// SPDX-License-Identifier: GPL-2.0 /* * Copyright ( c ) 2000 - 2006 Silicon Graphics , Inc . * Copyright ( c ) 2012 Red Hat , Inc . * All Rights Reserved . #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_trans.h" #include "xfs_alloc.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" #include "xfs_bmap_btree.h" #include "xfs_rtalloc.h" #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_trans_space.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_iomap.h" #include "xfs_reflink.h" #include "xfs_rtbitmap.h" #include "xfs_rtgroup.h" #include "xfs_zone_alloc.h" /* Kernel only BMAP related definitions and functions */ /* * Convert the given file system block to a disk block . We have to treat it * differently based on whether the file is a real time file or not , because the * bmap code does . struct xfs_inode *ip, xfs_fsblock_t fsb)if (XFS_IS_REALTIME_INODE(ip))return xfs_rtb_to_daddr(ip->i_mount, fsb);return XFS_FSB_TO_DADDR(ip->i_mount, fsb);/* * Routine to zero an extent on disk allocated to the specific inode . int struct xfs_inode *ip,return blkdev_issue_zeroout(xfs_inode_buftarg(ip)->bt_bdev,0 );/* * Extent tree block counting routines . /* * Count leaf blocks given a range of extent records . Delayed allocation * extents are not counted towards the totals . struct xfs_ifork *ifp,struct xfs_iext_cursor icur;struct xfs_bmbt_irec got;0 ;if (!isnullstartblock(got.br_startblock)) {return numrecs;/* * Count fsblocks of the given fork . Delayed allocation extents are * not counted towards the totals . int struct xfs_trans *tp,struct xfs_inode *ip,int whichfork,struct xfs_mount *mp = ip->i_mount;struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);struct xfs_btree_cur *cur;0 ;int error;0 ;0 ;if (!ifp)return 0 ;switch (ifp->if_format) {case XFS_DINODE_FMT_BTREE:if (error)return error;if (error)return error;/* * 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 . 1 ;case XFS_DINODE_FMT_EXTENTS:break ;return 0 ;static int struct xfs_inode *ip,struct getbmapx *bmv,struct kgetbmap *out,struct xfs_bmbt_irec *got)struct kgetbmap *p = out + bmv->bmv_entries;bool shared = false ;int error;if (error)return error;if (isnullstartblock(got->br_startblock) ||/* * Take the flush completion as being a point - in - time snapshot * where there are no delalloc extents , and if any new ones * have been created racily , just skip them as being ' after ' * the flush and so don ' t get reported . if (!(bmv->bmv_iflags & BMV_IF_DELALLOC))return 0 ;2 ;else {if (got->br_state == XFS_EXT_UNWRITTEN &&if (shared)0 LL, bmv_end - bmv->bmv_offset);return 0 ;static void struct xfs_inode *ip,struct getbmapx *bmv,struct kgetbmap *out,struct kgetbmap *p = out + bmv->bmv_entries;if (bmv->bmv_iflags & BMV_IF_NO_HOLES)return ;1 ;0 LL, bmv_end - bmv->bmv_offset);static inline bool struct getbmapx *bmv)return bmv->bmv_length == 0 || bmv->bmv_entries >= bmv->bmv_count - 1 ;static bool struct xfs_bmbt_irec *rec,if (end == total_end)return false ;if (!isnullstartblock(rec->br_startblock) &&return true ;/* * Get inode ' s extents as described in bmv , and format for output . * Calls formatter to fill the user ' s buffer until all extents * are mapped , until the passed - in bmv - > bmv_count slots have * been filled , or until the formatter short - circuits the loop , * if it is tracking filled - in extents on its own . int /* error code */ struct xfs_inode *ip,struct getbmapx *bmv, /* user bmap structure */ struct kgetbmap *out)struct xfs_mount *mp = ip->i_mount;int iflags = bmv->bmv_iflags;int whichfork, lock, error = 0 ;struct xfs_ifork *ifp;struct xfs_bmbt_irec got, rec;struct xfs_iext_cursor icur;if (bmv->bmv_iflags & ~BMV_IF_VALID)return -EINVAL;#ifndef DEBUG/* Only allow CoW fork queries if we're debugging. */ if (iflags & BMV_IF_COWFORK)return -EINVAL;#endif if ((iflags & BMV_IF_ATTRFORK) && (iflags & BMV_IF_COWFORK))return -EINVAL;if (bmv->bmv_length < -1 )return -EINVAL;0 ;if (bmv->bmv_length == 0 )return 0 ;if (iflags & BMV_IF_ATTRFORK)else if (iflags & BMV_IF_COWFORK)else switch (whichfork) {case XFS_ATTR_FORK:if (!xfs_inode_has_attr_fork(ip))goto out_unlock_ilock;1 LL << 32 ;break ;case XFS_COW_FORK:/* No CoW fork? Just return */ if (!xfs_ifork_ptr(ip, whichfork))goto out_unlock_ilock;if (xfs_get_cowextsz_hint(ip))else break ;case XFS_DATA_FORK:if (!(iflags & BMV_IF_DELALLOC) &&if (error)goto out_unlock_iolock;/* * Even after flushing the inode , there can still be * delalloc blocks on the inode beyond EOF due to * speculative preallocation . These are not removed * until the release function is called or the inode * is inactivated . Hence we cannot assert here that * ip - > i_delayed_blks = = 0 . if (xfs_get_extsz_hint(ip) ||else break ;switch (ifp->if_format) {case XFS_DINODE_FMT_EXTENTS:case XFS_DINODE_FMT_BTREE:break ;case XFS_DINODE_FMT_LOCAL:/* Local format inode forks report no extents. */ goto out_unlock_ilock;default :goto out_unlock_ilock;if (bmv->bmv_length == -1 ) {0 LL, max_len - bmv->bmv_offset);if (error)goto out_unlock_ilock;if (!xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got)) {/* * Report a whole - file hole if the delalloc flag is set to * stay compatible with the old implementation . if (iflags & BMV_IF_DELALLOC)goto out_unlock_ilock;while (!xfs_getbmap_full(bmv)) {/* * Report an entry for a hole if this extent doesn ' t directly * follow the previous one . if (got.br_startoff > bno) {if (xfs_getbmap_full(bmv))break ;/* * In order to report shared extents accurately , we report each * distinct shared / unshared part of a single bmbt record with * an individual getbmapx record . do {if (error || xfs_getbmap_full(bmv))goto out_unlock_ilock;while (xfs_getbmap_next_rec(&rec, bno));if (!xfs_iext_next_extent(ifp, &icur, &got)) {if (bmv->bmv_entries > 0 )1 ].bmv_oflags |=if (whichfork != XFS_ATTR_FORK && bno < end &&break ;if (bno >= first_bno + len)break ;return error;/* * Dead simple method of punching delalyed allocation blocks from a range in * the inode . This will always punch out both the start and end blocks , even * if the ranges only partially overlap them , so it is up to the caller to * ensure that partial blocks are not passed in . void struct xfs_inode *ip,int whichfork,struct xfs_zone_alloc_ctx *ac)struct xfs_mount *mp = ip->i_mount;struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);struct xfs_bmbt_irec got, del;struct xfs_iext_cursor icur;if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))goto out_unlock;while (got.br_startoff + got.br_blockcount > start_fsb) {/* * A delete can push the cursor forward . Step back to the * previous extent on non - delalloc or extents outside the * target range . if (!del.br_blockcount ||if (!xfs_iext_prev_extent(ifp, &icur, &got))break ;continue ;if (xfs_is_zoned_inode(ip) && ac) {/* * In a zoned buffered write context we need to return * the punched delalloc allocations to the allocation * context . This allows reusing them in the following * iomap iterations . else {0 );if (!xfs_iext_get_extent(ifp, &icur, &got))break ;if (whichfork == XFS_COW_FORK && !ifp->if_bytes)/* * Test whether it is appropriate to check an inode for and free post EOF * blocks . bool struct xfs_inode *ip)struct xfs_mount *mp = ip->i_mount;bool found_blocks = false ;struct xfs_bmbt_irec imap;struct xfs_iext_cursor icur;/* * Caller must either hold the exclusive io lock ; or be inactivating * the inode , which guarantees there are no other users of the inode . if (!(VFS_I(ip)->i_state & I_FREEING))/* prealloc/delalloc exists only on regular files */ if (!S_ISREG(VFS_I(ip)->i_mode))return false ;/* * Zero sized files with no cached pages and delalloc blocks will not * have speculative prealloc / delalloc blocks to remove . if (VFS_I(ip)->i_size == 0 &&0 &&0 )return false ;/* If we haven't read in the extent list, then don't do it now. */ if (xfs_need_iread_extents(&ip->i_df))return false ;/* * Do not free real extents in preallocated files unless the file has * delalloc blocks and we are forced to remove them . if ((ip->i_diflags & XFS_DIFLAG_PREALLOC) && !ip->i_delayed_blks)return false ;/* * Do not try to free post - EOF blocks if EOF is beyond the end of the * range supported by the page cache , because the truncation will loop * forever . if (xfs_inode_has_bigrtalloc(ip))if (last_fsb <= end_fsb)return false ;/* * Check if there is an post - EOF extent to free . If there are any * delalloc blocks attached to the inode ( data fork delalloc * reservations or CoW extents of any kind ) , we need to free them so * that inactivation doesn ' t fail to erase them . if (ip->i_delayed_blks ||true ;return found_blocks;/* * This is called to free any blocks beyond eof . The caller must hold * IOLOCK_EXCL unless we are in the inode reclaim path and have the only * reference to the inode . int struct xfs_inode *ip)struct xfs_trans *tp;struct xfs_mount *mp = ip->i_mount;int error;/* Attach the dquots to the inode up front. */ if (error)return error;/* Wait on dio to ensure i_size has settled. */ /* * For preallocated files only free delayed allocations . * * Note that this means we also leave speculative preallocations in * place for preallocated files . if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) {if (ip->i_delayed_blks) {return 0 ;0 , 0 , 0 , &tp);if (error) {return error;0 );/* * Do not update the on - disk file size . If we update the on - disk file * size and then the system crashes before the contents of the file are * flushed to disk then the files may be full of holes ( ie NULL files * bug ) . if (error)goto err_cancel;if (error)goto out_unlock;goto out_unlock;/* * If we get an error at this point we simply don ' t * bother truncating the file . return error;int struct xfs_inode *ip,int rt;1 ], *imapp;int error;if (xfs_is_always_cow_inode(ip))return 0 ;if (xfs_is_shutdown(mp))return -EIO;if (error)return error;if (len <= 0 )return -EINVAL;0 ];/* * Allocate file space until done or until there is an error while (allocatesize_fsb && !error) {unsigned int dblocks, rblocks, resblks;int nimaps = 1 ;/* * Determine space reservations for data / realtime . if (unlikely(extsz)) {if (temp)if (temp)else {0 ;/* * The transaction reservation is limited to a 32 - bit block * count , hence we need to limit the number of blocks we are * trying to reserve to avoid an overflow . We can ' t allocate * more than @ nimaps extents , and an extent is limited on disk * to XFS_BMBT_MAX_EXTLEN ( 21 bits ) , so use that to enforce the * limit . if (unlikely(rt)) {0 );else {0 ;false , &tp);if (error)break ;if (error)goto error;/* * If the allocator cannot find a single free extent large * enough to cover the start block of the requested range , * xfs_bmapi_write will return - ENOSR . * * In that case we simply need to keep looping with the same * startoffset_fsb so that one of the following allocations * will eventually reach the requested range . 0 , imapp,if (error) {if (error != -ENOSR)goto error;0 ;else {return error;return error;static int struct xfs_inode *ip,int *done)struct xfs_mount *mp = ip->i_mount;struct xfs_trans *tp;0 );int error;0 ,false , &tp);if (error)return error;if (error)goto out_trans_cancel;0 , 2 , done);if (error)goto out_trans_cancel;return error;goto out_unlock;/* Caller must first wait for the completion of any pending DIOs if required. */ int struct xfs_inode *ip,struct inode *inode = VFS_I(ip);int error;/* * Make sure we extend the flush out to extent alignment * boundaries so any extent range overlapping the start / end * of the modification we are about to do is clean and idle . 1 ;if (error)return error;return 0 ;int struct xfs_inode *ip,struct xfs_zone_alloc_ctx *ac)struct xfs_mount *mp = ip->i_mount;int done = 0 , error;if (error)return error;if (len <= 0 ) /* if nothing being freed */ return 0 ;/* * Now AIO and DIO has drained we flush and ( if necessary ) invalidate * the cached range over the first operation we are about to run . if (error)return error;/* We can only free complete realtime extents. */ if (xfs_inode_has_bigrtalloc(ip)) {/* * Need to zero the stuff we ' re not freeing , on disk . if (endoffset_fsb > startoffset_fsb) {while (!done) {if (error)return error;/* * Now that we ' ve unmap all full blocks we ' ll have to zero out any * partial block at the beginning and / or end . xfs_zero_range is smart * enough to skip any holes , including those we just created , but we * must take care not to zero beyond EOF and enlarge i_size . if (offset >= XFS_ISIZE(ip))return 0 ;if (offset + len > XFS_ISIZE(ip))if (error)return error;/* * If we zeroed right up to EOF and EOF straddles a page boundary we * must make sure that the post - EOF area is also zeroed because the * page could be mmap ' d and xfs_zero_range doesn ' t do that for us . * Writeback of the eof page will do this , albeit clumsily . if (offset + len >= XFS_ISIZE(ip) && offset_in_page(offset + len) > 0 ) {return error;static int struct xfs_inode *ip,unsigned int rounding;int error;/* * Trim eofblocks to avoid shifting uninitialized post - eof preallocation * into the accessible region of the file . if (xfs_can_free_eofblocks(ip)) {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 allocation unit just prior to the start to stabilize the * boundary . if (offset)/* * Writeback and invalidate cache for the remainder of the file as we ' re * about to shift down every extent from offset to EOF . if (error)return error;/* * Clean out anything hanging around in the cow fork now that * we ' ve flushed all the dirty data out to disk to avoid having * CoW extents at the wrong offsets . if (xfs_inode_has_cow_data(ip)) {true );if (error)return error;return 0 ;/* * xfs_collapse_file_space ( ) * This routine frees disk space and shift extent for the given file . * The first thing we do is to free data blocks in the specified range * by calling xfs_free_file_space ( ) . It would also sync dirty data * and invalidate page cache over the region on which collapse range * is working . And Shift extent records to the left to cover a hole . * RETURNS : * 0 on success * errno on error * int struct xfs_inode *ip,struct xfs_zone_alloc_ctx *ac)struct xfs_mount *mp = ip->i_mount;struct xfs_trans *tp;int error;bool done = false ;if (error)return error;if (error)return error;0 , 0 , 0 , &tp);if (error)return error;0 );while (!done) {if (error)goto out_trans_cancel;if (done)break ;/* finish any deferred frees and roll the transaction */ if (error)goto out_trans_cancel;return error;return error;/* * xfs_insert_file_space ( ) * This routine create hole space by shifting extents for the given file . * The first thing we do is to sync dirty data and invalidate page cache * over the region on which insert range is working . And split an extent * to two extents at given offset by calling xfs_bmap_split_extent . * And shift all extent records which are laying between [ offset , * last allocated extent ] to the right to reserve hole range . * RETURNS : * 0 on success * errno on error int struct xfs_inode *ip,struct xfs_mount *mp = ip->i_mount;struct xfs_trans *tp;int error;bool done = false ;if (error)return error;if (error)return error;0 ), 0 , 0 , &tp);if (error)return error;0 );if (error)goto out_trans_cancel;/* * 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 . if (error)goto out_trans_cancel;do {if (error)goto out_trans_cancel;if (error)goto out_trans_cancel;while (!done);return error;return error;/* * We need to check that the format of the data fork in the temporary inode is * valid for the target inode before doing the swap . This is not a problem with * attr1 because of the fixed fork offset , but attr2 has a dynamically sized * data fork depending on the space the attribute fork is taking so we can get * invalid formats on the target inode . * * E . g . target has space for 7 extents in extent format , temp inode only has * space for 6 . If we defragment down to 7 extents , then the tmp format is a * btree , but when swapped it needs to be in extent format . Hence we can ' t just * blindly swap data forks on attr2 filesystems . * * Note that we check the swap in both directions so that we don ' t end up with * a corrupt temporary inode , either . * * Note that fixing the way xfs_fsr sets up the attribute fork in the source * inode will prevent this situation from occurring , so all we do here is * reject and log the attempt . basically we are putting the responsibility on * userspace to get this right . static int 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) &&return -EINVAL;/* Should never get a local format */ if (ifp->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 (ifp->if_nextents < tifp->if_nextents)return -EINVAL;/* * If we have to use the ( expensive ) rmap swap method , we can * handle any number of extents and any format . if (xfs_has_rmapbt(ip->i_mount))return 0 ;/* * if the target inode is in extent form and the temp inode is in btree * 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 (ifp->if_format == XFS_DINODE_FMT_EXTENTS &&return -EINVAL;/* Check temp in extent form to max in target */ if (tifp->if_format == XFS_DINODE_FMT_EXTENTS &&return -EINVAL;/* Check target in extent form to max in temp */ if (ifp->if_format == XFS_DINODE_FMT_EXTENTS &&return -EINVAL;/* * If we are in a btree format , check that the temp root block will fit * in the target and that it has enough extents to be in btree format * in the target . * * Note that we have to be careful to allow btree - > extent conversions * ( a common defrag case ) which will occur when the temp inode is in * extent format . . . if (tifp->if_format == XFS_DINODE_FMT_BTREE) {if (xfs_inode_has_attr_fork(ip) &&return -EINVAL;if (tifp->if_nextents <= XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))return -EINVAL;/* Reciprocal target->temp btree format checks */ if (ifp->if_format == XFS_DINODE_FMT_BTREE) {if (xfs_inode_has_attr_fork(tip) &&return -EINVAL;if (ifp->if_nextents <= XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))return -EINVAL;return 0 ;static int struct xfs_inode *ip)int error;if (error)return error;0 , -1 );/* Verify O_DIRECT for ftmp */ if (VFS_I(ip)->i_mapping->nrpages)return -EINVAL;return 0 ;/* * Move extents from one file to another , when rmap is enabled . STATIC int struct xfs_trans **tpp,struct xfs_inode *ip,struct xfs_inode *tip)struct xfs_trans *tp = *tpp;struct xfs_bmbt_irec irec;struct xfs_bmbt_irec uirec;struct xfs_bmbt_irec tirec;int error;int nimaps;/* * If the source file has shared blocks , we must flag the donor * file as having shared blocks so that we get the shared - block * rmap functions when we go to fix up the rmaps . The flags * will be switch for reals later . if (ip->i_diflags2 & XFS_DIFLAG2_REFLINK)0 ;while (count_fsb) {/* Read extent from the donor file */ 1 ;0 );if (error)goto out;1 );/* Unmap the old blocks in the source file. */ while (tirec.br_blockcount) {/* Read extent from the source file */ 1 ;0 );if (error)goto out;1 );/* Trim the extent. */ if (xfs_bmap_is_real_extent(&uirec)) {if (error)goto out;if (xfs_bmap_is_real_extent(&irec)) {if (error)goto out;/* Remove the mapping from the donor file. */ /* Remove the mapping from the source file. */ /* Map the donor file's blocks into the source file. */ /* Map the source file's blocks into the donor file. */ if (error)goto out;if (tirec.br_startblock != HOLESTARTBLOCK &&/* Roll on... */ return 0 ;return error;/* Swap the extents of two files by swapping data forks. */ STATIC int struct xfs_trans *tp,struct xfs_inode *ip,struct xfs_inode *tip,int *src_log_flags,int *target_log_flags)0 ;0 ;int error;/* * Count the number of extended attribute blocks if (xfs_inode_has_attr_fork(ip) && ip->i_af.if_nextents > 0 &&if (error)return error;if (xfs_inode_has_attr_fork(tip) && tip->i_af.if_nextents > 0 &&if (error)return error;/* * Btree format ( v3 ) inodes have the inode number stamped in the bmbt * block headers . We can ' t start changing the bmbt blocks until the * inode owner change is logged so recovery does the right thing in the * event of a crash . Set the owner change log flags now and leave the * bmbt scan as the last step . if (xfs_has_v3inodes(ip->i_mount)) {if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE)if (tip->i_df.if_format == XFS_DINODE_FMT_BTREE)/* * Swap the data forks of the inodes /* * Fix the on - disk inode values /* * The extents in the source inode could still contain speculative * preallocation beyond EOF ( e . g . the file is open but not modified * while defrag is in progress ) . In that case , we need to copy over the * number of delalloc blocks the data fork in the source inode is * tracking beyond EOF so that when the fork is truncated away when the * temporary inode is unlinked we don ' t underrun the i_delayed_blks * counter on that inode . 0 );0 ;switch (ip->i_df.if_format) {case XFS_DINODE_FMT_EXTENTS:break ;case XFS_DINODE_FMT_BTREE:break ;switch (tip->i_df.if_format) {case XFS_DINODE_FMT_EXTENTS:break ;case XFS_DINODE_FMT_BTREE:break ;return 0 ;/* * Fix up the owners of the bmbt blocks to refer to the current inode . The * change owner scan attempts to order all modified buffers in the current * transaction . In the event of ordered buffer failure , the offending buffer is * physically logged as a fallback and the scan returns - EAGAIN . We must roll * the transaction in this case to replenish the fallback log reservation and * restart the scan . This process repeats until the scan completes . static int struct xfs_trans **tpp,struct xfs_inode *ip,struct xfs_inode *tmpip)int error;struct xfs_trans *tp = *tpp;do {/* success or fatal error */ if (error != -EAGAIN)break ;if (error)break ;/* * Redirty both inodes so they can relog and keep the log tail * moving forward . 0 );0 );while (true );return error;int struct xfs_inode *ip, /* target inode */ struct xfs_inode *tip, /* tmp inode */ struct xfs_swapext *sxp)struct xfs_mount *mp = ip->i_mount;struct xfs_trans *tp;struct xfs_bstat *sbp = &sxp->sx_stat;int src_log_flags, target_log_flags;int error = 0 ;int resblks = 0 ;unsigned int flags = 0 ;struct timespec64 ctime, mtime;/* * Lock the inodes against other IO , page faults and truncate to * begin with . Then we can ensure the inodes are flushed and have no * page cache safely . Once we have done this we can take the ilocks and * do the rest of the checks . /* Verify that both files have the same format */ if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) {goto out_unlock;/* Verify both files are either real-time or non-realtime */ if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {goto out_unlock;/* * The rmapbt implementation is unable to resume a swapext operation * after a crash if the allocation unit size is larger than a block . * This ( deprecated ) interface will not be upgraded to handle this * situation . Defragmentation must be performed with the commit range * ioctl . if (XFS_IS_REALTIME_INODE(ip) && xfs_has_rtgroups(ip->i_mount)) {goto out_unlock;if (error)goto out_unlock;if (error)goto out_unlock;if (error)goto out_unlock;if (error)goto out_unlock;if (xfs_inode_has_cow_data(tip)) {0 , NULLFILEOFF, true );if (error)goto out_unlock;/* * Extent " swapping " with rmap requires a permanent reservation and * a block reservation because it ' s really just a remap operation * performed with log redo items ! if (xfs_has_rmapbt(mp)) {int w = XFS_DATA_FORK;/* * Conceptually this shouldn ' t affect the shape of either bmbt , * but since we atomically move extents one by one , we reserve * enough space to rebuild both trees . /* * 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 . 0 , flags,if (error)goto out_unlock;/* * Lock and join the inodes to the tansaction so that transaction commit * or cancel will unlock the inodes from this point onwards . 0 );0 );/* Verify all data are being swapped */ if (sxp->sx_offset != 0 ||goto out_trans_cancel;0 );1 );/* check inode formats now that data is flushed */ if (error) {"%s: inode 0x%llx format is incompatible for exchanging." ,goto out_trans_cancel;/* * Compare the current change & modify times with that * passed in . If they differ , we abort this swap . * This is the mechanism used to ensure the calling * process that the file was not changed out from * under it . if ((sbp->bs_ctime.tv_sec != ctime.tv_sec) ||goto out_trans_cancel;/* * Note the trickiness in setting the log flags - we set the owner log * flag on the opposite inode ( i . e . the inode we are setting the new * owner to be ) because once we swap the forks and log that , log * recovery is going to see the fork as owned by the swapped inode , * not the pre - swapped inodes . if (xfs_has_rmapbt(mp))else if (error)goto out_trans_cancel;/* Do we have to swap reflink flags? */ if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^/* Swap the cow forks. */ if (xfs_has_reflink(mp)) {if (ip->i_cowfp && ip->i_cowfp->if_bytes)else if (tip->i_cowfp && tip->i_cowfp->if_bytes)else /* * The extent forks have been swapped , but crc = 1 , rmapbt = 0 filesystems * have inode number owner values in the bmbt blocks that still refer to * the old inode . Scan each bmbt to fix up the owner values with the * inode number of the current inode . if (src_log_flags & XFS_ILOG_DOWNER) {if (error)goto out_trans_cancel;if (target_log_flags & XFS_ILOG_DOWNER) {if (error)goto out_trans_cancel;/* * If this is a synchronous mount , make sure that the * transaction goes to disk before returning to the user . if (xfs_has_wsync(mp))0 );1 );return error;goto out_unlock_ilock;
Messung V0.5 in Prozent C=95 H=79 G=87
¤ Dauer der Verarbeitung: 0.44 Sekunden
(vorverarbeitet am 2026-09-28)
¤ *© Formatika GbR, Deutschland
