diff options
Diffstat (limited to 'fs/xfs/libxfs/xfs_bmap.c')
| -rw-r--r-- | fs/xfs/libxfs/xfs_bmap.c | 6183 |
1 files changed, 2949 insertions, 3234 deletions
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index c09c16b1ad3b..53ef4b7e504d 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1,19 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2006 Silicon Graphics, Inc. * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #include "xfs.h" #include "xfs_fs.h" @@ -25,35 +13,36 @@ #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_defer.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_dir2.h" #include "xfs_inode.h" #include "xfs_btree.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_rtbitmap.h" +#include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_trans_space.h" #include "xfs_buf_item.h" #include "xfs_trace.h" -#include "xfs_symlink.h" #include "xfs_attr_leaf.h" #include "xfs_filestream.h" #include "xfs_rmap.h" +#include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_refcount.h" -#include "xfs_rmap_btree.h" -#include "xfs_icache.h" - +#include "xfs_iomap.h" +#include "xfs_health.h" +#include "xfs_bmap_item.h" +#include "xfs_symlink_remote.h" +#include "xfs_inode_util.h" +#include "xfs_rtgroup.h" +#include "xfs_zone_alloc.h" -kmem_zone_t *xfs_bmap_free_item_zone; +struct kmem_cache *xfs_bmap_intent_cache; /* * Miscellaneous helper functions @@ -68,73 +57,74 @@ xfs_bmap_compute_maxlevels( xfs_mount_t *mp, /* file system mount structure */ int whichfork) /* data or attr fork */ { + uint64_t maxblocks; /* max blocks at this level */ + xfs_extnum_t maxleafents; /* max leaf entries possible */ int level; /* btree level */ - uint maxblocks; /* max blocks at this level */ - uint maxleafents; /* max leaf entries possible */ int maxrootrecs; /* max records in root block */ int minleafrecs; /* min records in leaf block */ int minnoderecs; /* min records in node block */ int sz; /* root block size */ /* - * The maximum number of extents in a file, hence the maximum - * number of leaf entries, is controlled by the type of di_nextents - * (a signed 32-bit number, xfs_extnum_t), or by di_anextents - * (a signed 16-bit number, xfs_aextnum_t). + * The maximum number of extents in a fork, hence the maximum number of + * leaf entries, is controlled by the size of the on-disk extent count. * - * Note that we can no longer assume that if we are in ATTR1 that - * the fork offset of all the inodes will be - * (xfs_default_attroffset(ip) >> 3) because we could have mounted - * with ATTR2 and then mounted back with ATTR1, keeping the - * di_forkoff's fixed but probably at various positions. Therefore, - * for both ATTR1 and ATTR2 we have to assume the worst case scenario - * of a minimum size available. + * Note that we can no longer assume that if we are in ATTR1 that the + * fork offset of all the inodes will be + * (xfs_default_attroffset(ip) >> 3) because we could have mounted with + * ATTR2 and then mounted back with ATTR1, keeping the i_forkoff's fixed + * but probably at various positions. Therefore, for both ATTR1 and + * ATTR2 we have to assume the worst case scenario of a minimum size + * available. */ - if (whichfork == XFS_DATA_FORK) { - maxleafents = MAXEXTNUM; - sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS); - } else { - maxleafents = MAXAEXTNUM; - sz = XFS_BMDR_SPACE_CALC(MINABTPTRS); - } + maxleafents = xfs_iext_max_nextents(xfs_has_large_extent_counts(mp), + whichfork); + if (whichfork == XFS_DATA_FORK) + sz = xfs_bmdr_space_calc(MINDBTPTRS); + else + sz = xfs_bmdr_space_calc(MINABTPTRS); + maxrootrecs = xfs_bmdr_maxrecs(sz, 0); minleafrecs = mp->m_bmap_dmnr[0]; minnoderecs = mp->m_bmap_dmnr[1]; - maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs; + maxblocks = howmany_64(maxleafents, minleafrecs); for (level = 1; maxblocks > 1; level++) { if (maxblocks <= maxrootrecs) maxblocks = 1; else - maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs; + maxblocks = howmany_64(maxblocks, minnoderecs); } mp->m_bm_maxlevels[whichfork] = level; + ASSERT(mp->m_bm_maxlevels[whichfork] <= xfs_bmbt_maxlevels_ondisk()); +} + +unsigned int +xfs_bmap_compute_attr_offset( + struct xfs_mount *mp) +{ + if (mp->m_sb.sb_inodesize == 256) + return XFS_LITINO(mp) - xfs_bmdr_space_calc(MINABTPTRS); + return xfs_bmdr_space_calc(6 * MINABTPTRS); } STATIC int /* error */ xfs_bmbt_lookup_eq( struct xfs_btree_cur *cur, - xfs_fileoff_t off, - xfs_fsblock_t bno, - xfs_filblks_t len, + struct xfs_bmbt_irec *irec, int *stat) /* success/failure */ { - cur->bc_rec.b.br_startoff = off; - cur->bc_rec.b.br_startblock = bno; - cur->bc_rec.b.br_blockcount = len; + cur->bc_rec.b = *irec; return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat); } STATIC int /* error */ -xfs_bmbt_lookup_ge( +xfs_bmbt_lookup_first( struct xfs_btree_cur *cur, - xfs_fileoff_t off, - xfs_fsblock_t bno, - xfs_filblks_t len, int *stat) /* success/failure */ { - cur->bc_rec.b.br_startoff = off; - cur->bc_rec.b.br_startblock = bno; - cur->bc_rec.b.br_blockcount = len; + cur->bc_rec.b.br_startoff = 0; + cur->bc_rec.b.br_startblock = 0; + cur->bc_rec.b.br_blockcount = 0; return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat); } @@ -143,10 +133,11 @@ xfs_bmbt_lookup_ge( */ static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork) { + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + return whichfork != XFS_COW_FORK && - XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_NEXTENTS(ip, whichfork) > - XFS_IFORK_MAXEXT(ip, whichfork); + ifp->if_format == XFS_DINODE_FMT_EXTENTS && + ifp->if_nextents > XFS_IFORK_MAXEXT(ip, whichfork); } /* @@ -154,28 +145,25 @@ static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork) */ static inline bool xfs_bmap_wants_extents(struct xfs_inode *ip, int whichfork) { + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + return whichfork != XFS_COW_FORK && - XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE && - XFS_IFORK_NEXTENTS(ip, whichfork) <= - XFS_IFORK_MAXEXT(ip, whichfork); + ifp->if_format == XFS_DINODE_FMT_BTREE && + ifp->if_nextents <= XFS_IFORK_MAXEXT(ip, whichfork); } /* - * Update the record referred to by cur to the value given - * by [off, bno, len, state]. + * Update the record referred to by cur to the value given by irec * This either works (return 0) or gets an EFSCORRUPTED error. */ STATIC int xfs_bmbt_update( struct xfs_btree_cur *cur, - xfs_fileoff_t off, - xfs_fsblock_t bno, - xfs_filblks_t len, - xfs_exntst_t state) + struct xfs_bmbt_irec *irec) { union xfs_btree_rec rec; - xfs_bmbt_disk_set_allf(&rec.bmbt, off, bno, len, state); + xfs_bmbt_disk_set_all(&rec.bmbt, irec); return xfs_btree_update(cur, &rec); } @@ -183,42 +171,28 @@ xfs_bmbt_update( * Compute the worst-case number of indirect blocks that will be used * for ip's delayed extent of length "len". */ -STATIC xfs_filblks_t +xfs_filblks_t xfs_bmap_worst_indlen( - xfs_inode_t *ip, /* incore inode pointer */ - xfs_filblks_t len) /* delayed extent length */ + struct xfs_inode *ip, /* incore inode pointer */ + xfs_filblks_t len) /* delayed extent length */ { - int level; /* btree level number */ - int maxrecs; /* maximum record count at this level */ - xfs_mount_t *mp; /* mount structure */ - xfs_filblks_t rval; /* return value */ - xfs_filblks_t orig_len; - - mp = ip->i_mount; + struct xfs_mount *mp = ip->i_mount; + int maxrecs = mp->m_bmap_dmxr[0]; + int level; + xfs_filblks_t rval; - /* Calculate the worst-case size of the bmbt. */ - orig_len = len; - maxrecs = mp->m_bmap_dmxr[0]; for (level = 0, rval = 0; level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK); level++) { len += maxrecs - 1; do_div(len, maxrecs); rval += len; - if (len == 1) { - rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - + if (len == 1) + return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - level - 1; - break; - } if (level == 0) maxrecs = mp->m_bmap_dmxr[1]; } - - /* Calculate the worst-case size of the rmapbt. */ - if (xfs_sb_version_hasrmapbt(&mp->m_sb)) - rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) + - mp->m_rmap_maxlevels; - return rval; } @@ -229,24 +203,15 @@ uint xfs_default_attroffset( struct xfs_inode *ip) { - struct xfs_mount *mp = ip->i_mount; - uint offset; - - if (mp->m_sb.sb_inodesize == 256) { - offset = XFS_LITINO(mp, ip->i_d.di_version) - - XFS_BMDR_SPACE_CALC(MINABTPTRS); - } else { - offset = XFS_BMDR_SPACE_CALC(6 * MINABTPTRS); - } - - ASSERT(offset < XFS_LITINO(mp, ip->i_d.di_version)); - return offset; + if (ip->i_df.if_format == XFS_DINODE_FMT_DEV) + return roundup(sizeof(xfs_dev_t), 8); + return M_IGEO(ip->i_mount)->attr_fork_offset; } /* - * Helper routine to reset inode di_forkoff field when switching - * attribute fork from local to extent format - we reset it where - * possible to make space available for inline data fork extents. + * Helper routine to reset inode i_forkoff field when switching attribute fork + * from local to extent format - we reset it where possible to make space + * available for inline data fork extents. */ STATIC void xfs_bmap_forkoff_reset( @@ -254,41 +219,62 @@ xfs_bmap_forkoff_reset( int whichfork) { if (whichfork == XFS_ATTR_FORK && - ip->i_d.di_format != XFS_DINODE_FMT_DEV && - ip->i_d.di_format != XFS_DINODE_FMT_UUID && - ip->i_d.di_format != XFS_DINODE_FMT_BTREE) { + ip->i_df.if_format != XFS_DINODE_FMT_DEV && + ip->i_df.if_format != XFS_DINODE_FMT_BTREE) { uint dfl_forkoff = xfs_default_attroffset(ip) >> 3; - if (dfl_forkoff > ip->i_d.di_forkoff) - ip->i_d.di_forkoff = dfl_forkoff; + if (dfl_forkoff > ip->i_forkoff) + ip->i_forkoff = dfl_forkoff; } } +static int +xfs_bmap_read_buf( + struct xfs_mount *mp, /* file system mount point */ + struct xfs_trans *tp, /* transaction pointer */ + xfs_fsblock_t fsbno, /* file system block number */ + struct xfs_buf **bpp) /* buffer for fsbno */ +{ + struct xfs_buf *bp; /* return value */ + int error; + + if (!xfs_verify_fsbno(mp, fsbno)) + return -EFSCORRUPTED; + error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, + XFS_FSB_TO_DADDR(mp, fsbno), mp->m_bsize, 0, &bp, + &xfs_bmbt_buf_ops); + if (!error) { + xfs_buf_set_ref(bp, XFS_BMAP_BTREE_REF); + *bpp = bp; + } + return error; +} + #ifdef DEBUG STATIC struct xfs_buf * xfs_bmap_get_bp( struct xfs_btree_cur *cur, xfs_fsblock_t bno) { - struct xfs_log_item_desc *lidp; + struct xfs_log_item *lip; int i; if (!cur) return NULL; - for (i = 0; i < XFS_BTREE_MAXLEVELS; i++) { - if (!cur->bc_bufs[i]) + for (i = 0; i < cur->bc_maxlevels; i++) { + if (!cur->bc_levels[i].bp) break; - if (XFS_BUF_ADDR(cur->bc_bufs[i]) == bno) - return cur->bc_bufs[i]; + if (xfs_buf_daddr(cur->bc_levels[i].bp) == bno) + return cur->bc_levels[i].bp; } /* Chase down all the log items to see if the bp is there */ - list_for_each_entry(lidp, &cur->bc_tp->t_items, lid_trans) { - struct xfs_buf_log_item *bip; - bip = (struct xfs_buf_log_item *)lidp->lid_item; + list_for_each_entry(lip, &cur->bc_tp->t_items, li_trans) { + struct xfs_buf_log_item *bip = (struct xfs_buf_log_item *)lip; + if (bip->bli_item.li_type == XFS_LI_BUF && - XFS_BUF_ADDR(bip->bli_buf) == bno) + xfs_buf_daddr(bip->bli_buf) == bno) return bip->bli_buf; } @@ -311,7 +297,7 @@ xfs_check_block( prevp = NULL; for( i = 1; i <= xfs_btree_get_numrecs(block); i++) { dmxr = mp->m_bmap_dmxr[0]; - keyp = XFS_BMBT_KEY_ADDR(mp, block, i); + keyp = xfs_bmbt_key_addr(mp, block, i); if (prevp) { ASSERT(be64_to_cpu(prevp->br_startoff) < @@ -323,21 +309,22 @@ xfs_check_block( * Compare the block numbers to see if there are dups. */ if (root) - pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, i, sz); + pp = xfs_bmap_broot_ptr_addr(mp, block, i, sz); else - pp = XFS_BMBT_PTR_ADDR(mp, block, i, dmxr); + pp = xfs_bmbt_ptr_addr(mp, block, i, dmxr); for (j = i+1; j <= be16_to_cpu(block->bb_numrecs); j++) { if (root) - thispa = XFS_BMAP_BROOT_PTR_ADDR(mp, block, j, sz); + thispa = xfs_bmap_broot_ptr_addr(mp, block, j, sz); else - thispa = XFS_BMBT_PTR_ADDR(mp, block, j, dmxr); + thispa = xfs_bmbt_ptr_addr(mp, block, j, dmxr); if (*thispa == *pp) { - xfs_warn(mp, "%s: thispa(%d) == pp(%d) %Ld", + xfs_warn(mp, "%s: thispa(%d) == pp(%d) %lld", __func__, j, i, (unsigned long long)be64_to_cpu(*thispa)); - panic("%s: ptrs are equal in node\n", + xfs_err(mp, "%s: ptrs are equal in node\n", __func__); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); } } } @@ -352,35 +339,32 @@ xfs_check_block( */ STATIC void xfs_bmap_check_leaf_extents( - xfs_btree_cur_t *cur, /* btree cursor or null */ + struct xfs_btree_cur *cur, /* btree cursor or null */ xfs_inode_t *ip, /* incore inode pointer */ int whichfork) /* data or attr fork */ { + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_block *block; /* current btree block */ xfs_fsblock_t bno; /* block # of "block" */ - xfs_buf_t *bp; /* buffer for "block" */ + struct xfs_buf *bp; /* buffer for "block" */ int error; /* error return value */ xfs_extnum_t i=0, j; /* index into the extents list */ - 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 */ xfs_bmbt_rec_t *ep; /* pointer to current extent */ xfs_bmbt_rec_t last = {0, 0}; /* last extent in prev block */ xfs_bmbt_rec_t *nextp; /* pointer to next extent */ int bp_release = 0; - if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE) { + if (ifp->if_format != XFS_DINODE_FMT_BTREE) return; - } /* skip large extent count inodes */ - if (ip->i_d.di_nextents > 10000) + if (ip->i_df.if_nextents > 10000) return; bno = NULLFSBLOCK; - mp = ip->i_mount; - ifp = XFS_IFORK_PTR(ip, whichfork); block = ifp->if_broot; /* * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out. @@ -388,7 +372,7 @@ xfs_bmap_check_leaf_extents( level = be16_to_cpu(block->bb_level); ASSERT(level > 0); xfs_check_block(block, mp, 1, ifp->if_broot_bytes); - pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes); + pp = xfs_bmap_broot_ptr_addr(mp, block, 1, ifp->if_broot_bytes); bno = be64_to_cpu(*pp); ASSERT(bno != NULLFSBLOCK); @@ -405,9 +389,9 @@ xfs_bmap_check_leaf_extents( bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno)); if (!bp) { bp_release = 1; - error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp, - XFS_BMAP_BTREE_REF, - &xfs_bmbt_buf_ops); + error = xfs_bmap_read_buf(mp, NULL, bno, &bp); + if (xfs_metadata_is_sick(error)) + xfs_btree_mark_sick(cur); if (error) goto error_norelse; } @@ -421,10 +405,13 @@ xfs_bmap_check_leaf_extents( */ xfs_check_block(block, mp, 0, 0); - pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]); + pp = xfs_bmbt_ptr_addr(mp, block, 1, mp->m_bmap_dmxr[1]); bno = be64_to_cpu(*pp); - XFS_WANT_CORRUPTED_GOTO(mp, - XFS_FSB_SANITY_CHECK(mp, bno), error0); + if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, bno))) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto error0; + } if (bp_release) { bp_release = 0; xfs_trans_brelse(NULL, bp); @@ -458,14 +445,14 @@ xfs_bmap_check_leaf_extents( * conform with the first entry in this one. */ - ep = XFS_BMBT_REC_ADDR(mp, block, 1); + ep = xfs_bmbt_rec_addr(mp, block, 1); if (i) { ASSERT(xfs_bmbt_disk_get_startoff(&last) + xfs_bmbt_disk_get_blockcount(&last) <= xfs_bmbt_disk_get_startoff(ep)); } for (j = 1; j < num_recs; j++) { - nextp = XFS_BMBT_REC_ADDR(mp, block, j + 1); + nextp = xfs_bmbt_rec_addr(mp, block, j + 1); ASSERT(xfs_bmbt_disk_get_startoff(ep) + xfs_bmbt_disk_get_blockcount(ep) <= xfs_bmbt_disk_get_startoff(nextp)); @@ -489,9 +476,9 @@ xfs_bmap_check_leaf_extents( bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno)); if (!bp) { bp_release = 1; - error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp, - XFS_BMAP_BTREE_REF, - &xfs_bmbt_buf_ops); + error = xfs_bmap_read_buf(mp, NULL, bno, &bp); + if (xfs_metadata_is_sick(error)) + xfs_btree_mark_sick(cur); if (error) goto error_norelse; } @@ -505,38 +492,14 @@ error0: if (bp_release) xfs_trans_brelse(NULL, bp); error_norelse: - xfs_warn(mp, "%s: BAD after btree leaves for %d extents", + xfs_warn(mp, "%s: BAD after btree leaves for %llu extents", __func__, i); - panic("%s: CORRUPTED BTREE OR SOMETHING", __func__); + xfs_err(mp, "%s: CORRUPTED BTREE OR SOMETHING", __func__); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return; } /* - * Add bmap trace insert entries for all the contents of the extent records. - */ -void -xfs_bmap_trace_exlist( - xfs_inode_t *ip, /* incore inode pointer */ - xfs_extnum_t cnt, /* count of entries in the list */ - int whichfork, /* data or attr or cow fork */ - unsigned long caller_ip) -{ - xfs_extnum_t idx; /* extent record index */ - xfs_ifork_t *ifp; /* inode fork pointer */ - int state = 0; - - if (whichfork == XFS_ATTR_FORK) - state |= BMAP_ATTRFORK; - else if (whichfork == XFS_COW_FORK) - state |= BMAP_COWFORK; - - ifp = XFS_IFORK_PTR(ip, whichfork); - ASSERT(cnt == xfs_iext_count(ifp)); - for (idx = 0; idx < cnt; idx++) - trace_xfs_extlist(ip, idx, state, caller_ip); -} - -/* * Validate that the bmbt_irecs being returned from bmapi are valid * given the caller's original parameters. Specifically check the * ranges of the returned irecs to ensure that they only extend beyond @@ -546,7 +509,7 @@ STATIC void xfs_bmap_validate_ret( xfs_fileoff_t bno, xfs_filblks_t len, - int flags, + uint32_t flags, xfs_bmbt_irec_t *mval, int nmap, int ret_nmap) @@ -579,119 +542,81 @@ xfs_bmap_validate_ret( #else #define xfs_bmap_check_leaf_extents(cur, ip, whichfork) do { } while (0) -#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap) +#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap) do { } while (0) #endif /* DEBUG */ /* - * bmap free list manipulation functions - */ - -/* - * Add the extent to the list of extents to be free at transaction end. - * The list is maintained sorted (by block number). - */ -void -xfs_bmap_add_free( - struct xfs_mount *mp, - struct xfs_defer_ops *dfops, - xfs_fsblock_t bno, - xfs_filblks_t len, - struct xfs_owner_info *oinfo) -{ - struct xfs_extent_free_item *new; /* new element */ -#ifdef DEBUG - xfs_agnumber_t agno; - xfs_agblock_t agbno; - - ASSERT(bno != NULLFSBLOCK); - ASSERT(len > 0); - ASSERT(len <= MAXEXTLEN); - ASSERT(!isnullstartblock(bno)); - agno = XFS_FSB_TO_AGNO(mp, bno); - agbno = XFS_FSB_TO_AGBNO(mp, bno); - ASSERT(agno < mp->m_sb.sb_agcount); - ASSERT(agbno < mp->m_sb.sb_agblocks); - ASSERT(len < mp->m_sb.sb_agblocks); - ASSERT(agbno + len <= mp->m_sb.sb_agblocks); -#endif - ASSERT(xfs_bmap_free_item_zone != NULL); - - new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP); - new->xefi_startblock = bno; - new->xefi_blockcount = (xfs_extlen_t)len; - if (oinfo) - new->xefi_oinfo = *oinfo; - else - xfs_rmap_skip_owner_update(&new->xefi_oinfo); - trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(mp, bno), 0, - XFS_FSB_TO_AGBNO(mp, bno), len); - xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list); -} - -/* * Inode fork format manipulation functions */ /* - * Transform a btree format file with only one leaf node, where the - * extents list will fit in the inode, into an extents format file. - * Since the file extents are already in-core, all we have to do is - * give up the space for the btree root and pitch the leaf block. + * Convert the inode format to extent format if it currently is in btree format, + * but the extent list is small enough that it fits into the extent format. + * + * Since the extents are already in-core, all we have to do is give up the space + * for the btree root and pitch the leaf block. */ STATIC int /* error */ xfs_bmap_btree_to_extents( - xfs_trans_t *tp, /* transaction pointer */ - xfs_inode_t *ip, /* incore inode pointer */ - xfs_btree_cur_t *cur, /* btree cursor */ + struct xfs_trans *tp, /* transaction pointer */ + struct xfs_inode *ip, /* incore inode pointer */ + struct xfs_btree_cur *cur, /* btree cursor */ int *logflagsp, /* inode logging flags */ int whichfork) /* data or attr fork */ { - /* REFERENCED */ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_mount *mp = ip->i_mount; + struct xfs_btree_block *rblock = ifp->if_broot; struct xfs_btree_block *cblock;/* child btree block */ xfs_fsblock_t cbno; /* child block number */ - xfs_buf_t *cbp; /* child block's buffer */ + struct xfs_buf *cbp; /* child block's buffer */ int error; /* error return value */ - xfs_ifork_t *ifp; /* inode fork data */ - xfs_mount_t *mp; /* mount point structure */ __be64 *pp; /* ptr to block address */ - struct xfs_btree_block *rblock;/* root btree block */ struct xfs_owner_info oinfo; - mp = ip->i_mount; - ifp = XFS_IFORK_PTR(ip, whichfork); + /* check if we actually need the extent format first: */ + if (!xfs_bmap_wants_extents(ip, whichfork)) + return 0; + + ASSERT(cur); ASSERT(whichfork != XFS_COW_FORK); - ASSERT(ifp->if_flags & XFS_IFEXTENTS); - ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE); - rblock = ifp->if_broot; + ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE); ASSERT(be16_to_cpu(rblock->bb_level) == 1); ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1); - ASSERT(xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0) == 1); - pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes); + ASSERT(xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false) == 1); + + pp = xfs_bmap_broot_ptr_addr(mp, rblock, 1, ifp->if_broot_bytes); cbno = be64_to_cpu(*pp); - *logflagsp = 0; #ifdef DEBUG - if ((error = xfs_btree_check_lptr(cur, cbno, 1))) - return error; + if (XFS_IS_CORRUPT(cur->bc_mp, !xfs_verify_fsbno(mp, cbno))) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } #endif - error = xfs_btree_read_bufl(mp, tp, cbno, 0, &cbp, XFS_BMAP_BTREE_REF, - &xfs_bmbt_buf_ops); + error = xfs_bmap_read_buf(mp, tp, cbno, &cbp); + if (xfs_metadata_is_sick(error)) + xfs_btree_mark_sick(cur); if (error) return error; cblock = XFS_BUF_TO_BLOCK(cbp); if ((error = xfs_btree_check_block(cur, cblock, 0, cbp))) return error; + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork); - xfs_bmap_add_free(mp, cur->bc_private.b.dfops, cbno, 1, &oinfo); - ip->i_d.di_nblocks--; + error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo, + XFS_AG_RESV_NONE, 0); + if (error) + return error; + + ip->i_nblocks--; xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); xfs_trans_binval(tp, cbp); - if (cur->bc_bufs[0] == cbp) - cur->bc_bufs[0] = NULL; - xfs_iroot_realloc(ip, -1, whichfork); + if (cur->bc_levels[0].bp == cbp) + cur->bc_levels[0].bp = NULL; + xfs_bmap_broot_realloc(ip, whichfork, 0); ASSERT(ifp->if_broot == NULL); - ASSERT((ifp->if_flags & XFS_IFBROOT) == 0); - XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); - *logflagsp = XFS_ILOG_CORE | xfs_ilog_fext(whichfork); + ifp->if_format = XFS_DINODE_FMT_EXTENTS; + *logflagsp |= XFS_ILOG_CORE | xfs_ilog_fext(whichfork); return 0; } @@ -701,127 +626,106 @@ xfs_bmap_btree_to_extents( */ STATIC int /* error */ xfs_bmap_extents_to_btree( - xfs_trans_t *tp, /* transaction pointer */ - xfs_inode_t *ip, /* incore inode pointer */ - xfs_fsblock_t *firstblock, /* first-block-allocated */ - struct xfs_defer_ops *dfops, /* blocks freed in xaction */ - xfs_btree_cur_t **curp, /* cursor returned to caller */ + struct xfs_trans *tp, /* transaction pointer */ + struct xfs_inode *ip, /* incore inode pointer */ + struct xfs_btree_cur **curp, /* cursor returned to caller */ int wasdel, /* converting a delayed alloc */ int *logflagsp, /* inode logging flags */ int whichfork) /* data or attr fork */ { struct xfs_btree_block *ablock; /* allocated (child) bt block */ - xfs_buf_t *abp; /* buffer for ablock */ - xfs_alloc_arg_t args; /* allocation arguments */ - xfs_bmbt_rec_t *arp; /* child record pointer */ + struct xfs_buf *abp; /* buffer for ablock */ + struct xfs_alloc_arg args; /* allocation arguments */ + struct xfs_bmbt_rec *arp; /* child record pointer */ struct xfs_btree_block *block; /* btree root block */ - xfs_btree_cur_t *cur; /* bmap btree cursor */ - xfs_bmbt_rec_host_t *ep; /* extent record pointer */ + struct xfs_btree_cur *cur; /* bmap btree cursor */ int error; /* error return value */ - xfs_extnum_t i, cnt; /* extent record index */ - xfs_ifork_t *ifp; /* inode fork pointer */ - xfs_bmbt_key_t *kp; /* root block key pointer */ - xfs_mount_t *mp; /* mount structure */ - xfs_extnum_t nextents; /* number of file extents */ + struct xfs_ifork *ifp; /* inode fork pointer */ + struct xfs_bmbt_key *kp; /* root block key pointer */ + struct xfs_mount *mp; /* mount structure */ xfs_bmbt_ptr_t *pp; /* root block address pointer */ + struct xfs_iext_cursor icur; + struct xfs_bmbt_irec rec; + xfs_extnum_t cnt = 0; mp = ip->i_mount; ASSERT(whichfork != XFS_COW_FORK); - ifp = XFS_IFORK_PTR(ip, whichfork); - ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS); + ifp = xfs_ifork_ptr(ip, whichfork); + ASSERT(ifp->if_format == XFS_DINODE_FMT_EXTENTS); /* - * Make space in the inode incore. + * Make space in the inode incore. This needs to be undone if we fail + * to expand the root. */ - xfs_iroot_realloc(ip, 1, whichfork); - ifp->if_flags |= XFS_IFBROOT; + block = xfs_bmap_broot_realloc(ip, whichfork, 1); /* * Fill in the root. */ - block = ifp->if_broot; - xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL, - XFS_BTNUM_BMAP, 1, 1, ip->i_ino, - XFS_BTREE_LONG_PTRS); + xfs_bmbt_init_block(ip, block, NULL, 1, 1); /* * Need a cursor. Can't allocate until bb_level is filled in. */ cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); - cur->bc_private.b.firstblock = *firstblock; - cur->bc_private.b.dfops = dfops; - cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0; + if (wasdel) + cur->bc_flags |= XFS_BTREE_BMBT_WASDEL; /* * Convert to a btree with two levels, one record in root. */ - XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_BTREE); + ifp->if_format = XFS_DINODE_FMT_BTREE; memset(&args, 0, sizeof(args)); args.tp = tp; args.mp = mp; xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork); - args.firstblock = *firstblock; - if (*firstblock == NULLFSBLOCK) { - args.type = XFS_ALLOCTYPE_START_BNO; - args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino); - } else if (dfops->dop_low) { - args.type = XFS_ALLOCTYPE_START_BNO; - args.fsbno = *firstblock; - } else { - args.type = XFS_ALLOCTYPE_NEAR_BNO; - args.fsbno = *firstblock; - } + args.minlen = args.maxlen = args.prod = 1; args.wasdel = wasdel; *logflagsp = 0; - if ((error = xfs_alloc_vextent(&args))) { - xfs_iroot_realloc(ip, -1, whichfork); - xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); - return error; - } + error = xfs_alloc_vextent_start_ag(&args, + XFS_INO_TO_FSB(mp, ip->i_ino)); + if (error) + goto out_root_realloc; - if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { - xfs_iroot_realloc(ip, -1, whichfork); - xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); - return -ENOSPC; - } /* * Allocation can't fail, the space was reserved. */ - ASSERT(*firstblock == NULLFSBLOCK || - args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock)); - *firstblock = cur->bc_private.b.firstblock = args.fsbno; - cur->bc_private.b.allocated++; - ip->i_d.di_nblocks++; + if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { + error = -ENOSPC; + goto out_root_realloc; + } + + cur->bc_bmap.allocated++; + ip->i_nblocks++; xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L); - abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0); + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, + XFS_FSB_TO_DADDR(mp, args.fsbno), + mp->m_bsize, 0, &abp); + if (error) + goto out_unreserve_dquot; + /* * Fill in the child block. */ - abp->b_ops = &xfs_bmbt_buf_ops; ablock = XFS_BUF_TO_BLOCK(abp); - xfs_btree_init_block_int(mp, ablock, abp->b_bn, - XFS_BTNUM_BMAP, 0, 0, ip->i_ino, - XFS_BTREE_LONG_PTRS); - - arp = XFS_BMBT_REC_ADDR(mp, ablock, 1); - nextents = xfs_iext_count(ifp); - for (cnt = i = 0; i < nextents; i++) { - ep = xfs_iext_get_ext(ifp, i); - if (!isnullstartblock(xfs_bmbt_get_startblock(ep))) { - arp->l0 = cpu_to_be64(ep->l0); - arp->l1 = cpu_to_be64(ep->l1); - arp++; cnt++; - } + xfs_bmbt_init_block(ip, ablock, abp, 0, 0); + + for_each_xfs_iext(ifp, &icur, &rec) { + if (isnullstartblock(rec.br_startblock)) + continue; + arp = xfs_bmbt_rec_addr(mp, ablock, 1 + cnt); + xfs_bmbt_disk_set_all(arp, &rec); + cnt++; } - ASSERT(cnt == XFS_IFORK_NEXTENTS(ip, whichfork)); + ASSERT(cnt == ifp->if_nextents); xfs_btree_set_numrecs(ablock, cnt); /* * Fill in the root key and pointer. */ - kp = XFS_BMBT_KEY_ADDR(mp, block, 1); - arp = XFS_BMBT_REC_ADDR(mp, ablock, 1); + kp = xfs_bmbt_key_addr(mp, block, 1); + arp = xfs_bmbt_rec_addr(mp, ablock, 1); kp->br_startoff = cpu_to_be64(xfs_bmbt_disk_get_startoff(arp)); - pp = XFS_BMBT_PTR_ADDR(mp, block, 1, xfs_bmbt_get_maxrecs(cur, + pp = xfs_bmbt_ptr_addr(mp, block, 1, xfs_bmbt_get_maxrecs(cur, be16_to_cpu(block->bb_level))); *pp = cpu_to_be64(args.fsbno); @@ -835,6 +739,16 @@ xfs_bmap_extents_to_btree( *curp = cur; *logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork); return 0; + +out_unreserve_dquot: + xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); +out_root_realloc: + xfs_bmap_broot_realloc(ip, whichfork, 0); + ifp->if_format = XFS_DINODE_FMT_EXTENTS; + ASSERT(ifp->if_broot == NULL); + xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); + + return error; } /* @@ -845,88 +759,88 @@ xfs_bmap_extents_to_btree( */ void xfs_bmap_local_to_extents_empty( + struct xfs_trans *tp, struct xfs_inode *ip, int whichfork) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(whichfork != XFS_COW_FORK); - ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL); + ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); ASSERT(ifp->if_bytes == 0); - ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0); + ASSERT(ifp->if_nextents == 0); 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); + ifp->if_data = NULL; + ifp->if_height = 0; + ifp->if_format = XFS_DINODE_FMT_EXTENTS; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } -STATIC int /* error */ +int /* error */ xfs_bmap_local_to_extents( xfs_trans_t *tp, /* transaction pointer */ xfs_inode_t *ip, /* incore inode pointer */ - xfs_fsblock_t *firstblock, /* first block allocated in xaction */ xfs_extlen_t total, /* total blocks needed by transaction */ int *logflagsp, /* inode logging flags */ int whichfork, void (*init_fn)(struct xfs_trans *tp, struct xfs_buf *bp, struct xfs_inode *ip, - struct xfs_ifork *ifp)) + struct xfs_ifork *ifp, void *priv), + void *priv) { int error = 0; int flags; /* logging flags returned */ - xfs_ifork_t *ifp; /* inode fork pointer */ + struct xfs_ifork *ifp; /* inode fork pointer */ xfs_alloc_arg_t args; /* allocation arguments */ - xfs_buf_t *bp; /* buffer for extent block */ - xfs_bmbt_rec_host_t *ep; /* extent record pointer */ + struct xfs_buf *bp; /* buffer for extent block */ + struct xfs_bmbt_irec rec; + struct xfs_iext_cursor icur; /* * We don't want to deal with the case of keeping inode data inline yet. * So sending the data fork of a regular inode is invalid. */ ASSERT(!(S_ISREG(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK)); - ifp = XFS_IFORK_PTR(ip, whichfork); - ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL); + ifp = xfs_ifork_ptr(ip, whichfork); + ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); if (!ifp->if_bytes) { - xfs_bmap_local_to_extents_empty(ip, whichfork); + xfs_bmap_local_to_extents_empty(tp, ip, whichfork); flags = XFS_ILOG_CORE; goto done; } flags = 0; error = 0; - ASSERT((ifp->if_flags & (XFS_IFINLINE|XFS_IFEXTENTS|XFS_IFEXTIREC)) == - XFS_IFINLINE); memset(&args, 0, sizeof(args)); args.tp = tp; args.mp = ip->i_mount; + args.total = total; + args.minlen = args.maxlen = args.prod = 1; xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0); - args.firstblock = *firstblock; + /* * Allocate a block. We know we need only one, since the * file currently fits in an inode. */ - if (*firstblock == NULLFSBLOCK) { - args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino); - args.type = XFS_ALLOCTYPE_START_BNO; - } else { - args.fsbno = *firstblock; - args.type = XFS_ALLOCTYPE_NEAR_BNO; - } args.total = total; args.minlen = args.maxlen = args.prod = 1; - error = xfs_alloc_vextent(&args); + error = xfs_alloc_vextent_start_ag(&args, + XFS_INO_TO_FSB(args.mp, ip->i_ino)); if (error) goto done; /* Can't fail, the space was reserved. */ ASSERT(args.fsbno != NULLFSBLOCK); ASSERT(args.len == 1); - *firstblock = args.fsbno; - bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0); + error = xfs_trans_get_buf(tp, args.mp->m_ddev_targp, + XFS_FSB_TO_DADDR(args.mp, args.fsbno), + args.mp->m_bsize, 0, &bp); + if (error) + goto done; /* * Initialize the block, copy the data and log the remote buffer. @@ -936,23 +850,26 @@ xfs_bmap_local_to_extents( * log here. Note that init_fn must also set the buffer log item type * correctly. */ - init_fn(tp, bp, ip, ifp); + init_fn(tp, bp, ip, ifp, priv); /* account for the change in fork size */ xfs_idata_realloc(ip, -ifp->if_bytes, whichfork); - xfs_bmap_local_to_extents_empty(ip, whichfork); + xfs_bmap_local_to_extents_empty(tp, ip, whichfork); flags |= XFS_ILOG_CORE; - xfs_iext_add(ifp, 0, 1); - ep = xfs_iext_get_ext(ifp, 0); - xfs_bmbt_set_allf(ep, 0, args.fsbno, 1, XFS_EXT_NORM); - trace_xfs_bmap_post_update(ip, 0, - whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0, - _THIS_IP_); - XFS_IFORK_NEXT_SET(ip, whichfork, 1); - ip->i_d.di_nblocks = 1; - xfs_trans_mod_dquot_byino(tp, ip, - XFS_TRANS_DQ_BCOUNT, 1L); + ifp->if_data = NULL; + ifp->if_height = 0; + + rec.br_startoff = 0; + rec.br_startblock = args.fsbno; + rec.br_blockcount = 1; + rec.br_state = XFS_EXT_NORM; + xfs_iext_first(ifp, &icur); + xfs_iext_insert(ip, &icur, &rec, 0); + + ifp->if_nextents = 1; + ip->i_nblocks = 1; + xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L); flags |= xfs_ilog_fext(whichfork); done: @@ -967,34 +884,36 @@ STATIC int /* error */ xfs_bmap_add_attrfork_btree( xfs_trans_t *tp, /* transaction pointer */ xfs_inode_t *ip, /* incore inode pointer */ - xfs_fsblock_t *firstblock, /* first block allocated */ - struct xfs_defer_ops *dfops, /* blocks to free at commit */ int *flags) /* inode logging flags */ { - xfs_btree_cur_t *cur; /* btree cursor */ + struct xfs_btree_block *block = ip->i_df.if_broot; + struct xfs_btree_cur *cur; /* btree cursor */ int error; /* error return value */ xfs_mount_t *mp; /* file system mount struct */ int stat; /* newroot status */ mp = ip->i_mount; - if (ip->i_df.if_broot_bytes <= XFS_IFORK_DSIZE(ip)) + + if (xfs_bmap_bmdr_space(block) <= xfs_inode_data_fork_size(ip)) *flags |= XFS_ILOG_DBROOT; else { cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK); - cur->bc_private.b.dfops = dfops; - cur->bc_private.b.firstblock = *firstblock; - if ((error = xfs_bmbt_lookup_ge(cur, 0, 0, 0, &stat))) + error = xfs_bmbt_lookup_first(cur, &stat); + if (error) goto error0; /* must be at least one entry */ - XFS_WANT_CORRUPTED_GOTO(mp, stat == 1, error0); + if (XFS_IS_CORRUPT(mp, stat != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto error0; + } if ((error = xfs_btree_new_iroot(cur, flags, &stat))) goto error0; if (stat == 0) { xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); return -ENOSPC; } - *firstblock = cur->bc_private.b.firstblock; - cur->bc_private.b.allocated = 0; + cur->bc_bmap.allocated = 0; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); } return 0; @@ -1008,24 +927,22 @@ error0: */ STATIC int /* error */ xfs_bmap_add_attrfork_extents( - xfs_trans_t *tp, /* transaction pointer */ - xfs_inode_t *ip, /* incore inode pointer */ - xfs_fsblock_t *firstblock, /* first block allocated */ - struct xfs_defer_ops *dfops, /* blocks to free at commit */ + struct xfs_trans *tp, /* transaction pointer */ + struct xfs_inode *ip, /* incore inode pointer */ int *flags) /* inode logging flags */ { - xfs_btree_cur_t *cur; /* bmap btree cursor */ + struct xfs_btree_cur *cur; /* bmap btree cursor */ int error; /* error return value */ - if (ip->i_d.di_nextents * sizeof(xfs_bmbt_rec_t) <= XFS_IFORK_DSIZE(ip)) + if (ip->i_df.if_nextents * sizeof(struct xfs_bmbt_rec) <= + xfs_inode_data_fork_size(ip)) return 0; cur = NULL; - error = xfs_bmap_extents_to_btree(tp, ip, firstblock, dfops, &cur, 0, - flags, XFS_DATA_FORK); + error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, flags, + XFS_DATA_FORK); if (cur) { - cur->bc_private.b.allocated = 0; - xfs_btree_del_cursor(cur, - error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); + cur->bc_bmap.allocated = 0; + xfs_btree_del_cursor(cur, error); } return error; } @@ -1043,132 +960,102 @@ xfs_bmap_add_attrfork_extents( */ STATIC int /* error */ xfs_bmap_add_attrfork_local( - xfs_trans_t *tp, /* transaction pointer */ - xfs_inode_t *ip, /* incore inode pointer */ - xfs_fsblock_t *firstblock, /* first block allocated */ - struct xfs_defer_ops *dfops, /* blocks to free at commit */ + struct xfs_trans *tp, /* transaction pointer */ + struct xfs_inode *ip, /* incore inode pointer */ int *flags) /* inode logging flags */ { - xfs_da_args_t dargs; /* args for dir/attr code */ + struct xfs_da_args dargs; /* args for dir/attr code */ - if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip)) + if (ip->i_df.if_bytes <= xfs_inode_data_fork_size(ip)) return 0; if (S_ISDIR(VFS_I(ip)->i_mode)) { memset(&dargs, 0, sizeof(dargs)); dargs.geo = ip->i_mount->m_dir_geo; dargs.dp = ip; - dargs.firstblock = firstblock; - dargs.dfops = dfops; dargs.total = dargs.geo->fsbcount; dargs.whichfork = XFS_DATA_FORK; dargs.trans = tp; + dargs.owner = ip->i_ino; return xfs_dir2_sf_to_block(&dargs); } if (S_ISLNK(VFS_I(ip)->i_mode)) - return xfs_bmap_local_to_extents(tp, ip, firstblock, 1, - flags, XFS_DATA_FORK, - xfs_symlink_local_to_remote); + return xfs_bmap_local_to_extents(tp, ip, 1, flags, + XFS_DATA_FORK, xfs_symlink_local_to_remote, + NULL); /* should only be called for types that support local format data */ ASSERT(0); + xfs_bmap_mark_sick(ip, XFS_ATTR_FORK); return -EFSCORRUPTED; } /* - * Convert inode from non-attributed to attributed. - * Must not be in a transaction, ip must not be locked. + * Set an inode attr fork offset based on the format of the data fork. */ -int /* error code */ -xfs_bmap_add_attrfork( - xfs_inode_t *ip, /* incore inode pointer */ - int size, /* space new attribute needs */ - int rsvd) /* xact may use reserved blks */ +static int +xfs_bmap_set_attrforkoff( + struct xfs_inode *ip, + int size) { - xfs_fsblock_t firstblock; /* 1st block/ag allocated */ - struct xfs_defer_ops dfops; /* freed extent records */ - xfs_mount_t *mp; /* mount structure */ - xfs_trans_t *tp; /* transaction pointer */ - int blks; /* space reservation */ - int version = 1; /* superblock attr version */ - int logflags; /* logging flags */ - int error; /* error return value */ + int default_size = xfs_default_attroffset(ip) >> 3; - ASSERT(XFS_IFORK_Q(ip) == 0); - - mp = ip->i_mount; - ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); - - blks = XFS_ADDAFORK_SPACE_RES(mp); - - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_addafork, blks, 0, - rsvd ? XFS_TRANS_RESERVE : 0, &tp); - if (error) - return error; - - 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) - goto trans_cancel; - if (XFS_IFORK_Q(ip)) - goto trans_cancel; - if (ip->i_d.di_anextents != 0) { - error = -EFSCORRUPTED; - goto trans_cancel; - } - if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS) { - /* - * For inodes coming from pre-6.2 filesystems. - */ - ASSERT(ip->i_d.di_aformat == 0); - ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS; - } - - xfs_trans_ijoin(tp, ip, 0); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - - switch (ip->i_d.di_format) { + switch (ip->i_df.if_format) { case XFS_DINODE_FMT_DEV: - ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3; - break; - case XFS_DINODE_FMT_UUID: - ip->i_d.di_forkoff = roundup(sizeof(uuid_t), 8) >> 3; + ip->i_forkoff = default_size; break; case XFS_DINODE_FMT_LOCAL: case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: - ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size); - if (!ip->i_d.di_forkoff) - ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3; - else if (mp->m_flags & XFS_MOUNT_ATTR2) - version = 2; + ip->i_forkoff = xfs_attr_shortform_bytesfit(ip, size); + if (!ip->i_forkoff) + ip->i_forkoff = default_size; break; default: ASSERT(0); - error = -EINVAL; - goto trans_cancel; + return -EINVAL; } - ASSERT(ip->i_afp == NULL); - ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP); - ip->i_afp->if_flags = XFS_IFEXTENTS; + return 0; +} + +/* + * Convert inode from non-attributed to attributed. Caller must hold the + * ILOCK_EXCL and the file cannot have an attr fork. + */ +int /* error code */ +xfs_bmap_add_attrfork( + struct xfs_trans *tp, + struct xfs_inode *ip, /* incore inode pointer */ + int size, /* space new attribute needs */ + int rsvd) /* xact may use reserved blks */ +{ + struct xfs_mount *mp = tp->t_mountp; + int logflags; /* logging flags */ + int error; /* error return value */ + + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); + if (!xfs_is_metadir_inode(ip)) + ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); + ASSERT(!xfs_inode_has_attr_fork(ip)); + + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + error = xfs_bmap_set_attrforkoff(ip, size); + if (error) + return error; + + xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0); logflags = 0; - xfs_defer_init(&dfops, &firstblock); - switch (ip->i_d.di_format) { + switch (ip->i_df.if_format) { case XFS_DINODE_FMT_LOCAL: - error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &dfops, - &logflags); + error = xfs_bmap_add_attrfork_local(tp, ip, &logflags); break; case XFS_DINODE_FMT_EXTENTS: - error = xfs_bmap_add_attrfork_extents(tp, ip, &firstblock, - &dfops, &logflags); + error = xfs_bmap_add_attrfork_extents(tp, ip, &logflags); break; case XFS_DINODE_FMT_BTREE: - error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock, &dfops, - &logflags); + error = xfs_bmap_add_attrfork_btree(tp, ip, &logflags); break; default: error = 0; @@ -1177,18 +1064,14 @@ xfs_bmap_add_attrfork( if (logflags) xfs_trans_log_inode(tp, ip, logflags); if (error) - goto bmap_cancel; - if (!xfs_sb_version_hasattr(&mp->m_sb) || - (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) { + return error; + if (!xfs_has_attr(mp)) { bool log_sb = false; spin_lock(&mp->m_sb_lock); - if (!xfs_sb_version_hasattr(&mp->m_sb)) { - xfs_sb_version_addattr(&mp->m_sb); - log_sb = true; - } - if (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2) { - xfs_sb_version_addattr2(&mp->m_sb); + if (!xfs_has_attr(mp)) { + xfs_add_attr(mp); + xfs_add_attr2(mp); log_sb = true; } spin_unlock(&mp->m_sb_lock); @@ -1196,195 +1079,196 @@ xfs_bmap_add_attrfork( xfs_log_sb(tp); } - error = xfs_defer_finish(&tp, &dfops, NULL); - if (error) - goto bmap_cancel; - error = xfs_trans_commit(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - return error; - -bmap_cancel: - xfs_defer_cancel(&dfops); -trans_cancel: - xfs_trans_cancel(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - return error; + return 0; } /* * Internal and external extent tree search functions. */ +struct xfs_iread_state { + struct xfs_iext_cursor icur; + xfs_extnum_t loaded; +}; + +int +xfs_bmap_complain_bad_rec( + struct xfs_inode *ip, + int whichfork, + xfs_failaddr_t fa, + const struct xfs_bmbt_irec *irec) +{ + struct xfs_mount *mp = ip->i_mount; + const char *forkname; + + switch (whichfork) { + case XFS_DATA_FORK: forkname = "data"; break; + case XFS_ATTR_FORK: forkname = "attr"; break; + case XFS_COW_FORK: forkname = "CoW"; break; + default: forkname = "???"; break; + } + + xfs_warn(mp, + "Bmap BTree record corruption in inode 0x%llx %s fork detected at %pS!", + ip->i_ino, forkname, fa); + xfs_warn(mp, + "Offset 0x%llx, start block 0x%llx, block count 0x%llx state 0x%x", + irec->br_startoff, irec->br_startblock, irec->br_blockcount, + irec->br_state); + + return -EFSCORRUPTED; +} + +/* Stuff every bmbt record from this block into the incore extent map. */ +static int +xfs_iread_bmbt_block( + struct xfs_btree_cur *cur, + int level, + void *priv) +{ + struct xfs_iread_state *ir = priv; + struct xfs_mount *mp = cur->bc_mp; + struct xfs_inode *ip = cur->bc_ino.ip; + struct xfs_btree_block *block; + struct xfs_buf *bp; + struct xfs_bmbt_rec *frp; + xfs_extnum_t num_recs; + xfs_extnum_t j; + int whichfork = cur->bc_ino.whichfork; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + + block = xfs_btree_get_block(cur, level, &bp); + + /* Abort if we find more records than nextents. */ + num_recs = xfs_btree_get_numrecs(block); + if (unlikely(ir->loaded + num_recs > ifp->if_nextents)) { + xfs_warn(ip->i_mount, "corrupt dinode %llu, (btree extents).", + (unsigned long long)ip->i_ino); + xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, block, + sizeof(*block), __this_address); + xfs_bmap_mark_sick(ip, whichfork); + return -EFSCORRUPTED; + } + + /* Copy records into the incore cache. */ + frp = xfs_bmbt_rec_addr(mp, block, 1); + for (j = 0; j < num_recs; j++, frp++, ir->loaded++) { + struct xfs_bmbt_irec new; + xfs_failaddr_t fa; + + xfs_bmbt_disk_get_all(frp, &new); + fa = xfs_bmap_validate_extent(ip, whichfork, &new); + if (fa) { + xfs_inode_verifier_error(ip, -EFSCORRUPTED, + "xfs_iread_extents(2)", frp, + sizeof(*frp), fa); + xfs_bmap_mark_sick(ip, whichfork); + return xfs_bmap_complain_bad_rec(ip, whichfork, fa, + &new); + } + xfs_iext_insert(ip, &ir->icur, &new, + xfs_bmap_fork_to_state(whichfork)); + trace_xfs_read_extent(ip, &ir->icur, + xfs_bmap_fork_to_state(whichfork), _THIS_IP_); + xfs_iext_next(ifp, &ir->icur); + } + + return 0; +} + /* - * Read in the extents to if_extents. - * All inode fields are set up by caller, we just traverse the btree - * and copy the records in. If the file system cannot contain unwritten - * extents, the records are checked for no "state" flags. + * Read in extents from a btree-format inode. */ -int /* error */ -xfs_bmap_read_extents( - xfs_trans_t *tp, /* transaction pointer */ - xfs_inode_t *ip, /* incore inode */ - int whichfork) /* data or attr fork */ +int +xfs_iread_extents( + struct xfs_trans *tp, + struct xfs_inode *ip, + int whichfork) { - struct xfs_btree_block *block; /* current btree block */ - xfs_fsblock_t bno; /* block # of "block" */ - xfs_buf_t *bp; /* buffer for "block" */ - int error; /* error return value */ - xfs_extnum_t i, j; /* index into the extents list */ - 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 */ - /* REFERENCED */ - xfs_extnum_t room; /* number of entries there's room for */ + struct xfs_iread_state ir; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_mount *mp = ip->i_mount; + struct xfs_btree_cur *cur; + int error; - mp = ip->i_mount; - ifp = XFS_IFORK_PTR(ip, whichfork); - block = ifp->if_broot; - /* - * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out. - */ - 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); + if (!xfs_need_iread_extents(ifp)) + return 0; - /* - * Go down the tree until leaf level is reached, following the first - * pointer (leftmost) at each level. - */ - while (level-- > 0) { - error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, - XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); - if (error) - return error; - block = XFS_BUF_TO_BLOCK(bp); - if (level == 0) - break; - pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]); - bno = be64_to_cpu(*pp); - XFS_WANT_CORRUPTED_GOTO(mp, - XFS_FSB_SANITY_CHECK(mp, bno), error0); - xfs_trans_brelse(tp, bp); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); + + ir.loaded = 0; + xfs_iext_first(ifp, &ir.icur); + cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); + error = xfs_btree_visit_blocks(cur, xfs_iread_bmbt_block, + XFS_BTREE_VISIT_RECORDS, &ir); + xfs_btree_del_cursor(cur, error); + if (error) + goto out; + + if (XFS_IS_CORRUPT(mp, ir.loaded != ifp->if_nextents)) { + xfs_bmap_mark_sick(ip, whichfork); + error = -EFSCORRUPTED; + goto out; } + ASSERT(ir.loaded == xfs_iext_count(ifp)); /* - * Here with bp and block set to the leftmost leaf node in the tree. - */ - room = xfs_iext_count(ifp); - i = 0; - /* - * Loop over all leaf nodes. Copy information to the extent records. + * Use release semantics so that we can use acquire semantics in + * xfs_need_iread_extents and be guaranteed to see a valid mapping tree + * after that load. */ - for (;;) { - xfs_bmbt_rec_t *frp; - xfs_fsblock_t nextbno; - xfs_extnum_t num_recs; - - num_recs = xfs_btree_get_numrecs(block); - if (unlikely(i + num_recs > room)) { - ASSERT(i + num_recs <= room); - xfs_warn(ip->i_mount, - "corrupt dinode %Lu, (btree extents).", - (unsigned long long) ip->i_ino); - XFS_CORRUPTION_ERROR("xfs_bmap_read_extents(1)", - XFS_ERRLEVEL_LOW, ip->i_mount, block); - goto error0; - } - /* - * Read-ahead the next leaf block, if any. - */ - nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib); - if (nextbno != NULLFSBLOCK) - xfs_btree_reada_bufl(mp, nextbno, 1, - &xfs_bmbt_buf_ops); - /* - * Copy records into the extent records. - */ - frp = XFS_BMBT_REC_ADDR(mp, block, 1); - for (j = 0; j < num_recs; j++, i++, frp++) { - xfs_bmbt_rec_host_t *trp = xfs_iext_get_ext(ifp, i); - trp->l0 = be64_to_cpu(frp->l0); - trp->l1 = be64_to_cpu(frp->l1); - if (!xfs_bmbt_validate_extent(mp, whichfork, trp)) { - XFS_ERROR_REPORT("xfs_bmap_read_extents(2)", - XFS_ERRLEVEL_LOW, mp); - goto error0; - } - } - xfs_trans_brelse(tp, bp); - bno = nextbno; - /* - * If we've reached the end, stop. - */ - if (bno == NULLFSBLOCK) - break; - error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, - XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); - if (error) - return error; - block = XFS_BUF_TO_BLOCK(bp); - } - if (i != XFS_IFORK_NEXTENTS(ip, whichfork)) - return -EFSCORRUPTED; - ASSERT(i == xfs_iext_count(ifp)); - XFS_BMAP_TRACE_EXLIST(ip, i, whichfork); + smp_store_release(&ifp->if_needextents, 0); return 0; -error0: - xfs_trans_brelse(tp, bp); - return -EFSCORRUPTED; +out: + if (xfs_metadata_is_sick(error)) + xfs_bmap_mark_sick(ip, whichfork); + xfs_iext_destroy(ifp); + return error; } /* - * Returns the file-relative block number of the first unused block(s) - * in the file with at least "len" logically contiguous blocks free. - * This is the lowest-address hole if the file has holes, else the first block - * past the end of file. - * Return 0 if the file is currently local (in-inode). + * Returns the relative block number of the first unused block(s) in the given + * fork with at least "len" logically contiguous blocks free. This is the + * lowest-address hole if the fork has holes, else the first block past the end + * of fork. Return 0 if the fork is currently local (in-inode). */ int /* error */ xfs_bmap_first_unused( - xfs_trans_t *tp, /* transaction pointer */ - xfs_inode_t *ip, /* incore inode */ - xfs_extlen_t len, /* size of hole to find */ - xfs_fileoff_t *first_unused, /* unused block */ - int whichfork) /* data or attr fork */ + struct xfs_trans *tp, /* transaction pointer */ + struct xfs_inode *ip, /* incore inode */ + xfs_extlen_t len, /* size of hole to find */ + xfs_fileoff_t *first_unused, /* unused block */ + int whichfork) /* data or attr fork */ { - int error; /* error return value */ - int idx; /* extent record index */ - xfs_ifork_t *ifp; /* inode fork pointer */ - xfs_fileoff_t lastaddr; /* last block number seen */ - xfs_fileoff_t lowest; /* lowest useful block */ - xfs_fileoff_t max; /* starting useful block */ - xfs_fileoff_t off; /* offset for this block */ - xfs_extnum_t nextents; /* number of extent entries */ - - ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE || - XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS || - XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL); - if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) { + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_bmbt_irec got; + struct xfs_iext_cursor icur; + xfs_fileoff_t lastaddr = 0; + xfs_fileoff_t lowest, max; + int error; + + if (ifp->if_format == XFS_DINODE_FMT_LOCAL) { *first_unused = 0; return 0; } - ifp = XFS_IFORK_PTR(ip, whichfork); - if (!(ifp->if_flags & XFS_IFEXTENTS) && - (error = xfs_iread_extents(tp, ip, whichfork))) + + ASSERT(xfs_ifork_has_extents(ifp)); + + error = xfs_iread_extents(tp, ip, whichfork); + if (error) return error; - lowest = *first_unused; - nextents = xfs_iext_count(ifp); - for (idx = 0, lastaddr = 0, max = lowest; idx < nextents; idx++) { - xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, idx); - off = xfs_bmbt_get_startoff(ep); + + lowest = max = *first_unused; + for_each_xfs_iext(ifp, &icur, &got) { /* * See if the hole before this extent will work. */ - if (off >= lowest + len && off - max >= len) { - *first_unused = max; - return 0; - } - lastaddr = off + xfs_bmbt_get_blockcount(ep); + if (got.br_startoff >= lowest + len && + got.br_startoff - max >= len) + break; + lastaddr = got.br_startoff + got.br_blockcount; max = XFS_FILEOFF_MAX(lastaddr, lowest); } + *first_unused = max; return 0; } @@ -1402,12 +1286,12 @@ xfs_bmap_last_before( xfs_fileoff_t *last_block, /* last block */ int whichfork) /* data or attr fork */ { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec got; - xfs_extnum_t idx; + struct xfs_iext_cursor icur; int error; - switch (XFS_IFORK_FORMAT(ip, whichfork)) { + switch (ifp->if_format) { case XFS_DINODE_FMT_LOCAL: *last_block = 0; return 0; @@ -1415,26 +1299,17 @@ xfs_bmap_last_before( case XFS_DINODE_FMT_EXTENTS: break; default: - return -EIO; - } - - if (!(ifp->if_flags & XFS_IFEXTENTS)) { - error = xfs_iread_extents(tp, ip, whichfork); - if (error) - return error; - } - - if (xfs_iext_lookup_extent(ip, ifp, *last_block - 1, &idx, &got)) { - if (got.br_startoff <= *last_block - 1) - return 0; + ASSERT(0); + xfs_bmap_mark_sick(ip, whichfork); + return -EFSCORRUPTED; } - if (xfs_iext_get_extent(ifp, idx - 1, &got)) { - *last_block = got.br_startoff + got.br_blockcount; - return 0; - } + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; - *last_block = 0; + if (!xfs_iext_lookup_extent_before(ip, ifp, last_block, &icur, &got)) + *last_block = 0; return 0; } @@ -1446,24 +1321,19 @@ xfs_bmap_last_extent( struct xfs_bmbt_irec *rec, int *is_empty) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_iext_cursor icur; int error; - int nextents; - if (!(ifp->if_flags & XFS_IFEXTENTS)) { - error = xfs_iread_extents(tp, ip, whichfork); - if (error) - return error; - } + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; - nextents = xfs_iext_count(ifp); - if (nextents == 0) { + xfs_iext_last(ifp, &icur); + if (!xfs_iext_get_extent(ifp, &icur, rec)) *is_empty = 1; - return 0; - } - - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, nextents - 1), rec); - *is_empty = 0; + else + *is_empty = 0; return 0; } @@ -1485,14 +1355,14 @@ xfs_bmap_isaeof( int is_empty; int error; - bma->aeof = 0; + bma->aeof = false; error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec, &is_empty); if (error) return error; if (is_empty) { - bma->aeof = 1; + bma->aeof = true; return 0; } @@ -1517,18 +1387,20 @@ xfs_bmap_last_offset( xfs_fileoff_t *last_block, int whichfork) { + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec rec; int is_empty; int error; *last_block = 0; - if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) + if (ifp->if_format == XFS_DINODE_FMT_LOCAL) return 0; - if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS) - return -EIO; + if (XFS_IS_CORRUPT(ip->i_mount, !xfs_ifork_has_extents(ifp))) { + xfs_bmap_mark_sick(ip, whichfork); + return -EFSCORRUPTED; + } error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, &is_empty); if (error || is_empty) @@ -1539,41 +1411,26 @@ xfs_bmap_last_offset( } /* - * Returns whether the selected fork of the inode has exactly one - * block or not. For the data fork we check this matches di_size, - * implying the file's range is 0..bsize-1. + * Extent tree manipulation functions used during allocation. */ -int /* 1=>1 block, 0=>otherwise */ -xfs_bmap_one_block( - xfs_inode_t *ip, /* incore inode */ - int whichfork) /* data or attr fork */ + +static inline bool +xfs_bmap_same_rtgroup( + struct xfs_inode *ip, + int whichfork, + struct xfs_bmbt_irec *left, + struct xfs_bmbt_irec *right) { - xfs_bmbt_rec_host_t *ep; /* ptr to fork's extent */ - xfs_ifork_t *ifp; /* inode fork pointer */ - int rval; /* return value */ - xfs_bmbt_irec_t s; /* internal version of extent */ + struct xfs_mount *mp = ip->i_mount; -#ifndef DEBUG - if (whichfork == XFS_DATA_FORK) - return XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize; -#endif /* !DEBUG */ - if (XFS_IFORK_NEXTENTS(ip, whichfork) != 1) - return 0; - if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS) - return 0; - ifp = XFS_IFORK_PTR(ip, whichfork); - ASSERT(ifp->if_flags & XFS_IFEXTENTS); - ep = xfs_iext_get_ext(ifp, 0); - xfs_bmbt_get_all(ep, &s); - rval = s.br_startoff == 0 && s.br_blockcount == 1; - if (rval && whichfork == XFS_DATA_FORK) - ASSERT(XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize); - return rval; -} + if (xfs_ifork_is_realtime(ip, whichfork) && xfs_has_rtgroups(mp)) { + if (xfs_rtb_to_rgno(mp, left->br_startblock) != + xfs_rtb_to_rgno(mp, right->br_startblock)) + return false; + } -/* - * Extent tree manipulation functions used during allocation. - */ + return true; +} /* * Convert a delayed allocation to a real allocation. @@ -1583,36 +1440,25 @@ xfs_bmap_add_extent_delay_real( struct xfs_bmalloca *bma, int whichfork) { + struct xfs_mount *mp = bma->ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork); struct xfs_bmbt_irec *new = &bma->got; - int diff; /* temp value */ - xfs_bmbt_rec_host_t *ep; /* extent entry for idx */ int error; /* error return value */ int i; /* temp state */ - xfs_ifork_t *ifp; /* inode fork pointer */ xfs_fileoff_t new_endoff; /* end offset of new entry */ xfs_bmbt_irec_t r[3]; /* neighbor extent entries */ /* left is 0, right is 1, prev is 2 */ int rval=0; /* return value (logging flags) */ - int state = 0;/* state bits, accessed thru macros */ + uint32_t state = xfs_bmap_fork_to_state(whichfork); xfs_filblks_t da_new; /* new count del alloc blocks used */ xfs_filblks_t da_old; /* old count del alloc blocks used */ xfs_filblks_t temp=0; /* value for da_new calculations */ - xfs_filblks_t temp2=0;/* value for da_new calculations */ int tmp_rval; /* partial logging flags */ - struct xfs_mount *mp; - xfs_extnum_t *nextents; + struct xfs_bmbt_irec old; - mp = bma->ip->i_mount; - ifp = XFS_IFORK_PTR(bma->ip, whichfork); ASSERT(whichfork != XFS_ATTR_FORK); - nextents = (whichfork == XFS_COW_FORK ? &bma->ip->i_cnextents : - &bma->ip->i_d.di_nextents); - - ASSERT(bma->idx >= 0); - ASSERT(bma->idx <= xfs_iext_count(ifp)); ASSERT(!isnullstartblock(new->br_startblock)); - ASSERT(!bma->cur || - (bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL)); + ASSERT(!bma->cur || (bma->cur->bc_flags & XFS_BTREE_BMBT_WASDEL)); XFS_STATS_INC(mp, xs_add_exlist); @@ -1620,15 +1466,12 @@ xfs_bmap_add_extent_delay_real( #define RIGHT r[1] #define PREV r[2] - if (whichfork == XFS_COW_FORK) - state |= BMAP_COWFORK; - /* * Set up a bunch of variables to make the tests simpler. */ - ep = xfs_iext_get_ext(ifp, bma->idx); - xfs_bmbt_get_all(ep, &PREV); + xfs_iext_get_extent(ifp, &bma->icur, &PREV); new_endoff = new->br_startoff + new->br_blockcount; + ASSERT(isnullstartblock(PREV.br_startblock)); ASSERT(PREV.br_startoff <= new->br_startoff); ASSERT(PREV.br_startoff + PREV.br_blockcount >= new_endoff); @@ -1648,10 +1491,8 @@ xfs_bmap_add_extent_delay_real( * Check and set flags if this segment has a left neighbor. * Don't set contiguous if the combined extent would be too large. */ - if (bma->idx > 0) { + if (xfs_iext_peek_prev_extent(ifp, &bma->icur, &LEFT)) { state |= BMAP_LEFT_VALID; - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx - 1), &LEFT); - if (isnullstartblock(LEFT.br_startblock)) state |= BMAP_LEFT_DELAY; } @@ -1660,7 +1501,8 @@ xfs_bmap_add_extent_delay_real( LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff && LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock && LEFT.br_state == new->br_state && - LEFT.br_blockcount + new->br_blockcount <= MAXEXTLEN) + LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN && + xfs_bmap_same_rtgroup(bma->ip, whichfork, &LEFT, new)) state |= BMAP_LEFT_CONTIG; /* @@ -1668,10 +1510,8 @@ xfs_bmap_add_extent_delay_real( * Don't set contiguous if the combined extent would be too large. * Also check for all-three-contiguous being too large. */ - if (bma->idx < xfs_iext_count(ifp) - 1) { + if (xfs_iext_peek_next_extent(ifp, &bma->icur, &RIGHT)) { state |= BMAP_RIGHT_VALID; - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx + 1), &RIGHT); - if (isnullstartblock(RIGHT.br_startblock)) state |= BMAP_RIGHT_DELAY; } @@ -1680,13 +1520,14 @@ xfs_bmap_add_extent_delay_real( new_endoff == RIGHT.br_startoff && new->br_startblock + new->br_blockcount == RIGHT.br_startblock && new->br_state == RIGHT.br_state && - new->br_blockcount + RIGHT.br_blockcount <= MAXEXTLEN && + new->br_blockcount + RIGHT.br_blockcount <= XFS_MAX_BMBT_EXTLEN && ((state & (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING)) != (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING) || LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount - <= MAXEXTLEN)) + <= XFS_MAX_BMBT_EXTLEN) && + xfs_bmap_same_rtgroup(bma->ip, whichfork, new, &RIGHT)) state |= BMAP_RIGHT_CONTIG; error = 0; @@ -1701,41 +1542,47 @@ xfs_bmap_add_extent_delay_real( * Filling in all of a previously delayed allocation extent. * The left and right neighbors are both contiguous with new. */ - bma->idx--; - trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, bma->idx), - LEFT.br_blockcount + PREV.br_blockcount + - RIGHT.br_blockcount); - trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_); - - xfs_iext_remove(bma->ip, bma->idx + 1, 2, state); - (*nextents)--; + LEFT.br_blockcount += PREV.br_blockcount + RIGHT.br_blockcount; + + xfs_iext_remove(bma->ip, &bma->icur, state); + xfs_iext_remove(bma->ip, &bma->icur, state); + xfs_iext_prev(ifp, &bma->icur); + xfs_iext_update_extent(bma->ip, state, &bma->icur, &LEFT); + ifp->if_nextents--; + if (bma->cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - error = xfs_bmbt_lookup_eq(bma->cur, RIGHT.br_startoff, - RIGHT.br_startblock, - RIGHT.br_blockcount, &i); + error = xfs_bmbt_lookup_eq(bma->cur, &RIGHT, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } error = xfs_btree_delete(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } error = xfs_btree_decrement(bma->cur, 0, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - error = xfs_bmbt_update(bma->cur, LEFT.br_startoff, - LEFT.br_startblock, - LEFT.br_blockcount + - PREV.br_blockcount + - RIGHT.br_blockcount, LEFT.br_state); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(bma->cur, &LEFT); if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_LEFT_CONTIG: @@ -1743,62 +1590,65 @@ xfs_bmap_add_extent_delay_real( * Filling in all of a previously delayed allocation extent. * The left neighbor is contiguous, the right is not. */ - bma->idx--; + old = LEFT; + LEFT.br_blockcount += PREV.br_blockcount; - trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, bma->idx), - LEFT.br_blockcount + PREV.br_blockcount); - trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_); + xfs_iext_remove(bma->ip, &bma->icur, state); + xfs_iext_prev(ifp, &bma->icur); + xfs_iext_update_extent(bma->ip, state, &bma->icur, &LEFT); - xfs_iext_remove(bma->ip, bma->idx + 1, 1, state); if (bma->cur == NULL) rval = XFS_ILOG_DEXT; else { rval = 0; - error = xfs_bmbt_lookup_eq(bma->cur, LEFT.br_startoff, - LEFT.br_startblock, LEFT.br_blockcount, - &i); + error = xfs_bmbt_lookup_eq(bma->cur, &old, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - error = xfs_bmbt_update(bma->cur, LEFT.br_startoff, - LEFT.br_startblock, - LEFT.br_blockcount + - PREV.br_blockcount, LEFT.br_state); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(bma->cur, &LEFT); if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG: /* * Filling in all of a previously delayed allocation extent. - * The right neighbor is contiguous, the left is not. + * The right neighbor is contiguous, the left is not. Take care + * with delay -> unwritten extent allocation here because the + * delalloc record we are overwriting is always written. */ - trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_); - xfs_bmbt_set_startblock(ep, new->br_startblock); - xfs_bmbt_set_blockcount(ep, - PREV.br_blockcount + RIGHT.br_blockcount); - trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_); + PREV.br_startblock = new->br_startblock; + PREV.br_blockcount += RIGHT.br_blockcount; + PREV.br_state = new->br_state; + + xfs_iext_next(ifp, &bma->icur); + xfs_iext_remove(bma->ip, &bma->icur, state); + xfs_iext_prev(ifp, &bma->icur); + xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV); - xfs_iext_remove(bma->ip, bma->idx + 1, 1, state); if (bma->cur == NULL) rval = XFS_ILOG_DEXT; else { rval = 0; - error = xfs_bmbt_lookup_eq(bma->cur, RIGHT.br_startoff, - RIGHT.br_startblock, - RIGHT.br_blockcount, &i); + error = xfs_bmbt_lookup_eq(bma->cur, &RIGHT, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - error = xfs_bmbt_update(bma->cur, PREV.br_startoff, - new->br_startblock, - PREV.br_blockcount + - RIGHT.br_blockcount, PREV.br_state); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(bma->cur, &PREV); if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING: @@ -1807,28 +1657,33 @@ xfs_bmap_add_extent_delay_real( * Neither the left nor right neighbors are contiguous with * the new one. */ - trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_); - xfs_bmbt_set_startblock(ep, new->br_startblock); - xfs_bmbt_set_state(ep, new->br_state); - trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_); + PREV.br_startblock = new->br_startblock; + PREV.br_state = new->br_state; + xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV); + ifp->if_nextents++; - (*nextents)++; if (bma->cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - error = xfs_bmbt_lookup_eq(bma->cur, new->br_startoff, - new->br_startblock, new->br_blockcount, - &i); + error = xfs_bmbt_lookup_eq(bma->cur, new, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); - bma->cur->bc_rec.b.br_state = XFS_EXT_NORM; + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } error = xfs_btree_insert(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG: @@ -1836,40 +1691,38 @@ xfs_bmap_add_extent_delay_real( * Filling in the first part of a previous delayed allocation. * The left neighbor is contiguous. */ - trace_xfs_bmap_pre_update(bma->ip, bma->idx - 1, state, _THIS_IP_); - xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, bma->idx - 1), - LEFT.br_blockcount + new->br_blockcount); - xfs_bmbt_set_startoff(ep, - PREV.br_startoff + new->br_blockcount); - trace_xfs_bmap_post_update(bma->ip, bma->idx - 1, state, _THIS_IP_); - + old = LEFT; temp = PREV.br_blockcount - new->br_blockcount; - trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); + da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp), + startblockval(PREV.br_startblock)); + + LEFT.br_blockcount += new->br_blockcount; + + PREV.br_blockcount = temp; + PREV.br_startoff += new->br_blockcount; + PREV.br_startblock = nullstartblock(da_new); + + xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV); + xfs_iext_prev(ifp, &bma->icur); + xfs_iext_update_extent(bma->ip, state, &bma->icur, &LEFT); + if (bma->cur == NULL) rval = XFS_ILOG_DEXT; else { rval = 0; - error = xfs_bmbt_lookup_eq(bma->cur, LEFT.br_startoff, - LEFT.br_startblock, LEFT.br_blockcount, - &i); + error = xfs_bmbt_lookup_eq(bma->cur, &old, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - error = xfs_bmbt_update(bma->cur, LEFT.br_startoff, - LEFT.br_startblock, - LEFT.br_blockcount + - new->br_blockcount, - LEFT.br_state); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(bma->cur, &LEFT); if (error) goto done; } - da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp), - startblockval(PREV.br_startblock)); - xfs_bmbt_set_startblock(ep, nullstartblock(da_new)); - trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_); - - bma->idx--; + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING: @@ -1877,43 +1730,50 @@ xfs_bmap_add_extent_delay_real( * Filling in the first part of a previous delayed allocation. * The left neighbor is not contiguous. */ - trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_); - xfs_bmbt_set_startoff(ep, new_endoff); - temp = PREV.br_blockcount - new->br_blockcount; - xfs_bmbt_set_blockcount(ep, temp); - xfs_iext_insert(bma->ip, bma->idx, 1, new, state); - (*nextents)++; + xfs_iext_update_extent(bma->ip, state, &bma->icur, new); + ifp->if_nextents++; + if (bma->cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - error = xfs_bmbt_lookup_eq(bma->cur, new->br_startoff, - new->br_startblock, new->br_blockcount, - &i); + error = xfs_bmbt_lookup_eq(bma->cur, new, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); - bma->cur->bc_rec.b.br_state = XFS_EXT_NORM; + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } error = xfs_btree_insert(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } } if (xfs_bmap_needs_btree(bma->ip, whichfork)) { error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, - bma->firstblock, bma->dfops, &bma->cur, 1, &tmp_rval, whichfork); rval |= tmp_rval; if (error) goto done; } + + temp = PREV.br_blockcount - new->br_blockcount; da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp), startblockval(PREV.br_startblock) - - (bma->cur ? bma->cur->bc_private.b.allocated : 0)); - ep = xfs_iext_get_ext(ifp, bma->idx + 1); - xfs_bmbt_set_startblock(ep, nullstartblock(da_new)); - trace_xfs_bmap_post_update(bma->ip, bma->idx + 1, state, _THIS_IP_); + (bma->cur ? bma->cur->bc_bmap.allocated : 0)); + + PREV.br_startoff = new_endoff; + PREV.br_blockcount = temp; + PREV.br_startblock = nullstartblock(da_new); + xfs_iext_next(ifp, &bma->icur); + xfs_iext_insert(bma->ip, &bma->icur, &PREV, state); + xfs_iext_prev(ifp, &bma->icur); break; case BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG: @@ -1921,40 +1781,39 @@ xfs_bmap_add_extent_delay_real( * Filling in the last part of a previous delayed allocation. * The right neighbor is contiguous with the new allocation. */ - temp = PREV.br_blockcount - new->br_blockcount; - trace_xfs_bmap_pre_update(bma->ip, bma->idx + 1, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, bma->idx + 1), - new->br_startoff, new->br_startblock, - new->br_blockcount + RIGHT.br_blockcount, - RIGHT.br_state); - trace_xfs_bmap_post_update(bma->ip, bma->idx + 1, state, _THIS_IP_); + old = RIGHT; + RIGHT.br_startoff = new->br_startoff; + RIGHT.br_startblock = new->br_startblock; + RIGHT.br_blockcount += new->br_blockcount; + if (bma->cur == NULL) rval = XFS_ILOG_DEXT; else { rval = 0; - error = xfs_bmbt_lookup_eq(bma->cur, RIGHT.br_startoff, - RIGHT.br_startblock, - RIGHT.br_blockcount, &i); + error = xfs_bmbt_lookup_eq(bma->cur, &old, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - error = xfs_bmbt_update(bma->cur, new->br_startoff, - new->br_startblock, - new->br_blockcount + - RIGHT.br_blockcount, - RIGHT.br_state); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(bma->cur, &RIGHT); if (error) goto done; } + temp = PREV.br_blockcount - new->br_blockcount; da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp), startblockval(PREV.br_startblock)); - trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_); - xfs_bmbt_set_startblock(ep, nullstartblock(da_new)); - trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_); - bma->idx++; + PREV.br_blockcount = temp; + PREV.br_startblock = nullstartblock(da_new); + + xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV); + xfs_iext_next(ifp, &bma->icur); + xfs_iext_update_extent(bma->ip, state, &bma->icur, &RIGHT); + ASSERT(da_new <= da_old); break; case BMAP_RIGHT_FILLING: @@ -1962,44 +1821,49 @@ xfs_bmap_add_extent_delay_real( * Filling in the last part of a previous delayed allocation. * The right neighbor is not contiguous. */ - temp = PREV.br_blockcount - new->br_blockcount; - trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - xfs_iext_insert(bma->ip, bma->idx + 1, 1, new, state); - (*nextents)++; + xfs_iext_update_extent(bma->ip, state, &bma->icur, new); + ifp->if_nextents++; + if (bma->cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - error = xfs_bmbt_lookup_eq(bma->cur, new->br_startoff, - new->br_startblock, new->br_blockcount, - &i); + error = xfs_bmbt_lookup_eq(bma->cur, new, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); - bma->cur->bc_rec.b.br_state = XFS_EXT_NORM; + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } error = xfs_btree_insert(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } } if (xfs_bmap_needs_btree(bma->ip, whichfork)) { error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, - bma->firstblock, bma->dfops, &bma->cur, 1, - &tmp_rval, whichfork); + &bma->cur, 1, &tmp_rval, whichfork); rval |= tmp_rval; if (error) goto done; } + + temp = PREV.br_blockcount - new->br_blockcount; da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp), startblockval(PREV.br_startblock) - - (bma->cur ? bma->cur->bc_private.b.allocated : 0)); - ep = xfs_iext_get_ext(ifp, bma->idx); - xfs_bmbt_set_startblock(ep, nullstartblock(da_new)); - trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_); + (bma->cur ? bma->cur->bc_bmap.allocated : 0)); - bma->idx++; + PREV.br_startblock = nullstartblock(da_new); + PREV.br_blockcount = temp; + xfs_iext_insert(bma->ip, &bma->icur, &PREV, state); + xfs_iext_next(ifp, &bma->icur); + ASSERT(da_new <= da_old); break; case 0: @@ -2023,68 +1887,64 @@ xfs_bmap_add_extent_delay_real( * PREV @ idx LEFT RIGHT * inserted at idx + 1 */ - temp = new->br_startoff - PREV.br_startoff; - temp2 = PREV.br_startoff + PREV.br_blockcount - new_endoff; - trace_xfs_bmap_pre_update(bma->ip, bma->idx, 0, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); /* truncate PREV */ + old = PREV; + + /* LEFT is the new middle */ LEFT = *new; + + /* RIGHT is the new right */ RIGHT.br_state = PREV.br_state; - RIGHT.br_startblock = nullstartblock( - (int)xfs_bmap_worst_indlen(bma->ip, temp2)); RIGHT.br_startoff = new_endoff; - RIGHT.br_blockcount = temp2; - /* insert LEFT (r[0]) and RIGHT (r[1]) at the same time */ - xfs_iext_insert(bma->ip, bma->idx + 1, 2, &LEFT, state); - (*nextents)++; + RIGHT.br_blockcount = + PREV.br_startoff + PREV.br_blockcount - new_endoff; + RIGHT.br_startblock = + nullstartblock(xfs_bmap_worst_indlen(bma->ip, + RIGHT.br_blockcount)); + + /* truncate PREV */ + PREV.br_blockcount = new->br_startoff - PREV.br_startoff; + PREV.br_startblock = + nullstartblock(xfs_bmap_worst_indlen(bma->ip, + PREV.br_blockcount)); + xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV); + + xfs_iext_next(ifp, &bma->icur); + xfs_iext_insert(bma->ip, &bma->icur, &RIGHT, state); + xfs_iext_insert(bma->ip, &bma->icur, &LEFT, state); + ifp->if_nextents++; + if (bma->cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - error = xfs_bmbt_lookup_eq(bma->cur, new->br_startoff, - new->br_startblock, new->br_blockcount, - &i); + error = xfs_bmbt_lookup_eq(bma->cur, new, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); - bma->cur->bc_rec.b.br_state = XFS_EXT_NORM; + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } error = xfs_btree_insert(bma->cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); + error = -EFSCORRUPTED; + goto done; + } } if (xfs_bmap_needs_btree(bma->ip, whichfork)) { error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, - bma->firstblock, bma->dfops, &bma->cur, - 1, &tmp_rval, whichfork); + &bma->cur, 1, &tmp_rval, whichfork); rval |= tmp_rval; if (error) goto done; } - temp = xfs_bmap_worst_indlen(bma->ip, temp); - temp2 = xfs_bmap_worst_indlen(bma->ip, temp2); - diff = (int)(temp + temp2 - - (startblockval(PREV.br_startblock) - - (bma->cur ? - bma->cur->bc_private.b.allocated : 0))); - if (diff > 0) { - error = xfs_mod_fdblocks(bma->ip->i_mount, - -((int64_t)diff), false); - ASSERT(!error); - if (error) - goto done; - } - - ep = xfs_iext_get_ext(ifp, bma->idx); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_); - trace_xfs_bmap_pre_update(bma->ip, bma->idx + 2, state, _THIS_IP_); - xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, bma->idx + 2), - nullstartblock((int)temp2)); - trace_xfs_bmap_post_update(bma->ip, bma->idx + 2, state, _THIS_IP_); - bma->idx++; - da_new = temp + temp2; + da_new = startblockval(PREV.br_startblock) + + startblockval(RIGHT.br_startblock); break; case BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: @@ -2100,10 +1960,9 @@ xfs_bmap_add_extent_delay_real( ASSERT(0); } - /* add reverse mapping */ - error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip, whichfork, new); - if (error) - goto done; + /* add reverse mapping unless caller opted out */ + if (!(bma->flags & XFS_BMAPI_NORMAP)) + xfs_rmap_map_extent(bma->tp, bma->ip, whichfork, new); /* convert to a btree if necessary */ if (xfs_bmap_needs_btree(bma->ip, whichfork)) { @@ -2111,26 +1970,26 @@ xfs_bmap_add_extent_delay_real( ASSERT(bma->cur == NULL); error = xfs_bmap_extents_to_btree(bma->tp, bma->ip, - bma->firstblock, bma->dfops, &bma->cur, - da_old > 0, &tmp_logflags, whichfork); + &bma->cur, da_old > 0, &tmp_logflags, + whichfork); bma->logflags |= tmp_logflags; if (error) goto done; } - /* adjust for changes in reserved delayed indirect blocks */ - if (da_old || da_new) { - temp = da_new; - if (bma->cur) - temp += bma->cur->bc_private.b.allocated; - if (temp < da_old) - xfs_mod_fdblocks(bma->ip->i_mount, - (int64_t)(da_old - temp), false); + if (da_new != da_old) + xfs_mod_delalloc(bma->ip, 0, (int64_t)da_new - da_old); + + if (bma->cur) { + da_new += bma->cur->bc_bmap.allocated; + bma->cur->bc_bmap.allocated = 0; } - /* clear out the allocated field, done with it now in any case. */ - if (bma->cur) - bma->cur->bc_private.b.allocated = 0; + /* adjust for changes in reserved delayed indirect blocks */ + if (da_new < da_old) + xfs_add_fdblocks(mp, da_old - da_new); + else if (da_new > da_old) + error = xfs_dec_fdblocks(mp, da_new - da_old, true); xfs_bmap_check_leaf_extents(bma->cur, bma->ip, whichfork); done: @@ -2145,41 +2004,33 @@ done: /* * Convert an unwritten allocation to a real allocation or vice versa. */ -STATIC int /* error */ +int /* error */ xfs_bmap_add_extent_unwritten_real( struct xfs_trans *tp, xfs_inode_t *ip, /* incore inode pointer */ int whichfork, - xfs_extnum_t *idx, /* extent number to update/insert */ - xfs_btree_cur_t **curp, /* if *curp is null, not a btree */ + struct xfs_iext_cursor *icur, + struct xfs_btree_cur **curp, /* if *curp is null, not a btree */ xfs_bmbt_irec_t *new, /* new data to add to file extents */ - xfs_fsblock_t *first, /* pointer to firstblock variable */ - struct xfs_defer_ops *dfops, /* list of extents to be freed */ int *logflagsp) /* inode logging flags */ { - xfs_btree_cur_t *cur; /* btree cursor */ - xfs_bmbt_rec_host_t *ep; /* extent entry for idx */ + struct xfs_btree_cur *cur; /* btree cursor */ int error; /* error return value */ int i; /* temp state */ - xfs_ifork_t *ifp; /* inode fork pointer */ + struct xfs_ifork *ifp; /* inode fork pointer */ xfs_fileoff_t new_endoff; /* end offset of new entry */ - xfs_exntst_t newext; /* new extent state */ - xfs_exntst_t oldext; /* old extent state */ xfs_bmbt_irec_t r[3]; /* neighbor extent entries */ /* left is 0, right is 1, prev is 2 */ int rval=0; /* return value (logging flags) */ - int state = 0;/* state bits, accessed thru macros */ + uint32_t state = xfs_bmap_fork_to_state(whichfork); struct xfs_mount *mp = ip->i_mount; + struct xfs_bmbt_irec old; *logflagsp = 0; cur = *curp; - ifp = XFS_IFORK_PTR(ip, whichfork); - if (whichfork == XFS_COW_FORK) - state |= BMAP_COWFORK; + ifp = xfs_ifork_ptr(ip, whichfork); - ASSERT(*idx >= 0); - ASSERT(*idx <= xfs_iext_count(ifp)); ASSERT(!isnullstartblock(new->br_startblock)); XFS_STATS_INC(mp, xs_add_exlist); @@ -2192,12 +2043,8 @@ xfs_bmap_add_extent_unwritten_real( * Set up a bunch of variables to make the tests simpler. */ error = 0; - ep = xfs_iext_get_ext(ifp, *idx); - xfs_bmbt_get_all(ep, &PREV); - newext = new->br_state; - oldext = (newext == XFS_EXT_UNWRITTEN) ? - XFS_EXT_NORM : XFS_EXT_UNWRITTEN; - ASSERT(PREV.br_state == oldext); + xfs_iext_get_extent(ifp, icur, &PREV); + ASSERT(new->br_state != PREV.br_state); new_endoff = new->br_startoff + new->br_blockcount; ASSERT(PREV.br_startoff <= new->br_startoff); ASSERT(PREV.br_startoff + PREV.br_blockcount >= new_endoff); @@ -2215,10 +2062,8 @@ xfs_bmap_add_extent_unwritten_real( * Check and set flags if this segment has a left neighbor. * Don't set contiguous if the combined extent would be too large. */ - if (*idx > 0) { + if (xfs_iext_peek_prev_extent(ifp, icur, &LEFT)) { state |= BMAP_LEFT_VALID; - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx - 1), &LEFT); - if (isnullstartblock(LEFT.br_startblock)) state |= BMAP_LEFT_DELAY; } @@ -2226,8 +2071,9 @@ xfs_bmap_add_extent_unwritten_real( if ((state & BMAP_LEFT_VALID) && !(state & BMAP_LEFT_DELAY) && LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff && LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock && - LEFT.br_state == newext && - LEFT.br_blockcount + new->br_blockcount <= MAXEXTLEN) + LEFT.br_state == new->br_state && + LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN && + xfs_bmap_same_rtgroup(ip, whichfork, &LEFT, new)) state |= BMAP_LEFT_CONTIG; /* @@ -2235,9 +2081,8 @@ xfs_bmap_add_extent_unwritten_real( * Don't set contiguous if the combined extent would be too large. * Also check for all-three-contiguous being too large. */ - if (*idx < xfs_iext_count(ifp) - 1) { + if (xfs_iext_peek_next_extent(ifp, icur, &RIGHT)) { state |= BMAP_RIGHT_VALID; - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx + 1), &RIGHT); if (isnullstartblock(RIGHT.br_startblock)) state |= BMAP_RIGHT_DELAY; } @@ -2245,14 +2090,15 @@ xfs_bmap_add_extent_unwritten_real( if ((state & BMAP_RIGHT_VALID) && !(state & BMAP_RIGHT_DELAY) && new_endoff == RIGHT.br_startoff && new->br_startblock + new->br_blockcount == RIGHT.br_startblock && - newext == RIGHT.br_state && - new->br_blockcount + RIGHT.br_blockcount <= MAXEXTLEN && + new->br_state == RIGHT.br_state && + new->br_blockcount + RIGHT.br_blockcount <= XFS_MAX_BMBT_EXTLEN && ((state & (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING)) != (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING) || LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount - <= MAXEXTLEN)) + <= XFS_MAX_BMBT_EXTLEN) && + xfs_bmap_same_rtgroup(ip, whichfork, new, &RIGHT)) state |= BMAP_RIGHT_CONTIG; /* @@ -2266,42 +2112,55 @@ xfs_bmap_add_extent_unwritten_real( * Setting all of a previous oldext extent to newext. * The left and right neighbors are both contiguous with new. */ - --*idx; + LEFT.br_blockcount += PREV.br_blockcount + RIGHT.br_blockcount; - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx), - LEFT.br_blockcount + PREV.br_blockcount + - RIGHT.br_blockcount); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); - - xfs_iext_remove(ip, *idx + 1, 2, state); - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) - 2); + xfs_iext_remove(ip, icur, state); + xfs_iext_remove(ip, icur, state); + xfs_iext_prev(ifp, icur); + xfs_iext_update_extent(ip, state, icur, &LEFT); + ifp->if_nextents -= 2; if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - if ((error = xfs_bmbt_lookup_eq(cur, RIGHT.br_startoff, - RIGHT.br_startblock, - RIGHT.br_blockcount, &i))) + error = xfs_bmbt_lookup_eq(cur, &RIGHT, &i); + if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } if ((error = xfs_btree_delete(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } if ((error = xfs_btree_decrement(cur, 0, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } if ((error = xfs_btree_delete(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } if ((error = xfs_btree_decrement(cur, 0, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - if ((error = xfs_bmbt_update(cur, LEFT.br_startoff, - LEFT.br_startblock, - LEFT.br_blockcount + PREV.br_blockcount + - RIGHT.br_blockcount, LEFT.br_state))) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(cur, &LEFT); + if (error) goto done; } break; @@ -2311,35 +2170,40 @@ xfs_bmap_add_extent_unwritten_real( * Setting all of a previous oldext extent to newext. * The left neighbor is contiguous, the right is not. */ - --*idx; - - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx), - LEFT.br_blockcount + PREV.br_blockcount); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + LEFT.br_blockcount += PREV.br_blockcount; - xfs_iext_remove(ip, *idx + 1, 1, state); - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) - 1); + xfs_iext_remove(ip, icur, state); + xfs_iext_prev(ifp, icur); + xfs_iext_update_extent(ip, state, icur, &LEFT); + ifp->if_nextents--; if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - if ((error = xfs_bmbt_lookup_eq(cur, PREV.br_startoff, - PREV.br_startblock, PREV.br_blockcount, - &i))) + error = xfs_bmbt_lookup_eq(cur, &PREV, &i); + if (error) + goto done; + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + } if ((error = xfs_btree_delete(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } if ((error = xfs_btree_decrement(cur, 0, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - if ((error = xfs_bmbt_update(cur, LEFT.br_startoff, - LEFT.br_startblock, - LEFT.br_blockcount + PREV.br_blockcount, - LEFT.br_state))) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(cur, &LEFT); + if (error) goto done; } break; @@ -2349,33 +2213,43 @@ xfs_bmap_add_extent_unwritten_real( * Setting all of a previous oldext extent to newext. * The right neighbor is contiguous, the left is not. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, - PREV.br_blockcount + RIGHT.br_blockcount); - xfs_bmbt_set_state(ep, newext); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); - xfs_iext_remove(ip, *idx + 1, 1, state); - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) - 1); + PREV.br_blockcount += RIGHT.br_blockcount; + PREV.br_state = new->br_state; + + xfs_iext_next(ifp, icur); + xfs_iext_remove(ip, icur, state); + xfs_iext_prev(ifp, icur); + xfs_iext_update_extent(ip, state, icur, &PREV); + ifp->if_nextents--; + if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - if ((error = xfs_bmbt_lookup_eq(cur, RIGHT.br_startoff, - RIGHT.br_startblock, - RIGHT.br_blockcount, &i))) + error = xfs_bmbt_lookup_eq(cur, &RIGHT, &i); + if (error) + goto done; + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + } if ((error = xfs_btree_delete(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } if ((error = xfs_btree_decrement(cur, 0, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - if ((error = xfs_bmbt_update(cur, new->br_startoff, - new->br_startblock, - new->br_blockcount + RIGHT.br_blockcount, - newext))) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(cur, &PREV); + if (error) goto done; } break; @@ -2386,22 +2260,23 @@ xfs_bmap_add_extent_unwritten_real( * Neither the left nor right neighbors are contiguous with * the new one. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_state(ep, newext); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + PREV.br_state = new->br_state; + xfs_iext_update_extent(ip, state, icur, &PREV); if (cur == NULL) rval = XFS_ILOG_DEXT; else { rval = 0; - if ((error = xfs_bmbt_lookup_eq(cur, new->br_startoff, - new->br_startblock, new->br_blockcount, - &i))) + error = xfs_bmbt_lookup_eq(cur, new, &i); + if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - if ((error = xfs_bmbt_update(cur, new->br_startoff, - new->br_startblock, new->br_blockcount, - newext))) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(cur, &PREV); + if (error) goto done; } break; @@ -2411,43 +2286,36 @@ xfs_bmap_add_extent_unwritten_real( * Setting the first part of a previous oldext extent to newext. * The left neighbor is contiguous. */ - trace_xfs_bmap_pre_update(ip, *idx - 1, state, _THIS_IP_); - xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx - 1), - LEFT.br_blockcount + new->br_blockcount); - xfs_bmbt_set_startoff(ep, - PREV.br_startoff + new->br_blockcount); - trace_xfs_bmap_post_update(ip, *idx - 1, state, _THIS_IP_); - - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_startblock(ep, - new->br_startblock + new->br_blockcount); - xfs_bmbt_set_blockcount(ep, - PREV.br_blockcount - new->br_blockcount); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); - - --*idx; + LEFT.br_blockcount += new->br_blockcount; + + old = PREV; + PREV.br_startoff += new->br_blockcount; + PREV.br_startblock += new->br_blockcount; + PREV.br_blockcount -= new->br_blockcount; + + xfs_iext_update_extent(ip, state, icur, &PREV); + xfs_iext_prev(ifp, icur); + xfs_iext_update_extent(ip, state, icur, &LEFT); if (cur == NULL) rval = XFS_ILOG_DEXT; else { rval = 0; - if ((error = xfs_bmbt_lookup_eq(cur, PREV.br_startoff, - PREV.br_startblock, PREV.br_blockcount, - &i))) + error = xfs_bmbt_lookup_eq(cur, &old, &i); + if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - if ((error = xfs_bmbt_update(cur, - PREV.br_startoff + new->br_blockcount, - PREV.br_startblock + new->br_blockcount, - PREV.br_blockcount - new->br_blockcount, - oldext))) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; goto done; - if ((error = xfs_btree_decrement(cur, 0, &i))) + } + error = xfs_bmbt_update(cur, &PREV); + if (error) + goto done; + error = xfs_btree_decrement(cur, 0, &i); + if (error) goto done; - error = xfs_bmbt_update(cur, LEFT.br_startoff, - LEFT.br_startblock, - LEFT.br_blockcount + new->br_blockcount, - LEFT.br_state); + error = xfs_bmbt_update(cur, &LEFT); if (error) goto done; } @@ -2458,37 +2326,38 @@ xfs_bmap_add_extent_unwritten_real( * Setting the first part of a previous oldext extent to newext. * The left neighbor is not contiguous. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - ASSERT(ep && xfs_bmbt_get_state(ep) == oldext); - xfs_bmbt_set_startoff(ep, new_endoff); - xfs_bmbt_set_blockcount(ep, - PREV.br_blockcount - new->br_blockcount); - xfs_bmbt_set_startblock(ep, - new->br_startblock + new->br_blockcount); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); - - xfs_iext_insert(ip, *idx, 1, new, state); - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) + 1); + old = PREV; + PREV.br_startoff += new->br_blockcount; + PREV.br_startblock += new->br_blockcount; + PREV.br_blockcount -= new->br_blockcount; + + xfs_iext_update_extent(ip, state, icur, &PREV); + xfs_iext_insert(ip, icur, new, state); + ifp->if_nextents++; + if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - if ((error = xfs_bmbt_lookup_eq(cur, PREV.br_startoff, - PREV.br_startblock, PREV.br_blockcount, - &i))) + error = xfs_bmbt_lookup_eq(cur, &old, &i); + if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - if ((error = xfs_bmbt_update(cur, - PREV.br_startoff + new->br_blockcount, - PREV.br_startblock + new->br_blockcount, - PREV.br_blockcount - new->br_blockcount, - oldext))) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(cur, &PREV); + if (error) goto done; cur->bc_rec.b = *new; if ((error = xfs_btree_insert(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } } break; @@ -2497,39 +2366,37 @@ xfs_bmap_add_extent_unwritten_real( * Setting the last part of a previous oldext extent to newext. * The right neighbor is contiguous with the new allocation. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, - PREV.br_blockcount - new->br_blockcount); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + old = PREV; + PREV.br_blockcount -= new->br_blockcount; - ++*idx; + RIGHT.br_startoff = new->br_startoff; + RIGHT.br_startblock = new->br_startblock; + RIGHT.br_blockcount += new->br_blockcount; - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, *idx), - new->br_startoff, new->br_startblock, - new->br_blockcount + RIGHT.br_blockcount, newext); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + xfs_iext_update_extent(ip, state, icur, &PREV); + xfs_iext_next(ifp, icur); + xfs_iext_update_extent(ip, state, icur, &RIGHT); if (cur == NULL) rval = XFS_ILOG_DEXT; else { rval = 0; - if ((error = xfs_bmbt_lookup_eq(cur, PREV.br_startoff, - PREV.br_startblock, - PREV.br_blockcount, &i))) + error = xfs_bmbt_lookup_eq(cur, &old, &i); + if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - if ((error = xfs_bmbt_update(cur, PREV.br_startoff, - PREV.br_startblock, - PREV.br_blockcount - new->br_blockcount, - oldext))) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; goto done; - if ((error = xfs_btree_increment(cur, 0, &i))) + } + error = xfs_bmbt_update(cur, &PREV); + if (error) goto done; - if ((error = xfs_bmbt_update(cur, new->br_startoff, - new->br_startblock, - new->br_blockcount + RIGHT.br_blockcount, - newext))) + error = xfs_btree_increment(cur, 0, &i); + if (error) + goto done; + error = xfs_bmbt_update(cur, &RIGHT); + if (error) goto done; } break; @@ -2539,39 +2406,44 @@ xfs_bmap_add_extent_unwritten_real( * Setting the last part of a previous oldext extent to newext. * The right neighbor is not contiguous. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, - PREV.br_blockcount - new->br_blockcount); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + old = PREV; + PREV.br_blockcount -= new->br_blockcount; - ++*idx; - xfs_iext_insert(ip, *idx, 1, new, state); + xfs_iext_update_extent(ip, state, icur, &PREV); + xfs_iext_next(ifp, icur); + xfs_iext_insert(ip, icur, new, state); + ifp->if_nextents++; - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) + 1); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - if ((error = xfs_bmbt_lookup_eq(cur, PREV.br_startoff, - PREV.br_startblock, PREV.br_blockcount, - &i))) + error = xfs_bmbt_lookup_eq(cur, &old, &i); + if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - if ((error = xfs_bmbt_update(cur, PREV.br_startoff, - PREV.br_startblock, - PREV.br_blockcount - new->br_blockcount, - oldext))) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; goto done; - if ((error = xfs_bmbt_lookup_eq(cur, new->br_startoff, - new->br_startblock, new->br_blockcount, - &i))) + } + error = xfs_bmbt_update(cur, &PREV); + if (error) + goto done; + error = xfs_bmbt_lookup_eq(cur, new, &i); + if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); - cur->bc_rec.b.br_state = XFS_EXT_NORM; + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } if ((error = xfs_btree_insert(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } } break; @@ -2581,59 +2453,68 @@ xfs_bmap_add_extent_unwritten_real( * newext. Contiguity is impossible here. * One extent becomes three extents. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, - new->br_startoff - PREV.br_startoff); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + old = PREV; + PREV.br_blockcount = new->br_startoff - PREV.br_startoff; r[0] = *new; r[1].br_startoff = new_endoff; r[1].br_blockcount = - PREV.br_startoff + PREV.br_blockcount - new_endoff; + old.br_startoff + old.br_blockcount - new_endoff; r[1].br_startblock = new->br_startblock + new->br_blockcount; - r[1].br_state = oldext; + r[1].br_state = PREV.br_state; - ++*idx; - xfs_iext_insert(ip, *idx, 2, &r[0], state); + xfs_iext_update_extent(ip, state, icur, &PREV); + xfs_iext_next(ifp, icur); + xfs_iext_insert(ip, icur, &r[1], state); + xfs_iext_insert(ip, icur, &r[0], state); + ifp->if_nextents += 2; - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) + 2); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { rval = XFS_ILOG_CORE; - if ((error = xfs_bmbt_lookup_eq(cur, PREV.br_startoff, - PREV.br_startblock, PREV.br_blockcount, - &i))) + error = xfs_bmbt_lookup_eq(cur, &old, &i); + if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } /* new right extent - oldext */ - if ((error = xfs_bmbt_update(cur, r[1].br_startoff, - r[1].br_startblock, r[1].br_blockcount, - r[1].br_state))) + error = xfs_bmbt_update(cur, &r[1]); + if (error) goto done; /* new left extent - oldext */ cur->bc_rec.b = PREV; - cur->bc_rec.b.br_blockcount = - new->br_startoff - PREV.br_startoff; if ((error = xfs_btree_insert(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } /* * Reset the cursor to the position of the new extent * we are about to insert as we can't trust it after * the previous insert. */ - if ((error = xfs_bmbt_lookup_eq(cur, new->br_startoff, - new->br_startblock, new->br_blockcount, - &i))) + error = xfs_bmbt_lookup_eq(cur, new, &i); + if (error) + goto done; + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); + } /* new middle extent - newext */ - cur->bc_rec.b.br_state = new->br_state; if ((error = xfs_btree_insert(cur, &i))) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } } break; @@ -2651,17 +2532,15 @@ xfs_bmap_add_extent_unwritten_real( } /* update reverse mappings */ - error = xfs_rmap_convert_extent(mp, dfops, ip, whichfork, new); - if (error) - goto done; + xfs_rmap_convert_extent(mp, tp, ip, whichfork, new); /* convert to a btree if necessary */ if (xfs_bmap_needs_btree(ip, whichfork)) { int tmp_logflags; /* partial log flag return val */ ASSERT(cur == NULL); - error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, &cur, - 0, &tmp_logflags, whichfork); + error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, + &tmp_logflags, whichfork); *logflagsp |= tmp_logflags; if (error) goto done; @@ -2669,7 +2548,7 @@ xfs_bmap_add_extent_unwritten_real( /* clear out the allocated field, done with it now in any case. */ if (cur) { - cur->bc_private.b.allocated = 0; + cur->bc_bmap.allocated = 0; *curp = cur; } @@ -2683,156 +2562,6 @@ done: } /* - * Convert a hole to a delayed allocation. - */ -STATIC void -xfs_bmap_add_extent_hole_delay( - xfs_inode_t *ip, /* incore inode pointer */ - int whichfork, - xfs_extnum_t *idx, /* extent number to update/insert */ - xfs_bmbt_irec_t *new) /* new data to add to file extents */ -{ - xfs_ifork_t *ifp; /* inode fork pointer */ - xfs_bmbt_irec_t left; /* left neighbor extent entry */ - xfs_filblks_t newlen=0; /* new indirect size */ - xfs_filblks_t oldlen=0; /* old indirect size */ - xfs_bmbt_irec_t right; /* right neighbor extent entry */ - int state; /* state bits, accessed thru macros */ - xfs_filblks_t temp=0; /* temp for indirect calculations */ - - ifp = XFS_IFORK_PTR(ip, whichfork); - state = 0; - if (whichfork == XFS_COW_FORK) - state |= BMAP_COWFORK; - ASSERT(isnullstartblock(new->br_startblock)); - - /* - * Check and set flags if this segment has a left neighbor - */ - if (*idx > 0) { - state |= BMAP_LEFT_VALID; - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx - 1), &left); - - if (isnullstartblock(left.br_startblock)) - state |= BMAP_LEFT_DELAY; - } - - /* - * Check and set flags if the current (right) segment exists. - * If it doesn't exist, we're converting the hole at end-of-file. - */ - if (*idx < xfs_iext_count(ifp)) { - state |= BMAP_RIGHT_VALID; - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx), &right); - - if (isnullstartblock(right.br_startblock)) - state |= BMAP_RIGHT_DELAY; - } - - /* - * Set contiguity flags on the left and right neighbors. - * Don't let extents get too large, even if the pieces are contiguous. - */ - if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) && - left.br_startoff + left.br_blockcount == new->br_startoff && - left.br_blockcount + new->br_blockcount <= MAXEXTLEN) - state |= BMAP_LEFT_CONTIG; - - if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) && - new->br_startoff + new->br_blockcount == right.br_startoff && - new->br_blockcount + right.br_blockcount <= MAXEXTLEN && - (!(state & BMAP_LEFT_CONTIG) || - (left.br_blockcount + new->br_blockcount + - right.br_blockcount <= MAXEXTLEN))) - state |= BMAP_RIGHT_CONTIG; - - /* - * Switch out based on the contiguity flags. - */ - switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { - case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: - /* - * New allocation is contiguous with delayed allocations - * on the left and on the right. - * Merge all three into a single extent record. - */ - --*idx; - temp = left.br_blockcount + new->br_blockcount + - right.br_blockcount; - - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx), temp); - oldlen = startblockval(left.br_startblock) + - startblockval(new->br_startblock) + - startblockval(right.br_startblock); - newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - oldlen); - xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, *idx), - nullstartblock((int)newlen)); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); - - xfs_iext_remove(ip, *idx + 1, 1, state); - break; - - case BMAP_LEFT_CONTIG: - /* - * New allocation is contiguous with a delayed allocation - * on the left. - * Merge the new allocation with the left neighbor. - */ - --*idx; - temp = left.br_blockcount + new->br_blockcount; - - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx), temp); - oldlen = startblockval(left.br_startblock) + - startblockval(new->br_startblock); - newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - oldlen); - xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, *idx), - nullstartblock((int)newlen)); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); - break; - - case BMAP_RIGHT_CONTIG: - /* - * New allocation is contiguous with a delayed allocation - * on the right. - * Merge the new allocation with the right neighbor. - */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - temp = new->br_blockcount + right.br_blockcount; - oldlen = startblockval(new->br_startblock) + - startblockval(right.br_startblock); - newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - oldlen); - xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, *idx), - new->br_startoff, - nullstartblock((int)newlen), temp, right.br_state); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); - break; - - case 0: - /* - * New allocation is not contiguous with another - * delayed allocation. - * Insert a new entry. - */ - oldlen = newlen = 0; - xfs_iext_insert(ip, *idx, 1, new, state); - break; - } - if (oldlen != newlen) { - ASSERT(oldlen > newlen); - xfs_mod_fdblocks(ip->i_mount, (int64_t)(oldlen - newlen), - false); - /* - * Nothing to do for disk quota accounting here. - */ - } -} - -/* * Convert a hole to a real allocation. */ STATIC int /* error */ @@ -2840,14 +2569,13 @@ xfs_bmap_add_extent_hole_real( struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, - xfs_extnum_t *idx, + struct xfs_iext_cursor *icur, struct xfs_btree_cur **curp, struct xfs_bmbt_irec *new, - xfs_fsblock_t *first, - struct xfs_defer_ops *dfops, - int *logflagsp) + int *logflagsp, + uint32_t flags) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_mount *mp = ip->i_mount; struct xfs_btree_cur *cur = *curp; int error; /* error return value */ @@ -2855,27 +2583,19 @@ xfs_bmap_add_extent_hole_real( xfs_bmbt_irec_t left; /* left neighbor extent entry */ xfs_bmbt_irec_t right; /* right neighbor extent entry */ int rval=0; /* return value (logging flags) */ - int state; /* state bits, accessed thru macros */ + uint32_t state = xfs_bmap_fork_to_state(whichfork); + struct xfs_bmbt_irec old; - ASSERT(*idx >= 0); - ASSERT(*idx <= xfs_iext_count(ifp)); ASSERT(!isnullstartblock(new->br_startblock)); - ASSERT(!cur || !(cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL)); + ASSERT(!cur || !(cur->bc_flags & XFS_BTREE_BMBT_WASDEL)); XFS_STATS_INC(mp, xs_add_exlist); - state = 0; - if (whichfork == XFS_ATTR_FORK) - state |= BMAP_ATTRFORK; - if (whichfork == XFS_COW_FORK) - state |= BMAP_COWFORK; - /* * Check and set flags if this segment has a left neighbor. */ - if (*idx > 0) { + if (xfs_iext_peek_prev_extent(ifp, icur, &left)) { state |= BMAP_LEFT_VALID; - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx - 1), &left); if (isnullstartblock(left.br_startblock)) state |= BMAP_LEFT_DELAY; } @@ -2884,9 +2604,8 @@ xfs_bmap_add_extent_hole_real( * Check and set flags if this segment has a current value. * Not true if we're inserting into the "hole" at eof. */ - if (*idx < xfs_iext_count(ifp)) { + if (xfs_iext_get_extent(ifp, icur, &right)) { state |= BMAP_RIGHT_VALID; - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx), &right); if (isnullstartblock(right.br_startblock)) state |= BMAP_RIGHT_DELAY; } @@ -2899,17 +2618,19 @@ xfs_bmap_add_extent_hole_real( left.br_startoff + left.br_blockcount == new->br_startoff && left.br_startblock + left.br_blockcount == new->br_startblock && left.br_state == new->br_state && - left.br_blockcount + new->br_blockcount <= MAXEXTLEN) + left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN && + xfs_bmap_same_rtgroup(ip, whichfork, &left, new)) state |= BMAP_LEFT_CONTIG; if ((state & BMAP_RIGHT_VALID) && !(state & BMAP_RIGHT_DELAY) && new->br_startoff + new->br_blockcount == right.br_startoff && new->br_startblock + new->br_blockcount == right.br_startblock && new->br_state == right.br_state && - new->br_blockcount + right.br_blockcount <= MAXEXTLEN && + new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN && (!(state & BMAP_LEFT_CONTIG) || left.br_blockcount + new->br_blockcount + - right.br_blockcount <= MAXEXTLEN)) + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN) && + xfs_bmap_same_rtgroup(ip, whichfork, new, &right)) state |= BMAP_RIGHT_CONTIG; error = 0; @@ -2923,41 +2644,42 @@ xfs_bmap_add_extent_hole_real( * left and on the right. * Merge all three into a single extent record. */ - --*idx; - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx), - left.br_blockcount + new->br_blockcount + - right.br_blockcount); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + left.br_blockcount += new->br_blockcount + right.br_blockcount; - xfs_iext_remove(ip, *idx + 1, 1, state); + xfs_iext_remove(ip, icur, state); + xfs_iext_prev(ifp, icur); + xfs_iext_update_extent(ip, state, icur, &left); + ifp->if_nextents--; - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) - 1); if (cur == NULL) { rval = XFS_ILOG_CORE | xfs_ilog_fext(whichfork); } else { rval = XFS_ILOG_CORE; - error = xfs_bmbt_lookup_eq(cur, right.br_startoff, - right.br_startblock, right.br_blockcount, - &i); + error = xfs_bmbt_lookup_eq(cur, &right, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } error = xfs_btree_delete(cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } error = xfs_btree_decrement(cur, 0, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - error = xfs_bmbt_update(cur, left.br_startoff, - left.br_startblock, - left.br_blockcount + - new->br_blockcount + - right.br_blockcount, - left.br_state); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(cur, &left); if (error) goto done; } @@ -2969,27 +2691,25 @@ xfs_bmap_add_extent_hole_real( * on the left. * Merge the new allocation with the left neighbor. */ - --*idx; - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx), - left.br_blockcount + new->br_blockcount); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + old = left; + left.br_blockcount += new->br_blockcount; + + xfs_iext_prev(ifp, icur); + xfs_iext_update_extent(ip, state, icur, &left); if (cur == NULL) { rval = xfs_ilog_fext(whichfork); } else { rval = 0; - error = xfs_bmbt_lookup_eq(cur, left.br_startoff, - left.br_startblock, left.br_blockcount, - &i); + error = xfs_bmbt_lookup_eq(cur, &old, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - error = xfs_bmbt_update(cur, left.br_startoff, - left.br_startblock, - left.br_blockcount + - new->br_blockcount, - left.br_state); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(cur, &left); if (error) goto done; } @@ -3001,29 +2721,26 @@ xfs_bmap_add_extent_hole_real( * on the right. * Merge the new allocation with the right neighbor. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, *idx), - new->br_startoff, new->br_startblock, - new->br_blockcount + right.br_blockcount, - right.br_state); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + old = right; + + right.br_startoff = new->br_startoff; + right.br_startblock = new->br_startblock; + right.br_blockcount += new->br_blockcount; + xfs_iext_update_extent(ip, state, icur, &right); if (cur == NULL) { rval = xfs_ilog_fext(whichfork); } else { rval = 0; - error = xfs_bmbt_lookup_eq(cur, - right.br_startoff, - right.br_startblock, - right.br_blockcount, &i); + error = xfs_bmbt_lookup_eq(cur, &old, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - error = xfs_bmbt_update(cur, new->br_startoff, - new->br_startblock, - new->br_blockcount + - right.br_blockcount, - right.br_state); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } + error = xfs_bmbt_update(cur, &right); if (error) goto done; } @@ -3035,41 +2752,44 @@ xfs_bmap_add_extent_hole_real( * real allocation. * Insert a new entry. */ - xfs_iext_insert(ip, *idx, 1, new, state); - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) + 1); + xfs_iext_insert(ip, icur, new, state); + ifp->if_nextents++; + if (cur == NULL) { rval = XFS_ILOG_CORE | xfs_ilog_fext(whichfork); } else { rval = XFS_ILOG_CORE; - error = xfs_bmbt_lookup_eq(cur, - new->br_startoff, - new->br_startblock, - new->br_blockcount, &i); + error = xfs_bmbt_lookup_eq(cur, new, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done); - cur->bc_rec.b.br_state = new->br_state; + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } error = xfs_btree_insert(cur, &i); if (error) goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto done; + } } break; } - /* add reverse mapping */ - error = xfs_rmap_map_extent(mp, dfops, ip, whichfork, new); - if (error) - goto done; + /* add reverse mapping unless caller opted out */ + if (!(flags & XFS_BMAPI_NORMAP)) + xfs_rmap_map_extent(tp, ip, whichfork, new); /* convert to a btree if necessary */ if (xfs_bmap_needs_btree(ip, whichfork)) { int tmp_logflags; /* partial log flag return val */ ASSERT(cur == NULL); - error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, curp, - 0, &tmp_logflags, whichfork); + error = xfs_bmap_extents_to_btree(tp, ip, curp, 0, + &tmp_logflags, whichfork); *logflagsp |= tmp_logflags; cur = *curp; if (error) @@ -3078,7 +2798,7 @@ xfs_bmap_add_extent_hole_real( /* clear out the allocated field, done with it now in any case. */ if (cur) - cur->bc_private.b.allocated = 0; + cur->bc_bmap.allocated = 0; xfs_bmap_check_leaf_extents(cur, ip, whichfork); done: @@ -3091,7 +2811,7 @@ done: */ /* - * Adjust the size of the new extent based on di_extsize and rt extsize. + * Adjust the size of the new extent based on i_extsize and rt extsize. */ int xfs_bmap_extsize_align( @@ -3139,7 +2859,7 @@ xfs_bmap_extsize_align( * perform this alignment, or if a truncate shot us in the * foot. */ - temp = do_mod(orig_off, extsz); + div_u64_rem(orig_off, extsz, &temp); if (temp) { align_alen += temp; align_off -= temp; @@ -3152,15 +2872,15 @@ xfs_bmap_extsize_align( /* * For large extent hint sizes, the aligned extent might be larger than - * MAXEXTLEN. In that case, reduce the size by an extsz so that it pulls - * the length back under MAXEXTLEN. The outer allocation loops handle - * short allocation just fine, so it is safe to do this. We only want to - * do it when we are forced to, though, because it means more allocation - * operations are required. + * XFS_BMBT_MAX_EXTLEN. In that case, reduce the size by an extsz so + * that it pulls the length back under XFS_BMBT_MAX_EXTLEN. The outer + * allocation loops handle short allocation just fine, so it is safe to + * do this. We only want to do it when we are forced to, though, because + * it means more allocation operations are required. */ - while (align_alen > MAXEXTLEN) + while (align_alen > XFS_MAX_BMBT_EXTLEN) align_alen -= extsz; - ASSERT(align_alen <= MAXEXTLEN); + ASSERT(align_alen <= XFS_MAX_BMBT_EXTLEN); /* * If the previous block overlaps with this proposed allocation @@ -3214,7 +2934,7 @@ xfs_bmap_extsize_align( * If realtime, and the result isn't a multiple of the realtime * extent size we need to remove blocks until it is. */ - if (rt && (temp = (align_alen % mp->m_sb.sb_rextsize))) { + if (rt && (temp = xfs_extlen_to_rtxmod(mp, align_alen))) { /* * We're not covering the original request, or * we won't be able to once we fix the length. @@ -3241,7 +2961,7 @@ xfs_bmap_extsize_align( else { align_alen -= orig_off - align_off; align_off = orig_off; - align_alen -= align_alen % mp->m_sb.sb_rextsize; + align_alen -= xfs_extlen_to_rtxmod(mp, align_alen); } /* * Result doesn't cover the request, fail it. @@ -3250,9 +2970,9 @@ xfs_bmap_extsize_align( return -EINVAL; } else { ASSERT(orig_off >= align_off); - /* see MAXEXTLEN handling above */ + /* see XFS_BMBT_MAX_EXTLEN handling above */ ASSERT(orig_end <= align_off + align_alen || - align_alen + extsz > MAXEXTLEN); + align_alen + extsz > XFS_MAX_BMBT_EXTLEN); } #ifdef DEBUG @@ -3267,54 +2987,65 @@ xfs_bmap_extsize_align( return 0; } +static inline bool +xfs_bmap_adjacent_valid( + struct xfs_bmalloca *ap, + xfs_fsblock_t x, + xfs_fsblock_t y) +{ + struct xfs_mount *mp = ap->ip->i_mount; + + if (XFS_IS_REALTIME_INODE(ap->ip) && + (ap->datatype & XFS_ALLOC_USERDATA)) { + if (!xfs_has_rtgroups(mp)) + return x < mp->m_sb.sb_rblocks; + + return xfs_rtb_to_rgno(mp, x) == xfs_rtb_to_rgno(mp, y) && + xfs_rtb_to_rgno(mp, x) < mp->m_sb.sb_rgcount && + xfs_rtb_to_rtx(mp, x) < mp->m_sb.sb_rgextents; + + } + + return XFS_FSB_TO_AGNO(mp, x) == XFS_FSB_TO_AGNO(mp, y) && + XFS_FSB_TO_AGNO(mp, x) < mp->m_sb.sb_agcount && + XFS_FSB_TO_AGBNO(mp, x) < mp->m_sb.sb_agblocks; +} + #define XFS_ALLOC_GAP_UNITS 4 -void +/* returns true if ap->blkno was modified */ +bool xfs_bmap_adjacent( 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 */ - xfs_mount_t *mp; /* mount point structure */ - int nullfb; /* true if ap->firstblock isn't set */ - int rt; /* true if inode is realtime */ - -#define ISVALID(x,y) \ - (rt ? \ - (x) < mp->m_sb.sb_rblocks : \ - XFS_FSB_TO_AGNO(mp, x) == XFS_FSB_TO_AGNO(mp, y) && \ - XFS_FSB_TO_AGNO(mp, x) < mp->m_sb.sb_agcount && \ - XFS_FSB_TO_AGBNO(mp, x) < mp->m_sb.sb_agblocks) - - mp = ap->ip->i_mount; - nullfb = *ap->firstblock == NULLFSBLOCK; - rt = XFS_IS_REALTIME_INODE(ap->ip) && - xfs_alloc_is_userdata(ap->datatype); - fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock); + xfs_fsblock_t adjust; /* adjustment to block numbers */ + /* * If allocating at eof, and there's a previous real block, * try to use its last block as our starting point. */ if (ap->eof && ap->prev.br_startoff != NULLFILEOFF && !isnullstartblock(ap->prev.br_startblock) && - ISVALID(ap->prev.br_startblock + ap->prev.br_blockcount, - ap->prev.br_startblock)) { + xfs_bmap_adjacent_valid(ap, + ap->prev.br_startblock + ap->prev.br_blockcount, + ap->prev.br_startblock)) { ap->blkno = ap->prev.br_startblock + ap->prev.br_blockcount; /* * Adjust for the gap between prevp and us. */ adjust = ap->offset - (ap->prev.br_startoff + ap->prev.br_blockcount); - if (adjust && - ISVALID(ap->blkno + adjust, ap->prev.br_startblock)) + if (adjust && xfs_bmap_adjacent_valid(ap, ap->blkno + adjust, + ap->prev.br_startblock)) ap->blkno += adjust; + return true; } /* * If not at eof, then compare the two neighbor blocks. * Figure out whether either one gives us a good starting point, * and pick the better one. */ - else if (!ap->eof) { + if (!ap->eof) { xfs_fsblock_t gotbno; /* right side block number */ xfs_fsblock_t gotdiff=0; /* right side difference */ xfs_fsblock_t prevbno; /* left side block number */ @@ -3328,7 +3059,8 @@ xfs_bmap_adjacent( !isnullstartblock(ap->prev.br_startblock) && (prevbno = ap->prev.br_startblock + ap->prev.br_blockcount) && - ISVALID(prevbno, ap->prev.br_startblock)) { + xfs_bmap_adjacent_valid(ap, prevbno, + ap->prev.br_startblock)) { /* * Calculate gap to end of previous block. */ @@ -3344,18 +3076,11 @@ xfs_bmap_adjacent( * number, then just use the end of the previous block. */ if (prevdiff <= XFS_ALLOC_GAP_UNITS * ap->length && - ISVALID(prevbno + prevdiff, - ap->prev.br_startblock)) + xfs_bmap_adjacent_valid(ap, prevbno + prevdiff, + ap->prev.br_startblock)) prevbno += adjust; else prevdiff += adjust; - /* - * If the firstblock forbids it, can't use it, - * must use default. - */ - if (!rt && !nullfb && - XFS_FSB_TO_AGNO(mp, prevbno) != fb_agno) - prevbno = NULLFSBLOCK; } /* * No previous block or can't follow it, just default. @@ -3384,20 +3109,15 @@ xfs_bmap_adjacent( * offset by our length. */ if (gotdiff <= XFS_ALLOC_GAP_UNITS * ap->length && - ISVALID(gotbno - gotdiff, gotbno)) + xfs_bmap_adjacent_valid(ap, gotbno - gotdiff, + gotbno)) gotbno -= adjust; - else if (ISVALID(gotbno - ap->length, gotbno)) { + else if (xfs_bmap_adjacent_valid(ap, gotbno - ap->length, + gotbno)) { gotbno -= ap->length; gotdiff += adjust - ap->length; } else gotdiff += adjust; - /* - * If the firstblock forbids it, can't use it, - * must use default. - */ - if (!rt && !nullfb && - XFS_FSB_TO_AGNO(mp, gotbno) != fb_agno) - gotbno = NULLFSBLOCK; } /* * No next block, just default. @@ -3408,404 +3128,545 @@ xfs_bmap_adjacent( * If both valid, pick the better one, else the only good * one, else ap->blkno is already set (to 0 or the inode block). */ - if (prevbno != NULLFSBLOCK && gotbno != NULLFSBLOCK) + if (prevbno != NULLFSBLOCK && gotbno != NULLFSBLOCK) { ap->blkno = prevdiff <= gotdiff ? prevbno : gotbno; - else if (prevbno != NULLFSBLOCK) + return true; + } + if (prevbno != NULLFSBLOCK) { ap->blkno = prevbno; - else if (gotbno != NULLFSBLOCK) + return true; + } + if (gotbno != NULLFSBLOCK) { ap->blkno = gotbno; + return true; + } } -#undef ISVALID + + return false; } -static int +int xfs_bmap_longest_free_extent( + struct xfs_perag *pag, struct xfs_trans *tp, - xfs_agnumber_t ag, - xfs_extlen_t *blen, - int *notinit) + xfs_extlen_t *blen) { - struct xfs_mount *mp = tp->t_mountp; - struct xfs_perag *pag; xfs_extlen_t longest; int error = 0; - pag = xfs_perag_get(mp, ag); - if (!pag->pagf_init) { - error = xfs_alloc_pagf_init(mp, tp, ag, XFS_ALLOC_FLAG_TRYLOCK); + if (!xfs_perag_initialised_agf(pag)) { + error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_TRYLOCK, + NULL); if (error) - goto out; - - if (!pag->pagf_init) { - *notinit = 1; - goto out; - } + return error; } - longest = xfs_alloc_longest_free_extent(mp, pag, - xfs_alloc_min_freelist(mp, pag), + longest = xfs_alloc_longest_free_extent(pag, + xfs_alloc_min_freelist(pag_mount(pag), pag), xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE)); if (*blen < longest) *blen = longest; -out: - xfs_perag_put(pag); - return error; + return 0; } -static void +static xfs_extlen_t xfs_bmap_select_minlen( struct xfs_bmalloca *ap, struct xfs_alloc_arg *args, - xfs_extlen_t *blen, - int notinit) + xfs_extlen_t blen) { - if (notinit || *blen < ap->minlen) { - /* - * Since we did a BUF_TRYLOCK above, it is possible that - * there is space for this request. - */ - 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 { - /* - * Otherwise we've seen an extent as big as maxlen, use that - * as the minimum. - */ - args->minlen = args->maxlen; - } + + /* + * Since we used XFS_ALLOC_FLAG_TRYLOCK in _longest_free_extent(), it is + * possible that there is enough contiguous free space for this request. + */ + if (blen < ap->minlen) + return ap->minlen; + + /* + * If the best seen length is less than the request length, + * use the best as the minimum, otherwise we've got the maxlen we + * were asked for. + */ + if (blen < args->maxlen) + return blen; + return args->maxlen; } -STATIC int -xfs_bmap_btalloc_nullfb( +static int +xfs_bmap_btalloc_select_lengths( 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, startag; - int notinit = 0; - int error; + struct xfs_mount *mp = args->mp; + struct xfs_perag *pag; + xfs_agnumber_t agno, startag; + int error = 0; - args->type = XFS_ALLOCTYPE_START_BNO; - args->total = ap->total; + if (ap->tp->t_flags & XFS_TRANS_LOWMODE) { + args->total = ap->minlen; + args->minlen = ap->minlen; + return 0; + } - startag = ag = XFS_FSB_TO_AGNO(mp, args->fsbno); + args->total = ap->total; + startag = XFS_FSB_TO_AGNO(mp, ap->blkno); if (startag == NULLAGNUMBER) - startag = ag = 0; + startag = 0; - while (*blen < args->maxlen) { - error = xfs_bmap_longest_free_extent(args->tp, ag, blen, - ¬init); - if (error) - return error; - - if (++ag == mp->m_sb.sb_agcount) - ag = 0; - if (ag == startag) + *blen = 0; + for_each_perag_wrap(mp, startag, agno, pag) { + error = xfs_bmap_longest_free_extent(pag, args->tp, blen); + if (error && error != -EAGAIN) + break; + error = 0; + if (*blen >= args->maxlen) break; } + if (pag) + xfs_perag_rele(pag); - xfs_bmap_select_minlen(ap, args, blen, notinit); - return 0; + args->minlen = xfs_bmap_select_minlen(ap, args, *blen); + return error; } -STATIC int -xfs_bmap_btalloc_filestreams( - struct xfs_bmalloca *ap, - struct xfs_alloc_arg *args, - xfs_extlen_t *blen) +/* Update all inode and quota accounting for the allocation we just did. */ +void +xfs_bmap_alloc_account( + struct xfs_bmalloca *ap) { - struct xfs_mount *mp = ap->ip->i_mount; - xfs_agnumber_t ag; - int notinit = 0; - int error; + bool isrt = XFS_IS_REALTIME_INODE(ap->ip) && + !(ap->flags & XFS_BMAPI_ATTRFORK); + uint fld; - 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; + if (ap->flags & XFS_BMAPI_COWFORK) { + /* + * COW fork blocks are in-core only and thus are treated as + * in-core quota reservation (like delalloc blocks) even when + * converted to real blocks. The quota reservation is not + * accounted to disk until blocks are remapped to the data + * fork. So if these blocks were previously delalloc, we + * already have quota reservation and there's nothing to do + * yet. + */ + if (ap->wasdel) { + xfs_mod_delalloc(ap->ip, -(int64_t)ap->length, 0); + return; + } + /* + * Otherwise, we've allocated blocks in a hole. The transaction + * has acquired in-core quota reservation for this extent. + * Rather than account these as real blocks, however, we reduce + * the transaction quota reservation based on the allocation. + * This essentially transfers the transaction quota reservation + * to that of a delalloc extent. + */ + ap->ip->i_delayed_blks += ap->length; + xfs_trans_mod_dquot_byino(ap->tp, ap->ip, isrt ? + XFS_TRANS_DQ_RES_RTBLKS : XFS_TRANS_DQ_RES_BLKS, + -(long)ap->length); + return; } - xfs_bmap_select_minlen(ap, args, blen, notinit); + /* data/attr fork only */ + ap->ip->i_nblocks += ap->length; + xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE); + if (ap->wasdel) { + ap->ip->i_delayed_blks -= ap->length; + xfs_mod_delalloc(ap->ip, -(int64_t)ap->length, 0); + fld = isrt ? XFS_TRANS_DQ_DELRTBCOUNT : XFS_TRANS_DQ_DELBCOUNT; + } else { + fld = isrt ? XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT; + } - /* - * Set the failure fallback case to look in the selected AG as stream - * may have moved. - */ - ap->blkno = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0); - return 0; + xfs_trans_mod_dquot_byino(ap->tp, ap->ip, fld, ap->length); } -STATIC int -xfs_bmap_btalloc( - struct xfs_bmalloca *ap) /* bmap alloc argument struct */ +static int +xfs_bmap_compute_alignments( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args) { - xfs_mount_t *mp; /* mount point structure */ - xfs_alloctype_t atype = 0; /* type for allocation routines */ - xfs_extlen_t align = 0; /* minimum allocation alignment */ - xfs_agnumber_t fb_agno; /* ag number of ap->firstblock */ - xfs_agnumber_t ag; - xfs_alloc_arg_t args; - xfs_extlen_t blen; - xfs_extlen_t nextminlen = 0; - int nullfb; /* true if ap->firstblock isn't set */ - int isaligned; - int tryagain; - int error; - int stripe_align; - - ASSERT(ap->length); - - mp = ap->ip->i_mount; + struct xfs_mount *mp = args->mp; + xfs_extlen_t align = 0; /* minimum allocation alignment */ + int stripe_align = 0; /* stripe alignment for allocation is determined by mount parameters */ - stripe_align = 0; - if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC)) + if (mp->m_swidth && xfs_has_swalloc(mp)) stripe_align = mp->m_swidth; else if (mp->m_dalign) stripe_align = mp->m_dalign; if (ap->flags & XFS_BMAPI_COWFORK) align = xfs_get_cowextsz_hint(ap->ip); - else if (xfs_alloc_is_userdata(ap->datatype)) + else if (ap->datatype & XFS_ALLOC_USERDATA) align = xfs_get_extsz_hint(ap->ip); + + /* Try to align start block to any minimum allocation alignment */ + if (align > 1 && (ap->flags & XFS_BMAPI_EXTSZALIGN)) + args->alignment = align; + if (align) { - error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, - align, 0, ap->eof, 0, ap->conv, - &ap->offset, &ap->length); - ASSERT(!error); + if (xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, align, 0, + ap->eof, 0, ap->conv, &ap->offset, + &ap->length)) + ASSERT(0); ASSERT(ap->length); } + /* apply extent size hints if obtained earlier */ + if (align) { + args->prod = align; + div_u64_rem(ap->offset, args->prod, &args->mod); + if (args->mod) + args->mod = args->prod - args->mod; + } else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) { + args->prod = 1; + args->mod = 0; + } else { + args->prod = PAGE_SIZE >> mp->m_sb.sb_blocklog; + div_u64_rem(ap->offset, args->prod, &args->mod); + if (args->mod) + args->mod = args->prod - args->mod; + } - nullfb = *ap->firstblock == NULLFSBLOCK; - fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock); - if (nullfb) { - if (xfs_alloc_is_userdata(ap->datatype) && - xfs_inode_is_filestream(ap->ip)) { - ag = xfs_filestream_lookup_ag(ap->ip); - ag = (ag != NULLAGNUMBER) ? ag : 0; - ap->blkno = XFS_AGB_TO_FSB(mp, ag, 0); - } else { - ap->blkno = XFS_INO_TO_FSB(mp, ap->ip->i_ino); - } - } else - ap->blkno = *ap->firstblock; + return stripe_align; +} + +static void +xfs_bmap_process_allocated_extent( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args, + xfs_fileoff_t orig_offset, + xfs_extlen_t orig_length) +{ + ap->blkno = args->fsbno; + ap->length = args->len; + /* + * If the extent size hint is active, we tried to round the + * caller's allocation request offset down to extsz and the + * length up to another extsz boundary. If we found a free + * extent we mapped it in starting at this new offset. If the + * newly mapped space isn't long enough to cover any of the + * range of offsets that was originally requested, move the + * mapping up so that we can fill as much of the caller's + * original request as possible. Free space is apparently + * very fragmented so we're unlikely to be able to satisfy the + * hints anyway. + */ + if (ap->length <= orig_length) + ap->offset = orig_offset; + else if (ap->offset + ap->length < orig_offset + orig_length) + ap->offset = orig_offset + orig_length - ap->length; + xfs_bmap_alloc_account(ap); +} - xfs_bmap_adjacent(ap); +static int +xfs_bmap_exact_minlen_extent_alloc( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args) +{ + if (ap->minlen != 1) { + args->fsbno = NULLFSBLOCK; + return 0; + } + + args->alloc_minlen_only = 1; + args->minlen = args->maxlen = ap->minlen; + args->total = ap->total; /* - * If allowed, use ap->blkno; otherwise must use firstblock since - * it's in the right allocation group. + * Unlike the longest extent available in an AG, we don't track + * the length of an AG's shortest extent. + * XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT is a debug only knob and + * hence we can afford to start traversing from the 0th AG since + * we need not be concerned about a drop in performance in + * "debug only" code paths. */ - if (nullfb || XFS_FSB_TO_AGNO(mp, ap->blkno) == fb_agno) - ; - else - ap->blkno = *ap->firstblock; + ap->blkno = XFS_AGB_TO_FSB(ap->ip->i_mount, 0, 0); + /* - * Normal allocation, done through xfs_alloc_vextent. + * Call xfs_bmap_btalloc_low_space here as it first does a "normal" AG + * iteration and then drops args->total to args->minlen, which might be + * required to find an allocation for the transaction reservation when + * the file system is very full. */ - tryagain = isaligned = 0; - memset(&args, 0, sizeof(args)); - args.tp = ap->tp; - args.mp = mp; - args.fsbno = ap->blkno; - xfs_rmap_skip_owner_update(&args.oinfo); + return xfs_bmap_btalloc_low_space(ap, args); +} + +/* + * If we are not low on available data blocks and we are allocating at + * EOF, optimise allocation for contiguous file extension and/or stripe + * alignment of the new extent. + * + * NOTE: ap->aeof is only set if the allocation length is >= the + * stripe unit and the allocation offset is at the end of file. + */ +static int +xfs_bmap_btalloc_at_eof( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args, + xfs_extlen_t blen, + int stripe_align, + bool ag_only) +{ + struct xfs_mount *mp = args->mp; + struct xfs_perag *caller_pag = args->pag; + int error; + + /* + * If there are already extents in the file, and xfs_bmap_adjacent() has + * given a better blkno, try an exact EOF block allocation to extend the + * file as a contiguous extent. If that fails, or it's the first + * allocation in a file, just try for a stripe aligned allocation. + */ + if (ap->eof) { + xfs_extlen_t nextminlen = 0; - /* Trim the allocation back to the maximum an AG can fit. */ - args.maxlen = MIN(ap->length, mp->m_ag_max_usable); - args.firstblock = *ap->firstblock; - blen = 0; - if (nullfb) { /* - * 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. + * Compute the minlen+alignment for the next case. Set slop so + * that the value of minlen+alignment+slop doesn't go up between + * the calls. */ - if (xfs_alloc_is_userdata(ap->datatype) && - xfs_inode_is_filestream(ap->ip)) - error = xfs_bmap_btalloc_filestreams(ap, &args, &blen); + args->alignment = 1; + if (blen > stripe_align && blen <= args->maxlen) + nextminlen = blen - stripe_align; + else + nextminlen = args->minlen; + if (nextminlen + stripe_align > args->minlen + 1) + args->minalignslop = nextminlen + stripe_align - + args->minlen - 1; else - error = xfs_bmap_btalloc_nullfb(ap, &args, &blen); + args->minalignslop = 0; + + if (!caller_pag) + args->pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ap->blkno)); + error = xfs_alloc_vextent_exact_bno(args, ap->blkno); + if (!caller_pag) { + xfs_perag_put(args->pag); + args->pag = NULL; + } if (error) return error; - } else if (ap->dfops->dop_low) { - if (xfs_inode_is_filestream(ap->ip)) - args.type = XFS_ALLOCTYPE_FIRST_AG; - else - args.type = XFS_ALLOCTYPE_START_BNO; - args.total = args.minlen = ap->minlen; + + if (args->fsbno != NULLFSBLOCK) + return 0; + /* + * Exact allocation failed. Reset to try an aligned allocation + * according to the original allocation specification. + */ + args->alignment = stripe_align; + args->minlen = nextminlen; + args->minalignslop = 0; } else { - args.type = XFS_ALLOCTYPE_NEAR_BNO; - args.total = ap->total; - args.minlen = ap->minlen; + /* + * Adjust minlen to try and preserve alignment if we + * can't guarantee an aligned maxlen extent. + */ + args->alignment = stripe_align; + if (blen > args->alignment && + blen <= args->maxlen + args->alignment) + args->minlen = blen - args->alignment; + args->minalignslop = 0; } - /* apply extent size hints if obtained earlier */ - if (align) { - args.prod = align; - if ((args.mod = (xfs_extlen_t)do_mod(ap->offset, args.prod))) - args.mod = (xfs_extlen_t)(args.prod - args.mod); - } else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) { - args.prod = 1; - args.mod = 0; + + if (ag_only) { + error = xfs_alloc_vextent_near_bno(args, ap->blkno); } else { - args.prod = PAGE_SIZE >> mp->m_sb.sb_blocklog; - if ((args.mod = (xfs_extlen_t)(do_mod(ap->offset, args.prod)))) - args.mod = (xfs_extlen_t)(args.prod - args.mod); + args->pag = NULL; + error = xfs_alloc_vextent_start_ag(args, ap->blkno); + ASSERT(args->pag == NULL); + args->pag = caller_pag; } + if (error) + return error; + + if (args->fsbno != NULLFSBLOCK) + return 0; + /* - * If we are not low on available data blocks, and the - * underlying logical volume manager is a stripe, and - * the file offset is zero then try to allocate data - * blocks on stripe unit boundary. - * NOTE: ap->aeof is only set if the allocation length - * is >= the stripe unit and the allocation offset is - * at the end of file. + * Allocation failed, so turn return the allocation args to their + * original non-aligned state so the caller can proceed on allocation + * failure as if this function was never called. */ - if (!ap->dfops->dop_low && ap->aeof) { - if (!ap->offset) { - args.alignment = stripe_align; - atype = args.type; - isaligned = 1; - /* - * Adjust for alignment - */ - if (blen > args.alignment && blen <= args.maxlen) - args.minlen = blen - args.alignment; - args.minalignslop = 0; - } else { - /* - * First try an exact bno allocation. - * If it fails then do a near or start bno - * allocation with alignment turned on. - */ - atype = args.type; - tryagain = 1; - args.type = XFS_ALLOCTYPE_THIS_BNO; - args.alignment = 1; - /* - * Compute the minlen+alignment for the - * next case. Set slop so that the value - * of minlen+alignment+slop doesn't go up - * between the calls. - */ - if (blen > stripe_align && blen <= args.maxlen) - nextminlen = blen - stripe_align; - else - nextminlen = args.minlen; - if (nextminlen + stripe_align > args.minlen + 1) - args.minalignslop = - nextminlen + stripe_align - - args.minlen - 1; - else - args.minalignslop = 0; - } - } else { - args.alignment = 1; - args.minalignslop = 0; + args->alignment = 1; + return 0; +} + +/* + * We have failed multiple allocation attempts so now are in a low space + * allocation situation. Try a locality first full filesystem minimum length + * allocation whilst still maintaining necessary total block reservation + * requirements. + * + * If that fails, we are now critically low on space, so perform a last resort + * allocation attempt: no reserve, no locality, blocking, minimum length, full + * filesystem free space scan. We also indicate to future allocations in this + * transaction that we are critically low on space so they don't waste time on + * allocation modes that are unlikely to succeed. + */ +int +xfs_bmap_btalloc_low_space( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args) +{ + int error; + + if (args->minlen > ap->minlen) { + args->minlen = ap->minlen; + error = xfs_alloc_vextent_start_ag(args, ap->blkno); + if (error || args->fsbno != NULLFSBLOCK) + return error; } - args.minleft = ap->minleft; - args.wasdel = ap->wasdel; - args.resv = XFS_AG_RESV_NONE; - args.datatype = ap->datatype; - if (ap->datatype & XFS_ALLOC_USERDATA_ZERO) - args.ip = ap->ip; - - error = xfs_alloc_vextent(&args); + + /* Last ditch attempt before failure is declared. */ + args->total = ap->minlen; + error = xfs_alloc_vextent_first_ag(args, 0); if (error) return error; + ap->tp->t_flags |= XFS_TRANS_LOWMODE; + return 0; +} - if (tryagain && args.fsbno == NULLFSBLOCK) { - /* - * Exact allocation failed. Now try with alignment - * turned on. - */ - args.type = atype; - args.fsbno = ap->blkno; - args.alignment = stripe_align; - args.minlen = nextminlen; - args.minalignslop = 0; - isaligned = 1; - if ((error = xfs_alloc_vextent(&args))) - return error; - } - if (isaligned && args.fsbno == NULLFSBLOCK) { - /* - * allocation failed, so turn off alignment and - * try again. - */ - args.type = atype; - args.fsbno = ap->blkno; - args.alignment = 0; - if ((error = xfs_alloc_vextent(&args))) - return error; - } - if (args.fsbno == NULLFSBLOCK && nullfb && - args.minlen > ap->minlen) { - args.minlen = ap->minlen; - args.type = XFS_ALLOCTYPE_START_BNO; - args.fsbno = ap->blkno; - if ((error = xfs_alloc_vextent(&args))) - return error; +static int +xfs_bmap_btalloc_filestreams( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args, + int stripe_align) +{ + xfs_extlen_t blen = 0; + int error = 0; + + + error = xfs_filestream_select_ag(ap, args, &blen); + if (error) + return error; + ASSERT(args->pag); + + /* + * If we are in low space mode, then optimal allocation will fail so + * prepare for minimal allocation and jump to the low space algorithm + * immediately. + */ + if (ap->tp->t_flags & XFS_TRANS_LOWMODE) { + args->minlen = ap->minlen; + ASSERT(args->fsbno == NULLFSBLOCK); + goto out_low_space; } - if (args.fsbno == NULLFSBLOCK && nullfb) { - args.fsbno = 0; - args.type = XFS_ALLOCTYPE_FIRST_AG; - args.total = ap->minlen; - if ((error = xfs_alloc_vextent(&args))) + + args->minlen = xfs_bmap_select_minlen(ap, args, blen); + if (ap->aeof) + error = xfs_bmap_btalloc_at_eof(ap, args, blen, stripe_align, + true); + + if (!error && args->fsbno == NULLFSBLOCK) + error = xfs_alloc_vextent_near_bno(args, ap->blkno); + +out_low_space: + /* + * We are now done with the perag reference for the filestreams + * association provided by xfs_filestream_select_ag(). Release it now as + * we've either succeeded, had a fatal error or we are out of space and + * need to do a full filesystem scan for free space which will take it's + * own references. + */ + xfs_perag_rele(args->pag); + args->pag = NULL; + if (error || args->fsbno != NULLFSBLOCK) + return error; + + return xfs_bmap_btalloc_low_space(ap, args); +} + +static int +xfs_bmap_btalloc_best_length( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args, + int stripe_align) +{ + xfs_extlen_t blen = 0; + int error; + + ap->blkno = XFS_INO_TO_FSB(args->mp, ap->ip->i_ino); + if (!xfs_bmap_adjacent(ap)) + ap->eof = false; + + /* + * 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. + */ + error = xfs_bmap_btalloc_select_lengths(ap, args, &blen); + if (error) + return error; + + /* + * Don't attempt optimal EOF allocation if previous allocations barely + * succeeded due to being near ENOSPC. It is highly unlikely we'll get + * optimal or even aligned allocations in this case, so don't waste time + * trying. + */ + if (ap->aeof && !(ap->tp->t_flags & XFS_TRANS_LOWMODE)) { + error = xfs_bmap_btalloc_at_eof(ap, args, blen, stripe_align, + false); + if (error || args->fsbno != NULLFSBLOCK) return error; - ap->dfops->dop_low = true; } + + error = xfs_alloc_vextent_start_ag(args, ap->blkno); + if (error || args->fsbno != NULLFSBLOCK) + return error; + + return xfs_bmap_btalloc_low_space(ap, args); +} + +static int +xfs_bmap_btalloc( + struct xfs_bmalloca *ap) +{ + struct xfs_mount *mp = ap->ip->i_mount; + struct xfs_alloc_arg args = { + .tp = ap->tp, + .mp = mp, + .fsbno = NULLFSBLOCK, + .oinfo = XFS_RMAP_OINFO_SKIP_UPDATE, + .minleft = ap->minleft, + .wasdel = ap->wasdel, + .resv = XFS_AG_RESV_NONE, + .datatype = ap->datatype, + .alignment = 1, + .minalignslop = 0, + }; + xfs_fileoff_t orig_offset; + xfs_extlen_t orig_length; + int error; + int stripe_align; + + ASSERT(ap->length); + orig_offset = ap->offset; + orig_length = ap->length; + + stripe_align = xfs_bmap_compute_alignments(ap, &args); + + /* Trim the allocation back to the maximum an AG can fit. */ + args.maxlen = min(ap->length, mp->m_ag_max_usable); + + if (unlikely(XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT))) + error = xfs_bmap_exact_minlen_extent_alloc(ap, &args); + else if ((ap->datatype & XFS_ALLOC_USERDATA) && + xfs_inode_is_filestream(ap->ip)) + error = xfs_bmap_btalloc_filestreams(ap, &args, stripe_align); + else + error = xfs_bmap_btalloc_best_length(ap, &args, stripe_align); + if (error) + return error; + if (args.fsbno != NULLFSBLOCK) { - /* - * check the allocation happened at the same or higher AG than - * the first block that was allocated. - */ - ASSERT(*ap->firstblock == NULLFSBLOCK || - XFS_FSB_TO_AGNO(mp, *ap->firstblock) <= - XFS_FSB_TO_AGNO(mp, args.fsbno)); - - ap->blkno = args.fsbno; - if (*ap->firstblock == NULLFSBLOCK) - *ap->firstblock = args.fsbno; - ASSERT(nullfb || fb_agno <= args.agno); - ap->length = args.len; - if (!(ap->flags & XFS_BMAPI_COWFORK)) - ap->ip->i_d.di_nblocks += args.len; - xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE); - if (ap->wasdel) - ap->ip->i_delayed_blks -= args.len; - /* - * Adjust the disk quota also. This was reserved - * earlier. - */ - xfs_trans_mod_dquot_byino(ap->tp, ap->ip, - ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : - XFS_TRANS_DQ_BCOUNT, - (long) args.len); + xfs_bmap_process_allocated_extent(ap, &args, orig_offset, + orig_length); } else { ap->blkno = NULLFSBLOCK; ap->length = 0; @@ -3813,20 +3674,6 @@ xfs_bmap_btalloc( return 0; } -/* - * xfs_bmap_alloc is called by xfs_bmapi to allocate an extent for a file. - * It figures out where to ask the underlying allocator to put the new extent. - */ -STATIC int -xfs_bmap_alloc( - struct xfs_bmalloca *ap) /* bmap alloc argument struct */ -{ - if (XFS_IS_REALTIME_INODE(ap->ip) && - xfs_alloc_is_userdata(ap->datatype)) - return xfs_bmap_rtalloc(ap); - return xfs_bmap_btalloc(ap); -} - /* Trim extent to fit a logical block range. */ void xfs_trim_extent( @@ -3872,7 +3719,7 @@ xfs_bmapi_trim_map( xfs_fileoff_t obno, xfs_fileoff_t end, int n, - int flags) + uint32_t flags) { if ((flags & XFS_BMAPI_ENTIRE) || got->br_startoff + got->br_blockcount <= obno) { @@ -3917,7 +3764,7 @@ xfs_bmapi_update_map( xfs_fileoff_t obno, xfs_fileoff_t end, int *n, - int flags) + uint32_t flags) { xfs_bmbt_irec_t *mval = *map; @@ -3940,8 +3787,7 @@ xfs_bmapi_update_map( mval[-1].br_startblock != HOLESTARTBLOCK && mval->br_startblock == mval[-1].br_startblock + mval[-1].br_blockcount && - ((flags & XFS_BMAPI_IGSTATE) || - mval[-1].br_state == mval->br_state)) { + mval[-1].br_state == mval->br_state) { ASSERT(mval->br_startoff == mval[-1].br_startoff + mval[-1].br_blockcount); mval[-1].br_blockcount += mval->br_blockcount; @@ -3971,56 +3817,44 @@ xfs_bmapi_read( xfs_filblks_t len, struct xfs_bmbt_irec *mval, int *nmap, - int flags) + uint32_t flags) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp; + int whichfork = xfs_bmapi_whichfork(flags); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec got; xfs_fileoff_t obno; xfs_fileoff_t end; - xfs_extnum_t idx; + struct xfs_iext_cursor icur; int error; bool eof = false; int n = 0; - int whichfork = xfs_bmapi_whichfork(flags); ASSERT(*nmap >= 1); - ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK|XFS_BMAPI_ENTIRE| - XFS_BMAPI_IGSTATE|XFS_BMAPI_COWFORK))); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)); - - 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_ERROR_REPORT("xfs_bmapi_read", XFS_ERRLEVEL_LOW, mp); + ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_ENTIRE))); + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + if (WARN_ON_ONCE(!ifp)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } - if (XFS_FORCED_SHUTDOWN(mp)) + if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); + return -EFSCORRUPTED; + } + + if (xfs_is_shutdown(mp)) return -EIO; XFS_STATS_INC(mp, xs_blk_mapr); - ifp = XFS_IFORK_PTR(ip, whichfork); - - /* No CoW fork? Return a hole. */ - if (whichfork == XFS_COW_FORK && !ifp) { - mval->br_startoff = bno; - mval->br_startblock = HOLESTARTBLOCK; - mval->br_blockcount = len; - mval->br_state = XFS_EXT_NORM; - *nmap = 1; - return 0; - } - - if (!(ifp->if_flags & XFS_IFEXTENTS)) { - error = xfs_iread_extents(NULL, ip, whichfork); - if (error) - return error; - } + error = xfs_iread_extents(NULL, ip, whichfork); + if (error) + return error; - if (!xfs_iext_lookup_extent(ip, ifp, bno, &idx, &got)) + if (!xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got)) eof = true; end = bno + len; obno = bno; @@ -4052,250 +3886,97 @@ xfs_bmapi_read( break; /* Else go on to the next record. */ - if (!xfs_iext_get_extent(ifp, ++idx, &got)) + if (!xfs_iext_next_extent(ifp, &icur, &got)) eof = true; } *nmap = n; return 0; } -/* - * Add a delayed allocation extent to an inode. Blocks are reserved from the - * global pool and the extent inserted into the inode in-core extent tree. - * - * On entry, got refers to the first extent beyond the offset of the extent to - * allocate or eof is specified if no such extent exists. On return, got refers - * to the extent record that was inserted to the inode fork. - * - * Note that the allocated extent may have been merged with contiguous extents - * during insertion into the inode fork. Thus, got does not reflect the current - * state of the inode fork on return. If necessary, the caller can use lastx to - * look up the updated record in the inode fork. - */ -int -xfs_bmapi_reserve_delalloc( - struct xfs_inode *ip, - int whichfork, - xfs_fileoff_t off, - xfs_filblks_t len, - xfs_filblks_t prealloc, - struct xfs_bmbt_irec *got, - xfs_extnum_t *lastx, - int eof) -{ - struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); - xfs_extlen_t alen; - xfs_extlen_t indlen; - char rt = XFS_IS_REALTIME_INODE(ip); - xfs_extlen_t extsz; - int error; - xfs_fileoff_t aoff = off; - - /* - * Cap the alloc length. Keep track of prealloc so we know whether to - * tag the inode before we return. - */ - alen = XFS_FILBLKS_MIN(len + prealloc, MAXEXTLEN); - if (!eof) - alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff); - if (prealloc && alen >= len) - prealloc = alen - len; - - /* Figure out the extent size, adjust alen */ - if (whichfork == XFS_COW_FORK) - extsz = xfs_get_cowextsz_hint(ip); - else - extsz = xfs_get_extsz_hint(ip); - if (extsz) { - struct xfs_bmbt_irec prev; - - if (!xfs_iext_get_extent(ifp, *lastx - 1, &prev)) - prev.br_startoff = NULLFILEOFF; - - error = xfs_bmap_extsize_align(mp, got, &prev, extsz, rt, eof, - 1, 0, &aoff, &alen); - ASSERT(!error); - } - - if (rt) - extsz = alen / mp->m_sb.sb_rextsize; - - /* - * Make a transaction-less quota reservation for delayed allocation - * blocks. This number gets adjusted later. We return if we haven't - * allocated blocks already inside this loop. - */ - error = xfs_trans_reserve_quota_nblks(NULL, ip, (long)alen, 0, - rt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS); - if (error) - return error; - - /* - * Split changing sb for alen and indlen since they could be coming - * from different places. - */ - indlen = (xfs_extlen_t)xfs_bmap_worst_indlen(ip, alen); - ASSERT(indlen > 0); - - if (rt) { - error = xfs_mod_frextents(mp, -((int64_t)extsz)); - } else { - error = xfs_mod_fdblocks(mp, -((int64_t)alen), false); - } - - if (error) - goto out_unreserve_quota; - - error = xfs_mod_fdblocks(mp, -((int64_t)indlen), false); - if (error) - goto out_unreserve_blocks; - - - ip->i_delayed_blks += alen; - - got->br_startoff = aoff; - got->br_startblock = nullstartblock(indlen); - got->br_blockcount = alen; - got->br_state = XFS_EXT_NORM; - - xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got); - - /* - * Tag the inode if blocks were preallocated. Note that COW fork - * preallocation can occur at the start or end of the extent, even when - * prealloc == 0, so we must also check the aligned offset and length. - */ - if (whichfork == XFS_DATA_FORK && prealloc) - xfs_inode_set_eofblocks_tag(ip); - if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len)) - xfs_inode_set_cowblocks_tag(ip); - - return 0; - -out_unreserve_blocks: - if (rt) - xfs_mod_frextents(mp, extsz); - else - xfs_mod_fdblocks(mp, alen, false); -out_unreserve_quota: - if (XFS_IS_QUOTA_ON(mp)) - xfs_trans_unreserve_quota_nblks(NULL, ip, (long)alen, 0, rt ? - XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS); - return error; -} - static int xfs_bmapi_allocate( struct xfs_bmalloca *bma) { struct xfs_mount *mp = bma->ip->i_mount; int whichfork = xfs_bmapi_whichfork(bma->flags); - struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork); - int tmp_logflags = 0; + struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork); int error; ASSERT(bma->length > 0); + ASSERT(bma->length <= XFS_MAX_BMBT_EXTLEN); - /* - * For the wasdelay case, we could also just allocate the stuff asked - * for in this bmap call but that wouldn't be as good. - */ - if (bma->wasdel) { - bma->length = (xfs_extlen_t)bma->got.br_blockcount; - bma->offset = bma->got.br_startoff; - if (bma->idx) { - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx - 1), - &bma->prev); - } - } else { - bma->length = XFS_FILBLKS_MIN(bma->length, MAXEXTLEN); - if (!bma->eof) - bma->length = XFS_FILBLKS_MIN(bma->length, - bma->got.br_startoff - bma->offset); - } + if (bma->flags & XFS_BMAPI_CONTIG) + bma->minlen = bma->length; + else + bma->minlen = 1; - /* - * Set the data type being allocated. For the data fork, the first data - * in the file is treated differently to all other allocations. For the - * attribute fork, we only need to ensure the allocated range is not on - * the busy list. - */ if (!(bma->flags & XFS_BMAPI_METADATA)) { + /* + * For the data and COW fork, the first data in the file is + * treated differently to all other allocations. For the + * attribute fork, we only need to ensure the allocated range + * is not on the busy list. + */ bma->datatype = XFS_ALLOC_NOBUSY; - if (whichfork == XFS_DATA_FORK) { + if (whichfork == XFS_DATA_FORK || whichfork == XFS_COW_FORK) { + bma->datatype |= XFS_ALLOC_USERDATA; if (bma->offset == 0) bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA; - else - bma->datatype |= XFS_ALLOC_USERDATA; + + if (mp->m_dalign && bma->length >= mp->m_dalign) { + error = xfs_bmap_isaeof(bma, whichfork); + if (error) + return error; + } } - if (bma->flags & XFS_BMAPI_ZERO) - bma->datatype |= XFS_ALLOC_USERDATA_ZERO; } - bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1; + if ((bma->datatype & XFS_ALLOC_USERDATA) && + XFS_IS_REALTIME_INODE(bma->ip)) + error = xfs_bmap_rtalloc(bma); + else + error = xfs_bmap_btalloc(bma); + if (error) + return error; + if (bma->blkno == NULLFSBLOCK) + return -ENOSPC; - /* - * Only want to do the alignment at the eof if it is userdata and - * allocation length is larger than a stripe unit. - */ - if (mp->m_dalign && bma->length >= mp->m_dalign && - !(bma->flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) { - error = xfs_bmap_isaeof(bma, whichfork); + if (WARN_ON_ONCE(!xfs_valid_startblock(bma->ip, bma->blkno))) { + xfs_bmap_mark_sick(bma->ip, whichfork); + return -EFSCORRUPTED; + } + + if (bma->flags & XFS_BMAPI_ZERO) { + error = xfs_zero_extent(bma->ip, bma->blkno, bma->length); if (error) return error; } - error = xfs_bmap_alloc(bma); - if (error) - return error; - - if (bma->cur) - bma->cur->bc_private.b.firstblock = *bma->firstblock; - if (bma->blkno == NULLFSBLOCK) - return 0; - if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) { + if (ifp->if_format == XFS_DINODE_FMT_BTREE && !bma->cur) bma->cur = xfs_bmbt_init_cursor(mp, bma->tp, bma->ip, whichfork); - bma->cur->bc_private.b.firstblock = *bma->firstblock; - bma->cur->bc_private.b.dfops = bma->dfops; - } /* * Bump the number of extents we've allocated * in this call. */ bma->nallocs++; - if (bma->cur) - bma->cur->bc_private.b.flags = - bma->wasdel ? XFS_BTCUR_BPRV_WASDEL : 0; + if (bma->cur && bma->wasdel) + bma->cur->bc_flags |= XFS_BTREE_BMBT_WASDEL; bma->got.br_startoff = bma->offset; bma->got.br_startblock = bma->blkno; bma->got.br_blockcount = bma->length; bma->got.br_state = XFS_EXT_NORM; - /* - * In the data fork, a wasdelay extent has been initialized, so - * shouldn't be flagged as unwritten. - * - * For the cow fork, however, we convert delalloc reservations - * (extents allocated for speculative preallocation) to - * allocated unwritten extents, and only convert the unwritten - * extents to real extents when we're about to write the data. - */ - if ((!bma->wasdel || (bma->flags & XFS_BMAPI_COWFORK)) && - (bma->flags & XFS_BMAPI_PREALLOC) && - xfs_sb_version_hasextflgbit(&mp->m_sb)) + if (bma->flags & XFS_BMAPI_PREALLOC) bma->got.br_state = XFS_EXT_UNWRITTEN; if (bma->wasdel) error = xfs_bmap_add_extent_delay_real(bma, whichfork); else error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip, - whichfork, &bma->idx, &bma->cur, &bma->got, - bma->firstblock, bma->dfops, &bma->logflags); - - bma->logflags |= tmp_logflags; + whichfork, &bma->icur, &bma->cur, &bma->got, + &bma->logflags, bma->flags); if (error) return error; @@ -4304,7 +3985,7 @@ xfs_bmapi_allocate( * or xfs_bmap_add_extent_hole_real might have merged it into one of * the neighbouring ones. */ - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx), &bma->got); + xfs_iext_get_extent(ifp, &bma->icur, &bma->got); ASSERT(bma->got.br_startoff <= bma->offset); ASSERT(bma->got.br_startoff + bma->got.br_blockcount >= @@ -4319,10 +4000,10 @@ xfs_bmapi_convert_unwritten( struct xfs_bmalloca *bma, struct xfs_bmbt_irec *mval, xfs_filblks_t len, - int flags) + uint32_t flags) { int whichfork = xfs_bmapi_whichfork(flags); - struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork); int tmp_logflags = 0; int error; @@ -4341,11 +4022,9 @@ xfs_bmapi_convert_unwritten( * Modify (by adding) the state flag, if writing. */ ASSERT(mval->br_blockcount <= len); - if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) { + if (ifp->if_format == XFS_DINODE_FMT_BTREE && !bma->cur) { bma->cur = xfs_bmbt_init_cursor(bma->ip->i_mount, bma->tp, bma->ip, whichfork); - bma->cur->bc_private.b.firstblock = *bma->firstblock; - bma->cur->bc_private.b.dfops = bma->dfops; } mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN) ? XFS_EXT_NORM : XFS_EXT_UNWRITTEN; @@ -4362,8 +4041,7 @@ xfs_bmapi_convert_unwritten( } error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, whichfork, - &bma->idx, &bma->cur, mval, bma->firstblock, bma->dfops, - &tmp_logflags); + &bma->icur, &bma->cur, mval, &tmp_logflags); /* * Log the inode core unconditionally in the unwritten extent conversion * path because the conversion might not have done so (e.g., if the @@ -4385,7 +4063,7 @@ xfs_bmapi_convert_unwritten( * xfs_bmap_add_extent_unwritten_real might have merged it into one * of the neighbouring ones. */ - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx), &bma->got); + xfs_iext_get_extent(ifp, &bma->icur, &bma->got); /* * We may have combined previously unwritten space with written space, @@ -4396,17 +4074,62 @@ xfs_bmapi_convert_unwritten( return 0; } +xfs_extlen_t +xfs_bmapi_minleft( + struct xfs_trans *tp, + struct xfs_inode *ip, + int fork) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, fork); + + if (tp && tp->t_highest_agno != NULLAGNUMBER) + return 0; + if (ifp->if_format != XFS_DINODE_FMT_BTREE) + return 1; + return be16_to_cpu(ifp->if_broot->bb_level) + 1; +} + +/* + * Log whatever the flags say, even if error. Otherwise we might miss detecting + * a case where the data is changed, there's an error, and it's not logged so we + * don't shutdown when we should. Don't bother logging extents/btree changes if + * we converted to the other format. + */ +static void +xfs_bmapi_finish( + struct xfs_bmalloca *bma, + int whichfork, + int error) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork); + + if ((bma->logflags & xfs_ilog_fext(whichfork)) && + ifp->if_format != XFS_DINODE_FMT_EXTENTS) + bma->logflags &= ~xfs_ilog_fext(whichfork); + else if ((bma->logflags & xfs_ilog_fbroot(whichfork)) && + ifp->if_format != XFS_DINODE_FMT_BTREE) + bma->logflags &= ~xfs_ilog_fbroot(whichfork); + + if (bma->logflags) + xfs_trans_log_inode(bma->tp, bma->ip, bma->logflags); + if (bma->cur) + xfs_btree_del_cursor(bma->cur, error); +} + /* * Map file blocks to filesystem blocks, and allocate blocks or convert the * extent state if necessary. Details behaviour is controlled by the flags * parameter. Only allocates blocks from a single allocation group, to avoid * locking problems. * - * The returned value in "firstblock" from the first call in a transaction - * must be remembered and presented to subsequent calls in "firstblock". - * An upper bound for the number of blocks to be allocated is supplied to - * the first call in "total"; if no allocation group has that many free - * blocks then the call will fail (return NULLFSBLOCK in "firstblock"). + * Returns 0 on success and places the extent mappings in mval. nmaps is used + * as an input/output parameter where the caller specifies the maximum number + * of mappings that may be returned and xfs_bmapi_write passes back the number + * of mappings (including existing mappings) it found. + * + * Returns a negative error code on failure, including -ENOSPC when it could not + * allocate any blocks and -ENOSR when it did allocate blocks to convert a + * delalloc range, but those blocks were before the passed in range. */ int xfs_bmapi_write( @@ -4414,23 +4137,24 @@ xfs_bmapi_write( struct xfs_inode *ip, /* incore inode */ xfs_fileoff_t bno, /* starting file offs. mapped */ xfs_filblks_t len, /* length to map in file */ - int flags, /* XFS_BMAPI_... */ - xfs_fsblock_t *firstblock, /* first allocated block - controls a.g. for allocs */ + uint32_t flags, /* XFS_BMAPI_... */ xfs_extlen_t total, /* total blocks needed */ struct xfs_bmbt_irec *mval, /* output: map values */ - int *nmap, /* i/o: mval size/count */ - struct xfs_defer_ops *dfops) /* i/o: list extents to free */ + int *nmap) /* i/o: mval size/count */ { + struct xfs_bmalloca bma = { + .tp = tp, + .ip = ip, + .total = total, + }; struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp; - struct xfs_bmalloca bma = { NULL }; /* args for xfs_bmap_alloc */ + int whichfork = xfs_bmapi_whichfork(flags); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); xfs_fileoff_t end; /* end of mapped file region */ bool eof = false; /* after the end of extents */ int error; /* error return */ int n; /* current extent index */ xfs_fileoff_t obno; /* old block number (offset) */ - int whichfork; /* data or attr fork */ #ifdef DEBUG xfs_fileoff_t orig_bno; /* original block number value */ @@ -4445,17 +4169,13 @@ xfs_bmapi_write( orig_mval = mval; orig_nmap = *nmap; #endif - whichfork = xfs_bmapi_whichfork(flags); ASSERT(*nmap >= 1); ASSERT(*nmap <= XFS_BMAP_MAX_NMAP); - ASSERT(!(flags & XFS_BMAPI_IGSTATE)); - ASSERT(tp != NULL || - (flags & (XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK)) == - (XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK)); + ASSERT(tp != NULL); ASSERT(len > 0); - ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + ASSERT(ifp->if_format != XFS_DINODE_FMT_LOCAL); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); ASSERT(!(flags & XFS_BMAPI_REMAP)); /* zeroing is for currently only for data extents, not metadata */ @@ -4470,76 +4190,44 @@ xfs_bmapi_write( ASSERT((flags & (XFS_BMAPI_PREALLOC | XFS_BMAPI_ZERO)) != (XFS_BMAPI_PREALLOC | XFS_BMAPI_ZERO)); - 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_ERROR_REPORT("xfs_bmapi_write", XFS_ERRLEVEL_LOW, mp); + if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) return -EIO; - ifp = XFS_IFORK_PTR(ip, whichfork); - XFS_STATS_INC(mp, xs_blk_mapw); - if (*firstblock == NULLFSBLOCK) { - if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE) - bma.minleft = be16_to_cpu(ifp->if_broot->bb_level) + 1; - else - bma.minleft = 1; - } else { - bma.minleft = 0; - } + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + goto error0; - if (!(ifp->if_flags & XFS_IFEXTENTS)) { - error = xfs_iread_extents(tp, ip, whichfork); - if (error) - goto error0; - } + if (!xfs_iext_lookup_extent(ip, ifp, bno, &bma.icur, &bma.got)) + eof = true; + if (!xfs_iext_peek_prev_extent(ifp, &bma.icur, &bma.prev)) + bma.prev.br_startoff = NULLFILEOFF; + bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork); n = 0; end = bno + len; obno = bno; - - if (!xfs_iext_lookup_extent(ip, ifp, bno, &bma.idx, &bma.got)) - eof = true; - if (!xfs_iext_get_extent(ifp, bma.idx - 1, &bma.prev)) - bma.prev.br_startoff = NULLFILEOFF; - bma.tp = tp; - bma.ip = ip; - bma.total = total; - bma.datatype = 0; - bma.dfops = dfops; - bma.firstblock = firstblock; - while (bno < end && n < *nmap) { bool need_alloc = false, wasdelay = false; - /* in hole or beyoned EOF? */ + /* in hole or beyond EOF? */ if (eof || bma.got.br_startoff > bno) { - if (flags & XFS_BMAPI_DELALLOC) { - /* - * For the COW fork we can reasonably get a - * request for converting an extent that races - * with other threads already having converted - * part of it, as there converting COW to - * regular blocks is not protected using the - * IOLOCK. - */ - ASSERT(flags & XFS_BMAPI_COWFORK); - if (!(flags & XFS_BMAPI_COWFORK)) { - error = -EIO; - goto error0; - } + /* + * CoW fork conversions should /never/ hit EOF or + * holes. There should always be something for us + * to work on. + */ + ASSERT(!((flags & XFS_BMAPI_CONVERT) && + (flags & XFS_BMAPI_COWFORK))); - if (eof || bno >= end) - break; - } else { - need_alloc = true; - } + need_alloc = true; } else if (isnullstartblock(bma.got.br_startblock)) { wasdelay = true; } @@ -4560,31 +4248,42 @@ xfs_bmapi_write( * allocation length request (which can be 64 bits in * length) and the bma length request, which is * xfs_extlen_t and therefore 32 bits. Hence we have to - * check for 32-bit overflows and handle them here. + * be careful and do the min() using the larger type to + * avoid overflows. */ - if (len > (xfs_filblks_t)MAXEXTLEN) - bma.length = MAXEXTLEN; - else - bma.length = len; + bma.length = XFS_FILBLKS_MIN(len, XFS_MAX_BMBT_EXTLEN); + + if (wasdelay) { + bma.length = XFS_FILBLKS_MIN(bma.length, + bma.got.br_blockcount - + (bno - bma.got.br_startoff)); + } else { + if (!eof) + bma.length = XFS_FILBLKS_MIN(bma.length, + bma.got.br_startoff - bno); + } - ASSERT(len > 0); ASSERT(bma.length > 0); error = xfs_bmapi_allocate(&bma); - if (error) + if (error) { + /* + * If we already allocated space in a previous + * iteration return what we go so far when + * running out of space. + */ + if (error == -ENOSPC && bma.nallocs) + break; goto error0; - if (bma.blkno == NULLFSBLOCK) - break; + } /* * If this is a CoW allocation, record the data in * the refcount btree for orphan recovery. */ - if (whichfork == XFS_COW_FORK) { - error = xfs_refcount_alloc_cow_extent(mp, dfops, + if (whichfork == XFS_COW_FORK) + xfs_refcount_alloc_cow_extent(tp, + XFS_IS_REALTIME_INODE(ip), bma.blkno, bma.length); - if (error) - goto error0; - } } /* Deal with the allocated space we found. */ @@ -4611,149 +4310,282 @@ xfs_bmapi_write( /* Else go on to the next record. */ bma.prev = bma.got; - if (!xfs_iext_get_extent(ifp, ++bma.idx, &bma.got)) + if (!xfs_iext_next_extent(ifp, &bma.icur, &bma.got)) eof = true; } + + error = xfs_bmap_btree_to_extents(tp, ip, bma.cur, &bma.logflags, + whichfork); + if (error) + goto error0; + + ASSERT(ifp->if_format != XFS_DINODE_FMT_BTREE || + ifp->if_nextents > XFS_IFORK_MAXEXT(ip, whichfork)); + xfs_bmapi_finish(&bma, whichfork, 0); + xfs_bmap_validate_ret(orig_bno, orig_len, orig_flags, orig_mval, + orig_nmap, n); + + /* + * When converting delayed allocations, xfs_bmapi_allocate ignores + * the passed in bno and always converts from the start of the found + * delalloc extent. + * + * To avoid a successful return with *nmap set to 0, return the magic + * -ENOSR error code for this particular case so that the caller can + * handle it. + */ + if (!n) { + ASSERT(bma.nallocs >= *nmap); + return -ENOSR; + } *nmap = n; + return 0; +error0: + xfs_bmapi_finish(&bma, whichfork, error); + return error; +} + +/* + * Convert an existing delalloc extent to real blocks based on file offset. This + * attempts to allocate the entire delalloc extent and may require multiple + * invocations to allocate the target offset if a large enough physical extent + * is not available. + */ +static int +xfs_bmapi_convert_one_delalloc( + struct xfs_inode *ip, + int whichfork, + xfs_off_t offset, + struct iomap *iomap, + unsigned int *seq) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_mount *mp = ip->i_mount; + xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + struct xfs_bmalloca bma = { NULL }; + uint16_t flags = 0; + struct xfs_trans *tp; + int error; + + if (whichfork == XFS_COW_FORK) + flags |= IOMAP_F_SHARED; /* - * Transform from btree to extents, give it cur. + * Space for the extent and indirect blocks was reserved when the + * delalloc extent was created so there's no need to do so here. */ - if (xfs_bmap_wants_extents(ip, whichfork)) { - int tmp_logflags = 0; + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, + XFS_TRANS_RESERVE, &tp); + if (error) + return error; - ASSERT(bma.cur); - error = xfs_bmap_btree_to_extents(tp, ip, bma.cur, - &tmp_logflags, whichfork); - bma.logflags |= tmp_logflags; - if (error) - goto error0; + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, 0); + + error = xfs_iext_count_extend(tp, ip, whichfork, + XFS_IEXT_ADD_NOSPLIT_CNT); + if (error) + goto out_trans_cancel; + + if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &bma.icur, &bma.got) || + bma.got.br_startoff > offset_fsb) { + /* + * No extent found in the range we are trying to convert. This + * should only happen for the COW fork, where another thread + * might have moved the extent to the data fork in the meantime. + */ + WARN_ON_ONCE(whichfork != XFS_COW_FORK); + error = -EAGAIN; + goto out_trans_cancel; } - ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE || - XFS_IFORK_NEXTENTS(ip, whichfork) > - XFS_IFORK_MAXEXT(ip, whichfork)); - error = 0; -error0: /* - * Log everything. Do this after conversion, there's no point in - * logging the extent records if we've converted to btree format. + * If we find a real extent here we raced with another thread converting + * the extent. Just return the real extent at this offset. + */ + if (!isnullstartblock(bma.got.br_startblock)) { + xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags, + xfs_iomap_inode_sequence(ip, flags)); + if (seq) + *seq = READ_ONCE(ifp->if_seq); + goto out_trans_cancel; + } + + bma.tp = tp; + bma.ip = ip; + bma.wasdel = true; + bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork); + + /* + * Always allocate convert from the start of the delalloc extent even if + * that is outside the passed in range to create large contiguous + * extents on disk. */ - if ((bma.logflags & xfs_ilog_fext(whichfork)) && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS) - bma.logflags &= ~xfs_ilog_fext(whichfork); - else if ((bma.logflags & xfs_ilog_fbroot(whichfork)) && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE) - bma.logflags &= ~xfs_ilog_fbroot(whichfork); + bma.offset = bma.got.br_startoff; + bma.length = bma.got.br_blockcount; + /* - * Log whatever the flags say, even if error. Otherwise we might miss - * detecting a case where the data is changed, there's an error, - * and it's not logged so we don't shutdown when we should. + * When we're converting the delalloc reservations backing dirty pages + * in the page cache, we must be careful about how we create the new + * extents: + * + * New CoW fork extents are created unwritten, turned into real extents + * when we're about to write the data to disk, and mapped into the data + * fork after the write finishes. End of story. + * + * New data fork extents must be mapped in as unwritten and converted + * to real extents after the write succeeds to avoid exposing stale + * disk contents if we crash. */ - if (bma.logflags) - xfs_trans_log_inode(tp, ip, bma.logflags); - - if (bma.cur) { - if (!error) { - ASSERT(*firstblock == NULLFSBLOCK || - XFS_FSB_TO_AGNO(mp, *firstblock) <= - XFS_FSB_TO_AGNO(mp, - bma.cur->bc_private.b.firstblock)); - *firstblock = bma.cur->bc_private.b.firstblock; - } - xfs_btree_del_cursor(bma.cur, - error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); - } - if (!error) - xfs_bmap_validate_ret(orig_bno, orig_len, orig_flags, orig_mval, - orig_nmap, *nmap); + bma.flags = XFS_BMAPI_PREALLOC; + if (whichfork == XFS_COW_FORK) + bma.flags |= XFS_BMAPI_COWFORK; + + if (!xfs_iext_peek_prev_extent(ifp, &bma.icur, &bma.prev)) + bma.prev.br_startoff = NULLFILEOFF; + + error = xfs_bmapi_allocate(&bma); + if (error) + goto out_finish; + + XFS_STATS_ADD(mp, xs_xstrat_bytes, XFS_FSB_TO_B(mp, bma.length)); + XFS_STATS_INC(mp, xs_xstrat_quick); + + ASSERT(!isnullstartblock(bma.got.br_startblock)); + xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags, + xfs_iomap_inode_sequence(ip, flags)); + if (seq) + *seq = READ_ONCE(ifp->if_seq); + + if (whichfork == XFS_COW_FORK) + xfs_refcount_alloc_cow_extent(tp, XFS_IS_REALTIME_INODE(ip), + bma.blkno, bma.length); + + error = xfs_bmap_btree_to_extents(tp, ip, bma.cur, &bma.logflags, + whichfork); + if (error) + goto out_finish; + + xfs_bmapi_finish(&bma, whichfork, 0); + error = xfs_trans_commit(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return error; + +out_finish: + xfs_bmapi_finish(&bma, whichfork, error); +out_trans_cancel: + xfs_trans_cancel(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } -static int +/* + * Pass in a dellalloc extent and convert it to real extents, return the real + * extent that maps offset_fsb in iomap. + */ +int +xfs_bmapi_convert_delalloc( + struct xfs_inode *ip, + int whichfork, + loff_t offset, + struct iomap *iomap, + unsigned int *seq) +{ + int error; + + /* + * Attempt to allocate whatever delalloc extent currently backs offset + * and put the result into iomap. Allocate in a loop because it may + * take several attempts to allocate real blocks for a contiguous + * delalloc extent if free space is sufficiently fragmented. + */ + do { + error = xfs_bmapi_convert_one_delalloc(ip, whichfork, offset, + iomap, seq); + if (error) + return error; + } while (iomap->offset + iomap->length <= offset); + + return 0; +} + +int xfs_bmapi_remap( struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock, - struct xfs_defer_ops *dfops) + uint32_t flags) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + struct xfs_ifork *ifp; struct xfs_btree_cur *cur = NULL; - xfs_fsblock_t firstblock = NULLFSBLOCK; struct xfs_bmbt_irec got; - xfs_extnum_t idx; + struct xfs_iext_cursor icur; + int whichfork = xfs_bmapi_whichfork(flags); int logflags = 0, error; + ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(len > 0); - ASSERT(len <= (xfs_filblks_t)MAXEXTLEN); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - - if (unlikely(XFS_TEST_ERROR( - (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE), - mp, XFS_ERRTAG_BMAPIFORMAT))) { - XFS_ERROR_REPORT("xfs_bmapi_remap", XFS_ERRLEVEL_LOW, mp); + ASSERT(len <= (xfs_filblks_t)XFS_MAX_BMBT_EXTLEN); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); + ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC | + XFS_BMAPI_NORMAP))); + ASSERT((flags & (XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC)) != + (XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC)); + + if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) return -EIO; - if (!(ifp->if_flags & XFS_IFEXTENTS)) { - error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK); - if (error) - return error; - } + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; - if (xfs_iext_lookup_extent(ip, ifp, bno, &idx, &got)) { + if (xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got)) { /* make sure we only reflink into a hole. */ ASSERT(got.br_startoff > bno); ASSERT(got.br_startoff - bno >= len); } - ip->i_d.di_nblocks += len; + ip->i_nblocks += len; + ip->i_delayed_blks -= len; /* see xfs_bmap_defer_add */ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - if (ifp->if_flags & XFS_IFBROOT) { - cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK); - cur->bc_private.b.firstblock = firstblock; - cur->bc_private.b.dfops = dfops; - cur->bc_private.b.flags = 0; - } + if (ifp->if_format == XFS_DINODE_FMT_BTREE) + cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); got.br_startoff = bno; got.br_startblock = startblock; got.br_blockcount = len; - got.br_state = XFS_EXT_NORM; + if (flags & XFS_BMAPI_PREALLOC) + got.br_state = XFS_EXT_UNWRITTEN; + else + got.br_state = XFS_EXT_NORM; - error = xfs_bmap_add_extent_hole_real(tp, ip, XFS_DATA_FORK, &idx, &cur, - &got, &firstblock, dfops, &logflags); + error = xfs_bmap_add_extent_hole_real(tp, ip, whichfork, &icur, + &cur, &got, &logflags, flags); if (error) goto error0; - if (xfs_bmap_wants_extents(ip, XFS_DATA_FORK)) { - int tmp_logflags = 0; - - error = xfs_bmap_btree_to_extents(tp, ip, cur, - &tmp_logflags, XFS_DATA_FORK); - logflags |= tmp_logflags; - } + error = xfs_bmap_btree_to_extents(tp, ip, cur, &logflags, whichfork); error0: - if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) + if (ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS) logflags &= ~XFS_ILOG_DEXT; - else if (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) + else if (ip->i_df.if_format != XFS_DINODE_FMT_BTREE) logflags &= ~XFS_ILOG_DBROOT; if (logflags) xfs_trans_log_inode(tp, ip, logflags); - if (cur) { - xfs_btree_del_cursor(cur, - error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); - } + if (cur) + xfs_btree_del_cursor(cur, error); return error; } @@ -4769,32 +4601,18 @@ error0: * ores == 1). The number of stolen blocks is returned. The availability and * subsequent accounting of stolen blocks is the responsibility of the caller. */ -static xfs_filblks_t +static void xfs_bmap_split_indlen( xfs_filblks_t ores, /* original res. */ xfs_filblks_t *indlen1, /* ext1 worst indlen */ - xfs_filblks_t *indlen2, /* ext2 worst indlen */ - xfs_filblks_t avail) /* stealable blocks */ + xfs_filblks_t *indlen2) /* ext2 worst indlen */ { xfs_filblks_t len1 = *indlen1; xfs_filblks_t len2 = *indlen2; xfs_filblks_t nres = len1 + len2; /* new total res. */ - xfs_filblks_t stolen = 0; xfs_filblks_t resfactor; /* - * Steal as many blocks as we can to try and satisfy the worst case - * indlen for both new extents. - */ - if (ores < nres && avail) - stolen = XFS_FILBLKS_MIN(nres - ores, avail); - ores += stolen; - - /* nothing else to do if we've satisfied the new reservation */ - if (ores >= nres) - return stolen; - - /* * We can't meet the total required reservation for the two extents. * Calculate the percent of the overall shortage between both extents * and apply this percentage to each of the requested indlen values. @@ -4838,100 +4656,80 @@ xfs_bmap_split_indlen( *indlen1 = len1; *indlen2 = len2; - - return stolen; } -int +void xfs_bmap_del_extent_delay( struct xfs_inode *ip, int whichfork, - xfs_extnum_t *idx, + struct xfs_iext_cursor *icur, struct xfs_bmbt_irec *got, - struct xfs_bmbt_irec *del) + struct xfs_bmbt_irec *del, + uint32_t bflags) /* bmapi flags */ { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec new; int64_t da_old, da_new, da_diff = 0; xfs_fileoff_t del_endoff, got_endoff; - xfs_filblks_t got_indlen, new_indlen, stolen; - int error = 0, state = 0; + xfs_filblks_t got_indlen, new_indlen, stolen = 0; + uint32_t state = xfs_bmap_fork_to_state(whichfork); + uint64_t fdblocks; bool isrt; XFS_STATS_INC(mp, xs_del_exlist); - isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip); + isrt = xfs_ifork_is_realtime(ip, whichfork); del_endoff = del->br_startoff + del->br_blockcount; got_endoff = got->br_startoff + got->br_blockcount; da_old = startblockval(got->br_startblock); da_new = 0; - ASSERT(*idx >= 0); - ASSERT(*idx <= xfs_iext_count(ifp)); ASSERT(del->br_blockcount > 0); ASSERT(got->br_startoff <= del->br_startoff); ASSERT(got_endoff >= del_endoff); - if (isrt) { - uint64_t rtexts = XFS_FSB_TO_B(mp, del->br_blockcount); - - do_div(rtexts, mp->m_sb.sb_rextsize); - xfs_mod_frextents(mp, rtexts); - } - /* * Update the inode delalloc counter now and wait to update the * sb counters as we might have to borrow some blocks for the * indirect block accounting. */ - error = xfs_trans_reserve_quota_nblks(NULL, ip, - -((long)del->br_blockcount), 0, - isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS); - if (error) - return error; + xfs_quota_unreserve_blkres(ip, del->br_blockcount); ip->i_delayed_blks -= del->br_blockcount; - if (whichfork == XFS_COW_FORK) - state |= BMAP_COWFORK; - if (got->br_startoff == del->br_startoff) - state |= BMAP_LEFT_CONTIG; + state |= BMAP_LEFT_FILLING; if (got_endoff == del_endoff) - state |= BMAP_RIGHT_CONTIG; + state |= BMAP_RIGHT_FILLING; - switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { - case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: + switch (state & (BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING)) { + case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING: /* * Matches the whole extent. Delete the entry. */ - xfs_iext_remove(ip, *idx, 1, state); - --*idx; + xfs_iext_remove(ip, icur, state); + xfs_iext_prev(ifp, icur); break; - case BMAP_LEFT_CONTIG: + case BMAP_LEFT_FILLING: /* * Deleting the first part of the extent. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); got->br_startoff = del_endoff; got->br_blockcount -= del->br_blockcount; da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, got->br_blockcount), da_old); got->br_startblock = nullstartblock((int)da_new); - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + xfs_iext_update_extent(ip, state, icur, got); break; - case BMAP_RIGHT_CONTIG: + case BMAP_RIGHT_FILLING: /* * Deleting the last part of the extent. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); got->br_blockcount = got->br_blockcount - del->br_blockcount; da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, got->br_blockcount), da_old); got->br_startblock = nullstartblock((int)da_new); - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + xfs_iext_update_extent(ip, state, icur, got); break; case 0: /* @@ -4943,8 +4741,6 @@ xfs_bmap_del_extent_delay( * Warn if either of the new indlen reservations is zero as this * can lead to delalloc problems. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - got->br_blockcount = del->br_startoff - got->br_startoff; got_indlen = xfs_bmap_worst_indlen(ip, got->br_blockcount); @@ -4952,451 +4748,417 @@ xfs_bmap_del_extent_delay( new_indlen = xfs_bmap_worst_indlen(ip, new.br_blockcount); WARN_ON_ONCE(!got_indlen || !new_indlen); - stolen = xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen, - del->br_blockcount); + /* + * Steal as many blocks as we can to try and satisfy the worst + * case indlen for both new extents. + * + * However, we can't just steal reservations from the data + * blocks if this is an RT inodes as the data and metadata + * blocks come from different pools. We'll have to live with + * under-filled indirect reservation in this case. + */ + da_new = got_indlen + new_indlen; + if (da_new > da_old && !isrt) { + stolen = XFS_FILBLKS_MIN(da_new - da_old, + del->br_blockcount); + da_old += stolen; + } + if (da_new > da_old) + xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen); + da_new = got_indlen + new_indlen; got->br_startblock = nullstartblock((int)got_indlen); - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); - trace_xfs_bmap_post_update(ip, *idx, 0, _THIS_IP_); new.br_startoff = del_endoff; new.br_state = got->br_state; new.br_startblock = nullstartblock((int)new_indlen); - ++*idx; - xfs_iext_insert(ip, *idx, 1, &new, state); + xfs_iext_update_extent(ip, state, icur, got); + xfs_iext_next(ifp, icur); + xfs_iext_insert(ip, icur, &new, state); - da_new = got_indlen + new_indlen - stolen; del->br_blockcount -= stolen; break; } ASSERT(da_old >= da_new); da_diff = da_old - da_new; - if (!isrt) - da_diff += del->br_blockcount; - if (da_diff) - xfs_mod_fdblocks(mp, da_diff, false); - return error; + fdblocks = da_diff; + + if (bflags & XFS_BMAPI_REMAP) { + ; + } else if (isrt) { + xfs_rtbxlen_t rtxlen; + + rtxlen = xfs_blen_to_rtbxlen(mp, del->br_blockcount); + if (xfs_is_zoned_inode(ip)) + xfs_zoned_add_available(mp, rtxlen); + xfs_add_frextents(mp, rtxlen); + } else { + fdblocks += del->br_blockcount; + } + + xfs_add_fdblocks(mp, fdblocks); + xfs_mod_delalloc(ip, -(int64_t)del->br_blockcount, -da_diff); } void xfs_bmap_del_extent_cow( struct xfs_inode *ip, - xfs_extnum_t *idx, + struct xfs_iext_cursor *icur, struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); struct xfs_bmbt_irec new; xfs_fileoff_t del_endoff, got_endoff; - int state = BMAP_COWFORK; + uint32_t state = BMAP_COWFORK; XFS_STATS_INC(mp, xs_del_exlist); del_endoff = del->br_startoff + del->br_blockcount; got_endoff = got->br_startoff + got->br_blockcount; - ASSERT(*idx >= 0); - ASSERT(*idx <= xfs_iext_count(ifp)); ASSERT(del->br_blockcount > 0); ASSERT(got->br_startoff <= del->br_startoff); ASSERT(got_endoff >= del_endoff); ASSERT(!isnullstartblock(got->br_startblock)); if (got->br_startoff == del->br_startoff) - state |= BMAP_LEFT_CONTIG; + state |= BMAP_LEFT_FILLING; if (got_endoff == del_endoff) - state |= BMAP_RIGHT_CONTIG; + state |= BMAP_RIGHT_FILLING; - switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { - case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: + switch (state & (BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING)) { + case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING: /* * Matches the whole extent. Delete the entry. */ - xfs_iext_remove(ip, *idx, 1, state); - --*idx; + xfs_iext_remove(ip, icur, state); + xfs_iext_prev(ifp, icur); break; - case BMAP_LEFT_CONTIG: + case BMAP_LEFT_FILLING: /* * Deleting the first part of the extent. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); got->br_startoff = del_endoff; got->br_blockcount -= del->br_blockcount; got->br_startblock = del->br_startblock + del->br_blockcount; - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + xfs_iext_update_extent(ip, state, icur, got); break; - case BMAP_RIGHT_CONTIG: + case BMAP_RIGHT_FILLING: /* * Deleting the last part of the extent. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); got->br_blockcount -= del->br_blockcount; - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + xfs_iext_update_extent(ip, state, icur, got); break; case 0: /* * Deleting the middle of the extent. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); got->br_blockcount = del->br_startoff - got->br_startoff; - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); new.br_startoff = del_endoff; new.br_blockcount = got_endoff - del_endoff; new.br_state = got->br_state; new.br_startblock = del->br_startblock + del->br_blockcount; - ++*idx; - xfs_iext_insert(ip, *idx, 1, &new, state); + xfs_iext_update_extent(ip, state, icur, got); + xfs_iext_next(ifp, icur); + xfs_iext_insert(ip, icur, &new, state); break; } + ip->i_delayed_blks -= del->br_blockcount; +} + +static int +xfs_bmap_free_rtblocks( + struct xfs_trans *tp, + struct xfs_bmbt_irec *del) +{ + struct xfs_rtgroup *rtg; + int error; + + rtg = xfs_rtgroup_grab(tp->t_mountp, 0); + if (!rtg) + return -EIO; + + /* + * Ensure the bitmap and summary inodes are locked and joined to the + * transaction before modifying them. + */ + if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) { + tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED; + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_BITMAP); + } + + error = xfs_rtfree_blocks(tp, rtg, del->br_startblock, + del->br_blockcount); + xfs_rtgroup_rele(rtg); + return error; } /* * Called by xfs_bmapi to update file extent records and the btree - * after removing space (or undoing a delayed allocation). + * after removing space. */ STATIC int /* error */ -xfs_bmap_del_extent( +xfs_bmap_del_extent_real( xfs_inode_t *ip, /* incore inode pointer */ xfs_trans_t *tp, /* current transaction pointer */ - xfs_extnum_t *idx, /* extent number to update/delete */ - struct xfs_defer_ops *dfops, /* list of extents to be freed */ - xfs_btree_cur_t *cur, /* if null, not a btree */ + struct xfs_iext_cursor *icur, + struct xfs_btree_cur *cur, /* if null, not a btree */ xfs_bmbt_irec_t *del, /* data to remove from extents */ int *logflagsp, /* inode logging flags */ int whichfork, /* data or attr fork */ - int bflags) /* bmapi flags */ + uint32_t bflags) /* bmapi flags */ { - xfs_filblks_t da_new; /* new delay-alloc indirect blocks */ - xfs_filblks_t da_old; /* old delay-alloc indirect blocks */ xfs_fsblock_t del_endblock=0; /* first block past del */ xfs_fileoff_t del_endoff; /* first offset past del */ - int delay; /* current block is delayed allocated */ - int do_fx; /* free extent at end of routine */ - xfs_bmbt_rec_host_t *ep; /* current extent entry pointer */ - int error; /* error return value */ - int flags; /* inode logging flags */ - xfs_bmbt_irec_t got; /* current extent entry */ + int error = 0; /* error return value */ + struct xfs_bmbt_irec got; /* current extent entry */ xfs_fileoff_t got_endoff; /* first offset past got */ int i; /* temp state */ - xfs_ifork_t *ifp; /* inode fork pointer */ + struct xfs_ifork *ifp; /* inode fork pointer */ xfs_mount_t *mp; /* mount structure */ xfs_filblks_t nblks; /* quota/sb block count */ xfs_bmbt_irec_t new; /* new record to be inserted */ /* REFERENCED */ uint qfield; /* quota field to update */ - xfs_filblks_t temp; /* for indirect length calculations */ - xfs_filblks_t temp2; /* for indirect length calculations */ - int state = 0; + uint32_t state = xfs_bmap_fork_to_state(whichfork); + struct xfs_bmbt_irec old; + + *logflagsp = 0; mp = ip->i_mount; XFS_STATS_INC(mp, xs_del_exlist); - if (whichfork == XFS_ATTR_FORK) - state |= BMAP_ATTRFORK; - else if (whichfork == XFS_COW_FORK) - state |= BMAP_COWFORK; - - ifp = XFS_IFORK_PTR(ip, whichfork); - ASSERT((*idx >= 0) && (*idx < xfs_iext_count(ifp))); + ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(del->br_blockcount > 0); - ep = xfs_iext_get_ext(ifp, *idx); - xfs_bmbt_get_all(ep, &got); + xfs_iext_get_extent(ifp, icur, &got); ASSERT(got.br_startoff <= del->br_startoff); del_endoff = del->br_startoff + del->br_blockcount; got_endoff = got.br_startoff + got.br_blockcount; ASSERT(got_endoff >= del_endoff); - delay = isnullstartblock(got.br_startblock); - ASSERT(isnullstartblock(del->br_startblock) == delay); - flags = 0; + ASSERT(!isnullstartblock(got.br_startblock)); qfield = 0; - error = 0; + /* - * If deleting a real allocation, must free up the disk space. + * If it's the case where the directory code is running with no block + * reservation, and the deleted block is in the middle of its extent, + * and the resulting insert of an extent would cause transformation to + * btree format, then reject it. The calling code will then swap blocks + * around instead. We have to do this now, rather than waiting for the + * conversion to btree format, since the transaction will be dirty then. */ - if (!delay) { - flags = XFS_ILOG_CORE; - /* - * Realtime allocation. Free it and record di_nblocks update. - */ - if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) { - xfs_fsblock_t bno; - xfs_filblks_t len; - - ASSERT(do_mod(del->br_blockcount, - mp->m_sb.sb_rextsize) == 0); - ASSERT(do_mod(del->br_startblock, - mp->m_sb.sb_rextsize) == 0); - bno = del->br_startblock; - len = del->br_blockcount; - do_div(bno, mp->m_sb.sb_rextsize); - do_div(len, mp->m_sb.sb_rextsize); - error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len); - if (error) - goto done; - do_fx = 0; - nblks = len * mp->m_sb.sb_rextsize; - qfield = XFS_TRANS_DQ_RTBCOUNT; - } - /* - * Ordinary allocation. - */ - else { - do_fx = 1; - nblks = del->br_blockcount; - qfield = XFS_TRANS_DQ_BCOUNT; - } - /* - * Set up del_endblock and cur for later. - */ - del_endblock = del->br_startblock + del->br_blockcount; - if (cur) { - if ((error = xfs_bmbt_lookup_eq(cur, got.br_startoff, - got.br_startblock, got.br_blockcount, - &i))) - goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + if (tp->t_blk_res == 0 && + ifp->if_format == XFS_DINODE_FMT_EXTENTS && + ifp->if_nextents >= XFS_IFORK_MAXEXT(ip, whichfork) && + del->br_startoff > got.br_startoff && del_endoff < got_endoff) + return -ENOSPC; + + *logflagsp = XFS_ILOG_CORE; + if (xfs_ifork_is_realtime(ip, whichfork)) + qfield = XFS_TRANS_DQ_RTBCOUNT; + else + qfield = XFS_TRANS_DQ_BCOUNT; + nblks = del->br_blockcount; + + del_endblock = del->br_startblock + del->br_blockcount; + if (cur) { + error = xfs_bmbt_lookup_eq(cur, &got, &i); + if (error) + return error; + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; } - da_old = da_new = 0; - } else { - da_old = startblockval(got.br_startblock); - da_new = 0; - nblks = 0; - do_fx = 0; } - /* - * Set flag value to use in switch statement. - * Left-contig is 2, right-contig is 1. - */ - switch (((got.br_startoff == del->br_startoff) << 1) | - (got_endoff == del_endoff)) { - case 3: + if (got.br_startoff == del->br_startoff) + state |= BMAP_LEFT_FILLING; + if (got_endoff == del_endoff) + state |= BMAP_RIGHT_FILLING; + + switch (state & (BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING)) { + case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING: /* * Matches the whole extent. Delete the entry. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_iext_remove(ip, *idx, 1, - whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0); - --*idx; - if (delay) - break; + xfs_iext_remove(ip, icur, state); + xfs_iext_prev(ifp, icur); + ifp->if_nextents--; - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) - 1); - flags |= XFS_ILOG_CORE; + *logflagsp |= XFS_ILOG_CORE; if (!cur) { - flags |= xfs_ilog_fext(whichfork); + *logflagsp |= xfs_ilog_fext(whichfork); break; } if ((error = xfs_btree_delete(cur, &i))) - goto done; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); + return error; + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } break; - - case 2: + case BMAP_LEFT_FILLING: /* * Deleting the first part of the extent. */ - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_startoff(ep, del_endoff); - temp = got.br_blockcount - del->br_blockcount; - xfs_bmbt_set_blockcount(ep, temp); - if (delay) { - temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - da_old); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); - da_new = temp; - break; - } - xfs_bmbt_set_startblock(ep, del_endblock); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + got.br_startoff = del_endoff; + got.br_startblock = del_endblock; + got.br_blockcount -= del->br_blockcount; + xfs_iext_update_extent(ip, state, icur, &got); if (!cur) { - flags |= xfs_ilog_fext(whichfork); + *logflagsp |= xfs_ilog_fext(whichfork); break; } - if ((error = xfs_bmbt_update(cur, del_endoff, del_endblock, - got.br_blockcount - del->br_blockcount, - got.br_state))) - goto done; + error = xfs_bmbt_update(cur, &got); + if (error) + return error; break; - - case 1: + case BMAP_RIGHT_FILLING: /* * Deleting the last part of the extent. */ - temp = got.br_blockcount - del->br_blockcount; - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - if (delay) { - temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - da_old); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); - da_new = temp; - break; - } - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + got.br_blockcount -= del->br_blockcount; + xfs_iext_update_extent(ip, state, icur, &got); if (!cur) { - flags |= xfs_ilog_fext(whichfork); + *logflagsp |= xfs_ilog_fext(whichfork); break; } - if ((error = xfs_bmbt_update(cur, got.br_startoff, - got.br_startblock, - got.br_blockcount - del->br_blockcount, - got.br_state))) - goto done; + error = xfs_bmbt_update(cur, &got); + if (error) + return error; break; - case 0: /* * Deleting the middle of the extent. */ - temp = del->br_startoff - got.br_startoff; - trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); + + old = got; + + got.br_blockcount = del->br_startoff - got.br_startoff; + xfs_iext_update_extent(ip, state, icur, &got); + new.br_startoff = del_endoff; - temp2 = got_endoff - del_endoff; - new.br_blockcount = temp2; + new.br_blockcount = got_endoff - del_endoff; new.br_state = got.br_state; - if (!delay) { - new.br_startblock = del_endblock; - flags |= XFS_ILOG_CORE; - if (cur) { - if ((error = xfs_bmbt_update(cur, - got.br_startoff, - got.br_startblock, temp, - got.br_state))) - goto done; - if ((error = xfs_btree_increment(cur, 0, &i))) - goto done; - cur->bc_rec.b = new; - error = xfs_btree_insert(cur, &i); - if (error && error != -ENOSPC) - goto done; - /* - * If get no-space back from btree insert, - * it tried a split, and we have a zero - * block reservation. - * Fix up our state and return the error. - */ - if (error == -ENOSPC) { - /* - * Reset the cursor, don't trust - * it after any insert operation. - */ - if ((error = xfs_bmbt_lookup_eq(cur, - got.br_startoff, - got.br_startblock, - temp, &i))) - goto done; - XFS_WANT_CORRUPTED_GOTO(mp, - i == 1, done); - /* - * Update the btree record back - * to the original value. - */ - if ((error = xfs_bmbt_update(cur, - got.br_startoff, - got.br_startblock, - got.br_blockcount, - got.br_state))) - goto done; - /* - * Reset the extent record back - * to the original value. - */ - xfs_bmbt_set_blockcount(ep, - got.br_blockcount); - flags = 0; - error = -ENOSPC; - goto done; - } - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done); - } else - flags |= xfs_ilog_fext(whichfork); - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) + 1); - } else { - xfs_filblks_t stolen; - ASSERT(whichfork == XFS_DATA_FORK); + new.br_startblock = del_endblock; + *logflagsp |= XFS_ILOG_CORE; + if (cur) { + error = xfs_bmbt_update(cur, &got); + if (error) + return error; + error = xfs_btree_increment(cur, 0, &i); + if (error) + return error; + cur->bc_rec.b = new; + error = xfs_btree_insert(cur, &i); + if (error && error != -ENOSPC) + return error; /* - * Distribute the original indlen reservation across the - * two new extents. Steal blocks from the deleted extent - * if necessary. Stealing blocks simply fudges the - * fdblocks accounting in xfs_bunmapi(). + * If get no-space back from btree insert, it tried a + * split, and we have a zero block reservation. Fix up + * our state and return the error. */ - temp = xfs_bmap_worst_indlen(ip, got.br_blockcount); - temp2 = xfs_bmap_worst_indlen(ip, new.br_blockcount); - stolen = xfs_bmap_split_indlen(da_old, &temp, &temp2, - del->br_blockcount); - da_new = temp + temp2 - stolen; - del->br_blockcount -= stolen; + if (error == -ENOSPC) { + /* + * Reset the cursor, don't trust it after any + * insert operation. + */ + error = xfs_bmbt_lookup_eq(cur, &got, &i); + if (error) + return error; + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + /* + * Update the btree record back + * to the original value. + */ + error = xfs_bmbt_update(cur, &old); + if (error) + return error; + /* + * Reset the extent record back + * to the original value. + */ + xfs_iext_update_extent(ip, state, icur, &old); + *logflagsp = 0; + return -ENOSPC; + } + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + } else + *logflagsp |= xfs_ilog_fext(whichfork); - /* - * Set the reservation for each extent. Warn if either - * is zero as this can lead to delalloc problems. - */ - WARN_ON_ONCE(!temp || !temp2); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - new.br_startblock = nullstartblock((int)temp2); - } - trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); - xfs_iext_insert(ip, *idx + 1, 1, &new, state); - ++*idx; + ifp->if_nextents++; + xfs_iext_next(ifp, icur); + xfs_iext_insert(ip, icur, &new, state); break; } /* remove reverse mapping */ - if (!delay) { - error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, del); - if (error) - goto done; - } + xfs_rmap_unmap_extent(tp, ip, whichfork, del); /* * If we need to, add to list of extents to delete. */ - if (do_fx && !(bflags & XFS_BMAPI_REMAP)) { + if (!(bflags & XFS_BMAPI_REMAP)) { + bool isrt = xfs_ifork_is_realtime(ip, whichfork); + if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) { - error = xfs_refcount_decrease_extent(mp, dfops, del); - if (error) - goto done; - } else - xfs_bmap_add_free(mp, dfops, del->br_startblock, - del->br_blockcount, NULL); + xfs_refcount_decrease_extent(tp, isrt, del); + } else if (isrt && !xfs_has_rtgroups(mp)) { + error = xfs_bmap_free_rtblocks(tp, del); + } else { + unsigned int efi_flags = 0; + + if ((bflags & XFS_BMAPI_NODISCARD) || + del->br_state == XFS_EXT_UNWRITTEN) + efi_flags |= XFS_FREE_EXTENT_SKIP_DISCARD; + + /* + * Historically, we did not use EFIs to free realtime + * extents. However, when reverse mapping is enabled, + * we must maintain the same order of operations as the + * data device, which is: Remove the file mapping, + * remove the reverse mapping, and then free the + * blocks. Reflink for realtime volumes requires the + * same sort of ordering. Both features rely on + * rtgroups, so let's gate rt EFI usage on rtgroups. + */ + if (isrt) + efi_flags |= XFS_FREE_EXTENT_REALTIME; + + error = xfs_free_extent_later(tp, del->br_startblock, + del->br_blockcount, NULL, + XFS_AG_RESV_NONE, efi_flags); + } + if (error) + return error; } /* * Adjust inode # blocks in the file. */ if (nblks) - ip->i_d.di_nblocks -= nblks; + ip->i_nblocks -= nblks; /* * Adjust quota data. */ if (qfield && !(bflags & XFS_BMAPI_REMAP)) xfs_trans_mod_dquot_byino(tp, ip, qfield, (long)-nblks); - /* - * Account for change in delayed indirect blocks. - * Nothing to do for disk quota accounting here. - */ - ASSERT(da_old >= da_new); - if (da_old > da_new) - xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false); -done: - *logflagsp = flags; - return error; + return 0; } /* @@ -5405,129 +5167,93 @@ done: * that value. If not all extents in the block range can be removed then * *done is set. */ -int /* error */ +static int __xfs_bunmapi( - xfs_trans_t *tp, /* transaction pointer */ + struct xfs_trans *tp, /* transaction pointer */ struct xfs_inode *ip, /* incore inode */ - xfs_fileoff_t bno, /* starting offset to unmap */ + xfs_fileoff_t start, /* first file offset deleted */ xfs_filblks_t *rlen, /* i/o: amount remaining */ - int flags, /* misc flags */ - xfs_extnum_t nexts, /* number of extents max */ - xfs_fsblock_t *firstblock, /* first allocated block - controls a.g. for allocs */ - struct xfs_defer_ops *dfops) /* i/o: deferred updates */ + uint32_t flags, /* misc flags */ + xfs_extnum_t nexts) /* number of extents max */ { - xfs_btree_cur_t *cur; /* bmap btree cursor */ - xfs_bmbt_irec_t del; /* extent being deleted */ + struct xfs_btree_cur *cur; /* bmap btree cursor */ + struct xfs_bmbt_irec del; /* extent being deleted */ int error; /* error return value */ xfs_extnum_t extno; /* extent number in list */ - xfs_bmbt_irec_t got; /* current extent record */ - xfs_ifork_t *ifp; /* inode fork pointer */ + struct xfs_bmbt_irec got; /* current extent record */ + struct xfs_ifork *ifp; /* inode fork pointer */ int isrt; /* freeing in rt area */ - xfs_extnum_t lastx; /* last extent index used */ int logflags; /* transaction logging flags */ xfs_extlen_t mod; /* rt extent offset */ - xfs_mount_t *mp; /* mount structure */ - xfs_fileoff_t start; /* first file offset deleted */ + struct xfs_mount *mp = ip->i_mount; int tmp_logflags; /* partial logging flags */ int wasdel; /* was a delayed alloc extent */ int whichfork; /* data or attribute fork */ - xfs_fsblock_t sum; xfs_filblks_t len = *rlen; /* length to unmap in file */ - xfs_fileoff_t max_len; - xfs_agnumber_t prev_agno = NULLAGNUMBER, agno; + xfs_fileoff_t end; + struct xfs_iext_cursor icur; + bool done = false; - trace_xfs_bunmap(ip, bno, len, flags, _RET_IP_); + trace_xfs_bunmap(ip, start, len, flags, _RET_IP_); whichfork = xfs_bmapi_whichfork(flags); ASSERT(whichfork != XFS_COW_FORK); - ifp = XFS_IFORK_PTR(ip, whichfork); - if (unlikely( - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE)) { - XFS_ERROR_REPORT("xfs_bunmapi", XFS_ERRLEVEL_LOW, - ip->i_mount); + ifp = xfs_ifork_ptr(ip, whichfork); + if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp))) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } - mp = ip->i_mount; - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) return -EIO; - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); ASSERT(len > 0); ASSERT(nexts >= 0); - /* - * Guesstimate how many blocks we can unmap without running the risk of - * blowing out the transaction with a mix of EFIs and reflink - * adjustments. - */ - if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) - max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res)); - else - max_len = len; - - if (!(ifp->if_flags & XFS_IFEXTENTS) && - (error = xfs_iread_extents(tp, ip, whichfork))) + error = xfs_iread_extents(tp, ip, whichfork); + if (error) return error; + if (xfs_iext_count(ifp) == 0) { *rlen = 0; return 0; } XFS_STATS_INC(mp, xs_blk_unmap); - isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip); - start = bno; - bno = start + len - 1; + isrt = xfs_ifork_is_realtime(ip, whichfork); + end = start + len; - /* - * Check to see if the given block number is past the end of the - * file, back up to the last block if so... - */ - if (!xfs_iext_lookup_extent(ip, ifp, bno, &lastx, &got)) { - ASSERT(lastx > 0); - xfs_iext_get_extent(ifp, --lastx, &got); - bno = got.br_startoff + got.br_blockcount - 1; + if (!xfs_iext_lookup_extent_before(ip, ifp, &end, &icur, &got)) { + *rlen = 0; + return 0; } + end--; logflags = 0; - if (ifp->if_flags & XFS_IFBROOT) { - ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE); + if (ifp->if_format == XFS_DINODE_FMT_BTREE) { + ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE); cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); - cur->bc_private.b.firstblock = *firstblock; - cur->bc_private.b.dfops = dfops; - cur->bc_private.b.flags = 0; } else cur = NULL; - if (isrt) { - /* - * Synchronize by locking the bitmap inode. - */ - xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP); - xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL); - xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM); - xfs_trans_ijoin(tp, mp->m_rsumip, XFS_ILOCK_EXCL); - } - extno = 0; - while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 && - (nexts == 0 || extno < nexts) && max_len > 0) { + while (end != (xfs_fileoff_t)-1 && end >= start && + (nexts == 0 || extno < nexts)) { /* - * Is the found extent after a hole in which bno lives? + * Is the found extent after a hole in which end lives? * Just back up to the previous extent, if so. */ - if (got.br_startoff > bno) { - if (--lastx < 0) - break; - xfs_iext_get_extent(ifp, lastx, &got); + if (got.br_startoff > end && + !xfs_iext_prev_extent(ifp, &icur, &got)) { + done = true; + break; } /* * Is the last block of this extent before the range * we're supposed to delete? If so, we're done. */ - bno = XFS_FILEOFF_MIN(bno, + end = XFS_FILEOFF_MIN(end, got.br_startoff + got.br_blockcount - 1); - if (bno < start) + if (end < start) break; /* * Then deal with the (possibly delayed) allocated space @@ -5536,36 +5262,21 @@ __xfs_bunmapi( del = got; wasdel = isnullstartblock(del.br_startblock); - /* - * Make sure we don't touch multiple AGF headers out of order - * in a single transaction, as that could cause AB-BA deadlocks. - */ - if (!wasdel) { - agno = XFS_FSB_TO_AGNO(mp, del.br_startblock); - if (prev_agno != NULLAGNUMBER && prev_agno > agno) - break; - prev_agno = agno; - } if (got.br_startoff < start) { del.br_startoff = start; del.br_blockcount -= start - got.br_startoff; if (!wasdel) del.br_startblock += start - got.br_startoff; } - if (del.br_startoff + del.br_blockcount > bno + 1) - del.br_blockcount = bno + 1 - del.br_startoff; + if (del.br_startoff + del.br_blockcount > end + 1) + del.br_blockcount = end + 1 - del.br_startoff; - /* How much can we safely unmap? */ - if (max_len < del.br_blockcount) { - del.br_startoff += del.br_blockcount - max_len; - if (!wasdel) - del.br_startblock += del.br_blockcount - max_len; - del.br_blockcount = max_len; - } + if (!isrt || (flags & XFS_BMAPI_REMAP)) + goto delete; - sum = del.br_startblock + del.br_blockcount; - if (isrt && - (mod = do_mod(sum, mp->m_sb.sb_rextsize))) { + mod = xfs_rtb_to_rtxoff(mp, + del.br_startblock + del.br_blockcount); + if (mod) { /* * Realtime extent not lined up at the end. * The extent could have been split into written @@ -5573,19 +5284,18 @@ __xfs_bunmapi( * unmapping part of it. But we can't really * get rid of part of a realtime extent. */ - if (del.br_state == XFS_EXT_UNWRITTEN || - !xfs_sb_version_hasextflgbit(&mp->m_sb)) { + if (del.br_state == XFS_EXT_UNWRITTEN) { /* * This piece is unwritten, or we're not * using unwritten extents. Skip over it. */ - ASSERT(bno >= mod); - bno -= mod > del.br_blockcount ? + ASSERT((flags & XFS_BMAPI_REMAP) || end >= mod); + end -= mod > del.br_blockcount ? del.br_blockcount : mod; - if (bno < got.br_startoff) { - if (--lastx >= 0) - xfs_bmbt_get_all(xfs_iext_get_ext( - ifp, lastx), &got); + if (end < got.br_startoff && + !xfs_iext_prev_extent(ifp, &icur, &got)) { + done = true; + break; } continue; } @@ -5606,38 +5316,44 @@ __xfs_bunmapi( } del.br_state = XFS_EXT_UNWRITTEN; error = xfs_bmap_add_extent_unwritten_real(tp, ip, - whichfork, &lastx, &cur, &del, - firstblock, dfops, &logflags); + whichfork, &icur, &cur, &del, + &logflags); if (error) goto error0; goto nodelete; } - if (isrt && (mod = do_mod(del.br_startblock, mp->m_sb.sb_rextsize))) { + + mod = xfs_rtb_to_rtxoff(mp, del.br_startblock); + if (mod) { + xfs_extlen_t off = mp->m_sb.sb_rextsize - mod; + /* * Realtime extent is lined up at the end but not * at the front. We'll get rid of full extents if * we can. */ - mod = mp->m_sb.sb_rextsize - mod; - if (del.br_blockcount > mod) { - del.br_blockcount -= mod; - del.br_startoff += mod; - del.br_startblock += mod; - } else if ((del.br_startoff == start && - (del.br_state == XFS_EXT_UNWRITTEN || - tp->t_blk_res == 0)) || - !xfs_sb_version_hasextflgbit(&mp->m_sb)) { + if (del.br_blockcount > off) { + del.br_blockcount -= off; + del.br_startoff += off; + del.br_startblock += off; + } else if (del.br_startoff == start && + (del.br_state == XFS_EXT_UNWRITTEN || + tp->t_blk_res == 0)) { /* * Can't make it unwritten. There isn't * a full extent here so just skip it. */ - ASSERT(bno >= del.br_blockcount); - bno -= del.br_blockcount; - if (got.br_startoff > bno && --lastx >= 0) - xfs_iext_get_extent(ifp, lastx, &got); + ASSERT(end >= del.br_blockcount); + end -= del.br_blockcount; + if (got.br_startoff > end && + !xfs_iext_prev_extent(ifp, &icur, &got)) { + done = true; + break; + } continue; } else if (del.br_state == XFS_EXT_UNWRITTEN) { struct xfs_bmbt_irec prev; + xfs_fileoff_t unwrite_start; /* * This one is already unwritten. @@ -5645,24 +5361,23 @@ __xfs_bunmapi( * Unwrite the killed part of that one and * try again. */ - ASSERT(lastx > 0); - xfs_iext_get_extent(ifp, lastx - 1, &prev); + if (!xfs_iext_prev_extent(ifp, &icur, &prev)) + ASSERT(0); ASSERT(prev.br_state == XFS_EXT_NORM); ASSERT(!isnullstartblock(prev.br_startblock)); ASSERT(del.br_startblock == prev.br_startblock + prev.br_blockcount); - if (prev.br_startoff < start) { - mod = start - prev.br_startoff; - prev.br_blockcount -= mod; - prev.br_startblock += mod; - prev.br_startoff = start; - } + unwrite_start = max3(start, + del.br_startoff - mod, + prev.br_startoff); + mod = unwrite_start - prev.br_startoff; + prev.br_startoff = unwrite_start; + prev.br_startblock += mod; + prev.br_blockcount -= mod; prev.br_state = XFS_EXT_UNWRITTEN; - lastx--; error = xfs_bmap_add_extent_unwritten_real(tp, - ip, whichfork, &lastx, &cur, - &prev, firstblock, dfops, - &logflags); + ip, whichfork, &icur, &cur, + &prev, &logflags); if (error) goto error0; goto nodelete; @@ -5670,131 +5385,70 @@ __xfs_bunmapi( ASSERT(del.br_state == XFS_EXT_NORM); del.br_state = XFS_EXT_UNWRITTEN; error = xfs_bmap_add_extent_unwritten_real(tp, - ip, whichfork, &lastx, &cur, - &del, firstblock, dfops, - &logflags); + ip, whichfork, &icur, &cur, + &del, &logflags); if (error) goto error0; goto nodelete; } } - /* - * If it's the case where the directory code is running - * with no block reservation, and the deleted block is in - * the middle of its extent, and the resulting insert - * of an extent would cause transformation to btree format, - * then reject it. The calling code will then swap - * blocks around instead. - * We have to do this now, rather than waiting for the - * conversion to btree format, since the transaction - * will be dirty. - */ - if (!wasdel && tp->t_blk_res == 0 && - XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_NEXTENTS(ip, whichfork) >= /* Note the >= */ - XFS_IFORK_MAXEXT(ip, whichfork) && - del.br_startoff > got.br_startoff && - del.br_startoff + del.br_blockcount < - got.br_startoff + got.br_blockcount) { - error = -ENOSPC; - goto error0; - } - - /* - * Unreserve quota and update realtime free space, if - * appropriate. If delayed allocation, update the inode delalloc - * counter now and wait to update the sb counters as - * xfs_bmap_del_extent() might need to borrow some blocks. - */ +delete: if (wasdel) { - ASSERT(startblockval(del.br_startblock) > 0); - if (isrt) { - xfs_filblks_t rtexts; - - rtexts = XFS_FSB_TO_B(mp, del.br_blockcount); - do_div(rtexts, mp->m_sb.sb_rextsize); - xfs_mod_frextents(mp, (int64_t)rtexts); - (void)xfs_trans_reserve_quota_nblks(NULL, - ip, -((long)del.br_blockcount), 0, - XFS_QMOPT_RES_RTBLKS); - } else { - (void)xfs_trans_reserve_quota_nblks(NULL, - ip, -((long)del.br_blockcount), 0, - XFS_QMOPT_RES_REGBLKS); - } - ip->i_delayed_blks -= del.br_blockcount; - if (cur) - cur->bc_private.b.flags |= - XFS_BTCUR_BPRV_WASDEL; - } else if (cur) - cur->bc_private.b.flags &= ~XFS_BTCUR_BPRV_WASDEL; - - error = xfs_bmap_del_extent(ip, tp, &lastx, dfops, cur, &del, - &tmp_logflags, whichfork, flags); - logflags |= tmp_logflags; - if (error) - goto error0; - - if (!isrt && wasdel) - xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false); + xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, + &del, flags); + } else { + error = xfs_bmap_del_extent_real(ip, tp, &icur, cur, + &del, &tmp_logflags, whichfork, + flags); + logflags |= tmp_logflags; + if (error) + goto error0; + } - max_len -= del.br_blockcount; - bno = del.br_startoff - 1; + end = del.br_startoff - 1; nodelete: /* * If not done go on to the next (previous) record. */ - if (bno != (xfs_fileoff_t)-1 && bno >= start) { - if (lastx >= 0) { - xfs_iext_get_extent(ifp, lastx, &got); - if (got.br_startoff > bno && --lastx >= 0) - xfs_iext_get_extent(ifp, lastx, &got); + if (end != (xfs_fileoff_t)-1 && end >= start) { + if (!xfs_iext_get_extent(ifp, &icur, &got) || + (got.br_startoff > end && + !xfs_iext_prev_extent(ifp, &icur, &got))) { + done = true; + break; } extno++; } } - if (bno == (xfs_fileoff_t)-1 || bno < start || lastx < 0) + if (done || end == (xfs_fileoff_t)-1 || end < start) *rlen = 0; else - *rlen = bno - start + 1; + *rlen = end - start + 1; /* * Convert to a btree if necessary. */ if (xfs_bmap_needs_btree(ip, whichfork)) { ASSERT(cur == NULL); - error = xfs_bmap_extents_to_btree(tp, ip, firstblock, dfops, - &cur, 0, &tmp_logflags, whichfork); + error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, + &tmp_logflags, whichfork); logflags |= tmp_logflags; - if (error) - goto error0; - } - /* - * transform from btree to extents, give it cur - */ - else if (xfs_bmap_wants_extents(ip, whichfork)) { - ASSERT(cur != NULL); - error = xfs_bmap_btree_to_extents(tp, ip, cur, &tmp_logflags, + } else { + error = xfs_bmap_btree_to_extents(tp, ip, cur, &logflags, whichfork); - logflags |= tmp_logflags; - if (error) - goto error0; } - /* - * transform from extents to local? - */ - error = 0; + error0: /* * Log everything. Do this after conversion, there's no point in * logging the extent records if we've converted to btree format. */ if ((logflags & xfs_ilog_fext(whichfork)) && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS) + ifp->if_format != XFS_DINODE_FMT_EXTENTS) logflags &= ~xfs_ilog_fext(whichfork); else if ((logflags & xfs_ilog_fbroot(whichfork)) && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE) + ifp->if_format != XFS_DINODE_FMT_BTREE) logflags &= ~xfs_ilog_fbroot(whichfork); /* * Log inode even in the error case, if the transaction @@ -5803,12 +5457,9 @@ error0: if (logflags) xfs_trans_log_inode(tp, ip, logflags); if (cur) { - if (!error) { - *firstblock = cur->bc_private.b.firstblock; - cur->bc_private.b.allocated = 0; - } - xfs_btree_del_cursor(cur, - error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); + if (!error) + cur->bc_bmap.allocated = 0; + xfs_btree_del_cursor(cur, error); } return error; } @@ -5820,16 +5471,13 @@ xfs_bunmapi( struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, - int flags, + uint32_t flags, xfs_extnum_t nexts, - xfs_fsblock_t *firstblock, - struct xfs_defer_ops *dfops, int *done) { int error; - error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts, firstblock, - dfops); + error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts); *done = (len == 0); return error; } @@ -5840,6 +5488,8 @@ xfs_bunmapi( */ STATIC bool xfs_bmse_can_merge( + struct xfs_inode *ip, + int whichfork, struct xfs_bmbt_irec *left, /* preceding extent */ struct xfs_bmbt_irec *got, /* current extent to shift */ xfs_fileoff_t shift) /* shift fsb */ @@ -5855,7 +5505,8 @@ xfs_bmse_can_merge( if ((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)) + (left->br_blockcount + got->br_blockcount > XFS_MAX_BMBT_EXTLEN) || + !xfs_bmap_same_rtgroup(ip, whichfork, left, got)) return false; return true; @@ -5872,429 +5523,392 @@ xfs_bmse_can_merge( */ STATIC int xfs_bmse_merge( + struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, xfs_fileoff_t shift, /* shift fsb */ - int current_ext, /* idx of gotp */ - struct xfs_bmbt_rec_host *gotp, /* extent to shift */ - struct xfs_bmbt_rec_host *leftp, /* preceding extent */ + struct xfs_iext_cursor *icur, + struct xfs_bmbt_irec *got, /* extent to shift */ + struct xfs_bmbt_irec *left, /* preceding extent */ struct xfs_btree_cur *cur, int *logflags) /* output */ { - struct xfs_bmbt_irec got; - struct xfs_bmbt_irec left; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_bmbt_irec new; xfs_filblks_t blockcount; int error, i; struct xfs_mount *mp = ip->i_mount; - xfs_bmbt_get_all(gotp, &got); - xfs_bmbt_get_all(leftp, &left); - blockcount = left.br_blockcount + got.br_blockcount; + blockcount = left->br_blockcount + got->br_blockcount; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ASSERT(xfs_bmse_can_merge(&left, &got, shift)); + xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); + ASSERT(xfs_bmse_can_merge(ip, whichfork, left, got, shift)); - /* - * Merge the in-core extents. Note that the host record pointers and - * current_ext index are invalid once the extent has been removed via - * xfs_iext_remove(). - */ - xfs_bmbt_set_blockcount(leftp, blockcount); - xfs_iext_remove(ip, current_ext, 1, 0); + new = *left; + new.br_blockcount = blockcount; /* * Update the on-disk extent count, the btree if necessary and log the * inode. */ - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) - 1); + ifp->if_nextents--; *logflags |= XFS_ILOG_CORE; if (!cur) { *logflags |= XFS_ILOG_DEXT; - return 0; + goto done; } /* lookup and remove the extent to merge */ - error = xfs_bmbt_lookup_eq(cur, got.br_startoff, got.br_startblock, - got.br_blockcount, &i); + error = xfs_bmbt_lookup_eq(cur, got, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(mp, i == 1); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } error = xfs_btree_delete(cur, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(mp, i == 1); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } /* lookup and update size of the previous extent */ - error = xfs_bmbt_lookup_eq(cur, left.br_startoff, left.br_startblock, - left.br_blockcount, &i); + error = xfs_bmbt_lookup_eq(cur, left, &i); if (error) return error; - XFS_WANT_CORRUPTED_RETURN(mp, i == 1); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } - left.br_blockcount = blockcount; + error = xfs_bmbt_update(cur, &new); + if (error) + return error; - return xfs_bmbt_update(cur, left.br_startoff, left.br_startblock, - left.br_blockcount, left.br_state); + /* change to extent format if required after extent removal */ + error = xfs_bmap_btree_to_extents(tp, ip, cur, logflags, whichfork); + if (error) + return error; + +done: + xfs_iext_remove(ip, icur, 0); + xfs_iext_prev(ifp, icur); + xfs_iext_update_extent(ip, xfs_bmap_fork_to_state(whichfork), icur, + &new); + + /* update reverse mapping. rmap functions merge the rmaps for us */ + xfs_rmap_unmap_extent(tp, ip, whichfork, got); + memcpy(&new, got, sizeof(new)); + new.br_startoff = left->br_startoff + left->br_blockcount; + xfs_rmap_map_extent(tp, ip, whichfork, &new); + return 0; } -/* - * Shift a single extent. - */ -STATIC int -xfs_bmse_shift_one( - struct xfs_inode *ip, - int whichfork, - xfs_fileoff_t offset_shift_fsb, - int *current_ext, - struct xfs_bmbt_rec_host *gotp, - struct xfs_btree_cur *cur, - int *logflags, - enum shift_direction direction, - struct xfs_defer_ops *dfops) +static int +xfs_bmap_shift_update_extent( + struct xfs_trans *tp, + struct xfs_inode *ip, + int whichfork, + struct xfs_iext_cursor *icur, + struct xfs_bmbt_irec *got, + struct xfs_btree_cur *cur, + int *logflags, + xfs_fileoff_t startoff) { - struct xfs_ifork *ifp; - struct xfs_mount *mp; - xfs_fileoff_t startoff; - struct xfs_bmbt_rec_host *adj_irecp; - struct xfs_bmbt_irec got; - struct xfs_bmbt_irec adj_irec; - int error; - int i; - int total_extents; - - mp = ip->i_mount; - ifp = XFS_IFORK_PTR(ip, whichfork); - total_extents = xfs_iext_count(ifp); - - xfs_bmbt_get_all(gotp, &got); + struct xfs_mount *mp = ip->i_mount; + struct xfs_bmbt_irec prev = *got; + int error, i; - /* delalloc extents should be prevented by caller */ - XFS_WANT_CORRUPTED_RETURN(mp, !isnullstartblock(got.br_startblock)); + *logflags |= XFS_ILOG_CORE; - if (direction == SHIFT_LEFT) { - startoff = got.br_startoff - offset_shift_fsb; + got->br_startoff = startoff; - /* - * Check for merge if we've got an extent to the left, - * otherwise make sure there's enough room at the start - * of the file for the shift. - */ - if (!*current_ext) { - if (got.br_startoff < offset_shift_fsb) - return -EINVAL; - goto update_current_ext; + if (cur) { + error = xfs_bmbt_lookup_eq(cur, &prev, &i); + if (error) + return error; + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; } - /* - * grab the left extent and check for a large - * enough hole. - */ - adj_irecp = xfs_iext_get_ext(ifp, *current_ext - 1); - xfs_bmbt_get_all(adj_irecp, &adj_irec); - - if (startoff < - adj_irec.br_startoff + adj_irec.br_blockcount) - return -EINVAL; - /* check whether to merge the extent or shift it down */ - if (xfs_bmse_can_merge(&adj_irec, &got, - offset_shift_fsb)) { - error = xfs_bmse_merge(ip, whichfork, offset_shift_fsb, - *current_ext, gotp, adj_irecp, - cur, logflags); - if (error) - return error; - adj_irec = got; - goto update_rmap; - } + error = xfs_bmbt_update(cur, got); + if (error) + return error; } else { - startoff = got.br_startoff + offset_shift_fsb; - /* nothing to move if this is the last extent */ - if (*current_ext >= (total_extents - 1)) - goto update_current_ext; - /* - * If this is not the last extent in the file, make sure there - * is enough room between current extent and next extent for - * accommodating the shift. - */ - adj_irecp = xfs_iext_get_ext(ifp, *current_ext + 1); - xfs_bmbt_get_all(adj_irecp, &adj_irec); - if (startoff + got.br_blockcount > adj_irec.br_startoff) - return -EINVAL; - /* - * Unlike a left shift (which involves a hole punch), - * a right shift does not modify extent neighbors - * in any way. We should never find mergeable extents - * in this scenario. Check anyways and warn if we - * encounter two extents that could be one. - */ - if (xfs_bmse_can_merge(&got, &adj_irec, offset_shift_fsb)) - WARN_ON_ONCE(1); - } - /* - * Increment the extent index for the next iteration, update the start - * offset of the in-core extent and update the btree if applicable. - */ -update_current_ext: - if (direction == SHIFT_LEFT) - (*current_ext)++; - else - (*current_ext)--; - xfs_bmbt_set_startoff(gotp, startoff); - *logflags |= XFS_ILOG_CORE; - adj_irec = got; - if (!cur) { *logflags |= XFS_ILOG_DEXT; - goto update_rmap; } - error = xfs_bmbt_lookup_eq(cur, got.br_startoff, got.br_startblock, - got.br_blockcount, &i); - if (error) - return error; - XFS_WANT_CORRUPTED_RETURN(mp, i == 1); + xfs_iext_update_extent(ip, xfs_bmap_fork_to_state(whichfork), icur, + got); - got.br_startoff = startoff; - error = xfs_bmbt_update(cur, got.br_startoff, got.br_startblock, - got.br_blockcount, got.br_state); - if (error) - return error; - -update_rmap: /* update reverse mapping */ - error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, &adj_irec); - if (error) - return error; - adj_irec.br_startoff = startoff; - return xfs_rmap_map_extent(mp, dfops, ip, whichfork, &adj_irec); + xfs_rmap_unmap_extent(tp, ip, whichfork, &prev); + xfs_rmap_map_extent(tp, ip, whichfork, got); + return 0; } -/* - * Shift extent records to the left/right to cover/create a hole. - * - * The maximum number of extents to be shifted in a single operation is - * @num_exts. @stop_fsb specifies the file offset at which to stop shift and the - * file offset where we've left off is returned in @next_fsb. @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 -xfs_bmap_shift_extents( +xfs_bmap_collapse_extents( struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb, - int *done, - xfs_fileoff_t stop_fsb, - xfs_fsblock_t *firstblock, - struct xfs_defer_ops *dfops, - enum shift_direction direction, - int num_exts) + bool *done) { - struct xfs_btree_cur *cur = NULL; - struct xfs_bmbt_rec_host *gotp; - struct xfs_bmbt_irec got; - struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp; - xfs_extnum_t nexts = 0; - xfs_extnum_t current_ext; - xfs_extnum_t total_extents; - xfs_extnum_t stop_extent; - int error = 0; - int whichfork = XFS_DATA_FORK; - int logflags = 0; + int whichfork = XFS_DATA_FORK; + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_btree_cur *cur = NULL; + struct xfs_bmbt_irec got, prev; + struct xfs_iext_cursor icur; + xfs_fileoff_t new_startoff; + int error = 0; + int logflags = 0; - 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_ERROR_REPORT("xfs_bmap_shift_extents", - XFS_ERRLEVEL_LOW, mp); + if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) return -EIO; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ASSERT(direction == SHIFT_LEFT || direction == SHIFT_RIGHT); - ASSERT(*next_fsb != NULLFSBLOCK || direction == SHIFT_RIGHT); + xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); - 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; - } + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; - if (ifp->if_flags & XFS_IFBROOT) { + if (ifp->if_format == XFS_DINODE_FMT_BTREE) cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); - cur->bc_private.b.firstblock = *firstblock; - cur->bc_private.b.dfops = dfops; - cur->bc_private.b.flags = 0; - } - /* - * 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. - */ - total_extents = xfs_iext_count(ifp); - if (total_extents == 0) { - *done = 1; + if (!xfs_iext_lookup_extent(ip, ifp, *next_fsb, &icur, &got)) { + *done = true; + goto del_cursor; + } + if (XFS_IS_CORRUPT(mp, isnullstartblock(got.br_startblock))) { + xfs_bmap_mark_sick(ip, whichfork); + error = -EFSCORRUPTED; goto del_cursor; } - /* - * In case of first right shift, we need to initialize next_fsb - */ - if (*next_fsb == NULLFSBLOCK) { - gotp = xfs_iext_get_ext(ifp, total_extents - 1); - xfs_bmbt_get_all(gotp, &got); - *next_fsb = got.br_startoff; - if (stop_fsb > *next_fsb) { - *done = 1; + new_startoff = got.br_startoff - offset_shift_fsb; + if (xfs_iext_peek_prev_extent(ifp, &icur, &prev)) { + if (new_startoff < prev.br_startoff + prev.br_blockcount) { + error = -EINVAL; + goto del_cursor; + } + + if (xfs_bmse_can_merge(ip, whichfork, &prev, &got, + offset_shift_fsb)) { + error = xfs_bmse_merge(tp, ip, whichfork, + offset_shift_fsb, &icur, &got, &prev, + cur, &logflags); + if (error) + goto del_cursor; + goto done; + } + } else { + if (got.br_startoff < offset_shift_fsb) { + error = -EINVAL; goto del_cursor; } } - /* Lookup the extent index at which we have to stop */ - if (direction == SHIFT_RIGHT) { - gotp = xfs_iext_bno_to_ext(ifp, stop_fsb, &stop_extent); - /* Make stop_extent exclusive of shift range */ - stop_extent--; - } else - stop_extent = total_extents; + error = xfs_bmap_shift_update_extent(tp, ip, whichfork, &icur, &got, + cur, &logflags, new_startoff); + if (error) + goto del_cursor; - /* - * Look up the extent index for the fsb where we start shifting. We can - * henceforth iterate with current_ext as extent list changes are locked - * out via ilock. - * - * gotp can be null in 2 cases: 1) if there are no extents or 2) - * *next_fsb lies in a hole beyond which there are no extents. Either - * way, we are done. - */ - gotp = xfs_iext_bno_to_ext(ifp, *next_fsb, ¤t_ext); - if (!gotp) { - *done = 1; +done: + if (!xfs_iext_next_extent(ifp, &icur, &got)) { + *done = true; goto del_cursor; } - /* some sanity checking before we finally start shifting extents */ - if ((direction == SHIFT_LEFT && current_ext >= stop_extent) || - (direction == SHIFT_RIGHT && current_ext <= stop_extent)) { - error = -EIO; - goto del_cursor; + *next_fsb = got.br_startoff; +del_cursor: + if (cur) + xfs_btree_del_cursor(cur, error); + if (logflags) + xfs_trans_log_inode(tp, ip, logflags); + return error; +} + +/* Make sure we won't be right-shifting an extent past the maximum bound. */ +int +xfs_bmap_can_insert_extents( + struct xfs_inode *ip, + xfs_fileoff_t off, + xfs_fileoff_t shift) +{ + struct xfs_bmbt_irec got; + int is_empty; + int error = 0; + + xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL); + + if (xfs_is_shutdown(ip->i_mount)) + return -EIO; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + error = xfs_bmap_last_extent(NULL, ip, XFS_DATA_FORK, &got, &is_empty); + if (!error && !is_empty && got.br_startoff >= off && + ((got.br_startoff + shift) & BMBT_STARTOFF_MASK) < got.br_startoff) + error = -EINVAL; + xfs_iunlock(ip, XFS_ILOCK_EXCL); + + return error; +} + +int +xfs_bmap_insert_extents( + struct xfs_trans *tp, + struct xfs_inode *ip, + xfs_fileoff_t *next_fsb, + xfs_fileoff_t offset_shift_fsb, + bool *done, + xfs_fileoff_t stop_fsb) +{ + int whichfork = XFS_DATA_FORK; + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_btree_cur *cur = NULL; + struct xfs_bmbt_irec got, next; + struct xfs_iext_cursor icur; + xfs_fileoff_t new_startoff; + int error = 0; + int logflags = 0; + + if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); + return -EFSCORRUPTED; } - while (nexts++ < num_exts) { - error = xfs_bmse_shift_one(ip, whichfork, offset_shift_fsb, - ¤t_ext, gotp, cur, &logflags, - direction, dfops); - if (error) + if (xfs_is_shutdown(mp)) + return -EIO; + + xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL); + + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; + + if (ifp->if_format == XFS_DINODE_FMT_BTREE) + cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); + + if (*next_fsb == NULLFSBLOCK) { + xfs_iext_last(ifp, &icur); + if (!xfs_iext_get_extent(ifp, &icur, &got) || + stop_fsb > got.br_startoff) { + *done = true; goto del_cursor; - /* - * If there was an extent merge during the shift, the extent - * count can change. Update the total and grade the next record. - */ - if (direction == SHIFT_LEFT) { - total_extents = xfs_iext_count(ifp); - stop_extent = total_extents; } + } else { + if (!xfs_iext_lookup_extent(ip, ifp, *next_fsb, &icur, &got)) { + *done = true; + goto del_cursor; + } + } + if (XFS_IS_CORRUPT(mp, isnullstartblock(got.br_startblock))) { + xfs_bmap_mark_sick(ip, whichfork); + error = -EFSCORRUPTED; + goto del_cursor; + } - if (current_ext == stop_extent) { - *done = 1; - *next_fsb = NULLFSBLOCK; - break; + if (XFS_IS_CORRUPT(mp, stop_fsb > got.br_startoff)) { + xfs_bmap_mark_sick(ip, whichfork); + error = -EFSCORRUPTED; + goto del_cursor; + } + + new_startoff = got.br_startoff + offset_shift_fsb; + if (xfs_iext_peek_next_extent(ifp, &icur, &next)) { + if (new_startoff + got.br_blockcount > next.br_startoff) { + error = -EINVAL; + goto del_cursor; } - gotp = xfs_iext_get_ext(ifp, current_ext); + + /* + * Unlike a left shift (which involves a hole punch), a right + * shift does not modify extent neighbors in any way. We should + * never find mergeable extents in this scenario. Check anyways + * and warn if we encounter two extents that could be one. + */ + if (xfs_bmse_can_merge(ip, whichfork, &got, &next, + offset_shift_fsb)) + WARN_ON_ONCE(1); } - if (!*done) { - xfs_bmbt_get_all(gotp, &got); - *next_fsb = got.br_startoff; + error = xfs_bmap_shift_update_extent(tp, ip, whichfork, &icur, &got, + cur, &logflags, new_startoff); + if (error) + goto del_cursor; + + if (!xfs_iext_prev_extent(ifp, &icur, &got) || + stop_fsb >= got.br_startoff + got.br_blockcount) { + *done = true; + goto del_cursor; } + *next_fsb = got.br_startoff; del_cursor: if (cur) - xfs_btree_del_cursor(cur, - error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); - + xfs_btree_del_cursor(cur, error); if (logflags) xfs_trans_log_inode(tp, ip, logflags); - return error; } /* - * Splits an extent into two extents at split_fsb block such that it is - * the first block of the current_ext. @current_ext is a target extent - * to be split. @split_fsb is a block where the extents is split. - * If split_fsb lies in a hole or the first block of extents, just return 0. + * Splits an extent into two extents at split_fsb block such that it is the + * first block of the current_ext. @ext is a target extent to be split. + * @split_fsb is a block where the extents is split. If split_fsb lies in a + * hole or the first block of extents, just return 0. */ -STATIC int -xfs_bmap_split_extent_at( +int +xfs_bmap_split_extent( struct xfs_trans *tp, struct xfs_inode *ip, - xfs_fileoff_t split_fsb, - xfs_fsblock_t *firstfsb, - struct xfs_defer_ops *dfops) + xfs_fileoff_t split_fsb) { int whichfork = XFS_DATA_FORK; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur = NULL; - struct xfs_bmbt_rec_host *gotp; struct xfs_bmbt_irec got; struct xfs_bmbt_irec new; /* split extent */ struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp; xfs_fsblock_t gotblkcnt; /* new block count for got */ - xfs_extnum_t current_ext; + struct xfs_iext_cursor icur; int error = 0; int logflags = 0; int i = 0; - 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_ERROR_REPORT("xfs_bmap_split_extent_at", - XFS_ERRLEVEL_LOW, mp); + if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) return -EIO; - 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; - } - - /* - * gotp can be null in 2 cases: 1) if there are no extents - * or 2) split_fsb lies in a hole beyond which there are - * no extents. Either way, we are done. - */ - gotp = xfs_iext_bno_to_ext(ifp, split_fsb, ¤t_ext); - if (!gotp) - return 0; - - xfs_bmbt_get_all(gotp, &got); + /* Read in all the extents */ + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; /* - * Check split_fsb lies in a hole or the start boundary offset - * of the extent. + * If there are not extents, or split_fsb lies in a hole we are done. */ - if (got.br_startoff >= split_fsb) + if (!xfs_iext_lookup_extent(ip, ifp, split_fsb, &icur, &got) || + got.br_startoff >= split_fsb) return 0; gotblkcnt = split_fsb - got.br_startoff; @@ -6303,53 +5917,52 @@ xfs_bmap_split_extent_at( new.br_blockcount = got.br_blockcount - gotblkcnt; new.br_state = got.br_state; - if (ifp->if_flags & XFS_IFBROOT) { + if (ifp->if_format == XFS_DINODE_FMT_BTREE) { cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); - cur->bc_private.b.firstblock = *firstfsb; - cur->bc_private.b.dfops = dfops; - cur->bc_private.b.flags = 0; - error = xfs_bmbt_lookup_eq(cur, got.br_startoff, - got.br_startblock, - got.br_blockcount, - &i); + error = xfs_bmbt_lookup_eq(cur, &got, &i); if (error) goto del_cursor; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, del_cursor); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto del_cursor; + } } - xfs_bmbt_set_blockcount(gotp, gotblkcnt); got.br_blockcount = gotblkcnt; + xfs_iext_update_extent(ip, xfs_bmap_fork_to_state(whichfork), &icur, + &got); logflags = XFS_ILOG_CORE; if (cur) { - error = xfs_bmbt_update(cur, got.br_startoff, - got.br_startblock, - got.br_blockcount, - got.br_state); + error = xfs_bmbt_update(cur, &got); if (error) goto del_cursor; } else logflags |= XFS_ILOG_DEXT; /* Add new extent */ - current_ext++; - xfs_iext_insert(ip, current_ext, 1, &new, 0); - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) + 1); + xfs_iext_next(ifp, &icur); + xfs_iext_insert(ip, &icur, &new, 0); + ifp->if_nextents++; if (cur) { - error = xfs_bmbt_lookup_eq(cur, new.br_startoff, - new.br_startblock, new.br_blockcount, - &i); + error = xfs_bmbt_lookup_eq(cur, &new, &i); if (error) goto del_cursor; - XFS_WANT_CORRUPTED_GOTO(mp, i == 0, del_cursor); - cur->bc_rec.b.br_state = new.br_state; - + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto del_cursor; + } error = xfs_btree_insert(cur, &i); if (error) goto del_cursor; - XFS_WANT_CORRUPTED_GOTO(mp, i == 1, del_cursor); + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto del_cursor; + } } /* @@ -6359,16 +5972,15 @@ xfs_bmap_split_extent_at( int tmp_logflags; /* partial log flag return val */ ASSERT(cur == NULL); - error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, dfops, - &cur, 0, &tmp_logflags, whichfork); + error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, + &tmp_logflags, whichfork); logflags |= tmp_logflags; } del_cursor: if (cur) { - cur->bc_private.b.allocated = 0; - xfs_btree_del_cursor(cur, - error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); + cur->bc_bmap.allocated = 0; + xfs_btree_del_cursor(cur, error); } if (logflags) @@ -6376,120 +5988,52 @@ del_cursor: return error; } -int -xfs_bmap_split_extent( - struct xfs_inode *ip, - xfs_fileoff_t split_fsb) -{ - struct xfs_mount *mp = ip->i_mount; - struct xfs_trans *tp; - struct xfs_defer_ops dfops; - xfs_fsblock_t firstfsb; - int 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, XFS_ILOCK_EXCL); - - xfs_defer_init(&dfops, &firstfsb); - - error = xfs_bmap_split_extent_at(tp, ip, split_fsb, - &firstfsb, &dfops); - if (error) - goto out; - - error = xfs_defer_finish(&tp, &dfops, NULL); - if (error) - goto out; - - return xfs_trans_commit(tp); - -out: - xfs_defer_cancel(&dfops); - xfs_trans_cancel(tp); - return error; -} - -/* Deferred mapping is only for real extents in the data fork. */ -static bool -xfs_bmap_is_update_needed( - struct xfs_bmbt_irec *bmap) -{ - return bmap->br_startblock != HOLESTARTBLOCK && - bmap->br_startblock != DELAYSTARTBLOCK; -} - /* Record a bmap intent. */ -static int +static inline void __xfs_bmap_add( - struct xfs_mount *mp, - struct xfs_defer_ops *dfops, + struct xfs_trans *tp, enum xfs_bmap_intent_type type, struct xfs_inode *ip, int whichfork, struct xfs_bmbt_irec *bmap) { - int error; struct xfs_bmap_intent *bi; - trace_xfs_bmap_defer(mp, - XFS_FSB_TO_AGNO(mp, bmap->br_startblock), - type, - XFS_FSB_TO_AGBNO(mp, bmap->br_startblock), - ip->i_ino, whichfork, - bmap->br_startoff, - bmap->br_blockcount, - bmap->br_state); + if ((whichfork != XFS_DATA_FORK && whichfork != XFS_ATTR_FORK) || + bmap->br_startblock == HOLESTARTBLOCK || + bmap->br_startblock == DELAYSTARTBLOCK) + return; - bi = kmem_alloc(sizeof(struct xfs_bmap_intent), KM_SLEEP | KM_NOFS); + bi = kmem_cache_alloc(xfs_bmap_intent_cache, GFP_KERNEL | __GFP_NOFAIL); INIT_LIST_HEAD(&bi->bi_list); bi->bi_type = type; bi->bi_owner = ip; bi->bi_whichfork = whichfork; bi->bi_bmap = *bmap; - error = xfs_defer_join(dfops, bi->bi_owner); - if (error) { - kmem_free(bi); - return error; - } - - xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list); - return 0; + xfs_bmap_defer_add(tp, bi); } /* Map an extent into a file. */ -int +void xfs_bmap_map_extent( - struct xfs_mount *mp, - struct xfs_defer_ops *dfops, + struct xfs_trans *tp, struct xfs_inode *ip, + int whichfork, struct xfs_bmbt_irec *PREV) { - if (!xfs_bmap_is_update_needed(PREV)) - return 0; - - return __xfs_bmap_add(mp, dfops, XFS_BMAP_MAP, ip, - XFS_DATA_FORK, PREV); + __xfs_bmap_add(tp, XFS_BMAP_MAP, ip, whichfork, PREV); } /* Unmap an extent out of a file. */ -int +void xfs_bmap_unmap_extent( - struct xfs_mount *mp, - struct xfs_defer_ops *dfops, + struct xfs_trans *tp, struct xfs_inode *ip, + int whichfork, struct xfs_bmbt_irec *PREV) { - if (!xfs_bmap_is_update_needed(PREV)) - return 0; - - return __xfs_bmap_add(mp, dfops, XFS_BMAP_UNMAP, ip, - XFS_DATA_FORK, PREV); + __xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, whichfork, PREV); } /* @@ -6499,53 +6043,224 @@ xfs_bmap_unmap_extent( int xfs_bmap_finish_one( struct xfs_trans *tp, - struct xfs_defer_ops *dfops, - struct xfs_inode *ip, - enum xfs_bmap_intent_type type, - int whichfork, - xfs_fileoff_t startoff, - xfs_fsblock_t startblock, - xfs_filblks_t *blockcount, - xfs_exntst_t state) + struct xfs_bmap_intent *bi) { - xfs_fsblock_t firstfsb; + struct xfs_bmbt_irec *bmap = &bi->bi_bmap; int error = 0; + int flags = 0; - /* - * firstfsb is tied to the transaction lifetime and is used to - * ensure correct AG locking order and schedule work item - * continuations. XFS_BUI_MAX_FAST_EXTENTS (== 1) restricts us - * to only making one bmap call per transaction, so it should - * be safe to have it as a local variable here. - */ - firstfsb = NULLFSBLOCK; + if (bi->bi_whichfork == XFS_ATTR_FORK) + flags |= XFS_BMAPI_ATTRFORK; - trace_xfs_bmap_deferred(tp->t_mountp, - XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type, - XFS_FSB_TO_AGBNO(tp->t_mountp, startblock), - ip->i_ino, whichfork, startoff, *blockcount, state); + ASSERT(tp->t_highest_agno == NULLAGNUMBER); - if (WARN_ON_ONCE(whichfork != XFS_DATA_FORK)) - return -EFSCORRUPTED; + trace_xfs_bmap_deferred(bi); - if (XFS_TEST_ERROR(false, tp->t_mountp, - XFS_ERRTAG_BMAP_FINISH_ONE)) + if (XFS_TEST_ERROR(tp->t_mountp, XFS_ERRTAG_BMAP_FINISH_ONE)) return -EIO; - switch (type) { + switch (bi->bi_type) { case XFS_BMAP_MAP: - error = xfs_bmapi_remap(tp, ip, startoff, *blockcount, - startblock, dfops); - *blockcount = 0; + if (bi->bi_bmap.br_state == XFS_EXT_UNWRITTEN) + flags |= XFS_BMAPI_PREALLOC; + error = xfs_bmapi_remap(tp, bi->bi_owner, bmap->br_startoff, + bmap->br_blockcount, bmap->br_startblock, + flags); + bmap->br_blockcount = 0; break; case XFS_BMAP_UNMAP: - error = __xfs_bunmapi(tp, ip, startoff, blockcount, - XFS_BMAPI_REMAP, 1, &firstfsb, dfops); + error = __xfs_bunmapi(tp, bi->bi_owner, bmap->br_startoff, + &bmap->br_blockcount, flags | XFS_BMAPI_REMAP, + 1); break; default: ASSERT(0); + xfs_bmap_mark_sick(bi->bi_owner, bi->bi_whichfork); error = -EFSCORRUPTED; } return error; } + +/* Check that an extent does not have invalid flags or bad ranges. */ +xfs_failaddr_t +xfs_bmap_validate_extent_raw( + struct xfs_mount *mp, + bool rtfile, + int whichfork, + struct xfs_bmbt_irec *irec) +{ + if (!xfs_verify_fileext(mp, irec->br_startoff, irec->br_blockcount)) + return __this_address; + + if (rtfile && whichfork == XFS_DATA_FORK) { + if (!xfs_verify_rtbext(mp, irec->br_startblock, + irec->br_blockcount)) + return __this_address; + } else { + if (!xfs_verify_fsbext(mp, irec->br_startblock, + irec->br_blockcount)) + return __this_address; + } + if (irec->br_state != XFS_EXT_NORM && whichfork != XFS_DATA_FORK) + return __this_address; + return NULL; +} + +int __init +xfs_bmap_intent_init_cache(void) +{ + xfs_bmap_intent_cache = kmem_cache_create("xfs_bmap_intent", + sizeof(struct xfs_bmap_intent), + 0, 0, NULL); + + return xfs_bmap_intent_cache != NULL ? 0 : -ENOMEM; +} + +void +xfs_bmap_intent_destroy_cache(void) +{ + kmem_cache_destroy(xfs_bmap_intent_cache); + xfs_bmap_intent_cache = NULL; +} + +/* Check that an inode's extent does not have invalid flags or bad ranges. */ +xfs_failaddr_t +xfs_bmap_validate_extent( + struct xfs_inode *ip, + int whichfork, + struct xfs_bmbt_irec *irec) +{ + return xfs_bmap_validate_extent_raw(ip->i_mount, + XFS_IS_REALTIME_INODE(ip), whichfork, irec); +} + +/* + * Used in xfs_itruncate_extents(). This is the maximum number of extents + * freed from a file in a single transaction. + */ +#define XFS_ITRUNC_MAX_EXTENTS 2 + +/* + * Unmap every extent in part of an inode's fork. We don't do any higher level + * invalidation work at all. + */ +int +xfs_bunmapi_range( + struct xfs_trans **tpp, + struct xfs_inode *ip, + uint32_t flags, + xfs_fileoff_t startoff, + xfs_fileoff_t endoff) +{ + xfs_filblks_t unmap_len = endoff - startoff + 1; + int error = 0; + + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); + + while (unmap_len > 0) { + ASSERT((*tpp)->t_highest_agno == NULLAGNUMBER); + error = __xfs_bunmapi(*tpp, ip, startoff, &unmap_len, flags, + XFS_ITRUNC_MAX_EXTENTS); + if (error) + goto out; + + /* free the just unmapped extents */ + error = xfs_defer_finish(tpp); + if (error) + goto out; + cond_resched(); + } +out: + return error; +} + +struct xfs_bmap_query_range { + xfs_bmap_query_range_fn fn; + void *priv; +}; + +/* Format btree record and pass to our callback. */ +STATIC int +xfs_bmap_query_range_helper( + struct xfs_btree_cur *cur, + const union xfs_btree_rec *rec, + void *priv) +{ + struct xfs_bmap_query_range *query = priv; + struct xfs_bmbt_irec irec; + xfs_failaddr_t fa; + + xfs_bmbt_disk_get_all(&rec->bmbt, &irec); + fa = xfs_bmap_validate_extent(cur->bc_ino.ip, cur->bc_ino.whichfork, + &irec); + if (fa) { + xfs_btree_mark_sick(cur); + return xfs_bmap_complain_bad_rec(cur->bc_ino.ip, + cur->bc_ino.whichfork, fa, &irec); + } + + return query->fn(cur, &irec, query->priv); +} + +/* Find all bmaps. */ +int +xfs_bmap_query_all( + struct xfs_btree_cur *cur, + xfs_bmap_query_range_fn fn, + void *priv) +{ + struct xfs_bmap_query_range query = { + .priv = priv, + .fn = fn, + }; + + return xfs_btree_query_all(cur, xfs_bmap_query_range_helper, &query); +} + +/* Helper function to extract extent size hint from inode */ +xfs_extlen_t +xfs_get_extsz_hint( + struct xfs_inode *ip) +{ + /* + * No point in aligning allocations if we need to COW to actually + * write to them. + */ + if (!xfs_is_always_cow_inode(ip) && + (ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize) + return ip->i_extsize; + if (XFS_IS_REALTIME_INODE(ip) && + ip->i_mount->m_sb.sb_rextsize > 1) + return ip->i_mount->m_sb.sb_rextsize; + return 0; +} + +/* + * Helper function to extract CoW extent size hint from inode. + * Between the extent size hint and the CoW extent size hint, we + * return the greater of the two. If the value is zero (automatic), + * use the default size. + */ +xfs_extlen_t +xfs_get_cowextsz_hint( + struct xfs_inode *ip) +{ + xfs_extlen_t a, b; + + a = 0; + if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) + a = ip->i_cowextsize; + if (XFS_IS_REALTIME_INODE(ip)) { + b = 0; + if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) + b = ip->i_extsize; + } else { + b = xfs_get_extsz_hint(ip); + } + + a = max(a, b); + if (a == 0) + return XFS_DEFAULT_COWEXTSZ_HINT; + return a; +} |