diff options
Diffstat (limited to 'fs/xfs/libxfs')
99 files changed, 23299 insertions, 7430 deletions
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index bb0c700afe3c..e6ba914f6d06 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -30,69 +30,7 @@ #include "xfs_trace.h" #include "xfs_inode.h" #include "xfs_icache.h" - - -/* - * Passive reference counting access wrappers to the perag structures. If the - * per-ag structure is to be freed, the freeing code is responsible for cleaning - * up objects with passive references before freeing the structure. This is - * things like cached buffers. - */ -struct xfs_perag * -xfs_perag_get( - struct xfs_mount *mp, - xfs_agnumber_t agno) -{ - struct xfs_perag *pag; - int ref = 0; - - rcu_read_lock(); - pag = radix_tree_lookup(&mp->m_perag_tree, agno); - if (pag) { - ASSERT(atomic_read(&pag->pag_ref) >= 0); - ref = atomic_inc_return(&pag->pag_ref); - } - rcu_read_unlock(); - trace_xfs_perag_get(mp, agno, ref, _RET_IP_); - return pag; -} - -/* - * search from @first to find the next perag with the given tag set. - */ -struct xfs_perag * -xfs_perag_get_tag( - struct xfs_mount *mp, - xfs_agnumber_t first, - unsigned int tag) -{ - struct xfs_perag *pag; - int found; - int ref; - - rcu_read_lock(); - found = radix_tree_gang_lookup_tag(&mp->m_perag_tree, - (void **)&pag, first, 1, tag); - if (found <= 0) { - rcu_read_unlock(); - return NULL; - } - ref = atomic_inc_return(&pag->pag_ref); - rcu_read_unlock(); - trace_xfs_perag_get_tag(mp, pag->pag_agno, ref, _RET_IP_); - return pag; -} - -void -xfs_perag_put( - struct xfs_perag *pag) -{ - int ref; - - ASSERT(atomic_read(&pag->pag_ref) > 0); - ref = atomic_dec_return(&pag->pag_ref); - trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_); -} +#include "xfs_group.h" /* * xfs_initialize_perag_data @@ -126,7 +64,7 @@ xfs_initialize_perag_data( pag = xfs_perag_get(mp, index); error = xfs_alloc_read_agf(pag, NULL, 0, NULL); if (!error) - error = xfs_ialloc_read_agi(pag, NULL, NULL); + error = xfs_ialloc_read_agi(pag, NULL, 0, NULL); if (error) { xfs_perag_put(pag); return error; @@ -149,6 +87,7 @@ xfs_initialize_perag_data( */ if (fdblocks > sbp->sb_dblocks || ifree > ialloc) { xfs_alert(mp, "AGF corruption. Please run xfs_repair."); + xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS); error = -EFSCORRUPTED; goto out; } @@ -166,38 +105,32 @@ out: return error; } -STATIC void -__xfs_free_perag( - struct rcu_head *head) +static void +xfs_perag_uninit( + struct xfs_group *xg) { - struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head); +#ifdef __KERNEL__ + struct xfs_perag *pag = to_perag(xg); - ASSERT(!delayed_work_pending(&pag->pag_blockgc_work)); - kmem_free(pag); + cancel_delayed_work_sync(&pag->pag_blockgc_work); + xfs_buf_cache_destroy(&pag->pag_bcache); +#endif } /* - * Free up the per-ag resources associated with the mount structure. + * Free up the per-ag resources within the specified AG range. */ void -xfs_free_perag( - struct xfs_mount *mp) +xfs_free_perag_range( + struct xfs_mount *mp, + xfs_agnumber_t first_agno, + xfs_agnumber_t end_agno) + { - struct xfs_perag *pag; xfs_agnumber_t agno; - for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) { - spin_lock(&mp->m_perag_lock); - pag = radix_tree_delete(&mp->m_perag_tree, agno); - spin_unlock(&mp->m_perag_lock); - ASSERT(pag); - XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0); - - cancel_delayed_work_sync(&pag->pag_blockgc_work); - xfs_buf_hash_destroy(pag); - - call_rcu(&pag->rcu_head, __xfs_free_perag); - } + for (agno = first_agno; agno < end_agno; agno++) + xfs_group_free(mp, agno, XG_TYPE_AG, xfs_perag_uninit); } /* Find the size of the AG, in blocks. */ @@ -259,104 +192,101 @@ xfs_agino_range( return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last); } +/* + * Update the perag of the previous tail AG if it has been changed during + * recovery (i.e. recovery of a growfs). + */ int -xfs_initialize_perag( +xfs_update_last_ag_size( struct xfs_mount *mp, + xfs_agnumber_t prev_agcount) +{ + struct xfs_perag *pag = xfs_perag_grab(mp, prev_agcount - 1); + + if (!pag) + return -EFSCORRUPTED; + pag_group(pag)->xg_block_count = __xfs_ag_block_count(mp, + prev_agcount - 1, mp->m_sb.sb_agcount, + mp->m_sb.sb_dblocks); + __xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min, + &pag->agino_max); + xfs_perag_rele(pag); + return 0; +} + +static int +xfs_perag_alloc( + struct xfs_mount *mp, + xfs_agnumber_t index, xfs_agnumber_t agcount, - xfs_rfsblock_t dblocks, - xfs_agnumber_t *maxagi) + xfs_rfsblock_t dblocks) { struct xfs_perag *pag; - xfs_agnumber_t index; - xfs_agnumber_t first_initialised = NULLAGNUMBER; int error; + pag = kzalloc(sizeof(*pag), GFP_KERNEL); + if (!pag) + return -ENOMEM; + +#ifdef __KERNEL__ + /* Place kernel structure only init below this point. */ + spin_lock_init(&pag->pag_ici_lock); + INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker); + INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); +#endif /* __KERNEL__ */ + + error = xfs_buf_cache_init(&pag->pag_bcache); + if (error) + goto out_free_perag; + /* - * Walk the current per-ag tree so we don't try to initialise AGs - * that already exist (growfs case). Allocate and insert all the - * AGs we don't find ready for initialisation. + * Pre-calculated geometry */ - for (index = 0; index < agcount; index++) { - pag = xfs_perag_get(mp, index); - if (pag) { - xfs_perag_put(pag); - continue; - } + pag_group(pag)->xg_block_count = __xfs_ag_block_count(mp, index, agcount, + dblocks); + pag_group(pag)->xg_min_gbno = XFS_AGFL_BLOCK(mp) + 1; + __xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min, + &pag->agino_max); - pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL); - if (!pag) { - error = -ENOMEM; - goto out_unwind_new_pags; - } - pag->pag_agno = index; - pag->pag_mount = mp; + error = xfs_group_insert(mp, pag_group(pag), index, XG_TYPE_AG); + if (error) + goto out_buf_cache_destroy; - error = radix_tree_preload(GFP_NOFS); - if (error) - goto out_free_pag; - - spin_lock(&mp->m_perag_lock); - if (radix_tree_insert(&mp->m_perag_tree, index, pag)) { - WARN_ON_ONCE(1); - spin_unlock(&mp->m_perag_lock); - radix_tree_preload_end(); - error = -EEXIST; - goto out_free_pag; - } - spin_unlock(&mp->m_perag_lock); - radix_tree_preload_end(); + return 0; -#ifdef __KERNEL__ - /* Place kernel structure only init below this point. */ - spin_lock_init(&pag->pag_ici_lock); - spin_lock_init(&pag->pagb_lock); - spin_lock_init(&pag->pag_state_lock); - INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker); - INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); - init_waitqueue_head(&pag->pagb_wait); - pag->pagb_count = 0; - pag->pagb_tree = RB_ROOT; -#endif /* __KERNEL__ */ +out_buf_cache_destroy: + xfs_buf_cache_destroy(&pag->pag_bcache); +out_free_perag: + kfree(pag); + return error; +} - error = xfs_buf_hash_init(pag); - if (error) - goto out_remove_pag; +int +xfs_initialize_perag( + struct xfs_mount *mp, + xfs_agnumber_t orig_agcount, + xfs_agnumber_t new_agcount, + xfs_rfsblock_t dblocks, + xfs_agnumber_t *maxagi) +{ + xfs_agnumber_t index; + int error; - /* first new pag is fully initialized */ - if (first_initialised == NULLAGNUMBER) - first_initialised = index; + if (orig_agcount >= new_agcount) + return 0; - /* - * Pre-calculated geometry - */ - pag->block_count = __xfs_ag_block_count(mp, index, agcount, - dblocks); - pag->min_block = XFS_AGFL_BLOCK(mp); - __xfs_agino_range(mp, pag->block_count, &pag->agino_min, - &pag->agino_max); + for (index = orig_agcount; index < new_agcount; index++) { + error = xfs_perag_alloc(mp, index, new_agcount, dblocks); + if (error) + goto out_unwind_new_pags; } - index = xfs_set_inode_alloc(mp, agcount); - - if (maxagi) - *maxagi = index; - + *maxagi = xfs_set_inode_alloc(mp, new_agcount); mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp); return 0; -out_remove_pag: - radix_tree_delete(&mp->m_perag_tree, index); -out_free_pag: - kmem_free(pag); out_unwind_new_pags: - /* unwind any prior newly initialized pags */ - for (index = first_initialised; index < agcount; index++) { - pag = radix_tree_delete(&mp->m_perag_tree, index); - if (!pag) - break; - xfs_buf_hash_destroy(pag); - kmem_free(pag); - } + xfs_free_perag_range(mp, orig_agcount, index); return error; } @@ -371,7 +301,7 @@ xfs_get_aghdr_buf( struct xfs_buf *bp; int error; - error = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, 0, &bp); + error = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, &bp); if (error) return error; @@ -391,7 +321,7 @@ xfs_btroot_init( struct xfs_buf *bp, struct aghdr_init_data *id) { - xfs_btree_init_block(mp, bp, id->type, 0, 0, id->agno); + xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno); } /* Finish initializing a free space btree. */ @@ -415,10 +345,12 @@ xfs_freesp_init_recs( ASSERT(start >= mp->m_ag_prealloc_blocks); if (start != mp->m_ag_prealloc_blocks) { /* - * Modify first record to pad stripe align of log + * Modify first record to pad stripe align of log and + * bump the record count. */ arec->ar_blockcount = cpu_to_be32(start - mp->m_ag_prealloc_blocks); + be16_add_cpu(&block->bb_numrecs, 1); nrec = arec + 1; /* @@ -429,7 +361,6 @@ xfs_freesp_init_recs( be32_to_cpu(arec->ar_startblock) + be32_to_cpu(arec->ar_blockcount)); arec = nrec; - be16_add_cpu(&block->bb_numrecs, 1); } /* * Change record start to after the internal log @@ -438,19 +369,17 @@ xfs_freesp_init_recs( } /* - * Calculate the record block count and check for the case where - * the log might have consumed all available space in the AG. If - * so, reset the record count to 0 to avoid exposure of an invalid - * record start block. + * Calculate the block count of this record; if it is nonzero, + * increment the record count. */ arec->ar_blockcount = cpu_to_be32(id->agsize - be32_to_cpu(arec->ar_startblock)); - if (!arec->ar_blockcount) - block->bb_numrecs = 0; + if (arec->ar_blockcount) + be16_add_cpu(&block->bb_numrecs, 1); } /* - * Alloc btree root block init functions + * bnobt/cntbt btree root block init functions */ static void xfs_bnoroot_init( @@ -458,17 +387,7 @@ xfs_bnoroot_init( struct xfs_buf *bp, struct aghdr_init_data *id) { - xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno); - xfs_freesp_init_recs(mp, bp, id); -} - -static void -xfs_cntroot_init( - struct xfs_mount *mp, - struct xfs_buf *bp, - struct aghdr_init_data *id) -{ - xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno); + xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno); xfs_freesp_init_recs(mp, bp, id); } @@ -484,7 +403,7 @@ xfs_rmaproot_init( struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_rmap_rec *rrec; - xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno); + xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 4, id->agno); /* * mark the AG header regions as static metadata The BNO @@ -579,14 +498,13 @@ xfs_agfblock_init( agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION); agf->agf_seqno = cpu_to_be32(id->agno); agf->agf_length = cpu_to_be32(id->agsize); - agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp)); - agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp)); - agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1); - agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1); + agf->agf_bno_root = cpu_to_be32(XFS_BNO_BLOCK(mp)); + agf->agf_cnt_root = cpu_to_be32(XFS_CNT_BLOCK(mp)); + agf->agf_bno_level = cpu_to_be32(1); + agf->agf_cnt_level = cpu_to_be32(1); if (xfs_has_rmapbt(mp)) { - agf->agf_roots[XFS_BTNUM_RMAPi] = - cpu_to_be32(XFS_RMAP_BLOCK(mp)); - agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1); + agf->agf_rmap_root = cpu_to_be32(XFS_RMAP_BLOCK(mp)); + agf->agf_rmap_level = cpu_to_be32(1); agf->agf_rmap_blocks = cpu_to_be32(1); } @@ -697,7 +615,7 @@ struct xfs_aghdr_grow_data { size_t numblks; const struct xfs_buf_ops *ops; aghdr_init_work_f work; - xfs_btnum_t type; + const struct xfs_btree_ops *bc_ops; bool need_init; }; @@ -751,13 +669,15 @@ xfs_ag_init_headers( .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_bnobt_buf_ops, .work = &xfs_bnoroot_init, + .bc_ops = &xfs_bnobt_ops, .need_init = true }, { /* CNT root block */ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)), .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_cntbt_buf_ops, - .work = &xfs_cntroot_init, + .work = &xfs_bnoroot_init, + .bc_ops = &xfs_cntbt_ops, .need_init = true }, { /* INO root block */ @@ -765,7 +685,7 @@ xfs_ag_init_headers( .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_inobt_buf_ops, .work = &xfs_btroot_init, - .type = XFS_BTNUM_INO, + .bc_ops = &xfs_inobt_ops, .need_init = true }, { /* FINO root block */ @@ -773,7 +693,7 @@ xfs_ag_init_headers( .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_finobt_buf_ops, .work = &xfs_btroot_init, - .type = XFS_BTNUM_FINO, + .bc_ops = &xfs_finobt_ops, .need_init = xfs_has_finobt(mp) }, { /* RMAP root block */ @@ -781,6 +701,7 @@ xfs_ag_init_headers( .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_rmapbt_buf_ops, .work = &xfs_rmaproot_init, + .bc_ops = &xfs_rmapbt_ops, .need_init = xfs_has_rmapbt(mp) }, { /* REFC root block */ @@ -788,7 +709,7 @@ xfs_ag_init_headers( .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_refcountbt_buf_ops, .work = &xfs_btroot_init, - .type = XFS_BTNUM_REFC, + .bc_ops = &xfs_refcountbt_ops, .need_init = xfs_has_reflink(mp) }, { /* NULL terminating block */ @@ -806,7 +727,7 @@ xfs_ag_init_headers( id->daddr = dp->daddr; id->numblks = dp->numblks; - id->type = dp->type; + id->bc_ops = dp->bc_ops; error = xfs_ag_init_hdr(mp, id, dp->work, dp->ops); if (error) break; @@ -820,11 +741,11 @@ xfs_ag_shrink_space( struct xfs_trans **tpp, xfs_extlen_t delta) { - struct xfs_mount *mp = pag->pag_mount; + struct xfs_mount *mp = pag_mount(pag); struct xfs_alloc_arg args = { .tp = *tpp, .mp = mp, - .type = XFS_ALLOCTYPE_THIS_BNO, + .pag = pag, .minlen = delta, .maxlen = delta, .oinfo = XFS_RMAP_OINFO_SKIP_UPDATE, @@ -837,8 +758,8 @@ xfs_ag_shrink_space( xfs_agblock_t aglen; int error, err2; - ASSERT(pag->pag_agno == mp->m_sb.sb_agcount - 1); - error = xfs_ialloc_read_agi(pag, *tpp, &agibp); + ASSERT(pag_agno(pag) == mp->m_sb.sb_agcount - 1); + error = xfs_ialloc_read_agi(pag, *tpp, 0, &agibp); if (error) return error; @@ -851,19 +772,18 @@ xfs_ag_shrink_space( agf = agfbp->b_addr; aglen = be32_to_cpu(agi->agi_length); /* some extra paranoid checks before we shrink the ag */ - if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length)) + if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length)) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF); return -EFSCORRUPTED; + } if (delta >= aglen) return -EINVAL; - args.fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, aglen - delta); - /* * Make sure that the last inode cluster cannot overlap with the new * end of the AG, even if it's sparse. */ - error = xfs_ialloc_check_shrink(*tpp, pag->pag_agno, agibp, - aglen - delta); + error = xfs_ialloc_check_shrink(pag, *tpp, agibp, aglen - delta); if (error) return error; @@ -871,25 +791,33 @@ xfs_ag_shrink_space( * Disable perag reservations so it doesn't cause the allocation request * to fail. We'll reestablish reservation before we return. */ - error = xfs_ag_resv_free(pag); - if (error) - return error; + xfs_ag_resv_free(pag); /* internal log shouldn't also show up in the free space btrees */ - error = xfs_alloc_vextent(&args); + error = xfs_alloc_vextent_exact_bno(&args, + xfs_agbno_to_fsb(pag, aglen - delta)); if (!error && args.agbno == NULLAGBLOCK) error = -ENOSPC; if (error) { /* - * if extent allocation fails, need to roll the transaction to + * If extent allocation fails, need to roll the transaction to * ensure that the AGFL fixup has been committed anyway. + * + * We need to hold the AGF across the roll to ensure nothing can + * access the AG for allocation until the shrink is fully + * cleaned up. And due to the resetting of the AG block + * reservation space needing to lock the AGI, we also have to + * hold that so we don't get AGI/AGF lock order inversions in + * the error handling path. */ xfs_trans_bhold(*tpp, agfbp); + xfs_trans_bhold(*tpp, agibp); err2 = xfs_trans_roll(tpp); if (err2) return err2; xfs_trans_bjoin(*tpp, agfbp); + xfs_trans_bjoin(*tpp, agibp); goto resv_init_out; } @@ -907,7 +835,10 @@ xfs_ag_shrink_space( if (err2 != -ENOSPC) goto resv_err; - __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, true); + err2 = xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, + XFS_AG_RESV_NONE, XFS_FREE_EXTENT_SKIP_DISCARD); + if (err2) + goto resv_err; /* * Roll the transaction before trying to re-init the per-ag @@ -921,6 +852,12 @@ xfs_ag_shrink_space( error = -ENOSPC; goto resv_init_out; } + + /* Update perag geometry */ + pag_group(pag)->xg_block_count -= delta; + __xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min, + &pag->agino_max); + xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH); xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH); return 0; @@ -944,14 +881,15 @@ xfs_ag_extend_space( struct xfs_trans *tp, xfs_extlen_t len) { + struct xfs_mount *mp = pag_mount(pag); struct xfs_buf *bp; struct xfs_agi *agi; struct xfs_agf *agf; int error; - ASSERT(pag->pag_agno == pag->pag_mount->m_sb.sb_agcount - 1); + ASSERT(pag_agno(pag) == mp->m_sb.sb_agcount - 1); - error = xfs_ialloc_read_agi(pag, tp, &bp); + error = xfs_ialloc_read_agi(pag, tp, 0, &bp); if (error) return error; @@ -982,17 +920,15 @@ xfs_ag_extend_space( if (error) return error; - error = xfs_free_extent(tp, XFS_AGB_TO_FSB(pag->pag_mount, pag->pag_agno, - be32_to_cpu(agf->agf_length) - len), - len, &XFS_RMAP_OINFO_SKIP_UPDATE, - XFS_AG_RESV_NONE); + error = xfs_free_extent(tp, pag, be32_to_cpu(agf->agf_length) - len, + len, &XFS_RMAP_OINFO_SKIP_UPDATE, XFS_AG_RESV_NONE); if (error) return error; /* Update perag geometry */ - pag->block_count = be32_to_cpu(agf->agf_length); - __xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min, - &pag->agino_max); + pag_group(pag)->xg_block_count = be32_to_cpu(agf->agf_length); + __xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min, + &pag->agino_max); return 0; } @@ -1010,7 +946,7 @@ xfs_ag_get_geometry( int error; /* Lock the AG headers. */ - error = xfs_ialloc_read_agi(pag, NULL, &agi_bp); + error = xfs_ialloc_read_agi(pag, NULL, 0, &agi_bp); if (error) return error; error = xfs_alloc_read_agf(pag, NULL, 0, &agf_bp); @@ -1019,7 +955,7 @@ xfs_ag_get_geometry( /* Fill out form. */ memset(ageo, 0, sizeof(*ageo)); - ageo->ag_number = pag->pag_agno; + ageo->ag_number = pag_agno(pag); agi = agi_bp->b_addr; ageo->ag_icount = be32_to_cpu(agi->agi_count); diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index 191b22b9a35b..1f24cfa27321 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -7,6 +7,8 @@ #ifndef __LIBXFS_AG_H #define __LIBXFS_AG_H 1 +#include "xfs_group.h" + struct xfs_mount; struct xfs_trans; struct xfs_perag; @@ -30,16 +32,11 @@ struct xfs_ag_resv { * performance of allocation group selection. */ struct xfs_perag { - struct xfs_mount *pag_mount; /* owner filesystem */ - xfs_agnumber_t pag_agno; /* AG this structure belongs to */ - atomic_t pag_ref; /* perag reference count */ - char pagf_init; /* this agf's entry is initialized */ - char pagi_init; /* this agi's entry is initialized */ - char pagf_metadata; /* the agf is preferred to be metadata */ - char pagi_inodeok; /* The agi is ok for inodes */ - uint8_t pagf_levels[XFS_BTNUM_AGF]; - /* # of levels in bno & cnt btree */ - bool pagf_agflreset; /* agfl requires reset before use */ + struct xfs_group pag_group; + unsigned long pag_opstate; + uint8_t pagf_bno_level; /* # of levels in bno btree */ + uint8_t pagf_cnt_level; /* # of levels in cnt btree */ + uint8_t pagf_rmap_level;/* # of levels in rmap btree */ uint32_t pagf_flcount; /* count of blocks in freelist */ xfs_extlen_t pagf_freeblks; /* total free blocks */ xfs_extlen_t pagf_longest; /* longest free space */ @@ -56,7 +53,6 @@ struct xfs_perag { xfs_agino_t pagl_leftrec; xfs_agino_t pagl_rightrec; - int pagb_count; /* pagb slots in use */ uint8_t pagf_refcount_level; /* recount btree height */ /* Blocks reserved for all kinds of metadata. */ @@ -64,30 +60,23 @@ struct xfs_perag { /* Blocks reserved for the reverse mapping btree. */ struct xfs_ag_resv pag_rmapbt_resv; - /* for rcu-safe freeing */ - struct rcu_head rcu_head; - /* Precalculated geometry info */ - xfs_agblock_t block_count; - xfs_agblock_t min_block; xfs_agino_t agino_min; xfs_agino_t agino_max; #ifdef __KERNEL__ /* -- kernel only structures below this line -- */ +#ifdef CONFIG_XFS_ONLINE_REPAIR /* - * Bitsets of per-ag metadata that have been checked and/or are sick. - * Callers should hold pag_state_lock before accessing this field. + * Alternate btree heights so that online repair won't trip the write + * verifiers while rebuilding the AG btrees. */ - uint16_t pag_checked; - uint16_t pag_sick; - spinlock_t pag_state_lock; - - spinlock_t pagb_lock; /* lock for pagb_tree */ - struct rb_root pagb_tree; /* ordered tree of busy extents */ - unsigned int pagb_gen; /* generation count for pagb_tree */ - wait_queue_head_t pagb_wait; /* woken when pagb_gen changes */ + uint8_t pagf_repair_bno_level; + uint8_t pagf_repair_cnt_level; + uint8_t pagf_repair_refcount_level; + uint8_t pagf_repair_rmap_level; +#endif atomic_t pagf_fstrms; /* # of filestreams active in this AG */ @@ -96,25 +85,128 @@ struct xfs_perag { int pag_ici_reclaimable; /* reclaimable inodes */ unsigned long pag_ici_reclaim_cursor; /* reclaim restart point */ - /* buffer cache index */ - spinlock_t pag_buf_lock; /* lock for pag_buf_hash */ - struct rhashtable pag_buf_hash; + struct xfs_buf_cache pag_bcache; /* background prealloc block trimming */ struct delayed_work pag_blockgc_work; - #endif /* __KERNEL__ */ }; -int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount, - xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi); +static inline struct xfs_perag *to_perag(struct xfs_group *xg) +{ + return container_of(xg, struct xfs_perag, pag_group); +} + +static inline struct xfs_group *pag_group(struct xfs_perag *pag) +{ + return &pag->pag_group; +} + +static inline struct xfs_mount *pag_mount(const struct xfs_perag *pag) +{ + return pag->pag_group.xg_mount; +} + +static inline xfs_agnumber_t pag_agno(const struct xfs_perag *pag) +{ + return pag->pag_group.xg_gno; +} + +/* + * Per-AG operational state. These are atomic flag bits. + */ +#define XFS_AGSTATE_AGF_INIT 0 +#define XFS_AGSTATE_AGI_INIT 1 +#define XFS_AGSTATE_PREFERS_METADATA 2 +#define XFS_AGSTATE_ALLOWS_INODES 3 +#define XFS_AGSTATE_AGFL_NEEDS_RESET 4 + +#define __XFS_AG_OPSTATE(name, NAME) \ +static inline bool xfs_perag_ ## name (struct xfs_perag *pag) \ +{ \ + return test_bit(XFS_AGSTATE_ ## NAME, &pag->pag_opstate); \ +} + +__XFS_AG_OPSTATE(initialised_agf, AGF_INIT) +__XFS_AG_OPSTATE(initialised_agi, AGI_INIT) +__XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA) +__XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES) +__XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET) + +int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t orig_agcount, + xfs_agnumber_t new_agcount, xfs_rfsblock_t dcount, + xfs_agnumber_t *maxagi); +void xfs_free_perag_range(struct xfs_mount *mp, xfs_agnumber_t first_agno, + xfs_agnumber_t end_agno); int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno); -void xfs_free_perag(struct xfs_mount *mp); +int xfs_update_last_ag_size(struct xfs_mount *mp, xfs_agnumber_t prev_agcount); + +/* Passive AG references */ +static inline struct xfs_perag * +xfs_perag_get( + struct xfs_mount *mp, + xfs_agnumber_t agno) +{ + return to_perag(xfs_group_get(mp, agno, XG_TYPE_AG)); +} + +static inline struct xfs_perag * +xfs_perag_hold( + struct xfs_perag *pag) +{ + return to_perag(xfs_group_hold(pag_group(pag))); +} + +static inline void +xfs_perag_put( + struct xfs_perag *pag) +{ + xfs_group_put(pag_group(pag)); +} + +/* Active AG references */ +static inline struct xfs_perag * +xfs_perag_grab( + struct xfs_mount *mp, + xfs_agnumber_t agno) +{ + return to_perag(xfs_group_grab(mp, agno, XG_TYPE_AG)); +} + +static inline void +xfs_perag_rele( + struct xfs_perag *pag) +{ + xfs_group_rele(pag_group(pag)); +} + +static inline struct xfs_perag * +xfs_perag_next_range( + struct xfs_mount *mp, + struct xfs_perag *pag, + xfs_agnumber_t start_agno, + xfs_agnumber_t end_agno) +{ + return to_perag(xfs_group_next_range(mp, pag ? pag_group(pag) : NULL, + start_agno, end_agno, XG_TYPE_AG)); +} -struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno); -struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *mp, xfs_agnumber_t agno, - unsigned int tag); -void xfs_perag_put(struct xfs_perag *pag); +static inline struct xfs_perag * +xfs_perag_next_from( + struct xfs_mount *mp, + struct xfs_perag *pag, + xfs_agnumber_t start_agno) +{ + return xfs_perag_next_range(mp, pag, start_agno, mp->m_sb.sb_agcount - 1); +} + +static inline struct xfs_perag * +xfs_perag_next( + struct xfs_mount *mp, + struct xfs_perag *pag) +{ + return xfs_perag_next_from(mp, pag, 0); +} /* * Per-ag geometry infomation and validation @@ -126,11 +218,7 @@ void xfs_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno, static inline bool xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno) { - if (agbno >= pag->block_count) - return false; - if (agbno <= pag->min_block) - return false; - return true; + return xfs_verify_gbno(pag_group(pag), agbno); } static inline bool @@ -139,13 +227,7 @@ xfs_verify_agbext( xfs_agblock_t agbno, xfs_agblock_t len) { - if (agbno + len <= agbno) - return false; - - if (!xfs_verify_agbno(pag, agbno)) - return false; - - return xfs_verify_agbno(pag, agbno + len - 1); + return xfs_verify_gbext(pag_group(pag), agbno, len); } /* @@ -181,43 +263,57 @@ xfs_ag_contains_log(struct xfs_mount *mp, xfs_agnumber_t agno) agno == XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart); } -/* - * Perag iteration APIs - */ static inline struct xfs_perag * -xfs_perag_next( +xfs_perag_next_wrap( struct xfs_perag *pag, xfs_agnumber_t *agno, - xfs_agnumber_t end_agno) + xfs_agnumber_t stop_agno, + xfs_agnumber_t restart_agno, + xfs_agnumber_t wrap_agno) { - struct xfs_mount *mp = pag->pag_mount; - - *agno = pag->pag_agno + 1; - xfs_perag_put(pag); - if (*agno > end_agno) - return NULL; - return xfs_perag_get(mp, *agno); + struct xfs_mount *mp = pag_mount(pag); + + *agno = pag_agno(pag) + 1; + xfs_perag_rele(pag); + while (*agno != stop_agno) { + if (*agno >= wrap_agno) { + if (restart_agno >= stop_agno) + break; + *agno = restart_agno; + } + + pag = xfs_perag_grab(mp, *agno); + if (pag) + return pag; + (*agno)++; + } + return NULL; } -#define for_each_perag_range(mp, agno, end_agno, pag) \ - for ((pag) = xfs_perag_get((mp), (agno)); \ +/* + * Iterate all AGs from start_agno through wrap_agno, then restart_agno through + * (start_agno - 1). + */ +#define for_each_perag_wrap_range(mp, start_agno, restart_agno, wrap_agno, agno, pag) \ + for ((agno) = (start_agno), (pag) = xfs_perag_grab((mp), (agno)); \ (pag) != NULL; \ - (pag) = xfs_perag_next((pag), &(agno), (end_agno))) - -#define for_each_perag_from(mp, agno, pag) \ - for_each_perag_range((mp), (agno), (mp)->m_sb.sb_agcount - 1, (pag)) - + (pag) = xfs_perag_next_wrap((pag), &(agno), (start_agno), \ + (restart_agno), (wrap_agno))) +/* + * Iterate all AGs from start_agno through wrap_agno, then 0 through + * (start_agno - 1). + */ +#define for_each_perag_wrap_at(mp, start_agno, wrap_agno, agno, pag) \ + for_each_perag_wrap_range((mp), (start_agno), 0, (wrap_agno), (agno), (pag)) -#define for_each_perag(mp, agno, pag) \ - (agno) = 0; \ - for_each_perag_from((mp), (agno), (pag)) +/* + * Iterate all AGs from start_agno through to the end of the filesystem, then 0 + * through (start_agno - 1). + */ +#define for_each_perag_wrap(mp, start_agno, agno, pag) \ + for_each_perag_wrap_at((mp), (start_agno), (mp)->m_sb.sb_agcount, \ + (agno), (pag)) -#define for_each_perag_tag(mp, agno, pag, tag) \ - for ((agno) = 0, (pag) = xfs_perag_get_tag((mp), 0, (tag)); \ - (pag) != NULL; \ - (agno) = (pag)->pag_agno + 1, \ - xfs_perag_put(pag), \ - (pag) = xfs_perag_get_tag((mp), (agno), (tag))) struct aghdr_init_data { /* per ag data */ @@ -229,7 +325,7 @@ struct aghdr_init_data { /* per header data */ xfs_daddr_t daddr; /* header location */ size_t numblks; /* size of header */ - xfs_btnum_t type; /* type of btree root block */ + const struct xfs_btree_ops *bc_ops; /* btree ops */ }; int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id); @@ -239,4 +335,28 @@ int xfs_ag_extend_space(struct xfs_perag *pag, struct xfs_trans *tp, xfs_extlen_t len); int xfs_ag_get_geometry(struct xfs_perag *pag, struct xfs_ag_geometry *ageo); +static inline xfs_fsblock_t +xfs_agbno_to_fsb( + struct xfs_perag *pag, + xfs_agblock_t agbno) +{ + return XFS_AGB_TO_FSB(pag_mount(pag), pag_agno(pag), agbno); +} + +static inline xfs_daddr_t +xfs_agbno_to_daddr( + struct xfs_perag *pag, + xfs_agblock_t agbno) +{ + return XFS_AGB_TO_DADDR(pag_mount(pag), pag_agno(pag), agbno); +} + +static inline xfs_ino_t +xfs_agino_to_ino( + struct xfs_perag *pag, + xfs_agino_t agino) +{ + return XFS_AGINO_TO_INO(pag_mount(pag), pag_agno(pag), agino); +} + #endif /* __LIBXFS_AG_H */ diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index 5af123d13a63..8ac8230c3d3c 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -70,6 +70,7 @@ xfs_ag_resv_critical( struct xfs_perag *pag, enum xfs_ag_resv_type type) { + struct xfs_mount *mp = pag_mount(pag); xfs_extlen_t avail; xfs_extlen_t orig; @@ -91,9 +92,8 @@ xfs_ag_resv_critical( trace_xfs_ag_resv_critical(pag, type, avail); /* Critically low if less than 10% or max btree height remains. */ - return XFS_TEST_ERROR(avail < orig / 10 || - avail < pag->pag_mount->m_agbtree_maxlevels, - pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL); + return avail < orig / 10 || avail < mp->m_agbtree_maxlevels || + XFS_TEST_ERROR(mp, XFS_ERRTAG_AG_RESV_CRITICAL); } /* @@ -113,6 +113,7 @@ xfs_ag_resv_needed( case XFS_AG_RESV_RMAPBT: len -= xfs_perag_resv(pag, type)->ar_reserved; break; + case XFS_AG_RESV_METAFILE: case XFS_AG_RESV_NONE: /* empty */ break; @@ -126,20 +127,19 @@ xfs_ag_resv_needed( } /* Clean out a reservation */ -static int +static void __xfs_ag_resv_free( struct xfs_perag *pag, enum xfs_ag_resv_type type) { struct xfs_ag_resv *resv; xfs_extlen_t oldresv; - int error; trace_xfs_ag_resv_free(pag, type, 0); resv = xfs_perag_resv(pag, type); - if (pag->pag_agno == 0) - pag->pag_mount->m_ag_max_usable += resv->ar_asked; + if (pag_agno(pag) == 0) + pag_mount(pag)->m_ag_max_usable += resv->ar_asked; /* * RMAPBT blocks come from the AGFL and AGFL blocks are always * considered "free", so whatever was reserved at mount time must be @@ -149,30 +149,19 @@ __xfs_ag_resv_free( oldresv = resv->ar_orig_reserved; else oldresv = resv->ar_reserved; - error = xfs_mod_fdblocks(pag->pag_mount, oldresv, true); + xfs_add_fdblocks(pag_mount(pag), oldresv); resv->ar_reserved = 0; resv->ar_asked = 0; resv->ar_orig_reserved = 0; - - if (error) - trace_xfs_ag_resv_free_error(pag->pag_mount, pag->pag_agno, - error, _RET_IP_); - return error; } /* Free a per-AG reservation. */ -int +void xfs_ag_resv_free( struct xfs_perag *pag) { - int error; - int err2; - - error = __xfs_ag_resv_free(pag, XFS_AG_RESV_RMAPBT); - err2 = __xfs_ag_resv_free(pag, XFS_AG_RESV_METADATA); - if (err2 && !error) - error = err2; - return error; + __xfs_ag_resv_free(pag, XFS_AG_RESV_RMAPBT); + __xfs_ag_resv_free(pag, XFS_AG_RESV_METADATA); } static int @@ -182,7 +171,7 @@ __xfs_ag_resv_init( xfs_extlen_t ask, xfs_extlen_t used) { - struct xfs_mount *mp = pag->pag_mount; + struct xfs_mount *mp = pag_mount(pag); struct xfs_ag_resv *resv; int error; xfs_extlen_t hidden_space; @@ -213,16 +202,15 @@ __xfs_ag_resv_init( return -EINVAL; } - if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_AG_RESV_FAIL)) + if (XFS_TEST_ERROR(mp, XFS_ERRTAG_AG_RESV_FAIL)) error = -ENOSPC; else - error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true); + error = xfs_dec_fdblocks(mp, hidden_space, true); if (error) { - trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno, - error, _RET_IP_); + trace_xfs_ag_resv_init_error(pag, error, _RET_IP_); xfs_warn(mp, "Per-AG reservation for AG %u failed. Filesystem may run out of space.", - pag->pag_agno); + pag_agno(pag)); return error; } @@ -232,7 +220,7 @@ __xfs_ag_resv_init( * counter, we only make the adjustment for AG 0. This assumes that * there aren't any AGs hungrier for per-AG reservation than AG 0. */ - if (pag->pag_agno == 0) + if (pag_agno(pag) == 0) mp->m_ag_max_usable -= ask; resv = xfs_perag_resv(pag, type); @@ -250,7 +238,7 @@ xfs_ag_resv_init( struct xfs_perag *pag, struct xfs_trans *tp) { - struct xfs_mount *mp = pag->pag_mount; + struct xfs_mount *mp = pag_mount(pag); xfs_extlen_t ask; xfs_extlen_t used; int error = 0, error2; @@ -264,7 +252,7 @@ xfs_ag_resv_init( if (error) goto out; - error = xfs_finobt_calc_reserves(mp, tp, pag, &ask, &used); + error = xfs_finobt_calc_reserves(pag, tp, &ask, &used); if (error) goto out; @@ -359,6 +347,7 @@ xfs_ag_resv_alloc_extent( switch (type) { case XFS_AG_RESV_AGFL: + case XFS_AG_RESV_METAFILE: return; case XFS_AG_RESV_METADATA: case XFS_AG_RESV_RMAPBT: @@ -401,6 +390,7 @@ xfs_ag_resv_free_extent( switch (type) { case XFS_AG_RESV_AGFL: + case XFS_AG_RESV_METAFILE: return; case XFS_AG_RESV_METADATA: case XFS_AG_RESV_RMAPBT: @@ -411,6 +401,8 @@ xfs_ag_resv_free_extent( fallthrough; case XFS_AG_RESV_NONE: xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, (int64_t)len); + fallthrough; + case XFS_AG_RESV_IGNORE: return; } diff --git a/fs/xfs/libxfs/xfs_ag_resv.h b/fs/xfs/libxfs/xfs_ag_resv.h index b74b210008ea..f247eeff7358 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.h +++ b/fs/xfs/libxfs/xfs_ag_resv.h @@ -6,7 +6,7 @@ #ifndef __XFS_AG_RESV_H__ #define __XFS_AG_RESV_H__ -int xfs_ag_resv_free(struct xfs_perag *pag); +void xfs_ag_resv_free(struct xfs_perag *pag); int xfs_ag_resv_init(struct xfs_perag *pag, struct xfs_trans *tp); bool xfs_ag_resv_critical(struct xfs_perag *pag, enum xfs_ag_resv_type type); @@ -33,23 +33,4 @@ xfs_perag_resv( } } -/* - * RMAPBT reservation accounting wrappers. Since rmapbt blocks are sourced from - * the AGFL, they are allocated one at a time and the reservation updates don't - * require a transaction. - */ -static inline void -xfs_ag_resv_rmapbt_alloc( - struct xfs_mount *mp, - xfs_agnumber_t agno) -{ - struct xfs_alloc_arg args = { NULL }; - struct xfs_perag *pag; - - args.len = 1; - pag = xfs_perag_get(mp, agno); - xfs_ag_resv_alloc_extent(pag, XFS_AG_RESV_RMAPBT, &args); - xfs_perag_put(pag); -} - #endif /* __XFS_AG_RESV_H__ */ diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 989cf341779b..ad381c73abc4 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -26,20 +26,16 @@ #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_bmap.h" +#include "xfs_health.h" +#include "xfs_extfree_item.h" struct kmem_cache *xfs_extfree_item_cache; struct workqueue_struct *xfs_alloc_wq; -#define XFS_ABSDIFF(a,b) (((a) <= (b)) ? ((b) - (a)) : ((a) - (b))) - #define XFSA_FIXUP_BNO_OK 1 #define XFSA_FIXUP_CNT_OK 2 -STATIC int xfs_alloc_ag_vextent_exact(xfs_alloc_arg_t *); -STATIC int xfs_alloc_ag_vextent_near(xfs_alloc_arg_t *); -STATIC int xfs_alloc_ag_vextent_size(xfs_alloc_arg_t *); - /* * Size of the AGFL. For CRC-enabled filesystes we steal a couple of slots in * the beginning of the block for a proper header with the location information @@ -82,7 +78,7 @@ xfs_prealloc_blocks( } /* - * The number of blocks per AG that we withhold from xfs_mod_fdblocks to + * The number of blocks per AG that we withhold from xfs_dec_fdblocks to * guarantee that we can refill the AGFL prior to allocating space in a nearly * full AG. Although the space described by the free space btrees, the * blocks used by the freesp btrees themselves, and the blocks owned by the @@ -92,7 +88,7 @@ xfs_prealloc_blocks( * until the fs goes down, we subtract this many AG blocks from the incore * fdblocks to ensure user allocation does not overcommit the space the * filesystem needs for the AGFLs. The rmap btree uses a per-AG reservation to - * withhold space from xfs_mod_fdblocks, so we do not account for that here. + * withhold space from xfs_dec_fdblocks, so we do not account for that here. */ #define XFS_ALLOCBT_AGFL_RESERVE 4 @@ -154,23 +150,38 @@ xfs_alloc_ag_max_usable( return mp->m_sb.sb_agblocks - blocks; } + +static int +xfs_alloc_lookup( + struct xfs_btree_cur *cur, + xfs_lookup_t dir, + xfs_agblock_t bno, + xfs_extlen_t len, + int *stat) +{ + int error; + + cur->bc_rec.a.ar_startblock = bno; + cur->bc_rec.a.ar_blockcount = len; + error = xfs_btree_lookup(cur, dir, stat); + if (*stat == 1) + cur->bc_flags |= XFS_BTREE_ALLOCBT_ACTIVE; + else + cur->bc_flags &= ~XFS_BTREE_ALLOCBT_ACTIVE; + return error; +} + /* * Lookup the record equal to [bno, len] in the btree given by cur. */ -STATIC int /* error */ +static inline int /* error */ xfs_alloc_lookup_eq( struct xfs_btree_cur *cur, /* btree cursor */ xfs_agblock_t bno, /* starting block of extent */ xfs_extlen_t len, /* length of extent */ int *stat) /* success/failure */ { - int error; - - cur->bc_rec.a.ar_startblock = bno; - cur->bc_rec.a.ar_blockcount = len; - error = xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat); - cur->bc_ag.abt.active = (*stat == 1); - return error; + return xfs_alloc_lookup(cur, XFS_LOOKUP_EQ, bno, len, stat); } /* @@ -184,13 +195,7 @@ xfs_alloc_lookup_ge( xfs_extlen_t len, /* length of extent */ int *stat) /* success/failure */ { - int error; - - cur->bc_rec.a.ar_startblock = bno; - cur->bc_rec.a.ar_blockcount = len; - error = xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat); - cur->bc_ag.abt.active = (*stat == 1); - return error; + return xfs_alloc_lookup(cur, XFS_LOOKUP_GE, bno, len, stat); } /* @@ -204,19 +209,14 @@ xfs_alloc_lookup_le( xfs_extlen_t len, /* length of extent */ int *stat) /* success/failure */ { - int error; - cur->bc_rec.a.ar_startblock = bno; - cur->bc_rec.a.ar_blockcount = len; - error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat); - cur->bc_ag.abt.active = (*stat == 1); - return error; + return xfs_alloc_lookup(cur, XFS_LOOKUP_LE, bno, len, stat); } static inline bool xfs_alloc_cur_active( struct xfs_btree_cur *cur) { - return cur && cur->bc_ag.abt.active; + return cur && (cur->bc_flags & XFS_BTREE_ALLOCBT_ACTIVE); } /* @@ -237,6 +237,50 @@ xfs_alloc_update( return xfs_btree_update(cur, &rec); } +/* Convert the ondisk btree record to its incore representation. */ +void +xfs_alloc_btrec_to_irec( + const union xfs_btree_rec *rec, + struct xfs_alloc_rec_incore *irec) +{ + irec->ar_startblock = be32_to_cpu(rec->alloc.ar_startblock); + irec->ar_blockcount = be32_to_cpu(rec->alloc.ar_blockcount); +} + +/* Simple checks for free space records. */ +xfs_failaddr_t +xfs_alloc_check_irec( + struct xfs_perag *pag, + const struct xfs_alloc_rec_incore *irec) +{ + if (irec->ar_blockcount == 0) + return __this_address; + + /* check for valid extent range, including overflow */ + if (!xfs_verify_agbext(pag, irec->ar_startblock, irec->ar_blockcount)) + return __this_address; + + return NULL; +} + +static inline int +xfs_alloc_complain_bad_rec( + struct xfs_btree_cur *cur, + xfs_failaddr_t fa, + const struct xfs_alloc_rec_incore *irec) +{ + struct xfs_mount *mp = cur->bc_mp; + + xfs_warn(mp, + "%sbt record corruption in AG %d detected at %pS!", + cur->bc_ops->name, cur->bc_group->xg_gno, fa); + xfs_warn(mp, + "start block 0x%x block count 0x%x", irec->ar_startblock, + irec->ar_blockcount); + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; +} + /* * Get the data from the pointed-to record. */ @@ -247,35 +291,23 @@ xfs_alloc_get_rec( xfs_extlen_t *len, /* output: length of extent */ int *stat) /* output: success/failure */ { - struct xfs_mount *mp = cur->bc_mp; - struct xfs_perag *pag = cur->bc_ag.pag; + struct xfs_alloc_rec_incore irec; union xfs_btree_rec *rec; + xfs_failaddr_t fa; int error; error = xfs_btree_get_rec(cur, &rec, stat); if (error || !(*stat)) return error; - *bno = be32_to_cpu(rec->alloc.ar_startblock); - *len = be32_to_cpu(rec->alloc.ar_blockcount); - - if (*len == 0) - goto out_bad_rec; - - /* check for valid extent range, including overflow */ - if (!xfs_verify_agbext(pag, *bno, *len)) - goto out_bad_rec; + xfs_alloc_btrec_to_irec(rec, &irec); + fa = xfs_alloc_check_irec(to_perag(cur->bc_group), &irec); + if (fa) + return xfs_alloc_complain_bad_rec(cur, fa, &irec); + *bno = irec.ar_startblock; + *len = irec.ar_blockcount; return 0; - -out_bad_rec: - xfs_warn(mp, - "%s Freespace BTree record corruption in AG %d detected!", - cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size", - pag->pag_agno); - xfs_warn(mp, - "start block 0x%x block count 0x%x", *bno, *len); - return -EFSCORRUPTED; } /* @@ -297,7 +329,8 @@ xfs_alloc_compute_aligned( bool busy; /* Trim busy sections out of found extent */ - busy = xfs_extent_busy_trim(args, &bno, &len, busy_gen); + busy = xfs_extent_busy_trim(pag_group(args->pag), args->minlen, + args->maxlen, &bno, &len, busy_gen); /* * If we have a largish extent that happens to start before min_agbno, @@ -375,8 +408,8 @@ xfs_alloc_compute_diff( if (newbno1 != NULLAGBLOCK && newbno2 != NULLAGBLOCK) { if (newlen1 < newlen2 || (newlen1 == newlen2 && - XFS_ABSDIFF(newbno1, wantbno) > - XFS_ABSDIFF(newbno2, wantbno))) + abs_diff(newbno1, wantbno) > + abs_diff(newbno2, wantbno))) newbno1 = newbno2; } else if (newbno2 != NULLAGBLOCK) newbno1 = newbno2; @@ -392,7 +425,7 @@ xfs_alloc_compute_diff( } else newbno1 = freeend - wantlen; *newbnop = newbno1; - return newbno1 == NULLAGBLOCK ? 0 : XFS_ABSDIFF(newbno1, wantbno); + return newbno1 == NULLAGBLOCK ? 0 : abs_diff(newbno1, wantbno); } /* @@ -433,6 +466,97 @@ xfs_alloc_fix_len( } /* + * Determine if the cursor points to the block that contains the right-most + * block of records in the by-count btree. This block contains the largest + * contiguous free extent in the AG, so if we modify a record in this block we + * need to call xfs_alloc_fixup_longest() once the modifications are done to + * ensure the agf->agf_longest field is kept up to date with the longest free + * extent tracked by the by-count btree. + */ +static bool +xfs_alloc_cursor_at_lastrec( + struct xfs_btree_cur *cnt_cur) +{ + struct xfs_btree_block *block; + union xfs_btree_ptr ptr; + struct xfs_buf *bp; + + block = xfs_btree_get_block(cnt_cur, 0, &bp); + + xfs_btree_get_sibling(cnt_cur, block, &ptr, XFS_BB_RIGHTSIB); + return xfs_btree_ptr_is_null(cnt_cur, &ptr); +} + +/* + * Find the rightmost record of the cntbt, and return the longest free space + * recorded in it. Simply set both the block number and the length to their + * maximum values before searching. + */ +static int +xfs_cntbt_longest( + struct xfs_btree_cur *cnt_cur, + xfs_extlen_t *longest) +{ + struct xfs_alloc_rec_incore irec; + union xfs_btree_rec *rec; + int stat = 0; + int error; + + memset(&cnt_cur->bc_rec, 0xFF, sizeof(cnt_cur->bc_rec)); + error = xfs_btree_lookup(cnt_cur, XFS_LOOKUP_LE, &stat); + if (error) + return error; + if (!stat) { + /* totally empty tree */ + *longest = 0; + return 0; + } + + error = xfs_btree_get_rec(cnt_cur, &rec, &stat); + if (error) + return error; + if (XFS_IS_CORRUPT(cnt_cur->bc_mp, !stat)) { + xfs_btree_mark_sick(cnt_cur); + return -EFSCORRUPTED; + } + + xfs_alloc_btrec_to_irec(rec, &irec); + *longest = irec.ar_blockcount; + return 0; +} + +/* + * Update the longest contiguous free extent in the AG from the by-count cursor + * that is passed to us. This should be done at the end of any allocation or + * freeing operation that touches the longest extent in the btree. + * + * Needing to update the longest extent can be determined by calling + * xfs_alloc_cursor_at_lastrec() after the cursor is positioned for record + * modification but before the modification begins. + */ +static int +xfs_alloc_fixup_longest( + struct xfs_btree_cur *cnt_cur) +{ + struct xfs_perag *pag = to_perag(cnt_cur->bc_group); + struct xfs_buf *bp = cnt_cur->bc_ag.agbp; + struct xfs_agf *agf = bp->b_addr; + xfs_extlen_t longest = 0; + int error; + + /* Lookup last rec in order to update AGF. */ + error = xfs_cntbt_longest(cnt_cur, &longest); + if (error) + return error; + + pag->pagf_longest = longest; + agf->agf_longest = cpu_to_be32(pag->pagf_longest); + xfs_alloc_log_agf(cnt_cur->bc_tp, bp, XFS_AGF_LONGEST); + + return 0; +} + +/* * Update the two btrees, logically removing from freespace the extent * starting at rbno, rlen blocks. The extent is contained within the * actual (current) free extent fbno for flen blocks. @@ -456,6 +580,7 @@ xfs_alloc_fixup_trees( xfs_extlen_t nflen1=0; /* first new free length */ xfs_extlen_t nflen2=0; /* second new free length */ struct xfs_mount *mp; + bool fixup_longest = false; mp = cnt_cur->bc_mp; @@ -469,14 +594,18 @@ xfs_alloc_fixup_trees( if (XFS_IS_CORRUPT(mp, i != 1 || nfbno1 != fbno || - nflen1 != flen)) + nflen1 != flen)) { + xfs_btree_mark_sick(cnt_cur); return -EFSCORRUPTED; + } #endif } else { if ((error = xfs_alloc_lookup_eq(cnt_cur, fbno, flen, &i))) return error; - if (XFS_IS_CORRUPT(mp, i != 1)) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); return -EFSCORRUPTED; + } } /* * Look up the record in the by-block tree if necessary. @@ -488,14 +617,18 @@ xfs_alloc_fixup_trees( if (XFS_IS_CORRUPT(mp, i != 1 || nfbno1 != fbno || - nflen1 != flen)) + nflen1 != flen)) { + xfs_btree_mark_sick(bno_cur); return -EFSCORRUPTED; + } #endif } else { if ((error = xfs_alloc_lookup_eq(bno_cur, fbno, flen, &i))) return error; - if (XFS_IS_CORRUPT(mp, i != 1)) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bno_cur); return -EFSCORRUPTED; + } } #ifdef DEBUG @@ -508,8 +641,10 @@ xfs_alloc_fixup_trees( if (XFS_IS_CORRUPT(mp, bnoblock->bb_numrecs != - cntblock->bb_numrecs)) + cntblock->bb_numrecs)) { + xfs_btree_mark_sick(bno_cur); return -EFSCORRUPTED; + } } #endif @@ -534,35 +669,49 @@ xfs_alloc_fixup_trees( nfbno2 = rbno + rlen; nflen2 = (fbno + flen) - nfbno2; } + + if (xfs_alloc_cursor_at_lastrec(cnt_cur)) + fixup_longest = true; + /* * Delete the entry from the by-size btree. */ if ((error = xfs_btree_delete(cnt_cur, &i))) return error; - if (XFS_IS_CORRUPT(mp, i != 1)) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); return -EFSCORRUPTED; + } /* * Add new by-size btree entry(s). */ if (nfbno1 != NULLAGBLOCK) { if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno1, nflen1, &i))) return error; - if (XFS_IS_CORRUPT(mp, i != 0)) + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cnt_cur); return -EFSCORRUPTED; + } if ((error = xfs_btree_insert(cnt_cur, &i))) return error; - if (XFS_IS_CORRUPT(mp, i != 1)) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); return -EFSCORRUPTED; + } } if (nfbno2 != NULLAGBLOCK) { if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno2, nflen2, &i))) return error; - if (XFS_IS_CORRUPT(mp, i != 0)) + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cnt_cur); return -EFSCORRUPTED; + } if ((error = xfs_btree_insert(cnt_cur, &i))) return error; - if (XFS_IS_CORRUPT(mp, i != 1)) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); return -EFSCORRUPTED; + } } /* * Fix up the by-block btree entry(s). @@ -573,8 +722,10 @@ xfs_alloc_fixup_trees( */ if ((error = xfs_btree_delete(bno_cur, &i))) return error; - if (XFS_IS_CORRUPT(mp, i != 1)) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bno_cur); return -EFSCORRUPTED; + } } else { /* * Update the by-block entry to start later|be shorter. @@ -588,16 +739,43 @@ xfs_alloc_fixup_trees( */ if ((error = xfs_alloc_lookup_eq(bno_cur, nfbno2, nflen2, &i))) return error; - if (XFS_IS_CORRUPT(mp, i != 0)) + if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(bno_cur); return -EFSCORRUPTED; + } if ((error = xfs_btree_insert(bno_cur, &i))) return error; - if (XFS_IS_CORRUPT(mp, i != 1)) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bno_cur); return -EFSCORRUPTED; + } } + + if (fixup_longest) + return xfs_alloc_fixup_longest(cnt_cur); + return 0; } +/* + * We do not verify the AGFL contents against AGF-based index counters here, + * even though we may have access to the perag that contains shadow copies. We + * don't know if the AGF based counters have been checked, and if they have they + * still may be inconsistent because they haven't yet been reset on the first + * allocation after the AGF has been read in. + * + * This means we can only check that all agfl entries contain valid or null + * values because we can't reliably determine the active range to exclude + * NULLAGBNO as a valid value. + * + * However, we can't even do that for v4 format filesystems because there are + * old versions of mkfs out there that does not initialise the AGFL to known, + * verifiable values. HEnce we can't tell the difference between a AGFL block + * allocated by mkfs and a corrupted AGFL block here on v4 filesystems. + * + * As a result, we can only fully validate AGFL block numbers when we pull them + * from the freelist in xfs_alloc_get_freelist(). + */ static xfs_failaddr_t xfs_agfl_verify( struct xfs_buf *bp) @@ -607,12 +785,6 @@ xfs_agfl_verify( __be32 *agfl_bno = xfs_buf_to_agfl_bno(bp); int i; - /* - * There is no verification of non-crc AGFLs because mkfs does not - * initialise the AGFL to zero or NULL. Hence the only valid part of the - * AGFL is what the AGF says is active. We can't get to the AGF, so we - * can't verify just those entries are valid. - */ if (!xfs_has_crc(mp)) return NULL; @@ -626,7 +798,7 @@ xfs_agfl_verify( * use it by using uncached buffers that don't have the perag attached * so we can detect and avoid this problem. */ - if (bp->b_pag && be32_to_cpu(agfl->agfl_seqno) != bp->b_pag->pag_agno) + if (bp->b_pag && be32_to_cpu(agfl->agfl_seqno) != pag_agno((bp->b_pag))) return __this_address; for (i = 0; i < xfs_agfl_size(mp); i++) { @@ -706,14 +878,15 @@ xfs_alloc_read_agfl( struct xfs_trans *tp, struct xfs_buf **bpp) { - struct xfs_mount *mp = pag->pag_mount; + struct xfs_mount *mp = pag_mount(pag); struct xfs_buf *bp; int error; - error = xfs_trans_read_buf( - mp, tp, mp->m_ddev_targp, - XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGFL_DADDR(mp)), + error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, + XFS_AG_DADDR(mp, pag_agno(pag), XFS_AGFL_DADDR(mp)), XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); if (error) return error; xfs_buf_set_ref(bp, XFS_AGFL_REF); @@ -735,6 +908,7 @@ xfs_alloc_update_counters( if (unlikely(be32_to_cpu(agf->agf_freeblks) > be32_to_cpu(agf->agf_length))) { xfs_buf_mark_corrupt(agbp); + xfs_ag_mark_sick(agbp->b_pag, XFS_SICK_AG_AGF); return -EFSCORRUPTED; } @@ -772,8 +946,6 @@ xfs_alloc_cur_setup( int error; int i; - ASSERT(args->alignment == 1 || args->type != XFS_ALLOCTYPE_THIS_BNO); - acur->cur_len = args->maxlen; acur->rec_bno = 0; acur->rec_len = 0; @@ -789,8 +961,8 @@ xfs_alloc_cur_setup( * attempt a small allocation. */ if (!acur->cnt) - acur->cnt = xfs_allocbt_init_cursor(args->mp, args->tp, - args->agbp, args->pag, XFS_BTNUM_CNT); + acur->cnt = xfs_cntbt_init_cursor(args->mp, args->tp, + args->agbp, args->pag); error = xfs_alloc_lookup_ge(acur->cnt, 0, args->maxlen, &i); if (error) return error; @@ -799,11 +971,11 @@ xfs_alloc_cur_setup( * Allocate the bnobt left and right search cursors. */ if (!acur->bnolt) - acur->bnolt = xfs_allocbt_init_cursor(args->mp, args->tp, - args->agbp, args->pag, XFS_BTNUM_BNO); + acur->bnolt = xfs_bnobt_init_cursor(args->mp, args->tp, + args->agbp, args->pag); if (!acur->bnogt) - acur->bnogt = xfs_allocbt_init_cursor(args->mp, args->tp, - args->agbp, args->pag, XFS_BTNUM_BNO); + acur->bnogt = xfs_bnobt_init_cursor(args->mp, args->tp, + args->agbp, args->pag); return i == 1 ? 0 : -ENOSPC; } @@ -845,15 +1017,17 @@ xfs_alloc_cur_check( bool busy; unsigned busy_gen = 0; bool deactivate = false; - bool isbnobt = cur->bc_btnum == XFS_BTNUM_BNO; + bool isbnobt = xfs_btree_is_bno(cur->bc_ops); *new = 0; error = xfs_alloc_get_rec(cur, &bno, &len, &i); if (error) return error; - if (XFS_IS_CORRUPT(args->mp, i != 1)) + if (XFS_IS_CORRUPT(args->mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } /* * Check minlen and deactivate a cntbt cursor if out of acceptable size @@ -887,7 +1061,6 @@ xfs_alloc_cur_check( * We have an aligned record that satisfies minlen and beats or matches * the candidate extent size. Compare locality for near allocation mode. */ - ASSERT(args->type == XFS_ALLOCTYPE_NEAR_BNO); diff = xfs_alloc_compute_diff(args->agbno, args->len, args->alignment, args->datatype, bnoa, lena, &bnew); @@ -920,9 +1093,8 @@ xfs_alloc_cur_check( deactivate = true; out: if (deactivate) - cur->bc_ag.abt.active = false; - trace_xfs_alloc_cur_check(args->mp, cur->bc_btnum, bno, len, diff, - *new); + cur->bc_flags &= ~XFS_BTREE_ALLOCBT_ACTIVE; + trace_xfs_alloc_cur_check(cur, bno, len, diff, *new); return 0; } @@ -935,13 +1107,12 @@ xfs_alloc_cur_finish( struct xfs_alloc_arg *args, struct xfs_alloc_cur *acur) { - struct xfs_agf __maybe_unused *agf = args->agbp->b_addr; int error; ASSERT(acur->cnt && acur->bnolt); ASSERT(acur->bno >= acur->rec_bno); ASSERT(acur->bno + acur->len <= acur->rec_bno + acur->rec_len); - ASSERT(acur->rec_bno + acur->rec_len <= be32_to_cpu(agf->agf_length)); + ASSERT(xfs_verify_agbext(args->pag, acur->rec_bno, acur->rec_len)); error = xfs_alloc_fixup_trees(acur->cnt, acur->bnolt, acur->rec_bno, acur->rec_len, acur->bno, acur->len, 0); @@ -1060,6 +1231,7 @@ xfs_alloc_ag_vextent_small( if (error) goto error; if (XFS_IS_CORRUPT(args->mp, i != 1)) { + xfs_btree_mark_sick(ccur); error = -EFSCORRUPTED; goto error; } @@ -1078,14 +1250,14 @@ xfs_alloc_ag_vextent_small( if (fbno == NULLAGBLOCK) goto out; - xfs_extent_busy_reuse(args->mp, args->pag, fbno, 1, + xfs_extent_busy_reuse(pag_group(args->pag), fbno, 1, (args->datatype & XFS_ALLOC_NOBUSY)); if (args->datatype & XFS_ALLOC_USERDATA) { struct xfs_buf *bp; error = xfs_trans_get_buf(args->tp, args->mp->m_ddev_targp, - XFS_AGB_TO_DADDR(args->mp, args->agno, fbno), + xfs_agbno_to_daddr(args->pag, fbno), args->mp->m_bsize, 0, &bp); if (error) goto error; @@ -1094,6 +1266,7 @@ xfs_alloc_ag_vextent_small( *fbnop = args->agbno = fbno; *flenp = args->len = 1; if (XFS_IS_CORRUPT(args->mp, fbno >= be32_to_cpu(agf->agf_length))) { + xfs_btree_mark_sick(ccur); error = -EFSCORRUPTED; goto error; } @@ -1133,78 +1306,6 @@ error: } /* - * Allocate a variable extent in the allocation group agno. - * Type and bno are used to determine where in the allocation group the - * extent will start. - * Extent's length (returned in *len) will be between minlen and maxlen, - * and of the form k * prod + mod unless there's nothing that large. - * Return the starting a.g. block, or NULLAGBLOCK if we can't do it. - */ -STATIC int /* error */ -xfs_alloc_ag_vextent( - xfs_alloc_arg_t *args) /* argument structure for allocation */ -{ - int error=0; - - ASSERT(args->minlen > 0); - ASSERT(args->maxlen > 0); - ASSERT(args->minlen <= args->maxlen); - ASSERT(args->mod < args->prod); - ASSERT(args->alignment > 0); - - /* - * Branch to correct routine based on the type. - */ - args->wasfromfl = 0; - switch (args->type) { - case XFS_ALLOCTYPE_THIS_AG: - error = xfs_alloc_ag_vextent_size(args); - break; - case XFS_ALLOCTYPE_NEAR_BNO: - error = xfs_alloc_ag_vextent_near(args); - break; - case XFS_ALLOCTYPE_THIS_BNO: - error = xfs_alloc_ag_vextent_exact(args); - break; - default: - ASSERT(0); - /* NOTREACHED */ - } - - if (error || args->agbno == NULLAGBLOCK) - return error; - - ASSERT(args->len >= args->minlen); - ASSERT(args->len <= args->maxlen); - ASSERT(!args->wasfromfl || args->resv != XFS_AG_RESV_AGFL); - ASSERT(args->agbno % args->alignment == 0); - - /* if not file data, insert new block into the reverse map btree */ - if (!xfs_rmap_should_skip_owner_update(&args->oinfo)) { - error = xfs_rmap_alloc(args->tp, args->agbp, args->pag, - args->agbno, args->len, &args->oinfo); - if (error) - return error; - } - - if (!args->wasfromfl) { - error = xfs_alloc_update_counters(args->tp, args->agbp, - -((long)(args->len))); - if (error) - return error; - - ASSERT(!xfs_extent_busy_search(args->mp, args->pag, - args->agbno, args->len)); - } - - xfs_ag_resv_alloc_extent(args->pag, args->resv, args); - - XFS_STATS_INC(args->mp, xs_allocx); - XFS_STATS_ADD(args->mp, xs_allocb, args->len); - return error; -} - -/* * Allocate a variable extent at exactly agno/bno. * Extent's length (returned in *len) will be between minlen and maxlen, * and of the form k * prod + mod unless there's nothing that large. @@ -1214,7 +1315,6 @@ STATIC int /* error */ xfs_alloc_ag_vextent_exact( xfs_alloc_arg_t *args) /* allocation argument structure */ { - struct xfs_agf __maybe_unused *agf = args->agbp->b_addr; struct xfs_btree_cur *bno_cur;/* by block-number btree cursor */ struct xfs_btree_cur *cnt_cur;/* by count btree cursor */ int error; @@ -1231,8 +1331,8 @@ xfs_alloc_ag_vextent_exact( /* * Allocate/initialize a cursor for the by-number freespace btree. */ - bno_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp, - args->pag, XFS_BTNUM_BNO); + bno_cur = xfs_bnobt_init_cursor(args->mp, args->tp, args->agbp, + args->pag); /* * Lookup bno and minlen in the btree (minlen is irrelevant, really). @@ -1252,6 +1352,7 @@ xfs_alloc_ag_vextent_exact( if (error) goto error0; if (XFS_IS_CORRUPT(args->mp, i != 1)) { + xfs_btree_mark_sick(bno_cur); error = -EFSCORRUPTED; goto error0; } @@ -1262,7 +1363,8 @@ xfs_alloc_ag_vextent_exact( */ tbno = fbno; tlen = flen; - xfs_extent_busy_trim(args, &tbno, &tlen, &busy_gen); + xfs_extent_busy_trim(pag_group(args->pag), args->minlen, args->maxlen, + &tbno, &tlen, &busy_gen); /* * Give up if the start of the extent is busy, or the freespace isn't @@ -1291,9 +1393,9 @@ xfs_alloc_ag_vextent_exact( * We are allocating agbno for args->len * Allocate/initialize a cursor for the by-size btree. */ - cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp, - args->pag, XFS_BTNUM_CNT); - ASSERT(args->agbno + args->len <= be32_to_cpu(agf->agf_length)); + cnt_cur = xfs_cntbt_init_cursor(args->mp, args->tp, args->agbp, + args->pag); + ASSERT(xfs_verify_agbext(args->pag, args->agbno, args->len)); error = xfs_alloc_fixup_trees(cnt_cur, bno_cur, fbno, flen, args->agbno, args->len, XFSA_FIXUP_BNO_OK); if (error) { @@ -1364,7 +1466,7 @@ xfs_alloc_walk_iter( if (error) return error; if (i == 0) - cur->bc_ag.abt.active = false; + cur->bc_flags &= ~XFS_BTREE_ALLOCBT_ACTIVE; if (count > 0) count--; @@ -1389,7 +1491,6 @@ xfs_alloc_ag_vextent_locality( bool fbinc; ASSERT(acur->len == 0); - ASSERT(args->type == XFS_ALLOCTYPE_NEAR_BNO); *stat = 0; @@ -1479,7 +1580,7 @@ xfs_alloc_ag_vextent_locality( if (error) return error; if (i) { - acur->cnt->bc_ag.abt.active = true; + acur->cnt->bc_flags |= XFS_BTREE_ALLOCBT_ACTIVE; fbcur = acur->cnt; fbinc = false; } @@ -1532,8 +1633,10 @@ xfs_alloc_ag_vextent_lastblock( error = xfs_alloc_get_rec(acur->cnt, bno, len, &i); if (error) return error; - if (XFS_IS_CORRUPT(args->mp, i != 1)) + if (XFS_IS_CORRUPT(args->mp, i != 1)) { + xfs_btree_mark_sick(acur->cnt); return -EFSCORRUPTED; + } if (*len >= args->minlen) break; error = xfs_btree_increment(acur->cnt, 0, &i); @@ -1569,7 +1672,8 @@ xfs_alloc_ag_vextent_lastblock( */ STATIC int xfs_alloc_ag_vextent_near( - struct xfs_alloc_arg *args) + struct xfs_alloc_arg *args, + uint32_t alloc_flags) { struct xfs_alloc_cur acur = {}; int error; /* error code */ @@ -1588,6 +1692,8 @@ xfs_alloc_ag_vextent_near( if (args->agbno > args->max_agbno) args->agbno = args->max_agbno; + /* Retry once quickly if we find busy extents before blocking. */ + alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH; restart: len = 0; @@ -1643,9 +1749,21 @@ restart: */ if (!acur.len) { if (acur.busy) { + /* + * Our only valid extents must have been busy. Flush and + * retry the allocation again. If we get an -EAGAIN + * error, we're being told that a deadlock was avoided + * and the current transaction needs committing before + * the allocation can be retried. + */ trace_xfs_alloc_near_busy(args); - xfs_extent_busy_flush(args->mp, args->pag, - acur.busy_gen); + error = xfs_extent_busy_flush(args->tp, + pag_group(args->pag), acur.busy_gen, + alloc_flags); + if (error) + goto out; + + alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH; goto restart; } trace_xfs_alloc_size_neither(args); @@ -1668,28 +1786,31 @@ out: * and of the form k * prod + mod unless there's nothing that large. * Return the starting a.g. block, or NULLAGBLOCK if we can't do it. */ -STATIC int /* error */ +static int xfs_alloc_ag_vextent_size( - xfs_alloc_arg_t *args) /* allocation argument structure */ + struct xfs_alloc_arg *args, + uint32_t alloc_flags) { - struct xfs_agf *agf = args->agbp->b_addr; - struct xfs_btree_cur *bno_cur; /* cursor for bno btree */ - struct xfs_btree_cur *cnt_cur; /* cursor for cnt btree */ - int error; /* error result */ - xfs_agblock_t fbno; /* start of found freespace */ - xfs_extlen_t flen; /* length of found freespace */ - int i; /* temp status variable */ - xfs_agblock_t rbno; /* returned block number */ - xfs_extlen_t rlen; /* length of returned extent */ - bool busy; - unsigned busy_gen; + struct xfs_agf *agf = args->agbp->b_addr; + struct xfs_btree_cur *bno_cur; + struct xfs_btree_cur *cnt_cur; + xfs_agblock_t fbno; /* start of found freespace */ + xfs_extlen_t flen; /* length of found freespace */ + xfs_agblock_t rbno; /* returned block number */ + xfs_extlen_t rlen; /* length of returned extent */ + bool busy; + unsigned busy_gen; + int error; + int i; + /* Retry once quickly if we find busy extents before blocking. */ + alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH; restart: /* * Allocate and initialize a cursor for the by-size btree. */ - cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp, - args->pag, XFS_BTNUM_CNT); + cnt_cur = xfs_cntbt_init_cursor(args->mp, args->tp, args->agbp, + args->pag); bno_cur = NULL; /* @@ -1728,6 +1849,7 @@ restart: if (error) goto error0; if (XFS_IS_CORRUPT(args->mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } @@ -1741,19 +1863,26 @@ restart: error = xfs_btree_increment(cnt_cur, 0, &i); if (error) goto error0; - if (i == 0) { - /* - * Our only valid extents must have been busy. - * Make it unbusy by forcing the log out and - * retrying. - */ - xfs_btree_del_cursor(cnt_cur, - XFS_BTREE_NOERROR); - trace_xfs_alloc_size_busy(args); - xfs_extent_busy_flush(args->mp, - args->pag, busy_gen); - goto restart; - } + if (i) + continue; + + /* + * Our only valid extents must have been busy. Flush and + * retry the allocation again. If we get an -EAGAIN + * error, we're being told that a deadlock was avoided + * and the current transaction needs committing before + * the allocation can be retried. + */ + trace_xfs_alloc_size_busy(args); + error = xfs_extent_busy_flush(args->tp, + pag_group(args->pag), busy_gen, + alloc_flags); + if (error) + goto error0; + + alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH; + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); + goto restart; } } @@ -1768,6 +1897,7 @@ restart: rlen != 0 && (rlen > flen || rbno + rlen > fbno + flen))) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } @@ -1790,10 +1920,11 @@ restart: &i))) goto error0; if (XFS_IS_CORRUPT(args->mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } - if (flen < bestrlen) + if (flen <= bestrlen) break; busy = xfs_alloc_compute_aligned(args, fbno, flen, &rbno, &rlen, &busy_gen); @@ -1802,6 +1933,7 @@ restart: rlen != 0 && (rlen > flen || rbno + rlen > fbno + flen))) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } @@ -1818,6 +1950,7 @@ restart: &i))) goto error0; if (XFS_IS_CORRUPT(args->mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } @@ -1833,9 +1966,22 @@ restart: args->len = rlen; if (rlen < args->minlen) { if (busy) { - xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); + /* + * Our only valid extents must have been busy. Flush and + * retry the allocation again. If we get an -EAGAIN + * error, we're being told that a deadlock was avoided + * and the current transaction needs committing before + * the allocation can be retried. + */ trace_xfs_alloc_size_busy(args); - xfs_extent_busy_flush(args->mp, args->pag, busy_gen); + error = xfs_extent_busy_flush(args->tp, + pag_group(args->pag), busy_gen, + alloc_flags); + if (error) + goto error0; + + alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH; + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); goto restart; } goto out_nominleft; @@ -1844,14 +1990,15 @@ restart: rlen = args->len; if (XFS_IS_CORRUPT(args->mp, rlen > flen)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } /* * Allocate and initialize a cursor for the by-block tree. */ - bno_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp, - args->pag, XFS_BTNUM_BNO); + bno_cur = xfs_bnobt_init_cursor(args->mp, args->tp, args->agbp, + args->pag); if ((error = xfs_alloc_fixup_trees(cnt_cur, bno_cur, fbno, flen, rbno, rlen, XFSA_FIXUP_CNT_OK))) goto error0; @@ -1863,6 +2010,7 @@ restart: if (XFS_IS_CORRUPT(args->mp, args->agbno + args->len > be32_to_cpu(agf->agf_length))) { + xfs_ag_mark_sick(args->pag, XFS_SICK_AG_BNOBT); error = -EFSCORRUPTED; goto error0; } @@ -1887,11 +2035,10 @@ out_nominleft: /* * Free the extent starting at agno/bno for length. */ -STATIC int +int xfs_free_ag_extent( struct xfs_trans *tp, struct xfs_buf *agbp, - xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, @@ -1911,6 +2058,7 @@ xfs_free_ag_extent( int i; int error; struct xfs_perag *pag = agbp->b_pag; + bool fixup_longest = false; bno_cur = cnt_cur = NULL; mp = tp->t_mountp; @@ -1924,7 +2072,7 @@ xfs_free_ag_extent( /* * Allocate and initialize a cursor for the by-block btree. */ - bno_cur = xfs_allocbt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_BNO); + bno_cur = xfs_bnobt_init_cursor(mp, tp, agbp, pag); /* * Look for a neighboring block on the left (lower block numbers) * that is contiguous with this space. @@ -1938,6 +2086,7 @@ xfs_free_ag_extent( if ((error = xfs_alloc_get_rec(bno_cur, <bno, <len, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bno_cur); error = -EFSCORRUPTED; goto error0; } @@ -1953,6 +2102,7 @@ xfs_free_ag_extent( * Very bad. */ if (XFS_IS_CORRUPT(mp, ltbno + ltlen > bno)) { + xfs_btree_mark_sick(bno_cur); error = -EFSCORRUPTED; goto error0; } @@ -1971,6 +2121,7 @@ xfs_free_ag_extent( if ((error = xfs_alloc_get_rec(bno_cur, >bno, >len, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bno_cur); error = -EFSCORRUPTED; goto error0; } @@ -1986,6 +2137,7 @@ xfs_free_ag_extent( * Very bad. */ if (XFS_IS_CORRUPT(mp, bno + len > gtbno)) { + xfs_btree_mark_sick(bno_cur); error = -EFSCORRUPTED; goto error0; } @@ -1994,7 +2146,7 @@ xfs_free_ag_extent( /* * Now allocate and initialize a cursor for the by-size tree. */ - cnt_cur = xfs_allocbt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_CNT); + cnt_cur = xfs_cntbt_init_cursor(mp, tp, agbp, pag); /* * Have both left and right contiguous neighbors. * Merge all three into a single free block. @@ -2006,12 +2158,14 @@ xfs_free_ag_extent( if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } if ((error = xfs_btree_delete(cnt_cur, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } @@ -2021,12 +2175,14 @@ xfs_free_ag_extent( if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } if ((error = xfs_btree_delete(cnt_cur, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } @@ -2036,6 +2192,7 @@ xfs_free_ag_extent( if ((error = xfs_btree_delete(bno_cur, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bno_cur); error = -EFSCORRUPTED; goto error0; } @@ -2045,6 +2202,7 @@ xfs_free_ag_extent( if ((error = xfs_btree_decrement(bno_cur, 0, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bno_cur); error = -EFSCORRUPTED; goto error0; } @@ -2064,6 +2222,7 @@ xfs_free_ag_extent( i != 1 || xxbno != ltbno || xxlen != ltlen)) { + xfs_btree_mark_sick(bno_cur); error = -EFSCORRUPTED; goto error0; } @@ -2088,12 +2247,14 @@ xfs_free_ag_extent( if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } if ((error = xfs_btree_delete(cnt_cur, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } @@ -2104,6 +2265,7 @@ xfs_free_ag_extent( if ((error = xfs_btree_decrement(bno_cur, 0, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bno_cur); error = -EFSCORRUPTED; goto error0; } @@ -2123,12 +2285,14 @@ xfs_free_ag_extent( if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } if ((error = xfs_btree_delete(cnt_cur, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } @@ -2151,27 +2315,43 @@ xfs_free_ag_extent( if ((error = xfs_btree_insert(bno_cur, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bno_cur); error = -EFSCORRUPTED; goto error0; } } xfs_btree_del_cursor(bno_cur, XFS_BTREE_NOERROR); bno_cur = NULL; + /* * In all cases we need to insert the new freespace in the by-size tree. + * + * If this new freespace is being inserted in the block that contains + * the largest free space in the btree, make sure we also fix up the + * agf->agf-longest tracker field. */ if ((error = xfs_alloc_lookup_eq(cnt_cur, nbno, nlen, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } + if (xfs_alloc_cursor_at_lastrec(cnt_cur)) + fixup_longest = true; if ((error = xfs_btree_insert(cnt_cur, &i))) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto error0; } + if (fixup_longest) { + error = xfs_alloc_fixup_longest(cnt_cur); + if (error) + goto error0; + } + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); cnt_cur = NULL; @@ -2179,19 +2359,19 @@ xfs_free_ag_extent( * Update the freespace totals in the ag and superblock. */ error = xfs_alloc_update_counters(tp, agbp, len); - xfs_ag_resv_free_extent(agbp->b_pag, type, tp, len); + xfs_ag_resv_free_extent(pag, type, tp, len); if (error) goto error0; XFS_STATS_INC(mp, xs_freex); XFS_STATS_ADD(mp, xs_freeb, len); - trace_xfs_free_extent(mp, agno, bno, len, type, haveleft, haveright); + trace_xfs_free_extent(pag, bno, len, type, haveleft, haveright); return 0; error0: - trace_xfs_free_extent(mp, agno, bno, len, type, -1, -1); + trace_xfs_free_extent(pag, bno, len, type, -1, -1); if (bno_cur) xfs_btree_del_cursor(bno_cur, XFS_BTREE_ERROR); if (cnt_cur) @@ -2250,7 +2430,7 @@ xfs_alloc_longest_free_extent( * reservations and AGFL rules in place, we can return this extent. */ if (pag->pagf_longest > delta) - return min_t(xfs_extlen_t, pag->pag_mount->m_ag_max_usable, + return min_t(xfs_extlen_t, pag_mount(pag)->m_ag_max_usable, pag->pagf_longest - delta); /* Otherwise, let the caller try for 1 block if there's space. */ @@ -2267,23 +2447,41 @@ xfs_alloc_min_freelist( struct xfs_perag *pag) { /* AG btrees have at least 1 level. */ - static const uint8_t fake_levels[XFS_BTNUM_AGF] = {1, 1, 1}; - const uint8_t *levels = pag ? pag->pagf_levels : fake_levels; + const unsigned int bno_level = pag ? pag->pagf_bno_level : 1; + const unsigned int cnt_level = pag ? pag->pagf_cnt_level : 1; + const unsigned int rmap_level = pag ? pag->pagf_rmap_level : 1; unsigned int min_free; ASSERT(mp->m_alloc_maxlevels > 0); + /* + * For a btree shorter than the maximum height, the worst case is that + * every level gets split and a new level is added, then while inserting + * another entry to refill the AGFL, every level under the old root gets + * split again. This is: + * + * (full height split reservation) + (AGFL refill split height) + * = (current height + 1) + (current height - 1) + * = (new height) + (new height - 2) + * = 2 * new height - 2 + * + * For a btree of maximum height, the worst case is that every level + * under the root gets split, then while inserting another entry to + * refill the AGFL, every level under the root gets split again. This is + * also: + * + * 2 * (current height - 1) + * = 2 * (new height - 1) + * = 2 * new height - 2 + */ + /* space needed by-bno freespace btree */ - min_free = min_t(unsigned int, levels[XFS_BTNUM_BNOi] + 1, - mp->m_alloc_maxlevels); + min_free = min(bno_level + 1, mp->m_alloc_maxlevels) * 2 - 2; /* space needed by-size freespace btree */ - min_free += min_t(unsigned int, levels[XFS_BTNUM_CNTi] + 1, - mp->m_alloc_maxlevels); + min_free += min(cnt_level + 1, mp->m_alloc_maxlevels) * 2 - 2; /* space needed reverse mapping used space btree */ if (xfs_has_rmapbt(mp)) - min_free += min_t(unsigned int, levels[XFS_BTNUM_RMAPi] + 1, - mp->m_rmap_maxlevels); - + min_free += min(rmap_level + 1, mp->m_rmap_maxlevels) * 2 - 2; return min_free; } @@ -2340,39 +2538,17 @@ xfs_alloc_space_available( return true; } -int -xfs_free_agfl_block( - struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agblock_t agbno, - struct xfs_buf *agbp, - struct xfs_owner_info *oinfo) -{ - int error; - struct xfs_buf *bp; - - error = xfs_free_ag_extent(tp, agbp, agno, agbno, 1, oinfo, - XFS_AG_RESV_AGFL); - if (error) - return error; - - error = xfs_trans_get_buf(tp, tp->t_mountp->m_ddev_targp, - XFS_AGB_TO_DADDR(tp->t_mountp, agno, agbno), - tp->t_mountp->m_bsize, 0, &bp); - if (error) - return error; - xfs_trans_binval(tp, bp); - - return 0; -} - /* - * Check the agfl fields of the agf for inconsistency or corruption. The purpose - * is to detect an agfl header padding mismatch between current and early v5 - * kernels. This problem manifests as a 1-slot size difference between the - * on-disk flcount and the active [first, last] range of a wrapped agfl. This - * may also catch variants of agfl count corruption unrelated to padding. Either - * way, we'll reset the agfl and warn the user. + * Check the agfl fields of the agf for inconsistency or corruption. + * + * The original purpose was to detect an agfl header padding mismatch between + * current and early v5 kernels. This problem manifests as a 1-slot size + * difference between the on-disk flcount and the active [first, last] range of + * a wrapped agfl. + * + * However, we need to use these same checks to catch agfl count corruptions + * unrelated to padding. This could occur on any v4 or v5 filesystem, so either + * way, we need to reset the agfl and warn the user. * * Return true if a reset is required before the agfl can be used, false * otherwise. @@ -2388,10 +2564,6 @@ xfs_agfl_needs_reset( int agfl_size = xfs_agfl_size(mp); int active; - /* no agfl header on v4 supers */ - if (!xfs_has_crc(mp)) - return false; - /* * The agf read verifier catches severe corruption of these fields. * Repeat some sanity checks to cover a packed -> unpacked mismatch if @@ -2435,13 +2607,13 @@ xfs_agfl_reset( struct xfs_mount *mp = tp->t_mountp; struct xfs_agf *agf = agbp->b_addr; - ASSERT(pag->pagf_agflreset); + ASSERT(xfs_perag_agfl_needs_reset(pag)); trace_xfs_agfl_reset(mp, agf, 0, _RET_IP_); xfs_warn(mp, "WARNING: Reset corrupted AGFL on AG %u. %d blocks leaked. " "Please unmount and run xfs_repair.", - pag->pag_agno, pag->pagf_flcount); + pag_agno(pag), pag->pagf_flcount); agf->agf_flfirst = 0; agf->agf_fllast = cpu_to_be32(xfs_agfl_size(mp) - 1); @@ -2450,99 +2622,162 @@ xfs_agfl_reset( XFS_AGF_FLCOUNT); pag->pagf_flcount = 0; - pag->pagf_agflreset = false; -} - -/* - * Defer an AGFL block free. This is effectively equivalent to - * xfs_free_extent_later() with some special handling particular to AGFL blocks. - * - * Deferring AGFL frees helps prevent log reservation overruns due to too many - * allocation operations in a transaction. AGFL frees are prone to this problem - * because for one they are always freed one at a time. Further, an immediate - * AGFL block free can cause a btree join and require another block free before - * the real allocation can proceed. Deferring the free disconnects freeing up - * the AGFL slot from freeing the block. - */ -STATIC void -xfs_defer_agfl_block( - struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_fsblock_t agbno, - struct xfs_owner_info *oinfo) -{ - struct xfs_mount *mp = tp->t_mountp; - struct xfs_extent_free_item *new; /* new element */ - - ASSERT(xfs_extfree_item_cache != NULL); - ASSERT(oinfo != NULL); - - new = kmem_cache_zalloc(xfs_extfree_item_cache, - GFP_KERNEL | __GFP_NOFAIL); - new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno); - new->xefi_blockcount = 1; - new->xefi_owner = oinfo->oi_owner; - - trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1); - - xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list); + clear_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate); } /* * Add the extent to the list of extents to be free at transaction end. * The list is maintained sorted (by block number). */ -void -__xfs_free_extent_later( +static int +xfs_defer_extent_free( struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, - bool skip_discard) + enum xfs_ag_resv_type type, + unsigned int free_flags, + struct xfs_defer_pending **dfpp) { - struct xfs_extent_free_item *new; /* new element */ -#ifdef DEBUG + struct xfs_extent_free_item *xefi; struct xfs_mount *mp = tp->t_mountp; - xfs_agnumber_t agno; - xfs_agblock_t agbno; - ASSERT(bno != NULLFSBLOCK); - ASSERT(len > 0); ASSERT(len <= XFS_MAX_BMBT_EXTLEN); 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_extfree_item_cache != NULL); + ASSERT(!(free_flags & ~XFS_FREE_EXTENT_ALL_FLAGS)); - new = kmem_cache_zalloc(xfs_extfree_item_cache, + if (free_flags & XFS_FREE_EXTENT_REALTIME) { + if (type != XFS_AG_RESV_NONE) { + ASSERT(type == XFS_AG_RESV_NONE); + return -EFSCORRUPTED; + } + if (XFS_IS_CORRUPT(mp, !xfs_verify_rtbext(mp, bno, len))) + return -EFSCORRUPTED; + } else { + if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len))) + return -EFSCORRUPTED; + } + + xefi = kmem_cache_zalloc(xfs_extfree_item_cache, GFP_KERNEL | __GFP_NOFAIL); - new->xefi_startblock = bno; - new->xefi_blockcount = (xfs_extlen_t)len; - if (skip_discard) - new->xefi_flags |= XFS_EFI_SKIP_DISCARD; + xefi->xefi_startblock = bno; + xefi->xefi_blockcount = (xfs_extlen_t)len; + xefi->xefi_agresv = type; + if (free_flags & XFS_FREE_EXTENT_SKIP_DISCARD) + xefi->xefi_flags |= XFS_EFI_SKIP_DISCARD; + if (free_flags & XFS_FREE_EXTENT_REALTIME) + xefi->xefi_flags |= XFS_EFI_REALTIME; if (oinfo) { ASSERT(oinfo->oi_offset == 0); if (oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK) - new->xefi_flags |= XFS_EFI_ATTR_FORK; + xefi->xefi_flags |= XFS_EFI_ATTR_FORK; if (oinfo->oi_flags & XFS_OWNER_INFO_BMBT_BLOCK) - new->xefi_flags |= XFS_EFI_BMBT_BLOCK; - new->xefi_owner = oinfo->oi_owner; + xefi->xefi_flags |= XFS_EFI_BMBT_BLOCK; + xefi->xefi_owner = oinfo->oi_owner; } else { - new->xefi_owner = XFS_RMAP_OWN_NULL; + xefi->xefi_owner = XFS_RMAP_OWN_NULL; } - trace_xfs_bmap_free_defer(tp->t_mountp, - XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0, - XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len); - xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list); + + xfs_extent_free_defer_add(tp, xefi, dfpp); + return 0; +} + +int +xfs_free_extent_later( + struct xfs_trans *tp, + xfs_fsblock_t bno, + xfs_filblks_t len, + const struct xfs_owner_info *oinfo, + enum xfs_ag_resv_type type, + unsigned int free_flags) +{ + struct xfs_defer_pending *dontcare = NULL; + + return xfs_defer_extent_free(tp, bno, len, oinfo, type, free_flags, + &dontcare); +} + +/* + * Set up automatic freeing of unwritten space in the filesystem. + * + * This function attached a paused deferred extent free item to the + * transaction. Pausing means that the EFI will be logged in the next + * transaction commit, but the pending EFI will not be finished until the + * pending item is unpaused. + * + * If the system goes down after the EFI has been persisted to the log but + * before the pending item is unpaused, log recovery will find the EFI, fail to + * find the EFD, and free the space. + * + * If the pending item is unpaused, the next transaction commit will log an EFD + * without freeing the space. + * + * Caller must ensure that the tp, fsbno, len, oinfo, and resv flags of the + * @args structure are set to the relevant values. + */ +int +xfs_alloc_schedule_autoreap( + const struct xfs_alloc_arg *args, + unsigned int free_flags, + struct xfs_alloc_autoreap *aarp) +{ + int error; + + error = xfs_defer_extent_free(args->tp, args->fsbno, args->len, + &args->oinfo, args->resv, free_flags, &aarp->dfp); + if (error) + return error; + + xfs_defer_item_pause(args->tp, aarp->dfp); + return 0; +} + +/* + * Cancel automatic freeing of unwritten space in the filesystem. + * + * Earlier, we created a paused deferred extent free item and attached it to + * this transaction so that we could automatically roll back a new space + * allocation if the system went down. Now we want to cancel the paused work + * item by marking the EFI stale so we don't actually free the space, unpausing + * the pending item and logging an EFD. + * + * The caller generally should have already mapped the space into the ondisk + * filesystem. If the reserved space was partially used, the caller must call + * xfs_free_extent_later to create a new EFI to free the unused space. + */ +void +xfs_alloc_cancel_autoreap( + struct xfs_trans *tp, + struct xfs_alloc_autoreap *aarp) +{ + struct xfs_defer_pending *dfp = aarp->dfp; + struct xfs_extent_free_item *xefi; + + if (!dfp) + return; + + list_for_each_entry(xefi, &dfp->dfp_work, xefi_list) + xefi->xefi_flags |= XFS_EFI_CANCELLED; + + xfs_defer_item_unpause(tp, dfp); +} + +/* + * Commit automatic freeing of unwritten space in the filesystem. + * + * This unpauses an earlier _schedule_autoreap and commits to freeing the + * allocated space. Call this if none of the reserved space was used. + */ +void +xfs_alloc_commit_autoreap( + struct xfs_trans *tp, + struct xfs_alloc_autoreap *aarp) +{ + if (aarp->dfp) + xfs_defer_item_unpause(tp, aarp->dfp); } -#ifdef DEBUG /* * Check if an AGF has a free extent record whose length is equal to * args->minlen. @@ -2558,13 +2793,14 @@ xfs_exact_minlen_extent_available( xfs_extlen_t flen; int error = 0; - cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, agbp, - args->pag, XFS_BTNUM_CNT); + cnt_cur = xfs_cntbt_init_cursor(args->mp, args->tp, agbp, + args->pag); error = xfs_alloc_lookup_ge(cnt_cur, 0, args->minlen, stat); if (error) goto out; if (*stat == 0) { + xfs_btree_mark_sick(cnt_cur); error = -EFSCORRUPTED; goto out; } @@ -2581,7 +2817,6 @@ out: return error; } -#endif /* * Decide whether to use this allocation group for this allocation. @@ -2590,7 +2825,7 @@ out: int /* error */ xfs_alloc_fix_freelist( struct xfs_alloc_arg *args, /* allocation argument structure */ - int flags) /* XFS_ALLOC_FLAG_... */ + uint32_t alloc_flags) { struct xfs_mount *mp = args->mp; struct xfs_perag *pag = args->pag; @@ -2605,8 +2840,8 @@ xfs_alloc_fix_freelist( /* deferred ops (AGFL block frees) require permanent transactions */ ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); - if (!pag->pagf_init) { - error = xfs_alloc_read_agf(pag, tp, flags, &agbp); + if (!xfs_perag_initialised_agf(pag)) { + error = xfs_alloc_read_agf(pag, tp, alloc_flags, &agbp); if (error) { /* Couldn't lock the AGF so skip this AG. */ if (error == -EAGAIN) @@ -2620,14 +2855,15 @@ xfs_alloc_fix_freelist( * somewhere else if we are not being asked to try harder at this * point */ - if (pag->pagf_metadata && (args->datatype & XFS_ALLOC_USERDATA) && - (flags & XFS_ALLOC_FLAG_TRYLOCK)) { - ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING)); + if (xfs_perag_prefers_metadata(pag) && + (args->datatype & XFS_ALLOC_USERDATA) && + (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK)) { + ASSERT(!(alloc_flags & XFS_ALLOC_FLAG_FREEING)); goto out_agbp_relse; } need = xfs_alloc_min_freelist(mp, pag); - if (!xfs_alloc_space_available(args, need, flags | + if (!xfs_alloc_space_available(args, need, alloc_flags | XFS_ALLOC_FLAG_CHECK)) goto out_agbp_relse; @@ -2636,7 +2872,7 @@ xfs_alloc_fix_freelist( * Can fail if we're not blocking on locks, and it's held. */ if (!agbp) { - error = xfs_alloc_read_agf(pag, tp, flags, &agbp); + error = xfs_alloc_read_agf(pag, tp, alloc_flags, &agbp); if (error) { /* Couldn't lock the AGF so skip this AG. */ if (error == -EAGAIN) @@ -2646,23 +2882,22 @@ xfs_alloc_fix_freelist( } /* reset a padding mismatched agfl before final free space check */ - if (pag->pagf_agflreset) + if (xfs_perag_agfl_needs_reset(pag)) xfs_agfl_reset(tp, agbp, pag); /* If there isn't enough total space or single-extent, reject it. */ need = xfs_alloc_min_freelist(mp, pag); - if (!xfs_alloc_space_available(args, need, flags)) + if (!xfs_alloc_space_available(args, need, alloc_flags)) goto out_agbp_relse; -#ifdef DEBUG - if (args->alloc_minlen_only) { + if (IS_ENABLED(CONFIG_XFS_DEBUG) && args->alloc_minlen_only) { int stat; error = xfs_exact_minlen_extent_available(args, agbp, &stat); if (error || !stat) goto out_agbp_relse; } -#endif + /* * Make the freelist shorter if it's too long. * @@ -2689,17 +2924,32 @@ xfs_alloc_fix_freelist( */ memset(&targs, 0, sizeof(targs)); /* struct copy below */ - if (flags & XFS_ALLOC_FLAG_NORMAP) + if (alloc_flags & XFS_ALLOC_FLAG_NORMAP) targs.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE; else targs.oinfo = XFS_RMAP_OINFO_AG; - while (!(flags & XFS_ALLOC_FLAG_NOSHRINK) && pag->pagf_flcount > need) { + while (!(alloc_flags & XFS_ALLOC_FLAG_NOSHRINK) && + pag->pagf_flcount > need) { error = xfs_alloc_get_freelist(pag, tp, agbp, &bno, 0); if (error) goto out_agbp_relse; - /* defer agfl frees */ - xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo); + /* + * Defer the AGFL block free. + * + * This helps to prevent log reservation overruns due to too + * many allocation operations in a transaction. AGFL frees are + * prone to this problem because for one they are always freed + * one at a time. Further, an immediate AGFL block free can + * cause a btree join and require another block free before the + * real allocation can proceed. + * Deferring the free disconnects freeing up the AGFL slot from + * freeing the block. + */ + error = xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, bno), + 1, &targs.oinfo, XFS_AG_RESV_AGFL, 0); + if (error) + goto out_agbp_relse; } targs.tp = tp; @@ -2707,7 +2957,6 @@ xfs_alloc_fix_freelist( targs.agbp = agbp; targs.agno = args->agno; targs.alignment = targs.minlen = targs.prod = 1; - targs.type = XFS_ALLOCTYPE_THIS_AG; targs.pag = pag; error = xfs_alloc_read_agfl(pag, tp, &agflbp); if (error) @@ -2720,7 +2969,7 @@ xfs_alloc_fix_freelist( targs.resv = XFS_AG_RESV_AGFL; /* Allocate as many blocks as possible at once. */ - error = xfs_alloc_ag_vextent(&targs); + error = xfs_alloc_ag_vextent_size(&targs, alloc_flags); if (error) goto out_agflbp_relse; @@ -2730,10 +2979,22 @@ xfs_alloc_fix_freelist( * on a completely full ag. */ if (targs.agbno == NULLAGBLOCK) { - if (flags & XFS_ALLOC_FLAG_FREEING) + if (alloc_flags & XFS_ALLOC_FLAG_FREEING) break; goto out_agflbp_relse; } + + if (!xfs_rmap_should_skip_owner_update(&targs.oinfo)) { + error = xfs_rmap_alloc(tp, agbp, pag, + targs.agbno, targs.len, &targs.oinfo); + if (error) + goto out_agflbp_relse; + } + error = xfs_alloc_update_counters(tp, agbp, + -((long)(targs.len))); + if (error) + goto out_agflbp_relse; + /* * Put each allocated block on the list. */ @@ -2798,12 +3059,15 @@ xfs_alloc_get_freelist( */ agfl_bno = xfs_buf_to_agfl_bno(agflbp); bno = be32_to_cpu(agfl_bno[be32_to_cpu(agf->agf_flfirst)]); + if (XFS_IS_CORRUPT(tp->t_mountp, !xfs_verify_agbno(pag, bno))) + return -EFSCORRUPTED; + be32_add_cpu(&agf->agf_flfirst, 1); xfs_trans_brelse(tp, agflbp); if (be32_to_cpu(agf->agf_flfirst) == xfs_agfl_size(mp)) agf->agf_flfirst = 0; - ASSERT(!pag->pagf_agflreset); + ASSERT(!xfs_perag_agfl_needs_reset(pag)); be32_add_cpu(&agf->agf_flcount, -1); pag->pagf_flcount--; @@ -2836,8 +3100,8 @@ xfs_alloc_log_agf( offsetof(xfs_agf_t, agf_versionnum), offsetof(xfs_agf_t, agf_seqno), offsetof(xfs_agf_t, agf_length), - offsetof(xfs_agf_t, agf_roots[0]), - offsetof(xfs_agf_t, agf_levels[0]), + offsetof(xfs_agf_t, agf_bno_root), /* also cnt/rmap root */ + offsetof(xfs_agf_t, agf_bno_level), /* also cnt/rmap levels */ offsetof(xfs_agf_t, agf_flfirst), offsetof(xfs_agf_t, agf_fllast), offsetof(xfs_agf_t, agf_flcount), @@ -2892,7 +3156,7 @@ xfs_alloc_put_freelist( if (be32_to_cpu(agf->agf_fllast) == xfs_agfl_size(mp)) agf->agf_fllast = 0; - ASSERT(!pag->pagf_agflreset); + ASSERT(!xfs_perag_agfl_needs_reset(pag)); be32_add_cpu(&agf->agf_flcount, 1); pag->pagf_flcount++; @@ -2903,8 +3167,6 @@ xfs_alloc_put_freelist( logflags |= XFS_AGF_BTREEBLKS; } - xfs_alloc_log_agf(tp, agbp, logflags); - ASSERT(be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp)); agfl_bno = xfs_buf_to_agfl_bno(agflbp); @@ -2920,12 +3182,69 @@ xfs_alloc_put_freelist( return 0; } +/* + * Check that this AGF/AGI header's sequence number and length matches the AG + * number and size in fsblocks. + */ +xfs_failaddr_t +xfs_validate_ag_length( + struct xfs_buf *bp, + uint32_t seqno, + uint32_t length) +{ + struct xfs_mount *mp = bp->b_mount; + /* + * During growfs operations, the perag is not fully initialised, + * so we can't use it for any useful checking. growfs ensures we can't + * use it by using uncached buffers that don't have the perag attached + * so we can detect and avoid this problem. + */ + if (bp->b_pag && seqno != pag_agno(bp->b_pag)) + return __this_address; + + /* + * Only the last AG in the filesystem is allowed to be shorter + * than the AG size recorded in the superblock. + */ + if (length != mp->m_sb.sb_agblocks) { + /* + * During growfs, the new last AG can get here before we + * have updated the superblock. Give it a pass on the seqno + * check. + */ + if (bp->b_pag && seqno != mp->m_sb.sb_agcount - 1) + return __this_address; + if (length < XFS_MIN_AG_BLOCKS) + return __this_address; + if (length > mp->m_sb.sb_agblocks) + return __this_address; + } + + return NULL; +} + +/* + * Verify the AGF is consistent. + * + * We do not verify the AGFL indexes in the AGF are fully consistent here + * because of issues with variable on-disk structure sizes. Instead, we check + * the agfl indexes for consistency when we initialise the perag from the AGF + * information after a read completes. + * + * If the index is inconsistent, then we mark the perag as needing an AGFL + * reset. The first AGFL update performed then resets the AGFL indexes and + * refills the AGFL with known good free blocks, allowing the filesystem to + * continue operating normally at the cost of a few leaked free space blocks. + */ static xfs_failaddr_t xfs_agf_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; struct xfs_agf *agf = bp->b_addr; + xfs_failaddr_t fa; + uint32_t agf_seqno = be32_to_cpu(agf->agf_seqno); + uint32_t agf_length = be32_to_cpu(agf->agf_length); if (xfs_has_crc(mp)) { if (!uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid)) @@ -2937,63 +3256,57 @@ xfs_agf_verify( if (!xfs_verify_magic(bp, agf->agf_magicnum)) return __this_address; - if (!(XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) && - be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) && - be32_to_cpu(agf->agf_flfirst) < xfs_agfl_size(mp) && - be32_to_cpu(agf->agf_fllast) < xfs_agfl_size(mp) && - be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp))) + if (!XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum))) return __this_address; - if (be32_to_cpu(agf->agf_length) > mp->m_sb.sb_dblocks) - return __this_address; + /* + * Both agf_seqno and agf_length need to validated before anything else + * block number related in the AGF or AGFL can be checked. + */ + fa = xfs_validate_ag_length(bp, agf_seqno, agf_length); + if (fa) + return fa; - if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) || - be32_to_cpu(agf->agf_freeblks) > be32_to_cpu(agf->agf_length)) + if (be32_to_cpu(agf->agf_flfirst) >= xfs_agfl_size(mp)) return __this_address; - - if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 || - be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) < 1 || - be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > - mp->m_alloc_maxlevels || - be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) > - mp->m_alloc_maxlevels) + if (be32_to_cpu(agf->agf_fllast) >= xfs_agfl_size(mp)) return __this_address; - - if (xfs_has_rmapbt(mp) && - (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 || - be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > - mp->m_rmap_maxlevels)) + if (be32_to_cpu(agf->agf_flcount) > xfs_agfl_size(mp)) return __this_address; - if (xfs_has_rmapbt(mp) && - be32_to_cpu(agf->agf_rmap_blocks) > be32_to_cpu(agf->agf_length)) + if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) || + be32_to_cpu(agf->agf_freeblks) > agf_length) return __this_address; - /* - * during growfs operations, the perag is not fully initialised, - * so we can't use it for any useful checking. growfs ensures we can't - * use it by using uncached buffers that don't have the perag attached - * so we can detect and avoid this problem. - */ - if (bp->b_pag && be32_to_cpu(agf->agf_seqno) != bp->b_pag->pag_agno) + if (be32_to_cpu(agf->agf_bno_level) < 1 || + be32_to_cpu(agf->agf_cnt_level) < 1 || + be32_to_cpu(agf->agf_bno_level) > mp->m_alloc_maxlevels || + be32_to_cpu(agf->agf_cnt_level) > mp->m_alloc_maxlevels) return __this_address; if (xfs_has_lazysbcount(mp) && - be32_to_cpu(agf->agf_btreeblks) > be32_to_cpu(agf->agf_length)) + be32_to_cpu(agf->agf_btreeblks) > agf_length) return __this_address; - if (xfs_has_reflink(mp) && - be32_to_cpu(agf->agf_refcount_blocks) > - be32_to_cpu(agf->agf_length)) - return __this_address; + if (xfs_has_rmapbt(mp)) { + if (be32_to_cpu(agf->agf_rmap_blocks) > agf_length) + return __this_address; - if (xfs_has_reflink(mp) && - (be32_to_cpu(agf->agf_refcount_level) < 1 || - be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels)) - return __this_address; + if (be32_to_cpu(agf->agf_rmap_level) < 1 || + be32_to_cpu(agf->agf_rmap_level) > mp->m_rmap_maxlevels) + return __this_address; + } - return NULL; + if (xfs_has_reflink(mp)) { + if (be32_to_cpu(agf->agf_refcount_blocks) > agf_length) + return __this_address; + + if (be32_to_cpu(agf->agf_refcount_level) < 1 || + be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels) + return __this_address; + } + return NULL; } static void @@ -3008,7 +3321,7 @@ xfs_agf_read_verify( xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_agf_verify(bp); - if (XFS_TEST_ERROR(fa, mp, XFS_ERRTAG_ALLOC_READ_AGF)) + if (fa || XFS_TEST_ERROR(mp, XFS_ERRTAG_ALLOC_READ_AGF)) xfs_verifier_error(bp, -EFSCORRUPTED, fa); } } @@ -3055,14 +3368,16 @@ xfs_read_agf( int flags, struct xfs_buf **agfbpp) { - struct xfs_mount *mp = pag->pag_mount; + struct xfs_mount *mp = pag_mount(pag); int error; - trace_xfs_read_agf(pag->pag_mount, pag->pag_agno); + trace_xfs_read_agf(pag); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, - XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGF_DADDR(mp)), + XFS_AG_DADDR(mp, pag_agno(pag), XFS_AGF_DADDR(mp)), XFS_FSS_TO_BB(mp, 1), flags, agfbpp, &xfs_agf_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF); if (error) return error; @@ -3082,12 +3397,13 @@ xfs_alloc_read_agf( int flags, struct xfs_buf **agfbpp) { + struct xfs_mount *mp = pag_mount(pag); struct xfs_buf *agfbp; struct xfs_agf *agf; int error; int allocbt_blks; - trace_xfs_alloc_read_agf(pag->pag_mount, pag->pag_agno); + trace_xfs_alloc_read_agf(pag); /* We don't support trylock when freeing. */ ASSERT((flags & (XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK)) != @@ -3099,20 +3415,19 @@ xfs_alloc_read_agf( return error; agf = agfbp->b_addr; - if (!pag->pagf_init) { + if (!xfs_perag_initialised_agf(pag)) { pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks); pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks); pag->pagf_flcount = be32_to_cpu(agf->agf_flcount); pag->pagf_longest = be32_to_cpu(agf->agf_longest); - pag->pagf_levels[XFS_BTNUM_BNOi] = - be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi]); - pag->pagf_levels[XFS_BTNUM_CNTi] = - be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]); - pag->pagf_levels[XFS_BTNUM_RMAPi] = - be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]); + pag->pagf_bno_level = be32_to_cpu(agf->agf_bno_level); + pag->pagf_cnt_level = be32_to_cpu(agf->agf_cnt_level); + pag->pagf_rmap_level = be32_to_cpu(agf->agf_rmap_level); pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level); - pag->pagf_init = 1; - pag->pagf_agflreset = xfs_agfl_needs_reset(pag->pag_mount, agf); + if (xfs_agfl_needs_reset(mp, agf)) + set_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate); + else + clear_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate); /* * Update the in-core allocbt counter. Filter out the rmapbt @@ -3122,24 +3437,48 @@ xfs_alloc_read_agf( * counter only tracks non-root blocks. */ allocbt_blks = pag->pagf_btreeblks; - if (xfs_has_rmapbt(pag->pag_mount)) + if (xfs_has_rmapbt(mp)) allocbt_blks -= be32_to_cpu(agf->agf_rmap_blocks) - 1; if (allocbt_blks > 0) - atomic64_add(allocbt_blks, - &pag->pag_mount->m_allocbt_blks); + atomic64_add(allocbt_blks, &mp->m_allocbt_blks); + + set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate); } + #ifdef DEBUG - else if (!xfs_is_shutdown(pag->pag_mount)) { - ASSERT(pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks)); - ASSERT(pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks)); - ASSERT(pag->pagf_flcount == be32_to_cpu(agf->agf_flcount)); - ASSERT(pag->pagf_longest == be32_to_cpu(agf->agf_longest)); - ASSERT(pag->pagf_levels[XFS_BTNUM_BNOi] == - be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi])); - ASSERT(pag->pagf_levels[XFS_BTNUM_CNTi] == - be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi])); + /* + * It's possible for the AGF to be out of sync if the block device is + * silently dropping writes. This can happen in fstests with dmflakey + * enabled, which allows the buffer to be cleaned and reclaimed by + * memory pressure and then re-read from disk here. We will get a + * stale version of the AGF from disk, and nothing good can happen from + * here. Hence if we detect this situation, immediately shut down the + * filesystem. + * + * This can also happen if we are already in the middle of a forced + * shutdown, so don't bother checking if we are already shut down. + */ + if (!xfs_is_shutdown(pag_mount(pag))) { + bool ok = true; + + ok &= pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks); + ok &= pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks); + ok &= pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks); + ok &= pag->pagf_flcount == be32_to_cpu(agf->agf_flcount); + ok &= pag->pagf_longest == be32_to_cpu(agf->agf_longest); + ok &= pag->pagf_bno_level == be32_to_cpu(agf->agf_bno_level); + ok &= pag->pagf_cnt_level == be32_to_cpu(agf->agf_cnt_level); + + if (XFS_IS_CORRUPT(pag_mount(pag), !ok)) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF); + xfs_trans_brelse(tp, agfbp); + xfs_force_shutdown(pag_mount(pag), + SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } } -#endif +#endif /* DEBUG */ + if (agfbpp) *agfbpp = agfbp; else @@ -3148,26 +3487,25 @@ xfs_alloc_read_agf( } /* - * Allocate an extent (variable-size). - * Depending on the allocation type, we either look in a single allocation - * group or loop over the allocation groups to find the result. + * Pre-proces allocation arguments to set initial state that we don't require + * callers to set up correctly, as well as bounds check the allocation args + * that are set up. */ -int /* error */ -xfs_alloc_vextent( - struct xfs_alloc_arg *args) /* allocation argument structure */ +static int +xfs_alloc_vextent_check_args( + struct xfs_alloc_arg *args, + xfs_fsblock_t target, + xfs_agnumber_t *minimum_agno) { - xfs_agblock_t agsize; /* allocation group size */ - int error; - int flags; /* XFS_ALLOC_FLAG_... locking flags */ - struct xfs_mount *mp; /* mount structure pointer */ - xfs_agnumber_t sagno; /* starting allocation group number */ - xfs_alloctype_t type; /* input allocation type */ - int bump_rotor = 0; - xfs_agnumber_t rotorstep = xfs_rotorstep; /* inode32 agf stepper */ - - mp = args->mp; - type = args->otype = args->type; - args->agbno = NULLAGBLOCK; + struct xfs_mount *mp = args->mp; + xfs_agblock_t agsize; + + args->fsbno = NULLFSBLOCK; + + *minimum_agno = 0; + if (args->tp->t_highest_agno != NULLAGNUMBER) + *minimum_agno = args->tp->t_highest_agno; + /* * Just fix this up, for the case where the last a.g. is shorter * (or there's only one a.g.) and the caller couldn't easily figure @@ -3178,168 +3516,452 @@ xfs_alloc_vextent( args->maxlen = agsize; if (args->alignment == 0) args->alignment = 1; - ASSERT(XFS_FSB_TO_AGNO(mp, args->fsbno) < mp->m_sb.sb_agcount); - ASSERT(XFS_FSB_TO_AGBNO(mp, args->fsbno) < agsize); + + ASSERT(args->minlen > 0); + ASSERT(args->maxlen > 0); + ASSERT(args->alignment > 0); + ASSERT(args->resv != XFS_AG_RESV_AGFL); + + ASSERT(XFS_FSB_TO_AGNO(mp, target) < mp->m_sb.sb_agcount); + ASSERT(XFS_FSB_TO_AGBNO(mp, target) < agsize); ASSERT(args->minlen <= args->maxlen); ASSERT(args->minlen <= agsize); ASSERT(args->mod < args->prod); - if (XFS_FSB_TO_AGNO(mp, args->fsbno) >= mp->m_sb.sb_agcount || - XFS_FSB_TO_AGBNO(mp, args->fsbno) >= agsize || + + if (XFS_FSB_TO_AGNO(mp, target) >= mp->m_sb.sb_agcount || + XFS_FSB_TO_AGBNO(mp, target) >= agsize || args->minlen > args->maxlen || args->minlen > agsize || args->mod >= args->prod) { - args->fsbno = NULLFSBLOCK; trace_xfs_alloc_vextent_badargs(args); + return -ENOSPC; + } + + if (args->agno != NULLAGNUMBER && *minimum_agno > args->agno) { + trace_xfs_alloc_vextent_skip_deadlock(args); + return -ENOSPC; + } + return 0; + +} + +/* + * Prepare an AG for allocation. If the AG is not prepared to accept the + * allocation, return failure. + * + * XXX(dgc): The complexity of "need_pag" will go away as all caller paths are + * modified to hold their own perag references. + */ +static int +xfs_alloc_vextent_prepare_ag( + struct xfs_alloc_arg *args, + uint32_t alloc_flags) +{ + bool need_pag = !args->pag; + int error; + + if (need_pag) + args->pag = xfs_perag_get(args->mp, args->agno); + + args->agbp = NULL; + error = xfs_alloc_fix_freelist(args, alloc_flags); + if (error) { + trace_xfs_alloc_vextent_nofix(args); + if (need_pag) + xfs_perag_put(args->pag); + args->agbno = NULLAGBLOCK; + return error; + } + if (!args->agbp) { + /* cannot allocate in this AG at all */ + trace_xfs_alloc_vextent_noagbp(args); + args->agbno = NULLAGBLOCK; return 0; } + args->wasfromfl = 0; + return 0; +} - switch (type) { - case XFS_ALLOCTYPE_THIS_AG: - case XFS_ALLOCTYPE_NEAR_BNO: - case XFS_ALLOCTYPE_THIS_BNO: - /* - * These three force us into a single a.g. - */ - args->agno = XFS_FSB_TO_AGNO(mp, args->fsbno); - args->pag = xfs_perag_get(mp, args->agno); - error = xfs_alloc_fix_freelist(args, 0); - if (error) { - trace_xfs_alloc_vextent_nofix(args); - goto error0; - } - if (!args->agbp) { - trace_xfs_alloc_vextent_noagbp(args); +/* + * Post-process allocation results to account for the allocation if it succeed + * and set the allocated block number correctly for the caller. + * + * XXX: we should really be returning ENOSPC for ENOSPC, not + * hiding it behind a "successful" NULLFSBLOCK allocation. + */ +static int +xfs_alloc_vextent_finish( + struct xfs_alloc_arg *args, + xfs_agnumber_t minimum_agno, + int alloc_error, + bool drop_perag) +{ + struct xfs_mount *mp = args->mp; + int error = 0; + + /* + * We can end up here with a locked AGF. If we failed, the caller is + * likely going to try to allocate again with different parameters, and + * that can widen the AGs that are searched for free space. If we have + * to do BMBT block allocation, we have to do a new allocation. + * + * Hence leaving this function with the AGF locked opens up potential + * ABBA AGF deadlocks because a future allocation attempt in this + * transaction may attempt to lock a lower number AGF. + * + * We can't release the AGF until the transaction is commited, so at + * this point we must update the "first allocation" tracker to point at + * this AG if the tracker is empty or points to a lower AG. This allows + * the next allocation attempt to be modified appropriately to avoid + * deadlocks. + */ + if (args->agbp && + (args->tp->t_highest_agno == NULLAGNUMBER || + args->agno > minimum_agno)) + args->tp->t_highest_agno = args->agno; + + /* + * If the allocation failed with an error or we had an ENOSPC result, + * preserve the returned error whilst also marking the allocation result + * as "no extent allocated". This ensures that callers that fail to + * capture the error will still treat it as a failed allocation. + */ + if (alloc_error || args->agbno == NULLAGBLOCK) { + args->fsbno = NULLFSBLOCK; + error = alloc_error; + goto out_drop_perag; + } + + args->fsbno = xfs_agbno_to_fsb(args->pag, args->agbno); + + ASSERT(args->len >= args->minlen); + ASSERT(args->len <= args->maxlen); + ASSERT(args->agbno % args->alignment == 0); + XFS_AG_CHECK_DADDR(mp, XFS_FSB_TO_DADDR(mp, args->fsbno), args->len); + + /* if not file data, insert new block into the reverse map btree */ + if (!xfs_rmap_should_skip_owner_update(&args->oinfo)) { + error = xfs_rmap_alloc(args->tp, args->agbp, args->pag, + args->agbno, args->len, &args->oinfo); + if (error) + goto out_drop_perag; + } + + if (!args->wasfromfl) { + error = xfs_alloc_update_counters(args->tp, args->agbp, + -((long)(args->len))); + if (error) + goto out_drop_perag; + + ASSERT(!xfs_extent_busy_search(pag_group(args->pag), + args->agbno, args->len)); + } + + xfs_ag_resv_alloc_extent(args->pag, args->resv, args); + + XFS_STATS_INC(mp, xs_allocx); + XFS_STATS_ADD(mp, xs_allocb, args->len); + + trace_xfs_alloc_vextent_finish(args); + +out_drop_perag: + if (drop_perag && args->pag) { + xfs_perag_rele(args->pag); + args->pag = NULL; + } + return error; +} + +/* + * Allocate within a single AG only. This uses a best-fit length algorithm so if + * you need an exact sized allocation without locality constraints, this is the + * fastest way to do it. + * + * Caller is expected to hold a perag reference in args->pag. + */ +int +xfs_alloc_vextent_this_ag( + struct xfs_alloc_arg *args, + xfs_agnumber_t agno) +{ + xfs_agnumber_t minimum_agno; + uint32_t alloc_flags = 0; + int error; + + ASSERT(args->pag != NULL); + ASSERT(pag_agno(args->pag) == agno); + + args->agno = agno; + args->agbno = 0; + + trace_xfs_alloc_vextent_this_ag(args); + + error = xfs_alloc_vextent_check_args(args, + xfs_agbno_to_fsb(args->pag, 0), &minimum_agno); + if (error) { + if (error == -ENOSPC) + return 0; + return error; + } + + error = xfs_alloc_vextent_prepare_ag(args, alloc_flags); + if (!error && args->agbp) + error = xfs_alloc_ag_vextent_size(args, alloc_flags); + + return xfs_alloc_vextent_finish(args, minimum_agno, error, false); +} + +/* + * Iterate all AGs trying to allocate an extent starting from @start_ag. + * + * If the incoming allocation type is XFS_ALLOCTYPE_NEAR_BNO, it means the + * allocation attempts in @start_agno have locality information. If we fail to + * allocate in that AG, then we revert to anywhere-in-AG for all the other AGs + * we attempt to allocation in as there is no locality optimisation possible for + * those allocations. + * + * On return, args->pag may be left referenced if we finish before the "all + * failed" return point. The allocation finish still needs the perag, and + * so the caller will release it once they've finished the allocation. + * + * When we wrap the AG iteration at the end of the filesystem, we have to be + * careful not to wrap into AGs below ones we already have locked in the + * transaction if we are doing a blocking iteration. This will result in an + * out-of-order locking of AGFs and hence can cause deadlocks. + */ +static int +xfs_alloc_vextent_iterate_ags( + struct xfs_alloc_arg *args, + xfs_agnumber_t minimum_agno, + xfs_agnumber_t start_agno, + xfs_agblock_t target_agbno, + uint32_t alloc_flags) +{ + struct xfs_mount *mp = args->mp; + xfs_agnumber_t restart_agno = minimum_agno; + xfs_agnumber_t agno; + int error = 0; + + if (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK) + restart_agno = 0; +restart: + for_each_perag_wrap_range(mp, start_agno, restart_agno, + mp->m_sb.sb_agcount, agno, args->pag) { + args->agno = agno; + error = xfs_alloc_vextent_prepare_ag(args, alloc_flags); + if (error) break; + if (!args->agbp) { + trace_xfs_alloc_vextent_loopfailed(args); + continue; } - args->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno); - if ((error = xfs_alloc_ag_vextent(args))) - goto error0; - break; - case XFS_ALLOCTYPE_START_BNO: - /* - * Try near allocation first, then anywhere-in-ag after - * the first a.g. fails. - */ - if ((args->datatype & XFS_ALLOC_INITIAL_USER_DATA) && - xfs_is_inode32(mp)) { - args->fsbno = XFS_AGB_TO_FSB(mp, - ((mp->m_agfrotor / rotorstep) % - mp->m_sb.sb_agcount), 0); - bump_rotor = 1; - } - args->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno); - args->type = XFS_ALLOCTYPE_NEAR_BNO; - fallthrough; - case XFS_ALLOCTYPE_FIRST_AG: + /* - * Rotate through the allocation groups looking for a winner. + * Allocation is supposed to succeed now, so break out of the + * loop regardless of whether we succeed or not. */ - if (type == XFS_ALLOCTYPE_FIRST_AG) { - /* - * Start with allocation group given by bno. - */ - args->agno = XFS_FSB_TO_AGNO(mp, args->fsbno); - args->type = XFS_ALLOCTYPE_THIS_AG; - sagno = 0; - flags = 0; + if (args->agno == start_agno && target_agbno) { + args->agbno = target_agbno; + error = xfs_alloc_ag_vextent_near(args, alloc_flags); } else { - /* - * Start with the given allocation group. - */ - args->agno = sagno = XFS_FSB_TO_AGNO(mp, args->fsbno); - flags = XFS_ALLOC_FLAG_TRYLOCK; - } - /* - * Loop over allocation groups twice; first time with - * trylock set, second time without. - */ - for (;;) { - args->pag = xfs_perag_get(mp, args->agno); - error = xfs_alloc_fix_freelist(args, flags); - if (error) { - trace_xfs_alloc_vextent_nofix(args); - goto error0; - } - /* - * If we get a buffer back then the allocation will fly. - */ - if (args->agbp) { - if ((error = xfs_alloc_ag_vextent(args))) - goto error0; - break; - } - - trace_xfs_alloc_vextent_loopfailed(args); - - /* - * Didn't work, figure out the next iteration. - */ - if (args->agno == sagno && - type == XFS_ALLOCTYPE_START_BNO) - args->type = XFS_ALLOCTYPE_THIS_AG; - /* - * For the first allocation, we can try any AG to get - * space. However, if we already have allocated a - * block, we don't want to try AGs whose number is below - * sagno. Otherwise, we may end up with out-of-order - * locking of AGF, which might cause deadlock. - */ - if (++(args->agno) == mp->m_sb.sb_agcount) { - if (args->tp->t_firstblock != NULLFSBLOCK) - args->agno = sagno; - else - args->agno = 0; - } - /* - * Reached the starting a.g., must either be done - * or switch to non-trylock mode. - */ - if (args->agno == sagno) { - if (flags == 0) { - args->agbno = NULLAGBLOCK; - trace_xfs_alloc_vextent_allfailed(args); - break; - } - - flags = 0; - if (type == XFS_ALLOCTYPE_START_BNO) { - args->agbno = XFS_FSB_TO_AGBNO(mp, - args->fsbno); - args->type = XFS_ALLOCTYPE_NEAR_BNO; - } - } - xfs_perag_put(args->pag); - } - if (bump_rotor) { - if (args->agno == sagno) - mp->m_agfrotor = (mp->m_agfrotor + 1) % - (mp->m_sb.sb_agcount * rotorstep); - else - mp->m_agfrotor = (args->agno * rotorstep + 1) % - (mp->m_sb.sb_agcount * rotorstep); + args->agbno = 0; + error = xfs_alloc_ag_vextent_size(args, alloc_flags); } break; - default: - ASSERT(0); - /* NOTREACHED */ } - if (args->agbno == NULLAGBLOCK) - args->fsbno = NULLFSBLOCK; - else { - args->fsbno = XFS_AGB_TO_FSB(mp, args->agno, args->agbno); -#ifdef DEBUG - ASSERT(args->len >= args->minlen); - ASSERT(args->len <= args->maxlen); - ASSERT(args->agbno % args->alignment == 0); - XFS_AG_CHECK_DADDR(mp, XFS_FSB_TO_DADDR(mp, args->fsbno), - args->len); -#endif + if (error) { + xfs_perag_rele(args->pag); + args->pag = NULL; + return error; + } + if (args->agbp) + return 0; + /* + * We didn't find an AG we can alloation from. If we were given + * constraining flags by the caller, drop them and retry the allocation + * without any constraints being set. + */ + if (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK) { + alloc_flags &= ~XFS_ALLOC_FLAG_TRYLOCK; + restart_agno = minimum_agno; + goto restart; } - xfs_perag_put(args->pag); + + ASSERT(args->pag == NULL); + trace_xfs_alloc_vextent_allfailed(args); return 0; -error0: - xfs_perag_put(args->pag); - return error; +} + +/* + * Iterate from the AGs from the start AG to the end of the filesystem, trying + * to allocate blocks. It starts with a near allocation attempt in the initial + * AG, then falls back to anywhere-in-ag after the first AG fails. It will wrap + * back to zero if allowed by previous allocations in this transaction, + * otherwise will wrap back to the start AG and run a second blocking pass to + * the end of the filesystem. + */ +int +xfs_alloc_vextent_start_ag( + struct xfs_alloc_arg *args, + xfs_fsblock_t target) +{ + struct xfs_mount *mp = args->mp; + xfs_agnumber_t minimum_agno; + xfs_agnumber_t start_agno; + xfs_agnumber_t rotorstep = xfs_rotorstep; + bool bump_rotor = false; + uint32_t alloc_flags = XFS_ALLOC_FLAG_TRYLOCK; + int error; + + ASSERT(args->pag == NULL); + + args->agno = NULLAGNUMBER; + args->agbno = NULLAGBLOCK; + + trace_xfs_alloc_vextent_start_ag(args); + + error = xfs_alloc_vextent_check_args(args, target, &minimum_agno); + if (error) { + if (error == -ENOSPC) + return 0; + return error; + } + + if ((args->datatype & XFS_ALLOC_INITIAL_USER_DATA) && + xfs_is_inode32(mp)) { + target = XFS_AGB_TO_FSB(mp, + ((mp->m_agfrotor / rotorstep) % + mp->m_sb.sb_agcount), 0); + bump_rotor = 1; + } + + start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target)); + error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno, + XFS_FSB_TO_AGBNO(mp, target), alloc_flags); + + if (bump_rotor) { + if (args->agno == start_agno) + mp->m_agfrotor = (mp->m_agfrotor + 1) % + (mp->m_sb.sb_agcount * rotorstep); + else + mp->m_agfrotor = (args->agno * rotorstep + 1) % + (mp->m_sb.sb_agcount * rotorstep); + } + + return xfs_alloc_vextent_finish(args, minimum_agno, error, true); +} + +/* + * Iterate from the agno indicated via @target through to the end of the + * filesystem attempting blocking allocation. This does not wrap or try a second + * pass, so will not recurse into AGs lower than indicated by the target. + */ +int +xfs_alloc_vextent_first_ag( + struct xfs_alloc_arg *args, + xfs_fsblock_t target) + { + struct xfs_mount *mp = args->mp; + xfs_agnumber_t minimum_agno; + xfs_agnumber_t start_agno; + uint32_t alloc_flags = XFS_ALLOC_FLAG_TRYLOCK; + int error; + + ASSERT(args->pag == NULL); + + args->agno = NULLAGNUMBER; + args->agbno = NULLAGBLOCK; + + trace_xfs_alloc_vextent_first_ag(args); + + error = xfs_alloc_vextent_check_args(args, target, &minimum_agno); + if (error) { + if (error == -ENOSPC) + return 0; + return error; + } + + start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target)); + error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno, + XFS_FSB_TO_AGBNO(mp, target), alloc_flags); + return xfs_alloc_vextent_finish(args, minimum_agno, error, true); +} + +/* + * Allocate at the exact block target or fail. Caller is expected to hold a + * perag reference in args->pag. + */ +int +xfs_alloc_vextent_exact_bno( + struct xfs_alloc_arg *args, + xfs_fsblock_t target) +{ + struct xfs_mount *mp = args->mp; + xfs_agnumber_t minimum_agno; + int error; + + ASSERT(args->pag != NULL); + ASSERT(pag_agno(args->pag) == XFS_FSB_TO_AGNO(mp, target)); + + args->agno = XFS_FSB_TO_AGNO(mp, target); + args->agbno = XFS_FSB_TO_AGBNO(mp, target); + + trace_xfs_alloc_vextent_exact_bno(args); + + error = xfs_alloc_vextent_check_args(args, target, &minimum_agno); + if (error) { + if (error == -ENOSPC) + return 0; + return error; + } + + error = xfs_alloc_vextent_prepare_ag(args, 0); + if (!error && args->agbp) + error = xfs_alloc_ag_vextent_exact(args); + + return xfs_alloc_vextent_finish(args, minimum_agno, error, false); +} + +/* + * Allocate an extent as close to the target as possible. If there are not + * viable candidates in the AG, then fail the allocation. + * + * Caller may or may not have a per-ag reference in args->pag. + */ +int +xfs_alloc_vextent_near_bno( + struct xfs_alloc_arg *args, + xfs_fsblock_t target) +{ + struct xfs_mount *mp = args->mp; + xfs_agnumber_t minimum_agno; + bool needs_perag = args->pag == NULL; + uint32_t alloc_flags = 0; + int error; + + if (!needs_perag) + ASSERT(pag_agno(args->pag) == XFS_FSB_TO_AGNO(mp, target)); + + args->agno = XFS_FSB_TO_AGNO(mp, target); + args->agbno = XFS_FSB_TO_AGBNO(mp, target); + + trace_xfs_alloc_vextent_near_bno(args); + + error = xfs_alloc_vextent_check_args(args, target, &minimum_agno); + if (error) { + if (error == -ENOSPC) + return 0; + return error; + } + + if (needs_perag) + args->pag = xfs_perag_grab(mp, args->agno); + + error = xfs_alloc_vextent_prepare_ag(args, alloc_flags); + if (!error && args->agbp) + error = xfs_alloc_ag_vextent_near(args, alloc_flags); + + return xfs_alloc_vextent_finish(args, minimum_agno, error, needs_perag); } /* Ensure that the freelist is at full capacity. */ @@ -3355,7 +3977,7 @@ xfs_free_extent_fix_freelist( memset(&args, 0, sizeof(struct xfs_alloc_arg)); args.tp = tp; args.mp = tp->t_mountp; - args.agno = pag->pag_agno; + args.agno = pag_agno(pag); args.pag = pag; /* @@ -3381,7 +4003,8 @@ xfs_free_extent_fix_freelist( int __xfs_free_extent( struct xfs_trans *tp, - xfs_fsblock_t bno, + struct xfs_perag *pag, + xfs_agblock_t agbno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type, @@ -3389,51 +4012,49 @@ __xfs_free_extent( { struct xfs_mount *mp = tp->t_mountp; struct xfs_buf *agbp; - xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, bno); - xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp, bno); struct xfs_agf *agf; int error; unsigned int busy_flags = 0; - struct xfs_perag *pag; ASSERT(len != 0); ASSERT(type != XFS_AG_RESV_AGFL); - if (XFS_TEST_ERROR(false, mp, - XFS_ERRTAG_FREE_EXTENT)) + if (XFS_TEST_ERROR(mp, XFS_ERRTAG_FREE_EXTENT)) return -EIO; - pag = xfs_perag_get(mp, agno); error = xfs_free_extent_fix_freelist(tp, pag, &agbp); - if (error) - goto err; + if (error) { + if (xfs_metadata_is_sick(error)) + xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT); + return error; + } + agf = agbp->b_addr; if (XFS_IS_CORRUPT(mp, agbno >= mp->m_sb.sb_agblocks)) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT); error = -EFSCORRUPTED; goto err_release; } /* validate the extent size is legal now we have the agf locked */ if (XFS_IS_CORRUPT(mp, agbno + len > be32_to_cpu(agf->agf_length))) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT); error = -EFSCORRUPTED; goto err_release; } - error = xfs_free_ag_extent(tp, agbp, agno, agbno, len, oinfo, type); + error = xfs_free_ag_extent(tp, agbp, agbno, len, oinfo, type); if (error) goto err_release; if (skip_discard) busy_flags |= XFS_EXTENT_BUSY_SKIP_DISCARD; - xfs_extent_busy_insert(tp, pag, agbno, len, busy_flags); - xfs_perag_put(pag); + xfs_extent_busy_insert(tp, pag_group(pag), agbno, len, busy_flags); return 0; err_release: xfs_trans_brelse(tp, agbp); -err: - xfs_perag_put(pag); return error; } @@ -3451,9 +4072,13 @@ xfs_alloc_query_range_helper( { struct xfs_alloc_query_range_info *query = priv; struct xfs_alloc_rec_incore irec; + xfs_failaddr_t fa; + + xfs_alloc_btrec_to_irec(rec, &irec); + fa = xfs_alloc_check_irec(to_perag(cur->bc_group), &irec); + if (fa) + return xfs_alloc_complain_bad_rec(cur, fa, &irec); - irec.ar_startblock = be32_to_cpu(rec->alloc.ar_startblock); - irec.ar_blockcount = be32_to_cpu(rec->alloc.ar_blockcount); return query->fn(cur, &irec, query->priv); } @@ -3466,15 +4091,11 @@ xfs_alloc_query_range( xfs_alloc_query_range_fn fn, void *priv) { - union xfs_btree_irec low_brec; - union xfs_btree_irec high_brec; - struct xfs_alloc_query_range_info query; + union xfs_btree_irec low_brec = { .a = *low_rec }; + union xfs_btree_irec high_brec = { .a = *high_rec }; + struct xfs_alloc_query_range_info query = { .priv = priv, .fn = fn }; - ASSERT(cur->bc_btnum == XFS_BTNUM_BNO); - low_brec.a = *low_rec; - high_brec.a = *high_rec; - query.priv = priv; - query.fn = fn; + ASSERT(xfs_btree_is_bno(cur->bc_ops)); return xfs_btree_query_range(cur, &low_brec, &high_brec, xfs_alloc_query_range_helper, &query); } @@ -3488,19 +4109,22 @@ xfs_alloc_query_all( { struct xfs_alloc_query_range_info query; - ASSERT(cur->bc_btnum == XFS_BTNUM_BNO); + ASSERT(xfs_btree_is_bno(cur->bc_ops)); query.priv = priv; query.fn = fn; return xfs_btree_query_all(cur, xfs_alloc_query_range_helper, &query); } -/* Is there a record covering a given extent? */ +/* + * Scan part of the keyspace of the free space and tell us if the area has no + * records, is fully mapped by records, or is partially filled. + */ int -xfs_alloc_has_record( +xfs_alloc_has_records( struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, - bool *exists) + enum xbtree_recpacking *outcome) { union xfs_btree_irec low; union xfs_btree_irec high; @@ -3510,7 +4134,7 @@ xfs_alloc_has_record( memset(&high, 0xFF, sizeof(high)); high.a.ar_startblock = bno + len - 1; - return xfs_btree_has_record(cur, &low, &high, exists); + return xfs_btree_has_records(cur, &low, &high, NULL, outcome); } /* diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 2c3f762dfb58..50ef79a1ed41 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -17,32 +17,14 @@ extern struct workqueue_struct *xfs_alloc_wq; unsigned int xfs_agfl_size(struct xfs_mount *mp); /* - * Freespace allocation types. Argument to xfs_alloc_[v]extent. - */ -#define XFS_ALLOCTYPE_FIRST_AG 0x02 /* ... start at ag 0 */ -#define XFS_ALLOCTYPE_THIS_AG 0x08 /* anywhere in this a.g. */ -#define XFS_ALLOCTYPE_START_BNO 0x10 /* near this block else anywhere */ -#define XFS_ALLOCTYPE_NEAR_BNO 0x20 /* in this a.g. and near this block */ -#define XFS_ALLOCTYPE_THIS_BNO 0x40 /* at exactly this block */ - -/* this should become an enum again when the tracing code is fixed */ -typedef unsigned int xfs_alloctype_t; - -#define XFS_ALLOC_TYPES \ - { XFS_ALLOCTYPE_FIRST_AG, "FIRST_AG" }, \ - { XFS_ALLOCTYPE_THIS_AG, "THIS_AG" }, \ - { XFS_ALLOCTYPE_START_BNO, "START_BNO" }, \ - { XFS_ALLOCTYPE_NEAR_BNO, "NEAR_BNO" }, \ - { XFS_ALLOCTYPE_THIS_BNO, "THIS_BNO" } - -/* * Flags for xfs_alloc_fix_freelist. */ -#define XFS_ALLOC_FLAG_TRYLOCK 0x00000001 /* use trylock for buffer locking */ -#define XFS_ALLOC_FLAG_FREEING 0x00000002 /* indicate caller is freeing extents*/ -#define XFS_ALLOC_FLAG_NORMAP 0x00000004 /* don't modify the rmapbt */ -#define XFS_ALLOC_FLAG_NOSHRINK 0x00000008 /* don't shrink the freelist */ -#define XFS_ALLOC_FLAG_CHECK 0x00000010 /* test only, don't modify args */ +#define XFS_ALLOC_FLAG_TRYLOCK (1U << 0) /* use trylock for buffer locking */ +#define XFS_ALLOC_FLAG_FREEING (1U << 1) /* indicate caller is freeing extents*/ +#define XFS_ALLOC_FLAG_NORMAP (1U << 2) /* don't modify the rmapbt */ +#define XFS_ALLOC_FLAG_NOSHRINK (1U << 3) /* don't shrink the freelist */ +#define XFS_ALLOC_FLAG_CHECK (1U << 4) /* test only, don't modify args */ +#define XFS_ALLOC_FLAG_TRYFLUSH (1U << 5) /* don't wait in busy extent flush */ /* * Argument structure for xfs_alloc routines. @@ -68,16 +50,12 @@ typedef struct xfs_alloc_arg { xfs_agblock_t min_agbno; /* set an agbno range for NEAR allocs */ xfs_agblock_t max_agbno; /* ... */ xfs_extlen_t len; /* output: actual size of extent */ - xfs_alloctype_t type; /* allocation type XFS_ALLOCTYPE_... */ - xfs_alloctype_t otype; /* original allocation type */ int datatype; /* mask defining data type treatment */ char wasdel; /* set if allocation was prev delayed */ char wasfromfl; /* set if allocation is from freelist */ + bool alloc_minlen_only; /* allocate exact minlen extent */ struct xfs_owner_info oinfo; /* owner of blocks being allocated */ enum xfs_ag_resv_type resv; /* block reservation to use */ -#ifdef DEBUG - bool alloc_minlen_only; /* allocate exact minlen extent */ -#endif } xfs_alloc_arg_t; /* @@ -100,6 +78,9 @@ int xfs_alloc_get_freelist(struct xfs_perag *pag, struct xfs_trans *tp, int xfs_alloc_put_freelist(struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agfbp, struct xfs_buf *agflbp, xfs_agblock_t bno, int btreeblk); +int xfs_free_ag_extent(struct xfs_trans *tp, struct xfs_buf *agbp, + xfs_agblock_t bno, xfs_extlen_t len, + const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type); /* * Compute and fill in value of m_alloc_maxlevels. @@ -118,11 +99,43 @@ xfs_alloc_log_agf( uint32_t fields);/* mask of fields to be logged (XFS_AGF_...) */ /* - * Allocate an extent (variable-size). + * Allocate an extent anywhere in the specific AG given. If there is no + * space matching the requirements in that AG, then the allocation will fail. */ -int /* error */ -xfs_alloc_vextent( - xfs_alloc_arg_t *args); /* allocation argument structure */ +int xfs_alloc_vextent_this_ag(struct xfs_alloc_arg *args, xfs_agnumber_t agno); + +/* + * Allocate an extent as close to the target as possible. If there are not + * viable candidates in the AG, then fail the allocation. + */ +int xfs_alloc_vextent_near_bno(struct xfs_alloc_arg *args, + xfs_fsblock_t target); + +/* + * Allocate an extent exactly at the target given. If this is not possible + * then the allocation fails. + */ +int xfs_alloc_vextent_exact_bno(struct xfs_alloc_arg *args, + xfs_fsblock_t target); + +/* + * Best effort full filesystem allocation scan. + * + * Locality aware allocation will be attempted in the initial AG, but on failure + * non-localised attempts will be made. The AGs are constrained by previous + * allocations in the current transaction. Two passes will be made - the first + * non-blocking, the second blocking. + */ +int xfs_alloc_vextent_start_ag(struct xfs_alloc_arg *args, + xfs_fsblock_t target); + +/* + * Iterate from the AG indicated from args->fsbno through to the end of the + * filesystem attempting blocking allocation. This is for use in last + * resort allocation attempts when everything else has failed. + */ +int xfs_alloc_vextent_first_ag(struct xfs_alloc_arg *args, + xfs_fsblock_t target); /* * Free an extent. @@ -130,7 +143,8 @@ xfs_alloc_vextent( int /* error */ __xfs_free_extent( struct xfs_trans *tp, /* transaction pointer */ - xfs_fsblock_t bno, /* starting block number of extent */ + struct xfs_perag *pag, + xfs_agblock_t agbno, xfs_extlen_t len, /* length of extent */ const struct xfs_owner_info *oinfo, /* extent owner */ enum xfs_ag_resv_type type, /* block reservation type */ @@ -139,12 +153,13 @@ __xfs_free_extent( static inline int xfs_free_extent( struct xfs_trans *tp, - xfs_fsblock_t bno, + struct xfs_perag *pag, + xfs_agblock_t agbno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type) { - return __xfs_free_extent(tp, bno, len, oinfo, type, false); + return __xfs_free_extent(tp, pag, agbno, len, oinfo, type, false); } int /* error */ @@ -168,15 +183,19 @@ xfs_alloc_get_rec( xfs_extlen_t *len, /* output: length of extent */ int *stat); /* output: success/failure */ +union xfs_btree_rec; +void xfs_alloc_btrec_to_irec(const union xfs_btree_rec *rec, + struct xfs_alloc_rec_incore *irec); +xfs_failaddr_t xfs_alloc_check_irec(struct xfs_perag *pag, + const struct xfs_alloc_rec_incore *irec); + int xfs_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags, struct xfs_buf **agfbpp); int xfs_alloc_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags, struct xfs_buf **agfbpp); int xfs_alloc_read_agfl(struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf **bpp); -int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t, - struct xfs_buf *, struct xfs_owner_info *); -int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags); +int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, uint32_t alloc_flags); int xfs_free_extent_fix_freelist(struct xfs_trans *tp, struct xfs_perag *pag, struct xfs_buf **agbp); @@ -194,8 +213,8 @@ int xfs_alloc_query_range(struct xfs_btree_cur *cur, int xfs_alloc_query_all(struct xfs_btree_cur *cur, xfs_alloc_query_range_fn fn, void *priv); -int xfs_alloc_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno, - xfs_extlen_t len, bool *exist); +int xfs_alloc_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno, + xfs_extlen_t len, enum xbtree_recpacking *outcome); typedef int (*xfs_agfl_walk_fn)(struct xfs_mount *mp, xfs_agblock_t bno, void *priv); @@ -211,9 +230,18 @@ xfs_buf_to_agfl_bno( return bp->b_addr; } -void __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, +int xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, - bool skip_discard); + enum xfs_ag_resv_type type, unsigned int free_flags); + +/* Don't issue a discard for the blocks freed. */ +#define XFS_FREE_EXTENT_SKIP_DISCARD (1U << 0) + +/* Free blocks on the realtime device. */ +#define XFS_FREE_EXTENT_REALTIME (1U << 1) + +#define XFS_FREE_EXTENT_ALL_FLAGS (XFS_FREE_EXTENT_SKIP_DISCARD | \ + XFS_FREE_EXTENT_REALTIME) /* * List of extents to be free "later". @@ -224,27 +252,39 @@ struct xfs_extent_free_item { uint64_t xefi_owner; xfs_fsblock_t xefi_startblock;/* starting fs block number */ xfs_extlen_t xefi_blockcount;/* number of blocks in extent */ + struct xfs_group *xefi_group; unsigned int xefi_flags; + enum xfs_ag_resv_type xefi_agresv; }; #define XFS_EFI_SKIP_DISCARD (1U << 0) /* don't issue discard */ #define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */ #define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */ +#define XFS_EFI_CANCELLED (1U << 3) /* dont actually free the space */ +#define XFS_EFI_REALTIME (1U << 4) /* freeing realtime extent */ -static inline void -xfs_free_extent_later( - struct xfs_trans *tp, - xfs_fsblock_t bno, - xfs_filblks_t len, - const struct xfs_owner_info *oinfo) +static inline bool xfs_efi_is_realtime(const struct xfs_extent_free_item *xefi) { - __xfs_free_extent_later(tp, bno, len, oinfo, false); + return xefi->xefi_flags & XFS_EFI_REALTIME; } +struct xfs_alloc_autoreap { + struct xfs_defer_pending *dfp; +}; + +int xfs_alloc_schedule_autoreap(const struct xfs_alloc_arg *args, + unsigned int free_flags, struct xfs_alloc_autoreap *aarp); +void xfs_alloc_cancel_autoreap(struct xfs_trans *tp, + struct xfs_alloc_autoreap *aarp); +void xfs_alloc_commit_autoreap(struct xfs_trans *tp, + struct xfs_alloc_autoreap *aarp); extern struct kmem_cache *xfs_extfree_item_cache; int __init xfs_extfree_intent_init_cache(void); void xfs_extfree_intent_destroy_cache(void); +xfs_failaddr_t xfs_validate_ag_length(struct xfs_buf *bp, uint32_t seqno, + uint32_t length); + #endif /* __XFS_ALLOC_H__ */ diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index 549a3cba0234..fa1f03c1331e 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -16,6 +16,7 @@ #include "xfs_alloc.h" #include "xfs_extent_busy.h" #include "xfs_error.h" +#include "xfs_health.h" #include "xfs_trace.h" #include "xfs_trans.h" #include "xfs_ag.h" @@ -23,11 +24,19 @@ static struct kmem_cache *xfs_allocbt_cur_cache; STATIC struct xfs_btree_cur * -xfs_allocbt_dup_cursor( +xfs_bnobt_dup_cursor( struct xfs_btree_cur *cur) { - return xfs_allocbt_init_cursor(cur->bc_mp, cur->bc_tp, - cur->bc_ag.agbp, cur->bc_ag.pag, cur->bc_btnum); + return xfs_bnobt_init_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ag.agbp, + to_perag(cur->bc_group)); +} + +STATIC struct xfs_btree_cur * +xfs_cntbt_dup_cursor( + struct xfs_btree_cur *cur) +{ + return xfs_cntbt_init_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ag.agbp, + to_perag(cur->bc_group)); } STATIC void @@ -36,15 +45,21 @@ xfs_allocbt_set_root( const union xfs_btree_ptr *ptr, int inc) { - struct xfs_buf *agbp = cur->bc_ag.agbp; - struct xfs_agf *agf = agbp->b_addr; - int btnum = cur->bc_btnum; + struct xfs_perag *pag = to_perag(cur->bc_group); + struct xfs_buf *agbp = cur->bc_ag.agbp; + struct xfs_agf *agf = agbp->b_addr; ASSERT(ptr->s != 0); - agf->agf_roots[btnum] = ptr->s; - be32_add_cpu(&agf->agf_levels[btnum], inc); - cur->bc_ag.pag->pagf_levels[btnum] += inc; + if (xfs_btree_is_bno(cur->bc_ops)) { + agf->agf_bno_root = ptr->s; + be32_add_cpu(&agf->agf_bno_level, inc); + pag->pagf_bno_level += inc; + } else { + agf->agf_cnt_root = ptr->s; + be32_add_cpu(&agf->agf_cnt_level, inc); + pag->pagf_cnt_level += inc; + } xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS); } @@ -60,7 +75,7 @@ xfs_allocbt_alloc_block( xfs_agblock_t bno; /* Allocate the new block from the freelist. If we can't, give up. */ - error = xfs_alloc_get_freelist(cur->bc_ag.pag, cur->bc_tp, + error = xfs_alloc_get_freelist(to_perag(cur->bc_group), cur->bc_tp, cur->bc_ag.agbp, &bno, 1); if (error) return error; @@ -71,7 +86,7 @@ xfs_allocbt_alloc_block( } atomic64_inc(&cur->bc_mp->m_allocbt_blks); - xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.pag, bno, 1, false); + xfs_extent_busy_reuse(cur->bc_group, bno, 1, false); new->s = cpu_to_be32(bno); @@ -89,78 +104,17 @@ xfs_allocbt_free_block( int error; bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp)); - error = xfs_alloc_put_freelist(cur->bc_ag.pag, cur->bc_tp, agbp, NULL, - bno, 1); + error = xfs_alloc_put_freelist(to_perag(cur->bc_group), cur->bc_tp, + agbp, NULL, bno, 1); if (error) return error; atomic64_dec(&cur->bc_mp->m_allocbt_blks); - xfs_extent_busy_insert(cur->bc_tp, agbp->b_pag, bno, 1, + xfs_extent_busy_insert(cur->bc_tp, pag_group(agbp->b_pag), bno, 1, XFS_EXTENT_BUSY_SKIP_DISCARD); return 0; } -/* - * Update the longest extent in the AGF - */ -STATIC void -xfs_allocbt_update_lastrec( - struct xfs_btree_cur *cur, - const struct xfs_btree_block *block, - const union xfs_btree_rec *rec, - int ptr, - int reason) -{ - struct xfs_agf *agf = cur->bc_ag.agbp->b_addr; - struct xfs_perag *pag; - __be32 len; - int numrecs; - - ASSERT(cur->bc_btnum == XFS_BTNUM_CNT); - - switch (reason) { - case LASTREC_UPDATE: - /* - * If this is the last leaf block and it's the last record, - * then update the size of the longest extent in the AG. - */ - if (ptr != xfs_btree_get_numrecs(block)) - return; - len = rec->alloc.ar_blockcount; - break; - case LASTREC_INSREC: - if (be32_to_cpu(rec->alloc.ar_blockcount) <= - be32_to_cpu(agf->agf_longest)) - return; - len = rec->alloc.ar_blockcount; - break; - case LASTREC_DELREC: - numrecs = xfs_btree_get_numrecs(block); - if (ptr <= numrecs) - return; - ASSERT(ptr == numrecs + 1); - - if (numrecs) { - xfs_alloc_rec_t *rrp; - - rrp = XFS_ALLOC_REC_ADDR(cur->bc_mp, block, numrecs); - len = rrp->ar_blockcount; - } else { - len = 0; - } - - break; - default: - ASSERT(0); - return; - } - - agf->agf_longest = len; - pag = cur->bc_ag.agbp->b_pag; - pag->pagf_longest = be32_to_cpu(len); - xfs_alloc_log_agf(cur->bc_tp, cur->bc_ag.agbp, XFS_AGF_LONGEST); -} - STATIC int xfs_allocbt_get_minrecs( struct xfs_btree_cur *cur, @@ -224,63 +178,65 @@ xfs_allocbt_init_ptr_from_cur( { struct xfs_agf *agf = cur->bc_ag.agbp->b_addr; - ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno)); + ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agf->agf_seqno)); - ptr->s = agf->agf_roots[cur->bc_btnum]; + if (xfs_btree_is_bno(cur->bc_ops)) + ptr->s = agf->agf_bno_root; + else + ptr->s = agf->agf_cnt_root; } -STATIC int64_t -xfs_bnobt_key_diff( +STATIC int +xfs_bnobt_cmp_key_with_cur( struct xfs_btree_cur *cur, const union xfs_btree_key *key) { struct xfs_alloc_rec_incore *rec = &cur->bc_rec.a; const struct xfs_alloc_rec *kp = &key->alloc; - return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock; + return cmp_int(be32_to_cpu(kp->ar_startblock), + rec->ar_startblock); } -STATIC int64_t -xfs_cntbt_key_diff( +STATIC int +xfs_cntbt_cmp_key_with_cur( struct xfs_btree_cur *cur, const union xfs_btree_key *key) { struct xfs_alloc_rec_incore *rec = &cur->bc_rec.a; const struct xfs_alloc_rec *kp = &key->alloc; - int64_t diff; - diff = (int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount; - if (diff) - return diff; - - return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock; + return cmp_int(be32_to_cpu(kp->ar_blockcount), rec->ar_blockcount) ?: + cmp_int(be32_to_cpu(kp->ar_startblock), rec->ar_startblock); } -STATIC int64_t -xfs_bnobt_diff_two_keys( +STATIC int +xfs_bnobt_cmp_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { - return (int64_t)be32_to_cpu(k1->alloc.ar_startblock) - - be32_to_cpu(k2->alloc.ar_startblock); + ASSERT(!mask || mask->alloc.ar_startblock); + + return cmp_int(be32_to_cpu(k1->alloc.ar_startblock), + be32_to_cpu(k2->alloc.ar_startblock)); } -STATIC int64_t -xfs_cntbt_diff_two_keys( +STATIC int +xfs_cntbt_cmp_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { - int64_t diff; - - diff = be32_to_cpu(k1->alloc.ar_blockcount) - - be32_to_cpu(k2->alloc.ar_blockcount); - if (diff) - return diff; + ASSERT(!mask || (mask->alloc.ar_blockcount && + mask->alloc.ar_startblock)); - return be32_to_cpu(k1->alloc.ar_startblock) - - be32_to_cpu(k2->alloc.ar_startblock); + return cmp_int(be32_to_cpu(k1->alloc.ar_blockcount), + be32_to_cpu(k2->alloc.ar_blockcount)) ?: + cmp_int(be32_to_cpu(k1->alloc.ar_startblock), + be32_to_cpu(k2->alloc.ar_startblock)); } static xfs_failaddr_t @@ -292,13 +248,12 @@ xfs_allocbt_verify( struct xfs_perag *pag = bp->b_pag; xfs_failaddr_t fa; unsigned int level; - xfs_btnum_t btnum = XFS_BTNUM_BNOi; if (!xfs_verify_magic(bp, block->bb_magic)) return __this_address; if (xfs_has_crc(mp)) { - fa = xfs_btree_sblock_v5hdr_verify(bp); + fa = xfs_btree_agblock_v5hdr_verify(bp); if (fa) return fa; } @@ -313,15 +268,32 @@ xfs_allocbt_verify( * against. */ level = be16_to_cpu(block->bb_level); - if (bp->b_ops->magic[0] == cpu_to_be32(XFS_ABTC_MAGIC)) - btnum = XFS_BTNUM_CNTi; - if (pag && pag->pagf_init) { - if (level >= pag->pagf_levels[btnum]) + if (pag && xfs_perag_initialised_agf(pag)) { + unsigned int maxlevel, repair_maxlevel = 0; + + /* + * Online repair could be rewriting the free space btrees, so + * we'll validate against the larger of either tree while this + * is going on. + */ + if (bp->b_ops->magic[0] == cpu_to_be32(XFS_ABTC_MAGIC)) { + maxlevel = pag->pagf_cnt_level; +#ifdef CONFIG_XFS_ONLINE_REPAIR + repair_maxlevel = pag->pagf_repair_cnt_level; +#endif + } else { + maxlevel = pag->pagf_bno_level; +#ifdef CONFIG_XFS_ONLINE_REPAIR + repair_maxlevel = pag->pagf_repair_bno_level; +#endif + } + + if (level >= max(maxlevel, repair_maxlevel)) return __this_address; } else if (level >= mp->m_alloc_maxlevels) return __this_address; - return xfs_btree_sblock_verify(bp, mp->m_alloc_mxr[level != 0]); + return xfs_btree_agblock_verify(bp, mp->m_alloc_mxr[level != 0]); } static void @@ -330,7 +302,7 @@ xfs_allocbt_read_verify( { xfs_failaddr_t fa; - if (!xfs_btree_sblock_verify_crc(bp)) + if (!xfs_btree_agblock_verify_crc(bp)) xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_allocbt_verify(bp); @@ -354,7 +326,7 @@ xfs_allocbt_write_verify( xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } - xfs_btree_sblock_calc_crc(bp); + xfs_btree_agblock_calc_crc(bp); } @@ -423,122 +395,128 @@ xfs_cntbt_recs_inorder( be32_to_cpu(r2->alloc.ar_startblock)); } -static const struct xfs_btree_ops xfs_bnobt_ops = { +STATIC enum xbtree_key_contig +xfs_allocbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->alloc.ar_startblock); + + return xbtree_key_contig(be32_to_cpu(key1->alloc.ar_startblock), + be32_to_cpu(key2->alloc.ar_startblock)); +} + +const struct xfs_btree_ops xfs_bnobt_ops = { + .name = "bno", + .type = XFS_BTREE_TYPE_AG, + .rec_len = sizeof(xfs_alloc_rec_t), .key_len = sizeof(xfs_alloc_key_t), + .ptr_len = XFS_BTREE_SHORT_PTR_LEN, + + .lru_refs = XFS_ALLOC_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_abtb_2), + .sick_mask = XFS_SICK_AG_BNOBT, - .dup_cursor = xfs_allocbt_dup_cursor, + .dup_cursor = xfs_bnobt_dup_cursor, .set_root = xfs_allocbt_set_root, .alloc_block = xfs_allocbt_alloc_block, .free_block = xfs_allocbt_free_block, - .update_lastrec = xfs_allocbt_update_lastrec, .get_minrecs = xfs_allocbt_get_minrecs, .get_maxrecs = xfs_allocbt_get_maxrecs, .init_key_from_rec = xfs_allocbt_init_key_from_rec, .init_high_key_from_rec = xfs_bnobt_init_high_key_from_rec, .init_rec_from_cur = xfs_allocbt_init_rec_from_cur, .init_ptr_from_cur = xfs_allocbt_init_ptr_from_cur, - .key_diff = xfs_bnobt_key_diff, + .cmp_key_with_cur = xfs_bnobt_cmp_key_with_cur, .buf_ops = &xfs_bnobt_buf_ops, - .diff_two_keys = xfs_bnobt_diff_two_keys, + .cmp_two_keys = xfs_bnobt_cmp_two_keys, .keys_inorder = xfs_bnobt_keys_inorder, .recs_inorder = xfs_bnobt_recs_inorder, + .keys_contiguous = xfs_allocbt_keys_contiguous, }; -static const struct xfs_btree_ops xfs_cntbt_ops = { +const struct xfs_btree_ops xfs_cntbt_ops = { + .name = "cnt", + .type = XFS_BTREE_TYPE_AG, + .rec_len = sizeof(xfs_alloc_rec_t), .key_len = sizeof(xfs_alloc_key_t), + .ptr_len = XFS_BTREE_SHORT_PTR_LEN, - .dup_cursor = xfs_allocbt_dup_cursor, + .lru_refs = XFS_ALLOC_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_abtc_2), + .sick_mask = XFS_SICK_AG_CNTBT, + + .dup_cursor = xfs_cntbt_dup_cursor, .set_root = xfs_allocbt_set_root, .alloc_block = xfs_allocbt_alloc_block, .free_block = xfs_allocbt_free_block, - .update_lastrec = xfs_allocbt_update_lastrec, .get_minrecs = xfs_allocbt_get_minrecs, .get_maxrecs = xfs_allocbt_get_maxrecs, .init_key_from_rec = xfs_allocbt_init_key_from_rec, .init_high_key_from_rec = xfs_cntbt_init_high_key_from_rec, .init_rec_from_cur = xfs_allocbt_init_rec_from_cur, .init_ptr_from_cur = xfs_allocbt_init_ptr_from_cur, - .key_diff = xfs_cntbt_key_diff, + .cmp_key_with_cur = xfs_cntbt_cmp_key_with_cur, .buf_ops = &xfs_cntbt_buf_ops, - .diff_two_keys = xfs_cntbt_diff_two_keys, + .cmp_two_keys = xfs_cntbt_cmp_two_keys, .keys_inorder = xfs_cntbt_keys_inorder, .recs_inorder = xfs_cntbt_recs_inorder, + .keys_contiguous = NULL, /* not needed right now */ }; -/* Allocate most of a new allocation btree cursor. */ -STATIC struct xfs_btree_cur * -xfs_allocbt_init_common( +/* + * Allocate a new bnobt cursor. + * + * For staging cursors tp and agbp are NULL. + */ +struct xfs_btree_cur * +xfs_bnobt_init_cursor( struct xfs_mount *mp, struct xfs_trans *tp, - struct xfs_perag *pag, - xfs_btnum_t btnum) + struct xfs_buf *agbp, + struct xfs_perag *pag) { struct xfs_btree_cur *cur; - ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT); - - cur = xfs_btree_alloc_cursor(mp, tp, btnum, mp->m_alloc_maxlevels, - xfs_allocbt_cur_cache); - cur->bc_ag.abt.active = false; + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_bnobt_ops, + mp->m_alloc_maxlevels, xfs_allocbt_cur_cache); + cur->bc_group = xfs_group_hold(pag_group(pag)); + cur->bc_ag.agbp = agbp; + if (agbp) { + struct xfs_agf *agf = agbp->b_addr; - if (btnum == XFS_BTNUM_CNT) { - cur->bc_ops = &xfs_cntbt_ops; - cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2); - cur->bc_flags = XFS_BTREE_LASTREC_UPDATE; - } else { - cur->bc_ops = &xfs_bnobt_ops; - cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2); + cur->bc_nlevels = be32_to_cpu(agf->agf_bno_level); } - - /* take a reference for the cursor */ - atomic_inc(&pag->pag_ref); - cur->bc_ag.pag = pag; - - if (xfs_has_crc(mp)) - cur->bc_flags |= XFS_BTREE_CRC_BLOCKS; - return cur; } /* - * Allocate a new allocation btree cursor. + * Allocate a new cntbt cursor. + * + * For staging cursors tp and agbp are NULL. */ -struct xfs_btree_cur * /* new alloc btree cursor */ -xfs_allocbt_init_cursor( - struct xfs_mount *mp, /* file system mount point */ - struct xfs_trans *tp, /* transaction pointer */ - struct xfs_buf *agbp, /* buffer for agf structure */ - struct xfs_perag *pag, - xfs_btnum_t btnum) /* btree identifier */ -{ - struct xfs_agf *agf = agbp->b_addr; - struct xfs_btree_cur *cur; - - cur = xfs_allocbt_init_common(mp, tp, pag, btnum); - if (btnum == XFS_BTNUM_CNT) - cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]); - else - cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]); - - cur->bc_ag.agbp = agbp; - - return cur; -} - -/* Create a free space btree cursor with a fake root for staging. */ struct xfs_btree_cur * -xfs_allocbt_stage_cursor( +xfs_cntbt_init_cursor( struct xfs_mount *mp, - struct xbtree_afakeroot *afake, - struct xfs_perag *pag, - xfs_btnum_t btnum) + struct xfs_trans *tp, + struct xfs_buf *agbp, + struct xfs_perag *pag) { struct xfs_btree_cur *cur; - cur = xfs_allocbt_init_common(mp, NULL, pag, btnum); - xfs_btree_stage_afakeroot(cur, afake); + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_cntbt_ops, + mp->m_alloc_maxlevels, xfs_allocbt_cur_cache); + cur->bc_group = xfs_group_hold(pag_group(pag)); + cur->bc_ag.agbp = agbp; + if (agbp) { + struct xfs_agf *agf = agbp->b_addr; + + cur->bc_nlevels = be32_to_cpu(agf->agf_cnt_level); + } return cur; } @@ -557,16 +535,16 @@ xfs_allocbt_commit_staged_btree( ASSERT(cur->bc_flags & XFS_BTREE_STAGING); - agf->agf_roots[cur->bc_btnum] = cpu_to_be32(afake->af_root); - agf->agf_levels[cur->bc_btnum] = cpu_to_be32(afake->af_levels); - xfs_alloc_log_agf(tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS); - - if (cur->bc_btnum == XFS_BTNUM_BNO) { - xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_bnobt_ops); + if (xfs_btree_is_bno(cur->bc_ops)) { + agf->agf_bno_root = cpu_to_be32(afake->af_root); + agf->agf_bno_level = cpu_to_be32(afake->af_levels); } else { - cur->bc_flags |= XFS_BTREE_LASTREC_UPDATE; - xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_cntbt_ops); + agf->agf_cnt_root = cpu_to_be32(afake->af_root); + agf->agf_cnt_level = cpu_to_be32(afake->af_levels); } + xfs_alloc_log_agf(tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS); + + xfs_btree_commit_afakeroot(cur, tp, agbp); } /* Calculate number of records in an alloc btree block. */ @@ -583,11 +561,11 @@ xfs_allocbt_block_maxrecs( /* * Calculate number of records in an alloc btree block. */ -int +unsigned int xfs_allocbt_maxrecs( struct xfs_mount *mp, - int blocklen, - int leaf) + unsigned int blocklen, + bool leaf) { blocklen -= XFS_ALLOC_BLOCK_LEN(mp); return xfs_allocbt_block_maxrecs(blocklen, leaf); diff --git a/fs/xfs/libxfs/xfs_alloc_btree.h b/fs/xfs/libxfs/xfs_alloc_btree.h index 45df893ef6bb..12647f9aaa6d 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.h +++ b/fs/xfs/libxfs/xfs_alloc_btree.h @@ -47,13 +47,14 @@ struct xbtree_afakeroot; (maxrecs) * sizeof(xfs_alloc_key_t) + \ ((index) - 1) * sizeof(xfs_alloc_ptr_t))) -extern struct xfs_btree_cur *xfs_allocbt_init_cursor(struct xfs_mount *mp, +struct xfs_btree_cur *xfs_bnobt_init_cursor(struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_buf *bp, - struct xfs_perag *pag, xfs_btnum_t btnum); -struct xfs_btree_cur *xfs_allocbt_stage_cursor(struct xfs_mount *mp, - struct xbtree_afakeroot *afake, struct xfs_perag *pag, - xfs_btnum_t btnum); -extern int xfs_allocbt_maxrecs(struct xfs_mount *, int, int); + struct xfs_perag *pag); +struct xfs_btree_cur *xfs_cntbt_init_cursor(struct xfs_mount *mp, + struct xfs_trans *tp, struct xfs_buf *bp, + struct xfs_perag *pag); +unsigned int xfs_allocbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, + bool leaf); extern xfs_extlen_t xfs_allocbt_calc_size(struct xfs_mount *mp, unsigned long long len); diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index e28d93d232de..8c04acd30d48 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -26,6 +26,7 @@ #include "xfs_trace.h" #include "xfs_attr_item.h" #include "xfs_xattr.h" +#include "xfs_parent.h" struct kmem_cache *xfs_attr_intent_cache; @@ -50,7 +51,6 @@ STATIC int xfs_attr_shortform_addname(xfs_da_args_t *args); STATIC int xfs_attr_leaf_get(xfs_da_args_t *args); STATIC int xfs_attr_leaf_removename(xfs_da_args_t *args); STATIC int xfs_attr_leaf_hasname(struct xfs_da_args *args, struct xfs_buf **bp); -STATIC int xfs_attr_leaf_try_add(struct xfs_da_args *args); /* * Internal routines when attribute list is more than one block. @@ -87,6 +87,8 @@ xfs_attr_is_leaf( struct xfs_iext_cursor icur; struct xfs_bmbt_irec imap; + ASSERT(!xfs_need_iread_extents(ifp)); + if (ifp->if_nextents != 1 || ifp->if_format != XFS_DINODE_FMT_EXTENTS) return false; @@ -224,11 +226,21 @@ int xfs_attr_get_ilocked( struct xfs_da_args *args) { - ASSERT(xfs_isilocked(args->dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + int error; + + xfs_assert_ilocked(args->dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); if (!xfs_inode_hasattr(args->dp)) return -ENOATTR; + /* + * The incore attr fork iext tree must be loaded for xfs_attr_is_leaf + * to work correctly. + */ + error = xfs_iread_extents(args->trans, args->dp, XFS_ATTR_FORK); + if (error) + return error; + if (args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) return xfs_attr_shortform_getvalue(args); if (xfs_attr_is_leaf(args->dp)) @@ -264,9 +276,11 @@ xfs_attr_get( if (xfs_is_shutdown(args->dp->i_mount)) return -EIO; + if (!args->owner) + args->owner = args->dp->i_ino; args->geo = args->dp->i_mount->m_attr_geo; args->whichfork = XFS_ATTR_FORK; - args->hashval = xfs_da_hashname(args->name, args->namelen); + xfs_attr_sethash(args); /* Entirely possible to look up a name which doesn't exist */ args->op_flags = XFS_DA_OP_OKNOENT; @@ -314,26 +328,20 @@ xfs_attr_calc_size( return nblks; } -/* Initialize transaction reservation for attr operations */ -void -xfs_init_attr_trans( - struct xfs_da_args *args, - struct xfs_trans_res *tres, - unsigned int *total) +/* Initialize transaction reservation for an xattr set/replace/upsert */ +inline struct xfs_trans_res +xfs_attr_set_resv( + const struct xfs_da_args *args) { - struct xfs_mount *mp = args->dp->i_mount; - - if (args->value) { - tres->tr_logres = M_RES(mp)->tr_attrsetm.tr_logres + - M_RES(mp)->tr_attrsetrt.tr_logres * - args->total; - tres->tr_logcount = XFS_ATTRSET_LOG_COUNT; - tres->tr_logflags = XFS_TRANS_PERM_LOG_RES; - *total = args->total; - } else { - *tres = M_RES(mp)->tr_attrrm; - *total = XFS_ATTRRM_SPACE_RES(mp); - } + struct xfs_mount *mp = args->dp->i_mount; + struct xfs_trans_res ret = { + .tr_logres = M_RES(mp)->tr_attrsetm.tr_logres + + M_RES(mp)->tr_attrsetrt.tr_logres * args->total, + .tr_logcount = XFS_ATTRSET_LOG_COUNT, + .tr_logflags = XFS_TRANS_PERM_LOG_RES, + }; + + return ret; } /* @@ -363,7 +371,7 @@ xfs_attr_try_sf_addname( * Commit the shortform mods, and we're done. * NOTE: this is also the error path (EEXIST, etc). */ - if (!error && !(args->op_flags & XFS_DA_OP_NOTIME)) + if (!error) xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG); if (xfs_has_wsync(dp->i_mount)) @@ -401,6 +409,77 @@ out: return error; } +/* Compute the hash value for a user/root/secure extended attribute */ +xfs_dahash_t +xfs_attr_hashname( + const uint8_t *name, + int namelen) +{ + return xfs_da_hashname(name, namelen); +} + +/* Compute the hash value for any extended attribute from any namespace. */ +xfs_dahash_t +xfs_attr_hashval( + struct xfs_mount *mp, + unsigned int attr_flags, + const uint8_t *name, + int namelen, + const void *value, + int valuelen) +{ + ASSERT(xfs_attr_check_namespace(attr_flags)); + + if (attr_flags & XFS_ATTR_PARENT) + return xfs_parent_hashattr(mp, name, namelen, value, valuelen); + + return xfs_attr_hashname(name, namelen); +} + +/* Save the current remote block info and clear the current pointers. */ +static void +xfs_attr_save_rmt_blk( + struct xfs_da_args *args) +{ + args->blkno2 = args->blkno; + args->index2 = args->index; + args->rmtblkno2 = args->rmtblkno; + args->rmtblkcnt2 = args->rmtblkcnt; + args->rmtvaluelen2 = args->rmtvaluelen; + args->rmtblkno = 0; + args->rmtblkcnt = 0; + args->rmtvaluelen = 0; +} + +/* Set stored info about a remote block */ +static void +xfs_attr_restore_rmt_blk( + struct xfs_da_args *args) +{ + args->blkno = args->blkno2; + args->index = args->index2; + args->rmtblkno = args->rmtblkno2; + args->rmtblkcnt = args->rmtblkcnt2; + args->rmtvaluelen = args->rmtvaluelen2; +} + +/* + * PPTR_REPLACE operations require the caller to set the old and new names and + * values explicitly. Update the canonical fields to the new name and value + * here now that the removal phase has finished. + */ +static void +xfs_attr_update_pptr_replace_args( + struct xfs_da_args *args) +{ + ASSERT(args->new_namelen > 0); + args->name = args->new_name; + args->namelen = args->new_namelen; + args->value = args->new_value; + args->valuelen = args->new_valuelen; + xfs_attr_sethash(args); +} + /* * Handle the state change on completion of a multi-state attr operation. * @@ -418,58 +497,84 @@ xfs_attr_complete_op( enum xfs_delattr_state replace_state) { struct xfs_da_args *args = attr->xattri_da_args; - bool do_replace = args->op_flags & XFS_DA_OP_REPLACE; + + if (!(args->op_flags & XFS_DA_OP_REPLACE)) + replace_state = XFS_DAS_DONE; + else if (xfs_attr_intent_op(attr) == XFS_ATTRI_OP_FLAGS_PPTR_REPLACE) + xfs_attr_update_pptr_replace_args(args); args->op_flags &= ~XFS_DA_OP_REPLACE; - if (do_replace) { - args->attr_filter &= ~XFS_ATTR_INCOMPLETE; - return replace_state; - } - return XFS_DAS_DONE; + args->attr_filter &= ~XFS_ATTR_INCOMPLETE; + return replace_state; } +/* + * Try to add an attribute to an inode in leaf form. + */ static int xfs_attr_leaf_addname( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; + struct xfs_buf *bp; int error; ASSERT(xfs_attr_is_leaf(args->dp)); + error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp); + if (error) + return error; + /* - * Use the leaf buffer we may already hold locked as a result of - * a sf-to-leaf conversion. + * Look up the xattr name to set the insertion point for the new xattr. */ - error = xfs_attr_leaf_try_add(args); - - if (error == -ENOSPC) { - error = xfs_attr3_leaf_to_node(args); - if (error) - return error; + error = xfs_attr3_leaf_lookup_int(bp, args); + switch (error) { + case -ENOATTR: + if (args->op_flags & XFS_DA_OP_REPLACE) + goto out_brelse; + break; + case -EEXIST: + if (!(args->op_flags & XFS_DA_OP_REPLACE)) + goto out_brelse; + trace_xfs_attr_leaf_replace(args); /* - * We're not in leaf format anymore, so roll the transaction and - * retry the add to the newly allocated node block. + * Save the existing remote attr state so that the current + * values reflect the state of the new attribute we are about to + * add, not the attribute we just found and will remove later. */ - attr->xattri_dela_state = XFS_DAS_NODE_ADD; - goto out; + xfs_attr_save_rmt_blk(args); + break; + case 0: + break; + default: + goto out_brelse; } - if (error) - return error; /* * We need to commit and roll if we need to allocate remote xattr blocks * or perform more xattr manipulations. Otherwise there is nothing more * to do and we can return success. */ - if (args->rmtblkno) + if (!xfs_attr3_leaf_add(bp, args)) { + error = xfs_attr3_leaf_to_node(args); + if (error) + return error; + + attr->xattri_dela_state = XFS_DAS_NODE_ADD; + } else if (args->rmtblkno) { attr->xattri_dela_state = XFS_DAS_LEAF_SET_RMT; - else - attr->xattri_dela_state = xfs_attr_complete_op(attr, - XFS_DAS_LEAF_REPLACE); -out: + } else { + attr->xattri_dela_state = + xfs_attr_complete_op(attr, XFS_DAS_LEAF_REPLACE); + } + trace_xfs_attr_leaf_addname_return(attr->xattri_dela_state, args->dp); + return 0; + +out_brelse: + xfs_trans_brelse(args->trans, bp); return error; } @@ -492,7 +597,7 @@ xfs_attr_node_addname( return error; error = xfs_attr_node_try_addname(attr); - if (error == -ENOSPC) { + if (error == 1) { error = xfs_attr3_leaf_to_node(args); if (error) return error; @@ -647,8 +752,8 @@ xfs_attr_leaf_remove_attr( int forkoff; int error; - error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, - &bp); + error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, + args->blkno, &bp); if (error) return error; @@ -679,7 +784,7 @@ xfs_attr_leaf_shrink( if (!xfs_attr_is_leaf(dp)) return 0; - error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp); + error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp); if (error) return error; @@ -862,8 +967,16 @@ xfs_attr_lookup( if (!xfs_inode_hasattr(dp)) return -ENOATTR; - if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) - return xfs_attr_sf_findname(args, NULL, NULL); + if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) { + if (xfs_attr_sf_findname(args)) + return -EEXIST; + return -ENOATTR; + } + + /* Prerequisite for xfs_attr_is_leaf */ + error = xfs_iread_extents(args->trans, args->dp, XFS_ATTR_FORK); + if (error) + return error; if (xfs_attr_is_leaf(dp)) { error = xfs_attr_leaf_hasname(args, &bp); @@ -880,118 +993,73 @@ xfs_attr_lookup( return error; } -static int -xfs_attr_intent_init( - struct xfs_da_args *args, - unsigned int op_flags, /* op flag (set or remove) */ - struct xfs_attr_intent **attr) /* new xfs_attr_intent */ +int +xfs_attr_add_fork( + struct xfs_inode *ip, /* incore inode pointer */ + int size, /* space new attribute needs */ + int rsvd) /* xact may use reserved blks */ { + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; /* transaction pointer */ + unsigned int blks; /* space reservation */ + int error; /* error return value */ - struct xfs_attr_intent *new; + if (!xfs_is_metadir_inode(ip)) + ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); - new = kmem_cache_zalloc(xfs_attr_intent_cache, GFP_NOFS | __GFP_NOFAIL); - new->xattri_op_flags = op_flags; - new->xattri_da_args = args; + blks = XFS_ADDAFORK_SPACE_RES(mp); - *attr = new; - return 0; -} - -/* Sets an attribute for an inode as a deferred operation */ -static int -xfs_attr_defer_add( - struct xfs_da_args *args) -{ - struct xfs_attr_intent *new; - int error = 0; - - error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_SET, &new); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_addafork, blks, 0, + rsvd, &tp); if (error) return error; - new->xattri_dela_state = xfs_attr_init_add_state(args); - xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list); - trace_xfs_attr_defer_add(new->xattri_dela_state, args->dp); - - return 0; -} - -/* Sets an attribute for an inode as a deferred operation */ -static int -xfs_attr_defer_replace( - struct xfs_da_args *args) -{ - struct xfs_attr_intent *new; - int error = 0; + if (xfs_inode_has_attr_fork(ip)) + goto trans_cancel; - error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_REPLACE, &new); + error = xfs_bmap_add_attrfork(tp, ip, size, rsvd); if (error) - return error; - - new->xattri_dela_state = xfs_attr_init_replace_state(args); - xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list); - trace_xfs_attr_defer_replace(new->xattri_dela_state, args->dp); + goto trans_cancel; - return 0; -} - -/* Removes an attribute for an inode as a deferred operation */ -static int -xfs_attr_defer_remove( - struct xfs_da_args *args) -{ - - struct xfs_attr_intent *new; - int error; - - error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_REMOVE, &new); - if (error) - return error; - - new->xattri_dela_state = xfs_attr_init_remove_state(args); - xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list); - trace_xfs_attr_defer_remove(new->xattri_dela_state, args->dp); + error = xfs_trans_commit(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return error; - return 0; +trans_cancel: + xfs_trans_cancel(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return error; } /* - * Note: If args->value is NULL the attribute will be removed, just like the - * Linux ->setattr API. + * Make a change to the xattr structure. + * + * The caller must have initialized @args, attached dquots, and must not hold + * any ILOCKs. Reserved data blocks may be used if @rsvd is set. + * + * Returns -EEXIST for XFS_ATTRUPDATE_CREATE if the name already exists. + * Returns -ENOATTR for XFS_ATTRUPDATE_REMOVE if the name does not exist. + * Returns 0 on success, or a negative errno if something else went wrong. */ int xfs_attr_set( - struct xfs_da_args *args) + struct xfs_da_args *args, + enum xfs_attr_update op, + bool rsvd) { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_trans_res tres; - bool rsvd = (args->attr_filter & XFS_ATTR_ROOT); int error, local; int rmt_blks = 0; - unsigned int total; + unsigned int total = 0; - if (xfs_is_shutdown(dp->i_mount)) - return -EIO; - - error = xfs_qm_dqattach(dp); - if (error) - return error; - - args->geo = mp->m_attr_geo; - args->whichfork = XFS_ATTR_FORK; - args->hashval = xfs_da_hashname(args->name, args->namelen); - - /* - * We have no control over the attribute names that userspace passes us - * to remove, so we have to allow the name lookup prior to attribute - * removal to fail as well. Preserve the logged flag, since we need - * to pass that through to the logging code. - */ - args->op_flags = XFS_DA_OP_OKNOENT | - (args->op_flags & XFS_DA_OP_LOGGED); + ASSERT(!args->trans); - if (args->value) { + switch (op) { + case XFS_ATTRUPDATE_UPSERT: + case XFS_ATTRUPDATE_CREATE: + case XFS_ATTRUPDATE_REPLACE: XFS_STATS_INC(mp, xs_attr_set); args->total = xfs_attr_calc_size(args, &local); @@ -1004,33 +1072,36 @@ xfs_attr_set( xfs_attr_sf_entsize_byname(args->namelen, args->valuelen); - error = xfs_bmap_add_attrfork(dp, sf_size, rsvd); + error = xfs_attr_add_fork(dp, sf_size, rsvd); if (error) return error; } if (!local) rmt_blks = xfs_attr3_rmt_blocks(mp, args->valuelen); - } else { + + tres = xfs_attr_set_resv(args); + total = args->total; + break; + case XFS_ATTRUPDATE_REMOVE: XFS_STATS_INC(mp, xs_attr_remove); - rmt_blks = xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX); + rmt_blks = xfs_attr3_max_rmt_blocks(mp); + tres = M_RES(mp)->tr_attrrm; + total = XFS_ATTRRM_SPACE_RES(mp); + break; } /* * Root fork attributes can use reserved data blocks for this * operation if necessary */ - xfs_init_attr_trans(args, &tres, &total); error = xfs_trans_alloc_inode(dp, &tres, total, 0, rsvd, &args->trans); if (error) return error; - if (args->value || xfs_inode_hasattr(dp)) { - error = xfs_iext_count_may_overflow(dp, XFS_ATTR_FORK, + if (op != XFS_ATTRUPDATE_REMOVE || xfs_inode_hasattr(dp)) { + error = xfs_iext_count_extend(args->trans, dp, XFS_ATTR_FORK, XFS_IEXT_ATTR_MANIP_CNT(rmt_blks)); - if (error == -EFBIG) - error = xfs_iext_count_upgrade(args->trans, dp, - XFS_IEXT_ATTR_MANIP_CNT(rmt_blks)); if (error) goto out_trans_cancel; } @@ -1038,33 +1109,30 @@ xfs_attr_set( error = xfs_attr_lookup(args); switch (error) { case -EEXIST: - /* if no value, we are performing a remove operation */ - if (!args->value) { - error = xfs_attr_defer_remove(args); + if (op == XFS_ATTRUPDATE_REMOVE) { + /* if no value, we are performing a remove operation */ + xfs_attr_defer_add(args, XFS_ATTR_DEFER_REMOVE); break; } + /* Pure create fails if the attr already exists */ - if (args->attr_flags & XATTR_CREATE) + if (op == XFS_ATTRUPDATE_CREATE) goto out_trans_cancel; - - error = xfs_attr_defer_replace(args); + xfs_attr_defer_add(args, XFS_ATTR_DEFER_REPLACE); break; case -ENOATTR: /* Can't remove what isn't there. */ - if (!args->value) + if (op == XFS_ATTRUPDATE_REMOVE) goto out_trans_cancel; /* Pure replace fails if no existing attr to replace. */ - if (args->attr_flags & XATTR_REPLACE) + if (op == XFS_ATTRUPDATE_REPLACE) goto out_trans_cancel; - - error = xfs_attr_defer_add(args); + xfs_attr_defer_add(args, XFS_ATTR_DEFER_SET); break; default: goto out_trans_cancel; } - if (error) - goto out_trans_cancel; /* * If this is a synchronous mount, make sure that the @@ -1073,8 +1141,7 @@ xfs_attr_set( if (xfs_has_wsync(mp)) xfs_trans_set_sync(args->trans); - if (!(args->op_flags & XFS_DA_OP_NOTIME)) - xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG); /* * Commit the last in the sequence of transactions. @@ -1083,6 +1150,7 @@ xfs_attr_set( error = xfs_trans_commit(args->trans); out_unlock: xfs_iunlock(dp, XFS_ILOCK_EXCL); + args->trans = NULL; return error; out_trans_cancel: @@ -1095,12 +1163,11 @@ out_trans_cancel: * External routines when attribute list is inside the inode *========================================================================*/ -static inline int xfs_attr_sf_totsize(struct xfs_inode *dp) +int xfs_attr_sf_totsize(struct xfs_inode *dp) { - struct xfs_attr_shortform *sf; + struct xfs_attr_sf_hdr *sf = dp->i_af.if_data; - sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data; - return be16_to_cpu(sf->hdr.totsize); + return be16_to_cpu(sf->totsize); } /* @@ -1112,19 +1179,13 @@ xfs_attr_shortform_addname( struct xfs_da_args *args) { int newsize, forkoff; - int error; trace_xfs_attr_sf_addname(args); - error = xfs_attr_shortform_lookup(args); - switch (error) { - case -ENOATTR: - if (args->op_flags & XFS_DA_OP_REPLACE) - return error; - break; - case -EEXIST: - if (!(args->op_flags & XFS_DA_OP_REPLACE)) - return error; + if (xfs_attr_sf_findname(args)) { + int error; + + ASSERT(args->op_flags & XFS_DA_OP_REPLACE); error = xfs_attr_sf_removename(args); if (error) @@ -1137,11 +1198,8 @@ xfs_attr_shortform_addname( * around. */ args->op_flags &= ~XFS_DA_OP_REPLACE; - break; - case 0: - break; - default: - return error; + } else { + ASSERT(!(args->op_flags & XFS_DA_OP_REPLACE)); } if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX || @@ -1164,88 +1222,6 @@ xfs_attr_shortform_addname( * External routines when attribute list is one block *========================================================================*/ -/* Save the current remote block info and clear the current pointers. */ -static void -xfs_attr_save_rmt_blk( - struct xfs_da_args *args) -{ - args->blkno2 = args->blkno; - args->index2 = args->index; - args->rmtblkno2 = args->rmtblkno; - args->rmtblkcnt2 = args->rmtblkcnt; - args->rmtvaluelen2 = args->rmtvaluelen; - args->rmtblkno = 0; - args->rmtblkcnt = 0; - args->rmtvaluelen = 0; -} - -/* Set stored info about a remote block */ -static void -xfs_attr_restore_rmt_blk( - struct xfs_da_args *args) -{ - args->blkno = args->blkno2; - args->index = args->index2; - args->rmtblkno = args->rmtblkno2; - args->rmtblkcnt = args->rmtblkcnt2; - args->rmtvaluelen = args->rmtvaluelen2; -} - -/* - * Tries to add an attribute to an inode in leaf form - * - * This function is meant to execute as part of a delayed operation and leaves - * the transaction handling to the caller. On success the attribute is added - * and the inode and transaction are left dirty. If there is not enough space, - * the attr data is converted to node format and -ENOSPC is returned. Caller is - * responsible for handling the dirty inode and transaction or adding the attr - * in node format. - */ -STATIC int -xfs_attr_leaf_try_add( - struct xfs_da_args *args) -{ - struct xfs_buf *bp; - int error; - - error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp); - if (error) - return error; - - /* - * Look up the xattr name to set the insertion point for the new xattr. - */ - error = xfs_attr3_leaf_lookup_int(bp, args); - switch (error) { - case -ENOATTR: - if (args->op_flags & XFS_DA_OP_REPLACE) - goto out_brelse; - break; - case -EEXIST: - if (!(args->op_flags & XFS_DA_OP_REPLACE)) - goto out_brelse; - - trace_xfs_attr_leaf_replace(args); - /* - * Save the existing remote attr state so that the current - * values reflect the state of the new attribute we are about to - * add, not the attribute we just found and will remove later. - */ - xfs_attr_save_rmt_blk(args); - break; - case 0: - break; - default: - goto out_brelse; - } - - return xfs_attr3_leaf_add(bp, args); - -out_brelse: - xfs_trans_brelse(args->trans, bp); - return error; -} - /* * Return EEXIST if attr is found, or ENOATTR if not */ @@ -1256,7 +1232,7 @@ xfs_attr_leaf_hasname( { int error = 0; - error = xfs_attr3_leaf_read(args->trans, args->dp, 0, bp); + error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, bp); if (error) return error; @@ -1411,9 +1387,12 @@ error: /* * Add a name to a Btree-format attribute list. * - * This will involve walking down the Btree, and may involve splitting - * leaf nodes and even splitting intermediate nodes up to and including - * the root node (a special case of an intermediate node). + * This will involve walking down the Btree, and may involve splitting leaf + * nodes and even splitting intermediate nodes up to and including the root + * node (a special case of an intermediate node). + * + * If the tree was still in single leaf format and needs to converted to + * real node format return 1 and let the caller handle that. */ static int xfs_attr_node_try_addname( @@ -1421,21 +1400,21 @@ xfs_attr_node_try_addname( { struct xfs_da_state *state = attr->xattri_da_state; struct xfs_da_state_blk *blk; - int error; + int error = 0; trace_xfs_attr_node_addname(state->args); blk = &state->path.blk[state->path.active-1]; ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC); - error = xfs_attr3_leaf_add(blk->bp, state->args); - if (error == -ENOSPC) { + if (!xfs_attr3_leaf_add(blk->bp, state->args)) { if (state->path.active == 1) { /* * Its really a single leaf node, but it had * out-of-line values so it looked like it *might* * have been a b-tree. Let the caller deal with this. */ + error = 1; goto out; } @@ -1565,12 +1544,23 @@ out_release: return error; } +/* Enforce that there is at most one namespace bit per attr. */ +inline bool xfs_attr_check_namespace(unsigned int attr_flags) +{ + return hweight32(attr_flags & XFS_ATTR_NSP_ONDISK_MASK) < 2; +} + /* Returns true if the attribute entry name is valid. */ bool xfs_attr_namecheck( + unsigned int attr_flags, const void *name, size_t length) { + /* Only one namespace bit allowed. */ + if (!xfs_attr_check_namespace(attr_flags)) + return false; + /* * MAXNAMELEN includes the trailing null, but (name/length) leave it * out, so use >= for the length check. @@ -1578,6 +1568,10 @@ xfs_attr_namecheck( if (length >= MAXNAMELEN) return false; + /* Parent pointers have their own validation. */ + if (attr_flags & XFS_ATTR_PARENT) + return xfs_parent_namecheck(attr_flags, name, length); + /* There shouldn't be any nulls here */ return !memchr(name, 0, length); } diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h index 81be9b3e4004..0e51d0723f9a 100644 --- a/fs/xfs/libxfs/xfs_attr.h +++ b/fs/xfs/libxfs/xfs_attr.h @@ -47,8 +47,9 @@ struct xfs_attrlist_cursor_kern { /* void; state communicated via *context */ -typedef void (*put_listent_func_t)(struct xfs_attr_list_context *, int, - unsigned char *, int, int); +typedef void (*put_listent_func_t)(struct xfs_attr_list_context *context, + int flags, unsigned char *name, int namelen, void *value, + int valuelen); struct xfs_attr_list_context { struct xfs_trans *tp; @@ -510,8 +511,8 @@ struct xfs_attr_intent { struct xfs_da_args *xattri_da_args; /* - * Shared buffer containing the attr name and value so that the logging - * code can share large memory buffers between log items. + * Shared buffer containing the attr name, new name, and value so that + * the logging code can share large memory buffers between log items. */ struct xfs_attri_log_nameval *xattri_nameval; @@ -529,6 +530,11 @@ struct xfs_attr_intent { struct xfs_bmbt_irec xattri_map; }; +static inline unsigned int +xfs_attr_intent_op(const struct xfs_attr_intent *attr) +{ + return attr->xattri_op_flags & XFS_ATTRI_OP_FLAGS_TYPE_MASK; +} /*======================================================================== * Function prototypes for the kernel. @@ -544,13 +550,22 @@ int xfs_inode_hasattr(struct xfs_inode *ip); bool xfs_attr_is_leaf(struct xfs_inode *ip); int xfs_attr_get_ilocked(struct xfs_da_args *args); int xfs_attr_get(struct xfs_da_args *args); -int xfs_attr_set(struct xfs_da_args *args); + +enum xfs_attr_update { + XFS_ATTRUPDATE_REMOVE, /* remove attr */ + XFS_ATTRUPDATE_UPSERT, /* set value, replace any existing attr */ + XFS_ATTRUPDATE_CREATE, /* set value, fail if attr already exists */ + XFS_ATTRUPDATE_REPLACE, /* set value, fail if attr does not exist */ +}; + +int xfs_attr_set(struct xfs_da_args *args, enum xfs_attr_update op, bool rsvd); int xfs_attr_set_iter(struct xfs_attr_intent *attr); int xfs_attr_remove_iter(struct xfs_attr_intent *attr); -bool xfs_attr_namecheck(const void *name, size_t length); +bool xfs_attr_check_namespace(unsigned int attr_flags); +bool xfs_attr_namecheck(unsigned int attr_flags, const void *name, + size_t length); int xfs_attr_calc_size(struct xfs_da_args *args, int *local); -void xfs_init_attr_trans(struct xfs_da_args *args, struct xfs_trans_res *tres, - unsigned int *total); +struct xfs_trans_res xfs_attr_set_resv(const struct xfs_da_args *args); /* * Check to see if the attr should be upgraded from non-existent or shortform to @@ -590,7 +605,6 @@ xfs_attr_init_add_state(struct xfs_da_args *args) static inline enum xfs_delattr_state xfs_attr_init_remove_state(struct xfs_da_args *args) { - args->op_flags |= XFS_DA_OP_REMOVE; if (xfs_attr_is_shortform(args->dp)) return XFS_DAS_SF_REMOVE; if (xfs_attr_is_leaf(args->dp)) @@ -614,8 +628,25 @@ xfs_attr_init_replace_state(struct xfs_da_args *args) return xfs_attr_init_add_state(args); } +xfs_dahash_t xfs_attr_hashname(const uint8_t *name, int namelen); + +xfs_dahash_t xfs_attr_hashval(struct xfs_mount *mp, unsigned int attr_flags, + const uint8_t *name, int namelen, const void *value, + int valuelen); + +/* Set the hash value for any extended attribute from any namespace. */ +static inline void xfs_attr_sethash(struct xfs_da_args *args) +{ + args->hashval = xfs_attr_hashval(args->dp->i_mount, args->attr_filter, + args->name, args->namelen, + args->value, args->valuelen); +} + extern struct kmem_cache *xfs_attr_intent_cache; int __init xfs_attr_intent_init_cache(void); void xfs_attr_intent_destroy_cache(void); +int xfs_attr_sf_totsize(struct xfs_inode *dp); +int xfs_attr_add_fork(struct xfs_inode *ip, int size, int rsvd); + #endif /* __XFS_ATTR_H__ */ diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index beee51ad75ce..91c1b30ebaab 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -29,6 +29,7 @@ #include "xfs_log.h" #include "xfs_ag.h" #include "xfs_errortag.h" +#include "xfs_health.h" /* @@ -46,7 +47,7 @@ */ STATIC int xfs_attr3_leaf_create(struct xfs_da_args *args, xfs_dablk_t which_block, struct xfs_buf **bpp); -STATIC int xfs_attr3_leaf_add_work(struct xfs_buf *leaf_buffer, +STATIC void xfs_attr3_leaf_add_work(struct xfs_buf *leaf_buffer, struct xfs_attr3_icleaf_hdr *ichdr, struct xfs_da_args *args, int freemap_index); STATIC void xfs_attr3_leaf_compact(struct xfs_da_args *args, @@ -387,6 +388,27 @@ xfs_attr3_leaf_verify( return NULL; } +xfs_failaddr_t +xfs_attr3_leaf_header_check( + struct xfs_buf *bp, + xfs_ino_t owner) +{ + struct xfs_mount *mp = bp->b_mount; + + if (xfs_has_crc(mp)) { + struct xfs_attr3_leafblock *hdr3 = bp->b_addr; + + if (hdr3->hdr.info.hdr.magic != + cpu_to_be16(XFS_ATTR3_LEAF_MAGIC)) + return __this_address; + + if (be64_to_cpu(hdr3->hdr.info.owner) != owner) + return __this_address; + } + + return NULL; +} + static void xfs_attr3_leaf_write_verify( struct xfs_buf *bp) @@ -447,16 +469,30 @@ int xfs_attr3_leaf_read( struct xfs_trans *tp, struct xfs_inode *dp, + xfs_ino_t owner, xfs_dablk_t bno, struct xfs_buf **bpp) { + xfs_failaddr_t fa; int err; err = xfs_da_read_buf(tp, dp, bno, 0, bpp, XFS_ATTR_FORK, &xfs_attr3_leaf_buf_ops); - if (!err && tp && *bpp) + if (err || !(*bpp)) + return err; + + fa = xfs_attr3_leaf_header_check(*bpp, owner); + if (fa) { + __xfs_buf_mark_corrupt(*bpp, fa); + xfs_trans_brelse(tp, *bpp); + *bpp = NULL; + xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); + return -EFSCORRUPTED; + } + + if (tp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF); - return err; + return 0; } /*======================================================================== @@ -471,28 +507,57 @@ xfs_attr3_leaf_read( * INCOMPLETE flag will not be set in attr->attr_filter, but rather * XFS_DA_OP_RECOVERY will be set in args->op_flags. */ +static inline unsigned int xfs_attr_match_mask(const struct xfs_da_args *args) +{ + if (args->op_flags & XFS_DA_OP_RECOVERY) + return XFS_ATTR_NSP_ONDISK_MASK; + return XFS_ATTR_NSP_ONDISK_MASK | XFS_ATTR_INCOMPLETE; +} + +static inline bool +xfs_attr_parent_match( + const struct xfs_da_args *args, + const void *value, + unsigned int valuelen) +{ + ASSERT(args->value != NULL); + + /* Parent pointers do not use remote values */ + if (!value) + return false; + + /* + * The only value we support is a parent rec. However, we'll accept + * any valuelen so that offline repair can delete ATTR_PARENT values + * that are not parent pointers. + */ + if (valuelen != args->valuelen) + return false; + + return memcmp(args->value, value, valuelen) == 0; +} + static bool xfs_attr_match( struct xfs_da_args *args, - uint8_t namelen, - unsigned char *name, - int flags) + unsigned int attr_flags, + const unsigned char *name, + unsigned int namelen, + const void *value, + unsigned int valuelen) { + unsigned int mask = xfs_attr_match_mask(args); if (args->namelen != namelen) return false; + if ((args->attr_filter & mask) != (attr_flags & mask)) + return false; if (memcmp(args->name, name, namelen) != 0) return false; - /* Recovery ignores the INCOMPLETE flag. */ - if ((args->op_flags & XFS_DA_OP_RECOVERY) && - args->attr_filter == (flags & XFS_ATTR_NSP_ONDISK_MASK)) - return true; + if (attr_flags & XFS_ATTR_PARENT) + return xfs_attr_parent_match(args, value, valuelen); - /* All remaining matches need to be filtered by INCOMPLETE state. */ - if (args->attr_filter != - (flags & (XFS_ATTR_NSP_ONDISK_MASK | XFS_ATTR_INCOMPLETE))) - return false; return true; } @@ -503,6 +568,13 @@ xfs_attr_copy_value( int valuelen) { /* + * Parent pointer lookups require the caller to specify the name and + * value, so don't copy anything. + */ + if (args->attr_filter & XFS_ATTR_PARENT) + return 0; + + /* * No copy if all we have to do is get the length */ if (!args->valuelen) { @@ -595,12 +667,8 @@ xfs_attr_shortform_bytesfit( /* * For attr2 we can try to move the forkoff if there is space in the - * literal area, but for the old format we are done if there is no - * space in the fixed attribute fork. + * literal area */ - if (!xfs_has_attr2(mp)) - return 0; - dsize = dp->i_df.if_bytes; switch (dp->i_df.if_format) { @@ -614,7 +682,7 @@ xfs_attr_shortform_bytesfit( */ if (!dp->i_forkoff && dp->i_df.if_bytes > xfs_default_attroffset(dp)) - dsize = XFS_BMDR_SPACE_CALC(MINDBTPTRS); + dsize = xfs_bmdr_space_calc(MINDBTPTRS); break; case XFS_DINODE_FMT_BTREE: /* @@ -628,7 +696,7 @@ xfs_attr_shortform_bytesfit( return 0; return dp->i_forkoff; } - dsize = XFS_BMAP_BROOT_SPACE(mp, dp->i_df.if_broot); + dsize = xfs_bmap_bmdr_space(dp->i_df.if_broot); break; } @@ -636,11 +704,11 @@ xfs_attr_shortform_bytesfit( * A data fork btree root must have space for at least * MINDBTPTRS key/ptr pairs if the data fork is small or empty. */ - minforkoff = max_t(int64_t, dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS)); + minforkoff = max_t(int64_t, dsize, xfs_bmdr_space_calc(MINDBTPTRS)); minforkoff = roundup(minforkoff, 8) >> 3; /* attr fork btree root can have at least this many key/ptr pairs */ - maxforkoff = XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS); + maxforkoff = XFS_LITINO(mp) - xfs_bmdr_space_calc(MINABTPTRS); maxforkoff = maxforkoff >> 3; /* rounded down */ if (offset >= maxforkoff) @@ -651,22 +719,16 @@ xfs_attr_shortform_bytesfit( } /* - * Switch on the ATTR2 superblock bit (implies also FEATURES2) unless: - * - noattr2 mount option is set, - * - on-disk version bit says it is already set, or - * - the attr2 mount option is not set to enable automatic upgrade from attr1. + * Switch on the ATTR2 superblock bit (implies also FEATURES2) unless + * on-disk version bit says it is already set */ STATIC void xfs_sbversion_add_attr2( struct xfs_mount *mp, struct xfs_trans *tp) { - if (xfs_has_noattr2(mp)) - return; if (mp->m_sb.sb_features2 & XFS_SB_VERSION2_ATTR2BIT) return; - if (!xfs_has_attr2(mp)) - return; spin_lock(&mp->m_sb_lock); xfs_add_attr2(mp); @@ -690,56 +752,33 @@ xfs_attr_shortform_create( ASSERT(ifp->if_bytes == 0); if (ifp->if_format == XFS_DINODE_FMT_EXTENTS) ifp->if_format = XFS_DINODE_FMT_LOCAL; - xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK); - hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data; + + hdr = xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK); memset(hdr, 0, sizeof(*hdr)); hdr->totsize = cpu_to_be16(sizeof(*hdr)); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA); } /* - * Return -EEXIST if attr is found, or -ENOATTR if not - * args: args containing attribute name and namelen - * sfep: If not null, pointer will be set to the last attr entry found on - -EEXIST. On -ENOATTR pointer is left at the last entry in the list - * basep: If not null, pointer is set to the byte offset of the entry in the - * list on -EEXIST. On -ENOATTR, pointer is left at the byte offset of - * the last entry in the list + * Return the entry if the attr in args is found, or NULL if not. */ -int +struct xfs_attr_sf_entry * xfs_attr_sf_findname( - struct xfs_da_args *args, - struct xfs_attr_sf_entry **sfep, - unsigned int *basep) + struct xfs_da_args *args) { - struct xfs_attr_shortform *sf; - struct xfs_attr_sf_entry *sfe; - unsigned int base = sizeof(struct xfs_attr_sf_hdr); - int size = 0; - int end; - int i; + struct xfs_attr_sf_hdr *sf = args->dp->i_af.if_data; + struct xfs_attr_sf_entry *sfe; - sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data; - sfe = &sf->list[0]; - end = sf->hdr.count; - for (i = 0; i < end; sfe = xfs_attr_sf_nextentry(sfe), - base += size, i++) { - size = xfs_attr_sf_entsize(sfe); - if (!xfs_attr_match(args, sfe->namelen, sfe->nameval, - sfe->flags)) - continue; - break; + for (sfe = xfs_attr_sf_firstentry(sf); + sfe < xfs_attr_sf_endptr(sf); + sfe = xfs_attr_sf_nextentry(sfe)) { + if (xfs_attr_match(args, sfe->flags, sfe->nameval, + sfe->namelen, &sfe->nameval[sfe->namelen], + sfe->valuelen)) + return sfe; } - if (sfep != NULL) - *sfep = sfe; - - if (basep != NULL) - *basep = base; - - if (i == end) - return -ENOATTR; - return -EEXIST; + return NULL; } /* @@ -751,38 +790,31 @@ xfs_attr_shortform_add( struct xfs_da_args *args, int forkoff) { - struct xfs_attr_shortform *sf; + struct xfs_inode *dp = args->dp; + struct xfs_mount *mp = dp->i_mount; + struct xfs_ifork *ifp = &dp->i_af; + struct xfs_attr_sf_hdr *sf = ifp->if_data; struct xfs_attr_sf_entry *sfe; - int offset, size; - struct xfs_mount *mp; - struct xfs_inode *dp; - struct xfs_ifork *ifp; + int size; trace_xfs_attr_sf_add(args); - dp = args->dp; - mp = dp->i_mount; dp->i_forkoff = forkoff; - ifp = &dp->i_af; ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); - sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data; - if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST) - ASSERT(0); + ASSERT(!xfs_attr_sf_findname(args)); - offset = (char *)sfe - (char *)sf; size = xfs_attr_sf_entsize_byname(args->namelen, args->valuelen); - xfs_idata_realloc(dp, size, XFS_ATTR_FORK); - sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data; - sfe = (struct xfs_attr_sf_entry *)((char *)sf + offset); + sf = xfs_idata_realloc(dp, size, XFS_ATTR_FORK); + sfe = xfs_attr_sf_endptr(sf); sfe->namelen = args->namelen; sfe->valuelen = args->valuelen; sfe->flags = args->attr_filter; memcpy(sfe->nameval, args->name, args->namelen); memcpy(&sfe->nameval[args->namelen], args->value, args->valuelen); - sf->hdr.count++; - be16_add_cpu(&sf->hdr.totsize, size); + sf->count++; + be16_add_cpu(&sf->totsize, size); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA); xfs_sbversion_add_attr2(mp, args->trans); @@ -811,59 +843,55 @@ int xfs_attr_sf_removename( struct xfs_da_args *args) { - struct xfs_attr_shortform *sf; + struct xfs_inode *dp = args->dp; + struct xfs_mount *mp = dp->i_mount; + struct xfs_attr_sf_hdr *sf = dp->i_af.if_data; struct xfs_attr_sf_entry *sfe; - int size = 0, end, totsize; - unsigned int base; - struct xfs_mount *mp; - struct xfs_inode *dp; - int error; + uint16_t totsize = be16_to_cpu(sf->totsize); + void *next, *end; + int size = 0; trace_xfs_attr_sf_remove(args); - dp = args->dp; - mp = dp->i_mount; - sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data; - - error = xfs_attr_sf_findname(args, &sfe, &base); - - /* - * If we are recovering an operation, finding nothing to - * remove is not an error - it just means there was nothing - * to clean up. - */ - if (error == -ENOATTR && (args->op_flags & XFS_DA_OP_RECOVERY)) - return 0; - if (error != -EEXIST) - return error; - size = xfs_attr_sf_entsize(sfe); + sfe = xfs_attr_sf_findname(args); + if (!sfe) { + /* + * If we are recovering an operation, finding nothing to remove + * is not an error, it just means there was nothing to clean up. + */ + if (args->op_flags & XFS_DA_OP_RECOVERY) + return 0; + return -ENOATTR; + } /* * Fix up the attribute fork data, covering the hole */ - end = base + size; - totsize = be16_to_cpu(sf->hdr.totsize); - if (end != totsize) - memmove(&((char *)sf)[base], &((char *)sf)[end], totsize - end); - sf->hdr.count--; - be16_add_cpu(&sf->hdr.totsize, -size); + size = xfs_attr_sf_entsize(sfe); + next = xfs_attr_sf_nextentry(sfe); + end = xfs_attr_sf_endptr(sf); + if (next < end) + memmove(sfe, next, end - next); + sf->count--; + totsize -= size; + sf->totsize = cpu_to_be16(totsize); /* * Fix up the start offset of the attribute fork */ - totsize -= size; - if (totsize == sizeof(xfs_attr_sf_hdr_t) && xfs_has_attr2(mp) && + if (totsize == sizeof(struct xfs_attr_sf_hdr) && (dp->i_df.if_format != XFS_DINODE_FMT_BTREE) && - !(args->op_flags & (XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE))) { + !(args->op_flags & (XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE)) && + !xfs_has_parent(mp)) { xfs_attr_fork_remove(dp, args->trans); } else { xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); dp->i_forkoff = xfs_attr_shortform_bytesfit(dp, totsize); ASSERT(dp->i_forkoff); - ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) || + ASSERT(totsize > sizeof(struct xfs_attr_sf_hdr) || (args->op_flags & XFS_DA_OP_ADDNAME) || - !xfs_has_attr2(mp) || - dp->i_df.if_format == XFS_DINODE_FMT_BTREE); + dp->i_df.if_format == XFS_DINODE_FMT_BTREE || + xfs_has_parent(mp)); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA); } @@ -874,33 +902,6 @@ xfs_attr_sf_removename( } /* - * Look up a name in a shortform attribute list structure. - */ -/*ARGSUSED*/ -int -xfs_attr_shortform_lookup(xfs_da_args_t *args) -{ - struct xfs_attr_shortform *sf; - struct xfs_attr_sf_entry *sfe; - int i; - struct xfs_ifork *ifp; - - trace_xfs_attr_sf_lookup(args); - - ifp = &args->dp->i_af; - ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); - sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data; - sfe = &sf->list[0]; - for (i = 0; i < sf->hdr.count; - sfe = xfs_attr_sf_nextentry(sfe), i++) { - if (xfs_attr_match(args, sfe->namelen, sfe->nameval, - sfe->flags)) - return -EEXIST; - } - return -ENOATTR; -} - -/* * Retrieve the attribute value and length. * * If args->valuelen is zero, only the length needs to be returned. Unlike a @@ -909,23 +910,19 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args) */ int xfs_attr_shortform_getvalue( - struct xfs_da_args *args) + struct xfs_da_args *args) { - struct xfs_attr_shortform *sf; - struct xfs_attr_sf_entry *sfe; - int i; + struct xfs_attr_sf_entry *sfe; ASSERT(args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL); - sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data; - sfe = &sf->list[0]; - for (i = 0; i < sf->hdr.count; - sfe = xfs_attr_sf_nextentry(sfe), i++) { - if (xfs_attr_match(args, sfe->namelen, sfe->nameval, - sfe->flags)) - return xfs_attr_copy_value(args, - &sfe->nameval[args->namelen], sfe->valuelen); - } - return -ENOATTR; + + trace_xfs_attr_sf_lookup(args); + + sfe = xfs_attr_sf_findname(args); + if (!sfe) + return -ENOATTR; + return xfs_attr_copy_value(args, &sfe->nameval[args->namelen], + sfe->valuelen); } /* Convert from using the shortform to the leaf format. */ @@ -933,26 +930,22 @@ int xfs_attr_shortform_to_leaf( struct xfs_da_args *args) { - struct xfs_inode *dp; - struct xfs_attr_shortform *sf; + struct xfs_inode *dp = args->dp; + struct xfs_ifork *ifp = &dp->i_af; + struct xfs_attr_sf_hdr *sf = ifp->if_data; struct xfs_attr_sf_entry *sfe; + int size = be16_to_cpu(sf->totsize); struct xfs_da_args nargs; char *tmpbuffer; - int error, i, size; + int error, i; xfs_dablk_t blkno; struct xfs_buf *bp; - struct xfs_ifork *ifp; trace_xfs_attr_sf_to_leaf(args); - dp = args->dp; - ifp = &dp->i_af; - sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data; - size = be16_to_cpu(sf->hdr.totsize); - tmpbuffer = kmem_alloc(size, 0); - ASSERT(tmpbuffer != NULL); - memcpy(tmpbuffer, ifp->if_u1.if_data, size); - sf = (struct xfs_attr_shortform *)tmpbuffer; + tmpbuffer = kmalloc(size, GFP_KERNEL | __GFP_NOFAIL); + memcpy(tmpbuffer, ifp->if_data, size); + sf = (struct xfs_attr_sf_hdr *)tmpbuffer; xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); xfs_bmap_local_to_extents_empty(args->trans, dp, XFS_ATTR_FORK); @@ -974,27 +967,30 @@ xfs_attr_shortform_to_leaf( nargs.whichfork = XFS_ATTR_FORK; nargs.trans = args->trans; nargs.op_flags = XFS_DA_OP_OKNOENT; + nargs.owner = args->owner; - sfe = &sf->list[0]; - for (i = 0; i < sf->hdr.count; i++) { + sfe = xfs_attr_sf_firstentry(sf); + for (i = 0; i < sf->count; i++) { nargs.name = sfe->nameval; nargs.namelen = sfe->namelen; nargs.value = &sfe->nameval[nargs.namelen]; nargs.valuelen = sfe->valuelen; - nargs.hashval = xfs_da_hashname(sfe->nameval, - sfe->namelen); nargs.attr_filter = sfe->flags & XFS_ATTR_NSP_ONDISK_MASK; + if (!xfs_attr_check_namespace(sfe->flags)) { + xfs_da_mark_sick(args); + error = -EFSCORRUPTED; + goto out; + } + xfs_attr_sethash(&nargs); error = xfs_attr3_leaf_lookup_int(bp, &nargs); /* set a->index */ ASSERT(error == -ENOATTR); - error = xfs_attr3_leaf_add(bp, &nargs); - ASSERT(error != -ENOSPC); - if (error) - goto out; + if (!xfs_attr3_leaf_add(bp, &nargs)) + ASSERT(0); sfe = xfs_attr_sf_nextentry(sfe); } error = 0; out: - kmem_free(tmpbuffer); + kfree(tmpbuffer); return error; } @@ -1033,30 +1029,22 @@ xfs_attr_shortform_allfit( bytes += xfs_attr_sf_entsize_byname(name_loc->namelen, be16_to_cpu(name_loc->valuelen)); } - if (xfs_has_attr2(dp->i_mount) && - (dp->i_df.if_format != XFS_DINODE_FMT_BTREE) && + if ((dp->i_df.if_format != XFS_DINODE_FMT_BTREE) && (bytes == sizeof(struct xfs_attr_sf_hdr))) return -1; return xfs_attr_shortform_bytesfit(dp, bytes); } -/* Verify the consistency of an inline attribute fork. */ +/* Verify the consistency of a raw inline attribute fork. */ xfs_failaddr_t xfs_attr_shortform_verify( - struct xfs_inode *ip) + struct xfs_attr_sf_hdr *sfp, + size_t size) { - struct xfs_attr_shortform *sfp; - struct xfs_attr_sf_entry *sfep; + struct xfs_attr_sf_entry *sfep = xfs_attr_sf_firstentry(sfp); struct xfs_attr_sf_entry *next_sfep; char *endp; - struct xfs_ifork *ifp; int i; - int64_t size; - - ASSERT(ip->i_af.if_format == XFS_DINODE_FMT_LOCAL); - ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK); - sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data; - size = ifp->if_bytes; /* * Give up if the attribute is way too short. @@ -1067,8 +1055,7 @@ xfs_attr_shortform_verify( endp = (char *)sfp + size; /* Check all reported entries */ - sfep = &sfp->list[0]; - for (i = 0; i < sfp->hdr.count; i++) { + for (i = 0; i < sfp->count; i++) { /* * struct xfs_attr_sf_entry has a variable length. * Check the fixed-offset parts of the structure are @@ -1105,7 +1092,7 @@ xfs_attr_shortform_verify( * one namespace flag per xattr, so we can just count the * bits (i.e. hweight) here. */ - if (hweight8(sfep->flags & XFS_ATTR_NSP_ONDISK_MASK) > 1) + if (!xfs_attr_check_namespace(sfep->flags)) return __this_address; sfep = next_sfep; @@ -1137,10 +1124,7 @@ xfs_attr3_leaf_to_shortform( trace_xfs_attr_leaf_to_sf(args); - tmpbuffer = kmem_alloc(args->geo->blksize, 0); - if (!tmpbuffer) - return -ENOMEM; - + tmpbuffer = kvmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL); memcpy(tmpbuffer, bp->b_addr, args->geo->blksize); leaf = (xfs_attr_leafblock_t *)tmpbuffer; @@ -1165,7 +1149,6 @@ xfs_attr3_leaf_to_shortform( * this case. */ if (!(args->op_flags & XFS_DA_OP_REPLACE)) { - ASSERT(xfs_has_attr2(dp->i_mount)); ASSERT(dp->i_df.if_format != XFS_DINODE_FMT_BTREE); xfs_attr_fork_remove(dp, args->trans); } @@ -1184,6 +1167,7 @@ xfs_attr3_leaf_to_shortform( nargs.whichfork = XFS_ATTR_FORK; nargs.trans = args->trans; nargs.op_flags = XFS_DA_OP_OKNOENT; + nargs.owner = args->owner; for (i = 0; i < ichdr.count; entry++, i++) { if (entry->flags & XFS_ATTR_INCOMPLETE) @@ -1203,7 +1187,7 @@ xfs_attr3_leaf_to_shortform( error = 0; out: - kmem_free(tmpbuffer); + kvfree(tmpbuffer); return error; } @@ -1228,7 +1212,7 @@ xfs_attr3_leaf_to_node( trace_xfs_attr_leaf_to_node(args); - if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_ATTR_LEAF_TO_NODE)) { + if (XFS_TEST_ERROR(mp, XFS_ERRTAG_ATTR_LEAF_TO_NODE)) { error = -EIO; goto out; } @@ -1236,7 +1220,7 @@ xfs_attr3_leaf_to_node( error = xfs_da_grow_inode(args, &blkno); if (error) goto out; - error = xfs_attr3_leaf_read(args->trans, dp, 0, &bp1); + error = xfs_attr3_leaf_read(args->trans, dp, args->owner, 0, &bp1); if (error) goto out; @@ -1244,14 +1228,10 @@ xfs_attr3_leaf_to_node( if (error) goto out; - /* copy leaf to new buffer, update identifiers */ - xfs_trans_buf_set_type(args->trans, bp2, XFS_BLFT_ATTR_LEAF_BUF); - bp2->b_ops = bp1->b_ops; - memcpy(bp2->b_addr, bp1->b_addr, args->geo->blksize); - if (xfs_has_crc(mp)) { - struct xfs_da3_blkinfo *hdr3 = bp2->b_addr; - hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp2)); - } + /* + * Copy leaf to new buffer and log it. + */ + xfs_da_buf_copy(bp2, bp1, args->geo->blksize); xfs_trans_log_buf(args->trans, bp2, 0, args->geo->blksize - 1); /* @@ -1319,7 +1299,7 @@ xfs_attr3_leaf_create( ichdr.magic = XFS_ATTR3_LEAF_MAGIC; hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp)); - hdr3->owner = cpu_to_be64(dp->i_ino); + hdr3->owner = cpu_to_be64(args->owner); uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid); ichdr.freemap[0].base = sizeof(struct xfs_attr3_leaf_hdr); @@ -1338,6 +1318,9 @@ xfs_attr3_leaf_create( /* * Split the leaf node, rebalance, then add the new entry. + * + * Returns 0 if the entry was added, 1 if a further split is needed or a + * negative error number otherwise. */ int xfs_attr3_leaf_split( @@ -1345,8 +1328,9 @@ xfs_attr3_leaf_split( struct xfs_da_state_blk *oldblk, struct xfs_da_state_blk *newblk) { - xfs_dablk_t blkno; - int error; + bool added; + xfs_dablk_t blkno; + int error; trace_xfs_attr_leaf_split(state->args); @@ -1381,10 +1365,10 @@ xfs_attr3_leaf_split( */ if (state->inleaf) { trace_xfs_attr_leaf_add_old(state->args); - error = xfs_attr3_leaf_add(oldblk->bp, state->args); + added = xfs_attr3_leaf_add(oldblk->bp, state->args); } else { trace_xfs_attr_leaf_add_new(state->args); - error = xfs_attr3_leaf_add(newblk->bp, state->args); + added = xfs_attr3_leaf_add(newblk->bp, state->args); } /* @@ -1392,13 +1376,15 @@ xfs_attr3_leaf_split( */ oldblk->hashval = xfs_attr_leaf_lasthash(oldblk->bp, NULL); newblk->hashval = xfs_attr_leaf_lasthash(newblk->bp, NULL); - return error; + if (!added) + return 1; + return 0; } /* * Add a name to the leaf attribute list structure. */ -int +bool xfs_attr3_leaf_add( struct xfs_buf *bp, struct xfs_da_args *args) @@ -1407,6 +1393,7 @@ xfs_attr3_leaf_add( struct xfs_attr3_icleaf_hdr ichdr; int tablesize; int entsize; + bool added = true; int sum; int tmp; int i; @@ -1435,7 +1422,7 @@ xfs_attr3_leaf_add( if (ichdr.freemap[i].base < ichdr.firstused) tmp += sizeof(xfs_attr_leaf_entry_t); if (ichdr.freemap[i].size >= tmp) { - tmp = xfs_attr3_leaf_add_work(bp, &ichdr, args, i); + xfs_attr3_leaf_add_work(bp, &ichdr, args, i); goto out_log_hdr; } sum += ichdr.freemap[i].size; @@ -1447,7 +1434,7 @@ xfs_attr3_leaf_add( * no good and we should just give up. */ if (!ichdr.holes && sum < entsize) - return -ENOSPC; + return false; /* * Compact the entries to coalesce free space. @@ -1460,24 +1447,24 @@ xfs_attr3_leaf_add( * free region, in freemap[0]. If it is not big enough, give up. */ if (ichdr.freemap[0].size < (entsize + sizeof(xfs_attr_leaf_entry_t))) { - tmp = -ENOSPC; + added = false; goto out_log_hdr; } - tmp = xfs_attr3_leaf_add_work(bp, &ichdr, args, 0); + xfs_attr3_leaf_add_work(bp, &ichdr, args, 0); out_log_hdr: xfs_attr3_leaf_hdr_to_disk(args->geo, leaf, &ichdr); xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, &leaf->hdr, xfs_attr3_leaf_hdr_size(leaf))); - return tmp; + return added; } /* * Add a name to a leaf attribute list structure. */ -STATIC int +STATIC void xfs_attr3_leaf_add_work( struct xfs_buf *bp, struct xfs_attr3_icleaf_hdr *ichdr, @@ -1595,7 +1582,6 @@ xfs_attr3_leaf_add_work( } } ichdr->usedbytes += xfs_attr_leaf_entsize(leaf, args->index); - return 0; } /* @@ -1615,7 +1601,7 @@ xfs_attr3_leaf_compact( trace_xfs_attr_leaf_compact(args); - tmpbuffer = kmem_alloc(args->geo->blksize, 0); + tmpbuffer = kvmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL); memcpy(tmpbuffer, bp->b_addr, args->geo->blksize); memset(bp->b_addr, 0, args->geo->blksize); leaf_src = (xfs_attr_leafblock_t *)tmpbuffer; @@ -1653,7 +1639,7 @@ xfs_attr3_leaf_compact( */ xfs_trans_log_buf(trans, bp, 0, args->geo->blksize - 1); - kmem_free(tmpbuffer); + kvfree(tmpbuffer); } /* @@ -2075,7 +2061,7 @@ xfs_attr3_leaf_toosmall( if (blkno == 0) continue; error = xfs_attr3_leaf_read(state->args->trans, state->args->dp, - blkno, &bp); + state->args->owner, blkno, &bp); if (error) return error; @@ -2293,8 +2279,6 @@ xfs_attr3_leaf_unbalance( trace_xfs_attr_leaf_unbalance(state->args); - drop_leaf = drop_blk->bp->b_addr; - save_leaf = save_blk->bp->b_addr; xfs_attr3_leaf_hdr_from_disk(state->args->geo, &drophdr, drop_leaf); xfs_attr3_leaf_hdr_from_disk(state->args->geo, &savehdr, save_leaf); entry = xfs_attr3_leaf_entryp(drop_leaf); @@ -2334,7 +2318,8 @@ xfs_attr3_leaf_unbalance( struct xfs_attr_leafblock *tmp_leaf; struct xfs_attr3_icleaf_hdr tmphdr; - tmp_leaf = kmem_zalloc(state->args->geo->blksize, 0); + tmp_leaf = kvzalloc(state->args->geo->blksize, + GFP_KERNEL | __GFP_NOFAIL); /* * Copy the header into the temp leaf so that all the stuff @@ -2374,7 +2359,7 @@ xfs_attr3_leaf_unbalance( } memcpy(save_leaf, tmp_leaf, state->args->geo->blksize); savehdr = tmphdr; /* struct copy */ - kmem_free(tmp_leaf); + kvfree(tmp_leaf); } xfs_attr3_leaf_hdr_to_disk(state->args->geo, save_leaf, &savehdr); @@ -2427,6 +2412,7 @@ xfs_attr3_leaf_lookup_int( entries = xfs_attr3_leaf_entryp(leaf); if (ichdr.count >= args->geo->blksize / 8) { xfs_buf_mark_corrupt(bp); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } @@ -2446,10 +2432,12 @@ xfs_attr3_leaf_lookup_int( } if (!(probe >= 0 && (!ichdr.count || probe < ichdr.count))) { xfs_buf_mark_corrupt(bp); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } if (!(span <= 4 || be32_to_cpu(entry->hashval) == hashval)) { xfs_buf_mark_corrupt(bp); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } @@ -2481,18 +2469,23 @@ xfs_attr3_leaf_lookup_int( */ if (entry->flags & XFS_ATTR_LOCAL) { name_loc = xfs_attr3_leaf_name_local(leaf, probe); - if (!xfs_attr_match(args, name_loc->namelen, - name_loc->nameval, entry->flags)) + if (!xfs_attr_match(args, entry->flags, + name_loc->nameval, name_loc->namelen, + &name_loc->nameval[name_loc->namelen], + be16_to_cpu(name_loc->valuelen))) continue; args->index = probe; return -EEXIST; } else { + unsigned int valuelen; + name_rmt = xfs_attr3_leaf_name_remote(leaf, probe); - if (!xfs_attr_match(args, name_rmt->namelen, - name_rmt->name, entry->flags)) + valuelen = be32_to_cpu(name_rmt->valuelen); + if (!xfs_attr_match(args, entry->flags, name_rmt->name, + name_rmt->namelen, NULL, valuelen)) continue; args->index = probe; - args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen); + args->rmtvaluelen = valuelen; args->rmtblkno = be32_to_cpu(name_rmt->valueblk); args->rmtblkcnt = xfs_attr3_rmt_blocks( args->dp->i_mount, @@ -2795,7 +2788,8 @@ xfs_attr3_leaf_clearflag( /* * Set up the operation. */ - error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp); + error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, + args->blkno, &bp); if (error) return error; @@ -2859,7 +2853,8 @@ xfs_attr3_leaf_setflag( /* * Set up the operation. */ - error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp); + error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, + args->blkno, &bp); if (error) return error; @@ -2918,7 +2913,8 @@ xfs_attr3_leaf_flipflags( /* * Read the block containing the "old" attr */ - error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp1); + error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, + args->blkno, &bp1); if (error) return error; @@ -2926,8 +2922,8 @@ xfs_attr3_leaf_flipflags( * Read the block containing the "new" attr, if it is different */ if (args->blkno2 != args->blkno) { - error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno2, - &bp2); + error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, + args->blkno2, &bp2); if (error) return error; } else { diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index 368f4d9fa1d5..589f810eedc0 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -47,16 +47,14 @@ struct xfs_attr3_icleaf_hdr { */ void xfs_attr_shortform_create(struct xfs_da_args *args); void xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff); -int xfs_attr_shortform_lookup(struct xfs_da_args *args); int xfs_attr_shortform_getvalue(struct xfs_da_args *args); int xfs_attr_shortform_to_leaf(struct xfs_da_args *args); int xfs_attr_sf_removename(struct xfs_da_args *args); -int xfs_attr_sf_findname(struct xfs_da_args *args, - struct xfs_attr_sf_entry **sfep, - unsigned int *basep); +struct xfs_attr_sf_entry *xfs_attr_sf_findname(struct xfs_da_args *args); int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp); int xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes); -xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_inode *ip); +xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_attr_sf_hdr *sfp, + size_t size); void xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp); /* @@ -78,7 +76,7 @@ int xfs_attr3_leaf_split(struct xfs_da_state *state, int xfs_attr3_leaf_lookup_int(struct xfs_buf *leaf, struct xfs_da_args *args); int xfs_attr3_leaf_getvalue(struct xfs_buf *bp, struct xfs_da_args *args); -int xfs_attr3_leaf_add(struct xfs_buf *leaf_buffer, +bool xfs_attr3_leaf_add(struct xfs_buf *leaf_buffer, struct xfs_da_args *args); int xfs_attr3_leaf_remove(struct xfs_buf *leaf_buffer, struct xfs_da_args *args); @@ -100,12 +98,14 @@ int xfs_attr_leaf_order(struct xfs_buf *leaf1_bp, struct xfs_buf *leaf2_bp); int xfs_attr_leaf_newentsize(struct xfs_da_args *args, int *local); int xfs_attr3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp, - xfs_dablk_t bno, struct xfs_buf **bpp); + xfs_ino_t owner, xfs_dablk_t bno, struct xfs_buf **bpp); void xfs_attr3_leaf_hdr_from_disk(struct xfs_da_geometry *geo, struct xfs_attr3_icleaf_hdr *to, struct xfs_attr_leafblock *from); void xfs_attr3_leaf_hdr_to_disk(struct xfs_da_geometry *geo, struct xfs_attr_leafblock *to, struct xfs_attr3_icleaf_hdr *from); +xfs_failaddr_t xfs_attr3_leaf_header_check(struct xfs_buf *bp, + xfs_ino_t owner); #endif /* __XFS_ATTR_LEAF_H__ */ diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index d440393b40eb..bff3dc226f81 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -22,6 +22,7 @@ #include "xfs_attr_remote.h" #include "xfs_trace.h" #include "xfs_error.h" +#include "xfs_health.h" #define ATTR_RMTVALUE_MAPSIZE 1 /* # of map entries at once */ @@ -42,19 +43,32 @@ * the logging system and therefore never have a log item. */ -/* - * Each contiguous block has a header, so it is not just a simple attribute - * length to FSB conversion. - */ -int +/* How many bytes can be stored in a remote value buffer? */ +inline unsigned int +xfs_attr3_rmt_buf_space( + struct xfs_mount *mp) +{ + unsigned int blocksize = mp->m_attr_geo->blksize; + + if (xfs_has_crc(mp)) + return blocksize - sizeof(struct xfs_attr3_rmt_hdr); + + return blocksize; +} + +/* Compute number of fsblocks needed to store a remote attr value */ +unsigned int xfs_attr3_rmt_blocks( - struct xfs_mount *mp, - int attrlen) + struct xfs_mount *mp, + unsigned int attrlen) { - if (xfs_has_crc(mp)) { - int buflen = XFS_ATTR3_RMT_BUF_SPACE(mp, mp->m_sb.sb_blocksize); - return (attrlen + buflen - 1) / buflen; - } + /* + * Each contiguous block has a header, so it is not just a simple + * attribute length to FSB conversion. + */ + if (xfs_has_crc(mp)) + return howmany(attrlen, xfs_attr3_rmt_buf_space(mp)); + return XFS_B_TO_FSB(mp, attrlen); } @@ -91,7 +105,6 @@ xfs_attr3_rmt_verify( struct xfs_mount *mp, struct xfs_buf *bp, void *ptr, - int fsbsize, xfs_daddr_t bno) { struct xfs_attr3_rmt_hdr *rmt = ptr; @@ -102,7 +115,7 @@ xfs_attr3_rmt_verify( return __this_address; if (be64_to_cpu(rmt->rm_blkno) != bno) return __this_address; - if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt)) + if (be32_to_cpu(rmt->rm_bytes) > mp->m_attr_geo->blksize - sizeof(*rmt)) return __this_address; if (be32_to_cpu(rmt->rm_offset) + be32_to_cpu(rmt->rm_bytes) > XFS_XATTR_SIZE_MAX) @@ -121,9 +134,9 @@ __xfs_attr3_rmt_read_verify( { struct xfs_mount *mp = bp->b_mount; char *ptr; - int len; + unsigned int len; xfs_daddr_t bno; - int blksize = mp->m_attr_geo->blksize; + unsigned int blksize = mp->m_attr_geo->blksize; /* no verification of non-crc buffers */ if (!xfs_has_crc(mp)) @@ -140,7 +153,7 @@ __xfs_attr3_rmt_read_verify( *failaddr = __this_address; return -EFSBADCRC; } - *failaddr = xfs_attr3_rmt_verify(mp, bp, ptr, blksize, bno); + *failaddr = xfs_attr3_rmt_verify(mp, bp, ptr, bno); if (*failaddr) return -EFSCORRUPTED; len -= blksize; @@ -185,7 +198,7 @@ xfs_attr3_rmt_write_verify( { struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; - int blksize = mp->m_attr_geo->blksize; + unsigned int blksize = mp->m_attr_geo->blksize; char *ptr; int len; xfs_daddr_t bno; @@ -202,7 +215,7 @@ xfs_attr3_rmt_write_verify( while (len > 0) { struct xfs_attr3_rmt_hdr *rmt = (struct xfs_attr3_rmt_hdr *)ptr; - fa = xfs_attr3_rmt_verify(mp, bp, ptr, blksize, bno); + fa = xfs_attr3_rmt_verify(mp, bp, ptr, bno); if (fa) { xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; @@ -276,32 +289,34 @@ xfs_attr3_rmt_hdr_set( */ STATIC int xfs_attr_rmtval_copyout( - struct xfs_mount *mp, - struct xfs_buf *bp, - xfs_ino_t ino, - int *offset, - int *valuelen, - uint8_t **dst) + struct xfs_mount *mp, + struct xfs_buf *bp, + struct xfs_inode *dp, + xfs_ino_t owner, + unsigned int *offset, + unsigned int *valuelen, + uint8_t **dst) { - char *src = bp->b_addr; - xfs_daddr_t bno = xfs_buf_daddr(bp); - int len = BBTOB(bp->b_length); - int blksize = mp->m_attr_geo->blksize; + char *src = bp->b_addr; + xfs_daddr_t bno = xfs_buf_daddr(bp); + unsigned int len = BBTOB(bp->b_length); + unsigned int blksize = mp->m_attr_geo->blksize; ASSERT(len >= blksize); while (len > 0 && *valuelen > 0) { - int hdr_size = 0; - int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize); + unsigned int hdr_size = 0; + unsigned int byte_cnt = xfs_attr3_rmt_buf_space(mp); byte_cnt = min(*valuelen, byte_cnt); if (xfs_has_crc(mp)) { - if (xfs_attr3_rmt_hdr_ok(src, ino, *offset, + if (xfs_attr3_rmt_hdr_ok(src, owner, *offset, byte_cnt, bno)) { xfs_alert(mp, "remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)", - bno, *offset, byte_cnt, ino); + bno, *offset, byte_cnt, owner); + xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); return -EFSCORRUPTED; } hdr_size = sizeof(struct xfs_attr3_rmt_hdr); @@ -327,20 +342,20 @@ xfs_attr_rmtval_copyin( struct xfs_mount *mp, struct xfs_buf *bp, xfs_ino_t ino, - int *offset, - int *valuelen, + unsigned int *offset, + unsigned int *valuelen, uint8_t **src) { char *dst = bp->b_addr; xfs_daddr_t bno = xfs_buf_daddr(bp); - int len = BBTOB(bp->b_length); - int blksize = mp->m_attr_geo->blksize; + unsigned int len = BBTOB(bp->b_length); + unsigned int blksize = mp->m_attr_geo->blksize; ASSERT(len >= blksize); while (len > 0 && *valuelen > 0) { - int hdr_size; - int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize); + unsigned int hdr_size; + unsigned int byte_cnt = xfs_attr3_rmt_buf_space(mp); byte_cnt = min(*valuelen, byte_cnt); hdr_size = xfs_attr3_rmt_hdr_set(mp, dst, ino, *offset, @@ -386,12 +401,12 @@ xfs_attr_rmtval_get( struct xfs_buf *bp; xfs_dablk_t lblkno = args->rmtblkno; uint8_t *dst = args->value; - int valuelen; + unsigned int valuelen; int nmap; int error; - int blkcnt = args->rmtblkcnt; + unsigned int blkcnt = args->rmtblkcnt; int i; - int offset = 0; + unsigned int offset = 0; trace_xfs_attr_rmtval_get(args); @@ -418,12 +433,20 @@ xfs_attr_rmtval_get( dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount); error = xfs_buf_read(mp->m_ddev_targp, dblkno, dblkcnt, 0, &bp, &xfs_attr3_rmt_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_dirattr_mark_sick(args->dp, XFS_ATTR_FORK); + /* + * ENODATA from disk implies a disk medium failure; + * ENODATA for xattrs means attribute not found, so + * disambiguate that here. + */ + if (error == -ENODATA) + error = -EIO; if (error) return error; - error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino, - &offset, &valuelen, - &dst); + error = xfs_attr_rmtval_copyout(mp, bp, args->dp, + args->owner, &offset, &valuelen, &dst); xfs_buf_relse(bp); if (error) return error; @@ -448,7 +471,7 @@ xfs_attr_rmt_find_hole( struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; int error; - int blkcnt; + unsigned int blkcnt; xfs_fileoff_t lfileoff = 0; /* @@ -477,11 +500,11 @@ xfs_attr_rmtval_set_value( struct xfs_bmbt_irec map; xfs_dablk_t lblkno; uint8_t *src = args->value; - int blkcnt; - int valuelen; + unsigned int blkcnt; + unsigned int valuelen; int nmap; int error; - int offset = 0; + unsigned int offset = 0; /* * Roll through the "value", copying the attribute value to the @@ -517,8 +540,8 @@ xfs_attr_rmtval_set_value( return error; bp->b_ops = &xfs_attr3_rmt_buf_ops; - xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset, - &valuelen, &src); + xfs_attr_rmtval_copyin(mp, bp, args->owner, &offset, &valuelen, + &src); error = xfs_bwrite(bp); /* GROT: NOTE: synchronous write */ xfs_buf_relse(bp); @@ -545,11 +568,13 @@ xfs_attr_rmtval_stale( struct xfs_buf *bp; int error; - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); if (XFS_IS_CORRUPT(mp, map->br_startblock == DELAYSTARTBLOCK) || - XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK)) + XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK)) { + xfs_bmap_mark_sick(ip, XFS_ATTR_FORK); return -EFSCORRUPTED; + } error = xfs_buf_incore(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, map->br_startblock), @@ -619,7 +644,6 @@ xfs_attr_rmtval_set_blk( if (error) return error; - ASSERT(nmap == 1); ASSERT((map->br_startblock != DELAYSTARTBLOCK) && (map->br_startblock != HOLESTARTBLOCK)); @@ -639,7 +663,7 @@ xfs_attr_rmtval_invalidate( struct xfs_da_args *args) { xfs_dablk_t lblkno; - int blkcnt; + unsigned int blkcnt; int error; /* @@ -659,8 +683,10 @@ xfs_attr_rmtval_invalidate( blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK); if (error) return error; - if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1)) + if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1)) { + xfs_bmap_mark_sick(args->dp, XFS_ATTR_FORK); return -EFSCORRUPTED; + } error = xfs_attr_rmtval_stale(args->dp, &map, XBF_TRYLOCK); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_attr_remote.h b/fs/xfs/libxfs/xfs_attr_remote.h index d097ec6c4dc3..e3c6c7d774bf 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.h +++ b/fs/xfs/libxfs/xfs_attr_remote.h @@ -6,7 +6,13 @@ #ifndef __XFS_ATTR_REMOTE_H__ #define __XFS_ATTR_REMOTE_H__ -int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen); +unsigned int xfs_attr3_rmt_blocks(struct xfs_mount *mp, unsigned int attrlen); + +/* Number of rmt blocks needed to store the maximally sized attr value */ +static inline unsigned int xfs_attr3_max_rmt_blocks(struct xfs_mount *mp) +{ + return xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX); +} int xfs_attr_rmtval_get(struct xfs_da_args *args); int xfs_attr_rmtval_stale(struct xfs_inode *ip, struct xfs_bmbt_irec *map, diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h index 37578b369d9b..73bdc0e55682 100644 --- a/fs/xfs/libxfs/xfs_attr_sf.h +++ b/fs/xfs/libxfs/xfs_attr_sf.h @@ -7,14 +7,6 @@ #define __XFS_ATTR_SF_H__ /* - * Attribute storage when stored inside the inode. - * - * Small attribute lists are packed as tightly as possible so as - * to fit into the literal area of the inode. - */ -typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t; - -/* * We generate this then sort it, attr_list() must return things in hash-order. */ typedef struct xfs_attr_sf_sort { @@ -24,6 +16,7 @@ typedef struct xfs_attr_sf_sort { uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */ xfs_dahash_t hash; /* this entry's hash value */ unsigned char *name; /* name value, pointer into buffer */ + void *value; } xfs_attr_sf_sort_t; #define XFS_ATTR_SF_ENTSIZE_MAX /* max space for name&value */ \ @@ -41,11 +34,25 @@ static inline int xfs_attr_sf_entsize(struct xfs_attr_sf_entry *sfep) return struct_size(sfep, nameval, sfep->namelen + sfep->valuelen); } -/* next entry in struct */ +/* first entry in the SF attr fork */ +static inline struct xfs_attr_sf_entry * +xfs_attr_sf_firstentry(struct xfs_attr_sf_hdr *hdr) +{ + return (struct xfs_attr_sf_entry *)(hdr + 1); +} + +/* next entry after sfep */ static inline struct xfs_attr_sf_entry * xfs_attr_sf_nextentry(struct xfs_attr_sf_entry *sfep) { return (void *)sfep + xfs_attr_sf_entsize(sfep); } +/* pointer to the space after the last entry, e.g. for adding a new one */ +static inline struct xfs_attr_sf_entry * +xfs_attr_sf_endptr(struct xfs_attr_sf_hdr *sf) +{ + return (void *)sf + be16_to_cpu(sf->totsize); +} + #endif /* __XFS_ATTR_SF_H__ */ diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 0d56a8d862e8..53ef4b7e504d 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -21,7 +21,7 @@ #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" @@ -34,8 +34,13 @@ #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_refcount.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" struct kmem_cache *xfs_bmap_intent_cache; @@ -75,9 +80,9 @@ xfs_bmap_compute_maxlevels( maxleafents = xfs_iext_max_nextents(xfs_has_large_extent_counts(mp), whichfork); if (whichfork == XFS_DATA_FORK) - sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS); + sz = xfs_bmdr_space_calc(MINDBTPTRS); else - sz = XFS_BMDR_SPACE_CALC(MINABTPTRS); + sz = xfs_bmdr_space_calc(MINABTPTRS); maxrootrecs = xfs_bmdr_maxrecs(sz, 0); minleafrecs = mp->m_bmap_dmnr[0]; @@ -98,8 +103,8 @@ 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); + return XFS_LITINO(mp) - xfs_bmdr_space_calc(MINABTPTRS); + return xfs_bmdr_space_calc(6 * MINABTPTRS); } STATIC int /* error */ @@ -166,18 +171,16 @@ 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 */ + struct xfs_mount *mp = ip->i_mount; + int maxrecs = mp->m_bmap_dmxr[0]; + int level; + xfs_filblks_t rval; - mp = ip->i_mount; - maxrecs = mp->m_bmap_dmxr[0]; for (level = 0, rval = 0; level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK); level++) { @@ -225,6 +228,28 @@ xfs_bmap_forkoff_reset( } } +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( @@ -272,7 +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) < @@ -284,15 +309,15 @@ 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) %lld", __func__, j, i, @@ -347,7 +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); @@ -364,9 +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, &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; } @@ -380,9 +405,10 @@ 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); if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, bno))) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -419,14 +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)); @@ -450,9 +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, &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; } @@ -557,29 +583,37 @@ xfs_bmap_btree_to_extents( 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); + ASSERT(xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false) == 1); - pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes); + pp = xfs_bmap_broot_ptr_addr(mp, rblock, 1, ifp->if_broot_bytes); cbno = be64_to_cpu(*pp); #ifdef DEBUG - if (XFS_IS_CORRUPT(cur->bc_mp, !xfs_btree_check_lptr(cur, cbno, 1))) + 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, &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_free_extent_later(cur->bc_tp, cbno, 1, &oinfo); + 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_levels[0].bp == cbp) cur->bc_levels[0].bp = NULL; - xfs_iroot_realloc(ip, -1, whichfork); + xfs_bmap_broot_realloc(ip, whichfork, 0); ASSERT(ifp->if_broot == NULL); ifp->if_format = XFS_DINODE_FMT_EXTENTS; *logflagsp |= XFS_ILOG_CORE | xfs_ilog_fext(whichfork); @@ -623,20 +657,18 @@ xfs_bmap_extents_to_btree( * Make space in the inode incore. This needs to be undone if we fail * to expand the root. */ - xfs_iroot_realloc(ip, 1, whichfork); + 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_ino.flags = wasdel ? XFS_BTCUR_BMBT_WASDEL : 0; + if (wasdel) + cur->bc_flags |= XFS_BTREE_BMBT_WASDEL; /* * Convert to a btree with two levels, one record in root. */ @@ -645,35 +677,24 @@ xfs_bmap_extents_to_btree( args.tp = tp; args.mp = mp; xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork); - if (tp->t_firstblock == NULLFSBLOCK) { - args.type = XFS_ALLOCTYPE_START_BNO; - args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino); - } else if (tp->t_flags & XFS_TRANS_LOWMODE) { - args.type = XFS_ALLOCTYPE_START_BNO; - args.fsbno = tp->t_firstblock; - } else { - args.type = XFS_ALLOCTYPE_NEAR_BNO; - args.fsbno = tp->t_firstblock; - } + args.minlen = args.maxlen = args.prod = 1; args.wasdel = wasdel; *logflagsp = 0; - error = xfs_alloc_vextent(&args); + error = xfs_alloc_vextent_start_ag(&args, + XFS_INO_TO_FSB(mp, ip->i_ino)); if (error) goto out_root_realloc; + /* + * Allocation can't fail, the space was reserved. + */ if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { error = -ENOSPC; goto out_root_realloc; } - /* - * Allocation can't fail, the space was reserved. - */ - ASSERT(tp->t_firstblock == NULLFSBLOCK || - args.agno >= XFS_FSB_TO_AGNO(mp, tp->t_firstblock)); - tp->t_firstblock = args.fsbno; - cur->bc_ino.allocated++; + cur->bc_bmap.allocated++; ip->i_nblocks++; xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L); error = xfs_trans_get_buf(tp, mp->m_ddev_targp, @@ -685,16 +706,13 @@ xfs_bmap_extents_to_btree( /* * 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, xfs_buf_daddr(abp), - XFS_BTNUM_BMAP, 0, 0, ip->i_ino, - XFS_BTREE_LONG_PTRS); + 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); + arp = xfs_bmbt_rec_addr(mp, ablock, 1 + cnt); xfs_bmbt_disk_set_all(arp, &rec); cnt++; } @@ -704,10 +722,10 @@ xfs_bmap_extents_to_btree( /* * 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); @@ -725,7 +743,7 @@ xfs_bmap_extents_to_btree( out_unreserve_dquot: xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); out_root_realloc: - xfs_iroot_realloc(ip, -1, whichfork); + 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); @@ -753,14 +771,14 @@ xfs_bmap_local_to_extents_empty( ASSERT(ifp->if_nextents == 0); xfs_bmap_forkoff_reset(ip, whichfork); - ifp->if_u1.if_root = NULL; + 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 */ @@ -770,7 +788,8 @@ xfs_bmap_local_to_extents( 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 */ @@ -799,28 +818,24 @@ xfs_bmap_local_to_extents( 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); + /* * Allocate a block. We know we need only one, since the * file currently fits in an inode. */ - if (tp->t_firstblock == NULLFSBLOCK) { - args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino); - args.type = XFS_ALLOCTYPE_START_BNO; - } else { - args.fsbno = tp->t_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); - tp->t_firstblock = args.fsbno; 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); @@ -835,14 +850,14 @@ 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(tp, ip, whichfork); flags |= XFS_ILOG_CORE; - ifp->if_u1.if_root = NULL; + ifp->if_data = NULL; ifp->if_height = 0; rec.br_startoff = 0; @@ -854,8 +869,7 @@ xfs_bmap_local_to_extents( ifp->if_nextents = 1; ip->i_nblocks = 1; - xfs_trans_mod_dquot_byino(tp, ip, - XFS_TRANS_DQ_BCOUNT, 1L); + xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L); flags |= xfs_ilog_fext(whichfork); done: @@ -880,7 +894,7 @@ xfs_bmap_add_attrfork_btree( mp = ip->i_mount; - if (XFS_BMAP_BMDR_SPACE(block) <= xfs_inode_data_fork_size(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); @@ -889,6 +903,7 @@ xfs_bmap_add_attrfork_btree( goto error0; /* must be at least one entry */ if (XFS_IS_CORRUPT(mp, stat != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -898,7 +913,7 @@ xfs_bmap_add_attrfork_btree( xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); return -ENOSPC; } - cur->bc_ino.allocated = 0; + cur->bc_bmap.allocated = 0; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); } return 0; @@ -926,7 +941,7 @@ xfs_bmap_add_attrfork_extents( error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, flags, XFS_DATA_FORK); if (cur) { - cur->bc_ino.allocated = 0; + cur->bc_bmap.allocated = 0; xfs_btree_del_cursor(cur, error); } return error; @@ -961,16 +976,18 @@ xfs_bmap_add_attrfork_local( 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, 1, flags, - XFS_DATA_FORK, - xfs_symlink_local_to_remote); + 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; } @@ -980,8 +997,7 @@ xfs_bmap_add_attrfork_local( static int xfs_bmap_set_attrforkoff( struct xfs_inode *ip, - int size, - int *version) + int size) { int default_size = xfs_default_attroffset(ip) >> 3; @@ -995,8 +1011,6 @@ xfs_bmap_set_attrforkoff( ip->i_forkoff = xfs_attr_shortform_bytesfit(ip, size); if (!ip->i_forkoff) ip->i_forkoff = default_size; - else if (xfs_has_attr2(ip->i_mount) && version) - *version = 2; break; default: ASSERT(0); @@ -1007,40 +1021,29 @@ xfs_bmap_set_attrforkoff( } /* - * Convert inode from non-attributed to attributed. - * Must not be in a transaction, ip must not be locked. + * 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( - xfs_inode_t *ip, /* incore inode pointer */ + struct xfs_trans *tp, + struct xfs_inode *ip, /* incore inode pointer */ int size, /* space new attribute needs */ int rsvd) /* xact may use reserved blks */ { - xfs_mount_t *mp; /* mount structure */ - xfs_trans_t *tp; /* transaction pointer */ - int blks; /* space reservation */ - int version = 1; /* superblock attr version */ + struct xfs_mount *mp = tp->t_mountp; int logflags; /* logging flags */ int error; /* error return value */ - ASSERT(xfs_inode_has_attr_fork(ip) == 0); - - mp = ip->i_mount; - ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); - - blks = XFS_ADDAFORK_SPACE_RES(mp); - - error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_addafork, blks, 0, - rsvd, &tp); - if (error) - return error; - if (xfs_inode_has_attr_fork(ip)) - goto trans_cancel; + 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, &version); + error = xfs_bmap_set_attrforkoff(ip, size); if (error) - goto trans_cancel; + return error; xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0); logflags = 0; @@ -1061,17 +1064,13 @@ xfs_bmap_add_attrfork( if (logflags) xfs_trans_log_inode(tp, ip, logflags); if (error) - goto trans_cancel; - if (!xfs_has_attr(mp) || - (!xfs_has_attr2(mp) && version == 2)) { + return error; + if (!xfs_has_attr(mp)) { bool log_sb = false; spin_lock(&mp->m_sb_lock); if (!xfs_has_attr(mp)) { xfs_add_attr(mp); - log_sb = true; - } - if (!xfs_has_attr2(mp) && version == 2) { xfs_add_attr2(mp); log_sb = true; } @@ -1080,14 +1079,7 @@ xfs_bmap_add_attrfork( xfs_log_sb(tp); } - error = xfs_trans_commit(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - return error; - -trans_cancel: - xfs_trans_cancel(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - return error; + return 0; } /* @@ -1099,6 +1091,34 @@ struct xfs_iread_state { 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( @@ -1126,11 +1146,12 @@ xfs_iread_bmbt_block( (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); + 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; @@ -1141,7 +1162,9 @@ xfs_iread_bmbt_block( xfs_inode_verifier_error(ip, -EFSCORRUPTED, "xfs_iread_extents(2)", frp, sizeof(*frp), fa); - return -EFSCORRUPTED; + 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)); @@ -1171,7 +1194,7 @@ xfs_iread_extents( if (!xfs_need_iread_extents(ifp)) return 0; - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); ir.loaded = 0; xfs_iext_first(ifp, &ir.icur); @@ -1183,12 +1206,21 @@ xfs_iread_extents( 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)); + /* + * 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. + */ + smp_store_release(&ifp->if_needextents, 0); return 0; out: + if (xfs_metadata_is_sick(error)) + xfs_bmap_mark_sick(ip, whichfork); xfs_iext_destroy(ifp); return error; } @@ -1268,6 +1300,7 @@ xfs_bmap_last_before( break; default: ASSERT(0); + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } @@ -1364,8 +1397,10 @@ xfs_bmap_last_offset( if (ifp->if_format == XFS_DINODE_FMT_LOCAL) return 0; - if (XFS_IS_CORRUPT(ip->i_mount, !xfs_ifork_has_extents(ifp))) + 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) @@ -1379,6 +1414,24 @@ xfs_bmap_last_offset( * Extent tree manipulation functions used during allocation. */ +static inline bool +xfs_bmap_same_rtgroup( + struct xfs_inode *ip, + int whichfork, + struct xfs_bmbt_irec *left, + struct xfs_bmbt_irec *right) +{ + struct xfs_mount *mp = ip->i_mount; + + 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; + } + + return true; +} + /* * Convert a delayed allocation to a real allocation. */ @@ -1405,8 +1458,7 @@ xfs_bmap_add_extent_delay_real( ASSERT(whichfork != XFS_ATTR_FORK); ASSERT(!isnullstartblock(new->br_startblock)); - ASSERT(!bma->cur || - (bma->cur->bc_ino.flags & XFS_BTCUR_BMBT_WASDEL)); + ASSERT(!bma->cur || (bma->cur->bc_flags & XFS_BTREE_BMBT_WASDEL)); XFS_STATS_INC(mp, xs_add_exlist); @@ -1449,7 +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 <= XFS_MAX_BMBT_EXTLEN) + LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN && + xfs_bmap_same_rtgroup(bma->ip, whichfork, &LEFT, new)) state |= BMAP_LEFT_CONTIG; /* @@ -1473,7 +1526,8 @@ xfs_bmap_add_extent_delay_real( (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING) || LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount - <= XFS_MAX_BMBT_EXTLEN)) + <= XFS_MAX_BMBT_EXTLEN) && + xfs_bmap_same_rtgroup(bma->ip, whichfork, new, &RIGHT)) state |= BMAP_RIGHT_CONTIG; error = 0; @@ -1504,6 +1558,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1511,6 +1566,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1518,6 +1574,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1525,6 +1582,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_LEFT_CONTIG: @@ -1547,6 +1605,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1554,6 +1613,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG: @@ -1580,6 +1640,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1587,6 +1648,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING: @@ -1608,6 +1670,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1615,10 +1678,12 @@ xfs_bmap_add_extent_delay_real( if (error) goto 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: @@ -1649,6 +1714,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1656,6 +1722,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING: @@ -1674,6 +1741,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1681,6 +1749,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1697,7 +1766,7 @@ xfs_bmap_add_extent_delay_real( 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_ino.allocated : 0)); + (bma->cur ? bma->cur->bc_bmap.allocated : 0)); PREV.br_startoff = new_endoff; PREV.br_blockcount = temp; @@ -1725,6 +1794,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1743,6 +1813,7 @@ xfs_bmap_add_extent_delay_real( 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: @@ -1761,6 +1832,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1768,6 +1840,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1784,12 +1857,13 @@ xfs_bmap_add_extent_delay_real( 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_ino.allocated : 0)); + (bma->cur ? bma->cur->bc_bmap.allocated : 0)); 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: @@ -1847,6 +1921,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1854,6 +1929,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(bma->cur); error = -EFSCORRUPTED; goto done; } @@ -1902,19 +1978,18 @@ xfs_bmap_add_extent_delay_real( } if (da_new != da_old) - xfs_mod_delalloc(mp, (int64_t)da_new - da_old); + xfs_mod_delalloc(bma->ip, 0, (int64_t)da_new - da_old); if (bma->cur) { - da_new += bma->cur->bc_ino.allocated; - bma->cur->bc_ino.allocated = 0; + da_new += bma->cur->bc_bmap.allocated; + bma->cur->bc_bmap.allocated = 0; } /* adjust for changes in reserved delayed indirect blocks */ - if (da_new != da_old) { - ASSERT(state == 0 || da_new < da_old); - error = xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), - false); - } + 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: @@ -1997,7 +2072,8 @@ xfs_bmap_add_extent_unwritten_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 <= XFS_MAX_BMBT_EXTLEN) + LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN && + xfs_bmap_same_rtgroup(ip, whichfork, &LEFT, new)) state |= BMAP_LEFT_CONTIG; /* @@ -2021,7 +2097,8 @@ xfs_bmap_add_extent_unwritten_real( (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING) || LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount - <= XFS_MAX_BMBT_EXTLEN)) + <= XFS_MAX_BMBT_EXTLEN) && + xfs_bmap_same_rtgroup(ip, whichfork, new, &RIGHT)) state |= BMAP_RIGHT_CONTIG; /* @@ -2050,30 +2127,35 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto 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; 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; 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; 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; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2102,18 +2184,21 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto 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; 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; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2145,18 +2230,21 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto 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; 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; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2183,6 +2271,7 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2216,6 +2305,7 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2253,6 +2343,7 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2263,6 +2354,7 @@ xfs_bmap_add_extent_unwritten_real( if ((error = xfs_btree_insert(cur, &i))) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2293,6 +2385,7 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2329,6 +2422,7 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2339,12 +2433,14 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto done; 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; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2381,6 +2477,7 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2393,6 +2490,7 @@ xfs_bmap_add_extent_unwritten_real( if ((error = xfs_btree_insert(cur, &i))) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2405,6 +2503,7 @@ xfs_bmap_add_extent_unwritten_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2412,6 +2511,7 @@ xfs_bmap_add_extent_unwritten_real( if ((error = xfs_btree_insert(cur, &i))) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2448,7 +2548,7 @@ xfs_bmap_add_extent_unwritten_real( /* clear out the allocated field, done with it now in any case. */ if (cur) { - cur->bc_ino.allocated = 0; + cur->bc_bmap.allocated = 0; *curp = cur; } @@ -2462,146 +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, - struct xfs_iext_cursor *icur, - xfs_bmbt_irec_t *new) /* new data to add to file extents */ -{ - struct xfs_ifork *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 */ - uint32_t state = xfs_bmap_fork_to_state(whichfork); - xfs_filblks_t temp; /* temp for indirect calculations */ - - ifp = xfs_ifork_ptr(ip, whichfork); - ASSERT(isnullstartblock(new->br_startblock)); - - /* - * Check and set flags if this segment has a left neighbor - */ - if (xfs_iext_peek_prev_extent(ifp, icur, &left)) { - state |= BMAP_LEFT_VALID; - 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 (xfs_iext_get_extent(ifp, icur, &right)) { - state |= BMAP_RIGHT_VALID; - 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 <= XFS_MAX_BMBT_EXTLEN) - 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 <= XFS_MAX_BMBT_EXTLEN && - (!(state & BMAP_LEFT_CONTIG) || - (left.br_blockcount + new->br_blockcount + - right.br_blockcount <= XFS_MAX_BMBT_EXTLEN))) - 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. - */ - temp = left.br_blockcount + new->br_blockcount + - right.br_blockcount; - - oldlen = startblockval(left.br_startblock) + - startblockval(new->br_startblock) + - startblockval(right.br_startblock); - newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - oldlen); - left.br_startblock = nullstartblock(newlen); - left.br_blockcount = temp; - - xfs_iext_remove(ip, icur, state); - xfs_iext_prev(ifp, icur); - xfs_iext_update_extent(ip, state, icur, &left); - break; - - case BMAP_LEFT_CONTIG: - /* - * New allocation is contiguous with a delayed allocation - * on the left. - * Merge the new allocation with the left neighbor. - */ - temp = left.br_blockcount + new->br_blockcount; - - oldlen = startblockval(left.br_startblock) + - startblockval(new->br_startblock); - newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - oldlen); - left.br_blockcount = temp; - left.br_startblock = nullstartblock(newlen); - - xfs_iext_prev(ifp, icur); - xfs_iext_update_extent(ip, state, icur, &left); - break; - - case BMAP_RIGHT_CONTIG: - /* - * New allocation is contiguous with a delayed allocation - * on the right. - * Merge the new allocation with the right neighbor. - */ - 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); - right.br_startoff = new->br_startoff; - right.br_startblock = nullstartblock(newlen); - right.br_blockcount = temp; - xfs_iext_update_extent(ip, state, icur, &right); - break; - - case 0: - /* - * New allocation is not contiguous with another - * delayed allocation. - * Insert a new entry. - */ - oldlen = newlen = 0; - xfs_iext_insert(ip, icur, 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. - */ - xfs_mod_delalloc(ip->i_mount, (int64_t)newlen - oldlen); - } -} - -/* * Convert a hole to a real allocation. */ STATIC int /* error */ @@ -2627,7 +2587,7 @@ xfs_bmap_add_extent_hole_real( struct xfs_bmbt_irec old; ASSERT(!isnullstartblock(new->br_startblock)); - ASSERT(!cur || !(cur->bc_ino.flags & XFS_BTCUR_BMBT_WASDEL)); + ASSERT(!cur || !(cur->bc_flags & XFS_BTREE_BMBT_WASDEL)); XFS_STATS_INC(mp, xs_add_exlist); @@ -2658,7 +2618,8 @@ 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 <= XFS_MAX_BMBT_EXTLEN) + 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) && @@ -2668,7 +2629,8 @@ xfs_bmap_add_extent_hole_real( new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN && (!(state & BMAP_LEFT_CONTIG) || left.br_blockcount + new->br_blockcount + - right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)) + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN) && + xfs_bmap_same_rtgroup(ip, whichfork, new, &right)) state |= BMAP_RIGHT_CONTIG; error = 0; @@ -2697,6 +2659,7 @@ xfs_bmap_add_extent_hole_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2704,6 +2667,7 @@ xfs_bmap_add_extent_hole_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2711,6 +2675,7 @@ xfs_bmap_add_extent_hole_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2740,6 +2705,7 @@ xfs_bmap_add_extent_hole_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2770,6 +2736,7 @@ xfs_bmap_add_extent_hole_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2796,6 +2763,7 @@ xfs_bmap_add_extent_hole_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2803,6 +2771,7 @@ xfs_bmap_add_extent_hole_real( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -2829,7 +2798,7 @@ xfs_bmap_add_extent_hole_real( /* clear out the allocated field, done with it now in any case. */ if (cur) - cur->bc_ino.allocated = 0; + cur->bc_bmap.allocated = 0; xfs_bmap_check_leaf_extents(cur, ip, whichfork); done: @@ -2965,7 +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. @@ -2992,7 +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. @@ -3018,55 +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->tp->t_firstblock == NULLFSBLOCK; - rt = XFS_IS_REALTIME_INODE(ap->ip) && - (ap->datatype & XFS_ALLOC_USERDATA); - fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, - ap->tp->t_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 */ @@ -3080,7 +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. */ @@ -3096,18 +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. @@ -3136,20 +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. @@ -3160,165 +3128,119 @@ 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) { + if (!xfs_perag_initialised_agf(pag)) { error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_TRYLOCK, NULL); - if (error) { - /* Couldn't lock the AGF, so skip this AG. */ - if (error == -EAGAIN) { - *notinit = 1; - error = 0; - } - goto out; - } + if (error) + return error; } longest = xfs_alloc_longest_free_extent(pag, - xfs_alloc_min_freelist(mp, 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) -{ - 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; - } -} - -STATIC int -xfs_bmap_btalloc_nullfb( - struct xfs_bmalloca *ap, - struct xfs_alloc_arg *args, - xfs_extlen_t *blen) + xfs_extlen_t blen) { - struct xfs_mount *mp = ap->ip->i_mount; - xfs_agnumber_t ag, startag; - int notinit = 0; - int error; - - args->type = XFS_ALLOCTYPE_START_BNO; - args->total = ap->total; - - startag = ag = XFS_FSB_TO_AGNO(mp, args->fsbno); - if (startag == NULLAGNUMBER) - startag = ag = 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) - break; - } + /* + * 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; - xfs_bmap_select_minlen(ap, args, blen, notinit); - return 0; + /* + * 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_filestreams( +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; - int notinit = 0; - int error; - - args->type = XFS_ALLOCTYPE_NEAR_BNO; - args->total = ap->total; - - ag = XFS_FSB_TO_AGNO(mp, args->fsbno); - if (ag == NULLAGNUMBER) - ag = 0; - - error = xfs_bmap_longest_free_extent(args->tp, ag, blen, ¬init); - if (error) - return error; + struct xfs_mount *mp = args->mp; + struct xfs_perag *pag; + xfs_agnumber_t agno, startag; + int error = 0; - if (*blen < args->maxlen) { - error = xfs_filestream_new_ag(ap, &ag); - if (error) - return error; + if (ap->tp->t_flags & XFS_TRANS_LOWMODE) { + args->total = ap->minlen; + args->minlen = ap->minlen; + return 0; + } - error = xfs_bmap_longest_free_extent(args->tp, ag, blen, - ¬init); - if (error) - return error; + args->total = ap->total; + startag = XFS_FSB_TO_AGNO(mp, ap->blkno); + if (startag == NULLAGNUMBER) + startag = 0; + *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); - - /* - * 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; + args->minlen = xfs_bmap_select_minlen(ap, args, *blen); + return error; } /* Update all inode and quota accounting for the allocation we just did. */ -static void -xfs_bmap_btalloc_accounting( - struct xfs_bmalloca *ap, - struct xfs_alloc_arg *args) +void +xfs_bmap_alloc_account( + struct xfs_bmalloca *ap) { + bool isrt = XFS_IS_REALTIME_INODE(ap->ip) && + !(ap->flags & XFS_BMAPI_ATTRFORK); + uint fld; + if (ap->flags & XFS_BMAPI_COWFORK) { /* * COW fork blocks are in-core only and thus are treated as @@ -3330,7 +3252,7 @@ xfs_bmap_btalloc_accounting( * yet. */ if (ap->wasdel) { - xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len); + xfs_mod_delalloc(ap->ip, -(int64_t)ap->length, 0); return; } @@ -3342,22 +3264,25 @@ xfs_bmap_btalloc_accounting( * This essentially transfers the transaction quota reservation * to that of a delalloc extent. */ - ap->ip->i_delayed_blks += args->len; - xfs_trans_mod_dquot_byino(ap->tp, ap->ip, XFS_TRANS_DQ_RES_BLKS, - -(long)args->len); + 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; } /* data/attr fork only */ - ap->ip->i_nblocks += args->len; + 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 -= args->len; - xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len); + 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; } - xfs_trans_mod_dquot_byino(ap->tp, ap->ip, - ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : XFS_TRANS_DQ_BCOUNT, - args->len); + + xfs_trans_mod_dquot_byino(ap->tp, ap->ip, fld, ap->length); } static int @@ -3379,6 +3304,11 @@ xfs_bmap_compute_alignments( align = xfs_get_cowextsz_hint(ap->ip); 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) { if (xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, align, 0, ap->eof, 0, ap->conv, &ap->offset, @@ -3413,21 +3343,7 @@ xfs_bmap_process_allocated_extent( xfs_fileoff_t orig_offset, xfs_extlen_t orig_length) { - int nullfb; - - nullfb = ap->tp->t_firstblock == NULLFSBLOCK; - - /* - * check the allocation happened at the same or higher AG than - * the first block that was allocated. - */ - ASSERT(nullfb || - XFS_FSB_TO_AGNO(args->mp, ap->tp->t_firstblock) <= - XFS_FSB_TO_AGNO(args->mp, args->fsbno)); - ap->blkno = args->fsbno; - if (nullfb) - ap->tp->t_firstblock = args->fsbno; ap->length = args->len; /* * If the extent size hint is active, we tried to round the @@ -3445,99 +3361,287 @@ xfs_bmap_process_allocated_extent( ap->offset = orig_offset; else if (ap->offset + ap->length < orig_offset + orig_length) ap->offset = orig_offset + orig_length - ap->length; - xfs_bmap_btalloc_accounting(ap, args); + xfs_bmap_alloc_account(ap); } -#ifdef DEBUG static int xfs_bmap_exact_minlen_extent_alloc( - struct xfs_bmalloca *ap) + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args) { - struct xfs_mount *mp = ap->ip->i_mount; - struct xfs_alloc_arg args = { .tp = ap->tp, .mp = mp }; - xfs_fileoff_t orig_offset; - xfs_extlen_t orig_length; - int error; - - ASSERT(ap->length); - if (ap->minlen != 1) { - ap->blkno = NULLFSBLOCK; - ap->length = 0; + args->fsbno = NULLFSBLOCK; return 0; } - orig_offset = ap->offset; - orig_length = ap->length; + args->alloc_minlen_only = 1; + args->minlen = args->maxlen = ap->minlen; + args->total = ap->total; - args.alloc_minlen_only = 1; + /* + * 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. + */ + ap->blkno = XFS_AGB_TO_FSB(ap->ip->i_mount, 0, 0); - xfs_bmap_compute_alignments(ap, &args); + /* + * 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. + */ + 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; + + /* + * 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. + */ + 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 + 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; - if (ap->tp->t_firstblock == NULLFSBLOCK) { + if (args->fsbno != NULLFSBLOCK) + return 0; /* - * 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. + * Exact allocation failed. Reset to try an aligned allocation + * according to the original allocation specification. */ - ap->blkno = XFS_AGB_TO_FSB(mp, 0, 0); + args->alignment = stripe_align; + args->minlen = nextminlen; + args->minalignslop = 0; } else { - ap->blkno = ap->tp->t_firstblock; + /* + * 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; } - args.fsbno = ap->blkno; - args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE; - args.type = XFS_ALLOCTYPE_FIRST_AG; - args.minlen = args.maxlen = ap->minlen; - args.total = ap->total; + if (ag_only) { + error = xfs_alloc_vextent_near_bno(args, ap->blkno); + } else { + args->pag = NULL; + error = xfs_alloc_vextent_start_ag(args, ap->blkno); + ASSERT(args->pag == NULL); + args->pag = caller_pag; + } + if (error) + return error; - args.alignment = 1; - args.minalignslop = 0; + if (args->fsbno != NULLFSBLOCK) + return 0; - args.minleft = ap->minleft; - args.wasdel = ap->wasdel; - args.resv = XFS_AG_RESV_NONE; - args.datatype = ap->datatype; + /* + * 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. + */ + 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; - error = xfs_alloc_vextent(&args); + 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; + } + + /* 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 (args.fsbno != NULLFSBLOCK) { - xfs_bmap_process_allocated_extent(ap, &args, orig_offset, - orig_length); - } else { - ap->blkno = NULLFSBLOCK; - ap->length = 0; +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; } - return 0; + 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); } -#else -#define xfs_bmap_exact_minlen_extent_alloc(bma) (-EFSCORRUPTED) +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; -#endif + /* + * 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; -STATIC int + /* + * 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; + } + + 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 }; - xfs_alloctype_t atype = 0; - xfs_agnumber_t fb_agno; /* ag number of ap->firstblock */ - xfs_agnumber_t ag; + 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; - 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; @@ -3547,168 +3651,19 @@ xfs_bmap_btalloc( stripe_align = xfs_bmap_compute_alignments(ap, &args); - nullfb = ap->tp->t_firstblock == NULLFSBLOCK; - fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, - ap->tp->t_firstblock); - if (nullfb) { - if ((ap->datatype & XFS_ALLOC_USERDATA) && - 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->tp->t_firstblock; - - xfs_bmap_adjacent(ap); - - /* - * If allowed, use ap->blkno; otherwise must use firstblock since - * it's in the right allocation group. - */ - if (nullfb || XFS_FSB_TO_AGNO(mp, ap->blkno) == fb_agno) - ; - else - ap->blkno = ap->tp->t_firstblock; - /* - * Normal allocation, done through xfs_alloc_vextent. - */ - tryagain = isaligned = 0; - args.fsbno = ap->blkno; - args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE; - /* Trim the allocation back to the maximum an AG can fit. */ args.maxlen = min(ap->length, mp->m_ag_max_usable); - 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. - */ - if ((ap->datatype & XFS_ALLOC_USERDATA) && - xfs_inode_is_filestream(ap->ip)) - error = xfs_bmap_btalloc_filestreams(ap, &args, &blen); - else - error = xfs_bmap_btalloc_nullfb(ap, &args, &blen); - if (error) - return error; - } else if (ap->tp->t_flags & XFS_TRANS_LOWMODE) { - 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; - } else { - args.type = XFS_ALLOCTYPE_NEAR_BNO; - args.total = ap->total; - args.minlen = ap->minlen; - } - /* - * 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. - */ - if (!(ap->tp->t_flags & XFS_TRANS_LOWMODE) && ap->aeof) { - if (!ap->offset) { - args.alignment = stripe_align; - atype = args.type; - isaligned = 1; - /* - * Adjust minlen to try and preserve alignment if we - * can't guarantee an aligned maxlen extent. - */ - if (blen > args.alignment && - blen <= args.maxlen + args.alignment) - 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.minleft = ap->minleft; - args.wasdel = ap->wasdel; - args.resv = XFS_AG_RESV_NONE; - args.datatype = ap->datatype; - - error = xfs_alloc_vextent(&args); + 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 (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; - } - if (args.fsbno == NULLFSBLOCK && nullfb) { - args.fsbno = 0; - args.type = XFS_ALLOCTYPE_FIRST_AG; - args.total = ap->minlen; - if ((error = xfs_alloc_vextent(&args))) - return error; - ap->tp->t_flags |= XFS_TRANS_LOWMODE; - } - if (args.fsbno != NULLFSBLOCK) { xfs_bmap_process_allocated_extent(ap, &args, orig_offset, orig_length); @@ -3877,14 +3832,18 @@ xfs_bmapi_read( ASSERT(*nmap >= 1); ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_ENTIRE))); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); - if (WARN_ON_ONCE(!ifp)) + if (WARN_ON_ONCE(!ifp)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; + } if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || - XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; + } if (xfs_is_shutdown(mp)) return -EIO; @@ -3934,152 +3893,6 @@ xfs_bmapi_read( 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, - struct xfs_iext_cursor *icur, - 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; - 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, XFS_MAX_BMBT_EXTLEN); - 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) { - struct xfs_bmbt_irec prev; - xfs_extlen_t extsz = xfs_get_cowextsz_hint(ip); - - if (!xfs_iext_peek_prev_extent(ifp, icur, &prev)) - prev.br_startoff = NULLFILEOFF; - - error = xfs_bmap_extsize_align(mp, got, &prev, extsz, 0, eof, - 1, 0, &aoff, &alen); - ASSERT(!error); - } - - /* - * 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_quota_reserve_blkres(ip, alen); - 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); - - 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; - xfs_mod_delalloc(ip->i_mount, alen + indlen); - - 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, icur, 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: - xfs_mod_fdblocks(mp, alen, false); -out_unreserve_quota: - if (XFS_IS_QUOTA_ON(mp)) - xfs_quota_unreserve_blkres(ip, alen); - return error; -} - -static int -xfs_bmap_alloc_userdata( - struct xfs_bmalloca *bma) -{ - struct xfs_mount *mp = bma->ip->i_mount; - int whichfork = xfs_bmapi_whichfork(bma->flags); - int error; - - /* - * 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. - */ - bma->datatype = XFS_ALLOC_NOBUSY; - 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; - - if (mp->m_dalign && bma->length >= mp->m_dalign) { - error = xfs_bmap_isaeof(bma, whichfork); - if (error) - return error; - } - - if (XFS_IS_REALTIME_INODE(bma->ip)) - return xfs_bmap_rtalloc(bma); - } - - if (unlikely(XFS_TEST_ERROR(false, mp, - XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT))) - return xfs_bmap_exact_minlen_extent_alloc(bma); - - return xfs_bmap_btalloc(bma); -} - static int xfs_bmapi_allocate( struct xfs_bmalloca *bma) @@ -4087,43 +3900,51 @@ xfs_bmapi_allocate( 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; int error; ASSERT(bma->length > 0); - - /* - * 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 (!xfs_iext_peek_prev_extent(ifp, &bma->icur, &bma->prev)) - bma->prev.br_startoff = NULLFILEOFF; - } else { - bma->length = XFS_FILBLKS_MIN(bma->length, XFS_MAX_BMBT_EXTLEN); - if (!bma->eof) - bma->length = XFS_FILBLKS_MIN(bma->length, - bma->got.br_startoff - bma->offset); - } + ASSERT(bma->length <= XFS_MAX_BMBT_EXTLEN); if (bma->flags & XFS_BMAPI_CONTIG) bma->minlen = bma->length; else bma->minlen = 1; - if (bma->flags & XFS_BMAPI_METADATA) { - if (unlikely(XFS_TEST_ERROR(false, mp, - XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT))) - error = xfs_bmap_exact_minlen_extent_alloc(bma); - else - error = xfs_bmap_btalloc(bma); - } else { - error = xfs_bmap_alloc_userdata(bma); + 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 || whichfork == XFS_COW_FORK) { + bma->datatype |= XFS_ALLOC_USERDATA; + if (bma->offset == 0) + bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA; + + if (mp->m_dalign && bma->length >= mp->m_dalign) { + error = xfs_bmap_isaeof(bma, whichfork); + if (error) + return error; + } + } } - if (error || bma->blkno == NULLFSBLOCK) + + 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; + + 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); @@ -4139,9 +3960,8 @@ xfs_bmapi_allocate( */ bma->nallocs++; - if (bma->cur) - bma->cur->bc_ino.flags = - bma->wasdel ? XFS_BTCUR_BMBT_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; @@ -4157,8 +3977,6 @@ xfs_bmapi_allocate( error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip, whichfork, &bma->icur, &bma->cur, &bma->got, &bma->logflags, bma->flags); - - bma->logflags |= tmp_logflags; if (error) return error; @@ -4256,7 +4074,7 @@ xfs_bmapi_convert_unwritten( return 0; } -static inline xfs_extlen_t +xfs_extlen_t xfs_bmapi_minleft( struct xfs_trans *tp, struct xfs_inode *ip, @@ -4264,7 +4082,7 @@ xfs_bmapi_minleft( { struct xfs_ifork *ifp = xfs_ifork_ptr(ip, fork); - if (tp && tp->t_firstblock != NULLFSBLOCK) + if (tp && tp->t_highest_agno != NULLAGNUMBER) return 0; if (ifp->if_format != XFS_DINODE_FMT_BTREE) return 1; @@ -4303,6 +4121,15 @@ xfs_bmapi_finish( * extent state if necessary. Details behaviour is controlled by the flags * parameter. Only allocates blocks from a single allocation group, to avoid * locking problems. + * + * 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( @@ -4348,7 +4175,7 @@ xfs_bmapi_write( ASSERT(tp != NULL); ASSERT(len > 0); ASSERT(ifp->if_format != XFS_DINODE_FMT_LOCAL); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); ASSERT(!(flags & XFS_BMAPI_REMAP)); /* zeroing is for currently only for data extents, not metadata */ @@ -4364,7 +4191,8 @@ xfs_bmapi_write( (XFS_BMAPI_PREALLOC | XFS_BMAPI_ZERO)); if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || - XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) { + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } @@ -4420,28 +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)XFS_MAX_BMBT_EXTLEN) - bma.length = XFS_MAX_BMBT_EXTLEN; - 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) - xfs_refcount_alloc_cow_extent(tp, bma.blkno, - bma.length); + xfs_refcount_alloc_cow_extent(tp, + XFS_IS_REALTIME_INODE(ip), + bma.blkno, bma.length); } /* Deal with the allocated space we found. */ @@ -4471,7 +4313,6 @@ xfs_bmapi_write( if (!xfs_iext_next_extent(ifp, &bma.icur, &bma.got)) eof = true; } - *nmap = n; error = xfs_bmap_btree_to_extents(tp, ip, bma.cur, &bma.logflags, whichfork); @@ -4482,7 +4323,22 @@ xfs_bmapi_write( 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, *nmap); + 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); @@ -4495,8 +4351,8 @@ error0: * invocations to allocate the target offset if a large enough physical extent * is not available. */ -int -xfs_bmapi_convert_delalloc( +static int +xfs_bmapi_convert_one_delalloc( struct xfs_inode *ip, int whichfork, xfs_off_t offset, @@ -4526,11 +4382,8 @@ xfs_bmapi_convert_delalloc( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); - error = xfs_iext_count_may_overflow(ip, whichfork, + error = xfs_iext_count_extend(tp, ip, whichfork, XFS_IEXT_ADD_NOSPLIT_CNT); - if (error == -EFBIG) - error = xfs_iext_count_upgrade(tp, ip, - XFS_IEXT_ADD_NOSPLIT_CNT); if (error) goto out_trans_cancel; @@ -4553,19 +4406,25 @@ xfs_bmapi_convert_delalloc( if (!isnullstartblock(bma.got.br_startblock)) { xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags, xfs_iomap_inode_sequence(ip, flags)); - *seq = READ_ONCE(ifp->if_seq); + if (seq) + *seq = READ_ONCE(ifp->if_seq); goto out_trans_cancel; } bma.tp = tp; bma.ip = ip; bma.wasdel = true; - bma.offset = bma.got.br_startoff; - bma.length = max_t(xfs_filblks_t, bma.got.br_blockcount, - XFS_MAX_BMBT_EXTLEN); 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. + */ + bma.offset = bma.got.br_startoff; + bma.length = bma.got.br_blockcount; + + /* * 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: @@ -4589,23 +4448,18 @@ xfs_bmapi_convert_delalloc( if (error) goto out_finish; - error = -ENOSPC; - if (WARN_ON_ONCE(bma.blkno == NULLFSBLOCK)) - goto out_finish; - error = -EFSCORRUPTED; - if (WARN_ON_ONCE(!xfs_valid_startblock(ip, bma.got.br_startblock))) - 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)); - *seq = READ_ONCE(ifp->if_seq); + if (seq) + *seq = READ_ONCE(ifp->if_seq); if (whichfork == XFS_COW_FORK) - xfs_refcount_alloc_cow_extent(tp, bma.blkno, bma.length); + 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); @@ -4625,6 +4479,36 @@ out_trans_cancel: return error; } +/* + * 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, @@ -4645,14 +4529,15 @@ xfs_bmapi_remap( ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(len > 0); ASSERT(len <= (xfs_filblks_t)XFS_MAX_BMBT_EXTLEN); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + 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(false, mp, XFS_ERRTAG_BMAPIFORMAT)) { + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } @@ -4670,12 +4555,11 @@ xfs_bmapi_remap( } 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_format == XFS_DINODE_FMT_BTREE) { + if (ifp->if_format == XFS_DINODE_FMT_BTREE) cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); - cur->bc_ino.flags = 0; - } got.br_startoff = bno; got.br_startblock = startblock; @@ -4717,32 +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. @@ -4786,31 +4656,30 @@ xfs_bmap_split_indlen( *indlen1 = len1; *indlen2 = len2; - - return stolen; } -int +void xfs_bmap_del_extent_delay( struct xfs_inode *ip, int whichfork, 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_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; + xfs_filblks_t got_indlen, new_indlen, stolen = 0; uint32_t state = xfs_bmap_fork_to_state(whichfork); - int error = 0; + 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); @@ -4820,22 +4689,12 @@ xfs_bmap_del_extent_delay( 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. */ - ASSERT(!isrt); - error = xfs_quota_unreserve_blkres(ip, del->br_blockcount); - if (error) - return error; + xfs_quota_unreserve_blkres(ip, del->br_blockcount); ip->i_delayed_blks -= del->br_blockcount; if (got->br_startoff == del->br_startoff) @@ -4889,8 +4748,24 @@ 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); @@ -4902,20 +4777,29 @@ xfs_bmap_del_extent_delay( 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); - xfs_mod_delalloc(mp, -da_diff); + 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; } - return error; + + xfs_add_fdblocks(mp, fdblocks); + xfs_mod_delalloc(ip, -(int64_t)del->br_blockcount, -da_diff); } void @@ -4989,6 +4873,34 @@ xfs_bmap_del_extent_cow( 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. @@ -5006,9 +4918,7 @@ xfs_bmap_del_extent_real( { xfs_fsblock_t del_endblock=0; /* first block past del */ xfs_fileoff_t del_endoff; /* first offset past del */ - int do_fx; /* free extent at end of routine */ - int error; /* error return value */ - int flags = 0;/* inode logging flags */ + 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 */ @@ -5021,6 +4931,8 @@ xfs_bmap_del_extent_real( 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); @@ -5033,7 +4945,6 @@ xfs_bmap_del_extent_real( ASSERT(got_endoff >= del_endoff); ASSERT(!isnullstartblock(got.br_startblock)); qfield = 0; - error = 0; /* * If it's the case where the directory code is running with no block @@ -5049,44 +4960,21 @@ xfs_bmap_del_extent_real( del->br_startoff > got.br_startoff && del_endoff < got_endoff) return -ENOSPC; - flags = XFS_ILOG_CORE; - if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) { - xfs_filblks_t len; - xfs_extlen_t mod; - - len = div_u64_rem(del->br_blockcount, mp->m_sb.sb_rextsize, - &mod); - ASSERT(mod == 0); - - if (!(bflags & XFS_BMAPI_REMAP)) { - xfs_fsblock_t bno; - - bno = div_u64_rem(del->br_startblock, - mp->m_sb.sb_rextsize, &mod); - ASSERT(mod == 0); - - error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len); - if (error) - goto done; - } - - do_fx = 0; - nblks = len * mp->m_sb.sb_rextsize; + *logflagsp = XFS_ILOG_CORE; + if (xfs_ifork_is_realtime(ip, whichfork)) qfield = XFS_TRANS_DQ_RTBCOUNT; - } else { - do_fx = 1; - nblks = del->br_blockcount; + 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) - goto done; + return error; if (XFS_IS_CORRUPT(mp, i != 1)) { - error = -EFSCORRUPTED; - goto done; + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; } } @@ -5104,16 +4992,16 @@ xfs_bmap_del_extent_real( xfs_iext_prev(ifp, icur); ifp->if_nextents--; - 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; + return error; if (XFS_IS_CORRUPT(mp, i != 1)) { - error = -EFSCORRUPTED; - goto done; + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; } break; case BMAP_LEFT_FILLING: @@ -5125,12 +5013,12 @@ xfs_bmap_del_extent_real( 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; } error = xfs_bmbt_update(cur, &got); if (error) - goto done; + return error; break; case BMAP_RIGHT_FILLING: /* @@ -5139,12 +5027,12 @@ xfs_bmap_del_extent_real( 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; } error = xfs_bmbt_update(cur, &got); if (error) - goto done; + return error; break; case 0: /* @@ -5161,18 +5049,18 @@ xfs_bmap_del_extent_real( new.br_state = got.br_state; new.br_startblock = del_endblock; - flags |= XFS_ILOG_CORE; + *logflagsp |= XFS_ILOG_CORE; if (cur) { error = xfs_bmbt_update(cur, &got); if (error) - goto done; + return error; error = xfs_btree_increment(cur, 0, &i); if (error) - goto done; + return error; cur->bc_rec.b = new; error = xfs_btree_insert(cur, &i); if (error && error != -ENOSPC) - goto done; + return error; /* * If get no-space back from btree insert, it tried a * split, and we have a zero block reservation. Fix up @@ -5185,10 +5073,10 @@ xfs_bmap_del_extent_real( */ error = xfs_bmbt_lookup_eq(cur, &got, &i); if (error) - goto done; + return error; if (XFS_IS_CORRUPT(mp, i != 1)) { - error = -EFSCORRUPTED; - goto done; + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; } /* * Update the btree record back @@ -5196,22 +5084,21 @@ xfs_bmap_del_extent_real( */ error = xfs_bmbt_update(cur, &old); if (error) - goto done; + return error; /* * Reset the extent record back * to the original value. */ xfs_iext_update_extent(ip, state, icur, &old); - flags = 0; - error = -ENOSPC; - goto done; + *logflagsp = 0; + return -ENOSPC; } if (XFS_IS_CORRUPT(mp, i != 1)) { - error = -EFSCORRUPTED; - goto done; + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; } } else - flags |= xfs_ilog_fext(whichfork); + *logflagsp |= xfs_ilog_fext(whichfork); ifp->if_nextents++; xfs_iext_next(ifp, icur); @@ -5225,15 +5112,39 @@ xfs_bmap_del_extent_real( /* * 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) { - xfs_refcount_decrease_extent(tp, del); + xfs_refcount_decrease_extent(tp, isrt, del); + } else if (isrt && !xfs_has_rtgroups(mp)) { + error = xfs_bmap_free_rtblocks(tp, del); } else { - __xfs_free_extent_later(tp, del->br_startblock, + 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, - (bflags & XFS_BMAPI_NODISCARD) || - del->br_state == XFS_EXT_UNWRITTEN); + XFS_AG_RESV_NONE, efi_flags); } + if (error) + return error; } /* @@ -5247,9 +5158,7 @@ xfs_bmap_del_extent_real( if (qfield && !(bflags & XFS_BMAPI_REMAP)) xfs_trans_mod_dquot_byino(tp, ip, qfield, (long)-nblks); -done: - *logflagsp = flags; - return error; + return 0; } /* @@ -5258,7 +5167,7 @@ done: * that value. If not all extents in the block range can be removed then * *done is set. */ -int /* error */ +static int __xfs_bunmapi( struct xfs_trans *tp, /* transaction pointer */ struct xfs_inode *ip, /* incore inode */ @@ -5280,7 +5189,6 @@ __xfs_bunmapi( 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 end; struct xfs_iext_cursor icur; @@ -5291,12 +5199,14 @@ __xfs_bunmapi( whichfork = xfs_bmapi_whichfork(flags); ASSERT(whichfork != XFS_COW_FORK); ifp = xfs_ifork_ptr(ip, whichfork); - if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp))) + if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp))) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; + } 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); @@ -5309,7 +5219,7 @@ __xfs_bunmapi( return 0; } XFS_STATS_INC(mp, xs_blk_unmap); - isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip); + isrt = xfs_ifork_is_realtime(ip, whichfork); end = start + len; if (!xfs_iext_lookup_extent_before(ip, ifp, &end, &icur, &got)) { @@ -5322,20 +5232,9 @@ __xfs_bunmapi( 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_ino.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 (end != (xfs_fileoff_t)-1 && end >= start && (nexts == 0 || extno < nexts)) { @@ -5372,11 +5271,11 @@ __xfs_bunmapi( if (del.br_startoff + del.br_blockcount > end + 1) del.br_blockcount = end + 1 - del.br_startoff; - if (!isrt) + if (!isrt || (flags & XFS_BMAPI_REMAP)) goto delete; - sum = del.br_startblock + del.br_blockcount; - div_u64_rem(sum, mp->m_sb.sb_rextsize, &mod); + mod = xfs_rtb_to_rtxoff(mp, + del.br_startblock + del.br_blockcount); if (mod) { /* * Realtime extent not lined up at the end. @@ -5390,7 +5289,7 @@ __xfs_bunmapi( * This piece is unwritten, or we're not * using unwritten extents. Skip over it. */ - ASSERT(end >= mod); + ASSERT((flags & XFS_BMAPI_REMAP) || end >= mod); end -= mod > del.br_blockcount ? del.br_blockcount : mod; if (end < got.br_startoff && @@ -5423,7 +5322,8 @@ __xfs_bunmapi( goto error0; goto nodelete; } - div_u64_rem(del.br_startblock, mp->m_sb.sb_rextsize, &mod); + + mod = xfs_rtb_to_rtxoff(mp, del.br_startblock); if (mod) { xfs_extlen_t off = mp->m_sb.sb_rextsize - mod; @@ -5495,18 +5395,17 @@ __xfs_bunmapi( delete: if (wasdel) { - error = xfs_bmap_del_extent_delay(ip, whichfork, &icur, - &got, &del); + 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; } - if (error) - goto error0; - end = del.br_startoff - 1; nodelete: /* @@ -5559,7 +5458,7 @@ error0: xfs_trans_log_inode(tp, ip, logflags); if (cur) { if (!error) - cur->bc_ino.allocated = 0; + cur->bc_bmap.allocated = 0; xfs_btree_del_cursor(cur, error); } return error; @@ -5589,6 +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 */ @@ -5604,7 +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 > XFS_MAX_BMBT_EXTLEN)) + (left->br_blockcount + got->br_blockcount > XFS_MAX_BMBT_EXTLEN) || + !xfs_bmap_same_rtgroup(ip, whichfork, left, got)) return false; return true; @@ -5639,9 +5541,8 @@ xfs_bmse_merge( 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)); new = *left; new.br_blockcount = blockcount; @@ -5661,21 +5562,27 @@ xfs_bmse_merge( error = xfs_bmbt_lookup_eq(cur, got, &i); if (error) return error; - if (XFS_IS_CORRUPT(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; - if (XFS_IS_CORRUPT(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, &i); if (error) return error; - if (XFS_IS_CORRUPT(mp, i != 1)) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } error = xfs_bmbt_update(cur, &new); if (error) @@ -5723,8 +5630,10 @@ xfs_bmap_shift_update_extent( error = xfs_bmbt_lookup_eq(cur, &prev, &i); if (error) return error; - if (XFS_IS_CORRUPT(mp, i != 1)) + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } error = xfs_bmbt_update(cur, got); if (error) @@ -5761,29 +5670,29 @@ xfs_bmap_collapse_extents( int logflags = 0; if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || - XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) { + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } if (xfs_is_shutdown(mp)) return -EIO; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL)); + 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) { + if (ifp->if_format == XFS_DINODE_FMT_BTREE) cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); - cur->bc_ino.flags = 0; - } 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; } @@ -5795,7 +5704,8 @@ xfs_bmap_collapse_extents( goto del_cursor; } - if (xfs_bmse_can_merge(&prev, &got, offset_shift_fsb)) { + 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); @@ -5841,7 +5751,7 @@ xfs_bmap_can_insert_extents( int is_empty; int error = 0; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL); if (xfs_is_shutdown(ip->i_mount)) return -EIO; @@ -5876,23 +5786,22 @@ xfs_bmap_insert_extents( int logflags = 0; if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || - XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) { + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } if (xfs_is_shutdown(mp)) return -EIO; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL)); + 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) { + if (ifp->if_format == XFS_DINODE_FMT_BTREE) cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); - cur->bc_ino.flags = 0; - } if (*next_fsb == NULLFSBLOCK) { xfs_iext_last(ifp, &icur); @@ -5908,11 +5817,13 @@ xfs_bmap_insert_extents( } } if (XFS_IS_CORRUPT(mp, isnullstartblock(got.br_startblock))) { + xfs_bmap_mark_sick(ip, whichfork); error = -EFSCORRUPTED; goto del_cursor; } if (XFS_IS_CORRUPT(mp, stop_fsb > got.br_startoff)) { + xfs_bmap_mark_sick(ip, whichfork); error = -EFSCORRUPTED; goto del_cursor; } @@ -5930,7 +5841,8 @@ xfs_bmap_insert_extents( * 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, &next, offset_shift_fsb)) + if (xfs_bmse_can_merge(ip, whichfork, &got, &next, + offset_shift_fsb)) WARN_ON_ONCE(1); } @@ -5979,7 +5891,8 @@ xfs_bmap_split_extent( int i = 0; if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) || - XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) { + XFS_TEST_ERROR(mp, XFS_ERRTAG_BMAPIFORMAT)) { + xfs_bmap_mark_sick(ip, whichfork); return -EFSCORRUPTED; } @@ -6006,11 +5919,11 @@ xfs_bmap_split_extent( if (ifp->if_format == XFS_DINODE_FMT_BTREE) { cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); - cur->bc_ino.flags = 0; error = xfs_bmbt_lookup_eq(cur, &got, &i); if (error) goto del_cursor; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto del_cursor; } @@ -6038,6 +5951,7 @@ xfs_bmap_split_extent( if (error) goto del_cursor; if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto del_cursor; } @@ -6045,6 +5959,7 @@ xfs_bmap_split_extent( if (error) goto del_cursor; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto del_cursor; } @@ -6064,7 +5979,7 @@ xfs_bmap_split_extent( del_cursor: if (cur) { - cur->bc_ino.allocated = 0; + cur->bc_bmap.allocated = 0; xfs_btree_del_cursor(cur, error); } @@ -6073,17 +5988,8 @@ del_cursor: 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_trans *tp, enum xfs_bmap_intent_type type, @@ -6093,24 +5999,19 @@ __xfs_bmap_add( { struct xfs_bmap_intent *bi; - trace_xfs_bmap_defer(tp->t_mountp, - XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock), - type, - XFS_FSB_TO_AGBNO(tp->t_mountp, 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_cache_alloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL); + 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; - xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list); - return 0; + xfs_bmap_defer_add(tp, bi); } /* Map an extent into a file. */ @@ -6118,12 +6019,10 @@ void xfs_bmap_map_extent( struct xfs_trans *tp, struct xfs_inode *ip, + int whichfork, struct xfs_bmbt_irec *PREV) { - if (!xfs_bmap_is_update_needed(PREV)) - return; - - __xfs_bmap_add(tp, 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. */ @@ -6131,12 +6030,10 @@ void xfs_bmap_unmap_extent( struct xfs_trans *tp, struct xfs_inode *ip, + int whichfork, struct xfs_bmbt_irec *PREV) { - if (!xfs_bmap_is_update_needed(PREV)) - return; - - __xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, XFS_DATA_FORK, PREV); + __xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, whichfork, PREV); } /* @@ -6146,63 +6043,59 @@ xfs_bmap_unmap_extent( int xfs_bmap_finish_one( struct xfs_trans *tp, - 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) { + struct xfs_bmbt_irec *bmap = &bi->bi_bmap; int error = 0; + int flags = 0; - ASSERT(tp->t_firstblock == 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, 0); - *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); + 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 inode's extent does not have invalid flags or bad ranges. */ +/* Check that an extent does not have invalid flags or bad ranges. */ xfs_failaddr_t -xfs_bmap_validate_extent( - struct xfs_inode *ip, +xfs_bmap_validate_extent_raw( + struct xfs_mount *mp, + bool rtfile, int whichfork, struct xfs_bmbt_irec *irec) { - struct xfs_mount *mp = ip->i_mount; - if (!xfs_verify_fileext(mp, irec->br_startoff, irec->br_blockcount)) return __this_address; - if (XFS_IS_REALTIME_INODE(ip) && whichfork == XFS_DATA_FORK) { - if (!xfs_verify_rtext(mp, irec->br_startblock, - irec->br_blockcount)) + 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, @@ -6230,3 +6123,144 @@ 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; +} diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 16db95b11589..d5f2729305fa 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -12,6 +12,7 @@ struct xfs_ifork; struct xfs_inode; struct xfs_mount; struct xfs_trans; +struct xfs_alloc_arg; /* * Argument structure for xfs_bmap_alloc. @@ -86,6 +87,9 @@ struct xfs_bmalloca { /* Do not update the rmap btree. Used for reconstructing bmbt from rmapbt. */ #define XFS_BMAPI_NORMAP (1u << 10) +/* Try to align allocations to the extent size hint */ +#define XFS_BMAPI_EXTSZALIGN (1u << 11) + #define XFS_BMAPI_FLAGS \ { XFS_BMAPI_ENTIRE, "ENTIRE" }, \ { XFS_BMAPI_METADATA, "METADATA" }, \ @@ -97,7 +101,8 @@ struct xfs_bmalloca { { XFS_BMAPI_REMAP, "REMAP" }, \ { XFS_BMAPI_COWFORK, "COWFORK" }, \ { XFS_BMAPI_NODISCARD, "NODISCARD" }, \ - { XFS_BMAPI_NORMAP, "NORMAP" } + { XFS_BMAPI_NORMAP, "NORMAP" },\ + { XFS_BMAPI_EXTSZALIGN, "EXTSZALIGN" } static inline int xfs_bmapi_aflag(int w) @@ -115,6 +120,8 @@ static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags) return XFS_DATA_FORK; } +void xfs_bmap_alloc_account(struct xfs_bmalloca *ap); + /* * Special values for xfs_bmbt_irec_t br_startblock field. */ @@ -144,7 +151,7 @@ static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags) { BMAP_COWFORK, "COW" } /* Return true if the extent is an allocated extent, written or not. */ -static inline bool xfs_bmap_is_real_extent(struct xfs_bmbt_irec *irec) +static inline bool xfs_bmap_is_real_extent(const struct xfs_bmbt_irec *irec) { return irec->br_startblock != HOLESTARTBLOCK && irec->br_startblock != DELAYSTARTBLOCK && @@ -155,7 +162,7 @@ static inline bool xfs_bmap_is_real_extent(struct xfs_bmbt_irec *irec) * Return true if the extent is a real, allocated extent, or false if it is a * delayed allocation, and unwritten extent or a hole. */ -static inline bool xfs_bmap_is_written_extent(struct xfs_bmbt_irec *irec) +static inline bool xfs_bmap_is_written_extent(const struct xfs_bmbt_irec *irec) { return xfs_bmap_is_real_extent(irec) && irec->br_state != XFS_EXT_UNWRITTEN; @@ -168,12 +175,21 @@ static inline bool xfs_bmap_is_written_extent(struct xfs_bmbt_irec *irec) #define xfs_valid_startblock(ip, startblock) \ ((startblock) != 0 || XFS_IS_REALTIME_INODE(ip)) +int xfs_bmap_longest_free_extent(struct xfs_perag *pag, + struct xfs_trans *tp, xfs_extlen_t *blen); void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, xfs_filblks_t len); unsigned int xfs_bmap_compute_attr_offset(struct xfs_mount *mp); -int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); +int xfs_bmap_add_attrfork(struct xfs_trans *tp, struct xfs_inode *ip, + int size, int rsvd); void xfs_bmap_local_to_extents_empty(struct xfs_trans *tp, struct xfs_inode *ip, int whichfork); +int xfs_bmap_local_to_extents(struct xfs_trans *tp, struct xfs_inode *ip, + xfs_extlen_t total, int *logflagsp, int whichfork, + void (*init_fn)(struct xfs_trans *tp, struct xfs_buf *bp, + struct xfs_inode *ip, struct xfs_ifork *ifp, + void *priv), + void *priv); void xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork); int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip, xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork); @@ -187,15 +203,12 @@ int xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno, int xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags, xfs_extlen_t total, struct xfs_bmbt_irec *mval, int *nmap); -int __xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip, - xfs_fileoff_t bno, xfs_filblks_t *rlen, uint32_t flags, - xfs_extnum_t nexts); int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags, xfs_extnum_t nexts, int *done); -int xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork, +void xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got, - struct xfs_bmbt_irec *del); + struct xfs_bmbt_irec *del, uint32_t bflags); void xfs_bmap_del_extent_cow(struct xfs_inode *ip, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del); @@ -210,38 +223,41 @@ int xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip, bool *done, xfs_fileoff_t stop_fsb); int xfs_bmap_split_extent(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t split_offset); -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, struct xfs_iext_cursor *cur, - int eof); int xfs_bmapi_convert_delalloc(struct xfs_inode *ip, int whichfork, xfs_off_t offset, struct iomap *iomap, unsigned int *seq); int xfs_bmap_add_extent_unwritten_real(struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, struct xfs_iext_cursor *icur, struct xfs_btree_cur **curp, struct xfs_bmbt_irec *new, int *logflagsp); +xfs_extlen_t xfs_bmapi_minleft(struct xfs_trans *tp, struct xfs_inode *ip, + int fork); +int xfs_bmap_btalloc_low_space(struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args); +xfs_filblks_t xfs_bmap_worst_indlen(struct xfs_inode *ip, xfs_filblks_t len); enum xfs_bmap_intent_type { XFS_BMAP_MAP = 1, XFS_BMAP_UNMAP, }; +#define XFS_BMAP_INTENT_STRINGS \ + { XFS_BMAP_MAP, "map" }, \ + { XFS_BMAP_UNMAP, "unmap" } + struct xfs_bmap_intent { struct list_head bi_list; enum xfs_bmap_intent_type bi_type; int bi_whichfork; struct xfs_inode *bi_owner; + struct xfs_group *bi_group; struct xfs_bmbt_irec bi_bmap; }; -int xfs_bmap_finish_one(struct xfs_trans *tp, 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); +int xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_bmap_intent *bi); void xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip, - struct xfs_bmbt_irec *imap); + int whichfork, struct xfs_bmbt_irec *imap); void xfs_bmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip, - struct xfs_bmbt_irec *imap); + int whichfork, struct xfs_bmbt_irec *imap); static inline uint32_t xfs_bmap_fork_to_state(int whichfork) { @@ -255,16 +271,33 @@ static inline uint32_t xfs_bmap_fork_to_state(int whichfork) } } +xfs_failaddr_t xfs_bmap_validate_extent_raw(struct xfs_mount *mp, bool rtfile, + int whichfork, struct xfs_bmbt_irec *irec); xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork, struct xfs_bmbt_irec *irec); +int xfs_bmap_complain_bad_rec(struct xfs_inode *ip, int whichfork, + xfs_failaddr_t fa, const struct xfs_bmbt_irec *irec); int xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock, uint32_t flags); +int xfs_bunmapi_range(struct xfs_trans **tpp, struct xfs_inode *ip, + uint32_t flags, xfs_fileoff_t startoff, xfs_fileoff_t endoff); extern struct kmem_cache *xfs_bmap_intent_cache; int __init xfs_bmap_intent_init_cache(void); void xfs_bmap_intent_destroy_cache(void); +typedef int (*xfs_bmap_query_range_fn)( + struct xfs_btree_cur *cur, + struct xfs_bmbt_irec *rec, + void *priv); + +int xfs_bmap_query_all(struct xfs_btree_cur *cur, xfs_bmap_query_range_fn fn, + void *priv); + +xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip); +xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip); + #endif /* __XFS_BMAP_H__ */ diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index cfa052d40105..188feac04b60 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -15,15 +15,33 @@ #include "xfs_trans.h" #include "xfs_alloc.h" #include "xfs_btree.h" +#include "xfs_btree_staging.h" #include "xfs_bmap_btree.h" #include "xfs_bmap.h" #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_trace.h" #include "xfs_rmap.h" +#include "xfs_ag.h" static struct kmem_cache *xfs_bmbt_cur_cache; +void +xfs_bmbt_init_block( + struct xfs_inode *ip, + struct xfs_btree_block *buf, + struct xfs_buf *bp, + __u16 level, + __u16 numrecs) +{ + if (bp) + xfs_btree_init_buf(ip->i_mount, bp, &xfs_bmbt_ops, level, + numrecs, ip->i_ino); + else + xfs_btree_init_block(ip->i_mount, buf, &xfs_bmbt_ops, level, + numrecs, ip->i_ino); +} + /* * Convert on-disk form of btree root to in-memory form. */ @@ -42,17 +60,15 @@ xfs_bmdr_to_bmbt( xfs_bmbt_key_t *tkp; __be64 *tpp; - xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL, - XFS_BTNUM_BMAP, 0, 0, ip->i_ino, - XFS_BTREE_LONG_PTRS); + xfs_bmbt_init_block(ip, rblock, NULL, 0, 0); rblock->bb_level = dblock->bb_level; ASSERT(be16_to_cpu(rblock->bb_level) > 0); rblock->bb_numrecs = dblock->bb_numrecs; dmxr = xfs_bmdr_maxrecs(dblocklen, 0); - fkp = XFS_BMDR_KEY_ADDR(dblock, 1); - tkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1); - fpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr); - tpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen); + fkp = xfs_bmdr_key_addr(dblock, 1); + tkp = xfs_bmbt_key_addr(mp, rblock, 1); + fpp = xfs_bmdr_ptr_addr(dblock, 1, dmxr); + tpp = xfs_bmap_broot_ptr_addr(mp, rblock, 1, rblocklen); dmxr = be16_to_cpu(dblock->bb_numrecs); memcpy(tkp, fkp, sizeof(*fkp) * dmxr); memcpy(tpp, fpp, sizeof(*fpp) * dmxr); @@ -152,10 +168,10 @@ xfs_bmbt_to_bmdr( dblock->bb_level = rblock->bb_level; dblock->bb_numrecs = rblock->bb_numrecs; dmxr = xfs_bmdr_maxrecs(dblocklen, 0); - fkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1); - tkp = XFS_BMDR_KEY_ADDR(dblock, 1); - fpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen); - tpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr); + fkp = xfs_bmbt_key_addr(mp, rblock, 1); + tkp = xfs_bmdr_key_addr(dblock, 1); + fpp = xfs_bmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_bmdr_ptr_addr(dblock, 1, dmxr); dmxr = be16_to_cpu(dblock->bb_numrecs); memcpy(tkp, fkp, sizeof(*fkp) * dmxr); memcpy(tpp, fpp, sizeof(*fpp) * dmxr); @@ -169,13 +185,8 @@ xfs_bmbt_dup_cursor( new = xfs_bmbt_init_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ino.ip, cur->bc_ino.whichfork); - - /* - * Copy the firstblock, dfops, and flags values, - * since init cursor doesn't get them. - */ - new->bc_ino.flags = cur->bc_ino.flags; - + new->bc_flags |= (cur->bc_flags & + (XFS_BTREE_BMBT_INVALID_OWNER | XFS_BTREE_BMBT_WASDEL)); return new; } @@ -184,13 +195,13 @@ xfs_bmbt_update_cursor( struct xfs_btree_cur *src, struct xfs_btree_cur *dst) { - ASSERT((dst->bc_tp->t_firstblock != NULLFSBLOCK) || + ASSERT((dst->bc_tp->t_highest_agno != NULLAGNUMBER) || (dst->bc_ino.ip->i_diflags & XFS_DIFLAG_REALTIME)); - dst->bc_ino.allocated += src->bc_ino.allocated; - dst->bc_tp->t_firstblock = src->bc_tp->t_firstblock; + dst->bc_bmap.allocated += src->bc_bmap.allocated; + dst->bc_tp->t_highest_agno = src->bc_tp->t_highest_agno; - src->bc_ino.allocated = 0; + src->bc_bmap.allocated = 0; } STATIC int @@ -200,46 +211,32 @@ xfs_bmbt_alloc_block( union xfs_btree_ptr *new, int *stat) { - xfs_alloc_arg_t args; /* block allocation args */ - int error; /* error return value */ + struct xfs_alloc_arg args; + int error; memset(&args, 0, sizeof(args)); args.tp = cur->bc_tp; args.mp = cur->bc_mp; - args.fsbno = cur->bc_tp->t_firstblock; xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_ino.ip->i_ino, cur->bc_ino.whichfork); + args.minlen = args.maxlen = args.prod = 1; + args.wasdel = cur->bc_flags & XFS_BTREE_BMBT_WASDEL; + if (!args.wasdel && args.tp->t_blk_res == 0) + return -ENOSPC; - if (args.fsbno == NULLFSBLOCK) { - args.fsbno = be64_to_cpu(start->l); - args.type = XFS_ALLOCTYPE_START_BNO; - /* - * Make sure there is sufficient room left in the AG to - * complete a full tree split for an extent insert. If - * we are converting the middle part of an extent then - * we may need space for two tree splits. - * - * We are relying on the caller to make the correct block - * reservation for this operation to succeed. If the - * reservation amount is insufficient then we may fail a - * block allocation here and corrupt the filesystem. - */ - args.minleft = args.tp->t_blk_res; - } else if (cur->bc_tp->t_flags & XFS_TRANS_LOWMODE) { - args.type = XFS_ALLOCTYPE_START_BNO; - } else { - args.type = XFS_ALLOCTYPE_NEAR_BNO; - } + /* + * If we are coming here from something like unwritten extent + * conversion, there has been no data extent allocation already done, so + * we have to ensure that we attempt to locate the entire set of bmbt + * allocations in the same AG, as xfs_bmapi_write() would have reserved. + */ + if (cur->bc_tp->t_highest_agno == NULLAGNUMBER) + args.minleft = xfs_bmapi_minleft(cur->bc_tp, cur->bc_ino.ip, + cur->bc_ino.whichfork); - args.minlen = args.maxlen = args.prod = 1; - args.wasdel = cur->bc_ino.flags & XFS_BTCUR_BMBT_WASDEL; - if (!args.wasdel && args.tp->t_blk_res == 0) { - error = -ENOSPC; - goto error0; - } - error = xfs_alloc_vextent(&args); + error = xfs_alloc_vextent_start_ag(&args, be64_to_cpu(start->l)); if (error) - goto error0; + return error; if (args.fsbno == NULLFSBLOCK && args.minleft) { /* @@ -247,11 +244,10 @@ xfs_bmbt_alloc_block( * a full btree split. Try again and if * successful activate the lowspace algorithm. */ - args.fsbno = 0; - args.type = XFS_ALLOCTYPE_FIRST_AG; - error = xfs_alloc_vextent(&args); + args.minleft = 0; + error = xfs_alloc_vextent_start_ag(&args, 0); if (error) - goto error0; + return error; cur->bc_tp->t_flags |= XFS_TRANS_LOWMODE; } if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { @@ -260,8 +256,7 @@ xfs_bmbt_alloc_block( } ASSERT(args.len == 1); - cur->bc_tp->t_firstblock = args.fsbno; - cur->bc_ino.allocated++; + cur->bc_bmap.allocated++; cur->bc_ino.ip->i_nblocks++; xfs_trans_log_inode(args.tp, cur->bc_ino.ip, XFS_ILOG_CORE); xfs_trans_mod_dquot_byino(args.tp, cur->bc_ino.ip, @@ -271,9 +266,6 @@ xfs_bmbt_alloc_block( *stat = 1; return 0; - - error0: - return error; } STATIC int @@ -286,11 +278,15 @@ xfs_bmbt_free_block( struct xfs_trans *tp = cur->bc_tp; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); struct xfs_owner_info oinfo; + int error; xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); - xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo); - ip->i_nblocks--; + error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo, + XFS_AG_RESV_NONE, 0); + if (error) + return error; + ip->i_nblocks--; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); return 0; @@ -302,10 +298,7 @@ xfs_bmbt_get_minrecs( int level) { if (level == cur->bc_nlevels - 1) { - struct xfs_ifork *ifp; - - ifp = xfs_ifork_ptr(cur->bc_ino.ip, - cur->bc_ino.whichfork); + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); return xfs_bmbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, level == 0) / 2; @@ -320,10 +313,7 @@ xfs_bmbt_get_maxrecs( int level) { if (level == cur->bc_nlevels - 1) { - struct xfs_ifork *ifp; - - ifp = xfs_ifork_ptr(cur->bc_ino.ip, - cur->bc_ino.whichfork); + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); return xfs_bmbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, level == 0); @@ -379,43 +369,26 @@ xfs_bmbt_init_rec_from_cur( xfs_bmbt_disk_set_all(&rec->bmbt, &cur->bc_rec.b); } -STATIC void -xfs_bmbt_init_ptr_from_cur( - struct xfs_btree_cur *cur, - union xfs_btree_ptr *ptr) -{ - ptr->l = 0; -} - -STATIC int64_t -xfs_bmbt_key_diff( +STATIC int +xfs_bmbt_cmp_key_with_cur( struct xfs_btree_cur *cur, const union xfs_btree_key *key) { - return (int64_t)be64_to_cpu(key->bmbt.br_startoff) - - cur->bc_rec.b.br_startoff; + return cmp_int(be64_to_cpu(key->bmbt.br_startoff), + cur->bc_rec.b.br_startoff); } -STATIC int64_t -xfs_bmbt_diff_two_keys( +STATIC int +xfs_bmbt_cmp_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { - uint64_t a = be64_to_cpu(k1->bmbt.br_startoff); - uint64_t b = be64_to_cpu(k2->bmbt.br_startoff); + ASSERT(!mask || mask->bmbt.br_startoff); - /* - * Note: This routine previously casted a and b to int64 and subtracted - * them to generate a result. This lead to problems if b was the - * "maximum" key value (all ones) being signed incorrectly, hence this - * somewhat less efficient version. - */ - if (a > b) - return 1; - if (b > a) - return -1; - return 0; + return cmp_int(be64_to_cpu(k1->bmbt.br_startoff), + be64_to_cpu(k2->bmbt.br_startoff)); } static xfs_failaddr_t @@ -435,7 +408,7 @@ xfs_bmbt_verify( * XXX: need a better way of verifying the owner here. Right now * just make sure there has been one set. */ - fa = xfs_btree_lblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); if (fa) return fa; } @@ -451,7 +424,7 @@ xfs_bmbt_verify( if (level > max(mp->m_bm_maxlevels[0], mp->m_bm_maxlevels[1])) return __this_address; - return xfs_btree_lblock_verify(bp, mp->m_bmap_dmxr[level != 0]); + return xfs_btree_fsblock_verify(bp, mp->m_bmap_dmxr[level != 0]); } static void @@ -460,7 +433,7 @@ xfs_bmbt_read_verify( { xfs_failaddr_t fa; - if (!xfs_btree_lblock_verify_crc(bp)) + if (!xfs_btree_fsblock_verify_crc(bp)) xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_bmbt_verify(bp); @@ -484,7 +457,7 @@ xfs_bmbt_write_verify( xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } - xfs_btree_lblock_calc_crc(bp); + xfs_btree_fsblock_calc_crc(bp); } const struct xfs_buf_ops xfs_bmbt_buf_ops = { @@ -518,9 +491,139 @@ xfs_bmbt_recs_inorder( xfs_bmbt_disk_get_startoff(&r2->bmbt); } -static const struct xfs_btree_ops xfs_bmbt_ops = { +STATIC enum xbtree_key_contig +xfs_bmbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->bmbt.br_startoff); + + return xbtree_key_contig(be64_to_cpu(key1->bmbt.br_startoff), + be64_to_cpu(key2->bmbt.br_startoff)); +} + +static inline void +xfs_bmbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_bmap_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_bmap_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_bmbt_ptr_t)); +} + +/* + * Reallocate the space for if_broot based on the number of records. Move the + * records and pointers in if_broot to fit the new size. When shrinking this + * will eliminate holes between the records and pointers created by the caller. + * When growing this will create holes to be filled in by the caller. + * + * The caller must not request to add more records than would fit in the + * on-disk inode root. If the if_broot is currently NULL, then if we are + * adding records, one will be allocated. The caller must also not request + * that the number of records go below zero, although it can go to zero. + * + * ip -- the inode whose if_broot area is changing + * whichfork -- which inode fork to change + * new_numrecs -- the new number of records requested for the if_broot array + * + * Returns the incore btree root block. + */ +struct xfs_btree_block * +xfs_bmap_broot_realloc( + struct xfs_inode *ip, + int whichfork, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + + /* + * Block mapping btrees do not support storing zero records; if this + * happens, the fork is being changed to FMT_EXTENTS. Free the broot + * and get out. + */ + if (new_numrecs == 0) + return xfs_broot_realloc(ifp, 0); + + new_size = xfs_bmap_broot_space_calc(mp, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just + * allocate it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need + * to realloc() it and shift the pointers to their new + * location. The records don't change location because + * they are kept butted up against the btree block header. + */ + old_numrecs = xfs_bmbt_maxrecs(mp, old_size, false); + broot = xfs_broot_realloc(ifp, new_size); + ASSERT(xfs_bmap_bmdr_space(broot) <= + xfs_inode_fork_size(ip, whichfork)); + xfs_bmbt_move_ptrs(mp, broot, old_size, new_size, old_numrecs); + return broot; + } + + /* + * We're reducing, but not totally eliminating, numrecs. In this case, + * we are shrinking the if_broot buffer, so it must already exist. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0 && new_size > 0); + + /* + * Shrink the btree root by moving the bmbt pointers, since they are + * not butted up against the btree block header, then reallocating + * broot. + */ + xfs_bmbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + ASSERT(xfs_bmap_bmdr_space(broot) <= + xfs_inode_fork_size(ip, whichfork)); + return broot; +} + +static struct xfs_btree_block * +xfs_bmbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + return xfs_bmap_broot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, + new_numrecs); +} + +const struct xfs_btree_ops xfs_bmbt_ops = { + .name = "bmap", + .type = XFS_BTREE_TYPE_INODE, + .rec_len = sizeof(xfs_bmbt_rec_t), .key_len = sizeof(xfs_bmbt_key_t), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_BMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2), .dup_cursor = xfs_bmbt_dup_cursor, .update_cursor = xfs_bmbt_update_cursor, @@ -532,44 +635,55 @@ static const struct xfs_btree_ops xfs_bmbt_ops = { .init_key_from_rec = xfs_bmbt_init_key_from_rec, .init_high_key_from_rec = xfs_bmbt_init_high_key_from_rec, .init_rec_from_cur = xfs_bmbt_init_rec_from_cur, - .init_ptr_from_cur = xfs_bmbt_init_ptr_from_cur, - .key_diff = xfs_bmbt_key_diff, - .diff_two_keys = xfs_bmbt_diff_two_keys, + .cmp_key_with_cur = xfs_bmbt_cmp_key_with_cur, + .cmp_two_keys = xfs_bmbt_cmp_two_keys, .buf_ops = &xfs_bmbt_buf_ops, .keys_inorder = xfs_bmbt_keys_inorder, .recs_inorder = xfs_bmbt_recs_inorder, + .keys_contiguous = xfs_bmbt_keys_contiguous, + .broot_realloc = xfs_bmbt_broot_realloc, }; /* - * Allocate a new bmap btree cursor. + * Create a new bmap btree cursor. + * + * For staging cursors -1 in passed in whichfork. */ -struct xfs_btree_cur * /* new bmap btree cursor */ +struct xfs_btree_cur * xfs_bmbt_init_cursor( - struct xfs_mount *mp, /* file system mount point */ - struct xfs_trans *tp, /* transaction pointer */ - struct xfs_inode *ip, /* inode owning the btree */ - int whichfork) /* data or attr fork */ + struct xfs_mount *mp, + struct xfs_trans *tp, + struct xfs_inode *ip, + int whichfork) { - struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur; - ASSERT(whichfork != XFS_COW_FORK); + unsigned int maxlevels; - cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP, - mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache); - cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1; - cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2); - - cur->bc_ops = &xfs_bmbt_ops; - cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE; - if (xfs_has_crc(mp)) - cur->bc_flags |= XFS_BTREE_CRC_BLOCKS; + ASSERT(whichfork != XFS_COW_FORK); - cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork); + /* + * The Data fork always has larger maxlevel, so use that for staging + * cursors. + */ + switch (whichfork) { + case XFS_STAGING_FORK: + maxlevels = mp->m_bm_maxlevels[XFS_DATA_FORK]; + break; + default: + maxlevels = mp->m_bm_maxlevels[whichfork]; + break; + } + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_bmbt_ops, maxlevels, + xfs_bmbt_cur_cache); cur->bc_ino.ip = ip; - cur->bc_ino.allocated = 0; - cur->bc_ino.flags = 0; cur->bc_ino.whichfork = whichfork; + cur->bc_bmap.allocated = 0; + if (whichfork != XFS_STAGING_FORK) { + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1; + cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork); + } return cur; } @@ -585,15 +699,58 @@ xfs_bmbt_block_maxrecs( } /* + * Swap in the new inode fork root. Once we pass this point the newly rebuilt + * mappings are in place and we have to kill off any old btree blocks. + */ +void +xfs_bmbt_commit_staged_btree( + struct xfs_btree_cur *cur, + struct xfs_trans *tp, + int whichfork) +{ + struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake; + struct xfs_ifork *ifp; + static const short brootflag[2] = {XFS_ILOG_DBROOT, XFS_ILOG_ABROOT}; + static const short extflag[2] = {XFS_ILOG_DEXT, XFS_ILOG_AEXT}; + int flags = XFS_ILOG_CORE; + + ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(whichfork != XFS_COW_FORK); + + /* + * Free any resources hanging off the real fork, then shallow-copy the + * staging fork's contents into the real fork to transfer everything + * we just built. + */ + ifp = xfs_ifork_ptr(cur->bc_ino.ip, whichfork); + xfs_idestroy_fork(ifp); + memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork)); + + switch (ifp->if_format) { + case XFS_DINODE_FMT_EXTENTS: + flags |= extflag[whichfork]; + break; + case XFS_DINODE_FMT_BTREE: + flags |= brootflag[whichfork]; + break; + default: + ASSERT(0); + break; + } + xfs_trans_log_inode(tp, cur->bc_ino.ip, flags); + xfs_btree_commit_ifakeroot(cur, tp, whichfork); +} + +/* * Calculate number of records in a bmap btree block. */ -int +unsigned int xfs_bmbt_maxrecs( struct xfs_mount *mp, - int blocklen, - int leaf) + unsigned int blocklen, + bool leaf) { - blocklen -= XFS_BMBT_BLOCK_LEN(mp); + blocklen -= xfs_bmbt_block_len(mp); return xfs_bmbt_block_maxrecs(blocklen, leaf); } @@ -667,7 +824,7 @@ xfs_bmbt_change_owner( ASSERT(xfs_ifork_ptr(ip, whichfork)->if_format == XFS_DINODE_FMT_BTREE); cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork); - cur->bc_ino.flags |= XFS_BTCUR_BMBT_INVALID_OWNER; + cur->bc_flags |= XFS_BTREE_BMBT_INVALID_OWNER; error = xfs_btree_change_owner(cur, new_owner, buffer_list); xfs_btree_del_cursor(cur, error); diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h index 3e7a40a83835..b238d559ab03 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.h +++ b/fs/xfs/libxfs/xfs_bmap_btree.h @@ -11,70 +11,7 @@ struct xfs_btree_block; struct xfs_mount; struct xfs_inode; struct xfs_trans; - -/* - * Btree block header size depends on a superblock flag. - */ -#define XFS_BMBT_BLOCK_LEN(mp) \ - (xfs_has_crc(((mp))) ? \ - XFS_BTREE_LBLOCK_CRC_LEN : XFS_BTREE_LBLOCK_LEN) - -#define XFS_BMBT_REC_ADDR(mp, block, index) \ - ((xfs_bmbt_rec_t *) \ - ((char *)(block) + \ - XFS_BMBT_BLOCK_LEN(mp) + \ - ((index) - 1) * sizeof(xfs_bmbt_rec_t))) - -#define XFS_BMBT_KEY_ADDR(mp, block, index) \ - ((xfs_bmbt_key_t *) \ - ((char *)(block) + \ - XFS_BMBT_BLOCK_LEN(mp) + \ - ((index) - 1) * sizeof(xfs_bmbt_key_t))) - -#define XFS_BMBT_PTR_ADDR(mp, block, index, maxrecs) \ - ((xfs_bmbt_ptr_t *) \ - ((char *)(block) + \ - XFS_BMBT_BLOCK_LEN(mp) + \ - (maxrecs) * sizeof(xfs_bmbt_key_t) + \ - ((index) - 1) * sizeof(xfs_bmbt_ptr_t))) - -#define XFS_BMDR_REC_ADDR(block, index) \ - ((xfs_bmdr_rec_t *) \ - ((char *)(block) + \ - sizeof(struct xfs_bmdr_block) + \ - ((index) - 1) * sizeof(xfs_bmdr_rec_t))) - -#define XFS_BMDR_KEY_ADDR(block, index) \ - ((xfs_bmdr_key_t *) \ - ((char *)(block) + \ - sizeof(struct xfs_bmdr_block) + \ - ((index) - 1) * sizeof(xfs_bmdr_key_t))) - -#define XFS_BMDR_PTR_ADDR(block, index, maxrecs) \ - ((xfs_bmdr_ptr_t *) \ - ((char *)(block) + \ - sizeof(struct xfs_bmdr_block) + \ - (maxrecs) * sizeof(xfs_bmdr_key_t) + \ - ((index) - 1) * sizeof(xfs_bmdr_ptr_t))) - -/* - * These are to be used when we know the size of the block and - * we don't have a cursor. - */ -#define XFS_BMAP_BROOT_PTR_ADDR(mp, bb, i, sz) \ - XFS_BMBT_PTR_ADDR(mp, bb, i, xfs_bmbt_maxrecs(mp, sz, 0)) - -#define XFS_BMAP_BROOT_SPACE_CALC(mp, nrecs) \ - (int)(XFS_BMBT_BLOCK_LEN(mp) + \ - ((nrecs) * (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t)))) - -#define XFS_BMAP_BROOT_SPACE(mp, bb) \ - (XFS_BMAP_BROOT_SPACE_CALC(mp, be16_to_cpu((bb)->bb_numrecs))) -#define XFS_BMDR_SPACE_CALC(nrecs) \ - (int)(sizeof(xfs_bmdr_block_t) + \ - ((nrecs) * (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t)))) -#define XFS_BMAP_BMDR_SPACE(bb) \ - (XFS_BMDR_SPACE_CALC(be16_to_cpu((bb)->bb_numrecs))) +struct xbtree_ifakeroot; /* * Maximum number of bmap btree levels. @@ -98,7 +35,8 @@ extern void xfs_bmbt_to_bmdr(struct xfs_mount *, struct xfs_btree_block *, int, extern int xfs_bmbt_get_maxrecs(struct xfs_btree_cur *, int level); extern int xfs_bmdr_maxrecs(int blocklen, int leaf); -extern int xfs_bmbt_maxrecs(struct xfs_mount *, int blocklen, int leaf); +unsigned int xfs_bmbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, + bool leaf); extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, xfs_ino_t new_owner, @@ -106,6 +44,8 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip, extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *, struct xfs_trans *, struct xfs_inode *, int); +void xfs_bmbt_commit_staged_btree(struct xfs_btree_cur *cur, + struct xfs_trans *tp, int whichfork); extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp, unsigned long long len); @@ -115,4 +55,150 @@ unsigned int xfs_bmbt_maxlevels_ondisk(void); int __init xfs_bmbt_init_cur_cache(void); void xfs_bmbt_destroy_cur_cache(void); +void xfs_bmbt_init_block(struct xfs_inode *ip, struct xfs_btree_block *buf, + struct xfs_buf *bp, __u16 level, __u16 numrecs); + +/* + * Btree block header size depends on a superblock flag. + */ +static inline size_t +xfs_bmbt_block_len(struct xfs_mount *mp) +{ + return xfs_has_crc(mp) ? + XFS_BTREE_LBLOCK_CRC_LEN : XFS_BTREE_LBLOCK_LEN; +} + +/* Addresses of key, pointers, and records within an incore bmbt block. */ + +static inline struct xfs_bmbt_rec * +xfs_bmbt_rec_addr( + struct xfs_mount *mp, + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_bmbt_rec *) + ((char *)block + xfs_bmbt_block_len(mp) + + (index - 1) * sizeof(struct xfs_bmbt_rec)); +} + +static inline struct xfs_bmbt_key * +xfs_bmbt_key_addr( + struct xfs_mount *mp, + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_bmbt_key *) + ((char *)block + xfs_bmbt_block_len(mp) + + (index - 1) * sizeof(struct xfs_bmbt_key *)); +} + +static inline xfs_bmbt_ptr_t * +xfs_bmbt_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_bmbt_ptr_t *) + ((char *)block + xfs_bmbt_block_len(mp) + + maxrecs * sizeof(struct xfs_bmbt_key) + + (index - 1) * sizeof(xfs_bmbt_ptr_t)); +} + +/* Addresses of key, pointers, and records within an ondisk bmbt block. */ + +static inline struct xfs_bmbt_rec * +xfs_bmdr_rec_addr( + struct xfs_bmdr_block *block, + unsigned int index) +{ + return (struct xfs_bmbt_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_bmbt_rec)); +} + +static inline struct xfs_bmbt_key * +xfs_bmdr_key_addr( + struct xfs_bmdr_block *block, + unsigned int index) +{ + return (struct xfs_bmbt_key *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_bmbt_key)); +} + +static inline xfs_bmbt_ptr_t * +xfs_bmdr_ptr_addr( + struct xfs_bmdr_block *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_bmbt_ptr_t *) + ((char *)(block + 1) + + maxrecs * sizeof(struct xfs_bmbt_key) + + (index - 1) * sizeof(xfs_bmbt_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_bmbt_ptr_t * +xfs_bmap_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int i, + unsigned int sz) +{ + return xfs_bmbt_ptr_addr(mp, bb, i, xfs_bmbt_maxrecs(mp, sz, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_bmap_broot_space_calc( + struct xfs_mount *mp, + unsigned int nrecs) +{ + return xfs_bmbt_block_len(mp) + + (nrecs * (sizeof(struct xfs_bmbt_key) + sizeof(xfs_bmbt_ptr_t))); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_bmap_broot_space( + struct xfs_mount *mp, + struct xfs_bmdr_block *bb) +{ + return xfs_bmap_broot_space_calc(mp, be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_bmdr_space_calc(unsigned int nrecs) +{ + return sizeof(struct xfs_bmdr_block) + + (nrecs * (sizeof(struct xfs_bmbt_key) + sizeof(xfs_bmbt_ptr_t))); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_bmap_bmdr_space(struct xfs_btree_block *bb) +{ + return xfs_bmdr_space_calc(be16_to_cpu(bb->bb_numrecs)); +} + +struct xfs_btree_block *xfs_bmap_broot_realloc(struct xfs_inode *ip, + int whichfork, unsigned int new_numrecs); + #endif /* __XFS_BMAP_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 35f574421670..dbe9df8c3300 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -27,28 +27,30 @@ #include "xfs_bmap_btree.h" #include "xfs_rmap_btree.h" #include "xfs_refcount_btree.h" +#include "xfs_health.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_bmap.h" +#include "xfs_rmap.h" +#include "xfs_quota.h" +#include "xfs_metafile.h" +#include "xfs_rtrefcount_btree.h" /* * Btree magic numbers. */ -static const uint32_t xfs_magics[2][XFS_BTNUM_MAX] = { - { XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, 0, XFS_BMAP_MAGIC, XFS_IBT_MAGIC, - XFS_FIBT_MAGIC, 0 }, - { XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC, XFS_RMAP_CRC_MAGIC, - XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC, - XFS_REFC_CRC_MAGIC } -}; - uint32_t xfs_btree_magic( - int crc, - xfs_btnum_t btnum) + struct xfs_mount *mp, + const struct xfs_btree_ops *ops) { - uint32_t magic = xfs_magics[crc][btnum]; + int idx = xfs_has_crc(mp) ? 1 : 0; + __be32 magic = ops->buf_ops->magic[idx]; /* Ensure we asked for crc for crc-only magics. */ ASSERT(magic != 0); - return magic; + return be32_to_cpu(magic); } /* @@ -63,10 +65,8 @@ xfs_btree_magic( * bytes. */ static inline xfs_failaddr_t -xfs_btree_check_lblock_siblings( +xfs_btree_check_fsblock_siblings( struct xfs_mount *mp, - struct xfs_btree_cur *cur, - int level, xfs_fsblock_t fsb, __be64 dsibling) { @@ -78,22 +78,33 @@ xfs_btree_check_lblock_siblings( sibling = be64_to_cpu(dsibling); if (sibling == fsb) return __this_address; - if (level >= 0) { - if (!xfs_btree_check_lptr(cur, sibling, level + 1)) - return __this_address; - } else { - if (!xfs_verify_fsbno(mp, sibling)) - return __this_address; - } + if (!xfs_verify_fsbno(mp, sibling)) + return __this_address; + return NULL; +} +static inline xfs_failaddr_t +xfs_btree_check_memblock_siblings( + struct xfs_buftarg *btp, + xfbno_t bno, + __be64 dsibling) +{ + xfbno_t sibling; + + if (dsibling == cpu_to_be64(NULLFSBLOCK)) + return NULL; + + sibling = be64_to_cpu(dsibling); + if (sibling == bno) + return __this_address; + if (!xmbuf_verify_daddr(btp, xfbno_to_daddr(sibling))) + return __this_address; return NULL; } static inline xfs_failaddr_t -xfs_btree_check_sblock_siblings( +xfs_btree_check_agblock_siblings( struct xfs_perag *pag, - struct xfs_btree_cur *cur, - int level, xfs_agblock_t agbno, __be32 dsibling) { @@ -105,34 +116,21 @@ xfs_btree_check_sblock_siblings( sibling = be32_to_cpu(dsibling); if (sibling == agbno) return __this_address; - if (level >= 0) { - if (!xfs_btree_check_sptr(cur, sibling, level + 1)) - return __this_address; - } else { - if (!xfs_verify_agbno(pag, sibling)) - return __this_address; - } + if (!xfs_verify_agbno(pag, sibling)) + return __this_address; return NULL; } -/* - * Check a long btree block header. Return the address of the failing check, - * or NULL if everything is ok. - */ -xfs_failaddr_t -__xfs_btree_check_lblock( +static xfs_failaddr_t +__xfs_btree_check_lblock_hdr( struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *bp) { struct xfs_mount *mp = cur->bc_mp; - xfs_btnum_t btnum = cur->bc_btnum; - int crc = xfs_has_crc(mp); - xfs_failaddr_t fa; - xfs_fsblock_t fsb = NULLFSBLOCK; - if (crc) { + if (xfs_has_crc(mp)) { if (!uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)) return __this_address; if (block->bb_u.l.bb_blkno != @@ -142,7 +140,7 @@ __xfs_btree_check_lblock( return __this_address; } - if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(crc, btnum)) + if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(mp, cur->bc_ops)) return __this_address; if (be16_to_cpu(block->bb_level) != level) return __this_address; @@ -150,65 +148,101 @@ __xfs_btree_check_lblock( cur->bc_ops->get_maxrecs(cur, level)) return __this_address; - if (bp) - fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); + return NULL; +} - fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb, +/* + * Check a long btree block header. Return the address of the failing check, + * or NULL if everything is ok. + */ +static xfs_failaddr_t +__xfs_btree_check_fsblock( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block, + int level, + struct xfs_buf *bp) +{ + struct xfs_mount *mp = cur->bc_mp; + xfs_failaddr_t fa; + xfs_fsblock_t fsb; + + fa = __xfs_btree_check_lblock_hdr(cur, block, level, bp); + if (fa) + return fa; + + /* + * For inode-rooted btrees, the root block sits in the inode fork. In + * that case bp is NULL, and the block must not have any siblings. + */ + if (!bp) { + if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK)) + return __this_address; + if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK)) + return __this_address; + return NULL; + } + + fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); + fa = xfs_btree_check_fsblock_siblings(mp, fsb, block->bb_u.l.bb_leftsib); if (!fa) - fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb, + fa = xfs_btree_check_fsblock_siblings(mp, fsb, block->bb_u.l.bb_rightsib); return fa; } -/* Check a long btree block header. */ -static int -xfs_btree_check_lblock( +/* + * Check an in-memory btree block header. Return the address of the failing + * check, or NULL if everything is ok. + */ +static xfs_failaddr_t +__xfs_btree_check_memblock( struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *bp) { - struct xfs_mount *mp = cur->bc_mp; + struct xfs_buftarg *btp = cur->bc_mem.xfbtree->target; xfs_failaddr_t fa; + xfbno_t bno; - fa = __xfs_btree_check_lblock(cur, block, level, bp); - if (XFS_IS_CORRUPT(mp, fa != NULL) || - XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BTREE_CHECK_LBLOCK)) { - if (bp) - trace_xfs_btree_corrupt(bp, _RET_IP_); - return -EFSCORRUPTED; - } - return 0; + fa = __xfs_btree_check_lblock_hdr(cur, block, level, bp); + if (fa) + return fa; + + bno = xfs_daddr_to_xfbno(xfs_buf_daddr(bp)); + fa = xfs_btree_check_memblock_siblings(btp, bno, + block->bb_u.l.bb_leftsib); + if (!fa) + fa = xfs_btree_check_memblock_siblings(btp, bno, + block->bb_u.l.bb_rightsib); + return fa; } /* * Check a short btree block header. Return the address of the failing check, * or NULL if everything is ok. */ -xfs_failaddr_t -__xfs_btree_check_sblock( +static xfs_failaddr_t +__xfs_btree_check_agblock( struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *bp) { struct xfs_mount *mp = cur->bc_mp; - struct xfs_perag *pag = cur->bc_ag.pag; - xfs_btnum_t btnum = cur->bc_btnum; - int crc = xfs_has_crc(mp); + struct xfs_perag *pag = to_perag(cur->bc_group); xfs_failaddr_t fa; - xfs_agblock_t agbno = NULLAGBLOCK; + xfs_agblock_t agbno; - if (crc) { + if (xfs_has_crc(mp)) { if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) return __this_address; - if (block->bb_u.s.bb_blkno != - cpu_to_be64(bp ? xfs_buf_daddr(bp) : XFS_BUF_DADDR_NULL)) + if (block->bb_u.s.bb_blkno != cpu_to_be64(xfs_buf_daddr(bp))) return __this_address; } - if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(crc, btnum)) + if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(mp, cur->bc_ops)) return __this_address; if (be16_to_cpu(block->bb_level) != level) return __this_address; @@ -216,36 +250,45 @@ __xfs_btree_check_sblock( cur->bc_ops->get_maxrecs(cur, level)) return __this_address; - if (bp) - agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp)); - - fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno, + agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp)); + fa = xfs_btree_check_agblock_siblings(pag, agbno, block->bb_u.s.bb_leftsib); if (!fa) - fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno, + fa = xfs_btree_check_agblock_siblings(pag, agbno, block->bb_u.s.bb_rightsib); return fa; } -/* Check a short btree block header. */ -STATIC int -xfs_btree_check_sblock( +/* + * Internal btree block check. + * + * Return NULL if the block is ok or the address of the failed check otherwise. + */ +xfs_failaddr_t +__xfs_btree_check_block( struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *bp) { - struct xfs_mount *mp = cur->bc_mp; - xfs_failaddr_t fa; - - fa = __xfs_btree_check_sblock(cur, block, level, bp); - if (XFS_IS_CORRUPT(mp, fa != NULL) || - XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BTREE_CHECK_SBLOCK)) { - if (bp) - trace_xfs_btree_corrupt(bp, _RET_IP_); - return -EFSCORRUPTED; + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_MEM: + return __xfs_btree_check_memblock(cur, block, level, bp); + case XFS_BTREE_TYPE_AG: + return __xfs_btree_check_agblock(cur, block, level, bp); + case XFS_BTREE_TYPE_INODE: + return __xfs_btree_check_fsblock(cur, block, level, bp); + default: + ASSERT(0); + return __this_address; } - return 0; +} + +static inline unsigned int xfs_btree_block_errtag(struct xfs_btree_cur *cur) +{ + if (cur->bc_ops->ptr_len == XFS_BTREE_SHORT_PTR_LEN) + return XFS_ERRTAG_BTREE_CHECK_SBLOCK; + return XFS_ERRTAG_BTREE_CHECK_LBLOCK; } /* @@ -258,34 +301,49 @@ xfs_btree_check_block( int level, /* level of the btree block */ struct xfs_buf *bp) /* buffer containing block, if any */ { - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) - return xfs_btree_check_lblock(cur, block, level, bp); - else - return xfs_btree_check_sblock(cur, block, level, bp); -} + struct xfs_mount *mp = cur->bc_mp; + xfs_failaddr_t fa; -/* Check that this long pointer is valid and points within the fs. */ -bool -xfs_btree_check_lptr( - struct xfs_btree_cur *cur, - xfs_fsblock_t fsbno, - int level) -{ - if (level <= 0) - return false; - return xfs_verify_fsbno(cur->bc_mp, fsbno); + fa = __xfs_btree_check_block(cur, block, level, bp); + if (XFS_IS_CORRUPT(mp, fa != NULL) || + XFS_TEST_ERROR(mp, xfs_btree_block_errtag(cur))) { + if (bp) + trace_xfs_btree_corrupt(bp, _RET_IP_); + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + return 0; } -/* Check that this short pointer is valid and points within the AG. */ -bool -xfs_btree_check_sptr( - struct xfs_btree_cur *cur, - xfs_agblock_t agbno, - int level) +int +__xfs_btree_check_ptr( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *ptr, + int index, + int level) { if (level <= 0) - return false; - return xfs_verify_agbno(cur->bc_ag.pag, agbno); + return -EFSCORRUPTED; + + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_MEM: + if (!xfbtree_verify_bno(cur->bc_mem.xfbtree, + be64_to_cpu((&ptr->l)[index]))) + return -EFSCORRUPTED; + break; + case XFS_BTREE_TYPE_INODE: + if (!xfs_verify_fsbno(cur->bc_mp, + be64_to_cpu((&ptr->l)[index]))) + return -EFSCORRUPTED; + break; + case XFS_BTREE_TYPE_AG: + if (!xfs_verify_agbno(to_perag(cur->bc_group), + be32_to_cpu((&ptr->s)[index]))) + return -EFSCORRUPTED; + break; + } + + return 0; } /* @@ -299,26 +357,35 @@ xfs_btree_check_ptr( int index, int level) { - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { - if (xfs_btree_check_lptr(cur, be64_to_cpu((&ptr->l)[index]), - level)) - return 0; - xfs_err(cur->bc_mp, -"Inode %llu fork %d: Corrupt btree %d pointer at level %d index %d.", + int error; + + error = __xfs_btree_check_ptr(cur, ptr, index, level); + if (error) { + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_MEM: + xfs_err(cur->bc_mp, +"In-memory: Corrupt %sbt flags 0x%x pointer at level %d index %d fa %pS.", + cur->bc_ops->name, cur->bc_flags, level, index, + __this_address); + break; + case XFS_BTREE_TYPE_INODE: + xfs_err(cur->bc_mp, +"Inode %llu fork %d: Corrupt %sbt pointer at level %d index %d.", cur->bc_ino.ip->i_ino, - cur->bc_ino.whichfork, cur->bc_btnum, + cur->bc_ino.whichfork, cur->bc_ops->name, level, index); - } else { - if (xfs_btree_check_sptr(cur, be32_to_cpu((&ptr->s)[index]), - level)) - return 0; - xfs_err(cur->bc_mp, -"AG %u: Corrupt btree %d pointer at level %d index %d.", - cur->bc_ag.pag->pag_agno, cur->bc_btnum, + break; + case XFS_BTREE_TYPE_AG: + xfs_err(cur->bc_mp, +"AG %u: Corrupt %sbt pointer at level %d index %d.", + cur->bc_group->xg_gno, cur->bc_ops->name, level, index); + break; + } + xfs_btree_mark_sick(cur); } - return -EFSCORRUPTED; + return error; } #ifdef DEBUG @@ -336,7 +403,7 @@ xfs_btree_check_ptr( * it to disk. */ void -xfs_btree_lblock_calc_crc( +xfs_btree_fsblock_calc_crc( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); @@ -350,7 +417,7 @@ xfs_btree_lblock_calc_crc( } bool -xfs_btree_lblock_verify_crc( +xfs_btree_fsblock_verify_crc( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); @@ -374,7 +441,7 @@ xfs_btree_lblock_verify_crc( * it to disk. */ void -xfs_btree_sblock_calc_crc( +xfs_btree_agblock_calc_crc( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); @@ -388,7 +455,7 @@ xfs_btree_sblock_calc_crc( } bool -xfs_btree_sblock_verify_crc( +xfs_btree_agblock_verify_crc( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); @@ -410,6 +477,17 @@ xfs_btree_free_block( { int error; + trace_xfs_btree_free_block(cur, bp); + + /* + * Don't allow block freeing for a staging cursor, because staging + * cursors do not support regular btree modifications. + */ + if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) { + ASSERT(0); + return -EFSCORRUPTED; + } + error = cur->bc_ops->free_block(cur, bp); if (!error) { xfs_trans_binval(cur->bc_tp, bp); @@ -448,33 +526,58 @@ xfs_btree_del_cursor( * zero, then we should be shut down or on our way to shutdown due to * cancelling a dirty transaction on error. */ - ASSERT(cur->bc_btnum != XFS_BTNUM_BMAP || cur->bc_ino.allocated == 0 || + ASSERT(!xfs_btree_is_bmap(cur->bc_ops) || cur->bc_bmap.allocated == 0 || xfs_is_shutdown(cur->bc_mp) || error != 0); - if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) - kmem_free(cur->bc_ops); - if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && cur->bc_ag.pag) - xfs_perag_put(cur->bc_ag.pag); + + if (cur->bc_group) + xfs_group_put(cur->bc_group); kmem_cache_free(cur->bc_cache, cur); } +/* Return the buffer target for this btree's buffer. */ +static inline struct xfs_buftarg * +xfs_btree_buftarg( + struct xfs_btree_cur *cur) +{ + if (cur->bc_ops->type == XFS_BTREE_TYPE_MEM) + return cur->bc_mem.xfbtree->target; + return cur->bc_mp->m_ddev_targp; +} + +/* Return the block size (in units of 512b sectors) for this btree. */ +static inline unsigned int +xfs_btree_bbsize( + struct xfs_btree_cur *cur) +{ + if (cur->bc_ops->type == XFS_BTREE_TYPE_MEM) + return XFBNO_BBSIZE; + return cur->bc_mp->m_bsize; +} + /* * Duplicate the btree cursor. * Allocate a new one, copy the record, re-get the buffers. */ -int /* error */ +int /* error */ xfs_btree_dup_cursor( - struct xfs_btree_cur *cur, /* input cursor */ - struct xfs_btree_cur **ncur) /* output cursor */ + struct xfs_btree_cur *cur, /* input cursor */ + struct xfs_btree_cur **ncur) /* output cursor */ { - struct xfs_buf *bp; /* btree block's buffer pointer */ - int error; /* error return value */ - int i; /* level number of btree block */ - xfs_mount_t *mp; /* mount structure for filesystem */ - struct xfs_btree_cur *new; /* new cursor value */ - xfs_trans_t *tp; /* transaction pointer, can be NULL */ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_trans *tp = cur->bc_tp; + struct xfs_buf *bp; + struct xfs_btree_cur *new; + int error; + int i; - tp = cur->bc_tp; - mp = cur->bc_mp; + /* + * Don't allow staging cursors to be duplicated because they're supposed + * to be kept private to a single thread. + */ + if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) { + ASSERT(0); + return -EFSCORRUPTED; + } /* * Allocate a new cursor like the old one. @@ -494,10 +597,13 @@ xfs_btree_dup_cursor( new->bc_levels[i].ra = cur->bc_levels[i].ra; bp = cur->bc_levels[i].bp; if (bp) { - error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, - xfs_buf_daddr(bp), mp->m_bsize, - 0, &bp, - cur->bc_ops->buf_ops); + error = xfs_trans_read_buf(mp, tp, + xfs_btree_buftarg(cur), + xfs_buf_daddr(bp), + xfs_btree_bbsize(cur), 0, &bp, + cur->bc_ops->buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_btree_mark_sick(new); if (error) { xfs_btree_del_cursor(new, error); *ncur = NULL; @@ -539,7 +645,7 @@ xfs_btree_dup_cursor( * record, key or pointer (xfs_btree_*_addr). Note that all addressing * inside the btree block is done using indices starting at one, not zero! * - * If XFS_BTREE_OVERLAPPING is set, then this btree supports keys containing + * If XFS_BTGEO_OVERLAPPING is set, then this btree supports keys containing * overlapping intervals. In such a tree, records are still sorted lowest to * highest and indexed by the smallest key value that refers to the record. * However, nodes are different: each pointer has two associated keys -- one @@ -589,26 +695,17 @@ xfs_btree_dup_cursor( */ static inline size_t xfs_btree_block_len(struct xfs_btree_cur *cur) { - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { - if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS) + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { + if (xfs_has_crc(cur->bc_mp)) return XFS_BTREE_LBLOCK_CRC_LEN; return XFS_BTREE_LBLOCK_LEN; } - if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS) + if (xfs_has_crc(cur->bc_mp)) return XFS_BTREE_SBLOCK_CRC_LEN; return XFS_BTREE_SBLOCK_LEN; } /* - * Return size of btree block pointers for this btree instance. - */ -static inline size_t xfs_btree_ptr_len(struct xfs_btree_cur *cur) -{ - return (cur->bc_flags & XFS_BTREE_LONG_PTRS) ? - sizeof(__be64) : sizeof(__be32); -} - -/* * Calculate offset of the n-th record in a btree block. */ STATIC size_t @@ -655,7 +752,7 @@ xfs_btree_ptr_offset( { return xfs_btree_block_len(cur) + cur->bc_ops->get_maxrecs(cur, level) * cur->bc_ops->key_len + - (n - 1) * xfs_btree_ptr_len(cur); + (n - 1) * cur->bc_ops->ptr_len; } /* @@ -718,7 +815,7 @@ struct xfs_ifork * xfs_btree_ifork_ptr( struct xfs_btree_cur *cur) { - ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); if (cur->bc_flags & XFS_BTREE_STAGING) return cur->bc_ino.ifake->if_fork; @@ -750,8 +847,7 @@ xfs_btree_get_block( int level, /* level in btree */ struct xfs_buf **bpp) /* buffer containing the block */ { - if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && - (level == cur->bc_nlevels - 1)) { + if (xfs_btree_at_iroot(cur, level)) { *bpp = NULL; return xfs_btree_get_iroot(cur); } @@ -856,95 +952,52 @@ xfs_btree_offsets( } } -/* - * Get a buffer for the block, return it read in. - * Long-form addressing. - */ -int -xfs_btree_read_bufl( - 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 */ - int refval, /* ref count value for buffer */ - const struct xfs_buf_ops *ops) -{ - struct xfs_buf *bp; /* return value */ - xfs_daddr_t d; /* real disk block address */ - int error; - - if (!xfs_verify_fsbno(mp, fsbno)) - return -EFSCORRUPTED; - d = XFS_FSB_TO_DADDR(mp, fsbno); - error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, d, - mp->m_bsize, 0, &bp, ops); - if (error) - return error; - if (bp) - xfs_buf_set_ref(bp, refval); - *bpp = bp; - return 0; -} - -/* - * Read-ahead the block, don't wait for it, don't return a buffer. - * Long-form addressing. - */ -/* ARGSUSED */ -void -xfs_btree_reada_bufl( - struct xfs_mount *mp, /* file system mount point */ - xfs_fsblock_t fsbno, /* file system block number */ - xfs_extlen_t count, /* count of filesystem blocks */ - const struct xfs_buf_ops *ops) +STATIC int +xfs_btree_readahead_fsblock( + struct xfs_btree_cur *cur, + int lr, + struct xfs_btree_block *block) { - xfs_daddr_t d; + struct xfs_mount *mp = cur->bc_mp; + xfs_fsblock_t left = be64_to_cpu(block->bb_u.l.bb_leftsib); + xfs_fsblock_t right = be64_to_cpu(block->bb_u.l.bb_rightsib); + int rval = 0; - ASSERT(fsbno != NULLFSBLOCK); - d = XFS_FSB_TO_DADDR(mp, fsbno); - xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count, ops); -} + if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) { + xfs_buf_readahead(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, left), + mp->m_bsize, cur->bc_ops->buf_ops); + rval++; + } -/* - * Read-ahead the block, don't wait for it, don't return a buffer. - * Short-form addressing. - */ -/* ARGSUSED */ -void -xfs_btree_reada_bufs( - struct xfs_mount *mp, /* file system mount point */ - xfs_agnumber_t agno, /* allocation group number */ - xfs_agblock_t agbno, /* allocation group block number */ - xfs_extlen_t count, /* count of filesystem blocks */ - const struct xfs_buf_ops *ops) -{ - xfs_daddr_t d; + if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLFSBLOCK) { + xfs_buf_readahead(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, right), + mp->m_bsize, cur->bc_ops->buf_ops); + rval++; + } - ASSERT(agno != NULLAGNUMBER); - ASSERT(agbno != NULLAGBLOCK); - d = XFS_AGB_TO_DADDR(mp, agno, agbno); - xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count, ops); + return rval; } STATIC int -xfs_btree_readahead_lblock( +xfs_btree_readahead_memblock( struct xfs_btree_cur *cur, int lr, struct xfs_btree_block *block) { + struct xfs_buftarg *btp = cur->bc_mem.xfbtree->target; + xfbno_t left = be64_to_cpu(block->bb_u.l.bb_leftsib); + xfbno_t right = be64_to_cpu(block->bb_u.l.bb_rightsib); int rval = 0; - xfs_fsblock_t left = be64_to_cpu(block->bb_u.l.bb_leftsib); - xfs_fsblock_t right = be64_to_cpu(block->bb_u.l.bb_rightsib); if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) { - xfs_btree_reada_bufl(cur->bc_mp, left, 1, - cur->bc_ops->buf_ops); + xfs_buf_readahead(btp, xfbno_to_daddr(left), XFBNO_BBSIZE, + cur->bc_ops->buf_ops); rval++; } if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLFSBLOCK) { - xfs_btree_reada_bufl(cur->bc_mp, right, 1, - cur->bc_ops->buf_ops); + xfs_buf_readahead(btp, xfbno_to_daddr(right), XFBNO_BBSIZE, + cur->bc_ops->buf_ops); rval++; } @@ -952,25 +1005,28 @@ xfs_btree_readahead_lblock( } STATIC int -xfs_btree_readahead_sblock( +xfs_btree_readahead_agblock( struct xfs_btree_cur *cur, int lr, - struct xfs_btree_block *block) + struct xfs_btree_block *block) { - int rval = 0; + struct xfs_mount *mp = cur->bc_mp; + struct xfs_perag *pag = to_perag(cur->bc_group); xfs_agblock_t left = be32_to_cpu(block->bb_u.s.bb_leftsib); xfs_agblock_t right = be32_to_cpu(block->bb_u.s.bb_rightsib); - + int rval = 0; if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) { - xfs_btree_reada_bufs(cur->bc_mp, cur->bc_ag.pag->pag_agno, - left, 1, cur->bc_ops->buf_ops); + xfs_buf_readahead(mp->m_ddev_targp, + xfs_agbno_to_daddr(pag, left), mp->m_bsize, + cur->bc_ops->buf_ops); rval++; } if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLAGBLOCK) { - xfs_btree_reada_bufs(cur->bc_mp, cur->bc_ag.pag->pag_agno, - right, 1, cur->bc_ops->buf_ops); + xfs_buf_readahead(mp->m_ddev_targp, + xfs_agbno_to_daddr(pag, right), mp->m_bsize, + cur->bc_ops->buf_ops); rval++; } @@ -993,8 +1049,7 @@ xfs_btree_readahead( * No readahead needed if we are at the root level and the * btree root is stored in the inode. */ - if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && - (lev == cur->bc_nlevels - 1)) + if (xfs_btree_at_iroot(cur, lev)) return 0; if ((cur->bc_levels[lev].ra | lr) == cur->bc_levels[lev].ra) @@ -1003,9 +1058,17 @@ xfs_btree_readahead( cur->bc_levels[lev].ra |= lr; block = XFS_BUF_TO_BLOCK(cur->bc_levels[lev].bp); - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) - return xfs_btree_readahead_lblock(cur, lr, block); - return xfs_btree_readahead_sblock(cur, lr, block); + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_AG: + return xfs_btree_readahead_agblock(cur, lr, block); + case XFS_BTREE_TYPE_INODE: + return xfs_btree_readahead_fsblock(cur, lr, block); + case XFS_BTREE_TYPE_MEM: + return xfs_btree_readahead_memblock(cur, lr, block); + default: + ASSERT(0); + return 0; + } } STATIC int @@ -1014,23 +1077,24 @@ xfs_btree_ptr_to_daddr( const union xfs_btree_ptr *ptr, xfs_daddr_t *daddr) { - xfs_fsblock_t fsbno; - xfs_agblock_t agbno; int error; error = xfs_btree_check_ptr(cur, ptr, 0, 1); if (error) return error; - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { - fsbno = be64_to_cpu(ptr->l); - *daddr = XFS_FSB_TO_DADDR(cur->bc_mp, fsbno); - } else { - agbno = be32_to_cpu(ptr->s); - *daddr = XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_ag.pag->pag_agno, - agbno); + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_AG: + *daddr = xfs_agbno_to_daddr(to_perag(cur->bc_group), + be32_to_cpu(ptr->s)); + break; + case XFS_BTREE_TYPE_INODE: + *daddr = XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l)); + break; + case XFS_BTREE_TYPE_MEM: + *daddr = xfbno_to_daddr(be64_to_cpu(ptr->l)); + break; } - return 0; } @@ -1050,8 +1114,9 @@ xfs_btree_readahead_ptr( if (xfs_btree_ptr_to_daddr(cur, ptr, &daddr)) return; - xfs_buf_readahead(cur->bc_mp->m_ddev_targp, daddr, - cur->bc_mp->m_bsize * count, cur->bc_ops->buf_ops); + xfs_buf_readahead(xfs_btree_buftarg(cur), daddr, + xfs_btree_bbsize(cur) * count, + cur->bc_ops->buf_ops); } /* @@ -1072,7 +1137,7 @@ xfs_btree_setbuf( cur->bc_levels[lev].ra = 0; b = XFS_BUF_TO_BLOCK(bp); - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { if (b->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)) cur->bc_levels[lev].ra |= XFS_BTCUR_LEFTRA; if (b->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)) @@ -1090,7 +1155,7 @@ xfs_btree_ptr_is_null( struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr) { - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) return ptr->l == cpu_to_be64(NULLFSBLOCK); else return ptr->s == cpu_to_be32(NULLAGBLOCK); @@ -1101,12 +1166,23 @@ xfs_btree_set_ptr_null( struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr) { - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) ptr->l = cpu_to_be64(NULLFSBLOCK); else ptr->s = cpu_to_be32(NULLAGBLOCK); } +static inline bool +xfs_btree_ptrs_equal( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr1, + union xfs_btree_ptr *ptr2) +{ + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) + return ptr1->l == ptr2->l; + return ptr1->s == ptr2->s; +} + /* * Get/set/init sibling pointers */ @@ -1119,7 +1195,7 @@ xfs_btree_get_sibling( { ASSERT(lr == XFS_BB_LEFTSIB || lr == XFS_BB_RIGHTSIB); - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { if (lr == XFS_BB_RIGHTSIB) ptr->l = block->bb_u.l.bb_rightsib; else @@ -1141,7 +1217,7 @@ xfs_btree_set_sibling( { ASSERT(lr == XFS_BB_LEFTSIB || lr == XFS_BB_RIGHTSIB); - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { if (lr == XFS_BB_RIGHTSIB) block->bb_u.l.bb_rightsib = ptr->l; else @@ -1154,25 +1230,24 @@ xfs_btree_set_sibling( } } -void -xfs_btree_init_block_int( +static void +__xfs_btree_init_block( struct xfs_mount *mp, struct xfs_btree_block *buf, + const struct xfs_btree_ops *ops, xfs_daddr_t blkno, - xfs_btnum_t btnum, __u16 level, __u16 numrecs, - __u64 owner, - unsigned int flags) + __u64 owner) { - int crc = xfs_has_crc(mp); - __u32 magic = xfs_btree_magic(crc, btnum); + bool crc = xfs_has_crc(mp); + __u32 magic = xfs_btree_magic(mp, ops); buf->bb_magic = cpu_to_be32(magic); buf->bb_level = cpu_to_be16(level); buf->bb_numrecs = cpu_to_be16(numrecs); - if (flags & XFS_BTREE_LONG_PTRS) { + if (ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { buf->bb_u.l.bb_leftsib = cpu_to_be64(NULLFSBLOCK); buf->bb_u.l.bb_rightsib = cpu_to_be64(NULLFSBLOCK); if (crc) { @@ -1183,14 +1258,12 @@ xfs_btree_init_block_int( buf->bb_u.l.bb_lsn = 0; } } else { - /* owner is a 32 bit value on short blocks */ - __u32 __owner = (__u32)owner; - buf->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK); buf->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK); if (crc) { buf->bb_u.s.bb_blkno = cpu_to_be64(blkno); - buf->bb_u.s.bb_owner = cpu_to_be32(__owner); + /* owner is a 32 bit value on short blocks */ + buf->bb_u.s.bb_owner = cpu_to_be32((__u32)owner); uuid_copy(&buf->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid); buf->bb_u.s.bb_lsn = 0; } @@ -1199,64 +1272,57 @@ xfs_btree_init_block_int( void xfs_btree_init_block( - struct xfs_mount *mp, - struct xfs_buf *bp, - xfs_btnum_t btnum, - __u16 level, - __u16 numrecs, - __u64 owner) + struct xfs_mount *mp, + struct xfs_btree_block *block, + const struct xfs_btree_ops *ops, + __u16 level, + __u16 numrecs, + __u64 owner) { - xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), xfs_buf_daddr(bp), - btnum, level, numrecs, owner, 0); + __xfs_btree_init_block(mp, block, ops, XFS_BUF_DADDR_NULL, level, + numrecs, owner); } void -xfs_btree_init_block_cur( - struct xfs_btree_cur *cur, - struct xfs_buf *bp, - int level, - int numrecs) +xfs_btree_init_buf( + struct xfs_mount *mp, + struct xfs_buf *bp, + const struct xfs_btree_ops *ops, + __u16 level, + __u16 numrecs, + __u64 owner) { - __u64 owner; - - /* - * we can pull the owner from the cursor right now as the different - * owners align directly with the pointer size of the btree. This may - * change in future, but is safe for current users of the generic btree - * code. - */ - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) - owner = cur->bc_ino.ip->i_ino; - else - owner = cur->bc_ag.pag->pag_agno; - - xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), - xfs_buf_daddr(bp), cur->bc_btnum, level, - numrecs, owner, cur->bc_flags); + __xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops, + xfs_buf_daddr(bp), level, numrecs, owner); + bp->b_ops = ops->buf_ops; } -/* - * Return true if ptr is the last record in the btree and - * we need to track updates to this record. The decision - * will be further refined in the update_lastrec method. - */ -STATIC int -xfs_btree_is_lastrec( - struct xfs_btree_cur *cur, - struct xfs_btree_block *block, - int level) +static inline __u64 +xfs_btree_owner( + struct xfs_btree_cur *cur) { - union xfs_btree_ptr ptr; - - if (level > 0) - return 0; - if (!(cur->bc_flags & XFS_BTREE_LASTREC_UPDATE)) + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_MEM: + return cur->bc_mem.xfbtree->owner; + case XFS_BTREE_TYPE_INODE: + return cur->bc_ino.ip->i_ino; + case XFS_BTREE_TYPE_AG: + return cur->bc_group->xg_gno; + default: + ASSERT(0); return 0; + } +} - xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB); - if (!xfs_btree_ptr_is_null(cur, &ptr)) - return 0; - return 1; +void +xfs_btree_init_block_cur( + struct xfs_btree_cur *cur, + struct xfs_buf *bp, + int level, + int numrecs) +{ + xfs_btree_init_buf(cur->bc_mp, bp, cur->bc_ops, level, numrecs, + xfs_btree_owner(cur)); } STATIC void @@ -1265,41 +1331,27 @@ xfs_btree_buf_to_ptr( struct xfs_buf *bp, union xfs_btree_ptr *ptr) { - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) - ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp, - xfs_buf_daddr(bp))); - else { + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_AG: ptr->s = cpu_to_be32(xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp))); + break; + case XFS_BTREE_TYPE_INODE: + ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp, + xfs_buf_daddr(bp))); + break; + case XFS_BTREE_TYPE_MEM: + ptr->l = cpu_to_be64(xfs_daddr_to_xfbno(xfs_buf_daddr(bp))); + break; } } -STATIC void +static inline void xfs_btree_set_refs( struct xfs_btree_cur *cur, struct xfs_buf *bp) { - switch (cur->bc_btnum) { - case XFS_BTNUM_BNO: - case XFS_BTNUM_CNT: - xfs_buf_set_ref(bp, XFS_ALLOC_BTREE_REF); - break; - case XFS_BTNUM_INO: - case XFS_BTNUM_FINO: - xfs_buf_set_ref(bp, XFS_INO_BTREE_REF); - break; - case XFS_BTNUM_BMAP: - xfs_buf_set_ref(bp, XFS_BMAP_BTREE_REF); - break; - case XFS_BTNUM_RMAP: - xfs_buf_set_ref(bp, XFS_RMAP_BTREE_REF); - break; - case XFS_BTNUM_REFC: - xfs_buf_set_ref(bp, XFS_REFC_BTREE_REF); - break; - default: - ASSERT(0); - } + xfs_buf_set_ref(bp, cur->bc_ops->lru_refs); } int @@ -1309,15 +1361,14 @@ xfs_btree_get_buf_block( struct xfs_btree_block **block, struct xfs_buf **bpp) { - struct xfs_mount *mp = cur->bc_mp; - xfs_daddr_t d; - int error; + xfs_daddr_t d; + int error; error = xfs_btree_ptr_to_daddr(cur, ptr, &d); if (error) return error; - error = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d, mp->m_bsize, - 0, bpp); + error = xfs_trans_get_buf(cur->bc_tp, xfs_btree_buftarg(cur), d, + xfs_btree_bbsize(cur), 0, bpp); if (error) return error; @@ -1330,7 +1381,7 @@ xfs_btree_get_buf_block( * Read in the buffer at the given ptr and return the buffer and * the block pointer within the buffer. */ -STATIC int +int xfs_btree_read_buf_block( struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr, @@ -1348,9 +1399,11 @@ xfs_btree_read_buf_block( error = xfs_btree_ptr_to_daddr(cur, ptr, &d); if (error) return error; - error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d, - mp->m_bsize, flags, bpp, - cur->bc_ops->buf_ops); + error = xfs_trans_read_buf(mp, cur->bc_tp, xfs_btree_buftarg(cur), d, + xfs_btree_bbsize(cur), flags, bpp, + cur->bc_ops->buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_btree_mark_sick(cur); if (error) return error; @@ -1398,7 +1451,7 @@ xfs_btree_copy_ptrs( int numptrs) { ASSERT(numptrs >= 0); - memcpy(dst_ptr, src_ptr, numptrs * xfs_btree_ptr_len(cur)); + memcpy(dst_ptr, src_ptr, numptrs * cur->bc_ops->ptr_len); } /* @@ -1454,8 +1507,8 @@ xfs_btree_shift_ptrs( ASSERT(numptrs >= 0); ASSERT(dir == 1 || dir == -1); - dst_ptr = (char *)ptr + (dir * xfs_btree_ptr_len(cur)); - memmove(dst_ptr, ptr, numptrs * xfs_btree_ptr_len(cur)); + dst_ptr = (char *)ptr + (dir * cur->bc_ops->ptr_len); + memmove(dst_ptr, ptr, numptrs * cur->bc_ops->ptr_len); } /* @@ -1490,12 +1543,16 @@ xfs_btree_log_recs( int first, int last) { + if (!bp) { + xfs_trans_log_inode(cur->bc_tp, cur->bc_ino.ip, + xfs_ilog_fbroot(cur->bc_ino.whichfork)); + return; + } xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF); xfs_trans_log_buf(cur->bc_tp, bp, xfs_btree_rec_offset(cur, first), xfs_btree_rec_offset(cur, last + 1) - 1); - } /* @@ -1566,7 +1623,7 @@ xfs_btree_log_block( if (bp) { int nbits; - if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS) { + if (xfs_has_crc(cur->bc_mp)) { /* * We don't log the CRC when updating a btree * block but instead recreate it during log @@ -1581,7 +1638,7 @@ xfs_btree_log_block( nbits = XFS_BB_NUM_BITS; } xfs_btree_offsets(fields, - (cur->bc_flags & XFS_BTREE_LONG_PTRS) ? + (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) ? loffsets : soffsets, nbits, &first, &last); xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF); @@ -1658,9 +1715,10 @@ xfs_btree_increment( * confused or have the tree root in an inode. */ if (lev == cur->bc_nlevels) { - if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) + if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) goto out0; ASSERT(0); + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -1751,9 +1809,10 @@ xfs_btree_decrement( * or the root of the tree is in an inode. */ if (lev == cur->bc_nlevels) { - if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) + if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) goto out0; ASSERT(0); + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -1786,6 +1845,33 @@ error0: return error; } +/* + * Check the btree block owner now that we have the context to know who the + * real owner is. + */ +static inline xfs_failaddr_t +xfs_btree_check_block_owner( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block) +{ + __u64 owner; + + if (!xfs_has_crc(cur->bc_mp) || + (cur->bc_flags & XFS_BTREE_BMBT_INVALID_OWNER)) + return NULL; + + owner = xfs_btree_owner(cur); + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { + if (be64_to_cpu(block->bb_u.l.bb_owner) != owner) + return __this_address; + } else { + if (be32_to_cpu(block->bb_u.s.bb_owner) != owner) + return __this_address; + } + + return NULL; +} + int xfs_btree_lookup_get_block( struct xfs_btree_cur *cur, /* btree cursor */ @@ -1798,8 +1884,7 @@ xfs_btree_lookup_get_block( int error = 0; /* special case the root block if in an inode */ - if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && - (level == cur->bc_nlevels - 1)) { + if (xfs_btree_at_iroot(cur, level)) { *blkp = xfs_btree_get_iroot(cur); return 0; } @@ -1824,11 +1909,7 @@ xfs_btree_lookup_get_block( return error; /* Check the inode owner since the verifiers don't. */ - if (xfs_has_crc(cur->bc_mp) && - !(cur->bc_ino.flags & XFS_BTCUR_BMBT_INVALID_OWNER) && - (cur->bc_flags & XFS_BTREE_LONG_PTRS) && - be64_to_cpu((*blkp)->bb_u.l.bb_owner) != - cur->bc_ino.ip->i_ino) + if (xfs_btree_check_block_owner(cur, *blkp) != NULL) goto out_bad; /* Did we get the level we were looking for? */ @@ -1846,6 +1927,7 @@ out_bad: *blkp = NULL; xfs_buf_mark_corrupt(bp); xfs_trans_brelse(cur->bc_tp, bp); + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } @@ -1872,6 +1954,27 @@ xfs_lookup_get_search_key( } /* + * Initialize a pointer to the root block. + */ +void +xfs_btree_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { + /* + * Inode-rooted btrees call xfs_btree_get_iroot to find the root + * in xfs_btree_lookup_get_block and don't need a pointer here. + */ + ptr->l = 0; + } else if (cur->bc_flags & XFS_BTREE_STAGING) { + ptr->s = cpu_to_be32(cur->bc_ag.afake->af_root); + } else { + cur->bc_ops->init_ptr_from_cur(cur, ptr); + } +} + +/* * Lookup the record. The cursor is made to point to it, based on dir. * stat is set to 0 if can't find any such record, 1 for success. */ @@ -1882,7 +1985,7 @@ xfs_btree_lookup( int *stat) /* success/failure */ { struct xfs_btree_block *block; /* current btree block */ - int64_t diff; /* difference for the current key */ + int cmp_r; /* current key comparison result */ int error; /* error return value */ int keyno; /* current key number */ int level; /* level in the btree */ @@ -1892,14 +1995,16 @@ xfs_btree_lookup( XFS_BTREE_STATS_INC(cur, lookup); /* No such thing as a zero-level tree. */ - if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0)) + if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } block = NULL; keyno = 0; /* initialise start pointer from cursor */ - cur->bc_ops->init_ptr_from_cur(cur, &ptr); + xfs_btree_init_ptr_from_cur(cur, &ptr); pp = &ptr; /* @@ -1908,13 +2013,13 @@ xfs_btree_lookup( * on the lookup record, then follow the corresponding block * pointer down to the next level. */ - for (level = cur->bc_nlevels - 1, diff = 1; level >= 0; level--) { + for (level = cur->bc_nlevels - 1, cmp_r = 1; level >= 0; level--) { /* Get the block we need to do the lookup on. */ error = xfs_btree_lookup_get_block(cur, level, pp, &block); if (error) goto error0; - if (diff == 0) { + if (cmp_r == 0) { /* * If we already had a key match at a higher level, we * know we need to use the first entry in this block. @@ -1936,6 +2041,7 @@ xfs_btree_lookup( XFS_ERRLEVEL_LOW, cur->bc_mp, block, sizeof(*block)); + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } @@ -1959,15 +2065,16 @@ xfs_btree_lookup( keyno, block, &key); /* - * Compute difference to get next direction: + * Compute comparison result to get next + * direction: * - less than, move right * - greater than, move left * - equal, we're done */ - diff = cur->bc_ops->key_diff(cur, kp); - if (diff < 0) + cmp_r = cur->bc_ops->cmp_key_with_cur(cur, kp); + if (cmp_r < 0) low = keyno + 1; - else if (diff > 0) + else if (cmp_r > 0) high = keyno - 1; else break; @@ -1983,7 +2090,7 @@ xfs_btree_lookup( * If we moved left, need the previous key number, * unless there isn't one. */ - if (diff > 0 && --keyno < 1) + if (cmp_r > 0 && --keyno < 1) keyno = 1; pp = xfs_btree_ptr_addr(cur, keyno, block); @@ -1996,7 +2103,7 @@ xfs_btree_lookup( } /* Done with the search. See if we need to adjust the results. */ - if (dir != XFS_LOOKUP_LE && diff < 0) { + if (dir != XFS_LOOKUP_LE && cmp_r < 0) { keyno++; /* * If ge search and we went off the end of the block, but it's @@ -2012,19 +2119,21 @@ xfs_btree_lookup( error = xfs_btree_increment(cur, 0, &i); if (error) goto error0; - if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) + if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } *stat = 1; return 0; } - } else if (dir == XFS_LOOKUP_LE && diff > 0) + } else if (dir == XFS_LOOKUP_LE && cmp_r > 0) keyno--; cur->bc_levels[0].ptr = keyno; /* Return if we succeeded or not. */ if (keyno == 0 || keyno > xfs_btree_get_numrecs(block)) *stat = 0; - else if (dir != XFS_LOOKUP_EQ || diff == 0) + else if (dir != XFS_LOOKUP_EQ || cmp_r == 0) *stat = 1; else *stat = 0; @@ -2040,7 +2149,7 @@ xfs_btree_high_key_from_key( struct xfs_btree_cur *cur, union xfs_btree_key *key) { - ASSERT(cur->bc_flags & XFS_BTREE_OVERLAPPING); + ASSERT(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING); return (union xfs_btree_key *)((char *)key + (cur->bc_ops->key_len / 2)); } @@ -2061,14 +2170,13 @@ xfs_btree_get_leaf_keys( rec = xfs_btree_rec_addr(cur, 1, block); cur->bc_ops->init_key_from_rec(key, rec); - if (cur->bc_flags & XFS_BTREE_OVERLAPPING) { + if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) { cur->bc_ops->init_high_key_from_rec(&max_hkey, rec); for (n = 2; n <= xfs_btree_get_numrecs(block); n++) { rec = xfs_btree_rec_addr(cur, n, block); cur->bc_ops->init_high_key_from_rec(&hkey, rec); - if (cur->bc_ops->diff_two_keys(cur, &hkey, &max_hkey) - > 0) + if (xfs_btree_keycmp_gt(cur, &hkey, &max_hkey)) max_hkey = hkey; } @@ -2089,14 +2197,14 @@ xfs_btree_get_node_keys( union xfs_btree_key *high; int n; - if (cur->bc_flags & XFS_BTREE_OVERLAPPING) { + if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) { memcpy(key, xfs_btree_key_addr(cur, 1, block), cur->bc_ops->key_len / 2); max_hkey = xfs_btree_high_key_addr(cur, 1, block); for (n = 2; n <= xfs_btree_get_numrecs(block); n++) { hkey = xfs_btree_high_key_addr(cur, n, block); - if (cur->bc_ops->diff_two_keys(cur, hkey, max_hkey) > 0) + if (xfs_btree_keycmp_gt(cur, hkey, max_hkey)) max_hkey = hkey; } @@ -2133,7 +2241,7 @@ xfs_btree_needs_key_update( struct xfs_btree_cur *cur, int ptr) { - return (cur->bc_flags & XFS_BTREE_OVERLAPPING) || ptr == 1; + return (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) || ptr == 1; } /* @@ -2157,7 +2265,7 @@ __xfs_btree_updkeys( struct xfs_buf *bp; int ptr; - ASSERT(cur->bc_flags & XFS_BTREE_OVERLAPPING); + ASSERT(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING); /* Exit if there aren't any parent levels to update. */ if (level + 1 >= cur->bc_nlevels) @@ -2183,8 +2291,8 @@ __xfs_btree_updkeys( nlkey = xfs_btree_key_addr(cur, ptr, block); nhkey = xfs_btree_high_key_addr(cur, ptr, block); if (!force_all && - !(cur->bc_ops->diff_two_keys(cur, nlkey, lkey) != 0 || - cur->bc_ops->diff_two_keys(cur, nhkey, hkey) != 0)) + xfs_btree_keycmp_eq(cur, nlkey, lkey) && + xfs_btree_keycmp_eq(cur, nhkey, hkey)) break; xfs_btree_copy_keys(cur, nlkey, lkey, 1); xfs_btree_log_keys(cur, bp, ptr, ptr); @@ -2226,7 +2334,7 @@ xfs_btree_update_keys( ASSERT(level >= 0); block = xfs_btree_get_block(cur, level, &bp); - if (cur->bc_flags & XFS_BTREE_OVERLAPPING) + if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) return __xfs_btree_updkeys(cur, level, block, bp, false); /* @@ -2287,15 +2395,6 @@ xfs_btree_update( xfs_btree_copy_recs(cur, rp, rec, 1); xfs_btree_log_recs(cur, bp, ptr, ptr); - /* - * If we are tracking the last record in the tree and - * we are at the far right edge of the tree, update it. - */ - if (xfs_btree_is_lastrec(cur, block, 0)) { - cur->bc_ops->update_lastrec(cur, block, rec, - ptr, LASTREC_UPDATE); - } - /* Pass new key value up to our parent. */ if (xfs_btree_needs_key_update(cur, ptr)) { error = xfs_btree_update_keys(cur, 0); @@ -2333,8 +2432,7 @@ xfs_btree_lshift( int error; /* error return value */ int i; - if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && - level == cur->bc_nlevels - 1) + if (xfs_btree_at_iroot(cur, level)) goto out0; /* Set up variables for this block as "right". */ @@ -2461,12 +2559,13 @@ xfs_btree_lshift( * Using a temporary cursor, update the parent key values of the * block on the left. */ - if (cur->bc_flags & XFS_BTREE_OVERLAPPING) { + if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) { error = xfs_btree_dup_cursor(cur, &tcur); if (error) goto error0; i = xfs_btree_firstrec(tcur, level); if (XFS_IS_CORRUPT(tcur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -2528,8 +2627,7 @@ xfs_btree_rshift( int error; /* error return value */ int i; /* loop counter */ - if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && - (level == cur->bc_nlevels - 1)) + if (xfs_btree_at_iroot(cur, level)) goto out0; /* Set up variables for this block as "left". */ @@ -2637,6 +2735,7 @@ xfs_btree_rshift( goto error0; i = xfs_btree_lastrec(tcur, level); if (XFS_IS_CORRUPT(tcur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -2646,7 +2745,7 @@ xfs_btree_rshift( goto error1; /* Update the parent high keys of the left block, if needed. */ - if (cur->bc_flags & XFS_BTREE_OVERLAPPING) { + if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) { error = xfs_btree_update_keys(cur, level); if (error) goto error1; @@ -2674,6 +2773,32 @@ error1: return error; } +static inline int +xfs_btree_alloc_block( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *hint_block, + union xfs_btree_ptr *new_block, + int *stat) +{ + int error; + + /* + * Don't allow block allocation for a staging cursor, because staging + * cursors do not support regular btree modifications. + * + * Bulk loading uses a separate callback to obtain new blocks from a + * preallocated list, which prevents ENOSPC failures during loading. + */ + if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) { + ASSERT(0); + return -EFSCORRUPTED; + } + + error = cur->bc_ops->alloc_block(cur, hint_block, new_block, stat); + trace_xfs_btree_alloc_block(cur, new_block, *stat, error); + return error; +} + /* * Split cur/level block in half. * Return new block number and the key to its first @@ -2717,7 +2842,7 @@ __xfs_btree_split( xfs_btree_buf_to_ptr(cur, lbp, &lptr); /* Allocate the new block. If we can't do it, we're toast. Give up. */ - error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, stat); + error = xfs_btree_alloc_block(cur, &lptr, &rptr, stat); if (error) goto error0; if (*stat == 0) @@ -2824,7 +2949,7 @@ __xfs_btree_split( } /* Update the parent high keys of the left block, if needed. */ - if (cur->bc_flags & XFS_BTREE_OVERLAPPING) { + if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) { error = xfs_btree_update_keys(cur, level); if (error) goto error0; @@ -2913,9 +3038,22 @@ xfs_btree_split_worker( } /* - * BMBT split requests often come in with little stack to work on. Push + * BMBT split requests often come in with little stack to work on so we push * them off to a worker thread so there is lots of stack to use. For the other * btree types, just call directly to avoid the context switch overhead here. + * + * Care must be taken here - the work queue rescuer thread introduces potential + * AGF <> worker queue deadlocks if the BMBT block allocation has to lock new + * AGFs to allocate blocks. A task being run by the rescuer could attempt to + * lock an AGF that is already locked by a task queued to run by the rescuer, + * resulting in an ABBA deadlock as the rescuer cannot run the lock holder to + * release it until the current thread it is running gains the lock. + * + * To avoid this issue, we only ever queue BMBT splits that don't have an AGF + * already locked to allocate from. The only place that doesn't hold an AGF + * locked is unwritten extent conversion at IO completion, but that has already + * been offloaded to a worker thread and hence has no stack consumption issues + * we have to worry about. */ STATIC int /* error */ xfs_btree_split( @@ -2929,7 +3067,8 @@ xfs_btree_split( struct xfs_btree_split_args args; DECLARE_COMPLETION_ONSTACK(done); - if (cur->bc_btnum != XFS_BTNUM_BMAP) + if (!xfs_btree_is_bmap(cur->bc_ops) || + cur->bc_tp->t_highest_agno == NULLAGNUMBER) return __xfs_btree_split(cur, level, ptrp, key, curp, stat); args.cur = cur; @@ -2950,6 +3089,130 @@ xfs_btree_split( #define xfs_btree_split __xfs_btree_split #endif /* __KERNEL__ */ +/* Move the records from a root leaf block to a separate block. */ +STATIC void +xfs_btree_promote_leaf_iroot( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block, + struct xfs_buf *cbp, + union xfs_btree_ptr *cptr, + struct xfs_btree_block *cblock) +{ + union xfs_btree_rec *rp; + union xfs_btree_rec *crp; + union xfs_btree_key *kp; + union xfs_btree_ptr *pp; + struct xfs_btree_block *broot; + int numrecs = xfs_btree_get_numrecs(block); + + /* Copy the records from the leaf broot into the new child block. */ + rp = xfs_btree_rec_addr(cur, 1, block); + crp = xfs_btree_rec_addr(cur, 1, cblock); + xfs_btree_copy_recs(cur, crp, rp, numrecs); + + /* + * Increment the tree height. + * + * Trickery here: The amount of memory that we need per record for the + * ifork's btree root block may change when we convert the broot from a + * leaf to a node block. Free the existing leaf broot so that nobody + * thinks we need to migrate node pointers when we realloc the broot + * buffer after bumping nlevels. + */ + cur->bc_ops->broot_realloc(cur, 0); + cur->bc_nlevels++; + cur->bc_levels[1].ptr = 1; + + /* + * Allocate a new node broot and initialize it to point to the new + * child block. + */ + broot = cur->bc_ops->broot_realloc(cur, 1); + xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, + cur->bc_nlevels - 1, 1, cur->bc_ino.ip->i_ino); + + pp = xfs_btree_ptr_addr(cur, 1, broot); + kp = xfs_btree_key_addr(cur, 1, broot); + xfs_btree_copy_ptrs(cur, pp, cptr, 1); + xfs_btree_get_keys(cur, cblock, kp); + + /* Attach the new block to the cursor and log it. */ + xfs_btree_setbuf(cur, 0, cbp); + xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); + xfs_btree_log_recs(cur, cbp, 1, numrecs); +} + +/* + * Move the keys and pointers from a root block to a separate block. + * + * Since the keyptr size does not change, all we have to do is increase the + * tree height, copy the keyptrs to the new internal node (cblock), shrink + * the root, and copy the pointers there. + */ +STATIC int +xfs_btree_promote_node_iroot( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block, + int level, + struct xfs_buf *cbp, + union xfs_btree_ptr *cptr, + struct xfs_btree_block *cblock) +{ + union xfs_btree_key *ckp; + union xfs_btree_key *kp; + union xfs_btree_ptr *cpp; + union xfs_btree_ptr *pp; + int i; + int error; + int numrecs = xfs_btree_get_numrecs(block); + + /* + * Increase tree height, adjusting the root block level to match. + * We cannot change the root btree node size until we've copied the + * block contents to the new child block. + */ + be16_add_cpu(&block->bb_level, 1); + cur->bc_nlevels++; + cur->bc_levels[level + 1].ptr = 1; + + /* + * Adjust the root btree record count, then copy the keys from the old + * root to the new child block. + */ + xfs_btree_set_numrecs(block, 1); + kp = xfs_btree_key_addr(cur, 1, block); + ckp = xfs_btree_key_addr(cur, 1, cblock); + xfs_btree_copy_keys(cur, ckp, kp, numrecs); + + /* Check the pointers and copy them to the new child block. */ + pp = xfs_btree_ptr_addr(cur, 1, block); + cpp = xfs_btree_ptr_addr(cur, 1, cblock); + for (i = 0; i < numrecs; i++) { + error = xfs_btree_debug_check_ptr(cur, pp, i, level); + if (error) + return error; + } + xfs_btree_copy_ptrs(cur, cpp, pp, numrecs); + + /* + * Set the first keyptr to point to the new child block, then shrink + * the memory buffer for the root block. + */ + error = xfs_btree_debug_check_ptr(cur, cptr, 0, level); + if (error) + return error; + xfs_btree_copy_ptrs(cur, pp, cptr, 1); + xfs_btree_get_keys(cur, cblock, kp); + + cur->bc_ops->broot_realloc(cur, 1); + + /* Attach the new block to the cursor and log it. */ + xfs_btree_setbuf(cur, level, cbp); + xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); + xfs_btree_log_keys(cur, cbp, 1, numrecs); + xfs_btree_log_ptrs(cur, cbp, 1, numrecs); + return 0; +} /* * Copy the old inode root contents into a real block and make the @@ -2964,26 +3227,27 @@ xfs_btree_new_iroot( struct xfs_buf *cbp; /* buffer for cblock */ struct xfs_btree_block *block; /* btree block */ struct xfs_btree_block *cblock; /* child btree block */ - union xfs_btree_key *ckp; /* child key pointer */ - union xfs_btree_ptr *cpp; /* child ptr pointer */ - union xfs_btree_key *kp; /* pointer to btree key */ - union xfs_btree_ptr *pp; /* pointer to block addr */ + union xfs_btree_ptr aptr; union xfs_btree_ptr nptr; /* new block addr */ int level; /* btree level */ int error; /* error return code */ - int i; /* loop counter */ XFS_BTREE_STATS_INC(cur, newroot); - ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); level = cur->bc_nlevels - 1; block = xfs_btree_get_iroot(cur); - pp = xfs_btree_ptr_addr(cur, 1, block); + ASSERT(level > 0 || (cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)); + if (level > 0) + aptr = *xfs_btree_ptr_addr(cur, 1, block); + else + aptr.l = cpu_to_be64(XFS_INO_TO_FSB(cur->bc_mp, + cur->bc_ino.ip->i_ino)); /* Allocate the new block. If we can't do it, we're toast. Give up. */ - error = cur->bc_ops->alloc_block(cur, pp, &nptr, stat); + error = xfs_btree_alloc_block(cur, &aptr, &nptr, stat); if (error) goto error0; if (*stat == 0) @@ -3001,61 +3265,45 @@ xfs_btree_new_iroot( * In that case have to also ensure the blkno remains correct */ memcpy(cblock, block, xfs_btree_block_len(cur)); - if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS) { + if (xfs_has_crc(cur->bc_mp)) { __be64 bno = cpu_to_be64(xfs_buf_daddr(cbp)); - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) cblock->bb_u.l.bb_blkno = bno; else cblock->bb_u.s.bb_blkno = bno; } - be16_add_cpu(&block->bb_level, 1); - xfs_btree_set_numrecs(block, 1); - cur->bc_nlevels++; - ASSERT(cur->bc_nlevels <= cur->bc_maxlevels); - cur->bc_levels[level + 1].ptr = 1; - - kp = xfs_btree_key_addr(cur, 1, block); - ckp = xfs_btree_key_addr(cur, 1, cblock); - xfs_btree_copy_keys(cur, ckp, kp, xfs_btree_get_numrecs(cblock)); - - cpp = xfs_btree_ptr_addr(cur, 1, cblock); - for (i = 0; i < be16_to_cpu(cblock->bb_numrecs); i++) { - error = xfs_btree_debug_check_ptr(cur, pp, i, level); + if (level > 0) { + error = xfs_btree_promote_node_iroot(cur, block, level, cbp, + &nptr, cblock); if (error) goto error0; + } else { + xfs_btree_promote_leaf_iroot(cur, block, cbp, &nptr, cblock); } - xfs_btree_copy_ptrs(cur, cpp, pp, xfs_btree_get_numrecs(cblock)); - - error = xfs_btree_debug_check_ptr(cur, &nptr, 0, level); - if (error) - goto error0; - - xfs_btree_copy_ptrs(cur, pp, &nptr, 1); - - xfs_iroot_realloc(cur->bc_ino.ip, - 1 - xfs_btree_get_numrecs(cblock), - cur->bc_ino.whichfork); - - xfs_btree_setbuf(cur, level, cbp); - - /* - * Do all this logging at the end so that - * the root is at the right level. - */ - xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); - xfs_btree_log_keys(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs)); - xfs_btree_log_ptrs(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs)); - - *logflags |= - XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork); + *logflags |= XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork); *stat = 1; return 0; error0: return error; } +static void +xfs_btree_set_root( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *ptr, + int inc) +{ + if (cur->bc_flags & XFS_BTREE_STAGING) { + /* Update the btree root information for a per-AG fake root. */ + cur->bc_ag.afake->af_root = be32_to_cpu(ptr->s); + cur->bc_ag.afake->af_levels += inc; + } else { + cur->bc_ops->set_root(cur, ptr, inc); + } +} + /* * Allocate a new root block, fill it in. */ @@ -3080,10 +3328,10 @@ xfs_btree_new_root( XFS_BTREE_STATS_INC(cur, newroot); /* initialise our start point from the cursor */ - cur->bc_ops->init_ptr_from_cur(cur, &rptr); + xfs_btree_init_ptr_from_cur(cur, &rptr); /* Allocate the new block. If we can't do it, we're toast. Give up. */ - error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, stat); + error = xfs_btree_alloc_block(cur, &rptr, &lptr, stat); if (error) goto error0; if (*stat == 0) @@ -3096,7 +3344,7 @@ xfs_btree_new_root( goto error0; /* Set the root in the holding structure increasing the level by 1. */ - cur->bc_ops->set_root(cur, &lptr, 1); + xfs_btree_set_root(cur, &lptr, 1); /* * At the previous root level there are now two blocks: the old root, @@ -3200,13 +3448,12 @@ xfs_btree_make_block_unfull( { int error = 0; - if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && - level == cur->bc_nlevels - 1) { + if (xfs_btree_at_iroot(cur, level)) { struct xfs_inode *ip = cur->bc_ino.ip; if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) { /* A root block that can be made bigger. */ - xfs_iroot_realloc(ip, 1, cur->bc_ino.whichfork); + cur->bc_ops->broot_realloc(cur, numrecs + 1); *stat = 1; } else { /* A root block that needs replacing */ @@ -3286,8 +3533,8 @@ xfs_btree_insrec( * If we have an external root pointer, and we've made it to the * root level, allocate a new root block and we're done. */ - if (!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && - (level >= cur->bc_nlevels)) { + if (cur->bc_ops->type != XFS_BTREE_TYPE_INODE && + level >= cur->bc_nlevels) { error = xfs_btree_new_root(cur, stat); xfs_btree_set_ptr_null(cur, ptrp); @@ -3416,14 +3663,31 @@ xfs_btree_insrec( xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS); /* - * If we just inserted into a new tree block, we have to - * recalculate nkey here because nkey is out of date. + * Update btree keys to reflect the newly added record or keyptr. + * There are three cases here to be aware of. Normally, all we have to + * do is walk towards the root, updating keys as necessary. + * + * If the caller had us target a full block for the insertion, we dealt + * with that by calling the _make_block_unfull function. If the + * "make unfull" function splits the block, it'll hand us back the key + * and pointer of the new block. We haven't yet added the new block to + * the next level up, so if we decide to add the new record to the new + * block (bp->b_bn != old_bn), we have to update the caller's pointer + * so that the caller adds the new block with the correct key. * - * Otherwise we're just updating an existing block (having shoved - * some records into the new tree block), so use the regular key - * update mechanism. + * However, there is a third possibility-- if the selected block is the + * root block of an inode-rooted btree and cannot be expanded further, + * the "make unfull" function moves the root block contents to a new + * block and updates the root block to point to the new block. In this + * case, no block pointer is passed back because the block has already + * been added to the btree. In this case, we need to use the regular + * key update function, just like the first case. This is critical for + * overlapping btrees, because the high key must be updated to reflect + * the entire tree, not just the subtree accessible through the first + * child of the root (which is now two levels down from the root). */ - if (bp && xfs_buf_daddr(bp) != old_bn) { + if (!xfs_btree_ptr_is_null(cur, &nptr) && + bp && xfs_buf_daddr(bp) != old_bn) { xfs_btree_get_keys(cur, block, lkey); } else if (xfs_btree_needs_key_update(cur, optr)) { error = xfs_btree_update_keys(cur, level); @@ -3432,15 +3696,6 @@ xfs_btree_insrec( } /* - * If we are tracking the last record in the tree and - * we are at the far right edge of the tree, update it. - */ - if (xfs_btree_is_lastrec(cur, block, level)) { - cur->bc_ops->update_lastrec(cur, block, rec, - ptr, LASTREC_INSREC); - } - - /* * Return the new block number, if any. * If there is one, give back a record value and a cursor too. */ @@ -3511,6 +3766,7 @@ xfs_btree_insert( } if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -3524,7 +3780,8 @@ xfs_btree_insert( if (pcur != cur && (ncur || xfs_btree_ptr_is_null(cur, &nptr))) { /* Save the state from the cursor before we trash it */ - if (cur->bc_ops->update_cursor) + if (cur->bc_ops->update_cursor && + !(cur->bc_flags & XFS_BTREE_STAGING)) cur->bc_ops->update_cursor(pcur, cur); cur->bc_nlevels = pcur->bc_nlevels; xfs_btree_del_cursor(pcur, XFS_BTREE_NOERROR); @@ -3542,6 +3799,97 @@ error0: return error; } +/* Move the records from a child leaf block to the root block. */ +STATIC void +xfs_btree_demote_leaf_child( + struct xfs_btree_cur *cur, + struct xfs_btree_block *cblock, + int numrecs) +{ + union xfs_btree_rec *rp; + union xfs_btree_rec *crp; + struct xfs_btree_block *broot; + + /* + * Decrease the tree height. + * + * Trickery here: The amount of memory that we need per record for the + * ifork's btree root block may change when we convert the broot from a + * node to a leaf. Free the old node broot so that we can get a fresh + * leaf broot. + */ + cur->bc_ops->broot_realloc(cur, 0); + cur->bc_nlevels--; + + /* + * Allocate a new leaf broot and copy the records from the old child. + * Detach the old child from the cursor. + */ + broot = cur->bc_ops->broot_realloc(cur, numrecs); + xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, 0, numrecs, + cur->bc_ino.ip->i_ino); + + rp = xfs_btree_rec_addr(cur, 1, broot); + crp = xfs_btree_rec_addr(cur, 1, cblock); + xfs_btree_copy_recs(cur, rp, crp, numrecs); + + cur->bc_levels[0].bp = NULL; +} + +/* + * Move the keyptrs from a child node block to the root block. + * + * Since the keyptr size does not change, all we have to do is increase the + * tree height, copy the keyptrs to the new internal node (cblock), shrink + * the root, and copy the pointers there. + */ +STATIC int +xfs_btree_demote_node_child( + struct xfs_btree_cur *cur, + struct xfs_btree_block *cblock, + int level, + int numrecs) +{ + struct xfs_btree_block *block; + union xfs_btree_key *ckp; + union xfs_btree_key *kp; + union xfs_btree_ptr *cpp; + union xfs_btree_ptr *pp; + int i; + int error; + + /* + * Adjust the root btree node size and the record count to match the + * doomed child so that we can copy the keyptrs ahead of changing the + * tree shape. + */ + block = cur->bc_ops->broot_realloc(cur, numrecs); + + xfs_btree_set_numrecs(block, numrecs); + ASSERT(block->bb_numrecs == cblock->bb_numrecs); + + /* Copy keys from the doomed block. */ + kp = xfs_btree_key_addr(cur, 1, block); + ckp = xfs_btree_key_addr(cur, 1, cblock); + xfs_btree_copy_keys(cur, kp, ckp, numrecs); + + /* Copy pointers from the doomed block. */ + pp = xfs_btree_ptr_addr(cur, 1, block); + cpp = xfs_btree_ptr_addr(cur, 1, cblock); + for (i = 0; i < numrecs; i++) { + error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1); + if (error) + return error; + } + xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); + + /* Decrease tree height, adjusting the root block level to match. */ + cur->bc_levels[level - 1].bp = NULL; + be16_add_cpu(&block->bb_level, -1); + cur->bc_nlevels--; + return 0; +} + /* * Try to merge a non-leaf block back into the inode root. * @@ -3554,34 +3902,31 @@ STATIC int xfs_btree_kill_iroot( struct xfs_btree_cur *cur) { - int whichfork = cur->bc_ino.whichfork; struct xfs_inode *ip = cur->bc_ino.ip; - struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_block *block; struct xfs_btree_block *cblock; - union xfs_btree_key *kp; - union xfs_btree_key *ckp; - union xfs_btree_ptr *pp; - union xfs_btree_ptr *cpp; struct xfs_buf *cbp; int level; - int index; int numrecs; int error; #ifdef DEBUG union xfs_btree_ptr ptr; #endif - int i; - ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); - ASSERT(cur->bc_nlevels > 1); + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); + ASSERT((cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS) || + cur->bc_nlevels > 1); /* * Don't deal with the root block needs to be a leaf case. * We're just going to turn the thing back into extents anyway. */ level = cur->bc_nlevels - 1; - if (level == 1) + if (level == 1 && !(cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)) + goto out0; + + /* If we're already a leaf, jump out. */ + if (level == 0) goto out0; /* @@ -3611,40 +3956,20 @@ xfs_btree_kill_iroot( ASSERT(xfs_btree_ptr_is_null(cur, &ptr)); #endif - index = numrecs - cur->bc_ops->get_maxrecs(cur, level); - if (index) { - xfs_iroot_realloc(cur->bc_ino.ip, index, - cur->bc_ino.whichfork); - block = ifp->if_broot; - } - - be16_add_cpu(&block->bb_numrecs, index); - ASSERT(block->bb_numrecs == cblock->bb_numrecs); - - kp = xfs_btree_key_addr(cur, 1, block); - ckp = xfs_btree_key_addr(cur, 1, cblock); - xfs_btree_copy_keys(cur, kp, ckp, numrecs); - - pp = xfs_btree_ptr_addr(cur, 1, block); - cpp = xfs_btree_ptr_addr(cur, 1, cblock); - - for (i = 0; i < numrecs; i++) { - error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1); + if (level > 1) { + error = xfs_btree_demote_node_child(cur, cblock, level, + numrecs); if (error) return error; - } - - xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); + } else + xfs_btree_demote_leaf_child(cur, cblock, numrecs); error = xfs_btree_free_block(cur, cbp); if (error) return error; - cur->bc_levels[level - 1].bp = NULL; - be16_add_cpu(&block->bb_level, -1); xfs_trans_log_inode(cur->bc_tp, ip, XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork)); - cur->bc_nlevels--; out0: return 0; } @@ -3667,7 +3992,7 @@ xfs_btree_kill_root( * Update the root pointer, decreasing the level by 1 and then * free the old root. */ - cur->bc_ops->set_root(cur, newroot, -1); + xfs_btree_set_root(cur, newroot, -1); error = xfs_btree_free_block(cur, bp); if (error) @@ -3796,40 +4121,29 @@ xfs_btree_delrec( xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS); /* - * If we are tracking the last record in the tree and - * we are at the far right edge of the tree, update it. - */ - if (xfs_btree_is_lastrec(cur, block, level)) { - cur->bc_ops->update_lastrec(cur, block, NULL, - ptr, LASTREC_DELREC); - } - - /* * We're at the root level. First, shrink the root block in-memory. * Try to get rid of the next level down. If we can't then there's - * nothing left to do. + * nothing left to do. numrecs was decremented above. */ - if (level == cur->bc_nlevels - 1) { - if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) { - xfs_iroot_realloc(cur->bc_ino.ip, -1, - cur->bc_ino.whichfork); + if (xfs_btree_at_iroot(cur, level)) { + cur->bc_ops->broot_realloc(cur, numrecs); - error = xfs_btree_kill_iroot(cur); - if (error) - goto error0; + error = xfs_btree_kill_iroot(cur); + if (error) + goto error0; - error = xfs_btree_dec_cursor(cur, level, stat); - if (error) - goto error0; - *stat = 1; - return 0; - } + error = xfs_btree_dec_cursor(cur, level, stat); + if (error) + goto error0; + *stat = 1; + return 0; + } - /* - * If this is the root level, and there's only one entry left, - * and it's NOT the leaf level, then we can get rid of this - * level. - */ + /* + * If this is the root level, and there's only one entry left, and it's + * NOT the leaf level, then we can get rid of this level. + */ + if (level == cur->bc_nlevels - 1) { if (numrecs == 1 && level > 0) { union xfs_btree_ptr *pp; /* @@ -3878,7 +4192,7 @@ xfs_btree_delrec( xfs_btree_get_sibling(cur, block, &rptr, XFS_BB_RIGHTSIB); xfs_btree_get_sibling(cur, block, &lptr, XFS_BB_LEFTSIB); - if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) { + if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { /* * One child of root, need to get a chance to copy its contents * into the root and delete it. Can't go up to next level, @@ -3918,6 +4232,7 @@ xfs_btree_delrec( */ i = xfs_btree_lastrec(tcur, level); if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -3926,12 +4241,14 @@ xfs_btree_delrec( if (error) goto error0; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } i = xfs_btree_lastrec(tcur, level); if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -3979,6 +4296,7 @@ xfs_btree_delrec( if (!xfs_btree_ptr_is_null(cur, &lptr)) { i = xfs_btree_firstrec(tcur, level); if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -3987,6 +4305,7 @@ xfs_btree_delrec( if (error) goto error0; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -4004,6 +4323,7 @@ xfs_btree_delrec( */ i = xfs_btree_firstrec(tcur, level); if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -4013,6 +4333,7 @@ xfs_btree_delrec( goto error0; i = xfs_btree_firstrec(tcur, level); if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -4188,8 +4509,8 @@ xfs_btree_delrec( * If we joined with the right neighbor and there's a level above * us, increment the cursor at that level. */ - else if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) || - (level + 1 < cur->bc_nlevels)) { + else if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE || + level + 1 < cur->bc_nlevels) { error = xfs_btree_increment(cur, level + 1, &i); if (error) goto error0; @@ -4257,7 +4578,7 @@ xfs_btree_delete( * If we combined blocks as part of deleting the record, delrec won't * have updated the parent high keys so we have to do that here. */ - if (joined && (cur->bc_flags & XFS_BTREE_OVERLAPPING)) { + if (joined && (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING)) { error = xfs_btree_updkeys_force(cur, 0); if (error) goto error0; @@ -4331,7 +4652,7 @@ xfs_btree_visit_block( { struct xfs_btree_block *block; struct xfs_buf *bp; - union xfs_btree_ptr rptr; + union xfs_btree_ptr rptr, bufptr; int error; /* do right sibling readahead */ @@ -4354,15 +4675,12 @@ xfs_btree_visit_block( * return the same block without checking if the right sibling points * back to us and creates a cyclic reference in the btree. */ - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { - if (be64_to_cpu(rptr.l) == XFS_DADDR_TO_FSB(cur->bc_mp, - xfs_buf_daddr(bp))) - return -EFSCORRUPTED; - } else { - if (be32_to_cpu(rptr.s) == xfs_daddr_to_agbno(cur->bc_mp, - xfs_buf_daddr(bp))) - return -EFSCORRUPTED; + xfs_btree_buf_to_ptr(cur, bp, &bufptr); + if (xfs_btree_ptrs_equal(cur, &rptr, &bufptr)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; } + return xfs_btree_lookup_get_block(cur, level, &rptr, &block); } @@ -4380,7 +4698,7 @@ xfs_btree_visit_blocks( struct xfs_btree_block *block = NULL; int error = 0; - cur->bc_ops->init_ptr_from_cur(cur, &lptr); + xfs_btree_init_ptr_from_cur(cur, &lptr); /* for each level */ for (level = cur->bc_nlevels - 1; level >= 0; level--) { @@ -4458,7 +4776,7 @@ xfs_btree_block_change_owner( /* modify the owner */ block = xfs_btree_get_block(cur, level, &bp); - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { if (block->bb_u.l.bb_owner == cpu_to_be64(bbcoi->new_owner)) return 0; block->bb_u.l.bb_owner = cpu_to_be64(bbcoi->new_owner); @@ -4476,7 +4794,7 @@ xfs_btree_block_change_owner( * though, so everything is consistent in memory. */ if (!bp) { - ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); ASSERT(level == cur->bc_nlevels - 1); return 0; } @@ -4510,7 +4828,7 @@ xfs_btree_change_owner( /* Verify the v5 fields of a long-format btree block. */ xfs_failaddr_t -xfs_btree_lblock_v5hdr_verify( +xfs_btree_fsblock_v5hdr_verify( struct xfs_buf *bp, uint64_t owner) { @@ -4531,7 +4849,7 @@ xfs_btree_lblock_v5hdr_verify( /* Verify a long-format btree block. */ xfs_failaddr_t -xfs_btree_lblock_verify( +xfs_btree_fsblock_verify( struct xfs_buf *bp, unsigned int max_recs) { @@ -4540,28 +4858,60 @@ xfs_btree_lblock_verify( xfs_fsblock_t fsb; xfs_failaddr_t fa; + ASSERT(!xfs_buftarg_is_mem(bp->b_target)); + /* numrecs verification */ if (be16_to_cpu(block->bb_numrecs) > max_recs) return __this_address; /* sibling pointer verification */ fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); - fa = xfs_btree_check_lblock_siblings(mp, NULL, -1, fsb, + fa = xfs_btree_check_fsblock_siblings(mp, fsb, block->bb_u.l.bb_leftsib); if (!fa) - fa = xfs_btree_check_lblock_siblings(mp, NULL, -1, fsb, + fa = xfs_btree_check_fsblock_siblings(mp, fsb, block->bb_u.l.bb_rightsib); return fa; } +/* Verify an in-memory btree block. */ +xfs_failaddr_t +xfs_btree_memblock_verify( + struct xfs_buf *bp, + unsigned int max_recs) +{ + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + struct xfs_buftarg *btp = bp->b_target; + xfs_failaddr_t fa; + xfbno_t bno; + + ASSERT(xfs_buftarg_is_mem(bp->b_target)); + + /* numrecs verification */ + if (be16_to_cpu(block->bb_numrecs) > max_recs) + return __this_address; + + /* sibling pointer verification */ + bno = xfs_daddr_to_xfbno(xfs_buf_daddr(bp)); + fa = xfs_btree_check_memblock_siblings(btp, bno, + block->bb_u.l.bb_leftsib); + if (fa) + return fa; + fa = xfs_btree_check_memblock_siblings(btp, bno, + block->bb_u.l.bb_rightsib); + if (fa) + return fa; + + return NULL; +} /** - * xfs_btree_sblock_v5hdr_verify() -- verify the v5 fields of a short-format + * xfs_btree_agblock_v5hdr_verify() -- verify the v5 fields of a short-format * btree block * * @bp: buffer containing the btree block */ xfs_failaddr_t -xfs_btree_sblock_v5hdr_verify( +xfs_btree_agblock_v5hdr_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; @@ -4574,19 +4924,19 @@ xfs_btree_sblock_v5hdr_verify( return __this_address; if (block->bb_u.s.bb_blkno != cpu_to_be64(xfs_buf_daddr(bp))) return __this_address; - if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno) + if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag_agno(pag)) return __this_address; return NULL; } /** - * xfs_btree_sblock_verify() -- verify a short-format btree block + * xfs_btree_agblock_verify() -- verify a short-format btree block * * @bp: buffer containing the btree block * @max_recs: maximum records allowed in this btree node */ xfs_failaddr_t -xfs_btree_sblock_verify( +xfs_btree_agblock_verify( struct xfs_buf *bp, unsigned int max_recs) { @@ -4595,16 +4945,18 @@ xfs_btree_sblock_verify( xfs_agblock_t agbno; xfs_failaddr_t fa; + ASSERT(!xfs_buftarg_is_mem(bp->b_target)); + /* numrecs verification */ if (be16_to_cpu(block->bb_numrecs) > max_recs) return __this_address; /* sibling pointer verification */ agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp)); - fa = xfs_btree_check_sblock_siblings(bp->b_pag, NULL, -1, agbno, + fa = xfs_btree_check_agblock_siblings(bp->b_pag, agbno, block->bb_u.s.bb_leftsib); if (!fa) - fa = xfs_btree_check_sblock_siblings(bp->b_pag, NULL, -1, agbno, + fa = xfs_btree_check_agblock_siblings(bp->b_pag, agbno, block->bb_u.s.bb_rightsib); return fa; } @@ -4702,13 +5054,12 @@ xfs_btree_simple_query_range( { union xfs_btree_rec *recp; union xfs_btree_key rec_key; - int64_t diff; int stat; bool firstrec = true; int error; ASSERT(cur->bc_ops->init_high_key_from_rec); - ASSERT(cur->bc_ops->diff_two_keys); + ASSERT(cur->bc_ops->cmp_two_keys); /* * Find the leftmost record. The btree cursor must be set @@ -4732,20 +5083,17 @@ xfs_btree_simple_query_range( if (error || !stat) break; - /* Skip if high_key(rec) < low_key. */ + /* Skip if low_key > high_key(rec). */ if (firstrec) { cur->bc_ops->init_high_key_from_rec(&rec_key, recp); firstrec = false; - diff = cur->bc_ops->diff_two_keys(cur, low_key, - &rec_key); - if (diff > 0) + if (xfs_btree_keycmp_gt(cur, low_key, &rec_key)) goto advloop; } - /* Stop if high_key < low_key(rec). */ + /* Stop if low_key(rec) > high_key. */ cur->bc_ops->init_key_from_rec(&rec_key, recp); - diff = cur->bc_ops->diff_two_keys(cur, &rec_key, high_key); - if (diff > 0) + if (xfs_btree_keycmp_gt(cur, &rec_key, high_key)) break; /* Callback */ @@ -4799,8 +5147,6 @@ xfs_btree_overlapped_query_range( union xfs_btree_key *hkp; union xfs_btree_rec *recp; struct xfs_btree_block *block; - int64_t ldiff; - int64_t hdiff; int level; struct xfs_buf *bp; int i; @@ -4808,7 +5154,7 @@ xfs_btree_overlapped_query_range( /* Load the root of the btree. */ level = cur->bc_nlevels - 1; - cur->bc_ops->init_ptr_from_cur(cur, &ptr); + xfs_btree_init_ptr_from_cur(cur, &ptr); error = xfs_btree_lookup_get_block(cur, level, &ptr, &block); if (error) return error; @@ -4840,25 +5186,23 @@ pop_up: block); cur->bc_ops->init_high_key_from_rec(&rec_hkey, recp); - ldiff = cur->bc_ops->diff_two_keys(cur, &rec_hkey, - low_key); - cur->bc_ops->init_key_from_rec(&rec_key, recp); - hdiff = cur->bc_ops->diff_two_keys(cur, high_key, - &rec_key); /* + * If (query's high key < record's low key), then there + * are no more interesting records in this block. Pop + * up to the leaf level to find more record blocks. + * * If (record's high key >= query's low key) and * (query's high key >= record's low key), then * this record overlaps the query range; callback. */ - if (ldiff >= 0 && hdiff >= 0) { + if (xfs_btree_keycmp_lt(cur, high_key, &rec_key)) + goto pop_up; + if (xfs_btree_keycmp_ge(cur, &rec_hkey, low_key)) { error = fn(cur, recp, priv); if (error) break; - } else if (hdiff < 0) { - /* Record is larger than high key; pop. */ - goto pop_up; } cur->bc_levels[level].ptr++; continue; @@ -4870,15 +5214,18 @@ pop_up: block); pp = xfs_btree_ptr_addr(cur, cur->bc_levels[level].ptr, block); - ldiff = cur->bc_ops->diff_two_keys(cur, hkp, low_key); - hdiff = cur->bc_ops->diff_two_keys(cur, high_key, lkp); - /* + * If (query's high key < pointer's low key), then there are no + * more interesting keys in this block. Pop up one leaf level + * to continue looking for records. + * * If (pointer's high key >= query's low key) and * (query's high key >= pointer's low key), then * this record overlaps the query range; follow pointer. */ - if (ldiff >= 0 && hdiff >= 0) { + if (xfs_btree_keycmp_lt(cur, high_key, lkp)) + goto pop_up; + if (xfs_btree_keycmp_ge(cur, hkp, low_key)) { level--; error = xfs_btree_lookup_get_block(cur, level, pp, &block); @@ -4893,9 +5240,6 @@ pop_up: #endif cur->bc_levels[level].ptr = 1; continue; - } else if (hdiff < 0) { - /* The low key is larger than the upper range; pop. */ - goto pop_up; } cur->bc_levels[level].ptr++; } @@ -4923,6 +5267,19 @@ out: return error; } +static inline void +xfs_btree_key_from_irec( + struct xfs_btree_cur *cur, + union xfs_btree_key *key, + const union xfs_btree_irec *irec) +{ + union xfs_btree_rec rec; + + cur->bc_rec = *irec; + cur->bc_ops->init_rec_from_cur(cur, &rec); + cur->bc_ops->init_key_from_rec(key, &rec); +} + /* * Query a btree for all records overlapping a given interval of keys. The * supplied function will be called with each record found; return one of the @@ -4937,24 +5294,18 @@ xfs_btree_query_range( xfs_btree_query_range_fn fn, void *priv) { - union xfs_btree_rec rec; union xfs_btree_key low_key; union xfs_btree_key high_key; /* Find the keys of both ends of the interval. */ - cur->bc_rec = *high_rec; - cur->bc_ops->init_rec_from_cur(cur, &rec); - cur->bc_ops->init_key_from_rec(&high_key, &rec); + xfs_btree_key_from_irec(cur, &high_key, high_rec); + xfs_btree_key_from_irec(cur, &low_key, low_rec); - cur->bc_rec = *low_rec; - cur->bc_ops->init_rec_from_cur(cur, &rec); - cur->bc_ops->init_key_from_rec(&low_key, &rec); - - /* Enforce low key < high key. */ - if (cur->bc_ops->diff_two_keys(cur, &low_key, &high_key) > 0) + /* Enforce low key <= high key. */ + if (!xfs_btree_keycmp_le(cur, &low_key, &high_key)) return -EINVAL; - if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING)) + if (!(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING)) return xfs_btree_simple_query_range(cur, &low_key, &high_key, fn, priv); return xfs_btree_overlapped_query_range(cur, &low_key, &high_key, @@ -4984,7 +5335,7 @@ xfs_btree_count_blocks_helper( int level, void *data) { - xfs_extlen_t *blocks = data; + xfs_filblks_t *blocks = data; (*blocks)++; return 0; @@ -4994,7 +5345,7 @@ xfs_btree_count_blocks_helper( int xfs_btree_count_blocks( struct xfs_btree_cur *cur, - xfs_extlen_t *blocks) + xfs_filblks_t *blocks) { *blocks = 0; return xfs_btree_visit_blocks(cur, xfs_btree_count_blocks_helper, @@ -5002,45 +5353,143 @@ xfs_btree_count_blocks( } /* Compare two btree pointers. */ -int64_t -xfs_btree_diff_two_ptrs( +int +xfs_btree_cmp_two_ptrs( struct xfs_btree_cur *cur, const union xfs_btree_ptr *a, const union xfs_btree_ptr *b) { - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) - return (int64_t)be64_to_cpu(a->l) - be64_to_cpu(b->l); - return (int64_t)be32_to_cpu(a->s) - be32_to_cpu(b->s); + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) + return cmp_int(be64_to_cpu(a->l), be64_to_cpu(b->l)); + return cmp_int(be32_to_cpu(a->s), be32_to_cpu(b->s)); } -/* If there's an extent, we're done. */ +struct xfs_btree_has_records { + /* Keys for the start and end of the range we want to know about. */ + union xfs_btree_key start_key; + union xfs_btree_key end_key; + + /* Mask for key comparisons, if desired. */ + const union xfs_btree_key *key_mask; + + /* Highest record key we've seen so far. */ + union xfs_btree_key high_key; + + enum xbtree_recpacking outcome; +}; + STATIC int -xfs_btree_has_record_helper( +xfs_btree_has_records_helper( struct xfs_btree_cur *cur, const union xfs_btree_rec *rec, void *priv) { - return -ECANCELED; + union xfs_btree_key rec_key; + union xfs_btree_key rec_high_key; + struct xfs_btree_has_records *info = priv; + enum xbtree_key_contig key_contig; + + cur->bc_ops->init_key_from_rec(&rec_key, rec); + + if (info->outcome == XBTREE_RECPACKING_EMPTY) { + info->outcome = XBTREE_RECPACKING_SPARSE; + + /* + * If the first record we find does not overlap the start key, + * then there is a hole at the start of the search range. + * Classify this as sparse and stop immediately. + */ + if (xfs_btree_masked_keycmp_lt(cur, &info->start_key, &rec_key, + info->key_mask)) + return -ECANCELED; + } else { + /* + * If a subsequent record does not overlap with the any record + * we've seen so far, there is a hole in the middle of the + * search range. Classify this as sparse and stop. + * If the keys overlap and this btree does not allow overlap, + * signal corruption. + */ + key_contig = cur->bc_ops->keys_contiguous(cur, &info->high_key, + &rec_key, info->key_mask); + if (key_contig == XBTREE_KEY_OVERLAP && + !(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING)) + return -EFSCORRUPTED; + if (key_contig == XBTREE_KEY_GAP) + return -ECANCELED; + } + + /* + * If high_key(rec) is larger than any other high key we've seen, + * remember it for later. + */ + cur->bc_ops->init_high_key_from_rec(&rec_high_key, rec); + if (xfs_btree_masked_keycmp_gt(cur, &rec_high_key, &info->high_key, + info->key_mask)) + info->high_key = rec_high_key; /* struct copy */ + + return 0; } -/* Is there a record covering a given range of keys? */ +/* + * Scan part of the keyspace of a btree and tell us if that keyspace does not + * map to any records; is fully mapped to records; or is partially mapped to + * records. This is the btree record equivalent to determining if a file is + * sparse. + * + * For most btree types, the record scan should use all available btree key + * fields to compare the keys encountered. These callers should pass NULL for + * @mask. However, some callers (e.g. scanning physical space in the rmapbt) + * want to ignore some part of the btree record keyspace when performing the + * comparison. These callers should pass in a union xfs_btree_key object with + * the fields that *should* be a part of the comparison set to any nonzero + * value, and the rest zeroed. + */ int -xfs_btree_has_record( +xfs_btree_has_records( struct xfs_btree_cur *cur, const union xfs_btree_irec *low, const union xfs_btree_irec *high, - bool *exists) + const union xfs_btree_key *mask, + enum xbtree_recpacking *outcome) { + struct xfs_btree_has_records info = { + .outcome = XBTREE_RECPACKING_EMPTY, + .key_mask = mask, + }; int error; - error = xfs_btree_query_range(cur, low, high, - &xfs_btree_has_record_helper, NULL); - if (error == -ECANCELED) { - *exists = true; - return 0; + /* Not all btrees support this operation. */ + if (!cur->bc_ops->keys_contiguous) { + ASSERT(0); + return -EOPNOTSUPP; } - *exists = false; - return error; + + xfs_btree_key_from_irec(cur, &info.start_key, low); + xfs_btree_key_from_irec(cur, &info.end_key, high); + + error = xfs_btree_query_range(cur, low, high, + xfs_btree_has_records_helper, &info); + if (error == -ECANCELED) + goto out; + if (error) + return error; + + if (info.outcome == XBTREE_RECPACKING_EMPTY) + goto out; + + /* + * If the largest high_key(rec) we saw during the walk is greater than + * the end of the search range, classify this as full. Otherwise, + * there is a hole at the end of the search range. + */ + if (xfs_btree_masked_keycmp_ge(cur, &info.high_key, &info.end_key, + mask)) + info.outcome = XBTREE_RECPACKING_FULL; + +out: + *outcome = info.outcome; + return 0; } /* Are there more records in this btree? */ @@ -5058,7 +5507,7 @@ xfs_btree_has_more_records( return true; /* There are more record blocks. */ - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) return block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK); else return block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK); @@ -5085,6 +5534,12 @@ xfs_btree_init_cur_caches(void) error = xfs_refcountbt_init_cur_cache(); if (error) goto err; + error = xfs_rtrmapbt_init_cur_cache(); + if (error) + goto err; + error = xfs_rtrefcountbt_init_cur_cache(); + if (error) + goto err; return 0; err: @@ -5101,4 +5556,97 @@ xfs_btree_destroy_cur_caches(void) xfs_bmbt_destroy_cur_cache(); xfs_rmapbt_destroy_cur_cache(); xfs_refcountbt_destroy_cur_cache(); + xfs_rtrmapbt_destroy_cur_cache(); + xfs_rtrefcountbt_destroy_cur_cache(); +} + +/* Move the btree cursor before the first record. */ +int +xfs_btree_goto_left_edge( + struct xfs_btree_cur *cur) +{ + int stat = 0; + int error; + + memset(&cur->bc_rec, 0, sizeof(cur->bc_rec)); + error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, &stat); + if (error) + return error; + if (!stat) + return 0; + + error = xfs_btree_decrement(cur, 0, &stat); + if (error) + return error; + if (stat != 0) { + ASSERT(0); + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + + return 0; +} + +/* Allocate a block for an inode-rooted metadata btree. */ +int +xfs_btree_alloc_metafile_block( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, + union xfs_btree_ptr *new, + int *stat) +{ + struct xfs_alloc_arg args = { + .mp = cur->bc_mp, + .tp = cur->bc_tp, + .resv = XFS_AG_RESV_METAFILE, + .minlen = 1, + .maxlen = 1, + .prod = 1, + }; + struct xfs_inode *ip = cur->bc_ino.ip; + int error; + + ASSERT(xfs_is_metadir_inode(ip)); + + xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, cur->bc_ino.whichfork); + error = xfs_alloc_vextent_start_ag(&args, + XFS_INO_TO_FSB(cur->bc_mp, ip->i_ino)); + if (error) + return error; + if (args.fsbno == NULLFSBLOCK) { + *stat = 0; + return 0; + } + ASSERT(args.len == 1); + + xfs_metafile_resv_alloc_space(ip, &args); + + new->l = cpu_to_be64(args.fsbno); + *stat = 1; + return 0; +} + +/* Free a block from an inode-rooted metadata btree. */ +int +xfs_btree_free_metafile_block( + struct xfs_btree_cur *cur, + struct xfs_buf *bp) +{ + struct xfs_owner_info oinfo; + struct xfs_mount *mp = cur->bc_mp; + struct xfs_inode *ip = cur->bc_ino.ip; + struct xfs_trans *tp = cur->bc_tp; + xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); + int error; + + ASSERT(xfs_is_metadir_inode(ip)); + + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); + error = xfs_free_extent_later(tp, fsbno, 1, &oinfo, XFS_AG_RESV_METAFILE, + 0); + if (error) + return error; + + xfs_metafile_resv_free_space(ip, tp, 1); + return 0; } diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 29c4b4ccb909..60e78572e725 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -55,15 +55,8 @@ union xfs_btree_rec { #define XFS_LOOKUP_LE ((xfs_lookup_t)XFS_LOOKUP_LEi) #define XFS_LOOKUP_GE ((xfs_lookup_t)XFS_LOOKUP_GEi) -#define XFS_BTNUM_BNO ((xfs_btnum_t)XFS_BTNUM_BNOi) -#define XFS_BTNUM_CNT ((xfs_btnum_t)XFS_BTNUM_CNTi) -#define XFS_BTNUM_BMAP ((xfs_btnum_t)XFS_BTNUM_BMAPi) -#define XFS_BTNUM_INO ((xfs_btnum_t)XFS_BTNUM_INOi) -#define XFS_BTNUM_FINO ((xfs_btnum_t)XFS_BTNUM_FINOi) -#define XFS_BTNUM_RMAP ((xfs_btnum_t)XFS_BTNUM_RMAPi) -#define XFS_BTNUM_REFC ((xfs_btnum_t)XFS_BTNUM_REFCi) - -uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum); +struct xfs_btree_ops; +uint32_t xfs_btree_magic(struct xfs_mount *mp, const struct xfs_btree_ops *ops); /* * For logging record fields. @@ -86,14 +79,64 @@ uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum); * Generic stats interface */ #define XFS_BTREE_STATS_INC(cur, stat) \ - XFS_STATS_INC_OFF((cur)->bc_mp, (cur)->bc_statoff + __XBTS_ ## stat) + XFS_STATS_INC_OFF((cur)->bc_mp, \ + (cur)->bc_ops->statoff + __XBTS_ ## stat) #define XFS_BTREE_STATS_ADD(cur, stat, val) \ - XFS_STATS_ADD_OFF((cur)->bc_mp, (cur)->bc_statoff + __XBTS_ ## stat, val) + XFS_STATS_ADD_OFF((cur)->bc_mp, \ + (cur)->bc_ops->statoff + __XBTS_ ## stat, val) + +enum xbtree_key_contig { + XBTREE_KEY_GAP = 0, + XBTREE_KEY_CONTIGUOUS, + XBTREE_KEY_OVERLAP, +}; + +/* + * Decide if these two numeric btree key fields are contiguous, overlapping, + * or if there's a gap between them. @x should be the field from the high + * key and @y should be the field from the low key. + */ +static inline enum xbtree_key_contig xbtree_key_contig(uint64_t x, uint64_t y) +{ + x++; + if (x < y) + return XBTREE_KEY_GAP; + if (x == y) + return XBTREE_KEY_CONTIGUOUS; + return XBTREE_KEY_OVERLAP; +} + +#define XFS_BTREE_LONG_PTR_LEN (sizeof(__be64)) +#define XFS_BTREE_SHORT_PTR_LEN (sizeof(__be32)) + +enum xfs_btree_type { + XFS_BTREE_TYPE_AG, + XFS_BTREE_TYPE_INODE, + XFS_BTREE_TYPE_MEM, +}; struct xfs_btree_ops { - /* size of the key and record structures */ - size_t key_len; - size_t rec_len; + const char *name; + + /* Type of btree - AG-rooted or inode-rooted */ + enum xfs_btree_type type; + + /* XFS_BTGEO_* flags that determine the geometry of the btree */ + unsigned int geom_flags; + + /* size of the key, pointer, and record structures */ + size_t key_len; + size_t ptr_len; + size_t rec_len; + + /* LRU refcount to set on each btree buffer created */ + unsigned int lru_refs; + + /* offset of btree stats array */ + unsigned int statoff; + + /* sick mask for health reporting (not for bmap btrees) */ + unsigned int sick_mask; /* cursor operations */ struct xfs_btree_cur *(*dup_cursor)(struct xfs_btree_cur *); @@ -111,12 +154,6 @@ struct xfs_btree_ops { int *stat); int (*free_block)(struct xfs_btree_cur *cur, struct xfs_buf *bp); - /* update last record information */ - void (*update_lastrec)(struct xfs_btree_cur *cur, - const struct xfs_btree_block *block, - const union xfs_btree_rec *rec, - int ptr, int reason); - /* records in block/level */ int (*get_minrecs)(struct xfs_btree_cur *cur, int level); int (*get_maxrecs)(struct xfs_btree_cur *cur, int level); @@ -134,17 +171,23 @@ struct xfs_btree_ops { void (*init_high_key_from_rec)(union xfs_btree_key *key, const union xfs_btree_rec *rec); - /* difference between key value and cursor value */ - int64_t (*key_diff)(struct xfs_btree_cur *cur, - const union xfs_btree_key *key); + /* + * Compare key value and cursor value -- positive if key > cur, + * negative if key < cur, and zero if equal. + */ + int (*cmp_key_with_cur)(struct xfs_btree_cur *cur, + const union xfs_btree_key *key); /* - * Difference between key2 and key1 -- positive if key1 > key2, - * negative if key1 < key2, and zero if equal. + * Compare key1 and key2 -- positive if key1 > key2, negative if + * key1 < key2, and zero if equal. If the @mask parameter is non NULL, + * each key field to be used in the comparison must contain a nonzero + * value. */ - int64_t (*diff_two_keys)(struct xfs_btree_cur *cur, - const union xfs_btree_key *key1, - const union xfs_btree_key *key2); + int (*cmp_two_keys)(struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask); const struct xfs_buf_ops *buf_ops; @@ -157,15 +200,43 @@ struct xfs_btree_ops { int (*recs_inorder)(struct xfs_btree_cur *cur, const union xfs_btree_rec *r1, const union xfs_btree_rec *r2); -}; -/* - * Reasons for the update_lastrec method to be called. - */ -#define LASTREC_UPDATE 0 -#define LASTREC_INSREC 1 -#define LASTREC_DELREC 2 + /* + * Are these two btree keys immediately adjacent? + * + * Given two btree keys @key1 and @key2, decide if it is impossible for + * there to be a third btree key K satisfying the relationship + * @key1 < K < @key2. To determine if two btree records are + * immediately adjacent, @key1 should be the high key of the first + * record and @key2 should be the low key of the second record. + * If the @mask parameter is non NULL, each key field to be used in the + * comparison must contain a nonzero value. + */ + enum xbtree_key_contig (*keys_contiguous)(struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask); + + /* + * Reallocate the space for if_broot to fit the number of records. + * Move the records and pointers in if_broot to fit the new size. When + * shrinking this will eliminate holes between the records and pointers + * created by the caller. When growing this will create holes to be + * filled in by the caller. + * + * The caller must not request to add more records than would fit in + * the on-disk inode root. If the if_broot is currently NULL, then if + * we are adding records, one will be allocated. The caller must also + * not request that the number of records go below zero, although it + * can go to zero. + */ + struct xfs_btree_block *(*broot_realloc)(struct xfs_btree_cur *cur, + unsigned int new_numrecs); +}; +/* btree geometry flags */ +#define XFS_BTGEO_OVERLAPPING (1U << 0) /* overlapping intervals */ +#define XFS_BTGEO_IROOT_RECORDS (1U << 1) /* iroot can store records */ union xfs_btree_irec { struct xfs_alloc_rec_incore a; @@ -175,39 +246,6 @@ union xfs_btree_irec { struct xfs_refcount_irec rc; }; -/* Per-AG btree information. */ -struct xfs_btree_cur_ag { - struct xfs_perag *pag; - union { - struct xfs_buf *agbp; - struct xbtree_afakeroot *afake; /* for staging cursor */ - }; - union { - struct { - unsigned int nr_ops; /* # record updates */ - unsigned int shape_changes; /* # of extent splits */ - } refc; - struct { - bool active; /* allocation cursor state */ - } abt; - }; -}; - -/* Btree-in-inode cursor information */ -struct xfs_btree_cur_ino { - struct xfs_inode *ip; - struct xbtree_ifakeroot *ifake; /* for staging cursor */ - int allocated; - short forksize; - char whichfork; - char flags; -/* We are converting a delalloc reservation */ -#define XFS_BTCUR_BMBT_WASDEL (1 << 0) - -/* For extent swap, ignore owner check in verifier */ -#define XFS_BTCUR_BMBT_INVALID_OWNER (1 << 1) -}; - struct xfs_btree_level { /* buffer pointer */ struct xfs_buf *bp; @@ -232,21 +270,37 @@ struct xfs_btree_cur const struct xfs_btree_ops *bc_ops; struct kmem_cache *bc_cache; /* cursor cache */ unsigned int bc_flags; /* btree features - below */ - xfs_btnum_t bc_btnum; /* identifies which btree type */ union xfs_btree_irec bc_rec; /* current insert/search record value */ uint8_t bc_nlevels; /* number of levels in the tree */ uint8_t bc_maxlevels; /* maximum levels for this btree type */ - int bc_statoff; /* offset of btree stats array */ + struct xfs_group *bc_group; - /* - * Short btree pointers need an agno to be able to turn the pointers - * into physical addresses for IO, so the btree cursor switches between - * bc_ino and bc_ag based on whether XFS_BTREE_LONG_PTRS is set for the - * cursor. - */ + /* per-type information */ union { - struct xfs_btree_cur_ag bc_ag; - struct xfs_btree_cur_ino bc_ino; + struct { + struct xfs_inode *ip; + short forksize; + char whichfork; + struct xbtree_ifakeroot *ifake; /* for staging cursor */ + } bc_ino; + struct { + struct xfs_buf *agbp; + struct xbtree_afakeroot *afake; /* for staging cursor */ + } bc_ag; + struct { + struct xfbtree *xfbtree; + } bc_mem; + }; + + /* per-format private data */ + union { + struct { + int allocated; + } bc_bmap; /* bmapbt */ + struct { + unsigned int nr_ops; /* # record updates */ + unsigned int shape_changes; /* # of extent splits */ + } bc_refc; /* refcountbt/rtrefcountbt */ }; /* Must be at the end of the struct! */ @@ -261,21 +315,25 @@ struct xfs_btree_cur static inline size_t xfs_btree_cur_sizeof(unsigned int nlevels) { - return struct_size((struct xfs_btree_cur *)NULL, bc_levels, nlevels); + return struct_size_t(struct xfs_btree_cur, bc_levels, nlevels); } -/* cursor flags */ -#define XFS_BTREE_LONG_PTRS (1<<0) /* pointers are 64bits long */ -#define XFS_BTREE_ROOT_IN_INODE (1<<1) /* root may be variable size */ -#define XFS_BTREE_LASTREC_UPDATE (1<<2) /* track last rec externally */ -#define XFS_BTREE_CRC_BLOCKS (1<<3) /* uses extended btree blocks */ -#define XFS_BTREE_OVERLAPPING (1<<4) /* overlapping intervals */ +/* cursor state flags */ /* * The root of this btree is a fakeroot structure so that we can stage a btree * rebuild without leaving it accessible via primary metadata. The ops struct * is dynamically allocated and must be freed when the cursor is deleted. */ -#define XFS_BTREE_STAGING (1<<5) +#define XFS_BTREE_STAGING (1U << 0) + +/* We are converting a delalloc reservation (only for bmbt btrees) */ +#define XFS_BTREE_BMBT_WASDEL (1U << 1) + +/* For extent swap, ignore owner check in verifier (only for bmbt btrees) */ +#define XFS_BTREE_BMBT_INVALID_OWNER (1U << 2) + +/* Cursor is active (only for allocbt btrees) */ +#define XFS_BTREE_ALLOCBT_ACTIVE (1U << 3) #define XFS_BTREE_NOERROR 0 #define XFS_BTREE_ERROR 1 @@ -285,14 +343,10 @@ xfs_btree_cur_sizeof(unsigned int nlevels) */ #define XFS_BUF_TO_BLOCK(bp) ((struct xfs_btree_block *)((bp)->b_addr)) -/* - * Internal long and short btree block checks. They return NULL if the - * block is ok or the address of the failed check otherwise. - */ -xfs_failaddr_t __xfs_btree_check_lblock(struct xfs_btree_cur *cur, - struct xfs_btree_block *block, int level, struct xfs_buf *bp); -xfs_failaddr_t __xfs_btree_check_sblock(struct xfs_btree_cur *cur, +xfs_failaddr_t __xfs_btree_check_block(struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *bp); +int __xfs_btree_check_ptr(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *ptr, int index, int level); /* * Check that block header is ok. @@ -305,24 +359,6 @@ xfs_btree_check_block( struct xfs_buf *bp); /* buffer containing block, if any */ /* - * Check that (long) pointer is ok. - */ -bool /* error (0 or EFSCORRUPTED) */ -xfs_btree_check_lptr( - struct xfs_btree_cur *cur, /* btree cursor */ - xfs_fsblock_t fsbno, /* btree block disk address */ - int level); /* btree block level */ - -/* - * Check that (short) pointer is ok. - */ -bool /* error (0 or EFSCORRUPTED) */ -xfs_btree_check_sptr( - struct xfs_btree_cur *cur, /* btree cursor */ - xfs_agblock_t agbno, /* btree block disk address */ - int level); /* btree block level */ - -/* * Delete the btree cursor. */ void @@ -352,63 +388,14 @@ xfs_btree_offsets( int *last); /* output: last byte offset */ /* - * Get a buffer for the block, return it read in. - * Long-form addressing. - */ -int /* error */ -xfs_btree_read_bufl( - 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 */ - int refval, /* ref count value for buffer */ - const struct xfs_buf_ops *ops); - -/* - * Read-ahead the block, don't wait for it, don't return a buffer. - * Long-form addressing. - */ -void /* error */ -xfs_btree_reada_bufl( - struct xfs_mount *mp, /* file system mount point */ - xfs_fsblock_t fsbno, /* file system block number */ - xfs_extlen_t count, /* count of filesystem blocks */ - const struct xfs_buf_ops *ops); - -/* - * Read-ahead the block, don't wait for it, don't return a buffer. - * Short-form addressing. - */ -void /* error */ -xfs_btree_reada_bufs( - struct xfs_mount *mp, /* file system mount point */ - xfs_agnumber_t agno, /* allocation group number */ - xfs_agblock_t agbno, /* allocation group block number */ - xfs_extlen_t count, /* count of filesystem blocks */ - const struct xfs_buf_ops *ops); - -/* * Initialise a new btree block header */ -void -xfs_btree_init_block( - struct xfs_mount *mp, - struct xfs_buf *bp, - xfs_btnum_t btnum, - __u16 level, - __u16 numrecs, - __u64 owner); - -void -xfs_btree_init_block_int( - struct xfs_mount *mp, - struct xfs_btree_block *buf, - xfs_daddr_t blkno, - xfs_btnum_t btnum, - __u16 level, - __u16 numrecs, - __u64 owner, - unsigned int flags); +void xfs_btree_init_buf(struct xfs_mount *mp, struct xfs_buf *bp, + const struct xfs_btree_ops *ops, __u16 level, __u16 numrecs, + __u64 owner); +void xfs_btree_init_block(struct xfs_mount *mp, + struct xfs_btree_block *buf, const struct xfs_btree_ops *ops, + __u16 level, __u16 numrecs, __u64 owner); /* * Common btree core entry points. @@ -427,10 +414,10 @@ int xfs_btree_change_owner(struct xfs_btree_cur *cur, uint64_t new_owner, /* * btree block CRC helpers */ -void xfs_btree_lblock_calc_crc(struct xfs_buf *); -bool xfs_btree_lblock_verify_crc(struct xfs_buf *); -void xfs_btree_sblock_calc_crc(struct xfs_buf *); -bool xfs_btree_sblock_verify_crc(struct xfs_buf *); +void xfs_btree_fsblock_calc_crc(struct xfs_buf *); +bool xfs_btree_fsblock_verify_crc(struct xfs_buf *); +void xfs_btree_agblock_calc_crc(struct xfs_buf *); +bool xfs_btree_agblock_verify_crc(struct xfs_buf *); /* * Internal btree helpers also used by xfs_bmap.c. @@ -470,12 +457,14 @@ static inline int xfs_btree_get_level(const struct xfs_btree_block *block) #define XFS_FILBLKS_MIN(a,b) min_t(xfs_filblks_t, (a), (b)) #define XFS_FILBLKS_MAX(a,b) max_t(xfs_filblks_t, (a), (b)) -xfs_failaddr_t xfs_btree_sblock_v5hdr_verify(struct xfs_buf *bp); -xfs_failaddr_t xfs_btree_sblock_verify(struct xfs_buf *bp, +xfs_failaddr_t xfs_btree_agblock_v5hdr_verify(struct xfs_buf *bp); +xfs_failaddr_t xfs_btree_agblock_verify(struct xfs_buf *bp, unsigned int max_recs); -xfs_failaddr_t xfs_btree_lblock_v5hdr_verify(struct xfs_buf *bp, +xfs_failaddr_t xfs_btree_fsblock_v5hdr_verify(struct xfs_buf *bp, uint64_t owner); -xfs_failaddr_t xfs_btree_lblock_verify(struct xfs_buf *bp, +xfs_failaddr_t xfs_btree_fsblock_verify(struct xfs_buf *bp, + unsigned int max_recs); +xfs_failaddr_t xfs_btree_memblock_verify(struct xfs_buf *bp, unsigned int max_recs); unsigned int xfs_btree_compute_maxlevels(const unsigned int *limits, @@ -514,7 +503,7 @@ typedef int (*xfs_btree_visit_blocks_fn)(struct xfs_btree_cur *cur, int level, int xfs_btree_visit_blocks(struct xfs_btree_cur *cur, xfs_btree_visit_blocks_fn fn, unsigned int flags, void *data); -int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_extlen_t *blocks); +int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_filblks_t *blocks); union xfs_btree_rec *xfs_btree_rec_addr(struct xfs_btree_cur *cur, int n, struct xfs_btree_block *block); @@ -530,9 +519,9 @@ struct xfs_btree_block *xfs_btree_get_block(struct xfs_btree_cur *cur, int level, struct xfs_buf **bpp); bool xfs_btree_ptr_is_null(struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr); -int64_t xfs_btree_diff_two_ptrs(struct xfs_btree_cur *cur, - const union xfs_btree_ptr *a, - const union xfs_btree_ptr *b); +int xfs_btree_cmp_two_ptrs(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *a, + const union xfs_btree_ptr *b); void xfs_btree_get_sibling(struct xfs_btree_cur *cur, struct xfs_btree_block *block, union xfs_btree_ptr *ptr, int lr); @@ -540,12 +529,105 @@ void xfs_btree_get_keys(struct xfs_btree_cur *cur, struct xfs_btree_block *block, union xfs_btree_key *key); union xfs_btree_key *xfs_btree_high_key_from_key(struct xfs_btree_cur *cur, union xfs_btree_key *key); -int xfs_btree_has_record(struct xfs_btree_cur *cur, +typedef bool (*xfs_btree_key_gap_fn)(struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2); + +int xfs_btree_has_records(struct xfs_btree_cur *cur, const union xfs_btree_irec *low, - const union xfs_btree_irec *high, bool *exists); + const union xfs_btree_irec *high, + const union xfs_btree_key *mask, + enum xbtree_recpacking *outcome); + bool xfs_btree_has_more_records(struct xfs_btree_cur *cur); struct xfs_ifork *xfs_btree_ifork_ptr(struct xfs_btree_cur *cur); +/* Key comparison helpers */ +static inline bool +xfs_btree_keycmp_lt( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return cur->bc_ops->cmp_two_keys(cur, key1, key2, NULL) < 0; +} + +static inline bool +xfs_btree_keycmp_gt( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return cur->bc_ops->cmp_two_keys(cur, key1, key2, NULL) > 0; +} + +static inline bool +xfs_btree_keycmp_eq( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return cur->bc_ops->cmp_two_keys(cur, key1, key2, NULL) == 0; +} + +static inline bool +xfs_btree_keycmp_le( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return !xfs_btree_keycmp_gt(cur, key1, key2); +} + +static inline bool +xfs_btree_keycmp_ge( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return !xfs_btree_keycmp_lt(cur, key1, key2); +} + +static inline bool +xfs_btree_keycmp_ne( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return !xfs_btree_keycmp_eq(cur, key1, key2); +} + +/* Masked key comparison helpers */ +static inline bool +xfs_btree_masked_keycmp_lt( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + return cur->bc_ops->cmp_two_keys(cur, key1, key2, mask) < 0; +} + +static inline bool +xfs_btree_masked_keycmp_gt( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + return cur->bc_ops->cmp_two_keys(cur, key1, key2, mask) > 0; +} + +static inline bool +xfs_btree_masked_keycmp_ge( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + return !xfs_btree_masked_keycmp_lt(cur, key1, key2, mask); +} + /* Does this cursor point to the last block in the given level? */ static inline bool xfs_btree_islastblock( @@ -557,7 +639,7 @@ xfs_btree_islastblock( block = xfs_btree_get_block(cur, level, &bp); - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) + if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) return block->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK); return block->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK); } @@ -567,6 +649,9 @@ void xfs_btree_set_ptr_null(struct xfs_btree_cur *cur, int xfs_btree_get_buf_block(struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr, struct xfs_btree_block **block, struct xfs_buf **bpp); +int xfs_btree_read_buf_block(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *ptr, int flags, + struct xfs_btree_block **block, struct xfs_buf **bpp); void xfs_btree_set_sibling(struct xfs_btree_cur *cur, struct xfs_btree_block *block, const union xfs_btree_ptr *ptr, int lr); @@ -578,21 +663,28 @@ void xfs_btree_copy_ptrs(struct xfs_btree_cur *cur, void xfs_btree_copy_keys(struct xfs_btree_cur *cur, union xfs_btree_key *dst_key, const union xfs_btree_key *src_key, int numkeys); +void xfs_btree_init_ptr_from_cur(struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr); static inline struct xfs_btree_cur * xfs_btree_alloc_cursor( struct xfs_mount *mp, struct xfs_trans *tp, - xfs_btnum_t btnum, + const struct xfs_btree_ops *ops, uint8_t maxlevels, struct kmem_cache *cache) { struct xfs_btree_cur *cur; - cur = kmem_cache_zalloc(cache, GFP_NOFS | __GFP_NOFAIL); + ASSERT(ops->ptr_len == XFS_BTREE_LONG_PTR_LEN || + ops->ptr_len == XFS_BTREE_SHORT_PTR_LEN); + + /* BMBT allocations can come through from non-transactional context. */ + cur = kmem_cache_zalloc(cache, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + cur->bc_ops = ops; cur->bc_tp = tp; cur->bc_mp = mp; - cur->bc_btnum = btnum; cur->bc_maxlevels = maxlevels; cur->bc_cache = cache; @@ -602,4 +694,22 @@ xfs_btree_alloc_cursor( int __init xfs_btree_init_cur_caches(void); void xfs_btree_destroy_cur_caches(void); +int xfs_btree_goto_left_edge(struct xfs_btree_cur *cur); + +/* Does this level of the cursor point to the inode root (and not a block)? */ +static inline bool +xfs_btree_at_iroot( + const struct xfs_btree_cur *cur, + int level) +{ + return cur->bc_ops->type == XFS_BTREE_TYPE_INODE && + level == cur->bc_nlevels - 1; +} + +int xfs_btree_alloc_metafile_block(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, union xfs_btree_ptr *newp, + int *stat); +int xfs_btree_free_metafile_block(struct xfs_btree_cur *cur, + struct xfs_buf *bp); + #endif /* __XFS_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree_mem.c b/fs/xfs/libxfs/xfs_btree_mem.c new file mode 100644 index 000000000000..f2f7b4305413 --- /dev/null +++ b/fs/xfs/libxfs/xfs_btree_mem.c @@ -0,0 +1,346 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_trans.h" +#include "xfs_btree.h" +#include "xfs_error.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" +#include "xfs_ag.h" +#include "xfs_buf_item.h" +#include "xfs_trace.h" +#include "xfs_rtgroup.h" + +/* Set the root of an in-memory btree. */ +void +xfbtree_set_root( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *ptr, + int inc) +{ + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM); + + cur->bc_mem.xfbtree->root = *ptr; + cur->bc_mem.xfbtree->nlevels += inc; +} + +/* Initialize a pointer from the in-memory btree header. */ +void +xfbtree_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM); + + *ptr = cur->bc_mem.xfbtree->root; +} + +/* Duplicate an in-memory btree cursor. */ +struct xfs_btree_cur * +xfbtree_dup_cursor( + struct xfs_btree_cur *cur) +{ + struct xfs_btree_cur *ncur; + + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM); + + ncur = xfs_btree_alloc_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ops, + cur->bc_maxlevels, cur->bc_cache); + ncur->bc_flags = cur->bc_flags; + ncur->bc_nlevels = cur->bc_nlevels; + ncur->bc_mem.xfbtree = cur->bc_mem.xfbtree; + if (cur->bc_group) + ncur->bc_group = xfs_group_hold(cur->bc_group); + return ncur; +} + +/* Close the btree xfile and release all resources. */ +void +xfbtree_destroy( + struct xfbtree *xfbt) +{ + xfs_buftarg_drain(xfbt->target); +} + +/* Compute the number of bytes available for records. */ +static inline unsigned int +xfbtree_rec_bytes( + struct xfs_mount *mp, + const struct xfs_btree_ops *ops) +{ + return XMBUF_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; +} + +/* Initialize an empty leaf block as the btree root. */ +STATIC int +xfbtree_init_leaf_block( + struct xfs_mount *mp, + struct xfbtree *xfbt, + const struct xfs_btree_ops *ops) +{ + struct xfs_buf *bp; + xfbno_t bno = xfbt->highest_bno++; + int error; + + error = xfs_buf_get(xfbt->target, xfbno_to_daddr(bno), XFBNO_BBSIZE, + &bp); + if (error) + return error; + + trace_xfbtree_create_root_buf(xfbt, bp); + + bp->b_ops = ops->buf_ops; + xfs_btree_init_buf(mp, bp, ops, 0, 0, xfbt->owner); + xfs_buf_relse(bp); + + xfbt->root.l = cpu_to_be64(bno); + return 0; +} + +/* + * Create an in-memory btree root that can be used with the given xmbuf. + * Callers must set xfbt->owner. + */ +int +xfbtree_init( + struct xfs_mount *mp, + struct xfbtree *xfbt, + struct xfs_buftarg *btp, + const struct xfs_btree_ops *ops) +{ + unsigned int blocklen = xfbtree_rec_bytes(mp, ops); + unsigned int keyptr_len; + int error; + + /* Requires a long-format CRC-format btree */ + if (!xfs_has_crc(mp)) { + ASSERT(xfs_has_crc(mp)); + return -EINVAL; + } + if (ops->ptr_len != XFS_BTREE_LONG_PTR_LEN) { + ASSERT(ops->ptr_len == XFS_BTREE_LONG_PTR_LEN); + return -EINVAL; + } + + memset(xfbt, 0, sizeof(*xfbt)); + xfbt->target = btp; + + /* Set up min/maxrecs for this btree. */ + keyptr_len = ops->key_len + sizeof(__be64); + xfbt->maxrecs[0] = blocklen / ops->rec_len; + xfbt->maxrecs[1] = blocklen / keyptr_len; + xfbt->minrecs[0] = xfbt->maxrecs[0] / 2; + xfbt->minrecs[1] = xfbt->maxrecs[1] / 2; + xfbt->highest_bno = 0; + xfbt->nlevels = 1; + + /* Initialize the empty btree. */ + error = xfbtree_init_leaf_block(mp, xfbt, ops); + if (error) + goto err_freesp; + + trace_xfbtree_init(mp, xfbt, ops); + + return 0; + +err_freesp: + xfs_buftarg_drain(xfbt->target); + return error; +} + +/* Allocate a block to our in-memory btree. */ +int +xfbtree_alloc_block( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, + union xfs_btree_ptr *new, + int *stat) +{ + struct xfbtree *xfbt = cur->bc_mem.xfbtree; + xfbno_t bno = xfbt->highest_bno++; + + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM); + + trace_xfbtree_alloc_block(xfbt, cur, bno); + + /* Fail if the block address exceeds the maximum for the buftarg. */ + if (!xfbtree_verify_bno(xfbt, bno)) { + ASSERT(xfbtree_verify_bno(xfbt, bno)); + *stat = 0; + return 0; + } + + new->l = cpu_to_be64(bno); + *stat = 1; + return 0; +} + +/* Free a block from our in-memory btree. */ +int +xfbtree_free_block( + struct xfs_btree_cur *cur, + struct xfs_buf *bp) +{ + struct xfbtree *xfbt = cur->bc_mem.xfbtree; + xfs_daddr_t daddr = xfs_buf_daddr(bp); + xfbno_t bno = xfs_daddr_to_xfbno(daddr); + + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM); + + trace_xfbtree_free_block(xfbt, cur, bno); + + if (bno + 1 == xfbt->highest_bno) + xfbt->highest_bno--; + + return 0; +} + +/* Return the minimum number of records for a btree block. */ +int +xfbtree_get_minrecs( + struct xfs_btree_cur *cur, + int level) +{ + struct xfbtree *xfbt = cur->bc_mem.xfbtree; + + return xfbt->minrecs[level != 0]; +} + +/* Return the maximum number of records for a btree block. */ +int +xfbtree_get_maxrecs( + struct xfs_btree_cur *cur, + int level) +{ + struct xfbtree *xfbt = cur->bc_mem.xfbtree; + + return xfbt->maxrecs[level != 0]; +} + +/* If this log item is a buffer item that came from the xfbtree, return it. */ +static inline struct xfs_buf * +xfbtree_buf_match( + struct xfbtree *xfbt, + const struct xfs_log_item *lip) +{ + const struct xfs_buf_log_item *bli; + struct xfs_buf *bp; + + if (lip->li_type != XFS_LI_BUF) + return NULL; + + bli = container_of(lip, struct xfs_buf_log_item, bli_item); + bp = bli->bli_buf; + if (bp->b_target != xfbt->target) + return NULL; + + return bp; +} + +/* + * Commit changes to the incore btree immediately by writing all dirty xfbtree + * buffers to the backing xfile. This detaches all xfbtree buffers from the + * transaction, even on failure. The buffer locks are dropped between the + * delwri queue and submit, so the caller must synchronize btree access. + * + * Normally we'd let the buffers commit with the transaction and get written to + * the xfile via the log, but online repair stages ephemeral btrees in memory + * and uses the btree_staging functions to write new btrees to disk atomically. + * The in-memory btree (and its backing store) are discarded at the end of the + * repair phase, which means that xfbtree buffers cannot commit with the rest + * of a transaction. + * + * In other words, online repair only needs the transaction to collect buffer + * pointers and to avoid buffer deadlocks, not to guarantee consistency of + * updates. + */ +int +xfbtree_trans_commit( + struct xfbtree *xfbt, + struct xfs_trans *tp) +{ + struct xfs_log_item *lip, *n; + bool tp_dirty = false; + int error = 0; + + /* + * For each xfbtree buffer attached to the transaction, write the dirty + * buffers to the xfile and release them. + */ + list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) { + struct xfs_buf *bp = xfbtree_buf_match(xfbt, lip); + + if (!bp) { + if (test_bit(XFS_LI_DIRTY, &lip->li_flags)) + tp_dirty |= true; + continue; + } + + trace_xfbtree_trans_commit_buf(xfbt, bp); + + xmbuf_trans_bdetach(tp, bp); + + /* + * If the buffer fails verification, note the failure but + * continue walking the transaction items so that we remove all + * ephemeral btree buffers. + */ + if (!error) + error = xmbuf_finalize(bp); + + xfs_buf_relse(bp); + } + + /* + * Reset the transaction's dirty flag to reflect the dirty state of the + * log items that are still attached. + */ + tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) | + (tp_dirty ? XFS_TRANS_DIRTY : 0); + + return error; +} + +/* + * Cancel changes to the incore btree by detaching all the xfbtree buffers. + * Changes are not undone, so callers must not access the btree ever again. + */ +void +xfbtree_trans_cancel( + struct xfbtree *xfbt, + struct xfs_trans *tp) +{ + struct xfs_log_item *lip, *n; + bool tp_dirty = false; + + list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) { + struct xfs_buf *bp = xfbtree_buf_match(xfbt, lip); + + if (!bp) { + if (test_bit(XFS_LI_DIRTY, &lip->li_flags)) + tp_dirty |= true; + continue; + } + + trace_xfbtree_trans_cancel_buf(xfbt, bp); + + xmbuf_trans_bdetach(tp, bp); + xfs_buf_relse(bp); + } + + /* + * Reset the transaction's dirty flag to reflect the dirty state of the + * log items that are still attached. + */ + tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) | + (tp_dirty ? XFS_TRANS_DIRTY : 0); +} diff --git a/fs/xfs/libxfs/xfs_btree_mem.h b/fs/xfs/libxfs/xfs_btree_mem.h new file mode 100644 index 000000000000..1c3825786ec8 --- /dev/null +++ b/fs/xfs/libxfs/xfs_btree_mem.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_BTREE_MEM_H__ +#define __XFS_BTREE_MEM_H__ + +typedef uint64_t xfbno_t; + +#define XFBNO_BLOCKSIZE (XMBUF_BLOCKSIZE) +#define XFBNO_BBSHIFT (XMBUF_BLOCKSHIFT - BBSHIFT) +#define XFBNO_BBSIZE (XFBNO_BLOCKSIZE >> BBSHIFT) + +static inline xfs_daddr_t xfbno_to_daddr(xfbno_t blkno) +{ + return blkno << XFBNO_BBSHIFT; +} + +static inline xfbno_t xfs_daddr_to_xfbno(xfs_daddr_t daddr) +{ + return daddr >> XFBNO_BBSHIFT; +} + +struct xfbtree { + /* buffer cache target for this in-memory btree */ + struct xfs_buftarg *target; + + /* Highest block number that has been written to. */ + xfbno_t highest_bno; + + /* Owner of this btree. */ + unsigned long long owner; + + /* Btree header */ + union xfs_btree_ptr root; + unsigned int nlevels; + + /* Minimum and maximum records per block. */ + unsigned int maxrecs[2]; + unsigned int minrecs[2]; +}; + +#ifdef CONFIG_XFS_BTREE_IN_MEM +static inline bool xfbtree_verify_bno(struct xfbtree *xfbt, xfbno_t bno) +{ + return xmbuf_verify_daddr(xfbt->target, xfbno_to_daddr(bno)); +} + +void xfbtree_set_root(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *ptr, int inc); +void xfbtree_init_ptr_from_cur(struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr); +struct xfs_btree_cur *xfbtree_dup_cursor(struct xfs_btree_cur *cur); + +int xfbtree_get_minrecs(struct xfs_btree_cur *cur, int level); +int xfbtree_get_maxrecs(struct xfs_btree_cur *cur, int level); + +int xfbtree_alloc_block(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, union xfs_btree_ptr *ptr, + int *stat); +int xfbtree_free_block(struct xfs_btree_cur *cur, struct xfs_buf *bp); + +/* Callers must set xfbt->target and xfbt->owner before calling this */ +int xfbtree_init(struct xfs_mount *mp, struct xfbtree *xfbt, + struct xfs_buftarg *btp, const struct xfs_btree_ops *ops); +void xfbtree_destroy(struct xfbtree *xfbt); + +int xfbtree_trans_commit(struct xfbtree *xfbt, struct xfs_trans *tp); +void xfbtree_trans_cancel(struct xfbtree *xfbt, struct xfs_trans *tp); +#else +# define xfbtree_verify_bno(...) (false) +#endif /* CONFIG_XFS_BTREE_IN_MEM */ + +#endif /* __XFS_BTREE_MEM_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c index dd75e208b543..5ed84f9cc877 100644 --- a/fs/xfs/libxfs/xfs_btree_staging.c +++ b/fs/xfs/libxfs/xfs_btree_staging.c @@ -39,63 +39,6 @@ */ /* - * Don't allow staging cursors to be duplicated because they're supposed to be - * kept private to a single thread. - */ -STATIC struct xfs_btree_cur * -xfs_btree_fakeroot_dup_cursor( - struct xfs_btree_cur *cur) -{ - ASSERT(0); - return NULL; -} - -/* - * Don't allow block allocation for a staging cursor, because staging cursors - * do not support regular btree modifications. - * - * Bulk loading uses a separate callback to obtain new blocks from a - * preallocated list, which prevents ENOSPC failures during loading. - */ -STATIC int -xfs_btree_fakeroot_alloc_block( - struct xfs_btree_cur *cur, - const union xfs_btree_ptr *start_bno, - union xfs_btree_ptr *new_bno, - int *stat) -{ - ASSERT(0); - return -EFSCORRUPTED; -} - -/* - * Don't allow block freeing for a staging cursor, because staging cursors - * do not support regular btree modifications. - */ -STATIC int -xfs_btree_fakeroot_free_block( - struct xfs_btree_cur *cur, - struct xfs_buf *bp) -{ - ASSERT(0); - return -EFSCORRUPTED; -} - -/* Initialize a pointer to the root block from the fakeroot. */ -STATIC void -xfs_btree_fakeroot_init_ptr_from_cur( - struct xfs_btree_cur *cur, - union xfs_btree_ptr *ptr) -{ - struct xbtree_afakeroot *afake; - - ASSERT(cur->bc_flags & XFS_BTREE_STAGING); - - afake = cur->bc_ag.afake; - ptr->s = cpu_to_be32(afake->af_root); -} - -/* * Bulk Loading for AG Btrees * ========================== * @@ -109,47 +52,20 @@ xfs_btree_fakeroot_init_ptr_from_cur( * cursor into a regular btree cursor. */ -/* Update the btree root information for a per-AG fake root. */ -STATIC void -xfs_btree_afakeroot_set_root( - struct xfs_btree_cur *cur, - const union xfs_btree_ptr *ptr, - int inc) -{ - struct xbtree_afakeroot *afake = cur->bc_ag.afake; - - ASSERT(cur->bc_flags & XFS_BTREE_STAGING); - afake->af_root = be32_to_cpu(ptr->s); - afake->af_levels += inc; -} - /* * Initialize a AG-rooted btree cursor with the given AG btree fake root. - * The btree cursor's bc_ops will be overridden as needed to make the staging - * functionality work. */ void xfs_btree_stage_afakeroot( struct xfs_btree_cur *cur, struct xbtree_afakeroot *afake) { - struct xfs_btree_ops *nops; - ASSERT(!(cur->bc_flags & XFS_BTREE_STAGING)); - ASSERT(!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)); + ASSERT(cur->bc_ops->type != XFS_BTREE_TYPE_INODE); ASSERT(cur->bc_tp == NULL); - nops = kmem_alloc(sizeof(struct xfs_btree_ops), KM_NOFS); - memcpy(nops, cur->bc_ops, sizeof(struct xfs_btree_ops)); - nops->alloc_block = xfs_btree_fakeroot_alloc_block; - nops->free_block = xfs_btree_fakeroot_free_block; - nops->init_ptr_from_cur = xfs_btree_fakeroot_init_ptr_from_cur; - nops->set_root = xfs_btree_afakeroot_set_root; - nops->dup_cursor = xfs_btree_fakeroot_dup_cursor; - cur->bc_ag.afake = afake; cur->bc_nlevels = afake->af_levels; - cur->bc_ops = nops; cur->bc_flags |= XFS_BTREE_STAGING; } @@ -163,17 +79,15 @@ void xfs_btree_commit_afakeroot( struct xfs_btree_cur *cur, struct xfs_trans *tp, - struct xfs_buf *agbp, - const struct xfs_btree_ops *ops) + struct xfs_buf *agbp) { ASSERT(cur->bc_flags & XFS_BTREE_STAGING); ASSERT(cur->bc_tp == NULL); trace_xfs_btree_commit_afakeroot(cur); - kmem_free((void *)cur->bc_ops); + cur->bc_ag.afake = NULL; cur->bc_ag.agbp = agbp; - cur->bc_ops = ops; cur->bc_flags &= ~XFS_BTREE_STAGING; cur->bc_tp = tp; } @@ -211,29 +125,17 @@ xfs_btree_commit_afakeroot( void xfs_btree_stage_ifakeroot( struct xfs_btree_cur *cur, - struct xbtree_ifakeroot *ifake, - struct xfs_btree_ops **new_ops) + struct xbtree_ifakeroot *ifake) { - struct xfs_btree_ops *nops; - ASSERT(!(cur->bc_flags & XFS_BTREE_STAGING)); - ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); ASSERT(cur->bc_tp == NULL); - nops = kmem_alloc(sizeof(struct xfs_btree_ops), KM_NOFS); - memcpy(nops, cur->bc_ops, sizeof(struct xfs_btree_ops)); - nops->alloc_block = xfs_btree_fakeroot_alloc_block; - nops->free_block = xfs_btree_fakeroot_free_block; - nops->init_ptr_from_cur = xfs_btree_fakeroot_init_ptr_from_cur; - nops->dup_cursor = xfs_btree_fakeroot_dup_cursor; - cur->bc_ino.ifake = ifake; cur->bc_nlevels = ifake->if_levels; - cur->bc_ops = nops; + cur->bc_ino.forksize = ifake->if_fork_size; + cur->bc_ino.whichfork = XFS_STAGING_FORK; cur->bc_flags |= XFS_BTREE_STAGING; - - if (new_ops) - *new_ops = nops; } /* @@ -246,18 +148,15 @@ void xfs_btree_commit_ifakeroot( struct xfs_btree_cur *cur, struct xfs_trans *tp, - int whichfork, - const struct xfs_btree_ops *ops) + int whichfork) { ASSERT(cur->bc_flags & XFS_BTREE_STAGING); ASSERT(cur->bc_tp == NULL); trace_xfs_btree_commit_ifakeroot(cur); - kmem_free((void *)cur->bc_ops); cur->bc_ino.ifake = NULL; cur->bc_ino.whichfork = whichfork; - cur->bc_ops = ops; cur->bc_flags &= ~XFS_BTREE_STAGING; cur->bc_tp = tp; } @@ -333,20 +232,41 @@ xfs_btree_commit_ifakeroot( /* * Put a btree block that we're loading onto the ordered list and release it. * The btree blocks will be written to disk when bulk loading is finished. + * If we reach the dirty buffer threshold, flush them to disk before + * continuing. */ -static void +static int xfs_btree_bload_drop_buf( - struct list_head *buffers_list, - struct xfs_buf **bpp) + struct xfs_btree_bload *bbl, + struct list_head *buffers_list, + struct xfs_buf **bpp) { - if (*bpp == NULL) - return; + struct xfs_buf *bp = *bpp; + int error; + + if (!bp) + return 0; - if (!xfs_buf_delwri_queue(*bpp, buffers_list)) - ASSERT(0); + /* + * Mark this buffer XBF_DONE (i.e. uptodate) so that a subsequent + * xfs_buf_read will not pointlessly reread the contents from the disk. + */ + bp->b_flags |= XBF_DONE; - xfs_buf_relse(*bpp); + xfs_buf_delwri_queue_here(bp, buffers_list); + xfs_buf_relse(bp); *bpp = NULL; + bbl->nr_dirty++; + + if (!bbl->max_dirty || bbl->nr_dirty < bbl->max_dirty) + return 0; + + error = xfs_buf_delwri_submit(buffers_list); + if (error) + return error; + + bbl->nr_dirty = 0; + return 0; } /* @@ -376,23 +296,20 @@ xfs_btree_bload_prep_block( struct xfs_btree_block *new_block; int ret; - if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && - level == cur->bc_nlevels - 1) { + if (xfs_btree_at_iroot(cur, level)) { struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); size_t new_size; ASSERT(*bpp == NULL); /* Allocate a new incore btree root block. */ - new_size = bbl->iroot_size(cur, nr_this_block, priv); - ifp->if_broot = kmem_zalloc(new_size, 0); + new_size = bbl->iroot_size(cur, level, nr_this_block, priv); + ifp->if_broot = kzalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); ifp->if_broot_bytes = (int)new_size; /* Initialize it and send it out. */ - xfs_btree_init_block_int(cur->bc_mp, ifp->if_broot, - XFS_BUF_DADDR_NULL, cur->bc_btnum, level, - nr_this_block, cur->bc_ino.ip->i_ino, - cur->bc_flags); + xfs_btree_init_block(cur->bc_mp, ifp->if_broot, cur->bc_ops, + level, nr_this_block, cur->bc_ino.ip->i_ino); *bpp = NULL; *blockp = ifp->if_broot; @@ -418,7 +335,10 @@ xfs_btree_bload_prep_block( */ if (*blockp) xfs_btree_set_sibling(cur, *blockp, &new_ptr, XFS_BB_RIGHTSIB); - xfs_btree_bload_drop_buf(buffers_list, bpp); + + ret = xfs_btree_bload_drop_buf(bbl, buffers_list, bpp); + if (ret) + return ret; /* Initialize the new btree block. */ xfs_btree_init_block_cur(cur, new_bp, level, nr_this_block); @@ -436,22 +356,19 @@ STATIC int xfs_btree_bload_leaf( struct xfs_btree_cur *cur, unsigned int recs_this_block, - xfs_btree_bload_get_record_fn get_record, + xfs_btree_bload_get_records_fn get_records, struct xfs_btree_block *block, void *priv) { - unsigned int j; + unsigned int j = 1; int ret; /* Fill the leaf block with records. */ - for (j = 1; j <= recs_this_block; j++) { - union xfs_btree_rec *block_rec; - - ret = get_record(cur, priv); - if (ret) + while (j <= recs_this_block) { + ret = get_records(cur, j, block, recs_this_block - j + 1, priv); + if (ret < 0) return ret; - block_rec = xfs_btree_rec_addr(cur, j, block); - cur->bc_ops->init_rec_from_cur(cur, block_rec); + j += ret; } return 0; @@ -485,7 +402,12 @@ xfs_btree_bload_node( ASSERT(!xfs_btree_ptr_is_null(cur, child_ptr)); - ret = xfs_btree_get_buf_block(cur, child_ptr, &child_block, + /* + * Read the lower-level block in case the buffer for it has + * been reclaimed. LRU refs will be set on the block, which is + * desirable if the new btree commits. + */ + ret = xfs_btree_read_buf_block(cur, child_ptr, 0, &child_block, &child_bp); if (ret) return ret; @@ -570,7 +492,14 @@ xfs_btree_bload_level_geometry( unsigned int desired_npb; unsigned int maxnr; - maxnr = cur->bc_ops->get_maxrecs(cur, level); + /* + * Compute the absolute maximum number of records that we can store in + * the ondisk block or inode root. + */ + if (cur->bc_ops->get_dmaxrecs) + maxnr = cur->bc_ops->get_dmaxrecs(cur, level); + else + maxnr = cur->bc_ops->get_maxrecs(cur, level); /* * Compute the number of blocks we need to fill each block with the @@ -645,6 +574,7 @@ xfs_btree_bload_compute_geometry( struct xfs_btree_bload *bbl, uint64_t nr_records) { + const struct xfs_btree_ops *ops = cur->bc_ops; uint64_t nr_blocks = 0; uint64_t nr_this_level; @@ -671,7 +601,7 @@ xfs_btree_bload_compute_geometry( xfs_btree_bload_level_geometry(cur, bbl, level, nr_this_level, &avg_per_block, &level_blocks, &dontcare64); - if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) { + if (ops->type == XFS_BTREE_TYPE_INODE) { /* * If all the items we want to store at this level * would fit in the inode root block, then we have our @@ -679,7 +609,9 @@ xfs_btree_bload_compute_geometry( * * Note that bmap btrees forbid records in the root. */ - if (level != 0 && nr_this_level <= avg_per_block) { + if ((level != 0 || + (ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)) && + nr_this_level <= avg_per_block) { nr_blocks++; break; } @@ -730,7 +662,7 @@ xfs_btree_bload_compute_geometry( return -EOVERFLOW; bbl->btree_height = cur->bc_nlevels; - if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) + if (ops->type == XFS_BTREE_TYPE_INODE) bbl->nr_blocks = nr_blocks - 1; else bbl->nr_blocks = nr_blocks; @@ -764,6 +696,7 @@ xfs_btree_bload( cur->bc_nlevels = bbl->btree_height; xfs_btree_set_ptr_null(cur, &child_ptr); xfs_btree_set_ptr_null(cur, &ptr); + bbl->nr_dirty = 0; xfs_btree_bload_level_geometry(cur, bbl, level, nr_this_level, &avg_per_block, &blocks, &blocks_with_extra); @@ -789,7 +722,7 @@ xfs_btree_bload( trace_xfs_btree_bload_block(cur, level, i, blocks, &ptr, nr_this_block); - ret = xfs_btree_bload_leaf(cur, nr_this_block, bbl->get_record, + ret = xfs_btree_bload_leaf(cur, nr_this_block, bbl->get_records, block, priv); if (ret) goto out; @@ -802,7 +735,10 @@ xfs_btree_bload( xfs_btree_copy_ptrs(cur, &child_ptr, &ptr, 1); } total_blocks += blocks; - xfs_btree_bload_drop_buf(&buffers_list, &bp); + + ret = xfs_btree_bload_drop_buf(bbl, &buffers_list, &bp); + if (ret) + goto out; /* Populate the internal btree nodes. */ for (level = 1; level < cur->bc_nlevels; level++) { @@ -844,12 +780,16 @@ xfs_btree_bload( xfs_btree_copy_ptrs(cur, &first_ptr, &ptr, 1); } total_blocks += blocks; - xfs_btree_bload_drop_buf(&buffers_list, &bp); + + ret = xfs_btree_bload_drop_buf(bbl, &buffers_list, &bp); + if (ret) + goto out; + xfs_btree_copy_ptrs(cur, &child_ptr, &first_ptr, 1); } /* Initialize the new root. */ - if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) { + if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { ASSERT(xfs_btree_ptr_is_null(cur, &ptr)); cur->bc_ino.ifake->if_levels = cur->bc_nlevels; cur->bc_ino.ifake->if_blocks = total_blocks - 1; diff --git a/fs/xfs/libxfs/xfs_btree_staging.h b/fs/xfs/libxfs/xfs_btree_staging.h index f0d2976050ae..0c9c2ffb127a 100644 --- a/fs/xfs/libxfs/xfs_btree_staging.h +++ b/fs/xfs/libxfs/xfs_btree_staging.h @@ -22,7 +22,7 @@ struct xbtree_afakeroot { void xfs_btree_stage_afakeroot(struct xfs_btree_cur *cur, struct xbtree_afakeroot *afake); void xfs_btree_commit_afakeroot(struct xfs_btree_cur *cur, struct xfs_trans *tp, - struct xfs_buf *agbp, const struct xfs_btree_ops *ops); + struct xfs_buf *agbp); /* Fake root for an inode-rooted btree. */ struct xbtree_ifakeroot { @@ -37,35 +37,33 @@ struct xbtree_ifakeroot { /* Number of bytes available for this fork in the inode. */ unsigned int if_fork_size; - - /* Fork format. */ - unsigned int if_format; - - /* Number of records. */ - unsigned int if_extents; }; /* Cursor interactions with fake roots for inode-rooted btrees. */ void xfs_btree_stage_ifakeroot(struct xfs_btree_cur *cur, - struct xbtree_ifakeroot *ifake, - struct xfs_btree_ops **new_ops); + struct xbtree_ifakeroot *ifake); void xfs_btree_commit_ifakeroot(struct xfs_btree_cur *cur, struct xfs_trans *tp, - int whichfork, const struct xfs_btree_ops *ops); + int whichfork); /* Bulk loading of staged btrees. */ -typedef int (*xfs_btree_bload_get_record_fn)(struct xfs_btree_cur *cur, void *priv); +typedef int (*xfs_btree_bload_get_records_fn)(struct xfs_btree_cur *cur, + unsigned int idx, struct xfs_btree_block *block, + unsigned int nr_wanted, void *priv); typedef int (*xfs_btree_bload_claim_block_fn)(struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr, void *priv); typedef size_t (*xfs_btree_bload_iroot_size_fn)(struct xfs_btree_cur *cur, - unsigned int nr_this_level, void *priv); + unsigned int level, unsigned int nr_this_level, void *priv); struct xfs_btree_bload { /* - * This function will be called nr_records times to load records into - * the btree. The function does this by setting the cursor's bc_rec - * field in in-core format. Records must be returned in sort order. + * This function will be called to load @nr_wanted records into the + * btree. The implementation does this by setting the cursor's bc_rec + * field in in-core format and using init_rec_from_cur to set the + * records in the btree block. Records must be returned in sort order. + * The function must return the number of records loaded or the usual + * negative errno. */ - xfs_btree_bload_get_record_fn get_record; + xfs_btree_bload_get_records_fn get_records; /* * This function will be called nr_blocks times to obtain a pointer @@ -77,8 +75,7 @@ struct xfs_btree_bload { /* * This function should return the size of the in-core btree root - * block. It is only necessary for XFS_BTREE_ROOT_IN_INODE btree - * types. + * block. It is only necessary for XFS_BTREE_TYPE_INODE btrees. */ xfs_btree_bload_iroot_size_fn iroot_size; @@ -113,6 +110,16 @@ struct xfs_btree_bload { * height of the new btree. */ unsigned int btree_height; + + /* + * Flush the new btree block buffer list to disk after this many blocks + * have been formatted. Zero prohibits writing any buffers until all + * blocks have been formatted. + */ + uint16_t max_dirty; + + /* Number of dirty buffers. */ + uint16_t nr_dirty; }; int xfs_btree_bload_compute_geometry(struct xfs_btree_cur *cur, diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index e576560b46e9..90f7fc219fcc 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -23,6 +23,7 @@ #include "xfs_buf_item.h" #include "xfs_log.h" #include "xfs_errortag.h" +#include "xfs_health.h" /* * xfs_da_btree.c @@ -85,7 +86,8 @@ xfs_da_state_alloc( { struct xfs_da_state *state; - state = kmem_cache_zalloc(xfs_da_state_cache, GFP_NOFS | __GFP_NOFAIL); + state = kmem_cache_zalloc(xfs_da_state_cache, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); state->args = args; state->mp = args->dp->i_mount; return state; @@ -250,6 +252,51 @@ xfs_da3_node_verify( return NULL; } +xfs_failaddr_t +xfs_da3_node_header_check( + struct xfs_buf *bp, + xfs_ino_t owner) +{ + struct xfs_mount *mp = bp->b_mount; + + if (xfs_has_crc(mp)) { + struct xfs_da3_blkinfo *hdr3 = bp->b_addr; + + if (hdr3->hdr.magic != cpu_to_be16(XFS_DA3_NODE_MAGIC)) + return __this_address; + + if (be64_to_cpu(hdr3->owner) != owner) + return __this_address; + } + + return NULL; +} + +xfs_failaddr_t +xfs_da3_header_check( + struct xfs_buf *bp, + xfs_ino_t owner) +{ + struct xfs_mount *mp = bp->b_mount; + struct xfs_da_blkinfo *hdr = bp->b_addr; + + if (!xfs_has_crc(mp)) + return NULL; + + switch (hdr->magic) { + case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC): + return xfs_attr3_leaf_header_check(bp, owner); + case cpu_to_be16(XFS_DA3_NODE_MAGIC): + return xfs_da3_node_header_check(bp, owner); + case cpu_to_be16(XFS_DIR3_LEAF1_MAGIC): + case cpu_to_be16(XFS_DIR3_LEAFN_MAGIC): + return xfs_dir3_leaf_header_check(bp, owner); + } + + ASSERT(0); + return NULL; +} + static void xfs_da3_node_write_verify( struct xfs_buf *bp) @@ -352,6 +399,8 @@ const struct xfs_buf_ops xfs_da3_node_buf_ops = { static int xfs_da3_node_set_type( struct xfs_trans *tp, + struct xfs_inode *dp, + int whichfork, struct xfs_buf *bp) { struct xfs_da_blkinfo *info = bp->b_addr; @@ -373,6 +422,7 @@ xfs_da3_node_set_type( XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, tp->t_mountp, info, sizeof(*info)); xfs_trans_brelse(tp, bp); + xfs_dirattr_mark_sick(dp, whichfork); return -EFSCORRUPTED; } } @@ -391,7 +441,7 @@ xfs_da3_node_read( &xfs_da3_node_buf_ops); if (error || !*bpp || !tp) return error; - return xfs_da3_node_set_type(tp, *bpp); + return xfs_da3_node_set_type(tp, dp, whichfork, *bpp); } int @@ -408,6 +458,8 @@ xfs_da3_node_read_mapped( error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, mappedbno, XFS_FSB_TO_BB(mp, xfs_dabuf_nfsb(mp, whichfork)), 0, bpp, &xfs_da3_node_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_dirattr_mark_sick(dp, whichfork); if (error || !*bpp) return error; @@ -418,7 +470,26 @@ xfs_da3_node_read_mapped( if (!tp) return 0; - return xfs_da3_node_set_type(tp, *bpp); + return xfs_da3_node_set_type(tp, dp, whichfork, *bpp); +} + +/* + * Copy src directory/attr leaf/node buffer to the dst. + * For v5 file systems make sure the right blkno is stamped in. + */ +void +xfs_da_buf_copy( + struct xfs_buf *dst, + struct xfs_buf *src, + size_t size) +{ + struct xfs_da3_blkinfo *da3 = dst->b_addr; + + memcpy(dst->b_addr, src->b_addr, size); + dst->b_ops = src->b_ops; + xfs_trans_buf_copy_type(dst, src); + if (xfs_has_crc(dst->b_mount)) + da3->blkno = cpu_to_be64(xfs_buf_daddr(dst)); } /*======================================================================== @@ -460,7 +531,7 @@ xfs_da3_node_create( memset(hdr3, 0, sizeof(struct xfs_da3_node_hdr)); ichdr.magic = XFS_DA3_NODE_MAGIC; hdr3->info.blkno = cpu_to_be64(xfs_buf_daddr(bp)); - hdr3->info.owner = cpu_to_be64(args->dp->i_ino); + hdr3->info.owner = cpu_to_be64(args->owner); uuid_copy(&hdr3->info.uuid, &mp->m_sb.sb_meta_uuid); } else { ichdr.magic = XFS_DA_NODE_MAGIC; @@ -494,7 +565,7 @@ xfs_da3_split( trace_xfs_da_split(state->args); - if (XFS_TEST_ERROR(false, state->mp, XFS_ERRTAG_DA_LEAF_SPLIT)) + if (XFS_TEST_ERROR(state->mp, XFS_ERRTAG_DA_LEAF_SPLIT)) return -EIO; /* @@ -522,9 +593,8 @@ xfs_da3_split( switch (oldblk->magic) { case XFS_ATTR_LEAF_MAGIC: error = xfs_attr3_leaf_split(state, oldblk, newblk); - if ((error != 0) && (error != -ENOSPC)) { + if (error < 0) return error; /* GROT: attr is inconsistent */ - } if (!error) { addblk = newblk; break; @@ -546,6 +616,8 @@ xfs_da3_split( error = xfs_attr3_leaf_split(state, newblk, &state->extrablk); } + if (error == 1) + return -ENOSPC; if (error) return error; /* GROT: attr inconsistent */ addblk = newblk; @@ -612,6 +684,7 @@ xfs_da3_split( if (node->hdr.info.forw) { if (be32_to_cpu(node->hdr.info.forw) != addblk->blkno) { xfs_buf_mark_corrupt(oldblk->bp); + xfs_da_mark_sick(state->args); error = -EFSCORRUPTED; goto out; } @@ -625,6 +698,7 @@ xfs_da3_split( if (node->hdr.info.back) { if (be32_to_cpu(node->hdr.info.back) != addblk->blkno) { xfs_buf_mark_corrupt(oldblk->bp); + xfs_da_mark_sick(state->args); error = -EFSCORRUPTED; goto out; } @@ -690,12 +764,6 @@ xfs_da3_root_split( btree = icnodehdr.btree; size = (int)((char *)&btree[icnodehdr.count] - (char *)oldroot); level = icnodehdr.level; - - /* - * we are about to copy oldroot to bp, so set up the type - * of bp while we know exactly what it will be. - */ - xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DA_NODE_BUF); } else { struct xfs_dir3_icleaf_hdr leafhdr; @@ -707,31 +775,17 @@ xfs_da3_root_split( size = (int)((char *)&leafhdr.ents[leafhdr.count] - (char *)leaf); level = 0; - - /* - * we are about to copy oldroot to bp, so set up the type - * of bp while we know exactly what it will be. - */ - xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_LEAFN_BUF); } /* - * we can copy most of the information in the node from one block to - * another, but for CRC enabled headers we have to make sure that the - * block specific identifiers are kept intact. We update the buffer - * directly for this. + * Copy old root to new buffer and log it. */ - memcpy(node, oldroot, size); - if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC) || - oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) { - struct xfs_da3_intnode *node3 = (struct xfs_da3_intnode *)node; - - node3->hdr.info.blkno = cpu_to_be64(xfs_buf_daddr(bp)); - } + xfs_da_buf_copy(bp, blk1->bp, size); xfs_trans_log_buf(tp, bp, 0, size - 1); - bp->b_ops = blk1->bp->b_ops; - xfs_trans_buf_copy_type(bp, blk1->bp); + /* + * Update blk1 to point to new buffer. + */ blk1->bp = bp; blk1->blkno = blkno; @@ -1191,6 +1245,7 @@ xfs_da3_root_join( struct xfs_da3_icnode_hdr oldroothdr; int error; struct xfs_inode *dp = state->args->dp; + xfs_failaddr_t fa; trace_xfs_da_root_join(state->args); @@ -1217,24 +1272,24 @@ xfs_da3_root_join( error = xfs_da3_node_read(args->trans, dp, child, &bp, args->whichfork); if (error) return error; + fa = xfs_da3_header_check(bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(bp, fa); + xfs_trans_brelse(args->trans, bp); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } xfs_da_blkinfo_onlychild_validate(bp->b_addr, oldroothdr.level); /* - * This could be copying a leaf back into the root block in the case of - * there only being a single leaf block left in the tree. Hence we have - * to update the b_ops pointer as well to match the buffer type change - * that could occur. For dir3 blocks we also need to update the block - * number in the buffer header. + * Copy child to root buffer and log it. */ - memcpy(root_blk->bp->b_addr, bp->b_addr, args->geo->blksize); - root_blk->bp->b_ops = bp->b_ops; - xfs_trans_buf_copy_type(root_blk->bp, bp); - if (oldroothdr.magic == XFS_DA3_NODE_MAGIC) { - struct xfs_da3_blkinfo *da3 = root_blk->bp->b_addr; - da3->blkno = cpu_to_be64(xfs_buf_daddr(root_blk->bp)); - } + xfs_da_buf_copy(root_blk->bp, bp, args->geo->blksize); xfs_trans_log_buf(args->trans, root_blk->bp, 0, args->geo->blksize - 1); + /* + * Now we can drop the child buffer. + */ error = xfs_da_shrink_inode(args, child, bp); return error; } @@ -1258,6 +1313,7 @@ xfs_da3_node_toosmall( struct xfs_da_blkinfo *info; xfs_dablk_t blkno; struct xfs_buf *bp; + xfs_failaddr_t fa; struct xfs_da3_icnode_hdr nodehdr; int count; int forward; @@ -1332,6 +1388,13 @@ xfs_da3_node_toosmall( state->args->whichfork); if (error) return error; + fa = xfs_da3_node_header_check(bp, state->args->owner); + if (fa) { + __xfs_buf_mark_corrupt(bp, fa); + xfs_trans_brelse(state->args->trans, bp); + xfs_da_mark_sick(state->args); + return -EFSCORRUPTED; + } node = bp->b_addr; xfs_da3_node_hdr_from_disk(dp->i_mount, &thdr, node); @@ -1590,6 +1653,7 @@ xfs_da3_node_lookup_int( struct xfs_da_node_entry *btree; struct xfs_da3_icnode_hdr nodehdr; struct xfs_da_args *args; + xfs_failaddr_t fa; xfs_dablk_t blkno; xfs_dahash_t hashval; xfs_dahash_t btreehashval; @@ -1628,6 +1692,12 @@ xfs_da3_node_lookup_int( if (magic == XFS_ATTR_LEAF_MAGIC || magic == XFS_ATTR3_LEAF_MAGIC) { + fa = xfs_attr3_leaf_header_check(blk->bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(blk->bp, fa); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } blk->magic = XFS_ATTR_LEAF_MAGIC; blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL); break; @@ -1635,6 +1705,12 @@ xfs_da3_node_lookup_int( if (magic == XFS_DIR2_LEAFN_MAGIC || magic == XFS_DIR3_LEAFN_MAGIC) { + fa = xfs_dir3_leaf_header_check(blk->bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(blk->bp, fa); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } blk->magic = XFS_DIR2_LEAFN_MAGIC; blk->hashval = xfs_dir2_leaf_lasthash(args->dp, blk->bp, NULL); @@ -1643,6 +1719,14 @@ xfs_da3_node_lookup_int( if (magic != XFS_DA_NODE_MAGIC && magic != XFS_DA3_NODE_MAGIC) { xfs_buf_mark_corrupt(blk->bp); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } + + fa = xfs_da3_node_header_check(blk->bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(blk->bp, fa); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } @@ -1658,6 +1742,7 @@ xfs_da3_node_lookup_int( /* Tree taller than we can handle; bail out! */ if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH) { xfs_buf_mark_corrupt(blk->bp); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } @@ -1666,6 +1751,7 @@ xfs_da3_node_lookup_int( expected_level = nodehdr.level - 1; else if (expected_level != nodehdr.level) { xfs_buf_mark_corrupt(blk->bp); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } else expected_level--; @@ -1717,12 +1803,16 @@ xfs_da3_node_lookup_int( } /* We can't point back to the root. */ - if (XFS_IS_CORRUPT(dp->i_mount, blkno == args->geo->leafblk)) + if (XFS_IS_CORRUPT(dp->i_mount, blkno == args->geo->leafblk)) { + xfs_da_mark_sick(args); return -EFSCORRUPTED; + } } - if (XFS_IS_CORRUPT(dp->i_mount, expected_level != 0)) + if (XFS_IS_CORRUPT(dp->i_mount, expected_level != 0)) { + xfs_da_mark_sick(args); return -EFSCORRUPTED; + } /* * A leaf block that ends in the hashval that we are interested in @@ -1740,6 +1830,7 @@ xfs_da3_node_lookup_int( args->blkno = blk->blkno; } else { ASSERT(0); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } if (((retval == -ENOENT) || (retval == -ENOATTR)) && @@ -1811,6 +1902,7 @@ xfs_da3_blk_link( struct xfs_da_blkinfo *tmp_info; struct xfs_da_args *args; struct xfs_buf *bp; + xfs_failaddr_t fa; int before = 0; int error; struct xfs_inode *dp = state->args->dp; @@ -1854,6 +1946,13 @@ xfs_da3_blk_link( &bp, args->whichfork); if (error) return error; + fa = xfs_da3_header_check(bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(bp, fa); + xfs_trans_brelse(args->trans, bp); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } ASSERT(bp != NULL); tmp_info = bp->b_addr; ASSERT(tmp_info->magic == old_info->magic); @@ -1875,6 +1974,13 @@ xfs_da3_blk_link( &bp, args->whichfork); if (error) return error; + fa = xfs_da3_header_check(bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(bp, fa); + xfs_trans_brelse(args->trans, bp); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } ASSERT(bp != NULL); tmp_info = bp->b_addr; ASSERT(tmp_info->magic == old_info->magic); @@ -1904,6 +2010,7 @@ xfs_da3_blk_unlink( struct xfs_da_blkinfo *tmp_info; struct xfs_da_args *args; struct xfs_buf *bp; + xfs_failaddr_t fa; int error; /* @@ -1934,6 +2041,13 @@ xfs_da3_blk_unlink( &bp, args->whichfork); if (error) return error; + fa = xfs_da3_header_check(bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(bp, fa); + xfs_trans_brelse(args->trans, bp); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } ASSERT(bp != NULL); tmp_info = bp->b_addr; ASSERT(tmp_info->magic == save_info->magic); @@ -1951,6 +2065,13 @@ xfs_da3_blk_unlink( &bp, args->whichfork); if (error) return error; + fa = xfs_da3_header_check(bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(bp, fa); + xfs_trans_brelse(args->trans, bp); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } ASSERT(bp != NULL); tmp_info = bp->b_addr; ASSERT(tmp_info->magic == save_info->magic); @@ -1987,6 +2108,7 @@ xfs_da3_path_shift( struct xfs_da_node_entry *btree; struct xfs_da3_icnode_hdr nodehdr; struct xfs_buf *bp; + xfs_failaddr_t fa; xfs_dablk_t blkno = 0; int level; int error; @@ -2065,6 +2187,12 @@ xfs_da3_path_shift( switch (be16_to_cpu(info->magic)) { case XFS_DA_NODE_MAGIC: case XFS_DA3_NODE_MAGIC: + fa = xfs_da3_node_header_check(blk->bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(blk->bp, fa); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } blk->magic = XFS_DA_NODE_MAGIC; xfs_da3_node_hdr_from_disk(dp->i_mount, &nodehdr, bp->b_addr); @@ -2078,6 +2206,12 @@ xfs_da3_path_shift( break; case XFS_ATTR_LEAF_MAGIC: case XFS_ATTR3_LEAF_MAGIC: + fa = xfs_attr3_leaf_header_check(blk->bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(blk->bp, fa); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } blk->magic = XFS_ATTR_LEAF_MAGIC; ASSERT(level == path->active-1); blk->index = 0; @@ -2085,6 +2219,12 @@ xfs_da3_path_shift( break; case XFS_DIR2_LEAFN_MAGIC: case XFS_DIR3_LEAFN_MAGIC: + fa = xfs_dir3_leaf_header_check(blk->bp, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(blk->bp, fa); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } blk->magic = XFS_DIR2_LEAFN_MAGIC; ASSERT(level == path->active-1); blk->index = 0; @@ -2158,8 +2298,8 @@ xfs_da_grow_inode_int( struct xfs_inode *dp = args->dp; int w = args->whichfork; xfs_rfsblock_t nblks = dp->i_nblocks; - struct xfs_bmbt_irec map, *mapp; - int nmap, error, got, i, mapi; + struct xfs_bmbt_irec map, *mapp = ↦ + int nmap, error, got, i, mapi = 1; /* * Find a spot in the file space to put the new block. @@ -2175,14 +2315,7 @@ xfs_da_grow_inode_int( error = xfs_bmapi_write(tp, dp, *bno, count, xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG, args->total, &map, &nmap); - if (error) - return error; - - ASSERT(nmap <= 1); - if (nmap == 1) { - mapp = ↦ - mapi = 1; - } else if (nmap == 0 && count > 1) { + if (error == -ENOSPC && count > 1) { xfs_fileoff_t b; int c; @@ -2190,7 +2323,8 @@ xfs_da_grow_inode_int( * If we didn't get it and the block might work if fragmented, * try without the CONTIG flag. Loop until we get it all. */ - mapp = kmem_alloc(sizeof(*mapp) * count, 0); + mapp = kmalloc(sizeof(*mapp) * count, + GFP_KERNEL | __GFP_NOFAIL); for (b = *bno, mapi = 0; b < *bno + count; ) { c = (int)(*bno + count - b); nmap = min(XFS_BMAP_MAX_NMAP, c); @@ -2199,16 +2333,13 @@ xfs_da_grow_inode_int( args->total, &mapp[mapi], &nmap); if (error) goto out_free_map; - if (nmap < 1) - break; mapi += nmap; b = mapp[mapi - 1].br_startoff + mapp[mapi - 1].br_blockcount; } - } else { - mapi = 0; - mapp = NULL; } + if (error) + goto out_free_map; /* * Count the blocks we got, make sure it matches the total. @@ -2227,7 +2358,7 @@ xfs_da_grow_inode_int( out_free_map: if (mapp != &map) - kmem_free(mapp); + kfree(mapp); return error; } @@ -2280,6 +2411,7 @@ xfs_da3_swap_lastblock( struct xfs_buf *last_buf; struct xfs_buf *sib_buf; struct xfs_buf *par_buf; + xfs_failaddr_t fa; xfs_dahash_t dead_hash; xfs_fileoff_t lastoff; xfs_dablk_t dead_blkno; @@ -2305,8 +2437,10 @@ xfs_da3_swap_lastblock( error = xfs_bmap_last_before(tp, dp, &lastoff, w); if (error) return error; - if (XFS_IS_CORRUPT(mp, lastoff == 0)) + if (XFS_IS_CORRUPT(mp, lastoff == 0)) { + xfs_da_mark_sick(args); return -EFSCORRUPTED; + } /* * Read the last block in the btree space. */ @@ -2314,12 +2448,21 @@ xfs_da3_swap_lastblock( error = xfs_da3_node_read(tp, dp, last_blkno, &last_buf, w); if (error) return error; + fa = xfs_da3_header_check(last_buf, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(last_buf, fa); + xfs_trans_brelse(tp, last_buf); + xfs_da_mark_sick(args); + return -EFSCORRUPTED; + } + /* * Copy the last block into the dead buffer and log it. */ - memcpy(dead_buf->b_addr, last_buf->b_addr, args->geo->blksize); + xfs_da_buf_copy(dead_buf, last_buf, args->geo->blksize); xfs_trans_log_buf(tp, dead_buf, 0, args->geo->blksize - 1); dead_info = dead_buf->b_addr; + /* * Get values from the moved block. */ @@ -2351,10 +2494,18 @@ xfs_da3_swap_lastblock( error = xfs_da3_node_read(tp, dp, sib_blkno, &sib_buf, w); if (error) goto done; + fa = xfs_da3_header_check(sib_buf, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(sib_buf, fa); + xfs_da_mark_sick(args); + error = -EFSCORRUPTED; + goto done; + } sib_info = sib_buf->b_addr; if (XFS_IS_CORRUPT(mp, be32_to_cpu(sib_info->forw) != last_blkno || sib_info->magic != dead_info->magic)) { + xfs_da_mark_sick(args); error = -EFSCORRUPTED; goto done; } @@ -2371,10 +2522,18 @@ xfs_da3_swap_lastblock( error = xfs_da3_node_read(tp, dp, sib_blkno, &sib_buf, w); if (error) goto done; + fa = xfs_da3_header_check(sib_buf, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(sib_buf, fa); + xfs_da_mark_sick(args); + error = -EFSCORRUPTED; + goto done; + } sib_info = sib_buf->b_addr; if (XFS_IS_CORRUPT(mp, be32_to_cpu(sib_info->back) != last_blkno || sib_info->magic != dead_info->magic)) { + xfs_da_mark_sick(args); error = -EFSCORRUPTED; goto done; } @@ -2393,10 +2552,18 @@ xfs_da3_swap_lastblock( error = xfs_da3_node_read(tp, dp, par_blkno, &par_buf, w); if (error) goto done; + fa = xfs_da3_node_header_check(par_buf, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(par_buf, fa); + xfs_da_mark_sick(args); + error = -EFSCORRUPTED; + goto done; + } par_node = par_buf->b_addr; xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node); if (XFS_IS_CORRUPT(mp, level >= 0 && level != par_hdr.level + 1)) { + xfs_da_mark_sick(args); error = -EFSCORRUPTED; goto done; } @@ -2408,6 +2575,7 @@ xfs_da3_swap_lastblock( entno++) continue; if (XFS_IS_CORRUPT(mp, entno == par_hdr.count)) { + xfs_da_mark_sick(args); error = -EFSCORRUPTED; goto done; } @@ -2433,15 +2601,24 @@ xfs_da3_swap_lastblock( xfs_trans_brelse(tp, par_buf); par_buf = NULL; if (XFS_IS_CORRUPT(mp, par_blkno == 0)) { + xfs_da_mark_sick(args); error = -EFSCORRUPTED; goto done; } error = xfs_da3_node_read(tp, dp, par_blkno, &par_buf, w); if (error) goto done; + fa = xfs_da3_node_header_check(par_buf, args->owner); + if (fa) { + __xfs_buf_mark_corrupt(par_buf, fa); + xfs_da_mark_sick(args); + error = -EFSCORRUPTED; + goto done; + } par_node = par_buf->b_addr; xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node); if (XFS_IS_CORRUPT(mp, par_hdr.level != level)) { + xfs_da_mark_sick(args); error = -EFSCORRUPTED; goto done; } @@ -2525,7 +2702,8 @@ xfs_dabuf_map( int error = 0, nirecs, i; if (nfsb > 1) - irecs = kmem_zalloc(sizeof(irec) * nfsb, KM_NOFS); + irecs = kzalloc(sizeof(irec) * nfsb, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); nirecs = nfsb; error = xfs_bmapi_read(dp, bno, nfsb, irecs, &nirecs, @@ -2538,7 +2716,8 @@ xfs_dabuf_map( * larger one that needs to be free by the caller. */ if (nirecs > 1) { - map = kmem_zalloc(nirecs * sizeof(struct xfs_buf_map), KM_NOFS); + map = kzalloc(nirecs * sizeof(struct xfs_buf_map), + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); if (!map) { error = -ENOMEM; goto out_free_irecs; @@ -2564,12 +2743,13 @@ xfs_dabuf_map( *nmaps = nirecs; out_free_irecs: if (irecs != &irec) - kmem_free(irecs); + kfree(irecs); return error; invalid_mapping: /* Caller ok with no mapping. */ if (XFS_IS_CORRUPT(mp, !(flags & XFS_DABUF_MAP_HOLE_OK))) { + xfs_dirattr_mark_sick(dp, whichfork); error = -EFSCORRUPTED; if (xfs_error_level >= XFS_ERRLEVEL_LOW) { xfs_alert(mp, "%s: bno %u inode %llu", @@ -2620,7 +2800,7 @@ xfs_da_get_buf( out_free: if (mapp != &map) - kmem_free(mapp); + kfree(mapp); return error; } @@ -2651,6 +2831,14 @@ xfs_da_read_buf( error = xfs_trans_read_buf_map(mp, tp, mp->m_ddev_targp, mapp, nmap, 0, &bp, ops); + if (xfs_metadata_is_sick(error)) + xfs_dirattr_mark_sick(dp, whichfork); + /* + * ENODATA from disk implies a disk medium failure; ENODATA for + * xattrs means attribute not found, so disambiguate that here. + */ + if (error == -ENODATA && whichfork == XFS_ATTR_FORK) + error = -EIO; if (error) goto out_free; @@ -2661,7 +2849,7 @@ xfs_da_read_buf( *bpp = bp; out_free: if (mapp != &map) - kmem_free(mapp); + kfree(mapp); return error; } @@ -2692,7 +2880,7 @@ xfs_da_reada_buf( out_free: if (mapp != &map) - kmem_free(mapp); + kfree(mapp); return error; } diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h index ffa3df5b2893..354d5d65043e 100644 --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -54,17 +54,24 @@ enum xfs_dacmp { */ typedef struct xfs_da_args { struct xfs_da_geometry *geo; /* da block geometry */ - const uint8_t *name; /* string (maybe not NULL terminated) */ - int namelen; /* length of string (maybe no NULL) */ - uint8_t filetype; /* filetype of inode for directories */ + const uint8_t *name; /* string (maybe not NULL terminated) */ + const uint8_t *new_name; /* new attr name */ void *value; /* set of bytes (maybe contain NULLs) */ - int valuelen; /* length of value */ - unsigned int attr_filter; /* XFS_ATTR_{ROOT,SECURE,INCOMPLETE} */ - unsigned int attr_flags; /* XATTR_{CREATE,REPLACE} */ - xfs_dahash_t hashval; /* hash value of name */ - xfs_ino_t inumber; /* input/output inode number */ + void *new_value; /* new xattr value (may contain NULLs) */ struct xfs_inode *dp; /* directory inode to manipulate */ struct xfs_trans *trans; /* current trans (changes over time) */ + + xfs_ino_t inumber; /* input/output inode number */ + xfs_ino_t owner; /* inode that owns the dir/attr data */ + + int valuelen; /* length of value */ + int new_valuelen; /* length of new_value */ + uint8_t filetype; /* filetype of inode for directories */ + uint8_t op_flags; /* operation flags */ + uint8_t attr_filter; /* XFS_ATTR_{ROOT,SECURE,INCOMPLETE} */ + short namelen; /* length of string (maybe no NULL) */ + short new_namelen; /* length of new attr name */ + xfs_dahash_t hashval; /* hash value of name */ xfs_extlen_t total; /* total blocks needed, for 1st bmap */ int whichfork; /* data or attribute fork */ xfs_dablk_t blkno; /* blkno of attr leaf of interest */ @@ -77,7 +84,6 @@ typedef struct xfs_da_args { xfs_dablk_t rmtblkno2; /* remote attr value starting blkno */ int rmtblkcnt2; /* remote attr value block count */ int rmtvaluelen2; /* remote attr value length in bytes */ - uint32_t op_flags; /* operation flags */ enum xfs_dacmp cmpresult; /* name compare result for lookups */ } xfs_da_args_t; @@ -89,10 +95,8 @@ typedef struct xfs_da_args { #define XFS_DA_OP_ADDNAME (1u << 2) /* this is an add operation */ #define XFS_DA_OP_OKNOENT (1u << 3) /* lookup op, ENOENT ok, else die */ #define XFS_DA_OP_CILOOKUP (1u << 4) /* lookup returns CI name if found */ -#define XFS_DA_OP_NOTIME (1u << 5) /* don't update inode timestamps */ -#define XFS_DA_OP_REMOVE (1u << 6) /* this is a remove operation */ -#define XFS_DA_OP_RECOVERY (1u << 7) /* Log recovery operation */ -#define XFS_DA_OP_LOGGED (1u << 8) /* Use intent items to track op */ +#define XFS_DA_OP_RECOVERY (1u << 5) /* Log recovery operation */ +#define XFS_DA_OP_LOGGED (1u << 6) /* Use intent items to track op */ #define XFS_DA_OP_FLAGS \ { XFS_DA_OP_JUSTCHECK, "JUSTCHECK" }, \ @@ -100,8 +104,6 @@ typedef struct xfs_da_args { { XFS_DA_OP_ADDNAME, "ADDNAME" }, \ { XFS_DA_OP_OKNOENT, "OKNOENT" }, \ { XFS_DA_OP_CILOOKUP, "CILOOKUP" }, \ - { XFS_DA_OP_NOTIME, "NOTIME" }, \ - { XFS_DA_OP_REMOVE, "REMOVE" }, \ { XFS_DA_OP_RECOVERY, "RECOVERY" }, \ { XFS_DA_OP_LOGGED, "LOGGED" } @@ -219,6 +221,8 @@ int xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno, const struct xfs_buf_ops *ops); int xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno, struct xfs_buf *dead_buf); +void xfs_da_buf_copy(struct xfs_buf *dst, struct xfs_buf *src, + size_t size); uint xfs_da_hashname(const uint8_t *name_string, int name_length); enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args, @@ -233,6 +237,8 @@ void xfs_da3_node_hdr_from_disk(struct xfs_mount *mp, struct xfs_da3_icnode_hdr *to, struct xfs_da_intnode *from); void xfs_da3_node_hdr_to_disk(struct xfs_mount *mp, struct xfs_da_intnode *to, struct xfs_da3_icnode_hdr *from); +xfs_failaddr_t xfs_da3_header_check(struct xfs_buf *bp, xfs_ino_t owner); +xfs_failaddr_t xfs_da3_node_header_check(struct xfs_buf *bp, xfs_ino_t owner); extern struct kmem_cache *xfs_da_state_cache; diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h index 25e2841084e1..86de99e2f757 100644 --- a/fs/xfs/libxfs/xfs_da_format.h +++ b/fs/xfs/libxfs/xfs_da_format.h @@ -159,6 +159,17 @@ struct xfs_da3_intnode { #define XFS_DIR3_FT_MAX 9 +#define XFS_DIR3_FTYPE_STR \ + { XFS_DIR3_FT_UNKNOWN, "unknown" }, \ + { XFS_DIR3_FT_REG_FILE, "file" }, \ + { XFS_DIR3_FT_DIR, "directory" }, \ + { XFS_DIR3_FT_CHRDEV, "char" }, \ + { XFS_DIR3_FT_BLKDEV, "block" }, \ + { XFS_DIR3_FT_FIFO, "fifo" }, \ + { XFS_DIR3_FT_SOCK, "sock" }, \ + { XFS_DIR3_FT_SYMLINK, "symlink" }, \ + { XFS_DIR3_FT_WHT, "whiteout" } + /* * Byte offset in data block and shortform entry. */ @@ -578,20 +589,25 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp) #define XFS_ATTR_LEAF_MAPSIZE 3 /* how many freespace slots */ /* - * Entries are packed toward the top as tight as possible. - */ -struct xfs_attr_shortform { - struct xfs_attr_sf_hdr { /* constant-structure header block */ - __be16 totsize; /* total bytes in shortform list */ - __u8 count; /* count of active entries */ - __u8 padding; - } hdr; - struct xfs_attr_sf_entry { - uint8_t namelen; /* actual length of name (no NULL) */ - uint8_t valuelen; /* actual length of value (no NULL) */ - uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */ - uint8_t nameval[]; /* name & value bytes concatenated */ - } list[1]; /* variable sized array */ + * Attribute storage when stored inside the inode. + * + * Small attribute lists are packed as tightly as possible so as to fit into the + * literal area of the inode. + * + * These "shortform" attribute forks consist of a single xfs_attr_sf_hdr header + * followed by zero or more xfs_attr_sf_entry structures. + */ +struct xfs_attr_sf_hdr { /* constant-structure header block */ + __be16 totsize; /* total bytes in shortform list */ + __u8 count; /* count of active entries */ + __u8 padding; +}; + +struct xfs_attr_sf_entry { + __u8 namelen; /* actual length of name (no NULL) */ + __u8 valuelen; /* actual length of value (no NULL) */ + __u8 flags; /* flags bits (XFS_ATTR_*) */ + __u8 nameval[]; /* name & value bytes concatenated */ }; typedef struct xfs_attr_leaf_map { /* RLE map of free bytes */ @@ -620,19 +636,29 @@ typedef struct xfs_attr_leaf_entry { /* sorted on key, not name */ typedef struct xfs_attr_leaf_name_local { __be16 valuelen; /* number of bytes in value */ __u8 namelen; /* length of name bytes */ - __u8 nameval[1]; /* name/value bytes */ + /* + * In Linux 6.5 this flex array was converted from nameval[1] to + * nameval[]. Be very careful here about extra padding at the end; + * see xfs_attr_leaf_entsize_local() for details. + */ + __u8 nameval[]; /* name/value bytes */ } xfs_attr_leaf_name_local_t; typedef struct xfs_attr_leaf_name_remote { __be32 valueblk; /* block number of value bytes */ __be32 valuelen; /* number of bytes in value */ __u8 namelen; /* length of name bytes */ - __u8 name[1]; /* name bytes */ + /* + * In Linux 6.5 this flex array was converted from name[1] to name[]. + * Be very careful here about extra padding at the end; see + * xfs_attr_leaf_entsize_remote() for details. + */ + __u8 name[]; /* name bytes */ } xfs_attr_leaf_name_remote_t; typedef struct xfs_attr_leafblock { xfs_attr_leaf_hdr_t hdr; /* constant-structure header block */ - xfs_attr_leaf_entry_t entries[1]; /* sorted on key, not name */ + xfs_attr_leaf_entry_t entries[]; /* sorted on key, not name */ /* * The rest of the block contains the following structures after the * leaf entries, growing from the bottom up. The variables are never @@ -664,7 +690,7 @@ struct xfs_attr3_leaf_hdr { struct xfs_attr3_leafblock { struct xfs_attr3_leaf_hdr hdr; - struct xfs_attr_leaf_entry entries[1]; + struct xfs_attr_leaf_entry entries[]; /* * The rest of the block contains the following structures after the @@ -688,12 +714,30 @@ struct xfs_attr3_leafblock { #define XFS_ATTR_LOCAL_BIT 0 /* attr is stored locally */ #define XFS_ATTR_ROOT_BIT 1 /* limit access to trusted attrs */ #define XFS_ATTR_SECURE_BIT 2 /* limit access to secure attrs */ +#define XFS_ATTR_PARENT_BIT 3 /* parent pointer attrs */ #define XFS_ATTR_INCOMPLETE_BIT 7 /* attr in middle of create/delete */ #define XFS_ATTR_LOCAL (1u << XFS_ATTR_LOCAL_BIT) #define XFS_ATTR_ROOT (1u << XFS_ATTR_ROOT_BIT) #define XFS_ATTR_SECURE (1u << XFS_ATTR_SECURE_BIT) +#define XFS_ATTR_PARENT (1u << XFS_ATTR_PARENT_BIT) #define XFS_ATTR_INCOMPLETE (1u << XFS_ATTR_INCOMPLETE_BIT) -#define XFS_ATTR_NSP_ONDISK_MASK (XFS_ATTR_ROOT | XFS_ATTR_SECURE) + +#define XFS_ATTR_NSP_ONDISK_MASK (XFS_ATTR_ROOT | \ + XFS_ATTR_SECURE | \ + XFS_ATTR_PARENT) + +/* Private attr namespaces not exposed to userspace */ +#define XFS_ATTR_PRIVATE_NSP_MASK (XFS_ATTR_PARENT) + +#define XFS_ATTR_ONDISK_MASK (XFS_ATTR_NSP_ONDISK_MASK | \ + XFS_ATTR_LOCAL | \ + XFS_ATTR_INCOMPLETE) + +#define XFS_ATTR_NAMESPACE_STR \ + { XFS_ATTR_LOCAL, "local" }, \ + { XFS_ATTR_ROOT, "root" }, \ + { XFS_ATTR_SECURE, "secure" }, \ + { XFS_ATTR_PARENT, "parent" } /* * Alignment for namelist and valuelist entries (since they are mixed @@ -747,14 +791,61 @@ xfs_attr3_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx) */ static inline int xfs_attr_leaf_entsize_remote(int nlen) { - return round_up(sizeof(struct xfs_attr_leaf_name_remote) - 1 + - nlen, XFS_ATTR_LEAF_NAME_ALIGN); + /* + * Prior to Linux 6.5, struct xfs_attr_leaf_name_remote ended with + * name[1], which was used as a flexarray. The layout of this struct + * is 9 bytes of fixed-length fields followed by a __u8 flex array at + * offset 9. + * + * On most architectures, struct xfs_attr_leaf_name_remote had two + * bytes of implicit padding at the end of the struct to make the + * struct length 12. After converting name[1] to name[], there are + * three implicit padding bytes and the struct size remains 12. + * However, there are compiler configurations that do not add implicit + * padding at all (m68k) and have been broken for years. + * + * This entsize computation historically added (the xattr name length) + * to (the padded struct length - 1) and rounded that sum up to the + * nearest multiple of 4 (NAME_ALIGN). IOWs, round_up(11 + nlen, 4). + * This is encoded in the ondisk format, so we cannot change this. + * + * Compute the entsize from offsetof of the flexarray and manually + * adding bytes for the implicit padding. + */ + const size_t remotesize = + offsetof(struct xfs_attr_leaf_name_remote, name) + 2; + + return round_up(remotesize + nlen, XFS_ATTR_LEAF_NAME_ALIGN); } static inline int xfs_attr_leaf_entsize_local(int nlen, int vlen) { - return round_up(sizeof(struct xfs_attr_leaf_name_local) - 1 + - nlen + vlen, XFS_ATTR_LEAF_NAME_ALIGN); + /* + * Prior to Linux 6.5, struct xfs_attr_leaf_name_local ended with + * nameval[1], which was used as a flexarray. The layout of this + * struct is 3 bytes of fixed-length fields followed by a __u8 flex + * array at offset 3. + * + * struct xfs_attr_leaf_name_local had zero bytes of implicit padding + * at the end of the struct to make the struct length 4. On most + * architectures, after converting nameval[1] to nameval[], there is + * one implicit padding byte and the struct size remains 4. However, + * there are compiler configurations that do not add implicit padding + * at all (m68k) and would break. + * + * This entsize computation historically added (the xattr name and + * value length) to (the padded struct length - 1) and rounded that sum + * up to the nearest multiple of 4 (NAME_ALIGN). IOWs, the formula is + * round_up(3 + nlen + vlen, 4). This is encoded in the ondisk format, + * so we cannot change this. + * + * Compute the entsize from offsetof of the flexarray and manually + * adding bytes for the implicit padding. + */ + const size_t localsize = + offsetof(struct xfs_attr_leaf_name_local, nameval); + + return round_up(localsize + nlen + vlen, XFS_ATTR_LEAF_NAME_ALIGN); } static inline int xfs_attr_leaf_entsize_local_max(int bsize) @@ -789,9 +880,7 @@ struct xfs_attr3_rmt_hdr { #define XFS_ATTR3_RMT_CRC_OFF offsetof(struct xfs_attr3_rmt_hdr, rm_crc) -#define XFS_ATTR3_RMT_BUF_SPACE(mp, bufsize) \ - ((bufsize) - (xfs_has_crc((mp)) ? \ - sizeof(struct xfs_attr3_rmt_hdr) : 0)) +unsigned int xfs_attr3_rmt_buf_space(struct xfs_mount *mp); /* Number of bytes in a directory block. */ static inline unsigned int xfs_dir2_dirblock_bytes(struct xfs_sb *sbp) @@ -802,4 +891,17 @@ static inline unsigned int xfs_dir2_dirblock_bytes(struct xfs_sb *sbp) xfs_failaddr_t xfs_da3_blkinfo_verify(struct xfs_buf *bp, struct xfs_da3_blkinfo *hdr3); +/* + * Parent pointer attribute format definition + * + * The xattr name contains the dirent name. + * The xattr value encodes the parent inode number and generation to ease + * opening parents by handle. + * The xattr hashval is xfs_dir2_namehash() ^ p_ino + */ +struct xfs_parent_rec { + __be64 p_ino; + __be32 p_gen; +} __packed; + #endif /* __XFS_DA_FORMAT_H__ */ diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 5a321b783398..5b377cbbb1f7 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -12,12 +12,14 @@ #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_trans.h" +#include "xfs_trans_priv.h" #include "xfs_buf_item.h" #include "xfs_inode.h" #include "xfs_inode_item.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_log.h" +#include "xfs_log_priv.h" #include "xfs_rmap.h" #include "xfs_refcount.h" #include "xfs_bmap.h" @@ -26,6 +28,7 @@ #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_attr.h" +#include "xfs_exchmaps.h" static struct kmem_cache *xfs_defer_pending_cache; @@ -181,16 +184,89 @@ static struct kmem_cache *xfs_defer_pending_cache; * Note that the continuation requested between t2 and t3 is likely to * reoccur. */ +STATIC struct xfs_log_item * +xfs_defer_barrier_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return NULL; +} + +STATIC void +xfs_defer_barrier_abort_intent( + struct xfs_log_item *intent) +{ + /* empty */ +} -static const struct xfs_defer_op_type *defer_op_types[] = { - [XFS_DEFER_OPS_TYPE_BMAP] = &xfs_bmap_update_defer_type, - [XFS_DEFER_OPS_TYPE_REFCOUNT] = &xfs_refcount_update_defer_type, - [XFS_DEFER_OPS_TYPE_RMAP] = &xfs_rmap_update_defer_type, - [XFS_DEFER_OPS_TYPE_FREE] = &xfs_extent_free_defer_type, - [XFS_DEFER_OPS_TYPE_AGFL_FREE] = &xfs_agfl_free_defer_type, - [XFS_DEFER_OPS_TYPE_ATTR] = &xfs_attr_defer_type, +STATIC struct xfs_log_item * +xfs_defer_barrier_create_done( + struct xfs_trans *tp, + struct xfs_log_item *intent, + unsigned int count) +{ + return NULL; +} + +STATIC int +xfs_defer_barrier_finish_item( + struct xfs_trans *tp, + struct xfs_log_item *done, + struct list_head *item, + struct xfs_btree_cur **state) +{ + ASSERT(0); + return -EFSCORRUPTED; +} + +STATIC void +xfs_defer_barrier_cancel_item( + struct list_head *item) +{ + ASSERT(0); +} + +static const struct xfs_defer_op_type xfs_barrier_defer_type = { + .max_items = 1, + .create_intent = xfs_defer_barrier_create_intent, + .abort_intent = xfs_defer_barrier_abort_intent, + .create_done = xfs_defer_barrier_create_done, + .finish_item = xfs_defer_barrier_finish_item, + .cancel_item = xfs_defer_barrier_cancel_item, }; +/* Create a log intent done item for a log intent item. */ +static inline void +xfs_defer_create_done( + struct xfs_trans *tp, + struct xfs_defer_pending *dfp) +{ + struct xfs_log_item *lip; + + /* If there is no log intent item, there can be no log done item. */ + if (!dfp->dfp_intent) + return; + + /* + * Mark the transaction dirty, even on error. This ensures the + * transaction is aborted, which: + * + * 1.) releases the log intent item and frees the log done item + * 2.) shuts down the filesystem + */ + tp->t_flags |= XFS_TRANS_DIRTY; + lip = dfp->dfp_ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count); + if (!lip) + return; + + tp->t_flags |= XFS_TRANS_HAS_INTENT_DONE; + xfs_trans_add_item(tp, lip); + set_bit(XFS_LI_DIRTY, &lip->li_flags); + dfp->dfp_done = lip; +} + /* * Ensure there's a log intent item associated with this deferred work item if * the operation must be restarted on crash. Returns 1 if there's a log item; @@ -202,18 +278,21 @@ xfs_defer_create_intent( struct xfs_defer_pending *dfp, bool sort) { - const struct xfs_defer_op_type *ops = defer_op_types[dfp->dfp_type]; struct xfs_log_item *lip; if (dfp->dfp_intent) return 1; - lip = ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count, sort); + lip = dfp->dfp_ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count, + sort); if (!lip) return 0; if (IS_ERR(lip)) return PTR_ERR(lip); + tp->t_flags |= XFS_TRANS_DIRTY; + xfs_trans_add_item(tp, lip); + set_bit(XFS_LI_DIRTY, &lip->li_flags); dfp->dfp_intent = lip; return 1; } @@ -245,26 +324,60 @@ xfs_defer_create_intents( return ret; } +static inline void +xfs_defer_pending_abort( + struct xfs_mount *mp, + struct xfs_defer_pending *dfp) +{ + trace_xfs_defer_pending_abort(mp, dfp); + + if (dfp->dfp_intent && !dfp->dfp_done) { + dfp->dfp_ops->abort_intent(dfp->dfp_intent); + dfp->dfp_intent = NULL; + } +} + +static inline void +xfs_defer_pending_cancel_work( + struct xfs_mount *mp, + struct xfs_defer_pending *dfp) +{ + struct list_head *pwi; + struct list_head *n; + + trace_xfs_defer_cancel_list(mp, dfp); + + list_del(&dfp->dfp_list); + list_for_each_safe(pwi, n, &dfp->dfp_work) { + list_del(pwi); + dfp->dfp_count--; + trace_xfs_defer_cancel_item(mp, dfp, pwi); + dfp->dfp_ops->cancel_item(pwi); + } + ASSERT(dfp->dfp_count == 0); + kmem_cache_free(xfs_defer_pending_cache, dfp); +} + +STATIC void +xfs_defer_pending_abort_list( + struct xfs_mount *mp, + struct list_head *dop_list) +{ + struct xfs_defer_pending *dfp; + + /* Abort intent items that don't have a done item. */ + list_for_each_entry(dfp, dop_list, dfp_list) + xfs_defer_pending_abort(mp, dfp); +} + /* Abort all the intents that were committed. */ STATIC void xfs_defer_trans_abort( struct xfs_trans *tp, struct list_head *dop_pending) { - struct xfs_defer_pending *dfp; - const struct xfs_defer_op_type *ops; - trace_xfs_defer_trans_abort(tp, _RET_IP_); - - /* Abort intent items that don't have a done item. */ - list_for_each_entry(dfp, dop_pending, dfp_list) { - ops = defer_op_types[dfp->dfp_type]; - trace_xfs_defer_pending_abort(tp->t_mountp, dfp); - if (dfp->dfp_intent && !dfp->dfp_done) { - ops->abort_intent(dfp->dfp_intent); - dfp->dfp_intent = NULL; - } - } + xfs_defer_pending_abort_list(tp->t_mountp, dop_pending); } /* @@ -382,26 +495,31 @@ xfs_defer_cancel_list( { struct xfs_defer_pending *dfp; struct xfs_defer_pending *pli; - struct list_head *pwi; - struct list_head *n; - const struct xfs_defer_op_type *ops; /* * Free the pending items. Caller should already have arranged * for the intent items to be released. */ - list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) { - ops = defer_op_types[dfp->dfp_type]; - trace_xfs_defer_cancel_list(mp, dfp); - list_del(&dfp->dfp_list); - list_for_each_safe(pwi, n, &dfp->dfp_work) { - list_del(pwi); - dfp->dfp_count--; - ops->cancel_item(pwi); - } - ASSERT(dfp->dfp_count == 0); - kmem_cache_free(xfs_defer_pending_cache, dfp); + list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) + xfs_defer_pending_cancel_work(mp, dfp); +} + +static inline void +xfs_defer_relog_intent( + struct xfs_trans *tp, + struct xfs_defer_pending *dfp) +{ + struct xfs_log_item *lip; + + xfs_defer_create_done(tp, dfp); + + lip = dfp->dfp_ops->relog_intent(tp, dfp->dfp_intent, dfp->dfp_done); + if (lip) { + xfs_trans_add_item(tp, lip); + set_bit(XFS_LI_DIRTY, &lip->li_flags); } + dfp->dfp_done = NULL; + dfp->dfp_intent = lip; } /* @@ -409,7 +527,7 @@ xfs_defer_cancel_list( * done item to release the intent item; and then log a new intent item. * The caller should provide a fresh transaction and roll it after we're done. */ -static int +static void xfs_defer_relog( struct xfs_trans **tpp, struct list_head *dfops) @@ -439,7 +557,7 @@ xfs_defer_relog( * the log threshold once per call. */ if (threshold_lsn == NULLCOMMITLSN) { - threshold_lsn = xlog_grant_push_threshold(log, 0); + threshold_lsn = xfs_ail_get_push_target(log->l_ailp); if (threshold_lsn == NULLCOMMITLSN) break; } @@ -448,34 +566,32 @@ xfs_defer_relog( trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp); XFS_STATS_INC((*tpp)->t_mountp, defer_relog); - dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent, *tpp); - } - if ((*tpp)->t_flags & XFS_TRANS_DIRTY) - return xfs_defer_trans_roll(tpp); - return 0; + xfs_defer_relog_intent(*tpp, dfp); + } } /* * Log an intent-done item for the first pending intent, and finish the work * items. */ -static int +int xfs_defer_finish_one( struct xfs_trans *tp, struct xfs_defer_pending *dfp) { - const struct xfs_defer_op_type *ops = defer_op_types[dfp->dfp_type]; + const struct xfs_defer_op_type *ops = dfp->dfp_ops; struct xfs_btree_cur *state = NULL; struct list_head *li, *n; int error; trace_xfs_defer_pending_finish(tp->t_mountp, dfp); - dfp->dfp_done = ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count); + xfs_defer_create_done(tp, dfp); list_for_each_safe(li, n, &dfp->dfp_work) { list_del(li); dfp->dfp_count--; + trace_xfs_defer_finish_item(tp->t_mountp, dfp, li); error = ops->finish_item(tp, dfp->dfp_done, li, &state); if (error == -EAGAIN) { int ret; @@ -508,6 +624,24 @@ out: return error; } +/* Move all paused deferred work from @tp to @paused_list. */ +static void +xfs_defer_isolate_paused( + struct xfs_trans *tp, + struct list_head *paused_list) +{ + struct xfs_defer_pending *dfp; + struct xfs_defer_pending *pli; + + list_for_each_entry_safe(dfp, pli, &tp->t_dfops, dfp_list) { + if (!(dfp->dfp_flags & XFS_DEFER_PAUSED)) + continue; + + list_move_tail(&dfp->dfp_list, paused_list); + trace_xfs_defer_isolate_paused(tp->t_mountp, dfp); + } +} + /* * Finish all the pending work. This involves logging intent items for * any work items that wandered in since the last transaction roll (if @@ -523,6 +657,7 @@ xfs_defer_finish_noroll( struct xfs_defer_pending *dfp = NULL; int error = 0; LIST_HEAD(dop_pending); + LIST_HEAD(dop_paused); ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES); @@ -541,6 +676,8 @@ xfs_defer_finish_noroll( */ int has_intents = xfs_defer_create_intents(*tp); + xfs_defer_isolate_paused(*tp, &dop_paused); + list_splice_init(&(*tp)->t_dfops, &dop_pending); if (has_intents < 0) { @@ -553,22 +690,33 @@ xfs_defer_finish_noroll( goto out_shutdown; /* Relog intent items to keep the log moving. */ - error = xfs_defer_relog(tp, &dop_pending); - if (error) - goto out_shutdown; + xfs_defer_relog(tp, &dop_pending); + xfs_defer_relog(tp, &dop_paused); + + if ((*tp)->t_flags & XFS_TRANS_DIRTY) { + error = xfs_defer_trans_roll(tp); + if (error) + goto out_shutdown; + } } - dfp = list_first_entry(&dop_pending, struct xfs_defer_pending, - dfp_list); + dfp = list_first_entry_or_null(&dop_pending, + struct xfs_defer_pending, dfp_list); + if (!dfp) + break; error = xfs_defer_finish_one(*tp, dfp); if (error && error != -EAGAIN) goto out_shutdown; } + /* Requeue the paused items in the outgoing transaction. */ + list_splice_tail_init(&dop_paused, &(*tp)->t_dfops); + trace_xfs_defer_finish_done(*tp, _RET_IP_); return 0; out_shutdown: + list_splice_tail_init(&dop_paused, &dop_pending); xfs_defer_trans_abort(*tp, &dop_pending); xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); trace_xfs_defer_finish_error(*tp, error); @@ -581,6 +729,9 @@ int xfs_defer_finish( struct xfs_trans **tp) { +#ifdef DEBUG + struct xfs_defer_pending *dfp; +#endif int error; /* @@ -600,7 +751,10 @@ xfs_defer_finish( } /* Reset LOWMODE now that we've finished all the dfops. */ - ASSERT(list_empty(&(*tp)->t_dfops)); +#ifdef DEBUG + list_for_each_entry(dfp, &(*tp)->t_dfops, dfp_list) + ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED); +#endif (*tp)->t_flags &= ~XFS_TRANS_LOWMODE; return 0; } @@ -612,48 +766,166 @@ xfs_defer_cancel( struct xfs_mount *mp = tp->t_mountp; trace_xfs_defer_cancel(tp, _RET_IP_); + xfs_defer_trans_abort(tp, &tp->t_dfops); xfs_defer_cancel_list(mp, &tp->t_dfops); } +/* + * Return the last pending work item attached to this transaction if it matches + * the deferred op type. + */ +static inline struct xfs_defer_pending * +xfs_defer_find_last( + struct xfs_trans *tp, + const struct xfs_defer_op_type *ops) +{ + struct xfs_defer_pending *dfp = NULL; + + /* No dfops at all? */ + if (list_empty(&tp->t_dfops)) + return NULL; + + dfp = list_last_entry(&tp->t_dfops, struct xfs_defer_pending, + dfp_list); + + /* Wrong type? */ + if (dfp->dfp_ops != ops) + return NULL; + return dfp; +} + +/* + * Decide if we can add a deferred work item to the last dfops item attached + * to the transaction. + */ +static inline bool +xfs_defer_can_append( + struct xfs_defer_pending *dfp, + const struct xfs_defer_op_type *ops) +{ + /* Already logged? */ + if (dfp->dfp_intent) + return false; + + /* Paused items cannot absorb more work */ + if (dfp->dfp_flags & XFS_DEFER_PAUSED) + return NULL; + + /* Already full? */ + if (ops->max_items && dfp->dfp_count >= ops->max_items) + return false; + + return true; +} + +/* Create a new pending item at the end of the transaction list. */ +static inline struct xfs_defer_pending * +xfs_defer_alloc( + struct list_head *dfops, + const struct xfs_defer_op_type *ops) +{ + struct xfs_defer_pending *dfp; + + dfp = kmem_cache_zalloc(xfs_defer_pending_cache, + GFP_KERNEL | __GFP_NOFAIL); + dfp->dfp_ops = ops; + INIT_LIST_HEAD(&dfp->dfp_work); + list_add_tail(&dfp->dfp_list, dfops); + + return dfp; +} + /* Add an item for later deferred processing. */ -void +struct xfs_defer_pending * xfs_defer_add( struct xfs_trans *tp, - enum xfs_defer_ops_type type, - struct list_head *li) + struct list_head *li, + const struct xfs_defer_op_type *ops) { struct xfs_defer_pending *dfp = NULL; - const struct xfs_defer_op_type *ops; ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); - BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX); - /* - * Add the item to a pending item at the end of the intake list. - * If the last pending item has the same type, reuse it. Else, - * create a new pending item at the end of the intake list. - */ - if (!list_empty(&tp->t_dfops)) { - dfp = list_last_entry(&tp->t_dfops, - struct xfs_defer_pending, dfp_list); - ops = defer_op_types[dfp->dfp_type]; - if (dfp->dfp_type != type || - (ops->max_items && dfp->dfp_count >= ops->max_items)) - dfp = NULL; - } - if (!dfp) { - dfp = kmem_cache_zalloc(xfs_defer_pending_cache, - GFP_NOFS | __GFP_NOFAIL); - dfp->dfp_type = type; - dfp->dfp_intent = NULL; - dfp->dfp_done = NULL; - dfp->dfp_count = 0; - INIT_LIST_HEAD(&dfp->dfp_work); - list_add_tail(&dfp->dfp_list, &tp->t_dfops); + if (!ops->finish_item) { + ASSERT(ops->finish_item != NULL); + xfs_force_shutdown(tp->t_mountp, SHUTDOWN_CORRUPT_INCORE); + return NULL; } - list_add_tail(li, &dfp->dfp_work); - dfp->dfp_count++; + dfp = xfs_defer_find_last(tp, ops); + if (!dfp || !xfs_defer_can_append(dfp, ops)) + dfp = xfs_defer_alloc(&tp->t_dfops, ops); + + xfs_defer_add_item(dfp, li); + trace_xfs_defer_add_item(tp->t_mountp, dfp, li); + return dfp; +} + +/* + * Add a defer ops barrier to force two otherwise adjacent deferred work items + * to be tracked separately and have separate log items. + */ +void +xfs_defer_add_barrier( + struct xfs_trans *tp) +{ + struct xfs_defer_pending *dfp; + + ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); + + /* If the last defer op added was a barrier, we're done. */ + dfp = xfs_defer_find_last(tp, &xfs_barrier_defer_type); + if (dfp) + return; + + xfs_defer_alloc(&tp->t_dfops, &xfs_barrier_defer_type); + + trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL); +} + +/* + * Create a pending deferred work item to replay the recovered intent item + * and add it to the list. + */ +void +xfs_defer_start_recovery( + struct xfs_log_item *lip, + struct list_head *r_dfops, + const struct xfs_defer_op_type *ops) +{ + struct xfs_defer_pending *dfp = xfs_defer_alloc(r_dfops, ops); + + dfp->dfp_intent = lip; +} + +/* + * Cancel a deferred work item created to recover a log intent item. @dfp + * will be freed after this function returns. + */ +void +xfs_defer_cancel_recovery( + struct xfs_mount *mp, + struct xfs_defer_pending *dfp) +{ + xfs_defer_pending_abort(mp, dfp); + xfs_defer_pending_cancel_work(mp, dfp); +} + +/* Replay the deferred work item created from a recovered log intent item. */ +int +xfs_defer_finish_recovery( + struct xfs_mount *mp, + struct xfs_defer_pending *dfp, + struct list_head *capture_list) +{ + const struct xfs_defer_op_type *ops = dfp->dfp_ops; + int error; + + /* dfp is freed by recover_work and must not be accessed afterwards */ + error = ops->recover_work(dfp, capture_list); + if (error) + trace_xlog_intent_recovery_failed(mp, ops, error); + return error; } /* @@ -710,7 +982,7 @@ xfs_defer_ops_capture( return ERR_PTR(error); /* Create an object to capture the defer ops. */ - dfc = kmem_zalloc(sizeof(*dfc), KM_NOFS); + dfc = kzalloc(sizeof(*dfc), GFP_KERNEL | __GFP_NOFAIL); INIT_LIST_HEAD(&dfc->dfc_list); INIT_LIST_HEAD(&dfc->dfc_dfops); @@ -742,7 +1014,7 @@ xfs_defer_ops_capture( * transaction. */ for (i = 0; i < dfc->dfc_held.dr_inos; i++) { - ASSERT(xfs_isilocked(dfc->dfc_held.dr_ip[i], XFS_ILOCK_EXCL)); + xfs_assert_ilocked(dfc->dfc_held.dr_ip[i], XFS_ILOCK_EXCL); ihold(VFS_I(dfc->dfc_held.dr_ip[i])); } @@ -754,12 +1026,13 @@ xfs_defer_ops_capture( /* Release all resources that we used to capture deferred ops. */ void -xfs_defer_ops_capture_free( +xfs_defer_ops_capture_abort( struct xfs_mount *mp, struct xfs_defer_capture *dfc) { unsigned short i; + xfs_defer_pending_abort_list(mp, &dfc->dfc_dfops); xfs_defer_cancel_list(mp, &dfc->dfc_dfops); for (i = 0; i < dfc->dfc_held.dr_bufs; i++) @@ -768,7 +1041,7 @@ xfs_defer_ops_capture_free( for (i = 0; i < dfc->dfc_held.dr_inos; i++) xfs_irele(dfc->dfc_held.dr_ip[i]); - kmem_free(dfc); + kfree(dfc); } /* @@ -800,7 +1073,7 @@ xfs_defer_ops_capture_and_commit( /* Commit the transaction and add the capture structure to the list. */ error = xfs_trans_commit(tp); if (error) { - xfs_defer_ops_capture_free(mp, dfc); + xfs_defer_ops_capture_abort(mp, dfc); return error; } @@ -826,7 +1099,11 @@ xfs_defer_ops_continue( ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY)); /* Lock the captured resources to the new transaction. */ - if (dfc->dfc_held.dr_inos == 2) + if (dfc->dfc_held.dr_inos > 2) { + xfs_sort_inodes(dfc->dfc_held.dr_ip, dfc->dfc_held.dr_inos); + xfs_lock_inodes(dfc->dfc_held.dr_ip, dfc->dfc_held.dr_inos, + XFS_ILOCK_EXCL); + } else if (dfc->dfc_held.dr_inos == 2) xfs_lock_two_inodes(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL, dfc->dfc_held.dr_ip[1], XFS_ILOCK_EXCL); else if (dfc->dfc_held.dr_inos == 1) @@ -844,7 +1121,7 @@ xfs_defer_ops_continue( list_splice_init(&dfc->dfc_dfops, &tp->t_dfops); tp->t_flags |= dfc->dfc_tpflags; - kmem_free(dfc); + kfree(dfc); } /* Release the resources captured and continued during recovery. */ @@ -911,6 +1188,10 @@ xfs_defer_init_item_caches(void) error = xfs_attr_intent_init_cache(); if (error) goto err; + error = xfs_exchmaps_intent_init_cache(); + if (error) + goto err; + return 0; err: xfs_defer_destroy_item_caches(); @@ -921,6 +1202,7 @@ err: void xfs_defer_destroy_item_caches(void) { + xfs_exchmaps_intent_destroy_cache(); xfs_attr_intent_destroy_cache(); xfs_extfree_intent_destroy_cache(); xfs_bmap_intent_destroy_cache(); @@ -928,3 +1210,36 @@ xfs_defer_destroy_item_caches(void) xfs_rmap_intent_destroy_cache(); xfs_defer_destroy_cache(); } + +/* + * Mark a deferred work item so that it will be requeued indefinitely without + * being finished. Caller must ensure there are no data dependencies on this + * work item in the meantime. + */ +void +xfs_defer_item_pause( + struct xfs_trans *tp, + struct xfs_defer_pending *dfp) +{ + ASSERT(!(dfp->dfp_flags & XFS_DEFER_PAUSED)); + + dfp->dfp_flags |= XFS_DEFER_PAUSED; + + trace_xfs_defer_item_pause(tp->t_mountp, dfp); +} + +/* + * Release a paused deferred work item so that it will be finished during the + * next transaction roll. + */ +void +xfs_defer_item_unpause( + struct xfs_trans *tp, + struct xfs_defer_pending *dfp) +{ + ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED); + + dfp->dfp_flags &= ~XFS_DEFER_PAUSED; + + trace_xfs_defer_item_unpause(tp->t_mountp, dfp); +} diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index 114a3a4930a3..9effd95ddcd4 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -11,19 +11,6 @@ struct xfs_defer_op_type; struct xfs_defer_capture; /* - * Header for deferred operation list. - */ -enum xfs_defer_ops_type { - XFS_DEFER_OPS_TYPE_BMAP, - XFS_DEFER_OPS_TYPE_REFCOUNT, - XFS_DEFER_OPS_TYPE_RMAP, - XFS_DEFER_OPS_TYPE_FREE, - XFS_DEFER_OPS_TYPE_AGFL_FREE, - XFS_DEFER_OPS_TYPE_ATTR, - XFS_DEFER_OPS_TYPE_MAX, -}; - -/* * Save a log intent item and a list of extents, so that we can replay * whatever action had to happen to the extent list and file the log done * item. @@ -33,19 +20,35 @@ struct xfs_defer_pending { struct list_head dfp_work; /* work items */ struct xfs_log_item *dfp_intent; /* log intent item */ struct xfs_log_item *dfp_done; /* log done item */ + const struct xfs_defer_op_type *dfp_ops; unsigned int dfp_count; /* # extent items */ - enum xfs_defer_ops_type dfp_type; + unsigned int dfp_flags; }; -void xfs_defer_add(struct xfs_trans *tp, enum xfs_defer_ops_type type, - struct list_head *h); +/* + * Create a log intent item for this deferred item, but don't actually finish + * the work. Caller must clear this before the final transaction commit. + */ +#define XFS_DEFER_PAUSED (1U << 0) + +#define XFS_DEFER_PENDING_STRINGS \ + { XFS_DEFER_PAUSED, "paused" } + +void xfs_defer_item_pause(struct xfs_trans *tp, struct xfs_defer_pending *dfp); +void xfs_defer_item_unpause(struct xfs_trans *tp, struct xfs_defer_pending *dfp); + +struct xfs_defer_pending *xfs_defer_add(struct xfs_trans *tp, struct list_head *h, + const struct xfs_defer_op_type *ops); int xfs_defer_finish_noroll(struct xfs_trans **tp); int xfs_defer_finish(struct xfs_trans **tp); +int xfs_defer_finish_one(struct xfs_trans *tp, struct xfs_defer_pending *dfp); void xfs_defer_cancel(struct xfs_trans *); void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp); /* Description of a deferred type. */ struct xfs_defer_op_type { + const char *name; + unsigned int max_items; struct xfs_log_item *(*create_intent)(struct xfs_trans *tp, struct list_head *items, unsigned int count, bool sort); void (*abort_intent)(struct xfs_log_item *intent); @@ -56,21 +59,34 @@ struct xfs_defer_op_type { void (*finish_cleanup)(struct xfs_trans *tp, struct xfs_btree_cur *state, int error); void (*cancel_item)(struct list_head *item); - unsigned int max_items; + int (*recover_work)(struct xfs_defer_pending *dfp, + struct list_head *capture_list); + struct xfs_log_item *(*relog_intent)(struct xfs_trans *tp, + struct xfs_log_item *intent, + struct xfs_log_item *done_item); }; extern const struct xfs_defer_op_type xfs_bmap_update_defer_type; extern const struct xfs_defer_op_type xfs_refcount_update_defer_type; +extern const struct xfs_defer_op_type xfs_rtrefcount_update_defer_type; extern const struct xfs_defer_op_type xfs_rmap_update_defer_type; +extern const struct xfs_defer_op_type xfs_rtrmap_update_defer_type; extern const struct xfs_defer_op_type xfs_extent_free_defer_type; extern const struct xfs_defer_op_type xfs_agfl_free_defer_type; +extern const struct xfs_defer_op_type xfs_rtextent_free_defer_type; extern const struct xfs_defer_op_type xfs_attr_defer_type; - +extern const struct xfs_defer_op_type xfs_exchmaps_defer_type; /* * Deferred operation item relogging limits. */ -#define XFS_DEFER_OPS_NR_INODES 2 /* join up to two inodes */ + +/* + * Rename w/ parent pointers can require up to 5 inodes with deferred ops to + * be joined to the transaction: src_dp, target_dp, src_ip, target_ip, and wip. + * These inodes are locked in sorted order by their inode numbers + */ +#define XFS_DEFER_OPS_NR_INODES 5 #define XFS_DEFER_OPS_NR_BUFS 2 /* join up to two buffers */ /* Resources that must be held across a transaction roll. */ @@ -121,11 +137,29 @@ int xfs_defer_ops_capture_and_commit(struct xfs_trans *tp, struct list_head *capture_list); void xfs_defer_ops_continue(struct xfs_defer_capture *d, struct xfs_trans *tp, struct xfs_defer_resources *dres); -void xfs_defer_ops_capture_free(struct xfs_mount *mp, +void xfs_defer_ops_capture_abort(struct xfs_mount *mp, struct xfs_defer_capture *d); void xfs_defer_resources_rele(struct xfs_defer_resources *dres); +void xfs_defer_start_recovery(struct xfs_log_item *lip, + struct list_head *r_dfops, const struct xfs_defer_op_type *ops); +void xfs_defer_cancel_recovery(struct xfs_mount *mp, + struct xfs_defer_pending *dfp); +int xfs_defer_finish_recovery(struct xfs_mount *mp, + struct xfs_defer_pending *dfp, struct list_head *capture_list); + +static inline void +xfs_defer_add_item( + struct xfs_defer_pending *dfp, + struct list_head *work) +{ + list_add_tail(work, &dfp->dfp_work); + dfp->dfp_count++; +} + int __init xfs_defer_init_item_caches(void); void xfs_defer_destroy_item_caches(void); +void xfs_defer_add_barrier(struct xfs_trans *tp); + #endif /* __XFS_DEFER_H__ */ diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 92bac3373f1f..82a338458a51 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -18,6 +18,12 @@ #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_trace.h" +#include "xfs_health.h" +#include "xfs_bmap_btree.h" +#include "xfs_trans_space.h" +#include "xfs_parent.h" +#include "xfs_ag.h" +#include "xfs_ialloc.h" const struct xfs_name xfs_name_dotdot = { .name = (const unsigned char *)"..", @@ -25,6 +31,12 @@ const struct xfs_name xfs_name_dotdot = { .type = XFS_DIR3_FT_DIR, }; +const struct xfs_name xfs_name_dot = { + .name = (const unsigned char *)".", + .len = 1, + .type = XFS_DIR3_FT_DIR, +}; + /* * Convert inode mode to directory entry filetype */ @@ -64,7 +76,7 @@ xfs_ascii_ci_hashname( int i; for (i = 0, hash = 0; i < name->len; i++) - hash = tolower(name->name[i]) ^ rol32(hash, 7); + hash = xfs_ascii_ci_xfrm(name->name[i]) ^ rol32(hash, 7); return hash; } @@ -85,7 +97,8 @@ xfs_ascii_ci_compname( for (i = 0; i < len; i++) { if (args->name[i] == name[i]) continue; - if (tolower(args->name[i]) != tolower(name[i])) + if (xfs_ascii_ci_xfrm(args->name[i]) != + xfs_ascii_ci_xfrm(name[i])) return XFS_CMP_DIFFERENT; result = XFS_CMP_CASE; } @@ -103,13 +116,13 @@ xfs_da_mount( ASSERT(mp->m_sb.sb_versionnum & XFS_SB_VERSION_DIRV2BIT); ASSERT(xfs_dir2_dirblock_bytes(&mp->m_sb) <= XFS_MAX_BLOCKSIZE); - mp->m_dir_geo = kmem_zalloc(sizeof(struct xfs_da_geometry), - KM_MAYFAIL); - mp->m_attr_geo = kmem_zalloc(sizeof(struct xfs_da_geometry), - KM_MAYFAIL); + mp->m_dir_geo = kzalloc(sizeof(struct xfs_da_geometry), + GFP_KERNEL | __GFP_RETRY_MAYFAIL); + mp->m_attr_geo = kzalloc(sizeof(struct xfs_da_geometry), + GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!mp->m_dir_geo || !mp->m_attr_geo) { - kmem_free(mp->m_dir_geo); - kmem_free(mp->m_attr_geo); + kfree(mp->m_dir_geo); + kfree(mp->m_attr_geo); return -ENOMEM; } @@ -177,14 +190,14 @@ void xfs_da_unmount( struct xfs_mount *mp) { - kmem_free(mp->m_dir_geo); - kmem_free(mp->m_attr_geo); + kfree(mp->m_dir_geo); + kfree(mp->m_attr_geo); } /* * Return 1 if directory contains only "." and "..". */ -int +static bool xfs_dir_isempty( xfs_inode_t *dp) { @@ -192,10 +205,10 @@ xfs_dir_isempty( ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); if (dp->i_disk_size == 0) /* might happen during shutdown. */ - return 1; + return true; if (dp->i_disk_size > xfs_inode_data_fork_size(dp)) - return 0; - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + return false; + sfp = dp->i_df.if_data; return !sfp->count; } @@ -210,7 +223,7 @@ xfs_dir_ino_validate( bool ino_ok = xfs_verify_dir_ino(mp, ino); if (XFS_IS_CORRUPT(mp, !ino_ok) || - XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DIR_INO_VALIDATE)) { + XFS_TEST_ERROR(mp, XFS_ERRTAG_DIR_INO_VALIDATE)) { xfs_warn(mp, "Invalid inode number 0x%Lx", (unsigned long long) ino); return -EFSCORRUPTED; @@ -235,18 +248,75 @@ xfs_dir_init( if (error) return error; - args = kmem_zalloc(sizeof(*args), KM_NOFS); + args = kzalloc(sizeof(*args), GFP_KERNEL | __GFP_NOFAIL); if (!args) return -ENOMEM; args->geo = dp->i_mount->m_dir_geo; args->dp = dp; args->trans = tp; + args->owner = dp->i_ino; error = xfs_dir2_sf_create(args, pdp->i_ino); - kmem_free(args); + kfree(args); return error; } +enum xfs_dir2_fmt +xfs_dir2_format( + struct xfs_da_args *args, + int *error) +{ + struct xfs_inode *dp = args->dp; + struct xfs_mount *mp = dp->i_mount; + struct xfs_da_geometry *geo = mp->m_dir_geo; + xfs_fileoff_t eof; + + xfs_assert_ilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + *error = 0; + if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) + return XFS_DIR2_FMT_SF; + + *error = xfs_bmap_last_offset(dp, &eof, XFS_DATA_FORK); + if (*error) + return XFS_DIR2_FMT_ERROR; + + if (eof == XFS_B_TO_FSB(mp, geo->blksize)) { + if (XFS_IS_CORRUPT(mp, dp->i_disk_size != geo->blksize)) { + xfs_da_mark_sick(args); + *error = -EFSCORRUPTED; + return XFS_DIR2_FMT_ERROR; + } + return XFS_DIR2_FMT_BLOCK; + } + if (eof == geo->leafblk + geo->fsbcount) + return XFS_DIR2_FMT_LEAF; + return XFS_DIR2_FMT_NODE; +} + +int +xfs_dir_createname_args( + struct xfs_da_args *args) +{ + int error; + + if (!args->inumber) + args->op_flags |= XFS_DA_OP_JUSTCHECK; + + switch (xfs_dir2_format(args, &error)) { + case XFS_DIR2_FMT_SF: + return xfs_dir2_sf_addname(args); + case XFS_DIR2_FMT_BLOCK: + return xfs_dir2_block_addname(args); + case XFS_DIR2_FMT_LEAF: + return xfs_dir2_leaf_addname(args); + case XFS_DIR2_FMT_NODE: + return xfs_dir2_node_addname(args); + default: + return error; + } +} + /* * Enter a name in a directory, or check for available space. * If inum is 0, only the available space test is performed. @@ -261,7 +331,6 @@ xfs_dir_createname( { struct xfs_da_args *args; int rval; - bool v; ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); @@ -272,7 +341,7 @@ xfs_dir_createname( XFS_STATS_INC(dp->i_mount, xs_dir_create); } - args = kmem_zalloc(sizeof(*args), KM_NOFS); + args = kzalloc(sizeof(*args), GFP_KERNEL | __GFP_NOFAIL); if (!args) return -ENOMEM; @@ -287,32 +356,10 @@ xfs_dir_createname( args->whichfork = XFS_DATA_FORK; args->trans = tp; args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT; - if (!inum) - args->op_flags |= XFS_DA_OP_JUSTCHECK; - - if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) { - rval = xfs_dir2_sf_addname(args); - goto out_free; - } + args->owner = dp->i_ino; - rval = xfs_dir2_isblock(args, &v); - if (rval) - goto out_free; - if (v) { - rval = xfs_dir2_block_addname(args); - goto out_free; - } - - rval = xfs_dir2_isleaf(args, &v); - if (rval) - goto out_free; - if (v) - rval = xfs_dir2_leaf_addname(args); - else - rval = xfs_dir2_node_addname(args); - -out_free: - kmem_free(args); + rval = xfs_dir_createname_args(args); + kfree(args); return rval; } @@ -332,15 +379,43 @@ xfs_dir_cilookup_result( !(args->op_flags & XFS_DA_OP_CILOOKUP)) return -EEXIST; - args->value = kmem_alloc(len, KM_NOFS | KM_MAYFAIL); + args->value = kmemdup(name, len, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_RETRY_MAYFAIL); if (!args->value) return -ENOMEM; - memcpy(args->value, name, len); args->valuelen = len; return -EEXIST; } +int +xfs_dir_lookup_args( + struct xfs_da_args *args) +{ + int error; + + switch (xfs_dir2_format(args, &error)) { + case XFS_DIR2_FMT_SF: + error = xfs_dir2_sf_lookup(args); + break; + case XFS_DIR2_FMT_BLOCK: + error = xfs_dir2_block_lookup(args); + break; + case XFS_DIR2_FMT_LEAF: + error = xfs_dir2_leaf_lookup(args); + break; + case XFS_DIR2_FMT_NODE: + error = xfs_dir2_node_lookup(args); + break; + default: + break; + } + + if (error != -EEXIST) + return error; + return 0; +} + /* * Lookup a name in a directory, give back the inode number. * If ci_name is not NULL, returns the actual name in ci_name if it differs @@ -357,21 +432,13 @@ xfs_dir_lookup( { struct xfs_da_args *args; int rval; - bool v; int lock_mode; ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); XFS_STATS_INC(dp->i_mount, xs_dir_lookup); - /* - * We need to use KM_NOFS here so that lockdep will not throw false - * positive deadlock warnings on a non-transactional lookup path. It is - * safe to recurse into inode recalim in that case, but lockdep can't - * easily be taught about it. Hence KM_NOFS avoids having to add more - * lockdep Doing this avoids having to add a bunch of lockdep class - * annotations into the reclaim path for the ilock. - */ - args = kmem_zalloc(sizeof(*args), KM_NOFS); + args = kzalloc(sizeof(*args), + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); args->geo = dp->i_mount->m_dir_geo; args->name = name->name; args->namelen = name->len; @@ -381,34 +448,12 @@ xfs_dir_lookup( args->whichfork = XFS_DATA_FORK; args->trans = tp; args->op_flags = XFS_DA_OP_OKNOENT; + args->owner = dp->i_ino; if (ci_name) args->op_flags |= XFS_DA_OP_CILOOKUP; lock_mode = xfs_ilock_data_map_shared(dp); - if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) { - rval = xfs_dir2_sf_lookup(args); - goto out_check_rval; - } - - rval = xfs_dir2_isblock(args, &v); - if (rval) - goto out_free; - if (v) { - rval = xfs_dir2_block_lookup(args); - goto out_check_rval; - } - - rval = xfs_dir2_isleaf(args, &v); - if (rval) - goto out_free; - if (v) - rval = xfs_dir2_leaf_lookup(args); - else - rval = xfs_dir2_node_lookup(args); - -out_check_rval: - if (rval == -EEXIST) - rval = 0; + rval = xfs_dir_lookup_args(args); if (!rval) { *inum = args->inumber; if (ci_name) { @@ -416,12 +461,31 @@ out_check_rval: ci_name->len = args->valuelen; } } -out_free: xfs_iunlock(dp, lock_mode); - kmem_free(args); + kfree(args); return rval; } +int +xfs_dir_removename_args( + struct xfs_da_args *args) +{ + int error; + + switch (xfs_dir2_format(args, &error)) { + case XFS_DIR2_FMT_SF: + return xfs_dir2_sf_removename(args); + case XFS_DIR2_FMT_BLOCK: + return xfs_dir2_block_removename(args); + case XFS_DIR2_FMT_LEAF: + return xfs_dir2_leaf_removename(args); + case XFS_DIR2_FMT_NODE: + return xfs_dir2_node_removename(args); + default: + return error; + } +} + /* * Remove an entry from a directory. */ @@ -429,18 +493,17 @@ int xfs_dir_removename( struct xfs_trans *tp, struct xfs_inode *dp, - struct xfs_name *name, + const struct xfs_name *name, xfs_ino_t ino, xfs_extlen_t total) /* bmap's total block count */ { struct xfs_da_args *args; int rval; - bool v; ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); XFS_STATS_INC(dp->i_mount, xs_dir_remove); - args = kmem_zalloc(sizeof(*args), KM_NOFS); + args = kzalloc(sizeof(*args), GFP_KERNEL | __GFP_NOFAIL); if (!args) return -ENOMEM; @@ -454,30 +517,30 @@ xfs_dir_removename( args->total = total; args->whichfork = XFS_DATA_FORK; args->trans = tp; + args->owner = dp->i_ino; + rval = xfs_dir_removename_args(args); + kfree(args); + return rval; +} - if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) { - rval = xfs_dir2_sf_removename(args); - goto out_free; - } +int +xfs_dir_replace_args( + struct xfs_da_args *args) +{ + int error; - rval = xfs_dir2_isblock(args, &v); - if (rval) - goto out_free; - if (v) { - rval = xfs_dir2_block_removename(args); - goto out_free; + switch (xfs_dir2_format(args, &error)) { + case XFS_DIR2_FMT_SF: + return xfs_dir2_sf_replace(args); + case XFS_DIR2_FMT_BLOCK: + return xfs_dir2_block_replace(args); + case XFS_DIR2_FMT_LEAF: + return xfs_dir2_leaf_replace(args); + case XFS_DIR2_FMT_NODE: + return xfs_dir2_node_replace(args); + default: + return error; } - - rval = xfs_dir2_isleaf(args, &v); - if (rval) - goto out_free; - if (v) - rval = xfs_dir2_leaf_removename(args); - else - rval = xfs_dir2_node_removename(args); -out_free: - kmem_free(args); - return rval; } /* @@ -493,7 +556,6 @@ xfs_dir_replace( { struct xfs_da_args *args; int rval; - bool v; ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); @@ -501,7 +563,7 @@ xfs_dir_replace( if (rval) return rval; - args = kmem_zalloc(sizeof(*args), KM_NOFS); + args = kzalloc(sizeof(*args), GFP_KERNEL | __GFP_NOFAIL); if (!args) return -ENOMEM; @@ -515,29 +577,9 @@ xfs_dir_replace( args->total = total; args->whichfork = XFS_DATA_FORK; args->trans = tp; - - if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) { - rval = xfs_dir2_sf_replace(args); - goto out_free; - } - - rval = xfs_dir2_isblock(args, &v); - if (rval) - goto out_free; - if (v) { - rval = xfs_dir2_block_replace(args); - goto out_free; - } - - rval = xfs_dir2_isleaf(args, &v); - if (rval) - goto out_free; - if (v) - rval = xfs_dir2_leaf_replace(args); - else - rval = xfs_dir2_node_replace(args); -out_free: - kmem_free(args); + args->owner = dp->i_ino; + rval = xfs_dir_replace_args(args); + kfree(args); return rval; } @@ -546,9 +588,9 @@ out_free: */ int xfs_dir_canenter( - xfs_trans_t *tp, - xfs_inode_t *dp, - struct xfs_name *name) /* name of entry to add */ + struct xfs_trans *tp, + struct xfs_inode *dp, + const struct xfs_name *name) /* name of entry to add */ { return xfs_dir_createname(tp, dp, name, 0, 0); } @@ -605,55 +647,6 @@ xfs_dir2_grow_inode( } /* - * See if the directory is a single-block form directory. - */ -int -xfs_dir2_isblock( - struct xfs_da_args *args, - bool *isblock) -{ - struct xfs_mount *mp = args->dp->i_mount; - xfs_fileoff_t eof; - int error; - - error = xfs_bmap_last_offset(args->dp, &eof, XFS_DATA_FORK); - if (error) - return error; - - *isblock = false; - if (XFS_FSB_TO_B(mp, eof) != args->geo->blksize) - return 0; - - *isblock = true; - if (XFS_IS_CORRUPT(mp, args->dp->i_disk_size != args->geo->blksize)) - return -EFSCORRUPTED; - return 0; -} - -/* - * See if the directory is a single-leaf form directory. - */ -int -xfs_dir2_isleaf( - struct xfs_da_args *args, - bool *isleaf) -{ - xfs_fileoff_t eof; - int error; - - error = xfs_bmap_last_offset(args->dp, &eof, XFS_DATA_FORK); - if (error) - return error; - - *isleaf = false; - if (eof != args->geo->leafblk + args->geo->fsbcount) - return 0; - - *isleaf = true; - return 0; -} - -/* * Remove the given block from the directory. * This routine is used for data and free blocks, leaf/node are done * by xfs_da_shrink_inode. @@ -767,3 +760,653 @@ xfs_dir2_compname( return xfs_ascii_ci_compname(args, name, len); return xfs_da_compname(args, name, len); } + +#ifdef CONFIG_XFS_LIVE_HOOKS +/* + * Use a static key here to reduce the overhead of directory live update hooks. + * If the compiler supports jump labels, the static branch will be replaced by + * a nop sled when there are no hook users. Online fsck is currently the only + * caller, so this is a reasonable tradeoff. + * + * Note: Patching the kernel code requires taking the cpu hotplug lock. Other + * parts of the kernel allocate memory with that lock held, which means that + * XFS callers cannot hold any locks that might be used by memory reclaim or + * writeback when calling the static_branch_{inc,dec} functions. + */ +DEFINE_STATIC_XFS_HOOK_SWITCH(xfs_dir_hooks_switch); + +void +xfs_dir_hook_disable(void) +{ + xfs_hooks_switch_off(&xfs_dir_hooks_switch); +} + +void +xfs_dir_hook_enable(void) +{ + xfs_hooks_switch_on(&xfs_dir_hooks_switch); +} + +/* Call hooks for a directory update relating to a child dirent update. */ +inline void +xfs_dir_update_hook( + struct xfs_inode *dp, + struct xfs_inode *ip, + int delta, + const struct xfs_name *name) +{ + if (xfs_hooks_switched_on(&xfs_dir_hooks_switch)) { + struct xfs_dir_update_params p = { + .dp = dp, + .ip = ip, + .delta = delta, + .name = name, + }; + struct xfs_mount *mp = ip->i_mount; + + xfs_hooks_call(&mp->m_dir_update_hooks, 0, &p); + } +} + +/* Call the specified function during a directory update. */ +int +xfs_dir_hook_add( + struct xfs_mount *mp, + struct xfs_dir_hook *hook) +{ + return xfs_hooks_add(&mp->m_dir_update_hooks, &hook->dirent_hook); +} + +/* Stop calling the specified function during a directory update. */ +void +xfs_dir_hook_del( + struct xfs_mount *mp, + struct xfs_dir_hook *hook) +{ + xfs_hooks_del(&mp->m_dir_update_hooks, &hook->dirent_hook); +} + +/* Configure directory update hook functions. */ +void +xfs_dir_hook_setup( + struct xfs_dir_hook *hook, + notifier_fn_t mod_fn) +{ + xfs_hook_setup(&hook->dirent_hook, mod_fn); +} +#endif /* CONFIG_XFS_LIVE_HOOKS */ + +/* + * Given a directory @dp, a newly allocated inode @ip, and a @name, link @ip + * into @dp under the given @name. If @ip is a directory, it will be + * initialized. Both inodes must have the ILOCK held and the transaction must + * have sufficient blocks reserved. + */ +int +xfs_dir_create_child( + struct xfs_trans *tp, + unsigned int resblks, + struct xfs_dir_update *du) +{ + struct xfs_inode *dp = du->dp; + const struct xfs_name *name = du->name; + struct xfs_inode *ip = du->ip; + int error; + + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); + xfs_assert_ilocked(dp, XFS_ILOCK_EXCL); + + error = xfs_dir_createname(tp, dp, name, ip->i_ino, resblks); + if (error) { + ASSERT(error != -ENOSPC); + return error; + } + + xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); + + if (S_ISDIR(VFS_I(ip)->i_mode)) { + error = xfs_dir_init(tp, ip, dp); + if (error) + return error; + + xfs_bumplink(tp, dp); + } + + /* + * If we have parent pointers, we need to add the attribute containing + * the parent information now. + */ + if (du->ppargs) { + error = xfs_parent_addname(tp, du->ppargs, dp, name, ip); + if (error) + return error; + } + + xfs_dir_update_hook(dp, ip, 1, name); + return 0; +} + +/* + * Given a directory @dp, an existing non-directory inode @ip, and a @name, + * link @ip into @dp under the given @name. Both inodes must have the ILOCK + * held. + */ +int +xfs_dir_add_child( + struct xfs_trans *tp, + unsigned int resblks, + struct xfs_dir_update *du) +{ + struct xfs_inode *dp = du->dp; + const struct xfs_name *name = du->name; + struct xfs_inode *ip = du->ip; + struct xfs_mount *mp = tp->t_mountp; + int error; + + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); + xfs_assert_ilocked(dp, XFS_ILOCK_EXCL); + ASSERT(!S_ISDIR(VFS_I(ip)->i_mode)); + + if (!resblks) { + error = xfs_dir_canenter(tp, dp, name); + if (error) + return error; + } + + /* + * Handle initial link state of O_TMPFILE inode + */ + if (VFS_I(ip)->i_nlink == 0) { + struct xfs_perag *pag; + + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); + error = xfs_iunlink_remove(tp, pag, ip); + xfs_perag_put(pag); + if (error) + return error; + } + + error = xfs_dir_createname(tp, dp, name, ip->i_ino, resblks); + if (error) + return error; + + xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); + + xfs_bumplink(tp, ip); + + /* + * If we have parent pointers, we now need to add the parent record to + * the attribute fork of the inode. If this is the initial parent + * attribute, we need to create it correctly, otherwise we can just add + * the parent to the inode. + */ + if (du->ppargs) { + error = xfs_parent_addname(tp, du->ppargs, dp, name, ip); + if (error) + return error; + } + + xfs_dir_update_hook(dp, ip, 1, name); + return 0; +} + +/* + * Given a directory @dp, a child @ip, and a @name, remove the (@name, @ip) + * entry from the directory. Both inodes must have the ILOCK held. + */ +int +xfs_dir_remove_child( + struct xfs_trans *tp, + unsigned int resblks, + struct xfs_dir_update *du) +{ + struct xfs_inode *dp = du->dp; + const struct xfs_name *name = du->name; + struct xfs_inode *ip = du->ip; + int error; + + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); + xfs_assert_ilocked(dp, XFS_ILOCK_EXCL); + + /* + * If we're removing a directory perform some additional validation. + */ + if (S_ISDIR(VFS_I(ip)->i_mode)) { + ASSERT(VFS_I(ip)->i_nlink >= 2); + if (VFS_I(ip)->i_nlink != 2) + return -ENOTEMPTY; + if (!xfs_dir_isempty(ip)) + return -ENOTEMPTY; + + /* Drop the link from ip's "..". */ + error = xfs_droplink(tp, dp); + if (error) + return error; + + /* Drop the "." link from ip to self. */ + error = xfs_droplink(tp, ip); + if (error) + return error; + + /* + * Point the unlinked child directory's ".." entry to the root + * directory to eliminate back-references to inodes that may + * get freed before the child directory is closed. If the fs + * gets shrunk, this can lead to dirent inode validation errors. + */ + if (dp->i_ino != tp->t_mountp->m_sb.sb_rootino) { + error = xfs_dir_replace(tp, ip, &xfs_name_dotdot, + tp->t_mountp->m_sb.sb_rootino, 0); + if (error) + return error; + } + } else { + /* + * When removing a non-directory we need to log the parent + * inode here. For a directory this is done implicitly + * by the xfs_droplink call for the ".." entry. + */ + xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); + } + xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + + /* Drop the link from dp to ip. */ + error = xfs_droplink(tp, ip); + if (error) + return error; + + error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks); + if (error) { + ASSERT(error != -ENOENT); + return error; + } + + /* Remove parent pointer. */ + if (du->ppargs) { + error = xfs_parent_removename(tp, du->ppargs, dp, name, ip); + if (error) + return error; + } + + xfs_dir_update_hook(dp, ip, -1, name); + return 0; +} + +/* + * Exchange the entry (@name1, @ip1) in directory @dp1 with the entry (@name2, + * @ip2) in directory @dp2, and update '..' @ip1 and @ip2's entries as needed. + * @ip1 and @ip2 need not be of the same type. + * + * All inodes must have the ILOCK held, and both entries must already exist. + */ +int +xfs_dir_exchange_children( + struct xfs_trans *tp, + struct xfs_dir_update *du1, + struct xfs_dir_update *du2, + unsigned int spaceres) +{ + struct xfs_inode *dp1 = du1->dp; + const struct xfs_name *name1 = du1->name; + struct xfs_inode *ip1 = du1->ip; + struct xfs_inode *dp2 = du2->dp; + const struct xfs_name *name2 = du2->name; + struct xfs_inode *ip2 = du2->ip; + int ip1_flags = 0; + int ip2_flags = 0; + int dp2_flags = 0; + int error; + + /* Swap inode number for dirent in first parent */ + error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, spaceres); + if (error) + return error; + + /* Swap inode number for dirent in second parent */ + error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, spaceres); + if (error) + return error; + + /* + * If we're renaming one or more directories across different parents, + * update the respective ".." entries (and link counts) to match the new + * parents. + */ + if (dp1 != dp2) { + dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; + + if (S_ISDIR(VFS_I(ip2)->i_mode)) { + error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot, + dp1->i_ino, spaceres); + if (error) + return error; + + /* transfer ip2 ".." reference to dp1 */ + if (!S_ISDIR(VFS_I(ip1)->i_mode)) { + error = xfs_droplink(tp, dp2); + if (error) + return error; + xfs_bumplink(tp, dp1); + } + + /* + * Although ip1 isn't changed here, userspace needs + * to be warned about the change, so that applications + * relying on it (like backup ones), will properly + * notify the change + */ + ip1_flags |= XFS_ICHGTIME_CHG; + ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; + } + + if (S_ISDIR(VFS_I(ip1)->i_mode)) { + error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot, + dp2->i_ino, spaceres); + if (error) + return error; + + /* transfer ip1 ".." reference to dp2 */ + if (!S_ISDIR(VFS_I(ip2)->i_mode)) { + error = xfs_droplink(tp, dp1); + if (error) + return error; + xfs_bumplink(tp, dp2); + } + + /* + * Although ip2 isn't changed here, userspace needs + * to be warned about the change, so that applications + * relying on it (like backup ones), will properly + * notify the change + */ + ip1_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; + ip2_flags |= XFS_ICHGTIME_CHG; + } + } + + if (ip1_flags) { + xfs_trans_ichgtime(tp, ip1, ip1_flags); + xfs_trans_log_inode(tp, ip1, XFS_ILOG_CORE); + } + if (ip2_flags) { + xfs_trans_ichgtime(tp, ip2, ip2_flags); + xfs_trans_log_inode(tp, ip2, XFS_ILOG_CORE); + } + if (dp2_flags) { + xfs_trans_ichgtime(tp, dp2, dp2_flags); + xfs_trans_log_inode(tp, dp2, XFS_ILOG_CORE); + } + xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE); + + /* Schedule parent pointer replacements */ + if (du1->ppargs) { + error = xfs_parent_replacename(tp, du1->ppargs, dp1, name1, + dp2, name2, ip1); + if (error) + return error; + } + + if (du2->ppargs) { + error = xfs_parent_replacename(tp, du2->ppargs, dp2, name2, + dp1, name1, ip2); + if (error) + return error; + } + + /* + * Inform our hook clients that we've finished an exchange operation as + * follows: removed the source and target files from their directories; + * added the target to the source directory; and added the source to + * the target directory. All inodes are locked, so it's ok to model a + * rename this way so long as we say we deleted entries before we add + * new ones. + */ + xfs_dir_update_hook(dp1, ip1, -1, name1); + xfs_dir_update_hook(dp2, ip2, -1, name2); + xfs_dir_update_hook(dp1, ip2, 1, name1); + xfs_dir_update_hook(dp2, ip1, 1, name2); + return 0; +} + +/* + * Given an entry (@src_name, @src_ip) in directory @src_dp, make the entry + * @target_name in directory @target_dp point to @src_ip and remove the + * original entry, cleaning up everything left behind. + * + * Cleanup involves dropping a link count on @target_ip, and either removing + * the (@src_name, @src_ip) entry from @src_dp or simply replacing the entry + * with (@src_name, @wip) if a whiteout inode @wip is supplied. + * + * All inodes must have the ILOCK held. We assume that if @src_ip is a + * directory then its '..' doesn't already point to @target_dp, and that @wip + * is a freshly allocated whiteout. + */ +int +xfs_dir_rename_children( + struct xfs_trans *tp, + struct xfs_dir_update *du_src, + struct xfs_dir_update *du_tgt, + unsigned int spaceres, + struct xfs_dir_update *du_wip) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_inode *src_dp = du_src->dp; + const struct xfs_name *src_name = du_src->name; + struct xfs_inode *src_ip = du_src->ip; + struct xfs_inode *target_dp = du_tgt->dp; + const struct xfs_name *target_name = du_tgt->name; + struct xfs_inode *target_ip = du_tgt->ip; + bool new_parent = (src_dp != target_dp); + bool src_is_directory; + int error; + + src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode); + + /* + * Check for expected errors before we dirty the transaction + * so we can return an error without a transaction abort. + */ + if (target_ip == NULL) { + /* + * If there's no space reservation, check the entry will + * fit before actually inserting it. + */ + if (!spaceres) { + error = xfs_dir_canenter(tp, target_dp, target_name); + if (error) + return error; + } + } else { + /* + * If target exists and it's a directory, check that whether + * it can be destroyed. + */ + if (S_ISDIR(VFS_I(target_ip)->i_mode) && + (!xfs_dir_isempty(target_ip) || + (VFS_I(target_ip)->i_nlink > 2))) + return -EEXIST; + } + + /* + * Directory entry creation below may acquire the AGF. Remove + * the whiteout from the unlinked list first to preserve correct + * AGI/AGF locking order. This dirties the transaction so failures + * after this point will abort and log recovery will clean up the + * mess. + * + * For whiteouts, we need to bump the link count on the whiteout + * inode. After this point, we have a real link, clear the tmpfile + * state flag from the inode so it doesn't accidentally get misused + * in future. + */ + if (du_wip->ip) { + struct xfs_perag *pag; + + ASSERT(VFS_I(du_wip->ip)->i_nlink == 0); + + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, du_wip->ip->i_ino)); + error = xfs_iunlink_remove(tp, pag, du_wip->ip); + xfs_perag_put(pag); + if (error) + return error; + + xfs_bumplink(tp, du_wip->ip); + } + + /* + * Set up the target. + */ + if (target_ip == NULL) { + /* + * If target does not exist and the rename crosses + * directories, adjust the target directory link count + * to account for the ".." reference from the new entry. + */ + error = xfs_dir_createname(tp, target_dp, target_name, + src_ip->i_ino, spaceres); + if (error) + return error; + + xfs_trans_ichgtime(tp, target_dp, + XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + + if (new_parent && src_is_directory) { + xfs_bumplink(tp, target_dp); + } + } else { /* target_ip != NULL */ + /* + * Link the source inode under the target name. + * If the source inode is a directory and we are moving + * it across directories, its ".." entry will be + * inconsistent until we replace that down below. + * + * In case there is already an entry with the same + * name at the destination directory, remove it first. + */ + error = xfs_dir_replace(tp, target_dp, target_name, + src_ip->i_ino, spaceres); + if (error) + return error; + + xfs_trans_ichgtime(tp, target_dp, + XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + + /* + * Decrement the link count on the target since the target + * dir no longer points to it. + */ + error = xfs_droplink(tp, target_ip); + if (error) + return error; + + if (src_is_directory) { + /* + * Drop the link from the old "." entry. + */ + error = xfs_droplink(tp, target_ip); + if (error) + return error; + } + } /* target_ip != NULL */ + + /* + * Remove the source. + */ + if (new_parent && src_is_directory) { + /* + * Rewrite the ".." entry to point to the new + * directory. + */ + error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot, + target_dp->i_ino, spaceres); + ASSERT(error != -EEXIST); + if (error) + return error; + } + + /* + * We always want to hit the ctime on the source inode. + * + * This isn't strictly required by the standards since the source + * inode isn't really being changed, but old unix file systems did + * it and some incremental backup programs won't work without it. + */ + xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, src_ip, XFS_ILOG_CORE); + + /* + * Adjust the link count on src_dp. This is necessary when + * renaming a directory, either within one parent when + * the target existed, or across two parent directories. + */ + if (src_is_directory && (new_parent || target_ip != NULL)) { + + /* + * Decrement link count on src_directory since the + * entry that's moved no longer points to it. + */ + error = xfs_droplink(tp, src_dp); + if (error) + return error; + } + + /* + * For whiteouts, we only need to update the source dirent with the + * inode number of the whiteout inode rather than removing it + * altogether. + */ + if (du_wip->ip) + error = xfs_dir_replace(tp, src_dp, src_name, du_wip->ip->i_ino, + spaceres); + else + error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino, + spaceres); + if (error) + return error; + + xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE); + if (new_parent) + xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE); + + /* Schedule parent pointer updates. */ + if (du_wip->ppargs) { + error = xfs_parent_addname(tp, du_wip->ppargs, src_dp, + src_name, du_wip->ip); + if (error) + return error; + } + + if (du_src->ppargs) { + error = xfs_parent_replacename(tp, du_src->ppargs, src_dp, + src_name, target_dp, target_name, src_ip); + if (error) + return error; + } + + if (du_tgt->ppargs) { + error = xfs_parent_removename(tp, du_tgt->ppargs, target_dp, + target_name, target_ip); + if (error) + return error; + } + + /* + * Inform our hook clients that we've finished a rename operation as + * follows: removed the source and target files from their directories; + * that we've added the source to the target directory; and finally + * that we've added the whiteout, if there was one. All inodes are + * locked, so it's ok to model a rename this way so long as we say we + * deleted entries before we add new ones. + */ + if (target_ip) + xfs_dir_update_hook(target_dp, target_ip, -1, target_name); + xfs_dir_update_hook(src_dp, src_ip, -1, src_name); + xfs_dir_update_hook(target_dp, src_ip, 1, target_name); + if (du_wip->ip) + xfs_dir_update_hook(src_dp, du_wip->ip, 1, src_name); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index dd39f17dd9a9..a6594a5a941d 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -22,6 +22,29 @@ struct xfs_dir3_icfree_hdr; struct xfs_dir3_icleaf_hdr; extern const struct xfs_name xfs_name_dotdot; +extern const struct xfs_name xfs_name_dot; + +static inline bool +xfs_dir2_samename( + const struct xfs_name *n1, + const struct xfs_name *n2) +{ + if (n1 == n2) + return true; + if (n1->len != n2->len) + return false; + return !memcmp(n1->name, n2->name, n1->len); +} + +enum xfs_dir2_fmt { + XFS_DIR2_FMT_SF, + XFS_DIR2_FMT_BLOCK, + XFS_DIR2_FMT_LEAF, + XFS_DIR2_FMT_NODE, + XFS_DIR2_FMT_ERROR, +}; + +enum xfs_dir2_fmt xfs_dir2_format(struct xfs_da_args *args, int *error); /* * Convert inode mode to directory entry filetype @@ -35,7 +58,6 @@ extern void xfs_dir_startup(void); extern int xfs_da_mount(struct xfs_mount *mp); extern void xfs_da_unmount(struct xfs_mount *mp); -extern int xfs_dir_isempty(struct xfs_inode *dp); extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_inode *pdp); extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp, @@ -45,13 +67,18 @@ extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp, const struct xfs_name *name, xfs_ino_t *inum, struct xfs_name *ci_name); extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp, - struct xfs_name *name, xfs_ino_t ino, + const struct xfs_name *name, xfs_ino_t ino, xfs_extlen_t tot); extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp, const struct xfs_name *name, xfs_ino_t inum, xfs_extlen_t tot); extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp, - struct xfs_name *name); + const struct xfs_name *name); + +int xfs_dir_lookup_args(struct xfs_da_args *args); +int xfs_dir_createname_args(struct xfs_da_args *args); +int xfs_dir_removename_args(struct xfs_da_args *args); +int xfs_dir_replace_args(struct xfs_da_args *args); /* * Direct call from the bmap code, bypassing the generic directory layer. @@ -61,8 +88,6 @@ extern int xfs_dir2_sf_to_block(struct xfs_da_args *args); /* * Interface routines used by userspace utilities */ -extern int xfs_dir2_isblock(struct xfs_da_args *args, bool *isblock); -extern int xfs_dir2_isleaf(struct xfs_da_args *args, bool *isleaf); extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db, struct xfs_buf *bp); @@ -88,6 +113,10 @@ extern struct xfs_dir2_data_free *xfs_dir2_data_freefind( extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino); +xfs_failaddr_t xfs_dir3_leaf_header_check(struct xfs_buf *bp, xfs_ino_t owner); +xfs_failaddr_t xfs_dir3_data_header_check(struct xfs_buf *bp, xfs_ino_t owner); +xfs_failaddr_t xfs_dir3_block_header_check(struct xfs_buf *bp, xfs_ino_t owner); + extern const struct xfs_buf_ops xfs_dir3_block_buf_ops; extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops; extern const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops; @@ -248,4 +277,82 @@ unsigned int xfs_dir3_data_end_offset(struct xfs_da_geometry *geo, struct xfs_dir2_data_hdr *hdr); bool xfs_dir2_namecheck(const void *name, size_t length); +/* + * The "ascii-ci" feature was created to speed up case-insensitive lookups for + * a Samba product. Because of the inherent problems with CI and UTF-8 + * encoding, etc, it was decided that Samba would be configured to export + * latin1/iso 8859-1 encodings as that covered >90% of the target markets for + * the product. Hence the "ascii-ci" casefolding code could be encoded into + * the XFS directory operations and remove all the overhead of casefolding from + * Samba. + * + * To provide consistent hashing behavior between the userspace and kernel, + * these functions prepare names for hashing by transforming specific bytes + * to other bytes. Robustness with other encodings is not guaranteed. + */ +static inline bool xfs_ascii_ci_need_xfrm(unsigned char c) +{ + if (c >= 0x41 && c <= 0x5a) /* A-Z */ + return true; + if (c >= 0xc0 && c <= 0xd6) /* latin A-O with accents */ + return true; + if (c >= 0xd8 && c <= 0xde) /* latin O-Y with accents */ + return true; + return false; +} + +static inline unsigned char xfs_ascii_ci_xfrm(unsigned char c) +{ + if (xfs_ascii_ci_need_xfrm(c)) + c -= 'A' - 'a'; + return c; +} + +struct xfs_dir_update_params { + const struct xfs_inode *dp; + const struct xfs_inode *ip; + const struct xfs_name *name; + int delta; +}; + +#ifdef CONFIG_XFS_LIVE_HOOKS +void xfs_dir_update_hook(struct xfs_inode *dp, struct xfs_inode *ip, + int delta, const struct xfs_name *name); + +struct xfs_dir_hook { + struct xfs_hook dirent_hook; +}; + +void xfs_dir_hook_disable(void); +void xfs_dir_hook_enable(void); + +int xfs_dir_hook_add(struct xfs_mount *mp, struct xfs_dir_hook *hook); +void xfs_dir_hook_del(struct xfs_mount *mp, struct xfs_dir_hook *hook); +void xfs_dir_hook_setup(struct xfs_dir_hook *hook, notifier_fn_t mod_fn); +#else +# define xfs_dir_update_hook(dp, ip, delta, name) ((void)0) +#endif /* CONFIG_XFS_LIVE_HOOKS */ + +struct xfs_parent_args; + +struct xfs_dir_update { + struct xfs_inode *dp; + const struct xfs_name *name; + struct xfs_inode *ip; + struct xfs_parent_args *ppargs; +}; + +int xfs_dir_create_child(struct xfs_trans *tp, unsigned int resblks, + struct xfs_dir_update *du); +int xfs_dir_add_child(struct xfs_trans *tp, unsigned int resblks, + struct xfs_dir_update *du); +int xfs_dir_remove_child(struct xfs_trans *tp, unsigned int resblks, + struct xfs_dir_update *du); + +int xfs_dir_exchange_children(struct xfs_trans *tp, struct xfs_dir_update *du1, + struct xfs_dir_update *du2, unsigned int spaceres); +int xfs_dir_rename_children(struct xfs_trans *tp, struct xfs_dir_update *du_src, + struct xfs_dir_update *du_tgt, unsigned int spaceres, + struct xfs_dir_update *du_wip); + #endif /* __XFS_DIR2_H__ */ diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c index 00f960a703b2..0f93ed1a4a74 100644 --- a/fs/xfs/libxfs/xfs_dir2_block.c +++ b/fs/xfs/libxfs/xfs_dir2_block.c @@ -20,6 +20,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_log.h" +#include "xfs_health.h" /* * Local function prototypes. @@ -114,17 +115,20 @@ const struct xfs_buf_ops xfs_dir3_block_buf_ops = { .verify_struct = xfs_dir3_block_verify, }; -static xfs_failaddr_t +xfs_failaddr_t xfs_dir3_block_header_check( - struct xfs_inode *dp, - struct xfs_buf *bp) + struct xfs_buf *bp, + xfs_ino_t owner) { - struct xfs_mount *mp = dp->i_mount; + struct xfs_mount *mp = bp->b_mount; if (xfs_has_crc(mp)) { struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; - if (be64_to_cpu(hdr3->owner) != dp->i_ino) + if (hdr3->magic != cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) + return __this_address; + + if (be64_to_cpu(hdr3->owner) != owner) return __this_address; } @@ -135,6 +139,7 @@ int xfs_dir3_block_read( struct xfs_trans *tp, struct xfs_inode *dp, + xfs_ino_t owner, struct xfs_buf **bpp) { struct xfs_mount *mp = dp->i_mount; @@ -147,11 +152,12 @@ xfs_dir3_block_read( return err; /* Check things that we can't do in the verifier. */ - fa = xfs_dir3_block_header_check(dp, *bpp); + fa = xfs_dir3_block_header_check(*bpp, owner); if (fa) { __xfs_buf_mark_corrupt(*bpp, fa); xfs_trans_brelse(tp, *bpp); *bpp = NULL; + xfs_dirattr_mark_sick(dp, XFS_DATA_FORK); return -EFSCORRUPTED; } @@ -161,12 +167,13 @@ xfs_dir3_block_read( static void xfs_dir3_block_init( - struct xfs_mount *mp, - struct xfs_trans *tp, - struct xfs_buf *bp, - struct xfs_inode *dp) + struct xfs_da_args *args, + struct xfs_buf *bp) { - struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; + struct xfs_trans *tp = args->trans; + struct xfs_inode *dp = args->dp; + struct xfs_mount *mp = dp->i_mount; + struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; bp->b_ops = &xfs_dir3_block_buf_ops; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_BLOCK_BUF); @@ -175,7 +182,7 @@ xfs_dir3_block_init( memset(hdr3, 0, sizeof(*hdr3)); hdr3->magic = cpu_to_be32(XFS_DIR3_BLOCK_MAGIC); hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp)); - hdr3->owner = cpu_to_be64(dp->i_ino); + hdr3->owner = cpu_to_be64(args->owner); uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid); return; @@ -380,7 +387,7 @@ xfs_dir2_block_addname( tp = args->trans; /* Read the (one and only) directory block into bp. */ - error = xfs_dir3_block_read(tp, dp, &bp); + error = xfs_dir3_block_read(tp, dp, args->owner, &bp); if (error) return error; @@ -695,7 +702,7 @@ xfs_dir2_block_lookup_int( dp = args->dp; tp = args->trans; - error = xfs_dir3_block_read(tp, dp, &bp); + error = xfs_dir3_block_read(tp, dp, args->owner, &bp); if (error) return error; @@ -979,7 +986,8 @@ xfs_dir2_leaf_to_block( * Read the data block if we don't already have it, give up if it fails. */ if (!dbp) { - error = xfs_dir3_data_read(tp, dp, args->geo->datablk, 0, &dbp); + error = xfs_dir3_data_read(tp, dp, args->owner, + args->geo->datablk, 0, &dbp); if (error) return error; } @@ -1007,7 +1015,7 @@ xfs_dir2_leaf_to_block( /* * Start converting it to block form. */ - xfs_dir3_block_init(mp, tp, dbp, dp); + xfs_dir3_block_init(args, dbp); needlog = 1; needscan = 0; @@ -1089,7 +1097,7 @@ xfs_dir2_sf_to_block( int newoffset; /* offset from current entry */ unsigned int offset = geo->data_entry_offset; xfs_dir2_sf_entry_t *sfep; /* sf entry pointer */ - xfs_dir2_sf_hdr_t *oldsfp; /* old shortform header */ + struct xfs_dir2_sf_hdr *oldsfp = ifp->if_data; xfs_dir2_sf_hdr_t *sfp; /* shortform header */ __be16 *tagp; /* end of data entry */ struct xfs_name name; @@ -1099,10 +1107,8 @@ xfs_dir2_sf_to_block( ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent)); - oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data; - ASSERT(ifp->if_bytes == dp->i_disk_size); - ASSERT(ifp->if_u1.if_data != NULL); + ASSERT(oldsfp != NULL); ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count)); ASSERT(dp->i_df.if_nextents == 0); @@ -1110,7 +1116,7 @@ xfs_dir2_sf_to_block( * Copy the directory into a temporary buffer. * Then pitch the incore inode data so we can make extents. */ - sfp = kmem_alloc(ifp->if_bytes, 0); + sfp = kmalloc(ifp->if_bytes, GFP_KERNEL | __GFP_NOFAIL); memcpy(sfp, oldsfp, ifp->if_bytes); xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK); @@ -1129,7 +1135,7 @@ xfs_dir2_sf_to_block( error = xfs_dir3_data_init(args, blkno, &bp); if (error) goto out_free; - xfs_dir3_block_init(mp, tp, bp, dp); + xfs_dir3_block_init(args, bp); hdr = bp->b_addr; /* @@ -1169,7 +1175,7 @@ xfs_dir2_sf_to_block( * Create entry for . */ dep = bp->b_addr + offset; - dep->inumber = cpu_to_be64(dp->i_ino); + dep->inumber = cpu_to_be64(args->owner); dep->namelen = 1; dep->name[0] = '.'; xfs_dir2_data_put_ftype(mp, dep, XFS_DIR3_FT_DIR); @@ -1255,7 +1261,7 @@ xfs_dir2_sf_to_block( sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep); } /* Done with the temporary buffer */ - kmem_free(sfp); + kfree(sfp); /* * Sort the leaf entries by hash value. */ @@ -1270,6 +1276,6 @@ xfs_dir2_sf_to_block( xfs_dir3_data_check(dp, bp); return 0; out_free: - kmem_free(sfp); + kfree(sfp); return error; } diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c index dbcf58979a59..a16b05c43e2e 100644 --- a/fs/xfs/libxfs/xfs_dir2_data.c +++ b/fs/xfs/libxfs/xfs_dir2_data.c @@ -18,6 +18,7 @@ #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_log.h" +#include "xfs_health.h" static xfs_failaddr_t xfs_dir2_data_freefind_verify( struct xfs_dir2_data_hdr *hdr, struct xfs_dir2_data_free *bf, @@ -177,6 +178,14 @@ __xfs_dir3_data_check( while (offset < end) { struct xfs_dir2_data_unused *dup = bp->b_addr + offset; struct xfs_dir2_data_entry *dep = bp->b_addr + offset; + unsigned int reclen; + + /* + * Are the remaining bytes large enough to hold an + * unused entry? + */ + if (offset > end - xfs_dir2_data_unusedsize(1)) + return __this_address; /* * If it's unused, look for the space in the bestfree table. @@ -186,9 +195,13 @@ __xfs_dir3_data_check( if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { xfs_failaddr_t fa; + reclen = xfs_dir2_data_unusedsize( + be16_to_cpu(dup->length)); if (lastfree != 0) return __this_address; - if (offset + be16_to_cpu(dup->length) > end) + if (be16_to_cpu(dup->length) != reclen) + return __this_address; + if (offset + reclen > end) return __this_address; if (be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) != offset) @@ -206,10 +219,18 @@ __xfs_dir3_data_check( be16_to_cpu(bf[2].length)) return __this_address; } - offset += be16_to_cpu(dup->length); + offset += reclen; lastfree = 1; continue; } + + /* + * This is not an unused entry. Are the remaining bytes + * large enough for a dirent with a single-byte name? + */ + if (offset > end - xfs_dir2_data_entsize(mp, 1)) + return __this_address; + /* * It's a real entry. Validate the fields. * If this is a block directory then make sure it's @@ -218,9 +239,10 @@ __xfs_dir3_data_check( */ if (dep->namelen == 0) return __this_address; - if (!xfs_verify_dir_ino(mp, be64_to_cpu(dep->inumber))) + reclen = xfs_dir2_data_entsize(mp, dep->namelen); + if (offset + reclen > end) return __this_address; - if (offset + xfs_dir2_data_entsize(mp, dep->namelen) > end) + if (!xfs_verify_dir_ino(mp, be64_to_cpu(dep->inumber))) return __this_address; if (be16_to_cpu(*xfs_dir2_data_entry_tag_p(mp, dep)) != offset) return __this_address; @@ -244,7 +266,7 @@ __xfs_dir3_data_check( if (i >= be32_to_cpu(btp->count)) return __this_address; } - offset += xfs_dir2_data_entsize(mp, dep->namelen); + offset += reclen; } /* * Need to have seen all the entries and all the bestfree slots. @@ -394,17 +416,20 @@ static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = { .verify_write = xfs_dir3_data_write_verify, }; -static xfs_failaddr_t +xfs_failaddr_t xfs_dir3_data_header_check( - struct xfs_inode *dp, - struct xfs_buf *bp) + struct xfs_buf *bp, + xfs_ino_t owner) { - struct xfs_mount *mp = dp->i_mount; + struct xfs_mount *mp = bp->b_mount; if (xfs_has_crc(mp)) { struct xfs_dir3_data_hdr *hdr3 = bp->b_addr; - if (be64_to_cpu(hdr3->hdr.owner) != dp->i_ino) + if (hdr3->hdr.magic != cpu_to_be32(XFS_DIR3_DATA_MAGIC)) + return __this_address; + + if (be64_to_cpu(hdr3->hdr.owner) != owner) return __this_address; } @@ -415,6 +440,7 @@ int xfs_dir3_data_read( struct xfs_trans *tp, struct xfs_inode *dp, + xfs_ino_t owner, xfs_dablk_t bno, unsigned int flags, struct xfs_buf **bpp) @@ -428,11 +454,12 @@ xfs_dir3_data_read( return err; /* Check things that we can't do in the verifier. */ - fa = xfs_dir3_data_header_check(dp, *bpp); + fa = xfs_dir3_data_header_check(*bpp, owner); if (fa) { __xfs_buf_mark_corrupt(*bpp, fa); xfs_trans_brelse(tp, *bpp); *bpp = NULL; + xfs_dirattr_mark_sick(dp, XFS_DATA_FORK); return -EFSCORRUPTED; } @@ -723,7 +750,7 @@ xfs_dir3_data_init( memset(hdr3, 0, sizeof(*hdr3)); hdr3->magic = cpu_to_be32(XFS_DIR3_DATA_MAGIC); hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp)); - hdr3->owner = cpu_to_be64(dp->i_ino); + hdr3->owner = cpu_to_be64(args->owner); uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid); } else @@ -1198,6 +1225,7 @@ xfs_dir2_data_use_free( corrupt: xfs_corruption_error(__func__, XFS_ERRLEVEL_LOW, args->dp->i_mount, hdr, sizeof(*hdr), __FILE__, __LINE__, fa); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index cb9e950a911d..71c2f22a3f6e 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -19,6 +19,7 @@ #include "xfs_trace.h" #include "xfs_trans.h" #include "xfs_buf_item.h" +#include "xfs_health.h" /* * Local function declarations. @@ -207,6 +208,29 @@ xfs_dir3_leaf_verify( return xfs_dir3_leaf_check_int(mp, &leafhdr, bp->b_addr, true); } +xfs_failaddr_t +xfs_dir3_leaf_header_check( + struct xfs_buf *bp, + xfs_ino_t owner) +{ + struct xfs_mount *mp = bp->b_mount; + + if (xfs_has_crc(mp)) { + struct xfs_dir3_leaf *hdr3 = bp->b_addr; + + if (hdr3->hdr.info.hdr.magic != + cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) && + hdr3->hdr.info.hdr.magic != + cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) + return __this_address; + + if (be64_to_cpu(hdr3->hdr.info.owner) != owner) + return __this_address; + } + + return NULL; +} + static void xfs_dir3_leaf_read_verify( struct xfs_buf *bp) @@ -270,32 +294,60 @@ int xfs_dir3_leaf_read( struct xfs_trans *tp, struct xfs_inode *dp, + xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp) { + xfs_failaddr_t fa; int err; err = xfs_da_read_buf(tp, dp, fbno, 0, bpp, XFS_DATA_FORK, &xfs_dir3_leaf1_buf_ops); - if (!err && tp && *bpp) + if (err || !(*bpp)) + return err; + + fa = xfs_dir3_leaf_header_check(*bpp, owner); + if (fa) { + __xfs_buf_mark_corrupt(*bpp, fa); + xfs_trans_brelse(tp, *bpp); + *bpp = NULL; + xfs_dirattr_mark_sick(dp, XFS_DATA_FORK); + return -EFSCORRUPTED; + } + + if (tp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF); - return err; + return 0; } int xfs_dir3_leafn_read( struct xfs_trans *tp, struct xfs_inode *dp, + xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp) { + xfs_failaddr_t fa; int err; err = xfs_da_read_buf(tp, dp, fbno, 0, bpp, XFS_DATA_FORK, &xfs_dir3_leafn_buf_ops); - if (!err && tp && *bpp) + if (err || !(*bpp)) + return err; + + fa = xfs_dir3_leaf_header_check(*bpp, owner); + if (fa) { + __xfs_buf_mark_corrupt(*bpp, fa); + xfs_trans_brelse(tp, *bpp); + *bpp = NULL; + xfs_dirattr_mark_sick(dp, XFS_DATA_FORK); + return -EFSCORRUPTED; + } + + if (tp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF); - return err; + return 0; } /* @@ -303,12 +355,12 @@ xfs_dir3_leafn_read( */ static void xfs_dir3_leaf_init( - struct xfs_mount *mp, - struct xfs_trans *tp, + struct xfs_da_args *args, struct xfs_buf *bp, - xfs_ino_t owner, uint16_t type) { + struct xfs_mount *mp = args->dp->i_mount; + struct xfs_trans *tp = args->trans; struct xfs_dir2_leaf *leaf = bp->b_addr; ASSERT(type == XFS_DIR2_LEAF1_MAGIC || type == XFS_DIR2_LEAFN_MAGIC); @@ -322,7 +374,7 @@ xfs_dir3_leaf_init( ? cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) : cpu_to_be16(XFS_DIR3_LEAFN_MAGIC); leaf3->info.blkno = cpu_to_be64(xfs_buf_daddr(bp)); - leaf3->info.owner = cpu_to_be64(owner); + leaf3->info.owner = cpu_to_be64(args->owner); uuid_copy(&leaf3->info.uuid, &mp->m_sb.sb_meta_uuid); } else { memset(leaf, 0, sizeof(*leaf)); @@ -355,7 +407,6 @@ xfs_dir3_leaf_get_buf( { struct xfs_inode *dp = args->dp; struct xfs_trans *tp = args->trans; - struct xfs_mount *mp = dp->i_mount; struct xfs_buf *bp; int error; @@ -368,7 +419,7 @@ xfs_dir3_leaf_get_buf( if (error) return error; - xfs_dir3_leaf_init(mp, tp, bp, dp->i_ino, magic); + xfs_dir3_leaf_init(args, bp, magic); xfs_dir3_leaf_log_header(args, bp); if (magic == XFS_DIR2_LEAF1_MAGIC) xfs_dir3_leaf_log_tail(args, bp); @@ -646,7 +697,8 @@ xfs_dir2_leaf_addname( trace_xfs_dir2_leaf_addname(args); - error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, &lbp); + error = xfs_dir3_leaf_read(tp, dp, args->owner, args->geo->leafblk, + &lbp); if (error) return error; @@ -833,9 +885,9 @@ xfs_dir2_leaf_addname( * Already had space in some data block. * Just read that one in. */ - error = xfs_dir3_data_read(tp, dp, - xfs_dir2_db_to_da(args->geo, use_block), - 0, &dbp); + error = xfs_dir3_data_read(tp, dp, args->owner, + xfs_dir2_db_to_da(args->geo, use_block), 0, + &dbp); if (error) { xfs_trans_brelse(tp, lbp); return error; @@ -1237,7 +1289,8 @@ xfs_dir2_leaf_lookup_int( tp = args->trans; mp = dp->i_mount; - error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, &lbp); + error = xfs_dir3_leaf_read(tp, dp, args->owner, args->geo->leafblk, + &lbp); if (error) return error; @@ -1275,9 +1328,9 @@ xfs_dir2_leaf_lookup_int( if (newdb != curdb) { if (dbp) xfs_trans_brelse(tp, dbp); - error = xfs_dir3_data_read(tp, dp, - xfs_dir2_db_to_da(args->geo, newdb), - 0, &dbp); + error = xfs_dir3_data_read(tp, dp, args->owner, + xfs_dir2_db_to_da(args->geo, newdb), 0, + &dbp); if (error) { xfs_trans_brelse(tp, lbp); return error; @@ -1317,9 +1370,9 @@ xfs_dir2_leaf_lookup_int( ASSERT(cidb != -1); if (cidb != curdb) { xfs_trans_brelse(tp, dbp); - error = xfs_dir3_data_read(tp, dp, - xfs_dir2_db_to_da(args->geo, cidb), - 0, &dbp); + error = xfs_dir3_data_read(tp, dp, args->owner, + xfs_dir2_db_to_da(args->geo, cidb), 0, + &dbp); if (error) { xfs_trans_brelse(tp, lbp); return error; @@ -1393,8 +1446,10 @@ xfs_dir2_leaf_removename( bestsp = xfs_dir2_leaf_bests_p(ltp); if (be16_to_cpu(bestsp[db]) != oldbest) { xfs_buf_mark_corrupt(lbp); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } + /* * Mark the former data entry unused. */ @@ -1611,7 +1666,8 @@ xfs_dir2_leaf_trim_data( /* * Read the offending data block. We need its buffer. */ - error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(geo, db), 0, &dbp); + error = xfs_dir3_data_read(tp, dp, args->owner, + xfs_dir2_db_to_da(geo, db), 0, &dbp); if (error) return error; @@ -1750,7 +1806,8 @@ xfs_dir2_node_to_leaf( /* * Read the freespace block. */ - error = xfs_dir2_free_read(tp, dp, args->geo->freeblk, &fbp); + error = xfs_dir2_free_read(tp, dp, args->owner, args->geo->freeblk, + &fbp); if (error) return error; xfs_dir2_free_hdr_from_disk(mp, &freehdr, fbp->b_addr); diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index 7a03aeb9f4c9..fe8d4fa13128 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -20,6 +20,7 @@ #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_log.h" +#include "xfs_health.h" /* * Function declarations. @@ -174,11 +175,11 @@ const struct xfs_buf_ops xfs_dir3_free_buf_ops = { /* Everything ok in the free block header? */ static xfs_failaddr_t xfs_dir3_free_header_check( - struct xfs_inode *dp, - xfs_dablk_t fbno, - struct xfs_buf *bp) + struct xfs_buf *bp, + xfs_ino_t owner, + xfs_dablk_t fbno) { - struct xfs_mount *mp = dp->i_mount; + struct xfs_mount *mp = bp->b_mount; int maxbests = mp->m_dir_geo->free_max_bests; unsigned int firstdb; @@ -194,7 +195,7 @@ xfs_dir3_free_header_check( return __this_address; if (be32_to_cpu(hdr3->nvalid) < be32_to_cpu(hdr3->nused)) return __this_address; - if (be64_to_cpu(hdr3->hdr.owner) != dp->i_ino) + if (be64_to_cpu(hdr3->hdr.owner) != owner) return __this_address; } else { struct xfs_dir2_free_hdr *hdr = bp->b_addr; @@ -213,6 +214,7 @@ static int __xfs_dir3_free_read( struct xfs_trans *tp, struct xfs_inode *dp, + xfs_ino_t owner, xfs_dablk_t fbno, unsigned int flags, struct xfs_buf **bpp) @@ -226,11 +228,12 @@ __xfs_dir3_free_read( return err; /* Check things that we can't do in the verifier. */ - fa = xfs_dir3_free_header_check(dp, fbno, *bpp); + fa = xfs_dir3_free_header_check(*bpp, owner, fbno); if (fa) { __xfs_buf_mark_corrupt(*bpp, fa); xfs_trans_brelse(tp, *bpp); *bpp = NULL; + xfs_dirattr_mark_sick(dp, XFS_DATA_FORK); return -EFSCORRUPTED; } @@ -297,20 +300,23 @@ int xfs_dir2_free_read( struct xfs_trans *tp, struct xfs_inode *dp, + xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp) { - return __xfs_dir3_free_read(tp, dp, fbno, 0, bpp); + return __xfs_dir3_free_read(tp, dp, owner, fbno, 0, bpp); } static int xfs_dir2_free_try_read( struct xfs_trans *tp, struct xfs_inode *dp, + xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp) { - return __xfs_dir3_free_read(tp, dp, fbno, XFS_DABUF_MAP_HOLE_OK, bpp); + return __xfs_dir3_free_read(tp, dp, owner, fbno, XFS_DABUF_MAP_HOLE_OK, + bpp); } static int @@ -347,7 +353,7 @@ xfs_dir3_free_get_buf( hdr.magic = XFS_DIR3_FREE_MAGIC; hdr3->hdr.blkno = cpu_to_be64(xfs_buf_daddr(bp)); - hdr3->hdr.owner = cpu_to_be64(dp->i_ino); + hdr3->hdr.owner = cpu_to_be64(args->owner); uuid_copy(&hdr3->hdr.uuid, &mp->m_sb.sb_meta_uuid); } else hdr.magic = XFS_DIR2_FREE_MAGIC; @@ -443,6 +449,7 @@ xfs_dir2_leaf_to_node( if (be32_to_cpu(ltp->bestcount) > (uint)dp->i_disk_size / args->geo->blksize) { xfs_buf_mark_corrupt(lbp); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } @@ -517,6 +524,7 @@ xfs_dir2_leafn_add( */ if (index < 0) { xfs_buf_mark_corrupt(bp); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } @@ -713,7 +721,7 @@ xfs_dir2_leafn_lookup_for_addname( if (curbp) xfs_trans_brelse(tp, curbp); - error = xfs_dir2_free_read(tp, dp, + error = xfs_dir2_free_read(tp, dp, args->owner, xfs_dir2_db_to_da(args->geo, newfdb), &curbp); @@ -736,6 +744,7 @@ xfs_dir2_leafn_lookup_for_addname( cpu_to_be16(NULLDATAOFF))) { if (curfdb != newfdb) xfs_trans_brelse(tp, curbp); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } curfdb = newfdb; @@ -804,6 +813,7 @@ xfs_dir2_leafn_lookup_for_entry( xfs_dir3_leaf_check(dp, bp); if (leafhdr.count <= 0) { xfs_buf_mark_corrupt(bp); + xfs_da_mark_sick(args); return -EFSCORRUPTED; } @@ -857,7 +867,7 @@ xfs_dir2_leafn_lookup_for_entry( ASSERT(state->extravalid); curbp = state->extrablk.bp; } else { - error = xfs_dir3_data_read(tp, dp, + error = xfs_dir3_data_read(tp, dp, args->owner, xfs_dir2_db_to_da(args->geo, newdb), 0, &curbp); @@ -1350,8 +1360,8 @@ xfs_dir2_leafn_remove( * read in the free block. */ fdb = xfs_dir2_db_to_fdb(geo, db); - error = xfs_dir2_free_read(tp, dp, xfs_dir2_db_to_da(geo, fdb), - &fbp); + error = xfs_dir2_free_read(tp, dp, args->owner, + xfs_dir2_db_to_da(geo, fdb), &fbp); if (error) return error; free = fbp->b_addr; @@ -1556,7 +1566,8 @@ xfs_dir2_leafn_toosmall( /* * Read the sibling leaf block. */ - error = xfs_dir3_leafn_read(state->args->trans, dp, blkno, &bp); + error = xfs_dir3_leafn_read(state->args->trans, dp, + state->args->owner, blkno, &bp); if (error) return error; @@ -1709,7 +1720,7 @@ xfs_dir2_node_add_datablk( * that was just allocated. */ fbno = xfs_dir2_db_to_fdb(args->geo, *dbno); - error = xfs_dir2_free_try_read(tp, dp, + error = xfs_dir2_free_try_read(tp, dp, args->owner, xfs_dir2_db_to_da(args->geo, fbno), &fbp); if (error) return error; @@ -1739,6 +1750,7 @@ xfs_dir2_node_add_datablk( } else { xfs_alert(mp, " ... fblk is NULL"); } + xfs_da_mark_sick(args); return -EFSCORRUPTED; } @@ -1855,7 +1867,7 @@ xfs_dir2_node_find_freeblk( * so this might not succeed. This should be really rare, so * there's no reason to avoid it. */ - error = xfs_dir2_free_try_read(tp, dp, + error = xfs_dir2_free_try_read(tp, dp, args->owner, xfs_dir2_db_to_da(args->geo, fbno), &fbp); if (error) @@ -1941,9 +1953,8 @@ xfs_dir2_node_addname_int( &freehdr, &findex); } else { /* Read the data block in. */ - error = xfs_dir3_data_read(tp, dp, - xfs_dir2_db_to_da(args->geo, dbno), - 0, &dbp); + error = xfs_dir3_data_read(tp, dp, args->owner, + xfs_dir2_db_to_da(args->geo, dbno), 0, &dbp); } if (error) return error; @@ -2295,7 +2306,7 @@ xfs_dir2_node_trim_free( /* * Read the freespace block. */ - error = xfs_dir2_free_try_read(tp, dp, fo, &bp); + error = xfs_dir2_free_try_read(tp, dp, args->owner, fo, &bp); if (error) return error; /* diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h index 7404a9ff1a92..10041350274a 100644 --- a/fs/xfs/libxfs/xfs_dir2_priv.h +++ b/fs/xfs/libxfs/xfs_dir2_priv.h @@ -50,8 +50,8 @@ extern int xfs_dir_cilookup_result(struct xfs_da_args *args, /* xfs_dir2_block.c */ -extern int xfs_dir3_block_read(struct xfs_trans *tp, struct xfs_inode *dp, - struct xfs_buf **bpp); +int xfs_dir3_block_read(struct xfs_trans *tp, struct xfs_inode *dp, + xfs_ino_t owner, struct xfs_buf **bpp); extern int xfs_dir2_block_addname(struct xfs_da_args *args); extern int xfs_dir2_block_lookup(struct xfs_da_args *args); extern int xfs_dir2_block_removename(struct xfs_da_args *args); @@ -78,7 +78,8 @@ extern void xfs_dir3_data_check(struct xfs_inode *dp, struct xfs_buf *bp); extern xfs_failaddr_t __xfs_dir3_data_check(struct xfs_inode *dp, struct xfs_buf *bp); int xfs_dir3_data_read(struct xfs_trans *tp, struct xfs_inode *dp, - xfs_dablk_t bno, unsigned int flags, struct xfs_buf **bpp); + xfs_ino_t owner, xfs_dablk_t bno, unsigned int flags, + struct xfs_buf **bpp); int xfs_dir3_data_readahead(struct xfs_inode *dp, xfs_dablk_t bno, unsigned int flags); @@ -95,9 +96,9 @@ void xfs_dir2_leaf_hdr_from_disk(struct xfs_mount *mp, void xfs_dir2_leaf_hdr_to_disk(struct xfs_mount *mp, struct xfs_dir2_leaf *to, struct xfs_dir3_icleaf_hdr *from); int xfs_dir3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp, - xfs_dablk_t fbno, struct xfs_buf **bpp); + xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp); int xfs_dir3_leafn_read(struct xfs_trans *tp, struct xfs_inode *dp, - xfs_dablk_t fbno, struct xfs_buf **bpp); + xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp); extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args, struct xfs_buf *dbp); extern int xfs_dir2_leaf_addname(struct xfs_da_args *args); @@ -154,8 +155,8 @@ extern int xfs_dir2_node_removename(struct xfs_da_args *args); extern int xfs_dir2_node_replace(struct xfs_da_args *args); extern int xfs_dir2_node_trim_free(struct xfs_da_args *args, xfs_fileoff_t fo, int *rvalp); -extern int xfs_dir2_free_read(struct xfs_trans *tp, struct xfs_inode *dp, - xfs_dablk_t fbno, struct xfs_buf **bpp); +int xfs_dir2_free_read(struct xfs_trans *tp, struct xfs_inode *dp, + xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp); /* xfs_dir2_sf.c */ xfs_ino_t xfs_dir2_sf_get_ino(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr, @@ -175,7 +176,8 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino); extern int xfs_dir2_sf_lookup(struct xfs_da_args *args); extern int xfs_dir2_sf_removename(struct xfs_da_args *args); extern int xfs_dir2_sf_replace(struct xfs_da_args *args); -extern xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_inode *ip); +xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_mount *mp, + struct xfs_dir2_sf_hdr *sfp, int64_t size); int xfs_dir2_sf_entsize(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr, int len); void xfs_dir2_sf_put_ino(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr, @@ -188,6 +190,13 @@ extern int xfs_readdir(struct xfs_trans *tp, struct xfs_inode *dp, struct dir_context *ctx, size_t bufsize); static inline unsigned int +xfs_dir2_data_unusedsize( + unsigned int len) +{ + return round_up(len, XFS_DIR2_DATA_ALIGN); +} + +static inline unsigned int xfs_dir2_data_entsize( struct xfs_mount *mp, unsigned int namelen) diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 8cd37e6e9d38..17a20384c8b7 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -276,7 +276,7 @@ xfs_dir2_block_to_sf( * format the data into. Once we have formatted the data, we can free * the block and copy the formatted data into the inode literal area. */ - sfp = kmem_alloc(mp->m_sb.sb_inodesize, 0); + sfp = kmalloc(mp->m_sb.sb_inodesize, GFP_KERNEL | __GFP_NOFAIL); memcpy(sfp, sfhp, xfs_dir2_sf_hdr_size(sfhp->i8count)); /* @@ -350,7 +350,7 @@ xfs_dir2_block_to_sf( xfs_dir2_sf_check(args); out: xfs_trans_log_inode(args->trans, dp, logflags); - kmem_free(sfp); + kfree(sfp); return error; } @@ -364,25 +364,23 @@ int /* error */ xfs_dir2_sf_addname( xfs_da_args_t *args) /* operation arguments */ { - xfs_inode_t *dp; /* incore directory inode */ + struct xfs_inode *dp = args->dp; + struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int error; /* error return value */ int incr_isize; /* total change in size */ int new_isize; /* size after adding name */ int objchange; /* changing to 8-byte inodes */ xfs_dir2_data_aoff_t offset = 0; /* offset for new entry */ int pick; /* which algorithm to use */ - xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ xfs_dir2_sf_entry_t *sfep = NULL; /* shortform entry */ trace_xfs_dir2_sf_addname(args); ASSERT(xfs_dir2_sf_lookup(args) == -ENOENT); - dp = args->dp; ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL); ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent)); ASSERT(dp->i_df.if_bytes == dp->i_disk_size); - ASSERT(dp->i_df.if_u1.if_data != NULL); - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(sfp != NULL); ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Compute entry (and change in) size. @@ -462,20 +460,17 @@ xfs_dir2_sf_addname_easy( { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; - int byteoff; /* byte offset in sf dir */ - xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ + struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; + int byteoff = (int)((char *)sfep - (char *)sfp); - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; - byteoff = (int)((char *)sfep - (char *)sfp); /* * Grow the in-inode space. */ - xfs_idata_realloc(dp, xfs_dir2_sf_entsize(mp, sfp, args->namelen), + sfp = xfs_idata_realloc(dp, xfs_dir2_sf_entsize(mp, sfp, args->namelen), XFS_DATA_FORK); /* * Need to set up again due to realloc of the inode data. */ - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; sfep = (xfs_dir2_sf_entry_t *)((char *)sfp + byteoff); /* * Fill in the new entry. @@ -528,11 +523,10 @@ xfs_dir2_sf_addname_hard( /* * Copy the old directory to the stack buffer. */ - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; old_isize = (int)dp->i_disk_size; - buf = kmem_alloc(old_isize, 0); + buf = kmalloc(old_isize, GFP_KERNEL | __GFP_NOFAIL); oldsfp = (xfs_dir2_sf_hdr_t *)buf; - memcpy(oldsfp, sfp, old_isize); + memcpy(oldsfp, dp->i_df.if_data, old_isize); /* * Loop over the old directory finding the place we're going * to insert the new entry. @@ -556,11 +550,8 @@ xfs_dir2_sf_addname_hard( * the data. */ xfs_idata_realloc(dp, -old_isize, XFS_DATA_FORK); - xfs_idata_realloc(dp, new_isize, XFS_DATA_FORK); - /* - * Reset the pointer since the buffer was reallocated. - */ - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + sfp = xfs_idata_realloc(dp, new_isize, XFS_DATA_FORK); + /* * Copy the first part of the directory, including the header. */ @@ -585,7 +576,7 @@ xfs_dir2_sf_addname_hard( sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep); memcpy(sfep, oldsfep, old_isize - nbytes); } - kmem_free(buf); + kfree(buf); dp->i_disk_size = new_isize; xfs_dir2_sf_check(args); } @@ -610,11 +601,10 @@ xfs_dir2_sf_addname_pick( int i; /* entry number */ xfs_dir2_data_aoff_t offset; /* data block offset */ xfs_dir2_sf_entry_t *sfep; /* shortform entry */ - xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ + struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int size; /* entry's data size */ int used; /* data bytes used */ - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; size = xfs_dir2_data_entsize(mp, args->namelen); offset = args->geo->data_first_offset; sfep = xfs_dir2_sf_firstentry(sfp); @@ -673,14 +663,13 @@ xfs_dir2_sf_check( { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; + struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int i; /* entry number */ int i8count; /* number of big inode#s */ xfs_ino_t ino; /* entry inode number */ int offset; /* data offset */ xfs_dir2_sf_entry_t *sfep; /* shortform dir entry */ - xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; offset = args->geo->data_first_offset; ino = xfs_dir2_sf_get_parent_ino(sfp); i8count = ino > XFS_DIR2_MAX_SHORT_INUM; @@ -707,11 +696,10 @@ xfs_dir2_sf_check( /* Verify the consistency of an inline directory. */ xfs_failaddr_t xfs_dir2_sf_verify( - struct xfs_inode *ip) + struct xfs_mount *mp, + struct xfs_dir2_sf_hdr *sfp, + int64_t size) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); - struct xfs_dir2_sf_hdr *sfp; struct xfs_dir2_sf_entry *sfep; struct xfs_dir2_sf_entry *next_sfep; char *endp; @@ -719,15 +707,9 @@ xfs_dir2_sf_verify( int i; int i8count; int offset; - int64_t size; int error; uint8_t filetype; - ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); - - sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data; - size = ifp->if_bytes; - /* * Give up if the directory is way too short. */ @@ -834,15 +816,13 @@ xfs_dir2_sf_create( ASSERT(dp->i_df.if_bytes == 0); i8count = pino > XFS_DIR2_MAX_SHORT_INUM; size = xfs_dir2_sf_hdr_size(i8count); + /* - * Make a buffer for the data. - */ - xfs_idata_realloc(dp, size, XFS_DATA_FORK); - /* - * Fill in the header, + * Make a buffer for the data and fill in the header. */ - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + sfp = xfs_idata_realloc(dp, size, XFS_DATA_FORK); sfp->i8count = i8count; + /* * Now can put in the inode number, since i8count is set. */ @@ -864,9 +844,9 @@ xfs_dir2_sf_lookup( { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; + struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int i; /* entry index */ xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ - xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ enum xfs_dacmp cmp; /* comparison result */ xfs_dir2_sf_entry_t *ci_sfep; /* case-insens. entry */ @@ -877,8 +857,7 @@ xfs_dir2_sf_lookup( ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL); ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent)); ASSERT(dp->i_df.if_bytes == dp->i_disk_size); - ASSERT(dp->i_df.if_u1.if_data != NULL); - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(sfp != NULL); ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Special case for . @@ -940,13 +919,13 @@ xfs_dir2_sf_removename( { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; + struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int byteoff; /* offset of removed entry */ int entsize; /* this entry's size */ int i; /* shortform entry index */ int newsize; /* new inode size */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ - xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ trace_xfs_dir2_sf_removename(args); @@ -954,8 +933,7 @@ xfs_dir2_sf_removename( oldsize = (int)dp->i_disk_size; ASSERT(oldsize >= offsetof(struct xfs_dir2_sf_hdr, parent)); ASSERT(dp->i_df.if_bytes == oldsize); - ASSERT(dp->i_df.if_u1.if_data != NULL); - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(sfp != NULL); ASSERT(oldsize >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Loop over the old directory entries. @@ -992,11 +970,12 @@ xfs_dir2_sf_removename( */ sfp->count--; dp->i_disk_size = newsize; + /* * Reallocate, making it smaller. */ - xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK); - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + sfp = xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK); + /* * Are we changing inode number size? */ @@ -1019,13 +998,12 @@ xfs_dir2_sf_replace_needblock( struct xfs_inode *dp, xfs_ino_t inum) { + struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int newsize; - struct xfs_dir2_sf_hdr *sfp; if (dp->i_df.if_format != XFS_DINODE_FMT_LOCAL) return false; - sfp = (struct xfs_dir2_sf_hdr *)dp->i_df.if_u1.if_data; newsize = dp->i_df.if_bytes + (sfp->count + 1) * XFS_INO64_DIFF; return inum > XFS_DIR2_MAX_SHORT_INUM && @@ -1041,19 +1019,18 @@ xfs_dir2_sf_replace( { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; + struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int i; /* entry index */ xfs_ino_t ino=0; /* entry old inode number */ int i8elevated; /* sf_toino8 set i8count=1 */ xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ - xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ trace_xfs_dir2_sf_replace(args); ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL); ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent)); ASSERT(dp->i_df.if_bytes == dp->i_disk_size); - ASSERT(dp->i_df.if_u1.if_data != NULL); - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(sfp != NULL); ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* @@ -1076,7 +1053,7 @@ xfs_dir2_sf_replace( */ xfs_dir2_sf_toino8(args); i8elevated = 1; - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + sfp = dp->i_df.if_data; } else i8elevated = 0; @@ -1157,11 +1134,11 @@ xfs_dir2_sf_toino4( { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; + struct xfs_dir2_sf_hdr *oldsfp = dp->i_df.if_data; char *buf; /* old dir's buffer */ int i; /* entry index */ int newsize; /* new inode size */ xfs_dir2_sf_entry_t *oldsfep; /* old sf entry */ - xfs_dir2_sf_hdr_t *oldsfp; /* old sf directory */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* new sf entry */ xfs_dir2_sf_hdr_t *sfp; /* new sf directory */ @@ -1174,8 +1151,7 @@ xfs_dir2_sf_toino4( * Don't want xfs_idata_realloc copying the data here. */ oldsize = dp->i_df.if_bytes; - buf = kmem_alloc(oldsize, 0); - oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + buf = kmalloc(oldsize, GFP_KERNEL | __GFP_NOFAIL); ASSERT(oldsfp->i8count == 1); memcpy(buf, oldsfp, oldsize); /* @@ -1188,7 +1164,7 @@ xfs_dir2_sf_toino4( * Reset our pointers, the data has moved. */ oldsfp = (xfs_dir2_sf_hdr_t *)buf; - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + sfp = dp->i_df.if_data; /* * Fill in the new header. */ @@ -1214,7 +1190,7 @@ xfs_dir2_sf_toino4( /* * Clean up the inode. */ - kmem_free(buf); + kfree(buf); dp->i_disk_size = newsize; xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); } @@ -1230,11 +1206,11 @@ xfs_dir2_sf_toino8( { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; + struct xfs_dir2_sf_hdr *oldsfp = dp->i_df.if_data; char *buf; /* old dir's buffer */ int i; /* entry index */ int newsize; /* new inode size */ xfs_dir2_sf_entry_t *oldsfep; /* old sf entry */ - xfs_dir2_sf_hdr_t *oldsfp; /* old sf directory */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* new sf entry */ xfs_dir2_sf_hdr_t *sfp; /* new sf directory */ @@ -1247,8 +1223,7 @@ xfs_dir2_sf_toino8( * Don't want xfs_idata_realloc copying the data here. */ oldsize = dp->i_df.if_bytes; - buf = kmem_alloc(oldsize, 0); - oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + buf = kmalloc(oldsize, GFP_KERNEL | __GFP_NOFAIL); ASSERT(oldsfp->i8count == 0); memcpy(buf, oldsfp, oldsize); /* @@ -1261,7 +1236,7 @@ xfs_dir2_sf_toino8( * Reset our pointers, the data has moved. */ oldsfp = (xfs_dir2_sf_hdr_t *)buf; - sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + sfp = dp->i_df.if_data; /* * Fill in the new header. */ @@ -1287,7 +1262,7 @@ xfs_dir2_sf_toino8( /* * Clean up the inode. */ - kmem_free(buf); + kfree(buf); dp->i_disk_size = newsize; xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); } diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c index 15a362e2f5ea..dceef2abd4e2 100644 --- a/fs/xfs/libxfs/xfs_dquot_buf.c +++ b/fs/xfs/libxfs/xfs_dquot_buf.c @@ -16,6 +16,9 @@ #include "xfs_trans.h" #include "xfs_qm.h" #include "xfs_error.h" +#include "xfs_health.h" +#include "xfs_metadir.h" +#include "xfs_metafile.h" int xfs_calc_dquots_per_chunk( @@ -323,3 +326,190 @@ xfs_dquot_to_disk_ts( return cpu_to_be32(t); } + +inline unsigned int +xfs_dqinode_sick_mask(xfs_dqtype_t type) +{ + switch (type) { + case XFS_DQTYPE_USER: + return XFS_SICK_FS_UQUOTA; + case XFS_DQTYPE_GROUP: + return XFS_SICK_FS_GQUOTA; + case XFS_DQTYPE_PROJ: + return XFS_SICK_FS_PQUOTA; + } + + ASSERT(0); + return 0; +} + +/* + * Load the inode for a given type of quota, assuming that the sb fields have + * been sorted out. This is not true when switching quota types on a V4 + * filesystem, so do not use this function for that. If metadir is enabled, + * @dp must be the /quota metadir. + * + * Returns -ENOENT if the quota inode field is NULLFSINO; 0 and an inode on + * success; or a negative errno. + */ +int +xfs_dqinode_load( + struct xfs_trans *tp, + struct xfs_inode *dp, + xfs_dqtype_t type, + struct xfs_inode **ipp) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_inode *ip; + enum xfs_metafile_type metafile_type = xfs_dqinode_metafile_type(type); + int error; + + if (!xfs_has_metadir(mp)) { + xfs_ino_t ino; + + switch (type) { + case XFS_DQTYPE_USER: + ino = mp->m_sb.sb_uquotino; + break; + case XFS_DQTYPE_GROUP: + ino = mp->m_sb.sb_gquotino; + break; + case XFS_DQTYPE_PROJ: + ino = mp->m_sb.sb_pquotino; + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + /* Should have set 0 to NULLFSINO when loading superblock */ + if (ino == NULLFSINO) + return -ENOENT; + + error = xfs_trans_metafile_iget(tp, ino, metafile_type, &ip); + } else { + error = xfs_metadir_load(tp, dp, xfs_dqinode_path(type), + metafile_type, &ip); + if (error == -ENOENT) + return error; + } + if (error) { + if (xfs_metadata_is_sick(error)) + xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type)); + return error; + } + + if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && + ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) { + xfs_irele(ip); + xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type)); + return -EFSCORRUPTED; + } + + if (XFS_IS_CORRUPT(mp, ip->i_projid != 0)) { + xfs_irele(ip); + xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type)); + return -EFSCORRUPTED; + } + + *ipp = ip; + return 0; +} + +/* Create a metadata directory quota inode. */ +int +xfs_dqinode_metadir_create( + struct xfs_inode *dp, + xfs_dqtype_t type, + struct xfs_inode **ipp) +{ + struct xfs_metadir_update upd = { + .dp = dp, + .metafile_type = xfs_dqinode_metafile_type(type), + .path = xfs_dqinode_path(type), + }; + int error; + + error = xfs_metadir_start_create(&upd); + if (error) + return error; + + error = xfs_metadir_create(&upd, S_IFREG); + if (error) + return error; + + xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE); + + error = xfs_metadir_commit(&upd); + if (error) + return error; + + xfs_finish_inode_setup(upd.ip); + *ipp = upd.ip; + return 0; +} + +#ifndef __KERNEL__ +/* Link a metadata directory quota inode. */ +int +xfs_dqinode_metadir_link( + struct xfs_inode *dp, + xfs_dqtype_t type, + struct xfs_inode *ip) +{ + struct xfs_metadir_update upd = { + .dp = dp, + .metafile_type = xfs_dqinode_metafile_type(type), + .path = xfs_dqinode_path(type), + .ip = ip, + }; + int error; + + error = xfs_metadir_start_link(&upd); + if (error) + return error; + + error = xfs_metadir_link(&upd); + if (error) + return error; + + xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE); + + return xfs_metadir_commit(&upd); +} +#endif /* __KERNEL__ */ + +/* Create the parent directory for all quota inodes and load it. */ +int +xfs_dqinode_mkdir_parent( + struct xfs_mount *mp, + struct xfs_inode **dpp) +{ + if (!mp->m_metadirip) { + xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); + return -EFSCORRUPTED; + } + + return xfs_metadir_mkdir(mp->m_metadirip, "quota", dpp); +} + +/* + * Load the parent directory of all quota inodes. Pass the inode to the caller + * because quota functions (e.g. QUOTARM) can be called on the quota files even + * if quotas are not enabled. + */ +int +xfs_dqinode_load_parent( + struct xfs_trans *tp, + struct xfs_inode **dpp) +{ + struct xfs_mount *mp = tp->t_mountp; + + if (!mp->m_metadirip) { + xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); + return -EFSCORRUPTED; + } + + return xfs_metadir_load(tp, mp->m_metadirip, "quota", XFS_METAFILE_DIR, + dpp); +} diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h index 01a9e86b3037..57e47077c75a 100644 --- a/fs/xfs/libxfs/xfs_errortag.h +++ b/fs/xfs/libxfs/xfs_errortag.h @@ -4,14 +4,22 @@ * Copyright (C) 2017 Oracle. * All Rights Reserved. */ -#ifndef __XFS_ERRORTAG_H_ +#if !defined(__XFS_ERRORTAG_H_) || defined(XFS_ERRTAG) #define __XFS_ERRORTAG_H_ /* - * error injection tags - the labels can be anything you want - * but each tag should have its own unique number + * There are two ways to use this header file. The first way is to #include it + * bare, which will define all the XFS_ERRTAG_* error injection knobs for use + * with the XFS_TEST_ERROR macro. The second way is to enclose the #include + * with a #define for an XFS_ERRTAG macro, in which case the header will define + " an XFS_ERRTAGS macro that expands to invoke that XFS_ERRTAG macro for each + * defined error injection knob. */ +/* + * These are the actual error injection tags. The numbers should be consecutive + * because arrays are sized based on the maximum. + */ #define XFS_ERRTAG_NOERROR 0 #define XFS_ERRTAG_IFLUSH_1 1 #define XFS_ERRTAG_IFLUSH_2 2 @@ -63,53 +71,71 @@ #define XFS_ERRTAG_ATTR_LEAF_TO_NODE 41 #define XFS_ERRTAG_WB_DELAY_MS 42 #define XFS_ERRTAG_WRITE_DELAY_MS 43 -#define XFS_ERRTAG_MAX 44 +#define XFS_ERRTAG_EXCHMAPS_FINISH_ONE 44 +#define XFS_ERRTAG_METAFILE_RESV_CRITICAL 45 +#define XFS_ERRTAG_FORCE_ZERO_RANGE 46 +#define XFS_ERRTAG_MAX 47 /* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc. */ #define XFS_RANDOM_DEFAULT 100 -#define XFS_RANDOM_IFLUSH_1 XFS_RANDOM_DEFAULT -#define XFS_RANDOM_IFLUSH_2 XFS_RANDOM_DEFAULT -#define XFS_RANDOM_IFLUSH_3 XFS_RANDOM_DEFAULT -#define XFS_RANDOM_IFLUSH_4 XFS_RANDOM_DEFAULT -#define XFS_RANDOM_IFLUSH_5 XFS_RANDOM_DEFAULT -#define XFS_RANDOM_IFLUSH_6 XFS_RANDOM_DEFAULT -#define XFS_RANDOM_DA_READ_BUF XFS_RANDOM_DEFAULT -#define XFS_RANDOM_BTREE_CHECK_LBLOCK (XFS_RANDOM_DEFAULT/4) -#define XFS_RANDOM_BTREE_CHECK_SBLOCK XFS_RANDOM_DEFAULT -#define XFS_RANDOM_ALLOC_READ_AGF XFS_RANDOM_DEFAULT -#define XFS_RANDOM_IALLOC_READ_AGI XFS_RANDOM_DEFAULT -#define XFS_RANDOM_ITOBP_INOTOBP XFS_RANDOM_DEFAULT -#define XFS_RANDOM_IUNLINK XFS_RANDOM_DEFAULT -#define XFS_RANDOM_IUNLINK_REMOVE XFS_RANDOM_DEFAULT -#define XFS_RANDOM_DIR_INO_VALIDATE XFS_RANDOM_DEFAULT -#define XFS_RANDOM_BULKSTAT_READ_CHUNK XFS_RANDOM_DEFAULT -#define XFS_RANDOM_IODONE_IOERR (XFS_RANDOM_DEFAULT/10) -#define XFS_RANDOM_STRATREAD_IOERR (XFS_RANDOM_DEFAULT/10) -#define XFS_RANDOM_STRATCMPL_IOERR (XFS_RANDOM_DEFAULT/10) -#define XFS_RANDOM_DIOWRITE_IOERR (XFS_RANDOM_DEFAULT/10) -#define XFS_RANDOM_BMAPIFORMAT XFS_RANDOM_DEFAULT -#define XFS_RANDOM_FREE_EXTENT 1 -#define XFS_RANDOM_RMAP_FINISH_ONE 1 -#define XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE 1 -#define XFS_RANDOM_REFCOUNT_FINISH_ONE 1 -#define XFS_RANDOM_BMAP_FINISH_ONE 1 -#define XFS_RANDOM_AG_RESV_CRITICAL 4 -#define XFS_RANDOM_LOG_BAD_CRC 1 -#define XFS_RANDOM_LOG_ITEM_PIN 1 -#define XFS_RANDOM_BUF_LRU_REF 2 -#define XFS_RANDOM_FORCE_SCRUB_REPAIR 1 -#define XFS_RANDOM_FORCE_SUMMARY_RECALC 1 -#define XFS_RANDOM_IUNLINK_FALLBACK (XFS_RANDOM_DEFAULT/10) -#define XFS_RANDOM_BUF_IOERROR XFS_RANDOM_DEFAULT -#define XFS_RANDOM_REDUCE_MAX_IEXTENTS 1 -#define XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT 1 -#define XFS_RANDOM_AG_RESV_FAIL 1 -#define XFS_RANDOM_LARP 1 -#define XFS_RANDOM_DA_LEAF_SPLIT 1 -#define XFS_RANDOM_ATTR_LEAF_TO_NODE 1 -#define XFS_RANDOM_WB_DELAY_MS 3000 -#define XFS_RANDOM_WRITE_DELAY_MS 3000 + +/* + * Table of errror injection knobs. The parameters to the XFS_ERRTAG macro are: + * 1. The XFS_ERRTAG_ flag but without the prefix; + * 2. The name of the sysfs knob; and + * 3. The default value for the knob. + */ +#ifdef XFS_ERRTAG +# undef XFS_ERRTAGS +# define XFS_ERRTAGS \ +XFS_ERRTAG(NOERROR, noerror, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(IFLUSH_1, iflush1, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(IFLUSH_2, iflush2, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(IFLUSH_3, iflush3, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(IFLUSH_4, iflush4, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(IFLUSH_5, iflush5, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(IFLUSH_6, iflush6, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(DA_READ_BUF, dareadbuf, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(BTREE_CHECK_LBLOCK, btree_chk_lblk, XFS_RANDOM_DEFAULT/4) \ +XFS_ERRTAG(BTREE_CHECK_SBLOCK, btree_chk_sblk, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(ALLOC_READ_AGF, readagf, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(IALLOC_READ_AGI, readagi, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(ITOBP_INOTOBP, itobp, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(IUNLINK, iunlink, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(IUNLINK_REMOVE, iunlinkrm, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(DIR_INO_VALIDATE, dirinovalid, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(BULKSTAT_READ_CHUNK, bulkstat, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(IODONE_IOERR, logiodone, XFS_RANDOM_DEFAULT/10) \ +XFS_ERRTAG(STRATREAD_IOERR, stratread, XFS_RANDOM_DEFAULT/10) \ +XFS_ERRTAG(STRATCMPL_IOERR, stratcmpl, XFS_RANDOM_DEFAULT/10) \ +XFS_ERRTAG(DIOWRITE_IOERR, diowrite, XFS_RANDOM_DEFAULT/10) \ +XFS_ERRTAG(BMAPIFORMAT, bmapifmt, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(FREE_EXTENT, free_extent, 1) \ +XFS_ERRTAG(RMAP_FINISH_ONE, rmap_finish_one, 1) \ +XFS_ERRTAG(REFCOUNT_CONTINUE_UPDATE, refcount_continue_update, 1) \ +XFS_ERRTAG(REFCOUNT_FINISH_ONE, refcount_finish_one, 1) \ +XFS_ERRTAG(BMAP_FINISH_ONE, bmap_finish_one, 1) \ +XFS_ERRTAG(AG_RESV_CRITICAL, ag_resv_critical, 4) \ +XFS_ERRTAG(LOG_BAD_CRC, log_bad_crc, 1) \ +XFS_ERRTAG(LOG_ITEM_PIN, log_item_pin, 1) \ +XFS_ERRTAG(BUF_LRU_REF, buf_lru_ref, 2) \ +XFS_ERRTAG(FORCE_SCRUB_REPAIR, force_repair, 1) \ +XFS_ERRTAG(FORCE_SUMMARY_RECALC, bad_summary, 1) \ +XFS_ERRTAG(IUNLINK_FALLBACK, iunlink_fallback, XFS_RANDOM_DEFAULT/10) \ +XFS_ERRTAG(BUF_IOERROR, buf_ioerror, XFS_RANDOM_DEFAULT) \ +XFS_ERRTAG(REDUCE_MAX_IEXTENTS, reduce_max_iextents, 1) \ +XFS_ERRTAG(BMAP_ALLOC_MINLEN_EXTENT, bmap_alloc_minlen_extent, 1) \ +XFS_ERRTAG(AG_RESV_FAIL, ag_resv_fail, 1) \ +XFS_ERRTAG(LARP, larp, 1) \ +XFS_ERRTAG(DA_LEAF_SPLIT, da_leaf_split, 1) \ +XFS_ERRTAG(ATTR_LEAF_TO_NODE, attr_leaf_to_node, 1) \ +XFS_ERRTAG(WB_DELAY_MS, wb_delay_ms, 3000) \ +XFS_ERRTAG(WRITE_DELAY_MS, write_delay_ms, 3000) \ +XFS_ERRTAG(EXCHMAPS_FINISH_ONE, exchmaps_finish_one, 1) \ +XFS_ERRTAG(METAFILE_RESV_CRITICAL, metafile_resv_crit, 4) \ +XFS_ERRTAG(FORCE_ZERO_RANGE, force_zero_range, 4) +#endif /* XFS_ERRTAG */ #endif /* __XFS_ERRORTAG_H_ */ diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c new file mode 100644 index 000000000000..932ee4619e9e --- /dev/null +++ b/fs/xfs/libxfs/xfs_exchmaps.c @@ -0,0 +1,1237 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2020-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_bmap.h" +#include "xfs_icache.h" +#include "xfs_quota.h" +#include "xfs_exchmaps.h" +#include "xfs_trace.h" +#include "xfs_bmap_btree.h" +#include "xfs_trans_space.h" +#include "xfs_error.h" +#include "xfs_errortag.h" +#include "xfs_health.h" +#include "xfs_exchmaps_item.h" +#include "xfs_da_format.h" +#include "xfs_da_btree.h" +#include "xfs_attr_leaf.h" +#include "xfs_attr.h" +#include "xfs_dir2_priv.h" +#include "xfs_dir2.h" +#include "xfs_symlink_remote.h" + +struct kmem_cache *xfs_exchmaps_intent_cache; + +/* bmbt mappings adjacent to a pair of records. */ +struct xfs_exchmaps_adjacent { + struct xfs_bmbt_irec left1; + struct xfs_bmbt_irec right1; + struct xfs_bmbt_irec left2; + struct xfs_bmbt_irec right2; +}; + +#define ADJACENT_INIT { \ + .left1 = { .br_startblock = HOLESTARTBLOCK }, \ + .right1 = { .br_startblock = HOLESTARTBLOCK }, \ + .left2 = { .br_startblock = HOLESTARTBLOCK }, \ + .right2 = { .br_startblock = HOLESTARTBLOCK }, \ +} + +/* Information to reset reflink flag / CoW fork state after an exchange. */ + +/* + * If the reflink flag is set on either inode, make sure it has an incore CoW + * fork, since all reflink inodes must have them. If there's a CoW fork and it + * has mappings in it, make sure the inodes are tagged appropriately so that + * speculative preallocations can be GC'd if we run low of space. + */ +static inline void +xfs_exchmaps_ensure_cowfork( + struct xfs_inode *ip) +{ + struct xfs_ifork *cfork; + + if (xfs_is_reflink_inode(ip)) + xfs_ifork_init_cow(ip); + + cfork = xfs_ifork_ptr(ip, XFS_COW_FORK); + if (!cfork) + return; + if (cfork->if_bytes > 0) + xfs_inode_set_cowblocks_tag(ip); + else + xfs_inode_clear_cowblocks_tag(ip); +} + +/* + * Adjust the on-disk inode size upwards if needed so that we never add + * mappings into the file past EOF. This is crucial so that log recovery won't + * get confused by the sudden appearance of post-eof mappings. + */ +STATIC void +xfs_exchmaps_update_size( + struct xfs_trans *tp, + struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, + xfs_fsize_t new_isize) +{ + struct xfs_mount *mp = tp->t_mountp; + xfs_fsize_t len; + + if (new_isize < 0) + return; + + len = min(XFS_FSB_TO_B(mp, imap->br_startoff + imap->br_blockcount), + new_isize); + + if (len <= ip->i_disk_size) + return; + + trace_xfs_exchmaps_update_inode_size(ip, len); + + ip->i_disk_size = len; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); +} + +/* Advance the incore state tracking after exchanging a mapping. */ +static inline void +xmi_advance( + struct xfs_exchmaps_intent *xmi, + const struct xfs_bmbt_irec *irec) +{ + xmi->xmi_startoff1 += irec->br_blockcount; + xmi->xmi_startoff2 += irec->br_blockcount; + xmi->xmi_blockcount -= irec->br_blockcount; +} + +/* Do we still have more mappings to exchange? */ +static inline bool +xmi_has_more_exchange_work(const struct xfs_exchmaps_intent *xmi) +{ + return xmi->xmi_blockcount > 0; +} + +/* Do we have post-operation cleanups to perform? */ +static inline bool +xmi_has_postop_work(const struct xfs_exchmaps_intent *xmi) +{ + return xmi->xmi_flags & (XFS_EXCHMAPS_CLEAR_INO1_REFLINK | + XFS_EXCHMAPS_CLEAR_INO2_REFLINK | + __XFS_EXCHMAPS_INO2_SHORTFORM); +} + +/* Check all mappings to make sure we can actually exchange them. */ +int +xfs_exchmaps_check_forks( + struct xfs_mount *mp, + const struct xfs_exchmaps_req *req) +{ + struct xfs_ifork *ifp1, *ifp2; + int whichfork = xfs_exchmaps_reqfork(req); + + /* No fork? */ + ifp1 = xfs_ifork_ptr(req->ip1, whichfork); + ifp2 = xfs_ifork_ptr(req->ip2, whichfork); + if (!ifp1 || !ifp2) + return -EINVAL; + + /* We don't know how to exchange local format forks. */ + if (ifp1->if_format == XFS_DINODE_FMT_LOCAL || + ifp2->if_format == XFS_DINODE_FMT_LOCAL) + return -EINVAL; + + return 0; +} + +#ifdef CONFIG_XFS_QUOTA +/* Log the actual updates to the quota accounting. */ +static inline void +xfs_exchmaps_update_quota( + struct xfs_trans *tp, + struct xfs_exchmaps_intent *xmi, + struct xfs_bmbt_irec *irec1, + struct xfs_bmbt_irec *irec2) +{ + int64_t ip1_delta = 0, ip2_delta = 0; + unsigned int qflag; + + qflag = XFS_IS_REALTIME_INODE(xmi->xmi_ip1) ? XFS_TRANS_DQ_RTBCOUNT : + XFS_TRANS_DQ_BCOUNT; + + if (xfs_bmap_is_real_extent(irec1)) { + ip1_delta -= irec1->br_blockcount; + ip2_delta += irec1->br_blockcount; + } + + if (xfs_bmap_is_real_extent(irec2)) { + ip1_delta += irec2->br_blockcount; + ip2_delta -= irec2->br_blockcount; + } + + xfs_trans_mod_dquot_byino(tp, xmi->xmi_ip1, qflag, ip1_delta); + xfs_trans_mod_dquot_byino(tp, xmi->xmi_ip2, qflag, ip2_delta); +} +#else +# define xfs_exchmaps_update_quota(tp, xmi, irec1, irec2) ((void)0) +#endif + +/* Decide if we want to skip this mapping from file1. */ +static inline bool +xfs_exchmaps_can_skip_mapping( + struct xfs_exchmaps_intent *xmi, + struct xfs_bmbt_irec *irec) +{ + struct xfs_mount *mp = xmi->xmi_ip1->i_mount; + + /* Do not skip this mapping if the caller did not tell us to. */ + if (!(xmi->xmi_flags & XFS_EXCHMAPS_INO1_WRITTEN)) + return false; + + /* Do not skip mapped, written mappings. */ + if (xfs_bmap_is_written_extent(irec)) + return false; + + /* + * The mapping is unwritten or a hole. It cannot be a delalloc + * reservation because we already excluded those. It cannot be an + * unwritten extent with dirty page cache because we flushed the page + * cache. For files where the allocation unit is 1FSB (files on the + * data dev, rt files if the extent size is 1FSB), we can safely + * skip this mapping. + */ + if (!xfs_inode_has_bigrtalloc(xmi->xmi_ip1)) + return true; + + /* + * For a realtime file with a multi-fsb allocation unit, the decision + * is trickier because we can only swap full allocation units. + * Unwritten mappings can appear in the middle of an rtx if the rtx is + * partially written, but they can also appear for preallocations. + * + * If the mapping is a hole, skip it entirely. Holes should align with + * rtx boundaries. + */ + if (!xfs_bmap_is_real_extent(irec)) + return true; + + /* + * All mappings below this point are unwritten. + * + * - If the beginning is not aligned to an rtx, trim the end of the + * mapping so that it does not cross an rtx boundary, and swap it. + * + * - If both ends are aligned to an rtx, skip the entire mapping. + */ + if (!isaligned_64(irec->br_startoff, mp->m_sb.sb_rextsize)) { + xfs_fileoff_t new_end; + + new_end = roundup_64(irec->br_startoff, mp->m_sb.sb_rextsize); + irec->br_blockcount = min(irec->br_blockcount, + new_end - irec->br_startoff); + return false; + } + if (isaligned_64(irec->br_blockcount, mp->m_sb.sb_rextsize)) + return true; + + /* + * All mappings below this point are unwritten, start on an rtx + * boundary, and do not end on an rtx boundary. + * + * - If the mapping is longer than one rtx, trim the end of the mapping + * down to an rtx boundary and skip it. + * + * - The mapping is shorter than one rtx. Swap it. + */ + if (irec->br_blockcount > mp->m_sb.sb_rextsize) { + xfs_fileoff_t new_end; + + new_end = rounddown_64(irec->br_startoff + irec->br_blockcount, + mp->m_sb.sb_rextsize); + irec->br_blockcount = new_end - irec->br_startoff; + return true; + } + + return false; +} + +/* + * Walk forward through the file ranges in @xmi until we find two different + * mappings to exchange. If there is work to do, return the mappings; + * otherwise we've reached the end of the range and xmi_blockcount will be + * zero. + * + * If the walk skips over a pair of mappings to the same storage, save them as + * the left records in @adj (if provided) so that the simulation phase can + * avoid an extra lookup. + */ +static int +xfs_exchmaps_find_mappings( + struct xfs_exchmaps_intent *xmi, + struct xfs_bmbt_irec *irec1, + struct xfs_bmbt_irec *irec2, + struct xfs_exchmaps_adjacent *adj) +{ + int nimaps; + int bmap_flags; + int error; + + bmap_flags = xfs_bmapi_aflag(xfs_exchmaps_whichfork(xmi)); + + for (; xmi_has_more_exchange_work(xmi); xmi_advance(xmi, irec1)) { + /* Read mapping from the first file */ + nimaps = 1; + error = xfs_bmapi_read(xmi->xmi_ip1, xmi->xmi_startoff1, + xmi->xmi_blockcount, irec1, &nimaps, + bmap_flags); + if (error) + return error; + if (nimaps != 1 || + irec1->br_startblock == DELAYSTARTBLOCK || + irec1->br_startoff != xmi->xmi_startoff1) { + /* + * We should never get no mapping or a delalloc mapping + * or something that doesn't match what we asked for, + * since the caller flushed both inodes and we hold the + * ILOCKs for both inodes. + */ + ASSERT(0); + return -EINVAL; + } + + if (xfs_exchmaps_can_skip_mapping(xmi, irec1)) { + trace_xfs_exchmaps_mapping1_skip(xmi->xmi_ip1, irec1); + continue; + } + + /* Read mapping from the second file */ + nimaps = 1; + error = xfs_bmapi_read(xmi->xmi_ip2, xmi->xmi_startoff2, + irec1->br_blockcount, irec2, &nimaps, + bmap_flags); + if (error) + return error; + if (nimaps != 1 || + irec2->br_startblock == DELAYSTARTBLOCK || + irec2->br_startoff != xmi->xmi_startoff2) { + /* + * We should never get no mapping or a delalloc mapping + * or something that doesn't match what we asked for, + * since the caller flushed both inodes and we hold the + * ILOCKs for both inodes. + */ + ASSERT(0); + return -EINVAL; + } + + /* + * We can only exchange as many blocks as the smaller of the + * two mapping maps. + */ + irec1->br_blockcount = min(irec1->br_blockcount, + irec2->br_blockcount); + + trace_xfs_exchmaps_mapping1(xmi->xmi_ip1, irec1); + trace_xfs_exchmaps_mapping2(xmi->xmi_ip2, irec2); + + /* We found something to exchange, so return it. */ + if (irec1->br_startblock != irec2->br_startblock) + return 0; + + /* + * Two mappings pointing to the same physical block must not + * have different states; that's filesystem corruption. Move + * on to the next mapping if they're both holes or both point + * to the same physical space extent. + */ + if (irec1->br_state != irec2->br_state) { + xfs_bmap_mark_sick(xmi->xmi_ip1, + xfs_exchmaps_whichfork(xmi)); + xfs_bmap_mark_sick(xmi->xmi_ip2, + xfs_exchmaps_whichfork(xmi)); + return -EFSCORRUPTED; + } + + /* + * Save the mappings if we're estimating work and skipping + * these identical mappings. + */ + if (adj) { + memcpy(&adj->left1, irec1, sizeof(*irec1)); + memcpy(&adj->left2, irec2, sizeof(*irec2)); + } + } + + return 0; +} + +/* Exchange these two mappings. */ +static void +xfs_exchmaps_one_step( + struct xfs_trans *tp, + struct xfs_exchmaps_intent *xmi, + struct xfs_bmbt_irec *irec1, + struct xfs_bmbt_irec *irec2) +{ + int whichfork = xfs_exchmaps_whichfork(xmi); + + xfs_exchmaps_update_quota(tp, xmi, irec1, irec2); + + /* Remove both mappings. */ + xfs_bmap_unmap_extent(tp, xmi->xmi_ip1, whichfork, irec1); + xfs_bmap_unmap_extent(tp, xmi->xmi_ip2, whichfork, irec2); + + /* + * Re-add both mappings. We exchange the file offsets between the two + * maps and add the opposite map, which has the effect of filling the + * logical offsets we just unmapped, but with with the physical mapping + * information exchanged. + */ + swap(irec1->br_startoff, irec2->br_startoff); + xfs_bmap_map_extent(tp, xmi->xmi_ip1, whichfork, irec2); + xfs_bmap_map_extent(tp, xmi->xmi_ip2, whichfork, irec1); + + /* Make sure we're not adding mappings past EOF. */ + if (whichfork == XFS_DATA_FORK) { + xfs_exchmaps_update_size(tp, xmi->xmi_ip1, irec2, + xmi->xmi_isize1); + xfs_exchmaps_update_size(tp, xmi->xmi_ip2, irec1, + xmi->xmi_isize2); + } + + /* + * Advance our cursor and exit. The caller (either defer ops or log + * recovery) will log the XMD item, and if *blockcount is nonzero, it + * will log a new XMI item for the remainder and call us back. + */ + xmi_advance(xmi, irec1); +} + +/* Convert inode2's leaf attr fork back to shortform, if possible.. */ +STATIC int +xfs_exchmaps_attr_to_sf( + struct xfs_trans *tp, + struct xfs_exchmaps_intent *xmi) +{ + struct xfs_da_args args = { + .dp = xmi->xmi_ip2, + .geo = tp->t_mountp->m_attr_geo, + .whichfork = XFS_ATTR_FORK, + .trans = tp, + .owner = xmi->xmi_ip2->i_ino, + }; + struct xfs_buf *bp; + int forkoff; + int error; + + if (!xfs_attr_is_leaf(xmi->xmi_ip2)) + return 0; + + error = xfs_attr3_leaf_read(tp, xmi->xmi_ip2, xmi->xmi_ip2->i_ino, 0, + &bp); + if (error) + return error; + + forkoff = xfs_attr_shortform_allfit(bp, xmi->xmi_ip2); + if (forkoff == 0) + return 0; + + return xfs_attr3_leaf_to_shortform(bp, &args, forkoff); +} + +/* Convert inode2's block dir fork back to shortform, if possible.. */ +STATIC int +xfs_exchmaps_dir_to_sf( + struct xfs_trans *tp, + struct xfs_exchmaps_intent *xmi) +{ + struct xfs_da_args args = { + .dp = xmi->xmi_ip2, + .geo = tp->t_mountp->m_dir_geo, + .whichfork = XFS_DATA_FORK, + .trans = tp, + .owner = xmi->xmi_ip2->i_ino, + }; + struct xfs_dir2_sf_hdr sfh; + struct xfs_buf *bp; + int size; + int error = 0; + + if (xfs_dir2_format(&args, &error) != XFS_DIR2_FMT_BLOCK) + return error; + + error = xfs_dir3_block_read(tp, xmi->xmi_ip2, xmi->xmi_ip2->i_ino, &bp); + if (error) + return error; + + size = xfs_dir2_block_sfsize(xmi->xmi_ip2, bp->b_addr, &sfh); + if (size > xfs_inode_data_fork_size(xmi->xmi_ip2)) + return 0; + + return xfs_dir2_block_to_sf(&args, bp, size, &sfh); +} + +/* Convert inode2's remote symlink target back to shortform, if possible. */ +STATIC int +xfs_exchmaps_link_to_sf( + struct xfs_trans *tp, + struct xfs_exchmaps_intent *xmi) +{ + struct xfs_inode *ip = xmi->xmi_ip2; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + char *buf; + int error; + + if (ifp->if_format == XFS_DINODE_FMT_LOCAL || + ip->i_disk_size > xfs_inode_data_fork_size(ip)) + return 0; + + /* Read the current symlink target into a buffer. */ + buf = kmalloc(ip->i_disk_size + 1, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + if (!buf) { + ASSERT(0); + return -ENOMEM; + } + + error = xfs_symlink_remote_read(ip, buf); + if (error) + goto free; + + /* Remove the blocks. */ + error = xfs_symlink_remote_truncate(tp, ip); + if (error) + goto free; + + /* Convert fork to local format and log our changes. */ + xfs_idestroy_fork(ifp); + ifp->if_bytes = 0; + ifp->if_format = XFS_DINODE_FMT_LOCAL; + xfs_init_local_fork(ip, XFS_DATA_FORK, buf, ip->i_disk_size); + xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE); +free: + kfree(buf); + return error; +} + +/* Clear the reflink flag after an exchange. */ +static inline void +xfs_exchmaps_clear_reflink( + struct xfs_trans *tp, + struct xfs_inode *ip) +{ + trace_xfs_reflink_unset_inode_flag(ip); + + ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); +} + +/* Finish whatever work might come after an exchange operation. */ +static int +xfs_exchmaps_do_postop_work( + struct xfs_trans *tp, + struct xfs_exchmaps_intent *xmi) +{ + if (xmi->xmi_flags & __XFS_EXCHMAPS_INO2_SHORTFORM) { + int error = 0; + + if (xmi->xmi_flags & XFS_EXCHMAPS_ATTR_FORK) + error = xfs_exchmaps_attr_to_sf(tp, xmi); + else if (S_ISDIR(VFS_I(xmi->xmi_ip2)->i_mode)) + error = xfs_exchmaps_dir_to_sf(tp, xmi); + else if (S_ISLNK(VFS_I(xmi->xmi_ip2)->i_mode)) + error = xfs_exchmaps_link_to_sf(tp, xmi); + xmi->xmi_flags &= ~__XFS_EXCHMAPS_INO2_SHORTFORM; + if (error) + return error; + } + + if (xmi->xmi_flags & XFS_EXCHMAPS_CLEAR_INO1_REFLINK) { + xfs_exchmaps_clear_reflink(tp, xmi->xmi_ip1); + xmi->xmi_flags &= ~XFS_EXCHMAPS_CLEAR_INO1_REFLINK; + } + + if (xmi->xmi_flags & XFS_EXCHMAPS_CLEAR_INO2_REFLINK) { + xfs_exchmaps_clear_reflink(tp, xmi->xmi_ip2); + xmi->xmi_flags &= ~XFS_EXCHMAPS_CLEAR_INO2_REFLINK; + } + + return 0; +} + +/* Finish one step in a mapping exchange operation, possibly relogging. */ +int +xfs_exchmaps_finish_one( + struct xfs_trans *tp, + struct xfs_exchmaps_intent *xmi) +{ + struct xfs_bmbt_irec irec1, irec2; + int error; + + if (xmi_has_more_exchange_work(xmi)) { + /* + * If the operation state says that some range of the files + * have not yet been exchanged, look for mappings in that range + * to exchange. If we find some mappings, exchange them. + */ + error = xfs_exchmaps_find_mappings(xmi, &irec1, &irec2, NULL); + if (error) + return error; + + if (xmi_has_more_exchange_work(xmi)) + xfs_exchmaps_one_step(tp, xmi, &irec1, &irec2); + + /* + * If the caller asked us to exchange the file sizes after the + * exchange and either we just exchanged the last mappings in + * the range or we didn't find anything to exchange, update the + * ondisk file sizes. + */ + if ((xmi->xmi_flags & XFS_EXCHMAPS_SET_SIZES) && + !xmi_has_more_exchange_work(xmi)) { + xmi->xmi_ip1->i_disk_size = xmi->xmi_isize1; + xmi->xmi_ip2->i_disk_size = xmi->xmi_isize2; + + xfs_trans_log_inode(tp, xmi->xmi_ip1, XFS_ILOG_CORE); + xfs_trans_log_inode(tp, xmi->xmi_ip2, XFS_ILOG_CORE); + } + } else if (xmi_has_postop_work(xmi)) { + /* + * Now that we're finished with the exchange operation, + * complete the post-op cleanup work. + */ + error = xfs_exchmaps_do_postop_work(tp, xmi); + if (error) + return error; + } + + if (XFS_TEST_ERROR(tp->t_mountp, XFS_ERRTAG_EXCHMAPS_FINISH_ONE)) + return -EIO; + + /* If we still have work to do, ask for a new transaction. */ + if (xmi_has_more_exchange_work(xmi) || xmi_has_postop_work(xmi)) { + trace_xfs_exchmaps_defer(tp->t_mountp, xmi); + return -EAGAIN; + } + + /* + * If we reach here, we've finished all the exchange work and the post + * operation work. The last thing we need to do before returning to + * the caller is to make sure that COW forks are set up correctly. + */ + if (!(xmi->xmi_flags & XFS_EXCHMAPS_ATTR_FORK)) { + xfs_exchmaps_ensure_cowfork(xmi->xmi_ip1); + xfs_exchmaps_ensure_cowfork(xmi->xmi_ip2); + } + + return 0; +} + +/* + * Compute the amount of bmbt blocks we should reserve for each file. In the + * worst case, each exchange will fill a hole with a new mapping, which could + * result in a btree split every time we add a new leaf block. + */ +static inline uint64_t +xfs_exchmaps_bmbt_blocks( + struct xfs_mount *mp, + const struct xfs_exchmaps_req *req) +{ + return howmany_64(req->nr_exchanges, + XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp)) * + XFS_EXTENTADD_SPACE_RES(mp, xfs_exchmaps_reqfork(req)); +} + +/* Compute the space we should reserve for the rmap btree expansions. */ +static inline uint64_t +xfs_exchmaps_rmapbt_blocks( + struct xfs_mount *mp, + const struct xfs_exchmaps_req *req) +{ + if (!xfs_has_rmapbt(mp)) + return 0; + if (XFS_IS_REALTIME_INODE(req->ip1)) + return howmany_64(req->nr_exchanges, + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)) * + XFS_RTRMAPADD_SPACE_RES(mp); + + return howmany_64(req->nr_exchanges, + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * + XFS_RMAPADD_SPACE_RES(mp); +} + +/* Estimate the bmbt and rmapbt overhead required to exchange mappings. */ +int +xfs_exchmaps_estimate_overhead( + struct xfs_exchmaps_req *req) +{ + struct xfs_mount *mp = req->ip1->i_mount; + xfs_filblks_t bmbt_blocks; + xfs_filblks_t rmapbt_blocks; + xfs_filblks_t resblks = req->resblks; + + /* + * Compute the number of bmbt and rmapbt blocks we might need to handle + * the estimated number of exchanges. + */ + bmbt_blocks = xfs_exchmaps_bmbt_blocks(mp, req); + rmapbt_blocks = xfs_exchmaps_rmapbt_blocks(mp, req); + + trace_xfs_exchmaps_overhead(mp, bmbt_blocks, rmapbt_blocks); + + /* Make sure the change in file block count doesn't overflow. */ + if (check_add_overflow(req->ip1_bcount, bmbt_blocks, &req->ip1_bcount)) + return -EFBIG; + if (check_add_overflow(req->ip2_bcount, bmbt_blocks, &req->ip2_bcount)) + return -EFBIG; + + /* + * Add together the number of blocks we need to handle btree growth, + * then add it to the number of blocks we need to reserve to this + * transaction. + */ + if (check_add_overflow(resblks, bmbt_blocks, &resblks)) + return -ENOSPC; + if (check_add_overflow(resblks, bmbt_blocks, &resblks)) + return -ENOSPC; + if (check_add_overflow(resblks, rmapbt_blocks, &resblks)) + return -ENOSPC; + if (check_add_overflow(resblks, rmapbt_blocks, &resblks)) + return -ENOSPC; + + /* Can't actually reserve more than UINT_MAX blocks. */ + if (req->resblks > UINT_MAX) + return -ENOSPC; + + req->resblks = resblks; + trace_xfs_exchmaps_final_estimate(req); + return 0; +} + +/* Decide if we can merge two real mappings. */ +static inline bool +xmi_can_merge( + const struct xfs_bmbt_irec *b1, + const struct xfs_bmbt_irec *b2) +{ + /* Don't merge holes. */ + if (b1->br_startblock == HOLESTARTBLOCK || + b2->br_startblock == HOLESTARTBLOCK) + return false; + + /* We don't merge holes. */ + if (!xfs_bmap_is_real_extent(b1) || !xfs_bmap_is_real_extent(b2)) + return false; + + if (b1->br_startoff + b1->br_blockcount == b2->br_startoff && + b1->br_startblock + b1->br_blockcount == b2->br_startblock && + b1->br_state == b2->br_state && + b1->br_blockcount + b2->br_blockcount <= XFS_MAX_BMBT_EXTLEN) + return true; + + return false; +} + +/* + * Decide if we can merge three mappings. Caller must ensure all three + * mappings must not be holes or delalloc reservations. + */ +static inline bool +xmi_can_merge_all( + const struct xfs_bmbt_irec *l, + const struct xfs_bmbt_irec *m, + const struct xfs_bmbt_irec *r) +{ + xfs_filblks_t new_len; + + new_len = l->br_blockcount + m->br_blockcount + r->br_blockcount; + return new_len <= XFS_MAX_BMBT_EXTLEN; +} + +#define CLEFT_CONTIG 0x01 +#define CRIGHT_CONTIG 0x02 +#define CHOLE 0x04 +#define CBOTH_CONTIG (CLEFT_CONTIG | CRIGHT_CONTIG) + +#define NLEFT_CONTIG 0x10 +#define NRIGHT_CONTIG 0x20 +#define NHOLE 0x40 +#define NBOTH_CONTIG (NLEFT_CONTIG | NRIGHT_CONTIG) + +/* Estimate the effect of a single exchange on mapping count. */ +static inline int +xmi_delta_nextents_step( + struct xfs_mount *mp, + const struct xfs_bmbt_irec *left, + const struct xfs_bmbt_irec *curr, + const struct xfs_bmbt_irec *new, + const struct xfs_bmbt_irec *right) +{ + bool lhole, rhole, chole, nhole; + unsigned int state = 0; + int ret = 0; + + lhole = left->br_startblock == HOLESTARTBLOCK; + rhole = right->br_startblock == HOLESTARTBLOCK; + chole = curr->br_startblock == HOLESTARTBLOCK; + nhole = new->br_startblock == HOLESTARTBLOCK; + + if (chole) + state |= CHOLE; + if (!lhole && !chole && xmi_can_merge(left, curr)) + state |= CLEFT_CONTIG; + if (!rhole && !chole && xmi_can_merge(curr, right)) + state |= CRIGHT_CONTIG; + if ((state & CBOTH_CONTIG) == CBOTH_CONTIG && + !xmi_can_merge_all(left, curr, right)) + state &= ~CRIGHT_CONTIG; + + if (nhole) + state |= NHOLE; + if (!lhole && !nhole && xmi_can_merge(left, new)) + state |= NLEFT_CONTIG; + if (!rhole && !nhole && xmi_can_merge(new, right)) + state |= NRIGHT_CONTIG; + if ((state & NBOTH_CONTIG) == NBOTH_CONTIG && + !xmi_can_merge_all(left, new, right)) + state &= ~NRIGHT_CONTIG; + + switch (state & (CLEFT_CONTIG | CRIGHT_CONTIG | CHOLE)) { + case CLEFT_CONTIG | CRIGHT_CONTIG: + /* + * left/curr/right are the same mapping, so deleting curr + * causes 2 new mappings to be created. + */ + ret += 2; + break; + case 0: + /* + * curr is not contiguous with any mapping, so we remove curr + * completely + */ + ret--; + break; + case CHOLE: + /* hole, do nothing */ + break; + case CLEFT_CONTIG: + case CRIGHT_CONTIG: + /* trim either left or right, no change */ + break; + } + + switch (state & (NLEFT_CONTIG | NRIGHT_CONTIG | NHOLE)) { + case NLEFT_CONTIG | NRIGHT_CONTIG: + /* + * left/curr/right will become the same mapping, so adding + * curr causes the deletion of right. + */ + ret--; + break; + case 0: + /* new is not contiguous with any mapping */ + ret++; + break; + case NHOLE: + /* hole, do nothing. */ + break; + case NLEFT_CONTIG: + case NRIGHT_CONTIG: + /* new is absorbed into left or right, no change */ + break; + } + + trace_xfs_exchmaps_delta_nextents_step(mp, left, curr, new, right, ret, + state); + return ret; +} + +/* Make sure we don't overflow the extent (mapping) counters. */ +static inline int +xmi_ensure_delta_nextents( + struct xfs_exchmaps_req *req, + struct xfs_inode *ip, + int64_t delta) +{ + struct xfs_mount *mp = ip->i_mount; + int whichfork = xfs_exchmaps_reqfork(req); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + uint64_t new_nextents; + xfs_extnum_t max_nextents; + + if (delta < 0) + return 0; + + /* + * It's always an error if the delta causes integer overflow. delta + * needs an explicit cast here to avoid warnings about implicit casts + * coded into the overflow check. + */ + if (check_add_overflow(ifp->if_nextents, (uint64_t)delta, + &new_nextents)) + return -EFBIG; + + if (XFS_TEST_ERROR(mp, XFS_ERRTAG_REDUCE_MAX_IEXTENTS) && + new_nextents > 10) + return -EFBIG; + + /* + * We always promote both inodes to have large extent counts if the + * superblock feature is enabled, so we only need to check against the + * theoretical maximum. + */ + max_nextents = xfs_iext_max_nextents(xfs_has_large_extent_counts(mp), + whichfork); + if (new_nextents > max_nextents) + return -EFBIG; + + return 0; +} + +/* Find the next mapping after irec. */ +static inline int +xmi_next( + struct xfs_inode *ip, + int bmap_flags, + const struct xfs_bmbt_irec *irec, + struct xfs_bmbt_irec *nrec) +{ + xfs_fileoff_t off; + xfs_filblks_t blockcount; + int nimaps = 1; + int error; + + off = irec->br_startoff + irec->br_blockcount; + blockcount = XFS_MAX_FILEOFF - off; + error = xfs_bmapi_read(ip, off, blockcount, nrec, &nimaps, bmap_flags); + if (error) + return error; + if (nrec->br_startblock == DELAYSTARTBLOCK || + nrec->br_startoff != off) { + /* + * If we don't get the mapping we want, return a zero-length + * mapping, which our estimator function will pretend is a hole. + * We shouldn't get delalloc reservations. + */ + nrec->br_startblock = HOLESTARTBLOCK; + } + + return 0; +} + +int __init +xfs_exchmaps_intent_init_cache(void) +{ + xfs_exchmaps_intent_cache = kmem_cache_create("xfs_exchmaps_intent", + sizeof(struct xfs_exchmaps_intent), + 0, 0, NULL); + + return xfs_exchmaps_intent_cache != NULL ? 0 : -ENOMEM; +} + +void +xfs_exchmaps_intent_destroy_cache(void) +{ + kmem_cache_destroy(xfs_exchmaps_intent_cache); + xfs_exchmaps_intent_cache = NULL; +} + +/* + * Decide if we will exchange the reflink flags between the two files after the + * exchange. The only time we want to do this is if we're exchanging all + * mappings under EOF and the inode reflink flags have different states. + */ +static inline bool +xmi_can_exchange_reflink_flags( + const struct xfs_exchmaps_req *req, + unsigned int reflink_state) +{ + struct xfs_mount *mp = req->ip1->i_mount; + + if (hweight32(reflink_state) != 1) + return false; + if (req->startoff1 != 0 || req->startoff2 != 0) + return false; + if (req->blockcount != XFS_B_TO_FSB(mp, req->ip1->i_disk_size)) + return false; + if (req->blockcount != XFS_B_TO_FSB(mp, req->ip2->i_disk_size)) + return false; + return true; +} + + +/* Allocate and initialize a new incore intent item from a request. */ +struct xfs_exchmaps_intent * +xfs_exchmaps_init_intent( + const struct xfs_exchmaps_req *req) +{ + struct xfs_exchmaps_intent *xmi; + unsigned int rs = 0; + + xmi = kmem_cache_zalloc(xfs_exchmaps_intent_cache, + GFP_NOFS | __GFP_NOFAIL); + INIT_LIST_HEAD(&xmi->xmi_list); + xmi->xmi_ip1 = req->ip1; + xmi->xmi_ip2 = req->ip2; + xmi->xmi_startoff1 = req->startoff1; + xmi->xmi_startoff2 = req->startoff2; + xmi->xmi_blockcount = req->blockcount; + xmi->xmi_isize1 = xmi->xmi_isize2 = -1; + xmi->xmi_flags = req->flags & XFS_EXCHMAPS_PARAMS; + + if (xfs_exchmaps_whichfork(xmi) == XFS_ATTR_FORK) { + xmi->xmi_flags |= __XFS_EXCHMAPS_INO2_SHORTFORM; + return xmi; + } + + if (req->flags & XFS_EXCHMAPS_SET_SIZES) { + xmi->xmi_flags |= XFS_EXCHMAPS_SET_SIZES; + xmi->xmi_isize1 = req->ip2->i_disk_size; + xmi->xmi_isize2 = req->ip1->i_disk_size; + } + + /* Record the state of each inode's reflink flag before the op. */ + if (xfs_is_reflink_inode(req->ip1)) + rs |= 1; + if (xfs_is_reflink_inode(req->ip2)) + rs |= 2; + + /* + * Figure out if we're clearing the reflink flags (which effectively + * exchanges them) after the operation. + */ + if (xmi_can_exchange_reflink_flags(req, rs)) { + if (rs & 1) + xmi->xmi_flags |= XFS_EXCHMAPS_CLEAR_INO1_REFLINK; + if (rs & 2) + xmi->xmi_flags |= XFS_EXCHMAPS_CLEAR_INO2_REFLINK; + } + + if (S_ISDIR(VFS_I(xmi->xmi_ip2)->i_mode) || + S_ISLNK(VFS_I(xmi->xmi_ip2)->i_mode)) + xmi->xmi_flags |= __XFS_EXCHMAPS_INO2_SHORTFORM; + + return xmi; +} + +/* + * Estimate the number of exchange operations and the number of file blocks + * in each file that will be affected by the exchange operation. + */ +int +xfs_exchmaps_estimate( + struct xfs_exchmaps_req *req) +{ + struct xfs_exchmaps_intent *xmi; + struct xfs_bmbt_irec irec1, irec2; + struct xfs_exchmaps_adjacent adj = ADJACENT_INIT; + xfs_filblks_t ip1_blocks = 0, ip2_blocks = 0; + int64_t d_nexts1, d_nexts2; + int bmap_flags; + int error; + + ASSERT(!(req->flags & ~XFS_EXCHMAPS_PARAMS)); + + bmap_flags = xfs_bmapi_aflag(xfs_exchmaps_reqfork(req)); + xmi = xfs_exchmaps_init_intent(req); + + /* + * To guard against the possibility of overflowing the extent counters, + * we have to estimate an upper bound on the potential increase in that + * counter. We can split the mapping at each end of the range, and for + * each step of the exchange we can split the mapping that we're + * working on if the mappings do not align. + */ + d_nexts1 = d_nexts2 = 3; + + while (xmi_has_more_exchange_work(xmi)) { + /* + * Walk through the file ranges until we find something to + * exchange. Because we're simulating the exchange, pass in + * adj to capture skipped mappings for correct estimation of + * bmbt record merges. + */ + error = xfs_exchmaps_find_mappings(xmi, &irec1, &irec2, &adj); + if (error) + goto out_free; + if (!xmi_has_more_exchange_work(xmi)) + break; + + /* Update accounting. */ + if (xfs_bmap_is_real_extent(&irec1)) + ip1_blocks += irec1.br_blockcount; + if (xfs_bmap_is_real_extent(&irec2)) + ip2_blocks += irec2.br_blockcount; + req->nr_exchanges++; + + /* Read the next mappings from both files. */ + error = xmi_next(req->ip1, bmap_flags, &irec1, &adj.right1); + if (error) + goto out_free; + + error = xmi_next(req->ip2, bmap_flags, &irec2, &adj.right2); + if (error) + goto out_free; + + /* Update extent count deltas. */ + d_nexts1 += xmi_delta_nextents_step(req->ip1->i_mount, + &adj.left1, &irec1, &irec2, &adj.right1); + + d_nexts2 += xmi_delta_nextents_step(req->ip1->i_mount, + &adj.left2, &irec2, &irec1, &adj.right2); + + /* Now pretend we exchanged the mappings. */ + if (xmi_can_merge(&adj.left2, &irec1)) + adj.left2.br_blockcount += irec1.br_blockcount; + else + memcpy(&adj.left2, &irec1, sizeof(irec1)); + + if (xmi_can_merge(&adj.left1, &irec2)) + adj.left1.br_blockcount += irec2.br_blockcount; + else + memcpy(&adj.left1, &irec2, sizeof(irec2)); + + xmi_advance(xmi, &irec1); + } + + /* Account for the blocks that are being exchanged. */ + if (XFS_IS_REALTIME_INODE(req->ip1) && + xfs_exchmaps_reqfork(req) == XFS_DATA_FORK) { + req->ip1_rtbcount = ip1_blocks; + req->ip2_rtbcount = ip2_blocks; + } else { + req->ip1_bcount = ip1_blocks; + req->ip2_bcount = ip2_blocks; + } + + /* + * Make sure that both forks have enough slack left in their extent + * counters that the exchange operation will not overflow. + */ + trace_xfs_exchmaps_delta_nextents(req, d_nexts1, d_nexts2); + if (req->ip1 == req->ip2) { + error = xmi_ensure_delta_nextents(req, req->ip1, + d_nexts1 + d_nexts2); + } else { + error = xmi_ensure_delta_nextents(req, req->ip1, d_nexts1); + if (error) + goto out_free; + error = xmi_ensure_delta_nextents(req, req->ip2, d_nexts2); + } + if (error) + goto out_free; + + trace_xfs_exchmaps_initial_estimate(req); + error = xfs_exchmaps_estimate_overhead(req); +out_free: + kmem_cache_free(xfs_exchmaps_intent_cache, xmi); + return error; +} + +/* Set the reflink flag before an operation. */ +static inline void +xfs_exchmaps_set_reflink( + struct xfs_trans *tp, + struct xfs_inode *ip) +{ + trace_xfs_reflink_set_inode_flag(ip); + + ip->i_diflags2 |= XFS_DIFLAG2_REFLINK; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); +} + +/* + * If either file has shared blocks and we're exchanging data forks, we must + * flag the other file as having shared blocks so that we get the shared-block + * rmap functions if we need to fix up the rmaps. + */ +void +xfs_exchmaps_ensure_reflink( + struct xfs_trans *tp, + const struct xfs_exchmaps_intent *xmi) +{ + unsigned int rs = 0; + + if (xfs_is_reflink_inode(xmi->xmi_ip1)) + rs |= 1; + if (xfs_is_reflink_inode(xmi->xmi_ip2)) + rs |= 2; + + if ((rs & 1) && !xfs_is_reflink_inode(xmi->xmi_ip2)) + xfs_exchmaps_set_reflink(tp, xmi->xmi_ip2); + + if ((rs & 2) && !xfs_is_reflink_inode(xmi->xmi_ip1)) + xfs_exchmaps_set_reflink(tp, xmi->xmi_ip1); +} + +/* Set the large extent count flag before an operation if needed. */ +static inline void +xfs_exchmaps_ensure_large_extent_counts( + struct xfs_trans *tp, + struct xfs_inode *ip) +{ + if (xfs_inode_has_large_extent_counts(ip)) + return; + + ip->i_diflags2 |= XFS_DIFLAG2_NREXT64; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); +} + +/* Widen the extent counter fields of both inodes if necessary. */ +void +xfs_exchmaps_upgrade_extent_counts( + struct xfs_trans *tp, + const struct xfs_exchmaps_intent *xmi) +{ + if (!xfs_has_large_extent_counts(tp->t_mountp)) + return; + + xfs_exchmaps_ensure_large_extent_counts(tp, xmi->xmi_ip1); + xfs_exchmaps_ensure_large_extent_counts(tp, xmi->xmi_ip2); +} + +/* + * Schedule an exchange a range of mappings from one inode to another. + * + * The use of file mapping exchange log intent items ensures the operation can + * be resumed even if the system goes down. The caller must commit the + * transaction to start the work. + * + * The caller must ensure the inodes must be joined to the transaction and + * ILOCKd; they will still be joined to the transaction at exit. + */ +void +xfs_exchange_mappings( + struct xfs_trans *tp, + const struct xfs_exchmaps_req *req) +{ + struct xfs_exchmaps_intent *xmi; + + BUILD_BUG_ON(XFS_EXCHMAPS_INTERNAL_FLAGS & XFS_EXCHMAPS_LOGGED_FLAGS); + + xfs_assert_ilocked(req->ip1, XFS_ILOCK_EXCL); + xfs_assert_ilocked(req->ip2, XFS_ILOCK_EXCL); + ASSERT(!(req->flags & ~XFS_EXCHMAPS_LOGGED_FLAGS)); + if (req->flags & XFS_EXCHMAPS_SET_SIZES) + ASSERT(!(req->flags & XFS_EXCHMAPS_ATTR_FORK)); + ASSERT(xfs_has_exchange_range(tp->t_mountp)); + + if (req->blockcount == 0) + return; + + xmi = xfs_exchmaps_init_intent(req); + xfs_exchmaps_defer_add(tp, xmi); + xfs_exchmaps_ensure_reflink(tp, xmi); + xfs_exchmaps_upgrade_extent_counts(tp, xmi); +} diff --git a/fs/xfs/libxfs/xfs_exchmaps.h b/fs/xfs/libxfs/xfs_exchmaps.h new file mode 100644 index 000000000000..fa822dff202a --- /dev/null +++ b/fs/xfs/libxfs/xfs_exchmaps.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2020-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_EXCHMAPS_H__ +#define __XFS_EXCHMAPS_H__ + +/* In-core deferred operation info about a file mapping exchange request. */ +struct xfs_exchmaps_intent { + /* List of other incore deferred work. */ + struct list_head xmi_list; + + /* Inodes participating in the operation. */ + struct xfs_inode *xmi_ip1; + struct xfs_inode *xmi_ip2; + + /* File offset range information. */ + xfs_fileoff_t xmi_startoff1; + xfs_fileoff_t xmi_startoff2; + xfs_filblks_t xmi_blockcount; + + /* Set these file sizes after the operation, unless negative. */ + xfs_fsize_t xmi_isize1; + xfs_fsize_t xmi_isize2; + + uint64_t xmi_flags; /* XFS_EXCHMAPS_* flags */ +}; + +/* Try to convert inode2 from block to short format at the end, if possible. */ +#define __XFS_EXCHMAPS_INO2_SHORTFORM (1ULL << 63) + +#define XFS_EXCHMAPS_INTERNAL_FLAGS (__XFS_EXCHMAPS_INO2_SHORTFORM) + +/* flags that can be passed to xfs_exchmaps_{estimate,mappings} */ +#define XFS_EXCHMAPS_PARAMS (XFS_EXCHMAPS_ATTR_FORK | \ + XFS_EXCHMAPS_SET_SIZES | \ + XFS_EXCHMAPS_INO1_WRITTEN) + +static inline int +xfs_exchmaps_whichfork(const struct xfs_exchmaps_intent *xmi) +{ + if (xmi->xmi_flags & XFS_EXCHMAPS_ATTR_FORK) + return XFS_ATTR_FORK; + return XFS_DATA_FORK; +} + +/* Parameters for a mapping exchange request. */ +struct xfs_exchmaps_req { + /* Inodes participating in the operation. */ + struct xfs_inode *ip1; + struct xfs_inode *ip2; + + /* File offset range information. */ + xfs_fileoff_t startoff1; + xfs_fileoff_t startoff2; + xfs_filblks_t blockcount; + + /* XFS_EXCHMAPS_* operation flags */ + uint64_t flags; + + /* + * Fields below this line are filled out by xfs_exchmaps_estimate; + * callers should initialize this part of the struct to zero. + */ + + /* + * Data device blocks to be moved out of ip1, and free space needed to + * handle the bmbt changes. + */ + xfs_filblks_t ip1_bcount; + + /* + * Data device blocks to be moved out of ip2, and free space needed to + * handle the bmbt changes. + */ + xfs_filblks_t ip2_bcount; + + /* rt blocks to be moved out of ip1. */ + xfs_filblks_t ip1_rtbcount; + + /* rt blocks to be moved out of ip2. */ + xfs_filblks_t ip2_rtbcount; + + /* Free space needed to handle the bmbt changes */ + unsigned long long resblks; + + /* Number of exchanges needed to complete the operation */ + unsigned long long nr_exchanges; +}; + +static inline int +xfs_exchmaps_reqfork(const struct xfs_exchmaps_req *req) +{ + if (req->flags & XFS_EXCHMAPS_ATTR_FORK) + return XFS_ATTR_FORK; + return XFS_DATA_FORK; +} + +int xfs_exchmaps_estimate_overhead(struct xfs_exchmaps_req *req); +int xfs_exchmaps_estimate(struct xfs_exchmaps_req *req); + +extern struct kmem_cache *xfs_exchmaps_intent_cache; + +int __init xfs_exchmaps_intent_init_cache(void); +void xfs_exchmaps_intent_destroy_cache(void); + +struct xfs_exchmaps_intent *xfs_exchmaps_init_intent( + const struct xfs_exchmaps_req *req); +void xfs_exchmaps_ensure_reflink(struct xfs_trans *tp, + const struct xfs_exchmaps_intent *xmi); +void xfs_exchmaps_upgrade_extent_counts(struct xfs_trans *tp, + const struct xfs_exchmaps_intent *xmi); + +int xfs_exchmaps_finish_one(struct xfs_trans *tp, + struct xfs_exchmaps_intent *xmi); + +int xfs_exchmaps_check_forks(struct xfs_mount *mp, + const struct xfs_exchmaps_req *req); + +void xfs_exchange_mappings(struct xfs_trans *tp, + const struct xfs_exchmaps_req *req); + +#endif /* __XFS_EXCHMAPS_H__ */ diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 371dc07233e0..779dac59b1f3 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -90,15 +90,14 @@ struct xfs_ifork; #define XFSLABEL_MAX 12 /* - * Superblock - in core version. Must match the ondisk version below. - * Must be padded to 64 bit alignment. + * Superblock - in core version. Must be padded to 64 bit alignment. */ typedef struct xfs_sb { uint32_t sb_magicnum; /* magic number == XFS_SB_MAGIC */ uint32_t sb_blocksize; /* logical block size, bytes */ xfs_rfsblock_t sb_dblocks; /* number of data blocks */ xfs_rfsblock_t sb_rblocks; /* number of realtime blocks */ - xfs_rtblock_t sb_rextents; /* number of realtime extents */ + xfs_rtbxlen_t sb_rextents; /* number of realtime extents */ uuid_t sb_uuid; /* user-visible file system unique id */ xfs_fsblock_t sb_logstart; /* starting block of log if internal */ xfs_ino_t sb_rootino; /* root inode number */ @@ -113,7 +112,7 @@ typedef struct xfs_sb { uint16_t sb_sectsize; /* volume sector size, bytes */ uint16_t sb_inodesize; /* inode size, bytes */ uint16_t sb_inopblock; /* inodes per block */ - char sb_fname[XFSLABEL_MAX]; /* file system name */ + char sb_fname[XFSLABEL_MAX] __nonstring; /* file system name */ uint8_t sb_blocklog; /* log2 of sb_blocksize */ uint8_t sb_sectlog; /* log2 of sb_sectsize */ uint8_t sb_inodelog; /* log2 of sb_inodesize */ @@ -175,13 +174,20 @@ typedef struct xfs_sb { xfs_lsn_t sb_lsn; /* last write sequence */ uuid_t sb_meta_uuid; /* metadata file system unique id */ + xfs_ino_t sb_metadirino; /* metadata directory tree root */ + + xfs_rgnumber_t sb_rgcount; /* number of realtime groups */ + xfs_rtxlen_t sb_rgextents; /* size of a realtime group in rtx */ + uint8_t sb_rgblklog; /* rt group number shift */ + uint8_t sb_pad[7]; /* zeroes */ + xfs_rfsblock_t sb_rtstart; /* start of internal RT section (FSB) */ + xfs_filblks_t sb_rtreserved; /* reserved (zoned) RT blocks */ + /* must be padded to 64 bit alignment */ } xfs_sb_t; -#define XFS_SB_CRC_OFF offsetof(struct xfs_sb, sb_crc) - /* - * Superblock - on disk version. Must match the in core version above. + * Superblock - on disk version. * Must be padded to 64 bit alignment. */ struct xfs_dsb { @@ -262,9 +268,24 @@ struct xfs_dsb { __be64 sb_lsn; /* last write sequence */ uuid_t sb_meta_uuid; /* metadata file system unique id */ - /* must be padded to 64 bit alignment */ + __be64 sb_metadirino; /* metadata directory tree root */ + __be32 sb_rgcount; /* # of realtime groups */ + __be32 sb_rgextents; /* size of rtgroup in rtx */ + __u8 sb_rgblklog; /* rt group number shift */ + __u8 sb_pad[7]; /* zeroes */ + __be64 sb_rtstart; /* start of internal RT section (FSB) */ + __be64 sb_rtreserved; /* reserved (zoned) RT blocks */ + + /* + * The size of this structure must be padded to 64 bit alignment. + * + * NOTE: Don't forget to update secondary_sb_whack in xfs_repair when + * adding new fields here. + */ }; +#define XFS_SB_CRC_OFF offsetof(struct xfs_dsb, sb_crc) + /* * Misc. Flags - warning - these will be cleared by xfs_repair unless * a feature bit is set when the flag is used. @@ -279,7 +300,7 @@ struct xfs_dsb { #define XFS_SB_VERSION_NUM(sbp) ((sbp)->sb_versionnum & XFS_SB_VERSION_NUMBITS) -static inline bool xfs_sb_is_v5(struct xfs_sb *sbp) +static inline bool xfs_sb_is_v5(const struct xfs_sb *sbp) { return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5; } @@ -288,12 +309,12 @@ static inline bool xfs_sb_is_v5(struct xfs_sb *sbp) * Detect a mismatched features2 field. Older kernels read/wrote * this into the wrong slot, so to be safe we keep them in sync. */ -static inline bool xfs_sb_has_mismatched_features2(struct xfs_sb *sbp) +static inline bool xfs_sb_has_mismatched_features2(const struct xfs_sb *sbp) { return sbp->sb_bad_features2 != sbp->sb_features2; } -static inline bool xfs_sb_version_hasmorebits(struct xfs_sb *sbp) +static inline bool xfs_sb_version_hasmorebits(const struct xfs_sb *sbp) { return xfs_sb_is_v5(sbp) || (sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT); @@ -343,8 +364,8 @@ static inline void xfs_sb_version_addprojid32(struct xfs_sb *sbp) #define XFS_SB_FEAT_COMPAT_UNKNOWN ~XFS_SB_FEAT_COMPAT_ALL static inline bool xfs_sb_has_compat_feature( - struct xfs_sb *sbp, - uint32_t feature) + const struct xfs_sb *sbp, + uint32_t feature) { return (sbp->sb_features_compat & feature) != 0; } @@ -361,31 +382,42 @@ xfs_sb_has_compat_feature( #define XFS_SB_FEAT_RO_COMPAT_UNKNOWN ~XFS_SB_FEAT_RO_COMPAT_ALL static inline bool xfs_sb_has_ro_compat_feature( - struct xfs_sb *sbp, - uint32_t feature) + const struct xfs_sb *sbp, + uint32_t feature) { return (sbp->sb_features_ro_compat & feature) != 0; } -#define XFS_SB_FEAT_INCOMPAT_FTYPE (1 << 0) /* filetype in dirent */ -#define XFS_SB_FEAT_INCOMPAT_SPINODES (1 << 1) /* sparse inode chunks */ -#define XFS_SB_FEAT_INCOMPAT_META_UUID (1 << 2) /* metadata UUID */ -#define XFS_SB_FEAT_INCOMPAT_BIGTIME (1 << 3) /* large timestamps */ -#define XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR (1 << 4) /* needs xfs_repair */ -#define XFS_SB_FEAT_INCOMPAT_NREXT64 (1 << 5) /* large extent counters */ +#define XFS_SB_FEAT_INCOMPAT_FTYPE (1 << 0) /* filetype in dirent */ +#define XFS_SB_FEAT_INCOMPAT_SPINODES (1 << 1) /* sparse inode chunks */ +#define XFS_SB_FEAT_INCOMPAT_META_UUID (1 << 2) /* metadata UUID */ +#define XFS_SB_FEAT_INCOMPAT_BIGTIME (1 << 3) /* large timestamps */ +#define XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR (1 << 4) /* needs xfs_repair */ +#define XFS_SB_FEAT_INCOMPAT_NREXT64 (1 << 5) /* large extent counters */ +#define XFS_SB_FEAT_INCOMPAT_EXCHRANGE (1 << 6) /* exchangerange supported */ +#define XFS_SB_FEAT_INCOMPAT_PARENT (1 << 7) /* parent pointers */ +#define XFS_SB_FEAT_INCOMPAT_METADIR (1 << 8) /* metadata dir tree */ +#define XFS_SB_FEAT_INCOMPAT_ZONED (1 << 9) /* zoned RT allocator */ +#define XFS_SB_FEAT_INCOMPAT_ZONE_GAPS (1 << 10) /* RTGs have LBA gaps */ + #define XFS_SB_FEAT_INCOMPAT_ALL \ - (XFS_SB_FEAT_INCOMPAT_FTYPE| \ - XFS_SB_FEAT_INCOMPAT_SPINODES| \ - XFS_SB_FEAT_INCOMPAT_META_UUID| \ - XFS_SB_FEAT_INCOMPAT_BIGTIME| \ - XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR| \ - XFS_SB_FEAT_INCOMPAT_NREXT64) + (XFS_SB_FEAT_INCOMPAT_FTYPE | \ + XFS_SB_FEAT_INCOMPAT_SPINODES | \ + XFS_SB_FEAT_INCOMPAT_META_UUID | \ + XFS_SB_FEAT_INCOMPAT_BIGTIME | \ + XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR | \ + XFS_SB_FEAT_INCOMPAT_NREXT64 | \ + XFS_SB_FEAT_INCOMPAT_EXCHRANGE | \ + XFS_SB_FEAT_INCOMPAT_PARENT | \ + XFS_SB_FEAT_INCOMPAT_METADIR | \ + XFS_SB_FEAT_INCOMPAT_ZONED | \ + XFS_SB_FEAT_INCOMPAT_ZONE_GAPS) #define XFS_SB_FEAT_INCOMPAT_UNKNOWN ~XFS_SB_FEAT_INCOMPAT_ALL static inline bool xfs_sb_has_incompat_feature( - struct xfs_sb *sbp, - uint32_t feature) + const struct xfs_sb *sbp, + uint32_t feature) { return (sbp->sb_features_incompat & feature) != 0; } @@ -396,8 +428,8 @@ xfs_sb_has_incompat_feature( #define XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN ~XFS_SB_FEAT_INCOMPAT_LOG_ALL static inline bool xfs_sb_has_incompat_log_feature( - struct xfs_sb *sbp, - uint32_t feature) + const struct xfs_sb *sbp, + uint32_t feature) { return (sbp->sb_features_log_incompat & feature) != 0; } @@ -417,7 +449,7 @@ xfs_sb_add_incompat_log_features( sbp->sb_features_log_incompat |= features; } -static inline bool xfs_sb_version_haslogxattrs(struct xfs_sb *sbp) +static inline bool xfs_sb_version_haslogxattrs(const struct xfs_sb *sbp) { return xfs_sb_is_v5(sbp) && (sbp->sb_features_log_incompat & XFS_SB_FEAT_INCOMPAT_LOG_XATTRS); @@ -477,15 +509,9 @@ xfs_is_quota_inode(struct xfs_sb *sbp, xfs_ino_t ino) #define XFS_AGI_GOOD_VERSION(v) ((v) == XFS_AGI_VERSION) /* - * Btree number 0 is bno, 1 is cnt, 2 is rmap. This value gives the size of the - * arrays below. - */ -#define XFS_BTNUM_AGF ((int)XFS_BTNUM_RMAPi + 1) - -/* - * The second word of agf_levels in the first a.g. overlaps the EFS - * superblock's magic number. Since the magic numbers valid for EFS - * are > 64k, our value cannot be confused for an EFS superblock's. + * agf_cnt_level in the first AGF overlaps the EFS superblock's magic number. + * Since the magic numbers valid for EFS are > 64k, our value cannot be confused + * for an EFS superblock. */ typedef struct xfs_agf { @@ -499,8 +525,13 @@ typedef struct xfs_agf { /* * Freespace and rmap information */ - __be32 agf_roots[XFS_BTNUM_AGF]; /* root blocks */ - __be32 agf_levels[XFS_BTNUM_AGF]; /* btree levels */ + __be32 agf_bno_root; /* bnobt root block */ + __be32 agf_cnt_root; /* cntbt root block */ + __be32 agf_rmap_root; /* rmapbt root block */ + + __be32 agf_bno_level; /* bnobt btree levels */ + __be32 agf_cnt_level; /* cntbt btree levels */ + __be32 agf_rmap_level; /* rmapbt btree levels */ __be32 agf_flfirst; /* first freelist block's index */ __be32 agf_fllast; /* last freelist block's index */ @@ -691,6 +722,59 @@ struct xfs_agfl { xfs_daddr_to_agno(mp, (d) + (len) - 1))) /* + * Realtime bitmap information is accessed by the word, which is currently + * stored in host-endian format. Starting with the realtime groups feature, + * the words are stored in be32 ondisk. + */ +union xfs_rtword_raw { + __u32 old; + __be32 rtg; +}; + +/* + * Realtime summary counts are accessed by the word, which is currently + * stored in host-endian format. Starting with the realtime groups feature, + * the words are stored in be32 ondisk. + */ +union xfs_suminfo_raw { + __u32 old; + __be32 rtg; +}; + +/* + * Realtime allocation groups break the rt section into multiple pieces that + * could be locked independently. Realtime block group numbers are 32-bit + * quantities. Block numbers within a group are also 32-bit quantities, but + * the upper bit must never be set. rtgroup 0 might have a superblock in it, + * so the minimum size of an rtgroup is 2 rtx. + */ +#define XFS_MAX_RGBLOCKS ((xfs_rgblock_t)(1U << 31) - 1) +#define XFS_MIN_RGEXTENTS ((xfs_rtxlen_t)2) +#define XFS_MAX_RGNUMBER ((xfs_rgnumber_t)(-1U)) + +#define XFS_RTSB_MAGIC 0x46726F67 /* 'Frog' */ + +/* + * Realtime superblock - on disk version. Must be padded to 64 bit alignment. + * The first block of the realtime volume contains this superblock. + */ +struct xfs_rtsb { + __be32 rsb_magicnum; /* magic number == XFS_RTSB_MAGIC */ + __le32 rsb_crc; /* superblock crc */ + + __be32 rsb_pad; /* zero */ + unsigned char rsb_fname[XFSLABEL_MAX]; /* file system name */ + + uuid_t rsb_uuid; /* user-visible file system unique id */ + uuid_t rsb_meta_uuid; /* metadata file system unique id */ + + /* must be padded to 64 bit alignment */ +}; + +#define XFS_RTSB_CRC_OFF offsetof(struct xfs_rtsb, rsb_crc) +#define XFS_RTSB_DADDR ((xfs_daddr_t)0) /* daddr in rt section */ + +/* * XFS Timestamps * ============== * @@ -772,6 +856,31 @@ static inline time64_t xfs_bigtime_to_unix(uint64_t ondisk_seconds) return (time64_t)ondisk_seconds - XFS_BIGTIME_EPOCH_OFFSET; } +enum xfs_metafile_type { + XFS_METAFILE_UNKNOWN, /* unknown */ + XFS_METAFILE_DIR, /* metadir directory */ + XFS_METAFILE_USRQUOTA, /* user quota */ + XFS_METAFILE_GRPQUOTA, /* group quota */ + XFS_METAFILE_PRJQUOTA, /* project quota */ + XFS_METAFILE_RTBITMAP, /* rt bitmap */ + XFS_METAFILE_RTSUMMARY, /* rt summary */ + XFS_METAFILE_RTRMAP, /* rt rmap */ + XFS_METAFILE_RTREFCOUNT, /* rt refcount */ + + XFS_METAFILE_MAX +} __packed; + +#define XFS_METAFILE_TYPE_STR \ + { XFS_METAFILE_UNKNOWN, "unknown" }, \ + { XFS_METAFILE_DIR, "dir" }, \ + { XFS_METAFILE_USRQUOTA, "usrquota" }, \ + { XFS_METAFILE_GRPQUOTA, "grpquota" }, \ + { XFS_METAFILE_PRJQUOTA, "prjquota" }, \ + { XFS_METAFILE_RTBITMAP, "rtbitmap" }, \ + { XFS_METAFILE_RTSUMMARY, "rtsummary" }, \ + { XFS_METAFILE_RTRMAP, "rtrmap" }, \ + { XFS_METAFILE_RTREFCOUNT, "rtrefcount" } + /* * On-disk inode structure. * @@ -794,7 +903,7 @@ struct xfs_dinode { __be16 di_mode; /* mode and type of file */ __u8 di_version; /* inode version */ __u8 di_format; /* format of di_c data */ - __be16 di_onlink; /* old number of links to file */ + __be16 di_metatype; /* XFS_METAFILE_*; was di_onlink */ __be32 di_uid; /* owner's user id */ __be32 di_gid; /* owner's group id */ __be32 di_nlink; /* number of links to file */ @@ -850,7 +959,12 @@ struct xfs_dinode { __be64 di_changecount; /* number of attribute changes */ __be64 di_lsn; /* flush sequence */ __be64 di_flags2; /* more random flags */ - __be32 di_cowextsize; /* basic cow extent size for file */ + union { + /* basic cow extent size for (regular) file */ + __be32 di_cowextsize; + /* used blocks in RTG for (zoned) rtrmap inode */ + __be32 di_used_blocks; + }; __u8 di_pad2[12]; /* more padding for future expansion */ /* fields only written to during inode creation */ @@ -883,6 +997,12 @@ static inline uint xfs_dinode_size(int version) #define XFS_MAXLINK ((1U << 31) - 1U) /* + * Any file that hits the maximum ondisk link count should be pinned to avoid + * a use-after-free situation. + */ +#define XFS_NLINK_PINNED (~0U) + +/* * Values for di_format * * This enum is used in string mapping in xfs_trace.h; please keep the @@ -893,7 +1013,8 @@ enum xfs_dinode_fmt { XFS_DINODE_FMT_LOCAL, /* bulk data */ XFS_DINODE_FMT_EXTENTS, /* struct xfs_bmbt_rec */ XFS_DINODE_FMT_BTREE, /* struct xfs_bmdr_block */ - XFS_DINODE_FMT_UUID /* added long ago, but never used */ + XFS_DINODE_FMT_UUID, /* added long ago, but never used */ + XFS_DINODE_FMT_META_BTREE, /* metadata btree */ }; #define XFS_INODE_FORMAT_STR \ @@ -901,7 +1022,8 @@ enum xfs_dinode_fmt { { XFS_DINODE_FMT_LOCAL, "local" }, \ { XFS_DINODE_FMT_EXTENTS, "extent" }, \ { XFS_DINODE_FMT_BTREE, "btree" }, \ - { XFS_DINODE_FMT_UUID, "uuid" } + { XFS_DINODE_FMT_UUID, "uuid" }, \ + { XFS_DINODE_FMT_META_BTREE, "meta_btree" } /* * Max values for extnum and aextnum. @@ -992,7 +1114,7 @@ enum xfs_dinode_fmt { * Return pointers to the data or attribute forks. */ #define XFS_DFORK_DPTR(dip) \ - ((char *)dip + xfs_dinode_size(dip->di_version)) + ((void *)dip + xfs_dinode_size(dip->di_version)) #define XFS_DFORK_APTR(dip) \ (XFS_DFORK_DPTR(dip) + XFS_DFORK_BOFF(dip)) #define XFS_DFORK_PTR(dip,w) \ @@ -1064,21 +1186,60 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev) * Values for di_flags2 These start by being exposed to userspace in the upper * 16 bits of the XFS_XFLAG_s range. */ -#define XFS_DIFLAG2_DAX_BIT 0 /* use DAX for this inode */ -#define XFS_DIFLAG2_REFLINK_BIT 1 /* file's blocks may be shared */ -#define XFS_DIFLAG2_COWEXTSIZE_BIT 2 /* copy on write extent size hint */ -#define XFS_DIFLAG2_BIGTIME_BIT 3 /* big timestamps */ -#define XFS_DIFLAG2_NREXT64_BIT 4 /* large extent counters */ +/* use DAX for this inode */ +#define XFS_DIFLAG2_DAX_BIT 0 + +/* file's blocks may be shared */ +#define XFS_DIFLAG2_REFLINK_BIT 1 + +/* copy on write extent size hint */ +#define XFS_DIFLAG2_COWEXTSIZE_BIT 2 + +/* big timestamps */ +#define XFS_DIFLAG2_BIGTIME_BIT 3 + +/* large extent counters */ +#define XFS_DIFLAG2_NREXT64_BIT 4 + +/* + * The inode contains filesystem metadata and can be found through the metadata + * directory tree. Metadata inodes must satisfy the following constraints: + * + * - V5 filesystem (and ftype) are enabled; + * - The only valid modes are regular files and directories; + * - The access bits must be zero; + * - DMAPI event and state masks are zero; + * - The user and group IDs must be zero; + * - The project ID can be used as a u32 annotation; + * - The immutable, sync, noatime, nodump, nodefrag flags must be set. + * - The dax flag must not be set. + * - Directories must have nosymlinks set. + * + * These requirements are chosen defensively to minimize the ability of + * userspace to read or modify the contents, should a metadata file ever + * escape to userspace. + * + * There are further constraints on the directory tree itself: + * + * - Metadata inodes must never be resolvable through the root directory; + * - They must never be accessed by userspace; + * - Metadata directory entries must have correct ftype. + * + * Superblock-rooted metadata files must have the METADATA iflag set even + * though they do not have a parent directory. + */ +#define XFS_DIFLAG2_METADATA_BIT 5 -#define XFS_DIFLAG2_DAX (1 << XFS_DIFLAG2_DAX_BIT) -#define XFS_DIFLAG2_REFLINK (1 << XFS_DIFLAG2_REFLINK_BIT) -#define XFS_DIFLAG2_COWEXTSIZE (1 << XFS_DIFLAG2_COWEXTSIZE_BIT) -#define XFS_DIFLAG2_BIGTIME (1 << XFS_DIFLAG2_BIGTIME_BIT) -#define XFS_DIFLAG2_NREXT64 (1 << XFS_DIFLAG2_NREXT64_BIT) +#define XFS_DIFLAG2_DAX (1ULL << XFS_DIFLAG2_DAX_BIT) +#define XFS_DIFLAG2_REFLINK (1ULL << XFS_DIFLAG2_REFLINK_BIT) +#define XFS_DIFLAG2_COWEXTSIZE (1ULL << XFS_DIFLAG2_COWEXTSIZE_BIT) +#define XFS_DIFLAG2_BIGTIME (1ULL << XFS_DIFLAG2_BIGTIME_BIT) +#define XFS_DIFLAG2_NREXT64 (1ULL << XFS_DIFLAG2_NREXT64_BIT) +#define XFS_DIFLAG2_METADATA (1ULL << XFS_DIFLAG2_METADATA_BIT) #define XFS_DIFLAG2_ANY \ (XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \ - XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64) + XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64 | XFS_DIFLAG2_METADATA) static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip) { @@ -1093,6 +1254,12 @@ static inline bool xfs_dinode_has_large_extent_counts( (dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_NREXT64)); } +static inline bool xfs_dinode_is_metadir(const struct xfs_dinode *dip) +{ + return dip->di_version >= 3 && + (dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA)); +} + /* * Inode number format: * low inopblog bits - offset in block @@ -1140,33 +1307,23 @@ static inline bool xfs_dinode_has_large_extent_counts( #define XFS_DFL_RTEXTSIZE (64 * 1024) /* 64kB */ #define XFS_MIN_RTEXTSIZE (4 * 1024) /* 4kB */ -#define XFS_BLOCKSIZE(mp) ((mp)->m_sb.sb_blocksize) -#define XFS_BLOCKMASK(mp) ((mp)->m_blockmask) -#define XFS_BLOCKWSIZE(mp) ((mp)->m_blockwsize) -#define XFS_BLOCKWMASK(mp) ((mp)->m_blockwmask) - /* - * RT Summary and bit manipulation macros. + * RT bit manipulation macros. */ -#define XFS_SUMOFFS(mp,ls,bb) ((int)((ls) * (mp)->m_sb.sb_rbmblocks + (bb))) -#define XFS_SUMOFFSTOBLOCK(mp,s) \ - (((s) * (uint)sizeof(xfs_suminfo_t)) >> (mp)->m_sb.sb_blocklog) -#define XFS_SUMPTR(mp,bp,so) \ - ((xfs_suminfo_t *)((bp)->b_addr + \ - (((so) * (uint)sizeof(xfs_suminfo_t)) & XFS_BLOCKMASK(mp)))) - -#define XFS_BITTOBLOCK(mp,bi) ((bi) >> (mp)->m_blkbit_log) -#define XFS_BLOCKTOBIT(mp,bb) ((bb) << (mp)->m_blkbit_log) -#define XFS_BITTOWORD(mp,bi) \ - ((int)(((bi) >> XFS_NBWORDLOG) & XFS_BLOCKWMASK(mp))) +#define XFS_RTBITMAP_MAGIC 0x424D505A /* BMPZ */ +#define XFS_RTSUMMARY_MAGIC 0x53554D59 /* SUMY */ -#define XFS_RTMIN(a,b) ((a) < (b) ? (a) : (b)) -#define XFS_RTMAX(a,b) ((a) > (b) ? (a) : (b)) - -#define XFS_RTLOBIT(w) xfs_lowbit32(w) -#define XFS_RTHIBIT(w) xfs_highbit32(w) +struct xfs_rtbuf_blkinfo { + __be32 rt_magic; /* validity check on block */ + __be32 rt_crc; /* CRC of block */ + __be64 rt_owner; /* inode that owns the block */ + __be64 rt_blkno; /* first block of the buffer */ + __be64 rt_lsn; /* sequence number of last write */ + uuid_t rt_uuid; /* filesystem we belong to */ +}; -#define XFS_RTBLOCKLOG(b) xfs_highbit64(b) +#define XFS_RTBUF_CRC_OFF \ + offsetof(struct xfs_rtbuf_blkinfo, rt_crc) /* * Dquot and dquot block format definitions @@ -1270,6 +1427,9 @@ static inline time64_t xfs_dq_bigtime_to_unix(uint32_t ondisk_seconds) #define XFS_DQ_GRACE_MIN ((int64_t)0) #define XFS_DQ_GRACE_MAX ((int64_t)U32_MAX) +/* Maximum id value for a quota record */ +#define XFS_DQ_ID_MAX (U32_MAX) + /* * This is the main portion of the on-disk representation of quota information * for a user. We pad this with some more expansion room to construct the on @@ -1584,6 +1744,24 @@ typedef __be32 xfs_rmap_ptr_t; XFS_IBT_BLOCK(mp) + 1) /* + * Realtime Reverse mapping btree format definitions + * + * This is a btree for reverse mapping records for realtime volumes + */ +#define XFS_RTRMAP_CRC_MAGIC 0x4d415052 /* 'MAPR' */ + +/* + * rtrmap root header, on-disk form only. + */ +struct xfs_rtrmap_root { + __be16 bb_level; /* 0 is a leaf */ + __be16 bb_numrecs; /* current # of data records */ +}; + +/* inode-based btree pointer type */ +typedef __be64 xfs_rtrmap_ptr_t; + +/* * Reference Count Btree format definitions * */ @@ -1626,12 +1804,29 @@ struct xfs_refcount_key { __be32 rc_startblock; /* starting block number */ }; -#define MAXREFCOUNT ((xfs_nlink_t)~0U) -#define MAXREFCEXTLEN ((xfs_extlen_t)~0U) +#define XFS_REFC_REFCOUNT_MAX ((xfs_nlink_t)~0U) +#define XFS_REFC_LEN_MAX ((xfs_extlen_t)~0U) /* btree pointer type */ typedef __be32 xfs_refcount_ptr_t; +/* + * Realtime Reference Count btree format definitions + * + * This is a btree for reference count records for realtime volumes + */ +#define XFS_RTREFC_CRC_MAGIC 0x52434e54 /* 'RCNT' */ + +/* + * rt refcount root header, on-disk form only. + */ +struct xfs_rtrefcount_root { + __be16 bb_level; /* 0 is a leaf */ + __be16 bb_numrecs; /* current # of data records */ +}; + +/* inode-rooted btree pointer type */ +typedef __be64 xfs_rtrefcount_ptr_t; /* * BMAP Btree format definitions diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 1cfd5bc6520a..12463ba766da 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -8,6 +8,7 @@ /* * SGI's XFS filesystem's major stuff (constants, structures) + * NOTE: This file must be compile-able with C++ compilers. */ /* @@ -186,7 +187,11 @@ struct xfs_fsop_geom { __u32 logsunit; /* log stripe unit, bytes */ uint32_t sick; /* o: unhealthy fs & rt metadata */ uint32_t checked; /* o: checked fs & rt metadata */ - __u64 reserved[17]; /* reserved space */ + __u32 rgextents; /* rt extents in a realtime group */ + __u32 rgcount; /* number of realtime groups */ + __u64 rtstart; /* start of internal rt section */ + __u64 rtreserved; /* RT (zoned) reserved blocks */ + __u64 reserved[14]; /* reserved space */ }; #define XFS_FSOP_GEOM_SICK_COUNTERS (1 << 0) /* summary counters */ @@ -195,6 +200,10 @@ struct xfs_fsop_geom { #define XFS_FSOP_GEOM_SICK_PQUOTA (1 << 3) /* project quota */ #define XFS_FSOP_GEOM_SICK_RT_BITMAP (1 << 4) /* realtime bitmap */ #define XFS_FSOP_GEOM_SICK_RT_SUMMARY (1 << 5) /* realtime summary */ +#define XFS_FSOP_GEOM_SICK_QUOTACHECK (1 << 6) /* quota counts */ +#define XFS_FSOP_GEOM_SICK_NLINKS (1 << 7) /* inode link counts */ +#define XFS_FSOP_GEOM_SICK_METADIR (1 << 8) /* metadata directory */ +#define XFS_FSOP_GEOM_SICK_METAPATH (1 << 9) /* metadir tree path */ /* Output for XFS_FS_COUNTS */ typedef struct xfs_fsop_counts { @@ -237,6 +246,10 @@ typedef struct xfs_fsop_resblks { #define XFS_FSOP_GEOM_FLAGS_BIGTIME (1 << 21) /* 64-bit nsec timestamps */ #define XFS_FSOP_GEOM_FLAGS_INOBTCNT (1 << 22) /* inobt btree counter */ #define XFS_FSOP_GEOM_FLAGS_NREXT64 (1 << 23) /* large extent counters */ +#define XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE (1 << 24) /* exchange range */ +#define XFS_FSOP_GEOM_FLAGS_PARENT (1 << 25) /* linux parent pointers */ +#define XFS_FSOP_GEOM_FLAGS_METADIR (1 << 26) /* metadata directories */ +#define XFS_FSOP_GEOM_FLAGS_ZONED (1 << 27) /* zoned rt device */ /* * Minimum and maximum sizes need for growth checks. @@ -257,6 +270,8 @@ typedef struct xfs_fsop_resblks { #define XFS_MAX_AG_BLOCKS (XFS_MAX_AG_BYTES / XFS_MIN_BLOCKSIZE) #define XFS_MAX_CRC_AG_BLOCKS (XFS_MAX_AG_BYTES / XFS_MIN_CRC_BLOCKSIZE) +#define XFS_MAX_AGNUMBER ((xfs_agnumber_t)(NULLAGNUMBER - 1)) + /* keep the maximum size under 2^31 by a small amount */ #define XFS_MAX_LOG_BYTES \ ((2 * 1024 * 1024 * 1024ULL) - XFS_MIN_LOG_BYTES) @@ -290,6 +305,7 @@ struct xfs_ag_geometry { #define XFS_AG_GEOM_SICK_FINOBT (1 << 7) /* free inode index */ #define XFS_AG_GEOM_SICK_RMAPBT (1 << 8) /* reverse mappings */ #define XFS_AG_GEOM_SICK_REFCNTBT (1 << 9) /* reference counts */ +#define XFS_AG_GEOM_SICK_INODES (1 << 10) /* bad inodes were seen */ /* * Structures for XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG & XFS_IOC_FSGROWFSRT @@ -404,6 +420,7 @@ struct xfs_bulkstat { #define XFS_BS_SICK_XATTR (1 << 5) /* extended attributes */ #define XFS_BS_SICK_SYMLINK (1 << 6) /* symbolic link remote target */ #define XFS_BS_SICK_PARENT (1 << 7) /* parent pointers */ +#define XFS_BS_SICK_DIRTREE (1 << 8) /* directory tree structure */ /* * Project quota id helpers (previously projid was 16bit only @@ -480,9 +497,17 @@ struct xfs_bulk_ireq { */ #define XFS_BULK_IREQ_NREXT64 (1U << 2) +/* + * Allow bulkstat to return information about metadata directories. This + * enables xfs_scrub to find them for scanning, as they are otherwise ordinary + * directories. + */ +#define XFS_BULK_IREQ_METADIR (1U << 3) + #define XFS_BULK_IREQ_FLAGS_ALL (XFS_BULK_IREQ_AGNO | \ XFS_BULK_IREQ_SPECIAL | \ - XFS_BULK_IREQ_NREXT64) + XFS_BULK_IREQ_NREXT64 | \ + XFS_BULK_IREQ_METADIR) /* Operate on the root directory inode. */ #define XFS_BULK_IREQ_SPECIAL_ROOT (1) @@ -590,12 +615,12 @@ typedef struct xfs_attrlist_cursor { struct xfs_attrlist { __s32 al_count; /* number of entries in attrlist */ __s32 al_more; /* T/F: more attrs (do call again) */ - __s32 al_offset[1]; /* byte offsets of attrs [var-sized] */ + __s32 al_offset[]; /* byte offsets of attrs [var-sized] */ }; struct xfs_attrlist_ent { /* data from attr_list() */ __u32 a_valuelen; /* number bytes in value of attr */ - char a_name[1]; /* attr name (NULL terminated) */ + char a_name[]; /* attr name (NULL terminated) */ }; typedef struct xfs_fsop_attrlist_handlereq { @@ -627,7 +652,9 @@ typedef struct xfs_fsop_attrmulti_handlereq { /* * per machine unique filesystem identifier types. */ -typedef struct { __u32 val[2]; } xfs_fsid_t; /* file system id type */ +typedef struct xfs_fsid { + __u32 val[2]; /* file system id type */ +} xfs_fsid_t; typedef struct xfs_fid { __u16 fid_len; /* length of remainder */ @@ -707,9 +734,26 @@ struct xfs_scrub_metadata { #define XFS_SCRUB_TYPE_GQUOTA 22 /* group quotas */ #define XFS_SCRUB_TYPE_PQUOTA 23 /* project quotas */ #define XFS_SCRUB_TYPE_FSCOUNTERS 24 /* fs summary counters */ +#define XFS_SCRUB_TYPE_QUOTACHECK 25 /* quota counters */ +#define XFS_SCRUB_TYPE_NLINKS 26 /* inode link counts */ +#define XFS_SCRUB_TYPE_HEALTHY 27 /* everything checked out ok */ +#define XFS_SCRUB_TYPE_DIRTREE 28 /* directory tree structure */ +#define XFS_SCRUB_TYPE_METAPATH 29 /* metadata directory tree paths */ +#define XFS_SCRUB_TYPE_RGSUPER 30 /* realtime superblock */ +#define XFS_SCRUB_TYPE_RTRMAPBT 31 /* rtgroup reverse mapping btree */ +#define XFS_SCRUB_TYPE_RTREFCBT 32 /* realtime reference count btree */ /* Number of scrub subcommands. */ -#define XFS_SCRUB_TYPE_NR 25 +#define XFS_SCRUB_TYPE_NR 33 + +/* + * This special type code only applies to the vectored scrub implementation. + * + * If any of the previous scrub vectors recorded runtime errors or have + * sv_flags bits set that match the OFLAG bits in the barrier vector's + * sv_flags, set the barrier's sv_ret to -ECANCELED and return to userspace. + */ +#define XFS_SCRUB_TYPE_BARRIER (0xFFFFFFFF) /* i: Repair this metadata. */ #define XFS_SCRUB_IFLAG_REPAIR (1u << 0) @@ -741,7 +785,11 @@ struct xfs_scrub_metadata { */ #define XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED (1u << 7) -#define XFS_SCRUB_FLAGS_IN (XFS_SCRUB_IFLAG_REPAIR) +/* i: Rebuild the data structure. */ +#define XFS_SCRUB_IFLAG_FORCE_REBUILD (1u << 8) + +#define XFS_SCRUB_FLAGS_IN (XFS_SCRUB_IFLAG_REPAIR | \ + XFS_SCRUB_IFLAG_FORCE_REBUILD) #define XFS_SCRUB_FLAGS_OUT (XFS_SCRUB_OFLAG_CORRUPT | \ XFS_SCRUB_OFLAG_PREEN | \ XFS_SCRUB_OFLAG_XFAIL | \ @@ -751,6 +799,47 @@ struct xfs_scrub_metadata { XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED) #define XFS_SCRUB_FLAGS_ALL (XFS_SCRUB_FLAGS_IN | XFS_SCRUB_FLAGS_OUT) +/* Vectored scrub calls to reduce the number of kernel transitions. */ + +struct xfs_scrub_vec { + __u32 sv_type; /* XFS_SCRUB_TYPE_* */ + __u32 sv_flags; /* XFS_SCRUB_FLAGS_* */ + __s32 sv_ret; /* 0 or a negative error code */ + __u32 sv_reserved; /* must be zero */ +}; + +/* Vectored metadata scrub control structure. */ +struct xfs_scrub_vec_head { + __u64 svh_ino; /* inode number. */ + __u32 svh_gen; /* inode generation. */ + __u32 svh_agno; /* ag number. */ + __u32 svh_flags; /* XFS_SCRUB_VEC_FLAGS_* */ + __u16 svh_rest_us; /* wait this much time between vector items */ + __u16 svh_nr; /* number of svh_vectors */ + __u64 svh_reserved; /* must be zero */ + __u64 svh_vectors; /* pointer to buffer of xfs_scrub_vec */ +}; + +#define XFS_SCRUB_VEC_FLAGS_ALL (0) + +/* + * i: sm_ino values for XFS_SCRUB_TYPE_METAPATH to select a metadata file for + * path checking. + */ +#define XFS_SCRUB_METAPATH_PROBE (0) /* do we have a metapath scrubber? */ +#define XFS_SCRUB_METAPATH_RTDIR (1) /* rtrgroups metadir */ +#define XFS_SCRUB_METAPATH_RTBITMAP (2) /* per-rtg bitmap */ +#define XFS_SCRUB_METAPATH_RTSUMMARY (3) /* per-rtg summary */ +#define XFS_SCRUB_METAPATH_QUOTADIR (4) /* quota metadir */ +#define XFS_SCRUB_METAPATH_USRQUOTA (5) /* user quota */ +#define XFS_SCRUB_METAPATH_GRPQUOTA (6) /* group quota */ +#define XFS_SCRUB_METAPATH_PRJQUOTA (7) /* project quota */ +#define XFS_SCRUB_METAPATH_RTRMAPBT (8) /* realtime reverse mapping */ +#define XFS_SCRUB_METAPATH_RTREFCOUNTBT (9) /* realtime refcount */ + +/* Number of metapath sm_ino values */ +#define XFS_SCRUB_METAPATH_NR (10) + /* * ioctl limits */ @@ -760,6 +849,159 @@ struct xfs_scrub_metadata { # define XFS_XATTR_LIST_MAX 65536 #endif +/* + * Exchange part of file1 with part of the file that this ioctl that is being + * called against (which we'll call file2). Filesystems must be able to + * restart and complete the operation even after the system goes down. + */ +struct xfs_exchange_range { + __s32 file1_fd; + __u32 pad; /* must be zeroes */ + __u64 file1_offset; /* file1 offset, bytes */ + __u64 file2_offset; /* file2 offset, bytes */ + __u64 length; /* bytes to exchange */ + + __u64 flags; /* see XFS_EXCHANGE_RANGE_* below */ +}; + +/* + * Using the same definition of file2 as struct xfs_exchange_range, commit the + * contents of file1 into file2 if file2 has the same inode number, mtime, and + * ctime as the arguments provided to the call. The old contents of file2 will + * be moved to file1. + * + * Returns -EBUSY if there isn't an exact match for the file2 fields. + * + * Filesystems must be able to restart and complete the operation even after + * the system goes down. + */ +struct xfs_commit_range { + __s32 file1_fd; + __u32 pad; /* must be zeroes */ + __u64 file1_offset; /* file1 offset, bytes */ + __u64 file2_offset; /* file2 offset, bytes */ + __u64 length; /* bytes to exchange */ + + __u64 flags; /* see XFS_EXCHANGE_RANGE_* below */ + + /* opaque file2 metadata for freshness checks */ + __u64 file2_freshness[6]; +}; + +/* + * Exchange file data all the way to the ends of both files, and then exchange + * the file sizes. This flag can be used to replace a file's contents with a + * different amount of data. length will be ignored. + */ +#define XFS_EXCHANGE_RANGE_TO_EOF (1ULL << 0) + +/* Flush all changes in file data and file metadata to disk before returning. */ +#define XFS_EXCHANGE_RANGE_DSYNC (1ULL << 1) + +/* Dry run; do all the parameter verification but do not change anything. */ +#define XFS_EXCHANGE_RANGE_DRY_RUN (1ULL << 2) + +/* + * Exchange only the parts of the two files where the file allocation units + * mapped to file1's range have been written to. This can accelerate + * scatter-gather atomic writes with a temp file if all writes are aligned to + * the file allocation unit. + */ +#define XFS_EXCHANGE_RANGE_FILE1_WRITTEN (1ULL << 3) + +#define XFS_EXCHANGE_RANGE_ALL_FLAGS (XFS_EXCHANGE_RANGE_TO_EOF | \ + XFS_EXCHANGE_RANGE_DSYNC | \ + XFS_EXCHANGE_RANGE_DRY_RUN | \ + XFS_EXCHANGE_RANGE_FILE1_WRITTEN) + +/* Iterating parent pointers of files. */ + +/* target was the root directory */ +#define XFS_GETPARENTS_OFLAG_ROOT (1U << 0) + +/* Cursor is done iterating pptrs */ +#define XFS_GETPARENTS_OFLAG_DONE (1U << 1) + +#define XFS_GETPARENTS_OFLAGS_ALL (XFS_GETPARENTS_OFLAG_ROOT | \ + XFS_GETPARENTS_OFLAG_DONE) + +#define XFS_GETPARENTS_IFLAGS_ALL (0) + +struct xfs_getparents_rec { + struct xfs_handle gpr_parent; /* Handle to parent */ + __u32 gpr_reclen; /* Length of entire record */ + __u32 gpr_reserved; /* zero */ + char gpr_name[]; /* Null-terminated filename */ +}; + +/* Iterate through this file's directory parent pointers */ +struct xfs_getparents { + /* + * Structure to track progress in iterating the parent pointers. + * Must be initialized to zeroes before the first ioctl call, and + * not touched by callers after that. + */ + struct xfs_attrlist_cursor gp_cursor; + + /* Input flags: XFS_GETPARENTS_IFLAG* */ + __u16 gp_iflags; + + /* Output flags: XFS_GETPARENTS_OFLAG* */ + __u16 gp_oflags; + + /* Size of the gp_buffer in bytes */ + __u32 gp_bufsize; + + /* Must be set to zero */ + __u64 gp_reserved; + + /* Pointer to a buffer in which to place xfs_getparents_rec */ + __u64 gp_buffer; +}; + +static inline struct xfs_getparents_rec * +xfs_getparents_first_rec(struct xfs_getparents *gp) +{ + return (struct xfs_getparents_rec *)(uintptr_t)gp->gp_buffer; +} + +static inline struct xfs_getparents_rec * +xfs_getparents_next_rec(struct xfs_getparents *gp, + struct xfs_getparents_rec *gpr) +{ + void *next = ((char *)gpr + gpr->gpr_reclen); + void *end = (void *)(uintptr_t)(gp->gp_buffer + gp->gp_bufsize); + + if (next >= end) + return NULL; + + return (struct xfs_getparents_rec *)next; +} + +/* Iterate through this file handle's directory parent pointers. */ +struct xfs_getparents_by_handle { + /* Handle to file whose parents we want. */ + struct xfs_handle gph_handle; + + struct xfs_getparents gph_request; +}; + +/* + * Output for XFS_IOC_RTGROUP_GEOMETRY + */ +struct xfs_rtgroup_geometry { + __u32 rg_number; /* i/o: rtgroup number */ + __u32 rg_length; /* o: length in blocks */ + __u32 rg_sick; /* o: sick things in ag */ + __u32 rg_checked; /* o: checked metadata in ag */ + __u32 rg_flags; /* i/o: flags for this ag */ + __u32 rg_reserved[27]; /* o: zero */ +}; +#define XFS_RTGROUP_GEOM_SICK_SUPER (1U << 0) /* superblock */ +#define XFS_RTGROUP_GEOM_SICK_BITMAP (1U << 1) /* rtbitmap */ +#define XFS_RTGROUP_GEOM_SICK_SUMMARY (1U << 2) /* rtsummary */ +#define XFS_RTGROUP_GEOM_SICK_RMAPBT (1U << 3) /* reverse mappings */ +#define XFS_RTGROUP_GEOM_SICK_REFCNTBT (1U << 4) /* reference counts */ /* * ioctl commands that are used by Linux filesystems @@ -796,6 +1038,10 @@ struct xfs_scrub_metadata { /* XFS_IOC_GETFSMAP ------ hoisted 59 */ #define XFS_IOC_SCRUB_METADATA _IOWR('X', 60, struct xfs_scrub_metadata) #define XFS_IOC_AG_GEOMETRY _IOWR('X', 61, struct xfs_ag_geometry) +#define XFS_IOC_GETPARENTS _IOWR('X', 62, struct xfs_getparents) +#define XFS_IOC_GETPARENTS_BY_HANDLE _IOWR('X', 63, struct xfs_getparents_by_handle) +#define XFS_IOC_SCRUBV_METADATA _IOWR('X', 64, struct xfs_scrub_vec_head) +#define XFS_IOC_RTGROUP_GEOMETRY _IOWR('X', 65, struct xfs_rtgroup_geometry) /* * ioctl commands that replace IRIX syssgi()'s @@ -831,8 +1077,20 @@ struct xfs_scrub_metadata { #define XFS_IOC_FSGEOMETRY _IOR ('X', 126, struct xfs_fsop_geom) #define XFS_IOC_BULKSTAT _IOR ('X', 127, struct xfs_bulkstat_req) #define XFS_IOC_INUMBERS _IOR ('X', 128, struct xfs_inumbers_req) +#define XFS_IOC_EXCHANGE_RANGE _IOW ('X', 129, struct xfs_exchange_range) +#define XFS_IOC_START_COMMIT _IOR ('X', 130, struct xfs_commit_range) +#define XFS_IOC_COMMIT_RANGE _IOW ('X', 131, struct xfs_commit_range) /* XFS_IOC_GETFSUUID ---------- deprecated 140 */ +/* + * Devices supported by a single XFS file system. Reported in fsmaps fmr_device + * when using internal RT devices. + */ +enum xfs_device { + XFS_DEV_DATA = 1, + XFS_DEV_LOG = 2, + XFS_DEV_RT = 3, +}; #ifndef HAVE_BBMACROS /* diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c new file mode 100644 index 000000000000..792f76d2e2a0 --- /dev/null +++ b/fs/xfs/libxfs/xfs_group.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 Red Hat, Inc. + */ + +#include "xfs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_error.h" +#include "xfs_trace.h" +#include "xfs_extent_busy.h" +#include "xfs_group.h" + +/* + * Groups can have passive and active references. + * + * For passive references the code freeing a group is responsible for cleaning + * up objects that hold the passive references (e.g. cached buffers). + * Routines manipulating passive references are xfs_group_get, xfs_group_hold + * and xfs_group_put. + * + * Active references are for short term access to the group for walking trees or + * accessing state. If a group is being shrunk or offlined, the lookup will fail + * to find that group and return NULL instead. + * Routines manipulating active references are xfs_group_grab and + * xfs_group_rele. + */ + +struct xfs_group * +xfs_group_get( + struct xfs_mount *mp, + uint32_t index, + enum xfs_group_type type) +{ + struct xfs_group *xg; + + rcu_read_lock(); + xg = xa_load(&mp->m_groups[type].xa, index); + if (xg) { + trace_xfs_group_get(xg, _RET_IP_); + ASSERT(atomic_read(&xg->xg_ref) >= 0); + atomic_inc(&xg->xg_ref); + } + rcu_read_unlock(); + return xg; +} + +struct xfs_group * +xfs_group_hold( + struct xfs_group *xg) +{ + ASSERT(atomic_read(&xg->xg_ref) > 0 || + atomic_read(&xg->xg_active_ref) > 0); + + trace_xfs_group_hold(xg, _RET_IP_); + atomic_inc(&xg->xg_ref); + return xg; +} + +void +xfs_group_put( + struct xfs_group *xg) +{ + trace_xfs_group_put(xg, _RET_IP_); + + ASSERT(atomic_read(&xg->xg_ref) > 0); + atomic_dec(&xg->xg_ref); +} + +struct xfs_group * +xfs_group_grab( + struct xfs_mount *mp, + uint32_t index, + enum xfs_group_type type) +{ + struct xfs_group *xg; + + rcu_read_lock(); + xg = xa_load(&mp->m_groups[type].xa, index); + if (xg) { + trace_xfs_group_grab(xg, _RET_IP_); + if (!atomic_inc_not_zero(&xg->xg_active_ref)) + xg = NULL; + } + rcu_read_unlock(); + return xg; +} + +/* + * Iterate to the next group. To start the iteration at @start_index, a %NULL + * @xg is passed, else the previous group returned from this function. The + * caller should break out of the loop when this returns %NULL. If the caller + * wants to break out of a loop that did not finish it needs to release the + * active reference to @xg using xfs_group_rele() itself. + */ +struct xfs_group * +xfs_group_next_range( + struct xfs_mount *mp, + struct xfs_group *xg, + uint32_t start_index, + uint32_t end_index, + enum xfs_group_type type) +{ + uint32_t index = start_index; + + if (xg) { + index = xg->xg_gno + 1; + xfs_group_rele(xg); + } + if (index > end_index) + return NULL; + return xfs_group_grab(mp, index, type); +} + +/* + * Find the next group after @xg, or the first group if @xg is NULL. + */ +struct xfs_group * +xfs_group_grab_next_mark( + struct xfs_mount *mp, + struct xfs_group *xg, + xa_mark_t mark, + enum xfs_group_type type) +{ + unsigned long index = 0; + + if (xg) { + index = xg->xg_gno + 1; + xfs_group_rele(xg); + } + + rcu_read_lock(); + xg = xa_find(&mp->m_groups[type].xa, &index, ULONG_MAX, mark); + if (xg) { + trace_xfs_group_grab_next_tag(xg, _RET_IP_); + if (!atomic_inc_not_zero(&xg->xg_active_ref)) + xg = NULL; + } + rcu_read_unlock(); + return xg; +} + +void +xfs_group_rele( + struct xfs_group *xg) +{ + trace_xfs_group_rele(xg, _RET_IP_); + atomic_dec(&xg->xg_active_ref); +} + +void +xfs_group_free( + struct xfs_mount *mp, + uint32_t index, + enum xfs_group_type type, + void (*uninit)(struct xfs_group *xg)) +{ + struct xfs_group *xg = xa_erase(&mp->m_groups[type].xa, index); + + XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_ref) != 0); + + xfs_defer_drain_free(&xg->xg_intents_drain); +#ifdef __KERNEL__ + if (xfs_group_has_extent_busy(xg->xg_mount, xg->xg_type)) + kfree(xg->xg_busy_extents); +#endif + + if (uninit) + uninit(xg); + + /* drop the mount's active reference */ + xfs_group_rele(xg); + XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_active_ref) > 0); + XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_active_ref) < 0); + kfree_rcu_mightsleep(xg); +} + +int +xfs_group_insert( + struct xfs_mount *mp, + struct xfs_group *xg, + uint32_t index, + enum xfs_group_type type) +{ + int error; + + xg->xg_mount = mp; + xg->xg_gno = index; + xg->xg_type = type; + +#ifdef __KERNEL__ + if (xfs_group_has_extent_busy(mp, type)) { + xg->xg_busy_extents = xfs_extent_busy_alloc(); + if (!xg->xg_busy_extents) + return -ENOMEM; + } + spin_lock_init(&xg->xg_state_lock); + xfs_hooks_init(&xg->xg_rmap_update_hooks); +#endif + xfs_defer_drain_init(&xg->xg_intents_drain); + + /* Active ref owned by mount indicates group is online. */ + atomic_set(&xg->xg_active_ref, 1); + + error = xa_insert(&mp->m_groups[type].xa, index, xg, GFP_KERNEL); + if (error) { + WARN_ON_ONCE(error == -EBUSY); + goto out_drain; + } + + return 0; +out_drain: + xfs_defer_drain_free(&xg->xg_intents_drain); +#ifdef __KERNEL__ + if (xfs_group_has_extent_busy(xg->xg_mount, xg->xg_type)) + kfree(xg->xg_busy_extents); +#endif + return error; +} + +struct xfs_group * +xfs_group_get_by_fsb( + struct xfs_mount *mp, + xfs_fsblock_t fsbno, + enum xfs_group_type type) +{ + return xfs_group_get(mp, xfs_fsb_to_gno(mp, fsbno, type), type); +} diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h new file mode 100644 index 000000000000..4ae638f1c2c5 --- /dev/null +++ b/fs/xfs/libxfs/xfs_group.h @@ -0,0 +1,192 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018 Red Hat, Inc. + */ +#ifndef __LIBXFS_GROUP_H +#define __LIBXFS_GROUP_H 1 + +struct xfs_group { + struct xfs_mount *xg_mount; + uint32_t xg_gno; + enum xfs_group_type xg_type; + atomic_t xg_ref; /* passive reference count */ + atomic_t xg_active_ref; /* active reference count */ + + /* Precalculated geometry info */ + uint32_t xg_block_count; /* max usable gbno */ + uint32_t xg_min_gbno; /* min usable gbno */ + +#ifdef __KERNEL__ + /* -- kernel only structures below this line -- */ + + union { + /* + * For perags and non-zoned RT groups: + * Track freed but not yet committed extents. + */ + struct xfs_extent_busy_tree *xg_busy_extents; + + /* + * For zoned RT groups: + * List of groups that need a zone reset. + * + * The zonegc code forces a log flush of the rtrmap inode before + * resetting the write pointer, so there is no need for + * individual busy extent tracking. + */ + struct xfs_group *xg_next_reset; + }; + + /* + * Bitsets of per-ag metadata that have been checked and/or are sick. + * Callers should hold xg_state_lock before accessing this field. + */ + uint16_t xg_checked; + uint16_t xg_sick; + spinlock_t xg_state_lock; + + /* + * We use xfs_drain to track the number of deferred log intent items + * that have been queued (but not yet processed) so that waiters (e.g. + * scrub) will not lock resources when other threads are in the middle + * of processing a chain of intent items only to find momentary + * inconsistencies. + */ + struct xfs_defer_drain xg_intents_drain; + + /* + * Hook to feed rmapbt updates to an active online repair. + */ + struct xfs_hooks xg_rmap_update_hooks; +#endif /* __KERNEL__ */ +}; + +struct xfs_group *xfs_group_get(struct xfs_mount *mp, uint32_t index, + enum xfs_group_type type); +struct xfs_group *xfs_group_get_by_fsb(struct xfs_mount *mp, + xfs_fsblock_t fsbno, enum xfs_group_type type); +struct xfs_group *xfs_group_hold(struct xfs_group *xg); +void xfs_group_put(struct xfs_group *xg); + +struct xfs_group *xfs_group_grab(struct xfs_mount *mp, uint32_t index, + enum xfs_group_type type); +struct xfs_group *xfs_group_next_range(struct xfs_mount *mp, + struct xfs_group *xg, uint32_t start_index, uint32_t end_index, + enum xfs_group_type type); +struct xfs_group *xfs_group_grab_next_mark(struct xfs_mount *mp, + struct xfs_group *xg, xa_mark_t mark, enum xfs_group_type type); +void xfs_group_rele(struct xfs_group *xg); + +void xfs_group_free(struct xfs_mount *mp, uint32_t index, + enum xfs_group_type type, void (*uninit)(struct xfs_group *xg)); +int xfs_group_insert(struct xfs_mount *mp, struct xfs_group *xg, + uint32_t index, enum xfs_group_type); + +#define xfs_group_set_mark(_xg, _mark) \ + xa_set_mark(&(_xg)->xg_mount->m_groups[(_xg)->xg_type].xa, \ + (_xg)->xg_gno, (_mark)) +#define xfs_group_clear_mark(_xg, _mark) \ + xa_clear_mark(&(_xg)->xg_mount->m_groups[(_xg)->xg_type].xa, \ + (_xg)->xg_gno, (_mark)) +#define xfs_group_marked(_mp, _type, _mark) \ + xa_marked(&(_mp)->m_groups[(_type)].xa, (_mark)) + +static inline xfs_agblock_t +xfs_group_max_blocks( + struct xfs_group *xg) +{ + return xg->xg_mount->m_groups[xg->xg_type].blocks; +} + +static inline xfs_rfsblock_t +xfs_groups_to_rfsbs( + struct xfs_mount *mp, + uint32_t nr_groups, + enum xfs_group_type type) +{ + return (xfs_rfsblock_t)mp->m_groups[type].blocks * nr_groups; +} + +static inline xfs_fsblock_t +xfs_group_start_fsb( + struct xfs_group *xg) +{ + return ((xfs_fsblock_t)xg->xg_gno) << + xg->xg_mount->m_groups[xg->xg_type].blklog; +} + +static inline xfs_fsblock_t +xfs_gbno_to_fsb( + struct xfs_group *xg, + xfs_agblock_t gbno) +{ + return xfs_group_start_fsb(xg) | gbno; +} + +static inline xfs_daddr_t +xfs_gbno_to_daddr( + struct xfs_group *xg, + xfs_agblock_t gbno) +{ + struct xfs_mount *mp = xg->xg_mount; + struct xfs_groups *g = &mp->m_groups[xg->xg_type]; + xfs_fsblock_t fsbno; + + if (g->has_daddr_gaps) + fsbno = xfs_gbno_to_fsb(xg, gbno); + else + fsbno = (xfs_fsblock_t)xg->xg_gno * g->blocks + gbno; + + return XFS_FSB_TO_BB(mp, g->start_fsb + fsbno); +} + +static inline uint32_t +xfs_fsb_to_gno( + struct xfs_mount *mp, + xfs_fsblock_t fsbno, + enum xfs_group_type type) +{ + if (!mp->m_groups[type].blklog) + return 0; + return fsbno >> mp->m_groups[type].blklog; +} + +static inline xfs_agblock_t +xfs_fsb_to_gbno( + struct xfs_mount *mp, + xfs_fsblock_t fsbno, + enum xfs_group_type type) +{ + return fsbno & mp->m_groups[type].blkmask; +} + +static inline bool +xfs_verify_gbno( + struct xfs_group *xg, + uint32_t gbno) +{ + if (gbno >= xg->xg_block_count) + return false; + if (gbno < xg->xg_min_gbno) + return false; + return true; +} + +static inline bool +xfs_verify_gbext( + struct xfs_group *xg, + uint32_t gbno, + uint32_t glen) +{ + uint32_t end; + + if (!xfs_verify_gbno(xg, gbno)) + return false; + if (glen == 0 || check_add_overflow(gbno, glen - 1, &end)) + return false; + if (!xfs_verify_gbno(xg, end)) + return false; + return true; +} + +#endif /* __LIBXFS_GROUP_H */ diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h index 99e796256c5d..b31000f7190c 100644 --- a/fs/xfs/libxfs/xfs_health.h +++ b/fs/xfs/libxfs/xfs_health.h @@ -6,6 +6,8 @@ #ifndef __XFS_HEALTH_H__ #define __XFS_HEALTH_H__ +struct xfs_group; + /* * In-Core Filesystem Health Assessments * ===================================== @@ -26,25 +28,50 @@ * and the "sick" field tells us if that piece was found to need repairs. * Therefore we can conclude that for a given sick flag value: * - * - checked && sick => metadata needs repair - * - checked && !sick => metadata is ok - * - !checked => has not been examined since mount + * - checked && sick => metadata needs repair + * - checked && !sick => metadata is ok + * - !checked && sick => errors have been observed during normal operation, + * but the metadata has not been checked thoroughly + * - !checked && !sick => has not been examined since mount + * + * Evidence of health problems can be sorted into three basic categories: + * + * a) Primary evidence, which signals that something is defective within the + * general grouping of metadata. + * + * b) Secondary evidence, which are side effects of primary problem but are + * not themselves problems. These can be forgotten when the primary + * health problems are addressed. + * + * c) Indirect evidence, which points to something being wrong in another + * group, but we had to release resources and this is all that's left of + * that state. */ struct xfs_mount; struct xfs_perag; struct xfs_inode; struct xfs_fsop_geom; +struct xfs_btree_cur; +struct xfs_da_args; +struct xfs_rtgroup; /* Observable health issues for metadata spanning the entire filesystem. */ #define XFS_SICK_FS_COUNTERS (1 << 0) /* summary counters */ #define XFS_SICK_FS_UQUOTA (1 << 1) /* user quota */ #define XFS_SICK_FS_GQUOTA (1 << 2) /* group quota */ #define XFS_SICK_FS_PQUOTA (1 << 3) /* project quota */ +#define XFS_SICK_FS_QUOTACHECK (1 << 4) /* quota counts */ +#define XFS_SICK_FS_NLINKS (1 << 5) /* inode link counts */ +#define XFS_SICK_FS_METADIR (1 << 6) /* metadata directory tree */ +#define XFS_SICK_FS_METAPATH (1 << 7) /* metadata directory tree path */ -/* Observable health issues for realtime volume metadata. */ -#define XFS_SICK_RT_BITMAP (1 << 0) /* realtime bitmap */ -#define XFS_SICK_RT_SUMMARY (1 << 1) /* realtime summary */ +/* Observable health issues for realtime group metadata. */ +#define XFS_SICK_RG_SUPER (1 << 0) /* rt group superblock */ +#define XFS_SICK_RG_BITMAP (1 << 1) /* rt group bitmap */ +#define XFS_SICK_RG_SUMMARY (1 << 2) /* rt groups summary */ +#define XFS_SICK_RG_RMAPBT (1 << 3) /* reverse mappings */ +#define XFS_SICK_RG_REFCNTBT (1 << 4) /* reference counts */ /* Observable health issues for AG metadata. */ #define XFS_SICK_AG_SB (1 << 0) /* superblock */ @@ -57,6 +84,7 @@ struct xfs_fsop_geom; #define XFS_SICK_AG_FINOBT (1 << 7) /* free inode index */ #define XFS_SICK_AG_RMAPBT (1 << 8) /* reverse mappings */ #define XFS_SICK_AG_REFCNTBT (1 << 9) /* reference counts */ +#define XFS_SICK_AG_INODES (1 << 10) /* inactivated bad inodes */ /* Observable health issues for inode metadata. */ #define XFS_SICK_INO_CORE (1 << 0) /* inode core */ @@ -68,14 +96,30 @@ struct xfs_fsop_geom; #define XFS_SICK_INO_SYMLINK (1 << 6) /* symbolic link remote target */ #define XFS_SICK_INO_PARENT (1 << 7) /* parent pointers */ +#define XFS_SICK_INO_BMBTD_ZAPPED (1 << 8) /* data fork erased */ +#define XFS_SICK_INO_BMBTA_ZAPPED (1 << 9) /* attr fork erased */ +#define XFS_SICK_INO_DIR_ZAPPED (1 << 10) /* directory erased */ +#define XFS_SICK_INO_SYMLINK_ZAPPED (1 << 11) /* symlink erased */ + +/* Don't propagate sick status to ag health summary during inactivation */ +#define XFS_SICK_INO_FORGET (1 << 12) +#define XFS_SICK_INO_DIRTREE (1 << 13) /* directory tree structure */ + /* Primary evidence of health problems in a given group. */ #define XFS_SICK_FS_PRIMARY (XFS_SICK_FS_COUNTERS | \ XFS_SICK_FS_UQUOTA | \ XFS_SICK_FS_GQUOTA | \ - XFS_SICK_FS_PQUOTA) + XFS_SICK_FS_PQUOTA | \ + XFS_SICK_FS_QUOTACHECK | \ + XFS_SICK_FS_NLINKS | \ + XFS_SICK_FS_METADIR | \ + XFS_SICK_FS_METAPATH) -#define XFS_SICK_RT_PRIMARY (XFS_SICK_RT_BITMAP | \ - XFS_SICK_RT_SUMMARY) +#define XFS_SICK_RG_PRIMARY (XFS_SICK_RG_SUPER | \ + XFS_SICK_RG_BITMAP | \ + XFS_SICK_RG_SUMMARY | \ + XFS_SICK_RG_RMAPBT | \ + XFS_SICK_RG_REFCNTBT) #define XFS_SICK_AG_PRIMARY (XFS_SICK_AG_SB | \ XFS_SICK_AG_AGF | \ @@ -95,31 +139,93 @@ struct xfs_fsop_geom; XFS_SICK_INO_DIR | \ XFS_SICK_INO_XATTR | \ XFS_SICK_INO_SYMLINK | \ - XFS_SICK_INO_PARENT) + XFS_SICK_INO_PARENT | \ + XFS_SICK_INO_DIRTREE) + +#define XFS_SICK_INO_ZAPPED (XFS_SICK_INO_BMBTD_ZAPPED | \ + XFS_SICK_INO_BMBTA_ZAPPED | \ + XFS_SICK_INO_DIR_ZAPPED | \ + XFS_SICK_INO_SYMLINK_ZAPPED) + +/* Secondary state related to (but not primary evidence of) health problems. */ +#define XFS_SICK_FS_SECONDARY (0) +#define XFS_SICK_RG_SECONDARY (0) +#define XFS_SICK_AG_SECONDARY (0) +#define XFS_SICK_INO_SECONDARY (XFS_SICK_INO_FORGET) -/* These functions must be provided by the xfs implementation. */ +/* Evidence of health problems elsewhere. */ +#define XFS_SICK_FS_INDIRECT (0) +#define XFS_SICK_RG_INDIRECT (0) +#define XFS_SICK_AG_INDIRECT (XFS_SICK_AG_INODES) +#define XFS_SICK_INO_INDIRECT (0) + +/* All health masks. */ +#define XFS_SICK_FS_ALL (XFS_SICK_FS_PRIMARY | \ + XFS_SICK_FS_SECONDARY | \ + XFS_SICK_FS_INDIRECT) + +#define XFS_SICK_RG_ALL (XFS_SICK_RG_PRIMARY | \ + XFS_SICK_RG_SECONDARY | \ + XFS_SICK_RG_INDIRECT) + +#define XFS_SICK_AG_ALL (XFS_SICK_AG_PRIMARY | \ + XFS_SICK_AG_SECONDARY | \ + XFS_SICK_AG_INDIRECT) + +#define XFS_SICK_INO_ALL (XFS_SICK_INO_PRIMARY | \ + XFS_SICK_INO_SECONDARY | \ + XFS_SICK_INO_INDIRECT | \ + XFS_SICK_INO_ZAPPED) + +/* + * These functions must be provided by the xfs implementation. Function + * behavior with respect to the first argument should be as follows: + * + * xfs_*_mark_sick: Set the sick flags and do not set checked flags. + * Runtime code should call this upon encountering + * a corruption. + * + * xfs_*_mark_corrupt: Set the sick and checked flags simultaneously. + * Fsck tools should call this when corruption is + * found. + * + * xfs_*_mark_healthy: Clear the sick flags and set the checked flags. + * Fsck tools should call this after correcting errors. + * + * xfs_*_measure_sickness: Return the sick and check status in the provided + * out parameters. + */ void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask); +void xfs_fs_mark_corrupt(struct xfs_mount *mp, unsigned int mask); void xfs_fs_mark_healthy(struct xfs_mount *mp, unsigned int mask); void xfs_fs_measure_sickness(struct xfs_mount *mp, unsigned int *sick, unsigned int *checked); -void xfs_rt_mark_sick(struct xfs_mount *mp, unsigned int mask); -void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask); -void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick, - unsigned int *checked); +void xfs_rgno_mark_sick(struct xfs_mount *mp, xfs_rgnumber_t rgno, + unsigned int mask); -void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask); -void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask); -void xfs_ag_measure_sickness(struct xfs_perag *pag, unsigned int *sick, +void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno, + unsigned int mask); +void xfs_group_mark_sick(struct xfs_group *xg, unsigned int mask); +#define xfs_ag_mark_sick(pag, mask) \ + xfs_group_mark_sick(pag_group(pag), (mask)) +void xfs_group_mark_corrupt(struct xfs_group *xg, unsigned int mask); +void xfs_group_mark_healthy(struct xfs_group *xg, unsigned int mask); +void xfs_group_measure_sickness(struct xfs_group *xg, unsigned int *sick, unsigned int *checked); void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask); +void xfs_inode_mark_corrupt(struct xfs_inode *ip, unsigned int mask); void xfs_inode_mark_healthy(struct xfs_inode *ip, unsigned int mask); void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick, unsigned int *checked); void xfs_health_unmount(struct xfs_mount *mp); +void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork); +void xfs_btree_mark_sick(struct xfs_btree_cur *cur); +void xfs_dirattr_mark_sick(struct xfs_inode *ip, int whichfork); +void xfs_da_mark_sick(struct xfs_da_args *args); /* Now some helpers. */ @@ -133,22 +239,25 @@ xfs_fs_has_sickness(struct xfs_mount *mp, unsigned int mask) } static inline bool -xfs_rt_has_sickness(struct xfs_mount *mp, unsigned int mask) +xfs_group_has_sickness( + struct xfs_group *xg, + unsigned int mask) { - unsigned int sick, checked; + unsigned int sick, checked; - xfs_rt_measure_sickness(mp, &sick, &checked); + xfs_group_measure_sickness(xg, &sick, &checked); return sick & mask; } -static inline bool -xfs_ag_has_sickness(struct xfs_perag *pag, unsigned int mask) -{ - unsigned int sick, checked; +#define xfs_ag_has_sickness(pag, mask) \ + xfs_group_has_sickness(pag_group(pag), (mask)) +#define xfs_ag_is_healthy(pag) \ + (!xfs_ag_has_sickness((pag), UINT_MAX)) - xfs_ag_measure_sickness(pag, &sick, &checked); - return sick & mask; -} +#define xfs_rtgroup_has_sickness(rtg, mask) \ + xfs_group_has_sickness(rtg_group(rtg), (mask)) +#define xfs_rtgroup_is_healthy(rtg) \ + (!xfs_rtgroup_has_sickness((rtg), UINT_MAX)) static inline bool xfs_inode_has_sickness(struct xfs_inode *ip, unsigned int mask) @@ -166,18 +275,6 @@ xfs_fs_is_healthy(struct xfs_mount *mp) } static inline bool -xfs_rt_is_healthy(struct xfs_mount *mp) -{ - return !xfs_rt_has_sickness(mp, -1U); -} - -static inline bool -xfs_ag_is_healthy(struct xfs_perag *pag) -{ - return !xfs_ag_has_sickness(pag, -1U); -} - -static inline bool xfs_inode_is_healthy(struct xfs_inode *ip) { return !xfs_inode_has_sickness(ip, -1U); @@ -185,6 +282,11 @@ xfs_inode_is_healthy(struct xfs_inode *ip) void xfs_fsop_geom_health(struct xfs_mount *mp, struct xfs_fsop_geom *geo); void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo); +void xfs_rtgroup_geom_health(struct xfs_rtgroup *rtg, + struct xfs_rtgroup_geometry *rgeo); void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bulkstat *bs); +#define xfs_metadata_is_sick(error) \ + (unlikely((error) == -EFSCORRUPTED || (error) == -EFSBADCRC)) + #endif /* __XFS_HEALTH_H__ */ diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 5118dedf9267..d97295eaebe6 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -27,6 +27,7 @@ #include "xfs_log.h" #include "xfs_rmap.h" #include "xfs_ag.h" +#include "xfs_health.h" /* * Lookup a record by ino in the btree given by cur. @@ -95,6 +96,61 @@ xfs_inobt_btrec_to_irec( irec->ir_free = be64_to_cpu(rec->inobt.ir_free); } +/* Compute the freecount of an incore inode record. */ +uint8_t +xfs_inobt_rec_freecount( + const struct xfs_inobt_rec_incore *irec) +{ + uint64_t realfree = irec->ir_free; + + if (xfs_inobt_issparse(irec->ir_holemask)) + realfree &= xfs_inobt_irec_to_allocmask(irec); + return hweight64(realfree); +} + +/* Simple checks for inode records. */ +xfs_failaddr_t +xfs_inobt_check_irec( + struct xfs_perag *pag, + const struct xfs_inobt_rec_incore *irec) +{ + /* Record has to be properly aligned within the AG. */ + if (!xfs_verify_agino(pag, irec->ir_startino)) + return __this_address; + if (!xfs_verify_agino(pag, + irec->ir_startino + XFS_INODES_PER_CHUNK - 1)) + return __this_address; + if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT || + irec->ir_count > XFS_INODES_PER_CHUNK) + return __this_address; + if (irec->ir_freecount > XFS_INODES_PER_CHUNK) + return __this_address; + + if (xfs_inobt_rec_freecount(irec) != irec->ir_freecount) + return __this_address; + + return NULL; +} + +static inline int +xfs_inobt_complain_bad_rec( + struct xfs_btree_cur *cur, + xfs_failaddr_t fa, + const struct xfs_inobt_rec_incore *irec) +{ + struct xfs_mount *mp = cur->bc_mp; + + xfs_warn(mp, + "%sbt record corruption in AG %d detected at %pS!", + cur->bc_ops->name, cur->bc_group->xg_gno, fa); + xfs_warn(mp, +"start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x", + irec->ir_startino, irec->ir_count, irec->ir_freecount, + irec->ir_free, irec->ir_holemask); + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; +} + /* * Get the data from the pointed-to record. */ @@ -106,43 +162,19 @@ xfs_inobt_get_rec( { struct xfs_mount *mp = cur->bc_mp; union xfs_btree_rec *rec; + xfs_failaddr_t fa; int error; - uint64_t realfree; error = xfs_btree_get_rec(cur, &rec, stat); if (error || *stat == 0) return error; xfs_inobt_btrec_to_irec(mp, rec, irec); - - if (!xfs_verify_agino(cur->bc_ag.pag, irec->ir_startino)) - goto out_bad_rec; - if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT || - irec->ir_count > XFS_INODES_PER_CHUNK) - goto out_bad_rec; - if (irec->ir_freecount > XFS_INODES_PER_CHUNK) - goto out_bad_rec; - - /* if there are no holes, return the first available offset */ - if (!xfs_inobt_issparse(irec->ir_holemask)) - realfree = irec->ir_free; - else - realfree = irec->ir_free & xfs_inobt_irec_to_allocmask(irec); - if (hweight64(realfree) != irec->ir_freecount) - goto out_bad_rec; + fa = xfs_inobt_check_irec(to_perag(cur->bc_group), irec); + if (fa) + return xfs_inobt_complain_bad_rec(cur, fa, irec); return 0; - -out_bad_rec: - xfs_warn(mp, - "%s Inode BTree record corruption in AG %d detected!", - cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free", - cur->bc_ag.pag->pag_agno); - xfs_warn(mp, -"start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x", - irec->ir_startino, irec->ir_count, irec->ir_freecount, - irec->ir_free, irec->ir_holemask); - return -EFSCORRUPTED; } /* @@ -169,20 +201,22 @@ xfs_inobt_insert_rec( */ STATIC int xfs_inobt_insert( - struct xfs_mount *mp, + struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, - struct xfs_perag *pag, xfs_agino_t newino, xfs_agino_t newlen, - xfs_btnum_t btnum) + bool is_finobt) { struct xfs_btree_cur *cur; xfs_agino_t thisino; int i; int error; - cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, btnum); + if (is_finobt) + cur = xfs_finobt_init_cursor(pag, tp, agbp); + else + cur = xfs_inobt_init_cursor(pag, tp, agbp); for (thisino = newino; thisino < newino + newlen; @@ -241,8 +275,10 @@ xfs_check_agi_freecount( } } while (i == 1); - if (!xfs_is_shutdown(cur->bc_mp)) - ASSERT(freecount == cur->bc_ag.pag->pagi_freecount); + if (!xfs_is_shutdown(cur->bc_mp)) { + ASSERT(freecount == + to_perag(cur->bc_group)->pagi_freecount); + } } return 0; } @@ -328,7 +364,7 @@ xfs_ialloc_inode_init( (j * M_IGEO(mp)->blocks_per_cluster)); error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize * M_IGEO(mp)->blocks_per_cluster, - XBF_UNMAPPED, &fbuf); + 0, &fbuf); if (error) return error; @@ -498,36 +534,32 @@ __xfs_inobt_rec_merge( } /* - * Insert a new sparse inode chunk into the associated inode btree. The inode - * record for the sparse chunk is pre-aligned to a startino that should match - * any pre-existing sparse inode record in the tree. This allows sparse chunks - * to fill over time. + * Insert a new sparse inode chunk into the associated inode allocation btree. + * The inode record for the sparse chunk is pre-aligned to a startino that + * should match any pre-existing sparse inode record in the tree. This allows + * sparse chunks to fill over time. * - * This function supports two modes of handling preexisting records depending on - * the merge flag. If merge is true, the provided record is merged with the + * If no preexisting record exists, the provided record is inserted. + * If there is a preexisting record, the provided record is merged with the * existing record and updated in place. The merged record is returned in nrec. - * If merge is false, an existing record is replaced with the provided record. - * If no preexisting record exists, the provided record is always inserted. * * It is considered corruption if a merge is requested and not possible. Given * the sparse inode alignment constraints, this should never happen. */ STATIC int xfs_inobt_insert_sprec( - struct xfs_mount *mp, + struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, - struct xfs_perag *pag, - int btnum, - struct xfs_inobt_rec_incore *nrec, /* in/out: new/merged rec. */ - bool merge) /* merge or replace */ + struct xfs_inobt_rec_incore *nrec) /* in/out: new/merged rec. */ { + struct xfs_mount *mp = pag_mount(pag); struct xfs_btree_cur *cur; int error; int i; struct xfs_inobt_rec_incore rec; - cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, btnum); + cur = xfs_inobt_init_cursor(pag, tp, agbp); /* the new record is pre-aligned so we know where to look */ error = xfs_inobt_lookup(cur, nrec->ir_startino, XFS_LOOKUP_EQ, &i); @@ -541,6 +573,7 @@ xfs_inobt_insert_sprec( if (error) goto error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } @@ -549,45 +582,42 @@ xfs_inobt_insert_sprec( } /* - * A record exists at this startino. Merge or replace the record - * depending on what we've been asked to do. + * A record exists at this startino. Merge the records. */ - if (merge) { - error = xfs_inobt_get_rec(cur, &rec, &i); - if (error) - goto error; - if (XFS_IS_CORRUPT(mp, i != 1)) { - error = -EFSCORRUPTED; - goto error; - } - if (XFS_IS_CORRUPT(mp, rec.ir_startino != nrec->ir_startino)) { - error = -EFSCORRUPTED; - goto error; - } + error = xfs_inobt_get_rec(cur, &rec, &i); + if (error) + goto error; + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto error; + } + if (XFS_IS_CORRUPT(mp, rec.ir_startino != nrec->ir_startino)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto error; + } - /* - * This should never fail. If we have coexisting records that - * cannot merge, something is seriously wrong. - */ - if (XFS_IS_CORRUPT(mp, !__xfs_inobt_can_merge(nrec, &rec))) { - error = -EFSCORRUPTED; - goto error; - } + /* + * This should never fail. If we have coexisting records that + * cannot merge, something is seriously wrong. + */ + if (XFS_IS_CORRUPT(mp, !__xfs_inobt_can_merge(nrec, &rec))) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto error; + } - trace_xfs_irec_merge_pre(mp, pag->pag_agno, rec.ir_startino, - rec.ir_holemask, nrec->ir_startino, - nrec->ir_holemask); + trace_xfs_irec_merge_pre(pag, &rec, nrec); - /* merge to nrec to output the updated record */ - __xfs_inobt_rec_merge(nrec, &rec); + /* merge to nrec to output the updated record */ + __xfs_inobt_rec_merge(nrec, &rec); - trace_xfs_irec_merge_post(mp, pag->pag_agno, nrec->ir_startino, - nrec->ir_holemask); + trace_xfs_irec_merge_post(pag, nrec); - error = xfs_inobt_rec_check_count(mp, nrec); - if (error) - goto error; - } + error = xfs_inobt_rec_check_count(mp, nrec); + if (error) + goto error; error = xfs_inobt_update(cur, nrec); if (error) @@ -602,6 +632,59 @@ error: } /* + * Insert a new sparse inode chunk into the free inode btree. The inode + * record for the sparse chunk is pre-aligned to a startino that should match + * any pre-existing sparse inode record in the tree. This allows sparse chunks + * to fill over time. + * + * The new record is always inserted, overwriting a pre-existing record if + * there is one. + */ +STATIC int +xfs_finobt_insert_sprec( + struct xfs_perag *pag, + struct xfs_trans *tp, + struct xfs_buf *agbp, + struct xfs_inobt_rec_incore *nrec) /* in/out: new rec. */ +{ + struct xfs_mount *mp = pag_mount(pag); + struct xfs_btree_cur *cur; + int error; + int i; + + cur = xfs_finobt_init_cursor(pag, tp, agbp); + + /* the new record is pre-aligned so we know where to look */ + error = xfs_inobt_lookup(cur, nrec->ir_startino, XFS_LOOKUP_EQ, &i); + if (error) + goto error; + /* if nothing there, insert a new record and return */ + if (i == 0) { + error = xfs_inobt_insert_rec(cur, nrec->ir_holemask, + nrec->ir_count, nrec->ir_freecount, + nrec->ir_free, &i); + if (error) + goto error; + if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); + error = -EFSCORRUPTED; + goto error; + } + } else { + error = xfs_inobt_update(cur, nrec); + if (error) + goto error; + } + + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + return 0; +error: + xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); + return error; +} + + +/* * Allocate new inodes in the allocation group specified by agbp. Returns 0 if * inodes were allocated in this AG; -EAGAIN if there was no space in this AG so * the caller knows it can try another AG, a hard -ENOSPC when over the maximum @@ -609,9 +692,9 @@ error: */ STATIC int xfs_ialloc_ag_alloc( + struct xfs_perag *pag, struct xfs_trans *tp, - struct xfs_buf *agbp, - struct xfs_perag *pag) + struct xfs_buf *agbp) { struct xfs_agi *agi; struct xfs_alloc_arg args; @@ -631,6 +714,7 @@ xfs_ialloc_ag_alloc( args.mp = tp->t_mountp; args.fsbno = NULLFSBLOCK; args.oinfo = XFS_RMAP_OINFO_INODES; + args.pag = pag; #ifdef DEBUG /* randomly do sparse inode allocations */ @@ -662,8 +746,6 @@ xfs_ialloc_ag_alloc( goto sparse_alloc; if (likely(newino != NULLAGINO && (args.agbno < be32_to_cpu(agi->agi_length)))) { - args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno); - args.type = XFS_ALLOCTYPE_THIS_BNO; args.prod = 1; /* @@ -684,7 +766,9 @@ xfs_ialloc_ag_alloc( /* Allow space for the inode btree to split. */ args.minleft = igeo->inobt_maxlevels; - if ((error = xfs_alloc_vextent(&args))) + error = xfs_alloc_vextent_exact_bno(&args, + xfs_agbno_to_fsb(pag, args.agbno)); + if (error) return error; /* @@ -717,22 +801,17 @@ xfs_ialloc_ag_alloc( } else args.alignment = igeo->cluster_align; /* - * Need to figure out where to allocate the inode blocks. - * Ideally they should be spaced out through the a.g. - * For now, just allocate blocks up front. - */ - args.agbno = be32_to_cpu(agi->agi_root); - args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno); - /* * Allocate a fixed-size extent of inodes. */ - args.type = XFS_ALLOCTYPE_NEAR_BNO; args.prod = 1; /* * Allow space for the inode btree to split. */ args.minleft = igeo->inobt_maxlevels; - if ((error = xfs_alloc_vextent(&args))) + error = xfs_alloc_vextent_near_bno(&args, + xfs_agbno_to_fsb(pag, + be32_to_cpu(agi->agi_root))); + if (error) return error; } @@ -741,11 +820,11 @@ xfs_ialloc_ag_alloc( * alignment. */ if (isaligned && args.fsbno == NULLFSBLOCK) { - args.type = XFS_ALLOCTYPE_NEAR_BNO; - args.agbno = be32_to_cpu(agi->agi_root); - args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno); args.alignment = igeo->cluster_align; - if ((error = xfs_alloc_vextent(&args))) + error = xfs_alloc_vextent_near_bno(&args, + xfs_agbno_to_fsb(pag, + be32_to_cpu(agi->agi_root))); + if (error) return error; } @@ -757,9 +836,6 @@ xfs_ialloc_ag_alloc( igeo->ialloc_min_blks < igeo->ialloc_blks && args.fsbno == NULLFSBLOCK) { sparse_alloc: - args.type = XFS_ALLOCTYPE_NEAR_BNO; - args.agbno = be32_to_cpu(agi->agi_root); - args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno); args.alignment = args.mp->m_sb.sb_spino_align; args.prod = 1; @@ -777,11 +853,14 @@ sparse_alloc: * the end of the AG. */ args.min_agbno = args.mp->m_sb.sb_inoalignmt; - args.max_agbno = round_down(args.mp->m_sb.sb_agblocks, + args.max_agbno = round_down(xfs_ag_block_count(args.mp, + pag_agno(pag)), args.mp->m_sb.sb_inoalignmt) - igeo->ialloc_blks; - error = xfs_alloc_vextent(&args); + error = xfs_alloc_vextent_near_bno(&args, + xfs_agbno_to_fsb(pag, + be32_to_cpu(agi->agi_root))); if (error) return error; @@ -804,7 +883,7 @@ sparse_alloc: * rather than a linear progression to prevent the next generation * number from being easily guessable. */ - error = xfs_ialloc_inode_init(args.mp, tp, NULL, newlen, pag->pag_agno, + error = xfs_ialloc_inode_init(args.mp, tp, NULL, newlen, pag_agno(pag), args.agbno, args.len, get_random_u32()); if (error) @@ -831,13 +910,11 @@ sparse_alloc: * if necessary. If a merge does occur, rec is updated to the * merged record. */ - error = xfs_inobt_insert_sprec(args.mp, tp, agbp, pag, - XFS_BTNUM_INO, &rec, true); + error = xfs_inobt_insert_sprec(pag, tp, agbp, &rec); if (error == -EFSCORRUPTED) { xfs_alert(args.mp, "invalid sparse inode record: ino 0x%llx holemask 0x%x count %u", - XFS_AGINO_TO_INO(args.mp, pag->pag_agno, - rec.ir_startino), + xfs_agino_to_ino(pag, rec.ir_startino), rec.ir_holemask, rec.ir_count); xfs_force_shutdown(args.mp, SHUTDOWN_CORRUPT_INCORE); } @@ -856,21 +933,19 @@ sparse_alloc: * existing record with this one. */ if (xfs_has_finobt(args.mp)) { - error = xfs_inobt_insert_sprec(args.mp, tp, agbp, pag, - XFS_BTNUM_FINO, &rec, false); + error = xfs_finobt_insert_sprec(pag, tp, agbp, &rec); if (error) return error; } } else { /* full chunk - insert new records to both btrees */ - error = xfs_inobt_insert(args.mp, tp, agbp, pag, newino, newlen, - XFS_BTNUM_INO); + error = xfs_inobt_insert(pag, tp, agbp, newino, newlen, false); if (error) return error; if (xfs_has_finobt(args.mp)) { - error = xfs_inobt_insert(args.mp, tp, agbp, pag, newino, - newlen, XFS_BTNUM_FINO); + error = xfs_inobt_insert(pag, tp, agbp, newino, + newlen, true); if (error) return error; } @@ -923,8 +998,10 @@ xfs_ialloc_next_rec( error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; - if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) + if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } } return 0; @@ -948,8 +1025,10 @@ xfs_ialloc_get_rec( error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; - if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) + if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } } return 0; @@ -977,13 +1056,40 @@ xfs_inobt_first_free_inode( } /* + * If this AG has corrupt inodes, check if allocating this inode would fail + * with corruption errors. Returns 0 if we're clear, or EAGAIN to try again + * somewhere else. + */ +static int +xfs_dialloc_check_ino( + struct xfs_perag *pag, + struct xfs_trans *tp, + xfs_ino_t ino) +{ + struct xfs_imap imap; + struct xfs_buf *bp; + int error; + + error = xfs_imap(pag, tp, ino, &imap, 0); + if (error) + return -EAGAIN; + + error = xfs_imap_to_bp(pag_mount(pag), tp, &imap, &bp); + if (error) + return -EAGAIN; + + xfs_trans_brelse(tp, bp); + return 0; +} + +/* * Allocate an inode using the inobt-only algorithm. */ STATIC int xfs_dialloc_ag_inobt( + struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, - struct xfs_perag *pag, xfs_ino_t parent, xfs_ino_t *inop) { @@ -999,12 +1105,12 @@ xfs_dialloc_ag_inobt( int i, j; int searchdistance = 10; - ASSERT(pag->pagi_init); - ASSERT(pag->pagi_inodeok); + ASSERT(xfs_perag_initialised_agi(pag)); + ASSERT(xfs_perag_allows_inodes(pag)); ASSERT(pag->pagi_freecount > 0); restart_pagno: - cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO); + cur = xfs_inobt_init_cursor(pag, tp, agbp); /* * If pagino is 0 (this is the root inode allocation) use newino. * This must work because we've just allocated some. @@ -1019,7 +1125,7 @@ xfs_dialloc_ag_inobt( /* * If in the same AG as the parent, try to get near the parent. */ - if (pagno == pag->pag_agno) { + if (pagno == pag_agno(pag)) { int doneleft; /* done, to the left */ int doneright; /* done, to the right */ @@ -1027,6 +1133,7 @@ xfs_dialloc_ag_inobt( if (error) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -1035,6 +1142,7 @@ xfs_dialloc_ag_inobt( if (error) goto error0; if (XFS_IS_CORRUPT(mp, j != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -1193,6 +1301,7 @@ xfs_dialloc_ag_inobt( if (error) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -1202,6 +1311,7 @@ xfs_dialloc_ag_inobt( if (error) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -1211,6 +1321,7 @@ xfs_dialloc_ag_inobt( if (error) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -1222,7 +1333,14 @@ alloc_inode: ASSERT(offset < XFS_INODES_PER_CHUNK); ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) % XFS_INODES_PER_CHUNK) == 0); - ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset); + ino = xfs_agino_to_ino(pag, rec.ir_startino + offset); + + if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) { + error = xfs_dialloc_check_ino(pag, tp, ino); + if (error) + goto error0; + } + rec.ir_free &= ~XFS_INOBT_MASK(offset); rec.ir_freecount--; error = xfs_inobt_update(cur, &rec); @@ -1271,8 +1389,10 @@ xfs_dialloc_ag_finobt_near( error = xfs_inobt_get_rec(lcur, rec, &i); if (error) return error; - if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1)) + if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1)) { + xfs_btree_mark_sick(lcur); return -EFSCORRUPTED; + } /* * See if we've landed in the parent inode record. The finobt @@ -1296,12 +1416,14 @@ xfs_dialloc_ag_finobt_near( if (error) goto error_rcur; if (XFS_IS_CORRUPT(lcur->bc_mp, j != 1)) { + xfs_btree_mark_sick(lcur); error = -EFSCORRUPTED; goto error_rcur; } } if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1 && j != 1)) { + xfs_btree_mark_sick(lcur); error = -EFSCORRUPTED; goto error_rcur; } @@ -1357,8 +1479,10 @@ xfs_dialloc_ag_finobt_newino( error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; - if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) + if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } return 0; } } @@ -1369,14 +1493,18 @@ xfs_dialloc_ag_finobt_newino( error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i); if (error) return error; - if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) + if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; - if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) + if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } return 0; } @@ -1398,14 +1526,18 @@ xfs_dialloc_ag_update_inobt( error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i); if (error) return error; - if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) + if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } error = xfs_inobt_get_rec(cur, &rec, &i); if (error) return error; - if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) + if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) % XFS_INODES_PER_CHUNK) == 0); @@ -1414,8 +1546,10 @@ xfs_dialloc_ag_update_inobt( if (XFS_IS_CORRUPT(cur->bc_mp, rec.ir_free != frec->ir_free || - rec.ir_freecount != frec->ir_freecount)) + rec.ir_freecount != frec->ir_freecount)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } return xfs_inobt_update(cur, &rec); } @@ -1429,9 +1563,9 @@ xfs_dialloc_ag_update_inobt( */ static int xfs_dialloc_ag( + struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, - struct xfs_perag *pag, xfs_ino_t parent, xfs_ino_t *inop) { @@ -1448,7 +1582,7 @@ xfs_dialloc_ag( int i; if (!xfs_has_finobt(mp)) - return xfs_dialloc_ag_inobt(tp, agbp, pag, parent, inop); + return xfs_dialloc_ag_inobt(pag, tp, agbp, parent, inop); /* * If pagino is 0 (this is the root inode allocation) use newino. @@ -1457,7 +1591,7 @@ xfs_dialloc_ag( if (!pagino) pagino = be32_to_cpu(agi->agi_newino); - cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_FINO); + cur = xfs_finobt_init_cursor(pag, tp, agbp); error = xfs_check_agi_freecount(cur); if (error) @@ -1468,7 +1602,7 @@ xfs_dialloc_ag( * parent. If so, find the closest available inode to the parent. If * not, consider the agi hint or find the first free inode in the AG. */ - if (pag->pag_agno == pagno) + if (pag_agno(pag) == pagno) error = xfs_dialloc_ag_finobt_near(pagino, &cur, &rec); else error = xfs_dialloc_ag_finobt_newino(agi, cur, &rec); @@ -1480,7 +1614,13 @@ xfs_dialloc_ag( ASSERT(offset < XFS_INODES_PER_CHUNK); ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) % XFS_INODES_PER_CHUNK) == 0); - ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset); + ino = xfs_agino_to_ino(pag, rec.ir_startino + offset); + + if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) { + error = xfs_dialloc_check_ino(pag, tp, ino); + if (error) + goto error_cur; + } /* * Modify or remove the finobt record. @@ -1500,7 +1640,7 @@ xfs_dialloc_ag( * the original freecount. If all is well, make the equivalent update to * the inobt using the finobt record and offset information. */ - icur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO); + icur = xfs_inobt_init_cursor(pag, tp, agbp); error = xfs_check_agi_freecount(icur); if (error) @@ -1577,25 +1717,10 @@ xfs_dialloc_roll( return error; } -static xfs_agnumber_t -xfs_ialloc_next_ag( - xfs_mount_t *mp) -{ - xfs_agnumber_t agno; - - spin_lock(&mp->m_agirotor_lock); - agno = mp->m_agirotor; - if (++mp->m_agirotor >= mp->m_maxagi) - mp->m_agirotor = 0; - spin_unlock(&mp->m_agirotor_lock); - - return agno; -} - static bool xfs_dialloc_good_ag( - struct xfs_trans *tp, struct xfs_perag *pag, + struct xfs_trans *tp, umode_t mode, int flags, bool ok_alloc) @@ -1606,11 +1731,13 @@ xfs_dialloc_good_ag( int needspace; int error; - if (!pag->pagi_inodeok) + if (!pag) + return false; + if (!xfs_perag_allows_inodes(pag)) return false; - if (!pag->pagi_init) { - error = xfs_ialloc_read_agi(pag, tp, NULL); + if (!xfs_perag_initialised_agi(pag)) { + error = xfs_ialloc_read_agi(pag, tp, 0, NULL); if (error) return false; } @@ -1620,7 +1747,7 @@ xfs_dialloc_good_ag( if (!ok_alloc) return false; - if (!pag->pagf_init) { + if (!xfs_perag_initialised_agf(pag)) { error = xfs_alloc_read_agf(pag, tp, flags, NULL); if (error) return false; @@ -1665,8 +1792,8 @@ xfs_dialloc_good_ag( static int xfs_dialloc_try_ag( - struct xfs_trans **tpp, struct xfs_perag *pag, + struct xfs_trans **tpp, xfs_ino_t parent, xfs_ino_t *new_ino, bool ok_alloc) @@ -1679,7 +1806,7 @@ xfs_dialloc_try_ag( * Then read in the AGI buffer and recheck with the AGI buffer * lock held. */ - error = xfs_ialloc_read_agi(pag, *tpp, &agbp); + error = xfs_ialloc_read_agi(pag, *tpp, 0, &agbp); if (error) return error; @@ -1689,7 +1816,7 @@ xfs_dialloc_try_ag( goto out_release; } - error = xfs_ialloc_ag_alloc(*tpp, agbp, pag); + error = xfs_ialloc_ag_alloc(pag, *tpp, agbp); if (error < 0) goto out_release; @@ -1705,7 +1832,7 @@ xfs_dialloc_try_ag( } /* Allocate an inode in the found AG */ - error = xfs_dialloc_ag(*tpp, agbp, pag, parent, &ino); + error = xfs_dialloc_ag(pag, *tpp, agbp, parent, &ino); if (!error) *new_ino = ino; return error; @@ -1716,6 +1843,40 @@ out_release: } /* + * Pick an AG for the new inode. + * + * Directories, symlinks, and regular files frequently allocate at least one + * block, so factor that potential expansion when we examine whether an AG has + * enough space for file creation. Try to keep metadata files all in the same + * AG. + */ +static inline xfs_agnumber_t +xfs_dialloc_pick_ag( + struct xfs_mount *mp, + struct xfs_inode *dp, + umode_t mode) +{ + xfs_agnumber_t start_agno; + + if (!dp) + return 0; + if (xfs_is_metadir_inode(dp)) { + if (mp->m_sb.sb_logstart) + return XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart); + return 0; + } + + if (S_ISDIR(mode)) + return (atomic_inc_return(&mp->m_agirotor) - 1) % mp->m_maxagi; + + start_agno = XFS_INO_TO_AGNO(mp, dp->i_ino); + if (start_agno >= mp->m_maxagi) + start_agno = 0; + + return start_agno; +} + +/* * Allocate an on-disk inode. * * Mode is used to tell whether the new inode is a directory and hence where to @@ -1726,32 +1887,23 @@ out_release: int xfs_dialloc( struct xfs_trans **tpp, - xfs_ino_t parent, - umode_t mode, + const struct xfs_icreate_args *args, xfs_ino_t *new_ino) { struct xfs_mount *mp = (*tpp)->t_mountp; - xfs_agnumber_t agno; - int error = 0; - xfs_agnumber_t start_agno; struct xfs_perag *pag; struct xfs_ino_geometry *igeo = M_IGEO(mp); + xfs_ino_t ino = NULLFSINO; + xfs_ino_t parent = args->pip ? args->pip->i_ino : 0; + xfs_agnumber_t agno; + xfs_agnumber_t start_agno; + umode_t mode = args->mode & S_IFMT; bool ok_alloc = true; + bool low_space = false; int flags; - xfs_ino_t ino; + int error = 0; - /* - * Directories, symlinks, and regular files frequently allocate at least - * one block, so factor that potential expansion when we examine whether - * an AG has enough space for file creation. - */ - if (S_ISDIR(mode)) - start_agno = xfs_ialloc_next_ag(mp); - else { - start_agno = XFS_INO_TO_AGNO(mp, parent); - if (start_agno >= mp->m_maxagi) - start_agno = 0; - } + start_agno = xfs_dialloc_pick_ag(mp, args->pip, mode); /* * If we have already hit the ceiling of inode blocks then clear @@ -1768,41 +1920,70 @@ xfs_dialloc( } /* + * If we are near to ENOSPC, we want to prefer allocation from AGs that + * have free inodes in them rather than use up free space allocating new + * inode chunks. Hence we turn off allocation for the first non-blocking + * pass through the AGs if we are near ENOSPC to consume free inodes + * that we can immediately allocate, but then we allow allocation on the + * second pass if we fail to find an AG with free inodes in it. + */ + if (xfs_estimate_freecounter(mp, XC_FREE_BLOCKS) < + mp->m_low_space[XFS_LOWSP_1_PCNT]) { + ok_alloc = false; + low_space = true; + } + + /* * Loop until we find an allocation group that either has free inodes * or in which we can allocate some inodes. Iterate through the * allocation groups upward, wrapping at the end. */ - agno = start_agno; flags = XFS_ALLOC_FLAG_TRYLOCK; - for (;;) { - pag = xfs_perag_get(mp, agno); - if (xfs_dialloc_good_ag(*tpp, pag, mode, flags, ok_alloc)) { - error = xfs_dialloc_try_ag(tpp, pag, parent, +retry: + for_each_perag_wrap_at(mp, start_agno, mp->m_maxagi, agno, pag) { + if (xfs_dialloc_good_ag(pag, *tpp, mode, flags, ok_alloc)) { + error = xfs_dialloc_try_ag(pag, tpp, parent, &ino, ok_alloc); if (error != -EAGAIN) break; + error = 0; } if (xfs_is_shutdown(mp)) { error = -EFSCORRUPTED; break; } - if (++agno == mp->m_maxagi) - agno = 0; - if (agno == start_agno) { - if (!flags) { - error = -ENOSPC; - break; - } + } + if (pag) + xfs_perag_rele(pag); + if (error) + return error; + if (ino == NULLFSINO) { + if (flags) { flags = 0; + if (low_space) + ok_alloc = true; + goto retry; } - xfs_perag_put(pag); + return -ENOSPC; } - if (!error) - *new_ino = ino; - xfs_perag_put(pag); - return error; + /* + * Protect against obviously corrupt allocation btree records. Later + * xfs_iget checks will catch re-allocation of other active in-memory + * and on-disk inodes. If we don't catch reallocating the parent inode + * here we will deadlock in xfs_iget() so we have to do these checks + * first. + */ + if (ino == parent || !xfs_verify_dir_ino(mp, ino)) { + xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino); + xfs_agno_mark_sick(mp, XFS_INO_TO_AGNO(mp, ino), + XFS_SICK_AG_INOBT); + return -EFSCORRUPTED; + } + + *new_ino = ino; + return 0; } /* @@ -1810,10 +1991,10 @@ xfs_dialloc( * might be sparse and only free the regions that are allocated as part of the * chunk. */ -STATIC void +static int xfs_difree_inode_chunk( struct xfs_trans *tp, - xfs_agnumber_t agno, + struct xfs_perag *pag, struct xfs_inobt_rec_incore *rec) { struct xfs_mount *mp = tp->t_mountp; @@ -1827,10 +2008,9 @@ xfs_difree_inode_chunk( if (!xfs_inobt_issparse(rec->ir_holemask)) { /* not sparse, calculate extent info directly */ - xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno), - M_IGEO(mp)->ialloc_blks, - &XFS_RMAP_OINFO_INODES); - return; + return xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, sagbno), + M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES, + XFS_AG_RESV_NONE, 0); } /* holemask is only 16-bits (fits in an unsigned long) */ @@ -1847,6 +2027,8 @@ xfs_difree_inode_chunk( XFS_INOBT_HOLEMASK_BITS); nextbit = startidx + 1; while (startidx < XFS_INOBT_HOLEMASK_BITS) { + int error; + nextbit = find_next_zero_bit(holemask, XFS_INOBT_HOLEMASK_BITS, nextbit); /* @@ -1872,8 +2054,11 @@ xfs_difree_inode_chunk( ASSERT(agbno % mp->m_sb.sb_spino_align == 0); ASSERT(contigblk % mp->m_sb.sb_spino_align == 0); - xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, agbno), - contigblk, &XFS_RMAP_OINFO_INODES); + error = xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, agbno), + contigblk, &XFS_RMAP_OINFO_INODES, + XFS_AG_RESV_NONE, 0); + if (error) + return error; /* reset range to current bit and carry on... */ startidx = endidx = nextbit; @@ -1881,18 +2066,19 @@ xfs_difree_inode_chunk( next: nextbit++; } + return 0; } STATIC int xfs_difree_inobt( - struct xfs_mount *mp, + struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, - struct xfs_perag *pag, xfs_agino_t agino, struct xfs_icluster *xic, struct xfs_inobt_rec_incore *orec) { + struct xfs_mount *mp = pag_mount(pag); struct xfs_agi *agi = agbp->b_addr; struct xfs_btree_cur *cur; struct xfs_inobt_rec_incore rec; @@ -1907,7 +2093,7 @@ xfs_difree_inobt( /* * Initialize the cursor. */ - cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO); + cur = xfs_inobt_init_cursor(pag, tp, agbp); error = xfs_check_agi_freecount(cur); if (error) @@ -1922,6 +2108,7 @@ xfs_difree_inobt( goto error0; } if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -1932,6 +2119,7 @@ xfs_difree_inobt( goto error0; } if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } @@ -1952,13 +2140,10 @@ xfs_difree_inobt( * remove the chunk if the block size is large enough for multiple inode * chunks (that might not be free). */ - if (!xfs_has_ikeep(mp) && rec.ir_free == XFS_INOBT_ALL_FREE && + if (rec.ir_free == XFS_INOBT_ALL_FREE && mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) { - struct xfs_perag *pag = agbp->b_pag; - xic->deleted = true; - xic->first_ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, - rec.ir_startino); + xic->first_ino = xfs_agino_to_ino(pag, rec.ir_startino); xic->alloc = xfs_inobt_irec_to_allocmask(&rec); /* @@ -1981,7 +2166,9 @@ xfs_difree_inobt( goto error0; } - xfs_difree_inode_chunk(tp, pag->pag_agno, &rec); + error = xfs_difree_inode_chunk(tp, pag, &rec); + if (error) + goto error0; } else { xic->deleted = false; @@ -2019,20 +2206,20 @@ error0: */ STATIC int xfs_difree_finobt( - struct xfs_mount *mp, + struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, - struct xfs_perag *pag, xfs_agino_t agino, struct xfs_inobt_rec_incore *ibtrec) /* inobt record */ { + struct xfs_mount *mp = pag_mount(pag); struct xfs_btree_cur *cur; struct xfs_inobt_rec_incore rec; int offset = agino - ibtrec->ir_startino; int error; int i; - cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_FINO); + cur = xfs_finobt_init_cursor(pag, tp, agbp); error = xfs_inobt_lookup(cur, ibtrec->ir_startino, XFS_LOOKUP_EQ, &i); if (error) @@ -2044,6 +2231,7 @@ xfs_difree_finobt( * something is out of sync. */ if (XFS_IS_CORRUPT(mp, ibtrec->ir_freecount != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } @@ -2070,6 +2258,7 @@ xfs_difree_finobt( if (error) goto error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } @@ -2080,6 +2269,7 @@ xfs_difree_finobt( if (XFS_IS_CORRUPT(mp, rec.ir_free != ibtrec->ir_free || rec.ir_freecount != ibtrec->ir_freecount)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } @@ -2096,7 +2286,7 @@ xfs_difree_finobt( * enough for multiple chunks. Leave the finobt record to remain in sync * with the inobt. */ - if (!xfs_has_ikeep(mp) && rec.ir_free == XFS_INOBT_ALL_FREE && + if (rec.ir_free == XFS_INOBT_ALL_FREE && mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) { error = xfs_btree_delete(cur, &i); if (error) @@ -2145,31 +2335,31 @@ xfs_difree( /* * Break up inode number into its components. */ - if (pag->pag_agno != XFS_INO_TO_AGNO(mp, inode)) { - xfs_warn(mp, "%s: agno != pag->pag_agno (%d != %d).", - __func__, XFS_INO_TO_AGNO(mp, inode), pag->pag_agno); + if (pag_agno(pag) != XFS_INO_TO_AGNO(mp, inode)) { + xfs_warn(mp, "%s: agno != pag_agno(pag) (%d != %d).", + __func__, XFS_INO_TO_AGNO(mp, inode), pag_agno(pag)); ASSERT(0); return -EINVAL; } agino = XFS_INO_TO_AGINO(mp, inode); - if (inode != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) { - xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).", + if (inode != xfs_agino_to_ino(pag, agino)) { + xfs_warn(mp, "%s: inode != xfs_agino_to_ino() (%llu != %llu).", __func__, (unsigned long long)inode, - (unsigned long long)XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)); + (unsigned long long)xfs_agino_to_ino(pag, agino)); ASSERT(0); return -EINVAL; } agbno = XFS_AGINO_TO_AGBNO(mp, agino); - if (agbno >= mp->m_sb.sb_agblocks) { - xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).", - __func__, agbno, mp->m_sb.sb_agblocks); + if (agbno >= xfs_ag_block_count(mp, pag_agno(pag))) { + xfs_warn(mp, "%s: agbno >= xfs_ag_block_count (%d >= %d).", + __func__, agbno, xfs_ag_block_count(mp, pag_agno(pag))); ASSERT(0); return -EINVAL; } /* * Get the allocation group header. */ - error = xfs_ialloc_read_agi(pag, tp, &agbp); + error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); if (error) { xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.", __func__, error); @@ -2179,7 +2369,7 @@ xfs_difree( /* * Fix up the inode allocation btree. */ - error = xfs_difree_inobt(mp, tp, agbp, pag, agino, xic, &rec); + error = xfs_difree_inobt(pag, tp, agbp, agino, xic, &rec); if (error) goto error0; @@ -2187,7 +2377,7 @@ xfs_difree( * Fix up the free inode btree. */ if (xfs_has_finobt(mp)) { - error = xfs_difree_finobt(mp, tp, agbp, pag, agino, &rec); + error = xfs_difree_finobt(pag, tp, agbp, agino, &rec); if (error) goto error0; } @@ -2200,26 +2390,26 @@ error0: STATIC int xfs_imap_lookup( - struct xfs_mount *mp, - struct xfs_trans *tp, struct xfs_perag *pag, + struct xfs_trans *tp, xfs_agino_t agino, xfs_agblock_t agbno, xfs_agblock_t *chunk_agbno, xfs_agblock_t *offset_agbno, int flags) { + struct xfs_mount *mp = pag_mount(pag); struct xfs_inobt_rec_incore rec; struct xfs_btree_cur *cur; struct xfs_buf *agbp; int error; int i; - error = xfs_ialloc_read_agi(pag, tp, &agbp); + error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); if (error) { xfs_alert(mp, "%s: xfs_ialloc_read_agi() returned error %d, agno %d", - __func__, error, pag->pag_agno); + __func__, error, pag_agno(pag)); return error; } @@ -2229,7 +2419,7 @@ xfs_imap_lookup( * we have a record, we need to ensure it contains the inode number * we are looking up. */ - cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO); + cur = xfs_inobt_init_cursor(pag, tp, agbp); error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i); if (!error) { if (i) @@ -2263,12 +2453,13 @@ xfs_imap_lookup( */ int xfs_imap( - struct xfs_mount *mp, /* file system mount structure */ - struct xfs_trans *tp, /* transaction pointer */ + struct xfs_perag *pag, + struct xfs_trans *tp, xfs_ino_t ino, /* inode to locate */ struct xfs_imap *imap, /* location map structure */ uint flags) /* flags for inode btree lookup */ { + struct xfs_mount *mp = pag_mount(pag); xfs_agblock_t agbno; /* block number of inode in the alloc group */ xfs_agino_t agino; /* inode number within alloc group */ xfs_agblock_t chunk_agbno; /* first block in inode chunk */ @@ -2276,18 +2467,16 @@ xfs_imap( int error; /* error code */ int offset; /* index of inode in its buffer */ xfs_agblock_t offset_agbno; /* blks from chunk start to inode */ - struct xfs_perag *pag; ASSERT(ino != NULLFSINO); /* * Split up the inode number into its parts. */ - pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino)); agino = XFS_INO_TO_AGINO(mp, ino); agbno = XFS_AGINO_TO_AGBNO(mp, agino); - if (!pag || agbno >= mp->m_sb.sb_agblocks || - ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) { + if (agbno >= xfs_ag_block_count(mp, pag_agno(pag)) || + ino != xfs_agino_to_ino(pag, agino)) { error = -EINVAL; #ifdef DEBUG /* @@ -2295,28 +2484,23 @@ xfs_imap( * as they can be invalid without implying corruption. */ if (flags & XFS_IGET_UNTRUSTED) - goto out_drop; - if (!pag) { - xfs_alert(mp, - "%s: agno (%d) >= mp->m_sb.sb_agcount (%d)", - __func__, XFS_INO_TO_AGNO(mp, ino), - mp->m_sb.sb_agcount); - } - if (agbno >= mp->m_sb.sb_agblocks) { + return error; + if (agbno >= xfs_ag_block_count(mp, pag_agno(pag))) { xfs_alert(mp, "%s: agbno (0x%llx) >= mp->m_sb.sb_agblocks (0x%lx)", __func__, (unsigned long long)agbno, - (unsigned long)mp->m_sb.sb_agblocks); + (unsigned long)xfs_ag_block_count(mp, + pag_agno(pag))); } - if (pag && ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) { + if (ino != xfs_agino_to_ino(pag, agino)) { xfs_alert(mp, - "%s: ino (0x%llx) != XFS_AGINO_TO_INO() (0x%llx)", + "%s: ino (0x%llx) != xfs_agino_to_ino() (0x%llx)", __func__, ino, - XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)); + xfs_agino_to_ino(pag, agino)); } xfs_stack_trace(); #endif /* DEBUG */ - goto out_drop; + return error; } /* @@ -2327,10 +2511,10 @@ xfs_imap( * in all cases where an untrusted inode number is passed. */ if (flags & XFS_IGET_UNTRUSTED) { - error = xfs_imap_lookup(mp, tp, pag, agino, agbno, + error = xfs_imap_lookup(pag, tp, agino, agbno, &chunk_agbno, &offset_agbno, flags); if (error) - goto out_drop; + return error; goto out_map; } @@ -2342,12 +2526,11 @@ xfs_imap( offset = XFS_INO_TO_OFFSET(mp, ino); ASSERT(offset < mp->m_sb.sb_inopblock); - imap->im_blkno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, agbno); + imap->im_blkno = xfs_agbno_to_daddr(pag, agbno); imap->im_len = XFS_FSB_TO_BB(mp, 1); imap->im_boffset = (unsigned short)(offset << mp->m_sb.sb_inodelog); - error = 0; - goto out_drop; + return 0; } /* @@ -2359,10 +2542,10 @@ xfs_imap( offset_agbno = agbno & M_IGEO(mp)->inoalign_mask; chunk_agbno = agbno - offset_agbno; } else { - error = xfs_imap_lookup(mp, tp, pag, agino, agbno, + error = xfs_imap_lookup(pag, tp, agino, agbno, &chunk_agbno, &offset_agbno, flags); if (error) - goto out_drop; + return error; } out_map: @@ -2373,7 +2556,7 @@ out_map: offset = ((agbno - cluster_agbno) * mp->m_sb.sb_inopblock) + XFS_INO_TO_OFFSET(mp, ino); - imap->im_blkno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, cluster_agbno); + imap->im_blkno = xfs_agbno_to_daddr(pag, cluster_agbno); imap->im_len = XFS_FSB_TO_BB(mp, M_IGEO(mp)->blocks_per_cluster); imap->im_boffset = (unsigned short)(offset << mp->m_sb.sb_inodelog); @@ -2390,14 +2573,9 @@ out_map: __func__, (unsigned long long) imap->im_blkno, (unsigned long long) imap->im_len, XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)); - error = -EINVAL; - goto out_drop; + return -EINVAL; } - error = 0; -out_drop: - if (pag) - xfs_perag_put(pag); - return error; + return 0; } /* @@ -2469,11 +2647,14 @@ xfs_ialloc_log_agi( static xfs_failaddr_t xfs_agi_verify( - struct xfs_buf *bp) + struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_mount; - struct xfs_agi *agi = bp->b_addr; - int i; + struct xfs_mount *mp = bp->b_mount; + struct xfs_agi *agi = bp->b_addr; + xfs_failaddr_t fa; + uint32_t agi_seqno = be32_to_cpu(agi->agi_seqno); + uint32_t agi_length = be32_to_cpu(agi->agi_length); + int i; if (xfs_has_crc(mp)) { if (!uuid_equal(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid)) @@ -2490,6 +2671,10 @@ xfs_agi_verify( if (!XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum))) return __this_address; + fa = xfs_validate_ag_length(bp, agi_seqno, agi_length); + if (fa) + return fa; + if (be32_to_cpu(agi->agi_level) < 1 || be32_to_cpu(agi->agi_level) > M_IGEO(mp)->inobt_maxlevels) return __this_address; @@ -2499,15 +2684,6 @@ xfs_agi_verify( be32_to_cpu(agi->agi_free_level) > M_IGEO(mp)->inobt_maxlevels)) return __this_address; - /* - * during growfs operations, the perag is not fully initialised, - * so we can't use it for any useful checking. growfs ensures we can't - * use it by using uncached buffers that don't have the perag attached - * so we can detect and avoid this problem. - */ - if (bp->b_pag && be32_to_cpu(agi->agi_seqno) != bp->b_pag->pag_agno) - return __this_address; - for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) { if (agi->agi_unlinked[i] == cpu_to_be32(NULLAGINO)) continue; @@ -2530,7 +2706,7 @@ xfs_agi_read_verify( xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_agi_verify(bp); - if (XFS_TEST_ERROR(fa, mp, XFS_ERRTAG_IALLOC_READ_AGI)) + if (fa || XFS_TEST_ERROR(mp, XFS_ERRTAG_IALLOC_READ_AGI)) xfs_verifier_error(bp, -EFSCORRUPTED, fa); } } @@ -2573,16 +2749,19 @@ int xfs_read_agi( struct xfs_perag *pag, struct xfs_trans *tp, + xfs_buf_flags_t flags, struct xfs_buf **agibpp) { - struct xfs_mount *mp = pag->pag_mount; + struct xfs_mount *mp = pag_mount(pag); int error; - trace_xfs_read_agi(pag->pag_mount, pag->pag_agno); + trace_xfs_read_agi(pag); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, - XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)), - XFS_FSS_TO_BB(mp, 1), 0, agibpp, &xfs_agi_buf_ops); + XFS_AG_DADDR(mp, pag_agno(pag), XFS_AGI_DADDR(mp)), + XFS_FSS_TO_BB(mp, 1), flags, agibpp, &xfs_agi_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); if (error) return error; if (tp) @@ -2600,31 +2779,57 @@ int xfs_ialloc_read_agi( struct xfs_perag *pag, struct xfs_trans *tp, + int flags, struct xfs_buf **agibpp) { struct xfs_buf *agibp; struct xfs_agi *agi; int error; - trace_xfs_ialloc_read_agi(pag->pag_mount, pag->pag_agno); + trace_xfs_ialloc_read_agi(pag); - error = xfs_read_agi(pag, tp, &agibp); + error = xfs_read_agi(pag, tp, + (flags & XFS_IALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0, + &agibp); if (error) return error; agi = agibp->b_addr; - if (!pag->pagi_init) { + if (!xfs_perag_initialised_agi(pag)) { pag->pagi_freecount = be32_to_cpu(agi->agi_freecount); pag->pagi_count = be32_to_cpu(agi->agi_count); - pag->pagi_init = 1; + set_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate); } +#ifdef DEBUG /* - * It's possible for these to be out of sync if - * we are in the middle of a forced shutdown. + * It's possible for the AGF to be out of sync if the block device is + * silently dropping writes. This can happen in fstests with dmflakey + * enabled, which allows the buffer to be cleaned and reclaimed by + * memory pressure and then re-read from disk here. We will get a + * stale version of the AGF from disk, and nothing good can happen from + * here. Hence if we detect this situation, immediately shut down the + * filesystem. + * + * This can also happen if we are already in the middle of a forced + * shutdown, so don't bother checking if we are already shut down. */ - ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) || - xfs_is_shutdown(pag->pag_mount)); + if (!xfs_is_shutdown(pag_mount(pag))) { + bool ok = true; + + ok &= pag->pagi_freecount == be32_to_cpu(agi->agi_freecount); + ok &= pag->pagi_count == be32_to_cpu(agi->agi_count); + + if (XFS_IS_CORRUPT(pag_mount(pag), !ok)) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); + xfs_trans_brelse(tp, agibp); + xfs_force_shutdown(pag_mount(pag), + SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } + } +#endif /* DEBUG */ + if (agibpp) *agibpp = agibp; else @@ -2632,44 +2837,50 @@ xfs_ialloc_read_agi( return 0; } -/* Is there an inode record covering a given range of inode numbers? */ -int -xfs_ialloc_has_inode_record( - struct xfs_btree_cur *cur, - xfs_agino_t low, - xfs_agino_t high, - bool *exists) +/* How many inodes are backed by inode clusters ondisk? */ +STATIC int +xfs_ialloc_count_ondisk( + struct xfs_btree_cur *cur, + xfs_agino_t low, + xfs_agino_t high, + unsigned int *allocated) { struct xfs_inobt_rec_incore irec; - xfs_agino_t agino; - uint16_t holemask; - int has_record; - int i; - int error; + unsigned int ret = 0; + int has_record; + int error; - *exists = false; error = xfs_inobt_lookup(cur, low, XFS_LOOKUP_LE, &has_record); - while (error == 0 && has_record) { + if (error) + return error; + + while (has_record) { + unsigned int i, hole_idx; + error = xfs_inobt_get_rec(cur, &irec, &has_record); - if (error || irec.ir_startino > high) + if (error) + return error; + if (irec.ir_startino > high) break; - agino = irec.ir_startino; - holemask = irec.ir_holemask; - for (i = 0; i < XFS_INOBT_HOLEMASK_BITS; holemask >>= 1, - i++, agino += XFS_INODES_PER_HOLEMASK_BIT) { - if (holemask & 1) + for (i = 0; i < XFS_INODES_PER_CHUNK; i++) { + if (irec.ir_startino + i < low) continue; - if (agino + XFS_INODES_PER_HOLEMASK_BIT > low && - agino <= high) { - *exists = true; - return 0; - } + if (irec.ir_startino + i > high) + break; + + hole_idx = i / XFS_INODES_PER_HOLEMASK_BIT; + if (!(irec.ir_holemask & (1U << hole_idx))) + ret++; } error = xfs_btree_increment(cur, 0, &has_record); + if (error) + return error; } - return error; + + *allocated = ret; + return 0; } /* Is there an inode record covering a given extent? */ @@ -2678,15 +2889,27 @@ xfs_ialloc_has_inodes_at_extent( struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, - bool *exists) + enum xbtree_recpacking *outcome) { - xfs_agino_t low; - xfs_agino_t high; + xfs_agino_t agino; + xfs_agino_t last_agino; + unsigned int allocated; + int error; + + agino = XFS_AGB_TO_AGINO(cur->bc_mp, bno); + last_agino = XFS_AGB_TO_AGINO(cur->bc_mp, bno + len) - 1; - low = XFS_AGB_TO_AGINO(cur->bc_mp, bno); - high = XFS_AGB_TO_AGINO(cur->bc_mp, bno + len) - 1; + error = xfs_ialloc_count_ondisk(cur, agino, last_agino, &allocated); + if (error) + return error; - return xfs_ialloc_has_inode_record(cur, low, high, exists); + if (allocated == 0) + *outcome = XBTREE_RECPACKING_EMPTY; + else if (allocated == last_agino - agino + 1) + *outcome = XBTREE_RECPACKING_FULL; + else + *outcome = XBTREE_RECPACKING_SPARSE; + return 0; } struct xfs_ialloc_count_inodes { @@ -2703,8 +2926,13 @@ xfs_ialloc_count_inodes_rec( { struct xfs_inobt_rec_incore irec; struct xfs_ialloc_count_inodes *ci = priv; + xfs_failaddr_t fa; xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec); + fa = xfs_inobt_check_irec(to_perag(cur->bc_group), &irec); + if (fa) + return xfs_inobt_complain_bad_rec(cur, fa, &irec); + ci->count += irec.ir_count; ci->freecount += irec.ir_freecount; @@ -2721,7 +2949,7 @@ xfs_ialloc_count_inodes( struct xfs_ialloc_count_inodes ci = {0}; int error; - ASSERT(cur->bc_btnum == XFS_BTNUM_INO); + ASSERT(xfs_btree_is_ino(cur->bc_ops)); error = xfs_btree_query_all(cur, xfs_ialloc_count_inodes_rec, &ci); if (error) return error; @@ -2762,8 +2990,8 @@ xfs_ialloc_setup_geometry( /* Compute inode btree geometry. */ igeo->agino_log = sbp->sb_inopblog + sbp->sb_agblklog; - igeo->inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 1); - igeo->inobt_mxr[1] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 0); + igeo->inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, true); + igeo->inobt_mxr[1] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, false); igeo->inobt_mnr[0] = igeo->inobt_mxr[0] / 2; igeo->inobt_mnr[1] = igeo->inobt_mxr[1] / 2; @@ -2848,6 +3076,11 @@ xfs_ialloc_setup_geometry( igeo->ialloc_align = mp->m_dalign; else igeo->ialloc_align = 0; + + if (mp->m_sb.sb_blocksize > PAGE_SIZE) + igeo->min_folio_order = mp->m_sb.sb_blocklog - PAGE_SHIFT; + else + igeo->min_folio_order = 0; } /* Compute the location of the root directory inode that is laid out by mkfs. */ @@ -2924,26 +3157,24 @@ xfs_ialloc_calc_rootino( */ int xfs_ialloc_check_shrink( + struct xfs_perag *pag, struct xfs_trans *tp, - xfs_agnumber_t agno, struct xfs_buf *agibp, xfs_agblock_t new_length) { struct xfs_inobt_rec_incore rec; struct xfs_btree_cur *cur; - struct xfs_mount *mp = tp->t_mountp; - struct xfs_perag *pag; - xfs_agino_t agino = XFS_AGB_TO_AGINO(mp, new_length); + xfs_agino_t agino; int has; int error; - if (!xfs_has_sparseinodes(mp)) + if (!xfs_has_sparseinodes(pag_mount(pag))) return 0; - pag = xfs_perag_get(mp, agno); - cur = xfs_inobt_init_cursor(mp, tp, agibp, pag, XFS_BTNUM_INO); + cur = xfs_inobt_init_cursor(pag, tp, agibp); /* Look up the inobt record that would correspond to the new EOFS. */ + agino = XFS_AGB_TO_AGINO(pag_mount(pag), new_length); error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has); if (error || !has) goto out; @@ -2953,6 +3184,7 @@ xfs_ialloc_check_shrink( goto out; if (!has) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_INOBT); error = -EFSCORRUPTED; goto out; } @@ -2964,6 +3196,5 @@ xfs_ialloc_check_shrink( } out: xfs_btree_del_cursor(cur, error); - xfs_perag_put(pag); return error; } diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index 9bbbca6ac4ed..3a1323155a45 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -12,6 +12,7 @@ struct xfs_imap; struct xfs_mount; struct xfs_trans; struct xfs_btree_cur; +struct xfs_perag; /* Move inodes in clusters of this size */ #define XFS_INODE_BIG_CLUSTER_SIZE 8192 @@ -32,11 +33,13 @@ xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o) return xfs_buf_offset(b, o << (mp)->m_sb.sb_inodelog); } +struct xfs_icreate_args; + /* * Allocate an inode on disk. Mode is used to tell whether the new inode will * need space, and whether it is a directory. */ -int xfs_dialloc(struct xfs_trans **tpp, xfs_ino_t parent, umode_t mode, +int xfs_dialloc(struct xfs_trans **tpp, const struct xfs_icreate_args *args, xfs_ino_t *new_ino); int xfs_difree(struct xfs_trans *tp, struct xfs_perag *pag, @@ -47,7 +50,7 @@ int xfs_difree(struct xfs_trans *tp, struct xfs_perag *pag, */ int xfs_imap( - struct xfs_mount *mp, /* file system mount structure */ + struct xfs_perag *pag, struct xfs_trans *tp, /* transaction pointer */ xfs_ino_t ino, /* inode to locate */ struct xfs_imap *imap, /* location map structure */ @@ -62,10 +65,11 @@ xfs_ialloc_log_agi( struct xfs_buf *bp, /* allocation group header buffer */ uint32_t fields); /* bitmask of fields to log */ -int xfs_read_agi(struct xfs_perag *pag, struct xfs_trans *tp, +int xfs_read_agi(struct xfs_perag *pag, struct xfs_trans *tp, xfs_buf_flags_t flags, struct xfs_buf **agibpp); int xfs_ialloc_read_agi(struct xfs_perag *pag, struct xfs_trans *tp, - struct xfs_buf **agibpp); + int flags, struct xfs_buf **agibpp); +#define XFS_IALLOC_FLAG_TRYLOCK (1U << 0) /* use trylock for buffer locking */ /* * Lookup a record by ino in the btree given by cur. @@ -78,6 +82,7 @@ int xfs_inobt_lookup(struct xfs_btree_cur *cur, xfs_agino_t ino, */ int xfs_inobt_get_rec(struct xfs_btree_cur *cur, xfs_inobt_rec_incore_t *rec, int *stat); +uint8_t xfs_inobt_rec_freecount(const struct xfs_inobt_rec_incore *irec); /* * Inode chunk initialisation routine @@ -92,10 +97,11 @@ union xfs_btree_rec; void xfs_inobt_btrec_to_irec(struct xfs_mount *mp, const union xfs_btree_rec *rec, struct xfs_inobt_rec_incore *irec); +xfs_failaddr_t xfs_inobt_check_irec(struct xfs_perag *pag, + const struct xfs_inobt_rec_incore *irec); int xfs_ialloc_has_inodes_at_extent(struct xfs_btree_cur *cur, - xfs_agblock_t bno, xfs_extlen_t len, bool *exists); -int xfs_ialloc_has_inode_record(struct xfs_btree_cur *cur, xfs_agino_t low, - xfs_agino_t high, bool *exists); + xfs_agblock_t bno, xfs_extlen_t len, + enum xbtree_recpacking *outcome); int xfs_ialloc_count_inodes(struct xfs_btree_cur *cur, xfs_agino_t *count, xfs_agino_t *freecount); int xfs_inobt_insert_rec(struct xfs_btree_cur *cur, uint16_t holemask, @@ -106,7 +112,7 @@ int xfs_ialloc_cluster_alignment(struct xfs_mount *mp); void xfs_ialloc_setup_geometry(struct xfs_mount *mp); xfs_ino_t xfs_ialloc_calc_rootino(struct xfs_mount *mp, int sunit); -int xfs_ialloc_check_shrink(struct xfs_trans *tp, xfs_agnumber_t agno, +int xfs_ialloc_check_shrink(struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agibp, xfs_agblock_t new_length); #endif /* __XFS_IALLOC_H__ */ diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 8c83e265770c..100afdd66cdd 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -17,6 +17,7 @@ #include "xfs_ialloc_btree.h" #include "xfs_alloc.h" #include "xfs_error.h" +#include "xfs_health.h" #include "xfs_trace.h" #include "xfs_trans.h" #include "xfs_rmap.h" @@ -36,8 +37,16 @@ STATIC struct xfs_btree_cur * xfs_inobt_dup_cursor( struct xfs_btree_cur *cur) { - return xfs_inobt_init_cursor(cur->bc_mp, cur->bc_tp, - cur->bc_ag.agbp, cur->bc_ag.pag, cur->bc_btnum); + return xfs_inobt_init_cursor(to_perag(cur->bc_group), cur->bc_tp, + cur->bc_ag.agbp); +} + +STATIC struct xfs_btree_cur * +xfs_finobt_dup_cursor( + struct xfs_btree_cur *cur) +{ + return xfs_finobt_init_cursor(to_perag(cur->bc_group), cur->bc_tp, + cur->bc_ag.agbp); } STATIC void @@ -81,9 +90,9 @@ xfs_inobt_mod_blockcount( if (!xfs_has_inobtcounts(cur->bc_mp)) return; - if (cur->bc_btnum == XFS_BTNUM_FINO) + if (xfs_btree_is_fino(cur->bc_ops)) be32_add_cpu(&agi->agi_fblocks, howmuch); - else if (cur->bc_btnum == XFS_BTNUM_INO) + else be32_add_cpu(&agi->agi_iblocks, howmuch); xfs_ialloc_log_agi(cur->bc_tp, agbp, XFS_AGI_IBLOCKS); } @@ -103,15 +112,15 @@ __xfs_inobt_alloc_block( memset(&args, 0, sizeof(args)); args.tp = cur->bc_tp; args.mp = cur->bc_mp; + args.pag = to_perag(cur->bc_group); args.oinfo = XFS_RMAP_OINFO_INOBT; - args.fsbno = XFS_AGB_TO_FSB(args.mp, cur->bc_ag.pag->pag_agno, sbno); args.minlen = 1; args.maxlen = 1; args.prod = 1; - args.type = XFS_ALLOCTYPE_NEAR_BNO; args.resv = resv; - error = xfs_alloc_vextent(&args); + error = xfs_alloc_vextent_near_bno(&args, + xfs_agbno_to_fsb(args.pag, sbno)); if (error) return error; @@ -156,10 +165,12 @@ __xfs_inobt_free_block( struct xfs_buf *bp, enum xfs_ag_resv_type resv) { + xfs_fsblock_t fsbno; + xfs_inobt_mod_blockcount(cur, -1); - return xfs_free_extent(cur->bc_tp, - XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp)), 1, - &XFS_RMAP_OINFO_INOBT, resv); + fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp)); + return xfs_free_extent_later(cur->bc_tp, fsbno, 1, + &XFS_RMAP_OINFO_INOBT, resv, 0); } STATIC int @@ -237,7 +248,7 @@ xfs_inobt_init_ptr_from_cur( { struct xfs_agi *agi = cur->bc_ag.agbp->b_addr; - ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agi->agi_seqno)); + ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agi->agi_seqno)); ptr->s = agi->agi_root; } @@ -249,27 +260,31 @@ xfs_finobt_init_ptr_from_cur( { struct xfs_agi *agi = cur->bc_ag.agbp->b_addr; - ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agi->agi_seqno)); + ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agi->agi_seqno)); + ptr->s = agi->agi_free_root; } -STATIC int64_t -xfs_inobt_key_diff( +STATIC int +xfs_inobt_cmp_key_with_cur( struct xfs_btree_cur *cur, const union xfs_btree_key *key) { - return (int64_t)be32_to_cpu(key->inobt.ir_startino) - - cur->bc_rec.i.ir_startino; + return cmp_int(be32_to_cpu(key->inobt.ir_startino), + cur->bc_rec.i.ir_startino); } -STATIC int64_t -xfs_inobt_diff_two_keys( +STATIC int +xfs_inobt_cmp_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { - return (int64_t)be32_to_cpu(k1->inobt.ir_startino) - - be32_to_cpu(k2->inobt.ir_startino); + ASSERT(!mask || mask->inobt.ir_startino); + + return cmp_int(be32_to_cpu(k1->inobt.ir_startino), + be32_to_cpu(k2->inobt.ir_startino)); } static xfs_failaddr_t @@ -291,11 +306,11 @@ xfs_inobt_verify( * Similarly, during log recovery we will have a perag structure * attached, but the agi information will not yet have been initialised * from the on disk AGI. We don't currently use any of this information, - * but beware of the landmine (i.e. need to check pag->pagi_init) if we - * ever do. + * but beware of the landmine (i.e. need to check + * xfs_perag_initialised_agi(pag)) if we ever do. */ if (xfs_has_crc(mp)) { - fa = xfs_btree_sblock_v5hdr_verify(bp); + fa = xfs_btree_agblock_v5hdr_verify(bp); if (fa) return fa; } @@ -305,7 +320,7 @@ xfs_inobt_verify( if (level >= M_IGEO(mp)->inobt_maxlevels) return __this_address; - return xfs_btree_sblock_verify(bp, + return xfs_btree_agblock_verify(bp, M_IGEO(mp)->inobt_mxr[level != 0]); } @@ -315,7 +330,7 @@ xfs_inobt_read_verify( { xfs_failaddr_t fa; - if (!xfs_btree_sblock_verify_crc(bp)) + if (!xfs_btree_agblock_verify_crc(bp)) xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_inobt_verify(bp); @@ -339,7 +354,7 @@ xfs_inobt_write_verify( xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } - xfs_btree_sblock_calc_crc(bp); + xfs_btree_agblock_calc_crc(bp); } @@ -380,9 +395,30 @@ xfs_inobt_recs_inorder( be32_to_cpu(r2->inobt.ir_startino); } -static const struct xfs_btree_ops xfs_inobt_ops = { +STATIC enum xbtree_key_contig +xfs_inobt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->inobt.ir_startino); + + return xbtree_key_contig(be32_to_cpu(key1->inobt.ir_startino), + be32_to_cpu(key2->inobt.ir_startino)); +} + +const struct xfs_btree_ops xfs_inobt_ops = { + .name = "ino", + .type = XFS_BTREE_TYPE_AG, + .rec_len = sizeof(xfs_inobt_rec_t), .key_len = sizeof(xfs_inobt_key_t), + .ptr_len = XFS_BTREE_SHORT_PTR_LEN, + + .lru_refs = XFS_INO_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_ibt_2), + .sick_mask = XFS_SICK_AG_INOBT, .dup_cursor = xfs_inobt_dup_cursor, .set_root = xfs_inobt_set_root, @@ -394,18 +430,27 @@ static const struct xfs_btree_ops xfs_inobt_ops = { .init_high_key_from_rec = xfs_inobt_init_high_key_from_rec, .init_rec_from_cur = xfs_inobt_init_rec_from_cur, .init_ptr_from_cur = xfs_inobt_init_ptr_from_cur, - .key_diff = xfs_inobt_key_diff, + .cmp_key_with_cur = xfs_inobt_cmp_key_with_cur, .buf_ops = &xfs_inobt_buf_ops, - .diff_two_keys = xfs_inobt_diff_two_keys, + .cmp_two_keys = xfs_inobt_cmp_two_keys, .keys_inorder = xfs_inobt_keys_inorder, .recs_inorder = xfs_inobt_recs_inorder, + .keys_contiguous = xfs_inobt_keys_contiguous, }; -static const struct xfs_btree_ops xfs_finobt_ops = { +const struct xfs_btree_ops xfs_finobt_ops = { + .name = "fino", + .type = XFS_BTREE_TYPE_AG, + .rec_len = sizeof(xfs_inobt_rec_t), .key_len = sizeof(xfs_inobt_key_t), + .ptr_len = XFS_BTREE_SHORT_PTR_LEN, - .dup_cursor = xfs_inobt_dup_cursor, + .lru_refs = XFS_INO_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_fibt_2), + .sick_mask = XFS_SICK_AG_FINOBT, + + .dup_cursor = xfs_finobt_dup_cursor, .set_root = xfs_finobt_set_root, .alloc_block = xfs_finobt_alloc_block, .free_block = xfs_finobt_free_block, @@ -415,77 +460,63 @@ static const struct xfs_btree_ops xfs_finobt_ops = { .init_high_key_from_rec = xfs_inobt_init_high_key_from_rec, .init_rec_from_cur = xfs_inobt_init_rec_from_cur, .init_ptr_from_cur = xfs_finobt_init_ptr_from_cur, - .key_diff = xfs_inobt_key_diff, + .cmp_key_with_cur = xfs_inobt_cmp_key_with_cur, .buf_ops = &xfs_finobt_buf_ops, - .diff_two_keys = xfs_inobt_diff_two_keys, + .cmp_two_keys = xfs_inobt_cmp_two_keys, .keys_inorder = xfs_inobt_keys_inorder, .recs_inorder = xfs_inobt_recs_inorder, + .keys_contiguous = xfs_inobt_keys_contiguous, }; /* - * Initialize a new inode btree cursor. + * Create an inode btree cursor. + * + * For staging cursors tp and agbp are NULL. */ -static struct xfs_btree_cur * -xfs_inobt_init_common( - struct xfs_mount *mp, /* file system mount point */ - struct xfs_trans *tp, /* transaction pointer */ +struct xfs_btree_cur * +xfs_inobt_init_cursor( struct xfs_perag *pag, - xfs_btnum_t btnum) /* ialloc or free ino btree */ + struct xfs_trans *tp, + struct xfs_buf *agbp) { + struct xfs_mount *mp = pag_mount(pag); struct xfs_btree_cur *cur; - cur = xfs_btree_alloc_cursor(mp, tp, btnum, + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_inobt_ops, M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache); - if (btnum == XFS_BTNUM_INO) { - cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_ibt_2); - cur->bc_ops = &xfs_inobt_ops; - } else { - cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_fibt_2); - cur->bc_ops = &xfs_finobt_ops; - } - - if (xfs_has_crc(mp)) - cur->bc_flags |= XFS_BTREE_CRC_BLOCKS; + cur->bc_group = xfs_group_hold(pag_group(pag)); + cur->bc_ag.agbp = agbp; + if (agbp) { + struct xfs_agi *agi = agbp->b_addr; - /* take a reference for the cursor */ - atomic_inc(&pag->pag_ref); - cur->bc_ag.pag = pag; + cur->bc_nlevels = be32_to_cpu(agi->agi_level); + } return cur; } -/* Create an inode btree cursor. */ +/* + * Create a free inode btree cursor. + * + * For staging cursors tp and agbp are NULL. + */ struct xfs_btree_cur * -xfs_inobt_init_cursor( - struct xfs_mount *mp, - struct xfs_trans *tp, - struct xfs_buf *agbp, +xfs_finobt_init_cursor( struct xfs_perag *pag, - xfs_btnum_t btnum) + struct xfs_trans *tp, + struct xfs_buf *agbp) { + struct xfs_mount *mp = pag_mount(pag); struct xfs_btree_cur *cur; - struct xfs_agi *agi = agbp->b_addr; - cur = xfs_inobt_init_common(mp, tp, pag, btnum); - if (btnum == XFS_BTNUM_INO) - cur->bc_nlevels = be32_to_cpu(agi->agi_level); - else - cur->bc_nlevels = be32_to_cpu(agi->agi_free_level); + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_finobt_ops, + M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache); + cur->bc_group = xfs_group_hold(pag_group(pag)); cur->bc_ag.agbp = agbp; - return cur; -} + if (agbp) { + struct xfs_agi *agi = agbp->b_addr; -/* Create an inode btree cursor with a fake root for staging. */ -struct xfs_btree_cur * -xfs_inobt_stage_cursor( - struct xfs_mount *mp, - struct xbtree_afakeroot *afake, - struct xfs_perag *pag, - xfs_btnum_t btnum) -{ - struct xfs_btree_cur *cur; - - cur = xfs_inobt_init_common(mp, NULL, pag, btnum); - xfs_btree_stage_afakeroot(cur, afake); + cur->bc_nlevels = be32_to_cpu(agi->agi_free_level); + } return cur; } @@ -505,7 +536,7 @@ xfs_inobt_commit_staged_btree( ASSERT(cur->bc_flags & XFS_BTREE_STAGING); - if (cur->bc_btnum == XFS_BTNUM_INO) { + if (xfs_btree_is_ino(cur->bc_ops)) { fields = XFS_AGI_ROOT | XFS_AGI_LEVEL; agi->agi_root = cpu_to_be32(afake->af_root); agi->agi_level = cpu_to_be32(afake->af_levels); @@ -514,7 +545,7 @@ xfs_inobt_commit_staged_btree( fields |= XFS_AGI_IBLOCKS; } xfs_ialloc_log_agi(tp, agbp, fields); - xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_inobt_ops); + xfs_btree_commit_afakeroot(cur, tp, agbp); } else { fields = XFS_AGI_FREE_ROOT | XFS_AGI_FREE_LEVEL; agi->agi_free_root = cpu_to_be32(afake->af_root); @@ -524,7 +555,7 @@ xfs_inobt_commit_staged_btree( fields |= XFS_AGI_IBLOCKS; } xfs_ialloc_log_agi(tp, agbp, fields); - xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_finobt_ops); + xfs_btree_commit_afakeroot(cur, tp, agbp); } } @@ -542,11 +573,11 @@ xfs_inobt_block_maxrecs( /* * Calculate number of records in an inobt btree block. */ -int +unsigned int xfs_inobt_maxrecs( struct xfs_mount *mp, - int blocklen, - int leaf) + unsigned int blocklen, + bool leaf) { blocklen -= XFS_INOBT_BLOCK_LEN(mp); return xfs_inobt_block_maxrecs(blocklen, leaf); @@ -609,7 +640,7 @@ xfs_iallocbt_maxlevels_ondisk(void) */ uint64_t xfs_inobt_irec_to_allocmask( - struct xfs_inobt_rec_incore *rec) + const struct xfs_inobt_rec_incore *rec) { uint64_t bitmap = 0; uint64_t inodespbit; @@ -685,8 +716,8 @@ static xfs_extlen_t xfs_inobt_max_size( struct xfs_perag *pag) { - struct xfs_mount *mp = pag->pag_mount; - xfs_agblock_t agblocks = pag->block_count; + struct xfs_mount *mp = pag_mount(pag); + xfs_agblock_t agblocks = pag_group(pag)->xg_block_count; /* Bail out if we're uninitialized, which can happen in mkfs. */ if (M_IGEO(mp)->inobt_mxr[0] == 0) @@ -697,7 +728,7 @@ xfs_inobt_max_size( * never be available for the kinds of things that would require btree * expansion. We therefore can pretend the space isn't there. */ - if (xfs_ag_contains_log(mp, pag->pag_agno)) + if (xfs_ag_contains_log(mp, pag_agno(pag))) agblocks -= mp->m_sb.sb_logblocks; return xfs_btree_calc_size(M_IGEO(mp)->inobt_mnr, @@ -705,50 +736,26 @@ xfs_inobt_max_size( XFS_INODES_PER_CHUNK); } -/* Read AGI and create inobt cursor. */ -int -xfs_inobt_cur( - struct xfs_mount *mp, - struct xfs_trans *tp, - struct xfs_perag *pag, - xfs_btnum_t which, - struct xfs_btree_cur **curpp, - struct xfs_buf **agi_bpp) -{ - struct xfs_btree_cur *cur; - int error; - - ASSERT(*agi_bpp == NULL); - ASSERT(*curpp == NULL); - - error = xfs_ialloc_read_agi(pag, tp, agi_bpp); - if (error) - return error; - - cur = xfs_inobt_init_cursor(mp, tp, *agi_bpp, pag, which); - *curpp = cur; - return 0; -} - static int -xfs_inobt_count_blocks( - struct xfs_mount *mp, - struct xfs_trans *tp, +xfs_finobt_count_blocks( struct xfs_perag *pag, - xfs_btnum_t btnum, + struct xfs_trans *tp, xfs_extlen_t *tree_blocks) { struct xfs_buf *agbp = NULL; - struct xfs_btree_cur *cur = NULL; + struct xfs_btree_cur *cur; + xfs_filblks_t blocks; int error; - error = xfs_inobt_cur(mp, tp, pag, btnum, &cur, &agbp); + error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); if (error) return error; - error = xfs_btree_count_blocks(cur, tree_blocks); + cur = xfs_finobt_init_cursor(pag, tp, agbp); + error = xfs_btree_count_blocks(cur, &blocks); xfs_btree_del_cursor(cur, error); xfs_trans_brelse(tp, agbp); + *tree_blocks = blocks; return error; } @@ -764,7 +771,7 @@ xfs_finobt_read_blocks( struct xfs_agi *agi; int error; - error = xfs_ialloc_read_agi(pag, tp, &agbp); + error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); if (error) return error; @@ -779,23 +786,21 @@ xfs_finobt_read_blocks( */ int xfs_finobt_calc_reserves( - struct xfs_mount *mp, - struct xfs_trans *tp, struct xfs_perag *pag, + struct xfs_trans *tp, xfs_extlen_t *ask, xfs_extlen_t *used) { xfs_extlen_t tree_len = 0; int error; - if (!xfs_has_finobt(mp)) + if (!xfs_has_finobt(pag_mount(pag))) return 0; - if (xfs_has_inobtcounts(mp)) + if (xfs_has_inobtcounts(pag_mount(pag))) error = xfs_finobt_read_blocks(pag, tp, &tree_len); else - error = xfs_inobt_count_blocks(mp, tp, pag, XFS_BTNUM_FINO, - &tree_len); + error = xfs_finobt_count_blocks(pag, tp, &tree_len); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h index 26451cb76b98..300edf5bc009 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.h +++ b/fs/xfs/libxfs/xfs_ialloc_btree.h @@ -46,16 +46,15 @@ struct xfs_perag; (maxrecs) * sizeof(xfs_inobt_key_t) + \ ((index) - 1) * sizeof(xfs_inobt_ptr_t))) -extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_mount *mp, - struct xfs_trans *tp, struct xfs_buf *agbp, - struct xfs_perag *pag, xfs_btnum_t btnum); -struct xfs_btree_cur *xfs_inobt_stage_cursor(struct xfs_mount *mp, - struct xbtree_afakeroot *afake, struct xfs_perag *pag, - xfs_btnum_t btnum); -extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int); +struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_perag *pag, + struct xfs_trans *tp, struct xfs_buf *agbp); +struct xfs_btree_cur *xfs_finobt_init_cursor(struct xfs_perag *pag, + struct xfs_trans *tp, struct xfs_buf *agbp); +unsigned int xfs_inobt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, + bool leaf); /* ir_holemask to inode allocation bitmap conversion */ -uint64_t xfs_inobt_irec_to_allocmask(struct xfs_inobt_rec_incore *); +uint64_t xfs_inobt_irec_to_allocmask(const struct xfs_inobt_rec_incore *irec); #if defined(DEBUG) || defined(XFS_WARN) int xfs_inobt_rec_check_count(struct xfs_mount *, @@ -64,13 +63,10 @@ int xfs_inobt_rec_check_count(struct xfs_mount *, #define xfs_inobt_rec_check_count(mp, rec) 0 #endif /* DEBUG */ -int xfs_finobt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp, - struct xfs_perag *pag, xfs_extlen_t *ask, xfs_extlen_t *used); +int xfs_finobt_calc_reserves(struct xfs_perag *perag, struct xfs_trans *tp, + xfs_extlen_t *ask, xfs_extlen_t *used); extern xfs_extlen_t xfs_iallocbt_calc_size(struct xfs_mount *mp, unsigned long long len); -int xfs_inobt_cur(struct xfs_mount *mp, struct xfs_trans *tp, - struct xfs_perag *pag, xfs_btnum_t btnum, - struct xfs_btree_cur **curpp, struct xfs_buf **agi_bpp); void xfs_inobt_commit_staged_btree(struct xfs_btree_cur *cur, struct xfs_trans *tp, struct xfs_buf *agbp); diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c index 773cf4349428..8796f2b3e534 100644 --- a/fs/xfs/libxfs/xfs_iext_tree.c +++ b/fs/xfs/libxfs/xfs_iext_tree.c @@ -158,7 +158,7 @@ static void * xfs_iext_find_first_leaf( struct xfs_ifork *ifp) { - struct xfs_iext_node *node = ifp->if_u1.if_root; + struct xfs_iext_node *node = ifp->if_data; int height; if (!ifp->if_height) @@ -176,7 +176,7 @@ static void * xfs_iext_find_last_leaf( struct xfs_ifork *ifp) { - struct xfs_iext_node *node = ifp->if_u1.if_root; + struct xfs_iext_node *node = ifp->if_data; int height, i; if (!ifp->if_height) @@ -306,7 +306,7 @@ xfs_iext_find_level( xfs_fileoff_t offset, int level) { - struct xfs_iext_node *node = ifp->if_u1.if_root; + struct xfs_iext_node *node = ifp->if_data; int height, i; if (!ifp->if_height) @@ -394,20 +394,27 @@ xfs_iext_leaf_key( return leaf->recs[n].lo & XFS_IEXT_STARTOFF_MASK; } +static inline void * +xfs_iext_alloc_node( + int size) +{ + return kzalloc(size, GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); +} + static void xfs_iext_grow( struct xfs_ifork *ifp) { - struct xfs_iext_node *node = kmem_zalloc(NODE_SIZE, KM_NOFS); + struct xfs_iext_node *node = xfs_iext_alloc_node(NODE_SIZE); int i; if (ifp->if_height == 1) { - struct xfs_iext_leaf *prev = ifp->if_u1.if_root; + struct xfs_iext_leaf *prev = ifp->if_data; node->keys[0] = xfs_iext_leaf_key(prev, 0); node->ptrs[0] = prev; } else { - struct xfs_iext_node *prev = ifp->if_u1.if_root; + struct xfs_iext_node *prev = ifp->if_data; ASSERT(ifp->if_height > 1); @@ -418,7 +425,7 @@ xfs_iext_grow( for (i = 1; i < KEYS_PER_NODE; i++) node->keys[i] = XFS_IEXT_KEY_INVALID; - ifp->if_u1.if_root = node; + ifp->if_data = node; ifp->if_height++; } @@ -430,7 +437,7 @@ xfs_iext_update_node( int level, void *ptr) { - struct xfs_iext_node *node = ifp->if_u1.if_root; + struct xfs_iext_node *node = ifp->if_data; int height, i; for (height = ifp->if_height; height > level; height--) { @@ -454,7 +461,7 @@ xfs_iext_split_node( int *nr_entries) { struct xfs_iext_node *node = *nodep; - struct xfs_iext_node *new = kmem_zalloc(NODE_SIZE, KM_NOFS); + struct xfs_iext_node *new = xfs_iext_alloc_node(NODE_SIZE); const int nr_move = KEYS_PER_NODE / 2; int nr_keep = nr_move + (KEYS_PER_NODE & 1); int i = 0; @@ -542,7 +549,7 @@ xfs_iext_split_leaf( int *nr_entries) { struct xfs_iext_leaf *leaf = cur->leaf; - struct xfs_iext_leaf *new = kmem_zalloc(NODE_SIZE, KM_NOFS); + struct xfs_iext_leaf *new = xfs_iext_alloc_node(NODE_SIZE); const int nr_move = RECS_PER_LEAF / 2; int nr_keep = nr_move + (RECS_PER_LEAF & 1); int i; @@ -583,11 +590,11 @@ xfs_iext_alloc_root( { ASSERT(ifp->if_bytes == 0); - ifp->if_u1.if_root = kmem_zalloc(sizeof(struct xfs_iext_rec), KM_NOFS); + ifp->if_data = xfs_iext_alloc_node(sizeof(struct xfs_iext_rec)); ifp->if_height = 1; /* now that we have a node step into it */ - cur->leaf = ifp->if_u1.if_root; + cur->leaf = ifp->if_data; cur->pos = 0; } @@ -603,9 +610,10 @@ xfs_iext_realloc_root( if (new_size / sizeof(struct xfs_iext_rec) == RECS_PER_LEAF) new_size = NODE_SIZE; - new = krealloc(ifp->if_u1.if_root, new_size, GFP_NOFS | __GFP_NOFAIL); + new = krealloc(ifp->if_data, new_size, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); memset(new + ifp->if_bytes, 0, new_size - ifp->if_bytes); - ifp->if_u1.if_root = new; + ifp->if_data = new; cur->leaf = new; } @@ -622,13 +630,11 @@ static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp) } void -xfs_iext_insert( - struct xfs_inode *ip, +xfs_iext_insert_raw( + struct xfs_ifork *ifp, struct xfs_iext_cursor *cur, - struct xfs_bmbt_irec *irec, - int state) + struct xfs_bmbt_irec *irec) { - struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state); xfs_fileoff_t offset = irec->br_startoff; struct xfs_iext_leaf *new = NULL; int nr_entries, i; @@ -662,12 +668,23 @@ xfs_iext_insert( xfs_iext_set(cur_rec(cur), irec); ifp->if_bytes += sizeof(struct xfs_iext_rec); - trace_xfs_iext_insert(ip, cur, state, _RET_IP_); - if (new) xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2); } +void +xfs_iext_insert( + struct xfs_inode *ip, + struct xfs_iext_cursor *cur, + struct xfs_bmbt_irec *irec, + int state) +{ + struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state); + + xfs_iext_insert_raw(ifp, cur, irec); + trace_xfs_iext_insert(ip, cur, state, _RET_IP_); +} + static struct xfs_iext_node * xfs_iext_rebalance_node( struct xfs_iext_node *parent, @@ -734,7 +751,7 @@ xfs_iext_remove_node( again: ASSERT(node->ptrs[pos]); ASSERT(node->ptrs[pos] == victim); - kmem_free(victim); + kfree(victim); nr_entries = xfs_iext_node_nr_entries(node, pos) - 1; offset = node->keys[0]; @@ -777,10 +794,10 @@ again: * If we are at the root and only one entry is left we can just * free this node and update the root pointer. */ - ASSERT(node == ifp->if_u1.if_root); - ifp->if_u1.if_root = node->ptrs[0]; + ASSERT(node == ifp->if_data); + ifp->if_data = node->ptrs[0]; ifp->if_height--; - kmem_free(node); + kfree(node); } } @@ -854,8 +871,8 @@ xfs_iext_free_last_leaf( struct xfs_ifork *ifp) { ifp->if_height--; - kmem_free(ifp->if_u1.if_root); - ifp->if_u1.if_root = NULL; + kfree(ifp->if_data); + ifp->if_data = NULL; } void @@ -872,7 +889,7 @@ xfs_iext_remove( trace_xfs_iext_remove(ip, cur, state, _RET_IP_); ASSERT(ifp->if_height > 0); - ASSERT(ifp->if_u1.if_root != NULL); + ASSERT(ifp->if_data != NULL); ASSERT(xfs_iext_valid(ifp, cur)); xfs_iext_inc_seq(ifp); @@ -1035,16 +1052,16 @@ xfs_iext_destroy_node( } } - kmem_free(node); + kfree(node); } void xfs_iext_destroy( struct xfs_ifork *ifp) { - xfs_iext_destroy_node(ifp->if_u1.if_root, ifp->if_height); + xfs_iext_destroy_node(ifp->if_data, ifp->if_height); ifp->if_bytes = 0; ifp->if_height = 0; - ifp->if_u1.if_root = NULL; + ifp->if_data = NULL; } diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 758aacd8166b..b1812b2c3cce 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -18,6 +18,8 @@ #include "xfs_trans.h" #include "xfs_ialloc.h" #include "xfs_dir2.h" +#include "xfs_health.h" +#include "xfs_metafile.h" #include <linux/iversion.h> @@ -59,8 +61,8 @@ xfs_inode_buf_verify( di_ok = xfs_verify_magic16(bp, dip->di_magic) && xfs_dinode_good_version(mp, dip->di_version) && xfs_verify_agino_or_null(bp->b_pag, unlinked_ino); - if (unlikely(XFS_TEST_ERROR(!di_ok, mp, - XFS_ERRTAG_ITOBP_INOTOBP))) { + if (unlikely(!di_ok || + XFS_TEST_ERROR(mp, XFS_ERRTAG_ITOBP_INOTOBP))) { if (readahead) { bp->b_flags &= ~XBF_DONE; xfs_buf_ioerror(bp, -EIO); @@ -132,9 +134,14 @@ xfs_imap_to_bp( struct xfs_imap *imap, struct xfs_buf **bpp) { - return xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno, - imap->im_len, XBF_UNMAPPED, bpp, - &xfs_inode_buf_ops); + int error; + + error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno, + imap->im_len, 0, bpp, &xfs_inode_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno), + XFS_SICK_AG_INODES); + return error; } static inline struct timespec64 xfs_inode_decode_bigtime(uint64_t ts) @@ -203,12 +210,15 @@ xfs_inode_from_disk( * They will also be unconditionally written back to disk as v2 inodes. */ if (unlikely(from->di_version == 1)) { - set_nlink(inode, be16_to_cpu(from->di_onlink)); + /* di_metatype used to be di_onlink */ + set_nlink(inode, be16_to_cpu(from->di_metatype)); ip->i_projid = 0; } else { set_nlink(inode, be32_to_cpu(from->di_nlink)); ip->i_projid = (prid_t)be16_to_cpu(from->di_projid_hi) << 16 | be16_to_cpu(from->di_projid_lo); + if (xfs_dinode_is_metadir(from)) + ip->i_metatype = be16_to_cpu(from->di_metatype); } i_uid_write(inode, be32_to_cpu(from->di_uid)); @@ -220,9 +230,12 @@ xfs_inode_from_disk( * a time before epoch is converted to a time long after epoch * on 64 bit systems. */ - inode->i_atime = xfs_inode_from_disk_ts(from, from->di_atime); - inode->i_mtime = xfs_inode_from_disk_ts(from, from->di_mtime); - inode->i_ctime = xfs_inode_from_disk_ts(from, from->di_ctime); + inode_set_atime_to_ts(inode, + xfs_inode_from_disk_ts(from, from->di_atime)); + inode_set_mtime_to_ts(inode, + xfs_inode_from_disk_ts(from, from->di_mtime)); + inode_set_ctime_to_ts(inode, + xfs_inode_from_disk_ts(from, from->di_ctime)); ip->i_disk_size = be64_to_cpu(from->di_size); ip->i_nblocks = be64_to_cpu(from->di_nblocks); @@ -239,7 +252,10 @@ xfs_inode_from_disk( be64_to_cpu(from->di_changecount)); ip->i_crtime = xfs_inode_from_disk_ts(from, from->di_crtime); ip->i_diflags2 = be64_to_cpu(from->di_flags2); + /* also covers the di_used_blocks union arm: */ ip->i_cowextsize = be32_to_cpu(from->di_cowextsize); + BUILD_BUG_ON(sizeof(from->di_cowextsize) != + sizeof(from->di_used_blocks)); } error = xfs_iformat_data_fork(ip, from); @@ -306,7 +322,10 @@ xfs_inode_to_disk( struct inode *inode = VFS_I(ip); to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC); - to->di_onlink = 0; + if (xfs_is_metadir_inode(ip)) + to->di_metatype = cpu_to_be16(ip->i_metatype); + else + to->di_metatype = 0; to->di_format = xfs_ifork_format(&ip->i_df); to->di_uid = cpu_to_be32(i_uid_read(inode)); @@ -314,9 +333,9 @@ xfs_inode_to_disk( to->di_projid_lo = cpu_to_be16(ip->i_projid & 0xffff); to->di_projid_hi = cpu_to_be16(ip->i_projid >> 16); - to->di_atime = xfs_inode_to_disk_ts(ip, inode->i_atime); - to->di_mtime = xfs_inode_to_disk_ts(ip, inode->i_mtime); - to->di_ctime = xfs_inode_to_disk_ts(ip, inode->i_ctime); + to->di_atime = xfs_inode_to_disk_ts(ip, inode_get_atime(inode)); + to->di_mtime = xfs_inode_to_disk_ts(ip, inode_get_mtime(inode)); + to->di_ctime = xfs_inode_to_disk_ts(ip, inode_get_ctime(inode)); to->di_nlink = cpu_to_be32(inode->i_nlink); to->di_gen = cpu_to_be32(inode->i_generation); to->di_mode = cpu_to_be16(inode->i_mode); @@ -333,6 +352,7 @@ xfs_inode_to_disk( to->di_changecount = cpu_to_be64(inode_peek_iversion(inode)); to->di_crtime = xfs_inode_to_disk_ts(ip, ip->i_crtime); to->di_flags2 = cpu_to_be64(ip->i_diflags2); + /* also covers the di_used_blocks union arm: */ to->di_cowextsize = cpu_to_be32(ip->i_cowextsize); to->di_ino = cpu_to_be64(ip->i_ino); to->di_lsn = cpu_to_be64(lsn); @@ -365,17 +385,40 @@ xfs_dinode_verify_fork( /* * For fork types that can contain local data, check that the fork * format matches the size of local data contained within the fork. - * - * For all types, check that when the size says the should be in extent - * or btree format, the inode isn't claiming it is in local format. */ if (whichfork == XFS_DATA_FORK) { - if (S_ISDIR(mode) || S_ISLNK(mode)) { + /* + * A directory small enough to fit in the inode must be stored + * in local format. The directory sf <-> extents conversion + * code updates the directory size accordingly. Directories + * being truncated have zero size and are not subject to this + * check. + */ + if (S_ISDIR(mode)) { + if (dip->di_size && + be64_to_cpu(dip->di_size) <= fork_size && + fork_format != XFS_DINODE_FMT_LOCAL) + return __this_address; + } + + /* + * A symlink with a target small enough to fit in the inode can + * be stored in extents format if xattrs were added (thus + * converting the data fork from shortform to remote format) + * and then removed. + */ + if (S_ISLNK(mode)) { if (be64_to_cpu(dip->di_size) <= fork_size && + fork_format != XFS_DINODE_FMT_EXTENTS && fork_format != XFS_DINODE_FMT_LOCAL) return __this_address; } + /* + * For all types, check that when the size says the fork should + * be in extent or btree format, the inode isn't claiming to be + * in local format. + */ if (be64_to_cpu(dip->di_size) > fork_size && fork_format == XFS_DINODE_FMT_LOCAL) return __this_address; @@ -402,6 +445,30 @@ xfs_dinode_verify_fork( if (di_nextents > max_extents) return __this_address; break; + case XFS_DINODE_FMT_META_BTREE: + if (!xfs_has_metadir(mp)) + return __this_address; + if (!(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA))) + return __this_address; + switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + /* + * growfs must create the rtrmap inodes before adding a + * realtime volume to the filesystem, so we cannot use + * the rtrmapbt predicate here. + */ + if (!xfs_has_rmapbt(mp)) + return __this_address; + break; + case XFS_METAFILE_RTREFCOUNT: + /* same comment about growfs and rmap inodes applies */ + if (!xfs_has_reflink(mp)) + return __this_address; + break; + default: + return __this_address; + } + break; default: return __this_address; } @@ -421,6 +488,10 @@ xfs_dinode_verify_forkoff( if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3)) return __this_address; break; + case XFS_DINODE_FMT_META_BTREE: + if (!xfs_has_metadir(mp) || !xfs_has_parent(mp)) + return __this_address; + fallthrough; case XFS_DINODE_FMT_LOCAL: /* fall through ... */ case XFS_DINODE_FMT_EXTENTS: /* fall through ... */ case XFS_DINODE_FMT_BTREE: @@ -451,6 +522,69 @@ xfs_dinode_verify_nrext64( return NULL; } +/* + * Validate all the picky requirements we have for a file that claims to be + * filesystem metadata. + */ +xfs_failaddr_t +xfs_dinode_verify_metadir( + struct xfs_mount *mp, + struct xfs_dinode *dip, + uint16_t mode, + uint16_t flags, + uint64_t flags2) +{ + if (!xfs_has_metadir(mp)) + return __this_address; + + /* V5 filesystem only */ + if (dip->di_version < 3) + return __this_address; + + if (be16_to_cpu(dip->di_metatype) >= XFS_METAFILE_MAX) + return __this_address; + + /* V3 inode fields that are always zero */ + if ((flags2 & XFS_DIFLAG2_NREXT64) && dip->di_nrext64_pad) + return __this_address; + if (!(flags2 & XFS_DIFLAG2_NREXT64) && dip->di_flushiter) + return __this_address; + + /* Metadata files can only be directories or regular files */ + if (!S_ISDIR(mode) && !S_ISREG(mode)) + return __this_address; + + /* They must have zero access permissions */ + if (mode & 0777) + return __this_address; + + /* DMAPI event and state masks are zero */ + if (dip->di_dmevmask || dip->di_dmstate) + return __this_address; + + /* + * User and group IDs must be zero. The project ID is used for + * grouping inodes. Metadata inodes are never accounted to quotas. + */ + if (dip->di_uid || dip->di_gid) + return __this_address; + + /* Mandatory inode flags must be set */ + if (S_ISDIR(mode)) { + if ((flags & XFS_METADIR_DIFLAGS) != XFS_METADIR_DIFLAGS) + return __this_address; + } else { + if ((flags & XFS_METAFILE_DIFLAGS) != XFS_METAFILE_DIFLAGS) + return __this_address; + } + + /* dax flags2 must not be set */ + if (flags2 & XFS_DIFLAG2_DAX) + return __this_address; + + return NULL; +} + xfs_failaddr_t xfs_dinode_verify( struct xfs_mount *mp, @@ -482,6 +616,23 @@ xfs_dinode_verify( return __this_address; } + /* + * Historical note: xfsprogs in the 3.2 era set up its incore inodes to + * have di_nlink track the link count, even if the actual filesystem + * only supported V1 inodes (i.e. di_onlink). When writing out the + * ondisk inode, it would set both the ondisk di_nlink and di_onlink to + * the the incore di_nlink value, which is why we cannot check for + * di_nlink==0 on a V1 inode. V2/3 inodes would get written out with + * di_onlink==0, so we can check that. + */ + if (dip->di_version == 2) { + if (dip->di_metatype) + return __this_address; + } else if (dip->di_version >= 3) { + if (!xfs_dinode_is_metadir(dip) && dip->di_metatype) + return __this_address; + } + /* don't allow invalid i_size */ di_size = be64_to_cpu(dip->di_size); if (di_size & (1ULL << 63)) @@ -491,9 +642,20 @@ xfs_dinode_verify( if (mode && xfs_mode_to_ftype(mode) == XFS_DIR3_FT_UNKNOWN) return __this_address; - /* No zero-length symlinks/dirs. */ - if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0) - return __this_address; + /* + * No zero-length symlinks/dirs unless they're unlinked and hence being + * inactivated. + */ + if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0) { + if (dip->di_version > 1) { + if (dip->di_nlink) + return __this_address; + } else { + /* di_metatype used to be di_onlink */ + if (dip->di_metatype) + return __this_address; + } + } fa = xfs_dinode_verify_nrext64(mp, dip); if (fa) @@ -590,20 +752,40 @@ xfs_dinode_verify( return __this_address; /* don't let reflink and realtime mix */ - if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME)) + if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME) && + !xfs_has_rtreflink(mp)) return __this_address; - /* COW extent size hint validation */ - fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize), - mode, flags, flags2); - if (fa) - return fa; + if (xfs_has_zoned(mp) && + dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP)) { + if (be32_to_cpu(dip->di_used_blocks) > mp->m_sb.sb_rgextents) + return __this_address; + } else { + /* COW extent size hint validation */ + fa = xfs_inode_validate_cowextsize(mp, + be32_to_cpu(dip->di_cowextsize), + mode, flags, flags2); + if (fa) + return fa; + } /* bigtime iflag can only happen on bigtime filesystems */ if (xfs_dinode_has_bigtime(dip) && !xfs_has_bigtime(mp)) return __this_address; + if (flags2 & XFS_DIFLAG2_METADATA) { + fa = xfs_dinode_verify_metadir(mp, dip, mode, flags, flags2); + if (fa) + return fa; + } + + /* metadata inodes containing btrees always have zero extent count */ + if (XFS_DFORK_FORMAT(dip, XFS_DATA_FORK) != XFS_DINODE_FMT_META_BTREE) { + if (nextents + naextents == 0 && nblocks != 0) + return __this_address; + } + return NULL; } @@ -739,11 +921,29 @@ xfs_inode_validate_cowextsize( bool rt_flag; bool hint_flag; uint32_t cowextsize_bytes; + uint32_t blocksize_bytes; rt_flag = (flags & XFS_DIFLAG_REALTIME); hint_flag = (flags2 & XFS_DIFLAG2_COWEXTSIZE); cowextsize_bytes = XFS_FSB_TO_B(mp, cowextsize); + /* + * Similar to extent size hints, a directory can be configured to + * propagate realtime status and a CoW extent size hint to newly + * created files even if there is no realtime device, and the hints on + * disk can become misaligned if the sysadmin changes the rt extent + * size while adding the realtime device. + * + * Therefore, we can only enforce the rextsize alignment check against + * regular realtime files, and rely on callers to decide when alignment + * checks are appropriate, and fix things up as needed. + */ + + if (rt_flag) + blocksize_bytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize); + else + blocksize_bytes = mp->m_sb.sb_blocksize; + if (hint_flag && !xfs_has_reflink(mp)) return __this_address; @@ -757,16 +957,13 @@ xfs_inode_validate_cowextsize( if (mode && !hint_flag && cowextsize != 0) return __this_address; - if (hint_flag && rt_flag) - return __this_address; - - if (cowextsize_bytes % mp->m_sb.sb_blocksize) + if (cowextsize_bytes % blocksize_bytes) return __this_address; if (cowextsize > XFS_MAX_BMBT_EXTLEN) return __this_address; - if (cowextsize > mp->m_sb.sb_agblocks / 2) + if (!rt_flag && cowextsize > mp->m_sb.sb_agblocks / 2) return __this_address; return NULL; diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index 585ed5a110af..8d43d2641c73 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -28,6 +28,9 @@ int xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from); xfs_failaddr_t xfs_dinode_verify(struct xfs_mount *mp, xfs_ino_t ino, struct xfs_dinode *dip); +xfs_failaddr_t xfs_dinode_verify_metadir(struct xfs_mount *mp, + struct xfs_dinode *dip, uint16_t mode, uint16_t flags, + uint64_t flags2); xfs_failaddr_t xfs_inode_validate_extsize(struct xfs_mount *mp, uint32_t extsize, uint16_t mode, uint16_t flags); xfs_failaddr_t xfs_inode_validate_cowextsize(struct xfs_mount *mp, diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 6b21760184d9..1772d82f2d68 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -25,6 +25,10 @@ #include "xfs_attr_leaf.h" #include "xfs_types.h" #include "xfs_errortag.h" +#include "xfs_health.h" +#include "xfs_symlink_remote.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" struct kmem_cache *xfs_ifork_cache; @@ -50,12 +54,16 @@ xfs_init_local_fork( mem_size++; if (size) { - ifp->if_u1.if_data = kmem_alloc(mem_size, KM_NOFS); - memcpy(ifp->if_u1.if_data, data, size); + char *new_data = kmalloc(mem_size, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + + memcpy(new_data, data, size); if (zero_terminate) - ifp->if_u1.if_data[size] = '\0'; + new_data[size] = '\0'; + + ifp->if_data = new_data; } else { - ifp->if_u1.if_data = NULL; + ifp->if_data = NULL; } ifp->if_bytes = size; @@ -74,7 +82,7 @@ xfs_iformat_local( /* * If the size is unreasonable, then something * is wrong and we just bail out rather than crash in - * kmem_alloc() or memcpy() below. + * kmalloc() or memcpy() below. */ if (unlikely(size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) { xfs_warn(ip->i_mount, @@ -84,6 +92,7 @@ xfs_iformat_local( xfs_inode_verifier_error(ip, -EFSCORRUPTED, "xfs_iformat_local", dip, sizeof(*dip), __this_address); + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); return -EFSCORRUPTED; } @@ -113,7 +122,7 @@ xfs_iformat_extents( /* * If the number of extents is unreasonable, then something is wrong and - * we just bail out rather than crash in kmem_alloc() or memcpy() below. + * we just bail out rather than crash in kmalloc() or memcpy() below. */ if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, mp, whichfork))) { xfs_warn(ip->i_mount, "corrupt inode %llu ((a)extents = %llu).", @@ -121,11 +130,12 @@ xfs_iformat_extents( xfs_inode_verifier_error(ip, -EFSCORRUPTED, "xfs_iformat_extents(1)", dip, sizeof(*dip), __this_address); + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); return -EFSCORRUPTED; } ifp->if_bytes = 0; - ifp->if_u1.if_root = NULL; + ifp->if_data = NULL; ifp->if_height = 0; if (size) { dp = (xfs_bmbt_rec_t *) XFS_DFORK_PTR(dip, whichfork); @@ -140,7 +150,9 @@ xfs_iformat_extents( xfs_inode_verifier_error(ip, -EFSCORRUPTED, "xfs_iformat_extents(2)", dp, sizeof(*dp), fa); - return -EFSCORRUPTED; + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return xfs_bmap_complain_bad_rec(ip, whichfork, + fa, &new); } xfs_iext_insert(ip, &icur, &new, state); @@ -168,14 +180,14 @@ xfs_iformat_btree( struct xfs_mount *mp = ip->i_mount; xfs_bmdr_block_t *dfp; struct xfs_ifork *ifp; - /* REFERENCED */ + struct xfs_btree_block *broot; int nrecs; int size; int level; ifp = xfs_ifork_ptr(ip, whichfork); dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork); - size = XFS_BMAP_BROOT_SPACE(mp, dfp); + size = xfs_bmap_broot_space(mp, dfp); nrecs = be16_to_cpu(dfp->bb_numrecs); level = be16_to_cpu(dfp->bb_level); @@ -188,7 +200,7 @@ xfs_iformat_btree( */ if (unlikely(ifp->if_nextents <= XFS_IFORK_MAXEXT(ip, whichfork) || nrecs == 0 || - XFS_BMDR_SPACE_CALC(nrecs) > + xfs_bmdr_space_calc(nrecs) > XFS_DFORK_SIZE(dip, mp, whichfork) || ifp->if_nextents > ip->i_nblocks) || level == 0 || level > XFS_BM_MAXLEVELS(mp, whichfork)) { @@ -197,21 +209,20 @@ xfs_iformat_btree( xfs_inode_verifier_error(ip, -EFSCORRUPTED, "xfs_iformat_btree", dfp, size, __this_address); + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); return -EFSCORRUPTED; } - ifp->if_broot_bytes = size; - ifp->if_broot = kmem_alloc(size, KM_NOFS); - ASSERT(ifp->if_broot != NULL); + broot = xfs_broot_alloc(ifp, size); /* * Copy and convert from the on-disk structure * to the in-memory structure. */ xfs_bmdr_to_bmbt(ip, dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork), - ifp->if_broot, size); + broot, size); ifp->if_bytes = 0; - ifp->if_u1.if_root = NULL; + ifp->if_data = NULL; ifp->if_height = 0; return 0; } @@ -226,10 +237,15 @@ xfs_iformat_data_fork( /* * Initialize the extent count early, as the per-format routines may - * depend on it. + * depend on it. Use release semantics to set needextents /after/ we + * set the format. This ensures that we can use acquire semantics on + * needextents in xfs_need_iread_extents() and be guaranteed to see a + * valid format value after that load. */ ip->i_df.if_format = dip->di_format; ip->i_df.if_nextents = xfs_dfork_data_extents(dip); + smp_store_release(&ip->i_df.if_needextents, + ip->i_df.if_format == XFS_DINODE_FMT_BTREE ? 1 : 0); switch (inode->i_mode & S_IFMT) { case S_IFIFO: @@ -253,15 +269,27 @@ xfs_iformat_data_fork( return xfs_iformat_extents(ip, dip, XFS_DATA_FORK); case XFS_DINODE_FMT_BTREE: return xfs_iformat_btree(ip, dip, XFS_DATA_FORK); + case XFS_DINODE_FMT_META_BTREE: + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + return xfs_iformat_rtrmap(ip, dip); + case XFS_METAFILE_RTREFCOUNT: + return xfs_iformat_rtrefcount(ip, dip); + default: + break; + } + fallthrough; default: xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, sizeof(*dip), __this_address); + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); return -EFSCORRUPTED; } break; default: xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, sizeof(*dip), __this_address); + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); return -EFSCORRUPTED; } } @@ -270,10 +298,9 @@ static uint16_t xfs_dfork_attr_shortform_size( struct xfs_dinode *dip) { - struct xfs_attr_shortform *atp = - (struct xfs_attr_shortform *)XFS_DFORK_APTR(dip); + struct xfs_attr_sf_hdr *sf = XFS_DFORK_APTR(dip); - return be16_to_cpu(atp->hdr.totsize); + return be16_to_cpu(sf->totsize); } void @@ -282,8 +309,17 @@ xfs_ifork_init_attr( enum xfs_dinode_fmt format, xfs_extnum_t nextents) { + /* + * Initialize the extent count early, as the per-format routines may + * depend on it. Use release semantics to set needextents /after/ we + * set the format. This ensures that we can use acquire semantics on + * needextents in xfs_need_iread_extents() and be guaranteed to see a + * valid format value after that load. + */ ip->i_af.if_format = format; ip->i_af.if_nextents = nextents; + smp_store_release(&ip->i_af.if_needextents, + ip->i_af.if_format == XFS_DINODE_FMT_BTREE ? 1 : 0); } void @@ -325,6 +361,7 @@ xfs_iformat_attr_fork( default: xfs_inode_verifier_error(ip, error, __func__, dip, sizeof(*dip), __this_address); + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); error = -EFSCORRUPTED; break; } @@ -335,134 +372,68 @@ xfs_iformat_attr_fork( } /* - * Reallocate the space for if_broot based on the number of records - * being added or deleted as indicated in rec_diff. Move the records - * and pointers in if_broot to fit the new size. When shrinking this - * will eliminate holes between the records and pointers created by - * the caller. When growing this will create holes to be filled in - * by the caller. - * - * The caller must not request to add more records than would fit in - * the on-disk inode root. If the if_broot is currently NULL, then - * if we are adding records, one will be allocated. The caller must also - * not request that the number of records go below zero, although - * it can go to zero. - * - * ip -- the inode whose if_broot area is changing - * ext_diff -- the change in the number of records, positive or negative, - * requested for the if_broot array. + * Allocate the if_broot component of an inode fork so that it is @new_size + * bytes in size, using __GFP_NOLOCKDEP like all the other code that + * initializes a broot during inode load. Returns if_broot. */ -void -xfs_iroot_realloc( - xfs_inode_t *ip, - int rec_diff, - int whichfork) +struct xfs_btree_block * +xfs_broot_alloc( + struct xfs_ifork *ifp, + size_t new_size) { - struct xfs_mount *mp = ip->i_mount; - int cur_max; - struct xfs_ifork *ifp; - struct xfs_btree_block *new_broot; - int new_max; - size_t new_size; - char *np; - char *op; + ASSERT(ifp->if_broot == NULL); - /* - * Handle the degenerate case quietly. - */ - if (rec_diff == 0) { - return; - } + ifp->if_broot = kmalloc(new_size, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + return ifp->if_broot; +} - ifp = xfs_ifork_ptr(ip, whichfork); - if (rec_diff > 0) { - /* - * If there wasn't any memory allocated before, just - * allocate it now and get out. - */ - if (ifp->if_broot_bytes == 0) { - new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, rec_diff); - ifp->if_broot = kmem_alloc(new_size, KM_NOFS); - ifp->if_broot_bytes = (int)new_size; - return; - } +/* + * Reallocate the if_broot component of an inode fork so that it is @new_size + * bytes in size. Returns if_broot. + */ +struct xfs_btree_block * +xfs_broot_realloc( + struct xfs_ifork *ifp, + size_t new_size) +{ + /* No size change? No action needed. */ + if (new_size == ifp->if_broot_bytes) + return ifp->if_broot; - /* - * If there is already an existing if_broot, then we need - * to realloc() it and shift the pointers to their new - * location. The records don't change location because - * they are kept butted up against the btree block header. - */ - cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0); - new_max = cur_max + rec_diff; - new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, new_max); - ifp->if_broot = krealloc(ifp->if_broot, new_size, - GFP_NOFS | __GFP_NOFAIL); - op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1, - ifp->if_broot_bytes); - np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1, - (int)new_size); - ifp->if_broot_bytes = (int)new_size; - ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - memmove(np, op, cur_max * (uint)sizeof(xfs_fsblock_t)); - return; + /* New size is zero, free it. */ + if (new_size == 0) { + ifp->if_broot_bytes = 0; + kfree(ifp->if_broot); + ifp->if_broot = NULL; + return NULL; } /* - * rec_diff is less than 0. In this case, we are shrinking the - * if_broot buffer. It must already exist. If we go to zero - * records, just get rid of the root and clear the status bit. + * Shrinking the iroot means we allocate a new smaller object and copy + * it. We don't trust krealloc not to nop on realloc-down. */ - ASSERT((ifp->if_broot != NULL) && (ifp->if_broot_bytes > 0)); - cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0); - new_max = cur_max + rec_diff; - ASSERT(new_max >= 0); - if (new_max > 0) - new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, new_max); - else - new_size = 0; - if (new_size > 0) { - new_broot = kmem_alloc(new_size, KM_NOFS); - /* - * First copy over the btree block header. - */ - memcpy(new_broot, ifp->if_broot, - XFS_BMBT_BLOCK_LEN(ip->i_mount)); - } else { - new_broot = NULL; + if (ifp->if_broot_bytes > 0 && ifp->if_broot_bytes > new_size) { + struct xfs_btree_block *old_broot = ifp->if_broot; + + ifp->if_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + memcpy(ifp->if_broot, old_broot, new_size); + kfree(old_broot); + return ifp->if_broot; } /* - * Only copy the records and pointers if there are any. + * Growing the iroot means we can krealloc. This may get us the same + * object. */ - if (new_max > 0) { - /* - * First copy the records. - */ - op = (char *)XFS_BMBT_REC_ADDR(mp, ifp->if_broot, 1); - np = (char *)XFS_BMBT_REC_ADDR(mp, new_broot, 1); - memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_rec_t)); - - /* - * Then copy the pointers. - */ - op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1, - ifp->if_broot_bytes); - np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, new_broot, 1, - (int)new_size); - memcpy(np, op, new_max * (uint)sizeof(xfs_fsblock_t)); - } - kmem_free(ifp->if_broot); - ifp->if_broot = new_broot; - ifp->if_broot_bytes = (int)new_size; - if (ifp->if_broot) - ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - return; + ifp->if_broot = krealloc(ifp->if_broot, new_size, + GFP_KERNEL | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + return ifp->if_broot; } - /* * This is called when the amount of space needed for if_data * is increased or decreased. The change in size is indicated by @@ -471,14 +442,14 @@ xfs_iroot_realloc( * * If the amount of space needed has decreased below the size of the * inline buffer, then switch to using the inline buffer. Otherwise, - * use kmem_realloc() or kmem_alloc() to adjust the size of the buffer + * use krealloc() or kmalloc() to adjust the size of the buffer * to what is needed. * * ip -- the inode whose if_data area is changing * byte_diff -- the change in the number of bytes, positive or negative, * requested for the if_data array. */ -void +void * xfs_idata_realloc( struct xfs_inode *ip, int64_t byte_diff, @@ -490,34 +461,31 @@ xfs_idata_realloc( ASSERT(new_size >= 0); ASSERT(new_size <= xfs_inode_fork_size(ip, whichfork)); - if (byte_diff == 0) - return; - - if (new_size == 0) { - kmem_free(ifp->if_u1.if_data); - ifp->if_u1.if_data = NULL; - ifp->if_bytes = 0; - return; + if (byte_diff) { + ifp->if_data = krealloc(ifp->if_data, new_size, + GFP_KERNEL | __GFP_NOFAIL); + if (new_size == 0) + ifp->if_data = NULL; + ifp->if_bytes = new_size; } - ifp->if_u1.if_data = krealloc(ifp->if_u1.if_data, new_size, - GFP_NOFS | __GFP_NOFAIL); - ifp->if_bytes = new_size; + return ifp->if_data; } +/* Free all memory and reset a fork back to its initial state. */ void xfs_idestroy_fork( struct xfs_ifork *ifp) { if (ifp->if_broot != NULL) { - kmem_free(ifp->if_broot); + kfree(ifp->if_broot); ifp->if_broot = NULL; } switch (ifp->if_format) { case XFS_DINODE_FMT_LOCAL: - kmem_free(ifp->if_u1.if_data); - ifp->if_u1.if_data = NULL; + kfree(ifp->if_data); + ifp->if_data = NULL; break; case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: @@ -548,7 +516,7 @@ xfs_iextents_copy( struct xfs_bmbt_irec rec; int64_t copied = 0; - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED); ASSERT(ifp->if_bytes > 0); for_each_xfs_iext(ifp, &icur, &rec) { @@ -610,9 +578,9 @@ xfs_iflush_fork( case XFS_DINODE_FMT_LOCAL: if ((iip->ili_fields & dataflag[whichfork]) && (ifp->if_bytes > 0)) { - ASSERT(ifp->if_u1.if_data != NULL); + ASSERT(ifp->if_data != NULL); ASSERT(ifp->if_bytes <= xfs_inode_fork_size(ip, whichfork)); - memcpy(cp, ifp->if_u1.if_data, ifp->if_bytes); + memcpy(cp, ifp->if_data, ifp->if_bytes); } break; @@ -629,7 +597,7 @@ xfs_iflush_fork( if ((iip->ili_fields & brootflag[whichfork]) && (ifp->if_broot_bytes > 0)) { ASSERT(ifp->if_broot != NULL); - ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <= + ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= xfs_inode_fork_size(ip, whichfork)); xfs_bmbt_to_bmdr(mp, ifp->if_broot, ifp->if_broot_bytes, (xfs_bmdr_block_t *)cp, @@ -645,6 +613,25 @@ xfs_iflush_fork( } break; + case XFS_DINODE_FMT_META_BTREE: + ASSERT(whichfork == XFS_DATA_FORK); + + if (!(iip->ili_fields & brootflag[whichfork])) + break; + + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + xfs_iflush_rtrmap(ip, dip); + break; + case XFS_METAFILE_RTREFCOUNT: + xfs_iflush_rtrefcount(ip, dip); + break; + default: + ASSERT(0); + break; + } + break; + default: ASSERT(0); break; @@ -675,7 +662,7 @@ xfs_ifork_init_cow( return; ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_cache, - GFP_NOFS | __GFP_NOFAIL); + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); ip->i_cowfp->if_format = XFS_DINODE_FMT_EXTENTS; } @@ -687,19 +674,27 @@ xfs_ifork_verify_local_data( xfs_failaddr_t fa = NULL; switch (VFS_I(ip)->i_mode & S_IFMT) { - case S_IFDIR: - fa = xfs_dir2_sf_verify(ip); + case S_IFDIR: { + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_dir2_sf_hdr *sfp = ifp->if_data; + + fa = xfs_dir2_sf_verify(mp, sfp, ifp->if_bytes); break; - case S_IFLNK: - fa = xfs_symlink_shortform_verify(ip); + } + case S_IFLNK: { + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + + fa = xfs_symlink_shortform_verify(ifp->if_data, ifp->if_bytes); break; + } default: break; } if (fa) { xfs_inode_verifier_error(ip, -EFSCORRUPTED, "data fork", - ip->i_df.if_u1.if_data, ip->i_df.if_bytes, fa); + ip->i_df.if_data, ip->i_df.if_bytes, fa); return -EFSCORRUPTED; } @@ -714,66 +709,70 @@ xfs_ifork_verify_local_attr( struct xfs_ifork *ifp = &ip->i_af; xfs_failaddr_t fa; - if (!xfs_inode_has_attr_fork(ip)) + if (!xfs_inode_has_attr_fork(ip)) { fa = __this_address; - else - fa = xfs_attr_shortform_verify(ip); + } else { + struct xfs_ifork *ifp = &ip->i_af; + ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); + fa = xfs_attr_shortform_verify(ifp->if_data, ifp->if_bytes); + } if (fa) { xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork", - ifp->if_u1.if_data, ifp->if_bytes, fa); + ifp->if_data, ifp->if_bytes, fa); return -EFSCORRUPTED; } return 0; } +/* + * Check if the inode fork supports adding nr_to_add more extents. + * + * If it doesn't but we can upgrade it to large extent counters, do the upgrade. + * If we can't upgrade or are already using big counters but still can't fit the + * additional extents, return -EFBIG. + */ int -xfs_iext_count_may_overflow( +xfs_iext_count_extend( + struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, - int nr_to_add) + uint nr_to_add) { + struct xfs_mount *mp = ip->i_mount; + bool has_large = + xfs_inode_has_large_extent_counts(ip); struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); - uint64_t max_exts; uint64_t nr_exts; + ASSERT(nr_to_add <= XFS_MAX_EXTCNT_UPGRADE_NR); + if (whichfork == XFS_COW_FORK) return 0; - max_exts = xfs_iext_max_nextents(xfs_inode_has_large_extent_counts(ip), - whichfork); - - if (XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS)) - max_exts = 10; - + /* no point in upgrading if if_nextents overflows */ nr_exts = ifp->if_nextents + nr_to_add; - if (nr_exts < ifp->if_nextents || nr_exts > max_exts) + if (nr_exts < ifp->if_nextents) + return -EFBIG; + + if (XFS_TEST_ERROR(mp, XFS_ERRTAG_REDUCE_MAX_IEXTENTS) && nr_exts > 10) return -EFBIG; + if (nr_exts > xfs_iext_max_nextents(has_large, whichfork)) { + if (has_large || !xfs_has_large_extent_counts(mp)) + return -EFBIG; + ip->i_diflags2 |= XFS_DIFLAG2_NREXT64; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + } return 0; } -/* - * Upgrade this inode's extent counter fields to be able to handle a potential - * increase in the extent count by nr_to_add. Normally this is the same - * quantity that caused xfs_iext_count_may_overflow() to return -EFBIG. - */ -int -xfs_iext_count_upgrade( - struct xfs_trans *tp, +/* Decide if a file mapping is on the realtime device or not. */ +bool +xfs_ifork_is_realtime( struct xfs_inode *ip, - uint nr_to_add) + int whichfork) { - ASSERT(nr_to_add <= XFS_MAX_EXTCNT_UPGRADE_NR); - - if (!xfs_has_large_extent_counts(ip->i_mount) || - xfs_inode_has_large_extent_counts(ip) || - XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS)) - return -EFBIG; - - ip->i_diflags2 |= XFS_DIFLAG2_NREXT64; - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - - return 0; + return XFS_IS_REALTIME_INODE(ip) && whichfork != XFS_ATTR_FORK; } diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index d3943d6ad0b9..69ed0919d60b 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -13,17 +13,16 @@ struct xfs_dinode; * File incore extent information, present for each of data & attr forks. */ struct xfs_ifork { - int64_t if_bytes; /* bytes in if_u1 */ + int64_t if_bytes; /* bytes in if_data */ struct xfs_btree_block *if_broot; /* file's incore btree root */ unsigned int if_seq; /* fork mod counter */ int if_height; /* height of the extent tree */ - union { - void *if_root; /* extent tree root */ - char *if_data; /* inline file data */ - } if_u1; + void *if_data; /* extent tree root or + inline data */ xfs_extnum_t if_nextents; /* # of extents in this fork */ short if_broot_bytes; /* bytes allocated for root */ int8_t if_format; /* format of this fork */ + uint8_t if_needextents; /* extents have not been read */ }; /* @@ -169,9 +168,13 @@ int xfs_iformat_attr_fork(struct xfs_inode *, struct xfs_dinode *); void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, struct xfs_inode_log_item *, int); void xfs_idestroy_fork(struct xfs_ifork *ifp); -void xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff, +void * xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff, int whichfork); -void xfs_iroot_realloc(struct xfs_inode *, int, int); +struct xfs_btree_block *xfs_broot_alloc(struct xfs_ifork *ifp, + size_t new_size); +struct xfs_btree_block *xfs_broot_realloc(struct xfs_ifork *ifp, + size_t new_size); + int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int); int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *, int); @@ -179,6 +182,9 @@ void xfs_init_local_fork(struct xfs_inode *ip, int whichfork, const void *data, int64_t size); xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp); +void xfs_iext_insert_raw(struct xfs_ifork *ifp, + struct xfs_iext_cursor *cur, + struct xfs_bmbt_irec *irec); void xfs_iext_insert(struct xfs_inode *, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *, int); void xfs_iext_remove(struct xfs_inode *, struct xfs_iext_cursor *, @@ -254,15 +260,15 @@ extern void xfs_ifork_init_cow(struct xfs_inode *ip); int xfs_ifork_verify_local_data(struct xfs_inode *ip); int xfs_ifork_verify_local_attr(struct xfs_inode *ip); -int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork, - int nr_to_add); -int xfs_iext_count_upgrade(struct xfs_trans *tp, struct xfs_inode *ip, - uint nr_to_add); +int xfs_iext_count_extend(struct xfs_trans *tp, struct xfs_inode *ip, + int whichfork, uint nr_to_add); +bool xfs_ifork_is_realtime(struct xfs_inode *ip, int whichfork); /* returns true if the fork has extents but they are not read in yet. */ -static inline bool xfs_need_iread_extents(struct xfs_ifork *ifp) +static inline bool xfs_need_iread_extents(const struct xfs_ifork *ifp) { - return ifp->if_format == XFS_DINODE_FMT_BTREE && ifp->if_height == 0; + /* see xfs_iformat_{data,attr}_fork() for needextents semantics */ + return smp_load_acquire(&ifp->if_needextents) != 0; } #endif /* __XFS_INODE_FORK_H__ */ diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c new file mode 100644 index 000000000000..309ce6dd5553 --- /dev/null +++ b/fs/xfs/libxfs/xfs_inode_util.c @@ -0,0 +1,741 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2000-2006 Silicon Graphics, Inc. + * All Rights Reserved. + */ +#include <linux/iversion.h> +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_inode_util.h" +#include "xfs_trans.h" +#include "xfs_ialloc.h" +#include "xfs_health.h" +#include "xfs_bmap.h" +#include "xfs_error.h" +#include "xfs_trace.h" +#include "xfs_ag.h" +#include "xfs_iunlink_item.h" +#include "xfs_inode_item.h" + +uint16_t +xfs_flags2diflags( + struct xfs_inode *ip, + unsigned int xflags) +{ + /* can't set PREALLOC this way, just preserve it */ + uint16_t di_flags = + (ip->i_diflags & XFS_DIFLAG_PREALLOC); + + if (xflags & FS_XFLAG_IMMUTABLE) + di_flags |= XFS_DIFLAG_IMMUTABLE; + if (xflags & FS_XFLAG_APPEND) + di_flags |= XFS_DIFLAG_APPEND; + if (xflags & FS_XFLAG_SYNC) + di_flags |= XFS_DIFLAG_SYNC; + if (xflags & FS_XFLAG_NOATIME) + di_flags |= XFS_DIFLAG_NOATIME; + if (xflags & FS_XFLAG_NODUMP) + di_flags |= XFS_DIFLAG_NODUMP; + if (xflags & FS_XFLAG_NODEFRAG) + di_flags |= XFS_DIFLAG_NODEFRAG; + if (xflags & FS_XFLAG_FILESTREAM) + di_flags |= XFS_DIFLAG_FILESTREAM; + if (S_ISDIR(VFS_I(ip)->i_mode)) { + if (xflags & FS_XFLAG_RTINHERIT) + di_flags |= XFS_DIFLAG_RTINHERIT; + if (xflags & FS_XFLAG_NOSYMLINKS) + di_flags |= XFS_DIFLAG_NOSYMLINKS; + if (xflags & FS_XFLAG_EXTSZINHERIT) + di_flags |= XFS_DIFLAG_EXTSZINHERIT; + if (xflags & FS_XFLAG_PROJINHERIT) + di_flags |= XFS_DIFLAG_PROJINHERIT; + } else if (S_ISREG(VFS_I(ip)->i_mode)) { + if (xflags & FS_XFLAG_REALTIME) + di_flags |= XFS_DIFLAG_REALTIME; + if (xflags & FS_XFLAG_EXTSIZE) + di_flags |= XFS_DIFLAG_EXTSIZE; + } + + return di_flags; +} + +uint64_t +xfs_flags2diflags2( + struct xfs_inode *ip, + unsigned int xflags) +{ + uint64_t di_flags2 = + (ip->i_diflags2 & (XFS_DIFLAG2_REFLINK | + XFS_DIFLAG2_BIGTIME | + XFS_DIFLAG2_NREXT64)); + + if (xflags & FS_XFLAG_DAX) + di_flags2 |= XFS_DIFLAG2_DAX; + if (xflags & FS_XFLAG_COWEXTSIZE) + di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; + + return di_flags2; +} + +uint32_t +xfs_ip2xflags( + struct xfs_inode *ip) +{ + uint32_t flags = 0; + + if (ip->i_diflags & XFS_DIFLAG_ANY) { + if (ip->i_diflags & XFS_DIFLAG_REALTIME) + flags |= FS_XFLAG_REALTIME; + if (ip->i_diflags & XFS_DIFLAG_PREALLOC) + flags |= FS_XFLAG_PREALLOC; + if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE) + flags |= FS_XFLAG_IMMUTABLE; + if (ip->i_diflags & XFS_DIFLAG_APPEND) + flags |= FS_XFLAG_APPEND; + if (ip->i_diflags & XFS_DIFLAG_SYNC) + flags |= FS_XFLAG_SYNC; + if (ip->i_diflags & XFS_DIFLAG_NOATIME) + flags |= FS_XFLAG_NOATIME; + if (ip->i_diflags & XFS_DIFLAG_NODUMP) + flags |= FS_XFLAG_NODUMP; + if (ip->i_diflags & XFS_DIFLAG_RTINHERIT) + flags |= FS_XFLAG_RTINHERIT; + if (ip->i_diflags & XFS_DIFLAG_PROJINHERIT) + flags |= FS_XFLAG_PROJINHERIT; + if (ip->i_diflags & XFS_DIFLAG_NOSYMLINKS) + flags |= FS_XFLAG_NOSYMLINKS; + if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) + flags |= FS_XFLAG_EXTSIZE; + if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) + flags |= FS_XFLAG_EXTSZINHERIT; + if (ip->i_diflags & XFS_DIFLAG_NODEFRAG) + flags |= FS_XFLAG_NODEFRAG; + if (ip->i_diflags & XFS_DIFLAG_FILESTREAM) + flags |= FS_XFLAG_FILESTREAM; + } + + if (ip->i_diflags2 & XFS_DIFLAG2_ANY) { + if (ip->i_diflags2 & XFS_DIFLAG2_DAX) + flags |= FS_XFLAG_DAX; + if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) + flags |= FS_XFLAG_COWEXTSIZE; + } + + if (xfs_inode_has_attr_fork(ip)) + flags |= FS_XFLAG_HASATTR; + return flags; +} + +prid_t +xfs_get_initial_prid(struct xfs_inode *dp) +{ + if (dp->i_diflags & XFS_DIFLAG_PROJINHERIT) + return dp->i_projid; + + /* Assign to the root project by default. */ + return 0; +} + +/* Propagate di_flags from a parent inode to a child inode. */ +static inline void +xfs_inode_inherit_flags( + struct xfs_inode *ip, + const struct xfs_inode *pip) +{ + unsigned int di_flags = 0; + xfs_failaddr_t failaddr; + umode_t mode = VFS_I(ip)->i_mode; + + if (S_ISDIR(mode)) { + if (pip->i_diflags & XFS_DIFLAG_RTINHERIT) + di_flags |= XFS_DIFLAG_RTINHERIT; + if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) { + di_flags |= XFS_DIFLAG_EXTSZINHERIT; + ip->i_extsize = pip->i_extsize; + } + if (pip->i_diflags & XFS_DIFLAG_PROJINHERIT) + di_flags |= XFS_DIFLAG_PROJINHERIT; + } else if (S_ISREG(mode)) { + if ((pip->i_diflags & XFS_DIFLAG_RTINHERIT) && + xfs_has_realtime(ip->i_mount)) + di_flags |= XFS_DIFLAG_REALTIME; + if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) { + di_flags |= XFS_DIFLAG_EXTSIZE; + ip->i_extsize = pip->i_extsize; + } + } + if ((pip->i_diflags & XFS_DIFLAG_NOATIME) && + xfs_inherit_noatime) + di_flags |= XFS_DIFLAG_NOATIME; + if ((pip->i_diflags & XFS_DIFLAG_NODUMP) && + xfs_inherit_nodump) + di_flags |= XFS_DIFLAG_NODUMP; + if ((pip->i_diflags & XFS_DIFLAG_SYNC) && + xfs_inherit_sync) + di_flags |= XFS_DIFLAG_SYNC; + if ((pip->i_diflags & XFS_DIFLAG_NOSYMLINKS) && + xfs_inherit_nosymlinks) + di_flags |= XFS_DIFLAG_NOSYMLINKS; + if ((pip->i_diflags & XFS_DIFLAG_NODEFRAG) && + xfs_inherit_nodefrag) + di_flags |= XFS_DIFLAG_NODEFRAG; + if (pip->i_diflags & XFS_DIFLAG_FILESTREAM) + di_flags |= XFS_DIFLAG_FILESTREAM; + + ip->i_diflags |= di_flags; + + /* + * Inode verifiers on older kernels only check that the extent size + * hint is an integer multiple of the rt extent size on realtime files. + * They did not check the hint alignment on a directory with both + * rtinherit and extszinherit flags set. If the misaligned hint is + * propagated from a directory into a new realtime file, new file + * allocations will fail due to math errors in the rt allocator and/or + * trip the verifiers. Validate the hint settings in the new file so + * that we don't let broken hints propagate. + */ + failaddr = xfs_inode_validate_extsize(ip->i_mount, ip->i_extsize, + VFS_I(ip)->i_mode, ip->i_diflags); + if (failaddr) { + ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | + XFS_DIFLAG_EXTSZINHERIT); + ip->i_extsize = 0; + } +} + +/* Propagate di_flags2 from a parent inode to a child inode. */ +static inline void +xfs_inode_inherit_flags2( + struct xfs_inode *ip, + const struct xfs_inode *pip) +{ + xfs_failaddr_t failaddr; + + if (pip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) { + ip->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE; + ip->i_cowextsize = pip->i_cowextsize; + } + if (pip->i_diflags2 & XFS_DIFLAG2_DAX) + ip->i_diflags2 |= XFS_DIFLAG2_DAX; + if (xfs_is_metadir_inode(pip)) + ip->i_diflags2 |= XFS_DIFLAG2_METADATA; + + /* Don't let invalid cowextsize hints propagate. */ + failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize, + VFS_I(ip)->i_mode, ip->i_diflags, ip->i_diflags2); + if (failaddr) { + ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE; + ip->i_cowextsize = 0; + } +} + +/* + * If we need to create attributes immediately after allocating the inode, + * initialise an empty attribute fork right now. We use the default fork offset + * for attributes here as we don't know exactly what size or how many + * attributes we might be adding. We can do this safely here because we know + * the data fork is completely empty and this saves us from needing to run a + * separate transaction to set the fork offset in the immediate future. + * + * If we have parent pointers and the caller hasn't told us that the file will + * never be linked into a directory tree, we /must/ create the attr fork. + */ +static inline bool +xfs_icreate_want_attrfork( + struct xfs_mount *mp, + const struct xfs_icreate_args *args) +{ + if (args->flags & XFS_ICREATE_INIT_XATTRS) + return true; + + if (!(args->flags & XFS_ICREATE_UNLINKABLE) && xfs_has_parent(mp)) + return true; + + return false; +} + +/* Initialise an inode's attributes. */ +void +xfs_inode_init( + struct xfs_trans *tp, + const struct xfs_icreate_args *args, + struct xfs_inode *ip) +{ + struct xfs_inode *pip = args->pip; + struct inode *dir = pip ? VFS_I(pip) : NULL; + struct xfs_mount *mp = tp->t_mountp; + struct inode *inode = VFS_I(ip); + unsigned int flags; + int times = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG | + XFS_ICHGTIME_ACCESS; + + if (args->flags & XFS_ICREATE_TMPFILE) + set_nlink(inode, 0); + else if (S_ISDIR(args->mode)) + set_nlink(inode, 2); + else + set_nlink(inode, 1); + inode->i_rdev = args->rdev; + + if (!args->idmap || pip == NULL) { + /* creating a tree root, sb rooted, or detached file */ + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + ip->i_projid = 0; + inode->i_mode = args->mode; + } else { + /* creating a child in the directory tree */ + if (dir && !(dir->i_mode & S_ISGID) && xfs_has_grpid(mp)) { + inode_fsuid_set(inode, args->idmap); + inode->i_gid = dir->i_gid; + inode->i_mode = args->mode; + } else { + inode_init_owner(args->idmap, inode, dir, args->mode); + } + ip->i_projid = xfs_get_initial_prid(pip); + } + + ip->i_disk_size = 0; + ip->i_df.if_nextents = 0; + ASSERT(ip->i_nblocks == 0); + + ip->i_extsize = 0; + ip->i_diflags = 0; + + if (xfs_has_v3inodes(mp)) { + inode_set_iversion(inode, 1); + /* also covers the di_used_blocks union arm: */ + ip->i_cowextsize = 0; + times |= XFS_ICHGTIME_CREATE; + } + + xfs_trans_ichgtime(tp, ip, times); + + flags = XFS_ILOG_CORE; + switch (args->mode & S_IFMT) { + case S_IFIFO: + case S_IFCHR: + case S_IFBLK: + case S_IFSOCK: + ip->i_df.if_format = XFS_DINODE_FMT_DEV; + flags |= XFS_ILOG_DEV; + break; + case S_IFREG: + case S_IFDIR: + if (pip && (pip->i_diflags & XFS_DIFLAG_ANY)) + xfs_inode_inherit_flags(ip, pip); + if (pip && (pip->i_diflags2 & XFS_DIFLAG2_ANY)) + xfs_inode_inherit_flags2(ip, pip); + fallthrough; + case S_IFLNK: + ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS; + ip->i_df.if_bytes = 0; + ip->i_df.if_data = NULL; + break; + default: + ASSERT(0); + } + + if (xfs_icreate_want_attrfork(mp, args)) { + ip->i_forkoff = xfs_default_attroffset(ip) >> 3; + xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0); + + if (!xfs_has_attr(mp)) { + spin_lock(&mp->m_sb_lock); + xfs_add_attr(mp); + spin_unlock(&mp->m_sb_lock); + xfs_log_sb(tp); + } + } + + xfs_trans_log_inode(tp, ip, flags); +} + +/* + * In-Core Unlinked List Lookups + * ============================= + * + * Every inode is supposed to be reachable from some other piece of metadata + * with the exception of the root directory. Inodes with a connection to a + * file descriptor but not linked from anywhere in the on-disk directory tree + * are collectively known as unlinked inodes, though the filesystem itself + * maintains links to these inodes so that on-disk metadata are consistent. + * + * XFS implements a per-AG on-disk hash table of unlinked inodes. The AGI + * header contains a number of buckets that point to an inode, and each inode + * record has a pointer to the next inode in the hash chain. This + * singly-linked list causes scaling problems in the iunlink remove function + * because we must walk that list to find the inode that points to the inode + * being removed from the unlinked hash bucket list. + * + * Hence we keep an in-memory double linked list to link each inode on an + * unlinked list. Because there are 64 unlinked lists per AGI, keeping pointer + * based lists would require having 64 list heads in the perag, one for each + * list. This is expensive in terms of memory (think millions of AGs) and cache + * misses on lookups. Instead, use the fact that inodes on the unlinked list + * must be referenced at the VFS level to keep them on the list and hence we + * have an existence guarantee for inodes on the unlinked list. + * + * Given we have an existence guarantee, we can use lockless inode cache lookups + * to resolve aginos to xfs inodes. This means we only need 8 bytes per inode + * for the double linked unlinked list, and we don't need any extra locking to + * keep the list safe as all manipulations are done under the AGI buffer lock. + * Keeping the list up to date does not require memory allocation, just finding + * the XFS inode and updating the next/prev unlinked list aginos. + */ + +/* + * Update the prev pointer of the next agino. Returns -ENOLINK if the inode + * is not in cache. + */ +static int +xfs_iunlink_update_backref( + struct xfs_perag *pag, + xfs_agino_t prev_agino, + xfs_agino_t next_agino) +{ + struct xfs_inode *ip; + + /* No update necessary if we are at the end of the list. */ + if (next_agino == NULLAGINO) + return 0; + + ip = xfs_iunlink_lookup(pag, next_agino); + if (!ip) + return -ENOLINK; + + ip->i_prev_unlinked = prev_agino; + return 0; +} + +/* + * Point the AGI unlinked bucket at an inode and log the results. The caller + * is responsible for validating the old value. + */ +STATIC int +xfs_iunlink_update_bucket( + struct xfs_trans *tp, + struct xfs_perag *pag, + struct xfs_buf *agibp, + unsigned int bucket_index, + xfs_agino_t new_agino) +{ + struct xfs_agi *agi = agibp->b_addr; + xfs_agino_t old_value; + int offset; + + ASSERT(xfs_verify_agino_or_null(pag, new_agino)); + + old_value = be32_to_cpu(agi->agi_unlinked[bucket_index]); + trace_xfs_iunlink_update_bucket(pag, bucket_index, old_value, + new_agino); + + /* + * We should never find the head of the list already set to the value + * passed in because either we're adding or removing ourselves from the + * head of the list. + */ + if (old_value == new_agino) { + xfs_buf_mark_corrupt(agibp); + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); + return -EFSCORRUPTED; + } + + agi->agi_unlinked[bucket_index] = cpu_to_be32(new_agino); + offset = offsetof(struct xfs_agi, agi_unlinked) + + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_log_buf(tp, agibp, offset, offset + sizeof(xfs_agino_t) - 1); + return 0; +} + +static int +xfs_iunlink_insert_inode( + struct xfs_trans *tp, + struct xfs_perag *pag, + struct xfs_buf *agibp, + struct xfs_inode *ip) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_agi *agi = agibp->b_addr; + xfs_agino_t next_agino; + xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); + short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; + int error; + + /* + * Get the index into the agi hash table for the list this inode will + * go on. Make sure the pointer isn't garbage and that this inode + * isn't already on the list. + */ + next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]); + if (next_agino == agino || + !xfs_verify_agino_or_null(pag, next_agino)) { + xfs_buf_mark_corrupt(agibp); + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); + return -EFSCORRUPTED; + } + + /* + * Update the prev pointer in the next inode to point back to this + * inode. + */ + error = xfs_iunlink_update_backref(pag, agino, next_agino); + if (error == -ENOLINK) + error = xfs_iunlink_reload_next(tp, agibp, agino, next_agino); + if (error) + return error; + + if (next_agino != NULLAGINO) { + /* + * There is already another inode in the bucket, so point this + * inode to the current head of the list. + */ + error = xfs_iunlink_log_inode(tp, ip, pag, next_agino); + if (error) + return error; + ip->i_next_unlinked = next_agino; + } + + /* Point the head of the list to point to this inode. */ + ip->i_prev_unlinked = NULLAGINO; + return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino); +} + +/* + * This is called when the inode's link count has gone to 0 or we are creating + * a tmpfile via O_TMPFILE. The inode @ip must have nlink == 0. + * + * We place the on-disk inode on a list in the AGI. It will be pulled from this + * list when the inode is freed. + */ +int +xfs_iunlink( + struct xfs_trans *tp, + struct xfs_inode *ip) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_perag *pag; + struct xfs_buf *agibp; + int error; + + ASSERT(VFS_I(ip)->i_nlink == 0); + ASSERT(VFS_I(ip)->i_mode != 0); + trace_xfs_iunlink(ip); + + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); + + /* Get the agi buffer first. It ensures lock ordering on the list. */ + error = xfs_read_agi(pag, tp, 0, &agibp); + if (error) + goto out; + + error = xfs_iunlink_insert_inode(tp, pag, agibp, ip); +out: + xfs_perag_put(pag); + return error; +} + +static int +xfs_iunlink_remove_inode( + struct xfs_trans *tp, + struct xfs_perag *pag, + struct xfs_buf *agibp, + struct xfs_inode *ip) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_agi *agi = agibp->b_addr; + xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); + xfs_agino_t head_agino; + short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; + int error; + + trace_xfs_iunlink_remove(ip); + + /* + * Get the index into the agi hash table for the list this inode will + * go on. Make sure the head pointer isn't garbage. + */ + head_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]); + if (!xfs_verify_agino(pag, head_agino)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + agi, sizeof(*agi)); + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); + return -EFSCORRUPTED; + } + + /* + * Set our inode's next_unlinked pointer to NULL and then return + * the old pointer value so that we can update whatever was previous + * to us in the list to point to whatever was next in the list. + */ + error = xfs_iunlink_log_inode(tp, ip, pag, NULLAGINO); + if (error) + return error; + + /* + * Update the prev pointer in the next inode to point back to previous + * inode in the chain. + */ + error = xfs_iunlink_update_backref(pag, ip->i_prev_unlinked, + ip->i_next_unlinked); + if (error == -ENOLINK) + error = xfs_iunlink_reload_next(tp, agibp, ip->i_prev_unlinked, + ip->i_next_unlinked); + if (error) + return error; + + if (head_agino != agino) { + struct xfs_inode *prev_ip; + + prev_ip = xfs_iunlink_lookup(pag, ip->i_prev_unlinked); + if (!prev_ip) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + error = xfs_iunlink_log_inode(tp, prev_ip, pag, + ip->i_next_unlinked); + prev_ip->i_next_unlinked = ip->i_next_unlinked; + } else { + /* Point the head of the list to the next unlinked inode. */ + error = xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, + ip->i_next_unlinked); + } + + ip->i_next_unlinked = NULLAGINO; + ip->i_prev_unlinked = 0; + return error; +} + +/* + * Pull the on-disk inode from the AGI unlinked list. + */ +int +xfs_iunlink_remove( + struct xfs_trans *tp, + struct xfs_perag *pag, + struct xfs_inode *ip) +{ + struct xfs_buf *agibp; + int error; + + trace_xfs_iunlink_remove(ip); + + /* Get the agi buffer first. It ensures lock ordering on the list. */ + error = xfs_read_agi(pag, tp, 0, &agibp); + if (error) + return error; + + return xfs_iunlink_remove_inode(tp, pag, agibp, ip); +} + +/* + * Decrement the link count on an inode & log the change. If this causes the + * link count to go to zero, move the inode to AGI unlinked list so that it can + * be freed when the last active reference goes away via xfs_inactive(). + */ +int +xfs_droplink( + struct xfs_trans *tp, + struct xfs_inode *ip) +{ + struct inode *inode = VFS_I(ip); + + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); + + if (inode->i_nlink == 0) { + xfs_info_ratelimited(tp->t_mountp, + "Inode 0x%llx link count dropped below zero. Pinning link count.", + ip->i_ino); + set_nlink(inode, XFS_NLINK_PINNED); + } + if (inode->i_nlink != XFS_NLINK_PINNED) + drop_nlink(inode); + + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + + if (inode->i_nlink) + return 0; + + return xfs_iunlink(tp, ip); +} + +/* + * Increment the link count on an inode & log the change. + */ +void +xfs_bumplink( + struct xfs_trans *tp, + struct xfs_inode *ip) +{ + struct inode *inode = VFS_I(ip); + + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); + + if (inode->i_nlink == XFS_NLINK_PINNED - 1) + xfs_info_ratelimited(tp->t_mountp, + "Inode 0x%llx link count exceeded maximum. Pinning link count.", + ip->i_ino); + if (inode->i_nlink != XFS_NLINK_PINNED) + inc_nlink(inode); + + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); +} + +/* Free an inode in the ondisk index and zero it out. */ +int +xfs_inode_uninit( + struct xfs_trans *tp, + struct xfs_perag *pag, + struct xfs_inode *ip, + struct xfs_icluster *xic) +{ + struct xfs_mount *mp = ip->i_mount; + int error; + + /* + * Free the inode first so that we guarantee that the AGI lock is going + * to be taken before we remove the inode from the unlinked list. This + * makes the AGI lock -> unlinked list modification order the same as + * used in O_TMPFILE creation. + */ + error = xfs_difree(tp, pag, ip->i_ino, xic); + if (error) + return error; + + error = xfs_iunlink_remove(tp, pag, ip); + if (error) + return error; + + /* + * Free any local-format data sitting around before we reset the + * data fork to extents format. Note that the attr fork data has + * already been freed by xfs_attr_inactive. + */ + if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) { + kfree(ip->i_df.if_data); + ip->i_df.if_data = NULL; + ip->i_df.if_bytes = 0; + } + + VFS_I(ip)->i_mode = 0; /* mark incore inode as free */ + ip->i_diflags = 0; + ip->i_diflags2 = mp->m_ino_geo.new_diflags2; + ip->i_forkoff = 0; /* mark the attr fork not in use */ + ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS; + + /* + * Bump the generation count so no one will be confused + * by reincarnations of this inode. + */ + VFS_I(ip)->i_generation++; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_inode_util.h b/fs/xfs/libxfs/xfs_inode_util.h new file mode 100644 index 000000000000..060242998a23 --- /dev/null +++ b/fs/xfs/libxfs/xfs_inode_util.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. + * All Rights Reserved. + */ +#ifndef __XFS_INODE_UTIL_H__ +#define __XFS_INODE_UTIL_H__ + +struct xfs_icluster; + +uint16_t xfs_flags2diflags(struct xfs_inode *ip, unsigned int xflags); +uint64_t xfs_flags2diflags2(struct xfs_inode *ip, unsigned int xflags); +uint32_t xfs_dic2xflags(struct xfs_inode *ip); +uint32_t xfs_ip2xflags(struct xfs_inode *ip); + +prid_t xfs_get_initial_prid(struct xfs_inode *dp); + +/* + * File creation context. + * + * Due to our only partial reliance on the VFS to propagate uid and gid values + * according to accepted Unix behaviors, callers must initialize idmap to the + * correct idmapping structure to get the correct inheritance behaviors when + * XFS_MOUNT_GRPID is set. + * + * To create files detached from the directory tree (e.g. quota inodes), set + * idmap to NULL. To create a tree root, set pip to NULL. + */ +struct xfs_icreate_args { + struct mnt_idmap *idmap; + struct xfs_inode *pip; /* parent inode or null */ + dev_t rdev; + umode_t mode; + +#define XFS_ICREATE_TMPFILE (1U << 0) /* create an unlinked file */ +#define XFS_ICREATE_INIT_XATTRS (1U << 1) /* will set xattrs immediately */ +#define XFS_ICREATE_UNLINKABLE (1U << 2) /* cannot link into dir tree */ + uint16_t flags; +}; + +/* + * Flags for xfs_trans_ichgtime(). + */ +#define XFS_ICHGTIME_MOD 0x1 /* data fork modification timestamp */ +#define XFS_ICHGTIME_CHG 0x2 /* inode field change timestamp */ +#define XFS_ICHGTIME_CREATE 0x4 /* inode create timestamp */ +#define XFS_ICHGTIME_ACCESS 0x8 /* last access timestamp */ +void xfs_trans_ichgtime(struct xfs_trans *tp, struct xfs_inode *ip, int flags); + +void xfs_inode_init(struct xfs_trans *tp, const struct xfs_icreate_args *args, + struct xfs_inode *ip); + +int xfs_inode_uninit(struct xfs_trans *tp, struct xfs_perag *pag, + struct xfs_inode *ip, struct xfs_icluster *xic); + +int xfs_iunlink(struct xfs_trans *tp, struct xfs_inode *ip); +int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag, + struct xfs_inode *ip); +int xfs_droplink(struct xfs_trans *tp, struct xfs_inode *ip); +void xfs_bumplink(struct xfs_trans *tp, struct xfs_inode *ip); + +#endif /* __XFS_INODE_UTIL_H__ */ diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index f13e0809dc63..908e7060428c 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -31,6 +31,7 @@ typedef uint32_t xlog_tid_t; #define XLOG_BIG_RECORD_BSIZE (32*1024) /* 32k buffers */ #define XLOG_MAX_RECORD_BSIZE (256*1024) #define XLOG_HEADER_CYCLE_SIZE (32*1024) /* cycle data in header */ +#define XLOG_CYCLE_DATA_SIZE (XLOG_HEADER_CYCLE_SIZE / BBSIZE) #define XLOG_MIN_RECORD_BSHIFT 14 /* 16384 == 1 << 14 */ #define XLOG_BIG_RECORD_BSHIFT 15 /* 32k == 1 << 15 */ #define XLOG_MAX_RECORD_BSHIFT 18 /* 256k == 1 << 18 */ @@ -86,40 +87,6 @@ struct xfs_unmount_log_format { uint32_t pad2; /* may as well make it 64 bits */ }; -/* Region types for iovec's i_type */ -#define XLOG_REG_TYPE_BFORMAT 1 -#define XLOG_REG_TYPE_BCHUNK 2 -#define XLOG_REG_TYPE_EFI_FORMAT 3 -#define XLOG_REG_TYPE_EFD_FORMAT 4 -#define XLOG_REG_TYPE_IFORMAT 5 -#define XLOG_REG_TYPE_ICORE 6 -#define XLOG_REG_TYPE_IEXT 7 -#define XLOG_REG_TYPE_IBROOT 8 -#define XLOG_REG_TYPE_ILOCAL 9 -#define XLOG_REG_TYPE_IATTR_EXT 10 -#define XLOG_REG_TYPE_IATTR_BROOT 11 -#define XLOG_REG_TYPE_IATTR_LOCAL 12 -#define XLOG_REG_TYPE_QFORMAT 13 -#define XLOG_REG_TYPE_DQUOT 14 -#define XLOG_REG_TYPE_QUOTAOFF 15 -#define XLOG_REG_TYPE_LRHEADER 16 -#define XLOG_REG_TYPE_UNMOUNT 17 -#define XLOG_REG_TYPE_COMMIT 18 -#define XLOG_REG_TYPE_TRANSHDR 19 -#define XLOG_REG_TYPE_ICREATE 20 -#define XLOG_REG_TYPE_RUI_FORMAT 21 -#define XLOG_REG_TYPE_RUD_FORMAT 22 -#define XLOG_REG_TYPE_CUI_FORMAT 23 -#define XLOG_REG_TYPE_CUD_FORMAT 24 -#define XLOG_REG_TYPE_BUI_FORMAT 25 -#define XLOG_REG_TYPE_BUD_FORMAT 26 -#define XLOG_REG_TYPE_ATTRI_FORMAT 27 -#define XLOG_REG_TYPE_ATTRD_FORMAT 28 -#define XLOG_REG_TYPE_ATTR_NAME 29 -#define XLOG_REG_TYPE_ATTR_VALUE 30 -#define XLOG_REG_TYPE_MAX 30 - - /* * Flags to log operation header * @@ -138,14 +105,13 @@ struct xfs_unmount_log_format { #define XLOG_END_TRANS 0x10 /* End a continued transaction */ #define XLOG_UNMOUNT_TRANS 0x20 /* Unmount a filesystem transaction */ - -typedef struct xlog_op_header { +struct xlog_op_header { __be32 oh_tid; /* transaction id of operation : 4 b */ __be32 oh_len; /* bytes in data region : 4 b */ __u8 oh_clientid; /* who sent me this : 1 b */ __u8 oh_flags; /* : 1 b */ __u16 oh_res2; /* 32 bit align : 2 b */ -} xlog_op_header_t; +}; /* valid values for h_fmt */ #define XLOG_FMT_UNKNOWN 0 @@ -160,7 +126,17 @@ typedef struct xlog_op_header { #define XLOG_FMT XLOG_FMT_LINUX_LE #endif -typedef struct xlog_rec_header { +struct xlog_rec_ext_header { + __be32 xh_cycle; /* write cycle of log */ + __be32 xh_cycle_data[XLOG_CYCLE_DATA_SIZE]; + __u8 xh_reserved[252]; +}; + +/* actual ext header payload size for checksumming */ +#define XLOG_REC_EXT_SIZE \ + offsetofend(struct xlog_rec_ext_header, xh_cycle_data) + +struct xlog_rec_header { __be32 h_magicno; /* log record (LR) identifier : 4 */ __be32 h_cycle; /* write cycle of log : 4 */ __be32 h_version; /* LR version : 4 */ @@ -170,34 +146,50 @@ typedef struct xlog_rec_header { __le32 h_crc; /* crc of log record : 4 */ __be32 h_prev_block; /* block number to previous LR : 4 */ __be32 h_num_logops; /* number of log operations in this LR : 4 */ - __be32 h_cycle_data[XLOG_HEADER_CYCLE_SIZE / BBSIZE]; - /* new fields */ + __be32 h_cycle_data[XLOG_CYCLE_DATA_SIZE]; + + /* fields added by the Linux port: */ __be32 h_fmt; /* format of log record : 4 */ uuid_t h_fs_uuid; /* uuid of FS : 16 */ + + /* fields added for log v2: */ __be32 h_size; /* iclog size : 4 */ -} xlog_rec_header_t; -typedef struct xlog_rec_ext_header { - __be32 xh_cycle; /* write cycle of log : 4 */ - __be32 xh_cycle_data[XLOG_HEADER_CYCLE_SIZE / BBSIZE]; /* : 256 */ -} xlog_rec_ext_header_t; + /* + * When h_size added for log v2 support, it caused structure to have + * a different size on i386 vs all other architectures because the + * sum of the size ofthe member is not aligned by that of the largest + * __be64-sized member, and i386 has really odd struct alignment rules. + * + * Due to the way the log headers are placed out on-disk that alone is + * not a problem becaue the xlog_rec_header always sits alone in a + * BBSIZEs area, and the rest of that area is padded with zeroes. + * But xlog_cksum used to calculate the checksum based on the structure + * size, and thus gives different checksums for i386 vs the rest. + * We now do two checksum validation passes for both sizes to allow + * moving v5 file systems with unclean logs between i386 and other + * (little-endian) architectures. + */ + __u32 h_pad0; -/* - * Quite misnamed, because this union lays out the actual on-disk log buffer. - */ -typedef union xlog_in_core2 { - xlog_rec_header_t hic_header; - xlog_rec_ext_header_t hic_xheader; - char hic_sector[XLOG_HEADER_SIZE]; -} xlog_in_core_2_t; + __u8 h_reserved[184]; + struct xlog_rec_ext_header h_ext[]; +}; + +#ifdef __i386__ +#define XLOG_REC_SIZE offsetofend(struct xlog_rec_header, h_size) +#define XLOG_REC_SIZE_OTHER offsetofend(struct xlog_rec_header, h_pad0) +#else +#define XLOG_REC_SIZE offsetofend(struct xlog_rec_header, h_pad0) +#define XLOG_REC_SIZE_OTHER offsetofend(struct xlog_rec_header, h_size) +#endif /* __i386__ */ /* not an on-disk structure, but needed by log recovery in userspace */ -typedef struct xfs_log_iovec { +struct xfs_log_iovec { void *i_addr; /* beginning address of region */ int i_len; /* length in bytes of region */ uint i_type; /* type of region */ -} xfs_log_iovec_t; - +}; /* * Transaction Header definitions. @@ -210,12 +202,12 @@ typedef struct xfs_log_iovec { * Do not change the below structure without redoing the code in * xlog_recover_add_to_trans() and xlog_recover_add_to_cont_trans(). */ -typedef struct xfs_trans_header { +struct xfs_trans_header { uint th_magic; /* magic number */ uint th_type; /* transaction type */ int32_t th_tid; /* transaction id (unused) */ uint th_num_items; /* num items logged by trans */ -} xfs_trans_header_t; +}; #define XFS_TRANS_HEADER_MAGIC 0x5452414e /* TRAN */ @@ -243,6 +235,14 @@ typedef struct xfs_trans_header { #define XFS_LI_BUD 0x1245 #define XFS_LI_ATTRI 0x1246 /* attr set/remove intent*/ #define XFS_LI_ATTRD 0x1247 /* attr set/remove done */ +#define XFS_LI_XMI 0x1248 /* mapping exchange intent */ +#define XFS_LI_XMD 0x1249 /* mapping exchange done */ +#define XFS_LI_EFI_RT 0x124a /* realtime extent free intent */ +#define XFS_LI_EFD_RT 0x124b /* realtime extent free done */ +#define XFS_LI_RUI_RT 0x124c /* realtime rmap update intent */ +#define XFS_LI_RUD_RT 0x124d /* realtime rmap update done */ +#define XFS_LI_CUI_RT 0x124e /* realtime refcount update intent */ +#define XFS_LI_CUD_RT 0x124f /* realtime refcount update done */ #define XFS_LI_TYPE_DESC \ { XFS_LI_EFI, "XFS_LI_EFI" }, \ @@ -260,7 +260,15 @@ typedef struct xfs_trans_header { { XFS_LI_BUI, "XFS_LI_BUI" }, \ { XFS_LI_BUD, "XFS_LI_BUD" }, \ { XFS_LI_ATTRI, "XFS_LI_ATTRI" }, \ - { XFS_LI_ATTRD, "XFS_LI_ATTRD" } + { XFS_LI_ATTRD, "XFS_LI_ATTRD" }, \ + { XFS_LI_XMI, "XFS_LI_XMI" }, \ + { XFS_LI_XMD, "XFS_LI_XMD" }, \ + { XFS_LI_EFI_RT, "XFS_LI_EFI_RT" }, \ + { XFS_LI_EFD_RT, "XFS_LI_EFD_RT" }, \ + { XFS_LI_RUI_RT, "XFS_LI_RUI_RT" }, \ + { XFS_LI_RUD_RT, "XFS_LI_RUD_RT" }, \ + { XFS_LI_CUI_RT, "XFS_LI_CUI_RT" }, \ + { XFS_LI_CUD_RT, "XFS_LI_CUD_RT" } /* * Inode Log Item Format definitions. @@ -324,7 +332,6 @@ struct xfs_inode_log_format_32 { #define XFS_ILOG_DOWNER 0x200 /* change the data fork owner on replay */ #define XFS_ILOG_AOWNER 0x400 /* change the attr fork owner on replay */ - /* * The timestamps are dirty, but not necessarily anything else in the inode * core. Unlike the other fields above this one must never make it to disk @@ -333,11 +340,13 @@ struct xfs_inode_log_format_32 { */ #define XFS_ILOG_TIMESTAMP 0x4000 -#define XFS_ILOG_NONCORE (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \ - XFS_ILOG_DBROOT | XFS_ILOG_DEV | \ - XFS_ILOG_ADATA | XFS_ILOG_AEXT | \ - XFS_ILOG_ABROOT | XFS_ILOG_DOWNER | \ - XFS_ILOG_AOWNER) +/* + * The version field has been changed, but not necessarily anything else of + * interest. This must never make it to disk - it is used purely to ensure that + * the inode item ->precommit operation can update the fsync flag triggers + * in the inode item correctly. + */ +#define XFS_ILOG_IVERSION 0x8000 #define XFS_ILOG_DFORK (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \ XFS_ILOG_DBROOT) @@ -390,7 +399,7 @@ struct xfs_log_dinode { uint16_t di_mode; /* mode and type of file */ int8_t di_version; /* inode version */ int8_t di_format; /* format of di_c data */ - uint8_t di_pad3[2]; /* unused in v2/3 inodes */ + uint16_t di_metatype; /* metadata type, if DIFLAG2_METADATA */ uint32_t di_uid; /* owner's user id */ uint32_t di_gid; /* owner's group id */ uint32_t di_nlink; /* number of links to file */ @@ -455,7 +464,12 @@ struct xfs_log_dinode { xfs_lsn_t di_lsn; uint64_t di_flags2; /* more random flags */ - uint32_t di_cowextsize; /* basic cow extent size for file */ + union { + /* basic cow extent size for (regular) file */ + uint32_t di_cowextsize; + /* used blocks in RTG for (zoned) rtrmap inode */ + uint32_t di_used_blocks; + }; uint8_t di_pad2[12]; /* more padding for future expansion */ /* fields only written to during inode creation */ @@ -517,7 +531,7 @@ struct xfs_log_dinode { #define __XFS_BLF_DATAMAP_SIZE ((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) / NBWORD) #define XFS_BLF_DATAMAP_SIZE (__XFS_BLF_DATAMAP_SIZE + 1) -typedef struct xfs_buf_log_format { +struct xfs_buf_log_format { unsigned short blf_type; /* buf log item type indicator */ unsigned short blf_size; /* size of this item */ unsigned short blf_flags; /* misc state */ @@ -525,7 +539,7 @@ typedef struct xfs_buf_log_format { int64_t blf_blkno; /* starting blkno of this buf */ unsigned int blf_map_size; /* used size of data bitmap in words */ unsigned int blf_data_map[XFS_BLF_DATAMAP_SIZE]; /* dirty bitmap */ -} xfs_buf_log_format_t; +}; /* * All buffers now need to tell recovery where the magic number @@ -581,40 +595,41 @@ xfs_blft_from_flags(struct xfs_buf_log_format *blf) /* * EFI/EFD log format definitions */ -typedef struct xfs_extent { +struct xfs_extent { xfs_fsblock_t ext_start; xfs_extlen_t ext_len; -} xfs_extent_t; +}; /* - * Since an xfs_extent_t has types (start:64, len: 32) - * there are different alignments on 32 bit and 64 bit kernels. - * So we provide the different variants for use by a - * conversion routine. + * Since the structures in struct xfs_extent add up to 96 bytes, it has + * different alignments on i386 vs all other architectures, because i386 + * does not pad structures to their natural alignment. + * + * Provide the different variants for use by a conversion routine. */ -typedef struct xfs_extent_32 { +struct xfs_extent_32 { uint64_t ext_start; uint32_t ext_len; -} __attribute__((packed)) xfs_extent_32_t; +} __attribute__((packed)); -typedef struct xfs_extent_64 { +struct xfs_extent_64 { uint64_t ext_start; uint32_t ext_len; uint32_t ext_pad; -} xfs_extent_64_t; +}; /* * This is the structure used to lay out an efi log item in the * log. The efi_extents field is a variable size array whose * size is given by efi_nextents. */ -typedef struct xfs_efi_log_format { +struct xfs_efi_log_format { uint16_t efi_type; /* efi log item type */ uint16_t efi_size; /* size of this item */ uint32_t efi_nextents; /* # extents to free */ uint64_t efi_id; /* efi identifier */ - xfs_extent_t efi_extents[]; /* array of extents to free */ -} xfs_efi_log_format_t; + struct xfs_extent efi_extents[]; /* array of extents to free */ +}; static inline size_t xfs_efi_log_format_sizeof( @@ -624,13 +639,13 @@ xfs_efi_log_format_sizeof( nr * sizeof(struct xfs_extent); } -typedef struct xfs_efi_log_format_32 { +struct xfs_efi_log_format_32 { uint16_t efi_type; /* efi log item type */ uint16_t efi_size; /* size of this item */ uint32_t efi_nextents; /* # extents to free */ uint64_t efi_id; /* efi identifier */ - xfs_extent_32_t efi_extents[]; /* array of extents to free */ -} __attribute__((packed)) xfs_efi_log_format_32_t; + struct xfs_extent_32 efi_extents[]; /* array of extents to free */ +} __attribute__((packed)); static inline size_t xfs_efi_log_format32_sizeof( @@ -640,13 +655,13 @@ xfs_efi_log_format32_sizeof( nr * sizeof(struct xfs_extent_32); } -typedef struct xfs_efi_log_format_64 { +struct xfs_efi_log_format_64 { uint16_t efi_type; /* efi log item type */ uint16_t efi_size; /* size of this item */ uint32_t efi_nextents; /* # extents to free */ uint64_t efi_id; /* efi identifier */ - xfs_extent_64_t efi_extents[]; /* array of extents to free */ -} xfs_efi_log_format_64_t; + struct xfs_extent_64 efi_extents[]; /* array of extents to free */ +}; static inline size_t xfs_efi_log_format64_sizeof( @@ -661,13 +676,13 @@ xfs_efi_log_format64_sizeof( * log. The efd_extents array is a variable size array whose * size is given by efd_nextents; */ -typedef struct xfs_efd_log_format { +struct xfs_efd_log_format { uint16_t efd_type; /* efd log item type */ uint16_t efd_size; /* size of this item */ uint32_t efd_nextents; /* # of extents freed */ uint64_t efd_efi_id; /* id of corresponding efi */ - xfs_extent_t efd_extents[]; /* array of extents freed */ -} xfs_efd_log_format_t; + struct xfs_extent efd_extents[]; /* array of extents freed */ +}; static inline size_t xfs_efd_log_format_sizeof( @@ -677,13 +692,13 @@ xfs_efd_log_format_sizeof( nr * sizeof(struct xfs_extent); } -typedef struct xfs_efd_log_format_32 { +struct xfs_efd_log_format_32 { uint16_t efd_type; /* efd log item type */ uint16_t efd_size; /* size of this item */ uint32_t efd_nextents; /* # of extents freed */ uint64_t efd_efi_id; /* id of corresponding efi */ - xfs_extent_32_t efd_extents[]; /* array of extents freed */ -} __attribute__((packed)) xfs_efd_log_format_32_t; + struct xfs_extent_32 efd_extents[]; /* array of extents freed */ +} __attribute__((packed)); static inline size_t xfs_efd_log_format32_sizeof( @@ -693,13 +708,13 @@ xfs_efd_log_format32_sizeof( nr * sizeof(struct xfs_extent_32); } -typedef struct xfs_efd_log_format_64 { +struct xfs_efd_log_format_64 { uint16_t efd_type; /* efd log item type */ uint16_t efd_size; /* size of this item */ uint32_t efd_nextents; /* # of extents freed */ uint64_t efd_efi_id; /* id of corresponding efi */ - xfs_extent_64_t efd_extents[]; /* array of extents freed */ -} xfs_efd_log_format_64_t; + struct xfs_extent_64 efd_extents[]; /* array of extents freed */ +}; static inline size_t xfs_efd_log_format64_sizeof( @@ -831,10 +846,12 @@ struct xfs_cud_log_format { #define XFS_BMAP_EXTENT_ATTR_FORK (1U << 31) #define XFS_BMAP_EXTENT_UNWRITTEN (1U << 30) +#define XFS_BMAP_EXTENT_REALTIME (1U << 29) #define XFS_BMAP_EXTENT_FLAGS (XFS_BMAP_EXTENT_TYPE_MASK | \ XFS_BMAP_EXTENT_ATTR_FORK | \ - XFS_BMAP_EXTENT_UNWRITTEN) + XFS_BMAP_EXTENT_UNWRITTEN | \ + XFS_BMAP_EXTENT_REALTIME) /* * This is the structure used to lay out an bui log item in the @@ -870,19 +887,74 @@ struct xfs_bud_log_format { }; /* + * XMI/XMD (file mapping exchange) log format definitions + */ + +/* This is the structure used to lay out an mapping exchange log item. */ +struct xfs_xmi_log_format { + uint16_t xmi_type; /* xmi log item type */ + uint16_t xmi_size; /* size of this item */ + uint32_t __pad; /* must be zero */ + uint64_t xmi_id; /* xmi identifier */ + + uint64_t xmi_inode1; /* inumber of first file */ + uint64_t xmi_inode2; /* inumber of second file */ + uint32_t xmi_igen1; /* generation of first file */ + uint32_t xmi_igen2; /* generation of second file */ + uint64_t xmi_startoff1; /* block offset into file1 */ + uint64_t xmi_startoff2; /* block offset into file2 */ + uint64_t xmi_blockcount; /* number of blocks */ + uint64_t xmi_flags; /* XFS_EXCHMAPS_* */ + uint64_t xmi_isize1; /* intended file1 size */ + uint64_t xmi_isize2; /* intended file2 size */ +}; + +/* Exchange mappings between extended attribute forks instead of data forks. */ +#define XFS_EXCHMAPS_ATTR_FORK (1ULL << 0) + +/* Set the file sizes when finished. */ +#define XFS_EXCHMAPS_SET_SIZES (1ULL << 1) + +/* + * Exchange the mappings of the two files only if the file allocation units + * mapped to file1's range have been written. + */ +#define XFS_EXCHMAPS_INO1_WRITTEN (1ULL << 2) + +/* Clear the reflink flag from inode1 after the operation. */ +#define XFS_EXCHMAPS_CLEAR_INO1_REFLINK (1ULL << 3) + +/* Clear the reflink flag from inode2 after the operation. */ +#define XFS_EXCHMAPS_CLEAR_INO2_REFLINK (1ULL << 4) + +#define XFS_EXCHMAPS_LOGGED_FLAGS (XFS_EXCHMAPS_ATTR_FORK | \ + XFS_EXCHMAPS_SET_SIZES | \ + XFS_EXCHMAPS_INO1_WRITTEN | \ + XFS_EXCHMAPS_CLEAR_INO1_REFLINK | \ + XFS_EXCHMAPS_CLEAR_INO2_REFLINK) + +/* This is the structure used to lay out an mapping exchange done log item. */ +struct xfs_xmd_log_format { + uint16_t xmd_type; /* xmd log item type */ + uint16_t xmd_size; /* size of this item */ + uint32_t __pad; + uint64_t xmd_xmi_id; /* id of corresponding xmi */ +}; + +/* * Dquot Log format definitions. * * The first two fields must be the type and size fitting into * 32 bits : log_recovery code assumes that. */ -typedef struct xfs_dq_logformat { +struct xfs_dq_logformat { uint16_t qlf_type; /* dquot log item type */ uint16_t qlf_size; /* size of this item */ xfs_dqid_t qlf_id; /* usr/grp/proj id : 32 bits */ int64_t qlf_blkno; /* blkno of dquot buffer */ int32_t qlf_len; /* len of dquot buffer */ uint32_t qlf_boffset; /* off of dquot in buffer */ -} xfs_dq_logformat_t; +}; /* * log format struct for QUOTAOFF records. @@ -892,12 +964,12 @@ typedef struct xfs_dq_logformat { * to the first and ensures that the first logitem is taken out of the AIL * only when the last one is securely committed. */ -typedef struct xfs_qoff_logformat { +struct xfs_qoff_logformat { unsigned short qf_type; /* quotaoff log item type */ unsigned short qf_size; /* size of this item */ unsigned int qf_flags; /* USR and/or GRP */ char qf_pad[12]; /* padding for future */ -} xfs_qoff_logformat_t; +}; /* * Disk quotas status in m_qflags, and also sb_qflags. 16 bits. @@ -957,6 +1029,9 @@ struct xfs_icreate_log { #define XFS_ATTRI_OP_FLAGS_SET 1 /* Set the attribute */ #define XFS_ATTRI_OP_FLAGS_REMOVE 2 /* Remove the attribute */ #define XFS_ATTRI_OP_FLAGS_REPLACE 3 /* Replace the attribute */ +#define XFS_ATTRI_OP_FLAGS_PPTR_SET 4 /* Set parent pointer */ +#define XFS_ATTRI_OP_FLAGS_PPTR_REMOVE 5 /* Remove parent pointer */ +#define XFS_ATTRI_OP_FLAGS_PPTR_REPLACE 6 /* Replace parent pointer */ #define XFS_ATTRI_OP_FLAGS_TYPE_MASK 0xFF /* Flags type mask */ /* @@ -965,6 +1040,7 @@ struct xfs_icreate_log { */ #define XFS_ATTRI_FILTER_MASK (XFS_ATTR_ROOT | \ XFS_ATTR_SECURE | \ + XFS_ATTR_PARENT | \ XFS_ATTR_INCOMPLETE) /* @@ -974,11 +1050,22 @@ struct xfs_icreate_log { struct xfs_attri_log_format { uint16_t alfi_type; /* attri log item type */ uint16_t alfi_size; /* size of this item */ - uint32_t __pad; /* pad to 64 bit aligned */ + uint32_t alfi_igen; /* generation of alfi_ino for pptr ops */ uint64_t alfi_id; /* attri identifier */ uint64_t alfi_ino; /* the inode for this attr operation */ uint32_t alfi_op_flags; /* marks the op as a set or remove */ - uint32_t alfi_name_len; /* attr name length */ + union { + uint32_t alfi_name_len; /* attr name length */ + struct { + /* + * For PPTR_REPLACE, these are the lengths of the old + * and new attr names. The new and old values must + * have the same length. + */ + uint16_t alfi_old_name_len; + uint16_t alfi_new_name_len; + }; + }; uint32_t alfi_value_len; /* attr value length */ uint32_t alfi_attr_filter;/* attr filter flags */ }; diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index 2420865f3007..9e712e62369c 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -11,6 +11,7 @@ * define how recovery should work for that type of log item. */ struct xlog_recover_item; +struct xfs_defer_op_type; /* Sorting hat for log items as they're read in. */ enum xlog_recover_reorder { @@ -74,6 +75,14 @@ extern const struct xlog_recover_item_ops xlog_cui_item_ops; extern const struct xlog_recover_item_ops xlog_cud_item_ops; extern const struct xlog_recover_item_ops xlog_attri_item_ops; extern const struct xlog_recover_item_ops xlog_attrd_item_ops; +extern const struct xlog_recover_item_ops xlog_xmi_item_ops; +extern const struct xlog_recover_item_ops xlog_xmd_item_ops; +extern const struct xlog_recover_item_ops xlog_rtefi_item_ops; +extern const struct xlog_recover_item_ops xlog_rtefd_item_ops; +extern const struct xlog_recover_item_ops xlog_rtrui_item_ops; +extern const struct xlog_recover_item_ops xlog_rtrud_item_ops; +extern const struct xlog_recover_item_ops xlog_rtcui_item_ops; +extern const struct xlog_recover_item_ops xlog_rtcud_item_ops; /* * Macros, structures, prototypes for internal log manager use. @@ -95,20 +104,20 @@ struct xlog_recover_item { struct list_head ri_list; int ri_cnt; /* count of regions found */ int ri_total; /* total regions */ - struct xfs_log_iovec *ri_buf; /* ptr to regions buffer */ + struct kvec *ri_buf; /* ptr to regions buffer */ const struct xlog_recover_item_ops *ri_ops; }; struct xlog_recover { struct hlist_node r_list; xlog_tid_t r_log_tid; /* log's transaction id */ - xfs_trans_header_t r_theader; /* trans header for partial */ + struct xfs_trans_header r_theader; /* trans header for partial */ int r_state; /* not needed */ xfs_lsn_t r_lsn; /* xact lsn */ struct list_head r_itemq; /* q for items */ }; -#define ITEM_TYPE(i) (*(unsigned short *)(i)->ri_buf[0].i_addr) +#define ITEM_TYPE(i) (*(unsigned short *)(i)->ri_buf[0].iov_base) #define XLOG_RECOVER_CRCPASS 0 #define XLOG_RECOVER_PASS1 1 @@ -120,6 +129,8 @@ bool xlog_is_buffer_cancelled(struct xlog *log, xfs_daddr_t blkno, uint len); int xlog_recover_iget(struct xfs_mount *mp, xfs_ino_t ino, struct xfs_inode **ipp); +int xlog_recover_iget_handle(struct xfs_mount *mp, xfs_ino_t ino, uint32_t gen, + struct xfs_inode **ipp); void xlog_recover_release_intent(struct xlog *log, unsigned short intent_type, uint64_t intent_id); int xlog_alloc_buf_cancel_table(struct xlog *log); @@ -131,4 +142,33 @@ void xlog_check_buf_cancel_table(struct xlog *log); #define xlog_check_buf_cancel_table(log) do { } while (0) #endif +/* + * Transform a regular reservation into one suitable for recovery of a log + * intent item. + * + * Intent recovery only runs a single step of the transaction chain and defers + * the rest to a separate transaction. Therefore, we reduce logcount to 1 here + * to avoid livelocks if the log grant space is nearly exhausted due to the + * recovered intent pinning the tail. Keep the same logflags to avoid tripping + * asserts elsewhere. Struct copies abound below. + */ +static inline struct xfs_trans_res +xlog_recover_resv(const struct xfs_trans_res *r) +{ + struct xfs_trans_res ret = { + .tr_logres = r->tr_logres, + .tr_logcount = 1, + .tr_logflags = r->tr_logflags, + }; + + return ret; +} + +struct xfs_defer_pending; + +void xlog_recover_intent_item(struct xlog *log, struct xfs_log_item *lip, + xfs_lsn_t lsn, const struct xfs_defer_op_type *ops); +int xlog_recover_finish_intent(struct xfs_trans *tp, + struct xfs_defer_pending *dfp); + #endif /* __XFS_LOG_RECOVER_H__ */ diff --git a/fs/xfs/libxfs/xfs_log_rlimit.c b/fs/xfs/libxfs/xfs_log_rlimit.c index 9975b93a7412..34bba96d30ca 100644 --- a/fs/xfs/libxfs/xfs_log_rlimit.c +++ b/fs/xfs/libxfs/xfs_log_rlimit.c @@ -17,6 +17,34 @@ #include "xfs_trace.h" /* + * Shortly after enabling the large extents count feature in 2023, longstanding + * bugs were found in the code that computes the minimum log size. Luckily, + * the bugs resulted in over-estimates of that size, so there's no impact to + * existing users. However, we don't want to reduce the minimum log size + * because that can create the situation where a newer mkfs writes a new + * filesystem that an older kernel won't mount. + * + * Several years prior, we also discovered that the transaction reservations + * for rmap and reflink operations were unnecessarily large. That was fixed, + * but the minimum log size computation was left alone to avoid the + * compatibility problems noted above. Fix that too. + * + * Therefore, we only may correct the computation starting with filesystem + * features that didn't exist in 2023. In other words, only turn this on if + * the filesystem has parent pointers. + * + * This function can be called before the XFS_HAS_* flags have been set up, + * (e.g. mkfs) so we must check the ondisk superblock. + */ +static inline bool +xfs_want_minlogsize_fixes( + struct xfs_sb *sb) +{ + return xfs_sb_is_v5(sb) && + xfs_sb_has_incompat_feature(sb, XFS_SB_FEAT_INCOMPAT_PARENT); +} + +/* * Calculate the maximum length in bytes that would be required for a local * attribute value as large attributes out of line are not logged. */ @@ -31,6 +59,15 @@ xfs_log_calc_max_attrsetm_res( MAXNAMELEN - 1; nblks = XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK); nblks += XFS_B_TO_FSB(mp, size); + + /* + * If the feature set is new enough, correct a unit conversion error in + * the xattr transaction reservation code that resulted in oversized + * minimum log size computations. + */ + if (xfs_want_minlogsize_fixes(&mp->m_sb)) + size = XFS_B_TO_FSB(mp, size); + nblks += XFS_NEXTENTADD_SPACE_RES(mp, size, XFS_ATTR_FORK); return M_RES(mp)->tr_attrsetm.tr_logres + @@ -49,6 +86,16 @@ xfs_log_calc_trans_resv_for_minlogblocks( unsigned int rmap_maxlevels = mp->m_rmap_maxlevels; /* + * If the feature set is new enough, drop the oversized minimum log + * size computation introduced by the original reflink code. + */ + if (xfs_want_minlogsize_fixes(&mp->m_sb)) { + xfs_trans_resv_calc(mp, resv); + resv->tr_atomic_ioend = M_RES(mp)->tr_atomic_ioend; + return; + } + + /* * In the early days of rmap+reflink, we always set the rmap maxlevels * to 9 even if the AG was small enough that it would never grow to * that height. Transaction reservation sizes influence the minimum @@ -61,6 +108,9 @@ xfs_log_calc_trans_resv_for_minlogblocks( xfs_trans_resv_calc(mp, resv); + /* Copy the dynamic transaction reservation types from the running fs */ + resv->tr_atomic_ioend = M_RES(mp)->tr_atomic_ioend; + if (xfs_has_reflink(mp)) { /* * In the early days of reflink, typical log operation counts diff --git a/fs/xfs/libxfs/xfs_metadir.c b/fs/xfs/libxfs/xfs_metadir.c new file mode 100644 index 000000000000..178e89711cb7 --- /dev/null +++ b/fs/xfs/libxfs/xfs_metadir.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_trans.h" +#include "xfs_metafile.h" +#include "xfs_metadir.h" +#include "xfs_trace.h" +#include "xfs_inode.h" +#include "xfs_quota.h" +#include "xfs_ialloc.h" +#include "xfs_bmap_btree.h" +#include "xfs_da_format.h" +#include "xfs_da_btree.h" +#include "xfs_trans_space.h" +#include "xfs_ag.h" +#include "xfs_dir2.h" +#include "xfs_dir2_priv.h" +#include "xfs_parent.h" +#include "xfs_health.h" +#include "xfs_errortag.h" +#include "xfs_error.h" +#include "xfs_btree.h" +#include "xfs_alloc.h" + +/* + * Metadata Directory Tree + * ======================= + * + * These functions provide an abstraction layer for looking up, creating, and + * deleting metadata inodes that live within a special metadata directory tree. + * + * This code does not manage the five existing metadata inodes: real time + * bitmap & summary; and the user, group, and quotas. All other metadata + * inodes must use only the xfs_meta{dir,file}_* functions. + * + * Callers wishing to create or hardlink a metadata inode must create an + * xfs_metadir_update structure, call the appropriate xfs_metadir* function, + * and then call xfs_metadir_commit or xfs_metadir_cancel to commit or cancel + * the update. Files in the metadata directory tree currently cannot be + * unlinked. + * + * When the metadir feature is enabled, all metadata inodes must have the + * "metadata" inode flag set to prevent them from being exposed to the outside + * world. + * + * Callers must take the ILOCK of any inode in the metadata directory tree to + * synchronize access to that inode. It is never necessary to take the IOLOCK + * or the MMAPLOCK since metadata inodes must not be exposed to user space. + */ + +static inline void +xfs_metadir_set_xname( + struct xfs_name *xname, + const char *path, + unsigned char ftype) +{ + xname->name = (const unsigned char *)path; + xname->len = strlen(path); + xname->type = ftype; +} + +/* + * Given a parent directory @dp and a metadata inode path component @xname, + * Look up the inode number in the directory, returning it in @ino. + * @xname.type must match the directory entry's ftype. + * + * Caller must hold ILOCK_EXCL. + */ +static inline int +xfs_metadir_lookup( + struct xfs_trans *tp, + struct xfs_inode *dp, + struct xfs_name *xname, + xfs_ino_t *ino) +{ + struct xfs_mount *mp = dp->i_mount; + struct xfs_da_args args = { + .trans = tp, + .dp = dp, + .geo = mp->m_dir_geo, + .name = xname->name, + .namelen = xname->len, + .hashval = xfs_dir2_hashname(mp, xname), + .whichfork = XFS_DATA_FORK, + .op_flags = XFS_DA_OP_OKNOENT, + .owner = dp->i_ino, + }; + int error; + + if (!S_ISDIR(VFS_I(dp)->i_mode)) { + xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); + return -EFSCORRUPTED; + } + if (xfs_is_shutdown(mp)) + return -EIO; + + error = xfs_dir_lookup_args(&args); + if (error) + return error; + + if (!xfs_verify_ino(mp, args.inumber)) { + xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); + return -EFSCORRUPTED; + } + if (xname->type != XFS_DIR3_FT_UNKNOWN && xname->type != args.filetype) { + xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); + return -EFSCORRUPTED; + } + + trace_xfs_metadir_lookup(dp, xname, args.inumber); + *ino = args.inumber; + return 0; +} + +/* + * Look up and read a metadata inode from the metadata directory. If the path + * component doesn't exist, return -ENOENT. + */ +int +xfs_metadir_load( + struct xfs_trans *tp, + struct xfs_inode *dp, + const char *path, + enum xfs_metafile_type metafile_type, + struct xfs_inode **ipp) +{ + struct xfs_name xname; + xfs_ino_t ino; + int error; + + xfs_metadir_set_xname(&xname, path, XFS_DIR3_FT_UNKNOWN); + + xfs_ilock(dp, XFS_ILOCK_EXCL); + error = xfs_metadir_lookup(tp, dp, &xname, &ino); + xfs_iunlock(dp, XFS_ILOCK_EXCL); + if (error) + return error; + return xfs_trans_metafile_iget(tp, ino, metafile_type, ipp); +} + +/* + * Unlock and release resources after committing (or cancelling) a metadata + * directory tree operation. The caller retains its reference to @upd->ip + * and must release it explicitly. + */ +static inline void +xfs_metadir_teardown( + struct xfs_metadir_update *upd, + int error) +{ + trace_xfs_metadir_teardown(upd, error); + + if (upd->ppargs) { + xfs_parent_finish(upd->dp->i_mount, upd->ppargs); + upd->ppargs = NULL; + } + + if (upd->ip) { + if (upd->ip_locked) + xfs_iunlock(upd->ip, XFS_ILOCK_EXCL); + upd->ip_locked = false; + } + + if (upd->dp_locked) + xfs_iunlock(upd->dp, XFS_ILOCK_EXCL); + upd->dp_locked = false; +} + +/* + * Begin the process of creating a metadata file by allocating transactions + * and taking whatever resources we're going to need. + */ +int +xfs_metadir_start_create( + struct xfs_metadir_update *upd) +{ + struct xfs_mount *mp = upd->dp->i_mount; + int error; + + ASSERT(upd->dp != NULL); + ASSERT(upd->ip == NULL); + ASSERT(xfs_has_metadir(mp)); + ASSERT(upd->metafile_type != XFS_METAFILE_UNKNOWN); + + error = xfs_parent_start(mp, &upd->ppargs); + if (error) + return error; + + /* + * If we ever need the ability to create rt metadata files on a + * pre-metadir filesystem, we'll need to dqattach the parent here. + * Currently we assume that mkfs will create the files and quotacheck + * will account for them. + */ + + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_create, + xfs_create_space_res(mp, MAXNAMELEN), 0, 0, &upd->tp); + if (error) + goto out_teardown; + + /* + * Lock the parent directory if there is one. We can't ijoin it to + * the transaction until after the child file has been created. + */ + xfs_ilock(upd->dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); + upd->dp_locked = true; + + trace_xfs_metadir_start_create(upd); + return 0; +out_teardown: + xfs_metadir_teardown(upd, error); + return error; +} + +/* + * Create a metadata inode with the given @mode, and insert it into the + * metadata directory tree at the given @upd->path. The path up to the final + * component must already exist. The final path component must not exist. + * + * The new metadata inode will be attached to the update structure @upd->ip, + * with the ILOCK held until the caller releases it. + * + * NOTE: This function may return a new inode to the caller even if it returns + * a negative error code. If an inode is passed back, the caller must finish + * setting up the inode before releasing it. + */ +int +xfs_metadir_create( + struct xfs_metadir_update *upd, + umode_t mode) +{ + struct xfs_icreate_args args = { + .pip = upd->dp, + .mode = mode, + }; + struct xfs_name xname; + struct xfs_dir_update du = { + .dp = upd->dp, + .name = &xname, + .ppargs = upd->ppargs, + }; + struct xfs_mount *mp = upd->dp->i_mount; + xfs_ino_t ino; + unsigned int resblks; + int error; + + xfs_assert_ilocked(upd->dp, XFS_ILOCK_EXCL); + + /* Check that the name does not already exist in the directory. */ + xfs_metadir_set_xname(&xname, upd->path, XFS_DIR3_FT_UNKNOWN); + error = xfs_metadir_lookup(upd->tp, upd->dp, &xname, &ino); + switch (error) { + case -ENOENT: + break; + case 0: + error = -EEXIST; + fallthrough; + default: + return error; + } + + /* + * A newly created regular or special file just has one directory + * entry pointing to them, but a directory also the "." entry + * pointing to itself. + */ + error = xfs_dialloc(&upd->tp, &args, &ino); + if (error) + return error; + error = xfs_icreate(upd->tp, ino, &args, &upd->ip); + if (error) + return error; + du.ip = upd->ip; + xfs_metafile_set_iflag(upd->tp, upd->ip, upd->metafile_type); + upd->ip_locked = true; + + /* + * Join the directory inode to the transaction. We do not do it + * earlier because xfs_dialloc rolls the transaction. + */ + xfs_trans_ijoin(upd->tp, upd->dp, 0); + + /* Create the entry. */ + if (S_ISDIR(args.mode)) + resblks = xfs_mkdir_space_res(mp, xname.len); + else + resblks = xfs_create_space_res(mp, xname.len); + xname.type = xfs_mode_to_ftype(args.mode); + + trace_xfs_metadir_try_create(upd); + + error = xfs_dir_create_child(upd->tp, resblks, &du); + if (error) + return error; + + /* Metadir files are not accounted to quota. */ + + trace_xfs_metadir_create(upd); + + return 0; +} + +#ifndef __KERNEL__ +/* + * Begin the process of linking a metadata file by allocating transactions + * and locking whatever resources we're going to need. + */ +int +xfs_metadir_start_link( + struct xfs_metadir_update *upd) +{ + struct xfs_mount *mp = upd->dp->i_mount; + unsigned int resblks; + int nospace_error = 0; + int error; + + ASSERT(upd->dp != NULL); + ASSERT(upd->ip != NULL); + ASSERT(xfs_has_metadir(mp)); + + error = xfs_parent_start(mp, &upd->ppargs); + if (error) + return error; + + resblks = xfs_link_space_res(mp, MAXNAMELEN); + error = xfs_trans_alloc_dir(upd->dp, &M_RES(mp)->tr_link, upd->ip, + &resblks, &upd->tp, &nospace_error); + if (error) + goto out_teardown; + if (!resblks) { + /* We don't allow reservationless updates. */ + xfs_trans_cancel(upd->tp); + upd->tp = NULL; + xfs_iunlock(upd->dp, XFS_ILOCK_EXCL); + xfs_iunlock(upd->ip, XFS_ILOCK_EXCL); + error = nospace_error; + goto out_teardown; + } + + upd->dp_locked = true; + upd->ip_locked = true; + + trace_xfs_metadir_start_link(upd); + return 0; +out_teardown: + xfs_metadir_teardown(upd, error); + return error; +} + +/* + * Link the metadata directory given by @path to the inode @upd->ip. + * The path (up to the final component) must already exist, but the final + * component must not already exist. + */ +int +xfs_metadir_link( + struct xfs_metadir_update *upd) +{ + struct xfs_name xname; + struct xfs_dir_update du = { + .dp = upd->dp, + .name = &xname, + .ip = upd->ip, + .ppargs = upd->ppargs, + }; + struct xfs_mount *mp = upd->dp->i_mount; + xfs_ino_t ino; + unsigned int resblks; + int error; + + xfs_assert_ilocked(upd->dp, XFS_ILOCK_EXCL); + xfs_assert_ilocked(upd->ip, XFS_ILOCK_EXCL); + + /* Look up the name in the current directory. */ + xfs_metadir_set_xname(&xname, upd->path, + xfs_mode_to_ftype(VFS_I(upd->ip)->i_mode)); + error = xfs_metadir_lookup(upd->tp, upd->dp, &xname, &ino); + switch (error) { + case -ENOENT: + break; + case 0: + error = -EEXIST; + fallthrough; + default: + return error; + } + + resblks = xfs_link_space_res(mp, xname.len); + error = xfs_dir_add_child(upd->tp, resblks, &du); + if (error) + return error; + + trace_xfs_metadir_link(upd); + + return 0; +} +#endif /* ! __KERNEL__ */ + +/* Commit a metadir update and unlock/drop all resources. */ +int +xfs_metadir_commit( + struct xfs_metadir_update *upd) +{ + int error; + + trace_xfs_metadir_commit(upd); + + error = xfs_trans_commit(upd->tp); + upd->tp = NULL; + + xfs_metadir_teardown(upd, error); + return error; +} + +/* Cancel a metadir update and unlock/drop all resources. */ +void +xfs_metadir_cancel( + struct xfs_metadir_update *upd, + int error) +{ + trace_xfs_metadir_cancel(upd); + + xfs_trans_cancel(upd->tp); + upd->tp = NULL; + + xfs_metadir_teardown(upd, error); +} + +/* Create a metadata for the last component of the path. */ +int +xfs_metadir_mkdir( + struct xfs_inode *dp, + const char *path, + struct xfs_inode **ipp) +{ + struct xfs_metadir_update upd = { + .dp = dp, + .path = path, + .metafile_type = XFS_METAFILE_DIR, + }; + int error; + + if (xfs_is_shutdown(dp->i_mount)) + return -EIO; + + /* Allocate a transaction to create the last directory. */ + error = xfs_metadir_start_create(&upd); + if (error) + return error; + + /* Create the subdirectory and take our reference. */ + error = xfs_metadir_create(&upd, S_IFDIR); + if (error) + goto out_cancel; + + error = xfs_metadir_commit(&upd); + if (error) + goto out_irele; + + xfs_finish_inode_setup(upd.ip); + *ipp = upd.ip; + return 0; + +out_cancel: + xfs_metadir_cancel(&upd, error); +out_irele: + /* Have to finish setting up the inode to ensure it's deleted. */ + if (upd.ip) { + xfs_finish_inode_setup(upd.ip); + xfs_irele(upd.ip); + } + return error; +} diff --git a/fs/xfs/libxfs/xfs_metadir.h b/fs/xfs/libxfs/xfs_metadir.h new file mode 100644 index 000000000000..bfecac7d3d14 --- /dev/null +++ b/fs/xfs/libxfs/xfs_metadir.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_METADIR_H__ +#define __XFS_METADIR_H__ + +/* Cleanup widget for metadata inode creation and deletion. */ +struct xfs_metadir_update { + /* Parent directory */ + struct xfs_inode *dp; + + /* Path to metadata file */ + const char *path; + + /* Parent pointer update context */ + struct xfs_parent_args *ppargs; + + /* Child metadata file */ + struct xfs_inode *ip; + + struct xfs_trans *tp; + + enum xfs_metafile_type metafile_type; + + unsigned int dp_locked:1; + unsigned int ip_locked:1; +}; + +int xfs_metadir_load(struct xfs_trans *tp, struct xfs_inode *dp, + const char *path, enum xfs_metafile_type metafile_type, + struct xfs_inode **ipp); + +int xfs_metadir_start_create(struct xfs_metadir_update *upd); +int xfs_metadir_create(struct xfs_metadir_update *upd, umode_t mode); + +int xfs_metadir_start_link(struct xfs_metadir_update *upd); +int xfs_metadir_link(struct xfs_metadir_update *upd); + +int xfs_metadir_commit(struct xfs_metadir_update *upd); +void xfs_metadir_cancel(struct xfs_metadir_update *upd, int error); + +int xfs_metadir_mkdir(struct xfs_inode *dp, const char *path, + struct xfs_inode **ipp); + +#endif /* __XFS_METADIR_H__ */ diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c new file mode 100644 index 000000000000..b02e3d6c0868 --- /dev/null +++ b/fs/xfs/libxfs/xfs_metafile.c @@ -0,0 +1,322 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_trans.h" +#include "xfs_metafile.h" +#include "xfs_trace.h" +#include "xfs_inode.h" +#include "xfs_quota.h" +#include "xfs_errortag.h" +#include "xfs_error.h" +#include "xfs_alloc.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" + +static const struct { + enum xfs_metafile_type mtype; + const char *name; +} xfs_metafile_type_strs[] = { XFS_METAFILE_TYPE_STR }; + +const char * +xfs_metafile_type_str(enum xfs_metafile_type metatype) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(xfs_metafile_type_strs); i++) { + if (xfs_metafile_type_strs[i].mtype == metatype) + return xfs_metafile_type_strs[i].name; + } + + return NULL; +} + +/* Set up an inode to be recognized as a metadata directory inode. */ +void +xfs_metafile_set_iflag( + struct xfs_trans *tp, + struct xfs_inode *ip, + enum xfs_metafile_type metafile_type) +{ + VFS_I(ip)->i_mode &= ~0777; + VFS_I(ip)->i_uid = GLOBAL_ROOT_UID; + VFS_I(ip)->i_gid = GLOBAL_ROOT_GID; + if (S_ISDIR(VFS_I(ip)->i_mode)) + ip->i_diflags |= XFS_METADIR_DIFLAGS; + else + ip->i_diflags |= XFS_METAFILE_DIFLAGS; + ip->i_diflags2 &= ~XFS_DIFLAG2_DAX; + ip->i_diflags2 |= XFS_DIFLAG2_METADATA; + ip->i_metatype = metafile_type; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); +} + +/* Clear the metadata directory inode flag. */ +void +xfs_metafile_clear_iflag( + struct xfs_trans *tp, + struct xfs_inode *ip) +{ + ASSERT(xfs_is_metadir_inode(ip)); + ASSERT(VFS_I(ip)->i_nlink == 0); + + ip->i_diflags2 &= ~XFS_DIFLAG2_METADATA; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); +} + +/* + * Is the metafile reservations at or beneath a certain threshold? + */ +static inline bool +xfs_metafile_resv_can_cover( + struct xfs_mount *mp, + int64_t rhs) +{ + /* + * The amount of space that can be allocated to this metadata file is + * the remaining reservation for the particular metadata file + the + * global free block count. Take care of the first case to avoid + * touching the per-cpu counter. + */ + if (mp->m_metafile_resv_avail >= rhs) + return true; + + /* + * There aren't enough blocks left in the inode's reservation, but it + * isn't critical unless there also isn't enough free space. + */ + return xfs_compare_freecounter(mp, XC_FREE_BLOCKS, + rhs - mp->m_metafile_resv_avail, 2048) >= 0; +} + +/* + * Is the metafile reservation critically low on blocks? For now we'll define + * that as the number of blocks we can get our hands on being less than 10% of + * what we reserved or less than some arbitrary number (maximum btree height). + */ +bool +xfs_metafile_resv_critical( + struct xfs_mount *mp) +{ + ASSERT(xfs_has_metadir(mp)); + + trace_xfs_metafile_resv_critical(mp, 0); + + if (!xfs_metafile_resv_can_cover(mp, mp->m_rtbtree_maxlevels)) + return true; + + if (!xfs_metafile_resv_can_cover(mp, + div_u64(mp->m_metafile_resv_target, 10))) + return true; + + return XFS_TEST_ERROR(mp, XFS_ERRTAG_METAFILE_RESV_CRITICAL); +} + +/* Allocate a block from the metadata file's reservation. */ +void +xfs_metafile_resv_alloc_space( + struct xfs_inode *ip, + struct xfs_alloc_arg *args) +{ + struct xfs_mount *mp = ip->i_mount; + int64_t len = args->len; + + ASSERT(xfs_is_metadir_inode(ip)); + ASSERT(args->resv == XFS_AG_RESV_METAFILE); + + trace_xfs_metafile_resv_alloc_space(mp, args->len); + + /* + * Allocate the blocks from the metadata inode's block reservation + * and update the ondisk sb counter. + */ + mutex_lock(&mp->m_metafile_resv_lock); + if (mp->m_metafile_resv_avail > 0) { + int64_t from_resv; + + from_resv = min_t(int64_t, len, mp->m_metafile_resv_avail); + mp->m_metafile_resv_avail -= from_resv; + xfs_mod_delalloc(ip, 0, -from_resv); + xfs_trans_mod_sb(args->tp, XFS_TRANS_SB_RES_FDBLOCKS, + -from_resv); + len -= from_resv; + } + + /* + * Any allocation in excess of the reservation requires in-core and + * on-disk fdblocks updates. If we can grab @len blocks from the + * in-core fdblocks then all we need to do is update the on-disk + * superblock; if not, then try to steal some from the transaction's + * block reservation. Overruns are only expected for rmap btrees. + */ + if (len) { + unsigned int field; + int error; + + error = xfs_dec_fdblocks(ip->i_mount, len, true); + if (error) + field = XFS_TRANS_SB_FDBLOCKS; + else + field = XFS_TRANS_SB_RES_FDBLOCKS; + + xfs_trans_mod_sb(args->tp, field, -len); + } + + mp->m_metafile_resv_used += args->len; + mutex_unlock(&mp->m_metafile_resv_lock); + + ip->i_nblocks += args->len; + xfs_trans_log_inode(args->tp, ip, XFS_ILOG_CORE); +} + +/* Free a block to the metadata file's reservation. */ +void +xfs_metafile_resv_free_space( + struct xfs_inode *ip, + struct xfs_trans *tp, + xfs_filblks_t len) +{ + struct xfs_mount *mp = ip->i_mount; + int64_t to_resv; + + ASSERT(xfs_is_metadir_inode(ip)); + + trace_xfs_metafile_resv_free_space(mp, len); + + ip->i_nblocks -= len; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + + mutex_lock(&mp->m_metafile_resv_lock); + mp->m_metafile_resv_used -= len; + + /* + * Add the freed blocks back into the inode's delalloc reservation + * until it reaches the maximum size. Update the ondisk fdblocks only. + */ + to_resv = mp->m_metafile_resv_target - + (mp->m_metafile_resv_used + mp->m_metafile_resv_avail); + if (to_resv > 0) { + to_resv = min_t(int64_t, to_resv, len); + mp->m_metafile_resv_avail += to_resv; + xfs_mod_delalloc(ip, 0, to_resv); + xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FDBLOCKS, to_resv); + len -= to_resv; + } + mutex_unlock(&mp->m_metafile_resv_lock); + + /* + * Everything else goes back to the filesystem, so update the in-core + * and on-disk counters. + */ + if (len) + xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, len); +} + +static void +__xfs_metafile_resv_free( + struct xfs_mount *mp) +{ + if (mp->m_metafile_resv_avail) { + xfs_mod_sb_delalloc(mp, -(int64_t)mp->m_metafile_resv_avail); + xfs_add_fdblocks(mp, mp->m_metafile_resv_avail); + } + mp->m_metafile_resv_avail = 0; + mp->m_metafile_resv_used = 0; + mp->m_metafile_resv_target = 0; +} + +/* Release unused metafile space reservation. */ +void +xfs_metafile_resv_free( + struct xfs_mount *mp) +{ + if (!xfs_has_metadir(mp)) + return; + + trace_xfs_metafile_resv_free(mp, 0); + + mutex_lock(&mp->m_metafile_resv_lock); + __xfs_metafile_resv_free(mp); + mutex_unlock(&mp->m_metafile_resv_lock); +} + +/* Set up a metafile space reservation. */ +int +xfs_metafile_resv_init( + struct xfs_mount *mp) +{ + struct xfs_rtgroup *rtg = NULL; + xfs_filblks_t used = 0, target = 0; + xfs_filblks_t hidden_space; + xfs_rfsblock_t dblocks_avail = mp->m_sb.sb_dblocks / 4; + int error = 0; + + if (!xfs_has_metadir(mp)) + return 0; + + /* + * Free any previous reservation to have a clean slate. + */ + mutex_lock(&mp->m_metafile_resv_lock); + __xfs_metafile_resv_free(mp); + + /* + * Currently the only btree metafiles that require reservations are the + * rtrmap and the rtrefcount. Anything new will have to be added here + * as well. + */ + while ((rtg = xfs_rtgroup_next(mp, rtg))) { + if (xfs_has_rtrmapbt(mp)) { + used += rtg_rmap(rtg)->i_nblocks; + target += xfs_rtrmapbt_calc_reserves(mp); + } + if (xfs_has_rtreflink(mp)) { + used += rtg_refcount(rtg)->i_nblocks; + target += xfs_rtrefcountbt_calc_reserves(mp); + } + } + + if (!target) + goto out_unlock; + + /* + * Space taken by the per-AG metadata btrees are accounted on-disk as + * used space. We therefore only hide the space that is reserved but + * not used by the trees. + */ + if (used > target) + target = used; + else if (target > dblocks_avail) + target = dblocks_avail; + hidden_space = target - used; + + error = xfs_dec_fdblocks(mp, hidden_space, true); + if (error) { + trace_xfs_metafile_resv_init_error(mp, 0); + goto out_unlock; + } + + xfs_mod_sb_delalloc(mp, hidden_space); + + mp->m_metafile_resv_target = target; + mp->m_metafile_resv_used = used; + mp->m_metafile_resv_avail = hidden_space; + + trace_xfs_metafile_resv_init(mp, target); + +out_unlock: + mutex_unlock(&mp->m_metafile_resv_lock); + return error; +} diff --git a/fs/xfs/libxfs/xfs_metafile.h b/fs/xfs/libxfs/xfs_metafile.h new file mode 100644 index 000000000000..ae6f9e779b98 --- /dev/null +++ b/fs/xfs/libxfs/xfs_metafile.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_METAFILE_H__ +#define __XFS_METAFILE_H__ + +const char *xfs_metafile_type_str(enum xfs_metafile_type metatype); + +/* All metadata files must have these flags set. */ +#define XFS_METAFILE_DIFLAGS (XFS_DIFLAG_IMMUTABLE | \ + XFS_DIFLAG_SYNC | \ + XFS_DIFLAG_NOATIME | \ + XFS_DIFLAG_NODUMP | \ + XFS_DIFLAG_NODEFRAG) + +/* All metadata directories must have these flags set. */ +#define XFS_METADIR_DIFLAGS (XFS_METAFILE_DIFLAGS | \ + XFS_DIFLAG_NOSYMLINKS) + +void xfs_metafile_set_iflag(struct xfs_trans *tp, struct xfs_inode *ip, + enum xfs_metafile_type metafile_type); +void xfs_metafile_clear_iflag(struct xfs_trans *tp, struct xfs_inode *ip); + +/* Space reservations for metadata inodes. */ +struct xfs_alloc_arg; + +bool xfs_metafile_resv_critical(struct xfs_mount *mp); +void xfs_metafile_resv_alloc_space(struct xfs_inode *ip, + struct xfs_alloc_arg *args); +void xfs_metafile_resv_free_space(struct xfs_inode *ip, struct xfs_trans *tp, + xfs_filblks_t len); +void xfs_metafile_resv_free(struct xfs_mount *mp); +int xfs_metafile_resv_init(struct xfs_mount *mp); + +/* Code specific to kernel/userspace; must be provided externally. */ + +int xfs_trans_metafile_iget(struct xfs_trans *tp, xfs_ino_t ino, + enum xfs_metafile_type metafile_type, struct xfs_inode **ipp); +int xfs_metafile_iget(struct xfs_mount *mp, xfs_ino_t ino, + enum xfs_metafile_type metafile_type, struct xfs_inode **ipp); + +#endif /* __XFS_METAFILE_H__ */ diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h new file mode 100644 index 000000000000..2e9715cc1641 --- /dev/null +++ b/fs/xfs/libxfs/xfs_ondisk.h @@ -0,0 +1,306 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2016 Oracle. + * All Rights Reserved. + */ +#ifndef __XFS_ONDISK_H +#define __XFS_ONDISK_H + +#define XFS_CHECK_STRUCT_SIZE(structname, size) \ + static_assert(sizeof(structname) == (size), \ + "XFS: sizeof(" #structname ") is wrong, expected " #size) + +#define XFS_CHECK_OFFSET(structname, member, off) \ + static_assert(offsetof(structname, member) == (off), \ + "XFS: offsetof(" #structname ", " #member ") is wrong, " \ + "expected " #off) + +#define XFS_CHECK_VALUE(value, expected) \ + static_assert((value) == (expected), \ + "XFS: value of " #value " is wrong, expected " #expected) + +#define XFS_CHECK_SB_OFFSET(field, offset) \ + XFS_CHECK_OFFSET(struct xfs_dsb, field, offset); \ + XFS_CHECK_OFFSET(struct xfs_sb, field, offset); + +static inline void __init +xfs_check_ondisk_structs(void) +{ + /* file structures */ + XFS_CHECK_STRUCT_SIZE(struct xfs_acl, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_acl_entry, 12); + XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_key, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_rec, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_bmdr_block, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_dinode, 176); + XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot, 104); + XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk, 136); + XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr, 56); + XFS_CHECK_STRUCT_SIZE(xfs_timestamp_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_timestamp, 8); + + /* space btrees */ + XFS_CHECK_STRUCT_SIZE(struct xfs_agf, 224); + XFS_CHECK_STRUCT_SIZE(struct xfs_agfl, 36); + XFS_CHECK_STRUCT_SIZE(struct xfs_agi, 344); + XFS_CHECK_STRUCT_SIZE(struct xfs_alloc_rec, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block, 72); + XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_lhdr, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_shdr, 48); + XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_key, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_rec, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_refcount_key, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_refcount_rec, 12); + XFS_CHECK_STRUCT_SIZE(struct xfs_rmap_key, 20); + XFS_CHECK_STRUCT_SIZE(struct xfs_rmap_rec, 24); + XFS_CHECK_STRUCT_SIZE(xfs_alloc_key_t, 8); + XFS_CHECK_STRUCT_SIZE(xfs_alloc_ptr_t, 4); + XFS_CHECK_STRUCT_SIZE(xfs_inobt_ptr_t, 4); + XFS_CHECK_STRUCT_SIZE(xfs_refcount_ptr_t, 4); + XFS_CHECK_STRUCT_SIZE(xfs_rmap_ptr_t, 4); + XFS_CHECK_STRUCT_SIZE(xfs_bmdr_key_t, 8); + + /* dir/attr trees */ + XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leaf_hdr, 80); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leafblock, 80); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_rmt_hdr, 56); + XFS_CHECK_STRUCT_SIZE(struct xfs_da3_blkinfo, 56); + XFS_CHECK_STRUCT_SIZE(struct xfs_da3_intnode, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_da3_node_hdr, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_blk_hdr, 48); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_data_hdr, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free_hdr, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf_hdr, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_entry, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_hdr, 32); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_map, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_local, 4); + + /* realtime structures */ + XFS_CHECK_STRUCT_SIZE(struct xfs_rtsb, 56); + XFS_CHECK_STRUCT_SIZE(union xfs_rtword_raw, 4); + XFS_CHECK_STRUCT_SIZE(union xfs_suminfo_raw, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtbuf_blkinfo, 48); + XFS_CHECK_STRUCT_SIZE(xfs_rtrmap_ptr_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtrmap_root, 4); + XFS_CHECK_STRUCT_SIZE(xfs_rtrefcount_ptr_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtrefcount_root, 4); + + /* + * m68k has problems with struct xfs_attr_leaf_name_remote, but we pad + * it to 4 bytes anyway so it's not obviously a problem. Hence for the + * moment we don't check this structure. This can be re-instated when + * the attr definitions are updated to use c99 VLA definitions. + * + XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_remote, 12); + */ + + XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, valuelen, 0); + XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, namelen, 2); + XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, nameval, 3); + XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, valueblk, 0); + XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, valuelen, 4); + XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, namelen, 8); + XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, name, 9); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leafblock, 32); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_hdr, 4); + XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, totsize, 0); + XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, count, 2); + XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, namelen, 0); + XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, valuelen, 1); + XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, flags, 2); + XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, nameval, 3); + XFS_CHECK_STRUCT_SIZE(struct xfs_da_blkinfo, 12); + XFS_CHECK_STRUCT_SIZE(struct xfs_da_intnode, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_entry, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_hdr, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr, 16); + XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, freetag, 0); + XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, length, 2); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free_hdr, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_entry, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_hdr, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_tail, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_entry, 3); + XFS_CHECK_OFFSET(struct xfs_dir2_sf_entry, namelen, 0); + XFS_CHECK_OFFSET(struct xfs_dir2_sf_entry, offset, 1); + XFS_CHECK_OFFSET(struct xfs_dir2_sf_entry, name, 3); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_hdr, 10); + XFS_CHECK_STRUCT_SIZE(struct xfs_parent_rec, 12); + + /* ondisk dir/attr structures from xfs/122 */ + XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_entry, 3); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_unused, 6); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free_hdr, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_entry, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_hdr, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_tail, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_entry, 3); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_hdr, 10); + + /* log structures */ + XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format, 88); + XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat, 24); + XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_extent_32, 12); + XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode, 176); + XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log, 28); + XFS_CHECK_STRUCT_SIZE(xfs_log_timestamp_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_log_legacy_timestamp, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32, 52); + XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format, 56); + XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat, 20); + XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_attri_log_format, 40); + XFS_CHECK_STRUCT_SIZE(struct xfs_attrd_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_bui_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_bud_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_cui_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_cud_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_rui_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_rud_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_map_extent, 32); + XFS_CHECK_STRUCT_SIZE(struct xfs_phys_extent, 16); + XFS_CHECK_STRUCT_SIZE(struct xlog_rec_header, 512); + XFS_CHECK_STRUCT_SIZE(struct xlog_rec_ext_header, 512); + + XFS_CHECK_OFFSET(struct xlog_rec_header, h_reserved, 328); + XFS_CHECK_OFFSET(struct xlog_rec_ext_header, xh_reserved, 260); + XFS_CHECK_OFFSET(struct xfs_bui_log_format, bui_extents, 16); + XFS_CHECK_OFFSET(struct xfs_cui_log_format, cui_extents, 16); + XFS_CHECK_OFFSET(struct xfs_rui_log_format, rui_extents, 16); + XFS_CHECK_OFFSET(struct xfs_efi_log_format, efi_extents, 16); + XFS_CHECK_OFFSET(struct xfs_efi_log_format_32, efi_extents, 16); + XFS_CHECK_OFFSET(struct xfs_efi_log_format_64, efi_extents, 16); + + /* ondisk log structures from xfs/122 */ + XFS_CHECK_STRUCT_SIZE(struct xfs_unmount_log_format, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_xmd_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_xmi_log_format, 88); + + /* parent pointer ioctls */ + XFS_CHECK_STRUCT_SIZE(struct xfs_getparents_rec, 32); + XFS_CHECK_STRUCT_SIZE(struct xfs_getparents, 40); + XFS_CHECK_STRUCT_SIZE(struct xfs_getparents_by_handle, 64); + + /* + * The v5 superblock format extended several v4 header structures with + * additional data. While new fields are only accessible on v5 + * superblocks, it's important that the v5 structures place original v4 + * fields/headers in the correct location on-disk. For example, we must + * be able to find magic values at the same location in certain blocks + * regardless of superblock version. + * + * The following checks ensure that various v5 data structures place the + * subset of v4 metadata associated with the same type of block at the + * start of the on-disk block. If there is no data structure definition + * for certain types of v4 blocks, traverse down to the first field of + * common metadata (e.g., magic value) and make sure it is at offset + * zero. + */ + XFS_CHECK_OFFSET(struct xfs_dir3_leaf, hdr.info.hdr, 0); + XFS_CHECK_OFFSET(struct xfs_da3_intnode, hdr.info.hdr, 0); + XFS_CHECK_OFFSET(struct xfs_dir3_data_hdr, hdr.magic, 0); + XFS_CHECK_OFFSET(struct xfs_dir3_free, hdr.hdr.magic, 0); + XFS_CHECK_OFFSET(struct xfs_attr3_leafblock, hdr.info.hdr, 0); + + XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat, 192); + XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers, 24); + XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat_req, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers_req, 64); + + /* + * Make sure the incore inode timestamp range corresponds to hand + * converted values based on the ondisk format specification. + */ + XFS_CHECK_VALUE(XFS_BIGTIME_TIME_MIN - XFS_BIGTIME_EPOCH_OFFSET, + XFS_LEGACY_TIME_MIN); + XFS_CHECK_VALUE(XFS_BIGTIME_TIME_MAX - XFS_BIGTIME_EPOCH_OFFSET, + 16299260424LL); + + /* Do the same with the incore quota expiration range. */ + XFS_CHECK_VALUE(XFS_DQ_BIGTIME_EXPIRY_MIN << XFS_DQ_BIGTIME_SHIFT, 4); + XFS_CHECK_VALUE(XFS_DQ_BIGTIME_EXPIRY_MAX << XFS_DQ_BIGTIME_SHIFT, + 16299260424LL); + + /* superblock field checks we got from xfs/122 */ + XFS_CHECK_STRUCT_SIZE(struct xfs_dsb, 304); + XFS_CHECK_STRUCT_SIZE(struct xfs_sb, 304); + XFS_CHECK_SB_OFFSET(sb_magicnum, 0); + XFS_CHECK_SB_OFFSET(sb_blocksize, 4); + XFS_CHECK_SB_OFFSET(sb_dblocks, 8); + XFS_CHECK_SB_OFFSET(sb_rblocks, 16); + XFS_CHECK_SB_OFFSET(sb_rextents, 24); + XFS_CHECK_SB_OFFSET(sb_uuid, 32); + XFS_CHECK_SB_OFFSET(sb_logstart, 48); + XFS_CHECK_SB_OFFSET(sb_rootino, 56); + XFS_CHECK_SB_OFFSET(sb_rbmino, 64); + XFS_CHECK_SB_OFFSET(sb_rsumino, 72); + XFS_CHECK_SB_OFFSET(sb_rextsize, 80); + XFS_CHECK_SB_OFFSET(sb_agblocks, 84); + XFS_CHECK_SB_OFFSET(sb_agcount, 88); + XFS_CHECK_SB_OFFSET(sb_rbmblocks, 92); + XFS_CHECK_SB_OFFSET(sb_logblocks, 96); + XFS_CHECK_SB_OFFSET(sb_versionnum, 100); + XFS_CHECK_SB_OFFSET(sb_sectsize, 102); + XFS_CHECK_SB_OFFSET(sb_inodesize, 104); + XFS_CHECK_SB_OFFSET(sb_inopblock, 106); + XFS_CHECK_SB_OFFSET(sb_blocklog, 120); + XFS_CHECK_SB_OFFSET(sb_fname[12], 120); + XFS_CHECK_SB_OFFSET(sb_sectlog, 121); + XFS_CHECK_SB_OFFSET(sb_inodelog, 122); + XFS_CHECK_SB_OFFSET(sb_inopblog, 123); + XFS_CHECK_SB_OFFSET(sb_agblklog, 124); + XFS_CHECK_SB_OFFSET(sb_rextslog, 125); + XFS_CHECK_SB_OFFSET(sb_inprogress, 126); + XFS_CHECK_SB_OFFSET(sb_imax_pct, 127); + XFS_CHECK_SB_OFFSET(sb_icount, 128); + XFS_CHECK_SB_OFFSET(sb_ifree, 136); + XFS_CHECK_SB_OFFSET(sb_fdblocks, 144); + XFS_CHECK_SB_OFFSET(sb_frextents, 152); + XFS_CHECK_SB_OFFSET(sb_uquotino, 160); + XFS_CHECK_SB_OFFSET(sb_gquotino, 168); + XFS_CHECK_SB_OFFSET(sb_qflags, 176); + XFS_CHECK_SB_OFFSET(sb_flags, 178); + XFS_CHECK_SB_OFFSET(sb_shared_vn, 179); + XFS_CHECK_SB_OFFSET(sb_inoalignmt, 180); + XFS_CHECK_SB_OFFSET(sb_unit, 184); + XFS_CHECK_SB_OFFSET(sb_width, 188); + XFS_CHECK_SB_OFFSET(sb_dirblklog, 192); + XFS_CHECK_SB_OFFSET(sb_logsectlog, 193); + XFS_CHECK_SB_OFFSET(sb_logsectsize, 194); + XFS_CHECK_SB_OFFSET(sb_logsunit, 196); + XFS_CHECK_SB_OFFSET(sb_features2, 200); + XFS_CHECK_SB_OFFSET(sb_bad_features2, 204); + XFS_CHECK_SB_OFFSET(sb_features_compat, 208); + XFS_CHECK_SB_OFFSET(sb_features_ro_compat, 212); + XFS_CHECK_SB_OFFSET(sb_features_incompat, 216); + XFS_CHECK_SB_OFFSET(sb_features_log_incompat, 220); + XFS_CHECK_SB_OFFSET(sb_crc, 224); + XFS_CHECK_SB_OFFSET(sb_spino_align, 228); + XFS_CHECK_SB_OFFSET(sb_pquotino, 232); + XFS_CHECK_SB_OFFSET(sb_lsn, 240); + XFS_CHECK_SB_OFFSET(sb_meta_uuid, 248); + XFS_CHECK_SB_OFFSET(sb_metadirino, 264); + XFS_CHECK_SB_OFFSET(sb_rgcount, 272); + XFS_CHECK_SB_OFFSET(sb_rgextents, 276); + XFS_CHECK_SB_OFFSET(sb_rgblklog, 280); + XFS_CHECK_SB_OFFSET(sb_pad, 281); + XFS_CHECK_SB_OFFSET(sb_rtstart, 288); + XFS_CHECK_SB_OFFSET(sb_rtreserved, 296); +} + +#endif /* __XFS_ONDISK_H */ diff --git a/fs/xfs/libxfs/xfs_parent.c b/fs/xfs/libxfs/xfs_parent.c new file mode 100644 index 000000000000..69366c44a701 --- /dev/null +++ b/fs/xfs/libxfs/xfs_parent.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022-2024 Oracle. + * All rights reserved. + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_format.h" +#include "xfs_da_format.h" +#include "xfs_log_format.h" +#include "xfs_shared.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_bmap_btree.h" +#include "xfs_inode.h" +#include "xfs_error.h" +#include "xfs_trace.h" +#include "xfs_trans.h" +#include "xfs_da_btree.h" +#include "xfs_attr.h" +#include "xfs_dir2.h" +#include "xfs_dir2_priv.h" +#include "xfs_attr_sf.h" +#include "xfs_bmap.h" +#include "xfs_defer.h" +#include "xfs_log.h" +#include "xfs_xattr.h" +#include "xfs_parent.h" +#include "xfs_trans_space.h" +#include "xfs_attr_item.h" +#include "xfs_health.h" + +struct kmem_cache *xfs_parent_args_cache; + +/* + * Parent pointer attribute handling. + * + * Because the attribute name is a filename component, it will never be longer + * than 255 bytes and must not contain nulls or slashes. These are roughly the + * same constraints that apply to attribute names. + * + * The attribute value must always be a struct xfs_parent_rec. This means the + * attribute will never be in remote format because 12 bytes is nowhere near + * xfs_attr_leaf_entsize_local_max() (~75% of block size). + * + * Creating a new parent attribute will always create a new attribute - there + * should never, ever be an existing attribute in the tree for a new inode. + * ENOSPC behavior is problematic - creating the inode without the parent + * pointer is effectively a corruption, so we allow parent attribute creation + * to dip into the reserve block pool to avoid unexpected ENOSPC errors from + * occurring. + */ + +/* Return true if parent pointer attr name is valid. */ +bool +xfs_parent_namecheck( + unsigned int attr_flags, + const void *name, + size_t length) +{ + /* + * Parent pointers always use logged operations, so there should never + * be incomplete xattrs. + */ + if (attr_flags & XFS_ATTR_INCOMPLETE) + return false; + + return xfs_dir2_namecheck(name, length); +} + +/* Return true if parent pointer attr value is valid. */ +bool +xfs_parent_valuecheck( + struct xfs_mount *mp, + const void *value, + size_t valuelen) +{ + const struct xfs_parent_rec *rec = value; + + if (!xfs_has_parent(mp)) + return false; + + /* The xattr value must be a parent record. */ + if (valuelen != sizeof(struct xfs_parent_rec)) + return false; + + /* The parent record must be local. */ + if (value == NULL) + return false; + + /* The parent inumber must be valid. */ + if (!xfs_verify_dir_ino(mp, be64_to_cpu(rec->p_ino))) + return false; + + return true; +} + +/* Compute the attribute name hash for a parent pointer. */ +xfs_dahash_t +xfs_parent_hashval( + struct xfs_mount *mp, + const uint8_t *name, + int namelen, + xfs_ino_t parent_ino) +{ + struct xfs_name xname = { + .name = name, + .len = namelen, + }; + + /* + * Use the same dirent name hash as would be used on the directory, but + * mix in the parent inode number to avoid collisions on hardlinked + * files with identical names but different parents. + */ + return xfs_dir2_hashname(mp, &xname) ^ + upper_32_bits(parent_ino) ^ lower_32_bits(parent_ino); +} + +/* Compute the attribute name hash from the xattr components. */ +xfs_dahash_t +xfs_parent_hashattr( + struct xfs_mount *mp, + const uint8_t *name, + int namelen, + const void *value, + int valuelen) +{ + const struct xfs_parent_rec *rec = value; + + /* Requires a local attr value in xfs_parent_rec format */ + if (valuelen != sizeof(struct xfs_parent_rec)) { + ASSERT(valuelen == sizeof(struct xfs_parent_rec)); + return 0; + } + + if (!value) { + ASSERT(value != NULL); + return 0; + } + + return xfs_parent_hashval(mp, name, namelen, be64_to_cpu(rec->p_ino)); +} + +/* + * Initialize the parent pointer arguments structure. Caller must have zeroed + * the contents of @args. @tp is only required for updates. + */ +static void +xfs_parent_da_args_init( + struct xfs_da_args *args, + struct xfs_trans *tp, + struct xfs_parent_rec *rec, + struct xfs_inode *child, + xfs_ino_t owner, + const struct xfs_name *parent_name) +{ + args->geo = child->i_mount->m_attr_geo; + args->whichfork = XFS_ATTR_FORK; + args->attr_filter = XFS_ATTR_PARENT; + args->op_flags = XFS_DA_OP_LOGGED | XFS_DA_OP_OKNOENT; + args->trans = tp; + args->dp = child; + args->owner = owner; + args->name = parent_name->name; + args->namelen = parent_name->len; + args->value = rec; + args->valuelen = sizeof(struct xfs_parent_rec); + xfs_attr_sethash(args); +} + +/* Make sure the incore state is ready for a parent pointer query/update. */ +static inline int +xfs_parent_iread_extents( + struct xfs_trans *tp, + struct xfs_inode *child) +{ + /* Parent pointers require that the attr fork must exist. */ + if (XFS_IS_CORRUPT(child->i_mount, !xfs_inode_has_attr_fork(child))) { + xfs_inode_mark_sick(child, XFS_SICK_INO_PARENT); + return -EFSCORRUPTED; + } + + return xfs_iread_extents(tp, child, XFS_ATTR_FORK); +} + +/* Add a parent pointer to reflect a dirent addition. */ +int +xfs_parent_addname( + struct xfs_trans *tp, + struct xfs_parent_args *ppargs, + struct xfs_inode *dp, + const struct xfs_name *parent_name, + struct xfs_inode *child) +{ + int error; + + error = xfs_parent_iread_extents(tp, child); + if (error) + return error; + + xfs_inode_to_parent_rec(&ppargs->rec, dp); + xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child, + child->i_ino, parent_name); + xfs_attr_defer_add(&ppargs->args, XFS_ATTR_DEFER_SET); + return 0; +} + +/* Remove a parent pointer to reflect a dirent removal. */ +int +xfs_parent_removename( + struct xfs_trans *tp, + struct xfs_parent_args *ppargs, + struct xfs_inode *dp, + const struct xfs_name *parent_name, + struct xfs_inode *child) +{ + int error; + + error = xfs_parent_iread_extents(tp, child); + if (error) + return error; + + xfs_inode_to_parent_rec(&ppargs->rec, dp); + xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child, + child->i_ino, parent_name); + xfs_attr_defer_add(&ppargs->args, XFS_ATTR_DEFER_REMOVE); + return 0; +} + +/* Replace one parent pointer with another to reflect a rename. */ +int +xfs_parent_replacename( + struct xfs_trans *tp, + struct xfs_parent_args *ppargs, + struct xfs_inode *old_dp, + const struct xfs_name *old_name, + struct xfs_inode *new_dp, + const struct xfs_name *new_name, + struct xfs_inode *child) +{ + int error; + + error = xfs_parent_iread_extents(tp, child); + if (error) + return error; + + xfs_inode_to_parent_rec(&ppargs->rec, old_dp); + xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child, + child->i_ino, old_name); + + xfs_inode_to_parent_rec(&ppargs->new_rec, new_dp); + ppargs->args.new_name = new_name->name; + ppargs->args.new_namelen = new_name->len; + ppargs->args.new_value = &ppargs->new_rec; + ppargs->args.new_valuelen = sizeof(struct xfs_parent_rec); + xfs_attr_defer_add(&ppargs->args, XFS_ATTR_DEFER_REPLACE); + return 0; +} + +/* + * Extract parent pointer information from any parent pointer xattr into + * @parent_ino/gen. The last two parameters can be NULL pointers. + * + * Returns 0 if this is not a parent pointer xattr at all; or -EFSCORRUPTED for + * garbage. + */ +int +xfs_parent_from_attr( + struct xfs_mount *mp, + unsigned int attr_flags, + const unsigned char *name, + unsigned int namelen, + const void *value, + unsigned int valuelen, + xfs_ino_t *parent_ino, + uint32_t *parent_gen) +{ + const struct xfs_parent_rec *rec = value; + + ASSERT(attr_flags & XFS_ATTR_PARENT); + + if (!xfs_parent_namecheck(attr_flags, name, namelen)) + return -EFSCORRUPTED; + if (!xfs_parent_valuecheck(mp, value, valuelen)) + return -EFSCORRUPTED; + + if (parent_ino) + *parent_ino = be64_to_cpu(rec->p_ino); + if (parent_gen) + *parent_gen = be32_to_cpu(rec->p_gen); + return 0; +} + +/* + * Look up a parent pointer record (@parent_name -> @pptr) of @ip. + * + * Caller must hold at least ILOCK_SHARED. The scratchpad need not be + * initialized. + * + * Returns 0 if the pointer is found, -ENOATTR if there is no match, or a + * negative errno. + */ +int +xfs_parent_lookup( + struct xfs_trans *tp, + struct xfs_inode *ip, + const struct xfs_name *parent_name, + struct xfs_parent_rec *pptr, + struct xfs_da_args *scratch) +{ + memset(scratch, 0, sizeof(struct xfs_da_args)); + xfs_parent_da_args_init(scratch, tp, pptr, ip, ip->i_ino, parent_name); + return xfs_attr_get_ilocked(scratch); +} + +/* Sanity-check a parent pointer before we try to perform repairs. */ +static inline bool +xfs_parent_sanity_check( + struct xfs_mount *mp, + const struct xfs_name *parent_name, + const struct xfs_parent_rec *pptr) +{ + if (!xfs_parent_namecheck(XFS_ATTR_PARENT, parent_name->name, + parent_name->len)) + return false; + + if (!xfs_parent_valuecheck(mp, pptr, sizeof(*pptr))) + return false; + + return true; +} + + +/* + * Attach the parent pointer (@parent_name -> @pptr) to @ip immediately. + * Caller must not have a transaction or hold the ILOCK. This is for + * specialized repair functions only. The scratchpad need not be initialized. + */ +int +xfs_parent_set( + struct xfs_inode *ip, + xfs_ino_t owner, + const struct xfs_name *parent_name, + struct xfs_parent_rec *pptr, + struct xfs_da_args *scratch) +{ + if (!xfs_parent_sanity_check(ip->i_mount, parent_name, pptr)) { + ASSERT(0); + return -EFSCORRUPTED; + } + + memset(scratch, 0, sizeof(struct xfs_da_args)); + xfs_parent_da_args_init(scratch, NULL, pptr, ip, owner, parent_name); + return xfs_attr_set(scratch, XFS_ATTRUPDATE_CREATE, false); +} + +/* + * Remove the parent pointer (@parent_name -> @pptr) from @ip immediately. + * Caller must not have a transaction or hold the ILOCK. This is for + * specialized repair functions only. The scratchpad need not be initialized. + */ +int +xfs_parent_unset( + struct xfs_inode *ip, + xfs_ino_t owner, + const struct xfs_name *parent_name, + struct xfs_parent_rec *pptr, + struct xfs_da_args *scratch) +{ + if (!xfs_parent_sanity_check(ip->i_mount, parent_name, pptr)) { + ASSERT(0); + return -EFSCORRUPTED; + } + + memset(scratch, 0, sizeof(struct xfs_da_args)); + xfs_parent_da_args_init(scratch, NULL, pptr, ip, owner, parent_name); + return xfs_attr_set(scratch, XFS_ATTRUPDATE_REMOVE, false); +} diff --git a/fs/xfs/libxfs/xfs_parent.h b/fs/xfs/libxfs/xfs_parent.h new file mode 100644 index 000000000000..b8036527cdc7 --- /dev/null +++ b/fs/xfs/libxfs/xfs_parent.h @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022-2024 Oracle. + * All Rights Reserved. + */ +#ifndef __XFS_PARENT_H__ +#define __XFS_PARENT_H__ + +/* Metadata validators */ +bool xfs_parent_namecheck(unsigned int attr_flags, const void *name, + size_t length); +bool xfs_parent_valuecheck(struct xfs_mount *mp, const void *value, + size_t valuelen); + +xfs_dahash_t xfs_parent_hashval(struct xfs_mount *mp, const uint8_t *name, + int namelen, xfs_ino_t parent_ino); +xfs_dahash_t xfs_parent_hashattr(struct xfs_mount *mp, const uint8_t *name, + int namelen, const void *value, int valuelen); + +/* Initializes a xfs_parent_rec to be stored as an attribute name. */ +static inline void +xfs_parent_rec_init( + struct xfs_parent_rec *rec, + xfs_ino_t ino, + uint32_t gen) +{ + rec->p_ino = cpu_to_be64(ino); + rec->p_gen = cpu_to_be32(gen); +} + +/* Initializes a xfs_parent_rec to be stored as an attribute name. */ +static inline void +xfs_inode_to_parent_rec( + struct xfs_parent_rec *rec, + const struct xfs_inode *dp) +{ + xfs_parent_rec_init(rec, dp->i_ino, VFS_IC(dp)->i_generation); +} + +extern struct kmem_cache *xfs_parent_args_cache; + +/* + * Parent pointer information needed to pass around the deferred xattr update + * machinery. + */ +struct xfs_parent_args { + struct xfs_parent_rec rec; + struct xfs_parent_rec new_rec; + struct xfs_da_args args; +}; + +/* + * Start a parent pointer update by allocating the context object we need to + * perform a parent pointer update. + */ +static inline int +xfs_parent_start( + struct xfs_mount *mp, + struct xfs_parent_args **ppargsp) +{ + if (!xfs_has_parent(mp)) { + *ppargsp = NULL; + return 0; + } + + *ppargsp = kmem_cache_zalloc(xfs_parent_args_cache, GFP_KERNEL); + if (!*ppargsp) + return -ENOMEM; + return 0; +} + +/* Finish a parent pointer update by freeing the context object. */ +static inline void +xfs_parent_finish( + struct xfs_mount *mp, + struct xfs_parent_args *ppargs) +{ + if (ppargs) + kmem_cache_free(xfs_parent_args_cache, ppargs); +} + +int xfs_parent_addname(struct xfs_trans *tp, struct xfs_parent_args *ppargs, + struct xfs_inode *dp, const struct xfs_name *parent_name, + struct xfs_inode *child); +int xfs_parent_removename(struct xfs_trans *tp, struct xfs_parent_args *ppargs, + struct xfs_inode *dp, const struct xfs_name *parent_name, + struct xfs_inode *child); +int xfs_parent_replacename(struct xfs_trans *tp, + struct xfs_parent_args *ppargs, + struct xfs_inode *old_dp, const struct xfs_name *old_name, + struct xfs_inode *new_dp, const struct xfs_name *new_name, + struct xfs_inode *child); + +int xfs_parent_from_attr(struct xfs_mount *mp, unsigned int attr_flags, + const unsigned char *name, unsigned int namelen, + const void *value, unsigned int valuelen, + xfs_ino_t *parent_ino, uint32_t *parent_gen); + +/* Repair functions */ +int xfs_parent_lookup(struct xfs_trans *tp, struct xfs_inode *ip, + const struct xfs_name *name, struct xfs_parent_rec *pptr, + struct xfs_da_args *scratch); +int xfs_parent_set(struct xfs_inode *ip, xfs_ino_t owner, + const struct xfs_name *name, struct xfs_parent_rec *pptr, + struct xfs_da_args *scratch); +int xfs_parent_unset(struct xfs_inode *ip, xfs_ino_t owner, + const struct xfs_name *name, struct xfs_parent_rec *pptr, + struct xfs_da_args *scratch); + +#endif /* __XFS_PARENT_H__ */ diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index cb035da3f990..551d7ae46c5c 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -29,11 +29,9 @@ typedef uint8_t xfs_dqtype_t; * flags for q_flags field in the dquot. */ #define XFS_DQFLAG_DIRTY (1u << 0) /* dquot is dirty */ -#define XFS_DQFLAG_FREEING (1u << 1) /* dquot is being torn down */ #define XFS_DQFLAG_STRINGS \ - { XFS_DQFLAG_DIRTY, "DIRTY" }, \ - { XFS_DQFLAG_FREEING, "FREEING" } + { XFS_DQFLAG_DIRTY, "DIRTY" } /* * We have the possibility of all three quota types being active at once, and @@ -56,7 +54,7 @@ typedef uint8_t xfs_dqtype_t; * And, of course, we also need to take into account the dquot log format item * used to describe each dquot. */ -#define XFS_DQUOT_LOGRES(mp) \ +#define XFS_DQUOT_LOGRES \ ((sizeof(struct xfs_dq_logformat) + sizeof(struct xfs_disk_dquot)) * 6) #define XFS_IS_QUOTA_ON(mp) ((mp)->m_qflags & XFS_ALL_QUOTA_ACCT) @@ -143,4 +141,47 @@ time64_t xfs_dquot_from_disk_ts(struct xfs_disk_dquot *ddq, __be32 dtimer); __be32 xfs_dquot_to_disk_ts(struct xfs_dquot *ddq, time64_t timer); +static inline const char * +xfs_dqinode_path(xfs_dqtype_t type) +{ + switch (type) { + case XFS_DQTYPE_USER: + return "user"; + case XFS_DQTYPE_GROUP: + return "group"; + case XFS_DQTYPE_PROJ: + return "project"; + } + + ASSERT(0); + return NULL; +} + +static inline enum xfs_metafile_type +xfs_dqinode_metafile_type(xfs_dqtype_t type) +{ + switch (type) { + case XFS_DQTYPE_USER: + return XFS_METAFILE_USRQUOTA; + case XFS_DQTYPE_GROUP: + return XFS_METAFILE_GRPQUOTA; + case XFS_DQTYPE_PROJ: + return XFS_METAFILE_PRJQUOTA; + } + + ASSERT(0); + return XFS_METAFILE_UNKNOWN; +} + +unsigned int xfs_dqinode_sick_mask(xfs_dqtype_t type); + +int xfs_dqinode_load(struct xfs_trans *tp, struct xfs_inode *dp, + xfs_dqtype_t type, struct xfs_inode **ipp); +int xfs_dqinode_metadir_create(struct xfs_inode *dp, xfs_dqtype_t type, + struct xfs_inode **ipp); +int xfs_dqinode_metadir_link(struct xfs_inode *dp, xfs_dqtype_t type, + struct xfs_inode *ip); +int xfs_dqinode_mkdir_parent(struct xfs_mount *mp, struct xfs_inode **dpp); +int xfs_dqinode_load_parent(struct xfs_trans *tp, struct xfs_inode **dpp); + #endif /* __XFS_QUOTA_H__ */ diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 6f7ed9288fe4..2484dc9f6d7e 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -23,6 +23,11 @@ #include "xfs_refcount.h" #include "xfs_rmap.h" #include "xfs_ag.h" +#include "xfs_health.h" +#include "xfs_refcount_item.h" +#include "xfs_rtgroup.h" +#include "xfs_rtalloc.h" +#include "xfs_rtrefcount_btree.h" struct kmem_cache *xfs_refcount_intent_cache; @@ -50,7 +55,7 @@ xfs_refcount_lookup_le( xfs_agblock_t bno, int *stat) { - trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, + trace_xfs_refcount_lookup(cur, xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_LE); cur->bc_rec.rc.rc_startblock = bno; @@ -70,7 +75,7 @@ xfs_refcount_lookup_ge( xfs_agblock_t bno, int *stat) { - trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, + trace_xfs_refcount_lookup(cur, xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_GE); cur->bc_rec.rc.rc_startblock = bno; @@ -90,7 +95,7 @@ xfs_refcount_lookup_eq( xfs_agblock_t bno, int *stat) { - trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, + trace_xfs_refcount_lookup(cur, xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_LE); cur->bc_rec.rc.rc_startblock = bno; @@ -120,6 +125,83 @@ xfs_refcount_btrec_to_irec( irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount); } +/* Simple checks for refcount records. */ +xfs_failaddr_t +xfs_refcount_check_irec( + struct xfs_perag *pag, + const struct xfs_refcount_irec *irec) +{ + if (irec->rc_blockcount == 0 || irec->rc_blockcount > XFS_REFC_LEN_MAX) + return __this_address; + + if (!xfs_refcount_check_domain(irec)) + return __this_address; + + /* check for valid extent range, including overflow */ + if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) + return __this_address; + + if (irec->rc_refcount == 0 || irec->rc_refcount > XFS_REFC_REFCOUNT_MAX) + return __this_address; + + return NULL; +} + +xfs_failaddr_t +xfs_rtrefcount_check_irec( + struct xfs_rtgroup *rtg, + const struct xfs_refcount_irec *irec) +{ + if (irec->rc_blockcount == 0 || irec->rc_blockcount > XFS_REFC_LEN_MAX) + return __this_address; + + if (!xfs_refcount_check_domain(irec)) + return __this_address; + + /* check for valid extent range, including overflow */ + if (!xfs_verify_rgbext(rtg, irec->rc_startblock, irec->rc_blockcount)) + return __this_address; + + if (irec->rc_refcount == 0 || irec->rc_refcount > XFS_REFC_REFCOUNT_MAX) + return __this_address; + + return NULL; +} + +static inline xfs_failaddr_t +xfs_refcount_check_btrec( + struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *irec) +{ + if (xfs_btree_is_rtrefcount(cur->bc_ops)) + return xfs_rtrefcount_check_irec(to_rtg(cur->bc_group), irec); + return xfs_refcount_check_irec(to_perag(cur->bc_group), irec); +} + +static inline int +xfs_refcount_complain_bad_rec( + struct xfs_btree_cur *cur, + xfs_failaddr_t fa, + const struct xfs_refcount_irec *irec) +{ + struct xfs_mount *mp = cur->bc_mp; + + if (xfs_btree_is_rtrefcount(cur->bc_ops)) { + xfs_warn(mp, + "RT Refcount BTree record corruption in rtgroup %u detected at %pS!", + cur->bc_group->xg_gno, fa); + } else { + xfs_warn(mp, + "Refcount BTree record corruption in AG %d detected at %pS!", + cur->bc_group->xg_gno, fa); + } + xfs_warn(mp, + "Start block 0x%x, block count 0x%x, references 0x%x", + irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; +} + /* * Get the data from the pointed-to record. */ @@ -129,9 +211,8 @@ xfs_refcount_get_rec( struct xfs_refcount_irec *irec, int *stat) { - struct xfs_mount *mp = cur->bc_mp; - struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; + xfs_failaddr_t fa; int error; error = xfs_btree_get_rec(cur, &rec, stat); @@ -139,30 +220,12 @@ xfs_refcount_get_rec( return error; xfs_refcount_btrec_to_irec(rec, irec); - if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN) - goto out_bad_rec; + fa = xfs_refcount_check_btrec(cur, irec); + if (fa) + return xfs_refcount_complain_bad_rec(cur, fa, irec); - if (!xfs_refcount_check_domain(irec)) - goto out_bad_rec; - - /* check for valid extent range, including overflow */ - if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) - goto out_bad_rec; - - if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT) - goto out_bad_rec; - - trace_xfs_refcount_get(cur->bc_mp, pag->pag_agno, irec); + trace_xfs_refcount_get(cur, irec); return 0; - -out_bad_rec: - xfs_warn(mp, - "Refcount BTree record corruption in AG %d detected!", - pag->pag_agno); - xfs_warn(mp, - "Start block 0x%x, block count 0x%x, references 0x%x", - irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); - return -EFSCORRUPTED; } /* @@ -179,7 +242,7 @@ xfs_refcount_update( uint32_t start; int error; - trace_xfs_refcount_update(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); + trace_xfs_refcount_update(cur, irec); start = xfs_refcount_encode_startblock(irec->rc_startblock, irec->rc_domain); @@ -189,8 +252,7 @@ xfs_refcount_update( error = xfs_btree_update(cur, &rec); if (error) - trace_xfs_refcount_update_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_update_error(cur, error, _RET_IP_); return error; } @@ -207,7 +269,7 @@ xfs_refcount_insert( { int error; - trace_xfs_refcount_insert(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); + trace_xfs_refcount_insert(cur, irec); cur->bc_rec.rc.rc_startblock = irec->rc_startblock; cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount; @@ -218,14 +280,14 @@ xfs_refcount_insert( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } out_error: if (error) - trace_xfs_refcount_insert_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_insert_error(cur, error, _RET_IP_); return error; } @@ -248,12 +310,14 @@ xfs_refcount_delete( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } - trace_xfs_refcount_delete(cur->bc_mp, cur->bc_ag.pag->pag_agno, &irec); + trace_xfs_refcount_delete(cur, &irec); error = xfs_btree_delete(cur, i); if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -263,8 +327,7 @@ xfs_refcount_delete( &found_rec); out_error: if (error) - trace_xfs_refcount_delete_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_delete_error(cur, error, _RET_IP_); return error; } @@ -378,6 +441,7 @@ xfs_refcount_split_extent( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -387,8 +451,7 @@ xfs_refcount_split_extent( return 0; *shape_changed = true; - trace_xfs_refcount_split_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, - &rcext, agbno); + trace_xfs_refcount_split_extent(cur, &rcext, agbno); /* Establish the right extent. */ tmp = rcext; @@ -405,14 +468,14 @@ xfs_refcount_split_extent( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } return error; out_error: - trace_xfs_refcount_split_extent_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_split_extent_error(cur, error, _RET_IP_); return error; } @@ -431,8 +494,7 @@ xfs_refcount_merge_center_extents( int error; int found_rec; - trace_xfs_refcount_merge_center_extents(cur->bc_mp, - cur->bc_ag.pag->pag_agno, left, center, right); + trace_xfs_refcount_merge_center_extents(cur, left, center, right); ASSERT(left->rc_domain == center->rc_domain); ASSERT(right->rc_domain == center->rc_domain); @@ -450,6 +512,7 @@ xfs_refcount_merge_center_extents( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -458,6 +521,7 @@ xfs_refcount_merge_center_extents( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -467,6 +531,7 @@ xfs_refcount_merge_center_extents( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -478,6 +543,7 @@ xfs_refcount_merge_center_extents( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -491,8 +557,7 @@ xfs_refcount_merge_center_extents( return error; out_error: - trace_xfs_refcount_merge_center_extents_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_merge_center_extents_error(cur, error, _RET_IP_); return error; } @@ -510,8 +575,7 @@ xfs_refcount_merge_left_extent( int error; int found_rec; - trace_xfs_refcount_merge_left_extent(cur->bc_mp, - cur->bc_ag.pag->pag_agno, left, cleft); + trace_xfs_refcount_merge_left_extent(cur, left, cleft); ASSERT(left->rc_domain == cleft->rc_domain); @@ -522,6 +586,7 @@ xfs_refcount_merge_left_extent( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -530,6 +595,7 @@ xfs_refcount_merge_left_extent( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -541,6 +607,7 @@ xfs_refcount_merge_left_extent( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -555,8 +622,7 @@ xfs_refcount_merge_left_extent( return error; out_error: - trace_xfs_refcount_merge_left_extent_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_merge_left_extent_error(cur, error, _RET_IP_); return error; } @@ -573,8 +639,7 @@ xfs_refcount_merge_right_extent( int error; int found_rec; - trace_xfs_refcount_merge_right_extent(cur->bc_mp, - cur->bc_ag.pag->pag_agno, cright, right); + trace_xfs_refcount_merge_right_extent(cur, cright, right); ASSERT(right->rc_domain == cright->rc_domain); @@ -588,6 +653,7 @@ xfs_refcount_merge_right_extent( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -596,6 +662,7 @@ xfs_refcount_merge_right_extent( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -607,6 +674,7 @@ xfs_refcount_merge_right_extent( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -621,8 +689,7 @@ xfs_refcount_merge_right_extent( return error; out_error: - trace_xfs_refcount_merge_right_extent_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_merge_right_extent_error(cur, error, _RET_IP_); return error; } @@ -654,6 +721,7 @@ xfs_refcount_find_left_extents( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -673,6 +741,7 @@ xfs_refcount_find_left_extents( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -709,13 +778,11 @@ not_found: cleft->rc_refcount = 1; cleft->rc_domain = domain; } - trace_xfs_refcount_find_left_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, - left, cleft, agbno); + trace_xfs_refcount_find_left_extent(cur, left, cleft, agbno); return error; out_error: - trace_xfs_refcount_find_left_extent_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_find_left_extent_error(cur, error, _RET_IP_); return error; } @@ -747,6 +814,7 @@ xfs_refcount_find_right_extents( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -766,6 +834,7 @@ xfs_refcount_find_right_extents( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -802,13 +871,12 @@ not_found: cright->rc_refcount = 1; cright->rc_domain = domain; } - trace_xfs_refcount_find_right_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, - cright, right, agbno + aglen); + trace_xfs_refcount_find_right_extent(cur, cright, right, + agbno + aglen); return error; out_error: - trace_xfs_refcount_find_right_extent_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_find_right_extent_error(cur, error, _RET_IP_); return error; } @@ -825,9 +893,9 @@ xfs_refc_merge_refcount( const struct xfs_refcount_irec *irec, enum xfs_refc_adjust_op adjust) { - /* Once a record hits MAXREFCOUNT, it is pinned there forever */ - if (irec->rc_refcount == MAXREFCOUNT) - return MAXREFCOUNT; + /* Once a record hits XFS_REFC_REFCOUNT_MAX, it is pinned forever */ + if (irec->rc_refcount == XFS_REFC_REFCOUNT_MAX) + return XFS_REFC_REFCOUNT_MAX; return irec->rc_refcount + adjust; } @@ -870,7 +938,7 @@ xfs_refc_want_merge_center( * hence we need to catch u32 addition overflows here. */ ulen += cleft->rc_blockcount + right->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; *ulenp = ulen; @@ -905,7 +973,7 @@ xfs_refc_want_merge_left( * hence we need to catch u32 addition overflows here. */ ulen += cleft->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; return true; @@ -939,7 +1007,7 @@ xfs_refc_want_merge_right( * hence we need to catch u32 addition overflows here. */ ulen += cright->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; return true; @@ -1036,25 +1104,40 @@ xfs_refcount_still_have_space( * to handle each of the shape changes to the refcount btree. */ overhead = xfs_allocfree_block_count(cur->bc_mp, - cur->bc_ag.refc.shape_changes); - overhead += cur->bc_mp->m_refc_maxlevels; + cur->bc_refc.shape_changes); + overhead += cur->bc_maxlevels; overhead *= cur->bc_mp->m_sb.sb_blocksize; /* * Only allow 2 refcount extent updates per transaction if the * refcount continue update "error" has been injected. */ - if (cur->bc_ag.refc.nr_ops > 2 && - XFS_TEST_ERROR(false, cur->bc_mp, - XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE)) + if (cur->bc_refc.nr_ops > 2 && + XFS_TEST_ERROR(cur->bc_mp, XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE)) return false; - if (cur->bc_ag.refc.nr_ops == 0) + if (cur->bc_refc.nr_ops == 0) return true; else if (overhead > cur->bc_tp->t_log_res) return false; - return cur->bc_tp->t_log_res - overhead > - cur->bc_ag.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD; + return cur->bc_tp->t_log_res - overhead > + cur->bc_refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD; +} + +/* Schedule an extent free. */ +static int +xrefc_free_extent( + struct xfs_btree_cur *cur, + struct xfs_refcount_irec *rec) +{ + unsigned int flags = 0; + + if (xfs_btree_is_rtrefcount(cur->bc_ops)) + flags |= XFS_FREE_EXTENT_REALTIME; + + return xfs_free_extent_later(cur->bc_tp, + xfs_gbno_to_fsb(cur->bc_group, rec->rc_startblock), + rec->rc_blockcount, NULL, XFS_AG_RESV_NONE, flags); } /* @@ -1073,7 +1156,6 @@ xfs_refcount_adjust_extents( struct xfs_refcount_irec ext, tmp; int error; int found_rec, found_tmp; - xfs_fsblock_t fsbno; /* Merging did all the work already. */ if (*aglen == 0) @@ -1089,7 +1171,7 @@ xfs_refcount_adjust_extents( if (error) goto out_error; if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) { - ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; + ext.rc_startblock = xfs_group_max_blocks(cur->bc_group); ext.rc_blockcount = 0; ext.rc_refcount = 0; ext.rc_domain = XFS_REFC_DOMAIN_SHARED; @@ -1107,14 +1189,13 @@ xfs_refcount_adjust_extents( tmp.rc_refcount = 1 + adj; tmp.rc_domain = XFS_REFC_DOMAIN_SHARED; - trace_xfs_refcount_modify_extent(cur->bc_mp, - cur->bc_ag.pag->pag_agno, &tmp); + trace_xfs_refcount_modify_extent(cur, &tmp); /* * Either cover the hole (increment) or * delete the range (decrement). */ - cur->bc_ag.refc.nr_ops++; + cur->bc_refc.nr_ops++; if (tmp.rc_refcount) { error = xfs_refcount_insert(cur, &tmp, &found_tmp); @@ -1122,15 +1203,14 @@ xfs_refcount_adjust_extents( goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_tmp != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } } else { - fsbno = XFS_AGB_TO_FSB(cur->bc_mp, - cur->bc_ag.pag->pag_agno, - tmp.rc_startblock); - xfs_free_extent_later(cur->bc_tp, fsbno, - tmp.rc_blockcount, NULL); + error = xrefc_free_extent(cur, &tmp); + if (error) + goto out_error; } (*agbno) += tmp.rc_blockcount; @@ -1157,6 +1237,7 @@ xfs_refcount_adjust_extents( */ if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) || XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -1165,12 +1246,11 @@ xfs_refcount_adjust_extents( * Adjust the reference count and either update the tree * (incr) or free the blocks (decr). */ - if (ext.rc_refcount == MAXREFCOUNT) + if (ext.rc_refcount == XFS_REFC_REFCOUNT_MAX) goto skip; ext.rc_refcount += adj; - trace_xfs_refcount_modify_extent(cur->bc_mp, - cur->bc_ag.pag->pag_agno, &ext); - cur->bc_ag.refc.nr_ops++; + trace_xfs_refcount_modify_extent(cur, &ext); + cur->bc_refc.nr_ops++; if (ext.rc_refcount > 1) { error = xfs_refcount_update(cur, &ext); if (error) @@ -1180,16 +1260,15 @@ xfs_refcount_adjust_extents( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } goto advloop; } else { - fsbno = XFS_AGB_TO_FSB(cur->bc_mp, - cur->bc_ag.pag->pag_agno, - ext.rc_startblock); - xfs_free_extent_later(cur->bc_tp, fsbno, - ext.rc_blockcount, NULL); + error = xrefc_free_extent(cur, &ext); + if (error) + goto out_error; } skip: @@ -1204,8 +1283,7 @@ advloop: return error; out_error: - trace_xfs_refcount_modify_extent_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_modify_extent_error(cur, error, _RET_IP_); return error; } @@ -1213,37 +1291,31 @@ out_error: STATIC int xfs_refcount_adjust( struct xfs_btree_cur *cur, - xfs_agblock_t agbno, - xfs_extlen_t aglen, - xfs_agblock_t *new_agbno, - xfs_extlen_t *new_aglen, + xfs_agblock_t *agbno, + xfs_extlen_t *aglen, enum xfs_refc_adjust_op adj) { bool shape_changed; int shape_changes = 0; int error; - *new_agbno = agbno; - *new_aglen = aglen; if (adj == XFS_REFCOUNT_ADJUST_INCREASE) - trace_xfs_refcount_increase(cur->bc_mp, cur->bc_ag.pag->pag_agno, - agbno, aglen); + trace_xfs_refcount_increase(cur, *agbno, *aglen); else - trace_xfs_refcount_decrease(cur->bc_mp, cur->bc_ag.pag->pag_agno, - agbno, aglen); + trace_xfs_refcount_decrease(cur, *agbno, *aglen); /* * Ensure that no rcextents cross the boundary of the adjustment range. */ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, - agbno, &shape_changed); + *agbno, &shape_changed); if (error) goto out_error; if (shape_changed) shape_changes++; error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, - agbno + aglen, &shape_changed); + *agbno + *aglen, &shape_changed); if (error) goto out_error; if (shape_changed) @@ -1253,44 +1325,26 @@ xfs_refcount_adjust( * Try to merge with the left or right extents of the range. */ error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_SHARED, - new_agbno, new_aglen, adj, &shape_changed); + agbno, aglen, adj, &shape_changed); if (error) goto out_error; if (shape_changed) shape_changes++; if (shape_changes) - cur->bc_ag.refc.shape_changes++; + cur->bc_refc.shape_changes++; /* Now that we've taken care of the ends, adjust the middle extents */ - error = xfs_refcount_adjust_extents(cur, new_agbno, new_aglen, adj); + error = xfs_refcount_adjust_extents(cur, agbno, aglen, adj); if (error) goto out_error; return 0; out_error: - trace_xfs_refcount_adjust_error(cur->bc_mp, cur->bc_ag.pag->pag_agno, - error, _RET_IP_); + trace_xfs_refcount_adjust_error(cur, error, _RET_IP_); return error; } -/* Clean up after calling xfs_refcount_finish_one. */ -void -xfs_refcount_finish_one_cleanup( - struct xfs_trans *tp, - struct xfs_btree_cur *rcur, - int error) -{ - struct xfs_buf *agbp; - - if (rcur == NULL) - return; - agbp = rcur->bc_ag.agbp; - xfs_btree_del_cursor(rcur, error); - if (error) - xfs_trans_brelse(tp, agbp); -} - /* * Set up a continuation a deferred refcount operation by updating the intent. * Checks to make sure we're not going to run off the end of the AG. @@ -1298,21 +1352,22 @@ xfs_refcount_finish_one_cleanup( static inline int xfs_refcount_continue_op( struct xfs_btree_cur *cur, - xfs_fsblock_t startblock, - xfs_agblock_t new_agbno, - xfs_extlen_t new_len, - xfs_fsblock_t *new_fsbno) + struct xfs_refcount_intent *ri, + xfs_agblock_t new_agbno) { struct xfs_mount *mp = cur->bc_mp; - struct xfs_perag *pag = cur->bc_ag.pag; + struct xfs_perag *pag = to_perag(cur->bc_group); - if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, new_len))) + if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, + ri->ri_blockcount))) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } - *new_fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno); + ri->ri_startblock = xfs_agbno_to_fsb(pag, new_agbno); - ASSERT(xfs_verify_fsbext(mp, *new_fsbno, new_len)); - ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, *new_fsbno)); + ASSERT(xfs_verify_fsbext(mp, ri->ri_startblock, ri->ri_blockcount)); + ASSERT(pag_agno(pag) == XFS_FSB_TO_AGNO(mp, ri->ri_startblock)); return 0; } @@ -1327,97 +1382,192 @@ xfs_refcount_continue_op( int xfs_refcount_finish_one( struct xfs_trans *tp, - enum xfs_refcount_intent_type type, - xfs_fsblock_t startblock, - xfs_extlen_t blockcount, - xfs_fsblock_t *new_fsb, - xfs_extlen_t *new_len, + struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_btree_cur *rcur; + struct xfs_btree_cur *rcur = *pcur; struct xfs_buf *agbp = NULL; int error = 0; xfs_agblock_t bno; - xfs_agblock_t new_agbno; unsigned long nr_ops = 0; int shape_changes = 0; - struct xfs_perag *pag; - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, startblock)); - bno = XFS_FSB_TO_AGBNO(mp, startblock); + bno = XFS_FSB_TO_AGBNO(mp, ri->ri_startblock); - trace_xfs_refcount_deferred(mp, XFS_FSB_TO_AGNO(mp, startblock), - type, XFS_FSB_TO_AGBNO(mp, startblock), - blockcount); + trace_xfs_refcount_deferred(mp, ri); - if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) { - error = -EIO; - goto out_drop; - } + if (XFS_TEST_ERROR(mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) + return -EIO; /* * If we haven't gotten a cursor or the cursor AG doesn't match * the startblock, get one now. */ - rcur = *pcur; - if (rcur != NULL && rcur->bc_ag.pag != pag) { - nr_ops = rcur->bc_ag.refc.nr_ops; - shape_changes = rcur->bc_ag.refc.shape_changes; - xfs_refcount_finish_one_cleanup(tp, rcur, 0); + if (rcur != NULL && rcur->bc_group != ri->ri_group) { + nr_ops = rcur->bc_refc.nr_ops; + shape_changes = rcur->bc_refc.shape_changes; + xfs_btree_del_cursor(rcur, 0); rcur = NULL; *pcur = NULL; } if (rcur == NULL) { - error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_FREEING, - &agbp); + struct xfs_perag *pag = to_perag(ri->ri_group); + + error = xfs_alloc_read_agf(pag, tp, + XFS_ALLOC_FLAG_FREEING, &agbp); if (error) - goto out_drop; + return error; - rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); - rcur->bc_ag.refc.nr_ops = nr_ops; - rcur->bc_ag.refc.shape_changes = shape_changes; + *pcur = rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); + rcur->bc_refc.nr_ops = nr_ops; + rcur->bc_refc.shape_changes = shape_changes; } - *pcur = rcur; - switch (type) { + switch (ri->ri_type) { case XFS_REFCOUNT_INCREASE: - error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno, - new_len, XFS_REFCOUNT_ADJUST_INCREASE); + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_INCREASE); if (error) - goto out_drop; - if (*new_len > 0) - error = xfs_refcount_continue_op(rcur, startblock, - new_agbno, *new_len, new_fsb); + return error; + if (ri->ri_blockcount > 0) + error = xfs_refcount_continue_op(rcur, ri, bno); break; case XFS_REFCOUNT_DECREASE: - error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno, - new_len, XFS_REFCOUNT_ADJUST_DECREASE); + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_DECREASE); if (error) - goto out_drop; - if (*new_len > 0) - error = xfs_refcount_continue_op(rcur, startblock, - new_agbno, *new_len, new_fsb); + return error; + if (ri->ri_blockcount > 0) + error = xfs_refcount_continue_op(rcur, ri, bno); break; case XFS_REFCOUNT_ALLOC_COW: - *new_fsb = startblock + blockcount; - *new_len = 0; - error = __xfs_refcount_cow_alloc(rcur, bno, blockcount); + error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount); + if (error) + return error; + ri->ri_blockcount = 0; break; case XFS_REFCOUNT_FREE_COW: - *new_fsb = startblock + blockcount; - *new_len = 0; - error = __xfs_refcount_cow_free(rcur, bno, blockcount); + error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount); + if (error) + return error; + ri->ri_blockcount = 0; break; default: ASSERT(0); - error = -EFSCORRUPTED; + return -EFSCORRUPTED; } - if (!error && *new_len > 0) - trace_xfs_refcount_finish_one_leftover(mp, pag->pag_agno, type, - bno, blockcount, new_agbno, *new_len); -out_drop: - xfs_perag_put(pag); + if (!error && ri->ri_blockcount > 0) + trace_xfs_refcount_finish_one_leftover(mp, ri); + return error; +} + +/* + * Set up a continuation a deferred rtrefcount operation by updating the + * intent. Checks to make sure we're not going to run off the end of the + * rtgroup. + */ +static inline int +xfs_rtrefcount_continue_op( + struct xfs_btree_cur *cur, + struct xfs_refcount_intent *ri, + xfs_agblock_t new_agbno) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + + if (XFS_IS_CORRUPT(mp, !xfs_verify_rgbext(rtg, new_agbno, + ri->ri_blockcount))) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + + ri->ri_startblock = xfs_rgbno_to_rtb(rtg, new_agbno); + + ASSERT(xfs_verify_rtbext(mp, ri->ri_startblock, ri->ri_blockcount)); + return 0; +} + +/* + * Process one of the deferred realtime refcount operations. We pass back the + * btree cursor to maintain our lock on the btree between calls. + */ +int +xfs_rtrefcount_finish_one( + struct xfs_trans *tp, + struct xfs_refcount_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + struct xfs_btree_cur *rcur = *pcur; + int error = 0; + xfs_rgblock_t bno; + unsigned long nr_ops = 0; + int shape_changes = 0; + + bno = xfs_rtb_to_rgbno(mp, ri->ri_startblock); + + trace_xfs_refcount_deferred(mp, ri); + + if (XFS_TEST_ERROR(mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) + return -EIO; + + /* + * If we haven't gotten a cursor or the cursor AG doesn't match + * the startblock, get one now. + */ + if (rcur != NULL && rcur->bc_group != ri->ri_group) { + nr_ops = rcur->bc_refc.nr_ops; + shape_changes = rcur->bc_refc.shape_changes; + xfs_btree_del_cursor(rcur, 0); + rcur = NULL; + *pcur = NULL; + } + if (rcur == NULL) { + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_REFCOUNT); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_REFCOUNT); + *pcur = rcur = xfs_rtrefcountbt_init_cursor(tp, rtg); + + rcur->bc_refc.nr_ops = nr_ops; + rcur->bc_refc.shape_changes = shape_changes; + } + + switch (ri->ri_type) { + case XFS_REFCOUNT_INCREASE: + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_INCREASE); + if (error) + return error; + if (ri->ri_blockcount > 0) + error = xfs_rtrefcount_continue_op(rcur, ri, bno); + break; + case XFS_REFCOUNT_DECREASE: + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_DECREASE); + if (error) + return error; + if (ri->ri_blockcount > 0) + error = xfs_rtrefcount_continue_op(rcur, ri, bno); + break; + case XFS_REFCOUNT_ALLOC_COW: + error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount); + if (error) + return error; + ri->ri_blockcount = 0; + break; + case XFS_REFCOUNT_FREE_COW: + error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount); + if (error) + return error; + ri->ri_blockcount = 0; + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + if (!error && ri->ri_blockcount > 0) + trace_xfs_refcount_finish_one_leftover(mp, ri); return error; } @@ -1428,24 +1578,21 @@ static void __xfs_refcount_add( struct xfs_trans *tp, enum xfs_refcount_intent_type type, + bool isrt, xfs_fsblock_t startblock, xfs_extlen_t blockcount) { struct xfs_refcount_intent *ri; - trace_xfs_refcount_defer(tp->t_mountp, - XFS_FSB_TO_AGNO(tp->t_mountp, startblock), - type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock), - blockcount); - ri = kmem_cache_alloc(xfs_refcount_intent_cache, - GFP_NOFS | __GFP_NOFAIL); + GFP_KERNEL | __GFP_NOFAIL); INIT_LIST_HEAD(&ri->ri_list); ri->ri_type = type; ri->ri_startblock = startblock; ri->ri_blockcount = blockcount; + ri->ri_realtime = isrt; - xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list); + xfs_refcount_defer_add(tp, ri); } /* @@ -1454,12 +1601,13 @@ __xfs_refcount_add( void xfs_refcount_increase_extent( struct xfs_trans *tp, + bool isrt, struct xfs_bmbt_irec *PREV) { if (!xfs_has_reflink(tp->t_mountp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, PREV->br_startblock, + __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, isrt, PREV->br_startblock, PREV->br_blockcount); } @@ -1469,12 +1617,13 @@ xfs_refcount_increase_extent( void xfs_refcount_decrease_extent( struct xfs_trans *tp, + bool isrt, struct xfs_bmbt_irec *PREV) { if (!xfs_has_reflink(tp->t_mountp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, PREV->br_startblock, + __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, isrt, PREV->br_startblock, PREV->br_blockcount); } @@ -1500,8 +1649,7 @@ xfs_refcount_find_shared( int have; int error; - trace_xfs_refcount_find_shared(cur->bc_mp, cur->bc_ag.pag->pag_agno, - agbno, aglen); + trace_xfs_refcount_find_shared(cur, agbno, aglen); /* By default, skip the whole range */ *fbno = NULLAGBLOCK; @@ -1524,6 +1672,7 @@ xfs_refcount_find_shared( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -1541,6 +1690,7 @@ xfs_refcount_find_shared( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -1574,6 +1724,7 @@ xfs_refcount_find_shared( if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -1585,13 +1736,11 @@ xfs_refcount_find_shared( } done: - trace_xfs_refcount_find_shared_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, *fbno, *flen); + trace_xfs_refcount_find_shared_result(cur, *fbno, *flen); out_error: if (error) - trace_xfs_refcount_find_shared_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_find_shared_error(cur, error, _RET_IP_); return error; } @@ -1671,11 +1820,12 @@ xfs_refcount_adjust_cow_extents( goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec && ext.rc_domain != XFS_REFC_DOMAIN_COW)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (!found_rec) { - ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; + ext.rc_startblock = xfs_group_max_blocks(cur->bc_group); ext.rc_blockcount = 0; ext.rc_refcount = 0; ext.rc_domain = XFS_REFC_DOMAIN_COW; @@ -1686,6 +1836,7 @@ xfs_refcount_adjust_cow_extents( /* Adding a CoW reservation, there should be nothing here. */ if (XFS_IS_CORRUPT(cur->bc_mp, agbno + aglen > ext.rc_startblock)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -1695,14 +1846,14 @@ xfs_refcount_adjust_cow_extents( tmp.rc_refcount = 1; tmp.rc_domain = XFS_REFC_DOMAIN_COW; - trace_xfs_refcount_modify_extent(cur->bc_mp, - cur->bc_ag.pag->pag_agno, &tmp); + trace_xfs_refcount_modify_extent(cur, &tmp); error = xfs_refcount_insert(cur, &tmp, &found_tmp); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_tmp != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -1710,25 +1861,28 @@ xfs_refcount_adjust_cow_extents( case XFS_REFCOUNT_ADJUST_COW_FREE: /* Removing a CoW reservation, there should be one extent. */ if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_startblock != agbno)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount != aglen)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_refcount != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } ext.rc_refcount = 0; - trace_xfs_refcount_modify_extent(cur->bc_mp, - cur->bc_ag.pag->pag_agno, &ext); + trace_xfs_refcount_modify_extent(cur, &ext); error = xfs_refcount_delete(cur, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -1739,8 +1893,7 @@ xfs_refcount_adjust_cow_extents( return error; out_error: - trace_xfs_refcount_modify_extent_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_refcount_modify_extent_error(cur, error, _RET_IP_); return error; } @@ -1786,8 +1939,7 @@ xfs_refcount_adjust_cow( return 0; out_error: - trace_xfs_refcount_adjust_cow_error(cur->bc_mp, cur->bc_ag.pag->pag_agno, - error, _RET_IP_); + trace_xfs_refcount_adjust_cow_error(cur, error, _RET_IP_); return error; } @@ -1800,8 +1952,7 @@ __xfs_refcount_cow_alloc( xfs_agblock_t agbno, xfs_extlen_t aglen) { - trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_ag.pag->pag_agno, - agbno, aglen); + trace_xfs_refcount_cow_increase(rcur, agbno, aglen); /* Add refcount btree reservation */ return xfs_refcount_adjust_cow(rcur, agbno, aglen, @@ -1817,8 +1968,7 @@ __xfs_refcount_cow_free( xfs_agblock_t agbno, xfs_extlen_t aglen) { - trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_ag.pag->pag_agno, - agbno, aglen); + trace_xfs_refcount_cow_decrease(rcur, agbno, aglen); /* Remove refcount btree reservation */ return xfs_refcount_adjust_cow(rcur, agbno, aglen, @@ -1829,6 +1979,7 @@ __xfs_refcount_cow_free( void xfs_refcount_alloc_cow_extent( struct xfs_trans *tp, + bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len) { @@ -1837,17 +1988,17 @@ xfs_refcount_alloc_cow_extent( if (!xfs_has_reflink(mp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len); + __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, isrt, fsb, len); /* Add rmap entry */ - xfs_rmap_alloc_extent(tp, XFS_FSB_TO_AGNO(mp, fsb), - XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); + xfs_rmap_alloc_extent(tp, isrt, fsb, len, XFS_RMAP_OWN_COW); } /* Forget a CoW staging event in the refcount btree. */ void xfs_refcount_free_cow_extent( struct xfs_trans *tp, + bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len) { @@ -1857,9 +2008,8 @@ xfs_refcount_free_cow_extent( return; /* Remove rmap entry */ - xfs_rmap_free_extent(tp, XFS_FSB_TO_AGNO(mp, fsb), - XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); - __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len); + xfs_rmap_free_extent(tp, isrt, fsb, len, XFS_RMAP_OWN_COW); + __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, isrt, fsb, len); } struct xfs_refcount_recovery { @@ -1878,16 +2028,20 @@ xfs_refcount_recover_extent( struct xfs_refcount_recovery *rr; if (XFS_IS_CORRUPT(cur->bc_mp, - be32_to_cpu(rec->refc.rc_refcount) != 1)) + be32_to_cpu(rec->refc.rc_refcount) != 1)) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } rr = kmalloc(sizeof(struct xfs_refcount_recovery), GFP_KERNEL | __GFP_NOFAIL); INIT_LIST_HEAD(&rr->rr_list); xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec); - if (XFS_IS_CORRUPT(cur->bc_mp, + if (xfs_refcount_check_btrec(cur, &rr->rr_rrec) != NULL || + XFS_IS_CORRUPT(cur->bc_mp, rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) { + xfs_btree_mark_sick(cur); kfree(rr); return -EFSCORRUPTED; } @@ -1899,23 +2053,38 @@ xfs_refcount_recover_extent( /* Find and remove leftover CoW reservations. */ int xfs_refcount_recover_cow_leftovers( - struct xfs_mount *mp, - struct xfs_perag *pag) + struct xfs_group *xg) { + struct xfs_mount *mp = xg->xg_mount; + bool isrt = xg->xg_type == XG_TYPE_RTG; struct xfs_trans *tp; struct xfs_btree_cur *cur; - struct xfs_buf *agbp; + struct xfs_buf *agbp = NULL; struct xfs_refcount_recovery *rr, *n; struct list_head debris; - union xfs_btree_irec low; - union xfs_btree_irec high; + union xfs_btree_irec low = { + .rc.rc_domain = XFS_REFC_DOMAIN_COW, + }; + union xfs_btree_irec high = { + .rc.rc_domain = XFS_REFC_DOMAIN_COW, + .rc.rc_startblock = -1U, + }; xfs_fsblock_t fsb; int error; - /* reflink filesystems mustn't have AGs larger than 2^31-1 blocks */ + /* reflink filesystems must not have groups larger than 2^31-1 blocks */ + BUILD_BUG_ON(XFS_MAX_RGBLOCKS >= XFS_REFC_COWFLAG); BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG); - if (mp->m_sb.sb_agblocks > XFS_MAX_CRC_AG_BLOCKS) - return -EOPNOTSUPP; + + if (isrt) { + if (!xfs_has_rtgroups(mp)) + return 0; + if (xfs_group_max_blocks(xg) >= XFS_MAX_RGBLOCKS) + return -EOPNOTSUPP; + } else { + if (xfs_group_max_blocks(xg) > XFS_MAX_CRC_AG_BLOCKS) + return -EOPNOTSUPP; + } INIT_LIST_HEAD(&debris); @@ -1929,24 +2098,26 @@ xfs_refcount_recover_cow_leftovers( * recording the CoW debris we cancel the (empty) transaction * and everything goes away cleanly. */ - error = xfs_trans_alloc_empty(mp, &tp); - if (error) - return error; + tp = xfs_trans_alloc_empty(mp); - error = xfs_alloc_read_agf(pag, tp, 0, &agbp); - if (error) - goto out_trans; - cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); + if (isrt) { + xfs_rtgroup_lock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT); + cur = xfs_rtrefcountbt_init_cursor(tp, to_rtg(xg)); + } else { + error = xfs_alloc_read_agf(to_perag(xg), tp, 0, &agbp); + if (error) + goto out_trans; + cur = xfs_refcountbt_init_cursor(mp, tp, agbp, to_perag(xg)); + } /* Find all the leftover CoW staging extents. */ - memset(&low, 0, sizeof(low)); - memset(&high, 0, sizeof(high)); - low.rc.rc_domain = high.rc.rc_domain = XFS_REFC_DOMAIN_COW; - high.rc.rc_startblock = -1U; error = xfs_btree_query_range(cur, &low, &high, xfs_refcount_recover_extent, &debris); xfs_btree_del_cursor(cur, error); - xfs_trans_brelse(tp, agbp); + if (agbp) + xfs_trans_brelse(tp, agbp); + else + xfs_rtgroup_unlock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT); xfs_trans_cancel(tp); if (error) goto out_free; @@ -1958,17 +2129,18 @@ xfs_refcount_recover_cow_leftovers( if (error) goto out_free; - trace_xfs_refcount_recover_extent(mp, pag->pag_agno, - &rr->rr_rrec); - /* Free the orphan record */ - fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, - rr->rr_rrec.rc_startblock); - xfs_refcount_free_cow_extent(tp, fsb, + fsb = xfs_gbno_to_fsb(xg, rr->rr_rrec.rc_startblock); + xfs_refcount_free_cow_extent(tp, isrt, fsb, rr->rr_rrec.rc_blockcount); /* Free the block. */ - xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL); + error = xfs_free_extent_later(tp, fsb, + rr->rr_rrec.rc_blockcount, NULL, + XFS_AG_RESV_NONE, + isrt ? XFS_FREE_EXTENT_REALTIME : 0); + if (error) + goto out_trans; error = xfs_trans_commit(tp); if (error) @@ -1990,14 +2162,17 @@ out_free: return error; } -/* Is there a record covering a given extent? */ +/* + * Scan part of the keyspace of the refcount records and tell us if the area + * has no records, is fully mapped by records, or is partially filled. + */ int -xfs_refcount_has_record( +xfs_refcount_has_records( struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, xfs_extlen_t len, - bool *exists) + enum xbtree_recpacking *outcome) { union xfs_btree_irec low; union xfs_btree_irec high; @@ -2008,7 +2183,48 @@ xfs_refcount_has_record( high.rc.rc_startblock = bno + len - 1; low.rc.rc_domain = high.rc.rc_domain = domain; - return xfs_btree_has_record(cur, &low, &high, exists); + return xfs_btree_has_records(cur, &low, &high, NULL, outcome); +} + +struct xfs_refcount_query_range_info { + xfs_refcount_query_range_fn fn; + void *priv; +}; + +/* Format btree record and pass to our callback. */ +STATIC int +xfs_refcount_query_range_helper( + struct xfs_btree_cur *cur, + const union xfs_btree_rec *rec, + void *priv) +{ + struct xfs_refcount_query_range_info *query = priv; + struct xfs_refcount_irec irec; + xfs_failaddr_t fa; + + xfs_refcount_btrec_to_irec(rec, &irec); + fa = xfs_refcount_check_btrec(cur, &irec); + if (fa) + return xfs_refcount_complain_bad_rec(cur, fa, &irec); + + return query->fn(cur, &irec, query->priv); +} + +/* Find all refcount records between two keys. */ +int +xfs_refcount_query_range( + struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *low_rec, + const struct xfs_refcount_irec *high_rec, + xfs_refcount_query_range_fn fn, + void *priv) +{ + union xfs_btree_irec low_brec = { .rc = *low_rec }; + union xfs_btree_irec high_brec = { .rc = *high_rec }; + struct xfs_refcount_query_range_info query = { .priv = priv, .fn = fn }; + + return xfs_btree_query_range(cur, &low_brec, &high_brec, + xfs_refcount_query_range_helper, &query); } int __init diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index 452f30556f5a..f2e299a716a4 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -12,6 +12,7 @@ struct xfs_perag; struct xfs_btree_cur; struct xfs_bmbt_irec; struct xfs_refcount_irec; +struct xfs_rtgroup; extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); @@ -48,11 +49,19 @@ enum xfs_refcount_intent_type { XFS_REFCOUNT_FREE_COW, }; +#define XFS_REFCOUNT_INTENT_STRINGS \ + { XFS_REFCOUNT_INCREASE, "incr" }, \ + { XFS_REFCOUNT_DECREASE, "decr" }, \ + { XFS_REFCOUNT_ALLOC_COW, "alloc_cow" }, \ + { XFS_REFCOUNT_FREE_COW, "free_cow" } + struct xfs_refcount_intent { struct list_head ri_list; + struct xfs_group *ri_group; enum xfs_refcount_intent_type ri_type; xfs_extlen_t ri_blockcount; xfs_fsblock_t ri_startblock; + bool ri_realtime; }; /* Check that the refcount is appropriate for the record domain. */ @@ -67,28 +76,25 @@ xfs_refcount_check_domain( return true; } -void xfs_refcount_increase_extent(struct xfs_trans *tp, +void xfs_refcount_increase_extent(struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *irec); -void xfs_refcount_decrease_extent(struct xfs_trans *tp, +void xfs_refcount_decrease_extent(struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *irec); -extern void xfs_refcount_finish_one_cleanup(struct xfs_trans *tp, - struct xfs_btree_cur *rcur, int error); -extern int xfs_refcount_finish_one(struct xfs_trans *tp, - enum xfs_refcount_intent_type type, xfs_fsblock_t startblock, - xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb, - xfs_extlen_t *new_len, struct xfs_btree_cur **pcur); +int xfs_refcount_finish_one(struct xfs_trans *tp, + struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); +int xfs_rtrefcount_finish_one(struct xfs_trans *tp, + struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); extern int xfs_refcount_find_shared(struct xfs_btree_cur *cur, xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_end_of_shared); -void xfs_refcount_alloc_cow_extent(struct xfs_trans *tp, xfs_fsblock_t fsb, - xfs_extlen_t len); -void xfs_refcount_free_cow_extent(struct xfs_trans *tp, xfs_fsblock_t fsb, - xfs_extlen_t len); -extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, - struct xfs_perag *pag); +void xfs_refcount_alloc_cow_extent(struct xfs_trans *tp, bool isrt, + xfs_fsblock_t fsb, xfs_extlen_t len); +void xfs_refcount_free_cow_extent(struct xfs_trans *tp, bool isrt, + xfs_fsblock_t fsb, xfs_extlen_t len); +int xfs_refcount_recover_cow_leftovers(struct xfs_group *xg); /* * While we're adjusting the refcounts records of an extent, we have @@ -109,12 +115,16 @@ extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, */ #define XFS_REFCOUNT_ITEM_OVERHEAD 32 -extern int xfs_refcount_has_record(struct xfs_btree_cur *cur, +extern int xfs_refcount_has_records(struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, - xfs_extlen_t len, bool *exists); + xfs_extlen_t len, enum xbtree_recpacking *outcome); union xfs_btree_rec; extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec); +xfs_failaddr_t xfs_refcount_check_irec(struct xfs_perag *pag, + const struct xfs_refcount_irec *irec); +xfs_failaddr_t xfs_rtrefcount_check_irec(struct xfs_rtgroup *rtg, + const struct xfs_refcount_irec *irec); extern int xfs_refcount_insert(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat); @@ -123,4 +133,14 @@ extern struct kmem_cache *xfs_refcount_intent_cache; int __init xfs_refcount_intent_init_cache(void); void xfs_refcount_intent_destroy_cache(void); +typedef int (*xfs_refcount_query_range_fn)( + struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *rec, + void *priv); + +int xfs_refcount_query_range(struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *low_rec, + const struct xfs_refcount_irec *high_rec, + xfs_refcount_query_range_fn fn, void *priv); + #endif /* __XFS_REFCOUNT_H__ */ diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index e1f789866683..06da3ca14727 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -16,6 +16,7 @@ #include "xfs_refcount.h" #include "xfs_alloc.h" #include "xfs_error.h" +#include "xfs_health.h" #include "xfs_trace.h" #include "xfs_trans.h" #include "xfs_bit.h" @@ -29,7 +30,7 @@ xfs_refcountbt_dup_cursor( struct xfs_btree_cur *cur) { return xfs_refcountbt_init_cursor(cur->bc_mp, cur->bc_tp, - cur->bc_ag.agbp, cur->bc_ag.pag); + cur->bc_ag.agbp, to_perag(cur->bc_group)); } STATIC void @@ -67,23 +68,20 @@ xfs_refcountbt_alloc_block( memset(&args, 0, sizeof(args)); args.tp = cur->bc_tp; args.mp = cur->bc_mp; - args.type = XFS_ALLOCTYPE_NEAR_BNO; - args.fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno, - xfs_refc_block(args.mp)); + args.pag = to_perag(cur->bc_group); args.oinfo = XFS_RMAP_OINFO_REFC; args.minlen = args.maxlen = args.prod = 1; args.resv = XFS_AG_RESV_METADATA; - error = xfs_alloc_vextent(&args); + error = xfs_alloc_vextent_near_bno(&args, + xfs_agbno_to_fsb(args.pag, xfs_refc_block(args.mp))); if (error) goto out_error; - trace_xfs_refcountbt_alloc_block(cur->bc_mp, cur->bc_ag.pag->pag_agno, - args.agbno, 1); if (args.fsbno == NULLFSBLOCK) { *stat = 0; return 0; } - ASSERT(args.agno == cur->bc_ag.pag->pag_agno); + ASSERT(args.agno == cur->bc_group->xg_gno); ASSERT(args.len == 1); new->s = cpu_to_be32(args.agbno); @@ -106,18 +104,11 @@ xfs_refcountbt_free_block( struct xfs_buf *agbp = cur->bc_ag.agbp; struct xfs_agf *agf = agbp->b_addr; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); - int error; - trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.pag->pag_agno, - XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1); be32_add_cpu(&agf->agf_refcount_blocks, -1); xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS); - error = xfs_free_extent(cur->bc_tp, fsbno, 1, &XFS_RMAP_OINFO_REFC, - XFS_AG_RESV_METADATA); - if (error) - return error; - - return error; + return xfs_free_extent_later(cur->bc_tp, fsbno, 1, + &XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA, 0); } STATIC int @@ -178,13 +169,13 @@ xfs_refcountbt_init_ptr_from_cur( { struct xfs_agf *agf = cur->bc_ag.agbp->b_addr; - ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno)); + ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agf->agf_seqno)); ptr->s = agf->agf_refcount_root; } -STATIC int64_t -xfs_refcountbt_key_diff( +STATIC int +xfs_refcountbt_cmp_key_with_cur( struct xfs_btree_cur *cur, const union xfs_btree_key *key) { @@ -194,17 +185,20 @@ xfs_refcountbt_key_diff( start = xfs_refcount_encode_startblock(irec->rc_startblock, irec->rc_domain); - return (int64_t)be32_to_cpu(kp->rc_startblock) - start; + return cmp_int(be32_to_cpu(kp->rc_startblock), start); } -STATIC int64_t -xfs_refcountbt_diff_two_keys( +STATIC int +xfs_refcountbt_cmp_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { - return (int64_t)be32_to_cpu(k1->refc.rc_startblock) - - be32_to_cpu(k2->refc.rc_startblock); + ASSERT(!mask || mask->refc.rc_startblock); + + return cmp_int(be32_to_cpu(k1->refc.rc_startblock), + be32_to_cpu(k2->refc.rc_startblock)); } STATIC xfs_failaddr_t @@ -222,18 +216,29 @@ xfs_refcountbt_verify( if (!xfs_has_reflink(mp)) return __this_address; - fa = xfs_btree_sblock_v5hdr_verify(bp); + fa = xfs_btree_agblock_v5hdr_verify(bp); if (fa) return fa; level = be16_to_cpu(block->bb_level); - if (pag && pag->pagf_init) { - if (level >= pag->pagf_refcount_level) + if (pag && xfs_perag_initialised_agf(pag)) { + unsigned int maxlevel = pag->pagf_refcount_level; + +#ifdef CONFIG_XFS_ONLINE_REPAIR + /* + * Online repair could be rewriting the refcount btree, so + * we'll validate against the larger of either tree while this + * is going on. + */ + maxlevel = max_t(unsigned int, maxlevel, + pag->pagf_repair_refcount_level); +#endif + if (level >= maxlevel) return __this_address; } else if (level >= mp->m_refc_maxlevels) return __this_address; - return xfs_btree_sblock_verify(bp, mp->m_refc_mxr[level != 0]); + return xfs_btree_agblock_verify(bp, mp->m_refc_mxr[level != 0]); } STATIC void @@ -242,7 +247,7 @@ xfs_refcountbt_read_verify( { xfs_failaddr_t fa; - if (!xfs_btree_sblock_verify_crc(bp)) + if (!xfs_btree_agblock_verify_crc(bp)) xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_refcountbt_verify(bp); @@ -266,7 +271,7 @@ xfs_refcountbt_write_verify( xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } - xfs_btree_sblock_calc_crc(bp); + xfs_btree_agblock_calc_crc(bp); } @@ -299,9 +304,30 @@ xfs_refcountbt_recs_inorder( be32_to_cpu(r2->refc.rc_startblock); } -static const struct xfs_btree_ops xfs_refcountbt_ops = { +STATIC enum xbtree_key_contig +xfs_refcountbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->refc.rc_startblock); + + return xbtree_key_contig(be32_to_cpu(key1->refc.rc_startblock), + be32_to_cpu(key2->refc.rc_startblock)); +} + +const struct xfs_btree_ops xfs_refcountbt_ops = { + .name = "refcount", + .type = XFS_BTREE_TYPE_AG, + .rec_len = sizeof(struct xfs_refcount_rec), .key_len = sizeof(struct xfs_refcount_key), + .ptr_len = XFS_BTREE_SHORT_PTR_LEN, + + .lru_refs = XFS_REFC_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_refcbt_2), + .sick_mask = XFS_SICK_AG_REFCNTBT, .dup_cursor = xfs_refcountbt_dup_cursor, .set_root = xfs_refcountbt_set_root, @@ -313,43 +339,19 @@ static const struct xfs_btree_ops xfs_refcountbt_ops = { .init_high_key_from_rec = xfs_refcountbt_init_high_key_from_rec, .init_rec_from_cur = xfs_refcountbt_init_rec_from_cur, .init_ptr_from_cur = xfs_refcountbt_init_ptr_from_cur, - .key_diff = xfs_refcountbt_key_diff, + .cmp_key_with_cur = xfs_refcountbt_cmp_key_with_cur, .buf_ops = &xfs_refcountbt_buf_ops, - .diff_two_keys = xfs_refcountbt_diff_two_keys, + .cmp_two_keys = xfs_refcountbt_cmp_two_keys, .keys_inorder = xfs_refcountbt_keys_inorder, .recs_inorder = xfs_refcountbt_recs_inorder, + .keys_contiguous = xfs_refcountbt_keys_contiguous, }; /* - * Initialize a new refcount btree cursor. + * Create a new refcount btree cursor. + * + * For staging cursors tp and agbp are NULL. */ -static struct xfs_btree_cur * -xfs_refcountbt_init_common( - struct xfs_mount *mp, - struct xfs_trans *tp, - struct xfs_perag *pag) -{ - struct xfs_btree_cur *cur; - - ASSERT(pag->pag_agno < mp->m_sb.sb_agcount); - - cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_REFC, - mp->m_refc_maxlevels, xfs_refcountbt_cur_cache); - cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_refcbt_2); - - cur->bc_flags |= XFS_BTREE_CRC_BLOCKS; - - /* take a reference for the cursor */ - atomic_inc(&pag->pag_ref); - cur->bc_ag.pag = pag; - - cur->bc_ag.refc.nr_ops = 0; - cur->bc_ag.refc.shape_changes = 0; - cur->bc_ops = &xfs_refcountbt_ops; - return cur; -} - -/* Create a btree cursor. */ struct xfs_btree_cur * xfs_refcountbt_init_cursor( struct xfs_mount *mp, @@ -357,26 +359,21 @@ xfs_refcountbt_init_cursor( struct xfs_buf *agbp, struct xfs_perag *pag) { - struct xfs_agf *agf = agbp->b_addr; struct xfs_btree_cur *cur; - cur = xfs_refcountbt_init_common(mp, tp, pag); - cur->bc_nlevels = be32_to_cpu(agf->agf_refcount_level); - cur->bc_ag.agbp = agbp; - return cur; -} + ASSERT(pag_agno(pag) < mp->m_sb.sb_agcount); -/* Create a btree cursor with a fake root for staging. */ -struct xfs_btree_cur * -xfs_refcountbt_stage_cursor( - struct xfs_mount *mp, - struct xbtree_afakeroot *afake, - struct xfs_perag *pag) -{ - struct xfs_btree_cur *cur; + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_refcountbt_ops, + mp->m_refc_maxlevels, xfs_refcountbt_cur_cache); + cur->bc_group = xfs_group_hold(pag_group(pag)); + cur->bc_refc.nr_ops = 0; + cur->bc_refc.shape_changes = 0; + cur->bc_ag.agbp = agbp; + if (agbp) { + struct xfs_agf *agf = agbp->b_addr; - cur = xfs_refcountbt_init_common(mp, NULL, pag); - xfs_btree_stage_afakeroot(cur, afake); + cur->bc_nlevels = be32_to_cpu(agf->agf_refcount_level); + } return cur; } @@ -401,7 +398,7 @@ xfs_refcountbt_commit_staged_btree( xfs_alloc_log_agf(tp, agbp, XFS_AGF_REFCOUNT_BLOCKS | XFS_AGF_REFCOUNT_ROOT | XFS_AGF_REFCOUNT_LEVEL); - xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_refcountbt_ops); + xfs_btree_commit_afakeroot(cur, tp, agbp); } /* Calculate number of records in a refcount btree block. */ @@ -419,9 +416,10 @@ xfs_refcountbt_block_maxrecs( /* * Calculate the number of records in a refcount btree block. */ -int +unsigned int xfs_refcountbt_maxrecs( - int blocklen, + struct xfs_mount *mp, + unsigned int blocklen, bool leaf) { blocklen -= XFS_REFCOUNT_BLOCK_LEN; @@ -516,7 +514,7 @@ xfs_refcountbt_calc_reserves( * never be available for the kinds of things that would require btree * expansion. We therefore can pretend the space isn't there. */ - if (xfs_ag_contains_log(mp, pag->pag_agno)) + if (xfs_ag_contains_log(mp, pag_agno(pag))) agblocks -= mp->m_sb.sb_logblocks; *ask += xfs_refcountbt_max_size(mp, agblocks); diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h index d66b37259bed..beb93bef6a81 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.h +++ b/fs/xfs/libxfs/xfs_refcount_btree.h @@ -48,9 +48,8 @@ struct xbtree_afakeroot; extern struct xfs_btree_cur *xfs_refcountbt_init_cursor(struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_buf *agbp, struct xfs_perag *pag); -struct xfs_btree_cur *xfs_refcountbt_stage_cursor(struct xfs_mount *mp, - struct xbtree_afakeroot *afake, struct xfs_perag *pag); -extern int xfs_refcountbt_maxrecs(int blocklen, bool leaf); +unsigned int xfs_refcountbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, + bool leaf); extern void xfs_refcountbt_compute_maxlevels(struct xfs_mount *mp); extern xfs_extlen_t xfs_refcountbt_calc_size(struct xfs_mount *mp, diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index b56aca1e7c66..83e0488ff773 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -23,6 +23,10 @@ #include "xfs_error.h" #include "xfs_inode.h" #include "xfs_ag.h" +#include "xfs_health.h" +#include "xfs_rmap_item.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" struct kmem_cache *xfs_rmap_intent_cache; @@ -56,8 +60,10 @@ xfs_rmap_lookup_le( error = xfs_rmap_get_rec(cur, irec, &get_stat); if (error) return error; - if (!get_stat) + if (!get_stat) { + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; + } return 0; } @@ -97,8 +103,7 @@ xfs_rmap_update( union xfs_btree_rec rec; int error; - trace_xfs_rmap_update(cur->bc_mp, cur->bc_ag.pag->pag_agno, - irec->rm_startblock, irec->rm_blockcount, + trace_xfs_rmap_update(cur, irec->rm_startblock, irec->rm_blockcount, irec->rm_owner, irec->rm_offset, irec->rm_flags); rec.rmap.rm_startblock = cpu_to_be32(irec->rm_startblock); @@ -108,8 +113,7 @@ xfs_rmap_update( xfs_rmap_irec_offset_pack(irec)); error = xfs_btree_update(cur, &rec); if (error) - trace_xfs_rmap_update_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_rmap_update_error(cur, error, _RET_IP_); return error; } @@ -125,13 +129,13 @@ xfs_rmap_insert( int i; int error; - trace_xfs_rmap_insert(rcur->bc_mp, rcur->bc_ag.pag->pag_agno, agbno, - len, owner, offset, flags); + trace_xfs_rmap_insert(rcur, agbno, len, owner, offset, flags); error = xfs_rmap_lookup_eq(rcur, agbno, len, owner, offset, flags, &i); if (error) goto done; if (XFS_IS_CORRUPT(rcur->bc_mp, i != 0)) { + xfs_btree_mark_sick(rcur); error = -EFSCORRUPTED; goto done; } @@ -145,13 +149,13 @@ xfs_rmap_insert( if (error) goto done; if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) { + xfs_btree_mark_sick(rcur); error = -EFSCORRUPTED; goto done; } done: if (error) - trace_xfs_rmap_insert_error(rcur->bc_mp, - rcur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_rmap_insert_error(rcur, error, _RET_IP_); return error; } @@ -167,13 +171,13 @@ xfs_rmap_delete( int i; int error; - trace_xfs_rmap_delete(rcur->bc_mp, rcur->bc_ag.pag->pag_agno, agbno, - len, owner, offset, flags); + trace_xfs_rmap_delete(rcur, agbno, len, owner, offset, flags); error = xfs_rmap_lookup_eq(rcur, agbno, len, owner, offset, flags, &i); if (error) goto done; if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) { + xfs_btree_mark_sick(rcur); error = -EFSCORRUPTED; goto done; } @@ -182,18 +186,18 @@ xfs_rmap_delete( if (error) goto done; if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) { + xfs_btree_mark_sick(rcur); error = -EFSCORRUPTED; goto done; } done: if (error) - trace_xfs_rmap_delete_error(rcur->bc_mp, - rcur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_rmap_delete_error(rcur, error, _RET_IP_); return error; } /* Convert an internal btree record to an rmap record. */ -int +xfs_failaddr_t xfs_rmap_btrec_to_irec( const union xfs_btree_rec *rec, struct xfs_rmap_irec *irec) @@ -205,58 +209,190 @@ xfs_rmap_btrec_to_irec( irec); } -/* - * Get the data from the pointed-to record. - */ -int -xfs_rmap_get_rec( - struct xfs_btree_cur *cur, - struct xfs_rmap_irec *irec, - int *stat) +/* Simple checks for rmap records. */ +xfs_failaddr_t +xfs_rmap_check_irec( + struct xfs_perag *pag, + const struct xfs_rmap_irec *irec) { - struct xfs_mount *mp = cur->bc_mp; - struct xfs_perag *pag = cur->bc_ag.pag; - union xfs_btree_rec *rec; - int error; - - error = xfs_btree_get_rec(cur, &rec, stat); - if (error || !*stat) - return error; - - if (xfs_rmap_btrec_to_irec(rec, irec)) - goto out_bad_rec; + struct xfs_mount *mp = pag_mount(pag); + bool is_inode; + bool is_unwritten; + bool is_bmbt; + bool is_attr; if (irec->rm_blockcount == 0) - goto out_bad_rec; + return __this_address; if (irec->rm_startblock <= XFS_AGFL_BLOCK(mp)) { if (irec->rm_owner != XFS_RMAP_OWN_FS) - goto out_bad_rec; + return __this_address; if (irec->rm_blockcount != XFS_AGFL_BLOCK(mp) + 1) - goto out_bad_rec; + return __this_address; } else { /* check for valid extent range, including overflow */ if (!xfs_verify_agbext(pag, irec->rm_startblock, irec->rm_blockcount)) - goto out_bad_rec; + return __this_address; } if (!(xfs_verify_ino(mp, irec->rm_owner) || (irec->rm_owner <= XFS_RMAP_OWN_FS && irec->rm_owner >= XFS_RMAP_OWN_MIN))) - goto out_bad_rec; + return __this_address; - return 0; -out_bad_rec: - xfs_warn(mp, - "Reverse Mapping BTree record corruption in AG %d detected!", - pag->pag_agno); + /* Check flags. */ + is_inode = !XFS_RMAP_NON_INODE_OWNER(irec->rm_owner); + is_bmbt = irec->rm_flags & XFS_RMAP_BMBT_BLOCK; + is_attr = irec->rm_flags & XFS_RMAP_ATTR_FORK; + is_unwritten = irec->rm_flags & XFS_RMAP_UNWRITTEN; + + if (is_bmbt && irec->rm_offset != 0) + return __this_address; + + if (!is_inode && irec->rm_offset != 0) + return __this_address; + + if (is_unwritten && (is_bmbt || !is_inode || is_attr)) + return __this_address; + + if (!is_inode && (is_bmbt || is_unwritten || is_attr)) + return __this_address; + + /* Check for a valid fork offset, if applicable. */ + if (is_inode && !is_bmbt && + !xfs_verify_fileext(mp, irec->rm_offset, irec->rm_blockcount)) + return __this_address; + + return NULL; +} + +static xfs_failaddr_t +xfs_rtrmap_check_meta_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (irec->rm_offset != 0) + return __this_address; + if (irec->rm_flags & XFS_RMAP_UNWRITTEN) + return __this_address; + + switch (irec->rm_owner) { + case XFS_RMAP_OWN_FS: + if (irec->rm_startblock != 0) + return __this_address; + if (irec->rm_blockcount != mp->m_sb.sb_rextsize) + return __this_address; + return NULL; + case XFS_RMAP_OWN_COW: + if (!xfs_has_rtreflink(mp)) + return __this_address; + if (!xfs_verify_rgbext(rtg, irec->rm_startblock, + irec->rm_blockcount)) + return __this_address; + return NULL; + default: + return __this_address; + } + + return NULL; +} + +static xfs_failaddr_t +xfs_rtrmap_check_inode_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (!xfs_verify_ino(mp, irec->rm_owner)) + return __this_address; + if (!xfs_verify_rgbext(rtg, irec->rm_startblock, irec->rm_blockcount)) + return __this_address; + if (!xfs_verify_fileext(mp, irec->rm_offset, irec->rm_blockcount)) + return __this_address; + return NULL; +} + +xfs_failaddr_t +xfs_rtrmap_check_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + if (irec->rm_blockcount == 0) + return __this_address; + if (irec->rm_flags & (XFS_RMAP_BMBT_BLOCK | XFS_RMAP_ATTR_FORK)) + return __this_address; + if (XFS_RMAP_NON_INODE_OWNER(irec->rm_owner)) + return xfs_rtrmap_check_meta_irec(rtg, irec); + return xfs_rtrmap_check_inode_irec(rtg, irec); +} + +static inline xfs_failaddr_t +xfs_rmap_check_btrec( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *irec) +{ + if (xfs_btree_is_rtrmap(cur->bc_ops) || + xfs_btree_is_mem_rtrmap(cur->bc_ops)) + return xfs_rtrmap_check_irec(to_rtg(cur->bc_group), irec); + return xfs_rmap_check_irec(to_perag(cur->bc_group), irec); +} + +static inline int +xfs_rmap_complain_bad_rec( + struct xfs_btree_cur *cur, + xfs_failaddr_t fa, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = cur->bc_mp; + + if (xfs_btree_is_mem_rmap(cur->bc_ops)) + xfs_warn(mp, + "In-Memory Reverse Mapping BTree record corruption detected at %pS!", fa); + else if (xfs_btree_is_rtrmap(cur->bc_ops)) + xfs_warn(mp, + "RT Reverse Mapping BTree record corruption in rtgroup %u detected at %pS!", + cur->bc_group->xg_gno, fa); + else + xfs_warn(mp, + "Reverse Mapping BTree record corruption in AG %d detected at %pS!", + cur->bc_group->xg_gno, fa); xfs_warn(mp, "Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x", irec->rm_owner, irec->rm_flags, irec->rm_startblock, irec->rm_blockcount); + xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } +/* + * Get the data from the pointed-to record. + */ +int +xfs_rmap_get_rec( + struct xfs_btree_cur *cur, + struct xfs_rmap_irec *irec, + int *stat) +{ + union xfs_btree_rec *rec; + xfs_failaddr_t fa; + int error; + + error = xfs_btree_get_rec(cur, &rec, stat); + if (error || !*stat) + return error; + + fa = xfs_rmap_btrec_to_irec(rec, irec); + if (!fa) + fa = xfs_rmap_check_btrec(cur, irec); + if (fa) + return xfs_rmap_complain_bad_rec(cur, fa, irec); + + return 0; +} + struct xfs_find_left_neighbor_info { struct xfs_rmap_irec high; struct xfs_rmap_irec *irec; @@ -271,8 +407,7 @@ xfs_rmap_find_left_neighbor_helper( { struct xfs_find_left_neighbor_info *info = priv; - trace_xfs_rmap_find_left_neighbor_candidate(cur->bc_mp, - cur->bc_ag.pag->pag_agno, rec->rm_startblock, + trace_xfs_rmap_find_left_neighbor_candidate(cur, rec->rm_startblock, rec->rm_blockcount, rec->rm_owner, rec->rm_offset, rec->rm_flags); @@ -322,8 +457,8 @@ xfs_rmap_find_left_neighbor( info.high.rm_blockcount = 0; info.irec = irec; - trace_xfs_rmap_find_left_neighbor_query(cur->bc_mp, - cur->bc_ag.pag->pag_agno, bno, 0, owner, offset, flags); + trace_xfs_rmap_find_left_neighbor_query(cur, bno, 0, owner, offset, + flags); /* * Historically, we always used the range query to walk every reverse @@ -354,8 +489,7 @@ xfs_rmap_find_left_neighbor( return error; *stat = 1; - trace_xfs_rmap_find_left_neighbor_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, irec->rm_startblock, + trace_xfs_rmap_find_left_neighbor_result(cur, irec->rm_startblock, irec->rm_blockcount, irec->rm_owner, irec->rm_offset, irec->rm_flags); return 0; @@ -370,8 +504,7 @@ xfs_rmap_lookup_le_range_helper( { struct xfs_find_left_neighbor_info *info = priv; - trace_xfs_rmap_lookup_le_range_candidate(cur->bc_mp, - cur->bc_ag.pag->pag_agno, rec->rm_startblock, + trace_xfs_rmap_lookup_le_range_candidate(cur, rec->rm_startblock, rec->rm_blockcount, rec->rm_owner, rec->rm_offset, rec->rm_flags); @@ -418,8 +551,7 @@ xfs_rmap_lookup_le_range( *stat = 0; info.irec = irec; - trace_xfs_rmap_lookup_le_range(cur->bc_mp, cur->bc_ag.pag->pag_agno, - bno, 0, owner, offset, flags); + trace_xfs_rmap_lookup_le_range(cur, bno, 0, owner, offset, flags); /* * Historically, we always used the range query to walk every reverse @@ -450,8 +582,7 @@ xfs_rmap_lookup_le_range( return error; *stat = 1; - trace_xfs_rmap_lookup_le_range_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, irec->rm_startblock, + trace_xfs_rmap_lookup_le_range_result(cur, irec->rm_startblock, irec->rm_blockcount, irec->rm_owner, irec->rm_offset, irec->rm_flags); return 0; @@ -463,14 +594,15 @@ xfs_rmap_lookup_le_range( */ static int xfs_rmap_free_check_owner( - struct xfs_mount *mp, + struct xfs_btree_cur *cur, uint64_t ltoff, struct xfs_rmap_irec *rec, - xfs_filblks_t len, + xfs_extlen_t len, uint64_t owner, uint64_t offset, unsigned int flags) { + struct xfs_mount *mp = cur->bc_mp; int error = 0; if (owner == XFS_RMAP_OWN_UNKNOWN) @@ -480,12 +612,14 @@ xfs_rmap_free_check_owner( if (XFS_IS_CORRUPT(mp, (flags & XFS_RMAP_UNWRITTEN) != (rec->rm_flags & XFS_RMAP_UNWRITTEN))) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out; } /* Make sure the owner matches what we expect to find in the tree. */ if (XFS_IS_CORRUPT(mp, owner != rec->rm_owner)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out; } @@ -497,16 +631,19 @@ xfs_rmap_free_check_owner( if (flags & XFS_RMAP_BMBT_BLOCK) { if (XFS_IS_CORRUPT(mp, !(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out; } } else { if (XFS_IS_CORRUPT(mp, rec->rm_offset > offset)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out; } if (XFS_IS_CORRUPT(mp, offset + len > ltoff + rec->rm_blockcount)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out; } @@ -557,8 +694,7 @@ xfs_rmap_unmap( (flags & XFS_RMAP_BMBT_BLOCK); if (unwritten) flags |= XFS_RMAP_UNWRITTEN; - trace_xfs_rmap_unmap(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_unmap(cur, bno, len, unwritten, oinfo); /* * We should always have a left record because there's a static record @@ -569,14 +705,14 @@ xfs_rmap_unmap( if (error) goto out_error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } - trace_xfs_rmap_lookup_le_range_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, ltrec.rm_startblock, - ltrec.rm_blockcount, ltrec.rm_owner, - ltrec.rm_offset, ltrec.rm_flags); + trace_xfs_rmap_lookup_le_range_result(cur, ltrec.rm_startblock, + ltrec.rm_blockcount, ltrec.rm_owner, ltrec.rm_offset, + ltrec.rm_flags); ltoff = ltrec.rm_offset; /* @@ -590,6 +726,7 @@ xfs_rmap_unmap( if (XFS_IS_CORRUPT(mp, bno < ltrec.rm_startblock + ltrec.rm_blockcount)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -616,6 +753,7 @@ xfs_rmap_unmap( if (error) goto out_error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -628,26 +766,27 @@ xfs_rmap_unmap( ltrec.rm_startblock > bno || ltrec.rm_startblock + ltrec.rm_blockcount < bno + len)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } /* Check owner information. */ - error = xfs_rmap_free_check_owner(mp, ltoff, <rec, len, owner, + error = xfs_rmap_free_check_owner(cur, ltoff, <rec, len, owner, offset, flags); if (error) goto out_error; if (ltrec.rm_startblock == bno && ltrec.rm_blockcount == len) { /* exact match, simply remove the record from rmap tree */ - trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno, - ltrec.rm_startblock, ltrec.rm_blockcount, - ltrec.rm_owner, ltrec.rm_offset, - ltrec.rm_flags); + trace_xfs_rmap_delete(cur, ltrec.rm_startblock, + ltrec.rm_blockcount, ltrec.rm_owner, + ltrec.rm_offset, ltrec.rm_flags); error = xfs_btree_delete(cur, &i); if (error) goto out_error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -718,8 +857,7 @@ xfs_rmap_unmap( else cur->bc_rec.r.rm_offset = offset + len; cur->bc_rec.r.rm_flags = flags; - trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno, - cur->bc_rec.r.rm_startblock, + trace_xfs_rmap_insert(cur, cur->bc_rec.r.rm_startblock, cur->bc_rec.r.rm_blockcount, cur->bc_rec.r.rm_owner, cur->bc_rec.r.rm_offset, @@ -730,15 +868,93 @@ xfs_rmap_unmap( } out_done: - trace_xfs_rmap_unmap_done(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_unmap_done(cur, bno, len, unwritten, oinfo); out_error: if (error) - trace_xfs_rmap_unmap_error(mp, cur->bc_ag.pag->pag_agno, - error, _RET_IP_); + trace_xfs_rmap_unmap_error(cur, error, _RET_IP_); return error; } +#ifdef CONFIG_XFS_LIVE_HOOKS +/* + * Use a static key here to reduce the overhead of rmapbt live updates. If + * the compiler supports jump labels, the static branch will be replaced by a + * nop sled when there are no hook users. Online fsck is currently the only + * caller, so this is a reasonable tradeoff. + * + * Note: Patching the kernel code requires taking the cpu hotplug lock. Other + * parts of the kernel allocate memory with that lock held, which means that + * XFS callers cannot hold any locks that might be used by memory reclaim or + * writeback when calling the static_branch_{inc,dec} functions. + */ +DEFINE_STATIC_XFS_HOOK_SWITCH(xfs_rmap_hooks_switch); + +void +xfs_rmap_hook_disable(void) +{ + xfs_hooks_switch_off(&xfs_rmap_hooks_switch); +} + +void +xfs_rmap_hook_enable(void) +{ + xfs_hooks_switch_on(&xfs_rmap_hooks_switch); +} + +/* Call downstream hooks for a reverse mapping update. */ +static inline void +xfs_rmap_update_hook( + struct xfs_trans *tp, + struct xfs_group *xg, + enum xfs_rmap_intent_type op, + xfs_agblock_t startblock, + xfs_extlen_t blockcount, + bool unwritten, + const struct xfs_owner_info *oinfo) +{ + if (xfs_hooks_switched_on(&xfs_rmap_hooks_switch)) { + struct xfs_rmap_update_params p = { + .startblock = startblock, + .blockcount = blockcount, + .unwritten = unwritten, + .oinfo = *oinfo, /* struct copy */ + }; + + if (xg) + xfs_hooks_call(&xg->xg_rmap_update_hooks, op, &p); + } +} + +/* Call the specified function during a reverse mapping update. */ +int +xfs_rmap_hook_add( + struct xfs_group *xg, + struct xfs_rmap_hook *hook) +{ + return xfs_hooks_add(&xg->xg_rmap_update_hooks, &hook->rmap_hook); +} + +/* Stop calling the specified function during a reverse mapping update. */ +void +xfs_rmap_hook_del( + struct xfs_group *xg, + struct xfs_rmap_hook *hook) +{ + xfs_hooks_del(&xg->xg_rmap_update_hooks, &hook->rmap_hook); +} + +/* Configure rmap update hook functions. */ +void +xfs_rmap_hook_setup( + struct xfs_rmap_hook *hook, + notifier_fn_t mod_fn) +{ + xfs_hook_setup(&hook->rmap_hook, mod_fn); +} +#else +# define xfs_rmap_update_hook(t, p, o, s, b, u, oi) do { } while (0) +#endif /* CONFIG_XFS_LIVE_HOOKS */ + /* * Remove a reference to an extent in the rmap btree. */ @@ -759,7 +975,8 @@ xfs_rmap_free( return 0; cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag); - + xfs_rmap_update_hook(tp, pag_group(pag), XFS_RMAP_UNMAP, bno, len, + false, oinfo); error = xfs_rmap_unmap(cur, bno, len, false, oinfo); xfs_btree_del_cursor(cur, error); @@ -825,8 +1042,7 @@ xfs_rmap_map( (flags & XFS_RMAP_BMBT_BLOCK); if (unwritten) flags |= XFS_RMAP_UNWRITTEN; - trace_xfs_rmap_map(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_map(cur, bno, len, unwritten, oinfo); ASSERT(!xfs_rmap_should_skip_owner_update(oinfo)); /* @@ -839,8 +1055,7 @@ xfs_rmap_map( if (error) goto out_error; if (have_lt) { - trace_xfs_rmap_lookup_le_range_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, ltrec.rm_startblock, + trace_xfs_rmap_lookup_le_range_result(cur, ltrec.rm_startblock, ltrec.rm_blockcount, ltrec.rm_owner, ltrec.rm_offset, ltrec.rm_flags); @@ -851,6 +1066,7 @@ xfs_rmap_map( if (XFS_IS_CORRUPT(mp, have_lt != 0 && ltrec.rm_startblock + ltrec.rm_blockcount > bno)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -868,17 +1084,19 @@ xfs_rmap_map( if (error) goto out_error; if (XFS_IS_CORRUPT(mp, have_gt != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (XFS_IS_CORRUPT(mp, bno + len > gtrec.rm_startblock)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } - trace_xfs_rmap_find_right_neighbor_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, gtrec.rm_startblock, - gtrec.rm_blockcount, gtrec.rm_owner, - gtrec.rm_offset, gtrec.rm_flags); + trace_xfs_rmap_find_right_neighbor_result(cur, + gtrec.rm_startblock, gtrec.rm_blockcount, + gtrec.rm_owner, gtrec.rm_offset, + gtrec.rm_flags); if (!xfs_rmap_is_mergeable(>rec, owner, flags)) have_gt = 0; } @@ -915,16 +1133,14 @@ xfs_rmap_map( * result: |rrrrrrrrrrrrrrrrrrrrrrrrrrrrr| */ ltrec.rm_blockcount += gtrec.rm_blockcount; - trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno, - gtrec.rm_startblock, - gtrec.rm_blockcount, - gtrec.rm_owner, - gtrec.rm_offset, - gtrec.rm_flags); + trace_xfs_rmap_delete(cur, gtrec.rm_startblock, + gtrec.rm_blockcount, gtrec.rm_owner, + gtrec.rm_offset, gtrec.rm_flags); error = xfs_btree_delete(cur, &i); if (error) goto out_error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -966,23 +1182,21 @@ xfs_rmap_map( cur->bc_rec.r.rm_owner = owner; cur->bc_rec.r.rm_offset = offset; cur->bc_rec.r.rm_flags = flags; - trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno, bno, len, - owner, offset, flags); + trace_xfs_rmap_insert(cur, bno, len, owner, offset, flags); error = xfs_btree_insert(cur, &i); if (error) goto out_error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } } - trace_xfs_rmap_map_done(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_map_done(cur, bno, len, unwritten, oinfo); out_error: if (error) - trace_xfs_rmap_map_error(mp, cur->bc_ag.pag->pag_agno, - error, _RET_IP_); + trace_xfs_rmap_map_error(cur, error, _RET_IP_); return error; } @@ -1006,6 +1220,8 @@ xfs_rmap_alloc( return 0; cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag); + xfs_rmap_update_hook(tp, pag_group(pag), XFS_RMAP_MAP, bno, len, false, + oinfo); error = xfs_rmap_map(cur, bno, len, false, oinfo); xfs_btree_del_cursor(cur, error); @@ -1055,8 +1271,7 @@ xfs_rmap_convert( (flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)))); oldext = unwritten ? XFS_RMAP_UNWRITTEN : 0; new_endoff = offset + len; - trace_xfs_rmap_convert(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_convert(cur, bno, len, unwritten, oinfo); /* * For the initial lookup, look for an exact match or the left-adjacent @@ -1067,14 +1282,14 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } - trace_xfs_rmap_lookup_le_range_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, PREV.rm_startblock, - PREV.rm_blockcount, PREV.rm_owner, - PREV.rm_offset, PREV.rm_flags); + trace_xfs_rmap_lookup_le_range_result(cur, PREV.rm_startblock, + PREV.rm_blockcount, PREV.rm_owner, PREV.rm_offset, + PREV.rm_flags); ASSERT(PREV.rm_offset <= offset); ASSERT(PREV.rm_offset + PREV.rm_blockcount >= new_endoff); @@ -1104,19 +1319,20 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } if (XFS_IS_CORRUPT(mp, LEFT.rm_startblock + LEFT.rm_blockcount > bno)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } - trace_xfs_rmap_find_left_neighbor_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, LEFT.rm_startblock, - LEFT.rm_blockcount, LEFT.rm_owner, - LEFT.rm_offset, LEFT.rm_flags); + trace_xfs_rmap_find_left_neighbor_result(cur, + LEFT.rm_startblock, LEFT.rm_blockcount, + LEFT.rm_owner, LEFT.rm_offset, LEFT.rm_flags); if (LEFT.rm_startblock + LEFT.rm_blockcount == bno && LEFT.rm_offset + LEFT.rm_blockcount == offset && xfs_rmap_is_mergeable(&LEFT, owner, newext)) @@ -1132,6 +1348,7 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1144,17 +1361,19 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } if (XFS_IS_CORRUPT(mp, bno + len > RIGHT.rm_startblock)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } - trace_xfs_rmap_find_right_neighbor_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, RIGHT.rm_startblock, - RIGHT.rm_blockcount, RIGHT.rm_owner, - RIGHT.rm_offset, RIGHT.rm_flags); + trace_xfs_rmap_find_right_neighbor_result(cur, + RIGHT.rm_startblock, RIGHT.rm_blockcount, + RIGHT.rm_owner, RIGHT.rm_offset, + RIGHT.rm_flags); if (bno + len == RIGHT.rm_startblock && offset + len == RIGHT.rm_offset && xfs_rmap_is_mergeable(&RIGHT, owner, newext)) @@ -1170,14 +1389,14 @@ xfs_rmap_convert( RIGHT.rm_blockcount > XFS_RMAP_LEN_MAX) state &= ~RMAP_RIGHT_CONTIG; - trace_xfs_rmap_convert_state(mp, cur->bc_ag.pag->pag_agno, state, - _RET_IP_); + trace_xfs_rmap_convert_state(cur, state, _RET_IP_); /* reset the cursor back to PREV */ error = xfs_rmap_lookup_le(cur, bno, owner, offset, oldext, NULL, &i); if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1197,17 +1416,18 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } - trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno, - RIGHT.rm_startblock, RIGHT.rm_blockcount, - RIGHT.rm_owner, RIGHT.rm_offset, - RIGHT.rm_flags); + trace_xfs_rmap_delete(cur, RIGHT.rm_startblock, + RIGHT.rm_blockcount, RIGHT.rm_owner, + RIGHT.rm_offset, RIGHT.rm_flags); error = xfs_btree_delete(cur, &i); if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1215,17 +1435,18 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } - trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno, - PREV.rm_startblock, PREV.rm_blockcount, - PREV.rm_owner, PREV.rm_offset, - PREV.rm_flags); + trace_xfs_rmap_delete(cur, PREV.rm_startblock, + PREV.rm_blockcount, PREV.rm_owner, + PREV.rm_offset, PREV.rm_flags); error = xfs_btree_delete(cur, &i); if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1233,6 +1454,7 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1248,14 +1470,14 @@ xfs_rmap_convert( * Setting all of a previous oldext extent to newext. * The left neighbor is contiguous, the right is not. */ - trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno, - PREV.rm_startblock, PREV.rm_blockcount, - PREV.rm_owner, PREV.rm_offset, - PREV.rm_flags); + trace_xfs_rmap_delete(cur, PREV.rm_startblock, + PREV.rm_blockcount, PREV.rm_owner, + PREV.rm_offset, PREV.rm_flags); error = xfs_btree_delete(cur, &i); if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1263,6 +1485,7 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1282,17 +1505,18 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } - trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno, - RIGHT.rm_startblock, RIGHT.rm_blockcount, - RIGHT.rm_owner, RIGHT.rm_offset, - RIGHT.rm_flags); + trace_xfs_rmap_delete(cur, RIGHT.rm_startblock, + RIGHT.rm_blockcount, RIGHT.rm_owner, + RIGHT.rm_offset, RIGHT.rm_flags); error = xfs_btree_delete(cur, &i); if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1300,6 +1524,7 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1364,12 +1589,12 @@ xfs_rmap_convert( NEW.rm_blockcount = len; NEW.rm_flags = newext; cur->bc_rec.r = NEW; - trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno, bno, - len, owner, offset, newext); + trace_xfs_rmap_insert(cur, bno, len, owner, offset, newext); error = xfs_btree_insert(cur, &i); if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1412,6 +1637,7 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1421,12 +1647,12 @@ xfs_rmap_convert( NEW.rm_blockcount = len; NEW.rm_flags = newext; cur->bc_rec.r = NEW; - trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno, bno, - len, owner, offset, newext); + trace_xfs_rmap_insert(cur, bno, len, owner, offset, newext); error = xfs_btree_insert(cur, &i); if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1452,14 +1678,14 @@ xfs_rmap_convert( NEW = PREV; NEW.rm_blockcount = offset - PREV.rm_offset; cur->bc_rec.r = NEW; - trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno, - NEW.rm_startblock, NEW.rm_blockcount, - NEW.rm_owner, NEW.rm_offset, + trace_xfs_rmap_insert(cur, NEW.rm_startblock, + NEW.rm_blockcount, NEW.rm_owner, NEW.rm_offset, NEW.rm_flags); error = xfs_btree_insert(cur, &i); if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1473,18 +1699,19 @@ xfs_rmap_convert( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 0)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } /* new middle extent - newext */ cur->bc_rec.r.rm_flags &= ~XFS_RMAP_UNWRITTEN; cur->bc_rec.r.rm_flags |= newext; - trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno, bno, len, - owner, offset, newext); + trace_xfs_rmap_insert(cur, bno, len, owner, offset, newext); error = xfs_btree_insert(cur, &i); if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1503,12 +1730,10 @@ xfs_rmap_convert( ASSERT(0); } - trace_xfs_rmap_convert_done(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_convert_done(cur, bno, len, unwritten, oinfo); done: if (error) - trace_xfs_rmap_convert_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_rmap_convert_error(cur, error, _RET_IP_); return error; } @@ -1544,8 +1769,7 @@ xfs_rmap_convert_shared( (flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)))); oldext = unwritten ? XFS_RMAP_UNWRITTEN : 0; new_endoff = offset + len; - trace_xfs_rmap_convert(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_convert(cur, bno, len, unwritten, oinfo); /* * For the initial lookup, look for and exact match or the left-adjacent @@ -1557,6 +1781,7 @@ xfs_rmap_convert_shared( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1585,6 +1810,7 @@ xfs_rmap_convert_shared( if (XFS_IS_CORRUPT(mp, LEFT.rm_startblock + LEFT.rm_blockcount > bno)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1603,17 +1829,19 @@ xfs_rmap_convert_shared( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } if (XFS_IS_CORRUPT(mp, bno + len > RIGHT.rm_startblock)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } - trace_xfs_rmap_find_right_neighbor_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, RIGHT.rm_startblock, - RIGHT.rm_blockcount, RIGHT.rm_owner, - RIGHT.rm_offset, RIGHT.rm_flags); + trace_xfs_rmap_find_right_neighbor_result(cur, + RIGHT.rm_startblock, RIGHT.rm_blockcount, + RIGHT.rm_owner, RIGHT.rm_offset, + RIGHT.rm_flags); if (xfs_rmap_is_mergeable(&RIGHT, owner, newext)) state |= RMAP_RIGHT_CONTIG; } @@ -1627,8 +1855,7 @@ xfs_rmap_convert_shared( RIGHT.rm_blockcount > XFS_RMAP_LEN_MAX) state &= ~RMAP_RIGHT_CONTIG; - trace_xfs_rmap_convert_state(mp, cur->bc_ag.pag->pag_agno, state, - _RET_IP_); + trace_xfs_rmap_convert_state(cur, state, _RET_IP_); /* * Switch out based on the FILLING and CONTIG state bits. */ @@ -1657,6 +1884,7 @@ xfs_rmap_convert_shared( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1683,6 +1911,7 @@ xfs_rmap_convert_shared( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1709,6 +1938,7 @@ xfs_rmap_convert_shared( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1732,6 +1962,7 @@ xfs_rmap_convert_shared( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1767,6 +1998,7 @@ xfs_rmap_convert_shared( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1812,6 +2044,7 @@ xfs_rmap_convert_shared( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1847,6 +2080,7 @@ xfs_rmap_convert_shared( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1885,6 +2119,7 @@ xfs_rmap_convert_shared( if (error) goto done; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto done; } @@ -1918,12 +2153,10 @@ xfs_rmap_convert_shared( ASSERT(0); } - trace_xfs_rmap_convert_done(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_convert_done(cur, bno, len, unwritten, oinfo); done: if (error) - trace_xfs_rmap_convert_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_rmap_convert_error(cur, error, _RET_IP_); return error; } @@ -1961,8 +2194,7 @@ xfs_rmap_unmap_shared( xfs_owner_info_unpack(oinfo, &owner, &offset, &flags); if (unwritten) flags |= XFS_RMAP_UNWRITTEN; - trace_xfs_rmap_unmap(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_unmap(cur, bno, len, unwritten, oinfo); /* * We should always have a left record because there's a static record @@ -1974,6 +2206,7 @@ xfs_rmap_unmap_shared( if (error) goto out_error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -1984,12 +2217,14 @@ xfs_rmap_unmap_shared( ltrec.rm_startblock > bno || ltrec.rm_startblock + ltrec.rm_blockcount < bno + len)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } /* Make sure the owner matches what we expect to find in the tree. */ if (XFS_IS_CORRUPT(mp, owner != ltrec.rm_owner)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -1998,16 +2233,19 @@ xfs_rmap_unmap_shared( if (XFS_IS_CORRUPT(mp, (flags & XFS_RMAP_UNWRITTEN) != (ltrec.rm_flags & XFS_RMAP_UNWRITTEN))) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } /* Check the offset. */ if (XFS_IS_CORRUPT(mp, ltrec.rm_offset > offset)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } if (XFS_IS_CORRUPT(mp, offset > ltoff + ltrec.rm_blockcount)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -2064,6 +2302,7 @@ xfs_rmap_unmap_shared( if (error) goto out_error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -2093,6 +2332,7 @@ xfs_rmap_unmap_shared( if (error) goto out_error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -2110,12 +2350,10 @@ xfs_rmap_unmap_shared( goto out_error; } - trace_xfs_rmap_unmap_done(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_unmap_done(cur, bno, len, unwritten, oinfo); out_error: if (error) - trace_xfs_rmap_unmap_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_rmap_unmap_error(cur, error, _RET_IP_); return error; } @@ -2150,8 +2388,7 @@ xfs_rmap_map_shared( xfs_owner_info_unpack(oinfo, &owner, &offset, &flags); if (unwritten) flags |= XFS_RMAP_UNWRITTEN; - trace_xfs_rmap_map(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_map(cur, bno, len, unwritten, oinfo); /* Is there a left record that abuts our range? */ error = xfs_rmap_find_left_neighbor(cur, bno, owner, offset, flags, @@ -2172,13 +2409,14 @@ xfs_rmap_map_shared( if (error) goto out_error; if (XFS_IS_CORRUPT(mp, have_gt != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } - trace_xfs_rmap_find_right_neighbor_result(cur->bc_mp, - cur->bc_ag.pag->pag_agno, gtrec.rm_startblock, - gtrec.rm_blockcount, gtrec.rm_owner, - gtrec.rm_offset, gtrec.rm_flags); + trace_xfs_rmap_find_right_neighbor_result(cur, + gtrec.rm_startblock, gtrec.rm_blockcount, + gtrec.rm_owner, gtrec.rm_offset, + gtrec.rm_flags); if (!xfs_rmap_is_mergeable(>rec, owner, flags)) have_gt = 0; @@ -2224,6 +2462,7 @@ xfs_rmap_map_shared( if (error) goto out_error; if (XFS_IS_CORRUPT(mp, i != 1)) { + xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out_error; } @@ -2269,12 +2508,10 @@ xfs_rmap_map_shared( goto out_error; } - trace_xfs_rmap_map_done(mp, cur->bc_ag.pag->pag_agno, bno, len, - unwritten, oinfo); + trace_xfs_rmap_map_done(cur, bno, len, unwritten, oinfo); out_error: if (error) - trace_xfs_rmap_map_error(cur->bc_mp, - cur->bc_ag.pag->pag_agno, error, _RET_IP_); + trace_xfs_rmap_map_error(cur, error, _RET_IP_); return error; } @@ -2286,15 +2523,12 @@ xfs_rmap_map_raw( { struct xfs_owner_info oinfo; - oinfo.oi_owner = rmap->rm_owner; - oinfo.oi_offset = rmap->rm_offset; - oinfo.oi_flags = 0; - if (rmap->rm_flags & XFS_RMAP_ATTR_FORK) - oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK; - if (rmap->rm_flags & XFS_RMAP_BMBT_BLOCK) - oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK; + xfs_owner_info_pack(&oinfo, rmap->rm_owner, rmap->rm_offset, + rmap->rm_flags); - if (rmap->rm_flags || XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner)) + if ((rmap->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK | + XFS_RMAP_UNWRITTEN)) || + XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner)) return xfs_rmap_map(cur, rmap->rm_startblock, rmap->rm_blockcount, rmap->rm_flags & XFS_RMAP_UNWRITTEN, @@ -2320,11 +2554,14 @@ xfs_rmap_query_range_helper( { struct xfs_rmap_query_range_info *query = priv; struct xfs_rmap_irec irec; - int error; + xfs_failaddr_t fa; + + fa = xfs_rmap_btrec_to_irec(rec, &irec); + if (!fa) + fa = xfs_rmap_check_btrec(cur, &irec); + if (fa) + return xfs_rmap_complain_bad_rec(cur, fa, &irec); - error = xfs_rmap_btrec_to_irec(rec, &irec); - if (error) - return error; return query->fn(cur, &irec, query->priv); } @@ -2337,14 +2574,10 @@ xfs_rmap_query_range( xfs_rmap_query_range_fn fn, void *priv) { - union xfs_btree_irec low_brec; - union xfs_btree_irec high_brec; - struct xfs_rmap_query_range_info query; + union xfs_btree_irec low_brec = { .r = *low_rec }; + union xfs_btree_irec high_brec = { .r = *high_rec }; + struct xfs_rmap_query_range_info query = { .priv = priv, .fn = fn }; - low_brec.r = *low_rec; - high_brec.r = *high_rec; - query.priv = priv; - query.fn = fn; return xfs_btree_query_range(cur, &low_brec, &high_brec, xfs_rmap_query_range_helper, &query); } @@ -2363,21 +2596,77 @@ xfs_rmap_query_all( return xfs_btree_query_all(cur, xfs_rmap_query_range_helper, &query); } -/* Clean up after calling xfs_rmap_finish_one. */ -void -xfs_rmap_finish_one_cleanup( - struct xfs_trans *tp, - struct xfs_btree_cur *rcur, - int error) +/* Commit an rmap operation into the ondisk tree. */ +int +__xfs_rmap_finish_intent( + struct xfs_btree_cur *rcur, + enum xfs_rmap_intent_type op, + xfs_agblock_t bno, + xfs_extlen_t len, + const struct xfs_owner_info *oinfo, + bool unwritten) { - struct xfs_buf *agbp; + switch (op) { + case XFS_RMAP_ALLOC: + case XFS_RMAP_MAP: + return xfs_rmap_map(rcur, bno, len, unwritten, oinfo); + case XFS_RMAP_MAP_SHARED: + return xfs_rmap_map_shared(rcur, bno, len, unwritten, oinfo); + case XFS_RMAP_FREE: + case XFS_RMAP_UNMAP: + return xfs_rmap_unmap(rcur, bno, len, unwritten, oinfo); + case XFS_RMAP_UNMAP_SHARED: + return xfs_rmap_unmap_shared(rcur, bno, len, unwritten, oinfo); + case XFS_RMAP_CONVERT: + return xfs_rmap_convert(rcur, bno, len, !unwritten, oinfo); + case XFS_RMAP_CONVERT_SHARED: + return xfs_rmap_convert_shared(rcur, bno, len, !unwritten, + oinfo); + default: + ASSERT(0); + return -EFSCORRUPTED; + } +} - if (rcur == NULL) - return; - agbp = rcur->bc_ag.agbp; - xfs_btree_del_cursor(rcur, error); - if (error) - xfs_trans_brelse(tp, agbp); +static int +xfs_rmap_finish_init_cursor( + struct xfs_trans *tp, + struct xfs_rmap_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_perag *pag = to_perag(ri->ri_group); + struct xfs_buf *agbp = NULL; + int error; + + /* + * Refresh the freelist before we start changing the rmapbt, because a + * shape change could cause us to allocate blocks. + */ + error = xfs_free_extent_fix_freelist(tp, pag, &agbp); + if (error) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + return error; + } + if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + return -EFSCORRUPTED; + } + *pcur = xfs_rmapbt_init_cursor(tp->t_mountp, tp, agbp, pag); + return 0; +} + +static int +xfs_rtrmap_finish_init_cursor( + struct xfs_trans *tp, + struct xfs_rmap_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP); + *pcur = xfs_rtrmapbt_init_cursor(tp, rtg); + return 0; } /* @@ -2390,101 +2679,51 @@ xfs_rmap_finish_one_cleanup( int xfs_rmap_finish_one( struct xfs_trans *tp, - enum xfs_rmap_intent_type type, - uint64_t owner, - int whichfork, - xfs_fileoff_t startoff, - xfs_fsblock_t startblock, - xfs_filblks_t blockcount, - xfs_exntst_t state, + struct xfs_rmap_intent *ri, struct xfs_btree_cur **pcur) { - struct xfs_mount *mp = tp->t_mountp; - struct xfs_perag *pag; - struct xfs_btree_cur *rcur; - struct xfs_buf *agbp = NULL; - int error = 0; struct xfs_owner_info oinfo; + struct xfs_mount *mp = tp->t_mountp; xfs_agblock_t bno; bool unwritten; + int error = 0; - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, startblock)); - bno = XFS_FSB_TO_AGBNO(mp, startblock); - - trace_xfs_rmap_deferred(mp, pag->pag_agno, type, bno, owner, whichfork, - startoff, blockcount, state); - - if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_RMAP_FINISH_ONE)) { - error = -EIO; - goto out_drop; - } + trace_xfs_rmap_deferred(mp, ri); + if (XFS_TEST_ERROR(mp, XFS_ERRTAG_RMAP_FINISH_ONE)) + return -EIO; /* * If we haven't gotten a cursor or the cursor AG doesn't match * the startblock, get one now. */ - rcur = *pcur; - if (rcur != NULL && rcur->bc_ag.pag != pag) { - xfs_rmap_finish_one_cleanup(tp, rcur, 0); - rcur = NULL; + if (*pcur != NULL && (*pcur)->bc_group != ri->ri_group) { + xfs_btree_del_cursor(*pcur, 0); *pcur = NULL; } - if (rcur == NULL) { - /* - * Refresh the freelist before we start changing the - * rmapbt, because a shape change could cause us to - * allocate blocks. - */ - error = xfs_free_extent_fix_freelist(tp, pag, &agbp); + if (*pcur == NULL) { + if (ri->ri_group->xg_type == XG_TYPE_RTG) + error = xfs_rtrmap_finish_init_cursor(tp, ri, pcur); + else + error = xfs_rmap_finish_init_cursor(tp, ri, pcur); if (error) - goto out_drop; - if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) { - error = -EFSCORRUPTED; - goto out_drop; - } - - rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag); + return error; } - *pcur = rcur; - xfs_rmap_ino_owner(&oinfo, owner, whichfork, startoff); - unwritten = state == XFS_EXT_UNWRITTEN; - bno = XFS_FSB_TO_AGBNO(rcur->bc_mp, startblock); + xfs_rmap_ino_owner(&oinfo, ri->ri_owner, ri->ri_whichfork, + ri->ri_bmap.br_startoff); + unwritten = ri->ri_bmap.br_state == XFS_EXT_UNWRITTEN; - switch (type) { - case XFS_RMAP_ALLOC: - case XFS_RMAP_MAP: - error = xfs_rmap_map(rcur, bno, blockcount, unwritten, &oinfo); - break; - case XFS_RMAP_MAP_SHARED: - error = xfs_rmap_map_shared(rcur, bno, blockcount, unwritten, - &oinfo); - break; - case XFS_RMAP_FREE: - case XFS_RMAP_UNMAP: - error = xfs_rmap_unmap(rcur, bno, blockcount, unwritten, - &oinfo); - break; - case XFS_RMAP_UNMAP_SHARED: - error = xfs_rmap_unmap_shared(rcur, bno, blockcount, unwritten, - &oinfo); - break; - case XFS_RMAP_CONVERT: - error = xfs_rmap_convert(rcur, bno, blockcount, !unwritten, - &oinfo); - break; - case XFS_RMAP_CONVERT_SHARED: - error = xfs_rmap_convert_shared(rcur, bno, blockcount, - !unwritten, &oinfo); - break; - default: - ASSERT(0); - error = -EFSCORRUPTED; - } -out_drop: - xfs_perag_put(pag); - return error; + bno = xfs_fsb_to_gbno(mp, ri->ri_bmap.br_startblock, + ri->ri_group->xg_type); + error = __xfs_rmap_finish_intent(*pcur, ri->ri_type, bno, + ri->ri_bmap.br_blockcount, &oinfo, unwritten); + if (error) + return error; + + xfs_rmap_update_hook(tp, ri->ri_group, ri->ri_type, bno, + ri->ri_bmap.br_blockcount, unwritten, &oinfo); + return 0; } /* @@ -2507,28 +2746,21 @@ __xfs_rmap_add( struct xfs_trans *tp, enum xfs_rmap_intent_type type, uint64_t owner, + bool isrt, int whichfork, struct xfs_bmbt_irec *bmap) { struct xfs_rmap_intent *ri; - trace_xfs_rmap_defer(tp->t_mountp, - XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock), - type, - XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock), - owner, whichfork, - bmap->br_startoff, - bmap->br_blockcount, - bmap->br_state); - - ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_NOFS | __GFP_NOFAIL); + ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_KERNEL | __GFP_NOFAIL); INIT_LIST_HEAD(&ri->ri_list); ri->ri_type = type; ri->ri_owner = owner; ri->ri_whichfork = whichfork; ri->ri_bmap = *bmap; + ri->ri_realtime = isrt; - xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list); + xfs_rmap_defer_add(tp, ri); } /* Map an extent into a file. */ @@ -2540,6 +2772,7 @@ xfs_rmap_map_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_MAP; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork)) return; @@ -2547,7 +2780,7 @@ xfs_rmap_map_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_MAP_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* Unmap an extent out of a file. */ @@ -2559,6 +2792,7 @@ xfs_rmap_unmap_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_UNMAP; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork)) return; @@ -2566,7 +2800,7 @@ xfs_rmap_unmap_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_UNMAP_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* @@ -2584,6 +2818,7 @@ xfs_rmap_convert_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_CONVERT; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(mp, whichfork)) return; @@ -2591,15 +2826,15 @@ xfs_rmap_convert_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_CONVERT_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* Schedule the creation of an rmap for non-file data. */ void xfs_rmap_alloc_extent( struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agblock_t bno, + bool isrt, + xfs_fsblock_t fsbno, xfs_extlen_t len, uint64_t owner) { @@ -2608,20 +2843,20 @@ xfs_rmap_alloc_extent( if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK)) return; - bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno); + bmap.br_startblock = fsbno; bmap.br_blockcount = len; bmap.br_startoff = 0; bmap.br_state = XFS_EXT_NORM; - __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, XFS_DATA_FORK, &bmap); + __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, isrt, XFS_DATA_FORK, &bmap); } /* Schedule the deletion of an rmap for non-file data. */ void xfs_rmap_free_extent( struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agblock_t bno, + bool isrt, + xfs_fsblock_t fsbno, xfs_extlen_t len, uint64_t owner) { @@ -2630,12 +2865,12 @@ xfs_rmap_free_extent( if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK)) return; - bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno); + bmap.br_startblock = fsbno; bmap.br_blockcount = len; bmap.br_startoff = 0; bmap.br_state = XFS_EXT_NORM; - __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, XFS_DATA_FORK, &bmap); + __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, isrt, XFS_DATA_FORK, &bmap); } /* Compare rmap records. Returns -1 if a < b, 1 if a > b, and 0 if equal. */ @@ -2666,14 +2901,21 @@ xfs_rmap_compare( return 0; } -/* Is there a record covering a given extent? */ +/* + * Scan the physical storage part of the keyspace of the reverse mapping index + * and tell us if the area has no records, is fully mapped by records, or is + * partially filled. + */ int -xfs_rmap_has_record( +xfs_rmap_has_records( struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, - bool *exists) + enum xbtree_recpacking *outcome) { + union xfs_btree_key mask = { + .rmap.rm_startblock = cpu_to_be32(-1U), + }; union xfs_btree_irec low; union xfs_btree_irec high; @@ -2682,68 +2924,144 @@ xfs_rmap_has_record( memset(&high, 0xFF, sizeof(high)); high.r.rm_startblock = bno + len - 1; - return xfs_btree_has_record(cur, &low, &high, exists); + return xfs_btree_has_records(cur, &low, &high, &mask, outcome); } -/* - * Is there a record for this owner completely covering a given physical - * extent? If so, *has_rmap will be set to true. If there is no record - * or the record only covers part of the range, we set *has_rmap to false. - * This function doesn't perform range lookups or offset checks, so it is - * not suitable for checking data fork blocks. - */ -int -xfs_rmap_record_exists( - struct xfs_btree_cur *cur, +struct xfs_rmap_ownercount { + /* Owner that we're looking for. */ + struct xfs_rmap_irec good; + + /* rmap search keys */ + struct xfs_rmap_irec low; + struct xfs_rmap_irec high; + + struct xfs_rmap_matches *results; + + /* Stop early if we find a nonmatch? */ + bool stop_on_nonmatch; +}; + +/* Does this rmap represent space that can have multiple owners? */ +static inline bool +xfs_rmap_shareable( + struct xfs_mount *mp, + const struct xfs_rmap_irec *rmap) +{ + if (!xfs_has_reflink(mp)) + return false; + if (XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner)) + return false; + if (rmap->rm_flags & (XFS_RMAP_ATTR_FORK | + XFS_RMAP_BMBT_BLOCK)) + return false; + return true; +} + +static inline void +xfs_rmap_ownercount_init( + struct xfs_rmap_ownercount *roc, xfs_agblock_t bno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, - bool *has_rmap) + struct xfs_rmap_matches *results) { - uint64_t owner; - uint64_t offset; - unsigned int flags; - int has_record; - struct xfs_rmap_irec irec; - int error; + memset(roc, 0, sizeof(*roc)); + roc->results = results; + + roc->low.rm_startblock = bno; + memset(&roc->high, 0xFF, sizeof(roc->high)); + roc->high.rm_startblock = bno + len - 1; + + memset(results, 0, sizeof(*results)); + roc->good.rm_startblock = bno; + roc->good.rm_blockcount = len; + roc->good.rm_owner = oinfo->oi_owner; + roc->good.rm_offset = oinfo->oi_offset; + if (oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK) + roc->good.rm_flags |= XFS_RMAP_ATTR_FORK; + if (oinfo->oi_flags & XFS_OWNER_INFO_BMBT_BLOCK) + roc->good.rm_flags |= XFS_RMAP_BMBT_BLOCK; +} - xfs_owner_info_unpack(oinfo, &owner, &offset, &flags); - ASSERT(XFS_RMAP_NON_INODE_OWNER(owner) || - (flags & XFS_RMAP_BMBT_BLOCK)); +/* Figure out if this is a match for the owner. */ +STATIC int +xfs_rmap_count_owners_helper( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xfs_rmap_ownercount *roc = priv; + struct xfs_rmap_irec check = *rec; + unsigned int keyflags; + bool filedata; + int64_t delta; + + filedata = !XFS_RMAP_NON_INODE_OWNER(check.rm_owner) && + !(check.rm_flags & XFS_RMAP_BMBT_BLOCK); + + /* Trim the part of check that comes before the comparison range. */ + delta = (int64_t)roc->good.rm_startblock - check.rm_startblock; + if (delta > 0) { + check.rm_startblock += delta; + check.rm_blockcount -= delta; + if (filedata) + check.rm_offset += delta; + } - error = xfs_rmap_lookup_le(cur, bno, owner, offset, flags, &irec, - &has_record); - if (error) - return error; - if (!has_record) { - *has_rmap = false; - return 0; + /* Trim the part of check that comes after the comparison range. */ + delta = (check.rm_startblock + check.rm_blockcount) - + (roc->good.rm_startblock + roc->good.rm_blockcount); + if (delta > 0) + check.rm_blockcount -= delta; + + /* Don't care about unwritten status for establishing ownership. */ + keyflags = check.rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK); + + if (check.rm_startblock == roc->good.rm_startblock && + check.rm_blockcount == roc->good.rm_blockcount && + check.rm_owner == roc->good.rm_owner && + check.rm_offset == roc->good.rm_offset && + keyflags == roc->good.rm_flags) { + roc->results->matches++; + } else { + roc->results->non_owner_matches++; + if (xfs_rmap_shareable(cur->bc_mp, &roc->good) ^ + xfs_rmap_shareable(cur->bc_mp, &check)) + roc->results->bad_non_owner_matches++; } - *has_rmap = (irec.rm_owner == owner && irec.rm_startblock <= bno && - irec.rm_startblock + irec.rm_blockcount >= bno + len); + if (roc->results->non_owner_matches && roc->stop_on_nonmatch) + return -ECANCELED; + return 0; } -struct xfs_rmap_key_state { - uint64_t owner; - uint64_t offset; - unsigned int flags; -}; - -/* For each rmap given, figure out if it doesn't match the key we want. */ -STATIC int -xfs_rmap_has_other_keys_helper( +/* Count the number of owners and non-owners of this range of blocks. */ +int +xfs_rmap_count_owners( struct xfs_btree_cur *cur, - const struct xfs_rmap_irec *rec, - void *priv) + xfs_agblock_t bno, + xfs_extlen_t len, + const struct xfs_owner_info *oinfo, + struct xfs_rmap_matches *results) { - struct xfs_rmap_key_state *rks = priv; + struct xfs_rmap_ownercount roc; + int error; - if (rks->owner == rec->rm_owner && rks->offset == rec->rm_offset && - ((rks->flags & rec->rm_flags) & XFS_RMAP_KEY_FLAGS) == rks->flags) - return 0; - return -ECANCELED; + xfs_rmap_ownercount_init(&roc, bno, len, oinfo, results); + error = xfs_rmap_query_range(cur, &roc.low, &roc.high, + xfs_rmap_count_owners_helper, &roc); + if (error) + return error; + + /* + * There can't be any non-owner rmaps that conflict with the given + * owner if we didn't find any rmaps matching the owner. + */ + if (!results->matches) + results->bad_non_owner_matches = 0; + + return 0; } /* @@ -2756,28 +3074,26 @@ xfs_rmap_has_other_keys( xfs_agblock_t bno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, - bool *has_rmap) + bool *has_other) { - struct xfs_rmap_irec low = {0}; - struct xfs_rmap_irec high; - struct xfs_rmap_key_state rks; + struct xfs_rmap_matches res; + struct xfs_rmap_ownercount roc; int error; - xfs_owner_info_unpack(oinfo, &rks.owner, &rks.offset, &rks.flags); - *has_rmap = false; - - low.rm_startblock = bno; - memset(&high, 0xFF, sizeof(high)); - high.rm_startblock = bno + len - 1; + xfs_rmap_ownercount_init(&roc, bno, len, oinfo, &res); + roc.stop_on_nonmatch = true; - error = xfs_rmap_query_range(cur, &low, &high, - xfs_rmap_has_other_keys_helper, &rks); + error = xfs_rmap_query_range(cur, &roc.low, &roc.high, + xfs_rmap_count_owners_helper, &roc); if (error == -ECANCELED) { - *has_rmap = true; + *has_other = true; return 0; } + if (error) + return error; - return error; + *has_other = false; + return 0; } const struct xfs_owner_info XFS_RMAP_OINFO_SKIP_UPDATE = { diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 54741a591a17..5f39f6e53cd1 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -7,6 +7,7 @@ #define __XFS_RMAP_H__ struct xfs_perag; +struct xfs_rtgroup; static inline void xfs_rmap_ino_bmbt_owner( @@ -62,13 +63,14 @@ xfs_rmap_irec_offset_pack( return x; } -static inline int +static inline xfs_failaddr_t xfs_rmap_irec_offset_unpack( __u64 offset, struct xfs_rmap_irec *irec) { if (offset & ~(XFS_RMAP_OFF_MASK | XFS_RMAP_OFF_FLAGS)) - return -EFSCORRUPTED; + return __this_address; + irec->rm_offset = XFS_RMAP_OFF(offset); irec->rm_flags = 0; if (offset & XFS_RMAP_OFF_ATTR_FORK) @@ -77,7 +79,7 @@ xfs_rmap_irec_offset_unpack( irec->rm_flags |= XFS_RMAP_BMBT_BLOCK; if (offset & XFS_RMAP_OFF_UNWRITTEN) irec->rm_flags |= XFS_RMAP_UNWRITTEN; - return 0; + return NULL; } static inline void @@ -156,12 +158,24 @@ enum xfs_rmap_intent_type { XFS_RMAP_FREE, }; +#define XFS_RMAP_INTENT_STRINGS \ + { XFS_RMAP_MAP, "map" }, \ + { XFS_RMAP_MAP_SHARED, "map_shared" }, \ + { XFS_RMAP_UNMAP, "unmap" }, \ + { XFS_RMAP_UNMAP_SHARED, "unmap_shared" }, \ + { XFS_RMAP_CONVERT, "cvt" }, \ + { XFS_RMAP_CONVERT_SHARED, "cvt_shared" }, \ + { XFS_RMAP_ALLOC, "alloc" }, \ + { XFS_RMAP_FREE, "free" } + struct xfs_rmap_intent { struct list_head ri_list; enum xfs_rmap_intent_type ri_type; int ri_whichfork; uint64_t ri_owner; struct xfs_bmbt_irec ri_bmap; + struct xfs_group *ri_group; + bool ri_realtime; }; /* functions for updating the rmapbt based on bmbt map/unmap operations */ @@ -172,17 +186,17 @@ void xfs_rmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip, void xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, struct xfs_bmbt_irec *imap); -void xfs_rmap_alloc_extent(struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner); -void xfs_rmap_free_extent(struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner); - -void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp, - struct xfs_btree_cur *rcur, int error); -int xfs_rmap_finish_one(struct xfs_trans *tp, enum xfs_rmap_intent_type type, - uint64_t owner, int whichfork, xfs_fileoff_t startoff, - xfs_fsblock_t startblock, xfs_filblks_t blockcount, - xfs_exntst_t state, struct xfs_btree_cur **pcur); +void xfs_rmap_alloc_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno, + xfs_extlen_t len, uint64_t owner); +void xfs_rmap_free_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno, + xfs_extlen_t len, uint64_t owner); + +int xfs_rmap_finish_one(struct xfs_trans *tp, struct xfs_rmap_intent *ri, + struct xfs_btree_cur **pcur); +int __xfs_rmap_finish_intent(struct xfs_btree_cur *rcur, + enum xfs_rmap_intent_type op, xfs_agblock_t bno, + xfs_extlen_t len, const struct xfs_owner_info *oinfo, + bool unwritten); int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno, uint64_t owner, uint64_t offset, unsigned int flags, @@ -190,16 +204,33 @@ int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno, int xfs_rmap_compare(const struct xfs_rmap_irec *a, const struct xfs_rmap_irec *b); union xfs_btree_rec; -int xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec, +xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_rmap_irec *irec); -int xfs_rmap_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno, - xfs_extlen_t len, bool *exists); -int xfs_rmap_record_exists(struct xfs_btree_cur *cur, xfs_agblock_t bno, +xfs_failaddr_t xfs_rmap_check_irec(struct xfs_perag *pag, + const struct xfs_rmap_irec *irec); +xfs_failaddr_t xfs_rtrmap_check_irec(struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec); + +int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno, + xfs_extlen_t len, enum xbtree_recpacking *outcome); + +struct xfs_rmap_matches { + /* Number of owner matches. */ + unsigned long long matches; + + /* Number of non-owner matches. */ + unsigned long long non_owner_matches; + + /* Number of non-owner matches that conflict with the owner matches. */ + unsigned long long bad_non_owner_matches; +}; + +int xfs_rmap_count_owners(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, - bool *has_rmap); + struct xfs_rmap_matches *rmatch); int xfs_rmap_has_other_keys(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, - bool *has_rmap); + bool *has_other); int xfs_rmap_map_raw(struct xfs_btree_cur *cur, struct xfs_rmap_irec *rmap); extern const struct xfs_owner_info XFS_RMAP_OINFO_SKIP_UPDATE; @@ -217,4 +248,29 @@ extern struct kmem_cache *xfs_rmap_intent_cache; int __init xfs_rmap_intent_init_cache(void); void xfs_rmap_intent_destroy_cache(void); +/* + * Parameters for tracking reverse mapping changes. The hook function arg + * parameter is enum xfs_rmap_intent_type, and the rest is below. + */ +struct xfs_rmap_update_params { + xfs_agblock_t startblock; + xfs_extlen_t blockcount; + struct xfs_owner_info oinfo; + bool unwritten; +}; + +#ifdef CONFIG_XFS_LIVE_HOOKS + +struct xfs_rmap_hook { + struct xfs_hook rmap_hook; +}; + +void xfs_rmap_hook_disable(void); +void xfs_rmap_hook_enable(void); + +int xfs_rmap_hook_add(struct xfs_group *xg, struct xfs_rmap_hook *hook); +void xfs_rmap_hook_del(struct xfs_group *xg, struct xfs_rmap_hook *hook); +void xfs_rmap_hook_setup(struct xfs_rmap_hook *hook, notifier_fn_t mod_fn); +#endif + #endif /* __XFS_RMAP_H__ */ diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index 7f83f62e51e0..bf16aee50d73 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -16,11 +16,14 @@ #include "xfs_btree_staging.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" +#include "xfs_health.h" #include "xfs_trace.h" #include "xfs_error.h" #include "xfs_extent_busy.h" #include "xfs_ag.h" #include "xfs_ag_resv.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" static struct kmem_cache *xfs_rmapbt_cur_cache; @@ -54,7 +57,7 @@ xfs_rmapbt_dup_cursor( struct xfs_btree_cur *cur) { return xfs_rmapbt_init_cursor(cur->bc_mp, cur->bc_tp, - cur->bc_ag.agbp, cur->bc_ag.pag); + cur->bc_ag.agbp, to_perag(cur->bc_group)); } STATIC void @@ -63,15 +66,15 @@ xfs_rmapbt_set_root( const union xfs_btree_ptr *ptr, int inc) { - struct xfs_buf *agbp = cur->bc_ag.agbp; - struct xfs_agf *agf = agbp->b_addr; - int btnum = cur->bc_btnum; + struct xfs_buf *agbp = cur->bc_ag.agbp; + struct xfs_agf *agf = agbp->b_addr; + struct xfs_perag *pag = to_perag(cur->bc_group); ASSERT(ptr->s != 0); - agf->agf_roots[btnum] = ptr->s; - be32_add_cpu(&agf->agf_levels[btnum], inc); - cur->bc_ag.pag->pagf_levels[btnum] += inc; + agf->agf_rmap_root = ptr->s; + be32_add_cpu(&agf->agf_rmap_level, inc); + pag->pagf_rmap_level += inc; xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS); } @@ -85,7 +88,8 @@ xfs_rmapbt_alloc_block( { struct xfs_buf *agbp = cur->bc_ag.agbp; struct xfs_agf *agf = agbp->b_addr; - struct xfs_perag *pag = cur->bc_ag.pag; + struct xfs_perag *pag = to_perag(cur->bc_group); + struct xfs_alloc_arg args = { .len = 1 }; int error; xfs_agblock_t bno; @@ -94,20 +98,22 @@ xfs_rmapbt_alloc_block( &bno, 1); if (error) return error; - - trace_xfs_rmapbt_alloc_block(cur->bc_mp, pag->pag_agno, bno, 1); if (bno == NULLAGBLOCK) { *stat = 0; return 0; } - xfs_extent_busy_reuse(cur->bc_mp, pag, bno, 1, false); + xfs_extent_busy_reuse(pag_group(pag), bno, 1, false); new->s = cpu_to_be32(bno); be32_add_cpu(&agf->agf_rmap_blocks, 1); xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS); - xfs_ag_resv_rmapbt_alloc(cur->bc_mp, pag->pag_agno); + /* + * Since rmapbt blocks are sourced from the AGFL, they are allocated one + * at a time and the reservation updates don't require a transaction. + */ + xfs_ag_resv_alloc_extent(pag, XFS_AG_RESV_RMAPBT, &args); *stat = 1; return 0; @@ -120,20 +126,18 @@ xfs_rmapbt_free_block( { struct xfs_buf *agbp = cur->bc_ag.agbp; struct xfs_agf *agf = agbp->b_addr; - struct xfs_perag *pag = cur->bc_ag.pag; + struct xfs_perag *pag = to_perag(cur->bc_group); xfs_agblock_t bno; int error; bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp)); - trace_xfs_rmapbt_free_block(cur->bc_mp, pag->pag_agno, - bno, 1); be32_add_cpu(&agf->agf_rmap_blocks, -1); xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS); error = xfs_alloc_put_freelist(pag, cur->bc_tp, agbp, NULL, bno, 1); if (error) return error; - xfs_extent_busy_insert(cur->bc_tp, pag, bno, 1, + xfs_extent_busy_insert(cur->bc_tp, pag_group(pag), bno, 1, XFS_EXTENT_BUSY_SKIP_DISCARD); xfs_ag_resv_free_extent(pag, XFS_AG_RESV_RMAPBT, NULL, 1); @@ -156,6 +160,16 @@ xfs_rmapbt_get_maxrecs( return cur->bc_mp->m_rmap_mxr[level != 0]; } +/* + * Convert the ondisk record's offset field into the ondisk key's offset field. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline __be64 ondisk_rec_offset_to_key(const union xfs_btree_rec *rec) +{ + return rec->rmap.rm_offset & ~cpu_to_be64(XFS_RMAP_OFF_UNWRITTEN); +} + STATIC void xfs_rmapbt_init_key_from_rec( union xfs_btree_key *key, @@ -163,7 +177,7 @@ xfs_rmapbt_init_key_from_rec( { key->rmap.rm_startblock = rec->rmap.rm_startblock; key->rmap.rm_owner = rec->rmap.rm_owner; - key->rmap.rm_offset = rec->rmap.rm_offset; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); } /* @@ -186,7 +200,7 @@ xfs_rmapbt_init_high_key_from_rec( key->rmap.rm_startblock = rec->rmap.rm_startblock; be32_add_cpu(&key->rmap.rm_startblock, adj); key->rmap.rm_owner = rec->rmap.rm_owner; - key->rmap.rm_offset = rec->rmap.rm_offset; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); if (XFS_RMAP_NON_INODE_OWNER(be64_to_cpu(rec->rmap.rm_owner)) || XFS_RMAP_IS_BMBT_BLOCK(be64_to_cpu(rec->rmap.rm_offset))) return; @@ -214,70 +228,71 @@ xfs_rmapbt_init_ptr_from_cur( { struct xfs_agf *agf = cur->bc_ag.agbp->b_addr; - ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno)); + ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agf->agf_seqno)); - ptr->s = agf->agf_roots[cur->bc_btnum]; + ptr->s = agf->agf_rmap_root; } -STATIC int64_t -xfs_rmapbt_key_diff( +/* + * Mask the appropriate parts of the ondisk key field for a key comparison. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline uint64_t offset_keymask(uint64_t offset) +{ + return offset & ~XFS_RMAP_OFF_UNWRITTEN; +} + +STATIC int +xfs_rmapbt_cmp_key_with_cur( struct xfs_btree_cur *cur, const union xfs_btree_key *key) { struct xfs_rmap_irec *rec = &cur->bc_rec.r; const struct xfs_rmap_key *kp = &key->rmap; - __u64 x, y; - int64_t d; - d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock; - if (d) - return d; - - x = be64_to_cpu(kp->rm_owner); - y = rec->rm_owner; - if (x > y) - return 1; - else if (y > x) - return -1; - - x = XFS_RMAP_OFF(be64_to_cpu(kp->rm_offset)); - y = rec->rm_offset; - if (x > y) - return 1; - else if (y > x) - return -1; - return 0; + return cmp_int(be32_to_cpu(kp->rm_startblock), rec->rm_startblock) ?: + cmp_int(be64_to_cpu(kp->rm_owner), rec->rm_owner) ?: + cmp_int(offset_keymask(be64_to_cpu(kp->rm_offset)), + offset_keymask(xfs_rmap_irec_offset_pack(rec))); } -STATIC int64_t -xfs_rmapbt_diff_two_keys( +STATIC int +xfs_rmapbt_cmp_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { const struct xfs_rmap_key *kp1 = &k1->rmap; const struct xfs_rmap_key *kp2 = &k2->rmap; - int64_t d; - __u64 x, y; + int d; - d = (int64_t)be32_to_cpu(kp1->rm_startblock) - - be32_to_cpu(kp2->rm_startblock); + /* Doesn't make sense to mask off the physical space part */ + ASSERT(!mask || mask->rmap.rm_startblock); + + d = cmp_int(be32_to_cpu(kp1->rm_startblock), + be32_to_cpu(kp2->rm_startblock)); if (d) return d; - x = be64_to_cpu(kp1->rm_owner); - y = be64_to_cpu(kp2->rm_owner); - if (x > y) - return 1; - else if (y > x) - return -1; + if (!mask || mask->rmap.rm_owner) { + d = cmp_int(be64_to_cpu(kp1->rm_owner), + be64_to_cpu(kp2->rm_owner)); + if (d) + return d; + } + + if (!mask || mask->rmap.rm_offset) { + /* Doesn't make sense to allow offset but not owner */ + ASSERT(!mask || mask->rmap.rm_owner); + + d = cmp_int(offset_keymask(be64_to_cpu(kp1->rm_offset)), + offset_keymask(be64_to_cpu(kp2->rm_offset))); + if (d) + return d; + } - x = XFS_RMAP_OFF(be64_to_cpu(kp1->rm_offset)); - y = XFS_RMAP_OFF(be64_to_cpu(kp2->rm_offset)); - if (x > y) - return 1; - else if (y > x) - return -1; return 0; } @@ -308,18 +323,29 @@ xfs_rmapbt_verify( if (!xfs_has_rmapbt(mp)) return __this_address; - fa = xfs_btree_sblock_v5hdr_verify(bp); + fa = xfs_btree_agblock_v5hdr_verify(bp); if (fa) return fa; level = be16_to_cpu(block->bb_level); - if (pag && pag->pagf_init) { - if (level >= pag->pagf_levels[XFS_BTNUM_RMAPi]) + if (pag && xfs_perag_initialised_agf(pag)) { + unsigned int maxlevel = pag->pagf_rmap_level; + +#ifdef CONFIG_XFS_ONLINE_REPAIR + /* + * Online repair could be rewriting the free space btrees, so + * we'll validate against the larger of either tree while this + * is going on. + */ + maxlevel = max_t(unsigned int, maxlevel, + pag->pagf_repair_rmap_level); +#endif + if (level >= maxlevel) return __this_address; } else if (level >= mp->m_rmap_maxlevels) return __this_address; - return xfs_btree_sblock_verify(bp, mp->m_rmap_mxr[level != 0]); + return xfs_btree_agblock_verify(bp, mp->m_rmap_mxr[level != 0]); } static void @@ -328,7 +354,7 @@ xfs_rmapbt_read_verify( { xfs_failaddr_t fa; - if (!xfs_btree_sblock_verify_crc(bp)) + if (!xfs_btree_agblock_verify_crc(bp)) xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_rmapbt_verify(bp); @@ -352,7 +378,7 @@ xfs_rmapbt_write_verify( xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } - xfs_btree_sblock_calc_crc(bp); + xfs_btree_agblock_calc_crc(bp); } @@ -387,8 +413,8 @@ xfs_rmapbt_keys_inorder( return 1; else if (a > b) return 0; - a = XFS_RMAP_OFF(be64_to_cpu(k1->rmap.rm_offset)); - b = XFS_RMAP_OFF(be64_to_cpu(k2->rmap.rm_offset)); + a = offset_keymask(be64_to_cpu(k1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(k2->rmap.rm_offset)); if (a <= b) return 1; return 0; @@ -417,16 +443,46 @@ xfs_rmapbt_recs_inorder( return 1; else if (a > b) return 0; - a = XFS_RMAP_OFF(be64_to_cpu(r1->rmap.rm_offset)); - b = XFS_RMAP_OFF(be64_to_cpu(r2->rmap.rm_offset)); + a = offset_keymask(be64_to_cpu(r1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(r2->rmap.rm_offset)); if (a <= b) return 1; return 0; } -static const struct xfs_btree_ops xfs_rmapbt_ops = { +STATIC enum xbtree_key_contig +xfs_rmapbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->rmap.rm_startblock); + + /* + * We only support checking contiguity of the physical space component. + * If any callers ever need more specificity than that, they'll have to + * implement it here. + */ + ASSERT(!mask || (!mask->rmap.rm_owner && !mask->rmap.rm_offset)); + + return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock), + be32_to_cpu(key2->rmap.rm_startblock)); +} + +const struct xfs_btree_ops xfs_rmapbt_ops = { + .name = "rmap", + .type = XFS_BTREE_TYPE_AG, + .geom_flags = XFS_BTGEO_OVERLAPPING, + .rec_len = sizeof(struct xfs_rmap_rec), + /* Overlapping btree; 2 keys per pointer. */ .key_len = 2 * sizeof(struct xfs_rmap_key), + .ptr_len = XFS_BTREE_SHORT_PTR_LEN, + + .lru_refs = XFS_RMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rmap_2), + .sick_mask = XFS_SICK_AG_RMAPBT, .dup_cursor = xfs_rmapbt_dup_cursor, .set_root = xfs_rmapbt_set_root, @@ -438,65 +494,183 @@ static const struct xfs_btree_ops xfs_rmapbt_ops = { .init_high_key_from_rec = xfs_rmapbt_init_high_key_from_rec, .init_rec_from_cur = xfs_rmapbt_init_rec_from_cur, .init_ptr_from_cur = xfs_rmapbt_init_ptr_from_cur, - .key_diff = xfs_rmapbt_key_diff, + .cmp_key_with_cur = xfs_rmapbt_cmp_key_with_cur, .buf_ops = &xfs_rmapbt_buf_ops, - .diff_two_keys = xfs_rmapbt_diff_two_keys, + .cmp_two_keys = xfs_rmapbt_cmp_two_keys, .keys_inorder = xfs_rmapbt_keys_inorder, .recs_inorder = xfs_rmapbt_recs_inorder, + .keys_contiguous = xfs_rmapbt_keys_contiguous, }; -static struct xfs_btree_cur * -xfs_rmapbt_init_common( +/* + * Create a new reverse mapping btree cursor. + * + * For staging cursors tp and agbp are NULL. + */ +struct xfs_btree_cur * +xfs_rmapbt_init_cursor( struct xfs_mount *mp, struct xfs_trans *tp, + struct xfs_buf *agbp, struct xfs_perag *pag) { struct xfs_btree_cur *cur; - /* Overlapping btree; 2 keys per pointer. */ - cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP, + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rmapbt_ops, mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache); - cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING; - cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2); - cur->bc_ops = &xfs_rmapbt_ops; - - /* take a reference for the cursor */ - atomic_inc(&pag->pag_ref); - cur->bc_ag.pag = pag; + cur->bc_group = xfs_group_hold(pag_group(pag)); + cur->bc_ag.agbp = agbp; + if (agbp) { + struct xfs_agf *agf = agbp->b_addr; + cur->bc_nlevels = be32_to_cpu(agf->agf_rmap_level); + } return cur; } -/* Create a new reverse mapping btree cursor. */ +#ifdef CONFIG_XFS_BTREE_IN_MEM +static inline unsigned int +xfs_rmapbt_mem_block_maxrecs( + unsigned int blocklen, + bool leaf) +{ + if (leaf) + return blocklen / sizeof(struct xfs_rmap_rec); + return blocklen / + (2 * sizeof(struct xfs_rmap_key) + sizeof(__be64)); +} + +/* + * Validate an in-memory rmap btree block. Callers are allowed to generate an + * in-memory btree even if the ondisk feature is not enabled. + */ +static xfs_failaddr_t +xfs_rmapbt_mem_verify( + struct xfs_buf *bp) +{ + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + unsigned int level; + unsigned int maxrecs; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + + level = be16_to_cpu(block->bb_level); + if (level >= xfs_rmapbt_maxlevels_ondisk()) + return __this_address; + + maxrecs = xfs_rmapbt_mem_block_maxrecs( + XFBNO_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN, level == 0); + return xfs_btree_memblock_verify(bp, maxrecs); +} + +static void +xfs_rmapbt_mem_rw_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa = xfs_rmapbt_mem_verify(bp); + + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); +} + +/* skip crc checks on in-memory btrees to save time */ +static const struct xfs_buf_ops xfs_rmapbt_mem_buf_ops = { + .name = "xfs_rmapbt_mem", + .magic = { 0, cpu_to_be32(XFS_RMAP_CRC_MAGIC) }, + .verify_read = xfs_rmapbt_mem_rw_verify, + .verify_write = xfs_rmapbt_mem_rw_verify, + .verify_struct = xfs_rmapbt_mem_verify, +}; + +const struct xfs_btree_ops xfs_rmapbt_mem_ops = { + .name = "mem_rmap", + .type = XFS_BTREE_TYPE_MEM, + .geom_flags = XFS_BTGEO_OVERLAPPING, + + .rec_len = sizeof(struct xfs_rmap_rec), + /* Overlapping btree; 2 keys per pointer. */ + .key_len = 2 * sizeof(struct xfs_rmap_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_RMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rmap_mem_2), + + .dup_cursor = xfbtree_dup_cursor, + .set_root = xfbtree_set_root, + .alloc_block = xfbtree_alloc_block, + .free_block = xfbtree_free_block, + .get_minrecs = xfbtree_get_minrecs, + .get_maxrecs = xfbtree_get_maxrecs, + .init_key_from_rec = xfs_rmapbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rmapbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rmapbt_init_rec_from_cur, + .init_ptr_from_cur = xfbtree_init_ptr_from_cur, + .cmp_key_with_cur = xfs_rmapbt_cmp_key_with_cur, + .buf_ops = &xfs_rmapbt_mem_buf_ops, + .cmp_two_keys = xfs_rmapbt_cmp_two_keys, + .keys_inorder = xfs_rmapbt_keys_inorder, + .recs_inorder = xfs_rmapbt_recs_inorder, + .keys_contiguous = xfs_rmapbt_keys_contiguous, +}; + +/* Create a cursor for an in-memory btree. */ struct xfs_btree_cur * -xfs_rmapbt_init_cursor( - struct xfs_mount *mp, +xfs_rmapbt_mem_cursor( + struct xfs_perag *pag, struct xfs_trans *tp, - struct xfs_buf *agbp, - struct xfs_perag *pag) + struct xfbtree *xfbt) { - struct xfs_agf *agf = agbp->b_addr; struct xfs_btree_cur *cur; - cur = xfs_rmapbt_init_common(mp, tp, pag); - cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]); - cur->bc_ag.agbp = agbp; + cur = xfs_btree_alloc_cursor(pag_mount(pag), tp, &xfs_rmapbt_mem_ops, + xfs_rmapbt_maxlevels_ondisk(), xfs_rmapbt_cur_cache); + cur->bc_mem.xfbtree = xfbt; + cur->bc_nlevels = xfbt->nlevels; + + cur->bc_group = xfs_group_hold(pag_group(pag)); return cur; } -/* Create a new reverse mapping btree cursor with a fake root for staging. */ -struct xfs_btree_cur * -xfs_rmapbt_stage_cursor( +/* Create an in-memory rmap btree. */ +int +xfs_rmapbt_mem_init( struct xfs_mount *mp, - struct xbtree_afakeroot *afake, - struct xfs_perag *pag) + struct xfbtree *xfbt, + struct xfs_buftarg *btp, + xfs_agnumber_t agno) { - struct xfs_btree_cur *cur; + xfbt->owner = agno; + return xfbtree_init(mp, xfbt, btp, &xfs_rmapbt_mem_ops); +} - cur = xfs_rmapbt_init_common(mp, NULL, pag); - xfs_btree_stage_afakeroot(cur, afake); - return cur; +/* Compute the max possible height for reverse mapping btrees in memory. */ +static unsigned int +xfs_rmapbt_mem_maxlevels(void) +{ + unsigned int minrecs[2]; + unsigned int blocklen; + + blocklen = XFBNO_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; + + minrecs[0] = xfs_rmapbt_mem_block_maxrecs(blocklen, true) / 2; + minrecs[1] = xfs_rmapbt_mem_block_maxrecs(blocklen, false) / 2; + + /* + * How tall can an in-memory rmap btree become if we filled the entire + * AG with rmap records? + */ + return xfs_btree_compute_maxlevels(minrecs, + XFS_MAX_AG_BYTES / sizeof(struct xfs_rmap_rec)); } +#else +# define xfs_rmapbt_mem_maxlevels() (0) +#endif /* CONFIG_XFS_BTREE_IN_MEM */ /* * Install a new reverse mapping btree root. Caller is responsible for @@ -513,12 +687,12 @@ xfs_rmapbt_commit_staged_btree( ASSERT(cur->bc_flags & XFS_BTREE_STAGING); - agf->agf_roots[cur->bc_btnum] = cpu_to_be32(afake->af_root); - agf->agf_levels[cur->bc_btnum] = cpu_to_be32(afake->af_levels); + agf->agf_rmap_root = cpu_to_be32(afake->af_root); + agf->agf_rmap_level = cpu_to_be32(afake->af_levels); agf->agf_rmap_blocks = cpu_to_be32(afake->af_blocks); xfs_alloc_log_agf(tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS | XFS_AGF_RMAP_BLOCKS); - xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_rmapbt_ops); + xfs_btree_commit_afakeroot(cur, tp, agbp); } /* Calculate number of records in a reverse mapping btree block. */ @@ -536,10 +710,11 @@ xfs_rmapbt_block_maxrecs( /* * Calculate number of records in an rmap btree block. */ -int +unsigned int xfs_rmapbt_maxrecs( - int blocklen, - int leaf) + struct xfs_mount *mp, + unsigned int blocklen, + bool leaf) { blocklen -= XFS_RMAP_BLOCK_LEN; return xfs_rmapbt_block_maxrecs(blocklen, leaf); @@ -568,7 +743,8 @@ xfs_rmapbt_maxlevels_ondisk(void) * like if it consumes almost all the blocks in the AG due to maximal * sharing factor. */ - return xfs_btree_space_to_height(minrecs, XFS_MAX_CRC_AG_BLOCKS); + return max(xfs_btree_space_to_height(minrecs, XFS_MAX_CRC_AG_BLOCKS), + xfs_rmapbt_mem_maxlevels()); } /* Compute the maximum height of an rmap btree. */ @@ -666,7 +842,7 @@ xfs_rmapbt_calc_reserves( * never be available for the kinds of things that would require btree * expansion. We therefore can pretend the space isn't there. */ - if (xfs_ag_contains_log(mp, pag->pag_agno)) + if (xfs_ag_contains_log(mp, pag_agno(pag))) agblocks -= mp->m_sb.sb_logblocks; /* Reserve 1% of the AG or enough for 1 block per record. */ diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h index 3244715dd111..119b1567cd0e 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.h +++ b/fs/xfs/libxfs/xfs_rmap_btree.h @@ -10,6 +10,7 @@ struct xfs_buf; struct xfs_btree_cur; struct xfs_mount; struct xbtree_afakeroot; +struct xfbtree; /* rmaps only exist on crc enabled filesystems */ #define XFS_RMAP_BLOCK_LEN XFS_BTREE_SBLOCK_CRC_LEN @@ -44,11 +45,10 @@ struct xbtree_afakeroot; struct xfs_btree_cur *xfs_rmapbt_init_cursor(struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_buf *bp, struct xfs_perag *pag); -struct xfs_btree_cur *xfs_rmapbt_stage_cursor(struct xfs_mount *mp, - struct xbtree_afakeroot *afake, struct xfs_perag *pag); void xfs_rmapbt_commit_staged_btree(struct xfs_btree_cur *cur, struct xfs_trans *tp, struct xfs_buf *agbp); -int xfs_rmapbt_maxrecs(int blocklen, int leaf); +unsigned int xfs_rmapbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, + bool leaf); extern void xfs_rmapbt_compute_maxlevels(struct xfs_mount *mp); extern xfs_extlen_t xfs_rmapbt_calc_size(struct xfs_mount *mp, @@ -64,4 +64,9 @@ unsigned int xfs_rmapbt_maxlevels_ondisk(void); int __init xfs_rmapbt_init_cur_cache(void); void xfs_rmapbt_destroy_cur_cache(void); +struct xfs_btree_cur *xfs_rmapbt_mem_cursor(struct xfs_perag *pag, + struct xfs_trans *tp, struct xfbtree *xfbtree); +int xfs_rmapbt_mem_init(struct xfs_mount *mp, struct xfbtree *xfbtree, + struct xfs_buftarg *btp, xfs_agnumber_t agno); + #endif /* __XFS_RMAP_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index fa180ab66b73..618061d898d4 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -13,31 +13,94 @@ #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_bmap.h" +#include "xfs_bmap_btree.h" +#include "xfs_trans_space.h" #include "xfs_trans.h" #include "xfs_rtalloc.h" #include "xfs_error.h" +#include "xfs_rtbitmap.h" +#include "xfs_health.h" +#include "xfs_sb.h" +#include "xfs_errortag.h" +#include "xfs_log.h" +#include "xfs_buf_item.h" +#include "xfs_extent_busy.h" /* * Realtime allocator bitmap functions shared with userspace. */ -/* - * Real time buffers need verifiers to avoid runtime warnings during IO. - * We don't have anything to verify, however, so these are just dummy - * operations. - */ +static xfs_failaddr_t +xfs_rtbuf_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_mount; + struct xfs_rtbuf_blkinfo *hdr = bp->b_addr; + + if (!xfs_verify_magic(bp, hdr->rt_magic)) + return __this_address; + if (!xfs_has_rtgroups(mp)) + return __this_address; + if (!xfs_has_crc(mp)) + return __this_address; + if (!uuid_equal(&hdr->rt_uuid, &mp->m_sb.sb_meta_uuid)) + return __this_address; + if (hdr->rt_blkno != cpu_to_be64(xfs_buf_daddr(bp))) + return __this_address; + return NULL; +} + static void xfs_rtbuf_verify_read( - struct xfs_buf *bp) + struct xfs_buf *bp) { + struct xfs_mount *mp = bp->b_mount; + struct xfs_rtbuf_blkinfo *hdr = bp->b_addr; + xfs_failaddr_t fa; + + if (!xfs_has_rtgroups(mp)) + return; + + if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr->rt_lsn))) { + fa = __this_address; + goto fail; + } + + if (!xfs_buf_verify_cksum(bp, XFS_RTBUF_CRC_OFF)) { + fa = __this_address; + goto fail; + } + + fa = xfs_rtbuf_verify(bp); + if (fa) + goto fail; + return; +fail: + xfs_verifier_error(bp, -EFSCORRUPTED, fa); } static void xfs_rtbuf_verify_write( struct xfs_buf *bp) { - return; + struct xfs_mount *mp = bp->b_mount; + struct xfs_rtbuf_blkinfo *hdr = bp->b_addr; + struct xfs_buf_log_item *bip = bp->b_log_item; + xfs_failaddr_t fa; + + if (!xfs_has_rtgroups(mp)) + return; + + fa = xfs_rtbuf_verify(bp); + if (fa) { + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + + if (bip) + hdr->rt_lsn = cpu_to_be64(bip->bli_item.li_lsn); + xfs_buf_update_cksum(bp, XFS_RTBUF_CRC_OFF); } const struct xfs_buf_ops xfs_rtbuf_ops = { @@ -46,93 +109,197 @@ const struct xfs_buf_ops xfs_rtbuf_ops = { .verify_write = xfs_rtbuf_verify_write, }; +const struct xfs_buf_ops xfs_rtbitmap_buf_ops = { + .name = "xfs_rtbitmap", + .magic = { 0, cpu_to_be32(XFS_RTBITMAP_MAGIC) }, + .verify_read = xfs_rtbuf_verify_read, + .verify_write = xfs_rtbuf_verify_write, + .verify_struct = xfs_rtbuf_verify, +}; + +const struct xfs_buf_ops xfs_rtsummary_buf_ops = { + .name = "xfs_rtsummary", + .magic = { 0, cpu_to_be32(XFS_RTSUMMARY_MAGIC) }, + .verify_read = xfs_rtbuf_verify_read, + .verify_write = xfs_rtbuf_verify_write, + .verify_struct = xfs_rtbuf_verify, +}; + +/* Release cached rt bitmap and summary buffers. */ +void +xfs_rtbuf_cache_relse( + struct xfs_rtalloc_args *args) +{ + if (args->rbmbp) { + xfs_trans_brelse(args->tp, args->rbmbp); + args->rbmbp = NULL; + args->rbmoff = NULLFILEOFF; + } + if (args->sumbp) { + xfs_trans_brelse(args->tp, args->sumbp); + args->sumbp = NULL; + args->sumoff = NULLFILEOFF; + } +} + /* * Get a buffer for the bitmap or summary file block specified. * The buffer is returned read and locked. */ -int +static int xfs_rtbuf_get( - xfs_mount_t *mp, /* file system mount structure */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_rtblock_t block, /* block number in bitmap or summary */ - int issum, /* is summary not bitmap */ - struct xfs_buf **bpp) /* output: buffer for the block */ + struct xfs_rtalloc_args *args, + xfs_fileoff_t block, /* block number in bitmap or summary */ + enum xfs_rtg_inodes type) { - struct xfs_buf *bp; /* block buffer, result */ - xfs_inode_t *ip; /* bitmap or summary inode */ - xfs_bmbt_irec_t map; - int nmap = 1; - int error; /* error value */ + struct xfs_inode *ip = args->rtg->rtg_inodes[type]; + struct xfs_mount *mp = args->mp; + struct xfs_buf **cbpp; /* cached block buffer */ + xfs_fileoff_t *coffp; /* cached block number */ + struct xfs_buf *bp; /* block buffer, result */ + struct xfs_bmbt_irec map; + enum xfs_blft buf_type; + int nmap = 1; + int error; + + switch (type) { + case XFS_RTGI_SUMMARY: + cbpp = &args->sumbp; + coffp = &args->sumoff; + buf_type = XFS_BLFT_RTSUMMARY_BUF; + break; + case XFS_RTGI_BITMAP: + cbpp = &args->rbmbp; + coffp = &args->rbmoff; + buf_type = XFS_BLFT_RTBITMAP_BUF; + break; + default: + return -EINVAL; + } + + /* + * If we have a cached buffer, and the block number matches, use that. + */ + if (*cbpp && *coffp == block) + return 0; - ip = issum ? mp->m_rsumip : mp->m_rbmip; + /* + * Otherwise we have to have to get the buffer. If there was an old + * one, get rid of it first. + */ + if (*cbpp) { + xfs_trans_brelse(args->tp, *cbpp); + *cbpp = NULL; + } error = xfs_bmapi_read(ip, block, 1, &map, &nmap, 0); if (error) return error; - if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map))) + if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map))) { + xfs_rtginode_mark_sick(args->rtg, type); return -EFSCORRUPTED; + } ASSERT(map.br_startblock != NULLFSBLOCK); - error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, + error = xfs_trans_read_buf(mp, args->tp, mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, map.br_startblock), - mp->m_bsize, 0, &bp, &xfs_rtbuf_ops); + mp->m_bsize, 0, &bp, + xfs_rtblock_ops(mp, type)); + if (xfs_metadata_is_sick(error)) + xfs_rtginode_mark_sick(args->rtg, type); if (error) return error; - xfs_trans_buf_set_type(tp, bp, issum ? XFS_BLFT_RTSUMMARY_BUF - : XFS_BLFT_RTBITMAP_BUF); - *bpp = bp; + if (xfs_has_rtgroups(mp)) { + struct xfs_rtbuf_blkinfo *hdr = bp->b_addr; + + if (hdr->rt_owner != cpu_to_be64(ip->i_ino)) { + xfs_buf_mark_corrupt(bp); + xfs_trans_brelse(args->tp, bp); + xfs_rtginode_mark_sick(args->rtg, type); + return -EFSCORRUPTED; + } + } + + xfs_trans_buf_set_type(args->tp, bp, buf_type); + *cbpp = bp; + *coffp = block; return 0; } +int +xfs_rtbitmap_read_buf( + struct xfs_rtalloc_args *args, + xfs_fileoff_t block) +{ + struct xfs_mount *mp = args->mp; + + if (XFS_IS_CORRUPT(mp, block >= mp->m_sb.sb_rbmblocks)) { + xfs_rtginode_mark_sick(args->rtg, XFS_RTGI_BITMAP); + return -EFSCORRUPTED; + } + + return xfs_rtbuf_get(args, block, XFS_RTGI_BITMAP); +} + +int +xfs_rtsummary_read_buf( + struct xfs_rtalloc_args *args, + xfs_fileoff_t block) +{ + struct xfs_mount *mp = args->mp; + + if (XFS_IS_CORRUPT(mp, block >= mp->m_rsumblocks)) { + xfs_rtginode_mark_sick(args->rtg, XFS_RTGI_SUMMARY); + return -EFSCORRUPTED; + } + return xfs_rtbuf_get(args, block, XFS_RTGI_SUMMARY); +} + /* - * Searching backward from start to limit, find the first block whose - * allocated/free state is different from start's. + * Searching backward from start find the first block whose allocated/free state + * is different from start's. */ int xfs_rtfind_back( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_rtblock_t start, /* starting block to look at */ - xfs_rtblock_t limit, /* last block to look at */ - xfs_rtblock_t *rtblock) /* out: start block found */ + struct xfs_rtalloc_args *args, + xfs_rtxnum_t start, /* starting rtext to look at */ + xfs_rtxnum_t *rtx) /* out: start rtext found */ { - xfs_rtword_t *b; /* current word in buffer */ - int bit; /* bit number in the word */ - xfs_rtblock_t block; /* bitmap block number */ - struct xfs_buf *bp; /* buf for the block */ - xfs_rtword_t *bufp; /* starting word in buffer */ - int error; /* error value */ - xfs_rtblock_t firstbit; /* first useful bit in the word */ - xfs_rtblock_t i; /* current bit number rel. to start */ - xfs_rtblock_t len; /* length of inspected area */ - xfs_rtword_t mask; /* mask of relevant bits for value */ - xfs_rtword_t want; /* mask for "good" values */ - xfs_rtword_t wdiff; /* difference from wanted value */ - int word; /* word number in the buffer */ + struct xfs_mount *mp = args->mp; + int bit; /* bit number in the word */ + xfs_fileoff_t block; /* bitmap block number */ + int error; /* error value */ + xfs_rtxnum_t firstbit; /* first useful bit in the word */ + xfs_rtxnum_t i; /* current bit number rel. to start */ + xfs_rtxnum_t len; /* length of inspected area */ + xfs_rtword_t mask; /* mask of relevant bits for value */ + xfs_rtword_t want; /* mask for "good" values */ + xfs_rtword_t wdiff; /* difference from wanted value */ + xfs_rtword_t incore; + unsigned int word; /* word number in the buffer */ /* * Compute and read in starting bitmap block for starting block. */ - block = XFS_BITTOBLOCK(mp, start); - error = xfs_rtbuf_get(mp, tp, block, 0, &bp); - if (error) { + block = xfs_rtx_to_rbmblock(mp, start); + error = xfs_rtbitmap_read_buf(args, block); + if (error) return error; - } - bufp = bp->b_addr; + /* * Get the first word's index & point to it. */ - word = XFS_BITTOWORD(mp, start); - b = &bufp[word]; + word = xfs_rtx_to_rbmword(mp, start); bit = (int)(start & (XFS_NBWORD - 1)); - len = start - limit + 1; + len = start + 1; /* * Compute match value, based on the bit at start: if 1 (free) * then all-ones, else all-zeroes. */ - want = (*b & ((xfs_rtword_t)1 << bit)) ? -1 : 0; + incore = xfs_rtbitmap_getword(args, word); + want = (incore & ((xfs_rtword_t)1 << bit)) ? -1 : 0; /* * If the starting position is not word-aligned, deal with the * partial word. @@ -142,20 +309,19 @@ xfs_rtfind_back( * Calculate first (leftmost) bit number to look at, * and mask for all the relevant bits in this word. */ - firstbit = XFS_RTMAX((xfs_srtblock_t)(bit - len + 1), 0); + firstbit = max_t(xfs_srtblock_t, bit - len + 1, 0); mask = (((xfs_rtword_t)1 << (bit - firstbit + 1)) - 1) << firstbit; /* * Calculate the difference between the value there * and what we're looking for. */ - if ((wdiff = (*b ^ want) & mask)) { + if ((wdiff = (incore ^ want) & mask)) { /* * Different. Mark where we are and return. */ - xfs_trans_brelse(tp, bp); - i = bit - XFS_RTHIBIT(wdiff); - *rtblock = start - i + 1; + i = bit - xfs_highbit32(wdiff); + *rtx = start - i + 1; return 0; } i = bit - firstbit + 1; @@ -167,19 +333,11 @@ xfs_rtfind_back( /* * If done with this block, get the previous one. */ - xfs_trans_brelse(tp, bp); - error = xfs_rtbuf_get(mp, tp, --block, 0, &bp); - if (error) { + error = xfs_rtbitmap_read_buf(args, --block); + if (error) return error; - } - bufp = bp->b_addr; - word = XFS_BLOCKWMASK(mp); - b = &bufp[word]; - } else { - /* - * Go on to the previous word in the buffer. - */ - b--; + + word = mp->m_blockwsize - 1; } } else { /* @@ -195,13 +353,13 @@ xfs_rtfind_back( /* * Compute difference between actual and desired value. */ - if ((wdiff = *b ^ want)) { + incore = xfs_rtbitmap_getword(args, word); + if ((wdiff = incore ^ want)) { /* * Different, mark where we are and return. */ - xfs_trans_brelse(tp, bp); - i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff); - *rtblock = start - i + 1; + i += XFS_NBWORD - 1 - xfs_highbit32(wdiff); + *rtx = start - i + 1; return 0; } i += XFS_NBWORD; @@ -213,19 +371,11 @@ xfs_rtfind_back( /* * If done with this block, get the previous one. */ - xfs_trans_brelse(tp, bp); - error = xfs_rtbuf_get(mp, tp, --block, 0, &bp); - if (error) { + error = xfs_rtbitmap_read_buf(args, --block); + if (error) return error; - } - bufp = bp->b_addr; - word = XFS_BLOCKWMASK(mp); - b = &bufp[word]; - } else { - /* - * Go on to the previous word in the buffer. - */ - b--; + + word = mp->m_blockwsize - 1; } } /* @@ -242,13 +392,13 @@ xfs_rtfind_back( /* * Compute difference between actual and desired value. */ - if ((wdiff = (*b ^ want) & mask)) { + incore = xfs_rtbitmap_getword(args, word); + if ((wdiff = (incore ^ want) & mask)) { /* * Different, mark where we are and return. */ - xfs_trans_brelse(tp, bp); - i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff); - *rtblock = start - i + 1; + i += XFS_NBWORD - 1 - xfs_highbit32(wdiff); + *rtx = start - i + 1; return 0; } else i = len; @@ -256,8 +406,7 @@ xfs_rtfind_back( /* * No match, return that we scanned the whole area. */ - xfs_trans_brelse(tp, bp); - *rtblock = start - i + 1; + *rtx = start - i + 1; return 0; } @@ -267,47 +416,46 @@ xfs_rtfind_back( */ int xfs_rtfind_forw( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_rtblock_t start, /* starting block to look at */ - xfs_rtblock_t limit, /* last block to look at */ - xfs_rtblock_t *rtblock) /* out: start block found */ + struct xfs_rtalloc_args *args, + xfs_rtxnum_t start, /* starting rtext to look at */ + xfs_rtxnum_t limit, /* last rtext to look at */ + xfs_rtxnum_t *rtx) /* out: start rtext found */ { - xfs_rtword_t *b; /* current word in buffer */ - int bit; /* bit number in the word */ - xfs_rtblock_t block; /* bitmap block number */ - struct xfs_buf *bp; /* buf for the block */ - xfs_rtword_t *bufp; /* starting word in buffer */ - int error; /* error value */ - xfs_rtblock_t i; /* current bit number rel. to start */ - xfs_rtblock_t lastbit; /* last useful bit in the word */ - xfs_rtblock_t len; /* length of inspected area */ - xfs_rtword_t mask; /* mask of relevant bits for value */ - xfs_rtword_t want; /* mask for "good" values */ - xfs_rtword_t wdiff; /* difference from wanted value */ - int word; /* word number in the buffer */ + struct xfs_mount *mp = args->mp; + int bit; /* bit number in the word */ + xfs_fileoff_t block; /* bitmap block number */ + int error; + xfs_rtxnum_t i; /* current bit number rel. to start */ + xfs_rtxnum_t lastbit;/* last useful bit in the word */ + xfs_rtxnum_t len; /* length of inspected area */ + xfs_rtword_t mask; /* mask of relevant bits for value */ + xfs_rtword_t want; /* mask for "good" values */ + xfs_rtword_t wdiff; /* difference from wanted value */ + xfs_rtword_t incore; + unsigned int word; /* word number in the buffer */ + + ASSERT(start <= limit); /* * Compute and read in starting bitmap block for starting block. */ - block = XFS_BITTOBLOCK(mp, start); - error = xfs_rtbuf_get(mp, tp, block, 0, &bp); - if (error) { + block = xfs_rtx_to_rbmblock(mp, start); + error = xfs_rtbitmap_read_buf(args, block); + if (error) return error; - } - bufp = bp->b_addr; + /* * Get the first word's index & point to it. */ - word = XFS_BITTOWORD(mp, start); - b = &bufp[word]; + word = xfs_rtx_to_rbmword(mp, start); bit = (int)(start & (XFS_NBWORD - 1)); len = limit - start + 1; /* * Compute match value, based on the bit at start: if 1 (free) * then all-ones, else all-zeroes. */ - want = (*b & ((xfs_rtword_t)1 << bit)) ? -1 : 0; + incore = xfs_rtbitmap_getword(args, word); + want = (incore & ((xfs_rtword_t)1 << bit)) ? -1 : 0; /* * If the starting position is not word-aligned, deal with the * partial word. @@ -317,19 +465,18 @@ xfs_rtfind_forw( * Calculate last (rightmost) bit number to look at, * and mask for all the relevant bits in this word. */ - lastbit = XFS_RTMIN(bit + len, XFS_NBWORD); + lastbit = min(bit + len, XFS_NBWORD); mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit; /* * Calculate the difference between the value there * and what we're looking for. */ - if ((wdiff = (*b ^ want) & mask)) { + if ((wdiff = (incore ^ want) & mask)) { /* * Different. Mark where we are and return. */ - xfs_trans_brelse(tp, bp); - i = XFS_RTLOBIT(wdiff) - bit; - *rtblock = start + i - 1; + i = xfs_lowbit32(wdiff) - bit; + *rtx = start + i - 1; return 0; } i = lastbit - bit; @@ -337,22 +484,15 @@ xfs_rtfind_forw( * Go on to next block if that's where the next word is * and we need the next word. */ - if (++word == XFS_BLOCKWSIZE(mp) && i < len) { + if (++word == mp->m_blockwsize && i < len) { /* * If done with this block, get the previous one. */ - xfs_trans_brelse(tp, bp); - error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp); - if (error) { + error = xfs_rtbitmap_read_buf(args, ++block); + if (error) return error; - } - b = bufp = bp->b_addr; + word = 0; - } else { - /* - * Go on to the previous word in the buffer. - */ - b++; } } else { /* @@ -368,13 +508,13 @@ xfs_rtfind_forw( /* * Compute difference between actual and desired value. */ - if ((wdiff = *b ^ want)) { + incore = xfs_rtbitmap_getword(args, word); + if ((wdiff = incore ^ want)) { /* * Different, mark where we are and return. */ - xfs_trans_brelse(tp, bp); - i += XFS_RTLOBIT(wdiff); - *rtblock = start + i - 1; + i += xfs_lowbit32(wdiff); + *rtx = start + i - 1; return 0; } i += XFS_NBWORD; @@ -382,22 +522,15 @@ xfs_rtfind_forw( * Go on to next block if that's where the next word is * and we need the next word. */ - if (++word == XFS_BLOCKWSIZE(mp) && i < len) { + if (++word == mp->m_blockwsize && i < len) { /* * If done with this block, get the next one. */ - xfs_trans_brelse(tp, bp); - error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp); - if (error) { + error = xfs_rtbitmap_read_buf(args, ++block); + if (error) return error; - } - b = bufp = bp->b_addr; + word = 0; - } else { - /* - * Go on to the next word in the buffer. - */ - b++; } } /* @@ -412,13 +545,13 @@ xfs_rtfind_forw( /* * Compute difference between actual and desired value. */ - if ((wdiff = (*b ^ want) & mask)) { + incore = xfs_rtbitmap_getword(args, word); + if ((wdiff = (incore ^ want) & mask)) { /* * Different, mark where we are and return. */ - xfs_trans_brelse(tp, bp); - i += XFS_RTLOBIT(wdiff); - *rtblock = start + i - 1; + i += xfs_lowbit32(wdiff); + *rtx = start + i - 1; return 0; } else i = len; @@ -426,102 +559,96 @@ xfs_rtfind_forw( /* * No match, return that we scanned the whole area. */ - xfs_trans_brelse(tp, bp); - *rtblock = start + i - 1; + *rtx = start + i - 1; return 0; } +/* Log rtsummary counter at @infoword. */ +static inline void +xfs_trans_log_rtsummary( + struct xfs_rtalloc_args *args, + unsigned int infoword) +{ + struct xfs_buf *bp = args->sumbp; + size_t first, last; + + first = (void *)xfs_rsumblock_infoptr(args, infoword) - bp->b_addr; + last = first + sizeof(xfs_suminfo_t) - 1; + + xfs_trans_log_buf(args->tp, bp, first, last); +} + /* - * Read and/or modify the summary information for a given extent size, - * bitmap block combination. - * Keeps track of a current summary block, so we don't keep reading - * it from the buffer cache. - * - * Summary information is returned in *sum if specified. - * If no delta is specified, returns summary only. + * Modify the summary information for a given extent size, bitmap block + * combination. */ int -xfs_rtmodify_summary_int( - xfs_mount_t *mp, /* file system mount structure */ - xfs_trans_t *tp, /* transaction pointer */ - int log, /* log2 of extent size */ - xfs_rtblock_t bbno, /* bitmap block number */ - int delta, /* change to make to summary info */ - struct xfs_buf **rbpp, /* in/out: summary block buffer */ - xfs_fsblock_t *rsb, /* in/out: summary block number */ - xfs_suminfo_t *sum) /* out: summary info for this block */ +xfs_rtmodify_summary( + struct xfs_rtalloc_args *args, + int log, /* log2 of extent size */ + xfs_fileoff_t bbno, /* bitmap block number */ + int delta) /* in/out: summary block number */ { - struct xfs_buf *bp; /* buffer for the summary block */ - int error; /* error value */ - xfs_fsblock_t sb; /* summary fsblock */ - int so; /* index into the summary file */ - xfs_suminfo_t *sp; /* pointer to returned data */ + struct xfs_mount *mp = args->mp; + xfs_rtsumoff_t so = xfs_rtsumoffs(mp, log, bbno); + uint8_t *rsum_cache = args->rtg->rtg_rsum_cache; + unsigned int infoword; + xfs_suminfo_t val; + int error; - /* - * Compute entry number in the summary file. - */ - so = XFS_SUMOFFS(mp, log, bbno); - /* - * Compute the block number in the summary file. - */ - sb = XFS_SUMOFFSTOBLOCK(mp, so); - /* - * If we have an old buffer, and the block number matches, use that. - */ - if (*rbpp && *rsb == sb) - bp = *rbpp; - /* - * Otherwise we have to get the buffer. - */ - else { - /* - * If there was an old one, get rid of it first. - */ - if (*rbpp) - xfs_trans_brelse(tp, *rbpp); - error = xfs_rtbuf_get(mp, tp, sb, 1, &bp); - if (error) { - return error; - } - /* - * Remember this buffer and block for the next call. - */ - *rbpp = bp; - *rsb = sb; - } - /* - * Point to the summary information, modify/log it, and/or copy it out. - */ - sp = XFS_SUMPTR(mp, bp, so); - if (delta) { - uint first = (uint)((char *)sp - (char *)bp->b_addr); - - *sp += delta; - if (mp->m_rsum_cache) { - if (*sp == 0 && log == mp->m_rsum_cache[bbno]) - mp->m_rsum_cache[bbno]++; - if (*sp != 0 && log < mp->m_rsum_cache[bbno]) - mp->m_rsum_cache[bbno] = log; - } - xfs_trans_log_buf(tp, bp, first, first + sizeof(*sp) - 1); + error = xfs_rtsummary_read_buf(args, xfs_rtsumoffs_to_block(mp, so)); + if (error) + return error; + + infoword = xfs_rtsumoffs_to_infoword(mp, so); + val = xfs_suminfo_add(args, infoword, delta); + + if (rsum_cache) { + if (val == 0 && log + 1 == rsum_cache[bbno]) + rsum_cache[bbno] = log; + if (val != 0 && log >= rsum_cache[bbno]) + rsum_cache[bbno] = log + 1; } - if (sum) - *sum = *sp; + + xfs_trans_log_rtsummary(args, infoword); return 0; } +/* + * Read and return the summary information for a given extent size, bitmap block + * combination. + */ int -xfs_rtmodify_summary( - xfs_mount_t *mp, /* file system mount structure */ - xfs_trans_t *tp, /* transaction pointer */ - int log, /* log2 of extent size */ - xfs_rtblock_t bbno, /* bitmap block number */ - int delta, /* change to make to summary info */ - struct xfs_buf **rbpp, /* in/out: summary block buffer */ - xfs_fsblock_t *rsb) /* in/out: summary block number */ +xfs_rtget_summary( + struct xfs_rtalloc_args *args, + int log, /* log2 of extent size */ + xfs_fileoff_t bbno, /* bitmap block number */ + xfs_suminfo_t *sum) /* out: summary info for this block */ { - return xfs_rtmodify_summary_int(mp, tp, log, bbno, - delta, rbpp, rsb, NULL); + struct xfs_mount *mp = args->mp; + xfs_rtsumoff_t so = xfs_rtsumoffs(mp, log, bbno); + int error; + + error = xfs_rtsummary_read_buf(args, xfs_rtsumoffs_to_block(mp, so)); + if (!error) + *sum = xfs_suminfo_get(args, xfs_rtsumoffs_to_infoword(mp, so)); + return error; +} + +/* Log rtbitmap block from the word @from to the byte before @next. */ +static inline void +xfs_trans_log_rtbitmap( + struct xfs_rtalloc_args *args, + unsigned int from, + unsigned int next) +{ + struct xfs_buf *bp = args->rbmbp; + size_t first, last; + + first = (void *)xfs_rbmblock_wordptr(args, from) - bp->b_addr; + last = ((void *)xfs_rbmblock_wordptr(args, next) - 1) - bp->b_addr; + + xfs_trans_log_buf(args->tp, bp, first, last); } /* @@ -530,41 +657,37 @@ xfs_rtmodify_summary( */ int xfs_rtmodify_range( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_rtblock_t start, /* starting block to modify */ - xfs_extlen_t len, /* length of extent to modify */ - int val) /* 1 for free, 0 for allocated */ + struct xfs_rtalloc_args *args, + xfs_rtxnum_t start, /* starting rtext to modify */ + xfs_rtxlen_t len, /* length of extent to modify */ + int val) /* 1 for free, 0 for allocated */ { - xfs_rtword_t *b; /* current word in buffer */ - int bit; /* bit number in the word */ - xfs_rtblock_t block; /* bitmap block number */ - struct xfs_buf *bp; /* buf for the block */ - xfs_rtword_t *bufp; /* starting word in buffer */ - int error; /* error value */ - xfs_rtword_t *first; /* first used word in the buffer */ - int i; /* current bit number rel. to start */ - int lastbit; /* last useful bit in word */ - xfs_rtword_t mask; /* mask o frelevant bits for value */ - int word; /* word number in the buffer */ + struct xfs_mount *mp = args->mp; + int bit; /* bit number in the word */ + xfs_fileoff_t block; /* bitmap block number */ + int error; + int i; /* current bit number rel. to start */ + int lastbit; /* last useful bit in word */ + xfs_rtword_t mask; /* mask of relevant bits for value */ + xfs_rtword_t incore; + unsigned int firstword; /* first word used in the buffer */ + unsigned int word; /* word number in the buffer */ /* * Compute starting bitmap block number. */ - block = XFS_BITTOBLOCK(mp, start); + block = xfs_rtx_to_rbmblock(mp, start); /* * Read the bitmap block, and point to its data. */ - error = xfs_rtbuf_get(mp, tp, block, 0, &bp); - if (error) { + error = xfs_rtbitmap_read_buf(args, block); + if (error) return error; - } - bufp = bp->b_addr; + /* * Compute the starting word's address, and starting bit. */ - word = XFS_BITTOWORD(mp, start); - first = b = &bufp[word]; + firstword = word = xfs_rtx_to_rbmword(mp, start); bit = (int)(start & (XFS_NBWORD - 1)); /* * 0 (allocated) => all zeroes; 1 (free) => all ones. @@ -578,39 +701,33 @@ xfs_rtmodify_range( /* * Compute first bit not changed and mask of relevant bits. */ - lastbit = XFS_RTMIN(bit + len, XFS_NBWORD); + lastbit = min(bit + len, XFS_NBWORD); mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit; /* * Set/clear the active bits. */ + incore = xfs_rtbitmap_getword(args, word); if (val) - *b |= mask; + incore |= mask; else - *b &= ~mask; + incore &= ~mask; + xfs_rtbitmap_setword(args, word, incore); i = lastbit - bit; /* * Go on to the next block if that's where the next word is * and we need the next word. */ - if (++word == XFS_BLOCKWSIZE(mp) && i < len) { + if (++word == mp->m_blockwsize && i < len) { /* * Log the changed part of this block. * Get the next one. */ - xfs_trans_log_buf(tp, bp, - (uint)((char *)first - (char *)bufp), - (uint)((char *)b - (char *)bufp)); - error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp); - if (error) { + xfs_trans_log_rtbitmap(args, firstword, word); + error = xfs_rtbitmap_read_buf(args, ++block); + if (error) return error; - } - first = b = bufp = bp->b_addr; - word = 0; - } else { - /* - * Go on to the next word in the buffer - */ - b++; + + firstword = word = 0; } } else { /* @@ -626,31 +743,23 @@ xfs_rtmodify_range( /* * Set the word value correctly. */ - *b = val; + xfs_rtbitmap_setword(args, word, val); i += XFS_NBWORD; /* * Go on to the next block if that's where the next word is * and we need the next word. */ - if (++word == XFS_BLOCKWSIZE(mp) && i < len) { + if (++word == mp->m_blockwsize && i < len) { /* * Log the changed part of this block. * Get the next one. */ - xfs_trans_log_buf(tp, bp, - (uint)((char *)first - (char *)bufp), - (uint)((char *)b - (char *)bufp)); - error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp); - if (error) { + xfs_trans_log_rtbitmap(args, firstword, word); + error = xfs_rtbitmap_read_buf(args, ++block); + if (error) return error; - } - first = b = bufp = bp->b_addr; - word = 0; - } else { - /* - * Go on to the next word in the buffer - */ - b++; + + firstword = word = 0; } } /* @@ -665,18 +774,19 @@ xfs_rtmodify_range( /* * Set/clear the active bits. */ + incore = xfs_rtbitmap_getword(args, word); if (val) - *b |= mask; + incore |= mask; else - *b &= ~mask; - b++; + incore &= ~mask; + xfs_rtbitmap_setword(args, word, incore); + word++; } /* * Log any remaining changed bytes. */ - if (b > first) - xfs_trans_log_buf(tp, bp, (uint)((char *)first - (char *)bufp), - (uint)((char *)b - (char *)bufp - 1)); + if (word > firstword) + xfs_trans_log_rtbitmap(args, firstword, word); return 0; } @@ -686,23 +796,21 @@ xfs_rtmodify_range( */ int xfs_rtfree_range( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_rtblock_t start, /* starting block to free */ - xfs_extlen_t len, /* length to free */ - struct xfs_buf **rbpp, /* in/out: summary block buffer */ - xfs_fsblock_t *rsb) /* in/out: summary block number */ + struct xfs_rtalloc_args *args, + xfs_rtxnum_t start, /* starting rtext to free */ + xfs_rtxlen_t len) /* in/out: summary block number */ { - xfs_rtblock_t end; /* end of the freed extent */ - int error; /* error value */ - xfs_rtblock_t postblock; /* first block freed > end */ - xfs_rtblock_t preblock; /* first block freed < start */ + struct xfs_mount *mp = args->mp; + xfs_rtxnum_t end; /* end of the freed extent */ + int error; /* error value */ + xfs_rtxnum_t postblock; /* first rtext freed > end */ + xfs_rtxnum_t preblock; /* first rtext freed < start */ end = start + len - 1; /* * Modify the bitmap to mark this extent freed. */ - error = xfs_rtmodify_range(mp, tp, start, len, 1); + error = xfs_rtmodify_range(args, start, len, 1); if (error) { return error; } @@ -711,15 +819,15 @@ xfs_rtfree_range( * We need to find the beginning and end of the extent so we can * properly update the summary. */ - error = xfs_rtfind_back(mp, tp, start, 0, &preblock); + error = xfs_rtfind_back(args, start, &preblock); if (error) { return error; } /* * Find the next allocated block (end of allocated extent). */ - error = xfs_rtfind_forw(mp, tp, end, mp->m_sb.sb_rextents - 1, - &postblock); + error = xfs_rtfind_forw(args, end, args->rtg->rtg_extents - 1, + &postblock); if (error) return error; /* @@ -727,9 +835,9 @@ xfs_rtfree_range( * old extent, add summary data for them to be allocated. */ if (preblock < start) { - error = xfs_rtmodify_summary(mp, tp, - XFS_RTBLOCKLOG(start - preblock), - XFS_BITTOBLOCK(mp, preblock), -1, rbpp, rsb); + error = xfs_rtmodify_summary(args, + xfs_highbit64(start - preblock), + xfs_rtx_to_rbmblock(mp, preblock), -1); if (error) { return error; } @@ -739,9 +847,9 @@ xfs_rtfree_range( * old extent, add summary data for them to be allocated. */ if (postblock > end) { - error = xfs_rtmodify_summary(mp, tp, - XFS_RTBLOCKLOG(postblock - end), - XFS_BITTOBLOCK(mp, end + 1), -1, rbpp, rsb); + error = xfs_rtmodify_summary(args, + xfs_highbit64(postblock - end), + xfs_rtx_to_rbmblock(mp, end + 1), -1); if (error) { return error; } @@ -750,10 +858,9 @@ xfs_rtfree_range( * Increment the summary information corresponding to the entire * (new) free extent. */ - error = xfs_rtmodify_summary(mp, tp, - XFS_RTBLOCKLOG(postblock + 1 - preblock), - XFS_BITTOBLOCK(mp, preblock), 1, rbpp, rsb); - return error; + return xfs_rtmodify_summary(args, + xfs_highbit64(postblock + 1 - preblock), + xfs_rtx_to_rbmblock(mp, preblock), 1); } /* @@ -762,43 +869,39 @@ xfs_rtfree_range( */ int xfs_rtcheck_range( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_rtblock_t start, /* starting block number of extent */ - xfs_extlen_t len, /* length of extent */ - int val, /* 1 for free, 0 for allocated */ - xfs_rtblock_t *new, /* out: first block not matching */ - int *stat) /* out: 1 for matches, 0 for not */ + struct xfs_rtalloc_args *args, + xfs_rtxnum_t start, /* starting rtext number of extent */ + xfs_rtxlen_t len, /* length of extent */ + int val, /* 1 for free, 0 for allocated */ + xfs_rtxnum_t *new, /* out: first rtext not matching */ + int *stat) /* out: 1 for matches, 0 for not */ { - xfs_rtword_t *b; /* current word in buffer */ - int bit; /* bit number in the word */ - xfs_rtblock_t block; /* bitmap block number */ - struct xfs_buf *bp; /* buf for the block */ - xfs_rtword_t *bufp; /* starting word in buffer */ - int error; /* error value */ - xfs_rtblock_t i; /* current bit number rel. to start */ - xfs_rtblock_t lastbit; /* last useful bit in word */ - xfs_rtword_t mask; /* mask of relevant bits for value */ - xfs_rtword_t wdiff; /* difference from wanted value */ - int word; /* word number in the buffer */ + struct xfs_mount *mp = args->mp; + int bit; /* bit number in the word */ + xfs_fileoff_t block; /* bitmap block number */ + int error; + xfs_rtxnum_t i; /* current bit number rel. to start */ + xfs_rtxnum_t lastbit; /* last useful bit in word */ + xfs_rtword_t mask; /* mask of relevant bits for value */ + xfs_rtword_t wdiff; /* difference from wanted value */ + xfs_rtword_t incore; + unsigned int word; /* word number in the buffer */ /* * Compute starting bitmap block number */ - block = XFS_BITTOBLOCK(mp, start); + block = xfs_rtx_to_rbmblock(mp, start); /* * Read the bitmap block. */ - error = xfs_rtbuf_get(mp, tp, block, 0, &bp); - if (error) { + error = xfs_rtbitmap_read_buf(args, block); + if (error) return error; - } - bufp = bp->b_addr; + /* * Compute the starting word's address, and starting bit. */ - word = XFS_BITTOWORD(mp, start); - b = &bufp[word]; + word = xfs_rtx_to_rbmword(mp, start); bit = (int)(start & (XFS_NBWORD - 1)); /* * 0 (allocated) => all zero's; 1 (free) => all one's. @@ -812,7 +915,7 @@ xfs_rtcheck_range( /* * Compute first bit not examined. */ - lastbit = XFS_RTMIN(bit + len, XFS_NBWORD); + lastbit = min(bit + len, XFS_NBWORD); /* * Mask of relevant bits. */ @@ -820,12 +923,12 @@ xfs_rtcheck_range( /* * Compute difference between actual and desired value. */ - if ((wdiff = (*b ^ val) & mask)) { + incore = xfs_rtbitmap_getword(args, word); + if ((wdiff = (incore ^ val) & mask)) { /* * Different, compute first wrong bit and return. */ - xfs_trans_brelse(tp, bp); - i = XFS_RTLOBIT(wdiff) - bit; + i = xfs_lowbit32(wdiff) - bit; *new = start + i; *stat = 0; return 0; @@ -835,22 +938,15 @@ xfs_rtcheck_range( * Go on to next block if that's where the next word is * and we need the next word. */ - if (++word == XFS_BLOCKWSIZE(mp) && i < len) { + if (++word == mp->m_blockwsize && i < len) { /* * If done with this block, get the next one. */ - xfs_trans_brelse(tp, bp); - error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp); - if (error) { + error = xfs_rtbitmap_read_buf(args, ++block); + if (error) return error; - } - b = bufp = bp->b_addr; + word = 0; - } else { - /* - * Go on to the next word in the buffer. - */ - b++; } } else { /* @@ -866,12 +962,12 @@ xfs_rtcheck_range( /* * Compute difference between actual and desired value. */ - if ((wdiff = *b ^ val)) { + incore = xfs_rtbitmap_getword(args, word); + if ((wdiff = incore ^ val)) { /* * Different, compute first wrong bit and return. */ - xfs_trans_brelse(tp, bp); - i += XFS_RTLOBIT(wdiff); + i += xfs_lowbit32(wdiff); *new = start + i; *stat = 0; return 0; @@ -881,22 +977,15 @@ xfs_rtcheck_range( * Go on to next block if that's where the next word is * and we need the next word. */ - if (++word == XFS_BLOCKWSIZE(mp) && i < len) { + if (++word == mp->m_blockwsize && i < len) { /* * If done with this block, get the next one. */ - xfs_trans_brelse(tp, bp); - error = xfs_rtbuf_get(mp, tp, ++block, 0, &bp); - if (error) { + error = xfs_rtbitmap_read_buf(args, ++block); + if (error) return error; - } - b = bufp = bp->b_addr; + word = 0; - } else { - /* - * Go on to the next word in the buffer. - */ - b++; } } /* @@ -911,12 +1000,12 @@ xfs_rtcheck_range( /* * Compute difference between actual and desired value. */ - if ((wdiff = (*b ^ val) & mask)) { + incore = xfs_rtbitmap_getword(args, word); + if ((wdiff = (incore ^ val) & mask)) { /* * Different, compute first wrong bit and return. */ - xfs_trans_brelse(tp, bp); - i += XFS_RTLOBIT(wdiff); + i += xfs_lowbit32(wdiff); *new = start + i; *stat = 0; return 0; @@ -926,7 +1015,6 @@ xfs_rtcheck_range( /* * Successful, return. */ - xfs_trans_brelse(tp, bp); *new = start + i; *stat = 1; return 0; @@ -936,163 +1024,481 @@ xfs_rtcheck_range( /* * Check that the given extent (block range) is allocated already. */ -STATIC int /* error */ +STATIC int xfs_rtcheck_alloc_range( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_rtblock_t bno, /* starting block number of extent */ - xfs_extlen_t len) /* length of extent */ + struct xfs_rtalloc_args *args, + xfs_rtxnum_t start, /* starting rtext number of extent */ + xfs_rtxlen_t len) /* length of extent */ { - xfs_rtblock_t new; /* dummy for xfs_rtcheck_range */ - int stat; - int error; + xfs_rtxnum_t new; /* dummy for xfs_rtcheck_range */ + int stat; + int error; - error = xfs_rtcheck_range(mp, tp, bno, len, 0, &new, &stat); + error = xfs_rtcheck_range(args, start, len, 0, &new, &stat); if (error) return error; ASSERT(stat); return 0; } #else -#define xfs_rtcheck_alloc_range(m,t,b,l) (0) +#define xfs_rtcheck_alloc_range(a,b,l) (0) #endif /* * Free an extent in the realtime subvolume. Length is expressed in * realtime extents, as is the block number. */ -int /* error */ +int xfs_rtfree_extent( - xfs_trans_t *tp, /* transaction pointer */ - xfs_rtblock_t bno, /* starting block number to free */ - xfs_extlen_t len) /* length of extent freed */ + struct xfs_trans *tp, /* transaction pointer */ + struct xfs_rtgroup *rtg, + xfs_rtxnum_t start, /* starting rtext number to free */ + xfs_rtxlen_t len) /* length of extent freed */ { - int error; /* error value */ - xfs_mount_t *mp; /* file system mount structure */ - xfs_fsblock_t sb; /* summary file block number */ - struct xfs_buf *sumbp = NULL; /* summary file block buffer */ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_inode *rbmip = rtg_bitmap(rtg); + struct xfs_rtalloc_args args = { + .mp = mp, + .tp = tp, + .rtg = rtg, + }; + int error; + struct timespec64 atime; - mp = tp->t_mountp; + ASSERT(rbmip->i_itemp != NULL); + xfs_assert_ilocked(rbmip, XFS_ILOCK_EXCL); - ASSERT(mp->m_rbmip->i_itemp != NULL); - ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL)); + if (XFS_TEST_ERROR(mp, XFS_ERRTAG_FREE_EXTENT)) + return -EIO; - error = xfs_rtcheck_alloc_range(mp, tp, bno, len); + error = xfs_rtcheck_alloc_range(&args, start, len); if (error) return error; /* * Free the range of realtime blocks. */ - error = xfs_rtfree_range(mp, tp, bno, len, &sumbp, &sb); - if (error) { - return error; - } + error = xfs_rtfree_range(&args, start, len); + if (error) + goto out; + /* * Mark more blocks free in the superblock. */ xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, (long)len); + /* * If we've now freed all the blocks, reset the file sequence - * number to 0. + * number to 0 for pre-RTG file systems. */ - if (tp->t_frextents_delta + mp->m_sb.sb_frextents == + if (!xfs_has_rtgroups(mp) && + tp->t_frextents_delta + mp->m_sb.sb_frextents == mp->m_sb.sb_rextents) { - if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) - mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM; - *(uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0; - xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE); + if (!(rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) + rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM; + + atime = inode_get_atime(VFS_I(rbmip)); + atime.tv_sec = 0; + inode_set_atime_to_ts(VFS_I(rbmip), atime); + xfs_trans_log_inode(tp, rbmip, XFS_ILOG_CORE); } + error = 0; +out: + xfs_rtbuf_cache_relse(&args); + return error; +} + +/* + * Free some blocks in the realtime subvolume. rtbno and rtlen are in units of + * rt blocks, not rt extents; must be aligned to the rt extent size; and rtlen + * cannot exceed XFS_MAX_BMBT_EXTLEN. + */ +int +xfs_rtfree_blocks( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg, + xfs_fsblock_t rtbno, + xfs_filblks_t rtlen) +{ + struct xfs_mount *mp = tp->t_mountp; + xfs_extlen_t mod; + int error; + + ASSERT(!xfs_has_zoned(mp)); + ASSERT(rtlen <= XFS_MAX_BMBT_EXTLEN); + + mod = xfs_blen_to_rtxoff(mp, rtlen); + if (mod) { + ASSERT(mod == 0); + return -EIO; + } + + mod = xfs_rtb_to_rtxoff(mp, rtbno); + if (mod) { + ASSERT(mod == 0); + return -EIO; + } + + error = xfs_rtfree_extent(tp, rtg, xfs_rtb_to_rtx(mp, rtbno), + xfs_extlen_to_rtxlen(mp, rtlen)); + if (error) + return error; + + if (xfs_has_rtgroups(mp)) + xfs_extent_busy_insert(tp, rtg_group(rtg), + xfs_rtb_to_rgbno(mp, rtbno), rtlen, 0); + return 0; } /* Find all the free records within a given range. */ int xfs_rtalloc_query_range( - struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_trans *tp, - const struct xfs_rtalloc_rec *low_rec, - const struct xfs_rtalloc_rec *high_rec, + xfs_rtxnum_t start, + xfs_rtxnum_t end, xfs_rtalloc_query_range_fn fn, void *priv) { - struct xfs_rtalloc_rec rec; - xfs_rtblock_t rtstart; - xfs_rtblock_t rtend; - xfs_rtblock_t high_key; - int is_free; + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_rtalloc_args args = { + .rtg = rtg, + .mp = mp, + .tp = tp, + }; int error = 0; - if (low_rec->ar_startext > high_rec->ar_startext) + if (start > end) return -EINVAL; - if (low_rec->ar_startext >= mp->m_sb.sb_rextents || - low_rec->ar_startext == high_rec->ar_startext) + if (start == end || start >= rtg->rtg_extents) return 0; - high_key = min(high_rec->ar_startext, mp->m_sb.sb_rextents - 1); + end = min(end, rtg->rtg_extents - 1); + + if (xfs_has_zoned(mp)) + return -EINVAL; /* Iterate the bitmap, looking for discrepancies. */ - rtstart = low_rec->ar_startext; - while (rtstart <= high_key) { + while (start <= end) { + struct xfs_rtalloc_rec rec; + int is_free; + xfs_rtxnum_t rtend; + /* Is the first block free? */ - error = xfs_rtcheck_range(mp, tp, rtstart, 1, 1, &rtend, + error = xfs_rtcheck_range(&args, start, 1, 1, &rtend, &is_free); if (error) break; /* How long does the extent go for? */ - error = xfs_rtfind_forw(mp, tp, rtstart, high_key, &rtend); + error = xfs_rtfind_forw(&args, start, end, &rtend); if (error) break; if (is_free) { - rec.ar_startext = rtstart; - rec.ar_extcount = rtend - rtstart + 1; + rec.ar_startext = start; + rec.ar_extcount = rtend - start + 1; - error = fn(mp, tp, &rec, priv); + error = fn(rtg, tp, &rec, priv); if (error) break; } - rtstart = rtend + 1; + start = rtend + 1; } + xfs_rtbuf_cache_relse(&args); return error; } /* Find all the free records. */ int xfs_rtalloc_query_all( - struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_trans *tp, xfs_rtalloc_query_range_fn fn, void *priv) { - struct xfs_rtalloc_rec keys[2]; - - keys[0].ar_startext = 0; - keys[1].ar_startext = mp->m_sb.sb_rextents - 1; - keys[0].ar_extcount = keys[1].ar_extcount = 0; - - return xfs_rtalloc_query_range(mp, tp, &keys[0], &keys[1], fn, priv); + return xfs_rtalloc_query_range(rtg, tp, 0, rtg->rtg_extents - 1, fn, + priv); } /* Is the given extent all free? */ int xfs_rtalloc_extent_is_free( - struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_trans *tp, - xfs_rtblock_t start, - xfs_extlen_t len, + xfs_rtxnum_t start, + xfs_rtxlen_t len, bool *is_free) { - xfs_rtblock_t end; + struct xfs_rtalloc_args args = { + .mp = rtg_mount(rtg), + .rtg = rtg, + .tp = tp, + }; + xfs_rtxnum_t end; int matches; int error; - error = xfs_rtcheck_range(mp, tp, start, len, 1, &end, &matches); + error = xfs_rtcheck_range(&args, start, len, 1, &end, &matches); + xfs_rtbuf_cache_relse(&args); if (error) return error; *is_free = matches; return 0; } + +/* Compute the number of rt extents tracked by a single bitmap block. */ +xfs_rtxnum_t +xfs_rtbitmap_rtx_per_rbmblock( + struct xfs_mount *mp) +{ + unsigned int rbmblock_bytes = mp->m_sb.sb_blocksize; + + if (xfs_has_rtgroups(mp)) + rbmblock_bytes -= sizeof(struct xfs_rtbuf_blkinfo); + + return rbmblock_bytes * NBBY; +} + +/* + * Compute the number of rtbitmap blocks needed to track the given number of rt + * extents. + */ +xfs_filblks_t +xfs_rtbitmap_blockcount_len( + struct xfs_mount *mp, + xfs_rtbxlen_t rtextents) +{ + if (xfs_has_zoned(mp)) + return 0; + return howmany_64(rtextents, xfs_rtbitmap_rtx_per_rbmblock(mp)); +} + +/* How many rt extents does each rtbitmap file track? */ +static inline xfs_rtbxlen_t +xfs_rtbitmap_bitcount( + struct xfs_mount *mp) +{ + if (!mp->m_sb.sb_rextents) + return 0; + + /* rtgroup size can be nonzero even if rextents is zero */ + if (xfs_has_rtgroups(mp)) + return mp->m_sb.sb_rgextents; + + return mp->m_sb.sb_rextents; +} + +/* + * Compute the number of rtbitmap blocks used for a given file system. + */ +xfs_filblks_t +xfs_rtbitmap_blockcount( + struct xfs_mount *mp) +{ + return xfs_rtbitmap_blockcount_len(mp, xfs_rtbitmap_bitcount(mp)); +} + +/* + * Compute the geometry of the rtsummary file needed to track the given rt + * space. + */ +xfs_filblks_t +xfs_rtsummary_blockcount( + struct xfs_mount *mp, + unsigned int *rsumlevels) +{ + xfs_rtbxlen_t rextents = xfs_rtbitmap_bitcount(mp); + unsigned long long rsumwords; + + if (xfs_has_zoned(mp)) { + *rsumlevels = 0; + return 0; + } + + *rsumlevels = xfs_compute_rextslog(rextents) + 1; + rsumwords = xfs_rtbitmap_blockcount_len(mp, rextents) * (*rsumlevels); + return howmany_64(rsumwords, mp->m_blockwsize); +} + +static int +xfs_rtfile_alloc_blocks( + struct xfs_inode *ip, + xfs_fileoff_t offset_fsb, + xfs_filblks_t count_fsb, + struct xfs_bmbt_irec *map) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; + int nmap = 1; + int error; + + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtalloc, + XFS_GROWFSRT_SPACE_RES(mp, count_fsb), 0, 0, &tp); + if (error) + return error; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + + error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK, + XFS_IEXT_ADD_NOSPLIT_CNT); + if (error) + goto out_trans_cancel; + + error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, + XFS_BMAPI_METADATA, 0, map, &nmap); + if (error) + goto out_trans_cancel; + + return xfs_trans_commit(tp); + +out_trans_cancel: + xfs_trans_cancel(tp); + return error; +} + +/* Get a buffer for the block. */ +static int +xfs_rtfile_initialize_block( + struct xfs_rtgroup *rtg, + enum xfs_rtg_inodes type, + xfs_fsblock_t fsbno, + void *data) +{ + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_inode *ip = rtg->rtg_inodes[type]; + struct xfs_trans *tp; + struct xfs_buf *bp; + void *bufdata; + const size_t copylen = mp->m_blockwsize << XFS_WORDLOG; + enum xfs_blft buf_type; + int error; + + if (type == XFS_RTGI_BITMAP) + buf_type = XFS_BLFT_RTBITMAP_BUF; + else if (type == XFS_RTGI_SUMMARY) + buf_type = XFS_BLFT_RTSUMMARY_BUF; + else + return -EINVAL; + + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtzero, 0, 0, 0, &tp); + if (error) + return error; + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, + XFS_FSB_TO_DADDR(mp, fsbno), mp->m_bsize, 0, &bp); + if (error) { + xfs_trans_cancel(tp); + return error; + } + bufdata = bp->b_addr; + + xfs_trans_buf_set_type(tp, bp, buf_type); + bp->b_ops = xfs_rtblock_ops(mp, type); + + if (xfs_has_rtgroups(mp)) { + struct xfs_rtbuf_blkinfo *hdr = bp->b_addr; + + if (type == XFS_RTGI_BITMAP) + hdr->rt_magic = cpu_to_be32(XFS_RTBITMAP_MAGIC); + else + hdr->rt_magic = cpu_to_be32(XFS_RTSUMMARY_MAGIC); + hdr->rt_owner = cpu_to_be64(ip->i_ino); + hdr->rt_blkno = cpu_to_be64(XFS_FSB_TO_DADDR(mp, fsbno)); + hdr->rt_lsn = 0; + uuid_copy(&hdr->rt_uuid, &mp->m_sb.sb_meta_uuid); + + bufdata += sizeof(*hdr); + } + + if (data) + memcpy(bufdata, data, copylen); + else + memset(bufdata, 0, copylen); + xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1); + return xfs_trans_commit(tp); +} + +/* + * Allocate space to the bitmap or summary file, and zero it, for growfs. + * @data must be a contiguous buffer large enough to fill all blocks in the + * file; or NULL to initialize the contents to zeroes. + */ +int +xfs_rtfile_initialize_blocks( + struct xfs_rtgroup *rtg, + enum xfs_rtg_inodes type, + xfs_fileoff_t offset_fsb, /* offset to start from */ + xfs_fileoff_t end_fsb, /* offset to allocate to */ + void *data) /* data to fill the blocks */ +{ + struct xfs_mount *mp = rtg_mount(rtg); + const size_t copylen = mp->m_blockwsize << XFS_WORDLOG; + + while (offset_fsb < end_fsb) { + struct xfs_bmbt_irec map; + xfs_filblks_t i; + int error; + + error = xfs_rtfile_alloc_blocks(rtg->rtg_inodes[type], + offset_fsb, end_fsb - offset_fsb, &map); + if (error) + return error; + + /* + * Now we need to clear the allocated blocks. + * + * Do this one block per transaction, to keep it simple. + */ + for (i = 0; i < map.br_blockcount; i++) { + error = xfs_rtfile_initialize_block(rtg, type, + map.br_startblock + i, data); + if (error) + return error; + if (data) + data += copylen; + } + + offset_fsb = map.br_startoff + map.br_blockcount; + } + + return 0; +} + +int +xfs_rtbitmap_create( + struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + ip->i_disk_size = mp->m_sb.sb_rbmblocks * mp->m_sb.sb_blocksize; + if (init && !xfs_has_rtgroups(mp)) { + ip->i_diflags |= XFS_DIFLAG_NEWRTBM; + inode_set_atime(VFS_I(ip), 0, 0); + } + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + return 0; +} + +int +xfs_rtsummary_create( + struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + ip->i_disk_size = mp->m_rsumblocks * mp->m_sb.sb_blocksize; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h new file mode 100644 index 000000000000..22e5d9cd95f4 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtbitmap.h @@ -0,0 +1,453 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. + * All Rights Reserved. + */ +#ifndef __XFS_RTBITMAP_H__ +#define __XFS_RTBITMAP_H__ + +#include "xfs_rtgroup.h" + +struct xfs_rtalloc_args { + struct xfs_rtgroup *rtg; + struct xfs_mount *mp; + struct xfs_trans *tp; + + struct xfs_buf *rbmbp; /* bitmap block buffer */ + struct xfs_buf *sumbp; /* summary block buffer */ + + xfs_fileoff_t rbmoff; /* bitmap block number */ + xfs_fileoff_t sumoff; /* summary block number */ +}; + +static inline xfs_rtblock_t +xfs_rtx_to_rtb( + struct xfs_rtgroup *rtg, + xfs_rtxnum_t rtx) +{ + struct xfs_mount *mp = rtg_mount(rtg); + xfs_rtblock_t start = xfs_group_start_fsb(rtg_group(rtg)); + + if (mp->m_rtxblklog >= 0) + return start + (rtx << mp->m_rtxblklog); + return start + (rtx * mp->m_sb.sb_rextsize); +} + +/* Convert an rgbno into an rt extent number. */ +static inline xfs_rtxnum_t +xfs_rgbno_to_rtx( + struct xfs_mount *mp, + xfs_rgblock_t rgbno) +{ + if (likely(mp->m_rtxblklog >= 0)) + return rgbno >> mp->m_rtxblklog; + return rgbno / mp->m_sb.sb_rextsize; +} + +static inline uint64_t +xfs_rtbxlen_to_blen( + struct xfs_mount *mp, + xfs_rtbxlen_t rtbxlen) +{ + if (mp->m_rtxblklog >= 0) + return rtbxlen << mp->m_rtxblklog; + + return rtbxlen * mp->m_sb.sb_rextsize; +} + +static inline xfs_extlen_t +xfs_rtxlen_to_extlen( + struct xfs_mount *mp, + xfs_rtxlen_t rtxlen) +{ + if (mp->m_rtxblklog >= 0) + return rtxlen << mp->m_rtxblklog; + + return rtxlen * mp->m_sb.sb_rextsize; +} + +/* Compute the misalignment between an extent length and a realtime extent .*/ +static inline unsigned int +xfs_extlen_to_rtxmod( + struct xfs_mount *mp, + xfs_extlen_t len) +{ + if (mp->m_rtxblklog >= 0) + return len & mp->m_rtxblkmask; + + return len % mp->m_sb.sb_rextsize; +} + +static inline xfs_rtxlen_t +xfs_extlen_to_rtxlen( + struct xfs_mount *mp, + xfs_extlen_t len) +{ + if (mp->m_rtxblklog >= 0) + return len >> mp->m_rtxblklog; + + return len / mp->m_sb.sb_rextsize; +} + +/* Convert an rt block count into an rt extent count. */ +static inline xfs_rtbxlen_t +xfs_blen_to_rtbxlen( + struct xfs_mount *mp, + uint64_t blen) +{ + if (likely(mp->m_rtxblklog >= 0)) + return blen >> mp->m_rtxblklog; + + return div_u64(blen, mp->m_sb.sb_rextsize); +} + +/* Return the offset of a file block length within an rt extent. */ +static inline xfs_extlen_t +xfs_blen_to_rtxoff( + struct xfs_mount *mp, + xfs_filblks_t blen) +{ + if (likely(mp->m_rtxblklog >= 0)) + return blen & mp->m_rtxblkmask; + + return do_div(blen, mp->m_sb.sb_rextsize); +} + +/* Round this block count up to the nearest rt extent size. */ +static inline xfs_filblks_t +xfs_blen_roundup_rtx( + struct xfs_mount *mp, + xfs_filblks_t blen) +{ + return roundup_64(blen, mp->m_sb.sb_rextsize); +} + +/* Convert an rt block number into an rt extent number. */ +static inline xfs_rtxnum_t +xfs_rtb_to_rtx( + struct xfs_mount *mp, + xfs_rtblock_t rtbno) +{ + /* open-coded 64-bit masking operation */ + rtbno &= mp->m_groups[XG_TYPE_RTG].blkmask; + if (likely(mp->m_rtxblklog >= 0)) + return rtbno >> mp->m_rtxblklog; + return div_u64(rtbno, mp->m_sb.sb_rextsize); +} + +/* Return the offset of a rtgroup block number within an rt extent. */ +static inline xfs_extlen_t +xfs_rgbno_to_rtxoff( + struct xfs_mount *mp, + xfs_rgblock_t rgbno) +{ + return rgbno % mp->m_sb.sb_rextsize; +} + +/* Return the offset of an rt block number within an rt extent. */ +static inline xfs_extlen_t +xfs_rtb_to_rtxoff( + struct xfs_mount *mp, + xfs_rtblock_t rtbno) +{ + /* open-coded 64-bit masking operation */ + rtbno &= mp->m_groups[XG_TYPE_RTG].blkmask; + if (likely(mp->m_rtxblklog >= 0)) + return rtbno & mp->m_rtxblkmask; + return do_div(rtbno, mp->m_sb.sb_rextsize); +} + +/* Round this file block offset up to the nearest rt extent size. */ +static inline xfs_rtblock_t +xfs_fileoff_roundup_rtx( + struct xfs_mount *mp, + xfs_fileoff_t off) +{ + return roundup_64(off, mp->m_sb.sb_rextsize); +} + +/* Round this file block offset down to the nearest rt extent size. */ +static inline xfs_rtblock_t +xfs_fileoff_rounddown_rtx( + struct xfs_mount *mp, + xfs_fileoff_t off) +{ + return rounddown_64(off, mp->m_sb.sb_rextsize); +} + +/* Convert an rt extent number to a file block offset in the rt bitmap file. */ +static inline xfs_fileoff_t +xfs_rtx_to_rbmblock( + struct xfs_mount *mp, + xfs_rtxnum_t rtx) +{ + if (xfs_has_rtgroups(mp)) + return div_u64(rtx, mp->m_rtx_per_rbmblock); + + return rtx >> mp->m_blkbit_log; +} + +/* Convert an rt extent number to a word offset within an rt bitmap block. */ +static inline unsigned int +xfs_rtx_to_rbmword( + struct xfs_mount *mp, + xfs_rtxnum_t rtx) +{ + if (xfs_has_rtgroups(mp)) { + unsigned int mod; + + div_u64_rem(rtx >> XFS_NBWORDLOG, mp->m_blockwsize, &mod); + return mod; + } + + return (rtx >> XFS_NBWORDLOG) & (mp->m_blockwsize - 1); +} + +/* Convert a file block offset in the rt bitmap file to an rt extent number. */ +static inline xfs_rtxnum_t +xfs_rbmblock_to_rtx( + struct xfs_mount *mp, + xfs_fileoff_t rbmoff) +{ + if (xfs_has_rtgroups(mp)) + return rbmoff * mp->m_rtx_per_rbmblock; + + return rbmoff << mp->m_blkbit_log; +} + +/* Return a pointer to a bitmap word within a rt bitmap block. */ +static inline union xfs_rtword_raw * +xfs_rbmblock_wordptr( + struct xfs_rtalloc_args *args, + unsigned int index) +{ + struct xfs_mount *mp = args->mp; + union xfs_rtword_raw *words; + struct xfs_rtbuf_blkinfo *hdr = args->rbmbp->b_addr; + + if (xfs_has_rtgroups(mp)) + words = (union xfs_rtword_raw *)(hdr + 1); + else + words = args->rbmbp->b_addr; + + return words + index; +} + +/* Convert an ondisk bitmap word to its incore representation. */ +static inline xfs_rtword_t +xfs_rtbitmap_getword( + struct xfs_rtalloc_args *args, + unsigned int index) +{ + union xfs_rtword_raw *word = xfs_rbmblock_wordptr(args, index); + + if (xfs_has_rtgroups(args->mp)) + return be32_to_cpu(word->rtg); + return word->old; +} + +/* Set an ondisk bitmap word from an incore representation. */ +static inline void +xfs_rtbitmap_setword( + struct xfs_rtalloc_args *args, + unsigned int index, + xfs_rtword_t value) +{ + union xfs_rtword_raw *word = xfs_rbmblock_wordptr(args, index); + + if (xfs_has_rtgroups(args->mp)) + word->rtg = cpu_to_be32(value); + else + word->old = value; +} + +/* + * Convert a rt extent length and rt bitmap block number to a xfs_suminfo_t + * offset within the rt summary file. + */ +static inline xfs_rtsumoff_t +xfs_rtsumoffs( + struct xfs_mount *mp, + int log2_len, + xfs_fileoff_t rbmoff) +{ + return log2_len * mp->m_sb.sb_rbmblocks + rbmoff; +} + +/* + * Convert an xfs_suminfo_t offset to a file block offset within the rt summary + * file. + */ +static inline xfs_fileoff_t +xfs_rtsumoffs_to_block( + struct xfs_mount *mp, + xfs_rtsumoff_t rsumoff) +{ + if (xfs_has_rtgroups(mp)) + return rsumoff / mp->m_blockwsize; + + return XFS_B_TO_FSBT(mp, rsumoff * sizeof(xfs_suminfo_t)); +} + +/* + * Convert an xfs_suminfo_t offset to an info word offset within an rt summary + * block. + */ +static inline unsigned int +xfs_rtsumoffs_to_infoword( + struct xfs_mount *mp, + xfs_rtsumoff_t rsumoff) +{ + unsigned int mask = mp->m_blockmask >> XFS_SUMINFOLOG; + + if (xfs_has_rtgroups(mp)) + return rsumoff % mp->m_blockwsize; + + return rsumoff & mask; +} + +/* Return a pointer to a summary info word within a rt summary block. */ +static inline union xfs_suminfo_raw * +xfs_rsumblock_infoptr( + struct xfs_rtalloc_args *args, + unsigned int index) +{ + union xfs_suminfo_raw *info; + struct xfs_rtbuf_blkinfo *hdr = args->sumbp->b_addr; + + if (xfs_has_rtgroups(args->mp)) + info = (union xfs_suminfo_raw *)(hdr + 1); + else + info = args->sumbp->b_addr; + + return info + index; +} + +/* Get the current value of a summary counter. */ +static inline xfs_suminfo_t +xfs_suminfo_get( + struct xfs_rtalloc_args *args, + unsigned int index) +{ + union xfs_suminfo_raw *info = xfs_rsumblock_infoptr(args, index); + + if (xfs_has_rtgroups(args->mp)) + return be32_to_cpu(info->rtg); + return info->old; +} + +/* Add to the current value of a summary counter and return the new value. */ +static inline xfs_suminfo_t +xfs_suminfo_add( + struct xfs_rtalloc_args *args, + unsigned int index, + int delta) +{ + union xfs_suminfo_raw *info = xfs_rsumblock_infoptr(args, index); + + if (xfs_has_rtgroups(args->mp)) { + be32_add_cpu(&info->rtg, delta); + return be32_to_cpu(info->rtg); + } + + info->old += delta; + return info->old; +} + +static inline const struct xfs_buf_ops * +xfs_rtblock_ops( + struct xfs_mount *mp, + enum xfs_rtg_inodes type) +{ + if (xfs_has_rtgroups(mp)) { + if (type == XFS_RTGI_SUMMARY) + return &xfs_rtsummary_buf_ops; + return &xfs_rtbitmap_buf_ops; + } + return &xfs_rtbuf_ops; +} + +/* + * Functions for walking free space rtextents in the realtime bitmap. + */ +struct xfs_rtalloc_rec { + xfs_rtxnum_t ar_startext; + xfs_rtbxlen_t ar_extcount; +}; + +typedef int (*xfs_rtalloc_query_range_fn)( + struct xfs_rtgroup *rtg, + struct xfs_trans *tp, + const struct xfs_rtalloc_rec *rec, + void *priv); + +#ifdef CONFIG_XFS_RT +void xfs_rtbuf_cache_relse(struct xfs_rtalloc_args *args); +int xfs_rtbitmap_read_buf(struct xfs_rtalloc_args *args, xfs_fileoff_t block); +int xfs_rtsummary_read_buf(struct xfs_rtalloc_args *args, xfs_fileoff_t block); +int xfs_rtcheck_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start, + xfs_rtxlen_t len, int val, xfs_rtxnum_t *new, int *stat); +int xfs_rtfind_back(struct xfs_rtalloc_args *args, xfs_rtxnum_t start, + xfs_rtxnum_t *rtblock); +int xfs_rtfind_forw(struct xfs_rtalloc_args *args, xfs_rtxnum_t start, + xfs_rtxnum_t limit, xfs_rtxnum_t *rtblock); +int xfs_rtmodify_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start, + xfs_rtxlen_t len, int val); +int xfs_rtget_summary(struct xfs_rtalloc_args *args, int log, + xfs_fileoff_t bbno, xfs_suminfo_t *sum); +int xfs_rtmodify_summary(struct xfs_rtalloc_args *args, int log, + xfs_fileoff_t bbno, int delta); +int xfs_rtfree_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start, + xfs_rtxlen_t len); +int xfs_rtalloc_query_range(struct xfs_rtgroup *rtg, struct xfs_trans *tp, + xfs_rtxnum_t start, xfs_rtxnum_t end, + xfs_rtalloc_query_range_fn fn, void *priv); +int xfs_rtalloc_query_all(struct xfs_rtgroup *rtg, struct xfs_trans *tp, + xfs_rtalloc_query_range_fn fn, void *priv); +int xfs_rtalloc_extent_is_free(struct xfs_rtgroup *rtg, struct xfs_trans *tp, + xfs_rtxnum_t start, xfs_rtxlen_t len, bool *is_free); +int xfs_rtfree_extent(struct xfs_trans *tp, struct xfs_rtgroup *rtg, + xfs_rtxnum_t start, xfs_rtxlen_t len); +/* Same as above, but in units of rt blocks. */ +int xfs_rtfree_blocks(struct xfs_trans *tp, struct xfs_rtgroup *rtg, + xfs_fsblock_t rtbno, xfs_filblks_t rtlen); + +xfs_rtxnum_t xfs_rtbitmap_rtx_per_rbmblock(struct xfs_mount *mp); +xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp); +xfs_filblks_t xfs_rtbitmap_blockcount_len(struct xfs_mount *mp, + xfs_rtbxlen_t rtextents); +xfs_filblks_t xfs_rtsummary_blockcount(struct xfs_mount *mp, + unsigned int *rsumlevels); + +int xfs_rtfile_initialize_blocks(struct xfs_rtgroup *rtg, + enum xfs_rtg_inodes type, xfs_fileoff_t offset_fsb, + xfs_fileoff_t end_fsb, void *data); +int xfs_rtbitmap_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xfs_trans *tp, bool init); +int xfs_rtsummary_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xfs_trans *tp, bool init); + +#else /* CONFIG_XFS_RT */ +# define xfs_rtfree_extent(t,b,l) (-ENOSYS) + +static inline int xfs_rtfree_blocks(struct xfs_trans *tp, + struct xfs_rtgroup *rtg, xfs_fsblock_t rtbno, + xfs_filblks_t rtlen) +{ + return -ENOSYS; +} +# define xfs_rtalloc_query_range(m,t,l,h,f,p) (-ENOSYS) +# define xfs_rtalloc_query_all(m,t,f,p) (-ENOSYS) +# define xfs_rtbitmap_read_buf(a,b) (-ENOSYS) +# define xfs_rtsummary_read_buf(a,b) (-ENOSYS) +# define xfs_rtbuf_cache_relse(a) (0) +# define xfs_rtalloc_extent_is_free(m,t,s,l,i) (-ENOSYS) +static inline xfs_filblks_t +xfs_rtbitmap_blockcount_len(struct xfs_mount *mp, xfs_rtbxlen_t rtextents) +{ + /* shut up gcc */ + return 0; +} +#endif /* CONFIG_XFS_RT */ + +#endif /* __XFS_RTBITMAP_H__ */ diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c new file mode 100644 index 000000000000..9186c58e83d5 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -0,0 +1,750 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2022-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_btree.h" +#include "xfs_alloc_btree.h" +#include "xfs_rmap_btree.h" +#include "xfs_alloc.h" +#include "xfs_ialloc.h" +#include "xfs_rmap.h" +#include "xfs_ag.h" +#include "xfs_ag_resv.h" +#include "xfs_health.h" +#include "xfs_error.h" +#include "xfs_bmap.h" +#include "xfs_defer.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_trace.h" +#include "xfs_inode.h" +#include "xfs_icache.h" +#include "xfs_buf_item.h" +#include "xfs_rtgroup.h" +#include "xfs_rtbitmap.h" +#include "xfs_metafile.h" +#include "xfs_metadir.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" + +/* Find the first usable fsblock in this rtgroup. */ +static inline uint32_t +xfs_rtgroup_min_block( + struct xfs_mount *mp, + xfs_rgnumber_t rgno) +{ + if (xfs_has_rtsb(mp) && rgno == 0) + return mp->m_sb.sb_rextsize; + + return 0; +} + +/* Precompute this group's geometry */ +void +xfs_rtgroup_calc_geometry( + struct xfs_mount *mp, + struct xfs_rtgroup *rtg, + xfs_rgnumber_t rgno, + xfs_rgnumber_t rgcount, + xfs_rtbxlen_t rextents) +{ + rtg->rtg_extents = __xfs_rtgroup_extents(mp, rgno, rgcount, rextents); + rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize; + rtg_group(rtg)->xg_min_gbno = xfs_rtgroup_min_block(mp, rgno); +} + +int +xfs_rtgroup_alloc( + struct xfs_mount *mp, + xfs_rgnumber_t rgno, + xfs_rgnumber_t rgcount, + xfs_rtbxlen_t rextents) +{ + struct xfs_rtgroup *rtg; + int error; + + rtg = kzalloc(sizeof(struct xfs_rtgroup), GFP_KERNEL); + if (!rtg) + return -ENOMEM; + + xfs_rtgroup_calc_geometry(mp, rtg, rgno, rgcount, rextents); + + error = xfs_group_insert(mp, rtg_group(rtg), rgno, XG_TYPE_RTG); + if (error) + goto out_free_rtg; + return 0; + +out_free_rtg: + kfree(rtg); + return error; +} + +void +xfs_rtgroup_free( + struct xfs_mount *mp, + xfs_rgnumber_t rgno) +{ + xfs_group_free(mp, rgno, XG_TYPE_RTG, NULL); +} + +/* Free a range of incore rtgroup objects. */ +void +xfs_free_rtgroups( + struct xfs_mount *mp, + xfs_rgnumber_t first_rgno, + xfs_rgnumber_t end_rgno) +{ + xfs_rgnumber_t rgno; + + for (rgno = first_rgno; rgno < end_rgno; rgno++) + xfs_rtgroup_free(mp, rgno); +} + +/* Initialize some range of incore rtgroup objects. */ +int +xfs_initialize_rtgroups( + struct xfs_mount *mp, + xfs_rgnumber_t first_rgno, + xfs_rgnumber_t end_rgno, + xfs_rtbxlen_t rextents) +{ + xfs_rgnumber_t index; + int error; + + if (first_rgno >= end_rgno) + return 0; + + for (index = first_rgno; index < end_rgno; index++) { + error = xfs_rtgroup_alloc(mp, index, end_rgno, rextents); + if (error) + goto out_unwind_new_rtgs; + } + + return 0; + +out_unwind_new_rtgs: + xfs_free_rtgroups(mp, first_rgno, index); + return error; +} + +/* Compute the number of rt extents in this realtime group. */ +xfs_rtxnum_t +__xfs_rtgroup_extents( + struct xfs_mount *mp, + xfs_rgnumber_t rgno, + xfs_rgnumber_t rgcount, + xfs_rtbxlen_t rextents) +{ + ASSERT(rgno < rgcount); + if (rgno == rgcount - 1) + return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents); + + ASSERT(xfs_has_rtgroups(mp)); + return mp->m_sb.sb_rgextents; +} + +xfs_rtxnum_t +xfs_rtgroup_extents( + struct xfs_mount *mp, + xfs_rgnumber_t rgno) +{ + return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount, + mp->m_sb.sb_rextents); +} + +/* + * Update the rt extent count of the previous tail rtgroup if it changed during + * recovery (i.e. recovery of a growfs). + */ +int +xfs_update_last_rtgroup_size( + struct xfs_mount *mp, + xfs_rgnumber_t prev_rgcount) +{ + struct xfs_rtgroup *rtg; + + ASSERT(prev_rgcount > 0); + + rtg = xfs_rtgroup_grab(mp, prev_rgcount - 1); + if (!rtg) + return -EFSCORRUPTED; + rtg->rtg_extents = __xfs_rtgroup_extents(mp, prev_rgcount - 1, + mp->m_sb.sb_rgcount, mp->m_sb.sb_rextents); + rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize; + xfs_rtgroup_rele(rtg); + return 0; +} + +/* Lock metadata inodes associated with this rt group. */ +void +xfs_rtgroup_lock( + struct xfs_rtgroup *rtg, + unsigned int rtglock_flags) +{ + ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS)); + ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) || + !(rtglock_flags & XFS_RTGLOCK_BITMAP)); + + if (!xfs_has_zoned(rtg_mount(rtg))) { + if (rtglock_flags & XFS_RTGLOCK_BITMAP) { + /* + * Lock both realtime free space metadata inodes for a + * freespace update. + */ + xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_EXCL); + xfs_ilock(rtg_summary(rtg), XFS_ILOCK_EXCL); + } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { + xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_SHARED); + } + } + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_ilock(rtg_refcount(rtg), XFS_ILOCK_EXCL); +} + +/* Unlock metadata inodes associated with this rt group. */ +void +xfs_rtgroup_unlock( + struct xfs_rtgroup *rtg, + unsigned int rtglock_flags) +{ + ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS)); + ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) || + !(rtglock_flags & XFS_RTGLOCK_BITMAP)); + + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_iunlock(rtg_refcount(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_EXCL); + + if (!xfs_has_zoned(rtg_mount(rtg))) { + if (rtglock_flags & XFS_RTGLOCK_BITMAP) { + xfs_iunlock(rtg_summary(rtg), XFS_ILOCK_EXCL); + xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_EXCL); + } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { + xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_SHARED); + } + } +} + +/* + * Join realtime group metadata inodes to the transaction. The ILOCKs will be + * released on transaction commit. + */ +void +xfs_rtgroup_trans_join( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg, + unsigned int rtglock_flags) +{ + ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS)); + ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED)); + + if (!xfs_has_zoned(rtg_mount(rtg)) && + (rtglock_flags & XFS_RTGLOCK_BITMAP)) { + xfs_trans_ijoin(tp, rtg_bitmap(rtg), XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, rtg_summary(rtg), XFS_ILOCK_EXCL); + } + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_trans_ijoin(tp, rtg_rmap(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_trans_ijoin(tp, rtg_refcount(rtg), XFS_ILOCK_EXCL); +} + +/* Retrieve rt group geometry. */ +int +xfs_rtgroup_get_geometry( + struct xfs_rtgroup *rtg, + struct xfs_rtgroup_geometry *rgeo) +{ + /* Fill out form. */ + memset(rgeo, 0, sizeof(*rgeo)); + rgeo->rg_number = rtg_rgno(rtg); + rgeo->rg_length = rtg_blocks(rtg); + xfs_rtgroup_geom_health(rtg, rgeo); + return 0; +} + +#ifdef CONFIG_PROVE_LOCKING +static struct lock_class_key xfs_rtginode_lock_class; + +static int +xfs_rtginode_ilock_cmp_fn( + const struct lockdep_map *m1, + const struct lockdep_map *m2) +{ + const struct xfs_inode *ip1 = + container_of(m1, struct xfs_inode, i_lock.dep_map); + const struct xfs_inode *ip2 = + container_of(m2, struct xfs_inode, i_lock.dep_map); + + if (ip1->i_projid < ip2->i_projid) + return -1; + if (ip1->i_projid > ip2->i_projid) + return 1; + return 0; +} + +static inline void +xfs_rtginode_ilock_print_fn( + const struct lockdep_map *m) +{ + const struct xfs_inode *ip = + container_of(m, struct xfs_inode, i_lock.dep_map); + + printk(KERN_CONT " rgno=%u metatype=%s", ip->i_projid, + xfs_metafile_type_str(ip->i_metatype)); +} + +/* + * Most of the time each of the RTG inode locks are only taken one at a time. + * But when committing deferred ops, more than one of a kind can be taken. + * However, deferred rt ops will be committed in rgno order so there is no + * potential for deadlocks. The code here is needed to tell lockdep about this + * order. + */ +static inline void +xfs_rtginode_lockdep_setup( + struct xfs_inode *ip, + xfs_rgnumber_t rgno, + enum xfs_rtg_inodes type) +{ + lockdep_set_class_and_subclass(&ip->i_lock, &xfs_rtginode_lock_class, + type); + lock_set_cmp_fn(&ip->i_lock, xfs_rtginode_ilock_cmp_fn, + xfs_rtginode_ilock_print_fn); +} +#else +#define xfs_rtginode_lockdep_setup(ip, rgno, type) do { } while (0) +#endif /* CONFIG_PROVE_LOCKING */ + +struct xfs_rtginode_ops { + const char *name; /* short name */ + + enum xfs_metafile_type metafile_type; + + unsigned int sick; /* rtgroup sickness flag */ + + unsigned int fmt_mask; /* all valid data fork formats */ + + /* Does the fs have this feature? */ + bool (*enabled)(const struct xfs_mount *mp); + + /* Create this rtgroup metadata inode and initialize it. */ + int (*create)(struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init); +}; + +static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = { + [XFS_RTGI_BITMAP] = { + .name = "bitmap", + .metafile_type = XFS_METAFILE_RTBITMAP, + .sick = XFS_SICK_RG_BITMAP, + .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | + (1U << XFS_DINODE_FMT_BTREE), + .enabled = xfs_has_nonzoned, + .create = xfs_rtbitmap_create, + }, + [XFS_RTGI_SUMMARY] = { + .name = "summary", + .metafile_type = XFS_METAFILE_RTSUMMARY, + .sick = XFS_SICK_RG_SUMMARY, + .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | + (1U << XFS_DINODE_FMT_BTREE), + .enabled = xfs_has_nonzoned, + .create = xfs_rtsummary_create, + }, + [XFS_RTGI_RMAP] = { + .name = "rmap", + .metafile_type = XFS_METAFILE_RTRMAP, + .sick = XFS_SICK_RG_RMAPBT, + .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, + /* + * growfs must create the rtrmap inodes before adding a + * realtime volume to the filesystem, so we cannot use the + * rtrmapbt predicate here. + */ + .enabled = xfs_has_rmapbt, + .create = xfs_rtrmapbt_create, + }, + [XFS_RTGI_REFCOUNT] = { + .name = "refcount", + .metafile_type = XFS_METAFILE_RTREFCOUNT, + .sick = XFS_SICK_RG_REFCNTBT, + .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, + /* same comment about growfs and rmap inodes applies here */ + .enabled = xfs_has_reflink, + .create = xfs_rtrefcountbt_create, + }, +}; + +/* Return the shortname of this rtgroup inode. */ +const char * +xfs_rtginode_name( + enum xfs_rtg_inodes type) +{ + return xfs_rtginode_ops[type].name; +} + +/* Return the metafile type of this rtgroup inode. */ +enum xfs_metafile_type +xfs_rtginode_metafile_type( + enum xfs_rtg_inodes type) +{ + return xfs_rtginode_ops[type].metafile_type; +} + +/* Should this rtgroup inode be present? */ +bool +xfs_rtginode_enabled( + struct xfs_rtgroup *rtg, + enum xfs_rtg_inodes type) +{ + const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type]; + + if (!ops->enabled) + return true; + return ops->enabled(rtg_mount(rtg)); +} + +/* Mark an rtgroup inode sick */ +void +xfs_rtginode_mark_sick( + struct xfs_rtgroup *rtg, + enum xfs_rtg_inodes type) +{ + const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type]; + + xfs_group_mark_sick(rtg_group(rtg), ops->sick); +} + +/* Load and existing rtgroup inode into the rtgroup structure. */ +int +xfs_rtginode_load( + struct xfs_rtgroup *rtg, + enum xfs_rtg_inodes type, + struct xfs_trans *tp) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_inode *ip; + const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type]; + int error; + + if (!xfs_rtginode_enabled(rtg, type)) + return 0; + + if (!xfs_has_rtgroups(mp)) { + xfs_ino_t ino; + + switch (type) { + case XFS_RTGI_BITMAP: + ino = mp->m_sb.sb_rbmino; + break; + case XFS_RTGI_SUMMARY: + ino = mp->m_sb.sb_rsumino; + break; + default: + /* None of the other types exist on !rtgroups */ + return 0; + } + + error = xfs_trans_metafile_iget(tp, ino, ops->metafile_type, + &ip); + } else { + const char *path; + + if (!mp->m_rtdirip) { + xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); + return -EFSCORRUPTED; + } + + path = xfs_rtginode_path(rtg_rgno(rtg), type); + if (!path) + return -ENOMEM; + error = xfs_metadir_load(tp, mp->m_rtdirip, path, + ops->metafile_type, &ip); + kfree(path); + } + + if (error) { + if (xfs_metadata_is_sick(error)) + xfs_rtginode_mark_sick(rtg, type); + return error; + } + + if (XFS_IS_CORRUPT(mp, !((1U << ip->i_df.if_format) & ops->fmt_mask))) { + xfs_irele(ip); + xfs_rtginode_mark_sick(rtg, type); + return -EFSCORRUPTED; + } + + if (XFS_IS_CORRUPT(mp, ip->i_projid != rtg_rgno(rtg))) { + xfs_irele(ip); + xfs_rtginode_mark_sick(rtg, type); + return -EFSCORRUPTED; + } + + xfs_rtginode_lockdep_setup(ip, rtg_rgno(rtg), type); + rtg->rtg_inodes[type] = ip; + return 0; +} + +/* Release an rtgroup metadata inode. */ +void +xfs_rtginode_irele( + struct xfs_inode **ipp) +{ + if (*ipp) + xfs_irele(*ipp); + *ipp = NULL; +} + +/* Add a metadata inode for a realtime rmap btree. */ +int +xfs_rtginode_create( + struct xfs_rtgroup *rtg, + enum xfs_rtg_inodes type, + bool init) +{ + const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type]; + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_metadir_update upd = { + .dp = mp->m_rtdirip, + .metafile_type = ops->metafile_type, + }; + int error; + + if (!xfs_rtginode_enabled(rtg, type)) + return 0; + + if (!mp->m_rtdirip) { + xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); + return -EFSCORRUPTED; + } + + upd.path = xfs_rtginode_path(rtg_rgno(rtg), type); + if (!upd.path) + return -ENOMEM; + + error = xfs_metadir_start_create(&upd); + if (error) + goto out_path; + + error = xfs_metadir_create(&upd, S_IFREG); + if (error) + goto out_cancel; + + xfs_rtginode_lockdep_setup(upd.ip, rtg_rgno(rtg), type); + + upd.ip->i_projid = rtg_rgno(rtg); + error = ops->create(rtg, upd.ip, upd.tp, init); + if (error) + goto out_cancel; + + error = xfs_metadir_commit(&upd); + if (error) + goto out_path; + + kfree(upd.path); + xfs_finish_inode_setup(upd.ip); + rtg->rtg_inodes[type] = upd.ip; + return 0; + +out_cancel: + xfs_metadir_cancel(&upd, error); + /* Have to finish setting up the inode to ensure it's deleted. */ + if (upd.ip) { + xfs_finish_inode_setup(upd.ip); + xfs_irele(upd.ip); + } +out_path: + kfree(upd.path); + return error; +} + +/* Create the parent directory for all rtgroup inodes and load it. */ +int +xfs_rtginode_mkdir_parent( + struct xfs_mount *mp) +{ + if (!mp->m_metadirip) { + xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); + return -EFSCORRUPTED; + } + + return xfs_metadir_mkdir(mp->m_metadirip, "rtgroups", &mp->m_rtdirip); +} + +/* Load the parent directory of all rtgroup inodes. */ +int +xfs_rtginode_load_parent( + struct xfs_trans *tp) +{ + struct xfs_mount *mp = tp->t_mountp; + + if (!mp->m_metadirip) { + xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); + return -EFSCORRUPTED; + } + + return xfs_metadir_load(tp, mp->m_metadirip, "rtgroups", + XFS_METAFILE_DIR, &mp->m_rtdirip); +} + +/* Check superblock fields for a read or a write. */ +static xfs_failaddr_t +xfs_rtsb_verify_common( + struct xfs_buf *bp) +{ + struct xfs_rtsb *rsb = bp->b_addr; + + if (!xfs_verify_magic(bp, rsb->rsb_magicnum)) + return __this_address; + if (rsb->rsb_pad) + return __this_address; + + /* Everything to the end of the fs block must be zero */ + if (memchr_inv(rsb + 1, 0, BBTOB(bp->b_length) - sizeof(*rsb))) + return __this_address; + + return NULL; +} + +/* Check superblock fields for a read or revalidation. */ +static inline xfs_failaddr_t +xfs_rtsb_verify_all( + struct xfs_buf *bp) +{ + struct xfs_rtsb *rsb = bp->b_addr; + struct xfs_mount *mp = bp->b_mount; + xfs_failaddr_t fa; + + fa = xfs_rtsb_verify_common(bp); + if (fa) + return fa; + + if (memcmp(&rsb->rsb_fname, &mp->m_sb.sb_fname, XFSLABEL_MAX)) + return __this_address; + if (!uuid_equal(&rsb->rsb_uuid, &mp->m_sb.sb_uuid)) + return __this_address; + if (!uuid_equal(&rsb->rsb_meta_uuid, &mp->m_sb.sb_meta_uuid)) + return __this_address; + + return NULL; +} + +static void +xfs_rtsb_read_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + if (!xfs_buf_verify_cksum(bp, XFS_RTSB_CRC_OFF)) { + xfs_verifier_error(bp, -EFSBADCRC, __this_address); + return; + } + + fa = xfs_rtsb_verify_all(bp); + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); +} + +static void +xfs_rtsb_write_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + fa = xfs_rtsb_verify_common(bp); + if (fa) { + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + + xfs_buf_update_cksum(bp, XFS_RTSB_CRC_OFF); +} + +const struct xfs_buf_ops xfs_rtsb_buf_ops = { + .name = "xfs_rtsb", + .magic = { 0, cpu_to_be32(XFS_RTSB_MAGIC) }, + .verify_read = xfs_rtsb_read_verify, + .verify_write = xfs_rtsb_write_verify, + .verify_struct = xfs_rtsb_verify_all, +}; + +/* Update a realtime superblock from the primary fs super */ +void +xfs_update_rtsb( + struct xfs_buf *rtsb_bp, + const struct xfs_buf *sb_bp) +{ + const struct xfs_dsb *dsb = sb_bp->b_addr; + struct xfs_rtsb *rsb = rtsb_bp->b_addr; + const uuid_t *meta_uuid; + + rsb->rsb_magicnum = cpu_to_be32(XFS_RTSB_MAGIC); + + rsb->rsb_pad = 0; + memcpy(&rsb->rsb_fname, &dsb->sb_fname, XFSLABEL_MAX); + + memcpy(&rsb->rsb_uuid, &dsb->sb_uuid, sizeof(rsb->rsb_uuid)); + + /* + * The metadata uuid is the fs uuid if the metauuid feature is not + * enabled. + */ + if (dsb->sb_features_incompat & + cpu_to_be32(XFS_SB_FEAT_INCOMPAT_META_UUID)) + meta_uuid = &dsb->sb_meta_uuid; + else + meta_uuid = &dsb->sb_uuid; + memcpy(&rsb->rsb_meta_uuid, meta_uuid, sizeof(rsb->rsb_meta_uuid)); +} + +/* + * Update the realtime superblock from a filesystem superblock and log it to + * the given transaction. + */ +struct xfs_buf * +xfs_log_rtsb( + struct xfs_trans *tp, + const struct xfs_buf *sb_bp) +{ + struct xfs_buf *rtsb_bp; + + if (!xfs_has_rtsb(tp->t_mountp)) + return NULL; + + rtsb_bp = xfs_trans_getrtsb(tp); + if (!rtsb_bp) { + /* + * It's possible for the rtgroups feature to be enabled but + * there is no incore rt superblock buffer if the rt geometry + * was specified at mkfs time but the rt section has not yet + * been attached. In this case, rblocks must be zero. + */ + ASSERT(tp->t_mountp->m_sb.sb_rblocks == 0); + return NULL; + } + + xfs_update_rtsb(rtsb_bp, sb_bp); + xfs_trans_ordered_buf(tp, rtsb_bp); + return rtsb_bp; +} diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h new file mode 100644 index 000000000000..03f1e2493334 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -0,0 +1,376 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2022-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __LIBXFS_RTGROUP_H +#define __LIBXFS_RTGROUP_H 1 + +#include "xfs_group.h" + +struct xfs_mount; +struct xfs_trans; + +enum xfs_rtg_inodes { + XFS_RTGI_BITMAP, /* allocation bitmap */ + XFS_RTGI_SUMMARY, /* allocation summary */ + XFS_RTGI_RMAP, /* rmap btree inode */ + XFS_RTGI_REFCOUNT, /* refcount btree inode */ + + XFS_RTGI_MAX, +}; + +#ifdef MAX_LOCKDEP_SUBCLASSES +static_assert(XFS_RTGI_MAX <= MAX_LOCKDEP_SUBCLASSES); +#endif + +/* + * Realtime group incore structure, similar to the per-AG structure. + */ +struct xfs_rtgroup { + struct xfs_group rtg_group; + + /* per-rtgroup metadata inodes */ + struct xfs_inode *rtg_inodes[XFS_RTGI_MAX]; + + /* Number of blocks in this group */ + xfs_rtxnum_t rtg_extents; + + /* + * For bitmap based RT devices this points to a cache of rt summary + * level per bitmap block with the invariant that rtg_rsum_cache[bbno] + * > the maximum i for which rsum[i][bbno] != 0, or 0 if + * rsum[i][bbno] == 0 for all i. + * Reads and writes are serialized by the rsumip inode lock. + * + * For zoned RT devices this points to the open zone structure for + * a group that is open for writers, or is NULL. + */ + union { + uint8_t *rtg_rsum_cache; + struct xfs_open_zone *rtg_open_zone; + }; + + /* + * Count of outstanding GC operations for zoned XFS. Any RTG with a + * non-zero rtg_gccount will not be picked as new GC victim. + */ + atomic_t rtg_gccount; +}; + +/* + * For zoned RT devices this is set on groups that have no written blocks + * and can be picked by the allocator for opening. + */ +#define XFS_RTG_FREE XA_MARK_0 + +static inline struct xfs_rtgroup *to_rtg(struct xfs_group *xg) +{ + return container_of(xg, struct xfs_rtgroup, rtg_group); +} + +static inline struct xfs_group *rtg_group(struct xfs_rtgroup *rtg) +{ + return &rtg->rtg_group; +} + +static inline struct xfs_mount *rtg_mount(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_group.xg_mount; +} + +static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_group.xg_gno; +} + +static inline xfs_rgblock_t rtg_blocks(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_group.xg_block_count; +} + +static inline struct xfs_inode *rtg_bitmap(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_BITMAP]; +} + +static inline struct xfs_inode *rtg_summary(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_SUMMARY]; +} + +static inline struct xfs_inode *rtg_rmap(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_RMAP]; +} + +static inline struct xfs_inode *rtg_refcount(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_REFCOUNT]; +} + +/* Passive rtgroup references */ +static inline struct xfs_rtgroup * +xfs_rtgroup_get( + struct xfs_mount *mp, + xfs_rgnumber_t rgno) +{ + return to_rtg(xfs_group_get(mp, rgno, XG_TYPE_RTG)); +} + +static inline struct xfs_rtgroup * +xfs_rtgroup_hold( + struct xfs_rtgroup *rtg) +{ + return to_rtg(xfs_group_hold(rtg_group(rtg))); +} + +static inline void +xfs_rtgroup_put( + struct xfs_rtgroup *rtg) +{ + xfs_group_put(rtg_group(rtg)); +} + +/* Active rtgroup references */ +static inline struct xfs_rtgroup * +xfs_rtgroup_grab( + struct xfs_mount *mp, + xfs_rgnumber_t rgno) +{ + return to_rtg(xfs_group_grab(mp, rgno, XG_TYPE_RTG)); +} + +static inline void +xfs_rtgroup_rele( + struct xfs_rtgroup *rtg) +{ + xfs_group_rele(rtg_group(rtg)); +} + +static inline struct xfs_rtgroup * +xfs_rtgroup_next_range( + struct xfs_mount *mp, + struct xfs_rtgroup *rtg, + xfs_rgnumber_t start_rgno, + xfs_rgnumber_t end_rgno) +{ + return to_rtg(xfs_group_next_range(mp, rtg ? rtg_group(rtg) : NULL, + start_rgno, end_rgno, XG_TYPE_RTG)); +} + +static inline struct xfs_rtgroup * +xfs_rtgroup_next( + struct xfs_mount *mp, + struct xfs_rtgroup *rtg) +{ + return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1); +} + +static inline bool +xfs_verify_rgbno( + struct xfs_rtgroup *rtg, + xfs_rgblock_t rgbno) +{ + ASSERT(xfs_has_rtgroups(rtg_mount(rtg))); + + return xfs_verify_gbno(rtg_group(rtg), rgbno); +} + +/* + * Check that [@rgbno,@len] is a valid extent range in @rtg. + * + * Must only be used for RTG-enabled file systems. + */ +static inline bool +xfs_verify_rgbext( + struct xfs_rtgroup *rtg, + xfs_rgblock_t rgbno, + xfs_extlen_t len) +{ + ASSERT(xfs_has_rtgroups(rtg_mount(rtg))); + + return xfs_verify_gbext(rtg_group(rtg), rgbno, len); +} + +static inline xfs_rtblock_t +xfs_rgbno_to_rtb( + struct xfs_rtgroup *rtg, + xfs_rgblock_t rgbno) +{ + return xfs_gbno_to_fsb(rtg_group(rtg), rgbno); +} + +static inline xfs_rgnumber_t +xfs_rtb_to_rgno( + struct xfs_mount *mp, + xfs_rtblock_t rtbno) +{ + return xfs_fsb_to_gno(mp, rtbno, XG_TYPE_RTG); +} + +static inline xfs_rgblock_t +xfs_rtb_to_rgbno( + struct xfs_mount *mp, + xfs_rtblock_t rtbno) +{ + return xfs_fsb_to_gbno(mp, rtbno, XG_TYPE_RTG); +} + +/* Is rtbno the start of a RT group? */ +static inline bool +xfs_rtbno_is_group_start( + struct xfs_mount *mp, + xfs_rtblock_t rtbno) +{ + return (rtbno & mp->m_groups[XG_TYPE_RTG].blkmask) == 0; +} + +/* Convert an rtgroups rt extent number into an rgbno. */ +static inline xfs_rgblock_t +xfs_rtx_to_rgbno( + struct xfs_rtgroup *rtg, + xfs_rtxnum_t rtx) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (likely(mp->m_rtxblklog >= 0)) + return rtx << mp->m_rtxblklog; + return rtx * mp->m_sb.sb_rextsize; +} + +static inline xfs_daddr_t +xfs_rtb_to_daddr( + struct xfs_mount *mp, + xfs_rtblock_t rtbno) +{ + struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG]; + + if (xfs_has_rtgroups(mp) && !g->has_daddr_gaps) { + xfs_rgnumber_t rgno = xfs_rtb_to_rgno(mp, rtbno); + + rtbno = (xfs_rtblock_t)rgno * g->blocks + (rtbno & g->blkmask); + } + + return XFS_FSB_TO_BB(mp, g->start_fsb + rtbno); +} + +static inline xfs_rtblock_t +xfs_daddr_to_rtb( + struct xfs_mount *mp, + xfs_daddr_t daddr) +{ + struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG]; + xfs_rfsblock_t bno; + + bno = XFS_BB_TO_FSBT(mp, daddr) - g->start_fsb; + if (xfs_has_rtgroups(mp) && !g->has_daddr_gaps) { + xfs_rgnumber_t rgno; + uint32_t rgbno; + + rgno = div_u64_rem(bno, g->blocks, &rgbno); + return ((xfs_rtblock_t)rgno << g->blklog) + rgbno; + } + + return bno; +} + +#ifdef CONFIG_XFS_RT +int xfs_rtgroup_alloc(struct xfs_mount *mp, xfs_rgnumber_t rgno, + xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents); +void xfs_rtgroup_free(struct xfs_mount *mp, xfs_rgnumber_t rgno); + +void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno, + xfs_rgnumber_t end_rgno); +int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno, + xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents); + +xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno, + xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents); +xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno); +void xfs_rtgroup_calc_geometry(struct xfs_mount *mp, struct xfs_rtgroup *rtg, + xfs_rgnumber_t rgno, xfs_rgnumber_t rgcount, + xfs_rtbxlen_t rextents); + +int xfs_update_last_rtgroup_size(struct xfs_mount *mp, + xfs_rgnumber_t prev_rgcount); + +/* Lock the rt bitmap inode in exclusive mode */ +#define XFS_RTGLOCK_BITMAP (1U << 0) +/* Lock the rt bitmap inode in shared mode */ +#define XFS_RTGLOCK_BITMAP_SHARED (1U << 1) +/* Lock the rt rmap inode in exclusive mode */ +#define XFS_RTGLOCK_RMAP (1U << 2) +/* Lock the rt refcount inode in exclusive mode */ +#define XFS_RTGLOCK_REFCOUNT (1U << 3) + +#define XFS_RTGLOCK_ALL_FLAGS (XFS_RTGLOCK_BITMAP | \ + XFS_RTGLOCK_BITMAP_SHARED | \ + XFS_RTGLOCK_RMAP | \ + XFS_RTGLOCK_REFCOUNT) + +void xfs_rtgroup_lock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags); +void xfs_rtgroup_unlock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags); +void xfs_rtgroup_trans_join(struct xfs_trans *tp, struct xfs_rtgroup *rtg, + unsigned int rtglock_flags); + +int xfs_rtgroup_get_geometry(struct xfs_rtgroup *rtg, + struct xfs_rtgroup_geometry *rgeo); + +int xfs_rtginode_mkdir_parent(struct xfs_mount *mp); +int xfs_rtginode_load_parent(struct xfs_trans *tp); + +const char *xfs_rtginode_name(enum xfs_rtg_inodes type); +enum xfs_metafile_type xfs_rtginode_metafile_type(enum xfs_rtg_inodes type); +bool xfs_rtginode_enabled(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type); +void xfs_rtginode_mark_sick(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type); +int xfs_rtginode_load(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type, + struct xfs_trans *tp); +int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type, + bool init); +void xfs_rtginode_irele(struct xfs_inode **ipp); + +void xfs_rtginode_irele(struct xfs_inode **ipp); + +static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno, + enum xfs_rtg_inodes type) +{ + return kasprintf(GFP_KERNEL, "%u.%s", rgno, xfs_rtginode_name(type)); +} + +void xfs_update_rtsb(struct xfs_buf *rtsb_bp, + const struct xfs_buf *sb_bp); +struct xfs_buf *xfs_log_rtsb(struct xfs_trans *tp, + const struct xfs_buf *sb_bp); +#else +static inline void xfs_free_rtgroups(struct xfs_mount *mp, + xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno) +{ +} + +static inline int xfs_initialize_rtgroups(struct xfs_mount *mp, + xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno, + xfs_rtbxlen_t rextents) +{ + return 0; +} + +# define xfs_rtgroup_extents(mp, rgno) (0) +# define xfs_update_last_rtgroup_size(mp, rgno) (0) +# define xfs_rtgroup_lock(rtg, gf) ((void)0) +# define xfs_rtgroup_unlock(rtg, gf) ((void)0) +# define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0) +# define xfs_update_rtsb(bp, sb_bp) ((void)0) +# define xfs_log_rtsb(tp, sb_bp) (NULL) +# define xfs_rtgroup_get_geometry(rtg, rgeo) (-EOPNOTSUPP) +#endif /* CONFIG_XFS_RT */ + +static inline xfs_rfsblock_t +xfs_rtgs_to_rfsbs( + struct xfs_mount *mp, + uint32_t nr_groups) +{ + return xfs_groups_to_rfsbs(mp, nr_groups, XG_TYPE_RTG); +} + +#endif /* __LIBXFS_RTGROUP_H */ diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.c b/fs/xfs/libxfs/xfs_rtrefcount_btree.c new file mode 100644 index 000000000000..ac11e94b42ae --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.c @@ -0,0 +1,757 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_alloc.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_refcount.h" +#include "xfs_trace.h" +#include "xfs_cksum.h" +#include "xfs_error.h" +#include "xfs_extent_busy.h" +#include "xfs_rtgroup.h" +#include "xfs_rtbitmap.h" +#include "xfs_metafile.h" +#include "xfs_health.h" + +static struct kmem_cache *xfs_rtrefcountbt_cur_cache; + +/* + * Realtime Reference Count btree. + * + * This is a btree used to track the owner(s) of a given extent in the realtime + * device. See the comments in xfs_refcount_btree.c for more information. + * + * This tree is basically the same as the regular refcount btree except that + * it's rooted in an inode. + */ + +static struct xfs_btree_cur * +xfs_rtrefcountbt_dup_cursor( + struct xfs_btree_cur *cur) +{ + return xfs_rtrefcountbt_init_cursor(cur->bc_tp, to_rtg(cur->bc_group)); +} + +STATIC int +xfs_rtrefcountbt_get_minrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrefcountbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0) / 2; + } + + return cur->bc_mp->m_rtrefc_mnr[level != 0]; +} + +STATIC int +xfs_rtrefcountbt_get_maxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrefcountbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0); + } + + return cur->bc_mp->m_rtrefc_mxr[level != 0]; +} + +/* + * Calculate number of records in a realtime refcount btree inode root. + */ +unsigned int +xfs_rtrefcountbt_droot_maxrecs( + unsigned int blocklen, + bool leaf) +{ + blocklen -= sizeof(struct xfs_rtrefcount_root); + + if (leaf) + return blocklen / sizeof(struct xfs_refcount_rec); + return blocklen / (2 * sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Get the maximum records we could store in the on-disk format. + * + * For non-root nodes this is equivalent to xfs_rtrefcountbt_get_maxrecs, but + * for the root node this checks the available space in the dinode fork so that + * we can resize the in-memory buffer to match it. After a resize to the + * maximum size this function returns the same value as + * xfs_rtrefcountbt_get_maxrecs for the root node, too. + */ +STATIC int +xfs_rtrefcountbt_get_dmaxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level != cur->bc_nlevels - 1) + return cur->bc_mp->m_rtrefc_mxr[level != 0]; + return xfs_rtrefcountbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); +} + +STATIC void +xfs_rtrefcountbt_init_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + key->refc.rc_startblock = rec->refc.rc_startblock; +} + +STATIC void +xfs_rtrefcountbt_init_high_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + __u32 x; + + x = be32_to_cpu(rec->refc.rc_startblock); + x += be32_to_cpu(rec->refc.rc_blockcount) - 1; + key->refc.rc_startblock = cpu_to_be32(x); +} + +STATIC void +xfs_rtrefcountbt_init_rec_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_rec *rec) +{ + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + rec->refc.rc_startblock = cpu_to_be32(start); + rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount); + rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount); +} + +STATIC void +xfs_rtrefcountbt_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + ptr->l = 0; +} + +STATIC int +xfs_rtrefcountbt_cmp_key_with_cur( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key) +{ + const struct xfs_refcount_key *kp = &key->refc; + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + return cmp_int(be32_to_cpu(kp->rc_startblock), start); +} + +STATIC int +xfs_rtrefcountbt_cmp_two_keys( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->refc.rc_startblock); + + return cmp_int(be32_to_cpu(k1->refc.rc_startblock), + be32_to_cpu(k2->refc.rc_startblock)); +} + +static xfs_failaddr_t +xfs_rtrefcountbt_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + int level; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + if (!xfs_has_reflink(mp)) + return __this_address; + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + level = be16_to_cpu(block->bb_level); + if (level > mp->m_rtrefc_maxlevels) + return __this_address; + + return xfs_btree_fsblock_verify(bp, mp->m_rtrefc_mxr[level != 0]); +} + +static void +xfs_rtrefcountbt_read_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + if (!xfs_btree_fsblock_verify_crc(bp)) + xfs_verifier_error(bp, -EFSBADCRC, __this_address); + else { + fa = xfs_rtrefcountbt_verify(bp); + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + } + + if (bp->b_error) + trace_xfs_btree_corrupt(bp, _RET_IP_); +} + +static void +xfs_rtrefcountbt_write_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + fa = xfs_rtrefcountbt_verify(bp); + if (fa) { + trace_xfs_btree_corrupt(bp, _RET_IP_); + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + xfs_btree_fsblock_calc_crc(bp); + +} + +const struct xfs_buf_ops xfs_rtrefcountbt_buf_ops = { + .name = "xfs_rtrefcountbt", + .magic = { 0, cpu_to_be32(XFS_RTREFC_CRC_MAGIC) }, + .verify_read = xfs_rtrefcountbt_read_verify, + .verify_write = xfs_rtrefcountbt_write_verify, + .verify_struct = xfs_rtrefcountbt_verify, +}; + +STATIC int +xfs_rtrefcountbt_keys_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2) +{ + return be32_to_cpu(k1->refc.rc_startblock) < + be32_to_cpu(k2->refc.rc_startblock); +} + +STATIC int +xfs_rtrefcountbt_recs_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_rec *r1, + const union xfs_btree_rec *r2) +{ + return be32_to_cpu(r1->refc.rc_startblock) + + be32_to_cpu(r1->refc.rc_blockcount) <= + be32_to_cpu(r2->refc.rc_startblock); +} + +STATIC enum xbtree_key_contig +xfs_rtrefcountbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->refc.rc_startblock); + + return xbtree_key_contig(be32_to_cpu(key1->refc.rc_startblock), + be32_to_cpu(key2->refc.rc_startblock)); +} + +static inline void +xfs_rtrefcountbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_rtrefcount_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_rtrefcount_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_rtrefcount_ptr_t)); +} + +static struct xfs_btree_block * +xfs_rtrefcountbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + const unsigned int level = cur->bc_nlevels - 1; + + new_size = xfs_rtrefcount_broot_space_calc(mp, level, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just allocate + * it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need to + * realloc it and possibly move the node block pointers because + * those are not butted up against the btree block header. + */ + old_numrecs = xfs_rtrefcountbt_maxrecs(mp, old_size, level); + broot = xfs_broot_realloc(ifp, new_size); + if (level > 0) + xfs_rtrefcountbt_move_ptrs(mp, broot, old_size, + new_size, old_numrecs); + goto out_broot; + } + + /* + * We're reducing numrecs. If we're going all the way to zero, just + * free the block. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0); + if (new_size == 0) + return xfs_broot_realloc(ifp, 0); + + /* + * Shrink the btree root by possibly moving the rtrmapbt pointers, + * since they are not butted up against the btree block header. Then + * reallocate broot. + */ + if (level > 0) + xfs_rtrefcountbt_move_ptrs(mp, ifp->if_broot, old_size, + new_size, new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + +out_broot: + ASSERT(xfs_rtrefcount_droot_space(broot) <= + xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); + return broot; +} + +const struct xfs_btree_ops xfs_rtrefcountbt_ops = { + .name = "rtrefcount", + .type = XFS_BTREE_TYPE_INODE, + .geom_flags = XFS_BTGEO_IROOT_RECORDS, + + .rec_len = sizeof(struct xfs_refcount_rec), + .key_len = sizeof(struct xfs_refcount_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_REFC_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrefcbt_2), + .sick_mask = XFS_SICK_RG_REFCNTBT, + + .dup_cursor = xfs_rtrefcountbt_dup_cursor, + .alloc_block = xfs_btree_alloc_metafile_block, + .free_block = xfs_btree_free_metafile_block, + .get_minrecs = xfs_rtrefcountbt_get_minrecs, + .get_maxrecs = xfs_rtrefcountbt_get_maxrecs, + .get_dmaxrecs = xfs_rtrefcountbt_get_dmaxrecs, + .init_key_from_rec = xfs_rtrefcountbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrefcountbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrefcountbt_init_rec_from_cur, + .init_ptr_from_cur = xfs_rtrefcountbt_init_ptr_from_cur, + .cmp_key_with_cur = xfs_rtrefcountbt_cmp_key_with_cur, + .buf_ops = &xfs_rtrefcountbt_buf_ops, + .cmp_two_keys = xfs_rtrefcountbt_cmp_two_keys, + .keys_inorder = xfs_rtrefcountbt_keys_inorder, + .recs_inorder = xfs_rtrefcountbt_recs_inorder, + .keys_contiguous = xfs_rtrefcountbt_keys_contiguous, + .broot_realloc = xfs_rtrefcountbt_broot_realloc, +}; + +/* Allocate a new rt refcount btree cursor. */ +struct xfs_btree_cur * +xfs_rtrefcountbt_init_cursor( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg) +{ + struct xfs_inode *ip = rtg_refcount(rtg); + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrefcountbt_ops, + mp->m_rtrefc_maxlevels, xfs_rtrefcountbt_cur_cache); + + cur->bc_ino.ip = ip; + cur->bc_refc.nr_ops = 0; + cur->bc_refc.shape_changes = 0; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + cur->bc_nlevels = be16_to_cpu(ip->i_df.if_broot->bb_level) + 1; + cur->bc_ino.forksize = xfs_inode_fork_size(ip, XFS_DATA_FORK); + cur->bc_ino.whichfork = XFS_DATA_FORK; + return cur; +} + +/* + * Install a new rt reverse mapping btree root. Caller is responsible for + * invalidating and freeing the old btree blocks. + */ +void +xfs_rtrefcountbt_commit_staged_btree( + struct xfs_btree_cur *cur, + struct xfs_trans *tp) +{ + struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake; + struct xfs_ifork *ifp; + int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; + + ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); + + /* + * Free any resources hanging off the real fork, then shallow-copy the + * staging fork's contents into the real fork to transfer everything + * we just built. + */ + ifp = xfs_ifork_ptr(cur->bc_ino.ip, XFS_DATA_FORK); + xfs_idestroy_fork(ifp); + memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork)); + + cur->bc_ino.ip->i_projid = cur->bc_group->xg_gno; + xfs_trans_log_inode(tp, cur->bc_ino.ip, flags); + xfs_btree_commit_ifakeroot(cur, tp, XFS_DATA_FORK); +} + +/* Calculate number of records in a realtime refcount btree block. */ +static inline unsigned int +xfs_rtrefcountbt_block_maxrecs( + unsigned int blocklen, + bool leaf) +{ + + if (leaf) + return blocklen / sizeof(struct xfs_refcount_rec); + return blocklen / (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Calculate number of records in an refcount btree block. + */ +unsigned int +xfs_rtrefcountbt_maxrecs( + struct xfs_mount *mp, + unsigned int blocklen, + bool leaf) +{ + blocklen -= XFS_RTREFCOUNT_BLOCK_LEN; + return xfs_rtrefcountbt_block_maxrecs(blocklen, leaf); +} + +/* Compute the max possible height for realtime refcount btrees. */ +unsigned int +xfs_rtrefcountbt_maxlevels_ondisk(void) +{ + unsigned int minrecs[2]; + unsigned int blocklen; + + blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; + + minrecs[0] = xfs_rtrefcountbt_block_maxrecs(blocklen, true) / 2; + minrecs[1] = xfs_rtrefcountbt_block_maxrecs(blocklen, false) / 2; + + /* We need at most one record for every block in an rt group. */ + return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_RGBLOCKS); +} + +int __init +xfs_rtrefcountbt_init_cur_cache(void) +{ + xfs_rtrefcountbt_cur_cache = kmem_cache_create("xfs_rtrefcountbt_cur", + xfs_btree_cur_sizeof( + xfs_rtrefcountbt_maxlevels_ondisk()), + 0, 0, NULL); + + if (!xfs_rtrefcountbt_cur_cache) + return -ENOMEM; + return 0; +} + +void +xfs_rtrefcountbt_destroy_cur_cache(void) +{ + kmem_cache_destroy(xfs_rtrefcountbt_cur_cache); + xfs_rtrefcountbt_cur_cache = NULL; +} + +/* Compute the maximum height of a realtime refcount btree. */ +void +xfs_rtrefcountbt_compute_maxlevels( + struct xfs_mount *mp) +{ + unsigned int d_maxlevels, r_maxlevels; + + if (!xfs_has_rtreflink(mp)) { + mp->m_rtrefc_maxlevels = 0; + return; + } + + /* + * The realtime refcountbt lives on the data device, which means that + * its maximum height is constrained by the size of the data device and + * the height required to store one refcount record for each rtextent + * in an rt group. + */ + d_maxlevels = xfs_btree_space_to_height(mp->m_rtrefc_mnr, + mp->m_sb.sb_dblocks); + r_maxlevels = xfs_btree_compute_maxlevels(mp->m_rtrefc_mnr, + mp->m_sb.sb_rgextents); + + /* Add one level to handle the inode root level. */ + mp->m_rtrefc_maxlevels = min(d_maxlevels, r_maxlevels) + 1; +} + +/* Calculate the rtrefcount btree size for some records. */ +unsigned long long +xfs_rtrefcountbt_calc_size( + struct xfs_mount *mp, + unsigned long long len) +{ + return xfs_btree_calc_size(mp->m_rtrefc_mnr, len); +} + +/* + * Calculate the maximum refcount btree size. + */ +static unsigned long long +xfs_rtrefcountbt_max_size( + struct xfs_mount *mp, + xfs_rtblock_t rtblocks) +{ + /* Bail out if we're uninitialized, which can happen in mkfs. */ + if (mp->m_rtrefc_mxr[0] == 0) + return 0; + + return xfs_rtrefcountbt_calc_size(mp, rtblocks); +} + +/* + * Figure out how many blocks to reserve and how many are used by this btree. + * We need enough space to hold one record for every rt extent in the rtgroup. + */ +xfs_filblks_t +xfs_rtrefcountbt_calc_reserves( + struct xfs_mount *mp) +{ + if (!xfs_has_rtreflink(mp)) + return 0; + + return xfs_rtrefcountbt_max_size(mp, mp->m_sb.sb_rgextents); +} + +/* + * Convert on-disk form of btree root to in-memory form. + */ +STATIC void +xfs_rtrefcountbt_from_disk( + struct xfs_inode *ip, + struct xfs_rtrefcount_root *dblock, + int dblocklen, + struct xfs_btree_block *rblock) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_refcount_key *fkp; + __be64 *fpp; + struct xfs_refcount_key *tkp; + __be64 *tpp; + struct xfs_refcount_rec *frp; + struct xfs_refcount_rec *trp; + unsigned int numrecs; + unsigned int maxrecs; + unsigned int rblocklen; + + rblocklen = xfs_rtrefcount_broot_space(mp, dblock); + + xfs_btree_init_block(mp, rblock, &xfs_rtrefcountbt_ops, 0, 0, + ip->i_ino); + + rblock->bb_level = dblock->bb_level; + rblock->bb_numrecs = dblock->bb_numrecs; + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrefcountbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrefcount_droot_key_addr(dblock, 1); + tkp = xfs_rtrefcount_key_addr(rblock, 1); + fpp = xfs_rtrefcount_droot_ptr_addr(dblock, 1, maxrecs); + tpp = xfs_rtrefcount_broot_ptr_addr(mp, rblock, 1, rblocklen); + numrecs = be16_to_cpu(dblock->bb_numrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrefcount_droot_rec_addr(dblock, 1); + trp = xfs_rtrefcount_rec_addr(rblock, 1); + numrecs = be16_to_cpu(dblock->bb_numrecs); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Load a realtime reference count btree root in from disk. */ +int +xfs_iformat_rtrefcount( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rtrefcount_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + struct xfs_btree_block *broot; + unsigned int numrecs; + unsigned int level; + int dsize; + + /* + * growfs must create the rtrefcount inodes before adding a realtime + * volume to the filesystem, so we cannot use the rtrefcount predicate + * here. + */ + if (!xfs_has_reflink(ip->i_mount)) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); + numrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > mp->m_rtrefc_maxlevels || + xfs_rtrefcount_droot_space_calc(level, numrecs) > dsize) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), + xfs_rtrefcount_broot_space_calc(mp, level, numrecs)); + if (broot) + xfs_rtrefcountbt_from_disk(ip, dfp, dsize, broot); + return 0; +} + +/* + * Convert in-memory form of btree root to on-disk form. + */ +void +xfs_rtrefcountbt_to_disk( + struct xfs_mount *mp, + struct xfs_btree_block *rblock, + int rblocklen, + struct xfs_rtrefcount_root *dblock, + int dblocklen) +{ + struct xfs_refcount_key *fkp; + __be64 *fpp; + struct xfs_refcount_key *tkp; + __be64 *tpp; + struct xfs_refcount_rec *frp; + struct xfs_refcount_rec *trp; + unsigned int maxrecs; + unsigned int numrecs; + + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTREFC_CRC_MAGIC)); + ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); + ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); + + dblock->bb_level = rblock->bb_level; + dblock->bb_numrecs = rblock->bb_numrecs; + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrefcountbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrefcount_key_addr(rblock, 1); + tkp = xfs_rtrefcount_droot_key_addr(dblock, 1); + fpp = xfs_rtrefcount_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_rtrefcount_droot_ptr_addr(dblock, 1, maxrecs); + numrecs = be16_to_cpu(rblock->bb_numrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrefcount_rec_addr(rblock, 1); + trp = xfs_rtrefcount_droot_rec_addr(dblock, 1); + numrecs = be16_to_cpu(rblock->bb_numrecs); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Flush a realtime reference count btree root out to disk. */ +void +xfs_iflush_rtrefcount( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_rtrefcount_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + + ASSERT(ifp->if_broot != NULL); + ASSERT(ifp->if_broot_bytes > 0); + ASSERT(xfs_rtrefcount_droot_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, XFS_DATA_FORK)); + xfs_rtrefcountbt_to_disk(ip->i_mount, ifp->if_broot, + ifp->if_broot_bytes, dfp, + XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); +} + +/* + * Create a realtime refcount btree inode. + */ +int +xfs_rtrefcountbt_create( + struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_mount *mp = ip->i_mount; + struct xfs_btree_block *broot; + + ifp->if_format = XFS_DINODE_FMT_META_BTREE; + ASSERT(ifp->if_broot_bytes == 0); + ASSERT(ifp->if_bytes == 0); + + /* Initialize the empty incore btree root. */ + broot = xfs_broot_realloc(ifp, + xfs_rtrefcount_broot_space_calc(mp, 0, 0)); + if (broot) + xfs_btree_init_block(mp, broot, &xfs_rtrefcountbt_ops, 0, 0, + ip->i_ino); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE | XFS_ILOG_DBROOT); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.h b/fs/xfs/libxfs/xfs_rtrefcount_btree.h new file mode 100644 index 000000000000..a99b7a8aec86 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.h @@ -0,0 +1,189 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_RTREFCOUNT_BTREE_H__ +#define __XFS_RTREFCOUNT_BTREE_H__ + +struct xfs_buf; +struct xfs_btree_cur; +struct xfs_mount; +struct xbtree_ifakeroot; +struct xfs_rtgroup; + +/* refcounts only exist on crc enabled filesystems */ +#define XFS_RTREFCOUNT_BLOCK_LEN XFS_BTREE_LBLOCK_CRC_LEN + +struct xfs_btree_cur *xfs_rtrefcountbt_init_cursor(struct xfs_trans *tp, + struct xfs_rtgroup *rtg); +struct xfs_btree_cur *xfs_rtrefcountbt_stage_cursor(struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xbtree_ifakeroot *ifake); +void xfs_rtrefcountbt_commit_staged_btree(struct xfs_btree_cur *cur, + struct xfs_trans *tp); +unsigned int xfs_rtrefcountbt_maxrecs(struct xfs_mount *mp, + unsigned int blocklen, bool leaf); +void xfs_rtrefcountbt_compute_maxlevels(struct xfs_mount *mp); +unsigned int xfs_rtrefcountbt_droot_maxrecs(unsigned int blocklen, bool leaf); + +/* + * Addresses of records, keys, and pointers within an incore rtrefcountbt block. + * + * (note that some of these may appear unused, but they are used in userspace) + */ +static inline struct xfs_refcount_rec * +xfs_rtrefcount_rec_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_refcount_rec *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_refcount_rec)); +} + +static inline struct xfs_refcount_key * +xfs_rtrefcount_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_refcount_key *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_refcount_key)); +} + +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_ptr_addr( + struct xfs_btree_block *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrefcount_ptr_t *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + maxrecs * sizeof(struct xfs_refcount_key) + + (index - 1) * sizeof(xfs_rtrefcount_ptr_t)); +} + +unsigned int xfs_rtrefcountbt_maxlevels_ondisk(void); +int __init xfs_rtrefcountbt_init_cur_cache(void); +void xfs_rtrefcountbt_destroy_cur_cache(void); + +xfs_filblks_t xfs_rtrefcountbt_calc_reserves(struct xfs_mount *mp); +unsigned long long xfs_rtrefcountbt_calc_size(struct xfs_mount *mp, + unsigned long long len); + +/* Addresses of key, pointers, and records within an ondisk rtrefcount block. */ + +static inline struct xfs_refcount_rec * +xfs_rtrefcount_droot_rec_addr( + struct xfs_rtrefcount_root *block, + unsigned int index) +{ + return (struct xfs_refcount_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_refcount_rec)); +} + +static inline struct xfs_refcount_key * +xfs_rtrefcount_droot_key_addr( + struct xfs_rtrefcount_root *block, + unsigned int index) +{ + return (struct xfs_refcount_key *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_refcount_key)); +} + +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_droot_ptr_addr( + struct xfs_rtrefcount_root *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrefcount_ptr_t *) + ((char *)(block + 1) + + maxrecs * sizeof(struct xfs_refcount_key) + + (index - 1) * sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int index, + unsigned int block_size) +{ + return xfs_rtrefcount_ptr_addr(bb, index, + xfs_rtrefcountbt_maxrecs(mp, block_size, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_rtrefcount_broot_space_calc( + struct xfs_mount *mp, + unsigned int level, + unsigned int nrecs) +{ + size_t sz = XFS_RTREFCOUNT_BLOCK_LEN; + + if (level > 0) + return sz + nrecs * (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); + return sz + nrecs * sizeof(struct xfs_refcount_rec); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_rtrefcount_broot_space(struct xfs_mount *mp, struct xfs_rtrefcount_root *bb) +{ + return xfs_rtrefcount_broot_space_calc(mp, be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_rtrefcount_droot_space_calc( + unsigned int level, + unsigned int nrecs) +{ + size_t sz = sizeof(struct xfs_rtrefcount_root); + + if (level > 0) + return sz + nrecs * (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); + return sz + nrecs * sizeof(struct xfs_refcount_rec); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_rtrefcount_droot_space(struct xfs_btree_block *bb) +{ + return xfs_rtrefcount_droot_space_calc(be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +int xfs_iformat_rtrefcount(struct xfs_inode *ip, struct xfs_dinode *dip); +void xfs_rtrefcountbt_to_disk(struct xfs_mount *mp, + struct xfs_btree_block *rblock, int rblocklen, + struct xfs_rtrefcount_root *dblock, int dblocklen); +void xfs_iflush_rtrefcount(struct xfs_inode *ip, struct xfs_dinode *dip); + +int xfs_rtrefcountbt_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xfs_trans *tp, bool init); + +#endif /* __XFS_RTREFCOUNT_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c new file mode 100644 index 000000000000..55f903165769 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c @@ -0,0 +1,1033 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_alloc.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_metafile.h" +#include "xfs_rmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_trace.h" +#include "xfs_cksum.h" +#include "xfs_error.h" +#include "xfs_extent_busy.h" +#include "xfs_rtgroup.h" +#include "xfs_bmap.h" +#include "xfs_health.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" + +static struct kmem_cache *xfs_rtrmapbt_cur_cache; + +/* + * Realtime Reverse Map btree. + * + * This is a btree used to track the owner(s) of a given extent in the realtime + * device. See the comments in xfs_rmap_btree.c for more information. + * + * This tree is basically the same as the regular rmap btree except that it + * is rooted in an inode and does not live in free space. + */ + +static struct xfs_btree_cur * +xfs_rtrmapbt_dup_cursor( + struct xfs_btree_cur *cur) +{ + return xfs_rtrmapbt_init_cursor(cur->bc_tp, to_rtg(cur->bc_group)); +} + +STATIC int +xfs_rtrmapbt_get_minrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrmapbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0) / 2; + } + + return cur->bc_mp->m_rtrmap_mnr[level != 0]; +} + +STATIC int +xfs_rtrmapbt_get_maxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrmapbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0); + } + + return cur->bc_mp->m_rtrmap_mxr[level != 0]; +} + +/* Calculate number of records in the ondisk realtime rmap btree inode root. */ +unsigned int +xfs_rtrmapbt_droot_maxrecs( + unsigned int blocklen, + bool leaf) +{ + blocklen -= sizeof(struct xfs_rtrmap_root); + + if (leaf) + return blocklen / sizeof(struct xfs_rmap_rec); + return blocklen / (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Get the maximum records we could store in the on-disk format. + * + * For non-root nodes this is equivalent to xfs_rtrmapbt_get_maxrecs, but + * for the root node this checks the available space in the dinode fork + * so that we can resize the in-memory buffer to match it. After a + * resize to the maximum size this function returns the same value + * as xfs_rtrmapbt_get_maxrecs for the root node, too. + */ +STATIC int +xfs_rtrmapbt_get_dmaxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level != cur->bc_nlevels - 1) + return cur->bc_mp->m_rtrmap_mxr[level != 0]; + return xfs_rtrmapbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); +} + +/* + * Convert the ondisk record's offset field into the ondisk key's offset field. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline __be64 ondisk_rec_offset_to_key(const union xfs_btree_rec *rec) +{ + return rec->rmap.rm_offset & ~cpu_to_be64(XFS_RMAP_OFF_UNWRITTEN); +} + +STATIC void +xfs_rtrmapbt_init_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + key->rmap.rm_startblock = rec->rmap.rm_startblock; + key->rmap.rm_owner = rec->rmap.rm_owner; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); +} + +STATIC void +xfs_rtrmapbt_init_high_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + uint64_t off; + int adj; + + adj = be32_to_cpu(rec->rmap.rm_blockcount) - 1; + + key->rmap.rm_startblock = rec->rmap.rm_startblock; + be32_add_cpu(&key->rmap.rm_startblock, adj); + key->rmap.rm_owner = rec->rmap.rm_owner; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); + if (XFS_RMAP_NON_INODE_OWNER(be64_to_cpu(rec->rmap.rm_owner)) || + XFS_RMAP_IS_BMBT_BLOCK(be64_to_cpu(rec->rmap.rm_offset))) + return; + off = be64_to_cpu(key->rmap.rm_offset); + off = (XFS_RMAP_OFF(off) + adj) | (off & ~XFS_RMAP_OFF_MASK); + key->rmap.rm_offset = cpu_to_be64(off); +} + +STATIC void +xfs_rtrmapbt_init_rec_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_rec *rec) +{ + rec->rmap.rm_startblock = cpu_to_be32(cur->bc_rec.r.rm_startblock); + rec->rmap.rm_blockcount = cpu_to_be32(cur->bc_rec.r.rm_blockcount); + rec->rmap.rm_owner = cpu_to_be64(cur->bc_rec.r.rm_owner); + rec->rmap.rm_offset = cpu_to_be64( + xfs_rmap_irec_offset_pack(&cur->bc_rec.r)); +} + +STATIC void +xfs_rtrmapbt_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + ptr->l = 0; +} + +/* + * Mask the appropriate parts of the ondisk key field for a key comparison. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline uint64_t offset_keymask(uint64_t offset) +{ + return offset & ~XFS_RMAP_OFF_UNWRITTEN; +} + +STATIC int +xfs_rtrmapbt_cmp_key_with_cur( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key) +{ + struct xfs_rmap_irec *rec = &cur->bc_rec.r; + const struct xfs_rmap_key *kp = &key->rmap; + + return cmp_int(be32_to_cpu(kp->rm_startblock), rec->rm_startblock) ?: + cmp_int(be64_to_cpu(kp->rm_owner), rec->rm_owner) ?: + cmp_int(offset_keymask(be64_to_cpu(kp->rm_offset)), + offset_keymask(xfs_rmap_irec_offset_pack(rec))); +} + +STATIC int +xfs_rtrmapbt_cmp_two_keys( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) +{ + const struct xfs_rmap_key *kp1 = &k1->rmap; + const struct xfs_rmap_key *kp2 = &k2->rmap; + int d; + + /* Doesn't make sense to mask off the physical space part */ + ASSERT(!mask || mask->rmap.rm_startblock); + + d = cmp_int(be32_to_cpu(kp1->rm_startblock), + be32_to_cpu(kp2->rm_startblock)); + if (d) + return d; + + if (!mask || mask->rmap.rm_owner) { + d = cmp_int(be64_to_cpu(kp1->rm_owner), + be64_to_cpu(kp2->rm_owner)); + if (d) + return d; + } + + if (!mask || mask->rmap.rm_offset) { + /* Doesn't make sense to allow offset but not owner */ + ASSERT(!mask || mask->rmap.rm_owner); + + d = cmp_int(offset_keymask(be64_to_cpu(kp1->rm_offset)), + offset_keymask(be64_to_cpu(kp2->rm_offset))); + if (d) + return d; + } + + return 0; +} + +static xfs_failaddr_t +xfs_rtrmapbt_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + int level; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + if (!xfs_has_rmapbt(mp)) + return __this_address; + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + level = be16_to_cpu(block->bb_level); + if (level > mp->m_rtrmap_maxlevels) + return __this_address; + + return xfs_btree_fsblock_verify(bp, mp->m_rtrmap_mxr[level != 0]); +} + +static void +xfs_rtrmapbt_read_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + if (!xfs_btree_fsblock_verify_crc(bp)) + xfs_verifier_error(bp, -EFSBADCRC, __this_address); + else { + fa = xfs_rtrmapbt_verify(bp); + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + } + + if (bp->b_error) + trace_xfs_btree_corrupt(bp, _RET_IP_); +} + +static void +xfs_rtrmapbt_write_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + fa = xfs_rtrmapbt_verify(bp); + if (fa) { + trace_xfs_btree_corrupt(bp, _RET_IP_); + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + xfs_btree_fsblock_calc_crc(bp); + +} + +const struct xfs_buf_ops xfs_rtrmapbt_buf_ops = { + .name = "xfs_rtrmapbt", + .magic = { 0, cpu_to_be32(XFS_RTRMAP_CRC_MAGIC) }, + .verify_read = xfs_rtrmapbt_read_verify, + .verify_write = xfs_rtrmapbt_write_verify, + .verify_struct = xfs_rtrmapbt_verify, +}; + +STATIC int +xfs_rtrmapbt_keys_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2) +{ + uint32_t x; + uint32_t y; + uint64_t a; + uint64_t b; + + x = be32_to_cpu(k1->rmap.rm_startblock); + y = be32_to_cpu(k2->rmap.rm_startblock); + if (x < y) + return 1; + else if (x > y) + return 0; + a = be64_to_cpu(k1->rmap.rm_owner); + b = be64_to_cpu(k2->rmap.rm_owner); + if (a < b) + return 1; + else if (a > b) + return 0; + a = offset_keymask(be64_to_cpu(k1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(k2->rmap.rm_offset)); + if (a <= b) + return 1; + return 0; +} + +STATIC int +xfs_rtrmapbt_recs_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_rec *r1, + const union xfs_btree_rec *r2) +{ + uint32_t x; + uint32_t y; + uint64_t a; + uint64_t b; + + x = be32_to_cpu(r1->rmap.rm_startblock); + y = be32_to_cpu(r2->rmap.rm_startblock); + if (x < y) + return 1; + else if (x > y) + return 0; + a = be64_to_cpu(r1->rmap.rm_owner); + b = be64_to_cpu(r2->rmap.rm_owner); + if (a < b) + return 1; + else if (a > b) + return 0; + a = offset_keymask(be64_to_cpu(r1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(r2->rmap.rm_offset)); + if (a <= b) + return 1; + return 0; +} + +STATIC enum xbtree_key_contig +xfs_rtrmapbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->rmap.rm_startblock); + + /* + * We only support checking contiguity of the physical space component. + * If any callers ever need more specificity than that, they'll have to + * implement it here. + */ + ASSERT(!mask || (!mask->rmap.rm_owner && !mask->rmap.rm_offset)); + + return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock), + be32_to_cpu(key2->rmap.rm_startblock)); +} + +static inline void +xfs_rtrmapbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_rtrmap_ptr_t)); +} + +static struct xfs_btree_block * +xfs_rtrmapbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + const unsigned int level = cur->bc_nlevels - 1; + + new_size = xfs_rtrmap_broot_space_calc(mp, level, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just allocate + * it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need to + * realloc it and possibly move the node block pointers because + * those are not butted up against the btree block header. + */ + old_numrecs = xfs_rtrmapbt_maxrecs(mp, old_size, level == 0); + broot = xfs_broot_realloc(ifp, new_size); + if (level > 0) + xfs_rtrmapbt_move_ptrs(mp, broot, old_size, new_size, + old_numrecs); + goto out_broot; + } + + /* + * We're reducing numrecs. If we're going all the way to zero, just + * free the block. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0); + if (new_size == 0) + return xfs_broot_realloc(ifp, 0); + + /* + * Shrink the btree root by possibly moving the rtrmapbt pointers, + * since they are not butted up against the btree block header. Then + * reallocate broot. + */ + if (level > 0) + xfs_rtrmapbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, + new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + +out_broot: + ASSERT(xfs_rtrmap_droot_space(broot) <= + xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); + return broot; +} + +const struct xfs_btree_ops xfs_rtrmapbt_ops = { + .name = "rtrmap", + .type = XFS_BTREE_TYPE_INODE, + .geom_flags = XFS_BTGEO_OVERLAPPING | + XFS_BTGEO_IROOT_RECORDS, + + .rec_len = sizeof(struct xfs_rmap_rec), + /* Overlapping btree; 2 keys per pointer. */ + .key_len = 2 * sizeof(struct xfs_rmap_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_RMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrmap_2), + .sick_mask = XFS_SICK_RG_RMAPBT, + + .dup_cursor = xfs_rtrmapbt_dup_cursor, + .alloc_block = xfs_btree_alloc_metafile_block, + .free_block = xfs_btree_free_metafile_block, + .get_minrecs = xfs_rtrmapbt_get_minrecs, + .get_maxrecs = xfs_rtrmapbt_get_maxrecs, + .get_dmaxrecs = xfs_rtrmapbt_get_dmaxrecs, + .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, + .init_ptr_from_cur = xfs_rtrmapbt_init_ptr_from_cur, + .cmp_key_with_cur = xfs_rtrmapbt_cmp_key_with_cur, + .buf_ops = &xfs_rtrmapbt_buf_ops, + .cmp_two_keys = xfs_rtrmapbt_cmp_two_keys, + .keys_inorder = xfs_rtrmapbt_keys_inorder, + .recs_inorder = xfs_rtrmapbt_recs_inorder, + .keys_contiguous = xfs_rtrmapbt_keys_contiguous, + .broot_realloc = xfs_rtrmapbt_broot_realloc, +}; + +/* Allocate a new rt rmap btree cursor. */ +struct xfs_btree_cur * +xfs_rtrmapbt_init_cursor( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg) +{ + struct xfs_inode *ip = rtg_rmap(rtg); + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_ops, + mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + + cur->bc_ino.ip = ip; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + cur->bc_ino.whichfork = XFS_DATA_FORK; + cur->bc_nlevels = be16_to_cpu(ip->i_df.if_broot->bb_level) + 1; + cur->bc_ino.forksize = xfs_inode_fork_size(ip, XFS_DATA_FORK); + + return cur; +} + +#ifdef CONFIG_XFS_BTREE_IN_MEM +/* + * Validate an in-memory realtime rmap btree block. Callers are allowed to + * generate an in-memory btree even if the ondisk feature is not enabled. + */ +static xfs_failaddr_t +xfs_rtrmapbt_mem_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + unsigned int level; + unsigned int maxrecs; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + + level = be16_to_cpu(block->bb_level); + if (xfs_has_rmapbt(mp)) { + if (level >= mp->m_rtrmap_maxlevels) + return __this_address; + } else { + if (level >= xfs_rtrmapbt_maxlevels_ondisk()) + return __this_address; + } + + maxrecs = xfs_rtrmapbt_maxrecs(mp, XFBNO_BLOCKSIZE, level == 0); + return xfs_btree_memblock_verify(bp, maxrecs); +} + +static void +xfs_rtrmapbt_mem_rw_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa = xfs_rtrmapbt_mem_verify(bp); + + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); +} + +/* skip crc checks on in-memory btrees to save time */ +static const struct xfs_buf_ops xfs_rtrmapbt_mem_buf_ops = { + .name = "xfs_rtrmapbt_mem", + .magic = { 0, cpu_to_be32(XFS_RTRMAP_CRC_MAGIC) }, + .verify_read = xfs_rtrmapbt_mem_rw_verify, + .verify_write = xfs_rtrmapbt_mem_rw_verify, + .verify_struct = xfs_rtrmapbt_mem_verify, +}; + +const struct xfs_btree_ops xfs_rtrmapbt_mem_ops = { + .type = XFS_BTREE_TYPE_MEM, + .geom_flags = XFS_BTGEO_OVERLAPPING, + + .rec_len = sizeof(struct xfs_rmap_rec), + /* Overlapping btree; 2 keys per pointer. */ + .key_len = 2 * sizeof(struct xfs_rmap_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_RMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrmap_mem_2), + + .dup_cursor = xfbtree_dup_cursor, + .set_root = xfbtree_set_root, + .alloc_block = xfbtree_alloc_block, + .free_block = xfbtree_free_block, + .get_minrecs = xfbtree_get_minrecs, + .get_maxrecs = xfbtree_get_maxrecs, + .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, + .init_ptr_from_cur = xfbtree_init_ptr_from_cur, + .cmp_key_with_cur = xfs_rtrmapbt_cmp_key_with_cur, + .buf_ops = &xfs_rtrmapbt_mem_buf_ops, + .cmp_two_keys = xfs_rtrmapbt_cmp_two_keys, + .keys_inorder = xfs_rtrmapbt_keys_inorder, + .recs_inorder = xfs_rtrmapbt_recs_inorder, + .keys_contiguous = xfs_rtrmapbt_keys_contiguous, +}; + +/* Create a cursor for an in-memory btree. */ +struct xfs_btree_cur * +xfs_rtrmapbt_mem_cursor( + struct xfs_rtgroup *rtg, + struct xfs_trans *tp, + struct xfbtree *xfbt) +{ + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_mem_ops, + mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + cur->bc_mem.xfbtree = xfbt; + cur->bc_nlevels = xfbt->nlevels; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + return cur; +} + +/* Create an in-memory realtime rmap btree. */ +int +xfs_rtrmapbt_mem_init( + struct xfs_mount *mp, + struct xfbtree *xfbt, + struct xfs_buftarg *btp, + xfs_rgnumber_t rgno) +{ + xfbt->owner = rgno; + return xfbtree_init(mp, xfbt, btp, &xfs_rtrmapbt_mem_ops); +} +#endif /* CONFIG_XFS_BTREE_IN_MEM */ + +/* + * Install a new rt reverse mapping btree root. Caller is responsible for + * invalidating and freeing the old btree blocks. + */ +void +xfs_rtrmapbt_commit_staged_btree( + struct xfs_btree_cur *cur, + struct xfs_trans *tp) +{ + struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake; + struct xfs_ifork *ifp; + int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; + + ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); + + /* + * Free any resources hanging off the real fork, then shallow-copy the + * staging fork's contents into the real fork to transfer everything + * we just built. + */ + ifp = xfs_ifork_ptr(cur->bc_ino.ip, XFS_DATA_FORK); + xfs_idestroy_fork(ifp); + memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork)); + + cur->bc_ino.ip->i_projid = cur->bc_group->xg_gno; + xfs_trans_log_inode(tp, cur->bc_ino.ip, flags); + xfs_btree_commit_ifakeroot(cur, tp, XFS_DATA_FORK); +} + +/* Calculate number of records in a rt reverse mapping btree block. */ +static inline unsigned int +xfs_rtrmapbt_block_maxrecs( + unsigned int blocklen, + bool leaf) +{ + if (leaf) + return blocklen / sizeof(struct xfs_rmap_rec); + return blocklen / + (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Calculate number of records in an rt reverse mapping btree block. + */ +unsigned int +xfs_rtrmapbt_maxrecs( + struct xfs_mount *mp, + unsigned int blocklen, + bool leaf) +{ + blocklen -= XFS_RTRMAP_BLOCK_LEN; + return xfs_rtrmapbt_block_maxrecs(blocklen, leaf); +} + +/* Compute the max possible height for realtime reverse mapping btrees. */ +unsigned int +xfs_rtrmapbt_maxlevels_ondisk(void) +{ + unsigned long long max_dblocks; + unsigned int minrecs[2]; + unsigned int blocklen; + + blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; + + minrecs[0] = xfs_rtrmapbt_block_maxrecs(blocklen, true) / 2; + minrecs[1] = xfs_rtrmapbt_block_maxrecs(blocklen, false) / 2; + + /* + * Compute the asymptotic maxlevels for an rtrmapbt on any rtreflink fs. + * + * On a reflink filesystem, each block in an rtgroup can have up to + * 2^32 (per the refcount record format) owners, which means that + * theoretically we could face up to 2^64 rmap records. However, we're + * likely to run out of blocks in the data device long before that + * happens, which means that we must compute the max height based on + * what the btree will look like if it consumes almost all the blocks + * in the data device due to maximal sharing factor. + */ + max_dblocks = -1U; /* max ag count */ + max_dblocks *= XFS_MAX_CRC_AG_BLOCKS; + return xfs_btree_space_to_height(minrecs, max_dblocks); +} + +int __init +xfs_rtrmapbt_init_cur_cache(void) +{ + xfs_rtrmapbt_cur_cache = kmem_cache_create("xfs_rtrmapbt_cur", + xfs_btree_cur_sizeof(xfs_rtrmapbt_maxlevels_ondisk()), + 0, 0, NULL); + + if (!xfs_rtrmapbt_cur_cache) + return -ENOMEM; + return 0; +} + +void +xfs_rtrmapbt_destroy_cur_cache(void) +{ + kmem_cache_destroy(xfs_rtrmapbt_cur_cache); + xfs_rtrmapbt_cur_cache = NULL; +} + +/* Compute the maximum height of an rt reverse mapping btree. */ +void +xfs_rtrmapbt_compute_maxlevels( + struct xfs_mount *mp) +{ + unsigned int d_maxlevels, r_maxlevels; + + if (!xfs_has_rtrmapbt(mp)) { + mp->m_rtrmap_maxlevels = 0; + return; + } + + /* + * The realtime rmapbt lives on the data device, which means that its + * maximum height is constrained by the size of the data device and + * the height required to store one rmap record for each block in an + * rt group. + * + * On a reflink filesystem, each rt block can have up to 2^32 (per the + * refcount record format) owners, which means that theoretically we + * could face up to 2^64 rmap records. This makes the computation of + * maxlevels based on record count meaningless, so we only consider the + * size of the data device. + */ + d_maxlevels = xfs_btree_space_to_height(mp->m_rtrmap_mnr, + mp->m_sb.sb_dblocks); + if (xfs_has_rtreflink(mp)) { + mp->m_rtrmap_maxlevels = d_maxlevels + 1; + return; + } + + r_maxlevels = xfs_btree_compute_maxlevels(mp->m_rtrmap_mnr, + mp->m_groups[XG_TYPE_RTG].blocks); + + /* Add one level to handle the inode root level. */ + mp->m_rtrmap_maxlevels = min(d_maxlevels, r_maxlevels) + 1; +} + +/* Calculate the rtrmap btree size for some records. */ +unsigned long long +xfs_rtrmapbt_calc_size( + struct xfs_mount *mp, + unsigned long long len) +{ + return xfs_btree_calc_size(mp->m_rtrmap_mnr, len); +} + +/* + * Calculate the maximum rmap btree size. + */ +static unsigned long long +xfs_rtrmapbt_max_size( + struct xfs_mount *mp, + xfs_rtblock_t rtblocks) +{ + /* Bail out if we're uninitialized, which can happen in mkfs. */ + if (mp->m_rtrmap_mxr[0] == 0) + return 0; + + return xfs_rtrmapbt_calc_size(mp, rtblocks); +} + +/* + * Figure out how many blocks to reserve and how many are used by this btree. + */ +xfs_filblks_t +xfs_rtrmapbt_calc_reserves( + struct xfs_mount *mp) +{ + uint32_t blocks = mp->m_groups[XG_TYPE_RTG].blocks; + + if (!xfs_has_rtrmapbt(mp)) + return 0; + + /* Reserve 1% of the rtgroup or enough for 1 block per record. */ + return max_t(xfs_filblks_t, blocks / 100, + xfs_rtrmapbt_max_size(mp, blocks)); +} + +/* Convert on-disk form of btree root to in-memory form. */ +STATIC void +xfs_rtrmapbt_from_disk( + struct xfs_inode *ip, + struct xfs_rtrmap_root *dblock, + unsigned int dblocklen, + struct xfs_btree_block *rblock) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rmap_key *fkp; + __be64 *fpp; + struct xfs_rmap_key *tkp; + __be64 *tpp; + struct xfs_rmap_rec *frp; + struct xfs_rmap_rec *trp; + unsigned int rblocklen = xfs_rtrmap_broot_space(mp, dblock); + unsigned int numrecs; + unsigned int maxrecs; + + xfs_btree_init_block(mp, rblock, &xfs_rtrmapbt_ops, 0, 0, ip->i_ino); + + rblock->bb_level = dblock->bb_level; + rblock->bb_numrecs = dblock->bb_numrecs; + numrecs = be16_to_cpu(dblock->bb_numrecs); + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrmap_droot_key_addr(dblock, 1); + tkp = xfs_rtrmap_key_addr(rblock, 1); + fpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); + tpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrmap_droot_rec_addr(dblock, 1); + trp = xfs_rtrmap_rec_addr(rblock, 1); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Load a realtime reverse mapping btree root in from disk. */ +int +xfs_iformat_rtrmap( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + struct xfs_btree_block *broot; + unsigned int numrecs; + unsigned int level; + int dsize; + + /* + * growfs must create the rtrmap inodes before adding a realtime volume + * to the filesystem, so we cannot use the rtrmapbt predicate here. + */ + if (!xfs_has_rmapbt(ip->i_mount)) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); + numrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > mp->m_rtrmap_maxlevels || + xfs_rtrmap_droot_space_calc(level, numrecs) > dsize) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), + xfs_rtrmap_broot_space_calc(mp, level, numrecs)); + if (broot) + xfs_rtrmapbt_from_disk(ip, dfp, dsize, broot); + return 0; +} + +/* Convert in-memory form of btree root to on-disk form. */ +void +xfs_rtrmapbt_to_disk( + struct xfs_mount *mp, + struct xfs_btree_block *rblock, + unsigned int rblocklen, + struct xfs_rtrmap_root *dblock, + unsigned int dblocklen) +{ + struct xfs_rmap_key *fkp; + __be64 *fpp; + struct xfs_rmap_key *tkp; + __be64 *tpp; + struct xfs_rmap_rec *frp; + struct xfs_rmap_rec *trp; + unsigned int numrecs; + unsigned int maxrecs; + + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTRMAP_CRC_MAGIC)); + ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); + ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); + + dblock->bb_level = rblock->bb_level; + dblock->bb_numrecs = rblock->bb_numrecs; + numrecs = be16_to_cpu(rblock->bb_numrecs); + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrmap_key_addr(rblock, 1); + tkp = xfs_rtrmap_droot_key_addr(dblock, 1); + fpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrmap_rec_addr(rblock, 1); + trp = xfs_rtrmap_droot_rec_addr(dblock, 1); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Flush a realtime reverse mapping btree root out to disk. */ +void +xfs_iflush_rtrmap( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + + ASSERT(ifp->if_broot != NULL); + ASSERT(ifp->if_broot_bytes > 0); + ASSERT(xfs_rtrmap_droot_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, XFS_DATA_FORK)); + xfs_rtrmapbt_to_disk(ip->i_mount, ifp->if_broot, ifp->if_broot_bytes, + dfp, XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); +} + +/* + * Create a realtime rmap btree inode. + */ +int +xfs_rtrmapbt_create( + struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_mount *mp = ip->i_mount; + struct xfs_btree_block *broot; + + ifp->if_format = XFS_DINODE_FMT_META_BTREE; + ASSERT(ifp->if_broot_bytes == 0); + ASSERT(ifp->if_bytes == 0); + + /* Initialize the empty incore btree root. */ + broot = xfs_broot_realloc(ifp, xfs_rtrmap_broot_space_calc(mp, 0, 0)); + if (broot) + xfs_btree_init_block(mp, broot, &xfs_rtrmapbt_ops, 0, 0, + ip->i_ino); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE | XFS_ILOG_DBROOT); + + return 0; +} + +/* + * Initialize an rmap for a realtime superblock using the potentially updated + * rt geometry in the provided @mp. + */ +int +xfs_rtrmapbt_init_rtsb( + struct xfs_mount *mp, + struct xfs_rtgroup *rtg, + struct xfs_trans *tp) +{ + struct xfs_rmap_irec rmap = { + .rm_blockcount = mp->m_sb.sb_rextsize, + .rm_owner = XFS_RMAP_OWN_FS, + }; + struct xfs_btree_cur *cur; + int error; + + ASSERT(xfs_has_rtsb(mp)); + ASSERT(rtg_rgno(rtg) == 0); + + cur = xfs_rtrmapbt_init_cursor(tp, rtg); + error = xfs_rmap_map_raw(cur, &rmap); + xfs_btree_del_cursor(cur, error); + return error; +} + +/* + * Return the highest rgbno currently tracked by the rmap for this rtg. + */ +xfs_rgblock_t +xfs_rtrmap_highest_rgbno( + struct xfs_rtgroup *rtg) +{ + struct xfs_btree_block *block = rtg_rmap(rtg)->i_df.if_broot; + union xfs_btree_key key = {}; + struct xfs_btree_cur *cur; + + if (block->bb_numrecs == 0) + return NULLRGBLOCK; + cur = xfs_rtrmapbt_init_cursor(NULL, rtg); + xfs_btree_get_keys(cur, block, &key); + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + return be32_to_cpu(key.__rmap_bigkey[1].rm_startblock); +} diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.h b/fs/xfs/libxfs/xfs_rtrmap_btree.h new file mode 100644 index 000000000000..e328fd62a149 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.h @@ -0,0 +1,212 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_RTRMAP_BTREE_H__ +#define __XFS_RTRMAP_BTREE_H__ + +struct xfs_buf; +struct xfs_btree_cur; +struct xfs_mount; +struct xbtree_ifakeroot; +struct xfs_rtgroup; +struct xfbtree; + +/* rmaps only exist on crc enabled filesystems */ +#define XFS_RTRMAP_BLOCK_LEN XFS_BTREE_LBLOCK_CRC_LEN + +struct xfs_btree_cur *xfs_rtrmapbt_init_cursor(struct xfs_trans *tp, + struct xfs_rtgroup *rtg); +struct xfs_btree_cur *xfs_rtrmapbt_stage_cursor(struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xbtree_ifakeroot *ifake); +void xfs_rtrmapbt_commit_staged_btree(struct xfs_btree_cur *cur, + struct xfs_trans *tp); +unsigned int xfs_rtrmapbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, + bool leaf); +void xfs_rtrmapbt_compute_maxlevels(struct xfs_mount *mp); +unsigned int xfs_rtrmapbt_droot_maxrecs(unsigned int blocklen, bool leaf); + +/* + * Addresses of records, keys, and pointers within an incore rtrmapbt block. + * + * (note that some of these may appear unused, but they are used in userspace) + */ +static inline struct xfs_rmap_rec * +xfs_rtrmap_rec_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_rec *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_rmap_rec)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_high_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + sizeof(struct xfs_rmap_key) + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_ptr_addr( + struct xfs_btree_block *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrmap_ptr_t *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + maxrecs * 2 * sizeof(struct xfs_rmap_key) + + (index - 1) * sizeof(xfs_rtrmap_ptr_t)); +} + +unsigned int xfs_rtrmapbt_maxlevels_ondisk(void); + +int __init xfs_rtrmapbt_init_cur_cache(void); +void xfs_rtrmapbt_destroy_cur_cache(void); + +xfs_filblks_t xfs_rtrmapbt_calc_reserves(struct xfs_mount *mp); + +/* Addresses of key, pointers, and records within an ondisk rtrmapbt block. */ + +static inline struct xfs_rmap_rec * +xfs_rtrmap_droot_rec_addr( + struct xfs_rtrmap_root *block, + unsigned int index) +{ + return (struct xfs_rmap_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_rmap_rec)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_droot_key_addr( + struct xfs_rtrmap_root *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)(block + 1) + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_droot_ptr_addr( + struct xfs_rtrmap_root *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrmap_ptr_t *) + ((char *)(block + 1) + + maxrecs * 2 * sizeof(struct xfs_rmap_key) + + (index - 1) * sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int index, + unsigned int block_size) +{ + return xfs_rtrmap_ptr_addr(bb, index, + xfs_rtrmapbt_maxrecs(mp, block_size, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_rtrmap_broot_space_calc( + struct xfs_mount *mp, + unsigned int level, + unsigned int nrecs) +{ + size_t sz = XFS_RTRMAP_BLOCK_LEN; + + if (level > 0) + return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); + return sz + nrecs * sizeof(struct xfs_rmap_rec); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_rtrmap_broot_space(struct xfs_mount *mp, struct xfs_rtrmap_root *bb) +{ + return xfs_rtrmap_broot_space_calc(mp, be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_rtrmap_droot_space_calc( + unsigned int level, + unsigned int nrecs) +{ + size_t sz = sizeof(struct xfs_rtrmap_root); + + if (level > 0) + return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); + return sz + nrecs * sizeof(struct xfs_rmap_rec); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_rtrmap_droot_space(struct xfs_btree_block *bb) +{ + return xfs_rtrmap_droot_space_calc(be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +int xfs_iformat_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip); +void xfs_rtrmapbt_to_disk(struct xfs_mount *mp, struct xfs_btree_block *rblock, + unsigned int rblocklen, struct xfs_rtrmap_root *dblock, + unsigned int dblocklen); +void xfs_iflush_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip); + +int xfs_rtrmapbt_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xfs_trans *tp, bool init); +int xfs_rtrmapbt_init_rtsb(struct xfs_mount *mp, struct xfs_rtgroup *rtg, + struct xfs_trans *tp); + +unsigned long long xfs_rtrmapbt_calc_size(struct xfs_mount *mp, + unsigned long long len); + +struct xfs_btree_cur *xfs_rtrmapbt_mem_cursor(struct xfs_rtgroup *rtg, + struct xfs_trans *tp, struct xfbtree *xfbtree); +int xfs_rtrmapbt_mem_init(struct xfs_mount *mp, struct xfbtree *xfbtree, + struct xfs_buftarg *btp, xfs_rgnumber_t rgno); + +xfs_rgblock_t xfs_rtrmap_highest_rgbno(struct xfs_rtgroup *rtg); + +#endif /* __XFS_RTRMAP_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 1eeecf2eb2a7..cdd16dd805d7 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -25,6 +25,11 @@ #include "xfs_da_format.h" #include "xfs_health.h" #include "xfs_ag.h" +#include "xfs_rtbitmap.h" +#include "xfs_exchrange.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* * Physical superblock buffer manipulations. Shared with libxfs in userspace. @@ -72,7 +77,8 @@ xfs_sb_validate_v5_features( } /* - * We support all XFS versions newer than a v4 superblock with V2 directories. + * We current support XFS v5 formats with known features and v4 superblocks with + * at least V2 directories. */ bool xfs_sb_good_version( @@ -86,16 +92,16 @@ xfs_sb_good_version( if (xfs_sb_is_v5(sbp)) return xfs_sb_validate_v5_features(sbp); + /* versions prior to v4 are not supported */ + if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_4) + return false; + /* We must not have any unknown v4 feature bits set */ if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) || ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) && (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS))) return false; - /* versions prior to v4 are not supported */ - if (XFS_SB_VERSION_NUM(sbp) < XFS_SB_VERSION_4) - return false; - /* V4 filesystems need v2 directories and unwritten extents */ if (!(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT)) return false; @@ -136,8 +142,6 @@ xfs_sb_version_to_features( if (sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) { if (sbp->sb_features2 & XFS_SB_VERSION2_LAZYSBCOUNTBIT) features |= XFS_FEAT_LAZYSBCOUNT; - if (sbp->sb_features2 & XFS_SB_VERSION2_ATTR2BIT) - features |= XFS_FEAT_ATTR2; if (sbp->sb_features2 & XFS_SB_VERSION2_PROJID32BIT) features |= XFS_FEAT_PROJID32; if (sbp->sb_features2 & XFS_SB_VERSION2_FTYPE) @@ -149,7 +153,7 @@ xfs_sb_version_to_features( /* Always on V5 features */ features |= XFS_FEAT_ALIGN | XFS_FEAT_LOGV2 | XFS_FEAT_EXTFLG | - XFS_FEAT_LAZYSBCOUNT | XFS_FEAT_ATTR2 | XFS_FEAT_PROJID32 | + XFS_FEAT_LAZYSBCOUNT | XFS_FEAT_PROJID32 | XFS_FEAT_V3INODES | XFS_FEAT_CRC | XFS_FEAT_PQUOTINO; /* Optional V5 features */ @@ -173,6 +177,14 @@ xfs_sb_version_to_features( features |= XFS_FEAT_NEEDSREPAIR; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NREXT64) features |= XFS_FEAT_NREXT64; + if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE) + features |= XFS_FEAT_EXCHANGE_RANGE; + if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_PARENT) + features |= XFS_FEAT_PARENT; + if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) + features |= XFS_FEAT_METADIR; + if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) + features |= XFS_FEAT_ZONED; return features; } @@ -225,6 +237,73 @@ xfs_validate_sb_read( return 0; } +/* Return the number of extents covered by a single rt bitmap file */ +static xfs_rtbxlen_t +xfs_extents_per_rbm( + struct xfs_sb *sbp) +{ + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) + return sbp->sb_rgextents; + return sbp->sb_rextents; +} + +/* + * Return the payload size of a single rt bitmap block (without the metadata + * header if any). + */ +static inline unsigned int +xfs_rtbmblock_size( + struct xfs_sb *sbp) +{ + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) + return sbp->sb_blocksize - sizeof(struct xfs_rtbuf_blkinfo); + return sbp->sb_blocksize; +} + +static uint64_t +xfs_expected_rbmblocks( + struct xfs_sb *sbp) +{ + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) + return 0; + return howmany_64(xfs_extents_per_rbm(sbp), + NBBY * xfs_rtbmblock_size(sbp)); +} + +/* Validate the realtime geometry */ +bool +xfs_validate_rt_geometry( + struct xfs_sb *sbp) +{ + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) { + if (sbp->sb_rextsize != 1) + return false; + } else { + if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE || + sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) + return false; + } + + if (sbp->sb_rblocks == 0) { + if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 || + sbp->sb_rextslog != 0 || sbp->sb_frextents != 0) + return false; + return true; + } + + if (sbp->sb_rextents == 0 || + sbp->sb_rextents != div_u64(sbp->sb_rblocks, sbp->sb_rextsize) || + sbp->sb_rextslog != xfs_compute_rextslog(sbp->sb_rextents) || + sbp->sb_rbmblocks != xfs_expected_rbmblocks(sbp)) + return false; + + return true; +} + /* Check all the superblock fields we care about when writing one out. */ STATIC int xfs_validate_sb_write( @@ -258,14 +337,8 @@ xfs_validate_sb_write( * the kernel cannot support since we checked for unsupported bits in * the read verifier, which means that memory is corrupt. */ - if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) { - xfs_warn(mp, -"Corruption detected in superblock compatible features (0x%x)!", - (sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN)); - return -EFSCORRUPTED; - } - - if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { + if (!xfs_is_readonly(mp) && + xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_alert(mp, "Corruption detected in superblock read-only compatible features (0x%x)!", (sbp->sb_features_ro_compat & @@ -299,6 +372,106 @@ xfs_validate_sb_write( return 0; } +int +xfs_compute_rgblklog( + xfs_rtxlen_t rgextents, + xfs_rgblock_t rextsize) +{ + uint64_t rgblocks = (uint64_t)rgextents * rextsize; + + return xfs_highbit64(rgblocks - 1) + 1; +} + +static int +xfs_validate_sb_rtgroups( + struct xfs_mount *mp, + struct xfs_sb *sbp) +{ + uint64_t groups; + int rgblklog; + + if (sbp->sb_rextsize == 0) { + xfs_warn(mp, +"Realtime extent size must not be zero."); + return -EINVAL; + } + + if (sbp->sb_rgextents > XFS_MAX_RGBLOCKS / sbp->sb_rextsize) { + xfs_warn(mp, +"Realtime group size (%u) must be less than %u rt extents.", + sbp->sb_rgextents, + XFS_MAX_RGBLOCKS / sbp->sb_rextsize); + return -EINVAL; + } + + if (sbp->sb_rgextents < XFS_MIN_RGEXTENTS) { + xfs_warn(mp, +"Realtime group size (%u) must be at least %u rt extents.", + sbp->sb_rgextents, XFS_MIN_RGEXTENTS); + return -EINVAL; + } + + if (sbp->sb_rgcount > XFS_MAX_RGNUMBER) { + xfs_warn(mp, +"Realtime groups (%u) must be less than %u.", + sbp->sb_rgcount, XFS_MAX_RGNUMBER); + return -EINVAL; + } + + groups = howmany_64(sbp->sb_rextents, sbp->sb_rgextents); + if (groups != sbp->sb_rgcount) { + xfs_warn(mp, +"Realtime groups (%u) do not cover the entire rt section; need (%llu) groups.", + sbp->sb_rgcount, groups); + return -EINVAL; + } + + /* Exchange-range is required for fsr to work on realtime files */ + if (!(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE)) { + xfs_warn(mp, +"Realtime groups feature requires exchange-range support."); + return -EINVAL; + } + + rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents, sbp->sb_rextsize); + if (sbp->sb_rgblklog != rgblklog) { + xfs_warn(mp, +"Realtime group log (%d) does not match expected value (%d).", + sbp->sb_rgblklog, rgblklog); + return -EINVAL; + } + + return 0; +} + +static int +xfs_validate_sb_zoned( + struct xfs_mount *mp, + struct xfs_sb *sbp) +{ + if (sbp->sb_frextents != 0) { + xfs_warn(mp, +"sb_frextents must be zero for zoned file systems."); + return -EINVAL; + } + + if (sbp->sb_rtstart && sbp->sb_rtstart < sbp->sb_dblocks) { + xfs_warn(mp, +"sb_rtstart (%lld) overlaps sb_dblocks (%lld).", + sbp->sb_rtstart, sbp->sb_dblocks); + return -EINVAL; + } + + if (sbp->sb_rtreserved && sbp->sb_rtreserved >= sbp->sb_rblocks) { + xfs_warn(mp, +"sb_rtreserved (%lld) larger than sb_rblocks (%lld).", + sbp->sb_rtreserved, sbp->sb_rblocks); + return -EINVAL; + } + + return 0; +} + /* Check the validity of the SB. */ STATIC int xfs_validate_sb_common( @@ -310,6 +483,7 @@ xfs_validate_sb_common( uint32_t agcount = 0; uint32_t rem; bool has_dalign; + int error; if (!xfs_verify_magic(bp, dsb->sb_magicnum)) { xfs_warn(mp, @@ -358,6 +532,38 @@ xfs_validate_sb_common( sbp->sb_inoalignmt, align); return -EINVAL; } + + if (sbp->sb_spino_align && + (sbp->sb_spino_align > sbp->sb_inoalignmt || + (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0)) { + xfs_warn(mp, +"Sparse inode alignment (%u) is invalid, must be integer factor of (%u).", + sbp->sb_spino_align, + sbp->sb_inoalignmt); + return -EINVAL; + } + } else if (sbp->sb_spino_align) { + xfs_warn(mp, + "Sparse inode alignment (%u) should be zero.", + sbp->sb_spino_align); + return -EINVAL; + } + + if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { + if (memchr_inv(sbp->sb_pad, 0, sizeof(sbp->sb_pad))) { + xfs_warn(mp, +"Metadir superblock padding fields must be zero."); + return -EINVAL; + } + + error = xfs_validate_sb_rtgroups(mp, sbp); + if (error) + return error; + } + if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { + error = xfs_validate_sb_zoned(mp, sbp); + if (error) + return error; } } else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD | XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) { @@ -411,7 +617,6 @@ xfs_validate_sb_common( sbp->sb_inodelog < XFS_DINODE_MIN_LOG || sbp->sb_inodelog > XFS_DINODE_MAX_LOG || sbp->sb_inodesize != (1 << sbp->sb_inodelog) || - sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE || sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) || XFS_FSB_TO_B(mp, sbp->sb_agblocks) < XFS_MIN_AG_BYTES || XFS_FSB_TO_B(mp, sbp->sb_agblocks) > XFS_MAX_AG_BYTES || @@ -429,38 +634,68 @@ xfs_validate_sb_common( return -EFSCORRUPTED; } - /* Validate the realtime geometry; stolen from xfs_repair */ - if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE || - sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) { + /* + * Logs that are too large are not supported at all. Reject them + * outright. Logs that are too small are tolerated on v4 filesystems, + * but we can only check that when mounting the log. Hence we skip + * those checks here. + */ + if (sbp->sb_logblocks > XFS_MAX_LOG_BLOCKS) { xfs_notice(mp, - "realtime extent sanity check failed"); + "Log size 0x%x blocks too large, maximum size is 0x%llx blocks", + sbp->sb_logblocks, XFS_MAX_LOG_BLOCKS); return -EFSCORRUPTED; } - if (sbp->sb_rblocks == 0) { - if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 || - sbp->sb_rextslog != 0 || sbp->sb_frextents != 0) { + if (XFS_FSB_TO_B(mp, sbp->sb_logblocks) > XFS_MAX_LOG_BYTES) { + xfs_warn(mp, + "log size 0x%llx bytes too large, maximum size is 0x%llx bytes", + XFS_FSB_TO_B(mp, sbp->sb_logblocks), + XFS_MAX_LOG_BYTES); + return -EFSCORRUPTED; + } + + /* + * Do not allow filesystems with corrupted log sector or stripe units to + * be mounted. We cannot safely size the iclogs or write to the log if + * the log stripe unit is not valid. + */ + if (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT) { + if (sbp->sb_logsectsize != (1U << sbp->sb_logsectlog)) { xfs_notice(mp, - "realtime zeroed geometry check failed"); + "log sector size in bytes/log2 (0x%x/0x%x) must match", + sbp->sb_logsectsize, 1U << sbp->sb_logsectlog); return -EFSCORRUPTED; } - } else { - uint64_t rexts; - uint64_t rbmblocks; - - rexts = div_u64(sbp->sb_rblocks, sbp->sb_rextsize); - rbmblocks = howmany_64(sbp->sb_rextents, - NBBY * sbp->sb_blocksize); + } else if (sbp->sb_logsectsize || sbp->sb_logsectlog) { + xfs_notice(mp, + "log sector size in bytes/log2 (0x%x/0x%x) are not zero", + sbp->sb_logsectsize, sbp->sb_logsectlog); + return -EFSCORRUPTED; + } - if (sbp->sb_rextents != rexts || - sbp->sb_rextslog != xfs_highbit32(sbp->sb_rextents) || - sbp->sb_rbmblocks != rbmblocks) { + if (sbp->sb_logsunit > 1) { + if (sbp->sb_logsunit % sbp->sb_blocksize) { + xfs_notice(mp, + "log stripe unit 0x%x bytes must be a multiple of block size", + sbp->sb_logsunit); + return -EFSCORRUPTED; + } + if (sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE) { xfs_notice(mp, - "realtime geometry sanity check failed"); + "log stripe unit 0x%x bytes over maximum size (0x%x bytes)", + sbp->sb_logsunit, XLOG_MAX_RECORD_BSIZE); return -EFSCORRUPTED; } } + if (!xfs_validate_rt_geometry(sbp)) { + xfs_notice(mp, + "realtime %sgeometry check failed", + sbp->sb_rblocks ? "" : "zeroed "); + return -EFSCORRUPTED; + } + /* * Either (sb_unit and !hasdalign) or (!sb_unit and hasdalign) * would imply the image is corrupted. @@ -472,7 +707,8 @@ xfs_validate_sb_common( } if (!xfs_validate_stripe_geometry(mp, XFS_FSB_TO_B(mp, sbp->sb_unit), - XFS_FSB_TO_B(mp, sbp->sb_width), 0, false)) + XFS_FSB_TO_B(mp, sbp->sb_width), 0, + xfs_buf_daddr(bp) == XFS_SB_DADDR, false)) return -EFSCORRUPTED; /* @@ -496,6 +732,14 @@ xfs_validate_sb_common( void xfs_sb_quota_from_disk(struct xfs_sb *sbp) { + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) { + sbp->sb_uquotino = NULLFSINO; + sbp->sb_gquotino = NULLFSINO; + sbp->sb_pquotino = NULLFSINO; + return; + } + /* * older mkfs doesn't initialize quota inodes to NULLFSINO. This * leads to in-core values having two different values for a quota @@ -619,6 +863,28 @@ __xfs_sb_from_disk( /* Convert on-disk flags to in-memory flags? */ if (convert_xquota) xfs_sb_quota_from_disk(to); + + if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { + to->sb_metadirino = be64_to_cpu(from->sb_metadirino); + to->sb_rgblklog = from->sb_rgblklog; + memcpy(to->sb_pad, from->sb_pad, sizeof(to->sb_pad)); + to->sb_rgcount = be32_to_cpu(from->sb_rgcount); + to->sb_rgextents = be32_to_cpu(from->sb_rgextents); + to->sb_rbmino = NULLFSINO; + to->sb_rsumino = NULLFSINO; + } else { + to->sb_metadirino = NULLFSINO; + to->sb_rgcount = 1; + to->sb_rgextents = 0; + } + + if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { + to->sb_rtstart = be64_to_cpu(from->sb_rtstart); + to->sb_rtreserved = be64_to_cpu(from->sb_rtreserved); + } else { + to->sb_rtstart = 0; + to->sb_rtreserved = 0; + } } void @@ -636,6 +902,15 @@ xfs_sb_quota_to_disk( { uint16_t qflags = from->sb_qflags; + if (xfs_sb_is_v5(from) && + (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) { + to->sb_qflags = cpu_to_be16(from->sb_qflags); + to->sb_uquotino = cpu_to_be64(0); + to->sb_gquotino = cpu_to_be64(0); + to->sb_pquotino = cpu_to_be64(0); + return; + } + to->sb_uquotino = cpu_to_be64(from->sb_uquotino); /* @@ -766,6 +1041,21 @@ xfs_sb_to_disk( to->sb_lsn = cpu_to_be64(from->sb_lsn); if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID) uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid); + + if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { + to->sb_metadirino = cpu_to_be64(from->sb_metadirino); + to->sb_rgblklog = from->sb_rgblklog; + memset(to->sb_pad, 0, sizeof(to->sb_pad)); + to->sb_rgcount = cpu_to_be32(from->sb_rgcount); + to->sb_rgextents = cpu_to_be32(from->sb_rgextents); + to->sb_rbmino = cpu_to_be64(0); + to->sb_rsumino = cpu_to_be64(0); + } + + if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { + to->sb_rtstart = cpu_to_be64(from->sb_rtstart); + to->sb_rtreserved = cpu_to_be64(from->sb_rtreserved); + } } /* @@ -895,6 +1185,49 @@ const struct xfs_buf_ops xfs_sb_quiet_buf_ops = { .verify_write = xfs_sb_write_verify, }; +/* Compute cached rt geometry from the incore sb. */ +void +xfs_sb_mount_rextsize( + struct xfs_mount *mp, + struct xfs_sb *sbp) +{ + struct xfs_groups *rgs = &mp->m_groups[XG_TYPE_RTG]; + + mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize); + mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize); + + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) { + rgs->blocks = sbp->sb_rgextents * sbp->sb_rextsize; + rgs->blklog = mp->m_sb.sb_rgblklog; + rgs->blkmask = xfs_mask32lo(mp->m_sb.sb_rgblklog); + rgs->start_fsb = mp->m_sb.sb_rtstart; + if (xfs_sb_has_incompat_feature(sbp, + XFS_SB_FEAT_INCOMPAT_ZONE_GAPS)) + rgs->has_daddr_gaps = true; + } else { + rgs->blocks = 0; + rgs->blklog = 0; + rgs->blkmask = (uint64_t)-1; + } +} + +/* Update incore sb rt extent size, then recompute the cached rt geometry. */ +void +xfs_mount_sb_set_rextsize( + struct xfs_mount *mp, + struct xfs_sb *sbp, + xfs_agblock_t rextsize) +{ + sbp->sb_rextsize = rextsize; + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) + sbp->sb_rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents, + rextsize); + + xfs_sb_mount_rextsize(mp, sbp); +} + /* * xfs_mount_common * @@ -909,36 +1242,57 @@ xfs_sb_mount_common( struct xfs_mount *mp, struct xfs_sb *sbp) { - mp->m_agfrotor = mp->m_agirotor = 0; + struct xfs_groups *ags = &mp->m_groups[XG_TYPE_AG]; + + mp->m_agfrotor = 0; + atomic_set(&mp->m_agirotor, 0); mp->m_maxagi = mp->m_sb.sb_agcount; mp->m_blkbit_log = sbp->sb_blocklog + XFS_NBBYLOG; mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT; mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT; mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1; mp->m_blockmask = sbp->sb_blocksize - 1; - mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG; - mp->m_blockwmask = mp->m_blockwsize - 1; + mp->m_blockwsize = xfs_rtbmblock_size(sbp) >> XFS_WORDLOG; + mp->m_rtx_per_rbmblock = mp->m_blockwsize << XFS_NBWORDLOG; - mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 1); - mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 0); + ags->blocks = mp->m_sb.sb_agblocks; + ags->blklog = mp->m_sb.sb_agblklog; + ags->blkmask = xfs_mask32lo(mp->m_sb.sb_agblklog); + + xfs_sb_mount_rextsize(mp, sbp); + + mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, true); + mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_alloc_mnr[0] = mp->m_alloc_mxr[0] / 2; mp->m_alloc_mnr[1] = mp->m_alloc_mxr[1] / 2; - mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 1); - mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 0); + mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, true); + mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_bmap_dmnr[0] = mp->m_bmap_dmxr[0] / 2; mp->m_bmap_dmnr[1] = mp->m_bmap_dmxr[1] / 2; - mp->m_rmap_mxr[0] = xfs_rmapbt_maxrecs(sbp->sb_blocksize, 1); - mp->m_rmap_mxr[1] = xfs_rmapbt_maxrecs(sbp->sb_blocksize, 0); + mp->m_rmap_mxr[0] = xfs_rmapbt_maxrecs(mp, sbp->sb_blocksize, true); + mp->m_rmap_mxr[1] = xfs_rmapbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_rmap_mnr[0] = mp->m_rmap_mxr[0] / 2; mp->m_rmap_mnr[1] = mp->m_rmap_mxr[1] / 2; - mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(sbp->sb_blocksize, true); - mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(sbp->sb_blocksize, false); + mp->m_rtrmap_mxr[0] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, true); + mp->m_rtrmap_mxr[1] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, false); + mp->m_rtrmap_mnr[0] = mp->m_rtrmap_mxr[0] / 2; + mp->m_rtrmap_mnr[1] = mp->m_rtrmap_mxr[1] / 2; + + mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, true); + mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_refc_mnr[0] = mp->m_refc_mxr[0] / 2; mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2; + mp->m_rtrefc_mxr[0] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, + true); + mp->m_rtrefc_mxr[1] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, + false); + mp->m_rtrefc_mnr[0] = mp->m_rtrefc_mxr[0] / 2; + mp->m_rtrefc_mnr[1] = mp->m_rtrefc_mxr[1] / 2; + mp->m_bsize = XFS_FSB_TO_BB(mp, 1); mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); mp->m_ag_max_usable = xfs_alloc_ag_max_usable(mp); @@ -964,18 +1318,24 @@ xfs_log_sb( * reservations that have been taken out percpu counters. If we have an * unclean shutdown, this will be corrected by log recovery rebuilding * the counters from the AGF block counts. - * - * Do not update sb_frextents here because it is not part of the lazy - * sb counters, despite having a percpu counter. It is always kept - * consistent with the ondisk rtbitmap by xfs_trans_apply_sb_deltas() - * and hence we don't need have to update it here. */ if (xfs_has_lazysbcount(mp)) { - mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount); + mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount); mp->m_sb.sb_ifree = min_t(uint64_t, - percpu_counter_sum(&mp->m_ifree), + percpu_counter_sum_positive(&mp->m_ifree), mp->m_sb.sb_icount); - mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks); + mp->m_sb.sb_fdblocks = xfs_sum_freecounter(mp, XC_FREE_BLOCKS); + } + + /* + * sb_frextents was added to the lazy sb counters when the rt groups + * feature was introduced. This counter can go negative due to the way + * we handle nearly-lockless reservations, so we must use the _positive + * variant here to avoid writing out nonsense frextents. + */ + if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) { + mp->m_sb.sb_frextents = + xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS); } xfs_sb_to_disk(bp->b_addr, &mp->m_sb); @@ -1027,18 +1387,17 @@ int xfs_update_secondary_sbs( struct xfs_mount *mp) { - struct xfs_perag *pag; - xfs_agnumber_t agno = 1; + struct xfs_perag *pag = NULL; int saved_error = 0; int error = 0; LIST_HEAD (buffer_list); /* update secondary superblocks. */ - for_each_perag_from(mp, agno, pag) { + while ((pag = xfs_perag_next_from(mp, pag, 1))) { struct xfs_buf *bp; error = xfs_buf_get(mp->m_ddev_targp, - XFS_AG_DADDR(mp, pag->pag_agno, XFS_SB_DADDR), + XFS_AG_DADDR(mp, pag_agno(pag), XFS_SB_DADDR), XFS_FSS_TO_BB(mp, 1), &bp); /* * If we get an error reading or writing alternate superblocks, @@ -1050,7 +1409,7 @@ xfs_update_secondary_sbs( if (error) { xfs_warn(mp, "error allocating secondary superblock for ag %d", - pag->pag_agno); + pag_agno(pag)); if (!saved_error) saved_error = error; continue; @@ -1064,26 +1423,22 @@ xfs_update_secondary_sbs( xfs_buf_relse(bp); /* don't hold too many buffers at once */ - if (agno % 16) + if (pag_agno(pag) % 16) continue; error = xfs_buf_delwri_submit(&buffer_list); if (error) { xfs_warn(mp, "write error %d updating a secondary superblock near ag %d", - error, pag->pag_agno); + error, pag_agno(pag)); if (!saved_error) saved_error = error; continue; } } error = xfs_buf_delwri_submit(&buffer_list); - if (error) { - xfs_warn(mp, - "write error %d updating a secondary superblock near ag %d", - error, agno); - } - + if (error) + xfs_warn(mp, "error %d writing secondary superblocks", error); return saved_error ? saved_error : error; } @@ -1093,10 +1448,12 @@ xfs_update_secondary_sbs( */ int xfs_sync_sb_buf( - struct xfs_mount *mp) + struct xfs_mount *mp, + bool update_rtsb) { struct xfs_trans *tp; struct xfs_buf *bp; + struct xfs_buf *rtsb_bp = NULL; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp); @@ -1106,6 +1463,11 @@ xfs_sync_sb_buf( bp = xfs_trans_getsb(tp); xfs_log_sb(tp); xfs_trans_bhold(tp, bp); + if (update_rtsb) { + rtsb_bp = xfs_log_rtsb(tp, bp); + if (rtsb_bp) + xfs_trans_bhold(tp, rtsb_bp); + } xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); if (error) @@ -1114,7 +1476,11 @@ xfs_sync_sb_buf( * write out the sb buffer to get the changes to disk */ error = xfs_bwrite(bp); + if (!error && rtsb_bp) + error = xfs_bwrite(rtsb_bp); out: + if (rtsb_bp) + xfs_buf_relse(rtsb_bp); xfs_buf_relse(bp); return error; } @@ -1156,7 +1522,8 @@ xfs_fs_geometry( geo->version = XFS_FSOP_GEOM_VERSION; geo->flags = XFS_FSOP_GEOM_FLAGS_NLINK | XFS_FSOP_GEOM_FLAGS_DIRV2 | - XFS_FSOP_GEOM_FLAGS_EXTFLG; + XFS_FSOP_GEOM_FLAGS_EXTFLG | + XFS_FSOP_GEOM_FLAGS_ATTR2; if (xfs_has_attr(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR; if (xfs_has_quota(mp)) @@ -1169,8 +1536,6 @@ xfs_fs_geometry( geo->flags |= XFS_FSOP_GEOM_FLAGS_DIRV2CI; if (xfs_has_lazysbcount(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_LAZYSB; - if (xfs_has_attr2(mp)) - geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR2; if (xfs_has_projid32(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_PROJID32; if (xfs_has_crc(mp)) @@ -1189,6 +1554,8 @@ xfs_fs_geometry( geo->flags |= XFS_FSOP_GEOM_FLAGS_BIGTIME; if (xfs_has_inobtcounts(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_INOBTCNT; + if (xfs_has_parent(mp)) + geo->flags |= XFS_FSOP_GEOM_FLAGS_PARENT; if (xfs_has_sector(mp)) { geo->flags |= XFS_FSOP_GEOM_FLAGS_SECTOR; geo->logsectsize = sbp->sb_logsectsize; @@ -1197,6 +1564,12 @@ xfs_fs_geometry( } if (xfs_has_large_extent_counts(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_NREXT64; + if (xfs_has_exchange_range(mp)) + geo->flags |= XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE; + if (xfs_has_metadir(mp)) + geo->flags |= XFS_FSOP_GEOM_FLAGS_METADIR; + if (xfs_has_zoned(mp)) + geo->flags |= XFS_FSOP_GEOM_FLAGS_ZONED; geo->rtsectsize = sbp->sb_blocksize; geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp); @@ -1212,6 +1585,15 @@ xfs_fs_geometry( return; geo->version = XFS_FSOP_GEOM_VERSION_V5; + + if (xfs_has_rtgroups(mp)) { + geo->rgcount = sbp->sb_rgcount; + geo->rgextents = sbp->sb_rgextents; + } + if (xfs_has_zoned(mp)) { + geo->rtstart = sbp->sb_rtstart; + geo->rtreserved = sbp->sb_rtreserved; + } } /* Read a secondary superblock. */ @@ -1229,6 +1611,8 @@ xfs_sb_read_secondary( error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)), XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_SB); if (error) return error; xfs_buf_set_ref(bp, XFS_SSB_REF); @@ -1260,8 +1644,10 @@ xfs_sb_get_secondary( } /* - * sunit, swidth, sectorsize(optional with 0) should be all in bytes, - * so users won't be confused by values in error messages. + * sunit, swidth, sectorsize(optional with 0) should be all in bytes, so users + * won't be confused by values in error messages. This function returns false + * if the stripe geometry is invalid and the caller is unable to repair the + * stripe configuration later in the mount process. */ bool xfs_validate_stripe_geometry( @@ -1269,20 +1655,21 @@ xfs_validate_stripe_geometry( __s64 sunit, __s64 swidth, int sectorsize, + bool may_repair, bool silent) { if (swidth > INT_MAX) { if (!silent) xfs_notice(mp, "stripe width (%lld) is too large", swidth); - return false; + goto check_override; } if (sunit > swidth) { if (!silent) xfs_notice(mp, "stripe unit (%lld) is larger than the stripe width (%lld)", sunit, swidth); - return false; + goto check_override; } if (sectorsize && (int)sunit % sectorsize) { @@ -1290,21 +1677,21 @@ xfs_validate_stripe_geometry( xfs_notice(mp, "stripe unit (%lld) must be a multiple of the sector size (%d)", sunit, sectorsize); - return false; + goto check_override; } if (sunit && !swidth) { if (!silent) xfs_notice(mp, "invalid stripe unit (%lld) and stripe width of 0", sunit); - return false; + goto check_override; } if (!sunit && swidth) { if (!silent) xfs_notice(mp, "invalid stripe width (%lld) and stripe unit of 0", swidth); - return false; + goto check_override; } if (sunit && (int)swidth % (int)sunit) { @@ -1312,7 +1699,39 @@ xfs_validate_stripe_geometry( xfs_notice(mp, "stripe width (%lld) must be a multiple of the stripe unit (%lld)", swidth, sunit); - return false; + goto check_override; } return true; + +check_override: + if (!may_repair) + return false; + /* + * During mount, mp->m_dalign will not be set unless the sunit mount + * option was set. If it was set, ignore the bad stripe alignment values + * and allow the validation and overwrite later in the mount process to + * attempt to overwrite the bad stripe alignment values with the values + * supplied by mount options. + */ + if (!mp->m_dalign) + return false; + if (!silent) + xfs_notice(mp, +"Will try to correct with specified mount options sunit (%d) and swidth (%d)", + BBTOB(mp->m_dalign), BBTOB(mp->m_swidth)); + return true; +} + +/* + * Compute the maximum level number of the realtime summary file, as defined by + * mkfs. The historic use of highbit32 on a 64-bit quantity prohibited correct + * use of rt volumes with more than 2^32 extents. + */ +uint8_t +xfs_compute_rextslog( + xfs_rtbxlen_t rtextents) +{ + if (!rtextents) + return 0; + return xfs_highbit64(rtextents); } diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h index a5e14740ec9a..34d0dd374e9b 100644 --- a/fs/xfs/libxfs/xfs_sb.h +++ b/fs/xfs/libxfs/xfs_sb.h @@ -15,8 +15,11 @@ struct xfs_perag; extern void xfs_log_sb(struct xfs_trans *tp); extern int xfs_sync_sb(struct xfs_mount *mp, bool wait); -extern int xfs_sync_sb_buf(struct xfs_mount *mp); +extern int xfs_sync_sb_buf(struct xfs_mount *mp, bool update_rtsb); extern void xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp); +void xfs_sb_mount_rextsize(struct xfs_mount *mp, struct xfs_sb *sbp); +void xfs_mount_sb_set_rextsize(struct xfs_mount *mp, + struct xfs_sb *sbp, xfs_agblock_t rextsize); extern void xfs_sb_from_disk(struct xfs_sb *to, struct xfs_dsb *from); extern void xfs_sb_to_disk(struct xfs_dsb *to, struct xfs_sb *from); extern void xfs_sb_quota_from_disk(struct xfs_sb *sbp); @@ -25,7 +28,7 @@ extern uint64_t xfs_sb_version_to_features(struct xfs_sb *sbp); extern int xfs_update_secondary_sbs(struct xfs_mount *mp); -#define XFS_FS_GEOM_MAX_STRUCT_VER (4) +#define XFS_FS_GEOM_MAX_STRUCT_VER (5) extern void xfs_fs_geometry(struct xfs_mount *mp, struct xfs_fsop_geom *geo, int struct_version); extern int xfs_sb_read_secondary(struct xfs_mount *mp, @@ -35,7 +38,12 @@ extern int xfs_sb_get_secondary(struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, struct xfs_buf **bpp); -extern bool xfs_validate_stripe_geometry(struct xfs_mount *mp, - __s64 sunit, __s64 swidth, int sectorsize, bool silent); +bool xfs_validate_stripe_geometry(struct xfs_mount *mp, + __s64 sunit, __s64 swidth, int sectorsize, bool may_repair, + bool silent); +bool xfs_validate_rt_geometry(struct xfs_sb *sbp); + +uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents); +int xfs_compute_rgblklog(xfs_rtxlen_t rgextents, xfs_rgblock_t rextsize); #endif /* __XFS_SB_H__ */ diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index c4381388c0c1..b1e0d9bc1f7d 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -38,11 +38,89 @@ extern const struct xfs_buf_ops xfs_inode_buf_ops; extern const struct xfs_buf_ops xfs_inode_buf_ra_ops; extern const struct xfs_buf_ops xfs_refcountbt_buf_ops; extern const struct xfs_buf_ops xfs_rmapbt_buf_ops; +extern const struct xfs_buf_ops xfs_rtbitmap_buf_ops; +extern const struct xfs_buf_ops xfs_rtsummary_buf_ops; extern const struct xfs_buf_ops xfs_rtbuf_ops; +extern const struct xfs_buf_ops xfs_rtsb_buf_ops; +extern const struct xfs_buf_ops xfs_rtrefcountbt_buf_ops; +extern const struct xfs_buf_ops xfs_rtrmapbt_buf_ops; extern const struct xfs_buf_ops xfs_sb_buf_ops; extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops; extern const struct xfs_buf_ops xfs_symlink_buf_ops; +/* btree ops */ +extern const struct xfs_btree_ops xfs_bnobt_ops; +extern const struct xfs_btree_ops xfs_cntbt_ops; +extern const struct xfs_btree_ops xfs_inobt_ops; +extern const struct xfs_btree_ops xfs_finobt_ops; +extern const struct xfs_btree_ops xfs_bmbt_ops; +extern const struct xfs_btree_ops xfs_refcountbt_ops; +extern const struct xfs_btree_ops xfs_rmapbt_ops; +extern const struct xfs_btree_ops xfs_rmapbt_mem_ops; +extern const struct xfs_btree_ops xfs_rtrmapbt_ops; +extern const struct xfs_btree_ops xfs_rtrmapbt_mem_ops; +extern const struct xfs_btree_ops xfs_rtrefcountbt_ops; + +static inline bool xfs_btree_is_bno(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_bnobt_ops; +} + +static inline bool xfs_btree_is_cnt(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_cntbt_ops; +} + +static inline bool xfs_btree_is_bmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_bmbt_ops; +} + +static inline bool xfs_btree_is_ino(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_inobt_ops; +} + +static inline bool xfs_btree_is_fino(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_finobt_ops; +} + +static inline bool xfs_btree_is_refcount(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_refcountbt_ops; +} + +static inline bool xfs_btree_is_rmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rmapbt_ops; +} + +#ifdef CONFIG_XFS_BTREE_IN_MEM +static inline bool xfs_btree_is_mem_rmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rmapbt_mem_ops; +} + +static inline bool xfs_btree_is_mem_rtrmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrmapbt_mem_ops; +} +#else +# define xfs_btree_is_mem_rmap(...) (false) +# define xfs_btree_is_mem_rtrmap(...) (false) +#endif + +static inline bool xfs_btree_is_rtrmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrmapbt_ops; +} + +static inline bool xfs_btree_is_rtrefcount(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrefcountbt_ops; +} + /* log size calculation functions */ int xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes); int xfs_log_calc_minimum_size(struct xfs_mount *); @@ -70,7 +148,6 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp, #define XFS_TRANS_RES_FDBLKS (1u << 6) /* Transaction contains an intent done log item */ #define XFS_TRANS_HAS_INTENT_DONE (1u << 7) - /* * LOWMODE is used by the allocator to activate the lowspace algorithm - when * free space is running low the extent allocator may choose to allocate an @@ -82,7 +159,10 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp, * for free space from AG 0. If the correct transaction reservations have been * made then this algorithm will eventually find all the space it needs. */ -#define XFS_TRANS_LOWMODE 0x100 /* allocate in low space mode */ +#define XFS_TRANS_LOWMODE (1u << 8) + +/* Transaction has locked the rtbitmap and rtsum inodes */ +#define XFS_TRANS_RTBITMAP_LOCKED (1u << 9) /* * Field values for xfs_trans_mod_sb. @@ -101,6 +181,7 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp, #define XFS_TRANS_SB_RBLOCKS 0x00000800 #define XFS_TRANS_SB_REXTENTS 0x00001000 #define XFS_TRANS_SB_REXTSLOG 0x00002000 +#define XFS_TRANS_SB_RGCOUNT 0x00004000 /* * Here we centralize the specification of XFS meta-data buffer reference count @@ -121,26 +202,6 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp, #define XFS_REFC_BTREE_REF 1 #define XFS_SSB_REF 0 -/* - * Flags for xfs_trans_ichgtime(). - */ -#define XFS_ICHGTIME_MOD 0x1 /* data fork modification timestamp */ -#define XFS_ICHGTIME_CHG 0x2 /* inode field change timestamp */ -#define XFS_ICHGTIME_CREATE 0x4 /* inode create timestamp */ - - -/* - * Symlink decoding/encoding functions - */ -int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen); -int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset, - uint32_t size, struct xfs_buf *bp); -bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset, - uint32_t size, struct xfs_buf *bp); -void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp, - struct xfs_inode *ip, struct xfs_ifork *ifp); -xfs_failaddr_t xfs_symlink_shortform_verify(struct xfs_inode *ip); - /* Computed inode geometry for the filesystem. */ struct xfs_ino_geometry { /* Maximum inode count in this filesystem. */ @@ -188,6 +249,9 @@ struct xfs_ino_geometry { /* precomputed value for di_flags2 */ uint64_t new_diflags2; + /* minimum folio order of a page cache allocation */ + unsigned int min_folio_order; + }; #endif /* __XFS_SHARED_H__ */ diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index bdc777b9ec4a..fb47a76ead18 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -16,7 +16,10 @@ #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_log.h" - +#include "xfs_symlink_remote.h" +#include "xfs_bit.h" +#include "xfs_bmap.h" +#include "xfs_health.h" /* * Each contiguous block has a header, so it is not just a simple pathlen @@ -89,8 +92,10 @@ xfs_symlink_verify( struct xfs_mount *mp = bp->b_mount; struct xfs_dsymlink_hdr *dsl = bp->b_addr; + /* no verification of non-crc buffers */ if (!xfs_has_crc(mp)) - return __this_address; + return NULL; + if (!xfs_verify_magic(bp, dsl->sl_magic)) return __this_address; if (!uuid_equal(&dsl->sl_uuid, &mp->m_sb.sb_meta_uuid)) @@ -166,7 +171,8 @@ xfs_symlink_local_to_remote( struct xfs_trans *tp, struct xfs_buf *bp, struct xfs_inode *ip, - struct xfs_ifork *ifp) + struct xfs_ifork *ifp, + void *priv) { struct xfs_mount *mp = ip->i_mount; char *buf; @@ -175,7 +181,7 @@ xfs_symlink_local_to_remote( if (!xfs_has_crc(mp)) { bp->b_ops = NULL; - memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes); + memcpy(bp->b_addr, ifp->if_data, ifp->if_bytes); xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1); return; } @@ -191,7 +197,7 @@ xfs_symlink_local_to_remote( buf = bp->b_addr; buf += xfs_symlink_hdr_set(mp, ip->i_ino, 0, ifp->if_bytes, bp); - memcpy(buf, ifp->if_u1.if_data, ifp->if_bytes); + memcpy(buf, ifp->if_data, ifp->if_bytes); xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsymlink_hdr) + ifp->if_bytes - 1); } @@ -202,15 +208,11 @@ xfs_symlink_local_to_remote( */ xfs_failaddr_t xfs_symlink_shortform_verify( - struct xfs_inode *ip) + void *sfp, + int64_t size) { - struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); - char *sfp = (char *)ifp->if_u1.if_data; - int size = ifp->if_bytes; char *endp = sfp + size; - ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); - /* * Zero length symlinks should never occur in memory as they are * never allowed to exist on disk. @@ -231,3 +233,200 @@ xfs_symlink_shortform_verify( return __this_address; return NULL; } + +/* Read a remote symlink target into the buffer. */ +int +xfs_symlink_remote_read( + struct xfs_inode *ip, + char *link) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS]; + struct xfs_buf *bp; + xfs_daddr_t d; + char *cur_chunk; + int pathlen = ip->i_disk_size; + int nmaps = XFS_SYMLINK_MAPS; + int byte_cnt; + int n; + int error = 0; + int fsblocks = 0; + int offset; + + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + fsblocks = xfs_symlink_blocks(mp, pathlen); + error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0); + if (error) + goto out; + + offset = 0; + for (n = 0; n < nmaps; n++) { + d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock); + byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount); + + error = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0, + &bp, &xfs_symlink_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK); + if (error) + return error; + byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt); + if (pathlen < byte_cnt) + byte_cnt = pathlen; + + cur_chunk = bp->b_addr; + if (xfs_has_crc(mp)) { + if (!xfs_symlink_hdr_ok(ip->i_ino, offset, + byte_cnt, bp)) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK); + error = -EFSCORRUPTED; + xfs_alert(mp, +"symlink header does not match required off/len/owner (0x%x/0x%x,0x%llx)", + offset, byte_cnt, ip->i_ino); + xfs_buf_relse(bp); + goto out; + + } + + cur_chunk += sizeof(struct xfs_dsymlink_hdr); + } + + memcpy(link + offset, cur_chunk, byte_cnt); + + pathlen -= byte_cnt; + offset += byte_cnt; + + xfs_buf_relse(bp); + } + ASSERT(pathlen == 0); + + link[ip->i_disk_size] = '\0'; + error = 0; + + out: + return error; +} + +/* Write the symlink target into the inode. */ +int +xfs_symlink_write_target( + struct xfs_trans *tp, + struct xfs_inode *ip, + xfs_ino_t owner, + const char *target_path, + int pathlen, + xfs_fsblock_t fs_blocks, + uint resblks) +{ + struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS]; + struct xfs_mount *mp = tp->t_mountp; + const char *cur_chunk; + struct xfs_buf *bp; + xfs_daddr_t d; + int byte_cnt; + int nmaps; + int offset = 0; + int n; + int error; + + /* + * If the symlink will fit into the inode, write it inline. + */ + if (pathlen <= xfs_inode_data_fork_size(ip)) { + xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen); + + ip->i_disk_size = pathlen; + ip->i_df.if_format = XFS_DINODE_FMT_LOCAL; + xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE); + return 0; + } + + nmaps = XFS_SYMLINK_MAPS; + error = xfs_bmapi_write(tp, ip, 0, fs_blocks, XFS_BMAPI_METADATA, + resblks, mval, &nmaps); + if (error) + return error; + + ip->i_disk_size = pathlen; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + + cur_chunk = target_path; + offset = 0; + for (n = 0; n < nmaps; n++) { + char *buf; + + d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock); + byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount); + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, + BTOBB(byte_cnt), 0, &bp); + if (error) + return error; + bp->b_ops = &xfs_symlink_buf_ops; + + byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt); + byte_cnt = min(byte_cnt, pathlen); + + buf = bp->b_addr; + buf += xfs_symlink_hdr_set(mp, owner, offset, byte_cnt, bp); + + memcpy(buf, cur_chunk, byte_cnt); + + cur_chunk += byte_cnt; + pathlen -= byte_cnt; + offset += byte_cnt; + + xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF); + xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) - + (char *)bp->b_addr); + } + ASSERT(pathlen == 0); + return 0; +} + +/* Remove all the blocks from a symlink and invalidate buffers. */ +int +xfs_symlink_remote_truncate( + struct xfs_trans *tp, + struct xfs_inode *ip) +{ + struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS]; + struct xfs_mount *mp = tp->t_mountp; + struct xfs_buf *bp; + int nmaps = XFS_SYMLINK_MAPS; + int done = 0; + int i; + int error; + + /* Read mappings and invalidate buffers. */ + error = xfs_bmapi_read(ip, 0, XFS_MAX_FILEOFF, mval, &nmaps, 0); + if (error) + return error; + + for (i = 0; i < nmaps; i++) { + if (!xfs_bmap_is_real_extent(&mval[i])) + break; + + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, + XFS_FSB_TO_DADDR(mp, mval[i].br_startblock), + XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0, + &bp); + if (error) + return error; + + xfs_trans_binval(tp, bp); + } + + /* Unmap the remote blocks. */ + error = xfs_bunmapi(tp, ip, 0, XFS_MAX_FILEOFF, 0, nmaps, &done); + if (error) + return error; + if (!done) { + ASSERT(done); + xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK); + return -EFSCORRUPTED; + } + + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_symlink_remote.h b/fs/xfs/libxfs/xfs_symlink_remote.h new file mode 100644 index 000000000000..c1672fe1f17b --- /dev/null +++ b/fs/xfs/libxfs/xfs_symlink_remote.h @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2000-2005 Silicon Graphics, Inc. + * Copyright (c) 2013 Red Hat, Inc. + * All Rights Reserved. + */ +#ifndef __XFS_SYMLINK_REMOTE_H +#define __XFS_SYMLINK_REMOTE_H + +/* + * Symlink decoding/encoding functions + */ +int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen); +int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset, + uint32_t size, struct xfs_buf *bp); +bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset, + uint32_t size, struct xfs_buf *bp); +void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp, + struct xfs_inode *ip, struct xfs_ifork *ifp, + void *priv); +xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size); +int xfs_symlink_remote_read(struct xfs_inode *ip, char *link); +int xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip, + xfs_ino_t owner, const char *target_path, int pathlen, + xfs_fsblock_t fs_blocks, uint resblks); +int xfs_symlink_remote_truncate(struct xfs_trans *tp, struct xfs_inode *ip); + +#endif /* __XFS_SYMLINK_REMOTE_H */ diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index 8b5547073379..c962ad64b0c1 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -31,7 +31,7 @@ xfs_trans_ijoin( { struct xfs_inode_log_item *iip; - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); if (ip->i_itemp == NULL) xfs_inode_item_init(ip, ip->i_mount); iip = ip->i_itemp; @@ -40,9 +40,8 @@ xfs_trans_ijoin( iip->ili_lock_flags = lock_flags; ASSERT(!xfs_iflags_test(ip, XFS_ISTALE)); - /* - * Get a log_item_desc to point at the new item. - */ + /* Reset the per-tx dirty context and add the item to the tx. */ + iip->ili_dirty_flags = 0; xfs_trans_add_item(tp, &iip->ili_item); } @@ -61,14 +60,16 @@ xfs_trans_ichgtime( struct timespec64 tv; ASSERT(tp); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); - tv = current_time(inode); + /* If the mtime changes, then ctime must also change */ + ASSERT(flags & XFS_ICHGTIME_CHG); + tv = inode_set_ctime_current(inode); if (flags & XFS_ICHGTIME_MOD) - inode->i_mtime = tv; - if (flags & XFS_ICHGTIME_CHG) - inode->i_ctime = tv; + inode_set_mtime_to_ts(inode, tv); + if (flags & XFS_ICHGTIME_ACCESS) + inode_set_atime_to_ts(inode, tv); if (flags & XFS_ICHGTIME_CREATE) ip->i_crtime = tv; } @@ -76,17 +77,10 @@ xfs_trans_ichgtime( /* * This is called to mark the fields indicated in fieldmask as needing to be * logged when the transaction is committed. The inode must already be - * associated with the given transaction. - * - * The values for fieldmask are defined in xfs_inode_item.h. We always log all - * of the core inode if any of it has changed, and we always log all of the - * inline data/extents/b-tree root if any of them has changed. - * - * Grab and pin the cluster buffer associated with this inode to avoid RMW - * cycles at inode writeback time. Avoid the need to add error handling to every - * xfs_trans_log_inode() call by shutting down on read error. This will cause - * transactions to fail and everything to error out, just like if we return a - * read error in a dirty transaction and cancel it. + * associated with the given transaction. All we do here is record where the + * inode was dirtied and mark the transaction and inode log item dirty; + * everything else is done in the ->precommit log item operation after the + * changes in the transaction have been completed. */ void xfs_trans_log_inode( @@ -96,27 +90,14 @@ xfs_trans_log_inode( { struct xfs_inode_log_item *iip = ip->i_itemp; struct inode *inode = VFS_I(ip); - uint iversion_flags = 0; ASSERT(iip); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); ASSERT(!xfs_iflags_test(ip, XFS_ISTALE)); tp->t_flags |= XFS_TRANS_DIRTY; /* - * Don't bother with i_lock for the I_DIRTY_TIME check here, as races - * don't matter - we either will need an extra transaction in 24 hours - * to log the timestamps, or will clear already cleared fields in the - * worst case. - */ - if (inode->i_state & I_DIRTY_TIME) { - spin_lock(&inode->i_lock); - inode->i_state &= ~I_DIRTY_TIME; - spin_unlock(&inode->i_lock); - } - - /* * First time we log the inode in a transaction, bump the inode change * counter if it is configured for this to occur. While we have the * inode locked exclusively for metadata modification, we can usually @@ -128,86 +109,10 @@ xfs_trans_log_inode( if (!test_and_set_bit(XFS_LI_DIRTY, &iip->ili_item.li_flags)) { if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, flags & XFS_ILOG_CORE)) - iversion_flags = XFS_ILOG_CORE; - } - - /* - * If we're updating the inode core or the timestamps and it's possible - * to upgrade this inode to bigtime format, do so now. - */ - if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) && - xfs_has_bigtime(ip->i_mount) && - !xfs_inode_has_bigtime(ip)) { - ip->i_diflags2 |= XFS_DIFLAG2_BIGTIME; - flags |= XFS_ILOG_CORE; - } - - /* - * Inode verifiers do not check that the extent size hint is an integer - * multiple of the rt extent size on a directory with both rtinherit - * and extszinherit flags set. If we're logging a directory that is - * misconfigured in this way, clear the hint. - */ - if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && - (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) && - (ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) { - ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | - XFS_DIFLAG_EXTSZINHERIT); - ip->i_extsize = 0; - flags |= XFS_ILOG_CORE; + flags |= XFS_ILOG_IVERSION; } - /* - * Record the specific change for fdatasync optimisation. This allows - * fdatasync to skip log forces for inodes that are only timestamp - * dirty. - */ - spin_lock(&iip->ili_lock); - iip->ili_fsync_fields |= flags; - - if (!iip->ili_item.li_buf) { - struct xfs_buf *bp; - int error; - - /* - * We hold the ILOCK here, so this inode is not going to be - * flushed while we are here. Further, because there is no - * buffer attached to the item, we know that there is no IO in - * progress, so nothing will clear the ili_fields while we read - * in the buffer. Hence we can safely drop the spin lock and - * read the buffer knowing that the state will not change from - * here. - */ - spin_unlock(&iip->ili_lock); - error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &bp); - if (error) { - xfs_force_shutdown(ip->i_mount, SHUTDOWN_META_IO_ERROR); - return; - } - - /* - * We need an explicit buffer reference for the log item but - * don't want the buffer to remain attached to the transaction. - * Hold the buffer but release the transaction reference once - * we've attached the inode log item to the buffer log item - * list. - */ - xfs_buf_hold(bp); - spin_lock(&iip->ili_lock); - iip->ili_item.li_buf = bp; - bp->b_flags |= _XBF_INODES; - list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); - xfs_trans_brelse(tp, bp); - } - - /* - * Always OR in the bits from the ili_last_fields field. This is to - * coordinate with the xfs_iflush() and xfs_buf_inode_iodone() routines - * in the eventual clearing of the ili_fields bits. See the big comment - * in xfs_iflush() for an explanation of this coordination mechanism. - */ - iip->ili_fields |= (flags | iip->ili_last_fields | iversion_flags); - spin_unlock(&iip->ili_lock); + iip->ili_dirty_flags |= flags; } int diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index 5b2f27cbdb80..86a111d0f2fc 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -19,6 +19,15 @@ #include "xfs_trans.h" #include "xfs_qm.h" #include "xfs_trans_space.h" +#include "xfs_rtbitmap.h" +#include "xfs_attr_item.h" +#include "xfs_log.h" +#include "xfs_defer.h" +#include "xfs_bmap_item.h" +#include "xfs_extfree_item.h" +#include "xfs_rmap_item.h" +#include "xfs_refcount_item.h" +#include "xfs_trace.h" #define _ALLOC true #define _FREE false @@ -89,6 +98,14 @@ xfs_refcountbt_block_count( return num_ops * (2 * mp->m_refc_maxlevels - 1); } +static unsigned int +xfs_rtrefcountbt_block_count( + struct xfs_mount *mp, + unsigned int num_ops) +{ + return num_ops * (2 * mp->m_rtrefc_maxlevels - 1); +} + /* * Logging inodes is really tricksy. They are logged in memory format, * which means that what we write into the log doesn't directly translate into @@ -127,7 +144,7 @@ xfs_calc_inode_res( (4 * sizeof(struct xlog_op_header) + sizeof(struct xfs_inode_log_format) + mp->m_sb.sb_inodesize + - 2 * XFS_BMBT_BLOCK_LEN(mp)); + 2 * xfs_bmbt_block_len(mp)); } /* @@ -210,18 +227,27 @@ xfs_calc_inode_chunk_res( * Per-extent log reservation for the btree changes involved in freeing or * allocating a realtime extent. We have to be able to log as many rtbitmap * blocks as needed to mark inuse XFS_BMBT_MAX_EXTLEN blocks' worth of realtime - * extents, as well as the realtime summary block. + * extents, as well as the realtime summary block (t1). Realtime rmap btree + * operations happen in a second transaction, so factor in a couple of rtrmapbt + * splits (t2). */ static unsigned int xfs_rtalloc_block_count( struct xfs_mount *mp, unsigned int num_ops) { - unsigned int blksz = XFS_FSB_TO_B(mp, 1); - unsigned int rtbmp_bytes; + unsigned int rtbmp_blocks; + xfs_rtxlen_t rtxlen; + unsigned int t1, t2 = 0; - rtbmp_bytes = (XFS_MAX_BMBT_EXTLEN / mp->m_sb.sb_rextsize) / NBBY; - return (howmany(rtbmp_bytes, blksz) + 1) * num_ops; + rtxlen = xfs_extlen_to_rtxlen(mp, XFS_MAX_BMBT_EXTLEN); + rtbmp_blocks = xfs_rtbitmap_blockcount_len(mp, rtxlen); + t1 = (rtbmp_blocks + 1) * num_ops; + + if (xfs_has_rmapbt(mp)) + t2 = num_ops * (2 * mp->m_rtrmap_maxlevels - 1); + + return max(t1, t2); } /* @@ -244,26 +270,64 @@ xfs_rtalloc_block_count( */ /* + * Finishing a data device refcount updates (t1): + * the agfs of the ags containing the blocks: nr_ops * sector size + * the refcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size + */ +inline unsigned int +xfs_calc_finish_cui_reservation( + struct xfs_mount *mp, + unsigned int nr_ops) +{ + if (!xfs_has_reflink(mp)) + return 0; + + return xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), + mp->m_sb.sb_blocksize); +} + +/* + * Realtime refcount updates (t2); + * the rt refcount inode + * the rtrefcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size + */ +inline unsigned int +xfs_calc_finish_rt_cui_reservation( + struct xfs_mount *mp, + unsigned int nr_ops) +{ + if (!xfs_has_rtreflink(mp)) + return 0; + + return xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(xfs_rtrefcountbt_block_count(mp, nr_ops), + mp->m_sb.sb_blocksize); +} + +/* * Compute the log reservation required to handle the refcount update * transaction. Refcount updates are always done via deferred log items. * - * This is calculated as: + * This is calculated as the max of: * Data device refcount updates (t1): * the agfs of the ags containing the blocks: nr_ops * sector size * the refcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size + * Realtime refcount updates (t2); + * the rt refcount inode + * the rtrefcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size */ static unsigned int xfs_calc_refcountbt_reservation( struct xfs_mount *mp, unsigned int nr_ops) { - unsigned int blksz = XFS_FSB_TO_B(mp, 1); + unsigned int t1, t2; - if (!xfs_has_reflink(mp)) - return 0; + t1 = xfs_calc_finish_cui_reservation(mp, nr_ops); + t2 = xfs_calc_finish_rt_cui_reservation(mp, nr_ops); - return xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), blksz); + return max(t1, t2); } /* @@ -334,11 +398,11 @@ xfs_calc_write_reservation( blksz); t1 += adj; t3 += adj; - return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); + return XFS_DQUOT_LOGRES + max3(t1, t2, t3); } t4 = xfs_calc_refcountbt_reservation(mp, 1); - return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3)); + return XFS_DQUOT_LOGRES + max(t4, max3(t1, t2, t3)); } unsigned int @@ -349,6 +413,96 @@ xfs_calc_write_reservation_minlogsize( } /* + * Finishing an EFI can free the blocks and bmap blocks (t2): + * the agf for each of the ags: nr * sector size + * the agfl for each of the ags: nr * sector size + * the super block to reflect the freed blocks: sector size + * worst case split in allocation btrees per extent assuming nr extents: + * nr exts * 2 trees * (2 * max depth - 1) * block size + */ +inline unsigned int +xfs_calc_finish_efi_reservation( + struct xfs_mount *mp, + unsigned int nr) +{ + return xfs_calc_buf_res((2 * nr) + 1, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_block_count(mp, nr), + mp->m_sb.sb_blocksize); +} + +/* + * Or, if it's a realtime file (t3): + * the agf for each of the ags: 2 * sector size + * the agfl for each of the ags: 2 * sector size + * the super block to reflect the freed blocks: sector size + * the realtime bitmap: + * 2 exts * ((XFS_BMBT_MAX_EXTLEN / rtextsize) / NBBY) bytes + * the realtime summary: 2 exts * 1 block + * worst case split in allocation btrees per extent assuming 2 extents: + * 2 exts * 2 trees * (2 * max depth - 1) * block size + */ +inline unsigned int +xfs_calc_finish_rt_efi_reservation( + struct xfs_mount *mp, + unsigned int nr) +{ + if (!xfs_has_realtime(mp)) + return 0; + + return xfs_calc_buf_res((2 * nr) + 1, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_rtalloc_block_count(mp, nr), + mp->m_sb.sb_blocksize) + + xfs_calc_buf_res(xfs_allocfree_block_count(mp, nr), + mp->m_sb.sb_blocksize); +} + +/* + * Finishing an RUI is the same as an EFI. We can split the rmap btree twice + * on each end of the record, and that can cause the AGFL to be refilled or + * emptied out. + */ +inline unsigned int +xfs_calc_finish_rui_reservation( + struct xfs_mount *mp, + unsigned int nr) +{ + if (!xfs_has_rmapbt(mp)) + return 0; + return xfs_calc_finish_efi_reservation(mp, nr); +} + +/* + * Finishing an RUI is the same as an EFI. We can split the rmap btree twice + * on each end of the record, and that can cause the AGFL to be refilled or + * emptied out. + */ +inline unsigned int +xfs_calc_finish_rt_rui_reservation( + struct xfs_mount *mp, + unsigned int nr) +{ + if (!xfs_has_rtrmapbt(mp)) + return 0; + return xfs_calc_finish_rt_efi_reservation(mp, nr); +} + +/* + * In finishing a BUI, we can modify: + * the inode being truncated: inode size + * dquots + * the inode's bmap btree: (max depth + 1) * block size + */ +inline unsigned int +xfs_calc_finish_bui_reservation( + struct xfs_mount *mp, + unsigned int nr) +{ + return xfs_calc_inode_res(mp, 1) + XFS_DQUOT_LOGRES + + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, + mp->m_sb.sb_blocksize); +} + +/* * In truncating a file we free up to two extents at once. We can modify (t1): * the inode being truncated: inode size * the inode's bmap btree: (max depth + 1) * block size @@ -380,16 +534,8 @@ xfs_calc_itruncate_reservation( t1 = xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, blksz); - t2 = xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_block_count(mp, 4), blksz); - - if (xfs_has_realtime(mp)) { - t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_rtalloc_block_count(mp, 2), blksz) + - xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2), blksz); - } else { - t3 = 0; - } + t2 = xfs_calc_finish_efi_reservation(mp, 4); + t3 = xfs_calc_finish_rt_efi_reservation(mp, 2); /* * In the early days of reflink, we included enough reservation to log @@ -406,11 +552,11 @@ xfs_calc_itruncate_reservation( xfs_refcountbt_block_count(mp, 4), blksz); - return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); + return XFS_DQUOT_LOGRES + max3(t1, t2, t3); } t4 = xfs_calc_refcountbt_reservation(mp, 2); - return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3)); + return XFS_DQUOT_LOGRES + max(t4, max3(t1, t2, t3)); } unsigned int @@ -420,29 +566,108 @@ xfs_calc_itruncate_reservation_minlogsize( return xfs_calc_itruncate_reservation(mp, true); } +static inline unsigned int xfs_calc_pptr_link_overhead(void) +{ + return sizeof(struct xfs_attri_log_format) + + xlog_calc_iovec_len(sizeof(struct xfs_parent_rec)) + + xlog_calc_iovec_len(MAXNAMELEN - 1); +} +static inline unsigned int xfs_calc_pptr_unlink_overhead(void) +{ + return sizeof(struct xfs_attri_log_format) + + xlog_calc_iovec_len(sizeof(struct xfs_parent_rec)) + + xlog_calc_iovec_len(MAXNAMELEN - 1); +} +static inline unsigned int xfs_calc_pptr_replace_overhead(void) +{ + return sizeof(struct xfs_attri_log_format) + + xlog_calc_iovec_len(sizeof(struct xfs_parent_rec)) + + xlog_calc_iovec_len(MAXNAMELEN - 1) + + xlog_calc_iovec_len(sizeof(struct xfs_parent_rec)) + + xlog_calc_iovec_len(MAXNAMELEN - 1); +} + /* * In renaming a files we can modify: * the five inodes involved: 5 * inode size * the two directory btrees: 2 * (max depth + v2) * dir block size * the two directory bmap btrees: 2 * max depth * block size * And the bmap_finish transaction can free dir and bmap blocks (two sets - * of bmap blocks) giving: + * of bmap blocks) giving (t2): * the agf for the ags in which the blocks live: 3 * sector size * the agfl for the ags in which the blocks live: 3 * sector size * the superblock for the free block count: sector size * the allocation btrees: 3 exts * 2 trees * (2 * max depth - 1) * block size + * If parent pointers are enabled (t3), then each transaction in the chain + * must be capable of setting or removing the extended attribute + * containing the parent information. It must also be able to handle + * the three xattr intent items that track the progress of the parent + * pointer update. */ STATIC uint xfs_calc_rename_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 5) + - xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp), - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_block_count(mp, 3), - XFS_FSB_TO_B(mp, 1)))); + unsigned int overhead = XFS_DQUOT_LOGRES; + struct xfs_trans_resv *resp = M_RES(mp); + unsigned int t1, t2, t3 = 0; + + t1 = xfs_calc_inode_res(mp, 5) + + xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp), + XFS_FSB_TO_B(mp, 1)); + + t2 = xfs_calc_finish_efi_reservation(mp, 3); + + if (xfs_has_parent(mp)) { + unsigned int rename_overhead, exchange_overhead; + + t3 = max(resp->tr_attrsetm.tr_logres, + resp->tr_attrrm.tr_logres); + + /* + * For a standard rename, the three xattr intent log items + * are (1) replacing the pptr for the source file; (2) + * removing the pptr on the dest file; and (3) adding a + * pptr for the whiteout file in the src dir. + * + * For an RENAME_EXCHANGE, there are two xattr intent + * items to replace the pptr for both src and dest + * files. Link counts don't change and there is no + * whiteout. + * + * In the worst case we can end up relogging all log + * intent items to allow the log tail to move ahead, so + * they become overhead added to each transaction in a + * processing chain. + */ + rename_overhead = xfs_calc_pptr_replace_overhead() + + xfs_calc_pptr_unlink_overhead() + + xfs_calc_pptr_link_overhead(); + exchange_overhead = 2 * xfs_calc_pptr_replace_overhead(); + + overhead += max(rename_overhead, exchange_overhead); + } + + return overhead + max3(t1, t2, t3); +} + +static inline unsigned int +xfs_rename_log_count( + struct xfs_mount *mp, + struct xfs_trans_resv *resp) +{ + /* One for the rename, one more for freeing blocks */ + unsigned int ret = XFS_RENAME_LOG_COUNT; + + /* + * Pre-reserve enough log reservation to handle the transaction + * rolling needed to remove or add one parent pointer. + */ + if (xfs_has_parent(mp)) + ret += max(resp->tr_attrsetm.tr_logcount, + resp->tr_attrrm.tr_logcount); + + return ret; } /* @@ -459,6 +684,23 @@ xfs_calc_iunlink_remove_reservation( 2 * M_IGEO(mp)->inode_cluster_size; } +static inline unsigned int +xfs_link_log_count( + struct xfs_mount *mp, + struct xfs_trans_resv *resp) +{ + unsigned int ret = XFS_LINK_LOG_COUNT; + + /* + * Pre-reserve enough log reservation to handle the transaction + * rolling needed to add one parent pointer. + */ + if (xfs_has_parent(mp)) + ret += resp->tr_attrsetm.tr_logcount; + + return ret; +} + /* * For creating a link to an inode: * the parent directory inode: inode size @@ -475,14 +717,21 @@ STATIC uint xfs_calc_link_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - xfs_calc_iunlink_remove_reservation(mp) + - max((xfs_calc_inode_res(mp, 2) + - xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1), - XFS_FSB_TO_B(mp, 1)))); + unsigned int overhead = XFS_DQUOT_LOGRES; + struct xfs_trans_resv *resp = M_RES(mp); + unsigned int t1, t2, t3 = 0; + + overhead += xfs_calc_iunlink_remove_reservation(mp); + t1 = xfs_calc_inode_res(mp, 2) + + xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1)); + t2 = xfs_calc_finish_efi_reservation(mp, 1); + + if (xfs_has_parent(mp)) { + t3 = resp->tr_attrsetm.tr_logres; + overhead += xfs_calc_pptr_link_overhead(); + } + + return overhead + max3(t1, t2, t3); } /* @@ -497,6 +746,23 @@ xfs_calc_iunlink_add_reservation(xfs_mount_t *mp) M_IGEO(mp)->inode_cluster_size; } +static inline unsigned int +xfs_remove_log_count( + struct xfs_mount *mp, + struct xfs_trans_resv *resp) +{ + unsigned int ret = XFS_REMOVE_LOG_COUNT; + + /* + * Pre-reserve enough log reservation to handle the transaction + * rolling needed to add one parent pointer. + */ + if (xfs_has_parent(mp)) + ret += resp->tr_attrrm.tr_logcount; + + return ret; +} + /* * For removing a directory entry we can modify: * the parent directory inode: inode size @@ -513,14 +779,22 @@ STATIC uint xfs_calc_remove_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - xfs_calc_iunlink_add_reservation(mp) + - max((xfs_calc_inode_res(mp, 2) + - xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2), - XFS_FSB_TO_B(mp, 1)))); + unsigned int overhead = XFS_DQUOT_LOGRES; + struct xfs_trans_resv *resp = M_RES(mp); + unsigned int t1, t2, t3 = 0; + + overhead += xfs_calc_iunlink_add_reservation(mp); + + t1 = xfs_calc_inode_res(mp, 2) + + xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1)); + t2 = xfs_calc_finish_efi_reservation(mp, 2); + + if (xfs_has_parent(mp)) { + t3 = resp->tr_attrrm.tr_logres; + overhead += xfs_calc_pptr_unlink_overhead(); + } + + return overhead + max3(t1, t2, t3); } /* @@ -569,24 +843,69 @@ xfs_calc_icreate_resv_alloc( xfs_calc_finobt_res(mp); } +static inline unsigned int +xfs_icreate_log_count( + struct xfs_mount *mp, + struct xfs_trans_resv *resp) +{ + unsigned int ret = XFS_CREATE_LOG_COUNT; + + /* + * Pre-reserve enough log reservation to handle the transaction + * rolling needed to add one parent pointer. + */ + if (xfs_has_parent(mp)) + ret += resp->tr_attrsetm.tr_logcount; + + return ret; +} + STATIC uint -xfs_calc_icreate_reservation(xfs_mount_t *mp) +xfs_calc_icreate_reservation( + struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - max(xfs_calc_icreate_resv_alloc(mp), - xfs_calc_create_resv_modify(mp)); + struct xfs_trans_resv *resp = M_RES(mp); + unsigned int overhead = XFS_DQUOT_LOGRES; + unsigned int t1, t2, t3 = 0; + + t1 = xfs_calc_icreate_resv_alloc(mp); + t2 = xfs_calc_create_resv_modify(mp); + + if (xfs_has_parent(mp)) { + t3 = resp->tr_attrsetm.tr_logres; + overhead += xfs_calc_pptr_link_overhead(); + } + + return overhead + max3(t1, t2, t3); } STATIC uint xfs_calc_create_tmpfile_reservation( struct xfs_mount *mp) { - uint res = XFS_DQUOT_LOGRES(mp); + uint res = XFS_DQUOT_LOGRES; res += xfs_calc_icreate_resv_alloc(mp); return res + xfs_calc_iunlink_add_reservation(mp); } +static inline unsigned int +xfs_mkdir_log_count( + struct xfs_mount *mp, + struct xfs_trans_resv *resp) +{ + unsigned int ret = XFS_MKDIR_LOG_COUNT; + + /* + * Pre-reserve enough log reservation to handle the transaction + * rolling needed to add one parent pointer. + */ + if (xfs_has_parent(mp)) + ret += resp->tr_attrsetm.tr_logcount; + + return ret; +} + /* * Making a new directory is the same as creating a new file. */ @@ -597,6 +916,22 @@ xfs_calc_mkdir_reservation( return xfs_calc_icreate_reservation(mp); } +static inline unsigned int +xfs_symlink_log_count( + struct xfs_mount *mp, + struct xfs_trans_resv *resp) +{ + unsigned int ret = XFS_SYMLINK_LOG_COUNT; + + /* + * Pre-reserve enough log reservation to handle the transaction + * rolling needed to add one parent pointer. + */ + if (xfs_has_parent(mp)) + ret += resp->tr_attrsetm.tr_logcount; + + return ret; +} /* * Making a new symplink is the same as creating a new file, but @@ -630,7 +965,7 @@ STATIC uint xfs_calc_ifree_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + xfs_calc_iunlink_remove_reservation(mp) + @@ -647,7 +982,7 @@ STATIC uint xfs_calc_ichange_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(1, mp->m_sb.sb_sectsize); @@ -719,7 +1054,7 @@ xfs_calc_growrtfree_reservation( return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) + xfs_calc_inode_res(mp, 2) + xfs_calc_buf_res(1, mp->m_sb.sb_blocksize) + - xfs_calc_buf_res(1, mp->m_rsumsize); + xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, mp->m_rsumblocks)); } /* @@ -756,7 +1091,7 @@ STATIC uint xfs_calc_addafork_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) + xfs_calc_buf_res(1, mp->m_dir_geo->blksize) + @@ -804,7 +1139,7 @@ STATIC uint xfs_calc_attrsetm_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) + xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1)); @@ -844,7 +1179,7 @@ STATIC uint xfs_calc_attrrm_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + max((xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1)) + @@ -909,54 +1244,85 @@ xfs_calc_sb_reservation( return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize); } -void -xfs_trans_resv_calc( +/* + * Namespace reservations. + * + * These get tricky when parent pointers are enabled as we have attribute + * modifications occurring from within these transactions. Rather than confuse + * each of these reservation calculations with the conditional attribute + * reservations, add them here in a clear and concise manner. This requires that + * the attribute reservations have already been calculated. + * + * Note that we only include the static attribute reservation here; the runtime + * reservation will have to be modified by the size of the attributes being + * added/removed/modified. See the comments on the attribute reservation + * calculations for more details. + */ +STATIC void +xfs_calc_namespace_reservations( struct xfs_mount *mp, struct xfs_trans_resv *resp) { - int logcount_adj = 0; - - /* - * The following transactions are logged in physical format and - * require a permanent reservation on space. - */ - resp->tr_write.tr_logres = xfs_calc_write_reservation(mp, false); - resp->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT; - resp->tr_write.tr_logflags |= XFS_TRANS_PERM_LOG_RES; - - resp->tr_itruncate.tr_logres = xfs_calc_itruncate_reservation(mp, false); - resp->tr_itruncate.tr_logcount = XFS_ITRUNCATE_LOG_COUNT; - resp->tr_itruncate.tr_logflags |= XFS_TRANS_PERM_LOG_RES; + ASSERT(resp->tr_attrsetm.tr_logres > 0); resp->tr_rename.tr_logres = xfs_calc_rename_reservation(mp); - resp->tr_rename.tr_logcount = XFS_RENAME_LOG_COUNT; + resp->tr_rename.tr_logcount = xfs_rename_log_count(mp, resp); resp->tr_rename.tr_logflags |= XFS_TRANS_PERM_LOG_RES; resp->tr_link.tr_logres = xfs_calc_link_reservation(mp); - resp->tr_link.tr_logcount = XFS_LINK_LOG_COUNT; + resp->tr_link.tr_logcount = xfs_link_log_count(mp, resp); resp->tr_link.tr_logflags |= XFS_TRANS_PERM_LOG_RES; resp->tr_remove.tr_logres = xfs_calc_remove_reservation(mp); - resp->tr_remove.tr_logcount = XFS_REMOVE_LOG_COUNT; + resp->tr_remove.tr_logcount = xfs_remove_log_count(mp, resp); resp->tr_remove.tr_logflags |= XFS_TRANS_PERM_LOG_RES; resp->tr_symlink.tr_logres = xfs_calc_symlink_reservation(mp); - resp->tr_symlink.tr_logcount = XFS_SYMLINK_LOG_COUNT; + resp->tr_symlink.tr_logcount = xfs_symlink_log_count(mp, resp); resp->tr_symlink.tr_logflags |= XFS_TRANS_PERM_LOG_RES; resp->tr_create.tr_logres = xfs_calc_icreate_reservation(mp); - resp->tr_create.tr_logcount = XFS_CREATE_LOG_COUNT; + resp->tr_create.tr_logcount = xfs_icreate_log_count(mp, resp); resp->tr_create.tr_logflags |= XFS_TRANS_PERM_LOG_RES; + resp->tr_mkdir.tr_logres = xfs_calc_mkdir_reservation(mp); + resp->tr_mkdir.tr_logcount = xfs_mkdir_log_count(mp, resp); + resp->tr_mkdir.tr_logflags |= XFS_TRANS_PERM_LOG_RES; +} + +STATIC void +xfs_calc_default_atomic_ioend_reservation( + struct xfs_mount *mp, + struct xfs_trans_resv *resp) +{ + /* Pick a default that will scale reasonably for the log size. */ + resp->tr_atomic_ioend = resp->tr_itruncate; +} + +void +xfs_trans_resv_calc( + struct xfs_mount *mp, + struct xfs_trans_resv *resp) +{ + int logcount_adj = 0; + + /* + * The following transactions are logged in physical format and + * require a permanent reservation on space. + */ + resp->tr_write.tr_logres = xfs_calc_write_reservation(mp, false); + resp->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT; + resp->tr_write.tr_logflags |= XFS_TRANS_PERM_LOG_RES; + + resp->tr_itruncate.tr_logres = xfs_calc_itruncate_reservation(mp, false); + resp->tr_itruncate.tr_logcount = XFS_ITRUNCATE_LOG_COUNT; + resp->tr_itruncate.tr_logflags |= XFS_TRANS_PERM_LOG_RES; + resp->tr_create_tmpfile.tr_logres = xfs_calc_create_tmpfile_reservation(mp); resp->tr_create_tmpfile.tr_logcount = XFS_CREATE_TMPFILE_LOG_COUNT; resp->tr_create_tmpfile.tr_logflags |= XFS_TRANS_PERM_LOG_RES; - resp->tr_mkdir.tr_logres = xfs_calc_mkdir_reservation(mp); - resp->tr_mkdir.tr_logcount = XFS_MKDIR_LOG_COUNT; - resp->tr_mkdir.tr_logflags |= XFS_TRANS_PERM_LOG_RES; - resp->tr_ifree.tr_logres = xfs_calc_ifree_reservation(mp); resp->tr_ifree.tr_logcount = XFS_INACTIVE_LOG_COUNT; resp->tr_ifree.tr_logflags |= XFS_TRANS_PERM_LOG_RES; @@ -986,6 +1352,8 @@ xfs_trans_resv_calc( resp->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT; resp->tr_qm_dqalloc.tr_logflags |= XFS_TRANS_PERM_LOG_RES; + xfs_calc_namespace_reservations(mp, resp); + /* * The following transactions are logged in logical format with * a default log count. @@ -1025,4 +1393,167 @@ xfs_trans_resv_calc( resp->tr_itruncate.tr_logcount += logcount_adj; resp->tr_write.tr_logcount += logcount_adj; resp->tr_qm_dqalloc.tr_logcount += logcount_adj; + + /* + * Now that we've finished computing the static reservations, we can + * compute the dynamic reservation for atomic writes. + */ + xfs_calc_default_atomic_ioend_reservation(mp, resp); +} + +/* + * Return the per-extent and fixed transaction reservation sizes needed to + * complete an atomic write. + */ +STATIC unsigned int +xfs_calc_atomic_write_ioend_geometry( + struct xfs_mount *mp, + unsigned int *step_size) +{ + const unsigned int efi = xfs_efi_log_space(1); + const unsigned int efd = xfs_efd_log_space(1); + const unsigned int rui = xfs_rui_log_space(1); + const unsigned int rud = xfs_rud_log_space(); + const unsigned int cui = xfs_cui_log_space(1); + const unsigned int cud = xfs_cud_log_space(); + const unsigned int bui = xfs_bui_log_space(1); + const unsigned int bud = xfs_bud_log_space(); + + /* + * Maximum overhead to complete an atomic write ioend in software: + * remove data fork extent + remove cow fork extent + map extent into + * data fork. + * + * tx0: Creates a BUI and a CUI and that's all it needs. + * + * tx1: Roll to finish the BUI. Need space for the BUD, an RUI, and + * enough space to relog the CUI (== CUI + CUD). + * + * tx2: Roll again to finish the RUI. Need space for the RUD and space + * to relog the CUI. + * + * tx3: Roll again, need space for the CUD and possibly a new EFI. + * + * tx4: Roll again, need space for an EFD. + * + * If the extent referenced by the pair of BUI/CUI items is not the one + * being currently processed, then we need to reserve space to relog + * both items. + */ + const unsigned int tx0 = bui + cui; + const unsigned int tx1 = bud + rui + cui + cud; + const unsigned int tx2 = rud + cui + cud; + const unsigned int tx3 = cud + efi; + const unsigned int tx4 = efd; + const unsigned int relog = bui + bud + cui + cud; + + const unsigned int per_intent = max(max3(tx0, tx1, tx2), + max3(tx3, tx4, relog)); + + /* Overhead to finish one step of each intent item type */ + const unsigned int f1 = xfs_calc_finish_efi_reservation(mp, 1); + const unsigned int f2 = xfs_calc_finish_rui_reservation(mp, 1); + const unsigned int f3 = xfs_calc_finish_cui_reservation(mp, 1); + const unsigned int f4 = xfs_calc_finish_bui_reservation(mp, 1); + + /* We only finish one item per transaction in a chain */ + *step_size = max(f4, max3(f1, f2, f3)); + + return per_intent; +} + +/* + * Compute the maximum size (in fsblocks) of atomic writes that we can complete + * given the existing log reservations. + */ +xfs_extlen_t +xfs_calc_max_atomic_write_fsblocks( + struct xfs_mount *mp) +{ + const struct xfs_trans_res *resv = &M_RES(mp)->tr_atomic_ioend; + unsigned int per_intent = 0; + unsigned int step_size = 0; + unsigned int ret = 0; + + if (resv->tr_logres > 0) { + per_intent = xfs_calc_atomic_write_ioend_geometry(mp, + &step_size); + + if (resv->tr_logres >= step_size) + ret = (resv->tr_logres - step_size) / per_intent; + } + + trace_xfs_calc_max_atomic_write_fsblocks(mp, per_intent, step_size, + resv->tr_logres, ret); + + return ret; +} + +/* + * Compute the log blocks and transaction reservation needed to complete an + * atomic write of a given number of blocks. Worst case, each block requires + * separate handling. A return value of 0 means something went wrong. + */ +xfs_extlen_t +xfs_calc_atomic_write_log_geometry( + struct xfs_mount *mp, + xfs_extlen_t blockcount, + unsigned int *new_logres) +{ + struct xfs_trans_res *curr_res = &M_RES(mp)->tr_atomic_ioend; + uint old_logres = curr_res->tr_logres; + unsigned int per_intent, step_size; + unsigned int logres; + xfs_extlen_t min_logblocks; + + ASSERT(blockcount > 0); + + xfs_calc_default_atomic_ioend_reservation(mp, M_RES(mp)); + + per_intent = xfs_calc_atomic_write_ioend_geometry(mp, &step_size); + + /* Check for overflows */ + if (check_mul_overflow(blockcount, per_intent, &logres) || + check_add_overflow(logres, step_size, &logres)) + return 0; + + curr_res->tr_logres = logres; + min_logblocks = xfs_log_calc_minimum_size(mp); + curr_res->tr_logres = old_logres; + + trace_xfs_calc_max_atomic_write_log_geometry(mp, per_intent, step_size, + blockcount, min_logblocks, logres); + + *new_logres = logres; + return min_logblocks; +} + +/* + * Compute the transaction reservation needed to complete an out of place + * atomic write of a given number of blocks. + */ +int +xfs_calc_atomic_write_reservation( + struct xfs_mount *mp, + xfs_extlen_t blockcount) +{ + unsigned int new_logres; + xfs_extlen_t min_logblocks; + + /* + * If the caller doesn't ask for a specific atomic write size, then + * use the defaults. + */ + if (blockcount == 0) { + xfs_calc_default_atomic_ioend_reservation(mp, M_RES(mp)); + return 0; + } + + min_logblocks = xfs_calc_atomic_write_log_geometry(mp, blockcount, + &new_logres); + if (!min_logblocks || min_logblocks > mp->m_sb.sb_logblocks) + return -EINVAL; + + M_RES(mp)->tr_atomic_ioend.tr_logres = new_logres; + return 0; } diff --git a/fs/xfs/libxfs/xfs_trans_resv.h b/fs/xfs/libxfs/xfs_trans_resv.h index 0554b9d775d2..336279e0fc61 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.h +++ b/fs/xfs/libxfs/xfs_trans_resv.h @@ -48,6 +48,7 @@ struct xfs_trans_resv { struct xfs_trans_res tr_qm_dqalloc; /* allocate quota on disk */ struct xfs_trans_res tr_sb; /* modify superblock */ struct xfs_trans_res tr_fsyncts; /* update timestamps on fsync */ + struct xfs_trans_res tr_atomic_ioend; /* untorn write completion */ }; /* shorthand way of accessing reservation structure */ @@ -98,8 +99,32 @@ struct xfs_trans_resv { void xfs_trans_resv_calc(struct xfs_mount *mp, struct xfs_trans_resv *resp); uint xfs_allocfree_block_count(struct xfs_mount *mp, uint num_ops); +unsigned int xfs_calc_finish_bui_reservation(struct xfs_mount *mp, + unsigned int nr_ops); + +unsigned int xfs_calc_finish_efi_reservation(struct xfs_mount *mp, + unsigned int nr_ops); +unsigned int xfs_calc_finish_rt_efi_reservation(struct xfs_mount *mp, + unsigned int nr_ops); + +unsigned int xfs_calc_finish_rui_reservation(struct xfs_mount *mp, + unsigned int nr_ops); +unsigned int xfs_calc_finish_rt_rui_reservation(struct xfs_mount *mp, + unsigned int nr_ops); + +unsigned int xfs_calc_finish_cui_reservation(struct xfs_mount *mp, + unsigned int nr_ops); +unsigned int xfs_calc_finish_rt_cui_reservation(struct xfs_mount *mp, + unsigned int nr_ops); + unsigned int xfs_calc_itruncate_reservation_minlogsize(struct xfs_mount *mp); unsigned int xfs_calc_write_reservation_minlogsize(struct xfs_mount *mp); unsigned int xfs_calc_qm_dqalloc_reservation_minlogsize(struct xfs_mount *mp); +xfs_extlen_t xfs_calc_max_atomic_write_fsblocks(struct xfs_mount *mp); +xfs_extlen_t xfs_calc_atomic_write_log_geometry(struct xfs_mount *mp, + xfs_extlen_t blockcount, unsigned int *new_logres); +int xfs_calc_atomic_write_reservation(struct xfs_mount *mp, + xfs_extlen_t blockcount); + #endif /* __XFS_TRANS_RESV_H__ */ diff --git a/fs/xfs/libxfs/xfs_trans_space.c b/fs/xfs/libxfs/xfs_trans_space.c new file mode 100644 index 000000000000..b9dc3752f702 --- /dev/null +++ b/fs/xfs/libxfs/xfs_trans_space.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2000,2005 Silicon Graphics, Inc. + * All Rights Reserved. + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_da_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_da_btree.h" +#include "xfs_bmap_btree.h" +#include "xfs_trans_space.h" + +/* Calculate the disk space required to add a parent pointer. */ +unsigned int +xfs_parent_calc_space_res( + struct xfs_mount *mp, + unsigned int namelen) +{ + /* + * Parent pointers are always the first attr in an attr tree, and never + * larger than a block + */ + return XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK) + + XFS_NEXTENTADD_SPACE_RES(mp, namelen, XFS_ATTR_FORK); +} + +unsigned int +xfs_create_space_res( + struct xfs_mount *mp, + unsigned int namelen) +{ + unsigned int ret; + + ret = XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp, namelen); + if (xfs_has_parent(mp)) + ret += xfs_parent_calc_space_res(mp, namelen); + + return ret; +} + +unsigned int +xfs_mkdir_space_res( + struct xfs_mount *mp, + unsigned int namelen) +{ + return xfs_create_space_res(mp, namelen); +} + +unsigned int +xfs_link_space_res( + struct xfs_mount *mp, + unsigned int namelen) +{ + unsigned int ret; + + ret = XFS_DIRENTER_SPACE_RES(mp, namelen); + if (xfs_has_parent(mp)) + ret += xfs_parent_calc_space_res(mp, namelen); + + return ret; +} + +unsigned int +xfs_symlink_space_res( + struct xfs_mount *mp, + unsigned int namelen, + unsigned int fsblocks) +{ + unsigned int ret; + + ret = XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp, namelen) + + fsblocks; + + if (xfs_has_parent(mp)) + ret += xfs_parent_calc_space_res(mp, namelen); + + return ret; +} + +unsigned int +xfs_remove_space_res( + struct xfs_mount *mp, + unsigned int namelen) +{ + unsigned int ret = XFS_DIRREMOVE_SPACE_RES(mp); + + if (xfs_has_parent(mp)) + ret += xfs_parent_calc_space_res(mp, namelen); + + return ret; +} + +unsigned int +xfs_rename_space_res( + struct xfs_mount *mp, + unsigned int src_namelen, + bool target_exists, + unsigned int target_namelen, + bool has_whiteout) +{ + unsigned int ret; + + ret = XFS_DIRREMOVE_SPACE_RES(mp) + + XFS_DIRENTER_SPACE_RES(mp, target_namelen); + + if (xfs_has_parent(mp)) { + if (has_whiteout) + ret += xfs_parent_calc_space_res(mp, src_namelen); + ret += 2 * xfs_parent_calc_space_res(mp, target_namelen); + } + + if (target_exists) + ret += xfs_parent_calc_space_res(mp, target_namelen); + + return ret; +} diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h index 87b31c69a773..d89b570aafcc 100644 --- a/fs/xfs/libxfs/xfs_trans_space.h +++ b/fs/xfs/libxfs/xfs_trans_space.h @@ -10,6 +10,23 @@ * Components of space reservations. */ +/* Worst case number of bmaps that can be held in a block. */ +#define XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp) \ + (((mp)->m_bmap_dmxr[0]) - ((mp)->m_bmap_dmnr[0])) + +/* Worst case number of realtime rmaps that can be held in a block. */ +#define XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp) \ + (((mp)->m_rtrmap_mxr[0]) - ((mp)->m_rtrmap_mnr[0])) + +/* Adding one realtime rmap could split every level to the top of the tree. */ +#define XFS_RTRMAPADD_SPACE_RES(mp) ((mp)->m_rtrmap_maxlevels) + +/* Blocks we might need to add "b" realtime rmaps to a tree. */ +#define XFS_NRTRMAPADD_SPACE_RES(mp, b) \ + ((((b) + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp) - 1) / \ + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)) * \ + XFS_RTRMAPADD_SPACE_RES(mp)) + /* Worst case number of rmaps that can be held in a block. */ #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) \ (((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0])) @@ -76,31 +93,32 @@ /* This macro is not used - see inline code in xfs_attr_set */ #define XFS_ATTRSET_SPACE_RES(mp, v) \ (XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK) + XFS_B_TO_FSB(mp, v)) -#define XFS_CREATE_SPACE_RES(mp,nl) \ - (XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl)) #define XFS_DIOSTRAT_SPACE_RES(mp, v) \ (XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK) + (v)) #define XFS_GROWFS_SPACE_RES(mp) \ (2 * (mp)->m_alloc_maxlevels) #define XFS_GROWFSRT_SPACE_RES(mp,b) \ ((b) + XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK)) -#define XFS_LINK_SPACE_RES(mp,nl) \ - XFS_DIRENTER_SPACE_RES(mp,nl) -#define XFS_MKDIR_SPACE_RES(mp,nl) \ - (XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl)) #define XFS_QM_DQALLOC_SPACE_RES(mp) \ (XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK) + \ XFS_DQUOT_CLUSTER_SIZE_FSB) #define XFS_QM_QINOCREATE_SPACE_RES(mp) \ XFS_IALLOC_SPACE_RES(mp) -#define XFS_REMOVE_SPACE_RES(mp) \ - XFS_DIRREMOVE_SPACE_RES(mp) -#define XFS_RENAME_SPACE_RES(mp,nl) \ - (XFS_DIRREMOVE_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl)) -#define XFS_SYMLINK_SPACE_RES(mp,nl,b) \ - (XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl) + (b)) #define XFS_IFREE_SPACE_RES(mp) \ (xfs_has_finobt(mp) ? M_IGEO(mp)->inobt_maxlevels : 0) +unsigned int xfs_parent_calc_space_res(struct xfs_mount *mp, + unsigned int namelen); + +unsigned int xfs_create_space_res(struct xfs_mount *mp, unsigned int namelen); +unsigned int xfs_mkdir_space_res(struct xfs_mount *mp, unsigned int namelen); +unsigned int xfs_link_space_res(struct xfs_mount *mp, unsigned int namelen); +unsigned int xfs_symlink_space_res(struct xfs_mount *mp, unsigned int namelen, + unsigned int fsblocks); +unsigned int xfs_remove_space_res(struct xfs_mount *mp, unsigned int namelen); + +unsigned int xfs_rename_space_res(struct xfs_mount *mp, + unsigned int src_namelen, bool target_exists, + unsigned int target_namelen, bool has_whiteout); #endif /* __XFS_TRANS_SPACE_H__ */ diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c index 5c2765934732..1faf04204c5d 100644 --- a/fs/xfs/libxfs/xfs_types.c +++ b/fs/xfs/libxfs/xfs_types.c @@ -12,6 +12,8 @@ #include "xfs_bit.h" #include "xfs_mount.h" #include "xfs_ag.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" /* @@ -111,7 +113,7 @@ xfs_verify_ino( /* Is this an internal inode number? */ inline bool -xfs_internal_inum( +xfs_is_sb_inum( struct xfs_mount *mp, xfs_ino_t ino) { @@ -129,29 +131,47 @@ xfs_verify_dir_ino( struct xfs_mount *mp, xfs_ino_t ino) { - if (xfs_internal_inum(mp, ino)) + if (xfs_is_sb_inum(mp, ino)) return false; return xfs_verify_ino(mp, ino); } /* - * Verify that an realtime block number pointer doesn't point off the - * end of the realtime device. + * Verify that a realtime block number pointer neither points outside the + * allocatable areas of the rtgroup nor off the end of the realtime + * device. */ inline bool xfs_verify_rtbno( struct xfs_mount *mp, xfs_rtblock_t rtbno) { + if (xfs_has_rtgroups(mp)) { + xfs_rgnumber_t rgno = xfs_rtb_to_rgno(mp, rtbno); + xfs_rtxnum_t rtx = xfs_rtb_to_rtx(mp, rtbno); + + if (rgno >= mp->m_sb.sb_rgcount) + return false; + if (rtx >= xfs_rtgroup_extents(mp, rgno)) + return false; + if (xfs_has_rtsb(mp) && rgno == 0 && rtx == 0) + return false; + return true; + } + return rtbno < mp->m_sb.sb_rblocks; } -/* Verify that a realtime device extent is fully contained inside the volume. */ +/* + * Verify that an allocated realtime device extent neither points outside + * allocatable areas of the rtgroup, across an rtgroup boundary, nor off the + * end of the realtime device. + */ bool -xfs_verify_rtext( +xfs_verify_rtbext( struct xfs_mount *mp, xfs_rtblock_t rtbno, - xfs_rtblock_t len) + xfs_filblks_t len) { if (rtbno + len <= rtbno) return false; @@ -159,7 +179,14 @@ xfs_verify_rtext( if (!xfs_verify_rtbno(mp, rtbno)) return false; - return xfs_verify_rtbno(mp, rtbno + len - 1); + if (!xfs_verify_rtbno(mp, rtbno + len - 1)) + return false; + + if (xfs_has_rtgroups(mp) && + xfs_rtb_to_rgno(mp, rtbno) != xfs_rtb_to_rgno(mp, rtbno + len - 1)) + return false; + + return true; } /* Calculate the range of valid icount values. */ @@ -170,13 +197,12 @@ xfs_icount_range( unsigned long long *max) { unsigned long long nr_inos = 0; - struct xfs_perag *pag; - xfs_agnumber_t agno; + struct xfs_perag *pag = NULL; /* root, rtbitmap, rtsum all live in the first chunk */ *min = XFS_INODES_PER_CHUNK; - for_each_perag(mp, agno, pag) + while ((pag = xfs_perag_next(mp, pag))) nr_inos += pag->agino_max - pag->agino_min + 1; *max = nr_inos; } diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index 5ebdda7e1078..f6f4f2d4b5db 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -9,15 +9,19 @@ typedef uint32_t prid_t; /* project ID */ typedef uint32_t xfs_agblock_t; /* blockno in alloc. group */ +typedef uint32_t xfs_rgblock_t; /* blockno in realtime group */ typedef uint32_t xfs_agino_t; /* inode # within allocation grp */ typedef uint32_t xfs_extlen_t; /* extent length in blocks */ +typedef uint32_t xfs_rtxlen_t; /* file extent length in rtextents */ typedef uint32_t xfs_agnumber_t; /* allocation group number */ +typedef uint32_t xfs_rgnumber_t; /* realtime group number */ typedef uint64_t xfs_extnum_t; /* # of extents in a file */ typedef uint32_t xfs_aextnum_t; /* # extents in an attribute fork */ typedef int64_t xfs_fsize_t; /* bytes in a file */ typedef uint64_t xfs_ufsize_t; /* unsigned bytes in a file */ typedef int32_t xfs_suminfo_t; /* type of bitmap summary info */ +typedef uint32_t xfs_rtsumoff_t; /* offset of an rtsummary info word */ typedef uint32_t xfs_rtword_t; /* word type for bitmap manipulations */ typedef int64_t xfs_lsn_t; /* log sequence number */ @@ -31,6 +35,8 @@ typedef uint64_t xfs_rfsblock_t; /* blockno in filesystem (raw) */ typedef uint64_t xfs_rtblock_t; /* extent (block) in realtime area */ typedef uint64_t xfs_fileoff_t; /* block number in a file */ typedef uint64_t xfs_filblks_t; /* number of blocks in a file */ +typedef uint64_t xfs_rtxnum_t; /* rtextent number */ +typedef uint64_t xfs_rtbxlen_t; /* rtbitmap extent length in rtextents */ typedef int64_t xfs_srtblock_t; /* signed version of xfs_rtblock_t */ @@ -49,7 +55,9 @@ typedef void * xfs_failaddr_t; #define NULLFILEOFF ((xfs_fileoff_t)-1) #define NULLAGBLOCK ((xfs_agblock_t)-1) +#define NULLRGBLOCK ((xfs_rgblock_t)-1) #define NULLAGNUMBER ((xfs_agnumber_t)-1) +#define NULLRGNUMBER ((xfs_rgnumber_t)-1) #define NULLCOMMITLSN ((xfs_lsn_t)-1) @@ -76,11 +84,13 @@ typedef void * xfs_failaddr_t; /* * Inode fork identifiers. */ -#define XFS_DATA_FORK 0 -#define XFS_ATTR_FORK 1 -#define XFS_COW_FORK 2 +#define XFS_STAGING_FORK (-1) /* fake fork for staging a btree */ +#define XFS_DATA_FORK (0) +#define XFS_ATTR_FORK (1) +#define XFS_COW_FORK (2) #define XFS_WHICHFORK_STRINGS \ + { XFS_STAGING_FORK, "staging" }, \ { XFS_DATA_FORK, "data" }, \ { XFS_ATTR_FORK, "attr" }, \ { XFS_COW_FORK, "cow" } @@ -110,24 +120,6 @@ typedef enum { { XFS_LOOKUP_LEi, "le" }, \ { XFS_LOOKUP_GEi, "ge" } -/* - * This enum is used in string mapping in xfs_trace.h and scrub/trace.h; - * please keep the TRACE_DEFINE_ENUMs for it up to date. - */ -typedef enum { - XFS_BTNUM_BNOi, XFS_BTNUM_CNTi, XFS_BTNUM_RMAPi, XFS_BTNUM_BMAPi, - XFS_BTNUM_INOi, XFS_BTNUM_FINOi, XFS_BTNUM_REFCi, XFS_BTNUM_MAX -} xfs_btnum_t; - -#define XFS_BTNUM_STRINGS \ - { XFS_BTNUM_BNOi, "bnobt" }, \ - { XFS_BTNUM_CNTi, "cntbt" }, \ - { XFS_BTNUM_RMAPi, "rmapbt" }, \ - { XFS_BTNUM_BMAPi, "bmbt" }, \ - { XFS_BTNUM_INOi, "inobt" }, \ - { XFS_BTNUM_FINOi, "finobt" }, \ - { XFS_BTNUM_REFCi, "refcbt" } - struct xfs_name { const unsigned char *name; int len; @@ -145,6 +137,7 @@ typedef uint32_t xfs_dqid_t; */ #define XFS_NBBYLOG 3 /* log2(NBBY) */ #define XFS_WORDLOG 2 /* log2(sizeof(xfs_rtword_t)) */ +#define XFS_SUMINFOLOG 2 /* log2(sizeof(xfs_suminfo_t)) */ #define XFS_NBWORDLOG (XFS_NBBYLOG + XFS_WORDLOG) #define XFS_NBWORD (1 << XFS_NBWORDLOG) #define XFS_WORDMASK ((1 << XFS_WORDLOG) - 1) @@ -202,8 +195,72 @@ enum xfs_ag_resv_type { XFS_AG_RESV_AGFL, XFS_AG_RESV_METADATA, XFS_AG_RESV_RMAPBT, + + /* + * Don't increase fdblocks when freeing extent. This is a pony for + * the bnobt repair functions to re-free the free space without + * altering fdblocks. If you think you need this you're wrong. + */ + XFS_AG_RESV_IGNORE, + + /* + * This allocation activity is being done on behalf of a metadata file. + * These files maintain their own permanent space reservations and are + * required to adjust fdblocks using the xfs_metafile_resv_* helpers. + */ + XFS_AG_RESV_METAFILE, +}; + +/* Results of scanning a btree keyspace to check occupancy. */ +enum xbtree_recpacking { + /* None of the keyspace maps to records. */ + XBTREE_RECPACKING_EMPTY = 0, + + /* Some, but not all, of the keyspace maps to records. */ + XBTREE_RECPACKING_SPARSE, + + /* The entire keyspace maps to records. */ + XBTREE_RECPACKING_FULL, }; +enum xfs_group_type { + XG_TYPE_AG, + XG_TYPE_RTG, + XG_TYPE_MAX, +} __packed; + +#define XG_TYPE_STRINGS \ + { XG_TYPE_AG, "ag" }, \ + { XG_TYPE_RTG, "rtg" } + +enum xfs_free_counter { + /* + * Number of free blocks on the data device. + */ + XC_FREE_BLOCKS, + + /* + * Number of free RT extents on the RT device. + */ + XC_FREE_RTEXTENTS, + + /* + * Number of available for use RT extents. + * + * This counter only exists for zoned RT device and indicates the number + * of RT extents that can be directly used by writes. XC_FREE_RTEXTENTS + * also includes blocks that have been written previously and freed, but + * sit in a rtgroup that still needs a zone reset. + */ + XC_FREE_RTAVAILABLE, + XC_FREE_NR, +}; + +#define XFS_FREECOUNTER_STR \ + { XC_FREE_BLOCKS, "blocks" }, \ + { XC_FREE_RTEXTENTS, "rtextents" }, \ + { XC_FREE_RTAVAILABLE, "rtavailable" } + /* * Type verifier functions */ @@ -214,11 +271,11 @@ bool xfs_verify_fsbext(struct xfs_mount *mp, xfs_fsblock_t fsbno, xfs_fsblock_t len); bool xfs_verify_ino(struct xfs_mount *mp, xfs_ino_t ino); -bool xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino); +bool xfs_is_sb_inum(struct xfs_mount *mp, xfs_ino_t ino); bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino); bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno); -bool xfs_verify_rtext(struct xfs_mount *mp, xfs_rtblock_t rtbno, - xfs_rtblock_t len); +bool xfs_verify_rtbext(struct xfs_mount *mp, xfs_rtblock_t rtbno, + xfs_filblks_t len); bool xfs_verify_icount(struct xfs_mount *mp, unsigned long long icount); bool xfs_verify_dablk(struct xfs_mount *mp, xfs_fileoff_t off); void xfs_icount_range(struct xfs_mount *mp, unsigned long long *min, diff --git a/fs/xfs/libxfs/xfs_zones.c b/fs/xfs/libxfs/xfs_zones.c new file mode 100644 index 000000000000..b40f71f878b5 --- /dev/null +++ b/fs/xfs/libxfs/xfs_zones.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023-2025 Christoph Hellwig. + * Copyright (c) 2024-2025, Western Digital Corporation or its affiliates. + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_rtgroup.h" +#include "xfs_zones.h" + +static bool +xfs_zone_validate_empty( + struct blk_zone *zone, + struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (rtg_rmap(rtg)->i_used_blocks > 0) { + xfs_warn(mp, "empty zone %u has non-zero used counter (0x%x).", + rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks); + return false; + } + + *write_pointer = 0; + return true; +} + +static bool +xfs_zone_validate_wp( + struct blk_zone *zone, + struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer) +{ + struct xfs_mount *mp = rtg_mount(rtg); + xfs_rtblock_t wp_fsb = xfs_daddr_to_rtb(mp, zone->wp); + + if (rtg_rmap(rtg)->i_used_blocks > rtg->rtg_extents) { + xfs_warn(mp, "zone %u has too large used counter (0x%x).", + rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks); + return false; + } + + if (xfs_rtb_to_rgno(mp, wp_fsb) != rtg_rgno(rtg)) { + xfs_warn(mp, "zone %u write pointer (0x%llx) outside of zone.", + rtg_rgno(rtg), wp_fsb); + return false; + } + + *write_pointer = xfs_rtb_to_rgbno(mp, wp_fsb); + if (*write_pointer >= rtg->rtg_extents) { + xfs_warn(mp, "zone %u has invalid write pointer (0x%x).", + rtg_rgno(rtg), *write_pointer); + return false; + } + + return true; +} + +static bool +xfs_zone_validate_full( + struct blk_zone *zone, + struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (rtg_rmap(rtg)->i_used_blocks > rtg->rtg_extents) { + xfs_warn(mp, "zone %u has too large used counter (0x%x).", + rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks); + return false; + } + + *write_pointer = rtg->rtg_extents; + return true; +} + +static bool +xfs_zone_validate_seq( + struct blk_zone *zone, + struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + switch (zone->cond) { + case BLK_ZONE_COND_EMPTY: + return xfs_zone_validate_empty(zone, rtg, write_pointer); + case BLK_ZONE_COND_IMP_OPEN: + case BLK_ZONE_COND_EXP_OPEN: + case BLK_ZONE_COND_CLOSED: + case BLK_ZONE_COND_ACTIVE: + return xfs_zone_validate_wp(zone, rtg, write_pointer); + case BLK_ZONE_COND_FULL: + return xfs_zone_validate_full(zone, rtg, write_pointer); + case BLK_ZONE_COND_NOT_WP: + case BLK_ZONE_COND_OFFLINE: + case BLK_ZONE_COND_READONLY: + xfs_warn(mp, "zone %u has unsupported zone condition 0x%x.", + rtg_rgno(rtg), zone->cond); + return false; + default: + xfs_warn(mp, "zone %u has unknown zone condition 0x%x.", + rtg_rgno(rtg), zone->cond); + return false; + } +} + +static bool +xfs_zone_validate_conv( + struct blk_zone *zone, + struct xfs_rtgroup *rtg) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + switch (zone->cond) { + case BLK_ZONE_COND_NOT_WP: + return true; + default: + xfs_warn(mp, +"conventional zone %u has unsupported zone condition 0x%x.", + rtg_rgno(rtg), zone->cond); + return false; + } +} + +bool +xfs_zone_validate( + struct blk_zone *zone, + struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer) +{ + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG]; + uint32_t expected_size; + + /* + * Check that the zone capacity matches the rtgroup size stored in the + * superblock. Note that all zones including the last one must have a + * uniform capacity. + */ + if (XFS_BB_TO_FSB(mp, zone->capacity) != g->blocks) { + xfs_warn(mp, +"zone %u capacity (0x%llx) does not match RT group size (0x%x).", + rtg_rgno(rtg), XFS_BB_TO_FSB(mp, zone->capacity), + g->blocks); + return false; + } + + if (g->has_daddr_gaps) { + expected_size = 1 << g->blklog; + } else { + if (zone->len != zone->capacity) { + xfs_warn(mp, +"zone %u has capacity != size ((0x%llx vs 0x%llx)", + rtg_rgno(rtg), + XFS_BB_TO_FSB(mp, zone->len), + XFS_BB_TO_FSB(mp, zone->capacity)); + return false; + } + expected_size = g->blocks; + } + + if (XFS_BB_TO_FSB(mp, zone->len) != expected_size) { + xfs_warn(mp, +"zone %u length (0x%llx) does match geometry (0x%x).", + rtg_rgno(rtg), XFS_BB_TO_FSB(mp, zone->len), + expected_size); + } + + switch (zone->type) { + case BLK_ZONE_TYPE_CONVENTIONAL: + return xfs_zone_validate_conv(zone, rtg); + case BLK_ZONE_TYPE_SEQWRITE_REQ: + return xfs_zone_validate_seq(zone, rtg, write_pointer); + default: + xfs_warn(mp, "zoned %u has unsupported type 0x%x.", + rtg_rgno(rtg), zone->type); + return false; + } +} diff --git a/fs/xfs/libxfs/xfs_zones.h b/fs/xfs/libxfs/xfs_zones.h new file mode 100644 index 000000000000..5fefd132e002 --- /dev/null +++ b/fs/xfs/libxfs/xfs_zones.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LIBXFS_ZONES_H +#define _LIBXFS_ZONES_H + +struct xfs_rtgroup; + +/* + * In order to guarantee forward progress for GC we need to reserve at least + * two zones: one that will be used for moving data into and one spare zone + * making sure that we have enough space to relocate a nearly-full zone. + * To allow for slightly sloppy accounting for when we need to reserve the + * second zone, we actually reserve three as that is easier than doing fully + * accurate bookkeeping. + */ +#define XFS_GC_ZONES 3U + +/* + * In addition we need two zones for user writes, one open zone for writing + * and one to still have available blocks without resetting the open zone + * when data in the open zone has been freed. + */ +#define XFS_RESERVED_ZONES (XFS_GC_ZONES + 1) +#define XFS_MIN_ZONES (XFS_RESERVED_ZONES + 1) + +/* + * Always keep one zone out of the general open zone pool to allow for GC to + * happen while other writers are waiting for free space. + */ +#define XFS_OPEN_GC_ZONES 1U +#define XFS_MIN_OPEN_ZONES (XFS_OPEN_GC_ZONES + 1U) + +/* + * For zoned devices that do not have a limit on the number of open zones, and + * for regular devices using the zoned allocator, use the most common SMR disks + * limit (128) as the default limit on the number of open zones. + */ +#define XFS_DEFAULT_MAX_OPEN_ZONES 128 + +bool xfs_zone_validate(struct blk_zone *zone, struct xfs_rtgroup *rtg, + xfs_rgblock_t *write_pointer); + +#endif /* _LIBXFS_ZONES_H */ |