diff options
Diffstat (limited to 'fs/xfs/xfs_bmap.c')
| -rw-r--r-- | fs/xfs/xfs_bmap.c | 1233 |
1 files changed, 346 insertions, 887 deletions
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 05c698ccb23..75c3fe5f3d9 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -17,38 +17,37 @@ */ #include "xfs.h" #include "xfs_fs.h" -#include "xfs_types.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_log.h" #include "xfs_inum.h" -#include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" -#include "xfs_dir2.h" #include "xfs_mount.h" +#include "xfs_da_format.h" #include "xfs_da_btree.h" -#include "xfs_bmap_btree.h" -#include "xfs_alloc_btree.h" -#include "xfs_ialloc_btree.h" -#include "xfs_dinode.h" +#include "xfs_dir2.h" #include "xfs_inode.h" #include "xfs_btree.h" -#include "xfs_mount.h" -#include "xfs_itable.h" +#include "xfs_trans.h" #include "xfs_inode_item.h" #include "xfs_extfree_item.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_attr_leaf.h" #include "xfs_quota.h" #include "xfs_trans_space.h" #include "xfs_buf_item.h" -#include "xfs_filestream.h" -#include "xfs_vnodeops.h" #include "xfs_trace.h" #include "xfs_symlink.h" +#include "xfs_attr_leaf.h" +#include "xfs_dinode.h" +#include "xfs_filestream.h" kmem_zone_t *xfs_bmap_free_item_zone; @@ -95,7 +94,7 @@ xfs_bmap_compute_maxlevels( maxleafents = MAXAEXTNUM; sz = XFS_BMDR_SPACE_CALC(MINABTPTRS); } - maxrootrecs = xfs_bmdr_maxrecs(mp, sz, 0); + maxrootrecs = xfs_bmdr_maxrecs(sz, 0); minleafrecs = mp->m_bmap_dmnr[0]; minnoderecs = mp->m_bmap_dmnr[1]; maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs; @@ -108,19 +107,6 @@ xfs_bmap_compute_maxlevels( mp->m_bm_maxlevels[whichfork] = level; } -/* - * 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. - */ -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))); -} - STATIC int /* error */ xfs_bmbt_lookup_eq( struct xfs_btree_cur *cur, @@ -247,7 +233,6 @@ xfs_default_attroffset( */ STATIC void xfs_bmap_forkoff_reset( - xfs_mount_t *mp, xfs_inode_t *ip, int whichfork) { @@ -263,173 +248,6 @@ xfs_bmap_forkoff_reset( } /* - * Extent tree block counting routines. - */ - -/* - * Count leaf blocks given a range of extent records. - */ -STATIC void -xfs_bmap_count_leaves( - xfs_ifork_t *ifp, - xfs_extnum_t idx, - int numrecs, - int *count) -{ - int b; - - for (b = 0; b < numrecs; b++) { - xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, idx + b); - *count += xfs_bmbt_get_blockcount(frp); - } -} - -/* - * 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, - int *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 is use. - */ -STATIC int /* error */ -xfs_bmap_count_tree( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_ifork_t *ifp, /* inode fork pointer */ - xfs_fsblock_t blockno, /* file system block number */ - int levelin, /* level in btree */ - int *count) /* Count of blocks */ -{ - int error; - xfs_buf_t *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); - if (unlikely((error = - xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) { - xfs_trans_brelse(tp, bp); - XFS_ERROR_REPORT("xfs_bmap_count_tree(1)", - XFS_ERRLEVEL_LOW, mp); - return XFS_ERROR(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); - 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. - */ -int /* error */ -xfs_bmap_count_blocks( - xfs_trans_t *tp, /* transaction pointer */ - xfs_inode_t *ip, /* incore inode */ - int whichfork, /* data or attr fork */ - int *count) /* out: count of blocks */ -{ - struct xfs_btree_block *block; /* current btree block */ - xfs_fsblock_t bno; /* block # of "block" */ - xfs_ifork_t *ifp; /* fork structure */ - int level; /* btree level, for checking */ - xfs_mount_t *mp; /* file system mount structure */ - __be64 *pp; /* pointer to block address */ - - bno = NULLFSBLOCK; - mp = ip->i_mount; - ifp = XFS_IFORK_PTR(ip, whichfork); - if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) { - xfs_bmap_count_leaves(ifp, 0, - ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t), - count); - return 0; - } - - /* - * 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 != NULLDFSBNO); - ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount); - ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks); - - if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) { - XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW, - mp); - return XFS_ERROR(EFSCORRUPTED); - } - - return 0; -} - -/* * Debug/sanity checking code */ @@ -724,8 +542,8 @@ xfs_bmap_trace_exlist( /* * Validate that the bmbt_irecs being returned from bmapi are valid - * given the callers original parameters. Specifically check the - * ranges of the returned irecs to ensure that they only extent beyond + * given the caller's original parameters. Specifically check the + * ranges of the returned irecs to ensure that they only extend beyond * the given parameters if the XFS_BMAPI_ENTIRE flag was set. */ STATIC void @@ -823,7 +641,7 @@ xfs_bmap_add_free( * Remove the entry "free" from the free item list. Prev points to the * previous entry, unless "free" is the head of the list. */ -STATIC void +void xfs_bmap_del_free( xfs_bmap_free_t *flist, /* free item list header */ xfs_bmap_free_item_t *prev, /* previous item on list, if any */ @@ -837,92 +655,6 @@ xfs_bmap_del_free( kmem_zone_free(xfs_bmap_free_item_zone, free); } - -/* - * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi - * caller. Frees all the extents that need freeing, which must be done - * last due to locking considerations. We never free any extents in - * the first transaction. - * - * Return 1 if the given transaction was committed and a new one - * started, and 0 otherwise in the committed parameter. - */ -int /* error */ -xfs_bmap_finish( - xfs_trans_t **tp, /* transaction pointer addr */ - xfs_bmap_free_t *flist, /* i/o: list extents to free */ - int *committed) /* xact committed or not */ -{ - xfs_efd_log_item_t *efd; /* extent free data */ - xfs_efi_log_item_t *efi; /* extent free intention */ - int error; /* error return value */ - xfs_bmap_free_item_t *free; /* free extent item */ - unsigned int logres; /* new log reservation */ - unsigned int logcount; /* new log count */ - xfs_mount_t *mp; /* filesystem mount structure */ - xfs_bmap_free_item_t *next; /* next item on free list */ - xfs_trans_t *ntp; /* new transaction pointer */ - - ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES); - if (flist->xbf_count == 0) { - *committed = 0; - return 0; - } - ntp = *tp; - efi = xfs_trans_get_efi(ntp, flist->xbf_count); - for (free = flist->xbf_first; free; free = free->xbfi_next) - xfs_trans_log_efi_extent(ntp, efi, free->xbfi_startblock, - free->xbfi_blockcount); - logres = ntp->t_log_res; - logcount = ntp->t_log_count; - ntp = xfs_trans_dup(*tp); - error = xfs_trans_commit(*tp, 0); - *tp = ntp; - *committed = 1; - /* - * We have a new transaction, so we should return committed=1, - * even though we're returning an error. - */ - if (error) - return error; - - /* - * transaction commit worked ok so we can drop the extra ticket - * reference that we gained in xfs_trans_dup() - */ - xfs_log_ticket_put(ntp->t_ticket); - - if ((error = xfs_trans_reserve(ntp, 0, logres, 0, XFS_TRANS_PERM_LOG_RES, - logcount))) - return error; - efd = xfs_trans_get_efd(ntp, efi, flist->xbf_count); - for (free = flist->xbf_first; free != NULL; free = next) { - next = free->xbfi_next; - if ((error = xfs_free_extent(ntp, free->xbfi_startblock, - free->xbfi_blockcount))) { - /* - * The bmap free list will be cleaned up at a - * higher level. The EFI will be canceled when - * this transaction is aborted. - * Need to force shutdown here to make sure it - * happens, since this transaction may not be - * dirty yet. - */ - mp = ntp->t_mountp; - if (!XFS_FORCED_SHUTDOWN(mp)) - xfs_force_shutdown(mp, - (error == EFSCORRUPTED) ? - SHUTDOWN_CORRUPT_INCORE : - SHUTDOWN_META_IO_ERROR); - return error; - } - xfs_trans_log_efd_extent(ntp, efd, free->xbfi_startblock, - free->xbfi_blockcount); - xfs_bmap_del_free(flist, NULL, free); - } - return 0; -} - /* * Free up any items left in the list. */ @@ -1172,7 +904,7 @@ xfs_bmap_local_to_extents_empty( ASSERT(ifp->if_bytes == 0); ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0); - xfs_bmap_forkoff_reset(ip->i_mount, ip, whichfork); + xfs_bmap_forkoff_reset(ip, whichfork); ifp->if_flags &= ~XFS_IFINLINE; ifp->if_flags |= XFS_IFEXTENTS; XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); @@ -1366,10 +1098,11 @@ xfs_bmap_add_attrfork_local( if (S_ISDIR(ip->i_d.di_mode)) { memset(&dargs, 0, sizeof(dargs)); + dargs.geo = ip->i_mount->m_dir_geo; dargs.dp = ip; dargs.firstblock = firstblock; dargs.flist = flist; - dargs.total = ip->i_mount->m_dirblkfsbs; + dargs.total = dargs.geo->fsbcount; dargs.whichfork = XFS_DATA_FORK; dargs.trans = tp; return xfs_dir2_sf_to_block(&dargs); @@ -1404,6 +1137,7 @@ xfs_bmap_add_attrfork( int committed; /* xaction was committed */ int logflags; /* logging flags */ int error; /* error return value */ + int cancel_flags = 0; ASSERT(XFS_IFORK_Q(ip) == 0); @@ -1413,20 +1147,21 @@ xfs_bmap_add_attrfork( blks = XFS_ADDAFORK_SPACE_RES(mp); if (rsvd) tp->t_flags |= XFS_TRANS_RESERVE; - if ((error = xfs_trans_reserve(tp, blks, XFS_ADDAFORK_LOG_RES(mp), 0, - XFS_TRANS_PERM_LOG_RES, XFS_ADDAFORK_LOG_COUNT))) - goto error0; + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_addafork, blks, 0); + if (error) { + xfs_trans_cancel(tp, 0); + return error; + } + cancel_flags = XFS_TRANS_RELEASE_LOG_RES; xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES : XFS_QMOPT_RES_REGBLKS); - if (error) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES); - return error; - } + if (error) + goto trans_cancel; + cancel_flags |= XFS_TRANS_ABORT; if (XFS_IFORK_Q(ip)) - goto error1; + goto trans_cancel; if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS) { /* * For inodes coming from pre-6.2 filesystems. @@ -1436,7 +1171,7 @@ xfs_bmap_add_attrfork( } ASSERT(ip->i_d.di_anextents == 0); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, 0); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); switch (ip->i_d.di_format) { @@ -1458,7 +1193,7 @@ xfs_bmap_add_attrfork( default: ASSERT(0); error = XFS_ERROR(EINVAL); - goto error1; + goto trans_cancel; } ASSERT(ip->i_afp == NULL); @@ -1486,7 +1221,7 @@ xfs_bmap_add_attrfork( if (logflags) xfs_trans_log_inode(tp, ip, logflags); if (error) - goto error2; + goto bmap_cancel; if (!xfs_sb_version_hasattr(&mp->m_sb) || (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) { __int64_t sbfields = 0; @@ -1509,14 +1244,16 @@ xfs_bmap_add_attrfork( error = xfs_bmap_finish(&tp, &flist, &committed); if (error) - goto error2; - return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); -error2: + goto bmap_cancel; + error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return error; + +bmap_cancel: xfs_bmap_cancel(&flist); -error1: +trans_cancel: + xfs_trans_cancel(tp, cancel_flags); xfs_iunlock(ip, XFS_ILOCK_EXCL); -error0: - xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT); return error; } @@ -1747,7 +1484,7 @@ xfs_bmap_search_extents( xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO, "Access to block zero in inode %llu " "start_block: %llx start_off: %llx " - "blkcnt: %llx extent-state: %x lastx: %x\n", + "blkcnt: %llx extent-state: %x lastx: %x", (unsigned long long)ip->i_ino, (unsigned long long)gotp->br_startblock, (unsigned long long)gotp->br_startoff, @@ -1815,7 +1552,7 @@ xfs_bmap_first_unused( } /* - * Returns the file-relative block number of the last block + 1 before + * Returns the file-relative block number of the last block - 1 before * last_block (input value) in the file. * This is not based on i_size, it is based on the extent records. * Returns 0 for local files, as they do not have extent records. @@ -1863,7 +1600,7 @@ xfs_bmap_last_before( return 0; } -STATIC int +int xfs_bmap_last_extent( struct xfs_trans *tp, struct xfs_inode *ip, @@ -1898,7 +1635,7 @@ xfs_bmap_last_extent( * blocks at the end of the file which do not start at the previous data block, * we will try to align the new blocks at stripe unit boundaries. * - * Returns 0 in bma->aeof if the file (fork) is empty as any new write will be + * Returns 1 in bma->aeof if the file (fork) is empty as any new write will be * at, or past the EOF. */ STATIC int @@ -1913,9 +1650,14 @@ xfs_bmap_isaeof( bma->aeof = 0; error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec, &is_empty); - if (error || is_empty) + if (error) return error; + if (is_empty) { + bma->aeof = 1; + return 0; + } + /* * Check if we are allocation or past the last extent, or at least into * the last delayed allocated extent. @@ -1927,36 +1669,12 @@ xfs_bmap_isaeof( } /* - * 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; -} - -/* * Returns the file-relative block number of the first block past eof in * the file. This is not based on i_size, it is based on the extent records. * Returns 0 for local files, as they do not have extent records. */ int xfs_bmap_last_offset( - struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t *last_block, int whichfork) @@ -3488,7 +3206,7 @@ done: /* * Adjust the size of the new extent based on di_extsize and rt extsize. */ -STATIC int +int xfs_bmap_extsize_align( xfs_mount_t *mp, xfs_bmbt_irec_t *gotp, /* next extent pointer */ @@ -3650,9 +3368,9 @@ xfs_bmap_extsize_align( #define XFS_ALLOC_GAP_UNITS 4 -STATIC void +void xfs_bmap_adjacent( - xfs_bmalloca_t *ap) /* bmap alloc argument struct */ + struct xfs_bmalloca *ap) /* bmap alloc argument struct */ { xfs_fsblock_t adjust; /* adjustment to block numbers */ xfs_agnumber_t fb_agno; /* ag number of ap->firstblock */ @@ -3798,107 +3516,65 @@ xfs_bmap_adjacent( #undef ISVALID } -STATIC int -xfs_bmap_rtalloc( - xfs_bmalloca_t *ap) /* bmap alloc argument struct */ +static int +xfs_bmap_longest_free_extent( + struct xfs_trans *tp, + xfs_agnumber_t ag, + xfs_extlen_t *blen, + int *notinit) { - xfs_alloctype_t atype = 0; /* type for allocation routines */ - int error; /* error return value */ - xfs_mount_t *mp; /* mount point structure */ - xfs_extlen_t prod = 0; /* product factor for allocators */ - xfs_extlen_t ralen = 0; /* realtime allocation length */ - xfs_extlen_t align; /* minimum allocation alignment */ - xfs_rtblock_t rtb; - - mp = ap->ip->i_mount; - align = xfs_get_extsz_hint(ap->ip); - prod = align / mp->m_sb.sb_rextsize; - error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, - align, 1, ap->eof, 0, - ap->conv, &ap->offset, &ap->length); - if (error) - return error; - ASSERT(ap->length); - ASSERT(ap->length % mp->m_sb.sb_rextsize == 0); - - /* - * If the offset & length are not perfectly aligned - * then kill prod, it will just get us in trouble. - */ - if (do_mod(ap->offset, align) || ap->length % align) - prod = 1; - /* - * Set ralen to be the actual requested length in rtextents. - */ - ralen = ap->length / mp->m_sb.sb_rextsize; - /* - * If the old value was close enough to MAXEXTLEN that - * we rounded up to it, cut it back so it's valid again. - * Note that if it's a really large request (bigger than - * MAXEXTLEN), we don't hear about that number, and can't - * adjust the starting point to match it. - */ - if (ralen * mp->m_sb.sb_rextsize >= MAXEXTLEN) - ralen = MAXEXTLEN / mp->m_sb.sb_rextsize; - - /* - * Lock out other modifications to the RT bitmap inode. - */ - xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL); - - /* - * If it's an allocation to an empty file at offset 0, - * 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 */ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_perag *pag; + xfs_extlen_t longest; + int error = 0; - error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx); + pag = xfs_perag_get(mp, ag); + if (!pag->pagf_init) { + error = xfs_alloc_pagf_init(mp, tp, ag, XFS_ALLOC_FLAG_TRYLOCK); if (error) - return error; - ap->blkno = rtx * mp->m_sb.sb_rextsize; - } else { - ap->blkno = 0; + goto out; + + if (!pag->pagf_init) { + *notinit = 1; + goto out; + } } - xfs_bmap_adjacent(ap); + longest = xfs_alloc_longest_free_extent(mp, pag); + if (*blen < longest) + *blen = longest; - /* - * Realtime allocation, done through xfs_rtallocate_extent. - */ - atype = ap->blkno == 0 ? XFS_ALLOCTYPE_ANY_AG : XFS_ALLOCTYPE_NEAR_BNO; - do_div(ap->blkno, mp->m_sb.sb_rextsize); - rtb = ap->blkno; - ap->length = ralen; - if ((error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length, - &ralen, atype, ap->wasdel, prod, &rtb))) - return error; - if (rtb == NULLFSBLOCK && prod > 1 && - (error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, - ap->length, &ralen, atype, - ap->wasdel, 1, &rtb))) - return error; - ap->blkno = rtb; - if (ap->blkno != NULLFSBLOCK) { - ap->blkno *= mp->m_sb.sb_rextsize; - ralen *= mp->m_sb.sb_rextsize; - ap->length = ralen; - ap->ip->i_d.di_nblocks += ralen; - xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE); - if (ap->wasdel) - ap->ip->i_delayed_blks -= ralen; +out: + xfs_perag_put(pag); + return error; +} + +static void +xfs_bmap_select_minlen( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args, + xfs_extlen_t *blen, + int notinit) +{ + if (notinit || *blen < ap->minlen) { /* - * Adjust the disk quota also. This was reserved - * earlier. + * Since we did a BUF_TRYLOCK above, it is possible that + * there is space for this request. */ - xfs_trans_mod_dquot_byino(ap->tp, ap->ip, - ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT : - XFS_TRANS_DQ_RTBCOUNT, (long) ralen); + args->minlen = ap->minlen; + } else if (*blen < args->maxlen) { + /* + * If the best seen length is less than the request length, + * use the best as the minimum. + */ + args->minlen = *blen; } else { - ap->length = 0; + /* + * Otherwise we've seen an extent as big as maxlen, use that + * as the minimum. + */ + args->minlen = args->maxlen; } - return 0; } STATIC int @@ -3908,117 +3584,80 @@ xfs_bmap_btalloc_nullfb( xfs_extlen_t *blen) { struct xfs_mount *mp = ap->ip->i_mount; - struct xfs_perag *pag; xfs_agnumber_t ag, startag; int notinit = 0; int error; - if (ap->userdata && xfs_inode_is_filestream(ap->ip)) - args->type = XFS_ALLOCTYPE_NEAR_BNO; - else - args->type = XFS_ALLOCTYPE_START_BNO; + args->type = XFS_ALLOCTYPE_START_BNO; args->total = ap->total; - /* - * Search for an allocation group with a single extent large enough - * for the request. If one isn't found, then adjust the minimum - * allocation size to the largest space found. - */ startag = ag = XFS_FSB_TO_AGNO(mp, args->fsbno); if (startag == NULLAGNUMBER) startag = ag = 0; - pag = xfs_perag_get(mp, ag); while (*blen < args->maxlen) { - if (!pag->pagf_init) { - error = xfs_alloc_pagf_init(mp, args->tp, ag, - XFS_ALLOC_FLAG_TRYLOCK); - if (error) { - xfs_perag_put(pag); - return error; - } - } - - /* - * See xfs_alloc_fix_freelist... - */ - if (pag->pagf_init) { - xfs_extlen_t longest; - longest = xfs_alloc_longest_free_extent(mp, pag); - if (*blen < longest) - *blen = longest; - } else - notinit = 1; - - if (xfs_inode_is_filestream(ap->ip)) { - if (*blen >= args->maxlen) - break; - - if (ap->userdata) { - /* - * If startag is an invalid AG, we've - * come here once before and - * xfs_filestream_new_ag picked the - * best currently available. - * - * Don't continue looping, since we - * could loop forever. - */ - if (startag == NULLAGNUMBER) - break; - - error = xfs_filestream_new_ag(ap, &ag); - xfs_perag_put(pag); - if (error) - return error; + error = xfs_bmap_longest_free_extent(args->tp, ag, blen, + ¬init); + if (error) + return error; - /* loop again to set 'blen'*/ - startag = NULLAGNUMBER; - pag = xfs_perag_get(mp, ag); - continue; - } - } if (++ag == mp->m_sb.sb_agcount) ag = 0; if (ag == startag) break; - xfs_perag_put(pag); - pag = xfs_perag_get(mp, ag); } - xfs_perag_put(pag); - /* - * Since the above loop did a BUF_TRYLOCK, it is - * possible that there is space for this request. - */ - if (notinit || *blen < ap->minlen) - args->minlen = ap->minlen; - /* - * If the best seen length is less than the request - * length, use the best as the minimum. - */ - else if (*blen < args->maxlen) - args->minlen = *blen; - /* - * Otherwise we've seen an extent as big as maxlen, - * use that as the minimum. - */ - else - args->minlen = args->maxlen; + xfs_bmap_select_minlen(ap, args, blen, notinit); + return 0; +} + +STATIC int +xfs_bmap_btalloc_filestreams( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args, + xfs_extlen_t *blen) +{ + struct xfs_mount *mp = ap->ip->i_mount; + xfs_agnumber_t ag; + int notinit = 0; + int error; + + args->type = XFS_ALLOCTYPE_NEAR_BNO; + args->total = ap->total; + + ag = XFS_FSB_TO_AGNO(mp, args->fsbno); + if (ag == NULLAGNUMBER) + ag = 0; + + error = xfs_bmap_longest_free_extent(args->tp, ag, blen, ¬init); + if (error) + return error; + + if (*blen < args->maxlen) { + error = xfs_filestream_new_ag(ap, &ag); + if (error) + return error; + + error = xfs_bmap_longest_free_extent(args->tp, ag, blen, + ¬init); + if (error) + return error; + + } + + xfs_bmap_select_minlen(ap, args, blen, notinit); /* - * set the failure fallback case to look in the selected - * AG as the stream may have moved. + * Set the failure fallback case to look in the selected AG as stream + * may have moved. */ - if (xfs_inode_is_filestream(ap->ip)) - ap->blkno = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0); - + ap->blkno = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0); return 0; } STATIC int xfs_bmap_btalloc( - xfs_bmalloca_t *ap) /* bmap alloc argument struct */ + struct xfs_bmalloca *ap) /* bmap alloc argument struct */ { xfs_mount_t *mp; /* mount point structure */ xfs_alloctype_t atype = 0; /* type for allocation routines */ @@ -4032,10 +3671,19 @@ xfs_bmap_btalloc( int isaligned; int tryagain; int error; + int stripe_align; ASSERT(ap->length); mp = ap->ip->i_mount; + + /* stripe alignment for allocation is determined by mount parameters */ + stripe_align = 0; + if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC)) + stripe_align = mp->m_swidth; + else if (mp->m_dalign) + stripe_align = mp->m_dalign; + align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0; if (unlikely(align)) { error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, @@ -4044,6 +3692,8 @@ xfs_bmap_btalloc( ASSERT(!error); ASSERT(ap->length); } + + nullfb = *ap->firstblock == NULLFSBLOCK; fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock); if (nullfb) { @@ -4081,7 +3731,15 @@ xfs_bmap_btalloc( args.firstblock = *ap->firstblock; blen = 0; if (nullfb) { - error = xfs_bmap_btalloc_nullfb(ap, &args, &blen); + /* + * Search for an allocation group with a single extent large + * enough for the request. If one isn't found, then adjust + * the minimum allocation size to the largest space found. + */ + if (ap->userdata && xfs_inode_is_filestream(ap->ip)) + error = xfs_bmap_btalloc_filestreams(ap, &args, &blen); + else + error = xfs_bmap_btalloc_nullfb(ap, &args, &blen); if (error) return error; } else if (ap->flist->xbf_low) { @@ -4119,7 +3777,7 @@ xfs_bmap_btalloc( */ if (!ap->flist->xbf_low && ap->aeof) { if (!ap->offset) { - args.alignment = mp->m_dalign; + args.alignment = stripe_align; atype = args.type; isaligned = 1; /* @@ -4144,13 +3802,13 @@ xfs_bmap_btalloc( * of minlen+alignment+slop doesn't go up * between the calls. */ - if (blen > mp->m_dalign && blen <= args.maxlen) - nextminlen = blen - mp->m_dalign; + if (blen > stripe_align && blen <= args.maxlen) + nextminlen = blen - stripe_align; else nextminlen = args.minlen; - if (nextminlen + mp->m_dalign > args.minlen + 1) + if (nextminlen + stripe_align > args.minlen + 1) args.minalignslop = - nextminlen + mp->m_dalign - + nextminlen + stripe_align - args.minlen - 1; else args.minalignslop = 0; @@ -4172,7 +3830,7 @@ xfs_bmap_btalloc( */ args.type = atype; args.fsbno = ap->blkno; - args.alignment = mp->m_dalign; + args.alignment = stripe_align; args.minlen = nextminlen; args.minalignslop = 0; isaligned = 1; @@ -4250,7 +3908,7 @@ xfs_bmap_btalloc( */ STATIC int xfs_bmap_alloc( - xfs_bmalloca_t *ap) /* bmap alloc argument struct */ + struct xfs_bmalloca *ap) /* bmap alloc argument struct */ { if (XFS_IS_REALTIME_INODE(ap->ip) && ap->userdata) return xfs_bmap_rtalloc(ap); @@ -4386,6 +4044,7 @@ xfs_bmapi_read( ASSERT(*nmap >= 1); ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK|XFS_BMAPI_ENTIRE| XFS_BMAPI_IGSTATE))); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)); if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && @@ -4580,6 +4239,7 @@ xfs_bmapi_delay( ASSERT(*nmap >= 1); ASSERT(*nmap <= XFS_BMAP_MAX_NMAP); ASSERT(!(flags & ~XFS_BMAPI_ENTIRE)); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS && @@ -4638,8 +4298,8 @@ xfs_bmapi_delay( } -STATIC int -__xfs_bmapi_allocate( +static int +xfs_bmapi_allocate( struct xfs_bmalloca *bma) { struct xfs_mount *mp = bma->ip->i_mount; @@ -4648,12 +4308,9 @@ __xfs_bmapi_allocate( struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork); int tmp_logflags = 0; int error; - int rt; ASSERT(bma->length > 0); - rt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(bma->ip); - /* * For the wasdelay case, we could also just allocate the stuff asked * for in this bmap call but that wouldn't be as good. @@ -4756,45 +4413,6 @@ __xfs_bmapi_allocate( return 0; } -static void -xfs_bmapi_allocate_worker( - struct work_struct *work) -{ - struct xfs_bmalloca *args = container_of(work, - struct xfs_bmalloca, work); - unsigned long pflags; - - /* we are in a transaction context here */ - current_set_flags_nested(&pflags, PF_FSTRANS); - - args->result = __xfs_bmapi_allocate(args); - complete(args->done); - - current_restore_flags_nested(&pflags, PF_FSTRANS); -} - -/* - * Some allocation requests often come in with little stack to work on. Push - * them off to a worker thread so there is lots of stack to use. Otherwise just - * call directly to avoid the context switch overhead here. - */ -int -xfs_bmapi_allocate( - struct xfs_bmalloca *args) -{ - DECLARE_COMPLETION_ONSTACK(done); - - if (!args->stack_switch) - return __xfs_bmapi_allocate(args); - - - args->done = &done; - INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker); - queue_work(xfs_alloc_wq, &args->work); - wait_for_completion(&done); - return args->result; -} - STATIC int xfs_bmapi_convert_unwritten( struct xfs_bmalloca *bma, @@ -4883,7 +4501,7 @@ xfs_bmapi_write( { struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp; - struct xfs_bmalloca bma = { 0 }; /* args for xfs_bmap_alloc */ + struct xfs_bmalloca bma = { NULL }; /* args for xfs_bmap_alloc */ xfs_fileoff_t end; /* end of mapped file region */ int eof; /* after the end of extents */ int error; /* error return */ @@ -4915,6 +4533,7 @@ xfs_bmapi_write( ASSERT(tp != NULL); ASSERT(len > 0); ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && @@ -4959,9 +4578,6 @@ xfs_bmapi_write( bma.flist = flist; bma.firstblock = firstblock; - if (flags & XFS_BMAPI_STACK_SWITCH) - bma.stack_switch = 1; - while (bno < end && n < *nmap) { inhole = eof || bma.got.br_startoff > bno; wasdelay = !inhole && isnullstartblock(bma.got.br_startblock); @@ -5466,6 +5082,7 @@ xfs_bunmapi( if (XFS_FORCED_SHUTDOWN(mp)) return XFS_ERROR(EIO); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); ASSERT(len > 0); ASSERT(nexts >= 0); @@ -5791,357 +5408,199 @@ error0: } /* - * returns 1 for success, 0 if we failed to map the extent. - */ -STATIC int -xfs_getbmapx_fix_eof_hole( - xfs_inode_t *ip, /* xfs incore inode pointer */ - struct getbmapx *out, /* output structure */ - int prealloced, /* this is a file with - * preallocated data space */ - __int64_t end, /* last block requested */ - xfs_fsblock_t startblock) -{ - __int64_t fixlen; - xfs_mount_t *mp; /* file system mount point */ - xfs_ifork_t *ifp; /* inode fork pointer */ - xfs_extnum_t lastx; /* last extent pointer */ - xfs_fileoff_t fileblock; - - if (startblock == HOLESTARTBLOCK) { - mp = ip->i_mount; - out->bmv_block = -1; - fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, XFS_ISIZE(ip))); - fixlen -= out->bmv_offset; - if (prealloced && out->bmv_offset + out->bmv_length == end) { - /* Came to hole at EOF. Trim it. */ - if (fixlen <= 0) - return 0; - out->bmv_length = fixlen; - } - } else { - if (startblock == DELAYSTARTBLOCK) - out->bmv_block = -2; - else - out->bmv_block = xfs_fsb_to_db(ip, startblock); - fileblock = XFS_BB_TO_FSB(ip->i_mount, out->bmv_offset); - ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); - if (xfs_iext_bno_to_ext(ifp, fileblock, &lastx) && - (lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1)) - out->bmv_oflags |= BMV_OF_LAST; - } - - return 1; -} - -/* - * 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. + * Shift extent records to the left to cover a hole. + * + * The maximum number of extents to be shifted in a single operation + * is @num_exts, and @current_ext keeps track of the current extent + * index we have shifted. @offset_shift_fsb is the length by which each + * extent is shifted. If there is no hole to shift the extents + * into, this will be considered invalid operation and we abort immediately. */ -int /* error code */ -xfs_getbmap( - xfs_inode_t *ip, - struct getbmapx *bmv, /* user bmap structure */ - xfs_bmap_format_t formatter, /* format to user */ - void *arg) /* formatter arg */ +int +xfs_bmap_shift_extents( + struct xfs_trans *tp, + struct xfs_inode *ip, + int *done, + xfs_fileoff_t start_fsb, + xfs_fileoff_t offset_shift_fsb, + xfs_extnum_t *current_ext, + xfs_fsblock_t *firstblock, + struct xfs_bmap_free *flist, + int num_exts) { - __int64_t bmvend; /* last block requested */ - int error = 0; /* return value */ - __int64_t fixlen; /* length for -1 case */ - int i; /* extent number */ - int lock; /* lock state */ - xfs_bmbt_irec_t *map; /* buffer for user's data */ - xfs_mount_t *mp; /* file system mount point */ - int nex; /* # of user extents can do */ - int nexleft; /* # of user extents left */ - int subnex; /* # of bmapi's can do */ - int nmap; /* number of map entries */ - struct getbmapx *out; /* output structure */ - int whichfork; /* data or attr fork */ - int prealloced; /* this is a file with - * preallocated data space */ - int iflags; /* interface flags */ - int bmapi_flags; /* flags for xfs_bmapi */ - int cur_ext = 0; - - mp = ip->i_mount; - iflags = bmv->bmv_iflags; - whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK; - - if (whichfork == XFS_ATTR_FORK) { - if (XFS_IFORK_Q(ip)) { - if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS && - ip->i_d.di_aformat != XFS_DINODE_FMT_BTREE && - ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL) - return XFS_ERROR(EINVAL); - } else if (unlikely( - ip->i_d.di_aformat != 0 && - ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS)) { - XFS_ERROR_REPORT("xfs_getbmap", XFS_ERRLEVEL_LOW, - ip->i_mount); - return XFS_ERROR(EFSCORRUPTED); - } + struct xfs_btree_cur *cur; + struct xfs_bmbt_rec_host *gotp; + struct xfs_bmbt_irec got; + struct xfs_bmbt_irec left; + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp; + xfs_extnum_t nexts = 0; + xfs_fileoff_t startoff; + int error = 0; + int i; + int whichfork = XFS_DATA_FORK; + int logflags; + xfs_filblks_t blockcount = 0; + int total_extents; - prealloced = 0; - fixlen = 1LL << 32; - } else { - if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS && - ip->i_d.di_format != XFS_DINODE_FMT_BTREE && - ip->i_d.di_format != XFS_DINODE_FMT_LOCAL) - return XFS_ERROR(EINVAL); - - if (xfs_get_extsz_hint(ip) || - ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){ - prealloced = 1; - fixlen = mp->m_super->s_maxbytes; - } else { - prealloced = 0; - fixlen = XFS_ISIZE(ip); - } - } - - if (bmv->bmv_length == -1) { - fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen)); - bmv->bmv_length = - max_t(__int64_t, fixlen - bmv->bmv_offset, 0); - } else if (bmv->bmv_length == 0) { - bmv->bmv_entries = 0; - return 0; - } else if (bmv->bmv_length < 0) { - return XFS_ERROR(EINVAL); + if (unlikely(XFS_TEST_ERROR( + (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && + XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE), + mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) { + XFS_ERROR_REPORT("xfs_bmap_shift_extents", + XFS_ERRLEVEL_LOW, mp); + return XFS_ERROR(EFSCORRUPTED); } - nex = bmv->bmv_count - 1; - if (nex <= 0) - return XFS_ERROR(EINVAL); - bmvend = bmv->bmv_offset + bmv->bmv_length; + if (XFS_FORCED_SHUTDOWN(mp)) + return XFS_ERROR(EIO); + ASSERT(current_ext != NULL); - if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx)) - return XFS_ERROR(ENOMEM); - out = kmem_zalloc(bmv->bmv_count * sizeof(struct getbmapx), KM_MAYFAIL); - if (!out) { - out = kmem_zalloc_large(bmv->bmv_count * - sizeof(struct getbmapx)); - if (!out) - return XFS_ERROR(ENOMEM); + ifp = XFS_IFORK_PTR(ip, whichfork); + if (!(ifp->if_flags & XFS_IFEXTENTS)) { + /* Read in all the extents */ + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; } - xfs_ilock(ip, XFS_IOLOCK_SHARED); - if (whichfork == XFS_DATA_FORK && !(iflags & BMV_IF_DELALLOC)) { - if (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size) { - error = -filemap_write_and_wait(VFS_I(ip)->i_mapping); - if (error) - goto out_unlock_iolock; - } + /* + * If *current_ext is 0, we would need to lookup the extent + * from where we would start shifting and store it in gotp. + */ + if (!*current_ext) { + gotp = xfs_iext_bno_to_ext(ifp, start_fsb, current_ext); /* - * 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. + * gotp can be null in 2 cases: 1) if there are no extents + * or 2) start_fsb lies in a hole beyond which there are + * no extents. Either way, we are done. */ + if (!gotp) { + *done = 1; + return 0; + } } - lock = xfs_ilock_map_shared(ip); - - /* - * Don't let nex be bigger than the number of extents - * we can have assuming alternating holes and real extents. - */ - if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1) - nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1; - - bmapi_flags = xfs_bmapi_aflag(whichfork); - if (!(iflags & BMV_IF_PREALLOC)) - bmapi_flags |= XFS_BMAPI_IGSTATE; + /* We are going to change core inode */ + logflags = XFS_ILOG_CORE; + if (ifp->if_flags & XFS_IFBROOT) { + cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); + cur->bc_private.b.firstblock = *firstblock; + cur->bc_private.b.flist = flist; + cur->bc_private.b.flags = 0; + } else { + cur = NULL; + logflags |= XFS_ILOG_DEXT; + } /* - * Allocate enough space to handle "subnex" maps at a time. + * There may be delalloc extents in the data fork before the range we + * are collapsing out, so we cannot + * use the count of real extents here. Instead we have to calculate it + * from the incore fork. */ - error = ENOMEM; - subnex = 16; - map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS); - if (!map) - goto out_unlock_ilock; - - bmv->bmv_entries = 0; - - if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0 && - (whichfork == XFS_ATTR_FORK || !(iflags & BMV_IF_DELALLOC))) { - error = 0; - goto out_free_map; - } + total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); + while (nexts++ < num_exts && *current_ext < total_extents) { - nexleft = nex; + gotp = xfs_iext_get_ext(ifp, *current_ext); + xfs_bmbt_get_all(gotp, &got); + startoff = got.br_startoff - offset_shift_fsb; - do { - nmap = (nexleft > subnex) ? subnex : nexleft; - error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset), - XFS_BB_TO_FSB(mp, bmv->bmv_length), - map, &nmap, bmapi_flags); - if (error) - goto out_free_map; - ASSERT(nmap <= subnex); - - for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) { - out[cur_ext].bmv_oflags = 0; - if (map[i].br_state == XFS_EXT_UNWRITTEN) - out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC; - else if (map[i].br_startblock == DELAYSTARTBLOCK) - out[cur_ext].bmv_oflags |= BMV_OF_DELALLOC; - out[cur_ext].bmv_offset = - XFS_FSB_TO_BB(mp, map[i].br_startoff); - out[cur_ext].bmv_length = - XFS_FSB_TO_BB(mp, map[i].br_blockcount); - out[cur_ext].bmv_unused1 = 0; - out[cur_ext].bmv_unused2 = 0; + /* + * Before shifting extent into hole, make sure that the hole + * is large enough to accomodate the shift. + */ + if (*current_ext) { + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, + *current_ext - 1), &left); + if (startoff < left.br_startoff + left.br_blockcount) + error = XFS_ERROR(EINVAL); + } else if (offset_shift_fsb > got.br_startoff) { /* - * delayed allocation extents that start beyond EOF can - * occur due to speculative EOF allocation when the - * delalloc extent is larger than the largest freespace - * extent at conversion time. These extents cannot be - * converted by data writeback, so can exist here even - * if we are not supposed to be finding delalloc - * extents. + * When first extent is shifted, offset_shift_fsb + * should be less than the stating offset of + * the first extent. */ - if (map[i].br_startblock == DELAYSTARTBLOCK && - map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip))) - ASSERT((iflags & BMV_IF_DELALLOC) != 0); - - if (map[i].br_startblock == HOLESTARTBLOCK && - whichfork == XFS_ATTR_FORK) { - /* came to the end of attribute fork */ - out[cur_ext].bmv_oflags |= BMV_OF_LAST; - goto out_free_map; - } + error = XFS_ERROR(EINVAL); + } - if (!xfs_getbmapx_fix_eof_hole(ip, &out[cur_ext], - prealloced, bmvend, - map[i].br_startblock)) - goto out_free_map; + if (error) + goto del_cursor; - bmv->bmv_offset = - out[cur_ext].bmv_offset + - out[cur_ext].bmv_length; - bmv->bmv_length = - max_t(__int64_t, 0, bmvend - bmv->bmv_offset); + if (cur) { + error = xfs_bmbt_lookup_eq(cur, got.br_startoff, + got.br_startblock, + got.br_blockcount, + &i); + if (error) + goto del_cursor; + XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor); + } - /* - * In case we don't want to return the hole, - * don't increase cur_ext so that we can reuse - * it in the next loop. - */ - if ((iflags & BMV_IF_NO_HOLES) && - map[i].br_startblock == HOLESTARTBLOCK) { - memset(&out[cur_ext], 0, sizeof(out[cur_ext])); - continue; + /* Check if we can merge 2 adjacent extents */ + if (*current_ext && + left.br_startoff + left.br_blockcount == startoff && + left.br_startblock + left.br_blockcount == + got.br_startblock && + left.br_state == got.br_state && + left.br_blockcount + got.br_blockcount <= MAXEXTLEN) { + blockcount = left.br_blockcount + + got.br_blockcount; + xfs_iext_remove(ip, *current_ext, 1, 0); + if (cur) { + error = xfs_btree_delete(cur, &i); + if (error) + goto del_cursor; + XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor); } + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) - 1); + gotp = xfs_iext_get_ext(ifp, --*current_ext); + xfs_bmbt_get_all(gotp, &got); - nexleft--; - bmv->bmv_entries++; - cur_ext++; - } - } while (nmap && nexleft && bmv->bmv_length); + /* Make cursor point to the extent we will update */ + if (cur) { + error = xfs_bmbt_lookup_eq(cur, got.br_startoff, + got.br_startblock, + got.br_blockcount, + &i); + if (error) + goto del_cursor; + XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor); + } - out_free_map: - kmem_free(map); - out_unlock_ilock: - xfs_iunlock_map_shared(ip, lock); - out_unlock_iolock: - xfs_iunlock(ip, XFS_IOLOCK_SHARED); + xfs_bmbt_set_blockcount(gotp, blockcount); + got.br_blockcount = blockcount; + } else { + /* We have to update the startoff */ + xfs_bmbt_set_startoff(gotp, startoff); + got.br_startoff = startoff; + } - for (i = 0; i < cur_ext; i++) { - int full = 0; /* user array is full */ + if (cur) { + error = xfs_bmbt_update(cur, got.br_startoff, + got.br_startblock, + got.br_blockcount, + got.br_state); + if (error) + goto del_cursor; + } - /* format results & advance arg */ - error = formatter(&arg, &out[i], &full); - if (error || full) - break; + (*current_ext)++; + total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); } - if (is_vmalloc_addr(out)) - kmem_free_large(out); - else - kmem_free(out); - return error; -} - -/* - * dead simple method of punching delalyed allocation blocks from a range in - * the inode. Walks a block at a time so will be slow, but is only executed in - * rare error cases so the overhead is not critical. This will alays 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. - */ -int -xfs_bmap_punch_delalloc_range( - struct xfs_inode *ip, - xfs_fileoff_t start_fsb, - xfs_fileoff_t length) -{ - xfs_fileoff_t remaining = length; - int error = 0; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - - do { - int done; - xfs_bmbt_irec_t imap; - int nimaps = 1; - xfs_fsblock_t firstblock; - xfs_bmap_free_t flist; - - /* - * Map the range first and check that it is a delalloc extent - * before trying to unmap the range. Otherwise we will be - * trying to remove a real extent (which requires a - * transaction) or a hole, which is probably a bad idea... - */ - error = xfs_bmapi_read(ip, start_fsb, 1, &imap, &nimaps, - XFS_BMAPI_ENTIRE); - - if (error) { - /* something screwed, just bail */ - if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { - xfs_alert(ip->i_mount, - "Failed delalloc mapping lookup ino %lld fsb %lld.", - ip->i_ino, start_fsb); - } - break; - } - if (!nimaps) { - /* nothing there */ - goto next_block; - } - if (imap.br_startblock != DELAYSTARTBLOCK) { - /* been converted, ignore */ - goto next_block; - } - WARN_ON(imap.br_blockcount == 0); - - /* - * Note: while we initialise the firstblock/flist pair, they - * should never be used because blocks should never be - * allocated or freed for a delalloc extent and hence we need - * don't cancel or finish them after the xfs_bunmapi() call. - */ - xfs_bmap_init(&flist, &firstblock); - error = xfs_bunmapi(NULL, ip, start_fsb, 1, 0, 1, &firstblock, - &flist, &done); - if (error) - break; + /* Check if we are done */ + if (*current_ext == total_extents) + *done = 1; - ASSERT(!flist.xbf_count && !flist.xbf_first); -next_block: - start_fsb++; - remaining--; - } while(remaining > 0); +del_cursor: + if (cur) + xfs_btree_del_cursor(cur, + error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); + xfs_trans_log_inode(tp, ip, logflags); return error; } |