/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_dir.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
-#include "xfs_dir_sf.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
-#include "xfs_imap.h"
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_log_priv.h"
#include "xfs_trans_priv.h"
#include "xfs_quota.h"
#include "xfs_rw.h"
+#include "xfs_utils.h"
STATIC int xlog_find_zeroed(xlog_t *, xfs_daddr_t *);
STATIC int xlog_clear_stale_blocks(xlog_t *, xfs_lsn_t);
xlog_recover_item_t *item);
#if defined(DEBUG)
STATIC void xlog_recover_check_summary(xlog_t *);
-STATIC void xlog_recover_check_ail(xfs_mount_t *, xfs_log_item_t *, int);
#else
#define xlog_recover_check_summary(log)
-#define xlog_recover_check_ail(mp, lip, gen)
#endif
xfs_buf_t *
xlog_get_bp(
xlog_t *log,
- int num_bblks)
+ int nbblks)
{
- ASSERT(num_bblks > 0);
+ if (nbblks <= 0 || nbblks > log->l_logBBsize) {
+ xlog_warn("XFS: Invalid block length (0x%x) given for buffer", nbblks);
+ XFS_ERROR_REPORT("xlog_get_bp(1)",
+ XFS_ERRLEVEL_HIGH, log->l_mp);
+ return NULL;
+ }
if (log->l_sectbb_log) {
- if (num_bblks > 1)
- num_bblks += XLOG_SECTOR_ROUNDUP_BBCOUNT(log, 1);
- num_bblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, num_bblks);
+ if (nbblks > 1)
+ nbblks += XLOG_SECTOR_ROUNDUP_BBCOUNT(log, 1);
+ nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);
}
- return xfs_buf_get_noaddr(BBTOB(num_bblks), log->l_mp->m_logdev_targp);
+ return xfs_buf_get_noaddr(BBTOB(nbblks), log->l_mp->m_logdev_targp);
}
void
xfs_buf_free(bp);
}
+STATIC xfs_caddr_t
+xlog_align(
+ xlog_t *log,
+ xfs_daddr_t blk_no,
+ int nbblks,
+ xfs_buf_t *bp)
+{
+ xfs_caddr_t ptr;
+
+ if (!log->l_sectbb_log)
+ return XFS_BUF_PTR(bp);
+
+ ptr = XFS_BUF_PTR(bp) + BBTOB((int)blk_no & log->l_sectbb_mask);
+ ASSERT(XFS_BUF_SIZE(bp) >=
+ BBTOB(nbblks + (blk_no & log->l_sectbb_mask)));
+ return ptr;
+}
+
/*
* nbblks should be uint, but oh well. Just want to catch that 32-bit length.
*/
-int
-xlog_bread(
+STATIC int
+xlog_bread_noalign(
xlog_t *log,
xfs_daddr_t blk_no,
int nbblks,
{
int error;
+ if (nbblks <= 0 || nbblks > log->l_logBBsize) {
+ xlog_warn("XFS: Invalid block length (0x%x) given for buffer", nbblks);
+ XFS_ERROR_REPORT("xlog_bread(1)",
+ XFS_ERRLEVEL_HIGH, log->l_mp);
+ return EFSCORRUPTED;
+ }
+
if (log->l_sectbb_log) {
blk_no = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, blk_no);
nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);
XFS_BUF_SET_TARGET(bp, log->l_mp->m_logdev_targp);
xfsbdstrat(log->l_mp, bp);
- if ((error = xfs_iowait(bp)))
+ error = xfs_iowait(bp);
+ if (error)
xfs_ioerror_alert("xlog_bread", log->l_mp,
bp, XFS_BUF_ADDR(bp));
return error;
}
+STATIC int
+xlog_bread(
+ xlog_t *log,
+ xfs_daddr_t blk_no,
+ int nbblks,
+ xfs_buf_t *bp,
+ xfs_caddr_t *offset)
+{
+ int error;
+
+ error = xlog_bread_noalign(log, blk_no, nbblks, bp);
+ if (error)
+ return error;
+
+ *offset = xlog_align(log, blk_no, nbblks, bp);
+ return 0;
+}
+
/*
* Write out the buffer at the given block for the given number of blocks.
* The buffer is kept locked across the write and is returned locked.
{
int error;
+ if (nbblks <= 0 || nbblks > log->l_logBBsize) {
+ xlog_warn("XFS: Invalid block length (0x%x) given for buffer", nbblks);
+ XFS_ERROR_REPORT("xlog_bwrite(1)",
+ XFS_ERRLEVEL_HIGH, log->l_mp);
+ return EFSCORRUPTED;
+ }
+
if (log->l_sectbb_log) {
blk_no = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, blk_no);
nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);
return error;
}
-STATIC xfs_caddr_t
-xlog_align(
- xlog_t *log,
- xfs_daddr_t blk_no,
- int nbblks,
- xfs_buf_t *bp)
-{
- xfs_caddr_t ptr;
-
- if (!log->l_sectbb_log)
- return XFS_BUF_PTR(bp);
-
- ptr = XFS_BUF_PTR(bp) + BBTOB((int)blk_no & log->l_sectbb_mask);
- ASSERT(XFS_BUF_SIZE(bp) >=
- BBTOB(nbblks + (blk_no & log->l_sectbb_mask)));
- return ptr;
-}
-
#ifdef DEBUG
/*
* dump debug superblock and log record information
{
int b;
- printk("%s: SB : uuid = ", __FUNCTION__);
+ cmn_err(CE_DEBUG, "%s: SB : uuid = ", __func__);
for (b = 0; b < 16; b++)
- printk("%02x",((unsigned char *)&mp->m_sb.sb_uuid)[b]);
- printk(", fmt = %d\n", XLOG_FMT);
- printk(" log : uuid = ");
+ cmn_err(CE_DEBUG, "%02x", ((__uint8_t *)&mp->m_sb.sb_uuid)[b]);
+ cmn_err(CE_DEBUG, ", fmt = %d\n", XLOG_FMT);
+ cmn_err(CE_DEBUG, " log : uuid = ");
for (b = 0; b < 16; b++)
- printk("%02x",((unsigned char *)&head->h_fs_uuid)[b]);
- printk(", fmt = %d\n", INT_GET(head->h_fmt, ARCH_CONVERT));
+ cmn_err(CE_DEBUG, "%02x", ((__uint8_t *)&head->h_fs_uuid)[b]);
+ cmn_err(CE_DEBUG, ", fmt = %d\n", be32_to_cpu(head->h_fmt));
}
#else
#define xlog_header_check_dump(mp, head)
xfs_mount_t *mp,
xlog_rec_header_t *head)
{
- ASSERT(INT_GET(head->h_magicno, ARCH_CONVERT) == XLOG_HEADER_MAGIC_NUM);
+ ASSERT(be32_to_cpu(head->h_magicno) == XLOG_HEADER_MAGIC_NUM);
/*
* IRIX doesn't write the h_fmt field and leaves it zeroed
* (XLOG_FMT_UNKNOWN). This stops us from trying to recover
* a dirty log created in IRIX.
*/
- if (unlikely(INT_GET(head->h_fmt, ARCH_CONVERT) != XLOG_FMT)) {
+ if (unlikely(be32_to_cpu(head->h_fmt) != XLOG_FMT)) {
xlog_warn(
"XFS: dirty log written in incompatible format - can't recover");
xlog_header_check_dump(mp, head);
xfs_mount_t *mp,
xlog_rec_header_t *head)
{
- ASSERT(INT_GET(head->h_magicno, ARCH_CONVERT) == XLOG_HEADER_MAGIC_NUM);
+ ASSERT(be32_to_cpu(head->h_magicno) == XLOG_HEADER_MAGIC_NUM);
if (uuid_is_nil(&head->h_fs_uuid)) {
/*
xlog_recover_iodone(
struct xfs_buf *bp)
{
- xfs_mount_t *mp;
-
- ASSERT(XFS_BUF_FSPRIVATE(bp, void *));
-
if (XFS_BUF_GETERROR(bp)) {
/*
* We're not going to bother about retrying
* this during recovery. One strike!
*/
- mp = XFS_BUF_FSPRIVATE(bp, xfs_mount_t *);
xfs_ioerror_alert("xlog_recover_iodone",
- mp, bp, XFS_BUF_ADDR(bp));
- xfs_force_shutdown(mp, XFS_METADATA_IO_ERROR);
+ bp->b_mount, bp, XFS_BUF_ADDR(bp));
+ xfs_force_shutdown(bp->b_mount, SHUTDOWN_META_IO_ERROR);
}
- XFS_BUF_SET_FSPRIVATE(bp, NULL);
+ bp->b_mount = NULL;
XFS_BUF_CLR_IODONE_FUNC(bp);
xfs_biodone(bp);
}
* Note that the algorithm can not be perfect because the disk will not
* necessarily be perfect.
*/
-int
+STATIC int
xlog_find_cycle_start(
xlog_t *log,
xfs_buf_t *bp,
mid_blk = BLK_AVG(first_blk, *last_blk);
while (mid_blk != first_blk && mid_blk != *last_blk) {
- if ((error = xlog_bread(log, mid_blk, 1, bp)))
+ error = xlog_bread(log, mid_blk, 1, bp, &offset);
+ if (error)
return error;
- offset = xlog_align(log, mid_blk, 1, bp);
- mid_cycle = GET_CYCLE(offset, ARCH_CONVERT);
+ mid_cycle = xlog_get_cycle(offset);
if (mid_cycle == cycle) {
*last_blk = mid_blk;
/* last_half_cycle == mid_cycle */
bcount = min(bufblks, (start_blk + nbblks - i));
- if ((error = xlog_bread(log, i, bcount, bp)))
+ error = xlog_bread(log, i, bcount, bp, &buf);
+ if (error)
goto out;
- buf = xlog_align(log, i, bcount, bp);
for (j = 0; j < bcount; j++) {
- cycle = GET_CYCLE(buf, ARCH_CONVERT);
+ cycle = xlog_get_cycle(buf);
if (cycle == stop_on_cycle_no) {
*new_blk = i+j;
goto out;
return ENOMEM;
smallmem = 1;
} else {
- if ((error = xlog_bread(log, start_blk, num_blks, bp)))
+ error = xlog_bread(log, start_blk, num_blks, bp, &offset);
+ if (error)
goto out;
- offset = xlog_align(log, start_blk, num_blks, bp);
offset += ((num_blks - 1) << BBSHIFT);
}
}
if (smallmem) {
- if ((error = xlog_bread(log, i, 1, bp)))
+ error = xlog_bread(log, i, 1, bp, &offset);
+ if (error)
goto out;
- offset = xlog_align(log, i, 1, bp);
}
head = (xlog_rec_header_t *)offset;
- if (XLOG_HEADER_MAGIC_NUM ==
- INT_GET(head->h_magicno, ARCH_CONVERT))
+ if (XLOG_HEADER_MAGIC_NUM == be32_to_cpu(head->h_magicno))
break;
if (!smallmem)
* reset last_blk. Only when last_blk points in the middle of a log
* record do we update last_blk.
*/
- if (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb)) {
- uint h_size = INT_GET(head->h_size, ARCH_CONVERT);
+ if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
+ uint h_size = be32_to_cpu(head->h_size);
xhdrs = h_size / XLOG_HEADER_CYCLE_SIZE;
if (h_size % XLOG_HEADER_CYCLE_SIZE)
xhdrs = 1;
}
- if (*last_blk - i + extra_bblks
- != BTOBB(INT_GET(head->h_len, ARCH_CONVERT)) + xhdrs)
+ if (*last_blk - i + extra_bblks !=
+ BTOBB(be32_to_cpu(head->h_len)) + xhdrs)
*last_blk = i;
out:
bp = xlog_get_bp(log, 1);
if (!bp)
return ENOMEM;
- if ((error = xlog_bread(log, 0, 1, bp)))
+
+ error = xlog_bread(log, 0, 1, bp, &offset);
+ if (error)
goto bp_err;
- offset = xlog_align(log, 0, 1, bp);
- first_half_cycle = GET_CYCLE(offset, ARCH_CONVERT);
+
+ first_half_cycle = xlog_get_cycle(offset);
last_blk = head_blk = log_bbnum - 1; /* get cycle # of last block */
- if ((error = xlog_bread(log, last_blk, 1, bp)))
+ error = xlog_bread(log, last_blk, 1, bp, &offset);
+ if (error)
goto bp_err;
- offset = xlog_align(log, last_blk, 1, bp);
- last_half_cycle = GET_CYCLE(offset, ARCH_CONVERT);
+
+ last_half_cycle = xlog_get_cycle(offset);
ASSERT(last_half_cycle != 0);
/*
* x | x ... | x - 1 | x
* Another case that fits this picture would be
* x | x + 1 | x ... | x
- * In this case the head really is somwhere at the end of the
+ * In this case the head really is somewhere at the end of the
* log, as one of the latest writes at the beginning was
* incomplete.
* One more case is
xlog_find_tail(
xlog_t *log,
xfs_daddr_t *head_blk,
- xfs_daddr_t *tail_blk,
- int readonly)
+ xfs_daddr_t *tail_blk)
{
xlog_rec_header_t *rhead;
xlog_op_header_t *op_head;
if (!bp)
return ENOMEM;
if (*head_blk == 0) { /* special case */
- if ((error = xlog_bread(log, 0, 1, bp)))
+ error = xlog_bread(log, 0, 1, bp, &offset);
+ if (error)
goto bread_err;
- offset = xlog_align(log, 0, 1, bp);
- if (GET_CYCLE(offset, ARCH_CONVERT) == 0) {
+
+ if (xlog_get_cycle(offset) == 0) {
*tail_blk = 0;
/* leave all other log inited values alone */
goto exit;
*/
ASSERT(*head_blk < INT_MAX);
for (i = (int)(*head_blk) - 1; i >= 0; i--) {
- if ((error = xlog_bread(log, i, 1, bp)))
+ error = xlog_bread(log, i, 1, bp, &offset);
+ if (error)
goto bread_err;
- offset = xlog_align(log, i, 1, bp);
- if (XLOG_HEADER_MAGIC_NUM ==
- INT_GET(*(uint *)offset, ARCH_CONVERT)) {
+
+ if (XLOG_HEADER_MAGIC_NUM == be32_to_cpu(*(__be32 *)offset)) {
found = 1;
break;
}
*/
if (!found) {
for (i = log->l_logBBsize - 1; i >= (int)(*head_blk); i--) {
- if ((error = xlog_bread(log, i, 1, bp)))
+ error = xlog_bread(log, i, 1, bp, &offset);
+ if (error)
goto bread_err;
- offset = xlog_align(log, i, 1, bp);
+
if (XLOG_HEADER_MAGIC_NUM ==
- INT_GET(*(uint*)offset, ARCH_CONVERT)) {
+ be32_to_cpu(*(__be32 *)offset)) {
found = 2;
break;
}
/* find blk_no of tail of log */
rhead = (xlog_rec_header_t *)offset;
- *tail_blk = BLOCK_LSN(INT_GET(rhead->h_tail_lsn, ARCH_CONVERT));
+ *tail_blk = BLOCK_LSN(be64_to_cpu(rhead->h_tail_lsn));
/*
* Reset log values according to the state of the log when we
*/
log->l_prev_block = i;
log->l_curr_block = (int)*head_blk;
- log->l_curr_cycle = INT_GET(rhead->h_cycle, ARCH_CONVERT);
+ log->l_curr_cycle = be32_to_cpu(rhead->h_cycle);
if (found == 2)
log->l_curr_cycle++;
- log->l_tail_lsn = INT_GET(rhead->h_tail_lsn, ARCH_CONVERT);
- log->l_last_sync_lsn = INT_GET(rhead->h_lsn, ARCH_CONVERT);
+ log->l_tail_lsn = be64_to_cpu(rhead->h_tail_lsn);
+ log->l_last_sync_lsn = be64_to_cpu(rhead->h_lsn);
log->l_grant_reserve_cycle = log->l_curr_cycle;
log->l_grant_reserve_bytes = BBTOB(log->l_curr_block);
log->l_grant_write_cycle = log->l_curr_cycle;
* unmount record if there is one, so we pass the lsn of the
* unmount record rather than the block after it.
*/
- if (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb)) {
- int h_size = INT_GET(rhead->h_size, ARCH_CONVERT);
- int h_version = INT_GET(rhead->h_version, ARCH_CONVERT);
+ if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
+ int h_size = be32_to_cpu(rhead->h_size);
+ int h_version = be32_to_cpu(rhead->h_version);
if ((h_version & XLOG_VERSION_2) &&
(h_size > XLOG_HEADER_CYCLE_SIZE)) {
hblks = 1;
}
after_umount_blk = (i + hblks + (int)
- BTOBB(INT_GET(rhead->h_len, ARCH_CONVERT))) % log->l_logBBsize;
+ BTOBB(be32_to_cpu(rhead->h_len))) % log->l_logBBsize;
tail_lsn = log->l_tail_lsn;
if (*head_blk == after_umount_blk &&
- INT_GET(rhead->h_num_logops, ARCH_CONVERT) == 1) {
+ be32_to_cpu(rhead->h_num_logops) == 1) {
umount_data_blk = (i + hblks) % log->l_logBBsize;
- if ((error = xlog_bread(log, umount_data_blk, 1, bp))) {
+ error = xlog_bread(log, umount_data_blk, 1, bp, &offset);
+ if (error)
goto bread_err;
- }
- offset = xlog_align(log, umount_data_blk, 1, bp);
+
op_head = (xlog_op_header_t *)offset;
if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) {
/*
* log records will point recovery to after the
* current unmount record.
*/
- ASSIGN_ANY_LSN_HOST(log->l_tail_lsn, log->l_curr_cycle,
- after_umount_blk);
- ASSIGN_ANY_LSN_HOST(log->l_last_sync_lsn, log->l_curr_cycle,
- after_umount_blk);
+ log->l_tail_lsn =
+ xlog_assign_lsn(log->l_curr_cycle,
+ after_umount_blk);
+ log->l_last_sync_lsn =
+ xlog_assign_lsn(log->l_curr_cycle,
+ after_umount_blk);
*tail_blk = after_umount_blk;
+
+ /*
+ * Note that the unmount was clean. If the unmount
+ * was not clean, we need to know this to rebuild the
+ * superblock counters from the perag headers if we
+ * have a filesystem using non-persistent counters.
+ */
+ log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN;
}
}
* -1 => use *blk_no as the first block of the log
* >0 => error has occurred
*/
-int
+STATIC int
xlog_find_zeroed(
xlog_t *log,
xfs_daddr_t *blk_no)
xfs_daddr_t num_scan_bblks;
int error, log_bbnum = log->l_logBBsize;
+ *blk_no = 0;
+
/* check totally zeroed log */
bp = xlog_get_bp(log, 1);
if (!bp)
return ENOMEM;
- if ((error = xlog_bread(log, 0, 1, bp)))
+ error = xlog_bread(log, 0, 1, bp, &offset);
+ if (error)
goto bp_err;
- offset = xlog_align(log, 0, 1, bp);
- first_cycle = GET_CYCLE(offset, ARCH_CONVERT);
+
+ first_cycle = xlog_get_cycle(offset);
if (first_cycle == 0) { /* completely zeroed log */
*blk_no = 0;
xlog_put_bp(bp);
}
/* check partially zeroed log */
- if ((error = xlog_bread(log, log_bbnum-1, 1, bp)))
+ error = xlog_bread(log, log_bbnum-1, 1, bp, &offset);
+ if (error)
goto bp_err;
- offset = xlog_align(log, log_bbnum-1, 1, bp);
- last_cycle = GET_CYCLE(offset, ARCH_CONVERT);
+
+ last_cycle = xlog_get_cycle(offset);
if (last_cycle != 0) { /* log completely written to */
xlog_put_bp(bp);
return 0;
xlog_rec_header_t *recp = (xlog_rec_header_t *)buf;
memset(buf, 0, BBSIZE);
- INT_SET(recp->h_magicno, ARCH_CONVERT, XLOG_HEADER_MAGIC_NUM);
- INT_SET(recp->h_cycle, ARCH_CONVERT, cycle);
- INT_SET(recp->h_version, ARCH_CONVERT,
- XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb) ? 2 : 1);
- ASSIGN_ANY_LSN_DISK(recp->h_lsn, cycle, block);
- ASSIGN_ANY_LSN_DISK(recp->h_tail_lsn, tail_cycle, tail_block);
- INT_SET(recp->h_fmt, ARCH_CONVERT, XLOG_FMT);
+ recp->h_magicno = cpu_to_be32(XLOG_HEADER_MAGIC_NUM);
+ recp->h_cycle = cpu_to_be32(cycle);
+ recp->h_version = cpu_to_be32(
+ xfs_sb_version_haslogv2(&log->l_mp->m_sb) ? 2 : 1);
+ recp->h_lsn = cpu_to_be64(xlog_assign_lsn(cycle, block));
+ recp->h_tail_lsn = cpu_to_be64(xlog_assign_lsn(tail_cycle, tail_block));
+ recp->h_fmt = cpu_to_be32(XLOG_FMT);
memcpy(&recp->h_fs_uuid, &log->l_mp->m_sb.sb_uuid, sizeof(uuid_t));
}
*/
balign = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, start_block);
if (balign != start_block) {
- if ((error = xlog_bread(log, start_block, 1, bp))) {
- xlog_put_bp(bp);
- return error;
- }
+ error = xlog_bread_noalign(log, start_block, 1, bp);
+ if (error)
+ goto out_put_bp;
+
j = start_block - balign;
}
if (j == 0 && (start_block + endcount > ealign)) {
offset = XFS_BUF_PTR(bp);
balign = BBTOB(ealign - start_block);
- XFS_BUF_SET_PTR(bp, offset + balign, BBTOB(sectbb));
- if ((error = xlog_bread(log, ealign, sectbb, bp)))
+ error = XFS_BUF_SET_PTR(bp, offset + balign,
+ BBTOB(sectbb));
+ if (error)
+ break;
+
+ error = xlog_bread_noalign(log, ealign, sectbb, bp);
+ if (error)
+ break;
+
+ error = XFS_BUF_SET_PTR(bp, offset, bufblks);
+ if (error)
break;
- XFS_BUF_SET_PTR(bp, offset, bufblks);
}
offset = xlog_align(log, start_block, endcount, bp);
start_block += endcount;
j = 0;
}
+
+ out_put_bp:
xlog_put_bp(bp);
return error;
}
int old_len;
item = trans->r_itemq;
- if (item == 0) {
+ if (item == NULL) {
/* finish copying rest of trans header */
xlog_recover_add_item(&trans->r_itemq);
ptr = (xfs_caddr_t) &trans->r_theader +
if (!len)
return 0;
item = trans->r_itemq;
- if (item == 0) {
- ASSERT(*(uint *)dp == XFS_TRANS_HEADER_MAGIC);
+ if (item == NULL) {
+ /* we need to catch log corruptions here */
+ if (*(uint *)dp != XFS_TRANS_HEADER_MAGIC) {
+ xlog_warn("XFS: xlog_recover_add_to_trans: "
+ "bad header magic number");
+ ASSERT(0);
+ return XFS_ERROR(EIO);
+ }
if (len == sizeof(xfs_trans_header_t))
xlog_recover_add_item(&trans->r_itemq);
memcpy(&trans->r_theader, dp, len); /* d, s, l */
item = item->ri_prev;
if (item->ri_total == 0) { /* first region to be added */
- item->ri_total = in_f->ilf_size;
- ASSERT(item->ri_total <= XLOG_MAX_REGIONS_IN_ITEM);
- item->ri_buf = kmem_zalloc((item->ri_total *
- sizeof(xfs_log_iovec_t)), KM_SLEEP);
+ if (in_f->ilf_size == 0 ||
+ in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) {
+ xlog_warn(
+ "XFS: bad number of regions (%d) in inode log format",
+ in_f->ilf_size);
+ ASSERT(0);
+ return XFS_ERROR(EIO);
+ }
+
+ item->ri_total = in_f->ilf_size;
+ item->ri_buf =
+ kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t),
+ KM_SLEEP);
}
ASSERT(item->ri_total > item->ri_cnt);
/* Description region is ri_buf[0] */
xlog_recover_t *tp;
int found = 0;
- ASSERT(trans != 0);
+ ASSERT(trans != NULL);
if (trans == *q) {
*q = (*q)->r_next;
} else {
tp = *q;
- while (tp != 0) {
+ while (tp) {
if (tp->r_next == trans) {
found = 1;
break;
xlog_recover_item_t **q,
xlog_recover_item_t *item)
{
- if (*q == 0) {
+ if (*q == NULL) {
item->ri_prev = item->ri_next = item;
*q = item;
} else {
STATIC int
xlog_recover_reorder_trans(
- xlog_t *log,
xlog_recover_t *trans)
{
xlog_recover_item_t *first_item, *itemq, *itemq_next;
xfs_buf_log_format_t *buf_f;
- xfs_buf_log_format_v1_t *obuf_f;
ushort flags = 0;
first_item = itemq = trans->r_itemq;
do {
itemq_next = itemq->ri_next;
buf_f = (xfs_buf_log_format_t *)itemq->ri_buf[0].i_addr;
- switch (ITEM_TYPE(itemq)) {
- case XFS_LI_BUF:
- flags = buf_f->blf_flags;
- break;
- case XFS_LI_6_1_BUF:
- case XFS_LI_5_3_BUF:
- obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
- flags = obuf_f->blf_flags;
- break;
- }
switch (ITEM_TYPE(itemq)) {
case XFS_LI_BUF:
- case XFS_LI_6_1_BUF:
- case XFS_LI_5_3_BUF:
+ flags = buf_f->blf_flags;
if (!(flags & XFS_BLI_CANCEL)) {
xlog_recover_insert_item_frontq(&trans->r_itemq,
itemq);
break;
}
case XFS_LI_INODE:
- case XFS_LI_6_1_INODE:
- case XFS_LI_5_3_INODE:
case XFS_LI_DQUOT:
case XFS_LI_QUOTAOFF:
case XFS_LI_EFD:
xfs_buf_cancel_t *nextp;
xfs_buf_cancel_t *prevp;
xfs_buf_cancel_t **bucket;
- xfs_buf_log_format_v1_t *obuf_f;
xfs_daddr_t blkno = 0;
uint len = 0;
ushort flags = 0;
len = buf_f->blf_len;
flags = buf_f->blf_flags;
break;
- case XFS_LI_6_1_BUF:
- case XFS_LI_5_3_BUF:
- obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
- blkno = (xfs_daddr_t) obuf_f->blf_blkno;
- len = obuf_f->blf_len;
- flags = obuf_f->blf_flags;
- break;
}
/*
} else {
prevp->bc_next = bcp->bc_next;
}
- kmem_free(bcp,
- sizeof(xfs_buf_cancel_t));
+ kmem_free(bcp);
}
}
return 1;
xlog_t *log,
xfs_buf_log_format_t *buf_f)
{
- xfs_buf_log_format_v1_t *obuf_f;
xfs_daddr_t blkno = 0;
ushort flags = 0;
uint len = 0;
flags = buf_f->blf_flags;
len = buf_f->blf_len;
break;
- case XFS_LI_6_1_BUF:
- case XFS_LI_5_3_BUF:
- obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
- blkno = (xfs_daddr_t) obuf_f->blf_blkno;
- flags = obuf_f->blf_flags;
- len = (xfs_daddr_t) obuf_f->blf_len;
- break;
}
return xlog_check_buffer_cancelled(log, blkno, len, flags);
int inodes_per_buf;
xfs_agino_t *logged_nextp;
xfs_agino_t *buffer_nextp;
- xfs_buf_log_format_v1_t *obuf_f;
unsigned int *data_map = NULL;
unsigned int map_size = 0;
data_map = buf_f->blf_data_map;
map_size = buf_f->blf_map_size;
break;
- case XFS_LI_6_1_BUF:
- case XFS_LI_5_3_BUF:
- obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
- data_map = obuf_f->blf_data_map;
- map_size = obuf_f->blf_map_size;
- break;
}
/*
* Set the variables corresponding to the current region to
buffer_nextp = (xfs_agino_t *)xfs_buf_offset(bp,
next_unlinked_offset);
- INT_SET(*buffer_nextp, ARCH_CONVERT, *logged_nextp);
+ *buffer_nextp = *logged_nextp;
}
return 0;
/*ARGSUSED*/
STATIC void
xlog_recover_do_reg_buffer(
- xfs_mount_t *mp,
xlog_recover_item_t *item,
xfs_buf_t *bp,
xfs_buf_log_format_t *buf_f)
int i;
int bit;
int nbits;
- xfs_buf_log_format_v1_t *obuf_f;
unsigned int *data_map = NULL;
unsigned int map_size = 0;
int error;
data_map = buf_f->blf_data_map;
map_size = buf_f->blf_map_size;
break;
- case XFS_LI_6_1_BUF:
- case XFS_LI_5_3_BUF:
- obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
- data_map = obuf_f->blf_data_map;
- map_size = obuf_f->blf_map_size;
- break;
}
bit = 0;
i = 1; /* 0 is the buf format structure */
break;
nbits = xfs_contig_bits(data_map, map_size, bit);
ASSERT(nbits > 0);
- ASSERT(item->ri_buf[i].i_addr != 0);
+ ASSERT(item->ri_buf[i].i_addr != NULL);
ASSERT(item->ri_buf[i].i_len % XFS_BLI_CHUNK == 0);
ASSERT(XFS_BUF_COUNT(bp) >=
((uint)bit << XFS_BLI_SHIFT)+(nbits<<XFS_BLI_SHIFT));
error = 0;
if (buf_f->blf_flags &
(XFS_BLI_UDQUOT_BUF|XFS_BLI_PDQUOT_BUF|XFS_BLI_GDQUOT_BUF)) {
+ if (item->ri_buf[i].i_addr == NULL) {
+ cmn_err(CE_ALERT,
+ "XFS: NULL dquot in %s.", __func__);
+ goto next;
+ }
+ if (item->ri_buf[i].i_len < sizeof(xfs_dqblk_t)) {
+ cmn_err(CE_ALERT,
+ "XFS: dquot too small (%d) in %s.",
+ item->ri_buf[i].i_len, __func__);
+ goto next;
+ }
error = xfs_qm_dqcheck((xfs_disk_dquot_t *)
item->ri_buf[i].i_addr,
-1, 0, XFS_QMOPT_DOWARN,
"dquot_buf_recover");
+ if (error)
+ goto next;
}
- if (!error)
- memcpy(xfs_buf_offset(bp,
- (uint)bit << XFS_BLI_SHIFT), /* dest */
- item->ri_buf[i].i_addr, /* source */
- nbits<<XFS_BLI_SHIFT); /* length */
+
+ memcpy(xfs_buf_offset(bp,
+ (uint)bit << XFS_BLI_SHIFT), /* dest */
+ item->ri_buf[i].i_addr, /* source */
+ nbits<<XFS_BLI_SHIFT); /* length */
+ next:
i++;
bit += nbits;
}
if (log->l_quotaoffs_flag & type)
return;
- xlog_recover_do_reg_buffer(mp, item, bp, buf_f);
+ xlog_recover_do_reg_buffer(item, bp, buf_f);
}
/*
int pass)
{
xfs_buf_log_format_t *buf_f;
- xfs_buf_log_format_v1_t *obuf_f;
xfs_mount_t *mp;
xfs_buf_t *bp;
int error;
len = buf_f->blf_len;
flags = buf_f->blf_flags;
break;
- case XFS_LI_6_1_BUF:
- case XFS_LI_5_3_BUF:
- obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
- blkno = obuf_f->blf_blkno;
- len = obuf_f->blf_len;
- flags = obuf_f->blf_flags;
- break;
default:
xfs_fs_cmn_err(CE_ALERT, log->l_mp,
"xfs_log_recover: unknown buffer type 0x%x, logdev %s",
(XFS_BLI_UDQUOT_BUF|XFS_BLI_PDQUOT_BUF|XFS_BLI_GDQUOT_BUF)) {
xlog_recover_do_dquot_buffer(mp, log, item, bp, buf_f);
} else {
- xlog_recover_do_reg_buffer(mp, item, bp, buf_f);
+ xlog_recover_do_reg_buffer(item, bp, buf_f);
}
if (error)
return XFS_ERROR(error);
* overlap with future reads of those inodes.
*/
if (XFS_DINODE_MAGIC ==
- INT_GET(*((__uint16_t *)(xfs_buf_offset(bp, 0))), ARCH_CONVERT) &&
+ be16_to_cpu(*((__be16 *)xfs_buf_offset(bp, 0))) &&
(XFS_BUF_COUNT(bp) != MAX(log->l_mp->m_sb.sb_blocksize,
(__uint32_t)XFS_INODE_CLUSTER_SIZE(log->l_mp)))) {
XFS_BUF_STALE(bp);
error = xfs_bwrite(mp, bp);
} else {
- ASSERT(XFS_BUF_FSPRIVATE(bp, void *) == NULL ||
- XFS_BUF_FSPRIVATE(bp, xfs_mount_t *) == mp);
- XFS_BUF_SET_FSPRIVATE(bp, mp);
+ ASSERT(bp->b_mount == NULL || bp->b_mount == mp);
+ bp->b_mount = mp;
XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone);
xfs_bdwrite(mp, bp);
}
xfs_inode_log_format_t *in_f;
xfs_mount_t *mp;
xfs_buf_t *bp;
- xfs_imap_t imap;
xfs_dinode_t *dip;
xfs_ino_t ino;
int len;
int error;
int attr_index;
uint fields;
- xfs_dinode_core_t *dicp;
+ xfs_icdinode_t *dicp;
+ int need_free = 0;
if (pass == XLOG_RECOVER_PASS1) {
return 0;
}
- in_f = (xfs_inode_log_format_t *)item->ri_buf[0].i_addr;
- ino = in_f->ilf_ino;
- mp = log->l_mp;
- if (ITEM_TYPE(item) == XFS_LI_INODE) {
- imap.im_blkno = (xfs_daddr_t)in_f->ilf_blkno;
- imap.im_len = in_f->ilf_len;
- imap.im_boffset = in_f->ilf_boffset;
+ if (item->ri_buf[0].i_len == sizeof(xfs_inode_log_format_t)) {
+ in_f = (xfs_inode_log_format_t *)item->ri_buf[0].i_addr;
} else {
- /*
- * It's an old inode format record. We don't know where
- * its cluster is located on disk, and we can't allow
- * xfs_imap() to figure it out because the inode btrees
- * are not ready to be used. Therefore do not pass the
- * XFS_IMAP_LOOKUP flag to xfs_imap(). This will give
- * us only the single block in which the inode lives
- * rather than its cluster, so we must make sure to
- * invalidate the buffer when we write it out below.
- */
- imap.im_blkno = 0;
- xfs_imap(log->l_mp, NULL, ino, &imap, 0);
+ in_f = (xfs_inode_log_format_t *)kmem_alloc(
+ sizeof(xfs_inode_log_format_t), KM_SLEEP);
+ need_free = 1;
+ error = xfs_inode_item_format_convert(&item->ri_buf[0], in_f);
+ if (error)
+ goto error;
}
+ ino = in_f->ilf_ino;
+ mp = log->l_mp;
/*
* Inode buffers can be freed, look out for it,
* and do not replay the inode.
*/
- if (xlog_check_buffer_cancelled(log, imap.im_blkno, imap.im_len, 0))
- return 0;
+ if (xlog_check_buffer_cancelled(log, in_f->ilf_blkno,
+ in_f->ilf_len, 0)) {
+ error = 0;
+ goto error;
+ }
- bp = xfs_buf_read_flags(mp->m_ddev_targp, imap.im_blkno, imap.im_len,
- XFS_BUF_LOCK);
+ bp = xfs_buf_read_flags(mp->m_ddev_targp, in_f->ilf_blkno,
+ in_f->ilf_len, XFS_BUF_LOCK);
if (XFS_BUF_ISERROR(bp)) {
xfs_ioerror_alert("xlog_recover_do..(read#2)", mp,
- bp, imap.im_blkno);
+ bp, in_f->ilf_blkno);
error = XFS_BUF_GETERROR(bp);
xfs_buf_relse(bp);
- return error;
+ goto error;
}
error = 0;
ASSERT(in_f->ilf_fields & XFS_ILOG_CORE);
- dip = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
+ dip = (xfs_dinode_t *)xfs_buf_offset(bp, in_f->ilf_boffset);
/*
* Make sure the place we're flushing out to really looks
* like an inode!
*/
- if (unlikely(INT_GET(dip->di_core.di_magic, ARCH_CONVERT) != XFS_DINODE_MAGIC)) {
+ if (unlikely(be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC)) {
xfs_buf_relse(bp);
xfs_fs_cmn_err(CE_ALERT, mp,
"xfs_inode_recover: Bad inode magic number, dino ptr = 0x%p, dino bp = 0x%p, ino = %Ld",
dip, bp, ino);
XFS_ERROR_REPORT("xlog_recover_do_inode_trans(1)",
XFS_ERRLEVEL_LOW, mp);
- return XFS_ERROR(EFSCORRUPTED);
+ error = EFSCORRUPTED;
+ goto error;
}
- dicp = (xfs_dinode_core_t*)(item->ri_buf[1].i_addr);
+ dicp = (xfs_icdinode_t *)(item->ri_buf[1].i_addr);
if (unlikely(dicp->di_magic != XFS_DINODE_MAGIC)) {
xfs_buf_relse(bp);
xfs_fs_cmn_err(CE_ALERT, mp,
item, ino);
XFS_ERROR_REPORT("xlog_recover_do_inode_trans(2)",
XFS_ERRLEVEL_LOW, mp);
- return XFS_ERROR(EFSCORRUPTED);
+ error = EFSCORRUPTED;
+ goto error;
}
/* Skip replay when the on disk inode is newer than the log one */
- if (dicp->di_flushiter <
- INT_GET(dip->di_core.di_flushiter, ARCH_CONVERT)) {
+ if (dicp->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
/*
* Deal with the wrap case, DI_MAX_FLUSH is less
* than smaller numbers
*/
- if ((INT_GET(dip->di_core.di_flushiter, ARCH_CONVERT)
- == DI_MAX_FLUSH) &&
- (dicp->di_flushiter < (DI_MAX_FLUSH>>1))) {
+ if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
+ dicp->di_flushiter < (DI_MAX_FLUSH >> 1)) {
/* do nothing */
} else {
xfs_buf_relse(bp);
- return 0;
+ error = 0;
+ goto error;
}
}
/* Take the opportunity to reset the flush iteration count */
xfs_fs_cmn_err(CE_ALERT, mp,
"xfs_inode_recover: Bad regular inode log record, rec ptr 0x%p, ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
item, dip, bp, ino);
- return XFS_ERROR(EFSCORRUPTED);
+ error = EFSCORRUPTED;
+ goto error;
}
} else if (unlikely((dicp->di_mode & S_IFMT) == S_IFDIR)) {
if ((dicp->di_format != XFS_DINODE_FMT_EXTENTS) &&
xfs_fs_cmn_err(CE_ALERT, mp,
"xfs_inode_recover: Bad dir inode log record, rec ptr 0x%p, ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
item, dip, bp, ino);
- return XFS_ERROR(EFSCORRUPTED);
+ error = EFSCORRUPTED;
+ goto error;
}
}
if (unlikely(dicp->di_nextents + dicp->di_anextents > dicp->di_nblocks)){
item, dip, bp, ino,
dicp->di_nextents + dicp->di_anextents,
dicp->di_nblocks);
- return XFS_ERROR(EFSCORRUPTED);
+ error = EFSCORRUPTED;
+ goto error;
}
if (unlikely(dicp->di_forkoff > mp->m_sb.sb_inodesize)) {
XFS_CORRUPTION_ERROR("xlog_recover_do_inode_trans(6)",
xfs_fs_cmn_err(CE_ALERT, mp,
"xfs_inode_recover: Bad inode log rec ptr 0x%p, dino ptr 0x%p, dino bp 0x%p, ino %Ld, forkoff 0x%x",
item, dip, bp, ino, dicp->di_forkoff);
- return XFS_ERROR(EFSCORRUPTED);
+ error = EFSCORRUPTED;
+ goto error;
}
- if (unlikely(item->ri_buf[1].i_len > sizeof(xfs_dinode_core_t))) {
+ if (unlikely(item->ri_buf[1].i_len > sizeof(struct xfs_icdinode))) {
XFS_CORRUPTION_ERROR("xlog_recover_do_inode_trans(7)",
XFS_ERRLEVEL_LOW, mp, dicp);
xfs_buf_relse(bp);
xfs_fs_cmn_err(CE_ALERT, mp,
"xfs_inode_recover: Bad inode log record length %d, rec ptr 0x%p",
item->ri_buf[1].i_len, item);
- return XFS_ERROR(EFSCORRUPTED);
+ error = EFSCORRUPTED;
+ goto error;
}
/* The core is in in-core format */
- xfs_xlate_dinode_core((xfs_caddr_t)&dip->di_core,
- (xfs_dinode_core_t*)item->ri_buf[1].i_addr, -1);
+ xfs_dinode_to_disk(dip, (xfs_icdinode_t *)item->ri_buf[1].i_addr);
/* the rest is in on-disk format */
- if (item->ri_buf[1].i_len > sizeof(xfs_dinode_core_t)) {
- memcpy((xfs_caddr_t) dip + sizeof(xfs_dinode_core_t),
- item->ri_buf[1].i_addr + sizeof(xfs_dinode_core_t),
- item->ri_buf[1].i_len - sizeof(xfs_dinode_core_t));
+ if (item->ri_buf[1].i_len > sizeof(struct xfs_icdinode)) {
+ memcpy((xfs_caddr_t) dip + sizeof(struct xfs_icdinode),
+ item->ri_buf[1].i_addr + sizeof(struct xfs_icdinode),
+ item->ri_buf[1].i_len - sizeof(struct xfs_icdinode));
}
fields = in_f->ilf_fields;
switch (fields & (XFS_ILOG_DEV | XFS_ILOG_UUID)) {
case XFS_ILOG_DEV:
- INT_SET(dip->di_u.di_dev, ARCH_CONVERT, in_f->ilf_u.ilfu_rdev);
-
+ xfs_dinode_put_rdev(dip, in_f->ilf_u.ilfu_rdev);
break;
case XFS_ILOG_UUID:
- dip->di_u.di_muuid = in_f->ilf_u.ilfu_uuid;
+ memcpy(XFS_DFORK_DPTR(dip),
+ &in_f->ilf_u.ilfu_uuid,
+ sizeof(uuid_t));
break;
}
switch (fields & XFS_ILOG_DFORK) {
case XFS_ILOG_DDATA:
case XFS_ILOG_DEXT:
- memcpy(&dip->di_u, src, len);
+ memcpy(XFS_DFORK_DPTR(dip), src, len);
break;
case XFS_ILOG_DBROOT:
- xfs_bmbt_to_bmdr((xfs_bmbt_block_t *)src, len,
- &(dip->di_u.di_bmbt),
+ xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src, len,
+ (xfs_bmdr_block_t *)XFS_DFORK_DPTR(dip),
XFS_DFORK_DSIZE(dip, mp));
break;
case XFS_ILOG_ABROOT:
dest = XFS_DFORK_APTR(dip);
- xfs_bmbt_to_bmdr((xfs_bmbt_block_t *)src, len,
- (xfs_bmdr_block_t*)dest,
+ xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src,
+ len, (xfs_bmdr_block_t*)dest,
XFS_DFORK_ASIZE(dip, mp));
break;
xlog_warn("XFS: xlog_recover_do_inode_trans: Invalid flag");
ASSERT(0);
xfs_buf_relse(bp);
- return XFS_ERROR(EIO);
+ error = EIO;
+ goto error;
}
}
write_inode_buffer:
- if (ITEM_TYPE(item) == XFS_LI_INODE) {
- ASSERT(XFS_BUF_FSPRIVATE(bp, void *) == NULL ||
- XFS_BUF_FSPRIVATE(bp, xfs_mount_t *) == mp);
- XFS_BUF_SET_FSPRIVATE(bp, mp);
- XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone);
- xfs_bdwrite(mp, bp);
- } else {
- XFS_BUF_STALE(bp);
- error = xfs_bwrite(mp, bp);
- }
-
- return (error);
+ ASSERT(bp->b_mount == NULL || bp->b_mount == mp);
+ bp->b_mount = mp;
+ XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone);
+ xfs_bdwrite(mp, bp);
+error:
+ if (need_free)
+ kmem_free(in_f);
+ return XFS_ERROR(error);
}
/*
/*
* The logitem format's flag tells us if this was user quotaoff,
- * group quotaoff or both.
+ * group/project quotaoff or both.
*/
if (qoff_f->qf_flags & XFS_UQUOTA_ACCT)
log->l_quotaoffs_flag |= XFS_DQ_USER;
+ if (qoff_f->qf_flags & XFS_PQUOTA_ACCT)
+ log->l_quotaoffs_flag |= XFS_DQ_PROJ;
if (qoff_f->qf_flags & XFS_GQUOTA_ACCT)
log->l_quotaoffs_flag |= XFS_DQ_GROUP;
return (0);
recddq = (xfs_disk_dquot_t *)item->ri_buf[1].i_addr;
- ASSERT(recddq);
+
+ if (item->ri_buf[1].i_addr == NULL) {
+ cmn_err(CE_ALERT,
+ "XFS: NULL dquot in %s.", __func__);
+ return XFS_ERROR(EIO);
+ }
+ if (item->ri_buf[1].i_len < sizeof(xfs_dqblk_t)) {
+ cmn_err(CE_ALERT,
+ "XFS: dquot too small (%d) in %s.",
+ item->ri_buf[1].i_len, __func__);
+ return XFS_ERROR(EIO);
+ }
+
/*
* This type of quotas was turned off, so ignore this record.
*/
- type = INT_GET(recddq->d_flags, ARCH_CONVERT) &
- (XFS_DQ_USER | XFS_DQ_PROJ | XFS_DQ_GROUP);
+ type = recddq->d_flags & (XFS_DQ_USER | XFS_DQ_PROJ | XFS_DQ_GROUP);
ASSERT(type);
if (log->l_quotaoffs_flag & type)
return (0);
memcpy(ddq, recddq, item->ri_buf[1].i_len);
ASSERT(dq_f->qlf_size == 2);
- ASSERT(XFS_BUF_FSPRIVATE(bp, void *) == NULL ||
- XFS_BUF_FSPRIVATE(bp, xfs_mount_t *) == mp);
- XFS_BUF_SET_FSPRIVATE(bp, mp);
+ ASSERT(bp->b_mount == NULL || bp->b_mount == mp);
+ bp->b_mount = mp;
XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone);
xfs_bdwrite(mp, bp);
* structure into it, and adds the efi to the AIL with the given
* LSN.
*/
-STATIC void
+STATIC int
xlog_recover_do_efi_trans(
xlog_t *log,
xlog_recover_item_t *item,
xfs_lsn_t lsn,
int pass)
{
+ int error;
xfs_mount_t *mp;
xfs_efi_log_item_t *efip;
xfs_efi_log_format_t *efi_formatp;
- SPLDECL(s);
if (pass == XLOG_RECOVER_PASS1) {
- return;
+ return 0;
}
efi_formatp = (xfs_efi_log_format_t *)item->ri_buf[0].i_addr;
- ASSERT(item->ri_buf[0].i_len ==
- (sizeof(xfs_efi_log_format_t) +
- ((efi_formatp->efi_nextents - 1) * sizeof(xfs_extent_t))));
mp = log->l_mp;
efip = xfs_efi_init(mp, efi_formatp->efi_nextents);
- memcpy((char *)&(efip->efi_format), (char *)efi_formatp,
- sizeof(xfs_efi_log_format_t) +
- ((efi_formatp->efi_nextents - 1) * sizeof(xfs_extent_t)));
+ if ((error = xfs_efi_copy_format(&(item->ri_buf[0]),
+ &(efip->efi_format)))) {
+ xfs_efi_item_free(efip);
+ return error;
+ }
efip->efi_next_extent = efi_formatp->efi_nextents;
efip->efi_flags |= XFS_EFI_COMMITTED;
- AIL_LOCK(mp,s);
+ spin_lock(&log->l_ailp->xa_lock);
/*
- * xfs_trans_update_ail() drops the AIL lock.
+ * xfs_trans_ail_update() drops the AIL lock.
*/
- xfs_trans_update_ail(mp, (xfs_log_item_t *)efip, lsn, s);
+ xfs_trans_ail_update(log->l_ailp, (xfs_log_item_t *)efip, lsn);
+ return 0;
}
xlog_recover_item_t *item,
int pass)
{
- xfs_mount_t *mp;
xfs_efd_log_format_t *efd_formatp;
xfs_efi_log_item_t *efip = NULL;
xfs_log_item_t *lip;
- int gen;
__uint64_t efi_id;
- SPLDECL(s);
+ struct xfs_ail_cursor cur;
+ struct xfs_ail *ailp = log->l_ailp;
if (pass == XLOG_RECOVER_PASS1) {
return;
}
efd_formatp = (xfs_efd_log_format_t *)item->ri_buf[0].i_addr;
- ASSERT(item->ri_buf[0].i_len ==
- (sizeof(xfs_efd_log_format_t) +
- ((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_t))));
+ ASSERT((item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_32_t) +
+ ((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_32_t)))) ||
+ (item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_64_t) +
+ ((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_64_t)))));
efi_id = efd_formatp->efd_efi_id;
/*
* Search for the efi with the id in the efd format structure
* in the AIL.
*/
- mp = log->l_mp;
- AIL_LOCK(mp,s);
- lip = xfs_trans_first_ail(mp, &gen);
+ spin_lock(&ailp->xa_lock);
+ lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
while (lip != NULL) {
if (lip->li_type == XFS_LI_EFI) {
efip = (xfs_efi_log_item_t *)lip;
if (efip->efi_format.efi_id == efi_id) {
/*
- * xfs_trans_delete_ail() drops the
+ * xfs_trans_ail_delete() drops the
* AIL lock.
*/
- xfs_trans_delete_ail(mp, lip, s);
+ xfs_trans_ail_delete(ailp, lip);
+ xfs_efi_item_free(efip);
+ spin_lock(&ailp->xa_lock);
break;
}
}
- lip = xfs_trans_next_ail(mp, lip, &gen, NULL);
- }
-
- /*
- * If we found it, then free it up. If it wasn't there, it
- * must have been overwritten in the log. Oh well.
- */
- if (lip != NULL) {
- xfs_efi_item_free(efip);
- } else {
- AIL_UNLOCK(mp, s);
+ lip = xfs_trans_ail_cursor_next(ailp, &cur);
}
+ xfs_trans_ail_cursor_done(ailp, &cur);
+ spin_unlock(&ailp->xa_lock);
}
/*
int error = 0;
xlog_recover_item_t *item, *first_item;
- if ((error = xlog_recover_reorder_trans(log, trans)))
+ error = xlog_recover_reorder_trans(trans);
+ if (error)
return error;
+
first_item = item = trans->r_itemq;
do {
- /*
- * we don't need to worry about the block number being
- * truncated in > 1 TB buffers because in user-land,
- * we're now n32 or 64-bit so xfs_daddr_t is 64-bits so
- * the blkno's will get through the user-mode buffer
- * cache properly. The only bad case is o32 kernels
- * where xfs_daddr_t is 32-bits but mount will warn us
- * off a > 1 TB filesystem before we get here.
- */
- if ((ITEM_TYPE(item) == XFS_LI_BUF) ||
- (ITEM_TYPE(item) == XFS_LI_6_1_BUF) ||
- (ITEM_TYPE(item) == XFS_LI_5_3_BUF)) {
- if ((error = xlog_recover_do_buffer_trans(log, item,
- pass)))
- break;
- } else if ((ITEM_TYPE(item) == XFS_LI_INODE) ||
- (ITEM_TYPE(item) == XFS_LI_6_1_INODE) ||
- (ITEM_TYPE(item) == XFS_LI_5_3_INODE)) {
- if ((error = xlog_recover_do_inode_trans(log, item,
- pass)))
- break;
- } else if (ITEM_TYPE(item) == XFS_LI_EFI) {
- xlog_recover_do_efi_trans(log, item, trans->r_lsn,
- pass);
- } else if (ITEM_TYPE(item) == XFS_LI_EFD) {
+ switch (ITEM_TYPE(item)) {
+ case XFS_LI_BUF:
+ error = xlog_recover_do_buffer_trans(log, item, pass);
+ break;
+ case XFS_LI_INODE:
+ error = xlog_recover_do_inode_trans(log, item, pass);
+ break;
+ case XFS_LI_EFI:
+ error = xlog_recover_do_efi_trans(log, item,
+ trans->r_lsn, pass);
+ break;
+ case XFS_LI_EFD:
xlog_recover_do_efd_trans(log, item, pass);
- } else if (ITEM_TYPE(item) == XFS_LI_DQUOT) {
- if ((error = xlog_recover_do_dquot_trans(log, item,
- pass)))
- break;
- } else if ((ITEM_TYPE(item) == XFS_LI_QUOTAOFF)) {
- if ((error = xlog_recover_do_quotaoff_trans(log, item,
- pass)))
- break;
- } else {
- xlog_warn("XFS: xlog_recover_do_trans");
+ error = 0;
+ break;
+ case XFS_LI_DQUOT:
+ error = xlog_recover_do_dquot_trans(log, item, pass);
+ break;
+ case XFS_LI_QUOTAOFF:
+ error = xlog_recover_do_quotaoff_trans(log, item,
+ pass);
+ break;
+ default:
+ xlog_warn(
+ "XFS: invalid item type (%d) xlog_recover_do_trans", ITEM_TYPE(item));
ASSERT(0);
error = XFS_ERROR(EIO);
break;
}
+
+ if (error)
+ return error;
item = item->ri_next;
} while (first_item != item);
- return error;
+ return 0;
}
/*
item = item->ri_next;
/* Free the regions in the item. */
for (i = 0; i < free_item->ri_cnt; i++) {
- kmem_free(free_item->ri_buf[i].i_addr,
- free_item->ri_buf[i].i_len);
+ kmem_free(free_item->ri_buf[i].i_addr);
}
/* Free the item itself */
- kmem_free(free_item->ri_buf,
- (free_item->ri_total * sizeof(xfs_log_iovec_t)));
- kmem_free(free_item, sizeof(xlog_recover_item_t));
+ kmem_free(free_item->ri_buf);
+ kmem_free(free_item);
} while (first_item != item);
/* Free the transaction recover structure */
- kmem_free(trans, sizeof(xlog_recover_t));
+ kmem_free(trans);
}
STATIC int
unsigned long hash;
uint flags;
- lp = dp + INT_GET(rhead->h_len, ARCH_CONVERT);
- num_logops = INT_GET(rhead->h_num_logops, ARCH_CONVERT);
+ lp = dp + be32_to_cpu(rhead->h_len);
+ num_logops = be32_to_cpu(rhead->h_num_logops);
/* check the log format matches our own - else we can't recover */
if (xlog_header_check_recover(log->l_mp, rhead))
ASSERT(0);
return (XFS_ERROR(EIO));
}
- tid = INT_GET(ohead->oh_tid, ARCH_CONVERT);
+ tid = be32_to_cpu(ohead->oh_tid);
hash = XLOG_RHASH(tid);
trans = xlog_recover_find_tid(rhash[hash], tid);
if (trans == NULL) { /* not found; add new tid */
if (ohead->oh_flags & XLOG_START_TRANS)
xlog_recover_new_tid(&rhash[hash], tid,
- INT_GET(rhead->h_lsn, ARCH_CONVERT));
+ be64_to_cpu(rhead->h_lsn));
} else {
- ASSERT(dp+INT_GET(ohead->oh_len, ARCH_CONVERT) <= lp);
+ if (dp + be32_to_cpu(ohead->oh_len) > lp) {
+ xlog_warn(
+ "XFS: xlog_recover_process_data: bad length");
+ WARN_ON(1);
+ return (XFS_ERROR(EIO));
+ }
flags = ohead->oh_flags & ~XLOG_END_TRANS;
if (flags & XLOG_WAS_CONT_TRANS)
flags &= ~XLOG_CONTINUE_TRANS;
break;
case XLOG_WAS_CONT_TRANS:
error = xlog_recover_add_to_cont_trans(trans,
- dp, INT_GET(ohead->oh_len,
- ARCH_CONVERT));
+ dp, be32_to_cpu(ohead->oh_len));
break;
case XLOG_START_TRANS:
xlog_warn(
case 0:
case XLOG_CONTINUE_TRANS:
error = xlog_recover_add_to_trans(trans,
- dp, INT_GET(ohead->oh_len,
- ARCH_CONVERT));
+ dp, be32_to_cpu(ohead->oh_len));
break;
default:
xlog_warn(
if (error)
return error;
}
- dp += INT_GET(ohead->oh_len, ARCH_CONVERT);
+ dp += be32_to_cpu(ohead->oh_len);
num_logops--;
}
return 0;
* Process an extent free intent item that was recovered from
* the log. We need to free the extents that it describes.
*/
-STATIC void
+STATIC int
xlog_recover_process_efi(
xfs_mount_t *mp,
xfs_efi_log_item_t *efip)
xfs_efd_log_item_t *efdp;
xfs_trans_t *tp;
int i;
+ int error = 0;
xfs_extent_t *extp;
xfs_fsblock_t startblock_fsb;
* free the memory associated with it.
*/
xfs_efi_release(efip, efip->efi_format.efi_nextents);
- return;
+ return XFS_ERROR(EIO);
}
}
tp = xfs_trans_alloc(mp, 0);
- xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0, 0, 0);
+ error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0, 0, 0);
+ if (error)
+ goto abort_error;
efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);
for (i = 0; i < efip->efi_format.efi_nextents; i++) {
extp = &(efip->efi_format.efi_extents[i]);
- xfs_free_extent(tp, extp->ext_start, extp->ext_len);
+ error = xfs_free_extent(tp, extp->ext_start, extp->ext_len);
+ if (error)
+ goto abort_error;
xfs_trans_log_efd_extent(tp, efdp, extp->ext_start,
extp->ext_len);
}
efip->efi_flags |= XFS_EFI_RECOVERED;
- xfs_trans_commit(tp, 0, NULL);
-}
-
-/*
- * Verify that once we've encountered something other than an EFI
- * in the AIL that there are no more EFIs in the AIL.
- */
-#if defined(DEBUG)
-STATIC void
-xlog_recover_check_ail(
- xfs_mount_t *mp,
- xfs_log_item_t *lip,
- int gen)
-{
- int orig_gen = gen;
+ error = xfs_trans_commit(tp, 0);
+ return error;
- do {
- ASSERT(lip->li_type != XFS_LI_EFI);
- lip = xfs_trans_next_ail(mp, lip, &gen, NULL);
- /*
- * The check will be bogus if we restart from the
- * beginning of the AIL, so ASSERT that we don't.
- * We never should since we're holding the AIL lock
- * the entire time.
- */
- ASSERT(gen == orig_gen);
- } while (lip != NULL);
+abort_error:
+ xfs_trans_cancel(tp, XFS_TRANS_ABORT);
+ return error;
}
-#endif /* DEBUG */
/*
* When this is called, all of the EFIs which did not have
* everything already in the AIL, we stop processing as soon as
* we see something other than an EFI in the AIL.
*/
-STATIC void
+STATIC int
xlog_recover_process_efis(
xlog_t *log)
{
xfs_log_item_t *lip;
xfs_efi_log_item_t *efip;
- int gen;
- xfs_mount_t *mp;
- SPLDECL(s);
-
- mp = log->l_mp;
- AIL_LOCK(mp,s);
+ int error = 0;
+ struct xfs_ail_cursor cur;
+ struct xfs_ail *ailp;
- lip = xfs_trans_first_ail(mp, &gen);
+ ailp = log->l_ailp;
+ spin_lock(&ailp->xa_lock);
+ lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
while (lip != NULL) {
/*
* We're done when we see something other than an EFI.
+ * There should be no EFIs left in the AIL now.
*/
if (lip->li_type != XFS_LI_EFI) {
- xlog_recover_check_ail(mp, lip, gen);
+#ifdef DEBUG
+ for (; lip; lip = xfs_trans_ail_cursor_next(ailp, &cur))
+ ASSERT(lip->li_type != XFS_LI_EFI);
+#endif
break;
}
*/
efip = (xfs_efi_log_item_t *)lip;
if (efip->efi_flags & XFS_EFI_RECOVERED) {
- lip = xfs_trans_next_ail(mp, lip, &gen, NULL);
+ lip = xfs_trans_ail_cursor_next(ailp, &cur);
continue;
}
- AIL_UNLOCK(mp, s);
- xlog_recover_process_efi(mp, efip);
- AIL_LOCK(mp,s);
- lip = xfs_trans_next_ail(mp, lip, &gen, NULL);
+ spin_unlock(&ailp->xa_lock);
+ error = xlog_recover_process_efi(log->l_mp, efip);
+ spin_lock(&ailp->xa_lock);
+ if (error)
+ goto out;
+ lip = xfs_trans_ail_cursor_next(ailp, &cur);
}
- AIL_UNLOCK(mp, s);
+out:
+ xfs_trans_ail_cursor_done(ailp, &cur);
+ spin_unlock(&ailp->xa_lock);
+ return error;
}
/*
int error;
tp = xfs_trans_alloc(mp, XFS_TRANS_CLEAR_AGI_BUCKET);
- xfs_trans_reserve(tp, 0, XFS_CLEAR_AGI_BUCKET_LOG_RES(mp), 0, 0, 0);
+ error = xfs_trans_reserve(tp, 0, XFS_CLEAR_AGI_BUCKET_LOG_RES(mp),
+ 0, 0, 0);
+ if (error)
+ goto out_abort;
- error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
- XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0, &agibp);
- if (error) {
- xfs_trans_cancel(tp, XFS_TRANS_ABORT);
- return;
- }
+ error = xfs_read_agi(mp, tp, agno, &agibp);
+ if (error)
+ goto out_abort;
agi = XFS_BUF_TO_AGI(agibp);
- if (INT_GET(agi->agi_magicnum, ARCH_CONVERT) != XFS_AGI_MAGIC) {
- xfs_trans_cancel(tp, XFS_TRANS_ABORT);
- return;
- }
- ASSERT(INT_GET(agi->agi_magicnum, ARCH_CONVERT) == XFS_AGI_MAGIC);
-
- INT_SET(agi->agi_unlinked[bucket], ARCH_CONVERT, NULLAGINO);
+ agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
offset = offsetof(xfs_agi_t, agi_unlinked) +
(sizeof(xfs_agino_t) * bucket);
xfs_trans_log_buf(tp, agibp, offset,
(offset + sizeof(xfs_agino_t) - 1));
- (void) xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
+ if (error)
+ goto out_error;
+ return;
+
+out_abort:
+ xfs_trans_cancel(tp, XFS_TRANS_ABORT);
+out_error:
+ xfs_fs_cmn_err(CE_WARN, mp, "xlog_recover_clear_agi_bucket: "
+ "failed to clear agi %d. Continuing.", agno);
+ return;
+}
+
+STATIC xfs_agino_t
+xlog_recover_process_one_iunlink(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno,
+ xfs_agino_t agino,
+ int bucket)
+{
+ struct xfs_buf *ibp;
+ struct xfs_dinode *dip;
+ struct xfs_inode *ip;
+ xfs_ino_t ino;
+ int error;
+
+ ino = XFS_AGINO_TO_INO(mp, agno, agino);
+ error = xfs_iget(mp, NULL, ino, 0, 0, &ip, 0);
+ if (error)
+ goto fail;
+
+ /*
+ * Get the on disk inode to find the next inode in the bucket.
+ */
+ error = xfs_itobp(mp, NULL, ip, &dip, &ibp, XFS_BUF_LOCK);
+ if (error)
+ goto fail_iput;
+
+ ASSERT(ip->i_d.di_nlink == 0);
+ ASSERT(ip->i_d.di_mode != 0);
+
+ /* setup for the next pass */
+ agino = be32_to_cpu(dip->di_next_unlinked);
+ xfs_buf_relse(ibp);
+
+ /*
+ * Prevent any DMAPI event from being sent when the reference on
+ * the inode is dropped.
+ */
+ ip->i_d.di_dmevmask = 0;
+
+ IRELE(ip);
+ return agino;
+
+ fail_iput:
+ IRELE(ip);
+ fail:
+ /*
+ * We can't read in the inode this bucket points to, or this inode
+ * is messed up. Just ditch this bucket of inodes. We will lose
+ * some inodes and space, but at least we won't hang.
+ *
+ * Call xlog_recover_clear_agi_bucket() to perform a transaction to
+ * clear the inode pointer in the bucket.
+ */
+ xlog_recover_clear_agi_bucket(mp, agno, bucket);
+ return NULLAGINO;
}
/*
* freeing of the inode and its removal from the list must be
* atomic.
*/
-void
+STATIC void
xlog_recover_process_iunlinks(
xlog_t *log)
{
xfs_agnumber_t agno;
xfs_agi_t *agi;
xfs_buf_t *agibp;
- xfs_buf_t *ibp;
- xfs_dinode_t *dip;
- xfs_inode_t *ip;
xfs_agino_t agino;
- xfs_ino_t ino;
int bucket;
int error;
uint mp_dmevmask;
/*
* Find the agi for this ag.
*/
- agibp = xfs_buf_read(mp->m_ddev_targp,
- XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0);
- if (XFS_BUF_ISERROR(agibp)) {
- xfs_ioerror_alert("xlog_recover_process_iunlinks(#1)",
- log->l_mp, agibp,
- XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)));
+ error = xfs_read_agi(mp, NULL, agno, &agibp);
+ if (error) {
+ /*
+ * AGI is b0rked. Don't process it.
+ *
+ * We should probably mark the filesystem as corrupt
+ * after we've recovered all the ag's we can....
+ */
+ continue;
}
agi = XFS_BUF_TO_AGI(agibp);
- ASSERT(XFS_AGI_MAGIC ==
- INT_GET(agi->agi_magicnum, ARCH_CONVERT));
for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++) {
-
- agino = INT_GET(agi->agi_unlinked[bucket], ARCH_CONVERT);
+ agino = be32_to_cpu(agi->agi_unlinked[bucket]);
while (agino != NULLAGINO) {
-
/*
* Release the agi buffer so that it can
* be acquired in the normal course of the
*/
xfs_buf_relse(agibp);
- ino = XFS_AGINO_TO_INO(mp, agno, agino);
- error = xfs_iget(mp, NULL, ino, 0, 0, &ip, 0);
- ASSERT(error || (ip != NULL));
-
- if (!error) {
- /*
- * Get the on disk inode to find the
- * next inode in the bucket.
- */
- error = xfs_itobp(mp, NULL, ip, &dip,
- &ibp, 0);
- ASSERT(error || (dip != NULL));
- }
-
- if (!error) {
- ASSERT(ip->i_d.di_nlink == 0);
-
- /* setup for the next pass */
- agino = INT_GET(dip->di_next_unlinked,
- ARCH_CONVERT);
- xfs_buf_relse(ibp);
- /*
- * Prevent any DMAPI event from
- * being sent when the
- * reference on the inode is
- * dropped.
- */
- ip->i_d.di_dmevmask = 0;
-
- /*
- * If this is a new inode, handle
- * it specially. Otherwise,
- * just drop our reference to the
- * inode. If there are no
- * other references, this will
- * send the inode to
- * xfs_inactive() which will
- * truncate the file and free
- * the inode.
- */
- if (ip->i_d.di_mode == 0)
- xfs_iput_new(ip, 0);
- else
- VN_RELE(XFS_ITOV(ip));
- } else {
- /*
- * We can't read in the inode
- * this bucket points to, or
- * this inode is messed up. Just
- * ditch this bucket of inodes. We
- * will lose some inodes and space,
- * but at least we won't hang. Call
- * xlog_recover_clear_agi_bucket()
- * to perform a transaction to clear
- * the inode pointer in the bucket.
- */
- xlog_recover_clear_agi_bucket(mp, agno,
- bucket);
-
- agino = NULLAGINO;
- }
+ agino = xlog_recover_process_one_iunlink(mp,
+ agno, agino, bucket);
/*
* Reacquire the agibuffer and continue around
- * the loop.
+ * the loop. This should never fail as we know
+ * the buffer was good earlier on.
*/
- agibp = xfs_buf_read(mp->m_ddev_targp,
- XFS_AG_DADDR(mp, agno,
- XFS_AGI_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0);
- if (XFS_BUF_ISERROR(agibp)) {
- xfs_ioerror_alert(
- "xlog_recover_process_iunlinks(#2)",
- log->l_mp, agibp,
- XFS_AG_DADDR(mp, agno,
- XFS_AGI_DADDR(mp)));
- }
+ error = xfs_read_agi(mp, NULL, agno, &agibp);
+ ASSERT(error == 0);
agi = XFS_BUF_TO_AGI(agibp);
- ASSERT(XFS_AGI_MAGIC == INT_GET(
- agi->agi_magicnum, ARCH_CONVERT));
}
}
int size)
{
int i;
- uint *up;
+ __be32 *up;
uint chksum = 0;
- up = (uint *)iclog->ic_datap;
+ up = (__be32 *)iclog->ic_datap;
/* divide length by 4 to get # words */
for (i = 0; i < (size >> 2); i++) {
- chksum ^= INT_GET(*up, ARCH_CONVERT);
+ chksum ^= be32_to_cpu(*up);
up++;
}
- INT_SET(iclog->ic_header.h_chksum, ARCH_CONVERT, chksum);
+ iclog->ic_header.h_chksum = cpu_to_be32(chksum);
}
#else
#define xlog_pack_data_checksum(log, iclog, size)
{
int i, j, k;
int size = iclog->ic_offset + roundoff;
- uint cycle_lsn;
+ __be32 cycle_lsn;
xfs_caddr_t dp;
- xlog_in_core_2_t *xhdr;
xlog_pack_data_checksum(log, iclog, size);
dp = iclog->ic_datap;
for (i = 0; i < BTOBB(size) &&
i < (XLOG_HEADER_CYCLE_SIZE / BBSIZE); i++) {
- iclog->ic_header.h_cycle_data[i] = *(uint *)dp;
- *(uint *)dp = cycle_lsn;
+ iclog->ic_header.h_cycle_data[i] = *(__be32 *)dp;
+ *(__be32 *)dp = cycle_lsn;
dp += BBSIZE;
}
- if (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb)) {
- xhdr = (xlog_in_core_2_t *)&iclog->ic_header;
+ if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
+ xlog_in_core_2_t *xhdr = iclog->ic_data;
+
for ( ; i < BTOBB(size); i++) {
j = i / (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
k = i % (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
- xhdr[j].hic_xheader.xh_cycle_data[k] = *(uint *)dp;
- *(uint *)dp = cycle_lsn;
+ xhdr[j].hic_xheader.xh_cycle_data[k] = *(__be32 *)dp;
+ *(__be32 *)dp = cycle_lsn;
dp += BBSIZE;
}
xfs_caddr_t dp,
xlog_t *log)
{
- uint *up = (uint *)dp;
+ __be32 *up = (__be32 *)dp;
uint chksum = 0;
int i;
/* divide length by 4 to get # words */
- for (i=0; i < INT_GET(rhead->h_len, ARCH_CONVERT) >> 2; i++) {
- chksum ^= INT_GET(*up, ARCH_CONVERT);
+ for (i=0; i < be32_to_cpu(rhead->h_len) >> 2; i++) {
+ chksum ^= be32_to_cpu(*up);
up++;
}
- if (chksum != INT_GET(rhead->h_chksum, ARCH_CONVERT)) {
+ if (chksum != be32_to_cpu(rhead->h_chksum)) {
if (rhead->h_chksum ||
((log->l_flags & XLOG_CHKSUM_MISMATCH) == 0)) {
cmn_err(CE_DEBUG,
- "XFS: LogR chksum mismatch: was (0x%x) is (0x%x)",
- INT_GET(rhead->h_chksum, ARCH_CONVERT), chksum);
+ "XFS: LogR chksum mismatch: was (0x%x) is (0x%x)\n",
+ be32_to_cpu(rhead->h_chksum), chksum);
cmn_err(CE_DEBUG,
"XFS: Disregard message if filesystem was created with non-DEBUG kernel");
- if (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb)) {
+ if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
cmn_err(CE_DEBUG,
- "XFS: LogR this is a LogV2 filesystem");
+ "XFS: LogR this is a LogV2 filesystem\n");
}
log->l_flags |= XLOG_CHKSUM_MISMATCH;
}
xlog_t *log)
{
int i, j, k;
- xlog_in_core_2_t *xhdr;
- for (i = 0; i < BTOBB(INT_GET(rhead->h_len, ARCH_CONVERT)) &&
+ for (i = 0; i < BTOBB(be32_to_cpu(rhead->h_len)) &&
i < (XLOG_HEADER_CYCLE_SIZE / BBSIZE); i++) {
- *(uint *)dp = *(uint *)&rhead->h_cycle_data[i];
+ *(__be32 *)dp = *(__be32 *)&rhead->h_cycle_data[i];
dp += BBSIZE;
}
- if (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb)) {
- xhdr = (xlog_in_core_2_t *)rhead;
- for ( ; i < BTOBB(INT_GET(rhead->h_len, ARCH_CONVERT)); i++) {
+ if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
+ xlog_in_core_2_t *xhdr = (xlog_in_core_2_t *)rhead;
+ for ( ; i < BTOBB(be32_to_cpu(rhead->h_len)); i++) {
j = i / (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
k = i % (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
- *(uint *)dp = xhdr[j].hic_xheader.xh_cycle_data[k];
+ *(__be32 *)dp = xhdr[j].hic_xheader.xh_cycle_data[k];
dp += BBSIZE;
}
}
{
int hlen;
- if (unlikely(
- (INT_GET(rhead->h_magicno, ARCH_CONVERT) !=
- XLOG_HEADER_MAGIC_NUM))) {
+ if (unlikely(be32_to_cpu(rhead->h_magicno) != XLOG_HEADER_MAGIC_NUM)) {
XFS_ERROR_REPORT("xlog_valid_rec_header(1)",
XFS_ERRLEVEL_LOW, log->l_mp);
return XFS_ERROR(EFSCORRUPTED);
}
if (unlikely(
(!rhead->h_version ||
- (INT_GET(rhead->h_version, ARCH_CONVERT) &
- (~XLOG_VERSION_OKBITS)) != 0))) {
+ (be32_to_cpu(rhead->h_version) & (~XLOG_VERSION_OKBITS))))) {
xlog_warn("XFS: %s: unrecognised log version (%d).",
- __FUNCTION__, INT_GET(rhead->h_version, ARCH_CONVERT));
+ __func__, be32_to_cpu(rhead->h_version));
return XFS_ERROR(EIO);
}
/* LR body must have data or it wouldn't have been written */
- hlen = INT_GET(rhead->h_len, ARCH_CONVERT);
+ hlen = be32_to_cpu(rhead->h_len);
if (unlikely( hlen <= 0 || hlen > INT_MAX )) {
XFS_ERROR_REPORT("xlog_valid_rec_header(2)",
XFS_ERRLEVEL_LOW, log->l_mp);
* Read the header of the tail block and get the iclog buffer size from
* h_size. Use this to tell how many sectors make up the log header.
*/
- if (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb)) {
+ if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
/*
* When using variable length iclogs, read first sector of
* iclog header and extract the header size from it. Get a
hbp = xlog_get_bp(log, 1);
if (!hbp)
return ENOMEM;
- if ((error = xlog_bread(log, tail_blk, 1, hbp)))
+
+ error = xlog_bread(log, tail_blk, 1, hbp, &offset);
+ if (error)
goto bread_err1;
- offset = xlog_align(log, tail_blk, 1, hbp);
+
rhead = (xlog_rec_header_t *)offset;
error = xlog_valid_rec_header(log, rhead, tail_blk);
if (error)
goto bread_err1;
- h_size = INT_GET(rhead->h_size, ARCH_CONVERT);
- if ((INT_GET(rhead->h_version, ARCH_CONVERT)
- & XLOG_VERSION_2) &&
+ h_size = be32_to_cpu(rhead->h_size);
+ if ((be32_to_cpu(rhead->h_version) & XLOG_VERSION_2) &&
(h_size > XLOG_HEADER_CYCLE_SIZE)) {
hblks = h_size / XLOG_HEADER_CYCLE_SIZE;
if (h_size % XLOG_HEADER_CYCLE_SIZE)
memset(rhash, 0, sizeof(rhash));
if (tail_blk <= head_blk) {
for (blk_no = tail_blk; blk_no < head_blk; ) {
- if ((error = xlog_bread(log, blk_no, hblks, hbp)))
+ error = xlog_bread(log, blk_no, hblks, hbp, &offset);
+ if (error)
goto bread_err2;
- offset = xlog_align(log, blk_no, hblks, hbp);
+
rhead = (xlog_rec_header_t *)offset;
error = xlog_valid_rec_header(log, rhead, blk_no);
if (error)
goto bread_err2;
/* blocks in data section */
- bblks = (int)BTOBB(INT_GET(rhead->h_len, ARCH_CONVERT));
- error = xlog_bread(log, blk_no + hblks, bblks, dbp);
+ bblks = (int)BTOBB(be32_to_cpu(rhead->h_len));
+ error = xlog_bread(log, blk_no + hblks, bblks, dbp,
+ &offset);
if (error)
goto bread_err2;
- offset = xlog_align(log, blk_no + hblks, bblks, dbp);
+
xlog_unpack_data(rhead, offset, log);
if ((error = xlog_recover_process_data(log,
rhash, rhead, offset, pass)))
wrapped_hblks = 0;
if (blk_no + hblks <= log->l_logBBsize) {
/* Read header in one read */
- error = xlog_bread(log, blk_no, hblks, hbp);
+ error = xlog_bread(log, blk_no, hblks, hbp,
+ &offset);
if (error)
goto bread_err2;
- offset = xlog_align(log, blk_no, hblks, hbp);
} else {
/* This LR is split across physical log end */
if (blk_no != log->l_logBBsize) {
ASSERT(blk_no <= INT_MAX);
split_hblks = log->l_logBBsize - (int)blk_no;
ASSERT(split_hblks > 0);
- if ((error = xlog_bread(log, blk_no,
- split_hblks, hbp)))
+ error = xlog_bread(log, blk_no,
+ split_hblks, hbp,
+ &offset);
+ if (error)
goto bread_err2;
- offset = xlog_align(log, blk_no,
- split_hblks, hbp);
}
+
/*
* Note: this black magic still works with
* large sector sizes (non-512) only because:
* _first_, then the log start (LR header end)
* - order is important.
*/
+ wrapped_hblks = hblks - split_hblks;
bufaddr = XFS_BUF_PTR(hbp);
- XFS_BUF_SET_PTR(hbp,
+ error = XFS_BUF_SET_PTR(hbp,
bufaddr + BBTOB(split_hblks),
BBTOB(hblks - split_hblks));
- wrapped_hblks = hblks - split_hblks;
- error = xlog_bread(log, 0, wrapped_hblks, hbp);
if (error)
goto bread_err2;
- XFS_BUF_SET_PTR(hbp, bufaddr, BBTOB(hblks));
+
+ error = xlog_bread_noalign(log, 0,
+ wrapped_hblks, hbp);
+ if (error)
+ goto bread_err2;
+
+ error = XFS_BUF_SET_PTR(hbp, bufaddr,
+ BBTOB(hblks));
+ if (error)
+ goto bread_err2;
+
if (!offset)
offset = xlog_align(log, 0,
wrapped_hblks, hbp);
if (error)
goto bread_err2;
- bblks = (int)BTOBB(INT_GET(rhead->h_len, ARCH_CONVERT));
+ bblks = (int)BTOBB(be32_to_cpu(rhead->h_len));
blk_no += hblks;
/* Read in data for log record */
if (blk_no + bblks <= log->l_logBBsize) {
- error = xlog_bread(log, blk_no, bblks, dbp);
+ error = xlog_bread(log, blk_no, bblks, dbp,
+ &offset);
if (error)
goto bread_err2;
- offset = xlog_align(log, blk_no, bblks, dbp);
} else {
/* This log record is split across the
* physical end of log */
split_bblks =
log->l_logBBsize - (int)blk_no;
ASSERT(split_bblks > 0);
- if ((error = xlog_bread(log, blk_no,
- split_bblks, dbp)))
+ error = xlog_bread(log, blk_no,
+ split_bblks, dbp,
+ &offset);
+ if (error)
goto bread_err2;
- offset = xlog_align(log, blk_no,
- split_bblks, dbp);
}
+
/*
* Note: this black magic still works with
* large sector sizes (non-512) only because:
* - order is important.
*/
bufaddr = XFS_BUF_PTR(dbp);
- XFS_BUF_SET_PTR(dbp,
+ error = XFS_BUF_SET_PTR(dbp,
bufaddr + BBTOB(split_bblks),
BBTOB(bblks - split_bblks));
- if ((error = xlog_bread(log, wrapped_hblks,
- bblks - split_bblks, dbp)))
+ if (error)
+ goto bread_err2;
+
+ error = xlog_bread_noalign(log, wrapped_hblks,
+ bblks - split_bblks,
+ dbp);
+ if (error)
goto bread_err2;
- XFS_BUF_SET_PTR(dbp, bufaddr, h_size);
+
+ error = XFS_BUF_SET_PTR(dbp, bufaddr, h_size);
+ if (error)
+ goto bread_err2;
+
if (!offset)
offset = xlog_align(log, wrapped_hblks,
bblks - split_bblks, dbp);
/* read first part of physical log */
while (blk_no < head_blk) {
- if ((error = xlog_bread(log, blk_no, hblks, hbp)))
+ error = xlog_bread(log, blk_no, hblks, hbp, &offset);
+ if (error)
goto bread_err2;
- offset = xlog_align(log, blk_no, hblks, hbp);
+
rhead = (xlog_rec_header_t *)offset;
error = xlog_valid_rec_header(log, rhead, blk_no);
if (error)
goto bread_err2;
- bblks = (int)BTOBB(INT_GET(rhead->h_len, ARCH_CONVERT));
- if ((error = xlog_bread(log, blk_no+hblks, bblks, dbp)))
+
+ bblks = (int)BTOBB(be32_to_cpu(rhead->h_len));
+ error = xlog_bread(log, blk_no+hblks, bblks, dbp,
+ &offset);
+ if (error)
goto bread_err2;
- offset = xlog_align(log, blk_no+hblks, bblks, dbp);
+
xlog_unpack_data(rhead, offset, log);
if ((error = xlog_recover_process_data(log, rhash,
rhead, offset, pass)))
error = xlog_do_recovery_pass(log, head_blk, tail_blk,
XLOG_RECOVER_PASS1);
if (error != 0) {
- kmem_free(log->l_buf_cancel_table,
- XLOG_BC_TABLE_SIZE * sizeof(xfs_buf_cancel_t*));
+ kmem_free(log->l_buf_cancel_table);
log->l_buf_cancel_table = NULL;
return error;
}
error = xlog_do_recovery_pass(log, head_blk, tail_blk,
XLOG_RECOVER_PASS2);
#ifdef DEBUG
- {
+ if (!error) {
int i;
for (i = 0; i < XLOG_BC_TABLE_SIZE; i++)
}
#endif /* DEBUG */
- kmem_free(log->l_buf_cancel_table,
- XLOG_BC_TABLE_SIZE * sizeof(xfs_buf_cancel_t*));
+ kmem_free(log->l_buf_cancel_table);
log->l_buf_cancel_table = NULL;
return error;
*/
bp = xfs_getsb(log->l_mp, 0);
XFS_BUF_UNDONE(bp);
+ ASSERT(!(XFS_BUF_ISWRITE(bp)));
+ ASSERT(!(XFS_BUF_ISDELAYWRITE(bp)));
XFS_BUF_READ(bp);
+ XFS_BUF_UNASYNC(bp);
xfsbdstrat(log->l_mp, bp);
- if ((error = xfs_iowait(bp))) {
+ error = xfs_iowait(bp);
+ if (error) {
xfs_ioerror_alert("xlog_do_recover",
log->l_mp, bp, XFS_BUF_ADDR(bp));
ASSERT(0);
/* Convert superblock from on-disk format */
sbp = &log->l_mp->m_sb;
- xfs_xlatesb(XFS_BUF_TO_SBP(bp), sbp, 1, XFS_SB_ALL_BITS);
+ xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp));
ASSERT(sbp->sb_magicnum == XFS_SB_MAGIC);
- ASSERT(XFS_SB_GOOD_VERSION(sbp));
+ ASSERT(xfs_sb_good_version(sbp));
xfs_buf_relse(bp);
+ /* We've re-read the superblock so re-initialize per-cpu counters */
+ xfs_icsb_reinit_counters(log->l_mp);
+
xlog_recover_check_summary(log);
/* Normal transactions can now occur */
*/
int
xlog_recover(
- xlog_t *log,
- int readonly)
+ xlog_t *log)
{
xfs_daddr_t head_blk, tail_blk;
int error;
/* find the tail of the log */
- if ((error = xlog_find_tail(log, &head_blk, &tail_blk, readonly)))
+ if ((error = xlog_find_tail(log, &head_blk, &tail_blk)))
return error;
if (tail_blk != head_blk) {
* under the vfs layer, so we can get away with it unless
* the device itself is read-only, in which case we fail.
*/
- if ((error = xfs_dev_is_read_only(log->l_mp,
- "recovery required"))) {
+ if ((error = xfs_dev_is_read_only(log->l_mp, "recovery"))) {
return error;
}
*/
int
xlog_recover_finish(
- xlog_t *log,
- int mfsi_flags)
+ xlog_t *log)
{
/*
* Now we're ready to do the transactions needed for the
* rather than accepting new requests.
*/
if (log->l_flags & XLOG_RECOVERY_NEEDED) {
- xlog_recover_process_efis(log);
+ int error;
+ error = xlog_recover_process_efis(log);
+ if (error) {
+ cmn_err(CE_ALERT,
+ "Failed to recover EFIs on filesystem: %s",
+ log->l_mp->m_fsname);
+ return error;
+ }
/*
* Sync the log to get all the EFIs out of the AIL.
* This isn't absolutely necessary, but it helps in
xfs_log_force(log->l_mp, (xfs_lsn_t)0,
(XFS_LOG_FORCE | XFS_LOG_SYNC));
- if ( (mfsi_flags & XFS_MFSI_NOUNLINK) == 0 ) {
- xlog_recover_process_iunlinks(log);
- }
+ xlog_recover_process_iunlinks(log);
xlog_recover_check_summary(log);
log->l_flags &= ~XLOG_RECOVERY_NEEDED;
} else {
cmn_err(CE_DEBUG,
- "!Ending clean XFS mount for filesystem: %s",
+ "!Ending clean XFS mount for filesystem: %s\n",
log->l_mp->m_fsname);
}
return 0;
{
xfs_mount_t *mp;
xfs_agf_t *agfp;
- xfs_agi_t *agip;
xfs_buf_t *agfbp;
xfs_buf_t *agibp;
- xfs_daddr_t agfdaddr;
- xfs_daddr_t agidaddr;
xfs_buf_t *sbbp;
#ifdef XFS_LOUD_RECOVERY
xfs_sb_t *sbp;
__uint64_t freeblks;
__uint64_t itotal;
__uint64_t ifree;
+ int error;
mp = log->l_mp;
itotal = 0LL;
ifree = 0LL;
for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
- agfdaddr = XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp));
- agfbp = xfs_buf_read(mp->m_ddev_targp, agfdaddr,
- XFS_FSS_TO_BB(mp, 1), 0);
- if (XFS_BUF_ISERROR(agfbp)) {
- xfs_ioerror_alert("xlog_recover_check_summary(agf)",
- mp, agfbp, agfdaddr);
+ error = xfs_read_agf(mp, NULL, agno, 0, &agfbp);
+ if (error) {
+ xfs_fs_cmn_err(CE_ALERT, mp,
+ "xlog_recover_check_summary(agf)"
+ "agf read failed agno %d error %d",
+ agno, error);
+ } else {
+ agfp = XFS_BUF_TO_AGF(agfbp);
+ freeblks += be32_to_cpu(agfp->agf_freeblks) +
+ be32_to_cpu(agfp->agf_flcount);
+ xfs_buf_relse(agfbp);
}
- agfp = XFS_BUF_TO_AGF(agfbp);
- ASSERT(XFS_AGF_MAGIC ==
- INT_GET(agfp->agf_magicnum, ARCH_CONVERT));
- ASSERT(XFS_AGF_GOOD_VERSION(
- INT_GET(agfp->agf_versionnum, ARCH_CONVERT)));
- ASSERT(INT_GET(agfp->agf_seqno, ARCH_CONVERT) == agno);
-
- freeblks += INT_GET(agfp->agf_freeblks, ARCH_CONVERT) +
- INT_GET(agfp->agf_flcount, ARCH_CONVERT);
- xfs_buf_relse(agfbp);
-
- agidaddr = XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp));
- agibp = xfs_buf_read(mp->m_ddev_targp, agidaddr,
- XFS_FSS_TO_BB(mp, 1), 0);
- if (XFS_BUF_ISERROR(agibp)) {
- xfs_ioerror_alert("xlog_recover_check_summary(agi)",
- mp, agibp, agidaddr);
+
+ error = xfs_read_agi(mp, NULL, agno, &agibp);
+ if (!error) {
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(agibp);
+
+ itotal += be32_to_cpu(agi->agi_count);
+ ifree += be32_to_cpu(agi->agi_freecount);
+ xfs_buf_relse(agibp);
}
- agip = XFS_BUF_TO_AGI(agibp);
- ASSERT(XFS_AGI_MAGIC ==
- INT_GET(agip->agi_magicnum, ARCH_CONVERT));
- ASSERT(XFS_AGI_GOOD_VERSION(
- INT_GET(agip->agi_versionnum, ARCH_CONVERT)));
- ASSERT(INT_GET(agip->agi_seqno, ARCH_CONVERT) == agno);
-
- itotal += INT_GET(agip->agi_count, ARCH_CONVERT);
- ifree += INT_GET(agip->agi_freecount, ARCH_CONVERT);
- xfs_buf_relse(agibp);
}
sbbp = xfs_getsb(mp, 0);
#ifdef XFS_LOUD_RECOVERY
sbp = &mp->m_sb;
- xfs_xlatesb(XFS_BUF_TO_SBP(sbbp), sbp, 1, XFS_SB_ALL_BITS);
+ xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(sbbp));
cmn_err(CE_NOTE,
"xlog_recover_check_summary: sb_icount %Lu itotal %Lu",
sbp->sb_icount, itotal);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff