From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/fs/xfs/xfs_bmap_util.c | 532 ++++++++++++++++++-----------------------------------------
1 files changed, 163 insertions(+), 369 deletions(-)
diff --git a/kernel/fs/xfs/xfs_bmap_util.c b/kernel/fs/xfs/xfs_bmap_util.c
index 3e1dd66..7371a7f 100644
--- a/kernel/fs/xfs/xfs_bmap_util.c
+++ b/kernel/fs/xfs/xfs_bmap_util.c
@@ -12,12 +12,10 @@
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_mount.h"
-#include "xfs_da_format.h"
#include "xfs_defer.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_trans.h"
-#include "xfs_extfree_item.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
@@ -28,11 +26,8 @@
#include "xfs_trans_space.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
-#include "xfs_log.h"
-#include "xfs_rmap_btree.h"
#include "xfs_iomap.h"
#include "xfs_reflink.h"
-#include "xfs_refcount.h"
/* Kernel only BMAP related definitions and functions */
@@ -44,9 +39,9 @@
xfs_daddr_t
xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
{
- return (XFS_IS_REALTIME_INODE(ip) ? \
- (xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \
- XFS_FSB_TO_DADDR((ip)->i_mount, (fsb)));
+ if (XFS_IS_REALTIME_INODE(ip))
+ return XFS_FSB_TO_BB(ip->i_mount, fsb);
+ return XFS_FSB_TO_DADDR(ip->i_mount, fsb);
}
/*
@@ -58,15 +53,16 @@
*/
int
xfs_zero_extent(
- struct xfs_inode *ip,
- xfs_fsblock_t start_fsb,
- xfs_off_t count_fsb)
+ struct xfs_inode *ip,
+ xfs_fsblock_t start_fsb,
+ xfs_off_t count_fsb)
{
- struct xfs_mount *mp = ip->i_mount;
- xfs_daddr_t sector = xfs_fsb_to_db(ip, start_fsb);
- sector_t block = XFS_BB_TO_FSBT(mp, sector);
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_buftarg *target = xfs_inode_buftarg(ip);
+ xfs_daddr_t sector = xfs_fsb_to_db(ip, start_fsb);
+ sector_t block = XFS_BB_TO_FSBT(mp, sector);
- return blkdev_issue_zeroout(xfs_find_bdev_for_inode(VFS_I(ip)),
+ return blkdev_issue_zeroout(target->bt_bdev,
block << (mp->m_super->s_blocksize_bits - 9),
count_fsb << (mp->m_super->s_blocksize_bits - 9),
GFP_NOFS, 0);
@@ -130,7 +126,7 @@
* pick an extent that will space things out in the rt area.
*/
if (ap->eof && ap->offset == 0) {
- xfs_rtblock_t uninitialized_var(rtx); /* realtime extent no */
+ xfs_rtblock_t rtx; /* realtime extent no */
error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx);
if (error)
@@ -169,42 +165,12 @@
xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
-
- /* Zero the extent if we were asked to do so */
- if (ap->datatype & XFS_ALLOC_USERDATA_ZERO) {
- error = xfs_zero_extent(ap->ip, ap->blkno, ap->length);
- if (error)
- return error;
- }
} else {
ap->length = 0;
}
return 0;
}
#endif /* CONFIG_XFS_RT */
-
-/*
- * Check if the endoff is outside the last extent. If so the caller will grow
- * the allocation to a stripe unit boundary. All offsets are considered outside
- * the end of file for an empty fork, so 1 is returned in *eof in that case.
- */
-int
-xfs_bmap_eof(
- struct xfs_inode *ip,
- xfs_fileoff_t endoff,
- int whichfork,
- int *eof)
-{
- struct xfs_bmbt_irec rec;
- int error;
-
- error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, eof);
- if (error || *eof)
- return error;
-
- *eof = endoff >= rec.br_startoff + rec.br_blockcount;
- return 0;
-}
/*
* Extent tree block counting routines.
@@ -234,106 +200,6 @@
}
/*
- * Count leaf blocks given a range of extent records originally
- * in btree format.
- */
-STATIC void
-xfs_bmap_disk_count_leaves(
- struct xfs_mount *mp,
- struct xfs_btree_block *block,
- int numrecs,
- xfs_filblks_t *count)
-{
- int b;
- xfs_bmbt_rec_t *frp;
-
- for (b = 1; b <= numrecs; b++) {
- frp = XFS_BMBT_REC_ADDR(mp, block, b);
- *count += xfs_bmbt_disk_get_blockcount(frp);
- }
-}
-
-/*
- * Recursively walks each level of a btree
- * to count total fsblocks in use.
- */
-STATIC int
-xfs_bmap_count_tree(
- struct xfs_mount *mp,
- struct xfs_trans *tp,
- struct xfs_ifork *ifp,
- xfs_fsblock_t blockno,
- int levelin,
- xfs_extnum_t *nextents,
- xfs_filblks_t *count)
-{
- int error;
- struct xfs_buf *bp, *nbp;
- int level = levelin;
- __be64 *pp;
- xfs_fsblock_t bno = blockno;
- xfs_fsblock_t nextbno;
- struct xfs_btree_block *block, *nextblock;
- int numrecs;
-
- error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, XFS_BMAP_BTREE_REF,
- &xfs_bmbt_buf_ops);
- if (error)
- return error;
- *count += 1;
- block = XFS_BUF_TO_BLOCK(bp);
-
- if (--level) {
- /* Not at node above leaves, count this level of nodes */
- nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
- while (nextbno != NULLFSBLOCK) {
- error = xfs_btree_read_bufl(mp, tp, nextbno, 0, &nbp,
- XFS_BMAP_BTREE_REF,
- &xfs_bmbt_buf_ops);
- if (error)
- return error;
- *count += 1;
- nextblock = XFS_BUF_TO_BLOCK(nbp);
- nextbno = be64_to_cpu(nextblock->bb_u.l.bb_rightsib);
- xfs_trans_brelse(tp, nbp);
- }
-
- /* Dive to the next level */
- pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
- bno = be64_to_cpu(*pp);
- error = xfs_bmap_count_tree(mp, tp, ifp, bno, level, nextents,
- count);
- if (error) {
- xfs_trans_brelse(tp, bp);
- XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
- XFS_ERRLEVEL_LOW, mp);
- return -EFSCORRUPTED;
- }
- xfs_trans_brelse(tp, bp);
- } else {
- /* count all level 1 nodes and their leaves */
- for (;;) {
- nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
- numrecs = be16_to_cpu(block->bb_numrecs);
- (*nextents) += numrecs;
- xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
- xfs_trans_brelse(tp, bp);
- if (nextbno == NULLFSBLOCK)
- break;
- bno = nextbno;
- error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
- XFS_BMAP_BTREE_REF,
- &xfs_bmbt_buf_ops);
- if (error)
- return error;
- *count += 1;
- block = XFS_BUF_TO_BLOCK(bp);
- }
- }
- return 0;
-}
-
-/*
* Count fsblocks of the given fork. Delayed allocation extents are
* not counted towards the totals.
*/
@@ -345,26 +211,19 @@
xfs_extnum_t *nextents,
xfs_filblks_t *count)
{
- struct xfs_mount *mp; /* file system mount structure */
- __be64 *pp; /* pointer to block address */
- struct xfs_btree_block *block; /* current btree block */
- struct xfs_ifork *ifp; /* fork structure */
- xfs_fsblock_t bno; /* block # of "block" */
- int level; /* btree level, for checking */
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_btree_cur *cur;
+ xfs_extlen_t btblocks = 0;
int error;
- bno = NULLFSBLOCK;
- mp = ip->i_mount;
*nextents = 0;
*count = 0;
- ifp = XFS_IFORK_PTR(ip, whichfork);
+
if (!ifp)
return 0;
- switch (XFS_IFORK_FORMAT(ip, whichfork)) {
- case XFS_DINODE_FMT_EXTENTS:
- *nextents = xfs_bmap_count_leaves(ifp, count);
- return 0;
+ switch (ifp->if_format) {
case XFS_DINODE_FMT_BTREE:
if (!(ifp->if_flags & XFS_IFEXTENTS)) {
error = xfs_iread_extents(tp, ip, whichfork);
@@ -372,26 +231,23 @@
return error;
}
- /*
- * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
- */
- block = ifp->if_broot;
- level = be16_to_cpu(block->bb_level);
- ASSERT(level > 0);
- pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
- bno = be64_to_cpu(*pp);
- ASSERT(bno != NULLFSBLOCK);
- ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
- ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
+ cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
+ error = xfs_btree_count_blocks(cur, &btblocks);
+ xfs_btree_del_cursor(cur, error);
+ if (error)
+ return error;
- error = xfs_bmap_count_tree(mp, tp, ifp, bno, level,
- nextents, count);
- if (error) {
- XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)",
- XFS_ERRLEVEL_LOW, mp);
- return -EFSCORRUPTED;
- }
- return 0;
+ /*
+ * xfs_btree_count_blocks includes the root block contained in
+ * the inode fork in @btblocks, so subtract one because we're
+ * only interested in allocated disk blocks.
+ */
+ *count += btblocks - 1;
+
+ /* fall through */
+ case XFS_DINODE_FMT_EXTENTS:
+ *nextents = xfs_bmap_count_leaves(ifp, count);
+ break;
}
return 0;
@@ -406,10 +262,10 @@
struct xfs_bmbt_irec *got)
{
struct kgetbmap *p = out + bmv->bmv_entries;
- bool shared = false, trimmed = false;
+ bool shared = false;
int error;
- error = xfs_reflink_trim_around_shared(ip, got, &shared, &trimmed);
+ error = xfs_reflink_trim_around_shared(ip, got, &shared);
if (error)
return error;
@@ -593,7 +449,7 @@
break;
}
- switch (XFS_IFORK_FORMAT(ip, whichfork)) {
+ switch (ifp->if_format) {
case XFS_DINODE_FMT_EXTENTS:
case XFS_DINODE_FMT_BTREE:
break;
@@ -869,6 +725,7 @@
xfs_filblks_t allocatesize_fsb;
xfs_extlen_t extsz, temp;
xfs_fileoff_t startoffset_fsb;
+ xfs_fileoff_t endoffset_fsb;
int nimaps;
int quota_flag;
int rt;
@@ -896,7 +753,8 @@
imapp = &imaps[0];
nimaps = 1;
startoffset_fsb = XFS_B_TO_FSBT(mp, offset);
- allocatesize_fsb = XFS_B_TO_FSB(mp, count);
+ endoffset_fsb = XFS_B_TO_FSB(mp, offset + count);
+ allocatesize_fsb = endoffset_fsb - startoffset_fsb;
/*
* Allocate file space until done or until there is an error
@@ -967,8 +825,8 @@
xfs_trans_ijoin(tp, ip, 0);
error = xfs_bmapi_write(tp, ip, startoffset_fsb,
- allocatesize_fsb, alloc_type, resblks,
- imapp, &nimaps);
+ allocatesize_fsb, alloc_type, 0, imapp,
+ &nimaps);
if (error)
goto error0;
@@ -1042,44 +900,7 @@
goto out_unlock;
}
-static int
-xfs_adjust_extent_unmap_boundaries(
- struct xfs_inode *ip,
- xfs_fileoff_t *startoffset_fsb,
- xfs_fileoff_t *endoffset_fsb)
-{
- struct xfs_mount *mp = ip->i_mount;
- struct xfs_bmbt_irec imap;
- int nimap, error;
- xfs_extlen_t mod = 0;
-
- nimap = 1;
- error = xfs_bmapi_read(ip, *startoffset_fsb, 1, &imap, &nimap, 0);
- if (error)
- return error;
-
- if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
- ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
- div_u64_rem(imap.br_startblock, mp->m_sb.sb_rextsize, &mod);
- if (mod)
- *startoffset_fsb += mp->m_sb.sb_rextsize - mod;
- }
-
- nimap = 1;
- error = xfs_bmapi_read(ip, *endoffset_fsb - 1, 1, &imap, &nimap, 0);
- if (error)
- return error;
-
- if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
- ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
- mod++;
- if (mod && mod != mp->m_sb.sb_rextsize)
- *endoffset_fsb -= mod;
- }
-
- return 0;
-}
-
+/* Caller must first wait for the completion of any pending DIOs if required. */
int
xfs_flush_unmap_range(
struct xfs_inode *ip,
@@ -1090,9 +911,6 @@
struct inode *inode = VFS_I(ip);
xfs_off_t rounding, start, end;
int error;
-
- /* wait for the completion of any pending DIOs */
- inode_dio_wait(inode);
rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_SIZE);
start = round_down(offset, rounding);
@@ -1125,27 +943,20 @@
if (len <= 0) /* if nothing being freed */
return 0;
- error = xfs_flush_unmap_range(ip, offset, len);
- if (error)
- return error;
-
startoffset_fsb = XFS_B_TO_FSB(mp, offset);
endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
- /*
- * Need to zero the stuff we're not freeing, on disk. If it's a RT file
- * and we can't use unwritten extents then we actually need to ensure
- * to zero the whole extent, otherwise we just need to take of block
- * boundaries, and xfs_bunmapi will handle the rest.
- */
- if (XFS_IS_REALTIME_INODE(ip) &&
- !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
- error = xfs_adjust_extent_unmap_boundaries(ip, &startoffset_fsb,
- &endoffset_fsb);
- if (error)
- return error;
+ /* We can only free complete realtime extents. */
+ if (XFS_IS_REALTIME_INODE(ip) && mp->m_sb.sb_rextsize > 1) {
+ startoffset_fsb = roundup_64(startoffset_fsb,
+ mp->m_sb.sb_rextsize);
+ endoffset_fsb = rounddown_64(endoffset_fsb,
+ mp->m_sb.sb_rextsize);
}
+ /*
+ * Need to zero the stuff we're not freeing, on disk.
+ */
if (endoffset_fsb > startoffset_fsb) {
while (!done) {
error = xfs_unmap_extent(ip, startoffset_fsb,
@@ -1165,7 +976,8 @@
return 0;
if (offset + len > XFS_ISIZE(ip))
len = XFS_ISIZE(ip) - offset;
- error = iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
+ error = iomap_zero_range(VFS_I(ip), offset, len, NULL,
+ &xfs_buffered_write_iomap_ops);
if (error)
return error;
@@ -1183,51 +995,12 @@
return error;
}
-/*
- * Preallocate and zero a range of a file. This mechanism has the allocation
- * semantics of fallocate and in addition converts data in the range to zeroes.
- */
-int
-xfs_zero_file_space(
- struct xfs_inode *ip,
- xfs_off_t offset,
- xfs_off_t len)
-{
- struct xfs_mount *mp = ip->i_mount;
- uint blksize;
- int error;
-
- trace_xfs_zero_file_space(ip);
-
- blksize = 1 << mp->m_sb.sb_blocklog;
-
- /*
- * Punch a hole and prealloc the range. We use hole punch rather than
- * unwritten extent conversion for two reasons:
- *
- * 1.) Hole punch handles partial block zeroing for us.
- *
- * 2.) If prealloc returns ENOSPC, the file range is still zero-valued
- * by virtue of the hole punch.
- */
- error = xfs_free_file_space(ip, offset, len);
- if (error)
- goto out;
-
- error = xfs_alloc_file_space(ip, round_down(offset, blksize),
- round_up(offset + len, blksize) -
- round_down(offset, blksize),
- XFS_BMAPI_PREALLOC);
-out:
- return error;
-
-}
-
static int
xfs_prepare_shift(
struct xfs_inode *ip,
loff_t offset)
{
+ struct xfs_mount *mp = ip->i_mount;
int error;
/*
@@ -1239,6 +1012,17 @@
if (error)
return error;
}
+
+ /*
+ * Shift operations must stabilize the start block offset boundary along
+ * with the full range of the operation. If we don't, a COW writeback
+ * completion could race with an insert, front merge with the start
+ * extent (after split) during the shift and corrupt the file. Start
+ * with the block just prior to the start to stabilize the boundary.
+ */
+ offset = round_down(offset, 1 << mp->m_sb.sb_blocklog);
+ if (offset)
+ offset -= (1 << mp->m_sb.sb_blocklog);
/*
* Writeback and invalidate cache for the remainder of the file as we're
@@ -1286,7 +1070,6 @@
int error;
xfs_fileoff_t next_fsb = XFS_B_TO_FSB(mp, offset + len);
xfs_fileoff_t shift_fsb = XFS_B_TO_FSB(mp, len);
- uint resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
bool done = false;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
@@ -1302,32 +1085,34 @@
if (error)
return error;
- while (!error && !done) {
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0,
- &tp);
- if (error)
- break;
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp);
+ if (error)
+ return error;
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot,
- ip->i_gdquot, ip->i_pdquot, resblks, 0,
- XFS_QMOPT_RES_REGBLKS);
- if (error)
- goto out_trans_cancel;
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
+ while (!done) {
error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
&done);
if (error)
goto out_trans_cancel;
+ if (done)
+ break;
- error = xfs_trans_commit(tp);
+ /* finish any deferred frees and roll the transaction */
+ error = xfs_defer_finish(&tp);
+ if (error)
+ goto out_trans_cancel;
}
+ error = xfs_trans_commit(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
out_trans_cancel:
xfs_trans_cancel(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
@@ -1370,35 +1155,41 @@
if (error)
return error;
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write,
+ XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp);
+ if (error)
+ return error;
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
+
/*
* The extent shifting code works on extent granularity. So, if stop_fsb
* is not the starting block of extent, we need to split the extent at
* stop_fsb.
*/
- error = xfs_bmap_split_extent(ip, stop_fsb);
+ error = xfs_bmap_split_extent(tp, ip, stop_fsb);
if (error)
- return error;
+ goto out_trans_cancel;
- while (!error && !done) {
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0,
- &tp);
+ do {
+ error = xfs_defer_finish(&tp);
if (error)
- break;
+ goto out_trans_cancel;
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb,
&done, stop_fsb);
if (error)
goto out_trans_cancel;
+ } while (!done);
- error = xfs_trans_commit(tp);
- }
-
+ error = xfs_trans_commit(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
out_trans_cancel:
xfs_trans_cancel(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
@@ -1427,17 +1218,26 @@
struct xfs_inode *ip, /* target inode */
struct xfs_inode *tip) /* tmp inode */
{
+ struct xfs_ifork *ifp = &ip->i_df;
+ struct xfs_ifork *tifp = &tip->i_df;
+
+ /* User/group/project quota ids must match if quotas are enforced. */
+ if (XFS_IS_QUOTA_ON(ip->i_mount) &&
+ (!uid_eq(VFS_I(ip)->i_uid, VFS_I(tip)->i_uid) ||
+ !gid_eq(VFS_I(ip)->i_gid, VFS_I(tip)->i_gid) ||
+ ip->i_d.di_projid != tip->i_d.di_projid))
+ return -EINVAL;
/* Should never get a local format */
- if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
- tip->i_d.di_format == XFS_DINODE_FMT_LOCAL)
+ if (ifp->if_format == XFS_DINODE_FMT_LOCAL ||
+ tifp->if_format == XFS_DINODE_FMT_LOCAL)
return -EINVAL;
/*
* if the target inode has less extents that then temporary inode then
* why did userspace call us?
*/
- if (ip->i_d.di_nextents < tip->i_d.di_nextents)
+ if (ifp->if_nextents < tifp->if_nextents)
return -EINVAL;
/*
@@ -1452,20 +1252,18 @@
* form then we will end up with the target inode in the wrong format
* as we already know there are less extents in the temp inode.
*/
- if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
- tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
+ if (ifp->if_format == XFS_DINODE_FMT_EXTENTS &&
+ tifp->if_format == XFS_DINODE_FMT_BTREE)
return -EINVAL;
/* Check temp in extent form to max in target */
- if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
- XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) >
- XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
+ if (tifp->if_format == XFS_DINODE_FMT_EXTENTS &&
+ tifp->if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
return -EINVAL;
/* Check target in extent form to max in temp */
- if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
- XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) >
- XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
+ if (ifp->if_format == XFS_DINODE_FMT_EXTENTS &&
+ ifp->if_nextents > XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
return -EINVAL;
/*
@@ -1477,22 +1275,20 @@
* (a common defrag case) which will occur when the temp inode is in
* extent format...
*/
- if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+ if (tifp->if_format == XFS_DINODE_FMT_BTREE) {
if (XFS_IFORK_Q(ip) &&
- XFS_BMAP_BMDR_SPACE(tip->i_df.if_broot) > XFS_IFORK_BOFF(ip))
+ XFS_BMAP_BMDR_SPACE(tifp->if_broot) > XFS_IFORK_BOFF(ip))
return -EINVAL;
- if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <=
- XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
+ if (tifp->if_nextents <= XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
return -EINVAL;
}
/* Reciprocal target->temp btree format checks */
- if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
if (XFS_IFORK_Q(tip) &&
XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > XFS_IFORK_BOFF(tip))
return -EINVAL;
- if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <=
- XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
+ if (ifp->if_nextents <= XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
return -EINVAL;
}
@@ -1589,24 +1385,16 @@
trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec);
/* Remove the mapping from the donor file. */
- error = xfs_bmap_unmap_extent(tp, tip, &uirec);
- if (error)
- goto out;
+ xfs_bmap_unmap_extent(tp, tip, &uirec);
/* Remove the mapping from the source file. */
- error = xfs_bmap_unmap_extent(tp, ip, &irec);
- if (error)
- goto out;
+ xfs_bmap_unmap_extent(tp, ip, &irec);
/* Map the donor file's blocks into the source file. */
- error = xfs_bmap_map_extent(tp, ip, &uirec);
- if (error)
- goto out;
+ xfs_bmap_map_extent(tp, ip, &uirec);
/* Map the source file's blocks into the donor file. */
- error = xfs_bmap_map_extent(tp, tip, &irec);
- if (error)
- goto out;
+ xfs_bmap_map_extent(tp, tip, &irec);
error = xfs_defer_finish(tpp);
tp = *tpp;
@@ -1652,15 +1440,15 @@
/*
* Count the number of extended attribute blocks
*/
- if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
- (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
+ if (XFS_IFORK_Q(ip) && ip->i_afp->if_nextents > 0 &&
+ ip->i_afp->if_format != XFS_DINODE_FMT_LOCAL) {
error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &junk,
&aforkblks);
if (error)
return error;
}
- if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
- (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
+ if (XFS_IFORK_Q(tip) && tip->i_afp->if_nextents > 0 &&
+ tip->i_afp->if_format != XFS_DINODE_FMT_LOCAL) {
error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK, &junk,
&taforkblks);
if (error)
@@ -1674,12 +1462,12 @@
* event of a crash. Set the owner change log flags now and leave the
* bmbt scan as the last step.
*/
- if (ip->i_d.di_version == 3 &&
- ip->i_d.di_format == XFS_DINODE_FMT_BTREE)
- (*target_log_flags) |= XFS_ILOG_DOWNER;
- if (tip->i_d.di_version == 3 &&
- tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
- (*src_log_flags) |= XFS_ILOG_DOWNER;
+ if (xfs_sb_version_has_v3inode(&ip->i_mount->m_sb)) {
+ if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE)
+ (*target_log_flags) |= XFS_ILOG_DOWNER;
+ if (tip->i_df.if_format == XFS_DINODE_FMT_BTREE)
+ (*src_log_flags) |= XFS_ILOG_DOWNER;
+ }
/*
* Swap the data forks of the inodes
@@ -1692,9 +1480,6 @@
tmp = (uint64_t)ip->i_d.di_nblocks;
ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
-
- swap(ip->i_d.di_nextents, tip->i_d.di_nextents);
- swap(ip->i_d.di_format, tip->i_d.di_format);
/*
* The extents in the source inode could still contain speculative
@@ -1709,24 +1494,24 @@
tip->i_delayed_blks = ip->i_delayed_blks;
ip->i_delayed_blks = 0;
- switch (ip->i_d.di_format) {
+ switch (ip->i_df.if_format) {
case XFS_DINODE_FMT_EXTENTS:
(*src_log_flags) |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
- ASSERT(ip->i_d.di_version < 3 ||
+ ASSERT(!xfs_sb_version_has_v3inode(&ip->i_mount->m_sb) ||
(*src_log_flags & XFS_ILOG_DOWNER));
(*src_log_flags) |= XFS_ILOG_DBROOT;
break;
}
- switch (tip->i_d.di_format) {
+ switch (tip->i_df.if_format) {
case XFS_DINODE_FMT_EXTENTS:
(*target_log_flags) |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
(*target_log_flags) |= XFS_ILOG_DBROOT;
- ASSERT(tip->i_d.di_version < 3 ||
+ ASSERT(!xfs_sb_version_has_v3inode(&ip->i_mount->m_sb) ||
(*target_log_flags & XFS_ILOG_DOWNER));
break;
}
@@ -1790,6 +1575,7 @@
int lock_flags;
uint64_t f;
int resblks = 0;
+ unsigned int flags = 0;
/*
* Lock the inodes against other IO, page faults and truncate to
@@ -1813,6 +1599,14 @@
goto out_unlock;
}
+ error = xfs_qm_dqattach(ip);
+ if (error)
+ goto out_unlock;
+
+ error = xfs_qm_dqattach(tip);
+ if (error)
+ goto out_unlock;
+
error = xfs_swap_extent_flush(ip);
if (error)
goto out_unlock;
@@ -1832,9 +1626,9 @@
* performed with log redo items!
*/
if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
- int w = XFS_DATA_FORK;
- uint32_t ipnext = XFS_IFORK_NEXTENTS(ip, w);
- uint32_t tipnext = XFS_IFORK_NEXTENTS(tip, w);
+ int w = XFS_DATA_FORK;
+ uint32_t ipnext = ip->i_df.if_nextents;
+ uint32_t tipnext = tip->i_df.if_nextents;
/*
* Conceptually this shouldn't affect the shape of either bmbt,
@@ -1845,17 +1639,16 @@
resblks += XFS_SWAP_RMAP_SPACE_RES(mp, tipnext, w);
/*
- * Handle the corner case where either inode might straddle the
- * btree format boundary. If so, the inode could bounce between
- * btree <-> extent format on unmap -> remap cycles, freeing and
- * allocating a bmapbt block each time.
+ * If either inode straddles a bmapbt block allocation boundary,
+ * the rmapbt algorithm triggers repeated allocs and frees as
+ * extents are remapped. This can exhaust the block reservation
+ * prematurely and cause shutdown. Return freed blocks to the
+ * transaction reservation to counter this behavior.
*/
- if (ipnext == (XFS_IFORK_MAXEXT(ip, w) + 1))
- resblks += XFS_IFORK_MAXEXT(ip, w);
- if (tipnext == (XFS_IFORK_MAXEXT(tip, w) + 1))
- resblks += XFS_IFORK_MAXEXT(tip, w);
+ flags |= XFS_TRANS_RES_FDBLKS;
}
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, flags,
+ &tp);
if (error)
goto out_unlock;
@@ -1934,10 +1727,11 @@
/* Swap the cow forks. */
if (xfs_sb_version_hasreflink(&mp->m_sb)) {
- ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS);
- ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+ ASSERT(!ip->i_cowfp ||
+ ip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS);
+ ASSERT(!tip->i_cowfp ||
+ tip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS);
- swap(ip->i_cnextents, tip->i_cnextents);
swap(ip->i_cowfp, tip->i_cowfp);
if (ip->i_cowfp && ip->i_cowfp->if_bytes)
--
Gitblit v1.6.2