfs_fsr -d -v $testfile & sleep 10 /home/dave/src/xfstests-dev/src/godown -f $mntpt wait umount $mntpt xfs_logprint -t $dev |tail -20 time mount $dev $mntpt xfs_bmap -vp $testfile umount $mntpt $ Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:45 +07:00
if (!cur)
return ENOMEM;
error = xfs_btree_change_owner(cur, new_owner, buffer_list);
xfs: swap extents operations for CRC filesystems For CRC enabled filesystems, we can't just swap inode forks from one inode to another when defragmenting a file - the blocks in the inode fork bmap btree contain pointers back to the owner inode. Hence if we are to swap the inode forks we have to atomically modify every block in the btree during the transaction. We are doing an entire fork swap here, so we could create a new transaction item type that indicates we are changing the owner of a certain structure from one value to another. If we combine this with ordered buffer logging to modify all the buffers in the tree, then we can change the buffers in the tree without needing log space for the operation. However, this then requires log recovery to perform the modification of the owner information of the objects/structures in question. This does introduce some interesting ordering details into recovery: we have to make sure that the owner change replay occurs after the change that moves the objects is made, not before. Hence we can't use a separate log item for this as we have no guarantee of strict ordering between multiple items in the log due to the relogging action of asynchronous transaction commits. Hence there is no "generic" method we can use for changing the ownership of arbitrary metadata structures. For inode forks, however, there is a simple method of communicating that the fork contents need the owner rewritten - we can pass a inode log format flag for the fork for the transaction that does a fork swap. This flag will then follow the inode fork through relogging actions so when the swap actually gets replayed the ownership can be changed immediately by log recovery. So that gives us a simple method of "whole fork" exchange between two inodes. This is relatively simple to implement, so it makes sense to do this as an initial implementation to support xfs_fsr on CRC enabled filesytems in the same manner as we do on existing filesystems. This commit introduces the swapext driven functionality, the recovery functionality will be in a separate patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 07:23:44 +07:00
xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
return error;
}