2005-04-16 16:20:36 -06:00
|
|
|
/*
|
2005-11-01 20:58:39 -07:00
|
|
|
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
|
|
|
|
* All Rights Reserved.
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
2005-11-01 20:58:39 -07:00
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License as
|
2005-04-16 16:20:36 -06:00
|
|
|
* published by the Free Software Foundation.
|
|
|
|
*
|
2005-11-01 20:58:39 -07:00
|
|
|
* 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.
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
2005-11-01 20:58:39 -07:00
|
|
|
* 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
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
|
|
|
#include "xfs.h"
|
2005-11-01 20:38:42 -07:00
|
|
|
#include "xfs_fs.h"
|
2005-04-16 16:20:36 -06:00
|
|
|
#include "xfs_types.h"
|
2005-11-01 20:38:42 -07:00
|
|
|
#include "xfs_bit.h"
|
2005-04-16 16:20:36 -06:00
|
|
|
#include "xfs_inum.h"
|
|
|
|
#include "xfs_log.h"
|
|
|
|
#include "xfs_trans.h"
|
|
|
|
#include "xfs_sb.h"
|
2005-11-01 20:38:42 -07:00
|
|
|
#include "xfs_ag.h"
|
|
|
|
#include "xfs_dir2.h"
|
2005-04-16 16:20:36 -06:00
|
|
|
#include "xfs_dmapi.h"
|
|
|
|
#include "xfs_mount.h"
|
|
|
|
#include "xfs_bmap_btree.h"
|
2005-11-01 20:38:42 -07:00
|
|
|
#include "xfs_alloc_btree.h"
|
2005-04-16 16:20:36 -06:00
|
|
|
#include "xfs_ialloc_btree.h"
|
2005-11-01 20:38:42 -07:00
|
|
|
#include "xfs_dir2_sf.h"
|
|
|
|
#include "xfs_attr_sf.h"
|
|
|
|
#include "xfs_dinode.h"
|
|
|
|
#include "xfs_inode.h"
|
|
|
|
#include "xfs_inode_item.h"
|
2005-04-16 16:20:36 -06:00
|
|
|
#include "xfs_btree.h"
|
|
|
|
#include "xfs_error.h"
|
|
|
|
#include "xfs_alloc.h"
|
|
|
|
#include "xfs_ialloc.h"
|
|
|
|
#include "xfs_fsops.h"
|
|
|
|
#include "xfs_itable.h"
|
|
|
|
#include "xfs_trans_space.h"
|
|
|
|
#include "xfs_rtalloc.h"
|
2005-11-01 20:38:42 -07:00
|
|
|
#include "xfs_rw.h"
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* File system operations
|
|
|
|
*/
|
|
|
|
|
|
|
|
int
|
|
|
|
xfs_fs_geometry(
|
|
|
|
xfs_mount_t *mp,
|
|
|
|
xfs_fsop_geom_t *geo,
|
|
|
|
int new_version)
|
|
|
|
{
|
|
|
|
geo->blocksize = mp->m_sb.sb_blocksize;
|
|
|
|
geo->rtextsize = mp->m_sb.sb_rextsize;
|
|
|
|
geo->agblocks = mp->m_sb.sb_agblocks;
|
|
|
|
geo->agcount = mp->m_sb.sb_agcount;
|
|
|
|
geo->logblocks = mp->m_sb.sb_logblocks;
|
|
|
|
geo->sectsize = mp->m_sb.sb_sectsize;
|
|
|
|
geo->inodesize = mp->m_sb.sb_inodesize;
|
|
|
|
geo->imaxpct = mp->m_sb.sb_imax_pct;
|
|
|
|
geo->datablocks = mp->m_sb.sb_dblocks;
|
|
|
|
geo->rtblocks = mp->m_sb.sb_rblocks;
|
|
|
|
geo->rtextents = mp->m_sb.sb_rextents;
|
|
|
|
geo->logstart = mp->m_sb.sb_logstart;
|
|
|
|
ASSERT(sizeof(geo->uuid)==sizeof(mp->m_sb.sb_uuid));
|
|
|
|
memcpy(geo->uuid, &mp->m_sb.sb_uuid, sizeof(mp->m_sb.sb_uuid));
|
|
|
|
if (new_version >= 2) {
|
|
|
|
geo->sunit = mp->m_sb.sb_unit;
|
|
|
|
geo->swidth = mp->m_sb.sb_width;
|
|
|
|
}
|
|
|
|
if (new_version >= 3) {
|
|
|
|
geo->version = XFS_FSOP_GEOM_VERSION;
|
|
|
|
geo->flags =
|
|
|
|
(XFS_SB_VERSION_HASATTR(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_ATTR : 0) |
|
|
|
|
(XFS_SB_VERSION_HASNLINK(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_NLINK : 0) |
|
|
|
|
(XFS_SB_VERSION_HASQUOTA(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_QUOTA : 0) |
|
|
|
|
(XFS_SB_VERSION_HASALIGN(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_IALIGN : 0) |
|
|
|
|
(XFS_SB_VERSION_HASDALIGN(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_DALIGN : 0) |
|
|
|
|
(XFS_SB_VERSION_HASSHARED(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_SHARED : 0) |
|
|
|
|
(XFS_SB_VERSION_HASEXTFLGBIT(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_EXTFLG : 0) |
|
|
|
|
(XFS_SB_VERSION_HASDIRV2(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_DIRV2 : 0) |
|
|
|
|
(XFS_SB_VERSION_HASSECTOR(&mp->m_sb) ?
|
2005-11-01 16:34:53 -07:00
|
|
|
XFS_FSOP_GEOM_FLAGS_SECTOR : 0) |
|
[XFS] Lazy Superblock Counters
When we have a couple of hundred transactions on the fly at once, they all
typically modify the on disk superblock in some way.
create/unclink/mkdir/rmdir modify inode counts, allocation/freeing modify
free block counts.
When these counts are modified in a transaction, they must eventually lock
the superblock buffer and apply the mods. The buffer then remains locked
until the transaction is committed into the incore log buffer. The result
of this is that with enough transactions on the fly the incore superblock
buffer becomes a bottleneck.
The result of contention on the incore superblock buffer is that
transaction rates fall - the more pressure that is put on the superblock
buffer, the slower things go.
The key to removing the contention is to not require the superblock fields
in question to be locked. We do that by not marking the superblock dirty
in the transaction. IOWs, we modify the incore superblock but do not
modify the cached superblock buffer. In short, we do not log superblock
modifications to critical fields in the superblock on every transaction.
In fact we only do it just before we write the superblock to disk every
sync period or just before unmount.
This creates an interesting problem - if we don't log or write out the
fields in every transaction, then how do the values get recovered after a
crash? the answer is simple - we keep enough duplicate, logged information
in other structures that we can reconstruct the correct count after log
recovery has been performed.
It is the AGF and AGI structures that contain the duplicate information;
after recovery, we walk every AGI and AGF and sum their individual
counters to get the correct value, and we do a transaction into the log to
correct them. An optimisation of this is that if we have a clean unmount
record, we know the value in the superblock is correct, so we can avoid
the summation walk under normal conditions and so mount/recovery times do
not change under normal operation.
One wrinkle that was discovered during development was that the blocks
used in the freespace btrees are never accounted for in the AGF counters.
This was once a valid optimisation to make; when the filesystem is full,
the free space btrees are empty and consume no space. Hence when it
matters, the "accounting" is correct. But that means the when we do the
AGF summations, we would not have a correct count and xfs_check would
complain. Hence a new counter was added to track the number of blocks used
by the free space btrees. This is an *on-disk format change*.
As a result of this, lazy superblock counters are a mkfs option and at the
moment on linux there is no way to convert an old filesystem. This is
possible - xfs_db can be used to twiddle the right bits and then
xfs_repair will do the format conversion for you. Similarly, you can
convert backwards as well. At some point we'll add functionality to
xfs_admin to do the bit twiddling easily....
SGI-PV: 964999
SGI-Modid: xfs-linux-melb:xfs-kern:28652a
Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Tim Shimmin <tes@sgi.com>
2007-05-23 23:26:31 -06:00
|
|
|
(xfs_sb_version_haslazysbcount(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_LAZYSB : 0) |
|
2005-11-01 16:34:53 -07:00
|
|
|
(XFS_SB_VERSION_HASATTR2(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_ATTR2 : 0);
|
2005-04-16 16:20:36 -06:00
|
|
|
geo->logsectsize = XFS_SB_VERSION_HASSECTOR(&mp->m_sb) ?
|
|
|
|
mp->m_sb.sb_logsectsize : BBSIZE;
|
|
|
|
geo->rtsectsize = mp->m_sb.sb_blocksize;
|
|
|
|
geo->dirblocksize = mp->m_dirblksize;
|
|
|
|
}
|
|
|
|
if (new_version >= 4) {
|
|
|
|
geo->flags |=
|
|
|
|
(XFS_SB_VERSION_HASLOGV2(&mp->m_sb) ?
|
|
|
|
XFS_FSOP_GEOM_FLAGS_LOGV2 : 0);
|
|
|
|
geo->logsunit = mp->m_sb.sb_logsunit;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
xfs_growfs_data_private(
|
|
|
|
xfs_mount_t *mp, /* mount point for filesystem */
|
|
|
|
xfs_growfs_data_t *in) /* growfs data input struct */
|
|
|
|
{
|
|
|
|
xfs_agf_t *agf;
|
|
|
|
xfs_agi_t *agi;
|
|
|
|
xfs_agnumber_t agno;
|
|
|
|
xfs_extlen_t agsize;
|
|
|
|
xfs_extlen_t tmpsize;
|
|
|
|
xfs_alloc_rec_t *arec;
|
|
|
|
xfs_btree_sblock_t *block;
|
|
|
|
xfs_buf_t *bp;
|
|
|
|
int bucket;
|
|
|
|
int dpct;
|
|
|
|
int error;
|
|
|
|
xfs_agnumber_t nagcount;
|
|
|
|
xfs_agnumber_t nagimax = 0;
|
|
|
|
xfs_rfsblock_t nb, nb_mod;
|
|
|
|
xfs_rfsblock_t new;
|
|
|
|
xfs_rfsblock_t nfree;
|
|
|
|
xfs_agnumber_t oagcount;
|
|
|
|
int pct;
|
|
|
|
xfs_sb_t *sbp;
|
|
|
|
xfs_trans_t *tp;
|
|
|
|
|
|
|
|
nb = in->newblocks;
|
|
|
|
pct = in->imaxpct;
|
|
|
|
if (nb < mp->m_sb.sb_dblocks || pct < 0 || pct > 100)
|
|
|
|
return XFS_ERROR(EINVAL);
|
2007-05-14 02:24:02 -06:00
|
|
|
if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
|
|
|
|
return error;
|
2005-04-16 16:20:36 -06:00
|
|
|
dpct = pct - mp->m_sb.sb_imax_pct;
|
|
|
|
error = xfs_read_buf(mp, mp->m_ddev_targp,
|
|
|
|
XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
|
|
|
|
XFS_FSS_TO_BB(mp, 1), 0, &bp);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
ASSERT(bp);
|
|
|
|
xfs_buf_relse(bp);
|
|
|
|
|
|
|
|
new = nb; /* use new as a temporary here */
|
|
|
|
nb_mod = do_div(new, mp->m_sb.sb_agblocks);
|
|
|
|
nagcount = new + (nb_mod != 0);
|
|
|
|
if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) {
|
|
|
|
nagcount--;
|
|
|
|
nb = nagcount * mp->m_sb.sb_agblocks;
|
|
|
|
if (nb < mp->m_sb.sb_dblocks)
|
|
|
|
return XFS_ERROR(EINVAL);
|
|
|
|
}
|
|
|
|
new = nb - mp->m_sb.sb_dblocks;
|
|
|
|
oagcount = mp->m_sb.sb_agcount;
|
|
|
|
if (nagcount > oagcount) {
|
|
|
|
down_write(&mp->m_peraglock);
|
|
|
|
mp->m_perag = kmem_realloc(mp->m_perag,
|
|
|
|
sizeof(xfs_perag_t) * nagcount,
|
|
|
|
sizeof(xfs_perag_t) * oagcount,
|
|
|
|
KM_SLEEP);
|
|
|
|
memset(&mp->m_perag[oagcount], 0,
|
|
|
|
(nagcount - oagcount) * sizeof(xfs_perag_t));
|
|
|
|
mp->m_flags |= XFS_MOUNT_32BITINODES;
|
2005-11-01 21:11:45 -07:00
|
|
|
nagimax = xfs_initialize_perag(XFS_MTOVFS(mp), mp, nagcount);
|
2005-04-16 16:20:36 -06:00
|
|
|
up_write(&mp->m_peraglock);
|
|
|
|
}
|
|
|
|
tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFS);
|
|
|
|
if ((error = xfs_trans_reserve(tp, XFS_GROWFS_SPACE_RES(mp),
|
|
|
|
XFS_GROWDATA_LOG_RES(mp), 0, 0, 0))) {
|
|
|
|
xfs_trans_cancel(tp, 0);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
nfree = 0;
|
|
|
|
for (agno = nagcount - 1; agno >= oagcount; agno--, new -= agsize) {
|
|
|
|
/*
|
|
|
|
* AG freelist header block
|
|
|
|
*/
|
|
|
|
bp = xfs_buf_get(mp->m_ddev_targp,
|
|
|
|
XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
|
|
|
|
XFS_FSS_TO_BB(mp, 1), 0);
|
|
|
|
agf = XFS_BUF_TO_AGF(bp);
|
|
|
|
memset(agf, 0, mp->m_sb.sb_sectsize);
|
2005-11-01 21:11:25 -07:00
|
|
|
agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
|
|
|
|
agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
|
|
|
|
agf->agf_seqno = cpu_to_be32(agno);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (agno == nagcount - 1)
|
|
|
|
agsize =
|
|
|
|
nb -
|
|
|
|
(agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
|
|
|
|
else
|
|
|
|
agsize = mp->m_sb.sb_agblocks;
|
2005-11-01 21:11:25 -07:00
|
|
|
agf->agf_length = cpu_to_be32(agsize);
|
|
|
|
agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp));
|
|
|
|
agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
|
|
|
|
agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
|
|
|
|
agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
|
2005-04-16 16:20:36 -06:00
|
|
|
agf->agf_flfirst = 0;
|
2005-11-01 21:11:25 -07:00
|
|
|
agf->agf_fllast = cpu_to_be32(XFS_AGFL_SIZE(mp) - 1);
|
2005-04-16 16:20:36 -06:00
|
|
|
agf->agf_flcount = 0;
|
|
|
|
tmpsize = agsize - XFS_PREALLOC_BLOCKS(mp);
|
2005-11-01 21:11:25 -07:00
|
|
|
agf->agf_freeblks = cpu_to_be32(tmpsize);
|
|
|
|
agf->agf_longest = cpu_to_be32(tmpsize);
|
2005-04-16 16:20:36 -06:00
|
|
|
error = xfs_bwrite(mp, bp);
|
|
|
|
if (error) {
|
|
|
|
goto error0;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* AG inode header block
|
|
|
|
*/
|
|
|
|
bp = xfs_buf_get(mp->m_ddev_targp,
|
|
|
|
XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
|
|
|
|
XFS_FSS_TO_BB(mp, 1), 0);
|
|
|
|
agi = XFS_BUF_TO_AGI(bp);
|
|
|
|
memset(agi, 0, mp->m_sb.sb_sectsize);
|
2005-11-01 21:11:25 -07:00
|
|
|
agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
|
|
|
|
agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
|
|
|
|
agi->agi_seqno = cpu_to_be32(agno);
|
|
|
|
agi->agi_length = cpu_to_be32(agsize);
|
2005-04-16 16:20:36 -06:00
|
|
|
agi->agi_count = 0;
|
2005-11-01 21:11:25 -07:00
|
|
|
agi->agi_root = cpu_to_be32(XFS_IBT_BLOCK(mp));
|
|
|
|
agi->agi_level = cpu_to_be32(1);
|
2005-04-16 16:20:36 -06:00
|
|
|
agi->agi_freecount = 0;
|
2005-11-01 21:11:25 -07:00
|
|
|
agi->agi_newino = cpu_to_be32(NULLAGINO);
|
|
|
|
agi->agi_dirino = cpu_to_be32(NULLAGINO);
|
2005-04-16 16:20:36 -06:00
|
|
|
for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
|
2005-11-01 21:11:25 -07:00
|
|
|
agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
|
2005-04-16 16:20:36 -06:00
|
|
|
error = xfs_bwrite(mp, bp);
|
|
|
|
if (error) {
|
|
|
|
goto error0;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* BNO btree root block
|
|
|
|
*/
|
|
|
|
bp = xfs_buf_get(mp->m_ddev_targp,
|
|
|
|
XFS_AGB_TO_DADDR(mp, agno, XFS_BNO_BLOCK(mp)),
|
|
|
|
BTOBB(mp->m_sb.sb_blocksize), 0);
|
|
|
|
block = XFS_BUF_TO_SBLOCK(bp);
|
|
|
|
memset(block, 0, mp->m_sb.sb_blocksize);
|
2005-11-01 21:11:25 -07:00
|
|
|
block->bb_magic = cpu_to_be32(XFS_ABTB_MAGIC);
|
2005-04-16 16:20:36 -06:00
|
|
|
block->bb_level = 0;
|
2005-11-01 21:11:25 -07:00
|
|
|
block->bb_numrecs = cpu_to_be16(1);
|
|
|
|
block->bb_leftsib = cpu_to_be32(NULLAGBLOCK);
|
|
|
|
block->bb_rightsib = cpu_to_be32(NULLAGBLOCK);
|
2007-02-10 00:37:33 -07:00
|
|
|
arec = XFS_BTREE_REC_ADDR(xfs_alloc, block, 1);
|
2005-11-01 21:11:25 -07:00
|
|
|
arec->ar_startblock = cpu_to_be32(XFS_PREALLOC_BLOCKS(mp));
|
|
|
|
arec->ar_blockcount = cpu_to_be32(
|
|
|
|
agsize - be32_to_cpu(arec->ar_startblock));
|
2005-04-16 16:20:36 -06:00
|
|
|
error = xfs_bwrite(mp, bp);
|
|
|
|
if (error) {
|
|
|
|
goto error0;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* CNT btree root block
|
|
|
|
*/
|
|
|
|
bp = xfs_buf_get(mp->m_ddev_targp,
|
|
|
|
XFS_AGB_TO_DADDR(mp, agno, XFS_CNT_BLOCK(mp)),
|
|
|
|
BTOBB(mp->m_sb.sb_blocksize), 0);
|
|
|
|
block = XFS_BUF_TO_SBLOCK(bp);
|
|
|
|
memset(block, 0, mp->m_sb.sb_blocksize);
|
2005-11-01 21:11:25 -07:00
|
|
|
block->bb_magic = cpu_to_be32(XFS_ABTC_MAGIC);
|
2005-04-16 16:20:36 -06:00
|
|
|
block->bb_level = 0;
|
2005-11-01 21:11:25 -07:00
|
|
|
block->bb_numrecs = cpu_to_be16(1);
|
|
|
|
block->bb_leftsib = cpu_to_be32(NULLAGBLOCK);
|
|
|
|
block->bb_rightsib = cpu_to_be32(NULLAGBLOCK);
|
2007-02-10 00:37:33 -07:00
|
|
|
arec = XFS_BTREE_REC_ADDR(xfs_alloc, block, 1);
|
2005-11-01 21:11:25 -07:00
|
|
|
arec->ar_startblock = cpu_to_be32(XFS_PREALLOC_BLOCKS(mp));
|
|
|
|
arec->ar_blockcount = cpu_to_be32(
|
|
|
|
agsize - be32_to_cpu(arec->ar_startblock));
|
|
|
|
nfree += be32_to_cpu(arec->ar_blockcount);
|
2005-04-16 16:20:36 -06:00
|
|
|
error = xfs_bwrite(mp, bp);
|
|
|
|
if (error) {
|
|
|
|
goto error0;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* INO btree root block
|
|
|
|
*/
|
|
|
|
bp = xfs_buf_get(mp->m_ddev_targp,
|
|
|
|
XFS_AGB_TO_DADDR(mp, agno, XFS_IBT_BLOCK(mp)),
|
|
|
|
BTOBB(mp->m_sb.sb_blocksize), 0);
|
|
|
|
block = XFS_BUF_TO_SBLOCK(bp);
|
|
|
|
memset(block, 0, mp->m_sb.sb_blocksize);
|
2005-11-01 21:11:25 -07:00
|
|
|
block->bb_magic = cpu_to_be32(XFS_IBT_MAGIC);
|
2005-04-16 16:20:36 -06:00
|
|
|
block->bb_level = 0;
|
|
|
|
block->bb_numrecs = 0;
|
2005-11-01 21:11:25 -07:00
|
|
|
block->bb_leftsib = cpu_to_be32(NULLAGBLOCK);
|
|
|
|
block->bb_rightsib = cpu_to_be32(NULLAGBLOCK);
|
2005-04-16 16:20:36 -06:00
|
|
|
error = xfs_bwrite(mp, bp);
|
|
|
|
if (error) {
|
|
|
|
goto error0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
xfs_trans_agblocks_delta(tp, nfree);
|
|
|
|
/*
|
|
|
|
* There are new blocks in the old last a.g.
|
|
|
|
*/
|
|
|
|
if (new) {
|
|
|
|
/*
|
|
|
|
* Change the agi length.
|
|
|
|
*/
|
|
|
|
error = xfs_ialloc_read_agi(mp, tp, agno, &bp);
|
|
|
|
if (error) {
|
|
|
|
goto error0;
|
|
|
|
}
|
|
|
|
ASSERT(bp);
|
|
|
|
agi = XFS_BUF_TO_AGI(bp);
|
2005-11-01 21:11:25 -07:00
|
|
|
be32_add(&agi->agi_length, new);
|
2005-04-16 16:20:36 -06:00
|
|
|
ASSERT(nagcount == oagcount ||
|
2005-11-01 21:11:25 -07:00
|
|
|
be32_to_cpu(agi->agi_length) == mp->m_sb.sb_agblocks);
|
2005-04-16 16:20:36 -06:00
|
|
|
xfs_ialloc_log_agi(tp, bp, XFS_AGI_LENGTH);
|
|
|
|
/*
|
|
|
|
* Change agf length.
|
|
|
|
*/
|
|
|
|
error = xfs_alloc_read_agf(mp, tp, agno, 0, &bp);
|
|
|
|
if (error) {
|
|
|
|
goto error0;
|
|
|
|
}
|
|
|
|
ASSERT(bp);
|
|
|
|
agf = XFS_BUF_TO_AGF(bp);
|
2005-11-01 21:11:25 -07:00
|
|
|
be32_add(&agf->agf_length, new);
|
|
|
|
ASSERT(be32_to_cpu(agf->agf_length) ==
|
|
|
|
be32_to_cpu(agi->agi_length));
|
2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* Free the new space.
|
|
|
|
*/
|
|
|
|
error = xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, agno,
|
2005-11-01 21:11:25 -07:00
|
|
|
be32_to_cpu(agf->agf_length) - new), new);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (error) {
|
|
|
|
goto error0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (nagcount > oagcount)
|
|
|
|
xfs_trans_mod_sb(tp, XFS_TRANS_SB_AGCOUNT, nagcount - oagcount);
|
|
|
|
if (nb > mp->m_sb.sb_dblocks)
|
|
|
|
xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS,
|
|
|
|
nb - mp->m_sb.sb_dblocks);
|
|
|
|
if (nfree)
|
|
|
|
xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, nfree);
|
|
|
|
if (dpct)
|
|
|
|
xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct);
|
2007-05-07 21:48:42 -06:00
|
|
|
error = xfs_trans_commit(tp, 0);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (error) {
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
/* New allocation groups fully initialized, so update mount struct */
|
|
|
|
if (nagimax)
|
|
|
|
mp->m_maxagi = nagimax;
|
|
|
|
if (mp->m_sb.sb_imax_pct) {
|
|
|
|
__uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
|
|
|
|
do_div(icount, 100);
|
|
|
|
mp->m_maxicount = icount << mp->m_sb.sb_inopblog;
|
|
|
|
} else
|
|
|
|
mp->m_maxicount = 0;
|
|
|
|
for (agno = 1; agno < nagcount; agno++) {
|
|
|
|
error = xfs_read_buf(mp, mp->m_ddev_targp,
|
|
|
|
XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
|
|
|
|
XFS_FSS_TO_BB(mp, 1), 0, &bp);
|
|
|
|
if (error) {
|
|
|
|
xfs_fs_cmn_err(CE_WARN, mp,
|
|
|
|
"error %d reading secondary superblock for ag %d",
|
|
|
|
error, agno);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
sbp = XFS_BUF_TO_SBP(bp);
|
|
|
|
xfs_xlatesb(sbp, &mp->m_sb, -1, XFS_SB_ALL_BITS);
|
|
|
|
/*
|
|
|
|
* If we get an error writing out the alternate superblocks,
|
|
|
|
* just issue a warning and continue. The real work is
|
|
|
|
* already done and committed.
|
|
|
|
*/
|
|
|
|
if (!(error = xfs_bwrite(mp, bp))) {
|
|
|
|
continue;
|
|
|
|
} else {
|
|
|
|
xfs_fs_cmn_err(CE_WARN, mp,
|
|
|
|
"write error %d updating secondary superblock for ag %d",
|
|
|
|
error, agno);
|
|
|
|
break; /* no point in continuing */
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
error0:
|
|
|
|
xfs_trans_cancel(tp, XFS_TRANS_ABORT);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
xfs_growfs_log_private(
|
|
|
|
xfs_mount_t *mp, /* mount point for filesystem */
|
|
|
|
xfs_growfs_log_t *in) /* growfs log input struct */
|
|
|
|
{
|
|
|
|
xfs_extlen_t nb;
|
|
|
|
|
|
|
|
nb = in->newblocks;
|
|
|
|
if (nb < XFS_MIN_LOG_BLOCKS || nb < XFS_B_TO_FSB(mp, XFS_MIN_LOG_BYTES))
|
|
|
|
return XFS_ERROR(EINVAL);
|
|
|
|
if (nb == mp->m_sb.sb_logblocks &&
|
|
|
|
in->isint == (mp->m_sb.sb_logstart != 0))
|
|
|
|
return XFS_ERROR(EINVAL);
|
|
|
|
/*
|
|
|
|
* Moving the log is hard, need new interfaces to sync
|
|
|
|
* the log first, hold off all activity while moving it.
|
|
|
|
* Can have shorter or longer log in the same space,
|
|
|
|
* or transform internal to external log or vice versa.
|
|
|
|
*/
|
|
|
|
return XFS_ERROR(ENOSYS);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* protected versions of growfs function acquire and release locks on the mount
|
|
|
|
* point - exported through ioctls: XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG,
|
|
|
|
* XFS_IOC_FSGROWFSRT
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
int
|
|
|
|
xfs_growfs_data(
|
|
|
|
xfs_mount_t *mp,
|
|
|
|
xfs_growfs_data_t *in)
|
|
|
|
{
|
|
|
|
int error;
|
|
|
|
if (!cpsema(&mp->m_growlock))
|
|
|
|
return XFS_ERROR(EWOULDBLOCK);
|
|
|
|
error = xfs_growfs_data_private(mp, in);
|
|
|
|
vsema(&mp->m_growlock);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
int
|
|
|
|
xfs_growfs_log(
|
|
|
|
xfs_mount_t *mp,
|
|
|
|
xfs_growfs_log_t *in)
|
|
|
|
{
|
|
|
|
int error;
|
|
|
|
if (!cpsema(&mp->m_growlock))
|
|
|
|
return XFS_ERROR(EWOULDBLOCK);
|
|
|
|
error = xfs_growfs_log_private(mp, in);
|
|
|
|
vsema(&mp->m_growlock);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* exported through ioctl XFS_IOC_FSCOUNTS
|
|
|
|
*/
|
|
|
|
|
|
|
|
int
|
|
|
|
xfs_fs_counts(
|
|
|
|
xfs_mount_t *mp,
|
|
|
|
xfs_fsop_counts_t *cnt)
|
|
|
|
{
|
|
|
|
unsigned long s;
|
|
|
|
|
2007-02-10 00:36:17 -07:00
|
|
|
xfs_icsb_sync_counters_flags(mp, XFS_ICSB_LAZY_COUNT);
|
2005-04-16 16:20:36 -06:00
|
|
|
s = XFS_SB_LOCK(mp);
|
2006-09-06 22:26:50 -06:00
|
|
|
cnt->freedata = mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
|
2005-04-16 16:20:36 -06:00
|
|
|
cnt->freertx = mp->m_sb.sb_frextents;
|
|
|
|
cnt->freeino = mp->m_sb.sb_ifree;
|
|
|
|
cnt->allocino = mp->m_sb.sb_icount;
|
|
|
|
XFS_SB_UNLOCK(mp, s);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* exported through ioctl XFS_IOC_SET_RESBLKS & XFS_IOC_GET_RESBLKS
|
|
|
|
*
|
|
|
|
* xfs_reserve_blocks is called to set m_resblks
|
|
|
|
* in the in-core mount table. The number of unused reserved blocks
|
2006-03-28 15:55:14 -07:00
|
|
|
* is kept in m_resblks_avail.
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* Reserve the requested number of blocks if available. Otherwise return
|
|
|
|
* as many as possible to satisfy the request. The actual number
|
|
|
|
* reserved are returned in outval
|
|
|
|
*
|
|
|
|
* A null inval pointer indicates that only the current reserved blocks
|
|
|
|
* available should be returned no settings are changed.
|
|
|
|
*/
|
|
|
|
|
|
|
|
int
|
|
|
|
xfs_reserve_blocks(
|
|
|
|
xfs_mount_t *mp,
|
|
|
|
__uint64_t *inval,
|
|
|
|
xfs_fsop_resblks_t *outval)
|
|
|
|
{
|
2007-02-10 00:36:17 -07:00
|
|
|
__int64_t lcounter, delta, fdblks_delta;
|
2005-04-16 16:20:36 -06:00
|
|
|
__uint64_t request;
|
|
|
|
unsigned long s;
|
|
|
|
|
|
|
|
/* If inval is null, report current values and return */
|
|
|
|
|
|
|
|
if (inval == (__uint64_t *)NULL) {
|
|
|
|
outval->resblks = mp->m_resblks;
|
|
|
|
outval->resblks_avail = mp->m_resblks_avail;
|
2006-01-14 18:37:08 -07:00
|
|
|
return 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
request = *inval;
|
2007-02-10 00:36:17 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* With per-cpu counters, this becomes an interesting
|
|
|
|
* problem. we needto work out if we are freeing or allocation
|
|
|
|
* blocks first, then we can do the modification as necessary.
|
|
|
|
*
|
|
|
|
* We do this under the XFS_SB_LOCK so that if we are near
|
|
|
|
* ENOSPC, we will hold out any changes while we work out
|
|
|
|
* what to do. This means that the amount of free space can
|
|
|
|
* change while we do this, so we need to retry if we end up
|
|
|
|
* trying to reserve more space than is available.
|
|
|
|
*
|
|
|
|
* We also use the xfs_mod_incore_sb() interface so that we
|
|
|
|
* don't have to care about whether per cpu counter are
|
|
|
|
* enabled, disabled or even compiled in....
|
|
|
|
*/
|
|
|
|
retry:
|
2005-04-16 16:20:36 -06:00
|
|
|
s = XFS_SB_LOCK(mp);
|
2007-02-10 00:36:17 -07:00
|
|
|
xfs_icsb_sync_counters_flags(mp, XFS_ICSB_SB_LOCKED);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If our previous reservation was larger than the current value,
|
|
|
|
* then move any unused blocks back to the free pool.
|
|
|
|
*/
|
2007-02-10 00:36:17 -07:00
|
|
|
fdblks_delta = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
if (mp->m_resblks > request) {
|
|
|
|
lcounter = mp->m_resblks_avail - request;
|
|
|
|
if (lcounter > 0) { /* release unused blocks */
|
2007-02-10 00:36:17 -07:00
|
|
|
fdblks_delta = lcounter;
|
2005-04-16 16:20:36 -06:00
|
|
|
mp->m_resblks_avail -= lcounter;
|
|
|
|
}
|
|
|
|
mp->m_resblks = request;
|
|
|
|
} else {
|
2006-09-06 22:26:50 -06:00
|
|
|
__int64_t free;
|
|
|
|
|
|
|
|
free = mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
|
2007-02-10 00:36:17 -07:00
|
|
|
if (!free)
|
|
|
|
goto out; /* ENOSPC and fdblks_delta = 0 */
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
delta = request - mp->m_resblks;
|
2006-09-06 22:26:50 -06:00
|
|
|
lcounter = free - delta;
|
2005-04-16 16:20:36 -06:00
|
|
|
if (lcounter < 0) {
|
|
|
|
/* We can't satisfy the request, just get what we can */
|
2006-09-06 22:26:50 -06:00
|
|
|
mp->m_resblks += free;
|
|
|
|
mp->m_resblks_avail += free;
|
2007-02-10 00:36:17 -07:00
|
|
|
fdblks_delta = -free;
|
2006-09-06 22:26:50 -06:00
|
|
|
mp->m_sb.sb_fdblocks = XFS_ALLOC_SET_ASIDE(mp);
|
2005-04-16 16:20:36 -06:00
|
|
|
} else {
|
2007-02-10 00:36:17 -07:00
|
|
|
fdblks_delta = -delta;
|
2006-09-06 22:26:50 -06:00
|
|
|
mp->m_sb.sb_fdblocks =
|
|
|
|
lcounter + XFS_ALLOC_SET_ASIDE(mp);
|
2005-04-16 16:20:36 -06:00
|
|
|
mp->m_resblks = request;
|
|
|
|
mp->m_resblks_avail += delta;
|
|
|
|
}
|
|
|
|
}
|
2007-02-10 00:36:17 -07:00
|
|
|
out:
|
2005-04-16 16:20:36 -06:00
|
|
|
outval->resblks = mp->m_resblks;
|
|
|
|
outval->resblks_avail = mp->m_resblks_avail;
|
|
|
|
XFS_SB_UNLOCK(mp, s);
|
2007-02-10 00:36:17 -07:00
|
|
|
|
|
|
|
if (fdblks_delta) {
|
|
|
|
/*
|
|
|
|
* If we are putting blocks back here, m_resblks_avail is
|
|
|
|
* already at it's max so this will put it in the free pool.
|
|
|
|
*
|
|
|
|
* If we need space, we'll either succeed in getting it
|
|
|
|
* from the free block count or we'll get an enospc. If
|
|
|
|
* we get a ENOSPC, it means things changed while we were
|
|
|
|
* calculating fdblks_delta and so we should try again to
|
|
|
|
* see if there is anything left to reserve.
|
|
|
|
*
|
|
|
|
* Don't set the reserved flag here - we don't want to reserve
|
|
|
|
* the extra reserve blocks from the reserve.....
|
|
|
|
*/
|
|
|
|
int error;
|
|
|
|
error = xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS, fdblks_delta, 0);
|
|
|
|
if (error == ENOSPC)
|
|
|
|
goto retry;
|
|
|
|
}
|
|
|
|
|
2006-01-14 18:37:08 -07:00
|
|
|
return 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2006-01-10 21:30:08 -07:00
|
|
|
void
|
2006-06-09 01:12:46 -06:00
|
|
|
xfs_fs_log_dummy(
|
|
|
|
xfs_mount_t *mp)
|
2006-01-10 21:30:08 -07:00
|
|
|
{
|
2006-06-09 01:12:46 -06:00
|
|
|
xfs_trans_t *tp;
|
|
|
|
xfs_inode_t *ip;
|
2006-01-10 21:30:08 -07:00
|
|
|
|
|
|
|
tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
|
|
|
|
if (xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0)) {
|
|
|
|
xfs_trans_cancel(tp, 0);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
ip = mp->m_rootip;
|
|
|
|
xfs_ilock(ip, XFS_ILOCK_EXCL);
|
|
|
|
|
|
|
|
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
|
|
|
|
xfs_trans_ihold(tp, ip);
|
|
|
|
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
|
|
|
|
xfs_trans_set_sync(tp);
|
2007-05-07 21:48:42 -06:00
|
|
|
xfs_trans_commit(tp, 0);
|
2006-01-10 21:30:08 -07:00
|
|
|
|
|
|
|
xfs_iunlock(ip, XFS_ILOCK_EXCL);
|
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
int
|
|
|
|
xfs_fs_goingdown(
|
|
|
|
xfs_mount_t *mp,
|
|
|
|
__uint32_t inflags)
|
|
|
|
{
|
|
|
|
switch (inflags) {
|
|
|
|
case XFS_FSOP_GOING_FLAGS_DEFAULT: {
|
2006-06-09 00:48:30 -06:00
|
|
|
struct bhv_vfs *vfsp = XFS_MTOVFS(mp);
|
2005-04-16 16:20:36 -06:00
|
|
|
struct super_block *sb = freeze_bdev(vfsp->vfs_super->s_bdev);
|
|
|
|
|
2005-11-24 22:41:47 -07:00
|
|
|
if (sb && !IS_ERR(sb)) {
|
2006-06-08 22:58:38 -06:00
|
|
|
xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
|
2005-04-16 16:20:36 -06:00
|
|
|
thaw_bdev(sb->s_bdev, sb);
|
|
|
|
}
|
|
|
|
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
case XFS_FSOP_GOING_FLAGS_LOGFLUSH:
|
2006-06-08 22:58:38 -06:00
|
|
|
xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
case XFS_FSOP_GOING_FLAGS_NOLOGFLUSH:
|
2006-06-08 22:58:38 -06:00
|
|
|
xfs_force_shutdown(mp,
|
|
|
|
SHUTDOWN_FORCE_UMOUNT | SHUTDOWN_LOG_IO_ERROR);
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
default:
|
|
|
|
return XFS_ERROR(EINVAL);
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|